Added test that fails on `master`.
`ToolNode` uses `get_type_hints` which doesn't work properly w/ partial
funcs on Python 3.12+
The diff here is nice anyways when we inline the logic.
## Summary
When invoking a tool with a `ToolCall`, the `tool_call_id` is extracted
but was **not forwarded** to callback handlers in `on_tool_start`. This
made it impossible for callback handlers to correlate tool executions
with the original LLM tool calls.
This fix adds `tool_call_id=tool_call_id` to both:
- Sync `run()` method's `on_tool_start` call
- Async `arun()` method's `on_tool_start` call
## Changes
- **`libs/core/langchain_core/tools/base.py`**: Added `tool_call_id`
parameter to `on_tool_start` calls (2 lines)
- **`libs/core/tests/unit_tests/test_tools.py`**: Added 6 comprehensive
tests covering:
- Sync tool invocation via `invoke()`
- Async tool invocation via `ainvoke()`
- `tool_call_id` is `None` when invoked without a ToolCall
- Empty string `tool_call_id` edge case
- Direct `run()` method
- Direct `arun()` method
## Test plan
- [x] All 147 existing tests pass
- [x] 6 new tests added and passing
- [x] Linting passes
Fixes#34168
---
This PR was developed with AI assistance (Claude).
---------
Co-authored-by: Mason Daugherty <github@mdrxy.com>
Co-authored-by: Mason Daugherty <mason@langchain.dev>
With this we get the correct types for `_runnable_support` annotated
functions.
* return list[BaseMessage] when messages is not None
* return Runnable when messages is None
* typing of function args
# PR Title: fix(core): prevent async task garbage collection (RUF006)
## Description
This PR addresses a cryptic issue (flagged by Ruff rule RUF006) where
`asyncio` tasks created via `loop.create_task` could be garbage
collected mid-execution because no strong reference was maintained.
In `libs/core/langchain_core/language_models/llms.py`, the retry
decorator's `_before_sleep` hook creates a fire-and-forget task for
logging/callbacks. If the garbage collector runs before this task
completes, the task may be destroyed, leading to silent failures.
## Changes
- Introduced a module-level set `_background_tasks` to hold strong
references to running tasks.
- Updated `_before_sleep` to add new tasks to this set.
- Added a `done_callback` to remove the task from the set upon
completion, preventing memory leaks.
## Verification
- Verified logic with a standalone script to ensure tasks are
added/removed from the set correctly.
- This is a standard pattern recommended in the Python `asyncio`
documentation.
## Checklist
- [x] I have read the contributing guidelines.
- [x] I have run tests locally (logic verification).
---------
Co-authored-by: Mason Daugherty <mason@langchain.dev>
Co-authored-by: Mason Daugherty <github@mdrxy.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
This PR changes how we find the cutoff for summarization, summarizing
content more eagerly if the initial cutoff point isn't safe (ie, would
break apart AI + tool message pairs)
This new algorithm is quite simple - it looks at the initial cutoff
point, if it's not safe, moves forward through the message list until it
finds the first non tool message.
For example:
```
H
AI
TM
--- theoretical cutoff based keep=('messages', 3)
TM
AI
TM
```
```
H
AI
TM
TM
--- actual cutoff, more aggressive summarization
AI
TM
```
