fix(sse): exact-domain cookie match and origin-equality URL assertions

Clears CodeQL js/incomplete-url-substring-sanitization alerts #860-#865:

- volcengineConsoleAutoLogin: cookie domain filter now uses an exact/
  dot-suffix helper (isVolcengineCookieDomain) instead of substring
  includes(), rejecting look-alike hosts like volcengine.com.evil.test
- security-s1-s2-s4 tests: agent-card/agent.json URL assertions compare
  parsed origin equality instead of startsWith prefix

AGENTS.md

@@ -46,7 +46,7 @@ Repository map and Reference Documentation sections below.
 
 ## Project at a Glance
 
-**OmniRoute** — unified AI proxy/router. One endpoint, 353 LLM providers, auto-fallback.
+**OmniRoute** — unified AI proxy/router. One endpoint, 350 LLM providers, auto-fallback.
 
 | Layer         | Location                | Purpose                                                                                                                                                                   |
 | ------------- | ----------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |

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 → 353 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. 353 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 → 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."/>
 
 </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 353 providers. Automatic fallback keeps routing while another healthy target is available. Six pillars: resilient fallback across 353 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 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."/>
 
 <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: 353 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: 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."/>
 
 <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 **353-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 **350-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">
 
-## 🌐 353 AI Providers — 154 Catalog-Marked Free
+## 🌐 350 AI Providers — 154 Catalog-Marked Free
 
 </div>
 
-> **353 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).
+> **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).
 
 <div align="center">
 

changelog.d/features/11146-subscription-first-routing.md

@@ -1 +0,0 @@
-- **feat(routing):** subscription-first auto groupings — `auto/subscription` routes only through plan-included connections with a documented hard-stop overage and fails closed on exhaustion, while `auto/thrifty` orders the pool `subscription → keyless → free → cheap → premium` and steps up one rung at a time as each is exhausted. Billing class comes from a curated per-connection catalog (uncurated is treated as metered, never plan-included), both reuse STRICT_ZERO_COST's per-connection verification, and a quota reading whose `resetAt` has passed is now refreshed regardless of TTL so routing returns to plan capacity as soon as it resets ([#11146](https://github.com/diegosouzapw/OmniRoute/pull/11146))

changelog.d/features/11340-web-session-contract.md

@@ -1 +0,0 @@
-- **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

changelog.d/features/11370-xquik-search-provider.md

@@ -1 +0,0 @@
-- **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

changelog.d/features/11389-exclusive-managed-session-dashboard.md

@@ -1 +0,0 @@
-- **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

changelog.d/fixes/11368-create-connection-tokenexpiresat.md

@@ -1 +0,0 @@
-- **Provider connections:** keep `tokenExpiresAt` when a connection is created. The create-path allowlist omitted it, so every insert stored NULL and the dashboard token badge could read a fresh connection as expired until its first background refresh ([#11368](https://github.com/diegosouzapw/OmniRoute/pull/11368)).

changelog.d/fixes/11441-discontinued-free-models.md

@@ -1 +0,0 @@
-- **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))

config/quality/file-size-baseline.json

@@ -478,8 +478,7 @@
     "_rebaseline_2026_08_23_tip_drift_post_batch0823": "Tip drift after the 2026-08-23 merge wave: chatBodyAdmission.ts 1009->1118 (+109, gate count incl. +1) and auth.ts 3337->3344 (+7), both grown by merges already on origin/release/v3.8.50 (verified identical on the pristine tip) — not by the codex-appserver-hardening PR that carries this bump. Owner pre-authorized baseline bumps 2026-08-22.",
     "_rebaseline_2026_08_24_11355_cooldown_recovery_guards": "PR #11355 own growth: test/route.ts 1215->1237, +22 (startup crash-recovery guard: clearStaleCrashCooldowns() now parses the persisted rate_limited_until deadline and skips clearing rows still genuinely in the future, instead of clearing every non-terminal cooldown unconditionally). Cohesive fix at the existing test-route dispatch chokepoint alongside the #11141 probe builder. Covered by tests/unit/startup-stale-cooldown-recovery.test.ts + tests/unit/repro-zai-cooldown-cleared-by-connection-test.test.ts.",
     "src/lib/guardrails/videoBridgeRuntime.ts": 1009,
-    "_rebaseline_2026_08_24_video_bridge_fu02_fu07_sampler": "PRs #11344 (FU-02 one-frame scene-aware determinism) + #11381 (FU-07 opt-in segment_aware structural sampling) own growth: videoBridgeRuntime.ts <1000->1009, +9 (sum of both boarded together in the same merge-batch). #11344 adds the deterministic one-frame midpoint fallback + policyEffective=uniform report at the existing scene_aware seam; #11381 adds the bounded local-only FFmpeg structural pre-analysis pass (scene/freeze/blur/exposure/SI-TI) and its budget-reallocation logic. Covered by tests/unit/guardrails/videoBridgeSampler.test.ts, tests/unit/guardrails/videoBridgeFu07StructuralSampling.test.ts, tests/integration/video-bridge-sampler-ffmpeg.test.ts. Owner pre-authorized rebaseline for legitimate PR growth (2026-08-19 directive).",
-    "open-sse/services/autoCombo/virtualFactory.ts": 1130
+    "_rebaseline_2026_08_24_video_bridge_fu02_fu07_sampler": "PRs #11344 (FU-02 one-frame scene-aware determinism) + #11381 (FU-07 opt-in segment_aware structural sampling) own growth: videoBridgeRuntime.ts <1000->1009, +9 (sum of both boarded together in the same merge-batch). #11344 adds the deterministic one-frame midpoint fallback + policyEffective=uniform report at the existing scene_aware seam; #11381 adds the bounded local-only FFmpeg structural pre-analysis pass (scene/freeze/blur/exposure/SI-TI) and its budget-reallocation logic. Covered by tests/unit/guardrails/videoBridgeSampler.test.ts, tests/unit/guardrails/videoBridgeFu07StructuralSampling.test.ts, tests/integration/video-bridge-sampler-ffmpeg.test.ts. Owner pre-authorized rebaseline for legitimate PR growth (2026-08-19 directive)."
   },
   "_rebaseline_base_2026_08_10_proxyfetch": "Base-red fix (green-prs sweep, issue #9985): open-sse/utils/proxyFetch.ts 1207 > cap 1000 — new proxied-TLS fetch helper introduced by the Fal reference-image work. Owner-authorized quick rebaseline to green; structural slim tracked for v3.9.0.",
   "_rebaseline_2026_07_27_v3849_train2": "Merge-train 2 (7 PRs) — owner-approved 2026-07-27. Single entry: chatCore.ts 4955->5006 (#8595, Responses multi-turn image compaction before the context hard-reject). Genuine irreducible growth at the existing compaction chokepoint in handleChatCore — the PR adds a last-resort retry against the concrete budget plus the estimateFinalInputTokens helper, both wired at the pre-existing call site rather than a new branch. Covered by tests/unit/8560-responses-image-compaction.test.ts (4 tests).",
@@ -647,6 +646,5 @@
   "_rebaseline_2026_08_18_imageregistry_merge_train": "merge-train 2026-08-18 (owner-authorized, /merge-prs batch of 84): open-sse/config/imageRegistry.ts crossed the 1000-line new-file cap for the first time purely from combining three independent, already-legitimate provider registrations boarded in the same local merge-train — #10542 (aihorde optional-key image catalog), #10494 (gemini-web image generation), #10594 (freepik/magnific provider rename + validation). 996 on release tip -> 1019 on the train tip. Each PR individually adds a small, additive IMAGE_PROVIDERS registry entry at the existing chokepoint; none crosses the cap alone. Not modularized as part of this train's gate fix (out of scope for a merge reconciliation, not a feature change). Covered by each PR's own focused tests (aihorde-image-catalog/generation, gemini-web image tests, freepik/magnific provider tests).",
   "_rebaseline_2026_08_20_v3850_merge_train_batch1": "Merge-train batch1 (2026-08-19/20, 30 PRs boarded onto release/v3.8.50): gateways.ts 1255->1268 = PR #10722 (Token Kiosk OpenAI-compatible provider gateway catalog entry, +13 declarative lines, same god-file no-split rationale as prior gateways.ts rebaselines); chatHelpers.ts (uncapped, not previously frozen) new 1017 = PR #10797 (relay/bifrost error normalization, +23/-2, own-PR growth, existing file already near cap from accumulated chokepoint wiring per its own rebaseline history above); chatBodyAdmission.ts (uncapped) new 1005 = pre-existing base-red on the pure release tip (1004>1000 before this train boarded anything, no PR in this batch touches this file) — frozen here at its current size, not authorizing further growth. Owner-authorized rebaseline (2026-08-19 merge-prs session).",
   "_rebaseline_2026_08_20_8338_cursor_image_provider": "PR (reimplementation of #8338, @valvesss): imageRegistry.ts 1019->1033 = new cursor IMAGE_PROVIDERS entry (Cursor plan image generation via Agent CLI), +14 lines of declarative provider metadata. Same god-registry no-split rationale as prior imageRegistry/gateways rebaselines.",
-  "_rebaseline_2026_08_20_imageregistry_1034": "imageRegistry.ts 1033->1034: +1 line drift between #10842 (cursor image provider, froze at 1033) and its actual merged state on release (measured 1034) — trivial rebaseline, not a new feature.",
-  "_rebaseline_2026_08_25_11146_subscription_first_auto": "PR #11146 (@yourspraveen, subscription-first auto groupings auto/subscription+auto/thrifty): open-sse/services/autoCombo/virtualFactory.ts is a NEW file in this PR landing at 1128 lines (+2 margin) — two opt-in flat auto ids built on the established auto/best-free pattern (connectionBillingCatalog + subscriptionLadder pure functions). Frozen at merge size per owner-authorized rebaseline directive (2026-08-19, merge-batch Step 4); no further growth without split rationale."
+  "_rebaseline_2026_08_20_imageregistry_1034": "imageRegistry.ts 1033->1034: +1 line drift between #10842 (cursor image provider, froze at 1033) and its actual merged state on release (measured 1034) — trivial rebaseline, not a new feature."
 }

docs/changelog/fragments/7778.md

@@ -1 +0,0 @@
-feat(resilience): atomically enforce cumulative global, provider, and account concurrency limits

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 (353 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 (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.">
 <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; 347 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; 346 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; 347 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; 346 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>

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: 353 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: 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.">
   <desc>Static-header comparison table where each capability row fades in top to bottom; the OmniRoute column is highlighted and shows a check or a leading value in every row, while competitors show a mix of checks, partials and crosses.</desc>
   <defs>
     <pattern id="gC" width="32" height="32" patternUnits="userSpaceOnUse"><path d="M 32 0 L 0 0 0 32" fill="none" stroke="#ffffff" stroke-opacity="0.05" stroke-width="1"/></pattern>

docs/diagrams/promise-pillars.svg

@@ -1,4 +1,4 @@
-<svg viewBox="0 0 1200 540" xmlns="http://www.w3.org/2000/svg" role="img" aria-label="The OmniRoute promise: one endpoint and 353 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 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.">
   <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">353 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">350 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 353 providers in</text>
+      <text x="66" y="204" font-size="13.5" fill="#a1a1aa">Auto-fallback across 350 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>

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 353 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: 353 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 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.">
   <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">353 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">350 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>

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 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                                                                       |
+| 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      |
 
 ## Advanced Tools (11) — Phase 2
 

docs/guides/TIERS.md

@@ -24,11 +24,8 @@ it expires.
 | Antigravity / Devin Desktop         | Built-in quotas                              |
 
 **Strategy**: route here first for every request that fits the model's
-strengths. The quota tracker monitors approaching resets, and the `reset-aware`
-combo strategy prioritizes accordingly. To route Tier 1 first and only step out
-to paid tiers as quota runs out, use the `auto/thrifty` id — or `auto/subscription`
-to stay on plan-included capacity and fail closed instead. See
-[Subscription-first routing](../routing/SUBSCRIPTION_LADDER.md).
+strengths. Quota tracker monitors approaching reset; combo strategies
+`reset-aware` and `subscription` prioritize accordingly.
 
 ## Tier 2 — Cheap
 

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 353 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 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.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **353 AI providers** with automatic format translation
+- **350 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
 
-- **353-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **350-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)

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 353 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 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.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **353 AI providers** with automatic format translation
+- **350 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
 
-- **353-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **350-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)

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 353 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 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.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **353 AI providers** with automatic format translation
+- **350 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
 
-- **353-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **350-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)

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 353 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 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.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **353 AI providers** with automatic format translation
+- **350 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
 
-- **353-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **350-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)

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 353 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 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.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **353 AI providers** with automatic format translation
+- **350 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
 
-- **353-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **350-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)

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 353 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 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.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **353 AI providers** with automatic format translation
+- **350 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
 
-- **353-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **350-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)

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 353 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 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.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **353 AI providers** with automatic format translation
+- **350 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
 
-- **353-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **350-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)

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 353 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 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.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **353 AI providers** with automatic format translation
+- **350 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
 
-- **353-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **350-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)

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 353 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 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.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **353 AI providers** with automatic format translation
+- **350 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
 
-- **353-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **350-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)

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 353 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 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.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **353 AI providers** with automatic format translation
+- **350 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
 
-- **353-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **350-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)

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 353 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 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.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **353 AI providers** with automatic format translation
+- **350 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
 
-- **353-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **350-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)

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 353 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 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.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **353 AI providers** with automatic format translation
+- **350 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
 
-- **353-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **350-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)

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 353 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 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.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **353 AI providers** with automatic format translation
+- **350 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
 
-- **353-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **350-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)

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 353 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 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.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **353 AI providers** with automatic format translation
+- **350 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
 
-- **353-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **350-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)

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 353 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 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.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **353 AI providers** with automatic format translation
+- **350 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
 
-- **353-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **350-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)

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 353 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 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.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **353 AI providers** with automatic format translation
+- **350 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
 
-- **353-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **350-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)

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 353 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 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.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **353 AI providers** with automatic format translation
+- **350 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
 
-- **353-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **350-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)

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 353 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 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.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **353 AI providers** with automatic format translation
+- **350 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
 
-- **353-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **350-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)

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 353 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 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.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **353 AI providers** with automatic format translation
+- **350 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
 
-- **353-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **350-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)

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 353 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 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.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **353 AI providers** with automatic format translation
+- **350 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
 
-- **353-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **350-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)

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 353 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 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.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **353 AI providers** with automatic format translation
+- **350 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
 
-- **353-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **350-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)

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 353 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 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.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **353 AI providers** with automatic format translation
+- **350 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
 
-- **353-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **350-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)

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 353 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 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.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **353 AI providers** with automatic format translation
+- **350 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
 
-- **353-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **350-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)

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 353 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 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.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **353 AI providers** with automatic format translation
+- **350 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
 
-- **353-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **350-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)

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 353 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 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.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **353 AI providers** with automatic format translation
+- **350 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
 
-- **353-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **350-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)

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 353 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 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.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **353 AI providers** with automatic format translation
+- **350 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
 
-- **353-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **350-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)

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 353 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 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.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **353 AI providers** with automatic format translation
+- **350 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
 
-- **353-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **350-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)

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 353 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 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.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **353 AI providers** with automatic format translation
+- **350 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
 
-- **353-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **350-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)

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 353 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 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.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **353 AI providers** with automatic format translation
+- **350 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
 
-- **353-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **350-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)

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 353 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 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.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **353 AI providers** with automatic format translation
+- **350 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
 
-- **353-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **350-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)

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 353 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 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.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **353 AI providers** with automatic format translation
+- **350 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
 
-- **353-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **350-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)

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 353 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 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.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **353 AI providers** with automatic format translation
+- **350 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
 
-- **353-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **350-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)

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 353 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 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.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **353 AI providers** with automatic format translation
+- **350 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
 
-- **353-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **350-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)

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 353 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 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.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **353 AI providers** with automatic format translation
+- **350 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
 
-- **353-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **350-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)

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 353 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 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.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **353 AI providers** with automatic format translation
+- **350 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
 
-- **353-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **350-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)

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 353 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 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.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **353 AI providers** with automatic format translation
+- **350 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
 
-- **353-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **350-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)

docs/i18n/tr/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 353 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 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.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **353 AI providers** with automatic format translation
+- **350 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
 
-- **353-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **350-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)

docs/i18n/uk-UA/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 353 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 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.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **353 AI providers** with automatic format translation
+- **350 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
 
-- **353-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **350-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)

docs/i18n/ur/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 353 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 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.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **353 AI providers** with automatic format translation
+- **350 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
 
-- **353-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **350-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)

docs/i18n/vi/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 353 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 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.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **353 AI providers** with automatic format translation
+- **350 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
 
-- **353-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **350-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)

docs/i18n/zh-CN/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 353 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 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.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **353 AI providers** with automatic format translation
+- **350 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
 
-- **353-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **350-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)

docs/i18n/zh-TW/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 353 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 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.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **353 AI providers** with automatic format translation
+- **350 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
 
-- **353-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **350-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)

docs/openapi.yaml

@@ -43,8 +43,6 @@ tags:
     description: Content moderation
   - name: Rerank
     description: Document reranking
-  - name: Search
-    description: Unified web, news, and X search
   - name: Models
     description: Available model listing
   - name: Providers
@@ -1155,199 +1153,6 @@ paths:
           $ref: "#/components/responses/Unauthorized"
   # ─── Proxy Endpoints ──────────────────────────────────────────
 
-  /api/v1/search:
-    get:
-      tags: [Search]
-      summary: List search providers
-      description: Lists configured search providers and their supported search types.
-      responses:
-        "200":
-          description: Search provider catalog
-          content:
-            application/json:
-              schema:
-                type: object
-                required: [object, data]
-                properties:
-                  object:
-                    type: string
-                    const: list
-                  data:
-                    type: array
-                    items:
-                      type: object
-                      required: [id, object, created, name, search_types]
-                      properties:
-                        id:
-                          type: string
-                        object:
-                          type: string
-                          const: search_provider
-                        created:
-                          type: integer
-                        name:
-                          type: string
-                        search_types:
-                          type: array
-                          items:
-                            type: string
-                            enum: [web, news, x]
-    post:
-      tags: [Search]
-      summary: Run a unified search
-      description: >-
-        Searches the web, news, or X through a configured provider. Set `provider`
-        to `xquik-search` to use Xquik for X search. The aliases `xquik` and
-        `xquik_search` resolve to the same provider.
-      security:
-        - BearerAuth: []
-      requestBody:
-        required: true
-        content:
-          application/json:
-            schema:
-              type: object
-              required: [query]
-              properties:
-                query:
-                  type: string
-                  minLength: 1
-                  maxLength: 500
-                provider:
-                  type: string
-                  minLength: 1
-                  description: A search provider id or registered alias.
-                  examples: [xquik-search]
-                max_results:
-                  type: integer
-                  minimum: 1
-                  maximum: 100
-                  default: 5
-                search_type:
-                  type: string
-                  enum: [web, news, x]
-                  default: web
-                offset:
-                  type: integer
-                  minimum: 0
-                  default: 0
-                country:
-                  type: string
-                  maxLength: 2
-                language:
-                  type: string
-                  minLength: 2
-                  maxLength: 5
-                time_range:
-                  type: string
-                  enum: [any, hour, day, week, month, year]
-                content:
-                  type: object
-                  properties:
-                    snippet: { type: boolean, default: true }
-                    full_page: { type: boolean, default: false }
-                    format: { type: string, enum: [text, markdown], default: text }
-                    max_characters: { type: integer, minimum: 100, maximum: 100000 }
-                filters:
-                  type: object
-                  properties:
-                    include_domains:
-                      type: array
-                      maxItems: 20
-                      items: { type: string, maxLength: 253 }
-                    exclude_domains:
-                      type: array
-                      maxItems: 20
-                      items: { type: string, maxLength: 253 }
-                    safe_search: { type: string, enum: [off, moderate, strict] }
-                provider_options:
-                  type: object
-                  additionalProperties: true
-                strict_filters:
-                  type: boolean
-                  default: false
-              additionalProperties: true
-      responses:
-        "200":
-          description: Normalized search results
-          content:
-            application/json:
-              schema:
-                type: object
-                required: [id, provider, query, results, answer, usage, metrics, errors, cached]
-                properties:
-                  id:
-                    type: string
-                    pattern: ^search-
-                  provider:
-                    type: string
-                  query:
-                    type: string
-                  cached:
-                    type: boolean
-                  results:
-                    type: array
-                    items:
-                      type: object
-                      required: [title, url, snippet, position, citation]
-                      properties:
-                        title: { type: string }
-                        url: { type: string, format: uri }
-                        display_url: { type: string }
-                        snippet: { type: string }
-                        position: { type: integer, minimum: 1 }
-                        score:
-                          type: [number, "null"]
-                          minimum: 0
-                          maximum: 1
-                        published_at: { type: [string, "null"] }
-                        favicon_url: { type: [string, "null"], format: uri }
-                        citation:
-                          type: object
-                          required: [provider, retrieved_at, rank]
-                          properties:
-                            provider: { type: string }
-                            retrieved_at: { type: string, format: date-time }
-                            rank: { type: integer, minimum: 1 }
-                  answer:
-                    type: [object, "null"]
-                  usage:
-                    type: object
-                    required: [queries_used, search_cost_usd]
-                    properties:
-                      queries_used: { type: integer, minimum: 0 }
-                      search_cost_usd: { type: number, minimum: 0 }
-                      llm_tokens: { type: integer, minimum: 0 }
-                  metrics:
-                    type: object
-                    required: [response_time_ms, upstream_latency_ms, total_results_available]
-                    properties:
-                      response_time_ms: { type: number, minimum: 0 }
-                      upstream_latency_ms: { type: number, minimum: 0 }
-                      gateway_latency_ms: { type: number, minimum: 0 }
-                      total_results_available: { type: [integer, "null"], minimum: 0 }
-                  errors:
-                    type: array
-                    items:
-                      type: object
-                      required: [provider, code, message]
-                      properties:
-                        provider: { type: string }
-                        code: { type: string }
-                        message: { type: string }
-        "400":
-          description: Invalid request, provider, credentials, or search type
-        "401":
-          $ref: "#/components/responses/Unauthorized"
-        "403":
-          description: Search provider blocked by API key or security policy
-        "429":
-          description: Every eligible provider credential is rate limited
-        "500":
-          $ref: "#/components/responses/InternalError"
-        "502":
-          description: Search provider failed
-
   /api/v1/chat/completions:
     post:
       tags: [Chat]

docs/plans/7778-hierarchical-admission.md

@@ -1,23 +0,0 @@
-# #7778 hierarchical admission cleanup plan
-
-1. Lock the existing single-key semaphore contract and the new atomic multi-key
-   contract with focused tests: no partial reservations, FIFO queueing, abort,
-   timeout, queue-full, idempotent release, stats, and cleanup.
-2. Generalize the existing account semaphore in place. Keep `acquire()` as a
-   compatibility wrapper around `acquireMany()`; do not add a second scheduler
-   or a dependency.
-3. Replace the account-only acquisition in `chatCore` with one cumulative
-   global/provider/account acquisition immediately before `withRateLimit`.
-   Reacquire the whole set whenever account rotation changes the connection,
-   and retain the release through streaming completion.
-4. Extend the existing resilience settings pipeline (types, defaults,
-   normalization, schema, API response, UI, and translations) with the global
-   and provider caps. Relabel the old Bottleneck concurrency control as
-   connection/quota-scope concurrency so its real scope is explicit.
-5. Run focused tests, lint, typecheck, static checks, and the full test suite;
-   document the behavioral change in the changelog.
-
-Behavior intentionally preserved: zero/null concurrency bypasses a gate,
-account-only callers keep using `acquire()`, blocked-account controls retain
-their key format and API, and provider rate-limit queue behavior remains
-unchanged.

docs/reference/PROVIDER_REFERENCE.md

@@ -1,16 +1,16 @@
 ---
 title: "Provider Reference"
-version: 3.8.51
-lastUpdated: 2026-08-25
+version: 3.8.50
+lastUpdated: 2026-08-23
 ---
 
 # Provider Reference
 
 > **Auto-generated** from `src/shared/constants/providers.ts` — do not edit by hand.
 > Regenerate with: `npm run gen:provider-reference`
-> **Last generated:** 2026-08-25
+> **Last generated:** 2026-08-23
 
-Total providers: **353**. See category breakdown below.
+Total providers: **350**. See category breakdown below.
 
 ## Categories
 
@@ -122,7 +122,7 @@ Use the dashboard at `/dashboard/providers` to enable, configure, and test each
 | `zai-web` | `zw` | Z.ai Web | Web cookie | [link](https://chat.z.ai) | Copy the "token" value from chat.z.ai → DevTools → Application → Local Storage. Do not copy cookies; OmniRoute handles the per-request CAPTCHA through its browser transport. | — |
 | `zenmux-free` | `zmf` | ZenMux Free (Web) | Web cookie | [link](https://zenmux.ai) | Login at zenmux.ai, then export all cookies using EditThisCookie or Cookie-Editor and paste the full Cookie header string here. Refresh every ~30 days. | — |
 
-## API Key Providers (paid / paid-with-free-credits) (233)
+## API Key Providers (paid / paid-with-free-credits) (231)
 
 | ID | Alias | Name | Tags | Website | Notes |
 |----|-------|------|------|---------|-------|
@@ -342,8 +342,6 @@ Use the dashboard at `/dashboard/providers` to enable, configure, and test each
 | `vertex-partner` | `vp` | Vertex AI Partners | API key, enterprise | [link](https://cloud.google.com/vertex-ai) | Provide the same Service Account JSON used for Vertex AI partner models. |
 | `void-ai` | `void-ai` | Void AI | API key, aggregator | [link](https://voidai.app) | The public model catalog marks some models with a free plan requirement, but access is conditional and no numeric quota is confirmed. |
 | `volcengine` | `volcengine` | Volcengine | API key | [link](https://www.volcengine.com) | — |
-| `volcengine-agent-plan` | `veap` | Volcengine Ark Agent Plan | API key | [link](https://console.volcengine.com/ark/region:cn-beijing/subscription/agent-plan) | Connect your Volcano Engine account or use an Ark Agent Plan subscription API key. |
-| `volcengine-coding-plan` | `vecp` | Volcengine Ark Coding Plan | API key | [link](https://console.volcengine.com/ark/region:cn-beijing/subscription/coding-plan) | Connect your Volcano Engine account or use an Ark Coding Plan subscription API key. |
 | `voyage-ai` | `voyage` | Voyage AI | API key, embed/rerank | [link](https://www.voyageai.com) | Bearer API key for Voyage AI embeddings and rerank APIs. |
 | `wafer` | `wafer` | Wafer AI | API key | [link](https://wafer.ai) | — |
 | `wandb` | `wandb` | Weights & Biases Inference | API key | [link](https://wandb.ai) | — |
@@ -379,7 +377,7 @@ Use the dashboard at `/dashboard/providers` to enable, configure, and test each
 | `vllm` | `vllm` | vLLM | Local, self-hosted | [link](https://github.com/vllm-project/vllm) | API key optional. Configure the local vLLM OpenAI-compatible base URL (default: http://localhost:8000/v1). |
 | `xinference` | `xinference` | XInference | Local, self-hosted | [link](https://inference.readthedocs.io) | API key optional. Configure the local XInference OpenAI-compatible base URL (default: http://localhost:9997/v1). |
 
-## Search Providers (15)
+## Search Providers (14)
 
 | ID | Alias | Name | Tags | Website | Notes |
 |----|-------|------|------|---------|-------|
@@ -396,7 +394,6 @@ Use the dashboard at `/dashboard/providers` to enable, configure, and test each
 | `serper-search` | `serper-search` | Serper Search | Search | [link](https://serper.dev) | API key from serper.dev dashboard |
 | `tavily-search` | `tavily-search` | Tavily Search | Search | [link](https://tavily.com) | API key from app.tavily.com (format: tvly-...) |
 | `x-search` | `x_search` | X Search (Grok) | Search | [link](https://docs.x.ai/developers/tools/x-search) | SuperGrok OAuth (xai-oauth) or xAI API key. This is Grok X Search, not the X Developer MCP. |
-| `xquik-search` | `xquik` | Xquik X Search | Search | [link](https://docs.xquik.com) | Xquik API key (xq_...). Search is metered per returned post; the catalog estimate uses 5 results. |
 | `youcom-search` | `youcom-search` | You.com Search | Search | [link](https://you.com/business/api/) | X-API-Key from the You.com platform dashboard |
 
 ## Audio-only Providers (12)
@@ -441,7 +438,7 @@ Use the dashboard at `/dashboard/providers` to enable, configure, and test each
 
 - Catalog: [`src/shared/constants/providers.ts`](../../src/shared/constants/providers.ts)
 - Registry (per-model details): [`open-sse/config/providerRegistry.ts`](../../open-sse/config/providerRegistry.ts)
-- Executors: [`open-sse/executors/`](../../open-sse/executors/) (109 implementations)
+- Executors: [`open-sse/executors/`](../../open-sse/executors/) (108 implementations)
 - Translators: [`open-sse/translator/`](../../open-sse/translator/)
 
 ## See Also

docs/routing/SUBSCRIPTION_LADDER.md

@@ -1,182 +0,0 @@
----
-title: "Subscription-first routing"
-version: 3.8.50
-lastUpdated: 2026-08-22
----
-
-# Subscription-first routing
-
-> Two new `auto/*` ids — `auto/subscription` and `auto/thrifty`. Both are opt-in by being
-> requested: nothing routes through them unless a caller asks for the id by name, and no
-> existing pool, strategy, or default changes.
-
-## Why this exists
-
-OmniRoute already answers two cost questions, and neither is the one most operators ask.
-
-| Existing mechanism                                       | Answers                             |
-| -------------------------------------------------------- | ----------------------------------- |
-| `hidePaidModels` (`autoCombo/paidModelFilter.ts`)        | "is this model catalogued free?"    |
-| `freeAccessPolicy: "strict"` (`strictZeroCostFilter.ts`) | "can this connection ever bill me?" |
-| `quotaPreflight` (`combo/quotaExhaustionCutoff.ts`)      | "is this connection near its wall?" |
-| `budgetCap` / `budgetFallback` (`autoCombo/engine.ts`)   | "cap spend, degrade to cheapest"    |
-
-Every free-only mechanism **fails closed** — an exhausted free pool is an empty pool, never a
-step up to a paid option — and every paid-side mechanism is tier-agnostic. Neither answers:
-
-> "Use the quota I already pay for. When it runs out, either stop, or step up one rung at a
-> time through the cheapest paid options — and come back the moment it resets."
-
-## Billing is a connection fact, not a model fact
-
-`classifyTier()` (`open-sse/services/tierResolver.ts`) keys on `(provider, model)` and returns
-`free | cheap | premium` from catalog pricing. But whether a request costs incremental money
-depends on **which connection serves it**: the same model is plan-included through a Claude Code
-OAuth connection and billed per token through an API-key connection.
-
-`provider_connections.auth_type` is not a safe proxy in either direction — metered OAuth
-connections exist, and plan-included API-key connections exist (a Copilot seat token is not a
-metered API key). So billing class comes from a **curated catalog**,
-`open-sse/config/connectionBillingCatalog.ts`, hand-set from each provider's published terms —
-the same pattern `FreeModelBudget.hardStopGuaranteed` already established for free models.
-
-```ts
-type ConnectionBillingClass = "subscription" | "metered" | "keyless" | "unknown";
-type ConnectionOverageBehavior = "hard-stop" | "meters-to-paid" | "unknown";
-```
-
-Resolution order (`autoCombo/connectionBilling.ts`): the synthetic no-auth sentinel →
-`keyless`; a catalog entry matching provider **and** `authType`; a provider-wide entry;
-otherwise `unknown`. **Uncurated is not free** — `unknown` is consumed as `metered`
-everywhere, so a provider added tomorrow starts outside the subscription rung and has to be
-curated in deliberately.
-
-## The rung model
-
-Five rungs in escalation order. They differ in more than price — each has its **own**
-exhaustion signal, which is why this is not merely a sort.
-
-| #   | Rung           | Membership                                         | Exhausted when                |
-| --- | -------------- | -------------------------------------------------- | ----------------------------- |
-| 0   | `subscription` | curated `billing: "subscription"`                  | quota window at/below cutoff  |
-| 1   | `keyless`      | the synthetic no-auth path                         | connection cooldown / breaker |
-| 2   | `free`         | metered connection, `classifyTier() === "free"`    | free allowance exhausted      |
-| 3   | `cheap`        | metered connection, `classifyTier() === "cheap"`   | per-rung budget consumed      |
-| 4   | `premium`      | metered connection, `classifyTier() === "premium"` | per-rung budget consumed      |
-
-Rungs 0-2 exhaust on **quota**, which is observable and already tracked. Rungs 3-4 have no
-quota — a paid connection serves forever — so their only sane exhaustion signal is a per-rung
-**budget**. Without one, "escalate when cheap is exhausted" has no trigger.
-
-## `auto/subscription` — fail closed
-
-Pool = rung 0 only, restricted to connections whose overage is a documented `hard-stop`, each
-verified live to have quota headroom. Everything ambiguous is excluded: an uncurated provider,
-an unverifiable quota reading, a stale reading, or an overage that meters to paid.
-
-An empty pool is the **intended** answer, not a defect — the caller's existing empty-pool path
-turns it into a clear error rather than a silent, billable fallback. That is the whole promise
-of the id.
-
-`keyless` deliberately does **not** qualify: this grouping means "the plan I pay for", so a
-no-auth backend does not belong in it. Use `auto/thrifty` (or `auto/best-free`) for that.
-
-### Connection safety
-
-A candidate is not always tied to one connection — a logical candidate carries an
-`allowedConnectionIds` allowlist, and the account actually used is chosen later, at dispatch,
-by `open-sse/services/combo/autoStrategy.ts`. Both groupings therefore verify **each connection
-individually** and rewrite `allowedConnectionIds` down to exactly the surviving subset — never
-the full original list, never one arbitrarily-chosen member. Because `autoStrategy.ts` already
-enforces that array as a hard allowlist, rewriting it here makes "verified" and "actually used"
-the same set by construction. This is the same invariant, and the same reasoning, as
-[STRICT_ZERO_COST](./STRICT_ZERO_COST.md).
-
-## `auto/thrifty` — escalate one rung at a time
-
-Pool = all rungs, ordered by rung index, with exhausted candidates gated out. The `auto` engine
-still scores **within** the surviving pool: the ladder decides which rungs are in play, scoring
-decides which candidate wins inside them. Ordering is stable within a rung, so the scorer's own
-ranking is never reshuffled by this overlay.
-
-This is an ordering + gating overlay, **not** a new dispatcher: `combo.ts`'s speculative loop
-already walks targets in order and falls through on failure, so a runtime exhaustion the
-preflight did not catch still escalates to the next rung inside the same request.
-
-Where `auto/subscription` fails closed, `auto/thrifty` fails **open**: a plan-included
-connection with no usable quota reading is still tried first. Trying it costs nothing, and if
-it turns out to be exhausted the fall-through reaches the next rung anyway — whereas refusing
-to try it would send the request to a paid rung on missing telemetry, the exact outcome the
-grouping exists to avoid.
-
-## Returning to the plan after a reset
-
-Three independent things must expire before routing returns to rung 0. Fixing only one leaves
-the ladder stuck on paid rungs long after the plan refilled.
-
-1. **The quota-state cache** — `freeAccessQuota.ts` caches per `(provider, connection)` with a
-   180s TTL. A cached entry whose own `resetAt` has already passed describes a window that no
-   longer exists, so it is now treated as stale **regardless of age** and forces a refresh.
-   Without this, a plan that refilled at midnight keeps reading exhausted until the TTL happens
-   to lapse.
-2. **The ladder's own state** — there is none, by design. Rung eligibility is recomputed from
-   live quota state on every pool build; no persisted "currently on rung 3" record exists that
-   could outlive a reset and wedge routing.
-3. **The connection cooldown** — the exhausting 429 sets `rateLimitedUntil` from exponential
-   backoff, which for a plan connection can overshoot the real reset. `clampCooldownToReset()`
-   (`subscriptionLadder.ts`) narrows a cooldown to the upstream's own reset instant and can
-   never extend one. **It is implemented and tested but not yet wired**: the quota cache is
-   invalidated in `src/sse/services/auth.ts` _before_ any cooldown is written, so `resetAt`
-   must be captured earlier in that function — a change to the resilience hot path that
-   belongs in its own reviewed PR. Until then, re-entry waits out the connection cooldown
-   (which already prefers upstream `Retry-After` hints when the provider sends them).
-
-### Anti-flap
-
-A rung that just reset is re-admitted only above `reentryMinRemainingPercent` (default 5),
-while a connection already in play only has to stay above `exitCutoffPercent` (default 2,
-matching `quotaPreflight.defaultThresholdPercent`). The gap is the hysteresis band — without
-it, a connection hovering at the cutoff oscillates between rungs on consecutive requests.
-
-## Configuration
-
-Tuning only. There is deliberately **no** `enabled` flag: a toggle able to switch these off
-would leave `auto/subscription` quietly serving the full pool — paid models included — under a
-name that promises the opposite.
-
-```jsonc
-{
-  "subscriptionLadder": {
-    "exitCutoffPercent": 2,
-    "reentryMinRemainingPercent": 5,
-    "rungBudgetUsd": { "cheap": 5.0, "premium": 0 }, // 0 disables a rung outright
-  },
-}
-```
-
-Budget gating is inert until a spend resolver is wired: with no accounting available a paid
-rung is ordered but never gated. As of v3.8.51 the `rungBudgetUsd` setting is accepted by the
-schema but NOT yet enforced — treat it as reserved configuration, not an active spend cap. Rung ordering, quota-based exhaustion, and reset re-entry all
-work without it.
-
-## Composition
-
-`subscription` and `thrifty` are `AutoTier` values, so they compose with every category:
-`auto/coding:thrifty`, `auto/reasoning:subscription`, and so on. The two flat ids
-(`auto/subscription`, `auto/thrifty`) are advertised in `/v1/models` and the dashboard.
-
-Neither id is paid-tier, so `isPaidTierAutoId()` returns `false` for both and
-`auto/subscription` survives `hidePaidModels`.
-
-## Where the code lives
-
-| Concern                         | File                                                |
-| ------------------------------- | --------------------------------------------------- |
-| Curated billing facts           | `open-sse/config/connectionBillingCatalog.ts`       |
-| Classifier                      | `open-sse/services/autoCombo/connectionBilling.ts`  |
-| Rungs, both groupings, re-entry | `open-sse/services/autoCombo/subscriptionLadder.ts` |
-| Wiring into the candidate pool  | `open-sse/services/autoCombo/virtualFactory.ts`     |
-| Reset-aware cache staleness     | `open-sse/services/autoCombo/freeAccessQuota.ts`    |
-| Tier surface                    | `open-sse/services/autoCombo/suffixComposition.ts`  |
-| Advertised ids                  | `open-sse/services/autoCombo/builtinCatalog.ts`     |
-| Tests                           | `tests/unit/autoCombo/subscription-ladder.test.ts`  |

llm.txt

@@ -1,6 +1,6 @@
 # OmniRoute
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 353 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 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.
 
 ## Overview
 
@@ -277,7 +277,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **353 AI providers** with automatic format translation
+- **350 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
@@ -475,7 +475,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **353-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **350-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)

open-sse/config/connectionBillingCatalog.ts

@@ -1,143 +0,0 @@
-/**
- * Curated billing classification for provider CONNECTIONS.
- *
- * The economic tier resolver (`open-sse/services/tierResolver.ts`) answers
- * "how much does this MODEL cost per token?" — a fact about the catalog. It
- * cannot answer the question subscription-first routing actually needs:
- *
- *   "does serving this request through THIS connection cost incremental money,
- *    or is it already covered by a flat-rate plan the operator pays anyway?"
- *
- * That is a property of the credential, not the model: `claude/claude-*` is
- * plan-included through a Claude Code OAuth connection and billed per token
- * through an API-key connection — same provider, same model, opposite
- * economics.
- *
- * `provider_connections.auth_type` alone is NOT a safe proxy in either
- * direction: metered OAuth connections exist (cloud-billed OAuth), and
- * plan-included API-key connections exist (Copilot seat tokens). So this is a
- * CURATED table, hand-set from each provider's published terms — deliberately
- * the same pattern `FreeModelBudget.hardStopGuaranteed`
- * (`open-sse/config/freeModelCatalog.ts`) already established: a fact about
- * the upstream's commercial terms, never derived from `authType` and never
- * inferred from a live API response.
- *
- * Uncurated is not "free": anything absent here resolves to `unknown`, which
- * every consumer treats as `metered`. New providers therefore start OUTSIDE
- * the subscription rung and have to be curated in deliberately — the same
- * fail-safe direction STRICT_ZERO_COST uses for uncatalogued models.
- */
-
-/**
- * How a connection's upstream charges for the requests it serves.
- *
- * - `subscription` — covered by a flat-rate plan the operator already pays.
- *   Consuming its quota costs nothing incremental; the plan is a sunk cost.
- * - `metered` — pay-per-token / pay-per-credit. Every request adds spend.
- * - `keyless` — no credential exists at all, so no request can be billed by
- *   construction (the synthetic no-auth path).
- * - `unknown` — not curated. Consumed as `metered` everywhere.
- */
-export type ConnectionBillingClass = "subscription" | "metered" | "keyless" | "unknown";
-
-/**
- * What happens when a subscription plan's allowance runs out.
- *
- * - `hard-stop` — the upstream refuses further requests until the window
- *   resets. Exhaustion cannot cost money, so such a connection is admissible
- *   to the strictest "never spend a cent extra" grouping.
- * - `meters-to-paid` — the upstream keeps serving and bills the overage.
- *   Perfectly usable while quota remains, never admissible to the strict
- *   grouping.
- * - `unknown` — not established. Treated exactly like `meters-to-paid` by
- *   every consumer; it is the conservative default for a provider whose terms
- *   allow an operator to opt into usage-based billing past the plan.
- */
-export type ConnectionOverageBehavior = "hard-stop" | "meters-to-paid" | "unknown";
-
-export interface ConnectionBillingEntry {
-  /** Provider id as registered in `open-sse/config/providers/registry/`. */
-  provider: string;
-  /**
-   * Restricts the entry to connections whose `authType` matches. Omit for a
-   * provider-wide entry. A matching auth-typed entry always wins over the
-   * provider-wide one, so a provider offering both a plan-included OAuth login
-   * and a metered API key can declare both.
-   */
-  authType?: string;
-  billing: ConnectionBillingClass;
-  overage: ConnectionOverageBehavior;
-  /** Operator-visible justification for the classification. */
-  reason: string;
-}
-
-/**
- * Curated entries. Conservative by design — a provider whose terms let the
- * operator enable usage-based billing past the plan is recorded as `unknown`
- * overage, not `hard-stop`, because the strict grouping's entire promise is
- * that it cannot surprise you.
- *
- * Providers already classified free by the economic tier resolver (`kiro`,
- * `qoder`, and the rest of `LEGACY_FREE_PROVIDERS` /
- * `deriveNoAuthFreeProviders()` in `open-sse/services/tierConfig.ts`) are
- * deliberately NOT listed here: they land on the ladder's `free` rung through
- * `classifyTier()` and would only be double-claimed by an entry here.
- */
-export const CONNECTION_BILLING_CATALOG: readonly ConnectionBillingEntry[] = [
-  {
-    provider: "claude",
-    authType: "oauth",
-    billing: "subscription",
-    overage: "hard-stop",
-    reason:
-      "Claude Code OAuth serves the operator's Anthropic Pro/Max plan windows. " +
-      "Exceeding a window is refused until it resets; no per-token charge accrues.",
-  },
-  {
-    provider: "codex",
-    authType: "oauth",
-    billing: "subscription",
-    overage: "hard-stop",
-    reason:
-      "Codex OAuth serves the ChatGPT plan's included Codex quota. Exhaustion is " +
-      "refused until the plan window resets rather than billed.",
-  },
-  {
-    provider: "antigravity",
-    authType: "oauth",
-    billing: "subscription",
-    overage: "hard-stop",
-    reason:
-      "Antigravity OAuth serves built-in plan quotas that stop serving once consumed; " +
-      "OmniRoute already tracks their reset windows (see antigravityCredits.ts).",
-  },
-  {
-    provider: "cursor",
-    authType: "oauth",
-    billing: "subscription",
-    overage: "unknown",
-    reason:
-      "Cursor Pro includes a request allowance, but usage-based pricing past the plan " +
-      "can be enabled per account and OmniRoute cannot observe that setting. Recorded " +
-      "as unknown overage so the strict grouping excludes it.",
-  },
-  {
-    provider: "copilot-web",
-    authType: "apikey",
-    billing: "subscription",
-    overage: "unknown",
-    reason:
-      "GitHub Copilot is a per-seat subscription (the credential is a seat token, not a " +
-      "metered API key), but additional premium requests can be billed when the account " +
-      "opts in. Recorded as unknown overage.",
-  },
-  {
-    provider: "devin-desktop",
-    authType: "oauth",
-    billing: "subscription",
-    overage: "meters-to-paid",
-    reason:
-      "Devin Desktop draws on the plan's included ACUs and continues billing past them, " +
-      "so it is plan-included while quota remains but never overage-safe.",
-  },
-];

open-sse/config/freeModelCatalog.ts

@@ -69,31 +69,6 @@ export interface FreeModelTotals {
 
 const RECURRING = new Set<FreeModelFreeType>(["recurring-daily", "recurring-monthly", "keyless"]);
 
-/**
- * What each free-tier regime engages for "can I route here without paying?".
- * Exhaustive by construction: adding a member to `FreeModelFreeType` will not
- * compile until it is classified here. `discontinued` is the one regime a
- * provider uses to retire a free tier behind a paid key — it does NOT grant
- * free access, and the shared predicate (`isFreeModel`) must read this instead
- * of treating every catalogued id as free. `RECURRING` (above) answers a
- * different question (which regimes feed the headline token totals) and is left
- * independent on purpose — deriving it from this table would silently change
- * the homepage totals.
- */
-const FREE_REGIME_TRAITS = {
-  "recurring-daily": { grantsFreeAccess: true },
-  "recurring-monthly": { grantsFreeAccess: true },
-  "recurring-credit": { grantsFreeAccess: true },
-  "recurring-uncapped": { grantsFreeAccess: true },
-  "one-time-initial": { grantsFreeAccess: true },
-  keyless: { grantsFreeAccess: true },
-  discontinued: { grantsFreeAccess: false },
-} satisfies Record<FreeModelFreeType, { grantsFreeAccess: boolean }>;
-
-export function grantsFreeAccess(freeType: FreeModelFreeType): boolean {
-  return FREE_REGIME_TRAITS[freeType].grantsFreeAccess;
-}
-
 /**
  * Deposit-unlock boosts: a one-time small top-up that permanently raises a
  * provider's recurring free quota. Kept OUT of the steady headline and surfaced

open-sse/config/searchRegistry.ts

@@ -330,25 +330,6 @@ export const SEARCH_PROVIDERS: Record<string, SearchProviderConfig> = {
     timeoutMs: 60_000,
     cacheTTLMs: 5 * 60 * 1000,
   },
-
-  // Direct X API search through Xquik. Keep it fallback-only so the existing
-  // SuperGrok provider remains the default for search_type "x".
-  "xquik-search": {
-    id: "xquik-search",
-    name: "Xquik X Search",
-    baseUrl: "https://xquik.com/api/v1/x/tweets/search",
-    method: "GET",
-    authType: "apikey",
-    authHeader: "x-api-key",
-    costPerQuery: 0.00075,
-    freeMonthlyQuota: 0,
-    searchTypes: ["x"],
-    defaultMaxResults: 5,
-    maxMaxResults: 20,
-    timeoutMs: 15_000,
-    cacheTTLMs: 5 * 60 * 1000,
-    fallbackOnly: true,
-  },
 };
 
 /**
@@ -396,8 +377,6 @@ export const SEARCH_PROVIDER_ALIASES: Record<string, string> = {
   c7: "context7",
   x_search: "x-search",
   x: "x-search",
-  xquik: "xquik-search",
-  xquik_search: "xquik-search",
 };
 
 export function resolveSearchProviderId(providerId: string): string {

open-sse/handlers/chatCore.ts

@@ -396,7 +396,7 @@ import {
 } from "../services/rateLimitManager.ts";
 import * as localLimiterErrors from "../services/rateLimitManager/errors.ts";
 import {
-  acquireMany as acquireConcurrencyGates,
+  acquire as acquireAccountSemaphore,
   markBlocked as markAccountSemaphoreBlocked,
 } from "../services/accountSemaphore.ts";
 import { lockModel, lockModelIfPerModelQuota } from "../services/accountFallback.ts";
@@ -447,7 +447,6 @@ import { extractFacts } from "@/lib/memory/extraction";
 import { handleToolCallExecution } from "@/lib/skills/interception";
 import { MEMORY_BUILTIN_TOOL_NAMES } from "@/lib/skills/memoryBuiltins";
 import { OMNIROUTE_RESPONSE_HEADERS } from "@/shared/constants/headers";
-import { resolveProviderId } from "@/shared/constants/providers";
 import { getClaudeCodeCompatibleRequestDefaults } from "@/lib/providers/requestDefaults";
 import {
   buildClaudeCodeCompatibleRequest,
@@ -526,7 +525,6 @@ export async function handleChatCore({
   managedLease = null,
 }) {
   let { provider, model, extendedContext } = modelInfo;
-  const resilienceSettings = resolveResilienceSettings(cachedSettings);
   if (!skipResourcePressureGuard) {
     try {
       const pressureGuard = checkResourcePressureGuard();
@@ -3053,10 +3051,6 @@ export async function handleChatCore({
               connectionId: attemptConnectionId,
               credentials: execCreds,
             });
-            const canonicalProviderKey = resolveProviderId(String(provider).trim().toLowerCase());
-            const providerConcurrency =
-              resilienceSettings.providerQuotaOverrides[canonicalProviderKey]
-                ?.providerConcurrency ?? 0;
 
             trace("pre_semaphore", {
               semaphoreKey: accountSemaphoreKey,
@@ -3067,27 +3061,13 @@ export async function handleChatCore({
                 stage: "waiting_account_slot",
               });
             }
-            const releaseAccountSemaphore = await acquireConcurrencyGates(
-              [
-                {
-                  key: "global",
-                  maxConcurrency: resilienceSettings.requestQueue.globalConcurrentRequests,
-                },
-                {
-                  key: `provider:${canonicalProviderKey}`,
-                  maxConcurrency: providerConcurrency,
-                },
-                {
-                  key: accountSemaphoreKey || "",
-                  maxConcurrency: accountSemaphoreKey ? accountSemaphoreMaxConcurrency : null,
-                },
-              ],
-              {
-                timeoutMs: resilienceSettings.requestQueue.maxWaitMs,
-                maxQueueSize: resilienceSettings.requestQueue.maxQueueDepth,
-                signal: streamController.signal,
-              }
-            );
+            const releaseAccountSemaphore =
+              accountSemaphoreKey && accountSemaphoreMaxConcurrency != null
+                ? await acquireAccountSemaphore(accountSemaphoreKey, {
+                    maxConcurrency: accountSemaphoreMaxConcurrency,
+                    signal: streamController.signal,
+                  })
+                : () => {};
             trace("post_semaphore");
             updatePendingScope(pendingScope, {
               stage: "waiting_rate_limit",
@@ -3348,7 +3328,6 @@ export async function handleChatCore({
                       "ANTIGRAVITY_BYOP_ROTATION",
                       `BYOP 422 on connection ${String(byopFailedId).slice(0, 8)} → rotating to ${String(byopNextCreds.connectionId).slice(0, 8)}`
                     );
-                    releaseAccountSemaphore();
                     Object.assign(credentials, byopNextCreds);
                     antigravityByopRotationPending = true;
                     continue;

open-sse/handlers/search.ts

@@ -8,7 +8,6 @@ import { randomUUID } from "crypto";
  *   firecrawl, google-pse-search, linkup-search, searchapi-search,
  *   youcom-search, searxng-search, ollama-search, zai-search, jina-search,
  *   duckduckgo-free, x-search (Grok / SuperGrok X Search — explicit or search_type "x")
- *   and xquik-search (direct X API search — explicit or credentialed fallback)
  *
  * Request format:
  * {
@@ -29,7 +28,6 @@ import * as fcSearch from "./search/firecrawlSearch.ts";
 import { type FirecrawlSearchEnvelope } from "./search/firecrawlSearch.ts";
 import { buildJinaSearchRequest, extractJinaSearchItems } from "./search/jinaSearch.ts";
 import * as xSearch from "./search/xSearch.ts";
-import * as xquikSearch from "./search/xquikSearch.ts";
 import { freeWebSearch } from "../services/freeWebSearch.ts";
 import { saveCallLog } from "@/lib/usageDb";
 import { safeOutboundFetch } from "@/shared/network/safeOutboundFetch";
@@ -716,7 +714,6 @@ const requestBuilders: Record<string, SearchRequestBuilder> = {
   "ollama-search": buildOllamaRequest,
   "jina-search": buildJinaSearchRequest,
   "x-search": xSearch.buildXSearchRequest,
-  "xquik-search": xquikSearch.buildXquikSearchRequest,
 };
 
 function buildRequest(
@@ -1293,7 +1290,6 @@ const responseNormalizers: Record<string, SearchResponseNormalizer> = {
   "ollama-search": normalizeOllamaResponse,
   "jina-search": normalizeJinaSearchResponse,
   "x-search": normalizeXSearchResponse,
-  "xquik-search": (data) => xquikSearch.normalizeXquikSearchResponse(data, makeResult),
 };
 
 function normalizeResponse(

open-sse/handlers/search/xquikSearch.ts

@@ -1,158 +0,0 @@
-/** Xquik-backed X search for the unified search gateway. */
-
-import { z } from "zod";
-import type { SearchProviderConfig } from "../../config/searchRegistry.ts";
-import type { SearchResult } from "../search.ts";
-
-export const XQUIK_SEARCH_PROVIDER_ID = "xquik-search";
-
-export interface XquikSearchParams {
-  query: string;
-  maxResults: number;
-  token?: string;
-  timeRange?: string;
-  providerOptions?: Record<string, unknown>;
-  providerSpecificData?: Record<string, unknown>;
-}
-
-export interface XquikSearchHit {
-  title: string;
-  url: string;
-  snippet: string;
-  author?: string;
-  publishedAt?: string;
-}
-
-type MakeResult = (
-  providerId: string,
-  item: {
-    title?: string;
-    url?: string;
-    snippet?: string;
-    published_at?: string;
-    author?: string;
-    source_type?: string;
-  },
-  index: number,
-  now: string
-) => SearchResult;
-
-const X_HANDLE_RE = /^[A-Za-z0-9_]{1,15}$/;
-const TWEET_ID_RE = /^\d+$/;
-
-const XquikTweetSchema = z
-  .object({
-    id: z.string().regex(TWEET_ID_RE),
-    text: z.string(),
-    createdAt: z.string().optional(),
-    author: z
-      .object({
-        username: z.string().regex(X_HANDLE_RE),
-        name: z.string().optional(),
-      })
-      .passthrough()
-      .optional(),
-  })
-  .passthrough();
-
-const XquikSearchEnvelopeSchema = z
-  .object({
-    tweets: z.array(z.unknown()).default([]),
-  })
-  .passthrough();
-
-function getProviderSettingString(
-  params: Pick<XquikSearchParams, "providerOptions" | "providerSpecificData">,
-  key: string
-): string | undefined {
-  const option = params.providerOptions?.[key];
-  if (typeof option === "string" && option.trim()) return option.trim();
-  const configured = params.providerSpecificData?.[key];
-  if (typeof configured === "string" && configured.trim()) return configured.trim();
-  return undefined;
-}
-
-function sinceTimeForRange(timeRange: string | undefined, now = Date.now()): string | undefined {
-  const hour = 60 * 60 * 1000;
-  const durations: Record<string, number> = {
-    hour,
-    day: 24 * hour,
-    week: 7 * 24 * hour,
-    month: 30 * 24 * hour,
-    year: 365 * 24 * hour,
-  };
-  const duration = timeRange ? durations[timeRange] : undefined;
-  return duration ? new Date(now - duration).toISOString() : undefined;
-}
-
-export function buildXquikSearchRequest(
-  config: SearchProviderConfig,
-  params: XquikSearchParams
-): { url: string; init: RequestInit } {
-  const queryType = getProviderSettingString(params, "queryType") === "Top" ? "Top" : "Latest";
-  const query = new URLSearchParams({
-    q: params.query,
-    queryType,
-    limit: String(params.maxResults),
-  });
-  const sinceTime = sinceTimeForRange(params.timeRange);
-  if (sinceTime) query.set("sinceTime", sinceTime);
-
-  return {
-    url: `${config.baseUrl.replace(/\/+$/, "")}?${query}`,
-    init: {
-      method: "GET",
-      headers: {
-        Accept: "application/json",
-        ...(params.token ? { "x-api-key": params.token } : {}),
-      },
-    },
-  };
-}
-
-export function extractXquikSearchHits(data: unknown, maxResults: number): XquikSearchHit[] {
-  const envelope = XquikSearchEnvelopeSchema.safeParse(data);
-  if (!envelope.success) return [];
-
-  const hits: XquikSearchHit[] = [];
-  for (const value of envelope.data.tweets) {
-    const parsed = XquikTweetSchema.safeParse(value);
-    if (!parsed.success) continue;
-    const tweet = parsed.data;
-    const author = tweet.author?.username;
-    hits.push({
-      title: author ? `@${author}` : "X post",
-      url: author
-        ? `https://x.com/${author}/status/${tweet.id}`
-        : `https://x.com/i/status/${tweet.id}`,
-      snippet: tweet.text,
-      author,
-      publishedAt: tweet.createdAt,
-    });
-    if (hits.length >= maxResults) break;
-  }
-  return hits;
-}
-
-export function normalizeXquikSearchResponse(
-  data: unknown,
-  makeResult: MakeResult
-): { results: SearchResult[]; totalResults: number } {
-  const now = new Date().toISOString();
-  const results = extractXquikSearchHits(data, 20).map((hit, index) =>
-    makeResult(
-      XQUIK_SEARCH_PROVIDER_ID,
-      {
-        title: hit.title,
-        url: hit.url,
-        snippet: hit.snippet,
-        published_at: hit.publishedAt,
-        author: hit.author,
-        source_type: "x",
-      },
-      index,
-      now
-    )
-  );
-  return { results, totalResults: results.length };
-}

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

@@ -358,38 +358,6 @@ describe("omniroute_x_search handler (via MCP dispatch)", () => {
     expect(body.search_type).toBe("x");
     expect(body.provider).toBe("x-search");
   });
-
-  it("should route an explicit Xquik search through xquik-search", async () => {
-    mockFetch.mockResolvedValueOnce({
-      ok: true,
-      json: async () => ({
-        id: "xs2",
-        provider: "xquik-search",
-        query: "agents sdk",
-        results: [
-          {
-            title: "@openai",
-            url: "https://x.com/openai/status/1912345678901234567",
-            snippet: "Agents SDK update",
-            position: 1,
-          },
-        ],
-        cached: false,
-        usage: { queries_used: 1, search_cost_usd: 0.00015 },
-      }),
-    });
-
-    const result = await client.callTool({
-      name: "omniroute_x_search",
-      arguments: { query: "agents sdk", max_results: 5, provider: "xquik-search" },
-    });
-
-    expect(result.isError).toBeFalsy();
-    const [, options] = mockFetch.mock.calls[0];
-    const body = JSON.parse(options.body as string);
-    expect(body.search_type).toBe("x");
-    expect(body.provider).toBe("xquik-search");
-  });
 });
 
 // ── omniroute_get_health: handler dispatch tests ──────────────────────────────

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

@@ -531,17 +531,12 @@ export const xSearchInput = z.object({
     .max(20)
     .default(5)
     .describe("Maximum number of X results to return"),
-  provider: z
-    .enum(["x-search", "xquik-search"])
-    .optional()
-    .default("x-search")
-    .describe("X search backend: x-search uses xAI/SuperGrok; xquik-search uses Xquik"),
 });
 
 export const xSearchTool: McpToolDefinition<typeof xSearchInput, typeof webSearchOutput> = {
   name: "omniroute_x_search",
   description:
-    "Search X (Twitter) through OmniRoute. Uses SuperGrok / xAI server-side x_search by default, or Xquik when provider is xquik-search. Requires credentials for the selected backend. This is not web search.",
+    "Search X (Twitter) through OmniRoute using SuperGrok / xAI server-side x_search. Requires a connected xai-oauth (SuperGrok) or xAI API key. This is Grok X Search, not web search and not the X Developer Platform MCP.",
   inputSchema: xSearchInput,
   outputSchema: webSearchOutput,
   scopes: ["execute:search"],

open-sse/mcp-server/server.ts

@@ -666,11 +666,7 @@ async function handleWebSearch(args: {
   }
 }
 
-async function handleXSearch(args: {
-  query: string;
-  max_results?: number;
-  provider?: "x-search" | "xquik-search";
-}) {
+async function handleXSearch(args: { query: string; max_results?: number }) {
   const start = Date.now();
   try {
     const result = await omniRouteFetch("/v1/search", {
@@ -679,7 +675,7 @@ async function handleXSearch(args: {
         query: args.query,
         max_results: args.max_results ?? 5,
         search_type: "x",
-        provider: args.provider ?? "x-search",
+        provider: "x-search",
       }),
       signal: AbortSignal.timeout(120000),
     });

open-sse/services/accountSemaphore.ts

@@ -1,40 +1,20 @@
 /**
- * Hierarchical in-memory concurrency admission.
+ * Account Semaphore
  *
- * `acquire()` preserves the account-semaphore API. `acquireMany()` admits one
- * request only when every applicable global/provider/account gate has room.
+ * In-memory provider/account concurrency limiter keyed by provider and account.
+ * Requests beyond the configured concurrency cap wait in a FIFO queue until a slot opens,
+ * the gate is unblocked, or the queue timeout expires.
  */
+
 export interface AccountSemaphoreKeyParts {
   provider: string;
   accountKey: string;
 }
 
-export interface AcquireAccountSemaphoreOptions {
-  maxConcurrency?: number | null;
-  timeoutMs?: number;
-  signal?: AbortSignal | null;
-  maxQueueSize?: number;
-}
-
-export interface SemaphoreRequirement {
-  key: string;
-  maxConcurrency?: number | null;
-}
-
-export type AcquireManyOptions = Omit<AcquireAccountSemaphoreOptions, "maxConcurrency">;
-
-interface AcquireRequest {
-  keys: string[];
+interface QueuedAcquire {
   resolve: (release: () => void) => void;
   reject: (error: Error) => void;
-  timer: ReturnType<typeof setTimeout> | null;
-  signal: AbortSignal | null;
-  abortListener: (() => void) | null;
-  settled: boolean;
-}
-
-interface QueuedAcquire {
-  request: AcquireRequest;
+  timer: ReturnType<typeof setTimeout>;
 }
 
 interface AccountGate {
@@ -45,6 +25,13 @@ interface AccountGate {
   cleanupTimer: ReturnType<typeof setTimeout> | null;
 }
 
+export interface AcquireAccountSemaphoreOptions {
+  maxConcurrency?: number | null;
+  timeoutMs?: number;
+  signal?: AbortSignal | null;
+  maxQueueSize?: number;
+}
+
 export interface AccountSemaphoreStatsEntry {
   running: number;
   queued: number;
@@ -54,9 +41,12 @@ export interface AccountSemaphoreStatsEntry {
 
 const DEFAULT_TIMEOUT_MS = 30_000;
 const DEFAULT_MAX_QUEUE_SIZE = 20;
-const gates = new Map<string, AccountGate>();
-const queuedRequests = new Set<AcquireRequest>();
 
+const gates = new Map<string, AccountGate>();
+
+/**
+ * Build the canonical account semaphore key.
+ */
 export function buildAccountSemaphoreKey({
   provider,
   accountKey,
@@ -65,23 +55,25 @@ export function buildAccountSemaphoreKey({
 }
 
 function isBypassed(maxConcurrency?: number | null): boolean {
-  return maxConcurrency == null || !Number.isFinite(maxConcurrency) || maxConcurrency <= 0;
+  return maxConcurrency == null || maxConcurrency <= 0;
 }
 
 function createNoopReleaseFn(): () => void {
   let released = false;
+
   return () => {
     if (released) return;
     released = true;
   };
 }
 
-function ensureGate(key: string, maxConcurrency: number): AccountGate {
-  const existing = gates.get(key);
+function ensureGate(semaphoreKey: string, maxConcurrency: number): AccountGate {
+  const existing = gates.get(semaphoreKey);
   if (existing) {
     existing.maxConcurrency = maxConcurrency;
     return existing;
   }
+
   const created: AccountGate = {
     running: 0,
     maxConcurrency,
@@ -89,7 +81,7 @@ function ensureGate(key: string, maxConcurrency: number): AccountGate {
     blockedUntil: null,
     cleanupTimer: null,
   };
-  gates.set(key, created);
+  gates.set(semaphoreKey, created);
   return created;
 }
 
@@ -108,101 +100,91 @@ function clearCleanupTimer(gate: AccountGate): void {
   gate.cleanupTimer = null;
 }
 
-function cleanupGateIfIdle(key: string): void {
-  const gate = gates.get(key);
-  if (!gate || gate.running > 0 || gate.queue.length > 0 || isBlocked(gate)) return;
+function cleanupGateIfIdle(semaphoreKey: string): void {
+  const gate = gates.get(semaphoreKey);
+  if (!gate) return;
+  if (gate.running > 0 || gate.queue.length > 0 || isBlocked(gate)) return;
   clearCleanupTimer(gate);
-  gates.delete(key);
+  gates.delete(semaphoreKey);
 }
 
-function scheduleCleanup(key: string): void {
-  const gate = gates.get(key);
+function scheduleCleanup(semaphoreKey: string): void {
+  const gate = gates.get(semaphoreKey);
   if (!gate) return;
   clearCleanupTimer(gate);
+
   gate.cleanupTimer = setTimeout(() => {
     gate.cleanupTimer = null;
-    cleanupGateIfIdle(key);
+    cleanupGateIfIdle(semaphoreKey);
   }, 0);
+
   gate.cleanupTimer.unref?.();
 }
 
-function makeAbortError(signal: AbortSignal): Error {
-  if (signal.reason instanceof Error) return signal.reason;
-  const error = new Error(
-    typeof signal.reason === "string" ? signal.reason : "The operation was aborted"
-  );
-  error.name = "AbortError";
-  return error;
-}
+function drainQueue(semaphoreKey: string): void {
+  const gate = gates.get(semaphoreKey);
+  if (!gate) return;
 
-function createSemaphoreError(code: string, message: string): Error & { code: string } {
-  const error = new Error(message) as Error & { code: string };
-  error.code = code;
-  return error;
-}
-
-function removeRequest(request: AcquireRequest): void {
-  queuedRequests.delete(request);
-  if (request.timer) clearTimeout(request.timer);
-  if (request.abortListener && request.signal) {
-    request.signal.removeEventListener("abort", request.abortListener);
+  while (gate.queue.length > 0 && gate.running < gate.maxConcurrency && !isBlocked(gate)) {
+    const next = gate.queue.shift();
+    if (!next) break;
+    clearTimeout(next.timer);
+    gate.running++;
+    next.resolve(createReleaseFn(semaphoreKey));
   }
-  for (const key of request.keys) {
-    const gate = gates.get(key);
-    if (!gate) continue;
-    const index = gate.queue.findIndex((queued) => queued.request === request);
-    if (index >= 0) gate.queue.splice(index, 1);
-    if (gate.running === 0 && gate.queue.length === 0) scheduleCleanup(key);
+
+  if (gate.running === 0 && gate.queue.length === 0) {
+    scheduleCleanup(semaphoreKey);
   }
 }
 
-function canAcquire(request: AcquireRequest): boolean {
-  return request.keys.every((key) => {
-    const gate = gates.get(key);
-    return (
-      gate != null &&
-      !isBlocked(gate) &&
-      gate.running < gate.maxConcurrency &&
-      gate.queue[0]?.request === request
-    );
-  });
-}
-
-function createCompositeReleaseFn(keys: string[]): () => void {
+function createReleaseFn(semaphoreKey: string): () => void {
   let released = false;
+
   return () => {
     if (released) return;
     released = true;
-    for (const key of keys) {
-      const gate = gates.get(key);
-      if (gate && gate.running > 0) gate.running--;
+
+    const gate = gates.get(semaphoreKey);
+    if (!gate) return;
+    if (gate.running > 0) {
+      gate.running--;
     }
-    drainQueues();
-    for (const key of keys) {
-      const gate = gates.get(key);
-      if (gate && gate.running === 0 && gate.queue.length === 0) scheduleCleanup(key);
+
+    if (gate.queue.length > 0) {
+      drainQueue(semaphoreKey);
+      return;
     }
+
+    scheduleCleanup(semaphoreKey);
   };
 }
 
-function drainQueues(): void {
-  let progressed = true;
-  while (progressed) {
-    progressed = false;
-    for (const request of queuedRequests) {
-      if (request.settled || !canAcquire(request)) continue;
-      request.settled = true;
-      removeRequest(request);
-      for (const key of request.keys) gates.get(key)!.running++;
-      request.resolve(createCompositeReleaseFn(request.keys));
-      progressed = true;
-      break;
-    }
-  }
+function createSemaphoreTimeoutError(
+  semaphoreKey: string,
+  timeoutMs: number
+): Error & { code: string } {
+  const error = new Error(`Semaphore timeout after ${timeoutMs}ms for ${semaphoreKey}`) as Error & {
+    code: string;
+  };
+  error.code = "SEMAPHORE_TIMEOUT";
+  return error;
 }
 
+function makeAbortError(signal: AbortSignal): Error {
+  const reason = signal.reason;
+  if (reason instanceof Error) return reason;
+  const err = new Error(typeof reason === "string" ? reason : "The operation was aborted");
+  err.name = "AbortError";
+  return err;
+}
+
+/**
+ * Acquire a slot for a provider/model/account tuple.
+ * Returns an idempotent release function that is safe to call in finally blocks.
+ */
 export function acquire(
-  key: string,
+  semaphoreKey: string,
   {
     maxConcurrency = null,
     timeoutMs = DEFAULT_TIMEOUT_MS,
@@ -210,118 +192,146 @@ export function acquire(
     maxQueueSize = DEFAULT_MAX_QUEUE_SIZE,
   }: AcquireAccountSemaphoreOptions = {}
 ): Promise<() => void> {
-  return acquireMany([{ key, maxConcurrency }], { timeoutMs, signal, maxQueueSize });
-}
-
-/**
- * Acquire all enabled requirements as one FIFO reservation.
- *
- * Waiting never increments any gate, preventing a saturated child gate from
- * holding capacity in a parent gate.
- */
-export function acquireMany(
-  requirements: SemaphoreRequirement[],
-  {
-    timeoutMs = DEFAULT_TIMEOUT_MS,
-    signal = null,
-    maxQueueSize = DEFAULT_MAX_QUEUE_SIZE,
-  }: AcquireManyOptions = {}
-): Promise<() => void> {
-  const enabled = new Map<string, number>();
-  for (const requirement of requirements) {
-    if (isBypassed(requirement.maxConcurrency)) continue;
-    const limit = Math.trunc(requirement.maxConcurrency as number);
-    enabled.set(requirement.key, Math.min(enabled.get(requirement.key) ?? limit, limit));
-  }
-  if (enabled.size === 0) return Promise.resolve(createNoopReleaseFn());
-  if (signal?.aborted) return Promise.reject(makeAbortError(signal));
-
-  const keys = [...enabled.keys()].sort();
-  for (const key of keys) {
-    const gate = ensureGate(key, enabled.get(key)!);
-    clearCleanupTimer(gate);
-    if (maxQueueSize > 0 && gate.queue.length >= maxQueueSize) {
-      return Promise.reject(
-        createSemaphoreError(
-          "SEMAPHORE_QUEUE_FULL",
-          `Semaphore queue full (${maxQueueSize}) for ${key}`
-        )
-      );
-    }
+  if (isBypassed(maxConcurrency)) {
+    return Promise.resolve(createNoopReleaseFn());
   }
 
-  if (
-    keys.every((key) => {
-      const gate = gates.get(key)!;
-      return gate.queue.length === 0 && gate.running < gate.maxConcurrency && !isBlocked(gate);
-    })
-  ) {
-    for (const key of keys) gates.get(key)!.running++;
-    return Promise.resolve(createCompositeReleaseFn(keys));
+  if (signal?.aborted) {
+    return Promise.reject(makeAbortError(signal));
+  }
+
+  // isBypassed() above already excluded null/<=0 — ensureGate requires a plain
+  // number, but a boolean-returning helper isn't a type predicate TS can narrow on.
+  const gate = ensureGate(semaphoreKey, maxConcurrency as number);
+  clearCleanupTimer(gate);
+
+  if (gate.running < gate.maxConcurrency && !isBlocked(gate)) {
+    gate.running++;
+    return Promise.resolve(createReleaseFn(semaphoreKey));
+  }
+
+  if (gate.queue.length >= maxQueueSize) {
+    const err = new Error(`Semaphore queue full (${maxQueueSize}) for ${semaphoreKey}`) as Error & {
+      code: string;
+    };
+    err.code = "SEMAPHORE_QUEUE_FULL";
+    return Promise.reject(err);
   }
 
   return new Promise((resolve, reject) => {
-    const request: AcquireRequest = {
-      keys,
-      resolve,
-      reject,
-      timer: null,
-      signal,
-      abortListener: null,
-      settled: false,
+    let abortListener: (() => void) | null = null;
+
+    const cleanup = () => {
+      if (abortListener && signal) {
+        signal.removeEventListener("abort", abortListener);
+      }
     };
-    request.timer = setTimeout(() => {
-      if (request.settled) return;
-      request.settled = true;
-      removeRequest(request);
-      reject(
-        createSemaphoreError(
-          "SEMAPHORE_TIMEOUT",
-          `Semaphore timeout after ${timeoutMs}ms for ${keys.join(",")}`
-        )
-      );
-      drainQueues();
+
+    const timer = setTimeout(() => {
+      cleanup();
+      const nextGate = gates.get(semaphoreKey);
+      if (!nextGate) {
+        reject(createSemaphoreTimeoutError(semaphoreKey, timeoutMs));
+        return;
+      }
+
+      const queueIndex = nextGate.queue.findIndex((item) => item.timer === timer);
+      if (queueIndex !== -1) {
+        nextGate.queue.splice(queueIndex, 1);
+      }
+
+      if (nextGate.running === 0 && nextGate.queue.length === 0) {
+        scheduleCleanup(semaphoreKey);
+      }
+
+      reject(createSemaphoreTimeoutError(semaphoreKey, timeoutMs));
     }, timeoutMs);
-    request.timer.unref?.();
+
+    timer.unref?.();
+
+    const queueItem: QueuedAcquire = {
+      resolve: (release) => {
+        cleanup();
+        resolve(release);
+      },
+      reject: (error) => {
+        cleanup();
+        reject(error);
+      },
+      timer,
+    };
+
+    gate.queue.push(queueItem);
+
     if (signal) {
-      request.abortListener = () => {
-        if (request.settled) return;
-        request.settled = true;
-        removeRequest(request);
+      abortListener = () => {
+        cleanup();
+        clearTimeout(timer);
+
+        const nextGate = gates.get(semaphoreKey);
+        if (!nextGate) {
+          reject(makeAbortError(signal));
+          return;
+        }
+
+        const queueIndex = nextGate.queue.findIndex((item) => item.timer === timer);
+        if (queueIndex !== -1) {
+          nextGate.queue.splice(queueIndex, 1);
+        }
+
+        if (nextGate.running === 0 && nextGate.queue.length === 0) {
+          scheduleCleanup(semaphoreKey);
+        }
+
         reject(makeAbortError(signal));
-        drainQueues();
       };
-      signal.addEventListener("abort", request.abortListener, { once: true });
+      if (signal.aborted) {
+        abortListener();
+      } else {
+        signal.addEventListener("abort", abortListener);
+      }
     }
-    queuedRequests.add(request);
-    for (const key of keys) gates.get(key)!.queue.push({ request });
-    drainQueues();
   });
 }
 
-export function markBlocked(key: string, until: Date | string | number): void {
-  const untilMs =
-    until instanceof Date
-      ? until.getTime()
-      : typeof until === "number"
-        ? Date.now() + Math.max(0, until)
-        : new Date(until).getTime();
-  if (!Number.isFinite(untilMs) || untilMs <= Date.now()) return;
-  const gate = ensureGate(key, gates.get(key)?.maxConcurrency ?? 1);
+/**
+ * Temporarily block new acquisitions for a key while allowing in-flight requests to finish.
+ */
+export function markBlocked(semaphoreKey: string, cooldownMs: number): void {
+  const safeCooldownMs = Number.isFinite(cooldownMs) && cooldownMs > 0 ? cooldownMs : 0;
+  if (safeCooldownMs <= 0) {
+    const gate = gates.get(semaphoreKey);
+    if (!gate) return;
+    gate.blockedUntil = null;
+    drainQueue(semaphoreKey);
+    return;
+  }
+
+  const gate = gates.get(semaphoreKey) ?? ensureGate(semaphoreKey, 1);
   clearCleanupTimer(gate);
-  gate.blockedUntil = untilMs;
-}
+  gate.blockedUntil = Date.now() + safeCooldownMs;
 
-export function unblock(key: string): void {
-  const gate = gates.get(key);
-  if (!gate) return;
-  gate.blockedUntil = null;
-  drainQueues();
-  cleanupGateIfIdle(key);
+  const timer = setTimeout(() => {
+    const nextGate = gates.get(semaphoreKey);
+    if (!nextGate) return;
+    if (nextGate.blockedUntil && Date.now() >= nextGate.blockedUntil) {
+      nextGate.blockedUntil = null;
+      drainQueue(semaphoreKey);
+      if (nextGate.running === 0 && nextGate.queue.length === 0) {
+        scheduleCleanup(semaphoreKey);
+      }
+    }
+  }, safeCooldownMs + 50);
+
+  timer.unref?.();
 }
 
+/**
+ * Return the current in-memory semaphore snapshot.
+ */
 export function getStats(): Record<string, AccountSemaphoreStatsEntry> {
   const stats: Record<string, AccountSemaphoreStatsEntry> = {};
+
   for (const [key, gate] of gates) {
     stats[key] = {
       running: gate.running,
@@ -330,50 +340,48 @@ export function getStats(): Record<string, AccountSemaphoreStatsEntry> {
       blockedUntil: gate.blockedUntil ? new Date(gate.blockedUntil).toISOString() : null,
     };
   }
+
   return stats;
 }
 
+/**
+ * Check if an account semaphore key is currently at or over its max concurrency limit.
+ * Returns true if running >= maxConcurrency or blocked.
+ */
 export function isAccountSemaphoreFull(
   provider: string,
   accountKey: string,
   maxConcurrency?: number | null
 ): boolean {
   if (isBypassed(maxConcurrency)) return false;
-  const gate = gates.get(buildAccountSemaphoreKey({ provider, accountKey }));
+  const key = buildAccountSemaphoreKey({ provider, accountKey });
+  const gate = gates.get(key);
   if (!gate) return false;
   const effectiveCap = maxConcurrency ?? gate.maxConcurrency;
-  return !isBypassed(effectiveCap) && (gate.running >= effectiveCap || isBlocked(gate));
+  if (isBypassed(effectiveCap)) return false;
+  return gate.running >= effectiveCap || isBlocked(gate);
 }
 
-export function reset(key: string): void {
-  const gate = gates.get(key);
+/**
+ * Reset a single key and reject queued waiters.
+ */
+export function reset(semaphoreKey: string): void {
+  const gate = gates.get(semaphoreKey);
   if (!gate) return;
+
   clearCleanupTimer(gate);
-  const error = createSemaphoreError("SEMAPHORE_RESET", `Semaphore reset for ${key}`);
-  const rejections: AcquireRequest[] = [];
-  for (const queued of [...gate.queue]) {
-    const request = queued.request;
-    if (request.settled) continue;
-    request.settled = true;
-    removeRequest(request);
-    rejections.push(request);
+  for (const entry of gate.queue) {
+    clearTimeout(entry.timer);
+    entry.reject(new Error("Semaphore reset"));
   }
-  gates.delete(key);
-  for (const request of rejections) request.reject(error);
-  drainQueues();
+  gates.delete(semaphoreKey);
 }
 
+/**
+ * Reset all keys and reject queued waiters.
+ */
 export function resetAll(): void {
-  const error = createSemaphoreError("SEMAPHORE_RESET", "Semaphore reset");
-  const rejections: AcquireRequest[] = [];
-  for (const request of [...queuedRequests]) {
-    if (request.settled) continue;
-    request.settled = true;
-    removeRequest(request);
-    rejections.push(request);
+  for (const key of gates.keys()) {
+    reset(key);
   }
-  for (const gate of gates.values()) clearCleanupTimer(gate);
-  gates.clear();
-  queuedRequests.clear();
-  for (const request of rejections) request.reject(error);
 }

open-sse/services/autoCombo/builtinCatalog.ts

@@ -44,12 +44,6 @@ export const AUTO_TEMPLATE_VARIANTS: Record<string, AutoVariant | undefined> = {
   "auto/claude-opus": "smart",
   "auto/claude-sonnet": "coding",
   "auto/best-free": "cheap",
-  // Subscription-first routing (see `subscriptionLadder.ts`). `auto/subscription`
-  // maps to no weight variant on purpose: its pool is already restricted to
-  // plan-included connections, so the scorer should rank them on merit rather
-  // than bias toward cheap/fast within an allowance the operator already paid for.
-  "auto/subscription": undefined,
-  "auto/thrifty": "cheap",
   // Chaos mode — parallel dispatch to top-N stable models
   "auto/best-chaos": "chaos",
   "auto/chaos": "chaos",
@@ -73,18 +67,6 @@ export const AUTO_SUFFIX_VARIANTS: string[] = [
   "auto/multimodal",
 ];
 
-/**
- * Flat `auto/*` ids that carry a tier overlay even though they are not written
- * in `<category>:<tier>` form. `auto/best-free` established the pattern; the
- * two subscription-first ids reuse it so a caller can ask for the behavior
- * without also having to pick a category.
- */
-export const FLAT_TIER_OVERLAY_IDS: Record<string, AutoTier> = {
-  "auto/best-free": "free",
-  "auto/subscription": "subscription",
-  "auto/thrifty": "thrifty",
-};
-
 type ResolvedAutoVariant =
   { recognized: true; variant: AutoVariant | undefined } | { recognized: false };
 
@@ -217,9 +199,8 @@ export async function createBuiltinAutoCombo(
   }
 
   if ("variant" in spec && spec.variant !== undefined) {
-    const overlayTier = FLAT_TIER_OVERLAY_IDS[modelStr];
     const virtualCombo = await materialize(spec.variant, {
-      ...(overlayTier ? { tier: overlayTier } : {}),
+      ...(modelStr === "auto/best-free" ? { tier: "free" as const } : {}),
     });
     virtualCombo.name = modelStr;
     virtualCombo.id = modelStr;
@@ -230,11 +211,7 @@ export async function createBuiltinAutoCombo(
   // auto/best-chat, auto/pro-chat) still materialize via the default
   // (unconstrained) virtual combo rather than throwing "Unknown built-in".
   if (Object.prototype.hasOwnProperty.call(AUTO_TEMPLATE_VARIANTS, modelStr)) {
-    const overlayTier = FLAT_TIER_OVERLAY_IDS[modelStr];
-    const virtualCombo = await materialize(
-      undefined,
-      overlayTier ? { tier: overlayTier } : undefined
-    );
+    const virtualCombo = await materialize(undefined);
     virtualCombo.name = modelStr;
     virtualCombo.id = modelStr;
     return virtualCombo;

open-sse/services/autoCombo/connectionBilling.ts

@@ -1,100 +0,0 @@
-/**
- * Pure classifier over the curated connection-billing catalog
- * (`open-sse/config/connectionBillingCatalog.ts`).
- *
- * Kept dependency-light on purpose — the same constraint `paidModelFilter.ts`
- * and `strictZeroCostFilter.ts` state in their own headers — so subscription
- * routing is unit-testable without seeding the DB or the virtual factory. No
- * provider name appears in this file: a connection is classified purely from
- * the catalog plus the two facts the caller already has (`provider`,
- * `authType`), so curating a new provider needs no code change here.
- */
-import {
-  CONNECTION_BILLING_CATALOG,
-  type ConnectionBillingClass,
-  type ConnectionBillingEntry,
-  type ConnectionOverageBehavior,
-} from "@omniroute/open-sse/config/connectionBillingCatalog.ts";
-import { SYNTHETIC_NOAUTH_CONNECTION_ID } from "./resilienceCandidateFilter";
-
-/** The minimum a caller must know about a connection to classify it. */
-export interface BillableConnection {
-  provider: string;
-  /** `provider_connections.auth_type` — `oauth` / `apikey` / `cookie` / … */
-  authType?: string | null;
-  /** Connection id; the synthetic no-auth sentinel classifies as `keyless`. */
-  connectionId?: string | null;
-}
-
-export interface ConnectionBillingVerdict {
-  billing: ConnectionBillingClass;
-  overage: ConnectionOverageBehavior;
-  reason: string;
-}
-
-const UNKNOWN_VERDICT: ConnectionBillingVerdict = {
-  billing: "unknown",
-  overage: "unknown",
-  reason: "No curated billing entry for this provider/authType — assumed metered.",
-};
-
-const KEYLESS_VERDICT: ConnectionBillingVerdict = {
-  billing: "keyless",
-  overage: "hard-stop",
-  reason:
-    "Synthetic no-auth connection: no credential exists, so no request against it can be billed.",
-};
-
-/**
- * Classify one connection.
- *
- * Resolution order, first match wins:
- *   1. the synthetic no-auth sentinel → `keyless` (no credential can be billed);
- *   2. a catalog entry matching BOTH provider and `authType`;
- *   3. a provider-wide catalog entry (no `authType` declared);
- *   4. otherwise `unknown`.
- *
- * `unknown` is never treated as free by any caller — `isPlanIncluded()` below
- * returns false for it, so an uncurated provider stays outside the
- * subscription rung until someone curates it deliberately.
- */
-export function classifyConnectionBilling(
-  connection: BillableConnection,
-  catalog: readonly ConnectionBillingEntry[] = CONNECTION_BILLING_CATALOG
-): ConnectionBillingVerdict {
-  if (connection.connectionId === SYNTHETIC_NOAUTH_CONNECTION_ID) return KEYLESS_VERDICT;
-
-  const provider = connection.provider;
-  if (!provider) return UNKNOWN_VERDICT;
-
-  const providerEntries = catalog.filter((entry) => entry.provider === provider);
-  if (providerEntries.length === 0) return UNKNOWN_VERDICT;
-
-  const authType = typeof connection.authType === "string" ? connection.authType : null;
-  const authMatch = authType
-    ? providerEntries.find((entry) => entry.authType === authType)
-    : undefined;
-  const entry = authMatch ?? providerEntries.find((entry) => entry.authType === undefined);
-  if (!entry) return UNKNOWN_VERDICT;
-
-  return { billing: entry.billing, overage: entry.overage, reason: entry.reason };
-}
-
-/**
- * True when serving a request through this connection consumes an allowance
- * the operator already pays for, rather than adding incremental spend.
- * `keyless` qualifies: it costs nothing by construction.
- */
-export function isPlanIncluded(verdict: ConnectionBillingVerdict): boolean {
-  return verdict.billing === "subscription" || verdict.billing === "keyless";
-}
-
-/**
- * True when exhausting this connection's allowance cannot start costing money.
- * The strict `auto/subscription` grouping admits nothing else: an operator who
- * asked never to spend extra must not be surprised by a provider that meters
- * past the plan, nor by one whose terms simply are not established.
- */
-export function isOverageSafe(verdict: ConnectionBillingVerdict): boolean {
-  return verdict.overage === "hard-stop";
-}

open-sse/services/autoCombo/freeAccessQuota.ts

@@ -22,7 +22,6 @@ import {
 import { getCachedProviderConnections } from "@/lib/db/readCache";
 import { defaultLogger as log } from "@omniroute/open-sse/utils/logger";
 import type { FreeAccessState } from "./strictZeroCostFilter";
-import { isStateStaleForReset } from "./subscriptionLadder";
 
 const USAGE_FETCHER_PROVIDER_SET = new Set<string>(USAGE_FETCHER_PROVIDERS);
 
@@ -192,13 +191,7 @@ export function resolveFreeAccessState(
 
   const key = cacheKey(provider, connectionId);
   const entry = cache.get(key);
-  // Subscription-first routing (decision 3): an entry whose own `resetAt` has
-  // already passed describes a quota window that no longer exists, so it is
-  // stale REGARDLESS of its age. Without this, a plan that refilled at
-  // midnight keeps reading EXHAUSTED until the TTL happens to lapse, and
-  // routing stays on paid rungs for no reason. See `subscriptionLadder.ts`.
-  const resetElapsed = entry !== undefined && isStateStaleForReset(entry.state);
-  const fresh = entry && !resetElapsed && Date.now() - entry.fetchedAtMs <= ttlMs();
+  const fresh = entry && Date.now() - entry.fetchedAtMs <= ttlMs();
   if (!fresh) {
     void refresh(provider, connectionId);
   }

open-sse/services/autoCombo/strictZeroCostFilter.ts

@@ -50,7 +50,6 @@
  */
 import {
   FREE_MODEL_BUDGETS,
-  grantsFreeAccess,
   type FreeModelBudget,
 } from "@omniroute/open-sse/config/freeModelCatalog.ts";
 import { SYNTHETIC_NOAUTH_CONNECTION_ID } from "./resilienceCandidateFilter";
@@ -185,7 +184,7 @@ export function evaluateCandidateConnections(
     // entries today, so it will correctly exclude).
     if (isGenuineNoAuthCandidate) return [SYNTHETIC_NOAUTH_CONNECTION_ID];
   }
-  if (!grantsFreeAccess(budgetEntry.freeType)) return [];
+  if (budgetEntry.freeType === "discontinued") return [];
   if (isGenuineNoAuthCandidate) return []; // no-auth path but a non-keyless catalog entry: contradictory metadata, fail closed
 
   // Every remaining freeType (recurring-*, one-time-initial, a keyless entry

open-sse/services/autoCombo/subscriptionLadder.ts

@@ -1,411 +0,0 @@
-/**
- * Subscription-first routing: the rung model, its two groupings, and the
- * reset re-entry rules.
- *
- * OmniRoute already answers "is this model free?" (`paidModelFilter.ts`) and
- * "can this connection ever bill me?" (`strictZeroCostFilter.ts`). Both fail
- * CLOSED — an exhausted free pool is an empty pool, never a step up to a paid
- * option. And every paid-side mechanism (`cost-optimized`, `budgetCap`,
- * the `cost-saver` mode pack) is tier-agnostic. Neither side answers:
- *
- *   "use the quota I already pay for; when it runs out either stop, or step up
- *    one rung at a time; and come back the moment it resets."
- *
- * This module supplies both halves of that, sharing one rung model:
- *
- *   - `filterSubscriptionOnlyCandidates` — the strict grouping (`auto/subscription`).
- *     Rung 0 only, overage-safe connections only, verified live. Fails CLOSED.
- *   - `orderPoolByRung` — the escalating grouping (`auto/thrifty`). All rungs,
- *     ordered, with exhausted rungs gated out. Fails OPEN, one rung at a time.
- *
- * Design mirrors `strictZeroCostFilter.ts` deliberately: pure functions, the
- * live quota lookup injected as a synchronous resolver, no DB or network
- * import, and the SAME connection-safety invariant — every connection in a
- * candidate's `allowedConnectionIds` is verified INDIVIDUALLY and the array is
- * rewritten to exactly the surviving subset, never the full original list.
- * `autoStrategy.ts` enforces `allowedConnectionIds` as a hard allowlist before
- * selecting a connection at dispatch, so rewriting it here is sufficient to
- * make "verified" and "actually used" the same set by construction.
- */
-import {
-  classifyConnectionBilling,
-  isOverageSafe,
-  type BillableConnection,
-} from "./connectionBilling";
-import type { ConnectionBillingEntry } from "@omniroute/open-sse/config/connectionBillingCatalog.ts";
-import type { FreeAccessState } from "./strictZeroCostFilter";
-
-/**
- * Rungs in escalation order. Index is the ordering key; membership is decided
- * by `assignRung` below.
- *
- * The rungs differ in more than price — each has its OWN exhaustion signal,
- * which is why this is not just a sort:
- *
- *   subscription / keyless / free → exhausted on QUOTA (observable, tracked)
- *   cheap / premium              → exhausted on BUDGET (no quota exists; a paid
- *                                  connection serves forever)
- */
-export const RUNG_ORDER = ["subscription", "keyless", "free", "cheap", "premium"] as const;
-
-export type LadderRung = (typeof RUNG_ORDER)[number];
-
-/** Rungs whose exhaustion is observable from provider quota state. */
-const QUOTA_BEARING_RUNGS: ReadonlySet<LadderRung> = new Set<LadderRung>([
-  "subscription",
-  "keyless",
-  "free",
-]);
-
-export function rungIndex(rung: LadderRung): number {
-  return RUNG_ORDER.indexOf(rung);
-}
-
-/** A candidate as this module needs to see it — a structural subset of
- * `VirtualAutoComboCandidate` (`virtualFactory.ts`), so this file has no
- * dependency on that module's full type. */
-export interface LadderCandidate {
-  provider: string;
-  model: string;
-  connectionId: string | null;
-  allowedConnectionIds?: string[];
-}
-
-export interface LadderOptions {
-  /** Master switch. When false every exported filter is the identity function
-   * — the same off-by-default contract `filterPaidOnlyCandidates` holds. */
-  enabled: boolean;
-  /**
-   * Live allowance/quota state for ONE (provider, connection) pair, resolved
-   * from the cache in `freeAccessQuota.ts`. Synchronous by design: nothing in
-   * a candidate-pool build may await a network call.
-   *
-   * `undefined` means "no usage adapter for this provider, or nothing fresh
-   * cached". The two groupings interpret that OPPOSITELY on purpose — see
-   * `admitUnknownQuota` below.
-   */
-  resolveFreeAccessState: (provider: string, connectionId: string) => FreeAccessState | undefined;
-  /**
-   * `authType` for a connection id (`provider_connections.auth_type`), needed
-   * to classify billing. Unknown ids resolve to `null` → the provider-wide
-   * catalog entry, or `unknown` billing.
-   */
-  resolveAuthType: (connectionId: string) => string | null;
-  /** Economic tier of a (provider, model) pair — `classifyTier()` in
-   * production, injected so this module needs no registry/pricing import. */
-  resolveEconomicTier: (provider: string, model: string) => "free" | "cheap" | "premium";
-  /**
-   * Remaining-percent at or below which a quota-bearing connection counts as
-   * exhausted. Default 2, matching `quotaPreflight.defaultThresholdPercent`
-   * (`src/lib/resilience/settings/types.ts`) so the two agree.
-   */
-  exitCutoffPercent?: number;
-  /**
-   * Remaining-percent a quota-bearing connection must EXCEED to be re-admitted
-   * after having been exhausted. Strictly greater than `exitCutoffPercent`;
-   * the gap is the hysteresis band that stops a connection hovering at the
-   * cutoff from oscillating between rungs on consecutive requests. Default 5.
-   */
-  reentryMinRemainingPercent?: number;
-  /** Max age of a `FreeAccessState.checkedAt` before it is treated as stale. */
-  maxStateAgeMs: number;
-  /**
-   * Whether a connection with no usable quota reading is admitted.
-   *
-   *   - `auto/thrifty` passes TRUE: trying a plan-included connection costs
-   *     nothing, and if it turns out to be exhausted the dispatcher's
-   *     fall-through reaches the next rung anyway. Refusing to try it would
-   *     send a request to a PAID rung on missing telemetry — the exact
-   *     outcome the grouping exists to avoid.
-   *   - `auto/subscription` passes FALSE: its promise is that no request can
-   *     cost extra, and an unverifiable connection cannot support that promise.
-   */
-  admitUnknownQuota: boolean;
-  /**
-   * Budget consumed so far on a paid rung, in USD, for the operator's current
-   * budget window. `null`/`undefined` means no spend accounting is available,
-   * in which case paid rungs are NOT budget-gated (they still order after
-   * every plan-included rung). See the spec's open question on the ledger.
-   */
-  resolveRungSpendUsd?: (rung: LadderRung) => number | null;
-  /** Per-rung budget in USD. A rung mapped to 0 is disabled outright. */
-  rungBudgetUsd?: Partial<Record<LadderRung, number>>;
-  /** `now` injection for deterministic tests. */
-  now?: () => number;
-  /** Catalog override for tests; production callers never pass this. */
-  catalog?: readonly ConnectionBillingEntry[];
-}
-
-const DEFAULT_EXIT_CUTOFF_PERCENT = 2;
-const DEFAULT_REENTRY_MIN_REMAINING_PERCENT = 5;
-
-/**
- * Which rung a specific (candidate, connection) pair belongs to.
- *
- * Billing class decides first because it is the fact that actually determines
- * whether money moves; only a genuinely metered connection falls through to
- * the model's economic tier. `unknown` billing is metered by definition
- * (`connectionBilling.ts`), so an uncurated provider lands on a paid rung
- * rather than silently joining the subscription rung.
- */
-export function assignRung(
-  candidate: Pick<LadderCandidate, "provider" | "model">,
-  connection: BillableConnection,
-  options: Pick<LadderOptions, "resolveEconomicTier" | "catalog">
-): LadderRung {
-  const verdict = classifyConnectionBilling(connection, options.catalog);
-  if (verdict.billing === "subscription") return "subscription";
-  if (verdict.billing === "keyless") return "keyless";
-  return options.resolveEconomicTier(candidate.provider, candidate.model);
-}
-
-/**
- * Is this connection's plan allowance usable right now?
- *
- * `hasBeenExhausted` selects which side of the hysteresis band applies: a
- * connection that is currently in play only has to stay above the exit cutoff,
- * while one that already dropped out has to climb back above the (higher)
- * re-entry threshold before it is admitted again.
- */
-export function isQuotaUsable(
-  state: FreeAccessState | undefined,
-  options: Pick<
-    LadderOptions,
-    | "exitCutoffPercent"
-    | "reentryMinRemainingPercent"
-    | "maxStateAgeMs"
-    | "admitUnknownQuota"
-    | "now"
-  >,
-  hasBeenExhausted = false
-): boolean {
-  if (!state) return options.admitUnknownQuota;
-  if (state.status === "EXHAUSTED") return false;
-  if (state.status === "UNKNOWN") return options.admitUnknownQuota;
-
-  const now = (options.now ?? Date.now)();
-  const checkedAtMs = Date.parse(state.checkedAt);
-  if (!Number.isFinite(checkedAtMs) || now - checkedAtMs > options.maxStateAgeMs) {
-    return options.admitUnknownQuota;
-  }
-
-  if (state.remainingFreeAllowance === null) return options.admitUnknownQuota;
-
-  const exitCutoff = options.exitCutoffPercent ?? DEFAULT_EXIT_CUTOFF_PERCENT;
-  const reentryFloor = Math.max(
-    options.reentryMinRemainingPercent ?? DEFAULT_REENTRY_MIN_REMAINING_PERCENT,
-    exitCutoff
-  );
-  const threshold = hasBeenExhausted ? reentryFloor : exitCutoff;
-  return state.remainingFreeAllowance > threshold;
-}
-
-/**
- * Decision 3 — re-entry after a plan quota resets.
- *
- * A cached state whose own `resetAt` has already passed describes a window
- * that no longer exists. Waiting out the cache TTL before re-reading it is
- * pure lag on the single transition subscription-first routing cares most
- * about, so such an entry is stale REGARDLESS of its age.
- *
- * Consumed by `freeAccessQuota.ts`, which owns the cache; kept here so the
- * rule sits with the rest of the ladder's semantics and is testable without
- * touching the cache.
- */
-export function isStateStaleForReset(
-  state: Pick<FreeAccessState, "resetAt"> | undefined,
-  now: number = Date.now()
-): boolean {
-  if (!state?.resetAt) return false;
-  const resetAtMs = Date.parse(state.resetAt);
-  if (!Number.isFinite(resetAtMs)) return false;
-  return resetAtMs <= now;
-}
-
-/**
- * Decision 3, second half — never hold a plan-included connection in cooldown
- * past the moment its own upstream says the quota is back.
- *
- * The exhausting 429 sets `rateLimitedUntil` from exponential backoff
- * (`baseCooldownMs * 2 ** failureIndex`, `src/sse/services/auth.ts`), which for
- * a subscription connection routinely overshoots the real reset — leaving
- * routing stuck on paid rungs long after the plan refilled.
- *
- * This only ever NARROWS a cooldown, and only when the upstream itself
- * supplied the reset instant. An absent, unparseable, or already-past
- * `resetAt` returns the original cooldown untouched.
- */
-export function clampCooldownToReset(
-  cooldownMs: number,
-  resetAt: string | null | undefined,
-  now: number = Date.now()
-): number {
-  if (!resetAt) return cooldownMs;
-  const resetAtMs = Date.parse(resetAt);
-  if (!Number.isFinite(resetAtMs)) return cooldownMs;
-  const untilResetMs = resetAtMs - now;
-  if (untilResetMs <= 0) return cooldownMs;
-  return Math.min(cooldownMs, untilResetMs);
-}
-
-/** True when a paid rung has consumed its configured budget for the window. */
-export function isRungBudgetExhausted(rung: LadderRung, options: LadderOptions): boolean {
-  const budget = options.rungBudgetUsd?.[rung];
-  if (budget === undefined) return false;
-  if (budget <= 0) return true; // explicitly disabled
-  const spent = options.resolveRungSpendUsd?.(rung);
-  if (spent === null || spent === undefined) return false; // no accounting → not gated
-  return spent >= budget;
-}
-
-/**
- * Connections on a candidate that are usable right now, paired with the rung
- * each one sits on. Quota-bearing rungs are verified per connection; paid
- * rungs have nothing per-connection to verify (they are gated per rung).
- */
-function evaluateConnections(
-  candidate: LadderCandidate,
-  options: LadderOptions,
-  accept: (rung: LadderRung) => boolean
-): { rung: LadderRung; connectionIds: string[] } | null {
-  const connectionIds = candidate.connectionId
-    ? [candidate.connectionId]
-    : (candidate.allowedConnectionIds ?? []);
-  if (connectionIds.length === 0) return null;
-
-  let bestRung: LadderRung | null = null;
-  const usable: string[] = [];
-
-  for (const connectionId of connectionIds) {
-    const rung = assignRung(
-      candidate,
-      {
-        provider: candidate.provider,
-        authType: options.resolveAuthType(connectionId),
-        connectionId,
-      },
-      options
-    );
-    if (!accept(rung)) continue;
-
-    if (QUOTA_BEARING_RUNGS.has(rung)) {
-      const state = options.resolveFreeAccessState(candidate.provider, connectionId);
-      if (!isQuotaUsable(state, options)) continue;
-    } else if (isRungBudgetExhausted(rung, options)) {
-      continue;
-    }
-
-    usable.push(connectionId);
-    // A candidate reachable through several accounts is represented by its
-    // CHEAPEST usable rung: that is the rung a request through it would
-    // actually land on once dispatch picks from the surviving allowlist.
-    if (bestRung === null || rungIndex(rung) < rungIndex(bestRung)) bestRung = rung;
-  }
-
-  if (usable.length === 0 || bestRung === null) return null;
-  return { rung: bestRung, connectionIds: usable };
-}
-
-/** Rewrite a candidate's connection allowlist to the verified subset, keeping
- * the identity-when-nothing-changed contract the sibling filters hold. */
-function withVerifiedConnections<T extends LadderCandidate>(
-  candidate: T,
-  connectionIds: string[]
-): { candidate: T; changed: boolean } {
-  if (candidate.connectionId !== null) return { candidate, changed: false };
-  const original = candidate.allowedConnectionIds ?? [];
-  const isSameSet =
-    original.length === connectionIds.length && connectionIds.every((id) => original.includes(id));
-  if (isSameSet) return { candidate, changed: false };
-  return { candidate: { ...candidate, allowedConnectionIds: connectionIds }, changed: true };
-}
-
-/**
- * `auto/subscription` — the strict grouping. Keeps only candidates servable by
- * a plan-included connection whose overage is a documented hard stop, with
- * live quota headroom verified per connection.
- *
- * Fails CLOSED in every ambiguous case: uncurated provider, unverifiable
- * quota, or an overage that meters to paid. An empty result is the correct,
- * intended answer for an operator who asked never to spend extra — the
- * caller's existing empty-pool path handles it, exactly as `hidePaidModels`
- * already does.
- */
-export function filterSubscriptionOnlyCandidates<T extends LadderCandidate>(
-  pool: T[],
-  options: LadderOptions
-): T[] {
-  if (!options.enabled) return pool;
-
-  const strictOptions: LadderOptions = { ...options, admitUnknownQuota: false };
-  const kept: T[] = [];
-  let changed = false;
-
-  for (const candidate of pool) {
-    const connectionIds = candidate.connectionId
-      ? [candidate.connectionId]
-      : (candidate.allowedConnectionIds ?? []);
-
-    const safe = connectionIds.filter((connectionId) => {
-      const connection: BillableConnection = {
-        provider: candidate.provider,
-        authType: options.resolveAuthType(connectionId),
-        connectionId,
-      };
-      const verdict = classifyConnectionBilling(connection, options.catalog);
-      // `keyless` is plan-included in the ladder's sense but is NOT a
-      // subscription: this grouping is "the plan I pay for", so a no-auth
-      // backend does not belong in it.
-      if (verdict.billing !== "subscription") return false;
-      if (!isOverageSafe(verdict)) return false;
-      const state = strictOptions.resolveFreeAccessState(candidate.provider, connectionId);
-      return isQuotaUsable(state, strictOptions);
-    });
-
-    if (safe.length === 0) {
-      changed = true;
-      continue;
-    }
-    const result = withVerifiedConnections(candidate, safe);
-    if (result.changed) changed = true;
-    kept.push(result.candidate);
-  }
-
-  return changed ? kept : pool;
-}
-
-/**
- * `auto/thrifty` — the escalating grouping. Returns the pool ordered by rung,
- * with candidates whose every connection is exhausted (quota) or whose rung is
- * budget-exhausted removed.
- *
- * Ordering only — the `auto` engine still scores WITHIN the surviving pool, so
- * this decides which rungs are in play, not which candidate wins on one. The
- * combo dispatcher already walks targets in order and falls through on
- * failure, so a runtime exhaustion the preflight did not catch still escalates
- * to the next rung inside the same request.
- *
- * Rung eligibility is recomputed from live state on every pool build and
- * nothing is persisted: there is deliberately no sticky "currently on rung 3"
- * record that could outlive a quota reset and wedge routing on paid rungs.
- */
-export function orderPoolByRung<T extends LadderCandidate>(pool: T[], options: LadderOptions): T[] {
-  if (!options.enabled) return pool;
-
-  const ranked: Array<{ candidate: T; rung: LadderRung; order: number }> = [];
-  for (const [order, candidate] of pool.entries()) {
-    const evaluated = evaluateConnections(candidate, options, () => true);
-    if (!evaluated) continue;
-    const result = withVerifiedConnections(candidate, evaluated.connectionIds);
-    ranked.push({ candidate: result.candidate, rung: evaluated.rung, order });
-  }
-
-  ranked.sort((a, b) => {
-    const byRung = rungIndex(a.rung) - rungIndex(b.rung);
-    // Stable within a rung: preserve the pool's incoming order so the auto
-    // scorer's own ranking is not reshuffled by this overlay.
-    return byRung !== 0 ? byRung : a.order - b.order;
-  });
-
-  return ranked.map((entry) => entry.candidate);
-}

open-sse/services/autoCombo/suffixComposition.ts

@@ -23,20 +23,7 @@ import { isVisionModelId } from "@/shared/constants/visionModels";
 import { isVisionBridgeForcedModel } from "@/shared/constants/visionBridgeDefaults";
 
 export type AutoCategory = "coding" | "reasoning" | "vision" | "chat" | "multimodal";
-export type AutoTier =
-  | "fast"
-  | "cheap"
-  | "floor"
-  | "free"
-  | "reliable"
-  | "pro"
-  // Subscription-first routing. Unlike every tier above, these two narrow by
-  // the CONNECTION's billing class, not the model's price — so they are
-  // applied in `virtualFactory.ts` against live connection state rather than
-  // by `buildAutoCandidateFilter` below, which only sees (provider, model).
-  // See `subscriptionLadder.ts` and `docs/routing/SUBSCRIPTION_LADDER.md`.
-  | "subscription"
-  | "thrifty";
+export type AutoTier = "fast" | "cheap" | "floor" | "free" | "reliable" | "pro";
 
 export const AUTO_CATEGORIES: readonly AutoCategory[] = [
   "coding",
@@ -52,8 +39,6 @@ export const AUTO_TIERS: readonly AutoTier[] = [
   "free",
   "reliable",
   "pro",
-  "subscription",
-  "thrifty",
 ];
 
 const CATEGORY_SET = new Set<string>(AUTO_CATEGORIES);
@@ -99,9 +84,6 @@ export function tierToWeightVariant(tier?: AutoTier): AutoVariant | "reliability
       return "fast";
     case "cheap":
     case "floor":
-    // The ladder already orders plan-included rungs first; within a rung it
-    // should still lean cheap rather than reach for the most expensive model.
-    case "thrifty":
       return "cheap";
     case "reliable":
       return "reliability";
@@ -136,7 +118,8 @@ export function buildAutoCandidateFilter(
       }
       try {
         const caps = getResolvedModelCapabilities({ provider: c.provider, model: c.model });
-        const capable = caps.supportsVision === true || isVisionModelId(c.model);
+        const capable =
+          caps.supportsVision === true || isVisionModelId(c.model);
         if (!capable) return false;
         // #vison-pool: registry entries whose catalog OVERSTATES vision support
         // (opencode-go/opencode-zen/tokenrouter — the backend models are text-only)

open-sse/services/autoCombo/virtualFactory.ts

@@ -28,11 +28,6 @@ import { buildFamilyCandidateFilter, type ModelFamily } from "./modelFamily";
 import { getHiddenModelsByProvider } from "@/models";
 import { getSyncedAvailableModelsByConnection, getCustomModels } from "@/lib/db/models";
 import { filterPaidOnlyCandidates } from "./paidModelFilter";
-import {
-  filterSubscriptionOnlyCandidates,
-  orderPoolByRung,
-  type LadderOptions,
-} from "./subscriptionLadder";
 import { filterStrictZeroCostCandidates, filterTosAvoidCandidates } from "./strictZeroCostFilter";
 import { resolveFreeAccessState } from "./freeAccessQuota";
 import { isModelExcludedByConnection } from "@/domain/connectionModelRules";
@@ -150,98 +145,6 @@ type VirtualAutoCombo = AutoComboConfig & {
 export interface PreparedVirtualAutoComboInputs {
   readonly regularCandidates: readonly VirtualAutoComboCandidate[];
   readonly familyCandidates: readonly VirtualAutoComboCandidate[];
-  /**
-   * `provider_connections.auth_type` per connection id. Subscription-first
-   * routing classifies billing per CONNECTION (`connectionBilling.ts`), and
-   * the candidate pool only carries connection ids — so the auth types are
-   * captured here, during the one bulk connection read this function already
-   * does, instead of re-reading the DB per pool narrowing.
-   */
-  readonly authTypeByConnectionId?: ReadonlyMap<string, string | null>;
-  /** Operator settings for the subscription ladder; absent = feature off. */
-  readonly subscriptionLadder?: SubscriptionLadderSettings;
-}
-
-/**
- * Operator-facing knobs for subscription-first routing. Mirrors the Zod shape
- * in `src/shared/validation/settingsSchemas.ts`.
- *
- * Deliberately TUNING ONLY — there is no `enabled` flag here. `auto/subscription`
- * and `auto/thrifty` are new ids that nothing routes through unless a caller
- * asks for them by name, so requesting the id IS the opt-in. A settings toggle
- * that could switch them off would be actively dangerous: it would leave an id
- * whose whole promise is "plan-included only" quietly serving the full pool,
- * paid models included.
- */
-export interface SubscriptionLadderSettings {
-  exitCutoffPercent?: number;
-  reentryMinRemainingPercent?: number;
-  rungBudgetUsd?: Record<string, number>;
-  /** Staleness bound for a cached quota reading, derived from the existing
-   * `autoRefreshProviderQuotaInterval` exactly as STRICT_ZERO_COST does. */
-  maxStateAgeMs: number;
-}
-
-function readSubscriptionLadderSettings(
-  settings: Record<string, unknown>
-): SubscriptionLadderSettings {
-  const maxStateAgeMs = (Number(settings.autoRefreshProviderQuotaInterval) || 180) * 1000;
-  const raw = settings.subscriptionLadder;
-  if (!raw || typeof raw !== "object") return { maxStateAgeMs };
-  const value = raw as Record<string, unknown>;
-  const numeric = (key: string): number | undefined =>
-    typeof value[key] === "number" && Number.isFinite(value[key] as number)
-      ? (value[key] as number)
-      : undefined;
-  const exitCutoffPercent = numeric("exitCutoffPercent");
-  const reentryMinRemainingPercent = numeric("reentryMinRemainingPercent");
-  return {
-    maxStateAgeMs,
-    ...(exitCutoffPercent === undefined ? {} : { exitCutoffPercent }),
-    ...(reentryMinRemainingPercent === undefined ? {} : { reentryMinRemainingPercent }),
-    ...(value.rungBudgetUsd && typeof value.rungBudgetUsd === "object"
-      ? { rungBudgetUsd: value.rungBudgetUsd as Record<string, number> }
-      : {}),
-  };
-}
-
-/**
- * Build the injected dependencies the pure ladder module needs. Everything it
- * touches is resolved here — the live quota cache, connection auth types, and
- * the economic tier resolver — so `subscriptionLadder.ts` itself stays free of
- * DB, network, and registry imports.
- */
-function buildLadderOptions(
-  prepared: PreparedVirtualAutoComboInputs,
-  tier: "subscription" | "thrifty"
-): LadderOptions {
-  const tuning = prepared.subscriptionLadder;
-  const authTypes = prepared.authTypeByConnectionId;
-  return {
-    enabled: true,
-    resolveFreeAccessState,
-    resolveAuthType: (connectionId: string) => authTypes?.get(connectionId) ?? null,
-    resolveEconomicTier: (provider: string, model: string) => {
-      try {
-        const resolved = classifyTier(provider, model).tier;
-        return resolved === "free" || resolved === "premium" ? resolved : "cheap";
-      } catch {
-        // Same conservative default `safeClassifyTier` uses in suffixComposition.
-        return "cheap";
-      }
-    },
-    maxStateAgeMs: tuning?.maxStateAgeMs ?? 180_000,
-    // The two groupings read a missing quota reading OPPOSITELY on purpose —
-    // see `LadderOptions.admitUnknownQuota`.
-    admitUnknownQuota: tier === "thrifty",
-    ...(tuning?.exitCutoffPercent === undefined
-      ? {}
-      : { exitCutoffPercent: tuning.exitCutoffPercent }),
-    ...(tuning?.reentryMinRemainingPercent === undefined
-      ? {}
-      : { reentryMinRemainingPercent: tuning.reentryMinRemainingPercent }),
-    ...(tuning?.rungBudgetUsd ? { rungBudgetUsd: tuning.rungBudgetUsd } : {}),
-  };
 }
 
 function toExpiryMs(value: unknown): number | null {
@@ -753,15 +656,8 @@ export async function prepareVirtualAutoComboInputs(
   const regularCandidates = buildPreparedPool(false);
   // #6453/#8183: family selectors bypass the reliability-curated no-auth allowlist.
   const familyCandidates = buildPreparedPool(true);
-  // Subscription-first routing inputs, captured from the connection read above
-  // so no later stage has to touch the DB again.
-  const authTypeByConnectionId = new Map<string, string | null>();
-  for (const conn of connections) {
-    authTypeByConnectionId.set(conn.id, typeof conn.authType === "string" ? conn.authType : null);
-  }
-  const subscriptionLadder = readSubscriptionLadderSettings(settings);
   if (!options.includeResolvedCapabilities) {
-    return { regularCandidates, familyCandidates, authTypeByConnectionId, subscriptionLadder };
+    return { regularCandidates, familyCandidates };
   }
 
   // One uninterrupted bulk read of all three capability tables for this prepare only.
@@ -775,8 +671,6 @@ export async function prepareVirtualAutoComboInputs(
   return {
     regularCandidates: await attachPreparedCapabilityValues(regularCandidates, capabilityState),
     familyCandidates: await attachPreparedCapabilityValues(familyCandidates, capabilityState),
-    authTypeByConnectionId,
-    subscriptionLadder,
   };
 }
 
@@ -948,32 +842,6 @@ export async function createVirtualAutoComboFromPrepared(
     }
   }
 
-  // Subscription-first routing (`auto/subscription`, `auto/thrifty`). Applied
-  // AFTER the category/tier narrowing above because, unlike every other tier,
-  // these two select on the connection's billing class and its live quota
-  // state rather than on the model's catalog price — see
-  // `subscriptionLadder.ts` and `docs/routing/SUBSCRIPTION_LADDER.md`.
-  if (spec?.tier === "subscription" || spec?.tier === "thrifty") {
-    const ladderOptions = buildLadderOptions(prepared, spec.tier);
-    const beforeCount = effectivePool.length;
-    effectivePool =
-      spec.tier === "subscription"
-        ? filterSubscriptionOnlyCandidates(effectivePool, ladderOptions)
-        : orderPoolByRung(effectivePool, ladderOptions);
-    if (spec.tier === "subscription" && effectivePool.length === 0 && beforeCount > 0) {
-      // Intended, not a defect: the operator asked for plan-included capacity
-      // only, and right now there is none with verified headroom. Failing
-      // closed here is the entire promise of the id — the caller's existing
-      // empty-pool path turns it into a clear error rather than a silent,
-      // billable fallback.
-      warnEmptyAutoPoolOnce(
-        "auto/subscription",
-        "auto/subscription: no plan-included connection has verified quota headroom; " +
-          "returning an empty pool rather than falling back to paid capacity."
-      );
-    }
-  }
-
   let weights: ScoringWeights = { ...DEFAULT_WEIGHTS };
   let explorationRate = 0.05; // Default exploration rate
   let routerStrategy = "lkgp"; // All auto variants use LKGP

open-sse/services/combo.ts

@@ -926,9 +926,6 @@ async function handleComboChatInner({
   if (activeNativeTurnPin) {
     orderedTargets = applyNativeCodexTurnPin(orderedTargets, activeNativeTurnPin);
     if (orderedTargets.length === 0) {
-      // #11371: quota-share ordering already reserved a winner slot; release it on
-      // this early exit (idempotent).
-      targetResolution.quotaShareRelease?.();
       return errorResponse(
         409,
         "The pinned native Codex turn target is no longer available; the turn cannot be moved to another provider"
@@ -956,8 +953,6 @@ async function handleComboChatInner({
     // no-target failures (silent-stop fix). Threshold of 3 prevents a one-off account
     // wipe from destroying the prompt-cache pin benefit on the next request.
     recordComboFailure(effectiveSessionId, combo.name);
-    // #11371: same early-exit release as the pinned-turn path above.
-    targetResolution.quotaShareRelease?.();
     return errorResponseWithComboDiagnostics(
       404,
       "Combo has no executable targets",
@@ -2846,9 +2841,6 @@ async function handleComboChatInner({
     return await dispatchWithCooldownRetry();
   } finally {
     quotaShareConcurrencyRelease?.();
-    // #11371: release the in-flight slot quota-share ordering reserved for its
-    // winner — the counter must not leak monotonically upward across requests.
-    targetResolution.quotaShareRelease?.();
     // G2: Clean up candidate registry to prevent unbounded memory growth.
     _unregisterExecutionCandidates(_registeredExecutionKeys);
   }

open-sse/services/combo/applyStrategyOrdering.ts

@@ -20,21 +20,6 @@ import {
 } from "./targetSorters.ts";
 import type { ComboLike, ComboLogger, ResolvedComboTarget } from "./types.ts";
 
-/**
- * Result of {@link applyStrategyOrdering}.
- *
- * `quotaShareRelease` carries the idempotent release for the in-flight slot that
- * quota-share ordering reserves for its winner (#11371). It is non-null only when
- * the `quota-share` strategy ran; every other strategy leaves it null. The caller
- * MUST invoke it exactly once when the request settles — selection reserves the
- * slot, so dropping the callback leaks the counter monotonically upward and
- * degenerates P2C into "fewest lifetime dispatches".
- */
-export interface ApplyStrategyOrderingResult {
-  orderedTargets: ResolvedComboTarget[];
-  quotaShareRelease: (() => void) | null;
-}
-
 export interface ApplyStrategyOrderingDeps {
   combo: ComboLike;
   config: Record<string, unknown>;
@@ -60,10 +45,9 @@ export async function applyStrategyOrdering(
   strategy: string,
   initialOrderedTargets: ResolvedComboTarget[],
   deps: ApplyStrategyOrderingDeps
-): Promise<ApplyStrategyOrderingResult> {
+): Promise<ResolvedComboTarget[]> {
   const { combo, config, body, log, apiKeyAllowedConnections, sessionKey } = deps;
   let orderedTargets = initialOrderedTargets;
-  let quotaShareRelease: (() => void) | null = null;
 
   if (strategy === "lkgp") {
     try {
@@ -245,18 +229,14 @@ export async function applyStrategyOrdering(
     const qsModel =
       typeof body?.model === "string" ? body.model : (orderedTargets[0]?.modelStr ?? "");
     const qsMaxConcurrent = await resolveMaxConcurrentByConnection(orderedTargets);
-    const qsSelection = selectQuotaShareTarget(orderedTargets, combo.name, qsModel, Date.now(), {
+    orderedTargets = selectQuotaShareTarget(orderedTargets, combo.name, qsModel, Date.now(), {
       maxConcurrentByConnection: qsMaxConcurrent,
-    });
-    orderedTargets = qsSelection.orderedTargets;
-    // #11371: the reservation made inside selectQuotaShareTarget must outlive this
-    // call — hand the release to the host so it can fire it when the request settles.
-    quotaShareRelease = qsSelection.decrementInflight;
+    }).orderedTargets;
     log.info(
       "COMBO",
       `Quota-share ordering: ${orderedTargets[0]?.modelStr}${orderedTargets[0]?.connectionId ? ` (${orderedTargets[0].connectionId})` : ""} selected (DRR+P2C)`
     );
   }
 
-  return { orderedTargets, quotaShareRelease };
+  return orderedTargets;
 }

open-sse/services/combo/targetResolution.ts

@@ -122,13 +122,6 @@ export interface ResolvedComboTargetPipeline {
   /** Session-stickiness result — the attempt loop reads `.messageHash` on success/failure. */
   sticky: ApplyStickinessResult;
   preScreenMap: Map<string, PreScreenResult>;
-  /**
-   * Idempotent release for the in-flight slot quota-share ordering reserved for
-   * its winner (#11371). Null unless the `quota-share` strategy ran. The host MUST
-   * invoke it when the request settles; this pipeline already releases it on any
-   * earlyResponse it produces after selection.
-   */
-  quotaShareRelease: (() => void) | null;
 }
 
 export type ResolveComboTargetPipelineResult =
@@ -401,11 +394,7 @@ async function orderByStrategy(
   initialOrderedTargets: ResolvedComboTarget[]
 ): Promise<
   | { earlyResponse: Response }
-  | {
-      orderedTargets: ResolvedComboTarget[];
-      autoUsedExplicitRouter: boolean;
-      quotaShareRelease: (() => void) | null;
-    }
+  | { orderedTargets: ResolvedComboTarget[]; autoUsedExplicitRouter: boolean }
 > {
   const { strategy, body, combo, settings, config, log } = deps;
   if (strategy === "auto") {
@@ -424,22 +413,17 @@ async function orderByStrategy(
     return {
       orderedTargets: autoResult.orderedTargets,
       autoUsedExplicitRouter: autoResult.autoUsedExplicitRouter,
-      quotaShareRelease: null,
     };
   }
-  const { orderedTargets, quotaShareRelease } = await applyStrategyOrdering(
-    strategy,
-    initialOrderedTargets,
-    {
-      combo,
-      config,
-      body,
-      log,
-      apiKeyAllowedConnections: deps.apiKeyAllowedConnections,
-      sessionKey: deps.relayOptions?.sessionId,
-    }
-  );
-  return { orderedTargets, autoUsedExplicitRouter: false, quotaShareRelease };
+  const orderedTargets = await applyStrategyOrdering(strategy, initialOrderedTargets, {
+    combo,
+    config,
+    body,
+    log,
+    apiKeyAllowedConnections: deps.apiKeyAllowedConnections,
+    sessionKey: deps.relayOptions?.sessionId,
+  });
+  return { orderedTargets, autoUsedExplicitRouter: false };
 }
 
 /**
@@ -730,15 +714,10 @@ export async function resolveComboTargetPipeline(
 
   const ordering = await orderByStrategy(deps, orderedTargets);
   if ("earlyResponse" in ordering) return ordering;
-  const { autoUsedExplicitRouter, quotaShareRelease } = ordering;
+  const { autoUsedExplicitRouter } = ordering;
 
   const continuity = await applyContinuityFilters(deps, ordering.orderedTargets);
-  if ("earlyResponse" in continuity) {
-    // #11371: selection already reserved the winner's in-flight slot; a hard
-    // filter exhausting the pool must not leak it.
-    quotaShareRelease?.();
-    return continuity;
-  }
+  if ("earlyResponse" in continuity) return continuity;
   orderedTargets = applyTaskAwareOrdering(deps, continuity.orderedTargets, autoUsedExplicitRouter);
   orderedTargets = await applyPromptCacheStage(
     deps,
@@ -762,6 +741,5 @@ export async function resolveComboTargetPipeline(
     getWeightedStepKeyForTarget,
     sticky: continuity.sticky,
     preScreenMap,
-    quotaShareRelease,
   };
 }

package.json

@@ -1,7 +1,7 @@
 {
   "name": "omniroute",
   "version": "3.8.51",
-  "description": "Unified AI router with 353 providers, RTK+Caveman compression, auto fallback, MCP/A2A, desktop, PWA, and OpenAI-compatible APIs.",
+  "description": "Unified AI router with 350 providers, RTK+Caveman compression, auto fallback, MCP/A2A, desktop, PWA, and OpenAI-compatible APIs.",
   "type": "module",
   "bin": {
     "omniroute": "bin/omniroute.mjs",

skills/omni-inference/SKILL.md

@@ -32,30 +32,6 @@ curl -X POST https://localhost:20128/api/v1/session-leases \
   -d '{}'
 ```
 
-### GET /api/v1/search
-
-List search providers
-
-Lists configured search providers and their supported search types.
-
-```bash
-curl https://localhost:20128/api/v1/search \
-  -H "Authorization: Bearer $OMNIROUTE_TOKEN"
-```
-
-### POST /api/v1/search
-
-Run a unified search
-
-Searches the web, news, or X through a configured provider. Set `provider` to `xquik-search` to use Xquik for X search. The aliases `xquik` and `xquik_search` resolve to the same provider.
-
-```bash
-curl -X POST https://localhost:20128/api/v1/search \
-  -H "Authorization: Bearer $OMNIROUTE_TOKEN" \
-  -H "Content-Type: application/json" \
-  -d '{}'
-```
-
 ### POST /api/v1/chat/completions
 
 Create chat completion

src/app/(dashboard)/dashboard/settings/components/ResilienceTab.tsx

@@ -13,7 +13,6 @@ type RequestQueueSettings = {
   requestsPerMinute: number;
   minTimeBetweenRequestsMs: number;
   concurrentRequests: number;
-  globalConcurrentRequests: number;
   maxWaitMs: number;
 };
 
@@ -241,21 +240,13 @@ function RequestQueueCard({
               }
             />
             <NumberField
-              label={t("resilienceConnectionScopeConcurrentRequests")}
+              label={t("resilienceConcurrentRequests")}
               value={draft.concurrentRequests}
               min={1}
               onChange={(concurrentRequests) =>
                 setDraft((prev) => ({ ...prev, concurrentRequests }))
               }
             />
-            <NumberField
-              label={t("resilienceGlobalConcurrentRequests")}
-              value={draft.globalConcurrentRequests}
-              min={0}
-              onChange={(globalConcurrentRequests) =>
-                setDraft((prev) => ({ ...prev, globalConcurrentRequests }))
-              }
-            />
             <NumberField
               label={t("resilienceMaxQueueWait")}
               value={draft.maxWaitMs}
@@ -287,21 +278,11 @@ function RequestQueueCard({
               </div>
             </div>
             <div className="rounded-xl border border-border bg-bg-subtle p-4">
-              <div className="text-xs text-text-muted">
-                {t("resilienceConnectionScopeConcurrentRequests")}
-              </div>
+              <div className="text-xs text-text-muted">{t("resilienceConcurrentRequests")}</div>
               <div className="mt-1 text-sm font-semibold text-text-main">
                 {value.concurrentRequests}
               </div>
             </div>
-            <div className="rounded-xl border border-border bg-bg-subtle p-4">
-              <div className="text-xs text-text-muted">
-                {t("resilienceGlobalConcurrentRequests")}
-              </div>
-              <div className="mt-1 text-sm font-semibold text-text-main">
-                {value.globalConcurrentRequests || t("statusDisabled")}
-              </div>
-            </div>
             <div className="rounded-xl border border-border bg-bg-subtle p-4">
               <div className="text-xs text-text-muted">{t("resilienceMaxQueueWait")}</div>
               <div className="mt-1 text-sm font-semibold text-text-main">

src/app/(dashboard)/dashboard/usage/components/SessionsTab.tsx

@@ -2,47 +2,19 @@
 
 import { useTranslations } from "next-intl";
 
-import { useCallback, useEffect, useMemo, useState } from "react";
-import {
-  mergeDashboardSessions,
-  type DashboardSession,
-  type ExclusiveDashboardSession,
-  type RecentSessionForDashboard,
-} from "@/lib/sessionObservability";
+import { useState, useEffect, useCallback } from "react";
 import { Card } from "@/shared/components";
 
-type SessionsResponse = {
-  sessions: RecentSessionForDashboard[];
-  exclusiveSessions: ExclusiveDashboardSession[];
-};
-
-const EMPTY_DATA: SessionsResponse = {
-  sessions: [],
-  exclusiveSessions: [],
-};
-
-function isLeaseBackedSession(session: DashboardSession): session is ExclusiveDashboardSession {
-  return "leaseBacked" in session && session.leaseBacked;
-}
-
 export default function SessionsTab() {
   const t = useTranslations("usage");
-  const tCommon = useTranslations("common");
-  const [data, setData] = useState<SessionsResponse>(EMPTY_DATA);
+  const [data, setData] = useState({ count: 0, sessions: [] });
   const [loading, setLoading] = useState(true);
 
   const loadSessions = useCallback(async () => {
     try {
       const res = await fetch("/api/sessions");
-      if (res.ok) {
-        const next = await res.json();
-        setData({
-          sessions: Array.isArray(next.sessions) ? next.sessions : [],
-          exclusiveSessions: Array.isArray(next.exclusiveSessions) ? next.exclusiveSessions : [],
-        });
-      }
+      if (res.ok) setData(await res.json());
     } catch {
-      // A failed background poll leaves the last successful Sessions snapshot visible.
     } finally {
       setLoading(false);
     }
@@ -54,12 +26,7 @@ export default function SessionsTab() {
     return () => clearInterval(interval);
   }, [loadSessions]);
 
-  const displaySessions = useMemo(() => {
-    return mergeDashboardSessions(data.exclusiveSessions, data.sessions);
-  }, [data.exclusiveSessions, data.sessions]);
-
-  const formatAge = (ms: number | null) => {
-    if (ms == null) return t("notAvailableSymbol");
+  const formatAge = (ms) => {
     if (ms < 60000) return t("durationSecondsShort", { value: Math.floor(ms / 1000) });
     if (ms < 3600000) return t("durationMinutesShort", { value: Math.floor(ms / 60000) });
     return t("durationHoursShort", { value: Math.floor(ms / 3600000) });
@@ -80,17 +47,12 @@ export default function SessionsTab() {
         <div className="flex items-center gap-2">
           <span className="flex items-center gap-1.5 px-3 py-1.5 rounded-full bg-cyan-500/10 border border-cyan-500/20">
             <span className="w-2 h-2 rounded-full bg-cyan-500 animate-pulse" />
-            <span
-              className="text-sm font-semibold tabular-nums text-cyan-400"
-              data-testid="session-count"
-            >
-              {displaySessions.length}
-            </span>
+            <span className="text-sm font-semibold tabular-nums text-cyan-400">{data.count}</span>
           </span>
         </div>
       </div>
 
-      {displaySessions.length === 0 ? (
+      {data.sessions.length === 0 ? (
         <div className="text-center py-8 text-text-muted">
           <span
             className="material-symbols-outlined text-[40px] mb-2 block opacity-40"
@@ -121,46 +83,31 @@ export default function SessionsTab() {
               </tr>
             </thead>
             <tbody>
-              {displaySessions.map((s) => {
-                const leaseBacked = isLeaseBackedSession(s);
-                return (
-                  <tr
-                    key={s.sessionId}
-                    className="border-b border-border/10 hover:bg-surface/20 transition-colors"
-                  >
-                    <td className="py-2.5 px-3">
-                      <div className="flex items-center gap-2">
-                        <span
-                          className="font-mono text-xs px-2 py-1 rounded bg-surface/40 text-text-muted"
-                          title={s.sessionId}
-                        >
-                          {s.sessionId.slice(0, 12)}…
-                        </span>
-                        {leaseBacked && s.active && (
-                          <span className="text-[10px] font-semibold tracking-wide px-2 py-0.5 rounded-full border text-green-400 border-green-500/30 bg-green-500/10">
-                            {tCommon("active")}
-                          </span>
-                        )}
-                      </div>
-                    </td>
-                    <td className="py-2.5 px-3 text-text-muted tabular-nums">
-                      {formatAge(s.ageMs)}
-                    </td>
-                    <td className="py-2.5 px-3 text-right">
-                      <span className="font-semibold tabular-nums">{s.requestCount}</span>
-                    </td>
-                    <td className="py-2.5 px-3">
-                      {s.connectionId ? (
-                        <span className="text-xs font-mono text-cyan-400" title={s.connectionId}>
-                          {(leaseBacked && s.connectionName) || s.connectionId.slice(0, 10)}
-                        </span>
-                      ) : (
-                        <span className="text-text-muted/40">{t("notAvailableSymbol")}</span>
-                      )}
-                    </td>
-                  </tr>
-                );
-              })}
+              {data.sessions.map((s) => (
+                <tr
+                  key={s.sessionId}
+                  className="border-b border-border/10 hover:bg-surface/20 transition-colors"
+                >
+                  <td className="py-2.5 px-3">
+                    <span className="font-mono text-xs px-2 py-1 rounded bg-surface/40 text-text-muted">
+                      {s.sessionId.slice(0, 12)}…
+                    </span>
+                  </td>
+                  <td className="py-2.5 px-3 text-text-muted tabular-nums">{formatAge(s.ageMs)}</td>
+                  <td className="py-2.5 px-3 text-right">
+                    <span className="font-semibold tabular-nums">{s.requestCount}</span>
+                  </td>
+                  <td className="py-2.5 px-3">
+                    {s.connectionId ? (
+                      <span className="text-xs font-mono text-cyan-400">
+                        {s.connectionId.slice(0, 10)}
+                      </span>
+                    ) : (
+                      <span className="text-text-muted/40">{t("notAvailableSymbol")}</span>
+                    )}
+                  </td>
+                </tr>
+              ))}
             </tbody>
           </table>
         </div>

src/app/api/providers/web-session-contract/route.ts

@@ -1,10 +0,0 @@
-import { NextResponse } from "next/server";
-import { requireManagementAuth } from "@/lib/api/requireManagementAuth";
-import { buildWebSessionContract } from "@/lib/providers/webSessionContract";
-
-export async function GET(request: Request) {
-  const authError = await requireManagementAuth(request);
-  if (authError) return authError;
-
-  return NextResponse.json(buildWebSessionContract());
-}

src/app/api/sessions/route.ts

@@ -5,44 +5,13 @@ import {
   getAllActiveSessionCountsByKey,
 } from "@omniroute/open-sse/services/sessionManager.ts";
 import { sanitizeErrorMessage } from "@omniroute/open-sse/utils/error";
-import { getExclusiveLeaseConnectionIds } from "@/lib/db/apiKeys";
-import { getExclusiveLeaseOccupancy } from "@/lib/db/exclusiveConnectionLeases";
-import { getProviderConnectionDisplayMetadata } from "@/lib/db/providers";
-import { getAccountDisplayName } from "@/lib/display/names";
-import { getPendingRequests } from "@/lib/usage/usageHistory";
-import { buildExclusiveDashboardSessions } from "@/lib/sessionObservability";
 
 export async function GET() {
   try {
     const sessions = getActiveSessions();
     const count = getActiveSessionCount();
     const byApiKey = getAllActiveSessionCountsByKey();
-
-    // Reuse the hard-lease authority added by #10362. The API-key policy derives
-    // the managed candidate set; SQLite occupancy is the source of truth for
-    // which of those connections are actually leased right now.
-    const managedConnectionIds = Array.from(await getExclusiveLeaseConnectionIds());
-    const occupancy = getExclusiveLeaseOccupancy(managedConnectionIds);
-    const leasedConnectionIds = new Set(occupancy.keys());
-    const connectionNames = new Map(
-      getProviderConnectionDisplayMetadata([...leasedConnectionIds]).map((connection) => [
-        connection.id,
-        getAccountDisplayName(connection),
-      ])
-    );
-    const exclusiveSessions = buildExclusiveDashboardSessions(
-      leasedConnectionIds,
-      getPendingRequests().byAccount,
-      sessions,
-      connectionNames
-    );
-
-    return NextResponse.json({
-      count,
-      sessions,
-      byApiKey,
-      exclusiveSessions,
-    });
+    return NextResponse.json({ count, sessions, byApiKey });
   } catch (error) {
     return NextResponse.json({ error: sanitizeErrorMessage(error) }, { status: 500 });
   }

src/i18n/messages/de.json

@@ -7538,8 +7538,6 @@
     "resilienceRequestsPerMinute": "Requests per minute",
     "resilienceMinTimeBetweenRequests": "Minimum time between requests",
     "resilienceConcurrentRequests": "Concurrent requests",
-    "resilienceConnectionScopeConcurrentRequests": "Gleichzeitige Anfragen pro Verbindung/Quota-Bereich",
-    "resilienceGlobalConcurrentRequests": "Globale gleichzeitige Upstream-Anfragen (0 = deaktiviert)",
     "resilienceMaxQueueWaitTime": "Maximale Wartezeit in der Warteschlange",
     "resilienceBaseCooldown": "Base cooldown",
     "resilienceUseUpstreamRetryHints": "Use upstream retry hints",

src/i18n/messages/en.json

@@ -7550,8 +7550,6 @@
     "resilienceRequestsPerMinute": "Requests per minute",
     "resilienceMinTimeBetweenRequests": "Minimum time between requests",
     "resilienceConcurrentRequests": "Concurrent requests",
-    "resilienceConnectionScopeConcurrentRequests": "Concurrent requests per connection/quota scope",
-    "resilienceGlobalConcurrentRequests": "Global concurrent upstream requests (0 = disabled)",
     "resilienceMaxQueueWaitTime": "Maximum queue wait time",
     "resilienceBaseCooldown": "Base cooldown",
     "resilienceUseUpstreamRetryHints": "Use upstream retry hints",

src/i18n/messages/pt-BR.json

@@ -7550,8 +7550,6 @@
     "resilienceRequestsPerMinute": "Requests per minute",
     "resilienceMinTimeBetweenRequests": "Minimum time between requests",
     "resilienceConcurrentRequests": "Concurrent requests",
-    "resilienceConnectionScopeConcurrentRequests": "Solicitações simultâneas por conexão/escopo de cota",
-    "resilienceGlobalConcurrentRequests": "Solicitações upstream simultâneas globais (0 = desativado)",
     "resilienceMaxQueueWaitTime": "Tempo máximo de espera na fila",
     "resilienceBaseCooldown": "Base cooldown",
     "resilienceUseUpstreamRetryHints": "Use upstream retry hints",

src/i18n/messages/vi.json

@@ -7550,8 +7550,6 @@
     "resilienceRequestsPerMinute": "Số yêu cầu mỗi phút",
     "resilienceMinTimeBetweenRequests": "Thời gian tối thiểu giữa các yêu cầu",
     "resilienceConcurrentRequests": "Số yêu cầu đồng thời",
-    "resilienceConnectionScopeConcurrentRequests": "Số yêu cầu đồng thời trên mỗi kết nối/phạm vi hạn ngạch",
-    "resilienceGlobalConcurrentRequests": "Số yêu cầu thượng nguồn đồng thời toàn cục (0 = tắt)",
     "resilienceMaxQueueWaitTime": "Thời gian chờ hàng đợi tối đa",
     "resilienceBaseCooldown": "Thời gian giãn cách cơ bản",
     "resilienceUseUpstreamRetryHints": "Sử dụng gợi ý thử lại từ máy chủ thượng nguồn",

src/lib/db/providers.ts

@@ -344,43 +344,6 @@ export async function getProviderConnectionById(id: string) {
   );
 }
 
-export interface ProviderConnectionDisplayMetadata {
-  id: string;
-  name: string | null;
-  displayName: string | null;
-  email: string | null;
-}
-
-/**
- * Reads only the non-credential fields needed by account display-name resolvers.
- *
- * This avoids decrypting provider credentials when a dashboard only needs labels.
- */
-export function getProviderConnectionDisplayMetadata(
-  connectionIds: readonly string[]
-): ProviderConnectionDisplayMetadata[] {
-  const ids = [...new Set(connectionIds.filter((id) => id.length > 0))];
-  if (ids.length === 0) return [];
-
-  const db = getDbInstance() as unknown as DbLike;
-  const rows = db
-    .prepare(
-      `SELECT id, name, display_name, email FROM provider_connections
-       WHERE id IN (${ids.map(() => "?").join(", ")})`
-    )
-    .all(...ids);
-
-  return rows.map((row) => {
-    const view = rowToCamel(row) as JsonRecord;
-    return {
-      id: toStringOrNull(view.id) || "",
-      name: toStringOrNull(view.name),
-      displayName: toStringOrNull(view.displayName),
-      email: toStringOrNull(view.email),
-    };
-  });
-}
-
 // #3368 PR6 — dedup web-session cookie/token credentials on connection create.
 // Re-importing the same session (e.g. via bulk web-session import) under a
 // different or blank name must update the existing connection instead of
@@ -625,10 +588,6 @@ export async function createProviderConnection(data: JsonRecord) {
     "accessToken",
     "refreshToken",
     "expiresAt",
-    // #5326's payload sets this and _insertConnectionRow binds it, but it was
-    // missing from this allowlist — so every created row stored NULL however good
-    // the payload was. The update path already carries it (`data.tokenExpiresAt`).
-    "tokenExpiresAt",
     "tokenType",
     "scope",
     "idToken",

src/lib/providers/validation/openaiFormat.ts

@@ -410,24 +410,16 @@ export async function validateOpenAICompatibleProvider({ apiKey, providerSpecifi
   const chatSuffix = apiType === "responses" ? "/responses" : "/chat/completions";
   const chatUrl = `${baseUrl}${chatSuffix}`;
   const testModelId = validationModelId;
-  const testBody =
-    apiType === "responses"
-      ? {
-          model: testModelId,
-          input: [{ role: "user", content: "test" }],
-          max_output_tokens: 1,
-        }
-      : {
-          model: testModelId,
-          messages: [{ role: "user", content: "test" }],
-          max_tokens: 1,
-        };
 
   try {
     const chatRes = await validationWrite(chatUrl, {
       method: "POST",
       headers: buildBearerHeaders(apiKey, providerSpecificData),
-      body: JSON.stringify(testBody),
+      body: JSON.stringify({
+        model: testModelId,
+        messages: [{ role: "user", content: "test" }],
+        max_tokens: 1,
+      }),
     });
 
     if (chatRes.ok) {

src/lib/providers/validation/searchProviders.ts

@@ -167,13 +167,6 @@ export const SEARCH_VALIDATOR_CONFIGS: Record<
       }),
     },
   }),
-  "xquik-search": (apiKey) => ({
-    url: "https://xquik.com/api/v1/x/tweets/search?q=test&limit=1",
-    init: {
-      method: "GET",
-      headers: { Accept: "application/json", "x-api-key": apiKey },
-    },
-  }),
   "zai-search": (apiKey, providerSpecificData = {}) => {
     const baseUrl =
       typeof providerSpecificData?.baseUrl === "string" && providerSpecificData.baseUrl.trim()

src/lib/providers/webSessionContract.ts

@@ -1,58 +0,0 @@
-import {
-  listExtractionConfigs,
-  type TokenSource,
-} from "@omniroute/open-sse/services/tokenExtractionConfig.ts";
-import { getWebSessionCredentialRequirement } from "@/shared/providers/webSessionCredentials";
-
-export const WEB_SESSION_CONTRACT_VERSION = 1;
-
-export interface WebSessionContractProvider {
-  providerId: string;
-  displayName: string;
-  loginUrl: string;
-  homeUrl: string;
-  tokenSources: TokenSource[];
-  credential: {
-    kind: "cookie" | "token";
-    storageKeys: string[];
-    acceptsFullCookieHeader: boolean;
-  };
-}
-
-export interface WebSessionContract {
-  version: typeof WEB_SESSION_CONTRACT_VERSION;
-  providers: WebSessionContractProvider[];
-}
-
-/**
- * Publish only the canonical, non-secret metadata needed by external
- * credential brokers to capture credentials in the same shape OmniRoute
- * accepts. Provider instructions, polling state, and credential values are
- * intentionally excluded.
- */
-export function buildWebSessionContract(): WebSessionContract {
-  const providers = listExtractionConfigs().flatMap<WebSessionContractProvider>((config) => {
-    const requirement = getWebSessionCredentialRequirement(config.providerId);
-    if (!requirement || requirement.kind === "none") return [];
-
-    return [
-      {
-        providerId: config.providerId,
-        displayName: config.displayName,
-        loginUrl: config.loginUrl,
-        homeUrl: config.homeUrl,
-        tokenSources: config.tokenSources.map((source) => ({ ...source })),
-        credential: {
-          kind: requirement.kind,
-          storageKeys: [...requirement.storageKeys],
-          acceptsFullCookieHeader: requirement.acceptsFullCookieHeader,
-        },
-      },
-    ];
-  });
-
-  return {
-    version: WEB_SESSION_CONTRACT_VERSION,
-    providers,
-  };
-}

src/lib/resilience/settings.ts

@@ -58,7 +58,6 @@ export const DEFAULT_RESILIENCE_SETTINGS: ResilienceSettings = {
     requestsPerMinute: DEFAULT_API_LIMITS.requestsPerMinute,
     minTimeBetweenRequestsMs: DEFAULT_API_LIMITS.minTimeBetweenRequests,
     concurrentRequests: DEFAULT_API_LIMITS.concurrentRequests,
-    globalConcurrentRequests: 0,
     maxWaitMs: DEFAULT_REQUEST_QUEUE_MAX_WAIT_MS,
     maxQueueDepth: DEFAULT_REQUEST_QUEUE_MAX_DEPTH,
   },
@@ -209,8 +208,6 @@ function buildLegacyFallback(settings: JsonRecord): ResilienceSettings {
         DEFAULT_RESILIENCE_SETTINGS.requestQueue.concurrentRequests,
         { min: 1, max: 10_000 }
       ),
-      globalConcurrentRequests:
-        DEFAULT_RESILIENCE_SETTINGS.requestQueue.globalConcurrentRequests,
       maxWaitMs: DEFAULT_RESILIENCE_SETTINGS.requestQueue.maxWaitMs,
       maxQueueDepth: DEFAULT_RESILIENCE_SETTINGS.requestQueue.maxQueueDepth,
     },

src/lib/resilience/settings/normalize.ts

@@ -124,11 +124,6 @@ export function normalizeRequestQueueSettings(
     min: 1,
     max: 10_000,
   });
-  const globalConcurrentRequests = toInteger(
-    record.globalConcurrentRequests,
-    fallback.globalConcurrentRequests,
-    { min: 0, max: 100_000 }
-  );
   const maxWaitMs = toInteger(record.maxWaitMs, fallback.maxWaitMs, {
     min: 1,
     max: 24 * 60 * 60 * 1000,
@@ -146,7 +141,6 @@ export function normalizeRequestQueueSettings(
     requestsPerMinute,
     minTimeBetweenRequestsMs,
     concurrentRequests,
-    globalConcurrentRequests,
     maxWaitMs,
     maxQueueDepth,
   };
@@ -437,16 +431,8 @@ function normalizeProviderQuotaOverrideEntry(raw: unknown): ProviderQuotaOverrid
   const out: ProviderQuotaOverrideSettings = {};
   const rpm = typeof record.rpm === "number" ? record.rpm : Number(record.rpm);
   if (Number.isFinite(rpm) && rpm > 0) out.rpm = Math.trunc(rpm);
-  const concurrency =
-    typeof record.concurrency === "number" ? record.concurrency : Number(record.concurrency);
+  const concurrency = typeof record.concurrency === "number" ? record.concurrency : Number(record.concurrency);
   if (Number.isFinite(concurrency) && concurrency > 0) out.concurrency = Math.trunc(concurrency);
-  const providerConcurrency =
-    typeof record.providerConcurrency === "number"
-      ? record.providerConcurrency
-      : Number(record.providerConcurrency);
-  if (Number.isFinite(providerConcurrency) && providerConcurrency >= 0) {
-    out.providerConcurrency = Math.trunc(providerConcurrency);
-  }
   return Object.keys(out).length > 0 ? out : null;
 }
 

src/lib/resilience/settings/types.ts

@@ -16,8 +16,6 @@ export interface RequestQueueSettings {
   requestsPerMinute: number;
   minTimeBetweenRequestsMs: number;
   concurrentRequests: number;
-  /** Whole-process upstream concurrency cap. Zero disables the global gate. */
-  globalConcurrentRequests: number;
   /**
    * Legacy persisted key used as Bottleneck's post-dispatch execution
    * expiration. It does not bound time spent in Bottleneck's QUEUED state.
@@ -171,8 +169,6 @@ export interface ProviderQuotaOverrideSettings {
   rpm?: number;
   /** Overrides the static per-connection concurrency cap. */
   concurrency?: number;
-  /** Shared concurrency cap across every connection for this provider. */
-  providerConcurrency?: number;
 }
 
 export interface StreamRecoverySettings {