- File locking via proper-lockfile for concurrent write safety
- Atomic writes with temp file + rename pattern
- Merge-on-write pattern to preserve concurrent changes
- PID-based offset so different sessions start at different accounts
- Remove unused import (extractVariantThinkingConfig)
Fixes#70 - Gemini thoughtSignature persisting when switching to Claude
Root cause: sanitizeCrossModelPayloadInPlace() was only called for batched
requests, not for single requests. Gemini's thoughtSignature in tool metadata
persisted and caused Claude to reject with 'Invalid signature in thinking block'.
Bumps version to 1.2.8-beta.0
Fixes 'Invalid signature in thinking block' error when switching models mid-session.
Root cause: Gemini stores thoughtSignature in metadata.google on tool call parts,
but existing strippers only checked top-level signatures. When switching to Claude
with a tool call, the foreign signature caused validation errors.
Changes:
- Add cross-model-sanitizer module for bi-directional sanitization (Gemini<->Claude)
- Integrate sanitizer into request pipeline for Claude models
- Add 42 new tests (28 unit + 14 integration)
- Add E2E test scripts for 5-model verification
Tested with: Gemini, Claude (Anthropic), Claude (Google), OpenAI, all passing.
- Add test-models.ts for validating all supported model endpoints
- Add test-regression.ts for multi-turn regression testing (Issue #50)
- Consolidate Gemini 3 Flash variants (low/medium/high) into single model
- Fix schema structure by flattening nested signature_cache properties
- Extract streaming transformer utilities to dedicated module
- Fix version from 1.2.5-beta.7 back to official 1.2.5
- Add prerelease version check in release workflow to prevent publishing beta versions as official
- Add branch verification in beta workflow to prevent accidental runs on main branch
This prevents the issue where dev branch with beta versions was merged into main,
causing the main branch to have a prerelease version number.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
- Add 'antigravity-' prefix to route to Antigravity quota
- Models without prefix route to Gemini CLI quota
- Claude/GPT models auto-route to Antigravity (only available there)
- Gemini 3 tiers: Pro supports low/high, Flash supports minimal/low/medium/high
- Add thinkingLevel param for Gemini CLI, keep tier in model name for Antigravity
Resolves#51
- Workflow now auto-detects highest existing beta (from tags + npm)
- Increments to next beta: X.Y.Z-beta.N -> X.Y.Z-beta.(N+1)
- Updates package.json automatically with [skip ci]
- No manual version bumping needed for dev releases
- Bump base version to 1.2.6 for next release cycle
- Added recovery functionality for tool_result_missing, thinking_block_order, and thinking_disabled_violation errors.
- Introduced constants and types for session recovery.
- Created storage utilities for reading and writing session data.
- Enhanced debug logging capabilities in debug.ts.
- Refactored debug state management for better initialization and access.
Implement comprehensive support for Claude thinking models with interleaved
thinking in multi-turn conversations:
- Add signature caching system to preserve and restore thinking block
signatures across conversation turns, preventing "invalid signature" errors
- Enable real-time SSE streaming with immediate forwarding of thinking tokens
- Add interleaved-thinking-2025-05-14 beta header for Claude thinking models
- Implement smart system hints to encourage thinking during tool use
- Add VALIDATED mode for tool calling on Claude models
- Ensure output token limits accommodate thinking budgets
- Filter and sanitize thinking blocks, removing SDK-injected cache_control
- Add comprehensive test suites for auth, cache, and request-helpers modules
- Update build config to exclude test files from production builds
- Document streaming and thinking features in README
- Add CLI prompt to choose between adding accounts or starting fresh
- Implement automatic retry with backoff for single-account rate limits
- Show toast notifications for account switching and rate limit status
- Clear stale account storage when OpenCode auth state changes
- Add sleep helper function with abort signal support
- Improve README with clearer step-by-step setup instructions
TUI flow now adds accounts non-destructively; CLI flow offers choice.
