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
7 changes: 7 additions & 0 deletions coding-agent/data/eval/golden/parent-child-subagent-001.jsonl
Original file line number Diff line number Diff line change
@@ -0,0 +1,7 @@
{"id":"parent-user","kind":"message","payload":{"role":"user","content":"parent task"},"timestamp":1700000101.0}
{"id":"parent-tool-call","kind":"tool_call","payload":{"id":"tc-subagent","name":"subagent","arguments":{"goal":"child task"}},"timestamp":1700000102.0}
{"id":"child-user","kind":"message","payload":{"role":"user","content":"child task"},"timestamp":1700000103.0,"meta":{"skip_context":true,"subagent_child":true}}
{"id":"child-assistant","kind":"message","payload":{"role":"assistant","content":"child done"},"timestamp":1700000104.0,"meta":{"skip_context":true,"subagent_child":true}}
{"id":"child-note","kind":"message","payload":{"role":"assistant","content":"child hidden note"},"timestamp":1700000105.0,"meta":{"skip_context":true,"subagent_child":true}}
{"id":"parent-tool-result","kind":"tool_result","payload":{"tool_call_id":"tc-subagent","content":"Subagent completed: child done"},"timestamp":1700000106.0}
{"id":"parent-assistant","kind":"message","payload":{"role":"assistant","content":"parent done"},"timestamp":1700000107.0}
11 changes: 11 additions & 0 deletions coding-agent/data/eval/golden/parent-child-subagent-001.yaml
Original file line number Diff line number Diff line change
@@ -0,0 +1,11 @@
task: "Run a child task and report back to the parent"

expected_tools:
- name: "subagent"
input_parameters:
goal: "child task"

forbidden_tools:
- "bash_run"

threshold: 1.0
Loading