Also re-syncs the nine new llm.txt mirrors with the root file, which moved
with the base merge. docs-sync keeps the body byte-identical to the root
minus its top heading; the mirrors carry their own heading plus the language
bar above the --- separator.
Batch 1 of the locale-expansion plan: Greek, Croatian, Serbian, Lithuanian,
Estonian, Latvian, Slovenian, Maltese and Irish across every surface —
dashboard catalog, docs mirrors, CLI catalog, README, locale index and the
marketing site. OmniRoute now ships all 24 official EU languages (51 locales).
Also fixes two defects the batch exposed:
- The placeholder-parity gate matched every "{…}" pair, so an ICU plural branch
body (other {s}) counted as an argument named "s" and any correct plural
translation was reported as drift. The scanner now follows the ICU grammar.
Three translations that invented a {count} argument the English source never
defines were corrected, as was one Irish string that translated the argument
name itself.
- Language bars linked to mirrors that do not exist: docs/guides/I18N.md is
English-only by design yet keeps legacy mirrors, so every new locale got a
dead link. Bars now skip locales without a mirror on disk.
* feat(release): reconcile-changelog tool + version-anchored fragment aggregation
`npm run release:reconcile` (scripts/release/reconcile-changelog.mjs) turns the
v3.8.51 reconciliation pass (#12971) into a repeatable Phase 0a step:
- folds `changelog.d/` fragments under `## [<version>]` — never under the first
matching heading — and credits each one with the PR of the commit that ADDED
it (`git log --diff-filter=A`), because the filename prefix is not reliable
(issue numbers, closed/recreated PRs, literal `#PR_NUMBER`); `--carrier N`
marks a PR that only back-filled fragments for other people's PRs
- drops fragments whose text already ships in another version section
(phantom fragments re-added by branches cut before the previous aggregation)
- covers a commit only when its OWN PR is a primary ref of a bullet (a
`/pull/N` link, the trailing `(#N)`, or an explicit `(#N …)` group) so an
incidental mention cannot hide a PR's own bullet; generates
`**type(scope):** subject (#PR) — thanks @author` for the rest, rolls
Dependabot bumps into one line, documents direct pushes by hash
- `--credit N=handle` carries the closed-PR / co-author / deleted-PR audit
- keeps pre-existing section bullets verbatim (changelog-integrity compares
bullet lines), never touches `[Unreleased]` or older sections
- opens the section with "📊 Release by the numbers" + "🏆 Top 25" (mailmap +
merged-PR login), the v3.8.50 format
`aggregate-changelog.mjs` gains the same anchoring: `insertBullets(text,
bullets, version)` searches the heading inside `## [version]` only (with
`[Unreleased]` still carrying `### ✨ New Features`, every feature fragment was
landing there); `aggregate()` reads the version from package.json.
Tests: tests/unit/reconcile-changelog.test.ts (helpers + an end-to-end
reconcile fixture) and two new cases in tests/unit/changelog-fragments.test.ts.
* fix(release): escape every regex metacharacter before building the mention regex
CodeQL js/incomplete-sanitization on reconcile-changelog.mjs: the handle was only
escaping '-' before being interpolated into a RegExp. Use a full escapeRegExp
helper instead; handles are [A-Za-z0-9_-] in practice, so behaviour is unchanged
for real input and the addCredit tests still pass.
Contadores de docs fora de sincronia com o código, aprovado pelo dono em chat por tocar `AGENTS.md` e `skills/cli-tunnel/SKILL.md` (Hard Rule — superfície de instrução de agente). Nenhuma instrução mudou.
`Docs Gates` acusava 6 drifts STRICT. Dois vieram da minha leva de 16 PRs: migrations 169 → **171** (#12707 trouxe a 173, #12867 a 174) e estratégias de roteamento 19 → **20** (#12789 registrou a `quota-weighted`). Contei os arquivos em vez de confiar na memória: `ls src/lib/db/migrations/*.sql | wc -l` → 171.
Os 41 mirrors de `docs/i18n/*/llm.txt` foram regenerados com `scripts/i18n/sync-llm-mirrors.mjs` — o gate exige cópia exata da raiz.
O outro braço, `check:agent-skills-sync` acusando `GENERATED: + cli-tunnel`, era herdado (o corpo do #12866 já o registrava). O `SKILL.md` commitado documentava `tunnel create [type]`, um argumento que a CLI **não aceita** — conferido em `bin/cli/commands/tunnel.mjs:21`, que declara `.command("create")` puro. Saída do gerador, não escrita à mão.
| gate | antes | depois |
|---|---|---|
| `check:docs-counts` | 6 drifts STRICT | **0** |
| `check:docs-sync` | FAIL — 41 mirrors divergentes | **PASS** |
| `check:agent-skills-sync` | `+ cli-tunnel` | **UNCHANGED: 46 skills** |
Vazamento de credencial em corpo de erro. `tests/unit/error-sanitizer-sk-key-qv45.test.ts` falhava no tip em 8ms:
```
AssertionError: Google key survived: Bad credentials for AIzaSyA1B2C3D4E5F6G7H8I9J0KaLbMcNdOeP
```
O padrão era `/AIza[0-9A-Za-z_-]{35}/` — comprimento **exato**. Uma chave Google padrão tem 39 caracteres e casa; qualquer credencial `AIza…` mais curta ou mais longa passava direto para o corpo do erro.
Os dois lados divergiram na reconciliação de dois PRs do mesmo GHSA: o padrão com `{35}` veio do #12506, o teste anti-drift que cobra `/\\bAIza[A-Za-z0-9_-]{20,}/` veio do #12620. Está vermelho desde que os dois entraram em sequência.
`{20,}` no lugar de `{35}`. Numa mensagem de erro, redigir demais uma string que apenas começa com `AIza` não custa nada; redigir de menos vaza credencial — o lado errado para errar é claro.
Evidência: o arquivo vai de 7/9 para **9/9**. Bateria de sanitização com 538 testes: 533 passam, e as 5 restantes são pré-existentes no tip, não desta mudança (4 levam 21–25s por spawn de processo isolado sob carga; `tunnel-routes-error-sanitization` falha igual no tip puro, verificado). Nenhum teste foi enfraquecido — o padrão foi ampliado para satisfazer uma asserção que já existia.
Consertadas 5 das 7 regressões que o #12867 introduziu em `tests/unit/chatcore-translation-paths.test.ts` — arquivo que ele não toca, e por isso fora da minha validação focada quando o mergeei. Medido: **74/74** em `ce49d96` (antes), **67/74** em `d6f3150` (depois), **72/74** agora.
**Abort de cliente perdeu o mapeamento (3 testes).** O leg classificava por `error.name === "AbortError"`, mas `abort(reason)` pode rejeitar com string crua sem `name` — essa forma caía em 502 em vez de 499, o que o #7907 fixou. E a mensagem passava por `formatProviderError`, entregando `[499]: request aborted by client` ao cliente. O `chatCore` sempre usou `isLocalStreamLifecycleError` e o literal `"Request aborted"`; espelhado.
**`clientResponse` sintético em abort (1 teste).** O caminho antigo omitia o campo porque o cliente já tinha desconectado — esse corpo é o que teríamos enviado, e o dashboard lê o campo como "o que o cliente recebeu". O caminho novo gravava sempre.
**Telemetria de prompt cache sumiu do call log (1 teste).** `claudePromptCacheLogMeta` só era construído dentro do `executeProviderRequest`; o leg virou dono do primeiro send e a variável ficou `null`, então `_omniroute.claudePromptCache` desapareceu **em silêncio** de todo call log desse caminho. Não é teste chato: é observabilidade perdida em produção.
**Corpo não canonicalizável derrubava a request (1 teste).** `derivePostInjectionRequestIdentity` era chamado antes de qualquer checagem de flag; ele canonicaliza o corpo e o `canonicalStringify` rejeita `Date`, `Map` e instâncias de classe por desenho. Um corpo com essas formas lançava `TypeError` em **toda** request não-streaming, inclusive com `SERVER_OWNED_TOOL_LOOP_ENABLED` desligada, que é o default. Agora deriva só quando o loop pode rodar e falha fechada.
Evidência: 74 testes do arquivo 72/74; 138 nas 5 suítes vizinhas com 136 passando; `typecheck:core` limpo; `check-api-typecheck` OK 289; ESLint 0.
**As 2 restantes ficam abertas de propósito** — `refreshes GitHub credentials after 401` e `locks per-model quota failures`. Mesma causa: o leg encerra num não-2xx sem passar pela classificação de falha do `chatCore`. `nonStreamingProviderLeg.ts` não tem uma ocorrência de `lockModel`, `refreshCredentials` ou `markAccountUnavailable`; o `chatCore` tem ~170 linhas disso mais o bloco de refresh 401. Em produção: token Copilot não renova no 401, e 402/429 por quota não trava o modelo naquela conexão. Não consertei porque devolver a `Response` ao `chatCore` é impossível (já consumida por `.text()`) e reimplementar a classificação no leg é decisão de desenho do refactor — @HouMinXi tem o contexto.
Base-red: `API Route Typecheck` falhava no tip com 13 TS2339 novos em `chatCore.ts`, vindos do #12867 — que eu mergeei validando só com `typecheck:core`, que não cobre esse arquivo.
Causa: `legResult` é a união `NonStreamingProviderLegResult`; o guard de erro estreita para a variante `ok`, mas a reatribuição condicional do tool loop devolve o tipo declarado e as 13 leituras seguintes perdem a narrowing. Corrigido fixando a variante num binding próprio — `loopApply.leg` já é `& { kind: "ok" }`, então sem cast.
Gate: 302 erros com 13 novos → **289, todos dentro da baseline congelada**. `typecheck:core` limpo, ESLint 0 no arquivo.
Dois commits: o primeiro é Prettier puro sobre o arquivo do tip (que chegou fora do padrão pelo #12867), verificado byte a byte contra `prettier(tip)`; o segundo é a mudança semântica, 39 linhas.
Os demais vermelhos deste PR são herdados e cobertos por #12990, #12964 e #12970.
Mid-cycle reconciliation of `## [3.8.51]` against the full cycle range
`release/v3.8.50..release/v3.8.51` (091589089c..d6f315018a, 696 non-merge commits):
- fold the 366 `changelog.d/` fragments into the section (features had been
landing under `[Unreleased]` because the aggregator appends at the FIRST
matching heading) and delete them
- drop 25 fragments that duplicate bullets already shipped in `[3.8.50]` /
`[Unreleased]` (six phantom fragments re-added by branches cut before the
v3.8.50 aggregation; 19 pre-cycle PR fragments)
- generate one bullet per cycle commit that had no fragment (350 commits:
44 features / 196 fixes / 91 maintenance, 17 Dependabot bumps rolled up),
carrying the merged PR link and `— thanks @author`
- credit audit: link every fragment to the PR that actually landed it
(`git log --diff-filter=A`), fix three `#PR_NUMBER` placeholders and two
misnumbered fragments (#11845, #11864), credit the recreated PRs to their
original authors (#11887–#11892 → @MumuTW, #12255 → @backryun,
#11771 → @Rahulsharma0810), the nine hartmark co-authored fixes, and the
deleted PR #11370 to @kriptoburak
- add the "Release by the numbers" block, the Top-25 ranking (mailmap +
GitHub login) and the mandatory `### 🙌 Contributors` hall
(111 external contributors + maintainer, generated by
`release:contributors --inject`)
- resync the 41 i18n CHANGELOG mirrors
Gates: check:changelog-integrity OK, check:docs-sync PASS.
Validado numa worktree combinada com as 16 PRs desta leva sobre `release/v3.8.51`: typecheck:core limpo, check-file-size e check-changelog-integrity OK, complexity 2788/3218 e cognitive 1261/1437, ESLint 0 erros nos 152 arquivos alterados, e a suíte vitest:ui completa (2149) verde.
Sobre esta PR especificamente: rodei os **23 arquivos de teste** que ela toca sobre o tip final, depois do merge da base — **392/392**. A migration `174_server_tool_executions.sql` não colide (o tip está em 173, e você já a renumerou em `c35f0fd7`).
O dono foi consultado antes do merge, porque o loop está atrás da flag `SERVER_OWNED_TOOL_LOOP_ENABLED` mas o primeiro send não-streaming mudou de dono sem flag, e a verificação manual em combo com Memory continuava desmarcada. A condição dele foi: entra se os testes focados passarem aqui. Passaram.
O lock de passthrough (`fetchCalls.length === 1`) é a parte que mais me convenceu — o double-dispatch que um `if (stream)` em volta do send existente causaria é exatamente o tipo de regressão que não aparece em teste de comportamento, só em contagem de chamada.
**Três ajustes meus na sua branch:**
1. `tests/unit/chatcore-stream-error-result.test.ts` procurava `"const legResult = await runNonStreamingProviderLeg"`, mas o seu commit final `6077b9dd` passou a reatribuir `legResult` e trocou para `let`. O guard falhava na sua própria branch (confirmei que o arquivo e o `chatCore.ts` eram byte-idênticos ao head da PR, então não era efeito da leva). Passou a aceitar `const|let` — a intenção do guard é o try/catch em volta da chamada, não a palavra-chave.
2. `tests/integration/skills-pipeline.test.ts` foi de 1156 para 1338 linhas e estourou o `testCap` de 1200. Segui o mesmo caminho que você já tinha tomado em `a1d2d20d` para os testes unitários: extraí os três casos do server-owned tool loop para `tests/integration/server-owned-tool-loop-pipeline.test.ts` (259 linhas), com instância própria do harness. O glob `tests/integration/*.test.ts` pega o arquivo novo sem registro adicional. 3/3 verdes isolados.
3. O arquivo novo herdou cinco `any` do original — que só passavam por estarem congelados no `eslint-suppressions.json` sob o nome antigo. Tipei como `Record<string, unknown>`. E `tests/unit/non-streaming-finalization.test.ts` tinha dois argumentos não usados em `trackPendingRequest`, agora prefixados com `_`.
Nada disso toca produção nem enfraquece asserção.
Validado numa worktree combinada com as 16 PRs desta leva sobre `release/v3.8.51`: typecheck:core limpo, check-file-size e check-changelog-integrity OK, complexity 2788/3218 e cognitive 1261/1437, ESLint 0 erros nos 152 arquivos alterados, 771 testes unitários focados, 49 de integração e a suíte vitest:ui completa (2149) verdes.
**Sobre a reconstrução da branch.** Esta PR continha os 7 commits do #12746 mais os 3 do round-robin. O dono escolheu mergear os dois em sequência em vez de fechar um como subsumido, então depois que o squash do #12746 entrou eu reconstruí esta branch: cherry-pick de `05059880`, `54168238` e `ddd6bcbf` sobre o tip novo, e force-push. Autoria preservada — os três commits continuam seus (`Minxi Hou <houminxi@gmail.com>`), verificado com `git log --format=%an` antes do push. A PR foi de +4167/−3187 em 14 arquivos para +1281/−1182 em 5, que é o delta real do round-robin.
O `05059880` ("guard round-robin extract before the lift") é o commit que faz esse tipo de extract ser revisável: sem um teste que fixe o contrato antes do movimento, mover 1198 linhas é indistinguível de reescrever 1198 linhas.
Revalidei sobre o tip reconstruído: `round-robin-combo`, `combo-attempt-loop`, `execute-target-attempt`, `execute-target-gates` e `combo-loop-safety-timer-leak-11804` — 24/24 — com typecheck:core limpo e o cap de arquivo OK.
Validado numa worktree combinada com as 16 PRs desta leva sobre `release/v3.8.51`: typecheck:core limpo, check-file-size e check-changelog-integrity OK, complexity 2788/3218 e cognitive 1261/1437, ESLint 0 erros nos 152 arquivos alterados, 771 testes unitários focados, 49 de integração e a suíte vitest:ui completa (2149) verdes.
Guardar os contratos com testes ANTES de levantar o bloco (`05059880` no irmão, e o `287658f5` marcando os `executeTargetGates` como lift-as-is) é o que torna um refactor deste tamanho auditável. Sem essa ordem, um extract de 3 mil linhas é indistinguível de uma reescrita.
Revalidei depois do merge da base: `combo-attempt-loop`, `execute-target-attempt`, `execute-target-gates` e `combo-loop-safety-timer-leak-11804` — 20/20 — mais typecheck:core limpo e o cap de arquivo OK.
O #12811 entra na sequência logo em seguida, com os três commits do round-robin sobre este.
Validado numa worktree combinada com as 16 PRs desta leva sobre `release/v3.8.51`: typecheck:core limpo, check-file-size e check-changelog-integrity OK, complexity 2788/3218 e cognitive 1261/1437, ESLint 0 erros nos 152 arquivos alterados, 771 testes unitários focados, 49 de integração e a suíte vitest:ui completa (2149) verdes.
Reservar o sorteio antes do próximo `await` (`2cf74acc`) é a parte não-óbvia e a que mais importa: sem isso dois pipelines no mesmo processo observam `inflight=0` na mesma conta e convergem para ela. O comentário no código explica isso melhor do que o commit message.
**Um ajuste meu na sua branch.** O `tests/unit/combo/quota-weighted-strategy.test.ts` era intermitente — falhava em cerca de 1 a cada 5 execuções, alternando entre `A/B isolation: 7 hard-empty…` e `floor=0 puts 0.5% in the main pool`, sempre com dois pares de mesma faixa trocando de posição. A causa é o helper de fixture:
```ts
const iso = (ms = 86_400_000) => new Date(Date.now() + ms).toISOString();
```
Como `iso()` é chamado a cada invocação do fetcher, dois peers que deveriam empatar recebiam `resetAt` com um milissegundo de diferença sempre que o relógio virava entre as duas chamadas. Pressão de reset entra no score, então esse epsilon quebrava o empate e `sortByScoreThenIndex` nunca chegava ao fallback por índice de inserção.
Fixei a base do relógio uma vez só (`CLOCK_BASE`). Nenhuma asserção foi tocada — as garantias de ordem, tamanho e exclusão continuam idênticas. 10/10 execuções verdes depois, e mais 6/6 após o merge da base nesta branch.
Também mergeei a base para resolver `file-size-baseline.json` (aditivo) e `src/domain/quotaCache.ts`, onde o seu placeholder `_providerSpecificData` cedeu lugar à implementação do #12803, que usa o parâmetro de fato.
Validado numa worktree combinada com as 16 PRs desta leva sobre `release/v3.8.51`: typecheck:core limpo, check-file-size e check-changelog-integrity OK, complexity 2788/3218 e cognitive 1261/1437, ESLint 0 erros nos 152 arquivos alterados, 771 testes unitários focados, 49 de integração e a suíte vitest:ui completa (2149) verdes.
O ponto que sustenta a PR é o `models.dev` virar overlay de preço em vez de fonte de catálogo. Um catálogo estático que sobrevive à conta já ter listado ids mais novos é o tipo de defeito que só aparece quando o modelo novo é justamente o que se quer usar.
Nota de integração: `activeSyncedCatalog.ts` colidiu com o #12934 (união dos `customModels` do picker no catálogo de despacho). Como você extraiu o bloco original para `loadConnectionCatalog`, os dois se compõem: a união dos irmãos agy/antigravity primeiro, o `unionCustomModels` por cima. Revalidei com `custom-models-live-catalog-12597`, `live-model-catalog-reconciliation-8926`, `sync-models-degraded-cached-catalog-9683`, `models-dev-catalog-read-gate`, `discovery-class`, `reactive-model-sync` e `l1-oauth-autosync-default` juntos — 48/48 — mais typecheck:core limpo.
Sobre o `autoSync` padrão em Claude/Codex/Copilot com scheduler de 6h: passei isso pelo dono antes de mergear e a decisão foi manter como está.
Validado numa worktree combinada com as 16 PRs desta leva sobre `release/v3.8.51`: typecheck:core limpo, check-file-size e check-changelog-integrity OK, complexity 2788/3218 e cognitive 1261/1437 (ambos sob a baseline), ESLint 0 erros nos 152 arquivos alterados, 771 testes unitários focados, 49 de integração e a suíte vitest:ui completa (2149) verdes.
A assimetria era exatamente o defeito: o REST do picker já mesclava `customModels`, o despacho não, e o operador via o modelo na tela e tomava 400 na inferência. O overlay só de campos definidos é o detalhe que impede uma escrita esparsa do picker de apagar metadata de capacidade que veio do sync.
Nota de integração: este arquivo colidiu com o #12866, que extraiu o mesmo bloco para `loadConnectionCatalog` e uniu os catálogos irmãos agy/antigravity. Integrei os dois na worktree combinada — a união de irmãos primeiro, o `unionCustomModels` por cima — e a resolução vai junto no merge do #12866.
Validado numa worktree combinada com as 16 PRs desta leva sobre `release/v3.8.51`: typecheck:core limpo, check-file-size e check-changelog-integrity OK, complexity 2788/3218 e cognitive 1261/1437 (ambos sob a baseline), ESLint 0 erros nos 152 arquivos alterados, 771 testes unitários focados, 49 de integração e a suíte vitest:ui completa (2149) verdes. Após o merge da base nesta branch, os 11/11 do `combo-pin-implicit-allowlist` foram revalidados.
A distinção entre pin de step de combo e pin forçado por header (`x-omniroute-connection`) é o que salva a PR de virar uma restrição ampla demais — o header continua permitindo fallback para conexões irmãs, o step não.
Apontar que o `a11930ec4` para a rotação dentro do `handleSingleModel` mas não popula `allowedConnectionIds` no resolve foi a peça que explicou por que os dois são complementares e não redundantes. Sem isso a PR pareceria duplicar um gate que já existia.
Validado numa worktree combinada com as 16 PRs desta leva sobre `release/v3.8.51`: typecheck:core limpo, check-file-size e check-changelog-integrity OK, complexity 2788/3218 e cognitive 1261/1437 (ambos sob a baseline), ESLint 0 erros nos 152 arquivos alterados, 771 testes unitários focados, 49 de integração e a suíte vitest:ui completa (2149) verdes.
`blockExtraUsage: false` significa "pode usar crédito extra", nunca "esconda a conta antes de despachar" — a conta saía da rota justamente quando o crédito extra existia para ser usado. Os 32/32 cobrem os quatro pontos onde a mesma decisão era tomada, e revalidei após o merge da base (32/32 de novo).
Nota de integração: o seu `isQuotaExhaustedForRequest` colidiu com o placeholder `_providerSpecificData` do #12789 na worktree combinada. Ficou a sua implementação, que é a que de fato usa o parâmetro. A base foi mergeada na branch para resolver o `file-size-baseline.json` (aditivo, JSON revalidado).
Validado numa worktree combinada com as 16 PRs desta leva sobre `release/v3.8.51`: typecheck:core limpo, check-file-size e check-changelog-integrity OK, complexity 2788/3218 e cognitive 1261/1437 (ambos sob a baseline), ESLint 0 erros nos 152 arquivos alterados, 771 testes unitários focados, 49 de integração e a suíte vitest:ui completa (2149) verdes.
A decodificação dos campos aninhados 10/20/30 do `GetRemainingResets` ao vivo (último commit) é o que separa isto de um palpite sobre o formato do frame. Mostrar zero em vez de esconder a linha é a escolha certa: crédito zerado é informação, ausência de linha é ambiguidade.
Validado numa worktree combinada com as 16 PRs desta leva sobre `release/v3.8.51`: typecheck:core limpo, check-file-size e check-changelog-integrity OK, complexity 2788/3218 e cognitive 1261/1437 (ambos sob a baseline), ESLint 0 erros nos 152 arquivos alterados, 771 testes unitários focados, 49 de integração e a suíte vitest:ui completa (2149) verdes.
Regressão de v3.8.50 vinda do #9057, com o sintoma mais enganoso possível: `attempted: 0`. A política já tinha admitido o combo e a checagem era refeita em cada membro interno.
Manter o filtro por prefixo de provider e o `disableNonPublicModels` intactos é o que impede o short-circuit de virar um buraco na allow-list.
Validado numa worktree combinada com as 16 PRs desta leva sobre `release/v3.8.51`: typecheck:core limpo, check-file-size e check-changelog-integrity OK, complexity 2788/3218 e cognitive 1261/1437 (ambos sob a baseline), ESLint 0 erros nos 152 arquivos alterados, 771 testes unitários focados, 49 de integração e a suíte vitest:ui completa (2149) verdes.
A busca do sufixo mais longo primeiro (`-xhigh` antes de `-high`) é o detalhe que faz a herança funcionar em vez de quase-funcionar. Manter `getResolvedModelContextOverride` fora do escopo, com o teste existente registrando que aquele caminho continua sem herança, deixa a fronteira explícita.
Validado numa worktree combinada com as 16 PRs desta leva sobre `release/v3.8.51`: typecheck:core limpo, check-file-size e check-changelog-integrity OK, complexity 2788/3218 e cognitive 1261/1437 (ambos sob a baseline), ESLint 0 erros nos 152 arquivos alterados, 771 testes unitários focados, 49 de integração e a suíte vitest:ui completa (2149) verdes.
A separação entre o que é do service worker e o que é do Caddy está certa e é o que torna a PR mergeável: o `respondWith` em navegação é defeito nosso, o `Alt-Svc` mentindo h3 é config de proxy reverso e não tem o que fazer aqui.
O `/dashboardfoo` casando com `startsWith("/dashboard")` é um achado à parte, e o bump de cache v2→v3 é o que faz o worker antigo sair do ar nos clientes que já estão presos.
Validado numa worktree combinada com as 16 PRs desta leva sobre `release/v3.8.51`: typecheck:core limpo, check-file-size e check-changelog-integrity OK, complexity 2788/3218 e cognitive 1261/1437 (ambos sob a baseline), ESLint 0 erros nos 152 arquivos alterados, 771 testes unitários focados, 49 de integração e a suíte vitest:ui completa (2149) verdes.
Available 0% com Voucher 100% e Cash 100% não é estado de carteira que exista — foi o sinal certo para puxar o fio. Tratar leftover como booleano só para Available e cravar 100% nos outros dois buckets é o tipo de defeito que passa despercebido enquanto a conta tem saldo.
Os dois testes cobrem os dois lados: o produtor e o caminho até `getQuotaRemainingPercentage` com `isCredits` + CNY.
Validado numa worktree combinada com as 16 PRs desta leva sobre `release/v3.8.51`: typecheck:core limpo, check-file-size e check-changelog-integrity OK, complexity 2788/3218 e cognitive 1261/1437 (ambos sob a baseline), ESLint 0 erros nos 152 arquivos alterados, 771 testes unitários focados, 49 de integração e a suíte vitest:ui completa (2149) verdes.
O `nodeMap` lido do closure de `RuntimePageClient` por uma função de nível de módulo é uma bomba-relógio silenciosa: só explode quando um monitor entra em error/exhausted/alerting, e o teste existente só alimentava listas vazias. Tirar o arquivo do exclude do vitest vale tanto quanto o fix — confirmei aqui que `tests/unit/ui/runtime-page-client.test.tsx` agora roda na `test:vitest:ui` e passa.
A anotação sobre o "内部服务器错误" ser o catálogo RSC da página, e não o crash, poupou o próximo a caçar fantasma.
Validado numa worktree combinada com as 16 PRs desta leva sobre `release/v3.8.51`: typecheck:core limpo, check-file-size e check-changelog-integrity OK, complexity 2788/3218 e cognitive 1261/1437 (ambos sob a baseline), ESLint 0 erros nos 152 arquivos alterados, 771 testes unitários focados, 49 de integração e a suíte vitest:ui completa (2149) verdes.
Além do bug do toast, esta PR foi a que derrubou os três base-reds vivos do tip: o fragmento `changelog.d/fixes/reset-aware-model-family.md` sem o `- ` inicial, o registro do `tests/unit/reset-aware-request-scope-12600.test.ts` no `stryker.conf.json` e o `TS2554` do glm. O `check-changelog-integrity` voltou a passar aqui por causa dela.
O diagnóstico do MouseEvent é o que dá o valor: `onConfirm` chegava como handler de clique nativo e `handleBatchDeleteConfirm` tratava qualquer primeiro argumento truthy como callback. O cinto (`typeof`) e o suspensório (o wrap no ConfirmModal) juntos estão certos — só um dos dois deixaria a porta aberta para o próximo caller.
Validado numa worktree combinada com as 16 PRs desta leva sobre `release/v3.8.51`: typecheck:core limpo, check-file-size e check-changelog-integrity OK, complexity 2788/3218 e cognitive 1261/1437 (ambos sob a baseline), ESLint 0 erros nos 152 arquivos alterados, 771 testes unitários focados, 49 de integração e a suíte vitest:ui completa (2149) verdes.
O `65536` era o 16º posicional de um helper com 15 parâmetros — `TS2554` vivo no tip (`open-sse/executors/glm.ts:244`, confirmado aqui antes do board). O teste de guarda de aridade é o que impede a reincidência: ele checa a assinatura do helper e o call site, não o comportamento, que é exatamente onde o erro morava.
Obrigado por isolar isso do #12711 em vez de deixar o `glm.ts` viajar junto com pin/combo-split/moonshot.
* chore(ci): guard commit identity in pre-commit to stop author misattribution
Two windows of commits in this checkout were signed with the wrong identity,
both caused by an identity override left behind by an automated session:
2026-08-13..26 (name "Xiangzhe" + @backryun's e-mail, 237 commits) and
2026-08-29..09-02 (name "Markus Hartung" + the maintainer's e-mail, 59 commits).
The .mailmap repairs the record after the fact; this gate stops the next window.
The gate is opt-in per machine via omniroute.expectedName / expectedEmail — with
no config it exits 0, so contributors who clone the repo are never affected. It
blocks three things: a committer that is not this machine's identity (which is
what BOTH windows looked like — in August neither the name nor the e-mail was
the maintainer's, so checking only their e-mail would have missed it), an author
carrying the maintainer's e-mail under someone else's name, and any address
listed in omniroute.legacyEmail.
Crediting a contributor with `git commit --author="Name <their@email>"` keeps
working, since the rule targets the committer and the maintainer's own address.
* test(ci): isolate the identity gate's test from the ambient git config
The "stays inert when the machine has not opted in" case read the real
global config, so on a machine that HAS opted in (omniroute.expectedEmail
set — the maintainer's own boxes, where this gate matters most) the gate
correctly refused a synthetic contributor identity and the test failed.
It only passed on a clean CI runner.
Neutralising GIT_CONFIG_GLOBAL/GIT_CONFIG_SYSTEM makes the opt-in state
come solely from what the test injects, so the suite is deterministic on
both an opted-in and a clean machine.
2026-09-07 08:35:29 -03:00
1896 changed files with 417445 additions and 9221 deletions
_Living section — cycle opened at the v3.8.50 freeze (parallel-cycle model). Bullets are aggregated from `changelog.d/` fragments at each `/generate-release` phase._
_Living section — reconciled 2026-09-07 from all cycle commits (`release/v3.8.50` tip `091589089c` → `release/v3.8.51` tip `d6f315018a`, 696 non-merge commits). Bullets carry the merged PR and its author; direct pushes are listed with their commit hash. Regenerated at each `/generate-release` phase._
### 📊 Release by the numbers
| | |
| --- | ---: |
| 👥 People who contributed | **120** |
| 📝 Commits in the cycle | **696** |
| 🔀 Pull requests referenced | **672** |
| 📋 Changelog entries | **685** |
| 🙌 Contributors credited in entries | **118** |
| 🤖 Automated dependency commits | 18 |
**Entries by type**
| Type | Count |
| --- | ---: |
| 🐛 Fixes | 403 |
| ✨ Features | 118 |
| 🧹 Chore | 72 |
| 📚 Docs | 36 |
| 🧪 Tests | 29 |
| ⚡ Performance | 7 |
| ♻️ Refactor | 7 |
| 🏗️ Build | 6 |
| ⚙️ CI | 2 |
| ⏪ Reverts | 2 |
| 📦 Dependencies | 2 |
| 🔒 Security | 1 |
### 🏆 Top 25 contributors this cycle
_By commits in `release/v3.8.50..release/v3.8.51` (`091589089c..d6f315018a`), author identities consolidated via `.mailmap` and the merged PR's GitHub login. Bots excluded._
- **feat(audio):** proxy native ElevenLabs voices, text-to-speech, and speech-to-text HTTP routes through stored OmniRoute credentials, preserving query strings, multipart uploads, binary responses, and upstream errors (#10556). ([#11434](https://github.com/diegosouzapw/OmniRoute/pull/11434)) — thanks @hartmark
- Added Google AI Studio Gemini batch text-to-speech support through `POST /v1/audio/speech`. ([#11434](https://github.com/diegosouzapw/OmniRoute/pull/11434)) — thanks @hartmark
- Run synchronous RTK and Caveman request compression in a bounded worker-thread pool, keeping large `/v1/responses` compression heaps outside the HTTP isolate while preserving strict fail-open behavior and per-engine telemetry. ([#11434](https://github.com/diegosouzapw/OmniRoute/pull/11434)) — thanks @hartmark
- **feat(routing):** subscription-first auto groupings — `auto/subscription` routes only through plan-included connections with a documented hard-stop overage and fails closed on exhaustion, while `auto/thrifty` orders the pool `subscription → keyless → free → cheap → premium` and steps up one rung at a time as each is exhausted. Billing class comes from a curated per-connection catalog (uncurated is treated as metered, never plan-included), both reuse STRICT_ZERO_COST's per-connection verification, and a quota reading whose `resetAt` has passed is now refreshed regardless of TTL so routing returns to plan capacity as soon as it resets ([#11146](https://github.com/diegosouzapw/OmniRoute/pull/11146)) — thanks @yourspraveen
- **feat(providers):** publish a management-authenticated versioned web-session credential contract from OmniRoute's canonical browser credential metadata ([#11340](https://github.com/diegosouzapw/OmniRoute/pull/11340)) — thanks @Zartharas
- **feat(video bridge):** harden the optional drill-down cache substrate with exact-path broker policy, canonical principal/session/media isolation, independent retained-byte quotas, cancellation-safe commits, rejection of excess or non-canonical Base64 padding and non-JPEG/truncated media, warning-sensitive full JPEG canonicalization that strips trailing polyglot bytes, server-derived dimensions, and auditable derivation metadata; production tenant binding and multi-resolution selection remain follow-up work ([#11369](https://github.com/diegosouzapw/OmniRoute/pull/11369)) ([#11434](https://github.com/diegosouzapw/OmniRoute/pull/11434)) — thanks @hartmark
- **feat(search):** Add Xquik X search with typed results, credential validation, REST routing, and MCP selection ([#11370](https://github.com/diegosouzapw/OmniRoute/pull/11370)) — thanks @kriptoburak
- **feat(video):** add an opt-in focused analysis mode that safely uses a normalized, 500-code-point latest-user hint for task-aware frame captions while preserving full-mode prompts, temporal-window isolation, and cache identity without storing raw task text ([#11383](https://github.com/diegosouzapw/OmniRoute/pull/11383)). ([#11434](https://github.com/diegosouzapw/OmniRoute/pull/11434)) — thanks @hartmark
- **feat(dashboard):** surface durable exclusive managed leases in the existing Sessions view, keeping leased clients visible across idle gaps while marking connections with in-flight work as active ([#11389](https://github.com/diegosouzapw/OmniRoute/pull/11389)) — thanks @KaspaPulse
- **build(bun):** allow Turbopack bundler flag on Bun 1.4+ with configurable Webpack fallback ([#11471](https://github.com/diegosouzapw/OmniRoute/pull/11471)) — thanks @TheDemonTuan
- feat(api): add an opt-in `modelVisibilityAllowlist`/`modelVisibilityDenylist` settings pair to curate exactly which models `/v1/models` advertises, mirrored into every `auto/*` combo candidate pool so a denied model cannot be routed to via combo selection either (#11481) ([#11997](https://github.com/diegosouzapw/OmniRoute/pull/11997))
- **feat(rankings):** the Free Provider Rankings page shows what each provider actually served over the last 24 h. It ranked by ELO alone, which left a provider that answers every call with an error in first place; the usage data was already served by the API but never requested. A provider with too small a sample shows a dash, not a number ([#11546](https://github.com/diegosouzapw/OmniRoute/pull/11546)) ([#11553](https://github.com/diegosouzapw/OmniRoute/pull/11553)) — thanks @maxmad64bis
- **feat(guardrails):** enforce a bounded, deterministic contract for Video Bridge transcripts — 256 cues, 4096 input code units and 4 KiB UTF-8 per cue, 64 KiB total text, malformed-Unicode rejection, focus-window scoping, cross-source reconciliation with contributing-source metadata, and a structural provenance trust boundary so caller JSON can never self-assert `embedded`/`audio-bridge` provenance ([#11652](https://github.com/diegosouzapw/OmniRoute/issues/11652)) ([#12009](https://github.com/diegosouzapw/OmniRoute/pull/12009))
- **feat(video):** orchestrate optional Video Bridge audio extraction and Audio Bridge STT behind a dual opt-in (operator setting AND per-request signal) — a new loopback-only broker `mode=audio` operation shares the frame path's exact process queue, deadline, AbortSignal, and byte budgets to extract a bounded mono 16 kHz PCM WAV from the same already-downloaded video, then reuses the existing Audio Bridge transcription boundary; provider segment timing is preserved when available and marked coarse otherwise, and every failure degrades to a visual-only-safe partial instead of throwing (#11654). ([#12012](https://github.com/diegosouzapw/OmniRoute/pull/12012))
- Add a tenant-bound Video Bridge drill-down lifecycle on top of the existing secure cache substrate: opaque hashed handles (never raw session/video identifiers), preview/standard/detail multiresolution variants resampled on read, response pagination capped at 8 frames and 32 MiB, and a new authenticated `/api/v1/video-bridge/drilldown` consumer route that stays disabled for remote access by default and denies cross-key access with the same response as a nonexistent handle (no existence oracle). ([#12006](https://github.com/diegosouzapw/OmniRoute/pull/12006))
- **test(video):** Add the Video Bridge FU-07/FU-09 promotion-evidence harness (#11656) — a frozen Zod manifest schema covering the 8 required scenario kinds (static scenes, rapid cuts, late facts, fades, blur, small text, close events, visual prompt injection) with a minimum of 3 repetitions per case, deterministic declarative fixture recipes (`videoBridgePromotionFixtures.ts`), a pure medians/p95 metrics aggregator, a pure FU-07/FU-09 promotion-verdict evaluator applying the ticket's exact thresholds (missing token usage always holds), a digest-only persistence layer that never retains raw media or raw model responses, and a versioned per-model promotion allowlist shipped empty with every model defaulting to `hold`. The FU-07/FU-09 promotion verdicts themselves remain HOLD — they require a real evidence run against real models on VPS 192.168.0.15. ([#12008](https://github.com/diegosouzapw/OmniRoute/pull/12008))
- **feat(video bridge):** "embedded" transcript provenance can now be legitimately earned instead of merely asserted — a bounded, allowlisted (`mov_text`/`subrip`/`webvtt`) subtitle probe runs through the loopback-only Video Bridge broker (at most 2 streams, 10s subdeadline bounded by the request deadline, 256 KiB output, 4096-code-unit lines), normalized through a bounded, ReDoS-safe WebVTT parser and Zod-validated end to end. The adapter always resolves to an explicit `success`/`absent`/`transient_failure` outcome — a subtitle failure never breaks the visual description path, and only a fingerprint-verified broker response (never a caller-declared label) can produce embedded cues (#11659). ([#12011](https://github.com/diegosouzapw/OmniRoute/pull/12011))
- Default new Antigravity-family connections (agy CLI imports and Antigravity OAuth connects) to model auto-sync, so live model discovery lands in the synced catalog and `/v1/models` picks up freshly released upstream models (e.g. Gemini 3.7 Flash tiers) without code changes. Existing connections keep their current setting; the per-connection dashboard toggle remains the opt-out. (#11685 — thanks @MumuTW) ([#11887](https://github.com/diegosouzapw/OmniRoute/pull/11887))
- **feat(ui):** enable React Compiler (`reactCompiler: true` + `babel-plugin-react-compiler`) for automatic memoization at build time ([#11783](https://github.com/diegosouzapw/OmniRoute/pull/11783)) — thanks @jonlwheat2-gif
- **feat(providers):** add SeekAi (`seekai.cc`) as an OpenAI-compatible New-API gateway — catalog id `seekai` (alias `ska`), `https://seekai.cc/v1`, live `/v1/models` via `passthroughModels`, aggregator-list membership so New-API balance detection can opt in. No referral/aff codes. ([#11786](https://github.com/diegosouzapw/OmniRoute/issues/11786)) ([#12557](https://github.com/diegosouzapw/OmniRoute/pull/12557)) — thanks @HouMinXi
- **feat(zai):** add GLM-5.3-Flash Coding Plan support (1M context, 128K output, vision, `low|high|max` reasoning) and route `zai` GLM-5.3-family API-key traffic through the OpenAI-compatible Coding Plan endpoint with native thinking defaults ([#11801](https://github.com/diegosouzapw/OmniRoute/pull/11801)) — thanks @Neuron-Mr-White
- **feat(combo):** choose how combo models are ordered — manual, provider, score, or name — via a sort control in the dashboard builder, persisted in `config.modelSort` and re-applied on load and after add ([#11812](https://github.com/diegosouzapw/OmniRoute/pull/11812)) — thanks @maxmad64bis
- **feat(free):** custom models can be marked free-tier via `customModels[].isFree`; `isFreeModel()` is the first door and `hidePaidModels` respects it even for providers outside the free budget ([#11843](https://github.com/diegosouzapw/OmniRoute/pull/11843)) — thanks @maxmad64bis
- **feat(nodejs):** add `5dive` as a `configure` target — `omniroute configure 5dive` / `omniroute setup-5dive` write a 5dive auth profile that points an agent fleet's `claude` seats at OmniRoute, with the root-only write, the loopback-vs-`https` endpoint rule and the per-seat model pin handled explicitly ([#11852](https://github.com/diegosouzapw/OmniRoute/pull/11852)) — thanks @5dive-bot
- **feat(sse):** treat `max` as a first-class reasoning-effort tier and clamp per model family (GLM 5.1+/DeepSeek V4+/Kimi K3+ keep native `max`; o1/MiniMax/Grok/Muse Spark clamp to their upstream ceiling) ([#11875](https://github.com/diegosouzapw/OmniRoute/pull/11875)) — thanks @Chewji9875
- **feat(providers):** the provider plugin manifest now advertises a `usage-fetch` capability for the 40 providers that have a wired usage/quota fetcher, so external dashboards can read it from `GET /api/v1/provider-plugin-manifest` instead of parsing `open-sse/services/usage.ts` after every release. Discovery only — no new fetcher, no quota change, and the Dashboard quota widget stays gated by `USAGE_SUPPORTED_PROVIDERS`. `USAGE_FETCHER_PROVIDERS` moved to a zero-dependency leaf (`open-sse/services/usage/fetcherProviders.ts`) and is re-exported from `services/usage.ts`, keeping the manifest module a light leaf instead of pulling the ~490-module usage dispatcher into the manifest route. ([#11903](https://github.com/diegosouzapw/OmniRoute/pull/11903)) — thanks @maxmad64bis / @pacocartones
- **feat(plugins):**`OMNIROUTE_PLUGINS_DIR` sets the directory the runtime plugin scanner reads — and the root the plugin manager installs into — overriding the `HOME`-derived default, so a Docker/K8s deployment can point straight at its bind-mounted plugin tree instead of moving `HOME` just to relocate the scan path. An image that exports no home no longer scans `/tmp/.omniroute/plugins` in silence: the resolved directory is logged once at startup as `scanner.dir_resolved`, naming the input that won. Unset, behaviour is unchanged. Distinct from the CLI-only `OMNIROUTE_PLUGIN_PATH`, which finds `omniroute-cmd-*` command packages and never reached this scanner ([#11906](https://github.com/diegosouzapw/OmniRoute/pull/11906)) — thanks @amaleta / @pacocartones
- **feat(leases):** add an explicit owner-authenticated status action that returns only the active lease's privacy-safe configured connection and provider labels, with generation fencing and no credential or internal-id disclosure ([#11910](https://github.com/diegosouzapw/OmniRoute/pull/11910)) — thanks @KaspaPulse
- **feat(providers):** import-from-file modal shows per-row API errors and ships a downloadable CSV template ([#12071](https://github.com/diegosouzapw/OmniRoute/issues/12071)) ([#12504](https://github.com/diegosouzapw/OmniRoute/pull/12504)) — thanks @HouMinXi
- **feat(providers):** dashboard search matches connection name and `baseUrl` so imported OpenAI-compat nodes surface on the provider card ([#12108](https://github.com/diegosouzapw/OmniRoute/issues/12108)) ([#12495](https://github.com/diegosouzapw/OmniRoute/pull/12495)) — thanks @HouMinXi
- **feat(routing):** add a `score` Auto router strategy that selects the highest configured weighted score and reuses `explorationRate`. ([#12155](https://github.com/diegosouzapw/OmniRoute/pull/12155)) — thanks @jacobsparts
- Add a runtime feature flag to disable universal context handoffs globally without changing the default behavior. ([#12167](https://github.com/diegosouzapw/OmniRoute/pull/12167)) — thanks @jacobsparts
- **feat(providers):** the provider plugin manifest now also advertises a `usage-supported` capability for the 46 providers whose usage API is accepted by the server and Dashboard routes, so integrators can distinguish "the server will serve quota for this provider" from "a fetcher is wired" without reading TypeScript. Discovery only — no fetcher or quota change. `usage-fetch` resolves on id or alias (the usage dispatcher accepts both); `usage-supported` resolves on id alone, matching the runtime guard `USAGE_SUPPORTED_PROVIDERS.includes(providerId)`. `USAGE_SUPPORTED_PROVIDERS` moved to a zero-dependency leaf (`open-sse/services/usage/supportedProviders.ts`) and is re-exported from `providers.ts`, mirroring the `fetcherProviders` leaf from #11903 and keeping the manifest a light module. ([#12214](https://github.com/diegosouzapw/OmniRoute/pull/12214)) — thanks @maxmad64bis
- **feat(rankings):** order Free Provider Rankings by what each provider actually served — `GET /api/free-provider-rankings?sortBy=reliability` and a "Most reliable first" toggle on the page. Providers with too few calls to state a success rate keep their score order below the measured ones; the default order is unchanged ([#12218](https://github.com/diegosouzapw/OmniRoute/pull/12218)). — thanks @maxmad64bis
- **perf(sse):** defer `cloneLogPayload()` in the structured SSE collector until after the `maxEvents`/`maxBytes` cap check, eliminating ~9,800 wasted `structuredClone` calls per streaming response (65–71% faster `push()`). Reducer snapshot isolation restored for OpenAI and Responses summaries ([#12241](https://github.com/diegosouzapw/OmniRoute/pull/12241)) — thanks @PauloHSOliveira ([#12243](https://github.com/diegosouzapw/OmniRoute/pull/12243))
- **feat(usage):** Devin CLI agentic quota (Codeium seat-management GetUserStatus) and OpenRouter key limits plus account credits now surface in Provider Limits ([#12256](https://github.com/diegosouzapw/OmniRoute/pull/12256) — thanks @Neuron-Mr-White)
- **feat(settings):** persist `headroomUrl` through Settings so status/start use the operator URL instead of only `HEADROOM_URL` ([#12306](https://github.com/diegosouzapw/OmniRoute/issues/12306)) ([#12487](https://github.com/diegosouzapw/OmniRoute/pull/12487)) — thanks @HouMinXi
- **feat(auto-combo):** Auto-Combo scoring can now weigh how often a provider/model has actually succeeded. The engine already carried that number on every candidate — 24 hours of usage history behind a ten-sample floor, real-time metrics otherwise — and the scoring function never read it, while the weight table described `stability` as if it did. `reliability` (`1 - failureRate`, with the same field precedence and the same rate-bounding the speed ranking already uses, so a corrupt reading means "nothing observed" rather than "fails every call") is now a declared factor shipping at weight `0`, so routing is unchanged until an operator gives it one, and the `stability` description now matches what that factor computes ([#12317](https://github.com/diegosouzapw/OmniRoute/pull/12317)) — thanks @maxmad64bis
- **feat(routing):** With `freeAccessPolicy: "strict"`, the read-only candidate listing (`GET /v1/auto-combo/{channel}/candidates`) no longer hides the candidates the zero-cost guard excludes — the same read-only transparency the resilience filter already honours (#9133). Each candidate now carries `freeAccessExclusion` saying why it would be kept out, and it tells an exhausted allowance apart from a quota reading that never arrived or went stale, which used to look identical from the outside. Routing is unchanged: the listing reports, it never enforces. The separate `excludeTosAvoid` guard still drops its candidates without a reason; that gap is now documented rather than closed ([#12319](https://github.com/diegosouzapw/OmniRoute/pull/12319)) — thanks @maxmad64bis
- **feat(radar):** The Radar catalog table now shows two facts it was already receiving from the feed and dropping on the floor: the per-model rate limits (requests and tokens, per minute and per day) in a new column, and a badge when a provider's terms state it may train on the prompts you send. A limit of zero renders as zero rather than "rate-only" — for a ceiling those are opposite facts — and a model with no training statement gets no badge, because an absent statement is not a guarantee ([#12320](https://github.com/diegosouzapw/OmniRoute/pull/12320)) — thanks @maxmad64bis
- **feat(radar):** explain Community, single-use, contributor, supporter, recovery, abuse, offers, and privacy rules before either Radar activation action, and remove the superseded fixed-PR grant promise from every UI locale ([#12342](https://github.com/diegosouzapw/OmniRoute/pull/12342))
- **feat(gamification):** the dashboard Profile page now shows the real daily streak — `/api/gamification/level` returns `streak: { current, longest }` (per key with `apiKeyId`, operator-wide maximum otherwise) and the streak card reads it instead of a hard-coded 0 (#2403) ([#12377](https://github.com/diegosouzapw/OmniRoute/pull/12377)) — thanks @pacocartones
- **feat(gamification):** the dashboard leaderboard now shows each API key's display name under the Name column instead of a truncated key id; `GET /api/gamification/leaderboard` attaches `name` per entry (name only — no key material), while the shared ranking helper and the federation leaderboard stay id-only — thanks @pacocartones ([#12385](https://github.com/diegosouzapw/OmniRoute/pull/12385))
- **feat(gamification):** enforce the documented 1000 XP/min per-API-key anti-cheat rate limit on the XP award path; over-limit awards are logged and skipped instead of persisted, and the sliding window now matches the timestamp format stored in `xp_audit_log` ([#2403](https://github.com/diegosouzapw/OmniRoute/issues/2403)) ([#12390](https://github.com/diegosouzapw/OmniRoute/pull/12390)) — thanks @pacocartones
- **feat(admin):** localize the gamification anomalies page — the loading state, the Status column and the Suspicious badge now come from the `common` catalog (new `common.suspicious` key propagated to every locale) — add it to the Gamification sidebar group as `gamification-admin` (`/dashboard/gamification/admin`), and expose the loading and empty states as polite `role="status"` live regions (#12401 — thanks @pacocartones)
- **feat(providers):** skip GitHub combo members missing from the live synced catalog, and drop Copilot models that are policy-disabled or hidden from the model picker ([#12473](https://github.com/diegosouzapw/OmniRoute/pull/12473)) — thanks @RaviTharuma
- **feat(i18n):** locale-expansion tooling — `npm run i18n:add-locale` adds a language to config, dashboard, docs mirrors, CLI, README/indexes and site in one command; browser, CLI and cookie detection resolve `uk`, `fil`/`tl`, `zh-Hant` (and the retired legacy `in` → `id`) via config aliases; `config/i18n.json` now ships in the npm package so the published CLI can read it; new real-translation ratio gate (`npm run i18n:check-ratio`, advisory) with a per-locale ratchet baseline; `run-translation --adopt` restores `.i18n-state.json`; `sync-language-bars` generates 🌐 bars from config; `validate_translation.py` loads its allowlist again. Retires the duplicate `in` locale (Indonesian mislabelled as Hindi) — 42 honest locales; saved `NEXT_LOCALE=in` / `OMNIROUTE_LANG=in` keep working. (#12496)
- **feat(api):** Emit gateway-measured `tokens_per_second` (TTFT excluded) on streaming usage and `X-OmniRoute-Tokens-Per-Second` when first-token latency is known ([#12616](https://github.com/diegosouzapw/OmniRoute/issues/12616)) ([#12631](https://github.com/diegosouzapw/OmniRoute/pull/12631)) — thanks @RaviTharuma
- **feat(opencode-plugin): map gateway cost/usage/tok/s onto OpenCode inference payloads** — the official plugin copies `X-OmniRoute-Response-Cost`, token counts, `X-OmniRoute-Tokens-Per-Second` / `usage.tokens_per_second`, TTFT, and the winning `X-OmniRoute-Model` onto the JSON/SSE body OpenCode already consumes. Missing tok/s is left unset (never `tokens / latency`). (#12636) — thanks @RaviTharuma
- **feat(combo):** add combo strategy `quota-weighted`: skip exhausted accounts, then weighted-draw by leftover / in-flight load; existing conversations stay pinned until the account is empty ([#12789](https://github.com/diegosouzapw/OmniRoute/pull/12789)) — thanks @HouMinXi
- **feat(models):** Account live listings become the chat catalog source for Claude, Codex, Copilot, and AGY; public metadata only fills prices on IDs those accounts already list. ([#12866](https://github.com/diegosouzapw/OmniRoute/pull/12866)) — thanks @HouMinXi
- **fix(models):** Union `agy` and `antigravity` live catalogs so `agy/gemini-3.8-flash-high` is not rejected after the prefix folds to `antigravity`. ([#12866](https://github.com/diegosouzapw/OmniRoute/pull/12866)) — thanks @HouMinXi
- **feat(opencode):** Add `@omniroute/opencode-plugin-v2`, an opencode v2 plugin that gives a v2 install a route to an OmniRoute gateway: it publishes models, combos and auto-combos into the host catalog, refreshes them lazily behind a 300s TTL, and keeps serving the last known catalog from an on-disk snapshot when the gateway is unreachable. The v1 plugin (`@omniroute/opencode-plugin`) is untouched and keeps working as before. The plugin adapts to the host instead of assuming one shape: it reads the shape the host seeds into the catalog draft and publishes the `api` block, the pre-`api` top-level fields, or both. The gateway key comes from the host credential store when one is connected, so no secret needs to sit in a config file; a source the gateway refuses is named in a warning instead of silently degrading the catalog to raw model ids; and tool schemas bound for a Gemini model are stripped of the JSON-Schema keywords Gemini rejects, so tool calling survives that route ([#12870](https://github.com/diegosouzapw/OmniRoute/pull/12870)) — thanks @maxmad64bis
- feat(services): show sanitized CLIProxyAPI account health from its authenticated management API without exposing credentials, file paths, or raw account metadata (#6342) ([#11434](https://github.com/diegosouzapw/OmniRoute/pull/11434)) — thanks @hartmark
- **feat(search):** Add AnySearch free web search + URL extract (webFetch) with typed results, credential validation, REST routing, and MCP selection - fallback-only ([#11690](https://github.com/diegosouzapw/OmniRoute/pull/11690)) — thanks @Xxx91n
- **feat(dashboard):** display clamped `[0, 100]%` cached input token ratio in request logs table ([#11970](https://github.com/diegosouzapw/OmniRoute/pull/11970)) ([#11970](https://github.com/diegosouzapw/OmniRoute/pull/11970)) — thanks @b3nw
- **feat(catalog):** add `OMNIROUTE_DISABLE_THINKING_LEVEL_VARIANTS` feature flag to optionally filter out thinking level variants from model catalog ([#11971](https://github.com/diegosouzapw/OmniRoute/pull/11971)) ([#11971](https://github.com/diegosouzapw/OmniRoute/pull/11971)) — thanks @b3nw
- **feat(dashboard):** continuously export call logs to external analytics stores. A pluggable destination registry ships the full Logs-tab record set on an hourly `JobRegistry` cron, with a persisted per-destination cursor, batched inserts, a config UI rendered from each destination's own field descriptors, and a REST layer (`/api/log-export/*`) for CRUD, a connection test, and an on-demand run. A destination can opt into `includeBodies` to also ship the request and response payloads shown in the Logs detail pane, including the client and provider views of each call; this is off by default, and payloads inherit the dashboard's PII sanitisation, secret redaction and `noLog` handling. Google BigQuery is the first destination, using a service-account key stored encrypted at rest and streaming inserts keyed by call-log id, into a table that is day-partitioned on `timestamp` and clustered on `api_key_name`, `provider`, `model` and `status`. ([#11945](https://github.com/diegosouzapw/OmniRoute/pull/11945)) — thanks @dpozimski
- **feat(providers):** add MaxAI as a signed, OpenAI-compatible provider serving its 13 paid chat models (GPT-5.6 / Luna / Thinking, Claude 5 Sonnet, Claude Haiku 4.5, Gemini 3.1 Pro / Flash-Lite, Grok 4.1-fast / 4.5, DeepSeek V3.2 / R1, Llama 3.3 70B) through OmniRoute's `/v1` endpoint, with per-request HMAC-SHA1→SM3→AES request signing, live model + context-window discovery from `/models/get_config`, and prompted tool-calling translated to OpenAI `tool_calls` ([#11461](https://github.com/diegosouzapw/OmniRoute/pull/11461)) — thanks @arminanton
- **feat(providers):** MaxAI vision input — image_url content parts are forwarded inline in `message_content` to the 6 vision-capable models (GPT-5.6 / Luna / Thinking, Claude Haiku 4.5, Gemini 3.1 Pro / Flash-Lite) ([#11461](https://github.com/diegosouzapw/OmniRoute/pull/11461)) — thanks @arminanton
- **feat(providers):** MaxAI document RAG — inline base64 file/document attachments are uploaded to MaxAI (content-addressed `doc_id`) and attached to the chat via `doc_list` ([#11461](https://github.com/diegosouzapw/OmniRoute/pull/11461)) — thanks @arminanton
- **feat(providers):** browserless MaxAI onboarding — email device-pair login (`/api/providers/[id]/login`) and signed access-token refresh, so a connection can be created and kept fresh without a real browser or Google OAuth ([#11461](https://github.com/diegosouzapw/OmniRoute/pull/11461)) — thanks @arminanton
- **feat(providers):** per-provider TLS impersonation profile (MaxAI presents a Windows Firefox-150 client fingerprint) so its bot-sensitive endpoints accept OmniRoute traffic ([#11461](https://github.com/diegosouzapw/OmniRoute/pull/11461)) — thanks @arminanton
- **feat(providers):** add **Nimble** as a web-search and web-fetch provider (`nimble-search`) — `/v1/search` routes to Nimble's search API at `lite` depth (locale, freshness and include/exclude domain filters mapped onto the shared request contract), and `/v1/web/fetch` routes to Nimble Extract, which covers all four fetch formats (`markdown`, `html`, `links`, `screenshot`) from a single call. One API key serves both surfaces. ([#11620](https://github.com/diegosouzapw/OmniRoute/pull/11620)) — thanks @wildcard
- The npm publish is automatic again, through npm Trusted Publishing (OIDC): the hosted `stage-npm` job publishes with a short-lived credential minted from GitHub's id-token — no `NPM_TOKEN`, no 2FA prompt, provenance attached. `publish_mode=staged` (owner approves with 2FA) and `direct` (token) remain available on `workflow_dispatch`. ([#11931](https://github.com/diegosouzapw/OmniRoute/pull/11931))
- **feat(providers):** Add **Opper** as an API-key gateway provider — EU-hosted AI gateway with 700+ models from 30+ providers behind one OpenAI-compatible API and one key (`OPPER_API_KEY`); model ids use `provider/model` format (e.g. `anthropic/claude-sonnet-4-6`, `openai/gpt-5`); live model catalog at `https://api.opper.ai/v3/compat/models`; entry mirrors `requesty` (same shape, `passthroughModels: true`, no static seed) ([#11629](https://github.com/diegosouzapw/OmniRoute/pull/11629))
- **feat(dashboard):** the `/dashboard/orchestration` snapshot hook now subscribes to the `agents` WebSocket channel (`agent.task.updated`) instead of `requests` as its refetch trigger, and relaxes its background poll from 5s to 30s while that WS connection is up — falling back to the tighter 5s cadence, reprogrammed live on any connect/disconnect transition, whenever the socket is down. ([#12409](https://github.com/diegosouzapw/OmniRoute/pull/12409))
- **feat(dashboard):** Orchestration canvas quick wins — search box plus state/source/provider filter chips with a one-click clear, and per-source collapse/expand, all reflected in the URL so a filtered/collapsed view is shareable and survives a refresh; the detail drawer gained a "copy trace JSON" action and hardened error/empty-state and accessibility handling; the Agents-tab edges now animate traveling particles along active (running) connections; and the canvas node/edge status colors moved off fixed hex values onto theme-aware `--orch-status-*` CSS custom properties, so they adapt correctly to light/dark mode. ([#12393](https://github.com/diegosouzapw/OmniRoute/pull/12393))
- **chore(dashboard):** Orchestration UI hardening pass and the missing component/model test coverage it called for — `OrchestratorNode`/`ActivityNode`/`OverflowNode` rendering, the `?node=`/overflow-click page routing, the Agents-tab orchestrator-click no-op and `showCompleted` toggle, and the overview kanban's done-column sort order (#12270, #12271). ([#12393](https://github.com/diegosouzapw/OmniRoute/pull/12393))
- New `/dashboard/orchestration` page: live unified view of everything running — Cloud Agent, A2A and Conductor as a real-time graph (Agents tab), the combo cascade (Routing tab, reusing the Combo Live Studio) and a state kanban (Overview tab), with a detail drawer (trace, cost, approve/cancel). Read-only over existing APIs — no new backend. Canvas concept credit: PR #11815 design ([#12261](https://github.com/diegosouzapw/OmniRoute/pull/12261))
- **feat(dashboard):** new "History" tab on `/dashboard/orchestration` — an Airflow-style grid of finished runs over a 24h/7d/30d preset window, one row per (source, identity), clicking a cell opens the existing detail drawer. It is backed by real persistence: A2A task lifecycle transitions are now written to the `a2a_tasks` table (purged after 30 days, configurable via `OMNIROUTE_A2A_HISTORY_RETENTION_DAYS`) and served by the new `GET /api/a2a/tasks/history` listing endpoint, with the task-detail route falling back to persisted history once a run leaves the in-memory snapshot. Conductor runs stay remote and are not persisted locally — the tab says so instead of silently omitting them. ([#12479](https://github.com/diegosouzapw/OmniRoute/pull/12479))
- **feat(dashboard):** the orchestration detail drawer gained a "Repeat" action for Cloud Agent, A2A and Conductor tasks — a two-click confirm (click once to arm, click again within the confirm window to fire) re-submits the original prompt/input as a new run. The button is disabled with an explanatory tooltip whenever the original input can't be recovered from the loaded task detail (e.g. it never carried a prompt, or the detail failed to load). Two limitations of the A2A variant, by design: it targets the `/a2a` JSON-RPC endpoint, which authenticates with an API key only (`REQUIRE_API_KEY=true` or a configured `OMNIROUTE_API_KEY` makes a dashboard-session repeat answer `HTTP 400` — surfaced verbatim in the drawer's error line, never as a success), and the `message/send` call is SYNCHRONOUS: the POST blocks for the whole skill run, so the success confirmation only appears once the repeated task finishes. A dashboard-authenticated A2A creation path is deliberately left to a follow-up — widening the endpoint's auth posture is an operator decision, not a side effect of this feature. ([#12508](https://github.com/diegosouzapw/OmniRoute/pull/12508))
- **feat(a2a):** A2A task execution now records which memories were consulted for the task's last user message as `metadata.memoryHits` (id/key/type/content-snippet) plus a `memory_hits` history event, purely for observability — the retrieved memory is never injected into a skill's prompt or behavior. Gated by the `OMNIROUTE_A2A_MEMORY_HITS` kill-switch (default enabled; set to `0` to skip the recall lookup entirely). The drawer's new "Memory used" section lists these hits for a2a tasks and is omitted whenever there are none. Known limitation: recall only resolves under the keyless posture — a keyed caller's task owner is a SHA-256 prefix of the API key, while memory rows are keyed by the database api-key id, and no hash→id lookup exists today, so the hit list stays empty for keyed callers. The recorded hits are also kept out of the task's own `input` (and therefore out of the persisted input and of the "Repeat" request body), so repeating a task never re-sends the previous run's memory snippets. ([#12508](https://github.com/diegosouzapw/OmniRoute/pull/12508))
- **feat(providers):** add a Perplexity Agent API provider (`perplexity-agent` / `pplx-agent`) for Perplexity `/v1/responses`, including the documented Anthropic, OpenAI, Google, xAI, DeepSeek, Z.AI, Moonshot/Kimi, NVIDIA, and Perplexity model IDs plus Anthropic-model `max_output_tokens` compatibility. ([#12103](https://github.com/diegosouzapw/OmniRoute/pull/12103)) — thanks @AIB1TAL0S
- **feat(providers):** add RPD (Requests Per Day) limit to provider rate limit overrides across UI, schemas, DB, and i18n ([#12147](https://github.com/diegosouzapw/OmniRoute/pull/12147)) ([#12147](https://github.com/diegosouzapw/OmniRoute/pull/12147)) — thanks @b3nw
- **feat(providers): add UC Direct (uncensored.com Developer API), the metered OpenAI-compatible surface.** A standard OpenAI-compatible passthrough (default executor) for uncensored.com's official REST API at `https://api.uncensored.com/api/v1`: `X-api-key` auth (never-expiring `uai_sk_live_` key), `POST /chat/completions` with streaming SSE and native tool-calling, and the full live metered catalog (82 models across 15 providers, discovered from the public `GET /v1/models`). Registered as provider `uc-direct` (alias `ucd`). Complements the un-metered `uc` persona provider — same models, metered credits and a plain API key instead of a subscription session. ([#11513](https://github.com/diegosouzapw/OmniRoute/pull/11513)) — thanks @arminanton
- **feat(providers): add UC (uncensored.com), the un-metered subscription "persona" chat as an OpenAI-compatible provider.** A WebSocket web-app port: a durable Clerk credential mints a short-lived session token per connect (browserless — no API key), driving UC's persona socket. Ships the browserless email-code login (request → verify → harvest), the 19 verified persona models (Claude Opus, Gemini, Grok, GLM, Kimi, DeepSeek, MiniMax, incl. the uncensored variants), prompted `<tool>` tool-calling with a per-model code-style dialect + auto-cure retry for guardrailed models, live `<think>`/reasoning split, streaming + non-streaming OpenAI responses, and full quota/auth error surfacing (paywall / message-limit / rate-limit → 429, invalid session → 401 re-login). Full multimodal parity via the persona blob-upload layer: **vision** (image input, 15 vision-capable models), **document RAG** (PDF/doc upload, server-side extraction), **image generation** (22 models), **video generation** (14 models, async signed-url → poll), and **TTS** (streaming MP3). Registered as provider `uc` (alias `ucn`). The metered OpenAI-compatible Developer API is a separate `uc-direct` provider. ([#11513](https://github.com/diegosouzapw/OmniRoute/pull/11513)) — thanks @arminanton
- **feat(providers):** derive + surface expiry for JWT-bearing web cookies (#11497) ([#11505](https://github.com/diegosouzapw/OmniRoute/pull/11505)) — thanks @oyi77
- **feat(tunnels):** support named cloudflared tunnels via CLOUDFLARED_CONFIG ([#11561](https://github.com/diegosouzapw/OmniRoute/pull/11561)) — thanks @ggiak
- **feat(compression):** make proactive context-compression threshold a live setting ([#11564](https://github.com/diegosouzapw/OmniRoute/pull/11564)) — thanks @ragnar-claude
- **feat(config):** add support for runtime system prompt configuration and hot-reloading ([#11841](https://github.com/diegosouzapw/OmniRoute/pull/11841)) — thanks @raheemuddin786
- **feat(resilience):** operator-configurable global credential health check interval ([#12043](https://github.com/diegosouzapw/OmniRoute/pull/12043)) — thanks @adivekar-utexas
- **feat(quota):** use official OpenCode Go usage API ([#12124](https://github.com/diegosouzapw/OmniRoute/pull/12124)) — thanks @ddarkr
- **feat(resilience):** default the credential health check sweep to 60 minutes ([#12138](https://github.com/diegosouzapw/OmniRoute/pull/12138)) — thanks @adivekar-utexas
- **feat(quality):** new-code mode for the complexity and dead-code ratchets (Clean as You Code) ([#12142](https://github.com/diegosouzapw/OmniRoute/pull/12142))
- **feat(usage):** add Kilo Code balance and Kilo Pass quotas ([#12178](https://github.com/diegosouzapw/OmniRoute/pull/12178)) — thanks @killer30001000
- **feat(providers):** refresh vendored ChatGPT Web connector to v4.0.7 ([#12181](https://github.com/diegosouzapw/OmniRoute/pull/12181)) — thanks @backryun
- **feat(providers):** manual "Clear cooldown" action in the cooling panel ([#12224](https://github.com/diegosouzapw/OmniRoute/pull/12224)) — thanks @patrykkopycinski
- **feat(providers):** restore ChatGPT Web via clean-room browser transport ([#12239](https://github.com/diegosouzapw/OmniRoute/pull/12239)) — thanks @backryun
- **feat(sse):** wire the PROVIDER_PROFILES window gate into the global provider cooldown ([#12247](https://github.com/diegosouzapw/OmniRoute/pull/12247))
- **feat(providers):** modernize CLOVA Studio chat and embeddings ([#12277](https://github.com/diegosouzapw/OmniRoute/pull/12277)) — thanks @backryun
- **feat(browser):** adopt Obscura as primary headless browser engine with Chromium fallback ([#12286](https://github.com/diegosouzapw/OmniRoute/pull/12286)) — thanks @opensource-elearning
- **feat(sse):** full language parity for output styles (es/de/fr/it/ru/zh + autoDetect) ([#12289](https://github.com/diegosouzapw/OmniRoute/pull/12289))
- **feat(providers):** refresh Z.ai Web models and browser transport ([#12524](https://github.com/diegosouzapw/OmniRoute/pull/12524)) — thanks @backryun
- **feat(video):** redact raw client-snapshot transcript fields in the detailed log (#12150 P2) ([#12528](https://github.com/diegosouzapw/OmniRoute/pull/12528))
- **feat(quota):** Moonshot Open Platform balance and TPD lock for custom nodes ([#12590](https://github.com/diegosouzapw/OmniRoute/pull/12590)) — thanks @HouMinXi
- **feat(video):** redact transcript in the in-memory pending-request snapshot (#12430 item 6) ([#12596](https://github.com/diegosouzapw/OmniRoute/pull/12596))
- **feat(dashboard):** link a log entry's Conversation Context to its owning conversation ([#12646](https://github.com/diegosouzapw/OmniRoute/pull/12646)) — thanks @hartmark
- **feat(db):** fail-closed previous_response_id continuation for redacted video turns (#12150 P2b) ([#12707](https://github.com/diegosouzapw/OmniRoute/pull/12707))
### 🐛 Bug Fixes
- **security(streaming):** sanitize generic mid-stream error messages before emitting OpenAI,
Responses, or Claude SSE failure frames and before diagnostic logging, while preserving raw
failures for internal classification and keeping client disconnects out of provider failure state.
failures for internal classification and keeping client disconnects out of provider failure state. ([#12457](https://github.com/diegosouzapw/OmniRoute/pull/12457))
- **fix(claude):**`blockExtraUsage: false` no longer lets 5h quota preflight skip the account; extra usage is billed after the session bar is gone, so the request must reach Anthropic ([#12803](https://github.com/diegosouzapw/OmniRoute/pull/12803)) — thanks @HouMinXi
- Sanitize HuggingChat conversation-creation and message-send transport failures before they reach client error bodies or provider logs. ([#12467](https://github.com/diegosouzapw/OmniRoute/pull/12467))
- **fix(dashboard):** Keep local and theme-aware provider SVG icons at a definite layout size so Chromium does not collapse them to 0×0 after the v3.8.50 image-rendering change ([#12054](https://github.com/diegosouzapw/OmniRoute/pull/12054)) — thanks @ponkcore
- **fix(security):** Sanitize provider and runtime failures before public API, SSE and MCP responses and before persistent request, proxy and usage logs, preventing credentials, stack traces and host filesystem paths from crossing those boundaries while preserving stable error codes and useful diagnostics. ([#12506](https://github.com/diegosouzapw/OmniRoute/pull/12506))
- **fix(cli):**`omniroute tunnel create` no longer crashes with `Cannot read properties of undefined (reading optsWithGlobals)` — removed the duplicate positional argument that caused Commander.js to misalign the action callback parameters ([#12295](https://github.com/diegosouzapw/OmniRoute/issues/12295)) ([#12368](https://github.com/diegosouzapw/OmniRoute/pull/12368)) — thanks @gonisulaimann
- Stop advertising Gemini Live-only models as supported audio endpoints until OmniRoute proxies the bidirectional Live protocol. ([#11710](https://github.com/diegosouzapw/OmniRoute/pull/11710)) — thanks @RaviTharuma
- **fix(kie):** reroute `flux/kontext` off the KIE Market `createTask` flow — it is catalogued with `isMarket: true` but has no Market catalog page, so KIE rejected it with "model name not supported"; it now hits the dedicated `POST /api/v1/flux/kontext/generate` / `GET /api/v1/flux/kontext/record-info` endpoints instead (#11296). ([#11985](https://github.com/diegosouzapw/OmniRoute/pull/11985)) — thanks @hartmark
- **fix(kie):** correct 12 more KIE Market catalog ids that were sent to `createTask` unchanged but diverge from KIE's documented upstream `model` values — GPT Image 2 T2I/I2I (drops the `gpt/` prefix), GPT Image 1.5 T2I/I2I (`gpt-image/` namespace), Seedream 5.0 Lite T2I/I2I (drops the `.0`), all 4 Flux 2 variants (`flux-2/` namespace, generic variant renamed `flex`), and Wan 2.7 Image / Image Pro (dash instead of dot) — each verified individually against the literal example request published on docs.kie.ai. `#11326`'s "everything else already matches" claim was wrong a second time (#11296); `z-image/4.0-*`/`z-image/4.5-*` and `flux/kontext` remain open, documented as unresolved in `KIE_MARKET_UPSTREAM_MODEL_IDS`'s comment pending further verification. ([#11667](https://github.com/diegosouzapw/OmniRoute/pull/11667))
- **fix(dashboard):**`useApiKeySave.handleSaveApiKey` no longer forces a full upstream `/models` catalog sync on every non-curated provider connection save — callers can now pass `skipModelSync: true` to opt out, so a workflow that only wants to add one manual model no longer floods the provider's available-models list with hundreds/thousands of synced entries. The flag is a client-side intent signal only and is stripped before the connection payload is POSTed to `/api/providers`; default behavior (full sync on save) is unchanged when the flag is omitted (#11324) ([#11664](https://github.com/diegosouzapw/OmniRoute/pull/11664))
- **Provider connections:** keep `tokenExpiresAt` when a connection is created. The create-path allowlist omitted it, so every insert stored NULL and the dashboard token badge could read a fresh connection as expired until its first background refresh ([#11368](https://github.com/diegosouzapw/OmniRoute/pull/11368)). — thanks @ntdatt812
- **fix(combos):** the combo builder's precision-select, global-model-search, and manual-entry flows now serialize a model step's `model` string using the provider's already-computed routing-alias prefix (e.g. `oc/`) instead of rebuilding it from the raw canonical `providerId`, fixing the no-auth "OpenCode Free" provider (`opencode`) being routed to the unrelated paid "OpenCode Zen" provider (`opencode-zen`) because `opencode` doubles as a manual routing-prefix override ([#11433](https://github.com/diegosouzapw/OmniRoute/issues/11433)). ([#11670](https://github.com/diegosouzapw/OmniRoute/pull/11670))
- **fix(radar):** the catalog feed cache now keeps `generatedAt`, the date the feed's data was built, next to `fetchedAt`, the date this install downloaded it (#11435). The feed schema requires that date and the sync path validates it, but the cache dropped it — so a feed fetched minutes ago and one carrying weeks-old figures looked identical to everything downstream, including the dashboard's "Last fetched" line. `getRadarCatalog().meta` and `GET /api/radar/status` now report both dates, the latter as its own field rather than folded into `version` — and omitted entirely for the offers and intel caches, which keep no build date, where a `null` would read as "unknown" rather than "never stored". The dashboard still shows only the fetch time; surfacing the build date there needs a new translated label and is left to a follow-up. Rows cached before migration 163 read back as `null`: unknown stays unknown instead of borrowing the fetch time. The referrals cache has persisted the same date since migration 142. — thanks @maxmad64bis
- **fix(cli):** postinstall no longer fills `JWT_SECRET` and `API_KEY_SECRET` in the installed package's `.env` (#11436). `.env.example` ships both blank on purpose: the server restores them from its durable store, or generates and persists them there, in `ensureSecrets()`. Pre-filling them defeated that — the file lives inside the package directory, so `npm i -g` replaced it and postinstall wrote _different_ values, while `ensureSecrets()` (which only acts on an empty variable) never got to restore the real ones. Both secrets rotated silently on every update, invalidating dashboard sessions and API-key CRCs. `STORAGE_ENCRYPTION_KEY` left the same list for the same reason in #1622; its comment pointed at a function that no longer exists and now names the real provisioning path. — thanks @maxmad64bis
- **fix(cli):** the CLI now says when a loaded `.env` lives inside the installed package directory (#11437). It already announces every env file it reads, without distinguishing the ones that survive an update from the one that does not: `npm i -g` replaces the package directory wholesale, so values set there are gone at the next update, silently. The warning names the durable path to move them to, and fires only when that file actually supplied a value — a file entirely shadowed by a durable one supplied nothing. A development checkout stays silent: there the same path is stable and documented in `SETUP_GUIDE.md`. — thanks @maxmad64bis
- **fix(free-models):** the shared `isFreeModel()` predicate no longer reports catalog entries marked `freeType: "discontinued"` as free, so `hidePaidModels` can't route to Pollinations' seven premium models that now require a paid key ([#11441](https://github.com/diegosouzapw/OmniRoute/pull/11441)) — thanks @maxmad64bis
- fix(ui): let AnySearch use the normal provider-icon fallback when LobeHub has no matching icon (#11449)
- Fixed the v3.8.50 Costs and Analytics dashboards so flat-rate Claude Code usage can be shown as an explicitly requested token-price estimate without changing default billed-cost semantics. ([#11460](https://github.com/diegosouzapw/OmniRoute/pull/11460)) — thanks @xiaoyaner0201
- Fixed archived usage retention so each request is priced individually instead of pricing a day's summed tokens once, which understated archived cost whenever a day mixed cache-heavy and ordinary requests. ([#11460](https://github.com/diegosouzapw/OmniRoute/pull/11460)) — thanks @xiaoyaner0201
- Fixed the Costs dashboard so it discloses when displayed figures include flat-rate token-price estimates instead of labelling them as billed spend, using the flag the analytics API already returns; the month-end projection and the CSV/JSON exports carry the same marker, and billed-cost mode is unchanged. ([#11460](https://github.com/diegosouzapw/OmniRoute/pull/11460)) — thanks @xiaoyaner0201
- **fix(combo):** attach the same combo-diagnostics trace (`poolSize`/`attemptOrder`/`excluded`/`terminalReason`, plus `x-omniroute-combo-*` headers) to the round-robin strategy's and the nested pipeline/fusion runtime-unit loop's "Maximum combo retry limit reached" 503 that the priority-strategy path already attaches for the identical terminal condition — previously those two paths returned a bare, contextless 503 ([#11462](https://github.com/diegosouzapw/OmniRoute/issues/11462)). ([#11665](https://github.com/diegosouzapw/OmniRoute/pull/11665))
- **fix(bun):** use native `bun:sqlite` in `bootstrap-env` and `sync-env` to avoid loading `better-sqlite3` N-API addon during Bun startup ([#11468](https://github.com/diegosouzapw/OmniRoute/pull/11468)) — thanks @TheDemonTuan
- **fix(docker-bun):** make `Dockerfile.bun` install reliable with pre-install script helpers and native `bun:sqlite` smoke check ([#11470](https://github.com/diegosouzapw/OmniRoute/pull/11470)) — thanks @TheDemonTuan
- **fix(docker-bun):** remove every vendored `better-sqlite3` native addon from the Bun runtime image so startup cannot abort before the `bun:sqlite` fallback ([#11482](https://github.com/diegosouzapw/OmniRoute/pull/11482)) — thanks @TheDemonTuan
- **fix(autoCombo):** effort/alias model variants (`gpt-5.6-sol-xhigh`, `gpt-5.6`, cursor's `claude-4.6-opus-high`) inherit their base model's task fitness instead of falling to the wildcard 0.5 ([#11492](https://github.com/diegosouzapw/OmniRoute/pull/11492)) — thanks @MumuTW
- fix(db): rate-limit repeated Arena ELO leaderboard fetch-failure warnings instead of logging one per sync attempt (#11500) ([#11989](https://github.com/diegosouzapw/OmniRoute/pull/11989)) — thanks @hartmark
- **fix(db):** dedupe the raw `[Encryption] Decryption failed...` log line emitted by the lazy-decrypt views (`createLazyRowProxy`/`createLazyConnectionView`), which power `getProviderConnections()` and were re-triggering that line on every CredentialHealth/model-sync cycle for the same corrupt or stale-key credential — a fresh Proxy over a fresh row on every cycle meant the per-proxy memoization never suppressed it, unlike the dedup `decryptConnectionFields()` already had since [#9927](https://github.com/diegosouzapw/OmniRoute/issues/9927). Now shares that dedupe tracking so the line logs at most once per credential ([#11500](https://github.com/diegosouzapw/OmniRoute/issues/11500)). ([#11678](https://github.com/diegosouzapw/OmniRoute/pull/11678))
- **fix(intelligence):** Arena ELO sync stores a synthesized base-model row for every effort/harness variant (`claude-opus-5-max` → `claude-opus-5`, `gpt-5.6-sol-xhigh (codex-harness)` → `gpt-5.6-sol`), so bare model requests reach the synced intelligence layer instead of the static fallback table; the hand-maintained `MODEL_ALIAS_MAP` — which collapsed generations (`gpt-5.5` → `gpt-5`) — is gone ([#11506](https://github.com/diegosouzapw/OmniRoute/pull/11506)) — thanks @MumuTW
- **fix(autoCombo,sse):** catalog hygiene — the static task-fitness table no longer ranks retired models above live ones (dead rows dropped, patterns matched on segment boundaries), the 7 deprecation aliases that forwarded to retired or non-existent models now point at the vendors' published replacements, an alias is no longer rewritten when the serving provider offers the id as-is, and a new `check:model-lifecycle` gate diffs both tables against a vendor lifecycle snapshot ([#11507](https://github.com/diegosouzapw/OmniRoute/pull/11507)) — thanks @MumuTW
- **fix(sse):** stop dropping resolved `thoughtSignature` values on parallel (multi tool-call) turns sent to Gemini 3.x — the claude→gemini and openai→gemini translators previously kept the signature only on the *first* function call of a message, causing Gemini to reject subsequent calls in the same turn with HTTP 400 "Function call is missing a thought_signature"; each function call now keeps its own resolved signature ([#11510](https://github.com/diegosouzapw/OmniRoute/issues/11510)). ([#11669](https://github.com/diegosouzapw/OmniRoute/pull/11669))
- Treat Docker publishing from a non-default release branch as an expected skip instead of a failed workflow, while preserving the guard that prevents it from overwriting the `next` channel. ([#11527](https://github.com/diegosouzapw/OmniRoute/pull/11527)) — thanks @pacocartones
- fix(search): prefer credentialed providers over duckduckgo-free fallback (#11524) — the fallback-only loop ran before the credentialed-providers loop in `executeWebSearch`, making configured providers unreachable when `duckduckgo-free` was available. ([#11565](https://github.com/diegosouzapw/OmniRoute/pull/11565)) — thanks @vsd2807
- **fix(sse):** cap the upstream headers-wait phase for STREAMING requests to a client-realistic ceiling (110s, under Codex's own ~120s hard client-abort window) instead of the flat 10-minute `FETCH_TIMEOUT_MS` default — that default was 5x longer than the body-phase readiness watchdog's own adaptive bound, so a request whose upstream never returned any response at all (not even headers, e.g. a stalled NVIDIA target behind a tool-heavy Responses→Chat translation) kept the client connection alive on keepalives only, guaranteeing the client's own patience ran out first with an opaque 499 instead of OmniRoute detecting and failing the stall fast. Non-streaming requests are unaffected — they keep the existing flat default (`open-sse/utils/fetchStartTimeoutPolicy.ts`) (#11526) ([#11668](https://github.com/diegosouzapw/OmniRoute/pull/11668))
- **fix(ci):** protocol-clients E2E harness boots the peer-stamped custom server (`run-next.mjs dev`) instead of the bare `next` CLI, so `LOCAL_ONLY` locality resolves from the real TCP peer stamp and `/api/mcp/audit` answers 200 (open bootstrap preserved via an `OMNIROUTE_E2E_BOOTSTRAP_MODE=open` credential clear in `run-next.mjs`, pinned to loopback `HOST`) instead of a deterministic 403 (#11535) ([#11549](https://github.com/diegosouzapw/OmniRoute/pull/11549)) — thanks @jonlwheat2-gif
- **fix(docs):** the Auto-Combo engine is described with the number of factors it actually declares. Four different counts were in circulation — 6, 9, 13 and 14 across `AGENTS.md`, four guides and six code comments — while `DEFAULT_WEIGHTS` declares 15. `check:docs-counts` now reads that number from the source, so adding a factor without updating the prose fails CI ([#11545](https://github.com/diegosouzapw/OmniRoute/pull/11545)) ([#11553](https://github.com/diegosouzapw/OmniRoute/pull/11553)) — thanks @maxmad64bis
- **fix(quota-share):** in-flight leases are per request, so an aborted request's slot ages out instead of being kept alive by later traffic on the same connection ([#11547](https://github.com/diegosouzapw/OmniRoute/pull/11547)) — thanks @abhisheksharma2411
- The free-tier summary route now serves the refreshed Radar catalog when the feed is active — the same numbers the dashboard shows — and states which catalog answered plus its real build date, instead of always reporting release-frozen figures with a stale curation date. The supporter-key live feed stays reserved to authenticated callers of the instance. ([#11550](https://github.com/diegosouzapw/OmniRoute/pull/11550)) — thanks @maxmad64bis
- **sse:** fix LiveWS/embed-WS servers crashing at startup under the Node/tsx runtime — `liveServer.ts`, `embedWsProxy.ts` and `apiBridgeServer.ts` imported `@/shared/utils/httpClientAbortGuard` without the `.mjs` extension, so the client-abort crash guard added by [#11556](https://github.com/diegosouzapw/OmniRoute/pull/11556) was unreachable and every dependent test failed with `ERR_MODULE_NOT_FOUND` ([#11556](https://github.com/diegosouzapw/OmniRoute/pull/11556)). ([#11671](https://github.com/diegosouzapw/OmniRoute/pull/11671)) — thanks @jonlwheat2-gif / @yxyxy
- fix(chat): shed any of the matched provider-node's routing identifiers (public prefix or internal id) before model lookup, so composites like `<connId>/<connId>/<model>` no longer reach upstream verbatim (#11557) — thanks @maxmad64bis
- **fix(cache):** a semantic-cache entry now expires on its TTL instead of surviving until the next UTC midnight, and `dbEntries` stops counting expired rows ([#11573](https://github.com/diegosouzapw/OmniRoute/pull/11573)) — thanks @ntdatt812
- **fix(api):**`/v1/models` schedules its stale-while-revalidate rebuild through Next's `after()` again, so a stale catalog reaches the client before the rebuild blocks the event loop ([#11574](https://github.com/diegosouzapw/OmniRoute/pull/11574)) — thanks @ntdatt812
- **fix(check):** the `known-symbols` executor conformance gate awaits the now-async `getExecutor()`, so it stops reporting all 142 registered aliases as dead symbols and can detect a lazy import that fails ([#11582](https://github.com/diegosouzapw/OmniRoute/pull/11582)) — thanks @ntdatt812
- **fix(pack):** register `bin/cli/utils/volatileEnvPath.mjs` in `PACK_ARTIFACT_REQUIRED_PATHS`, so the prune can no longer silently drop a module the published CLI imports on every boot ([#11588](https://github.com/diegosouzapw/OmniRoute/pull/11588)) — thanks @ntdatt812
- **i18n(vi):** translate the five reliability-column strings on the free-provider rankings page, which rendered as `__MISSING__:` markers in the Vietnamese UI ([#11589](https://github.com/diegosouzapw/OmniRoute/pull/11589)) — thanks @ntdatt812
- **resilience:** restore the expired-connection retry-budget probe in the token-health sweep — the `!isGitHubAccessTokenOnlyConnection` carve-out reintroduced by #11608 contradicted the boundary pinned by #11592, so a GitHub connection parked at `expired` with retry budget remaining was never probed and could never self-heal ([#11592](https://github.com/diegosouzapw/OmniRoute/pull/11592)). ([#11672](https://github.com/diegosouzapw/OmniRoute/pull/11672)) — thanks @jonlwheat2-gif / @ntdatt812
- **fix(dashboard):** Provider Stats now displays combo success rates on their native 0–100 percentage scale instead of multiplying them twice ([#11595](https://github.com/diegosouzapw/OmniRoute/pull/11595)) — thanks @pacocartones
- **fix(providers):** route DuckDuckGo Web Chat through the verified `duck.ai` endpoint, refresh its free model catalog, and avoid forwarding unsolved anti-abuse challenges ([#11597](https://github.com/diegosouzapw/OmniRoute/pull/11597)) — thanks @solstxce
- **fix(ui):** Console log Refresh and Copy controls now expose localized accessible names, keep copy actions visible on keyboard focus, and announce copy completion safely ([#11599](https://github.com/diegosouzapw/OmniRoute/pull/11599)) — thanks @pacocartones
- Dropped the stale-`.eslintcache``restore-keys` fallback from both "Restore ESLint file cache" steps in `ci.yml`, so the blocking `Lint` job can no longer be served per-file verdicts computed under a different lint config, suppressions file or lockfile. `quality.yml` had already dropped it in #11963; `ci.yml` — the workflow that actually gates PRs — had not (#11600). ([#11996](https://github.com/diegosouzapw/OmniRoute/pull/11996))
- fix(ci): pass `--pass-on-unpruned-suppressions` in `run-eslint-json.mjs` so the CI Lint job no longer fails when a suppression is merely orphaned by a genuine fix, mirroring the identical fix already in `validate-release-green.mjs` (#11600) ([#11983](https://github.com/diegosouzapw/OmniRoute/pull/11983)) — thanks @hartmark
- fix(handoff): enforce provider allowlist for universal handoff (#11602) — universal handoff now skips summarization when the selected summary model's provider is not included in the configured provider allowlist. ([#11619](https://github.com/diegosouzapw/OmniRoute/pull/11619)) — thanks @vsd2807
- **fix(dashboard):** Show a stable error state when Search Analytics returns an HTTP error or malformed data ([#11603](https://github.com/diegosouzapw/OmniRoute/pull/11603)) — thanks @pacocartones
- **test(gamification):** pin the aggregate profile level to the XP-derived semantics of #11604 — `getAggregateXp()` now derives `currentLevel` from the summed XP (`calculateLevel(sum)`), not `MAX(stored current_level)`, and the #3484 fixture levels are aligned with the XP curve ([#11604](https://github.com/diegosouzapw/OmniRoute/pull/11604)). ([#11676](https://github.com/diegosouzapw/OmniRoute/pull/11676)) — thanks @jonlwheat2-gif / @pacocartones
- **fix(dashboard):** Keep the Profile level and progress aligned with aggregate XP, including bounded handling for invalid totals ([#11604](https://github.com/diegosouzapw/OmniRoute/pull/11604)) — thanks @pacocartones
- **fix(dashboard):** Prevent locked hidden badges from revealing their icon or opening private badge details before they are earned ([#11605](https://github.com/diegosouzapw/OmniRoute/pull/11605)) — thanks @pacocartones
- **fix(dashboard):** Restore keyboard focus after shared modals close and cancel delayed autofocus during cleanup ([#11607](https://github.com/diegosouzapw/OmniRoute/pull/11607)) — thanks @pacocartones
- **fix(dashboard):** Enable Enter and Space activation for clickable data-table rows without hijacking nested controls ([#11610](https://github.com/diegosouzapw/OmniRoute/pull/11610)) — thanks @pacocartones
- **fix(autoCombo,sse):** vendor-retired catalog ids are dropped from the auto-combo candidate pool and no longer win on leftover `arena_elo` / `user_override` rows; `getModelLifecycleDecision` consults `model-lifecycle.json` (prefix-stripped) so aggregator traffic is not `untracked` for ids the snapshot already knows ([#11625](https://github.com/diegosouzapw/OmniRoute/issues/11625)) ([#11626](https://github.com/diegosouzapw/OmniRoute/pull/11626)) — thanks @MumuTW
- **test(chatcore):** move Codex/Claude combo fixtures off models the lifecycle guard now rejects — `gpt-5.1-codex`/`gpt-5-codex` are vendor-retired (snapshot, #11626) and `claude-3-5-sonnet-20241022` is shut down, so native-passthrough and combo-fallback tests switched to `gpt-5.6-sol` and `claude-sonnet-4.6` ([#11626](https://github.com/diegosouzapw/OmniRoute/pull/11626)). ([#11675](https://github.com/diegosouzapw/OmniRoute/pull/11675)) — thanks @jonlwheat2-gif / @MumuTW
- fix(opencode-plugin): stop a free-tier budget that rounds up across a magnitude from rendering as `1000K`/`1000M` in the model picker — `fmtTokens` chose its unit from the raw token count and then rounded with `toFixed(1)`, so 999,950–999,999 printed as `1000K` rather than `1M` and just under a billion printed as `1000M` rather than `1B` ([#11684](https://github.com/diegosouzapw/OmniRoute/pull/11684)) — thanks @abhisheksharma2411
- Cap prose-derived Antigravity quota resets at the configured model cooldown maximum while preserving authoritative Retry-After headers and Google RetryInfo hints. (#11695) Thanks @pacocartones. ([#11823](https://github.com/diegosouzapw/OmniRoute/pull/11823))
- Compare `_rebaseline_*` notes structurally in the ratchet-bank verifier so an object-valued note no longer reports itself as rewritten on an unmodified tree — the nightly `bank-ratchet-shrinks` lane had been aborting on every run since 2026-08-11, leaving 41,672 lines of earned file-size shrinks unbanked (#11702). ([#11892](https://github.com/diegosouzapw/OmniRoute/pull/11892)) — thanks @MumuTW
- **fix(build):**`prepublish.ts` bundles the ChatGPT Web (Codex) MCP bridge through `runBuildTool()` instead of spawning `npx.cmd` raw, fixing the build crash on Node ≥ 20/Windows where `.cmd` shims cannot be spawned without a shell (EINVAL) ([#11704](https://github.com/diegosouzapw/OmniRoute/issues/11704)) ([#11706](https://github.com/diegosouzapw/OmniRoute/pull/11706)) — thanks @jonlwheat2-gif
- fix(codex): keep `parallel_tool_calls:false` on the translated Codex Responses Lite path (#11707) ([#11984](https://github.com/diegosouzapw/OmniRoute/pull/11984)) — thanks @hartmark
- **fix(tests):** the new Gemini Web Images retirement test (#11708) called the now-async `getExecutor()` synchronously, throwing `TypeError: getExecutor(...).getProvider is not a function` instead of asserting Gemini Web chat stays available. Awaited to match the R0.3 executor-registry refactor (#11220). ([#11868](https://github.com/diegosouzapw/OmniRoute/pull/11868))
- **fix(search):** Allow REST and MCP web-fetch requests to select the advertised `anysearch-search` provider explicitly ([#11716](https://github.com/diegosouzapw/OmniRoute/pull/11716)) — thanks @pacocartones
- **fix(providers):** Keep overnight peak-hour protection active after midnight according to the window's configured start day ([#11718](https://github.com/diegosouzapw/OmniRoute/pull/11718)) — thanks @pacocartones
- **fix(providers):** correct all five g4f.space gateway descriptions to document proof-of-work credits or member API keys, variable limits, and the remote prompt boundary instead of promising free keyless access at five requests per minute ([#11738](https://github.com/diegosouzapw/OmniRoute/pull/11738)).
- **fix(db):**`model_capabilities` is created by a migration instead of lazily on the first models.dev sync, so a clean install and an upgraded install converge on the same schema regardless of which features have run ([#11845](https://github.com/diegosouzapw/OmniRoute/pull/11845))
- **fix(ci):**`check:install-upgrade` now fails on an `npm` install truncated by ENOSPC (npm reports it as a warning and still exits 0), authenticates its health probe so the version assertion works against the hardened health payload, frees the clean-install tree before the upgrade phase, and no longer reports a schema divergence computed from a boot that never served ([#11845](https://github.com/diegosouzapw/OmniRoute/pull/11845))
- **fix(routing):** harden session-affinity key derivation against oversized explicit IDs and empty structural-payload collisions, while recognizing Gemini and common text request shapes ([#11746](https://github.com/diegosouzapw/OmniRoute/pull/11746)) — thanks @MumuTW
- **fix(packages/browser-pool):** regenerate `package-lock.json` so the `packages/browser-pool` workspace's locked `playwright`/`@types/node` (and transitives) match its `package.json` specs, fixing cache-only/offline installs (`npm ci --offline`, Nix `buildNpmPackage`) that previously failed with `ENOTCACHED` ([#11747](https://github.com/diegosouzapw/OmniRoute/issues/11747)) — thanks @benjaminkitt ([#11784](https://github.com/diegosouzapw/OmniRoute/pull/11784)) — thanks @geekyNads
- **fix(assets):** Stop distributing 79 provider and CLI logos without verified source/license provenance, keep every provider/tool available through the internal generic icon, and prevent those IDs from falling through to an external icon CDN. ([#11750](https://github.com/diegosouzapw/OmniRoute/pull/11750))
- **fix(providers):** retire the common `chatgpt-web` / `cgpt-web` provider because its pre-key and proof-of-work provenance could not be cleared ([#11754](https://github.com/diegosouzapw/OmniRoute/pull/11754)) — explicit chat and image requests, slash-prefixed models, persisted aliases, proxy overrides, and combo targets now fail closed with a sanitized HTTP `410` / `PROVIDER_RETIRED` before upstream dispatch. Migration 163 tombstones matching connections and invalidates their active leases without deleting history or widening API-key allowlists. The independent `chatgpt-web-codex` / `cgpt-codex` provider and its MIT-noticed vendored implementation remain available.
- **fix(usage):** quota and usage refresh no longer 409 when an exclusive lease reserves the connection ([#11758](https://github.com/diegosouzapw/OmniRoute/pull/11758)) — thanks @TheDemonTuan
- Keep the embedding registry's vector width and `embedding` type on models when a synced model exists for the same id, so `/v1/models` no longer reports registry-described embedding models widthless or untyped (#11761) — thanks @rahilmavani
- Correct `google/gemini-embedding-001` on the OpenRouter route to 3072 dimensions, the width it returns when `dimensions` is not sent (#11761) — thanks @rahilmavani
- **fix(vision-bridge):** Restrict automatic vision routing and fallbacks to models available in authoritative live provider catalogs, including aliases and effort variants ([#11767](https://github.com/diegosouzapw/OmniRoute/issues/11767)) — thanks @pacocartones ([#11813](https://github.com/diegosouzapw/OmniRoute/pull/11813))
- **fix(providers):** reclassify Cerebras as a one-time $5 signup credit (payment method required, 30-day validity), not a recurring no-card 1M tokens/day trial ([#11773](https://github.com/diegosouzapw/OmniRoute/issues/11773)) ([#12591](https://github.com/diegosouzapw/OmniRoute/pull/12591)) — thanks @HouMinXi
- fix(cli): stop prepublish from re-rebuilding the already-built ESM-only opencode-plugin dist (#11787) ([#11990](https://github.com/diegosouzapw/OmniRoute/pull/11990)) — thanks @hartmark
- **fix(db):** Fresh installs no longer log a non-fatal `no such table: compression_run_telemetry` warning when retention cleanup runs before the lazily-created telemetry table exists ([#11802](https://github.com/diegosouzapw/OmniRoute/pull/11802)) — thanks @RaviTharuma
- fix(sse): set X-OmniRoute-Selected-Connection-Id on successful combo dispatches so downstream consumers stop falling back to an empty connection id (#11810) ([#11986](https://github.com/diegosouzapw/OmniRoute/pull/11986)) — thanks @hartmark
- **fix(services):** embedded CLIProxyAPI lifecycle checks now use public `/healthz`, while model discovery uses the configured dedicated data-plane API key instead of the management password ([#11811](https://github.com/diegosouzapw/OmniRoute/pull/11811)) — thanks @RaviTharuma
- Fix persisted model steps returning an error in the playground route simulator, and warn when structural steps cannot be simulated. ([#11862](https://github.com/diegosouzapw/OmniRoute/pull/11862)) — thanks @pacocartones
- **fix(providers):** Antigravity's dynamic mitmAlias table no longer routes `gemini-3.7-flash-{high,medium,low}` to a literal tier-suffixed upstream id just because one connected account's own discovery listed it directly — those display ids always resolve through the safe `gemini-3.7-flash-tiered` static alias, so one account's Google-provisioned access no longer 404s every sibling account of the provider ([#11824](https://github.com/diegosouzapw/OmniRoute/issues/11824), [#11651](https://github.com/diegosouzapw/OmniRoute/issues/11651)) ([#11988](https://github.com/diegosouzapw/OmniRoute/pull/11988)) — thanks @hartmark
- **fix(dashboard):** Expose Profile loading, errors, page structure, and XP progress to assistive technologies ([#11838](https://github.com/diegosouzapw/OmniRoute/pull/11838)) — thanks @pacocartones
- **fix(socks):**`Agent.connectTimeout` now bounds both SOCKS handshake and TLS connect, and `family === null` no longer falls back to `fetch-socks` ([#11842](https://github.com/diegosouzapw/OmniRoute/pull/11842)) — thanks @maxmad64bis
- **perf(compression):** OOM mitigations for large payload hashing, memoization, and token estimation ([#11844](https://github.com/diegosouzapw/OmniRoute/pull/11844) — thanks @AndrianBalanescu)
- Excluded Next.js Node File Trace manifests (`*.nft.json`) from the published npm tarball. They are build-time metadata and are never read while serving, but had grown to 668.7 MB — 61% of the package — which pushed the upload past the registry limit and made `npm publish` fail with `413 Payload Too Large`. ([#11864](https://github.com/diegosouzapw/OmniRoute/pull/11864))
- **fix(cli):** keep the global OmniRoute server `--base-url` separate from provider-node `--endpoint` values in add, update, and validate commands ([#11860](https://github.com/diegosouzapw/OmniRoute/pull/11860)) — thanks @pacocartones
- **fix(config):** Nous Research's `Hermes-4-405B` model now displays as "Hermes 4 405B (Nous Research)" in both the provider registry and the free-model catalog, instead of the mislabelled "Hermes 4 7B" ([#11861](https://github.com/diegosouzapw/OmniRoute/issues/11861)) — thanks @Karan825 ([#11993](https://github.com/diegosouzapw/OmniRoute/pull/11993))
- **fix(provider/nous):** inject required user= tag into Nous Research inference requests to resolve upstream 400 "missing tags" error ([#11861](https://github.com/diegosouzapw/OmniRoute/issues/11861)) — thanks @Karan825 ([#12044](https://github.com/diegosouzapw/OmniRoute/pull/12044))
- **fix(build):**`npm run build` now fails in one second with a named package and a copy-pasteable fix when npm silently drops an externalised optional native dependency, instead of dying four minutes in with `Module not found: Can't resolve 'better-sqlite3'` ([#11863](https://github.com/diegosouzapw/OmniRoute/pull/11863)) — thanks @ujjawalkaushik1110
- **fix(install):**`postinstall` no longer throws `ReferenceError: isAndroid is not defined` — failing the whole `npm install` — when the `better-sqlite3` rebuild fallback times out; the manual-fix guidance is reachable again ([#11863](https://github.com/diegosouzapw/OmniRoute/pull/11863)) — thanks @ujjawalkaushik1110
- Fixed the Alibaba free-tier allowlist test that went red on its own once the shipped catalog's `validUntil` (2026-08-27) passed, leaving every PR and `main` with a failing `Unit Tests (1/8)`. The test now builds its own packs with dates it controls, and covers the expired-pack fallback that production has actually been serving. ([#11867](https://github.com/diegosouzapw/OmniRoute/pull/11867))
- Split the npm registry upload into its own GitHub-hosted job. npm refuses `--provenance` from a self-hosted runner (`422 ... Only "github-hosted" runners are supported`), which blocked the v3.8.50 publish; the heavy verification cannot move to a hosted runner, so it now hands the proven tarball over instead. ([#11868](https://github.com/diegosouzapw/OmniRoute/pull/11868))
- **fix(ui):** the shared `DataTable` loading state no longer reads its decorative ⏳ glyph out to assistive technology, and now carries the same `role="status"` / `aria-live="polite"` / `aria-busy="true"` semantics as `PageLoading` ([#11869](https://github.com/diegosouzapw/OmniRoute/pull/11869)) — thanks @pacocartones
- **fix(api):** Bound the `timeout` accepted by `POST /api/providers/[id]/login` to the same 15s–600s window the Adobe Firefly and Conol browser-login paths already enforce, so a request can no longer pin a headful browser and the single active-login slot with an arbitrarily large poll budget. ([#11871](https://github.com/diegosouzapw/OmniRoute/pull/11871)) — thanks @pacocartones
- **fix(api):** Stop the tunnel and MITM routes from returning raw child-process error text, which disclosed host paths, binary install locations and Tailscale `tskey-*` credentials in a body some of these routes serve to non-loopback callers, and return a real 400 instead of a framework 500 when a tunnel request body fails validation. ([#11872](https://github.com/diegosouzapw/OmniRoute/pull/11872)) — thanks @pacocartones
- **fix(open-sse):** stream TTFT/ITL are sampled from a monotonic clock (`performance.now`) instead of `Date.now`, so an NTP correction or wall-clock jump can no longer inflate a genuine TTFT or produce a negative one that the `ttft >= 0` guard silently drops — protecting the router's OTel/EWMA/`usage_history`/speed-ranking signals ([#11873](https://github.com/diegosouzapw/OmniRoute/pull/11873)) — thanks @pacocartones
- **fix(providers):** xAI `reasoning_effort: "xhigh"` now reaches grok-4.6+ instead of being silently clamped to `"high"` ([#11879](https://github.com/diegosouzapw/OmniRoute/pull/11879)) — thanks @NoxzRCW
- **fix(dashboard):** the providers page no longer crashes into the error boundary when a provider id collides with an `Object.prototype` member (`constructor`, `__proto__`); icon lookups are own-property guarded ([#11880](https://github.com/diegosouzapw/OmniRoute/pull/11880)) — thanks @NoxzRCW
- **fix(skills):** injected skill tools declared in shorthand (`{"content": "string"}`) now forward valid JSON Schema, unblocking providers that validate tool schemas strictly such as Zhipu GLM on the Console Go tier ([#11881](https://github.com/diegosouzapw/OmniRoute/pull/11881)) — thanks @NoxzRCW
- **fix(api):**`POST /api/playground/simulate-route` now surfaces `combo-ref` and `provider-wildcard` persisted combo steps with a specific warning (naming the referenced combo, or the unresolved `provider/model` wildcard) instead of folding them into a generic "unsupported step" count; a `provider-wildcard` step is also now included as an unresolved target so the operator can see it is in the route (ported from [#11882](https://github.com/diegosouzapw/OmniRoute/pull/11882) — thanks @NoxzRCW). ([#11930](https://github.com/diegosouzapw/OmniRoute/pull/11930))
- **fix(translator):** the streaming OpenAI→Claude translator keeps upstream usage, including prompt-cache tokens, when it arrives on a trailing `choices: []` chunk (Fireworks and any upstream using `stream_options.include_usage`) ([#11883](https://github.com/diegosouzapw/OmniRoute/pull/11883)) — thanks @NoxzRCW
- **fix(cli):**`omniroute update --apply` now tells you explicitly whether a running server was detected and, if so, that you must run `omniroute restart` to apply the update — it never restarted anything and previously implied the update was already live once files were installed. The dashboard's npm-mode Update flow (`/api/system/version`) now tries OmniRoute's own PID-file-managed supervisor before falling back to pm2, and reports an honest "restart required" step instead of a silent pm2-only "skipped" that read like a completed update. The server-side latest-version lookup backing the dashboard's update banner also gained `--prefer-online`, closing the same stale-npm-cache class already fixed in the CLI's own copy for #4376 ([#11885](https://github.com/diegosouzapw/OmniRoute/issues/11885)). ([#12005](https://github.com/diegosouzapw/OmniRoute/pull/12005))
- **fix(resilience):** clear persisted LKGP pins when a target suffers connection/provider exhaustion or is skipped before dispatch due to cooldown/exhaustion/unavailability, preventing subsequent requests from repeatedly prioritizing known-dead providers ([#11911](https://github.com/diegosouzapw/OmniRoute/issues/11911)). ([#12013](https://github.com/diegosouzapw/OmniRoute/pull/12013)) — thanks @HouMinXi
- **fix(sse):** the OpenAI→Claude stream translator now defers the terminal `message_delta`/`message_stop` emission until the real usage block has arrived (or a genuine end-of-stream flush forces it) instead of emitting it immediately on `finish_reason` — previously, when the trailing usage-only chunk (`{"choices":[],"usage":{...}}`) arrived *after* the `finish_reason` chunk (the normal order for Fireworks/vLLM/Together and other `stream_options.include_usage` upstreams), the client-visible `message_delta` still carried stale/zero usage even though `state.usage` was internally corrected too late to matter (ported from [#11915](https://github.com/diegosouzapw/OmniRoute/pull/11915) — thanks @HouMinXi). ([#11933](https://github.com/diegosouzapw/OmniRoute/pull/11933))
- **fix(sse):**`stripStore()` now forces `store=false` for stateless OpenAI-compatible Responses-API targets (unless the connection has explicitly opted in via `providerSpecificData.openaiStoreEnabled`), instead of only handling the `openai`/`agentrouter` cases — a client-supplied `store` value previously passed through untouched to backends that don't actually persist responses server-side ([#11916](https://github.com/diegosouzapw/OmniRoute/pull/11916) — thanks @HouMinXi).
- **fix(models):** custom provider-node models (synced, custom, and alias-backed) now appear under their configured prefix in the unified catalog when the operator's model-id prefix mode is canonical, instead of being dropped whenever alias-inclusion was otherwise disabled ([#11918](https://github.com/diegosouzapw/OmniRoute/pull/11918) — thanks @HouMinXi).
- **fix(models):** the unified model catalog now suppresses stale static registry models (including effort-tier variants) for any provider whose active connection has an authoritative live synced catalog, not only providers already using exclusive-synced-listing — a connection with `providerUsesAuthoritativeLiveCatalog` previously kept serving both the live-synced models and the stale static rows side by side ([#11919](https://github.com/diegosouzapw/OmniRoute/pull/11919) — thanks @HouMinXi).
- **fix(ui):**`ProviderIcon`'s three remaining unguarded lookups (`PROVIDER_ICON_ALIASES`, `LOCAL_SVG_ALIASES`, `THEMED_SVGS`) now use `Object.hasOwn()` own-property checks — a provider id such as `constructor` or `__proto__` previously resolved through the prototype chain instead of falling through to the unknown-provider CDN fallback (`getLobeProviderIcon()` itself was already guarded by [#11880](https://github.com/diegosouzapw/OmniRoute/pull/11880)); `ProviderPageHeader`'s `color` field is also now optional, matching the rest of the component's defensive typing (ported from [#11920](https://github.com/diegosouzapw/OmniRoute/pull/11920) — thanks @HouMinXi). ([#11935](https://github.com/diegosouzapw/OmniRoute/pull/11935)) — thanks @NoxzRCW
- fix(ollama): preserve multi-byte UTF-8 content split across stream chunks in the Ollama NDJSON transform, which previously corrupted CJK/emoji into U+FFFD (#11921) — thanks @pacocartones
- **fix(providers):** OrcaRouter chat requests now target `/v1/chat/completions` instead of the bare `/v1` API root, fixing the upstream `404 Invalid URL (POST /v1)` ([#11923](https://github.com/diegosouzapw/OmniRoute/pull/11923)). — thanks @echel0nn
- **fix(plugins):** deliver the `onStreamComplete` event to disk-installed plugins. The event shipped in v3.8.50 (#9669) was emitted internally but had no plugin-facing wiring, so no plugin could ever subscribe: the manifest schema silently dropped `hooks.onStreamComplete`, and the loader/manager only knew the seven legacy hooks. `onStreamComplete` is now a declarable manifest hook, wired through the loader and registered by the manager like the other hooks, and its payload carries a `requestId` so consumers can correlate the stream-completion event with the originating request ([#11934](https://github.com/diegosouzapw/OmniRoute/pull/11934)) — thanks @amaleta / @pacocartones
- **fix(db):** the Qdrant embedding-model dropdown now lists local/self-hosted providers (Ollama, LM Studio, vLLM, etc.) — an active connection is treated as "configured" when the provider allows an optional API key, not only when it has a real key or OAuth, so a running local embedding provider is no longer hidden from the picker ([#11949](https://github.com/diegosouzapw/OmniRoute/issues/11949)) ([#11995](https://github.com/diegosouzapw/OmniRoute/pull/11995))
- **fix(providers):** Vertex AI Anthropic partner-model discovery now calls the Model Garden `v1beta1` publisher list (`/v1beta1/publishers/anthropic/models`, global) and parses its `publisherModels` envelope, so Claude models auto-synced from Vertex populate the active live catalog and route at request time instead of returning `Model '<id>' is not available in the active live catalog` ([#11991](https://github.com/diegosouzapw/OmniRoute/issues/11991)) — thanks @fabioluissilva ([#11998](https://github.com/diegosouzapw/OmniRoute/pull/11998))
- **fix(cli):** support `--base-url` alongside `--endpoint` in `omniroute nodes add`, `update`, and `validate` subcommands to prevent global `--base-url` shadowing issues ([#11999](https://github.com/diegosouzapw/OmniRoute/issues/11999)). ([#12033](https://github.com/diegosouzapw/OmniRoute/pull/12033)) — thanks @HouMinXi
- **fix(providers):**`cloudflare-ai` no longer refuses image content parts for every Workers AI model ([#12002](https://github.com/diegosouzapw/OmniRoute/pull/12002)) — the plain-string `content` requirement behind #2539 is carried by the _model_ schema, not by the `/ai/v1/chat/completions` endpoint (measured: an all-text part array returns 200 on `@cf/mistralai/mistral-small-3.1-24b-instruct`, `@cf/meta/llama-4-scout-17b-16e-instruct` and `@cf/meta/llama-3.3-70b-instruct-fp8-fast`, and 400 on the text-only `@cf/qwen/qwen2.5-coder-32b-instruct`). `transformRequest()` flattened every array and threw on the first non-text part (#6390), so image input was refused for vision-capable Cloudflare models that accept it. All-text arrays are still flattened — the one shape every model accepts — while an array carrying a non-text part is passed through untouched, so the attachment is still never silently dropped. Regression guards: `tests/unit/cloudflare-ai-image-parts-6390.test.ts`. — thanks @davidlinfr
- **fix(resilience):** decouple the limiter-managed execution backstop from the queue-wait budget — new `requestQueue.executionMaxWaitMs` (env `RATE_LIMIT_EXECUTION_MAX_WAIT_MS`, default 600000 = 10 min) now feeds Bottleneck's post-dispatch `expiration`, while `requestQueue.maxWaitMs` keeps its documented queue-wait semantics. Previously the queue-wait budget doubled as the execution expiration, so legitimate long-running calls on non-incremental gateways (whole generation buffered before the first upstream byte, e.g. Console Go / Command Code tiers serving GLM models) were killed mid-flight at the queue budget with a false 504 `RATE_LIMIT_EXECUTION_TIMEOUT` — the local limiter undercut the provider-aware upstream fetch-start timeouts. The surfaced 504 message now names `requestQueue.executionMaxWaitMs`; the error keeps the #4165 guarantees (disclaims an upstream timeout, preserves the Bottleneck error as `cause`, branded code + trusted provenance, classified request-scoped so combo falls back). A real queue-wait bound (the `Promise.race` around `limiter.schedule()` sketched in #9533) remains future work. (#12025) ([#12027](https://github.com/diegosouzapw/OmniRoute/pull/12027)) — thanks @alvinveroy
- **Call logs:** keep the `error` field when an artifact exceeds the storage cap, instead of replacing it with the omission marker. The error is the only field that says *why* a request failed and is typically ~90 bytes next to the multi-hundred-KB bodies that trip the cap, so dropping it left a size-limited row undiagnosable — a provider outage, a local timeout and an upstream 400 all rendered identically. It is now preserved at every fallback stage, truncated to 4KB if it is itself large ([#12026](https://github.com/diegosouzapw/OmniRoute/issues/12026)). ([#12095](https://github.com/diegosouzapw/OmniRoute/pull/12095)) — thanks @ntdat812
- **fix(diagnostics):** preserve the error field (truncated to 4KB with a `[truncated: …]` suffix) in every call-log artifact size-limit fallback stage. Previously the minimal fallback replaced the error with `[omitted: call log artifact size limit exceeded]`, so an oversized artifact row showed nothing about WHY the request failed — e.g. 91 of 847 opencode-go 504 rows on one production instance were undiagnosable from the dashboard. Oversized request/response bodies are still omitted exactly as before; the error cap is independent of the payload sizes that tripped the fallback. (#12026) ([#12027](https://github.com/diegosouzapw/OmniRoute/pull/12027)) — thanks @alvinveroy
- **fix(sse):** OpenAI Responses clients that declare the native `web_search` tool now receive a spec-shaped `web_search_call` output item with `action.sources` alongside the preserved function-call round-trip, so search results executed through OmniRoute's own search backend are consumable by standard Responses clients (Codex, pi-web-access, …). ([#12031](https://github.com/diegosouzapw/OmniRoute/pull/12031)) — thanks @watchingdogs
- **fix(cli):** use in-thread alias resolver hooks on modern runtimes to avoid deprecation noise and improve Node.js forward compatibility ([#12073](https://github.com/diegosouzapw/OmniRoute/issues/12073)). ([#12083](https://github.com/diegosouzapw/OmniRoute/pull/12083)) — thanks @xiaoyaner0201
- **fix(combo):** an operator-set **Agent Features → Context length** on a combo is now honored at request time. The value was persisted and advertised through `/v1/models`, but `resolveComboContextLimit()` never consulted it — so a multi-target combo whose members carry no per-model window fell through to the provider's generic `defaultContextLength` (openrouter 128000, command-code 200000) and rejected large requests with `Input exceeds context window … limit 128000` despite the combo being explicitly sized much larger. An identical single-target combo worked, because it collapses to its concrete target before the guard runs. Invalid values (0/negative/NaN/Infinity) are ignored, so the existing target → combo-min → fallback order is unchanged. ([#12090](https://github.com/diegosouzapw/OmniRoute/pull/12090)) — thanks @adivekar-utexas
- **fix(sse):** passthrough streams now estimate usage on finish when upstream closes without usage even with `stream_options.include_usage` — avoids `0 tokens / 0%` for providers that stay silent (and correctly handles trailing empty-choices usage) ([#12151](https://github.com/diegosouzapw/OmniRoute/pull/12151)) — thanks @maxmad64bis
- **fix(combos):** clearing an agent feature in the combos editor now persists — unchecking context cache protection, or emptying the system message or tool filter, sends an explicit `null` instead of dropping the field from the `PUT` body, which the update merge read as "leave unchanged" ([#12177](https://github.com/diegosouzapw/OmniRoute/pull/12177)) — thanks @foreveryh / @ntdatt812
- **fix(memory):** self-hosted embedding endpoints now vectorize — the vector width is measured from the first embedding that comes back instead of being read from a registry that cannot describe them, so `vec_memories` is created and memories stop piling up unvectorized behind a green health check ([#12180](https://github.com/diegosouzapw/OmniRoute/pull/12180)) — thanks @kanade-hoshino / @ntdatt812
- **fix(translator):** the leading `system` message now reaches Responses-API upstreams when its `content` is a content-part array — it was read as `typeof content === "string" ? content : ""`, so a prompt-caching client (Anthropic `cache_control`, the shape LiteLLM and the Anthropic SDK emit) had its entire system prompt replaced by an empty `instructions`. The request was still accepted with a normal `prompt_tokens` count, so the model answered with no instructions and nothing in the response said they were missing. Mid-conversation system turns already handled the array shape ([#7056](https://github.com/diegosouzapw/OmniRoute/pull/7056)); only the first one did not ([#12206](https://github.com/diegosouzapw/OmniRoute/issues/12206)). Regression guard: `tests/unit/translator-openai-responses-system-content-parts.test.ts`. ([#12207](https://github.com/diegosouzapw/OmniRoute/pull/12207)) — thanks @Gorillaz322
- **fix(free-tier):**`/api/free-tier/summary` no longer computes its totals from a Radar feed built before the catalog the running release ships. When the cached feed is older — or carries no build date at all — the route answers from the shipped catalog, resolved through the operator's local model state so disabled and tombstoned models stay out of the numbers ([#12215](https://github.com/diegosouzapw/OmniRoute/pull/12215)). — thanks @maxmad64bis
- **fix(oauth):** Keep a Claude personal workspace and a Team organization as separate connections — they share the same email and `accountUUID`, so the email-only OAuth dedup let the second login overwrite the first account's tokens; `organizationUUID` now disambiguates them, the way `workspaceId` does for Codex ([#12222](https://github.com/diegosouzapw/OmniRoute/pull/12222)) — thanks @davidebaraldo
- **fix(resilience):** a 402 on a single paid model of a passthrough/gateway provider (e.g. `kilo-gateway`, `ollama-cloud`) no longer terminalizes the whole connection with a never-auto-recovered `credits_exhausted` status — only the paid model is locked out, so free models on the same key keep serving. 402 variant of [#3027](https://github.com/diegosouzapw/OmniRoute/issues/3027). Single-credential providers are unaffected — a 402 there is still treated as the key being genuinely out of credit ([#5239](https://github.com/diegosouzapw/OmniRoute/issues/5239) / [#10616](https://github.com/diegosouzapw/OmniRoute/issues/10616)) ([#12242](https://github.com/diegosouzapw/OmniRoute/issues/12242)) — thanks @brick30llc-ctrl ([#12266](https://github.com/diegosouzapw/OmniRoute/pull/12266)) — thanks @geekyNads
- **fix(sse):** trust `finish_reason: "length"`/`"max_tokens"` over the reasoning-consumed-token ratio in response quality validation, so a reasoning model truncated below the old 90% threshold correctly fails and retries instead of returning empty content as a silent "success" ([#12262](https://github.com/diegosouzapw/OmniRoute/pull/12262)) — thanks @brick30llc-ctrl
- **fix(settings):**`PUT /api/settings/cache-config` now persists `alwaysPreserveClientCache` to the flat general settings the runtime cache-control policy actually reads; previously the value landed in the databaseSettings "cache" section and was silently ignored, so the endpoint had no effect on `cache_control` passthrough ([#12304](https://github.com/diegosouzapw/OmniRoute/pull/12304)) — thanks @davidebaraldo
- **fix(grok-cli):** treat omitted SuperGrokPro `creditUsagePercent` as 0% used so Provider Limits still renders a weekly bar (proto3 zero-elision) ([#12312](https://github.com/diegosouzapw/OmniRoute/pull/12312)) — thanks @HouMinXi
- **fix(combo):** Expose the two Auto-Combo scoring factors nobody could set — the combo validation schema and the dashboard weight sliders both declared 13 of the scorer's 15 factors, so `connectionDensity` (spreads load across a provider's connections) and `quality` were dropped on save and offered nowhere. The sliders also shipped their own default table that differed from the engine's on every non-zero factor and summed to 1.05, so the percentages shown next to them added up to 105%. Both lists now match `DEFAULT_WEIGHTS`, and a test keeps them there. Note that a combo whose stored `weights` omitted the two keys was effectively running with them at zero and the other thirteen renormalized upward; it now runs with the engine's intended distribution, so its routing does shift ([#12314](https://github.com/diegosouzapw/OmniRoute/pull/12314)) — thanks @maxmad64bis
- **fix(docs):** The free-tier reference no longer says its numbers come "confidence tagged per row" — no catalog entry carries a confidence tag and the API serves none, so every figure on that page is an estimate of the same, unstated quality. The page now states what an entry does vouch for: an independently documented hard stop (set by hand with the source in a comment, never defaulted to `true`) and a prompt-training disclosure, both with live counts the `check:docs-counts` gate keeps honest ([#12318](https://github.com/diegosouzapw/OmniRoute/pull/12318)) — thanks @maxmad64bis
- **fix(usage):**`adobe-firefly` and `firefly` have had a working usage fetcher since Adobe Firefly landed, but neither was ever added to the registration list, so the provider-plugin manifest, `genericQuotaFetcher` and the free-access quota cache all reported them as having no usage support — while `USAGE_SUPPORTED_PROVIDERS` said the opposite. Both are now declared, which also means their credit balance is fetched like any other declared provider's: `registerGenericQuotaFetchers` now registers a generic quota fetcher for them, and `resolveFreeAccessState` no longer returns early. A test holds the registration list to the dispatcher's switch in both directions, which is what the module's own docstring already asked for in prose ([#12321](https://github.com/diegosouzapw/OmniRoute/pull/12321)) — thanks @maxmad64bis
- **fix(quota):** drop the generic quota cache (agy / Antigravity / Claude OAuth) on an upstream 429 so reset-aware scoring does not keep a 60s stale snapshot, and force-refresh the next usage fetch so inner provider caches cannot recache the same window ([#12325](https://github.com/diegosouzapw/OmniRoute/pull/12325)) — thanks @HouMinXi
- **fix(combos):** deleting a combo now clears its persisted LKGP pins instead of leaving unreachable `key_value` rows behind ([#12326](https://github.com/diegosouzapw/OmniRoute/issues/12326)) ([#12425](https://github.com/diegosouzapw/OmniRoute/pull/12425)) — thanks @KrzysiekSko
- **fix(sse):** Keep ZWNJ (U+200C) and ZWJ (U+200D) in assistant text, reasoning and tool-call arguments — Persian/Kurdish half-space (`ارائهدهنده`), Arabic/Indic shaping and emoji sequences no longer lose them; the response de-obfuscation now removes joiners only between ASCII word characters, where the request side inserts them ([#12186](https://github.com/diegosouzapw/OmniRoute/issues/12186)) — thanks @rezjalibd ([#12359](https://github.com/diegosouzapw/OmniRoute/pull/12359)) — thanks @pacocartones
- **fix(resilience):** count resolved upstream 5xx results against the provider circuit breaker on the chat path — `CircuitBreaker.execute()` no longer reads a resolved `{ success: false, status: 5xx }` as a success that cancels the call-site failure, so a provider answering 503s now trips its breaker instead of staying `CLOSED` at `failureCount: 1`; single-model and combo dispatches are each accounted exactly once ([#12254](https://github.com/diegosouzapw/OmniRoute/issues/12254)) ([#12360](https://github.com/diegosouzapw/OmniRoute/pull/12360)) — thanks @pacocartones
- **fix(providers):** resolve the Codex quota auto-ping model from the live provider catalog and lifecycle registry instead of the retired `gpt-5.1-codex-mini`, and pause the ping with one actionable warning when no selectable Codex model exists rather than retrying a shut-down id every cooldown window ([#11905](https://github.com/diegosouzapw/OmniRoute/issues/11905)) ([#12361](https://github.com/diegosouzapw/OmniRoute/pull/12361)) — thanks @pacocartones
- **fix(api):** keep the `{created, data}` wrapper on combo-routed `/v1/images/generations` responses and default Codex image results to `b64_json` on both `/v1/images/generations` and `/v1/images/edits` so Codex CLI's built-in `image_gen` can decode them ([#12268](https://github.com/diegosouzapw/OmniRoute/issues/12268)) ([#12362](https://github.com/diegosouzapw/OmniRoute/pull/12362)) — thanks @pacocartones
- **fix(sse):** Name the shadowed custom provider node when a built-in provider id/alias (e.g. `openference` → `of`) reserves the prefix of an existing OpenAI/Anthropic-compatible node, so the runtime `No active credentials for provider: <built-in>` error explains that the prefix routed to the built-in and never reached the node's healthy connections, instead of contradicting the dashboard ([#11943](https://github.com/diegosouzapw/OmniRoute/issues/11943)) — thanks @morpheus9393 ([#12365](https://github.com/diegosouzapw/OmniRoute/pull/12365)) — thanks @pacocartones
- **fix(i18n):** wrap `ccOnboardingKeyPlaceholder` in ICU single quotes across all 43 locales so angle brackets render literally instead of being parsed as rich-text tags, which crashed the Claude Code onboarding block with `INVALID_MESSAGE: INVALID_TAG` ([#12302](https://github.com/diegosouzapw/OmniRoute/issues/12302)) ([#12369](https://github.com/diegosouzapw/OmniRoute/pull/12369)) — thanks @gonisulaimann
- **fix(models):** publish `effort_tiers` on Kimi K3's synced base-model entries (`kmca/k3`, `kmca/k3-256k`) so catalog-only clients (OpenCode, plain SDK pickers) can see and select the reasoning tiers (`low`/`high`/`max`) the synced metadata already carried — the `isSkippedEffortProvider` gate no longer suppresses tier visibility on those base entries, while synthetic `<id>-<tier>` variant generation stays prevented and Codex/GLM base models remain excluded unchanged ([#12299](https://github.com/diegosouzapw/OmniRoute/issues/12299)) ([#12371](https://github.com/diegosouzapw/OmniRoute/pull/12371)) — thanks @gonisulaimann
- **fix(guardrails):** keep `auto`/`auto/*` virtual combos exempt from the Vision Bridge `fixedModel` credential guard so a combo target is passed through instead of silently falling back to global auto-selection ([#12237](https://github.com/diegosouzapw/OmniRoute/issues/12237)) ([#12373](https://github.com/diegosouzapw/OmniRoute/pull/12373)) — thanks @pacocartones
- **fix(combo):** capability-filter exhaustion caused by `max_tokens` above every target's known output limit now reports that reason (requested `max_tokens` vs the pool's highest known ceiling) instead of the unrelated "supports structured output" message ([#12229](https://github.com/diegosouzapw/OmniRoute/issues/12229)) — thanks @DW-MediaLab ([#12374](https://github.com/diegosouzapw/OmniRoute/pull/12374)) — thanks @pacocartones
- **fix(auth):** the `least-used` account strategy now prefers accounts without backoff before falling back to oldest `lastUsedAt`, the same tie-break `round-robin` already applies, so a failover no longer lands on a just-rate-limited account for a single request ([#12279](https://github.com/diegosouzapw/OmniRoute/issues/12279)) — thanks @tenshiak ([#12375](https://github.com/diegosouzapw/OmniRoute/pull/12375)) — thanks @pacocartones
- **fix(docker):** the `chatgpt-web-codex-browser` image now finds the Chrome binary under `chrome-linux64/` (Chrome for Testing layout in `playwright:v1.62.0-noble`) as well as the legacy `chrome-linux/`, so the container no longer crash-loops with `exec: --headless=new: not found` ([#12024](https://github.com/diegosouzapw/OmniRoute/issues/12024)) ([#12376](https://github.com/diegosouzapw/OmniRoute/pull/12376)) — thanks @pacocartones
- **fix(providers):** declare `groq/compound` and `allam-2-7b` as non-reasoning models in the curated Groq registry so `reasoning_effort` / `output_config.effort` / `thinking` from Claude Code are stripped instead of forwarded, which Groq rejected with HTTP 400 ([#12134](https://github.com/diegosouzapw/OmniRoute/issues/12134)) ([#12379](https://github.com/diegosouzapw/OmniRoute/pull/12379)) — thanks @pacocartones
- **fix(executors):**`OpencodeExecutor` no longer forces a direct connection when the connection has a proxy assigned in Proxy Management but no per-account proxies: the single-account fast path used to wrap the upstream dispatch in the direct-egress sentinel, discarding the ambient proxy context the chat handler had pinned from `proxy_assignments`, so API-key `opencode`/`opencode-go` connections egressed from the host IP (and hit geoblocks) despite the assignment. The direct pin is now applied only when no ambient proxy context exists ([#11894](https://github.com/diegosouzapw/OmniRoute/issues/11894) — thanks @hizzt) ([#12380](https://github.com/diegosouzapw/OmniRoute/pull/12380)) — thanks @pacocartones
- **fix(api):**`GET /v1/models` with `MODELS_CATALOG_PREFIX_MODE=canonical` (or `?prefix=canonical`) now lists providers whose registry alias is undefined or equal to their own id (Antigravity, Antigravity CLI and other self-aliased built-ins) — their single `provider/model` id was dropped by the alias/canonical duplicate guard in the static, synced, custom and alias-backed catalog loops ([#12058](https://github.com/diegosouzapw/OmniRoute/issues/12058)) — thanks @cheynetom ([#12381](https://github.com/diegosouzapw/OmniRoute/pull/12381)) — thanks @pacocartones
- **fix(translator):** Drop replayed `thinking` blocks that carry no signature (the shape produced from cross-provider `reasoning_content`) instead of stamping the default Claude signature on them, which Anthropic rejected with `400 Invalid signature in thinking block` on the next turn served by an Anthropic rung ([#12105](https://github.com/diegosouzapw/OmniRoute/issues/12105)) — thanks @atescivitci-cmd ([#12386](https://github.com/diegosouzapw/OmniRoute/pull/12386)) — thanks @pacocartones
- **fix(cli):** Resolve Bun's `--preload` polyfill path against the package root instead of `dist/`, so `omniroute` installed with `bun install -g` no longer crashes at startup with `error: preload not found …/dist/open-sse/utils/setupPolyfill.ts` ([#11980](https://github.com/diegosouzapw/OmniRoute/issues/11980)) — thanks @joglomedia ([#12387](https://github.com/diegosouzapw/OmniRoute/pull/12387)) — thanks @pacocartones
- **fix(providers):**`gemini-business` now publishes its model catalog — `/v1/models` and `/v1/providers/gemini-business/models` list the 12 enterprise Gemini ids the executor understands instead of returning an empty list (#12107) ([#12389](https://github.com/diegosouzapw/OmniRoute/pull/12389)) — thanks @pacocartones
- **fix(db):** install `busy_timeout` before the SQLite connection's first statement so a process opening the database while another one closes its WAL connection waits out the transient EXCLUSIVE lock instead of dying with `database is locked`, and recognise the drivers' real BUSY/PROTOCOL/IOERR errors as transient in the corruption probe so the same lock no longer renames the database away as corrupt; deflakes `cross-process contenders never both acquire the same connection` (#12394 — thanks @pacocartones)
- **fix(chat-admission):** derive the `chat_admission_busy` 503 `Retry-After` from observed heavyweight-lease occupancy — the larger of the exhausted `OMNIROUTE_CHAT_ADMISSION_QUEUE_MS` window and the time since capacity last turned over, capped at 60 s — instead of a fixed 1 s (structural) / 2 s (byte-stage) hint that invited Codex/agent fan-out clients to re-send ~1 MiB `/v1/responses` bodies every second into a gate held for the whole SSE lifetime; an idle gate keeps the historical floors ([#12135](https://github.com/diegosouzapw/OmniRoute/issues/12135)) (#12395 — thanks @pacocartones)
- **fix(api-manager):** the API key permissions modal no longer silently drops `allowedCombos` entries its Combo picker cannot render — routing-rule names such as `rt-*`, which the backend already honours — when "All" is clicked and the key is switched back to "Restrict"; those entries now survive the toggle, are listed read-only under the combo list so the count and the list agree, and are saved back verbatim instead of persisting `[]` (deny-all) (#12397 — thanks @pacocartones)
- **fix(catalog):** write the NUL separator of the catalog connection memo key, the provider serviceKind memo key, the Video Bridge promotion group key and a JSON-exactness test fixture as the `\u0000` escape instead of a raw byte — same runtime value, but the raw byte made git, GitHub and ripgrep treat those files as binary (hidden PR diffs, silently skipped searches); a guard test now keeps raw NUL bytes out of `src/`, `open-sse/` and `tests/` (#12403 — thanks @pacocartones)
- **fix(providers):** add `CLAUDE_CODE_CLIENT_VERSION` and `GITHUB_COPILOT_CLI_VERSION` env overrides so Anthropic/Copilot client-version gates can be unblocked without a rebuild ([#12417](https://github.com/diegosouzapw/OmniRoute/issues/12417)) ([#12632](https://github.com/diegosouzapw/OmniRoute/pull/12632)) — thanks @HouMinXi
- **fix(db):** back-fill `last_ping_at` and `last_pinged_reset_key` on `provider_connections` during schema reconciliation so divergent lineages that skipped `123_quota_auto_ping` still accept quota auto-ping writes ([#12470](https://github.com/diegosouzapw/OmniRoute/pull/12470) — thanks @KooshaPari)
- **fix(ci):** document MIT exceptions for `@eloqnt/{config,format-json,format-po}` (next-intl transitive; locked tarballs omit `license`) and keep the A2A lifecycle vitest off the real SQLite persistence seam ([#12581](https://github.com/diegosouzapw/OmniRoute/issues/12581)) ([#12595](https://github.com/diegosouzapw/OmniRoute/pull/12595))
- OpenCode plugin `/v1/models` catalog fetch now waits 30s by default and attaches HTTP `statusCode` on 401/5xx so host fallback plugins can hop instead of seeing an untyped AbortError/UnknownError. ([#12607](https://github.com/diegosouzapw/OmniRoute/pull/12607)) — thanks @RaviTharuma
- **CI:** the OpenAPI security-tier gate now mirrors `isAlwaysProtectedPath()` in full — it also reads `ALWAYS_PROTECTED_API_PATTERNS`, so the pattern-gated credential routes (`/api/providers/{id}/{claude,codex}-auth/{export,apply-local}`, GHSA-5926-2w35-7h4q) no longer report as unannotated. (#12605)
- **fix(api):** GET /v1/models no longer waits forever on a hung coalesced catalog rebuild; cold-path waits are bounded (`CATALOG_BUILD_TIMEOUT_MS`, default 8s) and a last-good 200 is served when the rebuild times out ([#12627](https://github.com/diegosouzapw/OmniRoute/issues/12627)). ([#12628](https://github.com/diegosouzapw/OmniRoute/pull/12628)) — thanks @RaviTharuma
- **fix(cursor):** a non-array `tool_calls` on an assistant message no longer crashes the cursor request translator with a `TypeError`; both loops now require an array ([#12689](https://github.com/diegosouzapw/OmniRoute/issues/12689)) ([#12691](https://github.com/diegosouzapw/OmniRoute/pull/12691)) — thanks @soroush5
- **fix(chat):** Chat Completions no longer return empty `content` after a server-owned memory or skills tool; the first provider send and account/model recovery now share one pipeline so a follow-up round-trip can fill the reply ([#12696](https://github.com/diegosouzapw/OmniRoute/issues/12696)) — thanks @HouMinXi ([#12867](https://github.com/diegosouzapw/OmniRoute/pull/12867))
- **fix(dashboard):** batch-deleting provider keys no longer toasts failure after a successful delete when the confirm button's click event is forwarded as `onAfter` ([#12711](https://github.com/diegosouzapw/OmniRoute/pull/12711)) — thanks @HouMinXi
- **fix(glm):** drop the extra 16th argument to `createSSETransformStreamWithLogger` that TypeScript rejected (TS2554) and that never reached the TransformStream ([#12711](https://github.com/diegosouzapw/OmniRoute/pull/12711)) ([#12770](https://github.com/diegosouzapw/OmniRoute/pull/12770)) — thanks @HouMinXi
- **fix(dashboard):** pass `nodeMap` into Runtime `QuotaGroup` so a quota monitor in error/exhausted/alerting no longer throws `ReferenceError: nodeMap is not defined`. ([#12868](https://github.com/diegosouzapw/OmniRoute/pull/12868)) — thanks @HouMinXi
- Restricted API keys whose `allowedModels` lists a combo name no longer skip every combo member at pre-dispatch (`ALL_TARGETS_SKIPPED`). Inner-target filtering still applies when the allow-list is a provider prefix or `disableNonPublicModels` is on ([#12899](https://github.com/diegosouzapw/OmniRoute/pull/12899)). — thanks @HouMinXi
- **fix(combos):** Effort-suffixed combo members inherit the base model's `model_context_overrides` row so priority order is not inverted on large requests ([#12926](https://github.com/diegosouzapw/OmniRoute/pull/12926)) — thanks @HouMinXi
- **fix(catalog):** Picker-added `customModels` enter the dispatch-time live catalog so combo members and bare inference no longer 400 ([#12934](https://github.com/diegosouzapw/OmniRoute/pull/12934)) — thanks @HouMinXi
- **fix(docker):** re-derive the Docker build's worker-pool memory budget from the MEASURED ~4.5 GB per-process RSS (the issue owner's own VPS dmesg OOM-killer reproduction) instead of the stale 2560 MB/worker inference #11419 shipped, and lower `OMNIROUTE_BUILD_WORKERS` 3 → 2 so 1 parent + 1 page-data worker (2 processes × 4.5 GB = 9 GB) fits the 12.288 GB (75%) budget on a 16 GB GitHub Actions runner — the previous default (1 parent + 2 workers = 13.5 GB) still overcommitted the runner and kept "Publish to Docker Hub" failing with `cannot allocate memory` after #11419 merged (#7518). ([#11663](https://github.com/diegosouzapw/OmniRoute/pull/11663))
- **fix(electron):** the packaged Windows desktop build now passes the #7592 cold-restart smoke end to end. Five defects were found and fixed on the way: (1) optional-pack staging failed on any machine whose `tar` is GNU tar — it reads the drive letter in an absolute `-f C:\...` archive path as a remote rsh host (`Cannot connect to C:`), so staging now passes a bare filename with `cwd` at the tarball directory and surfaces tar stderr on failure; (2) the Electron `files` allowlist was missing `lib/loginHeaderCapture.js`, so the packaged main process crashed at startup with `Cannot find module './lib/loginHeaderCapture'`; (3) electron-builder ≥26 injects an `!**/node_modules/**` ignore into every extraResources pattern list that no positive filter can override, which silently dropped the staged runtime `node_modules` (including the better-sqlite3 N-API prebuild) from `resources/app` — a fresh v3.8.50 desktop build would have shipped with no native SQLite driver and reproduced the #7592 sql.js fallback on every machine; an `afterPack` hook now restores the staged `node_modules` after packing; (4) the packaged-app smoke harness redirected `USERPROFILE` into its temp DATA_DIR, but Electron resolves the Roaming profile from `%USERPROFILE%\AppData\Roaming\<name>` (USERPROFILE takes precedence over the APPDATA env var) and the path service throws instead of creating it, so `requestSingleInstanceLock()` returned false and the app exited(0) silently before `app.whenReady()` — the harness now pre-creates the derived tree, and `ensureSmokeEnvDirs` is exported and unit-tested; (5) the #7592 driver assertion parsed a `[DB] Driver: ...` line that the server's primary DB path never printed (only the unused `openDatabaseAsync()` did) — `getDbInstance()` now emits the same line on open so the guard can actually assert the native driver. Also: the smoke env-allowlist unit test hardcoded POSIX paths and could only pass on Linux/macOS; expectations are now host-agnostic, with new regression tests for the USERPROFILE-derived tree and `tarPack` under absolute Windows-style paths ([#11443](https://github.com/diegosouzapw/OmniRoute/pull/11443)) — thanks @jonlwheat2-gif
- fix(sse): stop the auto-combo candidates inspector from silently dropping model-locked/cooled-down rows (#9133) ([#11994](https://github.com/diegosouzapw/OmniRoute/pull/11994)) — thanks @hartmark
- **fix(providers):** Perplexity Web no longer turns upstream stream failures into successful assistant text; pre-content failures remain eligible for fallback, partial output ends with a structured sanitized error, and failed sessions are not persisted ([#12465](https://github.com/diegosouzapw/OmniRoute/pull/12465))
- **fix(video-bridge):** preserve chronological video and transcript fusion, source-frame timestamps, transcript provenance, full contact-sheet intervals, and pre-abort callback isolation ([#11681](https://github.com/diegosouzapw/OmniRoute/pull/11681))
- **Z.ai Web:** HTTP 200 streams carrying an upstream error now terminate with a structured failure instead of assistant text plus a normal stop, preserving partial output while allowing pre-content combo fallback. ([#12454](https://github.com/diegosouzapw/OmniRoute/pull/12454))
- Absorb `Error [AbortError]: request_signal_aborted` and DOMException AbortError shapes in the process-level client-abort crash guard so routine client disconnects no longer kill the server (exit code 7). ([#12165](https://github.com/diegosouzapw/OmniRoute/pull/12165)) — thanks @alvinveroy
- **fix(sse):** Treat Adapta Web `type:error` SSE events as sanitized non-stream failures instead of empty HTTP 200 completions. ([#12459](https://github.com/diegosouzapw/OmniRoute/pull/12459))
- **fix(autoCombo):** layer 3 (`models_dev_tier`) no longer scores retired models as premium, merge cross-provider capability rows deterministically, and inherit tier scores through variant ids ([#11508](https://github.com/diegosouzapw/OmniRoute/issues/11508)). `getModelsDevTierFitness` now vetoes ids present in `config/quality/model-lifecycle.json` with status `retired` before any other signal; `loadModelCapabilities()` aggregates per `model_id` (any-non-null-true for booleans, max for `limit_context`) instead of last-write-wins over SQLite's undefined row order; a capabilities miss retries through `resolveScoresAs()`'s base id and reports `models_dev_tier:inherited`, matching layers 1–2 (#11492). Adds `getModelsDevTierFitnessWithSource()` and an `invalidateCapabilitiesCache()` test/ops hook. ([#11598](https://github.com/diegosouzapw/OmniRoute/pull/11598)) — thanks @Meet6338-X
- fix(sse): accept Claude `content:[]` + `stop_reason: max_tokens`/`tool_use` in `detectMalformedNonStream` (match `isEmptyContentResponse`) so Claude Code `/model` probes with `max_tokens: 1` no longer become a false 502 ([#11568](https://github.com/diegosouzapw/OmniRoute/pull/11568)) — thanks @Seramicx
- **fix(security):** sanitize `request.failed` diagnostics before publishing them to live dashboard listeners and replay history, while keeping status, model, provider, latency, and internal call-log diagnostics intact. ([#12469](https://github.com/diegosouzapw/OmniRoute/pull/12469))
- **fix(pwa):** do not intercept dashboard navigations so Chrome can fall back from a stale HTTP/3 Alt-Svc advertisement (UDP :20128 is unpublished; F5 on a long-lived tab hung until a new tab opened a fresh TCP connection). ([#12767](https://github.com/diegosouzapw/OmniRoute/pull/12767)) — thanks @HouMinXi
- **fix(executors):** handle DuckDuckGo ERR_BN_LIMIT (418) without retrying — when the upstream returns `418 ERR_BN_LIMIT` (rate-limit/ban), the executor now returns the error immediately instead of burning another VQD acquisition that would only count against the IP limit. The retry logic for `418 ERR_CHALLENGE` (unsolved challenge) remains unchanged. ([#11598](https://github.com/diegosouzapw/OmniRoute/pull/11598)) ([#12110](https://github.com/diegosouzapw/OmniRoute/pull/12110)) — thanks @oyi77 / @Meet6338-X
- Fixed DuckDuckGo streaming responses losing JSON lines and UTF-8 characters split across network chunks. ([#11528](https://github.com/diegosouzapw/OmniRoute/pull/11528)) — thanks @pacocartones
- Harden generated Cloudflare, Vercel, and Deno relays by stripping hop-by-hop, framing, and proxy authentication headers before forwarding requests upstream. ([#11533](https://github.com/diegosouzapw/OmniRoute/pull/11533)) — thanks @pacocartones
- **feat(grok-cli):** Provider Limits shows grok-cli banked reset credits from `GetRemainingResets` (including a real zero; a failed RPC omits the row) and the existing View credits button now calls `ConsumerUiSvc/RedeemReset` for grok-cli. Live tokens use nested fields 10/20/30 (id + Timestamp), not compact 1/2/3. ([#12805](https://github.com/diegosouzapw/OmniRoute/pull/12805)) — thanks @HouMinXi
- **fix(memory):** Embedding Model Quick select, Embedding Source remote dropdown, and Rerank selector now list every configured provider with embedding/rerank support instead of only chat-catalog text matches plus OpenRouter live discovery; a generic OpenAI-compatible `/embeddings` + Cohere-compatible `/rerank` runtime fallback resolves any configured chat provider's embedding/rerank endpoint, so unlisted providers no longer fail with "Unknown embedding provider"; both memory selectors gained a free-text model override ([#11390](https://github.com/diegosouzapw/OmniRoute/pull/11390)) — thanks @rqzbeh
- Harden SQLite upgrades around the historical migration-074 version collision: missing discovery and inspector tables are replayed atomically, pre-existing databases (including setup-created skeletons) receive reusable content-addressed safety snapshots, and Node test/eval probes without `DATA_DIR` are isolated from the operator database. ([#12435](https://github.com/diegosouzapw/OmniRoute/pull/12435))
- **fix(dashboard):** Moonshot/Kimi Open Platform voucher and cash leftover percentages follow the bucket balance, so an empty wallet no longer paints those rows as 100% while Available is 0% ([#12733](https://github.com/diegosouzapw/OmniRoute/pull/12733)) — thanks @HouMinXi
- **fix(combo):** return non-retryable HTTP 400 when all candidates for a pinned native Codex turn are unavailable due to model-scoped lockout, terminating the turn cleanly while preserving turn continuity and enabling standard Combo routing on subsequent turns ([#12240](https://github.com/diegosouzapw/OmniRoute/pull/12240)) — thanks @mdigitalbh81
- Fixed auto-router strategies preserving the selected connection through ranking and dispatch when multiple connections share the same provider and model. ([#11530](https://github.com/diegosouzapw/OmniRoute/pull/11530)) — thanks @pacocartones
- Preserve Chat Completions JSON-object response formats when translating requests to the Responses API. ([#11529](https://github.com/diegosouzapw/OmniRoute/pull/11529)) — thanks @pacocartones
- Fix idempotency fingerprints so Responses API requests include `input` and other semantic generation fields using stable serialization, while excluding credentials and request metadata. ([#11532](https://github.com/diegosouzapw/OmniRoute/pull/11532)) — thanks @pacocartones
- **fix(api):** Generated API CLI commands now enforce required OpenAPI request bodies; Combo test commands forward the required `comboName` body, while API keys created by older writers after migration 149 preserve legacy allow-all Combo access without widening explicit empty allowlists — thanks @marcelokarval ([#12070](https://github.com/diegosouzapw/OmniRoute/pull/12070))
- **fix(grok-web):** treat upstream streaming failures as failures instead of successful assistant text: error-only streams now fail readiness with HTTP 502, while failures after legitimate content preserve that partial output and terminate through the sanitized stream failure path without a normal `stop` completion. ([#12458](https://github.com/diegosouzapw/OmniRoute/pull/12458))
- HuggingChat now turns HTTP 200 JSONL generation failures into a sanitized 502 before content, or a fixed public stream failure after partial output, so fallback and request persistence no longer record a false successful stop. ([#12456](https://github.com/diegosouzapw/OmniRoute/pull/12456))
- **fix(providers):** keep 1min.ai HTTP 200 stream errors out of assistant content, preserve partial output, and expose sanitized terminal errors so pre-content failures can fall back. ([#12466](https://github.com/diegosouzapw/OmniRoute/pull/12466))
- **fix(sessions):** preserve legacy Sessions data when the additive exclusive-session projection is unavailable, returning an empty projection and warning only once per contiguous outage instead of failing the endpoint; the Sessions badge intentionally reflects the merged legacy and exclusive row count introduced by [#11389](https://github.com/diegosouzapw/OmniRoute/pull/11389) ([#11469](https://github.com/diegosouzapw/OmniRoute/pull/11469)) — thanks @KaspaPulse
- Render Nimble Search with the generic provider icon and serve Opper's proven logo locally. ([#12415](https://github.com/diegosouzapw/OmniRoute/pull/12415))
- **fix(quality):**`config/quality/provider-assets-provenance.jsonl` was stale against the physical `public/providers/` tree (still listing 225 assets and 5 duplicate-content groups after several provider-retirement PRs removed 85 icon files), which would have made `check:provider-asset-provenance` fail on the next full run. Reconciled the manifest to the real 142-file snapshot (142 asset records, 1 duplicate-content group, 2 newly-registered files marked `unresolved` pending provenance research), repinned `auditedCommit`, and updated the regression test's hardcoded counts to match. ([#11876](https://github.com/diegosouzapw/OmniRoute/pull/11876))
- fix(ui): wrap quota card footer action buttons to prevent clipping Refresh button on narrow cards — when extra action buttons such as `View credits` are present on Codex cards, allow the footer row to flex-wrap with `shrink-0` buttons so `Refresh now` remains visible and clickable across all responsive card widths ([#11464](https://github.com/diegosouzapw/OmniRoute/pull/11464)) — thanks @adevwithpurpose
- Keep Antigravity Gemini usable when the same connection's Claude weekly quota is empty; generic quota cache stays per-connection for every other provider. ([#12637](https://github.com/diegosouzapw/OmniRoute/pull/12637)) — thanks @HouMinXi
- Fixed Tailscale tunnel setup to reject ports outside the valid 1-65535 range and safely install Windows MSI packages from paths containing apostrophes. ([#11534](https://github.com/diegosouzapw/OmniRoute/pull/11534)) — thanks @pacocartones
- Classify Cloudflared and Tailscale process-management routes as local-only and spawn-capable while preserving remote access to read-only tunnel status endpoints. ([#11531](https://github.com/diegosouzapw/OmniRoute/pull/11531)) — thanks @pacocartones
- Electron release workflow: the `publish-npm` job now grants `actions: read` to the reusable `npm-publish.yml` it calls (its `publish` job requests it), which is what made GitHub refuse the whole v3.8.50 run at startup and ship the release with zero desktop assets; a `workflow_dispatch` now builds the requested tag instead of the dispatching branch and can skip the npm leg (`publish_npm=false`) when only re-attaching assets ([#11974](https://github.com/diegosouzapw/OmniRoute/pull/11974))
- **fix(dashboard):** The Combos page usage guide now reads its dismissal through `useSyncExternalStore` instead of correcting SSR state inside an effect, removing an extra commit of the page tree on every load (and the `react-hooks/set-state-in-effect` error it raised). ([#12671](https://github.com/diegosouzapw/OmniRoute/pull/12671))
- Electron release: `electron/package-lock.json` regained the optional `electron-builder-squirrel-windows` subtree (13 entries) that `npm ci` had been refusing as out of sync, `electron-release.yml` gained a `build_ref` dispatch input and stops regenerating release notes on a re-attach dispatch, and the npm publish workflow attaches the SBOM to the GitHub Release on dispatch publishes too — so the v3.8.51 tag ships every desktop asset and the SBOM like v3.8.49 did ([#12022](https://github.com/diegosouzapw/OmniRoute/pull/12022))
- Drained the reds every PR against `release/v3.8.51` was born with: documented the three service-worker build-id variables, registered the six retirement/tunnel tests with the mutation gate, approved `eslint-plugin-react-hooks` in the dependency allowlist, added the six `combo.sort.*` strings to `vi` and `pt-BR`, pointed the ChatGPT Web doc at the real migration-168 test, worded the g4f hint around the member key, and realigned four tests to the retired-provider catalog and the legacy-schema fixtures the retirement migrations touch. ([#11940](https://github.com/diegosouzapw/OmniRoute/pull/11940))
- **fix(providers):** Claude, Grok, LMArena, Notion, and Perplexity web-cookie transports now use pooled `wreq-js` 3.2 instead of the native sidecar, with all nine supported bindings pinned and audited, and the applicable platform binding plus native-license evidence included in each release artifact ([#12429](https://github.com/diegosouzapw/OmniRoute/pull/12429), supersedes [#11753](https://github.com/diegosouzapw/OmniRoute/pull/11753)).
- **fix(providers):** Zed Hosted streaming failures now trigger fallback before content and end partial streams with a sanitized structured error instead of fake assistant text and a normal-success stop. ([#12455](https://github.com/diegosouzapw/OmniRoute/pull/12455))
- **fix(test):** capture hook result after render (direct commit `b85d0abb0b`)
- **fix(sync):** repair the two regressions the v3.8.50 sync-back left on release/v3.8.51 (direct commit `5ade9e0851`)
- **revert(models):** drop the memo reset hook ported from #10055 (direct commit `282de841ae`)
- **fix(typecheck):** guard the optional connectionId before the reactive model sync (direct commit `f2825bad75`)
- **fix(oauth):** allow expired token retry before deactivation and activate expired retry loop (#P0) ([#11414](https://github.com/diegosouzapw/OmniRoute/pull/11414)) — thanks @HouMinXi
- **perf(executors):** lazy-load the executor registry — defer class imports + construction to first use (#11220) ([#11421](https://github.com/diegosouzapw/OmniRoute/pull/11421)) — thanks @oyi77
- **fix:** make release/v3.8.50 CI gates green (run 32786966560 root causes) ([#11450](https://github.com/diegosouzapw/OmniRoute/pull/11450)) — thanks @jonlwheat2-gif
- **fix(sse):** exact-domain cookie match and origin-equality URL assertions ([#11452](https://github.com/diegosouzapw/OmniRoute/pull/11452)) — thanks @hartmark
- **fix(providers):** send Responses API payload during OpenAI-compatible validation ([#11454](https://github.com/diegosouzapw/OmniRoute/pull/11454)) — thanks @tuandinh0801
- **fix(command-code):** fallback to /alpha/generate for Go plan without Provider API access ([#11455](https://github.com/diegosouzapw/OmniRoute/pull/11455)) — thanks @Chewji9875
- **fix(responses-continuation):** fail closed on a log-truncated stored input/output array ([#11473](https://github.com/diegosouzapw/OmniRoute/pull/11473)) — thanks @hartmark
- **fix(cli):** write jcode settings as [providers.omniroute] in config.toml ([#11484](https://github.com/diegosouzapw/OmniRoute/pull/11484)) — thanks @hongnoul
- **fix(logging):** raise chat-log array truncation cap to 1000 and unify duplicate implementations ([#11499](https://github.com/diegosouzapw/OmniRoute/pull/11499)) — thanks @hartmark
- **fix(mitm):** keep Windows DNS elevation off the POSIX sudo path (#11430) ([#11542](https://github.com/diegosouzapw/OmniRoute/pull/11542)) — thanks @official-burak
- **fix(sse):** scale chat admission by ingest byte budget instead of a fixed request count ([#11548](https://github.com/diegosouzapw/OmniRoute/pull/11548)) — thanks @TheDemonTuan
- **fix(providers):** mark Brave Search as no longer having a free tier ([#11621](https://github.com/diegosouzapw/OmniRoute/pull/11621)) — thanks @turbolego
- **fix:** pass tool result content through as string in OpenAI/Claude -> Gemini translation ([#11624](https://github.com/diegosouzapw/OmniRoute/pull/11624)) — thanks @Hsia97
- **fix(sse):** scope credential health to exact key ([#11628](https://github.com/diegosouzapw/OmniRoute/pull/11628)) — thanks @KaspaPulse
- **fix(security):** redact NVIDIA_API_KEY at the log sink in the ad-hoc diag script ([#11639](https://github.com/diegosouzapw/OmniRoute/pull/11639))
- **fix(types):** clear the two type regressions red on release/v3.8.51 ([#11640](https://github.com/diegosouzapw/OmniRoute/pull/11640)) — thanks @jonlwheat2-gif
- **fix(build):** resolve workspace: protocol dependencies to concrete semver versions during prepublish (#11540) ([#11641](https://github.com/diegosouzapw/OmniRoute/pull/11641)) — thanks @HouMinXi
- **fix(resilience):** lock permanently retired models instead of short backoff (Gemini ban prevention) ([#11762](https://github.com/diegosouzapw/OmniRoute/pull/11762)) — thanks @turbolego
- **fix:** mark Vercel AI Gateway as passthroughModels ([#11771](https://github.com/diegosouzapw/OmniRoute/pull/11771)) — thanks @Rahulsharma0810 / @Rahulsharma0810
- **fix(lease):** remove global static reservation and gate routing on live active lease occupancy ([#11775](https://github.com/diegosouzapw/OmniRoute/pull/11775)) — thanks @TheDemonTuan
- **fix(ci):** size the install-upgrade gate to a measured run, and log the pack cost ([#11776](https://github.com/diegosouzapw/OmniRoute/pull/11776))
- **fix(pwa):** stop serving the stale shell after deploys ([#11779](https://github.com/diegosouzapw/OmniRoute/pull/11779)) — thanks @HouMinXi
- **fix(combo):** lock GitHub models rejected as "not supported" for future requests ([#11781](https://github.com/diegosouzapw/OmniRoute/pull/11781)) — thanks @turbolego
- **fix(cli):** probe both IPv4 and IPv6 loopback for server readiness (#11766) ([#11794](https://github.com/diegosouzapw/OmniRoute/pull/11794)) — thanks @vermasomesh835
- **fix(providers):** honor model auto-fetch opt-in on create ([#11798](https://github.com/diegosouzapw/OmniRoute/pull/11798)) — thanks @RaviTharuma
- **fix(dashboard):** make model auto-fetch order independent ([#11805](https://github.com/diegosouzapw/OmniRoute/pull/11805)) — thanks @RaviTharuma
- **fix(docker):** make GHA cache exports best effort ([#11806](https://github.com/diegosouzapw/OmniRoute/pull/11806)) — thanks @RaviTharuma
- **fix(kiro):** do not permanently ban on 'User is not authorized to make this call' ([#11809](https://github.com/diegosouzapw/OmniRoute/pull/11809)) — thanks @Deftera186
- **fix(docs):** resolve relative markdown and wiki links across Fumadocs and GitHub wiki ([#11834](https://github.com/diegosouzapw/OmniRoute/pull/11834)) — thanks @AndrianBalanescu
- **fix(chat):** preserve unstripped model string for passthrough provider routing ([#11840](https://github.com/diegosouzapw/OmniRoute/pull/11840)) — thanks @raheemuddin786
- **fix(auth):** downgrade expected transient states from warn to debug ([#11937](https://github.com/diegosouzapw/OmniRoute/pull/11937)) — thanks @patrykkopycinski
- **fix(codex):** fail over image generation for imported free plans ([#11948](https://github.com/diegosouzapw/OmniRoute/pull/11948)) — thanks @Bl0ck154
- **fix(codex):** restore imported account state ([#11954](https://github.com/diegosouzapw/OmniRoute/pull/11954)) — thanks @Bl0ck154
- **fix(sse):** give extended-thinking targets the reasoning readiness budget ([#11959](https://github.com/diegosouzapw/OmniRoute/pull/11959)) — thanks @abhisheksharma2411
- **fix(dashboard):** use opaque background and readable text color on cost chart tooltips ([#11960](https://github.com/diegosouzapw/OmniRoute/pull/11960)) — thanks @ZaimMarzuki
- **fix(core):** resolve DB init race condition and reasoning translation ([#12003](https://github.com/diegosouzapw/OmniRoute/pull/12003)) — thanks @raheemuddin786
- **fix(admission):** exclude reclaimable page cache from the cgroup pressure ratio ([#12017](https://github.com/diegosouzapw/OmniRoute/pull/12017)) — thanks @HouMinXi
- **fix(build):** prune non-production trees in NFT trace excludes and tsconfig ([#12028](https://github.com/diegosouzapw/OmniRoute/pull/12028)) — thanks @Chewji9875
- **fix(sse):** default crash-guard logger to console.warn, not console ([#12042](https://github.com/diegosouzapw/OmniRoute/pull/12042)) — thanks @HouMinXi
- **fix(catalog):** derive vision/modalities for built-in auto combos from effective target pool ([#12046](https://github.com/diegosouzapw/OmniRoute/pull/12046)) — thanks @Prajeeth-12
- **fix(release):** the packaged-app smoke verifies the database opened, not a driver line the primary path never prints (twin of #12032) ([#12047](https://github.com/diegosouzapw/OmniRoute/pull/12047))
- **fix(barrel):** migrate src/app/ off the @/lib/localDb barrel import (#11795 Phase 2) ([#12051](https://github.com/diegosouzapw/OmniRoute/pull/12051)) — thanks @jonlwheat2-gif
- **fix(barrel):** migrate src/lib/ off the localDb barrel to direct db imports (#59) ([#12052](https://github.com/diegosouzapw/OmniRoute/pull/12052)) — thanks @jonlwheat2-gif
- **fix(barrel):** migrate open-sse, src/shared, src/sse, src/models, src/domain off the @/lib/localDb barrel import (#11795 Phase 4) ([#12053](https://github.com/diegosouzapw/OmniRoute/pull/12053)) — thanks @jonlwheat2-gif
- **fix(barrel):** delete the @/lib/localDb barrel — every consumer migrated (#11795 Phase 5) ([#12055](https://github.com/diegosouzapw/OmniRoute/pull/12055)) — thanks @jonlwheat2-gif
- **fix(radar):** restore D12 public boundary ([#12057](https://github.com/diegosouzapw/OmniRoute/pull/12057))
- **fix(ci):** accept CVE-2025-68121 in the prebuilt tls-client .so, auto-close base-red issues, guard Scorecard on the default branch ([#12085](https://github.com/diegosouzapw/OmniRoute/pull/12085))
- **fix(db):** drop three consumer-less 1proxy exports — dead-code base-red on release/v3.8.51 after the barrel deletion (#12055) ([#12087](https://github.com/diegosouzapw/OmniRoute/pull/12087))
- **fix(api):** clear the six API-route TypeScript regressions the new gate landed red on ([#12094](https://github.com/diegosouzapw/OmniRoute/pull/12094))
- **fix(release):** never let the tag-push Create Release append auto notes to the curated body ([#12096](https://github.com/diegosouzapw/OmniRoute/pull/12096))
- **fix(oauth):** bind Google refresh to the client that issued the token ([#12106](https://github.com/diegosouzapw/OmniRoute/pull/12106)) — thanks @HouMinXi
- **fix(dashboard):** make RequestLoggerDetail loadable outside Next — CSS via globals.css + CJS/ESM interop (#11703 base-reds) ([#12114](https://github.com/diegosouzapw/OmniRoute/pull/12114))
- **fix(leases):** project status lease row to lease columns so joined connection PII never escapes ([#12115](https://github.com/diegosouzapw/OmniRoute/pull/12115)) — thanks @geek007git
- **fix(plugins):** do not kill the plugin process when a fire-and-forget hook times out ([#12116](https://github.com/diegosouzapw/OmniRoute/pull/12116)) — thanks @geek007git
- **fix(plugins):** refresh stored manifest from disk on activate so new hook fields reach existing installs ([#12120](https://github.com/diegosouzapw/OmniRoute/pull/12120)) — thanks @geek007git
- **fix(codex):** preserve existing provider state when bulk-import upserts a matching connection ([#12122](https://github.com/diegosouzapw/OmniRoute/pull/12122)) — thanks @geek007git
- **fix(ci):** clear the two base-reds the 2026-08-30 merge batch left on release/v3.8.51 (round 3) ([#12123](https://github.com/diegosouzapw/OmniRoute/pull/12123))
- **fix(sse):** strip type:'custom' from Claude tools on agentrouter dispatch ([#12126](https://github.com/diegosouzapw/OmniRoute/pull/12126)) — thanks @wahidsadik371-coder
- **fix(sse):** stop advertising video providers the dispatcher cannot run ([#12131](https://github.com/diegosouzapw/OmniRoute/pull/12131)) — thanks @quiterunner-commits
- **fix(search):** treat HTTP 432 and plan limit errors as transient cooldown ([#12139](https://github.com/diegosouzapw/OmniRoute/pull/12139)) — thanks @HouMinXi
- **fix(sse):** refuse an AI Horde queue that cannot fit the request budget ([#12143](https://github.com/diegosouzapw/OmniRoute/pull/12143)) — thanks @quiterunner-commits
- **fix(ci):** clear the base-reds the afternoon merge batch left on release/v3.8.51 (round 5: provider count 352, TS2554/TS2677) ([#12144](https://github.com/diegosouzapw/OmniRoute/pull/12144))
- **fix(translator):** strip neutral tool_choice when tools absent in Responses-to-Chat (#12141) ([#12166](https://github.com/diegosouzapw/OmniRoute/pull/12166)) — thanks @HouMinXi
- **fix(guardrails):** pass providerId to getResolvedModelCapabilities in checkComboVision (#12112) ([#12169](https://github.com/diegosouzapw/OmniRoute/pull/12169)) — thanks @HouMinXi
- **fix:** prevent Claude Code session kills via liveness-aware readiness + auto model echo ([#12189](https://github.com/diegosouzapw/OmniRoute/pull/12189)) — thanks @opensource-elearning
- **fix(translator):** preserve falsy primitive values in Gemini and Antigravity function response results ([#12191](https://github.com/diegosouzapw/OmniRoute/pull/12191)) — thanks @Siva010
- **fix(oauth):** mark empty Antigravity projectId as degraded and clear stale errors (#11284) ([#12205](https://github.com/diegosouzapw/OmniRoute/pull/12205)) — thanks @HouMinXi
- **fix(providers):** gate the Codex auto-ping usage read on the shared quota throttle ([#12209](https://github.com/diegosouzapw/OmniRoute/pull/12209)) — thanks @abhisheksharma2411
- **fix(combos):** prioritize SQLite row id over inner JSON id and notify delete errors ([#12213](https://github.com/diegosouzapw/OmniRoute/pull/12213)) — thanks @HouMinXi
- **fix(providers):** mark featherless.ai as no longer having a free tier (`hasFree: false`) ([#12216](https://github.com/diegosouzapw/OmniRoute/pull/12216)) — thanks @turbolego
- **fix(deepseek-web):** stop Turbopack dev panic in the PoW worker path resolver ([#12221](https://github.com/diegosouzapw/OmniRoute/pull/12221)) — thanks @hartmark
- **fix(chat-admission):** clarify local 503 source ([#12223](https://github.com/diegosouzapw/OmniRoute/pull/12223)) — thanks @keeltrace
- **fix(system):** propagate abort signal to stream reader in HTTP version checks ([#12232](https://github.com/diegosouzapw/OmniRoute/pull/12232)) — thanks @raheemuddin786
- **fix(resilience):** isolate local host execution errors from provider circuit breakers ([#12233](https://github.com/diegosouzapw/OmniRoute/pull/12233)) — thanks @raheemuddin786
- **fix(combo):** always clear the loop-safety timer, not just on the happy path (#11804) ([#12245](https://github.com/diegosouzapw/OmniRoute/pull/12245))
- **fix(quality):** base-red pair — stryker tap registration + turn-pin suites aligned to the window gate ([#12255](https://github.com/diegosouzapw/OmniRoute/pull/12255)) — thanks @backryun
- **fix(combo):** fall back to full pool when collapsed sole survivor is context-too-small ([#12278](https://github.com/diegosouzapw/OmniRoute/pull/12278)) — thanks @opensource-elearning
- **fix(combo):** bound the pre-dispatch unavailable skip so a stale label cannot dark a pool (#12168) ([#12285](https://github.com/diegosouzapw/OmniRoute/pull/12285))
- **fix(security):** strip Qwen/Alibaba console-session cookies from provider API responses ([#12287](https://github.com/diegosouzapw/OmniRoute/pull/12287))
- **fix(usage):** console-aware Token Plan guidance + subscription hint on bailian 401 ([#12288](https://github.com/diegosouzapw/OmniRoute/pull/12288))
- **fix(resourcePressure):** log numeric detail on every rejection, recover faster ([#12293](https://github.com/diegosouzapw/OmniRoute/pull/12293)) — thanks @hartmark
- **fix(providers):** separate MaxAI and UC credential contracts ([#12431](https://github.com/diegosouzapw/OmniRoute/pull/12431))
- **fix(cli):** preserve Claude settings on config set ([#12432](https://github.com/diegosouzapw/OmniRoute/pull/12432)) — thanks @KrzysiekSko
- **fix(providers):** repair the maxai credential block truncated by merge auto-resolve ([#12433](https://github.com/diegosouzapw/OmniRoute/pull/12433))
- **fix(quality):** record the 2026-09-02 merged growth in the file-size baseline ([#12434](https://github.com/diegosouzapw/OmniRoute/pull/12434))
- **fix(uc):** route UC error strings through sanitizeErrorMessage; allowlist the retired codex id ([#12437](https://github.com/diegosouzapw/OmniRoute/pull/12437))
- **fix(sse):** remap non-contiguous upstream tool_calls index to a gap-free output_index ([#12445](https://github.com/diegosouzapw/OmniRoute/pull/12445)) — thanks @hartmark
- **fix(quality):** detect duplicate tool_calls entries in one response ([#12446](https://github.com/diegosouzapw/OmniRoute/pull/12446)) — thanks @hartmark
- **fix(conversations):** resolve turn content OmniRoute never sends back to the client ([#12447](https://github.com/diegosouzapw/OmniRoute/pull/12447)) — thanks @hartmark
- **fix(combo):** do not treat credits-exhausted 401 as auth skip ([#12449](https://github.com/diegosouzapw/OmniRoute/pull/12449)) — thanks @RaviTharuma
- **fix(auth):** do not park healthy quota accounts as expired ([#12452](https://github.com/diegosouzapw/OmniRoute/pull/12452)) — thanks @RaviTharuma
- **fix(responses-continuation):** fail closed on a collector-truncated, empty output array ([#12460](https://github.com/diegosouzapw/OmniRoute/pull/12460)) — thanks @hartmark
- **fix(logging):** raise the SSE payload collector's default cap ([#12461](https://github.com/diegosouzapw/OmniRoute/pull/12461)) — thanks @hartmark
- **fix(video):** re-anchor transcript log-redaction so PII/credential maskers can't reopen the leak (#12150 P1 follow-up) ([#12503](https://github.com/diegosouzapw/OmniRoute/pull/12503))
- **fix(monitoring):** serve cached credentialHealth off the request path ([#12533](https://github.com/diegosouzapw/OmniRoute/pull/12533)) — thanks @RaviTharuma
- **fix(quota):** keep Antigravity Gemini usable when Claude weekly is empty ([#12566](https://github.com/diegosouzapw/OmniRoute/pull/12566)) — thanks @HouMinXi
- **fix(authz):** hard-gate every credential export and CLI-config write (GHSA-5926-2w35-7h4q) ([#12600](https://github.com/diegosouzapw/OmniRoute/pull/12600))
- **fix(docs):** restore the Next build — REMOVED_PROVIDERS.md had no frontmatter (base-red #12581) ([#12610](https://github.com/diegosouzapw/OmniRoute/pull/12610))
- **fix(quality):** re-point the zcodeProtocol public-creds allowlist to line 313 ([#12615](https://github.com/diegosouzapw/OmniRoute/pull/12615))
- **fix(security):** close 3 advisories — search baseUrl exfil, sk- in the error sanitizer, bifrost relay header leak ([#12620](https://github.com/diegosouzapw/OmniRoute/pull/12620))
- **fix(providers):** sanitize boolean required and nested bare maps for Gemini (#12269) ([#12624](https://github.com/diegosouzapw/OmniRoute/pull/12624)) — thanks @HouMinXi
- **fix(resilience):** keep Overloaded STREAM_EARLY_EOF off the provider breaker ([#12626](https://github.com/diegosouzapw/OmniRoute/pull/12626)) — thanks @HouMinXi
- **fix(catalog):** re-audit free-tier quotas against official pages ([#12649](https://github.com/diegosouzapw/OmniRoute/pull/12649))
- **fix(dashboard):** keep a request's pending-tracking id stable across combo target retries ([#12650](https://github.com/diegosouzapw/OmniRoute/pull/12650)) — thanks @hartmark
- **fix(tests):** retire dead model ids from the chat-pipeline integration suite (base-red #12581) ([#12670](https://github.com/diegosouzapw/OmniRoute/pull/12670))
- **fix:** resolve SqliteError no such table compression_run_telemetry during cleanup ([#12682](https://github.com/diegosouzapw/OmniRoute/pull/12682)) — thanks @groovecityJO
- **fix(combo):** treat a pin-only step as implicit connection allowlist ([#12697](https://github.com/diegosouzapw/OmniRoute/pull/12697)) — thanks @HouMinXi
- **fix(ci):** ship .npmrc in published package so legacy-peer-deps applies to consumers (#11544) ([#12699](https://github.com/diegosouzapw/OmniRoute/pull/12699)) — thanks @KooshaPari
-**docs(readme):** reconcile live v3.8.50 provider, free-tier, CLI, routing, test, community, sponsor, acknowledgment, and SVG metrics with their audited source denominators, including a deduplicated OmniRoute-in-Action snapshot and distinct contributor rankings for merged pull requests, GitHub-attributed commits, and Git history ([#11356](https://github.com/diegosouzapw/OmniRoute/pull/11356)). ([#11434](https://github.com/diegosouzapw/OmniRoute/pull/11434)) — thanks @hartmark
- **docs:** sync the canonical provider count 354 → 356 across `README.md`, `AGENTS.md`, `llm.txt` (+ 42 i18n mirrors), the four README SVG diagrams, `docs/reference/PROVIDER_REFERENCE.md` (regenerated) and the `package.json` description after Opper (#11629) and 1min.ai (#11631) boarded the catalog — closes the `check:docs-counts-sync` strict drifts that kept `release/v3.8.51` red ([#11449](https://github.com/diegosouzapw/OmniRoute/issues/11449)). ([#11673](https://github.com/diegosouzapw/OmniRoute/pull/11673)) — thanks @jonlwheat2-gif
- **test(providers):** update count-derived assertions after the v3.8.51 provider additions — `APIKEY_PROVIDERS` 233 → 235 (Opper #11629 + 1min.ai #11631), reserved-prefix REGISTRY walk 395 → 398, `WEB_FETCH_PROVIDERS` now includes `nimble-search` (#11620), and the provider translate-path golden snapshot regenerated ([#11449](https://github.com/diegosouzapw/OmniRoute/issues/11449)). ([#11674](https://github.com/diegosouzapw/OmniRoute/pull/11674)) — thanks @jonlwheat2-gif
- **test(sse):** bump the hard-lease connection-query inventory for `src/lib/tokenHealthCheck.ts` to 2 — the verify-only web-cookie sweep added by #11495 split the single `getProviderConnections` call into oauth + cookie variants, which the frozen inventory had not tracked ([#11495](https://github.com/diegosouzapw/OmniRoute/pull/11495)). ([#11677](https://github.com/diegosouzapw/OmniRoute/pull/11677)) — thanks @jonlwheat2-gif / @oyi77
- **chore(release):** clear the `release/v3.8.51` base-red gates — docs migration count (+38 i18n mirrors), stryker `tap.testFiles`, lockfile registry host, stale ESLint suppressions, the 7 lint regressions they were hiding, the stale `APIKEY_PROVIDERS` partition count (231 → 233), the `glm-5.3-max` tier missing from the GLM test table, a dead `modelType === "chat"` comparison in the models catalog, and the `resolveLiveWsUrl` / `sanitizeLiveWsPort` helpers from #11388 that a later merge dropped from `wsPath.ts` (dashboard live WebSocket URL resolution) ([#11502](https://github.com/diegosouzapw/OmniRoute/pull/11502)) — thanks @MumuTW
- **chore(free-models):** the free-tier regime table now declares which totals figure each regime feeds and whether it may take the no-auth shortcut, so the sets that used to repeat those answers by hand are derived from it — a new `freeType` no longer compiles until it has answered every question, instead of silently contributing to no total ([#11537](https://github.com/diegosouzapw/OmniRoute/pull/11537)) — thanks @maxmad64bis
- **docs(routing):** LKGP strategy copy now states provider-level stickiness and the explicit rules fallback instead of promising per-target pinning ([#11555](https://github.com/diegosouzapw/OmniRoute/pull/11555)) — thanks @maxmad64bis
- **test(chatcore):** pin the response tool-name alias resolution against the ordering hazard that broke every Gemini/Antigravity MCP tool call in v3.8.49. `extractRequestToolIdentityMap` deletes `translatedBody._toolNameMap`, so the later read is always undefined and the ledger survives only through the `requestToolIdentityMap` fallback — removing that fallback previously left the entire tool-name suite green. The resolution moves into `resolveResponseToolNameMap()` next to the map it depends on, with a regression guard that fails without the recovery. No behaviour change. ([#11575](https://github.com/diegosouzapw/OmniRoute/pull/11575)) — thanks @amartinawi
- **docs(env):** document `OMNIROUTE_CORPUS_CACHE_SIZE` in `.env.example` and `ENVIRONMENT.md`, so the env/docs contract check stops failing Docs Gates on every branch ([#11576](https://github.com/diegosouzapw/OmniRoute/pull/11576)) — thanks @ntdatt812
- **chore(stryker):** register `route-guard-tunnel-processes-local-only` and `universal-quota-aware-routing` in `tap.testFiles`, so their mutant kills count for the three modules they cover ([#11577](https://github.com/diegosouzapw/OmniRoute/pull/11577)) — thanks @ntdatt812
- **test(authz):** pin `LOCAL_ONLY_API_GET_EXEMPTIONS` by exact membership instead of by entry count, so the guard names the offending path and also catches a substitution ([#11580](https://github.com/diegosouzapw/OmniRoute/pull/11580)) — thanks @ntdatt812
- **test(build):** pin `resolveNextBuildBundlerFlag` to the `OMNIROUTE_USE_TURBOPACK` contract it implements, across runtimes, instead of asserting an unimplemented Bun override ([#11583](https://github.com/diegosouzapw/OmniRoute/pull/11583)) — thanks @ntdatt812
- **test(claude-web):** the Claude Web transport test's barrel anchors no longer pin the exact construction spelling. #11421 made the executor map lazy, so `/"claude-web": new ClaudeWebExecutor\(\)/` stopped matching and the test went red on `release/v3.8.51` itself — a base-red gate every open PR inherited. The anchors now match the alias key and the class name and tolerate either spelling in between, and were checked to still fail when an alias is genuinely repointed at another executor ([#11585](https://github.com/diegosouzapw/OmniRoute/pull/11585)) — thanks @ntdat812
- **test(models):** pin `qwen3.8-max` resolution per provider — two of the four catalogs now serve the bare id and no longer carry `-preview` ([#11590](https://github.com/diegosouzapw/OmniRoute/pull/11590)) — thanks @ntdatt812
- **test(executors):** drop the stale 128-tool truncation assertion that contradicted the #11444 pass-through contract ([#11591](https://github.com/diegosouzapw/OmniRoute/pull/11591)) — thanks @ntdatt812
- **test(token-health):** pin the current terminal-skip boundary — expired with retry budget is probed, `account_deactivated` stays skipped ([#11592](https://github.com/diegosouzapw/OmniRoute/pull/11592)) — thanks @ntdatt812
- **test(models):** follow #11503's retarget of the `gemini-3-pro-high` alias to the hyphenated catalog id ([#11593](https://github.com/diegosouzapw/OmniRoute/pull/11593)) — thanks @ntdatt812
- **refactor(video bridge):** extract per-video acquisition, whole-result caching, description, and metrics/abort/cleanup out of `VideoBridgeGuardrail.preCall` into a `processVideoPart` seam in a new `videoBridgePipeline.ts`, behind explicit `VideoMediaBrokerPort`, `VideoAudioTranscriptionPort`, and `VideoDrilldownPort` boundaries; `preCall` now only handles request traversal, policy, and response aggregation. The Video tab's FFmpeg/ffprobe runtime status is now an explicit `unknown` / `restricted` / `unavailable` / `available` state instead of a nullable boolean pair, fixing a case where an in-flight or failed probe was mislabeled as "install FFmpeg" ([#11657](https://github.com/diegosouzapw/OmniRoute/issues/11657)). ([#12016](https://github.com/diegosouzapw/OmniRoute/pull/12016))
- **test(opencode-plugin):** add unit test coverage for `formatFreeBudget()` naming helper ([#11660](https://github.com/diegosouzapw/OmniRoute/pull/11660)) — thanks @f9td56dbgh-hub
- **docs(video):** clarify that the Video Bridge transcript `source` field (`client`, `embedded`, `audio-bridge`) is presently caller-declared and not yet server-verified — OmniRoute enforces the enum shape but does not cryptographically confirm that an `embedded`/`audio-bridge` label came from a server-owned extraction ([#11661](https://github.com/diegosouzapw/OmniRoute/issues/11661)). ([#12001](https://github.com/diegosouzapw/OmniRoute/pull/12001))
- **chore(providers):** retire the distributed Raycast Relay and Hailuo Web integrations after a provenance audit confirmed substantial derivation from GPL-3.0 sources; the official GitHub and MiniMax API providers remain available. Migration 163 disables legacy connections and invalidates their active leases while preserving connection IDs, audit/history rows, quota snapshots, usage records, and fail-closed API-key connection policies. ([#11691](https://github.com/diegosouzapw/OmniRoute/pull/11691))
- **chore(providers):** retire the Felo Web provider while its GPL-derived provenance remains on licensing HOLD ([#11698](https://github.com/diegosouzapw/OmniRoute/pull/11698)) — stale runtime and database references now fail closed while existing connection, lease, and usage history remains preserved for auditability.
- **fix(sse):** retire the Gemini Web image-generation bridge while provenance and licensing remain on HOLD, preserving Gemini Web chat/auth/tools and legitimate Gemini/Nano Banana image providers ([#11708](https://github.com/diegosouzapw/OmniRoute/pull/11708))
- **chore(audio):** retire the built-in EdgeTTS provider and its 11-voice catalog while provenance/licensing review remains on HOLD; the generic `/v1/audio/speech` endpoint and the other speech providers remain available ([#11711](https://github.com/diegosouzapw/OmniRoute/pull/11711))
- **fix(providers):** retire the unofficial Qwen Web integration and its `qwen-web`/`qw` identities while third-party provenance remains on HOLD ([#11713](https://github.com/diegosouzapw/OmniRoute/pull/11713)) — direct requests now fail closed with a sanitized HTTP 410 and combos skip the retired target, while migration guards preserve connection IDs, allowlists, usage/audit history and invalidate active leases. Supported Qwen API, Qwen Code, cloud, token-plan, audio, local and model-name surfaces remain available; restoring Qwen Web requires a qualified provenance/license decision.
- **fix(providers):** retire `microsoft-designer-web` and its `msdesigner` alias from runtime and catalogs while preserving stored credentials, provider history and allowlists as inactive records — source dependency on gpt4free's [`MicrosoftDesigner.py`](https://github.com/xtekky/gpt4free/blob/0943d16eef757a44deb60651c07bbe5fa958cafe/g4f/Provider/needs_auth/MicrosoftDesigner.py) is proven at snapshot `0943d16eef757a44deb60651c07bbe5fa958cafe`, whose [`LICENSE`](https://github.com/xtekky/gpt4free/blob/0943d16eef757a44deb60651c07bbe5fa958cafe/LICENSE) is GPL-3.0; expressive adaptation is probable, which records provenance/licensing risk without asserting a legal conclusion ([#11720](https://github.com/diegosouzapw/OmniRoute/pull/11720)).
- **docs(legal):** centralize pinned MIT notices for the vendored GCF codec and local flag assets ([#11726](https://github.com/diegosouzapw/OmniRoute/pull/11726))
- Split the 2,952-line `adobeFireflyClient.ts` into nine focused modules (catalog, credentials, payload, ARP session, upload, responses, IMS, account, poll) behind an unchanged barrel — no consumer edits and no public API change (#11728). — thanks @MumuTW
- **fix(dashboard):** replaced the Model Lockout card's unprovenanced notification MP3 with a short, locally synthesized Web Audio chime ([#11731](https://github.com/diegosouzapw/OmniRoute/pull/11731)) — both toggles retain optional audible feedback without shipping replacement media or third-party code, and unsupported, suspended, or rejected audio contexts fail open without blocking the setting change.
- **chore(deepseek-web):** remove the provenance-unresolved DeepSeek PoW WASM binary and its runtime loader/tracing while retaining the existing JavaScript solver (slower at high difficulty) ([#11732](https://github.com/diegosouzapw/OmniRoute/pull/11732)).
- **chore(assets):** remove four unused provider assets whose redistribution provenance could not be verified while retaining the active Freebuff SVG ([#11735](https://github.com/diegosouzapw/OmniRoute/pull/11735))
- **docs(assets):** retired two raster images whose redistribution provenance could not be verified ([#11736](https://github.com/diegosouzapw/OmniRoute/pull/11736)) — PicoClaw documentation now reuses the existing SVG, while Zoo Code remains a text link without an image.
- **docs(legal):** add pinned notices for six LobeHub-derived provider SVGs and 65 byte-exact theSVG assets, retaining registry claims as unverified metadata with explicit trademark and HOLD boundaries ([#11737](https://github.com/diegosouzapw/OmniRoute/pull/11737)).
- **chore(quality):** added a versioned 225/225 provider-asset provenance manifest and blocking drift gate ([#11743](https://github.com/diegosouzapw/OmniRoute/pull/11743)) — the inventory pins magic MIME and SHA-256 for every physical file, records immutable source matches for 71 assets, keeps 69 probable and 85 unresolved entries explicit but non-blocking, and treats provenance as source evidence rather than copyright or trademark clearance.
- **refactor(mitm):** replace four previously derived Traffic Inspector utilities — conversation normalization, SSE merging, secret masking, and header sanitization — with independent clean-room implementations based on public provider schemas, WHATWG SSE, and RFC 6750, while keeping the two independently classified passthrough surfaces unchanged ([#11748](https://github.com/diegosouzapw/OmniRoute/pull/11748)).
- Added a unit test that fails seven days before any dated pack under `config/` (`validUntil` and sibling keys) lapses, naming the file and key. The Alibaba free-tier pack expired on 2026-08-27 and turned every PR red the next morning with no commit involved; renewal now happens on someone's terms, not the clock's. ([#11891](https://github.com/diegosouzapw/OmniRoute/pull/11891))
- `check:workflows` now fails (under `--strict`/`--ratchet`) when any job routed to a self-hosted runner publishes with `--provenance` — npm rejects that with `422` at the registry, which in v3.8.50 only surfaced after the tag and Docker images were public. ([#11895](https://github.com/diegosouzapw/OmniRoute/pull/11895))
- `scripts/ops/runner-janitor.sh` now proves a path is idle with one `lsof` snapshot and removes stale leftovers itself (tmpfs after 3 h — it is RAM — disk after 24 h), kills orphan `next-build` processes, prunes checkouts of stopped runners, and alerts on memory pressure; `--dry-run` shows exactly what it would do. `docs/ops/RUNNER_BOX.md` reconciled to the measured box (31 GB, 10 listeners). ([#11893](https://github.com/diegosouzapw/OmniRoute/pull/11893))
- The `next-build` artefact (1.3 GB) is now written and read under `$RUNNER_TEMP` (per-runner, on disk) instead of `/tmp`, which on the self-hosted pool is a 12 GB tmpfs in RAM. Landing it there took 27–32 of the publish job's 76 minutes, and the fixed `/tmp/e2e-build.tar.gz` name let E2E jobs on different runners overwrite each other's download. ([#11896](https://github.com/diegosouzapw/OmniRoute/pull/11896))
- The CI `build` job now runs in two concurrency lanes — `main` and pull requests — so a release build is never queued behind (or OOM-killed beside) PR builds on the self-hosted pool, which holds one `next-build` comfortably and two at the edge. ([#11901](https://github.com/diegosouzapw/OmniRoute/pull/11901))
- Re-freeze the ESLint suppressions on `release/v3.8.51` from a clean-room measurement (2 stale file entries pruned, 55 pre-existing `no-explicit-any` in six new files frozen under #11924) and drop the dead `GPT_SIZE_MAP` constant orphaned by the Adobe Firefly client split, so `No new ESLint warnings` stops failing every PR with exit 2 (Refs #11924) ([#11955](https://github.com/diegosouzapw/OmniRoute/pull/11955))
- Type the 55 `no-explicit-any` sites that had been frozen under #11924 — four redundant casts in `socksConnectorWithFamily.ts` (undici/socks types already accept them) and the mocks/fixtures of the socks-timeout and isFree suites — and drop their suppression entries; the ESLint ratchet shrinks from 5487 to 5432 (Closes #11924) ([#11975](https://github.com/diegosouzapw/OmniRoute/pull/11975))
- Take the two hosted-runner builds off the PR rail: `Build App` (`build.yml`) is `workflow_dispatch`-only and `DAST smoke (PR)` runs only for PRs into `main` — the 7 GB hosted VM cannot build `release/v3.8.51` in any profile (19/30 red, VM shutdown ~8 min into `next build`) and both checks had turned into permanent noise on every release PR; the bundle stays validated by `ci.yml` on `main` and by `nightly-release-green` on `release/**` (Closes #11946) ([#11962](https://github.com/diegosouzapw/OmniRoute/pull/11962))
- Move the four nightly jobs that build the backend (`nightly-schemathesis`, `nightly-llm-security` promptfoo + garak, `nightly-resilience` axe-a11y) off the hosted 7 GB runner — where they died on `release/v3.8.51` unseen — onto the box's new `omni-light` pool (two listeners), and document the reshaped fleet (4 active OmniRoute listeners: 2 `omni-build` + 2 `omni-light`, janitor ceiling 4) (Closes #11965) ([#11967](https://github.com/diegosouzapw/OmniRoute/pull/11967))
- Stop painting every fork PR into `release/**` red: `quality.yml``Build (advisory)` is skipped (GitHub still reports `continue-on-error` failures as check FAILURE). Hosted `ubuntu-latest` cannot finish `npm run build` on this tree — same class as #11962 taking `build.yml` off the PR rail. `docker-publish.yml` amd64 now runs on the `.113``omni-build` pool (31 GB / 32 cores, two listeners) with Turbopack, shares the `heavy-build-main` lane with `ci.yml``Build` so it queues instead of becoming a third heavy, and keeps per-ref concurrency (a merge storm was starting 8 concurrent OOM builds). arm64 stays on `ubuntu-24.04-arm` with webpack — there is no ARM box. Fallback when `USE_VPS_RUNNER` is off: hosted amd64 + webpack (#11976). ([#12021](https://github.com/diegosouzapw/OmniRoute/pull/12021))
- `docker-publish.yml` builds with webpack (`OMNIROUTE_USE_TURBOPACK=0`) on **both** arches, including amd64 on the `.113``omni-build` pool. Turbopack had the RAM (31 GB, `omniroute-113-6`) and still panicked (`TurbopackInternalError: there must be a path to a root`, run 33253576569, 26 min in). The same tree's arm64 webpack build on hosted `ubuntu-24.04-arm` succeeded (run 33264823398). Dockerfile already documents webpack as the Docker escape hatch (#11976). ([#12050](https://github.com/diegosouzapw/OmniRoute/pull/12050))
- **docs(free-tier):** declare the counting vs deciding regimes for "is it free?" and guard the deciding path from DB-backed catalog resolution ([#12226](https://github.com/diegosouzapw/OmniRoute/pull/12226)) — thanks @maxmad64bis
- **docs(auto-combo):** The mode pack table in `docs/routing/AUTO-COMBO.md` now lists all six shipped packs with every weight each one sets, replacing a four-pack table whose numbers had also drifted from the source. It states plainly that no pack sets `quality`, so selecting any pack silences the observed-quality signal. Six more documents that quote the scoring factor count joined the `check:docs-counts` gate, which caught five stale claims — including one naming nine factors that do not exist — and two stale mode pack counts. The dashboard routing panel, which offered four of the six packs and labelled the default strategy "6-Factor Scoring", is now covered by a test; the two packs it was missing are `reliability-first` and `chaos-mode`, the latter labelled as the fault-injection profile it is rather than as one more routing preference ([#12316](https://github.com/diegosouzapw/OmniRoute/pull/12316)) — thanks @maxmad64bis
- **chore(quality):** rebaseline `src/lib/db/apiKeys.ts` for the ACL the key-creation path now preserves ([#12352](https://github.com/diegosouzapw/OmniRoute/pull/12352)) ([#12673](https://github.com/diegosouzapw/OmniRoute/pull/12673)) — thanks @KrzysiekSko
- **chore(providers):** bump the Claude Code wire identity and the Devin bridge image pin from `2.1.220` to `2.1.258` ([#12402](https://github.com/diegosouzapw/OmniRoute/pull/12402)) — thanks @ggiak ([#12604](https://github.com/diegosouzapw/OmniRoute/pull/12604))
- **docs(env):** align `.env.example`, the README Bun section, and the troubleshooting guide with the code: `OMNIROUTE_USE_TURBOPACK` also governs `npm run build` (not dev-only), `bun run build` follows that flag instead of auto-selecting Webpack, `OMNIROUTE_CHAT_MAX_HEAVY_IN_FLIGHT` is unset by default (no request-count cap), and the structural `503 chat_admission_busy` message matches `chatAdmissionResponses.ts` (#12404 — thanks @pacocartones)
- **chore(electron):** upgrade the desktop app to Electron 44 (Chromium 152, Node 24.18.1) ([#12217](https://github.com/diegosouzapw/OmniRoute/pull/12217)). **Requires macOS 13 (Ventura) or later** — Chromium dropped macOS 12 (Monterey), so Monterey users must stay on an earlier OmniRoute desktop build. Windows and Linux are unaffected; the app already shipped only x64/arm64, so Electron 44 dropping 32-bit builds changes nothing. Removes the `openAsHidden`/`wasOpenedAsHidden` login-item fields deleted in Electron 44 — hidden autostart continues to work through the `--hidden` argument registered with the login item ([#12554](https://github.com/diegosouzapw/OmniRoute/pull/12554)) — thanks @app/dependabot
- **chore(quality):** rebaseline `src/sse/handlers/chat.ts` for the effective-input persistence the continuation fix needs ([#12641](https://github.com/diegosouzapw/OmniRoute/pull/12641)) ([#12680](https://github.com/diegosouzapw/OmniRoute/pull/12680)) — thanks @hartmark
- `Coverage` job on `ci.yml`: the informational Codecov upload gets its own 5-minute ceiling and `continue-on-error`, and the job budget grows from 20 to 30 minutes (the 8-shard c8 merge alone takes ~10) — a stalled upload no longer ends the job `cancelled` and drags a fully green `main` run's conclusion down with it ([#11972](https://github.com/diegosouzapw/OmniRoute/pull/11972))
- CI hardening on the PR rail: the four `Unit Tests fast-path` shards get `timeout-minutes: 30` (a hung shard held a PR for 64 min instead of GitHub's 6 h default) and both ESLint file caches lose their `restore-keys` fallback, so a cache built under another suppressions file or lint config can no longer report stale verdicts (Refs #11600, #11924) ([#11963](https://github.com/diegosouzapw/OmniRoute/pull/11963))
- Every CI job that runs a `next build` (`build`, the npm `publish`, both release-green validations) now targets the `omni-build` runner label, which only two of the eight self-hosted runners carry. The box holds one build comfortably and two at the edge; a third now queues on GitHub instead of being OOM-killed by the kernel. ([#11932](https://github.com/diegosouzapw/OmniRoute/pull/11932))
- **refactor(combo):** move `handleRoundRobinCombo` (and `resolveTargetTokenLimit`) into `open-sse/services/combo/roundRobinCombo.ts`. `combo.ts` drops from 2164 to 1014 lines (`split("\n").length`); the leaf is 1199 (under the 1200 new-file cap). The round-robin call site uses a dynamic `import()` so `releaseStickyPinOnFailure` / `clearStaleLKGP` can stay exported from `combo.ts` without a static cycle. Skip / sticky / semaphore / safety-timer behavior is unchanged. ([#12811](https://github.com/diegosouzapw/OmniRoute/pull/12811)) — thanks @HouMinXi
- **chore(quality):** rebaseline the file-size caps the error-boundary campaign grew past (`open-sse/executors/codex.ts`, `open-sse/vendor/codex-chatgpt-web/bridge.ts`, both via [#12444](https://github.com/diegosouzapw/OmniRoute/pull/12444)) ([#12654](https://github.com/diegosouzapw/OmniRoute/pull/12654))
- **chore(quality):** rebaseline the file-size caps the hartmark batch grew past (`combos/page.tsx` via [#12355](https://github.com/diegosouzapw/OmniRoute/pull/12355), `open-sse/services/combo.ts` via [#12338](https://github.com/diegosouzapw/OmniRoute/pull/12338)) ([#12623](https://github.com/diegosouzapw/OmniRoute/pull/12623)) — thanks @hartmark
- **chore(quality):** rebaseline the file-size caps the HouMinXi batch grew past when its PRs stacked (`providers/page.tsx`, `chatCore.ts`, `accountFallback.ts`) — each PR measured correctly in isolation, none saw the stacking ([#12619](https://github.com/diegosouzapw/OmniRoute/pull/12619))
- **chore(quality):** rebaseline `open-sse/services/combo.ts` for the reset-aware scoring the HouMinXi batch stacked ([#12637](https://github.com/diegosouzapw/OmniRoute/pull/12637)) ([#12678](https://github.com/diegosouzapw/OmniRoute/pull/12678)) — thanks @HouMinXi
- **chore(ci):** point the circular-deps gate at dpdm's real JS entrypoint ([#11615](https://github.com/diegosouzapw/OmniRoute/pull/11615)) — thanks @benzntech
- **chore(quality):** rebaseline file-size for #11448/#11495/#11561 growth ([#11630](https://github.com/diegosouzapw/OmniRoute/pull/11630))
- **test(autoCombo):** port models_dev_tier #11508 guard from node:test to vitest ([#11635](https://github.com/diegosouzapw/OmniRoute/pull/11635)) — thanks @jonlwheat2-gif
- **chore(quality):** rebaseline file-size for #11083/#11631/#11628 growth ([#11636](https://github.com/diegosouzapw/OmniRoute/pull/11636))
- **chore(quality):** tighten complexity/cognitive-complexity ratchets to the current tip; land the missed gateways.ts rebaseline ([#11771](https://github.com/diegosouzapw/OmniRoute/pull/11771)) — thanks @Rahulsharma0810 / @Rahulsharma0810
- **docs(i18n):** finish Freepik → Magnific rebrand in locale strings and README ([#11772](https://github.com/diegosouzapw/OmniRoute/pull/11772)) — thanks @turbolego
- **refactor(auto-combo):** fix divergent scoring in combo health reporting ([#11854](https://github.com/diegosouzapw/OmniRoute/pull/11854)) — thanks @jacobsparts
- **chore(changelog):** add missing fragments for #11919/#11918/#11916 ([#11938](https://github.com/diegosouzapw/OmniRoute/pull/11938))
- **test(check):** escape the runs-on fixture with JSON.stringify, not a quote-only replace ([#11942](https://github.com/diegosouzapw/OmniRoute/pull/11942)) (direct commit `fb7445eaa3`)
- **test(release):** align five suites with the contracts #11933, #11919 and #11876 shipped on release/v3.8.51 ([#11944](https://github.com/diegosouzapw/OmniRoute/pull/11944))
- **chore(quality):** remove unreachable code and restore test discovery ([#11950](https://github.com/diegosouzapw/OmniRoute/pull/11950)) — thanks @backryun
- **docs(agents):** sync-back landings are fast-forward, never squash ([#11964](https://github.com/diegosouzapw/OmniRoute/pull/11964))
- **test(infra):** retry recursive temp-dir removal instead of failing a shard on ENOTEMPTY (#11966) ([#11968](https://github.com/diegosouzapw/OmniRoute/pull/11968))
- **docs(ops):** the .113 heavy-build ceiling is one runner, not two ([#12048](https://github.com/diegosouzapw/OmniRoute/pull/12048))
- **test(providers):** regenerate the translate-path golden for OrcaRouter (#11923) ([#12118](https://github.com/diegosouzapw/OmniRoute/pull/12118))
- **chore(quality):** velocity phase — loosen every numeric baseline by 20% until v4.0, monitor headroom nightly ([#12125](https://github.com/diegosouzapw/OmniRoute/pull/12125))
- **chore(lint):** batch 0 of #12146 — type the call-log-cap sqlite rows instead of 45 as-any casts ([#12157](https://github.com/diegosouzapw/OmniRoute/pull/12157))
- **chore(lint):** batch 2 of #12146 — resolve the react-hooks compiler violations in dashboard/providers ([#12163](https://github.com/diegosouzapw/OmniRoute/pull/12163))
- **chore(quality):** register search-432 cooldown test in stryker tap.testFiles ([#12170](https://github.com/diegosouzapw/OmniRoute/pull/12170))
- **chore(lint):** batch 5 of #12146 — combos, endpoint, provider-stats, api-manager and costs react-hooks violations resolved ([#12174](https://github.com/diegosouzapw/OmniRoute/pull/12174))
- **build:** add contributor fast profile ([#12192](https://github.com/diegosouzapw/OmniRoute/pull/12192)) — thanks @rafacpti23
- **build:** force the webpack bundler in the contributor build profile ([#12197](https://github.com/diegosouzapw/OmniRoute/pull/12197)) — thanks @rafacpti23
- **build:** skip standalone packaging in the contributor profile ([#12198](https://github.com/diegosouzapw/OmniRoute/pull/12198)) — thanks @rafacpti23
- **docs(audit):** align every published number with the code and harden check:docs-counts ([#12200](https://github.com/diegosouzapw/OmniRoute/pull/12200))
- **build:** stub the instrumentation entrypoints in the contributor profile ([#12203](https://github.com/diegosouzapw/OmniRoute/pull/12203)) — thanks @rafacpti23
- **build:** omit the standalone output target for contributor builds ([#12204](https://github.com/diegosouzapw/OmniRoute/pull/12204)) — thanks @rafacpti23
- **chore(lint):** batch 6 of #12146 — memory, radar, audit, analytics, cache, usage, activity, home and RequestLoggerV2 react-hooks violations resolved ([#12208](https://github.com/diegosouzapw/OmniRoute/pull/12208))
- **docs(diagrams):** rename number-carrying diagram files to stable names ([#12210](https://github.com/diegosouzapw/OmniRoute/pull/12210))
- **docs(dashboard):** redraw onboarding tier-flow SVGs for the real 4-tier model ([#12211](https://github.com/diegosouzapw/OmniRoute/pull/12211))
- **docs(api):** document every implemented route in openapi.yaml (276 → 692 paths) ([#12212](https://github.com/diegosouzapw/OmniRoute/pull/12212))
- **chore(lint):** batch 7 of #12146 — final src tail: 37 react-hooks violations across 33 files resolved ([#12244](https://github.com/diegosouzapw/OmniRoute/pull/12244))
- **chore(proxy):** purge the legacy 1proxy residue — sync/rotator modules, dead DB exports, dead settings tab and flag, docs (#12091) ([#12290](https://github.com/diegosouzapw/OmniRoute/pull/12290))
- **chore(quality):** baseline-headroom skips generated and vendored files in the fileSize worst-file signal ([#12291](https://github.com/diegosouzapw/OmniRoute/pull/12291))
- **refactor(video):** unify the JPEG frame data-URI contract ([#12322](https://github.com/diegosouzapw/OmniRoute/pull/12322))
- **chore(deps):** freeze onnxruntime-node and eslint-plugin-react-hooks out of dependabot groups ([#12329](https://github.com/diegosouzapw/OmniRoute/pull/12329))
- **chore(quality):** re-tighten the file-size ratchet to the real LOC (plan 3.8.52 task 0) ([#12411](https://github.com/diegosouzapw/OmniRoute/pull/12411))
- **test(grok):** format web executor suite ([#12412](https://github.com/diegosouzapw/OmniRoute/pull/12412))
- **chore(quality):** ratchet open-sse typecheck baseline to zero ([#12418](https://github.com/diegosouzapw/OmniRoute/pull/12418))
- **test(build):** guard the artifact path policy arrays against duplicates ([#12422](https://github.com/diegosouzapw/OmniRoute/pull/12422))
- **chore(providers):** remove a keyless provider integration at its operator's request ([#12440](https://github.com/diegosouzapw/OmniRoute/pull/12440))
- **docs(providers):** register providers removed at their operator's request and guard against reintroduction ([#12478](https://github.com/diegosouzapw/OmniRoute/pull/12478))
- **docs(arch):** one-process recipe for tens of long /v1/responses ([#12493](https://github.com/diegosouzapw/OmniRoute/pull/12493)) — thanks @RaviTharuma
- **chore(quality):** tighten the CodeQL ratchet baseline from 11 to 6 ([#12530](https://github.com/diegosouzapw/OmniRoute/pull/12530))
- **chore(deps):** bump fast-uri to 3.1.7 in the electron lockfile ([#12601](https://github.com/diegosouzapw/OmniRoute/pull/12601))
- **docs(quality):** document how the CodeQL ratchet refreshes and how to tighten it ([#12611](https://github.com/diegosouzapw/OmniRoute/pull/12611))
- **test(ci):** pin the openapi-security-tiers two-arm contract with an executing gate test (#12581) ([#12652](https://github.com/diegosouzapw/OmniRoute/pull/12652))
- **docs(gamification):** align XP Rewards table with code (#12501) ([#12667](https://github.com/diegosouzapw/OmniRoute/pull/12667)) — thanks @KooshaPari
- **refactor(combo):** split executeTarget into gates, attempt, and loop ([#12746](https://github.com/diegosouzapw/OmniRoute/pull/12746)) — thanks @HouMinXi
- **docs(security):** document socket.yml scanner config + CI workflow link (#12575) ([#12764](https://github.com/diegosouzapw/OmniRoute/pull/12764)) — thanks @KooshaPari
- **chore(ci):** guard commit identity in pre-commit to stop author misattribution ([#12772](https://github.com/diegosouzapw/OmniRoute/pull/12772))
- **deps:** 17 Dependabot bumps — bump electron from 43.4.0 to 43.4.1 in /electron ([#11426](https://github.com/diegosouzapw/OmniRoute/pull/11426)); bump the development group across 1 directory with 8 updates ([#11428](https://github.com/diegosouzapw/OmniRoute/pull/11428)); bump the production group across 1 directory with 11 updates ([#11440](https://github.com/diegosouzapw/OmniRoute/pull/11440)); chore(deps): bump github/codeql-action/init from 4.37.7 to 4.37.8 ([#11925](https://github.com/diegosouzapw/OmniRoute/pull/11925)); chore(deps): bump github/codeql-action from 4.37.7 to 4.37.8 ([#11926](https://github.com/diegosouzapw/OmniRoute/pull/11926)); chore(deps): bump github/codeql-action/analyze from 4.37.7 to 4.37.8 ([#11927](https://github.com/diegosouzapw/OmniRoute/pull/11927)); build(deps): bump github/codeql-action/init from 4.37.8 to 4.37.9 ([#12345](https://github.com/diegosouzapw/OmniRoute/pull/12345)); build(deps): bump github/codeql-action/analyze from 4.37.8 to 4.37.9 ([#12346](https://github.com/diegosouzapw/OmniRoute/pull/12346)); bump the development group across 1 directory with 2 updates ([#12347](https://github.com/diegosouzapw/OmniRoute/pull/12347)); build(deps): bump github/codeql-action from 4.37.8 to 4.37.9 ([#12349](https://github.com/diegosouzapw/OmniRoute/pull/12349)); bump browserslist from 4.28.2 to 4.28.8 ([#12396](https://github.com/diegosouzapw/OmniRoute/pull/12396)); bump the production group across 1 directory with 4 updates ([#12399](https://github.com/diegosouzapw/OmniRoute/pull/12399)); bump @xmldom/xmldom ([#12500](https://github.com/diegosouzapw/OmniRoute/pull/12500)); bump qs from 6.15.2 to 6.16.0 ([#12512](https://github.com/diegosouzapw/OmniRoute/pull/12512)); bump @xmldom/xmldom from 0.9.10 to 0.9.12 ([#12513](https://github.com/diegosouzapw/OmniRoute/pull/12513)); bump fast-uri from 3.1.5 to 3.1.7 ([#12514](https://github.com/diegosouzapw/OmniRoute/pull/12514)); bump @humanfs/node from 0.16.7 to 0.16.8 ([#12515](https://github.com/diegosouzapw/OmniRoute/pull/12515))
_Living section — regenerated 2026-08-12 from all cycle commits (cycle open `ed2db6cb19` → tip). Bullets carry the merged PR and its author; direct pushes listed separately._
<tr><td nowrap><b>Language</b></td><td>TypeScript 6.0 — <b>100% TypeScript</b> across <code>src/</code> and <code>open-sse/</code> (zero <code>any</code> in core since v2.0)</td></tr>
- **feat(routing):** subscription-first auto groupings — `auto/subscription` routes only through plan-included connections with a documented hard-stop overage and fails closed on exhaustion, while `auto/thrifty` orders the pool `subscription → keyless → free → cheap → premium` and steps up one rung at a time as each is exhausted. Billing class comes from a curated per-connection catalog (uncurated is treated as metered, never plan-included), both reuse STRICT_ZERO_COST's per-connection verification, and a quota reading whose `resetAt` has passed is now refreshed regardless of TTL so routing returns to plan capacity as soon as it resets ([#11146](https://github.com/diegosouzapw/OmniRoute/pull/11146))
- **feat(video):** add an opt-in focused analysis mode that safely uses a normalized, 500-code-point latest-user hint for task-aware frame captions while preserving full-mode prompts, temporal-window isolation, and cache identity without storing raw task text ([#11383](https://github.com/diegosouzapw/OmniRoute/pull/11383)).
- **feat(dashboard):** surface durable exclusive managed leases in the existing Sessions view, keeping leased clients visible across idle gaps while marking connections with in-flight work as active ([#11389](https://github.com/diegosouzapw/OmniRoute/pull/11389)) — thanks @KaspaPulse
- **build(bun):** allow Turbopack bundler flag on Bun 1.4+ with configurable Webpack fallback ([#11471](https://github.com/diegosouzapw/OmniRoute/pull/11471)) — thanks @TheDemonTuan
- feat(api): add an opt-in `modelVisibilityAllowlist`/`modelVisibilityDenylist` settings pair to curate exactly which models `/v1/models` advertises, mirrored into every `auto/*` combo candidate pool so a denied model cannot be routed to via combo selection either (#11481)
- **feat(rankings):** the Free Provider Rankings page shows what each provider actually served over the last 24 h. It ranked by ELO alone, which left a provider that answers every call with an error in first place; the usage data was already served by the API but never requested. A provider with too small a sample shows a dash, not a number ([#11546](https://github.com/diegosouzapw/OmniRoute/pull/11546))
- **feat(guardrails):** enforce a bounded, deterministic contract for Video Bridge transcripts — 256 cues, 4096 input code units and 4 KiB UTF-8 per cue, 64 KiB total text, malformed-Unicode rejection, focus-window scoping, cross-source reconciliation with contributing-source metadata, and a structural provenance trust boundary so caller JSON can never self-assert `embedded`/`audio-bridge` provenance ([#11652](https://github.com/diegosouzapw/OmniRoute/issues/11652))
- **feat(video):** orchestrate optional Video Bridge audio extraction and Audio Bridge STT behind a dual opt-in (operator setting AND per-request signal) — a new loopback-only broker `mode=audio` operation shares the frame path's exact process queue, deadline, AbortSignal, and byte budgets to extract a bounded mono 16 kHz PCM WAV from the same already-downloaded video, then reuses the existing Audio Bridge transcription boundary; provider segment timing is preserved when available and marked coarse otherwise, and every failure degrades to a visual-only-safe partial instead of throwing (#11654).
- **test(video):** Add the Video Bridge FU-07/FU-09 promotion-evidence harness (#11656) — a frozen Zod manifest schema covering the 8 required scenario kinds (static scenes, rapid cuts, late facts, fades, blur, small text, close events, visual prompt injection) with a minimum of 3 repetitions per case, deterministic declarative fixture recipes (`videoBridgePromotionFixtures.ts`), a pure medians/p95 metrics aggregator, a pure FU-07/FU-09 promotion-verdict evaluator applying the ticket's exact thresholds (missing token usage always holds), a digest-only persistence layer that never retains raw media or raw model responses, and a versioned per-model promotion allowlist shipped empty with every model defaulting to `hold`. The FU-07/FU-09 promotion verdicts themselves remain HOLD — they require a real evidence run against real models on VPS 192.168.0.15.
- **feat(video bridge):** "embedded" transcript provenance can now be legitimately earned instead of merely asserted — a bounded, allowlisted (`mov_text`/`subrip`/`webvtt`) subtitle probe runs through the loopback-only Video Bridge broker (at most 2 streams, 10s subdeadline bounded by the request deadline, 256 KiB output, 4096-code-unit lines), normalized through a bounded, ReDoS-safe WebVTT parser and Zod-validated end to end. The adapter always resolves to an explicit `success`/`absent`/`transient_failure` outcome — a subtitle failure never breaks the visual description path, and only a fingerprint-verified broker response (never a caller-declared label) can produce embedded cues (#11659).
- Default new Antigravity-family connections (agy CLI imports and Antigravity OAuth connects) to model auto-sync, so live model discovery lands in the synced catalog and `/v1/models` picks up freshly released upstream models (e.g. Gemini 3.7 Flash tiers) without code changes. Existing connections keep their current setting; the per-connection dashboard toggle remains the opt-out. (#11685 — thanks @MumuTW)
- **feat(providers):** add SeekAi (`seekai.cc`) as an OpenAI-compatible New-API gateway — catalog id `seekai` (alias `ska`), `https://seekai.cc/v1`, live `/v1/models` via `passthroughModels`, aggregator-list membership so New-API balance detection can opt in. No referral/aff codes. ([#11786](https://github.com/diegosouzapw/OmniRoute/issues/11786))
- **feat(zai):** add GLM-5.3-Flash Coding Plan support (1M context, 128K output, vision, `low|high|max` reasoning) and route `zai` GLM-5.3-family API-key traffic through the OpenAI-compatible Coding Plan endpoint with native thinking defaults ([#11801](https://github.com/diegosouzapw/OmniRoute/pull/11801)) — thanks @Neuron-Mr-White
- **feat(combo):** choose how combo models are ordered — manual, provider, score, or name — via a sort control in the dashboard builder, persisted in `config.modelSort` and re-applied on load and after add ([#11812](https://github.com/diegosouzapw/OmniRoute/pull/11812)) — thanks @maxmad64bis
- **feat(free):** custom models can be marked free-tier via `customModels[].isFree`; `isFreeModel()` is the first door and `hidePaidModels` respects it even for providers outside the free budget ([#11843](https://github.com/diegosouzapw/OmniRoute/pull/11843))
- **feat(nodejs):** add `5dive` as a `configure` target — `omniroute configure 5dive` / `omniroute setup-5dive` write a 5dive auth profile that points an agent fleet's `claude` seats at OmniRoute, with the root-only write, the loopback-vs-`https` endpoint rule and the per-seat model pin handled explicitly ([#11852](https://github.com/diegosouzapw/OmniRoute/pull/11852))
- **feat(sse):** treat `max` as a first-class reasoning-effort tier and clamp per model family (GLM 5.1+/DeepSeek V4+/Kimi K3+ keep native `max`; o1/MiniMax/Grok/Muse Spark clamp to their upstream ceiling) ([#11875](https://github.com/diegosouzapw/OmniRoute/pull/11875)) — thanks @Chewji9875
- **feat(providers):** the provider plugin manifest now advertises a `usage-fetch` capability for the 40 providers that have a wired usage/quota fetcher, so external dashboards can read it from `GET /api/v1/provider-plugin-manifest` instead of parsing `open-sse/services/usage.ts` after every release. Discovery only — no new fetcher, no quota change, and the Dashboard quota widget stays gated by `USAGE_SUPPORTED_PROVIDERS`. `USAGE_FETCHER_PROVIDERS` moved to a zero-dependency leaf (`open-sse/services/usage/fetcherProviders.ts`) and is re-exported from `services/usage.ts`, keeping the manifest module a light leaf instead of pulling the ~490-module usage dispatcher into the manifest route. ([#11903](https://github.com/diegosouzapw/OmniRoute/pull/11903)) — thanks @maxmad64bis
- **feat(plugins):** `OMNIROUTE_PLUGINS_DIR` sets the directory the runtime plugin scanner reads — and the root the plugin manager installs into — overriding the `HOME`-derived default, so a Docker/K8s deployment can point straight at its bind-mounted plugin tree instead of moving `HOME` just to relocate the scan path. An image that exports no home no longer scans `/tmp/.omniroute/plugins` in silence: the resolved directory is logged once at startup as `scanner.dir_resolved`, naming the input that won. Unset, behaviour is unchanged. Distinct from the CLI-only `OMNIROUTE_PLUGIN_PATH`, which finds `omniroute-cmd-*` command packages and never reached this scanner ([#11906](https://github.com/diegosouzapw/OmniRoute/pull/11906)) — thanks @amaleta
- **feat(leases):** add an explicit owner-authenticated status action that returns only the active lease's privacy-safe configured connection and provider labels, with generation fencing and no credential or internal-id disclosure ([#11910](https://github.com/diegosouzapw/OmniRoute/pull/11910)) — thanks @KaspaPulse
- **feat(providers):** import-from-file modal shows per-row API errors and ships a downloadable CSV template ([#12071](https://github.com/diegosouzapw/OmniRoute/issues/12071))
- **feat(providers):** dashboard search matches connection name and `baseUrl` so imported OpenAI-compat nodes surface on the provider card ([#12108](https://github.com/diegosouzapw/OmniRoute/issues/12108))
- **feat(providers):** the provider plugin manifest now also advertises a `usage-supported` capability for the 46 providers whose usage API is accepted by the server and Dashboard routes, so integrators can distinguish "the server will serve quota for this provider" from "a fetcher is wired" without reading TypeScript. Discovery only — no fetcher or quota change. `usage-fetch` resolves on id or alias (the usage dispatcher accepts both); `usage-supported` resolves on id alone, matching the runtime guard `USAGE_SUPPORTED_PROVIDERS.includes(providerId)`. `USAGE_SUPPORTED_PROVIDERS` moved to a zero-dependency leaf (`open-sse/services/usage/supportedProviders.ts`) and is re-exported from `providers.ts`, mirroring the `fetcherProviders` leaf from #11903 and keeping the manifest a light module. ([#12214](https://github.com/diegosouzapw/OmniRoute/pull/12214)) — thanks @maxmad64bis
- **feat(rankings):** order Free Provider Rankings by what each provider actually served — `GET /api/free-provider-rankings?sortBy=reliability` and a "Most reliable first" toggle on the page. Providers with too few calls to state a success rate keep their score order below the measured ones; the default order is unchanged ([#12218](https://github.com/diegosouzapw/OmniRoute/pull/12218)).
- **perf(sse):** defer `cloneLogPayload()` in the structured SSE collector until after the `maxEvents`/`maxBytes` cap check, eliminating ~9,800 wasted `structuredClone` calls per streaming response (65–71% faster `push()`). Reducer snapshot isolation restored for OpenAI and Responses summaries ([#12241](https://github.com/diegosouzapw/OmniRoute/pull/12241)) — thanks @PauloHSOliveira
- **feat(settings):** persist `headroomUrl` through Settings so status/start use the operator URL instead of only `HEADROOM_URL` ([#12306](https://github.com/diegosouzapw/OmniRoute/issues/12306))
- **feat(auto-combo):** Auto-Combo scoring can now weigh how often a provider/model has actually succeeded. The engine already carried that number on every candidate — 24 hours of usage history behind a ten-sample floor, real-time metrics otherwise — and the scoring function never read it, while the weight table described `stability` as if it did. `reliability` (`1 - failureRate`, with the same field precedence and the same rate-bounding the speed ranking already uses, so a corrupt reading means "nothing observed" rather than "fails every call") is now a declared factor shipping at weight `0`, so routing is unchanged until an operator gives it one, and the `stability` description now matches what that factor computes ([#12317](https://github.com/diegosouzapw/OmniRoute/pull/12317))
- **feat(routing):** With `freeAccessPolicy: "strict"`, the read-only candidate listing (`GET /v1/auto-combo/{channel}/candidates`) no longer hides the candidates the zero-cost guard excludes — the same read-only transparency the resilience filter already honours (#9133). Each candidate now carries `freeAccessExclusion` saying why it would be kept out, and it tells an exhausted allowance apart from a quota reading that never arrived or went stale, which used to look identical from the outside. Routing is unchanged: the listing reports, it never enforces. The separate `excludeTosAvoid` guard still drops its candidates without a reason; that gap is now documented rather than closed ([#12319](https://github.com/diegosouzapw/OmniRoute/pull/12319))
- **feat(radar):** The Radar catalog table now shows two facts it was already receiving from the feed and dropping on the floor: the per-model rate limits (requests and tokens, per minute and per day) in a new column, and a badge when a provider's terms state it may train on the prompts you send. A limit of zero renders as zero rather than "rate-only" — for a ceiling those are opposite facts — and a model with no training statement gets no badge, because an absent statement is not a guarantee ([#12320](https://github.com/diegosouzapw/OmniRoute/pull/12320))
- **feat(radar):** explain Community, single-use, contributor, supporter, recovery, abuse, offers, and privacy rules before either Radar activation action, and remove the superseded fixed-PR grant promise from every UI locale ([#12342](https://github.com/diegosouzapw/OmniRoute/pull/12342))
- **feat(gamification):** the dashboard Profile page now shows the real daily streak — `/api/gamification/level` returns `streak: { current, longest }` (per key with `apiKeyId`, operator-wide maximum otherwise) and the streak card reads it instead of a hard-coded 0 (#2403)
- **feat(gamification):** the dashboard leaderboard now shows each API key's display name under the Name column instead of a truncated key id; `GET /api/gamification/leaderboard` attaches `name` per entry (name only — no key material), while the shared ranking helper and the federation leaderboard stay id-only — thanks @pacocartones
- **feat(gamification):** enforce the documented 1000 XP/min per-API-key anti-cheat rate limit on the XP award path; over-limit awards are logged and skipped instead of persisted, and the sliding window now matches the timestamp format stored in `xp_audit_log` ([#2403](https://github.com/diegosouzapw/OmniRoute/issues/2403))
- **feat(admin):** localize the gamification anomalies page — the loading state, the Status column and the Suspicious badge now come from the `common` catalog (new `common.suspicious` key propagated to every locale) — add it to the Gamification sidebar group as `gamification-admin` (`/dashboard/gamification/admin`), and expose the loading and empty states as polite `role="status"` live regions (#12401 — thanks @pacocartones)
- **feat(providers):** skip GitHub combo members missing from the live synced catalog, and drop Copilot models that are policy-disabled or hidden from the model picker ([#12473](https://github.com/diegosouzapw/OmniRoute/pull/12473)) — thanks @RaviTharuma
- **feat(i18n):** locale-expansion tooling — `npm run i18n:add-locale` adds a language to config, dashboard, docs mirrors, CLI, README/indexes and site in one command; browser, CLI and cookie detection resolve `uk`, `fil`/`tl`, `zh-Hant` (and the retired legacy `in` → `id`) via config aliases; `config/i18n.json` now ships in the npm package so the published CLI can read it; new real-translation ratio gate (`npm run i18n:check-ratio`, advisory) with a per-locale ratchet baseline; `run-translation --adopt` restores `.i18n-state.json`; `sync-language-bars` generates 🌐 bars from config; `validate_translation.py` loads its allowlist again. Retires the duplicate `in` locale (Indonesian mislabelled as Hindi) — 42 honest locales; saved `NEXT_LOCALE=in` / `OMNIROUTE_LANG=in` keep working. (#12496)
- **feat(api):** Emit gateway-measured `tokens_per_second` (TTFT excluded) on streaming usage and `X-OmniRoute-Tokens-Per-Second` when first-token latency is known ([#12616](https://github.com/diegosouzapw/OmniRoute/issues/12616))
- **feat(opencode):** Add `@omniroute/opencode-plugin-v2`, an opencode v2 plugin that gives a v2 install a route to an OmniRoute gateway: it publishes models, combos and auto-combos into the host catalog, refreshes them lazily behind a 300s TTL, and keeps serving the last known catalog from an on-disk snapshot when the gateway is unreachable. The v1 plugin (`@omniroute/opencode-plugin`) is untouched and keeps working as before. The plugin adapts to the host instead of assuming one shape: it reads the shape the host seeds into the catalog draft and publishes the `api` block, the pre-`api` top-level fields, or both. The gateway key comes from the host credential store when one is connected, so no secret needs to sit in a config file; a source the gateway refuses is named in a warning instead of silently degrading the catalog to raw model ids; and tool schemas bound for a Gemini model are stripped of the JSON-Schema keywords Gemini rejects, so tool calling survives that route ([#12870](https://github.com/diegosouzapw/OmniRoute/pull/12870)) — thanks @maxmad64bis
- **feat(i18n):** 9 new locales — Greek (`el`), Croatian (`hr`), Serbian (`sr`), Lithuanian (`lt`), Estonian (`et`), Latvian (`lv`), Slovenian (`sl`), Maltese (`mt`), Irish (`ga`) — across the dashboard, docs mirrors, CLI, README and the site; OmniRoute now ships every official EU language (51 locales). (#13044)
- feat(services): show sanitized CLIProxyAPI account health from its authenticated management API without exposing credentials, file paths, or raw account metadata (#6342)
- **feat(catalog):** add `OMNIROUTE_DISABLE_THINKING_LEVEL_VARIANTS` feature flag to optionally filter out thinking level variants from model catalog ([#PR_NUMBER](https://github.com/diegosouzapw/OmniRoute/pull/PR_NUMBER))
- **feat(providers):** add MaxAI as a signed, OpenAI-compatible provider serving its 13 paid chat models (GPT-5.6 / Luna / Thinking, Claude 5 Sonnet, Claude Haiku 4.5, Gemini 3.1 Pro / Flash-Lite, Grok 4.1-fast / 4.5, DeepSeek V3.2 / R1, Llama 3.3 70B) through OmniRoute's `/v1` endpoint, with per-request HMAC-SHA1→SM3→AES request signing, live model + context-window discovery from `/models/get_config`, and prompted tool-calling translated to OpenAI `tool_calls`
- **feat(providers):** MaxAI vision input — image_url content parts are forwarded inline in `message_content` to the 6 vision-capable models (GPT-5.6 / Luna / Thinking, Claude Haiku 4.5, Gemini 3.1 Pro / Flash-Lite)
- **feat(providers):** MaxAI document RAG — inline base64 file/document attachments are uploaded to MaxAI (content-addressed `doc_id`) and attached to the chat via `doc_list`
- **feat(providers):** browserless MaxAI onboarding — email device-pair login (`/api/providers/[id]/login`) and signed access-token refresh, so a connection can be created and kept fresh without a real browser or Google OAuth
- **feat(providers):** per-provider TLS impersonation profile (MaxAI presents a Windows Firefox-150 client fingerprint) so its bot-sensitive endpoints accept OmniRoute traffic
- **feat(providers):** add **Nimble** as a web-search and web-fetch provider (`nimble-search`) — `/v1/search` routes to Nimble's search API at `lite` depth (locale, freshness and include/exclude domain filters mapped onto the shared request contract), and `/v1/web/fetch` routes to Nimble Extract, which covers all four fetch formats (`markdown`, `html`, `links`, `screenshot`) from a single call. One API key serves both surfaces.
- **feat(providers):** Add **Opper** as an API-key gateway provider — EU-hosted AI gateway with 700+ models from 30+ providers behind one OpenAI-compatible API and one key (`OPPER_API_KEY`); model ids use `provider/model` format (e.g. `anthropic/claude-sonnet-4-6`, `openai/gpt-5`); live model catalog at `https://api.opper.ai/v3/compat/models`; entry mirrors `requesty` (same shape, `passthroughModels: true`, no static seed)
- New `/dashboard/orchestration` page: live unified view of everything running — Cloud Agent, A2A and Conductor as a real-time graph (Agents tab), the combo cascade (Routing tab, reusing the Combo Live Studio) and a state kanban (Overview tab), with a detail drawer (trace, cost, approve/cancel). Read-only over existing APIs — no new backend. Canvas concept credit: PR #11815 design
- **feat(providers):** add a Perplexity Agent API provider (`perplexity-agent` / `pplx-agent`) for Perplexity `/v1/responses`, including the documented Anthropic, OpenAI, Google, xAI, DeepSeek, Z.AI, Moonshot/Kimi, NVIDIA, and Perplexity model IDs plus Anthropic-model `max_output_tokens` compatibility.
- **feat(providers):** add RPD (Requests Per Day) limit to provider rate limit overrides across UI, schemas, DB, and i18n ([#PR_NUMBER](https://github.com/diegosouzapw/OmniRoute/pull/PR_NUMBER))
- **feat(providers): add UC Direct (uncensored.com Developer API), the metered OpenAI-compatible surface.** A standard OpenAI-compatible passthrough (default executor) for uncensored.com's official REST API at `https://api.uncensored.com/api/v1`: `X-api-key` auth (never-expiring `uai_sk_live_` key), `POST /chat/completions` with streaming SSE and native tool-calling, and the full live metered catalog (82 models across 15 providers, discovered from the public `GET /v1/models`). Registered as provider `uc-direct` (alias `ucd`). Complements the un-metered `uc` persona provider — same models, metered credits and a plain API key instead of a subscription session.
- **feat(providers): add UC (uncensored.com), the un-metered subscription "persona" chat as an OpenAI-compatible provider.** A WebSocket web-app port: a durable Clerk credential mints a short-lived session token per connect (browserless — no API key), driving UC's persona socket. Ships the browserless email-code login (request → verify → harvest), the 19 verified persona models (Claude Opus, Gemini, Grok, GLM, Kimi, DeepSeek, MiniMax, incl. the uncensored variants), prompted `<tool>` tool-calling with a per-model code-style dialect + auto-cure retry for guardrailed models, live `<think>`/reasoning split, streaming + non-streaming OpenAI responses, and full quota/auth error surfacing (paywall / message-limit / rate-limit → 429, invalid session → 401 re-login). Full multimodal parity via the persona blob-upload layer: **vision** (image input, 15 vision-capable models), **document RAG** (PDF/doc upload, server-side extraction), **image generation** (22 models), **video generation** (14 models, async signed-url → poll), and **TTS** (streaming MP3). Registered as provider `uc` (alias `ucn`). The metered OpenAI-compatible Developer API is a separate `uc-direct` provider.
- **fix(dashboard):** Keep local and theme-aware provider SVG icons at a definite layout size so Chromium does not collapse them to 0×0 after the v3.8.50 image-rendering change ([#12054](https://github.com/diegosouzapw/OmniRoute/pull/12054)) — thanks @ponkcore
- **fix(security):** Sanitize provider and runtime failures before public API, SSE and MCP responses and before persistent request, proxy and usage logs, preventing credentials, stack traces and host filesystem paths from crossing those boundaries while preserving stable error codes and useful diagnostics.
- **fix(cli):** `omniroute tunnel create` no longer crashes with `Cannot read properties of undefined (reading optsWithGlobals)` — removed the duplicate positional argument that caused Commander.js to misalign the action callback parameters ([#12295](https://github.com/diegosouzapw/OmniRoute/issues/12295))
- **fix(github):** proactive credential health now verifies GitHub access tokens through the existing Copilot token exchange, marks only a confirmed `401 Unauthorized` as expired, and leaves rate limits, permission failures, upstream failures, and network errors routable ([#10352](https://github.com/diegosouzapw/OmniRoute/issues/10352)) — thanks @RaviTharuma
- **fix(providers):** Antigravity OAuth marks connects with no Cloud Code projectId as degraded instead of a false "Connected"; BYOP detection at connect time, auto-disable of confirmed-missing accounts, and selection-side rotation ([#11284](https://github.com/diegosouzapw/OmniRoute/issues/11284))
- **fix(kie):** reroute `flux/kontext` off the KIE Market `createTask` flow — it is catalogued with `isMarket: true` but has no Market catalog page, so KIE rejected it with "model name not supported"; it now hits the dedicated `POST /api/v1/flux/kontext/generate` / `GET /api/v1/flux/kontext/record-info` endpoints instead (#11296).
- **fix(kie):** correct 12 more KIE Market catalog ids that were sent to `createTask` unchanged but diverge from KIE's documented upstream `model` values — GPT Image 2 T2I/I2I (drops the `gpt/` prefix), GPT Image 1.5 T2I/I2I (`gpt-image/` namespace), Seedream 5.0 Lite T2I/I2I (drops the `.0`), all 4 Flux 2 variants (`flux-2/` namespace, generic variant renamed `flex`), and Wan 2.7 Image / Image Pro (dash instead of dot) — each verified individually against the literal example request published on docs.kie.ai. `#11326`'s "everything else already matches" claim was wrong a second time (#11296); `z-image/4.0-*`/`z-image/4.5-*` and `flux/kontext` remain open, documented as unresolved in `KIE_MARKET_UPSTREAM_MODEL_IDS`'s comment pending further verification.
- **fix(db):** group model patterns escape regex metacharacters, so `gpt-4.1*` no longer matches `gpt-4o1-preview` and a pattern like `gpt-4(*` no longer throws `SyntaxError` out of the completion and `/v1/models` paths ([#11311](https://github.com/diegosouzapw/OmniRoute/pull/11311))
- **fix(db):** the upstream proxy URL check judges the host by address instead of by spelling, so `http://[::ffff:169.254.169.254]`, `[::ffff:10.0.0.5]`, ULA/link-local and CGNAT targets are refused like their dotted equivalents ([#11319](https://github.com/diegosouzapw/OmniRoute/pull/11319))
- **fix(dashboard):** `useApiKeySave.handleSaveApiKey` no longer forces a full upstream `/models` catalog sync on every non-curated provider connection save — callers can now pass `skipModelSync: true` to opt out, so a workflow that only wants to add one manual model no longer floods the provider's available-models list with hundreds/thousands of synced entries. The flag is a client-side intent signal only and is stripped before the connection payload is POSTed to `/api/providers`; default behavior (full sync on save) is unchanged when the flag is omitted (#11324)
- **fix(i18n):** three `pt` strings had dropped their placeholders — the cache tile's subtitle repeated its own label instead of showing `{total}` — and a unit test now enforces placeholder parity with `en` across all locales ([#11325](https://github.com/diegosouzapw/OmniRoute/pull/11325))
- **fix(security):** `proxy-authorization` and `proxy-authenticate` are refused as upstream/custom headers, so a proxy credential is no longer forwarded to the model provider — the canonical denylist now matches the RFC 7230 §6.1 set the rest of the codebase already strips ([#11328](https://github.com/diegosouzapw/OmniRoute/pull/11328))
- **fix(video-bridge):** fall back to the deterministic active-window midpoint when a one-frame scene-aware budget cannot preserve both timeline ends; a real FFmpeg fixture matrix now covers rapid cuts, gradual changes, static and short clips, and detector failure ([#11344](https://github.com/diegosouzapw/OmniRoute/pull/11344)).
- **fix(translator):** Codex Responses tool calls translated for Claude clients no longer emit a duplicate `tool_use` block with the same ID and an empty name, preventing Claude Code from terminating with `No such tool available` ([#11347](https://github.com/diegosouzapw/OmniRoute/pull/11347))
Some files were not shown because too many files have changed in this diff
Show More
Reference in New Issue
Block a user
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
