Several adjacent fix shapes that together drop 19 files from the pyrightconfig.json ignore list (96 → 77) and full-pyright errors from 605 → 580. Default pyright stays clean. TTS voice/context_id None handling — most files in this batch had a single error of the shape "value typed `T | None` passed where `T` is required" coming out of `assert_given(self._settings.voice)` (which strips `_NotGiven` but not `None`) or `get_active_audio_context_id()`. Two patterns: - For services where a missing voice means the request can't proceed (hume, openai, xtts, groq, kokoro, piper), added an explicit None check. Inside `run_tts` we yield an `ErrorFrame` and return — matching each service's existing error-emission style (a few wrap `Exception` broadly and were fine; openai/hume/xtts had narrower or no try blocks so a bare `raise ValueError` would have escaped uncaught). Piper validates in `__init__`, where failing fast at construction is the right shape. OpenAI also gained a `voice not in VALID_VOICES` guard with a clear message listing supported voices. - For services where a missing audio context just means "skip this message" (fish, lmnt, smallest, sarvam, neuphonic), widened `TTSService.append_to_audio_context`'s `context_id` signature to `str | None`. The function body already explicitly handled the None case with a debug log + early return, so the prior `str` annotation was a lie; making it honest cleared call sites without local guards. inworld's `_close_context` got the same treatment. google.genai imports — switched `from google import genai` to `import google.genai as genai` in google/image.py and google/llm.py. The dotted form sidesteps a PEP 420 namespace-package stub gap (the `google` namespace stubs come from a different distribution and don't declare `genai`), which means pyright now resolves `genai` to the real module rather than `Unknown`. IDE autocomplete on `genai.<x>` works for the first time. In image.py this surfaced three latent bugs that the `Unknown` resolution had been hiding (model was `str | _NotGiven | None` not narrowed before passing to the SDK; two spots accessed `.image_bytes` on an `Image | None` without a guard) — all fixed. llm.py's dotted import surfaced 8 errors (Content-list typing nuances, internal `_api_client` access, a few small Optionals); deferred to a future pass since they're outside this commit's scope, so the file stays in the ignore list with the dotted import. Latent bug fixes spotted along the way: - resembleai/tts.py was calling `push_error(ErrorFrame(...))`, but `push_error` takes a string — there's a separate `push_error_frame` for the frame case. Switched to the right method. - openai/base_llm.py: `max_completion_tokens` was the only sibling field on `OpenAILLMSettings` missing `| None` in its type, which caused the assignment in openai/llm.py from `params.max_completion_tokens` (`int | None`) to fail. Added `| None` for consistency with `max_tokens` etc. - heygen/base_api.py: `livekit_url: str = None` and `ws_url: str = None` declared `str` while defaulting to `None`. Removed the bogus defaults — both fields are required at construction in every in-tree call site, and the previous `str = None` was a Pydantic footgun. Other small ones: gladia/stt.py needed a None guard on `_session_url` before `websocket_connect`; openrouter/llm.py's `build_chat_completion_params` override widened to `dict[str, Any]` diverging from the parent's `OpenAILLMInvocationParams` — restored the parent's type; neuphonic/tts.py guarded the receive loop's `async for message in self._websocket` with a local-variable narrowing matching the pattern from 9e9b1f39e. groq/tts.py: tightened `output_format`'s typing to `Literal["flac","mp3","mulaw","ogg","wav"] | str = "wav"`. The literal side gives IDE autocomplete hints for the currently-supported set; the `| str` side keeps callers unblocked if groq adds a new format before this list is updated. A `cast` at the API boundary satisfies groq's stricter `Literal` parameter type. The literal alias mirrors the inlined Literal on `groq.resources.audio.speech.AsyncSpeech.create`'s `response_format` (the SDK doesn't export it as a named symbol). websocket_service.py: scoped `# pyright: ignore[reportAttributeAccessIssue]` on `websockets.WebSocketClientProtocol`. That alias is now a deprecated re-export from the legacy submodule and pyright doesn't surface it on the top-level `websockets` namespace; runtime is fine. Migrating to `websockets.ClientConnection` is a separate piece of work (transports/websocket/client.py uses the same alias four times) and left for a future commit. Files dropped from the ignore list: fish/tts.py, gladia/stt.py, google/image.py, groq/tts.py, heygen/base_api.py, hume/tts.py, inworld/tts.py, kokoro/tts.py, lmnt/tts.py, neuphonic/tts.py, openai/llm.py, openai/tts.py, openrouter/llm.py, piper/tts.py, resembleai/tts.py, sarvam/tts.py, smallest/tts.py, websocket_service.py, xtts/tts.py.
133 lines
4.7 KiB
Python
133 lines
4.7 KiB
Python
#
|
|
# Copyright (c) 2024-2026, Daily
|
|
#
|
|
# SPDX-License-Identifier: BSD 2-Clause License
|
|
#
|
|
|
|
"""OpenRouter LLM service implementation.
|
|
|
|
This module provides an OpenAI-compatible interface for interacting with OpenRouter's API,
|
|
extending the base OpenAI LLM service functionality.
|
|
"""
|
|
|
|
from dataclasses import dataclass
|
|
from typing import Any
|
|
|
|
from loguru import logger
|
|
|
|
from pipecat.adapters.services.open_ai_adapter import OpenAILLMInvocationParams
|
|
from pipecat.services.openai.base_llm import BaseOpenAILLMService
|
|
from pipecat.services.openai.llm import OpenAILLMService
|
|
from pipecat.services.settings import assert_given
|
|
|
|
|
|
@dataclass
|
|
class OpenRouterLLMSettings(BaseOpenAILLMService.Settings):
|
|
"""Settings for OpenRouterLLMService."""
|
|
|
|
pass
|
|
|
|
|
|
class OpenRouterLLMService(OpenAILLMService):
|
|
"""A service for interacting with OpenRouter's API using the OpenAI-compatible interface.
|
|
|
|
This service extends OpenAILLMService to connect to OpenRouter's API endpoint while
|
|
maintaining full compatibility with OpenAI's interface and functionality.
|
|
"""
|
|
|
|
Settings = OpenRouterLLMSettings
|
|
_settings: Settings
|
|
|
|
def __init__(
|
|
self,
|
|
*,
|
|
api_key: str | None = None,
|
|
model: str | None = None,
|
|
base_url: str = "https://openrouter.ai/api/v1",
|
|
settings: Settings | None = None,
|
|
**kwargs,
|
|
):
|
|
"""Initialize the OpenRouter LLM service.
|
|
|
|
Args:
|
|
api_key: The API key for accessing OpenRouter's API. If None, will attempt
|
|
to read from environment variables.
|
|
model: The model identifier to use. Defaults to "openai/gpt-4o-2024-11-20".
|
|
|
|
.. deprecated:: 0.0.105
|
|
Use ``settings=OpenRouterLLMService.Settings(model=...)`` instead.
|
|
|
|
base_url: The base URL for OpenRouter API. Defaults to "https://openrouter.ai/api/v1".
|
|
settings: Runtime-updatable settings. When provided alongside deprecated
|
|
parameters, ``settings`` values take precedence.
|
|
**kwargs: Additional keyword arguments passed to OpenAILLMService.
|
|
"""
|
|
# 1. Initialize default_settings with hardcoded defaults
|
|
default_settings = self.Settings(model="openai/gpt-4o-2024-11-20")
|
|
|
|
# 2. Apply direct init arg overrides (deprecated)
|
|
if model is not None:
|
|
self._warn_init_param_moved_to_settings("model", "model")
|
|
default_settings.model = model
|
|
|
|
# 3. (No step 3, as there's no params object to apply)
|
|
|
|
# 4. Apply settings delta (canonical API, always wins)
|
|
if settings is not None:
|
|
default_settings.apply_update(settings)
|
|
|
|
super().__init__(
|
|
api_key=api_key,
|
|
base_url=base_url,
|
|
settings=default_settings,
|
|
**kwargs,
|
|
)
|
|
|
|
def create_client(self, api_key=None, base_url=None, **kwargs):
|
|
"""Create an OpenRouter API client.
|
|
|
|
Args:
|
|
api_key: The API key to use for authentication. If None, uses instance default.
|
|
base_url: The base URL for the API. If None, uses instance default.
|
|
**kwargs: Additional arguments passed to the parent client creation method.
|
|
|
|
Returns:
|
|
The configured OpenRouter API client instance.
|
|
"""
|
|
logger.debug(f"Creating OpenRouter client with api {base_url}")
|
|
return super().create_client(api_key, base_url, **kwargs)
|
|
|
|
def build_chat_completion_params(
|
|
self, params_from_context: OpenAILLMInvocationParams
|
|
) -> dict[str, Any]:
|
|
"""Builds chat parameters, handling model-specific constraints.
|
|
|
|
Args:
|
|
params_from_context: Parameters from the LLM context.
|
|
|
|
Returns:
|
|
Transformed parameters ready for the API call.
|
|
"""
|
|
params = super().build_chat_completion_params(params_from_context)
|
|
model = assert_given(self._settings.model)
|
|
if model is not None and "gemini" in model.lower():
|
|
messages = params.get("messages", [])
|
|
if not messages:
|
|
return params
|
|
transformed_messages = []
|
|
system_message_seen = False
|
|
for msg in messages:
|
|
if msg.get("role") == "system":
|
|
if not system_message_seen:
|
|
transformed_messages.append(msg)
|
|
system_message_seen = True
|
|
else:
|
|
new_msg = msg.copy()
|
|
new_msg["role"] = "user"
|
|
transformed_messages.append(new_msg)
|
|
else:
|
|
transformed_messages.append(msg)
|
|
params["messages"] = transformed_messages
|
|
|
|
return params
|