wx44wx/pipecat
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix: type fixes (and a few latent bug fixes) in 4 LLM adapters

Browse Source 
Same shape of fix we applied to anthropic_adapter.py earlier — these
adapters do dict-style mutation on values typed as
ChatCompletionMessageParam (a union of TypedDicts) or against Optional
fields. Apply boundary casts (`cast(dict[str, Any], ...)` for the
mutation block, cast back to the TypedDict at return sites). Most
changes are pure typing (rename + cast); a handful in gemini and
openai_realtime are small defensive bug fixes for code paths that
were latently broken by Optional fields slipping through:

perplexity_adapter.py — pure typing. Cast the deepcopied messages to
`list[dict[str, Any]]` for the role-merging / system-conversion /
trailing-assistant-removal transformations and cast back to
ChatCompletionMessageParam at the return.

bedrock_adapter.py — pure typing. Cast the message to
`dict[str, Any]` at the top of `_from_standard_message` for the
tool-result / tool-use / image-content transformations. Cast the
constructed dict at the return site of `get_llm_invocation_params`.

gemini_adapter.py — typing + several None guards on Content.parts and
related Optional fields. Each guard turns a latent
`TypeError`/`AttributeError` (when the type-system-allowed None
showed up at runtime) into a defensive skip — the type annotations
say these can be None and we now handle that.

open_ai_realtime_adapter.py:
- Typing: cast the deepcopied messages, cast back where needed.
- LLMSpecificMessage handling: previously the function would crash on
  the first `.get()` call if any LLMSpecificMessage was in the list.
  Filter them out and document the limitation — this adapter's
  pack-into-single-text-message strategy doesn't compose with opaque
  per-provider payloads.
- Real bug fix: `events.ConversationItem` is a Pydantic BaseModel,
  not a TypedDict. The bulk-packing path was constructing a raw dict
  where a ConversationItem was expected. Replaced with proper
  constructor calls (matches what the single-user-message path
  already does).
- Real bug fix: `_from_universal_context_message` was declared
  `-> events.ConversationItem` but on the unhandled-message
  fallthrough it logged and returned None implicitly. Raise
  ValueError so the violation is loud, not silent.

Removes 4 newly-clean files from the pyright ignore list:
adapters/services/{perplexity,bedrock,gemini,open_ai_realtime}_adapter.py.

Net: -95 pyright errors (full-config: 775 -> 680).
This commit is contained in:
Paul Kompfner
2026-04-28 17:15:35 -04:00
parent ef226c8a8e
commit 5e24027fd5
5 changed files with 112 additions and 77 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
pyrightconfig.json
View File

@@ -7,14 +7,10 @@
"ignore": [
"tests",
"src/pipecat/adapters/services/aws_nova_sonic_adapter.py",
"src/pipecat/adapters/services/bedrock_adapter.py",
"src/pipecat/adapters/services/gemini_adapter.py",
"src/pipecat/adapters/services/grok_realtime_adapter.py",
"src/pipecat/adapters/services/inworld_realtime_adapter.py",
"src/pipecat/adapters/services/open_ai_adapter.py",
"src/pipecat/adapters/services/open_ai_realtime_adapter.py",
"src/pipecat/adapters/services/open_ai_responses_adapter.py",
"src/pipecat/adapters/services/perplexity_adapter.py",
"src/pipecat/audio/dtmf/utils.py",
"src/pipecat/audio/filters/aic_filter.py",
"src/pipecat/audio/filters/krisp_viva_filter.py",

60
src/pipecat/adapters/services/bedrock_adapter.py
View File

@@ -10,7 +10,7 @@ import base64
import copy
import json
from dataclasses import dataclass
from typing import Any, TypedDict
from typing import Any, TypedDict, cast
from loguru import logger
@@ -68,16 +68,19 @@ class AWSBedrockLLMAdapter(BaseLLMAdapter[AWSBedrockLLMInvocationParams]):
system_instruction,
discard_context_system=True,
)
return {
"system": [{"text": effective_system}] if effective_system else None,
"messages": converted.messages,
# NOTE: LLMContext's tools are guaranteed to be a ToolsSchema (or NOT_GIVEN)
"tools": self.from_standard_tools(context.tools) or [],
# To avoid refactoring in AWSBedrockLLMService, we just pass through tool_choice.
# Eventually (when we don't have to maintain the non-LLMContext code path) we should do
# the conversion to Bedrock's expected format here rather than in AWSBedrockLLMService.
"tool_choice": context.tool_choice,
}
return cast(
AWSBedrockLLMInvocationParams,
{
"system": [{"text": effective_system}] if effective_system else None,
"messages": converted.messages,
# NOTE: LLMContext's tools are guaranteed to be a ToolsSchema (or NOT_GIVEN)
"tools": self.from_standard_tools(context.tools) or [],
# To avoid refactoring in AWSBedrockLLMService, we just pass through tool_choice.
# Eventually (when we don't have to maintain the non-LLMContext code path) we should do
# the conversion to Bedrock's expected format here rather than in AWSBedrockLLMService.
"tool_choice": context.tool_choice,
},
)
def get_messages_for_logging(self, context) -> list[dict[str, Any]]:
"""Get messages from a universal LLM context in a format ready for logging about AWS Bedrock.
@@ -213,35 +216,36 @@ class AWSBedrockLLMAdapter(BaseLLMAdapter[AWSBedrockLLMInvocationParams]):
]
}
"""
message = copy.deepcopy(message)
if message["role"] == "tool":
# ChatCompletionMessageParam (input) and the dict shape Bedrock expects
# are different — work with the deepcopied message as a plain dict for
# the transformations below.
msg = cast(dict[str, Any], copy.deepcopy(message))
if msg["role"] == "tool":
# Try to parse the content as JSON if it looks like JSON
try:
if message["content"].strip().startswith("{") and message[
"content"
].strip().endswith("}"):
content_json = json.loads(message["content"])
if msg["content"].strip().startswith("{") and msg["content"].strip().endswith("}"):
content_json = json.loads(msg["content"])
tool_result_content = [{"json": content_json}]
else:
tool_result_content = [{"text": message["content"]}]
tool_result_content = [{"text": msg["content"]}]
except (json.JSONDecodeError, ValueError, AttributeError):
tool_result_content = [{"text": message["content"]}]
tool_result_content = [{"text": msg["content"]}]
return {
"role": "user",
"content": [
{
"toolResult": {
"toolUseId": message["tool_call_id"],
"toolUseId": msg["tool_call_id"],
"content": tool_result_content,
},
},
],
}
if message.get("tool_calls"):
tc = message["tool_calls"]
ret = {"role": "assistant", "content": []}
if msg.get("tool_calls"):
tc = msg["tool_calls"]
ret: dict[str, Any] = {"role": "assistant", "content": []}
for tool_call in tc:
function = tool_call["function"]
arguments = json.loads(function["arguments"])
@@ -256,12 +260,12 @@ class AWSBedrockLLMAdapter(BaseLLMAdapter[AWSBedrockLLMInvocationParams]):
return ret
# Handle text content
content = message.get("content")
content = msg.get("content")
if isinstance(content, str):
if content == "":
return {"role": message["role"], "content": [{"text": "(empty)"}]}
return {"role": msg["role"], "content": [{"text": "(empty)"}]}
else:
return {"role": message["role"], "content": [{"text": content}]}
return {"role": msg["role"], "content": [{"text": content}]}
elif isinstance(content, list):
new_content = []
for item in content:
@@ -300,9 +304,9 @@ class AWSBedrockLLMAdapter(BaseLLMAdapter[AWSBedrockLLMInvocationParams]):
# Move image before the first text
image_item = new_content.pop(img_idx)
new_content.insert(first_txt_idx, image_item)
return {"role": message["role"], "content": new_content}
return {"role": msg["role"], "content": new_content}
return message
return msg
@staticmethod
def _to_bedrock_function_format(function: FunctionSchema) -> dict[str, Any]:

37
src/pipecat/adapters/services/gemini_adapter.py
View File

@@ -9,7 +9,7 @@
import base64
import json
from dataclasses import dataclass, field
from typing import Any, TypedDict
from typing import Any, TypedDict, cast
from loguru import logger
from openai import NotGiven
@@ -154,9 +154,12 @@ class GeminiLLMAdapter(BaseLLMAdapter[GeminiLLMInvocationParams]):
messages = self._from_universal_context_messages(self.get_messages(context)).messages
# Sanitize messages for logging
messages_for_logging = []
messages_for_logging: list[dict[str, Any]] = []
for message in messages:
obj = message.to_json_dict()
# `to_json_dict()` returns `dict[str, object]`; treat as a plain
# dict for the value indexing/mutation below. The broad `except`
# below is the safety net if any item isn't shaped as expected.
obj: dict[str, Any] = cast(dict[str, Any], message.to_json_dict())
try:
if "parts" in obj:
for part in obj["parts"]:
@@ -274,7 +277,8 @@ class GeminiLLMAdapter(BaseLLMAdapter[GeminiLLMInvocationParams]):
# Check if we only have function-related messages (no regular text)
effective_system = extracted_system or system_instruction
has_regular_messages = any(
len(msg.parts) == 1
msg.parts is not None
and len(msg.parts) == 1
and getattr(msg.parts[0], "text", None)
and not getattr(msg.parts[0], "function_call", None)
and not getattr(msg.parts[0], "function_response", None)
@@ -346,8 +350,11 @@ class GeminiLLMAdapter(BaseLLMAdapter[GeminiLLMInvocationParams]):
parts=[Part(function_call=FunctionCall(name="search", args={"query": "test"}))]
)
"""
role = message["role"]
content = message.get("content", [])
# ChatCompletionMessageParam (a union of TypedDicts) doesn't allow
# the dict-style key access used below; treat it as a plain dict.
msg = cast(dict[str, Any], message)
role = msg["role"]
content = msg.get("content", [])
# Convert non-initial system/developer messages to user role,
# as Gemini doesn't support these as input messages.
@@ -359,8 +366,8 @@ class GeminiLLMAdapter(BaseLLMAdapter[GeminiLLMInvocationParams]):
parts = []
tool_call_id_to_name_mapping = {}
if message.get("tool_calls"):
for tc in message["tool_calls"]:
if msg.get("tool_calls"):
for tc in msg["tool_calls"]:
id = tc["id"]
name = tc["function"]["name"]
tool_call_id_to_name_mapping[id] = name
@@ -376,7 +383,7 @@ class GeminiLLMAdapter(BaseLLMAdapter[GeminiLLMInvocationParams]):
elif role == "tool":
role = "user"
try:
response = json.loads(message["content"])
response = json.loads(msg["content"])
if isinstance(response, dict):
response_dict = response
else:
@@ -384,10 +391,10 @@ class GeminiLLMAdapter(BaseLLMAdapter[GeminiLLMInvocationParams]):
except Exception as e:
# Response might not be JSON-deserializable.
# This occurs with a UserImageFrame, for example, where we get a plain "COMPLETED" string.
response_dict = {"value": message["content"]}
response_dict = {"value": msg["content"]}
# Get function name from mapping using tool_call_id, or fallback
tool_call_id = message.get("tool_call_id")
tool_call_id = msg.get("tool_call_id")
function_name = "tool_call_result" # Default fallback
if tool_call_id and tool_call_id in params.tool_call_id_to_name_mapping:
function_name = params.tool_call_id_to_name_mapping[tool_call_id]
@@ -491,7 +498,7 @@ class GeminiLLMAdapter(BaseLLMAdapter[GeminiLLMInvocationParams]):
def is_tool_call_message(msg: Content) -> bool:
"""Check if message contains only function_call parts."""
return (
return bool(
msg.role == "model"
and msg.parts
and all(getattr(part, "function_call", None) for part in msg.parts)
@@ -499,6 +506,8 @@ class GeminiLLMAdapter(BaseLLMAdapter[GeminiLLMInvocationParams]):
def message_has_thought_signature(msg: Content) -> bool:
"""Check if any part in the message has a thought_signature."""
if msg.parts is None:
return False
return any(getattr(part, "thought_signature", None) for part in msg.parts)
merged_messages = []
@@ -564,6 +573,8 @@ class GeminiLLMAdapter(BaseLLMAdapter[GeminiLLMInvocationParams]):
logger.debug(f"Thought signatures to apply: {len(thought_signature_dicts)}")
for ts in thought_signature_dicts:
bookmark = ts.get("bookmark")
if bookmark is None:
continue
if bookmark.get("function_call"):
logger.trace(f" - To function call: {bookmark['function_call']}")
elif bookmark.get("text"):
@@ -665,6 +676,8 @@ class GeminiLLMAdapter(BaseLLMAdapter[GeminiLLMInvocationParams]):
if (
hasattr(part, "inline_data")
and part.inline_data
and part.inline_data.data is not None
and bookmark_inline_data.data is not None
# Comparing length should be good enough for matching inline data,
# especially since we're already matching thought signatures in
# strict message order. Comparing actual data is expensive.

61
src/pipecat/adapters/services/open_ai_realtime_adapter.py
View File

@@ -9,7 +9,7 @@
import copy
import json
from dataclasses import dataclass
from typing import Any, TypedDict
from typing import Any, TypedDict, cast
from loguru import logger
@@ -81,7 +81,7 @@ class OpenAIRealtimeLLMAdapter(BaseLLMAdapter):
Returns:
List of messages in a format ready for logging about OpenAI Realtime.
"""
return self.get_messages(context, truncate_large_values=True)
return cast(list[dict[str, Any]], self.get_messages(context, truncate_large_values=True))
@dataclass
class ConvertedMessages:
@@ -101,12 +101,24 @@ class OpenAIRealtimeLLMAdapter(BaseLLMAdapter):
if not universal_context_messages:
return self.ConvertedMessages(messages=[])
messages = copy.deepcopy(universal_context_messages)
# NOTE: This adapter does not yet handle ``LLMSpecificMessage`` — those
# are filtered out below. Other adapters (e.g. Anthropic) dispatch
# LLMSpecific items through a per-provider passthrough. For OpenAI
# Realtime, the strategy here packs a multi-message history into a
# single text message (see comment further down), which doesn't
# compose with opaque per-provider payloads. If/when this adapter
# adopts the per-message strategy, LLMSpecific items can flow
# through `_from_universal_context_message` like in other adapters.
messages: list[dict[str, Any]] = [
cast(dict[str, Any], m)
for m in copy.deepcopy(universal_context_messages)
if isinstance(m, dict)
]
system_instruction = None
# If we have a "system" message as our first message,
# pull that out into session "instructions"
if messages[0].get("role") == "system":
if messages and messages[0].get("role") == "system":
system = messages.pop(0)
content = system.get("content")
if isinstance(content, str):
@@ -124,7 +136,9 @@ class OpenAIRealtimeLLMAdapter(BaseLLMAdapter):
# If we have just a single "user" item, we can just send it normally
if len(messages) == 1 and messages[0].get("role") == "user":
return self.ConvertedMessages(
messages=[self._from_universal_context_message(messages[0])],
messages=[
self._from_universal_context_message(cast(LLMContextMessage, messages[0]))
],
system_instruction=system_instruction,
)
@@ -142,18 +156,18 @@ class OpenAIRealtimeLLMAdapter(BaseLLMAdapter):
return self.ConvertedMessages(
messages=[
{
"role": "user",
"type": "message",
"content": [
{
"type": "input_text",
"text": "\n\n".join(
events.ConversationItem(
role="user",
type="message",
content=[
events.ItemContent(
type="input_text",
text="\n\n".join(
[intro_text, json.dumps(messages, indent=2), trailing_text]
),
}
)
],
}
)
],
system_instruction=system_instruction,
)
@@ -161,31 +175,34 @@ class OpenAIRealtimeLLMAdapter(BaseLLMAdapter):
def _from_universal_context_message(
self, message: LLMContextMessage
) -> events.ConversationItem:
if message.get("role") == "user":
content = message.get("content")
if isinstance(message.get("content"), list):
# NOTE: ``LLMSpecificMessage`` is not yet handled here — see the
# corresponding note in `_from_universal_context_messages`.
msg = cast(dict[str, Any], message)
if msg.get("role") == "user":
content = msg.get("content")
if isinstance(content, list):
content = ""
for c in message.get("content"):
for c in msg.get("content", []):
if c.get("type") == "text":
content += " " + c.get("text")
else:
logger.error(
f"Unhandled content type in context message: {c.get('type')} - {message}"
f"Unhandled content type in context message: {c.get('type')} - {msg}"
)
return events.ConversationItem(
role="user",
type="message",
content=[events.ItemContent(type="input_text", text=content)],
)
if message.get("role") == "assistant" and message.get("tool_calls"):
tc = message.get("tool_calls")[0]
if msg.get("role") == "assistant" and msg.get("tool_calls"):
tc = msg["tool_calls"][0]
return events.ConversationItem(
type="function_call",
call_id=tc["id"],
name=tc["function"]["name"],
arguments=tc["function"]["arguments"],
)
logger.error(f"Unhandled message type in _from_universal_context_message: {message}")
raise ValueError(f"Unhandled message type in _from_universal_context_message: {msg}")
@staticmethod
def _to_openai_realtime_function_format(function: FunctionSchema) -> dict[str, Any]:

27
src/pipecat/adapters/services/perplexity_adapter.py
View File

@@ -28,6 +28,7 @@ the messages are sent to Perplexity's API.
"""
import copy
from typing import Any, cast
from openai.types.chat import ChatCompletionMessageParam
@@ -116,7 +117,11 @@ class PerplexityLLMAdapter(OpenAILLMAdapter):
if not messages:
return messages
messages = copy.deepcopy(messages)
# ChatCompletionMessageParam is a union of TypedDicts; the
# transformations below mutate by key/index in ways those TypedDicts
# don't permit. Work against a plain-dict view for the duration of
# the transformation and cast back at the return site.
msgs: list[dict[str, Any]] = cast(list[dict[str, Any]], copy.deepcopy(messages))
# Note: "developer" → "user" conversion is handled by the parent adapter
# via the convert_developer_to_user parameter.
@@ -125,10 +130,10 @@ class PerplexityLLMAdapter(OpenAILLMAdapter):
# Perplexity allows system messages at the start, but rejects them
# after any non-system message.
in_initial_system_block = True
for i in range(len(messages)):
if messages[i].get("role") == "system":
for i in range(len(msgs)):
if msgs[i].get("role") == "system":
if not in_initial_system_block:
messages[i]["role"] = "user"
msgs[i]["role"] = "user"
else:
in_initial_system_block = False
@@ -137,9 +142,9 @@ class PerplexityLLMAdapter(OpenAILLMAdapter):
# messages that violate Perplexity's strict alternation requirement.
# Skip consecutive system messages at the start — Perplexity allows those.
i = 0
while i < len(messages) - 1:
current = messages[i]
next_msg = messages[i + 1]
while i < len(msgs) - 1:
current = msgs[i]
next_msg = msgs[i + 1]
if current["role"] == next_msg["role"] == "system":
# Perplexity allows multiple initial system messages, don't merge
i += 1
@@ -154,7 +159,7 @@ class PerplexityLLMAdapter(OpenAILLMAdapter):
next_msg.get("content"), list
):
current["content"].extend(next_msg["content"])
messages.pop(i + 1)
msgs.pop(i + 1)
else:
i += 1
@@ -162,7 +167,7 @@ class PerplexityLLMAdapter(OpenAILLMAdapter):
# Perplexity requires the last message to be "user" or "tool".
# OpenAI appears to silently ignore trailing assistant messages
# server-side, so removing them preserves equivalent behavior.
while messages and messages[-1].get("role") == "assistant":
messages.pop()
while msgs and msgs[-1].get("role") == "assistant":
msgs.pop()
return messages
return cast(list[ChatCompletionMessageParam], msgs)