forkless/strix
1
0
Fork 0
mirror of https://github.com/usestrix/strix.git synced 2026-08-23 03:12:37 +02:00
Code Issues Packages Projects Releases Wiki Activity

Clarify introduction wording and Ollama context guidance

Browse Source
This commit is contained in:
Alex Schapiro
2026-08-14 18:01:10 +00:00
parent b79483c6b7
commit 067597cfdb
2 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/llm-providers/local.mdx
+1 -1
View File
@@ -94,7 +94,7 @@ Configure the inference server to parse tool tokens into structured `tool_calls`
**Ollama**
- Use a recent Ollama version and a model whose template supports tools. Ollama returns `tools param requires --jinja flag` when the template lacks tool support.
- For reasoning models such as qwen3, disable **thinking** mode. Thinking mode can move tool calls into `content` instead of `tool_calls`. Disable it in Ollama with a non-thinking model or `think: false` in the model parameters or `Modelfile`.
- Raise **`num_ctx`** to at least 16k to 32k. Strix sends a large system prompt and many tool schemas. A small context can truncate the tool definitions and stop valid calls. A short test prompt can look fine while a real scan fails.
- Raise **`num_ctx`** to a value between 16k and 32k, or higher. Strix sends a large system prompt and many tool schemas. A small context can truncate the tool definitions and stop valid calls. A short test prompt can look fine while a real scan fails.
**vLLM**
- Start with `--enable-auto-tool-choice`, a matching `--tool-call-parser` (`hermes`, `qwen3_xml`, or `llama3_json`), and a matching `--reasoning-parser` for reasoning models.