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>

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_a == "anthropic/claude-sonnet-4-6"
-    assert s.llm_model_tier_b == "anthropic/claude-sonnet-4-6"
-    assert s.llm_model_tier_c == "qwen/qwen-2.5-72b-instruct"
-    assert s.llm_model_tier_d == "meta-llama/llama-3.3-70b-instruct"
+    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_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 out.model == "anthropic/claude-sonnet-4-6"
+    assert call_kwargs["model"] == "deepseek/deepseek-v4-flash"
+    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):