rodin
cabbb5a55a
fix: repair unescaped quotes in LLM JSON responses ( #45 )
...
CI / test (push) Successful in 14s
CI / review (/anthropic/v1, claude-sonnet-4-6, sonnet, anthropic, SONNET_REVIEW_TOKEN) (push) Has been skipped
CI / review (/openai/v1, gpt-4.1, gpt41, openai, GPT_REVIEW_TOKEN) (push) Has been skipped
CI / review (/openai/v1, gpt-4.1-mini, gpt41-mini, openai, GPT_REVIEW_TOKEN) (push) Has been skipped
CI / review (/openai/v1, gpt-5, gpt, openai, GPT_REVIEW_TOKEN) (push) Has been skipped
CI / review (/openai/v1, gpt-5, security, openai, SECURITY_REVIEW.md, SECURITY_REVIEW_TOKEN) (push) Has been skipped
CI / review (/openai/v1, gpt-5-mini, gpt5-mini, openai, GPT_REVIEW_TOKEN) (push) Has been skipped
Release / release (push) Successful in 34s
fix: repair unescaped quotes in LLM JSON responses
Add repairJSON fallback that handles unescaped quotes in LLM string
values using first-valid-candidate heuristic with structural lookahead.
Reviewed-by: sonnet-review-bot
Reviewed-by: gpt-review-bot
Reviewed-by: security-review-bot
2026-05-05 12:40:39 +00:00
700f186023
Initial implementation: AI code review bot for Gitea
...
- CLI binary with flag/env var configuration
- Gitea API client (PR metadata, diff, CI status, post review)
- OpenAI-compatible LLM client
- Structured review prompt with conventions support
- JSON response parser with validation
- Markdown review formatter for Gitea
- CI failure auto-detection (REQUEST_CHANGES)
- Dry-run mode for testing
2026-05-01 09:42:45 -07:00
rodin
Rodin