Problem:
The coding agent can implement in-memory storage (e.g., `dev-store.ts` with
`globalThis`) instead of a real database. These implementations pass all tests
because data persists during runtime, but data is lost on server restart.
This is a root cause for #68 - agent "passes" features that don't actually work.
Solution:
1. Add 5 mandatory Infrastructure Features (indices 0-4) that run first:
- Feature 0: Database connection established
- Feature 1: Database schema applied correctly
- Feature 2: Data persists across server restart (CRITICAL)
- Feature 3: No mock data patterns in codebase
- Feature 4: Backend API queries real database
2. Add STEP 5.7: Server Restart Persistence Test to coding prompt:
- Create test data, stop server, restart, verify data still exists
3. Extend grep patterns for mock detection in STEP 5.6:
- globalThis., devStore, dev-store, mockData, fakeData
- TODO.*real, STUB, MOCK, new Map() as data stores
Changes:
- .claude/templates/initializer_prompt.template.md - Infrastructure features
- .claude/templates/coding_prompt.template.md - STEP 5.6/5.7 enhancements
- .claude/commands/create-spec.md - Phase 3b database question
Backwards Compatible:
- Works with YOLO mode (uses bash/grep, not browser automation)
- Stateless apps can skip database features via create-spec question
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add multiple escape hatches to prevent users from getting stuck during
spec creation when the WebSocket completion signal fails.
Changes:
- Add "Exit to Project" button always visible in chat header
- Add /exit command detection to immediately exit to project
- Add backend GET /api/spec/status/{project} endpoint to poll status file
- Add getSpecStatus() API function in frontend
- Add status file polling (every 3s) in useSpecChat hook
- Update create-spec.md with status file write instructions
How it works:
1. Happy path: Claude writes .spec_status.json as final step, UI polls
and detects completion, shows "Continue to Project" button
2. Escape hatch: User can always click "Exit to Project" or type /exit
to instantly select the project and close modal, then manually start
the agent from the main UI
This ensures users always have a way forward even if the WebSocket
completion detection fails due to tool call tracking issues.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add a new YOLO (You Only Live Once) mode that skips all browser testing
and regression tests for faster feature iteration during prototyping.
Changes made:
**Core YOLO Mode Implementation:**
- Add --yolo CLI flag to autonomous_agent_demo.py
- Update agent.py to accept yolo_mode parameter and select appropriate prompt
- Modify client.py to conditionally include Playwright MCP server (excluded in YOLO mode)
- Add coding_prompt_yolo.template.md with static analysis only verification
- Add get_coding_prompt_yolo() to prompts.py
**Server/API Updates:**
- Add AgentStartRequest schema with yolo_mode field
- Update AgentStatus to include yolo_mode
- Modify process_manager.py to pass --yolo flag to subprocess
- Update agent router to accept yolo_mode in start request
**UI Updates:**
- Add YOLO toggle button (lightning bolt icon) in AgentControl
- Show YOLO mode indicator when agent is running in YOLO mode
- Add useAgentStatus hook to track current mode
- Update startAgent API to accept yoloMode parameter
- Add YOLO toggle in SpecCreationChat completion flow
**Spec Creation Improvements:**
- Fix create-spec.md to properly replace [FEATURE_COUNT] placeholder
- Add REQUIRED FEATURE COUNT section to initializer_prompt.template.md
- Fix spec_chat_session.py to create security settings file for Claude SDK
- Delete app_spec.txt before spec creation to allow fresh creation
**Documentation:**
- Add YOLO mode section to CLAUDE.md with usage examples
- Add checkpoint.md slash command for creating detailed commits
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
