generated from coulomb/repo-seed
tegwick
90eb39c247
Switch the custodian triage default from anthropic/claude-sonnet-4 to google/gemini-2.5-flash, which advertises structured-output support on OpenRouter. Tighten the OpenRouter adapter to send strict JSON schema requests and set provider.require_parameters=true so routing only hits providers that honor the requested response_format. Update Kubernetes deploy docs and config for the verified coulombcore handoff: Containerfile build path, image-pull-policy=Never for smoke pods, credential-routing notes, and live smoke evidence. Mark LLM-WP-0006 finished with closure notes from 2026-06-18.
82 lines
2.3 KiB
Python
82 lines
2.3 KiB
Python
from llm_connect._payload import merge_gemini_model_params, merge_openai_chat_model_params
|
|
|
|
|
|
STRUCTURED_SCHEMA = {
|
|
"type": "object",
|
|
"properties": {
|
|
"summary": {"type": "string"},
|
|
"recommendations": {"type": "array", "items": {"type": "string"}},
|
|
},
|
|
"required": ["summary", "recommendations"],
|
|
}
|
|
|
|
|
|
ACTIVITY_CORE_MODEL_PARAMS = {
|
|
"reasoning_effort": "medium",
|
|
"max_depth": 4,
|
|
"json_schema": STRUCTURED_SCHEMA,
|
|
"top_p": 0.8,
|
|
}
|
|
|
|
|
|
def test_openai_chat_model_params_translate_activity_core_shape():
|
|
payload = {
|
|
"model": "gpt-4.1-mini",
|
|
"messages": [{"role": "user", "content": "triage"}],
|
|
"temperature": 0.2,
|
|
"max_tokens": 200,
|
|
}
|
|
|
|
merge_openai_chat_model_params(payload, ACTIVITY_CORE_MODEL_PARAMS)
|
|
|
|
assert payload["response_format"] == {
|
|
"type": "json_schema",
|
|
"json_schema": {
|
|
"name": "structured_output",
|
|
"schema": STRUCTURED_SCHEMA,
|
|
"strict": True,
|
|
},
|
|
}
|
|
assert payload["top_p"] == 0.8
|
|
assert "reasoning_effort" not in payload
|
|
assert "max_depth" not in payload
|
|
assert "json_schema" not in payload
|
|
|
|
|
|
def test_openai_chat_model_params_preserve_explicit_response_format():
|
|
explicit = {
|
|
"type": "json_schema",
|
|
"json_schema": {
|
|
"name": "custom",
|
|
"schema": STRUCTURED_SCHEMA,
|
|
"strict": True,
|
|
},
|
|
}
|
|
payload = {"model": "gpt-4.1-mini", "messages": []}
|
|
|
|
merge_openai_chat_model_params(
|
|
payload,
|
|
{"json_schema": STRUCTURED_SCHEMA, "response_format": explicit},
|
|
)
|
|
|
|
assert payload["response_format"] == explicit
|
|
|
|
|
|
def test_gemini_model_params_translate_activity_core_shape():
|
|
payload = {
|
|
"contents": [{"role": "user", "parts": [{"text": "triage"}]}],
|
|
"generationConfig": {
|
|
"temperature": 0.2,
|
|
"maxOutputTokens": 200,
|
|
},
|
|
}
|
|
|
|
merge_gemini_model_params(payload, ACTIVITY_CORE_MODEL_PARAMS)
|
|
|
|
assert payload["generationConfig"]["responseMimeType"] == "application/json"
|
|
assert payload["generationConfig"]["responseSchema"] == STRUCTURED_SCHEMA
|
|
assert payload["generationConfig"]["topP"] == 0.8
|
|
assert "reasoning_effort" not in payload
|
|
assert "max_depth" not in payload
|
|
assert "json_schema" not in payload
|