Commit Graph

22 Commits

Author SHA1 Message Date
diegosouzapw
3b4e7b0e5f feat(claude-code): PR #1188 — Native parity with CCH signing, tool remapping, and API constraints
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
2026-04-12 22:41:12 -03:00
diegosouzapw
25bd04e400 feat(settings): unify routing rules and model aliases controls
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.
2026-04-12 18:43:19 -03:00
diegosouzapw
d4609762bb fix: resolve macOS Electron ABI mismatch and test regressions (#1081) 2026-04-11 11:36:58 -03:00
diegosouzapw
8bacde0262 feat: global email privacy toggle with eye icon button
- Add emailPrivacyStore (Zustand + persist) for global toggle state
- Add EmailPrivacyToggle component with eye open/closed icons
- Add pickDisplayValue() visibility-aware masking function
- Integrate toggle into provider detail, usage limits & playground pages
- Per-modal showEmail now uses global store (synced across all pages)
- Default: emails hidden; toggle persists across page reloads
- Add showEmails/hideEmails i18n keys
- Update CHANGELOG.md and openapi.yaml to v3.6.2
2026-04-11 09:38:17 -03:00
diegosouzapw
f5cd841056 fix(responses): legacy openai-compatible routing (#1069)
Integrated into release/v3.5.5.
Co-authored-by: rdself <rdself@users.noreply.github.com>
2026-04-08 14:15:19 -03:00
R.D.
231ca8a935 support custom user agent for third-party providers 2026-04-04 01:09:51 -04:00
oyi77
d82a7040f1 feat(cliproxyapi): add executor, proxy routing with SSRF guard & module-level cache
Part 2 of CLIProxyAPI integration (#902). Depends on PR1.

- CliproxyapiExecutor: HTTP bridge to localhost:8317, reuses BaseExecutor.mergeAbortSignals
- Executor registration with cliproxyapi + cpa aliases
- chatCore.ts: resolveExecutorWithProxy() with Object.create (preserves prototype methods)
- Module-level proxy config cache (10s TTL, shared across requests)
- Three routing modes: native (default), cliproxyapi (passthrough), fallback (auto-retry on 5xx/429)
- 21 unit tests for executor
2026-04-02 13:28:46 +07:00
Chris Staley
d852a51672 fix: refresh Gemini CLI project ID via loadCodeAssist to prevent 403 errors
The stored projectId from OAuth connection time becomes stale because the
Cloud Code API rotates free-tier projects. Native Gemini CLI refreshes the
project every 30 seconds via loadCodeAssist — OmniRoute never did, causing
403 "has not been used in project X" errors that permanently banned accounts.

- Add refreshProject() to GeminiCLIExecutor that calls loadCodeAssist API
  with 10s timeout and caches the result for 30s (matching native CLI)
- transformRequest() replaces the stale projectId in the envelope before
  sending to the Cloud Code API, falling back to the stored ID on failure
- Make transformRequest calls await-compatible in base executor and
  all subclasses (antigravity, cursor, kiro) so async overrides work
2026-03-31 11:13:04 -06:00
diegosouzapw
1c070d16a6 fix: add missing i18n keys for windsurf/copilot and apply fetch timeout to streaming requests (#748, #769)
- Add windsurf and copilot entries to toolDescriptions in all 33 locale files
  to fix MISSING_MESSAGE errors on the CLI Tools page (#748)
- Apply FETCH_TIMEOUT_MS to streaming requests' initial fetch() call to prevent
  300s TCP default timeout causing silent failures on long-running requests (#769)
- Previously only non-streaming requests had timeout protection; streaming requests
  relied solely on stream idle detection which doesn't cover initial connection hangs
2026-03-29 19:43:21 -03:00
zhang-qiang
a8ca88797a feat(dashboard,sse,api): per-model upstream headers, compat PATCH, chat alignment
- Store/sanitize upstreamHeaders; shared forbidden header names (upstreamHeaders.ts)

- chatCore: buildUpstreamHeadersForExecute; T5 recomputes; 401 retry uses translatedBody.model

- Dashboard compat popover + i18n; Zod partialRecord + header value newline guard

- Executors merge upstreamExtraHeaders; sanitize unit tests

- Dev: bootstrap env in run-next, instrumentation-node import, credentialLoader dedupe

Made-with: Cursor
2026-03-24 17:24:11 +08:00
diegosouzapw
047ff187f6 Merge branch 'feat/custom-endpoint-paths'
# Conflicts:
#	src/shared/constants/providers.ts
2026-03-20 19:34:10 -03:00
Sergey Morozov
8420e565d4 feat: add responses subpath passthrough for codex (#457) 2026-03-18 17:18:29 -03:00
diegosouzapw
605c3f9be1 feat(provider): add Alibaba Cloud DashScope + path validation for custom endpoint paths
- Add Alibaba Cloud (DashScope) as OpenAI-compatible provider with 12 Qwen models:
  qwen-max, qwen-plus, qwen-turbo, qwen3-coder-plus/flash, qwq-plus,
  qwq-32b, qwen3-32b, qwen3-235b-a22b
  International endpoint: dashscope-intl.aliyuncs.com/compatible-mode/v1
  Auth: Bearer API key (same as groq/xai/mistral)

- Add path traversal protection to custom endpoint paths (PR #400):
  sanitizePath() validates chatPath/modelsPath values:
  must start with '/', no '..' segments, no null bytes, max 512 chars

Closes #400 (custom endpoint paths), part of Alibaba provider integration
2026-03-16 09:44:17 -03:00
Regis
e25029939d feat(api): add custom endpoint paths for compatible provider nodes
Allow provider_nodes to configure custom chat and models endpoint
paths via chatPath/modelsPath fields. This enables providers with
non-standard versioned APIs (e.g. /v4/chat/completions) to work
without embedding the version prefix in base_url.

- Add migration 003: chat_path and models_path columns
- Update Zod schemas (create, update, validate)
- Update CRUD in providers.ts (INSERT/UPDATE)
- Wire chatPath/modelsPath through API routes and providerSpecificData cascade
- Read chatPath in DefaultExecutor and BaseExecutor buildUrl()
- Use modelsPath in validate endpoint
- Add Advanced Settings UI section (collapsible) in create/edit modals
- Update base URL hint to reference Advanced Settings
- Add i18n keys across all 30 locales
- Add unit tests for buildUrl with custom paths

Backward compatible: NULL chatPath/modelsPath = default behavior.
2026-03-16 10:23:44 +01:00
diegosouzapw
1b354be827 feat: T07 — API Key Round-Robin per provider connection
- New: open-sse/services/apiKeyRotator.ts — round-robin rotation
  between primary API key + providerSpecificData.extraApiKeys[]
- Modified: open-sse/executors/base.ts — buildHeaders() rotates key
  using getRotatingApiKey() when extraApiKeys configured
- Modified: open-sse/handlers/chatCore.ts — injects connectionId into
  credentials to enable per-connection rotation index tracking
- Modified: providers/[id]/page.tsx — 'Extra API Keys' UI section in
  EditConnectionModal: add/remove keys, persisted in providerSpecificData

T08 (quota window rolling) and T13 (wildcard model routing) confirmed
already implemented in accountFallback.ts and wildcardRouter.ts.
2026-03-14 15:03:54 -03:00
diegosouzapw
a87d64372f feat: Phase 1 & 2 implementation plan — T1-T10, T12
T1 (openai-to-claude.ts): response_format injection for json_schema/json_object
T2 (base.ts): intra-URL retry for 429 errors (2x, 2s delay)
T3 (gemini-cli.ts): CLI fingerprint headers (User-Agent, X-Goog-Api-Client)
T5 (modelFamilyFallback.ts + chatCore.ts): intra-family model fallback on 400/404
T9 (pricing.ts): deepseek-3.1, deepseek-3.2, qwen3-coder-next pricing
T10 (scoring.ts + modePacks.ts): tierPriority as 7th scoring factor (Ultra>Pro>Free)
T12 (cliRuntime.ts): isSafePath() guard for CLI_*_BIN env var paths
2026-03-12 18:06:53 -03:00
DavyMassoneto
623c63baf6 feat(claude): support [1m] suffix for 1M context window
Parse [1m] suffix from model name (e.g. claude-sonnet-4-6[1m]) and
propagate extendedContext flag through the request pipeline to append
context-1m-2025-08-07 to the Anthropic-Beta header.
2026-03-11 23:53:09 -03:00
diegosouzapw
ac89069671 feat: playground, CLI fingerprints, ACP support (#234, #223, #235)
- Add model playground page to dashboard (provider/model/endpoint selectors, Monaco editor, streaming, abort)
- Add CLI fingerprint matching (per-provider header/body ordering to match native CLI binaries)
- Add ACP module (CLI agent discovery, process spawner, session manager, API endpoint)
- Add playground to sidebar debug section with i18n support
- Close #192 and #200 as stale (v1.8.1, no repro info)
2026-03-07 10:24:43 -03:00
diegosouzapw
baa0208fa9 feat: v2.0.0 - MCP server, A2A agent, proxy improvements and docs update 2026-03-05 01:16:56 -03:00
diegosouzapw
0d8f28a4a4 feat: Introduce A2A lifecycle management, add type safety to ComfyUI and stream handling, and update various handlers and translators. 2026-03-04 21:02:56 -03:00
diegosouzapw
afa2cea678 feat: 16 pain points docs, configurable User-Agent (#155), fix hardcoded $HOME (#156)
- Add collapsible '16 Real Pain Points' section to all 30 READMEs
- Fix 5 files bypassing dataPaths.ts with hardcoded os.homedir() (closes #156)
- Add per-provider User-Agent env var overrides in base executor (closes #155)
- Sync .env and .env.example with 9 provider UA defaults
- Update CHANGELOG.md for v1.7.0
2026-02-28 17:41:55 -03:00
diegosouzapw
71d14209a4 feat: OmniRoute v1.0.0 — Intelligent AI Gateway & Universal LLM Proxy
OmniRoute is an intelligent API gateway that unifies 20+ AI providers behind a single
OpenAI-compatible endpoint. Features include intelligent routing with 6 strategies,
multi-format translation (OpenAI/Claude/Gemini/Responses API), circuit breakers,
semantic caching, combo fallback chains, real-time health monitoring, and a full
dashboard with provider management, analytics, and CLI tool integration.

Key highlights:
- 20+ providers (Claude Code, Codex, Gemini CLI, GitHub Copilot, iFlow, Qwen, Kiro, etc.)
- 6 routing strategies (Fill First, Round Robin, P2C, Random, Least Used, Cost Optimized)
- Export/Import database backup with full archive support
- Translator Playground with 4 modes (Playground, Chat Tester, Test Bench, Live Monitor)
- 100% TypeScript across src/ and open-sse/
- Docker support with multi-stage builds
- Comprehensive documentation and 9 dashboard screenshots
2026-02-18 00:02:15 -03:00