fix(langchain_v1): ensure HITL middleware edits persist correctly

[zhangzhefang-github]

Description

Fixes a critical bug in the Human-in-the-Loop middleware where edits to tool calls were not persisting correctly in the agent's message history.

The Problem:
When a user edited a tool call via HITL middleware, the edited tool would execute correctly. However, the agent's subsequent model calls would still see the ORIGINAL (unedited) tool_calls in the AIMessage, causing the agent to re-attempt the original tool call and leading to duplicate or incorrect executions.

Root Cause:
The middleware was directly mutating the AIMessage.tool_calls attribute (last_ai_msg.tool_calls = revised_tool_calls), but LangGraph's state management doesn't properly persist direct object mutations.

The Fix:

• Create a new AIMessage instance instead of mutating the original
• Ensure the message has an ID (generate UUID if needed) so LangGraph's add_messages reducer properly replaces the message instead of appending a duplicate
• Copy all relevant fields (content, name, metadata, etc.) to the new message

Testing:

• Added comprehensive test case test_human_in_the_loop_middleware_edit_actually_executes_with_edited_args that simulates the exact scenario from the issues
• Verifies the edited tool call executes with correct arguments
• Verifies the AIMessage in state contains edited (not original) parameters
• Confirms no duplicate executions occur
• All 16 existing HITL middleware tests pass

Issue

Fixes #33787
Fixes #33784

Dependencies

No new dependencies added.

[zhangzhefang-github]

@sydney-runkle Hi! I've investigated the CI failure and found:

The failing test is unrelated to my PR:

• My PR only modifies libs/langchain_v1 code (HITL middleware)
• The failing test is in libs/core/tests/unit_tests/runnables/test_runnable.py
• I didn't modify any libs/core files

The test only fails on Python 3.12:

• ✅ Passes on Python 3.10 (both master and this PR branch)
• ❌ Fails on Python 3.12 (CI environment)
• Error: ValueError('generator already executing')

All my HITL tests pass:

• ✅ All 70 HITL middleware tests pass locally
• ✅ Including the new test that verifies the fix for Agent re-attempts original tool call after HumanInTheLoopMiddleware edit decision #33787 and when using human-in-the-loop, i find that the llm recall the same tool with original parameter if i had edited the tool parameter,why #33784

This appears to be a Python 3.12-specific issue in libs/core, possibly related to recent tracing changes (commit 76dd656). Could you please re-run CI or advise how to proceed?

[zhangzhefang-github]

Hi @sydney-runkle,

I've reverted the master merge that was causing CI failures. Here's what happened:

Timeline:

• Nov 3: Original commit (69d4f40) - ✅ All tests passed
• Nov 4: GitHub suggested updating the branch, so I merged master
• Result: ❌ CI failed on libs/core tests (unrelated to my changes)

Analysis:

• The failing test test_runnable_lambda_context_config is in libs/core
• My PR only modifies libs/langchain_v1 files
• The test failure is Python 3.12-specific, likely from recent master changes
• Error: ValueError('generator already executing')

Resolution:

• Reverted to original commit (69d4f40)
• ✅ All 70 HITL middleware tests pass
• ✅ Including the new test that fixes Agent re-attempts original tool call after HumanInTheLoopMiddleware edit decision #33787 and when using human-in-the-loop, i find that the llm recall the same tool with original parameter if i had edited the tool parameter,why #33784

The PR is ready for review. I can merge master again after the core test issue is resolved.