Skip to content

[Bug] MemOS 2.0.19 untagged cluster _|_ enters L3 abstraction pipeline and causes 100% llm_failed due to missing title #2374

Closed as not planned

Description

@Memtensor-AI

产品线:MemOS 正式版开源项目
仓库:https://github.com/MemTensor/MemOS
记录 ID:WeFBbZFjXX

MemOS 2.0.19 中 _|_ 无标签簇(untagged cluster)进入 L3 世界模型抽象流水线,因 abstractDraft 未做前置过滤,title 字段缺失,导致 world_model_generate 100% llm_failed。错误签名:kind=l3.failed / stage=abstract / error.code=llm_failed / error.message="l3.abstraction: 'title' must be a non-empty string" / clusterKey=|。本机累计 1686 次失败 / 26.2 小时持续无冷却重试(785 次来自 | 簇,历史 0 次成功)。
OpenClaw 知识库结果:NO_REPLY
判断依据:完整故障报告已提供:环境、错误签名、数据规模、失败率统计(785/785,100%)、根因分析(无标签簇无 title 但未前置拦截)、永久重试机制导致放大效应、本地临时规避方案及副作用均已说明。知识库无此 bug 的官方修复方案,需官方在算法层修复。
trace_id=ca1c022a8286b7d99eaf80aa31b09307
xiaoyi:9c5f3c1925f26ce47a38c05f
issue:5eed599b754d3c49961f3f6c

分析及待补充信息

反馈描述指向 MemOS 正式版开源项目,候选仓库唯一且注册表已明确归属为 GitHub 上的 MemOS。问题具备明确版本、错误签名、触发条件、影响范围、失败统计与根因分析,属于可复现且症状清晰的产品缺陷。根据规则,已有产品归属且症状明确的 bug 应先创建 GitHub issue 跟踪。

Activity

  1. added
    ai:taskDispatched to AI coding agent | 已派发给 AI 编码任务
    status:in-progressSomeone or AI is working on it | 人工或 AI 正在处理
    on Sep 16, 2026
  2. self-assigned this
    on Sep 16, 2026
  3. Memtensor-AI commented on Sep 16, 2026

    @Memtensor-AI
    CollaboratorAuthor

    🤖 AutoDev has picked up this issue and started working on it.

    Task ID: 358488c1954c9ee6
    Working branch: feature/autodev-2374-20260916030702169
    Target branch: latest dev* branch
    Workflow: opsp (analysis → coding → testing → PR)

    I will post the PR link here once done. If I need more information, I will ask in the comments.

  4. Memtensor-AI commented on Sep 16, 2026

    @Memtensor-AI
    CollaboratorAuthor

    ✅ AutoDev task 358488c1954c9ee6 completed.

    Summary: Fixed issue #2374: MemOS 2.0.19 L3 pipeline no longer feeds the _|_ untagged cluster into abstractDraft. When domainKeyOf returns the catch-all "_|_" key (all TAG_REGEX / TOOL_REGEX matchers missed), the cluster has no shared organising principle and the LLM consistently returns empty title, tripping abstract.ts::validate and yielding 100% llm_failed. Field data reported 785/785 _|_-cluster abstractions failing, roughly 47% of the 1686 total L3 failures over 26.2h.

    The fix adds a per-cluster guard in runL3 (positioned after no_centroid, before cooldown/LLM) that: (1) records an AbstractionResult with the new skippedReason: "untagged_cluster" value, (2) emits an info-level "untagged.skipped" log on the abstract channel, and (3) continues without invoking abstractDraft, spending an LLM round-trip, marking cooldown, or emitting l3.failed. domainKeyOf / clusterPolicies / abstractDraft are unchanged so cluster-count metrics and tagged-cluster behaviour stay intact.

    Test evidence — RED phase: the two new integration tests (skips the '_|_' untagged cluster before calling the LLM and still processes tagged clusters when mixed with an untagged bucket) initially failed on baseline (expected null to be 'untagged_cluster'). GREEN phase after the fix: 6/6 L3 integration tests, 35/35 L3 unit+integration tests, and the full plugin suite 1559 passed / 2 pre-existing skips / 0 failed. tsc --noEmit clean.

    Three files changed under apps/memos-local-plugin/core/memory/l3/ (l3.ts +27, types.ts +1) and tests/unit/memory/l3/l3.integration.test.ts (+175). .ai-tasks/ and openspec/changes/ are gitignored via .git/info/exclude and stay out of the PR. opsp artifacts also archived and pushed to memos-autodev-specs main.

    Base branch: main
    Branch: feature/autodev-2374-20260916030702169
    Commit: 612964e
    PR: #2375
    Assigned to: @hijzy
    Reviewers: @MatthewZhuang, @CarltonXiang, @syzsunshine219, @World-controller

  5. added
    ai:testingAI agent is running tests | AI 正在运行测试
    and removed
    ai:codingAI agent is coding | AI 正在编码
    on Sep 16, 2026
  6. github-actions commented on Oct 17, 2026

    @github-actions
    Contributor

    This issue has been automatically marked as stale due to inactivity.

  7. added
    status:staleAuto-marked stale after 30d inactivity; closes 7d later unless exempt.
    on Oct 17, 2026
  8. github-actions commented on Oct 26, 2026

    @github-actions
    Contributor

    This issue has been automatically closed due to inactivity.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Labels

ai:taskDispatched to AI coding agent | 已派发给 AI 编码任务ai:testingAI agent is running tests | AI 正在运行测试area:coreMOS 编排层 / 框架底座 / 跨模块问题status:in-progressSomeone or AI is working on it | 人工或 AI 正在处理status:staleAuto-marked stale after 30d inactivity; closes 7d later unless exempt.

Type

No type

Projects

No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions