vultr/openclaw
1
0
Fork 0
mirror of https://github.com/openclaw/openclaw.git synced 2026-05-06 18:50:42 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix(ollama): honor configured num_ctx params

Browse Source
This commit is contained in:
Peter Steinberger
2026-04-27 03:02:12 +01:00
parent fc3abc139b
commit 2dba9e6a76
13 changed files with 305 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
docs/providers/ollama.md
View File

@@ -401,7 +401,7 @@ For the full setup and behavior details, see [Ollama Web Search](/tools/ollama-s
<Accordion title="Context windows">
For auto-discovered models, OpenClaw uses the context window reported by Ollama when available, including larger `PARAMETER num_ctx` values from custom Modelfiles. Otherwise it falls back to the default Ollama context window used by OpenClaw.
You can override `contextWindow` and `maxTokens` in explicit provider config:
You can override `contextWindow` and `maxTokens` in explicit provider config. To cap Ollama's per-request runtime context without rebuilding a Modelfile, set `params.num_ctx`; OpenClaw sends it as `options.num_ctx` for both native Ollama and the OpenAI-compatible Ollama adapter. Invalid, zero, negative, and non-finite values are ignored and fall back to `contextWindow`.
```json5
{
@@ -413,6 +413,9 @@ For the full setup and behavior details, see [Ollama Web Search](/tools/ollama-s
id: "llama3.3",
contextWindow: 131072,
maxTokens: 65536,
params: {
num_ctx: 32768,
},
}
]
}
@@ -421,6 +424,8 @@ For the full setup and behavior details, see [Ollama Web Search](/tools/ollama-s
}
```
Per-model `agents.defaults.models["ollama/<model>"].params.num_ctx` works too. If both are configured, the explicit provider model entry wins over the agent default.
</Accordion>
<Accordion title="Reasoning models">