 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 |
|
 Rodin
|
3c536c42d5
|
Add unit tests, integration test, CI workflow, and conventions
CI / test (push) Successful in 18s
CI / review (push) Has been skipped
- gitea/client_test.go: mock HTTP tests for all API methods + error cases
- llm/client_test.go: mock tests for completion, errors, timeouts
- review/parser_test.go: JSON parsing, markdown fences, validation
- review/formatter_test.go: markdown output, empty/multiple findings
- review/prompt_test.go: system/user prompt construction
- integration_test.go: full end-to-end flow (build tag: integration)
- .gitea/workflows/ci.yml: test + vet + build on push, dual LLM review on PRs
- CONVENTIONS.md: coding standards for self-review dogfooding
- README.md: usage docs, env vars, architecture
|
2026-05-01 10:03:44 -07:00 |
|