9 Commits

Author SHA1 Message Date
Rodin 2287a8238c feat: add role title as H1 header for visual differentiation
CI / test (pull_request) Successful in 14s
CI / review (gpt-4.1, gpt, GPT_REVIEW_TOKEN) (pull_request) Successful in 19s
CI / review (gpt-5, security, SECURITY_REVIEW.md, SONNET_REVIEW_TOKEN) (pull_request) Successful in 1m27s
CI / review (gpt-5, sonnet, SONNET_REVIEW_TOKEN) (pull_request) Successful in 1m42s
When reviewer-name is set, prepend "# Security Review" / "# Sonnet Review"
etc. as a top-level header. Makes it immediately obvious which role each
review represents in the Gitea UI, especially when multiple reviews come
from the same bot account.
2026-05-01 21:36:32 -07:00
Rodin 69e0a459c3 feat: sentinel-based review cleanup + system prompt file + security review
CI / test (pull_request) Successful in 14s
CI / review (gpt-4.1, gpt, GPT_REVIEW_TOKEN) (pull_request) Successful in 23s
CI / review (gpt-5, sonnet, SONNET_REVIEW_TOKEN) (pull_request) Successful in 58s
CI / review (gpt-5, security, SECURITY_REVIEW.md, SONNET_REVIEW_TOKEN) (pull_request) Successful in 1m35s
Sentinel-based cleanup:
- Reviews embed <!-- review-bot:NAME --> in body (hidden HTML comment)
- Cleanup matches by sentinel, not token identity
- Each reviewer-name is a logical identity (sonnet, gpt, security)
- Same token can run multiple review types without conflict
- No extra API scopes needed

System prompt file (--system-prompt-file / SYSTEM_PROMPT_FILE):
- Loads a local file with additional review instructions
- Appended to system base as "Additional Review Instructions"
- Enables specialized reviews (security, performance, etc.)
- Partially addresses #5

Security review:
- SECURITY_REVIEW.md prompt focused on vulnerabilities
- 3rd CI matrix entry using same token, different prompt
- Focus: injection, auth, secrets, input validation, crypto, races

CI changes:
- REVIEWER_NAME passed from matrix.name
- SYSTEM_PROMPT_FILE passed from matrix (empty for standard reviews)
- 3 reviewers: sonnet (general), gpt (general), security (focused)
2026-05-01 20:55:09 -07:00
Rodin dab7871cb4 fix: address review findings on budget system
CI / test (pull_request) Successful in 14s
CI / review (gpt-5, sonnet, SONNET_REVIEW_TOKEN) (pull_request) Successful in 1m41s
CI / review (gpt-5-mini, gpt, GPT_REVIEW_TOKEN) (pull_request) Successful in 3m2s
- Account for truncation marker tokens when computing diff budget
  (prevents EstTokens exceeding model limit in edge cases)
- Rune-safe truncation for both UserMeta and Diff (no split multi-byte)
- Fix misleading comment (1000 chars → ~1000 tokens/4000 chars)
- Extract marker strings as constants
- Add unit tests for BuildSystemBase and BuildUserMeta
2026-05-01 18:59:07 -07:00
Rodin 67d835909f feat: add context budget system for LLM overflow (#19)
CI / test (pull_request) Successful in 13s
CI / review (gpt-5, sonnet, SONNET_REVIEW_TOKEN) (pull_request) Successful in 1m30s
CI / review (gpt-5-mini, gpt, GPT_REVIEW_TOKEN) (pull_request) Successful in 2m29s
Adds a budget package that estimates token usage and progressively
trims context to fit within model-specific limits.

Trim order (least important first):
1. Language patterns
2. Repository conventions
3. Full file context
4. Diff (truncated as last resort)

When content is trimmed, a note is appended to the user prompt so
the LLM knows context was reduced.

- New budget package with Fit(), EstimateTokens(), LimitForModel()
- Model limit table (GPT-4.1: 128K, GPT-5: 200K, Claude: 200K)
- Refactored review/prompt.go: BuildSystemBase() and BuildUserMeta()
  extract non-trimmable content; old functions delegate to new ones
- main.go uses budget.Fit() instead of direct prompt assembly
- 7 unit tests covering all trim paths

Closes #19
2026-05-01 18:46:53 -07:00
Rodin aade891129 docs: add package-level documentation
CI / test (pull_request) Successful in 14s
CI / review (gpt-5, sonnet, SONNET_REVIEW_TOKEN) (pull_request) Failing after 55s
CI / review (gpt-5-mini, gpt, GPT_REVIEW_TOKEN) (pull_request) Failing after 1m6s
Per go-patterns/package-design.md, every package needs a doc comment.
Added to gitea, llm, and review packages.
2026-05-01 14:54:58 -07:00
Rodin e234dca474 feat: full file context + patterns-repo support
CI / test (pull_request) Successful in 13s
CI / review (gpt-5, sonnet, SONNET_REVIEW_TOKEN) (pull_request) Successful in 1m51s
CI / review (gpt-5-mini, gpt, GPT_REVIEW_TOKEN) (pull_request) Successful in 2m0s
Major improvements to review quality:

1. Full file context: fetch complete content of all modified files from
   the PR branch and include as reference. This eliminates false-positive
   "missing import" findings since the model sees the entire file.

2. Patterns repo: new --patterns-repo / PATTERNS_REPO flag fetches
   language idiom files from a separate Gitea repo (e.g. rodin/elixir-patterns)
   and includes them as review criteria.

3. Multi-file patterns: --patterns-files / PATTERNS_FILES accepts
   comma-separated file paths to fetch from the patterns repo.

New API methods:
- GetPullRequestFiles: list changed files in a PR
- GetFileContentRef: fetch file content from a specific branch/ref

Prompt changes:
- BuildSystemPrompt now accepts (conventions, patterns)
- BuildUserPrompt now accepts fileContext parameter
- File context displayed before diff for model reference
- Patterns presented as "review criteria" in system prompt

Composite action updated with patterns-repo and patterns-files inputs.
2026-05-01 12:11:49 -07:00
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