llama-server core-dumps on every SIGTERM, so each mavgpud yield writes a core file #116

2026-08-04T00:01:22+02:00

claude commented

2026-08-04 00:01:22 +02:00

Closes Vikunja #491.

Opened during an unattended overnight run: the diff-budget block was off (task overnight). Read the diff, not only the tests.

Acceptance criteria and quality gate are in TASK.md on this branch.
Review the review, not the diff — leave comments and the agent will apply them via task start 491.

Closes Vikunja #491. Opened during an unattended overnight run: the diff-budget block was off (`task overnight`). Read the diff, not only the tests. Acceptance criteria and quality gate are in `TASK.md` on this branch. Review the review, not the diff — leave comments and the agent will apply them via `task start 491`.

claude added 1 commit 2026-08-04 00:01:22 +02:00

mavgpud: a yield stops writing a core and reads as a yield (V-491) eda1112f3b

llama-server aborts inside its own static teardown on SIGTERM — the
handler calls exit(), stream_session_manager's destructor throws, and the
process dies "signal: aborted (core dumped)". mavgpud sends that signal on
every eviction, so a routine yield wrote a multi-gigabyte core into
systemd-coredump and logged the same line a real crash would.

LimitCORE=0 in the unit stops the disk cost. A yielding flag, set by stop
and cleared by start, makes the log distinguish the two: only an exit we
did not ask for is still reported as an exit.

Not filed upstream. Searched ggml-org/llama.cpp for
"ggml_uncaught_exception" with SIGTERM and for stream_session_manager and
found nothing matching, so the issue still wants writing — by someone with
an account on that tracker, which is why it is not in this commit.

kami referenced this pull request

2026-08-04 00:02:00 +02:00

Stale-task sweep 2026-08-04: what is left, and who it is blocked on #106

kami requested review from kami 2026-08-04 12:47:18 +02:00

kami approved these changes 2026-08-04 12:47:35 +02:00

claude added 2 commits 2026-08-04 14:09:01 +02:00

router: a reminder with no subject asks instead of guessing (V-383) 6d3f5b5b01

Slots.Text was the raw utterance for every intent, so a reminder could not
have an empty subject. StillMissing never reported SlotText, the question
"О чём напомнить?" was unaskable, and the branch in PendingQuestion.Answer
that fills a text slot could only overwrite the whole request.

The LLM path now keeps the model's own text, empty included, and the gate
turns a subjectless reminder into a question. The classifier path is
unchanged: it has no subject parser, so the utterance is the only signal it
has.

Merge PR #117 into task/491 (V-383) c69023c310

claude merged commit bdafc82e35 into master

2026-08-04 14:09:26 +02:00

Sign in to join this conversation.

2 Participants

Notifications

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: kami/Maven#116