mirror of
https://github.com/turnstonelabs/turnstone.git
synced 2026-08-16 00:42:28 -06:00
Patrick Buckley
f4701bf0f9
The Gemini effort fix (ee9e9c1f) adds a flat reasoning_effort to every
Google chat-completions request at the session default knob — the
golden fixtures now carry it. Only the eight google__* goldens change
(one added key each); other providers' goldens are untouched — the
UPDATE_WIRE_GOLDENS pass also wanted to rewrite twelve passing goldens
with escape-format-only churn (raw em-dash vs \u2014), reverted to
keep the diff semantic.
25 lines
428 B
JSON
25 lines
428 B
JSON
{
|
|
"max_tokens": 4096,
|
|
"messages": [
|
|
{
|
|
"content": "Hi there.",
|
|
"role": "user"
|
|
},
|
|
{
|
|
"content": "Hello! How can I help?",
|
|
"role": "assistant"
|
|
},
|
|
{
|
|
"content": "What's the weather in Paris?",
|
|
"role": "user"
|
|
}
|
|
],
|
|
"model": "gemini-2.5-pro",
|
|
"reasoning_effort": "medium",
|
|
"stream": true,
|
|
"stream_options": {
|
|
"include_usage": true
|
|
},
|
|
"temperature": 0.5
|
|
}
|