salvacybersec/strix
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

chore: update default model to gpt-5.4 and remove Strix Router from docs

Browse Source 
- Change default model from gpt-5 to gpt-5.4 across docs, tests, and examples
- Remove Strix Router references from docs, quickstart, overview, and README
- Delete models.mdx (Strix Router page) and its nav entry
- Simplify install script to suggest openai/ prefix directly
- Keep strix/ model routing support intact in code

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
0xallam
2026-03-22 20:32:53 -07:00
committed by Ahmed Allam
parent b6a0a949a3
commit a2f1aae5ed
18 changed files with 40 additions and 147 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
CONTRIBUTING.md
View File

@@ -30,7 +30,7 @@ Thank you for your interest in contributing to Strix! This guide will help you g
3. **Configure your LLM provider** 3. **Configure your LLM provider**
```bash ```bash
export STRIX_LLM="openai/gpt-5" export STRIX_LLM="openai/gpt-5.4"
export LLM_API_KEY="your-api-key" export LLM_API_KEY="your-api-key"
``` ```

10
README.md
View File

@@ -73,9 +73,7 @@ Strix are autonomous AI agents that act just like real hackers - they run your c
**Prerequisites:** **Prerequisites:**
- Docker (running) - Docker (running)
- An LLM API key: - An LLM API key from any [supported provider](https://docs.strix.ai/llm-providers/overview) (OpenAI, Anthropic, Google, etc.)
- Any [supported provider](https://docs.strix.ai/llm-providers/overview) (OpenAI, Anthropic, Google, etc.)
- Or [Strix Router](https://models.strix.ai) — single API key for multiple providers
### Installation & First Scan ### Installation & First Scan
@@ -84,7 +82,7 @@ Strix are autonomous AI agents that act just like real hackers - they run your c
curl -sSL https://strix.ai/install | bash curl -sSL https://strix.ai/install | bash
# Configure your AI provider # Configure your AI provider
export STRIX_LLM="openai/gpt-5" # or "strix/gpt-5" via Strix Router (https://models.strix.ai) export STRIX_LLM="openai/gpt-5.4"
export LLM_API_KEY="your-api-key" export LLM_API_KEY="your-api-key"
# Run your first security assessment # Run your first security assessment
@@ -215,7 +213,7 @@ jobs:
### Configuration ### Configuration
```bash ```bash
export STRIX_LLM="openai/gpt-5" export STRIX_LLM="openai/gpt-5.4"
export LLM_API_KEY="your-api-key" export LLM_API_KEY="your-api-key"
# Optional # Optional
@@ -229,7 +227,7 @@ export STRIX_REASONING_EFFORT="high" # control thinking effort (default: high,
**Recommended models for best results:** **Recommended models for best results:**
- [OpenAI GPT-5](https://openai.com/api/) — `openai/gpt-5` - [OpenAI GPT-5.4](https://openai.com/api/) — `openai/gpt-5.4`
- [Anthropic Claude Sonnet 4.6](https://claude.com/platform/api) — `anthropic/claude-sonnet-4-6` - [Anthropic Claude Sonnet 4.6](https://claude.com/platform/api) — `anthropic/claude-sonnet-4-6`
- [Google Gemini 3 Pro Preview](https://cloud.google.com/vertex-ai) — `vertex_ai/gemini-3-pro-preview` - [Google Gemini 3 Pro Preview](https://cloud.google.com/vertex-ai) — `vertex_ai/gemini-3-pro-preview`

6
docs/advanced/configuration.mdx
View File

@@ -8,7 +8,7 @@ Configure Strix using environment variables or a config file.
## LLM Configuration ## LLM Configuration
<ParamField path="STRIX_LLM" type="string" required> <ParamField path="STRIX_LLM" type="string" required>
Model name in LiteLLM format (e.g., `openai/gpt-5`, `anthropic/claude-sonnet-4-6`). Model name in LiteLLM format (e.g., `openai/gpt-5.4`, `anthropic/claude-sonnet-4-6`).
</ParamField> </ParamField>
<ParamField path="LLM_API_KEY" type="string"> <ParamField path="LLM_API_KEY" type="string">
@@ -114,7 +114,7 @@ strix --target ./app --config /path/to/config.json
```json ```json
{ {
"env": { "env": {
"STRIX_LLM": "openai/gpt-5", "STRIX_LLM": "openai/gpt-5.4",
"LLM_API_KEY": "sk-...", "LLM_API_KEY": "sk-...",
"STRIX_REASONING_EFFORT": "high" "STRIX_REASONING_EFFORT": "high"
} }
@@ -125,7 +125,7 @@ strix --target ./app --config /path/to/config.json
```bash ```bash
# Required # Required
export STRIX_LLM="openai/gpt-5" export STRIX_LLM="openai/gpt-5.4"
export LLM_API_KEY="sk-..." export LLM_API_KEY="sk-..."
# Optional: Enable web search # Optional: Enable web search

2
docs/contributing.mdx
View File

@@ -32,7 +32,7 @@ description: "Contribute to Strix development"
</Step> </Step>
<Step title="Configure LLM"> <Step title="Configure LLM">
```bash ```bash
export STRIX_LLM="openai/gpt-5" export STRIX_LLM="openai/gpt-5.4"
export LLM_API_KEY="your-api-key" export LLM_API_KEY="your-api-key"
``` ```
</Step> </Step>

1
docs/docs.json
View File

@@ -32,7 +32,6 @@
"group": "LLM Providers", "group": "LLM Providers",
"pages": [ "pages": [
"llm-providers/overview", "llm-providers/overview",
"llm-providers/models",
"llm-providers/openai", "llm-providers/openai",
"llm-providers/anthropic", "llm-providers/anthropic",
"llm-providers/openrouter", "llm-providers/openrouter",

2
docs/index.mdx
View File

@@ -78,7 +78,7 @@ Strix uses a graph of specialized agents for comprehensive security testing:
curl -sSL https://strix.ai/install | bash curl -sSL https://strix.ai/install | bash
# Configure # Configure
export STRIX_LLM="openai/gpt-5" export STRIX_LLM="openai/gpt-5.4"
export LLM_API_KEY="your-api-key" export LLM_API_KEY="your-api-key"
# Scan # Scan

2
docs/integrations/github-actions.mdx
View File

@@ -35,7 +35,7 @@ Add these secrets to your repository:
| Secret | Description | | Secret | Description |
|--------|-------------| |--------|-------------|
| `STRIX_LLM` | Model name (e.g., `openai/gpt-5`) | | `STRIX_LLM` | Model name (e.g., `openai/gpt-5.4`) |
| `LLM_API_KEY` | API key for your LLM provider | | `LLM_API_KEY` | API key for your LLM provider |
## Exit Codes ## Exit Codes

2
docs/llm-providers/anthropic.mdx
View File

@@ -6,7 +6,7 @@ description: "Configure Strix with Claude models"
## Setup ## Setup
```bash ```bash
export STRIX_LLM="openai/gpt-5" export STRIX_LLM="openai/gpt-5.4"
export LLM_API_KEY="sk-ant-..." export LLM_API_KEY="sk-ant-..."
``` ```

4
docs/llm-providers/azure.mdx
View File

@@ -24,7 +24,7 @@ export AZURE_API_VERSION="2025-11-01-preview"
## Example ## Example
```bash ```bash
export STRIX_LLM="azure/gpt-5-deployment" export STRIX_LLM="azure/gpt-5.4-deployment"
export AZURE_API_KEY="abc123..." export AZURE_API_KEY="abc123..."
export AZURE_API_BASE="https://mycompany.openai.azure.com" export AZURE_API_BASE="https://mycompany.openai.azure.com"
export AZURE_API_VERSION="2025-11-01-preview" export AZURE_API_VERSION="2025-11-01-preview"
@@ -33,5 +33,5 @@ export AZURE_API_VERSION="2025-11-01-preview"
## Prerequisites ## Prerequisites
1. Create an Azure OpenAI resource 1. Create an Azure OpenAI resource
2. Deploy a model (e.g., GPT-5) 2. Deploy a model (e.g., GPT-5.4)
3. Get the endpoint URL and API key from the Azure portal 3. Get the endpoint URL and API key from the Azure portal

75
docs/llm-providers/models.mdx
View File

@@ -1,75 +0,0 @@
---
title: "Strix Router"
description: "Access top LLMs through a single API with high rate limits and zero data retention"
---
Strix Router gives you access to the best LLMs through a single API key.
<Note>
Strix Router is currently in **beta**. It's completely optional — Strix works with any [LiteLLM-compatible provider](/llm-providers/overview) using your own API keys, or with [local models](/llm-providers/local). Strix Router is just the setup we test and optimize for.
</Note>
## Why Use Strix Router?
- **High rate limits** — No throttling during long-running scans
- **Zero data retention** — Routes to providers with zero data retention policies enabled
- **Failover & load balancing** — Automatic fallback across providers for reliability
- **Simple setup** — One API key, one environment variable, no provider accounts needed
- **No markup** — Same token pricing as the underlying providers, no extra fees
## Quick Start
1. Get your API key at [models.strix.ai](https://models.strix.ai)
2. Set your environment:
```bash
export LLM_API_KEY='your-strix-api-key'
export STRIX_LLM='strix/gpt-5'
```
3. Run a scan:
```bash
strix --target ./your-app
```
## Available Models
### Anthropic
| Model | ID |
|-------|-----|
| Claude Sonnet 4.6 | `strix/claude-sonnet-4.6` |
| Claude Opus 4.6 | `strix/claude-opus-4.6` |
### OpenAI
| Model | ID |
|-------|-----|
| GPT-5.2 | `strix/gpt-5.2` |
| GPT-5.1 | `strix/gpt-5.1` |
| GPT-5 | `strix/gpt-5` |
### Google
| Model | ID |
|-------|-----|
| Gemini 3 Pro | `strix/gemini-3-pro-preview` |
| Gemini 3 Flash | `strix/gemini-3-flash-preview` |
### Other
| Model | ID |
|-------|-----|
| GLM-5 | `strix/glm-5` |
| GLM-4.7 | `strix/glm-4.7` |
## Configuration Reference
<ParamField path="LLM_API_KEY" type="string" required>
Your Strix API key from [models.strix.ai](https://models.strix.ai).
</ParamField>
<ParamField path="STRIX_LLM" type="string" required>
Model ID from the tables above. Must be prefixed with `strix/`.
</ParamField>

4
docs/llm-providers/openai.mdx
View File

@@ -6,7 +6,7 @@ description: "Configure Strix with OpenAI models"
## Setup ## Setup
```bash ```bash
export STRIX_LLM="openai/gpt-5" export STRIX_LLM="openai/gpt-5.4"
export LLM_API_KEY="sk-..." export LLM_API_KEY="sk-..."
``` ```
@@ -25,7 +25,7 @@ See [OpenAI Models Documentation](https://platform.openai.com/docs/models) for t
For OpenAI-compatible APIs: For OpenAI-compatible APIs:
```bash ```bash
export STRIX_LLM="openai/gpt-5" export STRIX_LLM="openai/gpt-5.4"
export LLM_API_KEY="your-key" export LLM_API_KEY="your-key"
export LLM_API_BASE="https://your-proxy.com/v1" export LLM_API_BASE="https://your-proxy.com/v1"
``` ```

4
docs/llm-providers/openrouter.mdx
View File

@@ -8,7 +8,7 @@ description: "Configure Strix with models via OpenRouter"
## Setup ## Setup
```bash ```bash
export STRIX_LLM="openrouter/openai/gpt-5" export STRIX_LLM="openrouter/openai/gpt-5.4"
export LLM_API_KEY="sk-or-..." export LLM_API_KEY="sk-or-..."
``` ```
@@ -18,7 +18,7 @@ Access any model on OpenRouter using the format `openrouter/<provider>/<model>`:
| Model | Configuration | | Model | Configuration |
|-------|---------------| |-------|---------------|
| GPT-5 | `openrouter/openai/gpt-5` | | GPT-5.4 | `openrouter/openai/gpt-5.4` |
| Claude Sonnet 4.6 | `openrouter/anthropic/claude-sonnet-4.6` | | Claude Sonnet 4.6 | `openrouter/anthropic/claude-sonnet-4.6` |
| Gemini 3 Pro | `openrouter/google/gemini-3-pro-preview` | | Gemini 3 Pro | `openrouter/google/gemini-3-pro-preview` |
| GLM-4.7 | `openrouter/z-ai/glm-4.7` | | GLM-4.7 | `openrouter/z-ai/glm-4.7` |

28
docs/llm-providers/overview.mdx
View File

@@ -5,29 +5,18 @@ description: "Configure your AI model for Strix"
Strix uses [LiteLLM](https://docs.litellm.ai/docs/providers) for model compatibility, supporting 100+ LLM providers. Strix uses [LiteLLM](https://docs.litellm.ai/docs/providers) for model compatibility, supporting 100+ LLM providers.
## Strix Router (Recommended) ## Configuration
The fastest way to get started. [Strix Router](/llm-providers/models) gives you access to tested models with the highest rate limits and zero data retention. Set your model and API key:
```bash
export STRIX_LLM="strix/gpt-5"
export LLM_API_KEY="your-strix-api-key"
```
Get your API key at [models.strix.ai](https://models.strix.ai).
## Bring Your Own Key
You can also use any LiteLLM-compatible provider with your own API keys:
| Model | Provider | Configuration | | Model | Provider | Configuration |
| ----------------- | ------------- | -------------------------------- | | ----------------- | ------------- | -------------------------------- |
| GPT-5 | OpenAI | `openai/gpt-5` | | GPT-5.4 | OpenAI | `openai/gpt-5.4` |
| Claude Sonnet 4.6 | Anthropic | `anthropic/claude-sonnet-4-6` | | Claude Sonnet 4.6 | Anthropic | `anthropic/claude-sonnet-4-6` |
| Gemini 3 Pro | Google Vertex | `vertex_ai/gemini-3-pro-preview` | | Gemini 3 Pro | Google Vertex | `vertex_ai/gemini-3-pro-preview` |
```bash ```bash
export STRIX_LLM="openai/gpt-5" export STRIX_LLM="openai/gpt-5.4"
export LLM_API_KEY="your-api-key" export LLM_API_KEY="your-api-key"
``` ```
@@ -45,11 +34,8 @@ See the [Local Models guide](/llm-providers/local) for setup instructions and re
## Provider Guides ## Provider Guides
<CardGroup cols={2}> <CardGroup cols={2}>
<Card title="Strix Router" href="/llm-providers/models">
Recommended models router with high rate limits.
</Card>
<Card title="OpenAI" href="/llm-providers/openai"> <Card title="OpenAI" href="/llm-providers/openai">
GPT-5 models. GPT-5.4 models.
</Card> </Card>
<Card title="Anthropic" href="/llm-providers/anthropic"> <Card title="Anthropic" href="/llm-providers/anthropic">
Claude Opus, Sonnet, and Haiku. Claude Opus, Sonnet, and Haiku.
@@ -64,7 +50,7 @@ See the [Local Models guide](/llm-providers/local) for setup instructions and re
Claude and Titan models via AWS. Claude and Titan models via AWS.
</Card> </Card>
<Card title="Azure OpenAI" href="/llm-providers/azure"> <Card title="Azure OpenAI" href="/llm-providers/azure">
GPT-5 via Azure. GPT-5.4 via Azure.
</Card> </Card>
<Card title="Local Models" href="/llm-providers/local"> <Card title="Local Models" href="/llm-providers/local">
Llama 4, Mistral, and self-hosted models. Llama 4, Mistral, and self-hosted models.
@@ -76,7 +62,7 @@ See the [Local Models guide](/llm-providers/local) for setup instructions and re
Use LiteLLM's `provider/model-name` format: Use LiteLLM's `provider/model-name` format:
``` ```
openai/gpt-5 openai/gpt-5.4
anthropic/claude-sonnet-4-6 anthropic/claude-sonnet-4-6
vertex_ai/gemini-3-pro-preview vertex_ai/gemini-3-pro-preview
bedrock/anthropic.claude-4-5-sonnet-20251022-v1:0 bedrock/anthropic.claude-4-5-sonnet-20251022-v1:0

16
docs/quickstart.mdx
View File

@@ -6,7 +6,7 @@ description: "Install Strix and run your first security scan"
## Prerequisites ## Prerequisites
- Docker (running) - Docker (running)
- An LLM API key — use [Strix Router](/llm-providers/models) for the easiest setup, or bring your own key from any [supported provider](/llm-providers/overview) - An LLM API key from any [supported provider](/llm-providers/overview) (OpenAI, Anthropic, Google, etc.)
## Installation ## Installation
@@ -27,23 +27,13 @@ description: "Install Strix and run your first security scan"
Set your LLM provider: Set your LLM provider:
<Tabs>
<Tab title="Strix Router">
```bash ```bash
export STRIX_LLM="strix/gpt-5" export STRIX_LLM="openai/gpt-5.4"
export LLM_API_KEY="your-strix-api-key"
```
</Tab>
<Tab title="Bring Your Own Key">
```bash
export STRIX_LLM="openai/gpt-5"
export LLM_API_KEY="your-api-key" export LLM_API_KEY="your-api-key"
``` ```
</Tab>
</Tabs>
<Tip> <Tip>
For best results, use `strix/gpt-5`, `strix/claude-opus-4.6`, or `strix/gpt-5.2`. For best results, use `openai/gpt-5.4`, `anthropic/claude-opus-4-6`, or `openai/gpt-5.2`.
</Tip> </Tip>
## Run Your First Scan ## Run Your First Scan

9
scripts/install.sh
View File

@@ -335,14 +335,11 @@ echo -e "${MUTED} AI Penetration Testing Agent${NC}"
echo "" echo ""
echo -e "${MUTED}To get started:${NC}" echo -e "${MUTED}To get started:${NC}"
echo "" echo ""
echo -e " ${CYAN}1.${NC} Get your Strix API key:" echo -e " ${CYAN}1.${NC} Set your environment:"
echo -e " ${MUTED}https://models.strix.ai${NC}"
echo ""
echo -e " ${CYAN}2.${NC} Set your environment:"
echo -e " ${MUTED}export LLM_API_KEY='your-api-key'${NC}" echo -e " ${MUTED}export LLM_API_KEY='your-api-key'${NC}"
echo -e " ${MUTED}export STRIX_LLM='strix/gpt-5'${NC}" echo -e " ${MUTED}export STRIX_LLM='openai/gpt-5.4'${NC}"
echo "" echo ""
echo -e " ${CYAN}3.${NC} Run a penetration test:" echo -e " ${CYAN}2.${NC} Run a penetration test:"
echo -e " ${MUTED}strix --target https://example.com${NC}" echo -e " ${MUTED}strix --target https://example.com${NC}"
echo "" echo ""
echo -e "${MUTED}For more information visit ${NC}https://strix.ai" echo -e "${MUTED}For more information visit ${NC}https://strix.ai"

7
strix/interface/main.py
View File

@@ -101,7 +101,7 @@ def validate_environment() -> None: # noqa: PLR0912, PLR0915
error_text.append("• ", style="white") error_text.append("• ", style="white")
error_text.append("STRIX_LLM", style="bold cyan") error_text.append("STRIX_LLM", style="bold cyan")
error_text.append( error_text.append(
" - Model name to use with litellm (e.g., 'openai/gpt-5')\n", " - Model name to use with litellm (e.g., 'openai/gpt-5.4')\n",
style="white", style="white",
) )
@@ -140,10 +140,7 @@ def validate_environment() -> None: # noqa: PLR0912, PLR0915
) )
error_text.append("\nExample setup:\n", style="white") error_text.append("\nExample setup:\n", style="white")
if uses_strix_models: error_text.append("export STRIX_LLM='openai/gpt-5.4'\n", style="dim white")
error_text.append("export STRIX_LLM='strix/gpt-5'\n", style="dim white")
else:
error_text.append("export STRIX_LLM='openai/gpt-5'\n", style="dim white")
if missing_optional_vars: if missing_optional_vars:
for var in missing_optional_vars: for var in missing_optional_vars:

2
strix/llm/utils.py
View File

@@ -36,7 +36,7 @@ STRIX_MODEL_MAP: dict[str, str] = {
"claude-opus-4.6": "anthropic/claude-opus-4-6", "claude-opus-4.6": "anthropic/claude-opus-4-6",
"gpt-5.2": "openai/gpt-5.2", "gpt-5.2": "openai/gpt-5.2",
"gpt-5.1": "openai/gpt-5.1", "gpt-5.1": "openai/gpt-5.1",
"gpt-5": "openai/gpt-5", "gpt-5.4": "openai/gpt-5.4",
"gemini-3-pro-preview": "gemini/gemini-3-pro-preview", "gemini-3-pro-preview": "gemini/gemini-3-pro-preview",
"gemini-3-flash-preview": "gemini/gemini-3-flash-preview", "gemini-3-flash-preview": "gemini/gemini-3-flash-preview",
"glm-5": "openrouter/z-ai/glm-5", "glm-5": "openrouter/z-ai/glm-5",

5
tests/llm/test_llm_otel.py
View File

@@ -1,15 +1,16 @@
import litellm import litellm
import pytest
from strix.llm.config import LLMConfig from strix.llm.config import LLMConfig
from strix.llm.llm import LLM from strix.llm.llm import LLM
def test_llm_does_not_modify_litellm_callbacks(monkeypatch) -> None: def test_llm_does_not_modify_litellm_callbacks(monkeypatch: pytest.MonkeyPatch) -> None:
monkeypatch.setenv("STRIX_TELEMETRY", "1") monkeypatch.setenv("STRIX_TELEMETRY", "1")
monkeypatch.setenv("STRIX_OTEL_TELEMETRY", "1") monkeypatch.setenv("STRIX_OTEL_TELEMETRY", "1")
monkeypatch.setattr(litellm, "callbacks", ["custom-callback"]) monkeypatch.setattr(litellm, "callbacks", ["custom-callback"])
llm = LLM(LLMConfig(model_name="openai/gpt-5"), agent_name=None) llm = LLM(LLMConfig(model_name="openai/gpt-5.4"), agent_name=None)
assert llm is not None assert llm is not None
assert litellm.callbacks == ["custom-callback"] assert litellm.callbacks == ["custom-callback"]