Fixes 3 critical bugs in parser.go:
1. Gemini detection: Change Delta from bool to *bool for proper field
presence detection. Fixes issue where delta:false events were lost.
2. Codex detection: Tighten logic to only classify as Codex if
thread_id exists OR item.type is non-empty. Prevents Claude events
with item:null/item:{} from being misclassified and dropped.
3. Performance: Move itemHeader parsing inside item.completed case,
only parse when actually needed.
Additional changes:
- Implement PR #86's Gemini notifyMessage trigger on Status field
instead of Content, resolving parser.go conflict between PRs
- Add regression tests for all fixed scenarios
- All tests pass: go test ./...
Co-authored-by: Codeagent (Codex)
Generated with SWE-Agent.ai
Co-Authored-By: SWE-Agent.ai <noreply@swe-agent.ai>
* fix(gemini): filter noisy stderr output from gemini backend
- Add filteringWriter to filter [STARTUP], Warning, Session cleanup etc.
- Apply filter only for gemini backend stderr output
- Add unit tests for filtering logic
* fix: use defer for stderrFilter.Flush to cover all return paths
Address review feedback: ensure filter is flushed on failure paths
- Add cliff.toml configuration matching current CHANGELOG.md format
- Replace awk script with npx git-cliff in release workflow
- Add `make changelog` command for one-click CHANGELOG updates
- Use git-cliff --current flag to generate release notes per version
Generated with swe-agent-bot
Co-Authored-By: swe-agent-bot <agent@swe-agent.ai>
Previously, all parallel tasks shared the same log file path, making it
difficult to debug individual task execution. This change creates a
separate log file for each task using the naming convention:
codeagent-wrapper-{pid}-{taskName}.log
Changes:
- Add withTaskLogger/taskLoggerFromContext for per-task logger injection
- Modify executeConcurrentWithContext to create independent Logger per task
- Update printTaskStart to display task-specific log paths
- Extract defaultRunCodexTaskFn for proper test hook reset
- Add runCodexTaskFn reset to resetTestHooks()
Test coverage: 93.7%
Generated with swe-agent-bot
Co-Authored-By: swe-agent-bot <agent@swe-agent.ai>
- Update version to 5.2.2 in README.md, README_CN.md, and codeagent-wrapper/main.go
- Remove non-existent documentation links from README.md (architecture.md, GITHUB-WORKFLOW.md, enterprise-workflow-ideas.md)
- Add coverage.out to .gitignore
Generated with swe-agent-bot
Co-Authored-By: swe-agent-bot <agent@swe-agent.ai>
- Added Skills System Enhancements section to CHANGELOG
- Documented new skills: codeagent, product-requirements, prototype-prompt-generator
- Removed deprecated test files (tests/test_*.py)
- Updated release date to 2025-12-13
Generated with swe-agent-bot
Co-Authored-By: swe-agent-bot <agent@swe-agent.ai>
- Add maxParallelWorkersLimit=100 cap for CODEAGENT_MAX_PARALLEL_WORKERS
- Remove scripts/install.sh (codex-wrapper legacy alias no longer needed)
- Fix README command example: /gh-implement -> /gh-issue-implement
- Add TestResolveMaxParallelWorkers unit test for limit validation
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Renamed "Enabled" column to "Default" and added hint explaining
the meaning of the checkmark.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Remove committed binaries from git tracking (codeagent-wrapper, *.test)
- Remove coverage.out from tracking (generated by CI)
- Update .gitignore to exclude build artifacts
- Add task block index to parallel config error messages for better debugging
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
