core/agent: share stream chunk builders across responses and messages bridges

src/plyngent/agent/messages_bridge.py

@@ -30,14 +30,9 @@ from plyngent.lmproto.openai_compatible.model import (
     AssistantFunctionTool,
     AssistantFunctionToolCall,
     ChatCompletionChoice,
-    ChatCompletionChunk,
     ChatCompletionResponse,
     ChatCompletionsParam,
-    ChunkChoice,
-    DeltaMessage,
     DeveloperChatMessage,
-    StreamFunctionDelta,
-    StreamToolCallDelta,
     SystemChatMessage,
     ToolFunctionItem,
     UserChatMessage,
@@ -290,88 +285,6 @@ def anthropic_response_to_chat_completion(
     )
 
 
-def finish_reason_chunk(
-    *,
-    model: str,
-    finish_reason: str,
-    created: int = 0,
-) -> ChatCompletionChunk:
-    return ChatCompletionChunk(
-        id="anthropic-stream",
-        object="chat.completion.chunk",
-        created=created,
-        model=model,
-        choices=[
-            ChunkChoice(
-                index=0,
-                delta=DeltaMessage(),
-                finish_reason=cast("Any", finish_reason),
-            )
-        ],
-    )
-
-
-def text_delta_chunk(*, model: str, content: str, created: int = 0) -> ChatCompletionChunk:
-    return ChatCompletionChunk(
-        id="anthropic-stream",
-        object="chat.completion.chunk",
-        created=created,
-        model=model,
-        choices=[
-            ChunkChoice(
-                index=0,
-                delta=DeltaMessage(content=content),
-            )
-        ],
-    )
-
-
-def tool_call_delta_chunk(
-    *,
-    model: str,
-    index: int,
-    call_id: str | None = None,
-    name: str | None = None,
-    arguments: str | None = None,
-    created: int = 0,
-) -> ChatCompletionChunk:
-    return ChatCompletionChunk(
-        id="anthropic-stream",
-        object="chat.completion.chunk",
-        created=created,
-        model=model,
-        choices=[
-            ChunkChoice(
-                index=0,
-                delta=DeltaMessage(
-                    tool_calls=[
-                        StreamToolCallDelta(
-                            index=index,
-                            id=call_id if call_id is not None else UNSET,
-                            type="function",
-                            function=StreamFunctionDelta(
-                                name=name if name is not None else UNSET,
-                                arguments=arguments if arguments is not None else UNSET,
-                            ),
-                        )
-                    ]
-                ),
-            )
-        ],
-    )
-
-
-def usage_chunk(*, model: str, usage: dict[str, Any], created: int = 0) -> ChatCompletionChunk:
-    return ChatCompletionChunk(
-        id="anthropic-stream",
-        object="chat.completion.chunk",
-        created=created,
-        model=model,
-        choices=[],
-        usage=usage,
-    )
-
-
 def _max_tokens_from_param(param: ChatCompletionsParam) -> int:
     if param.max_completion_tokens is not UNSET:
         return int(param.max_completion_tokens)

src/plyngent/agent/messages_dispatch.py

@@ -13,6 +13,8 @@ from plyngent.agent.messages_bridge import (
     anthropic_stop_to_finish_reason,
     anthropic_usage_to_dict,
     chat_param_to_anthropic_param,
+)
+from plyngent.agent.stream_chunks import (
     finish_reason_chunk,
     text_delta_chunk,
     tool_call_delta_chunk,

src/plyngent/agent/responses_bridge.py

@@ -27,11 +27,7 @@ from plyngent.lmproto.openai_compatible.model import (
     ChatCompletionChunk,
     ChatCompletionResponse,
     ChatCompletionsParam,
-    ChunkChoice,
-    DeltaMessage,
     DeveloperChatMessage,
-    StreamFunctionDelta,
-    StreamToolCallDelta,
     SystemChatMessage,
     ToolFunctionItem,
     UserChatMessage,
@@ -204,58 +200,6 @@ def response_to_chat_completion(response: Response) -> ChatCompletionResponse:
     )
 
 
-def finish_reason_chunk(
-    *,
-    model: str,
-    finish_reason: str,
-    created: int = 0,
-) -> ChatCompletionChunk:
-    """Terminal stream chunk carrying only ``finish_reason`` (no delta text)."""
-    return ChatCompletionChunk(
-        id="resp-stream",
-        object="chat.completion.chunk",
-        created=created,
-        model=model,
-        choices=[
-            ChunkChoice(
-                index=0,
-                delta=DeltaMessage(),
-                finish_reason=cast("Any", finish_reason),
-            )
-        ],
-    )
-
-
-def text_delta_chunk(*, model: str, content: str, created: int = 0) -> ChatCompletionChunk:
-    return ChatCompletionChunk(
-        id="resp-stream",
-        object="chat.completion.chunk",
-        created=created,
-        model=model,
-        choices=[
-            ChunkChoice(
-                index=0,
-                delta=DeltaMessage(content=content),
-            )
-        ],
-    )
-
-
-def reasoning_delta_chunk(*, model: str, content: str, created: int = 0) -> ChatCompletionChunk:
-    return ChatCompletionChunk(
-        id="resp-stream",
-        object="chat.completion.chunk",
-        created=created,
-        model=model,
-        choices=[
-            ChunkChoice(
-                index=0,
-                delta=DeltaMessage(reasoning_content=content),
-            )
-        ],
-    )
-
-
 def tool_call_chunks_from_response(
     response: Response,
     *,
@@ -263,50 +207,28 @@ def tool_call_chunks_from_response(
     created: int = 0,
 ) -> list[ChatCompletionChunk]:
     """Emit complete tool-call stream deltas (one chunk per call) for loop merge."""
+    from .stream_chunks import tool_call_delta_chunk
+
     calls = response_function_calls(response)
-    chunks: list[ChatCompletionChunk] = []
-    for index, call in enumerate(calls):
-        chunks.append(
-            ChatCompletionChunk(
-                id=response.id,
-                object="chat.completion.chunk",
-                created=created,
-                model=model,
-                choices=[
-                    ChunkChoice(
-                        index=0,
-                        delta=DeltaMessage(
-                            tool_calls=[
-                                StreamToolCallDelta(
-                                    index=index,
-                                    id=call.call_id,
-                                    type="function",
-                                    function=StreamFunctionDelta(
-                                        name=call.name,
-                                        arguments=call.arguments,
-                                    ),
-                                )
-                            ]
-                        ),
-                    )
-                ],
-            )
+    return [
+        tool_call_delta_chunk(
+            model=model,
+            index=index,
+            call_id=call.call_id,
+            name=call.name,
+            arguments=call.arguments,
+            created=created,
         )
-    return chunks
+        for index, call in enumerate(calls)
+    ]
 
 
 def usage_chunk_from_response(response: Response, *, model: str) -> ChatCompletionChunk | None:
+    from .stream_chunks import usage_chunk
+
     if response.usage is UNSET or response.usage is None:
         return None
-    created = int(response.created_at)
-    return ChatCompletionChunk(
-        id=response.id,
-        object="chat.completion.chunk",
-        created=created,
-        model=model,
-        choices=[],
-        usage=response.usage,
-    )
+    return usage_chunk(model=model, usage=response.usage, created=int(response.created_at))
 
 
 def _merge_response_tools(

src/plyngent/agent/responses_dispatch.py

@@ -16,15 +16,17 @@ from msgspec import UNSET
 
 from plyngent.agent.responses_bridge import (
     chat_param_to_responses_kwargs,
-    finish_reason_chunk,
-    reasoning_delta_chunk,
     response_to_assistant_message,
     response_to_chat_completion,
     responses_status_to_finish_reason,
-    text_delta_chunk,
     tool_call_chunks_from_response,
     usage_chunk_from_response,
 )
+from plyngent.agent.stream_chunks import (
+    finish_reason_chunk,
+    reasoning_delta_chunk,
+    text_delta_chunk,
+)
 from plyngent.lmproto.openai.model import Response as ResponseModel
 from plyngent.lmproto.openai.model import ResponsesCreateParam
 

src/plyngent/agent/stream_chunks.py

@@ -0,0 +1,128 @@
+"""Shared chat-completions stream chunk builders for protocol bridges.
+
+Both the Responses bridge and the Anthropic Messages bridge synthesize
+``ChatCompletionChunk`` objects so the agent loop can consume provider streams
+uniformly. The generic builders below are provider-agnostic; provider bridges
+map their events onto them.
+"""
+
+from __future__ import annotations
+
+from typing import Any, cast
+
+from msgspec import UNSET
+
+from plyngent.lmproto.openai_compatible.model import (
+    ChatCompletionChunk,
+    ChunkChoice,
+    DeltaMessage,
+    StreamFunctionDelta,
+    StreamToolCallDelta,
+)
+
+
+def finish_reason_chunk(
+    *,
+    model: str,
+    finish_reason: str,
+    created: int = 0,
+) -> ChatCompletionChunk:
+    """Terminal stream chunk carrying only ``finish_reason`` (no delta text)."""
+    return ChatCompletionChunk(
+        id="bridge-stream",
+        object="chat.completion.chunk",
+        created=created,
+        model=model,
+        choices=[
+            ChunkChoice(
+                index=0,
+                delta=DeltaMessage(),
+                finish_reason=cast("Any", finish_reason),
+            )
+        ],
+    )
+
+
+def text_delta_chunk(*, model: str, content: str, created: int = 0) -> ChatCompletionChunk:
+    return ChatCompletionChunk(
+        id="bridge-stream",
+        object="chat.completion.chunk",
+        created=created,
+        model=model,
+        choices=[
+            ChunkChoice(
+                index=0,
+                delta=DeltaMessage(content=content),
+            )
+        ],
+    )
+
+
+def reasoning_delta_chunk(*, model: str, content: str, created: int = 0) -> ChatCompletionChunk:
+    return ChatCompletionChunk(
+        id="bridge-stream",
+        object="chat.completion.chunk",
+        created=created,
+        model=model,
+        choices=[
+            ChunkChoice(
+                index=0,
+                delta=DeltaMessage(reasoning_content=content),
+            )
+        ],
+    )
+
+
+def tool_call_delta_chunk(
+    *,
+    model: str,
+    index: int,
+    call_id: str | None = None,
+    name: str | None = None,
+    arguments: str | None = None,
+    created: int = 0,
+) -> ChatCompletionChunk:
+    return ChatCompletionChunk(
+        id="bridge-stream",
+        object="chat.completion.chunk",
+        created=created,
+        model=model,
+        choices=[
+            ChunkChoice(
+                index=0,
+                delta=DeltaMessage(
+                    tool_calls=[
+                        StreamToolCallDelta(
+                            index=index,
+                            id=call_id if call_id is not None else UNSET,
+                            type="function",
+                            function=StreamFunctionDelta(
+                                name=name if name is not None else UNSET,
+                                arguments=arguments if arguments is not None else UNSET,
+                            ),
+                        )
+                    ]
+                ),
+            )
+        ],
+    )
+
+
+def usage_chunk(*, model: str, usage: dict[str, Any], created: int = 0) -> ChatCompletionChunk:
+    return ChatCompletionChunk(
+        id="bridge-stream",
+        object="chat.completion.chunk",
+        created=created,
+        model=model,
+        choices=[],
+        usage=usage,
+    )
+
+
+__all__ = [
+    "finish_reason_chunk",
+    "reasoning_delta_chunk",
+    "text_delta_chunk",
+    "tool_call_delta_chunk",
+    "usage_chunk",
+]