Adriano
4dad8be36b
Tutti i tier (S/A/B/C/D) ora passano per OpenRouter via OpenAI SDK.
Modelli Anthropic raggiungibili via prefisso `anthropic/...`.
- pyproject: rimosso `anthropic>=0.39` da deps + uv.lock
- config: rimosso `anthropic_api_key` field
- LLMClient: dispatch unico, single client OpenAI con base_url OpenRouter
- defaults S/A/B → `anthropic/claude-{opus-4-7,sonnet-4-6}`
- retry exceptions: solo openai.* (drop anthropic.*)
- test rinominati e adattati: tier S/A/B mockano OpenAI con prefisso `anthropic/`
- rimosso test `tier_S_without_anthropic_key_raises` (non più rilevante)
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
100 lines
3.0 KiB
Python
100 lines
3.0 KiB
Python
from __future__ import annotations
|
|
|
|
from dataclasses import dataclass
|
|
|
|
import openai
|
|
from openai import OpenAI
|
|
from tenacity import (
|
|
retry,
|
|
retry_if_exception_type,
|
|
stop_after_attempt,
|
|
wait_exponential,
|
|
)
|
|
|
|
from ..genome.hypothesis import HypothesisAgentGenome, ModelTier
|
|
|
|
# Modelli configurati per Phase 1 — tutti via OpenRouter
|
|
MODEL_TIER_S = "anthropic/claude-opus-4-7"
|
|
MODEL_TIER_A = "anthropic/claude-sonnet-4-6"
|
|
MODEL_TIER_B = "anthropic/claude-sonnet-4-6"
|
|
MODEL_TIER_C = "qwen/qwen-2.5-72b-instruct"
|
|
MODEL_TIER_D = "meta-llama/llama-3.3-70b-instruct"
|
|
OPENROUTER_BASE_URL = "https://openrouter.ai/api/v1"
|
|
|
|
# Errori transient: retry. RateLimit/Auth/InvalidRequest: NO retry.
|
|
_RETRYABLE_EXCEPTIONS: tuple[type[BaseException], ...] = (
|
|
openai.APIConnectionError,
|
|
openai.APITimeoutError,
|
|
openai.InternalServerError,
|
|
)
|
|
|
|
|
|
@dataclass(frozen=True)
|
|
class CompletionResult:
|
|
text: str
|
|
input_tokens: int
|
|
output_tokens: int
|
|
tier: ModelTier
|
|
model: str
|
|
|
|
|
|
class LLMClient:
|
|
def __init__(
|
|
self,
|
|
openrouter_api_key: str,
|
|
model_tier_s: str = MODEL_TIER_S,
|
|
model_tier_a: str = MODEL_TIER_A,
|
|
model_tier_b: str = MODEL_TIER_B,
|
|
model_tier_c: str = MODEL_TIER_C,
|
|
model_tier_d: str = MODEL_TIER_D,
|
|
openrouter_base_url: str = OPENROUTER_BASE_URL,
|
|
) -> None:
|
|
self.model_tier_s = model_tier_s
|
|
self.model_tier_a = model_tier_a
|
|
self.model_tier_b = model_tier_b
|
|
self.model_tier_c = model_tier_c
|
|
self.model_tier_d = model_tier_d
|
|
self.openrouter_base_url = openrouter_base_url
|
|
self._tier_models: dict[ModelTier, str] = {
|
|
ModelTier.S: model_tier_s,
|
|
ModelTier.A: model_tier_a,
|
|
ModelTier.B: model_tier_b,
|
|
ModelTier.C: model_tier_c,
|
|
ModelTier.D: model_tier_d,
|
|
}
|
|
self._client = OpenAI(api_key=openrouter_api_key, base_url=openrouter_base_url)
|
|
|
|
@retry(
|
|
stop=stop_after_attempt(3),
|
|
wait=wait_exponential(multiplier=1.0, min=2.0, max=10.0),
|
|
retry=retry_if_exception_type(_RETRYABLE_EXCEPTIONS),
|
|
reraise=True,
|
|
)
|
|
def complete(
|
|
self,
|
|
genome: HypothesisAgentGenome,
|
|
system: str,
|
|
user: str,
|
|
max_tokens: int = 2000,
|
|
) -> CompletionResult:
|
|
model = self._tier_models[genome.model_tier]
|
|
resp = self._client.chat.completions.create(
|
|
model=model,
|
|
messages=[
|
|
{"role": "system", "content": system},
|
|
{"role": "user", "content": user},
|
|
],
|
|
temperature=genome.temperature,
|
|
top_p=genome.top_p,
|
|
max_tokens=max_tokens,
|
|
)
|
|
usage = resp.usage
|
|
assert usage is not None
|
|
return CompletionResult(
|
|
text=resp.choices[0].message.content or "",
|
|
input_tokens=usage.prompt_tokens,
|
|
output_tokens=usage.completion_tokens,
|
|
tier=genome.model_tier,
|
|
model=model,
|
|
)
|