feat(dashboard): add CheaperInference sponsor banner and route banner links through the shortener

- New CheaperInferenceSponsorBanner on the dashboard home, same size/shape as
  KimiSponsorBanner, no version gate (durable partnership). Uses the
  cheaperinference ProviderIcon and the brand green (#31f889) with the dark
  ink CTA (contrast, per colors.ts token).
- CTA points at https://link.omniroute.online/cheaper — the branded short
  link — so clicks land in our Kutt metrics.
- VscodeCopilotBanner CTA now points at https://link.omniroute.online/vsx
  instead of the raw Marketplace URL, for the same reason.
- i18n strings in en + pt (en is the namespace-level fallback for the other
  41 locales).
- Tests: new cheaperInferenceSponsorBanner.test.tsx (render, CTA href, dismiss
  persistence); vscodeCopilotBanner.test.tsx updated to the new CTA URL.

.env.example

@@ -87,6 +87,10 @@ DISABLE_SQLITE_AUTO_BACKUP=false
 # Used by: src/shared/utils/rateLimiter.ts
 # Example: redis://localhost:6379 (or redis://redis:6379 in Docker)
 # REDIS_URL=redis://localhost:6379
+# Namespace prefix for ALL OmniRoute Redis keys (rate limiter + auth cache +
+# quota store). Prevents key collisions when OmniRoute shares a Redis instance
+# with other apps (e.g. on 127.0.0.1:6379). Default when unset: omniroute:
+# REDIS_KEY_PREFIX=omniroute:
 # Host interface docker-compose publishes the Redis sidecar on.
 # Default: 127.0.0.1 (loopback only). The compose Redis runs WITHOUT
 # `requirepass`, and app containers reach it over the compose network
@@ -372,9 +376,8 @@ ALLOW_API_KEY_REVEAL=false
 # NO_LOG_API_KEY_IDS=key_abc123,key_def456
 
 # Fallback per-day request budget applied to API keys whose `rate_limits`
-# column is null. Default (unset/empty/malformed) preserves the legacy
-# 1000/day, 5000/week, 20000/month windows so existing deployments do not
-# silently lose rate limiting on upgrade.
+# column is null. Default (unset/empty) is unlimited (no implicit caps).
+# Malformed values preserve the legacy 1000/day, 5000/week, 20000/month windows.
 # Set explicitly to "0" to opt out entirely (unlimited fallback). Any
 # positive integer N enables N/day, 5N/week, 20N/month.
 # Used by: src/shared/utils/apiKeyPolicy.ts — checkRateLimit() fallback.

.github/workflows/docker-publish.yml

@@ -183,15 +183,55 @@ jobs:
         env:
           DOCKER_BUILDKIT_INLINE_CACHE: 1
 
+      - name: Build and push BUN base platform image by digest
+        id: build-bun-base
+        uses: docker/build-push-action@53b7df96c91f9c12dcc8a07bcb9ccacbed38856a # v7
+        with:
+          context: .
+          file: Dockerfile.bun
+          target: runner-base
+          platforms: ${{ matrix.platform }}
+          outputs: type=image,push-by-digest=true,name-canonical=true,push=true
+          tags: |
+            ${{ env.IMAGE_NAME }}
+            ${{ env.GHCR_IMAGE_NAME }}
+          cache-from: type=gha,scope=docker-bun-base-${{ matrix.arch }}
+          cache-to: type=gha,scope=docker-bun-base-${{ matrix.arch }},mode=max
+          no-cache: false
+        env:
+          DOCKER_BUILDKIT_INLINE_CACHE: 1
+
+      - name: Build and push BUN web platform image by digest
+        id: build-bun-web
+        uses: docker/build-push-action@53b7df96c91f9c12dcc8a07bcb9ccacbed38856a # v7
+        with:
+          context: .
+          file: Dockerfile.bun
+          target: runner-web
+          platforms: ${{ matrix.platform }}
+          outputs: type=image,push-by-digest=true,name-canonical=true,push=true
+          tags: |
+            ${{ env.IMAGE_NAME }}
+            ${{ env.GHCR_IMAGE_NAME }}
+          cache-from: type=gha,scope=docker-bun-web-${{ matrix.arch }}
+          cache-to: type=gha,scope=docker-bun-web-${{ matrix.arch }},mode=max
+          no-cache: false
+        env:
+          DOCKER_BUILDKIT_INLINE_CACHE: 1
+
       - name: Export digests
         env:
           DIGEST_BASE: ${{ steps.build.outputs.digest }}
           DIGEST_WEB: ${{ steps.build-web.outputs.digest }}
+          DIGEST_BUN_BASE: ${{ steps.build-bun-base.outputs.digest }}
+          DIGEST_BUN_WEB: ${{ steps.build-bun-web.outputs.digest }}
         run: |
           set -euo pipefail
-          mkdir -p /tmp/digests/base /tmp/digests/web
+          mkdir -p /tmp/digests/base /tmp/digests/web /tmp/digests/bun-base /tmp/digests/bun-web
           touch "/tmp/digests/base/${DIGEST_BASE#sha256:}"
           touch "/tmp/digests/web/${DIGEST_WEB#sha256:}"
+          touch "/tmp/digests/bun-base/${DIGEST_BUN_BASE#sha256:}"
+          touch "/tmp/digests/bun-web/${DIGEST_BUN_WEB#sha256:}"
 
       - name: Upload base digests
         uses: actions/upload-artifact@v7
@@ -209,6 +249,22 @@ jobs:
           if-no-files-found: error
           retention-days: 1
 
+      - name: Upload bun-base digests
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
+        with:
+          name: digests-bun-base-${{ matrix.arch }}
+          path: /tmp/digests/bun-base/*
+          if-no-files-found: error
+          retention-days: 1
+
+      - name: Upload bun-web digests
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
+        with:
+          name: digests-bun-web-${{ matrix.arch }}
+          path: /tmp/digests/bun-web/*
+          if-no-files-found: error
+          retention-days: 1
+
   merge:
     name: Publish multi-arch manifests
     needs:
@@ -263,6 +319,20 @@ jobs:
           path: /tmp/digests/web
           merge-multiple: true
 
+      - name: Download bun-base digests
+        uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8
+        with:
+          pattern: digests-bun-base-*
+          path: /tmp/digests/bun-base
+          merge-multiple: true
+
+      - name: Download bun-web digests
+        uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8
+        with:
+          pattern: digests-bun-web-*
+          path: /tmp/digests/bun-web
+          merge-multiple: true
+
       - name: Create Docker Hub manifest
         run: |
           set -euo pipefail
@@ -286,6 +356,8 @@ jobs:
 
           create_manifest "${IMAGE_NAME}" "" /tmp/digests/base
           create_manifest "${IMAGE_NAME}" "-web" /tmp/digests/web
+          create_manifest "${IMAGE_NAME}" "-bun" /tmp/digests/bun-base
+          create_manifest "${IMAGE_NAME}" "-web-bun" /tmp/digests/bun-web
 
       - name: Create GHCR manifest
         run: |
@@ -310,6 +382,8 @@ jobs:
 
           create_manifest "${GHCR_IMAGE_NAME}" "" /tmp/digests/base
           create_manifest "${GHCR_IMAGE_NAME}" "-web" /tmp/digests/web
+          create_manifest "${GHCR_IMAGE_NAME}" "-bun" /tmp/digests/bun-base
+          create_manifest "${GHCR_IMAGE_NAME}" "-web-bun" /tmp/digests/bun-web
 
       - name: Inspect image
         if: needs.prepare.outputs.version != 'main'

AGENTS.md

@@ -56,7 +56,7 @@ Repository map and Reference Documentation sections below.
 | Translators   | `open-sse/translator/`  | Format conversion (OpenAI↔Claude↔Gemini)                                                                                                                                  |
 | Transformer   | `open-sse/transformer/` | Responses API ↔ Chat Completions                                                                                                                                          |
 | Services      | `open-sse/services/`    | Combo routing, rate limits, caching, etc                                                                                                                                  |
-| Database      | `src/lib/db/`           | SQLite domain modules (157 migrations)                                                                                                                                    |
+| Database      | `src/lib/db/`           | SQLite domain modules (159 migrations)                                                                                                                                    |
 | Domain/Policy | `src/domain/`           | Policy engine, cost rules, fallback logic                                                                                                                                 |
 | MCP Server    | `open-sse/mcp-server/`  | 110 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                                                                                                                                               |

Dockerfile.bun

@@ -49,8 +49,8 @@ ENV NODE_ENV=production
 # Bun native Next.js build execution
 RUN bun run --quiet build
 
-# ── Runner stage (100% Bun Native Production Runtime) ──────────────────────
-FROM oven/bun:1.3.14-slim AS runner
+# ── Runner Base stage (100% Bun Native Production Runtime) ──────────────────
+FROM oven/bun:1.3.14-slim AS runner-base
 
 LABEL org.opencontainers.image.title="omniroute" \
   org.opencontainers.image.description="Unified AI proxy — route any LLM through one endpoint (Bun Native)" \
@@ -86,4 +86,61 @@ EXPOSE 20128
 HEALTHCHECK --interval=30s --timeout=5s --start-period=15s --retries=3 \
   CMD bun healthcheck.mjs || exit 1
 
-ENTRYPOINT ["bun", "bin/omniroute.mjs", "serve", "--no-open"]
+ENTRYPOINT ["bun", "dev/run-standalone.mjs"]
+
+# ── Runner Web stage (Bun Native + Chromium/Playwright for Web providers) ───
+FROM runner-base AS runner-web
+
+USER root
+
+RUN apt-get update \
+  && apt-get install -y --no-install-recommends \
+     chromium \
+     chromium-driver \
+     fonts-liberation \
+     libasound2t64 \
+     gconf-service \
+     libatk-bridge2.0-0 \
+     libatk1.0-0 \
+     libc6 \
+     libcairo2 \
+     libcups2 \
+     libdbus-1-3 \
+     libexpat1 \
+     libfontconfig1 \
+     libgbm1 \
+     libgcc-s1 \
+     libglib2.0-0 \
+     libgtk-3-0 \
+     libnspr4 \
+     libnss3 \
+     libpango-1.0-0 \
+     pangocairo-1.0-0 \
+     stdc++6 \
+     libx11-6 \
+     libx11-xcb1 \
+     libxcb1 \
+     libxcomposite1 \
+     libxcursor1 \
+     libxdamage1 \
+     libxext6 \
+     libxfixes3 \
+     libxi6 \
+     libxrandr2 \
+     libxrender1 \
+     libxss1 \
+     libxtst6 \
+     ca-certificates \
+     fonts-gargi \
+     fonts-ipafont-gothic \
+     fonts-kacst \
+     fonts-thai-tlwg \
+     fonts-wqy-zenhei \
+  && rm -rf /var/lib/apt/lists/*
+
+ENV PLAYWRIGHT_SKIP_BROWSER_DOWNLOAD=1
+ENV PLAYWRIGHT_CHROMIUM_EXECUTABLE_PATH=/usr/bin/chromium
+
+# Return to the base image non-root user after the apt install (mirrors the
+# Node Dockerfile runner-web stage, which re-asserts USER node).
+USER bun

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. 348 providers. Never stop building — OmniRoute picks the cheapest one that works. Six pillars: Never hit limits (auto-fallback across 348 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, 57 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 110 tools, A2A, memory, guardrails, evals — 25,000+ tests)."/>
+<img src="./docs/diagrams/promise-pillars.svg" width="100%" alt="The Promise — One endpoint. 348 providers. Never stop building — OmniRoute picks the cheapest one that works. Six pillars: Never hit limits (auto-fallback across 348 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, 56 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 110 tools, A2A, memory, guardrails, evals — 25,000+ tests)."/>
 
 <br/>
 <br/>
@@ -646,7 +646,7 @@ of your shell history. → [CLI Integrations](docs/guides/CLI-INTEGRATIONS.md)
 
 </div>
 
-> The most complete catalog of any open-source router: **348 providers**, **90+ with a free tier**, **57 free forever**.
+> The most complete catalog of any open-source router: **348 providers**, **90+ with a free tier**, **56 free forever**.
 
 <div align="center">
 
@@ -1200,7 +1200,7 @@ Métricas de validação: 1002 vídeos rastreados · 7,069,190 visualizações c
   <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) — 120 domain modules, 157 migrations</td></tr>
+  <tr><td nowrap><b>Database</b></td><td>better-sqlite3 (SQLite, WAL journaling) + LowDB (JSON legacy) — 120 domain modules, 159 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>

bin/cli/commands/combo.mjs

@@ -307,6 +307,12 @@ export async function runComboCreateCommand(name, strategy = "priority", opts =
   }
 
   const models = Array.isArray(opts.models) ? opts.models : [];
+  if (!models.length) {
+    console.error(
+      "combo create requires at least one target. Pass --models <provider/model,...> and/or repeat --model <provider/model>."
+    );
+    return 1;
+  }
 
   try {
     return await withRuntime(async ({ kind, api, db }) => {

bin/cli/commands/oauth.mjs

@@ -228,20 +228,38 @@ async function runSocialFlow(def, opts) {
 
 async function runDeviceFlow(def, opts) {
   const providerKey = resolveBackendKey(def.id);
-  const startRes = await apiFetch(`/api/providers/${providerKey}/auth/start`, {
-    ...targetApiOptions(opts),
-    method: "POST",
-  });
+  let startRes = await apiFetch(`/api/oauth/${providerKey}/device-code`, targetApiOptions(opts));
+  if (!startRes.ok) {
+    startRes = await apiFetch(`/api/providers/${providerKey}/auth/start`, {
+      ...targetApiOptions(opts),
+      method: "POST",
+    });
+  }
   if (!startRes.ok) {
     process.stderr.write(`Failed to start device flow: ${startRes.status}\n`);
     process.exit(1);
   }
   const start = await startRes.json();
-  process.stdout.write(
-    `\nDevice code: ${start.userCode ?? start.user_code ?? ""}\nVisit: ${start.verificationUri ?? start.verification_uri}\n\n`
-  );
-  if (opts.browser !== false)
-    await openBrowser(start.verificationUri ?? start.verification_uri ?? "");
+  const userCode = start.userCode ?? start.user_code ?? "";
+  const verificationUri =
+    start.verificationUriComplete ??
+    start.verification_uri_complete ??
+    start.verificationUri ??
+    start.verification_uri ??
+    start.authUrl ??
+    start.url ??
+    "";
+
+  if (userCode) {
+    process.stdout.write(`\nDevice code: ${userCode}\nVisit: ${verificationUri}\n\n`);
+  } else if (verificationUri) {
+    process.stdout.write(`\nVisit: ${verificationUri}\n\n`);
+  } else {
+    process.stdout.write(`\nAuthorization URL not available\n\n`);
+  }
+
+  if (opts.browser !== false && verificationUri)
+    await openBrowser(verificationUri);
   process.stderr.write("Waiting for device authorization...\n");
   const deadline = Date.now() + (opts.timeout ?? 300000);
   const intervalMs = (start.intervalMs ?? start.interval ?? 5) * 1000;

changelog.d/features/11104-operator-error-rules.md

@@ -0,0 +1 @@
+- **feat(providers):** let operators declare per-provider error rules through `settings.providerErrorRules` instead of patching the catalog — an operator-supplied rule for a provider is consulted before the built-in `providerRuleRegistry`, receives the raw error text, and has its declared scope/cooldown/reason actually honored end to end, for any provider (declaring the rule is the opt-in — no extra allowlist entry needed). Matches are plain case-insensitive substrings (never RegExp) and bounded to 50 rules to keep the hot path safe ([#11104](https://github.com/diegosouzapw/OmniRoute/pull/11104))

changelog.d/features/11190-usage-command-json.md

@@ -0,0 +1 @@
+- **feat(api):** `/api/usage/om-usage` gains a structured form — `?format=json` returns the key's own usage as `ApiKeyUsageLimitStatus` + `UsageSnapshot` instead of `text/plain`. This is the surface a UI (the OmniCopilot panel) consumes to show a key holder their daily/weekly spend and quota reset. The route is self-service (the caller's own key, gated by `allowUsageCommand`), not the management surface; refusals come back as a discriminated `{ "allowed": false, "error": … }` so a UI can tell "not allowed" apart from "allowed but nothing cached yet". The endpoint was previously undocumented in `API_REFERENCE.md`; it now has a section ([#11190](https://github.com/diegosouzapw/OmniRoute/pull/11190))

changelog.d/fixes/11060-perplexity-filter.md

@@ -0,0 +1 @@
+- fix(providers): filter Perplexity model import to the Sonar family so Agent-API catalog ids stop surfacing as routable chat models (#11060)

changelog.d/fixes/11085-claude-code-tool-name-casing.md

@@ -0,0 +1 @@
+- **fix(claude):** restore canonical tool names (`bash` → `Bash`, `croncreate` → `CronCreate`) on non-streaming OpenAI→Claude conversion and through identity-echo alias maps, so Claude Code stops rejecting tool calls with "No such tool available" ([#11085](https://github.com/diegosouzapw/OmniRoute/pull/11085)) — thanks @linhdmn

changelog.d/fixes/11095-termux-onnx.md

@@ -0,0 +1 @@
+- fix(install): make the ONNX dependency chain optional so Termux/Android installs succeed again (#11095)

changelog.d/fixes/11101-reject-silent-validation.md

@@ -0,0 +1 @@
+- **fix(providers):** Reject silent validation degradation on provider connection patch — unknown `rateLimitOverrides` keys (e.g. a typo'd `tpm`) and empty/non-numeric values now return `400` with the rejected key list instead of being silently dropped ([#11101](https://github.com/diegosouzapw/OmniRoute/pull/11101))

changelog.d/fixes/11102-combo-suggestion-count.md

@@ -0,0 +1 @@
+- **Autopilot suggestion counter:** the combo health autopilot summary now reports `suggestionCount` (the real number of suggested actions across all issues) instead of conflating it with link counts, while keeping `actionableCount` as a deprecated alias for backward compatibility. The `run_combo_test` action now links to the dashboard with the combo id (`/dashboard/combos?test=<comboId>`) rather than the read-only API route, so operators can actually trigger a test from the UI ([#11102](https://github.com/diegosouzapw/OmniRoute/pull/11102)).

changelog.d/fixes/11103-persist-config-audit-log.md

@@ -0,0 +1 @@
+- **Config audit persistence:** persist the configuration audit trail to SQLite (`config_audit_log`) instead of an in-memory buffer capped at 1000 volatile entries, and bound its growth with `cleanupConfigAudit()` driven by the `retention.configAudit` setting (default 30 days), wired into `runAutoCleanup` ([#11103](https://github.com/diegosouzapw/OmniRoute/pull/11103)).

changelog.d/fixes/11109-stream-recovery-toolcall.md

@@ -0,0 +1 @@
+- fix(sse): resume mid-stream recovery after a _completed_ tool call — `finish_reason: "tool_calls"` is now tracked per-call instead of as a general terminal marker, so truncation of trailing prose after a fully-delivered tool call is recoverable while in-flight calls stay blocked ([#11109](https://github.com/diegosouzapw/OmniRoute/pull/11109))

changelog.d/fixes/11116-reasoning-effort-capability-discovery.md

@@ -0,0 +1 @@
+- **fix(providers):** `reasoning_effort` now learns the accepted values from a provider's own 400/422 response and clamps to the highest one instead of forwarding an unsupported `xhigh`/`max` (or a hardcoded `"high"` fallback) — fixes custom OpenAI-compatible connections and registered providers with no reasoning metadata ([#11116](https://github.com/diegosouzapw/OmniRoute/pull/11116)) — thanks @maxmad64bis

changelog.d/fixes/11144-responses-parallel-tool-calls-index.md

@@ -0,0 +1 @@
+- **fix(sse):** parallel `function_call` items in a Responses API stream (e.g. several tool calls dispatched in the same turn) now each get a stable, distinct `index`/`id` when translated to Chat Completions streaming deltas, instead of colliding on index 0 and tripping strict stream parsers with `Expected 'id' to be a string.` ([#11144](https://github.com/diegosouzapw/OmniRoute/pull/11144))

changelog.d/fixes/11154-provider-registry-node-net-bundle.md

@@ -0,0 +1 @@
+- fix(dashboard): keep `open-sse/config/providerRegistry.ts` free of `node:net` so the provider detail client bundle builds again — the host classification moved to a platform-free `src/shared/network/privateHost.ts` with a pure-JS `isIP` equivalent, leaving the #11122 routing behaviour unchanged (#11154)

changelog.d/fixes/11162-combo-create-requires-model.md

@@ -0,0 +1 @@
+- **Combo create:** creating a routing combo without any model is now refused (`400`) — the CLI requires `--models`/`--model` on `combo create`, matching the dashboard which already rejected empty combos.

changelog.d/fixes/11165-shared-registry-passthrough-model-lockout.md

@@ -0,0 +1 @@
+- **fix(resilience):** a missing-model `404` on a provider that declares `passthroughModels: true` in the shared registry (novita, uncloseai, orcarouter and 37 others) now locks out only that model instead of cooling the entire connection — `hasPerModelQuota()` previously read only the open-sse registry and the local/self-hosted families ([#11165](https://github.com/diegosouzapw/OmniRoute/pull/11165)) — thanks @yourspraveen

changelog.d/fixes/pending-opencode-empty-rejection-rotation.md

@@ -0,0 +1 @@
+- **fix(executors):** OpencodeExecutor rotates (or retries once on a single-account direct path) on upstream 400 empty-body rejections — malformed completion envelopes with no error field were propagated as success and killed client sessions. Bounded +1 attempt per request; body reads are conditioned on status 400 so successful/streaming responses are never buffered. 400s carrying an error field keep propagating immediately.

changelog.d/fixes/release-v3850-basereds-tests-i18n.md

@@ -0,0 +1 @@
+- fix(i18n): complete Vietnamese translations for recently added UI strings (#9985)

changelog.d/maintenance/11053-stryker-oauth-autoimport-registration.md

@@ -0,0 +1 @@
+- fix(quality): register `tests/unit/authz/oauth-autoimport-local-only.test.ts` in stryker `tap.testFiles` (residual of #11053)

changelog.d/maintenance/11160-drain-v3850-basereds-docs-counts-orphan-test.md

@@ -0,0 +1 @@
+- chore(quality): drain two `release/v3.8.50` base-reds — refresh the drifted doc counts (159 migrations, 56 free-forever providers, 40 free-tier pools, incl. the 42 `llm.txt` locale mirrors) and move `uncloseai-noauth.test.ts` to a collected path so the UncloseAI no-auth regression guard actually runs (#11160)

changelog.d/maintenance/vi-harimport-parity.md

@@ -0,0 +1 @@
+- fix(i18n): translate the 14 `providers.harImport*` keys into Vietnamese (parity gap left by #11069)

config/quality/file-size-baseline.json

@@ -388,6 +388,8 @@
     "open-sse/services/claudeCodeCompatible.ts": 1563,
     "open-sse/services/combo.ts": 4742,
     "open-sse/services/compression/strategySelector.ts": 1379,
+    "open-sse/services/contextManager.ts": 1001,
+    "_rebaseline_2026_08_22_11113_purify_system_first": "PR #11113 (ggdayup) own growth: open-sse/services/contextManager.ts 1000->1001 (+1, purifyHistory merges the compression notice into the leading system message instead of splicing a second one mid-array — live-confirmed TokenRouter 400s; the +1 is the merge-into-leading branch, not extractable). Covered by tests/unit/context-manager-purify-system-first.test.ts. Owner pre-authorized baseline bumps 2026-08-22.",
     "open-sse/services/rateLimitManager.ts": 1517,
     "open-sse/translator/response/openai-responses.ts": 1652,
     "open-sse/utils/cursorAgentProtobuf.ts": 1956,
@@ -443,7 +445,8 @@
       "src/shared/components/ModelSelectModal.tsx": 1138,
       "src/shared/constants/providers/apikey/gateways.ts": 1250
     },
-    "src/app/(dashboard)/dashboard/providers/[id]/components/modals/AddApiKeyModal.tsx": 1080,
+    "src/app/(dashboard)/dashboard/providers/[id]/components/modals/AddApiKeyModal.tsx": 1082,
+    "_rebaseline_2026_08_22_11156_enter_check_disabled": "PR #11156 (rqzbeh) own growth: AddApiKeyModal.tsx 1080->1082 (+2, Enter keydown handler now mirrors the isCheckDisabled condition — owner-requested post-merge polish from #11056; the rest of the diff is Prettier reflow). Covered by tests/unit/ui/add-api-key-modal-enter-key.test.tsx (jsdom render test, Enter dispatch assertions).",
     "src/app/(dashboard)/dashboard/providers/[id]/hooks/useProviderConnections.ts": 1051,
     "src/shared/components/ModelSelectModal.tsx": 1138,
     "src/shared/constants/providers/apikey/gateways.ts": 1298,

config/quality/quality-baseline.json

@@ -197,10 +197,11 @@
       "_rebaseline_2026_08_09_v3850_release_close": "7666 -> 8045 (+379 gzip bytes, +4.9%). Release v3.8.50 close reconciliation measured twice with the real size-limit + @size-limit/file path on tip e0ce95c592. Per-entry measurements remain below their absolute budgets: omniroute.mjs 4380/15000, mcp-server.mjs 1195/5000, nodeRuntimeSupport.mjs 887/8000, reset-password.mjs 1583/6000. The growth accumulated through legitimate CLI/runtime work in this cycle, including global-install ESM alias resolution, Termux cache preparation, and MCP stdio startup hardening; no entrypoint is near its absolute ceiling. The direction:down ratchet stays blocking from this exact measured tip."
     },
     "openapiBreaking": {
-      "value": 0,
+      "value": 4,
       "direction": "down",
       "dedicatedGate": true,
-      "_note": "oasdiff breaking-change gate (Fase 9 Onda 0). Blocks any breaking change vs base spec."
+      "_note": "oasdiff breaking-change gate (Fase 9 Onda 0). Blocks any breaking change vs base spec.",
+      "_rebaseline_2026_08_22_combo_create_min1": "0 -> 4, split 3 own + 1 inherited. Docs-only alignment of components.schemas.ComboCreate with the request contract already enforced by the API since 638fc5fbd (combo create refuses an empty model list) and d5034ea52: `model`/`nodes` were phantom properties the server never accepted, and `models` (array, minItems 1) is the real required field. OWN findings (3, caused by this commit): removed `model`, removed `nodes`, added required `models` on POST /api/combos — spec-vs-server drift, not client-facing breakage, no working client could have relied on the removed shapes. INHERITED finding (1, NOT caused by this PR's code changes — pre-existing drift already present at parent d5034ea52): PATCH /api/combos/{id} request-body-added-required; that route's patch operation declares its own inline requestBody (required: true, bare object schema, docs/openapi.yaml ~2107-2118) and does not reference ComboCreate, so this finding exists independently of the ComboCreate alignment (same own-growth vs inherited-drift convention as _rebaseline_2026_07_20_aliasresolver_hook_split_7808). No code change in this PR; follow-up tracking = this change's PR description."
     },
     "mutationScore.src/sse/services/auth.ts": {
       "value": 52.57,

docs/architecture/RESILIENCE_GUIDE.md

@@ -448,14 +448,14 @@ classification rules pick the fallback `reason` and lock `scope`
 Classification rules only see full error **text** (needed to match body
 markers like `额度不足`) for providers listed in the `FULL_TEXT_RULE_PROVIDERS`
 allowlist in `providerErrorRules.ts` — currently only `"agentrouter"`. For
-every other provider, `checkFallbackError` hands `getProviderErrorRuleMatch`
-only the structured error (`{code, type}`), which is enough for
-header/status/code-based rules but blind to body-text markers. The helper
-`resolveRuleMatchBody()` performs this selection: full error text for
-allowlisted providers, the structured error otherwise. Adding a provider to
-`FULL_TEXT_RULE_PROVIDERS` is an explicit per-provider opt-in — it exists so
-that the default path for every provider not on the list stays
-byte-for-byte unchanged.
+every other **built-in catalog** provider, `checkFallbackError` hands
+`getProviderErrorRuleMatch` only the structured error (`{code, type}`), which
+is enough for header/status/code-based rules but blind to body-text markers.
+The helper `resolveRuleMatchBody()` performs this selection: full error text
+for allowlisted providers, the structured error otherwise. Adding a
+**built-in** provider to `FULL_TEXT_RULE_PROVIDERS` is an explicit per-provider
+opt-in — it exists so 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
@@ -466,6 +466,31 @@ honorsRuleLockScope()` — today only `"agentrouter"`). See "Restated quota
 errors" above for what a `scope: "connection"` match actually does once a
 provider is on that allowlist.
 
+**#11104 — operator-declared rules bypass both allowlists.** An operator can
+declare a per-provider rule at runtime via `settings.providerErrorRules`
+(`open-sse/config/providerErrorRules.ts::setOperatorProviderErrorRules`)
+without editing this file. Gating an operator rule behind
+`FULL_TEXT_RULE_PROVIDERS`/`HONORS_RULE_LOCK_SCOPE_PROVIDERS` — allowlists
+meant to protect the **default** behavior of built-in catalog rules — would
+make the settings mechanism inert for every provider except the ones already
+listed there, since declaring the rule is already the operator's explicit
+opt-in. `resolveRuleMatchBody()` and `honorsRuleLockScope()` both check
+`hasOperatorRuleForProvider()` first: a provider with an operator rule gets
+the raw error text and has its declared `scope` honored, regardless of
+whether it also appears in either allowlist.
+
+**Known gap — `providerRuleRegistry` is never consulted for HTTP 400.**
+`checkFallbackError`'s `BAD_REQUEST` branch classifies status 400 entirely
+through its own pattern arrays (`MODEL_ACCESS_DENIED_PATTERNS`,
+`CONTEXT_OVERFLOW_PATTERNS`, etc. in `accountFallback.ts`) and returns before
+the `configuredRule`/`getProviderErrorRuleMatch` branch above it is reached.
+A built-in catalog rule (or an operator rule) with `status: 400` is
+syntactically valid but will never fire. No existing rule targets 400 today,
+so nothing in production is affected — but a future 400 rule needs this
+branch touched first, which is a larger change than adding a rule (it
+reclassifies 400 for every provider already relying on the pattern-array
+behavior) and is out of scope for a single-provider rule addition.
+
 ### Adding a new quota-misstating gateway
 
 1. Register one rule array in `statusRestatementRegistry`

docs/diagrams/free-tier-budget.svg

@@ -1,4 +1,4 @@
-<svg viewBox="0 0 1200 842" xmlns="http://www.w3.org/2000/svg" role="img" aria-label="OmniRoute free-tier budget: about 1.51 billion free tokens per month steady, up to about 2.13 billion in your first month with signup credits, aggregated from the documented free tiers of 41 provider pools and 495 models behind one endpoint, live on /dashboard/free-tiers. Honest pool-deduped math: each shared free pool is counted once — counting every rate limit 24/7 would read about 10B, which we don't publish; 15 providers carry a ToS flag so you decide. Budget bar of the 19 countable free pools with per-model breakdown: Mistral Large 3 1B, GPT-4o mini 150M, Gemini 2.5 Flash 60M, GLM 4.7 30M, Llama 3.3 70B 30M, Grok-3 24M, DeepSeek V4 Pro 20M, GPT-4.1 18M, Llama 4 Scout 15M, GPT-4o 7M, MiniMax-M2.7 6M, Arcee Trinity 5M, and more. First month adds one-time signup credits of about 626M (vertex 300M, agentrouter 200M, predibase 25M, together 25M, glm-cn 20M, doubao 15M, ai21 10M, longcat 10M, deepseek 5M, hyperbolic 5M, nscale 5M). Plus the un-countable: permanently-free no-token-cap providers (SiliconFlow, Z.AI GLM-Flash, Kilo, OpenCode Zen, baidu and more) and a $10 OpenRouter top-up unlocking +24M per month, surfaced separately so they never inflate the headline. Live used/remaining and per-model breakdown on the dashboard.">
+<svg viewBox="0 0 1200 842" xmlns="http://www.w3.org/2000/svg" role="img" aria-label="OmniRoute free-tier budget: about 1.51 billion free tokens per month steady, up to about 2.13 billion in your first month with signup credits, aggregated from the documented free tiers of 40 provider pools and 495 models behind one endpoint, live on /dashboard/free-tiers. Honest pool-deduped math: each shared free pool is counted once — counting every rate limit 24/7 would read about 10B, which we don't publish; 15 providers carry a ToS flag so you decide. Budget bar of the 19 countable free pools with per-model breakdown: Mistral Large 3 1B, GPT-4o mini 150M, Gemini 2.5 Flash 60M, GLM 4.7 30M, Llama 3.3 70B 30M, Grok-3 24M, DeepSeek V4 Pro 20M, GPT-4.1 18M, Llama 4 Scout 15M, GPT-4o 7M, MiniMax-M2.7 6M, Arcee Trinity 5M, and more. First month adds one-time signup credits of about 626M (vertex 300M, agentrouter 200M, predibase 25M, together 25M, glm-cn 20M, doubao 15M, ai21 10M, longcat 10M, deepseek 5M, hyperbolic 5M, nscale 5M). Plus the un-countable: permanently-free no-token-cap providers (SiliconFlow, Z.AI GLM-Flash, Kilo, OpenCode Zen, baidu and more) and a $10 OpenRouter top-up unlocking +24M per month, surfaced separately so they never inflate the headline. Live used/remaining and per-model breakdown on the dashboard.">
   <defs>
     <pattern id="gridPaperF" width="32" height="32" patternUnits="userSpaceOnUse">
       <path d="M 32 0 L 0 0 0 32" fill="none" stroke="#ffffff" stroke-opacity="0.06" stroke-width="1"/>
@@ -63,7 +63,7 @@
   <text x="60" y="228" font-family="Consolas, 'Courier New', monospace" font-size="104" font-weight="800" fill="url(#gradBrandF)">~1.51B</text>
   <text x="62" y="266" font-family="Consolas, 'Courier New', monospace" font-size="15" letter-spacing="3" font-weight="700" fill="#a1a1aa">FREE TOKENS / MONTH &#183; <tspan fill="#22c55e">STEADY</tspan></text>
   <text x="62" y="298" font-family="Inter, 'Segoe UI', Arial, Helvetica, system-ui, sans-serif" font-size="16" fill="#F7F6FC">up to <tspan font-weight="800" fill="#22c55e">~2.13B</tspan> in your first month &#8212; signup credits</text>
-  <text x="62" y="326" font-family="Consolas, 'Courier New', monospace" font-size="12" fill="#71717a">documented free tiers &#183; <tspan fill="#8b5cf6">41 provider pools</tspan> &#183; <tspan fill="#8b5cf6">495 models</tspan> &#183; one endpoint</text>
+  <text x="62" y="326" font-family="Consolas, 'Courier New', monospace" font-size="12" fill="#71717a">documented free tiers &#183; <tspan fill="#8b5cf6">40 provider pools</tspan> &#183; <tspan fill="#8b5cf6">495 models</tspan> &#183; one endpoint</text>
 
   <!-- ═══ Panel · The honest math ═══ -->
   <rect x="680" y="84" width="460" height="216" rx="14" fill="#161b22" stroke="#ffffff" stroke-opacity="0.08" stroke-width="1"/>

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, 348 providers — never stop building, OmniRoute picks the cheapest one that works. Six pillars. Never hit limits: auto-fallback across 348 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, 57 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 110 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, 348 providers — never stop building, OmniRoute picks the cheapest one that works. Six pillars. Never hit limits: auto-fallback across 348 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, 56 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 110 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">

docs/i18n/ar/llm.txt

@@ -18,7 +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, 157 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 159 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
@@ -438,7 +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 (120 domain-specific files, 157 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 (120 domain-specific files, 159 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.
 

docs/i18n/az/llm.txt

@@ -18,7 +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, 157 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 159 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
@@ -438,7 +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 (120 domain-specific files, 157 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 (120 domain-specific files, 159 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.
 

docs/i18n/bg/llm.txt

@@ -18,7 +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, 157 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 159 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
@@ -438,7 +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 (120 domain-specific files, 157 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 (120 domain-specific files, 159 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.
 

docs/i18n/bn/llm.txt

@@ -18,7 +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, 157 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 159 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
@@ -438,7 +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 (120 domain-specific files, 157 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 (120 domain-specific files, 159 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.
 

docs/i18n/cs/llm.txt

@@ -18,7 +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, 157 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 159 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
@@ -438,7 +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 (120 domain-specific files, 157 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 (120 domain-specific files, 159 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.
 

docs/i18n/da/llm.txt

@@ -18,7 +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, 157 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 159 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
@@ -438,7 +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 (120 domain-specific files, 157 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 (120 domain-specific files, 159 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.
 

docs/i18n/de/llm.txt

@@ -18,7 +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, 157 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 159 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
@@ -438,7 +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 (120 domain-specific files, 157 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 (120 domain-specific files, 159 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.
 

docs/i18n/es/llm.txt

@@ -18,7 +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, 157 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 159 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
@@ -438,7 +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 (120 domain-specific files, 157 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 (120 domain-specific files, 159 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.
 

docs/i18n/fa/llm.txt

@@ -18,7 +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, 157 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 159 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
@@ -438,7 +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 (120 domain-specific files, 157 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 (120 domain-specific files, 159 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.
 

docs/i18n/fi/llm.txt

@@ -18,7 +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, 157 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 159 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
@@ -438,7 +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 (120 domain-specific files, 157 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 (120 domain-specific files, 159 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.
 

docs/i18n/fr/llm.txt

@@ -18,7 +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, 157 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 159 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
@@ -438,7 +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 (120 domain-specific files, 157 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 (120 domain-specific files, 159 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.
 

docs/i18n/gu/llm.txt

@@ -18,7 +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, 157 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 159 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
@@ -438,7 +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 (120 domain-specific files, 157 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 (120 domain-specific files, 159 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.
 

docs/i18n/he/llm.txt

@@ -18,7 +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, 157 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 159 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
@@ -438,7 +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 (120 domain-specific files, 157 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 (120 domain-specific files, 159 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.
 

docs/i18n/hi/llm.txt

@@ -18,7 +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, 157 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 159 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
@@ -438,7 +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 (120 domain-specific files, 157 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 (120 domain-specific files, 159 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.
 

docs/i18n/hu/llm.txt

@@ -18,7 +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, 157 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 159 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
@@ -438,7 +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 (120 domain-specific files, 157 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 (120 domain-specific files, 159 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.
 

docs/i18n/id/llm.txt

@@ -18,7 +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, 157 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 159 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
@@ -438,7 +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 (120 domain-specific files, 157 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 (120 domain-specific files, 159 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.
 

docs/i18n/in/llm.txt

@@ -18,7 +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, 157 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 159 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
@@ -438,7 +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 (120 domain-specific files, 157 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 (120 domain-specific files, 159 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.
 

docs/i18n/it/llm.txt

@@ -18,7 +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, 157 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 159 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
@@ -438,7 +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 (120 domain-specific files, 157 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 (120 domain-specific files, 159 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.
 

docs/i18n/ja/llm.txt

@@ -18,7 +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, 157 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 159 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
@@ -438,7 +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 (120 domain-specific files, 157 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 (120 domain-specific files, 159 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.
 

docs/i18n/ko/llm.txt

@@ -18,7 +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, 157 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 159 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
@@ -438,7 +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 (120 domain-specific files, 157 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 (120 domain-specific files, 159 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.
 

docs/i18n/mr/llm.txt

@@ -18,7 +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, 157 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 159 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
@@ -438,7 +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 (120 domain-specific files, 157 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 (120 domain-specific files, 159 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.
 

docs/i18n/ms/llm.txt

@@ -18,7 +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, 157 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 159 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
@@ -438,7 +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 (120 domain-specific files, 157 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 (120 domain-specific files, 159 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.
 

docs/i18n/nl/llm.txt

@@ -18,7 +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, 157 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 159 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
@@ -438,7 +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 (120 domain-specific files, 157 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 (120 domain-specific files, 159 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.
 

docs/i18n/no/llm.txt

@@ -18,7 +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, 157 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 159 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
@@ -438,7 +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 (120 domain-specific files, 157 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 (120 domain-specific files, 159 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.
 

docs/i18n/phi/llm.txt

@@ -18,7 +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, 157 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 159 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
@@ -438,7 +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 (120 domain-specific files, 157 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 (120 domain-specific files, 159 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.
 

docs/i18n/pl/llm.txt

@@ -18,7 +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, 157 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 159 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
@@ -438,7 +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 (120 domain-specific files, 157 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 (120 domain-specific files, 159 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.
 

docs/i18n/pt-BR/llm.txt

@@ -18,7 +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, 157 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 159 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
@@ -438,7 +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 (120 domain-specific files, 157 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 (120 domain-specific files, 159 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.
 

docs/i18n/pt/llm.txt

@@ -18,7 +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, 157 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 159 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
@@ -438,7 +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 (120 domain-specific files, 157 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 (120 domain-specific files, 159 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.
 

docs/i18n/ro/llm.txt

@@ -18,7 +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, 157 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 159 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
@@ -438,7 +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 (120 domain-specific files, 157 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 (120 domain-specific files, 159 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.
 

docs/i18n/ru/llm.txt

@@ -18,7 +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, 157 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 159 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
@@ -438,7 +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 (120 domain-specific files, 157 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 (120 domain-specific files, 159 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.
 

docs/i18n/sk/llm.txt

@@ -18,7 +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, 157 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 159 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
@@ -438,7 +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 (120 domain-specific files, 157 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 (120 domain-specific files, 159 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.
 

docs/i18n/sv/llm.txt

@@ -18,7 +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, 157 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 159 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
@@ -438,7 +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 (120 domain-specific files, 157 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 (120 domain-specific files, 159 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.
 

docs/i18n/sw/llm.txt

@@ -18,7 +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, 157 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 159 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
@@ -438,7 +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 (120 domain-specific files, 157 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 (120 domain-specific files, 159 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.
 

docs/i18n/ta/llm.txt

@@ -18,7 +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, 157 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 159 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
@@ -438,7 +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 (120 domain-specific files, 157 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 (120 domain-specific files, 159 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.
 

docs/i18n/te/llm.txt

@@ -18,7 +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, 157 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 159 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
@@ -438,7 +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 (120 domain-specific files, 157 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 (120 domain-specific files, 159 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.
 

docs/i18n/th/llm.txt

@@ -18,7 +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, 157 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 159 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
@@ -438,7 +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 (120 domain-specific files, 157 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 (120 domain-specific files, 159 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.
 

docs/i18n/tr/llm.txt

@@ -18,7 +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, 157 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 159 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
@@ -438,7 +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 (120 domain-specific files, 157 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 (120 domain-specific files, 159 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.
 

docs/i18n/uk-UA/llm.txt

@@ -18,7 +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, 157 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 159 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
@@ -438,7 +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 (120 domain-specific files, 157 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 (120 domain-specific files, 159 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.
 

docs/i18n/ur/llm.txt

@@ -18,7 +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, 157 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 159 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
@@ -438,7 +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 (120 domain-specific files, 157 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 (120 domain-specific files, 159 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.
 

docs/i18n/vi/llm.txt

@@ -18,7 +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, 157 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 159 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
@@ -438,7 +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 (120 domain-specific files, 157 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 (120 domain-specific files, 159 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.
 

docs/i18n/zh-CN/llm.txt

@@ -18,7 +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, 157 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 159 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
@@ -438,7 +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 (120 domain-specific files, 157 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 (120 domain-specific files, 159 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.
 

docs/i18n/zh-TW/llm.txt

@@ -18,7 +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, 157 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 159 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
@@ -438,7 +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 (120 domain-specific files, 157 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 (120 domain-specific files, 159 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.
 

docs/openapi.yaml

@@ -8893,12 +8893,20 @@ components:
 
     ComboCreate:
       type: object
-      required: [name, model]
+      required: [name, models]
       properties:
         name:
           type: string
-        model:
-          type: string
+        models:
+          type: array
+          minItems: 1
+          items:
+            oneOf:
+              - type: string
+                description: "provider/model reference"
+              - type: object
+                description: "structured combo step (provider, model, weight, ...)"
+                additionalProperties: true
         strategy:
           type: string
           enum:
@@ -8920,14 +8928,3 @@ components:
             - context-optimized
             - fusion
           default: priority
-        nodes:
-          type: array
-          items:
-            type: object
-            properties:
-              connectionId:
-                type: string
-              weight:
-                type: integer
-              priority:
-                type: integer

docs/ops/REDIS_PRODUCTION_CONFIG.md

@@ -14,9 +14,12 @@ workloads:
 
 | Workload | Driver | Client Factory | Key Pattern |
 |---|---|---|---|
-| Rate limiting | `rateLimiter.ts` | `getRedisClient()` — lazy `ioredis` singleton | Lua‑atomic rate limit windows |
-| Auth cache | `apiKeys.ts` | Reuses `rateLimiter`'s client | `auth:api_key:<sha256>` with TTL |
-| Quota store | `redisQuotaStore.ts` | Separate `getRedisClient(url)` singleton | Configurable per-instance |
+| Rate limiting | `rateLimiter.ts` | `getRedisClient()` — lazy `ioredis` singleton | `<prefix>rl:*` Lua‑atomic rate limit windows |
+| Auth cache | `apiKeys.ts` | Reuses `rateLimiter`'s client | `<prefix>auth:api_key:<sha256>` with TTL |
+| Quota store | `redisQuotaStore.ts` | Separate `getRedisClient(url)` singleton | `<prefix>quota:*` configurable per-instance |
+
+All three workloads share one namespace prefix so OmniRoute can co-exist with other apps on a
+single Redis instance (e.g. `127.0.0.1:6379`). See [Key Namespacing](#key-namespacing).
 
 ---
 
@@ -25,6 +28,7 @@ workloads:
 | Setting | Value | Where |
 |---|---|---|
 | `REDIS_URL` env var | `redis://redis:6379` (compose), optional | `rateLimiter.ts:5`, `.env.example` |
+| `REDIS_KEY_PREFIX` env var | `omniroute:` (default) | `rateLimiter.ts`, `redisQuotaStore.ts`, `.env.example` |
 | `QUOTA_STORE_REDIS_URL` env var | separate, can differ from `REDIS_URL` | `quota/storeFactory.ts` |
 | `QUOTA_STORE_DRIVER` | `"sqlite"` (default), `"redis"` optional | `quota/storeFactory.ts` |
 | ioredis `maxRetriesPerRequest` | `3` | `rateLimiter.ts` client creation |
@@ -36,6 +40,29 @@ workloads:
 
 ---
 
+## Key Namespacing
+
+OmniRoute shares a Redis instance with whatever else runs on the host. Without a namespace,
+keys like `auth:api_key:<sha256>` or `rl:*` could collide with keys from other applications
+using the same Redis (this instance runs Redis on `127.0.0.1:6379` alongside other services).
+
+Set `REDIS_KEY_PREFIX` to a non-empty string to prefix **every** OmniRoute key:
+
+```bash
+# .env — all OmniRoute keys become omniroute:rl:*, omniroute:auth:*, omniroute:quota:*
+REDIS_KEY_PREFIX=omniroute:
+```
+
+- **Default:** `omniroute:` (applied when `REDIS_KEY_PREFIX` is unset or blank).
+- **Applied to:** rate limiter + auth cache (shared `ioredis` client via `keyPrefix`) and the
+  quota store (`KEY_PREFIX = "${REDIS_KEY_PREFIX}quota"`).
+- **Changing the prefix** when keys already exist in Redis orphans the old keys (they expire
+  via TTL / LRU). Safe to change; no migration needed.
+- **ioredis `keyPrefix`** automatically prepends the prefix on writes **and** strips it on reads,
+  so application code never sees the prefix.
+
+---
+
 ## Recommended Production Tuning
 
 ### 1. Connection Pool / Client Options (ioredis `Redis` constructor)

docs/reference/API_REFERENCE.md

@@ -636,6 +636,47 @@ completion.
 
 ---
 
+## Self-service usage (`/api/usage/om-usage`)
+
+Any API key can read **its own** usage and quotas — no management auth. This is the endpoint a
+client (CLI, the OmniCopilot panel) uses to show a key holder their spend.
+
+```bash
+# Text form (the historical contract — plain text for a terminal)
+curl -H "Authorization: Bearer <your-api-key>" \
+  http://localhost:20128/api/usage/om-usage
+
+# Structured form — what a UI consumes
+curl -H "Authorization: Bearer <your-api-key>" \
+  "http://localhost:20128/api/usage/om-usage?format=json"
+```
+
+The key must have **`allowUsageCommand`** enabled (off by default — the dashboard's API-key
+manager toggles it per key). Without it the endpoint answers `403`.
+
+`?format=json` returns a discriminated shape so a caller never reads a data field off a
+refusal. On success:
+
+```jsonc
+{
+  "allowed": true,
+  // present only when the key opted into per-key usage limits (daily/weekly USD):
+  "personal": { "dailySpentUsd": 1.25, "dailyLimitUsd": 5, "dailyResetAtIso": "…", "weeklySpentUsd": 8, "weeklyLimitUsd": 20, "weeklyResetAtIso": "…" /* … */ },
+  // the selected provider quota snapshot, or null when nothing is cached yet:
+  "provider": { "connectionId": "…", "provider": "claude", "plan": "…", "quotas": { /* … */ } }
+}
+```
+
+On refusal (`401` bad key / `403` not allowed) the same route returns
+`{ "allowed": false, "error": { "message": "…" } }` — a present-but-empty `personal`/`provider`
+(key allowed, nothing learned yet) is a different state from a refusal, and only the JSON form
+distinguishes them.
+
+**Auth:** the caller's own Bearer API key, validated with `isValidApiKey` — this is *not* the
+management surface (`/api/keys/…`), which stays behind `requireManagementAuth`.
+
+---
+
 ## Semantic Cache
 
 ```bash

docs/reference/ENVIRONMENT.md

@@ -1343,6 +1343,7 @@ Provider quota endpoints, network tunnels (Tailscale, Ngrok, MITM debug proxy),
 | `OMNIROUTE_REDIS_BIND_HOST`                 | `127.0.0.1`                                                                 | `bin/cli/commands/redis.mjs`                                              | Host interface the 1-click Redis launcher publishes on. The launcher starts Redis WITHOUT a password, so binding `0.0.0.0` hands every host on your LAN an unauthenticated Redis — only widen this if you also set a password on the instance yourself.                                                                                                                |
 | `REDIS_BIND_HOST`                           | `127.0.0.1`                                                                 | `docker-compose.yml`                                                      | Host interface docker-compose publishes the Redis sidecar on (#9286). The compose Redis runs without `requirepass`; app containers reach it over the compose network (`redis:6379`) — the published port exists only for host-side tooling. `0.0.0.0` exposes an unauthenticated Redis to the whole LAN.                                                              |
 | `REDIS_PORT`                                | `6379`                                                                      | `docker-compose.yml`                                                      | Host port for the compose Redis sidecar.                                                                                                                                                                                                                                                                                                                              |
+| `REDIS_KEY_PREFIX`                         | `omniroute:`                                                                | `src/shared/utils/rateLimiter.ts`                                         | Namespace prefix applied to every OmniRoute Redis key (rate limiter, auth cache, quota store). Prevents key collisions when the Redis instance is shared with other apps (#11042).                                                                                                                                                    |
 | `OMNIROUTE_INTERNAL_SERVICE_TOKEN`          | _(unset — mechanism disabled)_                                              | `src/lib/api/internalServiceAuth.ts`                                      | Shared secret for identity-preserving internal REST hops (#9260): OmniRoute components calling other local OmniRoute routes send it as `x-omniroute-internal-service-token` so the original caller identity is preserved. Compared with `timingSafeEqual`.                                                                                                              |
 | `OMNIROUTE_INTERNAL_SERVICE_TOKEN_FILE`     | _(unset)_                                                                   | `src/lib/api/internalServiceAuth.ts`                                      | Secret-file variant of the internal service token: path to a file whose trimmed content is the token. Only consulted when the inline var is unset.                                                                                                                                                                                                                    |
 | `OPENROUTER_PROVIDER_STATS_ENABLED`         | `true`                                                                      | `src/lib/catalog/openrouterProviderStats.ts`                              | Enrich the dashboard providers list with OpenRouter weekly ranking stats (#9324). On by default; set `false` to skip the background fetch entirely (non-blocking, never fatal).                                                                                                                                                                                       |

docs/reference/FREE_TIERS.md

@@ -120,7 +120,6 @@ A 50-agent web-research pass (official docs + last-7-days news, adversarially ve
 | `firecrawl`      | caution   | Cloud API ToS has no explicit personal-proxy prohibition found, but the open-source self-hosted version is AGPL-3.0 (re… |
 | `gemini`         | caution   | ToS explicitly states the free tier is for "developers building with Google AI models for professional or business purp… |
 | `groq`           | caution   | Services Agreement §6.3 prohibits reselling, sublicensing, or distributing API access; §3.2 bars reselling/leasing acco… |
-| `hackclub`       | caution   | Service is explicitly scoped to Hack Club teen members building projects/learning; no public ToS found explicitly permi… |
 | `huggingchat`    | caution   | Hugging Face ToS does not explicitly ban personal self-hosted proxies, but supplemental terms (referenced but not fully… |
 | `huggingface`    | caution   | ToS grants a limited license to access/use the service; the document does not explicitly permit or forbid a single-user… |
 | `hyperbolic`     | caution   | ToS grants API access "solely for your own personal or internal business purposes" and explicitly prohibits licensing, … |
@@ -222,7 +221,6 @@ A 50-agent web-research pass (official docs + last-7-days news, adversarially ve
 | `duckduckgo-web` | keyless       | —                | —                  | avoid     | 6      |
 | `freemodel-dev`  | keyless       | —                | —                  | unknown   | 4      |
 | `friendliai`     | keyless       | —                | —                  | avoid     | 2      |
-| `hackclub`       | keyless       | —                | —                  | caution   | 3      |
 | `iflytek`        | keyless       | —                | —                  | avoid     | 1      |
 | `inference-net`  | keyless       | —                | —                  | caution   | 3      |
 | `liquid`         | keyless       | —                | —                  | unknown   | 1      |
@@ -280,7 +278,6 @@ A 50-agent web-research pass (official docs + last-7-days news, adversarially ve
 - **`gitlawb`** — The shipped freeNote "Free tier available" is effectively stale. The original free MiMo access was removed in May 2026; the only remaining "free" option is a temporary promotional model (Nemotron 3 U…
 - **`gitlawb-gmi`** — Partially still accurate — free tier exists but is now narrowed to a single model (Nemotron 3 Ultra) after MiMo free access was revoked in late May 2026. The shipped note "Free tier available" unders…
 - **`groq`** — The shipped freeNote "30 RPM / 14.4K RPD" is accurate only for llama-3.1-8b-instant. Most other models (including llama-3.3-70b-versatile) have a much lower 1K RPD cap. The note omits model-specific …
-- **`hackclub`** — The "30+ models" count appears accurate and still matches. The core offering remains free for Hack Club members. No evidence of tightening — still "$0 ALWAYS FREE" per the homepage. The freeNote omit…
 - **`huggingchat`** — The shipped freeNote ("Free LLM chat — no subscription required. Rate limits apply.") is partially accurate but significantly understates the restrictions. The free tier now operates on a hard $0.10/…
 - **`huggingface`** — Significantly tightened. The shipped freeNote ("Free Inference API for thousands of models") implied unlimited/generous free access, but as of mid-2025 the free tier is capped at $0.10/month in recur…
 - **`hyperbolic`** — Our shipped freeNote says "$1-5 trial credits on signup" — the $1 trial credit portion is accurate, but the "$5" figure refers to the minimum deposit required to unlock GPU rental (not free credits g…

docs/reference/PROVIDER_REFERENCE.md

@@ -1,14 +1,14 @@
 ---
 title: "Provider Reference"
 version: 3.8.50
-lastUpdated: 2026-08-21
+lastUpdated: 2026-08-22
 ---
 
 # Provider Reference
 
 > **Auto-generated** from `src/shared/constants/providers.ts` — do not edit by hand.
 > Regenerate with: `npm run gen:provider-reference`
-> **Last generated:** 2026-08-21
+> **Last generated:** 2026-08-22
 
 Total providers: **348**. See category breakdown below.
 
@@ -34,7 +34,7 @@ Use the dashboard at `/dashboard/providers` to enable, configure, and test each
 
 ---
 
-## No-auth Providers (no key required) (11)
+## No-auth Providers (no key required) (12)
 
 | ID | Alias | Name | Tags | Website | Notes | Tool calling |
 |----|-------|------|------|---------|-------|--------------|
@@ -47,6 +47,7 @@ Use the dashboard at `/dashboard/providers` to enable, configure, and test each
 | `felo-web` | `felo` | Felo | No-auth | [link](https://felo.ai) | No credentials required — Felo is a free, no-signup chat/search aggregator. | — |
 | `opencode` | `oc` | OpenCode Free | No-auth | [link](https://opencode.ai) | No API key required — uses OpenCode's public free endpoint. | — |
 | `theoldllm` | `tllm` | The Old LLM (Free) | No-auth | [link](https://theoldllm.vercel.app) | No credentials required. The executor auto-generates access tokens via an embedded Playwright browser instance. | — |
+| `uncloseai` | `unc` | UncloseAI | No-auth | [link](https://uncloseai.com) | No auth required. API accepts any non-empty string as key for identification. If older built-in models return 404, use Available Models → Import from /models or Auto-Sync; verified live model: solidrust/Hermes-3-Llama-3.1-8B-AWQ. | — |
 | `veoaifree-web` | `veo-free` | Veo AI Free | No-auth, video | [link](https://veoaifree.com) | No auth required. Rate limited to 6 requests/hour per IP. | — |
 | `zcode` | `zc` | ZCode (GLM Coding Plan) | No-auth | [link](https://zcode.z.ai) | No API key stored by OmniRoute. The local ZCode app-server uses the existing builtin:zai-coding-plan login. | — |
 
@@ -98,7 +99,7 @@ Use the dashboard at `/dashboard/providers` to enable, configure, and test each
 | `gemini-business` | `gembiz` | Gemini Business (Enterprise) | Web cookie | [link](https://business.gemini.google) | From your enterprise account: open business.gemini.google/home/cid/{your-cid}, then copy __Secure-1PSID and __Secure-1PSIDTS cookies from DevTools → Application → Cookies. Paste as a cookie header below. | — |
 | `gemini-web` | `gweb` | Gemini Web (Free) | Web cookie | [link](https://gemini.google.com) | Paste your __Secure-1PSID cookie value from gemini.google.com. Optionally add __Secure-1PSIDTS separated by semicolon. | emulated |
 | `grok-web` | `gw` | Grok Web (Subscription) | Web cookie | [link](https://grok.com) | Paste the full grok.com cookie line from DevTools → Application → Cookies. Include both `sso` and `sso-rw` (e.g. `sso=...; sso-rw=...`) — Grok's anti-bot rejects `sso` on its own. | — |
-| `hailuo-web` | `hailuo-web` | Hailuo Web (MiniMax) | Web cookie | [link](https://hailuo.ai) | Open hailuo.ai, log in, then open DevTools → Application → Local Storage → copy the "_token" value. device_id/uuid fingerprint fields are derived automatically; if requests fail, re-capture _token (sessions can expire). | — |
+| `hailuo-web` | `hailuo-web` | Hailuo Web (MiniMax) | Web cookie | [link](https://chat.minimax.io) | Open hailuo.ai, log in, then open DevTools → Application → Local Storage → copy the "_token" value. device_id/uuid fingerprint fields are derived automatically; if requests fail, re-capture _token (sessions can expire). | — |
 | `huggingchat` | `huggingchat` | HuggingChat (Free) | Web cookie | [link](https://huggingface.co/chat) | Paste the full Cookie header from huggingface.co/chat (DevTools → Network → /chat/conversation → Request Headers → Cookie). It should include hf-chat and may also include token / aws-waf-token. | — |
 | `hyperagent` | `ha` | HyperAgent (Unofficial/Experimental) | Web cookie | [link](https://hyperagent.com) | Paste the full Cookie header from hyperagent.com (DevTools → Network → any request → Request Headers → Cookie). Session cookies power chat + billing usage. | — |
 | `inner-ai` | `in-ai` | Inner.ai (Subscription) | Web cookie | [link](https://app.innerai.com) | Paste your token cookie and email separated by a space: open DevTools → Application → Cookies → .innerai.com, copy the token value, then append a space and your Inner.ai login email. Example: eyJhbG... user@example.com | emulated |
@@ -120,7 +121,7 @@ Use the dashboard at `/dashboard/providers` to enable, configure, and test each
 | `zai-web` | `zw` | Z.ai Web | Web cookie | [link](https://chat.z.ai) | Copy the "token" value from chat.z.ai → DevTools → Application → Local Storage. Do not copy cookies; OmniRoute handles the per-request CAPTCHA through its browser transport. | — |
 | `zenmux-free` | `zmf` | ZenMux Free (Web) | Web cookie | [link](https://zenmux.ai) | Login at zenmux.ai, then export all cookies using EditThisCookie or Cookie-Editor and paste the full Cookie header string here. Refresh every ~30 days. | — |
 
-## API Key Providers (paid / paid-with-free-credits) (232)
+## API Key Providers (paid / paid-with-free-credits) (231)
 
 | ID | Alias | Name | Tags | Website | Notes |
 |----|-------|------|------|---------|-------|
@@ -149,7 +150,7 @@ Use the dashboard at `/dashboard/providers` to enable, configure, and test each
 | `bazaarlink` | `bzl` | BazaarLink | API key | [link](https://bazaarlink.ai) | Use your BazaarLink API key (starts with sk-bl-) in Authorization: Bearer <key>. OpenAI SDK works with base URL https://bazaarlink.ai/api/v1. Models use provider/model-name format. |
 | `bedrock` | `bedrock` | Amazon Bedrock | API key, enterprise | [link](https://aws.amazon.com/bedrock) | Use your Amazon Bedrock API key and configure the AWS region where your models are enabled (for example eu-west-2). OmniRoute calls Bedrock's native Converse API directly. |
 | `black-forest-labs` | `bfl` | Black Forest Labs | API key, image | [link](https://blackforestlabs.ai) | — |
-| `blackbox` | `bb` | Blackbox AI | API key | [link](https://blackbox.ai) | Limited free access is available through Blackbox; model availability and account limits apply |
+| `blackbox` | `bb` | Blackbox AI | API key | [link](https://blackbox.ai) | ⚠️ **DEPRECATED.** api.blackbox.ai returns HTTP 404 on every path variant (sweep 2026-08-21); the public inference surface has moved to the gated enterprise.blackbox.ai/v1 endpoint. |
 | `bluesminds` | `bm` | BluesMinds | API key | [link](https://www.bluesminds.com) | Free daily pi credits — supports 200+ models including GPT-4o, GPT-4.1, Claude Sonnet 4.5, Gemini 2.0 Flash, DeepSeek V4, Qwen, Kimi K2 |
 | `byteplus` | `bpm` | BytePlus ModelArk | API key | [link](https://console.byteplus.com/ark) | — |
 | `bytez` | `bytez` | Bytez | API key | [link](https://bytez.com) | $1 free credits, refreshes every 4 weeks |
@@ -166,7 +167,7 @@ Use the dashboard at `/dashboard/providers` to enable, configure, and test each
 | `clova-studio` | `clova` | Naver CLOVA Studio | API key | [link](https://api.ncloud-docs.com/docs/en/ai-naver-clovastudio-summary) | — |
 | `codestral` | `codestral` | Codestral | API key | [link](https://mistral.ai) | — |
 | `cohere` | `cohere` | Cohere | API key | [link](https://cohere.com) | Free Trial: 1,000 API calls/month for testing, no credit card required |
-| `command-code` | `cmd` | Command Code | API key | [link](https://commandcode.ai/) | Use a Command Code API key. Requests are sent to Command Code's /alpha/generate endpoint. |
+| `command-code` | `cmd` | Command Code | API key | [link](https://commandcode.ai/) | Use a Command Code API key. Requests are sent to Command Code's /provider/v1/chat/completions endpoint. |
 | `coze` | `coze` | Coze | API key | [link](https://coze.com) | Get API key at coze.com/open/api |
 | `crof` | `crof` | CrofAI | API key | [link](https://crof.ai) | — |
 | `cursor-api` | `cua` | Cursor API | API key | [link](https://cursor.com/dashboard/api) | Paste a Cursor user API key (crsr_...) from cursor.com/dashboard/api. OmniRoute exchanges it for a session token on demand; no IDE or cursor-agent install is needed. Usage bills to the Cursor plan that owns the key. |
@@ -213,7 +214,7 @@ Use the dashboard at `/dashboard/providers` to enable, configure, and test each
 | `glm-cn` | `glmcn` | GLM Coding (China) | API key | [link](https://open.bigmodel.cn) | — |
 | `glmt` | `glmt` | GLM Thinking | API key | [link](https://open.bigmodel.cn) | — |
 | `groq` | `groq` | Groq | API key | [link](https://groq.com) | Free tier: 30 RPM / 14.4K RPD — no credit card |
-| `hackclub` | `hc` | Hackclub AI | API key, aggregator | [link](https://ai.hackclub.com) | Sign in with your Hack Club account at ai.hackclub.com. |
+| `hackclub` | `hc` | Hackclub AI | API key | [link](https://ai.hackclub.com) | Sign in with your Hack Club account at ai.hackclub.com. |
 | `haiper` | `hp` | Haiper | API key, video | [link](https://haiper.ai) | Get API key at haiper.ai/haiper-api |
 | `hcnsec` | `hcnsec` | Huancheng Public API | API key | [link](https://api.hcnsec.cn) | Get API key at api.hcnsec.cn |
 | `helixmind` | `helixmind` | HelixMind | API key, aggregator | [link](https://helixmind.online) | Previously circulated 3 RPM/50 RPD and no-card claims were not confirmed during the 2026-08-02 audit; current quota and billing require account verification. |
@@ -331,7 +332,6 @@ Use the dashboard at `/dashboard/providers` to enable, configure, and test each
 | `topaz` | `topaz` | Topaz | API key, image | [link](https://topazlabs.com) | — |
 | `typhoon` | `typhoon` | Typhoon | API key | [link](https://docs.opentyphoon.ai) | Free API key with a 5 req/s and 200 req/m rate limit. |
 | `udio` | `udio` | Udio | API key | [link](https://udio.com) | Paste session cookie from udio.com (Supabase auth) |
-| `uncloseai` | `unc` | UncloseAI | API key | [link](https://uncloseai.com) | No auth required. API accepts any non-empty string as key for identification. If older built-in models return 404, use Available Models → Import from /models or Auto-Sync; verified live model: solidrust/Hermes-3-Llama-3.1-8B-AWQ. |
 | `unorouter` | `unorouter` | UnoRouter | API key, aggregator | [link](https://unorouter.ai) | Models with the :free suffix do not debit balance; limit is 1 request/minute per free model per user. |
 | `upstage` | `upstage` | Upstage | API key | [link](https://www.upstage.ai) | — |
 | `v0-vercel` | `v0` | v0 (Vercel) | API key | [link](https://v0.dev) | — |

llm.txt

@@ -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, 157 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 159 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
@@ -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 (120 domain-specific files, 157 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 (120 domain-specific files, 159 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.
 

open-sse/config/constants.ts

@@ -171,6 +171,7 @@ export const HTTP_STATUS = {
   FORBIDDEN: 403,
   NOT_FOUND: 404,
   NOT_ACCEPTABLE: 406,
+  UNPROCESSABLE_ENTITY: 422,
   REQUEST_TIMEOUT: 408,
   GONE: 410,
   RATE_LIMITED: 429,
@@ -263,11 +264,17 @@ export const PROVIDER_PROFILES = {
     circuitBreakerReset: envInt("OMNIROUTE_CIRCUIT_BREAKER_API_KEY_RESET_MS", 30000),
     // Provider-level circuit breaker (entire provider cooldown after repeated failures)
     providerFailureThreshold: envInt("OMNIROUTE_PROVIDER_BREAKER_API_KEY_FAILURE_THRESHOLD", 15), // Scaled for 500+ connections (was 5)
-    providerFailureWindowMs: envInt("OMNIROUTE_PROVIDER_BREAKER_API_KEY_FAILURE_WINDOW_MS", 1800000), // 30min window (was 20min)
+    providerFailureWindowMs: envInt(
+      "OMNIROUTE_PROVIDER_BREAKER_API_KEY_FAILURE_WINDOW_MS",
+      1800000
+    ), // 30min window (was 20min)
     providerCooldownMs: envInt("OMNIROUTE_PROVIDER_BREAKER_API_KEY_COOLDOWN_MS", 600000), // 10min cooldown when threshold reached
     degradationThreshold: envInt("OMNIROUTE_PROVIDER_BREAKER_API_KEY_DEGRADATION_THRESHOLD", 7),
     maxBackoffMultiplier: envInt("OMNIROUTE_PROVIDER_BREAKER_API_KEY_MAX_BACKOFF_MULTIPLIER", 4),
-    backoffEscalationCount: envInt("OMNIROUTE_PROVIDER_BREAKER_API_KEY_BACKOFF_ESCALATION_COUNT", 3),
+    backoffEscalationCount: envInt(
+      "OMNIROUTE_PROVIDER_BREAKER_API_KEY_BACKOFF_ESCALATION_COUNT",
+      3
+    ),
   },
   // Local providers (localhost inference backends like Ollama, LM Studio, oMLX).
   // Not yet wired into getProviderProfile() — will be used when local provider_nodes
@@ -348,6 +355,23 @@ export const STREAM_RECOVERY = {
   HOLDBACK_MS: 750,
   BUFFER_MAX_BYTES: 65536,
   EARLY_RETRY_MAX: 4,
+  /**
+   * Minimum character overlap `trimContinuationOverlap` must find between the
+   * already-emitted text and a mid-stream continuation for the continuation to be
+   * accepted as a real resume, rather than an unrelated restart the model produced after
+   * ignoring the assistant-prefill.
+   *
+   * This is a DOCUMENTED TRADE-OFF, not a solved distinction: a model that continues
+   * cleanly with fewer than this many echoed characters (a legitimate, even preferred,
+   * outcome — there was nothing to de-duplicate) is indistinguishable, from string data
+   * alone, from a model that silently restarted on an unrelated sentence. Both produce a
+   * low/zero overlap. Rejecting below this threshold trades some false-positive rejections
+   * of legitimate low-overlap continuations (bounded retry, then a clean close — no data
+   * loss beyond that retry) against not silently gluing two unrelated fragments into one
+   * corrupted, unrecoverable answer. It does not eliminate the residual false negative
+   * either (an accidental coincidence at or above this many characters is still accepted).
+   */
+  MIN_CONTINUATION_OVERLAP_CHARS: 8,
 } as const;
 
 /**

open-sse/config/freeModelCatalog.data.ts

@@ -194,9 +194,6 @@ export const FREE_MODEL_BUDGETS: FreeModelBudget[] = [
   { provider: "groq", modelId: "openai/gpt-oss-120b", displayName: "GPT-OSS 120B", monthlyTokens: 15000000, creditTokens: 0, freeType: "recurring-daily", poolKey: "groq", tos: "caution", hardStopGuaranteed: true },
   { provider: "groq", modelId: "openai/gpt-oss-20b", displayName: "GPT-OSS 20B", monthlyTokens: 15000000, creditTokens: 0, freeType: "recurring-daily", poolKey: "groq", tos: "caution", hardStopGuaranteed: true },
   { provider: "groq", modelId: "qwen/qwen3-32b", displayName: "Qwen3 32B", monthlyTokens: 15000000, creditTokens: 0, freeType: "recurring-daily", poolKey: "groq", tos: "caution", hardStopGuaranteed: true },
-  { provider: "hackclub", modelId: "meta-llama/llama-3.3-70b-instruct", displayName: "Llama 3.3 70B", monthlyTokens: 0, creditTokens: 0, freeType: "keyless", poolKey: "hackclub", tos: "caution" },
-  { provider: "hackclub", modelId: "mistralai/mistral-7b-instruct", displayName: "Mistral 7B", monthlyTokens: 0, creditTokens: 0, freeType: "keyless", poolKey: "hackclub", tos: "caution" },
-  { provider: "hackclub", modelId: "deepseek-ai/deepseek-coder-33b", displayName: "DeepSeek Coder 33B", monthlyTokens: 0, creditTokens: 0, freeType: "keyless", poolKey: "hackclub", tos: "caution" },
   { provider: "huggingchat", modelId: "baidu/ERNIE-4.5-VL-424B-A47B-Base-PT", displayName: "ERNIE 4.5 VL 424B A47B Base PT", monthlyTokens: 500000, creditTokens: 0, freeType: "recurring-monthly", poolKey: "huggingchat", tos: "caution" },
   { provider: "huggingchat", modelId: "CohereLabs/c4ai-command-r7b-12-2024", displayName: "Command R7B 12-2024", monthlyTokens: 500000, creditTokens: 0, freeType: "recurring-monthly", poolKey: "huggingchat", tos: "caution" },
   { provider: "huggingchat", modelId: "CohereLabs/command-a-reasoning-08-2025", displayName: "Command A Reasoning 08-2025", monthlyTokens: 500000, creditTokens: 0, freeType: "recurring-monthly", poolKey: "huggingchat", tos: "caution" },

open-sse/config/providerErrorRules.ts

@@ -30,21 +30,63 @@ export type ProviderErrorRule = {
 export type ProviderErrorRuleMatch = {
   reason: ConfiguredErrorReason;
   /**
-   * Intended lock scope. #10334: this field is CONSUMED end-to-end only for
-   * providers in `HONORS_RULE_LOCK_SCOPE_PROVIDERS` (agentrouter-exclusive
-   * today, gated by `honorsRuleLockScope()`) — for those, `checkFallbackError`
-   * surfaces it as `ruleScope` on its return value for the persistence layer
-   * to honor instead of re-deriving scope from `hasPerModelQuota()`. For
-   * every other provider it remains INFORMATIONAL: `getProviderErrorRuleMatch`
-   * 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.
+   * Intended lock scope. #10334: for a BUILT-IN catalog rule, this field is
+   * CONSUMED end-to-end only for providers in `HONORS_RULE_LOCK_SCOPE_PROVIDERS`
+   * (agentrouter-exclusive today, gated by `honorsRuleLockScope()`) — for those,
+   * `checkFallbackError` surfaces it as `ruleScope` on its return value for the
+   * persistence layer to honor instead of re-deriving scope from
+   * `hasPerModelQuota()`. For every other built-in-rule provider it remains
+   * INFORMATIONAL. #11104: an OPERATOR-declared rule (`OperatorProviderErrorRule`)
+   * is exempt from this allowlist — `honorsRuleLockScope()` always returns true
+   * when the provider has one, since the operator already opted in by declaring
+   * the rule. Widening `HONORS_RULE_LOCK_SCOPE_PROVIDERS` itself (for a new
+   * built-in catalog rule) 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. */
   cooldownMs?: number;
 };
 
+/**
+ * Operator-declared per-provider error rule (settings-driven).
+ *
+ * Mirrors the catalog `ProviderErrorRule` but is data-only so an operator can
+ * add a scope/cooldown/reason override for a provider without editing this
+ * file. `match` is a plain case-insensitive SUBSTRING of the error body — never
+ * a RegExp — so an operator-supplied pattern can never introduce a ReDoS on the
+ * error-classification hot path. Bounded to <= 50 rules total by the settings
+ * schema. An operator rule is consulted BEFORE the built-in `providerRuleRegistry`
+ * and wins on the first status+substring match for a provider.
+ */
+export type OperatorProviderErrorRule = {
+  status: number;
+  match: string;
+  scope: "model" | "provider" | "connection";
+  reason?: ConfiguredErrorReason;
+  cooldownMs?: number;
+};
+
+let operatorProviderErrorRules: Record<string, OperatorProviderErrorRule[]> = {};
+
+/**
+ * Inject operator-declared rules. Called from the runtime-settings applier
+ * (`applyRuntimeSettings`) once at boot and on every settings update, with the
+ * value validated by the settings schema. Pass `undefined`/empty/null to clear.
+ * Provider keys are lowercased so lookups are case-insensitive.
+ */
+export function setOperatorProviderErrorRules(
+  rules: Record<string, OperatorProviderErrorRule[]> | undefined | null
+): void {
+  operatorProviderErrorRules = {};
+  if (!rules) return;
+  for (const [provider, list] of Object.entries(rules)) {
+    if (Array.isArray(list) && list.length > 0) {
+      operatorProviderErrorRules[provider.toLowerCase()] = list;
+    }
+  }
+}
+
 // ─── Opencode ───────────────────────────────────────────────────────────────────
 // Opencode Go uses an account-wide quota. The body usually says "rate limit
 // reached" but the presence of `x-ratelimit-remaining-requests: 0` is the
@@ -272,11 +314,21 @@ export const providerRuleRegistry = new Map<string, ProviderErrorRule[]>([
  * 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.
+ *
+ * Providers with an operator-declared rule (`setOperatorProviderErrorRules`)
+ * are honored too, without being added here: the allowlist exists to gate
+ * BUILT-IN catalog rules, which change default behavior for every operator
+ * running that provider — an operator rule is already an explicit, per-operator
+ * opt-in, so gating it a second time behind this list would make the settings
+ * mechanism (#11104) silently inert for every provider except the ones listed
+ * below. See `hasOperatorRuleForProvider`.
  */
 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());
+  if (!provider) return false;
+  const key = provider.toLowerCase();
+  return HONORS_RULE_LOCK_SCOPE_PROVIDERS.has(key) || hasOperatorRuleForProvider(key);
 }
 
 /**
@@ -310,28 +362,51 @@ export function egressBucketedLockProviders(): string[] {
 }
 
 /**
- * Providers whose rules match on the FULL upstream error text.
- * checkFallbackError's rule lookup normally passes only the structured
+ * Providers whose BUILT-IN catalog rules match on the FULL upstream error
+ * text. checkFallbackError's rule lookup normally passes only the structured
  * error ({code, type} — message stripped by the combo callers), which is
  * enough for header/status/code rules but blind to body-text markers like
  * agentrouter's "额度不足". Providers in this set get the raw error text as
  * the match body instead. EXCLUSIVE allowlist by owner decision (2026-08-13):
  * adding a provider here is an explicit opt-in — the default path for every
  * other provider must remain byte-for-byte unchanged.
+ *
+ * Operator-declared rules bypass this allowlist entirely (see
+ * `hasOperatorRuleForProvider`): the operator's `match` is a literal substring
+ * of the error body by construction, so a rule that never sees body text could
+ * never match anything, defeating the point of declaring it.
  */
 const FULL_TEXT_RULE_PROVIDERS = new Set(["agentrouter"]);
 
+/**
+ * True when an operator has declared at least one rule for this provider via
+ * `settings.providerErrorRules` (injected through `setOperatorProviderErrorRules`).
+ * Presence of the rule IS the opt-in — no separate allowlist to maintain, and
+ * no widening decision needed as new operators configure new providers.
+ */
+export function hasOperatorRuleForProvider(provider: string | null | undefined): boolean {
+  if (!provider) return false;
+  const rules = operatorProviderErrorRules[provider.toLowerCase()];
+  return !!rules && rules.length > 0;
+}
+
 /**
  * Resolve the body handed to getProviderErrorRuleMatch inside
- * checkFallbackError: full error text for FULL_TEXT_RULE_PROVIDERS,
- * the structured error for everyone else.
+ * checkFallbackError: full error text for FULL_TEXT_RULE_PROVIDERS or any
+ * provider with an operator-declared rule, the structured error for everyone
+ * else.
  */
 export function resolveRuleMatchBody(
   provider: string | null | undefined,
   structuredError: unknown,
   errorText: string | null | undefined
 ): unknown {
-  if (provider && FULL_TEXT_RULE_PROVIDERS.has(provider.toLowerCase()) && errorText) {
+  if (
+    provider &&
+    (FULL_TEXT_RULE_PROVIDERS.has(provider.toLowerCase()) ||
+      hasOperatorRuleForProvider(provider)) &&
+    errorText
+  ) {
     return errorText;
   }
   return structuredError ?? null;
@@ -346,10 +421,32 @@ export function getProviderErrorRuleMatch(
   provider: string | null | undefined,
   status: number,
   headers: Headers | Record<string, string> | null | undefined,
-  body?: unknown
+  body?: unknown,
+  operatorRules?: Record<string, OperatorProviderErrorRule[]>
 ): ProviderErrorRuleMatch | null {
   if (!provider) return null;
-  const rules = providerRuleRegistry.get(provider.toLowerCase());
+  const key = provider.toLowerCase();
+
+  // Operator-declared rules win first: an operator can override any catalog
+  // rule for a provider without editing this file. `operatorRules` is the
+  // injected source (tests / direct callers); when omitted we fall back to the
+  // settings-backed cache populated by `setOperatorProviderErrorRules`.
+  const opRules = (operatorRules ?? operatorProviderErrorRules)?.[key];
+  if (opRules && opRules.length > 0) {
+    const text = typeof body === "string" ? body : JSON.stringify(body ?? "");
+    const lowered = text.toLowerCase();
+    for (const r of opRules) {
+      if (r.status === status && lowered.includes(r.match.toLowerCase())) {
+        return {
+          reason: r.reason ?? "quota_exhausted",
+          scope: r.scope,
+          cooldownMs: r.cooldownMs,
+        };
+      }
+    }
+  }
+
+  const rules = providerRuleRegistry.get(key);
   if (!rules) return null;
   // Normalize headers: accept either a `Headers` object (from `fetch()`) or
   // a plain record. Provider rules access headers via plain object indexing.

open-sse/config/providerRegistry.ts

@@ -10,6 +10,10 @@ export {
 } from "./providers/registry/alibaba/index.ts";
 export { REGISTRY } from "./providers/index.ts";
 import { REGISTRY } from "./providers/index.ts";
+// Imported from `privateHost` rather than `outboundUrlGuard`: this module is reachable from
+// `ProviderDetailPageClient.tsx`, so anything it pulls in has to survive a browser bundle
+// (#11122). `privateHost` is platform-free by contract; the guard module is not.
+import { isPrivateHost } from "@/shared/network/privateHost";
 import {
   RegistryModel,
   REASONING_UNSUPPORTED,
@@ -132,11 +136,8 @@ export function isLocalProvider(baseUrl?: string | null): boolean {
   try {
     const url = new URL(baseUrl);
     const hostname = url.hostname;
-    // Strictly matching 172.16.0.0/12 (Docker/local) and explicitly blocking ::1 per SSRF hardening
-    return (
-      LOCAL_HOSTNAMES.has(hostname) ||
-      /^172\.(1[6-9]|2[0-9]|3[0-1])\.\d{1,3}\.\d{1,3}$/.test(hostname)
-    );
+    if (!hostname) return false;
+    return LOCAL_HOSTNAMES.has(hostname) || isPrivateHost(hostname);
   } catch {
     return false;
   }

open-sse/config/providers/index.ts

@@ -70,7 +70,6 @@ import { togetherProvider } from "./registry/together/index.ts";
 import { cohereProvider } from "./registry/cohere/index.ts";
 import { cursorProvider, cursor_apiProvider } from "./registry/cursor/index.ts";
 import { volcengineProvider } from "./registry/volcengine/index.ts";
-import { hackclubProvider } from "./registry/hackclub/index.ts";
 import { freetheaiProvider } from "./registry/freetheai/index.ts";
 import { g4f_groqProvider } from "./registry/g4f-groq/index.ts";
 import { g4f_geminiProvider } from "./registry/g4f-gemini/index.ts";
@@ -336,7 +335,6 @@ export const REGISTRY: Record<string, RegistryEntry> = {
   cursor: cursorProvider,
   "cursor-api": cursor_apiProvider,
   volcengine: volcengineProvider,
-  hackclub: hackclubProvider,
   freetheai: freetheaiProvider,
   "g4f-groq": g4f_groqProvider,
   "g4f-gemini": g4f_geminiProvider,

open-sse/config/providers/registry/cline/index.ts

@@ -27,7 +27,7 @@ export const clineProvider: RegistryEntry = {
   // the official free bucket and text-output models advertised as zero-cost.
   models: [
     {
-      id: "zai/glm-5.2",
+      id: "z-ai/glm-5.2",
       name: "GLM 5.2",
       toolCalling: true,
       supportsReasoning: true,

open-sse/config/providers/registry/hackclub/index.ts

@@ -1,19 +0,0 @@
-import type { RegistryEntry } from "../../shared.ts";
-
-export const hackclubProvider: RegistryEntry = {
-  id: "hackclub",
-  alias: "hc",
-  format: "openai",
-  executor: "default",
-  baseUrl: "https://ai.hackclub.com/proxy/v1/chat/completions",
-  modelsUrl: "https://ai.hackclub.com/proxy/v1/models",
-  authType: "optional",
-  authHeader: "bearer",
-  passthroughModels: true,
-  defaultContextLength: 128000,
-  models: [
-    { id: "meta-llama/llama-3.3-70b-instruct", name: "Llama 3.3 70B" },
-    { id: "mistralai/mistral-7b-instruct", name: "Mistral 7B" },
-    { id: "deepseek-ai/deepseek-coder-33b", name: "DeepSeek Coder 33B" },
-  ],
-};

open-sse/config/providers/registry/kimi/web/index.ts

@@ -12,10 +12,9 @@ export const kimi_webProvider: RegistryEntry = {
   alias: "kimi-web",
   format: "openai",
   executor: "kimi-web",
-  // International consumer chat — the legacy `kimi.moonshot.cn` domain now
-  // redirects every non-CN visitor to www.kimi.com, which speaks a different
-  // Connect-RPC API. See `open-sse/executors/kimi-web.ts` for the wire format.
-  baseUrl: "https://www.kimi.com",
+  // International consumer chat — Connect-RPC API at www.kimi.ai.
+  // See `open-sse/executors/kimi-web.ts` for the wire format.
+  baseUrl: "https://www.kimi.ai",
   authType: "apikey",
   authHeader: "Authorization",
   // Curated-only catalog. Agent Swarm is excluded because it requires Kimi's

open-sse/config/providers/registry/opencode/go/index.ts

@@ -14,8 +14,6 @@ export const opencode_goProvider: RegistryEntry = {
   authPrefix: "Bearer",
   defaultContextLength: 200000,
   models: [
-    ...OPENCODE_ZEN_GO_SHARED_MODELS,
-
     // Port from decolua/9router 8efacc11: align with official Go endpoints —
     // glm-5.2 is now advertised and Kimi chat traffic must route through
     // `kimi-k2.7-code` (the live API rejects the plain `kimi-k2.7` alias for
@@ -26,6 +24,10 @@ export const opencode_goProvider: RegistryEntry = {
     { id: "glm-5.2", name: "GLM-5.2", supportsReasoning: true },
     { id: "glm-5.2-high", name: "GLM-5.2 (high effort)", supportsReasoning: true },
     { id: "glm-5.2-max", name: "GLM-5.2 (max effort)", supportsReasoning: true },
+
+    ...OPENCODE_ZEN_GO_SHARED_MODELS,
+    // models[0] (glm-5.2) is the dashboard default (LlmChatCard/ProviderTestSlideOver take models[0]).
+
     { id: "glm-5.1", name: "GLM-5.1" },
     { id: "glm-5", name: "GLM-5" },
     // kimi-k2.7-code declared identically on opencode-zen — see OPENCODE_ZEN_GO_SHARED_MODELS.

open-sse/config/providers/registry/opencode/zen/index.ts

@@ -16,8 +16,6 @@ export const opencode_zenProvider: RegistryEntry = {
   // from the live API response so new models work without a code deploy.
   passthroughModels: true,
   models: [
-    ...OPENCODE_ZEN_GO_SHARED_MODELS,
-
     // ── Chat / Coding ──────────────────────────────────────────
     // #2900: big-pickle's upstream runs DeepSeek thinking mode — declare the
     // interleaved reasoning_content contract so follow-up/tool-use turns replay
@@ -28,6 +26,10 @@ export const opencode_zenProvider: RegistryEntry = {
       supportsReasoning: true,
       interleavedField: "reasoning_content",
     },
+
+    ...OPENCODE_ZEN_GO_SHARED_MODELS,
+    // models[0] (big-pickle) is the dashboard default; SHARED spread kept after it.
+
     { id: "gpt-5.6-sol", name: "GPT 5.6 Sol" },
     { id: "gpt-5.6-terra", name: "GPT 5.6 Terra" },
     { id: "gpt-5.6-luna", name: "GPT 5.6 Luna" },
@@ -67,6 +69,8 @@ export const opencode_zenProvider: RegistryEntry = {
       supportsReasoning: true,
       targetFormat: "openai-responses",
     },
+    // Explicit wire-format overlay of the base opencode provider's muse-spark entry
+    // (targetFormat: openai-responses). Keep in sync with base on catalog syncs.
     {
       id: "muse-spark-1.2-contributor-free",
       name: "Muse Spark 1.2 Contributor Free",

open-sse/config/searchRegistry.ts

@@ -10,6 +10,8 @@
  * perplexity-search reuses credentials from the "perplexity" chat provider.
  */
 
+import { isProviderBlockedByIdOrAlias } from "@/shared/utils/noAuthProviders";
+
 export interface SearchProviderConfig {
   id: string;
   name: string;
@@ -394,16 +396,18 @@ export function supportsSearchType(
 /**
  * Get all search providers as a flat list
  */
-export function getAllSearchProviders(): Array<{
+export function getAllSearchProviders(blockedProviders: string[] = []): Array<{
   id: string;
   name: string;
   searchTypes: string[];
 }> {
-  return Object.values(SEARCH_PROVIDERS).map((p) => ({
-    id: p.id,
-    name: p.name,
-    searchTypes: p.searchTypes,
-  }));
+  return Object.values(SEARCH_PROVIDERS)
+    .filter((p) => !p.disabled && !isProviderBlockedByIdOrAlias(p.id, blockedProviders))
+    .map((p) => ({
+      id: p.id,
+      name: p.name,
+      searchTypes: p.searchTypes,
+    }));
 }
 
 /**

open-sse/executors/accountRotation.ts

@@ -1,7 +1,7 @@
 /**
  * Shared multi-account rotation mechanics for noauth executors that round-robin
  * across several "accounts" (fingerprints), each with an optional dedicated
- * proxy — currently `OpencodeExecutor` and `MimocodeExecutor`.
+ * proxy — currently `OpencodeExecutor`.
  *
  * Extracted after both executors independently implemented the same
  * pickAccount/markCooldown/markSuccess skeleton with the same exponential
@@ -120,3 +120,58 @@ export function maskAccountId(fingerprint: string): string {
 export function isNetworkErrorRotatable(account: RotatableAccount): boolean {
   return account.proxy !== null;
 }
+
+/**
+ * Detect an *empty* upstream rejection: a 400 whose body carries no usable
+ * completion — the kind `OpencodeExecutor` must rotate/retry on instead of
+ * propagating as a fatal success.
+ *
+ * Signature is deliberately strict and scoped to the observed malformed
+ * envelope (`choices[0].message` with no `error`, no real `content`,
+ * `finish_reason: null`):
+ *  - status must be exactly 400 (anything else → false);
+ *  - body must parse and contain a `choices` array with at least one entry
+ *    holding a `message` object;
+ *  - an `error` field (present or empty) → false, so genuine 400s keep
+ *    propagating immediately (#10460 precedent: classify by signature before
+ *    rotating);
+ *  - `tool_calls` / `reasoning_content` → false (real content);
+ *  - `message.content` absent / null / "" → eligible; any other value
+ *    (non-empty text, number, block array…) → false (conservative);
+ *  - a literal `finish_reason` (not null) → false (a completed, if empty, turn).
+ *
+ * Does NOT reuse `detectMalformedNonStream` (diagnostics.ts): that classifier
+ * also flags `{error:{…}}` bodies as `empty_choices`, which would rotate on
+ * real errors — a false-positive class with a history here.
+ */
+export function isEmptyUpstreamRejection(status: number, bodyText: string): boolean {
+  if (status !== 400) return false;
+  let parsed: unknown;
+  try {
+    parsed = JSON.parse(bodyText);
+  } catch {
+    return false;
+  }
+  const choices = (parsed as { choices?: unknown })?.choices;
+  if (!Array.isArray(choices) || choices.length === 0) return false;
+  const first = choices[0] as { message?: unknown; finish_reason?: unknown };
+  if (typeof first !== "object" || first === null) return false;
+  const rawMessage = (first as { message?: unknown }).message;
+  if (typeof rawMessage === "undefined" || rawMessage === null) return false;
+  if (typeof parsed !== "object" || parsed === null) return false;
+  if ("error" in (parsed as Record<string, unknown>)) return false;
+  const msg = rawMessage as Record<string, unknown>;
+  if ("tool_calls" in msg) return false;
+  if ("reasoning_content" in msg) return false;
+  const content = msg.content;
+  if (content !== undefined && content !== null && content !== "") return false;
+  if (first.finish_reason !== null && first.finish_reason !== undefined) return false;
+  return true;
+}
+
+/** Best-effort extraction of the upstream `chatcmpl_*` id from a response body,
+ * for observability logging. Returns `"unknown"` when absent or unparseable. */
+export function extractChatcmplId(bodyText: string): string {
+  const match = /"id"\s*:\s*"(chatcmpl_[^"]+)"/.exec(bodyText);
+  return match ? match[1] : "unknown";
+}

open-sse/executors/base.ts

@@ -20,6 +20,10 @@ import {
   recordLearnedThinkingCap,
   parseThinkingBudgetMax,
 } from "../services/learnedThinkingCaps.ts";
+import {
+  recordLearnedReasoningEffort,
+  parseReasoningEffortEnum,
+} from "../services/learnedReasoningEffortCaps.ts";
 import {
   getParamFilterConfig,
   addParamToBlocklist,
@@ -826,6 +830,9 @@ export class BaseExecutor {
     // loop. The learned cap is also recorded process-wide via
     // recordLearnedThinkingCap so future requests skip the 400 entirely.
     let thinkingBudgetClampedMax: number | null = null;
+    // Set by the reasoning_effort 4xx clamp-and-retry below — guards the same
+    // "fires at most once per URL" invariant as thinkingBudgetClampedMax above.
+    let reasoningEffortClamped = false;
 
     for (let urlIndex = 0; urlIndex < fallbackCount; urlIndex++) {
       const requestCredentials = withForcedResponsesUpstream(
@@ -1529,6 +1536,49 @@ export class BaseExecutor {
           }
         }
 
+        // Reasoning-effort enum 4xx clamp-and-retry (any provider/model without a
+        // declared reasoning_effort capability — custom OpenAI-compatible
+        // connections, or a registered provider the registry hasn't caught up
+        // with). Mirrors the thinking_budget clamp-and-retry above: parse the
+        // upstream-advertised accepted values, record them process-wide (so
+        // FUTURE requests clamp proactively via sanitizeReasoningEffortForProvider
+        // → getLearnedReasoningEffort), clamp the live transformedBody by
+        // re-running the sanitizer, and retry the same URL once.
+        if (
+          (response.status === HTTP_STATUS.BAD_REQUEST ||
+            response.status === HTTP_STATUS.UNPROCESSABLE_ENTITY) &&
+          !reasoningEffortClamped &&
+          transformedBody &&
+          typeof transformedBody === "object"
+        ) {
+          const errText = await response
+            .clone()
+            .text()
+            .catch(() => "");
+          const acceptedValues = parseReasoningEffortEnum(errText);
+          if (acceptedValues) {
+            reasoningEffortClamped = true;
+            const learned = recordLearnedReasoningEffort(this.provider, model, acceptedValues);
+            if (learned) {
+              transformedBody = sanitizeReasoningEffortForProvider(
+                transformedBody,
+                this.provider,
+                model,
+                log
+              );
+              let retryBody = JSON.stringify(transformedBody);
+              if (usesClaudeCodeProtocol || this.provider === "claude") {
+                retryBody = await signRequestBody(retryBody);
+              }
+              log?.info?.(
+                "REASONING_SANITIZE",
+                `Upstream ${response.status} rejected reasoning_effort on ${url} — clamped to ${learned} and retrying (learned for ${this.provider}/${model})`
+              );
+              response = await fetchWithStartTimeout(url, { ...fetchOptions, body: retryBody });
+            }
+          }
+        }
+
         // Generic reactive 400 field-downgrade; each field is stripped at most once.
         if (
           response.status === HTTP_STATUS.BAD_REQUEST &&

open-sse/executors/base/reasoningEffort.ts

@@ -8,6 +8,10 @@ import {
   getProviderModel,
   getProviderModels,
 } from "../../config/providerModels.ts";
+import {
+  getLearnedReasoningEffort,
+  REASONING_EFFORT_ORDER,
+} from "../../services/learnedReasoningEffortCaps.ts";
 
 /**
  * Sanitize reasoning_effort for providers that don't accept all values.
@@ -338,10 +342,24 @@ export function sanitizeReasoningEffortForProvider(
 
   const supportsXHigh = supportsXHighEffort(provider, modelStr);
   const supportsMax = supportsMaxEffortForProvider(provider, modelStr);
+  // Highest value we've actually seen this provider+model accept in a real
+  // upstream 4xx (learnedReasoningEffortCaps.ts) — takes priority over the
+  // static registry (which defaults to "supports everything" when there's no
+  // entry, e.g. custom OpenAI-compatible connections) and over the hardcoded
+  // "high" fallback below (which isn't always valid either).
+  const learnedCap = getLearnedReasoningEffort(provider, modelStr);
+  const learnedRank = learnedCap ? REASONING_EFFORT_ORDER.indexOf(learnedCap) : -1;
 
   // ── xhigh handling ──────────────────────────────────────────────────────
   // xhigh is OmniRoute-internal. Map it to the best effort the model accepts.
   if (effortStr === "xhigh") {
+    if (learnedCap && learnedRank < REASONING_EFFORT_ORDER.indexOf("xhigh")) {
+      log?.info?.(
+        "REASONING_SANITIZE",
+        `${provider}/${modelStr}: clamped reasoning_effort xhigh → ${learnedCap} (learned)`
+      );
+      return writeEffortValue(b, learnedCap, c);
+    }
     if (supportsXHigh) return body; // model accepts xhigh natively
     if (supportsMax) {
       log?.info?.(
@@ -366,6 +384,13 @@ export function sanitizeReasoningEffortForProvider(
   // upstream, and if it 400s the user gets a clear signal. This prevents
   // new models from being unusable for weeks until they're whitelisted (#8057).
   if (effortStr === "max") {
+    if (learnedCap && learnedRank < REASONING_EFFORT_ORDER.indexOf("max")) {
+      log?.info?.(
+        "REASONING_SANITIZE",
+        `${provider}/${modelStr}: clamped reasoning_effort max → ${learnedCap} (learned)`
+      );
+      return writeEffortValue(b, learnedCap, c);
+    }
     if (supportsMax) return body; // explicitly known to accept max
 
     // A model that explicitly advertises its accepted tiers is safe to normalize.

open-sse/executors/hailuo-web.ts

@@ -1,11 +1,11 @@
 /**
- * HailuoWebExecutor — Hailuo AI (MiniMax) web chat via www.hailuo.ai.
+ * HailuoWebExecutor — Hailuo AI (MiniMax) web chat via chat.minimax.io.
  *
  * Distinct from the paid API-key `minimax`/`minimax-cn` providers
  * (open-sse/config/providers/registry/minimax/) — this targets the free
- * consumer chat product at hailuo.ai / chat.minimax.io.
+ * consumer chat product at chat.minimax.io.
  *
- * Endpoint: POST https://www.hailuo.ai/v4/api/chat/msg?<fingerprint query>
+ * Endpoint: POST https://chat.minimax.io/v4/api/chat/msg?<fingerprint query>
  * Auth:     `token` header — value read from the site's `_token` localStorage
  *           entry, plus a per-request `yy` signature header.
  * Body:     multipart/form-data — characterID, msgContent, chatID, searchMode.

open-sse/executors/kimi-web.ts

@@ -1,10 +1,10 @@
 /**
- * KimiWebExecutor — Moonshot AI Chat via www.kimi.com (international)
+ * KimiWebExecutor — Moonshot AI Chat via www.kimi.ai (international)
  *
  * Routes requests through Kimi's consumer chat API on the international domain.
  * Originally this executor targeted `kimi.moonshot.cn` (mainland-CN consumer
  * chat). That domain now redirects every visitor outside CN to
- * `https://www.kimi.com/`, which speaks a completely different API surface:
+ * `https://www.kimi.ai/`, which speaks a completely different API surface:
  *
  *   - Endpoint:  POST /apiv2/kimi.gateway.chat.v1.ChatService/Chat
  *   - Protocol:  Connect-RPC (unary envelope framing — 5-byte header + JSON)
@@ -326,7 +326,7 @@ export class KimiWebExecutor extends BaseExecutor {
     if (!accessToken) {
       return makeErrorResult(
         400,
-        "Missing Kimi access_token — log in at www.kimi.com and capture access_token from localStorage.",
+        "Missing Kimi access_token — log in at www.kimi.ai and capture access_token from localStorage.",
         body,
         CHAT_URL
       );
@@ -410,10 +410,7 @@ export class KimiWebExecutor extends BaseExecutor {
       const refreshToken =
         credentials?.refreshToken || credentials?.providerSpecificData?.refreshToken;
       if (refreshToken && typeof refreshToken === "string") {
-        const refreshRes = await exchangeKimiRefreshToken(
-          refreshToken,
-          getKimiWebBaseUrl()
-        );
+        const refreshRes = await exchangeKimiRefreshToken(refreshToken, getKimiWebBaseUrl());
         if (refreshRes.success && refreshRes.accessToken) {
           accessToken = refreshRes.accessToken;
           const retryHeaders = this.buildKimiHeaders(accessToken);

open-sse/executors/opencode.ts

@@ -15,6 +15,8 @@ import {
   markSuccess as markAccountSuccess,
   maskAccountId,
   isNetworkErrorRotatable,
+  isEmptyUpstreamRejection,
+  extractChatcmplId,
 } from "./accountRotation.ts";
 import { isNetworkRotationSharedEgressGuardEnabled } from "@/shared/utils/featureFlags";
 
@@ -253,14 +255,41 @@ export class OpencodeExecutor extends BaseExecutor {
 
     try {
       this.syncAccountsFromCredentials(input.credentials);
+      const { log } = input;
 
       const hasProxies = this.accounts.some((a) => a.proxy !== null);
-      // Fast path: no multi-account proxy wiring configured → original behavior.
+      // Fast path: no multi-account proxy wiring configured → original behavior,
+      // plus exactly ONE bounded retry when the upstream answers a 400 empty
+      // rejection (same predicate and logging as the rotation loop). Everything
+      // else passes untouched: this path deliberately preserves BaseExecutor's
+      // intra-URL 429 retries (no skipUpstreamRetry here).
       if (this.accounts.length === 1 && !hasProxies) {
-        return await super.execute(input);
+        const single = (await super.execute(input)) as HttpExecuteResult;
+        if (single.response.status === 400) {
+          let bodyText: string | null = null;
+          try {
+            bodyText = await single.response.clone().text();
+          } catch {
+            log?.debug?.("OPENCODE", "body read failed on direct account");
+          }
+          if (bodyText !== null) {
+            if (isEmptyUpstreamRejection(400, bodyText)) {
+              const chatcmplId = extractChatcmplId(bodyText);
+              log?.warn?.(
+                "OPENCODE",
+                `upstream empty rejection on direct account (${chatcmplId}), retrying once…`
+              );
+              return await super.execute(input);
+            }
+            log?.debug?.(
+              "OPENCODE",
+              "400 without error field, signature not matched on direct account — observing"
+            );
+          }
+        }
+        return single;
       }
 
-      const { log } = input;
       // This loop only ever dispatches through super.execute() (the HTTP request
       // path), which always resolves the object-shaped arm of ExecutorExecuteResult
       // — the bare-Response arm belongs to web/scraping executors only (base.ts:290).
@@ -277,8 +306,13 @@ export class OpencodeExecutor extends BaseExecutor {
       // network call, but proxied accounts (independent egress) are still
       // tried normally.
       let sharedEgressDown = false;
+      // Bounded extra attempts for empty upstream rejections: +1 for a single
+      // account (retry the same one), none for a multi-account fleet (rotation
+      // through the accounts is the retry). Avoids an unbounded loop on a
+      // persistently malformed upstream.
+      const emptyRejectionBudget = this.accounts.length === 1 ? 1 : 0;
 
-      for (let attempt = 0; attempt < this.accounts.length; attempt++) {
+      for (let attempt = 0; attempt < this.accounts.length + emptyRejectionBudget; attempt++) {
         const account = this.pickAccount();
         const masked = maskAccountId(account.fingerprint);
 
@@ -354,6 +388,34 @@ export class OpencodeExecutor extends BaseExecutor {
           continue;
         }
 
+        // Empty upstream rejection (malformed 400: no error field, no real
+        // content, finish_reason null — see isEmptyUpstreamRejection). Rotate/
+        // retry instead of propagating it as a fatal success: the observed
+        // envelope was marking subagent sessions as failed. Read the body ONLY
+        // for a 400 (never a 200/streaming — that would buffer the good path);
+        // classify, log, and continue. Neitheries markCooldown nor markSuccess:
+        // the failure is upstream's, not this account's.
+        if (status === 400) {
+          let bodyText: string | null = null;
+          try {
+            bodyText = await result.response.clone().text();
+          } catch {
+            log?.debug?.("OPENCODE", "body read failed on empty rejection check");
+          }
+          if (bodyText !== null && isEmptyUpstreamRejection(400, bodyText)) {
+            const chatcmplId = extractChatcmplId(bodyText);
+            log?.warn?.(
+              "OPENCODE",
+              `upstream empty rejection on account ${masked} (${chatcmplId}), rotating to next…`
+            );
+            continue;
+          }
+          // A 400 carrying a real error (or non-empty content): propagate
+          // immediately, untouched — same as before this change.
+          this.markSuccess(account);
+          return result;
+        }
+
         this.markSuccess(account);
         return result;
       }

open-sse/handlers/rerank.ts

@@ -199,6 +199,8 @@ export async function handleRerank({
   return_documents,
   credentials,
   connectionId = null,
+  apiKeyId = null,
+  apiKeyName = null,
 }) {
   const startTime = Date.now();
   if (!model) return errorResponse(400, "model is required");
@@ -267,10 +269,23 @@ export async function handleRerank({
 
     if (!res.ok) {
       const errData = await res.json().catch(() => ({}));
-      return errorResponse(
-        res.status,
-        errData.message || errData.error?.message || `Provider returned HTTP ${res.status}`
-      );
+      const errorMessage =
+        errData.message || errData.error?.message || `Provider returned HTTP ${res.status}`;
+      saveCallLog({
+        method: "POST",
+        path: "/v1/rerank",
+        status: res.status,
+        model: `${providerId}/${modelId}`,
+        provider: providerId,
+        connectionId: connectionId || undefined,
+        duration: Date.now() - startTime,
+        requestBody,
+        responseBody: errData,
+        error: errorMessage,
+        apiKeyId: apiKeyId || undefined,
+        apiKeyName: apiKeyName || undefined,
+      }).catch(() => {});
+      return errorResponse(res.status, errorMessage);
     }
 
     const data = await res.json();
@@ -289,10 +304,13 @@ export async function handleRerank({
       status: 200,
       model: `${providerId}/${modelId}`,
       provider: providerId,
+      connectionId: connectionId || undefined,
       duration: Date.now() - startTime,
       tokens: { prompt_tokens: 0, completion_tokens: 0 },
-      responseBody: { results_count: Array.isArray(result?.results) ? result.results.length : 0 },
-      connectionId,
+      requestBody,
+      responseBody: result,
+      apiKeyId: apiKeyId || undefined,
+      apiKeyName: apiKeyName || undefined,
     }).catch(() => {});
 
     const headers = new Headers({ ...CORS_HEADERS, "Content-Type": "application/json" });

open-sse/handlers/responseTranslator.ts

@@ -10,6 +10,7 @@ import {
   caseInsensitiveToolNameLookup,
   restoreOpenAIToolNames,
 } from "../translator/helpers/toolCallHelper.ts";
+import { restoreClaudeToolName } from "../services/claudeCodeToolRemapper.ts";
 import { extractReplayableResponsesReasoningText } from "../services/reasoningInputPolicy.ts";
 import { sanitizeToolId } from "../translator/helpers/schemaCoercion.ts";
 
@@ -631,7 +632,7 @@ export function translateNonStreamingResponse(
 
   // Phase 3: Translate from OpenAI back to Client Source format
   if (sourceFormat === FORMATS.CLAUDE && sourceFormat !== targetFormat) {
-    return convertOpenAINonStreamingToClaude(toRecord(intermediateOpenAI));
+    return convertOpenAINonStreamingToClaude(toRecord(intermediateOpenAI), toolNameMap ?? null);
   }
 
   // Gemini-family clients (Gemini, Antigravity): the streaming SSE path already
@@ -667,8 +668,18 @@ function resolveReasoningText(messageObj: JsonRecord): string {
 
 /**
  * Helper to convert an OpenAI chat.completion JSON object to Claude format for non-streaming.
+ *
+ * `toolNameMap` carries request-side aliases; when it does not resolve a name,
+ * `restoreClaudeToolName` upgrades known Claude Code tools to their canonical
+ * PascalCase ("bash" → "Bash", "croncreate" → "CronCreate"). Without this, a
+ * non-streaming upstream JSON body (or a stream:true request the upstream
+ * answered with application/json) reaches Claude Code with lowercase tool_use
+ * names the CLI rejects as "No such tool available".
  */
-function convertOpenAINonStreamingToClaude(openaiResponse: JsonRecord): JsonRecord {
+function convertOpenAINonStreamingToClaude(
+  openaiResponse: JsonRecord,
+  toolNameMap?: Map<string, string> | null
+): JsonRecord {
   const choices = openaiResponse.choices as unknown[] | undefined;
   const isChoicesArray = Array.isArray(choices);
   if (!isChoicesArray && openaiResponse.object !== "chat.completion") {
@@ -717,7 +728,7 @@ function convertOpenAINonStreamingToClaude(openaiResponse: JsonRecord): JsonReco
       content.push({
         type: "tool_use",
         id: sanitizeToolId(rawId),
-        name: toString(fn.name),
+        name: restoreClaudeToolName(toString(fn.name), toolNameMap ?? null),
         input:
           typeof fn.arguments === "string" ? JSON.parse(fn.arguments || "{}") : fn.arguments || {},
       });

open-sse/mcp-server/__tests__/mcp-runtime-blocked-provider-schema.test.ts

@@ -0,0 +1,58 @@
+import { describe, it, expect } from "vitest";
+import { createMcpServer } from "../server";
+import { buildWebSearchInputSchema } from "../schemas/tools";
+import { getActiveSearchProviders } from "../schemas/providerEnums";
+
+interface ToolWithSchema {
+  inputSchema: {
+    safeParse: (arg: unknown) => { success: boolean };
+  };
+}
+
+describe("MCP Dynamic Runtime Schema Plumbing", () => {
+  it("getActiveSearchProviders excludes blocked providers dynamically by id or alias", () => {
+    const allProviders = getActiveSearchProviders([]);
+    expect(allProviders).toContain("serper-search");
+    expect(allProviders).toContain("brave-search");
+
+    const filteredProviders = getActiveSearchProviders(["serper", "brave"]);
+    expect(filteredProviders).not.toContain("serper-search");
+    expect(filteredProviders).not.toContain("brave-search");
+    expect(filteredProviders.length).toBeGreaterThan(0);
+  });
+
+  it("buildWebSearchInputSchema excludes blocked providers from Zod enum", () => {
+    const fullSchema = buildWebSearchInputSchema([]);
+    const fullParsed = fullSchema.safeParse({ query: "test", provider: "serper-search" });
+    expect(fullParsed.success).toBe(true);
+
+    const blockedSchema = buildWebSearchInputSchema(["serper"]);
+    const blockedParsed = blockedSchema.safeParse({ query: "test", provider: "serper-search" });
+    expect(blockedParsed.success).toBe(false);
+  });
+
+  it("createMcpServer with blockedProviders option registers dynamic tool schema", async () => {
+    const server = createMcpServer({ blockedProviders: ["serper", "brave"] });
+    expect(server).toBeTruthy();
+
+    const registeredTools = (
+      server as unknown as { _registeredTools: Record<string, ToolWithSchema> }
+    )._registeredTools;
+    expect(registeredTools).toBeTruthy();
+
+    const webSearchTool = registeredTools["omniroute_web_search"];
+    expect(webSearchTool).toBeTruthy();
+
+    const parsedWithUnblocked = webSearchTool.inputSchema.safeParse({
+      query: "test",
+      provider: "perplexity-search",
+    });
+    expect(parsedWithUnblocked.success).toBe(true);
+
+    const parsedWithBlocked = webSearchTool.inputSchema.safeParse({
+      query: "test",
+      provider: "serper-search",
+    });
+    expect(parsedWithBlocked.success).toBe(false);
+  });
+});