refactor(devgen/providers): shared provider base class

Abstract out generate validation and error handling into BaseProvider, eliminating duplicated logic across Anthropic, OpenRouter, and OpenAI providers.

devgen/providers/huggingface.py

@@ -1,34 +1,19 @@
 import requests
 
+from devgen.providers.base import BaseProvider
 from devgen.utils import format_token_limit_error, is_token_limit_error
 
 
-class HuggingfaceProvider:
+class HuggingfaceProvider(BaseProvider):
     """Generates content using Hugging Face Inference API."""
 
+    DISPLAY_NAME = "Hugging Face"
     API_URL_TEMPLATE = "https://api-inference.huggingface.co/models/{model}"
+    DEFAULT_MODEL = "mistralai/Mistral-7B-Instruct-v0.2"
 
-    def generate(
-        self,
-        prompt: str,
-        api_key: str,
-        model: str = "mistralai/Mistral-7B-Instruct-v0.2",
-        **kwargs,
-    ) -> str:
-        """Generates a response using Hugging Face API."""
-        if not api_key:
-            raise ValueError(
-                "Hugging Face API token is missing. "
-                "Set it via `devgen setup config` or pass --api-key."
-            )
-
+    def _generate(self, prompt, api_key, model, **kwargs):
         api_url = self.API_URL_TEMPLATE.format(model=model)
         headers = {"Authorization": f"Bearer {api_key}"}
-
-        # HF models often expect specific prompting formats, but we'll send raw prompt
-        # Some models are text-generation, some are conversational.
-        # Assuming text-generation for generic usage.
-
         payload = {
             "inputs": prompt,
             "parameters": {"max_new_tokens": 500, "return_full_text": False},
@@ -38,31 +23,12 @@ class HuggingfaceProvider:
             response = requests.post(api_url, headers=headers, json=payload)
             response.raise_for_status()
             result = response.json()
-
-            if isinstance(result, list) and result and "generated_text" in result[0]:
-                return result[0]["generated_text"].strip()
-            elif isinstance(result, dict) and "error" in result:
-                err = result["error"]
-                if "is currently loading" in str(err).lower():
-                    raise RuntimeError(
-                        f"Hugging Face model is loading: {err}. "
-                        "Wait a minute and retry, or pick a different model."
-                    )
-                if is_token_limit_error(err):
-                    raise RuntimeError(
-                        format_token_limit_error("Hugging Face", err)
-                    ) from err
-                raise RuntimeError(f"Hugging Face API error: {err}")
-            else:
-                raise RuntimeError(
-                    "Hugging Face returned an unexpected response shape. "
-                    "The model may not support text-generation."
-                )
-
         except requests.HTTPError as e:
-            status = e.response.status_code if e.response is not None else "?"
             if is_token_limit_error(e):
-                raise RuntimeError(format_token_limit_error("Hugging Face", e)) from e
+                raise RuntimeError(
+                    format_token_limit_error(self.DISPLAY_NAME, e)
+                ) from e
+            status = e.response.status_code if e.response is not None else "?"
             raise RuntimeError(
                 f"Hugging Face request failed (HTTP {status}): {e}. "
                 "Check the model id and your token permissions."
@@ -71,9 +37,18 @@ class HuggingfaceProvider:
             raise RuntimeError(
                 f"Hugging Face network error: {e}. Check your connection."
             ) from e
-        except RuntimeError:
-            raise
-        except Exception as e:
-            if is_token_limit_error(e):
-                raise RuntimeError(format_token_limit_error("Hugging Face", e)) from e
-            raise RuntimeError(f"Hugging Face generation failed: {e}") from e
+
+        if isinstance(result, list) and result and "generated_text" in result[0]:
+            return result[0]["generated_text"]
+        if isinstance(result, dict) and "error" in result:
+            err = result["error"]
+            if "is currently loading" in str(err).lower():
+                raise RuntimeError(
+                    f"Hugging Face model is loading: {err}. "
+                    "Wait a minute and retry, or pick a different model."
+                )
+            raise RuntimeError(f"Hugging Face API error: {err}")
+        raise RuntimeError(
+            "Hugging Face returned an unexpected response shape. "
+            "The model may not support text-generation."
+        )