first commit

strix/config/models.py

@@ -0,0 +1,164 @@
+"""SDK model configuration helpers."""
+
+from __future__ import annotations
+
+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,
+    retry_policies,
+)
+
+
+if TYPE_CHECKING:
+    from agents.models.interface import ModelProvider
+
+    from strix.config.settings import Settings
+
+
+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,
+            )
+        if prefix == "ollama" and stripped_model_name:
+            return self._get_fallback_provider("litellm"), f"ollama_chat/{stripped_model_name}"
+        return self._get_fallback_provider("litellm"), original_model_name
+
+
+DEFAULT_MODEL_RETRY = ModelRetrySettings(
+    max_retries=5,
+    backoff=ModelRetryBackoffSettings(
+        initial_delay=2.0,
+        max_delay=90.0,
+        multiplier=2.0,
+        jitter=False,
+    ),
+    policy=retry_policies.any(
+        retry_policies.provider_suggested(),
+        retry_policies.network_error(),
+        retry_policies.http_status((429, 500, 502, 503, 504)),
+    ),
+)
+
+
+def configure_sdk_model_defaults(settings: Settings) -> None:
+    """Apply Strix config to SDK-native defaults."""
+    llm = settings.llm
+    set_tracing_disabled(True)
+    _configure_litellm_compatibility()
+    if llm.api_key:
+        set_default_openai_key(llm.api_key, use_for_tracing=False)
+        _configure_litellm_default("api_key", llm.api_key)
+        _mirror_api_key_to_provider_env(llm.model, llm.api_key)
+    if llm.api_base:
+        os.environ["OPENAI_BASE_URL"] = llm.api_base
+        _configure_litellm_default("api_base", llm.api_base)
+        set_default_openai_api("chat_completions")
+    else:
+        set_default_openai_api("responses")
+
+
+def _mirror_api_key_to_provider_env(model_name: str | None, api_key: str) -> None:
+    if not model_name:
+        return
+    import litellm
+
+    name = model_name.strip()
+    for prefix in ("litellm/", "any-llm/"):
+        if name.lower().startswith(prefix):
+            name = name[len(prefix) :]
+            break
+    try:
+        report = litellm.validate_environment(model=name.lower())
+    except Exception:  # noqa: BLE001
+        return
+    for env_key in report.get("missing_keys") or []:
+        if env_key.endswith("_API_KEY"):
+            os.environ.setdefault(env_key, api_key)
+
+
+def _configure_litellm_compatibility() -> None:
+    """Enable LiteLLM's permissive param handling and disable its callbacks."""
+    import litellm
+
+    litellm.drop_params = True
+    litellm.modify_params = True
+    litellm.turn_off_message_logging = True
+    litellm.disable_streaming_logging = True
+    litellm.suppress_debug_info = True
+
+    _register_litellm_cost_callback()
+
+
+def _register_litellm_cost_callback() -> None:
+    import litellm
+
+    from strix.report.state import litellm_cost_callback
+
+    for bucket_name in ("success_callback", "_async_success_callback"):
+        bucket = getattr(litellm, bucket_name, None)
+        if not isinstance(bucket, list):
+            continue
+        if litellm_cost_callback in bucket:
+            continue
+        bucket.append(litellm_cost_callback)
+
+
+def _configure_litellm_default(name: str, value: str) -> None:
+    """Set LiteLLM's module-level defaults without adding a provider wrapper."""
+    import litellm
+
+    setattr(litellm, name, value)
+
+
+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 "/" in model and not model.startswith("openai/"):
+        return True
+    if settings.llm.api_base:
+        return True
+    return not model_supports_reasoning(model_name)
+
+
+def model_supports_reasoning(model_name: str) -> bool:
+    import litellm
+
+    name = model_name.strip().lower()
+    for prefix in ("litellm/", "any-llm/", "openai/"):
+        if name.startswith(prefix):
+            name = name[len(prefix) :]
+            break
+    entry = litellm.model_cost.get(name)
+    if entry is None and "/" in name:
+        entry = litellm.model_cost.get(name.rsplit("/", 1)[1])
+    return bool(entry and entry.get("supports_reasoning"))
+
+
+def is_known_openai_bare_model(model_name: str) -> bool:
+    import litellm
+
+    name = model_name.strip().lower()
+    if not name or "/" in name:
+        return False
+    entry = litellm.model_cost.get(name)
+    return bool(entry and entry.get("litellm_provider") == "openai")