livekit-plugins-volcenginee 1.3.3__tar.gz → 1.3.5__tar.gz

livekit_plugins_volcenginee-1.3.5/.gitignore

@@ -0,0 +1,7 @@
+.vscode/
+.venv/
+.pytest_cache/
+__pycache__/
+.env
+.env.*
+dist/

{livekit_plugins_volcenginee-1.3.3 → livekit_plugins_volcenginee-1.3.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: livekit-plugins-volcenginee
-Version: 1.3.3
+Version: 1.3.5
 Summary: LiveKit Agent Plugins for Volcengine
 Author-email: linsanzhu <2287225730@qq.com>
 Keywords: audio,livekit,realtime,video,webrtc
@@ -18,6 +18,11 @@ Requires-Dist: numpy
 Requires-Dist: openai>=1.80.0
 Requires-Dist: osc-data~=0.3.1
 Requires-Dist: pydantic
+Provides-Extra: test
+Requires-Dist: aiohttp>=3.9; extra == 'test'
+Requires-Dist: pyaudio>=0.2.14; extra == 'test'
+Requires-Dist: pytest-asyncio>=0.21; extra == 'test'
+Requires-Dist: pytest>=7.0; extra == 'test'
 Description-Content-Type: text/markdown
 
 # livekit-plugins-volcengine

{livekit_plugins_volcenginee-1.3.3 → livekit_plugins_volcenginee-1.3.5}/livekit/plugins/volcengine/llm.py

@@ -21,7 +21,7 @@ from livekit.agents.types import (
 from livekit.agents.utils import is_given
 
 from .log import logger
-from .utils import to_chat_ctx, to_fnc_ctx
+from .utils import to_fnc_ctx
 
 
 @dataclass
@@ -32,7 +32,18 @@ class _LLMOptions:
     parallel_tool_calls: NotGivenOr[bool]
     tool_choice: NotGivenOr[ToolChoice]
     metadata: NotGivenOr[dict[str, str]]
-    thinking: NotGivenOr[Literal["enabled", "disabled", "auto"] | dict[str, Any]]
+    reasoning_effort: NotGivenOr[Literal["minimal", "low", "medium", "high", "max"]]
+
+    def __post_init__(self) -> None:
+        if is_given(self.reasoning_effort):
+            if self.reasoning_effort not in (
+                "minimal", "low", "medium", "high", "max",
+            ):
+                raise ValueError(
+                    f"reasoning_effort must be one of "
+                    f"'minimal', 'low', 'medium', 'high', 'max'; "
+                    f"got {self.reasoning_effort!r}"
+                )
 
 
 class LLM(llm.LLM):
@@ -48,7 +59,9 @@ class LLM(llm.LLM):
         parallel_tool_calls: NotGivenOr[bool] = NOT_GIVEN,
         tool_choice: NotGivenOr[ToolChoice] = NOT_GIVEN,
         metadata: NotGivenOr[dict[str, str]] = NOT_GIVEN,
-        thinking: NotGivenOr[Literal["enabled", "disabled", "auto"] | dict[str, Any]] = NOT_GIVEN,
+        reasoning_effort: NotGivenOr[
+            Literal["minimal", "low", "medium", "high", "max"]
+        ] = NOT_GIVEN,
         timeout: httpx.Timeout | None = None,
     ) -> None:
         """
@@ -58,11 +71,14 @@ class LLM(llm.LLM):
             model: The model to use for the LLM, end
             api_key: The API key to use for the LLM.
             base_url: The base URL to use for the LLM.
-            thinking: Controls deep thinking mode. Pass ``"disabled"`` to turn
-                it off, ``"enabled"`` to force it on, ``"auto"`` to let the
-                model decide, or a raw ``{"type": "..."}`` dict for extended
-                parameters. See the Volcengine Chat Completions API reference
-                for details. Omit to use the API default (``enabled``).
+            reasoning_effort: Constrains the effort the model spends on
+                reasoning before producing a final answer. One of
+                ``"minimal"``, ``"low"``, ``"medium"``, ``"high"``, ``"max"``.
+                Mapped to Volcengine Ark's ``reasoning_effort`` field; also
+                accepted by the OpenAI Python SDK as a standard Chat
+                Completions kwarg (same name, same semantics) so it is
+                forwarded at the top level of the request body. Omit to use
+                the API default (``medium``).
         """
         super().__init__()
         self._opts = _LLMOptions(
@@ -72,7 +88,7 @@ class LLM(llm.LLM):
             parallel_tool_calls=parallel_tool_calls,
             tool_choice=tool_choice,
             metadata=metadata,
-            thinking=thinking,
+            reasoning_effort=reasoning_effort,
         )
         api_key = api_key if is_given(api_key) else os.getenv("VOLCENGINE_LLM_API_KEY")
         if api_key is None:
@@ -118,12 +134,13 @@ class LLM(llm.LLM):
         if is_given(self._opts.temperature):
             extra["temperature"] = self._opts.temperature
 
-        if is_given(self._opts.thinking):
-            extra["thinking"] = (
-                self._opts.thinking
-                if isinstance(self._opts.thinking, dict)
-                else {"type": self._opts.thinking}
-            )
+        if is_given(self._opts.reasoning_effort):
+            # ``reasoning_effort`` is part of the OpenAI Chat Completions
+            # signature (added for the o1 series; the OpenAI Python SDK
+            # accepts it at the top level). Volcengine Ark also accepts the
+            # same field name on its OpenAI-compatible endpoint, so we can
+            # forward it as a normal kwarg without ``extra_body``.
+            extra["reasoning_effort"] = self._opts.reasoning_effort
 
         parallel_tool_calls = (
             parallel_tool_calls
@@ -189,7 +206,7 @@ class LLMStream(llm.LLMStream):
             stream: openai.AsyncStream[
                 ChatCompletionChunk
             ] = await self._client.chat.completions.create(
-                messages=to_chat_ctx(self._chat_ctx, id(self._llm)),
+                messages=self._chat_ctx.to_provider_format(format="openai")[0],
                 tools=to_fnc_ctx(self._tools) if self._tools else openai.NOT_GIVEN,
                 model=self._model,
                 stream_options={"include_usage": True},

{livekit_plugins_volcenginee-1.3.3 → livekit_plugins_volcenginee-1.3.5}/livekit/plugins/volcengine/tts.py

@@ -10,7 +10,7 @@ from collections.abc import ByteString
 from typing import Literal, Tuple
 
 import aiohttp
-from pydantic import BaseModel, Field
+from pydantic import BaseModel, ConfigDict, Field
 from osc_data.text_stream import TextStreamSentencizer
 
 from livekit.agents import (
@@ -46,6 +46,10 @@ def _volume_to_loudness_rate(volume: float) -> int:
 
 
 class _TTSOptions(BaseModel):
+    # Reject unknown fields so the legacy ``speech_rate`` / ``loudness_rate``
+    # kwargs that were removed from the public API surface immediately.
+    model_config = ConfigDict(extra="forbid")
+
     api_key: str
     resource_id: str | None = None
     voice: str = "zh_female_xiaohe_uranus_bigtts"

livekit_plugins_volcenginee-1.3.5/livekit/plugins/volcengine/utils.py

@@ -0,0 +1,25 @@
+from __future__ import annotations
+
+import os
+from collections.abc import Sequence
+from typing import Awaitable, Callable, Union, cast
+
+from livekit.agents import llm
+from openai.types.chat import ChatCompletionToolParam
+
+AsyncAzureADTokenProvider = Callable[[], Union[str, Awaitable[str]]]
+
+
+def get_base_url(base_url: str | None) -> str:
+    if not base_url:
+        base_url = os.getenv(
+            "VOLCENGINE_LLM_BASE_URL", "https://ark.cn-beijing.volces.com/api/v3"
+        )
+    return base_url
+
+
+def to_fnc_ctx(fnc_ctx: Sequence[llm.Tool]) -> list[ChatCompletionToolParam]:
+    return cast(
+        list[ChatCompletionToolParam],
+        llm.ToolContext(fnc_ctx).parse_function_tools("openai"),
+    )

livekit_plugins_volcenginee-1.3.5/livekit/plugins/volcengine/version.py

@@ -0,0 +1 @@
+__version__ = "1.3.5"

{livekit_plugins_volcenginee-1.3.3 → livekit_plugins_volcenginee-1.3.5}/pyproject.toml

@@ -27,6 +27,13 @@ classifiers = [
     "Programming Language :: Python :: 3 :: Only",
 ]
 
+[project.optional-dependencies]
+test = [
+    "pytest>=7.0",
+    "pytest-asyncio>=0.21",
+    "aiohttp>=3.9",
+    "pyaudio>=0.2.14",
+]
 
 
 [build-system]
@@ -41,3 +48,16 @@ packages = ["livekit"]
 
 [tool.hatch.build.targets.sdist]
 include = ["/livekit"]
+
+[tool.pytest.ini_options]
+asyncio_mode = "auto"
+testpaths = ["tests"]
+log_cli = true
+log_cli_level = "INFO"
+log_cli_format = "%(asctime)s [%(levelname)s] %(name)s: %(message)s"
+log_cli_date_format = "%H:%M:%S"
+markers = [
+    "integration: marks tests that require real Volcengine API credentials (skipped automatically when keys are not set in the environment)",
+    "llm: marks LLM integration tests (require VOLCENGINE_LLM_API_KEY)",
+    "tts: marks TTS integration tests (require VOLCENGINE_TTS_API_KEY)",
+]

livekit_plugins_volcenginee-1.3.3/.gitignore

@@ -1,183 +0,0 @@
-# Byte-compiled / optimized / DLL files
-__pycache__/
-*.py[cod]
-*$py.class
-
-# C extensions
-*.so
-
-# Distribution / packaging
-.Python
-build/
-develop-eggs/
-dist/
-downloads/
-eggs/
-.eggs/
-lib/
-lib64/
-parts/
-sdist/
-var/
-wheels/
-share/python-wheels/
-*.egg-info/
-.installed.cfg
-*.egg
-MANIFEST
-
-# PyInstaller
-#  Usually these files are written by a python script from a template
-#  before PyInstaller builds the exe, so as to inject date/other infos into it.
-*.manifest
-*.spec
-
-# Installer logs
-pip-log.txt
-pip-delete-this-directory.txt
-
-# Unit test / coverage reports
-htmlcov/
-.tox/
-.nox/
-.coverage
-.coverage.*
-.cache
-nosetests.xml
-coverage.xml
-*.cover
-*.py,cover
-.hypothesis/
-.pytest_cache/
-cover/
-
-# Translations
-*.mo
-*.pot
-
-# Django stuff:
-*.log
-local_settings.py
-db.sqlite3
-db.sqlite3-journal
-
-# Flask stuff:
-instance/
-.webassets-cache
-
-# Scrapy stuff:
-.scrapy
-
-# Sphinx documentation
-docs/_build/
-
-# PyBuilder
-.pybuilder/
-target/
-
-# Jupyter Notebook
-.ipynb_checkpoints
-
-# IPython
-profile_default/
-ipython_config.py
-
-# pyenv
-#   For a library or package, you might want to ignore these files since the code is
-#   intended to run in multiple environments; otherwise, check them in:
-# .python-version
-
-# pipenv
-#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
-#   However, in case of collaboration, if having platform-specific dependencies or dependencies
-#   having no cross-platform support, pipenv may install dependencies that don't work, or not
-#   install all needed dependencies.
-#Pipfile.lock
-
-# UV
-#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
-#   This is especially recommended for binary packages to ensure reproducibility, and is more
-#   commonly ignored for libraries.
-#uv.lock
-
-# poetry
-#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
-#   This is especially recommended for binary packages to ensure reproducibility, and is more
-#   commonly ignored for libraries.
-#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
-#poetry.lock
-
-# pdm
-#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
-#pdm.lock
-#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
-#   in version control.
-#   https://pdm.fming.dev/latest/usage/project/#working-with-version-control
-.pdm.toml
-.pdm-python
-.pdm-build/
-
-# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
-__pypackages__/
-
-# Celery stuff
-celerybeat-schedule
-celerybeat.pid
-
-# SageMath parsed files
-*.sage.py
-
-# Environments
-.env
-.venv
-env/
-venv/
-ENV/
-env.bak/
-venv.bak/
-
-# Spyder project settings
-.spyderproject
-.spyproject
-
-# Rope project settings
-.ropeproject
-
-# mkdocs documentation
-/site
-
-# mypy
-.mypy_cache/
-.dmypy.json
-dmypy.json
-
-# Pyre type checker
-.pyre/
-
-# pytype static type analyzer
-.pytype/
-
-# Cython debug symbols
-cython_debug/
-
-# PyCharm
-#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
-#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
-#  and can be added to the global gitignore or merged into this file.  For a more nuclear
-#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
-#.idea/
-
-# Ruff stuff:
-.ruff_cache/
-
-# PyPI configuration file
-.pypirc
-
-# tests
-test.py
-
-.python-version
-
-*.ipynb
-config.yaml
-uv.lock

livekit_plugins_volcenginee-1.3.3/livekit/plugins/volcengine/utils.py

@@ -1,154 +0,0 @@
-from __future__ import annotations
-
-import base64
-import os
-from collections import OrderedDict
-from collections.abc import Awaitable, Sequence
-from typing import Any, Callable, Union, cast
-
-from openai.types.chat import (
-    ChatCompletionContentPartParam,
-    ChatCompletionMessageParam,
-    ChatCompletionToolParam,
-)
-
-from livekit.agents import llm
-
-AsyncAzureADTokenProvider = Callable[[], Union[str, Awaitable[str]]]
-
-
-def get_base_url(base_url: str | None) -> str:
-    if not base_url:
-        base_url = os.getenv(
-            "VOLCENGINE_LLM_BASE_URL", "https://ark.cn-beijing.volces.com/api/v3"
-        )
-    return base_url
-
-
-def to_fnc_ctx(fnc_ctx: Sequence[llm.Tool]) -> list[ChatCompletionToolParam]:
-    return cast(
-        list[ChatCompletionToolParam],
-        llm.ToolContext(fnc_ctx).parse_function_tools("openai"),
-    )
-
-
-def to_chat_ctx(
-    chat_ctx: llm.ChatContext, cache_key: Any
-) -> list[ChatCompletionMessageParam]:
-    # group the message and function_calls
-    item_groups: dict[str, list[llm.ChatItem]] = OrderedDict()
-    for item in chat_ctx.items:
-        if (
-            item.type == "message" and item.role == "assistant"
-        ) or item.type == "function_call":
-            group_id = item.id.split("/")[0]
-            if group_id not in item_groups:
-                item_groups[group_id] = []
-            item_groups[group_id].append(item)
-        else:
-            item_groups[item.id] = [item]
-
-    return [_group_to_chat_item(items, cache_key) for items in item_groups.values()]
-
-
-def _group_to_chat_item(
-    items: list[llm.ChatItem], cache_key: Any
-) -> ChatCompletionMessageParam:
-    if len(items) == 1:
-        return _to_chat_item(items[0], cache_key)
-    else:
-        msg = {"role": "assistant", "tool_calls": []}
-        for item in items:
-            if item.type == "message":
-                assert item.role == "assistant", (
-                    "only assistant messages can be grouped"
-                )
-                assert "content" not in msg, (
-                    "only one assistant message is allowed in a group"
-                )
-
-                msg.update(_to_chat_item(item, cache_key))
-            elif item.type == "function_call":
-                msg["tool_calls"].append(
-                    {
-                        "id": item.call_id,
-                        "type": "function",
-                        "function": {"name": item.name, "arguments": item.arguments},
-                    }
-                )
-        return msg
-
-
-def _to_chat_item(msg: llm.ChatItem, cache_key: Any) -> ChatCompletionMessageParam:
-    if msg.type == "message":
-        list_content: list[ChatCompletionContentPartParam] = []
-        text_content = ""
-        for content in msg.content:
-            if isinstance(content, str):
-                if text_content:
-                    text_content += "\n"
-                text_content += content
-            elif isinstance(content, llm.ImageContent):
-                list_content.append(_to_image_content(content, cache_key))
-
-        if not list_content:
-            # certain providers require text-only content in a string vs a list.
-            # for max-compatibility, we will combine all text content into a single string.
-            return {
-                "role": msg.role,  # type: ignore
-                "content": text_content,
-            }
-
-        if text_content:
-            list_content.append({"type": "text", "text": text_content})
-
-        return {
-            "role": msg.role,  # type: ignore
-            "content": list_content,
-        }
-
-    elif msg.type == "function_call":
-        return {
-            "role": "assistant",
-            "tool_calls": [
-                {
-                    "id": msg.call_id,
-                    "type": "function",
-                    "function": {
-                        "name": msg.name,
-                        "arguments": msg.arguments,
-                    },
-                }
-            ],
-        }
-
-    elif msg.type == "function_call_output":
-        return {
-            "role": "tool",
-            "tool_call_id": msg.call_id,
-            "content": msg.output,
-        }
-
-
-def _to_image_content(
-    image: llm.ImageContent, cache_key: Any
-) -> ChatCompletionContentPartParam:
-    img = llm.utils.serialize_image(image)
-    if img.external_url:
-        return {
-            "type": "image_url",
-            "image_url": {
-                "url": img.external_url,
-                "detail": img.inference_detail,
-            },
-        }
-    if cache_key not in image._cache:
-        image._cache[cache_key] = img.data_bytes
-    b64_data = base64.b64encode(image._cache[cache_key]).decode("utf-8")
-    return {
-        "type": "image_url",
-        "image_url": {
-            "url": f"data:{img.mime_type};base64,{b64_data}",
-            "detail": img.inference_detail,
-        },
-    }

livekit_plugins_volcenginee-1.3.3/livekit/plugins/volcengine/version.py

@@ -1 +0,0 @@
-__version__ = "1.3.3"