mirror of
https://github.com/turnstonelabs/turnstone.git
synced 2026-08-12 23:12:23 -06:00
Patrick Buckley
530958e06b
Local lanes dropped the knob's graded value unless the operator declared
reasoning_effort_values (and, on the template channel, an effort key) —
picking Max sent a bare thinking toggle and the effort select
degenerated into seven positions that all meant 'on'. The user's
setting now always rides:
- openai-compatible: the flat reasoning_effort param carries the knob
verbatim (effort_passthrough on the lane default); declared values
still snap ordinally, and a declared effort_param still claims the
template channel and suppresses the flat param.
- anthropic-compatible: the graded value rides chat_template_kwargs
alongside the toggle whenever reasoning control is engaged — under
the operator's effort_param, else the conventional fallback key
(reasoning_effort); templates that don't reference the kwarg ignore
it. thinking_mode=none still injects nothing.
- Commercial lanes untouched: empty declared values still mean 'no
effort control' (o1-mini) and the ordinal snap is unchanged.
Golden writer now pins ensure_ascii=False: the baselines' literal em
dashes came from a hand edit (03f82521) the default-escaping writer
could never reproduce — regens no longer churn unrelated lines.
25 lines
436 B
JSON
25 lines
436 B
JSON
{
|
|
"max_completion_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": "gpt-4o-mini",
|
|
"reasoning_effort": "medium",
|
|
"stream": true,
|
|
"stream_options": {
|
|
"include_usage": true
|
|
},
|
|
"temperature": 0.5
|
|
}
|