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]>
41 lines
1.6 KiB
Python
41 lines
1.6 KiB
Python
"""Send request.json to Kai with the hanzoai SDK and check each answer against expect.json."""
|
|
import json
|
|
import os
|
|
import sys
|
|
from pathlib import Path
|
|
|
|
from hanzoai.cloud import ApiClient, Configuration
|
|
from hanzoai.cloud.api import AiApi
|
|
from hanzoai.cloud.models.ai_decisions_request import AiDecisionsRequest
|
|
|
|
here = Path(__file__).parent
|
|
body = json.loads((here / "request.json").read_text())
|
|
body["model"] = os.environ.get("KAI_MODEL", body["model"])
|
|
expect = json.loads((here / "expect.json").read_text())
|
|
|
|
ai = AiApi(ApiClient(Configuration(access_token=os.environ["HANZO_API_KEY"])))
|
|
decision = ai.post_decisions(AiDecisionsRequest.from_dict(body))
|
|
print(f"{decision.id} {decision.model}: {decision.usage.input_tokens} input tokens, {decision.latency_ms:.0f} ms")
|
|
|
|
wrong = 0
|
|
for name in sorted(set(expect) - set(decision.answers)):
|
|
wrong += 1
|
|
print(f" FAIL {name}: expected an answer, got none")
|
|
for name, a in decision.answers.items():
|
|
if a.type == "noul":
|
|
got, said = a.noul > 0.5, f"P(true) {a.noul:.3f}"
|
|
elif a.type == "score":
|
|
top = max(a.probabilities, key=a.probabilities.get)
|
|
got, said = int(top), f"level {top} '{a.legend[top]}' at {a.probabilities[top]:.3f} (score {a.score:.2f})"
|
|
else:
|
|
got, said = a.choice, f"{a.choice} at {a.answer_confidence:.3f}"
|
|
want = expect.get(name)
|
|
if want is None:
|
|
print(f" ---- {name}: {said} (not checked: no obvious answer on this input)")
|
|
elif got == want if isinstance(want, bool) else got in want:
|
|
print(f" pass {name}: {said}")
|
|
else:
|
|
wrong += 1
|
|
print(f" FAIL {name}: {said}, expected {want}")
|
|
sys.exit(1 if wrong else 0)
|