cryptorugmunch
a7c30b12cd
Mass ruff auto-fix:
- ruff check --fix: 109 issues fixed (F401 unused imports,
I001 unsorted imports, UP037 quoted annotations, SIM105
suppressible exception, RUF100 unused-noqa)
- ruff check --fix --unsafe-fixes: 22 additional issues
- ruff format: 70 files reformatted
- Manual pass: fix 16 misplaced import httpx lines
- Manual pass: fix remaining E402 (import-after-docstring)
Result: 283 errors -> 30 errors.
The remaining 30 are real issues that need manual review:
5 F401 unused-import (likely auto-generated stubs)
5 F821 undefined-name (real bugs in code that references
redis/pydantic/LLMRegistry without imports)
3 BLE001 (the compliance LLM fallback is intentional; the
other two are real)
3 RUF012 mutable-class-default
3 SIM105, 3 SIM117, 2 E722, 2 E741
1 B007, 1 B025, 1 E402, 1 RUF200 (pyproject.toml issue)
Tests: 436/437 pass (1 pre-existing SSE sandbox failure).
format check + import sort: now clean.
make ci: still gated on the 30 remaining real issues.
Follow-up: triage the 30 issues file-by-file.
83 lines
2.4 KiB
Python
83 lines
2.4 KiB
Python
"""Pry — LLM Provider abstraction with referral revenue tracking.
|
|
Supports pluggable providers: OpenAI, Anthropic, Google, Cohere, Mistral, Ollama, OpenRouter.
|
|
Includes referral/affiliate link tracking for revenue sharing."""
|
|
|
|
# SPDX-License-Identifier: MIT
|
|
# Copyright (c) 2026 Rug Munch Media LLC
|
|
#
|
|
# Part of Pry — https://git.rugmunch.io/RugMunchMedia/pryscraper
|
|
# Licensed under MIT. See LICENSE.
|
|
|
|
import logging
|
|
from abc import ABC, abstractmethod
|
|
from dataclasses import dataclass, field
|
|
from typing import Any
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
|
|
@dataclass
|
|
class LLMResponse:
|
|
"""Standard response from any LLM provider."""
|
|
|
|
text: str
|
|
model: str
|
|
provider: str
|
|
input_tokens: int = 0
|
|
output_tokens: int = 0
|
|
cost_usd: float = 0.0
|
|
referral_id: str = ""
|
|
latency_ms: int = 0
|
|
raw: dict[str, Any] = field(default_factory=dict)
|
|
|
|
|
|
@dataclass
|
|
class ReferralConfig:
|
|
"""Referral/affiliate config for revenue sharing."""
|
|
|
|
enabled: bool = True
|
|
program_id: str = "pry-default"
|
|
# Provider-specific referral links (with our affiliate ID)
|
|
referral_links: dict[str, str] = field(default_factory=dict)
|
|
# NEW: link to the full provider catalog
|
|
catalog: dict = field(default_factory=dict)
|
|
|
|
def __post_init__(self):
|
|
if not self.referral_links:
|
|
from referrals import PROVIDER_CATALOG
|
|
|
|
for _category, providers in PROVIDER_CATALOG.items():
|
|
for p in providers:
|
|
self.referral_links[p["tag"]] = p["url"]
|
|
self.catalog = PROVIDER_CATALOG
|
|
|
|
|
|
class LLMProvider(ABC):
|
|
"""Abstract base class for LLM providers."""
|
|
|
|
name: str = ""
|
|
cost_per_1k_input: float = 0.0
|
|
cost_per_1k_output: float = 0.0
|
|
referral_url: str = ""
|
|
|
|
@abstractmethod
|
|
async def complete(
|
|
self,
|
|
prompt: str,
|
|
system: str = "",
|
|
max_tokens: int = 1024,
|
|
temperature: float = 0.7,
|
|
model: str = "",
|
|
) -> LLMResponse:
|
|
"""Send completion request to provider."""
|
|
raise NotImplementedError
|
|
|
|
@abstractmethod
|
|
async def embed(self, text: str, model: str = "") -> list[float]:
|
|
"""Generate embedding for text."""
|
|
raise NotImplementedError
|
|
|
|
def estimate_cost(self, input_tokens: int, output_tokens: int) -> float:
|
|
return (input_tokens / 1000) * self.cost_per_1k_input + (
|
|
output_tokens / 1000
|
|
) * self.cost_per_1k_output
|