"""Tests for agent.auxiliary_client resolution chain, provider overrides, and model overrides."""

import json
import logging
import os
from pathlib import Path
from unittest.mock import patch, MagicMock, AsyncMock

import pytest

from agent.auxiliary_client import (
    get_text_auxiliary_client,
    get_available_vision_backends,
    resolve_vision_provider_client,
    resolve_provider_client,
    auxiliary_max_tokens_param,
    call_llm,
    async_call_llm,
    _build_call_kwargs,
    _read_codex_access_token,
    _get_provider_chain,
    _is_payment_error,
    _normalize_aux_provider,
    _try_payment_fallback,
    _resolve_auto,
)


@pytest.fixture(autouse=True)
def _clean_env(monkeypatch):
    """Strip provider env vars so each test starts clean."""
    for key in (
        "OPENROUTER_API_KEY", "OPENAI_BASE_URL", "OPENAI_API_KEY",
        "OPENAI_MODEL", "LLM_MODEL", "NOUS_INFERENCE_BASE_URL",
        "ANTHROPIC_API_KEY", "ANTHROPIC_TOKEN", "CLAUDE_CODE_OAUTH_TOKEN",
    ):
        monkeypatch.delenv(key, raising=False)


@pytest.fixture
def codex_auth_dir(tmp_path, monkeypatch):
    """Provide a writable ~/.codex/ directory with a valid auth.json."""
    codex_dir = tmp_path / ".codex"
    codex_dir.mkdir()
    auth_file = codex_dir / "auth.json"
    auth_file.write_text(json.dumps({
        "tokens": {
            "access_token": "codex-test-token-abc123",
            "refresh_token": "codex-refresh-xyz",
        }
    }))
    monkeypatch.setattr(
        "agent.auxiliary_client._read_codex_access_token",
        lambda: "codex-test-token-abc123",
    )
    return codex_dir


class TestNormalizeAuxProvider:
    def test_maps_github_copilot_aliases(self):
        assert _normalize_aux_provider("github") == "copilot"
        assert _normalize_aux_provider("github-copilot") == "copilot"
        assert _normalize_aux_provider("github-models") == "copilot"

    def test_maps_github_copilot_acp_aliases(self):
        assert _normalize_aux_provider("github-copilot-acp") == "copilot-acp"
        assert _normalize_aux_provider("copilot-acp-agent") == "copilot-acp"


class TestReadCodexAccessToken:
    def test_valid_auth_store(self, tmp_path, monkeypatch):
        hermes_home = tmp_path / "hermes"
        hermes_home.mkdir(parents=True, exist_ok=True)
        (hermes_home / "auth.json").write_text(json.dumps({
            "version": 1,
            "providers": {
                "openai-codex": {
                    "tokens": {"access_token": "tok-123", "refresh_token": "r-456"},
                },
            },
        }))
        monkeypatch.setenv("HERMES_HOME", str(hermes_home))
        result = _read_codex_access_token()
        assert result == "tok-123"

    def test_pool_without_selected_entry_falls_back_to_auth_store(self, tmp_path, monkeypatch):
        hermes_home = tmp_path / "hermes"
        hermes_home.mkdir(parents=True, exist_ok=True)
        monkeypatch.setenv("HERMES_HOME", str(hermes_home))

        valid_jwt = "eyJhbGciOiJSUzI1NiJ9.eyJleHAiOjk5OTk5OTk5OTl9.sig"
        with patch("agent.auxiliary_client._select_pool_entry", return_value=(True, None)), \
             patch("hermes_cli.auth._read_codex_tokens", return_value={
                 "tokens": {"access_token": valid_jwt, "refresh_token": "refresh"}
             }):
            result = _read_codex_access_token()

        assert result == valid_jwt

    def test_missing_returns_none(self, tmp_path, monkeypatch):
        hermes_home = tmp_path / "hermes"
        hermes_home.mkdir(parents=True, exist_ok=True)
        (hermes_home / "auth.json").write_text(json.dumps({"version": 1, "providers": {}}))
        monkeypatch.setenv("HERMES_HOME", str(hermes_home))
        with patch("agent.auxiliary_client._select_pool_entry", return_value=(False, None)):
            result = _read_codex_access_token()
        assert result is None

    def test_empty_token_returns_none(self, tmp_path, monkeypatch):
        hermes_home = tmp_path / "hermes"
        hermes_home.mkdir(parents=True, exist_ok=True)
        (hermes_home / "auth.json").write_text(json.dumps({
            "version": 1,
            "providers": {
                "openai-codex": {
                    "tokens": {"access_token": "  ", "refresh_token": "r"},
                },
            },
        }))
        monkeypatch.setenv("HERMES_HOME", str(hermes_home))
        result = _read_codex_access_token()
        assert result is None

    def test_malformed_json_returns_none(self, tmp_path):
        codex_dir = tmp_path / ".codex"
        codex_dir.mkdir()
        (codex_dir / "auth.json").write_text("{bad json")
        with patch("agent.auxiliary_client.Path.home", return_value=tmp_path):
            result = _read_codex_access_token()
        assert result is None

    def test_missing_tokens_key_returns_none(self, tmp_path):
        codex_dir = tmp_path / ".codex"
        codex_dir.mkdir()
        (codex_dir / "auth.json").write_text(json.dumps({"other": "data"}))
        with patch("agent.auxiliary_client.Path.home", return_value=tmp_path):
            result = _read_codex_access_token()
        assert result is None


    def test_expired_jwt_returns_none(self, tmp_path, monkeypatch):
        """Expired JWT tokens should be skipped so auto chain continues."""
        import base64
        import time as _time

        # Build a JWT with exp in the past
        header = base64.urlsafe_b64encode(b'{"alg":"RS256","typ":"JWT"}').rstrip(b"=").decode()
        payload_data = json.dumps({"exp": int(_time.time()) - 3600}).encode()
        payload = base64.urlsafe_b64encode(payload_data).rstrip(b"=").decode()
        expired_jwt = f"{header}.{payload}.fakesig"

        hermes_home = tmp_path / "hermes"
        hermes_home.mkdir(parents=True, exist_ok=True)
        (hermes_home / "auth.json").write_text(json.dumps({
            "version": 1,
            "providers": {
                "openai-codex": {
                    "tokens": {"access_token": expired_jwt, "refresh_token": "r"},
                },
            },
        }))
        monkeypatch.setenv("HERMES_HOME", str(hermes_home))
        with patch("agent.auxiliary_client._select_pool_entry", return_value=(False, None)):
            result = _read_codex_access_token()
        assert result is None, "Expired JWT should return None"

    def test_valid_jwt_returns_token(self, tmp_path, monkeypatch):
        """Non-expired JWT tokens should be returned."""
        import base64
        import time as _time

        header = base64.urlsafe_b64encode(b'{"alg":"RS256","typ":"JWT"}').rstrip(b"=").decode()
        payload_data = json.dumps({"exp": int(_time.time()) + 3600}).encode()
        payload = base64.urlsafe_b64encode(payload_data).rstrip(b"=").decode()
        valid_jwt = f"{header}.{payload}.fakesig"

        hermes_home = tmp_path / "hermes"
        hermes_home.mkdir(parents=True, exist_ok=True)
        (hermes_home / "auth.json").write_text(json.dumps({
            "version": 1,
            "providers": {
                "openai-codex": {
                    "tokens": {"access_token": valid_jwt, "refresh_token": "r"},
                },
            },
        }))
        monkeypatch.setenv("HERMES_HOME", str(hermes_home))
        result = _read_codex_access_token()
        assert result == valid_jwt

    def test_non_jwt_token_passes_through(self, tmp_path, monkeypatch):
        """Non-JWT tokens (no dots) should be returned as-is."""
        hermes_home = tmp_path / "hermes"
        hermes_home.mkdir(parents=True, exist_ok=True)
        (hermes_home / "auth.json").write_text(json.dumps({
            "version": 1,
            "providers": {
                "openai-codex": {
                    "tokens": {"access_token": "plain-token-no-jwt", "refresh_token": "r"},
                },
            },
        }))
        monkeypatch.setenv("HERMES_HOME", str(hermes_home))
        result = _read_codex_access_token()
        assert result == "plain-token-no-jwt"


class TestAnthropicOAuthFlag:
    """Test that OAuth tokens get is_oauth=True in auxiliary Anthropic client."""

    def test_oauth_token_sets_flag(self, monkeypatch):
        """OAuth tokens (sk-ant-oat01-*) should create client with is_oauth=True."""
        monkeypatch.setenv("ANTHROPIC_TOKEN", "sk-ant-oat01-test-token")
        with patch("agent.anthropic_adapter.build_anthropic_client") as mock_build:
            mock_build.return_value = MagicMock()
            from agent.auxiliary_client import _try_anthropic, AnthropicAuxiliaryClient
            client, model = _try_anthropic()
            assert client is not None
            assert isinstance(client, AnthropicAuxiliaryClient)
            # The adapter inside should have is_oauth=True
            adapter = client.chat.completions
            assert adapter._is_oauth is True

    def test_api_key_no_oauth_flag(self, monkeypatch):
        """Regular API keys (sk-ant-api-*) should create client with is_oauth=False."""
        with patch("agent.anthropic_adapter.resolve_anthropic_token", return_value="sk-ant-api03-testkey1234"), \
             patch("agent.anthropic_adapter.build_anthropic_client") as mock_build, \
             patch("agent.auxiliary_client._select_pool_entry", return_value=(False, None)):
            mock_build.return_value = MagicMock()
            from agent.auxiliary_client import _try_anthropic, AnthropicAuxiliaryClient
            client, model = _try_anthropic()
            assert client is not None
            assert isinstance(client, AnthropicAuxiliaryClient)
            adapter = client.chat.completions
            assert adapter._is_oauth is False

    def test_pool_entry_takes_priority_over_legacy_resolution(self):
        class _Entry:
            access_token = "sk-ant-oat01-pooled"
            base_url = "https://api.anthropic.com"

        class _Pool:
            def has_credentials(self):
                return True

            def select(self):
                return _Entry()

        with (
            patch("agent.auxiliary_client.load_pool", return_value=_Pool()),
            patch("agent.anthropic_adapter.resolve_anthropic_token", side_effect=AssertionError("legacy path should not run")),
            patch("agent.anthropic_adapter.build_anthropic_client", return_value=MagicMock()) as mock_build,
        ):
            from agent.auxiliary_client import _try_anthropic

            client, model = _try_anthropic()

        assert client is not None
        assert model == "claude-haiku-4-5-20251001"
        assert mock_build.call_args.args[0] == "sk-ant-oat01-pooled"


class TestBuildCodexClient:
    def test_pool_without_selected_entry_falls_back_to_auth_store(self):
        with (
            patch("agent.auxiliary_client._select_pool_entry", return_value=(True, None)),
            patch("agent.auxiliary_client._read_codex_access_token", return_value="codex-auth-token"),
            patch("agent.auxiliary_client.OpenAI") as mock_openai,
        ):
            mock_openai.return_value = MagicMock()
            from agent.auxiliary_client import _build_codex_client

            client, model = _build_codex_client("gpt-5.4")

        assert client is not None
        assert model == "gpt-5.4"
        assert mock_openai.call_args.kwargs["api_key"] == "codex-auth-token"
        assert mock_openai.call_args.kwargs["base_url"] == "https://chatgpt.com/backend-api/codex"

    def test_rejects_missing_model(self):
        """Callers must pass an explicit model; no hardcoded default."""
        from agent.auxiliary_client import _build_codex_client

        client, model = _build_codex_client("")
        assert client is None
        assert model is None


class TestExpiredCodexFallback:
    """Test that expired Codex tokens don't block the auto chain."""

    def test_expired_codex_falls_through_to_next(self, tmp_path, monkeypatch):
        """When Codex token is expired, auto chain should skip it and try next provider."""
        import base64
        import time as _time

        # Expired Codex JWT
        header = base64.urlsafe_b64encode(b'{"alg":"RS256","typ":"JWT"}').rstrip(b"=").decode()
        payload_data = json.dumps({"exp": int(_time.time()) - 3600}).encode()
        payload = base64.urlsafe_b64encode(payload_data).rstrip(b"=").decode()
        expired_jwt = f"{header}.{payload}.fakesig"

        hermes_home = tmp_path / "hermes"
        hermes_home.mkdir(parents=True, exist_ok=True)
        (hermes_home / "auth.json").write_text(json.dumps({
            "version": 1,
            "providers": {
                "openai-codex": {
                    "tokens": {"access_token": expired_jwt, "refresh_token": "r"},
                },
            },
        }))
        monkeypatch.setenv("HERMES_HOME", str(hermes_home))

        # Set up Anthropic as fallback
        monkeypatch.setenv("ANTHROPIC_TOKEN", "sk-ant-oat01-test-fallback")
        with patch("agent.anthropic_adapter.build_anthropic_client") as mock_build:
            mock_build.return_value = MagicMock()
            from agent.auxiliary_client import _resolve_auto, AnthropicAuxiliaryClient
            client, model = _resolve_auto()
            # Should NOT be Codex, should be Anthropic (or another available provider)
            assert not isinstance(client, type(None)), "Should find a provider after expired Codex"


    def test_expired_codex_openrouter_wins(self, tmp_path, monkeypatch):
        """With expired Codex + OpenRouter key, OpenRouter should win (1st in chain)."""
        import base64
        import time as _time

        header = base64.urlsafe_b64encode(b'{"alg":"RS256","typ":"JWT"}').rstrip(b"=").decode()
        payload_data = json.dumps({"exp": int(_time.time()) - 3600}).encode()
        payload = base64.urlsafe_b64encode(payload_data).rstrip(b"=").decode()
        expired_jwt = f"{header}.{payload}.fakesig"

        hermes_home = tmp_path / "hermes"
        hermes_home.mkdir(parents=True, exist_ok=True)
        (hermes_home / "auth.json").write_text(json.dumps({
            "version": 1,
            "providers": {
                "openai-codex": {
                    "tokens": {"access_token": expired_jwt, "refresh_token": "r"},
                },
            },
        }))
        monkeypatch.setenv("HERMES_HOME", str(hermes_home))
        monkeypatch.setenv("OPENROUTER_API_KEY", "or-test-key")

        with patch("agent.auxiliary_client.OpenAI") as mock_openai:
            mock_openai.return_value = MagicMock()
            from agent.auxiliary_client import _resolve_auto
            client, model = _resolve_auto()
            assert client is not None
            # OpenRouter is 1st in chain, should win
            mock_openai.assert_called()

    def test_expired_codex_custom_endpoint_wins(self, tmp_path, monkeypatch):
        """With expired Codex + custom endpoint (Ollama), custom should win (3rd in chain)."""
        import base64
        import time as _time

        header = base64.urlsafe_b64encode(b'{"alg":"RS256","typ":"JWT"}').rstrip(b"=").decode()
        payload_data = json.dumps({"exp": int(_time.time()) - 3600}).encode()
        payload = base64.urlsafe_b64encode(payload_data).rstrip(b"=").decode()
        expired_jwt = f"{header}.{payload}.fakesig"

        hermes_home = tmp_path / "hermes"
        hermes_home.mkdir(parents=True, exist_ok=True)
        (hermes_home / "auth.json").write_text(json.dumps({
            "version": 1,
            "providers": {
                "openai-codex": {
                    "tokens": {"access_token": expired_jwt, "refresh_token": "r"},
                },
            },
        }))
        monkeypatch.setenv("HERMES_HOME", str(hermes_home))

        # Simulate Ollama or custom endpoint
        with patch("agent.auxiliary_client._resolve_custom_runtime",
                   return_value=("http://localhost:11434/v1", "sk-dummy")):
            with patch("agent.auxiliary_client.OpenAI") as mock_openai:
                mock_openai.return_value = MagicMock()
                from agent.auxiliary_client import _resolve_auto
                client, model = _resolve_auto()
                assert client is not None


    def test_hermes_oauth_file_sets_oauth_flag(self, monkeypatch):
        """OAuth-style tokens should get is_oauth=*** (token is not sk-ant-api-*)."""
        # Mock resolve_anthropic_token to return an OAuth-style token
        with patch("agent.anthropic_adapter.resolve_anthropic_token", return_value="sk-ant-oat-hermes-token"), \
             patch("agent.anthropic_adapter.build_anthropic_client") as mock_build, \
             patch("agent.auxiliary_client._select_pool_entry", return_value=(False, None)):
            mock_build.return_value = MagicMock()
            from agent.auxiliary_client import _try_anthropic, AnthropicAuxiliaryClient
            client, model = _try_anthropic()
            assert client is not None, "Should resolve token"
            adapter = client.chat.completions
            assert adapter._is_oauth is True, "Non-sk-ant-api token should set is_oauth=True"

    def test_jwt_missing_exp_passes_through(self, tmp_path, monkeypatch):
        """JWT with valid JSON but no exp claim should pass through."""
        import base64
        header = base64.urlsafe_b64encode(b'{"alg":"RS256","typ":"JWT"}').rstrip(b"=").decode()
        payload_data = json.dumps({"sub": "user123"}).encode()  # no exp
        payload = base64.urlsafe_b64encode(payload_data).rstrip(b"=").decode()
        no_exp_jwt = f"{header}.{payload}.fakesig"

        hermes_home = tmp_path / "hermes"
        hermes_home.mkdir(parents=True, exist_ok=True)
        (hermes_home / "auth.json").write_text(json.dumps({
            "version": 1,
            "providers": {
                "openai-codex": {
                    "tokens": {"access_token": no_exp_jwt, "refresh_token": "r"},
                },
            },
        }))
        monkeypatch.setenv("HERMES_HOME", str(hermes_home))
        result = _read_codex_access_token()
        assert result == no_exp_jwt, "JWT without exp should pass through"

    def test_jwt_invalid_json_payload_passes_through(self, tmp_path, monkeypatch):
        """JWT with valid base64 but invalid JSON payload should pass through."""
        import base64
        header = base64.urlsafe_b64encode(b'{"alg":"RS256"}').rstrip(b"=").decode()
        payload = base64.urlsafe_b64encode(b"not-json-content").rstrip(b"=").decode()
        bad_jwt = f"{header}.{payload}.fakesig"

        hermes_home = tmp_path / "hermes"
        hermes_home.mkdir(parents=True, exist_ok=True)
        (hermes_home / "auth.json").write_text(json.dumps({
            "version": 1,
            "providers": {
                "openai-codex": {
                    "tokens": {"access_token": bad_jwt, "refresh_token": "r"},
                },
            },
        }))
        monkeypatch.setenv("HERMES_HOME", str(hermes_home))
        result = _read_codex_access_token()
        assert result == bad_jwt, "JWT with invalid JSON payload should pass through"

    def test_claude_code_oauth_env_sets_flag(self, monkeypatch):
        """CLAUDE_CODE_OAUTH_TOKEN env var should get is_oauth=True."""
        monkeypatch.setenv("CLAUDE_CODE_OAUTH_TOKEN", "sk-ant-oat-cc-test-token")
        monkeypatch.delenv("ANTHROPIC_TOKEN", raising=False)
        with patch("agent.anthropic_adapter.build_anthropic_client") as mock_build:
            mock_build.return_value = MagicMock()
            from agent.auxiliary_client import _try_anthropic, AnthropicAuxiliaryClient
            client, model = _try_anthropic()
            assert client is not None
            adapter = client.chat.completions
            assert adapter._is_oauth is True


class TestExplicitProviderRouting:
    """Test explicit provider selection bypasses auto chain correctly."""

    def test_explicit_anthropic_api_key(self, monkeypatch):
        """provider='anthropic' + regular API key should work with is_oauth=False."""
        with patch("agent.anthropic_adapter.resolve_anthropic_token", return_value="sk-ant-api-regular-key"), \
             patch("agent.anthropic_adapter.build_anthropic_client") as mock_build, \
             patch("agent.auxiliary_client._select_pool_entry", return_value=(False, None)):
            mock_build.return_value = MagicMock()
            client, model = resolve_provider_client("anthropic")
            assert client is not None
            adapter = client.chat.completions
            assert adapter._is_oauth is False

    def test_explicit_openrouter_pool_exhausted_logs_precise_warning(self, monkeypatch, caplog):
        monkeypatch.delenv("OPENROUTER_API_KEY", raising=False)
        with patch("agent.auxiliary_client._select_pool_entry", return_value=(True, None)):
            with caplog.at_level(logging.WARNING, logger="agent.auxiliary_client"):
                client, model = resolve_provider_client("openrouter")
        assert client is None
        assert model is None
        assert any(
            "credential pool has no usable entries" in record.message
            for record in caplog.records
        )
        assert not any(
            "OPENROUTER_API_KEY not set" in record.message
            for record in caplog.records
        )

    def test_explicit_openrouter_missing_env_keeps_not_set_warning(self, monkeypatch, caplog):
        monkeypatch.delenv("OPENROUTER_API_KEY", raising=False)
        with patch("agent.auxiliary_client._select_pool_entry", return_value=(False, None)):
            with caplog.at_level(logging.WARNING, logger="agent.auxiliary_client"):
                client, model = resolve_provider_client("openrouter")
        assert client is None
        assert model is None
        assert any(
            "OPENROUTER_API_KEY not set" in record.message
            for record in caplog.records
        )

class TestGetTextAuxiliaryClient:
    """Test the full resolution chain for get_text_auxiliary_client."""

    def test_codex_pool_entry_takes_priority_over_auth_store(self):
        class _Entry:
            access_token = "pooled-codex-token"
            base_url = "https://chatgpt.com/backend-api/codex"

        class _Pool:
            def has_credentials(self):
                return True

            def select(self):
                return _Entry()

        with (
            patch("agent.auxiliary_client.load_pool", return_value=_Pool()),
            patch("agent.auxiliary_client.OpenAI"),
            patch("hermes_cli.auth._read_codex_tokens", side_effect=AssertionError("legacy codex store should not run")),
        ):
            from agent.auxiliary_client import _build_codex_client

            client, model = _build_codex_client("gpt-5.4")

        from agent.auxiliary_client import CodexAuxiliaryClient

        assert isinstance(client, CodexAuxiliaryClient)
        assert model == "gpt-5.4"

    def test_returns_none_when_nothing_available(self, monkeypatch):
        monkeypatch.delenv("OPENAI_BASE_URL", raising=False)
        monkeypatch.delenv("OPENAI_API_KEY", raising=False)
        monkeypatch.delenv("OPENROUTER_API_KEY", raising=False)
        with patch("agent.auxiliary_client._read_nous_auth", return_value=None), \
             patch("agent.auxiliary_client._read_codex_access_token", return_value=None), \
             patch("agent.auxiliary_client._resolve_api_key_provider", return_value=(None, None)):
            client, model = get_text_auxiliary_client()
        assert client is None
        assert model is None

    def test_custom_endpoint_uses_codex_wrapper_when_runtime_requests_responses_api(self):
        with patch("agent.auxiliary_client._resolve_custom_runtime",
                   return_value=("https://api.openai.com/v1", "sk-test", "codex_responses")), \
             patch("agent.auxiliary_client._read_main_model", return_value="gpt-5.3-codex"), \
             patch("agent.auxiliary_client.OpenAI") as mock_openai:
            client, model = get_text_auxiliary_client()

        from agent.auxiliary_client import CodexAuxiliaryClient
        assert isinstance(client, CodexAuxiliaryClient)
        assert model == "gpt-5.3-codex"
        assert mock_openai.call_args.kwargs["base_url"] == "https://api.openai.com/v1"
        assert mock_openai.call_args.kwargs["api_key"] == "sk-test"


class TestVisionClientFallback:
    """Vision client auto mode resolves known-good multimodal backends."""

    def test_vision_auto_includes_active_provider_when_configured(self, monkeypatch):
        """Active provider appears in available backends when credentials exist."""
        monkeypatch.setenv("ANTHROPIC_API_KEY", "***")
        with (
            patch("agent.auxiliary_client._read_nous_auth", return_value=None),
            patch("agent.auxiliary_client._read_main_provider", return_value="anthropic"),
            patch("agent.auxiliary_client._read_main_model", return_value="claude-sonnet-4"),
            patch("agent.anthropic_adapter.build_anthropic_client", return_value=MagicMock()),
            patch("agent.anthropic_adapter.resolve_anthropic_token", return_value="***"),
        ):
            backends = get_available_vision_backends()

        assert "anthropic" in backends

    def test_resolve_provider_client_returns_native_anthropic_wrapper(self, monkeypatch):
        monkeypatch.setenv("ANTHROPIC_API_KEY", "***")
        with (
            patch("agent.auxiliary_client._read_nous_auth", return_value=None),
            patch("agent.anthropic_adapter.build_anthropic_client", return_value=MagicMock()),
            patch("agent.anthropic_adapter.resolve_anthropic_token", return_value="***"),
        ):
            client, model = resolve_provider_client("anthropic")

        assert client is not None
        assert client.__class__.__name__ == "AnthropicAuxiliaryClient"
        assert model == "claude-haiku-4-5-20251001"


class TestAuxiliaryPoolAwareness:
    def test_try_nous_uses_pool_entry(self):
        class _Entry:
            access_token = "pooled-access-token"
            agent_key = "pooled-agent-key"
            inference_base_url = "https://inference.pool.example/v1"

        class _Pool:
            def has_credentials(self):
                return True

            def select(self):
                return _Entry()

        with (
            patch("agent.auxiliary_client.load_pool", return_value=_Pool()),
            patch("agent.auxiliary_client.OpenAI") as mock_openai,
        ):
            from agent.auxiliary_client import _try_nous

            client, model = _try_nous()

        assert client is not None
        assert model == "google/gemini-3-flash-preview"
        assert mock_openai.call_args.kwargs["api_key"] == "pooled-agent-key"
        assert mock_openai.call_args.kwargs["base_url"] == "https://inference.pool.example/v1"

    def test_try_nous_uses_portal_recommendation_for_text(self):
        """When the Portal recommends a compaction model, _try_nous honors it."""
        fresh_base = "https://inference-api.nousresearch.com/v1"
        with (
            patch("agent.auxiliary_client._read_nous_auth", return_value={"access_token": "***"}),
            patch("agent.auxiliary_client._resolve_nous_runtime_api", return_value=("fresh-agent-key", fresh_base)),
            patch("hermes_cli.models.get_nous_recommended_aux_model", return_value="minimax/minimax-m2.7") as mock_rec,
            patch("agent.auxiliary_client.OpenAI") as mock_openai,
        ):
            from agent.auxiliary_client import _try_nous

            mock_openai.return_value = MagicMock()
            client, model = _try_nous(vision=False)

        assert client is not None
        assert model == "minimax/minimax-m2.7"
        assert mock_rec.call_args.kwargs["vision"] is False

    def test_try_nous_uses_portal_recommendation_for_vision(self):
        """Vision tasks should ask for the vision-specific recommendation."""
        fresh_base = "https://inference-api.nousresearch.com/v1"
        with (
            patch("agent.auxiliary_client._read_nous_auth", return_value={"access_token": "***"}),
            patch("agent.auxiliary_client._resolve_nous_runtime_api", return_value=("fresh-agent-key", fresh_base)),
            patch("hermes_cli.models.get_nous_recommended_aux_model", return_value="google/gemini-3-flash-preview") as mock_rec,
            patch("agent.auxiliary_client.OpenAI"),
        ):
            from agent.auxiliary_client import _try_nous
            client, model = _try_nous(vision=True)

        assert client is not None
        assert model == "google/gemini-3-flash-preview"
        assert mock_rec.call_args.kwargs["vision"] is True

    def test_try_nous_falls_back_when_recommendation_lookup_raises(self):
        """If the Portal lookup throws, we must still return a usable model."""
        fresh_base = "https://inference-api.nousresearch.com/v1"
        with (
            patch("agent.auxiliary_client._read_nous_auth", return_value={"access_token": "***"}),
            patch("agent.auxiliary_client._resolve_nous_runtime_api", return_value=("fresh-agent-key", fresh_base)),
            patch("hermes_cli.models.get_nous_recommended_aux_model", side_effect=RuntimeError("portal down")),
            patch("agent.auxiliary_client.OpenAI"),
        ):
            from agent.auxiliary_client import _try_nous
            client, model = _try_nous()

        assert client is not None
        assert model == "google/gemini-3-flash-preview"

    def test_call_llm_retries_nous_after_401(self):
        class _Auth401(Exception):
            status_code = 401

        stale_client = MagicMock()
        stale_client.base_url = "https://inference-api.nousresearch.com/v1"
        stale_client.chat.completions.create.side_effect = _Auth401("stale nous key")

        fresh_client = MagicMock()
        fresh_client.base_url = "https://inference-api.nousresearch.com/v1"
        fresh_client.chat.completions.create.return_value = {"ok": True}

        with (
            patch("agent.auxiliary_client._resolve_task_provider_model", return_value=("nous", "nous-model", None, None, None)),
            patch("agent.auxiliary_client._get_cached_client", return_value=(stale_client, "nous-model")),
            patch("agent.auxiliary_client.OpenAI", return_value=fresh_client),
            patch("agent.auxiliary_client._validate_llm_response", side_effect=lambda resp, _task: resp),
            patch("agent.auxiliary_client._resolve_nous_runtime_api", return_value=("fresh-agent-key", "https://inference-api.nousresearch.com/v1")),
        ):
            result = call_llm(
                task="compression",
                messages=[{"role": "user", "content": "hi"}],
            )

        assert result == {"ok": True}
        assert stale_client.chat.completions.create.call_count == 1
        assert fresh_client.chat.completions.create.call_count == 1

    @pytest.mark.asyncio
    async def test_async_call_llm_retries_nous_after_401(self):
        class _Auth401(Exception):
            status_code = 401

        stale_client = MagicMock()
        stale_client.base_url = "https://inference-api.nousresearch.com/v1"
        stale_client.chat.completions.create = AsyncMock(side_effect=_Auth401("stale nous key"))

        fresh_async_client = MagicMock()
        fresh_async_client.base_url = "https://inference-api.nousresearch.com/v1"
        fresh_async_client.chat.completions.create = AsyncMock(return_value={"ok": True})

        with (
            patch("agent.auxiliary_client._resolve_task_provider_model", return_value=("nous", "nous-model", None, None, None)),
            patch("agent.auxiliary_client._get_cached_client", return_value=(stale_client, "nous-model")),
            patch("agent.auxiliary_client._to_async_client", return_value=(fresh_async_client, "nous-model")),
            patch("agent.auxiliary_client._validate_llm_response", side_effect=lambda resp, _task: resp),
            patch("agent.auxiliary_client._resolve_nous_runtime_api", return_value=("fresh-agent-key", "https://inference-api.nousresearch.com/v1")),
        ):
            result = await async_call_llm(
                task="session_search",
                messages=[{"role": "user", "content": "hi"}],
            )

        assert result == {"ok": True}
        assert stale_client.chat.completions.create.await_count == 1
        assert fresh_async_client.chat.completions.create.await_count == 1

    def test_cached_gmi_client_keeps_explicit_slash_model_override(self):
        import agent.auxiliary_client as aux

        fake_client = MagicMock()

        with patch(
            "agent.auxiliary_client.resolve_provider_client",
            return_value=(fake_client, "google/gemini-3.1-flash-lite-preview"),
        ) as mock_resolve:
            aux.shutdown_cached_clients()
            try:
                client, model = aux._get_cached_client(
                    "gmi",
                    "google/gemini-3.1-flash-lite-preview",
                    base_url="https://api.gmi-serving.com/v1",
                    api_key="gmi-key",
                )
                assert client is fake_client
                assert model == "google/gemini-3.1-flash-lite-preview"

                client, model = aux._get_cached_client(
                    "gmi",
                    "openai/gpt-5.4-mini",
                    base_url="https://api.gmi-serving.com/v1",
                    api_key="gmi-key",
                )
            finally:
                aux.shutdown_cached_clients()

        assert client is fake_client
        assert model == "openai/gpt-5.4-mini"
        assert mock_resolve.call_count == 1


# ── Payment / credit exhaustion fallback ─────────────────────────────────


class TestIsPaymentError:
    """_is_payment_error detects 402 and credit-related errors."""

    def test_402_status_code(self):
        exc = Exception("Payment Required")
        exc.status_code = 402
        assert _is_payment_error(exc) is True

    def test_402_with_credits_message(self):
        exc = Exception("You requested up to 65535 tokens, but can only afford 8029")
        exc.status_code = 402
        assert _is_payment_error(exc) is True

    def test_429_with_credits_message(self):
        exc = Exception("insufficient credits remaining")
        exc.status_code = 429
        assert _is_payment_error(exc) is True

    def test_429_without_credits_message_is_not_payment(self):
        """Normal rate limits should NOT be treated as payment errors."""
        exc = Exception("Rate limit exceeded, try again in 2 seconds")
        exc.status_code = 429
        assert _is_payment_error(exc) is False

    def test_generic_500_is_not_payment(self):
        exc = Exception("Internal server error")
        exc.status_code = 500
        assert _is_payment_error(exc) is False

    def test_no_status_code_with_billing_message(self):
        exc = Exception("billing: payment required for this request")
        assert _is_payment_error(exc) is True

    def test_no_status_code_no_message(self):
        exc = Exception("connection reset")
        assert _is_payment_error(exc) is False


class TestGetProviderChain:
    """_get_provider_chain() resolves functions at call time (testable)."""

    def test_returns_four_entries(self):
        chain = _get_provider_chain()
        assert len(chain) == 4
        labels = [label for label, _ in chain]
        assert labels == ["openrouter", "nous", "local/custom", "api-key"]
        # Codex is deliberately NOT in this chain — see _get_provider_chain
        # docstring. ChatGPT-account Codex has a shifting model allow-list;
        # guessing a model to fall back on breaks more often than it helps.
        assert "openai-codex" not in labels

    def test_picks_up_patched_functions(self):
        """Patches on _try_* functions must be visible in the chain."""
        sentinel = lambda: ("patched", "model")
        with patch("agent.auxiliary_client._try_openrouter", sentinel):
            chain = _get_provider_chain()
        assert chain[0] == ("openrouter", sentinel)


class TestTryPaymentFallback:
    """_try_payment_fallback skips the failed provider and tries alternatives."""

    def test_skips_failed_provider(self):
        mock_client = MagicMock()
        with patch("agent.auxiliary_client._try_openrouter", return_value=(None, None)), \
             patch("agent.auxiliary_client._try_nous", return_value=(mock_client, "nous-model")), \
             patch("agent.auxiliary_client._read_main_provider", return_value="openrouter"):
            client, model, label = _try_payment_fallback("openrouter", task="compression")
        assert client is mock_client
        assert model == "nous-model"
        assert label == "nous"

    def test_returns_none_when_no_fallback(self):
        with patch("agent.auxiliary_client._try_openrouter", return_value=(None, None)), \
             patch("agent.auxiliary_client._try_nous", return_value=(None, None)), \
             patch("agent.auxiliary_client._try_custom_endpoint", return_value=(None, None)), \
             patch("agent.auxiliary_client._resolve_api_key_provider", return_value=(None, None)), \
             patch("agent.auxiliary_client._read_main_provider", return_value="openrouter"):
            client, model, label = _try_payment_fallback("openrouter")
        assert client is None
        assert label == ""

    def test_codex_alias_maps_to_chain_label(self):
        """'codex' should map to 'openai-codex' in the skip set."""
        mock_client = MagicMock()
        with patch("agent.auxiliary_client._try_openrouter", return_value=(mock_client, "or-model")), \
             patch("agent.auxiliary_client._read_main_provider", return_value="openai-codex"):
            client, model, label = _try_payment_fallback("openai-codex", task="vision")
        assert client is mock_client
        assert label == "openrouter"

    def test_codex_not_in_fallback_chain(self):
        """Codex is deliberately NOT a fallback rung (shifting model allow-list).

        When OR/Nous/custom/api-key all fail, payment-fallback returns None —
        Codex is never tried with a guessed model.
        """
        with patch("agent.auxiliary_client._try_openrouter", return_value=(None, None)), \
             patch("agent.auxiliary_client._try_nous", return_value=(None, None)), \
             patch("agent.auxiliary_client._try_custom_endpoint", return_value=(None, None)), \
             patch("agent.auxiliary_client._resolve_api_key_provider", return_value=(None, None)), \
             patch("agent.auxiliary_client._read_main_provider", return_value="openrouter"):
            client, model, label = _try_payment_fallback("openrouter")
        assert client is None
        assert model is None
        assert label == ""


class TestCallLlmPaymentFallback:
    """call_llm() retries with a different provider on 402 / payment errors."""

    def _make_402_error(self, msg="Payment Required: insufficient credits"):
        exc = Exception(msg)
        exc.status_code = 402
        return exc

    def test_non_payment_error_not_caught(self, monkeypatch):
        """Non-payment/non-connection errors (500) should NOT trigger fallback."""
        monkeypatch.setenv("OPENROUTER_API_KEY", "or-key")

        primary_client = MagicMock()
        server_err = Exception("Internal Server Error")
        server_err.status_code = 500
        primary_client.chat.completions.create.side_effect = server_err

        with patch("agent.auxiliary_client._get_cached_client",
                    return_value=(primary_client, "google/gemini-3-flash-preview")), \
             patch("agent.auxiliary_client._resolve_task_provider_model",
                    return_value=("auto", "google/gemini-3-flash-preview", None, None, None)):
            with pytest.raises(Exception, match="Internal Server Error"):
                call_llm(
                    task="compression",
                    messages=[{"role": "user", "content": "hello"}],
                )

# ---------------------------------------------------------------------------
# Gate: _resolve_api_key_provider must skip anthropic when not configured
# ---------------------------------------------------------------------------


def test_resolve_api_key_provider_skips_unconfigured_anthropic(monkeypatch):
    """_resolve_api_key_provider must not try anthropic when user never configured it."""
    from collections import OrderedDict
    from hermes_cli.auth import ProviderConfig

    # Build a minimal registry with only "anthropic" so the loop is guaranteed
    # to reach it without being short-circuited by earlier providers.
    fake_registry = OrderedDict({
        "anthropic": ProviderConfig(
            id="anthropic",
            name="Anthropic",
            auth_type="api_key",
            inference_base_url="https://api.anthropic.com",
            api_key_env_vars=("ANTHROPIC_API_KEY",),
        ),
    })

    called = []

    def mock_try_anthropic():
        called.append("anthropic")
        return None, None

    monkeypatch.setattr("agent.auxiliary_client._try_anthropic", mock_try_anthropic)
    monkeypatch.setattr("hermes_cli.auth.PROVIDER_REGISTRY", fake_registry)
    monkeypatch.setattr(
        "hermes_cli.auth.is_provider_explicitly_configured",
        lambda pid: False,
    )

    from agent.auxiliary_client import _resolve_api_key_provider
    _resolve_api_key_provider()

    assert "anthropic" not in called, \
        "_try_anthropic() should not be called when anthropic is not explicitly configured"


# ---------------------------------------------------------------------------
# model="default" elimination (#7512)
# ---------------------------------------------------------------------------


# ---------------------------------------------------------------------------
# _try_payment_fallback reason parameter (#7512 bug 3)
# ---------------------------------------------------------------------------


# ---------------------------------------------------------------------------
# _is_connection_error coverage
# ---------------------------------------------------------------------------


class TestIsConnectionError:
    """Tests for _is_connection_error detection."""

    def test_connection_refused(self):
        from agent.auxiliary_client import _is_connection_error
        err = Exception("Connection refused")
        assert _is_connection_error(err) is True

    def test_timeout(self):
        from agent.auxiliary_client import _is_connection_error
        err = Exception("Request timed out.")
        assert _is_connection_error(err) is True

    def test_dns_failure(self):
        from agent.auxiliary_client import _is_connection_error
        err = Exception("Name or service not known")
        assert _is_connection_error(err) is True

    def test_normal_api_error_not_connection(self):
        from agent.auxiliary_client import _is_connection_error
        err = Exception("Bad Request: invalid model")
        err.status_code = 400
        assert _is_connection_error(err) is False

    def test_500_not_connection(self):
        from agent.auxiliary_client import _is_connection_error
        err = Exception("Internal Server Error")
        err.status_code = 500
        assert _is_connection_error(err) is False


class TestKimiTemperatureOmitted:
    """Kimi/Moonshot models should have temperature OMITTED from API kwargs.

    The Kimi gateway selects the correct temperature server-side based on the
    active mode (thinking → 1.0, non-thinking → 0.6).  Sending any temperature
    value conflicts with gateway-managed defaults.
    """

    @pytest.mark.parametrize(
        "model",
        [
            "kimi-for-coding",
            "kimi-k2.5",
            "kimi-k2.6",
            "kimi-k2-turbo-preview",
            "kimi-k2-0905-preview",
            "kimi-k2-thinking",
            "kimi-k2-thinking-turbo",
            "kimi-k2-instruct",
            "kimi-k2-instruct-0905",
            "moonshotai/kimi-k2.5",
            "moonshotai/Kimi-K2-Thinking",
            "moonshotai/Kimi-K2-Instruct",
        ],
    )
    def test_kimi_models_omit_temperature(self, model):
        """No kimi model should have a temperature key in kwargs."""
        from agent.auxiliary_client import _build_call_kwargs

        kwargs = _build_call_kwargs(
            provider="kimi-coding",
            model=model,
            messages=[{"role": "user", "content": "hello"}],
            temperature=0.3,
        )

        assert "temperature" not in kwargs

    def test_kimi_for_coding_no_temperature_when_none(self):
        """When caller passes temperature=None, still no temperature key."""
        from agent.auxiliary_client import _build_call_kwargs

        kwargs = _build_call_kwargs(
            provider="kimi-coding",
            model="kimi-for-coding",
            messages=[{"role": "user", "content": "hello"}],
            temperature=None,
        )

        assert "temperature" not in kwargs

    def test_sync_call_omits_temperature(self):
        client = MagicMock()
        client.base_url = "https://api.kimi.com/coding/v1"
        response = MagicMock()
        client.chat.completions.create.return_value = response

        with patch(
            "agent.auxiliary_client._get_cached_client",
            return_value=(client, "kimi-for-coding"),
        ), patch(
            "agent.auxiliary_client._resolve_task_provider_model",
            return_value=("auto", "kimi-for-coding", None, None, None),
        ):
            result = call_llm(
                task="session_search",
                messages=[{"role": "user", "content": "hello"}],
                temperature=0.1,
            )

        assert result is response
        kwargs = client.chat.completions.create.call_args.kwargs
        assert kwargs["model"] == "kimi-for-coding"
        assert "temperature" not in kwargs

    @pytest.mark.asyncio
    async def test_async_call_omits_temperature(self):
        client = MagicMock()
        client.base_url = "https://api.kimi.com/coding/v1"
        response = MagicMock()
        client.chat.completions.create = AsyncMock(return_value=response)

        with patch(
            "agent.auxiliary_client._get_cached_client",
            return_value=(client, "kimi-for-coding"),
        ), patch(
            "agent.auxiliary_client._resolve_task_provider_model",
            return_value=("auto", "kimi-for-coding", None, None, None),
        ):
            result = await async_call_llm(
                task="session_search",
                messages=[{"role": "user", "content": "hello"}],
                temperature=0.1,
            )

        assert result is response
        kwargs = client.chat.completions.create.call_args.kwargs
        assert kwargs["model"] == "kimi-for-coding"
        assert "temperature" not in kwargs

    @pytest.mark.parametrize(
        "model",
        [
            "anthropic/claude-sonnet-4-6",
            "gpt-5.4",
            "deepseek-chat",
        ],
    )
    def test_non_kimi_models_preserve_temperature(self, model):
        from agent.auxiliary_client import _build_call_kwargs

        kwargs = _build_call_kwargs(
            provider="openrouter",
            model=model,
            messages=[{"role": "user", "content": "hello"}],
            temperature=0.3,
        )

        assert kwargs["temperature"] == 0.3

    @pytest.mark.parametrize(
        "base_url",
        [
            "https://api.moonshot.ai/v1",
            "https://api.moonshot.cn/v1",
            "https://api.kimi.com/coding/v1",
        ],
    )
    def test_kimi_k2_5_omits_temperature_regardless_of_endpoint(self, base_url):
        """Temperature is omitted regardless of which Kimi endpoint is used."""
        from agent.auxiliary_client import _build_call_kwargs

        kwargs = _build_call_kwargs(
            provider="kimi-coding",
            model="kimi-k2.5",
            messages=[{"role": "user", "content": "hello"}],
            temperature=0.1,
            base_url=base_url,
        )

        assert "temperature" not in kwargs


# ---------------------------------------------------------------------------
# async_call_llm payment / connection fallback (#7512 bug 2)
# ---------------------------------------------------------------------------


class TestStaleBaseUrlWarning:
    """_resolve_auto() warns when OPENAI_BASE_URL conflicts with config provider (#5161)."""

    def test_warns_when_openai_base_url_set_with_named_provider(self, monkeypatch, caplog):
        """Warning fires when OPENAI_BASE_URL is set but provider is a named provider."""
        import agent.auxiliary_client as mod
        # Reset the module-level flag so the warning fires
        monkeypatch.setattr(mod, "_stale_base_url_warned", False)
        monkeypatch.setenv("OPENAI_BASE_URL", "http://localhost:11434/v1")
        monkeypatch.setenv("OPENROUTER_API_KEY", "sk-or-test")

        with patch("agent.auxiliary_client._read_main_provider", return_value="openrouter"), \
             patch("agent.auxiliary_client._read_main_model", return_value="google/gemini-flash"), \
             caplog.at_level(logging.WARNING, logger="agent.auxiliary_client"):
            _resolve_auto()

        assert any("OPENAI_BASE_URL is set" in rec.message for rec in caplog.records), \
            "Expected a warning about stale OPENAI_BASE_URL"
        assert mod._stale_base_url_warned is True


class TestAuxiliaryTaskExtraBody:
    def test_sync_call_merges_task_extra_body_from_config(self):
        client = MagicMock()
        client.base_url = "https://api.example.com/v1"
        response = MagicMock()
        client.chat.completions.create.return_value = response

        config = {
            "auxiliary": {
                "session_search": {
                    "extra_body": {
                        "enable_thinking": False,
                        "reasoning": {"effort": "none"},
                    }
                }
            }
        }

        with patch("hermes_cli.config.load_config", return_value=config), patch(
            "agent.auxiliary_client._get_cached_client",
            return_value=(client, "glm-4.5-air"),
        ):
            result = call_llm(
                task="session_search",
                messages=[{"role": "user", "content": "hello"}],
                extra_body={"metadata": {"source": "test"}},
            )

        assert result is response
        kwargs = client.chat.completions.create.call_args.kwargs
        assert kwargs["extra_body"]["enable_thinking"] is False
        assert kwargs["extra_body"]["reasoning"] == {"effort": "none"}
        assert kwargs["extra_body"]["metadata"] == {"source": "test"}

    @pytest.mark.asyncio
    async def test_async_call_explicit_extra_body_overrides_task_config(self):
        client = MagicMock()
        client.base_url = "https://api.example.com/v1"
        response = MagicMock()
        client.chat.completions.create = AsyncMock(return_value=response)

        config = {
            "auxiliary": {
                "session_search": {
                    "extra_body": {"enable_thinking": False}
                }
            }
        }

        with patch("hermes_cli.config.load_config", return_value=config), patch(
            "agent.auxiliary_client._get_cached_client",
            return_value=(client, "glm-4.5-air"),
        ):
            result = await async_call_llm(
                task="session_search",
                messages=[{"role": "user", "content": "hello"}],
                extra_body={"enable_thinking": True},
            )

        assert result is response
        kwargs = client.chat.completions.create.call_args.kwargs
        assert kwargs["extra_body"]["enable_thinking"] is True

    def test_no_warning_when_provider_is_custom(self, monkeypatch, caplog):
        """No warning when the provider is 'custom' — OPENAI_BASE_URL is expected."""
        import agent.auxiliary_client as mod
        monkeypatch.setattr(mod, "_stale_base_url_warned", False)
        monkeypatch.setenv("OPENAI_BASE_URL", "http://localhost:11434/v1")
        monkeypatch.setenv("OPENAI_API_KEY", "test-key")

        with patch("agent.auxiliary_client._read_main_provider", return_value="custom"), \
             patch("agent.auxiliary_client._read_main_model", return_value="llama3"), \
             patch("agent.auxiliary_client._resolve_custom_runtime",
                   return_value=("http://localhost:11434/v1", "test-key", None)), \
             patch("agent.auxiliary_client.OpenAI") as mock_openai, \
             caplog.at_level(logging.WARNING, logger="agent.auxiliary_client"):
            mock_openai.return_value = MagicMock()
            _resolve_auto()

        assert not any("OPENAI_BASE_URL is set" in rec.message for rec in caplog.records), \
            "Should NOT warn when provider is 'custom'"

    def test_no_warning_when_provider_is_named_custom(self, monkeypatch, caplog):
        """No warning when the provider is 'custom:myname' — base_url comes from config."""
        import agent.auxiliary_client as mod
        monkeypatch.setattr(mod, "_stale_base_url_warned", False)
        monkeypatch.setenv("OPENAI_BASE_URL", "http://localhost:11434/v1")
        monkeypatch.setenv("OPENAI_API_KEY", "test-key")

        with patch("agent.auxiliary_client._read_main_provider", return_value="custom:ollama-local"), \
             patch("agent.auxiliary_client._read_main_model", return_value="llama3"), \
             patch("agent.auxiliary_client.resolve_provider_client",
                   return_value=(MagicMock(), "llama3")), \
             caplog.at_level(logging.WARNING, logger="agent.auxiliary_client"):
            _resolve_auto()

        assert not any("OPENAI_BASE_URL is set" in rec.message for rec in caplog.records), \
            "Should NOT warn when provider is 'custom:*'"

    def test_no_warning_when_openai_base_url_not_set(self, monkeypatch, caplog):
        """No warning when OPENAI_BASE_URL is absent."""
        import agent.auxiliary_client as mod
        monkeypatch.setattr(mod, "_stale_base_url_warned", False)
        monkeypatch.delenv("OPENAI_BASE_URL", raising=False)
        monkeypatch.setenv("OPENROUTER_API_KEY", "sk-or-test")

        with patch("agent.auxiliary_client._read_main_provider", return_value="openrouter"), \
             patch("agent.auxiliary_client._read_main_model", return_value="google/gemini-flash"), \
             caplog.at_level(logging.WARNING, logger="agent.auxiliary_client"):
            _resolve_auto()

        assert not any("OPENAI_BASE_URL is set" in rec.message for rec in caplog.records), \
            "Should NOT warn when OPENAI_BASE_URL is not set"

# ---------------------------------------------------------------------------
# Anthropic-compatible image block conversion
# ---------------------------------------------------------------------------

class TestAnthropicCompatImageConversion:
    """Tests for _is_anthropic_compat_endpoint and _convert_openai_images_to_anthropic."""

    def test_known_providers_detected(self):
        from agent.auxiliary_client import _is_anthropic_compat_endpoint
        assert _is_anthropic_compat_endpoint("minimax", "")
        assert _is_anthropic_compat_endpoint("minimax-cn", "")

    def test_openrouter_not_detected(self):
        from agent.auxiliary_client import _is_anthropic_compat_endpoint
        assert not _is_anthropic_compat_endpoint("openrouter", "")
        assert not _is_anthropic_compat_endpoint("anthropic", "")

    def test_url_based_detection(self):
        from agent.auxiliary_client import _is_anthropic_compat_endpoint
        assert _is_anthropic_compat_endpoint("custom", "https://api.minimax.io/anthropic")
        assert _is_anthropic_compat_endpoint("custom", "https://example.com/anthropic/v1")
        assert not _is_anthropic_compat_endpoint("custom", "https://api.openai.com/v1")

    def test_base64_image_converted(self):
        from agent.auxiliary_client import _convert_openai_images_to_anthropic
        messages = [{
            "role": "user",
            "content": [
                {"type": "text", "text": "describe"},
                {"type": "image_url", "image_url": {"url": "data:image/png;base64,iVBOR="}}
            ]
        }]
        result = _convert_openai_images_to_anthropic(messages)
        img_block = result[0]["content"][1]
        assert img_block["type"] == "image"
        assert img_block["source"]["type"] == "base64"
        assert img_block["source"]["media_type"] == "image/png"
        assert img_block["source"]["data"] == "iVBOR="

    def test_url_image_converted(self):
        from agent.auxiliary_client import _convert_openai_images_to_anthropic
        messages = [{
            "role": "user",
            "content": [
                {"type": "image_url", "image_url": {"url": "https://example.com/img.jpg"}}
            ]
        }]
        result = _convert_openai_images_to_anthropic(messages)
        img_block = result[0]["content"][0]
        assert img_block["type"] == "image"
        assert img_block["source"]["type"] == "url"
        assert img_block["source"]["url"] == "https://example.com/img.jpg"

    def test_text_only_messages_unchanged(self):
        from agent.auxiliary_client import _convert_openai_images_to_anthropic
        messages = [{"role": "user", "content": "Hello"}]
        result = _convert_openai_images_to_anthropic(messages)
        assert result[0] is messages[0]  # same object, not copied

    def test_jpeg_media_type_parsed(self):
        from agent.auxiliary_client import _convert_openai_images_to_anthropic
        messages = [{
            "role": "user",
            "content": [
                {"type": "image_url", "image_url": {"url": "data:image/jpeg;base64,/9j/="}}
            ]
        }]
        result = _convert_openai_images_to_anthropic(messages)
        assert result[0]["content"][0]["source"]["media_type"] == "image/jpeg"


class _AuxAuth401(Exception):
    status_code = 401

    def __init__(self, message="Provided authentication token is expired"):
        super().__init__(message)


class _DummyResponse:
    def __init__(self, text="ok"):
        self.choices = [MagicMock(message=MagicMock(content=text))]


class _FailingThenSuccessCompletions:
    def __init__(self):
        self.calls = 0

    def create(self, **kwargs):
        self.calls += 1
        if self.calls == 1:
            raise _AuxAuth401()
        return _DummyResponse("sync-ok")


class _AsyncFailingThenSuccessCompletions:
    def __init__(self):
        self.calls = 0

    async def create(self, **kwargs):
        self.calls += 1
        if self.calls == 1:
            raise _AuxAuth401()
        return _DummyResponse("async-ok")


class TestAuxiliaryAuthRefreshRetry:
    def test_call_llm_refreshes_codex_on_401_for_vision(self):
        failing_client = MagicMock()
        failing_client.base_url = "https://chatgpt.com/backend-api/codex"
        failing_client.chat.completions = _FailingThenSuccessCompletions()

        fresh_client = MagicMock()
        fresh_client.base_url = "https://chatgpt.com/backend-api/codex"
        fresh_client.chat.completions.create.return_value = _DummyResponse("fresh-sync")

        with (
            patch(
                "agent.auxiliary_client.resolve_vision_provider_client",
                side_effect=[("openai-codex", failing_client, "gpt-5.4"), ("openai-codex", fresh_client, "gpt-5.4")],
            ),
            patch("agent.auxiliary_client._refresh_provider_credentials", return_value=True) as mock_refresh,
        ):
            resp = call_llm(
                task="vision",
                provider="openai-codex",
                model="gpt-5.4",
                messages=[{"role": "user", "content": "hi"}],
            )

        assert resp.choices[0].message.content == "fresh-sync"
        mock_refresh.assert_called_once_with("openai-codex")

    def test_call_llm_refreshes_codex_on_401_for_non_vision(self):
        stale_client = MagicMock()
        stale_client.base_url = "https://chatgpt.com/backend-api/codex"
        stale_client.chat.completions.create.side_effect = _AuxAuth401("stale codex token")

        fresh_client = MagicMock()
        fresh_client.base_url = "https://chatgpt.com/backend-api/codex"
        fresh_client.chat.completions.create.return_value = _DummyResponse("fresh-non-vision")

        with (
            patch("agent.auxiliary_client._resolve_task_provider_model", return_value=("openai-codex", "gpt-5.4", None, None, None)),
            patch("agent.auxiliary_client._get_cached_client", side_effect=[(stale_client, "gpt-5.4"), (fresh_client, "gpt-5.4")]),
            patch("agent.auxiliary_client._refresh_provider_credentials", return_value=True) as mock_refresh,
        ):
            resp = call_llm(
                task="compression",
                provider="openai-codex",
                model="gpt-5.4",
                messages=[{"role": "user", "content": "hi"}],
            )

        assert resp.choices[0].message.content == "fresh-non-vision"
        mock_refresh.assert_called_once_with("openai-codex")
        assert stale_client.chat.completions.create.call_count == 1
        assert fresh_client.chat.completions.create.call_count == 1

    def test_call_llm_refreshes_anthropic_on_401_for_non_vision(self):
        stale_client = MagicMock()
        stale_client.base_url = "https://api.anthropic.com"
        stale_client.chat.completions.create.side_effect = _AuxAuth401("anthropic token expired")

        fresh_client = MagicMock()
        fresh_client.base_url = "https://api.anthropic.com"
        fresh_client.chat.completions.create.return_value = _DummyResponse("fresh-anthropic")

        with (
            patch("agent.auxiliary_client._resolve_task_provider_model", return_value=("anthropic", "claude-haiku-4-5-20251001", None, None, None)),
            patch("agent.auxiliary_client._get_cached_client", side_effect=[(stale_client, "claude-haiku-4-5-20251001"), (fresh_client, "claude-haiku-4-5-20251001")]),
            patch("agent.auxiliary_client._refresh_provider_credentials", return_value=True) as mock_refresh,
        ):
            resp = call_llm(
                task="compression",
                provider="anthropic",
                model="claude-haiku-4-5-20251001",
                messages=[{"role": "user", "content": "hi"}],
            )

        assert resp.choices[0].message.content == "fresh-anthropic"
        mock_refresh.assert_called_once_with("anthropic")
        assert stale_client.chat.completions.create.call_count == 1
        assert fresh_client.chat.completions.create.call_count == 1

    @pytest.mark.asyncio
    async def test_async_call_llm_refreshes_codex_on_401_for_vision(self):
        failing_client = MagicMock()
        failing_client.base_url = "https://chatgpt.com/backend-api/codex"
        failing_client.chat.completions = _AsyncFailingThenSuccessCompletions()

        fresh_client = MagicMock()
        fresh_client.base_url = "https://chatgpt.com/backend-api/codex"
        fresh_client.chat.completions.create = AsyncMock(return_value=_DummyResponse("fresh-async"))

        with (
            patch(
                "agent.auxiliary_client.resolve_vision_provider_client",
                side_effect=[("openai-codex", failing_client, "gpt-5.4"), ("openai-codex", fresh_client, "gpt-5.4")],
            ),
            patch("agent.auxiliary_client._refresh_provider_credentials", return_value=True) as mock_refresh,
        ):
            resp = await async_call_llm(
                task="vision",
                provider="openai-codex",
                model="gpt-5.4",
                messages=[{"role": "user", "content": "hi"}],
            )

        assert resp.choices[0].message.content == "fresh-async"
        mock_refresh.assert_called_once_with("openai-codex")

    def test_refresh_provider_credentials_force_refreshes_anthropic_oauth_and_evicts_cache(self, monkeypatch):
        stale_client = MagicMock()
        cache_key = ("anthropic", False, None, None, None)

        monkeypatch.setenv("ANTHROPIC_TOKEN", "")
        monkeypatch.setenv("CLAUDE_CODE_OAUTH_TOKEN", "")
        monkeypatch.setenv("ANTHROPIC_API_KEY", "")

        with (
            patch("agent.auxiliary_client._client_cache", {cache_key: (stale_client, "claude-haiku-4-5-20251001", None)}),
            patch("agent.anthropic_adapter.read_claude_code_credentials", return_value={
                "accessToken": "expired-token",
                "refreshToken": "refresh-token",
                "expiresAt": 0,
            }),
            patch("agent.anthropic_adapter.refresh_anthropic_oauth_pure", return_value={
                "access_token": "fresh-token",
                "refresh_token": "refresh-token-2",
                "expires_at_ms": 9999999999999,
            }) as mock_refresh_oauth,
            patch("agent.anthropic_adapter._write_claude_code_credentials") as mock_write,
        ):
            from agent.auxiliary_client import _refresh_provider_credentials

            assert _refresh_provider_credentials("anthropic") is True

        mock_refresh_oauth.assert_called_once_with("refresh-token", use_json=False)
        mock_write.assert_called_once_with("fresh-token", "refresh-token-2", 9999999999999)
        stale_client.close.assert_called_once()

    @pytest.mark.asyncio
    async def test_async_call_llm_refreshes_anthropic_on_401_for_non_vision(self):
        stale_client = MagicMock()
        stale_client.base_url = "https://api.anthropic.com"
        stale_client.chat.completions.create = AsyncMock(side_effect=_AuxAuth401("anthropic token expired"))

        fresh_client = MagicMock()
        fresh_client.base_url = "https://api.anthropic.com"
        fresh_client.chat.completions.create = AsyncMock(return_value=_DummyResponse("fresh-async-anthropic"))

        with (
            patch("agent.auxiliary_client._resolve_task_provider_model", return_value=("anthropic", "claude-haiku-4-5-20251001", None, None, None)),
            patch("agent.auxiliary_client._get_cached_client", side_effect=[(stale_client, "claude-haiku-4-5-20251001"), (fresh_client, "claude-haiku-4-5-20251001")]),
            patch("agent.auxiliary_client._refresh_provider_credentials", return_value=True) as mock_refresh,
        ):
            resp = await async_call_llm(
                task="compression",
                provider="anthropic",
                model="claude-haiku-4-5-20251001",
                messages=[{"role": "user", "content": "hi"}],
            )

        assert resp.choices[0].message.content == "fresh-async-anthropic"
        mock_refresh.assert_called_once_with("anthropic")
        assert stale_client.chat.completions.create.await_count == 1
        assert fresh_client.chat.completions.create.await_count == 1


class TestCodexAdapterReasoningTranslation:
    """Verify _CodexCompletionsAdapter translates extra_body.reasoning
    into the Responses API's top-level reasoning + include fields, matching
    agent/transports/codex.py::build_kwargs() behavior.

    Regression for user feedback (Apr 26): auxiliary callers that configure
    reasoning via auxiliary.<task>.extra_body.reasoning had that config
    silently dropped because the adapter only forwarded messages/model/tools.
    """

    @staticmethod
    def _build_adapter():
        """Build a _CodexCompletionsAdapter with a mocked responses.stream()."""
        from agent.auxiliary_client import _CodexCompletionsAdapter
        from types import SimpleNamespace

        # Mock the stream context manager: yields no events, get_final_response
        # returns a minimal empty-output response.
        fake_final = SimpleNamespace(
            output=[SimpleNamespace(
                type="message",
                content=[SimpleNamespace(type="output_text", text="hi")],
            )],
            usage=SimpleNamespace(input_tokens=1, output_tokens=1, total_tokens=2),
        )

        class _FakeStream:
            def __enter__(self): return self
            def __exit__(self, *a): return False
            def __iter__(self): return iter([])
            def get_final_response(self): return fake_final

        captured_kwargs = {}

        def _stream(**kwargs):
            captured_kwargs.update(kwargs)
            return _FakeStream()

        real_client = MagicMock()
        real_client.responses.stream = _stream
        adapter = _CodexCompletionsAdapter(real_client, "gpt-5.3-codex")
        return adapter, captured_kwargs

    def test_reasoning_effort_medium_translated_to_top_level(self):
        adapter, captured = self._build_adapter()
        adapter.create(
            messages=[{"role": "user", "content": "hi"}],
            extra_body={"reasoning": {"effort": "medium"}},
        )
        assert captured.get("reasoning") == {"effort": "medium", "summary": "auto"}
        assert captured.get("include") == ["reasoning.encrypted_content"]

    def test_reasoning_effort_minimal_clamped_to_low(self):
        """Codex backend rejects 'minimal'; adapter clamps to 'low' per main transport."""
        adapter, captured = self._build_adapter()
        adapter.create(
            messages=[{"role": "user", "content": "hi"}],
            extra_body={"reasoning": {"effort": "minimal"}},
        )
        assert captured.get("reasoning") == {"effort": "low", "summary": "auto"}
        assert captured.get("include") == ["reasoning.encrypted_content"]

    def test_reasoning_effort_low_passed_through(self):
        adapter, captured = self._build_adapter()
        adapter.create(
            messages=[{"role": "user", "content": "hi"}],
            extra_body={"reasoning": {"effort": "low"}},
        )
        assert captured.get("reasoning") == {"effort": "low", "summary": "auto"}

    def test_reasoning_effort_high_passed_through(self):
        adapter, captured = self._build_adapter()
        adapter.create(
            messages=[{"role": "user", "content": "hi"}],
            extra_body={"reasoning": {"effort": "high"}},
        )
        assert captured.get("reasoning") == {"effort": "high", "summary": "auto"}

    def test_reasoning_disabled_omits_reasoning_and_include(self):
        adapter, captured = self._build_adapter()
        adapter.create(
            messages=[{"role": "user", "content": "hi"}],
            extra_body={"reasoning": {"enabled": False}},
        )
        assert "reasoning" not in captured
        assert "include" not in captured

    def test_reasoning_default_effort_when_only_enabled_flag(self):
        """extra_body={"reasoning": {}} (truthy enabled by omission) → default 'medium'."""
        adapter, captured = self._build_adapter()
        adapter.create(
            messages=[{"role": "user", "content": "hi"}],
            extra_body={"reasoning": {}},
        )
        assert captured.get("reasoning") == {"effort": "medium", "summary": "auto"}
        assert captured.get("include") == ["reasoning.encrypted_content"]

    def test_no_extra_body_means_no_reasoning_keys(self):
        """Baseline: without extra_body, no reasoning/include is sent (preserves
        current behavior for callers that don't opt in)."""
        adapter, captured = self._build_adapter()
        adapter.create(messages=[{"role": "user", "content": "hi"}])
        assert "reasoning" not in captured
        assert "include" not in captured

    def test_extra_body_without_reasoning_key_is_noop(self):
        adapter, captured = self._build_adapter()
        adapter.create(
            messages=[{"role": "user", "content": "hi"}],
            extra_body={"metadata": {"source": "test"}},
        )
        assert "reasoning" not in captured
        assert "include" not in captured

    def test_non_dict_reasoning_value_is_ignored_gracefully(self):
        """Defensive: if a caller accidentally passes a string/None, we
        silently skip instead of crashing inside the adapter."""
        adapter, captured = self._build_adapter()
        adapter.create(
            messages=[{"role": "user", "content": "hi"}],
            extra_body={"reasoning": "medium"},  # wrong shape — must not crash
        )
        assert "reasoning" not in captured



class TestVisionAutoSkipsKimiCoding:
    """_resolve_auto vision branch skips providers that have no vision on
    their main endpoint (e.g. Kimi Coding Plan /coding) and falls through
    to the aggregator chain instead of handing back a client that will 404
    on every request (#17076).
    """

    def test_kimi_coding_skipped_falls_through_to_openrouter(self, monkeypatch):
        """kimi-coding as main + vision auto → OpenRouter (not kimi)."""
        fake_or_client = MagicMock(name="openrouter_client")

        monkeypatch.setattr(
            "agent.auxiliary_client._read_main_provider", lambda: "kimi-coding",
        )
        monkeypatch.setattr(
            "agent.auxiliary_client._read_main_model", lambda: "kimi-code",
        )
        # Guard: if the skip doesn't fire, _resolve_strict_vision_backend
        # and resolve_provider_client both would try kimi-coding — detect
        # either via the main-provider call and fail loud.
        rpc_mock = MagicMock(side_effect=AssertionError(
            "resolve_provider_client should NOT be called for kimi-coding "
            "on the vision auto path"))
        monkeypatch.setattr(
            "agent.auxiliary_client.resolve_provider_client", rpc_mock,
        )

        def fake_strict(provider, model=None):
            if provider == "openrouter":
                return fake_or_client, "google/gemini-3-flash-preview"
            if provider == "nous":
                return None, None
            raise AssertionError(
                f"strict vision backend should not be called for {provider!r} "
                "when main provider is kimi-coding"
            )
        monkeypatch.setattr(
            "agent.auxiliary_client._resolve_strict_vision_backend",
            fake_strict,
        )

        provider, client, model = resolve_vision_provider_client()
        assert provider == "openrouter"
        assert client is fake_or_client
        assert model == "google/gemini-3-flash-preview"

    def test_kimi_coding_cn_skipped_too(self, monkeypatch):
        """Same skip applies to the CN variant."""
        fake_or_client = MagicMock(name="openrouter_client")

        monkeypatch.setattr(
            "agent.auxiliary_client._read_main_provider", lambda: "kimi-coding-cn",
        )
        monkeypatch.setattr(
            "agent.auxiliary_client._read_main_model", lambda: "kimi-code",
        )
        rpc_mock = MagicMock(side_effect=AssertionError(
            "resolve_provider_client should NOT be called for kimi-coding-cn"))
        monkeypatch.setattr(
            "agent.auxiliary_client.resolve_provider_client", rpc_mock,
        )
        monkeypatch.setattr(
            "agent.auxiliary_client._resolve_strict_vision_backend",
            lambda p, m=None: (fake_or_client, "gemini")
            if p == "openrouter"
            else (None, None),
        )

        provider, client, _ = resolve_vision_provider_client()
        assert provider == "openrouter"
        assert client is fake_or_client

    def test_explicit_override_to_kimi_coding_still_honored(self, monkeypatch):
        """When a user *explicitly* requests kimi-coding for vision (e.g.
        they know what they're doing, or are running a future build that
        adds image_in capability to Kimi Code), the explicit path still
        routes to kimi-coding — only the auto branch applies the skip.
        """
        monkeypatch.setattr(
            "agent.auxiliary_client._read_main_provider", lambda: "openrouter",
        )
        fake_kimi_client = MagicMock(name="kimi_client")
        gcc_mock = MagicMock(return_value=(fake_kimi_client, "kimi-code"))
        monkeypatch.setattr(
            "agent.auxiliary_client._get_cached_client", gcc_mock,
        )

        provider, client, model = resolve_vision_provider_client(
            provider="kimi-coding",
        )
        assert provider == "kimi-coding"
        assert client is fake_kimi_client
        gcc_mock.assert_called_once()

    def test_skip_set_covers_exactly_known_entries(self):
        """Guard against accidental widening of the skip list."""
        from agent.auxiliary_client import _PROVIDERS_WITHOUT_VISION
        assert _PROVIDERS_WITHOUT_VISION == frozenset({
            "kimi-coding",
            "kimi-coding-cn",
        })


# ---------------------------------------------------------------------------
# _build_call_kwargs — tool dedup at API boundary
# ---------------------------------------------------------------------------

class TestBuildCallKwargsToolDedup:
    """_build_call_kwargs must deduplicate tool names before passing to API.

    Providers like Google Vertex, Azure, and Bedrock reject requests with
    duplicate tool names (HTTP 400).  This guard converts a hard failure into
    a warning log so agent turns succeed even if an upstream injection path
    regresses.  See: https://github.com/NousResearch/hermes-agent/issues/18478
    """

    def _make_tool(self, name: str) -> dict:
        return {
            "type": "function",
            "function": {
                "name": name,
                "description": f"Tool {name}",
                "parameters": {"type": "object", "properties": {}},
            },
        }

    def test_unique_tools_pass_through_unchanged(self):
        tools = [self._make_tool("alpha"), self._make_tool("beta")]
        kwargs = _build_call_kwargs(
            provider="openai", model="gpt-4o", messages=[], tools=tools,
        )
        assert len(kwargs["tools"]) == 2
        names = [t["function"]["name"] for t in kwargs["tools"]]
        assert names == ["alpha", "beta"]

    def test_duplicate_tool_names_are_deduplicated(self):
        """RED test — must fail until dedup guard is added."""
        tools = [
            self._make_tool("lcm_grep"),
            self._make_tool("lcm_describe"),
            self._make_tool("lcm_grep"),  # duplicate
            self._make_tool("lcm_expand"),
            self._make_tool("lcm_describe"),  # duplicate
        ]
        kwargs = _build_call_kwargs(
            provider="google", model="gemini-2.5-pro", messages=[], tools=tools,
        )
        result_tools = kwargs["tools"]
        names = [t["function"]["name"] for t in result_tools]
        # Must be deduplicated — no repeated names
        assert len(names) == len(set(names)), (
            f"Duplicate tool names found: {names}"
        )
        assert len(result_tools) == 3  # lcm_grep, lcm_describe, lcm_expand

    def test_empty_tools_unchanged(self):
        kwargs = _build_call_kwargs(
            provider="openai", model="gpt-4o", messages=[], tools=[],
        )
        assert kwargs.get("tools") == [] or "tools" not in kwargs

    def test_none_tools_unchanged(self):
        kwargs = _build_call_kwargs(
            provider="openai", model="gpt-4o", messages=[], tools=None,
        )
        assert "tools" not in kwargs


@pytest.fixture(autouse=True)
def _clean_env(monkeypatch):
    """Strip provider env vars so each test starts clean."""
    for key in (
        "OPENROUTER_API_KEY", "OPENAI_BASE_URL", "OPENAI_API_KEY",
    ):
        monkeypatch.delenv(key, raising=False)


class TestOpenRouterExplicitApiKey:
    """Test that explicit_api_key is correctly propagated to _try_openrouter()."""

    def test_resolve_provider_client_passes_explicit_api_key_to_openrouter(
        self, monkeypatch
    ):
        """
        When resolve_provider_client() is called with explicit_api_key for OpenRouter,
        the explicit key should be passed to the OpenAI client instead of falling back
        to OPENROUTER_API_KEY env var.
        """
        # Set up env var as fallback (should NOT be used when explicit_api_key is provided)
        monkeypatch.setenv("OPENROUTER_API_KEY", "env-fallback-key")

        # Mock OpenAI to capture the api_key used
        mock_openai = MagicMock()
        mock_openai.return_value = MagicMock(name="openrouter-client")

        with patch("agent.auxiliary_client.OpenAI", mock_openai):
            client, model = resolve_provider_client(
                provider="openrouter",
                explicit_api_key="explicit-pool-key",
            )

            # Verify a client was created
            assert client is not None
            # Verify the explicit key was used, not the env var fallback
            mock_openai.assert_called_once()
            call_kwargs = mock_openai.call_args[1]
            assert call_kwargs["api_key"] == "explicit-pool-key", (
                f"Expected explicit_api_key to be passed, got: {call_kwargs['api_key']}"
            )
            assert call_kwargs["api_key"] != "env-fallback-key", (
                "Should NOT fall back to OPENROUTER_API_KEY when explicit_api_key is provided"
            )

    def test_resolve_provider_client_without_explicit_api_key_falls_back_to_env(
        self, monkeypatch
    ):
        """
        When resolve_provider_client() is called WITHOUT explicit_api_key for OpenRouter,
        it should fall back to OPENROUTER_API_KEY env var.
        """
        # Set up env var as fallback (should be used when explicit_api_key is NOT provided)
        monkeypatch.setenv("OPENROUTER_API_KEY", "env-fallback-key")

        # Mock OpenAI to capture the api_key used
        mock_openai = MagicMock()
        mock_openai.return_value = MagicMock(name="openrouter-client")

        with patch("agent.auxiliary_client.OpenAI", mock_openai):
            client, model = resolve_provider_client(
                provider="openrouter",
                explicit_api_key=None,
            )

            # Verify a client was created
            assert client is not None
            # Verify the env var fallback was used
            mock_openai.assert_called_once()
            call_kwargs = mock_openai.call_args[1]
            assert call_kwargs["api_key"] == "env-fallback-key", (
                f"Expected env fallback key to be used when explicit_api_key is None, got: {call_kwargs['api_key']}"
            )