Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 5 additions & 0 deletions 03-evolution-case-study/iteration-1-bad/evals/agent.yaml
Original file line number Diff line number Diff line change
@@ -0,0 +1,5 @@
kind: Agent
metadata:
name: "claude-code-acp"
acp:
cmd: "claude-agent-acp"
10 changes: 5 additions & 5 deletions 03-evolution-case-study/iteration-1-bad/evals/eval.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -5,17 +5,17 @@ metadata:
config:
# Use Claude Code as the AI agent
agent:
type: "builtin.claude-code"
type: file
path: agent.yaml

# MCP server configuration
mcpConfigFile: mcp-config.yaml

# LLM judge configuration
llmJudge:
env:
baseUrlKey: JUDGE_BASE_URL
apiKeyKey: JUDGE_API_KEY
modelNameKey: JUDGE_MODEL_NAME
ref:
type: file
path: agent.yaml

# Test tasks
taskSets:
Expand Down
5 changes: 5 additions & 0 deletions 03-evolution-case-study/iteration-2-good/evals/agent.yaml
Original file line number Diff line number Diff line change
@@ -0,0 +1,5 @@
kind: Agent
metadata:
name: "claude-code-acp"
acp:
cmd: "claude-agent-acp"
10 changes: 5 additions & 5 deletions 03-evolution-case-study/iteration-2-good/evals/eval.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -5,17 +5,17 @@ metadata:
config:
# Use Claude Code as the AI agent
agent:
type: "builtin.claude-code"
type: file
path: agent.yaml

# MCP server configuration
mcpConfigFile: mcp-config.yaml

# LLM judge configuration
llmJudge:
env:
baseUrlKey: JUDGE_BASE_URL
apiKeyKey: JUDGE_API_KEY
modelNameKey: JUDGE_MODEL_NAME
ref:
type: file
path: agent.yaml

# Test tasks
taskSets:
Expand Down