feat(llm): full multi-tier S/A/B/C/D with routing + pricing

Estende ModelTier a 5 livelli (S/A/B/C/D) con routing automatico:
S/A/B via Anthropic SDK, C/D via OpenRouter (OpenAI SDK). Aggiunge
prezzi per tier S (Opus), A (Sonnet placeholder) e D (Llama). Refactor
LLMClient.complete con dispatch tramite tier_models map e helper
_call_anthropic / _call_openrouter. Settings esposte per tutti e 5
i modelli env-configurabili.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
2026-05-10 09:18:57 +02:00
parent 7482600146
commit 33d8e275e7
10 changed files with 241 additions and 36 deletions
+16 -4
View File
@@ -45,26 +45,38 @@ def test_settings_requires_tokens(monkeypatch: pytest.MonkeyPatch) -> None:
def test_settings_loads_llm_model_overrides(monkeypatch: pytest.MonkeyPatch) -> None:
monkeypatch.setenv("CERBERO_TESTNET_TOKEN", "tok-test")
monkeypatch.setenv("OPENROUTER_API_KEY", "or-key")
monkeypatch.setenv("LLM_MODEL_TIER_C", "deepseek/deepseek-chat")
monkeypatch.setenv("LLM_MODEL_TIER_S", "claude-mega-x")
monkeypatch.setenv("LLM_MODEL_TIER_A", "claude-premium-y")
monkeypatch.setenv("LLM_MODEL_TIER_B", "claude-opus-4-7")
monkeypatch.setenv("LLM_MODEL_TIER_C", "deepseek/deepseek-chat")
monkeypatch.setenv("LLM_MODEL_TIER_D", "mistralai/mistral-7b")
monkeypatch.setenv("OPENROUTER_BASE_URL", "https://example.com/api/v1")
s = Settings(_env_file=None) # type: ignore[call-arg]
assert s.llm_model_tier_c == "deepseek/deepseek-chat"
assert s.llm_model_tier_s == "claude-mega-x"
assert s.llm_model_tier_a == "claude-premium-y"
assert s.llm_model_tier_b == "claude-opus-4-7"
assert s.llm_model_tier_c == "deepseek/deepseek-chat"
assert s.llm_model_tier_d == "mistralai/mistral-7b"
assert s.openrouter_base_url == "https://example.com/api/v1"
def test_settings_llm_model_defaults(monkeypatch: pytest.MonkeyPatch) -> None:
monkeypatch.setenv("CERBERO_TESTNET_TOKEN", "tok-test")
monkeypatch.setenv("OPENROUTER_API_KEY", "or-key")
monkeypatch.delenv("LLM_MODEL_TIER_C", raising=False)
monkeypatch.delenv("LLM_MODEL_TIER_S", raising=False)
monkeypatch.delenv("LLM_MODEL_TIER_A", raising=False)
monkeypatch.delenv("LLM_MODEL_TIER_B", raising=False)
monkeypatch.delenv("LLM_MODEL_TIER_C", raising=False)
monkeypatch.delenv("LLM_MODEL_TIER_D", raising=False)
monkeypatch.delenv("OPENROUTER_BASE_URL", raising=False)
s = Settings(_env_file=None) # type: ignore[call-arg]
assert s.llm_model_tier_c == "qwen/qwen-2.5-72b-instruct"
assert s.llm_model_tier_s == "claude-opus-4-7"
assert s.llm_model_tier_a == "claude-sonnet-4-6"
assert s.llm_model_tier_b == "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.openrouter_base_url == "https://openrouter.ai/api/v1"