Skip to content

fix: The feedback function fails when calling the search interface due to the failure in passing the 'user_name' parameter.#1174

Merged
CaralHsi merged 4 commits intoMemTensor:dev-20260302-v2.0.8from
whipser030:dev-20260302-v2.0.8_0306
Mar 6, 2026
Merged

fix: The feedback function fails when calling the search interface due to the failure in passing the 'user_name' parameter.#1174
CaralHsi merged 4 commits intoMemTensor:dev-20260302-v2.0.8from
whipser030:dev-20260302-v2.0.8_0306

Conversation

@whipser030
Copy link
Contributor

@whipser030 whipser030 commented Mar 6, 2026

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 #1173

Type of change

Please delete options that are not relevant.

  • Bug fix (non-breaking change which fixes an issue)
  • New feature (non-breaking change which adds functionality)
  • Breaking change (fix or feature that would cause existing functionality to not work as expected)
  • Refactor (does not change functionality, e.g. code style improvements, linting)
  • Documentation update

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

  • Unit Test
  • Test Script Or Test Steps (please provide)
  • Pipeline Automated API Test (please provide)

Checklist

  • I have performed a self-review of my own code | 我已自行检查了自己的代码
  • I have commented my code in hard-to-understand areas | 我已在难以理解的地方对代码进行了注释
  • I have added tests that prove my fix is effective or that my feature works | 我已添加测试以证明我的修复有效或功能正常
  • I have created related documentation issue/PR in MemOS-Docs (if applicable) | 我已在 MemOS-Docs 中创建了相关的文档 issue/PR(如果适用)
  • I have linked the issue to this PR (if applicable) | 我已将 issue 链接到此 PR(如果适用)
  • I have mentioned the person who will review this PR | 我已提及将审查此 PR 的人

Reviewer Checklist

  • closes #xxxx (Replace xxxx with the GitHub issue number)
  • Made sure Checks passed
  • Tests have been provided

@CaralHsi CaralHsi merged commit 39623ab into MemTensor:dev-20260302-v2.0.8 Mar 6, 2026
16 checks passed
CaralHsi added a commit that referenced this pull request Mar 9, 2026
* fix: The feedback function fails when calling the search interface due to the failure in passing the 'user_name' parameter. (#1174)

* add log

* add log

* add log

* hot fix

---------

Co-authored-by: 黑布林 <11641432+heiheiyouyou@user.noreply.gitee.com>

* feat:optimize config (#1176)

feat:optimize search_by_fulltext

* refactor: move openwork-memos-integration into apps/ directory

Reorganize project structure by moving the openwork-memos-integration
module under the apps/ directory for consistency.

Made-with: Cursor

* refactor: add openwork-memos-integration under apps/

Move the openwork-memos-integration module to apps/ directory as part
of the monorepo restructuring.

Made-with: Cursor

* fix: add multi-agent memory isolation and cursor reset protection

- Extract agentId from OpenClaw events, pass owner to captureMessages,
  ownerFilter to search/recall/dedup across the full pipeline
- Task creation now uses per-agent owner instead of hardcoded "agent:main"
- Add owner filter to getActiveTask, getAllActiveTasks, getUnassignedChunks,
  listTasks in sqlite.ts for proper task-level isolation
- Dedup (findDuplicate/findTopSimilar) now scopes to agent's own + public
  embeddings to prevent cross-agent deduplication
- Fix cursor key to include agentId, preventing shared session cursor
  conflicts in multi-agent scenarios
- On gateway restart, initialize cursor from last user message instead of
  zero to avoid re-ingesting entire session history
- Add multi-agent isolation tests for task owner filtering
- Bump version to 0.3.20

Made-with: Cursor

* chore: clean up gitignore and add missing config files

- Update root .gitignore to whitelist apps/ directory files (json, html,
  ts, etc.) that were previously excluded by the global *.json rule
- Update memos-local-openclaw .gitignore to exclude package-lock.json,
  www/, docs/, ppt/, .DS_Store, and database files
- Remove unnecessary www/docs symlink from tracking
- Add missing package.json, tsconfig.json, openclaw.plugin.json to git
- Add previously ignored config files for openwork-memos-integration

Made-with: Cursor

* chore: remove large binary assets and add development guide

- Remove video-thumbnail.png (4.6MB), font files (280KB), lock files
  (258KB), and usecase image assets from git tracking
- Add .gitignore for openwork-memos-integration to prevent re-adding
  binary assets, lock files, and build artifacts
- Add comprehensive Development Guide to memos-local-openclaw README
  covering prerequisites, project structure, build, test, local dev
  workflow, publishing, and utility scripts

Made-with: Cursor

* fix(memos-local-openclaw): honor memory_search maxResults

* fix(memos-local-openclaw): preserve memory_search default maxResults

* fix(memos-local-openclaw): sanitize captured metadata and evidence

* fix(memos-local-openclaw): enforce owner isolation for memory tools

* fix(memos-local-openclaw): flush ingest work before shutdown

* feat(memos-local-openclaw): task CRUD, topic boundary detection, skill evolution improvements

- Add task/skill edit, delete, retry-skill-generation on list cards
- Fix task boundary detection: per-turn LLM judgment with warm-up=1
- Fix detectAndProcess to not blindly assign all unassigned chunks
- Strengthen topic judge prompt to reduce false NEW splits
- Add LLM fallback chain (strongCfg → cfg → OpenClaw native model)
- Add skill evolver FK constraint safety checks
- Remove redundant edit/delete buttons from detail modals
- Add input validation for /api/memory content field
- Add /api/search minScore filter (0.64) and keyword fallback
- Shared LLM call utility (src/shared/llm-call.ts)

Made-with: Cursor

* docs(memos-local-openclaw): update README with latest features and install guidance

- Add Step 0: proactive C++ build tools install before plugin install
- Clarify Windows users usually don't need build tools (prebuilt binaries)
- Document per-turn LLM topic judge, warm-up=1, Task/Skill CRUD on cards
- Add LLM fallback chain details (skillSummarizer → summarizer → OpenClaw native)
- Add viewer search minScore 0.64 and keyword fallback docs
- Add agent parallelism (1-8 concurrency) for import
- Add shared/llm-call.ts to project structure
- Link to better-sqlite3 official troubleshooting in all install sections

Made-with: Cursor

* docs: update READMEs and bump local plugin to v1.0.0

- Root README: consolidate Cloud & Local OpenClaw plugins under one
  section with aligned formatting; add Local plugin to News and Resources
- Plugin README: add npm/license/node/GitHub badges and homepage links;
  fix git clone URL (tangbotony → MemTensor)
- Bump memos-local-openclaw-plugin version from 0.3.20 to 1.0.0

Made-with: Cursor

* docs: remove duplicate Local plugin entry from Resources section

Made-with: Cursor

* docs(memos-local-openclaw): update homepage links to production domain

Made-with: Cursor

* chore: change version number to v2.0.8 (#1186)

---------

Co-authored-by: Dubberman <48425266+whipser030@users.noreply.github.com>
Co-authored-by: 黑布林 <11641432+heiheiyouyou@user.noreply.gitee.com>
Co-authored-by: Hustzdy <67457465+wustzdy@users.noreply.github.com>
Co-authored-by: tangbo <1502220175@qq.com>
Co-authored-by: jiaqian <jiaqian@jiaqiandeMacBook-Air.local>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants