vultr/openclaw
1
0
Fork 0
mirror of https://github.com/openclaw/openclaw.git synced 2026-05-06 12:00:44 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix: normalize LM Studio binary reasoning efforts

Browse Source
This commit is contained in:
Peter Steinberger
2026-05-02 22:46:14 +01:00
parent 9f8744b140
commit 2fd1e7b32d
5 changed files with 134 additions and 60 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
docs/providers/lmstudio.md
View File

@@ -117,10 +117,13 @@ Same streaming usage behavior applies to these OpenAI-compatible local backends:
### Thinking compatibility
When LM Studio's `/api/v1/models` discovery reports model-specific reasoning
options, OpenClaw preserves those native values in model compat metadata. For
binary thinking models that advertise `allowed_options: ["off", "on"]`,
OpenClaw maps disabled thinking to `off` and enabled `/think` levels to `on`
instead of sending OpenAI-only values such as `low` or `medium`.
options, OpenClaw exposes the matching OpenAI-compatible `reasoning_effort`
values in model compat metadata. Current LM Studio builds can advertise binary
UI options such as `allowed_options: ["off", "on"]` while rejecting those values
on `/v1/chat/completions`; OpenClaw normalizes that binary discovery shape to
`none`, `minimal`, `low`, `medium`, `high`, and `xhigh` before sending requests.
Older saved LM Studio config that contains `off`/`on` reasoning maps is
normalized the same way when the catalog is loaded.
### Explicit configuration