Context management: long tasks

Your first line in any agent design is what the agent must not do. Most failures come from unclear scope, sloppy tool contracts and missing failure handling, not from a weak model.

Task: The agent forgets early constraints in long tasks.

[Before you start, do three things]
1. Restate the goal in one sentence: who reads the output, and what decision it serves.
2. If I have not given you the following, ask me. Do not assume:
   - number of steps and context length
   - what must never be dropped
   - what can be compressed
   - external storage
3. Say how you plan to do it (at most 5 steps) and wait for my go-ahead.

[Go through each of these]
- pin non-negotiable constraints at the front of every turn
- compress intermediate work, keeping decisions and numbers
- keep an external file and retrieve rather than stuff the context
- every N steps, restate the goal and constraints

[Process]
1. Write the boundary: what it may do, must never do, and when to hand back to a human
2. Define each tool's inputs, outputs, failure semantics, idempotency
3. Write the flow as a state machine with exit conditions
4. Design failure paths: retry, degrade, abort, escalate
5. Give one testable success criterion

[Output]
Fixed shape: boundary, tool contracts, state machine, failure paths, criteria.

[Do not]
- No general-purpose agent that does everything
- Never let fuzzy prose stand in for a tool contract
- The agent must not decide whether approval is needed
- No 'do your best' instead of an abort condition