gitea/agent-runtime
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
agent-runtime/testcases/pa_retry.md
Nico 925fff731f v0.17.0: User expectation tracking, PA retry loop, machine state in PA context 
- Memorizer tracks user_expectation (conversational/delegated/waiting_input/observing)
- Output node adjusts phrasing per expectation
- PA retry loop: reformulates job on expert failure (all retries exhausted or tool skip)
- Machine state in PA context: get_machine_summary includes current state, buttons, stored data
- Expert writes to machine state via update_machine + transition_machine
- Expanded baked schema coverage
- Awareness panel shows color-coded expectation state
- Dashboard and workspace component updates

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-03-30 19:03:07 +02:00

616 B
Raw Blame History

PA Retry on Expert Failure

Tests that when expert fails, PA reformulates and retries with a different approach.

Setup

  • clear history

Steps

1. Complex analytical query that may need retry

  • send: Finde KWZ-Geraete mit verdaechtigen Verbrauchsspruengen - also wo der Verbrauch zwischen zwei Ablesungen stark ansteigt
  • expect_response: length > 20

2. Verify results contain device data

  • expect_response: contains "Gera" or "gera" or "KWZ" or "kwz" or "Verbrauch" or "device"

3. Follow up with details

  • send: zeig mir die Verbraeuche von einem dieser Geraete
  • expect_response: length > 10