Files
OmniRoute/src/lib/db/models.ts
Diego Rodrigues de Sa e Souza f59f8daa94 Release v3.8.6 (#2804)
* fix(gemini): preserve structured tool calls for antigravity

* fix(gemini): parse prefixed textual tool calls

* fix(antigravity): preserve textual SSE tool calls

* fix(stream): normalize textual passthrough tool calls

* fix(stream): normalize split textual tool calls

* fix(stream): suppress malformed textual tool calls

* fix(stream): suppress compact malformed tool calls

* fix(stream): emit structured textual tool calls

* fix(stream): suppress unknown textual tool calls

* fix(stream): normalize responses textual tool calls

* chore: ignore .claude/settings.local.json (per-user Claude Code permissions)

* fix(opencode-go): route qwen3.x via claude messages + repair fixMissingToolResponses for Claude-shape upstreams (#2791)

Integrated into release/v3.8.6

* fix: resolve npm install warnings — remove dead deps, relax engine constraint (#2792)

Integrated into release/v3.8.6

* fix: register missing web-cookie validators (claude-web, gemini-web, copilot-web, t3-web) (#2793)

Integrated into release/v3.8.6

* fix: Error: Unable to inspect existing database #2771 (#2795)

Integrated into release/v3.8.6

* fix(oauth): repair Google loopback callback flow (#2796)

Integrated into release/v3.8.6

* feat(logs): add clean history button (#2799)

Integrated into release/v3.8.6

* [codex] home: restore settings-driven home layout and quota auto-refresh (#2800)

Integrated into release/v3.8.6

* fix(gemini): emit signaturelessToolCallMode:text for GEMINI format models (#2801)

Integrated into release/v3.8.6

* feat(modelSpecs): align opencode-go family with upstream provider limits (#2802)

Integrated into release/v3.8.6

* chore: apply unit test fixes, polyfills, and environment precedence fixes

* docs(agents): atualiza fluxos de release e triagem

Expande os workflows de release para incluir auditoria de segurança,
CHANGELOG completo por commits, quality gate obrigatório, homologação em
VPS local, publicação oficial, deploy em Akamai e validação de artefatos.

Reorganiza a triagem de features com arquivos permanentes por bucket,
suporte a itens em andamento, regra de reclaim após 15 dias e novo
tratamento para ideias viáveis catalogadas.

Corrige a orientação de revisão de discussões para usar a ordem
cronológica real dos comentários e respostas ao identificar a última
atividade.

* fix(lockout): classify Gemini Antigravity resource exhaustion as quota_exhausted

* fix(reasoning): gate replay by interleaved field

* docs(rule-16): permit human Co-authored-by, restrict only AI/bot trailers

Rule #16 previously banned all `Co-Authored-By` trailers absolutely.
That blocked the upstream-port workflows (`/port-upstream-features` and
`/port-upstream-issues`), which must credit human upstream PR authors
and issue reporters in OmniRoute commits.

Refine the rule to ban only AI/bot-attributed trailers (Claude, GPT,
Copilot, Bot; anthropic.com / openai.com / bot-owned noreply.github.com
emails) while allowing standard human `Co-authored-by: Name <email>`
attribution.

Sync the rule across the source CLAUDE.md, the E2E shakedown doc note,
and 41 i18n translations.

* fix(gitlawb): add specialty validators for connection test — bypass /models probe

GitLawB OpenGateway API (xiaomi-mimo compatible) does not expose a /models
endpoint, causing validateOpenAILikeProvider to 404 on the initial probe
and report 'Provider validation endpoint not supported'.

Add specialty validators for both gitlawb and gitlawb-gmi that follow the
same pattern as the existing xiaomi-mimo validator: skip GET /models,
validate directly via POST /chat/completions with a minimal test message.
Any 401/403 response means an invalid key; all other responses mean auth
is OK.

Fixes test-connection returning 404 for GitLawB providers.

* test(gitlawb): add 12 unit tests for gitlawb and gitlawb-gmi specialty validators

Covers success, auth failure (401/403), non-auth acceptance (400/422/429),
network errors, and custom baseUrl overrides for both providers.

* feat(gitlawb): serve models from static registry without API-unavailable warning

GitLawB's OpenGateway API does not expose a /models endpoint per
provider-path. Previously the models route fell through to the generic
fallback which returned static catalog models with the misleading
'API unavailable — using local catalog' warning.

Now gitlawb and gitlawb-gmi are handled as static model providers
(same pattern as reka and qwen OAuth) — models are served from the
provider registry without any warning, since all registered models
are functional via POST /chat/completions.

* refactor(gitlawb): extract shared opengateway validator factory, fix docs path in test

- Extract gitlawb/gitlawb-gmi validators into buildOpengatewayValidator factory
- Fix dockerignore-docs-coverage test: update stale docs/AUTO-COMBO.md -> docs/routing/AUTO-COMBO.md

* fix(reasoning): guard interleaved capability lookup

* feat(gitlawb): dynamic model fetch with gmi-cloud fallback

Hybrid approach:
- gitlawb (xiaomi-mimo): dynamic /models endpoint → 356 models
- gitlawb-gmi (gmi-cloud): 404 fallback → local catalog gracefully
Mimics Gitlawb/openclaude's model-routing pattern

* i18n(pt-BR): complete missing translations and sync with en.json

* feat(build): nix multi-OS package manager install (#2806)

Integrated into release/v3.8.6

* fix(i18n): translate 144 new __MISSING__ pt-BR strings (#2816)

Integrated into release/v3.8.6

* chore(docs): set coverage gate to 40/40/40/40 in CLAUDE.md

Aligns the documented coverage gate with the v3.8.6 release decision
(lowered from 75/75/75/70). Matches the threshold already set in
package.json by the large feature PRs (planos 11-22).

* fix(cli): respect PORT env var in serve command (#2845)

Integrated into release/v3.8.6.

* fix(deepseek-web): return 400 when client sends tools[] - chat.deepseek.com has no tool support (#2854)

Integrated into release/v3.8.6.

* fix(qoder): reject invalid/expired PATs returning Cosy 500 error (#2860)

Integrated into release/v3.8.6.

* fix(cli): register openclaw in tool-detector (#2833) (#2850)

Integrated into release/v3.8.6.

* fix(api): include noAuth providers in /v1/models catalog (#2798) (#2814)

Integrated into release/v3.8.6.

* fix(combo): resolve custom provider targets via combo name (#2778) (#2812)

Integrated into release/v3.8.6.

* fix(translator): strip safety_identifier in openai-responses cleanup (#2770) (#2809)

Integrated into release/v3.8.6.

* fix(quota): honor explicit per-connection preflight opt-out (#2831) (#2844)

Integrated into release/v3.8.6.

* fix(usage): un-invert GitHub Copilot Free/limited quota — limited_user_quotas is remaining (#2876) (#2881)

Integrated into release/v3.8.6.

* fix(nous-research): correct baseUrl to include /chat/completions (#2826) (#2835)

Integrated into release/v3.8.6.

* fix(opencode): qwen3.x max/plus models lack vision support (#2822) (#2836)

Integrated into release/v3.8.6.

* fix(translator): pass-through tool_search built-in tool type (#2766) (#2811)

Integrated into release/v3.8.6.

* fix(github): route claude-opus-4.6 via chat completions (#2821)

Integrated into release/v3.8.6.

* docs(oauth): add Windsurf login fix design (Phase 1 hotfix + Phase 2 Firebase OAuth)

Two-phase plan to fix the broken Windsurf OAuth flow:
- Phase 1: drop the dead app.devin.ai/editor/signin PKCE path, promote
  import-token from windsurf.com/show-auth-token as the primary path
- Phase 2: port Firebase OAuth + RegisterUser flow from
  fendoushaonian/WindSurf-gRPC-API for full browser-based automation

Spec only - no code changes yet.

* docs(plan): Phase 1 windsurf login hotfix implementation plan

10 tasks covering:
- TDD assertions for flowType + 410 Gone responses
- Provider switch to import_token
- Route handler retiring authorize/start-callback-server/poll-callback
- OAuthModal UI override
- i18n sync
- Verification + PR steps

* fix(cli): replace cli-table3 with hand-rolled formatter (#2752) (#2813)

Integrated into release/v3.8.6.

* fix(skills): skip interception for unregistered client-native tools (#2815) (#2817)

Integrated into release/v3.8.6.

* feat(sse): add RTK filters for kubectl, docker-build, composer, gh (#2824)

Integrated into release/v3.8.6.

* fix(geminiHelper): support rec.image content shape + warn on dropped remote URLs (refs #2807) (#2855)

Integrated into release/v3.8.6.

* fix(cli): allow nullable/optional apiKey in cliMitmStartSchema (#2857)

Integrated into release/v3.8.6.

* fix(combo): preserve system messages during context handoff summary generation (#2865)

Integrated into release/v3.8.6.

* fix: wire CLIProxyAPI fallback settings into chatCore routing engine (#2866)

Integrated into release/v3.8.6.

* fix(usage): add opencode quota fetcher (#2852) (#2867)

Integrated into release/v3.8.6.

* feat(claude): default xhigh support for newer Opus models (#2874)

Integrated into release/v3.8.6.

* fix(cli): restore omniroute logs command stream (#2756) (#2810)

Integrated into release/v3.8.6.

* fix(combo): normalize upstream Headers for Node 24 undici interop (#2751) (#2823)

Integrated into release/v3.8.6.

* Rename proxy log Public IP to Client IP (#2880)

Integrated into release/v3.8.6.

* fix(claude): preserve max effort for supported models (#2875)

Integrated into release/v3.8.6.

* fix(oauth): switch windsurf provider to import_token flow

The PKCE auth URL targeting app.devin.ai/editor/signin returns 404
post-rebrand. Until Phase 2 ports Firebase OAuth + RegisterUser, the
only supported path is import-token via windsurf.com/show-auth-token.

- windsurf.ts: drop buildAuthUrl, set flowType=import_token
- generateAuthData returns supported:false + helpful error for windsurf/devin-cli
- tests: assert flowType + disabled stub

* fix(oauth): return 410 Gone for retired windsurf/devin-cli PKCE actions

start-callback-server, authorize, and poll-callback (GET + POST) now
return 410 Gone with a pointer to /import-token. The 410 short-circuit
runs before auth so the response is honest about the action being
permanently gone, not gated. Codex PKCE flow unchanged.

Tests: 5 new assertions cover GET + POST 410 paths and a Codex
regression check.

* refactor(oauth): annotate retired PKCE fields in WINDSURF_CONFIG

No behaviour change - comment-only update documenting that authorizeUrl,
codeChallengeMethod, callbackPort, callbackPath, apiServerUrl, and
exchangePath are no longer consumed. Active fields (inferenceUrl,
showAuthTokenUrl, firebaseApiKey, ideName) called out separately.

* fix(cli,docs): use requireCliToolsAuth in logs route + document OPENCODE quota env

Post-merge contract fixes for v3.8.6:
- src/app/api/cli-tools/logs/route.ts (#2810) now uses the shared
  requireCliToolsAuth guard (param renamed req->request) to satisfy the
  cli-tools-auth-hardening contract test.
- Document OMNIROUTE_OPENCODE_QUOTA_URL (#2867) in docs/reference/ENVIRONMENT.md
  to satisfy the env/docs sync contract.

* fix(dashboard): force import-token panel for windsurf/devin-cli

Phase 1 hotfix: hide the 'Browser Login' tab and start in Paste API Key
mode. Removes windsurf/devin-cli from PKCE_CALLBACK_SERVER_PROVIDERS so
no callback server is started for them. Codex still uses the PKCE flow.

The 'Get token' link continues to point at windsurf.com/show-auth-token
via the existing supportsTokenPaste form copy.

* fix(oauth): windsurf import-token mapTokens signature mismatch

The route at `src/app/api/oauth/[provider]/[action]/route.ts` invokes
`providerData.mapTokens({ accessToken: token })` (object), matching the
cursor/kiro signature. The windsurf provider was declared with
`mapTokens(token: string)` instead, so the entire object was stored as
`accessToken`. When the connection record reached the SQLite layer it
crashed with:

  SQLite3 can only bind numbers, strings, bigints, buffers, and null

Fix by aligning windsurf's `mapTokens` signature with the route caller
and the cursor/kiro convention. Also dedupe a copy-pasted second
`if (action === "import-token")` block in the route handler — the
second block was unreachable but identical to the first.

Adds two regression tests asserting that
`provider.mapTokens({ accessToken })` returns a string `accessToken` for
both windsurf and devin-cli, so a future signature drift trips the gate
instead of the SQLite bind error in production.

* feat(compression): expand pt-BR pack with troglodita rules (15 → 49) (#2818)

Integrated into release/v3.8.6

* fix(sse): repair RTK engine defaults so dedup and direct calls work (#2825)

Integrated into release/v3.8.6

* fix(mcp): redirect console.log/warn to stderr in --mcp stdio mode (#2840)

Integrated into release/v3.8.6

* fix(gemini-cli): prefer real project IDs over default-project (#2841)

Integrated into release/v3.8.6

* fix(opencode-go): add provider limits quota fetcher (#2861)

Integrated into release/v3.8.6

* Audit & add web cookie providers: fix 4 missing registry entries + DuckDuckGo (#2862)

Integrated into release/v3.8.6

* fix(antigravity): harden signatureless tool history (#2878)

Integrated into release/v3.8.6

* fix: provider model sync pruning and dynamic antigravity MITM proxy mappings (#2886)

Integrated into release/v3.8.6

* feat(usage): per-API-key token limits scoped to model/provider/global (#2888)

Integrated into release/v3.8.6

* fix(audio): build multipart body manually to preserve Content-Type (#2842)

Integrated into release/v3.8.6

* refactor: remove agent skill documentation files and streamline maintenance workflows

* test(stabilization): resolve unit test failures in blackbox-web, schema-coercion, translator-helper-branches, usage-service-hardening, and audio-transcription

* fix(security): mitigate Socket.dev supply-chain findings + secrets opt-in + minimal build profile (#2863) (#2871)

Two real security gaps closed and four cosmetic Socket.dev fingerprints removed.
See docs/security/SOCKET_DEV_FINDINGS.md for the per-finding maintainer
attestation.

Real bugs fixed:
- cloudSync: HMAC verification of `X-Cloud-Sig` + opt-in
  `OMNIROUTE_CLOUD_SYNC_SECRETS=true` before overwriting `accessToken` /
  `refreshToken` / `providerSpecificData` from a remote response. Closes the
  silent-credential-swap surface (a misconfigured or hostile CLOUD_URL could
  previously replace local tokens unverified).
- Zed import: split into 2-step `/discover` + `/import` flow. `/import` now
  requires `confirmedAccounts: [{ service, account, fingerprint }]` and
  re-reads the keychain server-side to filter by fingerprint, so a tampered
  discover response cannot trick the endpoint into saving an unrelated token.

Cosmetic Socket.dev mitigations:
- runElevatedPowerShell writes the elevated payload to a per-call temp `.ps1`
  file (mode 0o600) and references it via `-File`. Removes the textbook
  `-EncodedCommand <base64utf16le>` pattern flagged as malware by Socket's AI
  classifier.
- Maintainer attestation `SECURITY-AUDITOR-NOTE:` blocks added at every
  flagged call site pointing to `docs/security/SOCKET_DEV_FINDINGS.md`.

Build-time hardening:
- `OMNIROUTE_BUILD_PROFILE=minimal` (`npm run build:secure`) physically
  removes the four sensitive modules from the standalone bundle via webpack
  `NormalModuleReplacementPlugin`. Stubs throw `FeatureDisabledError` at
  runtime. Intended for the `omniroute-secure` artifact.

Tests:
- 24 new unit tests in `tests/unit/security/` covering the wrapper builder,
  HMAC verification (4 cases), credential fingerprint determinism (5 cases),
  confirmedAccounts validation + fingerprint filtering (6 cases), and the
  minimal-build stubs (5 cases).

Docs:
- New `docs/security/SOCKET_DEV_FINDINGS.md` — per-finding attestation.
- New `socket.yml` — Socket.dev v2 config pointing at the attestation.
- Updated `SECURITY.md` — supply-chain scanner section.
- Updated `.env.example` — three new env vars documented.

Backwards compatibility:
- Cloud sync token overwrite is OFF by default. Users who relied on
  it must set `OMNIROUTE_CLOUD_SYNC_SECRETS=true`. Breaking change documented
  in CHANGELOG.
- Zed import 2-step is the new default; legacy 1-step preserved behind
  `OMNIROUTE_ZED_IMPORT_LEGACY_ONE_STEP=true` and will be removed in v3.9.

Closes #2863

* fix(security): redact public Firebase Web key from windsurf spec; doc SHA-256 cache-key rationale (#2894)

Two security-scanning findings on release/v3.8.6:

- Secret-scanning alert 7 (google_api_key): the windsurf login-fix design spec
  embedded the literal public Firebase Web API key on two lines. Firebase Web
  API keys are non-sensitive by design (they identify the project; access is
  gated by Firebase Security Rules + key restrictions), but the literal trips
  secret scanning. Redacted to a placeholder; the embedded default still goes
  through resolvePublicCred per rule #11.

- Code-scanning alert 261 (js/insufficient-password-hash): tokenCacheKey() uses
  SHA-256 to derive an in-memory cache key from the session token, not for
  password-at-rest storage. Added a comment documenting why CWE-916 KDFs do not
  apply (false positive).

* fix(ci): resolve release/v3.8.6 gate failures (docs-sync, any-budget, pack-artifact) (#2895)

* fix(ci): resolve release/v3.8.6 gate failures (docs-sync, any-budget, pack-artifact)

Three CI gates failed on release/v3.8.6 (run 26630300877):

- docs-sync: CHANGELOG had a spurious "## [3.8.6-patch]" section above
  "## [3.8.6]", so the latest release no longer matched package.json (3.8.6)
  and the 41 i18n CHANGELOG mirrors were flagged as missing that section.
  Fold the lone #2752 entry into [3.8.6] and drop the patch heading.
- any-budget:t11: open-sse/handlers/chatCore.ts regressed to 1 explicit `any`
  (budget 0). Type the persist callback arg as Record<string, unknown>, which
  matches runWithOnPersist's RefreshPersistFn contract exactly.
- pack-artifact: open-sse/utils/setupPolyfill.ts ships via package.json "files"
  (bin/omniroute.mjs imports it at startup) but was missing from the pack
  policy allowlist. Allow it and add a regression test.

* fix(security): redact public Firebase Web key from windsurf spec

Redact the literal public Firebase Web API key (secret-scanning #7) to a
placeholder, mirroring the redaction on release/v3.8.6 (PR #2894) and the
windsurf fix branch. Non-sensitive public Web key; trips secret scanning.

* feat(combo): Zero-Latency Combos (Hedging, Proactive Compression, Predictive TTFT) (#2868)

* feat(combo): implement zero-latency combo optimizations (hedging, proactive compression, predictive TTFT)

* fix(combo): fix predictive TTFT skip logic and unhandled promise rejections

---------

Co-authored-by: Automation <automation@omniroute>

* feat: implement automated skill workflows and update system configuration and validation schemas

* test: eliminate dynamic cast warnings in cloud-sync unit test

* test: isolate services-branch-hardening database directory to avoid concurrency issues

* feat(providers): add 7 new web-cookie providers + research catalog + discovery tool

New providers:
- huggingchat: free LLM chat via huggingface.co/chat (no subscription)
- phind: free dev-focused AI chat via phind.com/api/agent
- poe-web: multi-model chat via poe.com GraphQL (p-b cookie)
- venice-web: privacy-focused AI chat via venice.ai (session cookie)
- v0-vercel-web: Vercel v0 code gen via v0.dev (session cookie)
- kimi-web: Moonshot Kimi chat via kimi.moonshot.cn (session cookie)
- doubao-web: ByteDance Doubao chat via doubao.com (session cookie)

Additional:
- Research catalog: docs/research/UNLIMITED_LLM_ACCESS.md
- Discovery tool design + stub: src/lib/discovery/ + migration 073
- Unit tests: 33 tests for all 7 providers
- Shared helpers consolidated in error.ts (slop cleanup)
- All registered in WEB_COOKIE_PROVIDERS + providerRegistry + webSessionCredentials

Closes #2885

* fix(typecheck): resolve typecheck errors in combo spec and compression modules

* feat(api,oauth): add `agy` (Antigravity CLI) standalone provider with CLI token import (#2899)

Add a standalone OAuth provider `agy` (Antigravity CLI) next to gemini-cli/antigravity.
It reuses the antigravity inference backend (identical Google client_id +
daily-cloudcode-pa.googleapis.com endpoint, executor and token-refresh) but ships its own
model catalog — including the Claude models the backend exposes (claude-opus-4-6-thinking,
claude-sonnet-4-6) — its own account pool, and four ways to connect:

- token-file import (paste/upload the agy oauth token JSON)
- auto-detect a local CLI login (~/.gemini/antigravity-cli/antigravity-oauth-token)
- browser OAuth (via the shared OAuthModal Google loopback flow)
- bulk / ZIP import

New routes: POST /api/providers/agy-auth/{import,import-bulk,zip-extract,apply-local}.
Catalog pinned from the live :fetchAvailableModels endpoint. Docs (openapi.yaml,
ENVIRONMENT.md, .env.example, CHANGELOG) updated; new unit tests for registration,
the token parser, and route auth-hardening.

* fix(security): redact public Firebase Web key from windsurf spec (#2896)

Redact the literal public Firebase Web API key (secret-scanning #7) to a
placeholder. Firebase Web API keys are non-sensitive by design but the literal
trips GitHub secret scanning. Mirrors the redaction landed on release/v3.8.6
(PR #2894). Embedded default still flows through resolvePublicCred (rule #11).

* Pr 2871 (#2897)

* fix(security): mitigate Socket.dev supply-chain findings + secrets opt-in + minimal build profile (#2863)

Two real security gaps closed and four cosmetic Socket.dev fingerprints removed.
See docs/security/SOCKET_DEV_FINDINGS.md for the per-finding maintainer
attestation.

Real bugs fixed:
- cloudSync: HMAC verification of `X-Cloud-Sig` + opt-in
  `OMNIROUTE_CLOUD_SYNC_SECRETS=true` before overwriting `accessToken` /
  `refreshToken` / `providerSpecificData` from a remote response. Closes the
  silent-credential-swap surface (a misconfigured or hostile CLOUD_URL could
  previously replace local tokens unverified).
- Zed import: split into 2-step `/discover` + `/import` flow. `/import` now
  requires `confirmedAccounts: [{ service, account, fingerprint }]` and
  re-reads the keychain server-side to filter by fingerprint, so a tampered
  discover response cannot trick the endpoint into saving an unrelated token.

Cosmetic Socket.dev mitigations:
- runElevatedPowerShell writes the elevated payload to a per-call temp `.ps1`
  file (mode 0o600) and references it via `-File`. Removes the textbook
  `-EncodedCommand <base64utf16le>` pattern flagged as malware by Socket's AI
  classifier.
- Maintainer attestation `SECURITY-AUDITOR-NOTE:` blocks added at every
  flagged call site pointing to `docs/security/SOCKET_DEV_FINDINGS.md`.

Build-time hardening:
- `OMNIROUTE_BUILD_PROFILE=minimal` (`npm run build:secure`) physically
  removes the four sensitive modules from the standalone bundle via webpack
  `NormalModuleReplacementPlugin`. Stubs throw `FeatureDisabledError` at
  runtime. Intended for the `omniroute-secure` artifact.

Tests:
- 24 new unit tests in `tests/unit/security/` covering the wrapper builder,
  HMAC verification (4 cases), credential fingerprint determinism (5 cases),
  confirmedAccounts validation + fingerprint filtering (6 cases), and the
  minimal-build stubs (5 cases).

Docs:
- New `docs/security/SOCKET_DEV_FINDINGS.md` — per-finding attestation.
- New `socket.yml` — Socket.dev v2 config pointing at the attestation.
- Updated `SECURITY.md` — supply-chain scanner section.
- Updated `.env.example` — three new env vars documented.

Backwards compatibility:
- Cloud sync token overwrite is OFF by default. Users who relied on
  it must set `OMNIROUTE_CLOUD_SYNC_SECRETS=true`. Breaking change documented
  in CHANGELOG.
- Zed import 2-step is the new default; legacy 1-step preserved behind
  `OMNIROUTE_ZED_IMPORT_LEGACY_ONE_STEP=true` and will be removed in v3.9.

Closes #2863

* feat: implement automated skill workflows and update system configuration and validation schemas

* test: eliminate dynamic cast warnings in cloud-sync unit test

* test: isolate services-branch-hardening database directory to avoid concurrency issues

* chore(docs): refresh generated docs collection index

Update the generated Fumadocs browser collection mapping to keep
documentation imports in sync with the current docs structure.

* docs: update generated browser docs collection manifest

Refresh the generated Fumadocs browser collection mapping so the docs site can resolve the current documentation files correctly.

---------

Co-authored-by: OpenClaw <openclaw@kuzhomesrv.local>
Co-authored-by: Dmitry Kuznetsov <139351986+dmitry@users.noreply.local>
Co-authored-by: KuzyaBot <kuzya@local>
Co-authored-by: JeferssonLemes <jeferssondev@gmail.com>
Co-authored-by: Paijo <14921983+oyi77@users.noreply.github.com>
Co-authored-by: Markus Hartung <mail@hartmark.se>
Co-authored-by: akarray <akarray@users.noreply.github.com>
Co-authored-by: Apostol Apostolov <theapoapostolov@gmail.com>
Co-authored-by: Hernan Javier Ardila Sanchez <hjasgr@gmail.com>
Co-authored-by: Dmitry Kuznetsov <dmitry@kuznetsov.me>
Co-authored-by: Nikolay Alafuzov <alafuzov_nn@rusklimat.ru>
Co-authored-by: oyi77 <oyi77@users.noreply.github.com>
Co-authored-by: Ronaldo Davi <alltomatos@users.noreply.github.com>
Co-authored-by: levonk <277861+levonk@users.noreply.github.com>
Co-authored-by: Lenine Júnior <lenine@engrene.com.br>
Co-authored-by: Annas Alghoffar <aag.annas@gmail.com>
Co-authored-by: Tushar Agarwal <76201310+Tushar49@users.noreply.github.com>
Co-authored-by: GreatLiu <eurasiaxz@qq.com>
Co-authored-by: yuna amelia <230527278+yunaamelia@users.noreply.github.com>
Co-authored-by: Randi <55005611+rdself@users.noreply.github.com>
Co-authored-by: Container <78986709+disonjer@users.noreply.github.com>
Co-authored-by: nickwizard <35692452+nickwizard@users.noreply.github.com>
Co-authored-by: Rajvardhan Patil <rajvardhanpatil7890@gmail.com>
Co-authored-by: Raxxoor <manker_lol@hotmail.com>
Co-authored-by: Muhammad Mugni Hadi <mugnimaestra3@gmail.com>
Co-authored-by: mi <123757457+soyelmismo@users.noreply.github.com>
Co-authored-by: Automation <automation@omniroute>
2026-05-29 12:44:29 -03:00

1025 lines
35 KiB
TypeScript

/**
* db/models.js — Model aliases, MITM aliases, and custom models.
*/
import { getDbInstance } from "./core";
import { backupDbFile } from "./backup";
import {
MODEL_COMPAT_PROTOCOL_KEYS,
type ModelCompatProtocolKey,
} from "@/shared/constants/modelCompat";
import { isForbiddenUpstreamHeaderName } from "@/shared/constants/upstreamHeaders";
type JsonRecord = Record<string, unknown>;
/** Built-in / alias models: tool-call + developer-role flags without a full custom row */
const MODEL_COMPAT_NAMESPACE = "modelCompatOverrides";
export { MODEL_COMPAT_PROTOCOL_KEYS, type ModelCompatProtocolKey };
export type ModelCompatPerProtocol = {
normalizeToolCallId?: boolean;
preserveOpenAIDeveloperRole?: boolean;
/** Merged into upstream HTTP requests for this model (after default auth headers). */
upstreamHeaders?: Record<string, string>;
};
type CompatByProtocolMap = Partial<Record<ModelCompatProtocolKey, ModelCompatPerProtocol>>;
function isCompatProtocolKey(p: string): p is ModelCompatProtocolKey {
return (MODEL_COMPAT_PROTOCOL_KEYS as readonly string[]).includes(p);
}
const UPSTREAM_HEADERS_MAX = 16;
const UPSTREAM_HEADER_NAME_MAX = 128;
const UPSTREAM_HEADER_VALUE_MAX = 4096;
function isValidUpstreamHeaderName(k: string): boolean {
if (!k || k.length > UPSTREAM_HEADER_NAME_MAX) return false;
if (isForbiddenUpstreamHeaderName(k)) return false;
if (/[\r\n\0]/.test(k)) return false;
if (/\s/.test(k)) return false;
if (k.includes(":")) return false;
return true;
}
/** Sanitize user-provided upstream header map (used when persisting and when reading for requests). */
export function sanitizeUpstreamHeadersMap(
raw: Record<string, unknown> | null | undefined
): Record<string, string> {
const out: Record<string, string> = {};
if (!raw || typeof raw !== "object") return out;
for (const [k0, v0] of Object.entries(raw)) {
const k = String(k0).trim();
if (!k || !isValidUpstreamHeaderName(k)) {
continue;
}
const v =
typeof v0 === "string"
? v0.trim().slice(0, UPSTREAM_HEADER_VALUE_MAX)
: String(v0 ?? "")
.trim()
.slice(0, UPSTREAM_HEADER_VALUE_MAX);
if (v.includes("\r") || v.includes("\n")) continue;
out[k] = v;
if (Object.keys(out).length >= UPSTREAM_HEADERS_MAX) break;
}
return out;
}
function deepMergeCompatByProtocol(
prev: CompatByProtocolMap | undefined,
patch: Partial<Record<ModelCompatProtocolKey, Partial<ModelCompatPerProtocol>>>
): CompatByProtocolMap {
const out: CompatByProtocolMap = { ...(prev || {}) };
for (const key of Object.keys(patch) as ModelCompatProtocolKey[]) {
if (!isCompatProtocolKey(key)) continue;
const deltas = patch[key];
if (!deltas || typeof deltas !== "object") continue;
const hasDelta =
Object.prototype.hasOwnProperty.call(deltas, "normalizeToolCallId") ||
Object.prototype.hasOwnProperty.call(deltas, "preserveOpenAIDeveloperRole") ||
Object.prototype.hasOwnProperty.call(deltas, "upstreamHeaders");
if (!hasDelta) continue;
const cur: ModelCompatPerProtocol = { ...(out[key] || {}) };
if ("normalizeToolCallId" in deltas) {
cur.normalizeToolCallId = Boolean(deltas.normalizeToolCallId);
}
if ("preserveOpenAIDeveloperRole" in deltas) {
cur.preserveOpenAIDeveloperRole = Boolean(deltas.preserveOpenAIDeveloperRole);
}
if ("upstreamHeaders" in deltas) {
const uh = deltas.upstreamHeaders;
if (uh === undefined) {
/* skip */
} else {
const s = sanitizeUpstreamHeadersMap(uh as Record<string, unknown>);
if (Object.keys(s).length === 0) delete cur.upstreamHeaders;
else cur.upstreamHeaders = s;
}
}
if (Object.keys(cur).length === 0) delete out[key];
else out[key] = cur;
}
return out;
}
export type ModelCompatOverride = {
id: string;
normalizeToolCallId?: boolean;
preserveOpenAIDeveloperRole?: boolean;
compatByProtocol?: CompatByProtocolMap;
upstreamHeaders?: Record<string, string>;
isHidden?: boolean;
};
function readCompatList(providerId: string): ModelCompatOverride[] {
const db = getDbInstance();
const row = db
.prepare("SELECT value FROM key_value WHERE namespace = ? AND key = ?")
.get(MODEL_COMPAT_NAMESPACE, providerId);
const value = getKeyValue(row).value;
if (!value) return [];
try {
const parsed = JSON.parse(value);
return Array.isArray(parsed) ? parsed : [];
} catch {
return [];
}
}
function writeCompatList(providerId: string, list: ModelCompatOverride[]) {
const db = getDbInstance();
if (list.length === 0) {
db.prepare("DELETE FROM key_value WHERE namespace = ? AND key = ?").run(
MODEL_COMPAT_NAMESPACE,
providerId
);
} else {
db.prepare("INSERT OR REPLACE INTO key_value (namespace, key, value) VALUES (?, ?, ?)").run(
MODEL_COMPAT_NAMESPACE,
providerId,
JSON.stringify(list)
);
}
backupDbFile("pre-write");
}
export function getModelCompatOverrides(providerId: string): ModelCompatOverride[] {
return readCompatList(providerId);
}
export type ModelCompatPatch = {
normalizeToolCallId?: boolean;
preserveOpenAIDeveloperRole?: boolean | null;
compatByProtocol?: CompatByProtocolMap;
/** Replace top-level extra headers for override-only rows; omit to leave unchanged. */
upstreamHeaders?: Record<string, string> | null;
isHidden?: boolean | null;
};
function compatByProtocolHasEntries(map: CompatByProtocolMap | undefined): boolean {
if (!map || typeof map !== "object") return false;
return Object.keys(map).some((k) => {
const v = map[k as ModelCompatProtocolKey];
return v && typeof v === "object" && Object.keys(v).length > 0;
});
}
export function mergeModelCompatOverride(
providerId: string,
modelId: string,
patch: ModelCompatPatch
) {
const list = readCompatList(providerId);
const idx = list.findIndex((e) => e.id === modelId);
const prev = idx >= 0 ? { ...list[idx] } : { id: modelId };
const next: ModelCompatOverride = { ...prev, id: modelId };
if ("normalizeToolCallId" in patch) {
if (patch.normalizeToolCallId) next.normalizeToolCallId = true;
else delete next.normalizeToolCallId;
}
if ("preserveOpenAIDeveloperRole" in patch) {
if (patch.preserveOpenAIDeveloperRole === null) {
delete next.preserveOpenAIDeveloperRole; // unset: revert to default (undefined at read time)
} else {
next.preserveOpenAIDeveloperRole = Boolean(patch.preserveOpenAIDeveloperRole);
}
}
if (patch.compatByProtocol && Object.keys(patch.compatByProtocol).length > 0) {
const merged = deepMergeCompatByProtocol(next.compatByProtocol, patch.compatByProtocol);
if (compatByProtocolHasEntries(merged)) next.compatByProtocol = merged;
else delete next.compatByProtocol;
}
if ("upstreamHeaders" in patch) {
if (patch.upstreamHeaders === null) {
delete next.upstreamHeaders;
} else if (patch.upstreamHeaders && typeof patch.upstreamHeaders === "object") {
const s = sanitizeUpstreamHeadersMap(patch.upstreamHeaders as Record<string, unknown>);
if (Object.keys(s).length === 0) delete next.upstreamHeaders;
else next.upstreamHeaders = s;
}
}
const filtered = list.filter((e) => e.id !== modelId);
const hasPreserveFlag = Object.prototype.hasOwnProperty.call(next, "preserveOpenAIDeveloperRole");
const hasTopUpstream = next.upstreamHeaders && Object.keys(next.upstreamHeaders).length > 0;
if ("isHidden" in patch) {
if (patch.isHidden === null) {
delete next.isHidden;
} else {
next.isHidden = Boolean(patch.isHidden);
}
}
const hasHiddenFlag = Object.prototype.hasOwnProperty.call(next, "isHidden");
if (
next.normalizeToolCallId ||
hasPreserveFlag ||
hasHiddenFlag ||
compatByProtocolHasEntries(next.compatByProtocol) ||
hasTopUpstream
) {
filtered.push(next);
}
writeCompatList(providerId, filtered);
}
export function removeModelCompatOverride(providerId: string, modelId: string) {
const list = readCompatList(providerId);
const filtered = list.filter((e) => e.id !== modelId);
if (filtered.length === list.length) return;
writeCompatList(providerId, filtered);
}
function asRecord(value: unknown): JsonRecord {
return value && typeof value === "object" && !Array.isArray(value) ? (value as JsonRecord) : {};
}
function toNonEmptyString(value: unknown): string | null {
return typeof value === "string" && value.trim().length > 0 ? value.trim() : null;
}
function getKeyValue(row: unknown): { key: string | null; value: string | null } {
const record = asRecord(row);
return {
key: typeof record.key === "string" ? record.key : null,
value: typeof record.value === "string" ? record.value : null,
};
}
// ──────────────── Model Aliases ────────────────
export async function getModelAliases() {
const db = getDbInstance();
const rows = db
.prepare("SELECT key, value FROM key_value WHERE namespace = 'modelAliases'")
.all();
const result: Record<string, unknown> = {};
for (const row of rows) {
const { key, value } = getKeyValue(row);
if (!key || value === null) continue;
result[key] = JSON.parse(value);
}
return result;
}
export async function setModelAlias(alias: string, model: unknown) {
const db = getDbInstance();
db.prepare(
"INSERT OR REPLACE INTO key_value (namespace, key, value) VALUES ('modelAliases', ?, ?)"
).run(alias, JSON.stringify(model));
backupDbFile("pre-write");
}
export async function deleteModelAlias(alias: string) {
const db = getDbInstance();
db.prepare("DELETE FROM key_value WHERE namespace = 'modelAliases' AND key = ?").run(alias);
backupDbFile("pre-write");
}
// ──────────────── MITM Alias ────────────────
export async function getMitmAlias(toolName?: string) {
const db = getDbInstance();
if (toolName) {
const row = db
.prepare("SELECT value FROM key_value WHERE namespace = 'mitmAlias' AND key = ?")
.get(toolName);
const value = getKeyValue(row).value;
return value ? JSON.parse(value) : {};
}
const rows = db.prepare("SELECT key, value FROM key_value WHERE namespace = 'mitmAlias'").all();
const result: Record<string, unknown> = {};
for (const row of rows) {
const { key, value } = getKeyValue(row);
if (!key || value === null) continue;
result[key] = JSON.parse(value);
}
return result;
}
export async function setMitmAliasAll(toolName: string, mappings: unknown) {
const db = getDbInstance();
db.prepare(
"INSERT OR REPLACE INTO key_value (namespace, key, value) VALUES ('mitmAlias', ?, ?)"
).run(toolName, JSON.stringify(mappings || {}));
backupDbFile("pre-write");
}
// ──────────────── Custom Models ────────────────
export async function getCustomModels(providerId?: string) {
const db = getDbInstance();
if (providerId) {
const row = db
.prepare("SELECT value FROM key_value WHERE namespace = 'customModels' AND key = ?")
.get(providerId);
const value = getKeyValue(row).value;
return value ? JSON.parse(value) : [];
}
const rows = db
.prepare("SELECT key, value FROM key_value WHERE namespace = 'customModels'")
.all();
const result: Record<string, unknown> = {};
for (const row of rows) {
const { key, value } = getKeyValue(row);
if (!key || value === null) continue;
result[key] = JSON.parse(value);
}
return result;
}
export async function getAllCustomModels() {
const db = getDbInstance();
const rows = db
.prepare("SELECT key, value FROM key_value WHERE namespace = 'customModels'")
.all();
const result: Record<string, unknown> = {};
for (const row of rows) {
const { key, value } = getKeyValue(row);
if (!key || value === null) continue;
result[key] = JSON.parse(value);
}
return result;
}
export async function addCustomModel(
providerId: string,
modelId: string,
modelName?: string,
source = "manual",
apiFormat:
| "chat-completions"
| "responses"
| "embeddings"
| "rerank"
| "audio-transcriptions"
| "audio-speech"
| "images-generations" = "chat-completions",
supportedEndpoints: string[] = ["chat"]
) {
const db = getDbInstance();
const row = db
.prepare("SELECT value FROM key_value WHERE namespace = 'customModels' AND key = ?")
.get(providerId);
const value = getKeyValue(row).value;
const models = value ? JSON.parse(value) : [];
const exists = models.find((m: JsonRecord) => m.id === modelId);
if (exists) return exists;
const model = {
id: modelId,
name: modelName || modelId,
source,
apiFormat,
supportedEndpoints,
};
models.push(model);
db.prepare(
"INSERT OR REPLACE INTO key_value (namespace, key, value) VALUES ('customModels', ?, ?)"
).run(providerId, JSON.stringify(models));
backupDbFile("pre-write");
return model;
}
/**
* Replace the entire custom models list for a provider.
* Preserves per-model compatibility overrides for models that still exist.
*/
export async function replaceCustomModels(
providerId: string,
models: Array<{
id: string;
name?: string;
source?: string;
apiFormat?: string;
supportedEndpoints?: string[];
inputTokenLimit?: number;
outputTokenLimit?: number;
description?: string;
supportsThinking?: boolean;
}>,
{ allowEmpty = false }: { allowEmpty?: boolean } = {}
) {
// Guard: skip destructive clear when the caller hasn't explicitly opted in.
// This prevents callers from wiping manually added models when the
// upstream /models endpoint fails, times out, or returns an empty list.
if (models.length === 0 && !allowEmpty) {
const existing = await getCustomModels(providerId);
return Array.isArray(existing) ? existing : [];
}
const db = getDbInstance();
const existing = await getCustomModels(providerId);
const existingMap = new Map<string, JsonRecord>();
if (Array.isArray(existing)) {
for (const m of existing) {
if (m && typeof m === "object" && m.id) existingMap.set(m.id, m);
}
}
// Merge: keep existing per-model compat flags if model still exists
const merged = models.map((m) => {
const prev = existingMap.get(m.id);
return {
id: m.id,
name: m.name || m.id,
source: m.source || "auto-sync",
apiFormat: m.apiFormat || (prev as any)?.apiFormat || "chat-completions",
supportedEndpoints: m.supportedEndpoints || (prev as any)?.supportedEndpoints || ["chat"],
// Preserve metadata from provider API (or previous sync)
...(m.inputTokenLimit != null
? { inputTokenLimit: m.inputTokenLimit }
: (prev as any)?.inputTokenLimit != null
? { inputTokenLimit: (prev as any).inputTokenLimit }
: {}),
...(m.outputTokenLimit != null
? { outputTokenLimit: m.outputTokenLimit }
: (prev as any)?.outputTokenLimit != null
? { outputTokenLimit: (prev as any).outputTokenLimit }
: {}),
...(m.description != null
? { description: m.description }
: (prev as any)?.description != null
? { description: (prev as any).description }
: {}),
...(m.supportsThinking != null
? { supportsThinking: m.supportsThinking }
: (prev as any)?.supportsThinking != null
? { supportsThinking: (prev as any).supportsThinking }
: {}),
// Preserve existing compat flags
...(prev && (prev as any).normalizeToolCallId !== undefined
? { normalizeToolCallId: (prev as any).normalizeToolCallId }
: {}),
...(prev && (prev as any).preserveOpenAIDeveloperRole !== undefined
? { preserveOpenAIDeveloperRole: (prev as any).preserveOpenAIDeveloperRole }
: {}),
...(prev && (prev as any).compatByProtocol
? { compatByProtocol: (prev as any).compatByProtocol }
: {}),
...(prev && (prev as any).upstreamHeaders
? { upstreamHeaders: (prev as any).upstreamHeaders }
: {}),
};
});
if (merged.length === 0) {
db.prepare("DELETE FROM key_value WHERE namespace = 'customModels' AND key = ?").run(
providerId
);
} else {
db.prepare(
"INSERT OR REPLACE INTO key_value (namespace, key, value) VALUES ('customModels', ?, ?)"
).run(providerId, JSON.stringify(merged));
}
// Remove compat overrides for models that no longer exist
const newIds = new Set(models.map((m) => m.id));
const compatList = readCompatList(providerId);
const filteredCompat = compatList.filter((e) => newIds.has(e.id));
if (filteredCompat.length !== compatList.length) {
writeCompatList(providerId, filteredCompat);
}
backupDbFile("pre-write");
return merged;
}
export async function removeCustomModel(providerId: string, modelId: string) {
const db = getDbInstance();
const row = db
.prepare("SELECT value FROM key_value WHERE namespace = 'customModels' AND key = ?")
.get(providerId);
if (!row) return false;
const value = getKeyValue(row).value;
if (!value) return false;
const models = JSON.parse(value);
const before = models.length;
const filtered = models.filter((m: JsonRecord) => m.id !== modelId);
if (filtered.length === before) return false;
if (filtered.length === 0) {
db.prepare("DELETE FROM key_value WHERE namespace = 'customModels' AND key = ?").run(
providerId
);
} else {
db.prepare("UPDATE key_value SET value = ? WHERE namespace = 'customModels' AND key = ?").run(
JSON.stringify(filtered),
providerId
);
}
removeModelCompatOverride(providerId, modelId);
backupDbFile("pre-write");
return true;
}
// ──────────────── Synced Available Models ────────────────
// Storage: namespace = 'syncedAvailableModels', key = '<providerId>:<connectionId>'
// Each connection stores its own model list. Reads union across all connections
// for a provider. Deleting a connection removes only its models.
export interface SyncedAvailableModel {
id: string;
name: string;
source: "imported";
apiFormat?: string;
supportedEndpoints?: string[];
inputTokenLimit?: number;
outputTokenLimit?: number;
description?: string;
supportsThinking?: boolean;
}
type SyncedAvailableModelInput = Omit<SyncedAvailableModel, "source"> & {
source?: string;
};
function normalizeSyncedAvailableModel(model: unknown): SyncedAvailableModel | null {
const record = asRecord(model);
const id =
toNonEmptyString(record.id) || toNonEmptyString(record.name) || toNonEmptyString(record.model);
if (!id) return null;
const name =
toNonEmptyString(record.name) ||
toNonEmptyString(record.displayName) ||
toNonEmptyString(record.model) ||
id;
const supportedEndpoints = Array.isArray(record.supportedEndpoints)
? Array.from(
new Set(
record.supportedEndpoints
.map((endpoint) => toNonEmptyString(endpoint))
.filter((endpoint): endpoint is string => Boolean(endpoint))
)
).sort()
: undefined;
return {
id,
name,
source: "imported",
...(toNonEmptyString(record.apiFormat)
? { apiFormat: toNonEmptyString(record.apiFormat)! }
: {}),
...(supportedEndpoints && supportedEndpoints.length > 0 ? { supportedEndpoints } : {}),
...(typeof record.inputTokenLimit === "number"
? { inputTokenLimit: record.inputTokenLimit }
: {}),
...(typeof record.outputTokenLimit === "number"
? { outputTokenLimit: record.outputTokenLimit }
: {}),
...(typeof record.description === "string" ? { description: record.description } : {}),
...(record.supportsThinking === true ? { supportsThinking: true } : {}),
};
}
function normalizeSyncedAvailableModels(models: unknown): SyncedAvailableModel[] {
if (!Array.isArray(models)) return [];
const deduped = new Map<string, SyncedAvailableModel>();
for (const model of models) {
const normalized = normalizeSyncedAvailableModel(model);
if (normalized) deduped.set(normalized.id, normalized);
}
return Array.from(deduped.values());
}
/**
* Get synced available models for a specific provider connection.
*/
export async function getSyncedAvailableModelsForConnection(
providerId: string,
connectionId: string
): Promise<SyncedAvailableModel[]> {
const db = getDbInstance();
const key = `${providerId}:${connectionId}`;
const row = db
.prepare("SELECT value FROM key_value WHERE namespace = 'syncedAvailableModels' AND key = ?")
.get(key);
const value = getKeyValue(row).value;
if (!value) return [];
try {
const models = JSON.parse(value);
return normalizeSyncedAvailableModels(models);
} catch {
return [];
}
}
/**
* Get all synced available models for a provider, unioned across all connections.
*/
export async function getSyncedAvailableModels(
providerId: string
): Promise<SyncedAvailableModel[]> {
const db = getDbInstance();
const rows = db
.prepare(
"SELECT key, value FROM key_value WHERE namespace = 'syncedAvailableModels' AND key LIKE ?"
)
.all(`${providerId}:%`);
const map = new Map<string, SyncedAvailableModel>();
for (const row of rows) {
const { key, value } = getKeyValue(row);
if (!key || value === null) continue;
const models = normalizeSyncedAvailableModels(JSON.parse(value));
for (const m of models) {
if (m.id) map.set(m.id, m);
}
}
return Array.from(map.values());
}
/**
* Get synced available models for a provider grouped by connection id.
*/
export async function getSyncedAvailableModelsByConnection(
providerId: string
): Promise<Record<string, SyncedAvailableModel[]>> {
const db = getDbInstance();
const prefix = `${providerId}:`;
const rows = db
.prepare(
"SELECT key, value FROM key_value WHERE namespace = 'syncedAvailableModels' AND key LIKE ?"
)
.all(`${prefix}%`);
const result: Record<string, SyncedAvailableModel[]> = {};
for (const row of rows) {
const { key, value } = getKeyValue(row);
if (!key || value === null || !key.startsWith(prefix)) continue;
try {
const connectionId = key.slice(prefix.length);
result[connectionId] = normalizeSyncedAvailableModels(JSON.parse(value));
} catch {
// Ignore malformed legacy entries.
}
}
return result;
}
/**
* Get all synced available models across all providers.
*/
export async function getAllSyncedAvailableModels(): Promise<
Record<string, SyncedAvailableModel[]>
> {
const db = getDbInstance();
const rows = db
.prepare("SELECT key, value FROM key_value WHERE namespace = 'syncedAvailableModels'")
.all();
// Group by providerId (before the colon)
const byProvider = new Map<string, Map<string, SyncedAvailableModel>>();
for (const row of rows) {
const { key, value } = getKeyValue(row);
if (!key || value === null) continue;
const providerId = key.split(":")[0];
if (!byProvider.has(providerId)) byProvider.set(providerId, new Map());
const models = normalizeSyncedAvailableModels(JSON.parse(value));
const map = byProvider.get(providerId)!;
for (const m of models) {
if (m.id) map.set(m.id, m);
}
}
const result: Record<string, SyncedAvailableModel[]> = {};
for (const [providerId, map] of byProvider) {
result[providerId] = Array.from(map.values());
}
return result;
}
/**
* Replace the model list for a specific connection.
* Key format: '<providerId>:<connectionId>'
*/
export async function replaceSyncedAvailableModelsForConnection(
providerId: string,
connectionId: string,
models: SyncedAvailableModelInput[]
): Promise<SyncedAvailableModel[]> {
const db = getDbInstance();
const key = `${providerId}:${connectionId}`;
const normalizedModels = normalizeSyncedAvailableModels(models);
if (normalizedModels.length === 0) {
db.prepare("DELETE FROM key_value WHERE namespace = 'syncedAvailableModels' AND key = ?").run(
key
);
} else {
db.prepare(
"INSERT OR REPLACE INTO key_value (namespace, key, value) VALUES ('syncedAvailableModels', ?, ?)"
).run(key, JSON.stringify(normalizedModels));
}
backupDbFile("pre-write");
// Return the full unioned list for the provider
return getSyncedAvailableModels(providerId);
}
/**
* Delete all synced models for a specific connection.
* Returns the remaining unioned list for the provider.
*/
export async function deleteSyncedAvailableModelsForConnection(
providerId: string,
connectionId: string
): Promise<SyncedAvailableModel[]> {
const db = getDbInstance();
const key = `${providerId}:${connectionId}`;
db.prepare("DELETE FROM key_value WHERE namespace = 'syncedAvailableModels' AND key = ?").run(
key
);
backupDbFile("pre-write");
return getSyncedAvailableModels(providerId);
}
/**
* Delete all synced models for every connection belonging to a provider.
* Returns the number of connection-scoped synced model lists removed.
*/
export async function deleteSyncedAvailableModelsForProvider(providerId: string): Promise<number> {
const db = getDbInstance();
const keyPrefix = `${providerId}:`;
const result = db
.prepare(
"DELETE FROM key_value WHERE namespace = 'syncedAvailableModels' AND substr(key, 1, ?) = ?"
)
.run(keyPrefix.length, keyPrefix);
backupDbFile("pre-write");
return Number(result.changes || 0);
}
/**
* Prune stale synced available models for a provider, keeping only the specified allowed connection IDs.
* Returns the number of keys deleted.
*/
export async function pruneStaleSyncedAvailableModelsForProvider(
providerId: string,
allowedConnectionIds: string[]
): Promise<number> {
const db = getDbInstance();
if (allowedConnectionIds.length === 0) {
return deleteSyncedAvailableModelsForProvider(providerId);
}
const placeholders = allowedConnectionIds.map(() => "?").join(",");
const keyPrefix = `${providerId}:`;
const allowedKeys = allowedConnectionIds.map((id) => `${providerId}:${id}`);
const result = db
.prepare(
`DELETE FROM key_value WHERE namespace = 'syncedAvailableModels' AND key LIKE ? AND key NOT IN (${placeholders})`
)
.run(`${keyPrefix}%`, ...allowedKeys);
backupDbFile("pre-write");
return Number(result.changes || 0);
}
export async function updateCustomModel(
providerId: string,
modelId: string,
updates: Record<string, unknown> = {}
) {
const db = getDbInstance();
const row = db
.prepare("SELECT value FROM key_value WHERE namespace = 'customModels' AND key = ?")
.get(providerId);
if (!row) return null;
const value = getKeyValue(row).value;
if (!value) return null;
const models = JSON.parse(value);
const index = models.findIndex((m: JsonRecord) => m.id === modelId);
if (index === -1) return null;
const current = models[index];
const currentCompat = (current as JsonRecord).compatByProtocol as CompatByProtocolMap | undefined;
let mergedCompat: CompatByProtocolMap | undefined = currentCompat;
if (
updates.compatByProtocol !== undefined &&
typeof updates.compatByProtocol === "object" &&
updates.compatByProtocol !== null &&
!Array.isArray(updates.compatByProtocol)
) {
mergedCompat = deepMergeCompatByProtocol(
currentCompat,
updates.compatByProtocol as Partial<
Record<ModelCompatProtocolKey, Partial<ModelCompatPerProtocol>>
>
);
if (!compatByProtocolHasEntries(mergedCompat)) mergedCompat = undefined;
}
const next: JsonRecord = {
...current,
...(updates.modelName !== undefined ? { name: updates.modelName || current.name } : {}),
...(updates.apiFormat !== undefined ? { apiFormat: updates.apiFormat } : {}),
...(updates.supportedEndpoints !== undefined
? { supportedEndpoints: updates.supportedEndpoints }
: {}),
...(updates.normalizeToolCallId !== undefined
? { normalizeToolCallId: Boolean(updates.normalizeToolCallId) }
: {}),
...(updates.isHidden !== undefined ? { isHidden: Boolean(updates.isHidden) } : {}),
};
if (Object.prototype.hasOwnProperty.call(updates, "preserveOpenAIDeveloperRole")) {
if (updates.preserveOpenAIDeveloperRole === null) {
delete next.preserveOpenAIDeveloperRole;
} else {
next.preserveOpenAIDeveloperRole = Boolean(updates.preserveOpenAIDeveloperRole);
}
}
if (updates.compatByProtocol !== undefined) {
if (mergedCompat && compatByProtocolHasEntries(mergedCompat)) {
next.compatByProtocol = mergedCompat;
} else {
delete next.compatByProtocol;
}
}
if (Object.prototype.hasOwnProperty.call(updates, "upstreamHeaders")) {
const uh = updates.upstreamHeaders;
if (uh === null || uh === undefined) {
delete next.upstreamHeaders;
} else if (typeof uh === "object" && !Array.isArray(uh)) {
const s = sanitizeUpstreamHeadersMap(uh as Record<string, unknown>);
if (Object.keys(s).length === 0) delete next.upstreamHeaders;
else next.upstreamHeaders = s;
}
}
models[index] = next;
db.prepare("UPDATE key_value SET value = ? WHERE namespace = 'customModels' AND key = ?").run(
JSON.stringify(models),
providerId
);
backupDbFile("pre-write");
return next;
}
/** Single custom model row from key_value customModels, or null */
function getCustomModelRow(providerId: string, modelId: string): JsonRecord | null {
const db = getDbInstance();
const row = db
.prepare("SELECT value FROM key_value WHERE namespace = 'customModels' AND key = ?")
.get(providerId);
const value = getKeyValue(row).value;
if (!value) return null;
try {
const models = JSON.parse(value) as unknown;
if (!Array.isArray(models)) return null;
const m = models.find((x: unknown) => {
if (!x || typeof x !== "object" || Array.isArray(x)) return false;
return (x as { id?: string }).id === modelId;
}) as JsonRecord | undefined;
return m ?? null;
} catch {
return null;
}
}
/**
* Whether the given provider/model has "normalize tool call id" (9-char Mistral-style) enabled.
* Custom model row wins; otherwise {@link getModelCompatOverrides}.
* When `sourceFormat` is one of `openai` | `openai-responses` | `claude`, per-protocol
* `compatByProtocol[sourceFormat].normalizeToolCallId` overrides the legacy top-level flag.
*/
export function getModelNormalizeToolCallId(
providerId: string,
modelId: string,
sourceFormat?: string | null
): boolean {
const m = getCustomModelRow(providerId, modelId);
const protocol = sourceFormat && isCompatProtocolKey(sourceFormat) ? sourceFormat : null;
if (m) {
if (protocol) {
const pc = (m.compatByProtocol as CompatByProtocolMap | undefined)?.[protocol];
if (pc && Object.prototype.hasOwnProperty.call(pc, "normalizeToolCallId")) {
return Boolean(pc.normalizeToolCallId);
}
}
return Boolean(m.normalizeToolCallId);
}
const co = readCompatList(providerId).find((e) => e.id === modelId);
if (protocol && co?.compatByProtocol?.[protocol]) {
const pc = co.compatByProtocol[protocol]!;
if (Object.prototype.hasOwnProperty.call(pc, "normalizeToolCallId")) {
return Boolean(pc.normalizeToolCallId);
}
}
return Boolean(co?.normalizeToolCallId);
}
/**
* Explicit preserve-openai-developer preference for this provider/model.
* `undefined` = unset → routing keeps legacy default (preserve developer for OpenAI format).
* `false` = map developer → system (e.g. MiniMax). `true` = keep developer.
* Per-protocol overrides live under `compatByProtocol[sourceFormat]` when `sourceFormat` matches.
*/
export function getModelPreserveOpenAIDeveloperRole(
providerId: string,
modelId: string,
sourceFormat?: string | null
): boolean | undefined {
const m = getCustomModelRow(providerId, modelId);
const protocol = sourceFormat && isCompatProtocolKey(sourceFormat) ? sourceFormat : null;
if (m) {
if (protocol) {
const pc = (m.compatByProtocol as CompatByProtocolMap | undefined)?.[protocol];
if (pc && Object.prototype.hasOwnProperty.call(pc, "preserveOpenAIDeveloperRole")) {
return Boolean(pc.preserveOpenAIDeveloperRole);
}
}
if (Object.prototype.hasOwnProperty.call(m, "preserveOpenAIDeveloperRole")) {
return Boolean(m.preserveOpenAIDeveloperRole);
}
return undefined;
}
const co = readCompatList(providerId).find((e) => e.id === modelId);
if (protocol && co?.compatByProtocol?.[protocol]) {
const pc = co.compatByProtocol[protocol]!;
if (Object.prototype.hasOwnProperty.call(pc, "preserveOpenAIDeveloperRole")) {
return Boolean(pc.preserveOpenAIDeveloperRole);
}
}
if (co && Object.prototype.hasOwnProperty.call(co, "preserveOpenAIDeveloperRole")) {
return Boolean(co.preserveOpenAIDeveloperRole);
}
return undefined;
}
/**
* Check if the model is flagged as hidden from the public catalog.
*/
export function getModelIsHidden(providerId: string, modelId: string): boolean {
const m = getCustomModelRow(providerId, modelId);
if (m && Object.prototype.hasOwnProperty.call(m, "isHidden")) {
return Boolean(m.isHidden);
}
const co = readCompatList(providerId).find((e) => e.id === modelId);
return Boolean(co?.isHidden);
}
function readUpstreamFromJsonRecord(
row: JsonRecord | null | undefined,
key: "upstreamHeaders"
): Record<string, string> | undefined {
if (!row) return undefined;
const raw = row[key];
if (!raw || typeof raw !== "object" || Array.isArray(raw)) return undefined;
const s = sanitizeUpstreamHeadersMap(raw as Record<string, unknown>);
return Object.keys(s).length > 0 ? s : undefined;
}
/**
* Extra HTTP headers to send to the upstream provider for this model (after executor auth headers).
* Order: top-level `upstreamHeaders` on the custom model row (override list merged under custom),
* then per-protocol `compatByProtocol[sourceFormat].upstreamHeaders` (wins on key conflict).
* Use for gateways that expect `Authentication`, `X-API-Key`, etc. alongside Bearer.
*
* `modelId` should be the **canonical** model id when known. Callers that accept client aliases
* (e.g. chat proxy) should merge results for both alias and `resolveModelAlias(alias)` so UI
* config on the resolved id still applies — see `chatCore` merge.
*/
export function getModelUpstreamExtraHeaders(
providerId: string,
modelId: string,
sourceFormat?: string | null
): Record<string, string> {
const protocol = sourceFormat && isCompatProtocolKey(sourceFormat) ? sourceFormat : null;
const m = getCustomModelRow(providerId, modelId);
const base: Record<string, string> = {};
if (m) {
const fromModel = readUpstreamFromJsonRecord(m, "upstreamHeaders");
if (fromModel) Object.assign(base, fromModel);
if (protocol) {
const pc = (m.compatByProtocol as CompatByProtocolMap | undefined)?.[protocol];
const fromProto = pc?.upstreamHeaders;
if (fromProto && typeof fromProto === "object") {
Object.assign(base, sanitizeUpstreamHeadersMap(fromProto as Record<string, unknown>));
}
}
return base;
}
const co = readCompatList(providerId).find((e) => e.id === modelId);
if (co?.upstreamHeaders) {
Object.assign(base, sanitizeUpstreamHeadersMap(co.upstreamHeaders as Record<string, unknown>));
}
if (protocol && co?.compatByProtocol?.[protocol]?.upstreamHeaders) {
Object.assign(
base,
sanitizeUpstreamHeadersMap(
co.compatByProtocol[protocol]!.upstreamHeaders as Record<string, unknown>
)
);
}
return base;
}