chore(release): merge release/v3.8.50 tip into release/v3.8.51 — sync-back step 1/2

The v3.8.50 close left 134 post-freeze commits on release/v3.8.50 that never
reached the cycle branch (the freeze cut release/v3.8.51 at 3192eb88d5). A
plain merge of main reproduces all of them through the `Release v3.8.50`
squash against a July merge-base and conflicted on 551 files; merging the
release tip first, against the recent common ancestor, narrows the real
conflicts to 102 (51 generated, 51 judged file by file with a proof each —
see _tasks/postmortems/2026-08-25-release-v3.8.50-pipeline-eficiencia.md,
Parte IV). Step 2 brings main's own post-tag fixes and the finalized
CHANGELOG through scripts/release/sync-next-cycle.mjs.

Resolution rules applied, in order of evidence:
- generated files regenerated with the repo's own generators
  (sync-llm-mirrors, gen-budget-card-svg, gen-provider-reference);
- where release/v3.8.51 already carried the same fix in a newer shape
  (#11524 search sweep, #11551 catalog scheduler, Google BYOP retry, KIE
  Market id map, Docker worker budget measured in #7518) its version stays;
- where release/v3.8.50 carried the newer shape (Volcengine cookie-domain
  CodeQL fix + shared Zod schemas, #11355/#10534 cooldown release helper,
  positive-anchor tests for security-hardening and cli-oneproxy) it wins;
- GPL-retired Raycast/Hailuo (#11691) stay retired: nothing of theirs comes
  back and the public-route test keeps the retired route out;
- the ten changelog.d fragments of v3.8.50 are dropped — they are already
  aggregated in main's CHANGELOG and would double-aggregate at v3.8.51.

Three things git's auto-merge silently produced were caught by a per-line
detector and fixed: providerLimits.ts lost T's imports and the
windowStillExhaustedAfterRealReset helper; catalogCache.ts and
providerLimits.ts kept both sides' identical copies of three declarations;
contextHandoff.ts's new provider-allowlist skip returned undefined against
the #11552 outcome type. Every decision was re-run through the tests both
sides own for it.

.github/workflows/ci.yml

@@ -688,7 +688,50 @@ jobs:
       - run: npm run build:cli
       - name: Assert dist/server.js exists
         run: test -f dist/server.js || (echo "dist/server.js missing — build:cli did not assemble correctly" && exit 1)
+      # `build:cli` monta dist/ mas NAO grava dist/BUILD_SHA — so `build:release` faz
+      # isso, chamando write-build-sha.mjs. O guard de proveniencia do #10427, dentro
+      # de check:pack-artifact, rejeita um artefato sem SHA (e rejeita mesmo com
+      # OMNIROUTE_ALLOW_CANARY_BUILD=1: o que nao da para identificar nao da para
+      # vouchear). Sem este passo o par build+validate deste job e estruturalmente
+      # incompativel e falha 100% das vezes.
+      - name: Stamp dist/BUILD_SHA for the provenance guard (#10427)
+        # O SHA TEM de vir do head da PR, nao de `git rev-parse HEAD`. Este workflow
+        # roda em `pull_request`, entao o checkout e o MERGE COMMIT efemero que o
+        # GitHub cria — um commit que nao existe em branch nenhuma e portanto nunca e
+        # ancestral da release. O guard de proveniencia (#10427) rejeita exatamente
+        # isso, e com razao: um artefato carimbado com o merge commit nao pode ser
+        # rastreado ate codigo que passou pelos gates.
+        env:
+          OMNIROUTE_BUILD_SHA: ${{ github.event.pull_request.head.sha || github.sha }}
+        run: |
+          export OMNIROUTE_BUILD_SHA="${OMNIROUTE_BUILD_SHA:0:7}"
+          node scripts/build/write-build-sha.mjs
+      # O guard de proveniencia checa ancestralidade contra `origin/main` por padrao.
+      # Esse e o ref certo na PUBLICACAO (npm-publish.yml roda em main), mas em
+      # `pull_request` e estruturalmente impossivel: enquanto a PR esta aberta o head
+      # dela NUNCA e ancestral de main — e o checkout raso nem traz `origin/main` para
+      # o grafo local, entao a sonda responde `false` de qualquer jeito. Resultado: o
+      # gate falhava 100% das vezes em PR. Pre-merge o unico invariante checavel e "o
+      # stamp corresponde a branch sob teste", entao apontamos o ref para o head da PR.
+      # Usamos `refs/pull/<N>/head` e nao `head.ref` porque aquele existe no PROPRIO
+      # origin mesmo quando a PR vem de um fork; `head.ref` so existe no repo do autor.
+      - name: Resolve the provenance ref for the pack gate (#10427)
+        id: provenance-ref
+        env:
+          PR_NUMBER: ${{ github.event.pull_request.number }}
+        run: |
+          if [ -n "$PR_NUMBER" ]; then
+            git fetch --no-tags --depth=50 origin \
+              "+refs/pull/$PR_NUMBER/head:refs/remotes/origin/pr-head"
+            echo "ref=origin/pr-head" >> "$GITHUB_OUTPUT"
+          else
+            git fetch --no-tags --depth=50 origin \
+              "+refs/heads/$GITHUB_REF_NAME:refs/remotes/origin/$GITHUB_REF_NAME"
+            echo "ref=origin/$GITHUB_REF_NAME" >> "$GITHUB_OUTPUT"
+          fi
       - run: npm run check:pack-artifact
+        env:
+          OMNIROUTE_RELEASE_REF: ${{ steps.provenance-ref.outputs.ref }}
       # WS1.2 (#7065 class): pack the real tarball, install it into a clean prefix and
       # BOOT it to a healthy /api/monitoring/health — the gate that structure checks
       # cannot provide (3 releases shipped boot-crashing tarballs with green lists).
@@ -795,9 +838,23 @@ jobs:
       # D3 (plano mestre): a coverage é coletada NESTE mesmo run (c8/NODE_V8_COVERAGE propaga
       # aos filhos através do npm) — elimina a matrix Coverage Shard ×8, que re-executava a
       # suíte inteira só para medir o gate. Padrão usado pelo CI do próprio nodejs/node.
+      # Heap: os shards rodam sob instrumentacao de cobertura do V8, que retem muito
+      # mais memoria que a suite crua. Com o teto antigo de 4096 MB os shards passaram
+      # a abortar com SIGABRT (exit 134, "Ineffective mark-compacts near heap limit")
+      # ao redor de 4086 MB conforme o catalogo de providers cresceu no ciclo v3.8.50 —
+      # todos os testes passavam e o processo morria no fim, o que le como falha de
+      # teste sem ser. O teto vive em `test:unit:ci:shard` (package.json) e agora
+      # acompanha os 8192 MB ja usados pelas variantes nao-shardadas; os runners
+      # GitHub-hosted tem 16 GB.
       - name: Unit tests (shard ${{ matrix.shard }}/8) with V8 coverage
         env:
           TEST_SHARD: ${{ matrix.shard }}/8
+          # NODE_OPTIONS (nao so o flag em test:unit:ci:shard) porque quem estoura o
+          # heap e o processo `c8` que embrulha a suite — ele agrega ~577 MB de JSON
+          # de cobertura bruta. Subir o teto so no node filho deixa o pai no default
+          # do V8 (~4 GB) e o OOM continua igual, em ~4083 MB. Mesmo padrao ja usado
+          # pelo job de merge de cobertura mais abaixo.
+          NODE_OPTIONS: --max-old-space-size=8192
         run: |
           rm -rf coverage-shard coverage-shard-report
           npx c8 \

AGENTS.md

@@ -718,3 +718,13 @@ The dashboard is reachable at the operator's chosen URL/port (default `http://lo
 - **Local VPS / shared dev environments**: ask the operator for the URL and current credentials — they live in their personal vault, NOT in this repo.
 
 > Any credential observed in a previous version of this file was a non-production demo value; treat it as compromised and do not reuse it.
+
+<!-- BEGIN:nextjs-agent-rules -->
+
+# This is NOT the Next.js you know
+
+This version has breaking changes — APIs, conventions, and file structure may all differ from your training data. Read the relevant guide in `node_modules/next/dist/docs/` (resolved from this file's directory; in monorepos the `next` package may not be visible from the repo root) before writing any code. Heed deprecation notices.
+
+This block is written and re-added by `next dev` — verify at `node_modules/next/dist/server/lib/generate-agent-files.js`. Removing it from a diff only re-creates the uncommitted change; committing it with your work keeps the tree clean.
+
+<!-- END:nextjs-agent-rules -->

changelog.d/features/10039-combo-lane-awareness-wave-2.md

@@ -1,2 +0,0 @@
-- **feat(admission):** add lane-aware admission probes for combo/fusion/chaos fan-out (fail-open, queueing disabled), an env-wins `OMNIROUTE_CHAT_VIRTUAL_LANES` activation flag applied at boot, and adaptive-lane visibility in the `omniroute_get_health` MCP tool (related to #9654)
-- **docs(mcp):** complete the MCP server README tool reference so the `schemas/` catalog is fully covered (agent-skills, oneproxy, web, tool-search, combo/routing, pricing and DB-health tools were previously only discoverable via `omniroute_tool_search`)

changelog.d/features/10057-docker-aware-auto-config.md

@@ -1 +0,0 @@
-- **feat(cli):** container-aware auto-config — `setup-*`, `omniroute configure`, `omniroute config set` and the CLI-tool config APIs now refuse to write into a containerised OmniRoute's ephemeral home (CLI exits `2`, API returns `422` with `containerEphemeralTarget`) and point at the host-CLI or bind-mount setup instead; `--allow-container-write` / `OMNIROUTE_ALLOW_CONTAINER_CONFIG_WRITE=true` opt back in. Also fixes `CLI_CONFIG_HOME` so the Compose `host` profile's `/host-home` bind mounts are honoured instead of silently falling back to the container home. (#10057)

changelog.d/features/10273-dashboard-embed-csp.md

@@ -1 +0,0 @@
-- feat(dashboard): opt-in `DASHBOARD_ALLOW_EMBED=vscode` relaxes CSP `frame-ancestors` to `'self' vscode-webview:` and drops `X-Frame-Options` for HTML pages only, so the dashboard renders inside the VS Code Simple Browser (OmniCopilot). Default posture unchanged — API routes stay unframable (#10273)

changelog.d/features/10303-healthz-event-loop-lag.md

@@ -1 +0,0 @@
-- **feat(resilience):** warn when `/healthz` is served under event-loop lag ≥200ms so a slow 200 is visible as sick, not healthy ([#10303](https://github.com/diegosouzapw/OmniRoute/issues/10303))

changelog.d/features/10316-livez-endpoint.md

@@ -1 +0,0 @@
-- **feat(docker):** add `GET`/`HEAD` `/livez` as a process-alive probe, distinct from `/healthz` readiness ([#10316](https://github.com/diegosouzapw/OmniRoute/issues/10316))

changelog.d/features/10389-cloudflare-playground.md

@@ -1 +0,0 @@
-- feat(providers): add **Cloudflare AI Playground** as a No Auth provider (`cloudflare-playground`, alias `cfp`) — free anonymous chat over the reverse-engineered `cf_agent` WebSocket protocol (PartySocket transport, no account/API key/cookies) with GLM 5.2, Kimi K2.7 Code, DeepSeek V4 Pro, gpt-oss-120B, Llama 3.3 70B, Qwen2.5 Coder 32B and 14 more curated models. The executor drives a headless Chromium via Playwright (the WS upgrade is TLS-fingerprint-gated), translates the `cf_agent` frame stream into OpenAI SSE, and surfaces upstream rate limits (3021) as HTTP 429. Fixes #10389

changelog.d/features/10542-aihorde-optional-key-image-catalog.md

@@ -1,2 +0,0 @@
-- **feat(providers):** AI Horde accepts an optional registered API key and advertises only live image models that currently have workers ([#10542](https://github.com/diegosouzapw/OmniRoute/pull/10542))
-- **fix(providers):** AI Horde Check validates keys via `/v2/find_user` instead of the unauthenticated OpenAI models list ([#10542](https://github.com/diegosouzapw/OmniRoute/pull/10542))

changelog.d/features/10581-jina-complete-provider.md

@@ -1 +0,0 @@
-- **feat(providers):** complete Jina AI as one credential pool — dashboard `jina-ai` / `jina-reader` share a token, `JINA_AI_API_KEY` is a real fallback, Test probes `GET https://api.jina.ai/v1/models` (embeddings fallback hits `jina-embeddings-v5-omni-small`), embed/rerank logs keep `connection_id`, catalog adds `jina-reranker-v3.5`, Omni v5 multimodal `{text}`/`{image}`/`{content}` docs pass through intact, and OmniRoute proxies classify / segment / `jina-search` (`s.jina.ai`). Reader stays a separate `r.jina.ai` card with an explicit label. Gemini Embedding 2 (`gemini/gemini-embedding-2`, alias `google/gemini-embedding-2`) uses dashboard `gemini` keys (or `GEMINI_API_KEY` / `GOOGLE_API_KEY` only when none exist), forwards native multimodal parts, and maps N OpenAI `input` items to N `:batchEmbedContents` vectors instead of one aggregated `:embedContent`. ([#10581](https://github.com/diegosouzapw/OmniRoute/pull/10581))

changelog.d/features/10587-ogg-speech-alias.md

@@ -1 +0,0 @@
-- **feat(providers):** accept `response_format=ogg` on `/v1/audio/speech` as an alias for the existing Opus/Ogg encoder ([#10587](https://github.com/diegosouzapw/OmniRoute/issues/10587))

changelog.d/features/10617-auto-disable-banned-scope.md

@@ -1 +0,0 @@
-- **feat(settings):** add `autoDisableBannedScope` so permanent-ban auto-disable can target subscription/OAuth accounts only, leaving prepaid API keys in the routing pool ([#10617](https://github.com/diegosouzapw/OmniRoute/pull/10617))

changelog.d/features/10662-systemd-notify.md

@@ -1 +0,0 @@
-- feat(server): emit systemd sd_notify READY/WATCHDOG/STOPPING (generated unit becomes Type=notify with WatchdogSec=180) so a frozen server process is killed and restarted by systemd instead of lingering undetected

changelog.d/features/10668-newapi-gateway-protocols.md

@@ -1,2 +0,0 @@
-- **feat(providers):** add the TabiToken NewAPI gateway (`tabitoken`) and teach the existing HCNSec entry (`hcnsec`) the three further protocols it actually serves. TabiToken leaves the NewAPI pricing endpoint public, so its catalog is read from the host rather than guessed: four Claude models, each reporting the Anthropic and OpenAI protocols. HCNSec shipped OpenAI-only; probing the host showed `/v1/messages`, `/v1/responses` and the Gemini `/v1beta` path all reach its token layer, so each is now declared as an alternate format — with its default format, base URL, auth scheme and regional catalog classification untouched. ([#10668](https://github.com/diegosouzapw/OmniRoute/pull/10668)) — thanks @yawar-aquil
-- **feat(sse):** allow an alternate protocol to build its own upstream URL. `AlternateFormat` gained an optional `urlBuilder`, because the Gemini protocol carries the model inside the path (`{base}/{model}:generateContent`) and the existing `chatPath`/`urlSuffix` fields are constants that cannot express it. The route builder is extracted as `buildGeminiGenerateContentUrl` and shared with the native `gemini` provider so the two consumers cannot drift on the `?alt=sse` streaming suffix. ([#10668](https://github.com/diegosouzapw/OmniRoute/pull/10668)) — thanks @yawar-aquil

changelog.d/features/10670-call-logs-error-type.md

@@ -1 +0,0 @@
-- **feat(call_logs):** persist the per-call error family in `call_logs.error_type` and expose a failure breakdown (`errorBreakdown`) in the usage analytics endpoint, reusing the existing production classifier ([#10670](https://github.com/diegosouzapw/OmniRoute/issues/10670))

changelog.d/features/10677-egress-sharing-summary.md

@@ -1 +0,0 @@
-- **feat(proxy):** the proxy-health sweep and `GET /api/settings/proxies/egress` now report an anonymous summary of egress-IP sharing — how many rotation groups share an egress IP and the largest number of accounts behind one IP — computed from persisted `proxy_logs` over a 24h window. No IPs and no account identities by default; `PROXY_LOG_INCLUDE_IPS=true` restores raw details. ([#10677](https://github.com/diegosouzapw/OmniRoute/issues/10677))

changelog.d/features/10697-vscode-copilot-guide.md

@@ -1 +0,0 @@
-- **docs(guides):** OmniRoute now serves VS Code's **native Copilot Chat model picker** through the [OmniCopilot](https://github.com/diegosouzapw/OmniCopilot) extension ([Marketplace](https://marketplace.visualstudio.com/items?itemName=diegosouzapw.omnicopilot) · [Open VSX](https://open-vsx.org/extension/diegosouzapw/omnicopilot) — Cursor, Windsurf, VSCodium, Theia…) — no Copilot subscription needed since VS Code 1.122. New [`docs/guides/VSCODE-COPILOT.md`](docs/guides/VSCODE-COPILOT.md) covers setup, how the picker collapses the `dual`-prefix catalog via `GET /v1/models?prefix=alias`, and the **build-time** `DASHBOARD_ALLOW_EMBED=vscode` flag that renders the dashboard in an editor tab ([#10697](https://github.com/diegosouzapw/OmniRoute/pull/10697))

changelog.d/features/10701-dockerfile-dashboard-embed-arg.md

@@ -1 +0,0 @@
-- **feat(docker):** `DASHBOARD_ALLOW_EMBED` is now a Docker build argument — `docker build --build-arg DASHBOARD_ALLOW_EMBED=vscode` produces an image whose dashboard renders inside the VS Code Simple Browser (OmniCopilot's `dashboardOpen: "editor"`). Previously the flag was only reachable from a source build: Docker silently drops a `--build-arg` with no matching `ARG`, so the operator got the default image and no error. Builder-stage only and empty by default — the runtime stages deliberately do not carry it, and the unframable default posture is unchanged ([#10701](https://github.com/diegosouzapw/OmniRoute/pull/10701))

changelog.d/features/10729-cursor-api-key-and-cli-passthrough.md

@@ -1 +0,0 @@
-- **feat(providers):** new `cursor-api` provider (card "Cursor API", alias `cua`): connect a Cursor user API key (`crsr_…`) and route `cursor-api/<model>` through the existing Cursor agent executor (the key is exchanged for a 1h session token and cached), plus a `/api/cursor-cli/*` passthrough so the Cursor CLI itself runs through OmniRoute (`CURSOR_API_ENDPOINT=http://<omniroute>/api/cursor-cli`, `CURSOR_API_KEY=<OmniRoute key>`) with every RPC attributed and logged. The IDE `cursor` provider is unchanged. (#10729)

changelog.d/features/10771-health-root-endpoint.md

@@ -1 +0,0 @@
-- **feat(api):** `GET /api/health` now answers `{ status, timestamp }` without a key. Until now the path had no route, so the management-auth boundary answered first with a 401 — indistinguishable from a wrong key or an unknown route, which left Docker HEALTHCHECKs and Kubernetes probes unable to tell "down" from "misconfigured". Kept deliberately minimal: version, uptime and memory stay behind the authenticated `/api/monitoring/health` ([#PRNUM](https://github.com/diegosouzapw/OmniRoute/pull/10771)).

changelog.d/features/10783-task-routing-configurable-patterns.md

@@ -1 +0,0 @@
-- feat(routing): make Task-Aware Smart Routing's detection patterns operator-configurable via `settings.taskRouting.patternOverrides` (`PUT /api/settings/task-routing`) — the built-in patterns are English-only, so a non-English dashboard had no recourse short of turning detection off entirely; an override now replaces the pattern list for one task type without touching the rest (#10783)

changelog.d/features/10869-combo-patch-verb.md

@@ -1 +0,0 @@
-- feat(api): accept PATCH on /api/combos/[id], the verb the OpenAPI spec already documents (#10869)

changelog.d/features/10896-glm-5.3.md

@@ -1 +0,0 @@
-- **feat(sse):** add GLM-5.3 support (`glm-5.3`, `glm-5.3-high`, `glm-5.3-low`) across the z.ai first-party providers, mapping the upstream `reasoning_effort` request parameter to the existing 5.2 tier UX ([#10896](https://github.com/diegosouzapw/OmniRoute/pull/10896)) — thanks @phuongddx

changelog.d/features/10897-home-recent-requests.md

@@ -1 +0,0 @@
-- **feat(home):** add a live **Recent Requests** panel beside the home Provider Topology (polls `GET /api/usage/call-logs?excludeTests=1` every ~3s, gated by the topology appearance toggle + page visibility). `excludeTests` is now an allowlist of real provider inference (`/v1/%` or `/api/v1/%`), applied before `LIMIT`, so connection-test/model-sync/management rows can never leak into the feed ([#10897](https://github.com/diegosouzapw/OmniRoute/pull/10897), extracted from [#8450](https://github.com/diegosouzapw/OmniRoute/pull/8450)) — thanks @nguyenha935

changelog.d/features/10909-free-provider-rankings-reliability.md

@@ -1 +0,0 @@
-- **feat(rankings):** free provider rankings now expose a `reliability` field (raw `testStatus`/`rateLimitedUntil` per connection plus a `healthy`/`degraded`/`down` state, reusing the `ProviderHealthState` vocabulary of the provider health matrix) when the configured/available filters are active — derived from already-loaded data, without touching the ranking order ([#10909](https://github.com/diegosouzapw/OmniRoute/pull/10909))

changelog.d/features/10920-egress-ip-lock.md

@@ -1,8 +0,0 @@
-- `feat(resilience)`: when an allowlisted provider (opencode family) answers
-  429 classified `quota_exhausted` or `rate_limit_exceeded` and its free-tier
-  quota is bucketed by egress IP (#9611), every connection of that family
-  sharing the IP is cooled down together before the rotation tries them — one
-  guaranteed-failed upstream call per episode instead of N, on the combo path
-  as well. For the allowlisted family a 429 now cools the connection instead
-  of locking a single model. Exclusive allowlist, never terminal, best-effort
-  when the egress IP is unknown (#10920).

changelog.d/features/10926-rankings-usage-reliability.md

@@ -1 +0,0 @@
-- **feat(rankings):** free provider rankings can now report what each provider actually served — `reliability.usage` (requests, successes, success rate over a window) behind the opt-in `withUsage`/`usageRange` query parameters, so a provider that answers every call with an error is no longer described as healthy ([#10926](https://github.com/diegosouzapw/OmniRoute/pull/10926))

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

@@ -1 +0,0 @@
-- **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/11104-operator-error-rules.md

@@ -1 +0,0 @@
-- **feat(providers):** let operators declare per-provider error rules through `settings.providerErrorRules` instead of patching the catalog — an operator-supplied rule for a provider is consulted before the built-in `providerRuleRegistry`, receives the raw error text, and has its declared scope/cooldown/reason actually honored end to end, for any provider (declaring the rule is the opt-in — no extra allowlist entry needed). Matches are plain case-insensitive substrings (never RegExp) and bounded to 50 rules to keep the hot path safe ([#11104](https://github.com/diegosouzapw/OmniRoute/pull/11104))

changelog.d/features/11134-configurable-max-global-attempts.md

@@ -1 +0,0 @@
-- **feat(combo):** the shared per-request combo attempt budget is now operator-configurable via `maxGlobalAttempts` (combo config / `comboDefaults` cascade), instead of the hardcoded 30. Lower it to fail fast on a dead target pool, raise it for large combos; clamped to `[1, 200]` so an unbounded budget can never cause runaway background requests ([#11134](https://github.com/diegosouzapw/OmniRoute/issues/11134))

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

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

@@ -1 +0,0 @@
-- **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/features/11251-connection-max-wait-ms-override.md

@@ -1 +0,0 @@
-- **feat(providers):** allow overriding the rate-limit queue wait timeout (`maxWaitMs`) per connection, alongside the existing `rpm`/`tpm`/`tpd`/`minTime`/`maxConcurrent` overrides — a single slow provider no longer has to lower the global wait budget for every other provider (#11251)

changelog.d/features/11282-first-run-readiness-card.md

@@ -1 +0,0 @@
-- **feat(dashboard):** replace the hard Home → onboarding redirect with a dismissable first-run readiness card so returning users can stay on Home while new users still get a clear 4-step path ([#11282](https://github.com/diegosouzapw/OmniRoute/pull/11282))

changelog.d/features/11283-traffic-inspector-purpose-header.md

@@ -1 +0,0 @@
-- **feat(dashboard):** lead Traffic Inspector with a purpose-first header that separates "what happened" from "how it happened", so beginners can read request outcomes without drowning in protocol detail ([#11283](https://github.com/diegosouzapw/OmniRoute/pull/11283))

changelog.d/features/11286-essentials-sidebar-preset.md

@@ -1 +0,0 @@
-- **feat(dashboard):** add an Essentials sidebar preset that shows only the beginner core path (Home → Endpoints → API Keys → Providers → Health → Settings) while keeping Advanced tools reachable via Command Palette search ([#11286](https://github.com/diegosouzapw/OmniRoute/pull/11286))

changelog.d/features/8443-credential-health-per-connection-interval.md

@@ -1,2 +0,0 @@
-- **feat(credential-health):** pace the credential health sweep per connection via `provider_connections.healthCheckInterval` (minutes, 0 = never), with `CREDENTIAL_HEALTH_CHECK_INTERVAL` as the global default ([#8443](https://github.com/diegosouzapw/OmniRoute/issues/8443))
-- **behavior change:** `healthCheckInterval` is a shared column — it paces both the OAuth token refresh and the credential health sweep, and `0` disables both. The connection editor defaults it to 60, so configured OAuth connections are now credential-checked at 60min instead of the previous ~10min (aligned with the probe-volume goal of #8443)

changelog.d/features/9085-poolside-laguna-model-ids.md

@@ -1 +0,0 @@
-- **feat(providers):** publish Poolside's Laguna Preview catalog statically — `poolside/laguna-xs-2.1` and `poolside/laguna-s-2.1` (262144 context, 32768 max completion, tools + reasoning, text-only), so the models are routable and visible before a key is configured instead of only after live discovery. Pins the catalog form of the XS id against the `laguna-xs.2` variant carried by third-party listings. ([#9085](https://github.com/diegosouzapw/OmniRoute/issues/9085))

changelog.d/features/9760-video-bridge.md

@@ -1 +0,0 @@
-- feat(modality-bridge): bridge Chat and Responses video parts through a strict trusted-loopback, quota-bounded FFmpeg broker; enforce HTTPS redirects/SSRF plus format, protocol, stream, pixel, frame, 50 MiB broker/remote, 36 MiB inline, and 120-second limits; propagate caller aborts; preserve the actual successful fallback model through cache/meta/headers; expose sampled latency and honest success telemetry; and ship the localized Video settings UI (#9760)

changelog.d/features/9830-radar-local-model-state.md

@@ -1 +0,0 @@
-- **feat(radar):** Persist local model display-name/enabled overrides and hide/restore tombstones, with authenticated catalog controls and feed safety precedence ([#9830](https://github.com/diegosouzapw/OmniRoute/pull/9830))

changelog.d/features/9836-radar-guided-combos.md

@@ -1 +0,0 @@
-- **feat(radar):** add curated-family combo suggestions, a guided combo page, and the read-only Radar MCP catalog tool ([#9836](https://github.com/diegosouzapw/OmniRoute/pull/9836))

changelog.d/features/9912-radar-supporter-offers.md

@@ -1 +0,0 @@
-- **feat(radar):** add a signed live offers feed and supporter offers dashboard ([#9912](https://github.com/diegosouzapw/OmniRoute/pull/9912))

changelog.d/features/9923-radar-intel.md

@@ -1 +0,0 @@
-- **feat(radar):** add signed Intel insights, supporter recognition, and local Radar CLI commands ([#9923](https://github.com/diegosouzapw/OmniRoute/pull/9923))

changelog.d/features/9926-radar-launch-news.md

@@ -1 +0,0 @@
-- **feat(radar):** add a localized public news feed and dismissible dashboard launch banner, with the Radar announcement staged inactive for a separately authorized launch ([#9926](https://github.com/diegosouzapw/OmniRoute/pull/9926))

changelog.d/features/command-code-reasoning-efforts.md

@@ -1 +0,0 @@
-- feat(command-code): advertise low/medium/high/xhigh/max reasoning-effort suffixes for reasoning-capable models in the catalog and Combo Builder, with request-time resolution to reasoning_effort

changelog.d/features/crofai-reasoning-efforts.md

@@ -1 +0,0 @@
-- feat(crof): advertise reasoning-effort tiers (none/low/medium/high/max) for live-discovered and seed models, so the catalog, Playground, and Combo Builder surface <model>-<tier> aliases and requests resolve max upstream

changelog.d/features/cursor-agent-image-provider.md

@@ -1 +0,0 @@
-- feat(sse): add Cursor plan image generation via Agent CLI (`IMAGE_PROVIDERS.cursor`, format `cursor-agent-image`), reusing the chat Cursor OAuth connection

changelog.d/features/disable-context-window-checks.md

@@ -1 +0,0 @@
-- feat(routing): add the default-off `DISABLE_CONTEXT_WINDOW_CHECKS` feature flag to let operators bypass OmniRoute's local context-window and max-input-token check for direct single-model requests, leaving upstream limits, prompt compression, and output-token caps intact.

changelog.d/features/effort-tiers-loop-learned-sets.md

@@ -1 +0,0 @@
-- **feat(catalog):** surface runtime-learned `reasoning_effort` tiers in `/v1/models` `capabilities.effort_tiers` (learned set replaces synced metadata when present), map them to OpenCode `ModelV2.variants` in the OmniRoute plugin, and align dispatch `-<tier>` suffix validation to the effective (learned ?? synced) set — so the UI offers exactly the tiers the upstream accepts (e.g. `{low, high, max}` for `oc/x-preview-f-free`) and each advertised variant completes. Excludes codex/glm/kimi, which keep their own dedicated `-{effort}` suffix mechanism and never gain `effort_tiers` from this path (related to #7694, builds on #11232)

changelog.d/features/kimi-coding-extra-usage.md

@@ -1 +0,0 @@
-- **feat(usage):** show Kimi Coding's fixed-order Code 5-hour/7-day quota windows plus Extra Usage status, balance, monthly spend/limit, and the official Additional Credits link on Dashboard → Quota cards.

changelog.d/features/m365-copilot-tool-calls.md

@@ -1 +0,0 @@
-- **feat(providers):** copilot-m365-web now supports OpenAI tool calling — a router planning turn asks the substrate model (as a tool-selection assistant emitting `CALL_TOOL: name({...})` / `NO_TOOL_NEEDED` text, which bypasses its plugin-registry refusal) and validated decisions surface as `tool_calls` with `finish_reason: "tool_calls"` in both stream and non-stream modes; also flattens the full message history (assistant `tool_calls` + compacted tool results) so multi-turn agent loops keep context, replies to SignalR `type:6` keepalives, surfaces `type:3` error frames instead of a silent empty `stop`, and suppresses `writeAtCursor` text from tool-progress frames

changelog.d/features/multimodal-embeddings-alias.md

@@ -1 +0,0 @@
-- **feat(api):** add `GET`/`POST` `/v1/multimodal-embeddings` as an alias of `/v1/embeddings` so Jina-compatible clients do not receive HTTP 404 `unknown_route` — thanks @RaviTharuma

changelog.d/features/opencode-go-muse-spark-efforts.md

@@ -1 +0,0 @@
-- feat(opencode-go): expose Muse Spark 1.2 Contributor reasoning-effort aliases (minimal/low/medium/high/xhigh) in the Combo Builder

changelog.d/features/per-connection-upstream-timeout.md

@@ -1 +0,0 @@
-- **feat(providers):** restore the operator-owned upstream timeout tier per connection via `providerSpecificData.timeoutMs` (preempts the maintainer-only model/provider registry tiers and the global `FETCH_TIMEOUT_MS`), and make the combo per-target timeout ceiling follow the selected connection

changelog.d/features/unreleased-detached-cli-tray.md

@@ -1 +0,0 @@
-- **feat(cli):** run `omniroute serve --tray` as a detached desktop process after server and tray readiness, with graphical login auto-start support.

changelog.d/features/unreleased-exclusive-managed-session-leases.md

@@ -1 +0,0 @@
-- **feat(routing):** add client-, provider-, and model-neutral exclusive managed session connection leases with API-key-bound generation fencing, durable SQLite ownership, explicit allowlist policy, and bounded 429 capacity retry semantics.

changelog.d/fixes/10017-sse-control-lines-leak-openai-clients.md

@@ -1 +0,0 @@
-- **Passthrough streaming:** stop leaking upstream SSE control lines (`id:`/`event:`/`retry:`/`:` comments) to plain OpenAI Chat-Completions-format clients, while preserving `event:` framing for OpenAI Responses API and Claude Messages API passthrough ([#10017](https://github.com/diegosouzapw/OmniRoute/issues/10017)).

changelog.d/fixes/10028-windows-instrumentation-hook.md

@@ -1 +0,0 @@
-- fix(cli): stop diagnosing every Next.js instrumentation-hook failure as the Android/Termux cache bug — only the Android "Unsupported platform: android" signal now triggers the Android hint, so a win32/desktop instrumentation error surfaces its real cause instead of a useless `mkdir -p ~/.cache` (#10028)

changelog.d/fixes/10060-build-sqlite-native-addon-guard.md

@@ -1 +0,0 @@
-- **fix(build):** stop the native `better-sqlite3` addon from loading during the Next.js production build (#10060). Its `Statement` destructor aborts with `SIGABRT` when a build worker thread exits (assertion in `node::RemoveEnvironmentCleanupHook`, `env == nullptr`), which can leave the build with no standalone bundle. Every DB entry point now keys off a reliable `OMNIROUTE_BUILDING=1` signal (set by `build-next-isolated.mjs` and inherited by every spawned build worker, because Next.js workers sometimes drop `NEXT_PHASE`): `getDbInstance()` returns a no-op SQLite stub during build, `driverFactory` skips the native driver and falls through to `node:sqlite`, and the `codegraph`/`kiro-import` lazy loaders fail closed. A build-time `better-sqlite3` alias to a stub (`next.config.mjs`, turbopack) backs this up without changing runtime behaviour (the real package is still `require()`d natively via `serverExternalPackages`). Also raises the default build heap 4096→6144 MB and caps Next build worker pools (`CIRCLE_NODE_TOTAL=8`) to avoid the many-core page-data-collection SIGSEGV, and adds `.gitattributes` (`*.sh text eol=lf`) so kernel-exec'd shell scripts never ship with CRLF shebangs. Deliberately does NOT downgrade the Node base image: per the maintainer's review on #10060, `release/v3.8.50` moved to `node:26-trixie-slim` through several considered commits, so the `OMNIROUTE_BUILDING` guard is re-derived against the current base rather than reverting the FROM line; the npm pin and binary-hide dance from the original PR are dropped because our build already rebuilds `better-sqlite3` deterministically via `node-gyp` and floats `npm@latest` for the CVE overlay.

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

@@ -1 +0,0 @@
-- **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/10077-chatgpt-web-max-thinking-effort.md

@@ -1 +0,0 @@
-- **fix(chatgpt-web):** Preserve native `max` thinking effort through ChatGPT Web routing ([#10077](https://github.com/diegosouzapw/OmniRoute/pull/10077)) — thanks @zannen7

changelog.d/fixes/10078-agentrouter-quota-missing-dashboard.md

@@ -1,2 +0,0 @@
-- Fix: wire AgentRouter's existing console balance fetcher into the Dashboard Quota UI (visibility gate + provider-limits data path + background sync) so its wallet balance renders instead of falling back to "Usage API not implemented" (#10078)
-- Fix: AgentRouter's dollar balance now renders as a currency-formatted "$X.XX" credits row in the Dashboard Quota UI instead of a bare percentage, and an exhausted wallet always shows exactly $0.00 (#10078)

changelog.d/fixes/10085-compatible-chat-credential-mismatch.md

@@ -1 +0,0 @@
-- fix(sse): bridge generic openai-compatible/anthropic-compatible provider type ids to their concrete uuid node id in credential lookup (#10085)

changelog.d/fixes/10095-antigravity-multiaccount-quota-false-exhaustion.md

@@ -1 +0,0 @@
-- fix(domain): stop treating an unreported Antigravity quota fraction (`fractionReported:false`) as 0% remaining in `quotaCache.ts`, which was falsely marking every fresh/newly-connected account as exhausted and blocking multi-account rotation (#10095)

changelog.d/fixes/10096-kimi-coding-apikey-save.md

@@ -1 +0,0 @@
-- fix(dashboard): remap unified Kimi Code card API-key save to the admitted `kimi-coding-apikey` connection id, fixing 400 "Invalid provider" on Save (#10096)

changelog.d/fixes/10104-antigravity-trailing-model-turn.md

@@ -1 +0,0 @@
-- fix(antigravity): strip trailing model turn for native Gemini requests too, not just Claude (#10104)

changelog.d/fixes/10111-adaptive-admission-latency-collapse.md

@@ -1 +0,0 @@
-- **fix(admission):** stop the adaptive latency-gradient collapse from permanently locking out ordinary requests — individually valid requests now make solo progress when the system is idle and normal pressure, and the collapsed limit actively recovers on sustained idle windows instead of being stuck; the critical-pressure fuse still wins over solo progress (#10111)

changelog.d/fixes/10119-claude-haiku-45-capability-flags.md

@@ -1 +0,0 @@
-- fix(sse): downgrade client-supplied `thinking:{type:"adaptive"}` to `enabled` and gate the `context-1m-2025-08-07` beta on model eligibility when a combo/fallback re-routes a request to a non-adaptive/non-1M model like claude-haiku-4-5 (avoids "adaptive thinking is not supported on this model" and "long context beta is not yet available" 400s, #10119)

changelog.d/fixes/10123-async-call-log-artifacts.md

@@ -1 +0,0 @@
-- **fix(logging):** move call-log artifact serialization and filesystem writes to a bounded singleton worker to keep request handling responsive (#10123)

changelog.d/fixes/10125-incremental-call-log-rotation.md

@@ -1 +0,0 @@
-- **perf(logging):** bound each scheduled call-log rotation pass to incremental database and filesystem work (#10125)

changelog.d/fixes/10127-early-sse-heartbeat.md

@@ -1 +0,0 @@
-- **fix(streaming):** start early SSE heartbeats when Responses or Messages requests opt into streaming through the request body (#10127)

changelog.d/fixes/10136-combo-scoped-session-stickiness.md

@@ -1 +0,0 @@
-- **fix(combo):** scope session-stickiness bindings to their owning Combo so identical first messages cannot carry a successful target into another priority chain and bypass its configured order (fixes #10136)

changelog.d/fixes/10139-thinking-output-cap-provider-scope.md

@@ -1 +0,0 @@
-- **fix(translator):** resolve the Claude thinking output cap with the routed provider so a provider-scoped-only `max_output_tokens` override is no longer invisible to `fitThinkingToMaxTokens()`, which previously let the synthesized `max_tokens` (caller room + thinking budget) go out unbounded and 400 upstream ([#10139](https://github.com/diegosouzapw/OmniRoute/issues/10139))

changelog.d/fixes/10140-conol-web-import-depth.md

@@ -1,3 +0,0 @@
-- fix(providers): correct the conol-web registry fallback-models import depth, which pointed at a
-  non-existent `open-sse/config/services/` and made any suite loading the provider registry fail to
-  resolve (#10140)

changelog.d/fixes/10144-claude-import-cli-user-id.md

@@ -1 +0,0 @@
-- **fix(oauth):** Claude connections created via `claude-auth/import` now send required CLI headers on the bootstrap identity call and persist a `cliUserID` device identity, fixing intermittent "Third-party apps now draw from your extra usage" 400s on otherwise valid imported subscription tokens ([#10144](https://github.com/diegosouzapw/OmniRoute/pull/10144), fixes [#10143](https://github.com/diegosouzapw/OmniRoute/issues/10143))

changelog.d/fixes/10156-responses-commentary-completed-snapshot.md

@@ -1 +0,0 @@
-- **fix(sse):** Responses-passthrough `response.completed` snapshots now drop `phase:"commentary"` items the same way live SSE frames already do, so the terminal `response.output` array no longer echoes internal commentary text that was already suppressed from the stream (#10156).

changelog.d/fixes/10158-local-proxy-subscription.md

@@ -1 +0,0 @@
-- fix(proxy-subscriptions): allow local/loopback proxy-subscription fetch URLs (local-first, cloud-metadata still blocked) (#10158)

changelog.d/fixes/10162-approximate-combo-context-advisory.md

@@ -1 +0,0 @@
-- **fix(routing):** keep approximate Combo context estimates advisory so requests reach concrete targets instead of returning a pre-dispatch 400 ([#10162](https://github.com/diegosouzapw/OmniRoute/pull/10162)) — thanks @xz-dev

changelog.d/fixes/10169-thinking-budget-docs-i18n.md

@@ -1 +0,0 @@
-- **docs(settings):** document Thinking Budget modes (passthrough vs auto-strip); fix dashboard i18n key collision that showed Auto Combo routing copy on the thinking tab; clarify independence from compression/cache ([#10169](https://github.com/diegosouzapw/OmniRoute/pull/10169))

changelog.d/fixes/10171-instrumentation-hook-boot-fatal-log.md

@@ -1 +0,0 @@
-- fix(cli): guarantee a non-empty `[STARTUP] Fatal:` log line for any instrumentation-hook boot throw, not just DB-driver init failures (#10171)

changelog.d/fixes/10183-10268-admission-heap-conditional-shed.md

@@ -1 +0,0 @@
-- fix(sse): gate structural chat admission shedding on real heap pressure instead of unconditional capacity, with a bounded headroom budget so a healthy heap can no longer bypass admission control indefinitely (#10183, #10268)

changelog.d/fixes/10202-responses-vision-bridge.md

@@ -1 +0,0 @@
-- **fix(guardrails):** Vision Bridge handles OpenAI Responses `input`/`input_image` requests before combo vision filtering ([#10202](https://github.com/diegosouzapw/OmniRoute/pull/10202)) — thanks @Zartharas

changelog.d/fixes/10215-cursor-kv-after-text-toolcalls.md

@@ -1 +0,0 @@
-- **fix(cursor):** Stop truncating pending tool calls on non-composer models when a KV checkpoint arrives after text but before the `exec_mcp` frame — the KV short-circuit is now gated to the composer family where it was verified ([#10215](https://github.com/diegosouzapw/OmniRoute/issues/10215)).

changelog.d/fixes/10223-deepseek-responses-sse-cjk-deltas.md

@@ -1 +0,0 @@
-- **fix(responses):** repair corrupted SSE deltas for non-ASCII streams by keeping a single stream-aware `TextDecoder` (`{ stream: true }`) across `transform()` calls instead of recreating it per chunk and decoding without the `stream` flag. When a multi-byte UTF-8 character (CJK/emoji) was split across two TCP chunks — common in Chinese streaming text — the per-chunk decoder truncated it to `U+FFFD`, corrupting every delta while the rebuilt `*.done` snapshot stayed internally identical ([#10223](https://github.com/diegosouzapw/OmniRoute/issues/10223))

changelog.d/fixes/10225-combo-context-overflow-before-compression.md

@@ -1 +0,0 @@
-- **fix(combo):** defer the known-context-overflow hard rejection for compressible requests so compression runs before the final context gate, instead of a raw-body estimate 400'ing generic Responses clients targeting a large model before OmniRoute can shrink it ([#10225](https://github.com/diegosouzapw/OmniRoute/issues/10225))

changelog.d/fixes/10228-provider-model-delete-tombstones-synced-sibling.md

@@ -1 +0,0 @@
-- **fix(api):** deleting a manually-added custom model no longer tombstones a provider-synced model that shares its id. `DELETE /api/provider-models` is addressed by `provider` + `model` alone, so when both a custom row and a synced row existed for one id it removed both and wrote `isDeleted:true`. `replaceSyncedAvailableModelsForConnection` then filtered that id out of every subsequent re-import, so the provider could never resync — model sync kept reporting `added: N` while the catalog stayed empty and `/v1/models` never listed the model again, even though routing to it still worked. The custom row is now removed first and its presence is treated as the operator's intent, leaving the synced sibling importable; a synced-only delete still tombstones as before (#3199, #3782 unaffected) ([#10228](https://github.com/diegosouzapw/OmniRoute/pull/10228)) — thanks @Neuron-Mr-White

changelog.d/fixes/10229-audio-bridge-multipart-runtime.md

@@ -1 +0,0 @@
-- **Audio Bridge:** fix production transcription self-loop uploads so real audio reaches the configured STT provider instead of falling back to an unavailable-provider stub ([#10229](https://github.com/diegosouzapw/OmniRoute/pull/10229)).

changelog.d/fixes/10230-deepseek-native-max-effort.md

@@ -1 +0,0 @@
-- **fix(api):** DeepSeek V4's native `max` reasoning tier is now reachable. DeepSeek accepts `reasoning_effort` `low`/`high`/`max` and maps `medium`/`xhigh` down to `high`, while OmniRoute's canonical vocabulary collapses `max` onto `xhigh` — so `{"effort":"max"}` silently resolved to `high` and the catalog never advertised a `max` tier (or its `<model>-max` variant). Following the existing `extendCodexGpt56EffortValues` precedent, the native tier is now preserved for `deepseek`/`ds` V4 models only; the global effort vocabulary is unchanged, routed namespaces (`openrouter/deepseek/…`, `tllm/deepseek_v4`, `oc/deepseek-v4-flash-free`) keep the canonical behavior, and an explicit client `reasoning_effort` still wins ([#10230](https://github.com/diegosouzapw/OmniRoute/pull/10230)) — thanks @Neuron-Mr-White

changelog.d/fixes/10233-freeaiapikey-endpoint-moved.md

@@ -1 +0,0 @@
-- **fix(providers):** FreeAIAPIKey now targets `api.freeaiapikey.com`, the host upstream names in its `410 endpoint_moved` response — every request through the provider was failing — and its catalog is resynced to the 10 models the live `/v1/models` actually serves ([#10233](https://github.com/diegosouzapw/OmniRoute/pull/10233))

changelog.d/fixes/10234-monsterapi-deprecation-inert.md

@@ -1 +0,0 @@
-- **fix(providers):** MonsterAPI's deprecation now actually applies — the flag was written as `isDeprecated`, a key no consumer or schema reads, so the provider kept rendering as healthy in the dashboard, the onboarding wizard and the generated provider reference ([#10234](https://github.com/diegosouzapw/OmniRoute/pull/10234))

changelog.d/fixes/10244-cliproxy-installer-windows-platform-detection.md

@@ -1 +0,0 @@
-- **fix(cliproxy):** read platform/arch at runtime via `os.platform()`/`os.arch()` in `binaryManager` so the embedded installer selects the Windows/ARM assets even when the release bundle is built on a Linux runner (fixes #10244)

changelog.d/fixes/10247-provider-icon-data-url-save.md

@@ -1 +0,0 @@
-- **fix(providers):** compatible/custom providers now save valid Data URL icons and show Add/Edit save failures instead of silently doing nothing ([#10247](https://github.com/diegosouzapw/OmniRoute/pull/10247)) — thanks @xz-dev

changelog.d/fixes/10248-custom-model-overrides.md

@@ -1 +0,0 @@
-- **fix(models):** custom model metadata and compatible-provider context overrides now take precedence over discovered metadata, while deleting a synced model no longer creates a permanent tombstone so a later provider sync can restore it ([#10248](https://github.com/diegosouzapw/OmniRoute/pull/10248)) — thanks @jackjinke

changelog.d/fixes/10249-dedup-hash-collision.md

@@ -1 +0,0 @@
-- fix(open-sse): stop concurrent requests colliding on the same dedup hash for non-OpenAI target formats (#10249)

changelog.d/fixes/10251-text-tool-call-parsing.md

@@ -1 +0,0 @@
-- **fix(translator):** Text-format tool calls emitted inline by some models are now converted to proper `tool_use` blocks. Certain models (DeepSeek, Qwen) return tool invocations as `<tool_call>{"name":"Bash","arguments":{…}}</tool_call>` or `TOOL_CALL Read: {"file_path":"…"}` inside the text stream instead of the structured `tool_calls` field. Both formats leaked through the Claude translators as plain text, so Claude Code rendered the raw block and stalled instead of executing the tool. `extractXmlInvokeBlocks` (previously `<invoke>`-only) now scans for all three shapes in a single pass and emits `content_block_start`/`input_json_delta`/`content_block_stop` events, in both `openai-to-claude` and `gemini-to-claude` (Antigravity) paths ([#10251](https://github.com/diegosouzapw/OmniRoute/pull/10251))

changelog.d/fixes/10261-provider-warning-badges.md

@@ -1 +0,0 @@
-- fix(dashboard): make provider card warning indicators expose the interaction they advertise (#10261)

changelog.d/fixes/10265-command-code-provider-api.md

@@ -1 +0,0 @@
-- fix(command-code): route chat to the documented /provider/v1/chat/completions endpoint instead of the CLI-only /alpha/generate, which Command Code gates/blocks for external callers (#10265)

changelog.d/fixes/10272-provider-test-statuscode-propagation.md

@@ -1 +0,0 @@
-- **fix(providers):** preserve validator HTTP status codes in API-key and web connection-test results so callers can distinguish authentication, rate-limit, and upstream failures ([#10272](https://github.com/diegosouzapw/OmniRoute/pull/10272)) — thanks @Zartharas

changelog.d/fixes/10284-reasoning-probe-truncated-200.md

@@ -1 +0,0 @@
-- **fix(sse):** tiny-budget reasoning probes (e.g. Claude Code's `/model` check sends `max_tokens: 1`) are answered with a valid truncated 200 instead of relaying the upstream 5xx "empty response content" — which previously also marked the connection unavailable and poisoned fallback/cooldown bookkeeping for a request that is only a probe ([#10281](https://github.com/diegosouzapw/OmniRoute/issues/10281)) — thanks @harkaranbrar7

changelog.d/fixes/10285-googleflow-video-wrong-path-auth.md

@@ -1 +0,0 @@
-- fix(video): stop advertising the googleflow (Veo) video provider as working and fail fast with a clear diagnostic — its submit/poll endpoints 404 and no server-side OAuth transport can satisfy the working endpoint (#10285)