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>

.env.example

@@ -11,11 +11,11 @@ OPENROUTER_API_KEY=
 OPENROUTER_BASE_URL=https://openrouter.ai/api/v1
 
 # Models per tier (override Phase 1 defaults if needed)
-LLM_MODEL_TIER_S=anthropic/claude-opus-4-7
+LLM_MODEL_TIER_S=google/gemini-3-flash-preview
-LLM_MODEL_TIER_A=anthropic/claude-sonnet-4-6
+LLM_MODEL_TIER_A=deepseek/deepseek-v4-flash
-LLM_MODEL_TIER_B=anthropic/claude-sonnet-4-6
+LLM_MODEL_TIER_B=deepseek/deepseek-v4-flash
-LLM_MODEL_TIER_C=qwen/qwen-2.5-72b-instruct
+LLM_MODEL_TIER_C=qwen/qwen3-235b-a22b-2507
-LLM_MODEL_TIER_D=meta-llama/llama-3.3-70b-instruct
+LLM_MODEL_TIER_D=openai/gpt-oss-20b
 
 # Run config
 RUN_NAME=phase1-spike-001

README.md

@@ -112,7 +112,7 @@ OPENROUTER_BASE_URL=https://openrouter.ai/api/v1
 LLM_MODEL_TIER_S=anthropic/claude-opus-4-7
 LLM_MODEL_TIER_A=anthropic/claude-sonnet-4-6
 LLM_MODEL_TIER_B=anthropic/claude-sonnet-4-6
-LLM_MODEL_TIER_C=qwen/qwen-2.5-72b-instruct
+LLM_MODEL_TIER_C=qwen/qwen3-235b-a22b-2507
 LLM_MODEL_TIER_D=meta-llama/llama-3.3-70b-instruct
 ```
 

src/multi_swarm/config.py

@@ -25,11 +25,11 @@ class Settings(BaseSettings):
 
     openrouter_api_key: SecretStr
 
-    llm_model_tier_s: str = "anthropic/claude-opus-4-7"
+    llm_model_tier_s: str = "google/gemini-3-flash-preview"
-    llm_model_tier_a: str = "anthropic/claude-sonnet-4-6"
+    llm_model_tier_a: str = "deepseek/deepseek-v4-flash"
-    llm_model_tier_b: str = "anthropic/claude-sonnet-4-6"
+    llm_model_tier_b: str = "deepseek/deepseek-v4-flash"
-    llm_model_tier_c: str = "qwen/qwen-2.5-72b-instruct"
+    llm_model_tier_c: str = "qwen/qwen3-235b-a22b-2507"
-    llm_model_tier_d: str = "meta-llama/llama-3.3-70b-instruct"
+    llm_model_tier_d: str = "openai/gpt-oss-20b"
     openrouter_base_url: str = "https://openrouter.ai/api/v1"
 
     run_name: str = "phase1-spike-001"

src/multi_swarm/llm/client.py

@@ -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_S = "google/gemini-3-flash-preview"
-MODEL_TIER_A = "anthropic/claude-sonnet-4-6"
+MODEL_TIER_A = "deepseek/deepseek-v4-flash"
-MODEL_TIER_B = "anthropic/claude-sonnet-4-6"
+MODEL_TIER_B = "deepseek/deepseek-v4-flash"
-MODEL_TIER_C = "qwen/qwen-2.5-72b-instruct"
+MODEL_TIER_C = "qwen/qwen3-235b-a22b-2507"
-MODEL_TIER_D = "meta-llama/llama-3.3-70b-instruct"
+MODEL_TIER_D = "openai/gpt-oss-20b"
 OPENROUTER_BASE_URL = "https://openrouter.ai/api/v1"
 
 class EmptyCompletionError(RuntimeError):

src/multi_swarm/llm/cost_tracker.py

@@ -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.S: {"input": 0.50, "output": 3.00},
-    ModelTier.A: {"input": 3.00, "output": 15.00},
+    ModelTier.A: {"input": 0.14, "output": 0.28},
-    ModelTier.B: {"input": 3.00, "output": 15.00},
+    ModelTier.B: {"input": 0.14, "output": 0.28},
-    ModelTier.C: {"input": 0.40, "output": 0.40},
+    ModelTier.C: {"input": 0.071, "output": 0.10},
-    ModelTier.D: {"input": 0.10, "output": 0.30},
+    ModelTier.D: {"input": 0.03, "output": 0.14},
 }
 
 

tests/unit/test_config.py

@@ -73,9 +73,9 @@ def test_settings_llm_model_defaults(monkeypatch: pytest.MonkeyPatch) -> None:
 
     s = Settings(_env_file=None)  # type: ignore[call-arg]
 
-    assert s.llm_model_tier_s == "anthropic/claude-opus-4-7"
+    assert s.llm_model_tier_s == "google/gemini-3-flash-preview"
-    assert s.llm_model_tier_a == "anthropic/claude-sonnet-4-6"
+    assert s.llm_model_tier_a == "deepseek/deepseek-v4-flash"
-    assert s.llm_model_tier_b == "anthropic/claude-sonnet-4-6"
+    assert s.llm_model_tier_b == "deepseek/deepseek-v4-flash"
-    assert s.llm_model_tier_c == "qwen/qwen-2.5-72b-instruct"
+    assert s.llm_model_tier_c == "qwen/qwen3-235b-a22b-2507"
-    assert s.llm_model_tier_d == "meta-llama/llama-3.3-70b-instruct"
+    assert s.llm_model_tier_d == "openai/gpt-oss-20b"
     assert s.openrouter_base_url == "https://openrouter.ai/api/v1"

tests/unit/test_cost_tracker.py

@@ -4,12 +4,12 @@ from multi_swarm.llm.cost_tracker import CostTracker, estimate_cost
 
 def test_estimate_cost_tier_c():
     cost = estimate_cost(input_tokens=1_000_000, output_tokens=1_000_000, tier=ModelTier.C)
-    assert cost == 0.40 + 0.40
+    assert cost == 0.071 + 0.10
 
 
 def test_estimate_cost_tier_b():
     cost = estimate_cost(input_tokens=1_000_000, output_tokens=1_000_000, tier=ModelTier.B)
-    assert cost == 3.00 + 15.00
+    assert cost == 0.14 + 0.28
 
 
 def test_tracker_accumulates():
@@ -34,17 +34,17 @@ def test_tracker_per_tier_breakdown():
 
 def test_estimate_cost_tier_s():
     cost = estimate_cost(input_tokens=1_000_000, output_tokens=1_000_000, tier=ModelTier.S)
-    assert cost == 15.00 + 75.00
+    assert cost == 0.50 + 3.00
 
 
 def test_estimate_cost_tier_a():
     cost = estimate_cost(input_tokens=1_000_000, output_tokens=1_000_000, tier=ModelTier.A)
-    assert cost == 3.00 + 15.00
+    assert cost == 0.14 + 0.28
 
 
 def test_estimate_cost_tier_d():
     cost = estimate_cost(input_tokens=1_000_000, output_tokens=1_000_000, tier=ModelTier.D)
-    assert cost == 0.10 + 0.30
+    assert cost == 0.03 + 0.14
 
 
 def test_tracker_summary_contains_all_five_tiers():

tests/unit/test_llm_client.py

@@ -54,8 +54,8 @@ def test_completion_tier_b_uses_openrouter_with_anthropic_model(mocker):
     assert out.output_tokens == 150
     assert out.tier == ModelTier.B
     call_kwargs = fake_openai.chat.completions.create.call_args.kwargs
-    assert call_kwargs["model"] == "anthropic/claude-sonnet-4-6"
+    assert call_kwargs["model"] == "deepseek/deepseek-v4-flash"
-    assert out.model == "anthropic/claude-sonnet-4-6"
+    assert out.model == "deepseek/deepseek-v4-flash"
 
 
 @pytest.mark.slow
@@ -138,9 +138,9 @@ def test_completion_tier_s_uses_openrouter_with_anthropic_model(mocker):
 
     fake_openai.chat.completions.create.assert_called_once()
     call_kwargs = fake_openai.chat.completions.create.call_args.kwargs
-    assert call_kwargs["model"] == "anthropic/claude-opus-4-7"
+    assert call_kwargs["model"] == "google/gemini-3-flash-preview"
     assert out.tier == ModelTier.S
-    assert out.model == "anthropic/claude-opus-4-7"
+    assert out.model == "google/gemini-3-flash-preview"
 
 
 def test_completion_tier_a_uses_openrouter_with_anthropic_model(mocker):
@@ -157,9 +157,9 @@ def test_completion_tier_a_uses_openrouter_with_anthropic_model(mocker):
 
     fake_openai.chat.completions.create.assert_called_once()
     call_kwargs = fake_openai.chat.completions.create.call_args.kwargs
-    assert call_kwargs["model"] == "anthropic/claude-sonnet-4-6"
+    assert call_kwargs["model"] == "deepseek/deepseek-v4-flash"
     assert out.tier == ModelTier.A
-    assert out.model == "anthropic/claude-sonnet-4-6"
+    assert out.model == "deepseek/deepseek-v4-flash"
 
 
 def test_completion_tier_d_uses_openrouter_with_llama(mocker):
@@ -178,9 +178,9 @@ def test_completion_tier_d_uses_openrouter_with_llama(mocker):
 
     fake_openai.chat.completions.create.assert_called_once()
     call_kwargs = fake_openai.chat.completions.create.call_args.kwargs
-    assert call_kwargs["model"] == "meta-llama/llama-3.3-70b-instruct"
+    assert call_kwargs["model"] == "openai/gpt-oss-20b"
     assert out.tier == ModelTier.D
-    assert out.model == "meta-llama/llama-3.3-70b-instruct"
+    assert out.model == "openai/gpt-oss-20b"
 
 
 def test_completion_uses_custom_model_tier_s(mocker):