mirror of
https://github.com/diegosouzapw/OmniRoute.git
synced 2026-07-31 12:22:14 +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>
1497 lines
46 KiB
TypeScript
1497 lines
46 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-stream-utils-"));
|
|
process.env.DATA_DIR = TEST_DATA_DIR;
|
|
const core = await import("../../src/lib/db/core.ts");
|
|
|
|
const { createSSEStream, createSSETransformStreamWithLogger, createPassthroughStreamWithLogger } =
|
|
await import("../../open-sse/utils/stream.ts");
|
|
const {
|
|
buildStreamSummaryFromEvents,
|
|
compactStructuredStreamPayload,
|
|
createStructuredSSECollector,
|
|
} = await import("../../open-sse/utils/streamPayloadCollector.ts");
|
|
const { FORMATS } = await import("../../open-sse/translator/formats.ts");
|
|
const { createRequestLogger } = await import("../../open-sse/utils/requestLogger.ts");
|
|
|
|
const textEncoder = new TextEncoder();
|
|
const SYNTHETIC_CLAUDE_EMPTY_RESPONSE_TEXT =
|
|
"[Proxy Error] The upstream API returned an empty response. Please retry the request.";
|
|
|
|
async function readTransformed(chunks, options) {
|
|
const source = new ReadableStream({
|
|
start(controller) {
|
|
for (const chunk of chunks) {
|
|
controller.enqueue(textEncoder.encode(chunk));
|
|
}
|
|
controller.close();
|
|
},
|
|
});
|
|
|
|
return new Response(source.pipeThrough(createSSEStream(options))).text();
|
|
}
|
|
|
|
async function readWithTransform(chunks, transformStream) {
|
|
const source = new ReadableStream({
|
|
start(controller) {
|
|
for (const chunk of chunks) {
|
|
controller.enqueue(textEncoder.encode(chunk));
|
|
}
|
|
controller.close();
|
|
},
|
|
});
|
|
|
|
return new Response(source.pipeThrough(transformStream)).text();
|
|
}
|
|
|
|
test.after(() => {
|
|
core.resetDbInstance();
|
|
if (fs.existsSync(TEST_DATA_DIR)) {
|
|
for (const entry of fs.readdirSync(TEST_DATA_DIR)) {
|
|
fs.rmSync(path.join(TEST_DATA_DIR, entry), { recursive: true, force: true });
|
|
}
|
|
}
|
|
});
|
|
|
|
test("createSSEStream passthrough normalizes tool-call finishes and reports the assembled response", async () => {
|
|
let onCompletePayload = null;
|
|
const text = await readTransformed(
|
|
[
|
|
`data: ${JSON.stringify({
|
|
id: "chatcmpl_1",
|
|
object: "chat.completion.chunk",
|
|
created: 1,
|
|
model: "gpt-4.1-mini",
|
|
choices: [{ index: 0, delta: { role: "assistant", content: "Hello " } }],
|
|
})}\n\n`,
|
|
`data: ${JSON.stringify({
|
|
id: "chatcmpl_1",
|
|
object: "chat.completion.chunk",
|
|
created: 1,
|
|
model: "gpt-4.1-mini",
|
|
choices: [
|
|
{
|
|
index: 0,
|
|
delta: {
|
|
tool_calls: [
|
|
{
|
|
index: 0,
|
|
id: "call_1",
|
|
type: "function",
|
|
function: {
|
|
name: "read_file",
|
|
arguments: '{"path":"/tmp/a"}',
|
|
},
|
|
},
|
|
],
|
|
},
|
|
},
|
|
],
|
|
})}\n\n`,
|
|
`data: ${JSON.stringify({
|
|
id: "chatcmpl_1",
|
|
object: "chat.completion.chunk",
|
|
created: 1,
|
|
model: "gpt-4.1-mini",
|
|
choices: [{ index: 0, delta: {}, finish_reason: "stop" }],
|
|
})}\n\n`,
|
|
],
|
|
{
|
|
mode: "passthrough",
|
|
sourceFormat: FORMATS.OPENAI,
|
|
provider: "openai",
|
|
model: "gpt-4.1-mini",
|
|
body: {
|
|
messages: [{ role: "user", content: "hello" }],
|
|
},
|
|
onComplete(payload) {
|
|
onCompletePayload = payload;
|
|
},
|
|
}
|
|
);
|
|
|
|
assert.match(text, /"content":"Hello "/);
|
|
assert.match(text, /"name":"read_file"/);
|
|
assert.match(text, /"finish_reason":"tool_calls"/);
|
|
assert.equal(onCompletePayload.status, 200);
|
|
assert.equal(onCompletePayload.responseBody.choices[0].finish_reason, "tool_calls");
|
|
assert.equal(onCompletePayload.responseBody.choices[0].message.tool_calls[0].id, "call_1");
|
|
assert.equal(onCompletePayload.responseBody.choices[0].message.content, "Hello");
|
|
assert.equal(onCompletePayload.clientPayload._streamed, true);
|
|
});
|
|
|
|
test("createSSEStream passthrough converts textual tool-call content into structured call log tool_calls", async () => {
|
|
let onCompletePayload = null;
|
|
const toolArgs = JSON.stringify({
|
|
command: 'sqlite3 /root/.o\u200dmniroute/omniroute.db ".tables"',
|
|
});
|
|
const toolText = `[Tool call: terminal]\nArguments: ${toolArgs}`;
|
|
|
|
const text = await readTransformed(
|
|
[
|
|
`data: ${JSON.stringify({
|
|
id: "chatcmpl_textual_tool",
|
|
object: "chat.completion.chunk",
|
|
created: 1,
|
|
model: "antigravity/gemini-3.5-flash-low",
|
|
choices: [{ index: 0, delta: { role: "assistant", content: toolText } }],
|
|
})}\n\n`,
|
|
`data: ${JSON.stringify({
|
|
id: "chatcmpl_textual_tool",
|
|
object: "chat.completion.chunk",
|
|
created: 1,
|
|
model: "antigravity/gemini-3.5-flash-low",
|
|
choices: [{ index: 0, delta: {}, finish_reason: "stop" }],
|
|
})}\n\n`,
|
|
],
|
|
{
|
|
mode: "passthrough",
|
|
sourceFormat: FORMATS.OPENAI,
|
|
provider: "antigravity",
|
|
model: "antigravity/gemini-3.5-flash-low",
|
|
body: {
|
|
messages: [{ role: "user", content: "inspect db" }],
|
|
},
|
|
onComplete(payload) {
|
|
onCompletePayload = payload;
|
|
},
|
|
}
|
|
);
|
|
|
|
assert.equal(onCompletePayload.status, 200);
|
|
assert.match(text, /"tool_calls":\[/);
|
|
assert.match(text, /"name":"terminal"/);
|
|
assert.doesNotMatch(text, /"content":"\[Tool call: terminal/);
|
|
const choice = onCompletePayload.responseBody.choices[0];
|
|
assert.equal(choice.finish_reason, "tool_calls");
|
|
assert.equal(choice.message.content, null);
|
|
assert.equal(choice.message.tool_calls[0].function.name, "terminal");
|
|
assert.deepEqual(JSON.parse(choice.message.tool_calls[0].function.arguments), {
|
|
command: 'sqlite3 /root/.omniroute/omniroute.db ".tables"',
|
|
});
|
|
assert.doesNotMatch(text, /\[Tool call: terminal\]/);
|
|
});
|
|
|
|
test("createSSEStream passthrough converts split textual tool-call content at completion", async () => {
|
|
let onCompletePayload = null;
|
|
const splitToolArgs = JSON.stringify({
|
|
command: 'sqlite3 ~/.o\u200dmniroute/o\u200dmniroute.db ".tables"',
|
|
});
|
|
const chunks = ["[Tool call: terminal]\n", `Arguments: ${splitToolArgs}`];
|
|
|
|
const text = await readTransformed(
|
|
[
|
|
`data: ${JSON.stringify({
|
|
id: "chatcmpl_split_textual_tool",
|
|
object: "chat.completion.chunk",
|
|
created: 1,
|
|
model: "antigravity/gemini-3.5-flash-low",
|
|
choices: [{ index: 0, delta: { role: "assistant", content: chunks[0] } }],
|
|
})}\n\n`,
|
|
`data: ${JSON.stringify({
|
|
id: "chatcmpl_split_textual_tool",
|
|
object: "chat.completion.chunk",
|
|
created: 1,
|
|
model: "antigravity/gemini-3.5-flash-low",
|
|
choices: [{ index: 0, delta: { content: chunks[1] } }],
|
|
})}\n\n`,
|
|
`data: ${JSON.stringify({
|
|
id: "chatcmpl_split_textual_tool",
|
|
object: "chat.completion.chunk",
|
|
created: 1,
|
|
model: "antigravity/gemini-3.5-flash-low",
|
|
choices: [{ index: 0, delta: {}, finish_reason: "stop" }],
|
|
})}\n\n`,
|
|
],
|
|
{
|
|
mode: "passthrough",
|
|
sourceFormat: FORMATS.OPENAI,
|
|
provider: "antigravity",
|
|
model: "antigravity/gemini-3.5-flash-low",
|
|
body: { messages: [{ role: "user", content: "inspect db" }] },
|
|
onComplete(payload) {
|
|
onCompletePayload = payload;
|
|
},
|
|
}
|
|
);
|
|
|
|
assert.match(text, /"tool_calls":\[/);
|
|
assert.match(text, /"name":"terminal"/);
|
|
assert.doesNotMatch(text, /"content":"\[Tool call: terminal/);
|
|
const choice = onCompletePayload.responseBody.choices[0];
|
|
assert.equal(choice.finish_reason, "tool_calls");
|
|
assert.equal(choice.message.content, null);
|
|
assert.equal(choice.message.tool_calls[0].function.name, "terminal");
|
|
assert.deepEqual(JSON.parse(choice.message.tool_calls[0].function.arguments), {
|
|
command: 'sqlite3 ~/.omniroute/omniroute.db ".tables"',
|
|
});
|
|
assert.doesNotMatch(text, /\[Tool call: terminal\]/);
|
|
});
|
|
|
|
test("createSSEStream passthrough buffers fragmented textual tool-call JSON before emitting", async () => {
|
|
let onCompletePayload = null;
|
|
const text = await readTransformed(
|
|
[
|
|
`data: ${JSON.stringify({
|
|
id: "chatcmpl_fragmented_live_shape",
|
|
object: "chat.completion.chunk",
|
|
created: 1,
|
|
model: "MainAgent",
|
|
choices: [
|
|
{
|
|
index: 0,
|
|
delta: { role: "assistant", content: '[Tool call: terminal]\nArguments: {"' },
|
|
},
|
|
],
|
|
})}\n\n`,
|
|
`data: ${JSON.stringify({
|
|
id: "chatcmpl_fragmented_live_shape",
|
|
object: "chat.completion.chunk",
|
|
created: 1,
|
|
model: "MainAgent",
|
|
choices: [
|
|
{
|
|
index: 0,
|
|
delta: { content: 'command":"echo live_shape","timeout":10}' },
|
|
},
|
|
],
|
|
})}\n\n`,
|
|
`data: ${JSON.stringify({
|
|
id: "chatcmpl_fragmented_live_shape",
|
|
object: "chat.completion.chunk",
|
|
created: 1,
|
|
model: "MainAgent",
|
|
choices: [{ index: 0, delta: {}, finish_reason: "stop" }],
|
|
})}\n\n`,
|
|
],
|
|
{
|
|
mode: "passthrough",
|
|
sourceFormat: FORMATS.OPENAI,
|
|
provider: "omniroute",
|
|
model: "MainAgent",
|
|
body: { messages: [{ role: "user", content: "inspect" }] },
|
|
onComplete(payload) {
|
|
onCompletePayload = payload;
|
|
},
|
|
}
|
|
);
|
|
|
|
assert.doesNotMatch(text, /\[Tool call:/);
|
|
assert.doesNotMatch(text, /Arguments:/);
|
|
assert.match(text, /"tool_calls":\[/);
|
|
assert.match(text, /"finish_reason":"tool_calls"/);
|
|
const choice = onCompletePayload.responseBody.choices[0];
|
|
assert.equal(choice.finish_reason, "tool_calls");
|
|
assert.equal(choice.message.content, null);
|
|
assert.equal(choice.message.tool_calls[0].function.name, "terminal");
|
|
assert.deepEqual(JSON.parse(choice.message.tool_calls[0].function.arguments), {
|
|
command: "echo live_shape",
|
|
timeout: 10,
|
|
});
|
|
});
|
|
|
|
test("createSSEStream passthrough suppresses trailing prose plus textual tool call", async () => {
|
|
let onCompletePayload = null;
|
|
const toolArgs = JSON.stringify({
|
|
command: "echo should_not_leak",
|
|
timeout: 10,
|
|
});
|
|
const toolText = `Вот оно! Статические файлы Next.js отдают 404. Чанки не найдены.\n\n[Tool call: terminal]\nArguments: ${toolArgs}`;
|
|
|
|
const text = await readTransformed(
|
|
[
|
|
`data: ${JSON.stringify({
|
|
id: "chatcmpl_trailing_textual_tool",
|
|
object: "chat.completion.chunk",
|
|
created: 1,
|
|
model: "MainAgent",
|
|
choices: [{ index: 0, delta: { role: "assistant", content: toolText } }],
|
|
})}\n\n`,
|
|
`data: ${JSON.stringify({
|
|
id: "chatcmpl_trailing_textual_tool",
|
|
object: "chat.completion.chunk",
|
|
created: 1,
|
|
model: "MainAgent",
|
|
choices: [{ index: 0, delta: {}, finish_reason: "stop" }],
|
|
})}\n\n`,
|
|
],
|
|
{
|
|
mode: "passthrough",
|
|
sourceFormat: FORMATS.OPENAI,
|
|
provider: "omniroute",
|
|
model: "MainAgent",
|
|
body: { messages: [{ role: "user", content: "inspect static files" }] },
|
|
onComplete(payload) {
|
|
onCompletePayload = payload;
|
|
},
|
|
}
|
|
);
|
|
|
|
assert.equal(onCompletePayload.status, 200);
|
|
const choice = onCompletePayload.responseBody.choices[0];
|
|
assert.equal(choice.finish_reason, "tool_calls");
|
|
assert.equal(choice.message.content, null);
|
|
assert.equal(choice.message.tool_calls[0].function.name, "terminal");
|
|
assert.deepEqual(JSON.parse(choice.message.tool_calls[0].function.arguments), {
|
|
command: "echo should_not_leak",
|
|
timeout: 10,
|
|
});
|
|
assert.doesNotMatch(text, /\[Tool call: terminal\]/);
|
|
assert.doesNotMatch(text, /Arguments:/);
|
|
assert.doesNotMatch(JSON.stringify(onCompletePayload.responseBody), /\[Tool call: terminal\]/);
|
|
assert.doesNotMatch(JSON.stringify(onCompletePayload.responseBody), /Arguments:/);
|
|
});
|
|
|
|
test("createSSEStream passthrough suppresses textual tool calls for unknown tools", async () => {
|
|
let onCompletePayload = null;
|
|
const toolText = `[Tool call: search_files_ide]
|
|
Arguments: {"path":"/opt/OmniRoute/src","target":"files"}`;
|
|
|
|
const text = await readTransformed(
|
|
[
|
|
`data: ${JSON.stringify({
|
|
id: "chatcmpl_unknown_textual_tool",
|
|
object: "chat.completion.chunk",
|
|
created: 1,
|
|
model: "antigravity/gemini-3.5-flash-low",
|
|
choices: [{ index: 0, delta: { role: "assistant", content: toolText } }],
|
|
})}\n\n`,
|
|
`data: ${JSON.stringify({
|
|
id: "chatcmpl_unknown_textual_tool",
|
|
object: "chat.completion.chunk",
|
|
created: 1,
|
|
model: "antigravity/gemini-3.5-flash-low",
|
|
choices: [{ index: 0, delta: {}, finish_reason: "stop" }],
|
|
})}\n\n`,
|
|
],
|
|
{
|
|
mode: "passthrough",
|
|
sourceFormat: FORMATS.OPENAI,
|
|
provider: "antigravity",
|
|
model: "antigravity/gemini-3.5-flash-low",
|
|
body: {
|
|
messages: [{ role: "user", content: "inspect files" }],
|
|
tools: [
|
|
{ type: "function", function: { name: "search_files", parameters: { type: "object" } } },
|
|
],
|
|
},
|
|
onComplete(payload) {
|
|
onCompletePayload = payload;
|
|
},
|
|
}
|
|
);
|
|
|
|
const choice = onCompletePayload.responseBody.choices[0];
|
|
assert.equal(choice.finish_reason, "stop");
|
|
assert.equal(choice.message.content, null);
|
|
assert.equal(choice.message.tool_calls, undefined);
|
|
assert.doesNotMatch(text, /search_files_ide/);
|
|
assert.doesNotMatch(JSON.stringify(onCompletePayload.responseBody), /search_files_ide/);
|
|
});
|
|
|
|
test("createSSEStream passthrough suppresses malformed textual tool-call content", async () => {
|
|
let onCompletePayload = null;
|
|
const malformedToolText = `(empty)[Tool call: terminal]\nArguments: {"command":"sqlite3 /opt/O\u200dmniRoute/data/o\u200dmniroute.`;
|
|
|
|
const text = await readTransformed(
|
|
[
|
|
`data: ${JSON.stringify({
|
|
id: "chatcmpl_malformed_textual_tool",
|
|
object: "chat.completion.chunk",
|
|
created: 1,
|
|
model: "antigravity/gemini-3.5-flash-low",
|
|
choices: [{ index: 0, delta: { role: "assistant", content: malformedToolText } }],
|
|
})}\n\n`,
|
|
`data: ${JSON.stringify({
|
|
id: "chatcmpl_malformed_textual_tool",
|
|
object: "chat.completion.chunk",
|
|
created: 1,
|
|
model: "antigravity/gemini-3.5-flash-low",
|
|
choices: [{ index: 0, delta: {}, finish_reason: "stop" }],
|
|
})}\n\n`,
|
|
],
|
|
{
|
|
mode: "passthrough",
|
|
sourceFormat: FORMATS.OPENAI,
|
|
provider: "antigravity",
|
|
model: "antigravity/gemini-3.5-flash-low",
|
|
body: { messages: [{ role: "user", content: "inspect db" }] },
|
|
onComplete(payload) {
|
|
onCompletePayload = payload;
|
|
},
|
|
}
|
|
);
|
|
|
|
const choice = onCompletePayload.responseBody.choices[0];
|
|
assert.equal(choice.finish_reason, "stop");
|
|
assert.equal(choice.message.content, null);
|
|
assert.equal(choice.message.tool_calls, undefined);
|
|
assert.doesNotMatch(text, /\[Tool call: terminal\]/);
|
|
assert.doesNotMatch(JSON.stringify(onCompletePayload.responseBody), /\[Tool call: terminal\]/);
|
|
});
|
|
|
|
test("createSSEStream suppresses malformed compact textual tool-call content", async () => {
|
|
let onCompletePayload = null;
|
|
|
|
const text = await readTransformed(
|
|
[
|
|
`data: ${JSON.stringify({
|
|
candidates: [
|
|
{
|
|
content: {
|
|
parts: [
|
|
{
|
|
text: "[Tool call: search_files_ide{file_glob:*combos*.ts,path:/opt/OmniRoute,target:files}]",
|
|
},
|
|
],
|
|
},
|
|
},
|
|
],
|
|
})}\n\n`,
|
|
`data: ${JSON.stringify({ candidates: [{ finishReason: "STOP" }] })}\n\n`,
|
|
],
|
|
{
|
|
mode: "translate",
|
|
targetFormat: FORMATS.ANTIGRAVITY,
|
|
sourceFormat: FORMATS.OPENAI,
|
|
provider: "antigravity",
|
|
model: "antigravity/gemini-3.5-flash-low",
|
|
body: { messages: [{ role: "user", content: "inspect files" }] },
|
|
onComplete(payload) {
|
|
onCompletePayload = payload;
|
|
},
|
|
}
|
|
);
|
|
|
|
const choice = onCompletePayload.responseBody.choices[0];
|
|
assert.equal(choice.finish_reason, "stop");
|
|
assert.equal(choice.message.content, null);
|
|
assert.equal(choice.message.tool_calls, undefined);
|
|
assert.doesNotMatch(JSON.stringify(onCompletePayload.responseBody), /\[Tool call:/);
|
|
});
|
|
|
|
test("createSSEStream passthrough flushes a buffered final line without a trailing newline", async () => {
|
|
const text = await readTransformed(
|
|
[
|
|
`data: ${JSON.stringify({
|
|
id: "chatcmpl_2",
|
|
object: "chat.completion.chunk",
|
|
created: 2,
|
|
model: "gpt-4.1-mini",
|
|
choices: [{ index: 0, delta: { role: "assistant", content: "tail chunk" } }],
|
|
})}`,
|
|
],
|
|
{
|
|
mode: "passthrough",
|
|
sourceFormat: FORMATS.OPENAI,
|
|
provider: "openai",
|
|
model: "gpt-4.1-mini",
|
|
body: {
|
|
messages: [{ role: "user", content: "hello" }],
|
|
},
|
|
}
|
|
);
|
|
|
|
assert.match(text, /tail chunk/);
|
|
assert.equal(text.includes("data: "), true);
|
|
});
|
|
|
|
test("createSSEStream translate mode converts Claude SSE into OpenAI chunks and completion payload", async () => {
|
|
let onCompletePayload = null;
|
|
const text = await readTransformed(
|
|
[
|
|
`data: ${JSON.stringify({
|
|
type: "message_start",
|
|
message: {
|
|
id: "msg_1",
|
|
model: "claude-sonnet-4",
|
|
role: "assistant",
|
|
usage: { input_tokens: 3 },
|
|
},
|
|
})}\n\n`,
|
|
`data: ${JSON.stringify({
|
|
type: "content_block_start",
|
|
index: 0,
|
|
content_block: { type: "text", text: "" },
|
|
})}\n\n`,
|
|
`data: ${JSON.stringify({
|
|
type: "content_block_delta",
|
|
index: 0,
|
|
delta: { type: "text_delta", text: "Hello Claude" },
|
|
})}\n\n`,
|
|
`data: ${JSON.stringify({
|
|
type: "message_delta",
|
|
delta: { stop_reason: "end_turn" },
|
|
usage: { output_tokens: 4 },
|
|
})}\n\n`,
|
|
`data: ${JSON.stringify({
|
|
type: "message_stop",
|
|
})}\n\n`,
|
|
],
|
|
{
|
|
mode: "translate",
|
|
targetFormat: FORMATS.CLAUDE,
|
|
sourceFormat: FORMATS.OPENAI,
|
|
provider: "claude",
|
|
model: "claude-sonnet-4",
|
|
body: {
|
|
messages: [{ role: "user", content: "hello" }],
|
|
},
|
|
onComplete(payload) {
|
|
onCompletePayload = payload;
|
|
},
|
|
}
|
|
);
|
|
|
|
assert.match(text, /"content":"Hello Claude"/);
|
|
assert.match(text, /\[DONE\]/);
|
|
assert.equal(onCompletePayload.status, 200);
|
|
assert.equal(onCompletePayload.responseBody.choices[0].message.content, "Hello Claude");
|
|
assert.equal(onCompletePayload.responseBody.usage.completion_tokens, 4);
|
|
assert.equal(onCompletePayload.responseBody.usage.total_tokens, 4);
|
|
});
|
|
|
|
test("createSSEStream Responses passthrough converts textual tool-call deltas before streaming", async () => {
|
|
let onCompletePayload = null;
|
|
const toolText = `[Tool call: terminal]
|
|
Arguments: {"command":"systemctl status omniroute"}`;
|
|
const text = await readTransformed(
|
|
[
|
|
`data: ${JSON.stringify({
|
|
type: "response.output_text.delta",
|
|
delta: toolText,
|
|
})}
|
|
|
|
`,
|
|
`data: ${JSON.stringify({
|
|
type: "response.completed",
|
|
response: {
|
|
id: "resp_textual_tool",
|
|
object: "response",
|
|
model: "antigravity/gemini-3.5-flash-low",
|
|
status: "completed",
|
|
output: [],
|
|
usage: { input_tokens: 10, output_tokens: 4, total_tokens: 14 },
|
|
},
|
|
})}
|
|
|
|
`,
|
|
],
|
|
{
|
|
mode: "passthrough",
|
|
sourceFormat: FORMATS.OPENAI_RESPONSES,
|
|
clientResponseFormat: FORMATS.OPENAI_RESPONSES,
|
|
provider: "antigravity",
|
|
model: "antigravity/gemini-3.5-flash-low",
|
|
body: {
|
|
input: "check service",
|
|
tools: [{ type: "function", name: "terminal", parameters: { type: "object" } }],
|
|
},
|
|
onComplete(payload) {
|
|
onCompletePayload = payload;
|
|
},
|
|
}
|
|
);
|
|
|
|
assert.doesNotMatch(text, /\[Tool call: terminal\]/);
|
|
assert.doesNotMatch(text, /Arguments:/);
|
|
assert.match(text, /response.output_item.added/);
|
|
assert.match(text, /response.function_call_arguments.done/);
|
|
assert.match(text, /"name":"terminal"/);
|
|
assert.equal(onCompletePayload.responseBody.choices[0].finish_reason, "tool_calls");
|
|
assert.equal(onCompletePayload.responseBody.choices[0].message.content, null);
|
|
assert.equal(
|
|
onCompletePayload.responseBody.choices[0].message.tool_calls[0].function.name,
|
|
"terminal"
|
|
);
|
|
assert.doesNotMatch(JSON.stringify(onCompletePayload.clientPayload), /\[Tool call: terminal\]/);
|
|
});
|
|
|
|
test("createSSEStream passthrough preserves Responses API events and completion summaries", async () => {
|
|
let onCompletePayload = null;
|
|
const text = await readTransformed(
|
|
[
|
|
`data: ${JSON.stringify({
|
|
type: "response.output_text.delta",
|
|
delta: "Hello ",
|
|
})}\n\n`,
|
|
`data: ${JSON.stringify({
|
|
type: "response.output_text.delta",
|
|
delta: "world",
|
|
})}\n\n`,
|
|
`data: ${JSON.stringify({
|
|
type: "response.completed",
|
|
response: {
|
|
id: "resp_1",
|
|
object: "response",
|
|
model: "gpt-4.1-mini",
|
|
status: "completed",
|
|
usage: { input_tokens: 2, output_tokens: 3, total_tokens: 5 },
|
|
},
|
|
})}\n\n`,
|
|
],
|
|
{
|
|
mode: "passthrough",
|
|
sourceFormat: FORMATS.OPENAI_RESPONSES,
|
|
provider: "openai",
|
|
model: "gpt-4.1-mini",
|
|
body: { input: "hello" },
|
|
onComplete(payload) {
|
|
onCompletePayload = payload;
|
|
},
|
|
}
|
|
);
|
|
|
|
assert.match(text, /response.output_text.delta/);
|
|
assert.match(text, /response.completed/);
|
|
assert.equal(onCompletePayload.responseBody.usage.total_tokens, 5);
|
|
assert.equal(onCompletePayload.providerPayload.summary.object, "response");
|
|
});
|
|
|
|
test("buildStreamSummaryFromEvents falls back to response.output_text.delta when completed output is empty", () => {
|
|
const summary = buildStreamSummaryFromEvents(
|
|
[
|
|
{
|
|
index: 0,
|
|
data: {
|
|
type: "response.output_text.delta",
|
|
delta: "Hello ",
|
|
},
|
|
},
|
|
{
|
|
index: 1,
|
|
data: {
|
|
type: "response.output_text.delta",
|
|
delta: "world",
|
|
},
|
|
},
|
|
{
|
|
index: 2,
|
|
data: {
|
|
type: "response.completed",
|
|
response: {
|
|
id: "resp_fallback",
|
|
object: "response",
|
|
model: "gpt-5.4",
|
|
status: "completed",
|
|
output: [],
|
|
usage: { output_tokens: 2 },
|
|
},
|
|
},
|
|
},
|
|
],
|
|
FORMATS.OPENAI_RESPONSES,
|
|
"gpt-5.4"
|
|
);
|
|
|
|
assert.equal((summary as any).object, "response");
|
|
assert.equal((summary as any).output[0].type, "message");
|
|
assert.equal((summary as any).output[0].content[0].type, "output_text");
|
|
assert.equal((summary as any).output[0].content[0].text, "Hello world");
|
|
assert.equal((summary as any).usage.output_tokens, 2);
|
|
});
|
|
|
|
test("createSSEStream translate mode aborts on Responses failure with rate limit error", async () => {
|
|
let onCompletePayload = null;
|
|
|
|
await assert.rejects(
|
|
readTransformed(
|
|
[
|
|
`data: ${JSON.stringify({
|
|
type: "response.created",
|
|
response: {
|
|
id: "resp_fail",
|
|
object: "response",
|
|
model: "gpt-5.4",
|
|
status: "in_progress",
|
|
output: [],
|
|
},
|
|
})}\n\n`,
|
|
`data: ${JSON.stringify({
|
|
type: "response.failed",
|
|
response: {
|
|
id: "resp_fail",
|
|
object: "response",
|
|
model: "gpt-5.4",
|
|
status: "failed",
|
|
error: {
|
|
message: "Rate limit reached for gpt-5.4",
|
|
code: "rate_limit_exceeded",
|
|
},
|
|
},
|
|
})}\n\n`,
|
|
`data: [DONE]\n\n`,
|
|
],
|
|
{
|
|
mode: "translate",
|
|
targetFormat: FORMATS.OPENAI_RESPONSES,
|
|
sourceFormat: FORMATS.OPENAI,
|
|
provider: "codex",
|
|
model: "gpt-5.4",
|
|
body: { messages: [{ role: "user", content: "hello" }] },
|
|
onComplete(payload) {
|
|
onCompletePayload = payload;
|
|
},
|
|
}
|
|
),
|
|
/Rate limit reached for gpt-5\.4|Upstream failure/
|
|
);
|
|
|
|
assert.ok(onCompletePayload, "should capture completion payload before aborting");
|
|
assert.equal(onCompletePayload.status, 429);
|
|
assert.equal(onCompletePayload.responseBody.error.type, "rate_limit_error");
|
|
assert.equal(onCompletePayload.responseBody.error.code, "rate_limit_exceeded");
|
|
assert.match(onCompletePayload.responseBody.error.message, /Rate limit reached/);
|
|
});
|
|
|
|
test("createSSEStream passthrough restores Claude tool names from the mapping table", async () => {
|
|
const toolNameMap = new Map([["tool_alias", "read_file"]]);
|
|
const text = await readTransformed(
|
|
[
|
|
`data: ${JSON.stringify({
|
|
type: "content_block_start",
|
|
index: 0,
|
|
content_block: {
|
|
type: "tool_use",
|
|
id: "tool_1",
|
|
name: "tool_alias",
|
|
input: { path: "/tmp/a" },
|
|
},
|
|
})}\n\n`,
|
|
],
|
|
{
|
|
mode: "passthrough",
|
|
sourceFormat: FORMATS.CLAUDE,
|
|
provider: "claude",
|
|
model: "claude-sonnet-4",
|
|
toolNameMap,
|
|
body: { messages: [{ role: "user", content: "hello" }] },
|
|
}
|
|
);
|
|
|
|
assert.match(text, /"name":"read_file"/);
|
|
assert.equal(text.includes("tool_alias"), false);
|
|
});
|
|
|
|
test("createSSEStream passthrough fixes generic ids and normalizes reasoning aliases", async () => {
|
|
const text = await readTransformed(
|
|
[
|
|
`data: ${JSON.stringify({
|
|
id: "chat",
|
|
object: "chat.completion.chunk",
|
|
created: 1,
|
|
model: "kimi-k2.5",
|
|
choices: [
|
|
{
|
|
index: 0,
|
|
delta: {
|
|
reasoning: "Let me think first",
|
|
},
|
|
},
|
|
],
|
|
})}\n\n`,
|
|
],
|
|
{
|
|
mode: "passthrough",
|
|
sourceFormat: FORMATS.OPENAI,
|
|
provider: "openai",
|
|
model: "kimi-k2.5",
|
|
body: { messages: [{ role: "user", content: "hello" }] },
|
|
}
|
|
);
|
|
|
|
assert.match(text, /"id":"chatcmpl-/);
|
|
assert.match(text, /"reasoning_content":"Let me think first"/);
|
|
assert.equal(text.includes('"reasoning":"Let me think first"'), false);
|
|
});
|
|
|
|
test("createSSEStream passthrough splits mixed reasoning and content deltas and estimates usage", async () => {
|
|
let onCompletePayload = null;
|
|
const text = await readTransformed(
|
|
[
|
|
`data: ${JSON.stringify({
|
|
id: "chatcmpl_reasoning",
|
|
object: "chat.completion.chunk",
|
|
created: 1,
|
|
model: "gpt-4.1-mini",
|
|
choices: [
|
|
{
|
|
index: 0,
|
|
delta: {
|
|
reasoning_content: "First think",
|
|
content: "Then answer",
|
|
},
|
|
},
|
|
],
|
|
})}\n\n`,
|
|
`data: ${JSON.stringify({
|
|
id: "chatcmpl_reasoning",
|
|
object: "chat.completion.chunk",
|
|
created: 1,
|
|
model: "gpt-4.1-mini",
|
|
choices: [{ index: 0, delta: {}, finish_reason: "stop" }],
|
|
})}\n\n`,
|
|
],
|
|
{
|
|
mode: "passthrough",
|
|
sourceFormat: FORMATS.OPENAI,
|
|
provider: "openai",
|
|
model: "gpt-4.1-mini",
|
|
body: {
|
|
messages: [{ role: "user", content: "hello world" }],
|
|
},
|
|
onComplete(payload) {
|
|
onCompletePayload = payload;
|
|
},
|
|
}
|
|
);
|
|
|
|
const reasoningIndex = text.indexOf('"reasoning_content":"First think"');
|
|
const contentIndex = text.indexOf('"content":"Then answer"');
|
|
|
|
assert.ok(reasoningIndex >= 0);
|
|
assert.ok(contentIndex > reasoningIndex);
|
|
assert.match(text, /"total_tokens":\d+/);
|
|
assert.equal(onCompletePayload.responseBody.choices[0].message.reasoning_content, "First think");
|
|
assert.equal(onCompletePayload.responseBody.choices[0].message.content, "Then answer");
|
|
assert.ok(onCompletePayload.responseBody.usage.total_tokens > 0);
|
|
});
|
|
|
|
test("createSSEStream passthrough merges Claude usage chunks and restores mapped tool names", async () => {
|
|
let onCompletePayload = null;
|
|
const text = await readTransformed(
|
|
[
|
|
`data: ${JSON.stringify({
|
|
type: "message_start",
|
|
message: {
|
|
id: "msg_passthrough",
|
|
model: "claude-sonnet-4",
|
|
role: "assistant",
|
|
usage: { input_tokens: 6 },
|
|
},
|
|
})}\n\n`,
|
|
`data: ${JSON.stringify({
|
|
type: "content_block_start",
|
|
index: 0,
|
|
content_block: {
|
|
type: "tool_use",
|
|
id: "tool_1",
|
|
name: "tool_alias",
|
|
input: { path: "/tmp/a" },
|
|
},
|
|
})}\n\n`,
|
|
`data: ${JSON.stringify({
|
|
type: "content_block_delta",
|
|
index: 1,
|
|
delta: { text: "Claude says hi" },
|
|
})}\n\n`,
|
|
`data: ${JSON.stringify({
|
|
type: "message_delta",
|
|
delta: { stop_reason: "end_turn" },
|
|
usage: { output_tokens: 4 },
|
|
})}\n\n`,
|
|
],
|
|
{
|
|
mode: "passthrough",
|
|
sourceFormat: FORMATS.CLAUDE,
|
|
provider: "claude",
|
|
model: "claude-sonnet-4",
|
|
toolNameMap: new Map([["tool_alias", "read_file"]]),
|
|
body: {
|
|
messages: [{ role: "user", content: "hello" }],
|
|
},
|
|
onComplete(payload) {
|
|
onCompletePayload = payload;
|
|
},
|
|
}
|
|
);
|
|
|
|
assert.match(text, /"name":"read_file"/);
|
|
assert.equal(text.includes('"name":"tool_alias"'), false);
|
|
assert.equal(onCompletePayload.responseBody.choices[0].message.content, "Claude says hi");
|
|
assert.equal(onCompletePayload.responseBody.usage.prompt_tokens, 6);
|
|
assert.equal(onCompletePayload.responseBody.usage.completion_tokens, 4);
|
|
assert.equal(onCompletePayload.responseBody.usage.total_tokens, 10);
|
|
});
|
|
|
|
test("createSSEStream passthrough injects a synthetic Claude text block for empty assistant SSE", async () => {
|
|
let onCompletePayload = null;
|
|
const text = await readTransformed(
|
|
[
|
|
`event: message_start\ndata: ${JSON.stringify({
|
|
type: "message_start",
|
|
message: {
|
|
id: "msg_empty_passthrough",
|
|
type: "message",
|
|
role: "assistant",
|
|
model: "claude-sonnet-4",
|
|
content: [],
|
|
stop_reason: null,
|
|
stop_sequence: null,
|
|
usage: { input_tokens: 7, output_tokens: 0 },
|
|
},
|
|
})}\n\n`,
|
|
`event: message_stop\ndata: ${JSON.stringify({
|
|
type: "message_stop",
|
|
})}\n\n`,
|
|
],
|
|
{
|
|
mode: "passthrough",
|
|
sourceFormat: FORMATS.CLAUDE,
|
|
provider: "claude",
|
|
model: "claude-sonnet-4",
|
|
body: {
|
|
messages: [{ role: "user", content: "hello" }],
|
|
},
|
|
onComplete(payload) {
|
|
onCompletePayload = payload;
|
|
},
|
|
}
|
|
);
|
|
|
|
assert.equal((text.match(/event: message_start/g) || []).length, 1);
|
|
assert.equal((text.match(/event: message_delta/g) || []).length, 1);
|
|
assert.match(text, /event: content_block_start/);
|
|
assert.match(text, /event: content_block_delta/);
|
|
assert.match(text, /event: message_stop/);
|
|
assert.match(text, /\[Proxy Error\] The upstream API returned an empty response/);
|
|
assert.ok(text.indexOf("event: content_block_start") > text.indexOf("event: message_start"));
|
|
assert.ok(text.indexOf("event: message_stop") > text.indexOf("event: content_block_stop"));
|
|
assert.equal(
|
|
onCompletePayload.responseBody.choices[0].message.content,
|
|
SYNTHETIC_CLAUDE_EMPTY_RESPONSE_TEXT
|
|
);
|
|
});
|
|
|
|
test("createSSEStream passthrough does not emit [DONE] for Claude SSE clients", async () => {
|
|
const text = await readTransformed(
|
|
[
|
|
`event: message_start\ndata: ${JSON.stringify({
|
|
type: "message_start",
|
|
message: {
|
|
id: "msg_claude_done_gate",
|
|
type: "message",
|
|
role: "assistant",
|
|
model: "claude-sonnet-4",
|
|
content: [],
|
|
stop_reason: null,
|
|
stop_sequence: null,
|
|
usage: { input_tokens: 3, output_tokens: 0 },
|
|
},
|
|
})}\n\n`,
|
|
`event: content_block_start\ndata: ${JSON.stringify({
|
|
type: "content_block_start",
|
|
index: 0,
|
|
content_block: { type: "text", text: "" },
|
|
})}\n\n`,
|
|
`event: content_block_delta\ndata: ${JSON.stringify({
|
|
type: "content_block_delta",
|
|
index: 0,
|
|
delta: { type: "text_delta", text: "Claude client stream" },
|
|
})}\n\n`,
|
|
`event: content_block_stop\ndata: ${JSON.stringify({
|
|
type: "content_block_stop",
|
|
index: 0,
|
|
})}\n\n`,
|
|
`event: message_delta\ndata: ${JSON.stringify({
|
|
type: "message_delta",
|
|
delta: { stop_reason: "end_turn", stop_sequence: null },
|
|
usage: { output_tokens: 3 },
|
|
})}\n\n`,
|
|
`event: message_stop\ndata: ${JSON.stringify({
|
|
type: "message_stop",
|
|
})}\n\n`,
|
|
],
|
|
{
|
|
mode: "passthrough",
|
|
sourceFormat: FORMATS.CLAUDE,
|
|
clientResponseFormat: FORMATS.CLAUDE,
|
|
provider: "claude",
|
|
model: "claude-sonnet-4",
|
|
body: {
|
|
messages: [{ role: "user", content: "hello" }],
|
|
},
|
|
}
|
|
);
|
|
|
|
assert.match(text, /event: message_stop/);
|
|
assert.match(text, /Claude client stream/);
|
|
assert.doesNotMatch(text, /\[DONE\]/);
|
|
});
|
|
|
|
test("createSSEStream translate mode injects a synthetic Claude text block when OpenAI finishes empty", async () => {
|
|
let onCompletePayload = null;
|
|
const text = await readTransformed(
|
|
[
|
|
`data: ${JSON.stringify({
|
|
id: "chatcmpl_empty_1",
|
|
object: "chat.completion.chunk",
|
|
created: 1,
|
|
model: "gpt-4.1-mini",
|
|
choices: [{ index: 0, delta: { role: "assistant" } }],
|
|
})}\n\n`,
|
|
`data: ${JSON.stringify({
|
|
id: "chatcmpl_empty_1",
|
|
object: "chat.completion.chunk",
|
|
created: 1,
|
|
model: "gpt-4.1-mini",
|
|
choices: [{ index: 0, delta: {}, finish_reason: "stop" }],
|
|
usage: { prompt_tokens: 3, completion_tokens: 0, total_tokens: 3 },
|
|
})}\n\n`,
|
|
],
|
|
{
|
|
mode: "translate",
|
|
targetFormat: FORMATS.OPENAI,
|
|
sourceFormat: FORMATS.CLAUDE,
|
|
provider: "openai",
|
|
model: "gpt-4.1-mini",
|
|
body: {
|
|
messages: [{ role: "user", content: "hello" }],
|
|
},
|
|
onComplete(payload) {
|
|
onCompletePayload = payload;
|
|
},
|
|
}
|
|
);
|
|
|
|
assert.equal((text.match(/event: message_start/g) || []).length, 1);
|
|
assert.match(text, /event: content_block_start/);
|
|
assert.match(text, /event: content_block_delta/);
|
|
assert.match(text, /event: message_delta/);
|
|
assert.match(text, /event: message_stop/);
|
|
assert.match(text, /\[Proxy Error\] The upstream API returned an empty response/);
|
|
assert.ok(text.indexOf("event: content_block_start") > text.indexOf("event: message_start"));
|
|
assert.ok(text.indexOf("event: message_delta") > text.indexOf("event: content_block_stop"));
|
|
assert.equal(
|
|
onCompletePayload.responseBody.choices[0].message.content,
|
|
SYNTHETIC_CLAUDE_EMPTY_RESPONSE_TEXT
|
|
);
|
|
assert.equal(onCompletePayload.responseBody.usage.total_tokens, 3);
|
|
});
|
|
|
|
test("createSSETransformStreamWithLogger flushes a trailing Claude usage event without a newline", async () => {
|
|
let onCompletePayload = null;
|
|
const text = await readWithTransform(
|
|
[
|
|
`data: ${JSON.stringify({
|
|
type: "message_start",
|
|
message: {
|
|
id: "msg_tail",
|
|
model: "claude-sonnet-4",
|
|
role: "assistant",
|
|
usage: { input_tokens: 3 },
|
|
},
|
|
})}\n\n`,
|
|
`data: ${JSON.stringify({
|
|
type: "content_block_start",
|
|
index: 0,
|
|
content_block: { type: "text", text: "" },
|
|
})}\n\n`,
|
|
`data: ${JSON.stringify({
|
|
type: "content_block_delta",
|
|
index: 0,
|
|
delta: { type: "text_delta", text: "Buffered tail" },
|
|
})}\n\n`,
|
|
`data: ${JSON.stringify({
|
|
type: "message_delta",
|
|
delta: { stop_reason: "end_turn" },
|
|
usage: { output_tokens: 5 },
|
|
})}`,
|
|
],
|
|
createSSETransformStreamWithLogger(
|
|
FORMATS.CLAUDE,
|
|
FORMATS.OPENAI,
|
|
"claude",
|
|
null,
|
|
null,
|
|
"claude-sonnet-4",
|
|
null,
|
|
{ messages: [{ role: "user", content: "hello" }] },
|
|
(payload) => {
|
|
onCompletePayload = payload;
|
|
}
|
|
)
|
|
);
|
|
|
|
assert.match(text, /Buffered tail/);
|
|
assert.match(text, /\[DONE\]/);
|
|
assert.equal(onCompletePayload.responseBody.choices[0].message.content, "Buffered tail");
|
|
assert.equal(onCompletePayload.responseBody.usage.completion_tokens, 5);
|
|
assert.equal(onCompletePayload.responseBody.usage.total_tokens, 5);
|
|
});
|
|
|
|
test("buildStreamSummaryFromEvents compacts Responses API deltas into a synthetic response", () => {
|
|
const summary = buildStreamSummaryFromEvents(
|
|
[
|
|
{ index: 0, data: { type: "response.output_text.delta", delta: "Hello " } },
|
|
{ index: 1, data: { type: "response.output_text.delta", delta: "world" } },
|
|
{
|
|
index: 2,
|
|
data: {
|
|
type: "response.output_text.done",
|
|
usage: { input_tokens: 2, output_tokens: 3, total_tokens: 5 },
|
|
},
|
|
},
|
|
],
|
|
FORMATS.OPENAI_RESPONSES,
|
|
"gpt-4.1-mini"
|
|
);
|
|
|
|
assert.equal((summary as any).object, "response");
|
|
assert.equal((summary as any).model, "gpt-4.1-mini");
|
|
assert.equal((summary as any).output[0].content[0].text, "Hello world");
|
|
assert.deepEqual((summary as any).usage, { input_tokens: 2, output_tokens: 3, total_tokens: 5 });
|
|
});
|
|
|
|
test("buildStreamSummaryFromEvents preserves Gemini thought parts and function calls", () => {
|
|
const summary = buildStreamSummaryFromEvents(
|
|
[
|
|
{
|
|
index: 0,
|
|
data: {
|
|
modelVersion: "gemini-2.5-pro",
|
|
candidates: [
|
|
{
|
|
content: {
|
|
role: "model",
|
|
parts: [
|
|
{ text: "Thinking", thought: true },
|
|
{ text: " aloud", thought: true },
|
|
],
|
|
},
|
|
},
|
|
],
|
|
},
|
|
},
|
|
{
|
|
index: 1,
|
|
data: {
|
|
candidates: [
|
|
{
|
|
content: {
|
|
role: "model",
|
|
parts: [
|
|
{ text: "Done." },
|
|
{ functionCall: { name: "read_file", args: { path: "/tmp/a" } } },
|
|
],
|
|
},
|
|
finishReason: "STOP",
|
|
},
|
|
],
|
|
usageMetadata: {
|
|
promptTokenCount: 4,
|
|
candidatesTokenCount: 5,
|
|
totalTokenCount: 9,
|
|
},
|
|
},
|
|
},
|
|
],
|
|
FORMATS.GEMINI,
|
|
"gemini-2.5-pro"
|
|
);
|
|
|
|
assert.equal((summary as any).modelVersion, "gemini-2.5-pro");
|
|
assert.equal((summary as any).candidates[0].content.parts[0].text, "Thinking aloud");
|
|
assert.equal((summary as any).candidates[0].content.parts[0].thought, true);
|
|
assert.deepEqual((summary as any).candidates[0].content.parts[2], {
|
|
functionCall: { name: "read_file", args: { path: "/tmp/a" } },
|
|
});
|
|
assert.deepEqual((summary as any).usageMetadata, {
|
|
promptTokenCount: 4,
|
|
candidatesTokenCount: 5,
|
|
totalTokenCount: 9,
|
|
});
|
|
});
|
|
|
|
test("compactStructuredStreamPayload wraps primitive summaries with Omniroute stream metadata", () => {
|
|
const compact = compactStructuredStreamPayload({
|
|
_streamed: true,
|
|
_format: "sse-json",
|
|
_stage: "client_response",
|
|
_eventCount: 2,
|
|
summary: "done",
|
|
});
|
|
|
|
assert.deepEqual(compact, {
|
|
summary: "done",
|
|
_omniroute_stream: {
|
|
format: "sse-json",
|
|
stage: "client_response",
|
|
eventCount: 2,
|
|
},
|
|
});
|
|
});
|
|
|
|
test("createSSETransformStreamWithLogger flushes Responses API terminal events on stream end", async () => {
|
|
const text = await readWithTransform(
|
|
[
|
|
`data: ${JSON.stringify({
|
|
id: "chatcmpl_flush",
|
|
object: "chat.completion.chunk",
|
|
created: 1,
|
|
model: "gpt-4.1-mini",
|
|
choices: [{ index: 0, delta: { role: "assistant", content: "Hello" } }],
|
|
})}\n\n`,
|
|
`data: ${JSON.stringify({
|
|
id: "chatcmpl_flush",
|
|
object: "chat.completion.chunk",
|
|
created: 1,
|
|
model: "gpt-4.1-mini",
|
|
choices: [{ index: 0, delta: {}, finish_reason: "stop" }],
|
|
usage: { prompt_tokens: 2, completion_tokens: 3, total_tokens: 5 },
|
|
})}\n\n`,
|
|
],
|
|
createSSETransformStreamWithLogger(
|
|
FORMATS.OPENAI,
|
|
FORMATS.OPENAI_RESPONSES,
|
|
"openai",
|
|
null,
|
|
null,
|
|
"gpt-4.1-mini",
|
|
null,
|
|
{ messages: [{ role: "user", content: "hello" }] }
|
|
)
|
|
);
|
|
|
|
assert.match(text, /response\.created/);
|
|
assert.match(text, /response\.completed/);
|
|
assert.doesNotMatch(text, /\[DONE\]/);
|
|
});
|
|
|
|
test("createPassthroughStreamWithLogger reuses passthrough mode helpers", async () => {
|
|
const text = await readWithTransform(
|
|
[
|
|
`data: ${JSON.stringify({
|
|
id: "chatcmpl_passthrough",
|
|
object: "chat.completion.chunk",
|
|
created: 1,
|
|
model: "gpt-4.1-mini",
|
|
choices: [{ index: 0, delta: { role: "assistant", content: "Hello again" } }],
|
|
})}\n\n`,
|
|
"data: [DONE]\n\n",
|
|
],
|
|
createPassthroughStreamWithLogger("openai", null, null, "gpt-4.1-mini", null, {
|
|
messages: [{ role: "user", content: "hello" }],
|
|
})
|
|
);
|
|
|
|
assert.match(text, /Hello again/);
|
|
assert.match(text, /\[DONE\]/);
|
|
});
|
|
|
|
test("createStructuredSSECollector drops excess events and compactStructuredStreamPayload preserves metadata for object summaries", () => {
|
|
const collector = createStructuredSSECollector({
|
|
stage: "client_response",
|
|
maxEvents: 1,
|
|
maxBytes: 512,
|
|
});
|
|
|
|
collector.push({ type: "response.output_text.delta", delta: "one" });
|
|
collector.push({ type: "response.output_text.delta", delta: "two" });
|
|
|
|
const built = collector.build(
|
|
{
|
|
object: "response",
|
|
status: "completed",
|
|
},
|
|
{ includeEvents: false }
|
|
);
|
|
const compact = compactStructuredStreamPayload(built);
|
|
|
|
assert.equal(built._truncated, true);
|
|
assert.equal(built._droppedEvents, 1);
|
|
assert.equal(built._eventCount, 2);
|
|
assert.deepEqual(compact, {
|
|
object: "response",
|
|
status: "completed",
|
|
_omniroute_stream: {
|
|
format: "sse-json",
|
|
stage: "client_response",
|
|
eventCount: 2,
|
|
truncated: true,
|
|
droppedEvents: 1,
|
|
},
|
|
});
|
|
});
|
|
|
|
test("createSSEStream passthrough drops keepalive event blocks without losing Responses deltas", async () => {
|
|
const text = await readTransformed(
|
|
[
|
|
"event: keepalive\ndata:\n\n",
|
|
`data: ${JSON.stringify({
|
|
type: "response.output_text.delta",
|
|
delta: "Hello keepalive-safe",
|
|
})}\n\n`,
|
|
`data: ${JSON.stringify({
|
|
type: "response.completed",
|
|
response: {
|
|
id: "resp_keepalive",
|
|
object: "response",
|
|
model: "gpt-4.1-mini",
|
|
status: "completed",
|
|
usage: { input_tokens: 2, output_tokens: 1, total_tokens: 3 },
|
|
},
|
|
})}\n\n`,
|
|
"data: [DONE]\n\n",
|
|
],
|
|
{
|
|
mode: "passthrough",
|
|
sourceFormat: FORMATS.OPENAI_RESPONSES,
|
|
provider: "openai",
|
|
model: "gpt-4.1-mini",
|
|
body: { input: "hello" },
|
|
}
|
|
);
|
|
|
|
assert.equal(text.includes("event: keepalive"), false);
|
|
assert.equal(text.includes("data:\n\n"), false);
|
|
assert.match(text, /response\.output_text\.delta/);
|
|
assert.match(text, /Hello keepalive-safe/);
|
|
assert.match(text, /data: \[DONE\]/);
|
|
});
|
|
|
|
test("createSSEStream passthrough aborts on Responses usage-limit failures and reports 429", async () => {
|
|
let failurePayload = null;
|
|
|
|
await assert.rejects(
|
|
readTransformed(
|
|
[
|
|
`data: ${JSON.stringify({
|
|
type: "response.failed",
|
|
response: {
|
|
id: "resp_usage_limit",
|
|
object: "response",
|
|
model: "gpt-5.5",
|
|
status: "failed",
|
|
error: {
|
|
code: "usage_limit_reached",
|
|
message: "Your weekly usage limit has been reached",
|
|
},
|
|
},
|
|
})}\n\n`,
|
|
],
|
|
{
|
|
mode: "passthrough",
|
|
sourceFormat: FORMATS.OPENAI_RESPONSES,
|
|
provider: "codex",
|
|
model: "gpt-5.5",
|
|
body: { input: "hello" },
|
|
onFailure(payload) {
|
|
failurePayload = payload;
|
|
},
|
|
}
|
|
),
|
|
/weekly usage limit|Upstream failure/
|
|
);
|
|
|
|
assert.ok(failurePayload, "should report the stream failure before aborting");
|
|
assert.equal(failurePayload.status, 429);
|
|
assert.equal(failurePayload.code, "usage_limit_reached");
|
|
});
|
|
|
|
test("createRequestLogger skips disabled logs and caps retained stream chunk bytes", async () => {
|
|
const disabled = await createRequestLogger("openai", "openai", "gpt-test", {
|
|
enabled: false,
|
|
});
|
|
disabled.logClientRawRequest("/v1/chat/completions", { prompt: "hello" });
|
|
disabled.appendProviderChunk("x".repeat(32));
|
|
assert.equal(disabled.getPipelinePayloads(), null);
|
|
|
|
const logger = await createRequestLogger("openai", "openai", "gpt-test", {
|
|
enabled: true,
|
|
captureStreamChunks: true,
|
|
maxStreamChunkBytes: 5,
|
|
});
|
|
logger.appendProviderChunk("abcdef");
|
|
logger.appendProviderChunk("ghijkl");
|
|
const payloads = logger.getPipelinePayloads();
|
|
|
|
assert.deepEqual(payloads.streamChunks.provider, [
|
|
"abcde",
|
|
"[stream chunk log truncated after 5 bytes]",
|
|
]);
|
|
});
|
|
|
|
test("createRequestLogger caps retained stream chunk item count", async () => {
|
|
const logger = await createRequestLogger("openai", "openai", "gpt-test", {
|
|
enabled: true,
|
|
captureStreamChunks: true,
|
|
maxStreamChunkBytes: 1024,
|
|
maxStreamChunkItems: 2,
|
|
});
|
|
|
|
logger.appendProviderChunk("one");
|
|
logger.appendProviderChunk("two");
|
|
logger.appendProviderChunk("three");
|
|
|
|
const payloads = logger.getPipelinePayloads();
|
|
assert.deepEqual(payloads.streamChunks.provider, [
|
|
"one",
|
|
"[stream chunk log truncated after 2 chunks]",
|
|
]);
|
|
});
|
|
|
|
// T-VERIFY: passthrough mode failure decrements pending requests
|
|
// Regression test for missing trackPendingRequest(false) on passthrough failure
|
|
import { getPendingRequests, clearPendingRequests } from "../../src/lib/usage/usageHistory.ts";
|
|
|
|
test("createSSEStream passthrough mode decrements pending requests on failure", async () => {
|
|
// Clear any existing pending requests first
|
|
clearPendingRequests();
|
|
const initial = getPendingRequests();
|
|
assert.equal(Object.keys(initial.byModel).length, 0, "should start with no pending requests");
|
|
|
|
let failurePayload = null;
|
|
const testProvider = "openai-compatible-test-failure";
|
|
const testModel = "gpt-test";
|
|
const testConnectionId = "test-conn-123";
|
|
|
|
await assert.rejects(
|
|
readTransformed(
|
|
[
|
|
`data: ${JSON.stringify({
|
|
type: "response.failed",
|
|
response: {
|
|
id: "resp_failed_test",
|
|
object: "response",
|
|
model: testModel,
|
|
status: "failed",
|
|
error: {
|
|
code: "test_failure",
|
|
message: "Test failure for pending request tracking",
|
|
},
|
|
},
|
|
})}\n\n`,
|
|
],
|
|
{
|
|
mode: "passthrough",
|
|
sourceFormat: FORMATS.OPENAI_RESPONSES,
|
|
provider: testProvider,
|
|
model: testModel,
|
|
connectionId: testConnectionId,
|
|
body: { input: "hello" },
|
|
onFailure(payload) {
|
|
failurePayload = payload;
|
|
},
|
|
}
|
|
),
|
|
/Test failure|Upstream failure/
|
|
);
|
|
|
|
assert.ok(failurePayload, "should report the stream failure");
|
|
|
|
// Verify pending requests are properly decremented after failure
|
|
const pending = getPendingRequests();
|
|
const modelKey = `${testModel} (${testProvider})`;
|
|
const count = pending.byModel[modelKey] || 0;
|
|
assert.equal(
|
|
count,
|
|
0,
|
|
`pending request count for ${modelKey} should be 0 after failure, got ${count}`
|
|
);
|
|
});
|