Skip to content

armgit / strix

Public Imported from GitHub
0

Open-source AI penetration testing tool to find and fix your app’s vulnerabilities.

fix(models): keep list additions-only, restore gpt-5.4 examples, make openrouter/z-ai/glm-5.3 the top pick

Ahmed Allamb438632e1265
diff --git a/AGENTS.md b/AGENTS.md
index 8630c12b..e9039195 100644
--- a/AGENTS.md
+++ b/AGENTS.md
@@ -28,7 +28,7 @@ Target-specific workflows built on the same engine:
- **Open-source CLI (self-hosted):** free, fully local, BYO LLM key, needs Docker. Best for local dev loops, air-gapped/offline, and full control.
```bash
curl -sSL https://strix.ai/install | bash # install
- export STRIX_LLM="openai/gpt-5.6" # any LiteLLM model id
+ export STRIX_LLM="openai/gpt-5.4" # any LiteLLM model id
export LLM_API_KEY="<key>"
strix -n -t ./ --scan-mode quick --max-budget 10 # headless scan; always use -n
```
diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md
index 265943d4..23028d3e 100644
--- a/CONTRIBUTING.md
+++ b/CONTRIBUTING.md
@@ -31,7 +31,7 @@ Thank you for your interest in contributing to Strix! This guide will help you g
3. **Configure your LLM provider**
```bash
- export STRIX_LLM="openai/gpt-5.6"
+ export STRIX_LLM="openai/gpt-5.4"
export LLM_API_KEY="your-api-key"
```
diff --git a/README.md b/README.md
index 451ef370..ecf57d0f 100644
--- a/README.md
+++ b/README.md
@@ -82,7 +82,7 @@ Strix are autonomous AI penetration testing agents that act just like real hacke
curl -sSL https://strix.ai/install | bash
# Configure your AI provider
-export STRIX_LLM="openai/gpt-5.6"
+export STRIX_LLM="openai/gpt-5.4"
export LLM_API_KEY="your-api-key"
# Run your first security assessment
@@ -294,7 +294,7 @@ jobs:
### Configuration
```bash
-export STRIX_LLM="openai/gpt-5.6"
+export STRIX_LLM="openai/gpt-5.4"
export LLM_API_KEY="your-api-key"
# Optional
@@ -313,7 +313,7 @@ Instead of a metered API key, you can run Strix on your ChatGPT Plus/Pro subscri
```bash
strix auth login chatgpt # sign in with your ChatGPT account
-export STRIX_LLM="chatgpt/gpt-5.6" # chatgpt/<model> runs on the subscription
+export STRIX_LLM="chatgpt/gpt-5.4" # chatgpt/<model> runs on the subscription
strix --target ./app-directory
strix auth status # show the active sign-in
@@ -448,12 +448,12 @@ Each server's tools are namespaced by `name` (for example `local_fs_read_file`).
**Recommended models for best results:**
-- [OpenAI GPT-5.6](https://openai.com/api/) - `openai/gpt-5.6`
-- [Anthropic Claude Opus 5](https://claude.com/platform/api) - `anthropic/claude-opus-5`
-- [Google Gemini 3.1 Pro Preview](https://cloud.google.com/vertex-ai) - `vertex_ai/gemini-3.1-pro-preview`
+- [Z.ai GLM-5.3 on OpenRouter](https://openrouter.ai/z-ai/glm-5.3) - `openrouter/z-ai/glm-5.3` (our top pick)
+- [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`
+- [Google Gemini 3 Pro Preview](https://cloud.google.com/vertex-ai) - `vertex_ai/gemini-3-pro-preview`
- [DeepSeek V4 Pro](https://platform.deepseek.com) - `deepseek/deepseek-v4-pro`
- [Moonshot Kimi K3](https://platform.kimi.ai) - `moonshot/kimi-k3`
-- [Z.ai GLM-5.3](https://z.ai) - `zai/glm-5.3`
See the [LLM Providers documentation](https://docs.strix.ai/llm-providers/overview) for all supported providers including Vertex AI, Bedrock, Azure, and local models.
diff --git a/docs/advanced/configuration.mdx b/docs/advanced/configuration.mdx
index c2f8edd0..f1542b75 100644
--- a/docs/advanced/configuration.mdx
+++ b/docs/advanced/configuration.mdx
@@ -8,7 +8,7 @@ Configure Strix using environment variables or a config file.
## LLM Configuration
<ParamField path="STRIX_LLM" type="string" required>
- Model name in LiteLLM format (e.g., `openai/gpt-5.6`, `anthropic/claude-sonnet-5`).
+ Model name in LiteLLM format (e.g., `openai/gpt-5.4`, `anthropic/claude-sonnet-4-6`).
</ParamField>
<ParamField path="LLM_API_KEY" type="string">
@@ -145,7 +145,7 @@ strix --target ./app --config /path/to/config.json
```json
{
"env": {
- "STRIX_LLM": "openai/gpt-5.6",
+ "STRIX_LLM": "openai/gpt-5.4",
"LLM_API_KEY": "sk-...",
"STRIX_REASONING_EFFORT": "high"
}
@@ -156,7 +156,7 @@ strix --target ./app --config /path/to/config.json
```bash
# Required
-export STRIX_LLM="openai/gpt-5.6"
+export STRIX_LLM="openai/gpt-5.4"
export LLM_API_KEY="sk-..."
# Optional: Enable web search
diff --git a/docs/contributing.mdx b/docs/contributing.mdx
index 4b61c8d0..4d7f8fb2 100644
--- a/docs/contributing.mdx
+++ b/docs/contributing.mdx
@@ -33,7 +33,7 @@ description: "Contribute to Strix development"
</Step>
<Step title="Configure LLM">
```bash
- export STRIX_LLM="openai/gpt-5.6"
+ export STRIX_LLM="openai/gpt-5.4"
export LLM_API_KEY="your-api-key"
```
</Step>
diff --git a/docs/index.mdx b/docs/index.mdx
index 15e81ecf..2d401489 100644
--- a/docs/index.mdx
+++ b/docs/index.mdx
@@ -78,7 +78,7 @@ Strix uses a graph of specialized agents for comprehensive security testing:
curl -sSL https://strix.ai/install | bash
# Configure
-export STRIX_LLM="openai/gpt-5.6"
+export STRIX_LLM="openai/gpt-5.4"
export LLM_API_KEY="your-api-key"
# Scan
diff --git a/docs/integrations/github-actions.mdx b/docs/integrations/github-actions.mdx
index 7c5bf3fd..5952c3a0 100644
--- a/docs/integrations/github-actions.mdx
+++ b/docs/integrations/github-actions.mdx
@@ -37,7 +37,7 @@ Add these secrets to your repository:
| Secret | Description |
|--------|-------------|
-| `STRIX_LLM` | Model name (e.g., `openai/gpt-5.6`) |
+| `STRIX_LLM` | Model name (e.g., `openai/gpt-5.4`) |
| `LLM_API_KEY` | API key for your LLM provider |
## Exit Codes
diff --git a/docs/llm-providers/anthropic.mdx b/docs/llm-providers/anthropic.mdx
index 0b5b389e..da32b13a 100644
--- a/docs/llm-providers/anthropic.mdx
+++ b/docs/llm-providers/anthropic.mdx
@@ -6,7 +6,7 @@ description: "Configure Strix with Claude models"
## Setup
```bash
-export STRIX_LLM="anthropic/claude-sonnet-5"
+export STRIX_LLM="anthropic/claude-sonnet-4-6"
export LLM_API_KEY="sk-ant-..."
```
@@ -14,8 +14,8 @@ export LLM_API_KEY="sk-ant-..."
| Model | Description |
|-------|-------------|
-| `anthropic/claude-sonnet-5` | Best balance of intelligence and speed |
-| `anthropic/claude-opus-5` | Maximum capability for deep analysis |
+| `anthropic/claude-sonnet-4-6` | Best balance of intelligence and speed |
+| `anthropic/claude-opus-4-6` | Maximum capability for deep analysis |
## Get API Key
diff --git a/docs/llm-providers/azure.mdx b/docs/llm-providers/azure.mdx
index 35f5f711..1a9be008 100644
--- a/docs/llm-providers/azure.mdx
+++ b/docs/llm-providers/azure.mdx
@@ -24,7 +24,7 @@ export AZURE_API_VERSION="2025-11-01-preview"
## Example
```bash
-export STRIX_LLM="azure/gpt-5.6-deployment"
+export STRIX_LLM="azure/gpt-5.4-deployment"
export AZURE_API_KEY="abc123..."
export AZURE_API_BASE="https://mycompany.openai.azure.com"
export AZURE_API_VERSION="2025-11-01-preview"
@@ -33,5 +33,5 @@ export AZURE_API_VERSION="2025-11-01-preview"
## Prerequisites
1. Create an Azure OpenAI resource
-2. Deploy a model (for example GPT-5.6)
+2. Deploy a model (e.g., GPT-5.4)
3. Get the endpoint URL and API key from the Azure portal
diff --git a/docs/llm-providers/novita.mdx b/docs/llm-providers/novita.mdx
index 45eed351..8ae514d4 100644
--- a/docs/llm-providers/novita.mdx
+++ b/docs/llm-providers/novita.mdx
@@ -8,7 +8,7 @@ description: "Configure Strix with Novita AI models"
## Setup
```bash
-export STRIX_LLM="openai/moonshotai/kimi-k3"
+export STRIX_LLM="openai/moonshotai/kimi-k2.5"
export LLM_API_KEY="your-novita-api-key"
export LLM_API_BASE="https://api.novita.ai/openai"
```
@@ -17,9 +17,11 @@ export LLM_API_BASE="https://api.novita.ai/openai"
| Model | Configuration |
|-------|---------------|
-| Kimi K3 | `openai/moonshotai/kimi-k3` |
| GLM-5.3 | `openai/zai-org/glm-5.3` |
+| Kimi K3 | `openai/moonshotai/kimi-k3` |
| DeepSeek V4 Pro | `openai/deepseek/deepseek-v4-pro` |
+| Kimi K2.5 | `openai/moonshotai/kimi-k2.5` |
+| GLM-5 | `openai/zai-org/glm-5` |
| MiniMax M2.5 | `openai/minimax/minimax-m2.5` |
## Get API Key
diff --git a/docs/llm-providers/openai.mdx b/docs/llm-providers/openai.mdx
index ecec6948..c8a48677 100644
--- a/docs/llm-providers/openai.mdx
+++ b/docs/llm-providers/openai.mdx
@@ -6,7 +6,7 @@ description: "Configure Strix with OpenAI models"
## Setup
```bash
-export STRIX_LLM="openai/gpt-5.6"
+export STRIX_LLM="openai/gpt-5.4"
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:
```bash
-export STRIX_LLM="openai/gpt-5.6"
+export STRIX_LLM="openai/gpt-5.4"
export LLM_API_KEY="your-key"
export LLM_API_BASE="https://your-proxy.com/v1"
```
diff --git a/docs/llm-providers/openrouter.mdx b/docs/llm-providers/openrouter.mdx
index 05fd009a..2bcf6e74 100644
--- a/docs/llm-providers/openrouter.mdx
+++ b/docs/llm-providers/openrouter.mdx
@@ -8,7 +8,7 @@ description: "Configure Strix with models via OpenRouter"
## Setup
```bash
-export STRIX_LLM="openrouter/openai/gpt-5.6-sol"
+export STRIX_LLM="openrouter/openai/gpt-5.4"
export LLM_API_KEY="sk-or-..."
```
@@ -18,12 +18,13 @@ Access any model on OpenRouter using the format `openrouter/<provider>/<model>`:
| Model | Configuration |
|-------|---------------|
-| GPT-5.6 Sol | `openrouter/openai/gpt-5.6-sol` |
-| Claude Opus 5 | `openrouter/anthropic/claude-opus-5` |
-| Gemini 3.1 Pro | `openrouter/google/gemini-3.1-pro-preview` |
+| GLM-5.3 (top pick) | `openrouter/z-ai/glm-5.3` |
+| GPT-5.4 | `openrouter/openai/gpt-5.4` |
+| Claude Sonnet 4.6 | `openrouter/anthropic/claude-sonnet-4.6` |
+| Gemini 3 Pro | `openrouter/google/gemini-3-pro-preview` |
| DeepSeek V4 Pro | `openrouter/deepseek/deepseek-v4-pro` |
| Kimi K3 | `openrouter/moonshotai/kimi-k3` |
-| GLM-5.3 | `openrouter/z-ai/glm-5.3` |
+| GLM-4.7 | `openrouter/z-ai/glm-4.7` |
## Get API Key
diff --git a/docs/llm-providers/overview.mdx b/docs/llm-providers/overview.mdx
index 77c08a40..bfeec62a 100644
--- a/docs/llm-providers/overview.mdx
+++ b/docs/llm-providers/overview.mdx
@@ -9,17 +9,17 @@ Strix uses [LiteLLM](https://docs.litellm.ai/docs/providers) for model compatibi
Set your model and API key:
-| Model | Provider | Configuration |
-| -------------- | ------------- | ---------------------------------- |
-| GPT-5.6 | OpenAI | `openai/gpt-5.6` |
-| Claude Opus 5 | Anthropic | `anthropic/claude-opus-5` |
-| Gemini 3.1 Pro | Google Vertex | `vertex_ai/gemini-3.1-pro-preview` |
-| DeepSeek V4 | DeepSeek | `deepseek/deepseek-v4-pro` |
-| Kimi K3 | Moonshot | `moonshot/kimi-k3` |
-| GLM-5.3 | Z.ai | `zai/glm-5.3` |
+| Model | Provider | Configuration |
+| -------------------- | ----------------- | -------------------------------- |
+| GLM-5.3 (top pick) | Z.ai (OpenRouter) | `openrouter/z-ai/glm-5.3` |
+| GPT-5.4 | OpenAI | `openai/gpt-5.4` |
+| Claude Sonnet 4.6 | Anthropic | `anthropic/claude-sonnet-4-6` |
+| Gemini 3 Pro | Google Vertex | `vertex_ai/gemini-3-pro-preview` |
+| DeepSeek V4 Pro | DeepSeek | `deepseek/deepseek-v4-pro` |
+| Kimi K3 | Moonshot | `moonshot/kimi-k3` |
```bash
-export STRIX_LLM="openai/gpt-5.6"
+export STRIX_LLM="openai/gpt-5.4"
export LLM_API_KEY="your-api-key"
```
@@ -38,7 +38,7 @@ See the [Local Models guide](/llm-providers/local) for setup instructions and re
<CardGroup cols={2}>
<Card title="OpenAI" href="/llm-providers/openai">
- GPT-5.6 models.
+ GPT-5.4 models.
</Card>
<Card title="Anthropic" href="/llm-providers/anthropic">
Claude Opus, Sonnet, and Haiku.
@@ -53,7 +53,7 @@ See the [Local Models guide](/llm-providers/local) for setup instructions and re
Claude and Titan models via AWS.
</Card>
<Card title="Azure OpenAI" href="/llm-providers/azure">
- GPT-5.6 through Azure.
+ GPT-5.4 via Azure.
</Card>
<Card title="Local Models" href="/llm-providers/local">
Llama 4, Mistral, and self-hosted models.
@@ -65,9 +65,10 @@ See the [Local Models guide](/llm-providers/local) for setup instructions and re
Use LiteLLM's `provider/model-name` format:
```
-openai/gpt-5.6
-anthropic/claude-sonnet-5
-vertex_ai/gemini-3.1-pro-preview
+openrouter/z-ai/glm-5.3
+openai/gpt-5.4
+anthropic/claude-sonnet-4-6
+vertex_ai/gemini-3-pro-preview
bedrock/anthropic.claude-4-5-sonnet-20251022-v1:0
ollama/llama4
```
diff --git a/docs/llm-providers/vertex.mdx b/docs/llm-providers/vertex.mdx
index 5c4efe2b..d7ed9710 100644
--- a/docs/llm-providers/vertex.mdx
+++ b/docs/llm-providers/vertex.mdx
@@ -14,7 +14,7 @@ pipx install "strix-agent[vertex]"
## Setup
```bash
-export STRIX_LLM="vertex_ai/gemini-3.1-pro-preview"
+export STRIX_LLM="vertex_ai/gemini-3-pro-preview"
```
No API key required—uses Google Cloud Application Default Credentials.
@@ -37,8 +37,8 @@ export GOOGLE_APPLICATION_CREDENTIALS="/path/to/service-account.json"
| Model | Description |
|-------|-------------|
-| `vertex_ai/gemini-3.1-pro-preview` | Best overall performance for security testing |
-| `vertex_ai/gemini-3.7-flash` | Faster and cheaper |
+| `vertex_ai/gemini-3-pro-preview` | Best overall performance for security testing |
+| `vertex_ai/gemini-3-flash-preview` | Faster and cheaper |
## Project Configuration
diff --git a/docs/quickstart.mdx b/docs/quickstart.mdx
index f336e8ca..9e13d69f 100644
--- a/docs/quickstart.mdx
+++ b/docs/quickstart.mdx
@@ -28,12 +28,12 @@ description: "Install Strix and run your first security scan"
Set your LLM provider:
```bash
-export STRIX_LLM="openai/gpt-5.6"
+export STRIX_LLM="openai/gpt-5.4"
export LLM_API_KEY="your-api-key"
```
<Tip>
-For best results, use `openai/gpt-5.6`, `anthropic/claude-opus-5`, or `deepseek/deepseek-v4-pro`.
+For best results, use `openrouter/z-ai/glm-5.3` (our top pick), `openai/gpt-5.4`, `anthropic/claude-opus-4-6`, or `openai/gpt-5.2`.
</Tip>
## Run Your First Scan
diff --git a/strix/config/models.py b/strix/config/models.py
index 002eadfc..15fa2546 100644
--- a/strix/config/models.py
+++ b/strix/config/models.py
@@ -562,27 +562,34 @@ DEFAULT_MODEL_RETRY = ModelRetrySettings(
)
RECOMMENDED_MODEL_NAMES = (
+ "openrouter/z-ai/glm-5.3",
+ "zai/glm-5.3",
+ "zai/glm-5.3-flash",
"openai/gpt-5.6-sol",
"openai/gpt-5.6-terra",
"openai/gpt-5.6-luna",
"openai/gpt-5.6",
"openai/gpt-5.5-pro",
"openai/gpt-5.5",
+ "openai/gpt-5.4",
+ "openai/gpt-5.3-codex",
"anthropic/claude-fable-5-1",
"anthropic/claude-fable-5",
"anthropic/claude-opus-5",
+ "anthropic/claude-opus-4-8",
"anthropic/claude-sonnet-5",
+ "anthropic/claude-sonnet-4-6",
"vertex_ai/gemini-3.1-pro-preview",
"gemini/gemini-3.1-pro-preview",
"vertex_ai/gemini-3.7-flash",
"gemini/gemini-3.7-flash",
+ "gemini/gemini-3.6-flash",
"deepseek/deepseek-v4-pro",
"deepseek/deepseek-v4-flash",
"dashscope/qwen3.8-max",
+ "dashscope/qwen3.7-max-2026-06-08",
"moonshot/kimi-k3",
"moonshot/kimi-k2.7-code",
- "zai/glm-5.3",
- "zai/glm-5.3-flash",
)
_RECOMMENDED_MODEL_NAME_SET = frozenset(name.lower() for name in RECOMMENDED_MODEL_NAMES)
diff --git a/strix/interface/auth_cli.py b/strix/interface/auth_cli.py
index 09354e54..51e6b9fe 100644
--- a/strix/interface/auth_cli.py
+++ b/strix/interface/auth_cli.py
@@ -254,7 +254,7 @@ def _status(console: Console) -> int:
console.print(f" Runs use the subscription (STRIX_LLM=[bold]{settings.llm.model}[/]).")
else:
console.print(
- " [yellow]Note:[/] set [cyan]STRIX_LLM[/] to e.g. [cyan]chatgpt/gpt-5.6[/] "
+ " [yellow]Note:[/] set [cyan]STRIX_LLM[/] to e.g. [cyan]chatgpt/gpt-5.4[/] "
"to run on the subscription."
)
return 0
@@ -293,7 +293,7 @@ def _print_success(console: Console) -> None:
text.append(" to a ", style="white")
text.append("chatgpt/", style="bold cyan")
text.append(" model (e.g. ", style="white")
- text.append("chatgpt/gpt-5.6", style="bold cyan")
+ text.append("chatgpt/gpt-5.4", style="bold cyan")
text.append(") — runs are billed to your ChatGPT plan.", style="white")
text.append("\n\n", style="white")
text.append("Run a scan as usual, e.g. ", style="white")
diff --git a/strix/interface/environment.py b/strix/interface/environment.py
index 2ace227f..5589a1fe 100644
--- a/strix/interface/environment.py
+++ b/strix/interface/environment.py
@@ -70,8 +70,8 @@ def validate_environment() -> None:
error_text.append("• ", style="white")
error_text.append("STRIX_LLM", style="bold cyan")
error_text.append(
- " - Model name to use (for example 'openai/gpt-5.6' or "
- "'anthropic/claude-opus-5')\n",
+ " - Model name to use (e.g., 'openai/gpt-5.4' or "
+ "'anthropic/claude-opus-4-7')\n",
style="white",
)
@@ -102,7 +102,7 @@ def validate_environment() -> None:
)
error_text.append("\nExample setup:\n", style="white")
- error_text.append("export STRIX_LLM='openai/gpt-5.6'\n", style="dim white")
+ error_text.append("export STRIX_LLM='openai/gpt-5.4'\n", style="dim white")
if missing_optional_vars:
for var in missing_optional_vars:
diff --git a/strix/interface/main.py b/strix/interface/main.py
index 1f933cd8..297c4838 100644
--- a/strix/interface/main.py
+++ b/strix/interface/main.py
@@ -118,8 +118,8 @@ def _subscription_error_hint(exc: BaseException) -> str | None:
joined = " ".join(_exception_messages(exc)).lower()
if "not supported when using codex with a chatgpt account" in joined:
return (
- "This model is not available on your ChatGPT subscription. "
- "Set STRIX_LLM to a model your plan includes (for example chatgpt/gpt-5.6)."
+ "This model isn't available on your ChatGPT subscription. "
+ "Set STRIX_LLM to a model your plan includes (e.g. chatgpt/gpt-5.4)."
)
if (
"error code: 401" in joined
@@ -171,7 +171,7 @@ async def warm_up_llm(show_model_warning: bool = True) -> None:
)
warn_text.append("<provider>/<model>", style="bold cyan")
warn_text.append(
- "' form, for example 'anthropic/claude-opus-5' or 'deepseek/deepseek-v4-pro'.",
+ "' form, e.g. 'anthropic/claude-opus-4-7', 'deepseek/deepseek-v4-pro'.",
style="white",
)
console.print(