| 123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354 |
- id: int-perf-001
- name: Performance Baseline Test
- description: |
- Simple test to establish performance baseline for the enhanced eval framework.
- Measures execution time with all new features enabled.
- category: developer
- agent: openagent
- model: anthropic/claude-sonnet-4-5
- prompts:
- - text: |
- Create a simple hello world function in evals/test_tmp/hello.ts
-
- - text: |
- Yes, proceed.
- delayMs: 1000
- # Minimal behavior to test performance
- behavior:
- mustUseTools: [write]
- requiresApproval: true
- minToolCalls: 1
-
- # Content validation (lightweight)
- contentExpectations:
- - filePath: "evals/test_tmp/hello.ts"
- mustContain:
- - "hello"
- minLength: 10
-
- # Debug options
- debug:
- logToolDetails: true
- saveReplayOnFailure: false
- # Expected violations
- expectedViolations:
- - rule: approval-gate
- shouldViolate: false
- severity: error
- description: Must ask approval before writing
- # Approval strategy
- approvalStrategy:
- type: auto-approve
- timeout: 60000
- tags:
- - integration
- - performance
- - baseline
- - v2-schema
|
