fix(service): enhance message filtering to drop empty chat messages while retaining tool requests

tests/unit/test_entrypoints/test_api/test_routes/test_memorize_route_validation.py

@@ -0,0 +1,32 @@
+"""Validation paths for ``POST /api/v1/memory/add`` request DTOs."""
+
+from __future__ import annotations
+
+from everos.entrypoints.api.routes.memorize import ContentItemDTO, MemorizeAddRequest
+
+
+def test_add_request_accepts_md_content_item() -> None:
+    req = MemorizeAddRequest.model_validate(
+        {
+            "session_id": "s_md",
+            "messages": [
+                {
+                    "sender_id": "u1",
+                    "role": "user",
+                    "timestamp": 1_700_000_000_000,
+                    "content": [
+                        {
+                            "type": "md",
+                            "text": "# Deploy\nUse nginx.",
+                            "name": "deploy.md",
+                        }
+                    ],
+                }
+            ],
+        }
+    )
+
+    content = req.messages[0].content
+    assert isinstance(content, list)
+    assert isinstance(content[0], ContentItemDTO)
+    assert content[0].type == "md"

tests/unit/test_memory/test_extract/test_ingest/test_multimodal.py

@@ -2,11 +2,18 @@
 
 from __future__ import annotations
 
+import base64
+from pathlib import Path
+
+import pytest
+
+from everos.config import load_settings
 from everos.memory.extract.ingest.multimodal import (
     coerce_items,
     derive_text,
     normalise_content,
 )
+from everos.memory.extract.ingest.service import process
 
 
 def test_coerce_str_to_text_item() -> None:
@@ -46,3 +53,85 @@ def test_normalise_content_text_only_unchanged() -> None:
     assert items == [{"type": "text", "text": "hello"}]
     assert text == "hello"
     assert non_text == 0
+
+
+@pytest.fixture(autouse=True)
+def _clear_settings_cache():
+    load_settings.cache_clear()
+    yield
+    load_settings.cache_clear()
+
+
+async def test_process_renders_md_text_without_multimodal_parser(
+    monkeypatch: pytest.MonkeyPatch,
+) -> None:
+    import everos.memory.extract.ingest.service as ingest_service
+
+    monkeypatch.setattr(
+        ingest_service,
+        "require_multimodal",
+        lambda: (_ for _ in ()).throw(AssertionError("parser should not run")),
+    )
+    result = await process(
+        {
+            "session_id": "s_md_text",
+            "messages": [
+                {
+                    "sender_id": "u1",
+                    "role": "user",
+                    "timestamp": 1_700_000_000_000,
+                    "content": [{"type": "md", "text": "# Deploy\nUse nginx."}],
+                }
+            ],
+        }
+    )
+
+    assert result.messages[0].text == "# Deploy\nUse nginx."
+    assert result.messages[0].content_items[0]["type"] == "md"
+    assert result.messages[0].content_items[0]["text"] == "# Deploy\nUse nginx."
+    assert result.unparsed_non_text_count == 0
+
+
+async def test_process_reads_md_file_uri_as_utf8_text(tmp_path: Path) -> None:
+    doc = tmp_path / "guide.md"
+    doc.write_text("# 部署\n配置域名。", encoding="utf-8")
+
+    result = await process(
+        {
+            "session_id": "s_md_uri",
+            "messages": [
+                {
+                    "sender_id": "u1",
+                    "role": "user",
+                    "timestamp": 1_700_000_000_000,
+                    "content": [
+                        {"type": "md", "uri": f"file://{doc}", "name": "guide.md"}
+                    ],
+                }
+            ],
+        }
+    )
+
+    assert result.messages[0].text == "# 部署\n配置域名。"
+    assert result.messages[0].content_items[0]["text"] == "# 部署\n配置域名。"
+
+
+async def test_process_decodes_md_base64_as_utf8_text() -> None:
+    encoded = base64.b64encode("## Notes\n记住配置。".encode()).decode("ascii")
+
+    result = await process(
+        {
+            "session_id": "s_md_base64",
+            "messages": [
+                {
+                    "sender_id": "u1",
+                    "role": "user",
+                    "timestamp": 1_700_000_000_000,
+                    "content": [{"type": "md", "base64": encoded, "ext": "md"}],
+                }
+            ],
+        }
+    )
+
+    assert result.messages[0].text == "## Notes\n记住配置。"
+    assert result.messages[0].content_items[0]["text"] == "## Notes\n记住配置。"

tests/unit/test_memory/test_extract/test_parser/test_availability.py

@@ -18,6 +18,11 @@ def test_has_unparsed_multimodal_false_when_all_text() -> None:
     assert availability.has_unparsed_multimodal(items) is False
 
 
+def test_has_unparsed_multimodal_false_for_md() -> None:
+    items = [{"type": "md", "text": "# hi"}]
+    assert availability.has_unparsed_multimodal(items) is False
+
+
 def test_has_unparsed_multimodal_false_when_already_parsed() -> None:
     items = [{"type": "image", "uri": "x", "parsed_content": "ocr"}]
     assert availability.has_unparsed_multimodal(items) is False

tests/unit/test_service/test_boundary_helpers.py

@@ -74,6 +74,26 @@ def test_filter_agent_keeps_everything() -> None:
     assert [m.message_id for m in out] == ["m1", "m2"]
 
 
+def test_filter_drops_empty_plain_chat_messages_but_keeps_tool_requests() -> None:
+    msgs = [
+        _msg("m1", "user", text=""),
+        _msg("m2", "assistant", text="   "),
+        _msg(
+            "m3",
+            "assistant",
+            text="",
+            tool_calls=[ToolCall(id="tc1", function={"name": "f", "arguments": "{}"})],
+        ),
+        _msg("m4", "user", text="ok"),
+    ]
+
+    chat_out = _filter_for_mode(msgs, "chat")
+    agent_out = _filter_for_mode(msgs, "agent")
+
+    assert [m.message_id for m in chat_out] == ["m4"]
+    assert [m.message_id for m in agent_out] == ["m3", "m4"]
+
+
 # ── _to_conversation_item dispatch ────────────────────────────────────────