Prompt for human feedback in LangGraph Functional API HITL sample

[musi22]

Description

Brings the LangGraph Functional API human-in-the-loop sample to parity with the Graph API version and makes both HITL samples deliberately model-free (per review feedback from @brianstrauch):

• Both Functional and Graph API HITL samples are deliberately model-free and runnable out of the box without an Anthropic API key or external network dependencies.
• The runner scripts prompt interactively at the terminal for approval or revision notes instead of auto-approving.
• Workflows generate an initial draft deterministically and revise it based on human feedback when requested.
• Unit tests (human_in_the_loop_test.py and functional_human_in_the_loop_test.py) test approval and revision deterministically without LLM mocking.
• Updated READMEs to describe the interactive flow.

Ref: #146, #324

[CLAassistant]

All committers have signed the CLA.

[Copilot]

🟡 Changes recommended

The README should document the required ANTHROPIC_API_KEY setup for the configured model.

Get a fresh assessment by requesting another Copilot review.

Pull request overview

Updates the Functional API human-in-the-loop sample with LLM-generated drafts, interactive feedback, and revision support.

Changes:

• Adds LLM-based drafting and revision.
• Prompts for terminal approval or revision feedback.
• Adds deterministic mocked tests.
• Updates the interactive workflow documentation.

File summaries

File	Summary
tests/langgraph_plugin/functional_human_in_the_loop_test.py	Tests approval and revision with mocked chat-model calls.
langgraph_plugin/functional_api/human_in_the_loop/workflow.py	Generates and revises drafts with an LLM.
langgraph_plugin/functional_api/human_in_the_loop/run_workflow.py	Prompts for interactive human feedback.
langgraph_plugin/functional_api/human_in_the_loop/README.md	Documents the workflow; should specify the required Anthropic credential setup.

Review details

• Files reviewed: 4/4 changed files
• Comments generated: 1
• Review effort level: Lite

---

💡 Add a code-review agent skill or configure MCP servers for context-aware, tailored reviews. Learn more in the docs.