Adriano
0e01de156f
Run phase2-5-qwen25-prompt-mut-003 fallito a gen 5 (76 evals done, $0.061 spesi) per HTTP 429 RateLimit upstream da DeepInfra su qwen-2.5-72b. RateLimitError NON era in _RETRYABLE_EXCEPTIONS quindi tenacity falliva subito, propagando il 429 a propose() e all'orchestrator (run failed). Tre fix: 1) Aggiunto openai.RateLimitError a _RETRYABLE_EXCEPTIONS. 2) Bumpato stop_after_attempt(3) → 5 e wait_exponential max 10s → 30s. Più tempo per il rate limit upstream di sbloccare prima di rinunciare. 3) hypothesis.py: try/except RateLimitError in propose() come per EmptyCompletionError — anche se tenacity esaurisce i 5 retry, il genome viene marcato fitness=0 e il loop esterno continua senza crash totale. Test: aggiornato test_completion_retries_on_connection_error per assert call_count == 5 (era 3). Tutti 182 verdi. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
122 lines
3.9 KiB
Python
122 lines
3.9 KiB
Python
from __future__ import annotations
|
|
|
|
from dataclasses import dataclass
|
|
from typing import Any
|
|
|
|
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 = "google/gemini-3-flash-preview"
|
|
MODEL_TIER_A = "deepseek/deepseek-v4-flash"
|
|
MODEL_TIER_B = "deepseek/deepseek-v4-flash"
|
|
MODEL_TIER_C = "qwen/qwen-2.5-72b-instruct"
|
|
MODEL_TIER_D = "openai/gpt-oss-20b"
|
|
OPENROUTER_BASE_URL = "https://openrouter.ai/api/v1"
|
|
|
|
class EmptyCompletionError(RuntimeError):
|
|
pass
|
|
|
|
|
|
# Errori transient: retry. Auth/InvalidRequest: NO retry.
|
|
# RateLimitError (HTTP 429) ora retryable: provider OpenRouter come DeepInfra
|
|
# applicano rate limit upstream temporaneo, recuperabile con backoff.
|
|
_RETRYABLE_EXCEPTIONS: tuple[type[BaseException], ...] = (
|
|
openai.APIConnectionError,
|
|
openai.APITimeoutError,
|
|
openai.InternalServerError,
|
|
openai.RateLimitError,
|
|
EmptyCompletionError,
|
|
)
|
|
|
|
|
|
@dataclass(frozen=True)
|
|
class CompletionResult:
|
|
text: str
|
|
input_tokens: int
|
|
output_tokens: int
|
|
tier: ModelTier
|
|
model: str
|
|
|
|
|
|
class LLMClient:
|
|
# Provider OpenRouter da escludere di default. Novita rifiuta /completions
|
|
# endpoint per modelli Qwen 2.x — vedi bug 2026-05-12.
|
|
DEFAULT_PROVIDER_IGNORE: tuple[str, ...] = ("Novita",)
|
|
|
|
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,
|
|
provider_ignore: tuple[str, ...] | None = None,
|
|
) -> 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._provider_ignore = (
|
|
provider_ignore if provider_ignore is not None else self.DEFAULT_PROVIDER_IGNORE
|
|
)
|
|
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(5),
|
|
wait=wait_exponential(multiplier=2.0, min=2.0, max=30.0),
|
|
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]
|
|
extra_body: dict[str, Any] = {}
|
|
if self._provider_ignore:
|
|
extra_body["provider"] = {"ignore": list(self._provider_ignore)}
|
|
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,
|
|
extra_body=extra_body or None,
|
|
)
|
|
if not resp.choices or resp.choices[0].message.content is None:
|
|
raise EmptyCompletionError(f"empty response from {model}")
|
|
usage = resp.usage
|
|
return CompletionResult(
|
|
text=resp.choices[0].message.content,
|
|
input_tokens=usage.prompt_tokens if usage else 0,
|
|
output_tokens=usage.completion_tokens if usage else 0,
|
|
tier=genome.model_tier,
|
|
model=model,
|
|
)
|