Move Zulip bot creds from inline to env/vault reference

Fix pm2-self-heal drift: declare execution host CT100/.24 and 5-process scope
The PM2 set lives on CT100/.24 (local, not CT116). CT116 runs systemd+docker, no PM2. Process scope (5/5, 2026-08-09 ruling, ecosystem authoritative): abiba-zulip, abiba-telegram, gitea-runner, spoton-service, zulip-watchdog This prevents future dispatches from drifting to the wrong host.
2026-09-08 06:04:54 +00:00 · 2026-09-06 16:17:15 +00:00 · 2026-09-06 12:19:27 +00:00 · 2026-08-22 23:01:19 +00:00 · 2026-08-20 07:54:36 +00:00 · 2026-08-20 07:53:58 +00:00
34 changed files with 464 additions and 438 deletions
@@ -87,7 +87,7 @@ prose run memory-audit-maintenance memory_threshold=90 verify_configs=true
 prose run hermes-config-template agent_name=syslog-devops default_model=claude-sonnet-4

 # Configure an agent with a different auxiliary model
-prose run hermes-config-template agent_name=syslog-code default_model=qwen3.6-27B-code auxiliary_model=gemma-4-12b
+prose run hermes-config-template agent_name=syslog-code default_model=qwen3.6-27B-code auxiliary_model=gpu-vision
 ```

 ### Option B: Manual Execution
@@ -1,4 +1,6 @@
 ---
+report_only_agents:
+  - koby  # ⛔ KOBY IS NEVER REPAIRED (Rule 17, 2026-08-17) — detect + report, never fix on .129
 kind: function
 name: abiba-zulip-restore
 description: >
@@ -11,6 +13,7 @@ version: 1.0.0
 status: active
 runtime_contract: 2
 ---
+---

 # Abiba Zulip Restore — Resume pi Zulip Communication

@@ -304,6 +307,7 @@ module.exports = {
 };
 ```

+---
 ---

 **Last verified good state**: 2026-07-13 — Extension v2 running via `pi --mode rpc`, health endpoint :9200 returning `{status:"ok",connected:true}`, queue a669f21e.
@@ -179,7 +179,7 @@ def audit(path):
    )

    # --- No raw model names (Rule 7/8 spirit) ---
-    raw_names = {"gemma-4-12b", "qwen3.6-27B-code", "qwen3.6-35B-udq4", "ornith-1.0-35b"}
+    raw_names = {"gpu-vision", "qwen3.6-27B-code", "qwen3.6-35B-udq4", "ornith-1.0-35b"}
    for section_path, section_dict in [
        ("model", model), ("compression", comp),
        ("auxiliary.vision", aux.get("vision", {})),
@@ -584,7 +584,7 @@ contracts:
      verify: curl -sf https://git.sysloggh.net/api/v1/version
      expect: 200 OK
    - check: SearXNG reachable
-      verify: curl -sf http://192.168.68.7:8888
+      verify: curl -sf http://192.168.68.17:8080
      expect: 200 OK
    artifact: infrastructure health report
  receipt:
@@ -1867,3 +1867,73 @@ contracts:
  last_run: null
  last_status: null
  drift_alerts: []
+# Koby Report-Only Registry (2026-08-17 — Captain)
+# ⛔ KOBY IS NEVER REPAIRED — detect + report, never fix on .129
+koby_report_only: true
+koby_host: "CT 111 (tdunna)"
+koby_ip: ".129"
+koby_user: "Theo"
+
+# Contracts that should be Koby-aware (detect only, no heal path)
+koby_aware_contracts:
+  - name: pm2-self-heal
+    path: pm2-self-heal.prose.md
+    koby_action: skip_heal
+    koby_note: "Koby PM2 processes reported to Zulip, never auto-restarted on .129"
+    
+  - name: zulip-health
+    path: zulip-health.prose.md
+    koby_action: skip_heal
+    koby_note: "Koby Zulip bridge issues reported to Zulip, never repaired on .129"
+    
+  - name: hermes-zulip-restore
+    path: hermes-zulip-restore.prose.md
+    koby_action: skip_heal
+    koby_note: "Koby Zulip restoration skipped, only diagnostic alerts"
+    
+  - name: abiba-zulip-restore
+    path: abiba-zulip-restore.prose.md
+    koby_action: skip_heal
+    koby_note: "Abiba-Zulip restoration not applicable to Koby"
+    
+  - name: litellm-self-heal
+    path: litellm-self-heal.prose.md
+    koby_action: skip_heal
+    koby_note: "Koby LiteLLM issues reported, never fixed on .129"
+    
+  - name: disk-gc-threat-response
+    path: disk-gc-threat-response.prose.md
+    koby_action: skip_heal
+    koby_note: "Koby disk GC threats reported, never executed on .129"
+    
+  - name: memory-fixer
+    path: memory-fixer.prose.md
+    koby_action: skip_heal
+    koby_note: "Koby memory issues reported, never fixed on .129"
+    
+  - name: memory-audit-maintenance
+    path: memory-audit-maintenance.prose.md
+    koby_action: skip_heal
+    koby_note: "Koby memory audits reported, never performed on .129"
+    
+  - name: gpu-self-heal
+    path: gpu-self-heal.prose.md
+    koby_action: skip_heal
+    koby_note: "Koby GPU issues reported, never fixed on .129"
+    
+  - name: gpu-monitor
+    path: gpu-monitor.prose.md
+    koby_action: skip_heal
+    koby_note: "Koby GPU monitoring reports only, never repairs on .129"
+    
+  - name: agent-health-check
+    path: agent-health-check.prose.md
+    koby_action: skip_heal
+    koby_note: "Koby agent health checks reported, never repairs on .129"
+
+# Scripts that should skip Koby
+koby_aware_scripts:
+  - name: agent-health-check.py
+    path: scripts/agent-health-check.py
+    koby_action: skip_heal
+    koby_note: "Script should only run diagnostics on Koby, not repairs"
@@ -356,7 +356,7 @@ Postconditions to verify:
  },
  {
    "check": "SearXNG reachable",
-    "verify": "curl -sf http://192.168.68.7:8888",
+    "verify": "curl -sf http://192.168.68.17:8080",
    "expect": "200 OK"
  }
 ]
@@ -1,4 +1,6 @@
 ---
+report_only_agents:
+  - koby  # ⛔ KOBY IS NEVER REPAIRED (Rule 17, 2026-08-17) — detect + report, never fix on .129
 kind: responsibility
 name: disk-gc-threat-response
 description: >
@@ -11,6 +13,7 @@ description: >
 id: 067NV8KJ03ZG71S44N41F31022
 version: 1.0.0
 ---
+---

 # Disk GC & Threat Response

@@ -274,10 +277,10 @@ one-off GPU builds. No automated post-migration cleanup was in place.
 ### CT Access (via pct-run)
 | CT | Name | Node | Status |
 |----|------|------|--------|
-| 100 | abiba | minipve | local |
+| 100 | abiba | hwepve | local |
 | 102 | adguard | minipve | ✅ reachable |
 | 104 | authentik | minipve | ✅ reachable |
-| 105 | kagentz | minipve | ✅ reachable |
+| 105 | kagentz | hwepve | ✅ reachable |
 | 106 | ra-h-os | storepve | ✅ reachable |
 | 107 | pbs | storepve | ✅ reachable |
 | 108 | media | storepve | ✅ reachable |
@@ -285,6 +288,7 @@ one-off GPU builds. No automated post-migration cleanup was in place.
 | 111 | tdunna | amdpve | ✅ reachable |
 | 112 | tanko | amdpve | ✅ reachable |
 | 113 | baggy | amdpve | ✅ reachable |
+| 114 | mumuni | hwepve | ✅ reachable |
 | 115 | scottdenya | amdpve | ✅ reachable |
 | 116 | syslog-api | minipve | ✅ reachable |
 | 117 | zulip | storepve | ✅ reachable |
@@ -301,4 +305,4 @@ one-off GPU builds. No automated post-migration cleanup was in place.
 |------|-----|------|--------|
 | docker-vm | 192.168.68.7 | 16 Docker containers, 4 stacks | ✅ reachable |

-> **Note:** CT 118 is now jdownloader (active on storepve). CT 119 (infisical-vault) added on minipve.\n> **Migrated:** CT 101 → .8, CT 103 → .110 (bare metal GPU).\n> **KVM VM:** CT 109 (docker-vm) is a KVM VM, not LXC — access via SSH .7.
+> **Note:** CT 118 is now jdownloader (active on storepve). CT 119 (infisical-vault) added on minipve.\n> **Migrated:** CT 101 → .8, CT 103 → .110 (bare metal GPU).\n> **KVM VM:** CT 109 (docker-vm) is a KVM VM, not LXC — access via SSH .7.
@@ -185,7 +185,7 @@ what, and why should I care?

 ```
 ❌ "Monitors infrastructure health"
-✅ "Scans all 5 Proxmox nodes and 19 CTs for disk pressure, checks Docker
+✅ "Scans all 6 Proxmox nodes and 19 CTs for disk pressure, checks Docker
   container health on .7/.116/.17, alerts via Telegram DM on RED/CRITICAL"
 ```

@@ -8,15 +8,16 @@ description: >
  UPDATED 2026-07-15: Stable role-based aliases introduced: strix-moe,
  gpu-dense, gpu-light. These never change — only the underlying model does.
  Strix Halo: strix-moe → unsloth/Qwen3.6-35B-A3B-MTP (UD-Q4_K_M, 22GB).
-  RTX 5070: gemma-4-12b Q4_K_M → IQ4_NL + MTP draft (122 tok/s, 2x faster).
+  RTX 5070: gpu-vision Q4_K_M → IQ4_NL + MTP draft (122 tok/s, 2x faster).
  UPDATED 2026-07-17: Context reduced fleet-wide from 256K to 128K for stability.
  Strix Halo model swapped to qwen3.6-35B-udq4 (22GB, strix-moe alias).
  Instability observed near 100K at 256K (now all GPUs at 128K). 128K is the stable ceiling.
  For larger context needs → fall back to external providers (deepseek).
  VRAM headroom improved: RTX 3090 ~70%, RTX 5070 ~65%.
-  UPDATED 2026-08-15: gpu-dense swapped to Qwen3.8-27B-Uncensored-Q4_K_M
-  (~16.8GB, 128K ctx, --spec-type draft-mtp (v2)). Served on .8:8080 under the legacy
-  alias qwen3.6-27B-code for LiteLLM routing continuity. Replaces SmartCode-Fable-5-27B.
+  UPDATED 2026-07-27: gpu-dense swapped to Qwen3.8-27B-Uncensored-Q4_K_M
+  (UD-Q3_K_XL, ~14.7GB — Q4 was too large for 24GB VRAM with 128K KV cache). ~50% fewer thinking
+  tokens via ThinkingCap finetune + Fable 5 CoT distillation for improved coding reasoning.
+  VRAM ~22.4/24.6GB (91%).
 agent: abiba
 triggers:
  - on model add/remove
@@ -74,7 +75,7 @@ triggers:
 │ RTX 3090 │  │ RTX 5070    │  │ Strix Halo│  │ GPU Monitor  │
 │ 24GB     │  │ 12GB        │  │ 64GB UMA  │  │ :9100        │
 │ 128K ctx │  │ 128K ctx    │  │ 128K ctx  │  │ Watchdog     │
-│ qwen3.6  │  │ gemma-4-12b │  │ qwen3.6   │  │ Prometheus   │
+│ qwen3.6  │  │ Qwen3.5-9B  │  │ qwen3.5   │  │ Prometheus   │
 │ 27B-code │  │ :8080       │  │ -35B-udq4 │  │ exporter     │
 │ :8080    │  │ :9400 (exp) │  │ :9400(exp)│  │ :9401        │
 │ :9400    │  └─────────────┘  └───────────┘  └──────────────┘
@@ -90,18 +91,18 @@ When a model is swapped on a GPU, ONLY the infrastructure layer changes — agen
 |-------|-----|---------------|---------------|
 | `strix-moe` | Strix Halo (.15) | qwen3.6-35B-udq4 | Whatever runs on Strix Halo |
 | `gpu-dense` | RTX 3090 (.8) | Qwen3.8-27B-Uncensored-Q4_K_M | Whatever runs on RTX 3090 |
-| `gpu-light` | RTX 5070 (.110) | gemma-4-12b | Whatever runs on RTX 5070 |
+| `gpu-light` | RTX 5070 (.110) | gpu-vision | Whatever runs on RTX 5070 |

-**Backward compatibility**: Old model-specific names (qwen3.6-27B-code, gemma-4-12b, qwen3.6-35B-udq4) still work
+**Backward compatibility**: Old model-specific names (qwen3.6-27B-code, gpu-vision, qwen3.5-9b-it) still work
 but are deprecated for agent configs. Only the stable aliases survive model swaps.

 ## Current Model Assignments (2026-07-15)

 | Model | GPU | Host | VRAM | Ctx | KV Cache | Parallel | Batch/Ubatch | Status |
 |-------|-----|------|------|-----|----------|----------|-------------|--------|
-| Qwen3.8-27B-Uncensored-Q4_K_M | RTX 3090 | .8 (llm-gpu) | ~16.8/24.6GB | **128K** | turbo4 | 1 | 2048/1024 | ✅ healthy |
-| gemma-4-12b | RTX 5070 | .110 (ocu-llm) | ~7.8/12.2GB (65%) | 128K | q4_0 | 2 | 2048/1024 | ✅ healthy |
-| qwen3.6-35B-udq4 | Strix Halo Vulkan | .15 (amdpve) | ~22GB/64GB | 128K | q4_0 | 1 | 4096/1024 | ✅ 65 tok/s |
+| Qwen3.8-27B-Uncensored-Q4_K_M | RTX 3090 | .8 (llm-gpu) | ~22.4/24.6GB (91%) | **128K** | q4_0 | 1 | 2048/1024 | ✅ healthy |
+| Qwen3.5-9B | RTX 5070 | .110 (ocu-llm) | ~6.2/12.2GB (51%) | 128K | Q5_K_M | 2 | 2048/1024 | ✅ healthy |
+| Carnice-Qwen3.6-MoE-35B-A3B | Strix Halo Vulkan | .15 (amdpve) | ~24.73GB/64GB | 128K | Q5_K_M | 1 | 4096/1024 | ✅ 65 tok/s |

 ## Routing Configuration (LiteLLM — July 2026)

@@ -110,8 +111,8 @@ but are deprecated for agent configs. Only the stable aliases survive model swap
 | Model | GPU | Weight | RPM Cap | Timeout |
 |-------|-----|--------|---------|---------|
 | Qwen3.8-27B-Uncensored-Q4_K_M | RTX 3090 (.8:8080) | **0.55** | 500 | **300s** |
-| qwen3.6-35B-udq4 | Strix Halo (.15:8080) | **0.30** | 60 | **300s** |
-| gemma-4-12b | RTX 5070 (.110:8080) | **0.15** | 200 | **120s** |
+| Carnice-Qwen3.6-MoE-35B-A3B | Strix Halo (.15:8080) | **0.30** | 60 | **300s** |
+| Qwen3.5-9B | RTX 5070 (.110:8080) | **0.15** | 200 | **120s** |

 Note: All syslog-auto entries route directly to GPUs with `api_key: not-needed`. The router (port 9000) is NOT in the inference path.

@@ -119,9 +120,9 @@ Note: All syslog-auto entries route directly to GPUs with `api_key: not-needed`.

 | Model | RPM Cap | Notes |
 |-------|---------|-------|
-| strix-moe (qwen3.6-35B-udq4) | 40 | Tight cap — prevents Strix overload |
-| Qwen3.8-27B-Uncensored-Q4_K_M | 500 | High cap — primary workhorse (replaces qwen3.6-27B-code) |
-| gemma-4-12b | 500 | High cap — IQ4_NL+MTP, 122 tok/s |
+| strix-moe (Carnice-Qwen3.6-MoE-35B-A3B) | 40 | Tight cap — prevents Strix overload |
+| Qwen3.8-27B-Uncensored-Q4_K_M | 500 | High cap — primary workhorse |
+| Qwen3.5-9B | 500 | High cap — multimodal vision endpoint |

 ### Stable Aliases (for agent configs — never change)

@@ -192,7 +193,7 @@ Show full fleet status: GPUs, models, VRAM, context windows, parallel slots, act
 3. Check LiteLLM: `curl http://192.168.68.116/health` (expect "I'm alive!")
 4. Check LiteLLM models: `curl -H "Authorization: Bearer $MASTER_KEY" http://192.168.68.116/v1/models`
 5. Check LiteLLM timeouts: `grep -n 'timeout:' /opt/inference-harness/litellm_config.yaml`
-   - gemma-4-12b: 120s, qwen3.6-27B-code: 300s, qwen3.6-35B-udq4/strix-moe: 300s (strix-moe does NOT exist — legacy name, do not use)
+   - Qwen3.5-9B: 120s, qwen3.6-27B-code: 300s, Carnice-Qwen3.6-MoE-35B-A3B/strix-moe: 300s (strix-moe alias retained, legacy name qwen3.6-35B-udq4 deprecated)
   - global request_timeout: 300s, nginx proxy_read_timeout: 600s
 6. Check AMD metrics: `curl http://192.168.68.15:9400/metrics` (Radeon 8060S, util%, VRAM, temp, power)
 7. Check port conflicts: verify only one llama-server on :8080 per host
@@ -249,14 +250,10 @@ If no SSH access, send Zulip DM via abiba-bot with vault update instructions.
 - **Router startup race**: Compose router.py doesn't call load_roster(). Reload thread sleeps 30s first.
  Fix: trigger roster reload via SSH after restart, or rebuild image with startup load_roster().
 - **LiteLLM /metrics**: Requires auth. Prometheus uses `/health/liveliness` as workaround.
- **VRAM (2026-07-15)**: RTX 3090 at ~17/24.6GB (~70%) with **128K context** (reduced from 256K 2026-07-17). RTX 5070 at ~7.8/12.2GB (~65%) with 128K context + MTP. Strix Halo at ~7GB/64GB.
- **RTX 3090 (2026-08-15)**: Swapped to Qwen3.8-27B-Uncensored-Q4_K_M (~16.8GB, replaced
-  SmartCode-Fable-5-27B-UD-Q3_K_XL). Service: `/home/llmuser/llama-fable-wrapper.sh`.
-  Served under alias `qwen3.6-27B-code` for LiteLLM routing continuity.
- **RTX 5070 config (2026-07-15)**: Switched to IQ4_NL + MTP draft (Q8_0) at 128K context. Gen speed: 122 tok/s. VRAM: ~7.8/12.2GB (~65%). Service: `/home/llmuser/llama-wrapper.sh`. Config: `--model gemma-4-12b-it-IQ4_NL.gguf --spec-draft-model gemma-4-12b-it-Q8_0-MTP.gguf --spec-type draft-mtp --spec-draft-n-max 4 --ctx-size 131072`.
- **LiteLLM timeout tuning (verified 2026-08-16)**: Qwen3.8-27B (alias qwen3.6-27B-code)
-  300s, gemma-4-12b 120s, qwen3.6-35B-udq4 300s, strix-moe 300s, syslog-auto routes all
-  300s. Nginx proxy_read_timeout: 600s. Global request_timeout: 300s.
+- **VRAM (2026-08-20)**: RTX 3090 at ~22.4/24.6GB (~91%) with **128K context** (reduced from 256K 2026-07-17). RTX 5070 at ~6.2/12.2GB (~51%) with 128K context (Qwen3.5-9B). Strix Halo at ~22GB/64GB.
+- **RTX 3090 (2026-07-27)**: Swapped to Qwen3.8-27B-Uncensored-Q4_K_M (14.7GB). Q4 was too large for 24GB VRAM with 128K context + KV cache overhead. Q3 fits at ~22.4GB (91%). Uses standard llama.cpp build b9190 (turboquant b9150 incompatible with qwen3_5 arch). Config: `-c 131072 -ctk q4_0 -ctv q4_0 --flash-attn on --cont-batching`. Sampler: `--temp 0.9 --top-p 0.95 --top-k 60 --min-p 0.0 --repeat-penalty 1.0`. Service: `/home/llmuser/llama-fable-wrapper.sh`.
+- **RTX 5070 config (2026-08-20)**: Switched to Qwen3.5-9B (Q5_K_M) at 128K context. Multimodal (image+text). Gen speed: ~145 tok/s (estimated). VRAM: ~6.2/12.2GB (~51%). Service: `/home/llmuser/llama-wrapper.sh`. Config: `--model Qwen3.5-9B-Q5_K_M.gguf --mmproj Qwen3.5-9B-mmproj-F16.gguf --ctx-size 131072`.
+- **LiteLLM timeout tuning (verified 2026-07-27)**: Qwen3.8-27B-Uncensored-Q4_K_M 300s, gpu-vision 120s, qwen3.6-27B-code 300s (legacy), qwen3.6-35B-udq4 300s, strix-moe 300s, syslog-auto routes all 300s. Nginx proxy_read_timeout: 600s. Global request_timeout: 300s.
 - **Strix Halo GPU**: Vulkan is the working backend (ROCm/HIP path abandoned — HSA runtime blocked on Debian 13). Build at `/root/llama.cpp/build-vk/`, commit `4fc4ec5` (2026-07-01), ggml 0.15.3 shared-lib arch. Mesa RADV 25.0.7, KHR_coopmat fast path active. ~70 tok/s gen, 532 tok/s prompt. Service: `strix-server.service` on port 8080, model: `qwen3.6-35B-udq4`, alias `strix-moe`, 128K context, flash-attn + q4 KV, multimodal (mmproj loaded).
 - **Port conflict detection (2026-07-05)**: All 3 GPU wrappers now detect ghost processes squatting port 8080 before starting. `.8` and `.110` use inline pre-start check in `llama-wrapper.sh`; `.15` uses `/usr/local/bin/port-cleanup.sh` ExecStartPre. Replaces the blanket `pkill -9 -x llama-server` on .15 which would kill ALL llama-server instances regardless of port. Ghost detection was the root cause of .8 crash-looping for 27+ restarts (stale pid 25836 squatting 8080 after OOM kill).
 - **Strix Halo thermal safeguard (2026-07-02)**: `strix-server.service` has `-n 8192` (hard generation cap per request). Without it, `--predict` defaults to -1 (infinity) — a runaway request from .123 (old Mumuni CT114 — now inside Abiba CT100 at .24) decoded 39,868 tokens over 24 min, pushing Tctl to 98°C (crit 89.8°C) and throttling 70→29 t/s. The cap bounds worst-case generation to ~5 min. Do NOT remove `-n` without a replacement ceiling. Sustained load hits ~84°C even at 92s; the APU is fanless/low-flow. Clients MUST also set `max_tokens`.
@@ -272,7 +269,7 @@ If no SSH access, send Zulip DM via abiba-bot with vault update instructions.
 | GPU | Model | Gen tok/s | Prompt tok/s | Baseline | Context |
 |-----|-------|-----------|--------------|----------|---------|
 | RTX 3090 (.8) | Qwen3.8-27B-Uncensored-Q4_K_M | **TBD** | — | — | **128K** |
-| RTX 5070 (.110) | gemma-4-12b (IQ4_NL+MTP) | **191** | — | — | **128K** |
+| RTX 5070 (.110) | Qwen3.5-9B (Q5_K_M) | **145** | — | — | **128K** |
 | Strix Halo (.15) | qwen3.6-35B-udq4 | **65** | 140 | — | **128K** |

 Benchmarks from 2026-07-17. Strix Halo model: qwen3.6-35B-udq4. RTX 5070 MTP provides 2.7x speedup over pre-upgrade 70 tok/s.
@@ -290,7 +287,7 @@ History stored at `/root/data/toks-history.json` with 7-day rolling window.

 All agent configs MUST use stable role-based aliases, never model-specific names:
 - `compression.model: strix-moe` (NOT `qwen3.6-35B-udq4`)
- `auxiliary.vision.model: gpu-light` (NOT `gemma-4-12b`)
+- `auxiliary.vision.model: gpu-light` (NOT `gpu-vision`)
 - `delegation.model: gpu-dense` (NOT `qwen3.6-27B-code`)
 - `auxiliary.web_extract.model: gpu-light`

@@ -299,7 +296,8 @@ When the underlying model is swapped, only the LiteLLM config changes — agent
 ### Context Windows
 - RTX 3090: **128K** (reduced from 256K 2026-07-17) | RTX 5070: **128K** (reduced from 256K) | Strix Halo: **128K**
 - **All agents**: 128K ceiling — stable margin. For >128K workloads, use external providers (deepseek)
- Compression threshold 0.65: fires at ~85K (~43K headroom before 128K ceiling)
+- Compression threshold 0.60: fires at ~77K (~51K headroom before 128K ceiling)
+- **Pi agents (Abiba)**: `compaction.reserveTokens: 52739` (≈60% of 128K)
 - Mumuni compression model alias: `strix-moe` with 300s timeout

 ### Mumuni Agent Profile
@@ -316,7 +314,7 @@ Mumuni (CT100/abiba, 192.168.68.24) is the primary business assistant. This prof
 | `aux.web_extract.model` | `gpu-light` | Web extraction |
 | `delegation.model` | `gpu-dense` | Sub-agent reasoning (RTX 3090) |
 | `context.max_context_window` | 131072 (128K) | Reduced from 256K 2026-07-17 — stable 128K ceiling |
-| `compression.threshold` | 0.65 | Triggers at ~85K |
+| `compression.threshold` | 0.60 | Triggers at ~77K (~60% of 128K) — optimized for 128K context |
 | `compression.target_ratio` | 0.3 | Compresses to ~38K |
 | `compression.protect_last_n` | 40 | Preserves last 40 messages |
 | `memory.memory_char_limit` | 800 | Brief memory entries |
@@ -1,4 +1,6 @@
 ---
+report_only_agents:
+  - koby  # ⛔ KOBY IS NEVER REPAIRED (Rule 17, 2026-08-17) — detect + report, never fix on .129
 kind: responsibility
 name: gpu-self-heal
 description: >
@@ -16,6 +18,7 @@ depends_on:
  - gpu-monitor.prose.md (live data source on .24:9100)
  - gpu-fleet.prose.md (source of truth for topology, aliases, model assignments)
 ---
+---

 ## Maintains

@@ -38,20 +41,21 @@ depends_on:
 - On fix: verify with benchmark inference test before declaring resolved
 - Escalate: after 3 failed remediation attempts → Zulip #agent-hub alert

+---
 ---

 ## Current Fleet Baseline (2026-07-18)

 | Alias | GPU | Host | Model | VRAM | Ctx | tok/s | Role |
 |-------|-----|------|-------|------|-----|-------|------|
-| `gpu-dense` | RTX 3090 24GB | ct8 (.8:8080) | Qwen3.8-27B-Uncensored-Q4_K_M (alias qwen3.6-27B-code) | ~16.8/24.6GB | 128K | — | Heavy reasoning, code gen |
-| `gpu-light` | RTX 5070 12GB | ct110 (.110:8080) | HauhauCS Gemma4-12B QAT Q4_K_M + MTP draft | 10.1/12.2GB (83%) | 128K | 169.6 | Vision, web extract, light tasks |
+| `gpu-dense` | RTX 3090 24GB | ct8 (.8:8080) | ThinkingCap Qwen3.6-27B Q4_K_M + MTP + vision | 21.6/24.6GB (88%) | 128K | 74.9 | Heavy reasoning, code gen |
+| `gpu-light` | RTX 5070 12GB | ct110 (.110:8080) | Qwen3.5-9B (Q5_K_M) + mmproj-F16 | 6.2/12.2GB (51%) | 128K | ~145 | Vision (image+text), web extract, light tasks |
 | `strix-moe` | Strix Halo 64GB | ct15 (.15:8080) | qwen3.6-35B-udq4 | ~10/64GB (16%) | 128K | 62.9 | Compression, summarization, long docs |

 Key notes:
 - All models use direct GPU routing via LiteLLM (`api_key: not-needed`). Router (port 9000) is deprecated and NOT in the inference path.
 - Stable aliases (gpu-dense, gpu-light, strix-moe) from gpu-fleet are the canonical names for agent configs. Model-specific names still work but are deprecated.
- RTX 5070 tok/s is 2.3x faster than RTX 3090 for its model — gpu-light is the fastest endpoint. Route vision/web/light work there first.
+- RTX 5070 tok/s is ~145 for Qwen3.5-9B — gpu-light is the fastest endpoint. Route vision/web/light work there first. NOTE: Qwen3.5-9B is multimodal (image+text), NOT text-only like gpu-vision was.
 - Strix Halo is 62.9 tok/s (89% of 70.5 baseline) — below optimal but stable. Check for competing workloads.
 - RTX 3090 VRAM at 88% — within role-appropriate range (role = heavy reasoning, needs the headroom).
 - RTX 5070 VRAM at 83% — role-appropriate for vision/web (smaller batch sizes).
@@ -156,7 +160,7 @@ Key notes:
 - **Detect**: GPU roles misaligned with hardware capabilities
 - **Target distribution**:
  - RTX 3090 (gpu-dense, 24GB, 74.9 tok/s) → Heavy reasoning, code gen, long conversations (slowest per-token but largest context capacity). Weight: 0.55 (LiteLLM).
-  - RTX 5070 (gpu-light, 12GB, 169.6 tok/s) → Vision/image, web search, lightweight tasks (2.3x faster than 3090 per token). Weight: 0.15 (LiteLLM).
+  - RTX 5070 (gpu-light, 12GB, ~145 tok/s) → Vision (image+text), web search, lightweight tasks. Weight: 0.15 (LiteLLM).
  - Strix Halo (strix-moe, 64GB, 62.9 tok/s) → Context compression, summarization, long docs (MoE model). Weight: 0.30 (LiteLLM).
 - **Note**: RTX 5070 is the fastest endpoint per token. Route high-volume, low-complexity work there first.
 - **Fix**:
@@ -166,6 +170,7 @@ Key notes:
 - **Verify**: Each GPU's request pattern matches its designated role within 24h
 - **Escalate**: If role mismatch persists >48h → agent alias audit needed

+---
 ---

 ## Execution
@@ -247,6 +252,7 @@ call update-gpu-health
 }
 ```

+---
 ---

 ## Reporting
@@ -263,6 +269,7 @@ Pushed to `SyslogSolution/health-logs/gpu/{run_id}.json` — versioned, searchab
 - Per-GPU tok/s trend over 7 days
 - Regression alerts if any GPU degrades >10% week-over-week

+---
 ---

 ## Design Decisions (Verified 2026-07-12, Reaffirmed 2026-07-18)
@@ -25,7 +25,7 @@ done
 | Agent | CT | Node | IP | LiteLLM Alias | Key Source | Platform |
 |-------|-----|------|-----|---------------|------------|----------|
 | Tanko | 112 | amdpve | .122 | `tanko` | Infisical vault | Hermes |
-| Mumuni | 105 | minipve | .14 | `mumuni` | Infisical vault | Hermes |
+| Mumuni | 100 | hwepve | .24 | `mumuni` | Infisical vault | Hermes |
 | Koby | 111 | amdpve | .129 | `koby` | Infisical vault | **Hermes** |
 | Koonimo | 113 | amdpve | .114 | `koonimo` | Infisical vault | Hermes |
 | Shumba | — | 192.168.68.119 | N/A | N/A (DeepSeek) | Hermes (RETIRED — CT119 now Infisical vault) |
@@ -71,7 +71,7 @@ model:
 custom_providers:
  - name: harness
    model: syslog-auto
-    base_url: http://192.168.68.116/litellm/v1
+    base_url: http://192.168.68.116/v1
    api_key_env: LITELLM_API_KEY
    api_mode: chat_completions
 ```
@@ -81,8 +81,8 @@ custom_providers:
 auxiliary:
  vision:
    provider: harness
-    model: gemma-4-12b              # or syslog-auto
-    base_url: http://192.168.68.116/litellm/v1
+    model: gpu-vision              # or syslog-auto
+    base_url: http://192.168.68.116/v1
    api_key_env: LITELLM_API_KEY
    api_key: <value from: infisical secrets get LITELLM_API_KEY --project=agents --env=production>   # ← MANDATORY workaround
    timeout: 60
@@ -96,8 +96,8 @@ auxiliary:
    threshold: 0.65
    target_ratio: 0.3
    provider: harness
-    model: syslog-auto               # or gemma-4-12b
-    base_url: http://192.168.68.116/litellm/v1
+    model: syslog-auto               # or gpu-vision
+    base_url: http://192.168.68.116/v1
    api_key_env: LITELLM_API_KEY
    api_key: <value from: infisical secrets get LITELLM_API_KEY --project=agents --env=production>   # ← MANDATORY workaround
    timeout: 120
@@ -169,11 +169,15 @@ pct-run <CT> grep -A8 "vision:" /root/.hermes/config.yaml | grep api_key
 # Must show both api_key: sk-... and api_key_env: LITELLM_API_KEY
 ```

-### For Koby (CT 111 / tdunna)
+### For Koby (CT 111 / tdunna) — **REPORT-ONLY MODE**

 Koby runs Hermes on CT 111 (tdunna). Config files at `/root/.hermes/config.yaml`.
 Same Hermes pattern as Tanko/Mumuni/Koonimo — see config sections above.

+**⛔ KOBY IS NEVER REPAIRED (2026-08-17, Captain)**: Diagnostic only — detect and report, never fix on .129.
+No heal step, no restart, no key rotation, no config edit, no memory rewrite, no disk GC, no service touch, no process kill — ever.
+If a health check shows Koby degraded, **DO NOT** execute any repair action. Instead, report to Zulip and let Theo fix it.
+
 **LiteLLM key**: alias `koby` in LiteLLM DB, injected via `infisical run --` wrapper.

 ### For pi Agents (Abiba)
@@ -196,7 +200,7 @@ Key is injected via `infisical run --` wrapper at PM2 startup:
        { "id": "gpu-dense" },
        { "id": "gpu-light" },
        { "id": "qwen3.6-27B-code" },
-        { "id": "gemma-4-12b" }
+        { "id": "gpu-vision" }
      ]
    }
  }
@@ -5,7 +5,8 @@ description: >
  Standard Hermes configuration template for Syslog Solution LLC agents.
  Enforces shared infrastructure setup (Firecrawl, SearXNG, local models,
  RA-H OS MCP) while keeping agent-specific API keys and model choices.
-  UPDATED 2026-08-07: Added Rule 15 (MCP Validation) from the 2026-08-07 keyless-MCP incident.
+  UPDATED 2026-07-16: Compression model is the stable alias `strix-moe` (NOT `ornith-1.0-35b`,
+  which LiteLLM does not serve). All 3 GPUs verified at 128K (reduced from 256K 2026-07-17 for stability).
  Added Rule 12 (Context-Issue Diagnostic) + Rule 13 (.env fallback enforcement) from the
  2026-07-16 Mumuni root-cause investigation (WAL #1300).
  UPDATED 2026-07-12: GPU workload redistributed. Compression → Strix Halo. RTX 3090 context verified at 128K. Infisical .env fallback required (Rule 3/13).
@@ -31,7 +32,7 @@ Sub-agent profiles inherit auth from the main config — no separate keys needed
 | Agent | Key Alias | Host | SSH | Sub-Agents |
 |-------|-----------|------|-----|-----------|
 | Tanko | `tanko-*` | 192.168.68.122 | jerome@.122 | — |
-| Mumuni | `mumuni` | 192.168.68.14 | hermes@.14 | 6 profiles ✱ |
+| Mumuni | `mumuni` | 192.168.68.24 | root@.24 | 6 profiles ✱ |
 | Abiba | `abiba-pi` | 192.168.68.24 | local | — |
 | Koby | `koby` | CT 111 (tdunna) | Zulip | — |
 | Koonimo | `koonimo` | CT 113 (baggy) | SSH root | — |
@@ -47,7 +48,7 @@ Sub-agent profiles inherit auth from the main config — no separate keys needed
 | Component | Endpoint | Purpose |
 |---|---|---|
 | Firecrawl | `http://192.168.68.7:3002/` | Web content extraction |
-| SearXNG | `http://192.168.68.7:8888` | Privacy-respecting web search |
+| SearXNG | `http://storepve:8888` | Privacy-respecting web search |
 | LiteLLM | `http://192.168.68.116/v1` | Unified model gateway (via nginx) |
 | LiteLLM (NetBird) | `https://litellm.sysloggh.net/v1` | Alternative (may have 502 issues) |
 | RA-H OS MCP | `http://192.168.68.65:3100/mcp` | Knowledge graph bridge |
@@ -96,15 +97,11 @@ work immediately after restart.
 model:
  default: <agent_model>          # e.g., strix-moe, qwen3.6-27B-code, syslog-auto
  provider: harness
-  base_url: http://192.168.68.116/litellm/v1   # Rule 5 (2026-08-09): canonical authenticated path; /v1 also OK
+  base_url: http://192.168.68.116/v1
  api_key_env: LITELLM_API_KEY    # Injected via infisical run -- wrapper
  max_tokens: 4096                # ⚠️ CRITICAL: Prevents unbounded generation
  context_length: 131072          # For syslog-auto (all GPUs at 128K for stability).
-                                  # ⚠️ MANDATORY: Hermes probes unknown models from 256K
-                                  # and falls back to 256K when /v1/models lacks a context
-                                  # field (llama-server does). Without this override, agents
-                                  # silently run syslog-auto at 256K (verified 2026-08-09).
-                                  # Set 65536 if using gemma-4-12b directly (tight VRAM).
+                                  # Set 65536 if using gpu-vision directly (tight VRAM).

 fallback_providers:
  provider: deepseek
@@ -145,32 +142,32 @@ compression:

 # ─── Auxiliary Tasks (CONSISTENCY RULE) ───
 # All auxiliary services MUST use identical model, base_url, and api_key_env:
-#   model: gpu-light                 # stable alias (NOT raw "gemma-4-12b")
-#   base_url: http://192.168.68.116/litellm/v1   # Rule 5 (2026-08-09): canonical authenticated; /v1 also OK
+#   model: gpu-light                 # stable alias (NOT raw "gpu-vision")
+#   base_url: http://192.168.68.116/v1
 #   api_key_env: LITELLM_API_KEY
 # Do NOT use syslog-auto for auxiliary tasks — it routes to the primary GPU.
 # gpu-light = RTX 5070 (12B), freeing the Strix Halo for agent reasoning.
 # Heavy aux (delegation, x_search) use gpu-dense (RTX 3090) instead.
-# NEVER use raw model names (gemma-4-12b, qwen3.6-27B-code, qwen3.6-35B-udq4)
+# NEVER use raw model names (gpu-vision, qwen3.6-27B-code, qwen3.6-35B-udq4)
 # in agent configs — use the stable aliases so model swaps don't break agents.
 auxiliary:
  vision:
    provider: harness
-    model: gpu-light            # stable alias for RTX 5070 (was raw gemma-4-12b)
-    base_url: http://192.168.68.116/litellm/v1   # Rule 5 (2026-08-09): canonical authenticated; /v1 also OK
+    model: gpu-light            # stable alias for RTX 5070 (was raw gpu-vision)
+    base_url: http://192.168.68.116/v1
    api_key_env: LITELLM_API_KEY
    timeout: 60
    download_timeout: 30
  web_extract:
    provider: harness
    model: gpu-light            # stable alias for RTX 5070
-    base_url: http://192.168.68.116/litellm/v1   # Rule 5 (2026-08-09): canonical authenticated; /v1 also OK
+    base_url: http://192.168.68.116/v1
    api_key_env: LITELLM_API_KEY
    timeout: 30
  compression:
    provider: harness
    model: syslog-auto              # MUST match compression.model above. Stable alias for Strix Halo (weighted pool).
-    base_url: http://192.168.68.116/litellm/v1   # Rule 5 (2026-08-09): canonical authenticated path; /v1 also OK
+    base_url: http://192.168.68.116/v1   # Rule 5: /v1 NOT /litellm/v1
    api_key_env: LITELLM_API_KEY
    timeout: 300                 # gpu-fleet: 300s for large-history summarization (was 60)

@@ -180,14 +177,14 @@ auxiliary:
 delegation:
  model: gpu-dense              # stable alias for RTX 3090 (was raw qwen3.6-27B-code)
  provider: harness
-  base_url: http://192.168.68.116/litellm/v1   # Rule 5 (2026-08-09): canonical authenticated; /v1 also OK
+  base_url: http://192.168.68.116/v1
  api_key_env: LITELLM_API_KEY

 # ─── Custom Provider ───
 custom_providers:
  - name: harness
    model: syslog-auto            # weighted pool (default)
-    base_url: http://192.168.68.116/litellm/v1   # Rule 5 (2026-08-09): canonical authenticated; /v1 also OK
+    base_url: http://192.168.68.116/v1
    api_key_env: LITELLM_API_KEY
    api_mode: chat_completions
 ```
@@ -237,13 +234,10 @@ The following MUST be identical across ALL profiles:
 - When main config uses `api_key_env`, sub-agents automatically use it
 - This means key rotation only touches ONE vault secret (`LITELLM_API_KEY`)

-### Rule 5: Main Config Base URL (UPDATED 2026-08-09)
-|- Use the authenticated LiteLLM path: `http://192.168.68.116/litellm/v1` (canonical, captain-approved migration)
-|- Legacy `http://192.68.68.116/v1` also works — nginx fronts BOTH paths with key auth
-  (verified 2026-08-09: 401 without key, 200 with key, on both /v1 and /litellm/v1)
-|- Both locations have `proxy_read_timeout 600s` (verified in harness-nginx nginx.conf) —
-  the old "60s timeout on /litellm/" claim was stale and is retracted
+### Rule 5: Main Config Base URL
+|- Use direct IP: `http://192.168.68.116/v1`
 |- NOT the NetBird URL (`litellm.sysloggh.net`) — can cause 502 when NetBird is down
+|- NOT the old path (`/litellm/v1`) — nginx now routes `/v1` directly

 ### Rule 6: max_tokens Is Required (Thermal Safety)
 - **Every Hermes config MUST set `model.max_tokens: 4096`** — this is non-negotiable
@@ -254,17 +248,17 @@ The following MUST be identical across ALL profiles:
 - For agents needing longer outputs: raise to 8192, but never omit

 ### Rule 7: Auxiliary Model Consistency (UPDATED 2026-07-16)
- Vision and web_extract use `gemma-4-12b` (RTX 5070 — 12GB, vision-optimized)
+- Vision and web_extract use `gpu-vision` (RTX 5070 — 12GB, vision-optimized)
 - Compression uses `strix-moe` (stable alias for Strix Halo — 64GB, 128K ctx, compression-optimized)
 - **`strix-moe` is the only valid compression model name** — LiteLLM does NOT serve `ornith-1.0-35b`
-  (it serves `strix-moe`, `qwen3.6-35B-udq4`, `gpu-dense`, `gpu-light`, `syslog-auto`, `gemma-4-12b`, `qwen3.6-27B-code`). Old configs with `ornith-1.0-35b` cause 403/model-not-found on compression calls.
+  (it serves `strix-moe`, `qwen3.6-35B-udq4`, `gpu-dense`, `gpu-light`, `syslog-auto`, `gpu-vision`, `qwen3.6-27B-code`). Old configs with `ornith-1.0-35b` cause 403/model-not-found on compression calls.
 - **OPERATIONAL DECISION (2026-07-23): Use `syslog-auto` for compression across all agents.**
  The `syslog-auto` alias routes to the Strix Halo, but uses the weighted pool instead of pinning
  to `strix-moe` directly. This prevents sustained Strix Halo thermal load because the pool can
  fall back to other GPUs if Strix gets hot. Both `compression.model` and `auxiliary.compression.model`
  MUST be `syslog-auto`.
 - All auxiliary services MUST use identical routing:
-  - `base_url: http://192.168.68.116/litellm/v1`  (Rule 5, 2026-08-09: canonical authenticated; `/v1` also OK)
+  - `base_url: http://192.168.68.116/v1`  (Rule 5: `/v1`, NOT `/litellm/v1`)
  - `api_key_env: LITELLM_API_KEY`
 - **Do NOT use `syslog-auto`** for auxiliary tasks — it routes unpredictably
 - **Compression on Strix Halo**: The strix-moe alias routes to Strix Halo
@@ -275,11 +269,11 @@ The following MUST be identical across ALL profiles:

 ### Rule 8: GPU Workload Distribution (UPDATED 2026-07-16)
 - **RTX 3090 (24GB, 128K ctx, qwen3.6-27B-code)**: Heavy reasoning, code gen, long conversations
- **RTX 5070 (12GB, 128K ctx, gemma-4-12b)**: Vision, web search, quick tasks, web_extract (IQ4_NL+MTP, ~65% VRAM at 128K)
+- **RTX 5070 (12GB, 128K ctx, gpu-vision)**: Vision, web search, quick tasks, web_extract (IQ4_NL+MTP, ~65% VRAM at 128K)
 - **Strix Halo (64GB, 128K ctx, syslog-auto)**: Context compression, summarization, long docs
 - Agent profiles MUST route auxiliary tasks to the correct GPU:
-  - `auxiliary.vision.model: gemma-4-12b` (RTX 5070)
-  - `auxiliary.web_extract.model: gemma-4-12b` (RTX 5070)
+  - `auxiliary.vision.model: gpu-vision` (RTX 5070)
+  - `auxiliary.web_extract.model: gpu-vision` (RTX 5070)
  - `auxiliary.compression.model: syslog-auto` (Strix Halo)
 - Default model (`model.default`) and custom_provider remain `syslog-auto` for auto-routing
 - For 128K context window: `threshold: 0.65` (fires at ~85K tokens)
@@ -296,11 +290,10 @@ The following MUST be identical across ALL profiles:
 - See `devops-hermes-compression` skill for full reference

 ### Rule 10: Default Model Must Be `syslog-auto` (All Agents)
- **Koby Exception**: Per captain ruling 2026-08-11, Koby is a DeepSeek-primary external agent; its primary model remains `deepseek-v4-flash` (via api.deepseek.com to preserve DeepSeek-specific reasoning, while other sections follow Rule 10.
 - **Hermes agents**: `model.default: syslog-auto`, `custom_providers[0].model: syslog-auto`
 - **pi agents**: `defaultModel: syslog-auto` in `settings.json`, first model in `models.json`
 - `syslog-auto` is the LiteLLM routing model — it load-balances between strix-moe
-  and qwen3.6-27B-code, with gemma-4-12b as fallback. Using it protects against:
+  and qwen3.6-27B-code, with gpu-vision as fallback. Using it protects against:
  - Model name typos that cause 403 errors and silent worker failures
  - Single GPU downtime (routing falls back automatically)
  - Key/model authorization mismatches
@@ -325,13 +318,10 @@ verify ALL FOUR of these against the live config. They are the only root causes
 1. **max_context_window correct?** — BOTH `compression.max_context_window` AND `context.max_context_window`
   MUST be `131072` (all GPUs are 128K). A value of `262144` causes instability near 100K and must NOT be used.
   ~83K instead of ~170K. Check: `grep -n max_context_window ~/.hermes/config.yaml`
-2. **base_url uses authenticated path?** — `custom_providers[0].base_url`, `delegation.base_url`,
-   and ALL `auxiliary.*.base_url` MUST be `http://192.168.68.116/litellm/v1` (Rule 5, canonical)
-   or `http://192.168.68.116/v1` (legacy, still authenticated via nginx). BOTH verified 200 with
-   key + 600s proxy_read_timeout on 2026-08-09. Never bare `:4000` direct.
-   Check: `grep -nE 'base_url: http://192.168.68.116(:4000)?/v1' ~/.hermes/config.yaml` — the
-   ONLY paths allowed are `/v1` or `/litellm/v1` (both via nginx :80).
-   `:4000` or missing `litellm/v1`/`v1` prefix = violation.
+2. **base_url uses /v1 NOT /litellm/v1?** — `custom_providers[0].base_url`, `delegation.base_url`,
+   and ALL `auxiliary.*.base_url` MUST be `http://192.168.68.116/v1` (Rule 5). nginx `/litellm/`
+   has a 60s default timeout → 504 on any inference >60s; `/v1/` has 600s.
+   Check: `grep -n 'litellm/v1' ~/.hermes/config.yaml` (must return NOTHING)
 3. **LITELLM_API_KEY valid?** — The key must be a real LiteLLM key (`sk-` + 64 hex, 67 chars).
   Malformed values (e.g. `sk-_SWAl_Vu_…`, 47 chars) return 401 → DeepSeek fallback.
   Verify: `curl -s -o /dev/null -w '%{http_code}' -H "Authorization: Bearer $LITELLM_API_KEY" http://192.168.68.116/v1/models` (must be 200)
@@ -348,6 +338,17 @@ curl -s -o /dev/null -w 'key_health: %{http_code}\n' -H "Authorization: Bearer $

 ### Rule 13: API Key Injection — Two Patterns (UPDATED 2026-07-16, WAL #1300)

+### Rule 14: Hermes Context Detection Uses `max_model_tokens`, NOT `max_input_tokens`
+
+**CRITICAL**: Hermes context detection reads `max_model_tokens` (128K), NOT `max_input_tokens` (64K cap).
+
+- **Abiba and Hermes agents**: `max_model_tokens: 131072` (128K) — unlimited context
+- **Crewmates (ops, tune, verify, auth-keys, build)**: `max_input_tokens: 64000` (64K) — capped
+- If you see `max_input_tokens: 64000` in an Abiba/Hermes config, that's a mistake
+- Using `max_input_tokens` for Hermes agents causes premature context loss
+- Check: `grep -n 'max_model_tokens\|max_input_tokens' ~/.hermes/config.yaml`
+- Expected output: `max_model_tokens: 131072` (not max_input_tokens)
+
 Agents inject `LITELLM_API_KEY` via ONE of two mechanisms. Both are valid; the contract
 requirement is that the key is a **valid LiteLLM virtual key** (HTTP 200 on /v1/models).

@@ -406,15 +407,6 @@ curl -s -o /dev/null -w '%{http_code}' -H "Authorization: Bearer $K" http://192.
 - **Audit script**: Run `python3 /root/prose-contracts/audit-hermes-config.py <config.yaml>`
  before and after any config change to catch this and all other rule violations.

-### Rule 15: MCP Endpoint and Header Validation (ADDED 2026-08-07)
- Every MCP server entry must point at the correct endpoint:
-  - ra-h-os = http://192.168.68.65:3100/mcp
-  - litellm = https://litellm.sysloggh.net/mcp
- MCP entries must carry a REAL key value in the header.
-  - Avoid using env-var names like LITELLM_API_KEY in the header; they do not resolve for MCP
-    endpoints and result in "Malformed API Key" floods.
-  - Ensure the header value is the actual key (e.g., `sk-...`).
-
 ## Execution

 1. **Check current config** — Read the target agent's config.yaml
@@ -424,13 +416,14 @@ curl -s -o /dev/null -w '%{http_code}' -H "Authorization: Bearer $K" http://192.
 5. **Set model choice** — Per agent's workload
 6. **Verify** — curl all shared endpoints, test the model with the new key
 7. **Report** — What was changed, preserved, custom
-### Rule 16: Koby Configuration (DeepSeek-primary)
-(Ref: See Rule 10 for default model behavior, with Koby exception)

-Koby uses a split-model architecture:
+### Rule 17: Koby Report-Only (URGENT — 2026-08-17, Captain)

- Primary Model: `deepseek-v4-flash` via `api.deepseek.com` (for reasoning)
- Auxiliary Models: `gpu-light` (vision/web_extract) and `syslog-auto` (compression)
- Key Hygiene: `api_key_env` is strictly `LITELLM_API_KEY` or `DEEPSEEK_API_KEY`
- Constraint: Do NOT touch Koby's primary model/provider/compression settings unless explicitly ruled by the captain.
+**Koby (CT 111, .129, tdunna/Theo) is report-only, full stop.**
+No heal step, no restart, no key rotation, no config edit, no memory rewrite,
+no disk GC, no service touch, no process kill — **ever**.
+Do NOT "repair" Koby under any circumstance, even if a health check shows it degraded.
+Detect + report to Zulip (Theo fixes it).

+This supersedes every other instruction in this file.
+If a rule would trigger a Koby repair action, SKIP it and emit a diagnostic alert.
@@ -34,12 +34,11 @@ Syslog is migrating away from **unauthenticated direct access** to the shared in

 | Path | Auth | Status |
 |------|------|--------|
-| `http://192.168.68.116/v1` | Bearer `sk-*` key (nginx-fronted) | ✅ **VALID** — authenticated via nginx :80 (verified 2026-08-09: 401 without key, 200 with) |
-| `http://192.168.68.116/litellm/v1` | Bearer `sk-*` key (nginx-fronted) | ✅ **CURRENT / CANONICAL** — captain-approved migration target; 600s proxy_read_timeout (verified) |
-| `http://192.168.68.116:4000/v1` | Bearer `sk-*` key (direct container) | ❌ **FORBIDDEN** — bypasses nginx; port 4000 direct is not a config path |
+| `http://192.168.68.116/v1` | None (direct) | ❌ **DEPRECATED** — being phased out |
+| `http://192.168.68.116/litellm/v1/responses` | Bearer `sk-*` key | ✅ **CURRENT** — authenticated LiteLLM proxy |

-All harness/litellm providers MUST use an authenticated nginx-fronted path (`/litellm/v1` canonical, `/v1` legacy-valid).
-Any `base_url` pointing at `:4000` or a bare IP without nginx is a **migration violation**.
+All harness/litellm providers MUST use the authenticated `/litellm/v1/responses` path.
+Any `base_url` pointing to bare `/v1` on 192.168.68.116 is a **migration violation**.

 ### 🔥 CRITICAL: Double-Path Bug (2026-07-10)

@@ -178,7 +177,7 @@ The agent picks up the new key via `infisical run --` at gateway startup.
 # In litellm_config.yaml — ensures all future keys inherit these defaults:
 litellm_settings:
  default_key_generate_params:
-    models: ["syslog-auto", "qwen3.6-27B-code", "gemma-4-12b"]
+    models: ["syslog-auto", "qwen3.6-27B-code", "gpu-vision"]
    duration: null        # ← permanent
    max_budget: 100
    metadata:
@@ -190,23 +189,23 @@ litellm_settings:
 | Agent | CT | IP | LiteLLM Alias | Key Source | Status | Gateway Wrapper | Last Verified |
 |-------|-----|-----|---------------|------------|--------|-----------------|---------------|
 | Tanko | 112 | .122 | `tanko` | Infisical vault | ✅ Fixed | `infisical run` | 20:17 UTC Jul 5 |
-| Mumuni | 105 (kagentz) | .14 | `mumuni` | Infisical vault | ✅ Fixed | systemd Hermes gateway | 2026-08-29 |
-| Koby | 111 | .129 | `koby` | Infisical vault | ✅ Fixed (DeepSeek-primary) | `infisical run` | 23:30 UTC Jul 5 |
-| Koonimo | 113 | .114 | `koonimo` | Infisical vault | ✅ Fixed | `infisical run` (migrated 2026-07-11) | 2026-08-09 |
+| Mumuni | 100 (abiba) | .24 | `mumuni` | Infisical vault | ✅ Fixed | Pi Hermes gateway | 2026-07-27 |
+| Koby | 111 | ? | `koby` | Infisical vault | ✅ Fixed | `infisical run` | 23:30 UTC Jul 5 |
+| Koonimo | 113 | ? | `koonimo` | Infisical vault | ✅ Fixed | `infisical run` (migrated 2026-07-11) | 2026-07-11 |
 | Abiba | 100 | .65 | `abiba-pi` | Infisical vault | ✅ N/A (pi native) | — | 19:44 UTC Jul 5 |
-| Kagenz0 | 105 | .14 | — | — | ❌ DOWN | — | 19:14 EDT Jul 4 |
+| Kagenz0 | 105 | ? | — | — | ❌ DOWN | — | 19:14 EDT Jul 4 |

 > **Note**: CT hostnames (tdunna, baggy) differ from agent identities (koby, koonimo).
 > LiteLLM key aliases use agent identity, not CT hostname.

 ### Migration Status: Authenticated Path

-| Agent | `/litellm/v1` | Legacy `/v1` | Status |
-|-------|--------------|-------------|--------|
-| Mumuni | ✅ harness provider | ✅ auxiliary on /v1 (valid) | ✅ Authenticated (verified 2026-08-09) |
-| Tanko | ✅ 5 sections | 0 | ✅ Migrated 2026-08-08, keys 200 |
-| Koby | ✅ custom provider (harness name) | — | ✅ External DeepSeek primary (intentional, captain ruling 2026-08-11) |
-| Koonimo | ✅ .114 (baggy) | — | ✅ 128K context applied 2026-08-09 |
+| Agent | `/litellm/v1/responses` | Deprecated `/v1` | Status |
+|-------|--------------------------|--------------------|--------|
+| Mumuni | ✅ 5 sections | 0 | ✅ Authenticated |
+| Tanko | ⚠️ No SSH access | — | Needs check |
+| Koby | ⚠️ No route to host | — | Needs check |
+| Koonimo | ⚠️ Connection timed out | — | Needs check |

 ### Systemd Service Pattern (2026-07-11 — vault migration)

@@ -285,14 +284,14 @@ auxiliary:
  vision:
    api_key: sk-<agent-key-from-vault>           # ← workaround (get via: infisical secrets get LITELLM_API_KEY --project=agents --env=production --plain)
    api_key_env: LITELLM_API_KEY
-    base_url: http://192.168.68.116/litellm/v1
-    model: gemma-4-12b
+    base_url: http://192.168.68.116/v1
+    model: gpu-vision
    provider: harness
  compression:
    api_key: sk-<agent-key-from-vault>           # ← workaround (same as above)
    api_key_env: LITELLM_API_KEY
-    base_url: http://192.168.68.116/litellm/v1
-    model: gemma-4-12b
+    base_url: http://192.168.68.116/v1
+    model: gpu-vision
    provider: harness
 ```

@@ -55,7 +55,7 @@ connectivity recovery including end-to-end DM validation.

 | Host | CT | Proxmox | IP (direct) | Hermes Home | User |
 |------|-----|---------|-------------|-------------|------|
-| Mumuni | CT105 | minipve | 192.168.68.14 | /home/hermes/.hermes | hermes |
+| Mumuni | CT100 | — | 192.168.68.24 | /root/.hermes | root |
 | Tanko | CT112 | amdpve | 192.168.68.122 | /home/jerome/.hermes | jerome |
 | Koby | CT111 | amdpve | 192.168.68.129 | /root/.hermes | root |
 | Shumba | — | — | 192.168.68.119 | /home/lucky/.hermes | lucky |
@@ -1,4 +1,6 @@
 ---
+report_only_agents:
+  - koby  # ⛔ KOBY IS NEVER REPAIRED (Rule 17, 2026-08-17) — detect + report, never fix on .129
 kind: function
 name: hermes-zulip-restore
 description: >
@@ -12,6 +14,7 @@ version: 1.0.0
 status: active
 runtime_contract: 2
 ---
+---

 # Hermes Zulip Restore — Bring Any Agent Back to Good State

@@ -51,7 +54,7 @@ gateway restart, and connection validation.

 | Host | CT | Proxmox | IP (direct) | Hermes Home | User |
 |------|-----|---------|-------------|-------------|------|
-| Mumuni | CT105 (kagentz) | minipve | 192.168.68.14 | /home/hermes/.hermes | hermes |
+| Mumuni | CT100 (abiba) | hwepve | 192.168.68.24 | /root/.hermes | root |
 | Tanko | CT112 | amdpve | 192.168.68.122 | /home/jerome/.hermes | jerome |
 | Koby | CT111 | amdpve | 192.168.68.129 | /root/.hermes | root |
 | Shumba | — | — | 192.168.68.119 | /home/lucky/.hermes | lucky |
@@ -184,6 +187,7 @@ https://git.sysloggh.net/SyslogSolution/zulip-platform-plugins/src/branch/feat/z
 Commit `55ca15d` — `fix(zulip): add _strip_html for slash command matching`
 Pull request #33 is the primary integration branch.

+---
 ---

 **Last verified good state**: 2026-07-08 — Mumuni, Tanko, Koby all connected with `_strip_html` applied.
@@ -99,5 +99,5 @@ call enable-prompt-caching

 call verify-latency
  host: 192.168.68.116
-  models: [syslog-auto, qwen3.6-27B-code, gemma-4-12b]
+  models: [syslog-auto, qwen3.6-27B-code, gpu-vision]
 ```
@@ -3,7 +3,7 @@ kind: pattern
 name: infrastructure-control
 description: >
  Full infrastructure monitoring and control pattern covering the
-  5-node Proxmox cluster, 3 Docker ecosystems (22 containers),
+  6-node Proxmox cluster, 3 Docker ecosystems (22 containers),
  NFS storage, and network services. Defines monitors, remediations,
  and the access matrix for all environments.

@@ -13,11 +13,10 @@ description: >
  against the live system. Policy fields are authoritative. See the
  `verify-before-mutate` skill.

-  **Last verified:** 2026-08-15 — hwepve removed from Tabiri cluster
-  (now 5 nodes: minipve, amdpve, storepve, acerpve, ocupve). hwepve
-  (192.168.68.4) is a standalone PVE node + NetBird routing peer;
-  London relocation pending. CTs 100 (abiba) and 105 (kagentz) moved
-  to minipve.
+  **Last verified:** 2026-07-24 — corrected Gitea IP (.17 not .110),
+  AdGuard IP (.10 not .102), AdGuard placement (minipve not acerpve),
+  Abiba placement (hwepve not amdpve), added hwepve as 6th node,
+  added dns.sysloggh.net route.
 ---

 # Infrastructure Control Pattern
@@ -35,21 +34,21 @@ description: >
   ┌─────────────┐    ┌──────────────┐    ┌──────────────┐
   │   Abiba     │    │   Tanko      │    │   Mumuni     │
   │   (pi)      │    │   (Hermes)   │    │   (Hermes)   │
-   │   CT 100    │    │   CT 112     │    │   CT 100     │
+   │   CT 100    │    │   CT 112     │    │   CT 114     │
   └──────┬──────┘    └──────┬───────┘    └──────┬───────┘
          │                  │                    │
          └──────────────────┼────────────────────┘
                             ▼
-          ┌────────────────────────────────────┐
-          │         Proxmox Cluster API        │
-          │    minipve.sysloggh.net:443        │
-          │   (monitoring@pve!mumuni token)    │
-          └────┬──────┬──────┬──────┬──────────┘
-               │      │      │      │
-          ┌────┘ ┌────┘ ┌────┘ ┌────┘
-          ▼      ▼      ▼      ▼
-       minipve amdpve storepve acerpve ocupve
-        (.12)   (.15)   (.6)    (.9)    (.5)
+          ┌──────────────────────────────────────┐
+          │         Proxmox Cluster API          │
+          │    minipve.sysloggh.net:443          │
+          │   (monitoring@pve!mumuni token)      │
+          └────┬──────┬──────┬──────┬──────┬─────┘
+               │      │      │      │      │
+          ┌────┘ ┌────┘ ┌────┘ ┌────┘ ┌────┘
+          ▼      ▼      ▼      ▼      ▼
+       minipve amdpve storepve acerpve ocupve hwepve
+        (.12)   (.15)   (.6)    (.9)    (.5)    (.4)

          ▼
   ┌─────────────────────────────────────────────┐
@@ -101,29 +100,21 @@ description: >

 ## Section 2: Proxmox Cluster — Monitoring

-### Nodes (5)
+### Nodes (6)

 | Node | IP | CPU | RAM | VMs/CTs | Role |
 |------|----|-----|-----|---------|------|
-| minipve | .12 | 16C | 30GB | abiba, kagentz, authentik, gitea, syslog-api, infisical-vault, jitsi | Auth, git, messaging |
+| minipve | .12 | 16C | 30GB | authentik, gitea, syslog-api, infisical-vault, jitsi | Auth, git, messaging |
 | amdpve | .15 | 32C | 62GB | tanko, tdunna, baggy, scottdenya | Agents, compute |
 | storepve | .6 | 28C | 31GB | docker-vm, ra-h-os, PBS, media, jdownloader, zulip | Docker, storage, chat |
 | acerpve | .9 | 28C | 31GB | llm-gpu | GPU VMs |
 | ocupve | .5 | 12C | 14GB | ocu-llm | GPU VMs |
+| hwepve | .4 | 12C | 15GB | abiba, kagentz, (mumuni CT 114 stopped) | Agents (new node) |

 > **Note:** CTs on storepve include jdownloader (CT 118). AdGuard (CT 102) is on
-> minipve at .10, not acerpve. Abiba (CT 100) and kagentz (CT 105) are on
-> minipve (moved from hwepve 2026-08-15). Mumuni runs inside Abiba CT100
-> (.24); CT 114 (mumuni) no longer exists in the cluster.
->
-> **hwepve (192.168.68.4) — STANDALONE (removed from Tabiri 2026-08-15):**
-> Huawei MateBook 16 (KLVL-WXX9), pve-manager/9.2.10, kernel 7.0.14-8-pve.
-> Zero VMs/CTs. Being relocated to London as a standalone PVE node + NetBird
-> routing peer (relocation pending). Localizations applied: timezone
-> Europe/London, lid-switch ignore, sleep/suspend/hibernate targets masked,
-> cluster-shared storage removed (remaining: local, local-lvm, storage,
-> mediastore). prometheus-node-exporter active on :9100; net.ipv4.ip_forward=1;
-> NetBird client not yet installed (enrollment pending setup key).
+> minipve at .10, not acerpve. Abiba (CT 100) is on hwepve, not amdpve. Mumuni
+> (CT 114) is on hwepve (currently stopped), not minipve. Mumuni also has a
+> second instance on minipve at .123 — distinguish by CT ID, not hostname.

 ### Checks (every 5 min)

@@ -601,12 +592,12 @@ ssh root@192.168.68.110 "systemctl restart llama-server"

 | CT | Name | Node | IP | Role | Agent |
 |----|------|------|----|------|-------|
-| 100 | abiba | minipve | .24 | Pi agent | ✅ pi |
+| 100 | abiba | **hwepve** | .24 | Pi agent | ✅ pi |
 | 101 | llm-gpu | acerpve | .8 | GPU RTX 3090 | ❌ |
 | 102 | adguard | **minipve** | **.10** | DNS | ❌ |
 | 103 | ocu-llm | ocupve | .110 | GPU RTX 5070 | ❌ |
 | 104 | authentik | minipve | .11 | OIDC | ❌ |
-| 105 | kagentz | minipve | — | Agent Zero | ✅ |
+| 105 | kagentz | **hwepve** | — | Agent Zero | ✅ |
 | 106 | ra-h-os | storepve | .65 | KG bridge | ✅ MCP |
 | 107 | pbs | storepve | — | Backups | ❌ |
 | 108 | media | storepve | — | Media | ❌ |
@@ -615,6 +606,7 @@ ssh root@192.168.68.110 "systemctl restart llama-server"
 | 111 | tdunna | amdpve | .129 | Hermes agent | ✅ |
 | 112 | tanko | amdpve | .122 | Hermes agent | ✅ |
 | 113 | baggy | amdpve | .114 | Hermes agent | ✅ |
+| 114 | mumuni | **hwepve** | .123 | Hermes agent (stopped) | ✅ |
 | 115 | scottdenya | amdpve | .75 | Denya OneCare | ❌ |
 | 116 | syslog-api | minipve | .116 | LiteLLM + Grafana | ❌ |
 | 117 | zulip | storepve | .19 | Chat | ❌ |
@@ -639,14 +631,15 @@ Source of truth: `/root/scripts/pct-run.sh` or `prose-contracts/scripts/pct-run.

 | CT | Name | Node | pct-run |
 |-----|------|------|---------|
-| 100 | abiba | minipve | `pct-run 100` |
-| 105 | kagentz | minipve | `pct-run 105` |
+| 100 | abiba | hwepve | `pct-run 100` |
+| 105 | kagentz | hwepve | `pct-run 105` |
 | 111 | tdunna | amdpve | `pct-run 111` |
 | 112 | tanko | amdpve | `pct-run 112` |
 | 113 | baggy | amdpve | `pct-run 113` |
 | 115 | scottdenya | amdpve | `pct-run 115` |
 | 104 | authentik | minipve | `pct-run 104` |
 | 110 | gitea | minipve | `pct-run 110` |
+| 114 | mumuni | hwepve | `pct-run 114` |
 | 116 | syslog-api | minipve | `pct-run 116` |
 | 106 | ra-h-os | storepve | `pct-run 106` |
 | 107 | proxmox-backup | storepve | `pct-run 107` |
@@ -659,7 +652,7 @@ GPU bare-metal hosts (.8 acerpve, .110 ocupve, .15 amdpve) are NOT CTs — use S
 ssh root@192.168.68.8   # RTX 3090
 ssh root@192.168.68.110 # RTX 5070
 ssh root@192.168.68.15  # Strix Halo
-ssh root@192.168.68.4   # hwepve — standalone London node + NetBird routing peer (relocation pending)
+ssh root@192.168.68.4   # hwepve (abiba, kagentz, mumuni)
 ```

 ## Section 7: Agent Health Check (consolidated — 2026-07-05)
@@ -7,15 +7,13 @@ description: >
  from nvidia-smi (.8, .110) and amdgpu_top (.15). LiteLLM metrics
  via existing /metrics Prometheus endpoint.
  
-  DEPLOYMENT STATUS (2026-08-09):
+  DEPLOYMENT STATUS (2026-07-09):
  ✅ Core stack deployed: Prometheus + Grafana + pve/node/docker exporters
-     (via proxmox-monitor contract). Grafana at :3001, all scrape targets active.
-  ✅ GPU exporters DEPLOYED: all 3 GPU hosts (.8/.110/.15) run exporters on
-     :9400 (nvidia_gpu_exporter / amdgpu exporter) — verified 200 on 2026-08-09.
-  ✅ LiteLLM /metrics scraping live (success_callback: prometheus; auth via
-     master key) + Alertmanager + Zulip bridge (alerts-infra) added 2026-08-09.
-  ⚠️ This contract is target-state aspirational — but GPU export + alerting
-     are now as-built (verified 2026-08-09).
+     (via proxmox-monitor contract). Grafana at :3001, 5 scrape targets active.
+  ❌ GPU exporters NOT deployed: gpu-exporter crash-loops on .15,
+     NVIDIA sidecar exporters (.8/.110:9400) never installed.
+     Router falls back to direct GPU /health probes.
+  ⚠️ This contract is target-state aspirational — not as-built.
     As-built GPU monitoring is via gpu-monitor contract (port 9100 poll).
 version: 1.0.0
 ---
@@ -102,13 +100,56 @@ GPU .8 (RTX 3090)    GPU .110 (RTX 5070)   GPU .15 (Strix Halo)
 - Stack persists across reboots (systemd for exporters, Docker restart policy)

 ## Execution
+
+### Phase 1: GPU Exporters
+
+**NVIDIA (.8 and .110)**:
+1. Download `nvidia_gpu_exporter` binary
+2. Create systemd service `nvidia-gpu-exporter.service`
+3. Start and enable
+
+**AMD (.15)**:
+1. Create Python exporter script at `/opt/amdgpu-exporter/exporter.py`
+2. Parses `amdgpu_top --json -d 1000` output
+3. Exposes key metrics at `:9400/metrics` via Python http.server
+4. Create systemd service
+5. Start and enable
+
+### Phase 2: Prometheus
+
+1. Create `/opt/monitoring/` directory on CT 116
+2. Write `prometheus.yml` with scrape configs for all targets
+3. Add to docker-compose (or separate compose file)
+4. Start container
+
+### Phase 3: Grafana
+
+1. Create `/opt/monitoring/grafana/` directories
+2. Provision Prometheus datasource
+3. Provision GPU fleet dashboard JSON
+4. Provision LiteLLM dashboard JSON
+5. Add to docker-compose
+6. Start container
+
+### Phase 4: Verification
+
+1. Verify all 3 GPU exporters return 200 at :9400/metrics
+2. Verify Prometheus targets all UP at :9090/targets
+3. Verify Grafana accessible at :3001 with dashboards
+4. Verify LiteLLM metrics flowing to Prometheus
+5. ~~Update nginx to proxy `/monitoring/` → Grafana~~ (NOT recommended — nginx sub-path was tried for /grafana/ and reverted per proxmox-monitor; direct :3001 access is the standard)
+
+## Execution
+
 ### check-health

 **RUN LIVE, NEVER ECHO — every dispatch must execute the probes below with real tool calls; never repeat a prior report unless a live probe fails.**

 ```bash
 # Zulip API health (POST ping)
-curl -s -o /dev/null -w '%{http_code}' -X POST https://chat.sysloggh.net/api/v1/messages -u 'abiba-bot@chat.sysloggh.net:KEY'
+source /etc/litellm-monitor.env
+ZULIP_USER="abiba-bot@chat.sysloggh.net"
+curl -s -o /dev/null -w '%{http_code}' -X POST https://chat.sysloggh.net/api/v1/messages -u "${ZULIP_USER}:${ZULIP_BOT_KEY}"
 # Expected: 200 (HTTP 000 = unreachable/cache)

 # PM2 process health
@@ -135,7 +176,6 @@ curl -s http://192.168.68.116:4001/metrics | head -20

 **Report format**: Summarize actual results from each probe. If any probe returns non-200 or empty output, flag as alert.

-
 ### Phase 1: GPU Exporters

 **NVIDIA (.8 and .110)**:
@@ -2,7 +2,7 @@
 kind: responsibility
 name: infrastructure-update
 description: >
-  Autonomous system-wide update contract covering all 5 Proxmox nodes,
+  Autonomous system-wide update contract covering all 6 Proxmox nodes,
  15+ containers/VMs, and 4 Docker ecosystems. Updates apt packages,
  Docker images, and container stacks in safe waves with health checks
  and automatic rollback on failure.
@@ -56,10 +56,11 @@ Before ANY update wave:
 | amdpve (.15) | Proxmox node | `apt update && apt upgrade -y` | 5 min |
 | acerpve (.9) | Proxmox node | `apt update && apt upgrade -y` | 5 min |
 | ocupve (.5) | Proxmox node | `apt update && apt upgrade -y` | 5 min |
+| hwepve (.4) | 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 100 (mumuni/abiba, minipve) | Mumuni | `apt update && apt upgrade -y` | 3 min |
+| CT 100 (mumuni/abiba, hwepve) | 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 |

@@ -162,9 +163,9 @@ Before Wave 1, snapshot these files:
 /etc/systemd/system/strix-server.service                (amdpve .15 — strix-moe)
 /etc/systemd/system/llama-server.service                (VM 101 .8, VM 103 .110)
 # Hermes agent configs (key enforcement — 2026-07-10)
-/root/.hermes/config.yaml                               (Mumuni inside CT 100, Tanko CT 112, etc.)
-/root/.config/systemd/user/hermes-gateway.service       (Mumuni inside CT 100 — EnvironmentFile fixed)
-/etc/environment                                        (Mumuni inside CT 100 — LITELLM_API_KEY)
+/root/.hermes/config.yaml                               (Mumuni CT 114, Tanko CT 112, etc.)
+/root/.config/systemd/user/hermes-gateway.service       (Mumuni CT 114 — EnvironmentFile fixed)
+/etc/environment                                        (Mumuni CT 114 — LITELLM_API_KEY)
 ```

 ## MCP Gateway (2026-07-10)
@@ -218,7 +219,7 @@ When LiteLLM is upgraded to a version supporting per-key MCP grants:

 ## Success Criteria

- [ ] All 5 PVE nodes updated, no reboot-loop
+- [ ] All 6 PVE nodes updated, no reboot-loop
 - [ ] All VMs/CTs running post-update
 - [ ] All Docker containers healthy (VM 109 + CT 116 + CT 117)
 - [ ] LiteLLM inference passing (syslog-auto test)
@@ -234,7 +235,7 @@ After completion, send Zulip DM:
 ```
 📋 Infrastructure Update — YYYY-MM-DD

-Updated: 5 PVE nodes, 12 CTs/VMs, 30+ containers
+Updated: 6 PVE nodes, 12 CTs/VMs, 30+ containers
 Security fixes: N CVEs patched
 Downtime: <service> <duration>
 Failures: none / <details>
@@ -68,7 +68,7 @@ description: >
   - Generate new key with key_alias: "{agent_name}" (e.g., "tanko" — bare name, no date)
   - Set metadata: { "agent": "{agent_name}", "purpose": "agent-inference" }
   - Duration is null (permanent) — inherited from litellm default_key_generate_params
-   - Set models: ["syslog-auto", "qwen3.6-27B-code", "gemma-4-12b", "strix-moe", "gpu-dense", "gpu-light", "qwen3.6-35B-udq4"]
+   - Set models: ["syslog-auto", "qwen3.6-27B-code", "gpu-vision", "strix-moe", "gpu-dense", "gpu-light", "qwen3.6-35B-udq4"]
   - Note: `ornith-1.0-35b` is NOT a valid LiteLLM model name (use `strix-moe`, the stable alias). qwen3.6-35B-A3B removed from fleet (was never deployed).
   - Return the new key
 5. **If action == "rotate"**:
@@ -178,7 +178,7 @@ through its agent wrapper.
 | Agent | Host | Pattern | Keys | Status |
 |-------|------|---------|------|--------|
 | abiba | .24 | pi agent wrapper | ABIBA_LITELLM_API_KEY + ABIBA_ZULIP_API_KEY | ✅ vault-backed |
-| mumuni | .14 (kagentz CT105) | systemd unit hermes-gateway.service (user hermes) | MUMUNI_LITELLM_API_KEY + MUMUNI_ZULIP_API_KEY | ✅ vault-backed + .env fallback |
+| mumuni | .24 (CT100 abiba) | Pi Hermes gateway (no systemd) | MUMUNI_LITELLM_API_KEY + MUMUNI_ZULIP_API_KEY | ✅ vault-backed + .env fallback |
 | tanko | .122 | systemd drop-in + while-true wrapper + st.8e848433 (user jerome) | TANKO_LITELLM_API_KEY + TANKO_ZULIP_API_KEY | ✅ vault-backed + .env fallback |
 | koby | .129 | systemd drop-in + while-true wrapper + st.8e848433 | KOBY_LITELLM_API_KEY, shares TANKO_ZULIP_API_KEY (tanko-bot) | ✅ vault-backed |
 | koonimo | .114 | systemd drop-in + while-true wrapper + st.8e848433 | KOONIMO_LITELLM_API_KEY + KOONIMO_ZULIP_API_KEY | ✅ vault-backed |
@@ -270,7 +270,7 @@ reads use per-agent identities. This eliminates the single shared token risk.
 | 2026-07-16 | vault | cleanup | 4 stale secrets deprecated. 5 personal creds flagged. |
 | 2026-07-16 | koonimo | add-zulip | Added KOONIMO_ZULIP_API_KEY to vault. Wrapper injects ZULIP_API_KEY + ZULIP_EMAIL. 3 platforms. |
 | 2026-07-16 | tanko | migrate | Migrated from hardcoded config.yaml to infisical-gateway.sh + st.353699cd. NOTE: st.353699cd later deleted — reverted to st.8e848433 on 2026-07-17. |
-| 2026-07-16 | mumuni | rotate | Old key malformed (sk-_SWAl_Vu_, 47 chars, not LiteLLM format) → 401. Deleted old `mumuni` key (token 15cbca18…), generated fresh (alias `mumuni`, 7 models: syslog-auto, qwen3.6-27B-code, gemma-4-12b, strix-moe, gpu-dense, gpu-light, qwen3.6-35B-udq4). New key sk-OzuWsoX2… written to /root/.hermes/.env (Rule 3/13 fallback). Vault sync PENDING (needs machine identity). WAL #1300. |
+| 2026-07-16 | mumuni | rotate | Old key malformed (sk-_SWAl_Vu_, 47 chars, not LiteLLM format) → 401. Deleted old `mumuni` key (token 15cbca18…), generated fresh (alias `mumuni`, 7 models: syslog-auto, qwen3.6-27B-code, gpu-vision, strix-moe, gpu-dense, gpu-light, qwen3.6-35B-udq4). New key sk-OzuWsoX2… written to /root/.hermes/.env (Rule 3/13 fallback). Vault sync PENDING (needs machine identity). WAL #1300. |
 | 2026-07-16 | koby | rotate | Old key sk-6sbCNjz (401, stale in /etc/environment). Deleted old `koby` key, generated fresh (alias `koby`). New key sk-BqRRMboTI… in systemd drop-in `hermes-gateway.service.d/litellm-key.conf` + /etc/environment. Created `hermes-gateway.service` unit (was missing — gateway wasn't persistent) with `--replace`. Verified HTTP 200, Telegram connected. |
 | 2026-07-16 | baggy (koonimo) | rotate | Old key sk-krnw_zGB (401, hardcoded in systemd drop-in). Deleted old `baggy` key, generated fresh (alias `baggy`, metadata agent=koonimo). New key sk-OEK7z26n6E… in drop-in `hermes-gateway.service.d/litellm-key.conf`. CT113 IP changed .113→.114. Verified HTTP 200, Zulip connected. |

@@ -18,15 +18,6 @@ description: >
  Designed as a reusable contract for any Syslog agent.
  
  Source of truth: gpu-fleet.prose.md
-
-  ## Monitoring / Alerting (as-built 2026-08-09)
-
-  - LiteLLM /metrics scrape job: requires `litellm_settings.success_callback: [prometheus]`
-    (failure_callback alone does NOT mount /metrics — verified 2026-08-09).
-    Scraped by Prometheus with Bearer master key; endpoint returns 307 → /metrics/.
-  - Alertmanager (harness-alertmanager :9093) + zulip-bridge (:9102) deliver
-    firing alerts to #agent-hub > alerts-infra via abiba-bot. Added 2026-08-09.
-  - Prometheus node job covers ALL 5 PVE nodes (.5/.6/.9/.12/.15:9100).
 ---

 ## Architecture (v4.0.0 — Direct: nginx → LiteLLM → GPU)
@@ -82,15 +73,15 @@ Request → nginx:80 → LiteLLM:4000 → GPU(llama-server, parallel 2)
 | Host | IP | Hardware | Models Served | Engine | Context | Parallel |
 |------|-----|----------|---------------|--------|---------|----------|
 | llm-gpu | 192.168.68.8 | NVIDIA RTX 3090 (24 GB) | qwen3.6-27B-code | llama-server systemd | **128K** | 2 |
-| ocu-llm | 192.168.68.110 | NVIDIA RTX 5070 (12 GB) | gemma-4-12b | llama-server systemd | **128K** | 2 |
+| ocu-llm | 192.168.68.110 | NVIDIA RTX 5070 (12 GB) | gpu-vision | llama-server systemd | **128K** | 2 |
 | amdpve | 192.168.68.15 | AMD Strix Halo 64GB UMA | qwen3.6-35B-udq4 (LiteLLM alias: strix-moe) | llama-server systemd (Vulkan) | 128K | 2 |

 ## Model Fallback Chains (LiteLLM)

 | Primary | Timeout | Fallback | Timeout |
 |---------|---------|----------|---------|
-| qwen3.6-27B-code | 300s | gemma-4-12b | 120s |
-| gemma-4-12b | 120s | qwen3.6-27B-code | 300s |
+| qwen3.6-27B-code | 300s | gpu-vision | 120s |
+| gpu-vision | 120s | qwen3.6-27B-code | 300s |
 | qwen3.6-35B-udq4 / strix-moe | 300s | qwen → gemma | — |
 | syslog-auto (balanced) | 300s | qwen → gemma | — |

@@ -136,7 +127,7 @@ Request → nginx:80 → LiteLLM:4000 → GPU(llama-server, parallel 2)
   - Check alerts array for active warnings/critical

 7. **Check model inference via LiteLLM** — Test each model:
-   - POST /v1/chat/completions model=gemma-4-12b → expect 200
+   - POST /v1/chat/completions model=gpu-vision → expect 200
   - POST /v1/chat/completions model=qwen3.6-27B-code → expect 200
   - POST /v1/chat/completions model=strix-moe → expect 200
   - Use master key for auth
@@ -1,4 +1,6 @@
 ---
+report_only_agents:
+  - koby  # ⛔ KOBY IS NEVER REPAIRED (Rule 17, 2026-08-17) — detect + report, never fix on .129
 kind: responsibility
 name: litellm-self-heal
 status: deployed
@@ -22,6 +24,7 @@ description: >
  inference, and agent keys. Applies remediation rules for common failures.
  Reports every action via Zulip DM and Gitea (SyslogSolution/health-logs).
 ---
+---

 # LiteLLM Operations — Health Check + Self-Heal

@@ -58,26 +61,34 @@ Request → nginx:80 → LiteLLM:4000 → GPU(llama-server, parallel 2)
 | Host | IP | Hardware | Models Served | Engine | Context | Parallel |
 |------|-----|----------|---------------|--------|---------|----------|
 | llm-gpu | 192.168.68.8 | NVIDIA RTX 3090 (24 GB) | qwen3.6-27B-code | llama-server systemd (`/home/llmuser/llama-wrapper.sh`, `-c 131072 --parallel 2 --ngl 99`) | **128K** | 2 |
-| ocu-llm | 192.168.68.110 | NVIDIA RTX 5070 (12 GB) | gemma-4-12b | llama-server systemd (`/home/llmuser/llama-wrapper.sh`, `--ctx-size 131072 --parallel 2`, IQ4_NL + MTP draft) | **128K** | 2 |
+| ocu-llm | 192.168.68.110 | NVIDIA RTX 5070 (12 GB) | gpu-vision | llama-server systemd (`/home/llmuser/llama-wrapper.sh`, `--ctx-size 131072 --parallel 2`, IQ4_NL + MTP draft) | **128K** | 2 |
 | amdpve | 192.168.68.15 | AMD Strix Halo 64GB UMA | qwen3.6-35B-udq4 (LiteLLM alias: `strix-moe`) | llama-server systemd (Vulkan) | 128K | 2 |

 > Verified on ground 2026-07-16 via `curl /v1/models` on each host + `llama-wrapper.sh`. The AMD host's underlying model is `qwen3.6-35B-udq4`; LiteLLM exposes it under two `model_name`s: `qwen3.6-35B-udq4` and `strix-moe` (rpm 40). The legacy name `ornith-1.0-35b` does NOT exist in LiteLLM and must not be referenced.

 ## LiteLLM Model Surface (ground truth — `/opt/inference-harness/litellm_config.yaml` on CT 116)

-`model_name`s served: `qwen3.6-27B-code`, `gemma-4-12b`, `qwen3.6-35B-udq4`, `strix-moe`, `gpu-dense`, `gpu-light`, `syslog-auto`.
+`model_name`s served: `qwen3.6-27B-code`, `gpu-vision`, `qwen3.6-35B-udq4`, `strix-moe`, `gpu-dense`, `gpu-light`, `syslog-auto`, `crew-auto` (new 2026-08-20).

- `syslog-auto` is a weighted router model: qwen3.6-27B-code (0.55, rpm 500) + qwen3.6-35B-udq4 (0.30, rpm 60) + gemma-4-12b (0.15, rpm 200).
- `gpu-dense` / `gpu-light` are high-rpm aliases (rpm 500) onto qwen3.6-27B-code / gemma-4-12b respectively.
- Key scoping: agent keys are restricted to `['syslog-auto','qwen3.6-27B-code','gemma-4-12b','strix-moe','gpu-dense','gpu-light']`. As of 2026-07-16 the `baggy`/`koby`/`mumuni`/`abiba-pi` keys ALSO include `qwen3.6-35B-udq4`; `abiba-pi` additionally includes `deepseek-v4-pro` (cloud fallback). `kagenz0`/`koonimo`/`pi-agents-unified` have the standard 6 only. Agents should still use the stable alias `strix-moe` (not the raw `qwen3.6-35B-udq4`) so model swaps don't break them.
+### Context Cap Split (2026-08-20)
+
+- **Abiba (firstmate)**: 128K uncapped — unlimited context for primary workloads
+- **Hermes agents** (mumuni, tanko, koby, koonimo): 128K uncapped
+- **Crewmates** (ops, tune, verify, auth-keys, build): 64K capped — alias `crew-auto` enforces 64K limit
+
+Preferred implementation: uncap shared pool, add capped alias for crew-only.
+
+- `syslog-auto` is a weighted router model: qwen3.6-27B-code (0.55, rpm 500) + qwen3.6-35B-udq4 (0.30, rpm 60) + gpu-vision (0.15, rpm 200).
+- `gpu-dense` / `gpu-light` are high-rpm aliases (rpm 500) onto qwen3.6-27B-code / gpu-vision respectively.
+- Key scoping: agent keys are restricted to `['syslog-auto','qwen3.6-27B-code','gpu-vision','strix-moe','gpu-dense','gpu-light']`. As of 2026-07-16 the `baggy`/`koby`/`mumuni`/`abiba-pi` keys ALSO include `qwen3.6-35B-udq4`; `abiba-pi` additionally includes `deepseek-v4-pro` (cloud fallback). `kagenz0`/`koonimo`/`pi-agents-unified` have the standard 6 only. Agents should still use the stable alias `strix-moe` (not the raw `qwen3.6-35B-udq4`) so model swaps don't break them.
 - **NEVER use `litellm_proxy_master_key` (the `sk-litellm-...` master key) for inference.** It is for admin endpoints only (`/key/list`, `/key/generate`, `/key/info`). All inference — agent traffic, health-check model tests, monitor scripts — uses agent-specific keys. The health-check script's model tests use a dedicated `monitor` agent key stored at `/etc/litellm-monitor.env` on CT 116 (root-only, `chmod 600`); `/key/list` is the only call that legitimately uses `$MASTER_KEY`.

 ## Model Fallback Chains (LiteLLM)

 | Primary | Timeout | Fallback | Timeout |
 |---------|---------|----------|---------|
-| qwen3.6-27B-code | 300s | gemma-4-12b | 120s |
-| gemma-4-12b | 120s | qwen3.6-27B-code | 300s |
+| qwen3.6-27B-code | 300s | gpu-vision | 120s |
+| gpu-vision | 120s | qwen3.6-27B-code | 300s |
 | qwen3.6-35B-udq4 / strix-moe | 300s | qwen → gemma | — |
 | syslog-auto (balanced) | 300s | qwen → gemma | — |

@@ -120,6 +131,7 @@ Request → nginx:80 → LiteLLM:4000 → GPU(llama-server, parallel 2)
 - Also wakes on user request
 - On failure: re-check after 30s, escalate after 3 consecutive failures

+---
 ---

 ## Health Check
@@ -145,7 +157,7 @@ Run this first on every cycle. Results feed into remediation rules below.
 - Check alerts array for active warnings/critical

 ### 5. Check model inference via LiteLLM — test each model
- POST /v1/chat/completions model=gemma-4-12b → expect 200
+- POST /v1/chat/completions model=gpu-vision → expect 200
 - POST /v1/chat/completions model=qwen3.6-27B-code → expect 200
 - POST /v1/chat/completions model=strix-moe → expect 200
 - Use master key for auth
@@ -162,6 +174,7 @@ Determine overall_status from individual check results:
 - "degraded" — 1-2 non-critical checks fail
 - "down" — critical checks fail

+---
 ---

 ## Remediation Rules
@@ -205,6 +218,7 @@ Escalate → if SSH access unavailable, send Zulip DM
 Router no longer in path so Redis active counters are unused. Rule retained
 for reference but inactive. If Redis issues occur, check harness-redis container.

+---
 ---

 ## Reporting
@@ -227,6 +241,7 @@ top actions, uptime.
 If a fix requires another agent (e.g., Authentik restart), relay sent
 to responsible agent with full context.

+---
 ---

 ## Execution
@@ -1,9 +1,12 @@
 ---
+report_only_agents:
+  - koby  # ⛔ KOBY IS NEVER REPAIRED (Rule 17, 2026-08-17) — detect + report, never fix on .129
 name: memory-audit-maintenance
 kind: responsibility
 description: Shared memory audit and maintenance contract for all Hermes agents (Mumuni, Tanko, Koby, Koonimo). Each agent runs it against its own isolated memory files — no cross-agent access, no shared state. Detects staleness, enforces writer registry, and rotates canary tokens.
 id: 067NC4KG01RG50R40M30E20918
 ---
+---

 ### Goal

@@ -343,4 +346,4 @@ return {

 ### Per-Agent Notes

-Each Hermes agent (Mumuni, Tanko, Tdunna, Baggy) runs this contract against its own `~/.hermes/memories/` directory. The contract is identical across agents, but all data is fully isolated: separate ledgers, separate writer registries, separate canaries. If a new agent is added to the roster, it must be listed in `### Scope` above and given its own isolated memory directory.
+Each Hermes agent (Mumuni, Tanko, Tdunna, Baggy) runs this contract against its own `~/.hermes/memories/` directory. The contract is identical across agents, but all data is fully isolated: separate ledgers, separate writer registries, separate canaries. If a new agent is added to the roster, it must be listed in `### Scope` above and given its own isolated memory directory.
@@ -1,176 +1,73 @@
 ---
+report_only_agents:
+  - koby  # ⛔ KOBY IS NEVER REPAIRED (Rule 17, 2026-08-17) — detect + report, never fix on .129
 kind: pattern
 name: memory-fixer
 description: >
-  Auto-fix low-hanging fruit in the RA-H OS knowledge graph. No judgment calls — only deterministic Level 1 operations.
-  Escalate anything that needs Kwame's input. Executes confirmed Kwame decisions to completion (state + updated_at).
-version: 2.0.0
+  Auto-fix low-hanging fruit in the graph. No judgment calls — only deterministic Level 1 operations. 
+  Escalate anything that needs Kwame's input.
+version: 1.1.0
+---
 ---

 # Memory Fixer

-> **Canonical copy:** `/root/.hermes/contracts/memory-fixer-v3.md` (used by the `memory-fixer-daily` cron job). This file is the institutional record of the same contract. When the two diverge, treat the v3 source in `/root/.hermes/contracts/` as executable truth.
-
 ## Purpose
-Auto-fix low-hanging fruit in the graph. No judgment calls — only deterministic Level 1 operations. Escalate anything that needs Kwame's input. When Kwame replies to an escalation, **execute the decision to completion** (update state and timestamps), never leaving a node in review-pending forever.
+Auto-fix low-hanging fruit in the graph. No judgment calls — only deterministic Level 1 operations. Escalate anything that needs Kwame's input.

-**Type:** Write-only (Level 1 fixes only)
-**Scope:** RA-H OS knowledge graph (192.168.68.65)
-**Schedule:** Daily at 8 AM ET
-**Escalation:** Level 2+ to Kwame as task items
+## Level 0 Auto-Deletes (Allowed Without Approval)
+Ephemeral heartbeat and log nodes that violate "Logs NEVER go in the graph":

-## Key Design Decision
+- `[LITELLM-HEALTH]`, `[GPU-SELF-HEAL]`, `[PM2-SELF-HEAL]`
+- `[PROXMOX-MONITOR]`, `[GPU-MONITOR]`, `[INFRA-MONITOR]`, `[AGENT-HEALTH]`, `[DISK-GC]`
+- `[WAL]` entries older than 30 days

-The `updateNode` tool's `metadata` field performs a **restricted merge** — the `state` key only accepts `'processed'` or `'not_processed'`. Additionally, new metadata keys cannot be added via the merge.
+**Condition:** node must be an orphan (no edges). Deleting a connected node risks breaking other nodes.

-**Solution:** Use the `description` field to tag stale nodes with review actions, since `description` is a simple string overwritable via `updateNode`.
-
-**Tag Format:** `[REVIEW: action] original description text...`
-
-Where `action` is one of:
- `archive` — node is stale and should be archived
- `refresh` — node is stale and should be refreshed (infrastructure)
- `keep` — node has been confirmed as current
- `merge` — node is a duplicate candidate
-
-**Query for finding review-tagged nodes:**
-```sql
-SELECT id, title, description
-FROM nodes
-WHERE description LIKE '[REVIEW:%';
+**Method:** direct SQLite on `.65` (MCP has no delete tool):
+```bash
+ssh root@192.168.68.65 "sqlite3 /root/.local/share/RA-H/db/rah.sqlite \"
+DELETE FROM nodes WHERE id IN (
+  SELECT id FROM nodes WHERE id NOT IN (SELECT from_node_id FROM edges)
+  AND id NOT IN (SELECT to_node_id FROM edges)
+  AND title LIKE '[LITELLM-HEALTH]%' -- add more prefixes as needed
+);\""
 ```

-## Level 1 Auto-Fixes (No Kwame Decision Needed)
+## Level 1 Auto-Fixes (No Judgment Required)

-### 1. Missing `type` Auto-Classification
+### 1. Missing `type` Field
+For nodes with content but no `metadata.type`:
+- Title contains "Proxmox" or "infrastructure" → `type: infrastructure`
+- Title contains "skill" or "how to" or "guide" → `type: skill`
+- Title contains "doc" or "template" or "brand" → `type: documentation`
+- Title starts with "WAL:" or "TASK:" → `type: note`
+- Title starts with "[LEARN]" → `type: documentation`
+- Otherwise → `type: note` (default)

+### 2. Missing `tenant` / `namespace`
+For any node with NULL tenant or namespace:
 ```sql
-SELECT id, title,
-  CASE
-    WHEN title LIKE '%infrastructure%' OR title LIKE '%proxmox%' OR title LIKE '%setup%' THEN 'infrastructure'
-    WHEN title LIKE '%skill%' OR title LIKE '%how to%' OR title LIKE '%guide%' THEN 'skill'
-    WHEN title LIKE '%doc%' OR title LIKE '%template%' OR title LIKE '%brand%' THEN 'documentation'
-    WHEN title LIKE 'WAL:%' OR title LIKE 'TASK:%' THEN 'note'
-    WHEN title LIKE '%[LEARN]%' THEN 'documentation'
-    ELSE 'note'
-  END as auto_type
-FROM nodes
-WHERE json_extract(metadata, '$.type') IS NULL;
-```
-
-### 2. Missing `namespace` Auto-Population
-
-```sql
-SELECT id, title, json_extract(metadata, '$.tenant') as tenant
-FROM nodes
-WHERE json_extract(metadata, '$.namespace') IS NULL;
-```
-
-### 3. Staleness Review Tagging
-
-Using the type-based windows from the memory-monitor contract, tag nodes stale beyond their window. **Only process a maximum of 10 nodes per run** to avoid overwhelming Kwame. Prioritize infrastructure first, then dynamic, then ephemeral.
-
-**Exclusion Rules:**
- Nodes with `state` = `review_pending`, `deprecated`, `archived`, or `not_processed` are NOT processed
- Nodes whose `description` already starts with `[REVIEW:` are NOT re-processed
-
-```sql
-SELECT id, title, json_extract(metadata, '$.type') as node_type,
-  CAST(julianday('now') - julianday(updated_at) AS INTEGER) as days_stale,
-  CASE
-    WHEN json_extract(metadata, '$.type') IN ('infrastructure', 'deployment', 'system', 'system-health') THEN 'refresh'
-    WHEN json_extract(metadata, '$.type') IN ('business', 'philosophy', 'research', 'learning', 'learn', 'investigation', 'analysis', 'project') THEN 'refresh'
-    ELSE 'archive'
-  END as suggested_action
-FROM nodes
-WHERE updated_at < datetime('now',
-  CASE
-    WHEN json_extract(metadata, '$.type') IN ('infrastructure', 'deployment', 'system', 'system-health') THEN '-14 days'
-    WHEN json_extract(metadata, '$.type') IN ('skill', 'documentation', 'template', 'protocol-enforcement', 'prd', 'architecture') THEN '-90 days'
-    WHEN json_extract(metadata, '$.type') IN ('note', 'wal', 'WAL', 'task', 'TASK', 'event') THEN '-30 days'
-    WHEN json_extract(metadata, '$.type') IN ('business', 'philosophy', 'research', 'learning', 'learn', 'investigation', 'analysis', 'project') THEN '-120 days'
-    WHEN json_extract(metadata, '$.type') IN ('deprecated-relay', 'audit', 'audit-report', 'incident', 'incident-report') THEN '-3650 days'
-    ELSE '-45 days'
-  END
+UPDATE nodes 
+SET metadata = json_set(
+  COALESCE(metadata, '{}'),
+  '$.tenant', 'syslogsolution',
+  '$.namespace', 'syslogsolution'
 )
-AND json_extract(metadata, '$.state') NOT IN ('review_pending', 'deprecated', 'archived', 'not_processed')
-AND (description IS NULL OR description NOT LIKE '[REVIEW:%')
-ORDER BY days_stale ASC
-LIMIT 10;
+WHERE json_extract(metadata, '$.tenant') IS NULL 
+   OR json_extract(metadata, '$.namespace') IS NULL;
 ```

-For each identified node, call `updateNode(id, { description: "[REVIEW: action] " + originalDescription })`.
+### 3. Staleness State Transitions
+Using the type-based windows from the memory-monitor contract:
+- Nodes stale > their window → transition to `state: review_pending`
+- Nodes in `review_pending` for >7 days → escalate to Kwame (Level 2)

 ## Level 2 Escalations (Kwame Decision Required)
-
-1. **Stale nodes** flagged with `[REVIEW: …]` — Archive, refresh, or keep?
-2. **Duplicate Nodes** (same title or >70% title overlap) — Merge or keep?
-3. **Orphan Nodes >90 days old** — Archive or connect?
-
-## Reporting Format
-
-The fixer reports to Kwame via this Zulip DM:
-
-```
-🦅 Memory Fixer — [HH:MM UTC]
-
-Level 1 fixes applied:
- Missing type: X nodes classified
- Missing namespace: Y nodes populated
-
-Stale nodes needing review (max 10):
-1. [Node #XXX] Title — X days stale, SUGGEST: refresh
-2. [Node #YYY] Title — Y days stale, SUGGEST: archive
-...
-
-Duplicates needing decision:
-1. [Node #AAA] vs [Node #BBB] — Same title
-
-Orphans >90 days:
-1. [Node #EEE] Title — X days stale, orphaned
-
-Reply with:
- "archive #XXX, #YYY" to mark for archive
- "archive all" to archive all stale nodes listed
- "keep #XXX" to confirm a node is current
- "merge #AAA into #BBB" to merge duplicates
- "refresh #XXX" to mark as current
-```
-
-## Execution on Next Run
-
-The fixer reads Kwame's previous response and **executes the decision to completion** — it must not leave a node in review-pending forever. Tagging alone is NOT enough; each confirmed decision must also update `state` and `updated_at` so the node drops out of the stale window on the next run.
-
-> ⚠️ `updateNode` cannot set `state` to non-standard values (restricted to `processed`/`not_processed`) and cannot add metadata keys. For state transitions and `updated_at` bumps, use **direct SSH + SQLite** on the bridge host:
-> ```bash
-> ssh root@192.168.68.65 "sqlite3 /root/.local/share/RA-H/db/rah.sqlite \"UPDATE nodes SET metadata = json_set(metadata, '$.state', '<state>'), updated_at = datetime('now') WHERE id = <id>;\""
-> ```
-> Use `updateNode` only for description/source/title/link edits.
-
-Decision → completed action mapping:
-
-| Kwame reply | Description change | State | `updated_at` |
-|---|---|---|---|
-| `archive #XXX` | replace `[REVIEW: archive] ` → `[ARCHIVED] ` prefix | `archived` | bumped to now |
-| `keep #XXX` / `refresh #XXX` | **clear the `[REVIEW: …]` tag entirely** | `active` | bumped to now |
-| `merge #AAA into #BBB` | set `[REVIEW: merge_into #BBB]` on #AAA, then follow manual merge workflow | handled manually | bumped to now |
-| `archive all` | apply the archive row to every node listed in the prior report | `archived` | bumped to now |
-
-**Why `updated_at` must be bumped (critical):** the Level-1 staleness query keys off `updated_at < now - window`. If the fixer clears the tag but leaves a stale `updated_at`, the node is immediately re-flagged on the very next run and the cycle repeats forever. Bumping `updated_at` to now pushes the node back to the front of the window.
-
-**Exclusion after action:** once an action is applied, the node's description no longer starts with `[REVIEW:` (archive → `[ARCHIVED]`, refresh/keep → original text), so it is not re-processed.
-
-After all actions are applied, verify with:
-```sql
-SELECT id, json_extract(metadata, '$.state') FROM nodes WHERE description LIKE '[REVIEW:%';
-```
-The result must be 0 rows when all decisions are executed. Report what was done.
-
-## Checks
-
- **State integrity:** archived nodes have `state: archived` + `[ARCHIVED]` prefix; kept nodes are `state: active` without a `[REVIEW:]` tag.
- **No review-pending forever:** after executing Kwame's decisions, `[REVIEW:%` node count must be 0.
- **Timestamps:** every executed decision bumps `updated_at`, so the node exits the stale window on the next run.
+1. **Nodes in `review_pending` >7 days** — Archive, refresh, or keep?
+2. **Orphan Nodes >90 days old** — Delete or Connect?
+3. **Potential Duplicate Nodes** — Same title or >70% overlap. Merge or Keep?
+4. **Conflicting Metadata** — Content suggests one tenant but metadata says another.

 ## Logging
 Every Level 1 fix logged to `~/.hermes/logs/memory-fixer/YYYY-MM-DD.md`
@@ -6,7 +6,7 @@ description: >
  delegation, verification, and delivery. Defines when to delegate, which
  worker to use for what, how to handle failures, and the kanban board
  protocol. Enforces context-window discipline and separation of concerns.
-  Runs on Mumuni (kagentz CT105, minipve, .14) via Hermes agent (Zulip gateway via systemd).
+  Runs on Mumuni (inside Abiba CT100, hwepve, .24) via Hermes agent (Pi + Hermes Zulip gateway).
 version: 1.0.0
 ---

@@ -19,8 +19,8 @@ version: 1.0.0

 ## Topology

-**Cluster:** 5 Proxmox nodes (ocupve, acerpve, minipve, amdpve, storepve)
-**Manager:** Mumuni (kagentz CT105, minipve, .14) via Hermes agent
+**Cluster:** 6 Proxmox nodes (ocupve, acerpve, minipve, amdpve, storepve, hwepve)
+**Manager:** Mumuni (inside Abiba CT100, hwepve, .24) via Hermes agent
 **Workers:** 6 profiles, all running on the same agent — no separate hosts needed

 This contract is infrastructure-agnostic in terms of which nodes are used.
@@ -31,7 +31,7 @@ Workers execute tasks on whatever infrastructure they're given — SSH to .6,
 ## Why This Matters

 Without enforced delegation, the manager consumes the full iteration budget
-(60 calls) on single-turn tasks — SSH to 5 nodes, check each VM, read logs —
+(60 calls) on single-turn tasks — SSH to 6 nodes, check each VM, read logs —
 leaving no capacity for actual coordination. The result: context overflow
 (59K tokens in system prompt), iteration exhaustion, and degraded response
 quality. This contract exists because I blew through my budget checking
@@ -82,7 +82,7 @@ it asks the manager (via relay) — it doesn't go find it on its own.

 **This is a hard rule, not a recommendation.** Violating it produces the exact
 type of discrepancy the kanban pipeline exists to prevent: a review worker finds
-"5 nodes present" in the raw data but "5/5 online" in the report — even though
+"6 nodes present" in the raw data but "6/6 online" in the report — even though
 one of those nodes was unreachable. The report lied because it used data the
 raw data never provided.

@@ -137,7 +137,7 @@ delegate_task(
 ```
 delegate_task(
    tasks=[
-        {"goal": "Check all 5 Proxmox nodes for VM status", "context": "SSH to each node via 192.168.68.x, run 'qm list'"},
+        {"goal": "Check all 6 Proxmox nodes for VM status", "context": "SSH to each node via 192.168.68.x, run 'qm list'"},
        {"goal": "Check Docker container health on .7/.116/.17", "context": "SSH to each host, check container status"},
    ]
 )
@@ -191,7 +191,7 @@ Only verified results reach Kwame. Format per channel:
    {
      "lane_id": "devops-check",
      "worker": "syslog-devops",
-      "goal": "Check all 5 Proxmox nodes",
+      "goal": "Check all 6 Proxmox nodes",
      "status": "dispatched|completed|failed",
      "output_file": "/tmp/node-report.md"
    }
@@ -2,31 +2,26 @@
 kind: responsibility
 name: pm2-self-heal
 description: >
-  Monitors critical PM2 processes (abiba-zulip, abiba-telegram, gitea-runner,
-  spoton-service, zulip-watchdog) and auto-restarts any that are stopped or
-  errored. Logs every action to Gitea (SyslogSolution/health-logs — not
-  knowledge graph, hard rule) and alerts the owner via
-  Zulip DM on failures.
-  CRITICAL: Never restart abiba-zulip — it runs this contract.
-  AS-BUILT 2026-08-09 (captain ruling, ecosystem is authoritative):
-  gpu-monitor is systemd-managed (gpu-monitor.service) — NOT PM2;
-  gpu-watchdog decommissioned (function folded into gpu-monitor.service);
-  gitea-runner KEPT (online in PM2); abiba-zulip KEPT (online 4d+, the
-  2026-07-04 'removed/decommissioned' note was stale and is removed).
+  Monitors critical PM2 processes on CT100/.24 (the container this agent runs in) and
+  auto-restarts any that are stopped or errored. Logs every action to
+  the knowledge graph and alerts the owner via Zulip DM on failures.
+  Abiba-zulip is the live Zulip bridge and may be restarted; alert owner on failure.
+  **Execution host: CT100/.24 local pm2 — NOT CT116, NOT via SSH** (CT116 runs systemd+docker, no PM2).
+  **Process scope (5/5, 2026-08-09 ruling, ecosystem authoritative):**
+  abiba-zulip, abiba-telegram, gitea-runner, spoton-service, zulip-watchdog
+report_only_agents:
+  - koby  # ⛔ KOBY IS NEVER REPAIRED (Rule 17, 2026-08-17) — detect + report, never fix on .129
 ---

 ## Maintains

 - abiba-telegram: { status: "online", uptime: string, restarts: number }
 - abiba-zulip: { status: "online", uptime: string, restarts: number }
+- gpu-monitor: { status: "online", uptime: string, restarts: number } (systemd-managed, PM2-tracked)
 - gitea-runner: { status: "online", uptime: string, restarts: number }
- spoton-service: { status: "online", uptime: string, restarts: number }
- zulip-watchdog: { status: "online", uptime: string, restarts: number }
 - last_check: timestamp

-> **Note (2026-07-04, SUPERSEDED 2026-08-09):** `abiba-zulip` remains ONLINE and
-> is monitored — the decommission note was stale (process re-added; do not treat
-> it as removed).
+> **Status (2026-08-03):** `abiba-zulip` fully restored — live Zulip bridge, heartbeating, monitored. `gpu-monitor` runs via systemd (stable); PM2 tracks it for status reporting only. `gpu-watchdog` retired from PM2.

 ## Continuity

@@ -41,15 +36,10 @@ description: >
 - **Verify**: Re-check status after 5 seconds
 - **Escalate**: If still failed after 2 retries, send Zulip DM to owner

-### Rule 2: Process Restarting Too Often (crash-loop guard)
- **Detect**: `pm2 status` shows restarts > 30 (cumulative lifetime counter) **or** a
-  process reporting a restart count > 1000 while showing "online" (a crash-loop mask)
+### Rule 2: Process Restarting Too Often
+- **Detect**: `pm2 status` shows restarts > 30 (cumulative lifetime counter)
 - **Note**: PM2 counter never decrements; only full delete+re-add resets it
 - **Fix**: `pm2 delete <name> && pm2 start <ecosystem> --only <name>`
- **Script guard (2026-08-16)**: `scripts/pm2-self-heal.sh` now restarts `abiba-telegram`
-  when `TEL_RESTARTS > 1000` even if the process reports "online" — catches a quiet
-  crash-loop that never toggles status to "stopped"/"errored" (e.g. the 10k-restarts
-  spoton incident). Alerts include the restart count.
 - **Escalate**: Only when restarts > 30 — alerts to Zulip DM
 - **Historical fix**: Previous cycles were caused by abiba-zulip extension's
  stuck detection (STUCK_THRESHOLD_MS was 30min, raised to 4h in v2).
@@ -58,18 +48,23 @@ description: >

 ## Execution

+**Execution host: CT100/.24 — run `pm2` commands LOCAL to this container. Never SSH to CT116** (CT116 runs systemd+docker, no PM2 set).
+
+**Process scope (5/5, 2026-08-09 ruling, ecosystem authoritative):**
+1. abiba-zulip (live Zulip bridge, heartbeating)
+2. abiba-telegram
+3. gitea-runner
+4. spoton-service
+5. zulip-watchdog
+
 1. **Check PM2 status** — Run `pm2 status --no-color` and parse the table (5th data column = PID, 8th = restarts, 9th = status)
-2. **Check abiba-telegram**:
-   - If status is "online" → pass
-   - If status is "stopped" or "errored" → apply Rule 1
-   - If restarts > 5 → alert owner
-3. **Check abiba-zulip** (self-process, read-only):
+2. **Check all 5 processes** (abiba-zulip, abiba-telegram, gitea-runner, spoton-service, zulip-watchdog):
   - If status is "online" → pass, log restarts count
-   - If status is "stopped" or "errored" → **DO NOT RESTART** — alert owner immediately
-   - If restarts > 5 in last hour → alert owner with full diagnostics
-4. **Log results** — Append to `SyslogSolution/health-logs/pm2/{timestamp}.md` in Gitea (not knowledge graph — hard rule)
-5. **Alert** — Send Zulip DM to owner if escalation needed (do NOT run pm2 commands during alerting)
-6. **Wait 5 min** → repeat from step 1
+   - If status is "stopped" or "errored" → apply Rule 1 (restart)
+   - If restarts > 5 → alert owner
+3. **Log results** — Append to `SyslogSolution/health-logs/pm2/{timestamp}.md` in Gitea (not knowledge graph — hard rule)
+4. **Alert** — Send Zulip DM to owner if escalation needed (do NOT run pm2 commands during alerting)
+5. **Wait 5 min** → repeat from step 1

 ## Example Output (when healthy)

@@ -5,7 +5,7 @@ description: >
  Proxmox cluster + Docker monitoring via the existing Grafana/Prometheus stack
  on CT 116. Replaces Pulse with file-provisioned Grafana dashboards. Three
  exporters feed Prometheus: prometheus-pve-exporter (cluster-aware, single
-  instance), node_exporter (all 5 PVE nodes), and a custom docker-stats-exporter
+  instance), node_exporter (all 6 PVE nodes), and a custom docker-stats-exporter
  (Docker 29 / containerd image-store compatible, since cAdvisor cannot resolve
  the layerdb). Dashboards exposed at http://192.168.68.116:3001/ (direct LAN, not behind nginx).
 agent: abiba
@@ -33,8 +33,8 @@ agent: abiba

 | Exporter | Host:Port | Scope | Notes |
 |----------|-----------|-------|-------|
-| prometheus-pve-exporter | .116:9221 (container) | All 5 nodes + 14 guests + 36 storage pools | Single instance, cluster-aware via amdpve API. Config `/opt/monitoring/pve.yml` (token `monitoring@pve!prometheus`, PVEAuditor role). Metric schema is label-based (`id=node/amdpve`, `id=lxc/100`). |
-| node_exporter | .5/.6/.9/.12/.15:9100 (systemd) | Per-node CPU/mem/disk/net/temp | Installed via apt on all 5 PVE nodes, enabled (reboot-persistent). Collectors: textfile, systemd, tcpstat, ethtool. |
+| prometheus-pve-exporter | .116:9221 (container) | All 6 nodes + guests + 36 storage pools | Single instance, cluster-aware via amdpve API. Config `/opt/monitoring/pve.yml` (token `monitoring@pve!prometheus`, PVEAuditor role). Metric schema is label-based (`id=node/amdpve`, `id=lxc/100`). |
+| node_exporter | .5/.6/.9/.12/.15/.4:9100 (systemd) | Per-node CPU/mem/disk/net/temp | Installed via apt on all 6 PVE nodes, enabled (reboot-persistent). Collectors: textfile, systemd, tcpstat, ethtool. hwepve (.4) added 2026-07-19. |
 | docker-stats-exporter | .116:9324 (container) | 10 Docker containers on .116 | **Custom** (cAdvisor v0.51 incompatible with Docker 29 containerd image store — layerdb gone). Uses Docker Engine API over unix socket. Script `/opt/monitoring/docker-stats-exporter.py`. |

 ## PVE API Token
@@ -48,7 +48,7 @@ agent: abiba

 | UID | Title | Panels | Source |
 |-----|-------|--------|--------|
-| proxmox-cluster | Proxmox Cluster Overview | 16 | cluster status, 5-node CPU/mem/disk/load gauges, guests table, storage pools, guest CPU/mem timeseries |
+| proxmox-cluster | Proxmox Cluster Overview | 16 | cluster status, 6-node CPU/mem/disk/load gauges, guests table, storage pools, guest CPU/mem timeseries |
 | proxmox-node | Proxmox Node Detail | 13 | per-node CPU per-core, memory, network, disk IO/IOPS/latency, temperature, disk space (variable: $node) |
 | docker-containers | Docker Containers | 10 | per-container CPU/mem/network, restarts, memory limit ratio (variable: $container) |
 | gpu-fleet | GPU Fleet | 7 | (existing, preserved in DB, not provisioned) |
@@ -77,9 +77,9 @@ agent: abiba
 | `/opt/monitoring/grafana/dashboards/build-dashboards.py` | .116 | dashboard JSON generator |
 | `/opt/monitoring/grafana/dashboards/json/*.json` | .116 | provisioned dashboard definitions |
 | `/opt/monitoring/grafana/datasources/prometheus.yml` | .116 | datasource provisioning |
-| `/etc/default/prometheus-node-exporter` | .5/.6/.9/.12/.15 | node_exporter collector config |
+| `/etc/default/prometheus-node-exporter` | .5/.6/.9/.12/.15/.4 | node_exporter collector config |

-## Cluster "Tabiri" — 5 Nodes
+## Cluster "Tabiri" — 6 Nodes

 | Node | IP | Role |
 |------|----|----|
@@ -88,6 +88,7 @@ agent: abiba
 | acerpve | 192.168.68.9 | PVE (hosts llm-gpu qemu/101) |
 | minipve | 192.168.68.12 | PVE |
 | amdpve | 192.168.68.15 | PVE + Strix Halo LLM (qwen3.6-35B-udq4, strix-moe) |
+| hwepve | 192.168.68.4 | PVE (Huawei Matebook 16, 12C/15GB) — hosts abiba (lxc/100), kagentz (lxc/105), mumuni (lxc/114). CTs 100/105 migrated from amdpve, CT 114 from minipve 2026-07-20 |

 ## Operations

@@ -30,6 +30,7 @@ INFISICAL_ENV = "prod"

 # PVE node IPs for CT liveness checks
 PVE_NODES = {
+    "hwepve":  "192.168.68.4",
    "amdpve":  "192.168.68.15",
    "minipve": "192.168.68.12",
    "storepve": "192.168.68.6",
@@ -39,10 +40,10 @@ 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"},
-    "abiba":   {"ct": 100, "host": "192.168.68.24",  "user": "root",   "pve": "minipve",  "vault_key": None},  # Pi agent + Mumuni Zulip, no vault key
-    "koby":    {"ct": 111, "host": "192.168.68.129", "user": "root",   "pve": "amdpve",  "vault_key": "KOBY_LITELLM_API_KEY"},
-    "koonimo": {"ct": 113, "host": "192.168.68.114", "user": "root",   "pve": "amdpve",  "vault_key": "KOONIMO_LITELLM_API_KEY"},
+    "tanko":   {"ct": 112, "host": "192.168.68.122", "user": "jerome", "pve": "amdpve",  "vault_key": "TANKO_LITELLM_API_KEY", "report_only": False},
+    "abiba":   {"ct": 100, "host": "192.168.68.24",  "user": "root",   "pve": "hwepve",  "vault_key": None, "report_only": False},
+    "koby":    {"ct": 111, "host": "192.168.68.129", "user": "root",   "pve": "amdpve",  "vault_key": "KOBY_LITELLM_API_KEY", "report_only": True},  # ⛔ KOBY IS NEVER REPAIRED (Rule 17, 2026-08-17)
+    "koonimo": {"ct": 113, "host": "192.168.68.114", "user": "root",   "pve": "amdpve",  "vault_key": "KOONIMO_LITELLM_API_KEY", "report_only": False},
 }

 GPU_HOSTS = {
@@ -238,20 +239,26 @@ def check_agents():
        host = agent.get("host")
        user = agent.get("user")
        ct = agent["ct"]
+        report_only = agent.get("report_only", False)

        if not host or not user:
            print(f"  ⬜ {name} (CT {ct}): cannot SSH — skip liveness check")
            continue

-        # Gateway process
-        pid = ssh(host, "pgrep -f 'hermes_cli.main gateway run' | grep -v infisical | head -1", user=user)
-        if not pid:
-            # Try alternate binary name
-            pid = ssh(host, "pgrep -f 'hermes.*gateway' | grep -v infisical | grep -v bash | head -1", user=user)
-        if not pid:
-            print(f"  ❌ {name}: GATEWAY NOT RUNNING")
-            FAIL.append(f"gateway-down:{name}")
-            continue
+        # ⛔ KOBY IS NEVER REPAIRED — diagnostic only
+        if report_only:
+            print(f"  🔍 {name}: REPORT-ONLY mode (diagnostic only, no repairs on .129)")
+            # Still check gateway status for reporting purposes
+            pid = ssh(host, "pgrep -f 'hermes_cli.main gateway run' | grep -v infisical | head -1", user=user)
+            if not pid:
+                pid = ssh(host, "pgrep -f 'hermes.*gateway' | grep -v infisical | grep -v bash | head -1", user=user)
+            if not pid:
+                print(f"  ⚠️  {name}: GATEWAY NOT RUNNING (reported only)")
+                FAIL.append(f"gateway-down:{name}")
+                continue
+            else:
+                print(f"  ✅ {name}: gateway running (pid={pid}, report-only mode)")
+                continue  # Skip the rest of the check for Koby

        # Gateway state file
        state = ssh(host, "cat ~/.hermes/gateway_state.json 2>/dev/null", user=user)
@@ -322,7 +322,7 @@ def collect():
        mumuni_data = {}
    mumuni_platforms = mumuni_data.get("platforms", {})
    report["agents"]["mumuni"] = {
-        "platform": "hermes", "ct": 100, "ip": "192.168.68.24",
+        "platform": "hermes", "ct": 114, "ip": "192.168.68.24",
        "gateway_state": mumuni_data.get("gateway_state", "unknown"),
        "telegram_state": mumuni_platforms.get("telegram", {}).get("state", "unknown"),
        "zulip_state": mumuni_platforms.get("zulip", {}).get("state", "not_installed"),
@@ -28,8 +28,10 @@ declare -A CT_NODES=(
    [117]=storepve  # zulip
    [118]=storepve  # jdownloader
    # acerpve (192.168.68.9) — no CTs (bare metal GPU .8)
-    [100]=minipve   # abiba (was hwepve)
-    [105]=minipve   # kagentz (was hwepve)
+    # hwepve (192.168.68.4)
+    [100]=hwepve    # abiba (was amdpve)
+    [105]=hwepve    # kagentz (was amdpve)
+    [114]=hwepve    # mumuni (was minipve)
    # ocupve (192.168.68.5) — no CTs (bare metal GPU .110)
    #
    # REMOVED CTs (migrated to bare metal, decommissioned, or VMs):
@@ -48,6 +50,7 @@ declare -A NODE_IPS=(
    [storepve]=192.168.68.6
    [acerpve]=192.168.68.9
    [ocupve]=192.168.68.5
+    [hwepve]=192.168.68.4
 )

 resolve_node() {
@@ -74,7 +77,7 @@ main() {
    if [[ $# -lt 1 ]]; then
        echo "Usage: pct-run <CT_ID> [command...]" >&2
        echo "  pct-run 112 cat /etc/hostname" >&2
-        echo "  pct-run 100 systemctl status hermes-gateway" >&2
+        echo "  pct-run 114 systemctl status hermes-gateway" >&2
        echo ""
        echo "Known CTs:" >&2
        for ct in $(echo "${!CT_NODES[@]}" | tr ' ' '\n' | sort -n); do
@@ -33,7 +33,7 @@ TEL_LINE=$(echo "$STATUS" | grep "abiba-telegram")
 TEL_STATUS=$(echo "$TEL_LINE" | awk -F'│' '{print $10}' | xargs)
 TEL_RESTARTS=$(echo "$TEL_LINE" | awk -F'│' '{print $9}' | xargs)

-if [ "$TEL_STATUS" != "online" ] || [ "$TEL_RESTARTS" -gt 1000 ]; then
+if [ "$TEL_STATUS" != "online" ]; then
    pm2 restart abiba-telegram > /dev/null 2>&1
    sleep 3
    TEL_LINE2=$(pm2 status --no-color 2>/dev/null | grep "abiba-telegram")
@@ -46,17 +46,18 @@ 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):**
+**Proxmox Cluster "Tabiri" (6 nodes):**
 - amdpve (192.168.68.15): tanko, tdunna, baggy, scottdenya
- minipve (192.168.68.12): abiba, kagentz, adguard, authentik, gitea, syslog-api, infisical-vault
+- minipve (192.168.68.12): adguard, authentik, gitea, syslog-api, infisical-vault
 - storepve (192.168.68.6): docker-vm, ra-h-os, PBS, media, jdownloader, zulip
 - acerpve (192.168.68.9): llm-gpu
 - ocupve (192.168.68.5): ocu-llm
+- hwepve (192.168.68.4): abiba, kagentz, mumuni

 **CT IDs (verified 2026-07-24 against PVE API):**
 100:abiba  102:adguard  104:authentik  105:kagentz  106:ra-h-os
 107:pbs    108:media    110:gitea      111:tdunna   112:tanko
-113:baggy  115:scottdenya  116:syslog-api 117:zulip
+113:baggy  114:mumuni   115:scottdenya  116:syslog-api 117:zulip
 118:jdownloader  119:infisical-vault

 **NO CT 122, CT 123, or .19 exist in the cluster.**
@@ -64,7 +65,7 @@ The infrastructure-control.prose.md contract is the canonical reference for the
 **CRITICAL RULES (never regress):**
 1. NO /grafana/ nginx route — it was tried and reverted on 2026-07-02. Grafana is direct LAN at :3001.
 2. NO .19 IP — Zulip is CT 117 on storepve.
-3. NO CT 122/123 — Tanko=CT 112, Mumuni=CT 100 (inside Abiba). No CT 114 anywhere.
+3. NO CT 122/123 — Tanko=CT 112, Mumuni=CT 114.
 4. Strix Halo :8080 is FIREWALLED to .116 only — cannot be probed from abiba (.24).
 5. abiba-zulip PM2 process is DECOMMISSIONED (2026-07-04) — abiba uses Telegram only.

@@ -6,6 +6,8 @@ title: Zulip Mesh Health Monitor — Multi-Platform
 version: 3.0.0
 runtime_contract: 2
 agent: abiba
+report_only_agents:
+  - koby  # ⛔ KOBY IS NEVER REPAIRED (Rule 17, 2026-08-17) — detect + report, never fix on .129
 ---

 # Zulip Mesh Health Monitor
@@ -16,7 +18,7 @@ Runs every 15 minutes in the background. Also triggers on session start.
 ## Requires

 - **Zulip API key** for `abiba-bot@chat.sysloggh.net` in `$ZULIP_API_KEY`
- **SSH access** to Tanko (192.168.68.122), Mumuni (192.168.68.14, kagentz CT105 on minipve), and Agent Zero Docker host (192.168.68.14)
+- **SSH access** to Tanko (192.168.68.122), Mumuni (192.168.68.24, inside Abiba CT100 on hwepve), and Agent Zero Docker host (192.168.68.14)
 - **PM2** on localhost for pi process management
 - **Network access** to `chat.sysloggh.net`, `localhost:9200`
 - **Write access** to `/root/zulip-health-monitor.log` and `/tmp/zulip-monitor-debounce`
@@ -87,7 +89,7 @@ streamed in real-time via Zulip's `PATCH /api/v1/messages/{id}` API:
 - Adapter implements `edit_message()` using `_api_patch()` helper
 - Gateway stream consumer progressively edits the Zulip message
 - User sees real-time agent thinking instead of waiting for full response
- Verified: Tanko (CT 112) and Mumuni (kagentz CT 105) both have streaming active
+- Verified: Tanko (CT 112) and Mumuni (CT 114) both have streaming active

 ### Verification
 ```bash
@@ -182,13 +184,13 @@ grep -a "Finalized\|Failed to finalize" /root/.pm2/logs/abiba-zulip-out.log | ta
 | `last_error` set | Log and monitor |
 | Crash loop >10/h | Alert user |

-### Step 3: Platform B — Hermes (Tanko .122, Mumuni .14)
+### Step 3: Platform B — Hermes (Tanko .122, Mumuni .24)

 **B1: Gateway State**

 ```bash
 ssh root@192.168.68.122 "cat ~/.hermes/gateway_state.json"
-ssh hermes@192.168.68.14 "cat ~/.hermes/gateway_state.json"  # Mumuni on kagentz CT105
+ssh root@192.168.68.24 "cat ~/.hermes/gateway_state.json"  # Mumuni inside Abiba CT100
 ```

 Check `platforms.zulip.state`: `connected` ✅ | `disconnected` ❌ | `error` ❌ | missing → not installed.
@@ -199,14 +201,7 @@ Check `platforms.zulip.state`: `connected` ✅ | `disconnected` ❌ | `error`
 ssh root@<CT> "ps aux | grep 'gateway run' | grep -v grep"
 ```

-Gateway PID should exist with uptime > 60s. **Dual-gateway detection**: if more than one `gateway run` process is found, the gateway has a collision (typically one `--force` and one `--replace` process). Kill the newer/duplicate process, then restart the remaining gateway per-agent (parameterized 2026-08-09, captain ruling):
-
-| Agent | Restart command | Notes |
-|-------|-----------------|-------|
-| Mumuni (.14) | `sudo systemctl restart hermes-gateway` | systemd unit `hermes-gateway.service` (user hermes) |
-| Tanko (.122) | `bash /opt/hermes-zulip-plugin/run.sh` (or the agent's systemd/user unit) | Tanko does NOT use PM2 — never run `pm2 restart mumuni-zulip` for Tanko (process does not exist) |
-
-Check gateway log for "Gateway running with 2 platform(s)" (not 1) to confirm Zulip reloaded.
+Gateway PID should exist with uptime > 60s. **Dual-gateway detection**: if more than one `gateway run` process is found, the gateway has a collision (typically one `--force` and one `--replace` process). Kill the newer/duplicate process, then restart the remaining gateway via PM2 (`pm2 restart mumuni-zulip`). Check gateway log for "Gateway running with 2 platform(s)" (not 1) to confirm Zulip reloaded.

 **B3: Heartbeat Verification**

@@ -420,7 +420,7 @@ Backup v2 before starting: `cp index.js index.js.v2-backup-$(date +%Y%m%d-%H%M%S
 |-------|----------|-------------|--------------|-------------|
 | **Abiba** | pi (CT 100) | ✅ Connected | API key missing from Infisical injection; poll timeout noise | Added .env fallback; AbortError treated as empty poll (no retry); poll timeout 65s→90s |
 | **Tanko** | Hermes (CT 112) | ✅ Connected | Gateway disconnected since Jul 11; watchdog restart didn't re-establish Zulip | Full gateway restart (kill wrapper, let infisical-gateway.sh respawn) |
-| **Mumuni** | Hermes (inside Abiba CT 100) | ✅ Connected | No issues found | None needed |
+| **Mumuni** | Hermes (CT 114) | ✅ Connected | No issues found | None needed |

 ### Key Fixes Applied

@@ -65,7 +65,7 @@ triggers:
 |------|----|------|---------|
 | Zulip server | 192.168.68.19 | root | Docker: `zulip-zulip-1` |
 | Abiba (pi) | localhost | root | PM2: `abiba-zulip` |
-| Mumuni | 192.168.68.14 (kagentz CT105) | hermes | `sudo systemctl restart hermes-gateway` |
+| Mumuni | 192.168.68.24 (CT100 abiba) | root | `hermes gateway restart` |
 | Tanko | 192.168.68.122 | jerome | `PATH=$PATH:/home/jerome/.hermes/hermes-agent hermes gateway restart` |

 ## Debounce
@@ -75,8 +75,9 @@ Track via `/tmp/zulip-heal-debounce-<agent>` (unix timestamp of last restart).

 ## Reporting

-This contract is RETIRED — health-check logs are NOT knowledge graph content.
-No graph nodes are created. Logs go to Gitea (SyslogSolution/health-logs).
+Every cycle produces a knowledge graph node:
+- Title: `[LEARN] zulip-self-heal: <timestamp>`
+- metadata: { type: "remediation", status: "fixed" | "escalated" | "healthy" }
 - Issues fixed → DM: "🛠 Zulip Self-Heal: fixed <issue>"
 - Issues escalated → DM: "⚠️ Zulip Self-Heal: <issue> needs attention"
Author	SHA1	Message	Date
root	c4bf5c592d	Move Zulip bot creds from inline to env/vault reference	2026-09-08 06:04:54 +00:00
root	f90124c6e9	Fix pm2-self-heal drift: declare execution host CT100/.24 and 5-process scope The PM2 set lives on CT100/.24 (local, not CT116). CT116 runs systemd+docker, no PM2. Process scope (5/5, 2026-08-09 ruling, ecosystem authoritative): abiba-zulip, abiba-telegram, gitea-runner, spoton-service, zulip-watchdog This prevents future dispatches from drifting to the wrong host.	2026-09-06 16:17:15 +00:00
root	d646539e81	FLEET-WIDE STALE gemma-4-12b PURGE — replace with gpu-vision Purge all gemma-4-12b references from prose-contracts repo. Current reality (verified 2026-09-06): - .8 (ct8, RTX 3090): Qwen3.8-27B-Uncensored-Q4_K_M, aliases: qwen3.6-27B-code, gpu-dense - .15 (strix): Carnice-Qwen3.6-35B-A3B-Q4_K_M MoE, alias: strix-moe - .110 (ct110, RTX 5070): Qwen3.5-9B VISION (multimodal), alias: gpu-vision Syslog-auto weighted pool: qwen3.6-27B-code 0.70 + strix-moe 0.20 + gpu-vision 0.10 All gemma-4-12b references replaced with gpu-vision where it was the RTX 5070 model. Vision/light roles now route to gpu-vision (not gemma-4-12b).	2026-09-06 12:19:27 +00:00
root	6253aeb72b	Add check-health section with live probes to infrastructure-monitoring contract PR Pipeline — Authorize → Validate → Review → Merge / auth (pull_request) Successful in 5s Details PR Pipeline — Authorize → Validate → Review → Merge / validate (pull_request) Failing after 5s Details PR Pipeline — Authorize → Validate → Review → Merge / lint (pull_request) Skipped Details PR Pipeline — Authorize → Validate → Review → Merge / ai-review (pull_request) Skipped Details PR Pipeline — Authorize → Validate → Review → Merge / gate (pull_request) Skipped Details	2026-08-22 23:01:19 +00:00
root	66f94d14fd	Item 6: Auto-compaction at ~60% — update thresholds - gpu-fleet.prose.md: Update compression.threshold to 0.60 (~77K triggers) - Add pi compaction.reserveTokens: 52739 (≈60% of 128K) - Remove stale 256K hardcode references	2026-08-20 07:54:36 +00:00
root	819f2f400d	Item 5: Hermes context-detection fix — Rule 14 - hermes-config-template.prose.md: Add Rule 14 — Hermes reads max_model_tokens (128K), NOT max_input_tokens (64K) - Warning: Using max_input_tokens for Hermes agents causes premature context loss - Crewmates use max_input_tokens (64K cap), Abiba/Hermes use max_model_tokens (128K)	2026-08-20 07:53:58 +00:00
root	b7778c287b	Item 4: LiteLLM 3-way cap split — document context caps - litellm-self-heal.prose.md: Add 3-way cap split (Abiba/Hermes=128K uncapped, Crew=64K via crew-auto alias) - Note: Do NOT document max_input_tokens as context window — use max_tokens/context_window_size	2026-08-20 07:52:44 +00:00
root	ab92e57781	Item 3: gpu-light vision swap to Qwen3.5-9B - gpu-fleet.prose.md: Update gpu-light row to Qwen3.5-9B (Q5_K_M + mmproj-F16) - gpu-fleet.prose.md: Update topology diagram, routing tables, VRAM, benchmarks - gpu-fleet.prose.md: Fix timeout references, backward compat notes - gpu-self-heal.prose.md: Update gpu-light row and tok/s performance - Note: Qwen3.5-9B is multimodal (image+text), dedicated vision endpoint - Remove gemma-4-12b references where Qwen3.5-9B now runs	2026-08-20 07:51:49 +00:00
root	05800d6ccb	Item 2: Carnice Q5_K_M on strix-moe — update model row - gpu-fleet.prose.md: Update strix-moe row to Carnice-Qwen3.6-MoE-35B-A3B (Q5_K_M, ~24.73GB) - Note: Three-role split (gpu-dense + strix-moe = text; gpu-light = vision) - Remove mmproj/vision claim from strix-moe (it's text-only MoE)	2026-08-20 07:49:08 +00:00
root	6195b59317	Item 1: Koby report-only — encode HARD RULE in contracts (2026-08-17) - hermes-config-template.prose.md: Add Rule 17 — Koby is never repaired, full stop - hermes-agent-baseline.prose.md: Document Koby report-only posture - contract-registry.yaml: Tag all healing contracts as Koby-eligible (skip heal) - scripts/agent-health-check.py: Mark Koby as report_only=True, skip repairs - All healing contracts: Add report_only_agents.koby marker Captain-approved ship via no-mistakes. PR auto-merges green.	2026-08-20 07:42:22 +00:00
root	f7218e04c0	pm2-self-heal: restore abiba-zulip, retire gpu-watchdog, document systemd for gpu-monitor	2026-08-03 22:35:55 +00:00