- Add test-schema-sanitizer.cjs to run-all.cjs test runner
- Add test:sanitizer npm script for running it individually
- Update test to use renamed cleanSchema function
- Fix interleaved thinking test to not require thinking blocks after
tool result (model decides when to use visible thinking)
Co-Authored-By: Claude <noreply@anthropic.com>
The /compact command was failing with 'Proto field is not repeating,
cannot start list' error for Claude models because tool schemas were
sent with lowercase JSON Schema types (array, object, string) but
Google's Cloud Code API expects uppercase protobuf types (ARRAY,
OBJECT, STRING).
Changes:
- Add toGoogleType() function to convert JSON Schema types to Google format
- Add Phase 5 to cleanSchemaForGemini() for type conversion
- Apply cleanSchemaForGemini() for ALL models (not just Gemini) since
all requests go through Cloud Code API which validates schema format
- Add comprehensive test suite with 10 tests covering nested arrays,
complex schemas, and real-world Claude Code tool scenarios
Fixes#82
- Add [ignore] tags around system instruction to prevent model from
identifying as "Antigravity" when asked "Who are you?"
- Replace full system instruction with minimal version used by
CLIProxyAPI/gcli2api to reduce token usage and improve response quality
Fixes#76
Co-Authored-By: Claude <noreply@anthropic.com>
Adopts issue template pattern from opencode-antigravity-auth:
- Bug report template with [BUG] prefix and 6-item checklist
- Feature request template with [FEATURE] prefix
- Config disables blank issues, adds links to Google Cloud Support, TOS, and Discussions
Co-Authored-By: Claude <noreply@anthropic.com>
Fixes issue #71 - 'No accounts available' error when API returns 429
The Google Cloud Code API can return 429 RESOURCE_EXHAUSTED errors even
when accounts have quota available due to:
- Temporary API load/throttling
- Per-minute request limits (not per-day quota)
- Transient backend issues
This fix adds:
1. A 500ms buffer after waiting for rate limits to expire
2. Optimistic rate limit reset when all accounts appear stuck
3. Retry logic that clears rate limits and tries again
The fix works in conjunction with the server-level optimistic reset
that already exists, providing multiple layers of protection against
false 'No accounts available' errors.
Co-Authored-By: Claude <noreply@anthropic.com>
- Add test:emptyretry script and include in test suite
- Fix test-interleaved-thinking: use complex prompt to force thinking
- Fix test-multiturn-thinking-tools: make Turn 2 lenient (thinking optional)
- Fix test-multiturn-thinking-tools-streaming: same lenient approach
- Use TEST_MODELS helper instead of hardcoded model ID
Models may skip thinking on obvious next steps - this is valid behavior.
Tests now only require thinking on first turn to verify signatures work.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Adds comprehensive test for the empty response retry mechanism:
- Verifies EmptyResponseError class exists and works correctly
- Tests basic requests still work (no regression)
- Validates error class behavior and detection
All tests pass successfully.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Issues found by Claude Opus 4.5 + Gemini 3 Pro:
HIGH PRIORITY FIXES:
- Mark account rate-limited when 429 occurs during retry (was losing resetMs)
- Add exponential backoff between retries (500ms, 1000ms, 2000ms)
- Fix 5xx handling: don't pass error response to streamer, refetch instead
- Use recognizable error messages (429/401) for isRateLimitError/isAuthError
MEDIUM PRIORITY FIXES:
- Refactor while loop to for loop for clearer retry semantics
- Simplify logic flow with early returns
Code review by: Claude Opus 4.5 + Gemini 3 Pro Preview
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- 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>
