fix(backends,markdown): stream turn events live, no blank lines for tool blocks

tests/test_claude_sdk_backend.py

@@ -1,3 +1,4 @@
+import asyncio
 import tempfile
 from pathlib import Path
 from typing import Any
@@ -419,3 +420,41 @@ async def test_close_disconnects(cwd: Path) -> None:
         )
     assert FakeClient.instances[0].connected is False
     assert backend.sessions == {}
+
+
+class GatedClient(FakeClient):
+    """Streams one delta, then waits for ``gate`` before finishing the turn."""
+
+    gate: asyncio.Event
+
+    async def receive_response(self):
+        yield StreamEvent(
+            uuid="u", session_id="s", event={"type": "message_start", "message": {}}
+        )
+        for e in _stream(0, "first"):
+            yield e
+        await GatedClient.gate.wait()
+        yield AssistantMessage(content=[TextBlock(text="first")], model="m")
+        yield _result(self.session_id)
+
+
+async def test_deltas_reach_the_caller_before_the_turn_ends(cwd: Path) -> None:
+    """The turn is not buffered: a delta is observable while the CLI still runs."""
+    GatedClient.gate = asyncio.Event()
+    backend = _backend(cwd, InMemorySessionStore())
+    backend._factory = GatedClient
+    events = backend.complete(
+        agent=backend.agent,
+        messages=[{"role": "user", "content": "hi"}],
+        conversation_id="conv-live",
+    )
+    seen: list[Any] = []
+    async for ev in events:
+        seen.append(ev)
+        if isinstance(ev, RawContentBlockDeltaEvent):
+            break
+    assert seen[-1].delta.text == "first"
+    assert not GatedClient.gate.is_set()
+    GatedClient.gate.set()
+    rest = [e async for e in events]
+    assert isinstance(rest[-1], RawMessageStopEvent)

tests/test_markdown_renderer.py

@@ -0,0 +1,45 @@
+from anthropic.types import Message, TextBlock, ThinkingBlock, ToolUseBlock, Usage
+
+from beaver_gateway.frontends.markdown import renderer
+
+
+def _message(*blocks: object) -> Message:
+    return Message(
+        id="m",
+        type="message",
+        role="assistant",
+        model="x",
+        content=list(blocks),  # type: ignore[arg-type]
+        stop_reason="end_turn",
+        stop_sequence=None,
+        usage=Usage(input_tokens=1, output_tokens=1),
+    )
+
+
+def test_tool_calls_leave_no_blank_lines() -> None:
+    message = _message(
+        TextBlock(type="text", text="first"),
+        ToolUseBlock(type="tool_use", id="t1", name="Bash", input={"command": "ls"}),
+        ToolUseBlock(type="tool_use", id="t2", name="Read", input={"file_path": "x"}),
+        ToolUseBlock(type="tool_use", id="t3", name="Grep", input={"pattern": "y"}),
+        TextBlock(type="text", text="second"),
+    )
+    assert renderer.render_assistant_message(message) == (
+        "### Assistant:\n\nfirst\n\nsecond\n"
+    )
+
+
+def test_thinking_renders_as_collapsed_callout() -> None:
+    message = _message(
+        ThinkingBlock(type="thinking", thinking="a\nb", signature="s"),
+        TextBlock(type="text", text="answer"),
+    )
+    assert renderer.render_assistant_message(message) == (
+        "### Assistant:\n\n> [!thinking]-\n> a\n> b\n\nanswer\n"
+    )
+
+
+def test_user_scaffold_matches_rendered_user_turn_shape() -> None:
+    body = renderer.append_to_body("### Assistant:\n\nhi\n", renderer.USER_SCAFFOLD)
+    assert body.endswith("\n\n---\n\n### User:\n\n")
+    assert renderer.render_user_text("q").startswith("### User:\n\n")