3.4 KiB
3.4 KiB
Implementation Plan: 4-Tier Architecture Implementation & Conductor Self-Improvement
Phase 1: manual_slop Migration Planning
- Task: Synthesize MMA Documentation [
46b351e]- Read and analyze
./MMA_Support/Data_Pipelines_and_Config.mdand./MMA_Support/OriginalDiscussion.md - Read and analyze
./MMA_Support/Tier1_Orchestrator.mdthrough./MMA_Support/Tier4_Utility.md - Document key takeaways and constraints for the migration plan
- Read and analyze
- Task: Draft Track 1 - The Memory Foundations (AST Parser) [
bdd935d]- Define TDD approach for
tree-sitterintegration infile_cache.py - Specify tasks for
ASTParserextraction rules (Skeleton View, Curated View) - Define acceptance testing criteria for AST extraction
- Define TDD approach for
- Task: Draft Track 2 - State Machine & Data Structures [
1198aee]- Define TDD approach for
models.py(Track,Ticket,WorkerContext) - Specify tasks for state mutator methods
- Define acceptance testing criteria for state transitions
- Define TDD approach for
- Task: Draft Track 3 - The Linear Orchestrator & Execution Clutch [
aaeed92]- Define TDD approach for
multi_agent_conductor.py(run_worker_lifecycle) - Specify tasks for context injection and HITL Clutch implementation
- Define acceptance testing criteria for the linear orchestration loop
- Define TDD approach for
- Task: Draft Track 4 - Tier 4 QA Interception [
584bff9]- Define TDD approach for
shell_runner.pystderr interception - Specify tasks for routing errors to the cheap API model
- Define acceptance testing criteria for the QA interception loop
- Define TDD approach for
- Task: Draft Track 5 - UI Decoupling & Tier 1/2 Routing (The Final Boss) [
67734c9]- Define TDD approach for async queue in
multi_agent_conductor.py - Specify tasks for Tier 1 & 2 system prompts and the Dispatcher async loop
- Define acceptance testing criteria for UI decoupling and dynamic routing
- Define TDD approach for async queue in
- [~] Task: Conductor - User Manual Verification '
manual_slopMigration Planning' (Protocol in workflow.md)
Phase 2: Conductor Self-Reflection & Upgrade Strategy
- Task: Research Optimal Proposal Format
- Search Gemini CLI documentation for extension guidelines
- Search Conductor documentation for tuning and advice
- Define the structure for
proposal.mdbased on findings
- Task: Draft Proposal - Memory Siloing & Token Firewalling
- Evaluate current
conductorcontext management - Propose strategies to prevent token bloat during planning and execution
- Write the corresponding section in
proposal.md
- Evaluate current
- Task: Draft Proposal - Execution Clutch & Linear Debug Mode
- Evaluate current
conductorexecution workflows - Propose mechanisms for manual step-through and auto modes
- Write the corresponding section in
proposal.md
- Evaluate current
- Task: Draft Proposal - Multi-Model/Sub-Agent Delegation
- Evaluate current
conductorsingle-model reliance - Propose a design for delegating tasks (e.g., summarization, syntax-fixing) to sub-agents
- Write the corresponding section in
proposal.md
- Evaluate current
- Task: Review and Finalize Proposal
- Ensure all three core areas are addressed with equal priority
- Verify alignment with the overall 4-Tier Architecture philosophy
- Task: Conductor - User Manual Verification 'Conductor Self-Reflection & Upgrade Strategy' (Protocol in workflow.md)