Skip to content

armgit / strix

Public Imported from GitHub
0

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

Stop exposing litellm/ prefix in user-facing model names

0xallam232711be8c33
diff --git a/strix/config/models.py b/strix/config/models.py
index 83f8e914..7f949b45 100644
--- a/strix/config/models.py
+++ b/strix/config/models.py
@@ -6,6 +6,7 @@ import os
from typing import TYPE_CHECKING
from agents import set_default_openai_api, set_default_openai_key, set_tracing_disabled
+from agents.models.multi_provider import MultiProvider
from agents.retry import (
ModelRetryBackoffSettings,
ModelRetrySettings,
@@ -14,10 +15,31 @@ from agents.retry import (
if TYPE_CHECKING:
+ from agents.models.interface import ModelProvider
+
from strix.config.settings import Settings
-_SDK_PREFIXES = {"any-llm", "litellm", "openai"}
+class StrixProvider(MultiProvider):
+ """Route any non-OpenAI prefix through LiteLLM with the prefix preserved,
+ so users type ``deepseek/deepseek-chat`` rather than
+ ``litellm/deepseek/deepseek-chat``.
+ """
+
+ def _resolve_prefixed_model(
+ self,
+ *,
+ original_model_name: str,
+ prefix: str,
+ stripped_model_name: str | None,
+ ) -> tuple[ModelProvider, str | None]:
+ if prefix in {"openai", "litellm", "any-llm"}:
+ return super()._resolve_prefixed_model(
+ original_model_name=original_model_name,
+ prefix=prefix,
+ stripped_model_name=stripped_model_name,
+ )
+ return self._get_fallback_provider("litellm"), original_model_name
DEFAULT_MODEL_RETRY = ModelRetrySettings(
@@ -99,16 +121,13 @@ def normalize_model_name(model_name: str) -> str:
return model
if "/" in model:
- prefix = model.split("/", 1)[0].lower()
- if prefix in _SDK_PREFIXES:
- return model
- return f"litellm/{model}"
+ return model
lower = model.lower()
if lower.startswith("claude"):
- return f"litellm/anthropic/{model}"
+ return f"anthropic/{model}"
if lower.startswith("gemini"):
- return f"litellm/gemini/{model}"
+ return f"gemini/{model}"
return model
@@ -116,7 +135,7 @@ def normalize_model_name(model_name: str) -> str:
def uses_chat_completions_tool_schema(model_name: str, settings: Settings) -> bool:
"""Return whether the resolved SDK route can only receive JSON function tools."""
model = model_name.strip().lower()
- if model.startswith(("litellm/", "any-llm/")):
+ if "/" in model and not model.startswith("openai/"):
return True
return bool(settings.llm.api_base)
diff --git a/strix/core/runner.py b/strix/core/runner.py
index e69e632d..4c0c3fb4 100644
--- a/strix/core/runner.py
+++ b/strix/core/runner.py
@@ -15,6 +15,7 @@ from agents.sandbox import SandboxRunConfig
from strix.agents.factory import build_strix_agent, make_child_factory
from strix.config import load_settings
from strix.config.models import (
+ StrixProvider,
configure_sdk_model_defaults,
normalize_model_name,
uses_chat_completions_tool_schema,
@@ -159,6 +160,7 @@ async def run_strix_scan(
)
run_config = RunConfig(
model=resolved_model,
+ model_provider=StrixProvider(),
model_settings=model_settings,
sandbox=SandboxRunConfig(client=bundle["client"], session=bundle["session"]),
trace_include_sensitive_data=False,
diff --git a/strix/interface/main.py b/strix/interface/main.py
index 9bb86ae1..8ef2fd26 100644
--- a/strix/interface/main.py
+++ b/strix/interface/main.py
@@ -13,7 +13,6 @@ from pathlib import Path
from agents.model_settings import ModelSettings
from agents.models.interface import ModelTracing
-from agents.models.multi_provider import MultiProvider
from docker.errors import DockerException
from rich.console import Console
from rich.panel import Panel
@@ -24,7 +23,7 @@ from strix.config import (
load_settings,
persist_current,
)
-from strix.config.models import configure_sdk_model_defaults, normalize_model_name
+from strix.config.models import StrixProvider, configure_sdk_model_defaults, normalize_model_name
from strix.core.paths import run_dir_for, runtime_state_dir
from strix.interface.cli import run_cli
from strix.interface.tui import run_tui
@@ -99,7 +98,8 @@ def validate_environment() -> None:
error_text.append("• ", style="white")
error_text.append("STRIX_LLM", style="bold cyan")
error_text.append(
- " - Model name to use (e.g., 'gpt-5.4' or 'claude-sonnet-4-6')\n",
+ " - Model name to use (e.g., 'openai/gpt-5.4' or "
+ "'anthropic/claude-opus-4-7')\n",
style="white",
)
@@ -138,7 +138,7 @@ def validate_environment() -> None:
)
error_text.append("\nExample setup:\n", style="white")
- error_text.append("export STRIX_LLM='gpt-5.4'\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:
@@ -216,7 +216,7 @@ async def warm_up_llm() -> None:
configure_sdk_model_defaults(settings)
llm = settings.llm
- model = MultiProvider().get_model(normalize_model_name(llm.model or ""))
+ model = StrixProvider().get_model(normalize_model_name(llm.model or ""))
await asyncio.wait_for(
model.get_response(
system_instructions="You are a helpful assistant.",
@@ -256,8 +256,8 @@ async def warm_up_llm() -> None:
f"\n\nHint: '{raw_model}' has no provider prefix, so the SDK "
f"routed it through OpenAI by default. For non-OpenAI providers "
f"use the '<provider>/<model>' form, e.g. "
- f"'deepseek/deepseek-chat', 'groq/llama-3.1-70b', "
- f"'anthropic/claude-3-5-sonnet'.",
+ f"'anthropic/claude-opus-4-7', 'deepseek/deepseek-reasoner', "
+ f"'openai/gpt-5.4'.",
style="yellow",
)