feat: adjust skill prompt and fix some bugs #988
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
* feat: skill with history * feat: pass chat-history into skill * feat: modify chat-history passing in skills * feat: modify code * fix: we don't need to pass history in part B * fix: process skill memory * feat: we do not return None with few history now * feat: update skill * feat: modify _split_task_chunk_by_llm * feat: filter by embedding * feat: modify skill --------- Co-authored-by: yuan.wang <yuan.wang@yuanwangdebijibendiannao.local> Co-authored-by: Wang Daoji <75928131+Wang-Daoji@users.noreply.github.com>
* feat: skill with history * feat: pass chat-history into skill * feat: modify chat-history passing in skills * feat: modify code * fix: we don't need to pass history in part B * fix: process skill memory * feat: we do not return None with few history now * feat: update skill * feat: modify _split_task_chunk_by_llm * feat: filter by embedding * feat: modify skill * feat: reinforce update rule --------- Co-authored-by: yuan.wang <yuan.wang@yuanwangdebijibendiannao.local> Co-authored-by: Wang Daoji <75928131+Wang-Daoji@users.noreply.github.com>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Description
Summary:
This PR improves the stability, contextual correctness, and abstraction discipline of the Skill Memory extraction pipeline.
As skill abstraction became more complex, several issues emerged in the previous implementation:
• Unclear and unsafe usage of chat_history during skill extraction
• Fragile task chunk splitting when message indices were malformed
• Incomplete parameter propagation across scheduler → reader → skill processor
• Rigid method signatures limiting extensibility
• Skill prompt lacking strict constraints on historical context usage
Key Changes
1. Controlled Introduction of chat_history into the Skill Pipeline
2. Stronger Skill Prompt Constraints
3. Fixes and Enhancements in Skill Extraction Logic
4. API & Scheduler Consistency Improvements
5. Concurrency & Robustness Improvements
Fix: #989
Docs Issue/PR: (docs-issue-or-pr-link)
Reviewer: @Wang-Daoji
Checklist: