- mcp-gateway.md: full rewrite for Bifrost at ai.nuclide.systems/mcp;
29 clients / ~760 tools; VK auth; n8n+shepard blocked on
streamable-HTTP; legacy gateway decommission checklist added
- connection-hosts.md: Bifrost at port 14003 is now ai.nuclide.systems;
LiteLLM demoted to internal-only; mcp.nuclide.systems marked pending
decommission; OIDC client 78c78998 flagged for removal
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
ct104-conf repo tracks /opt/stacks/ compose files and configs daily.
Bifrost and Open WebUI now covered.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- docs-server now runs on ops (192.168.1.8:13080), not dev (192.168.1.42)
- mkdocs.yml: fix site_url (was pointing at .111 instead of .42, now .8)
- mkdocs.yml: add all services added since last nav update (pocket-id,
backrest, databases, arcane, mcp-servers, llm-benchmark, RESUME, connection-hosts)
- portmap.md: move :13080 entry from CT 111 to CT 109 section; add Homarr :7575;
fix stale Promtail note → Alloy add-on
- README.md: update rendered docs URL to 192.168.1.8:13080
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Proxmox VE metrics via prometheus-pve-exporter on CT 109 :9221.
monitor@pve!prometheus token with Monitor (read-only) role.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Loki (CT 109 :3100, 30d retention) and Grafana Alloy deployed across
all 12 hosts. Portmap updated with new services and agent deployment notes.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- infra/connection-hosts.md: every host, LAN IP, port, and public URL
across all Proxmox guests, Docker services, network infra, and
external hardware; OIDC client registry; SSH cheat-sheet
- services/mcp-servers.md: all 27 MCP servers with full credentials,
upstream URLs, transport, group, gateway management API examples,
and gateway .env token inventory
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Add RESUME.md for cross-session continuity (open items, key state, constraints)
- claude-max-bridge: implement /v1/responses (OpenAI Responses API) with
previous_response_id chaining via server-side history injection into system prompt.
Root cause of "session already in use": CLI leaves JSONL in un-resumable
"dequeued" state after each --print run; fix avoids session reuse entirely.
Also fixed: assistant content must be array-of-blocks not plain string (silent
JS crash otherwise).
- LiteLLM: add pass_through_endpoints for /v1/responses → claude-max-bridge
- Storage, volumes, architecture docs reconciled (Vaultwarden → local zfs,
Pocket-ID backup, WAL-G fix, apps/ decommission, Nextcloud CIFS→NFS)
- Add ideas/, proxmox-memory-audit.md, llm-benchmark.md (new docs this session)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
fkrebs