mirror of
https://gitee.com/wanwujie/deer-flow
synced 2026-04-03 06:12:14 +08:00
* fix(memory): inject stored facts into system prompt memory context - add Facts section rendering in format_memory_for_injection - rank facts by confidence and coerce confidence values safely - enforce max token budget while appending fact lines - add regression tests for fact inclusion, ordering, and budget behavior Fixes #1059 * Update the document with the latest status * fix(memory): harden fact injection — NaN/inf confidence, None content, incremental token budget (#1090) * Initial plan * fix(memory): address review feedback on confidence coercion, None content, and token budget Co-authored-by: WillemJiang <219644+WillemJiang@users.noreply.github.com> --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: WillemJiang <219644+WillemJiang@users.noreply.github.com> --------- Co-authored-by: Copilot <198982749+Copilot@users.noreply.github.com>
1.2 KiB
1.2 KiB
Memory System Improvements - Summary
Sync Note (2026-03-10)
This summary is synchronized with the main branch implementation.
TF-IDF/context-aware retrieval is planned, not merged yet.
Implemented
- Accurate token counting with
tiktokenin memory injection. - Facts are injected into
<memory>prompt content. - Facts are ordered by confidence and bounded by
max_injection_tokens.
Planned (Not Yet Merged)
- TF-IDF cosine similarity recall based on recent conversation context.
current_contextparameter forformat_memory_for_injection.- Weighted ranking (
similarity+confidence). - Runtime extraction/injection flow for context-aware fact selection.
Why This Sync Was Needed
Earlier docs described TF-IDF behavior as already implemented, which did not match code in main.
This mismatch is tracked in issue #1059.
Current API Shape
def format_memory_for_injection(memory_data: dict[str, Any], max_tokens: int = 2000) -> str:
No current_context argument is currently available in main.
Verification Pointers
- Implementation:
backend/src/agents/memory/prompt.py - Prompt assembly:
backend/src/agents/lead_agent/prompt.py - Regression tests:
backend/tests/test_memory_prompt_injection.py