jpmschweitzerandClaude Fable 5
23217bdb26
Each pipeline phase owns one llama-server slot (steward 0, orchestrator 1, synthesizer 2), carried as id_slot in extra_body through the same mechanism tool_choice already uses, so the phase's stable prompt prefix stays in that slot's KV cache and a turn re-prefills only its new tokens. Off by default; a no-op on the Claude backend and ignored by Ollama, so the flag is safe on any backend and the cutover itself stays a pure env swap. The merge helper preserves existing extra_body keys — mutation-checked (dropping the merge fails exactly the test written for it). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
123 lines
5.3 KiB
Python
123 lines
5.3 KiB
Python
"""
|
|
Unit tests for backend selection (Ollama primary, Claude fallback).
|
|
|
|
These tests set the cached health-check globals directly so they are
|
|
deterministic regardless of which services are reachable.
|
|
"""
|
|
|
|
import pytest
|
|
|
|
from src.anthropic import model_selector
|
|
from src.core.config import config
|
|
|
|
|
|
@pytest.fixture
|
|
def local_first(monkeypatch):
|
|
"""Baseline: local-first config, both backends healthy."""
|
|
monkeypatch.setattr(config, "PREFER_CLOUD_BACKEND", False)
|
|
monkeypatch.setattr(config, "ANTHROPIC_API_KEY", "sk-test-fake")
|
|
monkeypatch.setattr(model_selector, "_claude_available", True)
|
|
monkeypatch.setattr(model_selector, "_ollama_available", True)
|
|
|
|
|
|
class TestResolveBackend:
|
|
def test_default_is_ollama(self, local_first):
|
|
assert model_selector.resolve_backend() == "ollama"
|
|
|
|
def test_prefer_cloud_config_selects_claude(self, local_first, monkeypatch):
|
|
monkeypatch.setattr(config, "PREFER_CLOUD_BACKEND", True)
|
|
assert model_selector.resolve_backend() == "claude"
|
|
|
|
def test_prefer_cloud_override_selects_claude(self, local_first):
|
|
assert model_selector.resolve_backend(prefer_cloud=True) == "claude"
|
|
|
|
def test_prefer_cloud_without_claude_falls_back_to_ollama(self, local_first, monkeypatch):
|
|
monkeypatch.setattr(config, "PREFER_CLOUD_BACKEND", True)
|
|
monkeypatch.setattr(model_selector, "_claude_available", False)
|
|
assert model_selector.resolve_backend() == "ollama"
|
|
|
|
def test_ollama_down_falls_back_to_claude(self, local_first, monkeypatch):
|
|
monkeypatch.setattr(model_selector, "_ollama_available", False)
|
|
assert model_selector.resolve_backend() == "claude"
|
|
|
|
def test_ollama_down_without_claude_stays_ollama(self, local_first, monkeypatch):
|
|
monkeypatch.setattr(model_selector, "_ollama_available", False)
|
|
monkeypatch.setattr(model_selector, "_claude_available", False)
|
|
assert model_selector.resolve_backend() == "ollama"
|
|
|
|
def test_unknown_ollama_state_counts_as_available(self, local_first, monkeypatch):
|
|
monkeypatch.setattr(model_selector, "_ollama_available", None)
|
|
assert model_selector.resolve_backend() == "ollama"
|
|
|
|
|
|
class TestGetModel:
|
|
def test_ollama_backend_returns_openai_chat_model(self, local_first):
|
|
from pydantic_ai.models.openai import OpenAIChatModel
|
|
|
|
model = model_selector.get_model()
|
|
assert isinstance(model, OpenAIChatModel)
|
|
assert model.model_name == config.OLLAMA_DEFAULT_MODEL
|
|
|
|
def test_claude_backend_returns_anthropic_model(self, local_first):
|
|
from pydantic_ai.models.anthropic import AnthropicModel
|
|
|
|
model = model_selector.get_model(prefer_cloud=True)
|
|
assert isinstance(model, AnthropicModel)
|
|
assert model.model_name == config.ANTHROPIC_MODEL
|
|
|
|
|
|
class TestToolChoiceSettings:
|
|
def test_ollama_forces_tool_choice(self, local_first):
|
|
settings = model_selector.get_tool_choice_settings()
|
|
assert settings.get("extra_body") == {"tool_choice": "required"}
|
|
|
|
def test_claude_uses_native_tool_choice(self, local_first, monkeypatch):
|
|
monkeypatch.setattr(config, "PREFER_CLOUD_BACKEND", True)
|
|
settings = model_selector.get_tool_choice_settings()
|
|
assert not settings.get("extra_body")
|
|
|
|
|
|
class TestGetModelInfo:
|
|
def test_reports_ollama_primary(self, local_first):
|
|
info = model_selector.get_model_info()
|
|
assert info["backend"] == "ollama"
|
|
assert info["model"] == config.OLLAMA_DEFAULT_MODEL
|
|
assert info["ollama_available"] is True
|
|
assert info["claude_available"] is True
|
|
assert info["prefer_cloud"] is False
|
|
|
|
def test_reports_claude_when_ollama_down(self, local_first, monkeypatch):
|
|
monkeypatch.setattr(model_selector, "_ollama_available", False)
|
|
info = model_selector.get_model_info()
|
|
assert info["backend"] == "claude"
|
|
assert info["model"] == config.ANTHROPIC_MODEL
|
|
|
|
|
|
class TestWithSlotPinning:
|
|
def test_disabled_returns_settings_unchanged(self, local_first, monkeypatch):
|
|
monkeypatch.setattr(config, "BACKEND_SLOT_PINNING", False)
|
|
base = model_selector.get_tool_choice_settings()
|
|
assert model_selector.with_slot_pinning(base, slot=1) is base
|
|
assert model_selector.with_slot_pinning(None, slot=2) is None
|
|
|
|
def test_enabled_merges_slot_with_existing_extra_body(self, local_first, monkeypatch):
|
|
monkeypatch.setattr(config, "BACKEND_SLOT_PINNING", True)
|
|
settings = model_selector.with_slot_pinning(
|
|
model_selector.get_tool_choice_settings(), slot=1
|
|
)
|
|
extra_body = settings["extra_body"]
|
|
assert extra_body["id_slot"] == 1
|
|
# tool_choice from the base settings survives the merge
|
|
assert extra_body["tool_choice"] == "required"
|
|
|
|
def test_enabled_pins_bare_settings(self, local_first, monkeypatch):
|
|
monkeypatch.setattr(config, "BACKEND_SLOT_PINNING", True)
|
|
settings = model_selector.with_slot_pinning(None, slot=2)
|
|
assert settings["extra_body"] == {"id_slot": 2}
|
|
|
|
def test_claude_backend_never_pinned(self, local_first, monkeypatch):
|
|
monkeypatch.setattr(config, "BACKEND_SLOT_PINNING", True)
|
|
monkeypatch.setattr(config, "PREFER_CLOUD_BACKEND", True)
|
|
base = model_selector.get_tool_choice_settings()
|
|
assert model_selector.with_slot_pinning(base, slot=1) is base
|