fulcra-agent-durable-state

# Fulcra Agent Durable State **Ephemeral compute + durable Fulcra state = agents that survive their machines.** Cloud agent containers get reclaimed and rolled back. Desktop hosts sleep, reboot, and disappear. Any agent whose tooling lives only on local disk is one filesystem event away from amnesia — and worse than losing a script is *silently regaining an old one*: a rollback can revert a patched loop to the unpatched version, or restore a rotated credential's stale predecessor, and nothing errors until it misbehaves. The Fulcra File Store is the piece of the platform that doesn't share the machine's fate. It's the same substrate the coordination bus runs on (versioned, last-writer-wins, survives every container the fleet has lost so far), and `fulcra-api` auth persists independently of scratch disk. So the pattern is: > **Local disk is a cache. The store is the truth.** ## Where to start — the re-entrancy probes Before touching the stash, probe how far this session already got. Enter at the **first probe that fails** (per the repo's skill-quality pattern, `docs/skill-quality-pattern.md`); every step is safely re-runnable (uploads/downloads are whole-file overwrites, last-writer-wins). Auth probes on `fulcra-api` (the engine inherits its credentials); the stash probes run on the engine's `stash` verb: | Probe (run in order) | Command | Passes when | If it fails, enter at | |---|---|---|---| | Auth usable? | `fulcra-api auth print-access-token >/dev/null && echo AUTH-...