board
OCuLink Riser for the Supermicro AIOM Slot
Public Unreviewedby John Lauer
Passive OCP NIC 3.0 SFF card that breaks a Supermicro AIOM slot's PCIe x16 into four OCuLink 4i ports (4 x4, Gen4): 6-layer, 85 ohm, length-matched, DRC-clean KiCad project with Gerbers, BOM and CPL.
← Commit history
aiflow run ocp-oculink-riser-claude-20261012-2119: thermal
3 files changed
+32−13
docs/runs/ocp-oculink-riser-claude-20261012-2119/README.md+32−13@@ -1,6 +1,6 @@ # AI Flow run: claude on board-0 -**Running**: step `current`, 165.0 min of AI time since the prompt (389.8 min on the wall clock). This page updates at every step change.+**Running**: step `thermal`, 220.7 min of AI time since the prompt (527.4 min on the wall clock). This page updates at every step change. 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. @@ -10,8 +10,8 @@ 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 | (open) | 165.0 | 225 | the first prompt |-| **all** | | | **165.0** | | |+| 1 | 2026-10-12T21:19:30Z | (open) | 220.7 | 307 | the first prompt |+| **all** | | | **220.7** | | | ## Per step @@ -21,9 +21,10 @@ 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 | 85.5 | 7.2 | 78.3 | 32 | 3 | 0 | 4.8 min |+| routing | 98.5 | 7.2 | 91.3 | 32 | 3 | 0 | 4.8 min | | pours | 0.9 | 0.0 | 0.9 | 5 | 1 | 0 | 0.0 min |-| current | 0.0 | 0.0 | 0.0 | 1 | 1 | 0 | 0.0 min |+| current | 42.6 | 0.0 | 42.6 | 21 | 1 | 0 | 0.0 min |+| thermal | 0.0 | 0.0 | 0.0 | 1 | 1 | 0 | 0.0 min | | components | 10.8 | 7.5 | 3.3 | 9 | 1 | 0 | 6.0 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 |@@ -31,7 +32,7 @@ AI time only, the idle cut out. | rules | 0.3 | 0.3 | 0.0 | 7 | 1 | 0 | 0.2 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** | **165.0** | **64.8** | **100.3** | | | | |+| **total** | **220.7** | **64.8** | **155.9** | | | | | ## Returns to earlier steps @@ -55,13 +56,13 @@ AI time only, the idle cut out. - 2026-10-13T03:46:43Z clip-start:pours-1 - 2026-10-13T03:49:09Z clip-start:outline-1 - 2026-10-13T03:49:18Z clip-start:current-1+- 2026-10-13T04:10:41Z clip guard: the current clip ran 21 min, past its 10 min budget twice over; stopped by the guard+- 2026-10-13T06:06:47Z artifact analysis-image for current-1: DC current density on all six copper layers: the 0.1 A +3V3 aux load peaks at 47 A/mm² on a 0.2 mm In4 trace, under the 60 A/mm² limit; 3 mW of Joule loss+- 2026-10-13T06:06:53Z clip-start:thermal-1 ## Where the board stands -- gate: 0 new DRC errors, 0 unconnected, null inherited-- landed live: 169 of 169 route entries-- pours (landed): 1 groups, failed []-- copper kept (mm2 per layer): {"B.Cu":7235.63,"F.Cu":5140.71,"In1.Cu":8012.11,"In2.Cu":6379.85,"In3.Cu":8012.11,"In4.Cu":6007.98}+- analyze-current: pass ## The steps on camera @@ -241,32 +242,50 @@ What this step does: Round the board's corners: every sharp outline corner becom What this step does: IPC-2221 on every loaded net, pour and via capacity, the same-layer rule; then the AI's own current density drawing and a walkthrough of the pours it judged +**This clip filmed nothing usable: no frames. It is kept as evidence and left out of the video.**+ **Clip: current, still recording (started 2026-10-13T03:49:18Z); it appears here when the step ends.** **Screenshot: the board when current began.**  +**The AI's drawing: DC current density on all six copper layers: the 0.1 A +3V3 aux load peaks at 47 A/mm² on a 0.2 mm In4 trace, under the 60 A/mm² limit; 3 mW of Joule loss**++++### thermal++What this step does: copper and vias at every hot tab against the rise budget; then the AI's own temperature rise drawing and a walkthrough of the pours it judged++**Clip: thermal, still recording (started 2026-10-13T06:06:53Z); it appears here when the step ends.**++**Screenshot: the board when thermal began.**+++ ## Plan usage, the second cost line Percent of each plan limit used, as the provider reports it, at the start of the run and at its end. | Provider | Limit | At start | At end | Used by this run | |---|---|---|---|---|-| claude | 5h | 2 % | 1 % | -1.0 % |+| claude | 5h | 2 % | 3 % | 1.0 % | | claude | Fable | 0 % | 0 % | 0.0 % | | claude | week | 0 % | 3 % | 3.0 % |-| codex | week | 49 % | 54 % | 5.0 % |+| codex | week | 49 % | 3 % | -46.0 % | *The limits are per account, not per run: every AI thread signed in as this user draws on the same numbers, so a run made while other threads were working shows their usage too. Read it as an upper bound unless this run was the only thread active.* ## Given back -4 issue(s) or PR(s) filed by this run's AI to make the tool better for every Adom user:+6 issue(s) or PR(s) filed by this run's AI to make the tool better for every Adom user: - issue https://wiki.adom.inc/adom/adom-aiflow/issues/45: etch planner: reversed top-face normal; TSSOP mark axis - issue https://wiki.adom.inc/adom/adom-aiflow/issues/47: rules install ignores layers; gate vs 6L pack; plan shape - issue https://wiki.adom.inc/adom/kicad-bridge/issues/125: courtyard check uses bounding boxes - issue https://wiki.adom.inc/adom/adom-symbol/issues/5: group gaps off grid+- issue https://wiki.adom.inc/adom/kicad-bridge/issues/126: IPC move drops polygon closing vertex -> lib_footprint_mismatch+- issue https://wiki.adom.inc/adom/adom-fields/issues/11: 6-layer stacks, PCG refinement, via ring lost at 0.2 mm Adom processes PRs within minutes during business hours: a non-stop PR intake runs all day.
docs/runs/ocp-oculink-riser-claude-20261012-2119/current-1-analysis-image-0.pngadded⋯ 1 unchanged line ⋯
docs/runs/ocp-oculink-riser-claude-20261012-2119/shot-thermal-1-start.pngadded⋯ 1 unchanged line ⋯