mirror of
https://github.com/turnstonelabs/turnstone.git
synced 2026-08-15 00:12:26 -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.
64 lines
1.2 KiB
JSON
64 lines
1.2 KiB
JSON
{
|
|
"max_tokens": 4096,
|
|
"messages": [
|
|
{
|
|
"content": "Run the deploy.",
|
|
"role": "user"
|
|
},
|
|
{
|
|
"content": "",
|
|
"role": "assistant",
|
|
"tool_calls": [
|
|
{
|
|
"function": {
|
|
"arguments": "{}",
|
|
"name": "deploy"
|
|
},
|
|
"id": "call_1",
|
|
"type": "function"
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"content": "deployed",
|
|
"role": "tool",
|
|
"tool_call_id": "call_1"
|
|
},
|
|
{
|
|
"content": "Output-guard: deploy output looked clean.",
|
|
"role": "system"
|
|
},
|
|
{
|
|
"content": "Great, what's next?",
|
|
"role": "user"
|
|
}
|
|
],
|
|
"model": "gemini-2.5-pro",
|
|
"reasoning_effort": "medium",
|
|
"stream": true,
|
|
"stream_options": {
|
|
"include_usage": true
|
|
},
|
|
"temperature": 0.5,
|
|
"tools": [
|
|
{
|
|
"function": {
|
|
"description": "Look up the weather for a city.",
|
|
"name": "get_weather",
|
|
"parameters": {
|
|
"properties": {
|
|
"city": {
|
|
"type": "string"
|
|
}
|
|
},
|
|
"required": [
|
|
"city"
|
|
],
|
|
"type": "object"
|
|
}
|
|
},
|
|
"type": "function"
|
|
}
|
|
]
|
|
}
|