* fix(streaming): #1211 greedy strip omniModel tags to prevent literal \n\n artifacts
- Changed regex quantifier from ? to * in combo.ts, comboAgentMiddleware.ts,
and contextHandoff.ts to greedily strip all JSON-escaped newline sequences
surrounding <omniModel> tags in SSE streaming chunks
- Added \r to the character class for cross-platform robustness
- Fixed Playwright strict-mode violation in combo-unification.spec.ts
- Bumped OpenAPI version and CHANGELOG to 3.6.6
* fix: 3 bugs found during issue triage (#1175, #1187/#1218, #1202)
- fix(gemini): strip VS Code JSON Schema extensions from tool schemas (#1175)
Add enumDescriptions, markdownDescription, markdownEnumDescriptions,
enumItemLabels and tags to UNSUPPORTED_SCHEMA_CONSTRAINTS so the Gemini
sanitizer removes them before forwarding. GitHub Copilot injects these
non-standard fields into tool definitions, causing Gemini to reject with
'Unknown name enumDescriptions at functionDeclarations[n].parameters'.
- fix(health-check): unwrap proxy config object before passing to getAccessToken (#1187#1218)
resolveProxyForConnection() returns { proxy, level, levelId } but the health
check loop was passing the full wrapper to getAccessToken(), which expects the
inner config object (.host, .port etc). The proxy dispatcher validated .host
on the wrapper (undefined) and threw 'Context proxy host is required', silently
marking every connection as unhealthy every sweep. Fix mirrors the pattern
already used in chatHelpers.ts: proxyResult?.proxy || null.
- fix(ui): debounce models.dev sync interval slider to save only on release (#1202)
The slider's onChange fired updateInterval() on every drag tick, sending a
PATCH per pixel of movement. Rapid API responses overwrote UI state mid-drag.
Introduce draftIntervalHours for smooth visual feedback; the PATCH fires
on onMouseUp / onBlur once the user releases the control.
* fix(providers): update Xiaomi MiMo token-plan endpoints (#1238)
Integrated into release/v3.6.6
* fix(cc-compatible): trim beta flags and preserve cache passthrough (#1230)
Integrated into release/v3.6.6
* feat(memory+skills): full-featured memory & skills systems with tests (#1228)
Integrated into release/v3.6.6
* fix: forward client x-initiator header to GitHub Copilot upstream (#1227)
Integrated into release/v3.6.6
* feat(bailian-quota): add Alibaba Coding Plan quota monitoring (#1235)
* fix: resolve v3.6.6 backlog bugs (#1206, #1211, #1220, #1231)
- fix(core): #1206 inject startup guard against app/ and src/app/ conflict
- fix(health): #1220 add HEALTHCHECK_STAGGER_MS to prevent token refresh bursting
- fix(proxy): #1231 prioritize HTTP 429 over quota body heuristics
- fix(sse): #1211 strip leading double-newlines in responses API stream
* fix(tests): resolve memory migration and skills route pagination bugs from PR overlaps
* docs: Update CHANGELOG.md with v3.6.6 features (#1182, #1165, #1177)
* chore(release): bump version to 3.6.6
Update package versions for the electron app and open-sse package.
Sync llm.txt metadata and feature headings with the 3.6.6 release.
* feat(core): harden outbound provider calls and add cooldown retries
Add guarded outbound fetch helpers with private/local URL blocking,
controlled retries, timeout normalization, and route-level status
propagation for provider validation and model discovery.
Introduce cooldown-aware chat retries with configurable
requestRetry and maxRetryIntervalSec settings, model-scoped cooldown
responses, and improved rate-limit learning from headers and error
bodies so short upstream lockouts can recover automatically.
Also align Antigravity and Codex header handling, require API keys
for Pollinations, validate web runtime env at startup, restore
sanitized Gemini tool names in translated responses, and inject a
synthetic Claude text block when upstream SSE completes empty.
* feat(models): add glmt preset and hybrid token counting
Introduce GLM Thinking as a first-class provider preset with shared GLM
model metadata, pricing, usage sync, dashboard support, and provider
request defaults for higher token budgets and longer timeouts.
Use provider-side /messages/count_tokens when a Claude-compatible
upstream supports it, while preserving estimated fallback behavior for
missing models, missing credentials, and upstream failures.
Also add startup seeding for default model aliases and normalize common
cross-proxy model dialects so canonical slashful model ids do not get
misrouted during resolution.
* feat(api): add sync tokens and v1 websocket bridge
Add dedicated sync token storage, issuance, revocation, and bundle
download routes backed by stable config bundle versioning and ETag
support.
Expose the v1 websocket handshake route and custom Next server bridge so
OpenAI-compatible websocket traffic can be upgraded and proxied through
the dashboard and API bridge.
Expand compliance auditing with structured metadata, pagination, request
context, auth and provider credential events, and SSRF-blocked
validation logging.
* docs: Update all documentation for v3.6.6
- CHANGELOG: Add WebSocket bridge, GLM Thinking preset, safe outbound
fetch/SSRF guard, cooldown-aware retries, compliance audit v2, model
alias seeding, and all Internal Improvements for the 3 new commits
- README: Expand v3.6.x highlights table with 10 new features; add
SafeOutboundFetch, CooldownAwareRetry, SSRF guard, TPS metric, sync
tokens, WebSocket bridge to Resilience/Observability/Deployment tables
- ARCHITECTURE: Bump date; add new modules to executive summary, API
routes, SSE core services, Auth/Security section; add SSRF/Outbound
guard failure mode (section 6); expand module mapping
- ENVIRONMENT: Add OMNIROUTE_CRYPT_KEY/OMNIROUTE_API_KEY_BASE64 legacy
aliases, OUTBOUND_SSRF_GUARD_ENABLED, CODEX_CLIENT_VERSION, and
REQUEST_RETRY/MAX_RETRY_INTERVAL_SEC cooldown retry settings
- FEATURES: Add 6 new feature sections — V1 WebSocket Bridge, Sync
Tokens & Config Bundle, GLM Thinking Preset, Safe Outbound Fetch &
SSRF Guard, Cooldown-Aware Retries, Compliance Audit v2
* fix: use api64 for proxy test (#1255)
Integrated into release/v3.6.6 — IPv6 proxy test fix
* fix(page): update custom models section to include all providers #1200 (#1256)
Integrated into release/v3.6.6 — Gemini custom model picker fix
* fix: provide default client_id fallbacks to prevent broken OAuth requests (#1246)
Integrated into release/v3.6.6 — OAuth client_id default fallbacks
* fix: translate max_tokens/max_completion_tokens → max_output_tokens in Chat→Responses translator (#1245)
Integrated into release/v3.6.6 — max_tokens → max_output_tokens Responses API translation + unit tests
* feat(oauth): support cursor-agent CLI as Cursor credential source (#1258)
Integrated into release/v3.6.6 — cursor-agent CLI credential source support
* fix(cc-compatible): restore upstream SSE and correct stream/combo timeout behavior (#1257)
Integrated into release/v3.6.6 — CC-compatible upstream SSE restore + stream timeout fix + README table repair
* fix(cli-tools): resolve API key resolution and model mapping bugs in CLI tools (#1263)
Integrated into release/v3.6.6
* feat(cli-tools): add Qwen Code CLI integration (#1266)
Integrated into release/v3.6.6
* fix(i18n): add missing zh-CN translations and fix logger imports (#1269)
Integrated into release/v3.6.6
* fix(i18n): add Chinese i18n support to dashboard components (#1274)
Integrated into release/v3.6.6
* feat: update Pollinations to require API key, remove free tier flag (#1177)
* feat: friendly error messages for crypto/encryption failures (#1165)
* feat: add TPS (tokens per second) metric column to request logs (#1182)
* feat: merge custom/imported models into filter list for all providers (#1191)
* feat(fallback): Fix provider-profile-driven lockouts (#1267)
This integrates rdself's unify-provider-profile-locks PR manually to handle structural conflicts.
* fix(claude): proper Anthropic SDK integration (#1271)
* fix(healthcheck): use correct proxy wrapper format for getAccessToken (#1272)
* chore(release): v3.6.6 — skills registry stability fix + final integration
* fix(auth): harden bootstrap auth and memory dashboard behavior
Restrict unauthenticated writes to /api/settings/require-login to
the initial bootstrap window while keeping read-only checks public.
This prevents post-setup config changes without blocking first-run
login setup, and the onboarding flow now logs in immediately after
setting the password.
Restore memory API filtering and pagination behavior by supporting q
searches, honoring offset-based requests, and avoiding unrelated
fallback results when FTS misses. Update dashboard stats fallback to
use the response totals consistently.
Package the MCP server with explicit file entries and add regression
tests for bootstrap auth and memory route behavior
* fix(codex): remove max_output_tokens from body for compatibility
* chore(release): v3.6.6 — include PR 1274 fixes in changelog
* chore: exclude additional build artifacts and internal directories from npm package distribution
* fix: update Gemini OAuth test to match registry defaults + codex UI improvements
* fix: restore .mjs refs for scripts/ in test imports after ts migration
* fix: restore next.config.mjs ref in dev-origins test
* fix: implement db migration safety checks and codex config format
* fix: disable mass-migration abort during unit tests based on auto-backup flag
* fix: update script regex in auto-update tests to use .mjs
* feat: Add Perplexity Web (Session) provider (#1289)
Integrated into release/v3.6.6
* fix(cli): resolve codex routing config parsing, standardize select model button positioning, and clarify oauth documentation
* docs(changelog): record recent cli, provider, and test updates
Document the latest fixes for Codex routing configuration parsing and
Lobehub provider icon fallback behavior.
Add the note that the remaining JavaScript test files were migrated to
TypeScript ES modules to reflect the completed test stack transition.
* chore(release): merge #1286 minor improvements manually to avoid testing conflict
* chore(test): rename perplexity-web.test.mjs to .ts to maintain 100% TS codebase
* chore(docs): update CHANGELOG.md for perplexity-web provider
* fix(security): resolve CodeQL incomplete URL substring sanitization via URL parsing in test mocks
* fix: integrate compressContext() into chatCore.ts request pipeline
Proactively compress oversized contexts before sending to upstream providers,
preventing context_length_exceeded errors. Compression triggers at 85% of
model's context limit using the existing 3-layer compressContext() function.
- Import compressContext, estimateTokens, getTokenLimit from contextManager
- Add compression check after translation, before executor dispatch
- Estimate tokens and compare against 85% threshold of model's context limit
- Apply 3-layer compression (trim tools, compress thinking, purify history)
- Log compression events with before/after token counts and layers applied
- Audit compression events for observability
- Add unit tests verifying integration behavior
Closes#1290
* fix(tests): align reasoning expectations with GLM thinking structure
* fix: prevent orphaned tool_result messages in purifyHistory()
When purifyHistory() drops oldest messages to fit context window, it can
split tool_use/tool_result pairs — keeping the tool_result but dropping
the tool_use that initiated it. This causes upstream providers to reject
the request with format errors.
Add fixToolPairs() that runs after each purification pass to remove:
- OpenAI format: orphaned role='tool' messages without matching tool_calls ID
- Claude format: orphaned tool_result content blocks without matching tool_use ID
Closes#1291
* fix(tests): supply tool_use in mock so it is not dropped
* chore: convert remaining test to TypeScript
* fix(tests): restore compatibility with compressContext threshold test after tsx migration
* docs: finalize v3.6.6 release documentation
* fix(core): finalize provider removal, type issues, and codex API key config
* fix(dashboard): render Web/Cookie, Search, Audio provider sections and fix TypeScript errors
* fix: increase MCP web_search timeout to 60s (#1278)
* fix: route combo testing properly for embedding models (#1260)
* fix: accumulate excluded accounts in combo fallback loop (#1233)
* fix: strip leading whitespace and newlines from first streaming chunk (#1211)
* docs: clarify VPS and Docker settings for OAuth credentials (#1204)
* fix: return real retry-after for pipeline gates (#1301)
Integrated into release/v3.6.6 — returns real Retry-After values from pipeline gates
* feat: streaming semantic cache, Cursor auto-version detection, and call-log enhancements (#1296)
Integrated into release/v3.6.6 — streaming semantic cache, Cursor auto-version detection, call-log cache_source tracking
* feat(api): support more OpenAI types (image, embeddings, audio-transcriptions, audio-speech) (#1297)
Integrated into release/v3.6.6 — adds embeddings, audio-transcriptions, audio-speech, and images-generations support for custom OpenAI-compatible providers, plus Pollinations image registry
* deps: bump hono from 4.12.12 to 4.12.14 (#1302)
Integrated into release/v3.6.6
* deps: bump hono from 4.12.12 to 4.12.14 (#1306)
Integrated into release/v3.6.6
* chore: stabilization fixes for v3.6.6 (#1298, #1254, #59, CI)
* fix(providers): match correct endpoint for Xiaomi MiMo, strip routing prefix for custom openai endpoints (#1303, #1261)
* feat(storage): add database backup cleanup controls
* chore(release): v3.6.6 — Final Stabilization Push
* Backport call log storage refactor to release/v3.6.6 (#1307)
Integrated into release/v3.6.6
* deps: update dompurify to 3.4.0 to resolve CVE-XYZ (#60)
* test: disable sqlite auto backup in CI to resolve E2E timeout (#24481475058)
* chore(docs): sync CHANGELOG for v3.6.6 with missing features and fixes
* chore(release): prep v3.6.6 infrastructure and type safety fixes
- Migrated legacy .mjs scripts to .ts (bin, prepublish, policies)
- Resolved pre-commit strict lint (t11 budget) errors in combo.ts
- Explicitly typed all TS bindings in pack-artifact policies
- Updated package.json commands to run Node via tsx/esm internally
- Hardened CI/CD with explicit node version 22.22.2 checks
- Completed stage validations for v3.6.6 final release
* chore: fix TS build errors and e2e timeouts in CI
- Migrate nodeRuntimeSupport to TS interfaces avoiding implicit any
- Increase visibility timeouts in skills-marketplace E2E test to 15s to bypass CI flakiness
- Complete migration of .mjs scripts to .ts ensuring type safety
* chore(release): sync package version 3.6.6 across workspaces
* test(e2e): universally increase UI component visibility timeouts from 5s to 15s to bypass CI starvation
* chore(build): inject baseUrl, paths, and types:node into MITM tsconfig within prepublish hook to fix missing types in CI check
---------
Co-authored-by: diegosouzapw <diegosouzapw@users.noreply.github.com>
Co-authored-by: Jack <5443152+hijak@users.noreply.github.com>
Co-authored-by: Randi <55005611+rdself@users.noreply.github.com>
Co-authored-by: Paijo <14921983+oyi77@users.noreply.github.com>
Co-authored-by: Samuel Cedric <ceds.sam@gmail.com>
Co-authored-by: Max Garmash <max@37bytes.com>
Co-authored-by: Markus Hartung <mail@hartmark.se>
Co-authored-by: Gi99lin <74502520+Gi99lin@users.noreply.github.com>
Co-authored-by: Payne <baboialex95@gmail.com>
Co-authored-by: Benson K B <bensonkbmca@gmail.com>
Co-authored-by: clousky2020 <33016567+clousky2020@users.noreply.github.com>
Co-authored-by: Ravi Tharuma <25951435+RaviTharuma@users.noreply.github.com>
Co-authored-by: oyi77 <oyi77@users.noreply.github.com>
Co-authored-by: Hdsje <vovan877@gmail.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: xiaoge1688 <moyekongling@gmail.com>
This document outlines the Code of Conduct for community members, including pledges, standards of behavior, enforcement responsibilities, and consequences for violations.
Adds a new provider that routes through Grok's internal NDJSON API using
an X/Grok subscription SSO cookie, enabling access to Grok 3, 4, 4.1,
4.2/4.20, and 4 Heavy via grok.com without xAI API costs.
- GrokWebExecutor with full NDJSON→OpenAI translation
- 12 models incl. grok-4.2 (4.20 beta), grok-4-heavy (SuperGrok)
- Dynamic x-statsig-id generation (base64 fake TypeError)
- W3C traceparent headers for Cloudflare compatibility
- Thinking/reasoning mode for mini/thinking/expert/heavy variants
- SSO cookie auth with auto-strip of 'sso=' prefix
- Fetch timeout + upstreamExtraHeaders (BaseExecutor parity)
- 16 unit tests, all passing
Derived from: GrokProxy, GrokBridge, grok-web-api, grok2api-merged,
Grok API Research Report
Remove unsupported Gemini schema fields including vendor-prefixed
`x-` properties so translated tool definitions avoid rejected keywords.
Emit an empty `content` field with the initial assistant role delta to
keep OpenAI-compatible streaming output consistent for clients that
expect content on the first chunk.
Also force undici's fetch whenever a dispatcher is provided and treat
`onRequestStart` version mismatches as fatal instead of falling back to
native fetch, preventing broken proxy requests under mixed undici
versions.
Cache the in-flight xxhash-wasm initialization so concurrent calls reuse
the same promise before the raw hash function is available.
This avoids redundant loader work and prevents races during early CCH
computations.
Persist background degradation settings as structured data so they can
be reloaded during node startup without double-encoding JSON.
Update settings validation to accept the missing fields used by the
API and align models.dev sync interval bounds with millisecond-based
values.
Also strip omniModel tags when they are wrapped by either literal
escaped newlines or actual newline characters, and adjust the combo
routing test to match the cleaned streamed content.
Add automated SQLite health diagnostics with optional auto-repair,
startup and scheduled execution, authenticated API routes, an MCP tool,
and dashboard visibility for status and repair actions.
Improve provider compatibility by adding Cursor usage fetching and
v3.1.0 parity headers, introducing a per-connection Codex Responses
store opt-in with session fallback, fixing Codex non-stream combo and
SSE translation behavior, sanitizing Gemini googleSearch tool payloads
and Qwen thinking tool_choice handling, and hardening cleanup and call
log storage paths.
CLIProxyAPI works without bans using hardcoded darwin/arm64 in the
Antigravity User-Agent. Real Antigravity is a macOS desktop tool —
reporting the actual server OS (linux/amd64 on a VPS) is MORE
suspicious than always claiming darwin/arm64. Matches proven
production fingerprint.
Matches the Antigravity executor treatment:
- Dynamic User-Agent: GeminiCLI/0.31.0/MODEL (OS; ARCH) per-model
- X-Goog-Api-Client: maintained (was already correct)
- Header scrubbing: removes proxy/fingerprint headers
- Sensitive word obfuscation in user message content
- Tracks current model for per-request UA generation
Brings the Antigravity executor to parity with CLIProxyAPI and
ZeroGravity for Gemini/Google traffic handling.
New modules:
- antigravityHeaderScrub.ts: Removes 28 proxy/fingerprint/Chromium
headers that reveal non-native traffic. Sets Accept-Encoding to
'gzip, deflate, br' (Node.js default).
- antigravity429Engine.ts: 4-tier 429 classification (unknown,
rate_limited, quota_exhausted, soft_rate_limit) with nuanced
retry decisions (soft_retry, instant_retry, short_cooldown,
full_quota_exhausted). Per-auth credits failure tracking with
auto-disable after 3 failures (5h cooldown).
- antigravityCredits.ts: Google One AI credits injection — retries
quota_exhausted 429s with enabledCreditTypes: ['GOOGLE_ONE_AI'].
Enabled via ANTIGRAVITY_CREDITS=1 env var.
- antigravityHeaders.ts: Dynamic User-Agent from OS/arch
(antigravity/1.21.9 darwin/arm64), Gemini CLI UA per-model
(GeminiCLI/0.31.0/MODEL (OS; ARCH)), X-Goog-Api-Client header
(google-genai-sdk/1.41.0 gl-node/v22.19.0).
- antigravityObfuscation.ts: Sensitive word obfuscation using
zero-width joiners for 17 client names (matching ZeroGravity).
Updated antigravity.ts:
- Dynamic UA replaces hardcoded 'antigravity/1.104.0 darwin/arm64'
- X-Goog-Api-Client header added (was missing entirely)
- Header scrubbing on all outbound requests
- 4-tier 429 engine replaces 2-category classification
- Google One AI credits retry on quota_exhausted
- Sensitive word obfuscation in user message content
Squash merge of feat/claude-code-native-parity into release/v3.6.5.
## Wiring
1. base.ts: CCH xxHash64 body signing for anthropic-compatible-cc-* providers,
applied after CLI fingerprint ordering so the hash covers the final bytes
sent upstream.
2. chatCore.ts: After buildClaudeCodeCompatibleRequest(), applies synchronous
parity pipeline steps:
- remapToolNamesInRequest() — TitleCase tool name mapping (14 tools)
- enforceThinkingTemperature() — temperature=1 when thinking active
- disableThinkingIfToolChoiceForced() — remove thinking on forced tool_choice
Cache-control limit enforcement intentionally omitted from chatCore because
the billing-header system block counts toward the 4-block cap and would strip
legitimate client cache markers.
3. xxhash-wasm: installed (was declared in package.json by PR but not installed).
## Test updates
- tests/unit/claude-code-parity.test.mjs: 25 new tests covering CCH signing,
fingerprint computation, tool remapping, and API constraints.
- tests/unit/cc-compatible-provider.test.mjs: fixed pre-existing assertion that
expected no cache_control on system blocks (billing header now carries ephemeral
per PR #1188 design).
Closes#1188
Integrated into release/v3.6.5. Fixed accountId key consistency between executor and fetcher. Added 13 unit tests for credit cache helpers, SSE parsing, and accountId derivation contract.
Integrated into release/v3.6.5. Added CHANGELOG breaking change entry for the removed /api/settings/codex-service-tier endpoint and deduplicated getCodexRequestDefaults in page.tsx (now imports from requestDefaults.ts).
Integrated into release/v3.6.5 — fixes Windows Electron packaged startup failure caused by split NODE_PATH between app.asar.unpacked and app/node_modules. Review improvement: added debug log for skipped candidate paths.
Fixes test expectations for non-streaming requests expecting 'Accept: application/json' instead of undefined. Resolves API_KEY_SECRET missing in unit tests post security hardening. Adds robust Playwright waits to combo E2E testing.
Protect database backup, export, restore, and translator save endpoints
with authentication checks to block unauthenticated data access and
state changes.
Also remove the insecure API key secret fallback, ignore nested app env
files from package publishes, and align tests with explicit
application/json Accept headers for non-stream requests
Load existing combos before normalizing POST and PUT payloads so
legacy string references can still resolve to combo-ref models.
This keeps stored combo references consistent while preserving DAG
validation for newly created and updated combos.
Move model routing management into Settings and add a unified
model alias editor for exact and wildcard remaps.
Sync combo defaults with global routing strategy settings, add
localized combo onboarding copy, and expand routing i18n across
supported locales.
Also fix supporting routing behavior by accepting all strategy
values in settings schemas, preserving connection ids in combo
tests, honoring non-stream JSON requests for CC-compatible
providers, and handling hashed external package subpaths.
Apply composite tier ordering to top-level combo steps and direct
targets so priority and round-robin strategies follow the configured
defaultTier to fallbackTier chain before using remaining steps.
Add defensive config parsing helpers, regression tests for composite
tier ordering, and documentation updates for the structured combo
builder, quota-aware P2C, and combo target health.
