fix: modify bug in skill memory#1060
fix: modify bug in skill memory#1060PolarisLiu1 wants to merge 1 commit intoMemTensor:dev-20260202-v2.0.5from
Conversation
There was a problem hiding this comment.
Pull request overview
This PR adjusts the skill-memory extraction prompts and the LLM extraction pipeline to improve “update vs create” behavior when existing skill memories are present, and to reduce incorrect update outputs when no prior skills exist.
Changes:
- Refines EN/ZH prompt instructions to update an existing skill only when the topic matches an existing skill memory.
- Updates
_extract_skill_memory_by_llm_mdto include allSkillMemoryitems (removing therelativitythreshold filter). - Adds language-dependent prompt headers and a post-parse guard to force
update=falsewhen no old skills exist.
Reviewed changes
Copilot reviewed 2 out of 2 changed files in this pull request and generated 4 comments.
| File | Description |
|---|---|
src/memos/templates/skill_mem_prompt.py |
Refines similarity/update instructions in EN/ZH prompt text to better control update vs create behavior. |
src/memos/mem_reader/read_skill_memory/process_skill_memory.py |
Modifies how prior skill/context is embedded into the LLM prompt and adds a hallucination guard for update/old_memory_id. |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
| old_skill_content = ( | ||
| ("Exsit Skill Schemas: \n" + json.dumps(old_skill_content, ensure_ascii=False, indent=2)) | ||
| "已有技能列表: \n" if lang == "zh" else "Exsit Skill Schemas: \n" + | ||
| json.dumps(old_skill_content, ensure_ascii=False, indent=2) | ||
| if old_skill_content | ||
| else "" | ||
| ) |
There was a problem hiding this comment.
The conditional expression building old_skill_content is parsed such that when lang == "zh" it always returns only the header ("已有技能列表") and never appends the JSON payload (and it will even return the header when the skill list is empty). Restructure this so the language-specific header is combined with json.dumps(...) only when the original skill list is non-empty (e.g., compute a header first, then header + dumps), otherwise use an empty string.
| old_memories_context = "相关历史对话:\n" if lang == "zh" else "Relavant Context:\n" + "\n".join( | ||
| [f"{k}:\n{v}" for k, v in old_memories_context.items()] | ||
| ) |
There was a problem hiding this comment.
old_memories_context currently drops the actual joined history content when lang == "zh" (it becomes only "相关历史对话:\n"). This makes the prompt miss the recalled context for Chinese conversations. Build the prefix based on language, then always append the joined content (and consider returning an empty string if old_memories_context is empty).
| # If no old skill content, set update to False (for llm hallucination) | ||
| if not old_skill_content: | ||
| skill_memory["old_memory_id"] = '' | ||
| skill_memory["update"] = False |
There was a problem hiding this comment.
The hallucination guard if not old_skill_content: is now checking the post-formatted string, but old_skill_content is reassigned from a list to a string earlier. With the current formatting logic, this can become non-empty even when there are no skills (or no JSON payload), so the guard may not fire. Keep the original list in a separate variable (or check it before formatting) to decide whether to force update=False/empty old_memory_id.
| "已有技能列表: \n" if lang == "zh" else "Exsit Skill Schemas: \n" + | ||
| json.dumps(old_skill_content, ensure_ascii=False, indent=2) | ||
| if old_skill_content | ||
| else "" | ||
| ) | ||
|
|
||
| old_memories_context = "Relavant Context:\n" + "\n".join( | ||
| old_memories_context = "相关历史对话:\n" if lang == "zh" else "Relavant Context:\n" + "\n".join( | ||
| [f"{k}:\n{v}" for k, v in old_memories_context.items()] |
There was a problem hiding this comment.
Spelling in the prompt labels: Exsit Skill Schemas / Relavant Context are misspelled. Typos in prompt text can reduce LLM instruction clarity; please correct them (e.g., Existing Skill Schemas, Relevant Context).
1 participant
Description
Please include a summary of the change, the problem it solves, the implementation approach, and relevant context. List any dependencies required for this change.
Related Issue (Required): Fixes @issue_number
Type of change
Please delete options that are not relevant.
How Has This Been Tested?
Please describe the tests that you ran to verify your changes. Provide instructions so we can reproduce. Please also list any relevant details for your test configuration
Checklist
Reviewer Checklist