Stop exposing litellm/ prefix in user-facing model names

Users had to type STRIX_LLM=litellm/deepseek/deepseek-chat — the
litellm/ wrapper was Strix-internal plumbing surfacing in user config.

Add StrixProvider, a MultiProvider subclass that routes any non-OpenAI
prefix (deepseek/, anthropic/, groq/, xai/, mistral/, openrouter/, …)
through LitellmProvider with the prefix preserved. normalize_model_name
no longer adds litellm/ to anything; bare claude-* / gemini-* shorthands
expand to anthropic/<model> / gemini/<model> instead of the wrapped form.

Wire StrixProvider into warm_up_llm and RunConfig.model_provider.
litellm/<provider>/<model> and any-llm/<provider>/<model> still resolve
unchanged for users on older config.

Refresh stale model names in the env-validation messages and the
warm-up hint (gpt-5.4, claude-opus-4-7, deepseek-reasoner).

Verified 24-case end-to-end matrix: OpenAI direct vs. LitellmProvider
routing, env-var mirroring via validate_environment, supports_reasoning
detection, and tool_choice gating all behave correctly across modern
providers including the user's unknown DeepSeek SKU.

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}"
 
     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)
 

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,

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",
             )