Testing

@threadplane/langgraph ships two purpose-built test doubles, plus an advanced manual-scripting transport for the rare cases that need it:

provideFakeAgent() — a one-call fake backend that runs the real adapter pipeline and streams canned tokens. No server, no LLM. Reach for this first.
mockLangGraphAgent() — a writable-signal mock for component/unit tests, where you set messages(), status(), etc. directly.
MockAgentTransport — an advanced escape hatch for hand-scripting exact wire event sequences (tool calls, interrupts, multi-batch lifecycles).

No flaky tests

None of these touch the network, the LLM, or server state. Every test run produces identical results. Your CI pipeline stays green.

See Choosing an adapter → Testing for when to use each test double.

#Fake backend: `provideFakeAgent()`

provideFakeAgent({ tokens, reasoningTokens, delayMs }) wires a fake backend into Angular DI in one call. It exercises the real adapter pipeline — injectAgent(), status transitions, message accumulation — but the wire events are canned, so there's no server and no LLM. Use it for adapter-integration tests, in-browser demos, and offline development.

It drops in exactly where provideAgent() would go:

import { ApplicationConfig } from '@angular/core';
import { provideFakeAgent } from '@threadplane/langgraph';
 
export const appConfig: ApplicationConfig = {
  providers: [
    provideFakeAgent({ tokens: ['Hello', ' world'] }),
  ],
};

The component is byte-identical to production — only the provider changes. FakeAgentConfig ({ tokens?, reasoningTokens?, delayMs? }) lives in @threadplane/chat/testing:

Option	Type	Notes
`tokens`	`string[]`	Emitted as streamed text deltas, in order.
`reasoningTokens`	`string[]`	Emitted before text deltas to exercise reasoning UI.
`delayMs`	`number`	Delay between streamed events.

#Contract mock: `mockLangGraphAgent()`

For component and unit tests where you don't need a streaming pipeline at all, mockLangGraphAgent(initial) returns a LangGraphAgent whose state surface is exposed as writable signals. Set state directly and assert your component reacts — nothing is real.

import { mockLangGraphAgent } from '@threadplane/langgraph';
 
const m = mockLangGraphAgent({ status: 'running' });
m.messages.set([{ role: 'assistant', content: 'Hello!' }]);
 
expect(m.messages()[0].content).toBe('Hello!');
expect(m.status()).toBe('running');

mockLangGraphAgent() extends the neutral mockAgent() from @threadplane/chat — it supplies the neutral Agent-contract writable signals (messages, status, isLoading, error, interrupt, …) plus submit/stop call tracking, then layers the LangGraph-specific signals (langGraphMessages, branch, queue, …) on top.

#Advanced: `MockAgentTransport`

Lead with provideFakeAgent() for the simple case. Reach for MockAgentTransport only when you need to hand-script exact wire event sequences — tool calls, interrupts, or multi-batch streaming lifecycles that the canned-token fake can't express.

No flaky tests

MockAgentTransport eliminates network dependencies, timing issues, and server state. Every test run produces identical results.

#Python: Testing the Agent

Before testing the Angular side, make sure your agent logic is correct. LangGraph agents are plain Python functions — test them directly with pytest.

import pytest
from langchain_core.messages import HumanMessage
from my_agent.agent import graph
 
@pytest.mark.asyncio
async def test_agent_responds():
    result = await graph.ainvoke(
        {"messages": [HumanMessage(content="Hello")]},
        config={"configurable": {"thread_id": "test_1"}},
    )
    assert len(result["messages"]) >= 2
    assert result["messages"][-1].type == "ai"
 
@pytest.mark.asyncio
async def test_agent_uses_tools():
    result = await graph.ainvoke(
        {"messages": [HumanMessage(content="Search for LangGraph docs")]},
        config={"configurable": {"thread_id": "test_2"}},
    )
    # Verify the agent called the search tool
    tool_messages = [m for m in result["messages"] if m.type == "tool"]
    assert len(tool_messages) > 0

Agent tests are fast

With MemorySaver and a mocked LLM, agent tests run in milliseconds. Use langchain_core.language_models.FakeListChatModel to remove the LLM dependency entirely.

#MockAgentTransport: Basic Setup

On the Angular side, MockAgentTransport replaces the real HTTP transport. Register it through provideAgent({ transport }) in TestBed's providers array, then call injectAgent() inside TestBed.runInInjectionContext.

import { TestBed } from '@angular/core/testing';
import { MockAgentTransport, provideAgent, injectAgent } from '@threadplane/langgraph';
 
describe('ChatComponent', () => {
  it('should display agent messages', () => {
    const transport = new MockAgentTransport();
 
    TestBed.configureTestingModule({
      providers: [
        provideAgent({
          apiUrl: '',
          assistantId: 'test_agent',
          transport,
        }),
      ],
    });
 
    TestBed.runInInjectionContext(() => {
      const chat = injectAgent();
 
      // Emit a values event — simulates the agent responding
      transport.emit([
        {
          type: 'values',
          messages: [{ role: 'assistant', content: 'Hello!' }],
        },
      ]);
 
      expect(chat.messages().length).toBe(1);
      expect(chat.messages()[0].content).toBe('Hello!');
    });
  });
});

#Scripted Event Sequences

Pass event batches to the constructor for sequential playback. Each call to nextBatch() returns one batch; emit that batch to advance what the component sees.

const transport = new MockAgentTransport([
  // Batch 1: Agent starts thinking
  [{ type: 'values', messages: [{ role: 'assistant', content: 'Analyzing...' }] }],
  // Batch 2: Agent finishes
  [{ type: 'values', messages: [{ role: 'assistant', content: 'Here is your answer.' }] }],
]);
 
TestBed.configureTestingModule({
  providers: [
    provideAgent({ apiUrl: '', assistantId: 'test_agent', transport }),
  ],
});
 
TestBed.runInInjectionContext(() => {
  const chat = injectAgent();
 
  chat.submit({ message: 'Explain signals' });
 
  // Step through each batch
  transport.emit(transport.nextBatch());
  expect(chat.messages()[0].content).toBe('Analyzing...');
 
  transport.emit(transport.nextBatch());
  expect(chat.messages()[0].content).toBe('Here is your answer.');
});

#Testing the Streaming Lifecycle

The most common test pattern verifies the full submit-to-idle lifecycle: submit sets the agent running, values arrive, and the status settles back to idle.

import { TestBed } from '@angular/core/testing';
import { MockAgentTransport, provideAgent, injectAgent } from '@threadplane/langgraph';
 
describe('streaming lifecycle', () => {
  it('should transition through running → values → idle', () => {
    const transport = new MockAgentTransport([
      [{ type: 'values', messages: [{ role: 'assistant', content: 'Thinking...' }] }],
      [{ type: 'values', messages: [{ role: 'assistant', content: 'Done!' }] }],
    ]);
 
    TestBed.configureTestingModule({
      providers: [
        provideAgent({ apiUrl: '', assistantId: 'test_agent', transport }),
      ],
    });
 
    TestBed.runInInjectionContext(() => {
      const chat = injectAgent();
 
      // Initial state
      expect(chat.status()).toBe('idle');
      expect(chat.messages()).toEqual([]);
 
      // Submit triggers running
      chat.submit({ message: 'Hello' });
      expect(chat.status()).toBe('running');
      expect(chat.isLoading()).toBe(true);
 
      // First batch — partial response
      transport.emit(transport.nextBatch());
      expect(chat.messages()[0].content).toBe('Thinking...');
      expect(chat.status()).toBe('running');
 
      // Second batch — final response
      transport.emit(transport.nextBatch());
      expect(chat.messages()[0].content).toBe('Done!');
 
      // Stream completes
      transport.close();
      expect(chat.status()).toBe('idle');
      expect(chat.isLoading()).toBe(false);
    });
  });
});

#Testing Interrupts

Script an interrupt event to test human-in-the-loop flows. Verify the interrupt signal surfaces the payload, then resume and confirm the agent continues.

import { TestBed } from '@angular/core/testing';
import { MockAgentTransport, provideAgent, injectAgent } from '@threadplane/langgraph';
 
describe('interrupt handling', () => {
  it('should surface interrupt and resume on approval', () => {
    const transport = new MockAgentTransport();
 
    TestBed.configureTestingModule({
      providers: [
        provideAgent({ apiUrl: '', assistantId: 'approval_agent', transport }),
      ],
    });
 
    TestBed.runInInjectionContext(() => {
      const chat = injectAgent();
 
      // Agent hits an interrupt
      transport.emit([
        {
          type: 'interrupt',
          value: { action: 'delete_account', risk: 'high' },
        },
      ]);
 
      // Verify interrupt signal
      expect(chat.interrupt()).toBeDefined();
      expect(chat.interrupt()?.value.action).toBe('delete_account');
      expect(chat.interrupt()?.value.risk).toBe('high');
 
      // User approves — resume the agent
      chat.submit({ resume: { approved: true } });
 
      // Agent continues after approval
      transport.emit([
        {
          type: 'values',
          messages: [{ role: 'assistant', content: 'Account deleted.' }],
        },
      ]);
 
      expect(chat.interrupt()).toBeUndefined();
      expect(chat.messages()[0].content).toBe('Account deleted.');
    });
  });
});

#Testing Errors

Inject errors with emitError() to verify your component handles failures gracefully.

import { TestBed } from '@angular/core/testing';
import { MockAgentTransport, provideAgent, injectAgent } from '@threadplane/langgraph';
 
describe('error handling', () => {
  function configureWithTransport(transport: MockAgentTransport) {
    TestBed.resetTestingModule();
    TestBed.configureTestingModule({
      providers: [
        provideAgent({ apiUrl: '', assistantId: 'test_agent', transport }),
      ],
    });
  }
 
  it('should surface errors and set error status', () => {
    const transport = new MockAgentTransport();
    configureWithTransport(transport);
 
    TestBed.runInInjectionContext(() => {
      const chat = injectAgent();
 
      chat.submit({ message: 'Hello' });
 
      // Simulate a connection failure
      transport.emitError(new Error('Connection lost'));
 
      expect(chat.error()).toBeDefined();
      expect(chat.error()?.message).toBe('Connection lost');
      expect(chat.status()).toBe('error');
      expect(chat.isLoading()).toBe(false);
    });
  });
 
  it('should recover from errors on retry', () => {
    const transport = new MockAgentTransport();
    configureWithTransport(transport);
 
    TestBed.runInInjectionContext(() => {
      const chat = injectAgent();
 
      // First attempt fails
      chat.submit({ message: 'Hello' });
      transport.emitError(new Error('Timeout'));
      expect(chat.status()).toBe('error');
 
      // Retry succeeds
      chat.submit({ message: 'Hello' });
      transport.emit([
        {
          type: 'values',
          messages: [{ role: 'assistant', content: 'Sorry for the delay!' }],
        },
      ]);
 
      expect(chat.status()).not.toBe('error');
      expect(chat.messages()[0].content).toBe('Sorry for the delay!');
    });
  });
});

#Testing Thread Switching

Verify that switching threads loads the correct conversation state and clears the previous thread's messages.

describe('thread switching', () => {
  it('should load new thread state on switch', () => {
    const transport = new MockAgentTransport();
    const threadId = signal<string | null>('thread_A');
 
    TestBed.configureTestingModule({
      providers: [
        provideAgent({
          apiUrl: '',
          assistantId: 'test_agent',
          threadId,
          transport,
        }),
      ],
    });
 
    TestBed.runInInjectionContext(() => {
      const chat = injectAgent();
 
      // Thread A has messages
      transport.emit([
        {
          type: 'values',
          messages: [{ role: 'assistant', content: 'Thread A response' }],
        },
      ]);
      expect(chat.messages()[0].content).toBe('Thread A response');
 
      // Switch to thread B
      chat.switchThread('thread_B');
 
      // Thread B loads its own state
      transport.emit([
        {
          type: 'values',
          messages: [{ role: 'assistant', content: 'Thread B response' }],
        },
      ]);
      expect(chat.messages()[0].content).toBe('Thread B response');
    });
  });
 
  it('should create a new thread when switching to null', () => {
    const transport = new MockAgentTransport();
 
    TestBed.resetTestingModule();
    TestBed.configureTestingModule({
      providers: [
        provideAgent({ apiUrl: '', assistantId: 'test_agent', transport }),
      ],
    });
 
    TestBed.runInInjectionContext(() => {
      const chat = injectAgent();
 
      // Start a conversation
      transport.emit([
        {
          type: 'values',
          messages: [{ role: 'assistant', content: 'Hello' }],
        },
      ]);
 
      // Switch to new thread
      chat.switchThread(null);
      expect(chat.messages()).toEqual([]);
    });
  });
});

#Test Setup Workflow

1

Install dependencies

Make sure @threadplane/langgraph is available in your test environment. MockAgentTransport ships with the main package — no extra install needed.

2

Create the transport

Instantiate MockAgentTransport with optional pre-scripted batches for sequential playback, or leave it empty for imperative emit() calls.

3

Wrap in injection context

Call TestBed.runInInjectionContext(() => { ... }) so injectAgent() can access Angular's injector for signal creation and cleanup.

4

Configure the provider

Pass the transport into provideAgent({ ..., transport }) in TestBed's providers array. All other options (assistantId, threadId, onThreadId) work identically to production code.

5

Script events

Use transport.emit() for ad-hoc events, transport.nextBatch() for pre-scripted sequences, or transport.emitError() for failure scenarios.

6

Assert signal values

Read signals like chat.messages(), chat.status(), chat.interrupt(), and chat.error() to verify your component reacts correctly.

#Integration Testing

For end-to-end confidence, run tests against a real LangGraph dev server. The LangGraph CLI starts a local server that your tests can hit directly.

# Start the dev server
langgraph dev --config langgraph.json
 
# Run Angular tests against it (no MockAgentTransport needed)
ng test --watch=false

Integration tests are slow

Integration tests hit a real server and (potentially) a real LLM. Reserve them for CI pipelines or pre-release smoke tests. Use MockAgentTransport for the vast majority of your test suite — it runs in milliseconds with zero external dependencies.