Auto claude/add followup on done task #1
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
…ather user input Add collect_followup_task() function that: - Presents a menu with options to type, paste, or load from file - Collects multiline input with empty line termination - Saves the follow-up task to FOLLOWUP_REQUEST.md in spec directory - Uses UI utilities (box, icon, muted, highlight) for consistent formatting - Handles cancellation and errors gracefully - Returns the collected task or None if cancelled 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <[email protected]>
…ollowup_task() - Replace placeholder TODO with actual call to collect_followup_task(spec_dir) - Handle cancelled case (returns None) with appropriate message - Show next steps message after successful task collection - Leave TODO for chunk-5-2 to add run_followup_planner() integration 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <[email protected]>
…ationPlan Add method to extend existing implementation plans with new follow-up phases. This enables the --followup workflow where users can add work to completed specs. The method: - Calculates the next phase number based on existing phases - Sets depends_on to all existing phases for proper sequencing - Updates status to in_progress since there's now pending work - Clears qa_signoff since the plan has changed 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <[email protected]>
…n plan Add reset_for_followup() method to ImplementationPlan class that: - Transitions plan from completed/done/review states back to in_progress - Clears QA signoff since new work invalidates previous approval - Clears recovery notes from previous run - Returns bool indicating if reset was needed/successful This enables the follow-up workflow to properly restart the build pipeline when new chunks are added to a completed spec. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <[email protected]>
🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <[email protected]>
…followup_planner() - Import run_followup_planner from agent module - Replace placeholder TODO with actual asyncio.run() call - Add proper error handling for KeyboardInterrupt and exceptions - Show success/failure messages with next steps - Validate environment before running planner 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <[email protected]>
…ion methods Add comprehensive test suite for follow-up task capability: - TestAddFollowupPhase: Tests for add_followup_phase() method - TestResetForFollowup: Tests for reset_for_followup() method - TestExistingChunksPreserved: Ensures completed chunks remain untouched - TestFollowupPlanSaveLoad: Tests persistence through save/load cycles - TestFollowupProgressCalculation: Tests progress calculation with follow-ups All 24 tests pass, verifying: - Phase numbering and dependency management - Status transitions (done -> in_progress) - QA signoff clearing - Multiple sequential follow-ups - Chunk preservation 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <[email protected]>
…sages - Enhanced collect_followup_task() with retry logic (max 3 attempts) - Added handling for empty file paths - Added handling for empty files with clear error message - Added PermissionError handling with actionable guidance - Improved error messages for incomplete builds with pending chunk count - Improved error messages for missing implementation plan with UI boxes - Added detection of prior follow-ups for sequential follow-up context - Show prior follow-up count when adding additional follow-ups
Files were tracked before being added to .gitignore. This removes them from git tracking while keeping the local files intact.
- Changed default OpenAI model from gpt-4o to gpt-5-mini in configuration files. - Added functionality to sync the implementation plan from worktree back to the main project directory. - Introduced a review requirement toggle in the task creation wizard to prompt for human review before coding. - Enhanced task metadata to include review settings. This update improves model capabilities and workflow management for task execution.
…aude/add-followup-on-done-task
- Introduced `isIncompleteHumanReview` function to detect tasks in human review with no completed chunks, indicating a potential crash. - Updated TaskCard and TaskDetailPanel components to display an "Incomplete" badge and a resume button for such tasks. - Enhanced user feedback for incomplete tasks, guiding users to resume implementation when necessary. This improves task management by clearly indicating when a task requires attention due to incomplete execution.
1 task
ariefsaid
added a commit
to ariefsaid/Auto-Claude
that referenced
this pull request
Dec 24, 2025
This commit fixes two critical issues with the ideation refresh feature: Issue AndyMik90#1: UI Stuck on "Refreshing ideation..." - Root cause: Missing event forwarding from AgentManager to renderer - Fix: Added IPC event listeners in ideation-handlers.ts that forward: * ideation-progress (real-time progress updates) * ideation-log (log messages) * ideation-type-complete (streaming idea updates as types complete) * ideation-type-failed (error handling) * ideation-complete (final completion) * ideation-error (error messages) * ideation-stopped (stop events) - Impact: UI now receives real-time progress instead of being stuck Issue #2: Dismissed Ideas Reappearing After Refresh - Root cause: formatter.py only preserved status when append=True - Fix: Modified merge_ideation_outputs() to ALWAYS load existing ideas and preserve user metadata (status, taskId, timestamps) by ID matching - Impact: Dismissed/archived/converted ideas maintain their status across refreshes Files changed: - auto-claude-ui/src/main/ipc-handlers/ideation-handlers.ts (+86 lines) - auto-claude/ideation/formatter.py (+43 lines, -10 lines) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Sonnet 4.5 <[email protected]>
ruinosus
pushed a commit
to ruinosus/Auto-Claude
that referenced
this pull request
Dec 25, 2025
…p-on-done-task Auto claude/add followup on done task
ruinosus
added a commit
to ruinosus/Auto-Claude
that referenced
this pull request
Dec 25, 2025
Fixed 5 critical security and code generation issues: **Issue AndyMik90#1: Invalid Python Boolean/Null Syntax** - Replaced JSON.stringify() with toPythonValue() function - Now correctly converts: true → True, false → False, null → None - Handles all Python types: strings, numbers, bools, lists, dicts **Issue #2: Code Injection - Server Name** - Added sanitizePythonString() to escape server names - Prevents code injection via unescaped quotes and backslashes **Issue AndyMik90#3: Code Injection - Tool Names** - Added sanitizePythonIdentifier() validation - Rejects invalid identifiers (123name, invalid-name, etc.) - Blocks Python reserved keywords (def, class, if, etc.) **Issue AndyMik90#4: Docstring Injection** - sanitizePythonString() escapes triple quotes in descriptions - Prevents breaking out of docstrings with """ sequences **Issue AndyMik90#5: Missing Input Validation** - Validates all identifiers (tool names, parameter names) - Comprehensive error messages with context - Follows Python PEP 8 identifier rules Test Coverage: - Boolean defaults: true/false → True/False - Null defaults: null → None - Invalid identifier rejection - Reserved keyword rejection - Triple quote escaping - Backslash and quote escaping - 17 tests, all passing Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Sonnet 4.5 <[email protected]>
11 tasks
This was referenced Jan 1, 2026
4 tasks
YoniBL
pushed a commit
to YoniBL/Auto-Claude
that referenced
this pull request
Jan 2, 2026
Add AUTO_CLAUDE_SCHEMA.md containing complete architectural reference: - Repository lineage (upstream → fork) - Full directory structure with explanations - Prompt template system (25+ templates categorized) - Workflow architecture (17 workflows detailed) - Data flow and agent pipeline architecture - Testing and development setup guides - Known issues reference (links to GitHub issues AndyMik90#1-5) Generated from deep ultrathink review with code-reasoning and MCTS analysis. Enables AI agents to understand and work with Auto-Claude codebase effectively. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Sonnet 4.5 <[email protected]>
doublefx
added a commit
to doublefx/Auto-Claude
that referenced
this pull request
Jan 2, 2026
…port - Pass commitMessage parameter from frontend components to backend API - Replace hardcoded error messages with i18n translation keys - Add useTranslation hooks to LoadingMessage and NoWorkspaceMessage components - Add missing translation keys for commit errors Addresses issues AndyMik90#1, AndyMik90#5, and AndyMik90#6 from code review on PR AndyMik90#574
This was referenced Jan 2, 2026
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
No description provided.