Merge remote-tracking branch 'origin/release/v3.8.50' into fix/radar-oss-cumulative-integration

Makes the ProviderErrorRule `scope` field real at the persistence layer, exclusively for agentrouter (owner decision; every other provider keeps byte-identical behavior).

checkFallbackError now surfaces `ruleScope` behind the HONORS_RULE_LOCK_SCOPE_PROVIDERS allowlist, and the agentrouter 403 path consults the rules before the generic apikey-FORBIDDEN early-return. markAccountUnavailable honors scope "connection" with a temporary connection cooldown instead of a per-model lockout — guarded so a permanent state can never be downgraded to a transient retry loop — and combo now skips the exhausted account within the same request, which also stops force-reusing the just-cooled connection via allowRateLimitedConnection.

Documented in RESILIENCE_GUIDE §7 with the honest limits (disableCooling connections keep per-model behavior; the 6h model-access cooldown is clamped by mlSettings.maxCooldownMs, 30min by default; same-request skip needs targets carrying their own connectionId).

Closes #10334

.env.example

@@ -2040,6 +2040,22 @@ APP_LOG_TO_FILE=true
 # ALIBABA_CODING_PLAN_HOST=
 # ALIBABA_CODING_PLAN_QUOTA_URL=
 
+# ── Qwen Cloud / Model Studio personal Token Plan quota ──
+# Cookie-authenticated console-gateway fetcher (issue #9603). Used by:
+# open-sse/services/qwenTokenPlanQuotaFetcher.ts. Prefer the per-connection
+# Dashboard fields (qwenCloudCookie / qwenCloudSecToken) — these env vars are
+# global fallbacks. Cookie/sec_token are SENSITIVE session credentials.
+# Getting the cookie: log in to home.qwencloud.com > Billing > Subscription,
+# press F12 > Network, reload, filter by api.json, click any request to
+# cs-data.qwencloud.com and copy the WHOLE Cookie value from Request Headers
+# (it contains login_qwencloud_ticket). Paste it on ONE line — the value may
+# contain '=' and ';'. It expires with the browser session; re-paste it when
+# the dashboard reports an expired session.
+# QWEN_CLOUD_COOKIE=
+# QWEN_CLOUD_SEC_TOKEN=
+# QWEN_TOKEN_PLAN_HOST=
+# QWEN_TOKEN_PLAN_DASHBOARD_URL=
+
 # ── Alibaba Model Studio free-tier quota sync ──
 # Console front-end path overrides for the free-tier quota fetcher. Used by:
 # open-sse/services/alibabaFreeTierQuotaFetcher.ts. When unset, the fetcher
@@ -2636,9 +2652,9 @@ QUOTA_STORE_DRIVER=sqlite
 # ═══════════════════════════════════════════════════════════════════════════════
 # Optional add-on (feature flag RADAR_ENABLED, default off — see feature flag
 # settings, not an env var) that overlays a signed, freshly-curated free-model
-# catalog on top of the release baseline. All four variables below are optional
+# catalog on top of the release baseline. The first four variables below are
-# and only needed to point the client at a self-hosted/forked feed or
+# optional overrides for a self-hosted/forked feed or supporter-key flow. The
-# supporter-key flow instead of the default OmniRoute Radar service. Used by:
+# fifth is an optional, default-free link to the owner's private operations panel. Used by:
 # src/lib/radar/sync.ts, src/lib/radar/pinnedKeys.ts, src/lib/radar/links.ts.
 
 # Base URL of the Radar feed service. Overrides the built-in default so forks
@@ -2659,6 +2675,11 @@ QUOTA_STORE_DRIVER=sqlite
 # page). No pricing/value lives in this repo — only the link.
 # RADAR_SUPPORTER_PLANS_URL=https://radar.omniroute.online/planos
 
+# Owner-only link to the private Radar operations panel. There is deliberately
+# no default: when unset or invalid, no "Radar Admin" navigation item exists.
+# Use HTTPS for a tunnel/tailnet URL, or HTTP only for an SSH loopback forward.
+# RADAR_ADMIN_URL=http://127.0.0.1:9351
+
 # ═══════════════════════════════════════════════════════════════════════════════
 # 27. RELEASE v3.8.50 ADDITIONS
 # ═══════════════════════════════════════════════════════════════════════════════

.github/pull_request_template.md

@@ -18,7 +18,7 @@ Vitest, the 60% coverage gate, and the production build all run in CI on this PR
 - [ ] `npm run lint`
 - [ ] Reconciled with the current active release base; focused checks rerun afterward
 - [ ] Production-code changes include a new or updated automated test in this PR
-- [ ] SonarQube PR analysis is green or any remaining issues are explicitly documented below
+- SonarQube is temporarily opt-in while the private project has no quota; it is not a PR gate.
 
 ## Tests Added Or Updated
 

.github/workflows/ci.yml

@@ -998,7 +998,10 @@ jobs:
     name: SonarQube
     runs-on: ubuntu-latest
     needs: test-coverage
-    if: ${{ !cancelled() && needs.test-coverage.result == 'success' }}
+    # Temporarily opt-in: the private project currently has no Sonar quota.
+    # Re-enable without another code change by setting the repository Actions
+    # variable SONARQUBE_ENABLED=true after quota/project access is restored.
+    if: ${{ vars.SONARQUBE_ENABLED == 'true' && !cancelled() && needs.test-coverage.result == 'success' }}
     env:
       SONAR_TOKEN: ${{ secrets.SONAR_TOKEN }}
       SONAR_HOST_URL: ${{ secrets.SONAR_HOST_URL }}
@@ -1397,7 +1400,7 @@ jobs:
           echo "| i18n UI Coverage | $(status '${{ needs.i18n-ui-coverage.result }}') |" >> "$GITHUB_STEP_SUMMARY"
           echo "| i18n Glossary (zh-CN, ko) | $(status '${{ needs.i18n-glossary-zhcn.result }}') |" >> "$GITHUB_STEP_SUMMARY"
           echo "| PR Test Policy | $(status '${{ needs.pr-test-policy.result }}') |" >> "$GITHUB_STEP_SUMMARY"
-          echo "| SonarQube | $(status '${{ needs.sonarqube.result }}') |" >> "$GITHUB_STEP_SUMMARY"
+          echo "| SonarQube (opt-in; disabled without SONARQUBE_ENABLED=true) | $(status '${{ needs.sonarqube.result }}') |" >> "$GITHUB_STEP_SUMMARY"
 
           echo "" >> "$GITHUB_STEP_SUMMARY"
           echo "## 🏗️ Build" >> "$GITHUB_STEP_SUMMARY"

.github/workflows/docker-publish.yml

@@ -372,7 +372,7 @@ jobs:
       - name: Upload Trivy SARIF to Security tab
         if: needs.prepare.outputs.version != 'main'
         continue-on-error: true
-        uses: github/codeql-action/upload-sarif@v4.37.6
+        uses: github/codeql-action/upload-sarif@v4.37.4
         with:
           sarif_file: trivy-results.sarif
           category: trivy-image

.github/workflows/quality.yml

@@ -60,13 +60,49 @@ jobs:
   build:
     name: Build (advisory)
     needs: changes
-    if: ${{ github.event_name != 'pull_request' || ((github.event.pull_request.draft == false || startsWith(github.head_ref, 'mergify/merge-queue/')) && needs.changes.outputs.code == 'true') }}
+    # FORK PRs ONLY. build.yml's `Fast Production Build` triggers on `push: branches: ["**"]`
-    # Dynamic runner — same fork-safe rule as ci.yml / fast-gates.
+    # and runs `build:release` — a superset of this job — so for an own-origin branch this job
-    runs-on: ${{ (vars.USE_VPS_RUNNER == 'true' && (github.event_name != 'pull_request' || github.event.pull_request.head.repo.full_name == github.repository)) && fromJSON('["self-hosted","omni-release"]') || 'ubuntu-latest' }}
+    # was building the same tree twice. A fork contributor pushes to THEIR repo, so that push
+    # never fires here, and this is the only pre-merge build signal they get. Measured
+    # 2026-08-14: 72 of the last 100 PRs into release/** came from forks, so the fork case is
+    # the majority of the traffic, not the exception — this job earns its place, it just should
+    # not duplicate build.yml for the own-origin 28%.
+    if: ${{ github.event_name != 'pull_request' || ((github.event.pull_request.draft == false || startsWith(github.head_ref, 'mergify/merge-queue/')) && needs.changes.outputs.code == 'true' && github.event.pull_request.head.repo.full_name != github.repository) }}
+    # PINNED to hosted — this was the last job in THIS workflow still on the USE_VPS_RUNNER
+    # switch (ci.yml's Build, nightly-release-green and npm-publish keep it, so the variable
+    # stays meaningful), and with USE_VPS_RUNNER=true it produced NO signal at all here.
+    # Measured 2026-08-14 over the last 25
+    # quality.yml runs: not one Build (advisory) reached a conclusion. Every sample was either
+    # queued on the self-hosted pool (2 runners, `omniroute-113-6/7`, both permanently busy — one
+    # job sat queued 2h+ and was still unclaimed) or, when it did land, killed mid-build by this
+    # workflow's own `cancel-in-progress` concurrency. 6/6 sampled "failures" are exit 143 /
+    # "The runner has received a shutdown signal" at ~3.5 min into `npm run build` — zero OOM,
+    # zero build errors. So the job burned a scarce runner that the gates actually need while
+    # reporting a permanent red on every PR.
+    #
+    # Gap 19 left USE_VPS_RUNNER governing build-like jobs on the premise that "the build needs
+    # the .113's RAM". That premise no longer holds: `Fast Production Build` (build.yml) runs
+    # `build:release` — a SUPERSET of this job's `npm run build`, plus the CLI bundle — on plain
+    # ubuntu-latest and passed 24/25 of its last runs in ~15 min. What it has and this job did
+    # not is memory PROVISIONING: a 10 GB swapfile plus a 12 GB V8 heap. That matters because
+    # --max-old-space-size only bounds V8's JS heap, never Turbopack's native (Rust) allocation
+    # (#6409) — swap is what absorbs the native peak. Both are mirrored below.
+    runs-on: ubuntu-latest
     # #7307: advisory for the first week of release-PR runs; remove
     # continue-on-error after the production-build signal is stable.
     continue-on-error: true
     steps:
+      # Mirrors build.yml: Turbopack's native peak is not bounded by --max-old-space-size, so
+      # the hosted runner needs swap headroom before the build starts.
+      - name: Expand virtual memory (10 GB swap)
+        run: |
+          sudo swapoff -a || true
+          sudo rm -f /mnt/swapfile /swapfile
+          sudo fallocate -l 10G /mnt/swapfile || sudo dd if=/dev/zero of=/mnt/swapfile bs=1M count=10240
+          sudo chmod 600 /mnt/swapfile
+          sudo mkswap /mnt/swapfile
+          sudo swapon /mnt/swapfile
+          free -h
       - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7
         with:
           persist-credentials: false
@@ -79,6 +115,10 @@ jobs:
       - run: npm run build
         env:
           OMNIROUTE_USE_TURBOPACK: "1"
+          # Same heap build.yml proves sufficient. build-next-isolated.mjs defaults to 8192 and
+          # honours OMNIROUTE_BUILD_MEMORY_MB; NODE_OPTIONS is set for parity with build.yml.
+          NODE_OPTIONS: "--max-old-space-size=12288"
+          OMNIROUTE_BUILD_MEMORY_MB: "12288"
       # No artifact upload here: the PR-to-release quality workflow has no
       # downstream package/e2e jobs that consume the Next.js build output.
 

AGENTS.md

@@ -48,20 +48,20 @@ Repository map and Reference Documentation sections below.
 
 **OmniRoute** — unified AI proxy/router. One endpoint, 339 LLM providers, auto-fallback.
 
-| Layer         | Location                | Purpose                                                                                                                                                 |
+| Layer         | Location                | Purpose                                                                                                                                                                   |
-| ------------- | ----------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| ------------- | ----------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| API Routes    | `src/app/api/v1/`       | Next.js App Router — entry points                                                                                                                       |
+| API Routes    | `src/app/api/v1/`       | Next.js App Router — entry points                                                                                                                                         |
-| Handlers      | `open-sse/handlers/`    | Request processing (chat, embeddings, etc)                                                                                                              |
+| Handlers      | `open-sse/handlers/`    | Request processing (chat, embeddings, etc)                                                                                                                                |
-| Executors     | `open-sse/executors/`   | Provider-specific HTTP dispatch                                                                                                                         |
+| Executors     | `open-sse/executors/`   | Provider-specific HTTP dispatch                                                                                                                                           |
-| Translators   | `open-sse/translator/`  | Format conversion (OpenAI↔Claude↔Gemini)                                                                                                                |
+| Translators   | `open-sse/translator/`  | Format conversion (OpenAI↔Claude↔Gemini)                                                                                                                                  |
-| Transformer   | `open-sse/transformer/` | Responses API ↔ Chat Completions                                                                                                                        |
+| Transformer   | `open-sse/transformer/` | Responses API ↔ Chat Completions                                                                                                                                          |
-| Services      | `open-sse/services/`    | Combo routing, rate limits, caching, etc                                                                                                                |
+| Services      | `open-sse/services/`    | Combo routing, rate limits, caching, etc                                                                                                                                  |
-| Database      | `src/lib/db/`           | SQLite domain modules (145 migrations)                                                                                                                  |
+| Database      | `src/lib/db/`           | SQLite domain modules (148 migrations)                                                                                                                                    |
-| Domain/Policy | `src/domain/`           | Policy engine, cost rules, fallback logic                                                                                                               |
+| Domain/Policy | `src/domain/`           | Policy engine, cost rules, fallback logic                                                                                                                                 |
-| MCP Server    | `open-sse/mcp-server/`  | 105 tools (43 base + memory/skill/agentSkill/pool/notion/obsidian/gamification/plugin modules), 3 transports (stdio / SSE / Streamable HTTP), 31 scopes |
+| MCP Server    | `open-sse/mcp-server/`  | 109 tools (44 canonical + memory/skill/GitHub/pool/gamification/plugin/Notion/Obsidian/local-corpus/RTK modules), 3 transports (stdio / SSE / Streamable HTTP), 33 scopes |
-| A2A Server    | `src/lib/a2a/`          | JSON-RPC 2.0 agent protocol                                                                                                                             |
+| A2A Server    | `src/lib/a2a/`          | JSON-RPC 2.0 agent protocol                                                                                                                                               |
-| Skills        | `src/lib/skills/`       | Extensible skill framework                                                                                                                              |
+| Skills        | `src/lib/skills/`       | Extensible skill framework                                                                                                                                                |
-| Memory        | `src/lib/memory/`       | Persistent conversational memory                                                                                                                        |
+| Memory        | `src/lib/memory/`       | Persistent conversational memory                                                                                                                                          |
 
 Monorepo: `src/` (Next.js 16 app), `open-sse/` (streaming engine workspace), `electron/` (desktop app), `tests/`, `bin/` (CLI entry point).
 
@@ -679,7 +679,7 @@ the stale-enforcement added in Fase 6A.3.
     causa-raiz de DOIS wipes (2026-08-08 e 2026-08-10: `git reset --hard` materializou o
     symlink rastreado por cima do diretório real e o git apagou todo o conteúdo ignorado sem
     aviso); (c) após qualquer escrita relevante, `git -C _tasks add -A && git -C _tasks commit
-    && git -C _tasks push` — o push frequente é o backup real; (d) repetir esta proibição
+&& git -C _tasks push` — o push frequente é o backup real; (d) repetir esta proibição
     VERBATIM no prompt de todo subagente que toque git; (e) se `_tasks` aparecer como symlink
     quebrado, NÃO commitar nada — restaurar do remote e avisar o operador. O gate
     `check:tracked-artifacts` (pre-commit + CI) bloqueia `_tasks` rastreado em qualquer forma.

README.md

@@ -210,7 +210,7 @@ curl http://localhost:20128/v1/chat/completions \
 
 </div>
 
-<img src="./docs/diagrams/promise-pillars.svg" width="100%" alt="The Promise — One endpoint. 339 providers. Never stop building — OmniRoute picks the cheapest one that works. Six pillars: Never hit limits (auto-fallback across 339 providers in milliseconds, zero downtime) · Save up to 95% tokens (RTK + Caveman stacked compression cuts 15–95%, ~89% avg on tool-heavy sessions) · $0 to start (90+ free tiers, 40+ free forever — no card needed) · Every tool works (33 coding agents through one config) · One endpoint (OpenAI ↔ Claude ↔ Gemini ↔ Responses API at /v1) · Production-grade (circuit breakers, TLS stealth, MCP 105 tools, A2A, memory, guardrails, evals — 25,000+ tests)."/>
+<img src="./docs/diagrams/promise-pillars.svg" width="100%" alt="The Promise — One endpoint. 339 providers. Never stop building — OmniRoute picks the cheapest one that works. Six pillars: Never hit limits (auto-fallback across 339 providers in milliseconds, zero downtime) · Save up to 95% tokens (RTK + Caveman stacked compression cuts 15–95%, ~89% avg on tool-heavy sessions) · $0 to start (90+ free tiers, 40+ free forever — no card needed) · Every tool works (33 coding agents through one config) · One endpoint (OpenAI ↔ Claude ↔ Gemini ↔ Responses API at /v1) · Production-grade (circuit breakers, TLS stealth, MCP 109 tools, A2A, memory, guardrails, evals — 25,000+ tests)."/>
 
 <br/>
 <br/>
@@ -461,7 +461,7 @@ All **19** strategies — mix & match per combo step:
 
 </div>
 
-<img src="./docs/diagrams/comparison-table.svg" width="100%" alt="What sets OmniRoute apart — comparison table vs 9router, OpenRouter, CLIProxyAPI and LiteLLM across 13 capabilities. OmniRoute: 339 providers, 90+ free providers built-in, 19 routing strategies, 12-engine token compression, built-in MCP server with 105 tools, A2A agent protocol, persistent memory, guardrails, cloud agents, TLS fingerprint stealth, Desktop/Termux/PWA, 43 i18n UI locales, 100% MIT self-hosted. OmniRoute is the only one with the full set; competitors show a mix of checks, partials and crosses. Verified from each project&apos;s docs."/>
+<img src="./docs/diagrams/comparison-table.svg" width="100%" alt="What sets OmniRoute apart — comparison table vs 9router, OpenRouter, CLIProxyAPI and LiteLLM across 13 capabilities. OmniRoute: 339 providers, 90+ free providers built-in, 19 routing strategies, 12-engine token compression, built-in MCP server with 109 tools, A2A agent protocol, persistent memory, guardrails, cloud agents, TLS fingerprint stealth, Desktop/Termux/PWA, 43 i18n UI locales, 100% MIT self-hosted. OmniRoute is the only one with the full set; competitors show a mix of checks, partials and crosses. Verified from each project&apos;s docs."/>
 
 <sub>📊 Full methodology &amp; per-feature detail vs 9router, OpenRouter, CLIProxyAPI &amp; LiteLLM → [`docs/comparison/OMNIROUTE_VS_ALTERNATIVES.md`](docs/comparison/OMNIROUTE_VS_ALTERNATIVES.md)</sub>
 
@@ -513,6 +513,25 @@ Pix copia-e-cola:
 
 <br/>
 
+## 📡 OmniRoute Radar
+
+The main free-tier headline remains **~1.53B tokens/month** from the documented,
+pool-deduplicated catalog above. Temporary provider signup credits can separately lift the first
+month to **~2.15B**. Radar is an optional, signed catalog overlay for people who want fresher
+free-model availability between OmniRoute releases; the community catalog and every existing free
+feature remain free.
+
+Supporters can receive the live catalog and additional provider opportunities. Its separate,
+mutable ceiling is **approximately 3B tokens/month at most**, depending on provider availability.
+That ceiling is not a guarantee: providers can change quotas, eligibility, models, or regions at
+any time.
+
+Radar is opt-in and GET-only. The OmniRoute client does not upload prompts, traffic, provider
+configuration, usage telemetry, or local announcement-dismiss state. Learn about eligibility and
+the current catalog at **[radar.omniroute.online/planos](https://radar.omniroute.online/planos)**.
+
+<br/>
+
 <div align="center">
 
 ## ✨ What's New
@@ -748,7 +767,7 @@ Expose OmniRoute over **MCP**, **A2A**, a **REST API**, **webhooks** or a **remo
 <table>
   <tr><th align="left">Interface</th><th align="left">Endpoint / command</th><th align="left">Use it for</th></tr>
   <tr><td align="left" nowrap>🧰 <b>MCP (stdio)</b></td><td align="left" nowrap><code>omniroute --mcp</code></td><td align="left">Plug into Claude Desktop, Cursor, any MCP client</td></tr>
-  <tr><td align="left" nowrap>🌊 <b>MCP (HTTP)</b></td><td align="left" nowrap><code>/api/mcp/stream</code></td><td align="left">Remote MCP — <b>105 tools</b>, 31 scopes, full audit trail</td></tr>
+  <tr><td align="left" nowrap>🌊 <b>MCP (HTTP)</b></td><td align="left" nowrap><code>/api/mcp/stream</code></td><td align="left">Remote MCP — <b>109 tools</b>, 33 scopes, full audit trail</td></tr>
   <tr><td align="left" nowrap>📡 <b>MCP (SSE)</b></td><td align="left" nowrap><code>/api/mcp/sse</code></td><td align="left">Streaming MCP transport</td></tr>
   <tr><td align="left" nowrap>🤝 <b>A2A</b></td><td align="left" nowrap><code>/.well-known/agent.json</code></td><td align="left">Agent-to-agent, <b>JSON-RPC 2.0</b> + SSE, 6 skills</td></tr>
   <tr><td align="left" nowrap>🌐 <b>REST API</b></td><td align="left" nowrap><code>/v1/*</code></td><td align="left">OpenAI-compatible — chat, embeddings, images, audio, OCR</td></tr>
@@ -1061,7 +1080,7 @@ same process on one port, so there is no separate CLI-only package today.
   <tr><td nowrap><b>Runtime</b></td><td>Node.js 22.x / 24.x LTS — <code>&gt;=22.22.2 &lt;23 || &gt;=24.0.0 &lt;27</code></td></tr>
   <tr><td nowrap><b>Language</b></td><td>TypeScript 6.0 — <b>100% TypeScript</b> across <code>src/</code> and <code>open-sse/</code> (zero <code>any</code> in core since v2.0)</td></tr>
   <tr><td nowrap><b>Framework</b></td><td>Next.js 16 + React 19 + Tailwind CSS 4</td></tr>
-  <tr><td nowrap><b>Database</b></td><td>better-sqlite3 (SQLite, WAL journaling) + LowDB (JSON legacy) — 95 domain modules, 145 migrations</td></tr>
+  <tr><td nowrap><b>Database</b></td><td>better-sqlite3 (SQLite, WAL journaling) + LowDB (JSON legacy) — 117 domain modules, 148 migrations</td></tr>
   <tr><td nowrap><b>Memory</b></td><td>SQLite FTS5 full-text + int8-quantized vector embeddings, typed decay</td></tr>
   <tr><td nowrap><b>Schemas</b></td><td>Zod 4 — MCP tool I/O validation + API contracts</td></tr>
   <tr><td nowrap><b>Protocols</b></td><td>MCP (stdio / HTTP / SSE) + A2A v0.3 (JSON-RPC 2.0 + SSE)</td></tr>
@@ -1135,7 +1154,7 @@ same process on one port, so there is no separate CLI-only package today.
   <tr><th align="left">Document</th><th align="left">Description</th></tr>
   <tr><td nowrap><b><a href="docs/reference/API_REFERENCE.md">API Reference</a></b></td><td>All endpoints with examples</td></tr>
   <tr><td nowrap><b><a href="docs/openapi.yaml">OpenAPI Spec</a></b></td><td>OpenAPI 3.0 specification</td></tr>
-  <tr><td nowrap><b><a href="open-sse/mcp-server/README.md">MCP Server</a></b></td><td>105 MCP tools, IDE configs, Python/TS/Go clients</td></tr>
+  <tr><td nowrap><b><a href="open-sse/mcp-server/README.md">MCP Server</a></b></td><td>109 MCP tools, IDE configs, Python/TS/Go clients</td></tr>
   <tr><td nowrap><b><a href="docs/frameworks/MCP-SERVER.md">MCP Server Guide</a></b></td><td>MCP installation, transports, and tool reference</td></tr>
   <tr><td nowrap><b><a href="src/lib/a2a/README.md">A2A Server</a></b></td><td>JSON-RPC 2.0 protocol, skills, streaming, task mgmt</td></tr>
   <tr><td nowrap><b><a href="docs/frameworks/A2A-SERVER.md">A2A Server Guide</a></b></td><td>A2A agent card, tasks, skills, and streaming</td></tr>

bin/cli/commands/radar.mjs

@@ -0,0 +1,76 @@
+import { apiFetch } from "../api.mjs";
+import { t } from "../i18n.mjs";
+import { emit } from "../output.mjs";
+
+const statusSchema = [
+  { key: "feed", header: "Feed" },
+  { key: "available", header: "Available" },
+  { key: "version", header: "Version" },
+  { key: "tier", header: "Tier" },
+  { key: "fetchedAt", header: "Fetched" },
+];
+
+const syncSchema = [
+  { key: "feed", header: "Feed" },
+  { key: "status", header: "Status" },
+  { key: "version", header: "Version" },
+  { key: "reason", header: "Reason" },
+];
+
+function exitCodeFor(response) {
+  return Number.isInteger(response.exitCode) ? response.exitCode : response.status === 401 ? 4 : 1;
+}
+
+export async function runRadarStatusCommand(opts = {}) {
+  const response = await apiFetch("/api/radar/status", { acceptNotOk: true });
+  if (!response.ok) return exitCodeFor(response);
+  const data = await response.json();
+  if (opts.output === "json") {
+    emit(data, opts);
+    return 0;
+  }
+  const rows = Object.entries(data.feeds ?? {}).map(([feed, value]) => ({
+    feed,
+    ...(value && typeof value === "object" ? value : { available: false }),
+  }));
+  emit(rows, opts, statusSchema);
+  return 0;
+}
+
+export async function runRadarSyncCommand(opts = {}) {
+  const response = await apiFetch("/api/radar/sync-all", {
+    method: "POST",
+    body: {},
+    acceptNotOk: true,
+  });
+  if (!response.ok) return exitCodeFor(response);
+  const data = await response.json();
+  if (opts.output === "json") {
+    emit(data, opts);
+    return 0;
+  }
+  const rows = Object.entries(data).map(([feed, value]) => ({
+    feed,
+    ...(value && typeof value === "object" ? value : { status: "error" }),
+  }));
+  emit(rows, opts, syncSchema);
+  return 0;
+}
+
+export function registerRadar(program) {
+  const radar = program.command("radar").description(t("radar.description"));
+  radar
+    .command("status")
+    .description(t("radar.status"))
+    .action(async (_opts, command) => {
+      const code = await runRadarStatusCommand(command.optsWithGlobals());
+      if (code !== 0) process.exitCode = code;
+    });
+  radar
+    .command("sync")
+    .description(t("radar.sync"))
+    .action(async (_opts, command) => {
+      const code = await runRadarSyncCommand(command.optsWithGlobals());
+      if (code !== 0) process.exitCode = code;
+    });
+}

bin/cli/commands/registry.mjs

@@ -78,6 +78,7 @@ import { registerTokens } from "./tokens.mjs";
 import { registerConfigure } from "./configure.mjs";
 import { registerApiCommands } from "../api-commands/registry.mjs";
 import { registerPlugin } from "./plugin.mjs";
+import { registerRadar } from "./radar.mjs";
 
 export function registerCommands(program) {
   registerMemory(program);
@@ -161,4 +162,5 @@ export function registerCommands(program) {
   registerConfigure(program);
   registerApiCommands(program);
   registerPlugin(program);
+  registerRadar(program);
 }

bin/cli/locales/en.json

@@ -921,6 +921,11 @@
       "model": "Filter by model"
     }
   },
+  "radar": {
+    "description": "Inspect and synchronize the local Radar catalog feeds",
+    "status": "Show local Radar settings and feed cache status",
+    "sync": "Synchronize catalog, referrals, offers, and Intel through the local server"
+  },
   "resilience": {
     "description": "Inspect and manage resilience mechanisms",
     "status": {

bin/cli/locales/pt-BR.json

@@ -918,6 +918,11 @@
       "model": "Filtrar por model"
     }
   },
+  "radar": {
+    "description": "Inspecionar e sincronizar os feeds locais do catálogo Radar",
+    "status": "Mostrar configurações locais e estado dos caches do Radar",
+    "sync": "Sincronizar catálogo, indicações, ofertas e Intel pelo servidor local"
+  },
   "resilience": {
     "description": "Inspecionar e gerenciar mecanismos de resiliência",
     "status": {

changelog.d/features/9830-radar-local-model-state.md

@@ -0,0 +1 @@
+- **feat(radar):** Persist local model display-name/enabled overrides and hide/restore tombstones, with authenticated catalog controls and feed safety precedence ([#9830](https://github.com/diegosouzapw/OmniRoute/pull/9830))

changelog.d/features/9836-radar-guided-combos.md

@@ -0,0 +1 @@
+- **feat(radar):** add curated-family combo suggestions, a guided combo page, and the read-only Radar MCP catalog tool ([#9836](https://github.com/diegosouzapw/OmniRoute/pull/9836))

changelog.d/features/9912-radar-supporter-offers.md

@@ -0,0 +1 @@
+- **feat(radar):** add a signed live offers feed and supporter offers dashboard ([#9912](https://github.com/diegosouzapw/OmniRoute/pull/9912))

changelog.d/features/9923-radar-intel.md

@@ -0,0 +1 @@
+- **feat(radar):** add signed Intel insights, supporter recognition, and local Radar CLI commands ([#9923](https://github.com/diegosouzapw/OmniRoute/pull/9923))

changelog.d/features/9926-radar-launch-news.md

@@ -0,0 +1 @@
+- **feat(radar):** add a localized public news feed and dismissible dashboard launch banner, with the Radar announcement staged inactive for a separately authorized launch ([#9926](https://github.com/diegosouzapw/OmniRoute/pull/9926))

changelog.d/fixes/build-advisory-hosted-runner.md

@@ -0,0 +1 @@
+- fix(ci): make `Build (advisory)` produce a signal again — pinned to a hosted runner with the swap/heap provisioning `Fast Production Build` proves sufficient, and scoped to fork PRs, which are the only ones `build.yml` cannot cover (72 of the last 100 PRs into `release/**`)

config/quality/e2e-timings.json

@@ -27,6 +27,7 @@
   "providers-bailian-coding-plan.spec.ts": 240,
   "providers-management.spec.ts": 324,
   "proxy-registry.smoke.spec.ts": 218,
+  "radar-guided-setup.spec.ts": 177,
   "resilience-plan-alignment.spec.ts": 382,
   "responsive.spec.ts": 21,
   "search-tools-studio.spec.ts": 133,

docs/architecture/QUALITY_GATES.md

@@ -205,10 +205,10 @@ Runs on pull requests only.
 
 Runs after `build`. Blocks merge on failure.
 
-| Suite            | Validates                                               | Blocking                                                                                                      |
+| Suite            | Validates                                                | Blocking                                                                                                      |
-| ---------------- | ------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------- |
+| ---------------- | -------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------- |
-| `test:vitest`    | MCP server (105 tools), autoCombo, cache — vitest runner | Yes                                                                                                           |
+| `test:vitest`    | MCP server (109 tools), autoCombo, cache — vitest runner | Yes                                                                                                           |
-| `test:vitest:ui` | UI component tests — vitest runner                      | **Blocking** — pre-existing failures are explicitly excluded in `vitest.config.ts`; new failures fail the job |
+| `test:vitest:ui` | UI component tests — vitest runner                       | **Blocking** — pre-existing failures are explicitly excluded in `vitest.config.ts`; new failures fail the job |
 
 ### Nightly workflows (scheduled, advisory)
 

docs/architecture/REPOSITORY_MAP.md

@@ -102,7 +102,7 @@ OmniRoute/
 | **.gitleaks.toml**                          | gitleaks secret-scan ruleset                                                             |
 | **.zizmor.yml**                             | zizmor GitHub-Actions security-lint config                                               |
 | **socket.yml**                              | Socket.dev supply-chain config                                                           |
-| **news.json**                               | In-app release-notes feed (read by `src/shared/utils/releaseNotes.ts`)                   |
+| **news.json**                               | Localized v2 announcement feed; Radar launch item ships inactive                         |
 | **flake.nix** / **flake.lock**              | Nix dev-shell definition + lock                                                          |
 | **.env**                                    | Local secrets (gitignored — generated from `.env.example`)                               |
 
@@ -182,7 +182,7 @@ src/
 | `compliance/`                            | Audit log + provider audit — see `docs/security/COMPLIANCE.md`                                                                                                                                                                                                                                                          |
 | `compression/`                           | Compression engine glue (engines live in `open-sse/services/compression/`)                                                                                                                                                                                                                                              |
 | `config/`                                | Runtime config helpers                                                                                                                                                                                                                                                                                                  |
-| `db/`                                    | 95+ domain DB modules + 144 migrations (always go through here for SQLite)                                                                                                                                                                                                                                             |
+| `db/`                                    | 95+ domain DB modules + 148 migrations (always go through here for SQLite)                                                                                                                                                                                                                                              |
 | `quota/`                                 | Quota Sharing Engine: `dimensions.ts` (types/Zod), `types.ts` (QuotaStore interface), `sqliteQuotaStore.ts`, `redisQuotaStore.ts`, `storeFactory.ts`, `fairShare.ts`, `burnRate.ts`, `planResolver.ts`, `planRegistry.ts`, `saturationSignals.ts`, `enforce.ts`, `spendRecorder.ts` — see `docs/routing/QUOTA_SHARE.md` |
 | `radar/`                                 | Radar free-model catalog client: `feedSchema.ts`, `pinnedKeys.ts`, `verify.ts`, `sync.ts`, `applyFeed.ts`, `index.ts` (`getRadarCatalog()`) — see `docs/frameworks/RADAR.md`                                                                                                                                            |
 | `display/`                               | UI formatting helpers (cost, latency, etc.)                                                                                                                                                                                                                                                                             |
@@ -196,7 +196,7 @@ src/
 | `memory/vectorStore.ts`                  | sqlite-vec v0.1.9 wrapper — KNN brute-force + hybrid RRF (FTS5 + vector, k=60). Lazy-init, degrades gracefully when sqlite-vec unavailable. (plan 21)                                                                                                                                                                   |
 | `memory/reindex.ts`                      | `runReindexBatch()` — processes memories with `needs_reindex=1` in background; called by `POST /api/memory/reindex` and lazy-backfill path. (plan 21)                                                                                                                                                                   |
 | `monitoring/`                            | Health checks, metrics emission                                                                                                                                                                                                                                                                                         |
-| `oauth/`                                 | OAuth/import flows for 22 provider modules (agy, antigravity, claude, cline, codebuddy-cn, codex, cursor, devin-desktop, ghe-copilot, github, gitlab-duo, grok-cli-oauth, grok-cli, kilocode, kimi-coding, kiro, qoder, raycast, trae, xai-oauth, zed-hosted, zed) |
+| `oauth/`                                 | OAuth/import flows for 22 provider modules (agy, antigravity, claude, cline, codebuddy-cn, codex, cursor, devin-desktop, ghe-copilot, github, gitlab-duo, grok-cli-oauth, grok-cli, kilocode, kimi-coding, kiro, qoder, raycast, trae, xai-oauth, zed-hosted, zed)                                                      |
 | `plugins/`                               | Plugin registry                                                                                                                                                                                                                                                                                                         |
 | `promptCache/`                           | Anthropic-style prompt cache breakpoints                                                                                                                                                                                                                                                                                |
 | `skills/`                                | Skills framework (built-in + marketplace + SkillsSH) — see `docs/frameworks/SKILLS.md`                                                                                                                                                                                                                                  |
@@ -209,7 +209,7 @@ src/
 | `cacheLayer.ts`, `idempotencyLayer.ts`   | Request caching + idempotency                                                                                                                                                                                                                                                                                           |
 | (~30 more top-level files)               | Specialized helpers (logEnv, modelsDevSync, piiSanitizer, etc.)                                                                                                                                                                                                                                                         |
 
-### `src/db/` — Database (117 modules + 144 migrations)
+### `src/db/` — Database (117 modules + 148 migrations)
 
 | Subdir                    | Purpose                                                                                                                                                                    |
 | ------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
@@ -256,6 +256,7 @@ src/
 | `utils/circuitBreaker.ts`        | Provider circuit breaker (see `docs/architecture/RESILIENCE_GUIDE.md`) |
 | `utils/apiAuth.ts`               | API key validation, scope checking                                     |
 | `utils/fetchTimeout.ts`          | Timeout/abort wrappers for upstream fetch                              |
+| `utils/releaseNotes.ts`          | Closed v2/legacy announcement parser, localization and ID dismissal    |
 
 ---
 
@@ -270,7 +271,7 @@ open-sse/
 ├── translator/          # Format converters (9 request, 9 response, 9 helpers)
 ├── transformer/         # Responses API ↔ Chat Completions (TransformStream)
 ├── services/            # ~80+ service modules (combo, accountFallback, autoCombo, reasoningCache, claude code/chatgpt stealth, modelDeprecation, taskAwareRouter, workflowFSM, etc.)
-├── mcp-server/          # MCP server (105 tools, 3 transports, 31 scopes)
+├── mcp-server/          # MCP server (109 tools, 3 transports, 33 scopes)
 ├── config/              # Provider/model registries, header config, model aliases
 ├── utils/               # TLS client, proxy fetch/dispatcher, network helpers
 ├── index.ts             # Workspace entry
@@ -406,7 +407,7 @@ open-sse/
 
 | Doc                        | Purpose                                                             |
 | -------------------------- | ------------------------------------------------------------------- |
-| `MCP-SERVER.md`            | MCP server: 105 tools, 3 transports, 31 scopes, REST endpoints       |
+| `MCP-SERVER.md`            | MCP server: 109 tools, 3 transports, 33 scopes, REST endpoints      |
 | `A2A-SERVER.md`            | A2A v0.3: JSON-RPC, 6 skills, REST helpers, agent card              |
 | `AGENT_PROTOCOLS_GUIDE.md` | Unified guide: A2A vs ACP vs Cloud Agents                           |
 | `CLOUD_AGENT.md`           | Codex Cloud / Devin / Jules orchestration                           |

docs/architecture/RESILIENCE_GUIDE.md

@@ -330,32 +330,75 @@ excludeMarkers, defaultRetryAfterMs}`), matched via `applyStatusRestatement()`.
 
 Permanent errors (agentrouter's `无权访问模型` — no access to this model) are
 NEVER restated: `excludeMarkers` vetoes the rule even when `textMarkers` hit,
-so the error keeps its original status and nothing retries it forever. A
+so the error keeps its original status and nothing retries it forever. The
-separate provider classification rule
+matching provider classification rule
-(`agentrouter-model-access-denied` in `open-sse/config/providerErrorRules.ts`)
+(`agentrouter-model-access-denied` in `open-sse/config/providerErrorRules.ts`:
-declares an `auth_error`/scope-`model` match for this text, but it does not
+`reason: "auth_error"`, `scope: "model"`, a `6h` declared base cooldown) is
-fire on the live production path today: the rule only matches `status ===
+consulted by `checkFallbackError` (`open-sse/services/accountFallback.ts`)
-403`, and `checkFallbackError`'s apikey-category `FORBIDDEN` branch
+*before* the generic apikey-category `FORBIDDEN` early-return, gated on
-(`open-sse/services/accountFallback.ts`) returns early for a plain 403
+`honorsRuleLockScope(provider)` (#10334 — currently agentrouter-exclusive via
-*before* the provider-rule lookup ever runs. In practice a `无权访问模型` 403
+the `HONORS_RULE_LOCK_SCOPE_PROVIDERS` allowlist in
-is handled the same way as the base apikey-provider 403 path (see Connection
+`providerErrorRules.ts`). The rule's declared 6h cooldown flows through as
-Cooldown, §2), not as a 6h model lockout. The rule still exists as a
+`fallbackResult.baseCooldownMs`, but it still feeds the pre-existing
-declarative classification consumable by future callers of `classifyError`
+per-model-quota lockout path (`lockModelIfPerModelQuota()` /
-with context — wiring it into the production `checkFallbackError` path is
+`recordModelLockoutFailure()`, unchanged by #10334 except for the cooldown
-tracked as a follow-up, not yet done.
+source): it is clamped down to the operator's `mlSettings.maxCooldownMs`
+(default `1_800_000ms` / 30min), like every other model lockout, and the
+*persisted lockout reason* stays the pre-existing hardcoded `"forbidden"`,
+not the rule's `"auth_error"` — only the cooldown duration is honored
+end-to-end, not the reason string. The connection itself stays active;
+sibling models on the same connection are unaffected.
 
-Restated quota errors (`额度不足`) do reach a provider rule in production
+Restated quota errors (`额度不足`) reach a provider rule in production
-(`agentrouter-user-quota-exhausted`, scope `"connection"`), but `scope` on
+(`agentrouter-user-quota-exhausted`: `reason: "quota_exhausted"`, `scope:
-`ProviderErrorRuleMatch` is currently informational — the persistence path
+"connection"`, no declared cooldown of its own — the persistence layer's
-(`checkFallbackError` → `combo.ts`) only consumes `reason` and `cooldownMs`,
+scaled backoff default applies). Since #10334, `scope` on
-never `scope`. What actually happens for agentrouter (`passthroughModels:
+`ProviderErrorRuleMatch` IS consumed end-to-end, but **only** for providers in
-true` → `hasPerModelQuota()` returns `true`) is a **per-model** lockout via
+the `HONORS_RULE_LOCK_SCOPE_PROVIDERS` allowlist (`providerErrorRules.ts` —
-`recordModelLockoutFailure()`: the connection itself is never cooled down for
+today only `"agentrouter"`, gated via `honorsRuleLockScope()`). For every
-this error (`combo.ts` skips `recordProviderCooldown` for 429 when
+other provider `scope` remains informational, exactly as before #10334.
-`hasPerModelQuota` is true), so other models on the same account keep being
+`checkFallbackError` surfaces the matched rule's scope as
-tried — each one burns one call and its own lockout before combo routing
+`fallbackResult.ruleScope`; `isAgentrouterConnectionQuotaScope()`
-moves on. Honoring `scope` end-to-end (so a `"connection"` match actually
+(`src/sse/services/auth.ts`) is the shared guard that confirms a
-locks the connection) is tracked as a follow-up.
+`ruleScope` is genuinely safe to honor as a connection-wide, self-recovering
+signal (scope `"connection"`, reason `quota_exhausted`, never `permanent`,
+never `creditsExhausted` — a defense against a future rule pairing scope
+`"connection"` with a permanent account state). Two consumers call it:
+
+- **Persistence** (`markAccountUnavailable()`, `src/sse/services/auth.ts`):
+  instead of falling into the passthrough-provider **per-model** lockout
+  branch (agentrouter is `passthroughModels: true` → `hasPerModelQuota()`
+  returns `true`), it applies a **temporary connection cooldown** —
+  `testStatus: "unavailable"` + `rateLimitedUntil`, never a terminal status
+  (`credits_exhausted`/`banned`/`expired`) — so the connection self-recovers
+  once the cooldown lapses instead of requiring a manual credential reset.
+  Skipped for connections with `disableCooling: true` (#2997): that opt-out
+  falls through to the per-model lockout instead (a documented trade-off —
+  see the code comment above the branch).
+- **Same-request combo routing** (`applyComboTargetExhaustion()`,
+  `open-sse/services/combo/targetExhaustion.ts`): the same guard marks the
+  connection into the in-memory `exhaustedConnections` set, keyed
+  `${provider}:${connectionId}`. This only skips a remaining SAME-REQUEST
+  target that *itself already carries that exact `connectionId`* on its own
+  target object (`getExhaustedTargetSkipReason()`,
+  `open-sse/services/combo/comboPredicates.ts`, `if (provider &&
+connectionId)` before the `exhaustedConnections` lookup) — a plain
+  model-list combo, where sibling targets carry no pinned `connectionId` of
+  their own and one is only resolved per-dispatch from the response's
+  `X-OmniRoute-Selected-Connection-Id` header, never hits that key match. For
+  that common case, the real protection against a remaining leg reusing the
+  just-exhausted account is NOT this Set — it is the persistence layer above
+  (the connection's `rateLimitedUntil` is now in the future) combined with
+  this same guard suppressing `transientRateLimitedProviders` for the
+  failure (see "Two-stage design" and the code comment on the
+  `isAgentrouterConnectionQuotaScope` branch in `targetExhaustion.ts`): with
+  that Set left unmarked, `combo.ts`'s `allowRateLimitedConnection` force-allow
+  (`open-sse/services/combo.ts:1005-1013`, `:2734-2738`) does NOT kick in for
+  the provider's remaining legs, so credential selection's `rateLimitedUntil`
+  filter (`src/sse/services/auth.ts:1238`) is honored normally and a
+  remaining leg either picks a different, still-eligible agentrouter
+  connection or fails with no credentials available — it does not force its
+  way back onto the connection this branch just cooled down.
 
 ### Two-stage design: status restatement, then classification
 
@@ -380,6 +423,15 @@ allowlisted providers, the structured error otherwise. Adding a provider to
 that the default path for every provider not on the list stays
 byte-for-byte unchanged.
 
+A rule's `scope` (`model` / `provider` / `connection`) is a separate opt-in
+from `FULL_TEXT_RULE_PROVIDERS`: `checkFallbackError` only surfaces it as
+`fallbackResult.ruleScope`, and downstream consumers only honor it as
+anything other than an informational label, for providers in the
+`HONORS_RULE_LOCK_SCOPE_PROVIDERS` allowlist in the same file (`gated via
+honorsRuleLockScope()` — today only `"agentrouter"`). See "Restated quota
+errors" above for what a `scope: "connection"` match actually does once a
+provider is on that allowlist.
+
 ### Adding a new quota-misstating gateway
 
 1. Register one rule array in `statusRestatementRegistry`
@@ -395,7 +447,15 @@ byte-for-byte unchanged.
    `checkFallbackError` only ever hands the rule the structured
    `{code, type}` error and a body-text rule will never match live traffic.
    Rules that match purely on `status`/`headers` (like Opencode's or
-   Minimax's) do not need this opt-in.
+   Minimax's) do not need this opt-in. Separately, if the rule declares
+   `scope: "connection"` and the intent is an actual connection-wide cooldown
+   plus same-request combo skip (not just an informational label), add the
+   provider id to `HONORS_RULE_LOCK_SCOPE_PROVIDERS` in the same file — this
+   is what gates `isAgentrouterConnectionQuotaScope()`-style consumption in
+   `markAccountUnavailable()` (`src/sse/services/auth.ts`) and
+   `applyComboTargetExhaustion()`
+   (`open-sse/services/combo/targetExhaustion.ts`); without it, `scope`
+   still flows through `fallbackResult.ruleScope` but nothing acts on it.
 3. Add unit tests mirroring `tests/unit/upstream-status-restatement.test.ts`
    and `tests/unit/agentrouter-error-rules.test.ts` (including the
    not-permanent / not-creditsExhausted guards, and — if the provider needs

docs/diagrams/comparison-table.svg

@@ -1,4 +1,4 @@
-<svg viewBox="0 0 1200 780" xmlns="http://www.w3.org/2000/svg" role="img" aria-label="Comparison table: OmniRoute versus 9router, OpenRouter, CLIProxyAPI and LiteLLM across 13 capabilities. OmniRoute is the only one with the full set: 339 providers, 90+ free providers built-in, 19 routing strategies, 12-engine token compression, a built-in MCP server with 105 tools, A2A protocol, persistent memory, guardrails, cloud agents, TLS fingerprint stealth, desktop/Termux/PWA, 43 UI locales and 100% MIT self-hosted. 9router has free providers, RTK compression and translation but no MCP, A2A, memory, guardrails, cloud agents or stealth. OpenRouter is a hosted SaaS with 400+ models, guardrails and a hosted MCP but is not self-hosted and lacks A2A, memory, cloud agents and stealth. CLIProxyAPI is a light OAuth proxy with two routing strategies. LiteLLM has 100+ providers, A2A and extensive guardrails but no memory, compression, free tier, stealth or cloud agents.">
+<svg viewBox="0 0 1200 780" xmlns="http://www.w3.org/2000/svg" role="img" aria-label="Comparison table: OmniRoute versus 9router, OpenRouter, CLIProxyAPI and LiteLLM across 13 capabilities. OmniRoute is the only one with the full set: 339 providers, 90+ free providers built-in, 19 routing strategies, 12-engine token compression, a built-in MCP server with 109 tools, A2A protocol, persistent memory, guardrails, cloud agents, TLS fingerprint stealth, desktop/Termux/PWA, 43 UI locales and 100% MIT self-hosted. 9router has free providers, RTK compression and translation but no MCP, A2A, memory, guardrails, cloud agents or stealth. OpenRouter is a hosted SaaS with 400+ models, guardrails and a hosted MCP but is not self-hosted and lacks A2A, memory, cloud agents and stealth. CLIProxyAPI is a light OAuth proxy with two routing strategies. LiteLLM has 100+ providers, A2A and extensive guardrails but no memory, compression, free tier, stealth or cloud agents.">
   <desc>Static-header comparison table where each capability row fades in top to bottom; the OmniRoute column is highlighted and shows a check or a leading value in every row, while competitors show a mix of checks, partials and crosses.</desc>
   <defs>
     <pattern id="gC" width="32" height="32" patternUnits="userSpaceOnUse"><path d="M 32 0 L 0 0 0 32" fill="none" stroke="#ffffff" stroke-opacity="0.05" stroke-width="1"/></pattern>
@@ -57,7 +57,7 @@
     </g>
     <g opacity="0"><animate attributeName="opacity" values="0;1" dur="0.4s" begin="0.51s" fill="freeze"/>
       <text x="44" y="364" font-size="14.5" fill="#c9d1d9">Built-in MCP server (own tools)</text>
-      <text x="440" y="364" text-anchor="middle" font-family="Inter, 'Segoe UI', Arial, Helvetica, system-ui, sans-serif" font-size="15" font-weight="800" fill="#7ee787">105</text>
+      <text x="440" y="364" text-anchor="middle" font-family="Inter, 'Segoe UI', Arial, Helvetica, system-ui, sans-serif" font-size="15" font-weight="800" fill="#7ee787">109</text>
       <use href="#no" x="604" y="359"/>
       <use href="#mid" x="760" y="359"/>
       <use href="#no" x="916" y="359"/>

docs/diagrams/promise-pillars.svg

@@ -1,4 +1,4 @@
-<svg viewBox="0 0 1200 540" xmlns="http://www.w3.org/2000/svg" role="img" aria-label="The OmniRoute promise: one endpoint, 339 providers — never stop building, OmniRoute picks the cheapest one that works. Six pillars. Never hit limits: auto-fallback across 339 providers in milliseconds, quota out means the next provider takes over with zero downtime. Save up to 95 percent of tokens: RTK plus Caveman stacked compression cuts 15 to 95 percent of eligible tokens, about 89 percent average on tool-heavy sessions. Zero dollars to start: 90+ providers with a free tier, 40+ free forever — Qoder, Pollinations, Cloudflare, SiliconFlow — no card needed. Every tool works: 33 coding agents including Claude Code, Codex, Cursor, Cline, Copilot and Antigravity through one config. One endpoint: OpenAI, Claude, Gemini and Responses API translation — point any tool at /v1 and it just works. Production-grade: circuit breakers, TLS stealth, MCP with 105 tools, A2A, memory, guardrails, evals — 25,000+ tests.">
+<svg viewBox="0 0 1200 540" xmlns="http://www.w3.org/2000/svg" role="img" aria-label="The OmniRoute promise: one endpoint, 339 providers — never stop building, OmniRoute picks the cheapest one that works. Six pillars. Never hit limits: auto-fallback across 339 providers in milliseconds, quota out means the next provider takes over with zero downtime. Save up to 95 percent of tokens: RTK plus Caveman stacked compression cuts 15 to 95 percent of eligible tokens, about 89 percent average on tool-heavy sessions. Zero dollars to start: 90+ providers with a free tier, 40+ free forever — Qoder, Pollinations, Cloudflare, SiliconFlow — no card needed. Every tool works: 33 coding agents including Claude Code, Codex, Cursor, Cline, Copilot and Antigravity through one config. One endpoint: OpenAI, Claude, Gemini and Responses API translation — point any tool at /v1 and it just works. Production-grade: circuit breakers, TLS stealth, MCP with 109 tools, A2A, memory, guardrails, evals — 25,000+ tests.">
   <desc>Animated promise card: six pillar tiles fade in in reading order, then a soft colored border highlight sweeps from tile to tile in a continuous cycle.</desc>
   <defs>
     <pattern id="gridPaperP" width="32" height="32" patternUnits="userSpaceOnUse">
@@ -125,7 +125,7 @@
         <path d="M 7,11 L 10,14 L 15.4,8.2"/>
       </g>
       <text x="862" y="354" font-size="18" font-weight="800" fill="#7ee787">Production-grade</text>
-      <text x="826" y="388" font-size="13.5" fill="#a1a1aa">Circuit breakers, TLS stealth, MCP (105</text>
+      <text x="826" y="388" font-size="13.5" fill="#a1a1aa">Circuit breakers, TLS stealth, MCP (109</text>
       <text x="826" y="410" font-size="13.5" fill="#a1a1aa">tools), A2A, memory, guardrails, evals —</text>
       <text x="826" y="432" font-size="13.5" fill="#a1a1aa">25,000+ tests.</text>
     </g>

docs/frameworks/MCP-SERVER.md

@@ -1,14 +1,14 @@
 ---
 title: "OmniRoute MCP Server Documentation"
-version: 3.8.40
+version: 3.8.50
-lastUpdated: 2026-06-28
+lastUpdated: 2026-08-08
 ---
 
 # OmniRoute MCP Server Documentation
 
-> Model Context Protocol server with 105 tools across routing, cache, compression, memory, skills, proxy, pool, and context source operations.
+> Model Context Protocol server with 109 tools across routing, cache, compression, memory, skills, proxy, pool, Radar, and context source operations.
 >
-> Source of truth: `open-sse/mcp-server/server.ts` computes **105 unique tools** with `countUniqueMcpTools()`: 42 canonical definitions (including the six CCR lifecycle tools and the agent-skills trio), plus memory (3), skills (4), GitHub skills (3), pool (6), gamification (8), plugins (8), Notion (6), Obsidian (22), and two RTK-only compression tools.
+> Source of truth: `open-sse/mcp-server/server.ts` computes **109 unique tools** with `countUniqueMcpTools()`: 44 canonical definitions (including the six CCR lifecycle tools, the agent-skills trio, and `omniroute_radar_catalog`), plus memory (3), skills (4), GitHub skills (3), pool (6), gamification (8), plugins (8), Notion (6), Obsidian (22), local corpus (3), and two RTK-only compression tools.
 
 ## Installation
 
@@ -64,7 +64,7 @@ Cursor, Cline, and compatible MCP client setup.
 
 ---
 
-## Essential Tools (8) — Phase 1
+## Essential Tools (13) — Phase 1
 
 | Tool                            | Scopes                | Description                                                   |
 | :------------------------------ | :-------------------- | :------------------------------------------------------------ |
@@ -72,16 +72,15 @@ Cursor, Cline, and compatible MCP client setup.
 | `omniroute_list_combos`         | `read:combos`         | All configured combos with strategies (optional metrics)      |
 | `omniroute_get_combo_metrics`   | `read:combos`         | Performance metrics for a specific combo                      |
 | `omniroute_switch_combo`        | `write:combos`        | Activate or deactivate a combo                                |
+| `omniroute_create_combo`        | `write:combos`        | Create a validated combo through the existing combo API       |
 | `omniroute_check_quota`         | `read:quota`          | Quota used/total, percent remaining, reset time, token health |
 | `omniroute_route_request`       | `execute:completions` | Send a chat completion through OmniRoute routing              |
 | `omniroute_cost_report`         | `read:usage`          | Cost report by period (session/day/week/month)                |
 | `omniroute_list_models_catalog` | `read:models`         | Full model catalog with capabilities, status, pricing         |
-
+| `omniroute_radar_catalog`       | `read:radar`          | Local signed Radar catalog; optional provider/family filters  |
-## Phase 1 — Search
+| `omniroute_tool_search`         | `read:tools`          | Discover tools from the registered MCP catalog                |
-
+| `omniroute_web_search`          | `execute:search`      | Web search through the configured search providers            |
-| Tool                   | Scopes           | Description                                                                                                                        |
+| `omniroute_web_fetch`           | `execute:search`      | Fetch web content through the configured fetch providers      |
-| :--------------------- | :--------------- | :--------------------------------------------------------------------------------------------------------------------------------- |
-| `omniroute_web_search` | `execute:search` | Web search through OmniRoute search gateway (Serper/Brave/Perplexity/Exa/Tavily/Google PSE/Linkup/SearchAPI/SearXNG) with failover |
 
 ## Advanced Tools (11) — Phase 2
 
@@ -227,7 +226,7 @@ See [AGENT-SKILLS.md](./AGENT-SKILLS.md) for the full catalog and how external a
 
 ## Related Frameworks (v3.8.0)
 
-computed = 105, computed by `countUniqueMcpTools()`) is intentionally
+The MCP tool inventory above (109 unique tools, computed by `countUniqueMcpTools()`) is intentionally
 scoped to runtime routing/cache/compression/memory/skills/proxy/context-source operations. Two adjacent
 frameworks ship alongside the MCP server in v3.8.0 and are documented separately:
 
@@ -369,7 +368,7 @@ MCP tool, prompt, and resource registries can compress descriptions at registrat
 
 Description compression shrinks each tool's metadata; **tool-cardinality reduction** goes one step further by reducing _how many_ tools are announced at all. Advertising fewer tools in the `tools/list` manifest cuts the per-request token cost the client's model pays for the tool catalog ("layer 5" compression). The implementation is a pure, stateless filter in `open-sse/mcp-server/toolCardinality.ts` (`reduceToolManifest`), wired into the registration loop in `createMcpServer()` (`open-sse/mcp-server/server.ts`).
 
-**Opt-in, off by default.** The filter only runs when at least one of two environment variables is set; with neither set, all 105 tools are announced unchanged.
+**Opt-in, off by default.** The filter only runs when at least one of two environment variables is set; with neither set, all 109 tools are announced unchanged.
 
 | Variable         | Mode                                                                                    |
 | :--------------- | :-------------------------------------------------------------------------------------- |

docs/frameworks/RADAR.md

@@ -1,13 +1,13 @@
 ---
 title: "Radar Free-Model Catalog"
 version: 3.8.50
-lastUpdated: 2026-08-08
+lastUpdated: 2026-08-13
 ---
 
 # Radar Free-Model Catalog
 
 > **Source of truth:** `src/lib/radar/`, `src/lib/db/radar.ts`, `src/app/api/radar/`
-> **Last updated:** 2026-08-08 — v3.8.50
+> **Last updated:** 2026-08-13 — v3.8.50
 
 Radar is an **optional add-on** that overlays a signed, freshly-curated free-model
 catalog on top of the release baseline (`FREE_MODEL_BUDGETS` in
@@ -15,11 +15,12 @@ catalog on top of the release baseline (`FREE_MODEL_BUDGETS` in
 faster than release cadence — providers add, shrink, or discontinue free quotas between
 releases, and the baseline catalog can only be refreshed when a new version ships.
 
-**Nothing that is free today stops being free.** Radar never removes or paywalls a
+**Nothing that is free today stops being free because of the remote feed.** Radar never
-baseline entry; it only refreshes limits/status fields at read time and can layer in
+paywalls a baseline entry; it only refreshes limits/status fields at read time and can
-newly-discovered free models between releases. The baseline catalog itself is never
+layer in newly-discovered free models between releases. An operator can still hide a
-mutated on disk — see [Read-time overlay merge rules](#read-time-overlay-merge-rules)
+model locally, and can restore it from the same dashboard. The baseline catalog itself
-below.
+is never mutated on disk — see
+[Read-time overlay merge rules](#read-time-overlay-merge-rules) below.
 
 ---
 
@@ -29,14 +30,39 @@ The following status distinguishes what this OSS release implements from later R
 workstreams. It is a code-level status, not a promise that a particular hosted deployment
 or external integration is currently available.
 
-| Area                             | Status in this release                                                                                                                                                                                                 |
+| Area                             | Status in this release                                                                                                                                                                                                   |
-| -------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| -------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| Signed catalog client            | Implemented behind `RADAR_ENABLED`, with separate opt-in, Ed25519 verification, local encrypted settings/cache, non-destructive overlay, scheduler, and dashboard.                                                     |
+| Signed catalog client            | Implemented behind `RADAR_ENABLED`, with separate opt-in, Ed25519 verification, local encrypted settings/cache, persistent display/enabled overrides, reversible tombstones, scheduler, and dashboard.                   |
-| Contributor activation           | The dashboard links to the server-hosted GitHub claim flow and accepts an existing `omr_…` key. Contributor eligibility is resolved by the private service; the OSS client contains no GitHub token or issuance logic. |
+| Contributor activation           | The dashboard links to the server-hosted GitHub claim flow and accepts an existing `omr_…` key. Contributor eligibility is resolved by the private service; the OSS client contains no GitHub token or issuance logic.   |
-| Supporter-key activation         | Implemented. The raw key is validated, encrypted at rest, masked on reads, and sent only by the server-side sync. Changing or clearing the key invalidates both entitlement-sensitive feed caches.                     |
+| Supporter-key activation         | Implemented. The raw key is validated, encrypted at rest, masked on reads, and sent only by server-side sync. Changing or clearing the key invalidates all four entitlement-sensitive feed caches.                       |
-| Referral links                   | Implemented as a separately signed, hourly-refreshed feed. Fixed links are available to the community tier immediately; limited campaigns remain live-tier data.                                                       |
+| Referral links                   | Implemented as a separately signed, hourly-refreshed feed. Fixed links are available to the community tier immediately; limited campaigns remain live-tier data.                                                         |
-| Payments and transactional email | Not implemented in the OSS client. Purchase, donation, receipt review, and mail delivery belong to the private service and its later operational workstream.                                                           |
+| Supporter offers                 | Implemented as a separate signed, live-only feed and dashboard page. The client revalidates the closed benefit schema, preserves the last good cache, filters expired entries, and labels partner offers explicitly.     |
-| Research-agent workstream        | Not part of this client release. Curated feed contents remain server-side data; no autonomous research agent runs in an OmniRoute installation.                                                                        |
+| Intel and supporter recognition  | Implemented as a strict signed live-only feed with Radar-owned ELO, factual catalog freshness/trend, a verified local supporter badge, dashboard page, and local-only CLI status/sync commands.                          |
+| Payments and transactional email | Not implemented in the OSS client. Purchase, donation, receipt review, recovery, and mail delivery belong to the private service; hosted availability still depends on its supervised deploy and provider configuration. |
+| Research-agent workstream        | Not part of this client release. Curated feed contents remain server-side data; no autonomous research agent runs in an OmniRoute installation.                                                                          |
+
+---
+
+## Public announcement reader
+
+The generic announcement reader is separate from the Radar feature flag. The dashboard Home and
+Changelog viewer fetch the repository's public `news.json` through a plain `GET` to
+`NEWS_JSON_URL` (`src/shared/utils/releaseNotes.ts`). They send no Radar setting, prompt, provider
+configuration, usage record, or local dismissal state.
+
+`news.json` uses the closed v2 schema implemented by `parseNewsPayload()`:
+
+- `schemaVersion: 2` and a bounded `items[]` collection;
+- stable, unique announcement `id` values;
+- explicit `active` and ISO `publishedAt` fields;
+- required English copy with optional localized copy;
+- optional credential-free HTTPS links and an allowlisted icon;
+- newest-active-first selection, locale fallback to English, and per-ID local dismissal.
+
+The parser temporarily accepts the former singular `{ active, title, message, ... }` shape so
+older forks can migrate without a broken Changelog view. Invalid feeds are inert. The Radar launch
+entry ships with `active: false`; changing it to `true` is a separate post-merge, post-deploy
+release action and does not change `RADAR_ENABLED` or the independent feed-sync opt-in.
 
 ---
 
@@ -48,15 +74,16 @@ Radar is gated end-to-end by the `RADAR_ENABLED` feature flag
 
 **When the flag is off, the surface does not exist:**
 
-- `GET /api/radar/catalog`, `POST /api/radar/sync`, `POST /api/radar/settings` all
+- All `/api/radar/*` endpoints, including local model-state reads and writes,
   return `404` before touching any Radar module.
-- The dashboard screens (`/dashboard/radar`, `/dashboard/radar/setup`) render
+- The dashboard screens (`/dashboard/radar`, `/dashboard/radar/setup`,
+  `/dashboard/radar/combos`, `/dashboard/radar/offers`, `/dashboard/radar/intel`) render
   `notFound()`.
 - `getRadarCatalog()` (`src/lib/radar/index.ts`) returns the untouched baseline —
   same entry count, same values, every entry tagged `origin: "baseline"` — and never
   reads the feed cache.
-- No network call is ever made; `syncRadar()` (`src/lib/radar/sync.ts`) returns
+- No Radar network call is ever made; each sync module returns `{ status: "disabled" }`
-  `{ status: "disabled" }` at step 1 without touching `fetch`.
+  before touching `fetch`.
 
 This is a strict superset gate: flipping the flag on unlocks the _screens_, nothing
 more. It does not upload data, does not start a background sync, and does not change
@@ -78,14 +105,17 @@ Opt-in false  → { status: "opt_out" }    — no network call
 
 When both are on, the sync path is:
 
-1. `GET <feed base URL>/v1/catalog/latest` with an optional `Authorization: Bearer
+1. `GET <feed base URL>/v1/catalog/latest` with `x-omniroute-radar-schema: 2` and an optional
-<supporter key>` header (see below).
+   `Authorization: Bearer <supporter key>` header (see below). Servers default to the separately
+   signed v1 transition artifact when the schema header is absent, so older installed clients keep
+   receiving updates.
 2. Nothing about the request, the operator, or their traffic is uploaded — it is a
    plain, unauthenticated-by-default GET. OmniRoute never posts usage data, provider
    configuration, or model traffic to the feed service.
 3. The response is verified, validated, and cached locally (see
-   [Security model](#security-model)). Radar has exactly two server-side network paths:
+   [Security model](#security-model)). Radar has exactly four server-side network paths:
-   `syncRadar()` for the catalog and `syncRadarReferrals()` for the standalone referrals feed.
+   `syncRadar()` for the catalog, `syncRadarReferrals()` for referrals, and
+   `syncRadarOffers()` / `syncRadarIntel()` for supporter-only offers and Intel.
 
 The **supporter key** is an optional Bearer token (`radar_settings.supporter_key`)
 that lets the feed service decide which tier to serve (see
@@ -95,7 +125,7 @@ that lets the feed service decide which tier to serve (see
   helpers (`src/lib/db/encryption.ts`) used for provider credentials.
 - Set via `POST /api/radar/settings` (`{ supporterKey: "omr_" + 40 hex chars }`) and
   **never echoed back** — the response returns a masked form (`omr_****abcd`).
-- Changing or clearing it atomically invalidates both the catalog and referrals caches. The
+- Changing or clearing it atomically invalidates the catalog, referrals, offers, and Intel caches. The
   next sync/read resolves the new entitlement server-side; saving a key does not itself make
   a network request or consume a single-use activation key.
 - Sent to the feed service as a Bearer token on the sync GET — nothing else about the
@@ -128,6 +158,29 @@ client component never reads `process.env` itself.
 | `RADAR_CONTRIBUTOR_CLAIM_URL` | Overrides the contributor-claim URL (default `https://radar.omniroute.online/auth/github`). |
 | `RADAR_SUPPORTER_PLANS_URL`   | Overrides the supporter-plans URL (default `https://radar.omniroute.online/planos`).        |
 
+### Recovering a lost supporter key
+
+The hosted service's recovery entry point is `https://radar.omniroute.online/recover`; it is also
+linked from the plans page. Recovery remains entirely outside the OSS client because the local
+installation never receives the purchaser/contributor e-mail and cannot reconstruct a raw key from
+its encrypted settings.
+
+1. Submit the e-mail associated with the key. The service returns the same accepted page whether a
+   recoverable license exists or not, so the form does not enumerate accounts.
+2. If eligible, the delivery worker sends a short-lived, one-use link. Opening it immediately moves
+   the token into a transient encrypted `HttpOnly`/`Secure` cookie and redirects to the clean
+   `/recover` URL; the page contains no token, e-mail, old key, or replacement key.
+3. Confirm the revocation. The private service revokes the prior key, creates the replacement with
+   the same plan/expiration, and queues it for e-mail in one transaction. The replacement is never
+   returned to the browser.
+4. Paste the replacement into `/dashboard/radar`. The old key must now degrade to `community`; the
+   replacement must produce a verified `live` sync. Reopening the same recovery link must fail with
+   a generic invalid/expired response.
+
+The hosted recovery route and mail worker can be present in code while still unavailable in a given
+deployment. Do not call the flow production-ready until the server has been deployed, the delivery
+provider has been configured with a controlled recipient, and the full one-use link has been tested.
+
 Once a visitor has a key (`omr_` + 40 hex chars), the activation screen
 (`src/app/(dashboard)/dashboard/radar/page.tsx`) has a paste-key input as the primary
 path: pasting a key and submitting sends `POST /api/radar/settings`
@@ -141,6 +194,57 @@ paste a new one — the raw key is never redisplayed. The two claim/plans button
 remain the way to _obtain_ a key in the first place; this input is where an operator
 who already has one activates it.
 
+### End-to-end activation and guided setup
+
+The private feed service and this OSS client have a deliberately narrow boundary: the service
+issues and validates the supporter key, while the local OmniRoute installation encrypts the key,
+syncs signed artifacts server-side, and guides provider setup. The assisted validation order is:
+
+1. Obtain a newly issued or recovered key from the contributor claim, plans/checkout, recovery
+   journey, or an authorized private server operator. Do not paste the raw key into logs,
+   screenshots, issue comments, or command-line arguments.
+2. Enable the `RADAR_ENABLED` feature flag on the local OmniRoute installation. This exposes the UI
+   but remains network-inert until the separate opt-in is saved.
+3. Open `/dashboard/radar`, paste the key, and activate. The browser sends one local
+   `POST /api/radar/settings` with `{ optIn: true, supporterKey }`; the key is encrypted locally and
+   the response contains only `omr_****<last4>`.
+4. Let the activation screen run its catalog sync, or select **Sync now**. Confirm that the page
+   reports `live`, a feed version, and a fetch time. For an authenticated local diagnostic,
+   `GET /api/radar/status` reports opt-in/key presence and the four cache states without returning
+   the key. `POST /api/radar/sync-all` can refresh catalog, referrals, offers, and Intel explicitly.
+5. Open `/dashboard/radar/setup?provider=<provider>`. Follow the provider-owned credential URL,
+   select **Add API key**, save through the real provider form, return to the guide, and run
+   **Test connection**. The guide uses the normal `/api/providers` and
+   `/api/providers/<connection-id>/test` routes; it does not create a parallel Radar credential.
+6. Open `/dashboard/radar/combos` after at least two compatible provider connections are active.
+   Review the suggested family and create the combo through the existing combo API. Offers and
+   Intel remain separate live-only signed caches and can be checked on their dedicated Radar pages.
+7. Reload `/dashboard/radar` and the setup page. The opt-in, masked-key state, verified cache, saved
+   provider connection, and test action must survive the reload. Capture evidence only after the
+   raw key and provider credential are no longer visible.
+
+Saving a key is not itself proof of live entitlement. The proof is the combination of the private
+service's `GET /v1/license/check` result, the OSS catalog's served `live` tier, a verified signed
+cache, and the real provider connection/test flow. An invalid, expired, or revoked key safely
+degrades the catalog to `community`; it must not be reported as a successful live-key validation.
+
+### Private admin-panel link
+
+`RADAR_ADMIN_URL` optionally adds **Radar Admin ↗** immediately after the user-facing
+Radar item in the Costs sidebar section. It has deliberately no default: when the variable is
+unset or invalid, the static sidebar, command palette, and sidebar-customization screen contain no
+admin item and no private URL.
+
+The value is resolved server-side and relayed through the management-authenticated
+`GET /api/settings` response only to an authenticated dashboard session, or to the trusted
+loopback owner during a local no-login bootstrap. CLI, internal-service, and manage-scope API-key
+authentication do not receive it. The browser validates the response again before materializing
+the external link, which opens with `noopener noreferrer`.
+
+Use a credential-free HTTPS tunnel/tailnet URL. Plain HTTP is accepted only for a loopback SSH
+forward such as `http://127.0.0.1:9351`; other schemes, embedded credentials, malformed URLs, and
+remote HTTP destinations fail closed and leave navigation inert.
+
 ---
 
 ## Security model
@@ -271,6 +375,54 @@ Four rules, in order of precedence:
    entry (`tombstones` set), the feed re-adding that `provider:modelId` in a later
    version does not bring it back.
 
+The editable fields and tombstones are persisted in
+`radar_local_model_state` (migration `153_radar_local_model_state.sql`). The public DB
+adapter (`src/lib/db/radar.ts`) converts those rows into the `localOverrides` map and
+`tombstones` set used by `applyFeed()`; production `getRadarCatalog()` loads that state
+after the flag, cache, and schema gates pass. Only `displayName` and `enabled` are
+operator-editable. Provider/model identity, feed provenance, quota, capabilities, ToS,
+and setup data cannot be written through this surface.
+
+The dashboard exposes four local actions:
+
+- **Edit** changes the local display name and enabled state.
+- **Reset local changes** clears both editable fields without changing a tombstone.
+- **Hide** creates a tombstone, so later feed updates cannot recreate the row.
+- **Restore** removes the tombstone; any separately-saved override remains in effect.
+
+A feed `enabled: false` remains the safety exception: it wins over a stale local
+`enabled: true`, keeps the merged entry disabled, and records `disabledBy: "radar"`.
+
+Catalog publications use `schemaVersion: 2`. `contextWindow` and each of `tools`, `vision`, and
+`thinking` are independently `number | null` / `boolean | null`: `null` means unknown, while
+`false` means a D16-confirmed official provider source explicitly says the capability is absent.
+Internal OmniRoute registry/model-spec flags are never promoted directly to feed facts. The client
+still accepts v1 snapshots; because the old builder used `false` as an absence placeholder, v1 `false` is
+normalized to unknown while v1 `true` remains factual. Unknown schema versions fail closed and the
+last valid cache remains available. Every v2 model with a non-null context/capability must carry a
+credential-free HTTPS `metadataEvidenceUrls[]`; otherwise schema validation fails and the cache is
+not replaced. The catalog table renders all three states as `✓`, `✕`, and `?`.
+
+### Guided combos and MCP access
+
+Confirmed `familyId` values survive the read-time overlay and drive the pure
+`buildRadarComboSuggestions()` module (`src/lib/radar/comboSuggestions.ts`). A family is suggested
+only when at least two distinct providers have active connections and expose the exact curated model
+ID. Disabled models, inactive providers, missing model IDs, singleton families, and ambiguous
+alias/prefix matches fail closed. Suggestions use the existing `priority` strategy, ordering the
+largest recurring monthly budget first; the UI creates them only through `POST /api/combos`.
+
+The guided UI lives at `/dashboard/radar/combos`. It reads only the local
+`GET /api/radar/catalog` and `GET /api/combos/builder/options` endpoints. It never triggers Radar sync,
+reads provider credentials, or writes directly to the combo database.
+
+MCP clients can read the same local projection with `omniroute_radar_catalog` (`read:radar`). The
+optional `provider`, `familyId`, and `enabledOnly` filters are evaluated after one local
+`GET /api/radar/catalog` read. Its closed output includes catalog metadata plus provider/model,
+display name, `familyId`, quota, capabilities, enabled state, origin, and `disabledBy`; setup URLs,
+steps, connections, e-mail addresses, keys, and referral data are never returned. This tool is
+read-only and never invokes `/api/radar/sync`.
+
 ### Provenance markers
 
 Every merged entry carries an `origin` field the UI renders as a badge:
@@ -284,30 +436,41 @@ Every merged entry carries an `origin` field the UI renders as a badge:
 
 ## Local surfaces — never a feed proxy
 
-Five local routes back the UI, all under `src/app/api/radar/`:
+The local Radar route families below back the UI under `src/app/api/radar/`:
 
-| Route                  | Method | Purpose                                                                                                               |
+| Route                          | Method | Purpose                                                                                                               |
-| ---------------------- | ------ | --------------------------------------------------------------------------------------------------------------------- |
+| ------------------------------ | ------ | --------------------------------------------------------------------------------------------------------------------- |
-| `/api/radar/catalog`   | GET    | Returns the merged catalog (`getRadarCatalog()`) from the local cache.                                                |
+| `/api/radar/catalog`           | GET    | Returns the merged catalog (`getRadarCatalog()`) from the local cache.                                                |
-| `/api/radar/sync`      | POST   | Triggers `syncRadar()` server-side; returns the resulting status.                                                     |
+| `/api/radar/sync`              | POST   | Triggers `syncRadar()` server-side; returns the resulting status.                                                     |
-| `/api/radar/settings`  | GET    | Returns `{ optIn, hasSupporterKey, supporterKeyMasked }` — never the raw key.                                         |
+| `/api/radar/settings`          | GET    | Returns `{ optIn, hasSupporterKey, supporterKeyMasked }` — never the raw key.                                         |
-| `/api/radar/settings`  | POST   | Sets opt-in and/or the (encrypted) supporter key.                                                                     |
+| `/api/radar/settings`          | POST   | Sets opt-in and/or the (encrypted) supporter key.                                                                     |
-| `/api/radar/referrals` | GET    | Returns `{ fixed, campaigns, tier }` from the local cache — see [Referral links](#referral-links-free-credits) below. |
+| `/api/radar/referrals`         | GET    | Returns `{ fixed, campaigns, tier }` from the local cache — see [Referral links](#referral-links-free-credits) below. |
+| `/api/radar/offers`            | GET    | Returns active offers from the verified local live cache; never returns the supporter key.                            |
+| `/api/radar/offers/sync`       | POST   | Triggers the server-side, live-key-only `syncRadarOffers()` pipeline.                                                 |
+| `/api/radar/intel`             | GET    | Returns verified local live Intel plus a supporter-recognition boolean; never an identity or key.                     |
+| `/api/radar/intel/sync`        | POST   | Triggers the server-side, live-key-only `syncRadarIntel()` pipeline.                                                  |
+| `/api/radar/status`            | GET    | Returns read-only local settings/cache status for catalog, referrals, offers, and Intel, without secrets.             |
+| `/api/radar/sync-all`          | POST   | Runs all four server-side sync modules and returns a separate status for each feed.                                   |
+| `/api/radar/local-model-state` | GET    | Lists persisted overrides and tombstones for edit/restore controls.                                                   |
+| `/api/radar/local-model-state` | PATCH  | Sets or clears the validated `displayName`/`enabled` override fields.                                                 |
+| `/api/radar/local-model-state` | PUT    | Creates or removes a tombstone with `{ provider, modelId, tombstoned }`.                                              |
+| `/api/radar/local-model-state` | DELETE | Clears editable override fields while preserving any tombstone.                                                       |
 
 **Hard rule: these routes never proxy the feed service.** The browser only ever talks
-to the local OmniRoute server. The two modules that touch the Radar service are
+to the local OmniRoute server. The four modules that touch the Radar service are
-`src/lib/radar/sync.ts` (catalog) and `src/lib/radar/referralsSync.ts` (referrals); both
+`src/lib/radar/sync.ts` (catalog), `src/lib/radar/referralsSync.ts` (referrals), and
-always run server-side, never client-side. This keeps the feed URL and any supporter key
+`src/lib/radar/offersSync.ts` (offers) plus `src/lib/radar/intelSync.ts` (Intel); all run
-out of client-facing network traffic entirely.
+server-side, never client-side. This keeps
+the feed URL and any supporter key out of client-facing network traffic entirely.
 
-All five routes return `404` when `RADAR_ENABLED` is off (see
+All Radar endpoints return `404` when `RADAR_ENABLED` is off (see
 [Flag](#flag-radar_enabled-default-off) above), and route error responses through
 `buildErrorBody()`/`sanitizeErrorMessage()` per the repo-wide error-sanitization rule
 (`docs/security/ERROR_SANITIZATION.md`).
 
 ### Authentication
 
-All five routes require authentication via `isAuthenticated()`
+All Radar endpoints require authentication via `isAuthenticated()`
 (`src/shared/utils/apiAuth.ts`) — a dashboard session cookie or a management-scoped
 API key, the same gate that protects the rest of `/api/settings/*`. The flag-off
 `404` check always runs **before** the auth check, so an install with `RADAR_ENABLED`
@@ -318,6 +481,58 @@ auth state — only the masked form and a `hasSupporterKey` boolean.
 
 ---
 
+## Supporter offers
+
+Offers use their own signed artifact, `GET /v1/offers/latest`, and never share the catalog or
+referrals cache. The server endpoint requires a valid live supporter Bearer key; there is no
+community fallback. `syncRadarOffers()` therefore stops before the network when the feature flag is
+off, the operator has not opted in, or no supporter key is configured.
+
+After a successful GET, the client verifies the Ed25519 signature over the exact response bytes,
+validates `RadarOffersFeedSchema`, requires both the signed body and
+`x-omniroute-feed-tier` header to say `live`, enforces a strictly newer dotted version, and only then
+atomically replaces `radar_offers_cache` (migration `144_radar_offers_cache.sql`). The same 10 MB
+header-plus-stream cap used by the other feeds applies. Signature, schema, tier, replay, size, HTTP,
+and network failures all preserve the last verified cache.
+
+The closed offer shape supports three comparable benefit types: percentage in basis points, credit
+in minor currency units, or trial days. A partner offer must include a same-kind public baseline and
+its benefit must be strictly greater; official offers have no partner baseline. URLs must be
+credential-free HTTPS. `getRadarOffers()` defensively revalidates the cached payload and filters
+expired entries on every local read; `/dashboard/radar/offers` filters expiry again before rendering,
+uses Portuguese text when available with English fallback, and labels partner offers explicitly.
+
+The browser calls only local routes: it reads the masked settings snapshot, asks
+`POST /api/radar/offers/sync` to refresh server-side, then reads `GET /api/radar/offers`. Without a
+key it shows the existing contributor/support links instead of attempting a feed request. External
+offer links open in a new tab with `noopener noreferrer`. No `radar_offers` MCP tool is exposed in
+this release.
+
+---
+
+## Radar Intel, supporter badge, and CLI
+
+Intel is a signed artifact at `GET /v1/intel/latest`. The closed `RadarIntelFeedSchema` accepts
+only Radar-owned ELO rankings derived by the private curator from confirmed comparisons and factual
+catalog age/count deltas derived from signed catalog snapshots. The methodology is fixed at initial
+rating 1000 and K=32. An empty ranking is valid when no comparison has been confirmed; the client
+never synthesizes one.
+
+`syncRadarIntel()` applies the same server-side Bearer, 30-second timeout, 10 MiB streamed cap,
+exact-byte Ed25519 verification, strict schema, `live` body/header requirement, version floor, and
+last-good-cache preservation as offers. After a verified live snapshot is persisted, the client
+derives `radar:<sha256(supporter key)>`, stores only that one-way identity, and emits the dedicated
+`radar_supporter` recognition event. Its `radar-supporter` badge is idempotent and awards zero XP;
+it never updates leaderboards or reuses `token_share`. `/dashboard/radar/intel` renders the badge
+only from verified local cache metadata.
+
+The CLI exposes `omniroute radar status` and `omniroute radar sync`. Both communicate only with the
+local OmniRoute API. `status` performs a read-only `GET /api/radar/status`; `sync` sends one
+`POST /api/radar/sync-all` and prints a result per feed. Neither command reads, accepts, or prints
+the supporter key, and neither contacts the Radar service directly.
+
+---
+
 ## Referral links (free credits)
 
 Referral links are served from a **standalone, always-current** feed —
@@ -473,8 +688,9 @@ service without touching client code:
 
 1. Serve a `GET /v1/catalog/latest` endpoint returning a JSON body that satisfies
    `RadarFeedSchema` (`src/lib/radar/feedSchema.ts`) — top-level `feed:
-"omniroute-radar"`, `schemaVersion: 1`, `version`, `tier`, `providers`, `models`,
+"omniroute-radar"`, `schemaVersion: 2`, `version`, `tier`, `providers`, `models`,
-   `quirks`, and `totals`.
+   `quirks`, and `totals`. Honor `x-omniroute-radar-schema: 2`; a transition-compatible server
+   should default requests without it to a separately signed v1 artifact.
 2. Sign the exact response bytes with an Ed25519 key pair and return the base64
    signature in the `x-omniroute-feed-signature` response header.
 3. Set `RADAR_FEED_URL` to the new base URL and `RADAR_FEED_PUBKEY` to the matching
@@ -498,11 +714,24 @@ instead of failing the rest of the page. To also offer referral links, serve
 (`src/lib/radar/referralsFeedSchema.ts`) and sign it with the same Ed25519 key pair as
 the catalog feed.
 
+Supporter offers are another optional artifact. To serve them, implement
+`GET /v1/offers/latest` with the closed `RadarOffersFeedSchema`
+(`src/lib/radar/offersFeedSchema.ts`), require live entitlement, return
+`x-omniroute-feed-tier: live`, and sign the exact bytes with the same key. A fork that omits this
+endpoint keeps the catalog/referrals behavior unchanged; offer refresh fails non-destructively and
+the last verified local offer cache remains available.
+
+Intel is optional in the same way. A self-hoster can serve `GET /v1/intel/latest` using
+`RadarIntelFeedSchema` (`src/lib/radar/intelFeedSchema.ts`), require live entitlement, return
+`x-omniroute-feed-tier: live`, and sign the exact bytes with the shared Ed25519 key. Omitting the
+endpoint leaves catalog, referrals, and offers unchanged; Intel refresh preserves any last verified
+local snapshot.
+
 ---
 
 ## Related docs
 
 - [`docs/security/ERROR_SANITIZATION.md`](../security/ERROR_SANITIZATION.md) — the
-  error-response pattern the five `/api/radar/*` routes follow.
+  error-response pattern the `/api/radar/*` routes follow.
 - [`docs/reference/ENVIRONMENT.md`](../reference/ENVIRONMENT.md#27-radar-feed-self-hosting)
   — `RADAR_FEED_URL` / `RADAR_FEED_PUBKEY` reference.

docs/i18n/ar/llm.txt

@@ -4,10 +4,7 @@
 
 ---
 
-
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 339 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (109 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
-
-
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 339 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (105 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -21,7 +18,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 - **Runtime:** Node.js `>=22.0.0 <23 || >=24.0.0 <27`, ES Modules (`"type": "module"`)
 - **Framework:** Next.js 16 (App Router) with TypeScript 6
-- **Database:** SQLite via better-sqlite3 (local, zero-config, 145 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 148 migrations)
 - **State management:** Zustand (client), SQLite (server persistence)
 - **UI:** React 19, Tailwind CSS 4, Recharts for analytics, @lobehub/icons for 130+ provider SVG icons
 - **Auth:** OAuth 2.0 (PKCE) for providers, bcrypt for local user auth
@@ -109,7 +106,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   └── streaming.ts      # SSE streaming for A2A
 │   │   ├── acp/                  # Agent Communication Protocol registry and manager
 │   │   ├── compliance/           # Compliance policy engine
-│   │   ├── db/                   # SQLite database layer (99 modules + migrations)
+│   │   ├── db/                   # SQLite database layer (117 modules + migrations)
 │   │   │   ├── core.ts           # Database initialization, connection, schema
 │   │   │   ├── providers.ts      # Provider connection CRUD
 │   │   │   ├── models.ts         # Model catalog management
@@ -131,7 +128,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   ├── secrets.ts        # Secrets management
 │   │   │   ├── stateReset.ts     # State reset utilities
 │   │   │   ├── migrationRunner.ts # Schema migration runner
-│   │   │   └── migrations/       # 117 versioned SQL migration files
+│   │   │   └── migrations/       # 148 versioned SQL migration files
 │   │   ├── evals/                # Eval runner and scheduler
 │   │   ├── memory/               # Persistent conversational memory
 │   │   │   ├── extraction.ts     # Memory extraction from conversations
@@ -214,11 +211,11 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── moderations.ts        # Content moderation
 │   │   ├── rerank.ts             # Reranking API
 │   │   └── search.ts             # Web search API
-│   ├── mcp-server/               # Built-in MCP server (105 tools, 3 transports: stdio/SSE/streamable-HTTP)
+│   ├── mcp-server/               # Built-in MCP server (109 tools, 3 transports: stdio/SSE/streamable-HTTP)
 │   │   ├── server.ts             # MCP server core (tool registration, scope enforcement)
 │   │   ├── tools/                # Tool implementations (advancedTools, memoryTools, skillTools)
 │   │   ├── schemas/              # Zod input schemas (tools, audit, a2a)
-│   │   ├── scopeEnforcement.ts   # Scope-based access control (31 scopes)
+│   │   ├── scopeEnforcement.ts   # Scope-based access control (33 scopes)
 │   │   ├── audit.ts              # Tool call audit logging
 │   │   ├── runtimeHeartbeat.ts   # MCP runtime heartbeat
 │   │   └── httpTransport.ts      # HTTP transport handler
@@ -269,7 +266,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── i18n/                     # 43-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
-│   ├── frameworks/               # MCP-SERVER.md (105 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
+│   ├── frameworks/               # MCP-SERVER.md (109 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
 │   ├── routing/                  # AUTO-COMBO.md (14-factor scoring), REASONING_REPLAY.md
 │   ├── security/                 # GUARDRAILS.md, COMPLIANCE.md, STEALTH_GUIDE.md, PUBLIC_CREDS.md, ERROR_SANITIZATION.md
 │   ├── guides/                   # USER_GUIDE.md, TROUBLESHOOTING.md, ELECTRON_GUIDE.md, I18N.md
@@ -352,9 +349,9 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 - **A2A** — Agent-to-Agent v0.3 protocol (JSON-RPC 2.0, 6 skills: smart-routing, quota-management, provider-discovery, cost-analysis, health-report, list-capabilities)
 - **ACP** — Agent Communication Protocol registry and manager
 
-### MCP Server (105 Tools)
+### MCP Server (109 Tools)
 
-105 tools across modules: **43 base** (health, combos, quotas, routing, cost, models, cache,
+109 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
 diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool**, **notion**,
 **obsidian**, **localCorpus**, **gamification**, and **plugin** modules. Full per-tool inventory:
 `docs/frameworks/MCP-SERVER.md`.
@@ -397,7 +394,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 8. **ProviderIcon component:** Unified icon system using `@lobehub/icons` (130+ SVG) with PNG fallback and generic icon fallback chain. Used on providers, dashboard, and agents pages.
 
-9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 99 `src/lib/db/` modules with 117 SQL migrations.
+9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 117 `src/lib/db/` modules with 148 SQL migrations.
 
 10. **Upstream headers:** Custom headers merged in executors after default auth; same header name replaces executor value. Forbidden header names in `src/shared/constants/upstreamHeaders.ts`.
 
@@ -441,7 +438,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 4. **Environment variables:** All configuration is in `.env` (from `.env.example`). Key vars: `PORT`, `NEXT_PUBLIC_BASE_URL`, `API_KEY`, `ADMIN_PASSWORD`.
 
-5. **Database layer:** Operations go through `src/lib/db/` modules (117 domain-specific files, 145 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
+5. **Database layer:** Operations go through `src/lib/db/` modules (117 domain-specific files, 148 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
 
 6. **Tests** use Node.js built-in test runner + Vitest. Run `npm test`. Vitest for MCP/autoCombo (`npm run test:vitest`). Playwright for E2E (`npm run test:e2e`). Coverage gate: ratchet vs `quality-baseline.json`, absolute floor 60% statements/lines/functions/branches.
 
@@ -485,7 +482,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 - **339-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
-- **MCP server expanded to 105 tools / 31 scopes** (base + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
+- **MCP server expanded to 109 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
 - **Cloud Agents** (Codex Cloud, Devin, Jules), **Guardrails**, **Evals**, **Webhooks**, **Compliance** frameworks
 - **Embedded services** manager (install/start/stop bundled services from the dashboard)
 - **Prompt compression** (RTK + Caveman codecs) saving up to ~95% tokens on eligible traffic

docs/i18n/az/llm.txt

@@ -4,10 +4,7 @@
 
 ---
 
-
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 339 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (109 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
-
-
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 339 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (105 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -21,7 +18,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 - **Runtime:** Node.js `>=22.0.0 <23 || >=24.0.0 <27`, ES Modules (`"type": "module"`)
 - **Framework:** Next.js 16 (App Router) with TypeScript 6
-- **Database:** SQLite via better-sqlite3 (local, zero-config, 145 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 148 migrations)
 - **State management:** Zustand (client), SQLite (server persistence)
 - **UI:** React 19, Tailwind CSS 4, Recharts for analytics, @lobehub/icons for 130+ provider SVG icons
 - **Auth:** OAuth 2.0 (PKCE) for providers, bcrypt for local user auth
@@ -109,7 +106,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   └── streaming.ts      # SSE streaming for A2A
 │   │   ├── acp/                  # Agent Communication Protocol registry and manager
 │   │   ├── compliance/           # Compliance policy engine
-│   │   ├── db/                   # SQLite database layer (99 modules + migrations)
+│   │   ├── db/                   # SQLite database layer (117 modules + migrations)
 │   │   │   ├── core.ts           # Database initialization, connection, schema
 │   │   │   ├── providers.ts      # Provider connection CRUD
 │   │   │   ├── models.ts         # Model catalog management
@@ -131,7 +128,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   ├── secrets.ts        # Secrets management
 │   │   │   ├── stateReset.ts     # State reset utilities
 │   │   │   ├── migrationRunner.ts # Schema migration runner
-│   │   │   └── migrations/       # 117 versioned SQL migration files
+│   │   │   └── migrations/       # 148 versioned SQL migration files
 │   │   ├── evals/                # Eval runner and scheduler
 │   │   ├── memory/               # Persistent conversational memory
 │   │   │   ├── extraction.ts     # Memory extraction from conversations
@@ -214,11 +211,11 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── moderations.ts        # Content moderation
 │   │   ├── rerank.ts             # Reranking API
 │   │   └── search.ts             # Web search API
-│   ├── mcp-server/               # Built-in MCP server (105 tools, 3 transports: stdio/SSE/streamable-HTTP)
+│   ├── mcp-server/               # Built-in MCP server (109 tools, 3 transports: stdio/SSE/streamable-HTTP)
 │   │   ├── server.ts             # MCP server core (tool registration, scope enforcement)
 │   │   ├── tools/                # Tool implementations (advancedTools, memoryTools, skillTools)
 │   │   ├── schemas/              # Zod input schemas (tools, audit, a2a)
-│   │   ├── scopeEnforcement.ts   # Scope-based access control (31 scopes)
+│   │   ├── scopeEnforcement.ts   # Scope-based access control (33 scopes)
 │   │   ├── audit.ts              # Tool call audit logging
 │   │   ├── runtimeHeartbeat.ts   # MCP runtime heartbeat
 │   │   └── httpTransport.ts      # HTTP transport handler
@@ -269,7 +266,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── i18n/                     # 43-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
-│   ├── frameworks/               # MCP-SERVER.md (105 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
+│   ├── frameworks/               # MCP-SERVER.md (109 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
 │   ├── routing/                  # AUTO-COMBO.md (14-factor scoring), REASONING_REPLAY.md
 │   ├── security/                 # GUARDRAILS.md, COMPLIANCE.md, STEALTH_GUIDE.md, PUBLIC_CREDS.md, ERROR_SANITIZATION.md
 │   ├── guides/                   # USER_GUIDE.md, TROUBLESHOOTING.md, ELECTRON_GUIDE.md, I18N.md
@@ -352,9 +349,9 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 - **A2A** — Agent-to-Agent v0.3 protocol (JSON-RPC 2.0, 6 skills: smart-routing, quota-management, provider-discovery, cost-analysis, health-report, list-capabilities)
 - **ACP** — Agent Communication Protocol registry and manager
 
-### MCP Server (105 Tools)
+### MCP Server (109 Tools)
 
-105 tools across modules: **43 base** (health, combos, quotas, routing, cost, models, cache,
+109 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
 diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool**, **notion**,
 **obsidian**, **localCorpus**, **gamification**, and **plugin** modules. Full per-tool inventory:
 `docs/frameworks/MCP-SERVER.md`.
@@ -397,7 +394,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 8. **ProviderIcon component:** Unified icon system using `@lobehub/icons` (130+ SVG) with PNG fallback and generic icon fallback chain. Used on providers, dashboard, and agents pages.
 
-9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 99 `src/lib/db/` modules with 117 SQL migrations.
+9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 117 `src/lib/db/` modules with 148 SQL migrations.
 
 10. **Upstream headers:** Custom headers merged in executors after default auth; same header name replaces executor value. Forbidden header names in `src/shared/constants/upstreamHeaders.ts`.
 
@@ -441,7 +438,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 4. **Environment variables:** All configuration is in `.env` (from `.env.example`). Key vars: `PORT`, `NEXT_PUBLIC_BASE_URL`, `API_KEY`, `ADMIN_PASSWORD`.
 
-5. **Database layer:** Operations go through `src/lib/db/` modules (117 domain-specific files, 145 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
+5. **Database layer:** Operations go through `src/lib/db/` modules (117 domain-specific files, 148 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
 
 6. **Tests** use Node.js built-in test runner + Vitest. Run `npm test`. Vitest for MCP/autoCombo (`npm run test:vitest`). Playwright for E2E (`npm run test:e2e`). Coverage gate: ratchet vs `quality-baseline.json`, absolute floor 60% statements/lines/functions/branches.
 
@@ -485,7 +482,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 - **339-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
-- **MCP server expanded to 105 tools / 31 scopes** (base + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
+- **MCP server expanded to 109 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
 - **Cloud Agents** (Codex Cloud, Devin, Jules), **Guardrails**, **Evals**, **Webhooks**, **Compliance** frameworks
 - **Embedded services** manager (install/start/stop bundled services from the dashboard)
 - **Prompt compression** (RTK + Caveman codecs) saving up to ~95% tokens on eligible traffic

docs/i18n/bg/llm.txt

@@ -4,10 +4,7 @@
 
 ---
 
-
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 339 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (109 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
-
-
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 339 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (105 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -21,7 +18,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 - **Runtime:** Node.js `>=22.0.0 <23 || >=24.0.0 <27`, ES Modules (`"type": "module"`)
 - **Framework:** Next.js 16 (App Router) with TypeScript 6
-- **Database:** SQLite via better-sqlite3 (local, zero-config, 145 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 148 migrations)
 - **State management:** Zustand (client), SQLite (server persistence)
 - **UI:** React 19, Tailwind CSS 4, Recharts for analytics, @lobehub/icons for 130+ provider SVG icons
 - **Auth:** OAuth 2.0 (PKCE) for providers, bcrypt for local user auth
@@ -109,7 +106,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   └── streaming.ts      # SSE streaming for A2A
 │   │   ├── acp/                  # Agent Communication Protocol registry and manager
 │   │   ├── compliance/           # Compliance policy engine
-│   │   ├── db/                   # SQLite database layer (99 modules + migrations)
+│   │   ├── db/                   # SQLite database layer (117 modules + migrations)
 │   │   │   ├── core.ts           # Database initialization, connection, schema
 │   │   │   ├── providers.ts      # Provider connection CRUD
 │   │   │   ├── models.ts         # Model catalog management
@@ -131,7 +128,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   ├── secrets.ts        # Secrets management
 │   │   │   ├── stateReset.ts     # State reset utilities
 │   │   │   ├── migrationRunner.ts # Schema migration runner
-│   │   │   └── migrations/       # 117 versioned SQL migration files
+│   │   │   └── migrations/       # 148 versioned SQL migration files
 │   │   ├── evals/                # Eval runner and scheduler
 │   │   ├── memory/               # Persistent conversational memory
 │   │   │   ├── extraction.ts     # Memory extraction from conversations
@@ -214,11 +211,11 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── moderations.ts        # Content moderation
 │   │   ├── rerank.ts             # Reranking API
 │   │   └── search.ts             # Web search API
-│   ├── mcp-server/               # Built-in MCP server (105 tools, 3 transports: stdio/SSE/streamable-HTTP)
+│   ├── mcp-server/               # Built-in MCP server (109 tools, 3 transports: stdio/SSE/streamable-HTTP)
 │   │   ├── server.ts             # MCP server core (tool registration, scope enforcement)
 │   │   ├── tools/                # Tool implementations (advancedTools, memoryTools, skillTools)
 │   │   ├── schemas/              # Zod input schemas (tools, audit, a2a)
-│   │   ├── scopeEnforcement.ts   # Scope-based access control (31 scopes)
+│   │   ├── scopeEnforcement.ts   # Scope-based access control (33 scopes)
 │   │   ├── audit.ts              # Tool call audit logging
 │   │   ├── runtimeHeartbeat.ts   # MCP runtime heartbeat
 │   │   └── httpTransport.ts      # HTTP transport handler
@@ -269,7 +266,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── i18n/                     # 43-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
-│   ├── frameworks/               # MCP-SERVER.md (105 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
+│   ├── frameworks/               # MCP-SERVER.md (109 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
 │   ├── routing/                  # AUTO-COMBO.md (14-factor scoring), REASONING_REPLAY.md
 │   ├── security/                 # GUARDRAILS.md, COMPLIANCE.md, STEALTH_GUIDE.md, PUBLIC_CREDS.md, ERROR_SANITIZATION.md
 │   ├── guides/                   # USER_GUIDE.md, TROUBLESHOOTING.md, ELECTRON_GUIDE.md, I18N.md
@@ -352,9 +349,9 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 - **A2A** — Agent-to-Agent v0.3 protocol (JSON-RPC 2.0, 6 skills: smart-routing, quota-management, provider-discovery, cost-analysis, health-report, list-capabilities)
 - **ACP** — Agent Communication Protocol registry and manager
 
-### MCP Server (105 Tools)
+### MCP Server (109 Tools)
 
-105 tools across modules: **43 base** (health, combos, quotas, routing, cost, models, cache,
+109 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
 diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool**, **notion**,
 **obsidian**, **localCorpus**, **gamification**, and **plugin** modules. Full per-tool inventory:
 `docs/frameworks/MCP-SERVER.md`.
@@ -397,7 +394,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 8. **ProviderIcon component:** Unified icon system using `@lobehub/icons` (130+ SVG) with PNG fallback and generic icon fallback chain. Used on providers, dashboard, and agents pages.
 
-9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 99 `src/lib/db/` modules with 117 SQL migrations.
+9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 117 `src/lib/db/` modules with 148 SQL migrations.
 
 10. **Upstream headers:** Custom headers merged in executors after default auth; same header name replaces executor value. Forbidden header names in `src/shared/constants/upstreamHeaders.ts`.
 
@@ -441,7 +438,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 4. **Environment variables:** All configuration is in `.env` (from `.env.example`). Key vars: `PORT`, `NEXT_PUBLIC_BASE_URL`, `API_KEY`, `ADMIN_PASSWORD`.
 
-5. **Database layer:** Operations go through `src/lib/db/` modules (117 domain-specific files, 145 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
+5. **Database layer:** Operations go through `src/lib/db/` modules (117 domain-specific files, 148 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
 
 6. **Tests** use Node.js built-in test runner + Vitest. Run `npm test`. Vitest for MCP/autoCombo (`npm run test:vitest`). Playwright for E2E (`npm run test:e2e`). Coverage gate: ratchet vs `quality-baseline.json`, absolute floor 60% statements/lines/functions/branches.
 
@@ -485,7 +482,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 - **339-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
-- **MCP server expanded to 105 tools / 31 scopes** (base + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
+- **MCP server expanded to 109 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
 - **Cloud Agents** (Codex Cloud, Devin, Jules), **Guardrails**, **Evals**, **Webhooks**, **Compliance** frameworks
 - **Embedded services** manager (install/start/stop bundled services from the dashboard)
 - **Prompt compression** (RTK + Caveman codecs) saving up to ~95% tokens on eligible traffic

docs/i18n/bn/llm.txt

@@ -4,10 +4,7 @@
 
 ---
 
-
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 339 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (109 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
-
-
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 339 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (105 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -21,7 +18,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 - **Runtime:** Node.js `>=22.0.0 <23 || >=24.0.0 <27`, ES Modules (`"type": "module"`)
 - **Framework:** Next.js 16 (App Router) with TypeScript 6
-- **Database:** SQLite via better-sqlite3 (local, zero-config, 145 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 148 migrations)
 - **State management:** Zustand (client), SQLite (server persistence)
 - **UI:** React 19, Tailwind CSS 4, Recharts for analytics, @lobehub/icons for 130+ provider SVG icons
 - **Auth:** OAuth 2.0 (PKCE) for providers, bcrypt for local user auth
@@ -109,7 +106,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   └── streaming.ts      # SSE streaming for A2A
 │   │   ├── acp/                  # Agent Communication Protocol registry and manager
 │   │   ├── compliance/           # Compliance policy engine
-│   │   ├── db/                   # SQLite database layer (99 modules + migrations)
+│   │   ├── db/                   # SQLite database layer (117 modules + migrations)
 │   │   │   ├── core.ts           # Database initialization, connection, schema
 │   │   │   ├── providers.ts      # Provider connection CRUD
 │   │   │   ├── models.ts         # Model catalog management
@@ -131,7 +128,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   ├── secrets.ts        # Secrets management
 │   │   │   ├── stateReset.ts     # State reset utilities
 │   │   │   ├── migrationRunner.ts # Schema migration runner
-│   │   │   └── migrations/       # 117 versioned SQL migration files
+│   │   │   └── migrations/       # 148 versioned SQL migration files
 │   │   ├── evals/                # Eval runner and scheduler
 │   │   ├── memory/               # Persistent conversational memory
 │   │   │   ├── extraction.ts     # Memory extraction from conversations
@@ -214,11 +211,11 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── moderations.ts        # Content moderation
 │   │   ├── rerank.ts             # Reranking API
 │   │   └── search.ts             # Web search API
-│   ├── mcp-server/               # Built-in MCP server (105 tools, 3 transports: stdio/SSE/streamable-HTTP)
+│   ├── mcp-server/               # Built-in MCP server (109 tools, 3 transports: stdio/SSE/streamable-HTTP)
 │   │   ├── server.ts             # MCP server core (tool registration, scope enforcement)
 │   │   ├── tools/                # Tool implementations (advancedTools, memoryTools, skillTools)
 │   │   ├── schemas/              # Zod input schemas (tools, audit, a2a)
-│   │   ├── scopeEnforcement.ts   # Scope-based access control (31 scopes)
+│   │   ├── scopeEnforcement.ts   # Scope-based access control (33 scopes)
 │   │   ├── audit.ts              # Tool call audit logging
 │   │   ├── runtimeHeartbeat.ts   # MCP runtime heartbeat
 │   │   └── httpTransport.ts      # HTTP transport handler
@@ -269,7 +266,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── i18n/                     # 43-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
-│   ├── frameworks/               # MCP-SERVER.md (105 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
+│   ├── frameworks/               # MCP-SERVER.md (109 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
 │   ├── routing/                  # AUTO-COMBO.md (14-factor scoring), REASONING_REPLAY.md
 │   ├── security/                 # GUARDRAILS.md, COMPLIANCE.md, STEALTH_GUIDE.md, PUBLIC_CREDS.md, ERROR_SANITIZATION.md
 │   ├── guides/                   # USER_GUIDE.md, TROUBLESHOOTING.md, ELECTRON_GUIDE.md, I18N.md
@@ -352,9 +349,9 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 - **A2A** — Agent-to-Agent v0.3 protocol (JSON-RPC 2.0, 6 skills: smart-routing, quota-management, provider-discovery, cost-analysis, health-report, list-capabilities)
 - **ACP** — Agent Communication Protocol registry and manager
 
-### MCP Server (105 Tools)
+### MCP Server (109 Tools)
 
-105 tools across modules: **43 base** (health, combos, quotas, routing, cost, models, cache,
+109 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
 diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool**, **notion**,
 **obsidian**, **localCorpus**, **gamification**, and **plugin** modules. Full per-tool inventory:
 `docs/frameworks/MCP-SERVER.md`.
@@ -397,7 +394,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 8. **ProviderIcon component:** Unified icon system using `@lobehub/icons` (130+ SVG) with PNG fallback and generic icon fallback chain. Used on providers, dashboard, and agents pages.
 
-9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 99 `src/lib/db/` modules with 117 SQL migrations.
+9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 117 `src/lib/db/` modules with 148 SQL migrations.
 
 10. **Upstream headers:** Custom headers merged in executors after default auth; same header name replaces executor value. Forbidden header names in `src/shared/constants/upstreamHeaders.ts`.
 
@@ -441,7 +438,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 4. **Environment variables:** All configuration is in `.env` (from `.env.example`). Key vars: `PORT`, `NEXT_PUBLIC_BASE_URL`, `API_KEY`, `ADMIN_PASSWORD`.
 
-5. **Database layer:** Operations go through `src/lib/db/` modules (117 domain-specific files, 145 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
+5. **Database layer:** Operations go through `src/lib/db/` modules (117 domain-specific files, 148 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
 
 6. **Tests** use Node.js built-in test runner + Vitest. Run `npm test`. Vitest for MCP/autoCombo (`npm run test:vitest`). Playwright for E2E (`npm run test:e2e`). Coverage gate: ratchet vs `quality-baseline.json`, absolute floor 60% statements/lines/functions/branches.
 
@@ -485,7 +482,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 - **339-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
-- **MCP server expanded to 105 tools / 31 scopes** (base + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
+- **MCP server expanded to 109 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
 - **Cloud Agents** (Codex Cloud, Devin, Jules), **Guardrails**, **Evals**, **Webhooks**, **Compliance** frameworks
 - **Embedded services** manager (install/start/stop bundled services from the dashboard)
 - **Prompt compression** (RTK + Caveman codecs) saving up to ~95% tokens on eligible traffic

docs/i18n/cs/llm.txt

@@ -4,10 +4,7 @@
 
 ---
 
-
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 339 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (109 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
-
-
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 339 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (105 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -21,7 +18,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 - **Runtime:** Node.js `>=22.0.0 <23 || >=24.0.0 <27`, ES Modules (`"type": "module"`)
 - **Framework:** Next.js 16 (App Router) with TypeScript 6
-- **Database:** SQLite via better-sqlite3 (local, zero-config, 145 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 148 migrations)
 - **State management:** Zustand (client), SQLite (server persistence)
 - **UI:** React 19, Tailwind CSS 4, Recharts for analytics, @lobehub/icons for 130+ provider SVG icons
 - **Auth:** OAuth 2.0 (PKCE) for providers, bcrypt for local user auth
@@ -109,7 +106,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   └── streaming.ts      # SSE streaming for A2A
 │   │   ├── acp/                  # Agent Communication Protocol registry and manager
 │   │   ├── compliance/           # Compliance policy engine
-│   │   ├── db/                   # SQLite database layer (99 modules + migrations)
+│   │   ├── db/                   # SQLite database layer (117 modules + migrations)
 │   │   │   ├── core.ts           # Database initialization, connection, schema
 │   │   │   ├── providers.ts      # Provider connection CRUD
 │   │   │   ├── models.ts         # Model catalog management
@@ -131,7 +128,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   ├── secrets.ts        # Secrets management
 │   │   │   ├── stateReset.ts     # State reset utilities
 │   │   │   ├── migrationRunner.ts # Schema migration runner
-│   │   │   └── migrations/       # 117 versioned SQL migration files
+│   │   │   └── migrations/       # 148 versioned SQL migration files
 │   │   ├── evals/                # Eval runner and scheduler
 │   │   ├── memory/               # Persistent conversational memory
 │   │   │   ├── extraction.ts     # Memory extraction from conversations
@@ -214,11 +211,11 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── moderations.ts        # Content moderation
 │   │   ├── rerank.ts             # Reranking API
 │   │   └── search.ts             # Web search API
-│   ├── mcp-server/               # Built-in MCP server (105 tools, 3 transports: stdio/SSE/streamable-HTTP)
+│   ├── mcp-server/               # Built-in MCP server (109 tools, 3 transports: stdio/SSE/streamable-HTTP)
 │   │   ├── server.ts             # MCP server core (tool registration, scope enforcement)
 │   │   ├── tools/                # Tool implementations (advancedTools, memoryTools, skillTools)
 │   │   ├── schemas/              # Zod input schemas (tools, audit, a2a)
-│   │   ├── scopeEnforcement.ts   # Scope-based access control (31 scopes)
+│   │   ├── scopeEnforcement.ts   # Scope-based access control (33 scopes)
 │   │   ├── audit.ts              # Tool call audit logging
 │   │   ├── runtimeHeartbeat.ts   # MCP runtime heartbeat
 │   │   └── httpTransport.ts      # HTTP transport handler
@@ -269,7 +266,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── i18n/                     # 43-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
-│   ├── frameworks/               # MCP-SERVER.md (105 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
+│   ├── frameworks/               # MCP-SERVER.md (109 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
 │   ├── routing/                  # AUTO-COMBO.md (14-factor scoring), REASONING_REPLAY.md
 │   ├── security/                 # GUARDRAILS.md, COMPLIANCE.md, STEALTH_GUIDE.md, PUBLIC_CREDS.md, ERROR_SANITIZATION.md
 │   ├── guides/                   # USER_GUIDE.md, TROUBLESHOOTING.md, ELECTRON_GUIDE.md, I18N.md
@@ -352,9 +349,9 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 - **A2A** — Agent-to-Agent v0.3 protocol (JSON-RPC 2.0, 6 skills: smart-routing, quota-management, provider-discovery, cost-analysis, health-report, list-capabilities)
 - **ACP** — Agent Communication Protocol registry and manager
 
-### MCP Server (105 Tools)
+### MCP Server (109 Tools)
 
-105 tools across modules: **43 base** (health, combos, quotas, routing, cost, models, cache,
+109 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
 diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool**, **notion**,
 **obsidian**, **localCorpus**, **gamification**, and **plugin** modules. Full per-tool inventory:
 `docs/frameworks/MCP-SERVER.md`.
@@ -397,7 +394,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 8. **ProviderIcon component:** Unified icon system using `@lobehub/icons` (130+ SVG) with PNG fallback and generic icon fallback chain. Used on providers, dashboard, and agents pages.
 
-9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 99 `src/lib/db/` modules with 117 SQL migrations.
+9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 117 `src/lib/db/` modules with 148 SQL migrations.
 
 10. **Upstream headers:** Custom headers merged in executors after default auth; same header name replaces executor value. Forbidden header names in `src/shared/constants/upstreamHeaders.ts`.
 
@@ -441,7 +438,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 4. **Environment variables:** All configuration is in `.env` (from `.env.example`). Key vars: `PORT`, `NEXT_PUBLIC_BASE_URL`, `API_KEY`, `ADMIN_PASSWORD`.
 
-5. **Database layer:** Operations go through `src/lib/db/` modules (117 domain-specific files, 145 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
+5. **Database layer:** Operations go through `src/lib/db/` modules (117 domain-specific files, 148 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
 
 6. **Tests** use Node.js built-in test runner + Vitest. Run `npm test`. Vitest for MCP/autoCombo (`npm run test:vitest`). Playwright for E2E (`npm run test:e2e`). Coverage gate: ratchet vs `quality-baseline.json`, absolute floor 60% statements/lines/functions/branches.
 
@@ -485,7 +482,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 - **339-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
-- **MCP server expanded to 105 tools / 31 scopes** (base + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
+- **MCP server expanded to 109 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
 - **Cloud Agents** (Codex Cloud, Devin, Jules), **Guardrails**, **Evals**, **Webhooks**, **Compliance** frameworks
 - **Embedded services** manager (install/start/stop bundled services from the dashboard)
 - **Prompt compression** (RTK + Caveman codecs) saving up to ~95% tokens on eligible traffic

docs/i18n/da/llm.txt

@@ -4,10 +4,7 @@
 
 ---
 
-
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 339 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (109 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
-
-
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 339 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (105 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -21,7 +18,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 - **Runtime:** Node.js `>=22.0.0 <23 || >=24.0.0 <27`, ES Modules (`"type": "module"`)
 - **Framework:** Next.js 16 (App Router) with TypeScript 6
-- **Database:** SQLite via better-sqlite3 (local, zero-config, 145 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 148 migrations)
 - **State management:** Zustand (client), SQLite (server persistence)
 - **UI:** React 19, Tailwind CSS 4, Recharts for analytics, @lobehub/icons for 130+ provider SVG icons
 - **Auth:** OAuth 2.0 (PKCE) for providers, bcrypt for local user auth
@@ -109,7 +106,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   └── streaming.ts      # SSE streaming for A2A
 │   │   ├── acp/                  # Agent Communication Protocol registry and manager
 │   │   ├── compliance/           # Compliance policy engine
-│   │   ├── db/                   # SQLite database layer (99 modules + migrations)
+│   │   ├── db/                   # SQLite database layer (117 modules + migrations)
 │   │   │   ├── core.ts           # Database initialization, connection, schema
 │   │   │   ├── providers.ts      # Provider connection CRUD
 │   │   │   ├── models.ts         # Model catalog management
@@ -131,7 +128,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   ├── secrets.ts        # Secrets management
 │   │   │   ├── stateReset.ts     # State reset utilities
 │   │   │   ├── migrationRunner.ts # Schema migration runner
-│   │   │   └── migrations/       # 117 versioned SQL migration files
+│   │   │   └── migrations/       # 148 versioned SQL migration files
 │   │   ├── evals/                # Eval runner and scheduler
 │   │   ├── memory/               # Persistent conversational memory
 │   │   │   ├── extraction.ts     # Memory extraction from conversations
@@ -214,11 +211,11 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── moderations.ts        # Content moderation
 │   │   ├── rerank.ts             # Reranking API
 │   │   └── search.ts             # Web search API
-│   ├── mcp-server/               # Built-in MCP server (105 tools, 3 transports: stdio/SSE/streamable-HTTP)
+│   ├── mcp-server/               # Built-in MCP server (109 tools, 3 transports: stdio/SSE/streamable-HTTP)
 │   │   ├── server.ts             # MCP server core (tool registration, scope enforcement)
 │   │   ├── tools/                # Tool implementations (advancedTools, memoryTools, skillTools)
 │   │   ├── schemas/              # Zod input schemas (tools, audit, a2a)
-│   │   ├── scopeEnforcement.ts   # Scope-based access control (31 scopes)
+│   │   ├── scopeEnforcement.ts   # Scope-based access control (33 scopes)
 │   │   ├── audit.ts              # Tool call audit logging
 │   │   ├── runtimeHeartbeat.ts   # MCP runtime heartbeat
 │   │   └── httpTransport.ts      # HTTP transport handler
@@ -269,7 +266,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── i18n/                     # 43-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
-│   ├── frameworks/               # MCP-SERVER.md (105 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
+│   ├── frameworks/               # MCP-SERVER.md (109 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
 │   ├── routing/                  # AUTO-COMBO.md (14-factor scoring), REASONING_REPLAY.md
 │   ├── security/                 # GUARDRAILS.md, COMPLIANCE.md, STEALTH_GUIDE.md, PUBLIC_CREDS.md, ERROR_SANITIZATION.md
 │   ├── guides/                   # USER_GUIDE.md, TROUBLESHOOTING.md, ELECTRON_GUIDE.md, I18N.md
@@ -352,9 +349,9 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 - **A2A** — Agent-to-Agent v0.3 protocol (JSON-RPC 2.0, 6 skills: smart-routing, quota-management, provider-discovery, cost-analysis, health-report, list-capabilities)
 - **ACP** — Agent Communication Protocol registry and manager
 
-### MCP Server (105 Tools)
+### MCP Server (109 Tools)
 
-105 tools across modules: **43 base** (health, combos, quotas, routing, cost, models, cache,
+109 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
 diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool**, **notion**,
 **obsidian**, **localCorpus**, **gamification**, and **plugin** modules. Full per-tool inventory:
 `docs/frameworks/MCP-SERVER.md`.
@@ -397,7 +394,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 8. **ProviderIcon component:** Unified icon system using `@lobehub/icons` (130+ SVG) with PNG fallback and generic icon fallback chain. Used on providers, dashboard, and agents pages.
 
-9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 99 `src/lib/db/` modules with 117 SQL migrations.
+9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 117 `src/lib/db/` modules with 148 SQL migrations.
 
 10. **Upstream headers:** Custom headers merged in executors after default auth; same header name replaces executor value. Forbidden header names in `src/shared/constants/upstreamHeaders.ts`.
 
@@ -441,7 +438,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 4. **Environment variables:** All configuration is in `.env` (from `.env.example`). Key vars: `PORT`, `NEXT_PUBLIC_BASE_URL`, `API_KEY`, `ADMIN_PASSWORD`.
 
-5. **Database layer:** Operations go through `src/lib/db/` modules (117 domain-specific files, 145 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
+5. **Database layer:** Operations go through `src/lib/db/` modules (117 domain-specific files, 148 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
 
 6. **Tests** use Node.js built-in test runner + Vitest. Run `npm test`. Vitest for MCP/autoCombo (`npm run test:vitest`). Playwright for E2E (`npm run test:e2e`). Coverage gate: ratchet vs `quality-baseline.json`, absolute floor 60% statements/lines/functions/branches.
 
@@ -485,7 +482,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 - **339-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
-- **MCP server expanded to 105 tools / 31 scopes** (base + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
+- **MCP server expanded to 109 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
 - **Cloud Agents** (Codex Cloud, Devin, Jules), **Guardrails**, **Evals**, **Webhooks**, **Compliance** frameworks
 - **Embedded services** manager (install/start/stop bundled services from the dashboard)
 - **Prompt compression** (RTK + Caveman codecs) saving up to ~95% tokens on eligible traffic

docs/i18n/de/llm.txt

@@ -4,10 +4,7 @@
 
 ---
 
-
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 339 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (109 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
-
-
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 339 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (105 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -21,7 +18,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 - **Runtime:** Node.js `>=22.0.0 <23 || >=24.0.0 <27`, ES Modules (`"type": "module"`)
 - **Framework:** Next.js 16 (App Router) with TypeScript 6
-- **Database:** SQLite via better-sqlite3 (local, zero-config, 145 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 148 migrations)
 - **State management:** Zustand (client), SQLite (server persistence)
 - **UI:** React 19, Tailwind CSS 4, Recharts for analytics, @lobehub/icons for 130+ provider SVG icons
 - **Auth:** OAuth 2.0 (PKCE) for providers, bcrypt for local user auth
@@ -109,7 +106,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   └── streaming.ts      # SSE streaming for A2A
 │   │   ├── acp/                  # Agent Communication Protocol registry and manager
 │   │   ├── compliance/           # Compliance policy engine
-│   │   ├── db/                   # SQLite database layer (99 modules + migrations)
+│   │   ├── db/                   # SQLite database layer (117 modules + migrations)
 │   │   │   ├── core.ts           # Database initialization, connection, schema
 │   │   │   ├── providers.ts      # Provider connection CRUD
 │   │   │   ├── models.ts         # Model catalog management
@@ -131,7 +128,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   ├── secrets.ts        # Secrets management
 │   │   │   ├── stateReset.ts     # State reset utilities
 │   │   │   ├── migrationRunner.ts # Schema migration runner
-│   │   │   └── migrations/       # 117 versioned SQL migration files
+│   │   │   └── migrations/       # 148 versioned SQL migration files
 │   │   ├── evals/                # Eval runner and scheduler
 │   │   ├── memory/               # Persistent conversational memory
 │   │   │   ├── extraction.ts     # Memory extraction from conversations
@@ -214,11 +211,11 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── moderations.ts        # Content moderation
 │   │   ├── rerank.ts             # Reranking API
 │   │   └── search.ts             # Web search API
-│   ├── mcp-server/               # Built-in MCP server (105 tools, 3 transports: stdio/SSE/streamable-HTTP)
+│   ├── mcp-server/               # Built-in MCP server (109 tools, 3 transports: stdio/SSE/streamable-HTTP)
 │   │   ├── server.ts             # MCP server core (tool registration, scope enforcement)
 │   │   ├── tools/                # Tool implementations (advancedTools, memoryTools, skillTools)
 │   │   ├── schemas/              # Zod input schemas (tools, audit, a2a)
-│   │   ├── scopeEnforcement.ts   # Scope-based access control (31 scopes)
+│   │   ├── scopeEnforcement.ts   # Scope-based access control (33 scopes)
 │   │   ├── audit.ts              # Tool call audit logging
 │   │   ├── runtimeHeartbeat.ts   # MCP runtime heartbeat
 │   │   └── httpTransport.ts      # HTTP transport handler
@@ -269,7 +266,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── i18n/                     # 43-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
-│   ├── frameworks/               # MCP-SERVER.md (105 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
+│   ├── frameworks/               # MCP-SERVER.md (109 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
 │   ├── routing/                  # AUTO-COMBO.md (14-factor scoring), REASONING_REPLAY.md
 │   ├── security/                 # GUARDRAILS.md, COMPLIANCE.md, STEALTH_GUIDE.md, PUBLIC_CREDS.md, ERROR_SANITIZATION.md
 │   ├── guides/                   # USER_GUIDE.md, TROUBLESHOOTING.md, ELECTRON_GUIDE.md, I18N.md
@@ -352,9 +349,9 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 - **A2A** — Agent-to-Agent v0.3 protocol (JSON-RPC 2.0, 6 skills: smart-routing, quota-management, provider-discovery, cost-analysis, health-report, list-capabilities)
 - **ACP** — Agent Communication Protocol registry and manager
 
-### MCP Server (105 Tools)
+### MCP Server (109 Tools)
 
-105 tools across modules: **43 base** (health, combos, quotas, routing, cost, models, cache,
+109 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
 diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool**, **notion**,
 **obsidian**, **localCorpus**, **gamification**, and **plugin** modules. Full per-tool inventory:
 `docs/frameworks/MCP-SERVER.md`.
@@ -397,7 +394,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 8. **ProviderIcon component:** Unified icon system using `@lobehub/icons` (130+ SVG) with PNG fallback and generic icon fallback chain. Used on providers, dashboard, and agents pages.
 
-9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 99 `src/lib/db/` modules with 117 SQL migrations.
+9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 117 `src/lib/db/` modules with 148 SQL migrations.
 
 10. **Upstream headers:** Custom headers merged in executors after default auth; same header name replaces executor value. Forbidden header names in `src/shared/constants/upstreamHeaders.ts`.
 
@@ -441,7 +438,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 4. **Environment variables:** All configuration is in `.env` (from `.env.example`). Key vars: `PORT`, `NEXT_PUBLIC_BASE_URL`, `API_KEY`, `ADMIN_PASSWORD`.
 
-5. **Database layer:** Operations go through `src/lib/db/` modules (117 domain-specific files, 145 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
+5. **Database layer:** Operations go through `src/lib/db/` modules (117 domain-specific files, 148 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
 
 6. **Tests** use Node.js built-in test runner + Vitest. Run `npm test`. Vitest for MCP/autoCombo (`npm run test:vitest`). Playwright for E2E (`npm run test:e2e`). Coverage gate: ratchet vs `quality-baseline.json`, absolute floor 60% statements/lines/functions/branches.
 
@@ -485,7 +482,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 - **339-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
-- **MCP server expanded to 105 tools / 31 scopes** (base + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
+- **MCP server expanded to 109 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
 - **Cloud Agents** (Codex Cloud, Devin, Jules), **Guardrails**, **Evals**, **Webhooks**, **Compliance** frameworks
 - **Embedded services** manager (install/start/stop bundled services from the dashboard)
 - **Prompt compression** (RTK + Caveman codecs) saving up to ~95% tokens on eligible traffic

docs/i18n/es/llm.txt

@@ -4,10 +4,7 @@
 
 ---
 
-
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 339 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (109 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
-
-
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 339 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (105 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -21,7 +18,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 - **Runtime:** Node.js `>=22.0.0 <23 || >=24.0.0 <27`, ES Modules (`"type": "module"`)
 - **Framework:** Next.js 16 (App Router) with TypeScript 6
-- **Database:** SQLite via better-sqlite3 (local, zero-config, 145 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 148 migrations)
 - **State management:** Zustand (client), SQLite (server persistence)
 - **UI:** React 19, Tailwind CSS 4, Recharts for analytics, @lobehub/icons for 130+ provider SVG icons
 - **Auth:** OAuth 2.0 (PKCE) for providers, bcrypt for local user auth
@@ -109,7 +106,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   └── streaming.ts      # SSE streaming for A2A
 │   │   ├── acp/                  # Agent Communication Protocol registry and manager
 │   │   ├── compliance/           # Compliance policy engine
-│   │   ├── db/                   # SQLite database layer (99 modules + migrations)
+│   │   ├── db/                   # SQLite database layer (117 modules + migrations)
 │   │   │   ├── core.ts           # Database initialization, connection, schema
 │   │   │   ├── providers.ts      # Provider connection CRUD
 │   │   │   ├── models.ts         # Model catalog management
@@ -131,7 +128,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   ├── secrets.ts        # Secrets management
 │   │   │   ├── stateReset.ts     # State reset utilities
 │   │   │   ├── migrationRunner.ts # Schema migration runner
-│   │   │   └── migrations/       # 117 versioned SQL migration files
+│   │   │   └── migrations/       # 148 versioned SQL migration files
 │   │   ├── evals/                # Eval runner and scheduler
 │   │   ├── memory/               # Persistent conversational memory
 │   │   │   ├── extraction.ts     # Memory extraction from conversations
@@ -214,11 +211,11 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── moderations.ts        # Content moderation
 │   │   ├── rerank.ts             # Reranking API
 │   │   └── search.ts             # Web search API
-│   ├── mcp-server/               # Built-in MCP server (105 tools, 3 transports: stdio/SSE/streamable-HTTP)
+│   ├── mcp-server/               # Built-in MCP server (109 tools, 3 transports: stdio/SSE/streamable-HTTP)
 │   │   ├── server.ts             # MCP server core (tool registration, scope enforcement)
 │   │   ├── tools/                # Tool implementations (advancedTools, memoryTools, skillTools)
 │   │   ├── schemas/              # Zod input schemas (tools, audit, a2a)
-│   │   ├── scopeEnforcement.ts   # Scope-based access control (31 scopes)
+│   │   ├── scopeEnforcement.ts   # Scope-based access control (33 scopes)
 │   │   ├── audit.ts              # Tool call audit logging
 │   │   ├── runtimeHeartbeat.ts   # MCP runtime heartbeat
 │   │   └── httpTransport.ts      # HTTP transport handler
@@ -269,7 +266,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── i18n/                     # 43-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
-│   ├── frameworks/               # MCP-SERVER.md (105 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
+│   ├── frameworks/               # MCP-SERVER.md (109 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
 │   ├── routing/                  # AUTO-COMBO.md (14-factor scoring), REASONING_REPLAY.md
 │   ├── security/                 # GUARDRAILS.md, COMPLIANCE.md, STEALTH_GUIDE.md, PUBLIC_CREDS.md, ERROR_SANITIZATION.md
 │   ├── guides/                   # USER_GUIDE.md, TROUBLESHOOTING.md, ELECTRON_GUIDE.md, I18N.md
@@ -352,9 +349,9 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 - **A2A** — Agent-to-Agent v0.3 protocol (JSON-RPC 2.0, 6 skills: smart-routing, quota-management, provider-discovery, cost-analysis, health-report, list-capabilities)
 - **ACP** — Agent Communication Protocol registry and manager
 
-### MCP Server (105 Tools)
+### MCP Server (109 Tools)
 
-105 tools across modules: **43 base** (health, combos, quotas, routing, cost, models, cache,
+109 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
 diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool**, **notion**,
 **obsidian**, **localCorpus**, **gamification**, and **plugin** modules. Full per-tool inventory:
 `docs/frameworks/MCP-SERVER.md`.
@@ -397,7 +394,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 8. **ProviderIcon component:** Unified icon system using `@lobehub/icons` (130+ SVG) with PNG fallback and generic icon fallback chain. Used on providers, dashboard, and agents pages.
 
-9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 99 `src/lib/db/` modules with 117 SQL migrations.
+9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 117 `src/lib/db/` modules with 148 SQL migrations.
 
 10. **Upstream headers:** Custom headers merged in executors after default auth; same header name replaces executor value. Forbidden header names in `src/shared/constants/upstreamHeaders.ts`.
 
@@ -441,7 +438,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 4. **Environment variables:** All configuration is in `.env` (from `.env.example`). Key vars: `PORT`, `NEXT_PUBLIC_BASE_URL`, `API_KEY`, `ADMIN_PASSWORD`.
 
-5. **Database layer:** Operations go through `src/lib/db/` modules (117 domain-specific files, 145 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
+5. **Database layer:** Operations go through `src/lib/db/` modules (117 domain-specific files, 148 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
 
 6. **Tests** use Node.js built-in test runner + Vitest. Run `npm test`. Vitest for MCP/autoCombo (`npm run test:vitest`). Playwright for E2E (`npm run test:e2e`). Coverage gate: ratchet vs `quality-baseline.json`, absolute floor 60% statements/lines/functions/branches.
 
@@ -485,7 +482,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 - **339-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
-- **MCP server expanded to 105 tools / 31 scopes** (base + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
+- **MCP server expanded to 109 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
 - **Cloud Agents** (Codex Cloud, Devin, Jules), **Guardrails**, **Evals**, **Webhooks**, **Compliance** frameworks
 - **Embedded services** manager (install/start/stop bundled services from the dashboard)
 - **Prompt compression** (RTK + Caveman codecs) saving up to ~95% tokens on eligible traffic

docs/i18n/fa/llm.txt

@@ -4,10 +4,7 @@
 
 ---
 
-
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 339 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (109 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
-
-
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 339 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (105 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -21,7 +18,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 - **Runtime:** Node.js `>=22.0.0 <23 || >=24.0.0 <27`, ES Modules (`"type": "module"`)
 - **Framework:** Next.js 16 (App Router) with TypeScript 6
-- **Database:** SQLite via better-sqlite3 (local, zero-config, 145 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 148 migrations)
 - **State management:** Zustand (client), SQLite (server persistence)
 - **UI:** React 19, Tailwind CSS 4, Recharts for analytics, @lobehub/icons for 130+ provider SVG icons
 - **Auth:** OAuth 2.0 (PKCE) for providers, bcrypt for local user auth
@@ -109,7 +106,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   └── streaming.ts      # SSE streaming for A2A
 │   │   ├── acp/                  # Agent Communication Protocol registry and manager
 │   │   ├── compliance/           # Compliance policy engine
-│   │   ├── db/                   # SQLite database layer (99 modules + migrations)
+│   │   ├── db/                   # SQLite database layer (117 modules + migrations)
 │   │   │   ├── core.ts           # Database initialization, connection, schema
 │   │   │   ├── providers.ts      # Provider connection CRUD
 │   │   │   ├── models.ts         # Model catalog management
@@ -131,7 +128,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   ├── secrets.ts        # Secrets management
 │   │   │   ├── stateReset.ts     # State reset utilities
 │   │   │   ├── migrationRunner.ts # Schema migration runner
-│   │   │   └── migrations/       # 117 versioned SQL migration files
+│   │   │   └── migrations/       # 148 versioned SQL migration files
 │   │   ├── evals/                # Eval runner and scheduler
 │   │   ├── memory/               # Persistent conversational memory
 │   │   │   ├── extraction.ts     # Memory extraction from conversations
@@ -214,11 +211,11 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── moderations.ts        # Content moderation
 │   │   ├── rerank.ts             # Reranking API
 │   │   └── search.ts             # Web search API
-│   ├── mcp-server/               # Built-in MCP server (105 tools, 3 transports: stdio/SSE/streamable-HTTP)
+│   ├── mcp-server/               # Built-in MCP server (109 tools, 3 transports: stdio/SSE/streamable-HTTP)
 │   │   ├── server.ts             # MCP server core (tool registration, scope enforcement)
 │   │   ├── tools/                # Tool implementations (advancedTools, memoryTools, skillTools)
 │   │   ├── schemas/              # Zod input schemas (tools, audit, a2a)
-│   │   ├── scopeEnforcement.ts   # Scope-based access control (31 scopes)
+│   │   ├── scopeEnforcement.ts   # Scope-based access control (33 scopes)
 │   │   ├── audit.ts              # Tool call audit logging
 │   │   ├── runtimeHeartbeat.ts   # MCP runtime heartbeat
 │   │   └── httpTransport.ts      # HTTP transport handler
@@ -269,7 +266,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── i18n/                     # 43-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
-│   ├── frameworks/               # MCP-SERVER.md (105 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
+│   ├── frameworks/               # MCP-SERVER.md (109 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
 │   ├── routing/                  # AUTO-COMBO.md (14-factor scoring), REASONING_REPLAY.md
 │   ├── security/                 # GUARDRAILS.md, COMPLIANCE.md, STEALTH_GUIDE.md, PUBLIC_CREDS.md, ERROR_SANITIZATION.md
 │   ├── guides/                   # USER_GUIDE.md, TROUBLESHOOTING.md, ELECTRON_GUIDE.md, I18N.md
@@ -352,9 +349,9 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 - **A2A** — Agent-to-Agent v0.3 protocol (JSON-RPC 2.0, 6 skills: smart-routing, quota-management, provider-discovery, cost-analysis, health-report, list-capabilities)
 - **ACP** — Agent Communication Protocol registry and manager
 
-### MCP Server (105 Tools)
+### MCP Server (109 Tools)
 
-105 tools across modules: **43 base** (health, combos, quotas, routing, cost, models, cache,
+109 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
 diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool**, **notion**,
 **obsidian**, **localCorpus**, **gamification**, and **plugin** modules. Full per-tool inventory:
 `docs/frameworks/MCP-SERVER.md`.
@@ -397,7 +394,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 8. **ProviderIcon component:** Unified icon system using `@lobehub/icons` (130+ SVG) with PNG fallback and generic icon fallback chain. Used on providers, dashboard, and agents pages.
 
-9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 99 `src/lib/db/` modules with 117 SQL migrations.
+9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 117 `src/lib/db/` modules with 148 SQL migrations.
 
 10. **Upstream headers:** Custom headers merged in executors after default auth; same header name replaces executor value. Forbidden header names in `src/shared/constants/upstreamHeaders.ts`.
 
@@ -441,7 +438,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 4. **Environment variables:** All configuration is in `.env` (from `.env.example`). Key vars: `PORT`, `NEXT_PUBLIC_BASE_URL`, `API_KEY`, `ADMIN_PASSWORD`.
 
-5. **Database layer:** Operations go through `src/lib/db/` modules (117 domain-specific files, 145 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
+5. **Database layer:** Operations go through `src/lib/db/` modules (117 domain-specific files, 148 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
 
 6. **Tests** use Node.js built-in test runner + Vitest. Run `npm test`. Vitest for MCP/autoCombo (`npm run test:vitest`). Playwright for E2E (`npm run test:e2e`). Coverage gate: ratchet vs `quality-baseline.json`, absolute floor 60% statements/lines/functions/branches.
 
@@ -485,7 +482,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 - **339-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
-- **MCP server expanded to 105 tools / 31 scopes** (base + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
+- **MCP server expanded to 109 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
 - **Cloud Agents** (Codex Cloud, Devin, Jules), **Guardrails**, **Evals**, **Webhooks**, **Compliance** frameworks
 - **Embedded services** manager (install/start/stop bundled services from the dashboard)
 - **Prompt compression** (RTK + Caveman codecs) saving up to ~95% tokens on eligible traffic

docs/i18n/fi/llm.txt

@@ -4,10 +4,7 @@
 
 ---
 
-
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 339 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (109 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
-
-
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 339 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (105 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -21,7 +18,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 - **Runtime:** Node.js `>=22.0.0 <23 || >=24.0.0 <27`, ES Modules (`"type": "module"`)
 - **Framework:** Next.js 16 (App Router) with TypeScript 6
-- **Database:** SQLite via better-sqlite3 (local, zero-config, 145 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 148 migrations)
 - **State management:** Zustand (client), SQLite (server persistence)
 - **UI:** React 19, Tailwind CSS 4, Recharts for analytics, @lobehub/icons for 130+ provider SVG icons
 - **Auth:** OAuth 2.0 (PKCE) for providers, bcrypt for local user auth
@@ -109,7 +106,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   └── streaming.ts      # SSE streaming for A2A
 │   │   ├── acp/                  # Agent Communication Protocol registry and manager
 │   │   ├── compliance/           # Compliance policy engine
-│   │   ├── db/                   # SQLite database layer (99 modules + migrations)
+│   │   ├── db/                   # SQLite database layer (117 modules + migrations)
 │   │   │   ├── core.ts           # Database initialization, connection, schema
 │   │   │   ├── providers.ts      # Provider connection CRUD
 │   │   │   ├── models.ts         # Model catalog management
@@ -131,7 +128,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   ├── secrets.ts        # Secrets management
 │   │   │   ├── stateReset.ts     # State reset utilities
 │   │   │   ├── migrationRunner.ts # Schema migration runner
-│   │   │   └── migrations/       # 117 versioned SQL migration files
+│   │   │   └── migrations/       # 148 versioned SQL migration files
 │   │   ├── evals/                # Eval runner and scheduler
 │   │   ├── memory/               # Persistent conversational memory
 │   │   │   ├── extraction.ts     # Memory extraction from conversations
@@ -214,11 +211,11 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── moderations.ts        # Content moderation
 │   │   ├── rerank.ts             # Reranking API
 │   │   └── search.ts             # Web search API
-│   ├── mcp-server/               # Built-in MCP server (105 tools, 3 transports: stdio/SSE/streamable-HTTP)
+│   ├── mcp-server/               # Built-in MCP server (109 tools, 3 transports: stdio/SSE/streamable-HTTP)
 │   │   ├── server.ts             # MCP server core (tool registration, scope enforcement)
 │   │   ├── tools/                # Tool implementations (advancedTools, memoryTools, skillTools)
 │   │   ├── schemas/              # Zod input schemas (tools, audit, a2a)
-│   │   ├── scopeEnforcement.ts   # Scope-based access control (31 scopes)
+│   │   ├── scopeEnforcement.ts   # Scope-based access control (33 scopes)
 │   │   ├── audit.ts              # Tool call audit logging
 │   │   ├── runtimeHeartbeat.ts   # MCP runtime heartbeat
 │   │   └── httpTransport.ts      # HTTP transport handler
@@ -269,7 +266,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── i18n/                     # 43-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
-│   ├── frameworks/               # MCP-SERVER.md (105 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
+│   ├── frameworks/               # MCP-SERVER.md (109 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
 │   ├── routing/                  # AUTO-COMBO.md (14-factor scoring), REASONING_REPLAY.md
 │   ├── security/                 # GUARDRAILS.md, COMPLIANCE.md, STEALTH_GUIDE.md, PUBLIC_CREDS.md, ERROR_SANITIZATION.md
 │   ├── guides/                   # USER_GUIDE.md, TROUBLESHOOTING.md, ELECTRON_GUIDE.md, I18N.md
@@ -352,9 +349,9 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 - **A2A** — Agent-to-Agent v0.3 protocol (JSON-RPC 2.0, 6 skills: smart-routing, quota-management, provider-discovery, cost-analysis, health-report, list-capabilities)
 - **ACP** — Agent Communication Protocol registry and manager
 
-### MCP Server (105 Tools)
+### MCP Server (109 Tools)
 
-105 tools across modules: **43 base** (health, combos, quotas, routing, cost, models, cache,
+109 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
 diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool**, **notion**,
 **obsidian**, **localCorpus**, **gamification**, and **plugin** modules. Full per-tool inventory:
 `docs/frameworks/MCP-SERVER.md`.
@@ -397,7 +394,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 8. **ProviderIcon component:** Unified icon system using `@lobehub/icons` (130+ SVG) with PNG fallback and generic icon fallback chain. Used on providers, dashboard, and agents pages.
 
-9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 99 `src/lib/db/` modules with 117 SQL migrations.
+9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 117 `src/lib/db/` modules with 148 SQL migrations.
 
 10. **Upstream headers:** Custom headers merged in executors after default auth; same header name replaces executor value. Forbidden header names in `src/shared/constants/upstreamHeaders.ts`.
 
@@ -441,7 +438,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 4. **Environment variables:** All configuration is in `.env` (from `.env.example`). Key vars: `PORT`, `NEXT_PUBLIC_BASE_URL`, `API_KEY`, `ADMIN_PASSWORD`.
 
-5. **Database layer:** Operations go through `src/lib/db/` modules (117 domain-specific files, 145 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
+5. **Database layer:** Operations go through `src/lib/db/` modules (117 domain-specific files, 148 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
 
 6. **Tests** use Node.js built-in test runner + Vitest. Run `npm test`. Vitest for MCP/autoCombo (`npm run test:vitest`). Playwright for E2E (`npm run test:e2e`). Coverage gate: ratchet vs `quality-baseline.json`, absolute floor 60% statements/lines/functions/branches.
 
@@ -485,7 +482,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 - **339-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
-- **MCP server expanded to 105 tools / 31 scopes** (base + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
+- **MCP server expanded to 109 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
 - **Cloud Agents** (Codex Cloud, Devin, Jules), **Guardrails**, **Evals**, **Webhooks**, **Compliance** frameworks
 - **Embedded services** manager (install/start/stop bundled services from the dashboard)
 - **Prompt compression** (RTK + Caveman codecs) saving up to ~95% tokens on eligible traffic

docs/i18n/fr/llm.txt

@@ -4,10 +4,7 @@
 
 ---
 
-
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 339 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (109 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
-
-
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 339 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (105 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -21,7 +18,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 - **Runtime:** Node.js `>=22.0.0 <23 || >=24.0.0 <27`, ES Modules (`"type": "module"`)
 - **Framework:** Next.js 16 (App Router) with TypeScript 6
-- **Database:** SQLite via better-sqlite3 (local, zero-config, 145 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 148 migrations)
 - **State management:** Zustand (client), SQLite (server persistence)
 - **UI:** React 19, Tailwind CSS 4, Recharts for analytics, @lobehub/icons for 130+ provider SVG icons
 - **Auth:** OAuth 2.0 (PKCE) for providers, bcrypt for local user auth
@@ -109,7 +106,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   └── streaming.ts      # SSE streaming for A2A
 │   │   ├── acp/                  # Agent Communication Protocol registry and manager
 │   │   ├── compliance/           # Compliance policy engine
-│   │   ├── db/                   # SQLite database layer (99 modules + migrations)
+│   │   ├── db/                   # SQLite database layer (117 modules + migrations)
 │   │   │   ├── core.ts           # Database initialization, connection, schema
 │   │   │   ├── providers.ts      # Provider connection CRUD
 │   │   │   ├── models.ts         # Model catalog management
@@ -131,7 +128,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   ├── secrets.ts        # Secrets management
 │   │   │   ├── stateReset.ts     # State reset utilities
 │   │   │   ├── migrationRunner.ts # Schema migration runner
-│   │   │   └── migrations/       # 117 versioned SQL migration files
+│   │   │   └── migrations/       # 148 versioned SQL migration files
 │   │   ├── evals/                # Eval runner and scheduler
 │   │   ├── memory/               # Persistent conversational memory
 │   │   │   ├── extraction.ts     # Memory extraction from conversations
@@ -214,11 +211,11 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── moderations.ts        # Content moderation
 │   │   ├── rerank.ts             # Reranking API
 │   │   └── search.ts             # Web search API
-│   ├── mcp-server/               # Built-in MCP server (105 tools, 3 transports: stdio/SSE/streamable-HTTP)
+│   ├── mcp-server/               # Built-in MCP server (109 tools, 3 transports: stdio/SSE/streamable-HTTP)
 │   │   ├── server.ts             # MCP server core (tool registration, scope enforcement)
 │   │   ├── tools/                # Tool implementations (advancedTools, memoryTools, skillTools)
 │   │   ├── schemas/              # Zod input schemas (tools, audit, a2a)
-│   │   ├── scopeEnforcement.ts   # Scope-based access control (31 scopes)
+│   │   ├── scopeEnforcement.ts   # Scope-based access control (33 scopes)
 │   │   ├── audit.ts              # Tool call audit logging
 │   │   ├── runtimeHeartbeat.ts   # MCP runtime heartbeat
 │   │   └── httpTransport.ts      # HTTP transport handler
@@ -269,7 +266,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── i18n/                     # 43-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
-│   ├── frameworks/               # MCP-SERVER.md (105 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
+│   ├── frameworks/               # MCP-SERVER.md (109 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
 │   ├── routing/                  # AUTO-COMBO.md (14-factor scoring), REASONING_REPLAY.md
 │   ├── security/                 # GUARDRAILS.md, COMPLIANCE.md, STEALTH_GUIDE.md, PUBLIC_CREDS.md, ERROR_SANITIZATION.md
 │   ├── guides/                   # USER_GUIDE.md, TROUBLESHOOTING.md, ELECTRON_GUIDE.md, I18N.md
@@ -352,9 +349,9 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 - **A2A** — Agent-to-Agent v0.3 protocol (JSON-RPC 2.0, 6 skills: smart-routing, quota-management, provider-discovery, cost-analysis, health-report, list-capabilities)
 - **ACP** — Agent Communication Protocol registry and manager
 
-### MCP Server (105 Tools)
+### MCP Server (109 Tools)
 
-105 tools across modules: **43 base** (health, combos, quotas, routing, cost, models, cache,
+109 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
 diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool**, **notion**,
 **obsidian**, **localCorpus**, **gamification**, and **plugin** modules. Full per-tool inventory:
 `docs/frameworks/MCP-SERVER.md`.
@@ -397,7 +394,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 8. **ProviderIcon component:** Unified icon system using `@lobehub/icons` (130+ SVG) with PNG fallback and generic icon fallback chain. Used on providers, dashboard, and agents pages.
 
-9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 99 `src/lib/db/` modules with 117 SQL migrations.
+9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 117 `src/lib/db/` modules with 148 SQL migrations.
 
 10. **Upstream headers:** Custom headers merged in executors after default auth; same header name replaces executor value. Forbidden header names in `src/shared/constants/upstreamHeaders.ts`.
 
@@ -441,7 +438,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 4. **Environment variables:** All configuration is in `.env` (from `.env.example`). Key vars: `PORT`, `NEXT_PUBLIC_BASE_URL`, `API_KEY`, `ADMIN_PASSWORD`.
 
-5. **Database layer:** Operations go through `src/lib/db/` modules (117 domain-specific files, 145 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
+5. **Database layer:** Operations go through `src/lib/db/` modules (117 domain-specific files, 148 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
 
 6. **Tests** use Node.js built-in test runner + Vitest. Run `npm test`. Vitest for MCP/autoCombo (`npm run test:vitest`). Playwright for E2E (`npm run test:e2e`). Coverage gate: ratchet vs `quality-baseline.json`, absolute floor 60% statements/lines/functions/branches.
 
@@ -485,7 +482,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 - **339-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
-- **MCP server expanded to 105 tools / 31 scopes** (base + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
+- **MCP server expanded to 109 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
 - **Cloud Agents** (Codex Cloud, Devin, Jules), **Guardrails**, **Evals**, **Webhooks**, **Compliance** frameworks
 - **Embedded services** manager (install/start/stop bundled services from the dashboard)
 - **Prompt compression** (RTK + Caveman codecs) saving up to ~95% tokens on eligible traffic

docs/i18n/gu/llm.txt

@@ -4,10 +4,7 @@
 
 ---
 
-
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 339 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (109 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
-
-
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 339 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (105 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -21,7 +18,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 - **Runtime:** Node.js `>=22.0.0 <23 || >=24.0.0 <27`, ES Modules (`"type": "module"`)
 - **Framework:** Next.js 16 (App Router) with TypeScript 6
-- **Database:** SQLite via better-sqlite3 (local, zero-config, 145 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 148 migrations)
 - **State management:** Zustand (client), SQLite (server persistence)
 - **UI:** React 19, Tailwind CSS 4, Recharts for analytics, @lobehub/icons for 130+ provider SVG icons
 - **Auth:** OAuth 2.0 (PKCE) for providers, bcrypt for local user auth
@@ -109,7 +106,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   └── streaming.ts      # SSE streaming for A2A
 │   │   ├── acp/                  # Agent Communication Protocol registry and manager
 │   │   ├── compliance/           # Compliance policy engine
-│   │   ├── db/                   # SQLite database layer (99 modules + migrations)
+│   │   ├── db/                   # SQLite database layer (117 modules + migrations)
 │   │   │   ├── core.ts           # Database initialization, connection, schema
 │   │   │   ├── providers.ts      # Provider connection CRUD
 │   │   │   ├── models.ts         # Model catalog management
@@ -131,7 +128,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   ├── secrets.ts        # Secrets management
 │   │   │   ├── stateReset.ts     # State reset utilities
 │   │   │   ├── migrationRunner.ts # Schema migration runner
-│   │   │   └── migrations/       # 117 versioned SQL migration files
+│   │   │   └── migrations/       # 148 versioned SQL migration files
 │   │   ├── evals/                # Eval runner and scheduler
 │   │   ├── memory/               # Persistent conversational memory
 │   │   │   ├── extraction.ts     # Memory extraction from conversations
@@ -214,11 +211,11 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── moderations.ts        # Content moderation
 │   │   ├── rerank.ts             # Reranking API
 │   │   └── search.ts             # Web search API
-│   ├── mcp-server/               # Built-in MCP server (105 tools, 3 transports: stdio/SSE/streamable-HTTP)
+│   ├── mcp-server/               # Built-in MCP server (109 tools, 3 transports: stdio/SSE/streamable-HTTP)
 │   │   ├── server.ts             # MCP server core (tool registration, scope enforcement)
 │   │   ├── tools/                # Tool implementations (advancedTools, memoryTools, skillTools)
 │   │   ├── schemas/              # Zod input schemas (tools, audit, a2a)
-│   │   ├── scopeEnforcement.ts   # Scope-based access control (31 scopes)
+│   │   ├── scopeEnforcement.ts   # Scope-based access control (33 scopes)
 │   │   ├── audit.ts              # Tool call audit logging
 │   │   ├── runtimeHeartbeat.ts   # MCP runtime heartbeat
 │   │   └── httpTransport.ts      # HTTP transport handler
@@ -269,7 +266,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── i18n/                     # 43-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
-│   ├── frameworks/               # MCP-SERVER.md (105 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
+│   ├── frameworks/               # MCP-SERVER.md (109 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
 │   ├── routing/                  # AUTO-COMBO.md (14-factor scoring), REASONING_REPLAY.md
 │   ├── security/                 # GUARDRAILS.md, COMPLIANCE.md, STEALTH_GUIDE.md, PUBLIC_CREDS.md, ERROR_SANITIZATION.md
 │   ├── guides/                   # USER_GUIDE.md, TROUBLESHOOTING.md, ELECTRON_GUIDE.md, I18N.md
@@ -352,9 +349,9 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 - **A2A** — Agent-to-Agent v0.3 protocol (JSON-RPC 2.0, 6 skills: smart-routing, quota-management, provider-discovery, cost-analysis, health-report, list-capabilities)
 - **ACP** — Agent Communication Protocol registry and manager
 
-### MCP Server (105 Tools)
+### MCP Server (109 Tools)
 
-105 tools across modules: **43 base** (health, combos, quotas, routing, cost, models, cache,
+109 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
 diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool**, **notion**,
 **obsidian**, **localCorpus**, **gamification**, and **plugin** modules. Full per-tool inventory:
 `docs/frameworks/MCP-SERVER.md`.
@@ -397,7 +394,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 8. **ProviderIcon component:** Unified icon system using `@lobehub/icons` (130+ SVG) with PNG fallback and generic icon fallback chain. Used on providers, dashboard, and agents pages.
 
-9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 99 `src/lib/db/` modules with 117 SQL migrations.
+9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 117 `src/lib/db/` modules with 148 SQL migrations.
 
 10. **Upstream headers:** Custom headers merged in executors after default auth; same header name replaces executor value. Forbidden header names in `src/shared/constants/upstreamHeaders.ts`.
 
@@ -441,7 +438,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 4. **Environment variables:** All configuration is in `.env` (from `.env.example`). Key vars: `PORT`, `NEXT_PUBLIC_BASE_URL`, `API_KEY`, `ADMIN_PASSWORD`.
 
-5. **Database layer:** Operations go through `src/lib/db/` modules (117 domain-specific files, 145 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
+5. **Database layer:** Operations go through `src/lib/db/` modules (117 domain-specific files, 148 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
 
 6. **Tests** use Node.js built-in test runner + Vitest. Run `npm test`. Vitest for MCP/autoCombo (`npm run test:vitest`). Playwright for E2E (`npm run test:e2e`). Coverage gate: ratchet vs `quality-baseline.json`, absolute floor 60% statements/lines/functions/branches.
 
@@ -485,7 +482,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 - **339-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
-- **MCP server expanded to 105 tools / 31 scopes** (base + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
+- **MCP server expanded to 109 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
 - **Cloud Agents** (Codex Cloud, Devin, Jules), **Guardrails**, **Evals**, **Webhooks**, **Compliance** frameworks
 - **Embedded services** manager (install/start/stop bundled services from the dashboard)
 - **Prompt compression** (RTK + Caveman codecs) saving up to ~95% tokens on eligible traffic

docs/i18n/he/llm.txt

@@ -4,10 +4,7 @@
 
 ---
 
-
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 339 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (109 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
-
-
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 339 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (105 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -21,7 +18,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 - **Runtime:** Node.js `>=22.0.0 <23 || >=24.0.0 <27`, ES Modules (`"type": "module"`)
 - **Framework:** Next.js 16 (App Router) with TypeScript 6
-- **Database:** SQLite via better-sqlite3 (local, zero-config, 145 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 148 migrations)
 - **State management:** Zustand (client), SQLite (server persistence)
 - **UI:** React 19, Tailwind CSS 4, Recharts for analytics, @lobehub/icons for 130+ provider SVG icons
 - **Auth:** OAuth 2.0 (PKCE) for providers, bcrypt for local user auth
@@ -109,7 +106,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   └── streaming.ts      # SSE streaming for A2A
 │   │   ├── acp/                  # Agent Communication Protocol registry and manager
 │   │   ├── compliance/           # Compliance policy engine
-│   │   ├── db/                   # SQLite database layer (99 modules + migrations)
+│   │   ├── db/                   # SQLite database layer (117 modules + migrations)
 │   │   │   ├── core.ts           # Database initialization, connection, schema
 │   │   │   ├── providers.ts      # Provider connection CRUD
 │   │   │   ├── models.ts         # Model catalog management
@@ -131,7 +128,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   ├── secrets.ts        # Secrets management
 │   │   │   ├── stateReset.ts     # State reset utilities
 │   │   │   ├── migrationRunner.ts # Schema migration runner
-│   │   │   └── migrations/       # 117 versioned SQL migration files
+│   │   │   └── migrations/       # 148 versioned SQL migration files
 │   │   ├── evals/                # Eval runner and scheduler
 │   │   ├── memory/               # Persistent conversational memory
 │   │   │   ├── extraction.ts     # Memory extraction from conversations
@@ -214,11 +211,11 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── moderations.ts        # Content moderation
 │   │   ├── rerank.ts             # Reranking API
 │   │   └── search.ts             # Web search API
-│   ├── mcp-server/               # Built-in MCP server (105 tools, 3 transports: stdio/SSE/streamable-HTTP)
+│   ├── mcp-server/               # Built-in MCP server (109 tools, 3 transports: stdio/SSE/streamable-HTTP)
 │   │   ├── server.ts             # MCP server core (tool registration, scope enforcement)
 │   │   ├── tools/                # Tool implementations (advancedTools, memoryTools, skillTools)
 │   │   ├── schemas/              # Zod input schemas (tools, audit, a2a)
-│   │   ├── scopeEnforcement.ts   # Scope-based access control (31 scopes)
+│   │   ├── scopeEnforcement.ts   # Scope-based access control (33 scopes)
 │   │   ├── audit.ts              # Tool call audit logging
 │   │   ├── runtimeHeartbeat.ts   # MCP runtime heartbeat
 │   │   └── httpTransport.ts      # HTTP transport handler
@@ -269,7 +266,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── i18n/                     # 43-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
-│   ├── frameworks/               # MCP-SERVER.md (105 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
+│   ├── frameworks/               # MCP-SERVER.md (109 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
 │   ├── routing/                  # AUTO-COMBO.md (14-factor scoring), REASONING_REPLAY.md
 │   ├── security/                 # GUARDRAILS.md, COMPLIANCE.md, STEALTH_GUIDE.md, PUBLIC_CREDS.md, ERROR_SANITIZATION.md
 │   ├── guides/                   # USER_GUIDE.md, TROUBLESHOOTING.md, ELECTRON_GUIDE.md, I18N.md
@@ -352,9 +349,9 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 - **A2A** — Agent-to-Agent v0.3 protocol (JSON-RPC 2.0, 6 skills: smart-routing, quota-management, provider-discovery, cost-analysis, health-report, list-capabilities)
 - **ACP** — Agent Communication Protocol registry and manager
 
-### MCP Server (105 Tools)
+### MCP Server (109 Tools)
 
-105 tools across modules: **43 base** (health, combos, quotas, routing, cost, models, cache,
+109 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
 diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool**, **notion**,
 **obsidian**, **localCorpus**, **gamification**, and **plugin** modules. Full per-tool inventory:
 `docs/frameworks/MCP-SERVER.md`.
@@ -397,7 +394,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 8. **ProviderIcon component:** Unified icon system using `@lobehub/icons` (130+ SVG) with PNG fallback and generic icon fallback chain. Used on providers, dashboard, and agents pages.
 
-9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 99 `src/lib/db/` modules with 117 SQL migrations.
+9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 117 `src/lib/db/` modules with 148 SQL migrations.
 
 10. **Upstream headers:** Custom headers merged in executors after default auth; same header name replaces executor value. Forbidden header names in `src/shared/constants/upstreamHeaders.ts`.
 
@@ -441,7 +438,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 4. **Environment variables:** All configuration is in `.env` (from `.env.example`). Key vars: `PORT`, `NEXT_PUBLIC_BASE_URL`, `API_KEY`, `ADMIN_PASSWORD`.
 
-5. **Database layer:** Operations go through `src/lib/db/` modules (117 domain-specific files, 145 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
+5. **Database layer:** Operations go through `src/lib/db/` modules (117 domain-specific files, 148 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
 
 6. **Tests** use Node.js built-in test runner + Vitest. Run `npm test`. Vitest for MCP/autoCombo (`npm run test:vitest`). Playwright for E2E (`npm run test:e2e`). Coverage gate: ratchet vs `quality-baseline.json`, absolute floor 60% statements/lines/functions/branches.
 
@@ -485,7 +482,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 - **339-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
-- **MCP server expanded to 105 tools / 31 scopes** (base + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
+- **MCP server expanded to 109 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
 - **Cloud Agents** (Codex Cloud, Devin, Jules), **Guardrails**, **Evals**, **Webhooks**, **Compliance** frameworks
 - **Embedded services** manager (install/start/stop bundled services from the dashboard)
 - **Prompt compression** (RTK + Caveman codecs) saving up to ~95% tokens on eligible traffic

docs/i18n/hi/llm.txt

@@ -4,10 +4,7 @@
 
 ---
 
-
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 339 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (109 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
-
-
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 339 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (105 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -21,7 +18,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 - **Runtime:** Node.js `>=22.0.0 <23 || >=24.0.0 <27`, ES Modules (`"type": "module"`)
 - **Framework:** Next.js 16 (App Router) with TypeScript 6
-- **Database:** SQLite via better-sqlite3 (local, zero-config, 145 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 148 migrations)
 - **State management:** Zustand (client), SQLite (server persistence)
 - **UI:** React 19, Tailwind CSS 4, Recharts for analytics, @lobehub/icons for 130+ provider SVG icons
 - **Auth:** OAuth 2.0 (PKCE) for providers, bcrypt for local user auth
@@ -109,7 +106,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   └── streaming.ts      # SSE streaming for A2A
 │   │   ├── acp/                  # Agent Communication Protocol registry and manager
 │   │   ├── compliance/           # Compliance policy engine
-│   │   ├── db/                   # SQLite database layer (99 modules + migrations)
+│   │   ├── db/                   # SQLite database layer (117 modules + migrations)
 │   │   │   ├── core.ts           # Database initialization, connection, schema
 │   │   │   ├── providers.ts      # Provider connection CRUD
 │   │   │   ├── models.ts         # Model catalog management
@@ -131,7 +128,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   ├── secrets.ts        # Secrets management
 │   │   │   ├── stateReset.ts     # State reset utilities
 │   │   │   ├── migrationRunner.ts # Schema migration runner
-│   │   │   └── migrations/       # 117 versioned SQL migration files
+│   │   │   └── migrations/       # 148 versioned SQL migration files
 │   │   ├── evals/                # Eval runner and scheduler
 │   │   ├── memory/               # Persistent conversational memory
 │   │   │   ├── extraction.ts     # Memory extraction from conversations
@@ -214,11 +211,11 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── moderations.ts        # Content moderation
 │   │   ├── rerank.ts             # Reranking API
 │   │   └── search.ts             # Web search API
-│   ├── mcp-server/               # Built-in MCP server (105 tools, 3 transports: stdio/SSE/streamable-HTTP)
+│   ├── mcp-server/               # Built-in MCP server (109 tools, 3 transports: stdio/SSE/streamable-HTTP)
 │   │   ├── server.ts             # MCP server core (tool registration, scope enforcement)
 │   │   ├── tools/                # Tool implementations (advancedTools, memoryTools, skillTools)
 │   │   ├── schemas/              # Zod input schemas (tools, audit, a2a)
-│   │   ├── scopeEnforcement.ts   # Scope-based access control (31 scopes)
+│   │   ├── scopeEnforcement.ts   # Scope-based access control (33 scopes)
 │   │   ├── audit.ts              # Tool call audit logging
 │   │   ├── runtimeHeartbeat.ts   # MCP runtime heartbeat
 │   │   └── httpTransport.ts      # HTTP transport handler
@@ -269,7 +266,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── i18n/                     # 43-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
-│   ├── frameworks/               # MCP-SERVER.md (105 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
+│   ├── frameworks/               # MCP-SERVER.md (109 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
 │   ├── routing/                  # AUTO-COMBO.md (14-factor scoring), REASONING_REPLAY.md
 │   ├── security/                 # GUARDRAILS.md, COMPLIANCE.md, STEALTH_GUIDE.md, PUBLIC_CREDS.md, ERROR_SANITIZATION.md
 │   ├── guides/                   # USER_GUIDE.md, TROUBLESHOOTING.md, ELECTRON_GUIDE.md, I18N.md
@@ -352,9 +349,9 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 - **A2A** — Agent-to-Agent v0.3 protocol (JSON-RPC 2.0, 6 skills: smart-routing, quota-management, provider-discovery, cost-analysis, health-report, list-capabilities)
 - **ACP** — Agent Communication Protocol registry and manager
 
-### MCP Server (105 Tools)
+### MCP Server (109 Tools)
 
-105 tools across modules: **43 base** (health, combos, quotas, routing, cost, models, cache,
+109 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
 diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool**, **notion**,
 **obsidian**, **localCorpus**, **gamification**, and **plugin** modules. Full per-tool inventory:
 `docs/frameworks/MCP-SERVER.md`.
@@ -397,7 +394,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 8. **ProviderIcon component:** Unified icon system using `@lobehub/icons` (130+ SVG) with PNG fallback and generic icon fallback chain. Used on providers, dashboard, and agents pages.
 
-9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 99 `src/lib/db/` modules with 117 SQL migrations.
+9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 117 `src/lib/db/` modules with 148 SQL migrations.
 
 10. **Upstream headers:** Custom headers merged in executors after default auth; same header name replaces executor value. Forbidden header names in `src/shared/constants/upstreamHeaders.ts`.
 
@@ -441,7 +438,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 4. **Environment variables:** All configuration is in `.env` (from `.env.example`). Key vars: `PORT`, `NEXT_PUBLIC_BASE_URL`, `API_KEY`, `ADMIN_PASSWORD`.
 
-5. **Database layer:** Operations go through `src/lib/db/` modules (117 domain-specific files, 145 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
+5. **Database layer:** Operations go through `src/lib/db/` modules (117 domain-specific files, 148 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
 
 6. **Tests** use Node.js built-in test runner + Vitest. Run `npm test`. Vitest for MCP/autoCombo (`npm run test:vitest`). Playwright for E2E (`npm run test:e2e`). Coverage gate: ratchet vs `quality-baseline.json`, absolute floor 60% statements/lines/functions/branches.
 
@@ -485,7 +482,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 - **339-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
-- **MCP server expanded to 105 tools / 31 scopes** (base + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
+- **MCP server expanded to 109 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
 - **Cloud Agents** (Codex Cloud, Devin, Jules), **Guardrails**, **Evals**, **Webhooks**, **Compliance** frameworks
 - **Embedded services** manager (install/start/stop bundled services from the dashboard)
 - **Prompt compression** (RTK + Caveman codecs) saving up to ~95% tokens on eligible traffic

docs/i18n/hu/llm.txt

@@ -4,10 +4,7 @@
 
 ---
 
-
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 339 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (109 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
-
-
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 339 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (105 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -21,7 +18,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 - **Runtime:** Node.js `>=22.0.0 <23 || >=24.0.0 <27`, ES Modules (`"type": "module"`)
 - **Framework:** Next.js 16 (App Router) with TypeScript 6
-- **Database:** SQLite via better-sqlite3 (local, zero-config, 145 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 148 migrations)
 - **State management:** Zustand (client), SQLite (server persistence)
 - **UI:** React 19, Tailwind CSS 4, Recharts for analytics, @lobehub/icons for 130+ provider SVG icons
 - **Auth:** OAuth 2.0 (PKCE) for providers, bcrypt for local user auth
@@ -109,7 +106,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   └── streaming.ts      # SSE streaming for A2A
 │   │   ├── acp/                  # Agent Communication Protocol registry and manager
 │   │   ├── compliance/           # Compliance policy engine
-│   │   ├── db/                   # SQLite database layer (99 modules + migrations)
+│   │   ├── db/                   # SQLite database layer (117 modules + migrations)
 │   │   │   ├── core.ts           # Database initialization, connection, schema
 │   │   │   ├── providers.ts      # Provider connection CRUD
 │   │   │   ├── models.ts         # Model catalog management
@@ -131,7 +128,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   ├── secrets.ts        # Secrets management
 │   │   │   ├── stateReset.ts     # State reset utilities
 │   │   │   ├── migrationRunner.ts # Schema migration runner
-│   │   │   └── migrations/       # 117 versioned SQL migration files
+│   │   │   └── migrations/       # 148 versioned SQL migration files
 │   │   ├── evals/                # Eval runner and scheduler
 │   │   ├── memory/               # Persistent conversational memory
 │   │   │   ├── extraction.ts     # Memory extraction from conversations
@@ -214,11 +211,11 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── moderations.ts        # Content moderation
 │   │   ├── rerank.ts             # Reranking API
 │   │   └── search.ts             # Web search API
-│   ├── mcp-server/               # Built-in MCP server (105 tools, 3 transports: stdio/SSE/streamable-HTTP)
+│   ├── mcp-server/               # Built-in MCP server (109 tools, 3 transports: stdio/SSE/streamable-HTTP)
 │   │   ├── server.ts             # MCP server core (tool registration, scope enforcement)
 │   │   ├── tools/                # Tool implementations (advancedTools, memoryTools, skillTools)
 │   │   ├── schemas/              # Zod input schemas (tools, audit, a2a)
-│   │   ├── scopeEnforcement.ts   # Scope-based access control (31 scopes)
+│   │   ├── scopeEnforcement.ts   # Scope-based access control (33 scopes)
 │   │   ├── audit.ts              # Tool call audit logging
 │   │   ├── runtimeHeartbeat.ts   # MCP runtime heartbeat
 │   │   └── httpTransport.ts      # HTTP transport handler
@@ -269,7 +266,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── i18n/                     # 43-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
-│   ├── frameworks/               # MCP-SERVER.md (105 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
+│   ├── frameworks/               # MCP-SERVER.md (109 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
 │   ├── routing/                  # AUTO-COMBO.md (14-factor scoring), REASONING_REPLAY.md
 │   ├── security/                 # GUARDRAILS.md, COMPLIANCE.md, STEALTH_GUIDE.md, PUBLIC_CREDS.md, ERROR_SANITIZATION.md
 │   ├── guides/                   # USER_GUIDE.md, TROUBLESHOOTING.md, ELECTRON_GUIDE.md, I18N.md
@@ -352,9 +349,9 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 - **A2A** — Agent-to-Agent v0.3 protocol (JSON-RPC 2.0, 6 skills: smart-routing, quota-management, provider-discovery, cost-analysis, health-report, list-capabilities)
 - **ACP** — Agent Communication Protocol registry and manager
 
-### MCP Server (105 Tools)
+### MCP Server (109 Tools)
 
-105 tools across modules: **43 base** (health, combos, quotas, routing, cost, models, cache,
+109 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
 diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool**, **notion**,
 **obsidian**, **localCorpus**, **gamification**, and **plugin** modules. Full per-tool inventory:
 `docs/frameworks/MCP-SERVER.md`.
@@ -397,7 +394,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 8. **ProviderIcon component:** Unified icon system using `@lobehub/icons` (130+ SVG) with PNG fallback and generic icon fallback chain. Used on providers, dashboard, and agents pages.
 
-9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 99 `src/lib/db/` modules with 117 SQL migrations.
+9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 117 `src/lib/db/` modules with 148 SQL migrations.
 
 10. **Upstream headers:** Custom headers merged in executors after default auth; same header name replaces executor value. Forbidden header names in `src/shared/constants/upstreamHeaders.ts`.
 
@@ -441,7 +438,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 4. **Environment variables:** All configuration is in `.env` (from `.env.example`). Key vars: `PORT`, `NEXT_PUBLIC_BASE_URL`, `API_KEY`, `ADMIN_PASSWORD`.
 
-5. **Database layer:** Operations go through `src/lib/db/` modules (117 domain-specific files, 145 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
+5. **Database layer:** Operations go through `src/lib/db/` modules (117 domain-specific files, 148 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
 
 6. **Tests** use Node.js built-in test runner + Vitest. Run `npm test`. Vitest for MCP/autoCombo (`npm run test:vitest`). Playwright for E2E (`npm run test:e2e`). Coverage gate: ratchet vs `quality-baseline.json`, absolute floor 60% statements/lines/functions/branches.
 
@@ -485,7 +482,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 - **339-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
-- **MCP server expanded to 105 tools / 31 scopes** (base + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
+- **MCP server expanded to 109 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
 - **Cloud Agents** (Codex Cloud, Devin, Jules), **Guardrails**, **Evals**, **Webhooks**, **Compliance** frameworks
 - **Embedded services** manager (install/start/stop bundled services from the dashboard)
 - **Prompt compression** (RTK + Caveman codecs) saving up to ~95% tokens on eligible traffic

docs/i18n/id/llm.txt

@@ -4,10 +4,7 @@
 
 ---
 
-
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 339 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (109 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
-
-
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 339 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (105 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -21,7 +18,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 - **Runtime:** Node.js `>=22.0.0 <23 || >=24.0.0 <27`, ES Modules (`"type": "module"`)
 - **Framework:** Next.js 16 (App Router) with TypeScript 6
-- **Database:** SQLite via better-sqlite3 (local, zero-config, 145 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 148 migrations)
 - **State management:** Zustand (client), SQLite (server persistence)
 - **UI:** React 19, Tailwind CSS 4, Recharts for analytics, @lobehub/icons for 130+ provider SVG icons
 - **Auth:** OAuth 2.0 (PKCE) for providers, bcrypt for local user auth
@@ -109,7 +106,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   └── streaming.ts      # SSE streaming for A2A
 │   │   ├── acp/                  # Agent Communication Protocol registry and manager
 │   │   ├── compliance/           # Compliance policy engine
-│   │   ├── db/                   # SQLite database layer (99 modules + migrations)
+│   │   ├── db/                   # SQLite database layer (117 modules + migrations)
 │   │   │   ├── core.ts           # Database initialization, connection, schema
 │   │   │   ├── providers.ts      # Provider connection CRUD
 │   │   │   ├── models.ts         # Model catalog management
@@ -131,7 +128,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   ├── secrets.ts        # Secrets management
 │   │   │   ├── stateReset.ts     # State reset utilities
 │   │   │   ├── migrationRunner.ts # Schema migration runner
-│   │   │   └── migrations/       # 117 versioned SQL migration files
+│   │   │   └── migrations/       # 148 versioned SQL migration files
 │   │   ├── evals/                # Eval runner and scheduler
 │   │   ├── memory/               # Persistent conversational memory
 │   │   │   ├── extraction.ts     # Memory extraction from conversations
@@ -214,11 +211,11 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── moderations.ts        # Content moderation
 │   │   ├── rerank.ts             # Reranking API
 │   │   └── search.ts             # Web search API
-│   ├── mcp-server/               # Built-in MCP server (105 tools, 3 transports: stdio/SSE/streamable-HTTP)
+│   ├── mcp-server/               # Built-in MCP server (109 tools, 3 transports: stdio/SSE/streamable-HTTP)
 │   │   ├── server.ts             # MCP server core (tool registration, scope enforcement)
 │   │   ├── tools/                # Tool implementations (advancedTools, memoryTools, skillTools)
 │   │   ├── schemas/              # Zod input schemas (tools, audit, a2a)
-│   │   ├── scopeEnforcement.ts   # Scope-based access control (31 scopes)
+│   │   ├── scopeEnforcement.ts   # Scope-based access control (33 scopes)
 │   │   ├── audit.ts              # Tool call audit logging
 │   │   ├── runtimeHeartbeat.ts   # MCP runtime heartbeat
 │   │   └── httpTransport.ts      # HTTP transport handler
@@ -269,7 +266,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── i18n/                     # 43-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
-│   ├── frameworks/               # MCP-SERVER.md (105 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
+│   ├── frameworks/               # MCP-SERVER.md (109 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
 │   ├── routing/                  # AUTO-COMBO.md (14-factor scoring), REASONING_REPLAY.md
 │   ├── security/                 # GUARDRAILS.md, COMPLIANCE.md, STEALTH_GUIDE.md, PUBLIC_CREDS.md, ERROR_SANITIZATION.md
 │   ├── guides/                   # USER_GUIDE.md, TROUBLESHOOTING.md, ELECTRON_GUIDE.md, I18N.md
@@ -352,9 +349,9 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 - **A2A** — Agent-to-Agent v0.3 protocol (JSON-RPC 2.0, 6 skills: smart-routing, quota-management, provider-discovery, cost-analysis, health-report, list-capabilities)
 - **ACP** — Agent Communication Protocol registry and manager
 
-### MCP Server (105 Tools)
+### MCP Server (109 Tools)
 
-105 tools across modules: **43 base** (health, combos, quotas, routing, cost, models, cache,
+109 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
 diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool**, **notion**,
 **obsidian**, **localCorpus**, **gamification**, and **plugin** modules. Full per-tool inventory:
 `docs/frameworks/MCP-SERVER.md`.
@@ -397,7 +394,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 8. **ProviderIcon component:** Unified icon system using `@lobehub/icons` (130+ SVG) with PNG fallback and generic icon fallback chain. Used on providers, dashboard, and agents pages.
 
-9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 99 `src/lib/db/` modules with 117 SQL migrations.
+9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 117 `src/lib/db/` modules with 148 SQL migrations.
 
 10. **Upstream headers:** Custom headers merged in executors after default auth; same header name replaces executor value. Forbidden header names in `src/shared/constants/upstreamHeaders.ts`.
 
@@ -441,7 +438,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 4. **Environment variables:** All configuration is in `.env` (from `.env.example`). Key vars: `PORT`, `NEXT_PUBLIC_BASE_URL`, `API_KEY`, `ADMIN_PASSWORD`.
 
-5. **Database layer:** Operations go through `src/lib/db/` modules (117 domain-specific files, 145 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
+5. **Database layer:** Operations go through `src/lib/db/` modules (117 domain-specific files, 148 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
 
 6. **Tests** use Node.js built-in test runner + Vitest. Run `npm test`. Vitest for MCP/autoCombo (`npm run test:vitest`). Playwright for E2E (`npm run test:e2e`). Coverage gate: ratchet vs `quality-baseline.json`, absolute floor 60% statements/lines/functions/branches.
 
@@ -485,7 +482,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 - **339-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
-- **MCP server expanded to 105 tools / 31 scopes** (base + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
+- **MCP server expanded to 109 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
 - **Cloud Agents** (Codex Cloud, Devin, Jules), **Guardrails**, **Evals**, **Webhooks**, **Compliance** frameworks
 - **Embedded services** manager (install/start/stop bundled services from the dashboard)
 - **Prompt compression** (RTK + Caveman codecs) saving up to ~95% tokens on eligible traffic

docs/i18n/in/llm.txt

@@ -4,10 +4,7 @@
 
 ---
 
-
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 339 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (109 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
-
-
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 339 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (105 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -21,7 +18,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 - **Runtime:** Node.js `>=22.0.0 <23 || >=24.0.0 <27`, ES Modules (`"type": "module"`)
 - **Framework:** Next.js 16 (App Router) with TypeScript 6
-- **Database:** SQLite via better-sqlite3 (local, zero-config, 145 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 148 migrations)
 - **State management:** Zustand (client), SQLite (server persistence)
 - **UI:** React 19, Tailwind CSS 4, Recharts for analytics, @lobehub/icons for 130+ provider SVG icons
 - **Auth:** OAuth 2.0 (PKCE) for providers, bcrypt for local user auth
@@ -109,7 +106,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   └── streaming.ts      # SSE streaming for A2A
 │   │   ├── acp/                  # Agent Communication Protocol registry and manager
 │   │   ├── compliance/           # Compliance policy engine
-│   │   ├── db/                   # SQLite database layer (99 modules + migrations)
+│   │   ├── db/                   # SQLite database layer (117 modules + migrations)
 │   │   │   ├── core.ts           # Database initialization, connection, schema
 │   │   │   ├── providers.ts      # Provider connection CRUD
 │   │   │   ├── models.ts         # Model catalog management
@@ -131,7 +128,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   ├── secrets.ts        # Secrets management
 │   │   │   ├── stateReset.ts     # State reset utilities
 │   │   │   ├── migrationRunner.ts # Schema migration runner
-│   │   │   └── migrations/       # 117 versioned SQL migration files
+│   │   │   └── migrations/       # 148 versioned SQL migration files
 │   │   ├── evals/                # Eval runner and scheduler
 │   │   ├── memory/               # Persistent conversational memory
 │   │   │   ├── extraction.ts     # Memory extraction from conversations
@@ -214,11 +211,11 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── moderations.ts        # Content moderation
 │   │   ├── rerank.ts             # Reranking API
 │   │   └── search.ts             # Web search API
-│   ├── mcp-server/               # Built-in MCP server (105 tools, 3 transports: stdio/SSE/streamable-HTTP)
+│   ├── mcp-server/               # Built-in MCP server (109 tools, 3 transports: stdio/SSE/streamable-HTTP)
 │   │   ├── server.ts             # MCP server core (tool registration, scope enforcement)
 │   │   ├── tools/                # Tool implementations (advancedTools, memoryTools, skillTools)
 │   │   ├── schemas/              # Zod input schemas (tools, audit, a2a)
-│   │   ├── scopeEnforcement.ts   # Scope-based access control (31 scopes)
+│   │   ├── scopeEnforcement.ts   # Scope-based access control (33 scopes)
 │   │   ├── audit.ts              # Tool call audit logging
 │   │   ├── runtimeHeartbeat.ts   # MCP runtime heartbeat
 │   │   └── httpTransport.ts      # HTTP transport handler
@@ -269,7 +266,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── i18n/                     # 43-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
-│   ├── frameworks/               # MCP-SERVER.md (105 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
+│   ├── frameworks/               # MCP-SERVER.md (109 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
 │   ├── routing/                  # AUTO-COMBO.md (14-factor scoring), REASONING_REPLAY.md
 │   ├── security/                 # GUARDRAILS.md, COMPLIANCE.md, STEALTH_GUIDE.md, PUBLIC_CREDS.md, ERROR_SANITIZATION.md
 │   ├── guides/                   # USER_GUIDE.md, TROUBLESHOOTING.md, ELECTRON_GUIDE.md, I18N.md
@@ -352,9 +349,9 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 - **A2A** — Agent-to-Agent v0.3 protocol (JSON-RPC 2.0, 6 skills: smart-routing, quota-management, provider-discovery, cost-analysis, health-report, list-capabilities)
 - **ACP** — Agent Communication Protocol registry and manager
 
-### MCP Server (105 Tools)
+### MCP Server (109 Tools)
 
-105 tools across modules: **43 base** (health, combos, quotas, routing, cost, models, cache,
+109 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
 diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool**, **notion**,
 **obsidian**, **localCorpus**, **gamification**, and **plugin** modules. Full per-tool inventory:
 `docs/frameworks/MCP-SERVER.md`.
@@ -397,7 +394,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 8. **ProviderIcon component:** Unified icon system using `@lobehub/icons` (130+ SVG) with PNG fallback and generic icon fallback chain. Used on providers, dashboard, and agents pages.
 
-9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 99 `src/lib/db/` modules with 117 SQL migrations.
+9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 117 `src/lib/db/` modules with 148 SQL migrations.
 
 10. **Upstream headers:** Custom headers merged in executors after default auth; same header name replaces executor value. Forbidden header names in `src/shared/constants/upstreamHeaders.ts`.
 
@@ -441,7 +438,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 4. **Environment variables:** All configuration is in `.env` (from `.env.example`). Key vars: `PORT`, `NEXT_PUBLIC_BASE_URL`, `API_KEY`, `ADMIN_PASSWORD`.
 
-5. **Database layer:** Operations go through `src/lib/db/` modules (117 domain-specific files, 145 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
+5. **Database layer:** Operations go through `src/lib/db/` modules (117 domain-specific files, 148 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
 
 6. **Tests** use Node.js built-in test runner + Vitest. Run `npm test`. Vitest for MCP/autoCombo (`npm run test:vitest`). Playwright for E2E (`npm run test:e2e`). Coverage gate: ratchet vs `quality-baseline.json`, absolute floor 60% statements/lines/functions/branches.
 
@@ -485,7 +482,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 - **339-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
-- **MCP server expanded to 105 tools / 31 scopes** (base + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
+- **MCP server expanded to 109 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
 - **Cloud Agents** (Codex Cloud, Devin, Jules), **Guardrails**, **Evals**, **Webhooks**, **Compliance** frameworks
 - **Embedded services** manager (install/start/stop bundled services from the dashboard)
 - **Prompt compression** (RTK + Caveman codecs) saving up to ~95% tokens on eligible traffic

docs/i18n/it/llm.txt

@@ -4,10 +4,7 @@
 
 ---
 
-
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 339 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (109 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
-
-
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 339 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (105 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -21,7 +18,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 - **Runtime:** Node.js `>=22.0.0 <23 || >=24.0.0 <27`, ES Modules (`"type": "module"`)
 - **Framework:** Next.js 16 (App Router) with TypeScript 6
-- **Database:** SQLite via better-sqlite3 (local, zero-config, 145 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 148 migrations)
 - **State management:** Zustand (client), SQLite (server persistence)
 - **UI:** React 19, Tailwind CSS 4, Recharts for analytics, @lobehub/icons for 130+ provider SVG icons
 - **Auth:** OAuth 2.0 (PKCE) for providers, bcrypt for local user auth
@@ -109,7 +106,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   └── streaming.ts      # SSE streaming for A2A
 │   │   ├── acp/                  # Agent Communication Protocol registry and manager
 │   │   ├── compliance/           # Compliance policy engine
-│   │   ├── db/                   # SQLite database layer (99 modules + migrations)
+│   │   ├── db/                   # SQLite database layer (117 modules + migrations)
 │   │   │   ├── core.ts           # Database initialization, connection, schema
 │   │   │   ├── providers.ts      # Provider connection CRUD
 │   │   │   ├── models.ts         # Model catalog management
@@ -131,7 +128,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   ├── secrets.ts        # Secrets management
 │   │   │   ├── stateReset.ts     # State reset utilities
 │   │   │   ├── migrationRunner.ts # Schema migration runner
-│   │   │   └── migrations/       # 117 versioned SQL migration files
+│   │   │   └── migrations/       # 148 versioned SQL migration files
 │   │   ├── evals/                # Eval runner and scheduler
 │   │   ├── memory/               # Persistent conversational memory
 │   │   │   ├── extraction.ts     # Memory extraction from conversations
@@ -214,11 +211,11 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── moderations.ts        # Content moderation
 │   │   ├── rerank.ts             # Reranking API
 │   │   └── search.ts             # Web search API
-│   ├── mcp-server/               # Built-in MCP server (105 tools, 3 transports: stdio/SSE/streamable-HTTP)
+│   ├── mcp-server/               # Built-in MCP server (109 tools, 3 transports: stdio/SSE/streamable-HTTP)
 │   │   ├── server.ts             # MCP server core (tool registration, scope enforcement)
 │   │   ├── tools/                # Tool implementations (advancedTools, memoryTools, skillTools)
 │   │   ├── schemas/              # Zod input schemas (tools, audit, a2a)
-│   │   ├── scopeEnforcement.ts   # Scope-based access control (31 scopes)
+│   │   ├── scopeEnforcement.ts   # Scope-based access control (33 scopes)
 │   │   ├── audit.ts              # Tool call audit logging
 │   │   ├── runtimeHeartbeat.ts   # MCP runtime heartbeat
 │   │   └── httpTransport.ts      # HTTP transport handler
@@ -269,7 +266,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── i18n/                     # 43-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
-│   ├── frameworks/               # MCP-SERVER.md (105 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
+│   ├── frameworks/               # MCP-SERVER.md (109 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
 │   ├── routing/                  # AUTO-COMBO.md (14-factor scoring), REASONING_REPLAY.md
 │   ├── security/                 # GUARDRAILS.md, COMPLIANCE.md, STEALTH_GUIDE.md, PUBLIC_CREDS.md, ERROR_SANITIZATION.md
 │   ├── guides/                   # USER_GUIDE.md, TROUBLESHOOTING.md, ELECTRON_GUIDE.md, I18N.md
@@ -352,9 +349,9 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 - **A2A** — Agent-to-Agent v0.3 protocol (JSON-RPC 2.0, 6 skills: smart-routing, quota-management, provider-discovery, cost-analysis, health-report, list-capabilities)
 - **ACP** — Agent Communication Protocol registry and manager
 
-### MCP Server (105 Tools)
+### MCP Server (109 Tools)
 
-105 tools across modules: **43 base** (health, combos, quotas, routing, cost, models, cache,
+109 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
 diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool**, **notion**,
 **obsidian**, **localCorpus**, **gamification**, and **plugin** modules. Full per-tool inventory:
 `docs/frameworks/MCP-SERVER.md`.
@@ -397,7 +394,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 8. **ProviderIcon component:** Unified icon system using `@lobehub/icons` (130+ SVG) with PNG fallback and generic icon fallback chain. Used on providers, dashboard, and agents pages.
 
-9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 99 `src/lib/db/` modules with 117 SQL migrations.
+9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 117 `src/lib/db/` modules with 148 SQL migrations.
 
 10. **Upstream headers:** Custom headers merged in executors after default auth; same header name replaces executor value. Forbidden header names in `src/shared/constants/upstreamHeaders.ts`.
 
@@ -441,7 +438,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 4. **Environment variables:** All configuration is in `.env` (from `.env.example`). Key vars: `PORT`, `NEXT_PUBLIC_BASE_URL`, `API_KEY`, `ADMIN_PASSWORD`.
 
-5. **Database layer:** Operations go through `src/lib/db/` modules (117 domain-specific files, 145 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
+5. **Database layer:** Operations go through `src/lib/db/` modules (117 domain-specific files, 148 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
 
 6. **Tests** use Node.js built-in test runner + Vitest. Run `npm test`. Vitest for MCP/autoCombo (`npm run test:vitest`). Playwright for E2E (`npm run test:e2e`). Coverage gate: ratchet vs `quality-baseline.json`, absolute floor 60% statements/lines/functions/branches.
 
@@ -485,7 +482,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 - **339-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
-- **MCP server expanded to 105 tools / 31 scopes** (base + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
+- **MCP server expanded to 109 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
 - **Cloud Agents** (Codex Cloud, Devin, Jules), **Guardrails**, **Evals**, **Webhooks**, **Compliance** frameworks
 - **Embedded services** manager (install/start/stop bundled services from the dashboard)
 - **Prompt compression** (RTK + Caveman codecs) saving up to ~95% tokens on eligible traffic

docs/i18n/ja/llm.txt

@@ -4,10 +4,7 @@
 
 ---
 
-
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 339 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (109 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
-
-
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 339 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (105 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -21,7 +18,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 - **Runtime:** Node.js `>=22.0.0 <23 || >=24.0.0 <27`, ES Modules (`"type": "module"`)
 - **Framework:** Next.js 16 (App Router) with TypeScript 6
-- **Database:** SQLite via better-sqlite3 (local, zero-config, 145 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 148 migrations)
 - **State management:** Zustand (client), SQLite (server persistence)
 - **UI:** React 19, Tailwind CSS 4, Recharts for analytics, @lobehub/icons for 130+ provider SVG icons
 - **Auth:** OAuth 2.0 (PKCE) for providers, bcrypt for local user auth
@@ -109,7 +106,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   └── streaming.ts      # SSE streaming for A2A
 │   │   ├── acp/                  # Agent Communication Protocol registry and manager
 │   │   ├── compliance/           # Compliance policy engine
-│   │   ├── db/                   # SQLite database layer (99 modules + migrations)
+│   │   ├── db/                   # SQLite database layer (117 modules + migrations)
 │   │   │   ├── core.ts           # Database initialization, connection, schema
 │   │   │   ├── providers.ts      # Provider connection CRUD
 │   │   │   ├── models.ts         # Model catalog management
@@ -131,7 +128,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   ├── secrets.ts        # Secrets management
 │   │   │   ├── stateReset.ts     # State reset utilities
 │   │   │   ├── migrationRunner.ts # Schema migration runner
-│   │   │   └── migrations/       # 117 versioned SQL migration files
+│   │   │   └── migrations/       # 148 versioned SQL migration files
 │   │   ├── evals/                # Eval runner and scheduler
 │   │   ├── memory/               # Persistent conversational memory
 │   │   │   ├── extraction.ts     # Memory extraction from conversations
@@ -214,11 +211,11 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── moderations.ts        # Content moderation
 │   │   ├── rerank.ts             # Reranking API
 │   │   └── search.ts             # Web search API
-│   ├── mcp-server/               # Built-in MCP server (105 tools, 3 transports: stdio/SSE/streamable-HTTP)
+│   ├── mcp-server/               # Built-in MCP server (109 tools, 3 transports: stdio/SSE/streamable-HTTP)
 │   │   ├── server.ts             # MCP server core (tool registration, scope enforcement)
 │   │   ├── tools/                # Tool implementations (advancedTools, memoryTools, skillTools)
 │   │   ├── schemas/              # Zod input schemas (tools, audit, a2a)
-│   │   ├── scopeEnforcement.ts   # Scope-based access control (31 scopes)
+│   │   ├── scopeEnforcement.ts   # Scope-based access control (33 scopes)
 │   │   ├── audit.ts              # Tool call audit logging
 │   │   ├── runtimeHeartbeat.ts   # MCP runtime heartbeat
 │   │   └── httpTransport.ts      # HTTP transport handler
@@ -269,7 +266,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── i18n/                     # 43-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
-│   ├── frameworks/               # MCP-SERVER.md (105 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
+│   ├── frameworks/               # MCP-SERVER.md (109 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
 │   ├── routing/                  # AUTO-COMBO.md (14-factor scoring), REASONING_REPLAY.md
 │   ├── security/                 # GUARDRAILS.md, COMPLIANCE.md, STEALTH_GUIDE.md, PUBLIC_CREDS.md, ERROR_SANITIZATION.md
 │   ├── guides/                   # USER_GUIDE.md, TROUBLESHOOTING.md, ELECTRON_GUIDE.md, I18N.md
@@ -352,9 +349,9 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 - **A2A** — Agent-to-Agent v0.3 protocol (JSON-RPC 2.0, 6 skills: smart-routing, quota-management, provider-discovery, cost-analysis, health-report, list-capabilities)
 - **ACP** — Agent Communication Protocol registry and manager
 
-### MCP Server (105 Tools)
+### MCP Server (109 Tools)
 
-105 tools across modules: **43 base** (health, combos, quotas, routing, cost, models, cache,
+109 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
 diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool**, **notion**,
 **obsidian**, **localCorpus**, **gamification**, and **plugin** modules. Full per-tool inventory:
 `docs/frameworks/MCP-SERVER.md`.
@@ -397,7 +394,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 8. **ProviderIcon component:** Unified icon system using `@lobehub/icons` (130+ SVG) with PNG fallback and generic icon fallback chain. Used on providers, dashboard, and agents pages.
 
-9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 99 `src/lib/db/` modules with 117 SQL migrations.
+9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 117 `src/lib/db/` modules with 148 SQL migrations.
 
 10. **Upstream headers:** Custom headers merged in executors after default auth; same header name replaces executor value. Forbidden header names in `src/shared/constants/upstreamHeaders.ts`.
 
@@ -441,7 +438,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 4. **Environment variables:** All configuration is in `.env` (from `.env.example`). Key vars: `PORT`, `NEXT_PUBLIC_BASE_URL`, `API_KEY`, `ADMIN_PASSWORD`.
 
-5. **Database layer:** Operations go through `src/lib/db/` modules (117 domain-specific files, 145 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
+5. **Database layer:** Operations go through `src/lib/db/` modules (117 domain-specific files, 148 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
 
 6. **Tests** use Node.js built-in test runner + Vitest. Run `npm test`. Vitest for MCP/autoCombo (`npm run test:vitest`). Playwright for E2E (`npm run test:e2e`). Coverage gate: ratchet vs `quality-baseline.json`, absolute floor 60% statements/lines/functions/branches.
 
@@ -485,7 +482,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 - **339-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
-- **MCP server expanded to 105 tools / 31 scopes** (base + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
+- **MCP server expanded to 109 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
 - **Cloud Agents** (Codex Cloud, Devin, Jules), **Guardrails**, **Evals**, **Webhooks**, **Compliance** frameworks
 - **Embedded services** manager (install/start/stop bundled services from the dashboard)
 - **Prompt compression** (RTK + Caveman codecs) saving up to ~95% tokens on eligible traffic

docs/i18n/ko/llm.txt

@@ -4,10 +4,7 @@
 
 ---
 
-
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 339 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (109 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
-
-
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 339 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (105 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -21,7 +18,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 - **Runtime:** Node.js `>=22.0.0 <23 || >=24.0.0 <27`, ES Modules (`"type": "module"`)
 - **Framework:** Next.js 16 (App Router) with TypeScript 6
-- **Database:** SQLite via better-sqlite3 (local, zero-config, 145 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 148 migrations)
 - **State management:** Zustand (client), SQLite (server persistence)
 - **UI:** React 19, Tailwind CSS 4, Recharts for analytics, @lobehub/icons for 130+ provider SVG icons
 - **Auth:** OAuth 2.0 (PKCE) for providers, bcrypt for local user auth
@@ -109,7 +106,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   └── streaming.ts      # SSE streaming for A2A
 │   │   ├── acp/                  # Agent Communication Protocol registry and manager
 │   │   ├── compliance/           # Compliance policy engine
-│   │   ├── db/                   # SQLite database layer (99 modules + migrations)
+│   │   ├── db/                   # SQLite database layer (117 modules + migrations)
 │   │   │   ├── core.ts           # Database initialization, connection, schema
 │   │   │   ├── providers.ts      # Provider connection CRUD
 │   │   │   ├── models.ts         # Model catalog management
@@ -131,7 +128,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   ├── secrets.ts        # Secrets management
 │   │   │   ├── stateReset.ts     # State reset utilities
 │   │   │   ├── migrationRunner.ts # Schema migration runner
-│   │   │   └── migrations/       # 117 versioned SQL migration files
+│   │   │   └── migrations/       # 148 versioned SQL migration files
 │   │   ├── evals/                # Eval runner and scheduler
 │   │   ├── memory/               # Persistent conversational memory
 │   │   │   ├── extraction.ts     # Memory extraction from conversations
@@ -214,11 +211,11 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── moderations.ts        # Content moderation
 │   │   ├── rerank.ts             # Reranking API
 │   │   └── search.ts             # Web search API
-│   ├── mcp-server/               # Built-in MCP server (105 tools, 3 transports: stdio/SSE/streamable-HTTP)
+│   ├── mcp-server/               # Built-in MCP server (109 tools, 3 transports: stdio/SSE/streamable-HTTP)
 │   │   ├── server.ts             # MCP server core (tool registration, scope enforcement)
 │   │   ├── tools/                # Tool implementations (advancedTools, memoryTools, skillTools)
 │   │   ├── schemas/              # Zod input schemas (tools, audit, a2a)
-│   │   ├── scopeEnforcement.ts   # Scope-based access control (31 scopes)
+│   │   ├── scopeEnforcement.ts   # Scope-based access control (33 scopes)
 │   │   ├── audit.ts              # Tool call audit logging
 │   │   ├── runtimeHeartbeat.ts   # MCP runtime heartbeat
 │   │   └── httpTransport.ts      # HTTP transport handler
@@ -269,7 +266,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── i18n/                     # 43-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
-│   ├── frameworks/               # MCP-SERVER.md (105 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
+│   ├── frameworks/               # MCP-SERVER.md (109 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
 │   ├── routing/                  # AUTO-COMBO.md (14-factor scoring), REASONING_REPLAY.md
 │   ├── security/                 # GUARDRAILS.md, COMPLIANCE.md, STEALTH_GUIDE.md, PUBLIC_CREDS.md, ERROR_SANITIZATION.md
 │   ├── guides/                   # USER_GUIDE.md, TROUBLESHOOTING.md, ELECTRON_GUIDE.md, I18N.md
@@ -352,9 +349,9 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 - **A2A** — Agent-to-Agent v0.3 protocol (JSON-RPC 2.0, 6 skills: smart-routing, quota-management, provider-discovery, cost-analysis, health-report, list-capabilities)
 - **ACP** — Agent Communication Protocol registry and manager
 
-### MCP Server (105 Tools)
+### MCP Server (109 Tools)
 
-105 tools across modules: **43 base** (health, combos, quotas, routing, cost, models, cache,
+109 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
 diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool**, **notion**,
 **obsidian**, **localCorpus**, **gamification**, and **plugin** modules. Full per-tool inventory:
 `docs/frameworks/MCP-SERVER.md`.
@@ -397,7 +394,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 8. **ProviderIcon component:** Unified icon system using `@lobehub/icons` (130+ SVG) with PNG fallback and generic icon fallback chain. Used on providers, dashboard, and agents pages.
 
-9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 99 `src/lib/db/` modules with 117 SQL migrations.
+9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 117 `src/lib/db/` modules with 148 SQL migrations.
 
 10. **Upstream headers:** Custom headers merged in executors after default auth; same header name replaces executor value. Forbidden header names in `src/shared/constants/upstreamHeaders.ts`.
 
@@ -441,7 +438,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 4. **Environment variables:** All configuration is in `.env` (from `.env.example`). Key vars: `PORT`, `NEXT_PUBLIC_BASE_URL`, `API_KEY`, `ADMIN_PASSWORD`.
 
-5. **Database layer:** Operations go through `src/lib/db/` modules (117 domain-specific files, 145 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
+5. **Database layer:** Operations go through `src/lib/db/` modules (117 domain-specific files, 148 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
 
 6. **Tests** use Node.js built-in test runner + Vitest. Run `npm test`. Vitest for MCP/autoCombo (`npm run test:vitest`). Playwright for E2E (`npm run test:e2e`). Coverage gate: ratchet vs `quality-baseline.json`, absolute floor 60% statements/lines/functions/branches.
 
@@ -485,7 +482,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 - **339-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
-- **MCP server expanded to 105 tools / 31 scopes** (base + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
+- **MCP server expanded to 109 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
 - **Cloud Agents** (Codex Cloud, Devin, Jules), **Guardrails**, **Evals**, **Webhooks**, **Compliance** frameworks
 - **Embedded services** manager (install/start/stop bundled services from the dashboard)
 - **Prompt compression** (RTK + Caveman codecs) saving up to ~95% tokens on eligible traffic

docs/i18n/mr/llm.txt

@@ -4,10 +4,7 @@
 
 ---
 
-
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 339 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (109 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
-
-
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 339 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (105 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -21,7 +18,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 - **Runtime:** Node.js `>=22.0.0 <23 || >=24.0.0 <27`, ES Modules (`"type": "module"`)
 - **Framework:** Next.js 16 (App Router) with TypeScript 6
-- **Database:** SQLite via better-sqlite3 (local, zero-config, 145 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 148 migrations)
 - **State management:** Zustand (client), SQLite (server persistence)
 - **UI:** React 19, Tailwind CSS 4, Recharts for analytics, @lobehub/icons for 130+ provider SVG icons
 - **Auth:** OAuth 2.0 (PKCE) for providers, bcrypt for local user auth
@@ -109,7 +106,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   └── streaming.ts      # SSE streaming for A2A
 │   │   ├── acp/                  # Agent Communication Protocol registry and manager
 │   │   ├── compliance/           # Compliance policy engine
-│   │   ├── db/                   # SQLite database layer (99 modules + migrations)
+│   │   ├── db/                   # SQLite database layer (117 modules + migrations)
 │   │   │   ├── core.ts           # Database initialization, connection, schema
 │   │   │   ├── providers.ts      # Provider connection CRUD
 │   │   │   ├── models.ts         # Model catalog management
@@ -131,7 +128,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   ├── secrets.ts        # Secrets management
 │   │   │   ├── stateReset.ts     # State reset utilities
 │   │   │   ├── migrationRunner.ts # Schema migration runner
-│   │   │   └── migrations/       # 117 versioned SQL migration files
+│   │   │   └── migrations/       # 148 versioned SQL migration files
 │   │   ├── evals/                # Eval runner and scheduler
 │   │   ├── memory/               # Persistent conversational memory
 │   │   │   ├── extraction.ts     # Memory extraction from conversations
@@ -214,11 +211,11 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── moderations.ts        # Content moderation
 │   │   ├── rerank.ts             # Reranking API
 │   │   └── search.ts             # Web search API
-│   ├── mcp-server/               # Built-in MCP server (105 tools, 3 transports: stdio/SSE/streamable-HTTP)
+│   ├── mcp-server/               # Built-in MCP server (109 tools, 3 transports: stdio/SSE/streamable-HTTP)
 │   │   ├── server.ts             # MCP server core (tool registration, scope enforcement)
 │   │   ├── tools/                # Tool implementations (advancedTools, memoryTools, skillTools)
 │   │   ├── schemas/              # Zod input schemas (tools, audit, a2a)
-│   │   ├── scopeEnforcement.ts   # Scope-based access control (31 scopes)
+│   │   ├── scopeEnforcement.ts   # Scope-based access control (33 scopes)
 │   │   ├── audit.ts              # Tool call audit logging
 │   │   ├── runtimeHeartbeat.ts   # MCP runtime heartbeat
 │   │   └── httpTransport.ts      # HTTP transport handler
@@ -269,7 +266,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── i18n/                     # 43-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
-│   ├── frameworks/               # MCP-SERVER.md (105 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
+│   ├── frameworks/               # MCP-SERVER.md (109 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
 │   ├── routing/                  # AUTO-COMBO.md (14-factor scoring), REASONING_REPLAY.md
 │   ├── security/                 # GUARDRAILS.md, COMPLIANCE.md, STEALTH_GUIDE.md, PUBLIC_CREDS.md, ERROR_SANITIZATION.md
 │   ├── guides/                   # USER_GUIDE.md, TROUBLESHOOTING.md, ELECTRON_GUIDE.md, I18N.md
@@ -352,9 +349,9 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 - **A2A** — Agent-to-Agent v0.3 protocol (JSON-RPC 2.0, 6 skills: smart-routing, quota-management, provider-discovery, cost-analysis, health-report, list-capabilities)
 - **ACP** — Agent Communication Protocol registry and manager
 
-### MCP Server (105 Tools)
+### MCP Server (109 Tools)
 
-105 tools across modules: **43 base** (health, combos, quotas, routing, cost, models, cache,
+109 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
 diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool**, **notion**,
 **obsidian**, **localCorpus**, **gamification**, and **plugin** modules. Full per-tool inventory:
 `docs/frameworks/MCP-SERVER.md`.
@@ -397,7 +394,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 8. **ProviderIcon component:** Unified icon system using `@lobehub/icons` (130+ SVG) with PNG fallback and generic icon fallback chain. Used on providers, dashboard, and agents pages.
 
-9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 99 `src/lib/db/` modules with 117 SQL migrations.
+9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 117 `src/lib/db/` modules with 148 SQL migrations.
 
 10. **Upstream headers:** Custom headers merged in executors after default auth; same header name replaces executor value. Forbidden header names in `src/shared/constants/upstreamHeaders.ts`.
 
@@ -441,7 +438,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 4. **Environment variables:** All configuration is in `.env` (from `.env.example`). Key vars: `PORT`, `NEXT_PUBLIC_BASE_URL`, `API_KEY`, `ADMIN_PASSWORD`.
 
-5. **Database layer:** Operations go through `src/lib/db/` modules (117 domain-specific files, 145 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
+5. **Database layer:** Operations go through `src/lib/db/` modules (117 domain-specific files, 148 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
 
 6. **Tests** use Node.js built-in test runner + Vitest. Run `npm test`. Vitest for MCP/autoCombo (`npm run test:vitest`). Playwright for E2E (`npm run test:e2e`). Coverage gate: ratchet vs `quality-baseline.json`, absolute floor 60% statements/lines/functions/branches.
 
@@ -485,7 +482,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 - **339-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
-- **MCP server expanded to 105 tools / 31 scopes** (base + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
+- **MCP server expanded to 109 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
 - **Cloud Agents** (Codex Cloud, Devin, Jules), **Guardrails**, **Evals**, **Webhooks**, **Compliance** frameworks
 - **Embedded services** manager (install/start/stop bundled services from the dashboard)
 - **Prompt compression** (RTK + Caveman codecs) saving up to ~95% tokens on eligible traffic

docs/i18n/ms/llm.txt

@@ -4,10 +4,7 @@
 
 ---
 
-
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 339 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (109 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
-
-
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 339 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (105 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -21,7 +18,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 - **Runtime:** Node.js `>=22.0.0 <23 || >=24.0.0 <27`, ES Modules (`"type": "module"`)
 - **Framework:** Next.js 16 (App Router) with TypeScript 6
-- **Database:** SQLite via better-sqlite3 (local, zero-config, 145 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 148 migrations)
 - **State management:** Zustand (client), SQLite (server persistence)
 - **UI:** React 19, Tailwind CSS 4, Recharts for analytics, @lobehub/icons for 130+ provider SVG icons
 - **Auth:** OAuth 2.0 (PKCE) for providers, bcrypt for local user auth
@@ -109,7 +106,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   └── streaming.ts      # SSE streaming for A2A
 │   │   ├── acp/                  # Agent Communication Protocol registry and manager
 │   │   ├── compliance/           # Compliance policy engine
-│   │   ├── db/                   # SQLite database layer (99 modules + migrations)
+│   │   ├── db/                   # SQLite database layer (117 modules + migrations)
 │   │   │   ├── core.ts           # Database initialization, connection, schema
 │   │   │   ├── providers.ts      # Provider connection CRUD
 │   │   │   ├── models.ts         # Model catalog management
@@ -131,7 +128,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   ├── secrets.ts        # Secrets management
 │   │   │   ├── stateReset.ts     # State reset utilities
 │   │   │   ├── migrationRunner.ts # Schema migration runner
-│   │   │   └── migrations/       # 117 versioned SQL migration files
+│   │   │   └── migrations/       # 148 versioned SQL migration files
 │   │   ├── evals/                # Eval runner and scheduler
 │   │   ├── memory/               # Persistent conversational memory
 │   │   │   ├── extraction.ts     # Memory extraction from conversations
@@ -214,11 +211,11 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── moderations.ts        # Content moderation
 │   │   ├── rerank.ts             # Reranking API
 │   │   └── search.ts             # Web search API
-│   ├── mcp-server/               # Built-in MCP server (105 tools, 3 transports: stdio/SSE/streamable-HTTP)
+│   ├── mcp-server/               # Built-in MCP server (109 tools, 3 transports: stdio/SSE/streamable-HTTP)
 │   │   ├── server.ts             # MCP server core (tool registration, scope enforcement)
 │   │   ├── tools/                # Tool implementations (advancedTools, memoryTools, skillTools)
 │   │   ├── schemas/              # Zod input schemas (tools, audit, a2a)
-│   │   ├── scopeEnforcement.ts   # Scope-based access control (31 scopes)
+│   │   ├── scopeEnforcement.ts   # Scope-based access control (33 scopes)
 │   │   ├── audit.ts              # Tool call audit logging
 │   │   ├── runtimeHeartbeat.ts   # MCP runtime heartbeat
 │   │   └── httpTransport.ts      # HTTP transport handler
@@ -269,7 +266,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── i18n/                     # 43-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
-│   ├── frameworks/               # MCP-SERVER.md (105 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
+│   ├── frameworks/               # MCP-SERVER.md (109 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
 │   ├── routing/                  # AUTO-COMBO.md (14-factor scoring), REASONING_REPLAY.md
 │   ├── security/                 # GUARDRAILS.md, COMPLIANCE.md, STEALTH_GUIDE.md, PUBLIC_CREDS.md, ERROR_SANITIZATION.md
 │   ├── guides/                   # USER_GUIDE.md, TROUBLESHOOTING.md, ELECTRON_GUIDE.md, I18N.md
@@ -352,9 +349,9 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 - **A2A** — Agent-to-Agent v0.3 protocol (JSON-RPC 2.0, 6 skills: smart-routing, quota-management, provider-discovery, cost-analysis, health-report, list-capabilities)
 - **ACP** — Agent Communication Protocol registry and manager
 
-### MCP Server (105 Tools)
+### MCP Server (109 Tools)
 
-105 tools across modules: **43 base** (health, combos, quotas, routing, cost, models, cache,
+109 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
 diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool**, **notion**,
 **obsidian**, **localCorpus**, **gamification**, and **plugin** modules. Full per-tool inventory:
 `docs/frameworks/MCP-SERVER.md`.
@@ -397,7 +394,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 8. **ProviderIcon component:** Unified icon system using `@lobehub/icons` (130+ SVG) with PNG fallback and generic icon fallback chain. Used on providers, dashboard, and agents pages.
 
-9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 99 `src/lib/db/` modules with 117 SQL migrations.
+9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 117 `src/lib/db/` modules with 148 SQL migrations.
 
 10. **Upstream headers:** Custom headers merged in executors after default auth; same header name replaces executor value. Forbidden header names in `src/shared/constants/upstreamHeaders.ts`.
 
@@ -441,7 +438,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 4. **Environment variables:** All configuration is in `.env` (from `.env.example`). Key vars: `PORT`, `NEXT_PUBLIC_BASE_URL`, `API_KEY`, `ADMIN_PASSWORD`.
 
-5. **Database layer:** Operations go through `src/lib/db/` modules (117 domain-specific files, 145 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
+5. **Database layer:** Operations go through `src/lib/db/` modules (117 domain-specific files, 148 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
 
 6. **Tests** use Node.js built-in test runner + Vitest. Run `npm test`. Vitest for MCP/autoCombo (`npm run test:vitest`). Playwright for E2E (`npm run test:e2e`). Coverage gate: ratchet vs `quality-baseline.json`, absolute floor 60% statements/lines/functions/branches.
 
@@ -485,7 +482,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 - **339-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
-- **MCP server expanded to 105 tools / 31 scopes** (base + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
+- **MCP server expanded to 109 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
 - **Cloud Agents** (Codex Cloud, Devin, Jules), **Guardrails**, **Evals**, **Webhooks**, **Compliance** frameworks
 - **Embedded services** manager (install/start/stop bundled services from the dashboard)
 - **Prompt compression** (RTK + Caveman codecs) saving up to ~95% tokens on eligible traffic

docs/i18n/nl/llm.txt

@@ -4,10 +4,7 @@
 
 ---
 
-
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 339 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (109 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
-
-
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 339 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (105 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -21,7 +18,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 - **Runtime:** Node.js `>=22.0.0 <23 || >=24.0.0 <27`, ES Modules (`"type": "module"`)
 - **Framework:** Next.js 16 (App Router) with TypeScript 6
-- **Database:** SQLite via better-sqlite3 (local, zero-config, 145 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 148 migrations)
 - **State management:** Zustand (client), SQLite (server persistence)
 - **UI:** React 19, Tailwind CSS 4, Recharts for analytics, @lobehub/icons for 130+ provider SVG icons
 - **Auth:** OAuth 2.0 (PKCE) for providers, bcrypt for local user auth
@@ -109,7 +106,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   └── streaming.ts      # SSE streaming for A2A
 │   │   ├── acp/                  # Agent Communication Protocol registry and manager
 │   │   ├── compliance/           # Compliance policy engine
-│   │   ├── db/                   # SQLite database layer (99 modules + migrations)
+│   │   ├── db/                   # SQLite database layer (117 modules + migrations)
 │   │   │   ├── core.ts           # Database initialization, connection, schema
 │   │   │   ├── providers.ts      # Provider connection CRUD
 │   │   │   ├── models.ts         # Model catalog management
@@ -131,7 +128,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   ├── secrets.ts        # Secrets management
 │   │   │   ├── stateReset.ts     # State reset utilities
 │   │   │   ├── migrationRunner.ts # Schema migration runner
-│   │   │   └── migrations/       # 117 versioned SQL migration files
+│   │   │   └── migrations/       # 148 versioned SQL migration files
 │   │   ├── evals/                # Eval runner and scheduler
 │   │   ├── memory/               # Persistent conversational memory
 │   │   │   ├── extraction.ts     # Memory extraction from conversations
@@ -214,11 +211,11 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── moderations.ts        # Content moderation
 │   │   ├── rerank.ts             # Reranking API
 │   │   └── search.ts             # Web search API
-│   ├── mcp-server/               # Built-in MCP server (105 tools, 3 transports: stdio/SSE/streamable-HTTP)
+│   ├── mcp-server/               # Built-in MCP server (109 tools, 3 transports: stdio/SSE/streamable-HTTP)
 │   │   ├── server.ts             # MCP server core (tool registration, scope enforcement)
 │   │   ├── tools/                # Tool implementations (advancedTools, memoryTools, skillTools)
 │   │   ├── schemas/              # Zod input schemas (tools, audit, a2a)
-│   │   ├── scopeEnforcement.ts   # Scope-based access control (31 scopes)
+│   │   ├── scopeEnforcement.ts   # Scope-based access control (33 scopes)
 │   │   ├── audit.ts              # Tool call audit logging
 │   │   ├── runtimeHeartbeat.ts   # MCP runtime heartbeat
 │   │   └── httpTransport.ts      # HTTP transport handler
@@ -269,7 +266,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── i18n/                     # 43-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
-│   ├── frameworks/               # MCP-SERVER.md (105 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
+│   ├── frameworks/               # MCP-SERVER.md (109 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
 │   ├── routing/                  # AUTO-COMBO.md (14-factor scoring), REASONING_REPLAY.md
 │   ├── security/                 # GUARDRAILS.md, COMPLIANCE.md, STEALTH_GUIDE.md, PUBLIC_CREDS.md, ERROR_SANITIZATION.md
 │   ├── guides/                   # USER_GUIDE.md, TROUBLESHOOTING.md, ELECTRON_GUIDE.md, I18N.md
@@ -352,9 +349,9 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 - **A2A** — Agent-to-Agent v0.3 protocol (JSON-RPC 2.0, 6 skills: smart-routing, quota-management, provider-discovery, cost-analysis, health-report, list-capabilities)
 - **ACP** — Agent Communication Protocol registry and manager
 
-### MCP Server (105 Tools)
+### MCP Server (109 Tools)
 
-105 tools across modules: **43 base** (health, combos, quotas, routing, cost, models, cache,
+109 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
 diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool**, **notion**,
 **obsidian**, **localCorpus**, **gamification**, and **plugin** modules. Full per-tool inventory:
 `docs/frameworks/MCP-SERVER.md`.
@@ -397,7 +394,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 8. **ProviderIcon component:** Unified icon system using `@lobehub/icons` (130+ SVG) with PNG fallback and generic icon fallback chain. Used on providers, dashboard, and agents pages.
 
-9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 99 `src/lib/db/` modules with 117 SQL migrations.
+9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 117 `src/lib/db/` modules with 148 SQL migrations.
 
 10. **Upstream headers:** Custom headers merged in executors after default auth; same header name replaces executor value. Forbidden header names in `src/shared/constants/upstreamHeaders.ts`.
 
@@ -441,7 +438,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 4. **Environment variables:** All configuration is in `.env` (from `.env.example`). Key vars: `PORT`, `NEXT_PUBLIC_BASE_URL`, `API_KEY`, `ADMIN_PASSWORD`.
 
-5. **Database layer:** Operations go through `src/lib/db/` modules (117 domain-specific files, 145 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
+5. **Database layer:** Operations go through `src/lib/db/` modules (117 domain-specific files, 148 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
 
 6. **Tests** use Node.js built-in test runner + Vitest. Run `npm test`. Vitest for MCP/autoCombo (`npm run test:vitest`). Playwright for E2E (`npm run test:e2e`). Coverage gate: ratchet vs `quality-baseline.json`, absolute floor 60% statements/lines/functions/branches.
 
@@ -485,7 +482,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 - **339-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
-- **MCP server expanded to 105 tools / 31 scopes** (base + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
+- **MCP server expanded to 109 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
 - **Cloud Agents** (Codex Cloud, Devin, Jules), **Guardrails**, **Evals**, **Webhooks**, **Compliance** frameworks
 - **Embedded services** manager (install/start/stop bundled services from the dashboard)
 - **Prompt compression** (RTK + Caveman codecs) saving up to ~95% tokens on eligible traffic

docs/i18n/no/llm.txt

@@ -4,10 +4,7 @@
 
 ---
 
-
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 339 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (109 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
-
-
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 339 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (105 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -21,7 +18,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 - **Runtime:** Node.js `>=22.0.0 <23 || >=24.0.0 <27`, ES Modules (`"type": "module"`)
 - **Framework:** Next.js 16 (App Router) with TypeScript 6
-- **Database:** SQLite via better-sqlite3 (local, zero-config, 145 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 148 migrations)
 - **State management:** Zustand (client), SQLite (server persistence)
 - **UI:** React 19, Tailwind CSS 4, Recharts for analytics, @lobehub/icons for 130+ provider SVG icons
 - **Auth:** OAuth 2.0 (PKCE) for providers, bcrypt for local user auth
@@ -109,7 +106,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   └── streaming.ts      # SSE streaming for A2A
 │   │   ├── acp/                  # Agent Communication Protocol registry and manager
 │   │   ├── compliance/           # Compliance policy engine
-│   │   ├── db/                   # SQLite database layer (99 modules + migrations)
+│   │   ├── db/                   # SQLite database layer (117 modules + migrations)
 │   │   │   ├── core.ts           # Database initialization, connection, schema
 │   │   │   ├── providers.ts      # Provider connection CRUD
 │   │   │   ├── models.ts         # Model catalog management
@@ -131,7 +128,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   ├── secrets.ts        # Secrets management
 │   │   │   ├── stateReset.ts     # State reset utilities
 │   │   │   ├── migrationRunner.ts # Schema migration runner
-│   │   │   └── migrations/       # 117 versioned SQL migration files
+│   │   │   └── migrations/       # 148 versioned SQL migration files
 │   │   ├── evals/                # Eval runner and scheduler
 │   │   ├── memory/               # Persistent conversational memory
 │   │   │   ├── extraction.ts     # Memory extraction from conversations
@@ -214,11 +211,11 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── moderations.ts        # Content moderation
 │   │   ├── rerank.ts             # Reranking API
 │   │   └── search.ts             # Web search API
-│   ├── mcp-server/               # Built-in MCP server (105 tools, 3 transports: stdio/SSE/streamable-HTTP)
+│   ├── mcp-server/               # Built-in MCP server (109 tools, 3 transports: stdio/SSE/streamable-HTTP)
 │   │   ├── server.ts             # MCP server core (tool registration, scope enforcement)
 │   │   ├── tools/                # Tool implementations (advancedTools, memoryTools, skillTools)
 │   │   ├── schemas/              # Zod input schemas (tools, audit, a2a)
-│   │   ├── scopeEnforcement.ts   # Scope-based access control (31 scopes)
+│   │   ├── scopeEnforcement.ts   # Scope-based access control (33 scopes)
 │   │   ├── audit.ts              # Tool call audit logging
 │   │   ├── runtimeHeartbeat.ts   # MCP runtime heartbeat
 │   │   └── httpTransport.ts      # HTTP transport handler
@@ -269,7 +266,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── i18n/                     # 43-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
-│   ├── frameworks/               # MCP-SERVER.md (105 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
+│   ├── frameworks/               # MCP-SERVER.md (109 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
 │   ├── routing/                  # AUTO-COMBO.md (14-factor scoring), REASONING_REPLAY.md
 │   ├── security/                 # GUARDRAILS.md, COMPLIANCE.md, STEALTH_GUIDE.md, PUBLIC_CREDS.md, ERROR_SANITIZATION.md
 │   ├── guides/                   # USER_GUIDE.md, TROUBLESHOOTING.md, ELECTRON_GUIDE.md, I18N.md
@@ -352,9 +349,9 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 - **A2A** — Agent-to-Agent v0.3 protocol (JSON-RPC 2.0, 6 skills: smart-routing, quota-management, provider-discovery, cost-analysis, health-report, list-capabilities)
 - **ACP** — Agent Communication Protocol registry and manager
 
-### MCP Server (105 Tools)
+### MCP Server (109 Tools)
 
-105 tools across modules: **43 base** (health, combos, quotas, routing, cost, models, cache,
+109 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
 diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool**, **notion**,
 **obsidian**, **localCorpus**, **gamification**, and **plugin** modules. Full per-tool inventory:
 `docs/frameworks/MCP-SERVER.md`.
@@ -397,7 +394,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 8. **ProviderIcon component:** Unified icon system using `@lobehub/icons` (130+ SVG) with PNG fallback and generic icon fallback chain. Used on providers, dashboard, and agents pages.
 
-9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 99 `src/lib/db/` modules with 117 SQL migrations.
+9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 117 `src/lib/db/` modules with 148 SQL migrations.
 
 10. **Upstream headers:** Custom headers merged in executors after default auth; same header name replaces executor value. Forbidden header names in `src/shared/constants/upstreamHeaders.ts`.
 
@@ -441,7 +438,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 4. **Environment variables:** All configuration is in `.env` (from `.env.example`). Key vars: `PORT`, `NEXT_PUBLIC_BASE_URL`, `API_KEY`, `ADMIN_PASSWORD`.
 
-5. **Database layer:** Operations go through `src/lib/db/` modules (117 domain-specific files, 145 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
+5. **Database layer:** Operations go through `src/lib/db/` modules (117 domain-specific files, 148 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
 
 6. **Tests** use Node.js built-in test runner + Vitest. Run `npm test`. Vitest for MCP/autoCombo (`npm run test:vitest`). Playwright for E2E (`npm run test:e2e`). Coverage gate: ratchet vs `quality-baseline.json`, absolute floor 60% statements/lines/functions/branches.
 
@@ -485,7 +482,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 - **339-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
-- **MCP server expanded to 105 tools / 31 scopes** (base + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
+- **MCP server expanded to 109 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
 - **Cloud Agents** (Codex Cloud, Devin, Jules), **Guardrails**, **Evals**, **Webhooks**, **Compliance** frameworks
 - **Embedded services** manager (install/start/stop bundled services from the dashboard)
 - **Prompt compression** (RTK + Caveman codecs) saving up to ~95% tokens on eligible traffic

docs/i18n/phi/llm.txt

@@ -4,10 +4,7 @@
 
 ---
 
-
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 339 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (109 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
-
-
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 339 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (105 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -21,7 +18,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 - **Runtime:** Node.js `>=22.0.0 <23 || >=24.0.0 <27`, ES Modules (`"type": "module"`)
 - **Framework:** Next.js 16 (App Router) with TypeScript 6
-- **Database:** SQLite via better-sqlite3 (local, zero-config, 145 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 148 migrations)
 - **State management:** Zustand (client), SQLite (server persistence)
 - **UI:** React 19, Tailwind CSS 4, Recharts for analytics, @lobehub/icons for 130+ provider SVG icons
 - **Auth:** OAuth 2.0 (PKCE) for providers, bcrypt for local user auth
@@ -109,7 +106,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   └── streaming.ts      # SSE streaming for A2A
 │   │   ├── acp/                  # Agent Communication Protocol registry and manager
 │   │   ├── compliance/           # Compliance policy engine
-│   │   ├── db/                   # SQLite database layer (99 modules + migrations)
+│   │   ├── db/                   # SQLite database layer (117 modules + migrations)
 │   │   │   ├── core.ts           # Database initialization, connection, schema
 │   │   │   ├── providers.ts      # Provider connection CRUD
 │   │   │   ├── models.ts         # Model catalog management
@@ -131,7 +128,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   ├── secrets.ts        # Secrets management
 │   │   │   ├── stateReset.ts     # State reset utilities
 │   │   │   ├── migrationRunner.ts # Schema migration runner
-│   │   │   └── migrations/       # 117 versioned SQL migration files
+│   │   │   └── migrations/       # 148 versioned SQL migration files
 │   │   ├── evals/                # Eval runner and scheduler
 │   │   ├── memory/               # Persistent conversational memory
 │   │   │   ├── extraction.ts     # Memory extraction from conversations
@@ -214,11 +211,11 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── moderations.ts        # Content moderation
 │   │   ├── rerank.ts             # Reranking API
 │   │   └── search.ts             # Web search API
-│   ├── mcp-server/               # Built-in MCP server (105 tools, 3 transports: stdio/SSE/streamable-HTTP)
+│   ├── mcp-server/               # Built-in MCP server (109 tools, 3 transports: stdio/SSE/streamable-HTTP)
 │   │   ├── server.ts             # MCP server core (tool registration, scope enforcement)
 │   │   ├── tools/                # Tool implementations (advancedTools, memoryTools, skillTools)
 │   │   ├── schemas/              # Zod input schemas (tools, audit, a2a)
-│   │   ├── scopeEnforcement.ts   # Scope-based access control (31 scopes)
+│   │   ├── scopeEnforcement.ts   # Scope-based access control (33 scopes)
 │   │   ├── audit.ts              # Tool call audit logging
 │   │   ├── runtimeHeartbeat.ts   # MCP runtime heartbeat
 │   │   └── httpTransport.ts      # HTTP transport handler
@@ -269,7 +266,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── i18n/                     # 43-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
-│   ├── frameworks/               # MCP-SERVER.md (105 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
+│   ├── frameworks/               # MCP-SERVER.md (109 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
 │   ├── routing/                  # AUTO-COMBO.md (14-factor scoring), REASONING_REPLAY.md
 │   ├── security/                 # GUARDRAILS.md, COMPLIANCE.md, STEALTH_GUIDE.md, PUBLIC_CREDS.md, ERROR_SANITIZATION.md
 │   ├── guides/                   # USER_GUIDE.md, TROUBLESHOOTING.md, ELECTRON_GUIDE.md, I18N.md
@@ -352,9 +349,9 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 - **A2A** — Agent-to-Agent v0.3 protocol (JSON-RPC 2.0, 6 skills: smart-routing, quota-management, provider-discovery, cost-analysis, health-report, list-capabilities)
 - **ACP** — Agent Communication Protocol registry and manager
 
-### MCP Server (105 Tools)
+### MCP Server (109 Tools)
 
-105 tools across modules: **43 base** (health, combos, quotas, routing, cost, models, cache,
+109 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
 diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool**, **notion**,
 **obsidian**, **localCorpus**, **gamification**, and **plugin** modules. Full per-tool inventory:
 `docs/frameworks/MCP-SERVER.md`.
@@ -397,7 +394,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 8. **ProviderIcon component:** Unified icon system using `@lobehub/icons` (130+ SVG) with PNG fallback and generic icon fallback chain. Used on providers, dashboard, and agents pages.
 
-9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 99 `src/lib/db/` modules with 117 SQL migrations.
+9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 117 `src/lib/db/` modules with 148 SQL migrations.
 
 10. **Upstream headers:** Custom headers merged in executors after default auth; same header name replaces executor value. Forbidden header names in `src/shared/constants/upstreamHeaders.ts`.
 
@@ -441,7 +438,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 4. **Environment variables:** All configuration is in `.env` (from `.env.example`). Key vars: `PORT`, `NEXT_PUBLIC_BASE_URL`, `API_KEY`, `ADMIN_PASSWORD`.
 
-5. **Database layer:** Operations go through `src/lib/db/` modules (117 domain-specific files, 145 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
+5. **Database layer:** Operations go through `src/lib/db/` modules (117 domain-specific files, 148 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
 
 6. **Tests** use Node.js built-in test runner + Vitest. Run `npm test`. Vitest for MCP/autoCombo (`npm run test:vitest`). Playwright for E2E (`npm run test:e2e`). Coverage gate: ratchet vs `quality-baseline.json`, absolute floor 60% statements/lines/functions/branches.
 
@@ -485,7 +482,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 - **339-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
-- **MCP server expanded to 105 tools / 31 scopes** (base + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
+- **MCP server expanded to 109 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
 - **Cloud Agents** (Codex Cloud, Devin, Jules), **Guardrails**, **Evals**, **Webhooks**, **Compliance** frameworks
 - **Embedded services** manager (install/start/stop bundled services from the dashboard)
 - **Prompt compression** (RTK + Caveman codecs) saving up to ~95% tokens on eligible traffic

docs/i18n/pl/llm.txt

@@ -4,10 +4,7 @@
 
 ---
 
-
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 339 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (109 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
-
-
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 339 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (105 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -21,7 +18,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 - **Runtime:** Node.js `>=22.0.0 <23 || >=24.0.0 <27`, ES Modules (`"type": "module"`)
 - **Framework:** Next.js 16 (App Router) with TypeScript 6
-- **Database:** SQLite via better-sqlite3 (local, zero-config, 145 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 148 migrations)
 - **State management:** Zustand (client), SQLite (server persistence)
 - **UI:** React 19, Tailwind CSS 4, Recharts for analytics, @lobehub/icons for 130+ provider SVG icons
 - **Auth:** OAuth 2.0 (PKCE) for providers, bcrypt for local user auth
@@ -109,7 +106,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   └── streaming.ts      # SSE streaming for A2A
 │   │   ├── acp/                  # Agent Communication Protocol registry and manager
 │   │   ├── compliance/           # Compliance policy engine
-│   │   ├── db/                   # SQLite database layer (99 modules + migrations)
+│   │   ├── db/                   # SQLite database layer (117 modules + migrations)
 │   │   │   ├── core.ts           # Database initialization, connection, schema
 │   │   │   ├── providers.ts      # Provider connection CRUD
 │   │   │   ├── models.ts         # Model catalog management
@@ -131,7 +128,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   ├── secrets.ts        # Secrets management
 │   │   │   ├── stateReset.ts     # State reset utilities
 │   │   │   ├── migrationRunner.ts # Schema migration runner
-│   │   │   └── migrations/       # 117 versioned SQL migration files
+│   │   │   └── migrations/       # 148 versioned SQL migration files
 │   │   ├── evals/                # Eval runner and scheduler
 │   │   ├── memory/               # Persistent conversational memory
 │   │   │   ├── extraction.ts     # Memory extraction from conversations
@@ -214,11 +211,11 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── moderations.ts        # Content moderation
 │   │   ├── rerank.ts             # Reranking API
 │   │   └── search.ts             # Web search API
-│   ├── mcp-server/               # Built-in MCP server (105 tools, 3 transports: stdio/SSE/streamable-HTTP)
+│   ├── mcp-server/               # Built-in MCP server (109 tools, 3 transports: stdio/SSE/streamable-HTTP)
 │   │   ├── server.ts             # MCP server core (tool registration, scope enforcement)
 │   │   ├── tools/                # Tool implementations (advancedTools, memoryTools, skillTools)
 │   │   ├── schemas/              # Zod input schemas (tools, audit, a2a)
-│   │   ├── scopeEnforcement.ts   # Scope-based access control (31 scopes)
+│   │   ├── scopeEnforcement.ts   # Scope-based access control (33 scopes)
 │   │   ├── audit.ts              # Tool call audit logging
 │   │   ├── runtimeHeartbeat.ts   # MCP runtime heartbeat
 │   │   └── httpTransport.ts      # HTTP transport handler
@@ -269,7 +266,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── i18n/                     # 43-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
-│   ├── frameworks/               # MCP-SERVER.md (105 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
+│   ├── frameworks/               # MCP-SERVER.md (109 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
 │   ├── routing/                  # AUTO-COMBO.md (14-factor scoring), REASONING_REPLAY.md
 │   ├── security/                 # GUARDRAILS.md, COMPLIANCE.md, STEALTH_GUIDE.md, PUBLIC_CREDS.md, ERROR_SANITIZATION.md
 │   ├── guides/                   # USER_GUIDE.md, TROUBLESHOOTING.md, ELECTRON_GUIDE.md, I18N.md
@@ -352,9 +349,9 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 - **A2A** — Agent-to-Agent v0.3 protocol (JSON-RPC 2.0, 6 skills: smart-routing, quota-management, provider-discovery, cost-analysis, health-report, list-capabilities)
 - **ACP** — Agent Communication Protocol registry and manager
 
-### MCP Server (105 Tools)
+### MCP Server (109 Tools)
 
-105 tools across modules: **43 base** (health, combos, quotas, routing, cost, models, cache,
+109 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
 diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool**, **notion**,
 **obsidian**, **localCorpus**, **gamification**, and **plugin** modules. Full per-tool inventory:
 `docs/frameworks/MCP-SERVER.md`.
@@ -397,7 +394,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 8. **ProviderIcon component:** Unified icon system using `@lobehub/icons` (130+ SVG) with PNG fallback and generic icon fallback chain. Used on providers, dashboard, and agents pages.
 
-9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 99 `src/lib/db/` modules with 117 SQL migrations.
+9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 117 `src/lib/db/` modules with 148 SQL migrations.
 
 10. **Upstream headers:** Custom headers merged in executors after default auth; same header name replaces executor value. Forbidden header names in `src/shared/constants/upstreamHeaders.ts`.
 
@@ -441,7 +438,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 4. **Environment variables:** All configuration is in `.env` (from `.env.example`). Key vars: `PORT`, `NEXT_PUBLIC_BASE_URL`, `API_KEY`, `ADMIN_PASSWORD`.
 
-5. **Database layer:** Operations go through `src/lib/db/` modules (117 domain-specific files, 145 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
+5. **Database layer:** Operations go through `src/lib/db/` modules (117 domain-specific files, 148 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
 
 6. **Tests** use Node.js built-in test runner + Vitest. Run `npm test`. Vitest for MCP/autoCombo (`npm run test:vitest`). Playwright for E2E (`npm run test:e2e`). Coverage gate: ratchet vs `quality-baseline.json`, absolute floor 60% statements/lines/functions/branches.
 
@@ -485,7 +482,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 - **339-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
-- **MCP server expanded to 105 tools / 31 scopes** (base + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
+- **MCP server expanded to 109 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
 - **Cloud Agents** (Codex Cloud, Devin, Jules), **Guardrails**, **Evals**, **Webhooks**, **Compliance** frameworks
 - **Embedded services** manager (install/start/stop bundled services from the dashboard)
 - **Prompt compression** (RTK + Caveman codecs) saving up to ~95% tokens on eligible traffic

docs/i18n/pt-BR/llm.txt

@@ -4,10 +4,7 @@
 
 ---
 
-
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 339 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (109 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
-
-
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 339 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (105 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -21,7 +18,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 - **Runtime:** Node.js `>=22.0.0 <23 || >=24.0.0 <27`, ES Modules (`"type": "module"`)
 - **Framework:** Next.js 16 (App Router) with TypeScript 6
-- **Database:** SQLite via better-sqlite3 (local, zero-config, 145 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 148 migrations)
 - **State management:** Zustand (client), SQLite (server persistence)
 - **UI:** React 19, Tailwind CSS 4, Recharts for analytics, @lobehub/icons for 130+ provider SVG icons
 - **Auth:** OAuth 2.0 (PKCE) for providers, bcrypt for local user auth
@@ -109,7 +106,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   └── streaming.ts      # SSE streaming for A2A
 │   │   ├── acp/                  # Agent Communication Protocol registry and manager
 │   │   ├── compliance/           # Compliance policy engine
-│   │   ├── db/                   # SQLite database layer (99 modules + migrations)
+│   │   ├── db/                   # SQLite database layer (117 modules + migrations)
 │   │   │   ├── core.ts           # Database initialization, connection, schema
 │   │   │   ├── providers.ts      # Provider connection CRUD
 │   │   │   ├── models.ts         # Model catalog management
@@ -131,7 +128,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   ├── secrets.ts        # Secrets management
 │   │   │   ├── stateReset.ts     # State reset utilities
 │   │   │   ├── migrationRunner.ts # Schema migration runner
-│   │   │   └── migrations/       # 117 versioned SQL migration files
+│   │   │   └── migrations/       # 148 versioned SQL migration files
 │   │   ├── evals/                # Eval runner and scheduler
 │   │   ├── memory/               # Persistent conversational memory
 │   │   │   ├── extraction.ts     # Memory extraction from conversations
@@ -214,11 +211,11 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── moderations.ts        # Content moderation
 │   │   ├── rerank.ts             # Reranking API
 │   │   └── search.ts             # Web search API
-│   ├── mcp-server/               # Built-in MCP server (105 tools, 3 transports: stdio/SSE/streamable-HTTP)
+│   ├── mcp-server/               # Built-in MCP server (109 tools, 3 transports: stdio/SSE/streamable-HTTP)
 │   │   ├── server.ts             # MCP server core (tool registration, scope enforcement)
 │   │   ├── tools/                # Tool implementations (advancedTools, memoryTools, skillTools)
 │   │   ├── schemas/              # Zod input schemas (tools, audit, a2a)
-│   │   ├── scopeEnforcement.ts   # Scope-based access control (31 scopes)
+│   │   ├── scopeEnforcement.ts   # Scope-based access control (33 scopes)
 │   │   ├── audit.ts              # Tool call audit logging
 │   │   ├── runtimeHeartbeat.ts   # MCP runtime heartbeat
 │   │   └── httpTransport.ts      # HTTP transport handler
@@ -269,7 +266,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── i18n/                     # 43-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
-│   ├── frameworks/               # MCP-SERVER.md (105 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
+│   ├── frameworks/               # MCP-SERVER.md (109 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
 │   ├── routing/                  # AUTO-COMBO.md (14-factor scoring), REASONING_REPLAY.md
 │   ├── security/                 # GUARDRAILS.md, COMPLIANCE.md, STEALTH_GUIDE.md, PUBLIC_CREDS.md, ERROR_SANITIZATION.md
 │   ├── guides/                   # USER_GUIDE.md, TROUBLESHOOTING.md, ELECTRON_GUIDE.md, I18N.md
@@ -352,9 +349,9 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 - **A2A** — Agent-to-Agent v0.3 protocol (JSON-RPC 2.0, 6 skills: smart-routing, quota-management, provider-discovery, cost-analysis, health-report, list-capabilities)
 - **ACP** — Agent Communication Protocol registry and manager
 
-### MCP Server (105 Tools)
+### MCP Server (109 Tools)
 
-105 tools across modules: **43 base** (health, combos, quotas, routing, cost, models, cache,
+109 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
 diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool**, **notion**,
 **obsidian**, **localCorpus**, **gamification**, and **plugin** modules. Full per-tool inventory:
 `docs/frameworks/MCP-SERVER.md`.
@@ -397,7 +394,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 8. **ProviderIcon component:** Unified icon system using `@lobehub/icons` (130+ SVG) with PNG fallback and generic icon fallback chain. Used on providers, dashboard, and agents pages.
 
-9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 99 `src/lib/db/` modules with 117 SQL migrations.
+9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 117 `src/lib/db/` modules with 148 SQL migrations.
 
 10. **Upstream headers:** Custom headers merged in executors after default auth; same header name replaces executor value. Forbidden header names in `src/shared/constants/upstreamHeaders.ts`.
 
@@ -441,7 +438,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 4. **Environment variables:** All configuration is in `.env` (from `.env.example`). Key vars: `PORT`, `NEXT_PUBLIC_BASE_URL`, `API_KEY`, `ADMIN_PASSWORD`.
 
-5. **Database layer:** Operations go through `src/lib/db/` modules (117 domain-specific files, 145 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
+5. **Database layer:** Operations go through `src/lib/db/` modules (117 domain-specific files, 148 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
 
 6. **Tests** use Node.js built-in test runner + Vitest. Run `npm test`. Vitest for MCP/autoCombo (`npm run test:vitest`). Playwright for E2E (`npm run test:e2e`). Coverage gate: ratchet vs `quality-baseline.json`, absolute floor 60% statements/lines/functions/branches.
 
@@ -485,7 +482,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 - **339-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
-- **MCP server expanded to 105 tools / 31 scopes** (base + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
+- **MCP server expanded to 109 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
 - **Cloud Agents** (Codex Cloud, Devin, Jules), **Guardrails**, **Evals**, **Webhooks**, **Compliance** frameworks
 - **Embedded services** manager (install/start/stop bundled services from the dashboard)
 - **Prompt compression** (RTK + Caveman codecs) saving up to ~95% tokens on eligible traffic

docs/i18n/pt/llm.txt

@@ -4,10 +4,7 @@
 
 ---
 
-
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 339 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (109 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
-
-
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 339 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (105 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -21,7 +18,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 - **Runtime:** Node.js `>=22.0.0 <23 || >=24.0.0 <27`, ES Modules (`"type": "module"`)
 - **Framework:** Next.js 16 (App Router) with TypeScript 6
-- **Database:** SQLite via better-sqlite3 (local, zero-config, 145 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 148 migrations)
 - **State management:** Zustand (client), SQLite (server persistence)
 - **UI:** React 19, Tailwind CSS 4, Recharts for analytics, @lobehub/icons for 130+ provider SVG icons
 - **Auth:** OAuth 2.0 (PKCE) for providers, bcrypt for local user auth
@@ -109,7 +106,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   └── streaming.ts      # SSE streaming for A2A
 │   │   ├── acp/                  # Agent Communication Protocol registry and manager
 │   │   ├── compliance/           # Compliance policy engine
-│   │   ├── db/                   # SQLite database layer (99 modules + migrations)
+│   │   ├── db/                   # SQLite database layer (117 modules + migrations)
 │   │   │   ├── core.ts           # Database initialization, connection, schema
 │   │   │   ├── providers.ts      # Provider connection CRUD
 │   │   │   ├── models.ts         # Model catalog management
@@ -131,7 +128,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   ├── secrets.ts        # Secrets management
 │   │   │   ├── stateReset.ts     # State reset utilities
 │   │   │   ├── migrationRunner.ts # Schema migration runner
-│   │   │   └── migrations/       # 117 versioned SQL migration files
+│   │   │   └── migrations/       # 148 versioned SQL migration files
 │   │   ├── evals/                # Eval runner and scheduler
 │   │   ├── memory/               # Persistent conversational memory
 │   │   │   ├── extraction.ts     # Memory extraction from conversations
@@ -214,11 +211,11 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── moderations.ts        # Content moderation
 │   │   ├── rerank.ts             # Reranking API
 │   │   └── search.ts             # Web search API
-│   ├── mcp-server/               # Built-in MCP server (105 tools, 3 transports: stdio/SSE/streamable-HTTP)
+│   ├── mcp-server/               # Built-in MCP server (109 tools, 3 transports: stdio/SSE/streamable-HTTP)
 │   │   ├── server.ts             # MCP server core (tool registration, scope enforcement)
 │   │   ├── tools/                # Tool implementations (advancedTools, memoryTools, skillTools)
 │   │   ├── schemas/              # Zod input schemas (tools, audit, a2a)
-│   │   ├── scopeEnforcement.ts   # Scope-based access control (31 scopes)
+│   │   ├── scopeEnforcement.ts   # Scope-based access control (33 scopes)
 │   │   ├── audit.ts              # Tool call audit logging
 │   │   ├── runtimeHeartbeat.ts   # MCP runtime heartbeat
 │   │   └── httpTransport.ts      # HTTP transport handler
@@ -269,7 +266,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── i18n/                     # 43-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
-│   ├── frameworks/               # MCP-SERVER.md (105 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
+│   ├── frameworks/               # MCP-SERVER.md (109 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
 │   ├── routing/                  # AUTO-COMBO.md (14-factor scoring), REASONING_REPLAY.md
 │   ├── security/                 # GUARDRAILS.md, COMPLIANCE.md, STEALTH_GUIDE.md, PUBLIC_CREDS.md, ERROR_SANITIZATION.md
 │   ├── guides/                   # USER_GUIDE.md, TROUBLESHOOTING.md, ELECTRON_GUIDE.md, I18N.md
@@ -352,9 +349,9 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 - **A2A** — Agent-to-Agent v0.3 protocol (JSON-RPC 2.0, 6 skills: smart-routing, quota-management, provider-discovery, cost-analysis, health-report, list-capabilities)
 - **ACP** — Agent Communication Protocol registry and manager
 
-### MCP Server (105 Tools)
+### MCP Server (109 Tools)
 
-105 tools across modules: **43 base** (health, combos, quotas, routing, cost, models, cache,
+109 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
 diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool**, **notion**,
 **obsidian**, **localCorpus**, **gamification**, and **plugin** modules. Full per-tool inventory:
 `docs/frameworks/MCP-SERVER.md`.
@@ -397,7 +394,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 8. **ProviderIcon component:** Unified icon system using `@lobehub/icons` (130+ SVG) with PNG fallback and generic icon fallback chain. Used on providers, dashboard, and agents pages.
 
-9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 99 `src/lib/db/` modules with 117 SQL migrations.
+9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 117 `src/lib/db/` modules with 148 SQL migrations.
 
 10. **Upstream headers:** Custom headers merged in executors after default auth; same header name replaces executor value. Forbidden header names in `src/shared/constants/upstreamHeaders.ts`.
 
@@ -441,7 +438,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 4. **Environment variables:** All configuration is in `.env` (from `.env.example`). Key vars: `PORT`, `NEXT_PUBLIC_BASE_URL`, `API_KEY`, `ADMIN_PASSWORD`.
 
-5. **Database layer:** Operations go through `src/lib/db/` modules (117 domain-specific files, 145 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
+5. **Database layer:** Operations go through `src/lib/db/` modules (117 domain-specific files, 148 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
 
 6. **Tests** use Node.js built-in test runner + Vitest. Run `npm test`. Vitest for MCP/autoCombo (`npm run test:vitest`). Playwright for E2E (`npm run test:e2e`). Coverage gate: ratchet vs `quality-baseline.json`, absolute floor 60% statements/lines/functions/branches.
 
@@ -485,7 +482,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 - **339-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
-- **MCP server expanded to 105 tools / 31 scopes** (base + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
+- **MCP server expanded to 109 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
 - **Cloud Agents** (Codex Cloud, Devin, Jules), **Guardrails**, **Evals**, **Webhooks**, **Compliance** frameworks
 - **Embedded services** manager (install/start/stop bundled services from the dashboard)
 - **Prompt compression** (RTK + Caveman codecs) saving up to ~95% tokens on eligible traffic

docs/i18n/ro/llm.txt

@@ -4,10 +4,7 @@
 
 ---
 
-
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 339 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (109 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
-
-
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 339 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (105 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -21,7 +18,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 - **Runtime:** Node.js `>=22.0.0 <23 || >=24.0.0 <27`, ES Modules (`"type": "module"`)
 - **Framework:** Next.js 16 (App Router) with TypeScript 6
-- **Database:** SQLite via better-sqlite3 (local, zero-config, 145 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 148 migrations)
 - **State management:** Zustand (client), SQLite (server persistence)
 - **UI:** React 19, Tailwind CSS 4, Recharts for analytics, @lobehub/icons for 130+ provider SVG icons
 - **Auth:** OAuth 2.0 (PKCE) for providers, bcrypt for local user auth
@@ -109,7 +106,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   └── streaming.ts      # SSE streaming for A2A
 │   │   ├── acp/                  # Agent Communication Protocol registry and manager
 │   │   ├── compliance/           # Compliance policy engine
-│   │   ├── db/                   # SQLite database layer (99 modules + migrations)
+│   │   ├── db/                   # SQLite database layer (117 modules + migrations)
 │   │   │   ├── core.ts           # Database initialization, connection, schema
 │   │   │   ├── providers.ts      # Provider connection CRUD
 │   │   │   ├── models.ts         # Model catalog management
@@ -131,7 +128,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   ├── secrets.ts        # Secrets management
 │   │   │   ├── stateReset.ts     # State reset utilities
 │   │   │   ├── migrationRunner.ts # Schema migration runner
-│   │   │   └── migrations/       # 117 versioned SQL migration files
+│   │   │   └── migrations/       # 148 versioned SQL migration files
 │   │   ├── evals/                # Eval runner and scheduler
 │   │   ├── memory/               # Persistent conversational memory
 │   │   │   ├── extraction.ts     # Memory extraction from conversations
@@ -214,11 +211,11 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── moderations.ts        # Content moderation
 │   │   ├── rerank.ts             # Reranking API
 │   │   └── search.ts             # Web search API
-│   ├── mcp-server/               # Built-in MCP server (105 tools, 3 transports: stdio/SSE/streamable-HTTP)
+│   ├── mcp-server/               # Built-in MCP server (109 tools, 3 transports: stdio/SSE/streamable-HTTP)
 │   │   ├── server.ts             # MCP server core (tool registration, scope enforcement)
 │   │   ├── tools/                # Tool implementations (advancedTools, memoryTools, skillTools)
 │   │   ├── schemas/              # Zod input schemas (tools, audit, a2a)
-│   │   ├── scopeEnforcement.ts   # Scope-based access control (31 scopes)
+│   │   ├── scopeEnforcement.ts   # Scope-based access control (33 scopes)
 │   │   ├── audit.ts              # Tool call audit logging
 │   │   ├── runtimeHeartbeat.ts   # MCP runtime heartbeat
 │   │   └── httpTransport.ts      # HTTP transport handler
@@ -269,7 +266,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── i18n/                     # 43-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
-│   ├── frameworks/               # MCP-SERVER.md (105 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
+│   ├── frameworks/               # MCP-SERVER.md (109 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
 │   ├── routing/                  # AUTO-COMBO.md (14-factor scoring), REASONING_REPLAY.md
 │   ├── security/                 # GUARDRAILS.md, COMPLIANCE.md, STEALTH_GUIDE.md, PUBLIC_CREDS.md, ERROR_SANITIZATION.md
 │   ├── guides/                   # USER_GUIDE.md, TROUBLESHOOTING.md, ELECTRON_GUIDE.md, I18N.md
@@ -352,9 +349,9 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 - **A2A** — Agent-to-Agent v0.3 protocol (JSON-RPC 2.0, 6 skills: smart-routing, quota-management, provider-discovery, cost-analysis, health-report, list-capabilities)
 - **ACP** — Agent Communication Protocol registry and manager
 
-### MCP Server (105 Tools)
+### MCP Server (109 Tools)
 
-105 tools across modules: **43 base** (health, combos, quotas, routing, cost, models, cache,
+109 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
 diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool**, **notion**,
 **obsidian**, **localCorpus**, **gamification**, and **plugin** modules. Full per-tool inventory:
 `docs/frameworks/MCP-SERVER.md`.
@@ -397,7 +394,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 8. **ProviderIcon component:** Unified icon system using `@lobehub/icons` (130+ SVG) with PNG fallback and generic icon fallback chain. Used on providers, dashboard, and agents pages.
 
-9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 99 `src/lib/db/` modules with 117 SQL migrations.
+9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 117 `src/lib/db/` modules with 148 SQL migrations.
 
 10. **Upstream headers:** Custom headers merged in executors after default auth; same header name replaces executor value. Forbidden header names in `src/shared/constants/upstreamHeaders.ts`.
 
@@ -441,7 +438,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 4. **Environment variables:** All configuration is in `.env` (from `.env.example`). Key vars: `PORT`, `NEXT_PUBLIC_BASE_URL`, `API_KEY`, `ADMIN_PASSWORD`.
 
-5. **Database layer:** Operations go through `src/lib/db/` modules (117 domain-specific files, 145 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
+5. **Database layer:** Operations go through `src/lib/db/` modules (117 domain-specific files, 148 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
 
 6. **Tests** use Node.js built-in test runner + Vitest. Run `npm test`. Vitest for MCP/autoCombo (`npm run test:vitest`). Playwright for E2E (`npm run test:e2e`). Coverage gate: ratchet vs `quality-baseline.json`, absolute floor 60% statements/lines/functions/branches.
 
@@ -485,7 +482,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 - **339-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
-- **MCP server expanded to 105 tools / 31 scopes** (base + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
+- **MCP server expanded to 109 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
 - **Cloud Agents** (Codex Cloud, Devin, Jules), **Guardrails**, **Evals**, **Webhooks**, **Compliance** frameworks
 - **Embedded services** manager (install/start/stop bundled services from the dashboard)
 - **Prompt compression** (RTK + Caveman codecs) saving up to ~95% tokens on eligible traffic

docs/i18n/ru/llm.txt

@@ -4,10 +4,7 @@
 
 ---
 
-
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 339 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (109 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
-
-
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 339 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (105 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -21,7 +18,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 - **Runtime:** Node.js `>=22.0.0 <23 || >=24.0.0 <27`, ES Modules (`"type": "module"`)
 - **Framework:** Next.js 16 (App Router) with TypeScript 6
-- **Database:** SQLite via better-sqlite3 (local, zero-config, 145 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 148 migrations)
 - **State management:** Zustand (client), SQLite (server persistence)
 - **UI:** React 19, Tailwind CSS 4, Recharts for analytics, @lobehub/icons for 130+ provider SVG icons
 - **Auth:** OAuth 2.0 (PKCE) for providers, bcrypt for local user auth
@@ -109,7 +106,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   └── streaming.ts      # SSE streaming for A2A
 │   │   ├── acp/                  # Agent Communication Protocol registry and manager
 │   │   ├── compliance/           # Compliance policy engine
-│   │   ├── db/                   # SQLite database layer (99 modules + migrations)
+│   │   ├── db/                   # SQLite database layer (117 modules + migrations)
 │   │   │   ├── core.ts           # Database initialization, connection, schema
 │   │   │   ├── providers.ts      # Provider connection CRUD
 │   │   │   ├── models.ts         # Model catalog management
@@ -131,7 +128,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   ├── secrets.ts        # Secrets management
 │   │   │   ├── stateReset.ts     # State reset utilities
 │   │   │   ├── migrationRunner.ts # Schema migration runner
-│   │   │   └── migrations/       # 117 versioned SQL migration files
+│   │   │   └── migrations/       # 148 versioned SQL migration files
 │   │   ├── evals/                # Eval runner and scheduler
 │   │   ├── memory/               # Persistent conversational memory
 │   │   │   ├── extraction.ts     # Memory extraction from conversations
@@ -214,11 +211,11 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── moderations.ts        # Content moderation
 │   │   ├── rerank.ts             # Reranking API
 │   │   └── search.ts             # Web search API
-│   ├── mcp-server/               # Built-in MCP server (105 tools, 3 transports: stdio/SSE/streamable-HTTP)
+│   ├── mcp-server/               # Built-in MCP server (109 tools, 3 transports: stdio/SSE/streamable-HTTP)
 │   │   ├── server.ts             # MCP server core (tool registration, scope enforcement)
 │   │   ├── tools/                # Tool implementations (advancedTools, memoryTools, skillTools)
 │   │   ├── schemas/              # Zod input schemas (tools, audit, a2a)
-│   │   ├── scopeEnforcement.ts   # Scope-based access control (31 scopes)
+│   │   ├── scopeEnforcement.ts   # Scope-based access control (33 scopes)
 │   │   ├── audit.ts              # Tool call audit logging
 │   │   ├── runtimeHeartbeat.ts   # MCP runtime heartbeat
 │   │   └── httpTransport.ts      # HTTP transport handler
@@ -269,7 +266,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── i18n/                     # 43-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
-│   ├── frameworks/               # MCP-SERVER.md (105 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
+│   ├── frameworks/               # MCP-SERVER.md (109 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
 │   ├── routing/                  # AUTO-COMBO.md (14-factor scoring), REASONING_REPLAY.md
 │   ├── security/                 # GUARDRAILS.md, COMPLIANCE.md, STEALTH_GUIDE.md, PUBLIC_CREDS.md, ERROR_SANITIZATION.md
 │   ├── guides/                   # USER_GUIDE.md, TROUBLESHOOTING.md, ELECTRON_GUIDE.md, I18N.md
@@ -352,9 +349,9 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 - **A2A** — Agent-to-Agent v0.3 protocol (JSON-RPC 2.0, 6 skills: smart-routing, quota-management, provider-discovery, cost-analysis, health-report, list-capabilities)
 - **ACP** — Agent Communication Protocol registry and manager
 
-### MCP Server (105 Tools)
+### MCP Server (109 Tools)
 
-105 tools across modules: **43 base** (health, combos, quotas, routing, cost, models, cache,
+109 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
 diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool**, **notion**,
 **obsidian**, **localCorpus**, **gamification**, and **plugin** modules. Full per-tool inventory:
 `docs/frameworks/MCP-SERVER.md`.
@@ -397,7 +394,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 8. **ProviderIcon component:** Unified icon system using `@lobehub/icons` (130+ SVG) with PNG fallback and generic icon fallback chain. Used on providers, dashboard, and agents pages.
 
-9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 99 `src/lib/db/` modules with 117 SQL migrations.
+9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 117 `src/lib/db/` modules with 148 SQL migrations.
 
 10. **Upstream headers:** Custom headers merged in executors after default auth; same header name replaces executor value. Forbidden header names in `src/shared/constants/upstreamHeaders.ts`.
 
@@ -441,7 +438,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 4. **Environment variables:** All configuration is in `.env` (from `.env.example`). Key vars: `PORT`, `NEXT_PUBLIC_BASE_URL`, `API_KEY`, `ADMIN_PASSWORD`.
 
-5. **Database layer:** Operations go through `src/lib/db/` modules (117 domain-specific files, 145 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
+5. **Database layer:** Operations go through `src/lib/db/` modules (117 domain-specific files, 148 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
 
 6. **Tests** use Node.js built-in test runner + Vitest. Run `npm test`. Vitest for MCP/autoCombo (`npm run test:vitest`). Playwright for E2E (`npm run test:e2e`). Coverage gate: ratchet vs `quality-baseline.json`, absolute floor 60% statements/lines/functions/branches.
 
@@ -485,7 +482,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 - **339-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
-- **MCP server expanded to 105 tools / 31 scopes** (base + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
+- **MCP server expanded to 109 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
 - **Cloud Agents** (Codex Cloud, Devin, Jules), **Guardrails**, **Evals**, **Webhooks**, **Compliance** frameworks
 - **Embedded services** manager (install/start/stop bundled services from the dashboard)
 - **Prompt compression** (RTK + Caveman codecs) saving up to ~95% tokens on eligible traffic

docs/i18n/sk/llm.txt

@@ -4,10 +4,7 @@
 
 ---
 
-
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 339 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (109 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
-
-
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 339 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (105 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -21,7 +18,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 - **Runtime:** Node.js `>=22.0.0 <23 || >=24.0.0 <27`, ES Modules (`"type": "module"`)
 - **Framework:** Next.js 16 (App Router) with TypeScript 6
-- **Database:** SQLite via better-sqlite3 (local, zero-config, 145 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 148 migrations)
 - **State management:** Zustand (client), SQLite (server persistence)
 - **UI:** React 19, Tailwind CSS 4, Recharts for analytics, @lobehub/icons for 130+ provider SVG icons
 - **Auth:** OAuth 2.0 (PKCE) for providers, bcrypt for local user auth
@@ -109,7 +106,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   └── streaming.ts      # SSE streaming for A2A
 │   │   ├── acp/                  # Agent Communication Protocol registry and manager
 │   │   ├── compliance/           # Compliance policy engine
-│   │   ├── db/                   # SQLite database layer (99 modules + migrations)
+│   │   ├── db/                   # SQLite database layer (117 modules + migrations)
 │   │   │   ├── core.ts           # Database initialization, connection, schema
 │   │   │   ├── providers.ts      # Provider connection CRUD
 │   │   │   ├── models.ts         # Model catalog management
@@ -131,7 +128,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   ├── secrets.ts        # Secrets management
 │   │   │   ├── stateReset.ts     # State reset utilities
 │   │   │   ├── migrationRunner.ts # Schema migration runner
-│   │   │   └── migrations/       # 117 versioned SQL migration files
+│   │   │   └── migrations/       # 148 versioned SQL migration files
 │   │   ├── evals/                # Eval runner and scheduler
 │   │   ├── memory/               # Persistent conversational memory
 │   │   │   ├── extraction.ts     # Memory extraction from conversations
@@ -214,11 +211,11 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── moderations.ts        # Content moderation
 │   │   ├── rerank.ts             # Reranking API
 │   │   └── search.ts             # Web search API
-│   ├── mcp-server/               # Built-in MCP server (105 tools, 3 transports: stdio/SSE/streamable-HTTP)
+│   ├── mcp-server/               # Built-in MCP server (109 tools, 3 transports: stdio/SSE/streamable-HTTP)
 │   │   ├── server.ts             # MCP server core (tool registration, scope enforcement)
 │   │   ├── tools/                # Tool implementations (advancedTools, memoryTools, skillTools)
 │   │   ├── schemas/              # Zod input schemas (tools, audit, a2a)
-│   │   ├── scopeEnforcement.ts   # Scope-based access control (31 scopes)
+│   │   ├── scopeEnforcement.ts   # Scope-based access control (33 scopes)
 │   │   ├── audit.ts              # Tool call audit logging
 │   │   ├── runtimeHeartbeat.ts   # MCP runtime heartbeat
 │   │   └── httpTransport.ts      # HTTP transport handler
@@ -269,7 +266,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── i18n/                     # 43-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
-│   ├── frameworks/               # MCP-SERVER.md (105 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
+│   ├── frameworks/               # MCP-SERVER.md (109 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
 │   ├── routing/                  # AUTO-COMBO.md (14-factor scoring), REASONING_REPLAY.md
 │   ├── security/                 # GUARDRAILS.md, COMPLIANCE.md, STEALTH_GUIDE.md, PUBLIC_CREDS.md, ERROR_SANITIZATION.md
 │   ├── guides/                   # USER_GUIDE.md, TROUBLESHOOTING.md, ELECTRON_GUIDE.md, I18N.md
@@ -352,9 +349,9 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 - **A2A** — Agent-to-Agent v0.3 protocol (JSON-RPC 2.0, 6 skills: smart-routing, quota-management, provider-discovery, cost-analysis, health-report, list-capabilities)
 - **ACP** — Agent Communication Protocol registry and manager
 
-### MCP Server (105 Tools)
+### MCP Server (109 Tools)
 
-105 tools across modules: **43 base** (health, combos, quotas, routing, cost, models, cache,
+109 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
 diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool**, **notion**,
 **obsidian**, **localCorpus**, **gamification**, and **plugin** modules. Full per-tool inventory:
 `docs/frameworks/MCP-SERVER.md`.
@@ -397,7 +394,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 8. **ProviderIcon component:** Unified icon system using `@lobehub/icons` (130+ SVG) with PNG fallback and generic icon fallback chain. Used on providers, dashboard, and agents pages.
 
-9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 99 `src/lib/db/` modules with 117 SQL migrations.
+9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 117 `src/lib/db/` modules with 148 SQL migrations.
 
 10. **Upstream headers:** Custom headers merged in executors after default auth; same header name replaces executor value. Forbidden header names in `src/shared/constants/upstreamHeaders.ts`.
 
@@ -441,7 +438,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 4. **Environment variables:** All configuration is in `.env` (from `.env.example`). Key vars: `PORT`, `NEXT_PUBLIC_BASE_URL`, `API_KEY`, `ADMIN_PASSWORD`.
 
-5. **Database layer:** Operations go through `src/lib/db/` modules (117 domain-specific files, 145 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
+5. **Database layer:** Operations go through `src/lib/db/` modules (117 domain-specific files, 148 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
 
 6. **Tests** use Node.js built-in test runner + Vitest. Run `npm test`. Vitest for MCP/autoCombo (`npm run test:vitest`). Playwright for E2E (`npm run test:e2e`). Coverage gate: ratchet vs `quality-baseline.json`, absolute floor 60% statements/lines/functions/branches.
 
@@ -485,7 +482,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 - **339-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
-- **MCP server expanded to 105 tools / 31 scopes** (base + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
+- **MCP server expanded to 109 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
 - **Cloud Agents** (Codex Cloud, Devin, Jules), **Guardrails**, **Evals**, **Webhooks**, **Compliance** frameworks
 - **Embedded services** manager (install/start/stop bundled services from the dashboard)
 - **Prompt compression** (RTK + Caveman codecs) saving up to ~95% tokens on eligible traffic

docs/i18n/sv/llm.txt

@@ -4,10 +4,7 @@
 
 ---
 
-
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 339 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (109 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
-
-
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 339 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (105 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -21,7 +18,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 - **Runtime:** Node.js `>=22.0.0 <23 || >=24.0.0 <27`, ES Modules (`"type": "module"`)
 - **Framework:** Next.js 16 (App Router) with TypeScript 6
-- **Database:** SQLite via better-sqlite3 (local, zero-config, 145 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 148 migrations)
 - **State management:** Zustand (client), SQLite (server persistence)
 - **UI:** React 19, Tailwind CSS 4, Recharts for analytics, @lobehub/icons for 130+ provider SVG icons
 - **Auth:** OAuth 2.0 (PKCE) for providers, bcrypt for local user auth
@@ -109,7 +106,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   └── streaming.ts      # SSE streaming for A2A
 │   │   ├── acp/                  # Agent Communication Protocol registry and manager
 │   │   ├── compliance/           # Compliance policy engine
-│   │   ├── db/                   # SQLite database layer (99 modules + migrations)
+│   │   ├── db/                   # SQLite database layer (117 modules + migrations)
 │   │   │   ├── core.ts           # Database initialization, connection, schema
 │   │   │   ├── providers.ts      # Provider connection CRUD
 │   │   │   ├── models.ts         # Model catalog management
@@ -131,7 +128,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   ├── secrets.ts        # Secrets management
 │   │   │   ├── stateReset.ts     # State reset utilities
 │   │   │   ├── migrationRunner.ts # Schema migration runner
-│   │   │   └── migrations/       # 117 versioned SQL migration files
+│   │   │   └── migrations/       # 148 versioned SQL migration files
 │   │   ├── evals/                # Eval runner and scheduler
 │   │   ├── memory/               # Persistent conversational memory
 │   │   │   ├── extraction.ts     # Memory extraction from conversations
@@ -214,11 +211,11 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── moderations.ts        # Content moderation
 │   │   ├── rerank.ts             # Reranking API
 │   │   └── search.ts             # Web search API
-│   ├── mcp-server/               # Built-in MCP server (105 tools, 3 transports: stdio/SSE/streamable-HTTP)
+│   ├── mcp-server/               # Built-in MCP server (109 tools, 3 transports: stdio/SSE/streamable-HTTP)
 │   │   ├── server.ts             # MCP server core (tool registration, scope enforcement)
 │   │   ├── tools/                # Tool implementations (advancedTools, memoryTools, skillTools)
 │   │   ├── schemas/              # Zod input schemas (tools, audit, a2a)
-│   │   ├── scopeEnforcement.ts   # Scope-based access control (31 scopes)
+│   │   ├── scopeEnforcement.ts   # Scope-based access control (33 scopes)
 │   │   ├── audit.ts              # Tool call audit logging
 │   │   ├── runtimeHeartbeat.ts   # MCP runtime heartbeat
 │   │   └── httpTransport.ts      # HTTP transport handler
@@ -269,7 +266,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── i18n/                     # 43-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
-│   ├── frameworks/               # MCP-SERVER.md (105 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
+│   ├── frameworks/               # MCP-SERVER.md (109 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
 │   ├── routing/                  # AUTO-COMBO.md (14-factor scoring), REASONING_REPLAY.md
 │   ├── security/                 # GUARDRAILS.md, COMPLIANCE.md, STEALTH_GUIDE.md, PUBLIC_CREDS.md, ERROR_SANITIZATION.md
 │   ├── guides/                   # USER_GUIDE.md, TROUBLESHOOTING.md, ELECTRON_GUIDE.md, I18N.md
@@ -352,9 +349,9 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 - **A2A** — Agent-to-Agent v0.3 protocol (JSON-RPC 2.0, 6 skills: smart-routing, quota-management, provider-discovery, cost-analysis, health-report, list-capabilities)
 - **ACP** — Agent Communication Protocol registry and manager
 
-### MCP Server (105 Tools)
+### MCP Server (109 Tools)
 
-105 tools across modules: **43 base** (health, combos, quotas, routing, cost, models, cache,
+109 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
 diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool**, **notion**,
 **obsidian**, **localCorpus**, **gamification**, and **plugin** modules. Full per-tool inventory:
 `docs/frameworks/MCP-SERVER.md`.
@@ -397,7 +394,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 8. **ProviderIcon component:** Unified icon system using `@lobehub/icons` (130+ SVG) with PNG fallback and generic icon fallback chain. Used on providers, dashboard, and agents pages.
 
-9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 99 `src/lib/db/` modules with 117 SQL migrations.
+9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 117 `src/lib/db/` modules with 148 SQL migrations.
 
 10. **Upstream headers:** Custom headers merged in executors after default auth; same header name replaces executor value. Forbidden header names in `src/shared/constants/upstreamHeaders.ts`.
 
@@ -441,7 +438,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 4. **Environment variables:** All configuration is in `.env` (from `.env.example`). Key vars: `PORT`, `NEXT_PUBLIC_BASE_URL`, `API_KEY`, `ADMIN_PASSWORD`.
 
-5. **Database layer:** Operations go through `src/lib/db/` modules (117 domain-specific files, 145 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
+5. **Database layer:** Operations go through `src/lib/db/` modules (117 domain-specific files, 148 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
 
 6. **Tests** use Node.js built-in test runner + Vitest. Run `npm test`. Vitest for MCP/autoCombo (`npm run test:vitest`). Playwright for E2E (`npm run test:e2e`). Coverage gate: ratchet vs `quality-baseline.json`, absolute floor 60% statements/lines/functions/branches.
 
@@ -485,7 +482,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 - **339-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
-- **MCP server expanded to 105 tools / 31 scopes** (base + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
+- **MCP server expanded to 109 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
 - **Cloud Agents** (Codex Cloud, Devin, Jules), **Guardrails**, **Evals**, **Webhooks**, **Compliance** frameworks
 - **Embedded services** manager (install/start/stop bundled services from the dashboard)
 - **Prompt compression** (RTK + Caveman codecs) saving up to ~95% tokens on eligible traffic

docs/i18n/sw/llm.txt

@@ -4,10 +4,7 @@
 
 ---
 
-
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 339 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (109 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
-
-
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 339 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (105 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -21,7 +18,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 - **Runtime:** Node.js `>=22.0.0 <23 || >=24.0.0 <27`, ES Modules (`"type": "module"`)
 - **Framework:** Next.js 16 (App Router) with TypeScript 6
-- **Database:** SQLite via better-sqlite3 (local, zero-config, 145 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 148 migrations)
 - **State management:** Zustand (client), SQLite (server persistence)
 - **UI:** React 19, Tailwind CSS 4, Recharts for analytics, @lobehub/icons for 130+ provider SVG icons
 - **Auth:** OAuth 2.0 (PKCE) for providers, bcrypt for local user auth
@@ -109,7 +106,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   └── streaming.ts      # SSE streaming for A2A
 │   │   ├── acp/                  # Agent Communication Protocol registry and manager
 │   │   ├── compliance/           # Compliance policy engine
-│   │   ├── db/                   # SQLite database layer (99 modules + migrations)
+│   │   ├── db/                   # SQLite database layer (117 modules + migrations)
 │   │   │   ├── core.ts           # Database initialization, connection, schema
 │   │   │   ├── providers.ts      # Provider connection CRUD
 │   │   │   ├── models.ts         # Model catalog management
@@ -131,7 +128,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   ├── secrets.ts        # Secrets management
 │   │   │   ├── stateReset.ts     # State reset utilities
 │   │   │   ├── migrationRunner.ts # Schema migration runner
-│   │   │   └── migrations/       # 117 versioned SQL migration files
+│   │   │   └── migrations/       # 148 versioned SQL migration files
 │   │   ├── evals/                # Eval runner and scheduler
 │   │   ├── memory/               # Persistent conversational memory
 │   │   │   ├── extraction.ts     # Memory extraction from conversations
@@ -214,11 +211,11 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── moderations.ts        # Content moderation
 │   │   ├── rerank.ts             # Reranking API
 │   │   └── search.ts             # Web search API
-│   ├── mcp-server/               # Built-in MCP server (105 tools, 3 transports: stdio/SSE/streamable-HTTP)
+│   ├── mcp-server/               # Built-in MCP server (109 tools, 3 transports: stdio/SSE/streamable-HTTP)
 │   │   ├── server.ts             # MCP server core (tool registration, scope enforcement)
 │   │   ├── tools/                # Tool implementations (advancedTools, memoryTools, skillTools)
 │   │   ├── schemas/              # Zod input schemas (tools, audit, a2a)
-│   │   ├── scopeEnforcement.ts   # Scope-based access control (31 scopes)
+│   │   ├── scopeEnforcement.ts   # Scope-based access control (33 scopes)
 │   │   ├── audit.ts              # Tool call audit logging
 │   │   ├── runtimeHeartbeat.ts   # MCP runtime heartbeat
 │   │   └── httpTransport.ts      # HTTP transport handler
@@ -269,7 +266,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── i18n/                     # 43-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
-│   ├── frameworks/               # MCP-SERVER.md (105 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
+│   ├── frameworks/               # MCP-SERVER.md (109 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
 │   ├── routing/                  # AUTO-COMBO.md (14-factor scoring), REASONING_REPLAY.md
 │   ├── security/                 # GUARDRAILS.md, COMPLIANCE.md, STEALTH_GUIDE.md, PUBLIC_CREDS.md, ERROR_SANITIZATION.md
 │   ├── guides/                   # USER_GUIDE.md, TROUBLESHOOTING.md, ELECTRON_GUIDE.md, I18N.md
@@ -352,9 +349,9 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 - **A2A** — Agent-to-Agent v0.3 protocol (JSON-RPC 2.0, 6 skills: smart-routing, quota-management, provider-discovery, cost-analysis, health-report, list-capabilities)
 - **ACP** — Agent Communication Protocol registry and manager
 
-### MCP Server (105 Tools)
+### MCP Server (109 Tools)
 
-105 tools across modules: **43 base** (health, combos, quotas, routing, cost, models, cache,
+109 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
 diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool**, **notion**,
 **obsidian**, **localCorpus**, **gamification**, and **plugin** modules. Full per-tool inventory:
 `docs/frameworks/MCP-SERVER.md`.
@@ -397,7 +394,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 8. **ProviderIcon component:** Unified icon system using `@lobehub/icons` (130+ SVG) with PNG fallback and generic icon fallback chain. Used on providers, dashboard, and agents pages.
 
-9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 99 `src/lib/db/` modules with 117 SQL migrations.
+9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 117 `src/lib/db/` modules with 148 SQL migrations.
 
 10. **Upstream headers:** Custom headers merged in executors after default auth; same header name replaces executor value. Forbidden header names in `src/shared/constants/upstreamHeaders.ts`.
 
@@ -441,7 +438,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 4. **Environment variables:** All configuration is in `.env` (from `.env.example`). Key vars: `PORT`, `NEXT_PUBLIC_BASE_URL`, `API_KEY`, `ADMIN_PASSWORD`.
 
-5. **Database layer:** Operations go through `src/lib/db/` modules (117 domain-specific files, 145 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
+5. **Database layer:** Operations go through `src/lib/db/` modules (117 domain-specific files, 148 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
 
 6. **Tests** use Node.js built-in test runner + Vitest. Run `npm test`. Vitest for MCP/autoCombo (`npm run test:vitest`). Playwright for E2E (`npm run test:e2e`). Coverage gate: ratchet vs `quality-baseline.json`, absolute floor 60% statements/lines/functions/branches.
 
@@ -485,7 +482,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 - **339-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
-- **MCP server expanded to 105 tools / 31 scopes** (base + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
+- **MCP server expanded to 109 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
 - **Cloud Agents** (Codex Cloud, Devin, Jules), **Guardrails**, **Evals**, **Webhooks**, **Compliance** frameworks
 - **Embedded services** manager (install/start/stop bundled services from the dashboard)
 - **Prompt compression** (RTK + Caveman codecs) saving up to ~95% tokens on eligible traffic

docs/i18n/ta/llm.txt

@@ -4,10 +4,7 @@
 
 ---
 
-
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 339 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (109 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
-
-
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 339 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (105 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -21,7 +18,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 - **Runtime:** Node.js `>=22.0.0 <23 || >=24.0.0 <27`, ES Modules (`"type": "module"`)
 - **Framework:** Next.js 16 (App Router) with TypeScript 6
-- **Database:** SQLite via better-sqlite3 (local, zero-config, 145 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 148 migrations)
 - **State management:** Zustand (client), SQLite (server persistence)
 - **UI:** React 19, Tailwind CSS 4, Recharts for analytics, @lobehub/icons for 130+ provider SVG icons
 - **Auth:** OAuth 2.0 (PKCE) for providers, bcrypt for local user auth
@@ -109,7 +106,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   └── streaming.ts      # SSE streaming for A2A
 │   │   ├── acp/                  # Agent Communication Protocol registry and manager
 │   │   ├── compliance/           # Compliance policy engine
-│   │   ├── db/                   # SQLite database layer (99 modules + migrations)
+│   │   ├── db/                   # SQLite database layer (117 modules + migrations)
 │   │   │   ├── core.ts           # Database initialization, connection, schema
 │   │   │   ├── providers.ts      # Provider connection CRUD
 │   │   │   ├── models.ts         # Model catalog management
@@ -131,7 +128,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   ├── secrets.ts        # Secrets management
 │   │   │   ├── stateReset.ts     # State reset utilities
 │   │   │   ├── migrationRunner.ts # Schema migration runner
-│   │   │   └── migrations/       # 117 versioned SQL migration files
+│   │   │   └── migrations/       # 148 versioned SQL migration files
 │   │   ├── evals/                # Eval runner and scheduler
 │   │   ├── memory/               # Persistent conversational memory
 │   │   │   ├── extraction.ts     # Memory extraction from conversations
@@ -214,11 +211,11 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── moderations.ts        # Content moderation
 │   │   ├── rerank.ts             # Reranking API
 │   │   └── search.ts             # Web search API
-│   ├── mcp-server/               # Built-in MCP server (105 tools, 3 transports: stdio/SSE/streamable-HTTP)
+│   ├── mcp-server/               # Built-in MCP server (109 tools, 3 transports: stdio/SSE/streamable-HTTP)
 │   │   ├── server.ts             # MCP server core (tool registration, scope enforcement)
 │   │   ├── tools/                # Tool implementations (advancedTools, memoryTools, skillTools)
 │   │   ├── schemas/              # Zod input schemas (tools, audit, a2a)
-│   │   ├── scopeEnforcement.ts   # Scope-based access control (31 scopes)
+│   │   ├── scopeEnforcement.ts   # Scope-based access control (33 scopes)
 │   │   ├── audit.ts              # Tool call audit logging
 │   │   ├── runtimeHeartbeat.ts   # MCP runtime heartbeat
 │   │   └── httpTransport.ts      # HTTP transport handler
@@ -269,7 +266,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── i18n/                     # 43-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
-│   ├── frameworks/               # MCP-SERVER.md (105 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
+│   ├── frameworks/               # MCP-SERVER.md (109 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
 │   ├── routing/                  # AUTO-COMBO.md (14-factor scoring), REASONING_REPLAY.md
 │   ├── security/                 # GUARDRAILS.md, COMPLIANCE.md, STEALTH_GUIDE.md, PUBLIC_CREDS.md, ERROR_SANITIZATION.md
 │   ├── guides/                   # USER_GUIDE.md, TROUBLESHOOTING.md, ELECTRON_GUIDE.md, I18N.md
@@ -352,9 +349,9 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 - **A2A** — Agent-to-Agent v0.3 protocol (JSON-RPC 2.0, 6 skills: smart-routing, quota-management, provider-discovery, cost-analysis, health-report, list-capabilities)
 - **ACP** — Agent Communication Protocol registry and manager
 
-### MCP Server (105 Tools)
+### MCP Server (109 Tools)
 
-105 tools across modules: **43 base** (health, combos, quotas, routing, cost, models, cache,
+109 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
 diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool**, **notion**,
 **obsidian**, **localCorpus**, **gamification**, and **plugin** modules. Full per-tool inventory:
 `docs/frameworks/MCP-SERVER.md`.
@@ -397,7 +394,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 8. **ProviderIcon component:** Unified icon system using `@lobehub/icons` (130+ SVG) with PNG fallback and generic icon fallback chain. Used on providers, dashboard, and agents pages.
 
-9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 99 `src/lib/db/` modules with 117 SQL migrations.
+9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 117 `src/lib/db/` modules with 148 SQL migrations.
 
 10. **Upstream headers:** Custom headers merged in executors after default auth; same header name replaces executor value. Forbidden header names in `src/shared/constants/upstreamHeaders.ts`.
 
@@ -441,7 +438,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 4. **Environment variables:** All configuration is in `.env` (from `.env.example`). Key vars: `PORT`, `NEXT_PUBLIC_BASE_URL`, `API_KEY`, `ADMIN_PASSWORD`.
 
-5. **Database layer:** Operations go through `src/lib/db/` modules (117 domain-specific files, 145 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
+5. **Database layer:** Operations go through `src/lib/db/` modules (117 domain-specific files, 148 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
 
 6. **Tests** use Node.js built-in test runner + Vitest. Run `npm test`. Vitest for MCP/autoCombo (`npm run test:vitest`). Playwright for E2E (`npm run test:e2e`). Coverage gate: ratchet vs `quality-baseline.json`, absolute floor 60% statements/lines/functions/branches.
 
@@ -485,7 +482,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 - **339-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
-- **MCP server expanded to 105 tools / 31 scopes** (base + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
+- **MCP server expanded to 109 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
 - **Cloud Agents** (Codex Cloud, Devin, Jules), **Guardrails**, **Evals**, **Webhooks**, **Compliance** frameworks
 - **Embedded services** manager (install/start/stop bundled services from the dashboard)
 - **Prompt compression** (RTK + Caveman codecs) saving up to ~95% tokens on eligible traffic

docs/i18n/te/llm.txt

@@ -4,10 +4,7 @@
 
 ---
 
-
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 339 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (109 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
-
-
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 339 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (105 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -21,7 +18,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 - **Runtime:** Node.js `>=22.0.0 <23 || >=24.0.0 <27`, ES Modules (`"type": "module"`)
 - **Framework:** Next.js 16 (App Router) with TypeScript 6
-- **Database:** SQLite via better-sqlite3 (local, zero-config, 145 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 148 migrations)
 - **State management:** Zustand (client), SQLite (server persistence)
 - **UI:** React 19, Tailwind CSS 4, Recharts for analytics, @lobehub/icons for 130+ provider SVG icons
 - **Auth:** OAuth 2.0 (PKCE) for providers, bcrypt for local user auth
@@ -109,7 +106,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   └── streaming.ts      # SSE streaming for A2A
 │   │   ├── acp/                  # Agent Communication Protocol registry and manager
 │   │   ├── compliance/           # Compliance policy engine
-│   │   ├── db/                   # SQLite database layer (99 modules + migrations)
+│   │   ├── db/                   # SQLite database layer (117 modules + migrations)
 │   │   │   ├── core.ts           # Database initialization, connection, schema
 │   │   │   ├── providers.ts      # Provider connection CRUD
 │   │   │   ├── models.ts         # Model catalog management
@@ -131,7 +128,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   ├── secrets.ts        # Secrets management
 │   │   │   ├── stateReset.ts     # State reset utilities
 │   │   │   ├── migrationRunner.ts # Schema migration runner
-│   │   │   └── migrations/       # 117 versioned SQL migration files
+│   │   │   └── migrations/       # 148 versioned SQL migration files
 │   │   ├── evals/                # Eval runner and scheduler
 │   │   ├── memory/               # Persistent conversational memory
 │   │   │   ├── extraction.ts     # Memory extraction from conversations
@@ -214,11 +211,11 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── moderations.ts        # Content moderation
 │   │   ├── rerank.ts             # Reranking API
 │   │   └── search.ts             # Web search API
-│   ├── mcp-server/               # Built-in MCP server (105 tools, 3 transports: stdio/SSE/streamable-HTTP)
+│   ├── mcp-server/               # Built-in MCP server (109 tools, 3 transports: stdio/SSE/streamable-HTTP)
 │   │   ├── server.ts             # MCP server core (tool registration, scope enforcement)
 │   │   ├── tools/                # Tool implementations (advancedTools, memoryTools, skillTools)
 │   │   ├── schemas/              # Zod input schemas (tools, audit, a2a)
-│   │   ├── scopeEnforcement.ts   # Scope-based access control (31 scopes)
+│   │   ├── scopeEnforcement.ts   # Scope-based access control (33 scopes)
 │   │   ├── audit.ts              # Tool call audit logging
 │   │   ├── runtimeHeartbeat.ts   # MCP runtime heartbeat
 │   │   └── httpTransport.ts      # HTTP transport handler
@@ -269,7 +266,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── i18n/                     # 43-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
-│   ├── frameworks/               # MCP-SERVER.md (105 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
+│   ├── frameworks/               # MCP-SERVER.md (109 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
 │   ├── routing/                  # AUTO-COMBO.md (14-factor scoring), REASONING_REPLAY.md
 │   ├── security/                 # GUARDRAILS.md, COMPLIANCE.md, STEALTH_GUIDE.md, PUBLIC_CREDS.md, ERROR_SANITIZATION.md
 │   ├── guides/                   # USER_GUIDE.md, TROUBLESHOOTING.md, ELECTRON_GUIDE.md, I18N.md
@@ -352,9 +349,9 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 - **A2A** — Agent-to-Agent v0.3 protocol (JSON-RPC 2.0, 6 skills: smart-routing, quota-management, provider-discovery, cost-analysis, health-report, list-capabilities)
 - **ACP** — Agent Communication Protocol registry and manager
 
-### MCP Server (105 Tools)
+### MCP Server (109 Tools)
 
-105 tools across modules: **43 base** (health, combos, quotas, routing, cost, models, cache,
+109 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
 diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool**, **notion**,
 **obsidian**, **localCorpus**, **gamification**, and **plugin** modules. Full per-tool inventory:
 `docs/frameworks/MCP-SERVER.md`.
@@ -397,7 +394,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 8. **ProviderIcon component:** Unified icon system using `@lobehub/icons` (130+ SVG) with PNG fallback and generic icon fallback chain. Used on providers, dashboard, and agents pages.
 
-9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 99 `src/lib/db/` modules with 117 SQL migrations.
+9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 117 `src/lib/db/` modules with 148 SQL migrations.
 
 10. **Upstream headers:** Custom headers merged in executors after default auth; same header name replaces executor value. Forbidden header names in `src/shared/constants/upstreamHeaders.ts`.
 
@@ -441,7 +438,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 4. **Environment variables:** All configuration is in `.env` (from `.env.example`). Key vars: `PORT`, `NEXT_PUBLIC_BASE_URL`, `API_KEY`, `ADMIN_PASSWORD`.
 
-5. **Database layer:** Operations go through `src/lib/db/` modules (117 domain-specific files, 145 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
+5. **Database layer:** Operations go through `src/lib/db/` modules (117 domain-specific files, 148 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
 
 6. **Tests** use Node.js built-in test runner + Vitest. Run `npm test`. Vitest for MCP/autoCombo (`npm run test:vitest`). Playwright for E2E (`npm run test:e2e`). Coverage gate: ratchet vs `quality-baseline.json`, absolute floor 60% statements/lines/functions/branches.
 
@@ -485,7 +482,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 - **339-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
-- **MCP server expanded to 105 tools / 31 scopes** (base + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
+- **MCP server expanded to 109 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
 - **Cloud Agents** (Codex Cloud, Devin, Jules), **Guardrails**, **Evals**, **Webhooks**, **Compliance** frameworks
 - **Embedded services** manager (install/start/stop bundled services from the dashboard)
 - **Prompt compression** (RTK + Caveman codecs) saving up to ~95% tokens on eligible traffic

docs/i18n/th/llm.txt

@@ -4,10 +4,7 @@
 
 ---
 
-
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 339 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (109 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
-
-
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 339 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (105 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -21,7 +18,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 - **Runtime:** Node.js `>=22.0.0 <23 || >=24.0.0 <27`, ES Modules (`"type": "module"`)
 - **Framework:** Next.js 16 (App Router) with TypeScript 6
-- **Database:** SQLite via better-sqlite3 (local, zero-config, 145 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 148 migrations)
 - **State management:** Zustand (client), SQLite (server persistence)
 - **UI:** React 19, Tailwind CSS 4, Recharts for analytics, @lobehub/icons for 130+ provider SVG icons
 - **Auth:** OAuth 2.0 (PKCE) for providers, bcrypt for local user auth
@@ -109,7 +106,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   └── streaming.ts      # SSE streaming for A2A
 │   │   ├── acp/                  # Agent Communication Protocol registry and manager
 │   │   ├── compliance/           # Compliance policy engine
-│   │   ├── db/                   # SQLite database layer (99 modules + migrations)
+│   │   ├── db/                   # SQLite database layer (117 modules + migrations)
 │   │   │   ├── core.ts           # Database initialization, connection, schema
 │   │   │   ├── providers.ts      # Provider connection CRUD
 │   │   │   ├── models.ts         # Model catalog management
@@ -131,7 +128,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   ├── secrets.ts        # Secrets management
 │   │   │   ├── stateReset.ts     # State reset utilities
 │   │   │   ├── migrationRunner.ts # Schema migration runner
-│   │   │   └── migrations/       # 117 versioned SQL migration files
+│   │   │   └── migrations/       # 148 versioned SQL migration files
 │   │   ├── evals/                # Eval runner and scheduler
 │   │   ├── memory/               # Persistent conversational memory
 │   │   │   ├── extraction.ts     # Memory extraction from conversations
@@ -214,11 +211,11 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── moderations.ts        # Content moderation
 │   │   ├── rerank.ts             # Reranking API
 │   │   └── search.ts             # Web search API
-│   ├── mcp-server/               # Built-in MCP server (105 tools, 3 transports: stdio/SSE/streamable-HTTP)
+│   ├── mcp-server/               # Built-in MCP server (109 tools, 3 transports: stdio/SSE/streamable-HTTP)
 │   │   ├── server.ts             # MCP server core (tool registration, scope enforcement)
 │   │   ├── tools/                # Tool implementations (advancedTools, memoryTools, skillTools)
 │   │   ├── schemas/              # Zod input schemas (tools, audit, a2a)
-│   │   ├── scopeEnforcement.ts   # Scope-based access control (31 scopes)
+│   │   ├── scopeEnforcement.ts   # Scope-based access control (33 scopes)
 │   │   ├── audit.ts              # Tool call audit logging
 │   │   ├── runtimeHeartbeat.ts   # MCP runtime heartbeat
 │   │   └── httpTransport.ts      # HTTP transport handler
@@ -269,7 +266,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── i18n/                     # 43-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
-│   ├── frameworks/               # MCP-SERVER.md (105 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
+│   ├── frameworks/               # MCP-SERVER.md (109 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
 │   ├── routing/                  # AUTO-COMBO.md (14-factor scoring), REASONING_REPLAY.md
 │   ├── security/                 # GUARDRAILS.md, COMPLIANCE.md, STEALTH_GUIDE.md, PUBLIC_CREDS.md, ERROR_SANITIZATION.md
 │   ├── guides/                   # USER_GUIDE.md, TROUBLESHOOTING.md, ELECTRON_GUIDE.md, I18N.md
@@ -352,9 +349,9 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 - **A2A** — Agent-to-Agent v0.3 protocol (JSON-RPC 2.0, 6 skills: smart-routing, quota-management, provider-discovery, cost-analysis, health-report, list-capabilities)
 - **ACP** — Agent Communication Protocol registry and manager
 
-### MCP Server (105 Tools)
+### MCP Server (109 Tools)
 
-105 tools across modules: **43 base** (health, combos, quotas, routing, cost, models, cache,
+109 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
 diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool**, **notion**,
 **obsidian**, **localCorpus**, **gamification**, and **plugin** modules. Full per-tool inventory:
 `docs/frameworks/MCP-SERVER.md`.
@@ -397,7 +394,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 8. **ProviderIcon component:** Unified icon system using `@lobehub/icons` (130+ SVG) with PNG fallback and generic icon fallback chain. Used on providers, dashboard, and agents pages.
 
-9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 99 `src/lib/db/` modules with 117 SQL migrations.
+9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 117 `src/lib/db/` modules with 148 SQL migrations.
 
 10. **Upstream headers:** Custom headers merged in executors after default auth; same header name replaces executor value. Forbidden header names in `src/shared/constants/upstreamHeaders.ts`.
 
@@ -441,7 +438,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 4. **Environment variables:** All configuration is in `.env` (from `.env.example`). Key vars: `PORT`, `NEXT_PUBLIC_BASE_URL`, `API_KEY`, `ADMIN_PASSWORD`.
 
-5. **Database layer:** Operations go through `src/lib/db/` modules (117 domain-specific files, 145 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
+5. **Database layer:** Operations go through `src/lib/db/` modules (117 domain-specific files, 148 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
 
 6. **Tests** use Node.js built-in test runner + Vitest. Run `npm test`. Vitest for MCP/autoCombo (`npm run test:vitest`). Playwright for E2E (`npm run test:e2e`). Coverage gate: ratchet vs `quality-baseline.json`, absolute floor 60% statements/lines/functions/branches.
 
@@ -485,7 +482,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 - **339-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
-- **MCP server expanded to 105 tools / 31 scopes** (base + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
+- **MCP server expanded to 109 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
 - **Cloud Agents** (Codex Cloud, Devin, Jules), **Guardrails**, **Evals**, **Webhooks**, **Compliance** frameworks
 - **Embedded services** manager (install/start/stop bundled services from the dashboard)
 - **Prompt compression** (RTK + Caveman codecs) saving up to ~95% tokens on eligible traffic

docs/i18n/tr/llm.txt

@@ -4,10 +4,7 @@
 
 ---
 
-
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 339 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (109 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
-
-
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 339 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (105 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -21,7 +18,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 - **Runtime:** Node.js `>=22.0.0 <23 || >=24.0.0 <27`, ES Modules (`"type": "module"`)
 - **Framework:** Next.js 16 (App Router) with TypeScript 6
-- **Database:** SQLite via better-sqlite3 (local, zero-config, 145 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 148 migrations)
 - **State management:** Zustand (client), SQLite (server persistence)
 - **UI:** React 19, Tailwind CSS 4, Recharts for analytics, @lobehub/icons for 130+ provider SVG icons
 - **Auth:** OAuth 2.0 (PKCE) for providers, bcrypt for local user auth
@@ -109,7 +106,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   └── streaming.ts      # SSE streaming for A2A
 │   │   ├── acp/                  # Agent Communication Protocol registry and manager
 │   │   ├── compliance/           # Compliance policy engine
-│   │   ├── db/                   # SQLite database layer (99 modules + migrations)
+│   │   ├── db/                   # SQLite database layer (117 modules + migrations)
 │   │   │   ├── core.ts           # Database initialization, connection, schema
 │   │   │   ├── providers.ts      # Provider connection CRUD
 │   │   │   ├── models.ts         # Model catalog management
@@ -131,7 +128,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   ├── secrets.ts        # Secrets management
 │   │   │   ├── stateReset.ts     # State reset utilities
 │   │   │   ├── migrationRunner.ts # Schema migration runner
-│   │   │   └── migrations/       # 117 versioned SQL migration files
+│   │   │   └── migrations/       # 148 versioned SQL migration files
 │   │   ├── evals/                # Eval runner and scheduler
 │   │   ├── memory/               # Persistent conversational memory
 │   │   │   ├── extraction.ts     # Memory extraction from conversations
@@ -214,11 +211,11 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── moderations.ts        # Content moderation
 │   │   ├── rerank.ts             # Reranking API
 │   │   └── search.ts             # Web search API
-│   ├── mcp-server/               # Built-in MCP server (105 tools, 3 transports: stdio/SSE/streamable-HTTP)
+│   ├── mcp-server/               # Built-in MCP server (109 tools, 3 transports: stdio/SSE/streamable-HTTP)
 │   │   ├── server.ts             # MCP server core (tool registration, scope enforcement)
 │   │   ├── tools/                # Tool implementations (advancedTools, memoryTools, skillTools)
 │   │   ├── schemas/              # Zod input schemas (tools, audit, a2a)
-│   │   ├── scopeEnforcement.ts   # Scope-based access control (31 scopes)
+│   │   ├── scopeEnforcement.ts   # Scope-based access control (33 scopes)
 │   │   ├── audit.ts              # Tool call audit logging
 │   │   ├── runtimeHeartbeat.ts   # MCP runtime heartbeat
 │   │   └── httpTransport.ts      # HTTP transport handler
@@ -269,7 +266,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── i18n/                     # 43-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
-│   ├── frameworks/               # MCP-SERVER.md (105 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
+│   ├── frameworks/               # MCP-SERVER.md (109 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
 │   ├── routing/                  # AUTO-COMBO.md (14-factor scoring), REASONING_REPLAY.md
 │   ├── security/                 # GUARDRAILS.md, COMPLIANCE.md, STEALTH_GUIDE.md, PUBLIC_CREDS.md, ERROR_SANITIZATION.md
 │   ├── guides/                   # USER_GUIDE.md, TROUBLESHOOTING.md, ELECTRON_GUIDE.md, I18N.md
@@ -352,9 +349,9 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 - **A2A** — Agent-to-Agent v0.3 protocol (JSON-RPC 2.0, 6 skills: smart-routing, quota-management, provider-discovery, cost-analysis, health-report, list-capabilities)
 - **ACP** — Agent Communication Protocol registry and manager
 
-### MCP Server (105 Tools)
+### MCP Server (109 Tools)
 
-105 tools across modules: **43 base** (health, combos, quotas, routing, cost, models, cache,
+109 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
 diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool**, **notion**,
 **obsidian**, **localCorpus**, **gamification**, and **plugin** modules. Full per-tool inventory:
 `docs/frameworks/MCP-SERVER.md`.
@@ -397,7 +394,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 8. **ProviderIcon component:** Unified icon system using `@lobehub/icons` (130+ SVG) with PNG fallback and generic icon fallback chain. Used on providers, dashboard, and agents pages.
 
-9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 99 `src/lib/db/` modules with 117 SQL migrations.
+9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 117 `src/lib/db/` modules with 148 SQL migrations.
 
 10. **Upstream headers:** Custom headers merged in executors after default auth; same header name replaces executor value. Forbidden header names in `src/shared/constants/upstreamHeaders.ts`.
 
@@ -441,7 +438,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 4. **Environment variables:** All configuration is in `.env` (from `.env.example`). Key vars: `PORT`, `NEXT_PUBLIC_BASE_URL`, `API_KEY`, `ADMIN_PASSWORD`.
 
-5. **Database layer:** Operations go through `src/lib/db/` modules (117 domain-specific files, 145 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
+5. **Database layer:** Operations go through `src/lib/db/` modules (117 domain-specific files, 148 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
 
 6. **Tests** use Node.js built-in test runner + Vitest. Run `npm test`. Vitest for MCP/autoCombo (`npm run test:vitest`). Playwright for E2E (`npm run test:e2e`). Coverage gate: ratchet vs `quality-baseline.json`, absolute floor 60% statements/lines/functions/branches.
 
@@ -485,7 +482,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 - **339-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
-- **MCP server expanded to 105 tools / 31 scopes** (base + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
+- **MCP server expanded to 109 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
 - **Cloud Agents** (Codex Cloud, Devin, Jules), **Guardrails**, **Evals**, **Webhooks**, **Compliance** frameworks
 - **Embedded services** manager (install/start/stop bundled services from the dashboard)
 - **Prompt compression** (RTK + Caveman codecs) saving up to ~95% tokens on eligible traffic

docs/i18n/uk-UA/llm.txt

@@ -4,10 +4,7 @@
 
 ---
 
-
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 339 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (109 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
-
-
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 339 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (105 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -21,7 +18,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 - **Runtime:** Node.js `>=22.0.0 <23 || >=24.0.0 <27`, ES Modules (`"type": "module"`)
 - **Framework:** Next.js 16 (App Router) with TypeScript 6
-- **Database:** SQLite via better-sqlite3 (local, zero-config, 145 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 148 migrations)
 - **State management:** Zustand (client), SQLite (server persistence)
 - **UI:** React 19, Tailwind CSS 4, Recharts for analytics, @lobehub/icons for 130+ provider SVG icons
 - **Auth:** OAuth 2.0 (PKCE) for providers, bcrypt for local user auth
@@ -109,7 +106,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   └── streaming.ts      # SSE streaming for A2A
 │   │   ├── acp/                  # Agent Communication Protocol registry and manager
 │   │   ├── compliance/           # Compliance policy engine
-│   │   ├── db/                   # SQLite database layer (99 modules + migrations)
+│   │   ├── db/                   # SQLite database layer (117 modules + migrations)
 │   │   │   ├── core.ts           # Database initialization, connection, schema
 │   │   │   ├── providers.ts      # Provider connection CRUD
 │   │   │   ├── models.ts         # Model catalog management
@@ -131,7 +128,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   ├── secrets.ts        # Secrets management
 │   │   │   ├── stateReset.ts     # State reset utilities
 │   │   │   ├── migrationRunner.ts # Schema migration runner
-│   │   │   └── migrations/       # 117 versioned SQL migration files
+│   │   │   └── migrations/       # 148 versioned SQL migration files
 │   │   ├── evals/                # Eval runner and scheduler
 │   │   ├── memory/               # Persistent conversational memory
 │   │   │   ├── extraction.ts     # Memory extraction from conversations
@@ -214,11 +211,11 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── moderations.ts        # Content moderation
 │   │   ├── rerank.ts             # Reranking API
 │   │   └── search.ts             # Web search API
-│   ├── mcp-server/               # Built-in MCP server (105 tools, 3 transports: stdio/SSE/streamable-HTTP)
+│   ├── mcp-server/               # Built-in MCP server (109 tools, 3 transports: stdio/SSE/streamable-HTTP)
 │   │   ├── server.ts             # MCP server core (tool registration, scope enforcement)
 │   │   ├── tools/                # Tool implementations (advancedTools, memoryTools, skillTools)
 │   │   ├── schemas/              # Zod input schemas (tools, audit, a2a)
-│   │   ├── scopeEnforcement.ts   # Scope-based access control (31 scopes)
+│   │   ├── scopeEnforcement.ts   # Scope-based access control (33 scopes)
 │   │   ├── audit.ts              # Tool call audit logging
 │   │   ├── runtimeHeartbeat.ts   # MCP runtime heartbeat
 │   │   └── httpTransport.ts      # HTTP transport handler
@@ -269,7 +266,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── i18n/                     # 43-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
-│   ├── frameworks/               # MCP-SERVER.md (105 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
+│   ├── frameworks/               # MCP-SERVER.md (109 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
 │   ├── routing/                  # AUTO-COMBO.md (14-factor scoring), REASONING_REPLAY.md
 │   ├── security/                 # GUARDRAILS.md, COMPLIANCE.md, STEALTH_GUIDE.md, PUBLIC_CREDS.md, ERROR_SANITIZATION.md
 │   ├── guides/                   # USER_GUIDE.md, TROUBLESHOOTING.md, ELECTRON_GUIDE.md, I18N.md
@@ -352,9 +349,9 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 - **A2A** — Agent-to-Agent v0.3 protocol (JSON-RPC 2.0, 6 skills: smart-routing, quota-management, provider-discovery, cost-analysis, health-report, list-capabilities)
 - **ACP** — Agent Communication Protocol registry and manager
 
-### MCP Server (105 Tools)
+### MCP Server (109 Tools)
 
-105 tools across modules: **43 base** (health, combos, quotas, routing, cost, models, cache,
+109 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
 diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool**, **notion**,
 **obsidian**, **localCorpus**, **gamification**, and **plugin** modules. Full per-tool inventory:
 `docs/frameworks/MCP-SERVER.md`.
@@ -397,7 +394,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 8. **ProviderIcon component:** Unified icon system using `@lobehub/icons` (130+ SVG) with PNG fallback and generic icon fallback chain. Used on providers, dashboard, and agents pages.
 
-9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 99 `src/lib/db/` modules with 117 SQL migrations.
+9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 117 `src/lib/db/` modules with 148 SQL migrations.
 
 10. **Upstream headers:** Custom headers merged in executors after default auth; same header name replaces executor value. Forbidden header names in `src/shared/constants/upstreamHeaders.ts`.
 
@@ -441,7 +438,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 4. **Environment variables:** All configuration is in `.env` (from `.env.example`). Key vars: `PORT`, `NEXT_PUBLIC_BASE_URL`, `API_KEY`, `ADMIN_PASSWORD`.
 
-5. **Database layer:** Operations go through `src/lib/db/` modules (117 domain-specific files, 145 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
+5. **Database layer:** Operations go through `src/lib/db/` modules (117 domain-specific files, 148 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
 
 6. **Tests** use Node.js built-in test runner + Vitest. Run `npm test`. Vitest for MCP/autoCombo (`npm run test:vitest`). Playwright for E2E (`npm run test:e2e`). Coverage gate: ratchet vs `quality-baseline.json`, absolute floor 60% statements/lines/functions/branches.
 
@@ -485,7 +482,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 - **339-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
-- **MCP server expanded to 105 tools / 31 scopes** (base + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
+- **MCP server expanded to 109 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
 - **Cloud Agents** (Codex Cloud, Devin, Jules), **Guardrails**, **Evals**, **Webhooks**, **Compliance** frameworks
 - **Embedded services** manager (install/start/stop bundled services from the dashboard)
 - **Prompt compression** (RTK + Caveman codecs) saving up to ~95% tokens on eligible traffic

docs/i18n/ur/llm.txt

@@ -4,10 +4,7 @@
 
 ---
 
-
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 339 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (109 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
-
-
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 339 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (105 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -21,7 +18,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 - **Runtime:** Node.js `>=22.0.0 <23 || >=24.0.0 <27`, ES Modules (`"type": "module"`)
 - **Framework:** Next.js 16 (App Router) with TypeScript 6
-- **Database:** SQLite via better-sqlite3 (local, zero-config, 145 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 148 migrations)
 - **State management:** Zustand (client), SQLite (server persistence)
 - **UI:** React 19, Tailwind CSS 4, Recharts for analytics, @lobehub/icons for 130+ provider SVG icons
 - **Auth:** OAuth 2.0 (PKCE) for providers, bcrypt for local user auth
@@ -109,7 +106,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   └── streaming.ts      # SSE streaming for A2A
 │   │   ├── acp/                  # Agent Communication Protocol registry and manager
 │   │   ├── compliance/           # Compliance policy engine
-│   │   ├── db/                   # SQLite database layer (99 modules + migrations)
+│   │   ├── db/                   # SQLite database layer (117 modules + migrations)
 │   │   │   ├── core.ts           # Database initialization, connection, schema
 │   │   │   ├── providers.ts      # Provider connection CRUD
 │   │   │   ├── models.ts         # Model catalog management
@@ -131,7 +128,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   ├── secrets.ts        # Secrets management
 │   │   │   ├── stateReset.ts     # State reset utilities
 │   │   │   ├── migrationRunner.ts # Schema migration runner
-│   │   │   └── migrations/       # 117 versioned SQL migration files
+│   │   │   └── migrations/       # 148 versioned SQL migration files
 │   │   ├── evals/                # Eval runner and scheduler
 │   │   ├── memory/               # Persistent conversational memory
 │   │   │   ├── extraction.ts     # Memory extraction from conversations
@@ -214,11 +211,11 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── moderations.ts        # Content moderation
 │   │   ├── rerank.ts             # Reranking API
 │   │   └── search.ts             # Web search API
-│   ├── mcp-server/               # Built-in MCP server (105 tools, 3 transports: stdio/SSE/streamable-HTTP)
+│   ├── mcp-server/               # Built-in MCP server (109 tools, 3 transports: stdio/SSE/streamable-HTTP)
 │   │   ├── server.ts             # MCP server core (tool registration, scope enforcement)
 │   │   ├── tools/                # Tool implementations (advancedTools, memoryTools, skillTools)
 │   │   ├── schemas/              # Zod input schemas (tools, audit, a2a)
-│   │   ├── scopeEnforcement.ts   # Scope-based access control (31 scopes)
+│   │   ├── scopeEnforcement.ts   # Scope-based access control (33 scopes)
 │   │   ├── audit.ts              # Tool call audit logging
 │   │   ├── runtimeHeartbeat.ts   # MCP runtime heartbeat
 │   │   └── httpTransport.ts      # HTTP transport handler
@@ -269,7 +266,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── i18n/                     # 43-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
-│   ├── frameworks/               # MCP-SERVER.md (105 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
+│   ├── frameworks/               # MCP-SERVER.md (109 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
 │   ├── routing/                  # AUTO-COMBO.md (14-factor scoring), REASONING_REPLAY.md
 │   ├── security/                 # GUARDRAILS.md, COMPLIANCE.md, STEALTH_GUIDE.md, PUBLIC_CREDS.md, ERROR_SANITIZATION.md
 │   ├── guides/                   # USER_GUIDE.md, TROUBLESHOOTING.md, ELECTRON_GUIDE.md, I18N.md
@@ -352,9 +349,9 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 - **A2A** — Agent-to-Agent v0.3 protocol (JSON-RPC 2.0, 6 skills: smart-routing, quota-management, provider-discovery, cost-analysis, health-report, list-capabilities)
 - **ACP** — Agent Communication Protocol registry and manager
 
-### MCP Server (105 Tools)
+### MCP Server (109 Tools)
 
-105 tools across modules: **43 base** (health, combos, quotas, routing, cost, models, cache,
+109 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
 diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool**, **notion**,
 **obsidian**, **localCorpus**, **gamification**, and **plugin** modules. Full per-tool inventory:
 `docs/frameworks/MCP-SERVER.md`.
@@ -397,7 +394,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 8. **ProviderIcon component:** Unified icon system using `@lobehub/icons` (130+ SVG) with PNG fallback and generic icon fallback chain. Used on providers, dashboard, and agents pages.
 
-9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 99 `src/lib/db/` modules with 117 SQL migrations.
+9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 117 `src/lib/db/` modules with 148 SQL migrations.
 
 10. **Upstream headers:** Custom headers merged in executors after default auth; same header name replaces executor value. Forbidden header names in `src/shared/constants/upstreamHeaders.ts`.
 
@@ -441,7 +438,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 4. **Environment variables:** All configuration is in `.env` (from `.env.example`). Key vars: `PORT`, `NEXT_PUBLIC_BASE_URL`, `API_KEY`, `ADMIN_PASSWORD`.
 
-5. **Database layer:** Operations go through `src/lib/db/` modules (117 domain-specific files, 145 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
+5. **Database layer:** Operations go through `src/lib/db/` modules (117 domain-specific files, 148 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
 
 6. **Tests** use Node.js built-in test runner + Vitest. Run `npm test`. Vitest for MCP/autoCombo (`npm run test:vitest`). Playwright for E2E (`npm run test:e2e`). Coverage gate: ratchet vs `quality-baseline.json`, absolute floor 60% statements/lines/functions/branches.
 
@@ -485,7 +482,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 - **339-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
-- **MCP server expanded to 105 tools / 31 scopes** (base + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
+- **MCP server expanded to 109 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
 - **Cloud Agents** (Codex Cloud, Devin, Jules), **Guardrails**, **Evals**, **Webhooks**, **Compliance** frameworks
 - **Embedded services** manager (install/start/stop bundled services from the dashboard)
 - **Prompt compression** (RTK + Caveman codecs) saving up to ~95% tokens on eligible traffic

docs/i18n/vi/llm.txt

@@ -4,10 +4,7 @@
 
 ---
 
-
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 339 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (109 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
-
-
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 339 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (105 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -21,7 +18,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 - **Runtime:** Node.js `>=22.0.0 <23 || >=24.0.0 <27`, ES Modules (`"type": "module"`)
 - **Framework:** Next.js 16 (App Router) with TypeScript 6
-- **Database:** SQLite via better-sqlite3 (local, zero-config, 145 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 148 migrations)
 - **State management:** Zustand (client), SQLite (server persistence)
 - **UI:** React 19, Tailwind CSS 4, Recharts for analytics, @lobehub/icons for 130+ provider SVG icons
 - **Auth:** OAuth 2.0 (PKCE) for providers, bcrypt for local user auth
@@ -109,7 +106,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   └── streaming.ts      # SSE streaming for A2A
 │   │   ├── acp/                  # Agent Communication Protocol registry and manager
 │   │   ├── compliance/           # Compliance policy engine
-│   │   ├── db/                   # SQLite database layer (99 modules + migrations)
+│   │   ├── db/                   # SQLite database layer (117 modules + migrations)
 │   │   │   ├── core.ts           # Database initialization, connection, schema
 │   │   │   ├── providers.ts      # Provider connection CRUD
 │   │   │   ├── models.ts         # Model catalog management
@@ -131,7 +128,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   ├── secrets.ts        # Secrets management
 │   │   │   ├── stateReset.ts     # State reset utilities
 │   │   │   ├── migrationRunner.ts # Schema migration runner
-│   │   │   └── migrations/       # 117 versioned SQL migration files
+│   │   │   └── migrations/       # 148 versioned SQL migration files
 │   │   ├── evals/                # Eval runner and scheduler
 │   │   ├── memory/               # Persistent conversational memory
 │   │   │   ├── extraction.ts     # Memory extraction from conversations
@@ -214,11 +211,11 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── moderations.ts        # Content moderation
 │   │   ├── rerank.ts             # Reranking API
 │   │   └── search.ts             # Web search API
-│   ├── mcp-server/               # Built-in MCP server (105 tools, 3 transports: stdio/SSE/streamable-HTTP)
+│   ├── mcp-server/               # Built-in MCP server (109 tools, 3 transports: stdio/SSE/streamable-HTTP)
 │   │   ├── server.ts             # MCP server core (tool registration, scope enforcement)
 │   │   ├── tools/                # Tool implementations (advancedTools, memoryTools, skillTools)
 │   │   ├── schemas/              # Zod input schemas (tools, audit, a2a)
-│   │   ├── scopeEnforcement.ts   # Scope-based access control (31 scopes)
+│   │   ├── scopeEnforcement.ts   # Scope-based access control (33 scopes)
 │   │   ├── audit.ts              # Tool call audit logging
 │   │   ├── runtimeHeartbeat.ts   # MCP runtime heartbeat
 │   │   └── httpTransport.ts      # HTTP transport handler
@@ -269,7 +266,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── i18n/                     # 43-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
-│   ├── frameworks/               # MCP-SERVER.md (105 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
+│   ├── frameworks/               # MCP-SERVER.md (109 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
 │   ├── routing/                  # AUTO-COMBO.md (14-factor scoring), REASONING_REPLAY.md
 │   ├── security/                 # GUARDRAILS.md, COMPLIANCE.md, STEALTH_GUIDE.md, PUBLIC_CREDS.md, ERROR_SANITIZATION.md
 │   ├── guides/                   # USER_GUIDE.md, TROUBLESHOOTING.md, ELECTRON_GUIDE.md, I18N.md
@@ -352,9 +349,9 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 - **A2A** — Agent-to-Agent v0.3 protocol (JSON-RPC 2.0, 6 skills: smart-routing, quota-management, provider-discovery, cost-analysis, health-report, list-capabilities)
 - **ACP** — Agent Communication Protocol registry and manager
 
-### MCP Server (105 Tools)
+### MCP Server (109 Tools)
 
-105 tools across modules: **43 base** (health, combos, quotas, routing, cost, models, cache,
+109 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
 diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool**, **notion**,
 **obsidian**, **localCorpus**, **gamification**, and **plugin** modules. Full per-tool inventory:
 `docs/frameworks/MCP-SERVER.md`.
@@ -397,7 +394,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 8. **ProviderIcon component:** Unified icon system using `@lobehub/icons` (130+ SVG) with PNG fallback and generic icon fallback chain. Used on providers, dashboard, and agents pages.
 
-9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 99 `src/lib/db/` modules with 117 SQL migrations.
+9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 117 `src/lib/db/` modules with 148 SQL migrations.
 
 10. **Upstream headers:** Custom headers merged in executors after default auth; same header name replaces executor value. Forbidden header names in `src/shared/constants/upstreamHeaders.ts`.
 
@@ -441,7 +438,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 4. **Environment variables:** All configuration is in `.env` (from `.env.example`). Key vars: `PORT`, `NEXT_PUBLIC_BASE_URL`, `API_KEY`, `ADMIN_PASSWORD`.
 
-5. **Database layer:** Operations go through `src/lib/db/` modules (117 domain-specific files, 145 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
+5. **Database layer:** Operations go through `src/lib/db/` modules (117 domain-specific files, 148 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
 
 6. **Tests** use Node.js built-in test runner + Vitest. Run `npm test`. Vitest for MCP/autoCombo (`npm run test:vitest`). Playwright for E2E (`npm run test:e2e`). Coverage gate: ratchet vs `quality-baseline.json`, absolute floor 60% statements/lines/functions/branches.
 
@@ -485,7 +482,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 - **339-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
-- **MCP server expanded to 105 tools / 31 scopes** (base + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
+- **MCP server expanded to 109 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
 - **Cloud Agents** (Codex Cloud, Devin, Jules), **Guardrails**, **Evals**, **Webhooks**, **Compliance** frameworks
 - **Embedded services** manager (install/start/stop bundled services from the dashboard)
 - **Prompt compression** (RTK + Caveman codecs) saving up to ~95% tokens on eligible traffic

docs/i18n/zh-CN/llm.txt

@@ -4,10 +4,7 @@
 
 ---
 
-
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 339 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (109 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
-
-
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 339 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (105 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -21,7 +18,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 - **Runtime:** Node.js `>=22.0.0 <23 || >=24.0.0 <27`, ES Modules (`"type": "module"`)
 - **Framework:** Next.js 16 (App Router) with TypeScript 6
-- **Database:** SQLite via better-sqlite3 (local, zero-config, 145 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 148 migrations)
 - **State management:** Zustand (client), SQLite (server persistence)
 - **UI:** React 19, Tailwind CSS 4, Recharts for analytics, @lobehub/icons for 130+ provider SVG icons
 - **Auth:** OAuth 2.0 (PKCE) for providers, bcrypt for local user auth
@@ -109,7 +106,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   └── streaming.ts      # SSE streaming for A2A
 │   │   ├── acp/                  # Agent Communication Protocol registry and manager
 │   │   ├── compliance/           # Compliance policy engine
-│   │   ├── db/                   # SQLite database layer (99 modules + migrations)
+│   │   ├── db/                   # SQLite database layer (117 modules + migrations)
 │   │   │   ├── core.ts           # Database initialization, connection, schema
 │   │   │   ├── providers.ts      # Provider connection CRUD
 │   │   │   ├── models.ts         # Model catalog management
@@ -131,7 +128,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   ├── secrets.ts        # Secrets management
 │   │   │   ├── stateReset.ts     # State reset utilities
 │   │   │   ├── migrationRunner.ts # Schema migration runner
-│   │   │   └── migrations/       # 117 versioned SQL migration files
+│   │   │   └── migrations/       # 148 versioned SQL migration files
 │   │   ├── evals/                # Eval runner and scheduler
 │   │   ├── memory/               # Persistent conversational memory
 │   │   │   ├── extraction.ts     # Memory extraction from conversations
@@ -214,11 +211,11 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── moderations.ts        # Content moderation
 │   │   ├── rerank.ts             # Reranking API
 │   │   └── search.ts             # Web search API
-│   ├── mcp-server/               # Built-in MCP server (105 tools, 3 transports: stdio/SSE/streamable-HTTP)
+│   ├── mcp-server/               # Built-in MCP server (109 tools, 3 transports: stdio/SSE/streamable-HTTP)
 │   │   ├── server.ts             # MCP server core (tool registration, scope enforcement)
 │   │   ├── tools/                # Tool implementations (advancedTools, memoryTools, skillTools)
 │   │   ├── schemas/              # Zod input schemas (tools, audit, a2a)
-│   │   ├── scopeEnforcement.ts   # Scope-based access control (31 scopes)
+│   │   ├── scopeEnforcement.ts   # Scope-based access control (33 scopes)
 │   │   ├── audit.ts              # Tool call audit logging
 │   │   ├── runtimeHeartbeat.ts   # MCP runtime heartbeat
 │   │   └── httpTransport.ts      # HTTP transport handler
@@ -269,7 +266,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── i18n/                     # 43-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
-│   ├── frameworks/               # MCP-SERVER.md (105 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
+│   ├── frameworks/               # MCP-SERVER.md (109 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
 │   ├── routing/                  # AUTO-COMBO.md (14-factor scoring), REASONING_REPLAY.md
 │   ├── security/                 # GUARDRAILS.md, COMPLIANCE.md, STEALTH_GUIDE.md, PUBLIC_CREDS.md, ERROR_SANITIZATION.md
 │   ├── guides/                   # USER_GUIDE.md, TROUBLESHOOTING.md, ELECTRON_GUIDE.md, I18N.md
@@ -352,9 +349,9 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 - **A2A** — Agent-to-Agent v0.3 protocol (JSON-RPC 2.0, 6 skills: smart-routing, quota-management, provider-discovery, cost-analysis, health-report, list-capabilities)
 - **ACP** — Agent Communication Protocol registry and manager
 
-### MCP Server (105 Tools)
+### MCP Server (109 Tools)
 
-105 tools across modules: **43 base** (health, combos, quotas, routing, cost, models, cache,
+109 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
 diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool**, **notion**,
 **obsidian**, **localCorpus**, **gamification**, and **plugin** modules. Full per-tool inventory:
 `docs/frameworks/MCP-SERVER.md`.
@@ -397,7 +394,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 8. **ProviderIcon component:** Unified icon system using `@lobehub/icons` (130+ SVG) with PNG fallback and generic icon fallback chain. Used on providers, dashboard, and agents pages.
 
-9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 99 `src/lib/db/` modules with 117 SQL migrations.
+9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 117 `src/lib/db/` modules with 148 SQL migrations.
 
 10. **Upstream headers:** Custom headers merged in executors after default auth; same header name replaces executor value. Forbidden header names in `src/shared/constants/upstreamHeaders.ts`.
 
@@ -441,7 +438,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 4. **Environment variables:** All configuration is in `.env` (from `.env.example`). Key vars: `PORT`, `NEXT_PUBLIC_BASE_URL`, `API_KEY`, `ADMIN_PASSWORD`.
 
-5. **Database layer:** Operations go through `src/lib/db/` modules (117 domain-specific files, 145 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
+5. **Database layer:** Operations go through `src/lib/db/` modules (117 domain-specific files, 148 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
 
 6. **Tests** use Node.js built-in test runner + Vitest. Run `npm test`. Vitest for MCP/autoCombo (`npm run test:vitest`). Playwright for E2E (`npm run test:e2e`). Coverage gate: ratchet vs `quality-baseline.json`, absolute floor 60% statements/lines/functions/branches.
 
@@ -485,7 +482,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 - **339-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
-- **MCP server expanded to 105 tools / 31 scopes** (base + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
+- **MCP server expanded to 109 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
 - **Cloud Agents** (Codex Cloud, Devin, Jules), **Guardrails**, **Evals**, **Webhooks**, **Compliance** frameworks
 - **Embedded services** manager (install/start/stop bundled services from the dashboard)
 - **Prompt compression** (RTK + Caveman codecs) saving up to ~95% tokens on eligible traffic

docs/i18n/zh-TW/llm.txt

@@ -4,10 +4,7 @@
 
 ---
 
-
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 339 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (109 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
-
-
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 339 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (105 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -21,7 +18,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 - **Runtime:** Node.js `>=22.0.0 <23 || >=24.0.0 <27`, ES Modules (`"type": "module"`)
 - **Framework:** Next.js 16 (App Router) with TypeScript 6
-- **Database:** SQLite via better-sqlite3 (local, zero-config, 145 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 148 migrations)
 - **State management:** Zustand (client), SQLite (server persistence)
 - **UI:** React 19, Tailwind CSS 4, Recharts for analytics, @lobehub/icons for 130+ provider SVG icons
 - **Auth:** OAuth 2.0 (PKCE) for providers, bcrypt for local user auth
@@ -109,7 +106,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   └── streaming.ts      # SSE streaming for A2A
 │   │   ├── acp/                  # Agent Communication Protocol registry and manager
 │   │   ├── compliance/           # Compliance policy engine
-│   │   ├── db/                   # SQLite database layer (99 modules + migrations)
+│   │   ├── db/                   # SQLite database layer (117 modules + migrations)
 │   │   │   ├── core.ts           # Database initialization, connection, schema
 │   │   │   ├── providers.ts      # Provider connection CRUD
 │   │   │   ├── models.ts         # Model catalog management
@@ -131,7 +128,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   ├── secrets.ts        # Secrets management
 │   │   │   ├── stateReset.ts     # State reset utilities
 │   │   │   ├── migrationRunner.ts # Schema migration runner
-│   │   │   └── migrations/       # 117 versioned SQL migration files
+│   │   │   └── migrations/       # 148 versioned SQL migration files
 │   │   ├── evals/                # Eval runner and scheduler
 │   │   ├── memory/               # Persistent conversational memory
 │   │   │   ├── extraction.ts     # Memory extraction from conversations
@@ -214,11 +211,11 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── moderations.ts        # Content moderation
 │   │   ├── rerank.ts             # Reranking API
 │   │   └── search.ts             # Web search API
-│   ├── mcp-server/               # Built-in MCP server (105 tools, 3 transports: stdio/SSE/streamable-HTTP)
+│   ├── mcp-server/               # Built-in MCP server (109 tools, 3 transports: stdio/SSE/streamable-HTTP)
 │   │   ├── server.ts             # MCP server core (tool registration, scope enforcement)
 │   │   ├── tools/                # Tool implementations (advancedTools, memoryTools, skillTools)
 │   │   ├── schemas/              # Zod input schemas (tools, audit, a2a)
-│   │   ├── scopeEnforcement.ts   # Scope-based access control (31 scopes)
+│   │   ├── scopeEnforcement.ts   # Scope-based access control (33 scopes)
 │   │   ├── audit.ts              # Tool call audit logging
 │   │   ├── runtimeHeartbeat.ts   # MCP runtime heartbeat
 │   │   └── httpTransport.ts      # HTTP transport handler
@@ -269,7 +266,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── i18n/                     # 43-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
-│   ├── frameworks/               # MCP-SERVER.md (105 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
+│   ├── frameworks/               # MCP-SERVER.md (109 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
 │   ├── routing/                  # AUTO-COMBO.md (14-factor scoring), REASONING_REPLAY.md
 │   ├── security/                 # GUARDRAILS.md, COMPLIANCE.md, STEALTH_GUIDE.md, PUBLIC_CREDS.md, ERROR_SANITIZATION.md
 │   ├── guides/                   # USER_GUIDE.md, TROUBLESHOOTING.md, ELECTRON_GUIDE.md, I18N.md
@@ -352,9 +349,9 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 - **A2A** — Agent-to-Agent v0.3 protocol (JSON-RPC 2.0, 6 skills: smart-routing, quota-management, provider-discovery, cost-analysis, health-report, list-capabilities)
 - **ACP** — Agent Communication Protocol registry and manager
 
-### MCP Server (105 Tools)
+### MCP Server (109 Tools)
 
-105 tools across modules: **43 base** (health, combos, quotas, routing, cost, models, cache,
+109 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
 diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool**, **notion**,
 **obsidian**, **localCorpus**, **gamification**, and **plugin** modules. Full per-tool inventory:
 `docs/frameworks/MCP-SERVER.md`.
@@ -397,7 +394,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 8. **ProviderIcon component:** Unified icon system using `@lobehub/icons` (130+ SVG) with PNG fallback and generic icon fallback chain. Used on providers, dashboard, and agents pages.
 
-9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 99 `src/lib/db/` modules with 117 SQL migrations.
+9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 117 `src/lib/db/` modules with 148 SQL migrations.
 
 10. **Upstream headers:** Custom headers merged in executors after default auth; same header name replaces executor value. Forbidden header names in `src/shared/constants/upstreamHeaders.ts`.
 
@@ -441,7 +438,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 4. **Environment variables:** All configuration is in `.env` (from `.env.example`). Key vars: `PORT`, `NEXT_PUBLIC_BASE_URL`, `API_KEY`, `ADMIN_PASSWORD`.
 
-5. **Database layer:** Operations go through `src/lib/db/` modules (117 domain-specific files, 145 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
+5. **Database layer:** Operations go through `src/lib/db/` modules (117 domain-specific files, 148 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
 
 6. **Tests** use Node.js built-in test runner + Vitest. Run `npm test`. Vitest for MCP/autoCombo (`npm run test:vitest`). Playwright for E2E (`npm run test:e2e`). Coverage gate: ratchet vs `quality-baseline.json`, absolute floor 60% statements/lines/functions/branches.
 
@@ -485,7 +482,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 - **339-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
-- **MCP server expanded to 105 tools / 31 scopes** (base + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
+- **MCP server expanded to 109 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
 - **Cloud Agents** (Codex Cloud, Devin, Jules), **Guardrails**, **Evals**, **Webhooks**, **Compliance** frameworks
 - **Embedded services** manager (install/start/stop bundled services from the dashboard)
 - **Prompt compression** (RTK + Caveman codecs) saving up to ~95% tokens on eligible traffic

docs/ops/RELEASE_CHECKLIST.md

@@ -65,6 +65,7 @@ directly from anywhere — CI can only stage; only the owner's 2FA releases.
 as the default reflex (minutes, reversible); `npm unpublish` only inside the 72h/no-dependents
 window and never as the first move. Docker: never rewrite a version tag — rollback is
 repointing `latest` to the last good digest.
+
 ## Hotfix Fast-Lane (label `hotfix`)
 
 A PR labeled `hotfix` skips the heavy CI matrix (9-shard E2E, coverage ratchet,
@@ -276,6 +277,22 @@ Deploy skills use the light rsync flow — no `npm pack`, no `npm i -g`:
 - [ ] Open milestone for next version
 - [ ] If critical: pin discussion or post in `news.json` for in-app banner
 
+### Radar public-launch gate
+
+The Radar announcement is intentionally committed with `active: false`. Activation is a separate
+change after every item below is evidenced:
+
+- [ ] All stacked Radar PRs are merged and the release-tip CI is green
+- [ ] Deploy and smoke the OSS Radar routes with `RADAR_ENABLED` still off by default
+- [ ] Smoke `GET /planos`, `/termos`, `/privacidade`, and `/reembolso` on the named Radar host
+- [ ] Record operator identity/contact/address and owner-approved legal review in the private service
+- [ ] Exercise Stripe Checkout and the signed webhook in test mode only
+- [ ] Exercise one encrypted transactional-email delivery with the approved sender/domain
+- [ ] Prove backup restore and one supervised, budget-capped research run
+- [ ] Approve the BRL/PIX review policy before accepting donation evidence
+- [ ] Enable public Checkout only after the preceding gates, then activate the new `news.json` ID
+- [ ] Verify the Home banner uses localized copy and a new ID reappears after an older ID is dismissed
+
 ## Embedded Services smoke (v3.8.4+)
 
 Before shipping any release that includes embedded services changes, verify:

docs/providers/ALIBABA-QWEN-PROVIDER-FAMILIES.md

@@ -32,7 +32,7 @@ different endpoint families, so all four products remain separate provider IDs.
 | Provider family         | `global-sg`                                                              | `china-beijing`                                                      | Wire format |
 | ----------------------- | ------------------------------------------------------------------------ | -------------------------------------------------------------------- | ----------- |
 | `alibaba`               | `https://dashscope-intl.aliyuncs.com/compatible-mode/v1`                 | `https://dashscope.aliyuncs.com/compatible-mode/v1`                  | OpenAI      |
-| `bailian-coding-plan`   | `https://coding-intl.dashscope.aliyuncs.com/apps/anthropic/v1`           | `https://coding.dashscope.aliyuncs.com/apps/anthropic/v1`            | Anthropic   |
+| `bailian-coding-plan`   | `https://token-plan.ap-southeast-1.maas.aliyuncs.com/apps/anthropic/v1` | `https://token-plan.cn-beijing.maas.aliyuncs.com/apps/anthropic/v1`  | Anthropic   |
 | `qwen-cloud`            | `https://dashscope-intl.aliyuncs.com/compatible-mode/v1`                 | `https://dashscope.aliyuncs.com/compatible-mode/v1`                  | OpenAI      |
 | `qwen-cloud-token-plan` | `https://token-plan.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1` | `https://token-plan.cn-beijing.maas.aliyuncs.com/compatible-mode/v1` | OpenAI      |
 

docs/reference/ENVIRONMENT.md

@@ -1142,6 +1142,10 @@ Provider quota endpoints, network tunnels (Tailscale, Ngrok, MITM debug proxy),
 | `REDIS_URL`                                 | `redis://localhost:6379`                                                    | `src/shared/utils/rateLimiter.ts`                                         | Redis connection string for the rate limiter backend.                                                                                                                                                                                                                                                                                                                 |
 | `ALIBABA_CODING_PLAN_HOST`                  | _(production host)_                                                         | `open-sse/services/bailianQuotaFetcher.ts`                                | Override the host used to fetch Alibaba Bailian coding-plan quotas.                                                                                                                                                                                                                                                                                                   |
 | `ALIBABA_CODING_PLAN_QUOTA_URL`             | derived from host                                                           | `open-sse/services/bailianQuotaFetcher.ts`                                | Full quota URL override for Alibaba Bailian.                                                                                                                                                                                                                                                                                                                          |
+| `QWEN_CLOUD_COOKIE`                         | _(unset)_                                                                   | `open-sse/services/qwenTokenPlanQuotaFetcher.ts`                          | Console session cookie for the Qwen Cloud / Model Studio personal Token Plan quota gateway (the inference API key cannot read it). Copy the whole `Cookie` request header — it contains `login_qwencloud_ticket` — from any `api.json` call to `cs-data.qwencloud.com` on home.qwencloud.com › Billing › Subscription (F12 › Network). Sensitive and session-scoped; prefer the per-connection `qwenCloudCookie` Dashboard field. |
+| `QWEN_CLOUD_SEC_TOKEN`                      | _(unset)_                                                                   | `open-sse/services/qwenTokenPlanQuotaFetcher.ts`                          | Manual `sec_token` override for the Token Plan console gateway. Sensitive; when unset the fetcher resolves it from the dashboard HTML using the cookie.                                                                                                                                                                                                                |
+| `QWEN_TOKEN_PLAN_HOST`                      | `https://cs-data.qwencloud.com`                                             | `open-sse/services/qwenTokenPlanQuotaFetcher.ts`                          | Gateway host override for the personal Token Plan quota fetcher (e.g. `bailian-singapore-cs.alibabacloud.com` for the Model Studio console).                                                                                                                                                                                                                           |
+| `QWEN_TOKEN_PLAN_DASHBOARD_URL`             | `https://home.qwencloud.com/`                                               | `open-sse/services/qwenTokenPlanQuotaFetcher.ts`                          | Dashboard URL used to resolve `sec_token` from the logged-in HTML.                                                                                                                                                                                                                                                                                                    |
 | `ALIBABA_FREE_TIER_VISION_FE_PATH`          | `/costing-balance/free-quota-image-video`                                   | `open-sse/services/alibabaFreeTierQuotaFetcher.ts`                        | Console front-end path override for fetching Alibaba Model Studio free-tier vision/media quota.                                                                                                                                                                                                                                                                      |
 | `ALIBABA_FREE_TIER_MULTIMODAL_FE_PATH`      | `/costing-balance/free-quota-multimodal`                                    | `open-sse/services/alibabaFreeTierQuotaFetcher.ts`                        | Console front-end path override for fetching Alibaba Model Studio free-tier multimodal quota.                                                                                                                                                                                                                                                                        |
 | `ALIBABA_FREE_TIER_AUDIO_FE_PATH`           | `/costing-balance/free-quota-audio`                                         | `open-sse/services/alibabaFreeTierQuotaFetcher.ts`                        | Console front-end path override for fetching Alibaba Model Studio free-tier audio quota.                                                                                                                                                                                                                                                                             |
@@ -1348,17 +1352,24 @@ that should be able to run the docs translator.
 Optional add-on gated by the RADAR_ENABLED feature flag (default off — a feature
 flag toggled via Settings/DB, not an env var; see
 [docs/frameworks/RADAR.md](../frameworks/RADAR.md#flag-radar_enabled-default-off)).
-The four variables below are optional overrides used only to point the client at a
+The first four variables below are optional overrides for a self-hosted or forked feed and
-self-hosted or forked feed / supporter-key flow instead of the default OmniRoute
+supporter-key flows. The fifth, `RADAR_ADMIN_URL`, is a separate default-free link to the owner's
-Radar service. See [docs/frameworks/RADAR.md](../frameworks/RADAR.md) for the full
+private operations panel. See [docs/frameworks/RADAR.md](../frameworks/RADAR.md) for the full
-module doc.
+module doc and its
+[end-to-end activation and guided-setup sequence](../frameworks/RADAR.md#end-to-end-activation-and-guided-setup).
+
+The generic Home/Changelog announcement reader is not configured by an environment
+variable and does not depend on the RADAR_ENABLED feature flag. It reads the public repository
+`news.json` URL declared in `src/shared/utils/releaseNotes.ts` by
+GET only; dismissal IDs remain in browser local storage.
 
 | Variable                       | Default                                          | Source File                   | Description                                                                                     |
 | -------------------------------- | --------------------------------------------------- | ------------------------------ | ------------------------------------------------------------------------------------------------ |
-| `RADAR_FEED_URL`               | `https://radar.omniroute.online`                 | `src/lib/radar/sync.ts`       | Base URL of the Radar feed service. Override to point at a self-hosted or forked feed.          |
+| `RADAR_FEED_URL`               | `https://radar.omniroute.online`                 | `src/lib/radar/{sync,referralsSync,offersSync,intelSync}.ts` | Base URL shared by the separately signed catalog, referrals, supporter-offers, and Intel feeds. Override to point at a self-hosted or forked service. |
 | `RADAR_FEED_PUBKEY`            | _(pinned default key)_                           | `src/lib/radar/pinnedKeys.ts` | Ed25519 public key (base64-DER SPKI or PEM) used to verify feed signatures from a custom feed.   |
 | `RADAR_CONTRIBUTOR_CLAIM_URL`  | `https://radar.omniroute.online/auth/github`     | `src/lib/radar/links.ts`      | URL the "I'm a contributor" dashboard button opens (GitHub OAuth supporter-key claim flow).      |
 | `RADAR_SUPPORTER_PLANS_URL`    | `https://radar.omniroute.online/planos`          | `src/lib/radar/links.ts`      | URL the "Support the project" dashboard button opens (payment/plans page).                       |
+| `RADAR_ADMIN_URL`              | _(unset)_                                         | `src/lib/radar/links.ts`      | Owner-only private operations-panel link. HTTPS is required except for an HTTP loopback SSH forward; unset or invalid values create no navigation item. |
 
 ---
 

llm.txt

@@ -1,6 +1,6 @@
 # OmniRoute
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 339 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (105 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 339 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (109 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -14,7 +14,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 - **Runtime:** Node.js `>=22.0.0 <23 || >=24.0.0 <27`, ES Modules (`"type": "module"`)
 - **Framework:** Next.js 16 (App Router) with TypeScript 6
-- **Database:** SQLite via better-sqlite3 (local, zero-config, 145 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 148 migrations)
 - **State management:** Zustand (client), SQLite (server persistence)
 - **UI:** React 19, Tailwind CSS 4, Recharts for analytics, @lobehub/icons for 130+ provider SVG icons
 - **Auth:** OAuth 2.0 (PKCE) for providers, bcrypt for local user auth
@@ -102,7 +102,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   └── streaming.ts      # SSE streaming for A2A
 │   │   ├── acp/                  # Agent Communication Protocol registry and manager
 │   │   ├── compliance/           # Compliance policy engine
-│   │   ├── db/                   # SQLite database layer (99 modules + migrations)
+│   │   ├── db/                   # SQLite database layer (117 modules + migrations)
 │   │   │   ├── core.ts           # Database initialization, connection, schema
 │   │   │   ├── providers.ts      # Provider connection CRUD
 │   │   │   ├── models.ts         # Model catalog management
@@ -124,7 +124,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   ├── secrets.ts        # Secrets management
 │   │   │   ├── stateReset.ts     # State reset utilities
 │   │   │   ├── migrationRunner.ts # Schema migration runner
-│   │   │   └── migrations/       # 117 versioned SQL migration files
+│   │   │   └── migrations/       # 148 versioned SQL migration files
 │   │   ├── evals/                # Eval runner and scheduler
 │   │   ├── memory/               # Persistent conversational memory
 │   │   │   ├── extraction.ts     # Memory extraction from conversations
@@ -207,11 +207,11 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── moderations.ts        # Content moderation
 │   │   ├── rerank.ts             # Reranking API
 │   │   └── search.ts             # Web search API
-│   ├── mcp-server/               # Built-in MCP server (105 tools, 3 transports: stdio/SSE/streamable-HTTP)
+│   ├── mcp-server/               # Built-in MCP server (109 tools, 3 transports: stdio/SSE/streamable-HTTP)
 │   │   ├── server.ts             # MCP server core (tool registration, scope enforcement)
 │   │   ├── tools/                # Tool implementations (advancedTools, memoryTools, skillTools)
 │   │   ├── schemas/              # Zod input schemas (tools, audit, a2a)
-│   │   ├── scopeEnforcement.ts   # Scope-based access control (31 scopes)
+│   │   ├── scopeEnforcement.ts   # Scope-based access control (33 scopes)
 │   │   ├── audit.ts              # Tool call audit logging
 │   │   ├── runtimeHeartbeat.ts   # MCP runtime heartbeat
 │   │   └── httpTransport.ts      # HTTP transport handler
@@ -262,7 +262,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── i18n/                     # 43-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
-│   ├── frameworks/               # MCP-SERVER.md (105 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
+│   ├── frameworks/               # MCP-SERVER.md (109 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
 │   ├── routing/                  # AUTO-COMBO.md (14-factor scoring), REASONING_REPLAY.md
 │   ├── security/                 # GUARDRAILS.md, COMPLIANCE.md, STEALTH_GUIDE.md, PUBLIC_CREDS.md, ERROR_SANITIZATION.md
 │   ├── guides/                   # USER_GUIDE.md, TROUBLESHOOTING.md, ELECTRON_GUIDE.md, I18N.md
@@ -345,9 +345,9 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 - **A2A** — Agent-to-Agent v0.3 protocol (JSON-RPC 2.0, 6 skills: smart-routing, quota-management, provider-discovery, cost-analysis, health-report, list-capabilities)
 - **ACP** — Agent Communication Protocol registry and manager
 
-### MCP Server (105 Tools)
+### MCP Server (109 Tools)
 
-105 tools across modules: **43 base** (health, combos, quotas, routing, cost, models, cache,
+109 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
 diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool**, **notion**,
 **obsidian**, **localCorpus**, **gamification**, and **plugin** modules. Full per-tool inventory:
 `docs/frameworks/MCP-SERVER.md`.
@@ -390,7 +390,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 8. **ProviderIcon component:** Unified icon system using `@lobehub/icons` (130+ SVG) with PNG fallback and generic icon fallback chain. Used on providers, dashboard, and agents pages.
 
-9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 99 `src/lib/db/` modules with 117 SQL migrations.
+9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 117 `src/lib/db/` modules with 148 SQL migrations.
 
 10. **Upstream headers:** Custom headers merged in executors after default auth; same header name replaces executor value. Forbidden header names in `src/shared/constants/upstreamHeaders.ts`.
 
@@ -434,7 +434,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 4. **Environment variables:** All configuration is in `.env` (from `.env.example`). Key vars: `PORT`, `NEXT_PUBLIC_BASE_URL`, `API_KEY`, `ADMIN_PASSWORD`.
 
-5. **Database layer:** Operations go through `src/lib/db/` modules (117 domain-specific files, 145 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
+5. **Database layer:** Operations go through `src/lib/db/` modules (117 domain-specific files, 148 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
 
 6. **Tests** use Node.js built-in test runner + Vitest. Run `npm test`. Vitest for MCP/autoCombo (`npm run test:vitest`). Playwright for E2E (`npm run test:e2e`). Coverage gate: ratchet vs `quality-baseline.json`, absolute floor 60% statements/lines/functions/branches.
 
@@ -478,7 +478,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 - **339-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
-- **MCP server expanded to 105 tools / 31 scopes** (base + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
+- **MCP server expanded to 109 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
 - **Cloud Agents** (Codex Cloud, Devin, Jules), **Guardrails**, **Evals**, **Webhooks**, **Compliance** frameworks
 - **Embedded services** manager (install/start/stop bundled services from the dashboard)
 - **Prompt compression** (RTK + Caveman codecs) saving up to ~95% tokens on eligible traffic

news.json

@@ -1,8 +1,43 @@
 {
-  "active": false,
+  "schemaVersion": 2,
-  "title": "Novidade no Omniverse",
+  "items": [
-  "message": "Está lançado hoje o tOmni, o terminal interativo múltiplo para Agentes de AI! Experimente a nova interface focada em produtividade para desenvolvedores.",
+    {
-  "link": "https://github.com/diegosouzapw/tOmni",
+      "id": "radar-launch-2026-08",
-  "linkLabel": "Conhecer o tOmni",
+      "active": false,
-  "icon": "campaign"
+      "publishedAt": "2026-08-09T00:00:00.000Z",
+      "text": {
+        "en": {
+          "title": "OmniRoute Radar",
+          "message": "An opt-in, GET-only free-model catalog overlay with no telemetry from the OmniRoute client.",
+          "linkLabel": "Learn about Radar"
+        },
+        "pt-BR": {
+          "title": "OmniRoute Radar",
+          "message": "Um catálogo opcional de modelos gratuitos, somente GET e sem telemetria enviada pelo cliente OmniRoute.",
+          "linkLabel": "Conheça o Radar"
+        }
+      },
+      "link": "https://radar.omniroute.online/planos",
+      "icon": "radar"
+    },
+    {
+      "id": "tomni-launch-2026-07",
+      "active": false,
+      "publishedAt": "2026-07-01T00:00:00.000Z",
+      "text": {
+        "en": {
+          "title": "New in the Omniverse",
+          "message": "tOmni is an interactive multi-agent terminal focused on developer productivity.",
+          "linkLabel": "Meet tOmni"
+        },
+        "pt-BR": {
+          "title": "Novidade no Omniverse",
+          "message": "O tOmni é um terminal interativo para múltiplos agentes, focado na produtividade de desenvolvedores.",
+          "linkLabel": "Conhecer o tOmni"
+        }
+      },
+      "link": "https://github.com/diegosouzapw/tOmni",
+      "icon": "campaign"
+    }
+  ]
 }

open-sse/config/providerErrorRules.ts

@@ -30,13 +30,15 @@ export type ProviderErrorRule = {
 export type ProviderErrorRuleMatch = {
   reason: ConfiguredErrorReason;
   /**
-   * Intended lock scope. NOTE: this field is currently INFORMATIONAL — no
+   * Intended lock scope. #10334: this field is CONSUMED end-to-end only for
-   * consumer of `getProviderErrorRuleMatch` (checkFallbackError, combo.ts)
+   * providers in `HONORS_RULE_LOCK_SCOPE_PROVIDERS` (agentrouter-exclusive
-   * reads `scope` today; only `reason` and `cooldownMs` are consulted. The
+   * today, gated by `honorsRuleLockScope()`) — for those, `checkFallbackError`
-   * actual lock scope applied at runtime is decided independently by each
+   * surfaces it as `ruleScope` on its return value for the persistence layer
-   * call site (e.g. `hasPerModelQuota()` deciding model- vs connection-level
+   * to honor instead of re-deriving scope from `hasPerModelQuota()`. For
-   * lockout). Honoring this field end-to-end is tracked as a follow-up —
+   * every other provider it remains INFORMATIONAL: `getProviderErrorRuleMatch`
-   * see `docs/architecture/RESILIENCE_GUIDE.md` §7.
+   * callers still read only `reason`/`cooldownMs`, and the actual lock scope
+   * is decided independently by each call site. Widening the allowlist is
+   * tracked as a follow-up — see `docs/architecture/RESILIENCE_GUIDE.md` §7.
    */
   scope: "model" | "provider" | "connection";
   /** Optional explicit cooldown; falls back to the existing per-reason defaults. */
@@ -188,31 +190,29 @@ function buildOpenrouterRules(): ProviderErrorRule[] {
 // agentrouter.org misstates temporary quota exhaustion as 403/400 with a
 // Chinese body. upstreamStatusRestatement.ts rewrites the status to 429
 // BEFORE classification, so rules here accept both the raw 403/400 and the
-// restated 429 (text is the real discriminator either way). In production,
+// restated 429 (text is the real discriminator either way). Both the raw 403
-// the raw 403 path is what actually matters here: checkFallbackError's
+// path AND the restated 429 path reach these rules in production:
-// apikey-category FORBIDDEN branch (~line 1699) returns EARLY for a plain
+// checkFallbackError's `honorsRuleLockScope("agentrouter")` pre-check
-// 403, before these rules are ever consulted — these rules fire on the
+// (#10334) consults these rules BEFORE the generic apikey-category FORBIDDEN
-// RESTATED 429 (chatCore's upstreamStatusRestatement hook runs first) via
+// branch, and the restated 429 reaches them via the existing provider-rule
-// resolveRuleMatchBody, which is the only path in checkFallbackError that
+// lookup in the configured-rule branch. Both paths use resolveRuleMatchBody,
-// hands these rules the full error text instead of just {code, type}.
+// the only mechanism in checkFallbackError that hands agentrouter's rules the
+// full error text instead of just {code, type}.
 //  - "额度不足": account-wide temporary quota → quota_exhausted, scope
 //    "connection" (mirror of the Opencode account-wide rationale above).
-//    NOTE: `scope` on ProviderErrorRuleMatch is currently informational —
+//    `scope` on ProviderErrorRuleMatch is CONSUMED for agentrouter (#10334,
-//    checkFallbackError/combo.ts only consume `reason` and `cooldownMs`, not
+//    exclusive allowlist via `honorsRuleLockScope`): checkFallbackError
-//    `scope`. For agentrouter specifically (passthroughModels: true →
+//    surfaces it as `ruleScope` on its return value. Whether the persistence
-//    hasPerModelQuota() is true), this quota_exhausted match actually
+//    layer (markAccountUnavailable / combo target exhaustion) actually
-//    resolves to a PER-MODEL lockout (recordModelLockoutFailure), not a
+//    switches from `hasPerModelQuota()`-derived scope to honoring `ruleScope`
-//    connection-wide lock — other models on the same account keep being
+//    is Tasks 2/3 of #10334 — this task only surfaces the field.
-//    tried by combo routing (each burning one call) until they lock out
-//    individually. Honoring `scope` end-to-end is tracked as a follow-up.
 //  - "无权访问模型": declares auth_error/scope "model" (intent: lock only the
 //    model so the connection keeps serving the rest — Model Lockout tier).
-//    This rule does NOT fire on the production path today: it only matches
+//    This rule now fires on the production 403 path (#10334): the
-//    `status === 403`, but checkFallbackError's apikey FORBIDDEN branch
+//    `honorsRuleLockScope` pre-check matches it and returns its declared
-//    returns early for a plain 403 before this rule is ever consulted (see
+//    reason/cooldown/scope before the generic apikey-FORBIDDEN early-return
-//    the note above). A live `无权访问模型` 403 is handled like the base
+//    ever runs. A live `无权访问模型` 403 therefore no longer falls through to
-//    apikey-provider 403 today. Wiring this rule into that path is tracked
+//    the base apikey-provider 403 handling.
-//    as a follow-up.
 function buildAgentrouterRules(): ProviderErrorRule[] {
   const AGENTROUTER_ERROR_STATUSES = new Set([400, 403, 429]);
   return [
@@ -231,8 +231,15 @@ function buildAgentrouterRules(): ProviderErrorRule[] {
         if (status !== 403) return null;
         const text = JSON.stringify(body ?? "").toLowerCase();
         if (!text.includes("无权访问模型")) return null;
-        // 6h: effectively "until the operator fixes the key's model grants",
+        // Declares a 6h cooldown, but the effective cooldown is NOT 6h: the
-        // without being an unrecoverable terminal state.
+        // model-lockout persistence layer (recordModelLockoutFailure, called from
+        // markAccountUnavailable) clamps every base cooldown — this one included —
+        // to the configured model-lockout maxCooldownMs, which defaults to
+        // 1_800_000ms / 30min (src/lib/resilience/modelLockoutSettings.ts,
+        // DEFAULT_MODEL_LOCKOUT_SETTINGS.maxCooldownMs). So in practice this is
+        // "locked for ~30min by default (up to 6h if an operator raises the model-
+        // lockout cap in settings)", not "until the operator fixes the key's model
+        // grants" — it is a recoverable window, not a real fix-driven unlock.
         return { reason: "auth_error", scope: "model", cooldownMs: 6 * 60 * 60 * 1000 };
       },
     },
@@ -255,6 +262,21 @@ export const providerRuleRegistry = new Map<string, ProviderErrorRule[]>([
   ["agentrouter", buildAgentrouterRules()],
 ]);
 
+/**
+ * Providers whose ProviderErrorRuleMatch.scope is actually CONSUMED at the
+ * persistence layer (markAccountUnavailable / combo target exhaustion) to pick
+ * connection-vs-model lock scope. EXCLUSIVE allowlist by owner decision
+ * (2026-08-14, issue #10334) — deliberately SEPARATE from
+ * FULL_TEXT_RULE_PROVIDERS: that set controls what body a rule matches against
+ * (input), this one controls whether the matched scope changes caller behavior
+ * (output). A provider could need one without the other.
+ */
+const HONORS_RULE_LOCK_SCOPE_PROVIDERS = new Set(["agentrouter"]);
+
+export function honorsRuleLockScope(provider: string | null | undefined): boolean {
+  return !!provider && HONORS_RULE_LOCK_SCOPE_PROVIDERS.has(provider.toLowerCase());
+}
+
 /**
  * Providers whose rules match on the FULL upstream error text.
  * checkFallbackError's rule lookup normally passes only the structured

open-sse/config/providers/registry/bailian-coding-plan/index.ts

@@ -60,7 +60,12 @@ export const bailian_coding_planProvider: RegistryEntry = {
   alias: "bcp",
   format: "claude",
   executor: "default",
-  baseUrl: "https://coding-intl.dashscope.aliyuncs.com/apps/anthropic/v1",
+  // Token Plan endpoint (the catalog entry is "Alibaba Token Plan"). The former
+  // coding-intl.dashscope.aliyuncs.com host only accepts Coding Plan keys and rejects
+  // Token Plan keys with 401 invalid_api_key. Verified live 2026-08-14: this host
+  // returns 200 for every model below with the same key.
+  // Docs: https://www.alibabacloud.com/help/en/model-studio/more-tools
+  baseUrl: "https://token-plan.ap-southeast-1.maas.aliyuncs.com/apps/anthropic/v1",
   chatPath: "/messages",
   authType: "apikey",
   authHeader: "x-api-key",

open-sse/mcp-server/README.md

@@ -1,6 +1,6 @@
 # OmniRoute MCP Server
 
-> **Model Context Protocol server** that exposes OmniRoute's gateway intelligence as **107 tools** for AI agents.
+> **Model Context Protocol server** that exposes OmniRoute's gateway intelligence as **109 tools** for AI agents.
 >
 > **Source of truth for the full tool catalog and REST surface:** [`docs/frameworks/MCP-SERVER.md`](../../docs/frameworks/MCP-SERVER.md). This README focuses on architecture, configuration, and integration examples; the catalog below is a summary subset.
 
@@ -20,7 +20,7 @@ The MCP Server allows any AI agent (Claude Desktop, Cursor, VS Code Copilot, cus
 ┌──────────────────────────────────────────────────────────────────┐
 │                      OmniRoute MCP Server                        │
 │  ┌──────────────┐  ┌─────────────────┐  ┌────────────────────┐  │
-│  │ Scope        │  │ 107 MCP Tools   │  │   Audit Logger     │  │
+│  │ Scope        │  │ 109 MCP Tools   │  │   Audit Logger     │  │
 │  │ Enforcement  │──│ (core + memory  │──│   (SHA-256/SQLite) │  │
 │  │              │  │  + skills + …)  │  │                    │  │
 │  └──────────────┘  └────────┬────────┘  └────────────────────┘  │
@@ -120,18 +120,23 @@ omniroute --mcp
 
 ## Tool Reference
 
-### Phase 1: Essential Tools (8)
+### Phase 1: Essential Tools (13)
 
 | #   | Tool                            | Scopes                | Description                                                                |
 | --- | ------------------------------- | --------------------- | -------------------------------------------------------------------------- |
-| 1   | `omniroute_get_health`          | `read:health`         | Gateway health, uptime, memory, circuit breakers, rate limits, cache stats |
+| 1   | `omniroute_tool_search`         | `read:tools`          | Discover tools from the registered MCP catalog                             |
-| 2   | `omniroute_list_combos`         | `read:combos`         | List all combos (model chains) with strategies and optional metrics        |
+| 2   | `omniroute_get_health`          | `read:health`         | Gateway health, uptime, memory, circuit breakers, rate limits, cache stats |
-| 3   | `omniroute_get_combo_metrics`   | `read:combos`         | Performance metrics for a specific combo                                   |
+| 3   | `omniroute_list_combos`         | `read:combos`         | List all combos (model chains) with strategies and optional metrics        |
-| 4   | `omniroute_switch_combo`        | `write:combos`        | Activate or deactivate a combo for routing                                 |
+| 4   | `omniroute_get_combo_metrics`   | `read:combos`         | Performance metrics for a specific combo                                   |
-| 5   | `omniroute_check_quota`         | `read:quota`          | Remaining API quota per provider with token health status                  |
+| 5   | `omniroute_switch_combo`        | `write:combos`        | Activate or deactivate a combo for routing                                 |
-| 6   | `omniroute_route_request`       | `execute:completions` | Send a chat completion through intelligent routing                         |
+| 6   | `omniroute_create_combo`        | `write:combos`        | Create a validated combo through the existing combo API                    |
-| 7   | `omniroute_cost_report`         | `read:usage`          | Cost report by period (session/day/week/month) with per-provider breakdown |
+| 7   | `omniroute_check_quota`         | `read:quota`          | Remaining API quota per provider with token health status                  |
-| 8   | `omniroute_list_models_catalog` | `read:models`         | List all available models across providers with capabilities and pricing   |
+| 8   | `omniroute_route_request`       | `execute:completions` | Send a chat completion through intelligent routing                         |
+| 9   | `omniroute_cost_report`         | `read:usage`          | Cost report by period (session/day/week/month) with per-provider breakdown |
+| 10  | `omniroute_list_models_catalog` | `read:models`         | List all available models across providers with capabilities and pricing   |
+| 11  | `omniroute_radar_catalog`       | `read:radar`          | Read the local signed Radar catalog with provider/family filters           |
+| 12  | `omniroute_web_search`          | `execute:search`      | Search the web through configured search providers                         |
+| 13  | `omniroute_web_fetch`           | `execute:search`      | Fetch web content through configured fetch providers                       |
 
 ### Phase 2: Advanced Tools (8)
 

open-sse/mcp-server/__tests__/essentialTools.test.ts

@@ -1,7 +1,7 @@
 /**
  * Unit tests for MCP Essential Tools (Phase 1)
  *
- * Tests all 10 essential tool handlers via the tool handler functions.
+ * Tests the essential tool handlers via the tool handler functions.
  * The omniroute_web_search tests use InMemoryTransport + Client to exercise
  * the actual registered handler (not mockFetch directly).
  */
@@ -22,10 +22,10 @@ describe("MCP Essential Tools", () => {
   });
 
   describe("Tool schema validation", () => {
-    it("should have exactly 12 essential tools (includes web_search + web_fetch + tool_search)", () => {
+    it("should have exactly 13 essential tools (including Radar catalog)", () => {
-      // 11 -> 12: #8925 shipped omniroute_create_combo as a phase-1 tool.
+      // 12 -> 13: F3 shipped omniroute_radar_catalog as a phase-1 read-only tool.
       const schemas = MCP_ESSENTIAL_TOOLS;
-      expect(schemas).toHaveLength(12);
+      expect(schemas).toHaveLength(13);
     });
 
     it("all tools should have omniroute_ prefix", () => {

open-sse/mcp-server/__tests__/radarCatalogTool.test.ts

@@ -0,0 +1,151 @@
+import { afterEach, beforeEach, describe, expect, it, vi } from "vitest";
+import { Client } from "@modelcontextprotocol/sdk/client/index.js";
+import { InMemoryTransport } from "@modelcontextprotocol/sdk/inMemory.js";
+
+import { MCP_SCOPE_LIST, MCP_TOOL_SCOPES } from "../../../src/shared/constants/mcpScopes.ts";
+import { evaluateToolScopes } from "../scopeEnforcement.ts";
+import { getMcpRadarCatalog } from "../radarCatalog.ts";
+import { MCP_ESSENTIAL_TOOLS, MCP_TOOL_MAP } from "../schemas/tools.ts";
+import { createMcpServer } from "../server.ts";
+
+vi.mock("../audit.ts", () => ({
+  logToolCall: vi.fn().mockResolvedValue(undefined),
+}));
+
+const catalog = {
+  entries: [
+    {
+      provider: "groq",
+      modelId: "llama",
+      displayName: "Llama on Groq",
+      familyId: "llama-family",
+      monthlyTokens: 200,
+      creditTokens: 0,
+      freeType: "recurring-daily",
+      poolKey: null,
+      tos: "ok",
+      enabled: true,
+      origin: "radar",
+      capabilities: { tools: true, vision: false, thinking: false },
+      limits: { rpm: 30, rpd: null, tpm: null, tpd: null },
+      setup: { keyUrl: "https://secret.example/key", steps: ["do not expose"] },
+    },
+    {
+      provider: "cerebras",
+      modelId: "llama",
+      displayName: "Llama on Cerebras",
+      familyId: "llama-family",
+      monthlyTokens: 300,
+      creditTokens: 0,
+      freeType: "recurring-daily",
+      poolKey: null,
+      tos: "ok",
+      enabled: false,
+      disabledBy: "radar",
+      origin: "radar",
+      capabilities: { tools: true, vision: false, thinking: true },
+      limits: { rpm: null, rpd: 100, tpm: null, tpd: null },
+    },
+  ],
+  meta: { version: "2026.08.08.1", tier: "community", fetchedAt: "2026-08-08T20:00:00Z" },
+};
+
+describe("omniroute_radar_catalog", () => {
+  it("is a phase-1 read-only registry tool with the dedicated Radar scope", () => {
+    const definition = MCP_TOOL_MAP.omniroute_radar_catalog;
+    expect(definition).toBeDefined();
+    expect(definition.phase).toBe(1);
+    expect(definition.scopes).toEqual(["read:radar"]);
+    expect(definition.auditLevel).toBe("none");
+    expect(definition.sourceEndpoints).toEqual(["/api/radar/catalog"]);
+    expect(MCP_ESSENTIAL_TOOLS).toContain(definition);
+    expect(MCP_SCOPE_LIST).toContain("read:radar");
+    expect(MCP_TOOL_SCOPES.omniroute_radar_catalog).toEqual(["read:radar"]);
+  });
+
+  it("reads only the local catalog and returns a closed filtered projection", async () => {
+    const fetchJson = vi.fn().mockResolvedValue(catalog);
+    const result = await getMcpRadarCatalog(
+      { provider: "groq", familyId: "llama-family", enabledOnly: true },
+      { fetchJson }
+    );
+
+    expect(fetchJson).toHaveBeenCalledOnce();
+    expect(fetchJson).toHaveBeenCalledWith("/api/radar/catalog");
+    expect(result.models).toHaveLength(1);
+    expect(result.models[0]).toEqual({
+      provider: "groq",
+      modelId: "llama",
+      displayName: "Llama on Groq",
+      familyId: "llama-family",
+      quota: {
+        monthlyTokens: 200,
+        creditTokens: 0,
+        freeType: "recurring-daily",
+        limits: { rpm: 30, rpd: null, tpm: null, tpd: null },
+      },
+      capabilities: { tools: true, vision: false, thinking: false },
+      enabled: true,
+      origin: "radar",
+      disabledBy: null,
+    });
+    expect(JSON.stringify(result)).not.toContain("secret.example");
+    expect(JSON.stringify(result)).not.toContain("setup");
+  });
+
+  it("defaults enabledOnly to true and includes disabled models only when explicitly requested", async () => {
+    const fetchJson = vi.fn().mockResolvedValue(catalog);
+    expect((await getMcpRadarCatalog({}, { fetchJson })).models).toHaveLength(1);
+    expect((await getMcpRadarCatalog({ enabledOnly: false }, { fetchJson })).models).toHaveLength(
+      2
+    );
+  });
+
+  it("allows read:radar and read:* but denies a missing scope when enforcement is active", () => {
+    expect(evaluateToolScopes("omniroute_radar_catalog", ["read:radar"], true).allowed).toBe(true);
+    expect(evaluateToolScopes("omniroute_radar_catalog", ["read:*"], true).allowed).toBe(true);
+    expect(evaluateToolScopes("omniroute_radar_catalog", [], true)).toMatchObject({
+      allowed: false,
+      reason: "missing_scopes",
+      missing: ["read:radar"],
+    });
+  });
+});
+
+describe("omniroute_radar_catalog MCP dispatch", () => {
+  const mockFetch = vi.fn();
+  let client: Client;
+
+  beforeEach(async () => {
+    mockFetch.mockReset();
+    vi.stubGlobal("fetch", mockFetch);
+    const [clientTransport, serverTransport] = InMemoryTransport.createLinkedPair();
+    const server = createMcpServer();
+    await server.connect(serverTransport);
+    client = new Client({ name: "radar-catalog-test", version: "1.0.0" });
+    await client.connect(clientTransport);
+  });
+
+  afterEach(async () => {
+    await client.close();
+    vi.unstubAllGlobals();
+  });
+
+  it("registers and dispatches a real read without sync or write", async () => {
+    mockFetch.mockResolvedValueOnce({ ok: true, json: async () => catalog });
+
+    const listed = await client.listTools();
+    expect(listed.tools.some((tool) => tool.name === "omniroute_radar_catalog")).toBe(true);
+
+    const result = await client.callTool({
+      name: "omniroute_radar_catalog",
+      arguments: { enabledOnly: false },
+    });
+    expect(result.isError).toBeFalsy();
+    expect(mockFetch).toHaveBeenCalledOnce();
+    expect(mockFetch.mock.calls[0][0]).toContain("/api/radar/catalog");
+    expect(mockFetch.mock.calls[0][1]).not.toMatchObject({ method: "POST" });
+    const body = JSON.parse((result.content[0] as { text: string }).text);
+    expect(body.models).toHaveLength(2);
+  });
+});

open-sse/mcp-server/radarCatalog.ts

@@ -0,0 +1,170 @@
+import type { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js";
+
+import { logToolCall } from "./audit.ts";
+import { radarCatalogInput, radarCatalogOutput } from "./schemas/radarCatalog.ts";
+import type { McpToolExtraLike } from "./scopeEnforcement.ts";
+import type { TextToolResult } from "./toolResult.ts";
+import { sanitizeErrorMessage } from "../utils/error.ts";
+
+type JsonRecord = Record<string, unknown>;
+
+type ScopeEnforcer = (
+  toolName: string,
+  handler: (args: unknown, extra?: McpToolExtraLike) => Promise<TextToolResult>,
+  toolScopes?: readonly string[]
+) => (args: unknown, extra?: McpToolExtraLike) => Promise<TextToolResult>;
+
+export interface McpRadarCatalogArgs {
+  provider?: string;
+  familyId?: string;
+  enabledOnly?: boolean;
+}
+
+interface McpRadarCatalogDeps {
+  fetchJson?: (path: string) => Promise<unknown>;
+}
+
+function record(value: unknown): JsonRecord {
+  return value !== null && typeof value === "object" && !Array.isArray(value)
+    ? (value as JsonRecord)
+    : {};
+}
+
+function text(value: unknown, fallback = ""): string {
+  return typeof value === "string" ? value : fallback;
+}
+
+function number(value: unknown): number {
+  return typeof value === "number" && Number.isFinite(value) && value >= 0 ? value : 0;
+}
+
+function nullableNumber(value: unknown): number | null {
+  return typeof value === "number" && Number.isFinite(value) && value >= 0 ? value : null;
+}
+
+function normalizeMeta(
+  value: unknown
+): { version: string; tier: string; fetchedAt: string } | null {
+  const meta = record(value);
+  if (
+    typeof meta.version !== "string" ||
+    typeof meta.tier !== "string" ||
+    typeof meta.fetchedAt !== "string"
+  ) {
+    return null;
+  }
+  return { version: meta.version, tier: meta.tier, fetchedAt: meta.fetchedAt };
+}
+
+function normalizeEntry(value: unknown) {
+  const entry = record(value);
+  const provider = text(entry.provider).trim();
+  const modelId = text(entry.modelId).trim();
+  if (!provider || !modelId) return null;
+
+  const capabilities = record(entry.capabilities);
+  const limits = record(entry.limits);
+  const origin =
+    entry.origin === "radar" || entry.origin === "local" ? entry.origin : ("baseline" as const);
+  return {
+    provider,
+    modelId,
+    displayName: text(entry.displayName, modelId),
+    familyId: typeof entry.familyId === "string" ? entry.familyId : null,
+    quota: {
+      monthlyTokens: number(entry.monthlyTokens),
+      creditTokens: number(entry.creditTokens),
+      freeType: text(entry.freeType, "unknown"),
+      limits:
+        Object.keys(limits).length > 0
+          ? {
+              rpm: nullableNumber(limits.rpm),
+              rpd: nullableNumber(limits.rpd),
+              tpm: nullableNumber(limits.tpm),
+              tpd: nullableNumber(limits.tpd),
+            }
+          : null,
+    },
+    capabilities:
+      Object.keys(capabilities).length > 0
+        ? {
+            tools: capabilities.tools === true,
+            vision: capabilities.vision === true,
+            thinking: capabilities.thinking === true,
+          }
+        : null,
+    enabled: entry.enabled !== false,
+    origin,
+    disabledBy: entry.disabledBy === "radar" ? ("radar" as const) : null,
+  };
+}
+
+function compareEntries(
+  left: NonNullable<ReturnType<typeof normalizeEntry>>,
+  right: NonNullable<ReturnType<typeof normalizeEntry>>
+): number {
+  return left.provider.localeCompare(right.provider) || left.modelId.localeCompare(right.modelId);
+}
+
+/** Read and project the local Radar catalog without exposing setup or secret-bearing state. */
+export async function getMcpRadarCatalog(
+  args: McpRadarCatalogArgs,
+  deps: McpRadarCatalogDeps = {}
+) {
+  const fetchJson =
+    deps.fetchJson ??
+    ((path: string) => import("./server.ts").then((module) => module.omniRouteFetch(path)));
+  const raw = record(await fetchJson("/api/radar/catalog"));
+  const providerFilter = args.provider?.trim().toLowerCase();
+  const familyFilter = args.familyId?.trim().toLowerCase();
+  const enabledOnly = args.enabledOnly !== false;
+  const entries = Array.isArray(raw.entries) ? raw.entries : [];
+  const models = entries
+    .map(normalizeEntry)
+    .filter((entry): entry is NonNullable<typeof entry> => entry !== null)
+    .filter((entry) => !enabledOnly || entry.enabled)
+    .filter((entry) => !providerFilter || entry.provider.toLowerCase() === providerFilter)
+    .filter((entry) => !familyFilter || entry.familyId?.toLowerCase() === familyFilter)
+    .sort(compareEntries);
+
+  return { meta: normalizeMeta(raw.meta), models };
+}
+
+async function handleRadarCatalog(args: {
+  provider?: string;
+  familyId?: string;
+  enabledOnly: boolean;
+}): Promise<TextToolResult> {
+  const start = Date.now();
+  try {
+    const result = radarCatalogOutput.parse(await getMcpRadarCatalog(args));
+    await logToolCall(
+      "omniroute_radar_catalog",
+      args,
+      { modelCount: result.models.length },
+      Date.now() - start,
+      true
+    );
+    return { content: [{ type: "text", text: JSON.stringify(result, null, 2) }] };
+  } catch (error) {
+    const message = sanitizeErrorMessage(error) || "Failed to read Radar catalog";
+    await logToolCall("omniroute_radar_catalog", args, null, Date.now() - start, false, message);
+    return { content: [{ type: "text", text: `Error: ${message}` }], isError: true };
+  }
+}
+
+export function registerRadarCatalogTool(
+  server: McpServer,
+  withScopeEnforcement: ScopeEnforcer
+): void {
+  server.registerTool(
+    "omniroute_radar_catalog",
+    {
+      description: "Reads the local signed Radar catalog with optional provider and family filters",
+      inputSchema: radarCatalogInput,
+    },
+    withScopeEnforcement("omniroute_radar_catalog", (args) =>
+      handleRadarCatalog(radarCatalogInput.parse(args))
+    )
+  );
+}

open-sse/mcp-server/schemas/index.ts

@@ -91,6 +91,8 @@ export {
   ccrStatsTool,
 } from "./tools.ts";
 
+export { radarCatalogInput, radarCatalogOutput, radarCatalogTool } from "./radarCatalog.ts";
+
 // A2A schemas
 export {
   AgentCardSchema,

open-sse/mcp-server/schemas/radarCatalog.ts

@@ -0,0 +1,65 @@
+import { z } from "zod";
+
+import type { McpToolDefinition } from "./toolDefinition.ts";
+
+export const radarCatalogInput = z.object({
+  provider: z.string().trim().min(1).max(100).optional().describe("Filter by provider id"),
+  familyId: z.string().trim().min(1).max(120).optional().describe("Filter by curated family id"),
+  enabledOnly: z.boolean().default(true).describe("Exclude models disabled by the Radar feed"),
+});
+
+const radarLimitOutput = z.object({
+  rpm: z.number().nullable(),
+  rpd: z.number().nullable(),
+  tpm: z.number().nullable(),
+  tpd: z.number().nullable(),
+});
+
+export const radarCatalogOutput = z.object({
+  meta: z
+    .object({
+      version: z.string(),
+      tier: z.string(),
+      fetchedAt: z.string(),
+    })
+    .nullable(),
+  models: z.array(
+    z.object({
+      provider: z.string(),
+      modelId: z.string(),
+      displayName: z.string(),
+      familyId: z.string().nullable(),
+      quota: z.object({
+        monthlyTokens: z.number(),
+        creditTokens: z.number(),
+        freeType: z.string(),
+        limits: radarLimitOutput.nullable(),
+      }),
+      capabilities: z
+        .object({
+          tools: z.boolean(),
+          vision: z.boolean(),
+          thinking: z.boolean(),
+        })
+        .nullable(),
+      enabled: z.boolean(),
+      origin: z.enum(["baseline", "radar", "local"]),
+      disabledBy: z.literal("radar").nullable(),
+    })
+  ),
+});
+
+export const radarCatalogTool: McpToolDefinition<
+  typeof radarCatalogInput,
+  typeof radarCatalogOutput
+> = {
+  name: "omniroute_radar_catalog",
+  description:
+    "Reads the local signed Radar catalog with optional provider and curated-family filters. Never syncs or writes data.",
+  inputSchema: radarCatalogInput,
+  outputSchema: radarCatalogOutput,
+  scopes: ["read:radar"],
+  auditLevel: "none",
+  phase: 1,
+  sourceEndpoints: ["/api/radar/catalog"],
+};

open-sse/mcp-server/schemas/tools.ts

@@ -1,5 +1,5 @@
 /**
- * MCP Tool Schemas — Contracts for all 23 core and advanced OmniRoute MCP tools.
+ * MCP Tool Schemas — Contracts for the canonical OmniRoute MCP tools.
  *
  * Defines input/output Zod schemas, descriptions, scopes, and audit levels
  * for both essential (Phase 1) and advanced (Phase 2) MCP tools.
@@ -13,11 +13,11 @@ import { z } from "zod";
 import { toolSearchTool } from "./toolSearch.ts";
 import { pickFastestModelTool } from "./pickFastestModel.ts";
 import { CCR_MCP_TOOLS } from "./ccrTools.ts";
+import { radarCatalogTool } from "./radarCatalog.ts";
 import {
   AUTO_ROUTING_STRATEGY_VALUES,
   ROUTING_STRATEGY_VALUES,
 } from "../../../src/shared/constants/routingStrategies.ts";
-
 // ============ Shared Types ============
 // AuditLevel + McpToolDefinition live in the leaf ./toolDefinition.ts so that
 // toolSearch.ts can import the type without forming a tools.ts ↔ toolSearch.ts cycle.
@@ -26,8 +26,7 @@ export type { AuditLevel, McpToolDefinition } from "./toolDefinition.ts";
 import type { McpToolDefinition } from "./toolDefinition.ts";
 export { pickFastestModelInput, pickFastestModelOutput } from "./pickFastestModel.ts";
 export * from "./ccrTools.ts";
-
+// ============ Phase 1: Essential Tools ============
-// ============ Phase 1: Essential Tools (8) ============
 
 // --- Tool 1: omniroute_get_health ---
 export const getHealthInput = z.object({}).describe("No parameters required");
@@ -440,7 +439,7 @@ export const listModelsCatalogTool: McpToolDefinition<
   sourceEndpoints: ["/api/models/catalog", "/v1/models"],
 };
 
-// --- Tool 9: omniroute_web_search ---
+// --- Tool 10: omniroute_web_search ---
 export const webSearchInput = z.object({
   query: z
     .string()
@@ -1519,6 +1518,7 @@ export const MCP_TOOLS = [
   routeRequestTool,
   costReportTool,
   listModelsCatalogTool,
+  radarCatalogTool,
   webSearchTool,
   webFetchTool,
   simulateRouteTool,

open-sse/mcp-server/server.ts

@@ -93,6 +93,8 @@ import { normalizeQuotaResponse } from "../../src/shared/contracts/quota.ts";
 import { resolveOmniRouteBaseUrl } from "../../src/shared/utils/resolveOmniRouteBaseUrl.ts";
 import { sanitizeErrorMessage } from "../utils/error.ts";
 import { getMcpModelsCatalog } from "./catalog.ts";
+import { registerRadarCatalogTool } from "./radarCatalog.ts";
+import type { TextToolResult } from "./toolResult.ts";
 export { getMcpModelsCatalog } from "./catalog.ts";
 
 const OMNIROUTE_BASE_URL = resolveOmniRouteBaseUrl();
@@ -146,11 +148,6 @@ function readMcpAccessibilityConfig(): McpAccessibilityConfig {
   }
 }
 
-type TextToolResult = {
-  content: Array<{ type: "text"; text: string }>;
-  isError?: boolean;
-};
-
 function toRecord(value: unknown): JsonRecord {
   return value && typeof value === "object" && !Array.isArray(value) ? (value as JsonRecord) : {};
 }
@@ -842,6 +839,8 @@ export function createMcpServer(): McpServer {
     )
   );
 
+  registerRadarCatalogTool(server, withScopeEnforcement);
+
   server.registerTool(
     "omniroute_simulate_route",
     {

open-sse/mcp-server/toolResult.ts

@@ -0,0 +1,4 @@
+export type TextToolResult = {
+  content: Array<{ type: "text"; text: string }>;
+  isError?: boolean;
+};

open-sse/services/accountFallback.ts

@@ -15,7 +15,11 @@ import {
   serviceSupervisorCooldown,
   isNimFunctionDegraded,
 } from "../config/errorConfig.ts";
-import { getProviderErrorRuleMatch, resolveRuleMatchBody } from "../config/providerErrorRules.ts";
+import {
+  getProviderErrorRuleMatch,
+  resolveRuleMatchBody,
+  honorsRuleLockScope,
+} from "../config/providerErrorRules.ts";
 import * as rot from "./rotationConfig.ts";
 import { getPassthroughProviders, getProviderCategory } from "../config/providerRegistry.ts";
 import {
@@ -1458,6 +1462,11 @@ export function checkFallbackError(
   /** #6061: the provider-configured cooldown (ms) before backoff scaling, surfaced so the
    * caller can persist an explicit reset window instead of the engine's scaled cooldown. */
   configuredCooldownMs?: number;
+  /** #10334 — the matched ProviderErrorRule's declared lock scope, surfaced so the
+   * persistence layer can honor it instead of re-deriving scope from
+   * hasPerModelQuota(). Populated ONLY when honorsRuleLockScope(provider) is true;
+   * always undefined for every other provider, so existing consumers are unaffected. */
+  ruleScope?: "model" | "provider" | "connection";
 } {
   // #10360: an executor-result contract violation is OUR bug, not the provider's.
   // Retrying reproduces it verbatim, and cooling the connection down (or tripping
@@ -1712,6 +1721,36 @@ export function checkFallbackError(
       return { shouldFallback: false, cooldownMs: 0, reason: RateLimitReason.UNKNOWN };
     }
 
+    // #10334 — agentrouter EXCLUSIVE: consult the provider rules BEFORE the
+    // apikey-FORBIDDEN early-return below, so a recognized 403 body (e.g.
+    // "无权访问模型") carries the rule's declared reason/cooldown/scope instead of
+    // the generic short auth cooldown. Gated on honorsRuleLockScope — for any
+    // other provider this block is a no-op and the early-return stays identical.
+    if (status === HTTP_STATUS.FORBIDDEN && provider && honorsRuleLockScope(provider)) {
+      const forbiddenMatch = getProviderErrorRuleMatch(
+        provider,
+        status,
+        headers,
+        resolveRuleMatchBody(provider, structuredError ?? null, errorStr)
+      );
+      if (forbiddenMatch) {
+        const scaled = getScaledBaseCooldown(
+          forbiddenMatch.reason as RateLimitReasonValue,
+          backoffLevel
+        );
+        const ruleCooldownMs = forbiddenMatch.cooldownMs;
+        return {
+          shouldFallback: true,
+          cooldownMs: ruleCooldownMs ?? scaled.cooldownMs,
+          baseCooldownMs: ruleCooldownMs ?? scaled.baseCooldownMs,
+          configuredCooldownMs: ruleCooldownMs,
+          newBackoffLevel: ruleCooldownMs !== undefined ? 0 : scaled.newBackoffLevel,
+          reason: forbiddenMatch.reason,
+          ruleScope: forbiddenMatch.scope,
+        };
+      }
+    }
+
     if (
       status === HTTP_STATUS.FORBIDDEN &&
       provider &&
@@ -1764,6 +1803,8 @@ export function checkFallbackError(
         providerMatch?.cooldownMs !== undefined && providerMatch.cooldownMs > 0
           ? providerMatch.cooldownMs
           : undefined;
+      const ruleScope =
+        providerMatch && honorsRuleLockScope(provider) ? providerMatch.scope : undefined;
       const fallback = buildRetryableFallback(reason);
       if (providerCooldownMs !== undefined) {
         return {
@@ -1771,9 +1812,10 @@ export function checkFallbackError(
           cooldownMs: providerCooldownMs,
           baseCooldownMs: providerCooldownMs,
           configuredCooldownMs: providerCooldownMs,
+          ruleScope,
         };
       }
-      return fallback;
+      return { ...fallback, ruleScope };
     }
     // #6842: non-backoff configured rules (e.g. status_402) previously never
     // consulted providerRuleRegistry, so a provider-specific rule (like
@@ -1789,12 +1831,15 @@ export function checkFallbackError(
         )
       : null;
     const cooldownMs = providerMatch?.cooldownMs ?? configuredRule.cooldownMs ?? 0;
+    const ruleScope =
+      providerMatch && honorsRuleLockScope(provider) ? providerMatch.scope : undefined;
     return {
       shouldFallback: true,
       cooldownMs,
       baseCooldownMs: cooldownMs,
       configuredCooldownMs: cooldownMs,
       reason: providerMatch?.reason ?? configuredRule.reason ?? RateLimitReason.UNKNOWN,
+      ruleScope,
     };
   }
 

open-sse/services/combo/targetExhaustion.ts

@@ -27,6 +27,10 @@ import {
 import { RateLimitReason } from "../../config/constants.ts";
 import { isProviderCircuitOpenResult, isRequestScopedUpstreamFailure } from "./comboPredicates.ts";
 import { isCloudflareFingerprintRejection } from "../errorClassifier.ts";
+// #10334 — agentrouter-exclusive predicate shared with the persistence layer
+// (markAccountUnavailable) so the same-request combo skip and the persisted
+// connection cooldown agree on exactly which fallbackResult shapes qualify.
+import { isAgentrouterConnectionQuotaScope } from "@/sse/services/auth";
 import type { ComboLogger, ResolvedComboTarget } from "./types.ts";
 
 // Connection-level failure statuses: the provider connection itself is likely bad (upstream
@@ -60,7 +64,13 @@ export type ComboExhaustionSets = {
 
 export type ApplyComboTargetExhaustionOptions = {
   result: { status: number; headers?: Headers | null };
-  fallbackResult: Parameters<typeof isProviderExhaustedReason>[0];
+  fallbackResult: Parameters<typeof isProviderExhaustedReason>[0] & {
+    /** #10334 — agentrouter-exclusive; see isAgentrouterConnectionQuotaScope
+     * (src/sse/services/auth.ts). Populated only for providers in
+     * HONORS_RULE_LOCK_SCOPE_PROVIDERS (today: agentrouter only). */
+    ruleScope?: "model" | "provider" | "connection";
+    permanent?: boolean;
+  };
   errorText: string;
   rawModel: string;
   isTokenLimitBreach: boolean;
@@ -86,6 +96,56 @@ export function applyComboTargetExhaustion(
   const { result, sets, log, tag, errorText, structuredError } = opts;
   const provider = target.provider;
 
+  // #10334: agentrouter-exclusive account-wide quota exhaustion ("额度不足")
+  // must skip remaining SAME-CONNECTION targets within THIS request too, not
+  // just via the persisted cooldown markAccountUnavailable applies for
+  // whichever leg runs next. agentrouter is a passthroughModels provider
+  // (hasPerModelQuota() === true), so without this branch the classification
+  // below would fall straight through isProviderQuotaExhausted's
+  // !hasPerModelQuota() guard, and — for the restated-429 case —
+  // markConnectionLevelExhaustion's connection-level guard (429 is not in
+  // CONNECTION_LEVEL_ERROR_STATUSES), marking nothing: combo would keep
+  // burning one upstream call per remaining model of the same exhausted
+  // account. isAgentrouterConnectionQuotaScope is the same guard
+  // markAccountUnavailable uses, so both consumers agree on exactly which
+  // fallbackResult shapes qualify (never a permanent/credits-exhausted
+  // result, even one carrying ruleScope "connection").
+  //
+  // Runs BEFORE the auth-level (401/403) branch below. This is deliberate,
+  // not incidental: the "额度不足" rule matches statuses {400, 403, 429}
+  // (buildAgentrouterRules, providerErrorRules.ts), and Task 1's FORBIDDEN
+  // pre-check (accountFallback.ts ~1729-1751) surfaces `ruleScope:
+  // "connection"` for a RAW 403 carrying that body too — so this branch can
+  // also fire on a 403, not just the restated 429. That is safe: for a 403
+  // this branch and markAuthLevelExhaustion below write the SAME set with
+  // the SAME `${provider}:${connId}` key and both return `true` — they are
+  // set-equivalent for agentrouter on that status. The Cloudflare-1010 and
+  // Alibaba free-tier EXEMPTIONS further down in the 401/403 branch cannot
+  // apply here regardless of ordering: 1010 is a CDN fingerprint rejection
+  // agentrouter's own text never carries, and the Alibaba exemption is
+  // gated on isAlibabaModelStudioProvider(provider), which agentrouter is
+  // not.
+  //
+  // Unlike the connection-level/auth-level branches, this path deliberately
+  // does NOT fall through to markTransientOrConnectionLevel, so
+  // sets.transientRateLimitedProviders is NEVER populated for this failure.
+  // That is required, not just incidental: combo.ts (both dispatchers, see
+  // the `allowRateLimitedConnection` reads keyed off
+  // transientRateLimitedProviders) uses that set to force-allow reusing a
+  // rate-limited CONNECTION for the provider's remaining legs — i.e. it
+  // bypasses the very `rateLimitedUntil` filter this branch (and Task 2's
+  // markAccountUnavailable) just set. Marking it here would silently
+  // re-open the account this branch just cooled down. One secondary
+  // consequence: a SIBLING agentrouter connection that is merely
+  // rate-limited (not the one this branch exhausted) will also no longer be
+  // force-allowed for a later leg on the same provider — a remaining leg
+  // can now resolve to "no credentials available" instead of retrying a
+  // rate-limited sibling account, which is the intended, safer outcome.
+  if (isAgentrouterConnectionQuotaScope(provider, opts.fallbackResult)) {
+    markAgentrouterConnectionQuotaExhaustion(target, { sets, log, tag });
+    return true;
+  }
+
   // #8133/#8137: auth-level failures (401/403) mean that connection's credentials are bad.
   // Split out to keep applyComboTargetExhaustion under the complexity ceiling.
   // Cloudflare 1010 (a 403 carrying error_code 1010 / browser_signature_banned) is NOT an
@@ -259,6 +319,35 @@ function markAuthLevelExhaustion(
   }
 }
 
+/**
+ * #10334: agentrouter-exclusive connection-scope account quota exhaustion. Mirrors
+ * markAuthLevelExhaustion's connectionId-present/absent split — when the target carries a
+ * connectionId, only that connection's account is exhausted (sibling agentrouter connections
+ * for the same user may still have quota); fall back to whole-provider exhaustion only when no
+ * connectionId is available.
+ */
+function markAgentrouterConnectionQuotaExhaustion(
+  target: ResolvedComboTarget,
+  opts: Pick<ApplyComboTargetExhaustionOptions, "sets" | "log" | "tag">
+): void {
+  const { sets, log, tag } = opts;
+  const provider = target.provider;
+  const connId = target.connectionId ?? undefined;
+  if (connId) {
+    sets.exhaustedConnections.add(`${provider}:${connId}`);
+    log.info(
+      tag,
+      `Provider ${provider} connection ${connId} account quota exhausted (rule scope=connection) — marking for skip on remaining targets (#10334)`
+    );
+  } else {
+    sets.exhaustedProviders.add(provider as string);
+    log.info(
+      tag,
+      `Provider ${provider} account quota exhausted (rule scope=connection, no connectionId) — marking for skip on remaining targets (#10334)`
+    );
+  }
+}
+
 /**
  * #1731v2: connection-level errors (408/5xx, excluding the OmniRoute circuit-open signal) suggest
  * the provider connection itself is bad → skip remaining same-connection (or same-provider, when

open-sse/services/qwenTokenPlanQuotaFetcher.ts

@@ -0,0 +1,437 @@
+/**
+ * qwenTokenPlanQuotaFetcher.ts — Qwen Cloud / Alibaba Model Studio PERSONAL Token Plan
+ * quota fetcher (issue #9603, "quota is missing").
+ *
+ * The personal Token Plan (5-hour / 7-day sliding windows) has NO official OpenAPI —
+ * the console gateway is the only quota surface, and the inference API key does NOT
+ * authenticate it. Both portals read the same backend:
+ *   - home.qwencloud.com portal        → https://cs-data.qwencloud.com          (default)
+ *   - Model Studio console (intl)      → https://bailian-singapore-cs.alibabacloud.com
+ *
+ * Transport (captured live 2026-08-13 from a logged-in session):
+ *   POST {host}/data/api.json?product=sfm_bailian&action=IntlBroadScopeAspnGateway
+ *        &api=zeldaHttp.apikeyMgr.%2Ftokenplan%2Fpersonal%2Fapi%2Fv2%2F<endpoint>
+ *   form body: product, action, sec_token, region, params =
+ *     {"Api":"zeldaHttp.apikeyMgr./tokenplan/personal/api/v2/<endpoint>","V":"1.0",
+ *      "Data":{"commodityCode":"sfm_tokenplansolo_public_intl","cornerstoneParam":{...}}}
+ *   Auth: browser session Cookie (providerSpecificData or QWEN_CLOUD_COOKIE env).
+ *   sec_token: best-effort — resolved from the dashboard HTML (`SEC_TOKEN: "…"`) when
+ *   not provided; some accounts reject requests without it
+ *   (BailianGateway.Workspace.NotAuthorised).
+ *
+ * Windows: usage returns per<Window>Percentage (fraction used, 0..1) +
+ * per<Window>ResetTime (epoch ms). Fields are OMITTED while a window is
+ * "Temporarily Removed" (observed for 5-hour), so every window is optional.
+ *
+ * Cache: usage 60s per connection; subscription/quota-config (slow-moving tier data)
+ * 1h per connection. Registration: registerQwenTokenPlanQuotaFetcher() at startup.
+ */
+
+import { registerQuotaFetcher, registerQuotaWindows, type QuotaInfo } from "./quotaPreflight.ts";
+import { registerMonitorFetcher } from "./quotaMonitor.ts";
+import { throttleQuotaFetch } from "./quotaFetchThrottle.ts";
+
+const DEFAULT_GATEWAY_HOST = "https://cs-data.qwencloud.com";
+const DEFAULT_DASHBOARD_URL = "https://home.qwencloud.com/";
+
+/**
+ * The same personal Token Plan is sold through two consoles that share one backend.
+ * The gateway validates the browser session against the console identity sent in the
+ * request, so an Alibaba cookie paired with the QwenCloud identity is rejected with
+ * `BailianGateway.Login.NotLogined` (verified live 2026-08-14).
+ */
+export interface TokenPlanConsoleSite {
+  consoleSite: "QWENCLOUD" | "ALIYUN";
+  domain: string;
+  gatewayHost: string;
+  dashboardUrl: string;
+  origin: string;
+}
+
+const CONSOLE_SITES: Record<"qwencloud" | "aliyun", TokenPlanConsoleSite> = {
+  qwencloud: {
+    consoleSite: "QWENCLOUD",
+    domain: "home.qwencloud.com",
+    gatewayHost: DEFAULT_GATEWAY_HOST,
+    dashboardUrl: DEFAULT_DASHBOARD_URL,
+    origin: "https://home.qwencloud.com",
+  },
+  aliyun: {
+    consoleSite: "ALIYUN",
+    domain: "modelstudio.console.alibabacloud.com",
+    gatewayHost: "https://bailian-singapore-cs.alibabacloud.com",
+    dashboardUrl: "https://modelstudio.console.alibabacloud.com/",
+    origin: "https://modelstudio.console.alibabacloud.com",
+  },
+};
+
+/** Providers served by the Alibaba (Model Studio) console rather than QwenCloud. */
+const ALIYUN_CONSOLE_PROVIDERS = new Set(["bailian-coding-plan", "alibaba", "alibaba-cn"]);
+
+/**
+ * Pick the console identity for a cookie: the login ticket names its console
+ * (`login_aliyunid_ticket` vs `login_qwencloud_ticket`). Unmarked cookies fall back to
+ * the provider, then to QwenCloud.
+ */
+export function resolveConsoleSite(
+  cookie: string,
+  provider: string | undefined
+): TokenPlanConsoleSite {
+  if (/login_aliyunid_ticket=/.test(cookie)) return CONSOLE_SITES.aliyun;
+  if (/login_qwencloud_ticket=/.test(cookie)) return CONSOLE_SITES.qwencloud;
+  if (provider && ALIYUN_CONSOLE_PROVIDERS.has(provider)) return CONSOLE_SITES.aliyun;
+  return CONSOLE_SITES.qwencloud;
+}
+const GATEWAY_REGION = "ap-southeast-1";
+const GATEWAY_PRODUCT = "sfm_bailian";
+const GATEWAY_ACTION = "IntlBroadScopeAspnGateway";
+const COMMODITY_CODE = "sfm_tokenplansolo_public_intl";
+const TOKEN_PLAN_API_PREFIX = "zeldaHttp.apikeyMgr./tokenplan/personal/api/v2/";
+
+const USAGE_CACHE_TTL_MS = 60_000;
+const TIER_CACHE_TTL_MS = 60 * 60_000;
+
+// Window keys surfaced to the dashboard / quota-window registry
+export const QWEN_TOKEN_PLAN_WINDOW_5H = "window_5h";
+export const QWEN_TOKEN_PLAN_WINDOW_WEEKLY = "window_weekly";
+
+// usage payload field prefix → window key (fields: per<prefix>Percentage / per<prefix>ResetTime)
+const WINDOW_FIELD_MAP: Record<string, string> = {
+  "5Hour": QWEN_TOKEN_PLAN_WINDOW_5H,
+  "1Week": QWEN_TOKEN_PLAN_WINDOW_WEEKLY,
+};
+
+export interface QwenTokenPlanQuota extends QuotaInfo {
+  windows: Record<string, { percentUsed: number; resetAt: string | null }>;
+  /** Which console served the quota — drives the plan label shown in the dashboard. */
+  consoleSite: TokenPlanConsoleSite["consoleSite"];
+  /** Subscription tier (e.g. "pro") or null when the subscription call failed. */
+  specCode: string | null;
+  /** Credit limits of the active tier (from quota-config), when resolvable. */
+  tierLimits: { fiveHour: number | null; weekly: number | null };
+}
+
+interface UsageCacheEntry {
+  quota: QwenTokenPlanQuota;
+  fetchedAt: number;
+}
+
+interface TierCacheEntry {
+  specCode: string | null;
+  tierLimits: { fiveHour: number | null; weekly: number | null };
+  fetchedAt: number;
+}
+
+const usageCache = new Map<string, UsageCacheEntry>();
+const tierCache = new Map<string, TierCacheEntry>();
+const secTokenCache = new Map<string, { token: string; fetchedAt: number }>();
+
+const _cacheCleanup = setInterval(() => {
+  const now = Date.now();
+  for (const [key, entry] of usageCache) {
+    if (now - entry.fetchedAt > USAGE_CACHE_TTL_MS * 5) usageCache.delete(key);
+  }
+  for (const [key, entry] of tierCache) {
+    if (now - entry.fetchedAt > TIER_CACHE_TTL_MS * 2) tierCache.delete(key);
+  }
+  for (const [key, entry] of secTokenCache) {
+    if (now - entry.fetchedAt > TIER_CACHE_TTL_MS * 2) secTokenCache.delete(key);
+  }
+}, 5 * 60_000);
+
+if (typeof _cacheCleanup === "object" && "unref" in _cacheCleanup) {
+  (_cacheCleanup as { unref?: () => void }).unref?.();
+}
+
+// ─── Helpers ─────────────────────────────────────────────────────────────────
+
+function toRecord(value: unknown): Record<string, unknown> {
+  return value && typeof value === "object" && !Array.isArray(value)
+    ? (value as Record<string, unknown>)
+    : {};
+}
+
+function toNumberOrNull(value: unknown): number | null {
+  if (typeof value === "number" && Number.isFinite(value)) return value;
+  if (typeof value === "string") {
+    const parsed = parseFloat(value);
+    if (Number.isFinite(parsed)) return parsed;
+  }
+  return null;
+}
+
+function toTrimmedString(value: unknown): string {
+  return typeof value === "string" ? value.trim() : "";
+}
+
+function getCookie(providerSpecificData: Record<string, unknown> | undefined): string {
+  for (const key of ["qwenCloudCookie", "alibabaConsoleCookie", "cookie"]) {
+    const value = toTrimmedString(providerSpecificData?.[key]);
+    if (value) return value;
+  }
+  return process.env.QWEN_CLOUD_COOKIE?.trim() || "";
+}
+
+function getConfiguredSecToken(providerSpecificData: Record<string, unknown> | undefined): string {
+  for (const key of ["qwenCloudSecToken", "alibabaConsoleSecToken"]) {
+    const value = toTrimmedString(providerSpecificData?.[key]);
+    if (value) return value;
+  }
+  return process.env.QWEN_CLOUD_SEC_TOKEN?.trim() || "";
+}
+
+function getGatewayHost(site: TokenPlanConsoleSite): string {
+  const configured = process.env.QWEN_TOKEN_PLAN_HOST?.trim();
+  if (!configured) return site.gatewayHost;
+  return /^https?:\/\//i.test(configured) ? configured : `https://${configured}`;
+}
+
+function getDashboardUrl(site: TokenPlanConsoleSite): string {
+  return process.env.QWEN_TOKEN_PLAN_DASHBOARD_URL?.trim() || site.dashboardUrl;
+}
+
+/** Extract the console `SEC_TOKEN: "…"` embedded in the logged-in dashboard HTML. */
+export function extractQwenSecToken(html: string): string | null {
+  const match = /SEC_?TOKEN["']?\s*[:=]\s*["']([^"']+)["']/i.exec(html);
+  return match ? match[1] : null;
+}
+
+async function resolveSecToken(
+  connectionId: string,
+  cookie: string,
+  site: TokenPlanConsoleSite
+): Promise<string> {
+  const cached = secTokenCache.get(connectionId);
+  if (cached && Date.now() - cached.fetchedAt < TIER_CACHE_TTL_MS) {
+    return cached.token;
+  }
+
+  try {
+    const response = await fetch(getDashboardUrl(site), {
+      method: "GET",
+      headers: {
+        Cookie: cookie,
+        "User-Agent":
+          "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/126.0 Safari/537.36",
+        Accept: "text/html",
+      },
+      redirect: "follow",
+      signal: AbortSignal.timeout(8_000),
+    });
+    const html = await response.text();
+    const token = extractQwenSecToken(html);
+    if (token) {
+      secTokenCache.set(connectionId, { token, fetchedAt: Date.now() });
+      return token;
+    }
+  } catch {
+    // best-effort — some accounts work without sec_token
+  }
+  return "";
+}
+
+// ─── Gateway transport ───────────────────────────────────────────────────────
+
+async function callGateway(
+  endpoint: string,
+  cookie: string,
+  secToken: string,
+  site: TokenPlanConsoleSite
+): Promise<unknown | null> {
+  const api = `${TOKEN_PLAN_API_PREFIX}${endpoint}`;
+  const url = `${getGatewayHost(site)}/data/api.json?product=${GATEWAY_PRODUCT}&action=${GATEWAY_ACTION}&api=${encodeURIComponent(api)}`;
+
+  const params = JSON.stringify({
+    Api: api,
+    V: "1.0",
+    Data: {
+      commodityCode: COMMODITY_CODE,
+      cornerstoneParam: {
+        console: "ONE_CONSOLE",
+        consoleSite: site.consoleSite,
+        domain: site.domain,
+        productCode: "p_efm",
+        protocol: "V2",
+        xsp_lang: "en-US",
+      },
+    },
+  });
+
+  const body = new URLSearchParams({
+    product: GATEWAY_PRODUCT,
+    action: GATEWAY_ACTION,
+    sec_token: secToken,
+    region: GATEWAY_REGION,
+    params,
+  });
+
+  try {
+    // #6911: space concurrent upstream quota fetches (mirrors bailianQuotaFetcher.ts).
+    await throttleQuotaFetch();
+    const response = await fetch(url, {
+      method: "POST",
+      headers: {
+        Cookie: cookie,
+        "Content-Type": "application/x-www-form-urlencoded",
+        Accept: "application/json",
+        Origin: site.origin,
+        Referer: `${site.origin}/`,
+      },
+      body: body.toString(),
+      signal: AbortSignal.timeout(8_000),
+    });
+
+    const raw = await response.json();
+    return parseGatewayEnvelope(raw);
+  } catch {
+    // Network error, timeout, non-JSON (login redirect page) — fail open
+    return null;
+  }
+}
+
+/** Unwrap {code:"200", data:{DataV2:{data:{code:"SUCCESS", data:<payload>}}}} → payload. */
+function parseGatewayEnvelope(raw: unknown): unknown | null {
+  const obj = toRecord(raw);
+  if (obj["code"] !== "200" && obj["code"] !== 200) return null;
+  const inner = toRecord(toRecord(toRecord(obj["data"])["DataV2"])["data"]);
+  if (inner["code"] !== "SUCCESS" || inner["success"] !== true) return null;
+  return inner["data"] ?? null;
+}
+
+// ─── Parsers ─────────────────────────────────────────────────────────────────
+
+function parseUsageWindows(
+  payload: unknown
+): Record<string, { percentUsed: number; resetAt: string | null }> {
+  const obj = toRecord(payload);
+  const windows: Record<string, { percentUsed: number; resetAt: string | null }> = {};
+
+  for (const [fieldPrefix, windowKey] of Object.entries(WINDOW_FIELD_MAP)) {
+    const percent = toNumberOrNull(obj[`per${fieldPrefix}Percentage`]);
+    if (percent === null) continue; // window omitted (e.g. 5-hour "Temporarily Removed")
+    const resetMs = toNumberOrNull(obj[`per${fieldPrefix}ResetTime`]);
+    windows[windowKey] = {
+      percentUsed: percent,
+      resetAt: resetMs && resetMs > 0 ? new Date(resetMs).toISOString() : null,
+    };
+  }
+
+  return windows;
+}
+
+async function resolveTierInfo(
+  connectionId: string,
+  cookie: string,
+  secToken: string,
+  site: TokenPlanConsoleSite
+): Promise<TierCacheEntry> {
+  const cached = tierCache.get(connectionId);
+  if (cached && Date.now() - cached.fetchedAt < TIER_CACHE_TTL_MS) {
+    return cached;
+  }
+
+  const [quotaConfig, subscription] = await Promise.all([
+    callGateway("quota-config", cookie, secToken, site),
+    callGateway("subscription", cookie, secToken, site),
+  ]);
+
+  const specCode = toTrimmedString(toRecord(subscription)["specCode"]) || null;
+  const tierRecord = specCode ? toRecord(toRecord(quotaConfig)[specCode]) : {};
+  const entry: TierCacheEntry = {
+    specCode,
+    tierLimits: {
+      fiveHour: toNumberOrNull(tierRecord["five_hour"]),
+      weekly: toNumberOrNull(tierRecord["weekly"]),
+    },
+    fetchedAt: Date.now(),
+  };
+
+  tierCache.set(connectionId, entry);
+  return entry;
+}
+
+// ─── Core fetcher ────────────────────────────────────────────────────────────
+
+/**
+ * Fetch the personal Token Plan quota for a qwen-cloud-token-plan connection.
+ * Returns percentUsed = max across the windows present in the usage response,
+ * or null when no cookie is configured / the console session expired.
+ */
+export async function fetchQwenTokenPlanQuota(
+  connectionId: string,
+  connection?: Record<string, unknown>
+): Promise<QuotaInfo | null> {
+  const cached = usageCache.get(connectionId);
+  if (cached && Date.now() - cached.fetchedAt < USAGE_CACHE_TTL_MS) {
+    return cached.quota;
+  }
+
+  const providerSpecificData =
+    connection?.providerSpecificData &&
+    typeof connection.providerSpecificData === "object" &&
+    !Array.isArray(connection.providerSpecificData)
+      ? (connection.providerSpecificData as Record<string, unknown>)
+      : undefined;
+
+  const cookie = getCookie(providerSpecificData);
+  if (!cookie) return null;
+
+  const site = resolveConsoleSite(
+    cookie,
+    typeof connection?.provider === "string" ? connection.provider : undefined
+  );
+
+  const secToken =
+    getConfiguredSecToken(providerSpecificData) ||
+    (await resolveSecToken(connectionId, cookie, site));
+
+  const usagePayload = await callGateway("usage", cookie, secToken, site);
+  if (usagePayload === null) return null;
+
+  const windows = parseUsageWindows(usagePayload);
+  const windowEntries = Object.values(windows);
+  if (windowEntries.length === 0) return null;
+
+  const worst = windowEntries.reduce((max, w) => (w.percentUsed > max.percentUsed ? w : max));
+
+  const tier = await resolveTierInfo(connectionId, cookie, secToken, site);
+  const total = tier.tierLimits.weekly ?? 100;
+
+  const quota: QwenTokenPlanQuota = {
+    used: Math.round(worst.percentUsed * total),
+    total,
+    percentUsed: worst.percentUsed,
+    resetAt: worst.resetAt,
+    windows,
+    consoleSite: site.consoleSite,
+    specCode: tier.specCode,
+    tierLimits: tier.tierLimits,
+    limitReached: worst.percentUsed >= 1,
+  };
+
+  usageCache.set(connectionId, { quota, fetchedAt: Date.now() });
+  return quota;
+}
+
+// ─── Invalidation ────────────────────────────────────────────────────────────
+
+export function invalidateQwenTokenPlanQuotaCache(connectionId: string): void {
+  usageCache.delete(connectionId);
+  tierCache.delete(connectionId);
+  secTokenCache.delete(connectionId);
+}
+
+// ─── Registration ────────────────────────────────────────────────────────────
+
+/**
+ * Register the Qwen Token Plan quota fetcher with the preflight and monitor systems.
+ * Call once at server startup (src/sse/handlers/chat.ts), BEFORE registerGenericQuotaFetchers().
+ */
+export function registerQwenTokenPlanQuotaFetcher(): void {
+  registerQuotaFetcher("qwen-cloud-token-plan", fetchQwenTokenPlanQuota);
+  registerMonitorFetcher("qwen-cloud-token-plan", fetchQwenTokenPlanQuota);
+  registerQuotaWindows("qwen-cloud-token-plan", [
+    QWEN_TOKEN_PLAN_WINDOW_5H,
+    QWEN_TOKEN_PLAN_WINDOW_WEEKLY,
+  ]);
+}

open-sse/services/usage.ts

@@ -69,6 +69,7 @@ import { getXaiOauthUsage } from "./usage/xaiOauth.ts";
 import { getGrokCliUsage } from "./usage/grokCli.ts";
 import { getFirecrawlUsage } from "./usage/firecrawl.ts";
 import { getCommandCodeUsage } from "./usage/command-code.ts";
+import { getQwenTokenPlanUsage } from "./usage/qwen-token-plan.ts";
 import { getConolUsage } from "./conolUsage.ts";
 
 type JsonRecord = Record<string, unknown>;
@@ -111,6 +112,7 @@ export const USAGE_FETCHER_PROVIDERS = [
   "minimax-cn",
   "crof",
   "bailian-coding-plan",
+  "qwen-cloud-token-plan",
   "nanogpt",
   "deepseek",
   "opencode",
@@ -202,6 +204,8 @@ export async function getUsageForProvider(
       return await getCrofUsage(apiKey || "");
     case "bailian-coding-plan":
       return await getBailianCodingPlanUsage(id || "", apiKey || "", providerSpecificData);
+    case "qwen-cloud-token-plan":
+      return await getQwenTokenPlanUsage(id || "", apiKey || "", providerSpecificData);
     case "nanogpt":
       return await getNanoGptUsage(apiKey || "");
     case "deepseek":

open-sse/services/usage/bailian.ts

@@ -10,6 +10,7 @@
  */
 
 import { fetchBailianQuota, type BailianTripleWindowQuota } from "../bailianQuotaFetcher.ts";
+import { getQwenTokenPlanUsage } from "./qwen-token-plan.ts";
 
 /**
  * Bailian (Alibaba Token Plan) Usage
@@ -21,11 +22,25 @@ export async function getBailianCodingPlanUsage(
   providerSpecificData?: Record<string, unknown>
 ) {
   try {
+    // The catalog entry is "Alibaba Token Plan" and now points at the Token Plan
+    // endpoint, so prefer the Token Plan quota (console cookie) when one is
+    // configured. The Coding Plan path below stays as the fallback for accounts
+    // that really do hold a Coding Plan key (#9603).
+    const tokenPlanUsage = await getQwenTokenPlanUsage(
+      connectionId,
+      apiKey,
+      providerSpecificData,
+      "bailian-coding-plan"
+    );
+    if ("quotas" in tokenPlanUsage) return tokenPlanUsage;
+
     const connection = { apiKey, providerSpecificData };
     const quota = await fetchBailianQuota(connectionId, connection);
 
     if (!quota) {
-      return { message: "Alibaba Token Plan connected. Unable to fetch quota." };
+      // Neither surface answered — surface the Token Plan guidance, which tells the
+      // operator how to supply the cookie the console gateway requires.
+      return tokenPlanUsage;
     }
 
     const bailianQuota = quota as BailianTripleWindowQuota;

open-sse/services/usage/qwen-token-plan.ts

@@ -0,0 +1,96 @@
+/**
+ * usage/qwen-token-plan.ts — Qwen Cloud / Alibaba Model Studio personal Token Plan
+ * usage leaf (issue #9603).
+ *
+ * Delegates to qwenTokenPlanQuotaFetcher (cookie-authenticated console gateway) and
+ * shapes the 5-hour / weekly sliding windows into the standard usage response. The
+ * inference API key cannot read this quota — the connection needs a console session
+ * cookie in providerSpecificData (qwenCloudCookie / alibabaConsoleCookie / cookie)
+ * or the QWEN_CLOUD_COOKIE env var.
+ */
+
+import {
+  fetchQwenTokenPlanQuota,
+  QWEN_TOKEN_PLAN_WINDOW_5H,
+  QWEN_TOKEN_PLAN_WINDOW_WEEKLY,
+  type QwenTokenPlanQuota,
+} from "../qwenTokenPlanQuotaFetcher.ts";
+import type { UsageQuota } from "./quota.ts";
+
+function windowToQuota(
+  window: { percentUsed: number; resetAt: string | null } | undefined,
+  totalCredits: number | null,
+  displayName: string
+): UsageQuota | null {
+  if (!window) return null;
+  const total = totalCredits ?? 100;
+  const used = Math.round(window.percentUsed * total);
+  const remaining = Math.max(0, total - used);
+  return {
+    used,
+    total,
+    remaining,
+    remainingPercentage: Math.round((1 - window.percentUsed) * 1000) / 10,
+    resetAt: window.resetAt,
+    unlimited: false,
+    displayName,
+  };
+}
+
+/**
+ * Qwen Cloud personal Token Plan usage (5-hour + weekly sliding windows).
+ */
+export async function getQwenTokenPlanUsage(
+  connectionId: string,
+  apiKey: string,
+  providerSpecificData?: Record<string, unknown>,
+  provider = "qwen-cloud-token-plan"
+) {
+  try {
+    const quota = await fetchQwenTokenPlanQuota(connectionId, {
+      apiKey,
+      providerSpecificData,
+      provider,
+    });
+
+    if (!quota) {
+      return {
+        message:
+          "Qwen Token Plan connected. Quota needs a console session cookie — the inference " +
+          "API key cannot read it. Get it at home.qwencloud.com › Billing › Subscription " +
+          "(logged in): F12 › Network, reload, filter by api.json, click a request to " +
+          "cs-data.qwencloud.com and copy the whole Cookie value from Request Headers " +
+          "(it contains login_qwencloud_ticket). Paste it into the connection's " +
+          "'Qwen / Model Studio console cookie' field, or set QWEN_CLOUD_COOKIE. " +
+          "The cookie expires with the browser session — re-paste it when this message returns.",
+      };
+    }
+
+    const tokenPlanQuota = quota as QwenTokenPlanQuota;
+    const quotas: Record<string, UsageQuota> = {};
+
+    const fiveHour = windowToQuota(
+      tokenPlanQuota.windows[QWEN_TOKEN_PLAN_WINDOW_5H],
+      tokenPlanQuota.tierLimits.fiveHour,
+      "5-hour window"
+    );
+    if (fiveHour) quotas.five_hour = fiveHour;
+
+    const weekly = windowToQuota(
+      tokenPlanQuota.windows[QWEN_TOKEN_PLAN_WINDOW_WEEKLY],
+      tokenPlanQuota.tierLimits.weekly,
+      "Weekly window"
+    );
+    if (weekly) quotas.weekly = weekly;
+
+    const specCode = tokenPlanQuota.specCode;
+    const brand = tokenPlanQuota.consoleSite === "ALIYUN" ? "Alibaba" : "Qwen";
+    const plan = specCode
+      ? `${brand} Token Plan (${specCode.charAt(0).toUpperCase()}${specCode.slice(1)})`
+      : `${brand} Token Plan`;
+
+    return { plan, quotas };
+  } catch (error) {
+    return { message: `Qwen Token Plan error: ${(error as Error).message}` };
+  }
+}

scripts/check/check-docs-counts-sync.mjs

@@ -158,6 +158,7 @@ function readCodeFacts() {
     'import {pluginTools} from "./open-sse/mcp-server/tools/pluginTools.ts";',
     'import {notionTools} from "./open-sse/mcp-server/tools/notionTools.ts";',
     'import {obsidianTools} from "./open-sse/mcp-server/tools/obsidianTools.ts";',
+    'import {localCorpusTools} from "./open-sse/mcp-server/tools/localCorpusTools.ts";',
     'import {compressionTools} from "./open-sse/mcp-server/tools/compressionTools.ts";',
     // Live provider total — the SAME collections gen-provider-reference.ts unions, so the
     // doc-vs-live check below cannot drift from the generator's definition of "provider".
@@ -169,7 +170,7 @@ function readCodeFacts() {
     "const pids=new Set();",
     "for(const c of provCols)for(const p of Object.values(c||{}))if(p&&p.id)pids.add(p.id);",
     "const cols={MCP_TOOLS,memoryTools,skillTools,agentSkillTools,githubSkillTools,poolTools,",
-    "gamificationTools,pluginTools,notionTools,obsidianTools,compressionTools};",
+    "gamificationTools,pluginTools,notionTools,obsidianTools,localCorpusTools,compressionTools};",
     "const sc=new Set();",
     "for(const col of Object.values(cols))for(const t of Object.values(col))",
     "for(const x of (t?.scopes||[]))sc.add(x);",
@@ -452,7 +453,7 @@ export function buildChecks() {
             // total ("33 tools (25 CLI Code's …)") are not the MCP aggregate
             // per-module rows read "… tool definitions (N tools" / "… management tools
             // (N tools" — the word tool(s)/definitions sits right before the paren. The
-            // aggregate ("MCP Server (104 tools", "all 104 tools") never does.
+            // aggregate ("MCP Server (109 tools", "all 109 tools") never does.
             skipBefore: /(tools?|definitions?)\s*\(\s*$/i,
             skipAfter: /^\s*\(\d+ CLI/,
           },

scripts/check/check-migration-numbering.mjs

@@ -43,15 +43,14 @@ export const KNOWN_DUPLICATE_VERSIONS = new Set([
 // ---------------------------------------------------------------------------
 // ALLOWLIST 2 — gaps de sequência CONHECIDOS.
 // Fonte: auditoria do disco (src/lib/db/migrations/). Além dos slots legados,
-// 144–145 seguem reservados pelas migrations Radar que já existem na série
+// As migrations Radar 144–145 e a migration 143 já aterrissaram. O job registry
-// empilhada; a migration 143 já aterrissou. O job registry foi promovido de 139
+// foi promovido de 139 para 146 pela tabela RENAMED_MIGRATION_COMPATIBILITY. A
-// para 146 pela tabela RENAMED_MIGRATION_COMPATIBILITY. A
 // 147–149 estão reservadas por migrations atualmente em trânsito nos PRs #8228,
 // #9313, #10047 e #10066; esta branch usa 150 para evitar essas colisões conhecidas.
 // O stale-enforcement exige que cada reserva seja removida quando os arquivos
 // correspondentes aterrissarem na release.
 // ---------------------------------------------------------------------------
-export const KNOWN_GAPS = new Set(["026", "055", "121", "144", "145", "148", "149"]); // 121: número queimado no ciclo v3.8.47 — 122 (#6909) mergeou antes e 121 nunca aterrissou (validação e2e 2026-07-12)
+export const KNOWN_GAPS = new Set(["026", "055", "121", "148", "149"]); // 121: número queimado no ciclo v3.8.47 — 122 (#6909) mergeou antes e 121 nunca aterrissou (validação e2e 2026-07-12)
 
 function pad3(n) {
   return String(n).padStart(3, "0");

src/app/(dashboard)/dashboard/HomePageClient.tsx

@@ -22,7 +22,6 @@ import { HomeProviderTopologySection } from "./HomeProviderTopologySection";
 import { shouldShowProviderTopologyOnHome } from "./homeAppearance";
 
 const ProviderQuotaWidget = dynamic(() => import("../home/ProviderQuotaWidget"), { ssr: false });
-import type { NewsAnnouncement } from "@/shared/utils/releaseNotes";
 
 type UpdateStep = {
   step: string;
@@ -37,7 +36,6 @@ type VersionInfo = {
   channel: string;
   autoUpdateSupported: boolean;
   autoUpdateError?: string | null;
-  news?: NewsAnnouncement | null;
 };
 
 type HomePageClientProps = {
@@ -1047,37 +1045,6 @@ export default function HomePageClient({ machineId }: HomePageClientProps) {
                 </div>
               )}
           </div>
-
-          {/* News Notification Banner */}
-          {versionInfo?.news && (
-            <div className="flex min-h-[64px] items-center justify-between rounded-lg border border-border bg-surface px-5 py-4">
-              <div className="flex min-w-0 items-center gap-4">
-                <div className="flex size-10 shrink-0 items-center justify-center rounded-lg bg-bg text-text-muted">
-                  <span className="material-symbols-outlined text-[22px] text-primary">
-                    {versionInfo.news.icon || "campaign"}
-                  </span>
-                </div>
-                <div className="min-w-0">
-                  <p className="text-sm font-semibold text-text-main">{versionInfo.news.title}</p>
-                  <p className="mt-0.5 max-w-[560px] text-xs leading-relaxed text-text-muted">
-                    {versionInfo.news.message}
-                  </p>
-                </div>
-              </div>
-
-              {versionInfo.news.link && (
-                <a
-                  href={versionInfo.news.link}
-                  target="_blank"
-                  rel="noopener noreferrer"
-                  className="ml-4 inline-flex shrink-0 items-center gap-1.5 rounded-lg border border-border bg-bg px-4 py-2 text-xs font-semibold text-text-main transition-colors hover:border-primary/30 hover:text-primary"
-                >
-                  {versionInfo.news.linkLabel || t("readMore")}
-                  <span className="material-symbols-outlined text-[14px]">arrow_forward</span>
-                </a>
-              )}
-            </div>
-          )}
         </div>
       )}
 

src/app/(dashboard)/dashboard/NewsBanner.tsx

@@ -0,0 +1,119 @@
+"use client";
+
+import { useEffect, useState, useSyncExternalStore } from "react";
+import { useLocale, useTranslations } from "next-intl";
+
+import {
+  NEWS_DISMISS_EVENT,
+  NEWS_DISMISS_STORAGE_NAME,
+  fetchNewsPayload,
+  parseDismissedNewsIds,
+  selectActiveNews,
+  serializeDismissedNewsIds,
+} from "@/shared/utils/releaseNotes";
+
+function subscribeToDismissals(callback: () => void) {
+  window.addEventListener("storage", callback);
+  window.addEventListener(NEWS_DISMISS_EVENT, callback);
+  return () => {
+    window.removeEventListener("storage", callback);
+    window.removeEventListener(NEWS_DISMISS_EVENT, callback);
+  };
+}
+
+function readDismissedIds(): string {
+  try {
+    return localStorage.getItem(NEWS_DISMISS_STORAGE_NAME) ?? "";
+  } catch {
+    return "";
+  }
+}
+
+function getServerDismissedIds(): string {
+  return "";
+}
+
+/**
+ * Generic, fail-silent reader for the public announcement feed. Fetching the
+ * static JSON is GET-only and does not send product state or telemetry.
+ */
+export default function NewsBanner() {
+  const locale = useLocale();
+  const t = useTranslations("common");
+  const [payload, setPayload] = useState<unknown>(null);
+  const dismissedSnapshot = useSyncExternalStore(
+    subscribeToDismissals,
+    readDismissedIds,
+    getServerDismissedIds
+  );
+  const dismissedIds = parseDismissedNewsIds(dismissedSnapshot);
+  const announcement = selectActiveNews(payload, locale, dismissedIds);
+
+  useEffect(() => {
+    const controller = new AbortController();
+
+    void fetchNewsPayload(fetch, controller.signal).then((value) => {
+      if (value !== null) setPayload(value);
+    });
+
+    return () => controller.abort();
+  }, []);
+
+  if (!announcement) return null;
+
+  const dismiss = () => {
+    dismissedIds.add(announcement.id);
+    try {
+      localStorage.setItem(NEWS_DISMISS_STORAGE_NAME, serializeDismissedNewsIds(dismissedIds));
+    } catch {
+      // Storage is optional; the next announcement fetch remains functional.
+    }
+    window.dispatchEvent(new Event(NEWS_DISMISS_EVENT));
+  };
+
+  return (
+    <div
+      role="complementary"
+      aria-label={announcement.title}
+      className="mb-4 flex flex-col gap-3 rounded-lg border border-primary/30 bg-primary/5 px-4 py-3 sm:flex-row sm:items-center sm:justify-between"
+    >
+      <div className="flex min-w-0 items-start gap-3">
+        <div className="flex size-9 shrink-0 items-center justify-center rounded-lg bg-primary/10">
+          <span className="material-symbols-outlined text-[22px] text-primary" aria-hidden="true">
+            {announcement.icon}
+          </span>
+        </div>
+        <div className="min-w-0">
+          <p className="text-sm font-semibold text-text-main">{announcement.title}</p>
+          <p className="mt-0.5 text-xs leading-relaxed text-text-muted">{announcement.message}</p>
+        </div>
+      </div>
+
+      <div className="flex shrink-0 items-center gap-3 self-end sm:self-auto">
+        {announcement.link && (
+          <a
+            href={announcement.link}
+            target="_blank"
+            rel="noopener noreferrer"
+            className="inline-flex items-center gap-1.5 whitespace-nowrap rounded-lg bg-primary px-3 py-1.5 text-xs font-semibold text-white transition-colors hover:brightness-110"
+          >
+            {announcement.linkLabel ?? announcement.title}
+            <span className="material-symbols-outlined text-[14px]" aria-hidden="true">
+              open_in_new
+            </span>
+          </a>
+        )}
+        <button
+          type="button"
+          onClick={dismiss}
+          aria-label={t("dismissNotification")}
+          className="text-text-muted transition-colors hover:text-text-main"
+        >
+          <span className="material-symbols-outlined text-[18px]" aria-hidden="true">
+            close
+          </span>
+        </button>
+      </div>
+    </div>
+  );
+}

src/app/(dashboard)/dashboard/changelog/components/NewsViewer.tsx

@@ -1,39 +1,39 @@
 "use client";
 
-import { useState, useEffect } from "react";
+import { useEffect, useState } from "react";
-import { useTranslations } from "next-intl";
+import { useLocale, useTranslations } from "next-intl";
+
 import { Button } from "@/shared/components";
 import {
-  NEWS_JSON_URL,
+  fetchNewsPayload,
-  parseActiveNewsPayload,
+  listActiveNews,
   type NewsAnnouncement,
 } from "@/shared/utils/releaseNotes";
 
 export default function NewsViewer() {
+  const locale = useLocale();
   const t = useTranslations("changelogPage");
-  const [news, setNews] = useState<NewsAnnouncement | null>(null);
+  const [news, setNews] = useState<NewsAnnouncement[]>([]);
   const [loading, setLoading] = useState(true);
   const [error, setError] = useState(false);
 
   useEffect(() => {
-    async function fetchNews() {
+    const controller = new AbortController();
-      try {
+
-        const res = await fetch(NEWS_JSON_URL, { cache: "no-store" });
+    void fetchNewsPayload(fetch, controller.signal)
-        if (res.ok) {
+      .then((payload) => {
-          const data = await res.json();
+        if (payload === null) {
-          setNews(parseActiveNewsPayload(data));
+          if (!controller.signal.aborted) setError(true);
-        } else {
+          return;
-          setError(true);
         }
-      } catch (err) {
+        setNews(listActiveNews(payload, locale));
-        console.error("Failed to fetch news:", err);
+      })
-        setError(true);
+      .finally(() => {
-      } finally {
+        if (!controller.signal.aborted) setLoading(false);
-        setLoading(false);
+      });
-      }
+
-    }
+    return () => controller.abort();
-    fetchNews();
+  }, [locale]);
-  }, []);
 
   if (loading) {
     return (
@@ -48,7 +48,7 @@ export default function NewsViewer() {
   if (error) {
     return (
       <div className="flex flex-col items-center justify-center py-20 text-text-muted">
-        <span className="material-symbols-outlined text-[48px] text-red-500/50 mb-4">
+        <span className="material-symbols-outlined mb-4 text-[48px] text-red-500/50">
           error_outline
         </span>
         <p>{t("announcementsLoadFailed")}</p>
@@ -56,10 +56,10 @@ export default function NewsViewer() {
     );
   }
 
-  if (!news || !news.active) {
+  if (news.length === 0) {
     return (
       <div className="flex flex-col items-center justify-center py-20 text-text-muted">
-        <span className="material-symbols-outlined text-[48px] opacity-50 mb-4">
+        <span className="material-symbols-outlined mb-4 text-[48px] opacity-50">
           notifications_off
         </span>
         <p>{t("noAnnouncements")}</p>
@@ -68,30 +68,37 @@ export default function NewsViewer() {
   }
 
   return (
-    <div className="p-8">
+    <div className="space-y-8 p-8">
-      <div className="flex flex-col gap-6 border-l-4 border-primary pl-5 md:flex-row md:items-center md:pl-6">
+      {news.map((announcement) => (
-        <div className="size-14 rounded-lg bg-primary/10 flex items-center justify-center shrink-0">
+        <article
-          <span className="material-symbols-outlined text-[30px] text-primary">
+          key={announcement.id}
-            {news.icon || "campaign"}
+          className="flex flex-col gap-6 border-l-4 border-primary pl-5 md:flex-row md:items-center md:pl-6"
-          </span>
+        >
-        </div>
+          <div className="flex size-14 shrink-0 items-center justify-center rounded-lg bg-primary/10">
-
+            <span className="material-symbols-outlined text-[30px] text-primary">
-        <div className="flex-1">
+              {announcement.icon}
-          <h2 className="text-xl font-bold text-text-main mb-2">{news.title}</h2>
+            </span>
-          <p className="text-sm text-text-muted leading-relaxed max-w-2xl">{news.message}</p>
-        </div>
-
-        {news.link && (
-          <div className="shrink-0 md:ml-auto">
-            <a href={news.link} target="_blank" rel="noopener noreferrer">
-              <Button variant="primary" className="gap-2">
-                {news.linkLabel || t("learnMore")}
-                <span className="material-symbols-outlined text-[18px]">arrow_forward</span>
-              </Button>
-            </a>
           </div>
-        )}
+
-      </div>
+          <div className="flex-1">
+            <h2 className="mb-2 text-xl font-bold text-text-main">{announcement.title}</h2>
+            <p className="max-w-2xl text-sm leading-relaxed text-text-muted">
+              {announcement.message}
+            </p>
+          </div>
+
+          {announcement.link && (
+            <div className="shrink-0 md:ml-auto">
+              <a href={announcement.link} target="_blank" rel="noopener noreferrer">
+                <Button variant="primary" className="gap-2">
+                  {announcement.linkLabel ?? t("learnMore")}
+                  <span className="material-symbols-outlined text-[18px]">arrow_forward</span>
+                </Button>
+              </a>
+            </div>
+          )}
+        </article>
+      ))}
     </div>
   );
 }

src/app/(dashboard)/dashboard/providers/[id]/ProviderDetailPageClient.tsx

@@ -2,7 +2,7 @@
 
 // Issue #3501 strangler-fig decomposition — Phase 1t (final push)
 import { useState, useEffect, useCallback, useMemo } from "react";
-import { useParams } from "next/navigation";
+import { useParams, useSearchParams } from "next/navigation";
 import Link from "next/link";
 import { useTranslations } from "next-intl";
 import { Card, Button, CardSkeleton } from "@/shared/components";
@@ -68,6 +68,7 @@ import AnonymousFallbackToggle from "./components/AnonymousFallbackToggle";
 
 export default function ProviderDetailPageClient() {
   const params = useParams();
+  const searchParams = useSearchParams();
   const providerId = params.id as string;
 
   // ── UI-only modal state (not owned by hooks) ─────────────────────────────
@@ -357,6 +358,10 @@ export default function ProviderDetailPageClient() {
     setShowAddApiKeyModal(true);
   }, [providerId]);
 
+  useEffect(() => {
+    if (searchParams.get("action") === "add-api-key") gateConnectionFlow(openApiKeyAddFlow);
+  }, [searchParams, gateConnectionFlow, openApiKeyAddFlow]);
+
   const openPrimaryAddFlow = useCallback(() => {
     if (providerId === "kimi-coding") return setShowKimiAuthMethodModal(true);
     if (isOAuth) {

src/app/(dashboard)/dashboard/providers/[id]/components/modals/EditConnectionModal.tsx

@@ -340,6 +340,8 @@ export default function EditConnectionModal({
         opencodeGoAuthCookie: "",
         ollamaCloudUsageCookie: "",
         alibabaConsoleCookie: stringField(connection.providerSpecificData?.alibabaConsoleCookie),
+        qwenCloudCookie: stringField(connection.providerSpecificData?.qwenCloudCookie),
+        qwenCloudSecToken: stringField(connection.providerSpecificData?.qwenCloudSecToken),
         alibabaConsoleSecToken: stringField(
           connection.providerSpecificData?.alibabaConsoleSecToken
         ),

src/app/(dashboard)/dashboard/providers/[id]/components/modals/QuotaScrapingFields.tsx

@@ -3,44 +3,16 @@
 import { Input } from "@/shared/components";
 import { providerText, type ProviderMessageTranslator } from "../../providerPageHelpers";
 
-export type QuotaScrapingFieldValues = {
+import {
-  opencodeGoWorkspaceId: string;
+  assignQuotaScrapingProviderData,
-  opencodeGoAuthCookie: string;
+  EMPTY_QUOTA_SCRAPING_FIELDS,
-  ollamaCloudUsageCookie: string;
+  QWEN_TOKEN_PLAN_PROVIDERS,
-  alibabaConsoleCookie: string;
+  type QuotaScrapingFieldValues,
-  alibabaConsoleSecToken: string;
+} from "./quotaScrapingFieldValues";
-};
 
-export const EMPTY_QUOTA_SCRAPING_FIELDS: QuotaScrapingFieldValues = {
+// Re-exported so existing importers (modals, tests) keep their current paths.
-  opencodeGoWorkspaceId: "",
+export { assignQuotaScrapingProviderData, EMPTY_QUOTA_SCRAPING_FIELDS };
-  opencodeGoAuthCookie: "",
+export type { QuotaScrapingFieldValues };
-  ollamaCloudUsageCookie: "",
-  alibabaConsoleCookie: "",
-  alibabaConsoleSecToken: "",
-};
-
-export function assignQuotaScrapingProviderData(
-  provider: string | undefined,
-  values: QuotaScrapingFieldValues,
-  target: Record<string, unknown>
-) {
-  if (provider === "opencode-go") {
-    target.opencodeGoWorkspaceId = values.opencodeGoWorkspaceId.trim() || undefined;
-    if (values.opencodeGoAuthCookie.trim()) {
-      target.opencodeGoAuthCookie = values.opencodeGoAuthCookie.trim();
-    }
-  } else if (provider === "ollama-cloud" && values.ollamaCloudUsageCookie.trim()) {
-    target.ollamaCloudUsageCookie = values.ollamaCloudUsageCookie.trim();
-  } else if (
-    (provider === "alibaba" || provider === "alibaba-cn") &&
-    values.alibabaConsoleCookie.trim()
-  ) {
-    target.alibabaConsoleCookie = values.alibabaConsoleCookie.trim();
-    if (values.alibabaConsoleSecToken.trim()) {
-      target.alibabaConsoleSecToken = values.alibabaConsoleSecToken.trim();
-    }
-  }
-}
 
 type QuotaScrapingFieldsProps = {
   provider?: string;
@@ -170,5 +142,50 @@ export default function QuotaScrapingFields({
     );
   }
 
+  if (QWEN_TOKEN_PLAN_PROVIDERS.has(provider ?? "")) {
+    return (
+      <div className="flex flex-col gap-3 rounded-lg border border-border/50 bg-surface/20 p-4">
+        <Input
+          label={providerText(t, "qwenCloudCookieLabel", "Qwen / Model Studio console cookie")}
+          name="qwenCloudCookie"
+          type="password"
+          value={values.qwenCloudCookie}
+          onChange={(e) => onChange({ qwenCloudCookie: e.target.value })}
+          placeholder="cna=...; login_qwencloud_ticket=...; ..."
+          hint={providerText(
+            t,
+            "qwenCloudCookieHint",
+            (editMode ? "Leave blank to keep the stored cookie. " : "") +
+              "Required for Token Plan quota — the inference API key cannot read it. " +
+              "How to get it: open home.qwencloud.com › Billing › Subscription while logged in, " +
+              "press F12 › Network, reload the page, filter by api.json, click any request to " +
+              "cs-data.qwencloud.com, then under Request Headers copy the WHOLE Cookie value " +
+              "(it contains login_qwencloud_ticket). It expires with the browser session — " +
+              "re-paste it when the quota reports an expired session."
+          )}
+          autoComplete="off"
+          spellCheck={false}
+          autoCapitalize="off"
+        />
+        <Input
+          label={providerText(t, "qwenCloudSecTokenLabel", "Qwen console sec_token (optional)")}
+          name="qwenCloudSecToken"
+          type="password"
+          value={values.qwenCloudSecToken}
+          onChange={(e) => onChange({ qwenCloudSecToken: e.target.value })}
+          placeholder="GjRV..."
+          hint={providerText(
+            t,
+            "qwenCloudSecTokenHint",
+            "Optional — resolved automatically from the dashboard. Set it only if quota sync reports a permission error."
+          )}
+          autoComplete="off"
+          spellCheck={false}
+          autoCapitalize="off"
+        />
+      </div>
+    );
+  }
+
   return null;
 }

src/app/(dashboard)/dashboard/providers/[id]/components/modals/quotaScrapingFieldValues.ts

@@ -0,0 +1,64 @@
+/**
+ * quotaScrapingFieldValues.ts — form-state shape + persistence rules for the
+ * quota-scraping credential fields (cookies / workspace ids) rendered by
+ * QuotaScrapingFields.tsx.
+ *
+ * Kept in a UI-free module on purpose: importing the .tsx pulls in
+ * `@/shared/components`, whose barrel reaches untranspiled ESM deps
+ * (@lobehub/icons) that the node:test runner cannot parse. Unit tests import
+ * this file instead; the component re-exports it for existing callers.
+ */
+
+/** Providers whose quota lives behind the Qwen/Model Studio console gateway (#9603). */
+export const QWEN_TOKEN_PLAN_PROVIDERS = new Set(["qwen-cloud-token-plan", "bailian-coding-plan"]);
+
+export type QuotaScrapingFieldValues = {
+  opencodeGoWorkspaceId: string;
+  opencodeGoAuthCookie: string;
+  ollamaCloudUsageCookie: string;
+  alibabaConsoleCookie: string;
+  alibabaConsoleSecToken: string;
+  qwenCloudCookie: string;
+  qwenCloudSecToken: string;
+};
+
+export const EMPTY_QUOTA_SCRAPING_FIELDS: QuotaScrapingFieldValues = {
+  opencodeGoWorkspaceId: "",
+  opencodeGoAuthCookie: "",
+  ollamaCloudUsageCookie: "",
+  alibabaConsoleCookie: "",
+  alibabaConsoleSecToken: "",
+  qwenCloudCookie: "",
+  qwenCloudSecToken: "",
+};
+
+export function assignQuotaScrapingProviderData(
+  provider: string | undefined,
+  values: QuotaScrapingFieldValues,
+  target: Record<string, unknown>
+) {
+  if (provider === "opencode-go") {
+    target.opencodeGoWorkspaceId = values.opencodeGoWorkspaceId.trim() || undefined;
+    if (values.opencodeGoAuthCookie.trim()) {
+      target.opencodeGoAuthCookie = values.opencodeGoAuthCookie.trim();
+    }
+  } else if (provider === "ollama-cloud" && values.ollamaCloudUsageCookie.trim()) {
+    target.ollamaCloudUsageCookie = values.ollamaCloudUsageCookie.trim();
+  } else if (
+    (provider === "alibaba" || provider === "alibaba-cn") &&
+    values.alibabaConsoleCookie.trim()
+  ) {
+    target.alibabaConsoleCookie = values.alibabaConsoleCookie.trim();
+    if (values.alibabaConsoleSecToken.trim()) {
+      target.alibabaConsoleSecToken = values.alibabaConsoleSecToken.trim();
+    }
+  } else if (QWEN_TOKEN_PLAN_PROVIDERS.has(provider ?? "") && values.qwenCloudCookie?.trim()) {
+    // Optional access: callers (AddApiKeyModal/EditConnectionModal form state, and
+    // existing tests) may pass a partial form object without the newer fields —
+    // bailian-coding-plan previously matched no branch here at all.
+    target.qwenCloudCookie = values.qwenCloudCookie.trim();
+    if (values.qwenCloudSecToken?.trim()) {
+      target.qwenCloudSecToken = values.qwenCloudSecToken.trim();
+    }
+  }
+}

src/app/(dashboard)/dashboard/radar/RadarCatalogTable.tsx

@@ -0,0 +1,381 @@
+"use client";
+
+import { useCallback, useEffect, useMemo, useState } from "react";
+import Link from "next/link";
+import { useTranslations } from "next-intl";
+import { Card } from "@/shared/components";
+
+export interface RadarMergedEntry {
+  provider: string;
+  modelId: string;
+  displayName: string;
+  monthlyTokens: number;
+  creditTokens: number;
+  freeType: string;
+  poolKey: string | null;
+  tos: string;
+  trainsOnPrompts?: boolean;
+  enabled?: boolean;
+  origin: "baseline" | "radar" | "local";
+  disabledBy?: "radar";
+  contextWindow?: number | null;
+  capabilities?: {
+    tools: boolean | null;
+    vision: boolean | null;
+    thinking: boolean | null;
+  };
+  metadataEvidenceUrls?: string[];
+  budget?: { kind: string; tokensPerMonth?: number; poolId?: string };
+  limits?: { rpm: number | null; rpd: number | null; tpm: number | null; tpd: number | null };
+  setup?: { keyUrl: string | null; steps: string[] } | null;
+}
+
+interface RadarLocalModelState {
+  provider: string;
+  modelId: string;
+  displayName: string | null;
+  enabled: boolean | null;
+  tombstoned: boolean;
+  updatedAt: string;
+}
+
+interface RadarCatalogTableProps {
+  entries: RadarMergedEntry[];
+  refreshCatalog: () => Promise<void>;
+  onError: (message: string) => void;
+}
+
+function formatTokens(value: number): string {
+  if (value === 0) return "rate-only";
+  if (value >= 1_000_000) return `${(value / 1_000_000).toFixed(1)}M`;
+  if (value >= 1_000) return `${(value / 1_000).toFixed(0)}K`;
+  return String(value);
+}
+
+function budgetLabel(entry: RadarMergedEntry): string {
+  if (entry.budget?.kind === "shared_pool") {
+    return `shared (${formatTokens(entry.budget.tokensPerMonth ?? entry.monthlyTokens)}/mo)`;
+  }
+  if (entry.budget?.kind === "rate_only" || entry.monthlyTokens === 0) return "rate-only";
+  return `${formatTokens(entry.monthlyTokens)}/mo`;
+}
+
+function capabilityBadge(label: string, value: boolean | null | undefined, trueClass: string) {
+  const state = value === true ? "✓" : value === false ? "✕" : "?";
+  const stateClass =
+    value === true
+      ? trueClass
+      : value === false
+        ? "bg-red-500/10 text-red-400"
+        : "bg-gray-500/10 text-gray-400";
+  return (
+    <span className={`text-[10px] px-1.5 py-0.5 rounded ${stateClass}`}>
+      {label} {state}
+    </span>
+  );
+}
+
+export function RadarCatalogTable({ entries, refreshCatalog, onError }: RadarCatalogTableProps) {
+  const t = useTranslations("radarPage");
+  const [states, setStates] = useState<RadarLocalModelState[]>([]);
+  const [editingKey, setEditingKey] = useState<string | null>(null);
+  const [displayName, setDisplayName] = useState("");
+  const [enabled, setEnabled] = useState(true);
+  const [saving, setSaving] = useState(false);
+
+  const loadState = useCallback(async () => {
+    try {
+      const response = await fetch("/api/radar/local-model-state");
+      if (!response.ok) return;
+      const payload = await response.json();
+      setStates(Array.isArray(payload.states) ? payload.states : []);
+    } catch {
+      onError(t("errorLoading"));
+    }
+  }, [onError, t]);
+
+  useEffect(() => {
+    void loadState();
+  }, [loadState]);
+
+  const stateByKey = useMemo(
+    () => new Map(states.map((state) => [`${state.provider}:${state.modelId}`, state])),
+    [states]
+  );
+  const hiddenModels = useMemo(() => states.filter((state) => state.tombstoned), [states]);
+
+  const applyResponse = useCallback(async (response: Response) => {
+    if (!response.ok) throw new Error("save_failed");
+    const payload = await response.json();
+    setStates(Array.isArray(payload.states) ? payload.states : []);
+  }, []);
+
+  const mutate = useCallback(
+    async (operation: () => Promise<Response>) => {
+      setSaving(true);
+      onError("");
+      try {
+        await applyResponse(await operation());
+        setEditingKey(null);
+        await refreshCatalog();
+      } catch {
+        onError(t("localStateSaveFailed"));
+      } finally {
+        setSaving(false);
+      }
+    },
+    [applyResponse, onError, refreshCatalog, t]
+  );
+
+  const beginEdit = useCallback((entry: RadarMergedEntry) => {
+    setEditingKey(`${entry.provider}:${entry.modelId}`);
+    setDisplayName(entry.displayName);
+    setEnabled(entry.enabled !== false);
+  }, []);
+
+  const saveOverride = useCallback(
+    (entry: RadarMergedEntry) =>
+      mutate(() =>
+        fetch("/api/radar/local-model-state", {
+          method: "PATCH",
+          headers: { "Content-Type": "application/json" },
+          body: JSON.stringify({
+            provider: entry.provider,
+            modelId: entry.modelId,
+            displayName,
+            enabled,
+          }),
+        })
+      ),
+    [displayName, enabled, mutate]
+  );
+
+  const resetOverride = useCallback(
+    (entry: Pick<RadarMergedEntry, "provider" | "modelId">) => {
+      const query = new URLSearchParams({ provider: entry.provider, modelId: entry.modelId });
+      return mutate(() =>
+        fetch(`/api/radar/local-model-state?${query.toString()}`, { method: "DELETE" })
+      );
+    },
+    [mutate]
+  );
+
+  const setTombstone = useCallback(
+    (provider: string, modelId: string, tombstoned: boolean) =>
+      mutate(() =>
+        fetch("/api/radar/local-model-state", {
+          method: "PUT",
+          headers: { "Content-Type": "application/json" },
+          body: JSON.stringify({ provider, modelId, tombstoned }),
+        })
+      ),
+    [mutate]
+  );
+
+  return (
+    <>
+      <Card>
+        <div className="overflow-x-auto">
+          <table className="w-full">
+            <thead>
+              <tr className="text-left text-sm text-text-muted border-b border-border">
+                <th className="pb-3 font-medium">{t("colProvider")}</th>
+                <th className="pb-3 font-medium">{t("colModel")}</th>
+                <th className="pb-3 font-medium">{t("colQuota")}</th>
+                <th className="pb-3 font-medium">{t("colContext")}</th>
+                <th className="pb-3 font-medium">{t("colCapabilities")}</th>
+                <th className="pb-3 font-medium">{t("colTos")}</th>
+                <th className="pb-3 font-medium text-right">{t("colActions")}</th>
+              </tr>
+            </thead>
+            <tbody>
+              {entries.map((entry) => {
+                const key = `${entry.provider}:${entry.modelId}`;
+                const localState = stateByKey.get(key);
+                const hasOverride =
+                  localState && (localState.displayName !== null || localState.enabled !== null);
+                return (
+                  <tr
+                    key={key}
+                    className={`border-b border-border/50 last:border-b-0 ${
+                      entry.enabled === false ? "opacity-50" : ""
+                    }`}
+                  >
+                    <td className="py-3">
+                      <div className="flex items-center gap-2">
+                        <span className="font-medium">{entry.provider}</span>
+                        {entry.origin === "radar" && (
+                          <span className="text-[10px] px-1.5 py-0.5 rounded bg-violet-500/10 text-violet-400 font-medium">
+                            {t("newBadge")}
+                          </span>
+                        )}
+                        {entry.origin === "local" && (
+                          <span className="text-[10px] px-1.5 py-0.5 rounded bg-blue-500/10 text-blue-400 font-medium">
+                            {t("localBadge")}
+                          </span>
+                        )}
+                        {entry.setup?.keyUrl && (
+                          <Link
+                            href={`/dashboard/radar/setup?provider=${encodeURIComponent(entry.provider)}`}
+                            className="text-xs text-violet-400 hover:underline"
+                            title={t("setupGuide")}
+                          >
+                            ⚙
+                          </Link>
+                        )}
+                      </div>
+                      {entry.enabled === false && entry.disabledBy === "radar" && (
+                        <p className="text-xs text-red-400 mt-0.5">{t("disabledByFeed")}</p>
+                      )}
+                    </td>
+                    <td className="py-3 text-text-muted text-sm font-mono max-w-[240px]">
+                      {editingKey === key ? (
+                        <input
+                          type="text"
+                          value={displayName}
+                          onChange={(event) => setDisplayName(event.target.value)}
+                          aria-label={t("modelDisplayName")}
+                          maxLength={160}
+                          className="w-full min-w-[180px] px-2 py-1 rounded border border-border bg-transparent text-text-main focus:outline-none focus:ring-2 focus:ring-violet-500"
+                        />
+                      ) : (
+                        <span className="block truncate">{entry.displayName}</span>
+                      )}
+                    </td>
+                    <td className="py-3 text-sm">{budgetLabel(entry)}</td>
+                    <td className="py-3 text-sm text-text-muted">
+                      {entry.contextWindow ? `${(entry.contextWindow / 1000).toFixed(0)}K` : "—"}
+                    </td>
+                    <td className="py-3">
+                      <div className="flex flex-wrap gap-1">
+                        {capabilityBadge(
+                          t("capTools"),
+                          entry.capabilities?.tools,
+                          "bg-blue-500/10 text-blue-400"
+                        )}
+                        {capabilityBadge(
+                          t("capVision"),
+                          entry.capabilities?.vision,
+                          "bg-purple-500/10 text-purple-400"
+                        )}
+                        {capabilityBadge(
+                          t("capThinking"),
+                          entry.capabilities?.thinking,
+                          "bg-amber-500/10 text-amber-400"
+                        )}
+                      </div>
+                    </td>
+                    <td className="py-3">
+                      <span
+                        className={`text-xs px-2 py-1 rounded ${
+                          entry.tos === "ok"
+                            ? "bg-green-500/10 text-green-400"
+                            : entry.tos === "caution"
+                              ? "bg-yellow-500/10 text-yellow-400"
+                              : entry.tos === "avoid"
+                                ? "bg-red-500/10 text-red-400"
+                                : "bg-gray-500/10 text-gray-400"
+                        }`}
+                      >
+                        {entry.tos}
+                      </span>
+                    </td>
+                    <td className="py-3 pl-3">
+                      {editingKey === key ? (
+                        <div className="flex flex-wrap items-center justify-end gap-2">
+                          <label className="inline-flex items-center gap-1 text-xs text-text-muted">
+                            <input
+                              type="checkbox"
+                              checked={enabled}
+                              disabled={entry.disabledBy === "radar"}
+                              onChange={(event) => setEnabled(event.target.checked)}
+                            />
+                            {t("modelEnabled")}
+                          </label>
+                          <button
+                            type="button"
+                            disabled={saving || displayName.trim().length === 0}
+                            onClick={() => void saveOverride(entry)}
+                            className="text-xs text-violet-400 hover:underline disabled:opacity-50"
+                          >
+                            {t("saveModel")}
+                          </button>
+                          <button
+                            type="button"
+                            disabled={saving}
+                            onClick={() => setEditingKey(null)}
+                            className="text-xs text-text-muted hover:text-text-main disabled:opacity-50"
+                          >
+                            {t("cancelEdit")}
+                          </button>
+                        </div>
+                      ) : (
+                        <div className="flex flex-wrap items-center justify-end gap-2">
+                          <button
+                            type="button"
+                            disabled={saving}
+                            onClick={() => beginEdit(entry)}
+                            className="text-xs text-violet-400 hover:underline disabled:opacity-50"
+                          >
+                            {t("editModel")}
+                          </button>
+                          {hasOverride && (
+                            <button
+                              type="button"
+                              disabled={saving}
+                              onClick={() => void resetOverride(entry)}
+                              className="text-xs text-text-muted hover:text-text-main disabled:opacity-50"
+                            >
+                              {t("resetModel")}
+                            </button>
+                          )}
+                          <button
+                            type="button"
+                            disabled={saving}
+                            onClick={() => void setTombstone(entry.provider, entry.modelId, true)}
+                            className="text-xs text-red-400 hover:underline disabled:opacity-50"
+                          >
+                            {t("hideModel")}
+                          </button>
+                        </div>
+                      )}
+                    </td>
+                  </tr>
+                );
+              })}
+            </tbody>
+          </table>
+        </div>
+      </Card>
+
+      {hiddenModels.length > 0 && (
+        <Card>
+          <div className="flex flex-col gap-3">
+            <h3 className="text-sm font-semibold">{t("hiddenModelsTitle")}</h3>
+            {hiddenModels.map((state) => (
+              <div
+                key={`${state.provider}:${state.modelId}:hidden`}
+                className="flex flex-wrap items-center justify-between gap-3 border-b border-border/50 pb-3 last:border-b-0 last:pb-0"
+              >
+                <div>
+                  <span className="font-medium">{state.provider}</span>
+                  <span className="ml-2 text-sm font-mono text-text-muted">
+                    {state.displayName ?? state.modelId}
+                  </span>
+                </div>
+                <button
+                  type="button"
+                  disabled={saving}
+                  onClick={() => void setTombstone(state.provider, state.modelId, false)}
+                  className="text-sm text-violet-400 hover:underline disabled:opacity-50"
+                >
+                  {t("restoreModel")}
+                </button>
+              </div>
+            ))}
+          </div>
+        </Card>
+      )}
+    </>
+  );
+}

src/app/(dashboard)/dashboard/radar/combos/page.tsx

@@ -0,0 +1,201 @@
+"use client";
+
+import { useCallback, useEffect, useMemo, useState } from "react";
+import { useTranslations } from "next-intl";
+import Link from "next/link";
+import { notFound } from "next/navigation";
+
+import type { ComboBuilderOptionsPayload } from "@/lib/combos/builderOptions";
+import type { MergedEntry } from "@/lib/radar/applyFeed";
+import {
+  buildRadarComboSuggestions,
+  type RadarComboSuggestion,
+} from "@/lib/radar/comboSuggestions";
+import { Card } from "@/shared/components";
+
+interface RadarCatalogPayload {
+  entries?: MergedEntry[];
+  meta?: unknown;
+}
+
+function comboNames(payload: ComboBuilderOptionsPayload): Set<string> {
+  return new Set(payload.comboRefs.map((combo) => combo.name));
+}
+
+export default function RadarCombosPage() {
+  const t = useTranslations("radarCombosPage");
+  const [entries, setEntries] = useState<MergedEntry[]>([]);
+  const [providers, setProviders] = useState<ComboBuilderOptionsPayload["providers"]>([]);
+  const [existingNames, setExistingNames] = useState<Set<string>>(new Set());
+  const [createdNames, setCreatedNames] = useState<Set<string>>(new Set());
+  const [hasCatalog, setHasCatalog] = useState(false);
+  const [flagOff, setFlagOff] = useState(false);
+  const [loading, setLoading] = useState(true);
+  const [creatingName, setCreatingName] = useState<string | null>(null);
+  const [error, setError] = useState("");
+
+  useEffect(() => {
+    async function load() {
+      try {
+        const [catalogResponse, optionsResponse] = await Promise.all([
+          fetch("/api/radar/catalog"),
+          fetch("/api/combos/builder/options"),
+        ]);
+        if (catalogResponse.status === 404) {
+          setFlagOff(true);
+          return;
+        }
+        if (!catalogResponse.ok || !optionsResponse.ok) throw new Error("load_failed");
+
+        const catalog = (await catalogResponse.json()) as RadarCatalogPayload;
+        const options = (await optionsResponse.json()) as ComboBuilderOptionsPayload;
+        if (!Array.isArray(catalog.entries) || !Array.isArray(options.providers)) {
+          throw new Error("invalid_shape");
+        }
+
+        setEntries(catalog.entries);
+        setProviders(options.providers);
+        setExistingNames(comboNames(options));
+        setHasCatalog(catalog.meta != null);
+      } catch {
+        setError(t("loadFailed"));
+      } finally {
+        setLoading(false);
+      }
+    }
+
+    void load();
+  }, [t]);
+
+  const suggestions = useMemo(
+    () => buildRadarComboSuggestions({ entries, providers, existingComboNames: existingNames }),
+    [entries, providers, existingNames]
+  );
+
+  const refreshExistingName = useCallback(async (name: string): Promise<boolean> => {
+    try {
+      const response = await fetch("/api/combos/builder/options");
+      if (!response.ok) return false;
+      const options = (await response.json()) as ComboBuilderOptionsPayload;
+      if (!Array.isArray(options.comboRefs)) return false;
+      const names = comboNames(options);
+      if (![...names].some((candidate) => candidate.toLowerCase() === name.toLowerCase())) {
+        return false;
+      }
+      setExistingNames(names);
+      return true;
+    } catch {
+      return false;
+    }
+  }, []);
+
+  const createSuggestion = useCallback(
+    async (suggestion: RadarComboSuggestion) => {
+      setCreatingName(suggestion.name);
+      setError("");
+      try {
+        const response = await fetch("/api/combos", {
+          method: "POST",
+          headers: { "Content-Type": "application/json" },
+          body: JSON.stringify(suggestion.payload),
+        });
+        if (!response.ok) {
+          if (response.status === 400 && (await refreshExistingName(suggestion.name))) return;
+          throw new Error("create_failed");
+        }
+        setExistingNames((current) => new Set([...current, suggestion.name]));
+        setCreatedNames((current) => new Set([...current, suggestion.name]));
+      } catch {
+        setError(t("createFailed"));
+      } finally {
+        setCreatingName(null);
+      }
+    },
+    [refreshExistingName, t]
+  );
+
+  if (flagOff) notFound();
+
+  return (
+    <div className="flex flex-col gap-6">
+      <div className="flex flex-col gap-3">
+        <Link
+          href="/dashboard/radar"
+          className="text-sm text-text-muted hover:text-text-main transition-colors w-fit"
+        >
+          ← {t("backToRadar")}
+        </Link>
+        <div>
+          <h1 className="text-2xl font-bold">{t("title")}</h1>
+          <p className="text-sm text-text-muted mt-1">{t("subtitle")}</p>
+        </div>
+      </div>
+
+      {error && <div className="p-3 rounded-lg bg-red-500/10 text-red-400 text-sm">{error}</div>}
+
+      {loading ? (
+        <div className="flex items-center justify-center min-h-[200px] text-text-muted">
+          {t("loading")}
+        </div>
+      ) : !hasCatalog ? (
+        <Card>
+          <p className="text-center text-text-muted py-8">{t("catalogRequired")}</p>
+        </Card>
+      ) : suggestions.length === 0 ? (
+        <Card>
+          <p className="text-center text-text-muted py-8">{t("noSuggestions")}</p>
+        </Card>
+      ) : (
+        <div className="grid gap-4">
+          {suggestions.map((suggestion) => {
+            const creating = creatingName === suggestion.name;
+            const created = createdNames.has(suggestion.name);
+            return (
+              <Card key={suggestion.familyId}>
+                <div className="flex flex-col gap-4">
+                  <div className="flex flex-col gap-1">
+                    <span className="text-xs uppercase tracking-wide text-text-muted">
+                      {t("familyLabel")}
+                    </span>
+                    <h2 className="text-lg font-semibold font-mono">{suggestion.familyId}</h2>
+                    <p className="text-sm text-text-muted">{t("strategyReason")}</p>
+                  </div>
+
+                  <div className="flex flex-col gap-2">
+                    <span className="text-sm font-medium">{t("modelsLabel")}</span>
+                    {suggestion.models.map((model) => (
+                      <div
+                        key={`${model.providerId}:${model.modelId}`}
+                        className="flex flex-wrap items-center justify-between gap-2 rounded-lg border border-border px-3 py-2"
+                      >
+                        <span className="font-medium">{model.providerName}</span>
+                        <span className="font-mono text-sm text-text-muted">
+                          {model.qualifiedModel}
+                        </span>
+                      </div>
+                    ))}
+                  </div>
+
+                  <button
+                    type="button"
+                    onClick={() => void createSuggestion(suggestion)}
+                    disabled={creating || suggestion.alreadyExists}
+                    className="self-start px-4 py-2 text-sm font-medium rounded-lg bg-violet-500 text-white hover:bg-violet-600 transition-colors disabled:opacity-50"
+                  >
+                    {created
+                      ? t("created")
+                      : suggestion.alreadyExists
+                        ? t("alreadyCreated")
+                        : creating
+                          ? t("generating")
+                          : t("generateButton")}
+                  </button>
+                </div>
+              </Card>
+            );
+          })}
+        </div>
+      )}
+    </div>
+  );
+}