Commit Graph

20 Commits

Author SHA1 Message Date
aweiker bd2df7d986 feat(#120): add GitHub Actions support with VCS host detection and security hardening
PR Ready Gate / clear-labels (pull_request) Successful in 1s
CI / test (pull_request) Successful in 17s
CI / review (anthropic--claude-4.6-sonnet, sonnet, SONNET_REVIEW_TOKEN) (pull_request) Successful in 33s
CI / review (gpt-5, security, ., rodin/security-patterns, SECURITY_REVIEW.md, SECURITY_REVIEW_TOKEN) (pull_request) Successful in 1m39s
CI / review (gpt-5, gpt, GPT_REVIEW_TOKEN) (pull_request) Successful in 1m58s
- Detect VCS host type from github.api_url (present on GitHub/GHES, absent on Gitea)
- Add action-repo input: specifies repo hosting review-bot releases, separate from
  the reviewed repo. Defaults to github.action_repository, then rodin/review-bot.
- Add action-repo-token input: auth for release downloads (defaults to github.token
  on GitHub, reviewer-token on Gitea).
- GitHub/GHES path: use github.api_url for version resolution and REST API asset
  download endpoint (required for private repos; web URLs redirect to S3 and don't
  support Authorization headers reliably).
- Gitea path: use validated SERVER_URL with direct download (no -L; prevents
  Authorization forwarding on potential CDN redirects).
- Security hardening:
  - inputs.vcs-url is IGNORED on GitHub/GHES to prevent token exfiltration
  - SERVER_URL validated for https scheme and no whitespace on Gitea path
  - action-repo validated against owner/repo pattern (prevent path traversal)
  - VERSION validated for no slashes/whitespace
  - TOKEN validated for no control characters (header injection defense)
  - ACTION_TOKEN passed via ::add-mask:: + GITHUB_ENV (not step output, which
    can leak in debug logs)
  - set -euo pipefail in both script steps
- Multi-arch support: OS/arch detection via uname (linux/darwin, amd64/arm64)
  for cache key and binary name — incorporates changes from #124
- Run review step: passes VCS_URL from step output (server_url) instead of
  direct input expression

Closes #120
2026-05-14 07:14:58 +00:00
Rodin b80a1517ed fix: remove trailing whitespace in action.yml
PR Ready Gate / clear-labels (pull_request) Successful in 1s
CI / test (pull_request) Successful in 15s
CI / review (anthropic--claude-4.6-sonnet, sonnet, SONNET_REVIEW_TOKEN) (pull_request) Successful in 38s
CI / review (gpt-5, security, ., rodin/security-patterns, SECURITY_REVIEW.md, SECURITY_REVIEW_TOKEN) (pull_request) Successful in 1m17s
CI / review (gpt-5, gpt, GPT_REVIEW_TOKEN) (pull_request) Successful in 1m24s
2026-05-13 23:00:35 -07:00
Rodin 5f7ffab487 feat(#125): rename GITEA_URL to VCS_URL with deprecated fallback
- Add --vcs-url flag as primary (reads VCS_URL env var)
- Keep --gitea-url and GITEA_URL as deprecated fallbacks with warnings
- Update action.yml: rename gitea-url input to vcs-url, pass VCS_URL to binary
- Update ci.yml: use VCS_URL env var in Run review step
- Update integration tests: INTEGRATION_GITEA_URL -> INTEGRATION_VCS_URL
- Update README: --vcs-url / VCS_URL with fallback note in env var table

Backward compat: existing GITEA_URL users get a deprecation warning and
continue to work unchanged until they migrate to VCS_URL.
2026-05-13 23:00:35 -07:00
aweiker f8b9d7d282 fix: portable checksum on darwin, anchor grep pattern
PR Ready Gate / clear-labels (pull_request) Successful in 2s
CI / test (pull_request) Successful in 17s
CI / review (anthropic--claude-4.6-sonnet, sonnet, SONNET_REVIEW_TOKEN) (pull_request) Successful in 27s
CI / review (gpt-5, security, ., rodin/security-patterns, SECURITY_REVIEW.md, SECURITY_REVIEW_TOKEN) (pull_request) Successful in 1m4s
CI / review (gpt-5, gpt, GPT_REVIEW_TOKEN) (pull_request) Successful in 1m13s
CI / test (push) Successful in 17s
CI / review (anthropic--claude-4.6-sonnet, sonnet, SONNET_REVIEW_TOKEN) (push) Has been skipped
CI / review (gpt-5, gpt, GPT_REVIEW_TOKEN) (push) Has been skipped
CI / review (gpt-5, security, ., rodin/security-patterns, SECURITY_REVIEW.md, SECURITY_REVIEW_TOKEN) (push) Has been skipped
- sha256sum is not available on macOS; use shasum -a 256 on darwin.
  Select based on steps.version.outputs.os which is already computed.
  Fixes MAJOR finding from gpt-review-bot (PR #127 review).

- Anchor checksum grep with ^ to avoid matching on partial lines.
  Fixes MINOR finding from gpt-review-bot (PR #127 review).
2026-05-14 05:48:21 +00:00
aweiker 7a8fc166ec feat(action): derive binary name from uname for multi-arch support (#124)
CI / test (pull_request) Successful in 17s
CI / review (anthropic--claude-4.6-sonnet, sonnet, SONNET_REVIEW_TOKEN) (pull_request) Successful in 26s
CI / review (gpt-5, security, ., rodin/security-patterns, SECURITY_REVIEW.md, SECURITY_REVIEW_TOKEN) (pull_request) Successful in 1m12s
CI / review (gpt-5, gpt, GPT_REVIEW_TOKEN) (pull_request) Successful in 1m33s
Previously the Install step hard-coded 'review-bot-linux-amd64'. This
fails on arm64 runners (Graviton, Apple Silicon) where uname -m returns
'aarch64' or 'arm64'.

Changes:
- Add OS/arch detection in 'Determine version' step using uname -s/-m
- Map uname output to asset name format: x86_64→amd64, aarch64/arm64→arm64,
  linux→linux, darwin→darwin
- Emit 'os' and 'arch' as step outputs alongside 'version'
- Update cache key: review-bot-{os}-{arch}-{version}
- Update Install step: BINARY derived from step outputs
- Anchor checksum grep to exact filename (not substring match)
- Unsupported OS or arch exits with a clear error message

Supported platforms: linux-amd64, linux-arm64, darwin-amd64, darwin-arm64
(matches what the release workflow builds)
2026-05-14 05:45:20 +00:00
Rodin 7dab35de41 feat: native SAP AI Core support
PR Ready Gate / clear-labels (pull_request) Successful in 2s
CI / test (pull_request) Successful in 14s
CI / review (anthropic--claude-4.6-sonnet, sonnet, SONNET_REVIEW_TOKEN) (pull_request) Successful in 35s
CI / review (gpt-5, gpt, GPT_REVIEW_TOKEN) (pull_request) Successful in 1m30s
CI / review (gpt-5, security, SECURITY_REVIEW.md, SECURITY_REVIEW_TOKEN) (pull_request) Successful in 2m0s
Add native SAP AI Core provider that handles OAuth token management and
deployment discovery automatically. This eliminates the need for the
external LLM proxy when running in SAP environments.

Changes:
- Add AICoreClient with OAuth token caching and deployment URL discovery
- Support both Anthropic and OpenAI models via AI Core deployments
- Update CI to use native AI Core provider
- Update action inputs to accept AI Core credentials
- Update README with AI Core configuration examples

Model names must match AI Core deployment names (e.g. anthropic--claude-4.6-sonnet, gpt-5).
2026-05-10 10:25:10 -07:00
Rodin 4dd67742f9 fix: address review feedback on persona feature
PR Ready Gate / clear-labels (pull_request) Successful in 2s
CI / test (pull_request) Successful in 15s
CI / review (/anthropic/v1, anthropic--claude-4.6-sonnet, sonnet, anthropic, SONNET_REVIEW_TOKEN) (pull_request) Successful in 43s
CI / review (/openai/v1, gpt-5, gpt, openai, GPT_REVIEW_TOKEN) (pull_request) Successful in 1m28s
CI / review (/openai/v1, gpt-5, security, openai, SECURITY_REVIEW.md, SECURITY_REVIEW_TOKEN) (pull_request) Successful in 1m55s
MAJOR fixes:
- Remove external YAML dependency (github.com/goccy/go-yaml)
  Per project convention: Go standard library only, zero dependencies.
  Convert all persona files from YAML to JSON format.
- Fix TestValidateWorkspacePath error expectation
  Go 1.21+ filepath.Join normalizes absolute paths differently.

MINOR fixes:
- Remove custom contains helper in persona_test.go (use strings.Contains)
- Add Unicode-safe CapitalizeFirst function for header titles
- ListBuiltinPersonas returns empty slice instead of nil on error
- Fix test comment about filepath.Join behavior

Documentation:
- Update README to reflect JSON-only persona format
- Update design doc with note about JSON decision
- Fix action.yml description for persona-file input
2026-05-10 10:01:34 -07:00
Rodin 57e62a345f feat(persona): add role-based review personas
PR Ready Gate / clear-labels (pull_request) Successful in 2s
CI / test (pull_request) Successful in 9m31s
CI / review (/anthropic/v1, anthropic--claude-4.6-sonnet, sonnet, anthropic, SONNET_REVIEW_TOKEN) (pull_request) Successful in 10m3s
CI / review (/openai/v1, gpt-5, gpt, openai, GPT_REVIEW_TOKEN) (pull_request) Successful in 11m30s
CI / review (/openai/v1, gpt-5, security, openai, SECURITY_REVIEW.md, SECURITY_REVIEW_TOKEN) (pull_request) Successful in 10m56s
Add persona system for specialized review roles. Each persona defines:
- A specific review focus (security, architecture, documentation)
- Custom system prompt additions
- Personality/tone adjustments

Built-in personas: security, architect, docs
Custom personas: load from JSON via persona-file flag

Includes workspace validation to prevent path traversal attacks.

Closes #51
2026-05-10 09:14:48 -07:00
Rodin 436e6a8824 fix: symlink traversal + worst-wins pre-check + user scoping
CI / test (pull_request) Successful in 14s
CI / review (gpt-4.1, gpt, GPT_REVIEW_TOKEN) (pull_request) Successful in 20s
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 1m16s
Security (MAJOR):
- Add filepath.EvalSymlinks after Clean for system-prompt-file
- Re-validate resolved path is still within workspace
- Prevents symlink → /etc/shadow exfiltration via malicious repo

Worst-wins:
- Check BEFORE posting (not after) — no delete+repost dance
- Identify sibling bots by <!-- review-bot: prefix in body
- Only escalates for bot reviews, not human REQUEST_CHANGES
- If sibling bot has REQUEST_CHANGES and we would APPROVE → post
  REQUEST_CHANGES instead

Addresses security review finding #1 (MAJOR) and sonnet finding #1.
2026-05-01 21:31:17 -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 14a0c2a946 feat: add Anthropic Messages API support (#18)
CI / test (pull_request) Successful in 13s
CI / review (gpt-5, sonnet, SONNET_REVIEW_TOKEN) (pull_request) Successful in 1m2s
CI / review (gpt-5-mini, gpt, GPT_REVIEW_TOKEN) (pull_request) Successful in 1m43s
Adds --llm-provider flag (openai|anthropic) to switch between API formats.

Anthropic implementation:
- POST /messages endpoint
- x-api-key + anthropic-version headers
- System prompt as top-level field (not a message)
- max_tokens: 8192 for response generation
- Parses content blocks [{type: "text", text: "..."}]

Changes:
- llm/client.go: Provider type, completeAnthropic(), doRequest() shared helper
- cmd/review-bot/main.go: --llm-provider / LLM_PROVIDER flag
- .gitea/actions/review/action.yml: llm-provider input + env
- llm/client_test.go: 4 new tests for Anthropic path

Backwards compatible — default provider is still openai.

Closes #18
2026-05-01 18:49:17 -07:00
Rodin 43041a00f5 fix: rewrite action.yml (was corrupted with duplicate keys)
CI / test (pull_request) Successful in 11s
CI / review (gpt-5, sonnet, SONNET_REVIEW_TOKEN) (pull_request) Successful in 1m34s
CI / review (gpt-5-mini, gpt, GPT_REVIEW_TOKEN) (pull_request) Successful in 1m33s
Clean single definition of all inputs: temperature, timeout,
patterns-repo, patterns-files. Also added runner requirements
comment at the top.
2026-05-01 13:08:18 -07:00
Rodin 1da61e514d feat: make LLM timeout configurable (default 5min)
CI / test (pull_request) Successful in 13s
CI / review (gpt-5, sonnet, SONNET_REVIEW_TOKEN) (pull_request) Successful in 1m6s
CI / review (gpt-5-mini, gpt, GPT_REVIEW_TOKEN) (pull_request) Successful in 1m14s
New flag: --llm-timeout / LLM_TIMEOUT (seconds, default 300)
New builder: llmClient.WithTimeout(duration)
Composite action: new timeout input

Keeps 5 minutes as the sensible default but allows tuning for
larger repos or slower models.
2026-05-01 13:04:00 -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 46c63ed121 fix: address all review findings (zero remaining)
CI / test (pull_request) Successful in 13s
CI / review (gpt-5-mini, gpt, GPT_REVIEW_TOKEN) (pull_request) Successful in 1m43s
CI / review (gpt-5, sonnet, SONNET_REVIEW_TOKEN) (pull_request) Successful in 2m19s
Tests:
- Add WithTemperature tests (builder method, chaining, zero omission)
- Add temperature serialization tests (omitted when 0, included when set)

Composite action:
- Use python3 for robust JSON version parsing (replaces sed)
- Verify SHA-256 checksum before executing downloaded binary
- Wire up repo input (no longer hardcodes rodin/review-bot)

Release workflow:
- Handle 409 conflict (existing release for tag)
- Use file-based JSON parsing for reliability

Code:
- Tighten WithTemperature doc comment (single clear line)
- Fix flag alignment (missing tab on llmTemp declaration)
2026-05-01 11:58:21 -07:00
Rodin 59fbd38837 fix: address all remaining review findings
CI / test (pull_request) Successful in 14s
CI / review (gpt-5, sonnet, SONNET_REVIEW_TOKEN) (pull_request) Successful in 2m20s
CI / review (gpt-5-mini, gpt, GPT_REVIEW_TOKEN) (pull_request) Successful in 2m20s
- Add temperature range validation (must be 0-2, fatal on invalid)
- release.yml: use python3 for robust JSON parsing instead of sed
- Composite action: add header comment confirming Gitea Actions compat
- All findings from review #385 addressed
2026-05-01 11:40:15 -07:00
Rodin 8d53b649ee fix: address review findings (cache path, docs)
CI / test (pull_request) Successful in 13s
CI / review (gpt-5, sonnet, SONNET_REVIEW_TOKEN) (pull_request) Successful in 2m13s
CI / review (gpt-5-mini, gpt, GPT_REVIEW_TOKEN) (pull_request) Successful in 2m48s
- Composite action: cache to runner.temp instead of /usr/local/bin
  (avoids permission issues on runners)
- Document that temperature=0 means server default (omitted from request)
- Note: strconv import already exists (false positive from GPT-5)
2026-05-01 11:38:28 -07:00
Rodin c458587cfc feat: add composite action for clean distribution
CI / test (pull_request) Successful in 13s
CI / review (gpt-5, sonnet, SONNET_REVIEW_TOKEN) (pull_request) Successful in 2m28s
CI / review (gpt-5-mini, gpt, GPT_REVIEW_TOKEN) (pull_request) Successful in 2m43s
- .gitea/actions/review/action.yml: composite action with caching
  Consumers just use:
    uses: https://gitea.weiker.me/rodin/review-bot/.gitea/actions/review@v0.1.0
  No Go toolchain needed, binary cached by version tag.

- Remove install.sh (replaced by composite action)
- CI workflow: use matrix strategy to parallelize reviews
- Self-review still builds from source (pre-release)
2026-05-01 11:32:15 -07:00