215 Commits

  • perf(hooks): batch format+typecheck at Stop instead of per Edit (#746)
    * perf(hooks): batch format+typecheck at Stop instead of per Edit
    
    Fixes #735. The per-edit post:edit:format and post:edit:typecheck hooks
    ran synchronously after every Edit call, adding 15-30s of latency per
    file — up to 7.5 minutes for a 10-file refactor.
    
    New approach:
    - post-edit-accumulator.js (PostToolUse/Edit): lightweight hook that
      records each edited JS/TS path to a session-scoped temp file in
      os.tmpdir(). No formatters, no tsc — exits in microseconds.
    - stop-format-typecheck.js (Stop): reads the accumulator once per
      response, groups files by project root and runs the formatter in
      one batched invocation per root, then groups .ts/.tsx files by
      tsconfig dir and runs tsc once per tsconfig. Clears the accumulator
      immediately on read so repeated Stop calls don't double-process.
    
    For a 10-file refactor: was 10 × (15s + 30s) = 7.5 min overhead,
    now 1 × (batch format + batch tsc) = ~5-30s total.
    
    * fix(hooks): address race condition, spawn timeout, and Windows path guard
    
    Three issues raised in code review:
    
    1. Race condition: switched accumulator from non-atomic JSON
       read-modify-write to appendFileSync (one path per line). Concurrent
       Edit hook processes each append independently without clobbering each
       other. Deduplication moved to the Stop hook at read time.
    
    2. Effective timeout: added run() export to stop-format-typecheck.js so
       run-with-flags.js uses the direct require() path instead of falling
       through to spawnSync (which has a hardcoded 30s cap). The 120s
       timeout in hooks.json now governs the full batch as intended.
    
    3. Windows path guard: added spaces and parentheses to UNSAFE_PATH_CHARS
       so paths like "C:\Users\John Doe\project\file.ts" are caught before
       being passed to cmd.exe with shell: true.
    
    * fix(hooks): fix session fallback, stale comment, trim verbose comments
    
    - Replace 'default' session ID fallback with a cwd-based sha1 hash so
      concurrent sessions in different projects don't share the same
      accumulator file when CLAUDE_SESSION_ID is unset
    - Remove stale "JSON file" reference in accumulator header (format is
      now newline-delimited plain text)
    - Remove redundant/verbose inline comments throughout both files
    
    * fix(hooks): sanitize session ID, fix Windows tsc, proportional timeouts
    
    - Sanitize CLAUDE_SESSION_ID with /[^a-zA-Z0-9_-]/g before embedding in
      the temp filename so crafted separators or '..' sequences cannot escape
      os.tmpdir() (cubic P1)
    - Fix typecheckBatch on Windows: npx.cmd requires shell:true like
      formatBatch already does; use spawnSync and extract stdout/stderr from
      the result object (coderabbit P1)
    - Proportional per-batch timeouts: divide 270s budget across all format
      and typecheck batches so sequential runs in monorepos stay within the
      Stop hook wall-clock limit (greptile P2)
    - Raise Stop hook timeout from 120s to 300s to give large monorepos
      adequate headroom (cubic P2)
    
    * fix(hooks): extend accumulator to Write|MultiEdit, fix tests
    
    - Extend matcher from Edit to Edit|Write|MultiEdit so files created with
      Write and all files in a MultiEdit batch are included in the Stop-time
      format+typecheck pass (cubic P1)
    - Handle tool_input.edits[] array in accumulator for MultiEdit support
    - Rename misleading 'concurrent writes' test to clarify it tests append
      preservation, not true concurrency (cubic P2)
    - Add Stop hook dedup test: writes duplicate paths to accumulator and
      verifies the hook clears it cleanly (cubic P2)
    - Add Write and MultiEdit accumulation tests
    
    * fix(hooks): move timeout to command level, add dedup unit tests
    
    - Move timeout: 300 from the matcher object to the hook command object
      where it is actually enforced; the previous position was a no-op
      (cubic P2)
    - Extract parseAccumulator() and export it so tests can assert dedup
      behavior directly without relying only on side effects (cubic P2)
    - Add two unit tests for parseAccumulator: deduplication and blank-line
      handling; rename the integration test to match its scope
    
    * fix(hooks): replace removed format/typecheck hooks with accumulator in cursor adapter
  • feat(install): add CodeBuddy(Tencent) adaptation with installation scripts (#1038)
    * feat(install): add CodeBuddy(Tencent) adaptation with installation scripts
    
    * fix: add codebuddy to SUPPORTED_INSTALL_TARGETS
    
    * fix(codebuddy): resolve installer path issues, unused vars, and uninstall safety
  • feat: add GAN-style generator-evaluator harness (#1029)
    Implements Anthropic's March 2026 harness design pattern — a multi-agent
    architecture that separates generation from evaluation, creating an
    adversarial feedback loop that produces production-quality applications.
    
    Components:
    - 3 agent definitions (planner, generator, evaluator)
    - 1 skill with full documentation (skills/gan-style-harness/)
    - 2 commands (gan-build for full apps, gan-design for frontend)
    - 1 shell orchestrator (scripts/gan-harness.sh)
    - Examples and configuration reference
    
    Based on: https://www.anthropic.com/engineering/harness-design-long-running-apps
    
    Co-authored-by: Hao Chen <haochen806@gmail.com>
  • fix: filter session-start injection by cwd/project to prevent cross-project contamination (#1054)
    * fix: filter session-start injection by cwd/project to prevent cross-project contamination
    
    The SessionStart hook previously selected the most recent session file
    purely by timestamp, ignoring the current working directory. This caused
    Claude to receive a previous project's session context when switching
    between projects, leading to incorrect file reads and project analysis.
    
    session-end.js already writes **Project:** and **Worktree:** header
    fields into each session file. This commit adds selectMatchingSession()
    which uses those fields with the following priority:
    
    1. Exact worktree (cwd) match — most recent
    2. Same project name match — most recent
    3. Fallback to overall most recent (preserves backward compatibility)
    
    No new dependencies. Gracefully falls back to original behavior when
    no matching session exists.
    
    * fix: address review feedback — eliminate duplicate I/O, add null guards, improve docstrings
    
    - Return { session, content, matchReason } from selectMatchingSession()
      to avoid reading the same file twice (coderabbitai, greptile P2)
    - Add empty array guard: return null when sessions.length === 0 (coderabbitai)
    - Stop mutating input objects — no more session._matchReason (coderabbitai)
    - Add null check on result before accessing properties (coderabbitai)
    - Only log "selected" after confirming content is readable (cubic-dev-ai P3)
    - Add full JSDoc with @param/@returns (docstring coverage)
    
    * fix: track fallback session object to prevent session/content mismatch
    
    When sessions[0] is unreadable, fallbackContent came from a later
    session (e.g. sessions[1]) while the returned session object still
    pointed to sessions[0]. This caused misleading logs and injected
    content from the wrong session — the exact problem this PR fixes.
    
    Now tracks fallbackSession alongside fallbackContent so the returned
    pair is always consistent.
    
    Addresses greptile-apps P1 review feedback.
    
    * fix: normalize worktree paths to handle symlinks and case differences
    
    On macOS /var is a symlink to /private/var, and on Windows paths may
    differ in casing (C:\repo vs c:\repo). Use fs.realpathSync() to
    resolve both sides before comparison so worktree matching is reliable
    across symlinked and case-insensitive filesystems.
    
    cwd is normalized once outside the loop to avoid repeated syscalls.
    
    Addresses coderabbitai Major review feedback.
    
    ---------
    
    Co-authored-by: kuqili <kuqili@tencent.com>
  • fix: extract inline SessionStart bootstrap to separate file (#1035)
    Inline `node -e "..."` in hooks.json contained `!` characters (e.g.
    `!org.isDirectory()`) that bash history expansion in certain shell
    environments would misinterpret, producing syntax errors and the
    "SessionStart:startup hook error" banner in the Claude Code CLI header.
    
    Extract the bootstrap logic to `scripts/hooks/session-start-bootstrap.js`
    so the shell never sees the JS source. Behaviour is identical: the script
    reads stdin, resolves the ECC plugin root via CLAUDE_PLUGIN_ROOT or a set
    of well-known fallback paths, then delegates to run-with-flags.js.
    
    Update the test that asserted the old inline pattern to verify the new
    file-based approach instead.
    
    Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
  • fix(hooks): pass phase argument from hook ID to observe.sh (#1042)
    The shell wrapper run-with-flags-shell.sh was not extracting the phase
    prefix from the hook ID (e.g., "pre:observe" -> "pre") and passing it
    as $1 to the invoked script. This caused observe.sh to always default
    to "post", recording all observations as tool_complete events with no
    tool_start events captured.
    
    Fixes #1018
    
    Co-authored-by: Millectable <noreply@github.com>
    Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
  • fix: CI fixes, security audit, remotion skill, lead-intelligence, npm audit (#1039)
    * fix(ci): resolve cross-platform test failures
    
    - Sanity check script (check-codex-global-state.sh) now falls back to
      grep -E when ripgrep is not available, fixing the codex-hooks sync
      test on all CI platforms. Patterns converted to POSIX ERE for
      portability.
    - Unicode safety test accepts both / and \ path separators so the
      executable-file assertion passes on Windows.
    - Gacha test sets PYTHONUTF8=1 so Python uses UTF-8 stdout encoding on
      Windows instead of cp1252, preventing UnicodeEncodeError on box-drawing
      characters.
    - Quoted-hook-path test skipped on Windows where NTFS disallows
      double-quote characters in filenames.
    
    * feat: port remotion-video-creation skill (29 rules), restore missing files
    
    New skill:
    - remotion-video-creation: 29 domain-specific Remotion rules covering 3D/Three.js,
      animations, audio, captions, charts, compositions, fonts, GIFs, Lottie,
      measuring, sequencing, tailwind, text animations, timing, transitions,
      trimming, and video embedding. Ported from personal skills.
    
    Restored:
    - autonomous-agent-harness/SKILL.md (was in commit but missing from worktree)
    - lead-intelligence/ (full directory restored from branch commit)
    
    Updated:
    - manifests/install-modules.json: added remotion-video-creation to media-generation
    - README.md + AGENTS.md: synced counts to 139 skills
    
    Catalog validates: 30 agents, 60 commands, 139 skills.
    
    * fix(security): pin MCP server versions, add dependabot, pin github-script SHA
    
    Critical:
    - Pin all npx -y MCP server packages to specific versions in .mcp.json
      to prevent supply chain attacks via version hijacking:
      - @modelcontextprotocol/server-github@2025.4.8
      - @modelcontextprotocol/server-memory@2026.1.26
      - @modelcontextprotocol/server-sequential-thinking@2025.12.18
      - @playwright/mcp@0.0.69 (was 0.0.68)
    
    Medium:
    - Add .github/dependabot.yml for weekly npm + github-actions updates
      with grouped minor/patch PRs
    - Pin actions/github-script to SHA (was @v7 tag, now pinned to commit)
    
    * feat: add social-graph-ranker skill — weighted network proximity scoring
    
    New skill: social-graph-ranker
    - Weighted social graph traversal with exponential decay across hops
    - Bridge Score: B(m) = Σ w(t) · λ^(d(m,t)-1) ranks mutuals by target proximity
    - Extended Score incorporates 2nd-order network (mutual-of-mutual connections)
    - Final ranking includes engagement bonus for responsive connections
    - Runs in parallel with lead-intelligence skill for combined warm+cold outreach
    - Supports X API + LinkedIn CSV for graph harvesting
    - Outputs tiered action list: warm intros, direct outreach, network gap analysis
    
    Added to business-content install module. Catalog validates: 30/60/140.
    
    * fix(security): npm audit fix — resolve all dependency vulnerabilities
    
    Applied npm audit fix --force to resolve:
    - minimatch ReDoS (3 vulnerabilities, HIGH)
    - smol-toml DoS (MODERATE)
    - brace-expansion memory exhaustion (MODERATE)
    - markdownlint-cli upgraded from 0.47.0 to 0.48.0
    
    npm audit now reports 0 vulnerabilities.
    
    * fix: resolve markdown lint and yarn lockfile sync
    
    - MD047: ensure single trailing newline on all remotion rule files
    - MD012: remove consecutive blank lines in lottie, measuring-dom-nodes, trimming
    - MD034: wrap bare URLs in angle brackets (tailwind, transcribe-captions)
    - yarn.lock: regenerated to sync with npm audit changes in package.json
    
    * fix: replace unicode arrows in lead-intelligence (CI unicode safety check)
  • feat(hooks): add WSL desktop notification support via PowerShell + BurntToast (#1019)
    * fix(hooks): add WSL desktop notification support via PowerShell + BurntToast
    
    Adds WSL (Windows Subsystem for Linux) desktop notification support to the
    existing desktop-notify hook. The hook now detects WSL, finds available
    PowerShell (7 or Windows PowerShell), checks for BurntToast module, and
    sends Windows toast notifications.
    
    New functions:
    - isWSL(): detects WSL environment
    - findPowerShell(): finds PowerShell 7 or Windows PowerShell on WSL
    - isBurntToastAvailable(): checks if BurntToast module is installed
    - notifyWindows(): sends Windows toast notification via BurntToast
    
    If BurntToast is not installed, logs helpful tip for installation.
    Falls back silently on non-WSL/non-macOS platforms.
    
    * docs(hooks): update desktop-notify description to include WSL
    
    Updates the hook description in hooks.json to reflect the newly
    added WSL notification support alongside macOS.
    
    * fix(hooks): capture stderr properly in notifyWindows
    
    Change stdio to ['ignore', 'pipe', 'pipe'] so stderr is captured
    and can be logged on errors. Without this, result.stderr is null
    and error logs show 'undefined' instead of the actual error.
    
    * fix(hooks): quote PowerShell path in install tip for shell safety
    
    The PowerShell path contains spaces and needs to be quoted
    when displayed as a copy-pasteable command.
    
    * fix(hooks): remove external repo URL from tip message
    
    BurntToast module is a well-known Microsoft module but per project
    policy avoiding unvetted external links in user-facing output.
    
    * fix(hooks): probe WSL interop PATH before hardcoded paths
    
    Adds 'pwsh.exe' and 'powershell.exe' as candidates to leverage
    WSL's Windows interop PATH resolution, making the hook work with
    non-default WSL mount prefixes or Windows drives.
    
    * perf(hooks): memoize isWSL detection at module load
    
    Avoids reading /proc/version twice (once in run(), once in findPowerShell())
    by computing the result once when the module loads.
    
    * perf(hooks): reduce PowerShell spawns from 3 to 1 per notification
    
    Merge findPowerShell version check and isBurntToastAvailable check
    into a single notifyWindows call. Now just tries to send directly;
    if it fails, tries next PowerShell path. Version field was unused.
    
    Net effect: up to 3 spawns reduced to 1 in the happy path.
    
    * fix(hooks): remove duplicate notifyWindows declaration
    
    There were two notifyWindows function declarations due to incomplete
    refactoring. Keeps only the version that returns true/false for the
    call site. Node.js would throw SyntaxError with 'use strict'.
    
    * fix(hooks): improve error handling and detection robustness
    
    - Increase PowerShell detection timeout from 1s to 3s to avoid false
      negatives on slower/cold WSL interop startup
    - Return error reason from notifyWindows to distinguish BurntToast
      module not found vs other PowerShell errors
    - Log actionable error details instead of always showing install tip
    
    ---------
    
    Co-authored-by: boss <boss@example.com>
  • fix: harden codex sync CI hermeticity (#1020)
    * test: isolate package-manager dependent hooks and formatter tests
    
    * fix: export codex sync env to child scripts
  • fix: audit consumer projects from cwd (#1014)
    * fix: audit consumer projects from cwd
    
    * fix: unblock unicode safety CI lint
    
    * fix: unblock shared CI regressions
    
    * test: isolate package-manager dependent hooks and formatter tests
  • fix: unblock unicode safety CI lint (#1017)
    * fix: unblock unicode safety CI lint
    
    * fix: unblock shared CI regressions
  • fix: skip pre-push checks on branch deletion
    The pre-push hook runs lint/typecheck/test/build checks on every push,
    including `git push origin --delete <branch>`. Branch deletion does not
    push any code, so verification checks are unnecessary and block the
    delete operation.
    
    Detect deletion pushes by reading stdin (local sha is all zeros for
    deletes) and exit early.
    
    Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
  • Merge pull request #926 from xingzihai/feature/pre-commit-quality-hook
    feat(hooks): add pre-commit quality check hook
  • fix(lint): prefix unused options parameter with underscore
    Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
    
    Signed-off-by: Lidang-Jiang <lidangjiang@gmail.com>
  • refactor: address reviewer feedback
    - Add options={} parameter to run() to match run-with-flags.js contract
    - Remove case-insensitive flag from extension pre-filter for consistency
      with ADHOC_FILENAMES regex (both now case-sensitive)
    - Expand warning text to list more structured paths
    - Add test cases for uppercase extensions (TODO.MD, NOTES.TXT)
    
    Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
    
    Signed-off-by: Lidang-Jiang <lidangjiang@gmail.com>
  • fix(hooks): port doc-file-warning denylist policy to current hook runtime
    Replace the broad allowlist approach with a targeted denylist that only
    warns on known ad-hoc filenames (NOTES, TODO, SCRATCH, TEMP, DRAFT,
    BRAINSTORM, SPIKE, DEBUG, WIP) outside structured directories. This
    eliminates false positives for legitimate markdown-heavy workflows while
    still catching impulse documentation files.
    
    Closes #988
    
    Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
    
    Signed-off-by: Lidang-Jiang <lidangjiang@gmail.com>
  • Merge pull request #892 from chris-yyau/fix/remove-redundant-skill-sync
    fix: remove redundant skill copy from sync-ecc-to-codex.sh
  • Merge pull request #964 from affaan-m/fix/claude-hooks-settings-merge-safe
    fix(installer): preserve existing Claude hook settings
  • Merge pull request #974 from Lidang-Jiang/fix/codex-sanity-check-persistent-instructions
    fix(codex): add persistent_instructions to baseline and relax sanity check
  • Merge pull request #971 from Lidang-Jiang/fix/codex-mcp-startup-timeout
    fix(codex): add startup_timeout_sec to MCP servers to prevent first-run timeouts
  • fix(installer): write error and help text to stderr for consistent stream output
    Extracted help text into getHelpText() and write both the error message
    and usage help to stderr via process.stderr.write(). This ensures that
    when output is redirected (e.g. 2>errors.txt), both the error and the
    guidance appear in the same stream.
    
    Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
  • fix(installer): show help text on error and document --profile full in README
    Running install.ps1/install.sh with no arguments gave a cryptic error
    with no guidance. Now the usage help is printed after the error so users
    know what arguments to pass.
    
    Also added --profile full as the recommended install option in the README
    quick-start section, which was previously undocumented.
    
    Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
  • fix(codex): align context7-mcp package specifier with config.toml
    Add @latest suffix to '@upstash/context7-mcp' in ECC_SERVERS so the
    generated merge spec matches .codex/config.toml exactly, preventing
    configDiffers from flagging false drift on --update-mcp runs.
    
    Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
    
    Signed-off-by: Lidang-Jiang <lidangjiang@gmail.com>
  • fix(codex): allow leading whitespace in persistent_instructions regex
    The rg pattern anchored at line start (^persistent_instructions) would
    miss indented TOML entries. Use ^\s* prefix to match both top-level and
    indented configurations.
    
    Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
    
    Signed-off-by: Lidang-Jiang <lidangjiang@gmail.com>
  • fix(scripts): add os.homedir() fallback for Windows compatibility
    On Windows (native cmd/PowerShell), process.env.HOME is undefined.
    Seven CLI entry points and two library files pass process.env.HOME
    directly as homeDir without a cross-platform fallback, causing all
    path resolutions to silently fail (resolving to "undefined/.claude/...").
    
    Node.js os.homedir() correctly handles all platforms (HOME on Unix,
    USERPROFILE on Windows, OS-level fallback). The project already uses
    this pattern in scripts/lib/state-store/index.js and has a getHomeDir()
    utility in scripts/lib/utils.js, but it was not applied consistently.
    
    Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
    
    Signed-off-by: Lidang-Jiang <lidangjiang@gmail.com>