 rcourtman
|
0561a1b5fa
|
Remove Assistant and Patrol tool-routing heuristics
|
2026-05-15 14:51:15 +01:00 |
|
|
rcourtman
|
895b78bd89
|
Make Assistant tool choice model-owned
|
2026-05-15 11:27:15 +01:00 |
|
|
rcourtman
|
f8fd641978
|
Harden Pulse Assistant action governance
|
2026-04-23 23:01:51 +01:00 |
|
|
rcourtman
|
a41c956320
|
fix(ai): fail closed on unknown v6 read commands
|
2026-04-09 19:21:16 +01:00 |
|
|
rcourtman
|
21fa343fa1
|
Enable structured AI auto-recovery paths
|
2026-03-31 09:24:56 +01:00 |
|
|
rcourtman
|
046a0e92c0
|
Normalize pulse_read native log denial paths
|
2026-03-31 09:07:57 +01:00 |
|
|
rcourtman
|
298b23626b
|
feat(ai): add canonical truenas app log reads
|
2026-03-29 20:13:39 +01:00 |
|
|
rcourtman
|
778a2577b6
|
feat: Pulse v6 release
|
2026-03-18 16:06:30 +00:00 |
|
|
rcourtman
|
95a0d7a6bd
|
feat(backend): implement AI Patrol, Investigation, and system-wide refactors
|
2026-01-30 19:02:14 +00:00 |
|
|
rcourtman
|
b2e0ae3fdb
|
Add ExecutionIntent classification and NonInteractiveOnly enforcement
Implement safety layers for command execution:
ExecutionIntent classifies commands as:
- ObservationOnly: Pure read (status, logs, metrics)
- SideEffects: May change state (restart, write, delete)
NonInteractiveOnly enforces safe command forms:
- Blocks interactive commands (vim, top without -b, etc)
- Blocks unbounded streaming (tail -f without limit)
- Suggests safe alternatives in error messages
Add phantom execution detection:
- Catches when model claims actions without using tools
- Skips check when tools actually succeeded (fixes false positives)
Includes comprehensive tests for:
- Intent classification accuracy
- Interactive command blocking
- Strict resolution validation
|
2026-01-28 16:49:00 +00:00 |
|