state-hub/workplans/ADHOC-2026-06-04.md
tegwick 4f68c5609f
All checks were successful
CI Smoke / host-smoke (push) Successful in 0s
CI Smoke / container-smoke (push) Successful in 1s
fix(workplans): qualify ad-hoc identifiers with the repository prefix
`ADHOC-YYYY-MM-DD` is unique per date but not per repository, so any two repos
opening an ad-hoc on the same day collide. The 2026-08-26 fleet projection
reset refused 9 records for exactly this reason.

Canon (work-record-types_v0.1, CUST-WP-0066) settled the form as
`{PREFIX}-WP-ADHOC-YYYY-MM-DD`, filename unchanged, and grandfathered existing
ids on the condition they are never *silently* re-derived. This is the explicit
migration that clause allows for.

The hub id is derived from the record id, so a changed id is a different
record: stale state_hub_*_id fields are dropped and fix-consistency re-derives.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

Assistant: claude-code
Assistant-Model: opus
Assistant-Process: 2583210@bnt-lap001
Assistant-Session: f2bff2d5-e9b2-4338-92ca-10282a927006
2026-08-28 00:28:24 +02:00

32 lines
929 B
Markdown

---
id: STATE-WP-ADHOC-2026-06-04
type: workplan
title: "Ad hoc fixes - 2026-06-04"
domain: custodian
repo: state-hub
status: finished
owner: codex
topic_slug: custodian
created: "2026-06-04"
updated: "2026-06-04"
---
# Ad hoc fixes - 2026-06-04
## Fix Dashboard Overview API Loading
```task
id: STATE-WP-ADHOC-2026-06-04-T01
status: done
priority: high
```
The overview page reported `Dashboard data load failed: NetworkError when
attempting to fetch resource.` even when the API was healthy from Windows.
The root cause was brittle browser/API connection setup: the dashboard assumed
`http://127.0.0.1:8000`, while the API CORS defaults allowed only the exact
dashboard origins on port 3000.
Result: the dashboard now resolves its API base from the current browser host
with explicit query/storage/global overrides, and the API allows common local
Observable dashboard origins on ports 3000-3005, including IPv6 loopback.