Repository navigation
Description
Pre-submission checklist | 提交前检查
- I have searched existing issues and this hasn't been mentioned before | 我已搜索现有问题,确认此问题尚未被提及
- I have read the project documentation and confirmed this issue doesn't already exist | 我已阅读项目文档并确认此问题尚未存在
- This issue is specific to MemOS and not a general software issue | 该问题是针对 MemOS 的,而不是一般软件问题
Bug Description | 问题描述
On my deployment (@memtensor/memos-local-plugin@2.0.19, DeepSeek Harness adapter, Windows), every L3 "new world model" run fails — i.e. exactly the runs that actually need an LLM call:
l3.failed / stage=abstract / error.code=llm_failed
error.message = "openai_compatible request failed: This operation was aborted"
clusterKey = "git|git-cli"
Meanwhile the merge path (which needs no LLM call) works perfectly, so L3 itself is alive:
run.start = 4 run.done = 4 l3.merge = 31 (successes)
run.done ... clusters=8 created=0 merged=8 skipped=0
中文简述:L3 里凡是真正要调 LLM 的新建簇,100% 失败,错误是 This operation was aborted(HTTP 请求被中止);而不需要 LLM 的合并路径完全正常(本次启动 31 次合并全成功)。
这不是 #2335 / #2374:那两个报的是 'title' must be a non-empty string(LLM 有返回但字段不合法)。我这条更早——请求本身被 abort,LLM 根本没返回。(而且我把 L3 的 maxTokens 提到 16384 之后,title / must be an array 那一族已经消失,剩下的就是这个 abort。)
How to Reproduce | 如何重现
Environment-agnostic: run the plugin inside an agent host, let it work in the background after a turn, and wait for an l2.policy.induced event whose cluster is not mergeable (i.e. requires a new world model).
Observed sequence (host log, 2026-09-21 03:45 UTC):
[core.memory.l3] run.start trigger="l2.policy.induced" episodeId="..."
[core.memory.l3.cluster] clusters.built eligiblePolicies=113 clusters=8
[core.pipeline.bootstrap] l3Llm.llm_error provider="openai_compatible" model="glm-4.5-air"
message="llm_unavailable: openai_compatible request failed: This operation was aborted"
[core.memory.l3.abstract] abstract.llm_failed clusterKey="git|git-cli"
err="openai_compatible request failed: This operation was aborted"
[core.memory.l3] run.done clusters=8 created=0 merged=7 skipped=1
What I ruled out (with evidence)
- Not the endpoint or the key — I called the same endpoint (
open.bigmodel.cn, same key, sameglm-4.5-air) directly with curl/fetch: HTTP 200 and valid JSON in ~12–30 s. - Not a timeout —
dist/core/llm/fetcher.js:42doesmergeSignals(opts.signal, AbortSignal.timeout(opts.timeoutMs)). An expiry ofAbortSignal.timeoutsurfaces asTimeoutError; what we see isAbortError: This operation was aborted. So the aborting signal is the caller-provided one (dist/core/llm/client.js:254threadsopts?.signaldown to the provider). My guess is that post-turn work inherits a signal that is already aborted by the time the background run executes — and every retry inherits it again, hence a permanent 0% success rate. - Not the DeepSeek Harness host-LLM bridge — I explicitly disabled it (
hostLlmEnabled: false) and re-tested: the abort is unchanged. (Also, that bridge can never serve background work anyway:dist/adapters/deepseek-harness/host-llm.js:58-62requires anAsyncLocalStorageroute that only exists inside a turn, and its own budget is 2000 ms.) - Not
maxTokens— already raised to 16384 (see below).
Environment | 环境信息
- Operating System: Windows 10.0.26200 (x64)
- Host: DeepSeek Harness
0.1.6-alpha.1(dsh web), Windows - Plugin:
@memtensor/memos-local-plugin@2.0.19— DeepSeek Harness adapter (dist/adapters/deepseek-harness/index.js) - LLM:
provider: openai_compatible→https://open.bigmodel.cn/api/paas/v4/chat/completions, modelglm-4.5-air - L3 slot (
l3Llm): same model,maxTokens: 16384,timeoutMs: 180000,temperature: 0 - Storage: local sqlite (3k+ traces, 200+ policies, 100 skills, 6 world models)
Additional Context | 其他信息
1. What I fixed locally, in case it is worth upstreaming: the L3 maxTokens budget
l3Llm is empty by default, so core/pipeline/memory-core.js:307 (l3Llm ?? llm) makes L3 silently inherit the shared llm.maxTokens — which is 1024 in the default config. With a real L3 stress prompt I measured:
max_tokens |
result (same prompt, stream, temperature 0.15) |
|---|---|
| 1024 | content = 0 bytes (the model burns 1024 completion tokens and returns nothing) |
| 4096 | truncated JSON → 'constraints' must be an array / 'inference' must be an array |
| 16384 | valid JSON, all three facets (ℰ/ℐ/𝒞) present |
This matches #1896 (add maxTokens to LlmSchema). After I set l3Llm.maxTokens: 16384, the whole title / must be an array failure family disappeared in my deployment — so I suspect #2335 / #2374 are at least partly a budget problem rather than only an algorithm-layer one.
2. Questions
- For post-turn / background L3 work, how is the LLM call supposed to obtain a signal and a lifecycle budget? Right now it seems to inherit a signal that is already aborted, and each retry inherits it again → permanent failure with no way to recover.
- Should
l3Llm.maxTokensdefault to something non-empty (e.g. the 4096 thatdist/core/config/defaults.js:60-76already documents) instead of falling back to the shared 1024?
2026-09-25 Re-confirmation on the same deployment | 同机复现确认(4 天后)
Same host, same plugin version, same L3 slot config — the abort is still there, and it is wider than L3:
- L3 create path still produces nothing:
2026-09-25 16:03 [core.memory.l3] run.done trigger="l2.policy.induced" clusters=8 created=0 merged=8 skipped=0(新建 0、合并 8 成功 —— 与报告主症状一致)。 world_model表最新一条停在2026-09-18—— 此后 7 天零新建(合并路径照常工作)。- 同一 abort 现在也打在检索链上(本报告原本只归因到 L3,这里更正/加强):同一份 host 日志里
This operation was aborted共 38 次,最近两次为
WARN [core.retrieval] llm_filter.failed err="openai_compatible request failed: This operation was aborted" candidateCount=10(16:41 / 16:53)。
→ 也就是说凡是"回合外/后台"发起的 openai_compatible 调用都可能拿到一个已 abort 的 signal,不止 L3 抽象一处。 - 排除项复核:宿主 LLM 桥保持关闭(
hostLlmEnabled: false),abort 依旧 —— 与报告"排除 3"一致;l3Llm.maxTokens = 16384也保持,title/must be an array那一族确实没再出现(报告"排除 4"成立)。
(新增段落由同一部署在 2026-09-25 复核,仅追加证据,未改动原结论。)
Willingness to Implement | 实现意愿
- I'm willing to implement this myself | 我愿意自己解决
- I would like someone else to implement this | 我希望其他人来解决
Activity
Memtensor-AI commentedon Sep 25, 2026
🤖 AutoDev has picked up this issue and started working on it.
Task ID:
0ea005334707e775Working branch:
bugfix/autodev-2412-20260925171256995Target branch:
latest dev* branchWorkflow: 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.
fix(llm): detach aborted signals in background LLM calls
Memtensor-AI commentedon Sep 25, 2026
✅ AutoDev task
0ea005334707e775completed.Summary: Fixed the critical bug where L3 world-model creation and retrieval LLM filter failed 100% of the time with "This operation was aborted" error in background operations.
Root cause: Background LLM calls inherited already-aborted AbortSignal objects from completed turns. When L3 or retrieval ran after a turn ended, the turn's AbortController was already aborted, causing all HTTP requests to fail immediately.
Solution implemented three-layer signal sanitization: (1) LlmClient.makeCtx() now detects and replaces aborted signals before passing to providers, (2) foreground-resources signalFor() ignores already-aborted signals and uses only the pipeline shutdown signal, (3) added detachForegroundResources() utility for standalone use cases.
The fix preserves pipeline shutdown semantics while allowing background work to proceed normally. All 1580 tests pass, with comprehensive coverage added for signal replacement scenarios. The solution is backward compatible and requires no configuration changes.
Files changed: core/llm/client.ts, core/util/foreground-resources.ts, and corresponding test files (151 lines added). Task archived to specs repository successfully.
Base branch:
mainBranch:
bugfix/autodev-2412-20260925171256995Commit:
d8d91c9PR: #2413
Assigned to: @syzsunshine219
Reviewers: @whipser030, @hijzy
fix(memos-local-plugin): replace aborted signals with singleton for b…
github-actions commentedon Oct 28, 2026
This issue has been automatically marked as stale due to inactivity.
github-actions commentedon Nov 9, 2026
This issue has been automatically closed due to inactivity.