mirror of
https://github.com/deepseek-ai/deepseek-harness
synced 2026-08-15 21:04:50 +00:00
93a6dc6716
Record the `todo-plan` snapshot scenario: a real prompt drives the model to call todo_write, and the golden captures the resulting `plan` sessionUpdate (three entries, priority synthesized as medium, status 1:1) plus the persisted todo/write event. Registered in SCENARIOS; replays deterministically keyless. Add a with-key coding-agent e2e that verifies the WORLD — a real model call to todo_write lands a todo/write event whose snapshot is a valid, one-in-progress list — not the agent's self-report. Wire tool-todo into the e2e harness.
8 lines
355 B
JSON
8 lines
355 B
JSON
{
|
|
"steps": [
|
|
{ "op": "initialize" },
|
|
{ "op": "newSession" },
|
|
{ "op": "prompt", "text": "Use the todo_write tool to record a plan with exactly three todos: \"read the code\" (in_progress), \"write the fix\" (pending), \"run the tests\" (pending). Send all three in one todo_write call. Then reply with the single word DONE and stop." }
|
|
]
|
|
}
|