wanwu/deer-flow
1
0
Fork 0
mirror of https://gitee.com/wanwujie/deer-flow synced 2026-04-19 12:24:46 +08:00
Code Issues Packages Projects Releases Wiki Activity

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

Browse Source 
* 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>
This commit is contained in:
Ryanba
2026-03-18 22:41:13 +08:00
committed by GitHub
parent 423ea59491
commit f67c3d2c9e
4 changed files with 169 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

27
backend/packages/harness/deerflow/agents/memory/updater.py
View File

@@ -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: