Add shared OAuth credential lifecycle manager with provider-aware refresh
decisions. Implement CodexExecutor.refreshCredentials so 401/403 retry
refresh works for Codex, track lastRefreshAt and refresh before the
upstream stale-token window, preserve omitted idToken, and add
per-connection single-flight refresh to avoid refresh-token rotation races.
Merged from PR #1664.
Co-authored-by: Cursor <cursoragent@cursor.com>
- Introduced Cloudflare AI as a new provider with specific configurations in providerModels.js and providers.js.
- Updated DefaultExecutor to handle account ID resolution for Cloudflare AI connections.
- Enhanced AddApiKeyModal and EditConnectionModal to include account ID input for Cloudflare AI.
- Implemented validation for Cloudflare AI API key connections in testUtils.js and route.js.
- Updated UI components to reflect changes in provider management and connection handling.
- Added new image models for GPT 5.2, 5.3, and 5.4, including capabilities for text-to-image and editing.
- Updated embedding handling to include optional dimensions in requests.
- Introduced support for custom embedding providers, allowing dynamic fetching and validation of custom nodes.
- Improved image generation handling with Codex integration, including progress tracking and error handling.
- Enhanced UI components to support adding custom embeddings and displaying their status.
- Added new provider models: DeepSeek 3.1, DeepSeek 3.2, and Qwen3 Coder Next.
- Implemented UI changes to support round-robin strategy with sticky limits in the provider detail page.
- Improved logging to display connection names instead of IDs for better clarity.
- Centralize proxy management with reusable proxy pools
- Per-connection proxy binding with legacy fallback
- Add strictProxy option: fail hard instead of silently falling back to direct
- Resolve alicode-intl conflict: keep alicode-intl support + proxy support
Made-with: Cursor
Cherry-picked from decolua/9router PR #183.
Note: open-sse changes included but need further review due to extensive modifications.
Co-authored-by: Cursor <cursoragent@cursor.com>
Providers like Antigravity maintain separate quota buckets per model family
(e.g. Claude vs Gemini). A 429 on claude-opus previously locked the entire
account, preventing gemini-pro requests even though its quota was full.
This adds in-memory per-model locking so that only the specific model is
skipped during account selection while other models remain accessible.
Changes:
- Add model-aware lock tracking in auth.js (Map<connectionId:model, expiry>)
- Pass model context from chat handler to auth service
- Multi-bucket behavior gated to known providers (MULTI_BUCKET_PROVIDERS set)
- No database schema changes — locks are in-memory and clear on restart
Closes#110
Adds a mutex to serialize account selection and updates in the
proxy engine. This ensures that concurrent requests respect the
sticky limit and don't distribute to the same account simultaneously.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Implements a "sticky" round-robin strategy that uses the same provider
account for a configurable number of consecutive calls (default 3)
before switching to the next one. This optimizes for prompt caching
by reducing organization/account rotation. Adds a configuration input
to the Profile settings page.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Implements a round-robin (least recently used) account selection strategy
alongside the existing fill-first priority system. Adds a toggle in the
Profile dashboard to switch between strategies.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
