Fix (#229) deployed and behaving — closing. The worker has been through multiple restart cycles since (deploys + a MinIO interruption mid-model-sync) with clean lease release/re-request each time…
Verified and closing. Since #230 (COPY *.py + the image import smoke gate) the worker boots, consumes, leases, and captions — 110 completed captions in Mongo. The CI gate now runs `python3 -c…
Superseded by the MinIO model architecture and verified working — closing. The gated-repo problem was eliminated rather than tokened-around: the worker now syncs Qwen/Qwen3-VL-8B-Instruct…
Verified in production and closing. Since infra #40 deployed (SERVER lane parked, 4090 lane enabled, budget 24576 MB): the 16000 MB ImageDescription lease grants immediately (17:48:15,…
Root-caused WITH production data and fixed — PR #234. Forensics (read-only via mongo-router): the bad book holds pages [1,1,2,2,3,3] under TWO ISBNs (both uploads of the same PDF); the…
Second code layer landed: PR #233 — the true mechanism of the zero-question quiz was the fixed pagesToSkip=3 making a 3-page book start at page 4 (its whole content skipped). New `ComputePag…
Reliability half fixed in spikersoft-backend PR #232 — both triage suspects confirmed and addressed: (a) SafetyCheckRpcConsumer now retries transport wiring with backoff instead of rethrowing…
✅ Fixed & verified — closing. Commit a4e9cd7b (fix(image-description): COPY *.py into the image + import smoke test in CI (#508)) landed the durable fix on master:
- Dockerfile: individual…
Fix up in spikersoft-infrastructure PR #42: drive-aware healthcheck. One correction to this ticket's option 1: curl was REMOVED from MinIO images in 2023, so the probe is mc-based — `mc ready…
Fix up in spikersoft-backend PR #231 (worker Failed-state + StartQuizAttempt guard + 400 mapping + 3 xUnit tests — details on the PR). The page-count-mismatch investigation (pages 4–6 'not…
Immediate outage is RESOLVED — image-description is back to 1/1, imports cleanly, consuming (message_failure.py committed to master + image rebuilt). BUT keep this open: the **durable root cause…
✅ Fixed & verified — closing. Landed on origin/master:
- New torch-free
message_failure.py:GpuClientNotReadyError(transient/retryable), `PERMANENT_FAILURES=(ValueError,KeyError,FileNotFound…
Fix up in spikersoft-backend PR #230, per this ticket's fix list:
COPY *.py ./in the Dockerfile (individual COPYs were the trap — a new sibling module could be imported by code yet…
⚠️ The fix for this is currently deployed but BROKEN — filed #508. The pushed image-description :latest (UpdatedAt 17:40 UTC) imports `from message_failure import GpuClientNotReadyError,…