mirror of
https://github.com/diegosouzapw/OmniRoute.git
synced 2026-08-01 04:42:10 +03:00
* 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>
1503 lines
49 KiB
TypeScript
1503 lines
49 KiB
TypeScript
import test from "node:test";
|
|
import assert from "node:assert/strict";
|
|
import fs from "node:fs";
|
|
import os from "node:os";
|
|
import path from "node:path";
|
|
|
|
const TEST_DATA_DIR = fs.mkdtempSync(path.join(os.tmpdir(), "omniroute-provider-model-routes-"));
|
|
process.env.DATA_DIR = TEST_DATA_DIR;
|
|
|
|
const core = await import("../../src/lib/db/core.ts");
|
|
const providersDb = await import("../../src/lib/db/providers.ts");
|
|
const modelsDb = await import("../../src/lib/db/models.ts");
|
|
const providerModelsRoute = await import("../../src/app/api/providers/[id]/models/route.ts");
|
|
const antigravityVersion = await import("../../open-sse/services/antigravityVersion.ts");
|
|
const providerRegistry = await import("../../open-sse/config/providerRegistry.ts");
|
|
|
|
const originalFetch = globalThis.fetch;
|
|
const originalAllowPrivateProviderUrls = process.env.OMNIROUTE_ALLOW_PRIVATE_PROVIDER_URLS;
|
|
|
|
async function resetStorage() {
|
|
globalThis.fetch = originalFetch;
|
|
if (originalAllowPrivateProviderUrls === undefined) {
|
|
delete process.env.OMNIROUTE_ALLOW_PRIVATE_PROVIDER_URLS;
|
|
} else {
|
|
process.env.OMNIROUTE_ALLOW_PRIVATE_PROVIDER_URLS = originalAllowPrivateProviderUrls;
|
|
}
|
|
antigravityVersion.clearAntigravityVersionCache();
|
|
core.resetDbInstance();
|
|
fs.rmSync(TEST_DATA_DIR, { recursive: true, force: true });
|
|
fs.mkdirSync(TEST_DATA_DIR, { recursive: true });
|
|
}
|
|
|
|
async function seedConnection(provider, overrides = {}) {
|
|
return providersDb.createProviderConnection({
|
|
provider,
|
|
authType: overrides.authType || "apikey",
|
|
name: overrides.name || `${provider}-${Math.random().toString(16).slice(2, 8)}`,
|
|
apiKey: overrides.apiKey,
|
|
accessToken: overrides.accessToken,
|
|
projectId: overrides.projectId,
|
|
isActive: overrides.isActive ?? true,
|
|
testStatus: overrides.testStatus || "active",
|
|
providerSpecificData: overrides.providerSpecificData || {},
|
|
});
|
|
}
|
|
|
|
async function callRoute(connectionId, search = "") {
|
|
return providerModelsRoute.GET(
|
|
new Request(`http://localhost/api/providers/${connectionId}/models${search}`),
|
|
{ params: { id: connectionId } }
|
|
);
|
|
}
|
|
|
|
test.beforeEach(async () => {
|
|
await resetStorage();
|
|
});
|
|
|
|
test.after(async () => {
|
|
globalThis.fetch = originalFetch;
|
|
core.resetDbInstance();
|
|
fs.rmSync(TEST_DATA_DIR, { recursive: true, force: true });
|
|
});
|
|
|
|
test("provider models route returns 404 for unknown connections", async () => {
|
|
const response = await callRoute("missing-connection");
|
|
|
|
assert.equal(response.status, 404);
|
|
assert.deepEqual(await response.json(), { error: "Connection not found" });
|
|
});
|
|
|
|
test("provider models route rejects connections with an empty provider id", async () => {
|
|
const connection = await seedConnection("openai", {
|
|
apiKey: "sk-openai",
|
|
});
|
|
const db = core.getDbInstance();
|
|
|
|
db.prepare("UPDATE provider_connections SET provider = '' WHERE id = ?").run(connection.id);
|
|
|
|
const response = await callRoute(connection.id);
|
|
|
|
assert.equal(response.status, 400);
|
|
assert.deepEqual(await response.json(), { error: "Invalid connection provider" });
|
|
});
|
|
|
|
test("provider models route rejects OpenAI-compatible providers without a base URL", async () => {
|
|
const connection = await seedConnection("openai-compatible-demo", {
|
|
apiKey: "sk-openai-compatible",
|
|
});
|
|
|
|
const response = await callRoute(connection.id);
|
|
|
|
assert.equal(response.status, 400);
|
|
assert.deepEqual(await response.json(), {
|
|
error: "No base URL configured for OpenAI compatible provider",
|
|
});
|
|
});
|
|
|
|
test("provider models route blocks private OpenAI-compatible base URLs", async () => {
|
|
delete process.env.OMNIROUTE_ALLOW_PRIVATE_PROVIDER_URLS;
|
|
|
|
const connection = await seedConnection("openai-compatible-private", {
|
|
apiKey: "sk-openai-compatible",
|
|
providerSpecificData: {
|
|
baseUrl: "http://127.0.0.1:11434/v1",
|
|
},
|
|
});
|
|
|
|
let called = false;
|
|
globalThis.fetch = async () => {
|
|
called = true;
|
|
return Response.json({ data: [] });
|
|
};
|
|
|
|
const response = await callRoute(connection.id);
|
|
|
|
assert.equal(response.status, 400);
|
|
assert.deepEqual(await response.json(), {
|
|
error: "Blocked private or local provider URL",
|
|
});
|
|
assert.equal(called, false);
|
|
});
|
|
|
|
test("provider models route returns auth failures from OpenAI-compatible upstreams", async () => {
|
|
const connection = await seedConnection("openai-compatible-auth", {
|
|
apiKey: "sk-openai-compatible",
|
|
providerSpecificData: {
|
|
baseUrl: "https://proxy.example.com/v1/chat/completions",
|
|
},
|
|
});
|
|
const seenUrls = [];
|
|
|
|
globalThis.fetch = async (url) => {
|
|
seenUrls.push(String(url));
|
|
return new Response("unauthorized", { status: 401 });
|
|
};
|
|
|
|
const response = await callRoute(connection.id);
|
|
|
|
assert.equal(response.status, 401);
|
|
assert.deepEqual(await response.json(), { error: "Auth failed: 401" });
|
|
assert.equal(seenUrls.length, 1);
|
|
});
|
|
|
|
test("provider models route falls back after OpenAI-compatible endpoint probes all fail", async () => {
|
|
const connection = await seedConnection("openai-compatible-fallback", {
|
|
apiKey: "sk-openai-compatible",
|
|
providerSpecificData: {
|
|
baseUrl: "https://proxy.example.com/v1",
|
|
},
|
|
});
|
|
const seenUrls = [];
|
|
|
|
globalThis.fetch = async (url) => {
|
|
seenUrls.push(String(url));
|
|
return new Response("bad gateway", { status: 502 });
|
|
};
|
|
|
|
const response = await callRoute(connection.id);
|
|
const body = (await response.json()) as any;
|
|
|
|
assert.equal(response.status, 200);
|
|
assert.equal(body.provider, "openai-compatible-fallback");
|
|
assert.ok(Array.isArray(body.models));
|
|
assert.ok(seenUrls.length >= 2);
|
|
});
|
|
|
|
test("provider models route retries transient OpenAI-compatible probe failures before succeeding", async () => {
|
|
const connection = await seedConnection("openai-compatible-retry", {
|
|
apiKey: "sk-openai-compatible",
|
|
providerSpecificData: {
|
|
baseUrl: "https://proxy.example.com/v1",
|
|
},
|
|
});
|
|
const seenUrls = [];
|
|
|
|
globalThis.fetch = async (url) => {
|
|
seenUrls.push(String(url));
|
|
if (seenUrls.length === 1) {
|
|
throw new Error("temporary upstream failure");
|
|
}
|
|
|
|
return Response.json({
|
|
data: [{ id: "demo-model", name: "Demo Model" }],
|
|
});
|
|
};
|
|
|
|
const response = await callRoute(connection.id);
|
|
const body = (await response.json()) as any;
|
|
|
|
assert.equal(response.status, 200);
|
|
assert.equal(body.source, "api");
|
|
assert.deepEqual(seenUrls, [
|
|
"https://proxy.example.com/v1/models",
|
|
"https://proxy.example.com/v1/models",
|
|
]);
|
|
assert.deepEqual(body.models, [{ id: "demo-model", name: "Demo Model" }]);
|
|
});
|
|
|
|
test("provider models route returns static catalog entries for providers with hardcoded models", async () => {
|
|
const connection = await seedConnection("bailian-coding-plan", {
|
|
apiKey: "bailian-key",
|
|
});
|
|
|
|
const response = await callRoute(connection.id);
|
|
const body = (await response.json()) as any;
|
|
|
|
assert.equal(response.status, 200);
|
|
assert.equal(body.provider, "bailian-coding-plan");
|
|
assert.equal(body.models.length, providerRegistry.REGISTRY["bailian-coding-plan"].models?.length);
|
|
assert.deepEqual(
|
|
body.models.map((model) => model.id),
|
|
providerRegistry.REGISTRY["bailian-coding-plan"].models?.map((model) => model.id)
|
|
);
|
|
});
|
|
|
|
test("provider models route returns AWS Polly speech engines from the audio registry", async () => {
|
|
const connection = await seedConnection("aws-polly", {
|
|
apiKey: "aws-secret-key",
|
|
providerSpecificData: {
|
|
accessKeyId: "AKIA_TEST",
|
|
region: "us-east-1",
|
|
},
|
|
});
|
|
|
|
const response = await callRoute(connection.id);
|
|
const body = (await response.json()) as any;
|
|
|
|
assert.equal(response.status, 200);
|
|
assert.equal(body.provider, "aws-polly");
|
|
assert.equal(body.source, "local_catalog");
|
|
assert.deepEqual(
|
|
body.models.map((model) => model.id),
|
|
["standard", "neural", "long-form", "generative"]
|
|
);
|
|
});
|
|
|
|
test("provider models route returns the local catalog for GitLab Duo fallback models", async () => {
|
|
const connection = await seedConnection("gitlab", {
|
|
apiKey: "glpat-test",
|
|
});
|
|
|
|
const response = await callRoute(connection.id);
|
|
const body = (await response.json()) as any;
|
|
|
|
assert.equal(response.status, 200);
|
|
assert.equal(body.provider, "gitlab");
|
|
assert.equal(body.source, "local_catalog");
|
|
assert.deepEqual(body.models, [
|
|
{ id: "gitlab-duo-code-suggestions", name: "GitLab Duo Code Suggestions" },
|
|
]);
|
|
});
|
|
|
|
test("provider models route discovers local OpenAI-style models without requiring an API key", async () => {
|
|
process.env.OMNIROUTE_ALLOW_PRIVATE_PROVIDER_URLS = "true";
|
|
|
|
const lmStudioConnection = await seedConnection("lm-studio", {
|
|
providerSpecificData: {
|
|
baseUrl: "http://localhost:1234/v1",
|
|
},
|
|
});
|
|
const lemonadeConnection = await seedConnection("lemonade", {
|
|
providerSpecificData: {
|
|
baseUrl: "http://localhost:13305/api/v1",
|
|
},
|
|
});
|
|
|
|
globalThis.fetch = async (url, init = {}) => {
|
|
const target = String(url);
|
|
assert.equal(init.headers.Authorization, undefined);
|
|
if (target === "http://localhost:1234/v1/models") {
|
|
return Response.json({
|
|
data: [{ id: "local-model", name: "Local Model" }],
|
|
});
|
|
}
|
|
if (target === "http://localhost:13305/api/v1/models") {
|
|
return Response.json({
|
|
data: [{ id: "Llama-3.2-1B-Instruct-Hybrid", name: "Lemonade Llama" }],
|
|
});
|
|
}
|
|
throw new Error(`unexpected fetch: ${target}`);
|
|
};
|
|
|
|
const lmStudioResponse = await callRoute(lmStudioConnection.id);
|
|
const lmStudioBody = (await lmStudioResponse.json()) as any;
|
|
const lemonadeResponse = await callRoute(lemonadeConnection.id);
|
|
const lemonadeBody = (await lemonadeResponse.json()) as any;
|
|
|
|
assert.equal(lmStudioResponse.status, 200);
|
|
assert.equal(lmStudioBody.provider, "lm-studio");
|
|
assert.equal(lmStudioBody.source, "api");
|
|
assert.deepEqual(lmStudioBody.models, [{ id: "local-model", name: "Local Model" }]);
|
|
|
|
assert.equal(lemonadeResponse.status, 200);
|
|
assert.equal(lemonadeBody.provider, "lemonade");
|
|
assert.equal(lemonadeBody.source, "api");
|
|
assert.deepEqual(lemonadeBody.models, [
|
|
{ id: "Llama-3.2-1B-Instruct-Hybrid", name: "Lemonade Llama" },
|
|
]);
|
|
});
|
|
|
|
test("provider models route returns the local catalog for built-in image providers", async () => {
|
|
const connection = await seedConnection("topaz", {
|
|
apiKey: "topaz-key",
|
|
});
|
|
|
|
const response = await callRoute(connection.id);
|
|
const body = (await response.json()) as any;
|
|
|
|
assert.equal(response.status, 200);
|
|
assert.equal(body.provider, "topaz");
|
|
assert.ok(Array.isArray(body.models));
|
|
assert.deepEqual(body.models, [{ id: "topaz-enhance", name: "topaz-enhance" }]);
|
|
});
|
|
|
|
test("provider models route prefers the remote OpenRouter /models API over static image models", async () => {
|
|
const connection = await seedConnection("openrouter", {
|
|
apiKey: "openrouter-key",
|
|
});
|
|
const seenUrls = [];
|
|
|
|
globalThis.fetch = async (url, init = {}) => {
|
|
seenUrls.push(String(url));
|
|
assert.equal(init.method, "GET");
|
|
assert.equal(init.headers.Authorization, "Bearer openrouter-key");
|
|
return Response.json({
|
|
data: [{ id: "openai/gpt-4.1", name: "GPT-4.1 via OpenRouter" }],
|
|
});
|
|
};
|
|
|
|
const response = await callRoute(connection.id, "?refresh=true");
|
|
const body = (await response.json()) as any;
|
|
|
|
assert.equal(response.status, 200);
|
|
assert.equal(body.source, "api");
|
|
assert.deepEqual(seenUrls, ["https://openrouter.ai/api/v1/models"]);
|
|
assert.deepEqual(body.models, [{ id: "openai/gpt-4.1", name: "GPT-4.1 via OpenRouter" }]);
|
|
});
|
|
|
|
test("provider models route returns the local catalog for embedding and rerank providers", async () => {
|
|
const voyage = await seedConnection("voyage-ai", {
|
|
apiKey: "voyage-key",
|
|
});
|
|
const jina = await seedConnection("jina-ai", {
|
|
apiKey: "jina-key",
|
|
});
|
|
|
|
const [voyageResponse, jinaResponse] = await Promise.all([
|
|
callRoute(voyage.id),
|
|
callRoute(jina.id),
|
|
]);
|
|
const voyageBody = (await voyageResponse.json()) as any;
|
|
const jinaBody = (await jinaResponse.json()) as any;
|
|
|
|
assert.equal(voyageResponse.status, 200);
|
|
assert.equal(voyageBody.provider, "voyage-ai");
|
|
assert.equal(voyageBody.source, "local_catalog");
|
|
assert.ok(voyageBody.models.some((model) => model.id === "voyage-4-large"));
|
|
assert.ok(voyageBody.models.some((model) => model.id === "voyage-code-3"));
|
|
assert.ok(voyageBody.models.some((model) => model.id === "voyage-4-lite"));
|
|
|
|
assert.equal(jinaResponse.status, 200);
|
|
assert.equal(jinaBody.provider, "jina-ai");
|
|
assert.equal(jinaBody.source, "local_catalog");
|
|
assert.ok(
|
|
jinaBody.models.some(
|
|
(model) =>
|
|
model.id === "jina-embeddings-v5-text-small" &&
|
|
model.apiFormat === "embeddings" &&
|
|
model.supportedEndpoints?.includes("embeddings")
|
|
)
|
|
);
|
|
assert.ok(
|
|
jinaBody.models.some(
|
|
(model) =>
|
|
model.id === "jina-reranker-v3" &&
|
|
model.apiFormat === "rerank" &&
|
|
model.supportedEndpoints?.includes("rerank")
|
|
)
|
|
);
|
|
assert.ok(jinaBody.models.some((model) => model.id === "jina-reranker-m0"));
|
|
});
|
|
|
|
test("provider models route returns the local catalog for Runway video models", async () => {
|
|
const connection = await seedConnection("runwayml", {
|
|
apiKey: "runway-key",
|
|
});
|
|
|
|
const response = await callRoute(connection.id);
|
|
const body = (await response.json()) as any;
|
|
|
|
assert.equal(response.status, 200);
|
|
assert.equal(body.provider, "runwayml");
|
|
assert.equal(body.source, "local_catalog");
|
|
assert.ok(body.models.some((model) => model.id === "gen4.5"));
|
|
assert.ok(body.models.some((model) => model.id === "veo3.1"));
|
|
assert.ok(body.models.some((model) => model.id === "gen3a_turbo"));
|
|
});
|
|
|
|
test("provider models route returns the updated local catalog for GitHub Copilot", async () => {
|
|
const connection = await seedConnection("github", {
|
|
authType: "oauth",
|
|
apiKey: null,
|
|
accessToken: "github-access",
|
|
providerSpecificData: {
|
|
copilotToken: "copilot-token",
|
|
},
|
|
});
|
|
|
|
const response = await callRoute(connection.id);
|
|
const body = (await response.json()) as any;
|
|
|
|
assert.equal(response.status, 200);
|
|
assert.equal(body.provider, "github");
|
|
assert.equal(body.source, "local_catalog");
|
|
assert.ok(body.models.some((model) => model.id === "gpt-5.4"));
|
|
assert.ok(body.models.some((model) => model.id === "gpt-5.3-codex"));
|
|
assert.ok(body.models.some((model) => model.id === "claude-opus-4.7"));
|
|
assert.equal(
|
|
body.models.some((model) => model.id === "gpt-5.1"),
|
|
false
|
|
);
|
|
});
|
|
|
|
test("provider models route returns the expanded local catalog for Kiro", async () => {
|
|
const connection = await seedConnection("kiro", {
|
|
authType: "oauth",
|
|
apiKey: null,
|
|
accessToken: "kiro-access",
|
|
});
|
|
|
|
const response = await callRoute(connection.id);
|
|
const body = (await response.json()) as any;
|
|
|
|
assert.equal(response.status, 200);
|
|
assert.equal(body.provider, "kiro");
|
|
assert.equal(body.source, "local_catalog");
|
|
assert.ok(body.models.some((model) => model.id === "claude-haiku-4.5"));
|
|
assert.ok(body.models.some((model) => model.id === "claude-opus-4.7"));
|
|
assert.ok(body.models.some((model) => model.id === "claude-sonnet-4.6"));
|
|
});
|
|
|
|
test("provider models route returns the local catalog for new built-in chat-openai-compat providers", async () => {
|
|
const connection = await seedConnection("deepinfra", {
|
|
apiKey: "deepinfra-key",
|
|
});
|
|
|
|
const response = await callRoute(connection.id);
|
|
const body = (await response.json()) as any;
|
|
|
|
assert.equal(response.status, 200);
|
|
assert.equal(body.provider, "deepinfra");
|
|
assert.equal(body.source, "local_catalog");
|
|
assert.match(body.warning, /local catalog/i);
|
|
assert.ok(Array.isArray(body.models));
|
|
assert.ok(body.models.length > 0);
|
|
assert.ok(body.models.some((model) => model.id === "openai/gpt-oss-120b"));
|
|
});
|
|
|
|
test("provider models route merges Upstage chat and embedding catalogs", async () => {
|
|
const connection = await seedConnection("upstage", {
|
|
apiKey: "upstage-key",
|
|
});
|
|
|
|
const response = await callRoute(connection.id);
|
|
const body = (await response.json()) as any;
|
|
const modelIds = body.models.map((model) => model.id);
|
|
|
|
assert.equal(response.status, 200);
|
|
assert.equal(body.provider, "upstage");
|
|
assert.equal(body.source, "local_catalog");
|
|
assert.ok(modelIds.includes("solar-pro3"));
|
|
assert.ok(modelIds.includes("solar-mini"));
|
|
assert.ok(modelIds.includes("embedding-query"));
|
|
assert.ok(modelIds.includes("embedding-passage"));
|
|
assert.equal(modelIds.includes("document-parse"), false);
|
|
});
|
|
|
|
test("provider models route caches discovered opencode-go models per connection", async () => {
|
|
const connection = await seedConnection("opencode-go", {
|
|
apiKey: "opencode-go-key",
|
|
});
|
|
let fetchCalls = 0;
|
|
|
|
globalThis.fetch = async (url, init = {}) => {
|
|
fetchCalls += 1;
|
|
assert.equal(String(url), "https://opencode.ai/zen/go/v1/models");
|
|
assert.equal(init.method, "GET");
|
|
assert.equal(init.headers.Authorization, "Bearer opencode-go-key");
|
|
return Response.json({
|
|
data: [{ id: "glm-5.1", name: "GLM 5.1" }],
|
|
});
|
|
};
|
|
|
|
const firstResponse = await callRoute(connection.id);
|
|
const firstBody = (await firstResponse.json()) as any;
|
|
const cachedModels = await modelsDb.getSyncedAvailableModelsForConnection(
|
|
"opencode-go",
|
|
connection.id
|
|
);
|
|
|
|
assert.equal(firstResponse.status, 200);
|
|
assert.equal(firstBody.source, "api");
|
|
assert.deepEqual(firstBody.models, [{ id: "glm-5.1", name: "GLM 5.1" }]);
|
|
assert.deepEqual(cachedModels, [{ id: "glm-5.1", name: "GLM 5.1", source: "imported" }]);
|
|
|
|
globalThis.fetch = async () => {
|
|
throw new Error("cached route should not hit upstream");
|
|
};
|
|
|
|
const cachedResponse = await callRoute(connection.id);
|
|
const cachedBody = (await cachedResponse.json()) as any;
|
|
|
|
assert.equal(cachedResponse.status, 200);
|
|
assert.equal(cachedBody.source, "cache");
|
|
assert.deepEqual(cachedBody.models, [{ id: "glm-5.1", name: "GLM 5.1", source: "imported" }]);
|
|
assert.equal(fetchCalls, 1);
|
|
});
|
|
|
|
test("provider models route falls back to cached models when a refresh fails", async () => {
|
|
const connection = await seedConnection("opencode-go", {
|
|
apiKey: "opencode-go-key",
|
|
});
|
|
await modelsDb.replaceSyncedAvailableModelsForConnection("opencode-go", connection.id, [
|
|
{ id: "cached-go", name: "Cached Go", source: "imported" },
|
|
]);
|
|
let fetchCalls = 0;
|
|
|
|
globalThis.fetch = async () => {
|
|
fetchCalls += 1;
|
|
return new Response("upstream unavailable", { status: 503 });
|
|
};
|
|
|
|
const response = await callRoute(connection.id, "?refresh=true");
|
|
const body = (await response.json()) as any;
|
|
|
|
assert.equal(response.status, 200);
|
|
assert.equal(body.source, "cache");
|
|
assert.match(body.warning, /cached catalog/i);
|
|
assert.deepEqual(body.models, [{ id: "cached-go", name: "Cached Go", source: "imported" }]);
|
|
assert.equal(fetchCalls, 1);
|
|
});
|
|
|
|
test("provider models route clears cached discovery when a refresh returns no remote models", async () => {
|
|
const connection = await seedConnection("opencode-go", {
|
|
apiKey: "opencode-go-key",
|
|
});
|
|
await modelsDb.replaceSyncedAvailableModelsForConnection("opencode-go", connection.id, [
|
|
{ id: "cached-go", name: "Cached Go", source: "imported" },
|
|
]);
|
|
|
|
globalThis.fetch = async () => {
|
|
return Response.json({ data: [] });
|
|
};
|
|
|
|
const response = await callRoute(connection.id, "?refresh=true");
|
|
const body = (await response.json()) as any;
|
|
const cachedModels = await modelsDb.getSyncedAvailableModelsForConnection(
|
|
"opencode-go",
|
|
connection.id
|
|
);
|
|
|
|
assert.equal(response.status, 200);
|
|
assert.equal(body.source, "local_catalog");
|
|
assert.match(body.warning, /no remote models discovered/i);
|
|
assert.ok(body.models.every((model) => model.id !== "cached-go"));
|
|
assert.deepEqual(cachedModels, []);
|
|
});
|
|
|
|
test("provider models route honors autoFetchModels=false and skips remote discovery", async () => {
|
|
const connection = await seedConnection("opencode-go", {
|
|
apiKey: "opencode-go-key",
|
|
providerSpecificData: {
|
|
autoFetchModels: false,
|
|
},
|
|
});
|
|
let called = false;
|
|
|
|
globalThis.fetch = async () => {
|
|
called = true;
|
|
return Response.json({
|
|
data: [{ id: "glm-5.1", name: "GLM 5.1" }],
|
|
});
|
|
};
|
|
|
|
const response = await callRoute(connection.id);
|
|
const body = (await response.json()) as any;
|
|
|
|
assert.equal(response.status, 200);
|
|
assert.equal(body.source, "local_catalog");
|
|
assert.match(body.warning, /auto-fetch disabled/i);
|
|
assert.equal(called, false);
|
|
assert.ok(body.models.some((model) => model.id === "glm-5"));
|
|
});
|
|
|
|
test("provider models route validates Gemini CLI credentials before fetching quota buckets", async () => {
|
|
const missingToken = await seedConnection("gemini-cli", {
|
|
authType: "oauth",
|
|
apiKey: null,
|
|
});
|
|
const missingProject = await seedConnection("gemini-cli", {
|
|
authType: "oauth",
|
|
name: "gemini-cli-projectless",
|
|
accessToken: "gemini-cli-access",
|
|
apiKey: null,
|
|
});
|
|
|
|
const missingTokenResponse = await callRoute(missingToken.id);
|
|
const missingProjectResponse = await callRoute(missingProject.id);
|
|
|
|
assert.equal(missingTokenResponse.status, 400);
|
|
assert.match((await missingTokenResponse.json()).error, /No access token/i);
|
|
assert.equal(missingProjectResponse.status, 400);
|
|
assert.match((await missingProjectResponse.json()).error, /project ID not available/i);
|
|
});
|
|
|
|
test("provider models route maps Gemini CLI quota buckets into a model list", async () => {
|
|
const connection = await seedConnection("gemini-cli", {
|
|
authType: "oauth",
|
|
accessToken: "gemini-cli-access",
|
|
apiKey: null,
|
|
projectId: "projects/demo-123",
|
|
});
|
|
|
|
globalThis.fetch = async (url, init = {}) => {
|
|
assert.equal(String(url), "https://cloudcode-pa.googleapis.com/v1internal:retrieveUserQuota");
|
|
assert.equal(init.headers.Authorization, "Bearer gemini-cli-access");
|
|
assert.deepEqual(JSON.parse(String(init.body)), { project: "projects/demo-123" });
|
|
return Response.json({
|
|
buckets: [{ modelId: "gemini-3-pro-preview" }, { modelId: "gemini-3-flash" }],
|
|
});
|
|
};
|
|
|
|
const response = await callRoute(connection.id);
|
|
const body = (await response.json()) as any;
|
|
|
|
assert.equal(response.status, 200);
|
|
assert.deepEqual(body.models, [
|
|
{ id: "gemini-3-pro-preview", name: "gemini-3-pro-preview", owned_by: "google" },
|
|
{ id: "gemini-3-flash", name: "gemini-3-flash", owned_by: "google" },
|
|
]);
|
|
});
|
|
|
|
test("provider models route prefers providerSpecificData projectId over default-project", async () => {
|
|
const connection = await seedConnection("gemini-cli", {
|
|
authType: "oauth",
|
|
accessToken: "gemini-cli-access",
|
|
apiKey: null,
|
|
projectId: "default-project",
|
|
providerSpecificData: {
|
|
projectId: "projects/custom-psd-456",
|
|
},
|
|
});
|
|
|
|
globalThis.fetch = async (url, init = {}) => {
|
|
assert.equal(String(url), "https://cloudcode-pa.googleapis.com/v1internal:retrieveUserQuota");
|
|
assert.equal(init.headers.Authorization, "Bearer gemini-cli-access");
|
|
assert.deepEqual(JSON.parse(String(init.body)), { project: "projects/custom-psd-456" });
|
|
return Response.json({ buckets: [{ modelId: "gemini-3.1-pro-preview" }] });
|
|
};
|
|
|
|
const response = await callRoute(connection.id);
|
|
const body = (await response.json()) as any;
|
|
|
|
assert.equal(response.status, 200);
|
|
assert.deepEqual(body.models, [
|
|
{ id: "gemini-3.1-pro-preview", name: "gemini-3.1-pro-preview", owned_by: "google" },
|
|
]);
|
|
});
|
|
|
|
test("provider models route rejects projects/default-project placeholders", async () => {
|
|
const connection = await seedConnection("gemini-cli", {
|
|
authType: "oauth",
|
|
accessToken: "gemini-cli-access",
|
|
apiKey: null,
|
|
projectId: "projects/default-project",
|
|
providerSpecificData: {
|
|
projectId: "default-project",
|
|
},
|
|
});
|
|
|
|
globalThis.fetch = async () => {
|
|
throw new Error("retrieveUserQuota should not be called for placeholder project IDs");
|
|
};
|
|
|
|
const response = await callRoute(connection.id);
|
|
const body = (await response.json()) as any;
|
|
|
|
assert.equal(response.status, 400);
|
|
assert.equal(body.error, "Gemini CLI project ID not available. Please reconnect OAuth.");
|
|
});
|
|
|
|
test("provider models route retries Antigravity discovery endpoints before returning remote models", async () => {
|
|
const connection = await seedConnection("antigravity", {
|
|
authType: "oauth",
|
|
accessToken: "ag-access",
|
|
apiKey: null,
|
|
});
|
|
const seenUrls: string[] = [];
|
|
antigravityVersion.seedAntigravityVersionCache("1.22.2");
|
|
|
|
globalThis.fetch = async (url, init = {}) => {
|
|
const urlString = String(url);
|
|
// After PR #2219, the discovery flow calls loadCodeAssist first as a project
|
|
// bootstrap; treat all bootstrap calls as non-fatal failures so the test
|
|
// exercises the discovery retry path.
|
|
if (urlString.includes("/v1internal:loadCodeAssist")) {
|
|
return new Response("nope", { status: 503 });
|
|
}
|
|
seenUrls.push(urlString);
|
|
if (seenUrls.length === 1) {
|
|
return new Response("unavailable", { status: 503 });
|
|
}
|
|
|
|
assert.equal(init.method, "POST");
|
|
assert.equal(init.headers.Authorization, "Bearer ag-access");
|
|
assert.match(init.headers["User-Agent"], /^Antigravity\/1\.22\.2 /);
|
|
assert.equal(init.headers["x-goog-api-client"], undefined);
|
|
return Response.json({
|
|
models: [{ id: "gemini-3-flash", displayName: "Gemini 3 Flash" }],
|
|
});
|
|
};
|
|
|
|
const response = await callRoute(connection.id);
|
|
const body = (await response.json()) as any;
|
|
// After PR #2219, the route tries `:fetchAvailableModels` URLs before
|
|
// `:models` URLs. The test mock returns 503 on the first call and success
|
|
// on the second, so only the first two `:fetchAvailableModels` URLs are
|
|
// hit — `:models` URLs are never reached. Assert on the actual discovery
|
|
// sequence the route follows.
|
|
const discoveryUrls = seenUrls.filter(
|
|
(url) => url.includes("/v1internal:fetchAvailableModels") || url.includes("/v1internal:models")
|
|
);
|
|
|
|
assert.equal(response.status, 200);
|
|
assert.equal(body.source, "api");
|
|
assert.deepEqual(discoveryUrls, [
|
|
"https://daily-cloudcode-pa.googleapis.com/v1internal:fetchAvailableModels",
|
|
"https://cloudcode-pa.googleapis.com/v1internal:fetchAvailableModels",
|
|
]);
|
|
assert.deepEqual(body.models, [{ id: "gemini-3-flash-preview", name: "Gemini 3 Flash" }]);
|
|
});
|
|
|
|
test("provider models route falls back through all Antigravity discovery endpoints when needed", async () => {
|
|
const connection = await seedConnection("antigravity", {
|
|
authType: "oauth",
|
|
accessToken: "ag-access",
|
|
apiKey: null,
|
|
});
|
|
const seenUrls = [];
|
|
|
|
globalThis.fetch = async (url) => {
|
|
seenUrls.push(String(url));
|
|
return new Response("down", { status: 502 });
|
|
};
|
|
|
|
const response = await callRoute(connection.id);
|
|
const body = (await response.json()) as any;
|
|
const discoveryUrls = seenUrls.filter((url) => url.includes("/v1internal:models"));
|
|
|
|
assert.equal(response.status, 200);
|
|
assert.equal(body.source, "local_catalog");
|
|
assert.match(body.warning, /local catalog/i);
|
|
assert.deepEqual(discoveryUrls, [
|
|
"https://daily-cloudcode-pa.googleapis.com/v1internal:models",
|
|
"https://cloudcode-pa.googleapis.com/v1internal:models",
|
|
"https://daily-cloudcode-pa.sandbox.googleapis.com/v1internal:models",
|
|
]);
|
|
assert.ok(body.models.some((model) => model.id === "gemini-3-pro-preview"));
|
|
});
|
|
|
|
test("provider models route returns the local catalog for OAuth-backed Qwen connections", async () => {
|
|
const connection = await seedConnection("qwen", {
|
|
authType: "oauth",
|
|
accessToken: "qwen-access",
|
|
apiKey: null,
|
|
});
|
|
|
|
const response = await callRoute(connection.id);
|
|
const body = (await response.json()) as any;
|
|
|
|
assert.equal(response.status, 200);
|
|
assert.equal(body.source, "local_catalog");
|
|
assert.ok(Array.isArray(body.models));
|
|
});
|
|
|
|
test("provider models route filters hidden models from the static Claude catalog when requested", async () => {
|
|
const connection = await seedConnection("claude", {
|
|
authType: "oauth",
|
|
accessToken: "claude-access",
|
|
apiKey: null,
|
|
});
|
|
modelsDb.mergeModelCompatOverride("claude", "claude-sonnet-4-6", { isHidden: true });
|
|
|
|
const response = await callRoute(connection.id, "?excludeHidden=true");
|
|
const body = (await response.json()) as any;
|
|
|
|
assert.equal(response.status, 200);
|
|
assert.equal(body.provider, "claude");
|
|
assert.ok(body.models.some((model) => model.id === "claude-opus-4-7"));
|
|
assert.equal(
|
|
body.models.some((model) => model.id === "claude-sonnet-4-6"),
|
|
false
|
|
);
|
|
assert.ok(body.models.some((model) => model.id === "claude-opus-4-6"));
|
|
});
|
|
|
|
test("provider models route rejects Anthropic-compatible providers without a base URL", async () => {
|
|
const connection = await seedConnection("anthropic-compatible-demo", {
|
|
apiKey: "sk-anthropic-compatible",
|
|
});
|
|
|
|
const response = await callRoute(connection.id);
|
|
|
|
assert.equal(response.status, 400);
|
|
assert.deepEqual(await response.json(), {
|
|
error: "No base URL configured for Anthropic compatible provider",
|
|
});
|
|
});
|
|
|
|
test("provider models route trims Anthropic-compatible message URLs and filters hidden upstream models", async () => {
|
|
const connection = await seedConnection("anthropic-compatible-demo", {
|
|
apiKey: "sk-anthropic-compatible",
|
|
accessToken: "anthropic-access",
|
|
providerSpecificData: {
|
|
baseUrl: "https://proxy.example.com/v1/messages",
|
|
},
|
|
});
|
|
modelsDb.mergeModelCompatOverride("anthropic-compatible-demo", "hidden-model", {
|
|
isHidden: true,
|
|
});
|
|
|
|
globalThis.fetch = async (url, init = {}) => {
|
|
assert.equal(String(url), "https://proxy.example.com/v1/models");
|
|
assert.equal(init.method, "GET");
|
|
assert.equal(init.headers["Content-Type"], "application/json");
|
|
assert.equal(init.headers["x-api-key"], "sk-anthropic-compatible");
|
|
assert.equal(init.headers.Authorization, "Bearer anthropic-access");
|
|
assert.equal(init.headers["anthropic-version"], "2023-06-01");
|
|
|
|
return Response.json({
|
|
data: [
|
|
{ id: "visible-model", name: "Visible Model" },
|
|
{ id: "hidden-model", name: "Hidden Model" },
|
|
],
|
|
});
|
|
};
|
|
|
|
const response = await callRoute(connection.id, "?excludeHidden=true");
|
|
const body = (await response.json()) as any;
|
|
|
|
assert.equal(response.status, 200);
|
|
assert.deepEqual(body.models, [{ id: "visible-model", name: "Visible Model" }]);
|
|
});
|
|
|
|
test("provider models route forwards Anthropic-compatible upstream failures", async () => {
|
|
const connection = await seedConnection("anthropic-compatible-demo", {
|
|
apiKey: "sk-anthropic-compatible",
|
|
providerSpecificData: {
|
|
baseUrl: "https://proxy.example.com/v1/messages",
|
|
},
|
|
});
|
|
|
|
globalThis.fetch = async () => new Response("upstream unavailable", { status: 502 });
|
|
|
|
const response = await callRoute(connection.id);
|
|
|
|
assert.equal(response.status, 502);
|
|
assert.deepEqual(await response.json(), {
|
|
error: "Failed to fetch models: 502",
|
|
});
|
|
});
|
|
|
|
test("provider models route paginates generic providers and filters hidden models when requested", async () => {
|
|
const connection = await seedConnection("gemini", {
|
|
apiKey: "gm-key",
|
|
});
|
|
modelsDb.mergeModelCompatOverride("gemini", "gemini-hidden", { isHidden: true });
|
|
const seenUrls = [];
|
|
|
|
globalThis.fetch = async (url) => {
|
|
const currentUrl = String(url);
|
|
seenUrls.push(currentUrl);
|
|
if (!currentUrl.includes("pageToken=")) {
|
|
assert.match(currentUrl, /key=gm-key/);
|
|
return Response.json({
|
|
models: [
|
|
{
|
|
name: "models/gemini-visible",
|
|
displayName: "Gemini Visible",
|
|
supportedGenerationMethods: ["generateContent"],
|
|
},
|
|
{
|
|
name: "models/gemini-hidden",
|
|
displayName: "Gemini Hidden",
|
|
supportedGenerationMethods: ["generateContent"],
|
|
},
|
|
],
|
|
nextPageToken: "page-2",
|
|
});
|
|
}
|
|
|
|
assert.match(currentUrl, /pageToken=page-2/);
|
|
assert.match(currentUrl, /key=gm-key/);
|
|
return Response.json({
|
|
models: [
|
|
{
|
|
name: "models/text-embedding-004",
|
|
displayName: "Text Embedding 004",
|
|
supportedGenerationMethods: ["embedContent"],
|
|
},
|
|
],
|
|
});
|
|
};
|
|
|
|
const response = await callRoute(connection.id, "?excludeHidden=true");
|
|
const body = (await response.json()) as any;
|
|
|
|
assert.equal(response.status, 200);
|
|
assert.deepEqual(body.models.map((model) => model.id).sort(), [
|
|
"gemini-visible",
|
|
"text-embedding-004",
|
|
]);
|
|
assert.equal(seenUrls.length, 2);
|
|
});
|
|
|
|
test("provider models route stops pagination when the upstream repeats the next page token", async () => {
|
|
const connection = await seedConnection("gemini", {
|
|
apiKey: "gm-key",
|
|
});
|
|
let calls = 0;
|
|
|
|
globalThis.fetch = async () => {
|
|
calls += 1;
|
|
return Response.json({
|
|
models: [
|
|
{
|
|
name: `models/gemini-page-${calls}`,
|
|
displayName: `Gemini Page ${calls}`,
|
|
supportedGenerationMethods: ["generateContent"],
|
|
},
|
|
],
|
|
nextPageToken: "duplicate-token",
|
|
});
|
|
};
|
|
|
|
const response = await callRoute(connection.id);
|
|
const body = (await response.json()) as any;
|
|
|
|
assert.equal(response.status, 200);
|
|
assert.deepEqual(
|
|
body.models.map((model) => model.id),
|
|
["gemini-page-1", "gemini-page-2"]
|
|
);
|
|
assert.equal(calls, 2);
|
|
});
|
|
|
|
test("provider models route forwards upstream status codes for generic provider model fetch failures", async () => {
|
|
const connection = await seedConnection("groq", {
|
|
apiKey: "groq-models-token",
|
|
});
|
|
|
|
globalThis.fetch = async () => new Response("upstream unavailable", { status: 503 });
|
|
|
|
const response = await callRoute(connection.id);
|
|
const body = (await response.json()) as any;
|
|
|
|
assert.equal(response.status, 200);
|
|
assert.equal(body.source, "local_catalog");
|
|
assert.match(body.warning, /local catalog/i);
|
|
assert.ok(Array.isArray(body.models));
|
|
assert.ok(body.models.length > 0);
|
|
});
|
|
|
|
test("provider models route returns 500 when fetching models throws unexpectedly", async () => {
|
|
const connection = await seedConnection("groq", {
|
|
apiKey: "groq-models-token",
|
|
});
|
|
|
|
globalThis.fetch = async () => {
|
|
throw new Error("socket closed");
|
|
};
|
|
|
|
const response = await callRoute(connection.id);
|
|
const body = (await response.json()) as any;
|
|
|
|
assert.equal(response.status, 200);
|
|
assert.equal(body.source, "local_catalog");
|
|
assert.match(body.warning, /local catalog/i);
|
|
});
|
|
|
|
test("provider models route rejects generic providers without any configured token", async () => {
|
|
const connection = await seedConnection("groq", {
|
|
apiKey: null,
|
|
accessToken: null,
|
|
});
|
|
let called = false;
|
|
|
|
globalThis.fetch = async () => {
|
|
called = true;
|
|
return Response.json({ data: [] });
|
|
};
|
|
|
|
const response = await callRoute(connection.id);
|
|
const body = (await response.json()) as any;
|
|
|
|
assert.equal(response.status, 200);
|
|
assert.equal(body.source, "local_catalog");
|
|
assert.match(body.warning, /local catalog/i);
|
|
assert.equal(called, false);
|
|
});
|
|
|
|
test("provider models route discovers active DataRobot gateway models from the catalog endpoint", async () => {
|
|
const connection = await seedConnection("datarobot", {
|
|
apiKey: "dr-key",
|
|
providerSpecificData: {
|
|
baseUrl: "https://app.datarobot.com",
|
|
},
|
|
});
|
|
|
|
globalThis.fetch = async (url, init = {}) => {
|
|
assert.equal(String(url), "https://app.datarobot.com/genai/llmgw/catalog/");
|
|
assert.equal(init.method, "GET");
|
|
assert.equal(init.headers.Authorization, "Bearer dr-key");
|
|
|
|
return Response.json({
|
|
data: [
|
|
{ model: "azure/gpt-5-mini-2025-08-07", isActive: true },
|
|
{ model: "azure/gpt-4o-mini", label: "Azure GPT-4o Mini", isActive: true },
|
|
{ model: "anthropic/claude-sonnet-4-6", isActive: false },
|
|
],
|
|
});
|
|
};
|
|
|
|
const response = await callRoute(connection.id);
|
|
const body = (await response.json()) as any;
|
|
|
|
assert.equal(response.status, 200);
|
|
assert.equal(body.provider, "datarobot");
|
|
assert.equal(body.source, "api");
|
|
assert.deepEqual(body.models, [
|
|
{
|
|
id: "azure/gpt-5-mini-2025-08-07",
|
|
name: "azure/gpt-5-mini-2025-08-07",
|
|
owned_by: "datarobot",
|
|
},
|
|
{
|
|
id: "azure/gpt-4o-mini",
|
|
name: "Azure GPT-4o Mini",
|
|
owned_by: "datarobot",
|
|
},
|
|
]);
|
|
});
|
|
|
|
test("provider models route discovers Clarifai OpenAI-compatible models with Key auth", async () => {
|
|
const connection = await seedConnection("clarifai", {
|
|
apiKey: "clarifai-pat",
|
|
});
|
|
|
|
globalThis.fetch = async (url, init = {}) => {
|
|
assert.equal(String(url), "https://api.clarifai.com/v2/ext/openai/v1/models");
|
|
assert.equal(init.method, "GET");
|
|
assert.equal(init.headers.Authorization, "Key clarifai-pat");
|
|
|
|
return Response.json({
|
|
data: [
|
|
{
|
|
id: "openai/chat-completion/models/gpt-oss-120b",
|
|
display_name: "GPT-OSS 120B",
|
|
},
|
|
{ id: "anthropic/completion/models/claude-sonnet-4" },
|
|
],
|
|
});
|
|
};
|
|
|
|
const response = await callRoute(connection.id);
|
|
const body = (await response.json()) as any;
|
|
|
|
assert.equal(response.status, 200);
|
|
assert.equal(body.provider, "clarifai");
|
|
assert.equal(body.source, "api");
|
|
assert.deepEqual(body.models, [
|
|
{
|
|
id: "openai/chat-completion/models/gpt-oss-120b",
|
|
name: "GPT-OSS 120B",
|
|
owned_by: "clarifai",
|
|
},
|
|
{
|
|
id: "anthropic/completion/models/claude-sonnet-4",
|
|
name: "anthropic/completion/models/claude-sonnet-4",
|
|
owned_by: "clarifai",
|
|
},
|
|
]);
|
|
});
|
|
|
|
test("provider models route discovers Azure AI Foundry deployments through the v1 models endpoint", async () => {
|
|
const connection = await seedConnection("azure-ai", {
|
|
apiKey: "azure-ai-key",
|
|
providerSpecificData: {
|
|
baseUrl: "https://my-foundry.services.ai.azure.com",
|
|
},
|
|
});
|
|
|
|
globalThis.fetch = async (url, init = {}) => {
|
|
assert.equal(String(url), "https://my-foundry.services.ai.azure.com/openai/v1/models");
|
|
assert.equal(init.method, "GET");
|
|
assert.equal(init.headers["api-key"], "azure-ai-key");
|
|
|
|
return Response.json({
|
|
data: [{ id: "DeepSeek-V3.1", display_name: "DeepSeek V3.1" }, { name: "Claude-Opus-4.6" }],
|
|
});
|
|
};
|
|
|
|
const response = await callRoute(connection.id);
|
|
const body = (await response.json()) as any;
|
|
|
|
assert.equal(response.status, 200);
|
|
assert.equal(body.provider, "azure-ai");
|
|
assert.equal(body.source, "api");
|
|
assert.deepEqual(body.models, [
|
|
{ id: "DeepSeek-V3.1", name: "DeepSeek V3.1", owned_by: "azure-ai" },
|
|
{ id: "Claude-Opus-4.6", name: "Claude-Opus-4.6", owned_by: "azure-ai" },
|
|
]);
|
|
});
|
|
|
|
test("provider models route discovers Azure OpenAI deployments from the resource endpoint", async () => {
|
|
const connection = await seedConnection("azure-openai", {
|
|
apiKey: "azure-openai-key",
|
|
providerSpecificData: {
|
|
baseUrl: "https://my-resource.openai.azure.com/openai",
|
|
apiVersion: "2024-12-01-preview",
|
|
},
|
|
});
|
|
|
|
globalThis.fetch = async (url, init = {}) => {
|
|
assert.equal(
|
|
String(url),
|
|
"https://my-resource.openai.azure.com/openai/deployments?api-version=2024-12-01-preview"
|
|
);
|
|
assert.equal(init.method, "GET");
|
|
assert.equal(init.headers["api-key"], "azure-openai-key");
|
|
|
|
return Response.json({
|
|
data: [
|
|
{ id: "gpt4o-prod", model: "gpt-4o", display_name: "GPT-4o Production" },
|
|
{ id: "o3-mini-staging", model: "o3-mini" },
|
|
],
|
|
});
|
|
};
|
|
|
|
const response = await callRoute(connection.id);
|
|
const body = (await response.json()) as any;
|
|
|
|
assert.equal(response.status, 200);
|
|
assert.equal(body.provider, "azure-openai");
|
|
assert.equal(body.source, "api");
|
|
assert.deepEqual(body.models, [
|
|
{ id: "gpt4o-prod", name: "GPT-4o Production", owned_by: "azure-openai" },
|
|
{ id: "o3-mini-staging", name: "o3-mini-staging", owned_by: "azure-openai" },
|
|
]);
|
|
});
|
|
|
|
test("provider models route discovers native Bedrock foundation models and inference profiles", async () => {
|
|
const connection = await seedConnection("bedrock", {
|
|
apiKey: "bedrock-key",
|
|
providerSpecificData: {
|
|
region: "eu-west-2",
|
|
},
|
|
});
|
|
const seenUrls: string[] = [];
|
|
|
|
globalThis.fetch = async (url, init = {}) => {
|
|
const target = String(url);
|
|
seenUrls.push(target);
|
|
assert.equal(init.method, "GET");
|
|
assert.equal(init.headers.Authorization, "Bearer bedrock-key");
|
|
|
|
if (
|
|
target === "https://bedrock.eu-west-2.amazonaws.com/foundation-models?byOutputModality=TEXT"
|
|
) {
|
|
return Response.json({
|
|
modelSummaries: [
|
|
{
|
|
modelId: "anthropic.claude-sonnet-4-6",
|
|
modelName: "Claude Sonnet 4.6",
|
|
providerName: "Anthropic",
|
|
inputModalities: ["TEXT", "IMAGE"],
|
|
outputModalities: ["TEXT"],
|
|
responseStreamingSupported: true,
|
|
},
|
|
],
|
|
});
|
|
}
|
|
|
|
if (
|
|
target ===
|
|
"https://bedrock.eu-west-2.amazonaws.com/inference-profiles?maxResults=100&typeEquals=SYSTEM_DEFINED"
|
|
) {
|
|
return Response.json({
|
|
inferenceProfileSummaries: [
|
|
{
|
|
inferenceProfileId: "eu.anthropic.claude-sonnet-4-6",
|
|
inferenceProfileName: "EU Claude Sonnet 4.6",
|
|
models: [
|
|
{
|
|
modelArn: "arn:aws:bedrock:eu-west-2::foundation-model/anthropic.claude-sonnet-4-6",
|
|
},
|
|
],
|
|
},
|
|
],
|
|
});
|
|
}
|
|
|
|
throw new Error("unexpected fetch: " + target);
|
|
};
|
|
|
|
const response = await callRoute(connection.id);
|
|
const body = (await response.json()) as any;
|
|
|
|
assert.equal(response.status, 200);
|
|
assert.equal(body.provider, "bedrock");
|
|
assert.equal(body.source, "api");
|
|
assert.deepEqual(seenUrls, [
|
|
"https://bedrock.eu-west-2.amazonaws.com/foundation-models?byOutputModality=TEXT",
|
|
"https://bedrock.eu-west-2.amazonaws.com/inference-profiles?maxResults=100&typeEquals=SYSTEM_DEFINED",
|
|
]);
|
|
assert.deepEqual(body.models, [
|
|
{
|
|
id: "anthropic.claude-sonnet-4-6",
|
|
name: "Claude Sonnet 4.6",
|
|
owned_by: "Anthropic",
|
|
source: "foundation",
|
|
supportsStreaming: true,
|
|
supportsVision: true,
|
|
inputTokenLimit: 1000000,
|
|
outputTokenLimit: 64000,
|
|
},
|
|
{
|
|
id: "eu.anthropic.claude-sonnet-4-6",
|
|
name: "EU Claude Sonnet 4.6",
|
|
owned_by: "bedrock",
|
|
source: "inference_profile",
|
|
supportsStreaming: true,
|
|
inputTokenLimit: 1000000,
|
|
outputTokenLimit: 64000,
|
|
},
|
|
]);
|
|
});
|
|
|
|
test("provider models route discovers watsonx gateway models from the v1 models endpoint", async () => {
|
|
const connection = await seedConnection("watsonx", {
|
|
apiKey: "watsonx-key",
|
|
providerSpecificData: {
|
|
baseUrl: "https://ca-tor.ml.cloud.ibm.com",
|
|
},
|
|
});
|
|
|
|
globalThis.fetch = async (url, init = {}) => {
|
|
assert.equal(String(url), "https://ca-tor.ml.cloud.ibm.com/ml/gateway/v1/models");
|
|
assert.equal(init.method, "GET");
|
|
assert.equal(init.headers.Authorization, "Bearer watsonx-key");
|
|
|
|
return Response.json({
|
|
data: [
|
|
{ id: "ibm/granite-3-3-8b-instruct", display_name: "Granite 3.3 8B Instruct" },
|
|
{ model: "openai/gpt-4o", provider: "openai" },
|
|
],
|
|
});
|
|
};
|
|
|
|
const response = await callRoute(connection.id);
|
|
const body = (await response.json()) as any;
|
|
|
|
assert.equal(response.status, 200);
|
|
assert.equal(body.provider, "watsonx");
|
|
assert.equal(body.source, "api");
|
|
assert.deepEqual(body.models, [
|
|
{
|
|
id: "ibm/granite-3-3-8b-instruct",
|
|
name: "Granite 3.3 8B Instruct",
|
|
owned_by: "watsonx",
|
|
},
|
|
{
|
|
id: "openai/gpt-4o",
|
|
name: "openai/gpt-4o",
|
|
owned_by: "openai",
|
|
},
|
|
]);
|
|
});
|
|
|
|
test("provider models route discovers OCI OpenAI-compatible models and forwards the project header", async () => {
|
|
const connection = await seedConnection("oci", {
|
|
apiKey: "oci-key",
|
|
projectId: "ocid1.generativeaiproject.oc1.us-chicago-1.demo",
|
|
providerSpecificData: {
|
|
baseUrl: "https://inference.generativeai.us-chicago-1.oci.oraclecloud.com",
|
|
},
|
|
});
|
|
|
|
globalThis.fetch = async (url, init = {}) => {
|
|
assert.equal(
|
|
String(url),
|
|
"https://inference.generativeai.us-chicago-1.oci.oraclecloud.com/openai/v1/models"
|
|
);
|
|
assert.equal(init.method, "GET");
|
|
assert.equal(init.headers.Authorization, "Bearer oci-key");
|
|
assert.equal(init.headers["OpenAI-Project"], "ocid1.generativeaiproject.oc1.us-chicago-1.demo");
|
|
|
|
return Response.json({
|
|
data: [
|
|
{ id: "openai.gpt-oss-20b", display_name: "OpenAI GPT-OSS 20B" },
|
|
{ id: "google.gemini-2.5-pro" },
|
|
],
|
|
});
|
|
};
|
|
|
|
const response = await callRoute(connection.id);
|
|
const body = (await response.json()) as any;
|
|
|
|
assert.equal(response.status, 200);
|
|
assert.equal(body.provider, "oci");
|
|
assert.equal(body.source, "api");
|
|
assert.deepEqual(body.models, [
|
|
{
|
|
id: "openai.gpt-oss-20b",
|
|
name: "OpenAI GPT-OSS 20B",
|
|
owned_by: "oci",
|
|
},
|
|
{
|
|
id: "google.gemini-2.5-pro",
|
|
name: "google.gemini-2.5-pro",
|
|
owned_by: "oci",
|
|
},
|
|
]);
|
|
});
|
|
|
|
test("provider models route discovers Modal models from the configured OpenAI-compatible /v1 endpoint", async () => {
|
|
const connection = await seedConnection("modal", {
|
|
apiKey: "modal-key",
|
|
providerSpecificData: {
|
|
baseUrl: "https://alice--demo.modal.run/v1",
|
|
},
|
|
});
|
|
|
|
globalThis.fetch = async (url, init = {}) => {
|
|
assert.equal(String(url), "https://alice--demo.modal.run/v1/models");
|
|
assert.equal(init.method, "GET");
|
|
assert.equal(init.headers.Authorization, "Bearer modal-key");
|
|
|
|
return Response.json({
|
|
data: [
|
|
{ id: "Qwen/Qwen3-4B-Thinking-2507-FP8", display_name: "Qwen3 4B Thinking FP8" },
|
|
{ id: "google/gemma-4-26B-A4B-it" },
|
|
],
|
|
});
|
|
};
|
|
|
|
const response = await callRoute(connection.id);
|
|
const body = (await response.json()) as any;
|
|
|
|
assert.equal(response.status, 200);
|
|
assert.equal(body.provider, "modal");
|
|
assert.equal(body.source, "api");
|
|
assert.deepEqual(body.models, [
|
|
{
|
|
id: "Qwen/Qwen3-4B-Thinking-2507-FP8",
|
|
name: "Qwen3 4B Thinking FP8",
|
|
owned_by: "modal",
|
|
},
|
|
{
|
|
id: "google/gemma-4-26B-A4B-it",
|
|
name: "google/gemma-4-26B-A4B-it",
|
|
owned_by: "modal",
|
|
},
|
|
]);
|
|
});
|
|
|
|
test("provider models route always returns the Reka preset catalog", async () => {
|
|
const connection = await seedConnection("reka", {
|
|
apiKey: "reka-key",
|
|
providerSpecificData: {
|
|
baseUrl: "https://api.reka.ai/v1",
|
|
},
|
|
});
|
|
|
|
globalThis.fetch = async () => {
|
|
throw new Error("Reka models endpoint should not be probed");
|
|
};
|
|
|
|
const response = await callRoute(connection.id);
|
|
const body = (await response.json()) as any;
|
|
|
|
assert.equal(response.status, 200);
|
|
assert.equal(body.provider, "reka");
|
|
assert.equal(body.source, "local_catalog");
|
|
assert.deepEqual(
|
|
body.models.map((model) => model.id),
|
|
["reka-flash-3", "reka-edge-2603"]
|
|
);
|
|
});
|
|
|
|
test("provider models route returns Reka local catalog without an API key", async () => {
|
|
const connection = await seedConnection("reka", {
|
|
providerSpecificData: {
|
|
baseUrl: "https://api.reka.ai/v1",
|
|
},
|
|
});
|
|
|
|
globalThis.fetch = async () => {
|
|
throw new Error("Reka models endpoint should not be probed without a token");
|
|
};
|
|
|
|
const response = await callRoute(connection.id);
|
|
const body = (await response.json()) as any;
|
|
|
|
assert.equal(response.status, 200);
|
|
assert.equal(body.provider, "reka");
|
|
assert.equal(body.source, "local_catalog");
|
|
assert.deepEqual(
|
|
body.models.map((model) => model.id),
|
|
["reka-flash-3", "reka-edge-2603"]
|
|
);
|
|
});
|
|
|
|
test("provider models route discovers SAP models from AI_API_URL derived from deploymentUrl", async () => {
|
|
const connection = await seedConnection("sap", {
|
|
apiKey: "sap-key",
|
|
providerSpecificData: {
|
|
baseUrl: "https://sap.example.com/v2/lm/deployments/demo-deployment",
|
|
resourceGroup: "shared",
|
|
},
|
|
});
|
|
|
|
globalThis.fetch = async (url, init = {}) => {
|
|
assert.equal(String(url), "https://sap.example.com/v2/lm/scenarios/foundation-models/models");
|
|
assert.equal(init.method, "GET");
|
|
assert.equal(init.headers.Authorization, "Bearer sap-key");
|
|
assert.equal(init.headers["AI-Resource-Group"], "shared");
|
|
|
|
return Response.json({
|
|
resources: [
|
|
{ model: "gpt-4o", displayName: "GPT-4o", provider: "OpenAI" },
|
|
{ model: "mistralai--mistral-medium-instruct", provider: "Mistral AI" },
|
|
],
|
|
});
|
|
};
|
|
|
|
const response = await callRoute(connection.id);
|
|
const body = (await response.json()) as any;
|
|
|
|
assert.equal(response.status, 200);
|
|
assert.equal(body.provider, "sap");
|
|
assert.equal(body.source, "api");
|
|
assert.deepEqual(body.models, [
|
|
{
|
|
id: "gpt-4o",
|
|
name: "GPT-4o",
|
|
owned_by: "OpenAI",
|
|
},
|
|
{
|
|
id: "mistralai--mistral-medium-instruct",
|
|
name: "mistralai--mistral-medium-instruct",
|
|
owned_by: "Mistral AI",
|
|
},
|
|
]);
|
|
});
|
|
|
|
test("provider models route rejects unsupported providers without a models config", async () => {
|
|
const connection = await seedConnection("unsupported-provider", {
|
|
apiKey: "sk-unsupported",
|
|
});
|
|
|
|
const response = await callRoute(connection.id);
|
|
|
|
assert.equal(response.status, 400);
|
|
assert.deepEqual(await response.json(), {
|
|
error: "Provider unsupported-provider does not support models listing",
|
|
});
|
|
});
|
|
|
|
test("provider models route uses provider-specific auth headers for Kimi Coding", async () => {
|
|
const connection = await seedConnection("kimi-coding", {
|
|
apiKey: "kimi-coding-key",
|
|
});
|
|
|
|
globalThis.fetch = async (url, init = {}) => {
|
|
assert.equal(String(url), "https://api.kimi.com/coding/v1/models");
|
|
assert.equal(init.method, "GET");
|
|
assert.equal(init.headers["x-api-key"], "kimi-coding-key");
|
|
assert.equal(init.headers.Authorization, undefined);
|
|
|
|
return Response.json({
|
|
data: [{ id: "kimi-k2.5", name: "Kimi K2.5" }],
|
|
});
|
|
};
|
|
|
|
const response = await callRoute(connection.id);
|
|
const body = (await response.json()) as any;
|
|
|
|
assert.equal(response.status, 200);
|
|
assert.equal(body.provider, "kimi-coding");
|
|
assert.deepEqual(body.models, [{ id: "kimi-k2.5", name: "Kimi K2.5" }]);
|
|
});
|