agent-runtime/testcases/s3_audit.md
Nico a2bc6347fc v0.13.0: Graph engine, versioned nodes, S3* audit, DB tools, Cytoscape
Architecture:
- Graph engine (engine.py) loads graph definitions, instantiates nodes
- Versioned nodes: input_v1, thinker_v1, output_v1, memorizer_v1, director_v1
- NODE_REGISTRY for dynamic node lookup by name
- Graph API: /api/graph/active, /api/graph/list, /api/graph/switch
- Graph definition: graphs/v1_current.py (7 nodes, 13 edges, 3 edge types)

S3* Audit system:
- Workspace mismatch detection (server vs browser controls)
- Code-without-tools retry (Thinker wrote code but no tool calls)
- Intent-without-action retry (request intent but Thinker only produced text)
- Dashboard feedback: browser sends workspace state on every message
- Sensor continuous comparison on 5s tick

State machines:
- create_machine / add_state / reset_machine / destroy_machine via function calling
- Local transitions (go:) resolve without LLM round-trip
- Button persistence across turns

Database tools:
- query_db tool via pymysql to MariaDB K3s pod (eras2_production)
- Table rendering in workspace (tab-separated parsing)
- Director pre-planning with Opus for complex data requests
- Error retry with corrected SQL

Frontend:
- Cytoscape.js pipeline graph with real-time node animations
- Overlay scrollbars (CSS-only, no reflow)
- Tool call/result trace events
- S3* audit events in trace

Testing:
- 167 integration tests (11 test suites)
- 22 node-level unit tests (test_nodes/)
- Three test levels: node unit, graph integration, scenario

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-29 00:18:45 +01:00

32 lines
973 B
Markdown

# S3* Audit Corrections
Tests that the S3* audit system detects and corrects Thinker failures:
code-without-tools mismatch, empty workspace recovery, error retry.
## Setup
- clear history
## Steps
### 1. Tool calls produce results (baseline)
- send: create two buttons: Alpha and Beta
- expect_actions: length >= 1
- expect_actions: any action contains "alpha" or "Alpha"
### 2. Dashboard mismatch triggers re-emit
- send: I see nothing on my dashboard, fix it |dashboard| []
- expect_response: not contains "sorry" or "apologize"
- expect_actions: length >= 1
### 3. DB error triggers retry with corrected SQL
- send: SELECT * FROM NichtExistent LIMIT 5
- expect_trace: has tool_call
- expect_response: not contains "1146"
- expect_response: length > 10
### 4. Complex request gets Director plan
- send: investigate which customers have the most devices in the database
- expect_trace: has director_plan
- expect_trace: has tool_call
- expect_response: length > 20