forkless/strix
1
0
Fork 0
mirror of https://github.com/usestrix/strix.git synced 2026-08-25 20:32:38 +02:00
Code Issues Packages Projects Releases Wiki Activity

Restore technical detail in OSS docs

Browse Source
This commit is contained in:
Alex Schapiro
2026-08-14 18:00:29 +00:00
parent 2bc86902a4
commit b79483c6b7
10 changed files with 41 additions and 23 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/llm-providers/local.mdx
+4 -4
View File
@@ -17,7 +17,7 @@ Running Strix with local models allows for completely offline, privacy-first sec
<Note>
Strix requires advanced agent capabilities, including tool use, multi-step planning, and self-correction. Most local models under 70B parameters struggle with these tasks.
Critical assessments often require capable cloud models. Local models suit assessments where privacy has priority.
Critical assessments often require capable cloud models, such as Claude 4.5 Sonnet or GPT-5. Local models suit assessments where privacy has priority.
</Note>
## Ollama
@@ -92,9 +92,9 @@ Configure the inference server to parse tool tokens into structured `tool_calls`
- Set a low temperature, such as `--temp 0.2`, to improve tool-call reliability.
**Ollama**
- Use a recent Ollama version and a model whose template supports tools. Ollama refuses tools 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`.
- Raise **`num_ctx`** to at least 16k. Strix sends a large system prompt and many tool schemas. A small context can truncate the tool definitions and stop valid calls.
- 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.
**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.