Repository navigation
feat: agent-executable tickets - #8
Merged
Merged
Conversation
Design for adding agent_context field to stories, enabling AI agents to execute tickets with structured exploration, pattern guidance, and self-check verification.
8 tasks with TDD approach: 1. AgentContext model 2. Story model update 3. Decomposition prompt 4. Prompt renderer 5. CLI prompt command 6. CSV export update 7. Integration test 8. README docs
Add AgentContext Pydantic model with fields for AI agent guidance: - goal (required): The 'why' - what problem this solves - exploration_paths: Keywords/concepts to search - exploration_hints: Specific paths to start with - known_patterns: Libraries/patterns to follow - verification_tests: Tests that should pass when done - self_check: Questions to verify before completion Includes 3 tests and public export from __init__.py.
Add guideline 8 instructing the LLM to generate agent_context for each story, including goal, exploration_paths, exploration_hints, known_patterns, verification_tests, and self_check fields. Update the example output and schema section to demonstrate the agent_context structure. Bump PROMPT_VERSION to 1.6.0.
Add 'prompt N' command (aliases: copy, show) to display a ready-to-paste prompt for any story by its 1-based index. This enables users to quickly extract formatted prompts for use with AI coding agents. Changes: - Add prompt/copy/show command parsing to parse_command - Add current_tickets field and get_story_by_index method to SessionState - Add prompt command handler using existing render_agent_prompt formatter - Store tickets in session when decompose_to_tickets results are extracted
Add agent_prompt column to CSV export that renders the story's agent_context using the render_agent_prompt formatter. This gives users a ready-to-paste prompt for AI agents directly in the CSV.
- Remove "Agent-Executable Tickets" from Future Iterations (now implemented) - Update test count from 243 to 305 - Add formatters.py and session_state.py to project structure - Add Session 10 documenting the agent-executable tickets feature - Update AI-generated files list with new files
HIGH: - Move inline import in export.py to module level MEDIUM: - Fix line length violations in models.py, agent.py, test files - Add AgentContext to top-level imports in test_models.py - Add test for reset() clearing current_tickets LOW: - Add agent_context to all example stories in decomposition prompt (improves LLM consistency in generating agent_context)
Add TestAgentContextGeneration eval class with 5 tests: - test_stories_have_agent_context (≥50% coverage) - test_agent_context_has_goal (meaningful goal text) - test_agent_context_has_exploration_paths - test_security_feature_has_self_check_questions - test_agent_context_verification_tests_present These evals verify that decompose_to_tickets generates useful agent_context metadata for AI-assisted implementation.
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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.
Summary
Add
agent_contextfield to stories so AI coding assistants (Claude Code, Cursor, etc.) can execute tickets with structured guidance.Key changes:
goal,exploration_paths,exploration_hints,known_patterns,verification_tests,self_checkprompt Ncommand in agent CLI for copy-paste promptsagent_promptcolumnrender_agent_prompt()formatter inprd_decomposer.formattersTest Plan