core/agent: fix deepseek responses reasoning_content for tool calls

tests/test_agent/test_responses_bridge.py

@@ -1,8 +1,13 @@
+from __future__ import annotations
+
+from typing import Any
+
 import msgspec
 
 from plyngent.agent.responses_bridge import (
     chat_messages_to_responses_input,
     chat_param_to_responses_kwargs,
+    reasoning_summary_text,
     response_to_assistant_message,
     response_to_chat_completion,
     responses_status_to_finish_reason,
@@ -145,6 +150,54 @@ def test_response_to_assistant_with_tools() -> None:
     assert completion.choices[0].finish_reason == "tool_calls"
 
 
+def _reasoning_response(
+    *,
+    output_reasoning: bool = False,
+    top_level: dict[str, Any] | None = None,
+) -> Response:
+    output: list[dict[str, Any]] = []
+    if output_reasoning:
+        output.append(
+            {
+                "id": "reason_1",
+                "type": "reasoning",
+                "summary": [{"type": "summary_text", "text": "openai-style reasoning"}],
+            }
+        )
+    return Response(
+        id="resp_r",
+        created_at=1,
+        model="deepseek-v4-flash",
+        output=output,
+        reasoning=top_level,
+    )
+
+
+def test_reasoning_summary_text_deepseek_top_level() -> None:
+    """DeepSeek Responses returns reasoning in the top-level ``reasoning`` field."""
+    response = _reasoning_response(top_level={"content": [{"type": "reasoning_content", "text": "think step by step"}]})
+    assert reasoning_summary_text(response) == "think step by step"
+    assistant = response_to_assistant_message(response)
+    assert assistant.reasoning_content == "think step by step"
+
+
+def test_reasoning_summary_text_prefers_top_level() -> None:
+    response = _reasoning_response(
+        output_reasoning=True,
+        top_level={"summary": [{"type": "summary_text", "text": "top-level reasoning"}]},
+    )
+    assert reasoning_summary_text(response) == "top-level reasoning"
+
+
+def test_reasoning_summary_text_falls_back_to_output_items() -> None:
+    response = _reasoning_response(output_reasoning=True)
+    assert reasoning_summary_text(response) == "openai-style reasoning"
+
+
+def test_reasoning_summary_text_empty_when_absent() -> None:
+    assert reasoning_summary_text(_reasoning_response()) == ""
+
+
 def test_responses_status_to_finish_reason_incomplete() -> None:
     body = {
         "id": "resp_i",

tests/test_agent/test_responses_dispatch.py

@@ -177,13 +177,67 @@ async def test_dispatch_responses_stream_text_and_usage() -> None:
     )
     stream = await dispatch_responses(cast("Any", client), param, stream=True)
     chunks = [chunk async for chunk in cast("Any", stream)]
-    # text deltas + finish + usage
     texts = [c.choices[0].delta.content for c in chunks if c.choices and isinstance(c.choices[0].delta.content, str)]
     assert texts == ["stream", "ed"]
     assert any(c.choices and c.choices[0].finish_reason == "stop" for c in chunks)
     assert any(token_usage_present(c) for c in chunks)
 
 
+async def _streamed_reasoning(
+    events: list[ResponseStreamEvent],
+) -> str:
+    """Run one Responses stream and join all streamed ``reasoning_content`` deltas."""
+    import msgspec
+
+    final = _completed_response(text="ok")
+    final.reasoning = {"content": [{"type": "reasoning_content", "text": "terminal reasoning"}]}
+    events.append(ResponseStreamEvent(type="response.completed", response=msgspec.to_builtins(final)))
+    client = ScriptedResponsesClient(stream_events=[events])
+    param = ChatCompletionsParam(model="gpt-test", messages=[UserChatMessage(content="hi")])
+    stream = await dispatch_responses(cast("Any", client), param, stream=True)
+    chunks = [chunk async for chunk in cast("Any", stream)]
+    parts: list[str] = []
+    for chunk in chunks:
+        if not chunk.choices:
+            continue
+        delta = chunk.choices[0].delta
+        if isinstance(delta.reasoning_content, str) and delta.reasoning_content:
+            parts.append(delta.reasoning_content)
+    return "".join(parts)
+
+
+async def test_dispatch_responses_stream_reasoning_text_done() -> None:
+    """DeepSeek ``response.reasoning_text.done`` carries the full reasoning text."""
+    reasoning = await _streamed_reasoning(
+        [ResponseStreamEvent(type="response.reasoning_text.done", delta="full chain of thought")]
+    )
+    assert reasoning == "full chain of thought"
+
+
+async def test_dispatch_responses_stream_reasoning_deltas() -> None:
+    reasoning = await _streamed_reasoning(
+        [
+            ResponseStreamEvent(type="response.reasoning_text.delta", delta="step one "),
+            ResponseStreamEvent(type="response.reasoning_text.delta", delta="step two"),
+        ]
+    )
+    assert reasoning == "step one step two"
+
+
+async def test_dispatch_responses_stream_terminal_only_reasoning() -> None:
+    """DeepSeek sometimes delivers reasoning only on the terminal response."""
+    reasoning = await _streamed_reasoning([])
+    assert reasoning == "terminal reasoning"
+
+
+async def test_dispatch_responses_stream_reasoning_no_duplicate() -> None:
+    """Streamed deltas win; the terminal reasoning is not re-emitted."""
+    reasoning = await _streamed_reasoning(
+        [ResponseStreamEvent(type="response.reasoning_text.delta", delta="streamed only")]
+    )
+    assert reasoning == "streamed only"
+
+
 def token_usage_present(chunk: object) -> bool:
     usage = getattr(chunk, "usage", UNSET)
     return usage is not UNSET and usage is not None