To make migration easier, things are more backwards compat
Very minimal footprint here
Will need to upgrade migration guide and other docs w/ this change
Adds `ToolRetryMiddleware` to automatically retry failed tool calls with
configurable exponential backoff, exception filtering, and error
handling.
## Example
```python
from langchain.agents import create_agent
from langchain.agents.middleware import ToolRetryMiddleware
from langchain_openai import ChatOpenAI
# Retry up to 3 times with exponential backoff
retry = ToolRetryMiddleware(
max_retries=3,
initial_delay=1.0,
backoff_factor=2.0,
)
agent = create_agent(
model=ChatOpenAI(model="gpt-4"),
tools=[search_tool, database_tool],
middleware=[retry],
)
# Tool failures are automatically retried
result = agent.invoke({"messages": [{"role": "user", "content": "Search for AI news"}]})
```
For advanced usage with specific exception handling:
```python
from requests.exceptions import Timeout, HTTPError
def should_retry(exc: Exception) -> bool:
# Only retry on 5xx errors or timeouts
if isinstance(exc, HTTPError):
return 500 <= exc.response.status_code < 600
return isinstance(exc, Timeout)
retry = ToolRetryMiddleware(
max_retries=4,
retry_on=should_retry,
tools=["search_database"], # Only apply to specific tools
)
```
Largely:
- Remove explicit `"Default is x"` since new refs show default inferred
from sig
- Inline code (useful for eventual parsing)
- Fix code block rendering (indentations)
The one risk point that I can see here is that model + tool call
counting now occurs in the `after_model` hook which introduces order
dependency (what if you have HITL execute before this hook and we jump
early to `model`, for example).
This is something users can work around at the moment and we can
document. We could also introduce a priority concept to middleware.
## 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>
Bumps [astral-sh/setup-uv](https://github.com/astral-sh/setup-uv) from 6
to 7.
<details>
<summary>Release notes</summary>
<p><em>Sourced from <a
href="https://github.com/astral-sh/setup-uv/releases">astral-sh/setup-uv's
releases</a>.</em></p>
<blockquote>
<h2>v7.0.0 🌈 node24 and a lot of bugfixes</h2>
<h2>Changes</h2>
<p>This release comes with a load of bug fixes and a speed up. Because
of switching from node20 to node24 it is also a breaking change. If you
are running on GitHub hosted runners this will just work, if you are
using self-hosted runners make sure, that your runners are up to date.
If you followed the normal installation instructions your self-hosted
runner will keep itself updated.</p>
<p>This release also removes the deprecated input
<code>server-url</code> which was used to download uv releases from a
different server.
The <a
href="https://github.com/astral-sh/setup-uv?tab=readme-ov-file#manifest-file">manifest-file</a>
input supersedes that functionality by adding a flexible way to define
available versions and where they should be downloaded from.</p>
<h3>Fixes</h3>
<ul>
<li>The action now respects when the environment variable
<code>UV_CACHE_DIR</code> is already set and does not overwrite it. It
now also finds <a
href="https://docs.astral.sh/uv/reference/settings/#cache-dir">cache-dir</a>
settings in config files if you set them.</li>
<li>Some users encountered problems that <a
href="https://github.com/astral-sh/setup-uv?tab=readme-ov-file#disable-cache-pruning">cache
pruning</a> took forever because they had some <code>uv</code> processes
running in the background. Starting with uv version <code>0.8.24</code>
this action uses <code>uv cache prune --ci --force</code> to ignore the
running processes</li>
<li>If you just want to install uv but not have it available in path,
this action now respects <code>UV_NO_MODIFY_PATH</code></li>
<li>Some other actions also set the env var <code>UV_CACHE_DIR</code>.
This action can now deal with that but as this could lead to unwanted
behavior in some edgecases a warning is now displayed.</li>
</ul>
<h3>Improvements</h3>
<p>If you are using minimum version specifiers for the version of uv to
install for example</p>
<pre lang="toml"><code>[tool.uv]
required-version = ">=0.8.17"
</code></pre>
<p>This action now detects that and directly uses the latest version.
Previously it would download all available releases from the uv repo
to determine the highest matching candidate for the version specifier,
which took much more time.</p>
<p>If you are using other specifiers like <code>0.8.x</code> this action
still needs to download all available releases because the specifier
defines an upper bound (not 0.9.0 or later) and "latest" would
possibly not satisfy that.</p>
<h2>🚨 Breaking changes</h2>
<ul>
<li>Use node24 instead of node20 <a
href="https://github.com/eifinger"><code>@eifinger</code></a> (<a
href="https://redirect.github.com/astral-sh/setup-uv/issues/608">#608</a>)</li>
<li>Remove deprecated input server-url <a
href="https://github.com/eifinger"><code>@eifinger</code></a> (<a
href="https://redirect.github.com/astral-sh/setup-uv/issues/607">#607</a>)</li>
</ul>
<h2>🐛 Bug fixes</h2>
<ul>
<li>Respect UV_CACHE_DIR and cache-dir <a
href="https://github.com/eifinger"><code>@eifinger</code></a> (<a
href="https://redirect.github.com/astral-sh/setup-uv/issues/612">#612</a>)</li>
<li>Use --force when pruning cache <a
href="https://github.com/eifinger"><code>@eifinger</code></a> (<a
href="https://redirect.github.com/astral-sh/setup-uv/issues/611">#611</a>)</li>
<li>Respect UV_NO_MODIFY_PATH <a
href="https://github.com/eifinger"><code>@eifinger</code></a> (<a
href="https://redirect.github.com/astral-sh/setup-uv/issues/603">#603</a>)</li>
<li>Warn when <code>UV_CACHE_DIR</code> has changed <a
href="https://github.com/jamesbraza"><code>@jamesbraza</code></a> (<a
href="https://redirect.github.com/astral-sh/setup-uv/issues/601">#601</a>)</li>
</ul>
<h2>🚀 Enhancements</h2>
<ul>
<li>Shortcut to latest version for minimum version specifier <a
href="https://github.com/eifinger"><code>@eifinger</code></a> (<a
href="https://redirect.github.com/astral-sh/setup-uv/issues/598">#598</a>)</li>
</ul>
<h2>🧰 Maintenance</h2>
<ul>
<li>Bump dependencies <a
href="https://github.com/eifinger"><code>@eifinger</code></a> (<a
href="https://redirect.github.com/astral-sh/setup-uv/issues/613">#613</a>)</li>
<li>Fix test-uv-no-modify-path <a
href="https://github.com/eifinger"><code>@eifinger</code></a> (<a
href="https://redirect.github.com/astral-sh/setup-uv/issues/604">#604</a>)</li>
</ul>
<!-- raw HTML omitted -->
</blockquote>
<p>... (truncated)</p>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="3259c6206f"><code>3259c62</code></a>
Bump deps (<a
href="https://redirect.github.com/astral-sh/setup-uv/issues/633">#633</a>)</li>
<li><a
href="bf8e8ed895"><code>bf8e8ed</code></a>
Split up documentation (<a
href="https://redirect.github.com/astral-sh/setup-uv/issues/632">#632</a>)</li>
<li><a
href="9c6b5e9fb5"><code>9c6b5e9</code></a>
Add resolution-strategy input to support oldest compatible version
selection ...</li>
<li><a
href="a5129e99f4"><code>a5129e9</code></a>
Add copilot-instructions.md (<a
href="https://redirect.github.com/astral-sh/setup-uv/issues/630">#630</a>)</li>
<li><a
href="d18bcc753a"><code>d18bcc7</code></a>
Add value of UV_PYTHON_INSTALL_DIR to path (<a
href="https://redirect.github.com/astral-sh/setup-uv/issues/628">#628</a>)</li>
<li><a
href="bd1f875aba"><code>bd1f875</code></a>
Set output venv when activate-environment is used (<a
href="https://redirect.github.com/astral-sh/setup-uv/issues/627">#627</a>)</li>
<li><a
href="1a91c3851d"><code>1a91c38</code></a>
chore: update known checksums for 0.9.2 (<a
href="https://redirect.github.com/astral-sh/setup-uv/issues/626">#626</a>)</li>
<li><a
href="c79f606987"><code>c79f606</code></a>
chore: update known checksums for 0.9.1 (<a
href="https://redirect.github.com/astral-sh/setup-uv/issues/625">#625</a>)</li>
<li><a
href="e0249f1599"><code>e0249f1</code></a>
Fall back to PR for updating known versions (<a
href="https://redirect.github.com/astral-sh/setup-uv/issues/623">#623</a>)</li>
<li><a
href="6d2eb15b49"><code>6d2eb15</code></a>
Cache python installs (<a
href="https://redirect.github.com/astral-sh/setup-uv/issues/621">#621</a>)</li>
<li>Additional commits viewable in <a
href="https://github.com/astral-sh/setup-uv/compare/v6...v7">compare
view</a></li>
</ul>
</details>
<br />
[](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)
Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.
[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)
---
<details>
<summary>Dependabot commands and options</summary>
<br />
You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after
your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge
and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating
it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)
</details>
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
