Implementation Plan: Architecture Boundary Hardening

Phase 1: Patch Context Amnesia Leak & Portability (Meta-Tooling)

Focus: Stop mma_exec.py from injecting massive full-text dependencies and remove hardcoded external paths.

Task 1.1: In scripts/mma_exec.py, completely remove the UNFETTERED_MODULES constant and its associated if dep in UNFETTERED_MODULES: check. Ensure all imported local dependencies strictly use generate_skeleton().
Task 1.2: In scripts/mma_exec.py and scripts/claude_mma_exec.py, remove the hardcoded reference to C:\projects\misc\setup_*.ps1. Rely on the active environment's PATH to resolve gemini and claude, or provide an .env configurable override.

Focus: Expose all native MCP tools in the config and GUI, and ensure mutating tools trigger user approval.

Task 2.1: Update manual_slop.toml and project_manager.py's default_project() to include all new tools (e.g., set_file_slice, py_update_definition, py_set_signature) under [agent.tools].
Task 2.2: Update gui_2.py's settings/config panels to expose toggles for these new tools.
Task 2.3: In mcp_client.py, define a MUTATING_TOOLS constant set.
Task 2.4: In ai_client.py's provider loops (_send_gemini, _send_gemini_cli, _send_anthropic, _send_deepseek), update the tool execution logic: if name in mcp_client.MUTATING_TOOLS, it MUST trigger a GUI approval mechanism (like pre_tool_callback) before dispatching the tool.

Focus: Prevent infinite deadlocks when Tier 3 workers fail repeatedly.

Task 3.1: In dag_engine.py, add a cascade_blocks() method to TrackDAG. This method should iterate through all todo tickets and if any of their dependencies are blocked, mark the ticket itself as blocked.
Task 3.2: In multi_agent_conductor.py, update ConductorEngine.run(). Before calling self.engine.tick(), call self.track_dag.cascade_blocks() (or equivalent) so that blocked states propagate cleanly, allowing the all_done or block detection logic to exit the while loop correctly.