wanwu/deer-flow
1
0
Fork 0
mirror of https://gitee.com/wanwujie/deer-flow synced 2026-04-25 07:04:44 +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

6
backend/CLAUDE.md
View File

@@ -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