fix(alignment): correct tanko status - hybrid (DSH + Hermes), not DSH-only

PR #145 originally claimed 'the other 3 CTs are DSH-only' but all 4 agents
run a Hermes gateway. Only tanko additionally runs DSH, making it the hybrid
one. Fixed line 300 to say what the contract actually checks for each agent,
and fixed line 76 to stop asserting tanko's Hermes config is gone.

agent-health-check.prose.md

@@ -24,7 +24,7 @@ Runs every 4 hours (2, 6, 10, 14, 18, 22 UTC at :35) via cron (`35 2,6,10,14,18,
 ## Requires
 
 - **LiteLLM admin key** for key validation (retrieved from `/root/.pi/agent/env.sh`)
-- **SSH access** to GPU hosts (.8, .110, .15) and agent CTs (.122, .129, .114, .24)
+- **SSH access** to GPU hosts — `llmuser` on .8 (owns `llama-server`), `root` on .110 and .15 — and agent CTs (.122, .129, .114, .24)
 - **Python 3** for script execution
 - **Network access** to LiteLLM (:4000), GPU exporters (:9400), and gateway endpoints
 

audit-hermes-config.py

@@ -94,7 +94,16 @@ def audit(path):
         cfg = yaml.safe_load(f)
 
     model = cfg.get("model", {})
-    fb = cfg.get("fallback_providers", {})
+    fb_raw = cfg.get("fallback_providers", {})
+    # Normalize: fallback_providers may be a dict (single provider) or a list of dicts
+    # (one entry per fallback). Both shapes are valid; we must handle both without crashing.
+    if isinstance(fb_raw, dict):
+        fb_entries = [fb_raw]
+    elif isinstance(fb_raw, list):
+        fb_entries = fb_raw
+    else:
+        fb_entries = [fb_raw]  # Let it fail the check below as malformed
+    fb = fb_entries[0] if fb_entries else {}
     comp = cfg.get("compression", {})
     aux = cfg.get("auxiliary", {})
     deleg = cfg.get("delegation", {})
@@ -207,22 +216,32 @@ def audit(path):
         "Rule 14",
         f"delegation.provider must be 'harness' (got {deleg.get('provider')!r})",
     )
-    check(
+    # Check each fallback entry. A malformed entry (not a mapping) is a VIOLATION, not a crash.
-        fb.get("provider") == "deepseek",
+    for idx, entry in enumerate(fb_entries):
-        "Rule 14",
+        prefix = f"fallback_providers[{idx}]"
-        f"fallback_providers.provider must be 'deepseek' (got {fb.get('provider')!r}) — "
+        if not isinstance(entry, dict):
-        f"true fallback diversity, not same endpoint as primary",
+            check(
-    )
+                False,
-    check(
+                "Rule 14",
-        fb.get("model") == "deepseek-v4-flash",
+                f"{prefix} must be a mapping (got {type(entry).__name__})",
-        "Rule 14",
+            )
-        f"fallback_providers.model must be 'deepseek-v4-flash' (got {fb.get('model')!r})",
+            continue
-    )
+        check(
-    check(
+            entry.get("provider") == "deepseek",
-        fb.get("api_key_env") == "DEEPSEEK_API_KEY",
+            "Rule 14",
-        "Rule 14",
+            f"{prefix}.provider must be 'deepseek' (got {entry.get('provider')!r}) — "
-        f"fallback_providers.api_key_env must be DEEPSEEK_API_KEY (got {fb.get('api_key_env')!r})",
+            f"true fallback diversity, not same endpoint as primary",
-    )
+        )
+        check(
+            entry.get("model") == "deepseek-v4-flash",
+            "Rule 14",
+            f"{prefix}.model must be 'deepseek-v4-flash' (got {entry.get('model')!r})",
+        )
+        check(
+            entry.get("api_key_env") == "DEEPSEEK_API_KEY",
+            "Rule 14",
+            f"{prefix}.api_key_env must be DEEPSEEK_API_KEY (got {entry.get('api_key_env')!r})",
+        )
 
     # --- custom_providers sanity ---
     check(

contract-registry.yaml

@@ -643,7 +643,7 @@ contracts:
     timeout: 120
     requires:
     - Zulip API key for abiba-bot@chat.sysloggh.net
-    - SSH access to amdpve (192.168.68.15) for Tanko (CT 112) and the Agent Zero Docker host (.14)
+    - SSH access to minipve (192.168.68.12) for Tanko (CT 112) and the Agent Zero Docker host (.14)
   verification:
     postconditions:
     - check: bot registration active

disk-gc-threat-response.prose.md

@@ -414,7 +414,7 @@ one-off GPU builds. No automated post-migration cleanup was in place.
 | 108 | media | storepve | lxc | ✅ reachable |
 | 110 | gitea | minipve | lxc | ✅ reachable |
 | 111 | tdunna | **storepve** | lxc | ⛔ **REPORT-ONLY** (192.168.68.129, Theo's box — no GC at any level) |
-| 112 | tanko | amdpve | lxc | ✅ reachable |
+| 112 | tanko | minipve | lxc | ✅ reachable |
 | 113 | baggy | amdpve | lxc | ✅ reachable |
 | 115 | scottdenya | amdpve | lxc | ✅ reachable |
 | 116 | syslog-api | minipve | lxc | ✅ reachable |

hermes-agent-baseline.prose.md

@@ -70,10 +70,10 @@ Agent (systemd) → LITELLM_API_KEY → LiteLLM (:116/v1) → GPU (llama-server)
 
 ## Config Pattern — Mandatory Fields
 
-### For Hermes Agents (Mumuni, Koonimo)
+### For Hermes Agents (Mumuni, Koonimo, Tanko-hybrid)
 
 Every Hermes agent's `/root/.hermes/config.yaml` (or `/home/jerome/.hermes/config.yaml`) MUST have:
-(Tanko is excluded — migrated to DSH/DeepSeek Harness on 2026-08-27, no longer uses Hermes config.)
+(Tanko is hybrid — runs both DSH and Hermes since 2026-08-27, so its Hermes config is also checked.)
 
 ### 1. Main Model
 ```yaml
@@ -297,7 +297,7 @@ Run the consolidated health check:
 ```bash
 python3 /root/scripts/agent-health-check.py
 ```
-This validates all 4 LiteLLM keys, detects GPU port conflicts (ghost processes),
+This validates each agent's live LiteLLM key against the gateway, including tanko, which runs HYBRID (DSH + Hermes) since 2026-08-27; detects GPU port conflicts (ghost processes),
 verifies gateway liveness, confirms Zulip streaming (`edit_message` present),
 and counts recent errors. Non-disruptive — never restarts anything.
 

hermes-zulip-plugin.prose.md

@@ -55,7 +55,7 @@ connectivity recovery including end-to-end DM validation.
 
 | Host | CT | Proxmox | IP (direct) | Hermes Home | User |
 |------|-----|---------|-------------|-------------|------|
-| Tanko | CT112 | amdpve | 192.168.68.122 | /home/jerome/.hermes | jerome | *(DSH since 2026-08-27 — historical, plugin retired on this host)* |
+| Tanko | CT112 | minipve | 192.168.68.122 | /home/jerome/.hermes | jerome | *(DSH since 2026-08-27 — historical, plugin retired on this host)* |
 | Koby | CT111 | storepve | 192.168.68.129 | /root/.hermes | root |
 | Shumba | — | — | 192.168.68.119 | /home/lucky/.hermes | lucky |
 
@@ -72,7 +72,7 @@ connectivity recovery including end-to-end DM validation.
 ### Step 1: Resolve Target
 
 Map `target` to host, CT ID, hermes_home, and user from the live-state table.
-For CT112 route through `ssh root@amdpve`; for CT111 route through `ssh root@storepve` — then `pct exec <id>`.
+For CT112 route through `ssh root@minipve`; for CT111 route through `ssh root@storepve` — then `pct exec <id>`.
 
 ### Step 2: Pull Latest Plugin Source
 

hermes-zulip-restore.prose.md

@@ -67,7 +67,7 @@ gateway restart, and connection validation.
 ### Step 1: Locate Target
 
 Map `target` to connectivity parameters from the live-state table above.
-For CT112 route through `ssh root@amdpve`; for CT111 route through `ssh root@storepve` — then `pct exec <id>`.
+For CT112 route through `ssh root@minipve`; for CT111 route through `ssh root@storepve` — then `pct exec <id>`.
 
 ### Step 2: Deploy Zulip Adapter
 

infrastructure-control.prose.md

@@ -105,8 +105,8 @@ description: >
 
 | Node | IP | CPU | RAM | VMs/CTs | Role |
 |------|----|-----|-----|---------|------|
-| minipve | .12 | 16C | 30GB | abiba, authentik, gitea, syslog-api, infisical-vault, jitsi | Auth, git, messaging |
+| minipve | .12 | 16C | 30GB | abiba, tanko, authentik, gitea, syslog-api, infisical-vault, jitsi | Auth, git, messaging |
-| amdpve | .15 | 32C | 62GB | kagentz, tanko, baggy, scottdenya, adguard2 | Agents, compute |
+| amdpve | .15 | 32C | 62GB | kagentz, baggy, scottdenya, adguard2 | Agents, compute |
 | storepve | .6 | 28C | 31GB | docker-vm, ra-h-os, PBS, media, jdownloader, zulip, tdunna | Docker, storage, chat |
 | acerpve | .9 | 28C | 31GB | llm-gpu | GPU VMs |
 | ocupve | .5 | 12C | 14GB | ocu-llm | GPU VMs |
@@ -682,7 +682,7 @@ ssh root@192.168.68.110 "systemctl restart llama-server"
 | 109 | docker-vm | storepve | .7 | Docker host | ❌ |
 | 110 | gitea | minipve | **.17** | Git | ❌ |
 | 111 | tdunna | storepve | .129 | Hermes agent — ⛔ REPORT-ONLY (Theo's box, no GC) | ✅ |
-| 112 | tanko | amdpve | .122 | DSH (DeepSeek Harness) agent | ✅ |
+| 112 | tanko | minipve | .122 | DSH (DeepSeek Harness) agent | ✅ |
 | 113 | baggy | amdpve | .114 | Hermes agent | ✅ |
 | 115 | scottdenya | amdpve | .75 | Denya OneCare | ❌ |
 | 116 | syslog-api | minipve | .116 | LiteLLM + Grafana | ❌ |
@@ -712,7 +712,7 @@ Source of truth: `/root/scripts/pct-run.sh` or `prose-contracts/scripts/pct-run.
 | 100 | abiba | minipve | `pct-run 100` |
 | 105 | kagentz | amdpve | `pct-run 105` |
 | 111 | tdunna | storepve | `pct-run 111` (⛔ report-only — no GC) |
-| 112 | tanko | amdpve | `pct-run 112` |
+| 112 | tanko | minipve | `pct-run 112` |
 | 113 | baggy | amdpve | `pct-run 113` |
 | 115 | scottdenya | amdpve | `pct-run 115` |
 | 104 | authentik | minipve | `pct-run 104` |

infrastructure-update.prose.md

@@ -59,7 +59,7 @@ Before ANY update wave:
 | ocupve (.5) | Proxmox node | `apt update && apt upgrade -y` | 5 min |
 | CT 100 (.24) | Abiba (pi) | `apt update && apt upgrade -y` | 3 min |
 | CT 116 (.116) | syslog-api (LiteLLM host) | `apt update && apt upgrade -y` | 3 min |
-| CT 112 (tanko, amdpve) | Tanko | `apt update && apt upgrade -y` | 3 min |
+| CT 112 (tanko, minipve) | Tanko | `apt update && apt upgrade -y` | 3 min |
 | CT 105 (kagentz, minipve) | Mumuni | `apt update && apt upgrade -y` | 3 min |
 | VM 101 (.8) | llm-gpu (RTX 3090) | `apt update && apt upgrade -y` | 3 min |
 | VM 103 (.110) | ocu-llm (RTX 5070) | `apt update && apt upgrade -y` | 3 min |

scripts/agent-health-check.py

@@ -50,6 +50,11 @@ Changelog:
     (kagentz CT 105 on minipve, .14, dedicated `hermes` user) and is monitored
     from her side. This script must not probe mumuni or .24 — the v2 changelog
     roster line was the last reference still placing her at .24 / CT100.
+  v6 (2026-09-28): .8 GPU health probe now runs as `llmuser` instead of `root`.
+    Root SSH to .8 was lost when the guest was rebuilt, so every .8 leg read as
+    UNREACHABLE for a healthy host. llmuser owns llama-server and can read
+    `systemctl is-active`, `systemctl show -p MainPID`, and the :8080 pid.
+    .110 and .15 keep the default `root` user.
 """
 
 import subprocess, json, sys, os, time, re, io, contextlib
@@ -70,7 +75,7 @@ PVE_NODES = {
 
 # Agent definitions: ct, host, user, pve_node, vault_key_name
 AGENTS = {
-    "tanko":   {"ct": 112, "host": "192.168.68.122", "user": "jerome", "pve": "amdpve",  "vault_key": "TANKO_LITELLM_API_KEY", "runtime": "dsh"},
+    "tanko":   {"ct": 112, "host": "192.168.68.122", "user": "jerome", "pve": "minipve", "vault_key": "TANKO_LITELLM_API_KEY", "runtime": "dsh"},
     # abiba = pi agent (.24) — no vault key; its LiteLLM key is read from its
     # local env file (key_env below), not from the shared vault or .bashrc.
     # runtime=pi: abiba has run pi-only since the harness purge. There is no
@@ -95,7 +100,7 @@ AGENTS = {
 #   .110 rtx5070 (ocu-llm VM) -> llama-server.service    (active)
 #   .15  strixhalo (amdpve)   -> strix-server.service    (active)
 GPU_HOSTS = {
-    "gpu-rtx3090 (.8)":     {"host": "192.168.68.8",   "port": 8080, "service": "llama-chat-api.service"},
+    "gpu-rtx3090 (.8)":     {"host": "192.168.68.8",   "port": 8080, "service": "llama-chat-api.service", "user": "llmuser"},
     "gpu-rtx5070 (.110)":   {"host": "192.168.68.110", "port": 8080, "service": "llama-server.service"},
     "gpu-strixhalo (.15)":  {"host": "192.168.68.15",  "port": 8080, "service": "strix-server.service"},
 }
@@ -300,13 +305,14 @@ def check_gpu_ports():
         host = gpu["host"]
         port = gpu["port"]
         svc = gpu["service"]
+        user = gpu.get("user", "root")  # default root, overridden per-host where needed
 
         # `systemctl is-active` exits non-zero when the unit is inactive or
         # missing, which the ssh() helper would swallow as an SSH failure and
         # report as UNREACHABLE. `|| true` keeps the real state word so we can
         # tell "unit inactive" from "host unreachable".
-        svc_status = ssh(host, f"systemctl is-active {svc} || true")
+        svc_status = ssh(host, f"systemctl is-active {svc} || true", user=user)
-        port_owner = ssh(host, f"ss -tlnp 2>/dev/null | grep -Po ':{port}\\s+.*pid=\\K[0-9]+' | head -1")
+        port_owner = ssh(host, f"ss -tlnp 2>/dev/null | grep -Po ':{port}\\s+.*pid=\\K[0-9]+' | head -1", user=user)
 
         if not svc_status:
             print(f"  ❌ {label}: UNREACHABLE")
@@ -317,14 +323,14 @@ def check_gpu_ports():
             print(f"  ❌ {label}: PORT {port} NOT LISTENING (svc={svc_status})")
             FAIL.append(f"gpu-no-port:{label}")
         elif svc_status != "active":
-            svc_pid = ssh(host, f"systemctl show {svc} -p MainPID 2>/dev/null | cut -d= -f2")
+            svc_pid = ssh(host, f"systemctl show {svc} -p MainPID 2>/dev/null | cut -d= -f2", user=user)
             if svc_pid and port_owner != svc_pid:
                 print(f"  ❌ {label}: GHOST PROCESS — port owned by pid {port_owner}, svc pid {svc_pid} (svc={svc_status})")
                 FAIL.append(f"gpu-ghost:{label}:{port_owner}")
             else:
                 print(f"  ⚠️  {label}: svc={svc_status}, port owned by {port_owner}")
         else:
-            health = ssh(host, f"curl -s --max-time 5 http://localhost:{port}/health")
+            health = ssh(host, f"curl -s --max-time 5 http://localhost:{port}/health", user=user)
             if health and '"status":"ok"' in health:
                 print(f"  ✅ {label}: healthy (pid={port_owner})")
             elif health and '"status":"no slot available"' in health:

scripts/disk-gc-scan.py

@@ -101,8 +101,6 @@ GUESTS: list[Guest] = [
     # amdpve (192.168.68.15)
     Guest(ct_id="105", hostname="kagentz", ip="192.168.68.105", node="amdpve",
           access_method="ssh-host", probe_target="kagentz (CT 105, amdpve)"),
-    Guest(ct_id="112", hostname="tanko", ip="192.168.68.112", node="amdpve",
-          access_method="pct-run", probe_target="tanko (CT 112, amdpve)"),
     Guest(ct_id="113", hostname="baggy", ip="192.168.68.113", node="amdpve",
           access_method="pct-run", probe_target="baggy (CT 113, amdpve)"),
     Guest(ct_id="115", hostname="scottdenya", ip="192.168.68.115", node="amdpve",
@@ -110,6 +108,8 @@ GUESTS: list[Guest] = [
     Guest(ct_id="120", hostname="adguard2", ip="192.168.68.120", node="amdpve",
           access_method="pct-run", probe_target="adguard2 (CT 120, amdpve)"),
     # minipve (192.168.68.12)
+    Guest(ct_id="112", hostname="tanko", ip="192.168.68.112", node="minipve",
+          access_method="pct-run", probe_target="tanko (CT 112, minipve)"),
     Guest(ct_id="100", hostname="abiba", ip="192.168.68.100", node="minipve",
           access_method="pct-run", probe_target="abiba (CT 100, minipve)"),
     Guest(ct_id="102", hostname="adguard", ip="192.168.68.102", node="minipve",

scripts/pct-run.sh

@@ -12,7 +12,6 @@ set -euo pipefail
 declare -A CT_NODES=(
     # amdpve (192.168.68.15)
     [105]=amdpve    # kagentz (was hwepve — corrected 2026-09-12; live per pvesh)
-    [112]=amdpve    # tanko
     [113]=amdpve    # baggy
     [115]=amdpve    # scottdenya
     [120]=amdpve    # adguard2 (added 2026-09-12)
@@ -21,6 +20,7 @@ declare -A CT_NODES=(
     [102]=minipve   # adguard (was acerpve)
     [104]=minipve   # authentik
     [110]=minipve   # gitea
+    [112]=minipve   # tanko (was amdpve — migrated 2026-09-27; live per pvesh)
     [116]=minipve   # syslog-api
     [119]=minipve   # infisical-vault
     # storepve (192.168.68.6)

scripts/prose-ai-review.sh

@@ -47,8 +47,8 @@ You are a code reviewer for OpenProse infrastructure contracts in the Syslog Sol
 The infrastructure-control.prose.md contract is the canonical reference for the cluster topology:
 
 **Proxmox Cluster "Tabiri" (5 nodes):**
-- amdpve (192.168.68.15): kagentz, tanko, baggy, scottdenya, adguard2
+- amdpve (192.168.68.15): kagentz, baggy, scottdenya, adguard2
-- minipve (192.168.68.12): abiba, adguard, authentik, gitea, syslog-api, infisical-vault
+- minipve (192.168.68.12): abiba, tanko, adguard, authentik, gitea, syslog-api, infisical-vault
 - storepve (192.168.68.6): docker-vm, ra-h-os, PBS, media, jdownloader, zulip, tdunna
 - acerpve (192.168.68.9): llm-gpu
 - ocupve (192.168.68.5): ocu-llm

scripts/zulip-monitor.sh

@@ -135,16 +135,16 @@ case "$PI_VERDICT" in
 esac
 # -- abiba-leg-end
 
-# ── Platform B: Tanko (DSH dsh-web on amdpve CT 112) ──
+# ── Platform B: Tanko (DSH dsh-web on minipve CT 112) ──
 # Direct SSH to 192.168.68.122 is not a dependency of this monitor — per-worker
-# key availability varies — so probes run from the amdpve vantage via `pct exec`.
+# key availability varies — so probes run from the minipve vantage via `pct exec`.
-# Tanko's Zulip gateway runs as the dsh-web systemd unit inside CT 112 on amdpve
+# Tanko's Zulip gateway runs as the dsh-web systemd unit inside CT 112 on minipve
-# (192.168.68.15). The gateway binds 127.0.0.1:3080 loopback-only by design — a
+# (192.168.68.12). The gateway binds 127.0.0.1:3080 loopback-only by design — a
 # remote :3080 probe is refused and is NOT a fault.
-TANKO_SVC=$(ssh -o StrictHostKeyChecking=no -o ConnectTimeout=5 root@192.168.68.15 \
+TANKO_SVC=$(ssh -o StrictHostKeyChecking=no -o ConnectTimeout=5 root@192.168.68.12 \
   "pct exec 112 -- systemctl is-active dsh-web" 2>/dev/null || true)
 [ -n "$TANKO_SVC" ] || TANKO_SVC="unknown"
-TANKO_HTTP=$(ssh -o StrictHostKeyChecking=no -o ConnectTimeout=5 root@192.168.68.15 \
+TANKO_HTTP=$(ssh -o StrictHostKeyChecking=no -o ConnectTimeout=5 root@192.168.68.12 \
   "pct exec 112 -- curl -s --connect-timeout 5 --max-time 10 -o /dev/null -w '%{http_code}' http://127.0.0.1:3080/" 2>/dev/null || true)
 [ -n "$TANKO_HTTP" ] || TANKO_HTTP="000"
 

tests/test_audit_hermes_fallback_list_shape.py

@@ -0,0 +1,236 @@
+"""Regression test for the fallback_providers list-shape crash in audit-hermes-config.py.
+
+WHY THIS FILE EXISTS: audit-hermes-config.py assumed `fallback_providers` was always a dict
+(single provider). Two live agents (koby, koonimo) carry it as a LIST of dicts (one entry per
+fallback), so the script crashed with:
+
+    File "audit-hermes-config.py", line 211, in audit
+        fb.get("provider") == "deepseek",
+    AttributeError: 'list' object has no attribute 'get'
+
+Both are REAL agent configs, so this is not a malformed-input case — the script simply could not
+audit two of the four agents it exists to audit. Until fixed, the key-hygiene check had no
+coverage for half the fleet while appearing to run.
+
+These tests execute the real CLI (`python3 audit-hermes-config.py <config>`) and assert:
+1. A config whose `fallback_providers` is a LIST of valid dicts does NOT crash (exit code is 0 or 1,
+   never a traceback/AttributeError).
+2. A config whose `fallback_providers` contains a MALFORMED entry (a list element that is not a
+   mapping) reports a VIOLATION naming the offending entry, NOT an uncaught exception.
+3. The dict shape still works (existing tests must stay green).
+
+No network, vault, or SSH access is required.
+"""
+from __future__ import annotations
+
+import pathlib
+import subprocess
+import sys
+
+ROOT = pathlib.Path(__file__).resolve().parent.parent
+AUDIT = ROOT / "audit-hermes-config.py"
+
+# A valid config where fallback_providers is a LIST of dicts (the real koby/koonimo shape).
+# One entry, well-formed: provider=deepseek, model=deepseek-v4-flash, api_key_env=DEEPSEEK_API_KEY.
+# This must produce a real verdict (PASS or FAIL) without crashing.
+LIST_SHAPE_VALID = """
+model:
+  api_key: ""
+  api_key_env: LITELLM_API_KEY
+  base_url: http://192.168.68.116/litellm/v1
+  max_tokens: 4096
+  default: syslog-auto
+  provider: harness
+fallback_providers:
+  - provider: deepseek
+    model: deepseek-v4-flash
+    api_key_env: DEEPSEEK_API_KEY
+compression:
+  model: syslog-auto
+  provider: harness
+  threshold: 0.65
+  max_context_window: 131072
+auxiliary:
+  vision:
+    model: gpu-vision
+    provider: harness
+  web_extract:
+    model: gpu-vision
+    provider: harness
+  compression:
+    model: syslog-auto
+    provider: harness
+delegation:
+  provider: harness
+custom_providers:
+  - name: harness
+    key_env: LITELLM_API_KEY
+    base_url: http://192.168.68.116/litellm/v1
+"""
+
+# A valid config where fallback_providers is a LIST with TWO entries (multiple fallbacks).
+# Both entries well-formed. Must not crash and should produce a real verdict.
+LIST_SHAPE_MULTI = """
+model:
+  api_key: ""
+  api_key_env: LITELLM_API_KEY
+  base_url: http://192.168.68.116/litellm/v1
+  max_tokens: 4096
+  default: syslog-auto
+  provider: harness
+fallback_providers:
+  - provider: deepseek
+    model: deepseek-v4-flash
+    api_key_env: DEEPSEEK_API_KEY
+  - provider: deepseek
+    model: deepseek-v4-flash
+    api_key_env: DEEPSEEK_API_KEY
+compression:
+  model: syslog-auto
+  provider: harness
+  threshold: 0.65
+  max_context_window: 131072
+auxiliary:
+  vision:
+    model: gpu-vision
+    provider: harness
+  web_extract:
+    model: gpu-vision
+    provider: harness
+  compression:
+    model: syslog-auto
+    provider: harness
+delegation:
+  provider: harness
+custom_providers:
+  - name: harness
+    key_env: LITELLM_API_KEY
+    base_url: http://192.168.68.116/litellm/v1
+"""
+
+# A config where fallback_providers is a LIST containing a MALFORMED entry:
+# one element is a plain string, not a mapping. The checker must report a VIOLATION
+# naming the offending entry (fallback_providers[1]) and NOT crash.
+LIST_SHAPE_MALFORMED = """
+model:
+  api_key: ""
+  api_key_env: LITELLM_API_KEY
+  base_url: http://192.168.68.116/litellm/v1
+  max_tokens: 4096
+  default: syslog-auto
+  provider: harness
+fallback_providers:
+  - provider: deepseek
+    model: deepseek-v4-flash
+    api_key_env: DEEPSEEK_API_KEY
+  - "not-a-mapping"
+compression:
+  model: syslog-auto
+  provider: harness
+  threshold: 0.65
+  max_context_window: 131072
+auxiliary:
+  vision:
+    model: gpu-vision
+    provider: harness
+  web_extract:
+    model: gpu-vision
+    provider: harness
+  compression:
+    model: syslog-auto
+    provider: harness
+delegation:
+  provider: harness
+custom_providers:
+  - name: harness
+    key_env: LITELLM_API_KEY
+    base_url: http://192.168.68.116/litellm/v1
+"""
+
+# The original DICT shape (single provider) must still work — existing behaviour preserved.
+DICT_SHAPE_VALID = """
+model:
+  api_key: ""
+  api_key_env: LITELLM_API_KEY
+  base_url: http://192.168.68.116/litellm/v1
+  max_tokens: 4096
+  default: syslog-auto
+  provider: harness
+fallback_providers:
+  provider: deepseek
+  model: deepseek-v4-flash
+  api_key_env: DEEPSEEK_API_KEY
+compression:
+  model: syslog-auto
+  provider: harness
+  threshold: 0.65
+  max_context_window: 131072
+auxiliary:
+  vision:
+    model: gpu-vision
+    provider: harness
+  web_extract:
+    model: gpu-vision
+    provider: harness
+  compression:
+    model: syslog-auto
+    provider: harness
+delegation:
+  provider: harness
+custom_providers:
+  - name: harness
+    key_env: LITELLM_API_KEY
+    base_url: http://192.168.68.116/litellm/v1
+"""
+
+
+def _run_config(tmp_path, name, text):
+    cfg = tmp_path / name
+    cfg.write_text(text)
+    proc = subprocess.run(
+        [sys.executable, str(AUDIT), str(cfg)],
+        capture_output=True, text=True,
+    )
+    return proc.returncode, proc.stdout, proc.stderr
+
+
+def test_list_shape_single_entry_does_not_crash(tmp_path):
+    """A LIST with one valid dict must not raise AttributeError; exit 0 (PASS)."""
+    code, out, err = _run_config(tmp_path, "list-single.yaml", LIST_SHAPE_VALID)
+    # Must NOT be a crash (traceback). A clean run exits 0 (PASS) or 1 (FAIL), never 2+ (exception).
+    assert code in (0, 1), f"Expected clean exit 0 or 1, got {code}\nSTDOUT:\n{out}\nSTDERR:\n{err}"
+    assert "AttributeError" not in err, f"Crashed with AttributeError:\n{err}"
+    assert "Traceback" not in err, f"Crashed with uncaught exception:\n{err}"
+    # The valid single-entry list should PASS (all rules satisfied).
+    assert code == 0, f"Expected PASS but got {code}\n{out}"
+    assert "RESULT: PASS" in out
+
+
+def test_list_shape_multiple_entries_does_not_crash(tmp_path):
+    """A LIST with two valid dicts must not raise AttributeError; exit 0 (PASS)."""
+    code, out, err = _run_config(tmp_path, "list-multi.yaml", LIST_SHAPE_MULTI)
+    assert code in (0, 1), f"Expected clean exit 0 or 1, got {code}\nSTDOUT:\n{out}\nSTDERR:\n{err}"
+    assert "AttributeError" not in err, f"Crashed with AttributeError:\n{err}"
+    assert "Traceback" not in err, f"Crashed with uncaught exception:\n{err}"
+    assert code == 0, f"Expected PASS but got {code}\n{out}"
+    assert "RESULT: PASS" in out
+
+
+def test_list_shape_malformed_entry_reports_violation_not_crash(tmp_path):
+    """A LIST containing a non-mapping element must be a reported VIOLATION, not a crash."""
+    code, out, err = _run_config(tmp_path, "list-malformed.yaml", LIST_SHAPE_MALFORMED)
+    # Must NOT be a crash.
+    assert "AttributeError" not in err, f"Crashed with AttributeError:\n{err}"
+    assert "Traceback" not in err, f"Crashed with uncaught exception:\n{err}"
+    # Should be a FAIL (exit 1) because the malformed entry is a violation.
+    assert code == 1, f"Expected FAIL (exit 1) but got {code}\n{out}"
+    assert "RESULT: FAIL" in out
+    # The violation must name the offending entry (fallback_providers[1]).
+    assert "fallback_providers[1]" in out, f"Violation did not name the offending entry:\n{out}"
+
+
+def test_dict_shape_still_passes(tmp_path):
+    """The original DICT shape (single provider) must still PASS — existing behaviour preserved."""
+    code, out, err = _run_config(tmp_path, "dict-valid.yaml", DICT_SHAPE_VALID)
+    assert code == 0, f"Expected PASS but got {code}\n{out}\nSTDERR:\n{err}"
+    assert "RESULT: PASS" in out

tests/test_mumuni_monitor_removal.py

@@ -49,7 +49,7 @@ HEALTH_CONTRACT = ROOT / "zulip-health.prose.md"
 CONNECTED_FIXTURE = ROOT / "tests" / "fixtures" / "zulip-health-connected.json"
 
 MUMUNI_IP = "192.168.68.24"       # Mumuni's old (decommissioned) deployment
-TANKO_VANTAGE = "192.168.68.15"   # amdpve — Tanko CT 112 via pct exec
+TANKO_VANTAGE = "192.168.68.12"   # minipve — Tanko CT 112 via pct exec
 AGENT_ZERO_HOST = "192.168.68.14"  # kagentz host, Agent Zero docker
 
 
@@ -82,7 +82,7 @@ done
 printf '%s\n' "$host" >> "$RECORD_DIR/ssh.hosts"
 cmd="${*: -1}"
 case "$host" in
-  192.168.68.15)
+  192.168.68.12)
     case "$cmd" in
       *"systemctl is-active"*) printf '%s' "$TANKO_SVC" ;;
       *curl*)                  printf '%s' "$TANKO_HTTP" ;;

tests/test_probe_drift.py

@@ -104,6 +104,59 @@ def test_koby_ct111_is_on_storepve(ahc):
     assert ahc.AGENTS["koby"]["pve"] == "storepve"
 
 
+def test_tanko_ct112_is_probed_on_minipve(ahc, monkeypatch, capsys):
+    # CT 112 (tanko) was live-migrated to minipve (.12) on 2026-09-27; the
+    # amdpve mapping made `pct status 112` fail and read as ct-unreachable.
+    # Execute the probe and assert the host the script actually contacts.
+    probes = []
+    monkeypatch.setattr(
+        ahc, "ssh",
+        lambda host, cmd, user="root": probes.append((host, cmd)) or "status: running",
+    )
+    ahc.FAIL.clear()
+    ahc.REPORT_ONLY.clear()
+    try:
+        ahc.check_ct_liveness()
+        tanko_hosts = [h for h, cmd in probes if cmd == "pct status 112 2>/dev/null"]
+        assert tanko_hosts == ["192.168.68.12"]
+    finally:
+        ahc.FAIL.clear()
+        ahc.REPORT_ONLY.clear()
+
+
+def test_gpu_rtx3090_probe_uses_llmuser_not_root(ahc, monkeypatch, capsys):
+    # 2026-09-28: root SSH to .8 was lost when the guest was rebuilt; llmuser
+    # owns llama-server and can read systemctl status and the :8080 pid. A root
+    # probe reads as UNREACHABLE for a healthy host (the reported bug). Execute
+    # check_gpu_ports() against an SSH boundary that only accepts llmuser@.8 and
+    # assert the .8 leg does not produce the false UNREACHABLE failure.
+    seen = []
+
+    def fake_ssh(host, cmd, user="root"):
+        seen.append((host, user))
+        if host == "192.168.68.8" and user != "llmuser":
+            return None  # root SSH denied -> baseline false UNREACHABLE
+        if cmd.startswith("systemctl is-active"):
+            return "active"
+        if cmd.startswith("ss -tlnp"):
+            return "48351"
+        if cmd.startswith("curl"):
+            return '{"status":"ok"}'
+        return None
+
+    monkeypatch.setattr(ahc, "ssh", fake_ssh)
+    ahc.FAIL.clear()
+    try:
+        ahc.check_gpu_ports()
+        out = capsys.readouterr().out
+        assert "gpu-unreachable:192.168.68.8" not in ahc.FAIL
+        assert "\u2705 gpu-rtx3090 (.8): healthy" in out
+        assert ("192.168.68.8", "llmuser") in seen
+        assert not any(host == "192.168.68.8" and user == "root" for host, user in seen)
+    finally:
+        ahc.FAIL.clear()
+
+
 def test_report_only_legs_never_count_as_failures(ahc):
     for agent, report_only in (("koby", True), ("koonimo", False), ("tanko", False)):
         ahc.FAIL.clear()

tests/test_zulip_kagentz_legs.py

@@ -34,7 +34,7 @@ ROOT = pathlib.Path(__file__).resolve().parents[1]
 ZULIP_MONITOR = ROOT / "scripts" / "zulip-monitor.sh"
 CONNECTED_FIXTURE = ROOT / "tests" / "fixtures" / "zulip-health-connected.json"
 
-TANKO_VANTAGE = "192.168.68.15"   # amdpve — Tanko CT 112 via pct exec
+TANKO_VANTAGE = "192.168.68.12"   # minipve — Tanko CT 112 via pct exec
 AGENT_ZERO_HOST = "192.168.68.14"  # kagentz host, Agent Zero docker
 
 
@@ -52,7 +52,7 @@ done
 printf '%s\n' "$host" >> "$RECORD_DIR/ssh.hosts"
 cmd="${*: -1}"
 case "$host" in
-  192.168.68.15)
+  192.168.68.12)
     case "$cmd" in
       *"systemctl is-active"*) printf '%s' "$TANKO_SVC" ;;
       *curl*)                  printf '%s' "$TANKO_HTTP" ;;

zulip-health.prose.md

@@ -28,7 +28,7 @@ session start.
 ## Requires
 
 - **Zulip API key** for `abiba-bot@chat.sysloggh.net` in `$ZULIP_API_KEY`
-- **SSH access** to amdpve (192.168.68.15) for Tanko — CT 112 reached via `pct exec` (direct SSH to .122 is not a dependency of this contract: per-worker key availability varies); and the Agent Zero Docker host (192.168.68.14)
+- **SSH access** to minipve (192.168.68.12) for Tanko — CT 112 reached via `pct exec` (direct SSH to .122 is not a dependency of this contract: per-worker key availability varies); and the Agent Zero Docker host (192.168.68.14)
 - **PM2** on localhost for pi process management
 - **Network access** to `chat.sysloggh.net`, `kagentz.sysloggh.net` (C3 public path), `localhost:9200`
 - **Write access** to `/root/zulip-health-monitor.log` and `/tmp/zulip-monitor-debounce`
@@ -228,20 +228,20 @@ grep -a "Finalized\|Failed to finalize" /root/.pm2/logs/abiba-zulip-out.log | ta
 | Crash loop >10/h | Alert user |
 
 
-### Step 3: Platform B — Tanko (DSH on amdpve CT 112)
+### Step 3: Platform B — Tanko (DSH on minipve CT 112)
 
 Mumuni is out of scope for this host (see the note above): she runs on her own
 container and is monitored on her side.
 
 Tanko runs on DSH (DeepSeek Harness) — it no longer runs a Hermes gateway, so
 there is no `~/.hermes/gateway_state.json` on CT 112. Tanko's Zulip gateway runs
-as the `dsh-web` systemd unit inside **CT 112**, which resides on the **amdpve**
+as the `dsh-web` systemd unit inside **CT 112**, which resides on the **minipve**
-PVE host (**192.168.68.15**). Direct SSH to 192.168.68.122 is not a dependency
+PVE host (**192.168.68.12**). Direct SSH to 192.168.68.122 is not a dependency
 of this contract — per-worker key availability varies — so CT 112 probes run
-from the amdpve vantage via `pct exec`:
+from the minipve vantage via `pct exec`:
 
 ```bash
-ssh root@192.168.68.15 "pct exec 112 -- <command>"
+ssh root@192.168.68.12 "pct exec 112 -- <command>"
 ```
 
 > **By design (verified 2026-09-08):** the `dsh-web` gateway binds
@@ -253,7 +253,7 @@ ssh root@192.168.68.15 "pct exec 112 -- <command>"
 **B1: Gateway Service State (Tanko)**
 
 ```bash
-ssh root@192.168.68.15 "pct exec 112 -- systemctl is-active dsh-web"
+ssh root@192.168.68.12 "pct exec 112 -- systemctl is-active dsh-web"
 ```
 
 Expected: `active`. Anything else → gateway service down → apply the Tanko heal
@@ -262,7 +262,7 @@ Expected: `active`. Anything else → gateway service down → apply the Tanko h
 **B2: Gateway HTTP Liveness (Tanko — loopback-only :3080)**
 
 ```bash
-ssh root@192.168.68.15 "pct exec 112 -- curl -s --connect-timeout 5 --max-time 10 -o /dev/null -w '%{http_code}' http://127.0.0.1:3080/"
+ssh root@192.168.68.12 "pct exec 112 -- curl -s --connect-timeout 5 --max-time 10 -o /dev/null -w '%{http_code}' http://127.0.0.1:3080/"
 ```
 
 Alive = **ANY** HTTP status response from the endpoint — the expected set is
@@ -273,13 +273,13 @@ process answering `503` is running and self-heal must NOT restart-loop it.
 Down = connection refused (`000`) or timeout only. Statuses outside the
 expected set are logged/reported as a warning — reported, never healed on.
 
-**B3: Public-URL Fallback Probe (Tanko — for nodes without pct/ssh access to amdpve)**
+**B3: Public-URL Fallback Probe (Tanko — for nodes without pct/ssh access to minipve)**
 
 ```bash
 curl -s --connect-timeout 10 --max-time 15 -o /dev/null -w '%{http_code}' https://tankodhs.sysloggh.net/
 ```
 
-Fallback only — used when the monitoring node has no pct/SSH path to amdpve.
+Fallback only — used when the monitoring node has no pct/SSH path to minipve.
 Alive = **ANY** HTTP status response from the endpoint — healthy signals are
 `302` (authentik proxy-auth redirect) and `401` (auth-gated), and any other
 status, including `404`/`5xx`, also counts alive: the endpoint is up and
@@ -404,29 +404,29 @@ ExecStartPost=/bin/systemctl --no-block start dsh-web-token.service
 4. Every later request through `/` presents that cookie; the token is not needed
    again until the cookie expires or a new browser is used.
 
-**Verification** (amdpve vantage):
+**Verification** (minipve vantage):
 ```bash
 # 1. Login endpoint is Authentik-gated: unauthenticated -> 302 (not 200/303).
-ssh root@192.168.68.15 "pct exec 112 -- curl -s -o /dev/null -w '%{http_code}\n' \
+ssh root@192.168.68.12 "pct exec 112 -- curl -s -o /dev/null -w '%{http_code}\n' \
   -H 'Host: tankodhs.sysloggh.net' http://127.0.0.1/dsh-web-login"
 # Expected: 302
 
 # 2. Legacy :8081 endpoint is gone (connection refused -> 000).
-ssh root@192.168.68.15 "pct exec 112 -- curl -s --max-time 3 -o /dev/null \
+ssh root@192.168.68.12 "pct exec 112 -- curl -s --max-time 3 -o /dev/null \
   -w '%{http_code}\n' http://192.168.68.122:8081/"
 # Expected: 000
 
 # 3. Backend cookie mint + reuse (exactly what /dsh-web-login proxies to).
-TOKEN=$(ssh root@192.168.68.15 "pct exec 112 -- cat /etc/dsh-web/launch-token")
+TOKEN=$(ssh root@192.168.68.12 "pct exec 112 -- cat /etc/dsh-web/launch-token")
-ssh root@192.168.68.15 "pct exec 112 -- curl -s -c /tmp/dsh.jar -o /dev/null \
+ssh root@192.168.68.12 "pct exec 112 -- curl -s -c /tmp/dsh.jar -o /dev/null \
   -H 'Host: tankodhs.sysloggh.net' 'http://127.0.0.1:3080/?token=$TOKEN'"
-ssh root@192.168.68.15 "pct exec 112 -- curl -s -b /tmp/dsh.jar -o /dev/null \
+ssh root@192.168.68.12 "pct exec 112 -- curl -s -b /tmp/dsh.jar -o /dev/null \
   -w '%{http_code}\n' -H 'Host: tankodhs.sysloggh.net' http://127.0.0.1:3080/"
 # Expected: 200 — the minted dsh-auth-... cookie (authority
 # tankodhs.sysloggh.net) is replayed on the next request and accepted.
 
 # 4. Token refresh is non-disruptive and idempotent.
-ssh root@192.168.68.15 "pct exec 112 -- /opt/deepseek-harness/capture-dsh-token.sh"
+ssh root@192.168.68.12 "pct exec 112 -- /opt/deepseek-harness/capture-dsh-token.sh"
 # Expected: "token unchanged; nginx not reloaded" when nothing changed
 ```
 
@@ -437,32 +437,32 @@ fresh cookie. Both verified live 2026-09-11.
 
 ```bash
 # 5. Cookie survives a dsh-web restart, and the new token mints a new cookie.
-ssh root@192.168.68.15 "pct exec 112 -- systemctl restart dsh-web"
+ssh root@192.168.68.12 "pct exec 112 -- systemctl restart dsh-web"
 # dsh-web is Type=simple: restart returns before :3080 is listening. Bounded-poll
 # until the socket answers (any status but 000) before asserting the cookie.
 for i in $(seq 1 60); do
-  UP=$(ssh root@192.168.68.15 "pct exec 112 -- curl -s -o /dev/null -w '%{http_code}' \
+  UP=$(ssh root@192.168.68.12 "pct exec 112 -- curl -s -o /dev/null -w '%{http_code}' \
     -H 'Host: tankodhs.sysloggh.net' http://127.0.0.1:3080/")
   [ "$UP" != "000" ] && break
   sleep 2
 done
-ssh root@192.168.68.15 "pct exec 112 -- curl -s -b /tmp/dsh.jar -o /dev/null \
+ssh root@192.168.68.12 "pct exec 112 -- curl -s -b /tmp/dsh.jar -o /dev/null \
   -w '%{http_code}\n' -H 'Host: tankodhs.sysloggh.net' http://127.0.0.1:3080/"
 # Expected: 200 — the pre-restart cookie is still accepted.
 # The restart's ExecStartPost (or the 2-minute timer) refreshes the include. A
 # manual run may no-op on the flock, so poll until the include carries a token
 # the running process accepts (bounded wait) before the mint+reuse check.
 for i in $(seq 1 60); do
-  TOKEN=$(ssh root@192.168.68.15 "pct exec 112 -- sed -n 's/.*token=//p' /etc/dsh-web/nginx-login.conf | tr -d ';\n'")
+  TOKEN=$(ssh root@192.168.68.12 "pct exec 112 -- sed -n 's/.*token=//p' /etc/dsh-web/nginx-login.conf | tr -d ';\n'")
-  CODE=$(ssh root@192.168.68.15 "pct exec 112 -- curl -s -o /dev/null -w '%{http_code}' \
+  CODE=$(ssh root@192.168.68.12 "pct exec 112 -- curl -s -o /dev/null -w '%{http_code}' \
     -H 'Host: tankodhs.sysloggh.net' 'http://127.0.0.1:3080/?token=$TOKEN'")
   [ "$CODE" = "303" ] && break
   sleep 2
 done
 # Expected: 303 — the include now holds the token the running process accepts.
-ssh root@192.168.68.15 "pct exec 112 -- curl -s -c /tmp/dsh-new.jar -o /dev/null \
+ssh root@192.168.68.12 "pct exec 112 -- curl -s -c /tmp/dsh-new.jar -o /dev/null \
   -H 'Host: tankodhs.sysloggh.net' 'http://127.0.0.1:3080/?token=$TOKEN'"
-ssh root@192.168.68.15 "pct exec 112 -- curl -s -b /tmp/dsh-new.jar -o /dev/null \
+ssh root@192.168.68.12 "pct exec 112 -- curl -s -b /tmp/dsh-new.jar -o /dev/null \
   -w '%{http_code}\n' -H 'Host: tankodhs.sysloggh.net' http://127.0.0.1:3080/"
 # Expected: 200 — the refreshed token minted a fresh cookie.
 ```