feat(config): align tier defaults to cost-conscious models + qwen3-235b on tier C
- Tier S → google/gemini-3-flash-preview ($0.50/$3.00) - Tier A/B → deepseek/deepseek-v4-flash ($0.14/$0.28) - Tier C → qwen/qwen3-235b-a22b-2507 ($0.071/$0.10) — Phase 2 target - Tier D → openai/gpt-oss-20b ($0.03/$0.14) Aggiornato cost_tracker con prezzi reali per tier. Defaults config.py ora rispecchiano .env corrente per evitare divergenze dead-code. Tier S/A/B/D restano cablati ma non ancora invocati nel loop Phase 2 (solo Hypothesis tier C attivo). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
@@ -25,11 +25,11 @@ class Settings(BaseSettings):
|
||||
|
||||
openrouter_api_key: SecretStr
|
||||
|
||||
llm_model_tier_s: str = "anthropic/claude-opus-4-7"
|
||||
llm_model_tier_a: str = "anthropic/claude-sonnet-4-6"
|
||||
llm_model_tier_b: str = "anthropic/claude-sonnet-4-6"
|
||||
llm_model_tier_c: str = "qwen/qwen-2.5-72b-instruct"
|
||||
llm_model_tier_d: str = "meta-llama/llama-3.3-70b-instruct"
|
||||
llm_model_tier_s: str = "google/gemini-3-flash-preview"
|
||||
llm_model_tier_a: str = "deepseek/deepseek-v4-flash"
|
||||
llm_model_tier_b: str = "deepseek/deepseek-v4-flash"
|
||||
llm_model_tier_c: str = "qwen/qwen3-235b-a22b-2507"
|
||||
llm_model_tier_d: str = "openai/gpt-oss-20b"
|
||||
openrouter_base_url: str = "https://openrouter.ai/api/v1"
|
||||
|
||||
run_name: str = "phase1-spike-001"
|
||||
|
||||
@@ -14,11 +14,11 @@ from tenacity import (
|
||||
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"
|
||||
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/qwen3-235b-a22b-2507"
|
||||
MODEL_TIER_D = "openai/gpt-oss-20b"
|
||||
OPENROUTER_BASE_URL = "https://openrouter.ai/api/v1"
|
||||
|
||||
class EmptyCompletionError(RuntimeError):
|
||||
|
||||
@@ -8,11 +8,11 @@ from typing import Any
|
||||
from ..genome.hypothesis import ModelTier
|
||||
|
||||
PRICE_PER_M_TOKENS: dict[ModelTier, dict[str, float]] = {
|
||||
ModelTier.S: {"input": 15.00, "output": 75.00},
|
||||
ModelTier.A: {"input": 3.00, "output": 15.00},
|
||||
ModelTier.B: {"input": 3.00, "output": 15.00},
|
||||
ModelTier.C: {"input": 0.40, "output": 0.40},
|
||||
ModelTier.D: {"input": 0.10, "output": 0.30},
|
||||
ModelTier.S: {"input": 0.50, "output": 3.00},
|
||||
ModelTier.A: {"input": 0.14, "output": 0.28},
|
||||
ModelTier.B: {"input": 0.14, "output": 0.28},
|
||||
ModelTier.C: {"input": 0.071, "output": 0.10},
|
||||
ModelTier.D: {"input": 0.03, "output": 0.14},
|
||||
}
|
||||
|
||||
|
||||
|
||||
Reference in New Issue
Block a user