docs(conductor): Synchronize docs for track 'Deep AST-Driven Context Pruning'

This commit is contained in:
2026-03-06 17:06:34 -05:00
parent af4a227d67
commit 2e44d0ea2e
2 changed files with 2 additions and 3 deletions

View File

@@ -40,7 +40,7 @@ For deep implementation details when planning or implementing tracks, consult `d
- **Role-Scoped Documentation:** Automated mapping of foundational documents to specific tiers to prevent token bloat and maintain high-signal context. - **Role-Scoped Documentation:** Automated mapping of foundational documents to specific tiers to prevent token bloat and maintain high-signal context.
- **Tiered Context Scoping:** Employs optimized context subsets for each tier. Tiers 1 & 2 receive strategic documents and full history, while Tier 3/4 workers receive task-specific "Focus Files" and automated AST dependency skeletons. - **Tiered Context Scoping:** Employs optimized context subsets for each tier. Tiers 1 & 2 receive strategic documents and full history, while Tier 3/4 workers receive task-specific "Focus Files" and automated AST dependency skeletons.
- **Worker Spawn Interceptor:** A mandatory security gate that intercepts every sub-agent launch. Provides a GUI modal allowing the user to review, modify, or reject the worker's prompt and file context before it is sent to the API. - **Worker Spawn Interceptor:** A mandatory security gate that intercepts every sub-agent launch. Provides a GUI modal allowing the user to review, modify, or reject the worker's prompt and file context before it is sent to the API.
- **Strict Memory Siloing:** Employs tree-sitter AST-based interface extraction (Skeleton View, Curated View) and "Context Amnesia" to provide workers only with the absolute minimum context required, preventing hallucination loops. - **Strict Memory Siloing:** Employs tree-sitter AST-based interface extraction (Skeleton View, Curated View, and Targeted View) and "Context Amnesia" to provide workers only with the absolute minimum context required. Features multi-level dependency traversal and AST caching to minimize re-parsing overhead and token burn.
- **Explicit Execution Control:** All AI-generated PowerShell scripts require explicit human confirmation via interactive UI dialogs before execution, supported by a global "Linear Execution Clutch" for deterministic debugging. - **Explicit Execution Control:** All AI-generated PowerShell scripts require explicit human confirmation via interactive UI dialogs before execution, supported by a global "Linear Execution Clutch" for deterministic debugging.
- **Parallel Multi-Agent Execution:** Executes multiple AI workers in parallel using a non-blocking execution engine and a dedicated `WorkerPool`. Features configurable concurrency limits (defaulting to 4) to optimize resource usage and prevent API rate limiting. - **Parallel Multi-Agent Execution:** Executes multiple AI workers in parallel using a non-blocking execution engine and a dedicated `WorkerPool`. Features configurable concurrency limits (defaulting to 4) to optimize resource usage and prevent API rate limiting.
- **Parallel Tool Execution:** Executes independent tool calls (e.g., parallel file reads) concurrently within a single agent turn using an asynchronous execution engine, significantly reducing end-to-end latency. - **Parallel Tool Execution:** Executes independent tool calls (e.g., parallel file reads) concurrently within a single agent turn using an asynchronous execution engine, significantly reducing end-to-end latency.

View File

@@ -31,8 +31,7 @@
- **src/paths.py:** Centralized module for path resolution, allowing directory paths (logs, conductor, scripts) to be configured via `config.toml` or environment variables, eliminating hardcoded filesystem dependencies. - **src/paths.py:** Centralized module for path resolution, allowing directory paths (logs, conductor, scripts) to be configured via `config.toml` or environment variables, eliminating hardcoded filesystem dependencies.
- **ast (Standard Library):** For deterministic AST parsing and automated generation of curated "Skeleton Views" - **tree-sitter / AST Parsing:** For deterministic AST parsing and automated generation of curated "Skeleton Views" and "Targeted Views" (extracting specific functions and their dependencies). Features an integrated AST cache with mtime-based invalidation to minimize re-parsing overhead.
(signatures and docstrings) to minimize context bloat for sub-agents.
- **pydantic / dataclasses:** For defining strict state schemas (Tracks, Tickets) used in linear orchestration. - **pydantic / dataclasses:** For defining strict state schemas (Tracks, Tickets) used in linear orchestration.
- **tomli-w:** For writing TOML configuration files. - **tomli-w:** For writing TOML configuration files.
- **tomllib:** For native TOML parsing (Python 3.11+). - **tomllib:** For native TOML parsing (Python 3.11+).