- Move MAX_EMPTY_RESPONSE_RETRIES to constants.js for consistency
- Handle 429/401/5xx errors properly during retry fetch
- Use proper message ID format (crypto.randomBytes) instead of Date.now()
- Add crypto import for UUID generation
Code review by: Gemini 3 Pro Preview + Claude Opus 4.5
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
When Claude Code sends requests with large thinking_budget values,
the model may spend all tokens on "thinking" and return empty responses,
causing Claude Code to stop mid-conversation.
This commit adds a retry mechanism that:
- Throws EmptyResponseError instead of emitting fake message on empty response
- Retries up to 2 times before giving up
- Emits fallback message only after all retries are exhausted
Changes:
- src/errors.js: Added EmptyResponseError class and isEmptyResponseError()
- src/cloudcode/sse-streamer.js: Throw error instead of yielding fake message
- src/cloudcode/streaming-handler.js: Added retry loop with fallback
Tested for 6+ hours with 1,884 API requests and 88% recovery rate
on empty responses.
Fixes#61🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Ensure proper encoding for international characters in error and success pages
by specifying charset=utf-8 in Content-Type headers and adding meta charset tags.
Replace generic Error instances with NativeModuleError in loadDatabaseModule
to provide more structured error information, including rebuild status and
restart requirements. Update getAuthStatus to re-throw NativeModuleError
instances without wrapping.
Add a new error class to handle native module errors, including version mismatches and rebuild requirements. This supports the auto-rebuild functionality by providing structured error information for rebuild success and restart needs.
Remove the local clearRequireCache function from database.js and import it from
utils/native-module-helper.js. Update the function call to pass require.cache
as the second parameter for proper cache clearing.
The function has been renamed to clearRequireCache and updated to recursively
clear the require cache for a module and all its dependencies, preventing
cycles with a visited set. This improves reliability after rebuilding native
modules by ensuring complete cache invalidation. Removed unused createRequire
import as it's no longer needed.
Add detailed stdout/stderr capture and logging for failed npm rebuild commands to improve troubleshooting. Also log successful rebuild output for debugging purposes.
Improve the findPackageRoot function to correctly detect filesystem root on all platforms by checking if dirname returns the same path, replacing the Unix-specific '/' check.
When Node.js is updated, native modules like better-sqlite3 can become
incompatible due to NODE_MODULE_VERSION differences. This change adds
automatic detection and rebuild capability:
- Add native-module-helper.js utility for detecting version errors
- Lazy-load better-sqlite3 to catch import errors at runtime
- Automatically run npm rebuild when version mismatch is detected
- Clear require cache and retry loading after successful rebuild
- Provide clear instructions if automatic rebuild fails
Fixes the issue where users running via npx encounter module errors
after updating Node.js.
- Fix extractCodeFromInput destructuring: returns { code, state } not
{ code, extractedState }, so state validation was being bypassed
- Add --no-browser hint to CLI banner for discoverability
- Document --no-browser mode in README.md and CLAUDE.md
- Add test:oauth script to package.json
- Add OAuth test to run-all.cjs test suite
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Add gemini-3-flash to MODEL_FALLBACK_MAP for completeness
- Add hasGeminiHistory() to detect Gemini→Claude cross-model switch
- Trigger recovery for Claude only when Gemini history detected
- Remove unnecessary thinking block filtering for Claude-only conversations
- Add comments explaining '.' placeholder usage
- Remove unused filterUnsignedThinkingFromMessages function
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Instead of stripping all thinking blocks during thinking recovery,
now only strips invalid or incompatible blocks. Uses signature cache
to validate family compatibility for cross-model fallback scenarios.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* feat: apply local user changes and fixes
* ;D
* Implement OpenAI support, model-specific rate limiting, and robustness fixes
* docs: update pr title
* feat: ensure unique openai models endpoint
* fix: startup banner alignment and removed duplicates
* feat: add model fallback system with --fallback flag
* fix: accounts cli hanging after completion
* feat: add exit option to accounts cli menu
* fix: remove circular dependency warning for fallback flag
* feat: show active modes in banner and hide their flags
* Remove OpenAI compatibility and fallback features from PR #35
Cherry-picked selective fixes from PR #35 while removing:
- OpenAI-compatible API endpoints (/openai/v1/*)
- Model fallback system (fallback-config.js)
- Thinking block skip for Gemini models
- Unnecessary files (pullrequest.md, test-fix.js, test-openai.js)
Retained improvements:
- Network error handling with retry logic
- Model-specific rate limiting
- Enhanced health check with quota info
- CLI fixes (exit option, process.exit)
- Startup banner alignment (debug mode only)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* banner alignment fix
* Refactor: Model-specific rate limits and cleanup deprecated code
- Remove global rate limit fields (isRateLimited, rateLimitResetTime) in favor of model-specific limits (modelRateLimits[modelId])
- Remove deprecated wrapper functions (is429Error, isAuthInvalidError) from handlers
- Filter fetchAvailableModels to only return Claude and Gemini models
- Fix getCurrentStickyAccount() to pass model param after waiting
- Update /account-limits endpoint to show model-specific limits
- Remove multi-account OAuth flow to avoid state mismatch errors
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* fix: show (x/y) limited status in account-limits table
- Status is now "ok" only when all models are available
- Shows "(x/y) limited" when x out of y models are exhausted
- Provides better visibility into partial rate limiting
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* docs: update CLAUDE.md with model-specific rate limiting
- Document modelRateLimits[modelId] for per-model rate tracking
- Add isNetworkError() helper to utilities section
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
---------
Co-authored-by: M1noa <minoa@minoa.cat>
Co-authored-by: Minoa <altgithub@minoa.cat>
Co-authored-by: Claude <noreply@anthropic.com>
Fixes#33 - Accounts marked as invalid were permanently stuck because
the isInvalid flag was persisted to disk but never reset on startup.
Changes:
- Reset isInvalid flag for all accounts on server startup, giving them
a fresh chance to refresh their OAuth tokens
- Add logging for project discovery failures (was silently failing)
- Add success logging when project is discovered
- Add warning message when falling back to default project
Bug introduced in 01cda83 (2025-12-25) when isInvalid persistence was
added without corresponding reset logic on load.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Replace CLI-based sqlite3 extraction with better-sqlite3 library:
- Create shared src/db/database.js module for cross-platform SQLite access
- Remove duplicate extractTokenFromDB functions from token-extractor.js and account-manager.js
- Add better-sqlite3 dependency with prebuilt Windows/Mac/Linux binaries
- Improve error handling with specific messages for common issues
Fixes#23🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Add in-memory signature cache to restore thoughtSignatures stripped by Claude Code
- Implement thinking recovery logic to handle interrupted tool loops for Gemini
- Enhance schema sanitizer to preserve constraints and enums as description hints
- Update CLAUDE.md with new architecture details
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
