sankalp
8069895bc7
Add token limit error detection and formatting across all provider modules to surface clear diagnostics when context windows are exceeded, improving error messages and preventing silent failures. New Features - Introduce `is_token_limit_error` checks in Anthropic, Gemini, Hugging Face, Ollama, OpenAI, and OpenRouter providers. - Use `format_token_limit_error` to generate user‑friendly error messages for token limit overs. Enhancements - Centralize token limit error handling for consistent diagnostics across providers. - Explicitly re‑raise `RuntimeError` in Hugging Face to preserve original behavior. Bug Fixes - None
47 lines
1.6 KiB
Python
47 lines
1.6 KiB
Python
from openai import OpenAI
|
|
|
|
from devgen.utils import format_token_limit_error, is_token_limit_error
|
|
|
|
|
|
class OpenrouterProvider:
|
|
"""Generates content using OpenRouter (OpenAI-compatible API)."""
|
|
|
|
BASE_URL = "https://openrouter.ai/api/v1"
|
|
|
|
def generate(
|
|
self, prompt: str, api_key: str, model: str = "openai/gpt-3.5-turbo", **kwargs
|
|
) -> str:
|
|
"""Generates a response using OpenRouter."""
|
|
if not api_key:
|
|
raise ValueError(
|
|
"OpenRouter API key is missing. "
|
|
"Set it via `devgen setup config` or pass --api-key."
|
|
)
|
|
|
|
try:
|
|
client = OpenAI(
|
|
base_url=self.BASE_URL,
|
|
api_key=api_key,
|
|
)
|
|
|
|
# Remove debug from kwargs if present
|
|
kwargs.pop("debug", None)
|
|
|
|
response = client.chat.completions.create(
|
|
model=model,
|
|
messages=[{"role": "user", "content": prompt}],
|
|
extra_headers={
|
|
"HTTP-Referer": "https://github.com/S4NKALP/devgen", # Optional
|
|
"X-Title": "devgen CLI", # Optional
|
|
},
|
|
**kwargs,
|
|
)
|
|
return response.choices[0].message.content.strip()
|
|
except Exception as e:
|
|
if is_token_limit_error(e):
|
|
raise RuntimeError(format_token_limit_error("OpenRouter", e)) from e
|
|
raise RuntimeError(
|
|
f"OpenRouter request failed: {e}. "
|
|
"Verify the model id (e.g. `openai/gpt-4o`) and your API key credits."
|
|
) from e
|