WIP almost done with track planning

conductor/tracks/deep_ast_context_pruning_20260306/index.md

@@ -0,0 +1,9 @@
+# Deep AST-Driven Context Pruning
+
+**Track ID:** deep_ast_context_pruning_20260306
+
+**Status:** Planned
+
+**See Also:**
+- [Spec](./spec.md)
+- [Plan](./plan.md)

conductor/tracks/deep_ast_context_pruning_20260306/metadata.json

@@ -0,0 +1,9 @@
+{
+  "id": "deep_ast_context_pruning_20260306",
+  "name": "Deep AST-Driven Context Pruning",
+  "status": "planned",
+  "created_at": "2026-03-06T00:00:00Z",
+  "updated_at": "2026-03-06T00:00:00Z",
+  "type": "feature",
+  "priority": "medium"
+}

conductor/tracks/deep_ast_context_pruning_20260306/plan.md

@@ -1,16 +1,30 @@
-# Implementation Plan: Deep AST-Driven Context Pruning (RAG for Code) (deep_ast_context_pruning)
+# Implementation Plan: Deep AST Context Pruning (deep_ast_context_pruning_20260306)
 
-## Phase 1: Research & Design
-- [ ] Task: Analyze existing backend implementation
-- [ ] Task: Design GUI/UX approach
-- [ ] Task: Conductor - User Manual Verification
+## Phase 1: AST Integration
+- [ ] Task: Initialize MMA Environment
+- [ ] Task: Verify tree_sitter availability
+    - WHERE: requirements.txt, imports
+    - WHAT: Ensure tree_sitter installed and importable
+    - HOW: pip install tree_sitter
 
-## Phase 2: Implementation
-- [ ] Task: Implement feature
-- [ ] Task: Write tests
-- [ ] Task: Conductor - User Manual Verification
+## Phase 2: Skeleton Generation
+- [ ] Task: Implement AST parser
+    - WHERE: src/file_cache.py or new module
+    - WHAT: Parse Python AST using tree_sitter
+    - HOW: tree_sitter.Language + Parser
+    - SAFETY: Exception handling for parse errors
+- [ ] Task: Implement skeleton generator
+    - WHERE: src/file_cache.py
+    - WHAT: Extract function signatures and docstrings
+    - HOW: Walk AST, collect Def nodes
+    - SAFETY: Handle large files gracefully
+- [ ] Task: Integrate with worker dispatch
+    - WHERE: src/multi_agent_conductor.py
+    - WHAT: Inject skeleton into worker prompt
+    - HOW: Modify context generation
+    - SAFETY: Verify tokens reduced
 
-## Phase 3: Verification
-- [ ] Task: Run test suite
-- [ ] Task: Verify coverage
-- [ ] Task: Conductor - Phase Completion Verification
+## Phase 3: Tests & Verification
+- [ ] Task: Write AST parsing tests
+- [ ] Task: Verify token reduction
+- [ ] Task: Conductor - Phase Verification

conductor/tracks/deep_ast_context_pruning_20260306/spec.md

@@ -1,28 +1,22 @@
-# Track Specification: Deep AST-Driven Context Pruning
+# Track Specification: Deep AST-Driven Context Pruning (deep_ast_context_pruning_20260306)
 
 ## Overview
-Use tree_sitter to parse target file AST and inject condensed skeletons into worker prompts.
+Use tree_sitter to parse target file AST and inject condensed skeletons into worker prompts. Currently workers receive full file context; this track reduces token burn by injecting only relevant function/method signatures.
 
-## Current State Audit
-### Already Implemented
-- file_cache.py with skeleton generation
-- outline_tool.py for code outlines
-- AST-based file analysis
-
-### Gaps to Fill
-- No automatic AST pruning based on edit target
-- Skeletons not customizable by user
-
-## Goals
-- Parse target file AST before worker dispatch
-- Strip unrelated function bodies
-- Inject surgical skeleton to reduce tokens
+## Architectural Constraints
+- **Parsing Performance**: AST parsing MUST complete in <100ms per file.
+- **Caching**: Parsed AST trees SHOULD be cached to avoid re-parsing.
+- **Selective Exposure**: Only target functions/classes related to the ticket's target_file should be included.
 
 ## Functional Requirements
-- tree_sitter integration
-- Target function/method detection
-- Configurable skeleton depth
+- **AST Parser**: Integrate tree_sitter to parse Python files.
+- **Target Detection**: Identify which functions/methods to include based on ticket target_file.
+- **Skeleton Generation**: Generate condensed skeletons with signatures and docstrings only.
+- **Worker Integration**: Inject skeleton into worker prompt instead of full file content.
 
-## Non-Functional Requirements
-- <100ms parsing time per file
-- >50% token reduction target
+## Acceptance Criteria
+- [ ] tree_sitter successfully parses Python AST.
+- [ ] Skeleton includes only target function/class with signature and docstring.
+- [ ] Token count reduced by >50% for typical worker prompts.
+- [ ] Workers can still complete tickets with skeleton-only context.
+- [ ] >80% test coverage.