041e3238bc
* docs: fix agent name casing in documentation - Update all instances of 'openagent' to 'OpenAgent' - Update all instances of 'opencoder' to 'OpenCoder' - Fixes #115: --agent flag is case-sensitive The --agent flag requires capitalized agent names (OpenAgent, OpenCoder) but documentation showed lowercase versions, causing confusion for users. Updated README.md and all docs/ files to use correct casing. * refactor: migrate from grok-code to big-pickle model - Remove model specification from contextscout.md subagent - Update eval YAML files to use opencode/big-pickle - Update documentation to reference big-pickle as default - Fixes compatibility as grok-code-fast is no longer available Files updated: - .opencode/agent/subagents/core/contextscout.md - evals/agents/shared/tests/golden/00-smoke-test.yaml - evals/agents/shared/tests/golden/02-delegation-test.yaml - evals/README.md - evals/EVAL_FRAMEWORK_GUIDE.md
65 lines
1.8 KiB
YAML
65 lines
1.8 KiB
YAML
id: golden-02-delegation-test
|
|
name: "Golden 02: Delegation Test - Parent & Child Agent"
|
|
description: |
|
|
Tests multi-agent delegation workflow.
|
|
|
|
This test validates:
|
|
- Agent can delegate to a subagent using task tool
|
|
- Subagent receives context and responds correctly
|
|
- Multi-agent logging captures both sessions
|
|
- Parent-child communication works
|
|
|
|
Expected completion time: 25-35 seconds (includes LLM inference for both agents)
|
|
|
|
This is more complex than the minimal smoke test because:
|
|
- Tests delegation (core feature of agent system)
|
|
- Runs TWO agents (parent + child)
|
|
- Tests context passing
|
|
- Validates multi-agent logging system
|
|
category: developer
|
|
|
|
prompts:
|
|
- text: |
|
|
Call the simple-responder subagent and ask it to respond. Use the task tool to delegate.
|
|
|
|
- text: |
|
|
Yes, proceed with the delegation.
|
|
delayMs: 2000
|
|
|
|
approvalStrategy:
|
|
type: auto-approve
|
|
|
|
behavior:
|
|
mustUseTools: [task]
|
|
minToolCalls: 1
|
|
maxToolCalls: 10
|
|
requiresApproval: false # This is a simple test, no approval ceremony needed
|
|
expectedAgent: "openagent" # Validate correct agent is loaded
|
|
expectedModel: "opencode/big-pickle" # Validate correct model is used
|
|
expectedResponse:
|
|
contains:
|
|
- "AWESOME TESTING"
|
|
description: "Subagent should respond with 'AWESOME TESTING'"
|
|
|
|
expectedViolations:
|
|
- rule: approval-gate
|
|
shouldViolate: false
|
|
severity: error
|
|
description: "Should request approval before delegation"
|
|
- rule: context-loading
|
|
shouldViolate: false
|
|
severity: warning
|
|
description: "Should load delegation context"
|
|
- rule: delegation
|
|
shouldViolate: false
|
|
severity: error
|
|
description: "Should successfully delegate to subagent using task tool"
|
|
|
|
timeout: 90000
|
|
|
|
tags:
|
|
- golden
|
|
- delegation
|
|
- subagent
|
|
- multi-agent
|
|
- parent-child
|