Review, no switch. node-laptop for talos/titan is excluded from
FleetTargetDown. llama-straylight scrape uses params.model for
ornith-1.5-35b-a3b (router 400 without it; will load if cold).
Honcho workspace_name keep, node_exporter restart metrics,
drop min_over_time on rule 1, Watchdog heartbeat, pin tether
to b267e2f so labelled series exist and rule 2 can fire.
VictoriaMetrics on 127.0.0.1:8428. LoadCredential for the Mattermost
webhook and the sift scrape token. Honcho scrapes keep a closed metric
name set. Meta-alerts for target-down, VM size, orion disk. Dixie gets
node_exporter, nvidia_gpu_exporter, and llama-server --metrics.
Tether labelled series still wait on titan's fix. Rule 2 is written
against reason=client_disconnect so it stays silent until then.
NM dispatcher plus a boot oneshot keep the AX9L (mt7921u) primary and
bring up the on-box iwlwifi profile if the dongle is gone. Connection
PSKs stay on-box; this only selects the radio.
Pin follows approved CLI fail-closed for non-default HERMES_HOME.
Does not switch straylight or orion. ~/.local/bin/sift (e36da19)
still shadows until that binary is removed after the switch.
The unit package is not in systemPackages, so `sift keys` is only
reachable via the store path. Track services.sift.package so it
follows the pin. Lands on the next orion switch.
Sift P3 ships with sources off. SearXNG engine WARNING lines include
q=; LogLevelMax=err keeps those out of the journal. Brave scraper
stays disabled. Do not enable search sources in this commit.
Prefill ran in 2048-token scheduler steps of ~2.4 s; each decoding slot
gets one token per step, so guardian calls (16 tokens) waited behind
Honcho's 10-28k-token prompts: p90 10 s, max 14 s under two sift
digests (2026-09-23 05:50). ubatch is already 512, so prefill
throughput is unchanged; steps drop to ~0.6 s.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
The unified 96k pool overflowed ~every 2-3 min under Honcho load
(39 events 2026-09-23 00:50-04:28). Each overflow fails every in-flight
slot with 'Context size has been exceeded', so Honcho retries and the
guardians' calls die with it. KV is ~20 KB/token on this model; 128k
costs ~0.65 GB of the ~2.5 GB free.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Add the sift flake input at fac1462e7b3deb2082c9f6ae8dc4676fddf8d089
(git+ssh; git+https cannot auth on orion) and enable services.sift on
orion: loopback :8890, tailscale serve :8443 from the module, static
home WAN /32 in denyPrefixes. Keys stay on-box.
0.4.1 dropped the no-mmap option (router refused to start: "option 'no-mmap'
not recognized in preset '*'"); --load-mode none is the equivalent. All other
preset keys checked against 0.4.1's option list.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Kyle 2026-09-22: the shared CA was only for Metacircular services (system
trust store + the MCR podman registry cert). No host should still depend on
it; anything that does should fail loudly rather than keep trusting it.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Kyle 2026-09-22: tear down MCP across the fleet. Drops the mcp/mcpkg imports
(agent, mcp user, packages), the unikernel-host agent overrides and kvm group,
the mcp-br0 bridge + FORWARD drop, the low-port sysctl (only MCNS/mc-proxy
needed it; Mattermost binds 8065), MCP firewall ports (53, 8443, 9443, 9444,
9555; keeps 443 for tailscale serve and 8080 for open-webui) and the MCNS
nameservers/~mcp.metacircular.net domain. State under /srv/mcp is kept.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
A Honcho catch-up wave (48 deriver batches + 11 dreams + dialectic prefetches)
held all 6 slots with long thinking generations; tiny aux calls (title,
approval guardian) queued behind them and title_generation timed out at 60 s.
Two spare slots plus a bigger shared KV pool (so 6 long prompts can't exhaust
it). VRAM 9.7 GB.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
searx-init loads EnvironmentFile at spawn, so the secret must exist
before systemd starts that unit. Drop the racing oneshot. Make
tailscale-serve restart on NoState during switch.
kyle
