openclaw/docs
openclaw/docs
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

chore(sync): mirror docs from openclaw/openclaw@8f262211ee

Browse Source
This commit is contained in:
openclaw-docs-sync[bot] 2026-04-27 09:52:13 +00:00
parent e0d3b000eb
commit 4cc4ed2c21
2 changed files with 5 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
.openclaw-sync/source.json
View File

@ -1,5 +1,5 @@
{
"repository": "openclaw/openclaw",
"sha": "7dc9a367efc1c154c84249c209cabbe692d8d086",
"syncedAt": "2026-04-27T09:47:35.512Z"
"sha": "8f262211ee8fdd7226357a38ba609cecd8451681",
"syncedAt": "2026-04-27T09:50:44.776Z"
}

4
docs/providers/ollama.md
View File

@ -415,6 +415,7 @@ Use these as starting points and replace model IDs with the exact names from `ol
input: ["text"],
params: {
num_ctx: 32768,
thinking: false,
keep_alive: "15m",
},
},
@ -585,6 +586,7 @@ Use these as starting points and replace model IDs with the exact names from `ol
```
Use `compat.supportsTools: false` only when the model or server reliably fails on tool schemas. It trades agent capability for stability.
`localModelLean` removes the browser, cron, and message tools from the agent surface, but it does not change Ollama's runtime context or thinking mode. Pair it with explicit `params.num_ctx` and `params.thinking: false` for small Qwen-style thinking models that loop or spend their response budget on hidden reasoning.
</Accordion>
</AccordionGroup>
@ -1012,7 +1014,7 @@ For the full setup and behavior details, see [Ollama Web Search](/tools/ollama-s
{
id: "qwen3.5:9b",
name: "qwen3.5:9b",
params: { num_ctx: 32768 },
params: { num_ctx: 32768, thinking: false },
},
],
},