fix(resilience): route chat by per-connection synced model inventory (#11089)

AGENTS.md

@@ -46,7 +46,7 @@ Repository map and Reference Documentation sections below.
 
 ## Project at a Glance
 
-**OmniRoute** — unified AI proxy/router. One endpoint, 348 LLM providers, auto-fallback.
+**OmniRoute** — unified AI proxy/router. One endpoint, 349 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 → 348 providers — 90+ free — through one endpoint. Claude Code, Codex, Cursor, Cline, Copilot & Antigravity into FREE Claude / GPT / Gemini with auto-fallback. RTK + Caveman stacked compression saves 15–95% tokens (~89% avg) — never hit limits. 348 AI providers · 90+ free tiers · ~1.51B free tokens/mo · 19 routing strategies · $0 to start."/>
+<img src="./docs/diagrams/readme-hero.svg" width="100%" alt="OmniRoute — Never stop coding. Every AI tool → 349 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. 349 AI providers · 90+ free tiers · ~1.51B free tokens/mo · 19 routing strategies · $0 to start."/>
 
 </div>
 
@@ -101,7 +101,7 @@
   <tr>
     <td align="right"><b>⚙️ Features</b></td>
     <td align="center"><a href="#-combos--the-flagship">🎯 Combos</a></td>
-    <td align="center"><a href="#-348-ai-providers--90-free">🌐 Providers</a></td>
+    <td align="center"><a href="#-349-ai-providers--90-free">🌐 Providers</a></td>
     <td align="center"><a href="#-full-cli--a2a--mcp">🔌 CLI &amp; MCP</a></td>
   </tr>
   <tr>
@@ -210,7 +210,7 @@ curl http://localhost:20128/v1/chat/completions \
 
 </div>
 
-<img src="./docs/diagrams/promise-pillars.svg" width="100%" alt="The Promise — One endpoint. 348 providers. Never stop building — OmniRoute picks the cheapest one that works. Six pillars: Never hit limits (auto-fallback across 348 providers in milliseconds, zero downtime) · Save up to 95% tokens (RTK + Caveman stacked compression cuts 15–95%, ~89% avg on tool-heavy sessions) · $0 to start (90+ free tiers, 56 free forever — no card needed) · Every tool works (33 coding agents through one config) · One endpoint (OpenAI ↔ Claude ↔ Gemini ↔ Responses API at /v1) · Production-grade (circuit breakers, TLS stealth, MCP 110 tools, A2A, memory, guardrails, evals — 25,000+ tests)."/>
+<img src="./docs/diagrams/promise-pillars.svg" width="100%" alt="The Promise — One endpoint. 349 providers. Never stop building — OmniRoute picks the cheapest one that works. Six pillars: Never hit limits (auto-fallback across 349 providers in milliseconds, zero downtime) · Save up to 95% tokens (RTK + Caveman stacked compression cuts 15–95%, ~89% avg on tool-heavy sessions) · $0 to start (90+ free tiers, 56 free forever — no card needed) · Every tool works (33 coding agents through one config) · One endpoint (OpenAI ↔ Claude ↔ Gemini ↔ Responses API at /v1) · Production-grade (circuit breakers, TLS stealth, MCP 110 tools, A2A, memory, guardrails, evals — 25,000+ tests)."/>
 
 <br/>
 <br/>
@@ -461,7 +461,7 @@ All **19** strategies — mix & match per combo step:
 
 </div>
 
-<img src="./docs/diagrams/comparison-table.svg" width="100%" alt="What sets OmniRoute apart — comparison table vs 9router, OpenRouter, CLIProxyAPI and LiteLLM across 13 capabilities. OmniRoute: 348 providers, 90+ free providers built-in, 19 routing strategies, 12-engine token compression, built-in MCP server with 110 tools, A2A agent protocol, persistent memory, guardrails, cloud agents, TLS fingerprint stealth, Desktop/Termux/PWA, 43 i18n UI locales, 100% MIT self-hosted. OmniRoute is the only one with the full set; competitors show a mix of checks, partials and crosses. Verified from each project&apos;s docs."/>
+<img src="./docs/diagrams/comparison-table.svg" width="100%" alt="What sets OmniRoute apart — comparison table vs 9router, OpenRouter, CLIProxyAPI and LiteLLM across 13 capabilities. OmniRoute: 349 providers, 90+ free providers built-in, 19 routing strategies, 12-engine token compression, built-in MCP server with 110 tools, A2A agent protocol, persistent memory, guardrails, cloud agents, TLS fingerprint stealth, Desktop/Termux/PWA, 43 i18n UI locales, 100% MIT self-hosted. OmniRoute is the only one with the full set; competitors show a mix of checks, partials and crosses. Verified from each project&apos;s docs."/>
 
 <sub>📊 Full methodology &amp; per-feature detail vs 9router, OpenRouter, CLIProxyAPI &amp; LiteLLM → [`docs/comparison/OMNIROUTE_VS_ALTERNATIVES.md`](docs/comparison/OMNIROUTE_VS_ALTERNATIVES.md)</sub>
 
@@ -559,7 +559,7 @@ the current catalog at **[radar.omniroute.online/planos](https://radar.omniroute
 - **🖼️ New endpoints** — `/v1/ocr` (Mistral OCR) and `/v1/audio/translations` (Whisper-style) round out the media surface. → [API Reference](docs/reference/API_REFERENCE.md)
 - **🎨 Image / video / audio generation** — one API for media: xAI Grok Imagine & Novita AI video, ComfyUI, Freepik, Adobe Firefly, Microsoft Designer, Segmind, EdgeTTS. → [API Reference](docs/reference/API_REFERENCE.md)
 - **🌍 Deployment & ops** — reverse-proxy `basePath`, browser-language auto-detect, per-key device tracking, root-less MITM trust, zh-TW localization. → [Environment](docs/reference/ENVIRONMENT.md)
-- **🤝 More providers & agents** — Cursor Cloud Agent, Grok Build (xAI) with browser + OAuth login, Ollama first-class card, Claude Opus 5 & Sonnet 5, Kimi official partnership (Code/Web/Moonshot), Zed, Requesty, SenseNova, Yuanbao, Agnes AI… and a refreshed **348-provider catalog**. → [Providers](docs/reference/PROVIDER_REFERENCE.md)
+- **🤝 More providers & agents** — Cursor Cloud Agent, Grok Build (xAI) with browser + OAuth login, Ollama first-class card, Claude Opus 5 & Sonnet 5, Kimi official partnership (Code/Web/Moonshot), Zed, Requesty, SenseNova, Yuanbao, Agnes AI… and a refreshed **349-provider catalog**. → [Providers](docs/reference/PROVIDER_REFERENCE.md)
 - **📡 Routing transparency** — every response carries an `X-OmniRoute-Decision` header naming the strategy/provider/latency that served it, a new `cache-optimized` combo strategy + Auto-Combo `cacheAffinity` factor route repeat requests back to the connection holding the cached prefix, and a read-only `/v1/auto-combo/{channel}/candidates` endpoint exposes an `auto/*` channel's live candidate pool. → [Auto-Combo](docs/routing/AUTO-COMBO.md)
 - **⚡ Local performance & infra** — one-click local Redis, Cloudflare Workers / Deno Deploy relay deployers, Bifrost & Mux as supervised embedded services. → [Embedded Services](docs/frameworks/EMBEDDED-SERVICES.md)
 
@@ -642,11 +642,11 @@ of your shell history. → [CLI Integrations](docs/guides/CLI-INTEGRATIONS.md)
 
 <div align="center">
 
-## 🌐 348 AI Providers — 90+ Free
+## 🌐 349 AI Providers — 90+ Free
 
 </div>
 
-> The most complete catalog of any open-source router: **348 providers**, **90+ with a free tier**, **56 free forever**.
+> The most complete catalog of any open-source router: **349 providers**, **90+ with a free tier**, **56 free forever**.
 
 <div align="center">
 
@@ -990,11 +990,11 @@ docker run -d --name omniroute --restart unless-stopped --stop-timeout 40 \
 
 `:latest` follows the highest **published** stable SemVer. It does not track git `main`. Pin `:X.Y.Z` for GitOps. See [Docker Release Channels](docs/guides/DOCKER_GUIDE.md#release-channels).The image pins **`OMNIROUTE_MEMORY_MB=1024`**. That is enough for the dashboard and a light chat. **Coding agents** (`POST /v1/responses` from Claude Code, Codex, Grok, …) need a much larger V8 heap or the process `FATAL ERROR`s at ~12 GiB under two overlapping long contexts. Size the container above the heap (native buffers sit outside V8):
 
-| Workload | Heap (`-e OMNIROUTE_MEMORY_MB`) | Container (`--memory`) |
-| --- | --- | --- |
-| Dashboard / light chat | `1024` (image default) | ≥2 g |
-| One coding agent | `8192` | ≥10 g |
-| Two concurrent long `/v1/responses` | `10240`–`12288` | ≥12–16 g |
+| Workload                            | Heap (`-e OMNIROUTE_MEMORY_MB`) | Container (`--memory`) |
+| ----------------------------------- | ------------------------------- | ---------------------- |
+| Dashboard / light chat              | `1024` (image default)          | ≥2 g                   |
+| One coding agent                    | `8192`                          | ≥10 g                  |
+| Two concurrent long `/v1/responses` | `10240`–`12288`                 | ≥12–16 g               |
 
 ```bash
 docker run -d --name omniroute --restart unless-stopped --stop-timeout 40 \
@@ -1003,6 +1003,7 @@ docker run -d --name omniroute --restart unless-stopped --stop-timeout 40 \
 ```
 
 Full table: [Docker Guide — runtime RAM](docs/guides/DOCKER_GUIDE.md#runtime-ram-for-coding-agents).
+
 > **Pre-release Docker channel:** `diegosouzapw/omniroute:next` and
 > `diegosouzapw/omniroute:next-web` follow the current default `release/v*`
 > branch. These mutable tags are intended only for testing unreleased fixes and

bin/cli/commands/combo.mjs

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

changelog.d/features/10987-logfare-free-provider.md

@@ -0,0 +1 @@
+- **feat(providers):** add Logfare as a free OpenAI-compatible provider — dashboard card with a Free badge and request-logging disclosure (every prompt/completion is logged for research; opt out at logfare.ai/consent), live model discovery from `https://logfare.ai/v1/models` (20 models, 11 chat-capable: kimi-k3, deepseek-v4-pro, glm-5.2, gpt-5.6-luna, minimax-m3…), full chat/streaming through the existing OpenAI-compatible path, the real Logfare logo on the card, and a listing in the free-tiers guide. ([#10987](https://github.com/diegosouzapw/OmniRoute/pull/10987))

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

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

changelog.d/features/11192-usage-command-providers-array.md

@@ -0,0 +1 @@
+- **feat(api):** `/api/usage/om-usage?format=json` now returns `providers[]` — every connection's quota snapshot, not just the single selected one — so a panel can render Codex / Claude / OpenCode side by side. The collector already gathered all of them; the single-pick `provider` field (kept) is a terminal presentation choice. Closes the per-connection gap from OmniCopilot #8 ([#11192](https://github.com/diegosouzapw/OmniRoute/pull/11192))

changelog.d/fixes/10071-g4f-space-anonymous-tier-proof-of-work.md

@@ -0,0 +1 @@
+- **fix(providers):** the five g4f.space sub-providers (Groq, Gemini, Pollinations, Ollama, NVIDIA) no longer advertise a free tier — a keyless `POST /v1/chat/completions` now returns `402 insufficient_credits` behind a proof-of-work "cake" wall (re-verified live 2026-08-22), so `hasFree` is `false` and the notes point at `g4f.dev/members.html`. The gateway still works with a member key, so its registry wiring and `authType: "optional"` are unchanged ([#10071](https://github.com/diegosouzapw/OmniRoute/issues/10071)) — thanks @chirag127

changelog.d/fixes/10550-responses-reasoning-transport.md

@@ -1 +1 @@
-- Preserve portable plaintext reasoning by default across streaming and non-streaming Chat Completions and Responses routes while keeping provider-bound opaque state target-compatible. Combos now drop incompatible continuation reasoning by default and can explicitly skip incompatible targets, while known providers no longer show redundant encrypted-reasoning controls. (#10550)
+- Preserve portable plaintext reasoning by default across streaming and non-streaming Chat Completions and Responses routes while keeping provider-bound opaque state target-compatible. Direct requests drop incompatible continuation reasoning by default; combos can explicitly skip incompatible targets without mutating the request. Known providers no longer show redundant encrypted-reasoning controls. (#10550, #10959)

changelog.d/fixes/10949-mixed-reasoning-plaintext.md

@@ -0,0 +1 @@
+- Preserve explicit plaintext reasoning when a Responses reasoning item also carries opaque provider state (rare OpenCode Go `deepseek-v4-flash` responses). Mixed plaintext + opaque input is projected onto the target transport: plaintext targets keep portable text, opaque targets keep provider state. Opaque-only reasoning is dropped when the selected target cannot replay it, allowing cross-model conversations to continue. (#10949, #10959)

changelog.d/fixes/11015-shutdown-track-sse.md

@@ -0,0 +1 @@
+- **fix(resilience):** count heavyweight `/v1` admission leases in the SIGTERM drain and send `Retry-After` on shutdown 503s so Recreate no longer looks like an empty 502 ([#11015](https://github.com/diegosouzapw/OmniRoute/issues/11015)) — thanks @RaviTharuma

changelog.d/fixes/11089-chat-routing-synced-inventory.md

@@ -0,0 +1 @@
+- **fix(resilience):** filter chat connection selection by each connection's *synced* model inventory on multi-host self-hosted providers (`ollama-local`, `lm-studio`, `vllm`, …), so a request for a model only one host advertises is pinned to that host instead of failing over onto a host that never had it ([#11089](https://github.com/diegosouzapw/OmniRoute/issues/11089))

changelog.d/fixes/11149-opencode-go-flat-rate.md

@@ -0,0 +1 @@
+- **fix(analytics):** `opencode-go` is now classified as a flat-rate subscription, so cost analytics shows $0 for it instead of billing every call at the underlying model’s metered rate — it resells GLM, Kimi, Grok, DeepSeek, MiniMax, Qwen and GPT-5.x under one flat monthly fee, which made the overstatement large rather than marginal ([#11149](https://github.com/diegosouzapw/OmniRoute/pull/11149)) — thanks @electrumguy

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

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

changelog.d/fixes/11180-keyless-custom-provider-auto-pool.md

@@ -0,0 +1 @@
+- **fix(routing):** a custom `openai-compatible-*` / `anthropic-compatible-*` connection pointing at a keyless self-hosted backend (llama.cpp, Ollama, vLLM started without an API key) now stays in the `auto/*` candidate pool instead of being silently dropped by the credential gate — for those IDs "no credential" is the normal configuration, not an unconfigured connection ([#11180](https://github.com/diegosouzapw/OmniRoute/pull/11180)) — thanks @marcs7

changelog.d/fixes/11181-lkgp-enabled-context.md

@@ -0,0 +1 @@
+- **fix(routing):** the Routing tab's "last known good provider" toggle now actually takes effect — `lkgpEnabled` was persisted and the `lkgp` strategy guarded on it, but the setting was never forwarded into the `RoutingContext` built in `resolveAutoStrategyOrder()`, so `context.lkgpEnabled` was always `undefined` and the off-switch was unreachable ([#11181](https://github.com/diegosouzapw/OmniRoute/issues/11181))

changelog.d/fixes/9763-ratelimit-mintime-floor.md

@@ -0,0 +1 @@
+- **fix(ratelimit):** respect operator `minTimeBetweenRequestsMs` floor when relaxing the limiter on headroom — the adaptive rate-limit learning no longer silently erases a configured minimum gap between requests when the upstream reports plenty of remaining capacity ([#9763](https://github.com/diegosouzapw/OmniRoute/issues/9763)).

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

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

config/quality/eslint-suppressions.json

@@ -853,11 +853,6 @@
       "count": 1
     }
   },
-  "src/app/api/usage/call-logs/route.ts": {
-    "no-restricted-imports": {
-      "count": 1
-    }
-  },
   "src/app/api/usage/quota/route.ts": {
     "no-restricted-imports": {
       "count": 1
@@ -953,11 +948,6 @@
       "count": 1
     }
   },
-  "src/app/api/v1/rerank/route.ts": {
-    "no-restricted-imports": {
-      "count": 1
-    }
-  },
   "src/app/api/v1/vscode/[token]/models/route.ts": {
     "no-restricted-syntax": {
       "count": 1
@@ -3259,4 +3249,4 @@
       "count": 5
     }
   }
-}
+}