LearnNewsExamplesServices
Frontmatter
id12713
titleRoot-cause why a miniSummary backfill model call hung for hours (mini-summaries should be cheap)
stateClosed
labels
bugaiperformancemodel-experience
assigneesneo-gpt
createdAtJun 8, 2026, 2:36 AM
updatedAtJun 8, 2026, 10:07 AM
githubUrlhttps://github.com/neomjs/neo/issues/12713
authorneo-opus-grace
commentsCount2
parentIssuenull
subIssues[]
subIssuesCompleted0
subIssuesTotal0
blockedBy[]
blocking[]
closedAtJun 8, 2026, 10:07 AM

Root-cause why a miniSummary backfill model call hung for hours (mini-summaries should be cheap)

Closed v13.0.0/archive-v13-0-0-chunk-17 bugaiperformancemodel-experience
neo-opus-grace
neo-opus-grace commented on Jun 8, 2026, 2:36 AM

Friction

PR #12712 added timeouts + an orchestrator watchdog so a hung miniSummary backfill can no longer wedge maintenance — but that guards the symptom. The deeper friction (raised by @tobiu): why did a mini-summary model call hang for ~4h in the first place?

A mini-summary is cheap by design — e.g. a ~5k-char memory compressed to a tweet-size summary — and should complete in seconds. A multi-hour hang (no error, no return) points at a real root cause worth fixing, not just guarding against.

Hypotheses to investigate

  • Model misconfiguration: is the backfill calling the right small/fast model, or a wrong / oversized / not-yet-resident one?
  • Provider/endpoint health: the openAiCompatible endpoint accepting the connection but never responding (vs erroring) — LM Studio model-not-resident, or saturation?
  • Prompt/payload: an oversized or malformed prompt the endpoint chokes on silently?
  • Concurrency/saturation: was the embedder / KB-sync saturation seen in the same window starving the model endpoint?

Acceptance Criteria

  • Root cause identified (reproduce or instrument the hang).
  • Mini-summaries are reliably cheap/fast (bounded p99 well under the new 30s per-call timeout).

Refs #12711, #12712 (the symptom guard). Recommended for a peer with memory-core / model-provider context — author is staying on the grid lane.

tobiu referenced in commit 6fce106 - "fix(memory-core): abort hung miniSummary provider calls (#12713) (#12722)" on Jun 8, 2026, 10:07 AM
tobiu closed this issue on Jun 8, 2026, 10:07 AM