From 067597cfdbc67f8095101f487f6dcc4737dc70bf Mon Sep 17 00:00:00 2001 From: Alex Schapiro Date: Fri, 14 Aug 2026 18:01:10 +0000 Subject: [PATCH] Clarify introduction wording and Ollama context guidance --- docs/index.mdx | 2 +- docs/llm-providers/local.mdx | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/docs/index.mdx b/docs/index.mdx index 6b86503e..c3c451c8 100644 --- a/docs/index.mdx +++ b/docs/index.mdx @@ -3,7 +3,7 @@ title: "Introduction" description: "Open-source AI hackers to secure your apps" --- -Strix agents are autonomous AI agents that act like real hackers. They run your code dynamically, find vulnerabilities, and validate each vulnerability with a proof of concept. Strix helps developers and security teams that need fast and accurate security testing. They avoid the overhead of a manual pentest and the false positives of a static analysis tool. +Strix agents are autonomous and act like real hackers. They run your code dynamically, find vulnerabilities, and validate each vulnerability with a proof of concept. Strix helps developers and security teams that need fast and accurate security testing. Strix does not have the overhead of a manual pentest or the false positives of a static analysis tool. Strix Demo diff --git a/docs/llm-providers/local.mdx b/docs/llm-providers/local.mdx index e3143dba..d50208ef 100644 --- a/docs/llm-providers/local.mdx +++ b/docs/llm-providers/local.mdx @@ -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.