Commit Graph

3 Commits

Author SHA1 Message Date
Rodin c76362af95 fix: prevent false-positive missing-import findings
CI / test (pull_request) Successful in 13s
CI / review (gpt-5, sonnet, SONNET_REVIEW_TOKEN) (pull_request) Successful in 1m59s
CI / review (gpt-5-mini, gpt, GPT_REVIEW_TOKEN) (pull_request) Successful in 3m36s
The LLM was treating the diff as complete file context and flagging
"missing imports" for symbols that exist in unchanged portions of
the file. Added explicit instructions to the system prompt:

- Clarify that the diff is partial; unchanged code already exists
- Explicitly instruct: do not flag missing imports/types unless the
  diff introduces a new usage without a corresponding addition
- Add rule: never flag undefined symbols that could exist in the
  unchanged portions
2026-05-01 12:00:27 -07:00
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
Rodin 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