{
  "lesson": "34-repo-memory-and-state",
  "title": "Repo Memory and Durable State",
  "questions": [
    {
      "stage": "pre",
      "question": "What is the durability test that decides whether a piece of information belongs in repo memory?",
      "options": [
        "Whether it is JSON",
        "Whether it would be useful three months from now in a CI rerun; if yes, repo; if no, telemetry",
        "Whether the user marked it as important",
        "Whether it fits in 4 kB"
      ],
      "correct": 1,
      "explanation": "Repo memory is for durable, three-months-from-now-useful state; transient data is telemetry."
    },
    {
      "stage": "pre",
      "question": "What schema field carries the agent's contract version?",
      "options": [
        "schema_version",
        "build_hash",
        "model_id",
        "session_uuid"
      ],
      "correct": 0,
      "explanation": "schema_version is the integer contract; the manager refuses to load from an unknown version."
    },
    {
      "stage": "check",
      "question": "How does atomic write work?",
      "options": [
        "tempfile.mkstemp in the same directory, write, fsync, os.replace (atomic rename) over the target",
        "Truncate-then-write to the target",
        "Append-only with a CRC",
        "Encrypt and overwrite"
      ],
      "correct": 0,
      "explanation": "Atomic rename on POSIX and Windows is what prevents partial-write corruption."
    },
    {
      "stage": "check",
      "question": "Why are idempotency keys required for non-idempotent tool calls?",
      "options": [
        "For billing",
        "If the agent crashes after a tool call but before checkpointing the result, retry safely; log call ID before execution and skip the call on retry",
        "To deduplicate logs",
        "To shorten output"
      ],
      "correct": 1,
      "explanation": "pending_calls.jsonl carries the call IDs; recovery checks and skips already-executed work."
    },
    {
      "stage": "check",
      "question": "Where should large artifacts (CSVs, long transcripts, generated files) live relative to state?",
      "options": [
        "Inline in agent_state.json",
        "As separate files (or object storage) with only the path kept in state, so checkpoints stay small and fast",
        "In environment variables",
        "Concatenated into one giant log"
      ],
      "correct": 1,
      "explanation": "Separate artifacts grow independently of state; checkpoints stay cheap to read and write."
    },
    {
      "stage": "post",
      "question": "What does event sourcing for audit + snapshots for resume buy you?",
      "options": [
        "Lower disk usage",
        "Replay agent decisions verbatim by reading the snapshot then replaying events after it; same shape as Postgres WAL",
        "Faster inference",
        "Native voice support"
      ],
      "correct": 1,
      "explanation": "Append to state.events.jsonl on every mutation; periodically snapshot to state.json; replay events after the snapshot timestamp."
    },
    {
      "stage": "post",
      "question": "What does the lesson say happens when schema_version mismatches?",
      "options": [
        "The manager silently upgrades",
        "The manager refuses to load until a migration script in tools/migrate_state.py runs",
        "The state is deleted",
        "The agent retries"
      ],
      "correct": 1,
      "explanation": "Schema migrations or refuse-to-load; never silent upgrade."
    }
  ]
}