letta-client 1.0.0a6__tar.gz → 1.0.0a7__tar.gz

letta_client-1.0.0a7/.release-please-manifest.json

@@ -0,0 +1,3 @@
+{
+  ".": "1.0.0-alpha.7"
+}

letta_client-1.0.0a7/CHANGELOG.md

@@ -0,0 +1,52 @@
+# Changelog
+
+## 1.0.0-alpha.7 (2025-10-24)
+
+Full Changelog: [v1.0.0-alpha.6...v1.0.0-alpha.7](https://github.com/letta-ai/letta-python/compare/v1.0.0-alpha.6...v1.0.0-alpha.7)
+
+### Features
+
+* add agent template route to config ([8eeda3f](https://github.com/letta-ai/letta-python/commit/8eeda3f8e946eced4fe1a0dfb7798d748aabb8fc))
+* add new archive routes to sdk ([2b0a253](https://github.com/letta-ai/letta-python/commit/2b0a2536cd5c14d5dcf2770c79aabcab426642c4))
+* add openai-style include param for agents relationship loading ([acb797b](https://github.com/letta-ai/letta-python/commit/acb797bb966dc05ca59fef4fcec3b2b2bed83580))
+* deprecate append copy suffix, add override name [LET-5779] ([1b51b08](https://github.com/letta-ai/letta-python/commit/1b51b082a92e9183789e0fabe3838b4e75312a28))
+* fix patch approvals endpoint incorrectly using queyr params ([d6a4fe6](https://github.com/letta-ai/letta-python/commit/d6a4fe6a48cd93d891cc635f356f85a1ff199a4a))
+* remove run tool for external sdk ([3c1b717](https://github.com/letta-ai/letta-python/commit/3c1b71780b5baecda6e246f8c1d034d62adcecc2))
+* remove unused max length parameter ([85b5f00](https://github.com/letta-ai/letta-python/commit/85b5f00fcbb7d825dfdc7065f867600b718863b7))
+* rename multi agent group to managed group ([733e959](https://github.com/letta-ai/letta-python/commit/733e959a5951d080a5c7318c5a98d724c18d86ef))
+* replace agent.identity_ids with agent.identities ([900384e](https://github.com/letta-ai/letta-python/commit/900384e2d4a73a9a2dae9076182e19902daa77b7))
+* reset message incorrectly using query param ([06229f4](https://github.com/letta-ai/letta-python/commit/06229f43eaaffdf5a2b355e28f550abc7540c65f))
+* Revert "feat: revise mcp tool routes [LET-4321]" ([a77127e](https://github.com/letta-ai/letta-python/commit/a77127eb90b3e79264cf7cd6b12a70859393c9d7))
+* Support embedding config on the archive [LET-5832] ([ccfc935](https://github.com/letta-ai/letta-python/commit/ccfc935d425c24a782bdda272a39defd012b9bfa))
+
+
+### Bug Fixes
+
+* sdk config code gen ([6074e64](https://github.com/letta-ai/letta-python/commit/6074e6480ad03e057639b40f983029ae01d9f7d1))
+
+
+### Chores
+
+* add context_window_limit and max_tokens to UpdateAgent [LET-3743] [LET-3741] ([a841c73](https://github.com/letta-ai/letta-python/commit/a841c7333841aa79a70b805b9373b88429db1922))
+
+## 1.0.0-alpha.6 (2025-10-22)
+
+Full Changelog: [v0.0.1...v1.0.0-alpha.6](https://github.com/letta-ai/letta-python/compare/v0.0.1...v1.0.0-alpha.6)
+
+### Features
+
+* add new tool fields to helpers ([#23](https://github.com/letta-ai/letta-python/issues/23)) ([e51d3a7](https://github.com/letta-ai/letta-python/commit/e51d3a7078e82e30b8e0da89c4e60260f61a6fc4))
+* add pip requirements to create/upsert_from_func ([#20](https://github.com/letta-ai/letta-python/issues/20)) ([190c493](https://github.com/letta-ai/letta-python/commit/190c493b8a7844ead8cfdec1c986c48723c65d05))
+
+
+### Bug Fixes
+
+* make tools client async ([#16](https://github.com/letta-ai/letta-python/issues/16)) ([c88e8dd](https://github.com/letta-ai/letta-python/commit/c88e8ddc175d6c1d7d872908907d701b936173aa))
+
+
+### Chores
+
+* sync repo ([e59730b](https://github.com/letta-ai/letta-python/commit/e59730bb7e0cff18c984f692250e4d0d5f1985eb))
+* update poetry download step in workflow ([#22](https://github.com/letta-ai/letta-python/issues/22)) ([dfa262a](https://github.com/letta-ai/letta-python/commit/dfa262aa4fec42ade045e9a41ffb62b37986bab9))
+* update SDK settings ([4763bfe](https://github.com/letta-ai/letta-python/commit/4763bfe2245828c3ec8b09427a7d0893ab10dc85))
+* update SDK settings ([b54a23a](https://github.com/letta-ai/letta-python/commit/b54a23a21356915fa530c6e29494aa2964741762))

{letta_client-1.0.0a6 → letta_client-1.0.0a7}/CONTRIBUTING.md

@@ -36,7 +36,7 @@ $ pip install -r requirements-dev.lock
 
 Most of the SDK is generated code. Modifications to code will be persisted between generations, but may
 result in merge conflicts between manual patches and changes from the generator. The generator will never
-modify the contents of the `src/letta_sdk/lib/` and `examples/` directories.
+modify the contents of the `src/letta_client/lib/` and `examples/` directories.
 
 ## Adding and running examples
 

{letta_client-1.0.0a6 → letta_client-1.0.0a7}/LICENSE

@@ -186,7 +186,7 @@
       same "printed page" as the copyright notice for easier
       identification within third-party archives.
 
-   Copyright 2025 Letta SDK
+   Copyright 2025 Letta
 
    Licensed under the Apache License, Version 2.0 (the "License");
    you may not use this file except in compliance with the License.

{letta_client-1.0.0a6 → letta_client-1.0.0a7}/PKG-INFO

@@ -1,10 +1,10 @@
 Metadata-Version: 2.3
 Name: letta-client
-Version: 1.0.0a6
-Summary: The official Python library for the letta-sdk API
+Version: 1.0.0a7
+Summary: The official Python library for the letta API
 Project-URL: Homepage, https://github.com/letta-ai/letta-python
 Project-URL: Repository, https://github.com/letta-ai/letta-python
-Author: Letta SDK
+Author: Letta
 License: Apache-2.0
 Classifier: Intended Audience :: Developers
 Classifier: License :: OSI Approved :: Apache Software License
@@ -33,12 +33,12 @@ Requires-Dist: aiohttp; extra == 'aiohttp'
 Requires-Dist: httpx-aiohttp>=0.1.9; extra == 'aiohttp'
 Description-Content-Type: text/markdown
 
-# Letta SDK Python API library
+# Letta Python API library
 
 <!-- prettier-ignore -->
 [![PyPI version](https://img.shields.io/pypi/v/letta-client.svg?label=pypi%20(stable))](https://pypi.org/project/letta-client/)
 
-The Letta SDK Python library provides convenient access to the Letta SDK REST API from any Python 3.8+
+The Letta Python library provides convenient access to the Letta REST API from any Python 3.8+
 application. The library includes type definitions for all request params and response fields,
 and offers both synchronous and asynchronous clients powered by [httpx](https://github.com/encode/httpx).
 
@@ -61,15 +61,20 @@ The full API of this library can be found in [api.md](https://github.com/letta-a
 
 ```python
 import os
-from letta_sdk import LettaSDK
+from letta_client import Letta
 
-client = LettaSDK(
-    api_key=os.environ.get("LETTA_SDK_API_KEY"),  # This is the default and can be omitted
-    # defaults to "production".
-    environment="environment_1",
+client = Letta(
+    api_key=os.environ.get("LETTA_API_KEY"),  # This is the default and can be omitted
+    # defaults to "cloud".
+    environment="local",
 )
 
-archive = client.archives.update(
+archive = client.archives.create(
+    embedding_config={
+        "embedding_dim": 0,
+        "embedding_endpoint_type": "openai",
+        "embedding_model": "embedding_model",
+    },
     name="name",
 )
 print(archive.id)
@@ -77,27 +82,32 @@ print(archive.id)
 
 While you can provide an `api_key` keyword argument,
 we recommend using [python-dotenv](https://pypi.org/project/python-dotenv/)
-to add `LETTA_SDK_API_KEY="My API Key"` to your `.env` file
+to add `LETTA_API_KEY="My API Key"` to your `.env` file
 so that your API Key is not stored in source control.
 
 ## Async usage
 
-Simply import `AsyncLettaSDK` instead of `LettaSDK` and use `await` with each API call:
+Simply import `AsyncLetta` instead of `Letta` and use `await` with each API call:
 
 ```python
 import os
 import asyncio
-from letta_sdk import AsyncLettaSDK
+from letta_client import AsyncLetta
 
-client = AsyncLettaSDK(
-    api_key=os.environ.get("LETTA_SDK_API_KEY"),  # This is the default and can be omitted
-    # defaults to "production".
-    environment="environment_1",
+client = AsyncLetta(
+    api_key=os.environ.get("LETTA_API_KEY"),  # This is the default and can be omitted
+    # defaults to "cloud".
+    environment="local",
 )
 
 
 async def main() -> None:
-    archive = await client.archives.update(
+    archive = await client.archives.create(
+        embedding_config={
+            "embedding_dim": 0,
+            "embedding_endpoint_type": "openai",
+            "embedding_model": "embedding_model",
+        },
         name="name",
     )
     print(archive.id)
@@ -123,16 +133,21 @@ Then you can enable it by instantiating the client with `http_client=DefaultAioH
 
 ```python
 import asyncio
-from letta_sdk import DefaultAioHttpClient
-from letta_sdk import AsyncLettaSDK
+from letta_client import DefaultAioHttpClient
+from letta_client import AsyncLetta
 
 
 async def main() -> None:
-    async with AsyncLettaSDK(
+    async with AsyncLetta(
         api_key="My API Key",
         http_client=DefaultAioHttpClient(),
     ) as client:
-        archive = await client.archives.update(
+        archive = await client.archives.create(
+            embedding_config={
+                "embedding_dim": 0,
+                "embedding_endpoint_type": "openai",
+                "embedding_model": "embedding_model",
+            },
             name="name",
         )
         print(archive.id)
@@ -155,19 +170,19 @@ Typed requests and responses provide autocomplete and documentation within your
 Nested parameters are dictionaries, typed using `TypedDict`, for example:
 
 ```python
-from letta_sdk import LettaSDK
+from letta_client import Letta
 
-client = LettaSDK()
+client = Letta()
 
-server = client.tools.mcp.servers.update(
-    mcp_server_name="mcp_server_name",
-    stdio_config={
-        "args": ["string"],
-        "command": "command",
-        "server_name": "server_name",
+archive = client.archives.create(
+    embedding_config={
+        "embedding_dim": 0,
+        "embedding_endpoint_type": "openai",
+        "embedding_model": "embedding_model",
     },
+    name="name",
 )
-print(server.stdio_config)
+print(archive.embedding_config)
 ```
 
 ## File uploads
@@ -176,12 +191,12 @@ Request parameters that correspond to file uploads can be passed as `bytes`, or
 
 ```python
 from pathlib import Path
-from letta_sdk import LettaSDK
+from letta_client import Letta
 
-client = LettaSDK()
+client = Letta()
 
-client.sources.upload_file(
-    source_id="source_id",
+client.folders.files.upload(
+    folder_id="source-123e4567-e89b-42d3-8456-426614174000",
     file=Path("/path/to/file"),
 )
 ```
@@ -190,29 +205,34 @@ The async client uses the exact same interface. If you pass a [`PathLike`](https
 
 ## Handling errors
 
-When the library is unable to connect to the API (for example, due to network connection problems or a timeout), a subclass of `letta_sdk.APIConnectionError` is raised.
+When the library is unable to connect to the API (for example, due to network connection problems or a timeout), a subclass of `letta_client.APIConnectionError` is raised.
 
 When the API returns a non-success status code (that is, 4xx or 5xx
-response), a subclass of `letta_sdk.APIStatusError` is raised, containing `status_code` and `response` properties.
+response), a subclass of `letta_client.APIStatusError` is raised, containing `status_code` and `response` properties.
 
-All errors inherit from `letta_sdk.APIError`.
+All errors inherit from `letta_client.APIError`.
 
 ```python
-import letta_sdk
-from letta_sdk import LettaSDK
+import letta_client
+from letta_client import Letta
 
-client = LettaSDK()
+client = Letta()
 
 try:
-    client.archives.update(
+    client.archives.create(
+        embedding_config={
+            "embedding_dim": 0,
+            "embedding_endpoint_type": "openai",
+            "embedding_model": "embedding_model",
+        },
         name="name",
     )
-except letta_sdk.APIConnectionError as e:
+except letta_client.APIConnectionError as e:
     print("The server could not be reached")
     print(e.__cause__)  # an underlying Exception, likely raised within httpx.
-except letta_sdk.RateLimitError as e:
+except letta_client.RateLimitError as e:
     print("A 429 status code was received; we should back off a bit.")
-except letta_sdk.APIStatusError as e:
+except letta_client.APIStatusError as e:
     print("Another non-200-range status code was received")
     print(e.status_code)
     print(e.response)
@@ -240,16 +260,21 @@ Connection errors (for example, due to a network connectivity problem), 408 Requ
 You can use the `max_retries` option to configure or disable retry settings:
 
 ```python
-from letta_sdk import LettaSDK
+from letta_client import Letta
 
 # Configure the default for all requests:
-client = LettaSDK(
+client = Letta(
     # default is 2
     max_retries=0,
 )
 
 # Or, configure per-request:
-client.with_options(max_retries=5).archives.update(
+client.with_options(max_retries=5).archives.create(
+    embedding_config={
+        "embedding_dim": 0,
+        "embedding_endpoint_type": "openai",
+        "embedding_model": "embedding_model",
+    },
     name="name",
 )
 ```
@@ -260,21 +285,26 @@ By default requests time out after 1 minute. You can configure this with a `time
 which accepts a float or an [`httpx.Timeout`](https://www.python-httpx.org/advanced/timeouts/#fine-tuning-the-configuration) object:
 
 ```python
-from letta_sdk import LettaSDK
+from letta_client import Letta
 
 # Configure the default for all requests:
-client = LettaSDK(
+client = Letta(
     # 20 seconds (default is 1 minute)
     timeout=20.0,
 )
 
 # More granular control:
-client = LettaSDK(
+client = Letta(
     timeout=httpx.Timeout(60.0, read=5.0, write=10.0, connect=2.0),
 )
 
 # Override per-request:
-client.with_options(timeout=5.0).archives.update(
+client.with_options(timeout=5.0).archives.create(
+    embedding_config={
+        "embedding_dim": 0,
+        "embedding_endpoint_type": "openai",
+        "embedding_model": "embedding_model",
+    },
     name="name",
 )
 ```
@@ -289,10 +319,10 @@ Note that requests that time out are [retried twice by default](https://github.c
 
 We use the standard library [`logging`](https://docs.python.org/3/library/logging.html) module.
 
-You can enable logging by setting the environment variable `LETTA_SDK_LOG` to `info`.
+You can enable logging by setting the environment variable `LETTA_LOG` to `info`.
 
 ```shell
-$ export LETTA_SDK_LOG=info
+$ export LETTA_LOG=info
 ```
 
 Or to `debug` for more verbose logging.
@@ -314,21 +344,26 @@ if response.my_field is None:
 The "raw" Response object can be accessed by prefixing `.with_raw_response.` to any HTTP method call, e.g.,
 
 ```py
-from letta_sdk import LettaSDK
-
-client = LettaSDK()
-response = client.archives.with_raw_response.update(
+from letta_client import Letta
+
+client = Letta()
+response = client.archives.with_raw_response.create(
+    embedding_config={
+        "embedding_dim": 0,
+        "embedding_endpoint_type": "openai",
+        "embedding_model": "embedding_model",
+    },
     name="name",
 )
 print(response.headers.get('X-My-Header'))
 
-archive = response.parse()  # get the object that `archives.update()` would have returned
+archive = response.parse()  # get the object that `archives.create()` would have returned
 print(archive.id)
 ```
 
-These methods return an [`APIResponse`](https://github.com/letta-ai/letta-python/tree/1.0-release/src/letta_sdk/_response.py) object.
+These methods return an [`APIResponse`](https://github.com/letta-ai/letta-python/tree/1.0-release/src/letta_client/_response.py) object.
 
-The async client returns an [`AsyncAPIResponse`](https://github.com/letta-ai/letta-python/tree/1.0-release/src/letta_sdk/_response.py) with the same structure, the only difference being `await`able methods for reading the response content.
+The async client returns an [`AsyncAPIResponse`](https://github.com/letta-ai/letta-python/tree/1.0-release/src/letta_client/_response.py) with the same structure, the only difference being `await`able methods for reading the response content.
 
 #### `.with_streaming_response`
 
@@ -337,7 +372,12 @@ The above interface eagerly reads the full response body when you make the reque
 To stream the response body, use `.with_streaming_response` instead, which requires a context manager and only reads the response body once you call `.read()`, `.text()`, `.json()`, `.iter_bytes()`, `.iter_text()`, `.iter_lines()` or `.parse()`. In the async client, these are async methods.
 
 ```python
-with client.archives.with_streaming_response.update(
+with client.archives.with_streaming_response.create(
+    embedding_config={
+        "embedding_dim": 0,
+        "embedding_endpoint_type": "openai",
+        "embedding_model": "embedding_model",
+    },
     name="name",
 ) as response:
     print(response.headers.get("X-My-Header"))
@@ -392,10 +432,10 @@ You can directly override the [httpx client](https://www.python-httpx.org/api/#c
 
 ```python
 import httpx
-from letta_sdk import LettaSDK, DefaultHttpxClient
+from letta_client import Letta, DefaultHttpxClient
 
-client = LettaSDK(
-    # Or use the `LETTA_SDK_BASE_URL` env var
+client = Letta(
+    # Or use the `LETTA_BASE_URL` env var
     base_url="http://my.test.server.example.com:8083",
     http_client=DefaultHttpxClient(
         proxy="http://my.test.proxy.example.com",
@@ -415,9 +455,9 @@ client.with_options(http_client=DefaultHttpxClient(...))
 By default the library closes underlying HTTP connections whenever the client is [garbage collected](https://docs.python.org/3/reference/datamodel.html#object.__del__). You can manually close the client using the `.close()` method if desired, or with a context manager that closes when exiting.
 
 ```py
-from letta_sdk import LettaSDK
+from letta_client import Letta
 
-with LettaSDK() as client:
+with Letta() as client:
   # make requests here
   ...
 
@@ -443,8 +483,8 @@ If you've upgraded to the latest version but aren't seeing any new features you
 You can determine the version that is being used at runtime with:
 
 ```py
-import letta_sdk
-print(letta_sdk.__version__)
+import letta_client
+print(letta_client.__version__)
 ```
 
 ## Requirements