manual_slop/conductor/tracks/saved_tool_presets_20260308/plan.md

Implementation Plan: Saved Tool Presets

Phase 1: Data Model & Storage

• Task: Define the ToolPreset data model and storage logic.
  • Create src/tool_presets.py to handle loading/saving to tool_presets.toml.
  • Implement ToolPresetManager to manage CRUD operations for presets and categorization.
• Task: Write unit tests for ToolPresetManager.
  • Test loading tool presets from TOML.
  • Test saving tool presets to TOML.
  • Test dynamic category parsing.
  • Test tool approval flag persistence.
• Task: Conductor - User Manual Verification 'Phase 1: Data Model & Storage' (Protocol in workflow.md)

Phase 2: UI Integration (AI Settings)

• Task: Relocate tool settings to the AI Settings panel.
  • Modify gui_2.py to remove the current tool listing from the main panel and move it to the AI Settings panel (global/project).
• Task: Implement dynamic tool categorization UI.
  • Modify gui_2.py to render tools in sections based on categories defined in tool_presets.toml.
  • Implement toggleable "auto"/"ask" flags for each tool.
• Task: Implement Tool Preset dropdown for MMA agent roles.
  • Add the "Tool Preset" dropdown to the MMA agent role configuration modal in gui_2.py.
• Task: Write integration tests for AI Settings UI using live_gui.
  • Verify tools are categorized correctly in the UI.
  • Verify toggling a tool's approval persists correctly.
  • Verify the "Tool Preset" dropdown shows all available presets.
• Task: Conductor - User Manual Verification 'Phase 2: UI Integration (AI Settings)' (Protocol in workflow.md)

Phase 3: AI Client & Execution Integration

• Task: Integrate tool presets into the AI Client.
  • Modify src/ai_client.py to load and apply the selected tool preset for a given agent role.
  • Implement logic to restrict available tools and enforce "auto"/"ask" behavior based on the preset.
• Task: Update MMA delegation to pass the selected tool preset.
  • Modify scripts/mma_exec.py and src/multi_agent_conductor.py to pass the tool_preset to sub-agents.
• Task: Write integration tests for AI execution with tool presets.
  • Verify agents only have access to tools in their assigned preset.
  • Verify "auto" tools execute without prompting, and "ask" tools require confirmation.
• Task: Conductor - User Manual Verification 'Phase 3: AI Client & Execution Integration' (Protocol in workflow.md)

Phase 4: Final Integration & Polish

• Task: Implement Preset Manager Modal.
  • Create a modal for creating, editing, and deleting tool presets.
• Task: Final UI polish (spacing, icons, tooltips).
• Task: Run full suite of relevant tests.
• Task: Conductor - User Manual Verification 'Phase 4: Final Integration & Polish' (Protocol in workflow.md)