Release: agent per-stage timing breakdown #167

2026-06-30T21:28:54-04:00

bvandeusen commented

2026-06-30 21:28:54 -04:00

Agent-only. Instruments the job pipeline with per-stage timing (lease / download / decode / gpu / submit) and logs a rolling breakdown every 30s to the agent console:

timing/30s — lease 8ms · download 310ms · decode 40ms · gpu 165ms · submit 70ms | wall/job 585ms (214 jobs)

This is the "measure before rearchitecting" step — it tells us whether downloads are actually the wall-clock gap (→ worth a download/compute split) or whether the lease-indexing fix (#166) already removed the dominant cost. Thread-safe accumulator summarised by a small daemon reporter; one-time model load excluded from the gpu figure. Ships in the agent image.

🤖 Generated with Claude Code

Agent-only. Instruments the job pipeline with per-stage timing (lease / download / decode / gpu / submit) and logs a rolling breakdown every 30s to the agent console: ``` timing/30s — lease 8ms · download 310ms · decode 40ms · gpu 165ms · submit 70ms | wall/job 585ms (214 jobs) ``` This is the "measure before rearchitecting" step — it tells us whether downloads are actually the wall-clock gap (→ worth a download/compute split) or whether the lease-indexing fix (#166) already removed the dominant cost. Thread-safe accumulator summarised by a small daemon reporter; one-time model load excluded from the gpu figure. Ships in the agent image. 🤖 Generated with [Claude Code](https://claude.com/claude-code)

bvandeusen added 1 commit 2026-06-30 21:28:54 -04:00

feat(agent): per-stage timing breakdown (lease/download/decode/gpu/submit)

CI / lint (push) Successful in 2s

Details

CI / frontend-build (push) Successful in 19s

Details

CI / backend-lint-and-test (push) Successful in 27s

Details

CI / integration (push) Successful in 3m24s

Details

e6a7fe7d03

Instrument the job pipeline so we can see where wall-clock actually goes and
decide — on data, not theory — whether a download/compute split is worth
building. Each stage is timed per job and a rolling breakdown is logged every
30s to the agent console, e.g.:

  timing/30s — lease 8ms · download 310ms · decode 40ms · gpu 165ms · submit 70ms | wall/job 585ms (214 jobs)

- lease timed around client.lease() in the slot loop (per batch).
- download = fetch_image; decode = image/frame decode; gpu = detect + CCIP +
  batched embed; submit = the results POST. One-time model load is excluded
  from the gpu figure.
- Thread-safe accumulator (stage -> [sum, count]) summarised + reset by a small
  daemon reporter thread; logs only when there was work.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Ttrj5P7upUTueSfoJcxEqa

bvandeusen merged commit 937cfb65b4 into main

2026-06-30 21:28:58 -04:00

Sign in to join this conversation.

1 Participants

Notifications

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: bvandeusen/FabledCurator#167