merge release/v3.8.50 into fix-10778

- ESLint: freeze 6 React Compiler rules (react-hooks/set-state-in-effect,
  preserve-manual-memoization, immutability, static-components, refs, purity)
  newly enabled by eslint-plugin-react-hooks v7 and never suppressed, via
  --suppress-rule (219 -> 0 errors, same pattern as the existing
  no-location-assign-relative-destination precedent).
- check:dead-code: remove 2 symbols dead since PR #10148
  (src/lib/quota/providerCapabilities.ts, ProviderQuotaMonitor interface),
  rebaseline the unattributable residual +1 (418 -> 416, documented).
- tests/unit/autoCombo/tieredRotation.test.ts: widen one test's timeout
  to 20000ms — 200 synchronous selectProvider() calls were hitting vitest's
  5000ms default under shared-devbox contention; assertion unchanged.

Refs #9985.

.env.example

@@ -1483,20 +1483,6 @@ CURSOR_USER_AGENT="Cursor/3.4"
 # OMNIROUTE_BROWSER_POOL=on
 # WEB_COOKIE_USE_BROWSER=0
 
-# ── Kimi Web (international kimi.ai Connect-RPC) ──
-# Used by: open-sse/executors/kimi-web.ts. Override the base/chat URLs only if
-# you need a mirror or proxy endpoint; defaults target https://www.kimi.ai with
-# the Connect-RPC chat path /apiv2/kimi.gateway.chat.v1.ChatService/Chat.
-# KIMI_WEB_BASE_URL=https://www.kimi.ai
-# KIMI_WEB_CHAT_URL=https://www.kimi.ai/apiv2/kimi.gateway.chat.v1.ChatService/Chat
-
-# When OIDC is enabled, disable password login so users can only authenticate
-# via OIDC Single Sign-On. The bare alias OIDC_DISABLE_PASSWORD_LOGIN is also
-# accepted; the Dashboard Feature Flag takes precedence. Used by:
-# src/app/api/auth/login/route.ts, src/app/api/settings/require-login/route.ts.
-# OMNIROUTE_OIDC_DISABLE_PASSWORD_LOGIN=false
-# OIDC_DISABLE_PASSWORD_LOGIN=false
-
 # ── Adobe Firefly browser sign-in (system Chrome/Edge CDP) ──
 # Used by: open-sse/services/adobeFireflyBrowserLogin.ts. The Firefly login
 # flow drives a real, system-installed Chrome or Microsoft Edge via CDP so the
@@ -1941,6 +1927,10 @@ APP_LOG_TO_FILE=true
 # Default: 300000 (5 minutes)
 # SEARCH_CACHE_TTL_MS=300000
 
+# ── OpenAI-compatible multi-connection ──
+# Allow multiple simultaneous connections per OpenAI-compatible provider node.
+# Used by: src/app/api/providers/route.ts
+# ALLOW_MULTI_CONNECTIONS_PER_COMPAT_NODE=false
 
 # ── CC-compatible provider (experimental) ──
 # Enable the Claude Code compatible provider endpoint.
@@ -2574,11 +2564,6 @@ APP_LOG_TO_FILE=true
 # intended to be published as `omniroute-secure`. See SECURITY.md.
 # OMNIROUTE_BUILD_PROFILE=full
 
-# Override the standalone build output directory consumed by the post-build
-# colocation step. Default: the real Next.js standalone output under .build/.
-# Used by: scripts/build/colocate-standalone.mjs (build tooling, not runtime).
-# OMNIROUTE_STANDALONE_DIR=
-
 # Skip emitting `.tar.gz` tarballs during optional-pack staging for the Electron
 # standalone tree (pack directories + optional-packs.index.json are still produced).
 # Used by the desktop release workflow to trim artifact upload size.
@@ -2593,8 +2578,6 @@ APP_LOG_TO_FILE=true
 # ELECTRON_SMOKE_DATA_DIR=
 # ELECTRON_SMOKE_KEEP_DATA=0
 # ELECTRON_SMOKE_STREAM_LOGS=0
-# #7592: second launch against the same DATA_DIR must pick the native driver.
-# ELECTRON_SMOKE_COLD_RESTART=0
 
 # Playground Studio
 # Default model used by the improve-prompt route (optional; falls back to model in request body).

AGENTS.md

@@ -46,7 +46,7 @@ Repository map and Reference Documentation sections below.
 
 ## Project at a Glance
 
-**OmniRoute** — unified AI proxy/router. One endpoint, 348 LLM providers, auto-fallback.
+**OmniRoute** — unified AI proxy/router. One endpoint, 346 LLM providers, auto-fallback.
 
 | Layer         | Location                | Purpose                                                                                                                                                                   |
 | ------------- | ----------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
@@ -58,7 +58,7 @@ Repository map and Reference Documentation sections below.
 | Services      | `open-sse/services/`    | Combo routing, rate limits, caching, etc                                                                                                                                  |
 | Database      | `src/lib/db/`           | SQLite domain modules (157 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 |
+| MCP Server    | `open-sse/mcp-server/`  | 109 tools (44 canonical + memory/skill/GitHub/pool/gamification/plugin/Notion/Obsidian/local-corpus/RTK modules), 3 transports (stdio / SSE / Streamable HTTP), 33 scopes |
 | A2A Server    | `src/lib/a2a/`          | JSON-RPC 2.0 agent protocol                                                                                                                                               |
 | Skills        | `src/lib/skills/`       | Extensible skill framework                                                                                                                                                |
 | Memory        | `src/lib/memory/`       | Persistent conversational memory                                                                                                                                          |

CHANGELOG.md

@@ -2,18 +2,6 @@
 
 ## [Unreleased]
 
-### ✨ New Features
-
-- **feat(sse): STRICT_ZERO_COST** — opt-in, off-by-default `freeAccessPolicy: "strict"` setting
-  that hard-verifies every auto-combo candidate against live quota state and per-connection
-  economic safety before it can be dispatched, going beyond `hidePaidModels`'s static catalog
-  check. Adds curated `hardStopGuaranteed` metadata to `FREE_MODEL_BUDGETS`, a short-TTL quota
-  cache reusing `getUsageForProvider()`, and a connection-safety guarantee: a candidate backed
-  by multiple accounts has its `allowedConnectionIds` narrowed to exactly the connections
-  independently verified `SAFE`, so dispatch can never use an unverified account. An
-  `excludeTosAvoid` guard (default `false`) is available separately for contractual risk. See
-  `docs/routing/STRICT_ZERO_COST.md`.
-
 ---
 
 ## [3.8.50] — TBD
@@ -21,7 +9,6 @@
 _Living section — regenerated 2026-08-12 from all cycle commits (cycle open `ed2db6cb19` → tip). Bullets carry the merged PR and its author; direct pushes listed separately._
 
 ### ✨ New Features
-- **feat(search):** first-class X Search provider (`x-search`) on `POST /v1/search` and MCP `omniroute_x_search` using SuperGrok / xAI server-side `x_search`. Explicit provider or `search_type: "x"` only — never auto-selected for web. Reuses `xai-oauth` / `xao` / `xai` credentials. Not the X Developer Platform MCP. ([#10985](https://github.com/diegosouzapw/OmniRoute/issues/10985))
 - **feat(core):** add Layer A capability filter at router (#5696)
 - **feat(providers):** add DeepAI as paid API-key image provider ([#6671](https://github.com/diegosouzapw/OmniRoute/issues/6671))
 - **feat(providers):** add Naga.ac and ChatAnywhere aggregator gateway providers (#6674 — thanks @chirag127)

README.md

@@ -7,7 +7,7 @@
 
 # 🚀 OmniRoute — The Free AI Gateway
 
-<img src="./docs/diagrams/readme-hero.svg" width="100%" alt="OmniRoute — Never stop coding. Every AI tool → 348 providers — 90+ free — through one endpoint. Claude Code, Codex, Cursor, Cline, Copilot & Antigravity into FREE Claude / GPT / Gemini with auto-fallback. RTK + Caveman stacked compression saves 15–95% tokens (~89% avg) — never hit limits. 348 AI providers · 90+ free tiers · ~1.51B free tokens/mo · 19 routing strategies · $0 to start."/>
+<img src="./docs/diagrams/readme-hero.svg" width="100%" alt="OmniRoute — Never stop coding. Every AI tool → 346 providers — 90+ free — through one endpoint. Claude Code, Codex, Cursor, Cline, Copilot & Antigravity into FREE Claude / GPT / Gemini with auto-fallback. RTK + Caveman stacked compression saves 15–95% tokens (~89% avg) — never hit limits. 346 AI providers · 90+ free tiers · ~1.51B free tokens/mo · 19 routing strategies · $0 to start."/>
 
 </div>
 
@@ -101,7 +101,7 @@
   <tr>
     <td align="right"><b>⚙️ Features</b></td>
     <td align="center"><a href="#-combos--the-flagship">🎯 Combos</a></td>
-    <td align="center"><a href="#-348-ai-providers--90-free">🌐 Providers</a></td>
+    <td align="center"><a href="#-346-ai-providers--90-free">🌐 Providers</a></td>
     <td align="center"><a href="#-full-cli--a2a--mcp">🔌 CLI &amp; MCP</a></td>
   </tr>
   <tr>
@@ -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. 346 providers. Never stop building — OmniRoute picks the cheapest one that works. Six pillars: Never hit limits (auto-fallback across 346 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 109 tools, A2A, memory, guardrails, evals — 25,000+ tests)."/>
 
 <br/>
 <br/>
@@ -461,7 +461,7 @@ All **19** strategies — mix & match per combo step:
 
 </div>
 
-<img src="./docs/diagrams/comparison-table.svg" width="100%" alt="What sets OmniRoute apart — comparison table vs 9router, OpenRouter, CLIProxyAPI and LiteLLM across 13 capabilities. OmniRoute: 348 providers, 90+ free providers built-in, 19 routing strategies, 12-engine token compression, built-in MCP server with 110 tools, A2A agent protocol, persistent memory, guardrails, cloud agents, TLS fingerprint stealth, Desktop/Termux/PWA, 43 i18n UI locales, 100% MIT self-hosted. OmniRoute is the only one with the full set; competitors show a mix of checks, partials and crosses. Verified from each project&apos;s docs."/>
+<img src="./docs/diagrams/comparison-table.svg" width="100%" alt="What sets OmniRoute apart — comparison table vs 9router, OpenRouter, CLIProxyAPI and LiteLLM across 13 capabilities. OmniRoute: 346 providers, 90+ free providers built-in, 19 routing strategies, 12-engine token compression, built-in MCP server with 109 tools, A2A agent protocol, persistent memory, guardrails, cloud agents, TLS fingerprint stealth, Desktop/Termux/PWA, 43 i18n UI locales, 100% MIT self-hosted. OmniRoute is the only one with the full set; competitors show a mix of checks, partials and crosses. Verified from each project&apos;s docs."/>
 
 <sub>📊 Full methodology &amp; per-feature detail vs 9router, OpenRouter, CLIProxyAPI &amp; LiteLLM → [`docs/comparison/OMNIROUTE_VS_ALTERNATIVES.md`](docs/comparison/OMNIROUTE_VS_ALTERNATIVES.md)</sub>
 
@@ -559,7 +559,7 @@ the current catalog at **[radar.omniroute.online/planos](https://radar.omniroute
 - **🖼️ New endpoints** — `/v1/ocr` (Mistral OCR) and `/v1/audio/translations` (Whisper-style) round out the media surface. → [API Reference](docs/reference/API_REFERENCE.md)
 - **🎨 Image / video / audio generation** — one API for media: xAI Grok Imagine & Novita AI video, ComfyUI, Freepik, Adobe Firefly, Microsoft Designer, Segmind, EdgeTTS. → [API Reference](docs/reference/API_REFERENCE.md)
 - **🌍 Deployment & ops** — reverse-proxy `basePath`, browser-language auto-detect, per-key device tracking, root-less MITM trust, zh-TW localization. → [Environment](docs/reference/ENVIRONMENT.md)
-- **🤝 More providers & agents** — Cursor Cloud Agent, Grok Build (xAI) with browser + OAuth login, Ollama first-class card, Claude Opus 5 & Sonnet 5, Kimi official partnership (Code/Web/Moonshot), Zed, Requesty, SenseNova, Yuanbao, Agnes AI… and a refreshed **348-provider catalog**. → [Providers](docs/reference/PROVIDER_REFERENCE.md)
+- **🤝 More providers & agents** — Cursor Cloud Agent, Grok Build (xAI) with browser + OAuth login, Ollama first-class card, Claude Opus 5 & Sonnet 5, Kimi official partnership (Code/Web/Moonshot), Zed, Requesty, SenseNova, Yuanbao, Agnes AI… and a refreshed **346-provider catalog**. → [Providers](docs/reference/PROVIDER_REFERENCE.md)
 - **📡 Routing transparency** — every response carries an `X-OmniRoute-Decision` header naming the strategy/provider/latency that served it, a new `cache-optimized` combo strategy + Auto-Combo `cacheAffinity` factor route repeat requests back to the connection holding the cached prefix, and a read-only `/v1/auto-combo/{channel}/candidates` endpoint exposes an `auto/*` channel's live candidate pool. → [Auto-Combo](docs/routing/AUTO-COMBO.md)
 - **⚡ Local performance & infra** — one-click local Redis, Cloudflare Workers / Deno Deploy relay deployers, Bifrost & Mux as supervised embedded services. → [Embedded Services](docs/frameworks/EMBEDDED-SERVICES.md)
 
@@ -642,11 +642,11 @@ of your shell history. → [CLI Integrations](docs/guides/CLI-INTEGRATIONS.md)
 
 <div align="center">
 
-## 🌐 348 AI Providers — 90+ Free
+## 🌐 346 AI Providers — 90+ Free
 
 </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: **346 providers**, **90+ with a free tier**, **57 free forever**.
 
 <div align="center">
 
@@ -821,7 +821,7 @@ Expose OmniRoute over **MCP**, **A2A**, a **REST API**, **webhooks** or a **remo
 <table>
   <tr><th align="left">Interface</th><th align="left">Endpoint / command</th><th align="left">Use it for</th></tr>
   <tr><td align="left" nowrap>🧰 <b>MCP (stdio)</b></td><td align="left" nowrap><code>omniroute --mcp</code></td><td align="left">Plug into Claude Desktop, Cursor, any MCP client</td></tr>
-  <tr><td align="left" nowrap>🌊 <b>MCP (HTTP)</b></td><td align="left" nowrap><code>/api/mcp/stream</code></td><td align="left">Remote MCP — <b>110 tools</b>, 33 scopes, full audit trail</td></tr>
+  <tr><td align="left" nowrap>🌊 <b>MCP (HTTP)</b></td><td align="left" nowrap><code>/api/mcp/stream</code></td><td align="left">Remote MCP — <b>109 tools</b>, 33 scopes, full audit trail</td></tr>
   <tr><td align="left" nowrap>📡 <b>MCP (SSE)</b></td><td align="left" nowrap><code>/api/mcp/sse</code></td><td align="left">Streaming MCP transport</td></tr>
   <tr><td align="left" nowrap>🤝 <b>A2A</b></td><td align="left" nowrap><code>/.well-known/agent.json</code></td><td align="left">Agent-to-agent, <b>JSON-RPC 2.0</b> + SSE, 6 skills</td></tr>
   <tr><td align="left" nowrap>🌐 <b>REST API</b></td><td align="left" nowrap><code>/v1/*</code></td><td align="left">OpenAI-compatible — chat, embeddings, images, audio, OCR</td></tr>
@@ -988,21 +988,8 @@ docker run -d --name omniroute --restart unless-stopped --stop-timeout 40 \
   -p 127.0.0.1:20128:20128 -v omniroute-data:/app/data diegosouzapw/omniroute:latest
 ```
 
-`:latest` follows the highest **published** stable SemVer. It does not track git `main`. Pin `:X.Y.Z` for GitOps. See [Docker Release Channels](docs/guides/DOCKER_GUIDE.md#release-channels).The image pins **`OMNIROUTE_MEMORY_MB=1024`**. That is enough for the dashboard and a light chat. **Coding agents** (`POST /v1/responses` from Claude Code, Codex, Grok, …) need a much larger V8 heap or the process `FATAL ERROR`s at ~12 GiB under two overlapping long contexts. Size the container above the heap (native buffers sit outside V8):
+`:latest` follows the highest **published** stable SemVer. It does not track git `main`. Pin `:X.Y.Z` for GitOps. See [Docker Release Channels](docs/guides/DOCKER_GUIDE.md#release-channels).
 
-| Workload | Heap (`-e OMNIROUTE_MEMORY_MB`) | Container (`--memory`) |
-| --- | --- | --- |
-| Dashboard / light chat | `1024` (image default) | ≥2 g |
-| One coding agent | `8192` | ≥10 g |
-| Two concurrent long `/v1/responses` | `10240`–`12288` | ≥12–16 g |
-
-```bash
-docker run -d --name omniroute --restart unless-stopped --stop-timeout 40 \
-  -e OMNIROUTE_MEMORY_MB=8192 --memory=10g \
-  -p 127.0.0.1:20128:20128 -v omniroute-data:/app/data diegosouzapw/omniroute:latest
-```
-
-Full table: [Docker Guide — runtime RAM](docs/guides/DOCKER_GUIDE.md#runtime-ram-for-coding-agents).
 > **Pre-release Docker channel:** `diegosouzapw/omniroute:next` and
 > `diegosouzapw/omniroute:next-web` follow the current default `release/v*`
 > branch. These mutable tags are intended only for testing unreleased fixes and

bin/cli/api-commands/combos.mjs

@@ -30,60 +30,20 @@ export function register_combos(parent) {
       const data = res.ok ? await res.json() : await res.text();
       emit(data, gOpts);
     });
-  tag.command("get-api-combos-id-")
-    .description("Get combo by ID")
-    .requiredOption("--id <id>", "")
-    .action(async (opts, cmd) => {
-      const gOpts = cmd.optsWithGlobals();
-      let url = "/api/combos/{id}";
-      url = url.replace("{id}", encodeURIComponent(opts.id ?? ""));
-      const res = await apiFetch(url, { method: "GET", baseUrl: gOpts.baseUrl, apiKey: gOpts.apiKey });
-      const data = res.ok ? await res.json() : await res.text();
-      emit(data, gOpts);
-    });
-  tag.command("put-api-combos-id-")
-    .description("Update combo")
-    .requiredOption("--id <id>", "")
-    .option("--body <jsonOrPath>", "JSON body or @path/to/file.json")
-    .action(async (opts, cmd) => {
-      const gOpts = cmd.optsWithGlobals();
-      let url = "/api/combos/{id}";
-      url = url.replace("{id}", encodeURIComponent(opts.id ?? ""));
-      let body;
-      if (opts.body) {
-        body = opts.body.startsWith("@")
-          ? JSON.parse(readFileSync(opts.body.slice(1), "utf8"))
-          : JSON.parse(opts.body);
-      }
-      const res = await apiFetch(url, { method: "PUT", body, baseUrl: gOpts.baseUrl, apiKey: gOpts.apiKey });
-      const data = res.ok ? await res.json() : await res.text();
-      emit(data, gOpts);
-    });
   tag.command("patch-api-combos-id-")
     .description("Update combo")
-    .requiredOption("--id <id>", "")
-    .option("--body <jsonOrPath>", "JSON body or @path/to/file.json")
     .action(async (opts, cmd) => {
       const gOpts = cmd.optsWithGlobals();
       let url = "/api/combos/{id}";
-      url = url.replace("{id}", encodeURIComponent(opts.id ?? ""));
-      let body;
-      if (opts.body) {
-        body = opts.body.startsWith("@")
-          ? JSON.parse(readFileSync(opts.body.slice(1), "utf8"))
-          : JSON.parse(opts.body);
-      }
-      const res = await apiFetch(url, { method: "PATCH", body, baseUrl: gOpts.baseUrl, apiKey: gOpts.apiKey });
+      const res = await apiFetch(url, { method: "PATCH", baseUrl: gOpts.baseUrl, apiKey: gOpts.apiKey });
       const data = res.ok ? await res.json() : await res.text();
       emit(data, gOpts);
     });
   tag.command("delete-api-combos-id-")
     .description("Delete combo")
-    .requiredOption("--id <id>", "")
     .action(async (opts, cmd) => {
       const gOpts = cmd.optsWithGlobals();
       let url = "/api/combos/{id}";
-      url = url.replace("{id}", encodeURIComponent(opts.id ?? ""));
       const res = await apiFetch(url, { method: "DELETE", baseUrl: gOpts.baseUrl, apiKey: gOpts.apiKey });
       const data = res.ok ? await res.json() : await res.text();
       emit(data, gOpts);

bin/cli/commands/combo.mjs

@@ -4,7 +4,6 @@ import { withRuntime } from "../runtime.mjs";
 import { t } from "../i18n.mjs";
 import { apiFetch } from "../api.mjs";
 import { emit } from "../output.mjs";
-import { resolveComboModels, collectModel } from "./comboModels.mjs";
 
 const VALID_STRATEGIES = [
   "priority",
@@ -126,31 +125,10 @@ export function registerCombo(program) {
         .choices(VALID_STRATEGIES)
         .default("priority")
     )
-    .option(
-      "--models <spec>",
-      "Models for the combo: comma-separated provider/model entries, or a JSON array " +
-        '(e.g. --models "openai/gpt-4o,anthropic/claude-3-opus" or ' +
-        '--models \'[{"model":"gpt-4o","providerId":"openai"}]\')'
-    )
-    .option(
-      "--model <spec>",
-      "Add one model to the combo (provider/model or bare model id) — repeatable",
-      collectModel,
-      []
-    )
     .action(async (name, opts, cmd) => {
       const globalOpts = cmd.parent.optsWithGlobals();
-      let models;
-      try {
-        models = resolveComboModels(opts);
-      } catch (err) {
-        console.error(`Error: ${err instanceof Error ? err.message : String(err)}`);
-        process.exit(1);
-        return;
-      }
       const exitCode = await runComboCreateCommand(name, opts.strategy, {
         ...opts,
-        models,
         output: globalOpts.output,
       });
       if (exitCode !== 0) process.exit(exitCode);
@@ -306,14 +284,12 @@ export async function runComboCreateCommand(name, strategy = "priority", opts =
     return 1;
   }
 
-  const models = Array.isArray(opts.models) ? opts.models : [];
-
   try {
     return await withRuntime(async ({ kind, api, db }) => {
       if (kind === "http") {
         const res = await api("/api/combos", {
           method: "POST",
-          body: { name, strategy, enabled: true, models, config: {} },
+          body: { name, strategy, enabled: true, models: [], config: {} },
           retry: false,
           acceptNotOk: true,
         });
@@ -329,7 +305,7 @@ export async function runComboCreateCommand(name, strategy = "priority", opts =
           console.error(`Combo '${name}' already exists. Delete it first.`);
           return 1;
         }
-        await db.combos.createCombo({ name, strategy, enabled: true, models, config: {} });
+        await db.combos.createCombo({ name, strategy, enabled: true, models: [], config: {} });
       }
 
       console.log(t("combo.created", { name }));

bin/cli/commands/comboModels.mjs

@@ -1,142 +0,0 @@
-// Parses the `--models` / `--model` options for `omniroute combo create` (#10954).
-//
-// Root cause of #10954: `combo create` only ever registered `--strategy`; the
-// HTTP body (POST /api/combos) and the local-db fallback (db.combos.createCombo)
-// both hardcoded `models: []`, so every combo created via the CLI came out
-// empty regardless of what the operator intended to route to.
-//
-// Accepted shapes mirror the server-side Zod union in
-// `src/shared/validation/schemas/combo.ts` (`comboModelEntry` /
-// `createComboSchema.models`) so a CLI-built payload never gets rejected by
-// the API that ultimately validates it:
-//   - a plain string ("provider/model" or a bare model id) — the server's
-//     `normalizeComboModels` (src/lib/combos/steps.ts) already splits the
-//     leading "provider/" segment off a plain string, so passing the raw
-//     token through is sufficient for the common case;
-//   - a structured `{ kind?: "model", model, providerId?, provider?, ... }`
-//     object;
-//   - a structured `{ kind: "combo-ref", comboName, ... }` object (nested
-//     combo reference).
-//
-// The CLI (bin/cli/**) ships as plain `.mjs` with relative-only imports — no
-// `@/` path aliases and no TS transpilation at runtime — so importing the
-// real Zod schema from `src/shared/validation/schemas/combo.ts` is not
-// viable here. This module instead validates the same minimal shape by hand
-// and stays a thin, independently testable unit.
-
-/**
- * Validates one already-parsed combo model entry against the shape accepted
- * by `comboModelEntry` (string | model-step | combo-ref). Throws with a
- * 1-based, human-readable position when the entry does not match.
- *
- * @param {unknown} entry
- * @param {number} index
- * @returns {string | Record<string, unknown>}
- */
-export function validateComboModelEntryShape(entry, index) {
-  const position = index + 1;
-
-  if (typeof entry === "string") {
-    const trimmed = entry.trim();
-    if (trimmed.length === 0) {
-      throw new Error(`--models entry #${position}: empty model string`);
-    }
-    if (trimmed.length > 300) {
-      throw new Error(`--models entry #${position}: model string exceeds 300 characters`);
-    }
-    return trimmed;
-  }
-
-  if (entry === null || typeof entry !== "object" || Array.isArray(entry)) {
-    throw new Error(`--models entry #${position}: must be a string or a JSON object`);
-  }
-
-  const kind = entry.kind;
-
-  if (kind === "combo-ref") {
-    if (typeof entry.comboName !== "string" || entry.comboName.trim().length === 0) {
-      throw new Error(
-        `--models entry #${position}: kind "combo-ref" requires a non-empty "comboName"`
-      );
-    }
-    return entry;
-  }
-
-  if (kind !== undefined && kind !== "model") {
-    throw new Error(`--models entry #${position}: unknown "kind" value ${JSON.stringify(kind)}`);
-  }
-
-  if (typeof entry.model !== "string" || entry.model.trim().length === 0) {
-    throw new Error(`--models entry #${position}: requires a non-empty "model"`);
-  }
-  if (entry.providerId !== undefined && typeof entry.providerId !== "string") {
-    throw new Error(`--models entry #${position}: "providerId" must be a string`);
-  }
-  if (entry.provider !== undefined && typeof entry.provider !== "string") {
-    throw new Error(`--models entry #${position}: "provider" must be a string`);
-  }
-
-  return entry;
-}
-
-/**
- * Parses one `--models` spec — either a JSON array (`--models '[{"model":"gpt-4o"}]'`)
- * or a comma-separated list of provider/model tokens
- * (`--models 'openai/gpt-4o,anthropic/claude-3-opus'`) — into an array of
- * combo model entries.
- *
- * @param {string} spec
- * @returns {Array<string | Record<string, unknown>>}
- */
-export function parseModelsSpec(spec) {
-  const trimmed = String(spec ?? "").trim();
-  if (trimmed.length === 0) return [];
-
-  if (trimmed.startsWith("[")) {
-    let parsed;
-    try {
-      parsed = JSON.parse(trimmed);
-    } catch (err) {
-      throw new Error(`--models: invalid JSON array (${err.message})`);
-    }
-    if (!Array.isArray(parsed)) {
-      throw new Error("--models: JSON value must be an array");
-    }
-    return parsed.map((entry, i) => validateComboModelEntryShape(entry, i));
-  }
-
-  return trimmed
-    .split(",")
-    .map((token) => token.trim())
-    .filter((token) => token.length > 0)
-    .map((token, i) => validateComboModelEntryShape(token, i));
-}
-
-/**
- * Resolves the final `models` array for `combo create` from Commander opts:
- * `--models <csv-or-json>` and/or repeatable `--model <spec>`.
- *
- * @param {{ models?: string, model?: string[] }} opts
- * @returns {Array<string | Record<string, unknown>>}
- */
-export function resolveComboModels(opts = {}) {
-  const result = [];
-
-  if (typeof opts.models === "string" && opts.models.trim().length > 0) {
-    result.push(...parseModelsSpec(opts.models));
-  }
-
-  if (Array.isArray(opts.model)) {
-    opts.model.forEach((token, i) => {
-      result.push(validateComboModelEntryShape(String(token).trim(), i));
-    });
-  }
-
-  return result;
-}
-
-/** Commander `collect`-style reducer for the repeatable `--model` option. */
-export function collectModel(value, previous) {
-  previous.push(value);
-  return previous;
-}

changelog.d/fixes/10736-corrupt-rotate-fence.md

@@ -1 +0,0 @@
-- **fix(db):** pause call-log rotation and record SQLITE_CORRUPT on `/api/db/health` instead of retrying writes against a malformed pager ([#10736](https://github.com/diegosouzapw/OmniRoute/issues/10736))

changelog.d/fixes/10850-readyz-alias.md

@@ -1 +0,0 @@
-- **fix(api):** alias `GET`/`HEAD` `/readyz` to `/healthz` so Kubernetes readiness probes do not 404 ([#10850](https://github.com/diegosouzapw/OmniRoute/issues/10850))

changelog.d/fixes/10940-opencode-limit-output.md

@@ -1 +0,0 @@
-- fix(cli): always emit limit.output in generated OpenCode config so schema validation passes for metadata-less models (#10940)

changelog.d/fixes/10954-combo-create-models.md

@@ -1 +0,0 @@
-- fix(cli): combo create accepts --models and no longer creates empty combos (#10954)

changelog.d/fixes/10955-cli-ref-params.md

@@ -1 +0,0 @@
-- fix(cli): resolve $ref path params and add PATCH combos requestBody in generated API commands (#10955)

changelog.d/fixes/10967-10966-combo-diag-recovery.md

@@ -1,2 +0,0 @@
-- fix(sse): combo diagnostics no longer truncate `exhausted_connection` entries to a hardcoded `provider: "unknown"` with the provider prefix eaten by an 8-char slice — the real provider id is preserved and only the connection id is truncated (#10967)
-- fix(sse): combo terminal failures caused entirely by quota/account-balance exhaustion (including a durable HTTP 403 `insufficient_quota` / `AUTHZ_INSUFFICIENT_BALANCE`) now stamp a stable `quota_exhausted` diagnostics reason with a `switch-combo` recovery hint instead of the misleading default `retry` action (#10966)

changelog.d/fixes/10976-skip-default-searxng.md

@@ -1 +0,0 @@
-- **fix(search):** skip catalog-default SearXNG `http://localhost:8888/search` so Docker/K8s search does not ECONNREFUSED then 502 into the next provider ([#10976](https://github.com/diegosouzapw/OmniRoute/issues/10976))

changelog.d/fixes/10986-reasoning-only-content.md

@@ -1 +0,0 @@
-- fix(command-code): surface reasoning-only output as content when a model emits no text-delta (#10986)

changelog.d/fixes/10988-release-v3850-quality-gates.md

@@ -1 +0,0 @@
-- **fix(ci):** clear inherited `release/v3.8.50` quality-gate reds on the X Search PR: drop the stale `copilot-m365-web.ts:330` public-creds allowlist, document six missing env vars, register four covering Stryker tap tests, prune leftover ESLint suppressions, replace the phantom `@/lib/db/connections` Utilization import with `getProviderConnectionById`, and fix open-sse/dashboard typecheck regressions in freebuff, browser-backed chat, auth, health matrix, and Monaco ([#10988](https://github.com/diegosouzapw/OmniRoute/pull/10988)).

changelog.d/fixes/10988-release-v3850-unit-shards.md

@@ -1 +0,0 @@
-- **fix(ci):** clear remaining `release/v3.8.50` unit-shard reds on the X Search PR: pin `onnxruntime-node` to the transformers 1.24.3 copy, rebaseline OpenAPI coverage, sync goldens/i18n, honor eye-hidden no-auth models across provider aliases, await rejected-request call-log writes, absorb catalog event-loop shard contention in #9147, and align inherited tests with advisory context estimates, #10501 combo terminal-status aggregation, and current catalog/auth behavior ([#10988](https://github.com/diegosouzapw/OmniRoute/pull/10988)).

changelog.d/fixes/11008-account-rotation-eviction.md

@@ -1 +0,0 @@
-- **fix(accounts):** `markCooldown` now carries the failure origin (`transient` vs `terminal`) — transient 429/network only cools down, repeated terminal failures evict and are skipped by `pickAccount` until a success or operator clear ([#11008](https://github.com/diegosouzapw/OmniRoute/pull/11008)) — thanks @maxmad64bis

changelog.d/fixes/11009-terminal-status-origin.md

@@ -1 +0,0 @@
-- **fix(providers):** route terminal `testStatus` writes (`banned`, `deactivated`, `credits_exhausted`) through a single origin-aware passage — probe failures are recorded but never deactivate the connection ([#11009](https://github.com/diegosouzapw/OmniRoute/pull/11009)) — thanks @maxmad64bis

changelog.d/fixes/11014-codex-drop-default-on.md

@@ -1 +0,0 @@
-- **fix(codex):** drop non-standard `codex.*` SSE events by default so OpenAI SDK / Codex CLI `/v1/responses` clients are not 502'd by `event: codex.rate_limits` ([#11014](https://github.com/diegosouzapw/OmniRoute/issues/11014)) — thanks @RaviTharuma

changelog.d/fixes/11016-cred-health-disable-log.md

@@ -1 +0,0 @@
-- **fix(startup):** log `Credential health scheduler disabled` when `OMNIROUTE_DISABLE_CREDENTIAL_HEALTH_CHECK` is set instead of lying with `started` ([#11016](https://github.com/diegosouzapw/OmniRoute/issues/11016)) — thanks @RaviTharuma

changelog.d/fixes/11017-rate-limit-docs.md

@@ -1 +0,0 @@
-- **docs(api-keys):** document that unset `DEFAULT_RATE_LIMIT_PER_DAY` is unlimited (#2289), not a hidden 1000/day cap ([#11017](https://github.com/diegosouzapw/OmniRoute/issues/11017)) — thanks @RaviTharuma

changelog.d/fixes/command-code-effort-capabilities.md

@@ -1 +0,0 @@
-- fix(combo): resolve effort-suffixed command-code variants (e.g. `deepseek-v4-flash-max`) to their base model for capability lookups, so tool-bearing combo requests keep the declared priority order instead of reordering behind models with confirmed capabilities

changelog.d/fixes/opencode-merge-provider-guard.md

@@ -1 +0,0 @@
-- **OpenCode config merge:** stop `mergeOpenCodeConfig` splaying a malformed `provider` block into index keys. The root was already guarded against a non-object; the `provider` branch it spreads one level down was not, so an existing `"provider": ["a", "b"]` merged to `{"0": "a", "1": "b", …}`. Its sibling `mergeOpenCodeConfigText` already refuses the same input.

changelog.d/maintenance/10778-grokbuild-suppression-fix.md

@@ -1 +0,0 @@
-- fix(quality): register GrokBuildToolCard.tsx react-hooks/set-state-in-effect suppression (dropped in #10778's uncommitted fix)

changelog.d/maintenance/10982-runtime-ram-coding-agents.md

@@ -1 +0,0 @@
-- **docs(docker):** document runtime RAM for coding-agent `/v1/responses` (image default 1 GiB heap is dashboard-only; 8–12 GiB heap for agents) ([#10982](https://github.com/diegosouzapw/OmniRoute/issues/10982))

changelog.d/maintenance/11024-n-instance-scale-out.md

@@ -1 +0,0 @@
-- **docs(docker):** document N independent `DATA_DIR`s as the supported large `/v1/responses` scale-out (one V8 heap ≠ host RAM; do not `replicas>1` on one SQLite file) ([#11024](https://github.com/diegosouzapw/OmniRoute/issues/11024)) — thanks @RaviTharuma

config/quality/eslint-suppressions.json

@@ -291,6 +291,109 @@
   "src/app/(dashboard)/dashboard/HomePageClient.tsx": {
     "react-hooks/exhaustive-deps": {
       "count": 1
+    },
+    "react-hooks/set-state-in-effect": {
+      "count": 2
+    }
+  },
+  "src/app/(dashboard)/dashboard/a2a/page.tsx": {
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    }
+  },
+  "src/app/(dashboard)/dashboard/acp-agents/page.tsx": {
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    }
+  },
+  "src/app/(dashboard)/dashboard/activity/ActivityFeedClient.tsx": {
+    "react-hooks/purity": {
+      "count": 1
+    },
+    "react-hooks/refs": {
+      "count": 1
+    },
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    }
+  },
+  "src/app/(dashboard)/dashboard/analytics/CacheHealthTab.tsx": {
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    }
+  },
+  "src/app/(dashboard)/dashboard/analytics/ComboHealthTab.tsx": {
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    }
+  },
+  "src/app/(dashboard)/dashboard/analytics/ProviderUtilizationTab.tsx": {
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    }
+  },
+  "src/app/(dashboard)/dashboard/analytics/RouteExplainabilityTab.tsx": {
+    "react-hooks/set-state-in-effect": {
+      "count": 2
+    }
+  },
+  "src/app/(dashboard)/dashboard/api-manager/ApiManagerPageClient.tsx": {
+    "react-hooks/immutability": {
+      "count": 4
+    },
+    "react-hooks/preserve-manual-memoization": {
+      "count": 2
+    },
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    }
+  },
+  "src/app/(dashboard)/dashboard/audit/A2aAuditTab.tsx": {
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    }
+  },
+  "src/app/(dashboard)/dashboard/audit/ComplianceTab.tsx": {
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    }
+  },
+  "src/app/(dashboard)/dashboard/audit/McpAuditTab.tsx": {
+    "react-hooks/set-state-in-effect": {
+      "count": 2
+    }
+  },
+  "src/app/(dashboard)/dashboard/batch/components/wizard/CostEstimateStep.tsx": {
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    }
+  },
+  "src/app/(dashboard)/dashboard/batch/components/wizard/JsonlValidationStep.tsx": {
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    }
+  },
+  "src/app/(dashboard)/dashboard/batch/files/page.tsx": {
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    }
+  },
+  "src/app/(dashboard)/dashboard/cache/components/CacheEntriesTab.tsx": {
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    }
+  },
+  "src/app/(dashboard)/dashboard/cache/components/ReasoningCacheTab.tsx": {
+    "react-hooks/purity": {
+      "count": 1
+    },
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    }
+  },
+  "src/app/(dashboard)/dashboard/cache/page.tsx": {
+    "react-hooks/set-state-in-effect": {
+      "count": 1
     }
   },
   "src/app/(dashboard)/dashboard/cli-agents/CliAgentsPageClient.tsx": {
@@ -301,6 +404,119 @@
   "src/app/(dashboard)/dashboard/cli-code/components/AntigravityToolCard.tsx": {
     "react-hooks/exhaustive-deps": {
       "count": 1
+    },
+    "react-hooks/immutability": {
+      "count": 3
+    },
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    }
+  },
+  "src/app/(dashboard)/dashboard/cli-code/components/ClaudeClassifierCompatToggle.tsx": {
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    }
+  },
+  "src/app/(dashboard)/dashboard/cli-code/components/ClaudeToolCard.tsx": {
+    "react-hooks/immutability": {
+      "count": 3
+    },
+    "react-hooks/set-state-in-effect": {
+      "count": 2
+    }
+  },
+  "src/app/(dashboard)/dashboard/cli-code/components/CliProfileAutoSyncToggles.tsx": {
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    }
+  },
+  "src/app/(dashboard)/dashboard/cli-code/components/ClineToolCard.tsx": {
+    "react-hooks/immutability": {
+      "count": 3
+    },
+    "react-hooks/set-state-in-effect": {
+      "count": 2
+    }
+  },
+  "src/app/(dashboard)/dashboard/cli-code/components/CliproxyapiToolCard.tsx": {
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    }
+  },
+  "src/app/(dashboard)/dashboard/cli-code/components/CodexToolCard.tsx": {
+    "react-hooks/immutability": {
+      "count": 4
+    },
+    "react-hooks/set-state-in-effect": {
+      "count": 2
+    }
+  },
+  "src/app/(dashboard)/dashboard/cli-code/components/DroidToolCard.tsx": {
+    "react-hooks/immutability": {
+      "count": 3
+    },
+    "react-hooks/set-state-in-effect": {
+      "count": 2
+    }
+  },
+  "src/app/(dashboard)/dashboard/cli-code/components/HermesAgentToolCard.tsx": {
+    "react-hooks/immutability": {
+      "count": 1
+    },
+    "react-hooks/purity": {
+      "count": 1
+    },
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    }
+  },
+  "src/app/(dashboard)/dashboard/cli-code/components/KiloToolCard.tsx": {
+    "react-hooks/immutability": {
+      "count": 3
+    },
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    }
+  },
+  "src/app/(dashboard)/dashboard/cli-code/components/OpenClawToolCard.tsx": {
+    "react-hooks/immutability": {
+      "count": 3
+    },
+    "react-hooks/set-state-in-effect": {
+      "count": 2
+    }
+  },
+  "src/app/(dashboard)/dashboard/combos/ComboControlCenterClient.tsx": {
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    }
+  },
+  "src/app/(dashboard)/dashboard/combos/page.tsx": {
+    "react-hooks/immutability": {
+      "count": 1
+    },
+    "react-hooks/set-state-in-effect": {
+      "count": 7
+    }
+  },
+  "src/app/(dashboard)/dashboard/conductor/ConductorPageClient.tsx": {
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    }
+  },
+  "src/app/(dashboard)/dashboard/conductor/FaroChat.tsx": {
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    }
+  },
+  "src/app/(dashboard)/dashboard/conversations/page.tsx": {
+    "react-hooks/set-state-in-effect": {
+      "count": 2
+    }
+  },
+  "src/app/(dashboard)/dashboard/costs/components/ApiKeyUsageLimitCard.tsx": {
+    "react-hooks/set-state-in-effect": {
+      "count": 1
     }
   },
   "src/app/(dashboard)/dashboard/costs/costExplorerUtils.ts": {
@@ -308,11 +524,258 @@
       "count": 1
     }
   },
+  "src/app/(dashboard)/dashboard/costs/quota-share/components/PoolWizard.tsx": {
+    "react-hooks/set-state-in-effect": {
+      "count": 3
+    }
+  },
+  "src/app/(dashboard)/dashboard/costs/quota-share/hooks/usePoolUsage.ts": {
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    }
+  },
+  "src/app/(dashboard)/dashboard/costs/quota-share/hooks/usePools.ts": {
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    }
+  },
+  "src/app/(dashboard)/dashboard/costs/useApiKeyUsageLimits.ts": {
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    }
+  },
+  "src/app/(dashboard)/dashboard/discovery/DiscoveryPageClient.tsx": {
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    }
+  },
+  "src/app/(dashboard)/dashboard/endpoint/EndpointPageClient.tsx": {
+    "react-hooks/immutability": {
+      "count": 3
+    }
+  },
+  "src/app/(dashboard)/dashboard/endpoint/components/A2ADashboard.tsx": {
+    "react-hooks/set-state-in-effect": {
+      "count": 2
+    }
+  },
+  "src/app/(dashboard)/dashboard/endpoint/components/MCPDashboard.tsx": {
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    }
+  },
+  "src/app/(dashboard)/dashboard/endpoint/components/NotionSourceCard.tsx": {
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    }
+  },
+  "src/app/(dashboard)/dashboard/endpoint/components/ObsidianSourceCard.tsx": {
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    }
+  },
+  "src/app/(dashboard)/dashboard/free-provider-rankings/page.tsx": {
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    }
+  },
+  "src/app/(dashboard)/dashboard/health/ProviderHealthAutopilotCard.tsx": {
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    }
+  },
+  "src/app/(dashboard)/dashboard/health/ProviderHealthMatrixCard.tsx": {
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    }
+  },
+  "src/app/(dashboard)/dashboard/health/TelemetryCard.tsx": {
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    }
+  },
+  "src/app/(dashboard)/dashboard/mcp/page.tsx": {
+    "react-hooks/set-state-in-effect": {
+      "count": 2
+    }
+  },
+  "src/app/(dashboard)/dashboard/memory/components/EditMemoryModal.tsx": {
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    }
+  },
+  "src/app/(dashboard)/dashboard/memory/components/QdrantConfigCard.tsx": {
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    }
+  },
+  "src/app/(dashboard)/dashboard/memory/components/tabs/MemoriesTab.tsx": {
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    }
+  },
+  "src/app/(dashboard)/dashboard/memory/hooks/useEngineStatus.ts": {
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    }
+  },
+  "src/app/(dashboard)/dashboard/memory/hooks/useMemorySettings.ts": {
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    }
+  },
   "src/app/(dashboard)/dashboard/playground/components/tabs/ApiTab.tsx": {
     "react-hooks/exhaustive-deps": {
       "count": 1
     }
   },
+  "src/app/(dashboard)/dashboard/plugins/[name]/config/page.tsx": {
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    }
+  },
+  "src/app/(dashboard)/dashboard/plugins/page.tsx": {
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    }
+  },
+  "src/app/(dashboard)/dashboard/provider-stats/page.tsx": {
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    },
+    "react-hooks/static-components": {
+      "count": 7
+    }
+  },
+  "src/app/(dashboard)/dashboard/providers/[id]/components/CustomModelsSection.tsx": {
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    }
+  },
+  "src/app/(dashboard)/dashboard/providers/[id]/components/ModelCompatPopover.tsx": {
+    "react-hooks/refs": {
+      "count": 4
+    },
+    "react-hooks/set-state-in-effect": {
+      "count": 3
+    }
+  },
+  "src/app/(dashboard)/dashboard/providers/[id]/components/ProviderCcAliasSection.tsx": {
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    }
+  },
+  "src/app/(dashboard)/dashboard/providers/[id]/components/ProviderInterceptionSection.tsx": {
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    }
+  },
+  "src/app/(dashboard)/dashboard/providers/[id]/components/ProviderParamFilterSection.tsx": {
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    }
+  },
+  "src/app/(dashboard)/dashboard/providers/[id]/components/modals/EditCompatibleNodeModal.tsx": {
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    }
+  },
+  "src/app/(dashboard)/dashboard/providers/[id]/components/modals/EditConnectionModal.tsx": {
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    }
+  },
+  "src/app/(dashboard)/dashboard/providers/[id]/hooks/useProviderConnections.ts": {
+    "react-hooks/set-state-in-effect": {
+      "count": 2
+    }
+  },
+  "src/app/(dashboard)/dashboard/providers/[id]/hooks/useProviderSettings.ts": {
+    "react-hooks/set-state-in-effect": {
+      "count": 2
+    }
+  },
+  "src/app/(dashboard)/dashboard/providers/components/AddCompatibleProviderModal.tsx": {
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    }
+  },
+  "src/app/(dashboard)/dashboard/providers/hooks/useProviderModels.ts": {
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    }
+  },
+  "src/app/(dashboard)/dashboard/providers/hooks/useProviderUrlFilters.ts": {
+    "react-hooks/set-state-in-effect": {
+      "count": 2
+    }
+  },
+  "src/app/(dashboard)/dashboard/providers/hooks/useRiskAcknowledged.ts": {
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    }
+  },
+  "src/app/(dashboard)/dashboard/providers/page.tsx": {
+    "react-hooks/set-state-in-effect": {
+      "count": 2
+    }
+  },
+  "src/app/(dashboard)/dashboard/providers/services/components/DarioAccountPanel.tsx": {
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    }
+  },
+  "src/app/(dashboard)/dashboard/providers/services/components/NinerouterModelList.tsx": {
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    }
+  },
+  "src/app/(dashboard)/dashboard/radar/RadarCatalogTable.tsx": {
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    }
+  },
+  "src/app/(dashboard)/dashboard/radar/intel/page.tsx": {
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    }
+  },
+  "src/app/(dashboard)/dashboard/radar/page.tsx": {
+    "react-hooks/set-state-in-effect": {
+      "count": 2
+    }
+  },
+  "src/app/(dashboard)/dashboard/radar/setup/page.tsx": {
+    "react-hooks/preserve-manual-memoization": {
+      "count": 1
+    },
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    }
+  },
+  "src/app/(dashboard)/dashboard/relay/RelayProxyClient.tsx": {
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    }
+  },
+  "src/app/(dashboard)/dashboard/resilience/connections/components/ResilienceConnectionsClient.tsx": {
+    "react-hooks/purity": {
+      "count": 1
+    },
+    "react-hooks/refs": {
+      "count": 1
+    }
+  },
+  "src/app/(dashboard)/dashboard/runtime/components/ModelCooldownsCard.tsx": {
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    }
+  },
+  "src/app/(dashboard)/dashboard/settings/components/AccessTokensTab.tsx": {
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    }
+  },
   "src/app/(dashboard)/dashboard/settings/components/AppearanceTab.tsx": {
     "@next/next/no-img-element": {
       "count": 4
@@ -321,16 +784,75 @@
   "src/app/(dashboard)/dashboard/settings/components/AuthzSection.tsx": {
     "no-restricted-syntax": {
       "count": 1
+    },
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    }
+  },
+  "src/app/(dashboard)/dashboard/settings/components/FallbackChainsEditor.tsx": {
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    }
+  },
+  "src/app/(dashboard)/dashboard/settings/components/IPFilterSection.tsx": {
+    "react-hooks/immutability": {
+      "count": 1
     }
   },
   "src/app/(dashboard)/dashboard/settings/components/MitmProxyTab.tsx": {
     "@next/next/no-html-link-for-pages": {
       "count": 1
+    },
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    }
+  },
+  "src/app/(dashboard)/dashboard/settings/components/ModelCapabilityOverridesTab.tsx": {
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    }
+  },
+  "src/app/(dashboard)/dashboard/settings/components/ModelsDevSyncTab.tsx": {
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    }
+  },
+  "src/app/(dashboard)/dashboard/settings/components/OneproxyTab.tsx": {
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    }
+  },
+  "src/app/(dashboard)/dashboard/settings/components/PayloadRulesTab.tsx": {
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    }
+  },
+  "src/app/(dashboard)/dashboard/settings/components/PoliciesPanel.tsx": {
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    }
+  },
+  "src/app/(dashboard)/dashboard/settings/components/PricingTab.tsx": {
+    "react-hooks/set-state-in-effect": {
+      "count": 2
     }
   },
   "src/app/(dashboard)/dashboard/settings/components/ProviderAccountRoutingCard.tsx": {
     "react-hooks/exhaustive-deps": {
       "count": 1
+    },
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    }
+  },
+  "src/app/(dashboard)/dashboard/settings/components/ResilienceTab.tsx": {
+    "react-hooks/set-state-in-effect": {
+      "count": 7
+    }
+  },
+  "src/app/(dashboard)/dashboard/settings/components/RoutingStrategyCard.tsx": {
+    "react-hooks/set-state-in-effect": {
+      "count": 1
     }
   },
   "src/app/(dashboard)/dashboard/settings/components/SessionInfoCard.tsx": {
@@ -338,11 +860,92 @@
       "count": 1
     }
   },
+  "src/app/(dashboard)/dashboard/settings/components/SystemStorageTab.tsx": {
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    }
+  },
+  "src/app/(dashboard)/dashboard/settings/components/proxy/GlobalConfigTab.tsx": {
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    }
+  },
+  "src/app/(dashboard)/dashboard/settings/components/proxy/SubscriptionTab.tsx": {
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    }
+  },
   "src/app/(dashboard)/dashboard/tools/agent-bridge/components/AgentList.tsx": {
     "no-restricted-syntax": {
       "count": 3
     }
   },
+  "src/app/(dashboard)/dashboard/tools/agent-bridge/components/ModelSelectorModal.tsx": {
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    }
+  },
+  "src/app/(dashboard)/dashboard/tools/agent-bridge/components/SetupWizard.tsx": {
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    }
+  },
+  "src/app/(dashboard)/dashboard/tools/traffic-inspector/components/CustomHostsManager.tsx": {
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    }
+  },
+  "src/app/(dashboard)/dashboard/translator/components/MonitorTab.tsx": {
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    }
+  },
+  "src/app/(dashboard)/dashboard/usage/components/EvalsTab.tsx": {
+    "react-hooks/set-state-in-effect": {
+      "count": 2
+    }
+  },
+  "src/app/(dashboard)/dashboard/usage/components/ProviderLimits/useCodexResetCreditRedemption.ts": {
+    "react-hooks/immutability": {
+      "count": 2
+    }
+  },
+  "src/app/(dashboard)/dashboard/usage/components/RateLimitStatus.tsx": {
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    }
+  },
+  "src/app/(dashboard)/dashboard/usage/components/SessionsTab.tsx": {
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    }
+  },
+  "src/app/(dashboard)/dashboard/webhooks/WebhooksPageClient.tsx": {
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    }
+  },
+  "src/app/(dashboard)/dashboard/webhooks/components/AddWebhookWizard.tsx": {
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    }
+  },
+  "src/app/(dashboard)/dashboard/webhooks/components/WebhookDeliveriesPanel.tsx": {
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    }
+  },
+  "src/app/(dashboard)/home/ProviderQuotaWidget.tsx": {
+    "react-hooks/purity": {
+      "count": 1
+    },
+    "react-hooks/refs": {
+      "count": 1
+    },
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    }
+  },
   "src/app/(dashboard)/home/page.tsx": {
     "no-restricted-imports": {
       "count": 1
@@ -808,6 +1411,7 @@
       "count": 1
     }
   },
+
   "src/app/api/settings/route.ts": {
     "no-restricted-imports": {
       "count": 1
@@ -988,6 +1592,16 @@
       "count": 1
     }
   },
+  "src/app/global-error.tsx": {
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    }
+  },
+  "src/app/status/page.tsx": {
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    }
+  },
   "src/domain/costRules.ts": {
     "no-restricted-syntax": {
       "count": 1
@@ -1256,14 +1870,55 @@
       "count": 1
     }
   },
+  "src/shared/components/CursorAuthModal.tsx": {
+    "react-hooks/exhaustive-deps": {
+      "count": 1
+    }
+  },
+  "src/shared/components/KiroAuthModal.tsx": {
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    }
+  },
   "src/shared/components/LanguageSelector.tsx": {
     "@next/next/no-img-element": {
       "count": 1
     }
   },
+  "src/shared/components/ModelSelectModal.tsx": {
+    "react-hooks/set-state-in-effect": {
+      "count": 4
+    }
+  },
+  "src/shared/components/OAuthModal.tsx": {
+    "react-hooks/set-state-in-effect": {
+      "count": 4
+    }
+  },
+  "src/shared/components/PricingModal.tsx": {
+    "react-hooks/immutability": {
+      "count": 1
+    }
+  },
   "src/shared/components/ProxyConfigModal.tsx": {
     "react-hooks/exhaustive-deps": {
       "count": 1
+    },
+    "react-hooks/immutability": {
+      "count": 1
+    },
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    }
+  },
+  "src/shared/components/ReasoningRoutingRules.tsx": {
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    }
+  },
+  "src/shared/components/RequestLoggerDetail.sections.tsx": {
+    "react-hooks/set-state-in-effect": {
+      "count": 1
     }
   },
   "src/shared/components/RequestLoggerV2.tsx": {
@@ -1274,6 +1929,27 @@
   "src/shared/components/Sidebar.tsx": {
     "@next/next/no-img-element": {
       "count": 1
+    },
+    "react-hooks/set-state-in-effect": {
+      "count": 2
+    }
+  },
+  "src/shared/components/UsageStats.tsx": {
+    "react-hooks/preserve-manual-memoization": {
+      "count": 1
+    },
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    }
+  },
+  "src/shared/components/analytics/useProviderDailyUsage.ts": {
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    }
+  },
+  "src/shared/components/compression/ComboCompressionModeSelect.tsx": {
+    "react-hooks/set-state-in-effect": {
+      "count": 1
     }
   },
   "src/shared/contracts/quota.ts": {
@@ -1281,6 +1957,11 @@
       "count": 1
     }
   },
+  "src/shared/hooks/cli/useToolBatchStatuses.ts": {
+    "react-hooks/set-state-in-effect": {
+      "count": 1
+    }
+  },
   "src/shared/services/apiKeyResolver.ts": {
     "no-restricted-imports": {
       "count": 1
@@ -1601,6 +2282,7 @@
       "count": 11
     }
   },
+
   "tests/unit/auth-ollama-cloud-per-model-403-3027.test.ts": {
     "@typescript-eslint/no-explicit-any": {
       "count": 11
@@ -2479,6 +3161,7 @@
       "count": 12
     }
   },
+
   "tests/unit/management-password.test.ts": {
     "@typescript-eslint/no-explicit-any": {
       "count": 4
@@ -3259,4 +3942,4 @@
       "count": 5
     }
   }
-}
+}

config/quality/file-size-baseline.json

@@ -455,10 +455,9 @@
     "src/sse/handlers/chatHelpers.ts": 1019,
     "src/shared/middleware/chatBodyAdmission.ts": 1005,
     "_rebaseline_2026_08_20_10668_tabitoken_gateway": "#10668 (yawar-aquil) own catalog growth: src/shared/constants/providers/apikey/gateways.ts 1268->1283 (+15, entirely this PR diff -- one new tabitoken gateway entry, data lines only; base moved from 1255 to 1268 via other merges since the PR forked). Not combination drift: reproducible on the PR branch alone, so the WS5.5 release-captain rule does not apply. Extraction is not available -- the file is pure data (own header: \"Pure data; merged by apikey/index.ts via spread\") and already split into 6 family files under apikey/. Same precedent as _rebaseline_2026_08_14_imagetotext_servicekinds (#10275/#10291, gateways.ts 1250->1255, data lines only) and _rebaseline_2026_08_11_v3850_merge_storm_provider_registry (owner-authorized for this same file).",
-    "open-sse/executors/commandCode.ts": 1059,
+    "open-sse/executors/commandCode.ts": 1038,
     "_rebaseline_2026_08_21_10859_vision_bridge_catalog": "#10859 own growth (Vision Bridge fixes #10808/#10809): src/lib/modelCapabilities.ts 1006->1016 (+10, cmd/gpt-5.3-codex* text-only capability resolution) and open-sse/executors/commandCode.ts 988->1023 (+35, Command Code wire-model normalization for bare ids + reasoning field fallback for opencode-routed gateways). Cohesive bug fixes at the existing capability-resolution / executor chokepoints; not extractable mid-fix. Covered by tests/unit/model-capabilities-command-code-codex-textonly-10703.test.ts, tests/unit/command-code-vision.test.ts, tests/unit/opencode-mimo-reasoning-details-nonstream.test.ts. Pushed directly to release (own-session miss: the original rebaseline was made in a throwaway validation worktree and never landed on the PR branch or the release before merge).",
-    "_rebaseline_2026_08_21_10907_sticky_pin_clear": "#10907 own growth: open-sse/executors/commandCode.ts 1023->1038 (+15, effort-suffix sanitization threading for the sticky-pin-clear fix). Cohesive change at the existing executor chokepoint. Covered by tests/unit/command-code-executor.test.ts.",
-    "_rebaseline_2026_08_21_10986_reasoning_only_content": "#10986 own growth: open-sse/executors/commandCode.ts 1038->1059 (+21, reasoning-only content fallback — when upstream emits only reasoning-delta events and never a text-delta, surface the reasoning text as message.content in createJsonResponse and emit a synthetic content delta in createStreamResponse). Cohesive bug fix at the existing executor chokepoint (mirrors precedent style of #10907/#10859). Covered by tests/unit/command-code-executor.test.ts (2 new cases: non-stream + streaming)."
+    "_rebaseline_2026_08_21_10907_sticky_pin_clear": "#10907 own growth: open-sse/executors/commandCode.ts 1023->1038 (+15, effort-suffix sanitization threading for the sticky-pin-clear fix). Cohesive change at the existing executor chokepoint. Covered by tests/unit/command-code-executor.test.ts."
   },
   "_rebaseline_base_2026_08_10_proxyfetch": "Base-red fix (green-prs sweep, issue #9985): open-sse/utils/proxyFetch.ts 1207 > cap 1000 — new proxied-TLS fetch helper introduced by the Fal reference-image work. Owner-authorized quick rebaseline to green; structural slim tracked for v3.9.0.",
   "_rebaseline_2026_07_27_v3849_train2": "Merge-train 2 (7 PRs) — owner-approved 2026-07-27. Single entry: chatCore.ts 4955->5006 (#8595, Responses multi-turn image compaction before the context hard-reject). Genuine irreducible growth at the existing compaction chokepoint in handleChatCore — the PR adds a last-resort retry against the concrete budget plus the estimateFinalInputTokens helper, both wired at the pre-existing call site rather than a new branch. Covered by tests/unit/8560-responses-image-compaction.test.ts (4 tests).",

config/quality/quality-baseline.json

@@ -82,10 +82,9 @@
       "tightenSlack": 10
     },
     "openapiCoverage.pct": {
-      "value": 38.4,
+      "value": 39.2,
       "direction": "up",
       "eps": 0.5,
-      "_rebaseline_2026_08_21_v3850_cycle_drift": "39.2 -> 38.4. Measured locally and in CI collect-metrics on release/v3.8.50 (260/677 implemented routes documented). Cycle added internal/dashboard routes faster than docs/openapi.yaml; documenting LOCAL_ONLY catch-all and service-management paths in the public spec would be gaming (same class as v3.8.34/v3.8.39/v3.8.47). This PR (#10988) adds 0 API routes.",
       "_tighten_2026_08_06_v3850_sweepreds": "38.0 -> 39.2 (aperto EXIGIDO pelo step 'Require-tighten (blocking)', que estava vermelho em ~60 PRs abertas de release/v3.8.50 — base-red herdado, nao defeito das PRs). A cobertura melhorou no ciclo porque as rotas novas entraram documentadas. 39.2 = valor medido pelo CI Quality Ratchet no run 31088889488; o tip puro 2ddbbc61a6 mede 39.3 localmente (npm run check:openapi-coverage: 247/628 rotas), entao 39.2 e o valor conservador dos dois. Aperto = gate mais ESTRITO, nunca mascaramento.",
       "_tighten_2026_07_04_v3844_release": "36.9 -> 39.3 (aperto exigido pelo --require-tighten no PR de release #5925). A cobertura OpenAPI melhorou no ciclo (9 rotas documentadas em 8fb020676 + as rotas novas de #5939/#5817/#6034/#5998 documentadas junto das features). 39.3 = valor medido pelo CI Quality Ratchet no run 28708141003 (tip 00c55afcb).",
       "_rebaseline_2026_06_28_v3839_release": "37.8 -> 36.9 (-0.9, beyond the 0.5 eps). v3.8.39 cycle drift surfaced ONLY on the release PR (the openapi-coverage ratchet does NOT run on PR->release fast-gates). The cycle added API/internal routes (antigravity paste-credentials onboarding, CCR ranged/grep/stats retrieve params, mcp 404 session handling) faster than docs/openapi.yaml coverage; documenting LOCAL_ONLY/internal onboarding routes in the PUBLIC spec would be gaming (same precedent as _rebaseline_2026_06_18_v3828_cycle_close). Measured by CI collect-metrics (run 28317145160) = 36.9. My release-finalize tree touches no routes (only the openapi.yaml version bump). Raising coverage by documenting public routes is tracked as follow-up doc debt.",

docs/README.md

@@ -34,7 +34,7 @@ Simple guides for using OmniRoute — no technical background needed.
 - [USAGE_QUOTA_GUIDE.md](guides/USAGE_QUOTA_GUIDE.md) — usage, quota & spend tracking.
 - [COST_TRACKING.md](guides/COST_TRACKING.md) — cost and spend tracking.
 - [FREE_PROVIDER_RANKINGS.md](guides/FREE_PROVIDER_RANKINGS.md) — free provider rankings (Arena ELO).
-- [DOCKER_GUIDE.md](guides/DOCKER_GUIDE.md) — running OmniRoute under Docker, including runtime RAM for coding agents.
+- [DOCKER_GUIDE.md](guides/DOCKER_GUIDE.md) — running OmniRoute under Docker.
 - [ELECTRON_GUIDE.md](guides/ELECTRON_GUIDE.md) — desktop (Electron) builds.
 - [TERMUX_GUIDE.md](guides/TERMUX_GUIDE.md) — running on Android via Termux.
 - [PWA_GUIDE.md](guides/PWA_GUIDE.md) — installing the dashboard as a PWA.

docs/architecture/ARCHITECTURE.md

@@ -1131,6 +1131,7 @@ Environment variables actively used by code:
 
 - App/auth: `JWT_SECRET`, `INITIAL_PASSWORD`
 - Storage: `DATA_DIR`
+- Compatible node behavior: `ALLOW_MULTI_CONNECTIONS_PER_COMPAT_NODE`
 - Optional storage base override (Linux/macOS when `DATA_DIR` unset): `XDG_CONFIG_HOME`
 - Security hashing: `API_KEY_SECRET`, `MACHINE_ID_SALT`
 - Logging: `APP_LOG_TO_FILE`, `APP_LOG_RETENTION_DAYS`, `CALL_LOG_RETENTION_DAYS`

docs/diagrams/cli-terminal.svg

@@ -1,6 +1,6 @@
-<svg viewBox="0 0 1200 350" xmlns="http://www.w3.org/2000/svg" role="img" aria-label="Animated terminal demoing the OmniRoute CLI: omniroute providers list (348 providers registered, anthropic, codex, glm, kimi shown active), omniroute combo list (always-on priority, cost-saver, fusion-panel, context-relay) and omniroute health (healthy, 18412 requests in 24h, p95 412ms, circuit breakers 24 closed, 1 half-open, 0 open), cycling over the 80+ command surface: providers, oauth, keys, combo, nodes, models, cache, compression, cost, usage, quota, health, resilience, telemetry, logs, audit, mcp, a2a, cloud, memory, skills, eval, doctor, repl, tunnel, backup, sync, webhooks, policy, pricing, translator, simulate and more.">
+<svg viewBox="0 0 1200 350" xmlns="http://www.w3.org/2000/svg" role="img" aria-label="Animated terminal demoing the OmniRoute CLI: omniroute providers list (346 providers registered, anthropic, codex, glm, kimi shown active), omniroute combo list (always-on priority, cost-saver, fusion-panel, context-relay) and omniroute health (healthy, 18412 requests in 24h, p95 412ms, circuit breakers 24 closed, 1 half-open, 0 open), cycling over the 80+ command surface: providers, oauth, keys, combo, nodes, models, cache, compression, cost, usage, quota, health, resilience, telemetry, logs, audit, mcp, a2a, cloud, memory, skills, eval, doctor, repl, tunnel, backup, sync, webhooks, policy, pricing, translator, simulate and more.">
 <desc>Compact animated terminal cycling three real OmniRoute CLI commands with a typewriter effect and a scrolling subcommand ticker; the first frame shows the completed providers-list screen.</desc>
-<defs><clipPath id="tickerClip"><rect x="12" y="304" width="1176" height="40"/></clipPath><clipPath id="tw0"><rect x="64" y="46" height="26" width="0"><animate attributeName="width" calcMode="discrete" values="0;31;61;92;122;153;184;214;245;245" keyTimes="0;0.012;0.018;0.024;0.030;0.036;0.042;0.048;0.054;1" dur="18s" repeatCount="indefinite"/></rect></clipPath><clipPath id="tw1"><rect x="64" y="46" height="26" width="0"><animate attributeName="width" calcMode="discrete" values="0;26;51;76;102;128;153;178;204;204" keyTimes="0;0.348;0.351;0.357;0.363;0.369;0.375;0.381;0.387;1" dur="18s" repeatCount="indefinite"/></rect></clipPath><clipPath id="tw2"><rect x="64" y="46" height="26" width="0"><animate attributeName="width" calcMode="discrete" values="0;20;41;61;82;102;122;143;163;163" keyTimes="0;0.678;0.684;0.690;0.696;0.702;0.708;0.714;0.720;1" dur="18s" repeatCount="indefinite"/></rect></clipPath></defs>
+<defs><clipPath id="tickerClip"><rect x="12" y="304" width="1176" height="40"/></clipPath><clipPath id="tw0"><rect x="64" y="46" height="26" width="0"><animate attributeName="width" calcMode="discrete" values="0;31;61;92;122;153;184;214;245;245" keyTimes="0;0.012;0.018;0.024;0.030;0.036;0.042;0.048;0.054;1" dur="18s" repeatCount="indefinite"/></rect></clipPath><clipPath id="tw1"><rect x="64" y="46" height="26" width="0"><animate attributeName="width" calcMode="discrete" values="0;26;51;76;102;128;153;178;204;204" keyTimes="0;0.346;0.351;0.357;0.363;0.369;0.375;0.381;0.387;1" dur="18s" repeatCount="indefinite"/></rect></clipPath><clipPath id="tw2"><rect x="64" y="46" height="26" width="0"><animate attributeName="width" calcMode="discrete" values="0;20;41;61;82;102;122;143;163;163" keyTimes="0;0.678;0.684;0.690;0.696;0.702;0.708;0.714;0.720;1" dur="18s" repeatCount="indefinite"/></rect></clipPath></defs>
 <rect width="1200" height="350" fill="#0d1117"/>
 <rect x="0" y="0" width="1200" height="34" fill="#161b22"/>
 <path d="M 0 34 L 1200 34" stroke="#ffffff" stroke-opacity="0.08" stroke-width="1"/>
@@ -16,12 +16,12 @@
 </rect>
 <text x="40" y="100" font-weight="700" fill="#38bdf8" opacity="0"><animate attributeName="opacity" calcMode="discrete" values="0;0;1" keyTimes="0;0.045;0.047" dur="18s" repeatCount="indefinite"/>OmniRoute Providers</text><text x="40" y="128" fill="#a1a1aa" opacity="0"><animate attributeName="opacity" calcMode="discrete" values="0;0;1" keyTimes="0;0.053;0.055" dur="18s" repeatCount="indefinite"/>1f3a9c2e&#160;&#160;anthropic&#160;&#160;&#160;Claude Max 20x&#160;&#160;&#160;&#160;<tspan fill='#22c55e'>active</tspan></text><text x="40" y="154" fill="#a1a1aa" opacity="0"><animate attributeName="opacity" calcMode="discrete" values="0;0;1" keyTimes="0;0.061;0.063" dur="18s" repeatCount="indefinite"/>8c2d5b1a&#160;&#160;codex&#160;&#160;&#160;&#160;&#160;&#160;&#160;Codex Pro (team)&#160;&#160;<tspan fill='#22c55e'>active</tspan></text><text x="40" y="180" fill="#a1a1aa" opacity="0"><animate attributeName="opacity" calcMode="discrete" values="0;0;1" keyTimes="0;0.069;0.07100000000000001" dur="18s" repeatCount="indefinite"/>f4e0a97b&#160;&#160;glm&#160;&#160;&#160;&#160;&#160;&#160;&#160;&#160;&#160;GLM Coding Plan&#160;&#160;&#160;<tspan fill='#22c55e'>active</tspan></text><text x="40" y="206" fill="#a1a1aa" opacity="0"><animate attributeName="opacity" calcMode="discrete" values="0;0;1" keyTimes="0;0.077;0.079" dur="18s" repeatCount="indefinite"/>03bd6e5f&#160;&#160;kimi&#160;&#160;&#160;&#160;&#160;&#160;&#160;&#160;Kimi K2 free&#160;&#160;&#160;&#160;&#160;&#160;<tspan fill='#22c55e'>active</tspan></text><text x="40" y="232" fill="#71717a" opacity="0"><animate attributeName="opacity" calcMode="discrete" values="0;0;1" keyTimes="0;0.085;0.08700000000000001" dur="18s" repeatCount="indefinite"/>&#8230; 334 more providers</text>
 </g><g opacity="0" font-family="Consolas, 'Courier New', monospace" font-size="17">
-<animate attributeName="opacity" values="0;0;1;1;0;0" keyTimes="0;0.333;0.34800000000000003;0.648;0.663;1" dur="18s" repeatCount="indefinite"/>
+<animate attributeName="opacity" values="0;0;1;1;0;0" keyTimes="0;0.333;0.34600000000000003;0.648;0.663;1" dur="18s" repeatCount="indefinite"/>
 <text x="40" y="66" fill="#22c55e">$</text>
 <g clip-path="url(#tw1)"><text x="64" y="66" fill="#F7F6FC">omniroute combo list</text></g>
 <rect y="52" width="9" height="20" fill="#a1a1aa" opacity="0">
-  <animate attributeName="x" calcMode="discrete" values="64;90;115;140;166;192;217;242;268;268" keyTimes="0;0.348;0.351;0.357;0.363;0.369;0.375;0.381;0.387;1" dur="18s" repeatCount="indefinite"/>
-  <animate attributeName="opacity" values="0;0;1;0.2;1;0.2;1;0;0" keyTimes="0;0.34400000000000003;0.34800000000000003;0.355;0.365;0.375;0.385;0.407;1" dur="18s" repeatCount="indefinite"/>
+  <animate attributeName="x" calcMode="discrete" values="64;90;115;140;166;192;217;242;268;268" keyTimes="0;0.346;0.351;0.357;0.363;0.369;0.375;0.381;0.387;1" dur="18s" repeatCount="indefinite"/>
+  <animate attributeName="opacity" values="0;0;1;0.2;1;0.2;1;0;0" keyTimes="0;0.34400000000000003;0.34600000000000003;0.355;0.365;0.375;0.385;0.407;1" dur="18s" repeatCount="indefinite"/>
 </rect>
 <text x="40" y="100" font-weight="700" fill="#38bdf8" opacity="0"><animate attributeName="opacity" calcMode="discrete" values="0;0;1" keyTimes="0;0.378;0.38" dur="18s" repeatCount="indefinite"/>OmniRoute Combos</text><text x="40" y="128" fill="#a1a1aa" opacity="0"><animate attributeName="opacity" calcMode="discrete" values="0;0;1" keyTimes="0;0.386;0.388" dur="18s" repeatCount="indefinite"/>&#160;&#160;<tspan fill='#22c55e'>&#9679;</tspan> always-on&#160;&#160;&#160;&#160;&#160;[priority&#160;&#160;&#160;&#160;&#160;&#160;] <tspan fill='#22c55e'>enabled</tspan></text><text x="40" y="154" fill="#a1a1aa" opacity="0"><animate attributeName="opacity" calcMode="discrete" values="0;0;1" keyTimes="0;0.394;0.396" dur="18s" repeatCount="indefinite"/>&#160;&#160;<tspan fill='#71717a'>&#9675;</tspan> cost-saver&#160;&#160;&#160;&#160;[cost-optimized] <tspan fill='#22c55e'>enabled</tspan></text><text x="40" y="180" fill="#a1a1aa" opacity="0"><animate attributeName="opacity" calcMode="discrete" values="0;0;1" keyTimes="0;0.402;0.404" dur="18s" repeatCount="indefinite"/>&#160;&#160;<tspan fill='#71717a'>&#9675;</tspan> fusion-panel&#160;&#160;[fusion&#160;&#160;&#160;&#160;&#160;&#160;&#160;&#160;] <tspan fill='#22c55e'>enabled</tspan></text><text x="40" y="206" fill="#a1a1aa" opacity="0"><animate attributeName="opacity" calcMode="discrete" values="0;0;1" keyTimes="0;0.41;0.412" dur="18s" repeatCount="indefinite"/>&#160;&#160;<tspan fill='#71717a'>&#9675;</tspan> context-relay [context-relay&#160;] <tspan fill='#22c55e'>enabled</tspan></text><text x="40" y="232" fill="#71717a" opacity="0"><animate attributeName="opacity" calcMode="discrete" values="0;0;1" keyTimes="0;0.418;0.42" dur="18s" repeatCount="indefinite"/>&#8230; run: omniroute combo create</text>
 </g><g opacity="0" font-family="Consolas, 'Courier New', monospace" font-size="17">

docs/diagrams/comparison-table.svg

@@ -1,4 +1,4 @@
-<svg viewBox="0 0 1200 780" xmlns="http://www.w3.org/2000/svg" role="img" aria-label="Comparison table: OmniRoute versus 9router, OpenRouter, CLIProxyAPI and LiteLLM across 13 capabilities. OmniRoute is the only one with the full set: 348 providers, 90+ free providers built-in, 19 routing strategies, 12-engine token compression, a built-in MCP server with 110 tools, A2A protocol, persistent memory, guardrails, cloud agents, TLS fingerprint stealth, desktop/Termux/PWA, 43 UI locales and 100% MIT self-hosted. 9router has free providers, RTK compression and translation but no MCP, A2A, memory, guardrails, cloud agents or stealth. OpenRouter is a hosted SaaS with 400+ models, guardrails and a hosted MCP but is not self-hosted and lacks A2A, memory, cloud agents and stealth. CLIProxyAPI is a light OAuth proxy with two routing strategies. LiteLLM has 100+ providers, A2A and extensive guardrails but no memory, compression, free tier, stealth or cloud agents.">
+<svg viewBox="0 0 1200 780" xmlns="http://www.w3.org/2000/svg" role="img" aria-label="Comparison table: OmniRoute versus 9router, OpenRouter, CLIProxyAPI and LiteLLM across 13 capabilities. OmniRoute is the only one with the full set: 346 providers, 90+ free providers built-in, 19 routing strategies, 12-engine token compression, a built-in MCP server with 109 tools, A2A protocol, persistent memory, guardrails, cloud agents, TLS fingerprint stealth, desktop/Termux/PWA, 43 UI locales and 100% MIT self-hosted. 9router has free providers, RTK compression and translation but no MCP, A2A, memory, guardrails, cloud agents or stealth. OpenRouter is a hosted SaaS with 400+ models, guardrails and a hosted MCP but is not self-hosted and lacks A2A, memory, cloud agents and stealth. CLIProxyAPI is a light OAuth proxy with two routing strategies. LiteLLM has 100+ providers, A2A and extensive guardrails but no memory, compression, free tier, stealth or cloud agents.">
   <desc>Static-header comparison table where each capability row fades in top to bottom; the OmniRoute column is highlighted and shows a check or a leading value in every row, while competitors show a mix of checks, partials and crosses.</desc>
   <defs>
     <pattern id="gC" width="32" height="32" patternUnits="userSpaceOnUse"><path d="M 32 0 L 0 0 0 32" fill="none" stroke="#ffffff" stroke-opacity="0.05" stroke-width="1"/></pattern>

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, 346 providers — never stop building, OmniRoute picks the cheapest one that works. Six pillars. Never hit limits: auto-fallback across 346 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 109 tools, A2A, memory, guardrails, evals — 25,000+ tests.">
   <desc>Animated promise card: six pillar tiles fade in in reading order, then a soft colored border highlight sweeps from tile to tile in a continuous cycle.</desc>
   <defs>
     <pattern id="gridPaperP" width="32" height="32" patternUnits="userSpaceOnUse">
@@ -21,7 +21,7 @@
     <line x1="150" y1="53" x2="1160" y2="53" stroke="#232b38" stroke-width="1.5"/>
   </g>
   <g>
-    <text x="40" y="100" font-family="Inter, 'Segoe UI', Arial, Helvetica, system-ui, sans-serif" font-size="23" font-weight="600" fill="#c9d1d9">One endpoint. <tspan fill="#a78bfa" font-weight="800">348 providers.</tspan> Never stop building — OmniRoute picks <tspan fill="#7ee787" font-weight="700">the cheapest one that works</tspan>.</text>
+    <text x="40" y="100" font-family="Inter, 'Segoe UI', Arial, Helvetica, system-ui, sans-serif" font-size="23" font-weight="600" fill="#c9d1d9">One endpoint. <tspan fill="#a78bfa" font-weight="800">346 providers.</tspan> Never stop building — OmniRoute picks <tspan fill="#7ee787" font-weight="700">the cheapest one that works</tspan>.</text>
   </g>
 
   <g font-family="Inter, 'Segoe UI', Arial, Helvetica, system-ui, sans-serif">
@@ -38,7 +38,7 @@
         <line x1="3.9" y1="3.9" x2="18.1" y2="18.1"/>
       </g>
       <text x="102" y="170" font-size="18" font-weight="800" fill="#74b9ff">Never hit limits</text>
-      <text x="66" y="204" font-size="13.5" fill="#a1a1aa">Auto-fallback across 348 providers in</text>
+      <text x="66" y="204" font-size="13.5" fill="#a1a1aa">Auto-fallback across 346 providers in</text>
       <text x="66" y="226" font-size="13.5" fill="#a1a1aa">milliseconds. Quota out? The next provider</text>
       <text x="66" y="248" font-size="13.5" fill="#a1a1aa">takes over — zero downtime.</text>
     </g>
@@ -125,7 +125,7 @@
         <path d="M 7,11 L 10,14 L 15.4,8.2"/>
       </g>
       <text x="862" y="354" font-size="18" font-weight="800" fill="#7ee787">Production-grade</text>
-      <text x="826" y="388" font-size="13.5" fill="#a1a1aa">Circuit breakers, TLS stealth, MCP (110</text>
+      <text x="826" y="388" font-size="13.5" fill="#a1a1aa">Circuit breakers, TLS stealth, MCP (109</text>
       <text x="826" y="410" font-size="13.5" fill="#a1a1aa">tools), A2A, memory, guardrails, evals —</text>
       <text x="826" y="432" font-size="13.5" fill="#a1a1aa">25,000+ tests.</text>
     </g>

docs/diagrams/readme-hero.svg

@@ -1,4 +1,4 @@
-<svg viewBox="0 0 1200 548" xmlns="http://www.w3.org/2000/svg" role="img" aria-label="OmniRoute hero: Never stop coding. Every AI tool to 348 providers — 90+ free — through one endpoint. Claude Code, Codex, Cursor, Cline, Copilot and Antigravity into free Claude, GPT and Gemini with auto-fallback. RTK + Caveman stacked compression saves 15 to 95 percent of tokens — about 89 percent average on tool-heavy sessions — so you never hit limits. Stats: 348 AI providers, 90+ free tiers, about 1.51B free tokens per month, 15 to 95 percent token savings, 19 routing strategies, zero dollars to start.">
+<svg viewBox="0 0 1200 548" xmlns="http://www.w3.org/2000/svg" role="img" aria-label="OmniRoute hero: Never stop coding. Every AI tool to 346 providers — 90+ free — through one endpoint. Claude Code, Codex, Cursor, Cline, Copilot and Antigravity into free Claude, GPT and Gemini with auto-fallback. RTK + Caveman stacked compression saves 15 to 95 percent of tokens — about 89 percent average on tool-heavy sessions — so you never hit limits. Stats: 346 AI providers, 90+ free tiers, about 1.51B free tokens per month, 15 to 95 percent token savings, 19 routing strategies, zero dollars to start.">
   <desc>Animated hero card: a pulse travels the divider line and a compression bar demo repeatedly shrinks a prompt by up to 95 percent; all headline content is static and readable on the first frame.</desc>
   <defs>
     <pattern id="gridPaperH" width="32" height="32" patternUnits="userSpaceOnUse">
@@ -28,7 +28,7 @@
   <text x="48" y="138" font-family="Inter, 'Segoe UI', Arial, Helvetica, system-ui, sans-serif" font-size="60" font-weight="800" fill="#e9edf3">Never stop coding<tspan fill="#a855f7">.</tspan></text>
 
   <!-- subheadline -->
-  <text x="48" y="184" font-family="Inter, 'Segoe UI', Arial, Helvetica, system-ui, sans-serif" font-size="25" font-weight="600" fill="#c9d1d9">Every AI tool → <tspan fill="#a78bfa" font-weight="800">348 providers</tspan> — <tspan fill="#7ee787" font-weight="800">90+ free</tspan> — through one endpoint.</text>
+  <text x="48" y="184" font-family="Inter, 'Segoe UI', Arial, Helvetica, system-ui, sans-serif" font-size="25" font-weight="600" fill="#c9d1d9">Every AI tool → <tspan fill="#a78bfa" font-weight="800">346 providers</tspan> — <tspan fill="#7ee787" font-weight="800">90+ free</tspan> — through one endpoint.</text>
 
   <!-- plug line -->
   <text x="48" y="222" font-family="Inter, 'Segoe UI', Arial, Helvetica, system-ui, sans-serif" font-size="16.5" fill="#a1a1aa">Claude Code · Codex · Cursor · Cline · Copilot · Antigravity&#160;&#160;→&#160;&#160;<tspan fill="#7ee787" font-weight="700">FREE</tspan> Claude / GPT / Gemini · auto-fallback</text>
@@ -46,7 +46,7 @@
   <g>
     <rect x="48" y="284" width="1104" height="132" rx="14" fill="#161b22" stroke="#ffffff" stroke-opacity="0.08" stroke-width="1"/>
     <text x="76" y="314" font-family="Consolas, 'Courier New', monospace" font-size="11" letter-spacing="2" fill="#e17055">RTK + CAVEMAN · STACKED COMPRESSION</text>
-    <text x="76" y="348" font-family="Inter, 'Segoe UI', Arial, Helvetica, system-ui, sans-serif" font-size="22" font-weight="800" fill="#e9edf3">Save 15–95% tokens</text>
+    <text x="76" y="346" font-family="Inter, 'Segoe UI', Arial, Helvetica, system-ui, sans-serif" font-size="22" font-weight="800" fill="#e9edf3">Save 15–95% tokens</text>
     <!-- live bar demo -->
     <rect x="76" y="364" width="640" height="12" rx="6" fill="#0b0e14" stroke="#232b38" stroke-width="1"/>
     <rect x="76" y="364" width="640" height="12" rx="6" fill="#e17055">

docs/frameworks/MCP-SERVER.md

@@ -6,9 +6,9 @@ lastUpdated: 2026-08-08
 
 # OmniRoute MCP Server Documentation
 
-> Model Context Protocol server with 110 tools across routing, cache, compression, memory, skills, proxy, pool, Radar, and context source operations.
+> Model Context Protocol server with 109 tools across routing, cache, compression, memory, skills, proxy, pool, Radar, and context source operations.
 >
-> Source of truth: `open-sse/mcp-server/server.ts` computes **110 unique tools** with `countUniqueMcpTools()`: 45 canonical definitions (including the six CCR lifecycle tools, the agent-skills trio, `omniroute_radar_catalog`, and `omniroute_x_search`), plus memory (3), skills (4), GitHub skills (3), pool (6), gamification (8), plugins (8), Notion (6), Obsidian (22), local corpus (3), and two RTK-only compression tools.
+> Source of truth: `open-sse/mcp-server/server.ts` computes **109 unique tools** with `countUniqueMcpTools()`: 44 canonical definitions (including the six CCR lifecycle tools, the agent-skills trio, and `omniroute_radar_catalog`), plus memory (3), skills (4), GitHub skills (3), pool (6), gamification (8), plugins (8), Notion (6), Obsidian (22), local corpus (3), and two RTK-only compression tools.
 
 ## Installation
 
@@ -79,8 +79,7 @@ Cursor, Cline, and compatible MCP client setup.
 | `omniroute_list_models_catalog` | `read:models`         | Full model catalog with capabilities, status, pricing         |
 | `omniroute_radar_catalog`       | `read:radar`          | Local signed Radar catalog; optional provider/family filters  |
 | `omniroute_tool_search`         | `read:tools`          | Discover tools from the registered MCP catalog                |
-| `omniroute_web_search`          | `execute:search`      | Web search through the configured search providers. Not X/Twitter. |
-| `omniroute_x_search`            | `execute:search`      | Search X (Twitter) through SuperGrok / xAI server-side `x_search`. Requires `xai-oauth` or an xAI API key. Not the X Developer Platform MCP. |
+| `omniroute_web_search`          | `execute:search`      | Web search through the configured search providers            |
 | `omniroute_web_fetch`           | `execute:search`      | Fetch web content through the configured fetch providers      |
 
 ## Advanced Tools (11) — Phase 2
@@ -227,7 +226,7 @@ See [AGENT-SKILLS.md](./AGENT-SKILLS.md) for the full catalog and how external a
 
 ## Related Frameworks (v3.8.0)
 
-The MCP tool inventory above (110 unique tools, computed by `countUniqueMcpTools()`) is intentionally
+The MCP tool inventory above (109 unique tools, computed by `countUniqueMcpTools()`) is intentionally
 scoped to runtime routing/cache/compression/memory/skills/proxy/context-source operations. Two adjacent
 frameworks ship alongside the MCP server in v3.8.0 and are documented separately:
 
@@ -371,7 +370,7 @@ MCP tool, prompt, and resource registries can compress descriptions at registrat
 
 Description compression shrinks each tool's metadata; **tool-cardinality reduction** goes one step further by reducing _how many_ tools are announced at all. Advertising fewer tools in the `tools/list` manifest cuts the per-request token cost the client's model pays for the tool catalog ("layer 5" compression). The implementation is a pure, stateless filter in `open-sse/mcp-server/toolCardinality.ts` (`reduceToolManifest`), wired into the registration loop in `createMcpServer()` (`open-sse/mcp-server/server.ts`).
 
-**Opt-in, off by default.** The filter only runs when at least one of two environment variables is set; with neither set, all 110 tools are announced unchanged.
+**Opt-in, off by default.** The filter only runs when at least one of two environment variables is set; with neither set, all 109 tools are announced unchanged.
 
 | Variable         | Mode                                                                                    |
 | :--------------- | :-------------------------------------------------------------------------------------- |

docs/guides/DOCKER_GUIDE.md

@@ -260,28 +260,7 @@ Memory behavior in Docker:
 - The image sets `OMNIROUTE_MEMORY_MB=1024` and derives `NODE_OPTIONS=--max-old-space-size=1024` from it.
 - The actual server process is started by the standalone launcher, which reads `OMNIROUTE_MEMORY_MB` and appends `--max-old-space-size=<OMNIROUTE_MEMORY_MB>`.
 - Node uses the last repeated `--max-old-space-size` value, so setting `OMNIROUTE_MEMORY_MB` controls the effective Docker heap limit.
-- Because the image always sets it, the launcher's own RAM-calibrated fallback never applies under Docker. Raise it explicitly for the workload (table below). `2048` is still too small for coding-agent `/v1/responses`.
-
-### Runtime RAM for coding agents
-
-The 1 GiB Docker default is a dashboard/light-chat floor, not a production size. Long `POST /v1/responses` bodies (hundreds of messages, tens of tools) retain multiple in-memory graphs during compression. Two overlapping ~3 MiB / ~750k-token requests have aborted V8 at a **12 GiB** old-space (`FATAL ERROR: Reached heap limit`) and also hit a 16 GiB cgroup OOM. See [#7849](https://github.com/diegosouzapw/OmniRoute/issues/7849).
-
-Size **cgroup `--memory` above the heap** — native buffers, SQLite, and compression intermediates sit outside V8.
-
-| Workload | `OMNIROUTE_MEMORY_MB` | Container / cgroup | Notes |
-| --- | --- | --- | --- |
-| Dashboard, one light chat | `1024` (image default) | ≥2 GiB | |
-| One coding agent (Claude/Codex/Grok) | `8192` | ≥10 GiB | Typical single-session `/v1/responses` |
-| Two concurrent long `/v1/responses` | `10240`–`12288` | ≥12–16 GiB | Measured V8 abort at ~12 GiB heap |
-| Three+ concurrent long contexts | do not on one process | serialize / more RAM | Default heavyweight admission is 1 in-flight; raising it without RAM reintroduces the abort |
-
-`omniroute serve` on bare metal calibrates ~35% of RAM (clamped `[512, 4096]`) when `OMNIROUTE_MEMORY_MB` is **unset**. Docker always sets `1024`, so that calibration never runs in the official image.
-
-```bash
-docker run -d --name omniroute --restart unless-stopped --stop-timeout 40 \
-  -e OMNIROUTE_MEMORY_MB=8192 --memory=10g \
-  -p 127.0.0.1:20128:20128 -v omniroute-data:/app/data diegosouzapw/omniroute:latest
-```
+- Because the image always sets it, the launcher's own RAM-calibrated fallback never applies under Docker. Raise it explicitly (`-e OMNIROUTE_MEMORY_MB=2048`) on a host with headroom.
 
 ## Critical Environment Variables
 
@@ -294,7 +273,7 @@ Beyond the defaults documented in [ENVIRONMENT.md](../reference/ENVIRONMENT.md),
 | `REDIS_PORT`                  | Host-side port for the bundled Redis container                                                      | `6379`                   |
 | `REDIS_BIND_HOST`             | Host interface the bundled Redis port is published on (loopback unless you add AUTH)                | `127.0.0.1`              |
 | `AUTO_UPDATE_HOST_REPO_DIR`   | Host path mounted into `cli` profile at `/workspace/omniroute` for self-update workflows            | `.` (current directory)  |
-| `OMNIROUTE_MEMORY_MB`         | Runtime Node heap ceiling for the Docker standalone server; overrides the image default above. Coding agents: `8192`+ (see [runtime RAM](#runtime-ram-for-coding-agents)). | `1024`                   |
+| `OMNIROUTE_MEMORY_MB`         | Runtime Node heap ceiling for the Docker standalone server; overrides the image default above       | `1024`                   |
 | `DASHBOARD_PORT` / `API_PORT` | Override exposed ports for dashboard (20128) and API (20129)                                        | `20128` / `20129`        |
 | `OMNIROUTE_BASE_PATH`         | URL subpath when the app is published behind a reverse proxy (e.g. `/omniroute`)                    | _(empty = root)_         |
 | `NEXT_PUBLIC_BASE_URL`        | Public browser origin including the subpath (e.g. `https://host/omniroute`)                         | unset                    |
@@ -518,52 +497,7 @@ Stock Docker / Kubernetes OmniRoute is **one Node process + one SQLite writer**.
 
 **Upgrades:** expect every session to drop. Drain clients if you can; there is no rolling update on default SQLite. Compose `restart: unless-stopped` plus Docker `HEALTHCHECK` will also replace the only process when the container is Unhealthy — same blast radius.
 
-External Postgres / multi-writer HA is **not** a documented stock path. If you need HA, keep a single replica or run a topology the project has tested and documented separately. The Postgres/MySQL work lives in [#8075](https://github.com/diegosouzapw/OmniRoute/issues/8075). Until that ships, the only supported way to multiply **large** `/v1/responses` capacity is N independent processes (next section), not `replicas > 1` on one volume.
-
-## Scale-out: N independent processes
-
-One Node process is **one V8 heap**. Two overlapping ~3 MiB / ~750k-token coding-agent `POST /v1/responses` (RTK + Caveman) abort that heap at ~12 Gi (`FATAL ERROR: Reached heap limit`) and can OOM a 16 Gi cgroup. See [#7849](https://github.com/diegosouzapw/OmniRoute/issues/7849). Raising `OMNIROUTE_CHAT_MAX_HEAVY_IN_FLIGHT` on that process reintroduces the abort. Small chats, `/healthz`, `/v1/models`, and MCP are **not** in that cap.
-
-To go beyond two concurrent **large** jobs **today**:
-
-| Do | Do not |
-| --- | --- |
-| Run **N containers/pods**, each with its **own** `DATA_DIR` / volume | Set `replicas > 1` against one SQLite file |
-| Keep each instance at 1–2 heavy in-flight and 12–16 Gi cgroup | Give one process 8× RAM and `max=8` |
-| Optional: `QUOTA_STORE_DRIVER=redis` + `QUOTA_STORE_REDIS_URL` for **shared quota counters** | Treat Redis as shared SQLite — it is not |
-| Duplicate provider secrets into each instance (or accept partitioned dashboards) | Expect one dashboard / one call-log across instances |
-| Front with any load balancer; sticky by API key or session is enough | Require a vendor-specific size-aware middleware |
-
-Hardware: `concurrent_large ≈ N × 2` at ~8–12 Gi heap / ~12–16 Gi cgroup **per instance**. Host RAM must cover `N × cgroup`, not “one 16 Gi pod with N=8.”
-
-Compose sketch (two heaps, two volumes — not `deploy.replicas: 2`):
-
-```yaml
-services:
-  omniroute-a:
-    image: diegosouzapw/omniroute:3.8.49
-    environment:
-      DATA_DIR: /app/data
-      OMNIROUTE_MEMORY_MB: "12288"
-      QUOTA_STORE_DRIVER: redis
-      QUOTA_STORE_REDIS_URL: redis://redis:6379
-    volumes: [omniroute-a-data:/app/data]
-    ports: ["20128:20128"]
-  omniroute-b:
-    image: diegosouzapw/omniroute:3.8.49
-    environment:
-      DATA_DIR: /app/data
-      OMNIROUTE_MEMORY_MB: "12288"
-      QUOTA_STORE_DRIVER: redis
-      QUOTA_STORE_REDIS_URL: redis://redis:6379
-    volumes: [omniroute-b-data:/app/data]
-    ports: ["20138:20128"]
-volumes:
-  omniroute-a-data:
-  omniroute-b-data:
-```
-
-In-process density (compression off the HTTP isolate) is [#11023](https://github.com/diegosouzapw/OmniRoute/issues/11023). One logical cluster on shared durable state is [#8075](https://github.com/diegosouzapw/OmniRoute/issues/8075).
+External Postgres / multi-writer HA is **not** a documented stock path. If you need HA, keep a single replica or run a topology the project has tested and documented separately.
 
 ## Important Notes
 

docs/guides/USER_GUIDE.md

@@ -263,8 +263,6 @@ Cost: currently listed as $0; terms and availability may change
 
 ### Cursor IDE
 
-**Using Cursor as an OmniRoute client** (route Cursor chat through OmniRoute):
-
 ```
 Settings → Models → Advanced:
   OpenAI API Base URL: http://localhost:20128/v1
@@ -272,10 +270,6 @@ Settings → Models → Advanced:
   Model: cc/claude-opus-4-7
 ```
 
-**Using OmniRoute as a Cursor provider** (OmniRoute calls Cursor upstream): prefer
-**Dashboard → Providers → Cursor → Login with Cursor**. In Docker, see
-[`docs/providers/CURSOR-DOCKER.md`](../providers/CURSOR-DOCKER.md).
-
 ### Claude Code
 
 Edit `~/.claude/settings.json`:

docs/i18n/ar/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 348 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 346 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (109 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -169,7 +169,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   └── manager.ts            # MITM proxy manager
 │   ├── shared/                   # Shared utilities, components, and constants
 │   │   ├── components/           # Reusable UI components (Card, Badge, Button, Modal, Sidebar, ProviderIcon, etc.)
-│   │   ├── constants/            # Provider definitions (348), model lists, pricing, routing strategies, MCP scopes
+│   │   ├── constants/            # Provider definitions (346), model lists, pricing, routing strategies, MCP scopes
 │   │   ├── contracts/            # Shared API contracts
 │   │   ├── hooks/                # React hooks
 │   │   ├── middleware/           # Shared middleware utilities
@@ -211,7 +211,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── moderations.ts        # Content moderation
 │   │   ├── rerank.ts             # Reranking API
 │   │   └── search.ts             # Web search API
-│   ├── mcp-server/               # Built-in MCP server (110 tools, 3 transports: stdio/SSE/streamable-HTTP)
+│   ├── mcp-server/               # Built-in MCP server (109 tools, 3 transports: stdio/SSE/streamable-HTTP)
 │   │   ├── server.ts             # MCP server core (tool registration, scope enforcement)
 │   │   ├── tools/                # Tool implementations (advancedTools, memoryTools, skillTools)
 │   │   ├── schemas/              # Zod input schemas (tools, audit, a2a)
@@ -266,7 +266,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── i18n/                     # 43-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
-│   ├── frameworks/               # MCP-SERVER.md (110 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
+│   ├── frameworks/               # MCP-SERVER.md (109 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
 │   ├── routing/                  # AUTO-COMBO.md (14-factor scoring), REASONING_REPLAY.md
 │   ├── security/                 # GUARDRAILS.md, COMPLIANCE.md, STEALTH_GUIDE.md, PUBLIC_CREDS.md, ERROR_SANITIZATION.md
 │   ├── guides/                   # USER_GUIDE.md, TROUBLESHOOTING.md, ELECTRON_GUIDE.md, I18N.md
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **348 AI providers** with automatic format translation
+- **346 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -351,7 +351,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 ### MCP Server (109 Tools)
 
-110 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
+109 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
 diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool**, **notion**,
 **obsidian**, **localCorpus**, **gamification**, and **plugin** modules. Full per-tool inventory:
 `docs/frameworks/MCP-SERVER.md`.
@@ -479,10 +479,10 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **348-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **346-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
-- **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
+- **MCP server expanded to 109 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
 - **Cloud Agents** (Codex Cloud, Devin, Jules), **Guardrails**, **Evals**, **Webhooks**, **Compliance** frameworks
 - **Embedded services** manager (install/start/stop bundled services from the dashboard)
 - **Prompt compression** (RTK + Caveman codecs) saving up to ~95% tokens on eligible traffic

docs/i18n/az/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 348 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 346 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (109 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -169,7 +169,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   └── manager.ts            # MITM proxy manager
 │   ├── shared/                   # Shared utilities, components, and constants
 │   │   ├── components/           # Reusable UI components (Card, Badge, Button, Modal, Sidebar, ProviderIcon, etc.)
-│   │   ├── constants/            # Provider definitions (348), model lists, pricing, routing strategies, MCP scopes
+│   │   ├── constants/            # Provider definitions (346), model lists, pricing, routing strategies, MCP scopes
 │   │   ├── contracts/            # Shared API contracts
 │   │   ├── hooks/                # React hooks
 │   │   ├── middleware/           # Shared middleware utilities
@@ -211,7 +211,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── moderations.ts        # Content moderation
 │   │   ├── rerank.ts             # Reranking API
 │   │   └── search.ts             # Web search API
-│   ├── mcp-server/               # Built-in MCP server (110 tools, 3 transports: stdio/SSE/streamable-HTTP)
+│   ├── mcp-server/               # Built-in MCP server (109 tools, 3 transports: stdio/SSE/streamable-HTTP)
 │   │   ├── server.ts             # MCP server core (tool registration, scope enforcement)
 │   │   ├── tools/                # Tool implementations (advancedTools, memoryTools, skillTools)
 │   │   ├── schemas/              # Zod input schemas (tools, audit, a2a)
@@ -266,7 +266,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── i18n/                     # 43-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
-│   ├── frameworks/               # MCP-SERVER.md (110 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
+│   ├── frameworks/               # MCP-SERVER.md (109 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
 │   ├── routing/                  # AUTO-COMBO.md (14-factor scoring), REASONING_REPLAY.md
 │   ├── security/                 # GUARDRAILS.md, COMPLIANCE.md, STEALTH_GUIDE.md, PUBLIC_CREDS.md, ERROR_SANITIZATION.md
 │   ├── guides/                   # USER_GUIDE.md, TROUBLESHOOTING.md, ELECTRON_GUIDE.md, I18N.md
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **348 AI providers** with automatic format translation
+- **346 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -351,7 +351,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 ### MCP Server (109 Tools)
 
-110 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
+109 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
 diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool**, **notion**,
 **obsidian**, **localCorpus**, **gamification**, and **plugin** modules. Full per-tool inventory:
 `docs/frameworks/MCP-SERVER.md`.
@@ -479,10 +479,10 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **348-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **346-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
-- **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
+- **MCP server expanded to 109 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
 - **Cloud Agents** (Codex Cloud, Devin, Jules), **Guardrails**, **Evals**, **Webhooks**, **Compliance** frameworks
 - **Embedded services** manager (install/start/stop bundled services from the dashboard)
 - **Prompt compression** (RTK + Caveman codecs) saving up to ~95% tokens on eligible traffic

docs/i18n/bg/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 348 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 346 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (109 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -169,7 +169,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   └── manager.ts            # MITM proxy manager
 │   ├── shared/                   # Shared utilities, components, and constants
 │   │   ├── components/           # Reusable UI components (Card, Badge, Button, Modal, Sidebar, ProviderIcon, etc.)
-│   │   ├── constants/            # Provider definitions (348), model lists, pricing, routing strategies, MCP scopes
+│   │   ├── constants/            # Provider definitions (346), model lists, pricing, routing strategies, MCP scopes
 │   │   ├── contracts/            # Shared API contracts
 │   │   ├── hooks/                # React hooks
 │   │   ├── middleware/           # Shared middleware utilities
@@ -211,7 +211,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── moderations.ts        # Content moderation
 │   │   ├── rerank.ts             # Reranking API
 │   │   └── search.ts             # Web search API
-│   ├── mcp-server/               # Built-in MCP server (110 tools, 3 transports: stdio/SSE/streamable-HTTP)
+│   ├── mcp-server/               # Built-in MCP server (109 tools, 3 transports: stdio/SSE/streamable-HTTP)
 │   │   ├── server.ts             # MCP server core (tool registration, scope enforcement)
 │   │   ├── tools/                # Tool implementations (advancedTools, memoryTools, skillTools)
 │   │   ├── schemas/              # Zod input schemas (tools, audit, a2a)
@@ -266,7 +266,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── i18n/                     # 43-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
-│   ├── frameworks/               # MCP-SERVER.md (110 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
+│   ├── frameworks/               # MCP-SERVER.md (109 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
 │   ├── routing/                  # AUTO-COMBO.md (14-factor scoring), REASONING_REPLAY.md
 │   ├── security/                 # GUARDRAILS.md, COMPLIANCE.md, STEALTH_GUIDE.md, PUBLIC_CREDS.md, ERROR_SANITIZATION.md
 │   ├── guides/                   # USER_GUIDE.md, TROUBLESHOOTING.md, ELECTRON_GUIDE.md, I18N.md
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **348 AI providers** with automatic format translation
+- **346 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -351,7 +351,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 ### MCP Server (109 Tools)
 
-110 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
+109 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
 diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool**, **notion**,
 **obsidian**, **localCorpus**, **gamification**, and **plugin** modules. Full per-tool inventory:
 `docs/frameworks/MCP-SERVER.md`.
@@ -479,10 +479,10 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **348-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **346-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
-- **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
+- **MCP server expanded to 109 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
 - **Cloud Agents** (Codex Cloud, Devin, Jules), **Guardrails**, **Evals**, **Webhooks**, **Compliance** frameworks
 - **Embedded services** manager (install/start/stop bundled services from the dashboard)
 - **Prompt compression** (RTK + Caveman codecs) saving up to ~95% tokens on eligible traffic

docs/i18n/bn/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 348 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 346 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (109 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -169,7 +169,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   └── manager.ts            # MITM proxy manager
 │   ├── shared/                   # Shared utilities, components, and constants
 │   │   ├── components/           # Reusable UI components (Card, Badge, Button, Modal, Sidebar, ProviderIcon, etc.)
-│   │   ├── constants/            # Provider definitions (348), model lists, pricing, routing strategies, MCP scopes
+│   │   ├── constants/            # Provider definitions (346), model lists, pricing, routing strategies, MCP scopes
 │   │   ├── contracts/            # Shared API contracts
 │   │   ├── hooks/                # React hooks
 │   │   ├── middleware/           # Shared middleware utilities
@@ -211,7 +211,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── moderations.ts        # Content moderation
 │   │   ├── rerank.ts             # Reranking API
 │   │   └── search.ts             # Web search API
-│   ├── mcp-server/               # Built-in MCP server (110 tools, 3 transports: stdio/SSE/streamable-HTTP)
+│   ├── mcp-server/               # Built-in MCP server (109 tools, 3 transports: stdio/SSE/streamable-HTTP)
 │   │   ├── server.ts             # MCP server core (tool registration, scope enforcement)
 │   │   ├── tools/                # Tool implementations (advancedTools, memoryTools, skillTools)
 │   │   ├── schemas/              # Zod input schemas (tools, audit, a2a)
@@ -266,7 +266,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── i18n/                     # 43-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
-│   ├── frameworks/               # MCP-SERVER.md (110 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
+│   ├── frameworks/               # MCP-SERVER.md (109 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
 │   ├── routing/                  # AUTO-COMBO.md (14-factor scoring), REASONING_REPLAY.md
 │   ├── security/                 # GUARDRAILS.md, COMPLIANCE.md, STEALTH_GUIDE.md, PUBLIC_CREDS.md, ERROR_SANITIZATION.md
 │   ├── guides/                   # USER_GUIDE.md, TROUBLESHOOTING.md, ELECTRON_GUIDE.md, I18N.md
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **348 AI providers** with automatic format translation
+- **346 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -351,7 +351,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 ### MCP Server (109 Tools)
 
-110 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
+109 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
 diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool**, **notion**,
 **obsidian**, **localCorpus**, **gamification**, and **plugin** modules. Full per-tool inventory:
 `docs/frameworks/MCP-SERVER.md`.
@@ -479,10 +479,10 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **348-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **346-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
-- **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
+- **MCP server expanded to 109 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
 - **Cloud Agents** (Codex Cloud, Devin, Jules), **Guardrails**, **Evals**, **Webhooks**, **Compliance** frameworks
 - **Embedded services** manager (install/start/stop bundled services from the dashboard)
 - **Prompt compression** (RTK + Caveman codecs) saving up to ~95% tokens on eligible traffic

docs/i18n/cs/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 348 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 346 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (109 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -169,7 +169,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   └── manager.ts            # MITM proxy manager
 │   ├── shared/                   # Shared utilities, components, and constants
 │   │   ├── components/           # Reusable UI components (Card, Badge, Button, Modal, Sidebar, ProviderIcon, etc.)
-│   │   ├── constants/            # Provider definitions (348), model lists, pricing, routing strategies, MCP scopes
+│   │   ├── constants/            # Provider definitions (346), model lists, pricing, routing strategies, MCP scopes
 │   │   ├── contracts/            # Shared API contracts
 │   │   ├── hooks/                # React hooks
 │   │   ├── middleware/           # Shared middleware utilities
@@ -211,7 +211,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── moderations.ts        # Content moderation
 │   │   ├── rerank.ts             # Reranking API
 │   │   └── search.ts             # Web search API
-│   ├── mcp-server/               # Built-in MCP server (110 tools, 3 transports: stdio/SSE/streamable-HTTP)
+│   ├── mcp-server/               # Built-in MCP server (109 tools, 3 transports: stdio/SSE/streamable-HTTP)
 │   │   ├── server.ts             # MCP server core (tool registration, scope enforcement)
 │   │   ├── tools/                # Tool implementations (advancedTools, memoryTools, skillTools)
 │   │   ├── schemas/              # Zod input schemas (tools, audit, a2a)
@@ -266,7 +266,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── i18n/                     # 43-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
-│   ├── frameworks/               # MCP-SERVER.md (110 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
+│   ├── frameworks/               # MCP-SERVER.md (109 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
 │   ├── routing/                  # AUTO-COMBO.md (14-factor scoring), REASONING_REPLAY.md
 │   ├── security/                 # GUARDRAILS.md, COMPLIANCE.md, STEALTH_GUIDE.md, PUBLIC_CREDS.md, ERROR_SANITIZATION.md
 │   ├── guides/                   # USER_GUIDE.md, TROUBLESHOOTING.md, ELECTRON_GUIDE.md, I18N.md
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **348 AI providers** with automatic format translation
+- **346 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -351,7 +351,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 ### MCP Server (109 Tools)
 
-110 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
+109 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
 diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool**, **notion**,
 **obsidian**, **localCorpus**, **gamification**, and **plugin** modules. Full per-tool inventory:
 `docs/frameworks/MCP-SERVER.md`.
@@ -479,10 +479,10 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **348-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **346-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
-- **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
+- **MCP server expanded to 109 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
 - **Cloud Agents** (Codex Cloud, Devin, Jules), **Guardrails**, **Evals**, **Webhooks**, **Compliance** frameworks
 - **Embedded services** manager (install/start/stop bundled services from the dashboard)
 - **Prompt compression** (RTK + Caveman codecs) saving up to ~95% tokens on eligible traffic

docs/i18n/da/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 348 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 346 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (109 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -169,7 +169,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   └── manager.ts            # MITM proxy manager
 │   ├── shared/                   # Shared utilities, components, and constants
 │   │   ├── components/           # Reusable UI components (Card, Badge, Button, Modal, Sidebar, ProviderIcon, etc.)
-│   │   ├── constants/            # Provider definitions (348), model lists, pricing, routing strategies, MCP scopes
+│   │   ├── constants/            # Provider definitions (346), model lists, pricing, routing strategies, MCP scopes
 │   │   ├── contracts/            # Shared API contracts
 │   │   ├── hooks/                # React hooks
 │   │   ├── middleware/           # Shared middleware utilities
@@ -211,7 +211,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── moderations.ts        # Content moderation
 │   │   ├── rerank.ts             # Reranking API
 │   │   └── search.ts             # Web search API
-│   ├── mcp-server/               # Built-in MCP server (110 tools, 3 transports: stdio/SSE/streamable-HTTP)
+│   ├── mcp-server/               # Built-in MCP server (109 tools, 3 transports: stdio/SSE/streamable-HTTP)
 │   │   ├── server.ts             # MCP server core (tool registration, scope enforcement)
 │   │   ├── tools/                # Tool implementations (advancedTools, memoryTools, skillTools)
 │   │   ├── schemas/              # Zod input schemas (tools, audit, a2a)
@@ -266,7 +266,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── i18n/                     # 43-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
-│   ├── frameworks/               # MCP-SERVER.md (110 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
+│   ├── frameworks/               # MCP-SERVER.md (109 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
 │   ├── routing/                  # AUTO-COMBO.md (14-factor scoring), REASONING_REPLAY.md
 │   ├── security/                 # GUARDRAILS.md, COMPLIANCE.md, STEALTH_GUIDE.md, PUBLIC_CREDS.md, ERROR_SANITIZATION.md
 │   ├── guides/                   # USER_GUIDE.md, TROUBLESHOOTING.md, ELECTRON_GUIDE.md, I18N.md
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **348 AI providers** with automatic format translation
+- **346 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -351,7 +351,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 ### MCP Server (109 Tools)
 
-110 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
+109 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
 diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool**, **notion**,
 **obsidian**, **localCorpus**, **gamification**, and **plugin** modules. Full per-tool inventory:
 `docs/frameworks/MCP-SERVER.md`.
@@ -479,10 +479,10 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **348-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **346-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
-- **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
+- **MCP server expanded to 109 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
 - **Cloud Agents** (Codex Cloud, Devin, Jules), **Guardrails**, **Evals**, **Webhooks**, **Compliance** frameworks
 - **Embedded services** manager (install/start/stop bundled services from the dashboard)
 - **Prompt compression** (RTK + Caveman codecs) saving up to ~95% tokens on eligible traffic

docs/i18n/de/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 348 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 346 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (109 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -169,7 +169,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   └── manager.ts            # MITM proxy manager
 │   ├── shared/                   # Shared utilities, components, and constants
 │   │   ├── components/           # Reusable UI components (Card, Badge, Button, Modal, Sidebar, ProviderIcon, etc.)
-│   │   ├── constants/            # Provider definitions (348), model lists, pricing, routing strategies, MCP scopes
+│   │   ├── constants/            # Provider definitions (346), model lists, pricing, routing strategies, MCP scopes
 │   │   ├── contracts/            # Shared API contracts
 │   │   ├── hooks/                # React hooks
 │   │   ├── middleware/           # Shared middleware utilities
@@ -211,7 +211,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── moderations.ts        # Content moderation
 │   │   ├── rerank.ts             # Reranking API
 │   │   └── search.ts             # Web search API
-│   ├── mcp-server/               # Built-in MCP server (110 tools, 3 transports: stdio/SSE/streamable-HTTP)
+│   ├── mcp-server/               # Built-in MCP server (109 tools, 3 transports: stdio/SSE/streamable-HTTP)
 │   │   ├── server.ts             # MCP server core (tool registration, scope enforcement)
 │   │   ├── tools/                # Tool implementations (advancedTools, memoryTools, skillTools)
 │   │   ├── schemas/              # Zod input schemas (tools, audit, a2a)
@@ -266,7 +266,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── i18n/                     # 43-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
-│   ├── frameworks/               # MCP-SERVER.md (110 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
+│   ├── frameworks/               # MCP-SERVER.md (109 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
 │   ├── routing/                  # AUTO-COMBO.md (14-factor scoring), REASONING_REPLAY.md
 │   ├── security/                 # GUARDRAILS.md, COMPLIANCE.md, STEALTH_GUIDE.md, PUBLIC_CREDS.md, ERROR_SANITIZATION.md
 │   ├── guides/                   # USER_GUIDE.md, TROUBLESHOOTING.md, ELECTRON_GUIDE.md, I18N.md
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **348 AI providers** with automatic format translation
+- **346 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -351,7 +351,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 ### MCP Server (109 Tools)
 
-110 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
+109 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
 diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool**, **notion**,
 **obsidian**, **localCorpus**, **gamification**, and **plugin** modules. Full per-tool inventory:
 `docs/frameworks/MCP-SERVER.md`.
@@ -479,10 +479,10 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **348-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **346-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
-- **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
+- **MCP server expanded to 109 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
 - **Cloud Agents** (Codex Cloud, Devin, Jules), **Guardrails**, **Evals**, **Webhooks**, **Compliance** frameworks
 - **Embedded services** manager (install/start/stop bundled services from the dashboard)
 - **Prompt compression** (RTK + Caveman codecs) saving up to ~95% tokens on eligible traffic

docs/i18n/es/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 348 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 346 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (109 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -169,7 +169,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   └── manager.ts            # MITM proxy manager
 │   ├── shared/                   # Shared utilities, components, and constants
 │   │   ├── components/           # Reusable UI components (Card, Badge, Button, Modal, Sidebar, ProviderIcon, etc.)
-│   │   ├── constants/            # Provider definitions (348), model lists, pricing, routing strategies, MCP scopes
+│   │   ├── constants/            # Provider definitions (346), model lists, pricing, routing strategies, MCP scopes
 │   │   ├── contracts/            # Shared API contracts
 │   │   ├── hooks/                # React hooks
 │   │   ├── middleware/           # Shared middleware utilities
@@ -211,7 +211,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── moderations.ts        # Content moderation
 │   │   ├── rerank.ts             # Reranking API
 │   │   └── search.ts             # Web search API
-│   ├── mcp-server/               # Built-in MCP server (110 tools, 3 transports: stdio/SSE/streamable-HTTP)
+│   ├── mcp-server/               # Built-in MCP server (109 tools, 3 transports: stdio/SSE/streamable-HTTP)
 │   │   ├── server.ts             # MCP server core (tool registration, scope enforcement)
 │   │   ├── tools/                # Tool implementations (advancedTools, memoryTools, skillTools)
 │   │   ├── schemas/              # Zod input schemas (tools, audit, a2a)
@@ -266,7 +266,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── i18n/                     # 43-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
-│   ├── frameworks/               # MCP-SERVER.md (110 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
+│   ├── frameworks/               # MCP-SERVER.md (109 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
 │   ├── routing/                  # AUTO-COMBO.md (14-factor scoring), REASONING_REPLAY.md
 │   ├── security/                 # GUARDRAILS.md, COMPLIANCE.md, STEALTH_GUIDE.md, PUBLIC_CREDS.md, ERROR_SANITIZATION.md
 │   ├── guides/                   # USER_GUIDE.md, TROUBLESHOOTING.md, ELECTRON_GUIDE.md, I18N.md
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **348 AI providers** with automatic format translation
+- **346 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -351,7 +351,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 ### MCP Server (109 Tools)
 
-110 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
+109 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
 diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool**, **notion**,
 **obsidian**, **localCorpus**, **gamification**, and **plugin** modules. Full per-tool inventory:
 `docs/frameworks/MCP-SERVER.md`.
@@ -479,10 +479,10 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **348-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **346-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
-- **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
+- **MCP server expanded to 109 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
 - **Cloud Agents** (Codex Cloud, Devin, Jules), **Guardrails**, **Evals**, **Webhooks**, **Compliance** frameworks
 - **Embedded services** manager (install/start/stop bundled services from the dashboard)
 - **Prompt compression** (RTK + Caveman codecs) saving up to ~95% tokens on eligible traffic

docs/i18n/fa/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 348 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 346 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (109 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -169,7 +169,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   └── manager.ts            # MITM proxy manager
 │   ├── shared/                   # Shared utilities, components, and constants
 │   │   ├── components/           # Reusable UI components (Card, Badge, Button, Modal, Sidebar, ProviderIcon, etc.)
-│   │   ├── constants/            # Provider definitions (348), model lists, pricing, routing strategies, MCP scopes
+│   │   ├── constants/            # Provider definitions (346), model lists, pricing, routing strategies, MCP scopes
 │   │   ├── contracts/            # Shared API contracts
 │   │   ├── hooks/                # React hooks
 │   │   ├── middleware/           # Shared middleware utilities
@@ -211,7 +211,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── moderations.ts        # Content moderation
 │   │   ├── rerank.ts             # Reranking API
 │   │   └── search.ts             # Web search API
-│   ├── mcp-server/               # Built-in MCP server (110 tools, 3 transports: stdio/SSE/streamable-HTTP)
+│   ├── mcp-server/               # Built-in MCP server (109 tools, 3 transports: stdio/SSE/streamable-HTTP)
 │   │   ├── server.ts             # MCP server core (tool registration, scope enforcement)
 │   │   ├── tools/                # Tool implementations (advancedTools, memoryTools, skillTools)
 │   │   ├── schemas/              # Zod input schemas (tools, audit, a2a)
@@ -266,7 +266,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── i18n/                     # 43-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
-│   ├── frameworks/               # MCP-SERVER.md (110 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
+│   ├── frameworks/               # MCP-SERVER.md (109 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
 │   ├── routing/                  # AUTO-COMBO.md (14-factor scoring), REASONING_REPLAY.md
 │   ├── security/                 # GUARDRAILS.md, COMPLIANCE.md, STEALTH_GUIDE.md, PUBLIC_CREDS.md, ERROR_SANITIZATION.md
 │   ├── guides/                   # USER_GUIDE.md, TROUBLESHOOTING.md, ELECTRON_GUIDE.md, I18N.md
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **348 AI providers** with automatic format translation
+- **346 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -351,7 +351,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 ### MCP Server (109 Tools)
 
-110 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
+109 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
 diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool**, **notion**,
 **obsidian**, **localCorpus**, **gamification**, and **plugin** modules. Full per-tool inventory:
 `docs/frameworks/MCP-SERVER.md`.
@@ -479,10 +479,10 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **348-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **346-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
-- **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
+- **MCP server expanded to 109 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
 - **Cloud Agents** (Codex Cloud, Devin, Jules), **Guardrails**, **Evals**, **Webhooks**, **Compliance** frameworks
 - **Embedded services** manager (install/start/stop bundled services from the dashboard)
 - **Prompt compression** (RTK + Caveman codecs) saving up to ~95% tokens on eligible traffic

docs/i18n/fi/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 348 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 346 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (109 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -169,7 +169,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   └── manager.ts            # MITM proxy manager
 │   ├── shared/                   # Shared utilities, components, and constants
 │   │   ├── components/           # Reusable UI components (Card, Badge, Button, Modal, Sidebar, ProviderIcon, etc.)
-│   │   ├── constants/            # Provider definitions (348), model lists, pricing, routing strategies, MCP scopes
+│   │   ├── constants/            # Provider definitions (346), model lists, pricing, routing strategies, MCP scopes
 │   │   ├── contracts/            # Shared API contracts
 │   │   ├── hooks/                # React hooks
 │   │   ├── middleware/           # Shared middleware utilities
@@ -211,7 +211,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── moderations.ts        # Content moderation
 │   │   ├── rerank.ts             # Reranking API
 │   │   └── search.ts             # Web search API
-│   ├── mcp-server/               # Built-in MCP server (110 tools, 3 transports: stdio/SSE/streamable-HTTP)
+│   ├── mcp-server/               # Built-in MCP server (109 tools, 3 transports: stdio/SSE/streamable-HTTP)
 │   │   ├── server.ts             # MCP server core (tool registration, scope enforcement)
 │   │   ├── tools/                # Tool implementations (advancedTools, memoryTools, skillTools)
 │   │   ├── schemas/              # Zod input schemas (tools, audit, a2a)
@@ -266,7 +266,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── i18n/                     # 43-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
-│   ├── frameworks/               # MCP-SERVER.md (110 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
+│   ├── frameworks/               # MCP-SERVER.md (109 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
 │   ├── routing/                  # AUTO-COMBO.md (14-factor scoring), REASONING_REPLAY.md
 │   ├── security/                 # GUARDRAILS.md, COMPLIANCE.md, STEALTH_GUIDE.md, PUBLIC_CREDS.md, ERROR_SANITIZATION.md
 │   ├── guides/                   # USER_GUIDE.md, TROUBLESHOOTING.md, ELECTRON_GUIDE.md, I18N.md
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **348 AI providers** with automatic format translation
+- **346 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -351,7 +351,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 ### MCP Server (109 Tools)
 
-110 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
+109 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
 diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool**, **notion**,
 **obsidian**, **localCorpus**, **gamification**, and **plugin** modules. Full per-tool inventory:
 `docs/frameworks/MCP-SERVER.md`.
@@ -479,10 +479,10 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **348-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **346-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
-- **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
+- **MCP server expanded to 109 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
 - **Cloud Agents** (Codex Cloud, Devin, Jules), **Guardrails**, **Evals**, **Webhooks**, **Compliance** frameworks
 - **Embedded services** manager (install/start/stop bundled services from the dashboard)
 - **Prompt compression** (RTK + Caveman codecs) saving up to ~95% tokens on eligible traffic

docs/i18n/fr/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 348 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 346 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (109 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -169,7 +169,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   └── manager.ts            # MITM proxy manager
 │   ├── shared/                   # Shared utilities, components, and constants
 │   │   ├── components/           # Reusable UI components (Card, Badge, Button, Modal, Sidebar, ProviderIcon, etc.)
-│   │   ├── constants/            # Provider definitions (348), model lists, pricing, routing strategies, MCP scopes
+│   │   ├── constants/            # Provider definitions (346), model lists, pricing, routing strategies, MCP scopes
 │   │   ├── contracts/            # Shared API contracts
 │   │   ├── hooks/                # React hooks
 │   │   ├── middleware/           # Shared middleware utilities
@@ -211,7 +211,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── moderations.ts        # Content moderation
 │   │   ├── rerank.ts             # Reranking API
 │   │   └── search.ts             # Web search API
-│   ├── mcp-server/               # Built-in MCP server (110 tools, 3 transports: stdio/SSE/streamable-HTTP)
+│   ├── mcp-server/               # Built-in MCP server (109 tools, 3 transports: stdio/SSE/streamable-HTTP)
 │   │   ├── server.ts             # MCP server core (tool registration, scope enforcement)
 │   │   ├── tools/                # Tool implementations (advancedTools, memoryTools, skillTools)
 │   │   ├── schemas/              # Zod input schemas (tools, audit, a2a)
@@ -266,7 +266,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── i18n/                     # 43-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
-│   ├── frameworks/               # MCP-SERVER.md (110 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
+│   ├── frameworks/               # MCP-SERVER.md (109 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
 │   ├── routing/                  # AUTO-COMBO.md (14-factor scoring), REASONING_REPLAY.md
 │   ├── security/                 # GUARDRAILS.md, COMPLIANCE.md, STEALTH_GUIDE.md, PUBLIC_CREDS.md, ERROR_SANITIZATION.md
 │   ├── guides/                   # USER_GUIDE.md, TROUBLESHOOTING.md, ELECTRON_GUIDE.md, I18N.md
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **348 AI providers** with automatic format translation
+- **346 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -351,7 +351,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 ### MCP Server (109 Tools)
 
-110 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
+109 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
 diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool**, **notion**,
 **obsidian**, **localCorpus**, **gamification**, and **plugin** modules. Full per-tool inventory:
 `docs/frameworks/MCP-SERVER.md`.
@@ -479,10 +479,10 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **348-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **346-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
-- **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
+- **MCP server expanded to 109 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
 - **Cloud Agents** (Codex Cloud, Devin, Jules), **Guardrails**, **Evals**, **Webhooks**, **Compliance** frameworks
 - **Embedded services** manager (install/start/stop bundled services from the dashboard)
 - **Prompt compression** (RTK + Caveman codecs) saving up to ~95% tokens on eligible traffic

docs/i18n/gu/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 348 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 346 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (109 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -169,7 +169,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   └── manager.ts            # MITM proxy manager
 │   ├── shared/                   # Shared utilities, components, and constants
 │   │   ├── components/           # Reusable UI components (Card, Badge, Button, Modal, Sidebar, ProviderIcon, etc.)
-│   │   ├── constants/            # Provider definitions (348), model lists, pricing, routing strategies, MCP scopes
+│   │   ├── constants/            # Provider definitions (346), model lists, pricing, routing strategies, MCP scopes
 │   │   ├── contracts/            # Shared API contracts
 │   │   ├── hooks/                # React hooks
 │   │   ├── middleware/           # Shared middleware utilities
@@ -211,7 +211,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── moderations.ts        # Content moderation
 │   │   ├── rerank.ts             # Reranking API
 │   │   └── search.ts             # Web search API
-│   ├── mcp-server/               # Built-in MCP server (110 tools, 3 transports: stdio/SSE/streamable-HTTP)
+│   ├── mcp-server/               # Built-in MCP server (109 tools, 3 transports: stdio/SSE/streamable-HTTP)
 │   │   ├── server.ts             # MCP server core (tool registration, scope enforcement)
 │   │   ├── tools/                # Tool implementations (advancedTools, memoryTools, skillTools)
 │   │   ├── schemas/              # Zod input schemas (tools, audit, a2a)
@@ -266,7 +266,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── i18n/                     # 43-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
-│   ├── frameworks/               # MCP-SERVER.md (110 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
+│   ├── frameworks/               # MCP-SERVER.md (109 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
 │   ├── routing/                  # AUTO-COMBO.md (14-factor scoring), REASONING_REPLAY.md
 │   ├── security/                 # GUARDRAILS.md, COMPLIANCE.md, STEALTH_GUIDE.md, PUBLIC_CREDS.md, ERROR_SANITIZATION.md
 │   ├── guides/                   # USER_GUIDE.md, TROUBLESHOOTING.md, ELECTRON_GUIDE.md, I18N.md
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **348 AI providers** with automatic format translation
+- **346 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -351,7 +351,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 ### MCP Server (109 Tools)
 
-110 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
+109 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
 diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool**, **notion**,
 **obsidian**, **localCorpus**, **gamification**, and **plugin** modules. Full per-tool inventory:
 `docs/frameworks/MCP-SERVER.md`.
@@ -479,10 +479,10 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **348-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **346-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
-- **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
+- **MCP server expanded to 109 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
 - **Cloud Agents** (Codex Cloud, Devin, Jules), **Guardrails**, **Evals**, **Webhooks**, **Compliance** frameworks
 - **Embedded services** manager (install/start/stop bundled services from the dashboard)
 - **Prompt compression** (RTK + Caveman codecs) saving up to ~95% tokens on eligible traffic

docs/i18n/he/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 348 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 346 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (109 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -169,7 +169,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   └── manager.ts            # MITM proxy manager
 │   ├── shared/                   # Shared utilities, components, and constants
 │   │   ├── components/           # Reusable UI components (Card, Badge, Button, Modal, Sidebar, ProviderIcon, etc.)
-│   │   ├── constants/            # Provider definitions (348), model lists, pricing, routing strategies, MCP scopes
+│   │   ├── constants/            # Provider definitions (346), model lists, pricing, routing strategies, MCP scopes
 │   │   ├── contracts/            # Shared API contracts
 │   │   ├── hooks/                # React hooks
 │   │   ├── middleware/           # Shared middleware utilities
@@ -211,7 +211,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── moderations.ts        # Content moderation
 │   │   ├── rerank.ts             # Reranking API
 │   │   └── search.ts             # Web search API
-│   ├── mcp-server/               # Built-in MCP server (110 tools, 3 transports: stdio/SSE/streamable-HTTP)
+│   ├── mcp-server/               # Built-in MCP server (109 tools, 3 transports: stdio/SSE/streamable-HTTP)
 │   │   ├── server.ts             # MCP server core (tool registration, scope enforcement)
 │   │   ├── tools/                # Tool implementations (advancedTools, memoryTools, skillTools)
 │   │   ├── schemas/              # Zod input schemas (tools, audit, a2a)
@@ -266,7 +266,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── i18n/                     # 43-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
-│   ├── frameworks/               # MCP-SERVER.md (110 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
+│   ├── frameworks/               # MCP-SERVER.md (109 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
 │   ├── routing/                  # AUTO-COMBO.md (14-factor scoring), REASONING_REPLAY.md
 │   ├── security/                 # GUARDRAILS.md, COMPLIANCE.md, STEALTH_GUIDE.md, PUBLIC_CREDS.md, ERROR_SANITIZATION.md
 │   ├── guides/                   # USER_GUIDE.md, TROUBLESHOOTING.md, ELECTRON_GUIDE.md, I18N.md
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **348 AI providers** with automatic format translation
+- **346 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -351,7 +351,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 ### MCP Server (109 Tools)
 
-110 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
+109 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
 diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool**, **notion**,
 **obsidian**, **localCorpus**, **gamification**, and **plugin** modules. Full per-tool inventory:
 `docs/frameworks/MCP-SERVER.md`.
@@ -479,10 +479,10 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **348-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **346-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
-- **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
+- **MCP server expanded to 109 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
 - **Cloud Agents** (Codex Cloud, Devin, Jules), **Guardrails**, **Evals**, **Webhooks**, **Compliance** frameworks
 - **Embedded services** manager (install/start/stop bundled services from the dashboard)
 - **Prompt compression** (RTK + Caveman codecs) saving up to ~95% tokens on eligible traffic

docs/i18n/hi/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 348 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 346 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (109 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -169,7 +169,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   └── manager.ts            # MITM proxy manager
 │   ├── shared/                   # Shared utilities, components, and constants
 │   │   ├── components/           # Reusable UI components (Card, Badge, Button, Modal, Sidebar, ProviderIcon, etc.)
-│   │   ├── constants/            # Provider definitions (348), model lists, pricing, routing strategies, MCP scopes
+│   │   ├── constants/            # Provider definitions (346), model lists, pricing, routing strategies, MCP scopes
 │   │   ├── contracts/            # Shared API contracts
 │   │   ├── hooks/                # React hooks
 │   │   ├── middleware/           # Shared middleware utilities
@@ -211,7 +211,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── moderations.ts        # Content moderation
 │   │   ├── rerank.ts             # Reranking API
 │   │   └── search.ts             # Web search API
-│   ├── mcp-server/               # Built-in MCP server (110 tools, 3 transports: stdio/SSE/streamable-HTTP)
+│   ├── mcp-server/               # Built-in MCP server (109 tools, 3 transports: stdio/SSE/streamable-HTTP)
 │   │   ├── server.ts             # MCP server core (tool registration, scope enforcement)
 │   │   ├── tools/                # Tool implementations (advancedTools, memoryTools, skillTools)
 │   │   ├── schemas/              # Zod input schemas (tools, audit, a2a)
@@ -266,7 +266,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── i18n/                     # 43-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
-│   ├── frameworks/               # MCP-SERVER.md (110 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
+│   ├── frameworks/               # MCP-SERVER.md (109 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
 │   ├── routing/                  # AUTO-COMBO.md (14-factor scoring), REASONING_REPLAY.md
 │   ├── security/                 # GUARDRAILS.md, COMPLIANCE.md, STEALTH_GUIDE.md, PUBLIC_CREDS.md, ERROR_SANITIZATION.md
 │   ├── guides/                   # USER_GUIDE.md, TROUBLESHOOTING.md, ELECTRON_GUIDE.md, I18N.md
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **348 AI providers** with automatic format translation
+- **346 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -351,7 +351,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 ### MCP Server (109 Tools)
 
-110 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
+109 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
 diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool**, **notion**,
 **obsidian**, **localCorpus**, **gamification**, and **plugin** modules. Full per-tool inventory:
 `docs/frameworks/MCP-SERVER.md`.
@@ -479,10 +479,10 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **348-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **346-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
-- **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
+- **MCP server expanded to 109 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
 - **Cloud Agents** (Codex Cloud, Devin, Jules), **Guardrails**, **Evals**, **Webhooks**, **Compliance** frameworks
 - **Embedded services** manager (install/start/stop bundled services from the dashboard)
 - **Prompt compression** (RTK + Caveman codecs) saving up to ~95% tokens on eligible traffic

docs/i18n/hu/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 348 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 346 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (109 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -169,7 +169,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   └── manager.ts            # MITM proxy manager
 │   ├── shared/                   # Shared utilities, components, and constants
 │   │   ├── components/           # Reusable UI components (Card, Badge, Button, Modal, Sidebar, ProviderIcon, etc.)
-│   │   ├── constants/            # Provider definitions (348), model lists, pricing, routing strategies, MCP scopes
+│   │   ├── constants/            # Provider definitions (346), model lists, pricing, routing strategies, MCP scopes
 │   │   ├── contracts/            # Shared API contracts
 │   │   ├── hooks/                # React hooks
 │   │   ├── middleware/           # Shared middleware utilities
@@ -211,7 +211,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── moderations.ts        # Content moderation
 │   │   ├── rerank.ts             # Reranking API
 │   │   └── search.ts             # Web search API
-│   ├── mcp-server/               # Built-in MCP server (110 tools, 3 transports: stdio/SSE/streamable-HTTP)
+│   ├── mcp-server/               # Built-in MCP server (109 tools, 3 transports: stdio/SSE/streamable-HTTP)
 │   │   ├── server.ts             # MCP server core (tool registration, scope enforcement)
 │   │   ├── tools/                # Tool implementations (advancedTools, memoryTools, skillTools)
 │   │   ├── schemas/              # Zod input schemas (tools, audit, a2a)
@@ -266,7 +266,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── i18n/                     # 43-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
-│   ├── frameworks/               # MCP-SERVER.md (110 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
+│   ├── frameworks/               # MCP-SERVER.md (109 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
 │   ├── routing/                  # AUTO-COMBO.md (14-factor scoring), REASONING_REPLAY.md
 │   ├── security/                 # GUARDRAILS.md, COMPLIANCE.md, STEALTH_GUIDE.md, PUBLIC_CREDS.md, ERROR_SANITIZATION.md
 │   ├── guides/                   # USER_GUIDE.md, TROUBLESHOOTING.md, ELECTRON_GUIDE.md, I18N.md
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **348 AI providers** with automatic format translation
+- **346 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -351,7 +351,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 ### MCP Server (109 Tools)
 
-110 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
+109 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
 diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool**, **notion**,
 **obsidian**, **localCorpus**, **gamification**, and **plugin** modules. Full per-tool inventory:
 `docs/frameworks/MCP-SERVER.md`.
@@ -479,10 +479,10 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **348-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **346-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
-- **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
+- **MCP server expanded to 109 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
 - **Cloud Agents** (Codex Cloud, Devin, Jules), **Guardrails**, **Evals**, **Webhooks**, **Compliance** frameworks
 - **Embedded services** manager (install/start/stop bundled services from the dashboard)
 - **Prompt compression** (RTK + Caveman codecs) saving up to ~95% tokens on eligible traffic

docs/i18n/id/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 348 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 346 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (109 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -169,7 +169,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   └── manager.ts            # MITM proxy manager
 │   ├── shared/                   # Shared utilities, components, and constants
 │   │   ├── components/           # Reusable UI components (Card, Badge, Button, Modal, Sidebar, ProviderIcon, etc.)
-│   │   ├── constants/            # Provider definitions (348), model lists, pricing, routing strategies, MCP scopes
+│   │   ├── constants/            # Provider definitions (346), model lists, pricing, routing strategies, MCP scopes
 │   │   ├── contracts/            # Shared API contracts
 │   │   ├── hooks/                # React hooks
 │   │   ├── middleware/           # Shared middleware utilities
@@ -211,7 +211,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── moderations.ts        # Content moderation
 │   │   ├── rerank.ts             # Reranking API
 │   │   └── search.ts             # Web search API
-│   ├── mcp-server/               # Built-in MCP server (110 tools, 3 transports: stdio/SSE/streamable-HTTP)
+│   ├── mcp-server/               # Built-in MCP server (109 tools, 3 transports: stdio/SSE/streamable-HTTP)
 │   │   ├── server.ts             # MCP server core (tool registration, scope enforcement)
 │   │   ├── tools/                # Tool implementations (advancedTools, memoryTools, skillTools)
 │   │   ├── schemas/              # Zod input schemas (tools, audit, a2a)
@@ -266,7 +266,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── i18n/                     # 43-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
-│   ├── frameworks/               # MCP-SERVER.md (110 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
+│   ├── frameworks/               # MCP-SERVER.md (109 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
 │   ├── routing/                  # AUTO-COMBO.md (14-factor scoring), REASONING_REPLAY.md
 │   ├── security/                 # GUARDRAILS.md, COMPLIANCE.md, STEALTH_GUIDE.md, PUBLIC_CREDS.md, ERROR_SANITIZATION.md
 │   ├── guides/                   # USER_GUIDE.md, TROUBLESHOOTING.md, ELECTRON_GUIDE.md, I18N.md
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **348 AI providers** with automatic format translation
+- **346 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -351,7 +351,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 ### MCP Server (109 Tools)
 
-110 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
+109 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
 diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool**, **notion**,
 **obsidian**, **localCorpus**, **gamification**, and **plugin** modules. Full per-tool inventory:
 `docs/frameworks/MCP-SERVER.md`.
@@ -479,10 +479,10 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **348-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **346-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
-- **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
+- **MCP server expanded to 109 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
 - **Cloud Agents** (Codex Cloud, Devin, Jules), **Guardrails**, **Evals**, **Webhooks**, **Compliance** frameworks
 - **Embedded services** manager (install/start/stop bundled services from the dashboard)
 - **Prompt compression** (RTK + Caveman codecs) saving up to ~95% tokens on eligible traffic

docs/i18n/in/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 348 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 346 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (109 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -169,7 +169,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   └── manager.ts            # MITM proxy manager
 │   ├── shared/                   # Shared utilities, components, and constants
 │   │   ├── components/           # Reusable UI components (Card, Badge, Button, Modal, Sidebar, ProviderIcon, etc.)
-│   │   ├── constants/            # Provider definitions (348), model lists, pricing, routing strategies, MCP scopes
+│   │   ├── constants/            # Provider definitions (346), model lists, pricing, routing strategies, MCP scopes
 │   │   ├── contracts/            # Shared API contracts
 │   │   ├── hooks/                # React hooks
 │   │   ├── middleware/           # Shared middleware utilities
@@ -211,7 +211,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── moderations.ts        # Content moderation
 │   │   ├── rerank.ts             # Reranking API
 │   │   └── search.ts             # Web search API
-│   ├── mcp-server/               # Built-in MCP server (110 tools, 3 transports: stdio/SSE/streamable-HTTP)
+│   ├── mcp-server/               # Built-in MCP server (109 tools, 3 transports: stdio/SSE/streamable-HTTP)
 │   │   ├── server.ts             # MCP server core (tool registration, scope enforcement)
 │   │   ├── tools/                # Tool implementations (advancedTools, memoryTools, skillTools)
 │   │   ├── schemas/              # Zod input schemas (tools, audit, a2a)
@@ -266,7 +266,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── i18n/                     # 43-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
-│   ├── frameworks/               # MCP-SERVER.md (110 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
+│   ├── frameworks/               # MCP-SERVER.md (109 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
 │   ├── routing/                  # AUTO-COMBO.md (14-factor scoring), REASONING_REPLAY.md
 │   ├── security/                 # GUARDRAILS.md, COMPLIANCE.md, STEALTH_GUIDE.md, PUBLIC_CREDS.md, ERROR_SANITIZATION.md
 │   ├── guides/                   # USER_GUIDE.md, TROUBLESHOOTING.md, ELECTRON_GUIDE.md, I18N.md
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **348 AI providers** with automatic format translation
+- **346 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -351,7 +351,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 ### MCP Server (109 Tools)
 
-110 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
+109 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
 diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool**, **notion**,
 **obsidian**, **localCorpus**, **gamification**, and **plugin** modules. Full per-tool inventory:
 `docs/frameworks/MCP-SERVER.md`.
@@ -479,10 +479,10 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **348-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **346-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
-- **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
+- **MCP server expanded to 109 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
 - **Cloud Agents** (Codex Cloud, Devin, Jules), **Guardrails**, **Evals**, **Webhooks**, **Compliance** frameworks
 - **Embedded services** manager (install/start/stop bundled services from the dashboard)
 - **Prompt compression** (RTK + Caveman codecs) saving up to ~95% tokens on eligible traffic

docs/i18n/it/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 348 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 346 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (109 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -169,7 +169,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   └── manager.ts            # MITM proxy manager
 │   ├── shared/                   # Shared utilities, components, and constants
 │   │   ├── components/           # Reusable UI components (Card, Badge, Button, Modal, Sidebar, ProviderIcon, etc.)
-│   │   ├── constants/            # Provider definitions (348), model lists, pricing, routing strategies, MCP scopes
+│   │   ├── constants/            # Provider definitions (346), model lists, pricing, routing strategies, MCP scopes
 │   │   ├── contracts/            # Shared API contracts
 │   │   ├── hooks/                # React hooks
 │   │   ├── middleware/           # Shared middleware utilities
@@ -211,7 +211,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── moderations.ts        # Content moderation
 │   │   ├── rerank.ts             # Reranking API
 │   │   └── search.ts             # Web search API
-│   ├── mcp-server/               # Built-in MCP server (110 tools, 3 transports: stdio/SSE/streamable-HTTP)
+│   ├── mcp-server/               # Built-in MCP server (109 tools, 3 transports: stdio/SSE/streamable-HTTP)
 │   │   ├── server.ts             # MCP server core (tool registration, scope enforcement)
 │   │   ├── tools/                # Tool implementations (advancedTools, memoryTools, skillTools)
 │   │   ├── schemas/              # Zod input schemas (tools, audit, a2a)
@@ -266,7 +266,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── i18n/                     # 43-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
-│   ├── frameworks/               # MCP-SERVER.md (110 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
+│   ├── frameworks/               # MCP-SERVER.md (109 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
 │   ├── routing/                  # AUTO-COMBO.md (14-factor scoring), REASONING_REPLAY.md
 │   ├── security/                 # GUARDRAILS.md, COMPLIANCE.md, STEALTH_GUIDE.md, PUBLIC_CREDS.md, ERROR_SANITIZATION.md
 │   ├── guides/                   # USER_GUIDE.md, TROUBLESHOOTING.md, ELECTRON_GUIDE.md, I18N.md
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **348 AI providers** with automatic format translation
+- **346 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -351,7 +351,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 ### MCP Server (109 Tools)
 
-110 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
+109 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
 diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool**, **notion**,
 **obsidian**, **localCorpus**, **gamification**, and **plugin** modules. Full per-tool inventory:
 `docs/frameworks/MCP-SERVER.md`.
@@ -479,10 +479,10 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **348-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **346-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
-- **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
+- **MCP server expanded to 109 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
 - **Cloud Agents** (Codex Cloud, Devin, Jules), **Guardrails**, **Evals**, **Webhooks**, **Compliance** frameworks
 - **Embedded services** manager (install/start/stop bundled services from the dashboard)
 - **Prompt compression** (RTK + Caveman codecs) saving up to ~95% tokens on eligible traffic

docs/i18n/ja/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 348 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 346 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (109 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -169,7 +169,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   └── manager.ts            # MITM proxy manager
 │   ├── shared/                   # Shared utilities, components, and constants
 │   │   ├── components/           # Reusable UI components (Card, Badge, Button, Modal, Sidebar, ProviderIcon, etc.)
-│   │   ├── constants/            # Provider definitions (348), model lists, pricing, routing strategies, MCP scopes
+│   │   ├── constants/            # Provider definitions (346), model lists, pricing, routing strategies, MCP scopes
 │   │   ├── contracts/            # Shared API contracts
 │   │   ├── hooks/                # React hooks
 │   │   ├── middleware/           # Shared middleware utilities
@@ -211,7 +211,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── moderations.ts        # Content moderation
 │   │   ├── rerank.ts             # Reranking API
 │   │   └── search.ts             # Web search API
-│   ├── mcp-server/               # Built-in MCP server (110 tools, 3 transports: stdio/SSE/streamable-HTTP)
+│   ├── mcp-server/               # Built-in MCP server (109 tools, 3 transports: stdio/SSE/streamable-HTTP)
 │   │   ├── server.ts             # MCP server core (tool registration, scope enforcement)
 │   │   ├── tools/                # Tool implementations (advancedTools, memoryTools, skillTools)
 │   │   ├── schemas/              # Zod input schemas (tools, audit, a2a)
@@ -266,7 +266,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── i18n/                     # 43-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
-│   ├── frameworks/               # MCP-SERVER.md (110 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
+│   ├── frameworks/               # MCP-SERVER.md (109 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
 │   ├── routing/                  # AUTO-COMBO.md (14-factor scoring), REASONING_REPLAY.md
 │   ├── security/                 # GUARDRAILS.md, COMPLIANCE.md, STEALTH_GUIDE.md, PUBLIC_CREDS.md, ERROR_SANITIZATION.md
 │   ├── guides/                   # USER_GUIDE.md, TROUBLESHOOTING.md, ELECTRON_GUIDE.md, I18N.md
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **348 AI providers** with automatic format translation
+- **346 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -351,7 +351,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 ### MCP Server (109 Tools)
 
-110 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
+109 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
 diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool**, **notion**,
 **obsidian**, **localCorpus**, **gamification**, and **plugin** modules. Full per-tool inventory:
 `docs/frameworks/MCP-SERVER.md`.
@@ -479,10 +479,10 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **348-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **346-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
-- **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
+- **MCP server expanded to 109 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
 - **Cloud Agents** (Codex Cloud, Devin, Jules), **Guardrails**, **Evals**, **Webhooks**, **Compliance** frameworks
 - **Embedded services** manager (install/start/stop bundled services from the dashboard)
 - **Prompt compression** (RTK + Caveman codecs) saving up to ~95% tokens on eligible traffic

docs/i18n/ko/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 348 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 346 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (109 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -169,7 +169,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   └── manager.ts            # MITM proxy manager
 │   ├── shared/                   # Shared utilities, components, and constants
 │   │   ├── components/           # Reusable UI components (Card, Badge, Button, Modal, Sidebar, ProviderIcon, etc.)
-│   │   ├── constants/            # Provider definitions (348), model lists, pricing, routing strategies, MCP scopes
+│   │   ├── constants/            # Provider definitions (346), model lists, pricing, routing strategies, MCP scopes
 │   │   ├── contracts/            # Shared API contracts
 │   │   ├── hooks/                # React hooks
 │   │   ├── middleware/           # Shared middleware utilities
@@ -211,7 +211,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── moderations.ts        # Content moderation
 │   │   ├── rerank.ts             # Reranking API
 │   │   └── search.ts             # Web search API
-│   ├── mcp-server/               # Built-in MCP server (110 tools, 3 transports: stdio/SSE/streamable-HTTP)
+│   ├── mcp-server/               # Built-in MCP server (109 tools, 3 transports: stdio/SSE/streamable-HTTP)
 │   │   ├── server.ts             # MCP server core (tool registration, scope enforcement)
 │   │   ├── tools/                # Tool implementations (advancedTools, memoryTools, skillTools)
 │   │   ├── schemas/              # Zod input schemas (tools, audit, a2a)
@@ -266,7 +266,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── i18n/                     # 43-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
-│   ├── frameworks/               # MCP-SERVER.md (110 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
+│   ├── frameworks/               # MCP-SERVER.md (109 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
 │   ├── routing/                  # AUTO-COMBO.md (14-factor scoring), REASONING_REPLAY.md
 │   ├── security/                 # GUARDRAILS.md, COMPLIANCE.md, STEALTH_GUIDE.md, PUBLIC_CREDS.md, ERROR_SANITIZATION.md
 │   ├── guides/                   # USER_GUIDE.md, TROUBLESHOOTING.md, ELECTRON_GUIDE.md, I18N.md
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **348 AI providers** with automatic format translation
+- **346 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -351,7 +351,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 ### MCP Server (109 Tools)
 
-110 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
+109 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
 diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool**, **notion**,
 **obsidian**, **localCorpus**, **gamification**, and **plugin** modules. Full per-tool inventory:
 `docs/frameworks/MCP-SERVER.md`.
@@ -479,10 +479,10 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **348-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **346-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
-- **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
+- **MCP server expanded to 109 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
 - **Cloud Agents** (Codex Cloud, Devin, Jules), **Guardrails**, **Evals**, **Webhooks**, **Compliance** frameworks
 - **Embedded services** manager (install/start/stop bundled services from the dashboard)
 - **Prompt compression** (RTK + Caveman codecs) saving up to ~95% tokens on eligible traffic

docs/i18n/mr/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 348 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 346 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (109 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -169,7 +169,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   └── manager.ts            # MITM proxy manager
 │   ├── shared/                   # Shared utilities, components, and constants
 │   │   ├── components/           # Reusable UI components (Card, Badge, Button, Modal, Sidebar, ProviderIcon, etc.)
-│   │   ├── constants/            # Provider definitions (348), model lists, pricing, routing strategies, MCP scopes
+│   │   ├── constants/            # Provider definitions (346), model lists, pricing, routing strategies, MCP scopes
 │   │   ├── contracts/            # Shared API contracts
 │   │   ├── hooks/                # React hooks
 │   │   ├── middleware/           # Shared middleware utilities
@@ -211,7 +211,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── moderations.ts        # Content moderation
 │   │   ├── rerank.ts             # Reranking API
 │   │   └── search.ts             # Web search API
-│   ├── mcp-server/               # Built-in MCP server (110 tools, 3 transports: stdio/SSE/streamable-HTTP)
+│   ├── mcp-server/               # Built-in MCP server (109 tools, 3 transports: stdio/SSE/streamable-HTTP)
 │   │   ├── server.ts             # MCP server core (tool registration, scope enforcement)
 │   │   ├── tools/                # Tool implementations (advancedTools, memoryTools, skillTools)
 │   │   ├── schemas/              # Zod input schemas (tools, audit, a2a)
@@ -266,7 +266,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── i18n/                     # 43-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
-│   ├── frameworks/               # MCP-SERVER.md (110 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
+│   ├── frameworks/               # MCP-SERVER.md (109 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
 │   ├── routing/                  # AUTO-COMBO.md (14-factor scoring), REASONING_REPLAY.md
 │   ├── security/                 # GUARDRAILS.md, COMPLIANCE.md, STEALTH_GUIDE.md, PUBLIC_CREDS.md, ERROR_SANITIZATION.md
 │   ├── guides/                   # USER_GUIDE.md, TROUBLESHOOTING.md, ELECTRON_GUIDE.md, I18N.md
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **348 AI providers** with automatic format translation
+- **346 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -351,7 +351,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 ### MCP Server (109 Tools)
 
-110 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
+109 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
 diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool**, **notion**,
 **obsidian**, **localCorpus**, **gamification**, and **plugin** modules. Full per-tool inventory:
 `docs/frameworks/MCP-SERVER.md`.
@@ -479,10 +479,10 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **348-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **346-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
-- **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
+- **MCP server expanded to 109 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
 - **Cloud Agents** (Codex Cloud, Devin, Jules), **Guardrails**, **Evals**, **Webhooks**, **Compliance** frameworks
 - **Embedded services** manager (install/start/stop bundled services from the dashboard)
 - **Prompt compression** (RTK + Caveman codecs) saving up to ~95% tokens on eligible traffic

docs/i18n/ms/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 348 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 346 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (109 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -169,7 +169,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   └── manager.ts            # MITM proxy manager
 │   ├── shared/                   # Shared utilities, components, and constants
 │   │   ├── components/           # Reusable UI components (Card, Badge, Button, Modal, Sidebar, ProviderIcon, etc.)
-│   │   ├── constants/            # Provider definitions (348), model lists, pricing, routing strategies, MCP scopes
+│   │   ├── constants/            # Provider definitions (346), model lists, pricing, routing strategies, MCP scopes
 │   │   ├── contracts/            # Shared API contracts
 │   │   ├── hooks/                # React hooks
 │   │   ├── middleware/           # Shared middleware utilities
@@ -211,7 +211,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── moderations.ts        # Content moderation
 │   │   ├── rerank.ts             # Reranking API
 │   │   └── search.ts             # Web search API
-│   ├── mcp-server/               # Built-in MCP server (110 tools, 3 transports: stdio/SSE/streamable-HTTP)
+│   ├── mcp-server/               # Built-in MCP server (109 tools, 3 transports: stdio/SSE/streamable-HTTP)
 │   │   ├── server.ts             # MCP server core (tool registration, scope enforcement)
 │   │   ├── tools/                # Tool implementations (advancedTools, memoryTools, skillTools)
 │   │   ├── schemas/              # Zod input schemas (tools, audit, a2a)
@@ -266,7 +266,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── i18n/                     # 43-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
-│   ├── frameworks/               # MCP-SERVER.md (110 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
+│   ├── frameworks/               # MCP-SERVER.md (109 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
 │   ├── routing/                  # AUTO-COMBO.md (14-factor scoring), REASONING_REPLAY.md
 │   ├── security/                 # GUARDRAILS.md, COMPLIANCE.md, STEALTH_GUIDE.md, PUBLIC_CREDS.md, ERROR_SANITIZATION.md
 │   ├── guides/                   # USER_GUIDE.md, TROUBLESHOOTING.md, ELECTRON_GUIDE.md, I18N.md
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **348 AI providers** with automatic format translation
+- **346 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -351,7 +351,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 ### MCP Server (109 Tools)
 
-110 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
+109 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
 diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool**, **notion**,
 **obsidian**, **localCorpus**, **gamification**, and **plugin** modules. Full per-tool inventory:
 `docs/frameworks/MCP-SERVER.md`.
@@ -479,10 +479,10 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **348-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **346-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
-- **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
+- **MCP server expanded to 109 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
 - **Cloud Agents** (Codex Cloud, Devin, Jules), **Guardrails**, **Evals**, **Webhooks**, **Compliance** frameworks
 - **Embedded services** manager (install/start/stop bundled services from the dashboard)
 - **Prompt compression** (RTK + Caveman codecs) saving up to ~95% tokens on eligible traffic

docs/i18n/nl/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 348 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 346 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (109 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -169,7 +169,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   └── manager.ts            # MITM proxy manager
 │   ├── shared/                   # Shared utilities, components, and constants
 │   │   ├── components/           # Reusable UI components (Card, Badge, Button, Modal, Sidebar, ProviderIcon, etc.)
-│   │   ├── constants/            # Provider definitions (348), model lists, pricing, routing strategies, MCP scopes
+│   │   ├── constants/            # Provider definitions (346), model lists, pricing, routing strategies, MCP scopes
 │   │   ├── contracts/            # Shared API contracts
 │   │   ├── hooks/                # React hooks
 │   │   ├── middleware/           # Shared middleware utilities
@@ -211,7 +211,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── moderations.ts        # Content moderation
 │   │   ├── rerank.ts             # Reranking API
 │   │   └── search.ts             # Web search API
-│   ├── mcp-server/               # Built-in MCP server (110 tools, 3 transports: stdio/SSE/streamable-HTTP)
+│   ├── mcp-server/               # Built-in MCP server (109 tools, 3 transports: stdio/SSE/streamable-HTTP)
 │   │   ├── server.ts             # MCP server core (tool registration, scope enforcement)
 │   │   ├── tools/                # Tool implementations (advancedTools, memoryTools, skillTools)
 │   │   ├── schemas/              # Zod input schemas (tools, audit, a2a)
@@ -266,7 +266,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── i18n/                     # 43-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
-│   ├── frameworks/               # MCP-SERVER.md (110 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
+│   ├── frameworks/               # MCP-SERVER.md (109 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
 │   ├── routing/                  # AUTO-COMBO.md (14-factor scoring), REASONING_REPLAY.md
 │   ├── security/                 # GUARDRAILS.md, COMPLIANCE.md, STEALTH_GUIDE.md, PUBLIC_CREDS.md, ERROR_SANITIZATION.md
 │   ├── guides/                   # USER_GUIDE.md, TROUBLESHOOTING.md, ELECTRON_GUIDE.md, I18N.md
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **348 AI providers** with automatic format translation
+- **346 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -351,7 +351,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 ### MCP Server (109 Tools)
 
-110 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
+109 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
 diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool**, **notion**,
 **obsidian**, **localCorpus**, **gamification**, and **plugin** modules. Full per-tool inventory:
 `docs/frameworks/MCP-SERVER.md`.
@@ -479,10 +479,10 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **348-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **346-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
-- **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
+- **MCP server expanded to 109 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
 - **Cloud Agents** (Codex Cloud, Devin, Jules), **Guardrails**, **Evals**, **Webhooks**, **Compliance** frameworks
 - **Embedded services** manager (install/start/stop bundled services from the dashboard)
 - **Prompt compression** (RTK + Caveman codecs) saving up to ~95% tokens on eligible traffic

docs/i18n/no/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 348 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 346 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (109 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -169,7 +169,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   └── manager.ts            # MITM proxy manager
 │   ├── shared/                   # Shared utilities, components, and constants
 │   │   ├── components/           # Reusable UI components (Card, Badge, Button, Modal, Sidebar, ProviderIcon, etc.)
-│   │   ├── constants/            # Provider definitions (348), model lists, pricing, routing strategies, MCP scopes
+│   │   ├── constants/            # Provider definitions (346), model lists, pricing, routing strategies, MCP scopes
 │   │   ├── contracts/            # Shared API contracts
 │   │   ├── hooks/                # React hooks
 │   │   ├── middleware/           # Shared middleware utilities
@@ -211,7 +211,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── moderations.ts        # Content moderation
 │   │   ├── rerank.ts             # Reranking API
 │   │   └── search.ts             # Web search API
-│   ├── mcp-server/               # Built-in MCP server (110 tools, 3 transports: stdio/SSE/streamable-HTTP)
+│   ├── mcp-server/               # Built-in MCP server (109 tools, 3 transports: stdio/SSE/streamable-HTTP)
 │   │   ├── server.ts             # MCP server core (tool registration, scope enforcement)
 │   │   ├── tools/                # Tool implementations (advancedTools, memoryTools, skillTools)
 │   │   ├── schemas/              # Zod input schemas (tools, audit, a2a)
@@ -266,7 +266,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── i18n/                     # 43-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
-│   ├── frameworks/               # MCP-SERVER.md (110 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
+│   ├── frameworks/               # MCP-SERVER.md (109 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
 │   ├── routing/                  # AUTO-COMBO.md (14-factor scoring), REASONING_REPLAY.md
 │   ├── security/                 # GUARDRAILS.md, COMPLIANCE.md, STEALTH_GUIDE.md, PUBLIC_CREDS.md, ERROR_SANITIZATION.md
 │   ├── guides/                   # USER_GUIDE.md, TROUBLESHOOTING.md, ELECTRON_GUIDE.md, I18N.md
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **348 AI providers** with automatic format translation
+- **346 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -351,7 +351,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 ### MCP Server (109 Tools)
 
-110 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
+109 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
 diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool**, **notion**,
 **obsidian**, **localCorpus**, **gamification**, and **plugin** modules. Full per-tool inventory:
 `docs/frameworks/MCP-SERVER.md`.
@@ -479,10 +479,10 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **348-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **346-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
-- **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
+- **MCP server expanded to 109 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
 - **Cloud Agents** (Codex Cloud, Devin, Jules), **Guardrails**, **Evals**, **Webhooks**, **Compliance** frameworks
 - **Embedded services** manager (install/start/stop bundled services from the dashboard)
 - **Prompt compression** (RTK + Caveman codecs) saving up to ~95% tokens on eligible traffic

docs/i18n/phi/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 348 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 346 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (109 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -169,7 +169,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   └── manager.ts            # MITM proxy manager
 │   ├── shared/                   # Shared utilities, components, and constants
 │   │   ├── components/           # Reusable UI components (Card, Badge, Button, Modal, Sidebar, ProviderIcon, etc.)
-│   │   ├── constants/            # Provider definitions (348), model lists, pricing, routing strategies, MCP scopes
+│   │   ├── constants/            # Provider definitions (346), model lists, pricing, routing strategies, MCP scopes
 │   │   ├── contracts/            # Shared API contracts
 │   │   ├── hooks/                # React hooks
 │   │   ├── middleware/           # Shared middleware utilities
@@ -211,7 +211,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── moderations.ts        # Content moderation
 │   │   ├── rerank.ts             # Reranking API
 │   │   └── search.ts             # Web search API
-│   ├── mcp-server/               # Built-in MCP server (110 tools, 3 transports: stdio/SSE/streamable-HTTP)
+│   ├── mcp-server/               # Built-in MCP server (109 tools, 3 transports: stdio/SSE/streamable-HTTP)
 │   │   ├── server.ts             # MCP server core (tool registration, scope enforcement)
 │   │   ├── tools/                # Tool implementations (advancedTools, memoryTools, skillTools)
 │   │   ├── schemas/              # Zod input schemas (tools, audit, a2a)
@@ -266,7 +266,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── i18n/                     # 43-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
-│   ├── frameworks/               # MCP-SERVER.md (110 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
+│   ├── frameworks/               # MCP-SERVER.md (109 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
 │   ├── routing/                  # AUTO-COMBO.md (14-factor scoring), REASONING_REPLAY.md
 │   ├── security/                 # GUARDRAILS.md, COMPLIANCE.md, STEALTH_GUIDE.md, PUBLIC_CREDS.md, ERROR_SANITIZATION.md
 │   ├── guides/                   # USER_GUIDE.md, TROUBLESHOOTING.md, ELECTRON_GUIDE.md, I18N.md
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **348 AI providers** with automatic format translation
+- **346 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -351,7 +351,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 ### MCP Server (109 Tools)
 
-110 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
+109 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
 diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool**, **notion**,
 **obsidian**, **localCorpus**, **gamification**, and **plugin** modules. Full per-tool inventory:
 `docs/frameworks/MCP-SERVER.md`.
@@ -479,10 +479,10 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **348-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **346-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
-- **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
+- **MCP server expanded to 109 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
 - **Cloud Agents** (Codex Cloud, Devin, Jules), **Guardrails**, **Evals**, **Webhooks**, **Compliance** frameworks
 - **Embedded services** manager (install/start/stop bundled services from the dashboard)
 - **Prompt compression** (RTK + Caveman codecs) saving up to ~95% tokens on eligible traffic

docs/i18n/pl/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 348 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 346 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (109 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -169,7 +169,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   └── manager.ts            # MITM proxy manager
 │   ├── shared/                   # Shared utilities, components, and constants
 │   │   ├── components/           # Reusable UI components (Card, Badge, Button, Modal, Sidebar, ProviderIcon, etc.)
-│   │   ├── constants/            # Provider definitions (348), model lists, pricing, routing strategies, MCP scopes
+│   │   ├── constants/            # Provider definitions (346), model lists, pricing, routing strategies, MCP scopes
 │   │   ├── contracts/            # Shared API contracts
 │   │   ├── hooks/                # React hooks
 │   │   ├── middleware/           # Shared middleware utilities
@@ -211,7 +211,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── moderations.ts        # Content moderation
 │   │   ├── rerank.ts             # Reranking API
 │   │   └── search.ts             # Web search API
-│   ├── mcp-server/               # Built-in MCP server (110 tools, 3 transports: stdio/SSE/streamable-HTTP)
+│   ├── mcp-server/               # Built-in MCP server (109 tools, 3 transports: stdio/SSE/streamable-HTTP)
 │   │   ├── server.ts             # MCP server core (tool registration, scope enforcement)
 │   │   ├── tools/                # Tool implementations (advancedTools, memoryTools, skillTools)
 │   │   ├── schemas/              # Zod input schemas (tools, audit, a2a)
@@ -266,7 +266,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── i18n/                     # 43-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
-│   ├── frameworks/               # MCP-SERVER.md (110 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
+│   ├── frameworks/               # MCP-SERVER.md (109 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
 │   ├── routing/                  # AUTO-COMBO.md (14-factor scoring), REASONING_REPLAY.md
 │   ├── security/                 # GUARDRAILS.md, COMPLIANCE.md, STEALTH_GUIDE.md, PUBLIC_CREDS.md, ERROR_SANITIZATION.md
 │   ├── guides/                   # USER_GUIDE.md, TROUBLESHOOTING.md, ELECTRON_GUIDE.md, I18N.md
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **348 AI providers** with automatic format translation
+- **346 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -351,7 +351,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 ### MCP Server (109 Tools)
 
-110 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
+109 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
 diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool**, **notion**,
 **obsidian**, **localCorpus**, **gamification**, and **plugin** modules. Full per-tool inventory:
 `docs/frameworks/MCP-SERVER.md`.
@@ -479,10 +479,10 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **348-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **346-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
-- **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
+- **MCP server expanded to 109 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
 - **Cloud Agents** (Codex Cloud, Devin, Jules), **Guardrails**, **Evals**, **Webhooks**, **Compliance** frameworks
 - **Embedded services** manager (install/start/stop bundled services from the dashboard)
 - **Prompt compression** (RTK + Caveman codecs) saving up to ~95% tokens on eligible traffic

docs/i18n/pt-BR/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 348 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 346 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (109 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -169,7 +169,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   └── manager.ts            # MITM proxy manager
 │   ├── shared/                   # Shared utilities, components, and constants
 │   │   ├── components/           # Reusable UI components (Card, Badge, Button, Modal, Sidebar, ProviderIcon, etc.)
-│   │   ├── constants/            # Provider definitions (348), model lists, pricing, routing strategies, MCP scopes
+│   │   ├── constants/            # Provider definitions (346), model lists, pricing, routing strategies, MCP scopes
 │   │   ├── contracts/            # Shared API contracts
 │   │   ├── hooks/                # React hooks
 │   │   ├── middleware/           # Shared middleware utilities
@@ -211,7 +211,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── moderations.ts        # Content moderation
 │   │   ├── rerank.ts             # Reranking API
 │   │   └── search.ts             # Web search API
-│   ├── mcp-server/               # Built-in MCP server (110 tools, 3 transports: stdio/SSE/streamable-HTTP)
+│   ├── mcp-server/               # Built-in MCP server (109 tools, 3 transports: stdio/SSE/streamable-HTTP)
 │   │   ├── server.ts             # MCP server core (tool registration, scope enforcement)
 │   │   ├── tools/                # Tool implementations (advancedTools, memoryTools, skillTools)
 │   │   ├── schemas/              # Zod input schemas (tools, audit, a2a)
@@ -266,7 +266,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── i18n/                     # 43-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
-│   ├── frameworks/               # MCP-SERVER.md (110 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
+│   ├── frameworks/               # MCP-SERVER.md (109 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
 │   ├── routing/                  # AUTO-COMBO.md (14-factor scoring), REASONING_REPLAY.md
 │   ├── security/                 # GUARDRAILS.md, COMPLIANCE.md, STEALTH_GUIDE.md, PUBLIC_CREDS.md, ERROR_SANITIZATION.md
 │   ├── guides/                   # USER_GUIDE.md, TROUBLESHOOTING.md, ELECTRON_GUIDE.md, I18N.md
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **348 AI providers** with automatic format translation
+- **346 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -351,7 +351,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 ### MCP Server (109 Tools)
 
-110 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
+109 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
 diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool**, **notion**,
 **obsidian**, **localCorpus**, **gamification**, and **plugin** modules. Full per-tool inventory:
 `docs/frameworks/MCP-SERVER.md`.
@@ -479,10 +479,10 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **348-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **346-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
-- **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
+- **MCP server expanded to 109 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
 - **Cloud Agents** (Codex Cloud, Devin, Jules), **Guardrails**, **Evals**, **Webhooks**, **Compliance** frameworks
 - **Embedded services** manager (install/start/stop bundled services from the dashboard)
 - **Prompt compression** (RTK + Caveman codecs) saving up to ~95% tokens on eligible traffic

docs/i18n/pt/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 348 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 346 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (109 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -169,7 +169,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   └── manager.ts            # MITM proxy manager
 │   ├── shared/                   # Shared utilities, components, and constants
 │   │   ├── components/           # Reusable UI components (Card, Badge, Button, Modal, Sidebar, ProviderIcon, etc.)
-│   │   ├── constants/            # Provider definitions (348), model lists, pricing, routing strategies, MCP scopes
+│   │   ├── constants/            # Provider definitions (346), model lists, pricing, routing strategies, MCP scopes
 │   │   ├── contracts/            # Shared API contracts
 │   │   ├── hooks/                # React hooks
 │   │   ├── middleware/           # Shared middleware utilities
@@ -211,7 +211,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── moderations.ts        # Content moderation
 │   │   ├── rerank.ts             # Reranking API
 │   │   └── search.ts             # Web search API
-│   ├── mcp-server/               # Built-in MCP server (110 tools, 3 transports: stdio/SSE/streamable-HTTP)
+│   ├── mcp-server/               # Built-in MCP server (109 tools, 3 transports: stdio/SSE/streamable-HTTP)
 │   │   ├── server.ts             # MCP server core (tool registration, scope enforcement)
 │   │   ├── tools/                # Tool implementations (advancedTools, memoryTools, skillTools)
 │   │   ├── schemas/              # Zod input schemas (tools, audit, a2a)
@@ -266,7 +266,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── i18n/                     # 43-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
-│   ├── frameworks/               # MCP-SERVER.md (110 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
+│   ├── frameworks/               # MCP-SERVER.md (109 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
 │   ├── routing/                  # AUTO-COMBO.md (14-factor scoring), REASONING_REPLAY.md
 │   ├── security/                 # GUARDRAILS.md, COMPLIANCE.md, STEALTH_GUIDE.md, PUBLIC_CREDS.md, ERROR_SANITIZATION.md
 │   ├── guides/                   # USER_GUIDE.md, TROUBLESHOOTING.md, ELECTRON_GUIDE.md, I18N.md
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **348 AI providers** with automatic format translation
+- **346 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -351,7 +351,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 ### MCP Server (109 Tools)
 
-110 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
+109 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
 diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool**, **notion**,
 **obsidian**, **localCorpus**, **gamification**, and **plugin** modules. Full per-tool inventory:
 `docs/frameworks/MCP-SERVER.md`.
@@ -479,10 +479,10 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **348-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **346-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
-- **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
+- **MCP server expanded to 109 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
 - **Cloud Agents** (Codex Cloud, Devin, Jules), **Guardrails**, **Evals**, **Webhooks**, **Compliance** frameworks
 - **Embedded services** manager (install/start/stop bundled services from the dashboard)
 - **Prompt compression** (RTK + Caveman codecs) saving up to ~95% tokens on eligible traffic

docs/i18n/ro/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 348 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 346 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (109 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -169,7 +169,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   └── manager.ts            # MITM proxy manager
 │   ├── shared/                   # Shared utilities, components, and constants
 │   │   ├── components/           # Reusable UI components (Card, Badge, Button, Modal, Sidebar, ProviderIcon, etc.)
-│   │   ├── constants/            # Provider definitions (348), model lists, pricing, routing strategies, MCP scopes
+│   │   ├── constants/            # Provider definitions (346), model lists, pricing, routing strategies, MCP scopes
 │   │   ├── contracts/            # Shared API contracts
 │   │   ├── hooks/                # React hooks
 │   │   ├── middleware/           # Shared middleware utilities
@@ -211,7 +211,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── moderations.ts        # Content moderation
 │   │   ├── rerank.ts             # Reranking API
 │   │   └── search.ts             # Web search API
-│   ├── mcp-server/               # Built-in MCP server (110 tools, 3 transports: stdio/SSE/streamable-HTTP)
+│   ├── mcp-server/               # Built-in MCP server (109 tools, 3 transports: stdio/SSE/streamable-HTTP)
 │   │   ├── server.ts             # MCP server core (tool registration, scope enforcement)
 │   │   ├── tools/                # Tool implementations (advancedTools, memoryTools, skillTools)
 │   │   ├── schemas/              # Zod input schemas (tools, audit, a2a)
@@ -266,7 +266,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── i18n/                     # 43-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
-│   ├── frameworks/               # MCP-SERVER.md (110 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
+│   ├── frameworks/               # MCP-SERVER.md (109 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
 │   ├── routing/                  # AUTO-COMBO.md (14-factor scoring), REASONING_REPLAY.md
 │   ├── security/                 # GUARDRAILS.md, COMPLIANCE.md, STEALTH_GUIDE.md, PUBLIC_CREDS.md, ERROR_SANITIZATION.md
 │   ├── guides/                   # USER_GUIDE.md, TROUBLESHOOTING.md, ELECTRON_GUIDE.md, I18N.md
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **348 AI providers** with automatic format translation
+- **346 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -351,7 +351,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 ### MCP Server (109 Tools)
 
-110 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
+109 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
 diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool**, **notion**,
 **obsidian**, **localCorpus**, **gamification**, and **plugin** modules. Full per-tool inventory:
 `docs/frameworks/MCP-SERVER.md`.
@@ -479,10 +479,10 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **348-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **346-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
-- **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
+- **MCP server expanded to 109 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
 - **Cloud Agents** (Codex Cloud, Devin, Jules), **Guardrails**, **Evals**, **Webhooks**, **Compliance** frameworks
 - **Embedded services** manager (install/start/stop bundled services from the dashboard)
 - **Prompt compression** (RTK + Caveman codecs) saving up to ~95% tokens on eligible traffic

docs/i18n/ru/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 348 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 346 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (109 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -169,7 +169,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   └── manager.ts            # MITM proxy manager
 │   ├── shared/                   # Shared utilities, components, and constants
 │   │   ├── components/           # Reusable UI components (Card, Badge, Button, Modal, Sidebar, ProviderIcon, etc.)
-│   │   ├── constants/            # Provider definitions (348), model lists, pricing, routing strategies, MCP scopes
+│   │   ├── constants/            # Provider definitions (346), model lists, pricing, routing strategies, MCP scopes
 │   │   ├── contracts/            # Shared API contracts
 │   │   ├── hooks/                # React hooks
 │   │   ├── middleware/           # Shared middleware utilities
@@ -211,7 +211,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── moderations.ts        # Content moderation
 │   │   ├── rerank.ts             # Reranking API
 │   │   └── search.ts             # Web search API
-│   ├── mcp-server/               # Built-in MCP server (110 tools, 3 transports: stdio/SSE/streamable-HTTP)
+│   ├── mcp-server/               # Built-in MCP server (109 tools, 3 transports: stdio/SSE/streamable-HTTP)
 │   │   ├── server.ts             # MCP server core (tool registration, scope enforcement)
 │   │   ├── tools/                # Tool implementations (advancedTools, memoryTools, skillTools)
 │   │   ├── schemas/              # Zod input schemas (tools, audit, a2a)
@@ -266,7 +266,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── i18n/                     # 43-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
-│   ├── frameworks/               # MCP-SERVER.md (110 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
+│   ├── frameworks/               # MCP-SERVER.md (109 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
 │   ├── routing/                  # AUTO-COMBO.md (14-factor scoring), REASONING_REPLAY.md
 │   ├── security/                 # GUARDRAILS.md, COMPLIANCE.md, STEALTH_GUIDE.md, PUBLIC_CREDS.md, ERROR_SANITIZATION.md
 │   ├── guides/                   # USER_GUIDE.md, TROUBLESHOOTING.md, ELECTRON_GUIDE.md, I18N.md
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **348 AI providers** with automatic format translation
+- **346 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -351,7 +351,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 ### MCP Server (109 Tools)
 
-110 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
+109 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
 diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool**, **notion**,
 **obsidian**, **localCorpus**, **gamification**, and **plugin** modules. Full per-tool inventory:
 `docs/frameworks/MCP-SERVER.md`.
@@ -479,10 +479,10 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **348-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **346-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
-- **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
+- **MCP server expanded to 109 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
 - **Cloud Agents** (Codex Cloud, Devin, Jules), **Guardrails**, **Evals**, **Webhooks**, **Compliance** frameworks
 - **Embedded services** manager (install/start/stop bundled services from the dashboard)
 - **Prompt compression** (RTK + Caveman codecs) saving up to ~95% tokens on eligible traffic

docs/i18n/sk/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 348 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 346 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (109 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -169,7 +169,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   └── manager.ts            # MITM proxy manager
 │   ├── shared/                   # Shared utilities, components, and constants
 │   │   ├── components/           # Reusable UI components (Card, Badge, Button, Modal, Sidebar, ProviderIcon, etc.)
-│   │   ├── constants/            # Provider definitions (348), model lists, pricing, routing strategies, MCP scopes
+│   │   ├── constants/            # Provider definitions (346), model lists, pricing, routing strategies, MCP scopes
 │   │   ├── contracts/            # Shared API contracts
 │   │   ├── hooks/                # React hooks
 │   │   ├── middleware/           # Shared middleware utilities
@@ -211,7 +211,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── moderations.ts        # Content moderation
 │   │   ├── rerank.ts             # Reranking API
 │   │   └── search.ts             # Web search API
-│   ├── mcp-server/               # Built-in MCP server (110 tools, 3 transports: stdio/SSE/streamable-HTTP)
+│   ├── mcp-server/               # Built-in MCP server (109 tools, 3 transports: stdio/SSE/streamable-HTTP)
 │   │   ├── server.ts             # MCP server core (tool registration, scope enforcement)
 │   │   ├── tools/                # Tool implementations (advancedTools, memoryTools, skillTools)
 │   │   ├── schemas/              # Zod input schemas (tools, audit, a2a)
@@ -266,7 +266,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── i18n/                     # 43-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
-│   ├── frameworks/               # MCP-SERVER.md (110 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
+│   ├── frameworks/               # MCP-SERVER.md (109 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
 │   ├── routing/                  # AUTO-COMBO.md (14-factor scoring), REASONING_REPLAY.md
 │   ├── security/                 # GUARDRAILS.md, COMPLIANCE.md, STEALTH_GUIDE.md, PUBLIC_CREDS.md, ERROR_SANITIZATION.md
 │   ├── guides/                   # USER_GUIDE.md, TROUBLESHOOTING.md, ELECTRON_GUIDE.md, I18N.md
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **348 AI providers** with automatic format translation
+- **346 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -351,7 +351,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 ### MCP Server (109 Tools)
 
-110 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
+109 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
 diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool**, **notion**,
 **obsidian**, **localCorpus**, **gamification**, and **plugin** modules. Full per-tool inventory:
 `docs/frameworks/MCP-SERVER.md`.
@@ -479,10 +479,10 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **348-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **346-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
-- **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
+- **MCP server expanded to 109 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
 - **Cloud Agents** (Codex Cloud, Devin, Jules), **Guardrails**, **Evals**, **Webhooks**, **Compliance** frameworks
 - **Embedded services** manager (install/start/stop bundled services from the dashboard)
 - **Prompt compression** (RTK + Caveman codecs) saving up to ~95% tokens on eligible traffic

docs/i18n/sv/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 348 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 346 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (109 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -169,7 +169,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   └── manager.ts            # MITM proxy manager
 │   ├── shared/                   # Shared utilities, components, and constants
 │   │   ├── components/           # Reusable UI components (Card, Badge, Button, Modal, Sidebar, ProviderIcon, etc.)
-│   │   ├── constants/            # Provider definitions (348), model lists, pricing, routing strategies, MCP scopes
+│   │   ├── constants/            # Provider definitions (346), model lists, pricing, routing strategies, MCP scopes
 │   │   ├── contracts/            # Shared API contracts
 │   │   ├── hooks/                # React hooks
 │   │   ├── middleware/           # Shared middleware utilities
@@ -211,7 +211,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── moderations.ts        # Content moderation
 │   │   ├── rerank.ts             # Reranking API
 │   │   └── search.ts             # Web search API
-│   ├── mcp-server/               # Built-in MCP server (110 tools, 3 transports: stdio/SSE/streamable-HTTP)
+│   ├── mcp-server/               # Built-in MCP server (109 tools, 3 transports: stdio/SSE/streamable-HTTP)
 │   │   ├── server.ts             # MCP server core (tool registration, scope enforcement)
 │   │   ├── tools/                # Tool implementations (advancedTools, memoryTools, skillTools)
 │   │   ├── schemas/              # Zod input schemas (tools, audit, a2a)
@@ -266,7 +266,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── i18n/                     # 43-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
-│   ├── frameworks/               # MCP-SERVER.md (110 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
+│   ├── frameworks/               # MCP-SERVER.md (109 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
 │   ├── routing/                  # AUTO-COMBO.md (14-factor scoring), REASONING_REPLAY.md
 │   ├── security/                 # GUARDRAILS.md, COMPLIANCE.md, STEALTH_GUIDE.md, PUBLIC_CREDS.md, ERROR_SANITIZATION.md
 │   ├── guides/                   # USER_GUIDE.md, TROUBLESHOOTING.md, ELECTRON_GUIDE.md, I18N.md
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **348 AI providers** with automatic format translation
+- **346 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -351,7 +351,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 ### MCP Server (109 Tools)
 
-110 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
+109 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
 diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool**, **notion**,
 **obsidian**, **localCorpus**, **gamification**, and **plugin** modules. Full per-tool inventory:
 `docs/frameworks/MCP-SERVER.md`.
@@ -479,10 +479,10 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **348-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **346-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
-- **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
+- **MCP server expanded to 109 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
 - **Cloud Agents** (Codex Cloud, Devin, Jules), **Guardrails**, **Evals**, **Webhooks**, **Compliance** frameworks
 - **Embedded services** manager (install/start/stop bundled services from the dashboard)
 - **Prompt compression** (RTK + Caveman codecs) saving up to ~95% tokens on eligible traffic

docs/i18n/sw/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 348 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 346 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (109 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -169,7 +169,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   └── manager.ts            # MITM proxy manager
 │   ├── shared/                   # Shared utilities, components, and constants
 │   │   ├── components/           # Reusable UI components (Card, Badge, Button, Modal, Sidebar, ProviderIcon, etc.)
-│   │   ├── constants/            # Provider definitions (348), model lists, pricing, routing strategies, MCP scopes
+│   │   ├── constants/            # Provider definitions (346), model lists, pricing, routing strategies, MCP scopes
 │   │   ├── contracts/            # Shared API contracts
 │   │   ├── hooks/                # React hooks
 │   │   ├── middleware/           # Shared middleware utilities
@@ -211,7 +211,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── moderations.ts        # Content moderation
 │   │   ├── rerank.ts             # Reranking API
 │   │   └── search.ts             # Web search API
-│   ├── mcp-server/               # Built-in MCP server (110 tools, 3 transports: stdio/SSE/streamable-HTTP)
+│   ├── mcp-server/               # Built-in MCP server (109 tools, 3 transports: stdio/SSE/streamable-HTTP)
 │   │   ├── server.ts             # MCP server core (tool registration, scope enforcement)
 │   │   ├── tools/                # Tool implementations (advancedTools, memoryTools, skillTools)
 │   │   ├── schemas/              # Zod input schemas (tools, audit, a2a)
@@ -266,7 +266,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── i18n/                     # 43-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
-│   ├── frameworks/               # MCP-SERVER.md (110 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
+│   ├── frameworks/               # MCP-SERVER.md (109 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
 │   ├── routing/                  # AUTO-COMBO.md (14-factor scoring), REASONING_REPLAY.md
 │   ├── security/                 # GUARDRAILS.md, COMPLIANCE.md, STEALTH_GUIDE.md, PUBLIC_CREDS.md, ERROR_SANITIZATION.md
 │   ├── guides/                   # USER_GUIDE.md, TROUBLESHOOTING.md, ELECTRON_GUIDE.md, I18N.md
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **348 AI providers** with automatic format translation
+- **346 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -351,7 +351,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 ### MCP Server (109 Tools)
 
-110 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
+109 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
 diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool**, **notion**,
 **obsidian**, **localCorpus**, **gamification**, and **plugin** modules. Full per-tool inventory:
 `docs/frameworks/MCP-SERVER.md`.
@@ -479,10 +479,10 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **348-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **346-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
-- **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
+- **MCP server expanded to 109 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
 - **Cloud Agents** (Codex Cloud, Devin, Jules), **Guardrails**, **Evals**, **Webhooks**, **Compliance** frameworks
 - **Embedded services** manager (install/start/stop bundled services from the dashboard)
 - **Prompt compression** (RTK + Caveman codecs) saving up to ~95% tokens on eligible traffic

docs/i18n/ta/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 348 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 346 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (109 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -169,7 +169,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   └── manager.ts            # MITM proxy manager
 │   ├── shared/                   # Shared utilities, components, and constants
 │   │   ├── components/           # Reusable UI components (Card, Badge, Button, Modal, Sidebar, ProviderIcon, etc.)
-│   │   ├── constants/            # Provider definitions (348), model lists, pricing, routing strategies, MCP scopes
+│   │   ├── constants/            # Provider definitions (346), model lists, pricing, routing strategies, MCP scopes
 │   │   ├── contracts/            # Shared API contracts
 │   │   ├── hooks/                # React hooks
 │   │   ├── middleware/           # Shared middleware utilities
@@ -211,7 +211,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── moderations.ts        # Content moderation
 │   │   ├── rerank.ts             # Reranking API
 │   │   └── search.ts             # Web search API
-│   ├── mcp-server/               # Built-in MCP server (110 tools, 3 transports: stdio/SSE/streamable-HTTP)
+│   ├── mcp-server/               # Built-in MCP server (109 tools, 3 transports: stdio/SSE/streamable-HTTP)
 │   │   ├── server.ts             # MCP server core (tool registration, scope enforcement)
 │   │   ├── tools/                # Tool implementations (advancedTools, memoryTools, skillTools)
 │   │   ├── schemas/              # Zod input schemas (tools, audit, a2a)
@@ -266,7 +266,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── i18n/                     # 43-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
-│   ├── frameworks/               # MCP-SERVER.md (110 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
+│   ├── frameworks/               # MCP-SERVER.md (109 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
 │   ├── routing/                  # AUTO-COMBO.md (14-factor scoring), REASONING_REPLAY.md
 │   ├── security/                 # GUARDRAILS.md, COMPLIANCE.md, STEALTH_GUIDE.md, PUBLIC_CREDS.md, ERROR_SANITIZATION.md
 │   ├── guides/                   # USER_GUIDE.md, TROUBLESHOOTING.md, ELECTRON_GUIDE.md, I18N.md
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **348 AI providers** with automatic format translation
+- **346 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -351,7 +351,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 ### MCP Server (109 Tools)
 
-110 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
+109 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
 diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool**, **notion**,
 **obsidian**, **localCorpus**, **gamification**, and **plugin** modules. Full per-tool inventory:
 `docs/frameworks/MCP-SERVER.md`.
@@ -479,10 +479,10 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **348-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **346-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
-- **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
+- **MCP server expanded to 109 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
 - **Cloud Agents** (Codex Cloud, Devin, Jules), **Guardrails**, **Evals**, **Webhooks**, **Compliance** frameworks
 - **Embedded services** manager (install/start/stop bundled services from the dashboard)
 - **Prompt compression** (RTK + Caveman codecs) saving up to ~95% tokens on eligible traffic

docs/i18n/te/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 348 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 346 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (109 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -169,7 +169,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   └── manager.ts            # MITM proxy manager
 │   ├── shared/                   # Shared utilities, components, and constants
 │   │   ├── components/           # Reusable UI components (Card, Badge, Button, Modal, Sidebar, ProviderIcon, etc.)
-│   │   ├── constants/            # Provider definitions (348), model lists, pricing, routing strategies, MCP scopes
+│   │   ├── constants/            # Provider definitions (346), model lists, pricing, routing strategies, MCP scopes
 │   │   ├── contracts/            # Shared API contracts
 │   │   ├── hooks/                # React hooks
 │   │   ├── middleware/           # Shared middleware utilities
@@ -211,7 +211,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── moderations.ts        # Content moderation
 │   │   ├── rerank.ts             # Reranking API
 │   │   └── search.ts             # Web search API
-│   ├── mcp-server/               # Built-in MCP server (110 tools, 3 transports: stdio/SSE/streamable-HTTP)
+│   ├── mcp-server/               # Built-in MCP server (109 tools, 3 transports: stdio/SSE/streamable-HTTP)
 │   │   ├── server.ts             # MCP server core (tool registration, scope enforcement)
 │   │   ├── tools/                # Tool implementations (advancedTools, memoryTools, skillTools)
 │   │   ├── schemas/              # Zod input schemas (tools, audit, a2a)
@@ -266,7 +266,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── i18n/                     # 43-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
-│   ├── frameworks/               # MCP-SERVER.md (110 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
+│   ├── frameworks/               # MCP-SERVER.md (109 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
 │   ├── routing/                  # AUTO-COMBO.md (14-factor scoring), REASONING_REPLAY.md
 │   ├── security/                 # GUARDRAILS.md, COMPLIANCE.md, STEALTH_GUIDE.md, PUBLIC_CREDS.md, ERROR_SANITIZATION.md
 │   ├── guides/                   # USER_GUIDE.md, TROUBLESHOOTING.md, ELECTRON_GUIDE.md, I18N.md
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **348 AI providers** with automatic format translation
+- **346 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -351,7 +351,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 ### MCP Server (109 Tools)
 
-110 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
+109 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
 diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool**, **notion**,
 **obsidian**, **localCorpus**, **gamification**, and **plugin** modules. Full per-tool inventory:
 `docs/frameworks/MCP-SERVER.md`.
@@ -479,10 +479,10 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **348-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **346-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
-- **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
+- **MCP server expanded to 109 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
 - **Cloud Agents** (Codex Cloud, Devin, Jules), **Guardrails**, **Evals**, **Webhooks**, **Compliance** frameworks
 - **Embedded services** manager (install/start/stop bundled services from the dashboard)
 - **Prompt compression** (RTK + Caveman codecs) saving up to ~95% tokens on eligible traffic

docs/i18n/th/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 348 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 346 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (109 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -169,7 +169,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   └── manager.ts            # MITM proxy manager
 │   ├── shared/                   # Shared utilities, components, and constants
 │   │   ├── components/           # Reusable UI components (Card, Badge, Button, Modal, Sidebar, ProviderIcon, etc.)
-│   │   ├── constants/            # Provider definitions (348), model lists, pricing, routing strategies, MCP scopes
+│   │   ├── constants/            # Provider definitions (346), model lists, pricing, routing strategies, MCP scopes
 │   │   ├── contracts/            # Shared API contracts
 │   │   ├── hooks/                # React hooks
 │   │   ├── middleware/           # Shared middleware utilities
@@ -211,7 +211,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── moderations.ts        # Content moderation
 │   │   ├── rerank.ts             # Reranking API
 │   │   └── search.ts             # Web search API
-│   ├── mcp-server/               # Built-in MCP server (110 tools, 3 transports: stdio/SSE/streamable-HTTP)
+│   ├── mcp-server/               # Built-in MCP server (109 tools, 3 transports: stdio/SSE/streamable-HTTP)
 │   │   ├── server.ts             # MCP server core (tool registration, scope enforcement)
 │   │   ├── tools/                # Tool implementations (advancedTools, memoryTools, skillTools)
 │   │   ├── schemas/              # Zod input schemas (tools, audit, a2a)
@@ -266,7 +266,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── i18n/                     # 43-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
-│   ├── frameworks/               # MCP-SERVER.md (110 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
+│   ├── frameworks/               # MCP-SERVER.md (109 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
 │   ├── routing/                  # AUTO-COMBO.md (14-factor scoring), REASONING_REPLAY.md
 │   ├── security/                 # GUARDRAILS.md, COMPLIANCE.md, STEALTH_GUIDE.md, PUBLIC_CREDS.md, ERROR_SANITIZATION.md
 │   ├── guides/                   # USER_GUIDE.md, TROUBLESHOOTING.md, ELECTRON_GUIDE.md, I18N.md
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **348 AI providers** with automatic format translation
+- **346 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -351,7 +351,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 ### MCP Server (109 Tools)
 
-110 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
+109 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
 diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool**, **notion**,
 **obsidian**, **localCorpus**, **gamification**, and **plugin** modules. Full per-tool inventory:
 `docs/frameworks/MCP-SERVER.md`.
@@ -479,10 +479,10 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **348-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **346-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
-- **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
+- **MCP server expanded to 109 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
 - **Cloud Agents** (Codex Cloud, Devin, Jules), **Guardrails**, **Evals**, **Webhooks**, **Compliance** frameworks
 - **Embedded services** manager (install/start/stop bundled services from the dashboard)
 - **Prompt compression** (RTK + Caveman codecs) saving up to ~95% tokens on eligible traffic

docs/i18n/tr/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 348 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 346 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (109 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -169,7 +169,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   └── manager.ts            # MITM proxy manager
 │   ├── shared/                   # Shared utilities, components, and constants
 │   │   ├── components/           # Reusable UI components (Card, Badge, Button, Modal, Sidebar, ProviderIcon, etc.)
-│   │   ├── constants/            # Provider definitions (348), model lists, pricing, routing strategies, MCP scopes
+│   │   ├── constants/            # Provider definitions (346), model lists, pricing, routing strategies, MCP scopes
 │   │   ├── contracts/            # Shared API contracts
 │   │   ├── hooks/                # React hooks
 │   │   ├── middleware/           # Shared middleware utilities
@@ -211,7 +211,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── moderations.ts        # Content moderation
 │   │   ├── rerank.ts             # Reranking API
 │   │   └── search.ts             # Web search API
-│   ├── mcp-server/               # Built-in MCP server (110 tools, 3 transports: stdio/SSE/streamable-HTTP)
+│   ├── mcp-server/               # Built-in MCP server (109 tools, 3 transports: stdio/SSE/streamable-HTTP)
 │   │   ├── server.ts             # MCP server core (tool registration, scope enforcement)
 │   │   ├── tools/                # Tool implementations (advancedTools, memoryTools, skillTools)
 │   │   ├── schemas/              # Zod input schemas (tools, audit, a2a)
@@ -266,7 +266,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── i18n/                     # 43-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
-│   ├── frameworks/               # MCP-SERVER.md (110 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
+│   ├── frameworks/               # MCP-SERVER.md (109 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
 │   ├── routing/                  # AUTO-COMBO.md (14-factor scoring), REASONING_REPLAY.md
 │   ├── security/                 # GUARDRAILS.md, COMPLIANCE.md, STEALTH_GUIDE.md, PUBLIC_CREDS.md, ERROR_SANITIZATION.md
 │   ├── guides/                   # USER_GUIDE.md, TROUBLESHOOTING.md, ELECTRON_GUIDE.md, I18N.md
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **348 AI providers** with automatic format translation
+- **346 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -351,7 +351,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 ### MCP Server (109 Tools)
 
-110 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
+109 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
 diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool**, **notion**,
 **obsidian**, **localCorpus**, **gamification**, and **plugin** modules. Full per-tool inventory:
 `docs/frameworks/MCP-SERVER.md`.
@@ -479,10 +479,10 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **348-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **346-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
-- **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
+- **MCP server expanded to 109 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
 - **Cloud Agents** (Codex Cloud, Devin, Jules), **Guardrails**, **Evals**, **Webhooks**, **Compliance** frameworks
 - **Embedded services** manager (install/start/stop bundled services from the dashboard)
 - **Prompt compression** (RTK + Caveman codecs) saving up to ~95% tokens on eligible traffic

docs/i18n/uk-UA/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 348 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 346 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (109 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -169,7 +169,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   └── manager.ts            # MITM proxy manager
 │   ├── shared/                   # Shared utilities, components, and constants
 │   │   ├── components/           # Reusable UI components (Card, Badge, Button, Modal, Sidebar, ProviderIcon, etc.)
-│   │   ├── constants/            # Provider definitions (348), model lists, pricing, routing strategies, MCP scopes
+│   │   ├── constants/            # Provider definitions (346), model lists, pricing, routing strategies, MCP scopes
 │   │   ├── contracts/            # Shared API contracts
 │   │   ├── hooks/                # React hooks
 │   │   ├── middleware/           # Shared middleware utilities
@@ -211,7 +211,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── moderations.ts        # Content moderation
 │   │   ├── rerank.ts             # Reranking API
 │   │   └── search.ts             # Web search API
-│   ├── mcp-server/               # Built-in MCP server (110 tools, 3 transports: stdio/SSE/streamable-HTTP)
+│   ├── mcp-server/               # Built-in MCP server (109 tools, 3 transports: stdio/SSE/streamable-HTTP)
 │   │   ├── server.ts             # MCP server core (tool registration, scope enforcement)
 │   │   ├── tools/                # Tool implementations (advancedTools, memoryTools, skillTools)
 │   │   ├── schemas/              # Zod input schemas (tools, audit, a2a)
@@ -266,7 +266,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── i18n/                     # 43-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
-│   ├── frameworks/               # MCP-SERVER.md (110 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
+│   ├── frameworks/               # MCP-SERVER.md (109 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
 │   ├── routing/                  # AUTO-COMBO.md (14-factor scoring), REASONING_REPLAY.md
 │   ├── security/                 # GUARDRAILS.md, COMPLIANCE.md, STEALTH_GUIDE.md, PUBLIC_CREDS.md, ERROR_SANITIZATION.md
 │   ├── guides/                   # USER_GUIDE.md, TROUBLESHOOTING.md, ELECTRON_GUIDE.md, I18N.md
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **348 AI providers** with automatic format translation
+- **346 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -351,7 +351,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 ### MCP Server (109 Tools)
 
-110 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
+109 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
 diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool**, **notion**,
 **obsidian**, **localCorpus**, **gamification**, and **plugin** modules. Full per-tool inventory:
 `docs/frameworks/MCP-SERVER.md`.
@@ -479,10 +479,10 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **348-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **346-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
-- **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
+- **MCP server expanded to 109 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
 - **Cloud Agents** (Codex Cloud, Devin, Jules), **Guardrails**, **Evals**, **Webhooks**, **Compliance** frameworks
 - **Embedded services** manager (install/start/stop bundled services from the dashboard)
 - **Prompt compression** (RTK + Caveman codecs) saving up to ~95% tokens on eligible traffic

docs/i18n/ur/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 348 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 346 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (109 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -169,7 +169,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   └── manager.ts            # MITM proxy manager
 │   ├── shared/                   # Shared utilities, components, and constants
 │   │   ├── components/           # Reusable UI components (Card, Badge, Button, Modal, Sidebar, ProviderIcon, etc.)
-│   │   ├── constants/            # Provider definitions (348), model lists, pricing, routing strategies, MCP scopes
+│   │   ├── constants/            # Provider definitions (346), model lists, pricing, routing strategies, MCP scopes
 │   │   ├── contracts/            # Shared API contracts
 │   │   ├── hooks/                # React hooks
 │   │   ├── middleware/           # Shared middleware utilities
@@ -211,7 +211,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── moderations.ts        # Content moderation
 │   │   ├── rerank.ts             # Reranking API
 │   │   └── search.ts             # Web search API
-│   ├── mcp-server/               # Built-in MCP server (110 tools, 3 transports: stdio/SSE/streamable-HTTP)
+│   ├── mcp-server/               # Built-in MCP server (109 tools, 3 transports: stdio/SSE/streamable-HTTP)
 │   │   ├── server.ts             # MCP server core (tool registration, scope enforcement)
 │   │   ├── tools/                # Tool implementations (advancedTools, memoryTools, skillTools)
 │   │   ├── schemas/              # Zod input schemas (tools, audit, a2a)
@@ -266,7 +266,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── i18n/                     # 43-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
-│   ├── frameworks/               # MCP-SERVER.md (110 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
+│   ├── frameworks/               # MCP-SERVER.md (109 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
 │   ├── routing/                  # AUTO-COMBO.md (14-factor scoring), REASONING_REPLAY.md
 │   ├── security/                 # GUARDRAILS.md, COMPLIANCE.md, STEALTH_GUIDE.md, PUBLIC_CREDS.md, ERROR_SANITIZATION.md
 │   ├── guides/                   # USER_GUIDE.md, TROUBLESHOOTING.md, ELECTRON_GUIDE.md, I18N.md
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **348 AI providers** with automatic format translation
+- **346 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -351,7 +351,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 ### MCP Server (109 Tools)
 
-110 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
+109 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
 diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool**, **notion**,
 **obsidian**, **localCorpus**, **gamification**, and **plugin** modules. Full per-tool inventory:
 `docs/frameworks/MCP-SERVER.md`.
@@ -479,10 +479,10 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **348-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **346-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
-- **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
+- **MCP server expanded to 109 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
 - **Cloud Agents** (Codex Cloud, Devin, Jules), **Guardrails**, **Evals**, **Webhooks**, **Compliance** frameworks
 - **Embedded services** manager (install/start/stop bundled services from the dashboard)
 - **Prompt compression** (RTK + Caveman codecs) saving up to ~95% tokens on eligible traffic

docs/i18n/vi/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 348 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 346 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (109 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -169,7 +169,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   └── manager.ts            # MITM proxy manager
 │   ├── shared/                   # Shared utilities, components, and constants
 │   │   ├── components/           # Reusable UI components (Card, Badge, Button, Modal, Sidebar, ProviderIcon, etc.)
-│   │   ├── constants/            # Provider definitions (348), model lists, pricing, routing strategies, MCP scopes
+│   │   ├── constants/            # Provider definitions (346), model lists, pricing, routing strategies, MCP scopes
 │   │   ├── contracts/            # Shared API contracts
 │   │   ├── hooks/                # React hooks
 │   │   ├── middleware/           # Shared middleware utilities
@@ -211,7 +211,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── moderations.ts        # Content moderation
 │   │   ├── rerank.ts             # Reranking API
 │   │   └── search.ts             # Web search API
-│   ├── mcp-server/               # Built-in MCP server (110 tools, 3 transports: stdio/SSE/streamable-HTTP)
+│   ├── mcp-server/               # Built-in MCP server (109 tools, 3 transports: stdio/SSE/streamable-HTTP)
 │   │   ├── server.ts             # MCP server core (tool registration, scope enforcement)
 │   │   ├── tools/                # Tool implementations (advancedTools, memoryTools, skillTools)
 │   │   ├── schemas/              # Zod input schemas (tools, audit, a2a)
@@ -266,7 +266,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── i18n/                     # 43-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
-│   ├── frameworks/               # MCP-SERVER.md (110 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
+│   ├── frameworks/               # MCP-SERVER.md (109 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
 │   ├── routing/                  # AUTO-COMBO.md (14-factor scoring), REASONING_REPLAY.md
 │   ├── security/                 # GUARDRAILS.md, COMPLIANCE.md, STEALTH_GUIDE.md, PUBLIC_CREDS.md, ERROR_SANITIZATION.md
 │   ├── guides/                   # USER_GUIDE.md, TROUBLESHOOTING.md, ELECTRON_GUIDE.md, I18N.md
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **348 AI providers** with automatic format translation
+- **346 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -351,7 +351,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 ### MCP Server (109 Tools)
 
-110 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
+109 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
 diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool**, **notion**,
 **obsidian**, **localCorpus**, **gamification**, and **plugin** modules. Full per-tool inventory:
 `docs/frameworks/MCP-SERVER.md`.
@@ -479,10 +479,10 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **348-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **346-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
-- **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
+- **MCP server expanded to 109 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
 - **Cloud Agents** (Codex Cloud, Devin, Jules), **Guardrails**, **Evals**, **Webhooks**, **Compliance** frameworks
 - **Embedded services** manager (install/start/stop bundled services from the dashboard)
 - **Prompt compression** (RTK + Caveman codecs) saving up to ~95% tokens on eligible traffic

docs/i18n/zh-CN/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 348 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 346 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (109 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -169,7 +169,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   └── manager.ts            # MITM proxy manager
 │   ├── shared/                   # Shared utilities, components, and constants
 │   │   ├── components/           # Reusable UI components (Card, Badge, Button, Modal, Sidebar, ProviderIcon, etc.)
-│   │   ├── constants/            # Provider definitions (348), model lists, pricing, routing strategies, MCP scopes
+│   │   ├── constants/            # Provider definitions (346), model lists, pricing, routing strategies, MCP scopes
 │   │   ├── contracts/            # Shared API contracts
 │   │   ├── hooks/                # React hooks
 │   │   ├── middleware/           # Shared middleware utilities
@@ -211,7 +211,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── moderations.ts        # Content moderation
 │   │   ├── rerank.ts             # Reranking API
 │   │   └── search.ts             # Web search API
-│   ├── mcp-server/               # Built-in MCP server (110 tools, 3 transports: stdio/SSE/streamable-HTTP)
+│   ├── mcp-server/               # Built-in MCP server (109 tools, 3 transports: stdio/SSE/streamable-HTTP)
 │   │   ├── server.ts             # MCP server core (tool registration, scope enforcement)
 │   │   ├── tools/                # Tool implementations (advancedTools, memoryTools, skillTools)
 │   │   ├── schemas/              # Zod input schemas (tools, audit, a2a)
@@ -266,7 +266,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── i18n/                     # 43-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
-│   ├── frameworks/               # MCP-SERVER.md (110 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
+│   ├── frameworks/               # MCP-SERVER.md (109 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
 │   ├── routing/                  # AUTO-COMBO.md (14-factor scoring), REASONING_REPLAY.md
 │   ├── security/                 # GUARDRAILS.md, COMPLIANCE.md, STEALTH_GUIDE.md, PUBLIC_CREDS.md, ERROR_SANITIZATION.md
 │   ├── guides/                   # USER_GUIDE.md, TROUBLESHOOTING.md, ELECTRON_GUIDE.md, I18N.md
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **348 AI providers** with automatic format translation
+- **346 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -351,7 +351,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 ### MCP Server (109 Tools)
 
-110 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
+109 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
 diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool**, **notion**,
 **obsidian**, **localCorpus**, **gamification**, and **plugin** modules. Full per-tool inventory:
 `docs/frameworks/MCP-SERVER.md`.
@@ -479,10 +479,10 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **348-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **346-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
-- **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
+- **MCP server expanded to 109 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
 - **Cloud Agents** (Codex Cloud, Devin, Jules), **Guardrails**, **Evals**, **Webhooks**, **Compliance** frameworks
 - **Embedded services** manager (install/start/stop bundled services from the dashboard)
 - **Prompt compression** (RTK + Caveman codecs) saving up to ~95% tokens on eligible traffic

docs/i18n/zh-TW/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 348 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 346 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (109 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -169,7 +169,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   └── manager.ts            # MITM proxy manager
 │   ├── shared/                   # Shared utilities, components, and constants
 │   │   ├── components/           # Reusable UI components (Card, Badge, Button, Modal, Sidebar, ProviderIcon, etc.)
-│   │   ├── constants/            # Provider definitions (348), model lists, pricing, routing strategies, MCP scopes
+│   │   ├── constants/            # Provider definitions (346), model lists, pricing, routing strategies, MCP scopes
 │   │   ├── contracts/            # Shared API contracts
 │   │   ├── hooks/                # React hooks
 │   │   ├── middleware/           # Shared middleware utilities
@@ -211,7 +211,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── moderations.ts        # Content moderation
 │   │   ├── rerank.ts             # Reranking API
 │   │   └── search.ts             # Web search API
-│   ├── mcp-server/               # Built-in MCP server (110 tools, 3 transports: stdio/SSE/streamable-HTTP)
+│   ├── mcp-server/               # Built-in MCP server (109 tools, 3 transports: stdio/SSE/streamable-HTTP)
 │   │   ├── server.ts             # MCP server core (tool registration, scope enforcement)
 │   │   ├── tools/                # Tool implementations (advancedTools, memoryTools, skillTools)
 │   │   ├── schemas/              # Zod input schemas (tools, audit, a2a)
@@ -266,7 +266,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── i18n/                     # 43-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
-│   ├── frameworks/               # MCP-SERVER.md (110 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
+│   ├── frameworks/               # MCP-SERVER.md (109 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
 │   ├── routing/                  # AUTO-COMBO.md (14-factor scoring), REASONING_REPLAY.md
 │   ├── security/                 # GUARDRAILS.md, COMPLIANCE.md, STEALTH_GUIDE.md, PUBLIC_CREDS.md, ERROR_SANITIZATION.md
 │   ├── guides/                   # USER_GUIDE.md, TROUBLESHOOTING.md, ELECTRON_GUIDE.md, I18N.md
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **348 AI providers** with automatic format translation
+- **346 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -351,7 +351,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 ### MCP Server (109 Tools)
 
-110 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
+109 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
 diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool**, **notion**,
 **obsidian**, **localCorpus**, **gamification**, and **plugin** modules. Full per-tool inventory:
 `docs/frameworks/MCP-SERVER.md`.
@@ -479,10 +479,10 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **348-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **346-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
-- **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
+- **MCP server expanded to 109 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
 - **Cloud Agents** (Codex Cloud, Devin, Jules), **Guardrails**, **Evals**, **Webhooks**, **Compliance** frameworks
 - **Embedded services** manager (install/start/stop bundled services from the dashboard)
 - **Prompt compression** (RTK + Caveman codecs) saving up to ~95% tokens on eligible traffic

docs/openapi.yaml

@@ -2105,26 +2105,11 @@ paths:
     patch:
       tags: [Combos]
       summary: Update combo
-      description: >-
-        Partial update: the body is merged onto the stored combo, so a field left out keeps
-        its current value. An array that IS sent replaces the stored one outright.
       parameters:
         - $ref: "#/components/parameters/ResourceId"
-      requestBody:
-        required: true
-        content:
-          application/json:
-            schema:
-              type: object
       responses:
         "200":
           description: Updated combo
-        "400":
-          description: Invalid body, or the resulting combo fails validation
-        "404":
-          description: Combo not found
-        "409":
-          description: Name already taken, or the combo is quota-share managed
     delete:
       tags: [Combos]
       summary: Delete combo

docs/providers/CURSOR-DOCKER.md

@@ -1,58 +1,15 @@
 ---
-title: "Cursor Provider in Docker Environments"
+title: "Cursor model listing"
 version: 3.8.50
-lastUpdated: 2026-08-17
+lastUpdated: 2026-08-09
 ---
 
-# Cursor Provider in Docker Environments
+# Cursor model listing
 
-When OmniRoute runs inside Docker, the legacy **Import from Cursor IDE** /
-`cursor-agent` flows fail because the container cannot see the host Cursor
-install. Use **Login with Cursor** (deep-control PKCE) instead.
-
-## Why IDE / CLI Import Fails in Docker
-
-1. **Filesystem isolation** — Auto-import looks for Linux paths such as
-   `~/.config/Cursor/User/globalStorage/state.vscdb` _inside_ the container.
-   On Docker Desktop for macOS the host IDE DB is not mounted by default, and
-   the container OS is Linux even when the host is Darwin.
-2. **No `cursor-agent` binary** — Official OmniRoute images do not ship
-   `cursor-agent`. Available Models previously shelled out to
-   `cursor-agent --list-models` and fell back to a static catalog.
-3. **Wrong binary** — Do **not** bind-mount a macOS `cursor-agent` into a Linux
-   container. It will not execute.
-
-## Recommended: Login with Cursor
-
-1. Open **Dashboard → Providers → Cursor**.
-2. Choose the **Login with Cursor** tab.
-3. Click **Login with Cursor** — OmniRoute opens
-   `https://cursor.com/loginDeepControl?…` in your **host** browser.
-4. Approve the login in the browser, then return to the dashboard. OmniRoute
-   polls `api2.cursor.sh/auth/poll` until tokens arrive.
-5. OmniRoute stores **access + refresh** tokens and refreshes them via
-   `https://api2.cursor.sh/auth/exchange_user_api_key`.
-
-This path does not require Cursor IDE or `cursor-agent` inside the container.
-
-## Model discovery
-
-With a logged-in connection, **Available Models / Auto-Sync** prefers Cursor’s
-HTTP `AiService/AvailableModels` catalog using the connection bearer token.
-If that fails, OmniRoute still tries host `cursor-agent` (when present), then
-the static registry seed.
-
-OmniRoute always exposes **`auto`** in the catalog (display “Auto”), plus
-OpenCodex-style router modes **`auto-cost`**, **`auto-balance`**, and
-**`auto-intelligence`**. On the wire these map to Cursor’s `default` model
-(with an `optimization` ModelParameter for the three variants). Prefer
-`cu/auto` when premium models are out of usage — Auto often still has budget.
-
-### Live catalog is exclusive when synced
+## Live catalog is exclusive when synced
 
 After a successful Cursor model sync (`cursor-agent --list-models` → persisted
-synced catalog, or the bearer-authenticated `AvailableModels` fetch above), the
-**dashboard**, **`/v1/models`**, and **Test All** list:
+synced catalog), the **dashboard**, **`/v1/models`**, and **Test All** list:
 
 1. Models returned by the live sync
 2. Injected auto-router ids: `auto`, `auto-cost`, `auto-balance`, `auto-intelligence`
@@ -67,63 +24,10 @@ Effort-suffixed ids (for example `claude-4.6-sonnet-high`) may still be
 `ModelParameter`. Exclusive listing intentionally hides those static variants
 from Test All so probes match what Cursor actually returns as available.
 
-### Helpers
+## Helpers
 
 - `providerUsesExclusiveSyncedListing("cursor"|"cu")` —
   `src/lib/providers/modelListingCapability.ts`
 - `mergeProviderModelListing` — dashboard merge
 - `ensureCursorAutoCatalogEntry` — auto* inject on discovery + listing
 - `shouldSuppressStaticModelForExclusiveListing` — `/v1/models` static loop
-
-## Provider Limits (quota)
-
-**Usage → Provider Limits** for Cursor uses Bearer APIs on `api2.cursor.sh`
-(`GetCurrentPeriodUsage` → usage summary → auth/usage) after PKCE or token
-import. The legacy cookie/`cursor.com` dashboard path remains a last fallback
-for older IDE-imported sessions.
-
-Windows typically include **Total**, **Auto + Composer**, and **API**. If
-limits look empty, re-run **Login with Cursor** or re-import tokens (IDE import
-alone is no longer required).
-
-## Empty turns / out of usage
-
-When Cursor accepts a Run but returns no assistant text (common when premium
-usage is exhausted), OmniRoute surfaces an actionable **429** (quota cues) or
-**502** with guidance — not a bare “Provider returned empty content”. Streaming
-failures such as `not_found: AI Model Not Found` (usage window exhausted) are
-classified as **Cursor rate limit / usage exceeded** and keep that message
-through the SSE pipeline (the shared empty-stream guard does not overwrite an
-already-emitted error). Check Provider Limits, try model **`auto`**, or raise
-Cursor plan limits.
-
-## Client version (headless)
-
-Without a local `cursor-agent` install, OmniRoute resolves
-`x-cursor-client-version` via env `CURSOR_AGENT_CLI_VERSION`, then a disk-cached
-scrape of the Cursor installer script, then a pinned build id. Override with
-`CURSOR_AGENT_CLI_VERSION` when needed.
-
-## Fallback: Manual Token Import
-
-If you cannot complete browser login:
-
-1. On the host, extract tokens from Cursor’s `state.vscdb`:
-
-   ```bash
-   sqlite3 "$HOME/Library/Application Support/Cursor/User/globalStorage/state.vscdb" \
-     "SELECT key, value FROM ItemTable WHERE key IN ('cursorAuth/accessToken','cursorAuth/refreshToken','storage.serviceMachineId');"
-   ```
-
-2. Open **Import token** in the Cursor auth modal.
-3. Paste **Access Token** and, when available, **Refresh Token** (required for
-   automatic refresh). Machine ID is optional.
-
-Access-token-only imports still work but will expire without a refresh token —
-re-import when chat returns authentication errors.
-
-## Related
-
-- Zed Docker guidance: [`docs/providers/ZED-DOCKER.md`](./ZED-DOCKER.md)
-- OpenCodex Cursor login reference (external):
-  https://github.com/lidge-jun/opencodex/blob/main/src/oauth/cursor.ts

docs/reference/ENVIRONMENT.md

@@ -198,11 +198,11 @@ OmniRoute uses **SQLite** (via `better-sqlite3`) for all persistence. These vari
 | `REQUIRE_API_KEY`                       | `false`                 | API middleware                                   | When `true`, all `/v1/*` proxy requests must include a valid API key.                                                                                                                                                                                                                                                                                              |
 | `ALLOW_API_KEY_REVEAL`                  | `false`                 | `src/shared/constants/featureFlagDefinitions.ts` | Allows revealing full API key values in the Dashboard UI. Configurable from Dashboard Feature Flags; security risk on shared instances.                                                                                                                                                                                                                            |
 | `NO_LOG_API_KEY_IDS`                    | _(empty)_               | `src/lib/compliance/index.ts`                    | Comma-separated API key IDs that bypass request logging (GDPR compliance).                                                                                                                                                                                                                                                                                         |
-| `DEFAULT_RATE_LIMIT_PER_DAY`            | _(unset = unlimited)_   | `src/shared/utils/apiKeyPolicy.ts`               | Fallback per-day request budget applied to API keys whose `rate_limits` column is null. Unset or empty: no implicit cap (#2289, #11017). `0` is the same (unlimited). Positive integer N enables N/day, 5N/week, 20N/month. Malformed non-empty values fall back to the legacy 1000/day, 5000/week, 20000/month windows. |
+| `DEFAULT_RATE_LIMIT_PER_DAY`            | `1000`                  | `src/shared/utils/apiKeyPolicy.ts`               | Fallback per-day request budget applied to API keys whose `rate_limits` column is null. Default (unset/empty/malformed) keeps the legacy 1000/day, 5000/week, 20000/month windows. Set explicitly to `0` to opt out (unlimited). Any positive integer N enables N/day, 5N/week, 20N/month. Zod-validated; invalid values log a warning and use the legacy default. |
 | `MAX_BODY_SIZE_BYTES`                   | `10485760` (10 MB)      | `src/shared/middleware/bodySizeGuard.ts`         | Maximum allowed request body size. Rejects payloads exceeding this limit.                                                                                                                                                                                                                                                                                          |
 | `OMNIROUTE_CHAT_LARGE_BODY_BYTES`       | `262144` (256 KB)       | `src/shared/middleware/chatBodyAdmission.ts`     | Actual request bodies at or above this threshold require an atomic process-local heavyweight admission lease before JSON parsing.                                                                                                                                                                                                                                  |
 | `OMNIROUTE_CHAT_HARD_MAX_BODY_BYTES`    | `52428800` (50 MB)      | `src/shared/middleware/chatBodyAdmission.ts`     | Chat-route hard cap enforced against bytes read during bounded ingestion, including requests with missing, invalid, or dishonest `Content-Length`; excess receives `413`.                                                                                                                                                                                          |
-| `OMNIROUTE_CHAT_MAX_HEAVY_IN_FLIGHT`    | `1`                     | `src/shared/middleware/chatBodyAdmission.ts`     | Maximum heavyweight chat requests admitted concurrently in **one process** (one V8 heap). Overload is retryable `503` with `Retry-After`. Two overlapping ~750k-token `/v1/responses` already abort ~12 Gi heaps (#7849); do not raise this to “use the host.” Multiply capacity with **N independent `DATA_DIR`s** (#11024), not `replicas>1` on one SQLite file. |
+| `OMNIROUTE_CHAT_MAX_HEAVY_IN_FLIGHT`    | `1`                     | `src/shared/middleware/chatBodyAdmission.ts`     | Maximum heavyweight chat requests admitted concurrently in one process. When capacity is unavailable, OmniRoute returns retryable `503` with `Retry-After`.                                                                                                                                                                                                        |
 | `OMNIROUTE_CHAT_ADMISSION_HEAP_SHED_RATIO` | `0.75`              | `src/shared/middleware/chatBodyAdmission.ts`     | Heap-pressure shed ratio (`heapUsed / heap_size_limit`) for the structural admission gate (#10183, #10268). A second concurrent heavyweight request past `OMNIROUTE_CHAT_MAX_HEAVY_IN_FLIGHT` is only shed with the retryable `503` when the heap is ALSO at or above this ratio; on a healthy heap it is admitted instead.                                       |
 | `OMNIROUTE_CHAT_ADMISSION_HEALTHY_HEADROOM` | `OMNIROUTE_CHAT_MAX_HEAVY_IN_FLIGHT` (default `1`) | `src/shared/middleware/chatBodyAdmission.ts` | Bounded extra capacity for the healthy-heap fast path above (#10437). Without this bound, every busy-but-healthy-heap request bypassed admission with no ceiling at all — a slow leak or a burst that never quite trips the heap-shed ratio could still pile up unlimited concurrent heavyweight work. Once this many concurrent leases are active through the healthy-heap path, further busy requests fall through to the SAME bounded-wait/shed path used under real heap pressure. `0` disables the bypass entirely. |
 | `OMNIROUTE_CHAT_HEAVY_MESSAGE_COUNT`    | `200`                   | `src/shared/middleware/chatBodyAdmission.ts`     | Message count that classifies a chat request as heavyweight even when its body is below the byte threshold.                                                                                                                                                                                                                                                        |
@@ -218,8 +218,6 @@ OmniRoute uses **SQLite** (via `better-sqlite3`) for all persistence. These vari
 | `OMNIROUTE_ALLOW_PRIVATE_PROVIDER_URLS` | `false`                 | `src/shared/network/outboundUrlGuard.ts`         | Allow provider URLs pointing to private/local networks (localhost, 192.168.x.x, 10.x.x.x, etc.). **REQUIRED for self-hosted providers** (LM Studio, Ollama, vLLM, Llamafile, Triton, SearXNG). When `false`, the dashboard rejects validation of local URLs.                                                                                                       |
 | `OMNIROUTE_ALLOW_LOCAL_PROVIDER_URLS`   | `true`                  | `src/shared/network/outboundUrlGuard.ts`         | Allow adding/validating providers on local/private addresses (127.0.0.1, localhost, LAN, private ranges) — scoped to the provider validation path. **Default `true`** (local-first); set `false` to enforce strict public-only blocking. Cloud-metadata endpoints (169.254.169.254, metadata.google.internal) stay blocked regardless. (#5066)                     |
 | `AUDIO_REMOTE_PROVIDER_NODES`           | `false`                 | `src/app/api/v1/_shared/audioProviderNodes.ts`   | Let the `/v1/audio/*` routes (transcriptions, speech, translations) use an OpenAI-compatible provider node hosted outside localhost. Off by default — routing audio to a remote host changes egress identity and must be an explicit operator decision. Loopback/private nodes (localhost, 127.0.0.1, 172.16-31.x) are always allowed and unaffected. (#3963)      |
-| `OMNIROUTE_OIDC_DISABLE_PASSWORD_LOGIN` | `false`                 | `src/app/api/auth/login/route.ts`                | When OIDC is enabled, disable password login so users can only authenticate via OIDC Single Sign-On. The bare alias `OIDC_DISABLE_PASSWORD_LOGIN` is also accepted; the Dashboard Feature Flag of the same key takes precedence. (#10889)                                                            |
-| `OIDC_DISABLE_PASSWORD_LOGIN`           | `false`                 | `src/app/api/auth/login/route.ts`                | Bare alias of `OMNIROUTE_OIDC_DISABLE_PASSWORD_LOGIN` (#10889).                                                                                                                                                                                                                                     |
 
 ### Hardening Checklist
 
@@ -296,7 +294,6 @@ OmniRoute provides a two-layer defense: request-side injection scanning and resp
 | `CLOUD_URL`                             | _(empty)_                                                       | `src/lib/cloudSync.ts`                      | Cloud relay endpoint URL (premium feature).                                                                                                                                                                                                                                                       |
 | `CLOUD_SYNC_TIMEOUT_MS`                 | `12000`                                                         | `src/lib/cloudSync.ts`                      | HTTP timeout for cloud sync requests.                                                                                                                                                                                                                                                             |
 | `OMNIROUTE_BUILD_PROFILE`               | `full`                                                          | Webpack build config                        | Build-time profile (set to `minimal` to physically exclude privileged modules from bundle).                                                                                                                                                                                                       |
-| `OMNIROUTE_STANDALONE_DIR`              | _.build/ standalone output_                                     | `scripts/build/colocate-standalone.mjs`     | Build-time override for the standalone output directory consumed by the post-build colocation step. Not a runtime setting.                                                                                                                                                                        |
 | `OMNIROUTE_CLOUD_SYNC_SECRET`           | _(empty)_                                                       | `src/lib/cloudSync.ts`                      | Shared secret used to verify the HMAC-SHA256 signature of Cloud Sync responses.                                                                                                                                                                                                                   |
 | `OMNIROUTE_CLOUD_SYNC_SECRETS`          | `false`                                                         | `src/lib/cloudSync.ts`                      | Set to `true` to allow the Cloud Sync endpoint to overwrite local credentials. Default is `false`.                                                                                                                                                                                                |
 | `OMNIROUTE_ZED_IMPORT_LEGACY_ONE_STEP`  | `false`                                                         | `src/app/api/providers/zed/import/route.ts` | Set to `true` to fall back to the v3.8.5 one-step "import everything" behavior without user confirmation.                                                                                                                                                                                         |
@@ -736,7 +733,7 @@ REQUEST_TIMEOUT_MS (global override)
 | `OMNIROUTE_AGENT_GOAL_POLICY_ENABLED`     | `true`               | Kill-switch for the `/goal` heuristic. Set `false`/`0`/`off` to fully disable detection — readiness timeouts and stream recovery are never elevated by request body/headers, mitigating client-controlled timeout amplification. |
 | `OMNIROUTE_AGENT_GOAL_READINESS_MAX_TIMEOUT_MS` | `600000`      | Maximum first-event readiness window for detected `/goal` agent runs or requests forced with `x-omniroute-agent-goal`.                                          |
 | `OMNIROUTE_AGENT_GOAL_STREAM_RECOVERY`    | `true`               | Enable early stream recovery automatically for detected `/goal` agent runs. Set `false`/`0`/`off` to disable the goal-specific opt-in. This can only ADD recovery on top of the operator default — it never overrides an explicit `STREAM_RECOVERY_ENABLED`/DB settings opt-out. |
-| `OMNIROUTE_CODEX_DROP_NONSTANDARD_EVENTS` | `true`               | Strip non-standard `codex.*` SSE events (e.g. `codex.rate_limits`) that break the OpenAI SDK's `responses.stream()` with a 502. Default ON (#11014). Set `0`/`false`/`no`/`off` to forward them. |
+| `OMNIROUTE_CODEX_DROP_NONSTANDARD_EVENTS` | _(off)_              | Strip non-standard `codex.*` SSE events (e.g. `codex.rate_limits`) that break the OpenAI SDK's `responses.stream()` with a 502. Set `true`/`1`/`yes` to enable. |
 | `FETCH_HEADERS_TIMEOUT_MS`                | = `FETCH_TIMEOUT_MS` | Time to receive response headers.                                                                                                                               |
 | `OMNIROUTE_DIRECT_HEADERS_TIMEOUT_MS`    | `30000` (30s)         | Maximum response-start wait (ms) for each direct no-proxy attempt. A timeout retries once on a fresh socket; set `0` to disable the bound and retain the previous behavior. |
 | `FETCH_BODY_TIMEOUT_MS`                   | = `FETCH_TIMEOUT_MS` | Time to receive the full response body.                                                                                                                         |
@@ -769,8 +766,6 @@ REQUEST_TIMEOUT_MS (global override)
 | `OMNIROUTE_NOTION_TLS_GRACE_MS`           | `10000`              | JS-side grace added on top of the wire timeout when the native binding is wedged.                                                                               |
 | `OMNIROUTE_BROWSER_POOL`                  | `on`                 | Shared Playwright browser pool for browser-backed web-cookie chat (`browserPool.ts`); set `off` to disable.                                                     |
 | `WEB_COOKIE_USE_BROWSER`                  | `0`                  | Opt a web-cookie chat request into the browser-backed path (`browserBackedChat.ts`); `1` to enable.                                                             |
-| `KIMI_WEB_BASE_URL`                       | `https://www.kimi.ai` | Base URL for the Kimi Web (international kimi.ai Connect-RPC) executor (`kimi-web.ts`); override only for mirror/proxy endpoints.                               |
-| `KIMI_WEB_CHAT_URL`                       | `<KIMI_WEB_BASE_URL>/apiv2/kimi.gateway.chat.v1.ChatService/Chat` | Full chat endpoint for the Kimi Web executor (`kimi-web.ts`).                                                                       |
 | `OMNIROUTE_LOGIN_BROWSER_PATH`            | _(auto-detected)_    | Path to a system Chrome/Edge executable for the Adobe Firefly interactive browser sign-in (`adobeFireflyBrowserLogin.ts`); overrides per-OS auto-detection.     |
 
 Combo target attempts inherit the resolved upstream request timeout (`FETCH_TIMEOUT_MS`, or
@@ -854,7 +849,7 @@ The logging system writes to both stdout and rotated log files. All configuratio
 
 | Variable                   | Default            | Description                                                                                                                                                                                                                                                                       |
 | -------------------------- | ------------------ | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| `OMNIROUTE_MEMORY_MB`      | _auto_ (bare metal); **`1024` in the Docker image** | **Recommended** Docker/standalone V8 heap limit (MB). When unset, calibrated dynamically (~35% of system RAM, clamped to `[512, 4096]`); `512` is only the floor when total memory can't be read. On `run-standalone.mjs` (Docker CMD), an **explicit** value is appended as `--max-old-space-size` and **wins** over a conflicting NODE_OPTIONS heap flag (V8 last-flag). `omniroute serve` still prefers an existing NODE_OPTIONS heap (#5238). Do not set both to different numbers — the process logs a warn naming both values and the winner. **The official Docker image always sets `1024`, so calibration never runs there.** Coding-agent `/v1/responses` needs `8192`–`12288` plus cgroup headroom — see [Docker Guide — runtime RAM](../guides/DOCKER_GUIDE.md#runtime-ram-for-coding-agents). |
+| `OMNIROUTE_MEMORY_MB`      | _auto_             | **Recommended** Docker/standalone V8 heap limit (MB). When unset, calibrated dynamically (~35% of system RAM, clamped to `[512, 4096]`); `512` is only the floor when total memory can't be read. On `run-standalone.mjs` (Docker CMD), an **explicit** value is appended as `--max-old-space-size` and **wins** over a conflicting NODE_OPTIONS heap flag (V8 last-flag). `omniroute serve` still prefers an existing NODE_OPTIONS heap (#5238). Do not set both to different numbers — the process logs a warn naming both values and the winner. |
 | `PROMPT_CACHE_MAX_SIZE`    | `50`               | Max cached system prompt entries.                                                                                                                                                                                                                                                 |
 | `PROMPT_CACHE_MAX_BYTES`   | `2097152` (2 MB)   | Max total prompt cache size.                                                                                                                                                                                                                                                      |
 | `PROMPT_CACHE_TTL_MS`      | `300000` (5 min)   | Prompt cache entry TTL.                                                                                                                                                                                                                                                           |
@@ -910,8 +905,6 @@ Embedding layer, vector store and reranking knobs for the persistent memory subs
 
 ### Low-RAM Docker Example
 
-`128` is dashboard-only. Coding agents on this heap `FATAL ERROR` during long `/v1/responses`. Do not use this example as a Claude/Codex/Grok gateway.
-
 ```bash
 OMNIROUTE_MEMORY_MB=128
 PROMPT_CACHE_MAX_SIZE=20
@@ -1025,6 +1018,7 @@ desktop install.
 | `NEXT_PUBLIC_DENO_RELAY_DEFAULT_PROJECT`       | `omniroute-deno-relay`                 | `src/app/(dashboard)/dashboard/settings/components/proxy/DenoRelayModal.tsx`       | Default Deno Deploy app name suggested in the proxy-pool "Deploy Relay" modal.                              |
 | `NEXT_PUBLIC_DENO_RELAY_ENABLED`               | `true`                                 | `src/app/(dashboard)/dashboard/settings/components/proxy/ProxyPoolTab.tsx`         | Set to `false` to hide the Deno Deploy relay option from the Proxy Pool tab.                                |
 | `SEARCH_CACHE_TTL_MS`                          | `300000` (5 min)                       | `open-sse/services/searchCache.ts`                                                 | TTL for search API (Perplexity, Brave, etc.) response caching.                                              |
+| `ALLOW_MULTI_CONNECTIONS_PER_COMPAT_NODE`      | `false`                                | `src/app/api/providers/route.ts`                                                   | Allow multiple simultaneous connections per OpenAI-compatible provider.                                     |
 | `ENABLE_CC_COMPATIBLE_PROVIDER`                | `false`                                | `src/shared/utils/featureFlags.ts`                                                 | Reveal the experimental CC-compatible provider UI for Claude Code-only relays.                              |
 | `NINEROUTER_HOST`                              | `127.0.0.1`                            | `open-sse/executors/ninerouter.ts`                                                 | Override the host where the embedded 9router instance listens.                                              |
 | `NINEROUTER_PORT`                              | `20130`                                | `open-sse/executors/ninerouter.ts`                                                 | Override the port where the embedded 9router instance listens.                                              |
@@ -1179,7 +1173,7 @@ AUTH_COOKIE_SECURE=true
 REQUIRE_API_KEY=true
 NEXT_PUBLIC_BASE_URL=https://omniroute.example.com
 BASE_URL=http://localhost:20128
-OMNIROUTE_MEMORY_MB=8192
+OMNIROUTE_MEMORY_MB=512
 CORS_ORIGIN=https://your-frontend.example.com
 ```
 
@@ -1429,7 +1423,6 @@ value below unset in production deployments.
 | `ELECTRON_SMOKE_DATA_DIR`              | _(tmpdir)_                       | `scripts/dev/smoke-electron-packaged.mjs` | Data directory for the Electron smoke run.                                                                                                                                                                                                 |
 | `ELECTRON_SMOKE_KEEP_DATA`             | `0`                              | `scripts/dev/smoke-electron-packaged.mjs` | Set `1` to preserve the smoke data directory after the run.                                                                                                                                                                                |
 | `ELECTRON_SMOKE_STREAM_LOGS`           | `0`                              | `scripts/dev/smoke-electron-packaged.mjs` | Set `1` to stream Electron logs to stdout during the run.                                                                                                                                                                                  |
-| `ELECTRON_SMOKE_COLD_RESTART`          | `0`                              | `scripts/dev/smoke-electron-packaged.mjs` | #7592: relaunch against the same data dir and assert the second launch selects the native SQLite driver.                                                                                                                                   |
 | `CLI_DEVIN_BIN`                        | _(PATH lookup)_                  | `open-sse/executors/devin-cli.ts`         | Override the Devin CLI binary path.                                                                                                                                                                                                        |
 
 ### Docs translation pipeline

docs/reference/FEATURE_FLAGS.md

@@ -46,7 +46,7 @@ A boolean flag is considered **enabled** when its effective value is `"true"`,
 
 ## Flag Catalog
 
-37 flags across 6 categories. **Default** is the definition default — the value
+38 flags across 6 categories. **Default** is the definition default — the value
 used when neither a DB override nor an environment variable is present.
 
 ### Security (7)
@@ -76,12 +76,13 @@ used when neither a DB override nor an environment variable is present.
 | `OMNIROUTE_ALLOW_LOCAL_PROVIDER_URLS`           | boolean | `true`  |         | Allow adding/validating providers on local/private addresses (127.0.0.1, localhost, LAN). On by default (local-first); disable for strict public-only blocking. Cloud-metadata stays blocked. |
 | `ENABLE_CC_COMPATIBLE_PROVIDER`                 | boolean | `false` | ✓       | Enable Claude Code compatible provider mode.                                                                                                                                                  |
 
-### Policies (3)
+### Policies (4)
 
 | Key                                       | Type    | Default    | Restart | Description                                                            |
 | ----------------------------------------- | ------- | ---------- | ------- | ---------------------------------------------------------------------- |
 | `TOOL_POLICY_MODE`                        | enum    | `disabled` |         | Tool-use policy enforcement mode. Values: `disabled`, `warn`, `block`. |
 | `RATE_LIMIT_AUTO_ENABLE`                  | boolean | `false`    |         | Automatically enable rate limiting based on usage patterns.            |
+| `ALLOW_MULTI_CONNECTIONS_PER_COMPAT_NODE` | boolean | `false`    | ✓       | Allow multiple connections per compatibility node.                     |
 | `DISABLE_CONTEXT_WINDOW_CHECKS`           | boolean | `false`    |         | Skip OmniRoute's local context-window / max-input-token check for direct single-model requests. Upstream limits still apply. |
 
 ### Runtime (11)

docs/reference/PROVIDER_REFERENCE.md

@@ -1,16 +1,16 @@
 ---
 title: "Provider Reference"
 version: 3.8.50
-lastUpdated: 2026-08-21
+lastUpdated: 2026-08-20
 ---
 
 # 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:** 2026-08-20
 
-Total providers: **348**. See category breakdown below.
+Total providers: **346**. See category breakdown below.
 
 ## Categories
 
@@ -62,8 +62,8 @@ Use the dashboard at `/dashboard/providers` to enable, configure, and test each
 | `clinepass` | `cp` | ClinePass | OAuth | [link](https://cline.bot/cline-pass) | ClinePass is Cline's $9.99/mo subscription bundling 10 open coding models. Sign in with your Cline account (same login as the Cline CLI/IDE), or paste a direct ClinePass API key (app.cline.bot → Settings → API Keys). A ClinePass subscription unlocks the cline-pass/* models. Reuses the Cline WorkOS OAuth flow. |
 | `codebuddy-cn` | `cbcn` | CodeBuddy CN | OAuth | [link](https://copilot.tencent.com) | Tencent CodeBuddy CN (copilot.tencent.com). Sign in via the official CLI device-code flow, or paste a direct API key (sent as Authorization: Bearer). Catalog: GLM / Kimi / MiniMax / DeepSeek / Hunyuan. |
 | `codex` | `cx` | OpenAI Codex | OAuth | — | — |
-| `cursor` | `cu` | Cursor IDE | OAuth | — | — |
-| `devin-cli` | `dv` | Devin CLI | OAuth | [link](https://cli.devin.ai) | Requires the Devin CLI binary. Run `devin auth login` to authenticate, or provide your WINDSURF_API_KEY. Install: https://cli.devin.ai |
+| `cursor` | `cu` | Cursor IDE | OAuth, image | — | Image via Agent CLI (`CURSOR_AGENT_BIN`); same seat as chat |
+| `devin-cli` | `dv` | Devin CLI (Official) | OAuth | [link](https://cli.devin.ai) | Requires the Devin CLI binary. Run `devin auth login` to authenticate, or provide your WINDSURF_API_KEY. Install: https://cli.devin.ai |
 | `devin-desktop` | — | Devin Desktop | OAuth | [link](https://devin.ai) | Paste an existing Devin API key from an authenticated Devin session. Key export availability and steps vary by Devin version and account. |
 | `ghe-copilot` | `ghe-copilot` | GitHub Enterprise Copilot | OAuth | — | Enter your GHE instance URL (e.g., https://ghe.company.com) in provider settings, then authenticate via device flow. |
 | `github` | `gh` | GitHub Copilot | OAuth | — | — |
@@ -120,7 +120,7 @@ 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 |
 |----|-------|------|------|---------|-------|
@@ -192,9 +192,9 @@ Use the dashboard at `/dashboard/providers` to enable, configure, and test each
 | `fireworks` | `fireworks` | Fireworks AI | API key | [link](https://fireworks.ai) | $1 free starter credits on signup for API testing |
 | `free-ai` | `free-ai` | Free.ai | API key, aggregator | [link](https://free.ai) | 30,000 tokens/day cover self-hosted models after email verification. Usage beyond the pool can bill at raw cost, and premium external models are paid. |
 | `freeaiapikey` | `faik` | FreeAIAPIKey | API key | [link](https://freeaiapikey.com) | — |
-| `freebuff` | `freebuff` | Freebuff | API key | [link](https://freebuff.com) | Enter Freebuff / Codebuff Auth Token (obtained via CLI login or automated harvester). |
 | `freeinference` | `freeinference` | FreeInference | API key, aggregator | [link](https://freeinference.org) | Free research access without a card; non-Harvard applicants require manual approval and no numeric quota is publicly guaranteed. |
 | `freemodel-dev` | `fmd` | FreeModel.dev | API key | [link](https://freemodel.dev) | $300 free credits on signup — no credit card required. Access GPT-5.4 and GPT-5.5 (OpenAI's latest flagship models) through an OpenAI-compatible API. |
+| `freepik` | `fpk` | Freepik (Mystic) | API key, image | [link](https://freepik.com) | Get API key at freepik.com/developers (Mystic image endpoint) |
 | `freetheai` | `fta` | FreeTheAi | API key, aggregator | [link](https://freetheai.xyz) | Join the FreeTheAi Discord to get your free API key. |
 | `friendliai` | `friendli` | FriendliAI | API key | [link](https://friendli.ai) | Free tier for serverless inference — no credit card required |
 | `g4f-gemini` | `g4fgem` | g4f.space — Gemini | API key, aggregator | [link](https://g4f.space) | No auth required. Free tier is limited to 5 requests/minute — sign up at g4f.dev/members.html for higher limits. |
@@ -243,7 +243,6 @@ Use the dashboard at `/dashboard/providers` to enable, configure, and test each
 | `llm7` | `llm7` | LLM7.io | API key | [link](https://llm7.io) | Use any non-empty key (for example 'unused'). If older built-in models return model_unavailable, use Available Models → Import from /models or Auto-Sync; verified live model: gemini-3.1-flash-lite. |
 | `llmgateway` | `llmgateway` | LLM Gateway | API key, aggregator | [link](https://llmgateway.io) | Hosted Free plan: free-priced models are limited to 5 requests per 10 minutes when the account has no credits. |
 | `longcat` | `lc` | LongCat AI | API key | [link](https://longcat.chat/platform/docs) | Free: one-time 10M-token grant after account signup + KYC verification (LongCat-2.0). One-time only — not a recurring daily/monthly allowance. |
-| `magnific` | `freepik` | Magnific | API key, image | [link](https://www.magnific.com) | Get an API key at magnific.com/user/api-keys (header x-magnific-api-key). Legacy Freepik developer keys still work. |
 | `maritalk` | `maritalk` | Maritalk | API key | [link](https://www.maritaca.ai) | — |
 | `meganova-ai` | `meganova-ai` | MegaNova AI | API key, aggregator | [link](https://meganova.ai) | Free signup without a card. Published Tier 1 per-model quotas total 550 requests/day; they are not a shared global pool, and paid overage can apply if enabled. |
 | `meta-llama` | `meta` | Meta Llama API | API key | [link](https://llama.developer.meta.com) | — |
@@ -367,8 +366,8 @@ Use the dashboard at `/dashboard/providers` to enable, configure, and test each
 | `llama-cpp` | `llamacpp` | llama.cpp | Local, self-hosted | [link](https://github.com/ggml-org/llama.cpp) | API key optional (use any value, e.g. sk-no-key-required). Configure the llama-server OpenAI-compatible base URL (default: http://127.0.0.1:8080/v1). Note: if Llamafile is also installed, both default to port 8080 — run only one at a time or override the port. |
 | `llamafile` | `llamafile` | Llamafile | Local, self-hosted | [link](https://github.com/Mozilla-Ocho/llamafile) | API key optional. Configure the local Llamafile OpenAI-compatible base URL (default: http://127.0.0.1:8080/v1). |
 | `lm-studio` | `lmstudio` | LM Studio | Local, self-hosted | [link](https://lmstudio.ai) | API key optional. Configure the local LM Studio OpenAI-compatible base URL (default: http://localhost:1234/v1). |
-| `mlx-gemma` | `mlx-gemma` | MLX Gemma 26B | Local, self-hosted | [link](https://github.com/ml-explore/mlx) | No API key required. Runs mlx-lm server locally on port 11435. Requires uv and mlx-lm installed. Model: mlx-community/gemma-4-26B-A4B-it-qat-q4_0-mlx-aligned (~15.9GB peak memory). |
-| `mlx-qwen` | `mlx-qwen` | MLX Qwen 3.8 27B | Local, self-hosted | [link](https://github.com/ml-explore/mlx) | No API key required. Runs mlx-lm server locally on port 11436. Requires uv and mlx-lm installed. Model: maglun/Qwen3.8-27B-MLX-Mixed-3.80bpw (~13.1GB peak memory). |
+| `mlx-gemma` | `mlx-gemma` | MLX Gemma 26B | Local, self-hosted | [link](https://github.com/ml-explore/mlx) | No API key required. Runs mlx-lm server locally on port 11435. Requires `uv` and `mlx-lm` installed. Model: `mlx-community/gemma-4-26B-A4B-it-qat-q4_0-mlx-aligned` (~15.9GB peak memory). |
+| `mlx-qwen` | `mlx-qwen` | MLX Qwen 3.8 27B | Local, self-hosted | [link](https://github.com/ml-explore/mlx) | No API key required. Runs mlx-lm server locally on port 11436. Requires `uv` and `mlx-lm` installed. Model: `maglun/Qwen3.8-27B-MLX-Mixed-3.80bpw` (~13.1GB peak memory). |
 | `ollama-local` | `ollama` | Ollama | Local, self-hosted | [link](https://ollama.com) | No API key required. Ollama runs locally — configure its OpenAI-compatible base URL (default: http://localhost:11434/v1) and make sure Ollama is running before connecting. |
 | `oobabooga` | `ooba` | oobabooga | Local, self-hosted | [link](https://github.com/oobabooga/text-generation-webui) | API key optional. Configure the local oobabooga OpenAI-compatible base URL (default: http://localhost:5000/v1). |
 | `sdwebui` | `sdwebui` | SD WebUI | Local | [link](https://github.com/AUTOMATIC1111/stable-diffusion-webui) | No API key required. Configure the local WebUI base URL (default: http://localhost:7860). |
@@ -376,7 +375,7 @@ Use the dashboard at `/dashboard/providers` to enable, configure, and test each
 | `vllm` | `vllm` | vLLM | Local, self-hosted | [link](https://github.com/vllm-project/vllm) | API key optional. Configure the local vLLM OpenAI-compatible base URL (default: http://localhost:8000/v1). |
 | `xinference` | `xinference` | XInference | Local, self-hosted | [link](https://inference.readthedocs.io) | API key optional. Configure the local XInference OpenAI-compatible base URL (default: http://localhost:9997/v1). |
 
-## Search Providers (13)
+## Search Providers (12)
 
 | ID | Alias | Name | Tags | Website | Notes |
 |----|-------|------|------|---------|-------|
@@ -391,7 +390,6 @@ Use the dashboard at `/dashboard/providers` to enable, configure, and test each
 | `searxng-search` | `searxng` | SearXNG Search | Search | [link](https://docs.searxng.org) | API key is optional. Set your SearXNG base URL. Some instances may require a bearer token for access. |
 | `serper-search` | `serper-search` | Serper Search | Search | [link](https://serper.dev) | API key from serper.dev dashboard |
 | `tavily-search` | `tavily-search` | Tavily Search | Search | [link](https://tavily.com) | API key from app.tavily.com (format: tvly-...) |
-| `x-search` | `x_search` | X Search (Grok) | Search | [link](https://docs.x.ai/developers/tools/x-search) | SuperGrok OAuth (xai-oauth) or xAI API key. This is Grok X Search, not the X Developer MCP. |
 | `youcom-search` | `youcom-search` | You.com Search | Search | [link](https://you.com/business/api/) | X-API-Key from the You.com platform dashboard |
 
 ## Audio-only Providers (12)
@@ -436,7 +434,7 @@ Use the dashboard at `/dashboard/providers` to enable, configure, and test each
 
 - Catalog: [`src/shared/constants/providers.ts`](../../src/shared/constants/providers.ts)
 - Registry (per-model details): [`open-sse/config/providerRegistry.ts`](../../open-sse/config/providerRegistry.ts)
-- Executors: [`open-sse/executors/`](../../open-sse/executors/) (106 implementations)
+- Executors: [`open-sse/executors/`](../../open-sse/executors/) (105 implementations)
 - Translators: [`open-sse/translator/`](../../open-sse/translator/)
 
 ## See Also

docs/routing/REASONING_REPLAY.md

@@ -26,8 +26,7 @@ But typical clients (Cursor, Cline, Roo Code, OpenAI SDK) strip `reasoning_conte
 ```
 Turn N (assistant generates):
   → response contains reasoning_content + tool_calls
-  → if requiresReasoningReplay(provider, model): cacheReasoningFromAssistantMessage()
-      writes (memory + DB), keyed by every tool_call.id
+  → cacheReasoningFromAssistantMessage() writes (memory + DB), keyed by every tool_call.id
   → forward response to client (which may or may not retain reasoning)
 
 Turn N+1 (client sends follow-up):
@@ -158,7 +157,6 @@ The cache exposes two endpoints under `src/app/api/cache/reasoning/route.ts`. Bo
 - **Cleanup:** `cleanupReasoningCache()` purges expired memory entries and runs `DELETE FROM reasoning_cache WHERE expires_at <= unixepoch('now')`. Health-check workers call this periodically.
 - **Crash recovery:** After a restart, memory is empty but the DB still holds unexpired entries. The first lookup for a given `tool_call_id` is a DB hit; subsequent lookups are memory hits.
 - **No reasoning, no cache:** `cacheReasoningFromAssistantMessage` returns `0` when the assistant message has no `reasoning_content` / `reasoning` field, so non-thinking responses cost nothing.
-- **Write is gated too:** both call sites in `chatCore.ts` (non-streaming and streaming) only call `cacheReasoningFromAssistantMessage()` when `requiresReasoningReplay(provider, model)` is `true` — the same predicate the read side checks. Installs that never touch a replay provider stop paying for the write, the index update, and the try/catch on every reasoning-bearing response.
 - **Non-strict providers:** When `requiresReasoningReplay` is `false` and the target format is OpenAI, the translator **strips** any `reasoning_content` field from outgoing messages — OpenAI Chat Completions does not accept it.
 
 ## See Also

docs/routing/STRICT_ZERO_COST.md

@@ -1,146 +0,0 @@
----
-title: "STRICT_ZERO_COST"
-version: 3.8.50
-lastUpdated: 2026-08-20
----
-
-# STRICT_ZERO_COST
-
-> Opt-in, off by default (`settings.freeAccessPolicy !== "strict"` leaves every `auto/*`
-> candidate pool byte-identical). A stricter sibling of `hidePaidModels`
-> (`open-sse/services/autoCombo/paidModelFilter.ts`, #6512) for operators who need a hard
-> guarantee against ANY incremental monetary spend, not just "documented as free".
-
-## Why this exists, and why `hidePaidModels` alone isn't enough
-
-`hidePaidModels` answers "is this model classified free in `FREE_MODEL_BUDGETS` right now?" —
-a point-in-time catalog fact, checked via `isFreeModel()`/`providerHasFreeModels()`
-(`src/shared/utils/freeModels.ts`). It says nothing about two real risks:
-
-1. A `recurring-*`/`one-time-initial` free tier's allowance can be **exhausted** — the catalog
-   still lists the model as free, but the account behind it has no headroom left.
-2. Exceeding a free tier is not always a hard stop. Some providers document explicitly that no
-   payment method can ever be attached ("no credit card required"); others don't say, and a
-   handful bill automatically past the free allowance.
-
-`hidePaidModels` cannot distinguish these — it was never meant to. STRICT_ZERO_COST adds exactly
-these two checks, evaluated per candidate, **before** category/tier ranking and **before**
-dispatch — never after a request has already gone out.
-
-## Candidate classification
-
-For every candidate in the pool (`open-sse/services/autoCombo/virtualFactory.ts::buildPreparedPool`,
-right after `filterPaidOnlyCandidates`):
-
-1. **Not in `FREE_MODEL_BUDGETS` at all** → excluded. This covers genuinely paid models and any
-   provider/model OmniRoute hasn't classified yet — new candidates start excluded, not included.
-2. **`freeType: "keyless"`** → passes immediately, **but only for a candidate that genuinely
-   arrived via the no-auth path** (`connectionId === SYNTHETIC_NOAUTH_CONNECTION_ID`,
-   `open-sse/services/autoCombo/resilienceCandidateFilter.ts`). No credential exists for that
-   candidate, so no request against it can ever be billed — no runtime check is needed or
-   possible. The same catalogued `keyless` provider/model reached through a **real** DB
-   connection (`connectionId` is an actual connection id, or the candidate carries
-   `allowedConnectionIds`) does **not** get this shortcut — `keyless` metadata describes the
-   no-auth path specifically, not the provider in general, and never authorizes a real,
-   credentialed account. Such a candidate falls through to check 3 like any other, where it is
-   excluded unless the catalog entry separately carries `hardStopGuaranteed: true` (real
-   `keyless` entries never do — the shortcut was their only path to safety).
-3. **Any other `freeType`** (`recurring-daily`, `recurring-monthly`, `recurring-credit`,
-   `recurring-uncapped`, `one-time-initial`, and any future type this module doesn't
-   special-case) → passes only if **all** of the following hold:
-   - `hardStopGuaranteed: true` is set on the catalog entry (`FreeModelBudget.hardStopGuaranteed`,
-     `open-sse/config/freeModelCatalog.ts`) — a **curated, hand-set fact** about the provider's
-     own published terms (e.g. an explicit "no credit card required" claim), never derived from
-     `freeType` or from a live API response. Unset (`undefined`) and `false` are both treated as
-     "not guaranteed".
-   - A usage adapter exists for the provider in `USAGE_FETCHER_PROVIDERS`
-     (`open-sse/services/usage.ts`) — the same registry that already backs the quota dashboard and
-     `getUsageForProvider()`. No adapter → excluded, permanently, until one is added.
-   - The live, cached `FreeAccessState` for **the specific connection actually being
-     evaluated** is `status: "SAFE"`, was checked within
-     `settings.autoRefreshProviderQuotaInterval` (default 180s — the existing setting, not a new
-     number), and reports `remainingFreeAllowance` above a small safety margin.
-4. **`freeType: "discontinued"`** → always excluded.
-
-## Connection safety (per-connection verification, never per-candidate)
-
-A candidate in the auto-combo pool is not always tied to one connection. A "logical" candidate
-(`connectionId: null`) carries an `allowedConnectionIds` allowlist — one or more actual
-provider connections/accounts any of which could serve the request — and the account actually
-used is decided later, at dispatch time, by `open-sse/services/combo/autoStrategy.ts`
-(intersecting `allowedConnectionIds` against its own connection-selection logic, ~line 315-331).
-
-STRICT_ZERO_COST verifies the free-access state of **each connection in that allowlist
-individually** (`evaluateCandidateConnections()` in `strictZeroCostFilter.ts`) and rewrites
-`allowedConnectionIds` down to exactly the subset that came back `SAFE` — never the full
-original list, and never a single arbitrarily-chosen member. Concretely:
-
-- Account A `SAFE`, account B `UNKNOWN`/exhausted/billable → only A remains selectable.
-- All accounts `UNKNOWN` → the candidate is dropped entirely (empty safe set).
-- A single-connection candidate (`connectionId` set directly, no allowlist) that fails is
-  dropped outright, never returned with an empty `allowedConnectionIds`.
-
-Because `autoStrategy.ts` already enforces `allowedConnectionIds` as a hard allowlist before
-selecting a connection to dispatch to, rewriting it to the verified-SAFE subset is sufficient to
-guarantee the connection actually used at dispatch is always one this filter itself verified —
-never a different, unverified account on the same candidate. See
-`tests/unit/autoCombo/strict-zero-cost-connection-safety.test.ts` for the regression proof
-(keyless-bypass cases A/B/C, multi-account cases 1-5).
-
-`discovered automatically`: a provider/model shipped tomorrow with the right metadata (in the
-catalog, with a usage adapter, `hardStopGuaranteed: true`) is usable the moment OmniRoute knows
-about it — no code change, no whitelist entry, nothing to edit in this module. One removed from
-the catalog disappears the same way. See
-`tests/unit/autoCombo/strict-zero-cost-autodiscovery.test.ts` for the regression proof (via
-injectable fixtures, not by mutating the real catalog).
-
-## Quota caching (`open-sse/services/autoCombo/freeAccessQuota.ts`)
-
-Reuses `getUsageForProvider()` — no second quota system. A short, in-memory,
-process-lifetime cache sits in front of it (TTL equal to the default
-`autoRefreshProviderQuotaInterval`) so a Telegram-scale request rate never triggers a live
-billing-API call per candidate per request. Reads are synchronous: a cache miss returns
-`undefined` (→ excluded, fail-closed) and kicks off a background refresh for the _next_ read —
-nothing in the candidate-pool build path ever awaits a network call.
-
-`invalidateFreeAccessState(provider, connectionId)` is called from
-`src/sse/services/auth.ts::markAccountUnavailable()` the moment a connection fails for any
-reason, so the very next pool build reads a clean cache miss instead of a stale `SAFE` entry —
-no waiting out the TTL after a 402/403/quota-exhausted response.
-
-## ToS guard (independent of economic safety)
-
-`excludeTosAvoid` (default `false`) drops any candidate whose curated `tos` verdict
-(`FreeModelBudget.tos`) is `"avoid"` — reuses the same field `hidePaidModels`'s sibling docs
-(`docs/reference/FREE_TIERS.md`) already populate. Deliberately separate from
-`freeAccessPolicy`: a candidate can be economically `SAFE` and still excluded here for
-contractual reasons, or left in when this guard is off even with `freeAccessPolicy: "strict"` on.
-
-## What passes today
-
-Run `npx tsx scripts/ad-hoc/dry-run-strict-zero-cost.ts` against a live instance's
-`GET /v1/auto-combo/{channel}/candidates` output for a real before/after — the script now reads
-each candidate's real `connectionId`, so it also proves the connection-safety fix live, not just
-in unit tests. As of 2026-08-20, only `freeType: "keyless"` candidates pass in practice (7 of 29
-live candidates on this instance: `opencode/big-pickle`, `opencode/deepseek-v4-flash-free`, and
-5 `felo-web` models — all confirmed arriving with the genuine no-auth `connectionId`, never a
-real connection) — no currently-catalogued `recurring-*` provider both has a usage adapter
-registered in `USAGE_FETCHER_PROVIDERS` **and** `hardStopGuaranteed: true` declared (e.g. `groq`
-has neither the adapter registered here nor is fetched offline in this dry run; `kiro` lacks
-`hardStopGuaranteed`). This is not a bug: it's the honest state of two independently-curated
-metadata sets that happen not to overlap yet, not a limitation of the filter itself.
-
-With `excludeTosAvoid: true` added on top of the same live pool, the count drops from 7 to 0 —
-every one of the 7 surviving candidates is curated `tos: "avoid"` today (`felo-web`, `opencode`).
-This is a real, expected trade-off of turning the ToS guard on, not a bug: the guard is
-`false` by default for exactly this reason (see "ToS guard" above).
-
-## Enabling
-
-```json
-PUT /api/settings
-{ "freeAccessPolicy": "strict", "excludeTosAvoid": false }
-```
-
-Both new settings default to their pre-feature values (`"off"` / `false`) — enabling neither
-changes any existing `auto/*` routing behavior.

llm.txt

@@ -1,6 +1,6 @@
 # OmniRoute
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 348 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 346 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (109 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -165,7 +165,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   └── manager.ts            # MITM proxy manager
 │   ├── shared/                   # Shared utilities, components, and constants
 │   │   ├── components/           # Reusable UI components (Card, Badge, Button, Modal, Sidebar, ProviderIcon, etc.)
-│   │   ├── constants/            # Provider definitions (348), model lists, pricing, routing strategies, MCP scopes
+│   │   ├── constants/            # Provider definitions (346), model lists, pricing, routing strategies, MCP scopes
 │   │   ├── contracts/            # Shared API contracts
 │   │   ├── hooks/                # React hooks
 │   │   ├── middleware/           # Shared middleware utilities
@@ -207,7 +207,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── moderations.ts        # Content moderation
 │   │   ├── rerank.ts             # Reranking API
 │   │   └── search.ts             # Web search API
-│   ├── mcp-server/               # Built-in MCP server (110 tools, 3 transports: stdio/SSE/streamable-HTTP)
+│   ├── mcp-server/               # Built-in MCP server (109 tools, 3 transports: stdio/SSE/streamable-HTTP)
 │   │   ├── server.ts             # MCP server core (tool registration, scope enforcement)
 │   │   ├── tools/                # Tool implementations (advancedTools, memoryTools, skillTools)
 │   │   ├── schemas/              # Zod input schemas (tools, audit, a2a)
@@ -262,7 +262,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   ├── i18n/                     # 43-language translated docs
 │   ├── architecture/             # ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, REPOSITORY_MAP.md, AUTHZ_GUIDE.md, RESILIENCE_GUIDE.md, QUALITY_GATES.md
 │   ├── reference/                # API_REFERENCE.md, PROVIDER_REFERENCE.md, CLI-TOOLS.md
-│   ├── frameworks/               # MCP-SERVER.md (110 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
+│   ├── frameworks/               # MCP-SERVER.md (109 tools), A2A-SERVER.md, SKILLS.md, MEMORY.md, CLOUD_AGENT.md, EVALS.md, WEBHOOKS.md
 │   ├── routing/                  # AUTO-COMBO.md (14-factor scoring), REASONING_REPLAY.md
 │   ├── security/                 # GUARDRAILS.md, COMPLIANCE.md, STEALTH_GUIDE.md, PUBLIC_CREDS.md, ERROR_SANITIZATION.md
 │   ├── guides/                   # USER_GUIDE.md, TROUBLESHOOTING.md, ELECTRON_GUIDE.md, I18N.md
@@ -277,7 +277,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **348 AI providers** with automatic format translation
+- **346 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -347,7 +347,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 ### MCP Server (109 Tools)
 
-110 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
+109 tools across modules: **44 canonical** (health, combos, quotas, routing, cost, models, cache,
 diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool**, **notion**,
 **obsidian**, **localCorpus**, **gamification**, and **plugin** modules. Full per-tool inventory:
 `docs/frameworks/MCP-SERVER.md`.
@@ -475,10 +475,10 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **348-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **346-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
-- **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
+- **MCP server expanded to 109 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)
 - **Cloud Agents** (Codex Cloud, Devin, Jules), **Guardrails**, **Evals**, **Webhooks**, **Compliance** frameworks
 - **Embedded services** manager (install/start/stop bundled services from the dashboard)
 - **Prompt compression** (RTK + Caveman codecs) saving up to ~95% tokens on eligible traffic

open-sse/config/freeModelCatalog.data.ts

@@ -108,9 +108,8 @@ export const FREE_MODEL_BUDGETS: FreeModelBudget[] = [
   { provider: "bytez", modelId: "meta-llama/Llama-3.3-70B-Instruct", displayName: "meta-llama/Llama-3.3-70B-Instruct", monthlyTokens: 0, creditTokens: 1000000, freeType: "recurring-credit", poolKey: "bytez", tos: "ambiguous" },
   { provider: "bytez", modelId: "mistralai/Mistral-7B-Instruct-v0.3", displayName: "mistralai/Mistral-7B-Instruct-v0.3", monthlyTokens: 0, creditTokens: 1000000, freeType: "recurring-credit", poolKey: "bytez", tos: "ambiguous" },
   { provider: "bytez", modelId: "Qwen/Qwen2.5-72B-Instruct", displayName: "Qwen/Qwen2.5-72B-Instruct", monthlyTokens: 0, creditTokens: 1000000, freeType: "recurring-credit", poolKey: "bytez", tos: "ambiguous" },
-  // hardStopGuaranteed: Cerebras pricing page states "Free Trial: 1M tokens/day... no credit card" (open-sse/services/../providers/apikey/inference-hosts.ts:74-84).
-  { provider: "cerebras", modelId: "zai-glm-4.7", displayName: "GLM 4.7", monthlyTokens: 30000000, creditTokens: 0, freeType: "recurring-daily", poolKey: "cerebras", tos: "caution", hardStopGuaranteed: true },
-  { provider: "cerebras", modelId: "gpt-oss-120b", displayName: "GPT OSS 120B", monthlyTokens: 30000000, creditTokens: 0, freeType: "recurring-daily", poolKey: "cerebras", tos: "caution", hardStopGuaranteed: true },
+  { provider: "cerebras", modelId: "zai-glm-4.7", displayName: "GLM 4.7", monthlyTokens: 30000000, creditTokens: 0, freeType: "recurring-daily", poolKey: "cerebras", tos: "caution" },
+  { provider: "cerebras", modelId: "gpt-oss-120b", displayName: "GPT OSS 120B", monthlyTokens: 30000000, creditTokens: 0, freeType: "recurring-daily", poolKey: "cerebras", tos: "caution" },
   // #8717: drop dead Workers AI ids (400/403/410). Keep Neurons/day budget on fp8-fast.
   { provider: "cloudflare-ai", modelId: "@cf/mistral/mistral-7b-instruct-v0.2-lora", displayName: "Mistral 7B (🆓)", monthlyTokens: 0, creditTokens: 0, freeType: "recurring-daily", poolKey: "cloudflare-ai", tos: "caution" },
   { provider: "cloudflare-ai", modelId: "@cf/qwen/qwen2.5-coder-32b-instruct", displayName: "Qwen 2.5 Coder 32B (🆓)", monthlyTokens: 0, creditTokens: 0, freeType: "recurring-daily", poolKey: "cloudflare-ai", tos: "caution" },
@@ -188,12 +187,11 @@ export const FREE_MODEL_BUDGETS: FreeModelBudget[] = [
   { provider: "glm-cn", modelId: "glm-4.5-flash", displayName: "GLM-4.5-Flash", monthlyTokens: 0, creditTokens: 0, freeType: "recurring-uncapped", poolKey: "zhipu-flash-free", tos: "ok" },
   { provider: "glm-cn", modelId: "glm-4.7-flash", displayName: "GLM-4.7-Flash", monthlyTokens: 0, creditTokens: 0, freeType: "recurring-uncapped", poolKey: "zhipu-flash-free", tos: "ok" },
   { provider: "glm-cn", modelId: "glm-signup-bonus", displayName: "Z.AI — 20M signup bonus", monthlyTokens: 0, creditTokens: 20000000, freeType: "one-time-initial", poolKey: "zhipu-signup", tos: "ok" },
-  // hardStopGuaranteed: Groq pricing page states "Free tier: 30 RPM / 14.4K RPD — no credit card" (open-sse/services/../providers/apikey/frontier-labs.ts:71-81).
-  { provider: "groq", modelId: "meta-llama/llama-4-scout-17b-16e-instruct", displayName: "Llama 4 Scout", monthlyTokens: 15000000, creditTokens: 0, freeType: "recurring-daily", poolKey: "groq", tos: "caution", hardStopGuaranteed: true },
-  { provider: "groq", modelId: "llama-3.3-70b-versatile", displayName: "Llama 3.3 70B", monthlyTokens: 15000000, creditTokens: 0, freeType: "recurring-daily", poolKey: "groq", tos: "caution", hardStopGuaranteed: true },
-  { 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: "groq", modelId: "meta-llama/llama-4-scout-17b-16e-instruct", displayName: "Llama 4 Scout", monthlyTokens: 15000000, creditTokens: 0, freeType: "recurring-daily", poolKey: "groq", tos: "caution" },
+  { provider: "groq", modelId: "llama-3.3-70b-versatile", displayName: "Llama 3.3 70B", monthlyTokens: 15000000, creditTokens: 0, freeType: "recurring-daily", poolKey: "groq", tos: "caution" },
+  { provider: "groq", modelId: "openai/gpt-oss-120b", displayName: "GPT-OSS 120B", monthlyTokens: 15000000, creditTokens: 0, freeType: "recurring-daily", poolKey: "groq", tos: "caution" },
+  { provider: "groq", modelId: "openai/gpt-oss-20b", displayName: "GPT-OSS 20B", monthlyTokens: 15000000, creditTokens: 0, freeType: "recurring-daily", poolKey: "groq", tos: "caution" },
+  { provider: "groq", modelId: "qwen/qwen3-32b", displayName: "Qwen3 32B", monthlyTokens: 15000000, creditTokens: 0, freeType: "recurring-daily", poolKey: "groq", tos: "caution" },
   { 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" },

open-sse/config/freeModelCatalog.ts

@@ -26,20 +26,6 @@ export interface FreeModelBudget {
    * reports this per model as `mayTrainOnYourPrompts` on its public catalog.
    */
   trainsOnPrompts?: boolean;
-  /**
-   * True only when the provider's own published terms document that exceeding
-   * the free allowance is a hard stop (request refused / rate-limited) and NOT
-   * automatic pay-as-you-go billing — e.g. an explicit "no credit card
-   * required" claim on the provider's pricing page. This is a curated fact
-   * about the upstream provider, not something derivable from `freeType` or
-   * from any live API response, so it must be set by hand per entry with the
-   * source of the claim in a comment. Leave unset (undefined) whenever this
-   * isn't independently documented — `undefined` and `false` are both treated
-   * as "not guaranteed" by `strictZeroCostFilter.ts`; never default to `true`
-   * to grow the catalog. See STRICT_ZERO_COST in
-   * `open-sse/services/autoCombo/strictZeroCostFilter.ts`.
-   */
-  hardStopGuaranteed?: boolean;
 }
 
 export interface FreeModelTotals {
@@ -94,7 +80,7 @@ function fmt(n: number): string {
 function dedupedSum(
   models: FreeModelBudget[],
   pick: (m: FreeModelBudget) => number,
-  include: (m: FreeModelBudget) => boolean
+  include: (m: FreeModelBudget) => boolean,
 ): number {
   const poolMax = new Map<string, number>();
   let loose = 0;
@@ -114,30 +100,30 @@ export function computeFreeModelTotals(opts: { excludeTosAvoid?: boolean } = {})
   const steadyRecurringTokens = dedupedSum(
     models,
     (m) => m.monthlyTokens,
-    (m) => RECURRING.has(m.freeType)
+    (m) => RECURRING.has(m.freeType),
   );
   const recurringCredits = dedupedSum(
     models,
     (m) => m.creditTokens,
-    (m) => m.freeType === "recurring-credit"
+    (m) => m.freeType === "recurring-credit",
   );
   const oneTimeCredits = dedupedSum(
     models,
     (m) => m.creditTokens,
-    (m) => m.freeType === "one-time-initial"
+    (m) => m.freeType === "one-time-initial",
   );
 
   const steadyWithRecurringCreditsTokens = steadyRecurringTokens + recurringCredits;
   const firstMonthRealisticTokens = steadyWithRecurringCreditsTokens + oneTimeCredits;
 
   const poolCount = new Set(
-    models.filter((m) => RECURRING.has(m.freeType) && m.poolKey).map((m) => m.poolKey)
+    models.filter((m) => RECURRING.has(m.freeType) && m.poolKey).map((m) => m.poolKey),
   ).size;
 
   // Deposit-unlock boost: sum the FREE_TIER_BOOSTS whose pool still has a live
   // recurring model in the (optionally ToS-filtered) set.
   const livePools = new Set(
-    models.filter((m) => RECURRING.has(m.freeType) && m.poolKey).map((m) => m.poolKey)
+    models.filter((m) => RECURRING.has(m.freeType) && m.poolKey).map((m) => m.poolKey),
   );
   const boostMonthlyTokens = Object.entries(FREE_TIER_BOOSTS)
     .filter(([pool]) => livePools.has(pool))

open-sse/config/providerFieldStrips.ts

@@ -56,21 +56,12 @@ export function stripGroqUnsupportedFields<T extends Record<string, unknown>>(bo
   delete next.top_logprobs;
   if (Array.isArray(next.messages)) {
     next.messages = next.messages.map((m) => {
-      if (m && typeof m === "object") {
-        const {
-          name: _name,
-          model: _model,
-          messageId: _msgId,
-          sender: _sender,
-          ...rest
-        } = m as Record<string, unknown>;
-
+      if (m && typeof m === "object" && "name" in m) {
+        const { name: _name, ...rest } = m as Record<string, unknown>;
         return rest;
       }
-
       return m;
     });
   }
   return next as T;
 }
-

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

@@ -14,228 +14,147 @@ export const cursorProvider: RegistryEntry = {
   headers: getCursorRegistryHeaders(),
   clientVersion: CURSOR_REGISTRY_VERSION,
   models: [
-    { id: "auto", name: "Auto (current, default)" },
-    { id: "auto-cost", name: "Auto (cost)" },
-    { id: "auto-balance", name: "Auto (balance)" },
-    { id: "auto-intelligence", name: "Auto (intelligence)" },
-    // Legacy combo ids kept so existing cu/<id> targets are not orphaned.
-    { id: "composer-2", name: "Composer 2" },
+    { id: "auto", name: "Auto (Server Picks)" },
+    { id: "composer-2.5-fast", name: "Composer 2.5 Fast" },
+    { id: "composer-2.5", name: "Composer 2.5" },
     { id: "composer-2-fast", name: "Composer 2 Fast" },
+    { id: "composer-2", name: "Composer 2" },
+    //
+    { id: "gpt-5.5-none", name: "GPT 5.5 None" },
+    { id: "gpt-5.5-none-fast", name: "GPT 5.5 None Fast" },
+    { id: "gpt-5.5-low", name: "GPT 5.5 Low" },
+    { id: "gpt-5.5-low-fast", name: "GPT 5.5 Low Fast" },
+    { id: "gpt-5.5-medium", name: "GPT 5.5 Medium" },
+    { id: "gpt-5.5-medium-fast", name: "GPT 5.5 Medium Fast" },
+    { id: "gpt-5.5-high", name: "GPT 5.5 High" },
+    { id: "gpt-5.5-high-fast", name: "GPT 5.5 High Fast" },
+    { id: "gpt-5.5-extra-high", name: "GPT 5.5 Extra High" },
+    { id: "gpt-5.5-extra-high-fast", name: "GPT 5.5 Extra High Fast" },
+    //
+    { id: "gpt-5.4-low", name: "GPT 5.4 Low" },
     { id: "gpt-5.4-low-fast", name: "GPT 5.4 Low Fast" },
+    { id: "gpt-5.4-medium", name: "GPT 5.4 Medium" },
+    { id: "gpt-5.4-medium-fast", name: "GPT 5.4 Medium Fast" },
+    { id: "gpt-5.4-high", name: "GPT 5.4 High" },
+    { id: "gpt-5.4-high-fast", name: "GPT 5.4 High Fast" },
+    { id: "gpt-5.4-xhigh", name: "GPT 5.4 XHigh" },
+    { id: "gpt-5.4-xhigh-fast", name: "GPT 5.4 XHigh Fast" },
+    //
+    { id: "gpt-5.4-mini-none", name: "GPT 5.4 Mini None" },
+    { id: "gpt-5.4-mini-low", name: "GPT 5.4 Mini Low" },
+    { id: "gpt-5.4-mini-medium", name: "GPT 5.4 Mini Medium" },
+    { id: "gpt-5.4-mini-high", name: "GPT 5.4 Mini High" },
+    { id: "gpt-5.4-mini-xhigh", name: "GPT 5.4 Mini XHigh" },
+    //
+    { id: "gpt-5.4-nano-none", name: "GPT 5.4 Nano None" },
+    { id: "gpt-5.4-nano-low", name: "GPT 5.4 Nano Low" },
+    { id: "gpt-5.4-nano-medium", name: "GPT 5.4 Nano Medium" },
+    { id: "gpt-5.4-nano-high", name: "GPT 5.4 Nano High" },
+    { id: "gpt-5.4-nano-xhigh", name: "GPT 5.4 Nano XHigh" },
+    //
     { id: "gpt-5.3-codex-spark-preview-low", name: "GPT 5.3 Codex Spark Preview Low" },
     { id: "gpt-5.3-codex-spark-preview", name: "GPT 5.3 Codex Spark Preview" },
     { id: "gpt-5.3-codex-spark-preview-high", name: "GPT 5.3 Codex Spark Preview High" },
     { id: "gpt-5.3-codex-spark-preview-xhigh", name: "GPT 5.3 Codex Spark Preview XHigh" },
+    //
+    { id: "gpt-5.3-codex-low", name: "GPT 5.3 Codex Low" },
+    { id: "gpt-5.3-codex-low-fast", name: "GPT 5.3 Codex Low Fast" },
+    { id: "gpt-5.3-codex", name: "GPT 5.3 Codex" },
+    { id: "gpt-5.3-codex-fast", name: "GPT 5.3 Codex Fast" },
+    { id: "gpt-5.3-codex-high", name: "GPT 5.3 Codex High" },
+    { id: "gpt-5.3-codex-high-fast", name: "GPT 5.3 Codex High Fast" },
+    { id: "gpt-5.3-codex-xhigh", name: "GPT 5.3 Codex XHigh" },
+    { id: "gpt-5.3-codex-xhigh-fast", name: "GPT 5.3 Codex XHigh Fast" },
+    //
+    { id: "gpt-5.2-low", name: "GPT 5.2 Low" },
+    { id: "gpt-5.2-low-fast", name: "GPT 5.2 Low Fast" },
+    { id: "gpt-5.2", name: "GPT 5.2" },
+    { id: "gpt-5.2-fast", name: "GPT 5.2 Fast" },
+    { id: "gpt-5.2-high", name: "GPT 5.2 High" },
+    { id: "gpt-5.2-high-fast", name: "GPT 5.2 High Fast" },
+    { id: "gpt-5.2-xhigh", name: "GPT 5.2 XHigh" },
+    { id: "gpt-5.2-xhigh-fast", name: "GPT 5.2 XHigh Fast" },
+    //
+    { id: "claude-opus-4-8-low", name: "Claude Opus 4.8 Low" },
+    { id: "claude-opus-4-8-low-fast", name: "Claude Opus 4.8 Low Fast" },
+    { id: "claude-opus-4-8-medium", name: "Claude Opus 4.8 Medium" },
+    { id: "claude-opus-4-8-medium-fast", name: "Claude Opus 4.8 Medium Fast" },
+    { id: "claude-opus-4-8-high", name: "Claude Opus 4.8 High" },
+    { id: "claude-opus-4-8-high-fast", name: "Claude Opus 4.8 High Fast" },
+    { id: "claude-opus-4-8-xhigh", name: "Claude Opus 4.8 XHigh" },
+    { id: "claude-opus-4-8-xhigh-fast", name: "Claude Opus 4.8 XHigh Fast" },
+    { id: "claude-opus-4-8-max", name: "Claude Opus 4.8 Max" },
+    { id: "claude-opus-4-8-max-fast", name: "Claude Opus 4.8 Max Fast" },
+    { id: "claude-opus-4-8-thinking-low", name: "Claude Opus 4.8 Thinking Low" },
+    { id: "claude-opus-4-8-thinking-low-fast", name: "Claude Opus 4.8 Thinking Low Fast" },
+    { id: "claude-opus-4-8-thinking-medium", name: "Claude Opus 4.8 Thinking Medium" },
+    { id: "claude-opus-4-8-thinking-medium-fast", name: "Claude Opus 4.8 Thinking Medium Fast" },
+    { id: "claude-opus-4-8-thinking-high", name: "Claude Opus 4.8 Thinking High" },
+    { id: "claude-opus-4-8-thinking-high-fast", name: "Claude Opus 4.8 Thinking High Fast" },
+    { id: "claude-opus-4-8-thinking-xhigh", name: "Claude Opus 4.8 Thinking XHigh" },
+    { id: "claude-opus-4-8-thinking-xhigh-fast", name: "Claude Opus 4.8 Thinking XHigh Fast" },
+    { id: "claude-opus-4-8-thinking-max", name: "Claude Opus 4.8 Thinking Max" },
+    { id: "claude-opus-4-8-thinking-max-fast", name: "Claude Opus 4.8 Thinking Max Fast" },
+    //
+    { id: "claude-fable-5-low", name: "Claude Fable 5 Low" },
+    { id: "claude-fable-5-medium", name: "Claude Fable 5 Medium" },
+    { id: "claude-fable-5-high", name: "Claude Fable 5 High" },
+    { id: "claude-fable-5-xhigh", name: "Claude Fable 5 XHigh" },
+    { id: "claude-fable-5-max", name: "Claude Fable 5 Max" },
+    { id: "claude-fable-5-thinking-low", name: "Claude Fable 5 Thinking Low" },
+    { id: "claude-fable-5-thinking-medium", name: "Claude Fable 5 Thinking Medium" },
+    { id: "claude-fable-5-thinking-high", name: "Claude Fable 5 Thinking High" },
+    { id: "claude-fable-5-thinking-xhigh", name: "Claude Fable 5 Thinking XHigh" },
+    { id: "claude-fable-5-thinking-max", name: "Claude Fable 5 Thinking Max" },
+    //
+    { id: "claude-sonnet-5-low", name: "Claude Sonnet 5 Low" },
+    { id: "claude-sonnet-5-medium", name: "Claude Sonnet 5 Medium" },
+    { id: "claude-sonnet-5-high", name: "Claude Sonnet 5 High" },
+    { id: "claude-sonnet-5-xhigh", name: "Claude Sonnet 5 XHigh" },
+    { id: "claude-sonnet-5-max", name: "Claude Sonnet 5 Max" },
+    { id: "claude-sonnet-5-thinking-low", name: "Claude Sonnet 5 Thinking Low" },
+    { id: "claude-sonnet-5-thinking-medium", name: "Claude Sonnet 5 Thinking Medium" },
+    { id: "claude-sonnet-5-thinking-high", name: "Claude Sonnet 5 Thinking High" },
+    { id: "claude-sonnet-5-thinking-xhigh", name: "Claude Sonnet 5 Thinking XHigh" },
+    { id: "claude-sonnet-5-thinking-max", name: "Claude Sonnet 5 Thinking Max" },
+    //
+    { id: "claude-opus-4-7-low", name: "Claude Opus 4.7 Low" },
+    { id: "claude-opus-4-7-medium", name: "Claude Opus 4.7 Medium" },
+    { id: "claude-opus-4-7-high", name: "Claude Opus 4.7 High" },
+    { id: "claude-opus-4-7-xhigh", name: "Claude Opus 4.7 XHigh" },
+    { id: "claude-opus-4-7-max", name: "Claude Opus 4.7 Max" },
+
+    { id: "claude-opus-4-7-thinking-low", name: "Claude Opus 4.7 Thinking Low" },
+    { id: "claude-opus-4-7-thinking-medium", name: "Claude Opus 4.7 Thinking Medium" },
+    { id: "claude-opus-4-7-thinking-high", name: "Claude Opus 4.7 Thinking High" },
+    { id: "claude-opus-4-7-thinking-xhigh", name: "Claude Opus 4.7 Thinking XHigh" },
+    { id: "claude-opus-4-7-thinking-max", name: "Claude Opus 4.7 Thinking Max" },
+    //
+    { id: "claude-4.6-opus-high", name: "Claude 4.6 Opus High" },
+    { id: "claude-4.6-opus-high-thinking", name: "Claude 4.6 Opus High Thinking" },
     { id: "claude-4.6-opus-high-thinking-fast", name: "Claude 4.6 Opus High Thinking Fast" },
+    { id: "claude-4.6-opus-max", name: "Claude 4.6 Opus Max" },
+    { id: "claude-4.6-opus-max-thinking", name: "Claude 4.6 Opus Max Thinking" },
     { id: "claude-4.6-opus-max-thinking-fast", name: "Claude 4.6 Opus Max Thinking Fast" },
+    //
     { id: "claude-4.6-sonnet-medium", name: "Claude 4.6 Sonnet Medium" },
     { id: "claude-4.6-sonnet-medium-thinking", name: "Claude 4.6 Sonnet Medium Thinking" },
+    //
     { id: "gemini-3.1-pro", name: "Gemini 3.1 Pro" },
+    //
     { id: "gemini-3.7-flash", name: "Gemini 3.7 Flash" },
     { id: "gemini-3-flash", name: "Gemini 3 Flash" },
+    //
     { id: "grok-4.6-medium", name: "Grok 4.6 Medium" },
     { id: "grok-4.6-fast-medium", name: "Grok 4.6 Fast Medium" },
     { id: "grok-4.6-high", name: "Grok 4.6 High" },
     { id: "grok-4.6-fast-high", name: "Grok 4.6 Fast High" },
     { id: "grok-4.6-xhigh", name: "Grok 4.6 XHigh" },
     { id: "grok-4.6-fast-xhigh", name: "Grok 4.6 Fast XHigh" },
+    //
     { id: "kimi-k3", name: "Kimi K3" },
     { id: "kimi-k2.7-code", name: "Kimi K2.7 Code" },
-    { id: "grok-4.3", name: "Grok 4.3" },
-    { id: "grok-4.5-medium", name: "Grok 4.5 Medium" },
-    { id: "grok-4.5-fast-medium", name: "Grok 4.5 Fast Medium" },
-    { id: "grok-4.5-high", name: "Grok 4.5 High" },
-    { id: "grok-4.5-fast-high", name: "Grok 4.5 Fast High" },
-    { id: "grok-4.5-xhigh", name: "Grok 4.5 XHigh" },
-    { id: "grok-4.5-fast-xhigh", name: "Grok 4.5 Fast XHigh" },
-    { id: "kimi-k2.5", name: "Kimi K2.5" },
-    { id: "gpt-5.3-codex-low", name: "Codex 5.3 Low" },
-    { id: "gpt-5.3-codex-low-fast", name: "Codex 5.3 Low Fast" },
-    { id: "gpt-5.3-codex", name: "Codex 5.3" },
-    { id: "gpt-5.3-codex-fast", name: "Codex 5.3 Fast" },
-    { id: "gpt-5.3-codex-high", name: "Codex 5.3 High" },
-    { id: "gpt-5.3-codex-high-fast", name: "Codex 5.3 High Fast" },
-    { id: "gpt-5.3-codex-xhigh", name: "Codex 5.3 Extra High" },
-    { id: "gpt-5.3-codex-xhigh-fast", name: "Codex 5.3 Extra High Fast" },
-    { id: "gpt-5.2", name: "GPT-5.2" },
-    { id: "cursor-grok-4.5-high", name: "Cursor Grok 4.5" },
-    { id: "cursor-grok-4.5-high-fast", name: "Cursor Grok 4.5 Fast" },
-    { id: "composer-2.5", name: "Composer 2.5" },
-    { id: "claude-opus-5-thinking-high", name: "Opus 5 1M Thinking" },
-    { id: "claude-opus-5-thinking-high-fast", name: "Opus 5 1M Thinking Fast" },
-    { id: "claude-opus-5-thinking-xhigh", name: "Opus 5 1M Extra High Thinking" },
-    { id: "claude-opus-5-thinking-xhigh-fast", name: "Opus 5 1M Extra High Thinking Fast" },
-    { id: "claude-opus-4-8-thinking-high", name: "Opus 4.8 1M Thinking" },
-    { id: "claude-opus-4-8-thinking-high-fast", name: "Opus 4.8 1M Thinking Fast" },
-    { id: "gpt-5.6-sol-high", name: "GPT-5.6 Sol 1M High" },
-    { id: "gpt-5.6-sol-high-fast", name: "GPT-5.6 Sol High Fast" },
-    { id: "gpt-5.6-sol-xhigh", name: "GPT-5.6 Sol 1M Extra High" },
-    { id: "gpt-5.6-sol-xhigh-fast", name: "GPT-5.6 Sol Extra High Fast" },
-    { id: "gpt-5.5-high", name: "GPT-5.5 1M High" },
-    { id: "gpt-5.5-high-fast", name: "GPT-5.5 High Fast" },
-    { id: "claude-fable-5-thinking-high", name: "Fable 5 1M Thinking (NO ZDR)" },
-    { id: "claude-fable-5-thinking-xhigh", name: "Fable 5 1M Extra High Thinking (NO ZDR)" },
-    { id: "claude-sonnet-5-thinking-high", name: "Sonnet 5 1M Thinking" },
-    { id: "claude-sonnet-5-thinking-xhigh", name: "Sonnet 5 1M Extra High Thinking" },
-    { id: "kimi-k3-high", name: "Kimi K3 High" },
-    { id: "cursor-grok-4.5-low", name: "Cursor Grok 4.5 Low" },
-    { id: "cursor-grok-4.5-low-fast", name: "Cursor Grok 4.5 Low Fast" },
-    { id: "cursor-grok-4.5-medium", name: "Cursor Grok 4.5 Medium" },
-    { id: "cursor-grok-4.5-medium-fast", name: "Cursor Grok 4.5 Medium Fast" },
-    { id: "composer-2.5-fast", name: "Composer 2.5 Fast" },
-    { id: "claude-opus-5-low", name: "Opus 5 1M Low" },
-    { id: "claude-opus-5-low-fast", name: "Opus 5 1M Low Fast" },
-    { id: "claude-opus-5-medium", name: "Opus 5 1M Medium" },
-    { id: "claude-opus-5-medium-fast", name: "Opus 5 1M Medium Fast" },
-    { id: "claude-opus-5-high", name: "Opus 5 1M" },
-    { id: "claude-opus-5-high-fast", name: "Opus 5 1M Fast" },
-    { id: "claude-opus-5-thinking-low", name: "Opus 5 1M Low Thinking" },
-    { id: "claude-opus-5-thinking-low-fast", name: "Opus 5 1M Low Thinking Fast" },
-    { id: "claude-opus-5-thinking-medium", name: "Opus 5 1M Medium Thinking" },
-    { id: "claude-opus-5-thinking-medium-fast", name: "Opus 5 1M Medium Thinking Fast" },
-    { id: "claude-opus-5-thinking-max", name: "Opus 5 1M Max Thinking" },
-    { id: "claude-opus-5-thinking-max-fast", name: "Opus 5 1M Max Thinking Fast" },
-    { id: "claude-opus-4-8-low", name: "Opus 4.8 1M Low" },
-    { id: "claude-opus-4-8-low-fast", name: "Opus 4.8 1M Low Fast" },
-    { id: "claude-opus-4-8-medium", name: "Opus 4.8 1M Medium" },
-    { id: "claude-opus-4-8-medium-fast", name: "Opus 4.8 1M Medium Fast" },
-    { id: "claude-opus-4-8-high", name: "Opus 4.8 1M" },
-    { id: "claude-opus-4-8-high-fast", name: "Opus 4.8 1M Fast" },
-    { id: "claude-opus-4-8-xhigh", name: "Opus 4.8 1M Extra High" },
-    { id: "claude-opus-4-8-xhigh-fast", name: "Opus 4.8 1M Extra High Fast" },
-    { id: "claude-opus-4-8-max", name: "Opus 4.8 1M Max" },
-    { id: "claude-opus-4-8-max-fast", name: "Opus 4.8 1M Max Fast" },
-    { id: "claude-opus-4-8-thinking-low", name: "Opus 4.8 1M Low Thinking" },
-    { id: "claude-opus-4-8-thinking-low-fast", name: "Opus 4.8 1M Low Thinking Fast" },
-    { id: "claude-opus-4-8-thinking-medium", name: "Opus 4.8 1M Medium Thinking" },
-    { id: "claude-opus-4-8-thinking-medium-fast", name: "Opus 4.8 1M Medium Thinking Fast" },
-    { id: "claude-opus-4-8-thinking-xhigh", name: "Opus 4.8 1M Extra High Thinking" },
-    { id: "claude-opus-4-8-thinking-xhigh-fast", name: "Opus 4.8 1M Extra High Thinking Fast" },
-    { id: "claude-opus-4-8-thinking-max", name: "Opus 4.8 1M Max Thinking" },
-    { id: "claude-opus-4-8-thinking-max-fast", name: "Opus 4.8 1M Max Thinking Fast" },
-    { id: "gpt-5.6-sol-none", name: "GPT-5.6 Sol 1M None" },
-    { id: "gpt-5.6-sol-none-fast", name: "GPT-5.6 Sol None Fast" },
-    { id: "gpt-5.6-sol-low", name: "GPT-5.6 Sol 1M Low" },
-    { id: "gpt-5.6-sol-low-fast", name: "GPT-5.6 Sol Low Fast" },
-    { id: "gpt-5.6-sol-medium", name: "GPT-5.6 Sol 1M" },
-    { id: "gpt-5.6-sol-medium-fast", name: "GPT-5.6 Sol Fast" },
-    { id: "gpt-5.6-sol-max", name: "GPT-5.6 Sol 1M Max" },
-    { id: "gpt-5.6-sol-max-fast", name: "GPT-5.6 Sol Max Fast" },
-    { id: "gpt-5.5-none", name: "GPT-5.5 1M None" },
-    { id: "gpt-5.5-none-fast", name: "GPT-5.5 None Fast" },
-    { id: "gpt-5.5-low", name: "GPT-5.5 1M Low" },
-    { id: "gpt-5.5-low-fast", name: "GPT-5.5 Low Fast" },
-    { id: "gpt-5.5-medium", name: "GPT-5.5 1M" },
-    { id: "gpt-5.5-medium-fast", name: "GPT-5.5 Fast" },
-    { id: "gpt-5.5-extra-high", name: "GPT-5.5 1M Extra High" },
-    { id: "gpt-5.5-extra-high-fast", name: "GPT-5.5 Extra High Fast" },
-    { id: "claude-fable-5-low", name: "Fable 5 1M Low (NO ZDR)" },
-    { id: "claude-fable-5-medium", name: "Fable 5 1M Medium (NO ZDR)" },
-    { id: "claude-fable-5-high", name: "Fable 5 1M (NO ZDR)" },
-    { id: "claude-fable-5-xhigh", name: "Fable 5 1M Extra High (NO ZDR)" },
-    { id: "claude-fable-5-max", name: "Fable 5 1M Max (NO ZDR)" },
-    { id: "claude-fable-5-thinking-low", name: "Fable 5 1M Low Thinking (NO ZDR)" },
-    { id: "claude-fable-5-thinking-medium", name: "Fable 5 1M Medium Thinking (NO ZDR)" },
-    { id: "claude-fable-5-thinking-max", name: "Fable 5 1M Max Thinking (NO ZDR)" },
-    { id: "claude-sonnet-5-low", name: "Sonnet 5 1M Low" },
-    { id: "claude-sonnet-5-medium", name: "Sonnet 5 1M Medium" },
-    { id: "claude-sonnet-5-high", name: "Sonnet 5 1M" },
-    { id: "claude-sonnet-5-xhigh", name: "Sonnet 5 1M Extra High" },
-    { id: "claude-sonnet-5-max", name: "Sonnet 5 1M Max" },
-    { id: "claude-sonnet-5-thinking-low", name: "Sonnet 5 1M Low Thinking" },
-    { id: "claude-sonnet-5-thinking-medium", name: "Sonnet 5 1M Medium Thinking" },
-    { id: "claude-sonnet-5-thinking-max", name: "Sonnet 5 1M Max Thinking" },
-    { id: "gpt-5.6-terra-none", name: "GPT-5.6 Terra 1M None" },
-    { id: "gpt-5.6-terra-none-fast", name: "GPT-5.6 Terra None Fast" },
-    { id: "gpt-5.6-terra-low", name: "GPT-5.6 Terra 1M Low" },
-    { id: "gpt-5.6-terra-low-fast", name: "GPT-5.6 Terra Low Fast" },
-    { id: "gpt-5.6-terra-medium", name: "GPT-5.6 Terra 1M" },
-    { id: "gpt-5.6-terra-medium-fast", name: "GPT-5.6 Terra Fast" },
-    { id: "gpt-5.6-terra-high", name: "GPT-5.6 Terra 1M High" },
-    { id: "gpt-5.6-terra-high-fast", name: "GPT-5.6 Terra High Fast" },
-    { id: "gpt-5.6-terra-xhigh", name: "GPT-5.6 Terra 1M Extra High" },
-    { id: "gpt-5.6-terra-xhigh-fast", name: "GPT-5.6 Terra Extra High Fast" },
-    { id: "gpt-5.6-terra-max", name: "GPT-5.6 Terra 1M Max" },
-    { id: "gpt-5.6-terra-max-fast", name: "GPT-5.6 Terra Max Fast" },
-    { id: "claude-opus-4-7-low", name: "Opus 4.7 1M Low" },
-    { id: "claude-opus-4-7-low-fast", name: "Opus 4.7 1M Low Fast" },
-    { id: "claude-opus-4-7-medium", name: "Opus 4.7 1M Medium" },
-    { id: "claude-opus-4-7-medium-fast", name: "Opus 4.7 1M Medium Fast" },
-    { id: "claude-opus-4-7-high", name: "Opus 4.7 1M High" },
-    { id: "claude-opus-4-7-high-fast", name: "Opus 4.7 1M High Fast" },
-    { id: "claude-opus-4-7-xhigh", name: "Opus 4.7 1M" },
-    { id: "claude-opus-4-7-xhigh-fast", name: "Opus 4.7 1M Fast" },
-    { id: "claude-opus-4-7-max", name: "Opus 4.7 1M Max" },
-    { id: "claude-opus-4-7-max-fast", name: "Opus 4.7 1M Max Fast" },
-    { id: "claude-opus-4-7-thinking-low", name: "Opus 4.7 1M Low Thinking" },
-    { id: "claude-opus-4-7-thinking-low-fast", name: "Opus 4.7 1M Low Thinking Fast" },
-    { id: "claude-opus-4-7-thinking-medium", name: "Opus 4.7 1M Medium Thinking" },
-    { id: "claude-opus-4-7-thinking-medium-fast", name: "Opus 4.7 1M Medium Thinking Fast" },
-    { id: "claude-opus-4-7-thinking-high", name: "Opus 4.7 1M High Thinking" },
-    { id: "claude-opus-4-7-thinking-high-fast", name: "Opus 4.7 1M High Thinking Fast" },
-    { id: "claude-opus-4-7-thinking-xhigh", name: "Opus 4.7 1M Thinking" },
-    { id: "claude-opus-4-7-thinking-xhigh-fast", name: "Opus 4.7 1M Thinking Fast" },
-    { id: "claude-opus-4-7-thinking-max", name: "Opus 4.7 1M Max Thinking" },
-    { id: "claude-opus-4-7-thinking-max-fast", name: "Opus 4.7 1M Max Thinking Fast" },
-    { id: "gpt-5.4-low", name: "GPT-5.4 1M Low" },
-    { id: "gpt-5.4-medium", name: "GPT-5.4 1M" },
-    { id: "gpt-5.4-medium-fast", name: "GPT-5.4 Fast" },
-    { id: "gpt-5.4-high", name: "GPT-5.4 1M High" },
-    { id: "gpt-5.4-high-fast", name: "GPT-5.4 High Fast" },
-    { id: "gpt-5.4-xhigh", name: "GPT-5.4 1M Extra High" },
-    { id: "gpt-5.4-xhigh-fast", name: "GPT-5.4 Extra High Fast" },
-    { id: "claude-4.6-opus-high", name: "Opus 4.6 1M" },
-    { id: "claude-4.6-opus-max", name: "Opus 4.6 1M Max" },
-    { id: "claude-4.6-opus-high-thinking", name: "Opus 4.6 1M Thinking" },
-    { id: "claude-4.6-opus-max-thinking", name: "Opus 4.6 1M Max Thinking" },
-    { id: "claude-4.5-opus-high", name: "Opus 4.5" },
-    { id: "claude-4.5-opus-high-thinking", name: "Opus 4.5 Thinking" },
-    { id: "gpt-5.2-low", name: "GPT-5.2 Low" },
-    { id: "gpt-5.2-low-fast", name: "GPT-5.2 Low Fast" },
-    { id: "gpt-5.2-fast", name: "GPT-5.2 Fast" },
-    { id: "gpt-5.2-high", name: "GPT-5.2 High" },
-    { id: "gpt-5.2-high-fast", name: "GPT-5.2 High Fast" },
-    { id: "gpt-5.2-xhigh", name: "GPT-5.2 Extra High" },
-    { id: "gpt-5.2-xhigh-fast", name: "GPT-5.2 Extra High Fast" },
-    { id: "gpt-5.6-luna-none", name: "GPT-5.6 Luna 1M None" },
-    { id: "gpt-5.6-luna-none-fast", name: "GPT-5.6 Luna None Fast" },
-    { id: "gpt-5.6-luna-low", name: "GPT-5.6 Luna 1M Low" },
-    { id: "gpt-5.6-luna-low-fast", name: "GPT-5.6 Luna Low Fast" },
-    { id: "gpt-5.6-luna-medium", name: "GPT-5.6 Luna 1M" },
-    { id: "gpt-5.6-luna-medium-fast", name: "GPT-5.6 Luna Fast" },
-    { id: "gpt-5.6-luna-high", name: "GPT-5.6 Luna 1M High" },
-    { id: "gpt-5.6-luna-high-fast", name: "GPT-5.6 Luna High Fast" },
-    { id: "gpt-5.6-luna-xhigh", name: "GPT-5.6 Luna 1M Extra High" },
-    { id: "gpt-5.6-luna-xhigh-fast", name: "GPT-5.6 Luna Extra High Fast" },
-    { id: "gpt-5.6-luna-max", name: "GPT-5.6 Luna 1M Max" },
-    { id: "gpt-5.6-luna-max-fast", name: "GPT-5.6 Luna Max Fast" },
-    { id: "gemini-3.6-flash-minimal", name: "Gemini 3.6 Flash Minimal" },
-    { id: "gemini-3.6-flash-low", name: "Gemini 3.6 Flash Low" },
-    { id: "gemini-3.6-flash-medium", name: "Gemini 3.6 Flash Medium" },
-    { id: "gemini-3.6-flash-high", name: "Gemini 3.6 Flash" },
-    { id: "gpt-5.4-mini-none", name: "GPT-5.4 Mini None" },
-    { id: "gpt-5.4-mini-low", name: "GPT-5.4 Mini Low" },
-    { id: "gpt-5.4-mini-medium", name: "GPT-5.4 Mini" },
-    { id: "gpt-5.4-mini-high", name: "GPT-5.4 Mini High" },
-    { id: "gpt-5.4-mini-xhigh", name: "GPT-5.4 Mini Extra High" },
-    { id: "gpt-5.4-nano-none", name: "GPT-5.4 Nano None" },
-    { id: "gpt-5.4-nano-low", name: "GPT-5.4 Nano Low" },
-    { id: "gpt-5.4-nano-medium", name: "GPT-5.4 Nano" },
-    { id: "gpt-5.4-nano-high", name: "GPT-5.4 Nano High" },
-    { id: "gpt-5.4-nano-xhigh", name: "GPT-5.4 Nano Extra High" },
-    { id: "claude-4.5-sonnet", name: "Sonnet 4.5" },
-    { id: "claude-4.5-sonnet-thinking", name: "Sonnet 4.5 Thinking" },
-    { id: "gpt-5.1-low", name: "GPT-5.1 Low" },
-    { id: "gpt-5.1", name: "GPT-5.1" },
-    { id: "gpt-5.1-high", name: "GPT-5.1 High" },
-    { id: "gemini-3.5-flash", name: "Gemini 3.5 Flash" },
-    { id: "claude-4-sonnet", name: "Sonnet 4" },
-    { id: "claude-4-sonnet-thinking", name: "Sonnet 4 Thinking" },
-    { id: "gpt-5-mini", name: "GPT-5 Mini" },
-    { id: "kimi-k3-low", name: "Kimi K3 Low" },
-    { id: "kimi-k3-max", name: "Kimi K3" },
-    { id: "glm-5.2-high", name: "GLM 5.2" },
-    { id: "glm-5.2-max", name: "GLM 5.2 Max" },  ],
+  ],
 };
 
 /**

open-sse/config/searchRegistry.ts

@@ -280,44 +280,19 @@ export const SEARCH_PROVIDERS: Record<string, SearchProviderConfig> = {
     cacheTTLMs: 5 * 60 * 1000,
     fallbackOnly: true,
   },
-
-  // SuperGrok / xAI server-side X Search. Not web search. Explicit provider or
-  // search_type "x" only — never auto-selected for generic web queries.
-  "x-search": {
-    id: "x-search",
-    name: "X Search (Grok)",
-    baseUrl: "https://api.x.ai/v1/responses",
-    method: "POST",
-    authType: "apikey",
-    authHeader: "bearer",
-    costPerQuery: 0,
-    freeMonthlyQuota: 0,
-    searchTypes: ["x"],
-    defaultMaxResults: 5,
-    maxMaxResults: 20,
-    timeoutMs: 60_000,
-    cacheTTLMs: 5 * 60 * 1000,
-  },
 };
 
 /**
  * Credential fallback mapping — search providers that can reuse credentials
  * from a related provider (e.g., perplexity-search uses the same API key as perplexity chat).
  */
-export const SEARCH_CREDENTIAL_FALLBACKS: Record<string, string | string[]> = {
+export const SEARCH_CREDENTIAL_FALLBACKS: Record<string, string> = {
   "perplexity-search": "perplexity",
   "ollama-search": "ollama-cloud",
   "zai-search": "zai",
   "jina-search": "jina-ai",
-  "x-search": ["xai-oauth", "xao", "xai"],
 };
 
-export function getSearchCredentialFallbacks(providerId: string): string[] {
-  const mapped = SEARCH_CREDENTIAL_FALLBACKS[providerId];
-  if (!mapped) return [];
-  return Array.isArray(mapped) ? mapped : [mapped];
-}
-
 /**
  * Request-only aliases for POST /v1/search.
  *
@@ -341,8 +316,6 @@ export const SEARCH_PROVIDER_ALIASES: Record<string, string> = {
   searxng: "searxng-search",
   zai: "zai-search",
   duckduckgo: "duckduckgo-free",
-  "x_search": "x-search",
-  x: "x-search",
 };
 
 export function resolveSearchProviderId(providerId: string): string {
@@ -354,24 +327,6 @@ export function resolveSearchProviderId(providerId: string): string {
  * Request routing should use resolveSearchProvider() so aliases work
  * without colliding with the Foundation jina-ai provider id.
  */
-const CATALOG_SEARXNG_DEFAULT_URL = "http://localhost:8888/search";
-
-/**
- * Catalog default SearXNG URL is a desktop convenience. In Docker/K8s nothing
- * listens on :8888, and OMNIROUTE_ALLOW_PRIVATE_PROVIDER_URLS (needed for
- * ClusterIP providers) lets ProxyFetch attempt it, producing ECONNREFUSED and
- * a 502 that then burns the next fallback's quota. Skip unless the operator
- * overrode baseUrl.
- */
-export function isUnconfiguredLoopbackSearchProvider(
-  provider: SearchProviderConfig | null | undefined
-): boolean {
-  if (!provider || provider.id !== "searxng-search") return false;
-  const configured = String(provider.baseUrl || "").replace(/\/+$/, "");
-  const catalog = CATALOG_SEARXNG_DEFAULT_URL.replace(/\/+$/, "");
-  return configured === catalog;
-}
-
 export function getSearchProvider(providerId: string): SearchProviderConfig | null {
   return SEARCH_PROVIDERS[providerId] || null;
 }
@@ -424,11 +379,10 @@ export function selectProvider(
 
   // Auto-selection excludes fallbackOnly providers so a free cost-0 provider never
   // overrides a configured paid one — they are reached only via explicit id or the
-  // route handler's last-resort step. Missing searchType follows the API default
-  // (`web`) so X-only providers are never cheapest-wins for generic queries.
-  const effectiveType = searchType || "web";
+  // route handler's last-resort step.
   const providers = Object.values(SEARCH_PROVIDERS).filter(
-    (provider) => !provider.fallbackOnly && supportsSearchType(provider, effectiveType)
+    (provider) =>
+      !provider.fallbackOnly && (searchType ? supportsSearchType(provider, searchType) : true)
   );
   if (providers.length === 0) return null;
 

open-sse/executors/accountRotation.ts

@@ -40,15 +40,6 @@ export interface RotatableAccount {
   cooldownUntil: number;
   consecutiveFails: number;
   proxy: AccountProxyConfig["proxy"];
-  evictedAt?: number | null;
-}
-
-export type CooldownKind = "transient" | "terminal";
-
-const EVICT_AFTER_TERMINAL = 3;
-
-export function isAccountEvicted(account: RotatableAccount): boolean {
-  return account.evictedAt != null;
 }
 
 const COOLDOWN_BASE_MS = TRANSIENT_COOLDOWN_MS;
@@ -83,21 +74,17 @@ export function pickAccount<T extends RotatableAccount>(
   return accounts[fallbackIdx];
 }
 
-export function markCooldown(account: RotatableAccount, kind: CooldownKind = "transient"): void {
+export function markCooldown(account: RotatableAccount): void {
   account.consecutiveFails++;
   const backoff = Math.min(
     COOLDOWN_BASE_MS * Math.pow(2, account.consecutiveFails - 1),
     COOLDOWN_MAX_MS
   );
   account.cooldownUntil = Date.now() + backoff + Math.random() * 1000;
-  if (kind === "terminal" && account.consecutiveFails >= EVICT_AFTER_TERMINAL) {
-    account.evictedAt = Date.now();
-  }
 }
 
 export function markSuccess(account: RotatableAccount): void {
   account.consecutiveFails = 0;
-  account.evictedAt = null;
 }
 
 /** Mask an account id for logs (UI calls it a fingerprint). */

open-sse/executors/codex.ts

@@ -481,18 +481,15 @@ function toCodexResponseFailedEvent(parsed: Record<string, unknown>): Record<str
   };
 }
 
-// Drop non-standard `codex.*` SSE events (notably `codex.rate_limits`) from
-// the Responses stream. These events are NOT part of the OpenAI Responses API
-// — strict clients (e.g. the OpenAI SDK's `responses.stream()`) choke on the
-// unknown event type / empty data field and tear the stream down, surfacing as
-// 502 "Unknown error" / "Invalid state: Controller is already closed".
-// Default ON (#11014). Opt out with 0/false/no/off if a client consumes them.
-export function codexDropNonstandardEvents(): boolean {
+// Env-gated kill-switch: drop ALL non-standard `codex.*` SSE events (notably
+// `codex.rate_limits`) from the Responses stream. These events are NOT part of
+// the OpenAI Responses API — strict clients (e.g. the OpenAI SDK's
+// `responses.stream()`) choke on the unknown event type / empty data field and
+// tear the stream down, surfacing as "Invalid state: Controller is already
+// closed". Opt-in so the default still forwards them for clients that want them.
+function codexDropNonstandardEvents(): boolean {
   const v = process.env.OMNIROUTE_CODEX_DROP_NONSTANDARD_EVENTS;
-  if (v === undefined || v.trim() === "") return true;
-  const n = v.trim().toLowerCase();
-  if (n === "0" || n === "false" || n === "no" || n === "off") return false;
-  return true;
+  return v === "true" || v === "1" || v === "yes";
 }
 
 // SSE block filter for the HTTP Responses path (super.execute). The HTTP
@@ -501,7 +498,7 @@ export function codexDropNonstandardEvents(): boolean {
 // encodeResponseSseEvent never runs for it. When the kill-switch is on, strip
 // every `codex.*` event block from the byte stream before it reaches the client.
 // Exported for unit testing (#4715). Strips `codex.*` SSE event blocks from a
-// streaming Response when `codexDropNonstandardEvents()` is on (default, #11014).
+// streaming Response when the OMNIROUTE_CODEX_DROP_NONSTANDARD_EVENTS kill-switch is on.
 export function filterNonstandardCodexSse(response: Response): Response {
   const contentType = response.headers.get("content-type") || "";
   if (!response.body || !contentType.includes("text/event-stream")) {
@@ -704,8 +701,8 @@ export function encodeResponseSseEvent(raw: string): { sse: string; terminal: bo
   // "Invalid state: Controller is already closed". The earlier empty-payload
   // check below never caught codex.rate_limits — over WS the frame carries a
   // non-empty JSON payload (`{"type":"codex.rate_limits", ...}`), so
-  // `!payload.trim()` is false. Match by event type instead. Default ON via
-  // OMNIROUTE_CODEX_DROP_NONSTANDARD_EVENTS (#11014); the HTTP transport is handled
+  // `!payload.trim()` is false. Match by event type instead. Opt-in via
+  // OMNIROUTE_CODEX_DROP_NONSTANDARD_EVENTS (the HTTP transport is handled
   // separately by filterNonstandardCodexSse, since super.execute forwards the
   // upstream stream verbatim and never runs this function).
   if (eventType.startsWith("codex.") && codexDropNonstandardEvents()) {

open-sse/executors/commandCode.ts

@@ -738,7 +738,6 @@ function createStreamResponse(
   const decoder = new TextDecoder();
   let buffer = "";
   let sentRole = false;
-  let sentContent = false;
   let closed = false;
   const state: AggregateState = {
     content: "",
@@ -773,10 +772,7 @@ function createStreamResponse(
         switch (event.type) {
           case "text-delta": {
             const text = stringValue(event.text) || "";
-            if (text) {
-              sentContent = true;
-              controller.enqueue(sse(chatCompletionChunk(id, model, { content: text })));
-            }
+            if (text) controller.enqueue(sse(chatCompletionChunk(id, model, { content: text })));
             state.content += text;
             break;
           }
@@ -814,12 +810,6 @@ function createStreamResponse(
             break;
           case "finish": {
             state.finishReason = mapFinishReason(event.finishReason);
-            // If the model only produced reasoning-delta events (no text-delta), the
-            // client-visible stream would otherwise end with no content. Emit one
-            // content delta carrying the accumulated reasoning text (#10986).
-            if (!sentContent && state.reasoning && state.toolCalls.length === 0) {
-              controller.enqueue(sse(chatCompletionChunk(id, model, { content: state.reasoning })));
-            }
             controller.enqueue(sse(chatCompletionChunk(id, model, {}, state.finishReason)));
             // Emit a standards-compliant usage-only chunk (choices: []) before
             // [DONE] when upstream reported usage. stream.ts's extractUsage
@@ -867,9 +857,6 @@ function createStreamResponse(
           if (!closed) {
             if (!sentRole)
               controller.enqueue(sse(chatCompletionChunk(id, model, { role: "assistant" })));
-            if (!sentContent && state.reasoning && state.toolCalls.length === 0) {
-              controller.enqueue(sse(chatCompletionChunk(id, model, { content: state.reasoning })));
-            }
             controller.enqueue(sse(chatCompletionChunk(id, model, {}, state.finishReason)));
             controller.enqueue(encoder.encode("data: [DONE]\n\n"));
             controller.close();
@@ -960,14 +947,6 @@ async function createJsonResponse(
   }
 
   const message: JsonRecord = { role: "assistant", content: state.content };
-  // Some Command Code models emit the whole answer as reasoning-delta events and
-  // never a text-delta. When that leaves content empty, surface the reasoning text
-  // as content too (#10986) so OpenAI-compatible clients get a usable answer. Keep
-  // reasoning_content populated as well for reasoning-aware clients, and do not
-  // override content when real text OR tool calls are present.
-  if (!state.content && state.reasoning && state.toolCalls.length === 0) {
-    message.content = state.reasoning;
-  }
   if (state.reasoning) message.reasoning_content = state.reasoning;
   if (state.toolCalls.length > 0) message.tool_calls = state.toolCalls;
 

open-sse/executors/cursor.ts

@@ -12,7 +12,6 @@ declare const EdgeRuntime: string | undefined;
 
 import { BaseExecutor, mergeUpstreamExtraHeaders } from "./base.ts";
 import { PROVIDERS, HTTP_STATUS } from "../config/constants.ts";
-import { getAccessToken } from "../services/tokenRefresh.ts";
 import {
   buildAgentRequestBody,
   decodeAgentServerMessage,
@@ -84,12 +83,6 @@ import {
   composerReasoningRemainder,
 } from "./cursor/composer.ts";
 import { CursorServerConfigError, resolveCursorAgentUrl } from "./cursor/agentEndpoint.ts";
-import {
-  classifyCursorError,
-  isCursorBenignCancelError,
-  resolveCursorEmptyTurnError,
-  type ClassifiedCursorError,
-} from "./cursor/cursorErrors.ts";
 import { getActiveSyncedCatalog } from "../../src/lib/db/models/activeSyncedCatalog.ts";
 // Composer helpers re-exported for external importers (tests).
 export {
@@ -257,33 +250,19 @@ function tryParseJsonError(payload: Buffer): { message: string; status: number }
     if (!text.includes('"error"')) return null;
     const parsed = JSON.parse(text);
     const err = parsed?.error || {};
-    const rawMessage =
+    const message =
       err?.details?.[0]?.debug?.details?.title ||
       err?.details?.[0]?.debug?.details?.detail ||
       err?.message ||
-      (typeof err?.code === "string" ? `${err.code}: ${text}` : text);
-    const codeHint =
-      typeof err?.code === "string" &&
-      !String(rawMessage).toLowerCase().includes(err.code.toLowerCase())
-        ? `${err.code}: ${rawMessage}`
-        : String(rawMessage);
-    const classified = classifyCursorError(codeHint);
-    return { message: classified.message, status: classified.status };
+      text;
+    const status =
+      err?.code === "resource_exhausted" ? HTTP_STATUS.RATE_LIMITED : HTTP_STATUS.BAD_REQUEST;
+    return { message, status };
   } catch {
     return null;
   }
 }
 
-/** True when the turn produced no client-visible assistant payload. */
-function isCursorEmptyTurn(ctx: StreamCtx): boolean {
-  return (
-    ctx.totalText.length === 0 &&
-    ctx.thinkingText.length === 0 &&
-    ctx.toolCalls.length === 0 &&
-    !ctx.composerInlineToolCallsEmitted
-  );
-}
-
 // ─── Phase 4: streaming dispatch context ───────────────────────────────────
 //
 // One StreamCtx flows through a single execute() call. It owns the live
@@ -376,27 +355,6 @@ function emitChunk(ctx: StreamCtx, delta: object, finishReason: string | null =
   ctx.emit(`data: ${JSON.stringify(payload)}\n\n`);
 }
 
-/**
- * Emit a terminal OpenAI SSE error matching `buildStreamErrorChunks` shape
- * (`finish_reason: "error"` + `error.message`) so #8649 sawError stands down
- * and Model Test All keeps the classified Cursor message.
- */
-export function emitCursorSseError(ctx: StreamCtx, classified: ClassifiedCursorError): void {
-  const payload = {
-    id: ctx.responseId,
-    object: "chat.completion.chunk",
-    created: ctx.created,
-    model: ctx.model,
-    choices: [{ index: 0, delta: {}, finish_reason: "error" }],
-    error: {
-      message: classified.message,
-      type: classified.type,
-    },
-  };
-  ctx.emit(`data: ${JSON.stringify(payload)}\n\n`);
-  ctx.emit("data: [DONE]\n\n");
-}
-
 export function buildCursorUsage(ctx: StreamCtx, body: { messages?: ChatMessage[] }) {
   const promptTokens = estimateInputTokens(body);
   const completionTokens =
@@ -1483,17 +1441,6 @@ export class CursorExecutor extends BaseExecutor {
               finishLifecycle(ctx, false);
               controller.close();
             } catch (err) {
-              // OpenCodex: NGHTTP2_CANCEL after client-tool suspend is expected — finish
-              // the SSE turn instead of surfacing a transport failure.
-              if (
-                isCursorBenignCancelError(err) &&
-                (ctx.totalText.length > 0 || ctx.pendingToolCalls.size > 0)
-              ) {
-                this.finalizeSseStream(ctx, body);
-                finishLifecycle(ctx, false);
-                controller.close();
-                return;
-              }
               finishLifecycle(ctx, true);
               controller.error(err);
             }
@@ -1521,23 +1468,10 @@ export class CursorExecutor extends BaseExecutor {
     try {
       await this.driveH2(h2, ctx, mcpTools, blobStore, clientPlatform, todoHistory, signal);
     } catch (err) {
-      if (
-        isCursorBenignCancelError(err) &&
-        (ctx.totalText.length > 0 || ctx.pendingToolCalls.size > 0)
-      ) {
-        finishLifecycle(ctx, false);
-        return {
-          response: this.buildResponseFromCtx(ctx, body),
-          url,
-          headers,
-          transformedBody: body,
-        };
-      }
       finishLifecycle(ctx, true);
       const message = err instanceof Error ? err.message : String(err);
-      const classified = classifyCursorError(message);
       return {
-        response: buildErrorResponse(classified.status, classified.message, classified.type),
+        response: buildErrorResponse(HTTP_STATUS.SERVER_ERROR, message, "connection_error"),
         url,
         headers,
         transformedBody: body,
@@ -1559,22 +1493,24 @@ export class CursorExecutor extends BaseExecutor {
    */
   private finalizeSseStream(ctx: StreamCtx, body: { messages?: ChatMessage[] }) {
     if (ctx.midStreamError && ctx.totalText.length === 0) {
-      emitCursorSseError(ctx, classifyCursorError(ctx.midStreamError.message));
+      const payload = {
+        id: ctx.responseId,
+        object: "chat.completion.chunk",
+        created: ctx.created,
+        model: ctx.model,
+        choices: [],
+        error: {
+          message: ctx.midStreamError.message,
+          type:
+            ctx.midStreamError.status === HTTP_STATUS.RATE_LIMITED
+              ? "rate_limit_error"
+              : "api_error",
+        },
+      };
+      ctx.emit(`data: ${JSON.stringify(payload)}\n\n`);
+      ctx.emit("data: [DONE]\n\n");
       return;
     }
-
-    // Silent empty turn (auth accepted, no text) — surface actionable error instead of
-    // an empty assistant completion that chatCore maps to opaque "empty content" 502.
-    if (isCursorEmptyTurn(ctx) && ctx.endReason && ctx.endReason !== "tool_calls") {
-      emitCursorSseError(
-        ctx,
-        resolveCursorEmptyTurnError({
-          upstreamMessage: ctx.midStreamError?.message,
-        })
-      );
-      return;
-    }
-
     if (!ctx.emittedRoleChunk) {
       // Edge case: empty response. Emit a role chunk so clients see at least
       // one delta before finish.
@@ -1629,34 +1565,18 @@ export class CursorExecutor extends BaseExecutor {
    */
   private buildResponseFromCtx(ctx: StreamCtx, body: { messages?: ChatMessage[] }): Response {
     if (ctx.midStreamError && ctx.totalText.length === 0) {
-      const classified = classifyCursorError(ctx.midStreamError.message);
       return new Response(
         JSON.stringify({
           error: {
-            message: classified.message,
-            type: classified.type,
+            message: ctx.midStreamError.message,
+            type:
+              ctx.midStreamError.status === HTTP_STATUS.RATE_LIMITED
+                ? "rate_limit_error"
+                : "api_error",
           },
         }),
         {
-          status: classified.status,
-          headers: { "Content-Type": "application/json" },
-        }
-      );
-    }
-
-    if (isCursorEmptyTurn(ctx) && ctx.endReason && ctx.endReason !== "tool_calls") {
-      const empty = resolveCursorEmptyTurnError({
-        upstreamMessage: ctx.midStreamError?.message,
-      });
-      return new Response(
-        JSON.stringify({
-          error: {
-            message: empty.message,
-            type: empty.type,
-          },
-        }),
-        {
-          status: empty.status,
+          status: ctx.midStreamError.status,
           headers: { "Content-Type": "application/json" },
         }
       );
@@ -1735,23 +1655,8 @@ export class CursorExecutor extends BaseExecutor {
     );
   }
 
-  async refreshCredentials(credentials, log) {
-    if (!credentials?.refreshToken) {
-      log?.warn?.(
-        "TOKEN_REFRESH",
-        "Cursor: no refresh token available, re-authentication required"
-      );
-      return null;
-    }
-    const result = await getAccessToken("cursor", credentials, log);
-    if (!result || result.error) {
-      log?.warn?.(
-        "TOKEN_REFRESH",
-        `Cursor: token refresh failed${result?.error ? ` (${result.error})` : ""} — re-authentication required`
-      );
-      return null;
-    }
-    return result;
+  async refreshCredentials() {
+    return null;
   }
 }
 

open-sse/executors/cursor/cursorErrors.ts

@@ -1,269 +0,0 @@
-/**
- * Classify Cursor transport / Connect / gRPC error text into actionable categories.
- * Modeled on OpenCodex `adapters/cursor/cursor-errors.ts` (safe messages + quota vs size).
- */
-
-const ABSOLUTE_PATH_PATTERN =
-  /(?:\/Users\/[^ "';,]+|\/home\/[^ "';,]+|[A-Za-z]:\\Users\\[^ "';,]+)/g;
-const CURSOR_CREDENTIAL_PATTERN =
-  /\b(authorization|auth[_-]?token|cursor[_-]?token|bearer)=([^&\s"',;]+)/gi;
-
-const QUOTA_RATE_CUES = [
-  "too many requests",
-  "quota",
-  "rate limit",
-  "rate-limit",
-  "throttl",
-  "out of usage",
-  "increase limits",
-  "actionrequired",
-];
-const REQUEST_TOO_LARGE_PATTERNS: (string | RegExp)[] = [
-  "tool catalog too large",
-  "tool registration too large",
-  "too many tools",
-  "message too large",
-  "payload too large",
-  "request too large",
-  /request exceeds .*size/,
-  /request (?:body|size) exceeds .*(?:size|limit)/,
-  "maximum allowed size",
-];
-
-export type CursorErrorKind =
-  "rate_limit" | "auth" | "invalid" | "overload" | "timeout" | "connection" | "upstream";
-
-export type ClassifiedCursorError = {
-  kind: CursorErrorKind;
-  /** HTTP status to surface to OmniRoute clients. */
-  status: number;
-  /** OpenAI-style error.type */
-  type: string;
-  /** Secret-safe user-facing message with category prefix. */
-  message: string;
-};
-
-function sanitize(value: string): string {
-  return value
-    .replace(CURSOR_CREDENTIAL_PATTERN, "$1=[REDACTED]")
-    .replace(ABSOLUTE_PATH_PATTERN, "[REDACTED_PATH]")
-    .replace(/eyJ[A-Za-z0-9_-]{10,}\.[A-Za-z0-9_-]+\.[A-Za-z0-9_-]+/g, "[REDACTED_JWT]");
-}
-
-export function isCursorRequestTooLargeDetail(lowerMessage: string): boolean {
-  if (QUOTA_RATE_CUES.some((cue) => lowerMessage.includes(cue))) return false;
-  return REQUEST_TOO_LARGE_PATTERNS.some((pattern) =>
-    typeof pattern === "string" ? lowerMessage.includes(pattern) : pattern.test(lowerMessage)
-  );
-}
-
-function errorMessage(value: unknown): string {
-  if (value instanceof Error) return value.message;
-  if (typeof value === "string") return value;
-  return String(value ?? "");
-}
-
-function errorCode(value: unknown): string {
-  if (typeof value !== "object" || !value || !("code" in value)) return "";
-  const code = (value as { code?: unknown }).code;
-  return code === undefined || code === null ? "" : String(code);
-}
-
-/**
- * True when Cursor intentionally cancelled the HTTP/2 stream after a client-tool
- * suspend (OpenCodex `isCursorBenignCancelError`). Not an upstream failure.
- */
-export function isCursorBenignCancelError(value: unknown): boolean {
-  const message = errorMessage(value).toLowerCase();
-  const code = errorCode(value).toUpperCase();
-  if (code === "NGHTTP2_CANCEL") return true;
-  if (message.includes("nghttp2_cancel")) return true;
-  if (message.includes("cursor stream suspended")) return true;
-  return false;
-}
-
-export function classifyCursorErrorKind(rawMessage: string): CursorErrorKind {
-  const lower = rawMessage.toLowerCase();
-
-  if (lower.includes("resource_exhausted") || lower.includes("resource exhausted")) {
-    return isCursorRequestTooLargeDetail(lower) ? "invalid" : "rate_limit";
-  }
-  if (QUOTA_RATE_CUES.some((cue) => lower.includes(cue))) return "rate_limit";
-
-  // Live Cursor out-of-usage for premium models often surfaces as:
-  //   not_found: AI Model Not Found (reset after 109h …)
-  // OmniRoute may also append "(reset after …)" after classification; treat the
-  // Cursor-specific "AI Model Not Found" cue as rate/quota either way.
-  if (
-    lower.includes("ai model not found") ||
-    (lower.includes("reset after") && lower.includes("model not found"))
-  ) {
-    return "rate_limit";
-  }
-
-  if (
-    lower.includes("unauthenticated") ||
-    lower.includes("unauthorized") ||
-    lower.includes("permission_denied") ||
-    lower.includes("permission denied") ||
-    lower.includes("forbidden") ||
-    lower.includes("invalid token") ||
-    lower.includes("expired token") ||
-    lower.includes("authentication") ||
-    lower.includes("access denied")
-  ) {
-    return "auth";
-  }
-
-  if (
-    lower.includes("unavailable") ||
-    lower.includes("overloaded") ||
-    lower.includes("temporarily") ||
-    lower.includes("server is busy")
-  ) {
-    return "overload";
-  }
-
-  if (
-    lower.includes("invalid") ||
-    lower.includes("not found") ||
-    lower.includes("unsupported") ||
-    lower.includes("malformed") ||
-    lower.includes("unimplemented")
-  ) {
-    return "invalid";
-  }
-
-  if (
-    lower.includes("timed out") ||
-    lower.includes("timeout") ||
-    lower.includes("etimedout") ||
-    lower.includes("deadline")
-  ) {
-    return "timeout";
-  }
-
-  if (
-    lower.includes("econnreset") ||
-    lower.includes("econnrefused") ||
-    lower.includes("goaway") ||
-    lower.includes("nghttp2") ||
-    lower.includes("socket hang up") ||
-    lower.includes("connection reset")
-  ) {
-    return "connection";
-  }
-
-  return "upstream";
-}
-
-function kindToStatus(kind: CursorErrorKind): number {
-  switch (kind) {
-    case "rate_limit":
-      return 429;
-    case "auth":
-      return 401;
-    case "invalid":
-      return 400;
-    case "overload":
-    case "timeout":
-    case "connection":
-    case "upstream":
-    default:
-      return 502;
-  }
-}
-
-function kindToType(kind: CursorErrorKind): string {
-  switch (kind) {
-    case "rate_limit":
-      return "rate_limit_error";
-    case "auth":
-      return "authentication_error";
-    case "invalid":
-      return "invalid_request_error";
-    default:
-      return "api_error";
-  }
-}
-
-function kindPrefix(kind: CursorErrorKind): string {
-  switch (kind) {
-    case "rate_limit":
-      return "Cursor rate limit / usage exceeded";
-    case "auth":
-      return "Cursor authentication failed";
-    case "invalid":
-      return "Cursor invalid request";
-    case "overload":
-      return "Cursor server overloaded";
-    case "timeout":
-      return "Cursor request timed out";
-    case "connection":
-      return "Cursor connection failed";
-    default:
-      return "Cursor upstream error";
-  }
-}
-
-/** Produce a classified, secret-safe Cursor error for HTTP / SSE responses. */
-export function classifyCursorError(rawMessage: string): ClassifiedCursorError {
-  const kind = classifyCursorErrorKind(rawMessage);
-  const detail = sanitize(rawMessage)
-    .replace(/resource[_ ]exhausted/gi, "resource limit exceeded")
-    .slice(0, 500);
-  const prefix = kindPrefix(kind);
-  const message = detail.startsWith(prefix) ? detail : detail ? `${prefix}: ${detail}` : prefix;
-  return {
-    kind,
-    status: kindToStatus(kind),
-    type: kindToType(kind),
-    message,
-  };
-}
-
-export const CURSOR_EMPTY_TURN_MESSAGE =
-  'Cursor returned an empty turn (often usage/quota exhausted). Try model "auto", or check Usage → Provider Limits / raise Cursor limits.';
-
-/**
- * Resolve the error to emit when a Cursor turn ends with no assistant text/tool_calls.
- * Prefer classifying an upstream JSON/error message; otherwise use the empty-turn hint.
- * When `quotaExhaustedHint` is true (fresh Provider Limits cache), force 429.
- */
-export function resolveCursorEmptyTurnError(options: {
-  upstreamMessage?: string | null;
-  quotaExhaustedHint?: boolean;
-}): ClassifiedCursorError {
-  const upstream = options.upstreamMessage?.trim();
-  if (upstream) {
-    const classified = classifyCursorError(upstream);
-    if (options.quotaExhaustedHint && classified.kind !== "auth") {
-      return {
-        ...classified,
-        kind: "rate_limit",
-        status: 429,
-        type: "rate_limit_error",
-        message: classified.message.includes("usage")
-          ? classified.message
-          : `${classified.message} (${CURSOR_EMPTY_TURN_MESSAGE})`,
-      };
-    }
-    return classified;
-  }
-
-  if (options.quotaExhaustedHint) {
-    return {
-      kind: "rate_limit",
-      status: 429,
-      type: "rate_limit_error",
-      message: CURSOR_EMPTY_TURN_MESSAGE,
-    };
-  }
-
-  return {
-    kind: "upstream",
-    status: 502,
-    type: "api_error",
-    message: CURSOR_EMPTY_TURN_MESSAGE,
-  };
-}

open-sse/executors/freebuff.ts

@@ -1,6 +1,9 @@
 import { randomInt } from "node:crypto";
 
-import { BaseExecutor, type ExecuteInput } from "./base.ts";
+import {
+  BaseExecutor,
+  type ExecuteInput,
+} from "./base.ts";
 import { PROVIDERS } from "../config/constants.ts";
 
 const MODEL_TO_AGENT: Record<string, string> = {
@@ -26,32 +29,23 @@ function generateClientSessionId(): string {
 
 export class FreebuffExecutor extends BaseExecutor {
   constructor() {
-    super("freebuff", PROVIDERS.freebuff || { format: "openai" });
+    super("freebuff", (PROVIDERS as Record<string, unknown>).freebuff as string || "freebuff");
   }
 
   override async execute(input: ExecuteInput) {
     const { model, body, stream, credentials, signal } = input;
     const token = credentials?.apiKey || credentials?.accessToken || "";
-    const payload =
-      body && typeof body === "object" && !Array.isArray(body)
-        ? (body as Record<string, unknown>)
-        : {};
 
     if (!token) {
       return {
         response: new Response(
-          JSON.stringify({
-            error: { message: "Freebuff Auth Token required", type: "authentication_error" },
-          }),
+          JSON.stringify({ error: { message: "Freebuff Auth Token required", type: "authentication_error" } }),
           { status: 401, headers: { "Content-Type": "application/json" } }
         ),
       };
     }
 
-    const requestedModel =
-      typeof model === "string"
-        ? model.replace(/^freebuff\//, "")
-        : model || "deepseek/deepseek-v4-flash";
+    const requestedModel = typeof model === "string" ? model.replace(/^freebuff\//, "") : (model || "deepseek/deepseek-v4-flash");
     const agentId = MODEL_TO_AGENT[requestedModel] || "base2-free";
 
     const authHeaders = {
@@ -81,12 +75,7 @@ export class FreebuffExecutor extends BaseExecutor {
         const errText = await sessionRes.text();
         return {
           response: new Response(
-            JSON.stringify({
-              error: {
-                message: `Freebuff session failed (${sessionRes.status}): ${errText}`,
-                type: "upstream_error",
-              },
-            }),
+            JSON.stringify({ error: { message: `Freebuff session failed (${sessionRes.status}): ${errText}`, type: "upstream_error" } }),
             { status: sessionRes.status, headers: { "Content-Type": "application/json" } }
           ),
         };
@@ -95,9 +84,7 @@ export class FreebuffExecutor extends BaseExecutor {
       const msg = e instanceof Error ? e.message : String(e);
       return {
         response: new Response(
-          JSON.stringify({
-            error: { message: `Freebuff session network error: ${msg}`, type: "upstream_error" },
-          }),
+          JSON.stringify({ error: { message: `Freebuff session network error: ${msg}`, type: "upstream_error" } }),
           { status: 502, headers: { "Content-Type": "application/json" } }
         ),
       };
@@ -118,18 +105,12 @@ export class FreebuffExecutor extends BaseExecutor {
     } catch {}
 
     // 3. Prepare Chat Payload & Buffy System Prompt
-    const incomingMessages: Array<Record<string, unknown>> = Array.isArray(payload.messages)
-      ? payload.messages.filter(
-          (message): message is Record<string, unknown> =>
-            !!message && typeof message === "object" && !Array.isArray(message)
-        )
-      : [];
-    const firstMessage = incomingMessages[0];
+    const incomingMessages = Array.isArray(body?.messages) ? [...body.messages] : [];
     const hasBuffyPrompt =
       incomingMessages.length > 0 &&
-      firstMessage?.role === "system" &&
-      typeof firstMessage.content === "string" &&
-      firstMessage.content.trim().startsWith("You are Buffy");
+      incomingMessages[0].role === "system" &&
+      typeof incomingMessages[0].content === "string" &&
+      incomingMessages[0].content.trim().startsWith("You are Buffy");
 
     if (!hasBuffyPrompt) {
       incomingMessages.unshift({
@@ -139,14 +120,8 @@ export class FreebuffExecutor extends BaseExecutor {
     }
 
     const clientSessionId = generateClientSessionId();
-    const existingMetadata =
-      payload.codebuff_metadata &&
-      typeof payload.codebuff_metadata === "object" &&
-      !Array.isArray(payload.codebuff_metadata)
-        ? (payload.codebuff_metadata as Record<string, unknown>)
-        : {};
     const upstreamBody = {
-      ...payload,
+      ...(body || {}),
       model: requestedModel,
       messages: incomingMessages,
       stream: stream !== false,
@@ -155,7 +130,7 @@ export class FreebuffExecutor extends BaseExecutor {
         cost_mode: "free",
         client_id: clientSessionId,
         freebuff_instance_id: instanceId,
-        ...existingMetadata,
+        ...((body as Record<string, unknown>)?.codebuff_metadata as Record<string, unknown> || {}),
       },
     };