- freshness: 36 stale / 93 fresh / 3 no-date -> 0 stale / 129 fresh / 3 no-date of 132 (same-day report regenerated after the corrections, per pattern 13) - skills: 299 skills / 67 categories (count unchanged; generator arithmetic re-verified by hand against the live tree: 300 SKILL.md files - 1 nested duplicate = 299) - runbooks/test-openrouter: live fallback chain rewritten (primary back to smart-route/custom:omni-101; mimo-v2.5, stepfun, qwen3.5/ollama-cloud out; guacano + kilo-reflection-beam-free in); ollama.com dropped from the URL test list; guacano/litellm noted as internal + key-gated - comparisons/hermes-vs-nanobot: the 2026-10-20 'CT333 is zeroclaw in Proxmox naming' claim was itself wrong - pct list and hostname both return clawtest - incidents/2026-10-22-nous: refresh-token failure gone from logs; new signature 404 insufficient_credits_for_paid_model from auxiliary.pulse_memory (ninth slot, back on nous, paid model) - open item revised - incidents/2026-08-29-gmail: email crons now ok but root cause unfixed 74 days (himalaya message read still in fetch_newsletters.py; goimapnotify back up PID 441; monitor still paused) - 30 further pages re-verified live and de-flagged with dated probe notes (ct207 ingress, CT205 guanaco v0.8.15, CT270 nextcloud 33.0.2.2, headless stack, hermes-ui both hosts, systemd units + cgroup limits, terminal/tool_search/mnemosyne/custom_providers config blocks, ops profile still deleted, hosts/pve guest lists) - log.md addendum + index.md date bump; no page deleted, no secrets written
2.9 KiB
title, type, status, created, updated, verified_on, confidence, tags, sources
| title | type | status | created | updated | verified_on | confidence | tags | sources | |||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Guanaco | system | active | 2026-08-14 | 2026-11-11 | 2026-11-11 | high |
|
|
Guanaco
Purpose
LLM proxy/router providing model routing and tool-call formatting for the Ollama-based inference stack on CT205.
Current Configuration
- Host: CT205 (
ollamaLXC container) on Proxmox - Version: v0.8.15 (updated from v0.8.14 on 2026-08-14; verified at tag
v0.8.15, commit5df435e, 2026-08-14 16:06:13 UTC) - Repo path (on CT205):
/root/.guanaco/repo - API endpoint:
ollama:11434(DNS) /localhost:11434 - Key component:
cmdcode_client.py— Guanaco's tool-call formatting layer (DSML)
Version History
v0.8.15 (current, updated 2026-08-14)
- Changelog bump + DSML fixes — HEAD is tagged
v0.8.15(commit5df435e, "chore: bump to v0.8.15 + changelog"), built fromorigin/main/origin/develop. - Live probe 2026-10-20:
/root/.guanaco/repoon CT205 at tagv0.8.15; Ollama API onlocalhost:11434answers 200.
v0.8.14 (previous, 2026-08-14)
- DSML tag leakage fixes (cumulative across v0.8.12–v0.8.14):
- v0.8.12 — incomplete DSML blocks leaking raw tags as content
- v0.8.13 — comprehensive DSML tag leakage: double-pipe, bare fragments, solo
invoke - v0.8.14 —
<dsml_ignore>blocks, bare parameter values, stray>cleanup
- Dashboard performance fix (
analytics.py): fixed wrong column names in optimized history query, cached content size, stoppedSELECT *on history table - No new features, no breaking config changes — low-risk incremental bug-fix release
- Local
app.pymodification (working-tree change) survived the tag checkout intact
v0.8.11 (previous)
- Had known DSML tag leakage issues where malformed tool-call output could leak raw
<dsml_...>syntax into model context stream
Live probe 2026-11-11 — the v0.8.15 record holds.
/root/.guanaco/repoon CT205 (pct exec 205) still sits at tagv0.8.15, HEAD5df435e3de11a51401972696d47daf9144b0d140(the abbreviated5df435erecorded above), and the Ollama API onlocalhost:11434/api/versionreturns 200. CT205 (ollama) is running; its LAN address is192.168.178.158. Note a naming nuance this page does not carry: Hermes'sguacanoprovider points athttp://ollama:11000/v1, i.e. Guanaco's own proxy port, not Ollama's11434.
What DSML Is
DSML = "Daily Smart Messaging Log" — Guanaco's tool-call formatting layer for the cmdcode client. When a model emits a tool call, Guanaco formats it through DSML. Malformed output from the model could previously leak raw tags (<dsml_invoke>, bare > characters) into the conversation context, which confused downstream models.
Related
- infrastructure/proxmox — CT205 in LXC container table
- systems/ollama — Ollama inference stack (if exists)