fix(wecombot): deliver sandbox outbox media through full pipeline chain (#2328)

* fix(wecombot): align media upload protocol

* fix(wecombot): deliver outbox media in reply and fix tool call recording

- Integrate _send_media into reply_message and reply_message_chunk so
  sandbox outbox images/voices/files are uploaded and sent instead of
  being silently dropped.
- Add missing import base64 that caused _send_media to fail with a
  NameError swallowed by its except clause.
- Change yiri2target to return component dicts (text/image/voice/file)
  so callers can distinguish text from media.
- Fix _get_message_for_tool_context using result.first()/row[0] which
  returned a raw string instead of the ORM object, causing
  "'str' object has no attribute 'pipeline_id'" in tool call recording.
  Use result.scalars().first() per SQLAlchemy 2.0 convention.

* fix(pipeline): collect outbox attachments on final chunk with empty content

When the last streaming chunk has is_final=True but empty content
(e.g. the LLM sends all text in earlier chunks), the 'if result.content'
branch is skipped entirely, so _append_outbound_attachments never runs
and sandbox outbox images are silently dropped.

Add an elif branch for _is_final_assistant_message that creates an
empty MessageChain and still collects outbox attachments, so images
are delivered even when the final chunk carries no text.

* fix(box): bypass stdout truncation when reading outbox via exec

_read_outbox_via_exec used execute_tool which returns _serialize_result
where stdout is truncated to output_limit_chars (4000). A 7KB JPEG
encodes to ~9400 base64 chars, so the JSON payload was truncated and
json.loads failed silently, returning an empty list.

Call client.execute directly to get the raw BoxExecutionResult with
untruncated stdout, so base64 file data is preserved.

* fix(tests): adapt box and wrapper tests for client.execute and strict is_final check

- wrapper.py: restrict outbox collection on empty-content chunks to
  actual MessageChunk instances with is_final=True, not generic Mock
  objects that happen to have role='assistant'
- test_box_service.py: update _read_outbox_via_exec tests to mock
  client.execute (returning BoxExecutionResult) instead of
  execute_tool, matching the implementation change

* chore(wecombot): remove temporary upload log

* test(box): preserve direct outbox read and cleanup coverage

---------

Co-authored-by: fdc310 <2213070223@qq.com>
Co-authored-by: dadachann <185672915+dadachann@users.noreply.github.com>

tests/unit_tests/box/test_box_service.py

@@ -2163,25 +2163,38 @@ class TestInboundOutboundRoundTrip:
 
         calls = []
 
-        async def fake_execute_tool(parameters, q):
-            calls.append(parameters['command'])
-            if 'os.scandir' in parameters['command']:
-                return {
-                    'ok': True,
-                    'stdout': '[{"name": "out.png", "b64": "QUJD"}]',
-                    'stderr': '',
-                }
+        async def fake_client_execute(spec):
+            cmd = spec.cmd
+            calls.append(cmd)
+            if 'os.scandir' in cmd:
+                return BoxExecutionResult(
+                    session_id='s',
+                    backend_name='test',
+                    status=BoxExecutionStatus.COMPLETED,
+                    exit_code=0,
+                    stdout='[{"name": "out.png", "b64": "QUJD"}]',
+                    duration_ms=10,
+                )
             # the rm -rf cleanup call
-            return {'ok': True, 'stdout': '', 'stderr': ''}
+            return BoxExecutionResult(
+                session_id='s',
+                backend_name='test',
+                status=BoxExecutionStatus.COMPLETED,
+                exit_code=0,
+                stdout='',
+                duration_ms=10,
+            )
 
-        service.execute_tool = AsyncMock(side_effect=fake_execute_tool)
+        service.client.execute = AsyncMock(side_effect=fake_client_execute)
+        service.execute_tool = AsyncMock(return_value={'ok': True, 'stdout': '', 'stderr': ''})
 
         attachments = await service.collect_outbound_attachments(query)
         assert len(attachments) == 1
         assert attachments[0]['type'] == 'Image'
         assert attachments[0]['name'] == 'out.png'
         # cleanup (rm -rf) must have been issued after a successful collection
-        assert any('rm -rf' in c for c in calls)
+        service.execute_tool.assert_awaited_once()
+        assert 'rm -rf' in service.execute_tool.await_args.args[0]['command']
 
     @pytest.mark.asyncio
     async def test_collect_outbound_empty_still_clears(self):
@@ -2193,16 +2206,33 @@ class TestInboundOutboundRoundTrip:
 
         calls = []
 
-        async def fake_execute_tool(parameters, q):
-            calls.append(parameters['command'])
-            if 'os.scandir' in parameters['command']:
-                return {'ok': True, 'stdout': '[]', 'stderr': ''}
-            return {'ok': True, 'stdout': '', 'stderr': ''}
+        async def fake_client_execute(spec):
+            cmd = spec.cmd
+            calls.append(cmd)
+            if 'os.scandir' in cmd:
+                return BoxExecutionResult(
+                    session_id='s',
+                    backend_name='test',
+                    status=BoxExecutionStatus.COMPLETED,
+                    exit_code=0,
+                    stdout='[]',
+                    duration_ms=10,
+                )
+            return BoxExecutionResult(
+                session_id='s',
+                backend_name='test',
+                status=BoxExecutionStatus.COMPLETED,
+                exit_code=0,
+                stdout='',
+                duration_ms=10,
+            )
 
-        service.execute_tool = AsyncMock(side_effect=fake_execute_tool)
+        service.client.execute = AsyncMock(side_effect=fake_client_execute)
+        service.execute_tool = AsyncMock(return_value={'ok': True, 'stdout': '', 'stderr': ''})
         assert await service.collect_outbound_attachments(query) == []
         # cleanup (rm -rf) is issued unconditionally now
-        assert any('rm -rf' in c for c in calls)
+        service.execute_tool.assert_awaited_once()
+        assert 'rm -rf' in service.execute_tool.await_args.args[0]['command']
 
     @pytest.mark.asyncio
     async def test_passthrough_noop_when_unavailable(self):