mirror of
https://github.com/hanzoai/kai.git
synced 2026-10-17 11:18:06 +00:00
zooqueenandHanzo Dev
b00044ece2
Every runner printed whatever came back and exited 0, and fell back to a second raw HTTP call when the SDK import failed. Now each recipe carries expect.json, the answers a careful reader gives on its own input: a list of acceptable options for a choice, of level indices for a score, true or false for a noul. run.py and run.ts send request.json through the SDK, print every answer, and exit 1 when a checked one is wrong. A question with no obvious answer on its input is printed and not checked. Recipes 09 and 11 had no input with an obvious answer, so each state gains the one fact that decides it. The recipe READMEs describe what each recipe asks instead of capabilities it never exercised, and copy the request and checked answers from the two JSON files. Co-authored-by: Hanzo Dev <[email protected]>
1.6 KiB
1.6 KiB
Agent Completion Check
Before an agent stops, ask Kai whether the work it reports covers everything the user asked for.
Request (request.json)
{
"model": "kai",
"state": {
"user_request": "Implement password reset flow with email token validation and 15-minute expiration test.",
"completed_work": [
"created /api/v1/auth/reset-password endpoint",
"token generation logic using crypto.randomBytes",
"written test for valid token verification",
"written test for expired token rejection"
],
"test_run_result": "12 tests passed, 0 failures"
},
"questions": {
"is_complete": {
"type": "noul",
"instructions": "Are all requirements in the user request satisfied?"
},
"quality_score": {
"type": "score",
"instructions": "Grade completeness and test coverage",
"criteria": [
"incomplete",
"partially implemented",
"complete with full tests"
]
}
}
}
Checked answers (expect.json)
is_complete(noul): P(true) above 0.5quality_score(score): most probable level 2complete with full tests
Run
From the repository root, after pip install -r requirements.txt and npm install:
curl -sS --fail-with-body https://api.hanzo.ai/v1/decisions \
-H "Authorization: Bearer $HANZO_API_KEY" \
-H "Content-Type: application/json" \
-d @recipes/05_agent_completion_check/request.json
python3 recipes/05_agent_completion_check/run.py
npx tsx recipes/05_agent_completion_check/run.ts
run.py and run.ts print every answer and exit 1 when a checked answer is wrong.