github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2026-02-21 14:43:07 +00:00
Code Issues Packages Projects Releases Wiki Activity
14,543 Commits 1,090 Branches 1,169 Tags
d642285c5adc4955562d2ea7c484ba965af158eb
Commit Graph

7823 Commits

Author SHA1 Message Date
Sydney Runkle
d642285c5a removing is_async 2025-10-14 15:49:43 -04:00
Sydney Runkle
086c6cc872 Merge branch 'master' into sr/deepagents 2025-10-14 15:23:07 -04:00
Sydney Runkle
83e7c4ea74 linting, renaming 2025-10-14 15:22:31 -04:00
ccurme
9f4366bc9d feat(mistralai): support reasoning feature and v1 content (#33485) 
Not yet supported: server-side tool calls
 2025-10-14 15:19:44 -04:00
Sydney Runkle
6677d57cdd HITL changes 2025-10-14 15:15:10 -04:00
Sydney Runkle
5e93774258 Merge branch 'master' into sr/deepagents 2025-10-14 15:10:03 -04:00
Eugene Yurtsev
99e0a60aab chore(langchain_v1): remove invocation request (#33482) 
Remove ToolNode primitives from langchain
 2025-10-14 15:07:30 -04:00
Sydney Runkle
93108324df remove anthropic stuff 2025-10-14 15:06:54 -04:00
Sydney Runkle
6eb8377e12 excluded keys 2025-10-14 14:30:03 -04:00
Eugene Yurtsev
d38729fbac feat(langchain_v1): add async implementations to wrap_model_call (#33467) 
Add async implementations to wrap_model_call for prebuilt middleware
 2025-10-14 17:39:38 +00:00
gsmini
ff0d21cfd5 fix(langchain_v1): can not import "wrap_tool_call" from agents.… (#33472) 
fix can not import `wrap_tool_call` from ` langchain.agents.middleware
import `
```python

from langchain.agents import create_agent
from langchain.agents.middleware import wrap_tool_call # here !
from langchain_core.messages import ToolMessage

@wrap_tool_call
def handle_tool_errors(request, handler):
    """Handle tool execution errors with custom messages."""
    try:
        return handler(request)
    except Exception as e:
        # Return a custom error message to the model
        return ToolMessage(
            content=f"Tool error: Please check your input and try again. ({str(e)})",
            tool_call_id=request.tool_call["id"]
        )

agent = create_agent(
    model="openai:gpt-4o",
    tools=[search, calculate],
    middleware=[handle_tool_errors]
)
```
> example code from:
https://docs.langchain.com/oss/python/langchain/agents#tool-error-handling
 2025-10-14 13:39:25 -04:00
Eugene Yurtsev
9140a7cb86 feat(langchain_v1): add override to model request and tool call request (#33465) 
Add override to model request and tool call request
 2025-10-14 10:31:46 -04:00
ccurme
41fe18bc80 chore(groq): fix integration tests (#33478) 
- add missing cassette
- update streaming metadata test for v1
 2025-10-14 14:16:34 +00:00
Mason Daugherty
9105573cb3 docs: create_agent style and clarify system_prompt (#33470) 2025-10-14 09:56:54 -04:00
Sydney Runkle
fff87e95d1 fix(langchain): rename PlanningMiddleware to TodoListMiddleware (#33476) 2025-10-14 09:06:06 -04:00
ccurme
9beb29a34c chore(mistralai): delete redundant tests (#33468) 2025-10-13 21:28:51 +00:00
ChoYongHo | 조용호
ca00f5aed9 fix(langchain_v1): export ModelResponse from agents.middleware (#33453) (#33454) 
## Description

  Fixes #33453

`ModelResponse` was defined in `types.py` and included in its `__all__`
list, but was not exported from the middleware package's `__init__.py`.
This caused `ImportError` when attempting to import it directly
from `langchain.agents.middleware`, despite being documented as a public
export.

  ## Changes

- Added `ModelResponse` to the import statement in
`langchain/agents/middleware/__init__.py`
- Added `ModelResponse` to the `__all__` list in
`langchain/agents/middleware/__init__.py`
- Added comprehensive unit tests in `test_imports.py` to verify the
import works correctly

  ## Issue

  The original issue reported that the following import failed:

  ```python
  from langchain.agents.middleware import ModelResponse
# ImportError: cannot import name 'ModelResponse' from
'langchain.agents.middleware'

  The workaround was to import from the submodule:

from langchain.agents.middleware.types import ModelResponse # Workaround

  Solution

  After this fix, ModelResponse can be imported directly as documented:

  from langchain.agents.middleware import ModelResponse  # Now works!

  Testing

- ✅ Added 3 unit tests in
tests/unit_tests/agents/middleware/test_imports.py
  - ✅ All tests pass locally: make format, make lint, make test
  - ✅ Verified ModelResponse is properly exported and importable
  - ✅ Verified ModelResponse appears in __all__ list

  Dependencies

  None. This is a simple export fix with no new dependencies.

---------

Co-authored-by: Eugene Yurtsev <eugene@langchain.dev>
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
 2025-10-13 16:02:30 -04:00
Eugene Yurtsev
1cf851e054 chore(langchain_v1,anthropic): migrate anthropic middleware to langchain_anthropic (#33463) 
Migrate prompt caching implementation into langchain_anthropic.middleware
 2025-10-13 15:12:54 -04:00
ccurme
961f965f0c feat(groq): support built-in tools in message content (#33459) 2025-10-13 15:06:01 -04:00
Nick Huang
ecbd43b660 Change how namespace is built 2025-10-13 14:45:05 -04:00
Sydney Runkle
760fc3bc12 chore(langchain_v1): use args for HITL (#33442) 2025-10-11 07:12:46 -04:00
Eugene Yurtsev
e3fc7d8aa6 chore(langchain_v1): bump release version (#33440) 
bump v1 for release
 2025-10-10 21:51:00 -04:00
Nick Huang
918e2ee567 Update default model 2025-10-10 17:22:22 -04:00
Eugene Yurtsev
2b3b209e40 chore(langchain_v1): improve error message (#33433) 
Make error messages actionable for sync / async decorators
 2025-10-10 17:18:20 -04:00
ccurme
78903ac285 fix(openai): conditionally skip test (#33431) 2025-10-10 21:04:18 +00:00
ccurme
f361acc11c chore(anthropic): speed up integration tests (#33430) 2025-10-10 20:57:44 +00:00
Eugene Yurtsev
ed185c0026 chore(langchain_v1): remove langchain_text_splitters from test group (#33425) 
Remove langchain_text_splitters from test group in langchain_v1
 2025-10-10 16:56:14 -04:00
Eugene Yurtsev
6dc34beb71 chore(langchain_v1): stricter handling of sync vs. async for wrap_model_call and wrap_tool_call (#33429) 
Wrap model call and wrap tool call
 2025-10-10 16:54:42 -04:00
Eugene Yurtsev
c2205f88e6 chore(langchain_v1): further namespace clean up (#33428) 
Reduce exposed namespace for now
 2025-10-10 20:48:24 +00:00
ccurme
abdbe185c5 release(anthropic): 1.0.0a4 (#33427) 2025-10-10 16:39:58 -04:00
ccurme
c1b816cb7e fix(fireworks): parse standard blocks in input (#33426) 2025-10-10 16:18:37 -04:00
Nick Huang
bcbf2fff5f Fix import in test 2025-10-10 16:05:00 -04:00
Nick Huang
206fa156ac Add dependencies to tests 2025-10-10 16:01:25 -04:00
Nick Huang
1713a149e4 Address comments 2025-10-10 15:45:50 -04:00
Eugene Yurtsev
0559558715 feat(langchain_v1): add async implementation for wrap_tool_call (#33420) 
Add async implementation. No automatic delegation to sync at the moment.
 2025-10-10 15:07:19 -04:00
Eugene Yurtsev
75965474fc chore(langchain_v1): tool error exceptions (#33424) 
Tool error exceptions
 2025-10-10 15:06:40 -04:00
Mason Daugherty
5dc014fdf4 chore(core): delete get_relevant_documents (#33378) 
Co-authored-by: Chester Curme <chester.curme@gmail.com>
 2025-10-10 14:51:54 -04:00
Nick Huang
f682a9e0a4 Fix and simplify filesystem substantially - add integration tests for filesystem 2025-10-10 14:48:38 -04:00
Mason Daugherty
291a9fcea1 style: llm -> model (#33423) 2025-10-10 13:19:13 -04:00
Christophe Bornet
dd994b9d7f chore(langchain): remove arg types from docstrings (#33413) 
Co-authored-by: Mason Daugherty <mason@langchain.dev>
 2025-10-10 11:51:00 -04:00
Christophe Bornet
83901b30e3 chore(text-splitters): remove arg types from docstrings (#33406) 
Co-authored-by: Mason Daugherty <mason@langchain.dev>
 2025-10-10 11:37:53 -04:00
ccurme
af1da28459 feat(langchain_v1): expand message exports (#33419) 2025-10-10 15:14:51 +00:00
Mason Daugherty
ed2ee4e8cc style: fix tables, capitalization (#33417) 2025-10-10 11:09:59 -04:00
Sydney Runkle
f293c8ffd6 chore(langchain_v1): add RemoveMessage (#33416) 2025-10-10 10:49:18 -04:00
Sydney Runkle
714c370191 release(langchain_v1): v1.0.0a13 (#33415) 2025-10-10 10:42:35 -04:00
Sydney Runkle
a29d4e9c3a fix(langchain_v1): out of date docstring (#33414) 2025-10-10 14:12:07 +00:00
Nick Huang
c7a52e8c78 Fix formatting 2025-10-09 23:31:54 -04:00
Eugene Yurtsev
74983f8a96 chore(langchain_v1): update on_tool_call to wrap_tool (#33410) 
Improve naming on ToolNode for on_tool_call interceptor
 2025-10-10 03:19:45 +00:00
Nick Huang
9cab0be047 Update imports 2025-10-09 23:16:06 -04:00
Eugene Yurtsev
11c5b86981 chore(langchain_v1): update wrap_on_model return (#33408) 
Update wrap on model return to capture the full return type of the model
so we can accommodate dynamic structured outputs.
 2025-10-09 23:01:21 -04:00