OCuLink Riser for the Supermicro AIOM Slot

@@ -1,6 +1,6 @@ # AI Flow run: claude on board-0 -**Delivered** at 2026-10-13T12:53:37Z: **503.8 min of AI time** from the prompt to "done, here is your video" (934.1 min on the wall clock). +**Delivered** at 2026-10-13T12:55:10Z: **505.3 min of AI time** from the prompt to "done, here is your video" (935.7 min on the wall clock). Since then 0.0 min more of AI time over 1 follow-up prompt(s), listed under Sessions; none of it is in the delivery number.  Prompt at 2026-10-12T21:19:30Z (UTC). Flow: board. Every number here is from the run's append-only ledger (run.jsonl). AI time is the time the AI was working on a prompt: from the human's prompt to the AI's done, with any gap over 15 min where no command ran (unobserved, not proven idle) cut out. @@ -17,7 +17,8 @@ One row per human prompt: the AI's time on it, unobserved gaps excluded by the h | Session | Prompt at | Done at | AI time min | Unobserved gap min | What | |---|---|---|---|---|---| | 1 | 2026-10-12T21:19:30Z | 2026-10-13T12:53:38Z | 503.8 | 430 | the first prompt |-| **all** | | | **503.8** | | |+| 2 | 2026-10-13T12:53:40Z | 2026-10-13T12:55:11Z | 1.5 | 0 | follow-up (no prompt mark; say `prompt --text` next time) |+| **all** | | | **505.3** | | |  ## Per step @@ -27,14 +28,14 @@ AI time only, the idle cut out. |---|---|---|---|---|---|---|---| | intake | 24.4 | 24.4 | 0.0 | 2 | 1 | 0 | 23.9 min | | placement | 20.9 | 8.1 | 12.8 | 17 | 3 | 2 | 5.7 min |-| routing | 151.2 | 7.2 | 143.9 | 32 | 3 | 0 | 4.8 min |+| routing | 151.5 | 7.2 | 144.3 | 32 | 3 | 0 | 4.8 min | | pours | 0.9 | 0.0 | 0.9 | 5 | 1 | 0 | 0.0 min | | current | 42.6 | 0.0 | 42.6 | 21 | 1 | 0 | 0.0 min | | thermal | 0.1 | 0.0 | 0.1 | 4 | 1 | 0 | 0.0 min | | finish | 33.5 | 0.0 | 33.5 | 20 | 1 | 0 | 0.0 min | | 3d | 3.6 | 0.0 | 3.6 | 6 | 1 | 0 | 0.0 min | | components | 10.8 | 7.5 | 3.3 | 9 | 1 | 0 | 6.0 min |-| export | 172.8 | 0.0 | 172.8 | 13 | 1 | 0 | 0.0 min |+| export | 173.9 | 0.0 | 173.9 | 16 | 1 | 0 | 0.0 min | | fields | 10.9 | 0.0 | 10.9 | 3 | 1 | 0 | 0.0 min | | libraries | 4.6 | 4.6 | 0.1 | 1 | 1 | 0 | 4.6 min | | models | 6.2 | 3.4 | 2.8 | 6 | 1 | 0 | 2.0 min |@@ -44,7 +45,7 @@ AI time only, the idle cut out. | silkscreen | 8.3 | 0.0 | 8.3 | 6 | 1 | 0 | 0.0 min | | test-plan | 11.0 | 9.2 | 1.8 | 5 | 1 | 0 | 9.1 min | | thermal-vias | 0.1 | 0.0 | 0.1 | 4 | 1 | 0 | 0.0 min |-| **total** | **503.8** | **64.8** | **439.0** | | | | |+| **total** | **505.3** | **64.8** | **440.5** | | | | |  ## Returns to earlier steps @@ -489,7 +490,7 @@ What this step does: The finish line for the human: Gerbers, drill, BOM and pick  What the AI said when it delivered (the video is at the top of this page): -> The OCP NIC 3.0 SFF (Supermicro AIOM) to 4x OCuLink riser is finished and published at https://wiki.adom.inc/john/oculink-aiom-riser: 6-layer 85 ohm board, 32 lanes skew-matched, DRC 0 errors / 0 unconnected on the JLC 6L rules, current and heat solved, silkscreen audited, Gerbers/drill/BOM/CPL exported and re-checked. The 18 'blank' clips are not blank: ffprobe was missing from PATH when each stopped, and ffprobe now counts 228 to 38515 frames in each (recorded per clip in run.json, adom/adom-aiflow#48). The composed run video is 60 s; the narrated build clips are on the page.+> Finished and published at https://wiki.adom.inc/john/oculink-aiom-riser (re-delivered after the land-vias evidence was refreshed). The 18 flagged clips have real frames (228 to 38515 each, recorded in run.json); the flags came from ffprobe missing at clip stop (adom/adom-aiflow#48).  ## Plan usage, the second cost line