Commit Graph

6 Commits

Author SHA1 Message Date
ajmallesh dcae34af81 fix: enable Playwright MCP browser automation in Docker containers
Resolves Playwright browser installation failures in Docker by using Wolfi's
system Chromium instead of downloading Playwright's bundled browsers at runtime.

## Problem
When running in Docker, agents attempted to install browsers via `browser_install`
tool, which failed due to:
- Permission issues (non-root user couldn't install system dependencies)
- npx @playwright/mcp spawns with its own Playwright dependency separate from
  global installations
- Playwright's bundled browsers require runtime download (~280MB) and glibc deps
- Environment variables alone (PLAYWRIGHT_BROWSERS_PATH) weren't sufficient

## Solution
**Dockerfile changes:**
- Use Wolfi's native `chromium` package (guaranteed compatible, already installed)
- Remove Playwright browser installation step (saves ~280MB and build time)
- Add explicit `SHANNON_DOCKER=true` environment variable for reliable detection
- Set PLAYWRIGHT_CHROMIUM_EXECUTABLE_PATH to point to system Chromium

**Code changes (claude-executor.js):**
- Detect Docker via `process.env.SHANNON_DOCKER` (more reliable than /.dockerenv)
- Conditionally add `--executable-path /usr/bin/chromium-browser` CLI arg for Docker
- Local: Use Playwright's bundled browsers (downloaded to ~/Library/Caches/)
- Docker: Use system Chromium with no runtime downloads

## Research Findings
- @playwright/mcp has separate playwright-core dependency (v1.56.0-alpha)
- MCP server spawned via npx doesn't inherit browser binaries from global install
- --executable-path CLI argument is required (env vars insufficient)
- /.dockerenv file is unreliable (missing in BuildKit, K8s, can be spoofed)

## Testing
 Docker: All 5 parallel agents successfully navigate, screenshot, create deliverables
 Local: All 5 parallel agents successfully navigate, screenshot, create deliverables
 No browser_install calls, no permission errors
 Image size reduced by ~280MB

Fixes #docker-playwright-browser-issues

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-10-23 17:56:19 -07:00
ajmallesh d372f87297 refactor: remove ~500 lines of dead code and consolidate duplicates
Comprehensive codebase cleanup based on parallel agent analysis and automated
dead code detection (knip, depcheck). Reduces codebase by ~10% with zero
functional changes.

## Phase 1: Obsolete MCP Setup Removal (~82 lines)
- Delete setupMCP() and cleanupMCP() functions from environment.js
- Remove all calls to cleanupMCP() (8 instances across 3 files)
- Migrate from claude CLI to SDK's mcpServers option
- Remove --log flag (obsolete logging system)

## Phase 2: Dead Code Removal (~317 lines)
- Delete src/utils/logger.js entirely (127 lines, superseded by audit system)
- Remove handleConfigError() and handleError() from error-handling.js
- Remove isToolAvailable() from tool-checker.js
- Remove 5 dead methods from audit-session.js (logSessionFailure, logMessage,
  markRolledBack, updateValidation, getValidation)
- Remove 6 wrapper methods from audit/logger.js (all callers use logEvent directly)
- Remove formatCost(), updateMessage(), compose() utilities (unused)

## Phase 3: Consolidation (~195 lines)
- Extract SessionMutex to src/utils/concurrency.js (was duplicated in 2 files)
- Consolidate formatDuration to src/audit/utils.js (was in 3 files)
- Extract readline prompts to src/cli/prompts.js (was duplicated in 2 files)
- Create validator factories in constants.js (reduce 72 lines to 30)

## Impact
- Total reduction: 488 lines (20 files modified, 2 created, 1 deleted)
- Codebase: ~4,900 → ~4,400 LOC (10% reduction)
- Zero functional changes, all tests pass
- Improved maintainability and DRY compliance

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-10-23 17:01:17 -07:00
ajmallesh 55716963da feat: migrate to use MCP tools instead of helper scripts 2025-10-23 11:56:47 -07:00
ajmallesh 3babf02d68 feat: implement unified audit system v3.0 with crash-safety and self-healing
## Unified Audit System (v3.0)
- Implemented crash-safe, append-only logging to audit-logs/{hostname}_{sessionId}/
- Added session.json with comprehensive metrics (timing, cost, attempts)
- Agent execution logs with turn-by-turn detail
- Prompt snapshots saved to audit-logs/.../prompts/{agent}.md
- SessionMutex prevents race conditions during parallel execution
- Self-healing reconciliation before every CLI command

## Session Metadata Standardization
- Fixed critical bug: standardized on 'id' field (not 'sessionId') throughout codebase
- Updated: shannon.mjs (recon, report), src/phases/pre-recon.js
- Added validation in AuditSession to fail fast on incorrect field usage
- JavaScript shorthand syntax was causing wrong field names

## Schema Improvements
- session.json: Added cost_usd per phase, removed redundant final_cost_usd
- Renamed 'percentage' -> 'duration_percentage' for clarity
- Simplified agent metrics to single total_cost_usd field
- Removed unused validation object from schema

## Legacy System Removal
- Removed savePromptSnapshot() - prompts now only saved by audit system
- Removed target repo pollution (prompt-snapshots/ no longer created)
- Single source of truth: audit-logs/{hostname}_{sessionId}/prompts/

## Export Script Simplification
- Removed JSON export mode (session.json already exists)
- CSV-only export with clean columns: agent, phase, status, attempts, duration_ms, cost_usd
- Tested on real session data

## Documentation
- Updated CLAUDE.md with audit system architecture
- Added .gitignore entry for audit-logs/

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-10-22 16:09:08 -07:00
ajmallesh de8c5ee041 chore: upgrade model from Sonnet 4 -> Sonnet 4.5 2025-10-21 16:34:56 -07:00
ajmallesh 9327630c45 Initial commit 2025-10-03 19:35:08 -07:00