## Summary
Full Pi PR review parity with Bun server, plus shared fixes and UI improvements.
### Pi PR Review (new)
- Parse PR/MR URLs, authenticate, fetch metadata and diff
- Create local worktree (same-repo) or shallow clone (cross-repo) for agent file access
- Full server parity: all 27 feature areas audited and aligned
### Shared Fixes (Bun + Pi)
- parseRemoteUrl: GitLab subgroup support, SSH+port, HTTPS non-standard port
- Cross-repo clone: --hostname replaced with GH_HOST/GITLAB_HOST env vars
- Cross-repo clone: shallow fetch depth 50 → 200
- Git Add button disabled in PR review mode (client-side)
- DiffViewer: eliminate dark flash on file switch (sync theme init)
### UI
- Resolved/Outdated toggle filters in PR comments tab
For provenance purposes, this commit was AI assisted.
gh pr diff computes diffs against the merge-base (common ancestor), but
file contents were fetched at baseSha (base branch tip). When the base
branch has moved since the branch point, line counts don't match the
diff hunks, causing iterateOverDiff trailing context mismatch crashes.
Fetch the merge-base SHA via GitHub's compare API and use it for old
file contents. Added try/catch around processFile as a safety net.
Fixed in both Bun and Pi servers.
For provenance purposes, this commit was AI assisted.
* feat(review): token-level code selection for annotations
Add the ability to click individual syntax tokens in the diff viewer to
create annotations with precise code context. Uses Pierre v1.1.12's
onTokenClick/onTokenEnter/onTokenLeave callbacks.
- Click a token → toolbar opens with token text in header
- Click same token again → deselects
- Gutter line selection still works independently
- Token metadata (charStart, charEnd, tokenText) stored on CodeAnnotation
- Sidebar shows token badge, export includes token context
For provenance purposes, this commit was AI assisted.
* fix(review): token draft roundtrip, export precision, truncation alignment
- Persist tokenSelection in drafts so token context survives file switches
- Include char offsets in exported feedback for duplicate token disambiguation
- Escape backticks in token text to prevent broken markdown fences
- Align sidebar token truncation to 30 chars (matching toolbar header)
For provenance purposes, this commit was AI assisted.
* feat(review): add Codex AI review agent with live logs, --local worktree, and panel UI
Hook up Codex as the first AI review agent in the code review system:
- Spawn `codex exec` with Codex's native review prompt and output schema
- Parse structured findings (ReviewOutputEvent) and push as external annotations
- Annotations appear inline in the diff viewer pinned to specific lines
- Review verdict (correct/incorrect + confidence + explanation) displayed in panel
Agent job infrastructure enhancements:
- Server-side command building via `buildCommand` callback (providers don't need frontend commands)
- Result ingestion via `onJobComplete` callback (reads output file, transforms findings)
- `addAnnotations` method on external annotation handler (bypasses HTTP for server-internal producers)
- Live stderr streaming via `job:log` SSE events with 200ms buffer-and-flush
- `cwd` and `summary` fields on AgentJobInfo
PR review with --local worktree:
- `plannotator review <PR_URL> --local` creates a temp git worktree with the PR branch
- Agent gets full local file access without touching the user's working tree
- Hybrid server mode: both prMetadata (platform features) and gitContext (local access)
- Automatic worktree cleanup on session end
- Runtime-agnostic worktree primitives in packages/shared/worktree.ts
Panel UI redesign:
- Findings | Logs tab system with underline-style tabs
- LiveLogViewer component with auto-scroll, truncation, and copy
- Review verdict card (correct/incorrect with confidence and explanation)
- Pending state with labeled "Review Verdict — Pending..." (not skeleton bars)
- Job card click opens detail panel directly (removed separate icon button)
- Dismissed annotation tracking (deleted annotations persist as "dismissed" in panel)
- Copy all annotations as formatted markdown
- Worktree badge in header with info dialog showing path
- CopyButton extended with inline variant for reuse
- ConfirmDialog extended with wide option
For provenance purposes, this commit was AI assisted.
* style(review): UX polish pass — visual quality improvements across code review UI
- VerdictCard: remove AI-template left-border, use background-only tint
- Inline annotations: 6px radius, subtle shadow, hover elevation, action button scale
- File tree: tighter indentation (4 + depth*10), reduced container padding
- Select dropdowns: normalized to 4px border-radius matching pierre diffs
- Dockview tabs: close button pushed to far right with margin-left auto, visible at 0.25 opacity
- PR icons moved from sidebar to header (next to PR link)
- AnnotationRow: translate-x hover feedback
- Border-radius normalized to `rounded` (4px) across all components
- Type scale consolidated: text-[8px]/[9px] → text-[10px], text-[11px] → text-xs
- Sidebar tab hit targets increased (px-2.5 py-1.5, w-4 icons)
- Sticky file group headers in annotation sidebar
- FileTree controls collapsed (worktree + diff selectors share one row)
- Tab micro-animations (transition-all duration-150)
- ScrollFade component for gradient indicators on scrollable containers
- Prose containment: max-w-2xl + px-6 padding on PR Summary/Comments/Checks panels
- MarkdownBody: leading-relaxed for comfortable reading
- PR Comments: surface lift (bg-muted/10), hover feedback, author font-semibold
- PR Checks: link affordance (text-primary, underline on hover, external link icon)
For provenance purposes, this commit was AI assisted.
* feat(review): PR comments panel — search, filter, collapse, navigation, and polish
Comments panel enhancements:
- Search: real-time text filter across author and body, match count display
- Keyboard navigation: j/k to move between comments, scroll-to-selected
- Sort: toggle between oldest/newest first
- Collapsible comments: click header to collapse, collapse/expand all controls
- Author exclusion filter: click authors to hide their comments (not inclusion)
- Comment actions: hover-reveal "View on GitHub" link + copy button (bottom-right)
- Review URLs: PRReview type now includes optional url field, populated from GitHub API
PR Summary fixes:
- Label contrast: use theme foreground color for label text instead of raw GitHub hex
- Linked issues: replaced broken hardcoded SVG with proper GitHub Octicons issue-opened icon
Data plumbing:
- platformUser exposed through ReviewStateContext for "Mine" filtering
- Panel wrapper changed to overflow-hidden for sticky toolbar support
- "Commented" review badge hidden (noise — only show Approved/Changes Requested/Dismissed)
For provenance purposes, this commit was AI assisted.
* feat(review): inline review threads with outdated/resolved state and diff hunk previews
PR Review Threads:
- Fetch inline code review comments via GitHub GraphQL (reviewThreads query)
- PRReviewThread and PRThreadComment types with isResolved, isOutdated, path, line, diffSide
- ThreadCard component: file/line context, Outdated/Resolved badges, nested replies
- Resolved/outdated threads: gradient fade on body with "Show full comment" expand
- GitLab: reviewThreads placeholder (TODO: parse DiffNote positions from notes)
DiffHunkPreview:
- Renders diff hunks using @pierre/diffs FileDiff component (read-only, compact)
- Full theme integration: reads computed CSS vars, injects via unsafeCSS (same as main DiffViewer)
- Respects user font settings from ReviewState context
- Handles bare GitHub diffHunk format (prepends synthetic file headers for pierre parsing)
Comments Panel Polish:
- Comment cards: bg-card + subtle shadow for depth and isolation from panel background
- Hover: shadow elevation (0_2px_6px) for interactive feedback
- Thread cards: dimmed shadow for resolved/outdated, full shadow for active
- Prose padding: px-8 (32px) across all dockview panels (Summary, Comments, Checks, Findings)
For provenance purposes, this commit was AI assisted.
* feat(review): Claude Code agent, cross-repo --local, render fixes
Claude Code review agent:
- claude-review.ts: prompt (adapted from code-review plugin), command builder
(dontAsk + granular allowedTools/disallowedTools), JSONL stream output parser
- Prompt sent via stdin (not argv) to avoid quoting/variadic flag conflicts
- stream-json --verbose for live JSONL streaming + final structured_output
- Same schema as Codex — transformReviewFindings is now provider-agnostic
Agent jobs infrastructure:
- stdout capture (captureStdout option) for providers that return results on stdout
- stdin prompt writing (stdinPrompt option) for providers that read prompt from stdin
- cwd override in buildCommand return for providers without -C flag
- await stdoutDone before onJobComplete to prevent drain race condition
- job.prompt field for transparent prompt display in detail panel
Cross-repo --local:
- Detect same-repo vs cross-repo via parseRemoteUrl comparison
- Cross-repo: shallow clone via gh/glab repo clone (--depth 1 --no-checkout + targeted fetch)
- Cross-repo uses platform diff (gh pr diff) for display, clone for agent file access
- Same-repo: existing worktree path unchanged
- Cleanup: rmSync for clones, worktree remove for same-repo
Performance: jobLogs context split
- Separate JobLogsContext to prevent high-frequency log SSE from re-rendering all panels
- Only ReviewAgentJobDetailPanel subscribes to JobLogsProvider
- Standard React pattern: split contexts by update frequency
Image error handling:
- SafeHtmlBlock component wraps dangerouslySetInnerHTML with img onerror handlers
- Broken images (expired GitHub JWTs) hide on first 404 instead of flickering
- Prevents console 404 flood from re-render retry loops
For provenance purposes, this commit was AI assisted.
* fix(review): decontaminate --local from diff pipeline, fix worktree setup, default local for PRs
The --local flag was setting gitContext from the worktree, which contaminated
the diff rendering pipeline — causing pierre "trailing context mismatch" errors
because /api/file-content read worktree files instead of using the GitHub API.
Root cause: gitContext serves two purposes — diff pipeline (file contents, diff
switching, staging) and agent sandbox (cwd for agent processes). These are now
properly separated via a new agentCwd option on ReviewServerOptions.
Changes:
- Add agentCwd to ReviewServerOptions, independent of gitContext
- Agent handler (getCwd, buildCommand, onJobComplete) prefers agentCwd
- Stop setting gitContext in --local PR path — diff pipeline untouched
- Revert band-aid !isPRMode guards (no longer needed)
- Fix same-repo worktree: fetch origin/<baseBranch> so agents see correct diff
- Fix cross-repo clone: create local branch at baseSha for git diff accuracy
- Fix FETCH_HEAD ordering: fetch base branch before PR head (createWorktree needs PR tip)
- Fix macOS path mismatch: realpathSync(tmpdir()) so agent paths strip correctly
- Change buildCodexReviewUserMessage signature from GitContext to focused options
- Make --local the default for PR/MR reviews (--no-local to opt out)
- Pass agentCwd to client for worktree badge display
For provenance purposes, this commit was AI assisted.
* style(review): unify panel headers, responsive buttons, dockview polish
- Unify all panel headers at 33px via --panel-header-h CSS variable
- FileHeader now uses shared variable instead of hardcoded 30px
- Dockview tab bar height, font size, and padding aligned with sidebars
- FileTree header uses fixed height instead of padding-based sizing
- Consistent border opacity (border-border/50) across all panels
- Consistent font weight (font-semibold) on all header labels
- Remove dockview tab focus outline (::after pseudo-element)
- Dockview tab close button pushed to right edge
- Tab bar void area uses muted background
- Top app header compacted from h-12 to py-1
- Sidebar footer: copy button and diff stats side by side
- FeedbackButton responsive labels (Send/Post at md, full labels at lg)
- Move ReviewAgentsIcon to packages/ui for shared use
- Agent empty state uses shared ReviewAgentsIcon instead of hardcoded SVG
- Sidebar header label truncates when narrow (tabs never clip)
- Detail panel prompt disclosures get proper spacing
- React.memo on PR tab components (PRSummaryTab, PRCommentsTab)
- Inline onerror on img tags for broken GitHub image handling
For provenance purposes, this commit was AI assisted.
* fix: type assertion for Bun stdin FileSink
Bun's proc.stdin is typed as `number | FileSink` but we need to call
.write() and .end() on it. Cast to FileSink to satisfy tsc --noEmit.
For provenance purposes, this commit was AI assisted.
* fix(review): XSS in sanitizeHtml, git flag injection, cross-repo ref mismatch
Security:
- Remove `onerror` from DOMPurify ALLOWED_ATTR — was allowing arbitrary JS
execution via PR descriptions containing `<img onerror="...">`. Replace
with SafeHtml component that attaches error handlers via useEffect + ref.
- Add `--` end-of-options separator to git fetch and git branch calls to
prevent flag injection via crafted branch names from API responses.
Bug fix:
- Cross-repo clones now create both local branch AND remote-tracking ref
(`refs/remotes/origin/<baseBranch>`) at baseSha, so agents can use either
`git diff main...HEAD` or `git diff origin/main...HEAD`.
Polish:
- Add copy button to verdict card in agent detail panel
- Remove hover:translate-x animation from finding rows
- Reduce file tree indent per level, remove extra file offset
- Add pr-action endpoint logging for debugging submit failures
For provenance purposes, this commit was AI assisted.
* chore: upgrade @pierre/diffs from 1.1.0-beta.19 to ^1.1.12
The beta pin was needed for processFile() API (expandable diff context),
which shipped in 1.1.0 stable on March 14. We were 13 releases behind.
Notable fixes in the upgrade path:
- 1.1.5: Fix diffAcceptRejectHunk with partial FileDiffMetadata
- 1.1.6: Patch parsing fix for renames and dotfiles
- 1.1.8: Fix maxLineDiffLength regression
May resolve intermittent "trailing context mismatch" errors in diff rendering.
For provenance purposes, this commit was AI assisted.
* fix(review): remove shell provider, flag injection, Claude log formatting, copy UX
Security:
- Remove shell provider from agent capabilities (unauthenticated RCE vector)
- Move `--` before prRepo in `gh repo clone` to prevent flag injection
Features:
- Wire up formatClaudeLogEvent — Claude live logs now show readable text
instead of raw JSONL
- Sidebar annotations: copy + delete buttons appear on hover (no overlap)
- Agent finding rows: copy button on hover (progressive disclosure)
- Verdict card: copy button pushed to the right
- File tree: reduced indent per level, files aligned with folders
Infra:
- PR action endpoint logging for debugging submit failures
For provenance purposes, this commit was AI assisted.
* fix: validate repo identifier to prevent flag injection in gh repo clone
The `--` separator in `gh repo clone` separates gh args from git args,
not positional args from flags. Using `--` before prRepo would break
the git flags. Instead, validate that the repo identifier doesn't start
with `-` to prevent flag injection via crafted PR URLs.
For provenance purposes, this commit was AI assisted.
* feat(review): Claude-specific review model with severity, reasoning, and multi-agent prompt
Claude review agent now has its own schema, prompt, and transform — separate
from Codex's P0-P3 priority model. Each provider uses its natural review style.
Schema changes:
- Claude findings use severity (important/nit/pre_existing) instead of priority (0-3)
- Flat structure: file, line, end_line instead of nested code_location
- description (single field) instead of title + body
- reasoning field captures the validation chain per finding
- summary with counts instead of overall_correctness/confidence
Prompt: Converges the open-source Claude Code review prompt with the remote
review service model. 4 parallel agents (Bug+Regression at Opus, Security at
Opus, Code Quality at Sonnet, Guideline Compliance at Haiku), validation step,
deduplication, severity classification. CLAUDE.md and REVIEW.md awareness.
UI: Severity markers (colored dots) on finding rows. Collapsible reasoning
section via <details>. New optional severity/reasoning fields on CodeAnnotation
and the external annotation store — backward compatible, only set by Claude.
Transform: transformClaudeFindings normalizes Claude output into the shared
annotation format. Codex path (transformReviewFindings) is completely untouched.
For provenance purposes, this commit was AI assisted.
* fix: use bg-amber-500 for nit severity dot (bg-warning may not be defined)
For provenance purposes, this commit was AI assisted.
* fix: security hardening, debug cleanup, deduplication, Pi mirroring, findings UX
Security:
- Add -- separator to ensureObjectAvailable git fetch (worktree.ts)
- Validate baseBranch against path traversal (..) before git ref operations
- Use process.once('exit') instead of process.on for worktree cleanup
Debug:
- Gate debugLog behind PLANNOTATOR_DEBUG env var (no more unconditional writes)
- Remove PARSE_OUTPUT_RAW dump that logged full JSON output to disk
Deduplication:
- Extract toRelativePath to packages/server/path-utils.ts (was duplicated
in codex-review.ts and claude-review.ts)
Pi extension:
- Remove shell provider from capabilities
- Add buildCommand callback to AgentJobHandlerOptions
- POST handler calls buildCommand for server-side command synthesis
UI:
- Findings sorted by severity (important → nit → pre_existing)
- Severity legend under findings header (colored dots)
- Reasoning always visible (not collapsible) — fixes click navigation bug
where <details> captured click events and broke annotation linkage
- Full finding text shown (removed line-clamp-2 truncation)
- Sidebar annotation hover actions aligned to the right
- DiffHunkPreview: cancel requestAnimationFrame on unmount
For provenance purposes, this commit was AI assisted.
* fix: move toRelativePath import to top of claude-review.ts
For provenance purposes, this commit was AI assisted.
* fix: same-repo detection compares host, platform-aware comment links, remove design docs
- Same-repo detection now compares both owner/repo AND hostname from the
git remote URL against prMetadata.host. Prevents false positives on
GitHub Enterprise where different instances share org/repo names.
- "View on GitHub" label in PR comments tab now shows "View on GitLab"
for GitLab MR comments based on the comment URL.
- Remove internal design docs (PR_LOCAL_WORKTREE.md, AGENT_LIVE_LOGS.md)
that were development artifacts, not user-facing documentation.
For provenance purposes, this commit was AI assisted.
* fix(review): show severity markers and reasoning in inline diff annotations
The severity and reasoning fields from Claude findings were only visible in
the agent detail panel, not in the inline diff annotations. Now:
- DiffAnnotationMetadata carries severity and reasoning fields
- DiffViewer passes them through when mapping annotations
- InlineAnnotation renders colored severity dot and reasoning text
For provenance purposes, this commit was AI assisted.
* fix: prefix Claude findings text with [severity] tag
Findings now show as "[important] description", "[nit] description",
"[pre_existing] description" — consistent with Codex's [P0]/[P1] tags.
For provenance purposes, this commit was AI assisted.
* feat(pi): full agent review mirroring — stdin, stdout, live logs, result ingestion
Pi extension agent-jobs handler now mirrors the Bun server's full capabilities:
- stdin piping for Claude prompt delivery
- stdout capture for Claude JSONL stream parsing
- Live stderr streaming with 200ms buffer-and-flush for job:log events
- Claude JSONL formatting via vendored formatClaudeLogEvent
- onJobComplete callback for result parsing and annotation push
- Full buildCommand integration in POST handler
- jobOutputPaths tracking with cleanup on kill
Pi serverReview.ts now wires buildCommand and onJobComplete with the same
logic as the Bun review server — Codex and Claude commands are built
server-side, results are parsed and transformed into external annotations.
Runtime compatibility: replaced Bun.file/Bun.write in codex-review.ts with
node:fs/promises equivalents (writeFile, readFile, existsSync) that work on
both Bun and Node. Verified Bun build passes.
Vendoring: vendor.sh now copies codex-review.ts, claude-review.ts, and
path-utils.ts from packages/server/ with import path rewriting for the
generated/ layout.
Also: Review Prompt label, px-8 padding on agent detail header/tabs/logs.
For provenance purposes, this commit was AI assisted.
* fix: remove duplicate isPRMode declaration in Pi serverReview.ts
For provenance purposes, this commit was AI assisted.
* fix: include reasoning in all copy and feedback export paths
- exportReviewFeedback: appends **Reasoning:** after finding text
- Per-finding copy button: appends reasoning to copy text
- Sidebar annotation copy: appends reasoning to copy text
This ensures reasoning flows through Copy All, Send Feedback, and
individual copy actions — not just the visual rendering.
For provenance purposes, this commit was AI assisted.
* fix: six verified findings — navigation, dedup, cleanup, copy, diff match, Windows paths
1. openDiffFile: clicking a finding now navigates to the correct file
before selecting the annotation (was silently selecting in wrong file)
2. SEVERITY_STYLES: extracted to packages/ui/types.ts as shared constant,
imported in both ReviewAgentJobDetailPanel and InlineAnnotation
(was duplicated with per-render rebuild in InlineAnnotation)
3. killJob: added jobOutputPaths.delete calls to match Pi's version
(was leaking two strings per killed job)
4. CommentActions: replaced hand-rolled copy with CopyButton inline
variant (was reimplementing useState/clipboard/setTimeout pattern)
5. Branch mode prompt: changed from three-dot to two-dot to match
the UI's actual diff computation (agent was reviewing different diff)
6. toRelativePath: uses path.relative + forward-slash normalization
for Windows compatibility (was string prefix matching with / only)
For provenance purposes, this commit was AI assisted.
* perf: wrap ReviewSidebar in React.memo to prevent re-renders during log streaming
Every job:log SSE event triggers setJobLogs in useAgentJobs, which re-renders
App.tsx. Without memo, the sidebar re-renders on every event (~5/sec) even
though its props (agentJobs.jobs, capabilities, callbacks) haven't changed.
This caused visible flickering when a review tab was open during agent runs.
React.memo shallow-compares props — all sidebar props are stable references
(jobs array only changes on status events, callbacks are useCallback-wrapped),
so the sidebar correctly skips re-renders during log streaming.
For provenance purposes, this commit was AI assisted.
* fix(security): remove find/ls/cat from Claude allowed tools, add glab CLI
Security: Bash(find:*) allowed find -exec to spawn arbitrary subprocesses
that bypassed --disallowedTools. Removed find, ls, and cat — Claude has
Glob, Read, and Grep built-in which cover file access without shell exec.
Feature: Added glab mr view/diff/list and glab api to allowed tools so
Claude can inspect GitLab MR context in remote-mode reviews.
For provenance purposes, this commit was AI assisted.
* fix: Pi addAnnotations, Pi stdout drain, cross-repo exit codes
Pi extension:
- Add addAnnotations() to external-annotations.ts return object —
serverReview.ts calls it when agent jobs complete but the method
was missing (build/runtime error)
- Change proc.on('exit') to proc.on('close') in agent-jobs.ts —
Node's 'exit' fires before stdio streams drain, so stdoutBuf could
be incomplete when onJobComplete parses Claude's JSONL result
Cross-repo --local:
- Check git checkout FETCH_HEAD exit code — throw if it fails so the
outer catch falls back to remote-only with a clear warning
- Log warning if baseSha fetch fails (non-fatal, agents just can't
diff locally)
For provenance purposes, this commit was AI assisted.
* fix: FETCH_HEAD ordering, Pi worktree-aware cwd, SEVERITY_ORDER hoisted
Critical:
- Move ensureObjectAvailable before PR head fetch — it can overwrite
FETCH_HEAD if baseSha needs fetching, causing createWorktree to
check out the base commit instead of the PR head
- Pi serverReview.ts: extract resolveAgentCwd() helper used by getCwd,
buildCommand, and onJobComplete — was bypassing worktree-aware path
resolution, causing agents to run in wrong directory
Cleanup:
- Hoist SEVERITY_ORDER to module scope in ReviewAgentJobDetailPanel
(was recreated inside component body on every render)
For provenance purposes, this commit was AI assisted.
* fix: Bun/Pi parity — provider default, annotation error logging
- Bun agent-jobs: change provider default from "shell" to "" (shell was
removed from capabilities, default should match Pi)
- Pi serverReview: log errors from addAnnotations in onJobComplete
(Bun logs them, Pi was silently ignoring)
For provenance purposes, this commit was AI assisted.
* docs: add AI Code Review Agents guide with full prompt transparency
New docs page covering:
- Overview of Codex and Claude review agents
- How findings work (severity/priority, reasoning, navigation)
- Local worktree behavior (same-repo vs cross-repo)
- Full transparency section with:
- Claude multi-agent pipeline prompt (all 6 steps)
- Claude command and allowed/blocked tools
- Codex review prompt and command
- Both output schemas (Claude severity + Codex priority)
- Security notes (read-only, no network, local execution, no commenting)
- Customization via CLAUDE.md and REVIEW.md
For provenance purposes, this commit was AI assisted.
* docs: add provenance links for Claude and Codex review integrations
Credit Anthropic's Claude Code Review service, the open-source
code-review plugin, and OpenAI's Codex CLI as the foundations
for our review agent integrations.
For provenance purposes, this commit was AI assisted.
* fix: temp clone leak, j/k key conflict, thread header null line
- Cross-repo: clean up localPath in catch block when fetch/checkout
fails after clone succeeds (directory was leaking in /tmp)
- Remove j/k/arrow keyboard navigation from PR comments panel —
these shortcuts belong to the file tree only, both registering
global handlers caused double-navigation
- Thread header null guard: check thread.line before building range
label to prevent "L12–null" for outdated GitHub threads
For provenance purposes, this commit was AI assisted.
* fix: hoist localPath for catch-block scope, validate baseSha format
The previous rmSync(localPath) in the catch block was dead code —
const declarations inside try are not in scope in catch (separate
lexical environments per ECMAScript spec). The ReferenceError was
silently swallowed by the inner try/catch, so temp directories
still leaked on failed fetch/checkout.
Fix: hoist `let localPath` before the try block so it's accessible
in catch. Guard with `if (localPath)` since the error could occur
before assignment.
Also: validate baseSha is a hex SHA (40-64 chars) to prevent git
flag injection via crafted API responses. Validate baseBranch
rejects both '..' and '-' prefixes.
For provenance purposes, this commit was AI assisted.
* docs: rewrite AI Code Review guide for clarity and readability
Restructured for a technical audience: shorter paragraphs, cleaner
tables, removed em-dashes and filler prose, tightened the pipeline
diagram, streamlined security section into scannable single-line items.
For provenance purposes, this commit was AI assisted.
* docs: rewrite transparency section with exact prompts and commands
Replaced summarized/paraphrased transparency section with the actual
prompts, commands, schemas, and tool allowlists as they exist in the
code. One short security note at the top, then raw content.
For provenance purposes, this commit was AI assisted.
* docs: add mini TOC to transparency section
For provenance purposes, this commit was AI assisted.
* fix: stdout drain hang, Codex verdict override, Claude parse logging, memo removal
Critical:
- Race stdoutDone against 2s timeout after proc.exited — prevents
permanent job hang when Bun's ReadableStream doesn't close after
process exit. The process is dead; 2s is a cleanup deadline.
Bug fix:
- Codex verdict: override to "Issues Found" when P0/P1 findings exist,
regardless of the freeform overall_correctness string. Prevents green
"Correct" badge when Codex says "mostly correct but has issues."
P2/P3-only findings still trust Codex's verdict.
Observability:
- Log Claude parse failures with buffer size and last 200 bytes so we
can diagnose empty-findings cases.
Performance:
- Remove React.memo from ReviewSidebar — was blocking legitimate
re-renders (job status, findings) to prevent cosmetic log flickering.
The tradeoff was wrong.
Docs:
- Remove "shell" from CLAUDE.md capabilities table (provider was removed).
For provenance purposes, this commit was AI assisted.
* fix: type assertions for Bun ReadableStream async iteration
Bun's proc.stdout/stderr support for-await at runtime but TypeScript's
ReadableStream type doesn't declare [Symbol.asyncIterator]. Cast through
unknown to AsyncIterable<Uint8Array> — standard Bun workaround, same
pattern as the FileSink cast for stdin.
For provenance purposes, this commit was AI assisted.
OpenCode can pass annotate targets as @file references, so resolve markdown paths with an @ fallback only after the primary lookup misses. This preserves real @-prefixed filenames while making @README.md and quoted @ inputs resolve reliably.
* fix: handle markdown hard line breaks and list continuation lines
List items with indented continuation lines (no blank line separator) now
merge into the preceding bullet instead of becoming orphan paragraphs.
InlineMarkdown now converts two-trailing-space and backslash line breaks
into <br> elements. Synced to the diff view's InlineMarkdown copy.
Closes#482
For provenance purposes, this commit was AI assisted.
* fix: allow bold/italic to span across hard line breaks
Changed bold/italic regexes from .+? to [\s\S]+? so emphasis can match
across newlines (per CommonMark spec). Moved hard break check after all
^-anchored inline patterns so bold/italic get first crack, then the
recursive InlineMarkdown call inside <strong>/<em> handles the break.
For provenance purposes, this commit was AI assisted.
* feat(gemini): add Gemini CLI plan review integration
Adds a new `apps/gemini-hook/` adapter that enables Plannotator plan
review for Gemini CLI users via the BeforeTool hook system.
The adapter reads the plan file from disk (Gemini provides a path, not
inline content), delegates to the shared @plannotator/server for the
browser-based review UI, and translates the decision back into Gemini's
hook output format.
Requires an upstream fix (google-gemini/gemini-cli#21802) that makes
`decision = "allow"` user policies work for exit_plan_mode, allowing
hooks to replace the built-in TUI approval dialog.
Includes:
- apps/gemini-hook/server/index.ts — stdin/stdout adapter
- apps/gemini-hook/hooks/ — policy TOML + settings snippet
- scripts/install.sh — Gemini binary download, policy install, settings config
For provenance purposes, this commit was AI assisted.
* refactor(gemini): use single binary with auto-detection instead of separate app
Removes apps/gemini-hook/ — the plannotator binary now auto-detects
Gemini CLI from stdin (plan_path = file on disk) vs Claude Code
(plan = inline content) and branches input parsing + output formatting.
Config fixtures live in apps/gemini/ (policy TOML + settings snippet).
Install script gates on ~/.gemini existing so Claude-only users are
unaffected.
For provenance purposes, this commit was AI assisted.
* test(gemini): add manual sandbox script for Gemini CLI integration
Three modes:
- --simulate: pipes BeforeTool JSON to hook, tests approve/deny output
- (default): runs local patched Gemini build
- --nightly: installs Gemini nightly and runs it
Backs up and restores ~/.gemini config on exit.
For provenance purposes, this commit was AI assisted.
* feat(gemini): add slash commands, marketing tab, and docs for Gemini CLI
- Add /plannotator-review and /plannotator-annotate slash commands (.toml)
- Install Gemini slash commands in all three install scripts (sh, ps1, cmd)
- Add Gemini tab to marketing landing page with icon
- Add Gemini CLI to top-level README install section
- Create apps/gemini/README.md with full setup and usage docs
- Remove stale dev:gemini script and regenerate bun.lock
For provenance purposes, this commit was AI assisted.
* fix(gemini): merge hook into existing settings.json instead of printing instructions
When ~/.gemini/settings.json already exists, use node to JSON-merge
the BeforeTool hook config rather than asking the user to do it manually.
Falls back to instructions only if node is unavailable.
For provenance purposes, this commit was AI assisted.
* fix(gemini): handle plan_filename rename and fix scoping bug
Gemini CLI nightly renamed plan_path to plan_filename in exit_plan_mode.
Accept both field names for forward/backward compatibility. Reconstruct
full plan path from transcript_path + session_id + plans/ + filename.
Also hoist planFilename variable out of try block so it's accessible
in the deny output path (was causing ReferenceError).
For provenance purposes, this commit was AI assisted.
* fix(gemini): dim approve button when annotations exist for Gemini CLI
Gemini's hook runner ignores systemMessage on the allow path, so
approve-with-feedback is silently dropped — same limitation as Claude
Code. Extend the existing UI gate to also apply for gemini-cli origin.
For provenance purposes, this commit was AI assisted.
* fix(gemini): add AGENT_CONFIG entry and fix sandbox simulate mode
Register "gemini-cli" in AGENT_CONFIG so the UI shows "Gemini CLI"
with proper badge styling instead of generic "Coding Agent" fallback.
Update sandbox simulate mode to match production input format:
use plan_filename instead of plan_path, include transcript_path,
and simulate the Gemini directory structure for path reconstruction.
For provenance purposes, this commit was AI assisted.
* feat: add Perforce pending changelist diff support for code review
Introduce P4 support alongside existing Git backend via a VCS dispatch
layer (vcs.ts). Detects Git vs Perforce workspace automatically and
routes diff/file-content operations to the appropriate backend.
- Add p4-default and p4-changelist:<N> DiffType variants
- Add P4 runtime (p4.ts): workspace detection with TTL cache, changelist
context, unified diff conversion, binary file exclusion, batch p4 where
- Add VCS dispatch layer (vcs.ts): auto-detect Git/P4, unified API
- Update review server and CLI entry point to use VCS dispatch
- Filter empty changelists from dropdown, disable staging for P4
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* refactor: introduce VcsProvider interface for extensible VCS support
Replace hardcoded Git/P4 dispatch with a provider-based architecture.
Each VCS implements VcsProvider interface and registers in a providers
array — adding a new VCS only requires implementing the interface.
- Define VcsProvider with detect, ownsDiffType, getContext, runDiff,
getFileContents, and optional stageFile/unstageFile/resolveCwd
- Create gitProvider and p4Provider as concrete implementations
- Replace isP4DiffType/gitAddFile/gitResetFile in review.ts with
provider-based canStageFiles/stageFile/unstageFile/resolveVcsCwd
- Remove VCS-specific branching from review server endpoints
Note: GitContext interface is not renamed to VcsContext in this commit.
The rename touches too many files across the codebase (Pi extension,
OpenCode plugin, shared types, tests) and should be handled as a
separate pull request to keep the diff reviewable.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: rtsummit <rtsummit@abutton.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* add pi signal support
* remove PLAN
* fix: pass cwd through to getGitContext in openCodeReview
getGitContext() was called without the custom cwd override, so the
initial diff was correct but live diff switching, file content, git-add,
and branch labels in the review UI would resolve against process.cwd()
instead of the caller-provided cwd.
For provenance purposes, this commit was AI assisted.
---------
Co-authored-by: Michael Ramos <mdramos8@gmail.com>
When user clicks "Add suggested code" button in an annotation comment, the textarea is now pre-filled with the original selected code, allowing them to edit from there instead of typing from scratch. The cursor is positioned at the end of the prefilled text using requestAnimationFrame to ensure proper focus after state updates.
Prevent stacking dialogs by hiding the AnnotationToolbar when the SuggestionModal (expanded editor) is open, avoiding the original dialog from overlaying the fullpage dialog.
Commit 3ac3d5b swapped the touch area bias so side="right" extended 8px
leftward into the content area, covering the 6px scrollbar. Changed to
`left-0 -right-3` so the touch target has zero left encroachment and
extends entirely into the sidebar panel instead.
For provenance purposes, this commit was AI assisted.
* feat(vscode): prepare VS Code extension for marketplace publish
- Remove `private: true` to enable publishing
- Add homepage, galleryBanner, update category to AI, bump version
- Fix .vscodeignore monorepo leak (was packaging 548 files from parent workspace)
- Upgrade @vscode/vsce to ^3.7.1 (fixes .cjs entry point validation)
- Rewrite README for marketplace with CloudFront-hosted screenshots and GIF
- Replace 128x128 placeholder icon with proper 256x256 icon
- Add VS Code tab to marketing site hero section with marketplace link
- Add VS Code SVG icon to marketing assets
For provenance purposes, this commit was AI assisted.
* fix: clean up HeroSection linkEl reference and unused variable
For provenance purposes, this commit was AI assisted.
* fix(vscode): use absolute URL for README icon
Marketplace resolves relative paths against repo root, not the extension
subdirectory, causing a broken image.
For provenance purposes, this commit was AI assisted.
* feat(vscode): prepare VS Code extension for marketplace publish
- Remove `private: true` to enable publishing
- Add homepage, galleryBanner, update category to AI, bump version
- Fix .vscodeignore monorepo leak (was packaging 548 files from parent workspace)
- Upgrade @vscode/vsce to ^3.7.1 (fixes .cjs entry point validation)
- Rewrite README for marketplace with CloudFront-hosted screenshots and GIF
- Replace 128x128 placeholder icon with proper 256x256 icon
- Add VS Code tab to marketing site hero section with marketplace link
- Add VS Code SVG icon to marketing assets
For provenance purposes, this commit was AI assisted.
* fix: clean up HeroSection linkEl reference and unused variable
For provenance purposes, this commit was AI assisted.
* feat(skill): add Claude Code fallback to compound planning skill
Plannotator remains the first-class data source. When users don't have a
Plannotator archive, the skill now falls back to extracting ExitPlanMode
denial reasons from Claude Code JSONL transcripts via a bundled parser.
Adds Source Selection section, per-phase fallback notes, a progressive
disclosure reference (references/claude-code-fallback.md), and the
extraction script (scripts/extract_exit_plan_mode_outcomes.py).
For provenance purposes, this commit was AI assisted.
* fix(skill): remove duplicate detection logic and fix fallback skip
Phase 0 was duplicating the Source Selection branching and telling
fallback mode to skip Previous Report Detection. Now Phase 0 defers
to the already-chosen mode and both paths proceed to report detection.
For provenance purposes, this commit was AI assisted.
* blog: add Continuously Improve Claude Code Plans post
Introduces compound planning to users — how denial feedback compounds
into better future plans, works for both Plannotator and plain Claude
Code users. Video placeholder included for later replacement.
For provenance purposes, this commit was AI assisted.
* blog: revise compound planning post and adjust prose typography
Rework blog copy, add looping video embeds from CloudFront media
bucket, simplify process overview, add install link. Bump prose
font-size to 0.95rem and line-height to 1.6 on desktop.
For provenance purposes, this commit was AI assisted.
* blog: move intro video, copy tweaks, video spacing
For provenance purposes, this commit was AI assisted.
* feat(shared): add improvement hook reader utility
Adds a runtime-agnostic module for reading improvement hook files from
~/.plannotator/hooks/. Uses a hardcoded base path with an allowlist of
known hook files and a 50KB size cap to prevent runaway context injection.
Designed for cross-harness reuse (Claude Code, OpenCode, Pi, etc.).
For provenance purposes, this commit was AI assisted.
* feat(hook): wire up improve-context PreToolUse hook for EnterPlanMode
Adds a PreToolUse hook on EnterPlanMode that injects corrective planning
instructions into Claude's context at plan mode entry. The new
`plannotator improve-context` subcommand reads the improvement hook file
and returns additionalContext, or silently passes through if no file exists.
For provenance purposes, this commit was AI assisted.
* fix(skill): update compound skill improvement hook path
Moves the improvement hook file path from ~/.plannotator/compound/ to
~/.plannotator/hooks/compound/ to namespace hook-injectable files
separately from other plannotator data.
For provenance purposes, this commit was AI assisted.
* fix(shared): add legacy path fallback for improvement hook reader
Users who ran the compound skill before the path migration have their
improvement hook file at ~/.plannotator/compound/ instead of the new
~/.plannotator/hooks/compound/ path. Add a fallback that checks the
legacy path only when the new path is absent — if the new path exists
but is invalid (empty, oversized), no fallback occurs to prevent
resurrecting stale instructions.
Includes tests for new-path-wins, legacy-fallback, and
invalid-new-blocks-legacy scenarios.
For provenance purposes, this commit was AI assisted.
* feat(review): support GitHub Enterprise and fix self-hosted GitLab MR diffs
Add `host` field to GitHub PR types and update URL parsing to accept any
host with `/pull/` pattern, enabling GitHub Enterprise Server URLs like
`ghe.company.com/owner/repo/pull/123`. All 8 `gh` CLI functions now pass
`--hostname` (for `gh api`/`gh auth`) and `HOST/OWNER/REPO` (for `gh pr`)
when targeting non-github.com hosts.
Replace broken `glab mr diff --hostname` invocation (glab mr subcommands
don't support --hostname) with `glab api .../diffs` which does. Diffs are
now reconstructed from structured API response instead of heuristic parsing
of bare diff output.
Closes#348Closes#457
For provenance purposes, this commit was AI assisted.
* fix(review): remove destructive regex from GitLab paginated JSON parser
glab api --paginate already returns a single merged JSON array, so the
regex that replaced ][ with , was unnecessary and could corrupt diff
content containing array indexing patterns like arr[i][j].
For provenance purposes, this commit was AI assisted.
* feat(skill): incremental reports, Haiku/Sonnet agents, and improvement hook
Enhance the compound planning skill with three capabilities:
- Detect previous reports and offer incremental analysis (only new files since last report), with versioned output filenames (v2, v3, etc.)
- Use Haiku agents for extraction (faster, cheaper) and Sonnet for reduction, with two-stage reduce for large datasets
- Add Phase 6 improvement hook that writes corrective prompts to ~/.plannotator/compound/ for automatic injection into future planning sessions
For provenance purposes, this commit was AI assisted.
* refactor(skill): drop redundant annotation files, read only denied plans
Denied files already contain the full plan + reviewer feedback after a ---
separator. Annotation files are exact subsets of this content — reading both
double-counts feedback. Simplifies extraction to a single prompt type.
For provenance purposes, this commit was AI assisted.
* fix(skill): raise two-stage reduce threshold from 7 to 21 extraction files
Single-stage reduce is sufficient for most datasets. The previous threshold
of 7 caused unnecessary partial reduce + final synthesis overhead (~13 min
vs ~5-8 min single-stage) for typical archive sizes.
For provenance purposes, this commit was AI assisted.
Three new themes derived from Cursor's color palettes. Code Fork supports
both dark and light modes; Clean Contrast and Midnight are dark-only.
For provenance purposes, this commit was AI assisted.
git ls-files scopes to the CWD subtree and returns CWD-relative paths,
unlike git diff HEAD which covers the full repo with root-relative paths.
When the hook process inherits a subdirectory CWD, untracked files outside
that subtree are silently dropped and paths for files inside it are wrong.
Resolve the repo root via rev-parse --show-toplevel and use it as the CWD
for both git ls-files and git diff --no-index in getUntrackedFileDiffs.
Fixes#449
* feat(server): add agent job manager with process lifecycle and SSE streaming
Introduces the backend for agentic review — a server-agnostic job runner
that spawns agent processes, monitors their lifecycle via proc.exited, and
broadcasts status updates over a dedicated SSE stream.
New files:
- packages/shared/agent-jobs.ts: runtime-agnostic types, SSE helpers, state machine
- packages/server/agent-jobs.ts: Bun HTTP adapter with spawn/kill/SSE/REST routes
Wired into the review server with late-bound serverUrl, killAll on stop
and process exit for defense-in-depth cleanup. Capability detection via
Bun.which() for Claude Code, Codex CLI, and shell.
For provenance purposes, this commit was AI assisted.
* feat(ui): add Review Agents tab with job management and live status
Adds the client-side UI for agentic review:
- useAgentJobs hook: SSE primary with polling fallback, capabilities fetch
- AgentsTab: shared component with provider dropdown, job cards, kill controls
- ReviewAgentsIcon: magnifying glass with cog icon
- ReviewPanel: new "Review Agents" tab conditional on detected capabilities
- App.tsx: initializes hook and passes props to ReviewPanel
Jobs show live elapsed time, status badges, annotation counts per source,
and expandable error details. Stub command (sleep 10-30s) for initial testing.
For provenance purposes, this commit was AI assisted.
* fix(server): narrow proc.stderr type to satisfy TS
Bun types proc.stderr as ReadableStream | number. Add typeof guard
to narrow before passing to Response constructor.
For provenance purposes, this commit was AI assisted.
* fix(server): prevent stdout deadlock, stderr pipe stall, and worktree cwd mismatch
- Change stdout from "pipe" to "ignore" — agents post findings via the
annotations API, not stdout. Unconsumed pipe buffer caused deadlock.
- Drain stderr continuously instead of reading after exit — prevents
pipe-full stall on chatty agents.
- Make agent getCwd worktree-aware using the same currentDiffType check
the AI endpoints use, so agents spawn in the correct checkout.
- Exclude 'agents' tab from PR context fetch guard in ReviewPanel.
For provenance purposes, this commit was AI assisted.
* feat(pi): mirror agent-job endpoints in Pi review server
Add apps/pi-extension/server/agent-jobs.ts — a Node.js port of the Bun
agent-jobs handler using child_process.spawn, res.write() SSE, and
execFileSync for capability detection.
Wire into serverReview.ts: route delegation, killAll in stop(),
process.on("exit") guard, worktree-aware getCwd, and serverUrl
late-binding. Add agent-jobs to vendor.sh for shared type vendoring.
For provenance purposes, this commit was AI assisted.
* fix(agents): harden agent jobs — listener leak, provider allowlist, Windows support, docs
- Use process.once instead of process.on to prevent exit listener accumulation
- Validate provider against known capabilities before spawning (rejects unknown providers)
- Use platform-aware which/where for CLI detection on Windows
- Broadcast jobs:cleared event from kill-all endpoint (was dead client code)
- Document all /api/agents/* endpoints in CLAUDE.md Review Server table
For provenance purposes, this commit was AI assisted.
* fix(agents): SSE ref reset, jobs:cleared divergence, exit listener cleanup
- Reset receivedSnapshotRef/fallbackRef on re-mount so polling fallback
activates correctly on subsequent tab switches
- Remove jobs:cleared broadcast from kill-all — killAll() already fires
individual job:completed events, so the UI shows status transitions
instead of going blank
- Store exit handler ref so stop() can removeListener, preventing
accumulation in long-lived hosts (OpenCode, Pi)
For provenance purposes, this commit was AI assisted.
- Shared CountBadge component replacing heavy TOC accent circles
- Per-file annotation count badges in FileBrowser and VaultBrowser
- Folder aggregate counts from descendant files
- Summary header showing total annotations across files
- Dot indicators on Files/Vault sidebar tabs when annotations exist
- Adaptive back button text (file list / file / message / plan)
- Cross-file annotation indicator in right panel with flash highlight
- Fix directory prefix matching bug (startsWith without trailing slash)
- Move flash animation CSS to shared theme stylesheet
For provenance purposes, this commit was AI assisted.
Makes the CommentPopover and AnnotationToolbar draggable by their headers via a shared `useDraggable` hook. Users can reposition popovers that land awkwardly near viewport edges.
- New `useDraggable` hook reads rendered position via getBoundingClientRect on drag start
- 3px movement threshold prevents interfering with button clicks
- CommentPopover: suppresses scroll/resize tracking after drag, resets on anchor change
- AnnotationToolbar: both comment and Ask AI modes are draggable
- Clamps position to keep at least 50px visible on screen
For provenance purposes, this commit was AI assisted.
* feat(review): custom font family and size overrides for code review diffs
Add Code Font and Code Font Size settings to the review Display tab,
letting users override the theme's monospace font in the diff viewer.
Supports 9 fonts (Fira Code, Hack, IBM Plex Mono, Inconsolata,
JetBrains Mono, Red Hat Mono, Roboto Mono, Source Code Pro, Atkinson
Hyperlegible Mono) loaded on demand from Google Fonts / jsDelivr CDN.
Font size uses a continuous slider (8–24px) with a Reset button.
Settings persist via cookies and sync to ~/.plannotator/config.json
under diffOptions.fontFamily / diffOptions.fontSize, matching the
existing config pattern.
For provenance purposes, this commit was AI assisted.
* fix(review): line-height scaling, inline annotation font coverage, and comment card cleanup
- Add line-height: 1.5 alongside font-size in Pierre shadow DOM so large sizes don't clip
- Include .review-comment-body selectors in font override CSS so inline annotation code spans get the custom font
- Simplify comment card: remove drop shadow, left border accent, translateX hover; use tight border with subtle hover
For provenance purposes, this commit was AI assisted.
Remove writeRemoteShareLink stderr output from the OpenCode plugin —
the base64 share URL was flooding the TUI on remote sessions. Also
strip leftover console.log debug statements from the PR viewed files
feature in the review server.
Closes#435
For provenance purposes, this commit was AI assisted.
- CommentPopover: add width to position state type (was returned but not declared)
- Settings: add missing ObsidianSettings fields (filenameSeparator, autoSave, vaultBrowserEnabled)
- Settings: add missing planWidth to UIPreferences initializer
- Viewer: use React.ElementType for dynamic heading tag
- useLinkedDoc: use SidebarTab instead of string for sidebar.open
- useActiveSection: accept RefObject<HTMLElement | null> (React 19)
- useInputMethodSwitch: pass explicit undefined to useRef
- package.json: add exports for config, ImageAnnotator, sidebar/*, plan-diff/*
- types.d.ts: add __APP_VERSION__ global declaration
For provenance purposes, this commit was AI assisted.
Adds ?cb=<encoded_url>&ct=<token> URL params for bot-initiated plan review callbacks.
When a bot posts a Plannotator share link with these params, Approve/Feedback buttons
appear and POST the user's decision (with annotated plan URL) back to the bot.
Changes:
- callback.ts: parse callback config from URL search/hash params, execute POST
- ToolbarButtons.tsx: extract shared FeedbackButton/ApproveButton components (6 instances → 2 components)
- sharing.ts: strip ?cb=&ct= from hash before decompressing share payload
- App.tsx: callback buttons gated on isSharedSession + shareUrl readiness
- 19 tests covering config parsing, URL validation, presigned URL preservation, and POST execution
Co-authored-by: aviadshiber <aviadshiber@users.noreply.github.com>
For provenance purposes, this commit was AI assisted.
Single source of truth — edit AGENTS.md, both Claude Code and other
agents see the same instructions.
For provenance purposes, this commit was AI assisted.
Symlinked from ~/.claude/skills/ to the repo's .agents/skills/ directory
so changes are reflected instantly without copying.
For provenance purposes, this commit was AI assisted.
Michael Ramos