LangGraph plugin samples by DABH · Pull Request #289 · temporalio/samples-python

DABH · 2026-04-14T23:09:55Z

Summary

Add samples demonstrating the Temporal LangGraph plugin, which runs LangGraph workflows as durable Temporal workflows. Each graph node or @task executes as a Temporal activity with automatic retries, timeouts, and crash recovery.

Samples are provided for both the Graph API (declarative StateGraph with nodes and edges) and the Functional API (imperative @task / @entrypoint decorators).

Sample	Graph API	Functional API	Description
Hello World	✅	✅	Minimal sample — single node/task that processes a query string. Start here.
Human-in-the-loop	✅	✅	Chatbot that uses `interrupt()` to pause for human approval, Temporal signals to receive feedback, and queries to expose the pending draft.
Continue-as-new	✅	✅	Multi-stage data pipeline that uses `continue-as-new` with task result caching so previously-completed stages are not re-executed.
ReAct Agent	✅	✅	Tool-calling agent loop. Graph API uses `add_conditional_edges`; Functional API uses a `while` loop.
Control Flow	—	✅	Parallel task execution, `for` loops, and `if/else` branching — patterns that are natural in the Functional API.
LangSmith Tracing	✅	✅	Combines `LangGraphPlugin` with Temporal's `LangSmithPlugin` for durable execution + full LLM observability. Requires API keys.

Key Features Demonstrated

Durable execution — Every graph node / @task runs as a Temporal activity with configurable timeouts and retry policies.
Human-in-the-loop — LangGraph's interrupt() pauses the graph; Temporal signals deliver human input; queries expose pending state to UIs.
Continue-as-new with caching — get_cache() captures completed task results; passing the cache to the next execution avoids re-running them.
Conditional routing — Graph API's add_conditional_edges and Functional API's native if/else/while for agent loops.
Parallel execution — Functional API launches multiple tasks concurrently by creating futures before awaiting them.
LangSmith observability — LangSmithPlugin on the client + LangGraphPlugin on the worker for full trace propagation through Temporal workflows.

Related PRs

SDK: AI-36: Add LangGraph plugin sdk-python#1448
Supersedes: LangGraph Samples #272

Test plan

Samples are not runnable until the SDK PR lands; verify after merge of AI-36: Add LangGraph plugin sdk-python#1448
Run each sample with uv run langgraph_plugin/<api>/<sample>/run_worker.py + run_workflow.py
LangSmith tracing samples require ANTHROPIC_API_KEY and LANGCHAIN_API_KEY

Seven samples demonstrating the Temporal LangGraph plugin across both the Graph API and Functional API: - Human-in-the-loop: interrupt() + Temporal signals for chatbot approval - Continue-as-new: task result caching across workflow boundaries - ReAct agent: tool-calling loop with conditional edges / while loop - Control flow (Functional API only): parallel, for-loop, if/else Related SDK PR: temporalio/sdk-python#1448

CLAassistant · 2026-04-14T23:10:01Z

All committers have signed the CLA.

CLAassistant · 2026-04-14T23:10:03Z

Thank you for your submission! We really appreciate it. Like many open source projects, we ask that you sign our Contributor License Agreement before we can accept your contribution.
_{You have signed the CLA already but the status is still pending? Let us recheck it.}

… merge) so that CI otherwise passes

Copilot

Pull request overview

Adds a new langgraph_plugin/ sample suite to demonstrate running LangGraph workflows as durable Temporal workflows via the Temporal LangGraph plugin, covering both LangGraph Graph API and Functional API patterns.

Changes:

Introduces 7 new LangGraph+Temporal sample workflows (human-in-the-loop, continue-as-new w/ caching, ReAct agent, control-flow).
Adds a new langgraph dependency group and includes langgraph_plugin in the build packages list.
Updates repository documentation to link to the new sample suite and provides a dedicated README for running the samples.

Reviewed changes

Copilot reviewed 24 out of 34 changed files in this pull request and generated 6 comments.

Show a summary per file

File	Description
pyproject.toml	Adds `langgraph` dependency group, includes `langgraph_plugin` in wheel packages, adjusts lint/test tasks, and adds mypy override.
README.md	Links the new `langgraph_plugin` samples from the repo root README.
langgraph_plugin/README.md	Adds usage documentation and a sample matrix for the new suite.
langgraph_plugin/init.py	Declares the new top-level sample package.
langgraph_plugin/graph_api/init.py	Declares Graph API samples namespace.
langgraph_plugin/graph_api/react_agent/init.py	Declares Graph API ReAct agent package.
langgraph_plugin/graph_api/react_agent/workflow.py	Implements Graph API ReAct agent workflow and graph definition.
langgraph_plugin/graph_api/react_agent/run_worker.py	Worker wiring for Graph API ReAct agent sample.
langgraph_plugin/graph_api/react_agent/run_workflow.py	Starter script for Graph API ReAct agent sample.
langgraph_plugin/graph_api/human_in_the_loop/init.py	Declares Graph API human-in-the-loop package.
langgraph_plugin/graph_api/human_in_the_loop/workflow.py	Implements Graph API interrupt + Temporal signal/query human approval flow.
langgraph_plugin/graph_api/human_in_the_loop/run_worker.py	Worker wiring for Graph API human-in-the-loop sample.
langgraph_plugin/graph_api/human_in_the_loop/run_workflow.py	Starter script for Graph API human-in-the-loop sample.
langgraph_plugin/graph_api/continue_as_new/init.py	Declares Graph API continue-as-new package.
langgraph_plugin/graph_api/continue_as_new/workflow.py	Implements Graph API pipeline w/ continue-as-new + cache handoff.
langgraph_plugin/graph_api/continue_as_new/run_worker.py	Worker wiring for Graph API continue-as-new sample.
langgraph_plugin/graph_api/continue_as_new/run_workflow.py	Starter script for Graph API continue-as-new sample.
langgraph_plugin/functional_api/init.py	Declares Functional API samples namespace.
langgraph_plugin/functional_api/react_agent/init.py	Declares Functional API ReAct agent package.
langgraph_plugin/functional_api/react_agent/workflow.py	Implements Functional API ReAct agent via `@task` + `@entrypoint`.
langgraph_plugin/functional_api/react_agent/run_worker.py	Worker wiring for Functional API ReAct agent sample.
langgraph_plugin/functional_api/react_agent/run_workflow.py	Starter script for Functional API ReAct agent sample.
langgraph_plugin/functional_api/human_in_the_loop/init.py	Declares Functional API human-in-the-loop package.
langgraph_plugin/functional_api/human_in_the_loop/workflow.py	Implements Functional API interrupt + signal/query human approval flow.
langgraph_plugin/functional_api/human_in_the_loop/run_worker.py	Worker wiring for Functional API human-in-the-loop sample.
langgraph_plugin/functional_api/human_in_the_loop/run_workflow.py	Starter script for Functional API human-in-the-loop sample.
langgraph_plugin/functional_api/control_flow/init.py	Declares Functional API control-flow package.
langgraph_plugin/functional_api/control_flow/workflow.py	Implements Functional API sample demonstrating parallelism + branching.
langgraph_plugin/functional_api/control_flow/run_worker.py	Worker wiring for Functional API control-flow sample.
langgraph_plugin/functional_api/control_flow/run_workflow.py	Starter script for Functional API control-flow sample.
langgraph_plugin/functional_api/continue_as_new/init.py	Declares Functional API continue-as-new package.
langgraph_plugin/functional_api/continue_as_new/workflow.py	Implements Functional API pipeline w/ continue-as-new + cache handoff.
langgraph_plugin/functional_api/continue_as_new/run_worker.py	Worker wiring for Functional API continue-as-new sample.
langgraph_plugin/functional_api/continue_as_new/run_workflow.py	Starter script for Functional API continue-as-new sample.

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

…gs, and configurable client

Combines LangGraphPlugin (durable execution) with LangSmithPlugin (observability) for full tracing of LLM calls through Temporal workflows.

- graphs parameter is now a list, not a dict - No graph()/entrypoint() lookup functions — reference objects directly - No entrypoints parameter on LangGraphPlugin - Use set_cache()/get_cache() for continue-as-new caching - Update tests and READMEs accordingly

# Conflicts: # pyproject.toml # uv.lock

The plugin API has evolved past PR #1448: - LangGraphPlugin(graphs=...) now takes dict[str, StateGraph], not list - Same for entrypoints (dict[str, Pregel]) - Each node/task must declare execute_in: "activity" | "workflow" in metadata - Workflows look up registered graphs/entrypoints via graph(name) / entrypoint(name) instead of importing them directly - get_cache/set_cache replaced by cache() and graph(name, cache=...) / entrypoint(name, cache=...) Other changes: - State schemas converted from primitives (str, int) to TypedDict, since langgraph's StateT is bound to TypedDict / dataclass / pydantic models - Module-level graph instances replaced with make_<name>_graph() factories because LangGraphPlugin mutates node metadata in-place at construction time, which prevented reuse across tests - langgraph dep group now pulls langchain, langchain-anthropic, and temporalio[langgraph,langsmith] so the langsmith_tracing samples and human_in_the_loop's RunnableConfig usage actually resolve

These features rely on contextvars propagation through asyncio.create_task(), which is only available in Python 3.11+. On 3.10 they hang rather than fail cleanly, so CI sat for an hour before today's fix landed. Mirrors the pytestmark skipif used in sdk-python's own contrib/langgraph tests.

- Drop cross-references between Functional API and Graph API READMEs so each stands alone (review comment 1) - Combine run_worker.py + run_workflow.py into a single main.py for the langsmith_tracing samples to reduce setup steps (review comment 2) - Fix workflow -> Workflow casing (review comment 3) - Alias temporalio's entrypoint and graph helpers as temporal_entrypoint / temporal_graph at import sites to avoid the langgraph.func.entrypoint collision (review comment 4) - Demonstrate @Traceable in three places in both langsmith_tracing samples: on the Activity/task itself, on a helper called from the Activity, and on a helper called from the Workflow (review comment 5) - Drop unnecessary single-task list comprehension for activity_options in hello_world and langsmith_tracing functional samples (review comment 6) - Spell out 'temporal server start-dev' in every sample README's prerequisites (review comment 7) - Fix stale README references to get_cache() now that the API is cache() (review comment 8) - Rename arbitrarily-named ETL pipeline functions in continue_as_new to honest math names (double / add_50 / triple) per review comment 9

brianstrauch · 2026-04-29T16:07:35Z

+      # (see [tool.uv.sources] in pyproject.toml). Drop this step once the SDK
+      # ships a release that includes the LangGraph plugin.


Can we just leave this step? I assume we'll need to constantly add and remove it as we write new plugins + samples.

brianstrauch · 2026-04-29T16:08:34Z

@@ -0,0 +1,36 @@
+# Continue-as-New with Caching (Functional API)
+
+Demonstrates combining Temporal's continue-as-new with LangGraph's task result caching to avoid re-executing completed `@task` functions across workflow boundaries.


It's actually OUR task result caching, right?

brianstrauch · 2026-04-29T16:15:09Z

+activity_options = {
+    t.func.__name__: {
+        "execute_in": "activity",
+        "start_to_close_timeout": timedelta(seconds=30),
+    }
+    for t in all_tasks
+}


It feels like we're hacking around our own limitations here. Let's just be explicit everywhere or make this more user friendly.

(My vote is to be more explicit, that was the point of making this change anyways)

brianstrauch · 2026-04-29T16:17:39Z

@@ -0,0 +1,37 @@
+# Human-in-the-Loop Chatbot (Functional API)
+
+Demonstrates using LangGraph's `interrupt()` to pause an entrypoint for human review, combined with Temporal signals and queries for asynchronous feedback, using the imperative `@task`/`@entrypoint` style.


Signals and Queries are important to mention here, but the real star of the show is wait_condition which can wait indefinitely

brianstrauch · 2026-04-29T16:18:25Z

+activity_options = {
+    t.func.__name__: {
+        "execute_in": "activity",
+        "start_to_close_timeout": timedelta(seconds=30),
+    }
+    for t in all_tasks
+}


brianstrauch · 2026-04-29T16:19:14Z

@@ -0,0 +1,37 @@
+# LangSmith Tracing (Functional API)
+
+Demonstrates combining `LangGraphPlugin` (durable task execution) with Temporal's `LangSmithPlugin` (observability) for full tracing of LLM calls through Temporal workflows, using LangGraph's `@task` and `@entrypoint` decorators.


Redundant, tracing = observability

Suggested change

Demonstrates combining `LangGraphPlugin` (durable task execution) with Temporal's `LangSmithPlugin` (observability) for full tracing of LLM calls through Temporal workflows, using LangGraph's `@task` and `@entrypoint` decorators.

Demonstrates combining `LangGraphPlugin` (durable task execution) with Temporal's `LangSmithPlugin` for full tracing of LLM calls through Temporal workflows, using LangGraph's `@task` and `@entrypoint` decorators.

DABH requested a review from a team as a code owner April 14, 2026 23:09

DABH requested review from brianstrauch and Copilot April 14, 2026 23:16

Copilot started reviewing on behalf of DABH April 14, 2026 23:16 View session

DABH added 2 commits April 14, 2026 18:17

Remove explicit langchain deps from langgraph group to avoid conflict

8a260c6

Declare langchain and langgraph as conflicting dependency groups

042a51f

This comment was marked as outdated.

Sign in to view

DABH added 2 commits April 14, 2026 18:22

Fix import sorting and formatting

3e7f91b

Update dependencies and lint config (temporarily - waiting for SDK PR…

0505fd1

… merge) so that CI otherwise passes

DABH force-pushed the langgraph-samples branch from 0256bd3 to 0505fd1 Compare April 15, 2026 00:38

DABH requested a review from Copilot April 15, 2026 00:40

Copilot started reviewing on behalf of DABH April 15, 2026 00:40 View session

Copilot AI reviewed Apr 15, 2026

View reviewed changes

DABH added 3 commits April 14, 2026 21:21

Add hello_world samples, per-sample READMEs, tests, __init__ docstrin…

ee781cd

…gs, and configurable client

Address review: consistent v2 API, unique thread_id, SDK prereq note

e2832bb

Remove SDK prereq note - PR won't merge until plugin is released

f3fb15c

DABH mentioned this pull request Apr 15, 2026

LangGraph Samples #272

Closed

Add LangSmith tracing sample (Graph API + Functional API)

67d1310

Combines LangGraphPlugin (durable execution) with LangSmithPlugin (observability) for full tracing of LLM calls through Temporal workflows.

brianstrauch reviewed Apr 15, 2026

View reviewed changes

DABH mentioned this pull request Apr 16, 2026

Add LangGraph integration documentation temporalio/documentation#4442

Draft

5 tasks

DABH added 3 commits April 18, 2026 17:24

Merge branch 'main' into langgraph-samples

a5e3871

# Conflicts: # pyproject.toml # uv.lock

DABH force-pushed the langgraph-samples branch from 3ebfbd2 to 9c06edd Compare April 29, 2026 04:05

DABH added 3 commits April 28, 2026 23:15

CI: install protoc for building temporalio from sdk-python git source

85a2ab1

DABH requested a review from brianstrauch April 29, 2026 06:30

brianstrauch reviewed Apr 29, 2026

View reviewed changes

		# (see [tool.uv.sources] in pyproject.toml). Drop this step once the SDK
		# ships a release that includes the LangGraph plugin.

		@@ -0,0 +1,36 @@
		# Continue-as-New with Caching (Functional API)

		Demonstrates combining Temporal's continue-as-new with LangGraph's task result caching to avoid re-executing completed `@task` functions across workflow boundaries.

		@@ -0,0 +1,37 @@
		# Human-in-the-Loop Chatbot (Functional API)

		Demonstrates using LangGraph's `interrupt()` to pause an entrypoint for human review, combined with Temporal signals and queries for asynchronous feedback, using the imperative `@task`/`@entrypoint` style.

		@@ -0,0 +1,37 @@
		# LangSmith Tracing (Functional API)

		Demonstrates combining `LangGraphPlugin` (durable task execution) with Temporal's `LangSmithPlugin` (observability) for full tracing of LLM calls through Temporal workflows, using LangGraph's `@task` and `@entrypoint` decorators.

Conversation

DABH commented Apr 14, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Summary

Key Features Demonstrated

Related PRs

Test plan

Uh oh!

CLAassistant commented Apr 14, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

CLAassistant commented Apr 14, 2026

Uh oh!

This comment was marked as outdated.

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Reviewed changes

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

brianstrauch Apr 29, 2026

Choose a reason for hiding this comment

Uh oh!

brianstrauch Apr 29, 2026

Choose a reason for hiding this comment

Uh oh!

brianstrauch Apr 29, 2026

Choose a reason for hiding this comment

Uh oh!

brianstrauch Apr 29, 2026

Choose a reason for hiding this comment

Uh oh!

brianstrauch Apr 29, 2026

Choose a reason for hiding this comment

Uh oh!

brianstrauch Apr 29, 2026

Choose a reason for hiding this comment

Uh oh!

brianstrauch Apr 29, 2026

Choose a reason for hiding this comment

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

4 participants

DABH commented Apr 14, 2026 •

edited

Loading

CLAassistant commented Apr 14, 2026 •

edited

Loading