Langchain Local Dev Loop

def test_summarize():
    out = chain.invoke({"text": "..."})
    assert out.content == "expected summary"

from langchain_core.language_models.fake import FakeListChatModel
from langchain_core.prompts import ChatPromptTemplate

def test_classifier_picks_positive():
    fake = FakeListChatModel(responses=["positive"])
    prompt = ChatPromptTemplate.from_messages([("user", "Classify: {text}")])
    chain = prompt | fake
    out = chain.invoke({"text": "I love it"})
    assert out.content == "positive"

from langchain_core.language_models.fake import FakeListChatModel
from langchain_core.outputs import ChatGeneration, ChatResult
from langchain_core.messages import AIMessage

class FakeChatWithUsage(FakeListChatModel):
    """FakeListChatModel that emits response_metadata['token_usage'] so
    downstream callbacks reading token usage do not crash under test."""

    def _generate(self, messages, stop=None, run_manager=None, **kwargs):
        response = self.responses[self.i % len(self.responses)]
        self.i += 1
        message = AIMessage(
            content=response,
            response_metadata={
                "token_usage": {
                    "input_tokens": 10,
                    "output_tokens": len(response.split()),
                    "total_tokens": 10 + len(response.split()),
                },
                "model_name": "fake-chat",
            },
            usage_metadata={
                "input_tokens": 10,
                "output_tokens": len(response.split()),
                "total_tokens": 10 + len(response.split()),
            },
        )
        return ChatResult(generations=[ChatGeneration(message=message)])

# tests/conftest.py
import pytest
from langchain_core.prompts import ChatPromptTemplate
from tests.fakes import FakeChatWithUsage

@pytest.fixture
def fake_chat():
    """Reusable fake chat model. Override responses per-test via
    monkeypatch.setattr(fake_chat, 'responses', [...])."""
    return FakeChatWithUsage(responses=["ok"])

@pytest.fixture
def summarize_chain(fake_chat):
    prompt = ChatPromptTemplate.from_messages([
        ("system", "Summarize the user's text in one line."),
        ("user", "{text}"),
    ])
    return prompt | fake_chat

def test_summary_shape(summarize_chain, fake_chat):
    fake_chat.responses = ["short summary"]
    out = summarize_chain.invoke({"text": "long input"})
    assert out.content == "short summary"

# tests/conftest.py (continued)
import pytest

@pytest.fixture(scope="module")
def vcr_config():
    return {
        "filter_headers": [
            "authorization",
            "x-api-key",
            "anthropic-version",
            "openai-organization",
            "cookie",
        ],
        "filter_query_parameters": ["api_key"],
        # Block accidental re-recording in CI:
        "record_mode": "none",
    }

import pytest

@pytest.mark.vcr  # cassette at tests/cassettes/<test_name>.yaml
@pytest.mark.integration
def test_live_claude_short_answer():
    from langchain_anthropic import ChatAnthropic
    chat = ChatAnthropic(model="claude-sonnet-4-6", temperature=0, timeout=30)
    out = chat.invoke("Say 'ok' and nothing else.")
    assert "ok" in out.content.lower()

# .git/hooks/pre-commit or .pre-commit-config.yaml entry
#!/usr/bin/env bash
set -e
if git diff --cached --name-only | grep -q '^tests/cassettes/'; then
    if git diff --cached -U0 -- 'tests/cassettes/' | \
       grep -E '(sk-ant-[a-zA-Z0-9_-]+|sk-[a-zA-Z0-9]{20,}|Bearer\s+[a-zA-Z0-9_-]{20,})'; then
        echo "ERROR: API key pattern found in staged cassette." >&2
        exit 1
    fi
fi

[tool.pytest.ini_options]
minversion = "8.0"
testpaths = ["tests"]
addopts = [
    "-ra",
    "--strict-markers",
    "--strict-config",
    "-W", "error",
]
markers = [
    "integration: hits real APIs or replays VCR cassettes (set RUN_INTEGRATION=1)",
    "slow: takes > 1s per test",
    "smoke: minimal healthcheck run in CI",
]
filterwarnings = [
    "error",
    "ignore::DeprecationWarning:langchain_community.*",
    "ignore::DeprecationWarning:pydantic.*",
    "ignore::PendingDeprecationWarning:langchain_core.*",
]

# tests/conftest.py (continued)
import os
import pytest

def pytest_collection_modifyitems(config, items):
    if os.getenv("RUN_INTEGRATION") == "1":
        return
    skip_integration = pytest.mark.skip(reason="set RUN_INTEGRATION=1 to run")
    for item in items:
        if "integration" in item.keywords:
            item.add_marker(skip_integration)

from langgraph.checkpoint.memory import MemorySaver
import uuid, pytest

@pytest.fixture
def graph_config():
    return {"configurable": {"thread_id": str(uuid.uuid4())}}

@pytest.fixture
def checkpointed_graph(fake_chat):
    from my_app.graphs import build_graph
    return build_graph(fake_chat).compile(checkpointer=MemorySaver())

def test_node_emits_plan(checkpointed_graph, graph_config, fake_chat):
    fake_chat.responses = ["step 1\nstep 2\nstep 3"]
    result = checkpointed_graph.invoke({"goal": "deploy"}, graph_config)
    # Assert state shape per node, not just the final output:
    assert result["plan"] == ["step 1", "step 2", "step 3"]
    # Time-travel: inspect every checkpoint for debugging
    history = list(checkpointed_graph.get_state_history(graph_config))
    assert history[-1].values == {"goal": "deploy"}  # initial state