ewilliams28/turnstone
1
0
Fork 0
mirror of https://github.com/turnstonelabs/turnstone.git synced 2026-08-12 23:12:23 -06:00
Code Issues Packages Projects Releases Wiki Activity

feat(console): Always-on thinking-mode option in the model form

Browse Source 
Post effort-knob rework, "Enabled" (manual) means knob-controlled —
effort none turns thinking off. Operators who want the pre-#771
always-on behavior (knob never disables) previously had to hand-write
thinking_mode "adaptive" into the raw capabilities JSON. The dropdown
now offers all three representable modes — None / Effort-knob
controlled / Always on — and the edit-load lift captures adaptive
instead of relegating it to raw JSON.
This commit is contained in:
Patrick Buckley
2026-07-04 01:19:24 -07:00
parent d564cee43d
commit c64dc16319
3 changed files with 18 additions and 15 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/architecture.md
+9 -8
View File
@@ -807,14 +807,15 @@ the levers live in the chat template, reached through
`chat_template_kwargs` in the request body. Two channels, dynamic first:
* **Session effort knob (dynamic).** Set the model's thinking mode to
Enabled in the admin Models form (or `thinking_mode = "manual"` +
`thinking_param` under `[models.*.capabilities]`) and the provider
maps the session's reasoning-effort knob onto the template toggle
per-request: effort `none` sends `{<thinking_param>: false}`, any
other level sends `true` — the same contract as the real lane's
manual mode. (`thinking_mode = "adaptive"` instead always sends
`true`: adaptive means the model self-regulates, so the knob never
force-disables — mirroring the native adaptive branch.) Templates
"Effort-knob controlled" in the admin Models form (or
`thinking_mode = "manual"` + `thinking_param` under
`[models.*.capabilities]`) and the provider maps the session's
reasoning-effort knob onto the template toggle per-request: effort
`none` sends `{<thinking_param>: false}`, any other level sends
`true` — the same contract as the real lane's manual mode. ("Always
on" / `thinking_mode = "adaptive"` instead always sends `true`: the
model self-regulates, so the knob never force-disables — mirroring
the native adaptive branch.) Templates
with a graded effort key (gpt-oss-style) additionally set
`effort_param` (e.g. `"reasoning_effort"`), plus optional
`reasoning_effort_values` / `default_reasoning_effort` to validate