* Create usage metadata on
[`message_delta`](https://docs.anthropic.com/en/docs/build-with-claude/streaming#event-types)
instead of at the beginning. Consequently, token counts are not included
during streaming but instead at the end. This allows for accurate
reporting of server-side tool usage (important for billing)
* Add some clarifying comments
* Fix some outstanding Pylance warnings
* Remove unnecessary `text` popping in thinking blocks
* Also now correctly reports `input_cache_read`/`input_cache_creation`
as a result
Supersedes #32461
Fixed incorrect input token reporting during streaming when tools are
used. Previously, input tokens were counted at `message_start` before
tool execution, leading to inaccurate counts. Now input tokens are
properly deferred until `message_delta` (completion), aligning with
Anthropic's billing model and SDK expectations.
**Before Fix:**
- Streaming with tools: Input tokens = 0 ❌
- Non-streaming with tools: Input tokens = 472 ✅
**After Fix:**
- Streaming with tools: Input tokens = 472 ✅
- Non-streaming with tools: Input tokens = 472 ✅
Aligns with Anthropic's SDK expectations. The SDK handles input token
updates in `message_delta` events:
```python
# https://github.com/anthropics/anthropic-sdk-python/blob/main/src/anthropic/lib/streaming/_messages.py
if event.usage.input_tokens is not None:
current_snapshot.usage.input_tokens = event.usage.input_tokens
```
Thank you for contributing to LangChain! Follow these steps to mark your
pull request as ready for review. **If any of these steps are not
completed, your PR will not be considered for review.**
- [x] **PR title**: Follows the format: {TYPE}({SCOPE}): {DESCRIPTION}
- [x] **PR message**: ***Delete this entire checklist*** and replace
with
fix#30146
- [x] **Add tests and docs**: If you're adding a new integration, you
must include:
- [x] **Lint and test**: Run `make format`, `make lint` and `make test`
from the root of the package(s) you've modified. **We will not consider
a PR unless these three are passing in CI.** See [contribution
guidelines](https://python.langchain.com/docs/contributing/) for more.
Additional guidelines:
- Make sure optional dependencies are imported within a function.
- Please do not add dependencies to `pyproject.toml` files (even
optional ones) unless they are **required** for unit tests.
- Most PRs should not touch more than one package.
- Changes should be backwards compatible.
---------
Co-authored-by: Mason Daugherty <mason@langchain.dev>
Co-authored-by: Mason Daugherty <github@mdrxy.com>
```python
from langchain_anthropic import ChatAnthropic
llm = ChatAnthropic(model="claude-3-5-haiku-latest")
caching_llm = llm.bind(cache_control={"type": "ephemeral"})
caching_llm.invoke(
[
HumanMessage("..."),
AIMessage("..."),
HumanMessage("..."), # <-- final message / content block gets cache annotation
]
)
```
Potentially useful given's Anthropic's [incremental
caching](https://docs.anthropic.com/en/docs/build-with-claude/prompt-caching#continuing-a-multi-turn-conversation)
capabilities:
> During each turn, we mark the final block of the final message with
cache_control so the conversation can be incrementally cached. The
system will automatically lookup and use the longest previously cached
prefix for follow-up messages.
---------
Co-authored-by: Mason Daugherty <mason@langchain.dev>
Co-authored-by: Mason Daugherty <github@mdrxy.com>
Multiple models were
[retired](https://docs.anthropic.com/en/docs/about-claude/model-deprecations#model-status)
yesterday.
Tests remain broken until we figure out what to do with the legacy
Anthropic LLM integration— currently uses their (legacy) text
completions API, for which there appear to be no remaining supported
models.
Anthropic updated how they report token counts during streaming today.
See changes to `MessageDeltaUsage` in [this
commit](2da00f26c5 (diff-1a396eba0cd9cd8952dcdb58049d3b13f6b7768ead1411888d66e28211f7bfc5)).
It's clean and simple to grab these fields from the final
`message_delta` event. However, some of them are typed as Optional, and
language
[here](e42451ab3f/src/anthropic/lib/streaming/_messages.py (L462))
suggests they may not always be present. So here we take the required
field from the `message_delta` event as we were doing previously, and
ignore the rest.
- **Description:** `ChatAnthropic.get_num_tokens_from_messages` does not
currently receive `kwargs` and pass those on to
`self._client.beta.messages.count_tokens`. This is a problem if you need
to pass specific options to `count_tokens`, such as the `thinking`
option. This PR fixes that.
- **Issue:** N/A
- **Dependencies:** None
- **Twitter handle:** @bengladwell
Co-authored-by: ccurme <chester.curme@gmail.com>
PR Summary
This change adds a fallback in ChatAnthropic.with_structured_output() to
handle Pydantic models that don’t include a docstring. Without it,
calling:
```py
from pydantic import BaseModel
from langchain_anthropic import ChatAnthropic
class SampleModel(BaseModel):
sample_field: str
llm = ChatAnthropic(
model="claude-3-7-sonnet-latest"
).with_structured_output(SampleModel.model_json_schema())
llm.invoke("test")
```
will raise a
```
KeyError: 'description'
```
because Pydantic omits the description field when no docstring is
present.
This issue doesn’t occur when using ChatOpenAI or if you add a docstring
to the model:
```py
from pydantic import BaseModel
from langchain_openai import ChatOpenAI
class SampleModel(BaseModel):
"""Schema for sample_field output."""
sample_field: str
llm = ChatOpenAI(
model="gpt-4o-mini"
).with_structured_output(SampleModel.model_json_schema())
llm.invoke("test")
```
---------
Co-authored-by: Chester Curme <chester.curme@gmail.com>
**Description:**
partners-anthropic: ChatAnthropic supports b64 and urls in the
part[image_url][url] message variable
**Issue**:
ChatAnthropic right now only supports b64 encoded images in the
part[image_url][url] message variable. This PR enables ChatAnthropic to
also accept image urls in said variable and makes it compatible with
OpenAI messages to make model switching easier.
---------
Co-authored-by: Chester Curme <chester.curme@gmail.com>
- Support features from recent update:
https://www.anthropic.com/news/token-saving-updates (mostly adding
support for built-in tools in `bind_tools`
- Add documentation around prompt caching, token-efficient tool use, and
built-in tools.
- Support thinking blocks in core's `convert_to_openai_messages` (pass
through instead of error)
- Ignore thinking blocks in ChatOpenAI (instead of error)
- Support Anthropic-style image blocks in ChatOpenAI
---
Standard integration tests include a `supports_anthropic_inputs`
property which is currently enabled only for tests on `ChatAnthropic`.
This test enforces compatibility with message histories of the form:
```
- system message
- human message
- AI message with tool calls specified only through `tool_use` content blocks
- human message containing `tool_result` and an additional `text` block
```
It additionally checks support for Anthropic-style image inputs if
`supports_image_inputs` is enabled.
Here we change this test, such that if you enable
`supports_anthropic_inputs`:
- You support AI messages with text and `tool_use` content blocks
- You support Anthropic-style image inputs (if `supports_image_inputs`
is enabled)
- You support thinking content blocks.
That is, we add a test case for thinking content blocks, but we also
remove the requirement of handling tool results within HumanMessages
(motivated by existing agent abstractions, which should all return
ToolMessage). We move that requirement to a ChatAnthropic-specific test.
Structured output will currently always raise a BadRequestError when
Claude 3.7 Sonnet's `thinking` is enabled, because we rely on forced
tool use for structured output and this feature is not supported when
`thinking` is enabled.
Here we:
- Emit a warning if `with_structured_output` is called when `thinking`
is enabled.
- Raise `OutputParserException` if no tool calls are generated.
This is arguably preferable to raising an error in all cases.
```python
from langchain_anthropic import ChatAnthropic
from pydantic import BaseModel
class Person(BaseModel):
name: str
age: int
llm = ChatAnthropic(
model="claude-3-7-sonnet-latest",
max_tokens=5_000,
thinking={"type": "enabled", "budget_tokens": 2_000},
)
structured_llm = llm.with_structured_output(Person) # <-- this generates a warning
```
```python
structured_llm.invoke("Alice is 30.") # <-- works
```
```python
structured_llm.invoke("Hello!") # <-- raises OutputParserException
```
Took a "census" of models supported by init_chat_model-- of those that
return model names in response metadata, these were the only two that
had it keyed under `"model"` instead of `"model_name"`.
We currently return string (and therefore no content blocks / citations)
if the response is of the form
```
[
{"text": "a claim", "citations": [...]},
]
```
There are other cases where we do return citations as-is:
```
[
{"text": "a claim", "citations": [...]},
{"text": "some other text"},
{"text": "another claim", "citations": [...]},
]
```
Here we update to return content blocks including citations in the first
case as well.
