first commit

strix/config/__init__.py

@@ -0,0 +1,37 @@
+"""Strix application settings.
+
+Public surface:
+
+- :class:`Settings` — composite model. Get via :func:`load_settings`.
+- :class:`LlmSettings`, :class:`RuntimeSettings`, :class:`TelemetrySettings`,
+  :class:`IntegrationSettings` — sub-models, attribute-accessed off
+  ``Settings``.
+- :func:`load_settings` — memoized resolve (env > JSON file > defaults).
+- :func:`apply_config_override` — switch the JSON source to a custom path.
+- :func:`persist_current` — write currently-set env vars to the active file.
+"""
+
+from strix.config.loader import (
+    apply_config_override,
+    load_settings,
+    persist_current,
+)
+from strix.config.settings import (
+    IntegrationSettings,
+    LlmSettings,
+    RuntimeSettings,
+    Settings,
+    TelemetrySettings,
+)
+
+
+__all__ = [
+    "IntegrationSettings",
+    "LlmSettings",
+    "RuntimeSettings",
+    "Settings",
+    "TelemetrySettings",
+    "apply_config_override",
+    "load_settings",
+    "persist_current",
+]

strix/config/loader.py

@@ -0,0 +1,126 @@
+"""Settings loader, override switch, and disk persistence."""
+
+from __future__ import annotations
+
+import contextlib
+import json
+import logging
+import os
+from pathlib import Path
+from typing import TYPE_CHECKING, Any
+
+from pydantic import AliasChoices, BaseModel
+
+from strix.config.settings import Settings
+
+
+if TYPE_CHECKING:
+    from pydantic.fields import FieldInfo
+
+
+logger = logging.getLogger(__name__)
+
+
+_DEFAULT_PATH: Path = Path.home() / ".strix" / "cli-config.json"
+_override: Path | None = None
+_cached: Settings | None = None
+
+
+def load_settings() -> Settings:
+    """Resolve settings from env + JSON file + defaults. Memoized.
+
+    Precedence: env vars win, then the JSON file, then field defaults.
+    """
+    global _cached  # noqa: PLW0603
+    if _cached is None:
+        source_path = _override or _DEFAULT_PATH
+        init_kwargs: dict[str, Any] = _read_json_overrides(source_path)
+        _cached = Settings(**init_kwargs)
+        logger.debug(
+            "load_settings: resolved (override=%s, file_used=%s, json_keys=%d)",
+            _override is not None,
+            source_path.exists(),
+            sum(len(v) for v in init_kwargs.values()),
+        )
+    return _cached
+
+
+def apply_config_override(path: Path) -> None:
+    """Switch the JSON source to ``path`` and invalidate the cache."""
+    global _override, _cached  # noqa: PLW0603
+    _override = path
+    _cached = None
+    logger.info("config override applied: %s", path)
+
+
+def persist_current() -> None:
+    """Write currently-set env vars to the active config file (0o600)."""
+    s = load_settings()
+    target = _override or _DEFAULT_PATH
+    target.parent.mkdir(parents=True, exist_ok=True)
+
+    env_block: dict[str, str] = {}
+    for sub_name in s.model_fields:
+        sub_model = getattr(s, sub_name)
+        if not isinstance(sub_model, BaseModel):
+            continue
+        for finfo in type(sub_model).model_fields.values():
+            for alias in _aliases_for(finfo):
+                value = os.environ.get(alias.upper())
+                if value:
+                    env_block[alias.upper()] = value
+                    break
+
+    target.write_text(json.dumps({"env": env_block}, indent=2), encoding="utf-8")
+    with contextlib.suppress(OSError):
+        target.chmod(0o600)
+
+
+def _aliases_for(finfo: FieldInfo) -> list[str]:
+    """Collect every env-var name that should populate ``finfo``."""
+    aliases: list[str] = []
+    if finfo.alias:
+        aliases.append(finfo.alias)
+    va = finfo.validation_alias
+    if isinstance(va, AliasChoices):
+        aliases.extend(c for c in va.choices if isinstance(c, str))
+    elif isinstance(va, str):
+        aliases.append(va)
+    return aliases
+
+
+def _read_json_overrides(path: Path) -> dict[str, dict[str, Any]]:
+    """Read ``{"env": {...}}`` from ``path`` and remap to nested kwargs.
+
+    Only includes keys whose env var is NOT already set, so env always
+    wins over the persisted file.
+    """
+    if not path.exists():
+        return {}
+    try:
+        data = json.loads(path.read_text(encoding="utf-8"))
+    except (json.JSONDecodeError, OSError):
+        return {}
+    env_block = data.get("env", {}) if isinstance(data, dict) else {}
+    if not isinstance(env_block, dict):
+        return {}
+
+    env_block_upper = {str(k).upper(): v for k, v in env_block.items()}
+
+    nested: dict[str, dict[str, Any]] = {}
+    for sub_name, sub_finfo in Settings.model_fields.items():
+        sub_cls = sub_finfo.annotation
+        if not (isinstance(sub_cls, type) and issubclass(sub_cls, BaseModel)):
+            continue
+        sub_data: dict[str, Any] = {}
+        for fname, finfo in sub_cls.model_fields.items():
+            for alias in _aliases_for(finfo):
+                key = alias.upper()
+                if key in os.environ:
+                    break  # env wins; skip JSON for this field
+                if key in env_block_upper:
+                    sub_data[fname] = env_block_upper[key]
+                    break
+        if sub_data:
+            nested[sub_name] = sub_data
+    return nested

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")

strix/config/settings.py

@@ -0,0 +1,75 @@
+"""Strix application settings — pydantic-settings powered."""
+
+from __future__ import annotations
+
+from typing import Literal
+
+from pydantic import AliasChoices, Field
+from pydantic_settings import BaseSettings, SettingsConfigDict
+
+
+ReasoningEffort = Literal["none", "minimal", "low", "medium", "high", "xhigh"]
+
+_BASE_CONFIG = SettingsConfigDict(
+    case_sensitive=False,
+    populate_by_name=True,
+    extra="ignore",
+)
+
+
+class LlmSettings(BaseSettings):
+    model_config = _BASE_CONFIG
+
+    model: str | None = Field(default=None, alias="STRIX_LLM")
+    api_key: str | None = Field(
+        default=None,
+        validation_alias=AliasChoices("LLM_API_KEY", "OPENAI_API_KEY"),
+    )
+    api_base: str | None = Field(
+        default=None,
+        validation_alias=AliasChoices(
+            "LLM_API_BASE",
+            "OPENAI_API_BASE",
+            "OPENAI_BASE_URL",
+            "LITELLM_BASE_URL",
+            "OLLAMA_API_BASE",
+        ),
+    )
+    reasoning_effort: ReasoningEffort = Field(default="high", alias="STRIX_REASONING_EFFORT")
+    timeout: int = Field(default=300, alias="LLM_TIMEOUT")
+
+
+class RuntimeSettings(BaseSettings):
+    model_config = _BASE_CONFIG
+
+    image: str = Field(
+        default="ghcr.io/usestrix/strix-sandbox:1.0.0",
+        alias="STRIX_IMAGE",
+    )
+    backend: str = Field(default="docker", alias="STRIX_RUNTIME_BACKEND")
+    # Hard cap on a local target's size before we refuse to stream it into the
+    # sandbox file-by-file (the SDK copies every file individually, which stalls
+    # on large repos). Above this, the user must bind-mount via ``--mount``.
+    # Set to 0 (or less) to disable the pre-flight check entirely.
+    max_local_copy_mb: int = Field(default=1024, alias="STRIX_MAX_LOCAL_COPY_MB")
+
+
+class TelemetrySettings(BaseSettings):
+    model_config = _BASE_CONFIG
+
+    enabled: bool = Field(default=True, alias="STRIX_TELEMETRY")
+
+
+class IntegrationSettings(BaseSettings):
+    model_config = _BASE_CONFIG
+
+    perplexity_api_key: str | None = Field(default=None, alias="PERPLEXITY_API_KEY")
+
+
+class Settings(BaseSettings):
+    model_config = _BASE_CONFIG
+
+    llm: LlmSettings = Field(default_factory=LlmSettings)
+    runtime: RuntimeSettings = Field(default_factory=RuntimeSettings)
+    telemetry: TelemetrySettings = Field(default_factory=TelemetrySettings)
+    integrations: IntegrationSettings = Field(default_factory=IntegrationSettings)