From 4916fc07ab08f3c2b16c585bd333d5f1f6b24ee6 Mon Sep 17 00:00:00 2001
From: chengyongru <chengyongru.ai@gmail.com>
Date: Tue, 14 Jul 2026 15:31:12 +0800
Subject: [PATCH] fix(agent): close reasoning on stream timeout

---
 docs/configuration.md           |  2 +-
 nanobot/agent/runner.py         | 13 ++++----
 tests/agent/test_runner_core.py | 59 +++++++++++++++++++++++++++++++++
 3 files changed, 67 insertions(+), 7 deletions(-)

diff --git a/docs/configuration.md b/docs/configuration.md
index 004f6938..a23d9c1f 100644
--- a/docs/configuration.md
+++ b/docs/configuration.md
@@ -187,7 +187,7 @@ These variables are process-level switches. Set them in the same terminal, servi
 | Variable | Default | Description |
 |----------|---------|-------------|
 | `NANOBOT_MAX_CONCURRENT_REQUESTS` | `3` | Maximum concurrently running inbound agent requests. Must be an integer; set `0` or a negative value for unlimited. |
-| `NANOBOT_LLM_TIMEOUT_S` | `300` | Wall-clock timeout, in seconds, around ordinary LLM requests. Set `0` to disable. Sustained-goal turns bypass this wall-clock cap. |
+| `NANOBOT_LLM_TIMEOUT_S` | `300` | Wall-clock timeout, in seconds. Ordinary requests use this value; streaming requests use the greater of 300 seconds or twice this value. Set `0` to disable. Sustained-goal turns bypass this wall-clock cap. |
 | `NANOBOT_STREAM_IDLE_TIMEOUT_S` | `90` | Streaming idle timeout, in seconds, used by streaming providers. Invalid or non-positive values are ignored; values above `3600` are clamped. |
 | `NANOBOT_OPENAI_COMPAT_TIMEOUT_S` | `120` | HTTP request timeout, in seconds, for OpenAI-compatible providers. Invalid or non-positive values are ignored. |
 | `NANOBOT_WORKSPACE_SANDBOX_ENFORCED` | unset | Marks that an external workspace sandbox is already enforced. Truthy values (`1`, `true`, `yes`, `on`, `enabled`) use `NANOBOT_WORKSPACE_SANDBOX_PROVIDER` as the label; any other non-false value is treated as the provider name. |
diff --git a/nanobot/agent/runner.py b/nanobot/agent/runner.py
index 3c37c176..0bc32938 100644
--- a/nanobot/agent/runner.py
+++ b/nanobot/agent/runner.py
@@ -824,16 +824,17 @@ class AgentRunner:
             )
         except asyncio.TimeoutError:
             if outer_timeout_s is None:
-                return LLMResponse(
+                response = LLMResponse(
                     content="Error calling LLM: stream stalled",
                     finish_reason="error",
                     error_kind="timeout",
                 )
-            return LLMResponse(
-                content=f"Error calling LLM: timed out after {outer_timeout_s:g}s",
-                finish_reason="error",
-                error_kind="timeout",
-            )
+            else:
+                response = LLMResponse(
+                    content=f"Error calling LLM: timed out after {outer_timeout_s:g}s",
+                    finish_reason="error",
+                    error_kind="timeout",
+                )
         if progress_state and progress_state.get("reasoning_open"):
             await hook.emit_reasoning_end()
         dropped, all_dropped, original_finish_reason = (
diff --git a/tests/agent/test_runner_core.py b/tests/agent/test_runner_core.py
index 1e3983f8..39b74725 100644
--- a/tests/agent/test_runner_core.py
+++ b/tests/agent/test_runner_core.py
@@ -280,6 +280,65 @@ async def test_runner_times_out_never_ending_streaming_request():
     provider.chat_with_retry.assert_not_awaited()
 
 
+@pytest.mark.asyncio
+async def test_runner_closes_progress_reasoning_on_streaming_wall_timeout():
+    from nanobot.agent.hook import AgentHook
+    from nanobot.agent.runner import AgentRunner
+
+    provider = MagicMock(spec=LLMProvider)
+    provider.supports_progress_deltas = True
+    events: list[tuple[str, str | None]] = []
+
+    async def chat_stream_with_retry(*, on_content_delta, **kwargs):
+        try:
+            await on_content_delta("<think>working...</think>")
+            await asyncio.sleep(3600)
+        finally:
+            events.append(("provider_cancelled", None))
+
+    provider.chat_stream_with_retry = chat_stream_with_retry
+    provider.chat_with_retry = AsyncMock()
+    tools = MagicMock()
+    tools.get_definitions.return_value = []
+
+    class ProgressReasoningHook(AgentHook):
+        async def emit_reasoning(self, reasoning_content: str | None) -> None:
+            if reasoning_content:
+                events.append(("reasoning", reasoning_content))
+
+        async def emit_reasoning_end(self) -> None:
+            events.append(("reasoning_end", None))
+
+    real_wait_for = asyncio.wait_for
+
+    async def fake_wait_for(coro, *, timeout):
+        assert timeout == 300.0
+        return await real_wait_for(coro, timeout=0.01)
+
+    runner = AgentRunner()
+    with patch("nanobot.agent.runner.asyncio.wait_for", fake_wait_for):
+        result = await runner.run(make_run_spec(provider,
+            initial_messages=[{"role": "user", "content": "think forever"}],
+            tools=tools,
+            model="test-model",
+            max_iterations=1,
+            max_tool_result_chars=_MAX_TOOL_RESULT_CHARS,
+            hook=ProgressReasoningHook(),
+            progress_callback=AsyncMock(),
+            stream_progress_deltas=True,
+            llm_timeout_s=1,
+        ))
+
+    assert result.stop_reason == "error"
+    assert result.final_content == "Error calling LLM: timed out after 300s"
+    assert events == [
+        ("reasoning", "working..."),
+        ("provider_cancelled", None),
+        ("reasoning_end", None),
+    ]
+    provider.chat_with_retry.assert_not_awaited()
+
+
 @pytest.mark.asyncio
 async def test_runner_replaces_empty_tool_result_with_marker():
     from nanobot.agent.runner import AgentRunner