feat: add wiki knowledge layer (Phase 0 + Phase 1 seed)

Implements LLM-compiled wiki layer between raw session logs and live
CONTEXT.md, inspired by Karpathy's knowledge base workflow. Adds wiki/
directory structure, article templates, spec docs, and seeds first two
articles (Cascades of Tucson, GuruRMM) from 60+ session logs.

Updates CLAUDE.md to check wiki first on all context-loading triggers.
Captures verified ACG IP/hostname map and Neptune physical-location
clarification (Dataforth D2, subnet overlap TODO) in memory.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
2026-05-24 15:42:38 -07:00
parent 435e921300
commit cd80f5e447
19 changed files with 1533 additions and 6 deletions

View File

@@ -27,4 +27,11 @@ ACG office LAN is 172.16.0.0/22, routed via Tailscale through pfSense node `pfse
**VMs on Jupiter (virsh):** GuruRMM, Unifi, OwnCloud, Claude-Builder (running); Windows 7, Windows Server 2016, Windows Server 2016_Template (shut off).
**Why:** How to apply: see [[power-failure-runbook]] for full post-outage recovery steps.
**Neptune (ACG infra, physically at Dataforth D2):**
- neptune.acghosting.com | internal 172.16.3.11 | external 67.206.163.124
- Exchange Server 2016 — active mail server for multiple ACG-hosted clients
- Physically colocated at Dataforth's D2 facility, NOT at ACG office
- Access from ACG office: must route through D2TESTNAS (192.168.0.9) because Dataforth's UDM runs a subnet overlapping ACG office LAN (both use 172.16.x.x range), making direct routing ambiguous
- **TODO:** Resubnet Dataforth UDM to a non-overlapping range to fix routing and simplify Neptune access
**Why:** How to apply: see [[power-failure-runbook]] for full post-outage recovery steps. Neptune is NOT on ACG office LAN despite the 172.16.x.x IP — always route via D2TESTNAS or Dataforth VPN.