fix(hermes): separate POLICY observations from FAULT findings in the audit contracts #90

Merged
abiba-bot merged 1 commits from fix/hermes-violation-classification-20260914 into master 2026-09-14 12:50:16 +00:00
1 Commits
Author SHA1 Message Date
root 9a789ab76d fix(hermes): separate policy observations from fault findings
PR Pipeline — Authorize → Validate → Review → Merge / auth (pull_request) Successful in 5s
PR Pipeline — Authorize → Validate → Review → Merge / validate (pull_request) Successful in 7s
PR Pipeline — Authorize → Validate → Review → Merge / lint (pull_request) Successful in 7s
PR Pipeline — Authorize → Validate → Review → Merge / ai-review (pull_request) Successful in 6s
PR Pipeline — Authorize → Validate → Review → Merge / gate (pull_request) Successful in 3s
Contract design defect: 'uses a non-harness provider' (POLICY) and
'cannot authenticate' (FAULT) were printed as the same violation class.
A policy observation must never be phrased as if the agent were broken.

Changes:
1. Added 'Violation Classification' section to all three contracts
2. Separated POLICY (observation only) from FAULT (requires request-level evidence)
3. Rules:
   - Do NOT infer runtime credential resolution from config text alone
   - Require request-level evidence before calling a FAULT: observed auth failure
     or absence of successful calls
   - If calls are succeeding, output is 'POLICY: uses <provider> directly; calls
     succeeding' - not a violation
   - State what you OBSERVED, not what the field implies

Files changed (3):
- hermes-key-enforcement.prose.md
- hermes-config-template.prose.md
- hermes-agent-baseline.prose.md
2026-09-14 12:32:06 +00:00