hermes-agent/tests/run_agent/test_anthropic_prompt_cache_policy.py

"""Tests for AIAgent._anthropic_prompt_cache_policy().

The policy returns ``(should_cache, use_native_layout)`` for five endpoint
classes. The test matrix pins the decision for each so a regression (e.g.
silently dropping caching on third-party Anthropic gateways, or applying
the native layout on OpenRouter) surfaces loudly.
"""

from __future__ import annotations

from unittest.mock import MagicMock

from run_agent import AIAgent


def _make_agent(
    *,
    provider: str = "openrouter",
    base_url: str = "https://openrouter.ai/api/v1",
    api_mode: str = "chat_completions",
    model: str = "anthropic/claude-sonnet-4.6",
) -> AIAgent:
    agent = AIAgent.__new__(AIAgent)
    agent.provider = provider
    agent.base_url = base_url
    agent.api_mode = api_mode
    agent.model = model
    agent._base_url_lower = (base_url or "").lower()
    agent.client = MagicMock()
    agent.quiet_mode = True
    return agent


class TestNativeAnthropic:
    def test_claude_on_native_anthropic_caches_with_native_layout(self):
        agent = _make_agent(
            provider="anthropic",
            base_url="https://api.anthropic.com",
            api_mode="anthropic_messages",
            model="claude-sonnet-4-6",
        )
        assert agent._anthropic_prompt_cache_policy() == (True, True)

    def test_api_anthropic_host_detected_even_when_provider_label_differs(self):
        # Some pool configurations label native Anthropic as "anthropic-direct"
        # or similar; falling back to hostname keeps caching on.
        agent = _make_agent(
            provider="anthropic-direct",
            base_url="https://api.anthropic.com",
            api_mode="anthropic_messages",
            model="claude-opus-4.6",
        )
        assert agent._anthropic_prompt_cache_policy() == (True, True)


class TestOpenRouter:
    def test_claude_on_openrouter_caches_with_envelope_layout(self):
        agent = _make_agent(
            provider="openrouter",
            base_url="https://openrouter.ai/api/v1",
            api_mode="chat_completions",
            model="anthropic/claude-sonnet-4.6",
        )
        should, native = agent._anthropic_prompt_cache_policy()
        assert should is True
        assert native is False  # OpenRouter uses envelope layout

    def test_non_claude_on_openrouter_does_not_cache(self):
        agent = _make_agent(
            provider="openrouter",
            base_url="https://openrouter.ai/api/v1",
            api_mode="chat_completions",
            model="openai/gpt-5.4",
        )
        assert agent._anthropic_prompt_cache_policy() == (False, False)


class TestThirdPartyAnthropicGateway:
    """Third-party gateways speaking the Anthropic protocol (MiniMax, Zhipu GLM, LiteLLM)."""

    def test_minimax_claude_via_anthropic_messages(self):
        agent = _make_agent(
            provider="custom",
            base_url="https://api.minimax.io/anthropic",
            api_mode="anthropic_messages",
            model="claude-sonnet-4-6",
        )
        should, native = agent._anthropic_prompt_cache_policy()
        assert should is True, "Third-party Anthropic gateway with Claude must cache"
        assert native is True, "Third-party Anthropic gateway uses native cache_control layout"

    def test_third_party_without_claude_name_does_not_cache(self):
        # A provider exposing e.g. GLM via anthropic_messages transport — we
        # don't know whether it supports cache_control, so stay conservative.
        agent = _make_agent(
            provider="custom",
            base_url="https://api.minimax.io/anthropic",
            api_mode="anthropic_messages",
            model="minimax-m2.7",
        )
        assert agent._anthropic_prompt_cache_policy() == (False, False)


class TestOpenAIWireFormatOnCustomProvider:
    """A custom provider using chat_completions (OpenAI wire) should NOT get caching."""

    def test_custom_openai_wire_does_not_cache_even_with_claude_name(self):
        # This is the blocklist risk #9621 failed to avoid: sending
        # cache_control fields in OpenAI-wire JSON can trip strict providers
        # that reject unknown keys.  Stay off unless the transport is
        # explicitly anthropic_messages or the aggregator is OpenRouter.
        agent = _make_agent(
            provider="custom",
            base_url="https://api.fireworks.ai/inference/v1",
            api_mode="chat_completions",
            model="claude-sonnet-4",
        )
        assert agent._anthropic_prompt_cache_policy() == (False, False)


class TestExplicitOverrides:
    """Policy accepts keyword overrides for switch_model / fallback activation."""

    def test_overrides_take_precedence_over_self(self):
        agent = _make_agent(
            provider="openrouter",
            base_url="https://openrouter.ai/api/v1",
            api_mode="chat_completions",
            model="openai/gpt-5.4",
        )
        # Simulate switch_model evaluating cache policy for a Claude target
        # before self.model is mutated.
        should, native = agent._anthropic_prompt_cache_policy(
            model="anthropic/claude-sonnet-4.6",
        )
        assert (should, native) == (True, False)

    def test_fallback_target_evaluated_independently(self):
        # Starting on native Anthropic but falling back to OpenRouter.
        agent = _make_agent(
            provider="anthropic",
            base_url="https://api.anthropic.com",
            api_mode="anthropic_messages",
            model="claude-opus-4.6",
        )
        should, native = agent._anthropic_prompt_cache_policy(
            provider="openrouter",
            base_url="https://openrouter.ai/api/v1",
            api_mode="chat_completions",
            model="anthropic/claude-sonnet-4.6",
        )
        assert (should, native) == (True, False)