state-memory-mcp CLAUDE.md

State Memory (state-memory-mcp)

This project tracks workflow state, tasks, design decisions, and blockers using state-memory-mcp with project slug "state-memory-mcp".

1. Priority Order

Before doing any coding or investigation:

1. manage_sessions(action: "start") — Start a tracking session for full change attribution.
2. get_analytics(action: "summary") — Run to understand current project state, active branches, and overall progress.
3. manage_tasks(action: "next") — Query prioritized runnable tasks.
4. manage_tasks(action: "find_blockers") — Identify any active blockers preventing progress.
5. manage_nodes(action: "list") — Find pending tasks, past decisions, or milestones.
6. query_graph(action: "trace") — Trace what depends on or blocks a task.

2. When to Write to the Graph

You MUST update the graph as you work:

• Starting a session: Always call manage_sessions(action: "start", agent_id: "my-agent") to track all mutations under a unique session.
• Starting a new task: Create a node with manage_nodes(action: "create", type: "task", title: "...", session_id: session_id).
• Making a design or implementation decision: Document it with manage_nodes(action: "create", type: "decision", title: "...", metadata: { "rationale": "..." }, session_id: session_id).
• Connecting UI tasks to visual states: Use manage_edges(action: "link_visual", target_id: task_id, visual_state_id: vs_id, relationship: "renders_state").
• Encountering a blocker: Record the blocker with manage_nodes(action: "create", type: "blocker", ..., session_id: session_id) and connect it using manage_edges(action: "add", type: "blocks", source_id: blocker_id, target_id: task_id, session_id: session_id).
• Adding observation notes: Atomically log notes using manage_nodes(action: "add_note", text: "...", attach_to: node_id).
• Batch updates: Bulk update tasks/nodes using manage_nodes(action: "batch_update", ids: ["..."], status: "done").
• Observability & Trajectories: Check manage_data(action: "export_synergy_metrics") for combined token savings & health, and manage_data(action: "export_joint_trajectories") for interleaved fine-tuning datasets.
• Completing a task: Update status to done using manage_tasks(action: "complete", task_id: task_id).
• Creating/generating a new file: Create an artifact node with manage_nodes(action: "create", type: "artifact", ..., session_id: session_id) and connect it using manage_edges(action: "add", type: "produces", ..., session_id: session_id).