Commit graph

1 commit

Author SHA1 Message Date
rcourtman
6a0ba8d1a4 Add FSM workflow guardrails for AI assistant safety
Implement a state machine that enforces structural safety guarantees:
- RESOLVING: Initial state, must discover resources before writing
- READING: Read tools allowed after discovery
- WRITING: Transitions to VERIFYING after any write operation
- VERIFYING: Must perform read verification before next write

This prevents:
- Write operations without resource discovery
- Consecutive writes without verification
- Final answers without post-write verification

The FSM is enforced at the tool execution layer, providing defense-in-depth
that doesn't rely on prompt instructions alone.
2026-01-28 16:47:54 +00:00