save

Save current session progress to Awareness Memory.

Focus (optional): $ARGUMENTS

How to call Awareness tools

Try MCP tools first (awareness_init, awareness_recall, awareness_record, awareness_lookup). If MCP tools are NOT available, use Bash to call the local daemon HTTP API directly:

# awareness_record (single)
curl -s -X POST http://localhost:37800/mcp -H "Content-Type: application/json" -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"awareness_record","arguments":{"action":"remember","content":"...","insights":{"knowledge_cards":[...],"action_items":[...],"risks":[...]}}}}'

# awareness_record (batch)
curl -s -X POST http://localhost:37800/mcp -H "Content-Type: application/json" -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"awareness_record","arguments":{"action":"remember_batch","items":[{"content":"step 1..."},{"content":"step 2..."}],"insights":{"knowledge_cards":[...],"action_items":[...],"risks":[...]}}}}'

The response is JSON-RPC: result.content[0].text contains the tool output as JSON string.

Steps

1. Gather context about what happened in this session.

2. Extract structured insights from the session — salience-aware, not greedy:

   Philosophy (distilled essence, not raw logs): your job is NOT "generate a card for every turn" — it is "identify what's worth recalling in 6 months on a fresh project". Returning empty arrays for knowledge_cards is a first-class answer when the session was just tool testing, chatter, or framework metadata.

   • knowledge_cards: only genuine insights (each with category, title, summary, confidence, + three 0.0-1.0 scores).
     • When to extract:

• The user made a decision — chose X over Y, with a stated reason
• A non-obvious bug was fixed — symptom + root cause + fix + how to avoid recurring
• A workflow / convention was established — ordered steps, preconditions, gotchas
• The user stated a preference or hard constraint — "I prefer X", "never do Y"
• A pitfall was encountered and a workaround found — trigger + impact + avoidance
• An important fact about the user or project surfaced for the first time

 - **When NOT to extract:**

• Agent framework metadata: content beginning with Sender (untrusted metadata), turn_brief, [Operational context metadata ...], [Subagent Context], or wrapped inside Request: / Result: / Send: envelopes that only carry such metadata. Strip those wrappers mentally and judge what remains.
• Greetings / command invocations: "hi", "run tests", "save this", "try again".
• "What can you do" / AI self-introduction turns.
• Code restatement: code itself lives in git; only extract the lesson if one exists.
• Test / debug sessions where the user is verifying the tool works (including tests of awareness_record / awareness_recall themselves). A bug fix in those tools IS worth extracting as problem_solution; a raw "let me test if recall works" turn is not.
• Transient status / progress updates — "building...", "retrying...", "✅ done".