v3.8.29

## [3.8.29] — 2026-06-19

### ✨ New Features

- **feat(cloud-agent): Cursor Cloud Agent via the official API-key REST API (no IDE-OAuth ban risk)** — adds a `cursor-cloud` cloud agent that drives Cursor's Background / Cloud Agents through the official REST API (`api.cursor.com`) authenticated with a user or service-account API key — the safer, first-party alternative to re-using the Cursor IDE's OAuth session (the existing `cursor` provider, which carries a ban-risk warning). Implemented as a plain REST adapter mirroring the Devin/Jules agents (`createTask`/`getStatus`/`sendMessage`/`listSources`), so it does **not** pull in the `@cursor/sdk` package and its per-platform native binaries (Cursor's SDK is itself a thin wrapper over this REST API). Cursor's UPPERCASE status enums (`CREATING`/`RUNNING`/`FINISHED`/`ERROR`) are mapped explicitly to the shared `CloudAgentStatus`, and `baseUrl` is overridable per-credential. Credentials are stored encrypted via the existing `cloud_agent_credentials` table; no schema change. ([#4227](https://github.com/diegosouzapw/OmniRoute/issues/4227) — thanks @MRDGH2821)
- **feat(routing): OpenRouter-style `auto/<category>:<tier>` combos** — auto-routing now understands suffixed combos that separate the _category_ (what kind of route) from the _tier_ (how to optimize): `auto/coding:fast`, `auto/coding:cheap` (alias `:floor`), `auto/coding:free`, `auto/coding:pro`, `auto/coding:reliable`, plus the new category roots `auto/reasoning`, `auto/vision`, `auto/multimodal`. The **tier** picks the scoring weights — `:fast` → ship-fast, `:cheap`/`:floor` → cost-saver, `:reliable` → a new reliability-first pack (circuit-breaker health + latency stability) — while `:free`/`:pro` filter the candidate pool by model tier (`classifyTier`: free-tier vs. premium models). The **category** filters the pool by capability (`vision`/`multimodal` → vision-capable models, `reasoning` → reasoning/thinking models). Any valid `auto/<category>:<tier>` resolves on demand; a curated set is advertised in `/v1/models` and the dashboard. Filtering is fail-open — if a constraint matches no connected models the full pool is used so routing never breaks. All composition lives in the new `open-sse/services/autoCombo/suffixComposition.ts`; the core combo scorer (`combo.ts`) is untouched. Second slice of #4235 (premium account-tier weighting is a later follow-up). ([#4235](https://github.com/diegosouzapw/OmniRoute/issues/4235) — thanks @MRDGH2821)
- **feat(routing): advertise the `auto/cheap`, `auto/offline`, `auto/smart` combos (catalog ↔ README sync)** — the README lists `auto/cheap` (cheapest-per-token first), `auto/offline` (most quota/rate-limit headroom first) and `auto/smart` (quality-first + 10% exploration), and they already resolved at request time via `parseAutoPrefix` → `createVirtualAutoCombo`. But they were missing from `AUTO_TEMPLATE_VARIANTS`, so `/v1/models` and the dashboard combos list (which iterate that catalog) never showed them — the catalog drifted from the docs (visible in the issue's screenshots). Added the three entries so they're advertised everywhere alongside the other built-in `auto/*` combos. First slice of #4235 (OpenRouter-style `auto/<category>:<tier>` suffixes + new categories follow). ([#4235](https://github.com/diegosouzapw/OmniRoute/issues/4235) — thanks @MRDGH2821)
- **feat(cli): remote mode — drive a remote OmniRoute with scoped access tokens** — a new CLI mode that connects to a remote OmniRoute instance using scoped access tokens, so a local CLI can drive a server you don't own a session on. ([#4256](https://github.com/diegosouzapw/OmniRoute/pull/4256))
- **feat(api): cost-telemetry parity — `X-OmniRoute-*` headers on every endpoint + a non-token cost engine** — every endpoint now emits the `X-OmniRoute-*` cost/usage headers, backed by a cost engine that also prices non-token (media/request-based) usage. ([#4247](https://github.com/diegosouzapw/OmniRoute/pull/4247))
- **feat(api): register Kimi K2.7 Code models (`kimi-k2.7-code` + `-highspeed`)** — the new Moonshot thinking-only coding models are registered (fixed sampling; `temperature`/`top_p` marked unsupported). ([#4183](https://github.com/diegosouzapw/OmniRoute/pull/4183))
- **feat(catalog): add `kimi-k2.7-code` to the kmca catalog + qwen-web models discovery** — surfaces the new Kimi coding model in the kmca catalog and wires qwen-web into model discovery. ([#4185](https://github.com/diegosouzapw/OmniRoute/pull/4185))
- **feat(api): expand the `zai` provider catalog with GLM-5.2 / GLM-4.7** — adds the real GLM-5.2, GLM-4.7 and GLM-4.7-flash model ids to the Anthropic-direct `zai` provider. ([#4201](https://github.com/diegosouzapw/OmniRoute/pull/4201))
- **feat(api): no-thinking gateway model IDs (FCC port, Fase 8.1)** — gateway model id variants that force thinking off, ported from free-claude-code. ([#4145](https://github.com/diegosouzapw/OmniRoute/pull/4145))
- **feat(sse): mid-stream continuation for truncated streams (FCC port, Task 4.4)** — when a stream is cut short, OmniRoute can transparently continue it, ported from free-claude-code. ([#4147](https://github.com/diegosouzapw/OmniRoute/pull/4147))
- **feat(sse): per-provider sliding-window rate-limit fallback (FCC port, Fase 8.2)** — a per-provider sliding-window rate limiter as a fallback path, ported from free-claude-code. ([#4146](https://github.com/diegosouzapw/OmniRoute/pull/4146))
- **feat(sse): transparent stream recovery (FCC port, Fase 4, opt-in)** — opt-in transparent recovery of interrupted upstream streams, ported from free-claude-code. ([#4131](https://github.com/diegosouzapw/OmniRoute/pull/4131))
- **feat(search): free DuckDuckGo web search as a last-resort provider (FCC port, Fase 6)** — adds a no-key DuckDuckGo web-search provider used as a last resort, ported from free-claude-code. ([#4136](https://github.com/diegosouzapw/OmniRoute/pull/4136))
- **feat(logging): credential-redaction safety net in the pino logger (FCC port, Fase 8.3)** — a logger-level redaction pass that scrubs credentials from log output, ported from free-claude-code. ([#4140](https://github.com/diegosouzapw/OmniRoute/pull/4140))
- **feat(memory): opt-in Qdrant scalar int8 quantization (F4.4 Q1)** — opt-in int8 scalar quantization for Qdrant-backed memory vectors. ([#4187](https://github.com/diegosouzapw/OmniRoute/pull/4187))
- **feat(memory): opt-in sqlite-vec int8 vector quantization (F4.4 Q2)** — opt-in int8 quantization for the sqlite-vec memory backend. ([#4190](https://github.com/diegosouzapw/OmniRoute/pull/4190))
- **feat(deploy): keep optional deps on `update` (`--include=optional`)** — the in-place update path now passes `--include=optional` so native/optional packages aren't dropped on update. ([#4260](https://github.com/diegosouzapw/OmniRoute/pull/4260))
- **feat(dashboard): unified visual identity — grid, primitives, tables, form controls (design phases 1-4)** — a sweeping design pass aligning the dashboard with the site: grid wallpaper, button/card/input primitives, theme-aware tables and form controls. ([#4122](https://github.com/diegosouzapw/OmniRoute/pull/4122))
- **feat(dashboard): grid wallpaper on all standalone screens + fluid 4K layout** — the identity grid now backs every standalone screen and the layout scales fluidly to 4K. ([#4158](https://github.com/diegosouzapw/OmniRoute/pull/4158))
- **feat(dashboard): make the identity grid visible + unify the focus ring on accent** — design follow-up making the grid actually visible and standardizing focus rings on the accent color. ([#4141](https://github.com/diegosouzapw/OmniRoute/pull/4141))
- **feat(dashboard): import only free models + free-model list controls** — the model-import page can import just the free models, with controls to manage the free-model list. ([#4176](https://github.com/diegosouzapw/OmniRoute/pull/4176) — thanks @felipesartori)
- **feat(dashboard): compact grid layout for no-auth provider accounts** — a denser grid layout for provider accounts when auth is disabled. ([#4137](https://github.com/diegosouzapw/OmniRoute/pull/4137) — thanks @felipesartori)
- **feat(dashboard): derive media `serviceKinds` from the registries (surface MiniMax + the media catalog)** — `/media-providers/[kind]` now derives its service kinds from the registries instead of a hand-maintained list, surfacing ~48 previously-invisible media providers (incl. MiniMax TTS/video/music). ([#4212](https://github.com/diegosouzapw/OmniRoute/pull/4212))
- **feat(traffic-inspector): live (in-flight) request filter (Gap 5)** — the Traffic Inspector can filter to in-flight requests as they happen. ([#4130](https://github.com/diegosouzapw/OmniRoute/pull/4130))
- **feat(agent-bridge): maintenance & diagnostics dashboard controls** — adds maintenance and diagnostics controls for the Agent Bridge to the dashboard. ([#4127](https://github.com/diegosouzapw/OmniRoute/pull/4127))
- **feat(mitm): TPROXY IP_TRANSPARENT native addon + conditional loader (Epic A)** — a native `IP_TRANSPARENT` addon with a conditional loader, the foundation for TPROXY capture. ([#4148](https://github.com/diegosouzapw/OmniRoute/pull/4148))
- **feat(mitm): Fase 3 Epic A spike — TPROXY command builder** — a transactional builder for the iptables/TPROXY command set. ([#4139](https://github.com/diegosouzapw/OmniRoute/pull/4139))
- **feat(mitm): TPROXY setup layer — transactional apply/revert (Epic A)** — applies and reverts the TPROXY routing setup transactionally. ([#4144](https://github.com/diegosouzapw/OmniRoute/pull/4144))
- **feat(mitm): add `setSocketMark` to the TPROXY addon (anti-loop primitive)** — exposes `setSocketMark` so OmniRoute's own egress can be marked and skipped (anti-loop). ([#4160](https://github.com/diegosouzapw/OmniRoute/pull/4160))
- **feat(mitm): TPROXY capture-mode listener + `connectMarked` (Epic A)** — the capture-mode listener plus a marked-connect primitive. ([#4169](https://github.com/diegosouzapw/OmniRoute/pull/4169))
- **feat(mitm): dynamic per-SNI cert authority for TPROXY (TLS decrypt 1/N)** — a per-SNI on-the-fly certificate authority, the first slice of TLS decrypt. ([#4173](https://github.com/diegosouzapw/OmniRoute/pull/4173))
- **feat(mitm): TLS-terminating capture for TPROXY (decrypt 2/N)** — terminates TLS to capture decrypted traffic. ([#4179](https://github.com/diegosouzapw/OmniRoute/pull/4179))
- **feat(mitm): wire the TLS decrypt engine into TPROXY capture mode (decrypt 3/N)** — connects the decrypt engine to the capture-mode pipeline. ([#4200](https://github.com/diegosouzapw/OmniRoute/pull/4200))
- **feat(mitm): TPROXY capture-mode manager (decrypt 4a/N)** — a manager coordinating the TPROXY capture lifecycle. ([#4208](https://github.com/diegosouzapw/OmniRoute/pull/4208))
- **feat(mitm): local-only route + trust-store installer for TPROXY decrypt (4b/N)** — a loopback-only management route plus a CA trust-store installer for the decrypt CA. ([#4211](https://github.com/diegosouzapw/OmniRoute/pull/4211))
- **feat(dashboard): TPROXY decrypt capture toggle in the Traffic Inspector (4c/N)** — a UI toggle to enable/disable decrypted capture. ([#4216](https://github.com/diegosouzapw/OmniRoute/pull/4216))
- **feat(compression): replace the headroom tabular encoder with a vendored GCF** — swaps the tabular encoder for a vendored GCF implementation. ([#4167](https://github.com/diegosouzapw/OmniRoute/pull/4167) — thanks @blackwell-systems)
- **feat(compression): live per-engine streaming via `compression.step` (F3.3)** — streams per-engine compression progress through a `compression.step` event. ([#4217](https://github.com/diegosouzapw/OmniRoute/pull/4217))
- **feat(compression): show an engine node for single-engine runs in the studio** — the Compression Studio now renders an engine node even when only one engine runs. ([#4210](https://github.com/diegosouzapw/OmniRoute/pull/4210))
- **feat(compression): expose the WaterfallInspector via a Canvas/Waterfall toggle** — adds a Canvas/Waterfall view toggle that surfaces the WaterfallInspector. ([#4238](https://github.com/diegosouzapw/OmniRoute/pull/4238))
- **feat(compression): make `mcpAccessibility` config reachable via a settings sub-route** — exposes the `mcpAccessibility` config under a dedicated settings sub-route. ([#4237](https://github.com/diegosouzapw/OmniRoute/pull/4237))
- **feat(compression): runnable A/B benchmark CLI (F2.4)** — a CLI to run A/B compression benchmarks. ([#4220](https://github.com/diegosouzapw/OmniRoute/pull/4220))
- **feat(compression): add a transcript loader to the replay harness** — the replay harness can now load real transcripts. ([#4246](https://github.com/diegosouzapw/OmniRoute/pull/4246))
- **feat(compression): wire MCP tool-cardinality reduction (F4.3, opt-in)** — opt-in reduction of MCP tool-set cardinality to shrink prompts. ([#4221](https://github.com/diegosouzapw/OmniRoute/pull/4221))
- **feat(compression): wire RTK comment-stripping config + honor `preserveDocstrings`** — RTK comment-stripping is now configurable and honors a `preserveDocstrings` flag. ([#4242](https://github.com/diegosouzapw/OmniRoute/pull/4242))
- **feat(compression): honor the per-filter RTK `deduplicate` flag** — RTK filters now respect a per-filter `deduplicate` flag. ([#4231](https://github.com/diegosouzapw/OmniRoute/pull/4231))
- **feat(compression): honor the registry `enabled` flag in the stacked loop** — the stacked compression loop now skips engines disabled in the registry. ([#4244](https://github.com/diegosouzapw/OmniRoute/pull/4244))
- **feat(compression): persist RTK grouping config (unlock R5 `enableGrouping`)** — persists the RTK grouping configuration, unlocking the R5 `enableGrouping` rule. ([#4207](https://github.com/diegosouzapw/OmniRoute/pull/4207))
- **feat(compression): wire ultra's `modelPath`/`slmFallbackToAggressive` to the LLMLingua SLM tier** — connects the ultra tier's small-language-model knobs to the LLMLingua SLM path. ([#4257](https://github.com/diegosouzapw/OmniRoute/pull/4257))
- **feat(quality): Onda 2 mutation-gate tooling — radiography classifier (T1) + `mutationScore` ratchet (T3)** — new mutation-testing tooling: a survivor-radiography classifier and a `mutationScore` ratchet. ([#4234](https://github.com/diegosouzapw/OmniRoute/pull/4234))
- **feat(ci): wire the F2.4 compression budget-gate ratchet** — adds a CI ratchet that gates compression budget regressions. ([#4232](https://github.com/diegosouzapw/OmniRoute/pull/4232))

### 🐛 Fixed

- **fix(providers): qwen-web model discovery now lists the live catalog instead of nothing** — the `qwen-web` cookie provider had no entry in `PROVIDER_MODELS_CONFIG`, so its model-discovery page returned an empty/stale local catalog (the OAuth fallback at the top of the route only fires for `provider === "qwen"`, leaving `qwen-web` to fall through to the no-config branch). Added a `qwen-web` entry that fetches the **public** `https://chat.qwen.ai/api/v2/models` endpoint (no auth header) and parses the `{ data: { data: [{ id, name, owned_by }] } }` shape (with a flatter `{ data: [] }` fallback). This is Problem #3 of #3931 (diagnosed by @thezukiru); Problem #1 — validator bare-token false-positive — shipped earlier in #3958, and Problem #2 — empty stream from Qwen WAF bot-detection on the streaming endpoint — remains a separate upstream/stealth concern. ([#3931](https://github.com/diegosouzapw/OmniRoute/issues/3931) — thanks @thezukiru)
- **fix(providers): ZenMux model discovery now lists the live catalog (incl. the free models) instead of the stale 9-entry hardcoded list** — adding a ZenMux key validated fine, but the connection then showed `API unavailable — using local catalog` and was missing the free models ZenMux advertises (`z-ai/glm-5.2-free`, `moonshotai/kimi-k2.7-code-free`). Root cause: `zenmux` carries a correct `modelsUrl` in the registry, but — like `llm7`/`byteplus` before #3976 — it was not classified by any live-fetch branch of the model-import route (not `openai-compatible-*`, not self-hosted, not in `NAMED_OPENAI_STYLE_PROVIDERS`), so the route never probed the upstream `/models` and fell through to the registry's hardcoded `models[]`. Added `zenmux` to `NAMED_OPENAI_STYLE_PROVIDERS`, so the route probes `https://zenmux.ai/api/v1/models` (the `/chat/completions`-stripped `<baseUrl>/models` candidate) and serves the live list, falling back to the local catalog only when the upstream fetch fails — import never breaks. ([#4202](https://github.com/diegosouzapw/OmniRoute/issues/4202) — thanks @mikmaneggahommie)
- **fix(providers): Vercel AI Gateway "import models" now loads the live catalog instead of nothing** — adding a Vercel AI Gateway key worked, but clicking **import** on the models page loaded nothing usable (manually adding the same models worked). Same class as #4202 (zenmux) / #3976 (llm7/byteplus): `vercel-ai-gateway` carries a real `baseUrl` (`https://ai-gateway.vercel.sh/v1/chat/completions`, format `openai`) in the registry, but was not classified by any live-fetch branch of the model-import route (not `openai-compatible-*`, not self-hosted, not in `NAMED_OPENAI_STYLE_PROVIDERS`), so the route never probed the upstream `/models` and fell through to the registry's tiny 5-entry hardcoded `models[]`. Added `vercel-ai-gateway` to `NAMED_OPENAI_STYLE_PROVIDERS`, so the route probes `https://ai-gateway.vercel.sh/v1/models` (the `/chat/completions`-stripped `<baseUrl>/models` candidate) and serves the live list, falling back to the local catalog only when the upstream fetch fails — import never breaks. ([#4249](https://github.com/diegosouzapw/OmniRoute/issues/4249) — thanks @FerLuisxd)
- **fix(sse): clear error when the request queue drops a job (no more fake-upstream "This job timed out after Nms")** — under concurrent load, requests that exceed the per-connection rate-limit queue budget (`resilienceSettings.requestQueue.maxWaitMs`) were dropped by Bottleneck with its raw `This job timed out after <maxWaitMs> ms.` message. That string is indistinguishable from an upstream gateway timeout, so the 502 body and call-log `last_error` looked like a provider outage across unrelated providers (TI:0\|TO:0) — an operator spent ~3h misdiagnosing local queue saturation as upstream failures. `withRateLimit` now rewrites that specific Bottleneck error into a clear, OmniRoute-owned message that names the knob (`requestQueue.maxWaitMs`, tunable in Settings → Resilience), explicitly disclaims an upstream timeout, preserves the original as `cause`, and tags `code: "RATE_LIMIT_QUEUE_TIMEOUT"`. Behavior is unchanged — the job is still dropped so combo falls back to the next target. ([#4165](https://github.com/diegosouzapw/OmniRoute/issues/4165) — thanks @KooshaPari)
- **fix(api): advertise the built-in `auto/*` combos in `/v1/models`** — OmniRoute ships a zero-setup `auto/*` catalog (`auto/best-coding`, `auto/pro-reasoning`, …, 16 variants) that the dashboard advertises and that resolve on demand, but the `/v1/models` listing only emitted persisted DB combos + provider models. Clients that build their model picker from `/v1/models` (e.g. Hermes Agent) never saw any `auto/*` option. The catalog now emits every `AUTO_TEMPLATE_VARIANTS` id (as `owned_by: "combo"`) at the top of the list, deduped against persisted combos. (Showing each `auto/*`'s dynamically-selected members is a separate enhancement.) ([#4164](https://github.com/diegosouzapw/OmniRoute/issues/4164) — thanks @MRDGH2821)
- **fix(sse): restore MCP / third-party tool names on the native Claude path (MCP dispatch broken in Claude Code)** — since 3.8.27, every MCP tool call routed through OmniRoute to a native Claude OAuth provider failed client-side with `Error: No such tool available: <PascalCaseName>`: tool schemas arrived fine but the streamed `tool_use.name` reached Claude Code in its cloaked form (e.g. `McpN8nMcpSearchWorkflows` instead of the registered `mcp__n8n-mcp__search_workflows`). The native-Claude tool-name cloak stashes its per-request alias→original map as a **non-enumerable** `_toolNameMap` on the request body; the request-inspector capture added in 3.8.27 rebuilds the captured body from its serialized form (`JSON.parse(JSON.stringify(...))`), which drops non-enumerable properties, so `finalBody._toolNameMap` was empty and the response-side un-cloak silently fell back to the static built-in map — never restoring dynamic MCP / snake_case names. Built-in tools (Bash/Read/…) were unaffected (static map); cross-format paths were unaffected (they attach the map enumerably). The provider-request capture now re-attaches the per-request map (kept non-enumerable, so it still never re-serializes upstream) when the captured copy lost it, restoring MCP tool dispatch. ([#4091](https://github.com/diegosouzapw/OmniRoute/issues/4091) — thanks @pedrotecinf, @NakHalal)
- **fix(dashboard): Logs auto-refresh self-heals in embedded/proxied hosts that pin or mis-fire visibility** — a follow-up to #4054: the Request Logger still froze auto-refresh on some hosts (reported on 3.8.28 Docker, works on 3.8.24). #4054 made the initial visibility fail-open, but the pause is event-driven — a host that fires a one-shot `visibilitychange` → hidden and then keeps reporting `"hidden"` (or recovers without firing the event again) left the cached visibility flag stuck `false`, so the interval ticked but never polled (only the manual Refresh button worked). The poll tick now also re-checks the **live** `document.visibilityState`, and a **window `focus`** listener re-arms polling (a focused window is a reliable signal the page is actively viewed). A genuinely backgrounded browser tab still pauses (it reports `"hidden"` and never receives focus), preserving the #3109 network-saturation optimization. ([#4133](https://github.com/diegosouzapw/OmniRoute/issues/4133) — thanks @tjengbudi)
- **fix(capabilities): unify vision model-id detection into one shared source** — three code paths kept independent, drifting vision-model lists, so the same model id could get up to three different verdicts. Two concrete bugs: lite compression's gate was missing pixtral / llava / qwen-vl / glm-4v / kimi-vl / mistral-medium-3, so it **stripped images for those real vision models and blinded them** (same class as #4071 / #4012); and the `/v1/models` list was too broad, flagging text models (`gemma`, bare `kimi` like `kimi-k2`) as vision. All three (`modelCapabilities` routing fallback, `/v1/models` listing, lite image-strip gate) now delegate to a single conservative source `src/shared/constants/visionModels.ts`, which also restores `glm-4v` / `gemini-3` coverage and keeps the #3328 MiniMax M3 carve-out. ([#4072](https://github.com/diegosouzapw/OmniRoute/issues/4072) — thanks @diego-anselmo)
- **fix(sse): surface mid-stream Gemini errors instead of returning a truncated 200** — when an upstream Gemini SSE stream emitted some partial content and then a JSON error object (`{"error":{"code":503,"message":"…high demand…","status":"UNAVAILABLE"}}`) instead of a `candidates` payload, OmniRoute silently dropped it: the gemini→openai translator's no-candidate branch only handled `promptFeedback` (content-filter) and returned `null` for anything else, so the stream simply ended and the client got HTTP 200 with a truncated body and `finish_reason: "stop"` — masking the failure and skipping combo fallback. `geminiToOpenAIResponse` now detects an `error` object (optionally wrapped in `response`), records it as `state.upstreamError` (preserving the real status — 503/`UNAVAILABLE`, or 429 for `RESOURCE_EXHAUSTED`), and lets `stream.ts` error the stream out through the existing `onFailure`/`buildErrorBody`/`controller.error` path — the same mechanism the openai-responses translator already uses. ([#4177](https://github.com/diegosouzapw/OmniRoute/issues/4177) — thanks @hartmark)
- **fix(capabilities): resolve models.dev-synced vision metadata for Mistral `-latest` aliases** — root cause behind the #4071 heuristic: `getResolvedModelCapabilities("mistral/pixtral-12b-latest").supportsVision` resolved `null` (vision came only from the #4071 model-id heuristic, with `attachment` still `null`) even though models.dev exposes the model as multimodal. Confirmed against the live models.dev API: it catalogs Pixtral 12B under the **short** id `pixtral-12b` (with `attachment: true`, `modalities.input: ["text","image"]`), while requests use the Mistral API alias `pixtral-12b-latest`. The synced lookup tried the exact / raw / static-spec-canonical ids — all of which miss the short form — so it fell through to the heuristic. `getSyncedCapabilityForResolved` now adds a last-resort fallback that retries with a trailing `-latest` stripped, so synced metadata (`attachment` / image modalities) wins for these aliases; models whose `-latest` id is stored verbatim (e.g. `pixtral-large-latest`) keep resolving directly. Note: the models.dev sync is currently manual-only (Settings → models.dev) with no scheduled refresh, so a fresh instance still relies on the #4071 heuristic until that sync runs — a periodic-refresh cadence is left as a separate follow-up. ([#4073](https://github.com/diegosouzapw/OmniRoute/issues/4073) — thanks @diego-anselmo)
- **fix(sse): map Xiaomi MiMo reasoning control to its native `thinking:{type}` shape** — MiMo (`api.xiaomimimo.com`) controls chain-of-thought **only** via top-level `thinking:{type:"enabled"|"disabled"}` and does not understand OpenAI's `reasoning_effort`/`reasoning`, while its request validator is strict (`400 Param Incorrect`). OmniRoute's OpenAI path carried reasoning intent as `reasoning_effort`, and the claude→openai translator can leave a Claude-shaped `thinking:{type, budget_tokens}` — so the client's on/off choice was silently dropped and `budget_tokens`/`reasoning_effort` rode along as extra params the validator can reject. New `open-sse/services/mimoThinking.ts::normalizeMimoThinking` (wired in `chatCore` for `provider==="xiaomi-mimo"`) reduces any thinking object to just `{type}` (`disabled` stays; `enabled`/`adaptive`/other → `enabled`) and drops `reasoning_effort`/`reasoning`. It deliberately does **not** synthesize thinking from a bare `reasoning_effort` — `mimo-v2-omni` is non-thinking, so that could turn a silently-ignored param into a hard error. ([#4224](https://github.com/diegosouzapw/OmniRoute/pull/4224))
- **fix(capabilities): Xiaomi MiMo `*-pro` chat models are text-only (no vision)** — only `mimo-v2.5` and `mimo-v2-omni` accept images per Xiaomi's docs; `mimo-v2.5-pro`/`mimo-v2-pro` are text-only, but `modelSpecs` marked them vision-capable and models.dev mislabels them ([hermes-agent#18884](https://github.com/NousResearch/hermes-agent/issues/18884)). Since `resolveVisionCapability` lets a synced `attachment:true` win first, an image request could be routed to a blind model (the #4071 failure mode). Corrected the specs **and** added a hard override in `resolveVisionCapability` (checked before the synced branch, anchored so `mimo-v2.5-pro` never matches the multimodal `mimo-v2.5`) that beats the wrong synced attachment. Also registered the missing native `mimo-v2-pro` chat model and the missing `mimo-v2-tts` speech model. ([#4224](https://github.com/diegosouzapw/OmniRoute/pull/4224))
- **fix(sse): Claude Opus 4.7+/Fable 5 use adaptive thinking only (no more manual-budget 400s)** — Opus 4.7 and later (Opus 4.7/4.8, Fable 5) removed manual extended thinking: `thinking.type:"enabled"` or **any** `thinking.budget_tokens` now returns `400` ("Any request that tries to set a fixed thinking budget gets a 400" — Anthropic migration guide). Reasoning is adaptive-only, steered by `output_config.effort`. OmniRoute's OpenAI→Claude translator mapped `reasoning_effort` low/medium/high to a manual `thinking:{type:"enabled", budget_tokens}`, so those requests hard-400'd on the most-used provider (and a Claude-native passthrough client sending the legacy shape did too). A new `adaptiveThinkingOnly` model flag now drives two fixes: the translator maps `reasoning_effort` of **every** level to `{type:"adaptive"}` + `output_config.effort` (preserving the requested level, never a budget) for these models, and a `normalizeClaudeAdaptiveThinking` catch-all at the existing post-translation thinking-normalization chokepoint collapses any residual manual thinking (passthrough legacy shape, per-model defaults) to `{type:"adaptive"}`, keyed on the resolved upstream model so it covers every routing mode. Pre-4.7 models (Opus 4.6/4.5, Sonnet, Haiku) keep manual budgets unchanged. ([#4230](https://github.com/diegosouzapw/OmniRoute/pull/4230))
- **fix(providers): strip non-default temperature/top_p/top_k for Claude Opus 4.7+/Fable 5 (fixed sampling → no 400)** — Opus 4.7 and later reject non-default `temperature`/`top_p`/`top_k` with a `400` (sampling is fixed; reasoning moved to `output_config.effort`). The translator forwarded client-supplied `temperature`/`top_p` unconditionally and the Claude registry models carried no `unsupportedParams`, so a plain OpenAI-format request with `temperature: 0.7` to `claude-opus-4-8` hard-400'd. Added `unsupportedParams: ["temperature","top_p","top_k"]` to the Opus 4.7+/Fable 5 ids in both the `claude` (dashed `claude-opus-4-8`) and `anthropic` (dotted `claude-opus-4.7`) registries, so they're stripped at the existing `getUnsupportedParams` dispatch chokepoint. Pre-4.7 Claude models still accept sampling params. ([#4230](https://github.com/diegosouzapw/OmniRoute/pull/4230))
- **fix(providers): conditionally strip temperature/top_p for GPT-5 reasoning on the `openai` Chat Completions path (no 400 when an effort is active)** — GPT-5 reasoning models reject non-default `temperature`/`top_p` with a `400` whenever a reasoning effort is active, yet accept them again under `reasoning_effort:"none"` (the GPT-5.1+ default, i.e. non-reasoning mode). On the `openai` provider only `o3` carried `REASONING_UNSUPPORTED`; `gpt-5.5`/`gpt-5.4`/`gpt-5.4-mini`/`gpt-5.4-nano` carried no sampling guard, so a `temperature` + active-effort request hard-400'd. A static `unsupportedParams` list can't express the `none`-mode carve-out (it would over-strip the legitimate case), so the new `gpt5SamplingGuard` drops `temperature`/`top_p` only when the resolved effort is active — wired at the existing `getUnsupportedParams` chokepoint and scoped to the `openai` Chat Completions surface (the `codex` Responses path is already covered by the CodexExecutor allowlist; other providers are untouched). ([#4245](https://github.com/diegosouzapw/OmniRoute/pull/4245))
- **fix(codex): stop silently dropping GPT-5 output verbosity (`verbosity` / `text.verbosity`)** — the GPT-5 series added an output-verbosity control: `verbosity` (low/medium/high) on Chat Completions, nested as `text.verbosity` on the Responses API. The CodexExecutor gates translated requests through an allowlist that had no `text` entry, so for the `codex` provider the hint was dropped before reaching upstream (the `openai` Chat path already forwarded it). `normalizeCodexVerbosity` now folds whichever shape arrived into a single validated `text:{verbosity}` before the allowlist (which now permits `text`), and the OpenAI Chat↔Responses request translators map `verbosity` across formats so the hint survives a format crossing for non-codex Responses backends too. Invalid/absent verbosity collapses to no `text` (status quo). ([#4245](https://github.com/diegosouzapw/OmniRoute/pull/4245))
- **fix(sse): map `reasoning_effort` to DeepSeek V4's native `{high, max}` vocabulary** — DeepSeek V4 only understands `high`/`max` reasoning levels, so other `reasoning_effort` values are mapped onto its native vocabulary instead of being rejected. ([#4219](https://github.com/diegosouzapw/OmniRoute/pull/4219))
- **fix(glm): default `max_tokens` and an extended timeout for GLM-5.2+ thinking** — GLM-5.2+ thinking responses are slow and need headroom, so OmniRoute now sets a sensible default `max_tokens` and a longer timeout for them. ([#4255](https://github.com/diegosouzapw/OmniRoute/pull/4255) — thanks @dhaern)
- **fix(antigravity): default `includeThoughts` for modern Gemini models** — modern Gemini models on the Antigravity path now default to including thoughts so reasoning isn't silently dropped. ([#4180](https://github.com/diegosouzapw/OmniRoute/pull/4180) — thanks @dhaern)
- **fix(models): expose combo model token limits** — `/v1/models` now reports token limits for combo models. ([#4189](https://github.com/diegosouzapw/OmniRoute/pull/4189) — thanks @megamen32)
- **fix(combo): keep the passthrough quota fallback scoped** — prevents the passthrough quota fallback from leaking across unrelated targets. ([#4194](https://github.com/diegosouzapw/OmniRoute/pull/4194) — thanks @Svetznaniy33)
- **fix(combo): opt proactive-fallback compression into the TV1 bail-out (no silent target drop)** — proactive-fallback compression now participates in the TV1 bail-out so a target is never silently dropped. ([#4228](https://github.com/diegosouzapw/OmniRoute/pull/4228))
- **fix(compression): show engine preview output** — the Compression Studio preview now renders the engine's output. ([#4128](https://github.com/diegosouzapw/OmniRoute/pull/4128) — thanks @megamen32)
- **fix(compression): harden engines against I/O failures and misconfig (F5.3)** — compression engines degrade gracefully on I/O errors and bad configuration instead of throwing. ([#4198](https://github.com/diegosouzapw/OmniRoute/pull/4198))
- **fix(compression): harden RTK raw-output redaction + ReDoS guard for custom filters (F5.3)** — broadens RTK raw-output redaction and adds a ReDoS guard for user-supplied filter patterns. ([#4203](https://github.com/diegosouzapw/OmniRoute/pull/4203))
- **fix(compression): bound `mcpAccessibility` `maxTextChars` on the live read path** — the live read path now clamps `maxTextChars` so a small value can't make tools disappear. ([#4206](https://github.com/diegosouzapw/OmniRoute/pull/4206))
- **fix(dashboard): data tables paint an opaque surface so the grid doesn't bleed through** — data tables now render on an opaque surface, fixing the grid wallpaper showing through. ([#4233](https://github.com/diegosouzapw/OmniRoute/pull/4233))
- **fix(dashboard): make the provider card hover visible (was ~1% opacity)** — the provider-card hover state was effectively invisible; it now has a visible surface. ([#4214](https://github.com/diegosouzapw/OmniRoute/pull/4214))
- **fix(vscode): sanitize implicit editor context** — redacts sensitive filenames/keywords from the implicit VS Code editor context before it's sent upstream. ([#4124](https://github.com/diegosouzapw/OmniRoute/pull/4124) — thanks @zhiru)
- **fix(build): raise the Node heap for the local `next build` to stop OOM/stall** — bumps the build-time heap so the local production build no longer OOMs or stalls. ([#4171](https://github.com/diegosouzapw/OmniRoute/pull/4171))
- **fix(mitm): TPROXY OUTPUT-based recipe for local traffic (validated e2e on VPS)** — switches the TPROXY rules to an OUTPUT-chain recipe so locally-originated traffic is captured; validated end-to-end on the VPS. ([#4156](https://github.com/diegosouzapw/OmniRoute/pull/4156))
- **fix(mitm): forward anti-loop — put the bypass-marked socket on the Agent (decrypt 4d)** — places the bypass-marked socket on the HTTP Agent so OmniRoute's own forwarded traffic never re-enters the capture loop; VPS-validated. ([#4229](https://github.com/diegosouzapw/OmniRoute/pull/4229))
- **fix(free-tiers): retire dead-tier `hasFree`, round the headline to ~1.6B, regenerate the per-provider table** — drops dead free tiers from the headline math and regenerates the per-provider free-tier table. ([#4142](https://github.com/diegosouzapw/OmniRoute/pull/4142))
- **fix(free-tiers): retire 4 re-verified-dead free tiers, flag iflytek/sparkdesk ToS, clarify monsterapi one-time** — removes four confirmed-dead free tiers and annotates ToS/one-time caveats. ([#4152](https://github.com/diegosouzapw/OmniRoute/pull/4152))

### 🧪 Tests

- **test(sse): guard the Antigravity `_toolNameMap` cloak map through the request-capture round-trip** — follow-up to #4091: the generic capture fix in `createPreparedRequestLogger().body()` (#4153) re-attaches the non-enumerable `_toolNameMap` that the request-inspector drops when it rebuilds the upstream body via `JSON.parse(JSON.stringify(...))`, but the only regression test covered the native-Claude OAuth cloak (PascalCase aliases). The Antigravity cloak differs — `cloakAntigravityToolPayload` suffixes custom tools with `_ide` (`workspace_read` → `workspace_read_ide`), leaves native tools untouched, and returns the reverse map separately — so a refactor of `providerRequestLogging.ts` or the executor could silently re-break Antigravity tool dispatch without tripping the Claude test. Adds a dedicated regression test driving the real `cloakAntigravityToolPayload` through the capture round-trip and asserting the `_ide` reverse map survives, stays non-enumerable (never re-serializes upstream), and that all-native traffic produces no spurious map (verified failing with the #4153 re-attach removed). No production change. ([#4181](https://github.com/diegosouzapw/OmniRoute/issues/4181) — thanks @hertznsk)
- **test(chatcore): dedicated unit tests for 6 leaves + wire into stryker mutate (QG v2 Fase 9 T5 Fase 3)** — adds focused unit tests for 6 chatCore leaf helpers and enrolls them in mutation testing. ([#4218](https://github.com/diegosouzapw/OmniRoute/pull/4218))
- **test(chatcore): telemetry / memory-skills / semantic-cache tests + wire 2 into stryker (QG v2 Fase 9 T5 Fase 3)** — new tests for the telemetry, memory-skills and semantic-cache leaves, two of which are added to the mutation set. ([#4222](https://github.com/diegosouzapw/OmniRoute/pull/4222))
- **test+ci(chatcore): semanticCache HIT-path fixture (15/15 mutate) + 350min budget headroom** — closes the semantic-cache HIT path to a full 15/15 mutation score and gives the nightly auth/accountFallback batches more budget headroom. ([#4225](https://github.com/diegosouzapw/OmniRoute/pull/4225))
- **test(compression): close F5.1 coverage gaps (replay reducer, live accumulator, StatusDot)** — fills the remaining F5.1 compression coverage gaps. ([#4192](https://github.com/diegosouzapw/OmniRoute/pull/4192))
- **test(db,sse): de-flake db-backup + chatcore streaming timing assertions** — stabilizes two timing-sensitive tests (fire-and-forget backup completion + a streaming race). ([#4132](https://github.com/diegosouzapw/OmniRoute/pull/4132))
- **test: align stale integration tests surfaced post-v3.8.28 on main** — realigns integration tests that drifted after the v3.8.28 merge. ([#4129](https://github.com/diegosouzapw/OmniRoute/pull/4129))

### 📝 Maintenance

- **refactor(sse): split chatCore.ts pure helpers into chatCore/ modules (−561 LOC)** — extracts pure helpers out of the chatCore god-file into dedicated modules (Onda 3). ([#4159](https://github.com/diegosouzapw/OmniRoute/pull/4159))
- **refactor(chatcore): extract passthrough/header/telemetry helpers (QG v2 Fase 9 T5 C2-C3-C5)** — further chatCore decomposition. ([#4188](https://github.com/diegosouzapw/OmniRoute/pull/4188))
- **refactor(chatcore): extract combo/proxy context cache + semaphore helpers (QG v2 Fase 9 T5 C6-C7)** — continues the chatCore split. ([#4193](https://github.com/diegosouzapw/OmniRoute/pull/4193))
- **refactor(combo): god-file split pilot — types + validateQuality + predicates (QG v2 Fase 9 T5 D1-D3)** — first slice of the combo.ts decomposition. ([#4162](https://github.com/diegosouzapw/OmniRoute/pull/4162))
- **refactor(combo): god-file split part 2 — shadow + sorters + structure (QG v2 Fase 9 T5 D4-D6)** — continues the combo.ts split. ([#4175](https://github.com/diegosouzapw/OmniRoute/pull/4175))
- **refactor(combo): god-file split part 3 — auto strategy (QG v2 Fase 9 T5 D8)** — extracts the auto strategy from combo.ts. ([#4186](https://github.com/diegosouzapw/OmniRoute/pull/4186))
- **refactor(combo): extract round-robin sticky state to `combo/rrState.ts` (D7a)** — moves round-robin sticky state into its own module. ([#4196](https://github.com/diegosouzapw/OmniRoute/pull/4196))
- **refactor(combo): extract the reset-aware quota block to `combo/quotaStrategies.ts` (D7b)** — moves the reset-aware quota strategies into their own module. ([#4204](https://github.com/diegosouzapw/OmniRoute/pull/4204))
- **refactor(compression): remove vestigial SLM seam + dead deprecated alias** — drops dead compression code. ([#4253](https://github.com/diegosouzapw/OmniRoute/pull/4253))
- **chore(compression): remove vestigial reconstructCcr/SessionDedup round-trip helpers** — removes unused round-trip helpers. ([#4226](https://github.com/diegosouzapw/OmniRoute/pull/4226))
- **chore(compression): remove dead exports + fix stale llmlingua docs** — prunes dead exports and corrects stale LLMLingua docs. ([#4223](https://github.com/diegosouzapw/OmniRoute/pull/4223))
- **chore(build): build + ship the TPROXY native addon in the standalone (prebuilds 4e)** — bundles the native TPROXY addon prebuilds into the standalone build. ([#4236](https://github.com/diegosouzapw/OmniRoute/pull/4236))
- **chore(ci): add quota + 6 covered chatCore leaves to stryker mutate (QG v2 Fase 9 T5 Fase 3 follow-up)** — enrolls more covered leaves into mutation testing. ([#4209](https://github.com/diegosouzapw/OmniRoute/pull/4209))
- **chore(ci): re-add 8 combo split leaves to stryker mutate + expand nightly batch-matrix 3→5 (QG v2 Fase 9 T5 Fase 3)** — restores mutation coverage for the split combo leaves and widens the nightly matrix. ([#4205](https://github.com/diegosouzapw/OmniRoute/pull/4205))
- **chore(quality): close v3.8.28 cycle gate drift (re-baseline + nightly-mutation scope)** — reconciles quality-gate baselines after the v3.8.28 cycle. ([#4135](https://github.com/diegosouzapw/OmniRoute/pull/4135))
- **ci(mutation): split nightly into 3 parallel batches to fit the 180min budget (QG v2 Fase 9 T0)** — parallelizes the nightly mutation run. ([#4150](https://github.com/diegosouzapw/OmniRoute/pull/4150))
- **ci(mutation): restore cold-seed timeout headroom (a/b lost in #4225 squash) + extend to c/d/g/h** — restores and extends per-batch cold-seed timeouts. ([#4258](https://github.com/diegosouzapw/OmniRoute/pull/4258))
- **ci(docs): harden the fabricated-docs checker + enforce `--strict` (QG v2 Fase 9 T9)** — tightens the anti-hallucination docs checker. ([#4149](https://github.com/diegosouzapw/OmniRoute/pull/4149))
- **ci: derive the oasdiff base-ref from the package version + flag the mutation-toolchain regression** — fixes the OpenAPI-diff base-ref and surfaces a mutation-toolchain regression. ([#4134](https://github.com/diegosouzapw/OmniRoute/pull/4134))
- **docs(ci): correct the mutation-gate note (no regression — `stryker -c` is `--concurrency`); record Task 12 GO** — corrects a misread of the stryker flag and records the spike GO. ([#4138](https://github.com/diegosouzapw/OmniRoute/pull/4138))
- **docs(api): document the `/api/v1/ws` chat WebSocket endpoint in openapi.yaml** — adds the WebSocket chat endpoint to the OpenAPI spec. ([#4215](https://github.com/diegosouzapw/OmniRoute/pull/4215))
- **docs(readme): expand Acknowledgments into a themed, star-counted credits hall** — reworks the README acknowledgments section. ([#4195](https://github.com/diegosouzapw/OmniRoute/pull/4195))
- **style(dashboard): shrink the identity grid cell 46px → 32px (~30% smaller)** — tightens the identity grid density. ([#4143](https://github.com/diegosouzapw/OmniRoute/pull/4143))

### 🔧 Dependencies

- **deps: bump the production group with 5 updates** — routine production-dependency bumps. ([#4121](https://github.com/diegosouzapw/OmniRoute/pull/4121))
- **chore(deps): bump github/codeql-action from 3 to 4** — CI action update. ([#4120](https://github.com/diegosouzapw/OmniRoute/pull/4120))
- **chore(deps): bump actions/setup-python from 5 to 6** — CI action update. ([#4119](https://github.com/diegosouzapw/OmniRoute/pull/4119))




## What's Changed
* Release v3.8.29 by @diegosouzapw in https://github.com/diegosouzapw/OmniRoute/pull/4126


**Full Changelog**: https://github.com/diegosouzapw/OmniRoute/compare/v3.8.28...v3.8.29