Initial Open-SWE-Traces cleanup pipeline

src/swe_data_processing/config.py

@@ -0,0 +1,93 @@
+"""Runtime configuration for the GLM API and local processing pipeline."""
+
+from __future__ import annotations
+
+import os
+from dataclasses import dataclass
+
+
+def _get_bool(name: str, default: bool) -> bool:
+    """Read a strict boolean environment variable with a safe default."""
+
+    raw_value = os.getenv(name)
+    if raw_value is None:
+        return default
+    normalized = raw_value.strip().lower()
+    if normalized in {"1", "true", "yes", "on"}:
+        return True
+    if normalized in {"0", "false", "no", "off"}:
+        return False
+    raise ValueError(f"{name} must be a boolean value, got {raw_value!r}")
+
+
+def _get_int(name: str, default: int, minimum: int = 1) -> int:
+    """Read and validate an integer environment variable."""
+
+    value = int(os.getenv(name, str(default)))
+    if value < minimum:
+        raise ValueError(f"{name} must be at least {minimum}, got {value}")
+    return value
+
+
+def _get_float(name: str, default: float, minimum: float = 0.0) -> float:
+    """Read and validate a floating-point environment variable."""
+
+    value = float(os.getenv(name, str(default)))
+    if value < minimum:
+        raise ValueError(f"{name} must be at least {minimum}, got {value}")
+    return value
+
+
+@dataclass(frozen=True)
+class Settings:
+    """Immutable settings used by API clients and command-line workflows."""
+
+    api_key: str
+    api_base: str = "https://llm-api.cowin.run"
+    api_path: str = "/v1/chat/completions"
+    model: str = "glm-5.2"
+    timeout_seconds: float = 300.0
+    max_retries: int = 3
+    max_tokens: int = 8192
+    temperature: float = 0.0
+    reasoning_effort: str = "high"
+    thinking_enabled: bool = True
+
+    @property
+    def endpoint(self) -> str:
+        """Return the normalized absolute chat-completions URL."""
+
+        base = self.api_base.rstrip("/")
+        path = self.api_path if self.api_path.startswith("/") else f"/{self.api_path}"
+        return f"{base}{path}"
+
+    @classmethod
+    def from_env(cls, *, require_api_key: bool = True) -> Settings:
+        """Construct settings from environment variables.
+
+        The API key is intentionally loaded only from ``GLM_API_KEY``. The
+        project never reads a committed configuration file containing a key.
+        """
+
+        api_key = os.getenv("GLM_API_KEY", "").strip()
+        if require_api_key and not api_key:
+            raise ValueError("GLM_API_KEY is required but was not set")
+
+        reasoning_effort = os.getenv("GLM_REASONING_EFFORT", "high").strip().lower()
+        if reasoning_effort not in {"low", "medium", "high", "max"}:
+            raise ValueError(
+                "GLM_REASONING_EFFORT must be one of: low, medium, high, max"
+            )
+
+        return cls(
+            api_key=api_key,
+            api_base=os.getenv("GLM_API_BASE", "https://llm-api.cowin.run"),
+            api_path=os.getenv("GLM_API_PATH", "/v1/chat/completions"),
+            model=os.getenv("GLM_MODEL", "glm-5.2"),
+            timeout_seconds=_get_float("GLM_TIMEOUT_SECONDS", 300.0, 1.0),
+            max_retries=_get_int("GLM_MAX_RETRIES", 3, 1),
+            max_tokens=_get_int("GLM_MAX_TOKENS", 8192, 1),
+            temperature=_get_float("GLM_TEMPERATURE", 0.0, 0.0),
+            reasoning_effort=reasoning_effort,
+            thinking_enabled=_get_bool("GLM_THINKING_ENABLED", True),
+        )