revert(config): rollback tier C a qwen-2.5-72b-instruct (qwen3-235b inferiore)

Run controllo phase2-qwen25-control-001 (seed 42, stessa pipeline Phase 2,
solo tier C switched) ha dimostrato che qwen-2.5-72b è qualitativamente
SUPERIORE a qwen3-235b sul nostro workload:

| metrica           | qwen3-235b | qwen-2.5-72b | delta |
| ----------------- | ---------- | ------------ | ----- |
| max fitness       | 0.0238     | 0.0311       | +30%  |
| median > 0 in gen | mai        | 4 gen su 10  | --    |
| entropy media     | 0.199      | 0.85         | 4.3x  |
| genomi fit > 0    | 5          | 10           | 2x    |
| parse success     | 97.7%      | 100%         | +     |
| durata            | 50 min     | 28 min       | 0.56x |
| LLM calls         | 148        | 90           | 0.61x |
| cost USD          | 0.0223     | 0.0122       | 0.55x |

Controintuitivo: 235B con context 262k era atteso superiore al 72B legacy.
In pratica qwen3-235b in tier C produce strategie meno diverse,
meno parsabili e meno ottimizzabili dal GA.

Ripristinati prezzi cost_tracker tier C a 0.40/0.40 (qwen-2.5-72b).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

.env.example

@@ -14,7 +14,7 @@ OPENROUTER_BASE_URL=https://openrouter.ai/api/v1
 LLM_MODEL_TIER_S=google/gemini-3-flash-preview
 LLM_MODEL_TIER_A=deepseek/deepseek-v4-flash
 LLM_MODEL_TIER_B=deepseek/deepseek-v4-flash
-LLM_MODEL_TIER_C=qwen/qwen3-235b-a22b-2507
+LLM_MODEL_TIER_C=qwen/qwen-2.5-72b-instruct
 LLM_MODEL_TIER_D=openai/gpt-oss-20b
 
 # Run config

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/qwen3-235b-a22b-2507
+LLM_MODEL_TIER_C=qwen/qwen-2.5-72b-instruct
 LLM_MODEL_TIER_D=meta-llama/llama-3.3-70b-instruct
 ```
 

src/multi_swarm/config.py

@@ -28,7 +28,7 @@ class Settings(BaseSettings):
     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_c: str = "qwen/qwen-2.5-72b-instruct"
     llm_model_tier_d: str = "openai/gpt-oss-20b"
     openrouter_base_url: str = "https://openrouter.ai/api/v1"
 

src/multi_swarm/llm/client.py

@@ -17,7 +17,7 @@ from ..genome.hypothesis import HypothesisAgentGenome, ModelTier
 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_C = "qwen/qwen-2.5-72b-instruct"
 MODEL_TIER_D = "openai/gpt-oss-20b"
 OPENROUTER_BASE_URL = "https://openrouter.ai/api/v1"
 

src/multi_swarm/llm/cost_tracker.py

@@ -11,7 +11,7 @@ PRICE_PER_M_TOKENS: dict[ModelTier, dict[str, float]] = {
     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.C: {"input": 0.40, "output": 0.40},
     ModelTier.D: {"input": 0.03, "output": 0.14},
 }
 

tests/unit/test_config.py

@@ -76,6 +76,6 @@ def test_settings_llm_model_defaults(monkeypatch: pytest.MonkeyPatch) -> None:
     assert s.llm_model_tier_s == "google/gemini-3-flash-preview"
     assert s.llm_model_tier_a == "deepseek/deepseek-v4-flash"
     assert s.llm_model_tier_b == "deepseek/deepseek-v4-flash"
-    assert s.llm_model_tier_c == "qwen/qwen3-235b-a22b-2507"
+    assert s.llm_model_tier_c == "qwen/qwen-2.5-72b-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

@@ -4,7 +4,7 @@ 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 == 0.071 + 0.10
+    assert cost == 0.40 + 0.40
 
 
 def test_estimate_cost_tier_b():