fix(harness): skip duplicate memory facts (#1193)

* fix(harness): skip duplicate memory facts

Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>

* docs: note memory fact deduplication

Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>

* Apply suggestions from code review

Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>

---------

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>

README.md

@@ -437,6 +437,8 @@ Most agents forget everything the moment a conversation ends. DeerFlow remembers
 
 Across sessions, DeerFlow builds a persistent memory of your profile, preferences, and accumulated knowledge. The more you use it, the better it knows you — your writing style, your technical stack, your recurring workflows. Memory is stored locally and stays under your control.
 
+Memory updates now skip duplicate fact entries at apply time, so repeated preferences and context do not accumulate endlessly across sessions.
+
 ## Recommended Models
 
 DeerFlow is model-agnostic — it works with any LLM that implements the OpenAI-compatible API. That said, it performs best with models that support:

backend/CLAUDE.md

@@ -312,7 +312,7 @@ Bridges external messaging platforms (Feishu, Slack, Telegram) to the DeerFlow a
 ### Memory System (`packages/harness/deerflow/agents/memory/`)
 
 **Components**:
-- `updater.py` - LLM-based memory updates with fact extraction and atomic file I/O
+- `updater.py` - LLM-based memory updates with fact extraction, whitespace-normalized fact deduplication (trims leading/trailing whitespace before comparing), and atomic file I/O
 - `queue.py` - Debounced update queue (per-thread deduplication, configurable wait time)
 - `prompt.py` - Prompt templates for memory updates
 
@@ -325,9 +325,11 @@ Bridges external messaging platforms (Feishu, Slack, Telegram) to the DeerFlow a
 1. `MemoryMiddleware` filters messages (user inputs + final AI responses) and queues conversation
 2. Queue debounces (30s default), batches updates, deduplicates per-thread
 3. Background thread invokes LLM to extract context updates and facts
-4. Applies updates atomically (temp file + rename) with cache invalidation
+4. Applies updates atomically (temp file + rename) with cache invalidation, skipping duplicate fact content before append
 5. Next interaction injects top 15 facts + context into `<memory>` tags in system prompt
 
+Focused regression coverage for the updater lives in `backend/tests/test_memory_updater.py`.
+
 **Configuration** (`config.yaml` → `memory`):
 - `enabled` / `injection_enabled` - Master switches
 - `storage_path` - Path to memory.json

backend/packages/harness/deerflow/agents/memory/updater.py

@@ -173,6 +173,15 @@ def _strip_upload_mentions_from_memory(memory_data: dict[str, Any]) -> dict[str,
     return memory_data
 
 
+def _fact_content_key(content: Any) -> str | None:
+    if not isinstance(content, str):
+        return None
+    stripped = content.strip()
+    if not stripped:
+        return None
+    return stripped
+
+
 def _save_memory_to_file(memory_data: dict[str, Any], agent_name: str | None = None) -> bool:
     """Save memory data to file and update cache.
 
@@ -343,19 +352,35 @@ class MemoryUpdater:
             current_memory["facts"] = [f for f in current_memory.get("facts", []) if f.get("id") not in facts_to_remove]
 
         # Add new facts
+        existing_fact_keys = {
+            fact_key
+            for fact_key in (
+                _fact_content_key(fact.get("content"))
+                for fact in current_memory.get("facts", [])
+            )
+            if fact_key is not None
+        }
         new_facts = update_data.get("newFacts", [])
         for fact in new_facts:
             confidence = fact.get("confidence", 0.5)
             if confidence >= config.fact_confidence_threshold:
+                raw_content = fact.get("content", "")
+                normalized_content = raw_content.strip()
+                fact_key = _fact_content_key(normalized_content)
+                if fact_key is not None and fact_key in existing_fact_keys:
+                    continue
+
                 fact_entry = {
                     "id": f"fact_{uuid.uuid4().hex[:8]}",
-                    "content": fact.get("content", ""),
+                    "content": normalized_content,
                     "category": fact.get("category", "context"),
                     "confidence": confidence,
                     "createdAt": now,
                     "source": thread_id or "unknown",
                 }
                 current_memory["facts"].append(fact_entry)
+                if fact_key is not None:
+                    existing_fact_keys.add(fact_key)
 
         # Enforce max facts limit
         if len(current_memory["facts"]) > config.max_facts:

backend/tests/test_memory_updater.py

@@ -0,0 +1,137 @@
+from unittest.mock import patch
+
+from deerflow.agents.memory.updater import MemoryUpdater
+from deerflow.config.memory_config import MemoryConfig
+
+
+def _make_memory(facts: list[dict[str, object]] | None = None) -> dict[str, object]:
+    return {
+        "version": "1.0",
+        "lastUpdated": "",
+        "user": {
+            "workContext": {"summary": "", "updatedAt": ""},
+            "personalContext": {"summary": "", "updatedAt": ""},
+            "topOfMind": {"summary": "", "updatedAt": ""},
+        },
+        "history": {
+            "recentMonths": {"summary": "", "updatedAt": ""},
+            "earlierContext": {"summary": "", "updatedAt": ""},
+            "longTermBackground": {"summary": "", "updatedAt": ""},
+        },
+        "facts": facts or [],
+    }
+
+
+def _memory_config(**overrides: object) -> MemoryConfig:
+    config = MemoryConfig()
+    for key, value in overrides.items():
+        setattr(config, key, value)
+    return config
+
+
+def test_apply_updates_skips_existing_duplicate_and_preserves_removals() -> None:
+    updater = MemoryUpdater()
+    current_memory = _make_memory(
+        facts=[
+            {
+                "id": "fact_existing",
+                "content": "User likes Python",
+                "category": "preference",
+                "confidence": 0.9,
+                "createdAt": "2026-03-18T00:00:00Z",
+                "source": "thread-a",
+            },
+            {
+                "id": "fact_remove",
+                "content": "Old context to remove",
+                "category": "context",
+                "confidence": 0.8,
+                "createdAt": "2026-03-18T00:00:00Z",
+                "source": "thread-a",
+            },
+        ]
+    )
+    update_data = {
+        "factsToRemove": ["fact_remove"],
+        "newFacts": [
+            {"content": "User likes Python", "category": "preference", "confidence": 0.95},
+        ],
+    }
+
+    with patch(
+        "deerflow.agents.memory.updater.get_memory_config",
+        return_value=_memory_config(max_facts=100, fact_confidence_threshold=0.7),
+    ):
+        result = updater._apply_updates(current_memory, update_data, thread_id="thread-b")
+
+    assert [fact["content"] for fact in result["facts"]] == ["User likes Python"]
+    assert all(fact["id"] != "fact_remove" for fact in result["facts"])
+
+
+def test_apply_updates_skips_same_batch_duplicates_and_keeps_source_metadata() -> None:
+    updater = MemoryUpdater()
+    current_memory = _make_memory()
+    update_data = {
+        "newFacts": [
+            {"content": "User prefers dark mode", "category": "preference", "confidence": 0.91},
+            {"content": "User prefers dark mode", "category": "preference", "confidence": 0.92},
+            {"content": "User works on DeerFlow", "category": "context", "confidence": 0.87},
+        ],
+    }
+
+    with patch(
+        "deerflow.agents.memory.updater.get_memory_config",
+        return_value=_memory_config(max_facts=100, fact_confidence_threshold=0.7),
+    ):
+        result = updater._apply_updates(current_memory, update_data, thread_id="thread-42")
+
+    assert [fact["content"] for fact in result["facts"]] == [
+        "User prefers dark mode",
+        "User works on DeerFlow",
+    ]
+    assert all(fact["id"].startswith("fact_") for fact in result["facts"])
+    assert all(fact["source"] == "thread-42" for fact in result["facts"])
+
+
+def test_apply_updates_preserves_threshold_and_max_facts_trimming() -> None:
+    updater = MemoryUpdater()
+    current_memory = _make_memory(
+        facts=[
+            {
+                "id": "fact_python",
+                "content": "User likes Python",
+                "category": "preference",
+                "confidence": 0.95,
+                "createdAt": "2026-03-18T00:00:00Z",
+                "source": "thread-a",
+            },
+            {
+                "id": "fact_dark_mode",
+                "content": "User prefers dark mode",
+                "category": "preference",
+                "confidence": 0.8,
+                "createdAt": "2026-03-18T00:00:00Z",
+                "source": "thread-a",
+            },
+        ]
+    )
+    update_data = {
+        "newFacts": [
+            {"content": "User prefers dark mode", "category": "preference", "confidence": 0.9},
+            {"content": "User uses uv", "category": "context", "confidence": 0.85},
+            {"content": "User likes noisy logs", "category": "behavior", "confidence": 0.6},
+        ],
+    }
+
+    with patch(
+        "deerflow.agents.memory.updater.get_memory_config",
+        return_value=_memory_config(max_facts=2, fact_confidence_threshold=0.7),
+    ):
+        result = updater._apply_updates(current_memory, update_data, thread_id="thread-9")
+
+    assert [fact["content"] for fact in result["facts"]] == [
+        "User likes Python",
+        "User uses uv",
+    ]
+    assert all(fact["content"] != "User likes noisy logs" for fact in result["facts"])
+    assert result["facts"][1]["source"] == "thread-9"