# Track Specification: Architecture Boundary Hardening

## Overview
The `manual_slop` project sandbox provides AI meta-tooling (`mma_exec.py`, `tool_call.py`) to orchestrate its own development. When AI agents added advanced AST tools (like `set_file_slice`) to `mcp_client.py` for meta-tooling, they failed to fully integrate them into the application's GUI, config, or HITL (Human-In-The-Loop) safety models. Additionally, meta-tooling scripts are bleeding tokens and rely on non-portable hardcoded machine paths, while the internal application's state machine can deadlock.

## Current State Audit

1. **Incomplete MCP Tool Integration & HITL Bypass (`ai_client.py`, `gui_2.py`)**:
   - Issue: New tools in `mcp_client.py` (e.g., `set_file_slice`, `py_update_definition`) are not exposed in the GUI or `manual_slop.toml` config `[agent.tools]`. If they were enabled, `ai_client.py` would execute them instantly without checking `pre_tool_callback`, bypassing GUI approval.
   - *Requirement*: Expose all `mcp_client.py` tools as toggles in the GUI/Config. Ensure any mutating tool triggers a GUI approval modal before execution.

2. **Token Firewall Leak in Meta-Tooling (`mma_exec.py`)**:
   - Location: `scripts/mma_exec.py:101`.
   - Issue: `UNFETTERED_MODULES` hardcodes `['mcp_client', 'project_manager', 'events', 'aggregate']`. If a worker targets a file that imports `mcp_client`, the script injects the full `mcp_client.py` (~450 lines) into the context instead of its skeleton, blowing out the token budget.

3. **Portability Leak in Meta-Tooling Scripts**:
   - Location: `scripts/mma_exec.py` and `scripts/claude_mma_exec.py`.
   - Issue: Both scripts hardcode absolute external paths (`C:\projects\misc\setup_gemini.ps1` and `setup_claude.ps1`) to initialize the subprocess environment. This breaks repository portability.

4. **DAG Engine Blocking Stalls (`dag_engine.py`)**:
   - Location: `dag_engine.py` -> `get_ready_tasks()`
   - Issue: `get_ready_tasks` requires all dependencies to be explicitly `completed`. If a task is marked `blocked`, its dependents stay `todo` forever, causing an infinite stall.

## Desired State
- All tools in `mcp_client.py` are configurable in `manual_slop.toml` and `gui_2.py`. Mutating tools must route through the GUI approval callback.
- The `UNFETTERED_MODULES` list must be completely removed from `mma_exec.py`.
- Meta-tooling scripts rely on standard PATH or local relative config files, not hardcoded absolute external paths.
- The `dag_engine.py` must cascade `blocked` status to downstream tasks so the track halts cleanly.