board #11389

board #11443
# Conflicts: # README.md # docs/diagrams/cli-terminal.svg # docs/diagrams/promise-pillars.svg
2026-08-25 16:42:16 +03:00 · 2026-08-24 23:21:27 -03:00 · 2026-08-24 23:21:17 -03:00 · 2026-08-24 23:20:55 -03:00 · 2026-08-24 23:20:52 -03:00 · 2026-08-24 23:20:49 -03:00
318 changed files with 8971 additions and 2187 deletions
--- a/.gitignore
+++ b/.gitignore
@@ -14,6 +14,7 @@ _tasks/
 .agents/**
 .claude/**
 .gemini/**
+.code-forge/**
 .config/**
 .data/**
 .logs/**
--- a/AGENTS.md
+++ b/AGENTS.md
@@ -46,7 +46,7 @@ Repository map and Reference Documentation sections below.

 ## Project at a Glance

-**OmniRoute** — unified AI proxy/router. One endpoint, 350 LLM providers, auto-fallback.
+**OmniRoute** — unified AI proxy/router. One endpoint, 351 LLM providers, auto-fallback.

 | Layer         | Location                | Purpose                                                                                                                                                                   |
 | ------------- | ----------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -16,6 +16,18 @@

 ---

+## [3.8.51] — TBD
+
+_Living section — cycle opened at the v3.8.50 freeze (parallel-cycle model). Bullets are aggregated from `changelog.d/` fragments at each `/generate-release` phase._
+
+### ✨ New Features
+
+### 🐛 Bug Fixes
+
+### 📝 Maintenance
+
+---
+
 ## [3.8.50] — TBD

 _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._
--- a/Dockerfile.bun
+++ b/Dockerfile.bun
@@ -1,5 +1,5 @@
 # ── Multi-stage Dockerfile for Native Bun Runtime (web-latest-bun) ───────────
-FROM oven/bun:1.3.14-slim AS base
+FROM oven/bun:1.4.0-slim AS base
 WORKDIR /app

 RUN apt-get update \
@@ -50,7 +50,7 @@ ENV NODE_ENV=production
 RUN bun run --quiet build

 # ── Runner Base stage (100% Bun Native Production Runtime) ──────────────────
-FROM oven/bun:1.3.14-slim AS runner-base
+FROM oven/bun:1.4.0-slim AS runner-base

 LABEL org.opencontainers.image.title="omniroute" \
  org.opencontainers.image.description="Unified AI proxy — route any LLM through one endpoint (Bun Native)" \
--- a/README.md
+++ b/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 → 350 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. 350 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 → 351 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. 351 AI providers · 90+ free tiers · ~1.51B free tokens/mo · 19 routing strategies · $0 to start."/>

 </div>

@@ -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 and 350 providers. Automatic fallback keeps routing while another healthy target is available. Six pillars: resilient fallback across 350 providers · up to 95% token savings on eligible workloads · $0 to start with 90+ free tiers and 56 recurring/keyless free-forever providers · 35 CLI/agent integrations through one config · OpenAI, Claude, Gemini and Responses API compatibility at /v1 · production controls including circuit breakers, TLS stealth, MCP 110 tools, A2A, memory, guardrails, evals and 39,000+ static test declarations across 5,100+ tracked test files."/>
+<img src="./docs/diagrams/promise-pillars.svg" width="100%" alt="The Promise — One endpoint and 351 providers. Automatic fallback keeps routing while another healthy target is available. Six pillars: resilient fallback across 351 providers · up to 95% token savings on eligible workloads · $0 to start with 90+ free tiers and 56 recurring/keyless free-forever providers · 35 CLI/agent integrations through one config · OpenAI, Claude, Gemini and Responses API compatibility at /v1 · production controls including circuit breakers, TLS stealth, MCP 110 tools, A2A, memory, guardrails, evals and 39,000+ static test declarations across 5,100+ tracked test files."/>

 <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 — a dated feature snapshot vs 9router, OpenRouter, CLIProxyAPI and LiteLLM across 13 capabilities. OmniRoute: 350 providers, 90+ free tiers 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 and 43 i18n UI locales. OmniRoute is MIT-licensed and self-hostable. Competitor capabilities and counts may change; see the linked methodology."/>
+<img src="./docs/diagrams/comparison-table.svg" width="100%" alt="What sets OmniRoute apart — a dated feature snapshot vs 9router, OpenRouter, CLIProxyAPI and LiteLLM across 13 capabilities. OmniRoute: 351 providers, 90+ free tiers 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 and 43 i18n UI locales. OmniRoute is MIT-licensed and self-hostable. Competitor capabilities and counts may change; see the linked methodology."/>

 <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 **350-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 **351-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">

-## 🌐 350 AI Providers — 154 Catalog-Marked Free
+## 🌐 351 AI Providers — 154 Catalog-Marked Free

 </div>

-> **350 registered providers** across the canonical chat, media, search, local, cloud-agent and system collections, including **154 carrying `hasFree: true` discovery metadata**. The chat model registry covers **268 providers / 2,566 distinct provider-model pairs / 1,312 raw model IDs**; the separate free-budget catalog has **455 per-model rows**, **40 recurring pools** and **56 recurring/keyless free-forever providers**. These are different denominators by design; definitions and pool-deduped calculations live in the [Provider Reference](docs/reference/PROVIDER_REFERENCE.md) and [Free Tiers](docs/reference/FREE_TIERS.md).
+> **351 registered providers** across the canonical chat, media, search, local, cloud-agent and system collections, including **154 carrying `hasFree: true` discovery metadata**. The chat model registry covers **268 providers / 2,566 distinct provider-model pairs / 1,312 raw model IDs**; the separate free-budget catalog has **455 per-model rows**, **40 recurring pools** and **56 recurring/keyless free-forever providers**. These are different denominators by design; definitions and pool-deduped calculations live in the [Provider Reference](docs/reference/PROVIDER_REFERENCE.md) and [Free Tiers](docs/reference/FREE_TIERS.md).

 <div align="center">

--- a/bin/cli/utils/volatileEnvPath.mjs
+++ b/bin/cli/utils/volatileEnvPath.mjs
@@ -0,0 +1,37 @@
+import { sep } from "node:path";
+
+/**
+ * A `.env` inside the installed package directory does not survive an update:
+ * `npm i -g` replaces that directory wholesale, and postinstall recreates the
+ * file from `.env.example`. The CLI announces every env file it loads without
+ * distinguishing the ones that last from the one that doesn't.
+ *
+ * Returns the warning to print, or null when there is nothing worth saying.
+ *
+ * Two conditions, both required, so a development checkout never sees this:
+ *  - the file sits inside the package root, and that root is inside a
+ *    `node_modules` directory — i.e. an installed package, not a checkout,
+ *    where the same path is stable and documented in SETUP_GUIDE.md;
+ *  - the file actually supplied at least one value. First writer wins, so a
+ *    file entirely shadowed by a durable one supplied nothing, and losing it
+ *    costs nothing.
+ *
+ * @param {{ envPath: string, packageRoot: string, durableEnvPath: string, suppliedKeys: boolean }} args
+ * @returns {string | null}
+ */
+export function describeVolatileEnvWarning({ envPath, packageRoot, durableEnvPath, suppliedKeys }) {
+  if (!suppliedKeys) return null;
+  if (envPath === durableEnvPath) return null;
+  if (!isInsideInstalledPackage(packageRoot)) return null;
+  if (!envPath.startsWith(packageRoot + sep)) return null;
+
+  return (
+    `${envPath} lives inside the installed package: updating OmniRoute replaces it. ` +
+    `Move the values you set to ${durableEnvPath}, which updates leave alone.`
+  );
+}
+
+/** True when the path sits under a `node_modules` directory. */
+function isInsideInstalledPackage(dir) {
+  return typeof dir === "string" && dir.split(sep).includes("node_modules");
+}
--- a/bin/omniroute.mjs
+++ b/bin/omniroute.mjs
@@ -29,6 +29,7 @@ import { getDefaultDataDir } from "./cli/data-dir.mjs";
 import { shouldProvisionStorageKey } from "./cli/utils/storageKeyProvision.mjs";
 import { isVersionFastPath } from "./cli/utils/versionFastPath.mjs";
 import { parseEnvValue } from "./cli/utils/parseEnvValue.mjs";
+import { describeVolatileEnvWarning } from "./cli/utils/volatileEnvPath.mjs";

 const __filename = fileURLToPath(import.meta.url);
 const __dirname = dirname(__filename);
@@ -91,9 +92,7 @@ function migrateElectronServerEnv(dataDir) {
    const serverEnvPath = join(dataDir, "server.env");
    if (existsSync(envPath) || !existsSync(serverEnvPath)) return;
    writeFileSync(envPath, readFileSync(serverEnvPath, "utf-8"), "utf-8");
-    console.log(
-      `  \x1b[2m♻ Migrated Electron secrets from ${serverEnvPath} to ${envPath}\x1b[0m`
-    );
+    console.log(`  \x1b[2m♻ Migrated Electron secrets from ${serverEnvPath} to ${envPath}\x1b[0m`);
  } catch {
    // Ignore errors migrating server.env — fall back to normal env loading below.
  }
@@ -164,6 +163,21 @@ function loadEnvFile() {
    const setter = winner ? winner : "the environment";
    console.warn(`  \x1b[33m⚠ ${key} in ${loser} is ignored, ${setter} set it first\x1b[0m`);
  }
+
+  // The package directory is replaced by the next `npm i -g`, so a .env kept
+  // there is silently lost. Say so once, and only when that file actually
+  // supplied something.
+  const durableEnvPath = join(process.env.DATA_DIR || getDefaultDataDir(), ".env");
+  const suppliedKeys = [...keyOrigin.values()].some((origin) => origin === join(ROOT, ".env"));
+  const volatileWarning = describeVolatileEnvWarning({
+    envPath: join(ROOT, ".env"),
+    packageRoot: ROOT,
+    durableEnvPath,
+    suppliedKeys,
+  });
+  if (volatileWarning && loadedEnvPaths.includes(join(ROOT, ".env"))) {
+    console.warn(`  \x1b[33m⚠ ${volatileWarning}\x1b[0m`);
+  }
 }

 loadEnvFile();
@@ -247,16 +261,16 @@ if (shouldProvisionStorageKey(process.argv)) {
  const langEnv = process.env.OMNIROUTE_LANG;
  const chosen = langArg || langEnv;
  if (chosen) {
-    const { setLocale } = await import(
-      pathToFileURL(join(ROOT, "bin", "cli", "i18n.mjs")).href
-    );
+    const { setLocale } = await import(pathToFileURL(join(ROOT, "bin", "cli", "i18n.mjs")).href);
    setLocale(chosen);
  }
 }

 // Register update notifier — checks npm once per 24h, notifies on exit via stderr.
 const _pkg = JSON.parse(readFileSync(join(ROOT, "package.json"), "utf8"));
-const _notifier = updateNotifier ? updateNotifier({ pkg: _pkg, updateCheckInterval: 1000 * 60 * 60 * 24 }) : null;
+const _notifier = updateNotifier
+  ? updateNotifier({ pkg: _pkg, updateCheckInterval: 1000 * 60 * 60 * 24 })
+  : null;
 process.on("exit", () => {
  if (!_notifier || !_notifier.update) return;
  if (process.env.OMNIROUTE_NO_UPDATE_NOTIFIER) return;
@@ -265,7 +279,15 @@ process.on("exit", () => {
  const outputIdx = process.argv.indexOf("--output");
  const outputVal = outputIdx >= 0 ? process.argv[outputIdx + 1] : null;
  if (outputVal === "json" || outputVal === "jsonl" || outputVal === "csv") return;
-  if (process.argv.some((a) => a.startsWith("--output=json") || a.startsWith("--output=jsonl") || a.startsWith("--output=csv"))) return;
+  if (
+    process.argv.some(
+      (a) =>
+        a.startsWith("--output=json") ||
+        a.startsWith("--output=jsonl") ||
+        a.startsWith("--output=csv")
+    )
+  )
+    return;
  if (_notifier.update) {
    _notifier.notify({
      defer: false,
--- a/changelog.d/features/11340-web-session-contract.md
+++ b/changelog.d/features/11340-web-session-contract.md
@@ -0,0 +1 @@
+- **feat(providers):** publish a management-authenticated versioned web-session credential contract from OmniRoute's canonical browser credential metadata ([#11340](https://github.com/diegosouzapw/OmniRoute/pull/11340)) — thanks @Zartharas
--- a/changelog.d/features/11370-xquik-search-provider.md
+++ b/changelog.d/features/11370-xquik-search-provider.md
@@ -0,0 +1 @@
+- **feat(search):** Add Xquik X search with typed results, credential validation, REST routing, and MCP selection ([#11370](https://github.com/diegosouzapw/OmniRoute/pull/11370)) — thanks @kriptoburak
--- a/changelog.d/features/11389-exclusive-managed-session-dashboard.md
+++ b/changelog.d/features/11389-exclusive-managed-session-dashboard.md
@@ -0,0 +1 @@
+- **feat(dashboard):** surface durable exclusive managed leases in the existing Sessions view, keeping leased clients visible across idle gaps while marking connections with in-flight work as active ([#11389](https://github.com/diegosouzapw/OmniRoute/pull/11389)) — thanks @KaspaPulse
--- a/changelog.d/fixes/11388-live-ws-handshake-port.md
+++ b/changelog.d/fixes/11388-live-ws-handshake-port.md
@@ -0,0 +1 @@
+- **Live dashboard:** honour the WebSocket port reported by `/api/v1/ws?handshake=1` instead of the port compiled into the bundle, so a `LIVE_WS_PORT` override reaches prebuilt Docker/npm images and Combo Studio Live connects behind a reverse proxy ([#11331](https://github.com/diegosouzapw/OmniRoute/issues/11331)).
--- a/changelog.d/fixes/11435-radar-feed-cache-generated-at.md
+++ b/changelog.d/fixes/11435-radar-feed-cache-generated-at.md
@@ -0,0 +1 @@
+- **fix(radar):** the catalog feed cache now keeps `generatedAt`, the date the feed's data was built, next to `fetchedAt`, the date this install downloaded it (#11435). The feed schema requires that date and the sync path validates it, but the cache dropped it — so a feed fetched minutes ago and one carrying weeks-old figures looked identical to everything downstream, including the dashboard's "Last fetched" line. `getRadarCatalog().meta` and `GET /api/radar/status` now report both dates, the latter as its own field rather than folded into `version` — and omitted entirely for the offers and intel caches, which keep no build date, where a `null` would read as "unknown" rather than "never stored". The dashboard still shows only the fetch time; surfacing the build date there needs a new translated label and is left to a follow-up. Rows cached before migration 163 read back as `null`: unknown stays unknown instead of borrowing the fetch time. The referrals cache has persisted the same date since migration 142.
--- a/changelog.d/fixes/11436-postinstall-stop-prefilling-server-secrets.md
+++ b/changelog.d/fixes/11436-postinstall-stop-prefilling-server-secrets.md
@@ -0,0 +1 @@
+- **fix(cli):** postinstall no longer fills `JWT_SECRET` and `API_KEY_SECRET` in the installed package's `.env` (#11436). `.env.example` ships both blank on purpose: the server restores them from its durable store, or generates and persists them there, in `ensureSecrets()`. Pre-filling them defeated that — the file lives inside the package directory, so `npm i -g` replaced it and postinstall wrote _different_ values, while `ensureSecrets()` (which only acts on an empty variable) never got to restore the real ones. Both secrets rotated silently on every update, invalidating dashboard sessions and API-key CRCs. `STORAGE_ENCRYPTION_KEY` left the same list for the same reason in #1622; its comment pointed at a function that no longer exists and now names the real provisioning path.
--- a/changelog.d/fixes/11437-cli-warn-volatile-package-env.md
+++ b/changelog.d/fixes/11437-cli-warn-volatile-package-env.md
@@ -0,0 +1 @@
+- **fix(cli):** the CLI now says when a loaded `.env` lives inside the installed package directory (#11437). It already announces every env file it reads, without distinguishing the ones that survive an update from the one that does not: `npm i -g` replaces the package directory wholesale, so values set there are gone at the next update, silently. The warning names the durable path to move them to, and fires only when that file actually supplied a value — a file entirely shadowed by a durable one supplied nothing. A development checkout stays silent: there the same path is stable and documented in `SETUP_GUIDE.md`.
--- a/changelog.d/fixes/11441-discontinued-free-models.md
+++ b/changelog.d/fixes/11441-discontinued-free-models.md
@@ -0,0 +1 @@
+- **fix(free-models):** the shared `isFreeModel()` predicate no longer reports catalog entries marked `freeType: "discontinued"` as free, so `hidePaidModels` can't route to Pollinations' seven premium models that now require a paid key ([#11441](https://github.com/diegosouzapw/OmniRoute/pull/11441))
--- a/changelog.d/fixes/7592-windows-packaged-smoke.md
+++ b/changelog.d/fixes/7592-windows-packaged-smoke.md
@@ -0,0 +1 @@
+- **fix(electron):** the packaged Windows desktop build now passes the #7592 cold-restart smoke end to end. Five defects were found and fixed on the way: (1) optional-pack staging failed on any machine whose `tar` is GNU tar — it reads the drive letter in an absolute `-f C:\...` archive path as a remote rsh host (`Cannot connect to C:`), so staging now passes a bare filename with `cwd` at the tarball directory and surfaces tar stderr on failure; (2) the Electron `files` allowlist was missing `lib/loginHeaderCapture.js`, so the packaged main process crashed at startup with `Cannot find module './lib/loginHeaderCapture'`; (3) electron-builder ≥26 injects an `!**/node_modules/**` ignore into every extraResources pattern list that no positive filter can override, which silently dropped the staged runtime `node_modules` (including the better-sqlite3 N-API prebuild) from `resources/app` — a fresh v3.8.50 desktop build would have shipped with no native SQLite driver and reproduced the #7592 sql.js fallback on every machine; an `afterPack` hook now restores the staged `node_modules` after packing; (4) the packaged-app smoke harness redirected `USERPROFILE` into its temp DATA_DIR, but Electron resolves the Roaming profile from `%USERPROFILE%\AppData\Roaming\<name>` (USERPROFILE takes precedence over the APPDATA env var) and the path service throws instead of creating it, so `requestSingleInstanceLock()` returned false and the app exited(0) silently before `app.whenReady()` — the harness now pre-creates the derived tree, and `ensureSmokeEnvDirs` is exported and unit-tested; (5) the #7592 driver assertion parsed a `[DB] Driver: ...` line that the server's primary DB path never printed (only the unused `openDatabaseAsync()` did) — `getDbInstance()` now emits the same line on open so the guard can actually assert the native driver. Also: the smoke env-allowlist unit test hardcoded POSIX paths and could only pass on Linux/macOS; expectations are now host-agnostic, with new regression tests for the USERPROFILE-derived tree and `tarPack` under absolute Windows-style paths
--- a/changelog.d/fixes/memory-embedding-quick-select-providers.md
+++ b/changelog.d/fixes/memory-embedding-quick-select-providers.md
@@ -0,0 +1 @@
+- **fix(memory):** Embedding Model Quick select, Embedding Source remote dropdown, and Rerank selector now list every configured provider with embedding/rerank support instead of only chat-catalog text matches plus OpenRouter live discovery; a generic OpenAI-compatible `/embeddings` + Cohere-compatible `/rerank` runtime fallback resolves any configured chat provider's embedding/rerank endpoint, so unlisted providers no longer fail with "Unknown embedding provider"; both memory selectors gained a free-text model override
--- a/changelog.d/maintenance/kimi-health-check-jitter-determinism.md
+++ b/changelog.d/maintenance/kimi-health-check-jitter-determinism.md
@@ -0,0 +1 @@
+- **test(kimi):** the Kimi background health sweep no longer draws its refresh window inside the assertion. `checkKimiWebConnectionIfNeeded` spreads the refresh over `[60, 240)` seconds before expiry so a fleet of connections does not stampede the token endpoint, and the test used a token expiring in 90 seconds and asserted that a refresh happened — which is true only when the draw lands at 90 or above, i.e. 150 of the 180 possible values. Measured: the test fails 1 run in 6 (16.7% by construction; 4 of 20 local runs), and it is what the Node 26 nightly hit and reported as a Node-compat break (#11361). The spread is now `defaultKimiRefreshJitterSec()` and the window is injectable as `jitterSecFn`, so the test decides it instead of rolling for it; production behaviour is unchanged. Cases were added for a token outside the window and for the default spread's range.
--- a/config/quality/dependency-allowlist.json
+++ b/config/quality/dependency-allowlist.json
@@ -12,6 +12,7 @@
    "@dnd-kit/core",
    "@dnd-kit/sortable",
    "@dnd-kit/utilities",
+    "@eslint/compat",
    "@huggingface/transformers",
    "@lobehub/icons",
    "@modelcontextprotocol/sdk",
@@ -60,6 +61,7 @@
    "eslint",
    "eslint-config-next",
    "eslint-plugin-sonarjs",
+    "espree",
    "express",
    "fast-check",
    "fetch-socks",
--- a/config/quality/eslint-suppressions.json
+++ b/config/quality/eslint-suppressions.json
@@ -2372,16 +2372,6 @@
      "count": 2
    }
  },
-  "src/lib/guardrails/videoBridgeContactSheet.ts": {
-    "@typescript-eslint/no-unused-vars": {
-      "count": 1
-    }
-  },
-  "src/lib/guardrails/videoBridgeRuntime.ts": {
-    "@typescript-eslint/no-unused-vars": {
-      "count": 1
-    }
-  },
  "src/lib/guardrails/visionBridgeHelpers.ts": {
    "@typescript-eslint/no-unused-vars": {
      "count": 1
@@ -2422,11 +2412,6 @@
      "count": 1
    }
  },
-  "src/lib/memory/embedding/index.ts": {
-    "no-restricted-imports": {
-      "count": 1
-    }
-  },
  "src/lib/memory/genericBackend.ts": {
    "@typescript-eslint/no-unused-vars": {
      "count": 1
--- a/docs/changelog/fragments/7778.md
+++ b/docs/changelog/fragments/7778.md
@@ -0,0 +1 @@
+feat(resilience): atomically enforce cumulative global, provider, and account concurrency limits
--- a/docs/design/EXTERNAL-DB-BACKEND.md
+++ b/docs/design/EXTERNAL-DB-BACKEND.md
@@ -0,0 +1,98 @@
+# Design: Pluggable External Durable-State DB Backend (PostgreSQL / MySQL)
+
+Status: PROPOSAL · Discussion issue: [#8075](https://github.com/diegosouzapw/OmniRoute/issues/8075) · Author: @oyi77
+
+Grounded in the tree at `release/v3.8.51` (`3192eb88d`). Every number below was measured on that tree, not estimated.
+
+---
+
+## 0. Why this document exists
+
+#8075 asks five questions (backends & order, abstraction contract, what stays SQLite-only, config surface, migration path). This document answers them with a census of how deeply the current data layer is coupled to SQLite, and proposes a repository-contract seam that lets external backends be adopted per domain instead of via a big-bang driver swap.
+
+## 1. Measured coupling census (`release/v3.8.51`)
+
+| Surface | Count | Implication for external backends |
+|---|---|---|
+| `src/lib/db/*.ts` modules calling `.prepare()` / `.transaction()` | **126 files** | The synchronous SQLite call shape is the de-facto data API; every module is a translation candidate |
+| `.pragma()` call sites | **36** | No equivalent in PG/MySQL — each needs an audit (many are performance tuning that becomes server config) |
+| SQLite migrations on disk | **159** | A second dialect needs its own migration lineage, not a translator |
+| `sqlite-vec` / `vec0` referencing files | **9** | Vector search must move to an external store (Qdrant proposed in #8075) |
+| FTS5 referencing files | **8** | Maps to Postgres `tsvector` / MySQL `FULLTEXT` — dialect work |
+| Existing driver adapters | **4** (`better-sqlite3`, `node:sqlite`, `bun:sqlite`, `sql.js`) behind `SqliteAdapter` (`src/lib/db/adapters/types.ts`) | Proves a seam exists at the DRIVER level — but all four are SQLite; the seam OmniRoute actually needs is one level up |
+
+The decisive fact: **the adapter interface is synchronous** (`prepare().run/get/all`, sync closure transactions). PostgreSQL and MySQL drivers are inherently async. A faithful external backend behind `SqliteAdapter` is therefore impossible without faking sync over async — which is exactly the trap #8037/#8073 already flagged ("not a drop-in ORM/driver swap"). The contract must live ABOVE the adapter layer.
+
+## 2. Proposed contract: durable-state repositories, not a driver swap
+
+Introduce a `DurableStateStore` port with per-domain repositories, defined once and implemented per dialect:
+
+```ts
+// src/lib/db/ports/ — dialect-agnostic, async, transactional by unit-of-work
+interface UnitOfWork {
+  connections: ConnectionRepository;   // provider connections + credentials
+  apiKeys: ApiKeyRepository;           // keys, groups, usage-limit fields
+  combos: ComboRepository;             // combo defs + routing policies
+  quotaState: QuotaStateRepository;    // quota/account state, cooldowns
+  sessionAffinity: AffinityRepository; // sticky routing state
+  audit: AuditRepository;              // config audit log
+}
+interface DurableStateStore {
+  readonly driver: "sqlite" | "postgres" | "mysql";
+  withUnitOfWork<T>(fn: (uow: UnitOfWork) => Promise<T>): Promise<T>;
+  healthCheck(): Promise<{ ok: boolean; latencyMs: number }>;
+}
+```
+
+Deliberate exclusions from v1 (stay SQLite-local, matching #8075 §3): WAL/VACUUM/PRAGMA lifecycle, file backup/import/export, `sqlite-vec` vector storage (external backends delegate vectors to Qdrant), FTS (dialect-native fulltext later).
+
+### What makes each repository shippable
+
+The single-writer pattern OmniRoute already uses internally (targeted raw-SQL stat bumps like `touchConnectionLastUsed`, single-writer caches) maps cleanly onto `UnitOfWork`. Repositories are adopted **per domain**: a deployment can run `postgres` for connections+keys while hot-path ephemeral state stays local — because the port is injected at the repository boundary, not under 126 modules.
+
+## 3. Sequencing: PostgreSQL first, MySQL second
+
+1. **Postgres-first** (`pg` + `pg-pool`): richer native JSONB (several modules persist JSON blobs), `tsvector`, `INSERT ... ON CONFLICT` semantics closest to `INSERT OR REPLACE` usage.
+2. **MySQL 8+ after**, gated by a shared **dialect-conformance suite**: the same behavioral test pack runs against both implementations (schema bootstrap, UoW rollback, credential round-trip incl. encryption-at-rest fields, pagination/ordering contracts). A backend is "supported" only when the suite is green.
+
+Rationale: one conformance suite prevents the MySQL implementation from drifting into a shim that passes smoke tests but corrupts ordering/collation edge cases.
+
+## 4. Config surface
+
+```
+DATABASE_DRIVER=sqlite            # sqlite (default) | postgres | mysql
+DATABASE_URL=postgres://...       # required when driver != sqlite
+DATABASE_POOL_MAX=10
+DATABASE_TLS_REJECT_UNAUTHORIZED=1
+DATABASE_MIGRATIONS_TABLE=_omniroute_migrations
+```
+
+- Default stays `sqlite` — zero-config npm/Electron/Termux behavior is non-negotiable (#8075 §6).
+- Health check surfaces in the existing `/api/monitoring/health` payload next to `inflightRequests`.
+- Migrations: per-dialect lineage directories (`migrations-postgres/`, `migrations-mysql/`) with their own runner sharing the safety checks (mass-migration abort, pre-migration backup → pg_dump/mysqldump equivalent) already proven in `migrationRunner.ts`.
+
+## 5. Migration path (one-way export tool)
+
+`omniroute db export --to postgres --dsn ...`:
+1. Snapshot `storage.sqlite` (reuse `createPreMigrationBackup`).
+2. Replay schema from the target dialect's lineage to head.
+3. Copy tables row-by-row through the new repositories (not raw SQL translation), preserving IDs; re-encrypt nothing (credential ciphertexts are dialect-neutral strings today).
+4. Verify with row-count + checksum comparison per table; write a receipt file.
+5. Refuse to continue on any mismatch (fail-closed).
+
+## 6. Phased delivery plan
+
+| Phase | Deliverable | Risk gate |
+|---|---|---|
+| P1 | `ports/` contract + SQLite implementation of `ConnectionRepository` + conformance-suite skeleton running against SQLite itself | Suite green on the reference driver |
+| P2 | Postgres implementation of the same repo + suite green on PG | Suite green on PG |
+| P3 | Remaining domains (apiKeys, combos, quotaState, affinity, audit) on PG | Full-suite parity vs SQLite run |
+| P4 | MySQL via conformance suite | Suite green on MySQL |
+| P5 | Export tool + docs | Round-trip receipt on a 1GB-scale fixture |
+
+P1–P2 alone deliver value: a clustered deployment can share connection/key state while everything else stays local.
+
+## 7. Explicitly out of scope
+
+- Translating the remaining ~120 SQLite-shaped modules verbatim ("just make prepare() hit Postgres") — rejected: it fakes sync over async and preserves dialect bugs forever.
+- Replacing `sqlite-vec` with pgvector — #8075 names Qdrant; keeping vector search out-of-process also keeps the lean proxy core lean (4.0 modular direction).
--- a/docs/diagrams/cli-terminal.svg
+++ b/docs/diagrams/cli-terminal.svg
@@ -1,4 +1,4 @@
-<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 (350 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 85 top-level commands: 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 (351 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 85 top-level commands: 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>
 <rect width="1200" height="350" fill="#0d1117"/>
@@ -6,7 +6,7 @@
 <path d="M 0 34 L 1200 34" stroke="#ffffff" stroke-opacity="0.08" stroke-width="1"/>
 <circle cx="24" cy="17" r="6" fill="#ff5f56"/><circle cx="46" cy="17" r="6" fill="#ffbd2e"/><circle cx="68" cy="17" r="6" fill="#27c93f"/>
 <text x="600" y="22" text-anchor="middle" font-family="Consolas, 'Courier New', monospace" font-size="13" fill="#71717a">omniroute &#8212; 85 top-level commands</text>
-<g font-family="Consolas, 'Courier New', monospace" font-size="17"><animate attributeName="opacity" values="1;0;0" keyTimes="0;0.006;1" dur="18s" repeatCount="indefinite"/><text x="64" y="66" fill="#F7F6FC">omniroute providers list</text><text x="40" y="100" font-weight="700" fill="#38bdf8">OmniRoute Providers</text><text x="40" y="128" fill="#a1a1aa">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">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">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">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">&#8230; 346 more providers</text></g><g opacity="1" font-family="Consolas, 'Courier New', monospace" font-size="17">
+<g font-family="Consolas, 'Courier New', monospace" font-size="17"><animate attributeName="opacity" values="1;0;0" keyTimes="0;0.006;1" dur="18s" repeatCount="indefinite"/><text x="64" y="66" fill="#F7F6FC">omniroute providers list</text><text x="40" y="100" font-weight="700" fill="#38bdf8">OmniRoute Providers</text><text x="40" y="128" fill="#a1a1aa">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">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">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">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">&#8230; 347 more providers</text></g><g opacity="1" font-family="Consolas, 'Courier New', monospace" font-size="17">
 <animate attributeName="opacity" values="1;1;0;0" keyTimes="0;0.315;0.33;1" dur="18s" repeatCount="indefinite"/>
 <text x="40" y="66" fill="#22c55e">$</text>
 <g clip-path="url(#tw0)"><text x="64" y="66" fill="#F7F6FC">omniroute providers list</text></g>
@@ -14,7 +14,7 @@
  <animate attributeName="x" calcMode="discrete" values="64;95;125;156;186;217;248;278;309;309" keyTimes="0.000;0.012;0.018;0.024;0.030;0.036;0.042;0.048;0.054;1" dur="18s" repeatCount="indefinite"/>
  <animate attributeName="opacity" values="0;0;1;0.2;1;0.2;1;0;0" keyTimes="0;0.011;0.012;0.022;0.032;0.042;0.052;0.074;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;0.045;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; 346 more providers</text>
+<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; 347 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"/>
 <text x="40" y="66" fill="#22c55e">$</text>
--- a/docs/diagrams/comparison-table.svg
+++ b/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: 350 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: 351 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.">
  <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>
--- a/docs/diagrams/promise-pillars.svg
+++ b/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 and 350 providers. Six pillars. Resilient fallback: automatic routing continues while another healthy target is available. Save up to 95 percent of eligible tokens: RTK plus Caveman stacked compression averages about 89 percent on tool-heavy sessions. Zero dollars to start: 90+ providers with a free tier and 56 recurring or keyless free-forever providers. Every tool works: 35 CLI and agent integration records, including Claude Code, Codex, Cursor, Cline, Copilot and Antigravity, through one config. One endpoint: OpenAI, Claude, Gemini and Responses API translation at /v1. Production controls: circuit breakers, TLS stealth, MCP with 110 tools, A2A, memory, guardrails, evals, and 39,000+ static test declarations across 5,100+ tracked test files.">
+<svg viewBox="0 0 1200 540" xmlns="http://www.w3.org/2000/svg" role="img" aria-label="The OmniRoute promise: one endpoint and 351 providers. Six pillars. Resilient fallback: automatic routing continues while another healthy target is available. Save up to 95 percent of eligible tokens: RTK plus Caveman stacked compression averages about 89 percent on tool-heavy sessions. Zero dollars to start: 90+ providers with a free tier and 56 recurring or keyless free-forever providers. Every tool works: 35 CLI and agent integration records, including Claude Code, Codex, Cursor, Cline, Copilot and Antigravity, through one config. One endpoint: OpenAI, Claude, Gemini and Responses API translation at /v1. Production controls: circuit breakers, TLS stealth, MCP with 110 tools, A2A, memory, guardrails, evals, and 39,000+ static test declarations across 5,100+ tracked test files.">
  <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">350 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">351 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 350 providers in</text>
+      <text x="66" y="204" font-size="13.5" fill="#a1a1aa">Auto-fallback across 351 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 while a healthy target remains.</text>
    </g>
--- a/docs/diagrams/readme-hero.svg
+++ b/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 350 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: 350 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 351 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: 351 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">350 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">351 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>
--- a/docs/frameworks/MCP-SERVER.md
+++ b/docs/frameworks/MCP-SERVER.md
@@ -66,22 +66,22 @@ Cursor, Cline, and compatible MCP client setup.

 ## Essential Tools (13) — Phase 1

-| Tool                            | Scopes                | Description                                                   |
-| :------------------------------ | :-------------------- | :------------------------------------------------------------ |
-| `omniroute_get_health`          | `read:health`         | Uptime, memory, circuit breakers, rate limits, cache stats    |
-| `omniroute_list_combos`         | `read:combos`         | All configured combos with strategies (optional metrics)      |
-| `omniroute_get_combo_metrics`   | `read:combos`         | Performance metrics for a specific combo                      |
-| `omniroute_switch_combo`        | `write:combos`        | Activate or deactivate a combo                                |
-| `omniroute_create_combo`        | `write:combos`        | Create a validated combo through the existing combo API       |
-| `omniroute_check_quota`         | `read:quota`          | Quota used/total, percent remaining, reset time, token health |
-| `omniroute_route_request`       | `execute:completions` | Send a chat completion through OmniRoute routing              |
-| `omniroute_cost_report`         | `read:usage`          | Cost report by period (session/day/week/month)                |
-| `omniroute_list_models_catalog` | `read:models`         | Full model catalog with capabilities, status, pricing         |
-| `omniroute_radar_catalog`       | `read:radar`          | Local signed Radar catalog; optional provider/family filters  |
-| `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_fetch`           | `execute:search`      | Fetch web content through the configured fetch providers      |
+| Tool                            | Scopes                | Description                                                                                                                    |
+| :------------------------------ | :-------------------- | :----------------------------------------------------------------------------------------------------------------------------- |
+| `omniroute_get_health`          | `read:health`         | Uptime, memory, circuit breakers, rate limits, cache stats                                                                     |
+| `omniroute_list_combos`         | `read:combos`         | All configured combos with strategies (optional metrics)                                                                       |
+| `omniroute_get_combo_metrics`   | `read:combos`         | Performance metrics for a specific combo                                                                                       |
+| `omniroute_switch_combo`        | `write:combos`        | Activate or deactivate a combo                                                                                                 |
+| `omniroute_create_combo`        | `write:combos`        | Create a validated combo through the existing combo API                                                                        |
+| `omniroute_check_quota`         | `read:quota`          | Quota used/total, percent remaining, reset time, token health                                                                  |
+| `omniroute_route_request`       | `execute:completions` | Send a chat completion through OmniRoute routing                                                                               |
+| `omniroute_cost_report`         | `read:usage`          | Cost report by period (session/day/week/month)                                                                                 |
+| `omniroute_list_models_catalog` | `read:models`         | Full model catalog with capabilities, status, pricing                                                                          |
+| `omniroute_radar_catalog`       | `read:radar`          | Local signed Radar catalog; optional provider/family filters                                                                   |
+| `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 through xAI/SuperGrok, or choose `xquik-search` for Xquik API results. Requires credentials for the selected backend. |
+| `omniroute_web_fetch`           | `execute:search`      | Fetch web content through the configured fetch providers                                                                       |

 ## Advanced Tools (11) — Phase 2

--- a/docs/frameworks/RADAR.md
+++ b/docs/frameworks/RADAR.md
@@ -283,6 +283,32 @@ currently cached version (`compareVersions()`, dotted `YYYY.MM.DD.n` comparison)
 `{ status: "stale" }`. This prevents a compromised or misconfigured feed endpoint from
 rolling a client back to an older, differently-signed payload.

+### Two dates, and why both are kept
+
+A cached feed carries two distinct dates, and confusing them is the whole point of
+keeping both:
+
+| Field         | Comes from           | Answers                             |
+| ------------- | -------------------- | ----------------------------------- |
+| `generatedAt` | the signed feed body | how old the **data** is             |
+| `fetchedAt`   | this install's clock | when this install **downloaded** it |
+
+A feed fetched minutes ago can carry weeks-old figures, so `fetchedAt` alone cannot
+tell an operator whether the overlay is fresher than the baseline it sits on. Both are
+persisted in `radar_feed_cache`, returned by `getRadarCatalog().meta`, and reported
+separately by `GET /api/radar/status`. A row cached before the `generated_at` column
+existed (migration 163) reads back as `null` — unknown stays unknown rather than
+borrowing the fetch time. `radar_referrals_cache` has kept its own `generated_at` since
+migration 142.
+
+The version floor above compares `version`, not either date.
+
+Two gaps remain, both deliberate: the dashboard still shows only `Last fetched`, so reading
+the build date there needs a new label (and its 42 locale entries); and the offers and intel
+caches keep no build date at all, even though their feed schemas carry one — `GET
+/api/radar/status` therefore omits the field for those two rather than reporting a `null`
+that would read as "unknown".
+
 ### Schema validation

 The downloaded bytes are parsed and validated against `RadarFeedSchema`
--- a/docs/i18n/ar/CHANGELOG.md
+++ b/docs/i18n/ar/CHANGELOG.md
@@ -6,6 +6,19 @@

 ## [3.8.31] — 2026-06-20

+## [3.8.51] — TBD
+
+_Living section — cycle opened at the v3.8.50 freeze (parallel-cycle model). Bullets are aggregated from `changelog.d/` fragments at each `/generate-release` phase._
+
+### ✨ New Features
+
+### 🐛 Bug Fixes
+
+### 📝 Maintenance
+
+---
+
+
 ## [3.8.50] — TBD

 _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._
--- a/docs/i18n/ar/llm.txt
+++ b/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 350 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 351 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.

 ## Overview

@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)

 ### Core Proxy
- **350 AI providers** with automatic format translation
+- **351 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
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool

 ## v3.8.x Highlights

- **350-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **351-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)
--- a/docs/i18n/az/CHANGELOG.md
+++ b/docs/i18n/az/CHANGELOG.md
@@ -6,6 +6,19 @@

 ## [3.8.31] — 2026-06-20

+## [3.8.51] — TBD
+
+_Living section — cycle opened at the v3.8.50 freeze (parallel-cycle model). Bullets are aggregated from `changelog.d/` fragments at each `/generate-release` phase._
+
+### ✨ New Features
+
+### 🐛 Bug Fixes
+
+### 📝 Maintenance
+
+---
+
+
 ## [3.8.50] — TBD

 _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._
--- a/docs/i18n/az/llm.txt
+++ b/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 350 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 351 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.

 ## Overview

@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)

 ### Core Proxy
- **350 AI providers** with automatic format translation
+- **351 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
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool

 ## v3.8.x Highlights

- **350-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **351-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)
--- a/docs/i18n/bg/CHANGELOG.md
+++ b/docs/i18n/bg/CHANGELOG.md
@@ -6,6 +6,19 @@

 ## [3.8.31] — 2026-06-20

+## [3.8.51] — TBD
+
+_Living section — cycle opened at the v3.8.50 freeze (parallel-cycle model). Bullets are aggregated from `changelog.d/` fragments at each `/generate-release` phase._
+
+### ✨ New Features
+
+### 🐛 Bug Fixes
+
+### 📝 Maintenance
+
+---
+
+
 ## [3.8.50] — TBD

 _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._
--- a/docs/i18n/bg/llm.txt
+++ b/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 350 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 351 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.

 ## Overview

@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)

 ### Core Proxy
- **350 AI providers** with automatic format translation
+- **351 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
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool

 ## v3.8.x Highlights

- **350-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **351-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)
--- a/docs/i18n/bn/CHANGELOG.md
+++ b/docs/i18n/bn/CHANGELOG.md
@@ -6,6 +6,19 @@

 ## [3.8.31] — 2026-06-20

+## [3.8.51] — TBD
+
+_Living section — cycle opened at the v3.8.50 freeze (parallel-cycle model). Bullets are aggregated from `changelog.d/` fragments at each `/generate-release` phase._
+
+### ✨ New Features
+
+### 🐛 Bug Fixes
+
+### 📝 Maintenance
+
+---
+
+
 ## [3.8.50] — TBD

 _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._
--- a/docs/i18n/bn/llm.txt
+++ b/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 350 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 351 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.

 ## Overview

@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)

 ### Core Proxy
- **350 AI providers** with automatic format translation
+- **351 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
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool

 ## v3.8.x Highlights

- **350-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **351-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)
--- a/docs/i18n/cs/CHANGELOG.md
+++ b/docs/i18n/cs/CHANGELOG.md
@@ -6,6 +6,19 @@

 ## [3.8.31] — 2026-06-20

+## [3.8.51] — TBD
+
+_Living section — cycle opened at the v3.8.50 freeze (parallel-cycle model). Bullets are aggregated from `changelog.d/` fragments at each `/generate-release` phase._
+
+### ✨ New Features
+
+### 🐛 Bug Fixes
+
+### 📝 Maintenance
+
+---
+
+
 ## [3.8.50] — TBD

 _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._
--- a/docs/i18n/cs/llm.txt
+++ b/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 350 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 351 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.

 ## Overview

@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)

 ### Core Proxy
- **350 AI providers** with automatic format translation
+- **351 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
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool

 ## v3.8.x Highlights

- **350-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **351-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)
--- a/docs/i18n/da/CHANGELOG.md
+++ b/docs/i18n/da/CHANGELOG.md
@@ -6,6 +6,19 @@

 ## [3.8.31] — 2026-06-20

+## [3.8.51] — TBD
+
+_Living section — cycle opened at the v3.8.50 freeze (parallel-cycle model). Bullets are aggregated from `changelog.d/` fragments at each `/generate-release` phase._
+
+### ✨ New Features
+
+### 🐛 Bug Fixes
+
+### 📝 Maintenance
+
+---
+
+
 ## [3.8.50] — TBD

 _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._
--- a/docs/i18n/da/llm.txt
+++ b/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 350 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 351 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.

 ## Overview

@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)

 ### Core Proxy
- **350 AI providers** with automatic format translation
+- **351 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
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool

 ## v3.8.x Highlights

- **350-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **351-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)
--- a/docs/i18n/de/CHANGELOG.md
+++ b/docs/i18n/de/CHANGELOG.md
@@ -6,6 +6,19 @@

 ## [3.8.31] — 2026-06-20

+## [3.8.51] — TBD
+
+_Living section — cycle opened at the v3.8.50 freeze (parallel-cycle model). Bullets are aggregated from `changelog.d/` fragments at each `/generate-release` phase._
+
+### ✨ New Features
+
+### 🐛 Bug Fixes
+
+### 📝 Maintenance
+
+---
+
+
 ## [3.8.50] — TBD

 _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._
--- a/docs/i18n/de/llm.txt
+++ b/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 350 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 351 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.

 ## Overview

@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)

 ### Core Proxy
- **350 AI providers** with automatic format translation
+- **351 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
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool

 ## v3.8.x Highlights

- **350-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **351-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)
--- a/docs/i18n/es/CHANGELOG.md
+++ b/docs/i18n/es/CHANGELOG.md
@@ -6,6 +6,19 @@

 ## [3.8.31] — 2026-06-20

+## [3.8.51] — TBD
+
+_Living section — cycle opened at the v3.8.50 freeze (parallel-cycle model). Bullets are aggregated from `changelog.d/` fragments at each `/generate-release` phase._
+
+### ✨ New Features
+
+### 🐛 Bug Fixes
+
+### 📝 Maintenance
+
+---
+
+
 ## [3.8.50] — TBD

 _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._
--- a/docs/i18n/es/llm.txt
+++ b/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 350 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 351 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.

 ## Overview

@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)

 ### Core Proxy
- **350 AI providers** with automatic format translation
+- **351 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
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool

 ## v3.8.x Highlights

- **350-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **351-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)
--- a/docs/i18n/fa/CHANGELOG.md
+++ b/docs/i18n/fa/CHANGELOG.md
@@ -6,6 +6,19 @@

 ## [3.8.31] — 2026-06-20

+## [3.8.51] — TBD
+
+_Living section — cycle opened at the v3.8.50 freeze (parallel-cycle model). Bullets are aggregated from `changelog.d/` fragments at each `/generate-release` phase._
+
+### ✨ New Features
+
+### 🐛 Bug Fixes
+
+### 📝 Maintenance
+
+---
+
+
 ## [3.8.50] — TBD

 _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._
--- a/docs/i18n/fa/llm.txt
+++ b/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 350 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 351 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.

 ## Overview

@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)

 ### Core Proxy
- **350 AI providers** with automatic format translation
+- **351 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
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool

 ## v3.8.x Highlights

- **350-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **351-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)
--- a/docs/i18n/fi/CHANGELOG.md
+++ b/docs/i18n/fi/CHANGELOG.md
@@ -6,6 +6,19 @@

 ## [3.8.31] — 2026-06-20

+## [3.8.51] — TBD
+
+_Living section — cycle opened at the v3.8.50 freeze (parallel-cycle model). Bullets are aggregated from `changelog.d/` fragments at each `/generate-release` phase._
+
+### ✨ New Features
+
+### 🐛 Bug Fixes
+
+### 📝 Maintenance
+
+---
+
+
 ## [3.8.50] — TBD

 _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._
--- a/docs/i18n/fi/llm.txt
+++ b/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 350 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 351 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.

 ## Overview

@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)

 ### Core Proxy
- **350 AI providers** with automatic format translation
+- **351 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
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool

 ## v3.8.x Highlights

- **350-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **351-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)
--- a/docs/i18n/fr/CHANGELOG.md
+++ b/docs/i18n/fr/CHANGELOG.md
@@ -6,6 +6,19 @@

 ## [3.8.31] — 2026-06-20

+## [3.8.51] — TBD
+
+_Living section — cycle opened at the v3.8.50 freeze (parallel-cycle model). Bullets are aggregated from `changelog.d/` fragments at each `/generate-release` phase._
+
+### ✨ New Features
+
+### 🐛 Bug Fixes
+
+### 📝 Maintenance
+
+---
+
+
 ## [3.8.50] — TBD

 _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._
--- a/docs/i18n/fr/llm.txt
+++ b/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 350 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 351 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.

 ## Overview

@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)

 ### Core Proxy
- **350 AI providers** with automatic format translation
+- **351 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
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool

 ## v3.8.x Highlights

- **350-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **351-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)
--- a/docs/i18n/gu/CHANGELOG.md
+++ b/docs/i18n/gu/CHANGELOG.md
@@ -6,6 +6,19 @@

 ## [3.8.31] — 2026-06-20

+## [3.8.51] — TBD
+
+_Living section — cycle opened at the v3.8.50 freeze (parallel-cycle model). Bullets are aggregated from `changelog.d/` fragments at each `/generate-release` phase._
+
+### ✨ New Features
+
+### 🐛 Bug Fixes
+
+### 📝 Maintenance
+
+---
+
+
 ## [3.8.50] — TBD

 _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._
--- a/docs/i18n/gu/llm.txt
+++ b/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 350 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 351 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.

 ## Overview

@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)

 ### Core Proxy
- **350 AI providers** with automatic format translation
+- **351 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
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool

 ## v3.8.x Highlights

- **350-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **351-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)
--- a/docs/i18n/he/CHANGELOG.md
+++ b/docs/i18n/he/CHANGELOG.md
@@ -6,6 +6,19 @@

 ## [3.8.31] — 2026-06-20

+## [3.8.51] — TBD
+
+_Living section — cycle opened at the v3.8.50 freeze (parallel-cycle model). Bullets are aggregated from `changelog.d/` fragments at each `/generate-release` phase._
+
+### ✨ New Features
+
+### 🐛 Bug Fixes
+
+### 📝 Maintenance
+
+---
+
+
 ## [3.8.50] — TBD

 _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._
--- a/docs/i18n/he/llm.txt
+++ b/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 350 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 351 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.

 ## Overview

@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)

 ### Core Proxy
- **350 AI providers** with automatic format translation
+- **351 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
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool

 ## v3.8.x Highlights

- **350-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **351-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)
--- a/docs/i18n/hi/CHANGELOG.md
+++ b/docs/i18n/hi/CHANGELOG.md
@@ -6,6 +6,19 @@

 ## [3.8.31] — 2026-06-20

+## [3.8.51] — TBD
+
+_Living section — cycle opened at the v3.8.50 freeze (parallel-cycle model). Bullets are aggregated from `changelog.d/` fragments at each `/generate-release` phase._
+
+### ✨ New Features
+
+### 🐛 Bug Fixes
+
+### 📝 Maintenance
+
+---
+
+
 ## [3.8.50] — TBD

 _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._
--- a/docs/i18n/hi/llm.txt
+++ b/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 350 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 351 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.

 ## Overview

@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)

 ### Core Proxy
- **350 AI providers** with automatic format translation
+- **351 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
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool

 ## v3.8.x Highlights

- **350-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **351-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)
--- a/docs/i18n/hu/CHANGELOG.md
+++ b/docs/i18n/hu/CHANGELOG.md
@@ -6,6 +6,19 @@

 ## [3.8.31] — 2026-06-20

+## [3.8.51] — TBD
+
+_Living section — cycle opened at the v3.8.50 freeze (parallel-cycle model). Bullets are aggregated from `changelog.d/` fragments at each `/generate-release` phase._
+
+### ✨ New Features
+
+### 🐛 Bug Fixes
+
+### 📝 Maintenance
+
+---
+
+
 ## [3.8.50] — TBD

 _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._
--- a/docs/i18n/hu/llm.txt
+++ b/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 350 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 351 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.

 ## Overview

@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)

 ### Core Proxy
- **350 AI providers** with automatic format translation
+- **351 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
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool

 ## v3.8.x Highlights

- **350-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **351-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)
--- a/docs/i18n/id/CHANGELOG.md
+++ b/docs/i18n/id/CHANGELOG.md
@@ -6,6 +6,19 @@

 ## [3.8.31] — 2026-06-20

+## [3.8.51] — TBD
+
+_Living section — cycle opened at the v3.8.50 freeze (parallel-cycle model). Bullets are aggregated from `changelog.d/` fragments at each `/generate-release` phase._
+
+### ✨ New Features
+
+### 🐛 Bug Fixes
+
+### 📝 Maintenance
+
+---
+
+
 ## [3.8.50] — TBD

 _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._
--- a/docs/i18n/id/llm.txt
+++ b/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 350 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 351 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.

 ## Overview

@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)

 ### Core Proxy
- **350 AI providers** with automatic format translation
+- **351 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
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool

 ## v3.8.x Highlights

- **350-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **351-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)
--- a/docs/i18n/in/CHANGELOG.md
+++ b/docs/i18n/in/CHANGELOG.md
@@ -6,6 +6,19 @@

 ## [3.8.31] — 2026-06-20

+## [3.8.51] — TBD
+
+_Living section — cycle opened at the v3.8.50 freeze (parallel-cycle model). Bullets are aggregated from `changelog.d/` fragments at each `/generate-release` phase._
+
+### ✨ New Features
+
+### 🐛 Bug Fixes
+
+### 📝 Maintenance
+
+---
+
+
 ## [3.8.50] — TBD

 _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._
--- a/docs/i18n/in/llm.txt
+++ b/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 350 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 351 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.

 ## Overview

@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)

 ### Core Proxy
- **350 AI providers** with automatic format translation
+- **351 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
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool

 ## v3.8.x Highlights

- **350-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **351-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)
--- a/docs/i18n/it/CHANGELOG.md
+++ b/docs/i18n/it/CHANGELOG.md
@@ -6,6 +6,19 @@

 ## [3.8.31] — 2026-06-20

+## [3.8.51] — TBD
+
+_Living section — cycle opened at the v3.8.50 freeze (parallel-cycle model). Bullets are aggregated from `changelog.d/` fragments at each `/generate-release` phase._
+
+### ✨ New Features
+
+### 🐛 Bug Fixes
+
+### 📝 Maintenance
+
+---
+
+
 ## [3.8.50] — TBD

 _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._
--- a/docs/i18n/it/llm.txt
+++ b/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 350 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 351 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.

 ## Overview

@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)

 ### Core Proxy
- **350 AI providers** with automatic format translation
+- **351 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
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool

 ## v3.8.x Highlights

- **350-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **351-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)
--- a/docs/i18n/ja/CHANGELOG.md
+++ b/docs/i18n/ja/CHANGELOG.md
@@ -6,6 +6,19 @@

 ## [3.8.31] — 2026-06-20

+## [3.8.51] — TBD
+
+_Living section — cycle opened at the v3.8.50 freeze (parallel-cycle model). Bullets are aggregated from `changelog.d/` fragments at each `/generate-release` phase._
+
+### ✨ New Features
+
+### 🐛 Bug Fixes
+
+### 📝 Maintenance
+
+---
+
+
 ## [3.8.50] — TBD

 _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._
--- a/docs/i18n/ja/llm.txt
+++ b/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 350 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 351 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.

 ## Overview

@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)

 ### Core Proxy
- **350 AI providers** with automatic format translation
+- **351 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
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool

 ## v3.8.x Highlights

- **350-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **351-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)
--- a/docs/i18n/ko/CHANGELOG.md
+++ b/docs/i18n/ko/CHANGELOG.md
@@ -6,6 +6,19 @@

 ## [3.8.31] — 2026-06-20

+## [3.8.51] — TBD
+
+_Living section — cycle opened at the v3.8.50 freeze (parallel-cycle model). Bullets are aggregated from `changelog.d/` fragments at each `/generate-release` phase._
+
+### ✨ New Features
+
+### 🐛 Bug Fixes
+
+### 📝 Maintenance
+
+---
+
+
 ## [3.8.50] — TBD

 _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._
--- a/docs/i18n/ko/llm.txt
+++ b/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 350 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 351 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.

 ## Overview

@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)

 ### Core Proxy
- **350 AI providers** with automatic format translation
+- **351 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
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool

 ## v3.8.x Highlights

- **350-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **351-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)
--- a/docs/i18n/mr/CHANGELOG.md
+++ b/docs/i18n/mr/CHANGELOG.md
@@ -6,6 +6,19 @@

 ## [3.8.31] — 2026-06-20

+## [3.8.51] — TBD
+
+_Living section — cycle opened at the v3.8.50 freeze (parallel-cycle model). Bullets are aggregated from `changelog.d/` fragments at each `/generate-release` phase._
+
+### ✨ New Features
+
+### 🐛 Bug Fixes
+
+### 📝 Maintenance
+
+---
+
+
 ## [3.8.50] — TBD

 _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._
--- a/docs/i18n/mr/llm.txt
+++ b/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 350 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 351 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.

 ## Overview

@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)

 ### Core Proxy
- **350 AI providers** with automatic format translation
+- **351 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
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool

 ## v3.8.x Highlights

- **350-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **351-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)
--- a/docs/i18n/ms/CHANGELOG.md
+++ b/docs/i18n/ms/CHANGELOG.md
@@ -6,6 +6,19 @@

 ## [3.8.31] — 2026-06-20

+## [3.8.51] — TBD
+
+_Living section — cycle opened at the v3.8.50 freeze (parallel-cycle model). Bullets are aggregated from `changelog.d/` fragments at each `/generate-release` phase._
+
+### ✨ New Features
+
+### 🐛 Bug Fixes
+
+### 📝 Maintenance
+
+---
+
+
 ## [3.8.50] — TBD

 _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._
--- a/docs/i18n/ms/llm.txt
+++ b/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 350 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 351 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.

 ## Overview

@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)

 ### Core Proxy
- **350 AI providers** with automatic format translation
+- **351 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
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool

 ## v3.8.x Highlights

- **350-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **351-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)
--- a/docs/i18n/nl/CHANGELOG.md
+++ b/docs/i18n/nl/CHANGELOG.md
@@ -6,6 +6,19 @@

 ## [3.8.31] — 2026-06-20

+## [3.8.51] — TBD
+
+_Living section — cycle opened at the v3.8.50 freeze (parallel-cycle model). Bullets are aggregated from `changelog.d/` fragments at each `/generate-release` phase._
+
+### ✨ New Features
+
+### 🐛 Bug Fixes
+
+### 📝 Maintenance
+
+---
+
+
 ## [3.8.50] — TBD

 _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._
--- a/docs/i18n/nl/llm.txt
+++ b/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 350 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 351 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.

 ## Overview

@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)

 ### Core Proxy
- **350 AI providers** with automatic format translation
+- **351 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
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool

 ## v3.8.x Highlights

- **350-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **351-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)
--- a/docs/i18n/no/CHANGELOG.md
+++ b/docs/i18n/no/CHANGELOG.md
@@ -6,6 +6,19 @@

 ## [3.8.31] — 2026-06-20

+## [3.8.51] — TBD
+
+_Living section — cycle opened at the v3.8.50 freeze (parallel-cycle model). Bullets are aggregated from `changelog.d/` fragments at each `/generate-release` phase._
+
+### ✨ New Features
+
+### 🐛 Bug Fixes
+
+### 📝 Maintenance
+
+---
+
+
 ## [3.8.50] — TBD

 _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._
--- a/docs/i18n/no/llm.txt
+++ b/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 350 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 351 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.

 ## Overview

@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)

 ### Core Proxy
- **350 AI providers** with automatic format translation
+- **351 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
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool

 ## v3.8.x Highlights

- **350-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **351-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)
--- a/docs/i18n/phi/CHANGELOG.md
+++ b/docs/i18n/phi/CHANGELOG.md
@@ -6,6 +6,19 @@

 ## [3.8.31] — 2026-06-20

+## [3.8.51] — TBD
+
+_Living section — cycle opened at the v3.8.50 freeze (parallel-cycle model). Bullets are aggregated from `changelog.d/` fragments at each `/generate-release` phase._
+
+### ✨ New Features
+
+### 🐛 Bug Fixes
+
+### 📝 Maintenance
+
+---
+
+
 ## [3.8.50] — TBD

 _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._
--- a/docs/i18n/phi/llm.txt
+++ b/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 350 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 351 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.

 ## Overview

@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)

 ### Core Proxy
- **350 AI providers** with automatic format translation
+- **351 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
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool

 ## v3.8.x Highlights

- **350-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **351-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)
--- a/docs/i18n/pl/CHANGELOG.md
+++ b/docs/i18n/pl/CHANGELOG.md
@@ -8,6 +8,19 @@

 ---

+## [3.8.51] — TBD
+
+_Living section — cycle opened at the v3.8.50 freeze (parallel-cycle model). Bullets are aggregated from `changelog.d/` fragments at each `/generate-release` phase._
+
+### ✨ New Features
+
+### 🐛 Bug Fixes
+
+### 📝 Maintenance
+
+---
+
+
 ## [3.8.50] — TBD

 _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._
--- a/docs/i18n/pl/llm.txt
+++ b/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 350 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 351 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.

 ## Overview

@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)

 ### Core Proxy
- **350 AI providers** with automatic format translation
+- **351 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
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool

 ## v3.8.x Highlights

- **350-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **351-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)
--- a/docs/i18n/pt-BR/CHANGELOG.md
+++ b/docs/i18n/pt-BR/CHANGELOG.md
@@ -6,6 +6,19 @@

 ## [3.8.31] — 2026-06-20

+## [3.8.51] — TBD
+
+_Living section — cycle opened at the v3.8.50 freeze (parallel-cycle model). Bullets are aggregated from `changelog.d/` fragments at each `/generate-release` phase._
+
+### ✨ New Features
+
+### 🐛 Bug Fixes
+
+### 📝 Maintenance
+
+---
+
+
 ## [3.8.50] — TBD

 _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._
--- a/docs/i18n/pt-BR/llm.txt
+++ b/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 350 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 351 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.

 ## Overview

@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)

 ### Core Proxy
- **350 AI providers** with automatic format translation
+- **351 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
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool

 ## v3.8.x Highlights

- **350-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **351-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)
--- a/docs/i18n/pt/CHANGELOG.md
+++ b/docs/i18n/pt/CHANGELOG.md
@@ -6,6 +6,19 @@

 ## [3.8.31] — 2026-06-20

+## [3.8.51] — TBD
+
+_Living section — cycle opened at the v3.8.50 freeze (parallel-cycle model). Bullets are aggregated from `changelog.d/` fragments at each `/generate-release` phase._
+
+### ✨ New Features
+
+### 🐛 Bug Fixes
+
+### 📝 Maintenance
+
+---
+
+
 ## [3.8.50] — TBD

 _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._
--- a/docs/i18n/pt/llm.txt
+++ b/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 350 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 351 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.

 ## Overview

@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)

 ### Core Proxy
- **350 AI providers** with automatic format translation
+- **351 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
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool

 ## v3.8.x Highlights

- **350-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **351-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)
--- a/docs/i18n/ro/CHANGELOG.md
+++ b/docs/i18n/ro/CHANGELOG.md
@@ -6,6 +6,19 @@

 ## [3.8.31] — 2026-06-20

+## [3.8.51] — TBD
+
+_Living section — cycle opened at the v3.8.50 freeze (parallel-cycle model). Bullets are aggregated from `changelog.d/` fragments at each `/generate-release` phase._
+
+### ✨ New Features
+
+### 🐛 Bug Fixes
+
+### 📝 Maintenance
+
+---
+
+
 ## [3.8.50] — TBD

 _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._
--- a/docs/i18n/ro/llm.txt
+++ b/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 350 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 351 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.

 ## Overview

@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)

 ### Core Proxy
- **350 AI providers** with automatic format translation
+- **351 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
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool

 ## v3.8.x Highlights

- **350-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **351-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)
--- a/docs/i18n/ru/CHANGELOG.md
+++ b/docs/i18n/ru/CHANGELOG.md
@@ -6,6 +6,19 @@

 ## [3.8.31] — 2026-06-20

+## [3.8.51] — TBD
+
+_Living section — cycle opened at the v3.8.50 freeze (parallel-cycle model). Bullets are aggregated from `changelog.d/` fragments at each `/generate-release` phase._
+
+### ✨ New Features
+
+### 🐛 Bug Fixes
+
+### 📝 Maintenance
+
+---
+
+
 ## [3.8.50] — TBD

 _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._
--- a/docs/i18n/ru/llm.txt
+++ b/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 350 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 351 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.

 ## Overview

@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)

 ### Core Proxy
- **350 AI providers** with automatic format translation
+- **351 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
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool

 ## v3.8.x Highlights

- **350-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **351-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)
--- a/docs/i18n/sk/CHANGELOG.md
+++ b/docs/i18n/sk/CHANGELOG.md
@@ -6,6 +6,19 @@

 ## [3.8.31] — 2026-06-20

+## [3.8.51] — TBD
+
+_Living section — cycle opened at the v3.8.50 freeze (parallel-cycle model). Bullets are aggregated from `changelog.d/` fragments at each `/generate-release` phase._
+
+### ✨ New Features
+
+### 🐛 Bug Fixes
+
+### 📝 Maintenance
+
+---
+
+
 ## [3.8.50] — TBD

 _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._
--- a/docs/i18n/sk/llm.txt
+++ b/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 350 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 351 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.

 ## Overview

@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)

 ### Core Proxy
- **350 AI providers** with automatic format translation
+- **351 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
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool

 ## v3.8.x Highlights

- **350-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **351-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)
--- a/docs/i18n/sv/CHANGELOG.md
+++ b/docs/i18n/sv/CHANGELOG.md
@@ -6,6 +6,19 @@

 ## [3.8.31] — 2026-06-20

+## [3.8.51] — TBD
+
+_Living section — cycle opened at the v3.8.50 freeze (parallel-cycle model). Bullets are aggregated from `changelog.d/` fragments at each `/generate-release` phase._
+
+### ✨ New Features
+
+### 🐛 Bug Fixes
+
+### 📝 Maintenance
+
+---
+
+
 ## [3.8.50] — TBD

 _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._
--- a/docs/i18n/sv/llm.txt
+++ b/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 350 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 351 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.

 ## Overview

@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)

 ### Core Proxy
- **350 AI providers** with automatic format translation
+- **351 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
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool

 ## v3.8.x Highlights

- **350-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **351-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)
--- a/docs/i18n/sw/CHANGELOG.md
+++ b/docs/i18n/sw/CHANGELOG.md
@@ -6,6 +6,19 @@

 ## [3.8.31] — 2026-06-20

+## [3.8.51] — TBD
+
+_Living section — cycle opened at the v3.8.50 freeze (parallel-cycle model). Bullets are aggregated from `changelog.d/` fragments at each `/generate-release` phase._
+
+### ✨ New Features
+
+### 🐛 Bug Fixes
+
+### 📝 Maintenance
+
+---
+
+
 ## [3.8.50] — TBD

 _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._
--- a/docs/i18n/sw/llm.txt
+++ b/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 350 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 351 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.

 ## Overview

@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)

 ### Core Proxy
- **350 AI providers** with automatic format translation
+- **351 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
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool

 ## v3.8.x Highlights

- **350-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **351-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)
--- a/docs/i18n/ta/CHANGELOG.md
+++ b/docs/i18n/ta/CHANGELOG.md
@@ -6,6 +6,19 @@

 ## [3.8.31] — 2026-06-20

+## [3.8.51] — TBD
+
+_Living section — cycle opened at the v3.8.50 freeze (parallel-cycle model). Bullets are aggregated from `changelog.d/` fragments at each `/generate-release` phase._
+
+### ✨ New Features
+
+### 🐛 Bug Fixes
+
+### 📝 Maintenance
+
+---
+
+
 ## [3.8.50] — TBD

 _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._
--- a/docs/i18n/ta/llm.txt
+++ b/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 350 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 351 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.

 ## Overview

@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)

 ### Core Proxy
- **350 AI providers** with automatic format translation
+- **351 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
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool

 ## v3.8.x Highlights

- **350-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **351-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)
--- a/docs/i18n/te/CHANGELOG.md
+++ b/docs/i18n/te/CHANGELOG.md
@@ -6,6 +6,19 @@

 ## [3.8.31] — 2026-06-20

+## [3.8.51] — TBD
+
+_Living section — cycle opened at the v3.8.50 freeze (parallel-cycle model). Bullets are aggregated from `changelog.d/` fragments at each `/generate-release` phase._
+
+### ✨ New Features
+
+### 🐛 Bug Fixes
+
+### 📝 Maintenance
+
+---
+
+
 ## [3.8.50] — TBD

 _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._
--- a/docs/i18n/te/llm.txt
+++ b/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 350 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 351 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.

 ## Overview

@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)

 ### Core Proxy
- **350 AI providers** with automatic format translation
+- **351 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
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool

 ## v3.8.x Highlights

- **350-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **351-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)
--- a/docs/i18n/th/CHANGELOG.md
+++ b/docs/i18n/th/CHANGELOG.md
@@ -6,6 +6,19 @@

 ## [3.8.31] — 2026-06-20

+## [3.8.51] — TBD
+
+_Living section — cycle opened at the v3.8.50 freeze (parallel-cycle model). Bullets are aggregated from `changelog.d/` fragments at each `/generate-release` phase._
+
+### ✨ New Features
+
+### 🐛 Bug Fixes
+
+### 📝 Maintenance
+
+---
+
+
 ## [3.8.50] — TBD

 _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._
--- a/docs/i18n/th/llm.txt
+++ b/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 350 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 351 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.

 ## Overview

@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)

 ### Core Proxy
- **350 AI providers** with automatic format translation
+- **351 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
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool

 ## v3.8.x Highlights

- **350-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **351-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)
--- a/Show More
+++ b/Show More
Author	SHA1	Message	Date
Markus Hartung	a582bef675	board #11389	2026-08-24 23:21:27 -03:00
Markus Hartung	f77254da79	board #11443 # Conflicts: # README.md # docs/diagrams/cli-terminal.svg # docs/diagrams/promise-pillars.svg	2026-08-24 23:21:17 -03:00
Markus Hartung	b1474b992f	board #11441	2026-08-24 23:20:55 -03:00
Markus Hartung	86514aa481	board #11423	2026-08-24 23:20:52 -03:00
Markus Hartung	a150c6bc40	board #11409	2026-08-24 23:20:49 -03:00
Markus Hartung	c59661cfd6	board #11340	2026-08-24 23:20:47 -03:00
Markus Hartung	b76866fa12	chore(deps): regenerate package-lock.json after ESLint 10 + bun 1.4.0 bump (#11259 )	2026-08-24 23:20:22 -03:00
backryun	8a14cefcb1	chore(deps): refresh runtimes and adopt ESLint 10	2026-08-24 23:15:54 -03:00
oyi77	158fb1a806	test(executors): adapt remaining 35 suites to the async lazy registry (round 2) Round 1 only covered suites importing from executors/index.ts directly; suites importing getExecutor through other paths (open-sse root re-export, dynamic imports inside tests) still called it synchronously, producing Promise-vs-instance assertion failures in CI (e.g. providers-yuanbao-web 'instanceof YuanbaoWebExecutor' false). Sweep method: repo-wide scan for un-awaited getExecutor call sites, adapted mechanically (await + async callbacks + Response\|{response} union narrowing); assert.rejects guards with promise-returning callbacks verified correct as-is. Locally verified green: providers-yuanbao-web, ninerouter-executor, provider-request-failure-pipeline, provider-limits-accesstoken-fallback, executor-registry, chatcore-executor-proxy, poe-api-executor-regression, web-cookie-providers-new (113/113).	2026-08-24 21:44:23 -03:00
oyi77	77ea656b12	perf(executors): lazy-load the executor registry — defer class imports + construction to first use (#11220 ) The executor barrel statically imported ~100 executor modules and constructed every instance at module load. Measured cold cost on top of the minimal set: ~0.7–1.2s boot time and ~35MB heap, paid by every deployment regardless of which providers it uses. Now: - executors/index.ts keeps the declarative alias table byte-stable (same keys, same order, same ctor args — pinned by the golden lock) but each value is a deferred loader using dynamic import; bundlers emit on-demand chunks - registry.ts gains registerLazyExecutor/loadRegisteredExecutor: aliases are declared eagerly so hasSpecializedExecutor() and listExecutorAliases() stay synchronous, instances materialize once on first use and cache into the same registry map - getExecutor() becomes async; production call sites (chatCore proxy resolver, video generation, compression judge/eval clients, quotaAutoPing deps, anthropic OAuth validation) await it - cliproxy wrapper ExecutorLike types drop their index signatures so BaseExecutor satisfies them structurally Measured after (isolated DATA_DIR): barrel boot 712-832ms / ~45MB with first-use materialization of an executor costing +120-150ms once. Test impact: 24 unit suites adapted mechanically to the async seam (await + union narrowing on the Response \| {response} execute result); class imports moved from the barrel to executor module files. The web-cookie sweep SIGABRT failure is pre-existing (reproduced identically on the clean base). Commit gate note: husky lint-staged fails with 'suppressions left that do not occur anymore' — reproduced identically on a stashed clean tree (22 baseline problems), independent of this change.	2026-08-24 21:44:22 -03:00
Minxi Hou	471052b904	fix(combo): enable genuine quota-aware routing for generic providers (antigravity, claude, etc.)	2026-08-24 21:44:06 -03:00
Rouzbeh	b8553c8f0d	fix(ci): prune stale ESLint suppressions fixed by this change Our PR fixed the last no-restricted-imports violation in src/lib/memory/embedding/index.ts (localDb barrel import replaced by a direct readCache import), so the frozen suppression entry for that file became stale. The gate (run-eslint-json.mjs) hard-fails on stale entries, so remove it to keep 'No new ESLint warnings' green.	2026-08-24 21:44:05 -03:00
Rouzbeh	1255b5869b	fix(memory): list and serve embedding/rerank models from all configured providers The memory Engine tab quick-select built its model list only from a keyword heuristic over the chat catalog plus OpenRouter live discovery, so configured providers whose embedding models are not in that catalog (e.g. Cloudflare Workers AI cf/@cf/baai/bge-m3) never appeared, and requests for them failed with 'Unknown embedding provider'. - add cloudflare-ai to EMBEDDING_PROVIDERS with a requiresAccountId URL template resolved per-request via buildEmbeddingProviderUrl() (mirrors CloudflareAIExecutor on the chat side) plus the cf provider alias - merge curated registry models into the quick-select catalog and add a generic fallback listing: any configured OpenAI-compatible chat provider without a curated entry appears with free-text model input - same treatment for rerank: listRerankProviders + generic Cohere- compatible fallback, new /api/memory/rerank-providers endpoint, selectors fall back to free-text when no static models exist - runtime: embeddings service/handler and rerank route/handler resolve derived providers instead of rejecting unlisted ones	2026-08-24 21:44:00 -03:00
kriptoburak	ea2746e594	docs(changelog): add Xquik search fragment	2026-08-24 21:43:50 -03:00
kriptoburak	c264c24de9	fix(search): sync generated inference skill	2026-08-24 21:43:50 -03:00
kriptoburak	15cbc1ede7	fix(search): document API and update dispatch golden	2026-08-24 21:43:50 -03:00
kriptoburak	a65666519d	feat(search): add Xquik X search provider	2026-08-24 21:43:50 -03:00
Ravi Tharuma	829634b741	fix(i18n): align Brazilian Portuguese resilience keys	2026-08-24 21:43:37 -03:00
Ravi Tharuma	09666c50e7	fix(i18n): keep Vietnamese resilience keys aligned	2026-08-24 21:43:36 -03:00
Ravi Tharuma	2b9f25accb	feat(resilience): add hierarchical concurrency admission	2026-08-24 21:43:36 -03:00
Dizzle	943b9aaa84	fix(cli): flag a .env that lives inside the installed package (#11437 ) Retargetado para release/v3.8.51 (release/v3.8.50 está congelada — freeze issue #11439). Resolvido o mesmo conflito não-relacionado em src/shared/utils/wsPath.ts (mesma causa do #11436 — refactor já mergeado na branch depois do fork deste PR; o diff real deste PR — bin/cli/utils/volatileEnvPath.mjs + bin/omniroute.mjs — ficou intacto) e revalidado: typecheck:core limpo, 12/12 testes focados passando. Companion do #11436, decisão pura testável isoladamente, sem mudança de comportamento fora do caso volátil. Obrigado pela contribuição!	2026-08-24 20:10:08 -03:00
WebPerson	9dc7711dc2	fix(electron): make the packaged Windows build pass the #7592 cold-restart smoke Five defects found while validating #7592 on a real packaged Windows build: - optionalPackStaging: GNU tar reads the drive letter in an absolute -f C:\... archive path as a remote rsh host (Cannot connect to C:), failing optional-pack staging on Git-for-Windows machines. Pass a bare filename with cwd at the tarball directory; surface tar stderr. - electron/package.json: lib/loginHeaderCapture.js was missing from the asar files allowlist; loginManager.js requires it top-level, so the packaged main process crashed on launch. - electron-builder >=26 injects !/node_modules/ into every extraResources pattern list and no positive filter can override it, silently dropping the staged runtime node_modules (including the better-sqlite3 N-API prebuild) from resources/app. Add an afterPack hook (scripts/build/afterpack-copy-node-modules.mjs) that restores it. - smoke harness: Electron resolves userData from %USERPROFILE%/AppData/Roaming/<name> (USERPROFILE wins over APPDATA) and the path service throws when it is missing, so requestSingleInstanceLock() returned false and the app exited(0) silently before whenReady. ensureSmokeEnvDirs now pre-creates the derived tree and is exported for tests. - core.ts: the #7592 guard parses a [DB] Driver: ... line that only the unused openDatabaseAsync() emitted; getDbInstance() now logs the same line on its primary open so the assertion is reachable. Also makes the smoke env-allowlist unit test host-agnostic (it hardcoded POSIX paths) and adds regression tests for the USERPROFILE derived tree and tarPack under Windows-style absolute paths. Closes #7592	2026-08-24 18:06:06 -05:00
Dizzle	6e8fc94732	fix(cli): stop pre-filling the secrets the server owns (#11436 ) Retargetado para release/v3.8.51 (release/v3.8.50 está congelada — freeze issue #11439). Resolvido um conflito de merge não-relacionado em src/shared/utils/wsPath.ts (originado de um refactor já mergeado nessa branch depois do fork deste PR; o diff real deste PR — scripts/dev/sync-env.mjs + tests/unit/sync-env.test.ts — ficou intacto) e revalidado: typecheck:core limpo, 13/13 testes focados passando. Segue o precedente correto do #1622 (STORAGE_ENCRYPTION_KEY) para os dois secrets restantes que a postinstall preenchia por engano, defeituando o mecanismo de ensureSecrets(). Obrigado pela contribuição!	2026-08-24 20:04:11 -03:00
Max	42c209797c	fix(free-models): stop reporting discontinued Pollinations models as free The shared isFreeModel() predicate ignored each catalog entry's freeType, so Pollinations models marked "discontinued" (moved behind a paid key) were still reported free and could be routed under hidePaidModels. Add a compiler-checked grantsFreeAccess(freeType) table and use it in both the routing predicate and strictZeroCostFilter. Tests: tests/unit/autoCombo/free-regime-not-read-by-predicate.test.ts	2026-08-25 01:03:45 +02:00
Xiangzhe	66ecc09050	chore(release): restore the living [3.8.51] CHANGELOG section The cycle-open commit's root CHANGELOG hunk was lost in the rebase onto the branch tip (the 42 i18n mirrors kept theirs, so the root and the mirrors had drifted apart). Re-inserts the section with the three canonical headings.	2026-08-24 20:00:10 -03:00
Xiangzhe	65a1808f84	chore(release): open v3.8.51 development cycle Completes the 0a.0b cut for the parallel-cycle model: the branch already existed (cut from the v3.8.50 tip) but had never been bumped. Bumps package.json x3, openapi.yaml and the lockfile, adds the living [3.8.51] CHANGELOG section with the three canonical headings so aggregate-changelog.mjs cannot mis-target an older published section, and syncs the 42 i18n mirrors.	2026-08-24 19:59:24 -03:00
Dizzle	a166752138	fix(radar): keep the feed's build date in the catalog cache (#11435 ) Retargetado para release/v3.8.51 (release/v3.8.50 está congelada — freeze issue #11439). Validado em lote combinado (batch-0824h2) contra o tip de release/v3.8.51: typecheck:core limpo, gates estáticos + migration-numbering OK, 127/127 testes focados passando (8/8 do PR entre migration-163 e radar-feed-cache-generated-at). Migração limpa (ADD COLUMN nullable, sem backfill necessário), aditiva na API, mantém "unknown" honesto para linhas antigas. Obrigado pela contribuição!	2026-08-24 19:57:24 -03:00
Markus Hartung	04dba0460e	fix(responses-continuation): recover a real id/output for passthrough and translate-mode replies (#11434 ) Retargetado para release/v3.8.51 (release/v3.8.50 está congelada — freeze issue #11439). Validado em lote combinado (batch-0824h2, junto de #11435/#11436/#11437) contra o tip de release/v3.8.51: typecheck:core limpo, gates estáticos OK, 127/127 testes focados passando. Investigação sólida com repro real via container isolado, três causas independentes identificadas e corrigidas com testes de regressão dedicados para cada uma. Obrigado pela contribuição!	2026-08-24 19:57:12 -03:00
oyi77	38527e4a21	docs(design): external durable-state DB backend proposal (#8075 ) Grounded design answering the five open questions in #8075 with a measured coupling census of release/v3.8.51: 126 db modules on the sync prepare()/transaction() shape, 36 pragma sites, 159 SQLite migrations, 9 sqlite-vec + 8 FTS5 files, and a 4-driver SqliteAdapter seam that is SQLite-only in practice (synchronous API). Proposal: dialect-agnostic async DurableStateStore port with per-domain repositories adopted incrementally; Postgres-first with MySQL gated by a shared dialect-conformance suite; DATABASE_DRIVER config surface with sqlite as the non-negotiable zero-config default; fail-closed one-way export tool; five-phase delivery plan.	2026-08-25 01:08:36 +07:00
oyi77	fa7ccaf679	fix(providers): stop silently dropping reasoning effort on opencode families (#10788 ) Dispatch: OpencodeExecutor.transformRequest stripped the effort-suffixed alias (e.g. glm-5.2-high) down to the base id and injected a flat reasoning_effort body field — but opencode-go's ChatCompletionRequest has no such field for non-DeepSeek families, so the tier never reached the upstream and every request ran at default effort. Only DeepSeek V4 accepts the flat field (its native contract, #4647), so it keeps the old rewrite; every other family now forwards the aliased model id verbatim, which is their only native effort mechanism. Registry: declare supportedThinkingEfforts on the base rows that had aliases but no tier vocabulary — opencode-go (glm-5.2, mimo-v2.5, grok-4.5, hy3, kimi-k3, qwen3.7-max/plus), the shared zen/go row (qwen3.6-plus) and opencode-zen (deepseek-v4-pro/flash, glm-5.2, kimi-k3) — so catalog variant synthesis (#9485) and sanitizeReasoningEffortForProvider clamp from one source of truth. nvidia z-ai/glm-5.2 is declared reasoning-capable with an EMPTY tier list: its upstream only exposes a binary enable_thinking switch (mapNvidiaGlm52ReasoningParams), so no honest tiers exist to advertise. Ollama Cloud declarations were already landed upstream (#11307); this change covers the remaining providers named in #10788.	2026-08-24 22:06:59 +07:00
KaspaPulse	85b2a06fad	feat(dashboard): surface exclusive managed leases in Sessions view Reuse the official exclusive-lease authority for durable idle visibility, and use pending-request accounting only for the localized active indication. Preserve legacy session fields and rows while de-duplicating leased connections and withholding lease ownership and fencing data. Refs #10514 Follow-up to #10362	2026-08-24 13:53:27 +00:00
Zartharas	c89bdb21a2	chore(changelog): document web-session contract	2026-08-24 00:07:51 -05:00
Zartharas	c5e694131a	style(test): format web-session contract regression	2026-08-24 00:07:33 -05:00
Aman	9e7096a048	refactor(providers): use canonical contract imports	2026-08-23 23:36:47 -05:00
Aman	a84f0b683e	test(providers): cover web-session contract publication	2026-08-23 23:36:47 -05:00
Aman	ae0b79ab7c	feat(api): publish web-session credential contract	2026-08-23 23:36:47 -05:00
Aman	6daa31de0b	feat(providers): add web-session contract builder	2026-08-23 23:36:46 -05:00
				`@@ -0,0 +1 @@`
				`- feat(providers): publish a management-authenticated versioned web-session credential contract from OmniRoute's canonical browser credential metadata ([#11340](https://github.com/diegosouzapw/OmniRoute/pull/11340)) — thanks @Zartharas`
				`@@ -0,0 +1 @@`
				`- feat(search): Add Xquik X search with typed results, credential validation, REST routing, and MCP selection ([#11370](https://github.com/diegosouzapw/OmniRoute/pull/11370)) — thanks @kriptoburak`
				`@@ -0,0 +1 @@`
				`- feat(dashboard): surface durable exclusive managed leases in the existing Sessions view, keeping leased clients visible across idle gaps while marking connections with in-flight work as active ([#11389](https://github.com/diegosouzapw/OmniRoute/pull/11389)) — thanks @KaspaPulse`
				`@@ -0,0 +1 @@`
				- Live dashboard: honour the WebSocket port reported by `/api/v1/ws?handshake=1` instead of the port compiled into the bundle, so a `LIVE_WS_PORT` override reaches prebuilt Docker/npm images and Combo Studio Live connects behind a reverse proxy ([#11331](https://github.com/diegosouzapw/OmniRoute/issues/11331)).
				`@@ -0,0 +1 @@`
				- fix(radar): the catalog feed cache now keeps `generatedAt`, the date the feed's data was built, next to `fetchedAt`, the date this install downloaded it (#11435). The feed schema requires that date and the sync path validates it, but the cache dropped it — so a feed fetched minutes ago and one carrying weeks-old figures looked identical to everything downstream, including the dashboard's "Last fetched" line. `getRadarCatalog().meta` and `GET /api/radar/status` now report both dates, the latter as its own field rather than folded into `version` — and omitted entirely for the offers and intel caches, which keep no build date, where a `null` would read as "unknown" rather than "never stored". The dashboard still shows only the fetch time; surfacing the build date there needs a new translated label and is left to a follow-up. Rows cached before migration 163 read back as `null`: unknown stays unknown instead of borrowing the fetch time. The referrals cache has persisted the same date since migration 142.
				`@@ -0,0 +1 @@`
				- fix(cli): postinstall no longer fills `JWT_SECRET` and `API_KEY_SECRET` in the installed package's `.env` (#11436). `.env.example` ships both blank on purpose: the server restores them from its durable store, or generates and persists them there, in `ensureSecrets()`. Pre-filling them defeated that — the file lives inside the package directory, so `npm i -g` replaced it and postinstall wrote _different_ values, while `ensureSecrets()` (which only acts on an empty variable) never got to restore the real ones. Both secrets rotated silently on every update, invalidating dashboard sessions and API-key CRCs. `STORAGE_ENCRYPTION_KEY` left the same list for the same reason in #1622; its comment pointed at a function that no longer exists and now names the real provisioning path.
				`@@ -0,0 +1 @@`
				- fix(cli): the CLI now says when a loaded `.env` lives inside the installed package directory (#11437). It already announces every env file it reads, without distinguishing the ones that survive an update from the one that does not: `npm i -g` replaces the package directory wholesale, so values set there are gone at the next update, silently. The warning names the durable path to move them to, and fires only when that file actually supplied a value — a file entirely shadowed by a durable one supplied nothing. A development checkout stays silent: there the same path is stable and documented in `SETUP_GUIDE.md`.
				`@@ -0,0 +1 @@`
				- fix(free-models): the shared `isFreeModel()` predicate no longer reports catalog entries marked `freeType: "discontinued"` as free, so `hidePaidModels` can't route to Pollinations' seven premium models that now require a paid key ([#11441](https://github.com/diegosouzapw/OmniRoute/pull/11441))
				`@@ -0,0 +1 @@`
				- fix(electron): the packaged Windows desktop build now passes the #7592 cold-restart smoke end to end. Five defects were found and fixed on the way: (1) optional-pack staging failed on any machine whose `tar` is GNU tar — it reads the drive letter in an absolute `-f C:\...` archive path as a remote rsh host (`Cannot connect to C:`), so staging now passes a bare filename with `cwd` at the tarball directory and surfaces tar stderr on failure; (2) the Electron `files` allowlist was missing `lib/loginHeaderCapture.js`, so the packaged main process crashed at startup with `Cannot find module './lib/loginHeaderCapture'`; (3) electron-builder ≥26 injects an `!/node_modules/` ignore into every extraResources pattern list that no positive filter can override, which silently dropped the staged runtime `node_modules` (including the better-sqlite3 N-API prebuild) from `resources/app` — a fresh v3.8.50 desktop build would have shipped with no native SQLite driver and reproduced the #7592 sql.js fallback on every machine; an `afterPack` hook now restores the staged `node_modules` after packing; (4) the packaged-app smoke harness redirected `USERPROFILE` into its temp DATA_DIR, but Electron resolves the Roaming profile from `%USERPROFILE%\AppData\Roaming\<name>` (USERPROFILE takes precedence over the APPDATA env var) and the path service throws instead of creating it, so `requestSingleInstanceLock()` returned false and the app exited(0) silently before `app.whenReady()` — the harness now pre-creates the derived tree, and `ensureSmokeEnvDirs` is exported and unit-tested; (5) the #7592 driver assertion parsed a `[DB] Driver: ...` line that the server's primary DB path never printed (only the unused `openDatabaseAsync()` did) — `getDbInstance()` now emits the same line on open so the guard can actually assert the native driver. Also: the smoke env-allowlist unit test hardcoded POSIX paths and could only pass on Linux/macOS; expectations are now host-agnostic, with new regression tests for the USERPROFILE-derived tree and `tarPack` under absolute Windows-style paths