Commit Graph

4 Commits

Author SHA1 Message Date
diegosouzapw
59a8b8db35 fix: cursor decompression fallback + codex token refresh + password setup bypass (#250, #251, #256)
fix(cursor): add zlib inflate/inflateRaw fallback for GZIP_ALT/GZIP_BOTH frames (#250)
- GZIP_ALT (0x02) and GZIP_BOTH (0x03) frames may use zlib deflate instead of gzip
- Now tries gunzipSync → inflateSync → inflateRawSync with verbose error logging

fix(codex): override refreshCredentials to enable automatic token refresh on 401 (#251)
- CodexExecutor was inheriting base class null return, blocking 401 recovery
- Now calls refreshCodexToken() from tokenRefresh.ts on 401 upstream response
- Handles rotating token errors and surfaces re-auth warning clearly

fix(auth): allow dashboard access when no password is set after onboarding skip (#256)
- isAuthRequired() was blocking /dashboard/settings when setupComplete=true but no password
- Removed setupComplete guard: if there's no password, auth cannot be required
- Configure Password button on login page now navigates correctly to security settings
2026-03-09 10:47:16 -03:00
diegosouzapw
1c2f553a7c feat: features 07/09/04/06 — codex clamp, openrouter cache, quota preflight & monitor
feat(codex): clamp reasoning effort per model (feature-07)
- Add MAX_EFFORT_BY_MODEL table in CodexExecutor
- Add clampEffort() applied after effort derivation
- Logs debug when clamp is applied

feat(catalog): OpenRouter catalog with persistent cache (feature-09)
- New src/lib/catalog/openrouterCatalog.ts with TTL 24h + stale-if-error
- New GET /api/models/openrouter-catalog endpoint (authenticated)
- Reduces redundant OpenRouter API calls from dashboard

feat(quota): quota preflight with per-provider toggle (feature-04)
- New open-sse/services/quotaPreflight.ts
- Toggle: providerSpecificData.quotaPreflightEnabled (default: false)
- Extensible via registerQuotaFetcher() pattern
- Graceful degradation when no fetcher registered

feat(quota): quota session monitor with per-provider toggle (feature-06)
- New open-sse/services/quotaMonitor.ts
- Toggle: providerSpecificData.quotaMonitorEnabled (default: false)
- Adaptive polling: 60s normal / 15s critical
- Alert deduplication (5min suppression window)
- timer.unref() ensures clean process exit

feat(providers): support providerSpecificData patch in PUT /api/providers/[id]
- Partial merge of providerSpecificData (preserves existing keys)
- Schema updated to accept providerSpecificData in updateProviderConnectionSchema
2026-03-08 17:36:17 -03:00
nyatoru
0610909116 feat(codex): add workspace binding via chatgpt-account-id header 2026-02-23 01:11:53 +07:00
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