- Test _handle_use_project updates user context
- Test success card when project exists
- Test error card with Create button when project doesn't exist
- Test handle_message routes use command
- Test empty project name returns error
- Test subsequent commands use project from user context
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add UserContextManager for per-user project tracking
- Add _handle_new_project method that pre-creates sessions
- Update user context after new-project creation
- Route new-project command in handle_message
- Add LONG_COMMANDS class attribute for timeout control
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Test Orchestrator initializes with UserContextManager
- Test _handle_new_project creates session before executing
- Test _handle_new_project updates user context
- Test _handle_new_project executes command in session
- Test _handle_new_project returns success card
- Test handle_message routes new-project command
- Test empty project name returns error
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add Orchestrator to __init__.py exports
- Update SKILL.md with "How It Works" section explaining orchestrator.py entry point
- Document command routing and approval workflow
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add Orchestrator class with handle_message() and handle_callback() entry points
- Command parsing via regex: /gsd:* pattern extraction
- Auto-session-creation per CONTEXT.md decision
- Error handling with try/except returning format_error() cards
- Approval detection integration with ApprovalHandler
- Output truncation to 2000 chars for Feishu card limits
- 18 tests passing with full coverage
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Test orchestrator initialization with dependencies
- Test command parsing for /gsd:* pattern extraction
- Test handle_message routing (session creation, command execution, error handling)
- Test handle_callback routing for approval workflow
- Add integration-style tests for full flows
18 tests total covering all orchestrator functionality.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Created 03-02-SUMMARY.md with:
- Approval workflow with confirm/reject card buttons
- Progress monitoring with 60-second throttled updates
- 15 tests across approval and progress modules
- Updated STATE.md with decisions and metrics
- Updated ROADMAP.md with plan progress
- Marked BRDG-04, BRDG-05 requirements complete
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add ProgressInfo dataclass for progress data
- Add ProgressMonitor class with:
- PROGRESS_PATTERNS for extraction (percentage, fraction, phase, completion)
- extract_progress() to find progress indicators in output
- should_send_update() with 60 second throttling
- create_progress_card() for Feishu card formatting
- Fix fraction pattern to allow content after fraction (e.g., [3/5 tasks])
- Fix should_send_update() to return False on first call
- Fix test assertions to use kwargs instead of positional args
All 7 tests pass for progress monitoring.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add ApprovalState dataclass for approval workflow state
- Add ApprovalHandler class with:
- APPROVAL_PATTERNS for detection (AskUserQuestion, ExitPlanMode, 需要确认, Please confirm)
- detect_approval_request() to find approval requests in output
- create_approval_card() with confirm/reject buttons using CardButton
- handle_callback() to process approval actions
- In-memory pending_approvals cache
- Fix test assertions to use kwargs instead of positional args
All 8 tests pass for approval handling.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add CommandResult, OutputCapture, and CommandExecutor to __init__.py
exports for public API access.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add CommandResult dataclass for storing execution results
- Add OutputCapture class with prompt detection and stabilization
- Add CommandExecutor class for command execution and error detection
- Support common shell prompts ($, ❯, ➜, >)
- Detect errors in both English and Chinese
- Use 60s default timeout from CONTEXT.md decision
- Mock-based testing (no real tmux required)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Test OutputCapture._is_prompt for prompt pattern detection
- Test OutputCapture.capture_until_complete for output capture
- Test CommandExecutor._detect_errors for error keyword detection
- Test CommandExecutor.execute for full command execution flow
- Test CommandResult dataclass for result storage
- Test CommandExecutor.send_command for pane interaction
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Created 02-02-SUMMARY.md with plan execution details
- Updated STATE.md with Phase 2 decisions
- Updated ROADMAP.md with Phase 2 completion
- All 6 tests pass for FeishuResponseFormatter
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- format_success() creates card with green theme
- format_error() creates card with red theme
- format_info() creates card with blue theme
- format_paginated() adds [N/M] marker
- _build_card() creates three-zone structure (header/elements/actions)
- _build_actions() creates interactive button elements
All 6 tests pass. Card JSON uses schema 2.0 with lark_md content.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Test SKILL.md file exists at skill/SKILL.md
- Test SKILL.md has valid YAML frontmatter
- Test SKILL.md has name field
- Test SKILL.md has description field
- Test description contains /gsd: trigger pattern
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- CardTheme enum with SUCCESS (green), ERROR (red), INFO (blue), WARNING (orange)
- CardButton dataclass with text, value dict, and button_type
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Test format_success returns valid card with green theme
- Test format_error returns red theme
- Test format_info returns blue theme
- Test format with buttons includes actions element
- Test format_paginated adds [N/M] marker
- Test card has required structure (schema 2.0, config, elements)
TDD RED phase - tests will fail until implementation is added.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- TestPromptTemplatesExist: 4 tests for template file existence
- TestPromptLoader: 6 tests for loading and rendering templates
- Tests fail (RED phase) - no templates or loader implemented yet
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
starmen1265