agent-runtime/testcases/artifact_system.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

34 lines
969 B
Markdown

# Artifact System
Tests that the artifact rendering pipeline works end-to-end.
Expert produces data → UINode converts to artifacts → frontend renders.
## Setup
- clear history
## Steps
### 1. Query produces data_table artifact
- send: show me 3 customers in a table
- expect_trace: has tool_call
- expect_response: length > 10
### 2. Entity detail via card
- send: show me details for customer 1
- expect_trace: has tool_call
- expect_response: length > 10
### 3. Action bar via buttons
- send: create two buttons on my dashboard: Refresh and Export
- expect_actions: length >= 2
- expect_actions: any action contains "refresh" or "Refresh"
### 4. Machine artifact
- send: create a machine called "flow" with initial state "ready" and a state called "done"
- expect_trace: has machine_created
### 5. Query after buttons survive
- send: how many customers are there?
- expect_response: length > 5
- expect_actions: any action contains "refresh" or "Refresh"