Commit Graph

23 Commits

Author SHA1 Message Date
Rodin d83ea4f726 feat: replace log.Printf with structured slog logging
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, security, SECURITY_REVIEW.md, SECURITY_REVIEW_TOKEN) (pull_request) Successful in 52s
CI / review (gpt-5, sonnet, SONNET_REVIEW_TOKEN) (pull_request) Successful in 1m5s
- Add --log-format flag (text/json) and --verbosity flag (debug/info/warn/error)
- Replace all log.Printf with slog.Info/Debug/Warn with structured key-value attrs
- Replace all log.Fatalf with slog.Error + os.Exit(1)
- Convert gitea/client.go warnings to slog.Warn
- Add comprehensive tests for logger initialization and level filtering

Closes #23
Partially addresses #32
2026-05-02 11:01:55 -07:00
Rodin 2339999d37 fix: URL-encode asset filename, truncate error body in APIError
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, security, SECURITY_REVIEW.md, SECURITY_REVIEW_TOKEN) (pull_request) Successful in 51s
CI / review (gpt-5, sonnet, SONNET_REVIEW_TOKEN) (pull_request) Successful in 1m21s
- URL-encode filename in release upload query param (MINOR)
- Truncate APIError.Body to 200 chars in Error() to avoid leaking
  verbose server responses into logs (NIT)
2026-05-02 10:02:03 -07:00
Rodin bfca28b2b2 fix: address review findings from PR #33
CI / test (pull_request) Successful in 13s
CI / review (gpt-4.1, gpt, GPT_REVIEW_TOKEN) (pull_request) Successful in 22s
CI / review (gpt-5, sonnet, SONNET_REVIEW_TOKEN) (pull_request) Successful in 1m9s
CI / review (gpt-5, security, SECURITY_REVIEW.md, SECURITY_REVIEW_TOKEN) (pull_request) Successful in 1m42s
- Wrap fileErr instead of err in GetAllFilesInPath fallback (MINOR)
- Use env var for asset name in release workflow to avoid quoting issues (NIT)
2026-05-02 09:58:41 -07:00
Rodin f047c994bf fix: distinguish 404 in GetAllFilesInPath, make uploads idempotent
CI / test (pull_request) Successful in 14s
CI / review (gpt-4.1, gpt, GPT_REVIEW_TOKEN) (pull_request) Successful in 22s
CI / review (gpt-5, security, SECURITY_REVIEW.md, SECURITY_REVIEW_TOKEN) (pull_request) Successful in 58s
CI / review (gpt-5, sonnet, SONNET_REVIEW_TOKEN) (pull_request) Successful in 1m7s
- Add APIError type with StatusCode field so callers can inspect HTTP
  status codes from Gitea API responses
- Add IsNotFound helper for ergonomic 404 checks
- GetAllFilesInPath now only falls back to single-file fetch on 404;
  all other errors (auth failures, server errors, rate limits) propagate
- Release workflow asset uploads are now idempotent: existing assets
  with the same name are deleted before re-upload on workflow re-runs

Closes #8
Closes #10
2026-05-02 09:50:35 -07:00
Rodin c2595d0263 fix: consistent url.PathEscape across all Gitea client endpoints
CI / test (pull_request) Successful in 14s
CI / review (gpt-4.1, gpt, GPT_REVIEW_TOKEN) (pull_request) Successful in 21s
CI / review (gpt-5, security, SECURITY_REVIEW.md, SONNET_REVIEW_TOKEN) (pull_request) Successful in 34s
CI / review (gpt-5, sonnet, SONNET_REVIEW_TOKEN) (pull_request) Successful in 35s
Apply url.PathEscape to owner, repo, and sha path segments in all
methods that were previously interpolating raw values. Methods already
using PathEscape (ListReviews, DeleteReview, GetTimelineReviewCommentID,
EditComment) are unchanged.

This eliminates an inconsistency flagged in PRs #17, #20, and #22 and
prevents potential path-injection bugs for names with special characters.

Closes #24
2026-05-02 02:41:51 -07:00
Rodin ec19622133 fix: address review findings (escalation, marshal error, redundant check)
CI / test (pull_request) Successful in 13s
CI / review (gpt-4.1, gpt, GPT_REVIEW_TOKEN) (pull_request) Successful in 23s
CI / review (gpt-5, security, SECURITY_REVIEW.md, SONNET_REVIEW_TOKEN) (pull_request) Successful in 1m11s
CI / review (gpt-5, sonnet, SONNET_REVIEW_TOKEN) (pull_request) Successful in 1m21s
1. First-run escalation regression (MAJOR): Add post-posting escalation
   fallback. After posting APPROVED on first run, check if a sibling
   from the same user has REQUEST_CHANGES — if so, mark ours as
   superseded and re-post as REQUEST_CHANGES.

2. json.Marshal error handling (MINOR): Return error from EditComment
   instead of ignoring it with blank identifier.

3. Redundant condition (NIT): Remove dead assignment in reviewUnchanged
   where existingEvent was assigned from r.State then compared to itself.
2026-05-01 22:50:13 -07:00
Rodin e261976dd8 feat: edit-in-place review updates (no more delete)
CI / test (pull_request) Successful in 13s
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 1m37s
CI / review (gpt-5, security, SECURITY_REVIEW.md, SONNET_REVIEW_TOKEN) (pull_request) Successful in 1m43s
Replace the delete-and-repost strategy with edit-in-place:

1. No existing review → POST new (first run)
2. Same state, same body → skip entirely (threads preserved)
3. Same state, body changed → PATCH body in place via timeline API
4. State change needed → PATCH old body to "Superseded", POST new

This preserves conversation threads on inline comments. Replies to
findings are never lost. The only time a new review is posted is on
first run or when the state transitions (APPROVED ↔ REQUEST_CHANGES).

New Gitea client methods:
- EditComment: PATCH /repos/{owner}/{repo}/issues/comments/{id}
- GetTimelineReviewCommentID: finds the comment ID for a review body
  by scanning the issue timeline for the sentinel

Also simplifies shouldEscalate: removes the login parameter requirement
for pre-posting scenarios (uses findOwnReview to get login from existing
review instead).

Tests: findOwnReview (4 cases), EditComment (2 cases),
GetTimelineReviewCommentID (2 cases), shouldEscalate (8 cases updated).
2026-05-01 22:46:45 -07:00
Rodin 2ac7f55396 feat: inline review comments on specific lines
CI / test (pull_request) Successful in 13s
CI / review (gpt-4.1, gpt, GPT_REVIEW_TOKEN) (pull_request) Successful in 23s
CI / review (gpt-5, security, SECURITY_REVIEW.md, SONNET_REVIEW_TOKEN) (pull_request) Successful in 43s
CI / review (gpt-5, sonnet, SONNET_REVIEW_TOKEN) (pull_request) Successful in 1m29s
Findings that reference a file+line within the diff are now posted as
inline comments directly on that line, in addition to appearing in the
summary table. Findings outside the diff range stay in the body only.

Implementation:
- gitea/diff.go: ParseDiffNewLines extracts new-file line numbers from
  each hunk in the unified diff
- gitea/client.go: PostReview accepts optional []ReviewComment with
  path + new_position + body (omitempty when nil)
- cmd/review-bot/main.go: maps findings → inline comments when the line
  exists in the diff, passes them to PostReview

Tests:
- diff parser: multi-hunk, new files, empty diff, boundary lines
- PostReview: with comments, nil comments (omitted from payload)
2026-05-01 21:59:21 -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 41c670b44b fix: post-then-cleanup flow, remove dead code, pagination
CI / test (pull_request) Successful in 14s
CI / review (gpt-4.1, gpt, GPT_REVIEW_TOKEN) (pull_request) Successful in 31s
CI / review (gpt-5, sonnet, SONNET_REVIEW_TOKEN) (pull_request) Successful in 1m22s
- PostReview now returns *Review (id + user login from response)
- Delete flow: post first, then delete stale reviews by same user
- No read:user scope needed (identity from POST response)
- Removed GetAuthenticatedUser (requires scope we lack)
- ListReviews: full pagination (loops until partial page)
- envOrDefaultBool: case-insensitive, whitespace-trimmed
- action.yml: document accepted boolean values
- Tests updated for new PostReview signature
2026-05-01 20:38:21 -07:00
Rodin 0d417e068e feat: delete previous review before posting new one (#6)
CI / test (pull_request) Successful in 13s
CI / review (gpt-4.1, gpt, GPT_REVIEW_TOKEN) (pull_request) Successful in 21s
CI / review (gpt-5, sonnet, SONNET_REVIEW_TOKEN) (pull_request) Successful in 1m20s
Before posting a review, the bot now:
1. Calls GET /api/v1/user to identify its own login
2. Lists all reviews on the PR
3. Deletes any existing reviews from itself
4. Posts the fresh review

This keeps PR threads clean — one review per bot at any time.

New Gitea client methods:
- GetAuthenticatedUser() — token self-identification
- ListReviews() — fetch reviews on a PR
- DeleteReview() — delete a review by ID

Flag: --update-existing / UPDATE_EXISTING (default true)
Set to false to preserve old behavior (stack reviews).

All delete failures are non-fatal (logged as warnings).

Closes #6
2026-05-01 20:17:01 -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 7b42de67ca fix: handle empty path in ListContents (root listing)
CI / test (pull_request) Successful in 14s
CI / review (gpt-5, sonnet, SONNET_REVIEW_TOKEN) (pull_request) Successful in 1m4s
CI / review (gpt-5-mini, gpt, GPT_REVIEW_TOKEN) (pull_request) Successful in 1m8s
Empty path now yields /contents instead of /contents/ (trailing slash).
Added doc comment noting empty path = repo root.
2026-05-01 14:46:40 -07:00
Rodin dd2661fe14 fix: address all review findings from PR #17
CI / test (pull_request) Successful in 13s
CI / review (gpt-5, sonnet, SONNET_REVIEW_TOKEN) (pull_request) Successful in 52s
CI / review (gpt-5-mini, gpt, GPT_REVIEW_TOKEN) (pull_request) Successful in 1m12s
- Rename all remaining url locals to reqURL (consistency)
- Use http.MethodGet/http.MethodPost constants
- Document escapePath: relative paths only, double-encoding expected
- Add TestEscapePath with 7 edge cases (empty, spaces, #, deep, encoded)
2026-05-01 14:40:19 -07:00
Rodin 98a4772f30 fix: path-escape file paths and eliminate url package shadowing
CI / test (pull_request) Successful in 14s
CI / review (gpt-5, sonnet, SONNET_REVIEW_TOKEN) (pull_request) Successful in 55s
CI / review (gpt-5-mini, gpt, GPT_REVIEW_TOKEN) (pull_request) Successful in 1m48s
- Add escapePath() helper: escapes each path segment individually
  (preserves slashes as separators, escapes spaces/#/? etc)
- Apply to GetFileContent, GetFileContentRef, ListContents
- Rename doGet parameter from url to reqURL (avoids shadowing net/url)
- Rename local variables in GetFileContent/ListContents for consistency

Addresses remaining findings from PR #16 review.
2026-05-01 14:33:18 -07:00
Rodin b02ade4f23 fix: quick wins (#7, #9, #13)
CI / test (pull_request) Successful in 13s
CI / review (gpt-5, sonnet, SONNET_REVIEW_TOKEN) (pull_request) Successful in 59s
CI / review (gpt-5-mini, gpt, GPT_REVIEW_TOKEN) (pull_request) Successful in 1m48s
- Add --version flag and log version on startup (closes #9)
- URL-escape ref query parameter in GetFileContentRef (closes #7)
- Add go vet to release workflow (closes #13)

Renamed local url variable to reqURL to avoid shadowing net/url package.
2026-05-01 14:19:37 -07:00
Rodin 0cca44b65a fix: address all remaining review findings on PR #14
CI / test (pull_request) Successful in 13s
CI / review (gpt-5, sonnet, SONNET_REVIEW_TOKEN) (pull_request) Successful in 1m29s
CI / review (gpt-5-mini, gpt, GPT_REVIEW_TOKEN) (pull_request) Successful in 1m36s
- Fix doc comments: WithTimeout and WithTemperature each get their own
- Add TestWithTimeout (verifies short timeout causes request failure)
- Log warning on directory recursion failure in GetAllFilesInPath
- Note: unexported fields is a breaking change, will document in release notes
2026-05-01 13:17:39 -07:00
Rodin cedb5e7b90 fix: address all review findings on PR #14
CI / test (pull_request) Successful in 13s
CI / review (gpt-5, sonnet, SONNET_REVIEW_TOKEN) (pull_request) Successful in 48s
CI / review (gpt-5-mini, gpt, GPT_REVIEW_TOKEN) (pull_request) Failing after 2m12s
- gitea.Client: add concurrency safety doc comment
- gitea.Client: set 30s HTTP client timeout as safety net
- llm.Client: add concurrency safety doc comment
- llm.Client: set 2min HTTP client timeout (LLM calls are slow)
- gitea/client.go: gofmt to fix indentation
- integration_test: update to current BuildSystemPrompt/BuildUserPrompt signatures
- integration_test: use strings.SplitN for owner/repo parsing
2026-05-01 12:56:07 -07:00
Rodin ecebd52371 fix: log warnings instead of swallowing errors
CI / test (pull_request) Successful in 13s
CI / review (gpt-5, sonnet, SONNET_REVIEW_TOKEN) (pull_request) Successful in 1m29s
CI / review (gpt-5-mini, gpt, GPT_REVIEW_TOKEN) (pull_request) Successful in 1m44s
- GetAllFilesInPath: log.Printf when file fetch or dir recursion fails
- integration_test: use strings.SplitN for owner/repo parsing (idiomatic)

Addresses GPT review findings #1, #2.
2026-05-01 12:45:52 -07:00
Rodin 27e0056f29 feat: add context.Context + unexport client fields
CI / test (pull_request) Successful in 13s
CI / review (gpt-5, sonnet, SONNET_REVIEW_TOKEN) (pull_request) Successful in 54s
CI / review (gpt-5-mini, gpt, GPT_REVIEW_TOKEN) (pull_request) Successful in 1m22s
REVIEW.md findings 1-4, 14:
- All Gitea client methods now accept context.Context as first param
- All LLM client methods now accept context.Context as first param
- Use http.NewRequestWithContext for cancellation/timeout support
- Main uses 3-minute timeout context for all operations
- Unexport Client struct fields (baseURL, token, apiKey, etc.)
- Use bytes.NewReader instead of strings.NewReader(string(...))
2026-05-01 12:31:41 -07:00
Rodin 56f5abda3c feat: multi-repo patterns + directory recursion
CI / test (pull_request) Successful in 14s
CI / review (gpt-5-mini, gpt, GPT_REVIEW_TOKEN) (pull_request) Successful in 1m57s
CI / review (gpt-5, sonnet, SONNET_REVIEW_TOKEN) (pull_request) Successful in 2m2s
patterns-repo now accepts a comma-separated list of repos:
  PATTERNS_REPO="rodin/elixir-patterns,rodin/phoenix-conventions"

patterns-files accepts files AND directories:
  PATTERNS_FILES="README.md,docs/"

When a path is a directory, all files within it are fetched
recursively via the Gitea contents API. Only .md, .txt, .yml,
and .yaml files are included as pattern content.

New API methods:
- ListContents: list files/dirs at a path via contents API
- GetAllFilesInPath: recursively fetch all file contents

This allows a single review action to pull idioms from multiple
pattern repos (e.g. elixir-patterns + phoenix-conventions) and
include entire directories of documentation as review criteria.
2026-05-01 12:14:19 -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 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