← Back to Hermes
Hermes proof

Validation and observability

Inspect visible state first, prove the expected change, then expand the rollout only after the evidence is clean.

Proof ruleUse the smallest checks that answer the real question before you claim success.

One of the most useful habits in the current Hermes research pack is the shift from guessing to proving. When something changes, the better question is: what is the smallest check that can prove the expected state is actually true?

Start with the smallest visible checks

Inspect config when behavior drifts

Use ~/.hermes/config.yaml as a real state surface when behavior changes after restart, resume, or provider switch.

Check logs and runtime traces before you guess

When visible state is not enough, move one layer deeper and inspect logs, command output, and runtime traces before you jump to rebuild logic. Observability is not only about the final response in chat. It also includes whether the CLI reported the right model, whether session listings changed as expected, whether a restart actually cleared the symptom, and whether the active lane produced a concrete error instead of just going quiet.

Validate security posture, not just output

Use a narrow escalation order

  1. inspect first
  2. prove the expected state
  3. reconfigure second
  4. restart third when the failure is transient
  5. rebuild only after path, config, session, platform, approval, and editor/runtime bridge lanes were checked

Related pages