fix: update Mumuni CT reference to 100 (Hermes gateway on CT 100)

.gitignore

@@ -1 +0,0 @@
-__pycache__/

abiba-zulip-restore.prose.md

@@ -1,6 +1,4 @@
 ---
-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: >
@@ -13,7 +11,6 @@ version: 1.0.0
 status: active
 runtime_contract: 2
 ---
----
 
 # Abiba Zulip Restore — Resume pi Zulip Communication
 
@@ -307,7 +304,6 @@ 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.

audit-hermes-config.py

@@ -1,230 +0,0 @@
-#!/usr/bin/env python3
-"""
-Hermes Config Audit — validates a live config.yaml against the prose contract rules.
-
-Usage:
-    python3 audit-hermes-config.py <config.yaml>
-    python3 audit-hermes-config.py /root/.hermes/config.yaml
-
-Exit codes:
-    0 = all checks pass
-    1 = one or more contract violations found
-
-This script encodes every rule from hermes-config-template.prose.md so config
-changes can be verified before and after application. It is the single automated
-enforcement layer for the prose contract.
-
-Contract: /root/prose-contracts/hermes-config-template.prose.md
-"""
-
-import sys
-import yaml
-
-VIOLATIONS = []
-WARNINGS = []
-PASSES = []
-
-
-def check(condition, rule, message):
-    if condition:
-        PASSES.append(f"[{rule}] {message}")
-    else:
-        VIOLATIONS.append(f"[{rule}] {message}")
-
-
-def warn(rule, message):
-    WARNINGS.append(f"[{rule}] {message}")
-
-
-def audit(path):
-    with open(path) as f:
-        cfg = yaml.safe_load(f)
-
-    model = cfg.get("model", {})
-    fb = cfg.get("fallback_providers", {})
-    comp = cfg.get("compression", {})
-    aux = cfg.get("auxiliary", {})
-    deleg = cfg.get("delegation", {})
-    cps = cfg.get("custom_providers", [])
-    cp = cps[0] if cps else {}
-
-    # --- Rule 3: API Keys via Environment ---
-    check(
-        model.get("api_key") in ("", None),
-        "Rule 3",
-        f"model.api_key must be empty (got {model.get('api_key')!r}) — keys via env var, not hardcoded",
-    )
-    check(
-        model.get("api_key_env") == "LITELLM_API_KEY",
-        "Rule 3",
-        f"model.api_key_env must be LITELLM_API_KEY (got {model.get('api_key_env')!r})",
-    )
-
-    # --- Rule 5: Main Config Base URL ---
-    expected_base = "http://192.168.68.116/v1"
-    check(
-        model.get("base_url") == expected_base,
-        "Rule 5",
-        f"model.base_url must be {expected_base} (got {model.get('base_url')!r}) — /v1 not /litellm/v1",
-    )
-
-    # --- Rule 6: max_tokens Is Required ---
-    check(
-        isinstance(model.get("max_tokens"), int) and model.get("max_tokens") <= 8192,
-        "Rule 6",
-        f"model.max_tokens must be set and <= 8192 (got {model.get('max_tokens')!r}) — thermal safety",
-    )
-
-    # --- Rule 7: Auxiliary Model Consistency ---
-    check(
-        comp.get("model") == "syslog-auto",
-        "Rule 7",
-        f"compression.model must be syslog-auto (got {comp.get('model')!r}) — auto-routing to prevent Strix Halo overload",
-    )
-    aux_comp = aux.get("compression", {})
-    check(
-        aux_comp.get("model") == "syslog-auto",
-        "Rule 7",
-        f"auxiliary.compression.model must be syslog-auto (got {aux_comp.get('model')!r}) — must match compression.model",
-    )
-
-    # --- Rule 8: GPU Workload Distribution ---
-    check(
-        aux.get("vision", {}).get("model") == "gpu-light",
-        "Rule 8",
-        f"auxiliary.vision.model must be gpu-light (got {aux.get('vision', {}).get('model')!r}) — RTX 5070 stable alias",
-    )
-    check(
-        aux.get("web_extract", {}).get("model") == "gpu-light",
-        "Rule 8",
-        f"auxiliary.web_extract.model must be gpu-light (got {aux.get('web_extract', {}).get('model')!r}) — RTX 5070 stable alias",
-    )
-
-    # --- Rule 9: Compression Threshold ---
-    check(
-        comp.get("threshold") == 0.65,
-        "Rule 9",
-        f"compression.threshold must be 0.65 for 128K models (got {comp.get('threshold')!r})",
-    )
-    check(
-        comp.get("max_context_window") == 131072,
-        "Rule 9",
-        f"compression.max_context_window must be 131072 (got {comp.get('max_context_window')!r}) — matches 128K GPU capacity",
-    )
-
-    # --- Rule 10: Default Model Must Be syslog-auto ---
-    check(
-        model.get("default") == "syslog-auto",
-        "Rule 10",
-        f"model.default must be syslog-auto (got {model.get('default')!r}) — auto-routing default",
-    )
-
-    # --- Rule 14: Provider Name Must Match custom_providers Name ---
-    check(
-        model.get("provider") == "harness",
-        "Rule 14",
-        f"model.provider must be 'harness' (got {model.get('provider')!r}) — NOT 'custom'. "
-        f"provider: custom causes generic resolution path that ignores key_env → 'no-key-required' → 401",
-    )
-    check(
-        comp.get("provider") == "harness",
-        "Rule 14",
-        f"compression.provider must be 'harness' (got {comp.get('provider')!r})",
-    )
-    for aux_name in ("vision", "web_extract", "compression"):
-        aux_provider = aux.get(aux_name, {}).get("provider")
-        check(
-            aux_provider == "harness",
-            "Rule 14",
-            f"auxiliary.{aux_name}.provider must be 'harness' (got {aux_provider!r})",
-        )
-    check(
-        deleg.get("provider") == "harness",
-        "Rule 14",
-        f"delegation.provider must be 'harness' (got {deleg.get('provider')!r})",
-    )
-    check(
-        fb.get("provider") == "deepseek",
-        "Rule 14",
-        f"fallback_providers.provider must be 'deepseek' (got {fb.get('provider')!r}) — "
-        f"true fallback diversity, not same endpoint as primary",
-    )
-    check(
-        fb.get("model") == "deepseek-v4-flash",
-        "Rule 14",
-        f"fallback_providers.model must be 'deepseek-v4-flash' (got {fb.get('model')!r})",
-    )
-    check(
-        fb.get("api_key_env") == "DEEPSEEK_API_KEY",
-        "Rule 14",
-        f"fallback_providers.api_key_env must be DEEPSEEK_API_KEY (got {fb.get('api_key_env')!r})",
-    )
-
-    # --- custom_providers sanity ---
-    check(
-        cp.get("name") == "harness",
-        "custom_providers",
-        f"custom_providers[0].name must be 'harness' (got {cp.get('name')!r})",
-    )
-    check(
-        cp.get("key_env") == "LITELLM_API_KEY" or cp.get("api_key_env") == "LITELLM_API_KEY",
-        "custom_providers",
-        f"custom_providers[0] must have key_env or api_key_env = LITELLM_API_KEY "
-        f"(got key_env={cp.get('key_env')!r}, api_key_env={cp.get('api_key_env')!r})",
-    )
-    check(
-        cp.get("base_url", "").endswith("/v1"),
-        "custom_providers",
-        f"custom_providers[0].base_url must end with /v1 (got {cp.get('base_url')!r})",
-    )
-
-    # --- 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"}
-    for section_path, section_dict in [
-        ("model", model), ("compression", comp),
-        ("auxiliary.vision", aux.get("vision", {})),
-        ("auxiliary.web_extract", aux.get("web_extract", {})),
-        ("auxiliary.compression", aux.get("compression", {})),
-        ("delegation", deleg),
-    ]:
-        m = section_dict.get("model", "")
-        if m in raw_names:
-            warn(
-                "Rule 7/8",
-                f"{section_path}.model = {m!r} — raw model name, use stable alias instead "
-                f"(gpu-light, gpu-dense, strix-moe, syslog-auto)",
-            )
-
-    # --- Report ---
-    print(f"{'=' * 60}")
-    print(f"Hermes Config Audit: {path}")
-    print(f"{'=' * 60}")
-    print(f"\n✅ PASSED ({len(PASSES)}):")
-    for p in PASSES:
-        print(f"  ✅ {p}")
-
-    if WARNINGS:
-        print(f"\n⚠️  WARNINGS ({len(WARNINGS)}):")
-        for w in WARNINGS:
-            print(f"  ⚠️  {w}")
-
-    if VIOLATIONS:
-        print(f"\n❌ VIOLATIONS ({len(VIOLATIONS)}):")
-        for v in VIOLATIONS:
-            print(f"  ❌ {v}")
-        print(f"\n{'=' * 60}")
-        print(f"RESULT: FAIL — {len(VIOLATIONS)} violation(s) must be fixed")
-        print(f"{'=' * 60}")
-        return 1
-    else:
-        print(f"\n{'=' * 60}")
-        print(f"RESULT: PASS — all contract rules satisfied")
-        print(f"{'=' * 60}")
-        return 0
-
-
-if __name__ == "__main__":
-    if len(sys.argv) < 2:
-        print("Usage: python3 audit-hermes-config.py <config.yaml>")
-        sys.exit(2)
-    sys.exit(audit(sys.argv[1]))

contract-registry.yaml

@@ -1867,73 +1867,3 @@ 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"

disk-gc-threat-response.prose.md

@@ -1,6 +1,4 @@
 ---
-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: >
@@ -13,7 +11,6 @@ description: >
 id: 067NV8KJ03ZG71S44N41F31022
 version: 1.0.0
 ---
----
 
 # Disk GC & Threat Response
 
@@ -38,7 +35,8 @@ Docker hosts get special attention:
 | All other CTs | — | LOW — no Docker | apt clean, log rotate |
 | GPU bare metal (.8, .110) | — | LOW — no Docker on GPU hosts | log rotate |
 
-> **Note:** CT 118 is now jdownloader (active on storepve). CT 101 (llm-gpu) → bare metal .8, CT 103 (ocu-llm) → bare metal .110.
+> **Decommissioned:** CT 118 (jitsi) — intentionally stopped, not scanned.
+> **Migrated:** CT 101 (llm-gpu) → bare metal .8, CT 103 (ocu-llm) → bare metal .110.
 
 ## Threat Levels
 
@@ -277,10 +275,10 @@ one-off GPU builds. No automated post-migration cleanup was in place.
 ### CT Access (via pct-run)
 | CT | Name | Node | Status |
 |----|------|------|--------|
-| 100 | abiba | hwepve | local |
-| 102 | adguard | minipve | ✅ reachable |
+| 100 | abiba | amdpve | local |
+| 102 | adguard | acerpve | ✅ reachable |
 | 104 | authentik | minipve | ✅ reachable |
-| 105 | kagentz | hwepve | ✅ reachable |
+| 105 | kagentz | amdpve | ✅ reachable |
 | 106 | ra-h-os | storepve | ✅ reachable |
 | 107 | pbs | storepve | ✅ reachable |
 | 108 | media | storepve | ✅ reachable |
@@ -288,7 +286,7 @@ 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 |
+| 114 | mumuni | minipve | ✅ reachable |
 | 115 | scottdenya | amdpve | ✅ reachable |
 | 116 | syslog-api | minipve | ✅ reachable |
 | 117 | zulip | storepve | ✅ reachable |
@@ -305,4 +303,4 @@ 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.
+> **Decommissioned:** CT 118 (jitsi) — intentionally stopped.\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.

docs/AUTHORING-GUIDE.md

@@ -13,7 +13,7 @@ the description:
 
 1. **What system does this contract touch?** Name the hosts, CTs, containers,
    and services explicitly. "The inference fleet" is vague. "GPU .8 (RTX 3090,
-   qwen), .110 (RTX 5070, gemma), .15 (Strix Halo, strix-moe), and LiteLLM on CT
+   qwen), .110 (RTX 5070, gemma), .15 (Strix Halo, ornith), and LiteLLM on CT
    116" is specific.
 
 2. **Who runs this contract, and when?** State the agent, the trigger (cron,
@@ -185,7 +185,7 @@ what, and why should I care?
 
 ```
 ❌ "Monitors infrastructure health"
-✅ "Scans all 6 Proxmox nodes and 19 CTs for disk pressure, checks Docker
+✅ "Scans all 5 Proxmox nodes and 19 CTs for disk pressure, checks Docker
    container health on .7/.116/.17, alerts via Telegram DM on RED/CRITICAL"
 ```
 

gpu-fleet.prose.md

@@ -14,7 +14,7 @@ description: >
   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 2026-07-27: gpu-dense swapped to Qwen3.8-27B-Uncensored-Q4_K_M
+  UPDATED 2026-07-27: gpu-dense swapped to SmartCode-Fable-5-CoT-Reasoning-QKVO-Qwen-3.6-27B-Distilled
   (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%).
@@ -75,7 +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  │  │ Qwen3.5-9B  │  │ qwen3.5   │  │ Prometheus   │
+│ qwen3.6  │  │ gemma-4-12b │  │ qwen3.6   │  │ Prometheus   │
 │ 27B-code │  │ :8080       │  │ -35B-udq4 │  │ exporter     │
 │ :8080    │  │ :9400 (exp) │  │ :9400(exp)│  │ :9401        │
 │ :9400    │  └─────────────┘  └───────────┘  └──────────────┘
@@ -90,19 +90,19 @@ When a model is swapped on a GPU, ONLY the infrastructure layer changes — agen
 | Alias | GPU | Current Model | Will Route To |
 |-------|-----|---------------|---------------|
 | `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-dense` | RTX 3090 (.8) | SmartCode-Fable-5-27B-UD-Q4_K_XL | Whatever runs on RTX 3090 |
 | `gpu-light` | RTX 5070 (.110) | gemma-4-12b | Whatever runs on RTX 5070 |
 
-**Backward compatibility**: Old model-specific names (qwen3.6-27B-code, gemma-4-12b, qwen3.5-9b-it) still work
+**Backward compatibility**: Old model-specific names (qwen3.6-27B-code, gemma-4-12b, qwen3.6-35B-udq4) 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) | ~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 |
+| SmartCode-Fable-5-27B-UD-Q3_K_XL | RTX 3090 | .8 (llm-gpu) | ~22.4/24.6GB (91%) | **128K** | q4_0 | 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 |
 
 ## Routing Configuration (LiteLLM — July 2026)
 
@@ -110,9 +110,9 @@ 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** |
-| 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** |
+| SmartCode-Fable-5-27B-UD-Q3_K_XL | 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** |
 
 Note: All syslog-auto entries route directly to GPUs with `api_key: not-needed`. The router (port 9000) is NOT in the inference path.
 
@@ -120,9 +120,9 @@ Note: All syslog-auto entries route directly to GPUs with `api_key: not-needed`.
 
 | Model | RPM Cap | Notes |
 |-------|---------|-------|
-| 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 |
+| strix-moe (qwen3.6-35B-udq4) | 40 | Tight cap — prevents Strix overload |
+| SmartCode-Fable-5-27B-UD-Q3_K_XL | 500 | High cap — primary workhorse (replaces qwen3.6-27B-code) |
+| gemma-4-12b | 500 | High cap — IQ4_NL+MTP, 122 tok/s |
 
 ### Stable Aliases (for agent configs — never change)
 
@@ -193,7 +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`
-   - 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)
+   - 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)
    - 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
@@ -250,10 +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 (2026-08-20)**: 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, gemma-4-12b 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.
+- **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 (2026-07-27)**: Swapped to SmartCode-Fable-5-27B-UD-Q3_K_XL (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 (2026-07-15)**: 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 2026-07-27)**: SmartCode-Fable-5-27B 300s, gemma-4-12b 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`.
@@ -268,8 +268,8 @@ 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) | Qwen3.5-9B (Q5_K_M) | **145** | — | — | **128K** |
+| RTX 3090 (.8) | SmartCode-Fable-5-27B-UD-Q3_K_XL | **TBD** | — | — | **128K** |
+| RTX 5070 (.110) | gemma-4-12b (IQ4_NL+MTP) | **191** | — | — | **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.
@@ -296,8 +296,7 @@ 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 0.60: fires at ~77K (~51K headroom before 128K ceiling)
-- **Pi agents (Abiba)**: `compaction.reserveTokens: 52739` (≈60% of 128K)
+- Compression threshold 0.65: fires at ~85K (~43K headroom before 128K ceiling)
 - Mumuni compression model alias: `strix-moe` with 300s timeout
 
 ### Mumuni Agent Profile
@@ -314,7 +313,7 @@ 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` | 0.60 | Triggers at ~77K (~60% of 128K) — optimized for 128K context |
+| `compression.threshold` | 0.65 | Triggers at ~85K |
 | `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 |

gpu-self-heal.prose.md

@@ -1,6 +1,4 @@
 ---
-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: >
@@ -18,7 +16,6 @@ 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
 
@@ -41,7 +38,6 @@ 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)
@@ -49,13 +45,13 @@ depends_on:
 | Alias | GPU | Host | Model | VRAM | Ctx | tok/s | Role |
 |-------|-----|------|-------|------|-----|-------|------|
 | `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 |
+| `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 |
 | `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 ~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 gemma-4-12b was.
+- 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.
 - 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).
@@ -160,7 +156,7 @@ 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, ~145 tok/s) → Vision (image+text), web search, lightweight tasks. Weight: 0.15 (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).
   - 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**:
@@ -170,7 +166,6 @@ 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
@@ -252,13 +247,12 @@ call update-gpu-health
 }
 ```
 
----
 ---
 
 ## Reporting
 
-### 1. Gitea Log (not knowledge graph — hard rule)
-Pushed to `SyslogSolution/health-logs/gpu/{run_id}.json` — versioned, searchable, not in graph.
+### 1. Knowledge Graph
+Every action logged as `[GPU-SELF-HEAL] <run_id>` node with full audit trail.
 
 ### 2. Zulip Alerts (#agent-hub → alerts-gpu)
 - `issues_fixed > 0` → "🛠 GPU Self-Heal — <gpu> <issue> resolved"
@@ -269,7 +263,6 @@ 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)

hermes-agent-baseline.prose.md

@@ -25,12 +25,12 @@ done
 | Agent | CT | Node | IP | LiteLLM Alias | Key Source | Platform |
 |-------|-----|------|-----|---------------|------------|----------|
 | Tanko | 112 | amdpve | .122 | `tanko` | 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 |
+| Mumuni | 100 (abiba) | hwepve | .24 | `mumuni` | Infisical vault | Hermes (Pi gateway) |
+| Koby | 129 | amdpve | srv1079750 | `koby` | Infisical vault | **Hermes** |
+| Koonimo | 114 | amdpve | ? | `koonimo` | Infisical vault | Hermes |
 | Shumba | — | 192.168.68.119 | N/A | N/A (DeepSeek) | Hermes (RETIRED — CT119 now Infisical vault) |
 
-> **Note**: CT hostnames (tdunna→CT111, baggy→CT113) differ from agent identities (koby, koonimo).
+> **Note**: CT hostnames (tdunna→CT129, baggy→CT114) differ from agent identities (koby, koonimo).
 
 Access: `pct-run <CT_ID> <command>` — no IPs needed. GPU hosts (.8, .110, .15) use SSH.
 Keys are stored in Infisical vault (project=agents, env=production) and injected at
@@ -169,15 +169,11 @@ 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) — **REPORT-ONLY MODE**
+### For Koby (CT 129 / tdunna)
 
-Koby runs Hermes on CT 111 (tdunna). Config files at `/root/.hermes/config.yaml`.
+Koby runs Hermes on CT 129 (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)
@@ -257,7 +253,7 @@ EnvironmentFile=/etc/environment        # sources LITELLM_API_KEY
 
 Run the consolidated health check:
 ```bash
-python3 /root/scripts/agent-health-check.py
+python3 /root/scripts/agent-health-check.py  # v2: now checks all 5 agents including Koby/Koonimo SSH, CT liveness, config YAML, wrapper integrity, vault non-emptiness
 ```
 This validates all 4 LiteLLM keys, detects GPU port conflicts (ghost processes),
 verifies gateway liveness, confirms Zulip streaming (`edit_message` present),

hermes-config-template.prose.md

@@ -5,11 +5,14 @@ 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 2026-07-16: Compression model is the stable alias `strix-moe` (NOT `ornith-1.0-35b`,
+  UPDATED 2026-07-18: Compression model switched to `syslog-auto` (was `strix-moe`)
+  to relieve Strix Halo pressure. syslog-auto distributes compression across the
+  weighted pool (55% RTX 3090, 30% Strix Halo, 15% RTX 5070).
+  UPDATED 2026-07-16: Compression model was 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).
+  UPDATED 2026-07-12: GPU workload redistributed. Compression → Strix Halo (later switched to syslog-auto 2026-07-18). RTX 3090 context verified at 128K. Infisical .env fallback required (Rule 3/13).
 ---
 
 ## Maintains
@@ -32,10 +35,10 @@ 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` | 192.168.68.24 | root@.24 | 6 profiles ✱ |
+| Mumuni | `mumuni` | 192.168.68.24 (CT100 abiba) | 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 | — |
+| Koonimo | `koonimo` | CT 114 (baggy) | SSH root | — |
 | Kagenz0 | `kagenz0-*` | ? | Zulip | — |
 
 > CT hostnames (tdunna, baggy) differ from agent identities (koby, koonimo).
@@ -130,7 +133,9 @@ mcp_servers:
 # ─── Compression ───
 compression:
   enabled: true
-  model: syslog-auto               # ⚠️ Must match auxiliary.compression.model. Stable alias (gpu-fleet § Stable Role-Based Aliases). NOT ornith-1.0-35b (LiteLLM does not serve that name).
+  model: syslog-auto              # ⚠️ Switched from strix-moe 2026-07-18 to relieve Strix Halo.
+                                  # syslog-auto distributes across weighted pool (55% RTX 3090,
+                                  # 30% Strix Halo, 15% RTX 5070). All GPUs at 128K.
   provider: harness
   max_context_window: 131072      # MUST match actual GPU capacity. All 3 GPUs are 128K (Jul 17).
   threshold: 0.65                 # Fires at ~170K for 262K window, ~85K for 128K
@@ -145,8 +150,9 @@ compression:
 #   model: gpu-light                 # stable alias (NOT raw "gemma-4-12b")
 #   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.
+# Compression uses syslog-auto (switched from strix-moe 2026-07-18) to distribute
+# load across the weighted pool and relieve Strix Halo pressure.
+# Vision and web_extract use gpu-light = RTX 5070 (12B).
 # 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)
 # in agent configs — use the stable aliases so model swaps don't break agents.
@@ -166,7 +172,7 @@ auxiliary:
     timeout: 30
   compression:
     provider: harness
-    model: syslog-auto              # MUST match compression.model above. Stable alias for Strix Halo (weighted pool).
+    model: syslog-auto             # Switched from strix-moe 2026-07-18. Relieves Strix Halo pressure.
     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)
@@ -247,34 +253,30 @@ The following MUST be identical across ALL profiles:
 - Apply to BOTH main config AND all sub-agent 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)
-- 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.
-- **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`.
+### Rule 7: Auxiliary Model Consistency (UPDATED 2026-07-18)
+- Vision and web_extract use `gpu-light` (stable alias, RTX 5070 — 12GB, vision-optimized)
+- Compression now uses `syslog-auto` (switched from `strix-moe` 2026-07-18) to distribute
+  compression load across the weighted pool (55% RTX 3090, 30% Strix Halo, 15% RTX 5070).
+  This relieves Strix Halo pressure while keeping compression functional on all GPUs.
+- **`syslog-auto` is the valid compression model** — LiteLLM serves it as the weighted pool.
+  Old configs with `strix-moe` for compression should be updated to `syslog-auto`.
 - All auxiliary services MUST use identical routing:
   - `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
-  (64GB UMA, 128K context) — the designated compression GPU. This frees the
-  RTX 5070 for vision and web search, and the RTX 3090 for heavy reasoning.
+- **Compression via syslog-auto**: Routes through the weighted pool. Strix Halo still handles
+  ~30% of compression calls (at 60 RPM via pool vs 40 RPM direct), but the bulk (55%)
+  goes to RTX 3090 which has ample spare capacity.
 - The `compression:` block's `model` MUST match `auxiliary: compression: model`
 - The `compression: max_context_window: 131072` MUST match actual GPU capacity (128K)
 
-### 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)
-- **Strix Halo (64GB, 128K ctx, syslog-auto)**: Context compression, summarization, long docs
+### Rule 8: GPU Workload Distribution (UPDATED 2026-07-18)
+- **RTX 3090 (24GB, 128K ctx, qwen3.6-27B-code)**: Heavy reasoning, code gen, long conversations — also handles ~55% of compression via syslog-auto pool
+- **RTX 5070 (12GB, 128K ctx, gemma-4-12b)**: Vision, web search, quick tasks, web_extract — handles ~15% of compression via syslog-auto pool
+- **Strix Halo (64GB, 128K ctx, qwen3.6-35B-udq4)**: Agent reasoning, compression (~30% via syslog-auto pool), fallback for other GPUs
 - 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.compression.model: syslog-auto` (Strix Halo)
+  - `auxiliary.vision.model: gpu-light` (RTX 5070)
+  - `auxiliary.web_extract.model: gpu-light` (RTX 5070)
+  - `auxiliary.compression.model: syslog-auto` (distributed pool, switched from strix-moe 2026-07-18)
 - Default model (`model.default`) and custom_provider remain `syslog-auto` for auto-routing
 - For 128K context window: `threshold: 0.65` (fires at ~85K tokens)
 - Do NOT use `threshold: 0.25` — this fires at 65K, causing premature context loss
@@ -338,17 +340,6 @@ 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).
 
@@ -387,26 +378,6 @@ curl -s -o /dev/null -w '%{http_code}' -H "Authorization: Bearer $K" http://192.
 - `/etc/environment` is NO LONGER the canonical key source (stale values there caused 401s).
 - Do NOT leave a hardcoded stale key in `/etc/environment` — it shadows the drop-in/wrapper.
 
-### Rule 14: Provider Name Must Match custom_providers Name (ADDED 2026-07-19, WAL #1471)
-
-- `model.provider` MUST be `harness` (the `custom_providers[0].name`), NOT the literal string `custom`
-- When `provider: custom`, Hermes' `_get_named_custom_provider("custom")` returns None (no provider is
-  named "custom" — it is named "harness"), causing a fall-through to the generic resolution path
-  (`source: env/config`) at `runtime_provider.py:1156`
-- The generic path builds `api_key_candidates` from `model.api_key` (empty), host-gated
-  OLLAMA/OPENAI/OPENROUTER keys, and `_host_derived_api_key` (returns "" for IP addresses)
-- **The generic path does NOT resolve `model.api_key_env` or `custom_providers.key_env`** —
-  `LITELLM_API_KEY` is never read, producing `api_key = "no-key-required"` → HTTP 401
-- The named custom provider path (`source: custom_provider:harness`) DOES read `key_env` —
-  but only triggers when `provider` matches the `custom_providers[0].name`
-- All sections MUST use `provider: harness`: `model`, `compression`, `auxiliary.vision`,
-  `auxiliary.web_extract`, `auxiliary.compression`, `delegation`
-- Only `fallback_providers` uses a different provider (`deepseek`) for true fallback diversity
-- **Diagnostic**: If you see `source: env/config` in a request dump or log, the provider name
-  is wrong. It should be `source: custom_provider:harness`.
-- **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.
-
 ## Execution
 
 1. **Check current config** — Read the target agent's config.yaml
@@ -416,14 +387,3 @@ 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 17: Koby Report-Only (URGENT — 2026-08-17, 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.

hermes-zulip-plugin.prose.md

@@ -55,7 +55,7 @@ connectivity recovery including end-to-end DM validation.
 
 | Host | CT | Proxmox | IP (direct) | Hermes Home | User |
 |------|-----|---------|-------------|-------------|------|
-| Mumuni | CT100 | — | 192.168.68.24 | /root/.hermes | root |
+| Mumuni | CT114 | — | 192.168.68.123 | /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 |

hermes-zulip-restore.prose.md

@@ -1,10 +1,8 @@
 ---
-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: >
-  Restores Zulip connectivity for any Hermes agent (Mumuni CT100, Tanko CT112,
+  Restores Zulip connectivity for any Hermes agent (Mumuni CT114, Tanko CT112,
   Koby CT111, Shumba on Lucky's mini PC). Deploys the zulip-platform adapter to the correct bundled plugin
   path, verifies env credentials, restarts the gateway, and confirms Zulip
   connects. Run this whenever a Hermes agent stops responding on Zulip or after
@@ -14,7 +12,6 @@ version: 1.0.0
 status: active
 runtime_contract: 2
 ---
----
 
 # Hermes Zulip Restore — Bring Any Agent Back to Good State
 
@@ -187,7 +184,6 @@ 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.

inference-optimization.prose.md

@@ -87,7 +87,7 @@ call apply-liteLLM-routing
 
 call apply-agent-compression
   agent: mumuni
-  host: 192.168.68.24
+  host: 192.168.68.123
   config_path: /root/.hermes/config.yaml
 
 -- Phase 4: Enable llama.cpp prompt caching on GPU hosts

infrastructure-control.prose.md

@@ -13,10 +13,10 @@ description: >
   against the live system. Policy fields are authoritative. See the
   `verify-before-mutate` skill.
 
-  **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.
+  **Last verified:** 2026-07-27 — gpu-dense swapped to SmartCode-Fable-5
+  (Qwen3.6-27B distilled, ~50% fewer thinking tokens, improved coding reasoning).
+  Model pricing reduced 100x across all models ($0.15/$0.60 per 1M tokens).
+  All LiteLLM models set to 128K max_model_tokens. See data/learnings.md.
 ---
 
 # Infrastructure Control Pattern
@@ -34,7 +34,7 @@ description: >
    ┌─────────────┐    ┌──────────────┐    ┌──────────────┐
    │   Abiba     │    │   Tanko      │    │   Mumuni     │
    │   (pi)      │    │   (Hermes)   │    │   (Hermes)   │
-   │   CT 100    │    │   CT 112     │    │   CT 114     │
+   │   CT 100    │    │   CT 112     │    │   CT 100     │
    └──────┬──────┘    └──────┬───────┘    └──────┬───────┘
           │                  │                    │
           └──────────────────┼────────────────────┘
@@ -72,7 +72,7 @@ description: >
 | docker-vm (.7) | SSH root | SSH key | ✅ |
 | CT 116 (syslog-api) | SSH root | SSH key | ✅ |
 | Tanko CT (.122) | SSH jerome | id_ed25519 | ✅ |
-| Mumuni CT (.123) | SSH root | id_ed25519 | ✅ |
+| Mumuni (inside CT100 abiba .24) | SSH root | id_ed25519 | ✅ |
 | Baggy CT (113) | SSH jerome | ❌ no key access |
 | Netbird (.17) | SSH root | SSH key | ✅ |
 | Gitea | API token | Infisical vault (`GITEA_BOT_TOKEN`) | ✅ |
@@ -94,7 +94,7 @@ description: >
 |-----------|---------|----------------|--------|-------------|---------------|----------------|
 | **Abiba** (.24) | ✅ :443 | ✅ SSH | ✅ SSH | ✅ SSH jerome | ✅ SSH root | ❌ SSH |
 | **Tanko** (.122) | ❌ | ❌ | ❌ via NetBird | ✅ | ❌ | ❌ |
-| **Mumuni** (.123) | ❌ | ❌ | ❌ | ❌ | ✅ | ❌ |
+| **Mumuni** (.24) | ❌ | ❌ | ❌ | ❌ | ✅ | ❌ |
 
 **Conclusion:** Only Abiba has cross-infrastructure access. All monitoring contracts run from Abiba.
 
@@ -109,12 +109,12 @@ description: >
 | 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) |
+| hwepve | .4 | ? | ? | abiba, (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) 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.
+> minipve at .10, not acerpve. Abiba (CT 100) is on hwepve and now runs Mumuni
+> Zulip gateway internally. CT 114 (old mumuni container) destroyed 2026-07-26.
+> Mumuni now runs inside Abiba CT100 (.24). Old CT114 destroyed 2026-07-26.
 
 ### Checks (every 5 min)
 
@@ -161,7 +161,7 @@ description: >
 |-------|------|-----------|
 | **Firecrawl** | `/opt/search-stack/firecrawl-source/` | api, rabbitmq, postgres, playwright, redis |
 | **SearXNG** | `/opt/search-stack/searxng/` | searxng, valkey |
-| **Home stack** | `/opt/home_stack/` | stirling-pdf, pulse (jdownloader decommissioned 2026-08-01 → dedicated CT 118 LXC) |
+| **Home stack** | `/opt/home_stack/` | jdownloader, stirling-pdf, pulse |
 | **Audiobookshelf** | `/opt/audiobookshelf/` | audiobookshelf |
 | **Trove agents** | docker run (standalone) | trove-agent-proxmox, trove-test-agent-1, trove-test-server-1, docker-stats |
 
@@ -178,15 +178,11 @@ description: >
 - Compose: `/opt/home_stack/docker-compose.yml`
 - Control script: `/opt/home_stack/infra-control.sh`
 
-**JDownloader** (decommissioned from docker-vm 2026-08-01 — moved to dedicated CT 118 LXC):
-- LXC: CT 118 on storepve, `192.168.68.20` (JDownloader + VNC 5900 + web UI 6080)
-- Web UI: `http://192.168.68.20:6080` (noVNC via websockify)
-- Docker container `jdownloader-2` on .7 removed; compose entry stripped
+**JDownloader**:
+- URL: `http://192.168.68.7:5800` (web UI via VNC)
 
-**Pulse**:
-- URL: `http://192.168.68.7:7655` (direct LAN)
-- Public: `https://pulse.sysloggh.net` (NetBird CNAME proxy)
-- Container: `rcourtman/pulse:5.1.35` in `/opt/home_stack` (port 7655, was 3001)
+**Pulse** (Uptime Kuma):
+- URL: `http://192.168.68.7:3001`
 
 ### Ecosystem B: CT 116 syslog-api (192.168.68.116)
 
@@ -369,10 +365,10 @@ fine. Services that resolve directly to a LAN IP are NetBird-independent.
 |---------|--------|-------------|-------------|-------------|--------|
 | Proxmox API | minipve.sysloggh.net:8006 | 192.168.68.12 | LAN IP | No | ✅ |
 | LiteLLM | litellm.sysloggh.net | 192.168.68.116 | LAN IP | No | ✅ |
-| Authentik | auth.sysloggh.net:443 | 192.168.68.11:9000 | CNAME → netbird | **Yes** | ⚠️ |
+| Authentik | auth.sysloggh.net:443 | 192.168.68.11 | CNAME → netbird | **Yes** | ⚠️ |
 | Gitea | git.sysloggh.net:443 | 192.168.68.17:3000 | CNAME → netbird | **Yes** | ⚠️ |
 | Zulip | chat.sysloggh.net:443 | 192.168.68.19 | CNAME → netbird | **Yes** | ⚠️ VERIFY-BEFORE-USE |
-| Pulse | pulse.sysloggh.net:443 | 192.168.68.7:7655 | CNAME → netbird | **Yes** | ✅ verified 2026-08-01 |
+| Pulse | pulse.sysloggh.net:443 | 192.168.68.7 | CNAME → netbird | **Yes** | ⚠️ |
 | DNS UI | dns.sysloggh.net:443 | 192.168.68.10:80 | CNAME → netbird | **Yes** | ⚠️ |
 | SearXNG | searxng.sysloggh.net:8888 | 192.168.68.7:8888 | LAN IP | No | ✅ |
 | Firecrawl | firecrawl.sysloggh.net:3002 | 192.168.68.7:3002 | LAN IP | No | ✅ |
@@ -590,6 +586,8 @@ ssh root@192.168.68.110 "systemctl restart llama-server"
 
 ## Appendix B: CT Inventory
 
+| CT | Name | Node | IP | Role | Agent |
+|----|------|------|----|------|-------|
 | CT | Name | Node | IP | Role | Agent |
 |----|------|------|----|------|-------|
 | 100 | abiba | **hwepve** | .24 | Pi agent | ✅ pi |
@@ -606,11 +604,10 @@ 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 | ❌ |
-| 118 | jdownloader | storepve | .20 | JDownloader LXC (dedicated, migrated from docker-vm 2026-08-01) | ✅ |
+| 118 | jdownloader | storepve | — | JDownloader container | ❌ |
 | 119 | infisical-vault | minipve | — | Vault | ❌ |
 
 ## Appendix C: Docker Compose Files Location
@@ -632,14 +629,14 @@ Source of truth: `/root/scripts/pct-run.sh` or `prose-contracts/scripts/pct-run.
 | CT | Name | Node | pct-run |
 |-----|------|------|---------|
 | 100 | abiba | hwepve | `pct-run 100` |
-| 105 | kagentz | hwepve | `pct-run 105` |
+| 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` |
@@ -652,27 +649,35 @@ 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 (abiba, kagentz, mumuni)
+ssh root@192.168.68.4   # hwepve (abiba, kagentz) — Mumuni runs inside CT 100
 ```
 
-## Section 7: Agent Health Check (consolidated — 2026-07-05)
+## Section 7: Agent Health Check v2 (2026-07-26)
 
-Replaces 7 scattered Zulip health scripts with a single non-disruptive check
-running every 10 minutes via cron (`/root/scripts/agent-health-check.py`).
+Single non-disruptive check running every 10 minutes via cron
+(`/root/scripts/agent-health-check.py`). v2 fixes critical gaps:
+- Koby (.129) and Koonimo (.114) now have SSH hosts — no longer skipped
+- Agent-specific vault keys (`{NAME}_LITELLM_API_KEY`) not shared master key
+- CT liveness check via `pct status` on PVE nodes
+- Config YAML integrity check
+- Wrapper/CLI integrity check
+- Vault secret non-emptiness check
 
 The script is **read-only** — it never restarts, kills, or modifies anything.
-Disruptive cron-based gateways restarts (like Mumuni's zulip-watchdog.sh,
-which was kill+nohup outside systemd) are banned by policy.
 
 ### Checks Performed
 
 | Check | Frequency | What It Detects |
 |-------|-----------|-----------------|
-| LiteLLM key validation | 10 min | All 4 agent keys authenticate and return models |
+| LiteLLM key validation | 10 min | All 5 agent-specific keys authenticate (not shared master key) |
 | GPU port conflict | 10 min | Ghost processes squatting port 8080 (ss vs systemd MainPID) |
-| Gateway liveness | 10 min | Gateway process running, state file readable |
+| Gateway liveness | 10 min | Gateway process running, state file readable (all 5 agents) |
 | Zulip streaming | 10 min | `edit_message` present in adapter (streaming supported) |
 | Recent errors | 10 min | Error count in journald for last 10 min |
+| CT liveness | 10 min | `pct status` on PVE nodes — catches stopped CTs |
+| Config YAML integrity | 10 min | Python `yaml.safe_load()` — catches syntax errors |
+| Wrapper/CLI integrity | 10 min | hermes wrapper exists, infisical path correct, hermes-real reachable |
+| Vault secrets | 10 min | Agent-specific vault keys are non-empty and start with `sk-` |
 
 ### Disabled Scripts
 

infrastructure-maintenance.prose.md

@@ -140,7 +140,7 @@ After ALL updates (apt + images + restarts), verify every critical service is ba
 | Zulip | `curl -sf https://chat.sysloggh.net/api/v1/server_settings` | 200 OK |
 | Gitea | `curl -sf https://git.sysloggh.net/api/v1/version` | 200 OK |
 | PM2 processes | `pm2 jlist` (CT 100) | all pi-agent processes `online` |
-| Hermes gateways | SSH to Mumuni CT 100, Tanko CT 112; `systemctl is-active hermes-gateway` | `active` for each |
+| Hermes gateways | SSH to Mumuni CT 114, Tanko CT 112; `systemctl is-active hermes-gateway` | `active` for each |
 
 Regression check: every service that was GREEN in `health-baseline` must still be GREEN. A service that was already RED (and caused a preflight abort) is excluded — but Phase 0 should have aborted before we got here.
 

infrastructure-monitoring.prose.md

@@ -139,79 +139,6 @@ GPU .8 (RTX 3090)    GPU .110 (RTX 5070)   GPU .15 (Strix Halo)
 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'
-# Expected: 200 (HTTP 000 = unreachable/cache)
-
-# PM2 process health
-pm2 jlist
-# Expected: 5/5 online (abiba-telegram, abiba-zulip, zulip-watchdog, gitea-runner, spoton-service)
-
-# GPU exporters (may be down per DEPLOYMENT STATUS)
-curl -s http://192.168.68.8:9400/metrics && echo " - OK" || echo " - FAIL"
-curl -s http://192.168.68.110:9400/metrics && echo " - OK" || echo " - FAIL"
-curl -s http://192.168.68.15:9400/metrics && echo " - OK" || echo " - FAIL"
-
-# Prometheus targets
-curl -s http://192.168.68.116:9090/api/v1/targets | jq '.data.activeTargets'
-# Expected: All targets UP (may show some down if exporters not deployed)
-
-# Grafana health
-curl -s http://192.168.68.116:3001/api/health | jq '{status, version}'
-# Expected: {"status":"ok","version":"..."}
-
-# LiteLLM metrics
-curl -s http://192.168.68.116:4001/metrics | head -20
-# Expected: Prometheus-formatted metrics output
-```
-
-**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)**:
-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)
-
 ## Verification Commands
 
 ```bash

infrastructure-update.prose.md

@@ -2,7 +2,7 @@
 kind: responsibility
 name: infrastructure-update
 description: >
-  Autonomous system-wide update contract covering all 6 Proxmox nodes,
+  Autonomous system-wide update contract covering all 5 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.
@@ -56,11 +56,10 @@ 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, hwepve) | Mumuni | `apt update && apt upgrade -y` | 3 min |
+| CT 114 (mumuni, minipve) | Mumuni | `apt update && apt upgrade -y` | 3 min |
 | VM 101 (.8) | llm-gpu (RTX 3090) | `apt update && apt upgrade -y` | 3 min |
 | VM 103 (.110) | ocu-llm (RTX 5070) | `apt update && apt upgrade -y` | 3 min |
 
@@ -78,7 +77,7 @@ Before ANY update wave:
 |------|-------|---------|
 | VM 109 (.7) | Firecrawl | `cd /opt/search-stack/firecrawl-source && docker compose pull && docker compose up -d` |
 | VM 109 (.7) | SearXNG | `cd /opt/search-stack/searxng && docker compose pull && docker compose up -d` |
-| VM 109 (.7) | Home stack (Pulse, Stirling PDF) — JDownloader moved to CT 118 LXC 2026-08-01 | `cd /opt/home_stack && docker compose pull && docker compose up -d` |
+| VM 109 (.7) | Home stack (Pulse, Stirling PDF, JDownloader 2) | `cd /opt/home_stack && docker compose pull && docker compose up -d` |
 | VM 109 (.7) | Audiobookshelf | `cd /opt/audiobookshelf && docker compose pull && docker compose up -d` |
 | CT 116 (.116) | Inference Harness (LiteLLM, Prometheus, Grafana) | `cd /opt/inference-harness && docker compose pull && docker compose up -d` |
 | CT 117 (zulip, storepve) | Zulip | `docker pull zulip/docker-zulip:latest && docker restart zulip-zulip-1` |
@@ -160,7 +159,7 @@ Before Wave 1, snapshot these files:
 /opt/home_stack/docker-compose.yml                      (VM 109 .7)
 /opt/audiobookshelf/docker-compose.yml                  (VM 109 .7)
 /root/.pi/agent/extensions/config.yaml                  (CT 100 .24)
-/etc/systemd/system/strix-server.service                (amdpve .15 — strix-moe)
+/etc/systemd/system/ornith-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 CT 114, Tanko CT 112, etc.)
@@ -219,7 +218,7 @@ When LiteLLM is upgraded to a version supporting per-key MCP grants:
 
 ## Success Criteria
 
-- [ ] All 6 PVE nodes updated, no reboot-loop
+- [ ] All 5 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)
@@ -235,7 +234,7 @@ After completion, send Zulip DM:
 ```
 📋 Infrastructure Update — YYYY-MM-DD
 
-Updated: 6 PVE nodes, 12 CTs/VMs, 30+ containers
+Updated: 5 PVE nodes, 12 CTs/VMs, 30+ containers
 Security fixes: N CVEs patched
 Downtime: <service> <duration>
 Failures: none / <details>

litellm-self-heal.prose.md

@@ -1,6 +1,4 @@
 ---
-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
@@ -9,7 +7,7 @@ note: >
   Auto-remediation code was removed from the pi Zulip extension (retired 2026-07-04),
   now reimplemented as `litellm-health-check.sh` on CT 116.
   Script: `/opt/inference-harness/scripts/litellm-health-check.sh` on CT 116 (cron `0 */6 * * *`).
-  Reports to /var/log/litellm/health-*.json and Gitea (SyslogSolution/health-logs).
+  Reports to /var/log/litellm/health-*.json and RA-H OS knowledge graph.
   GPU monitoring integrated from gpu-monitor on .24:9100.
   
   Consolidated from litellm-health + litellm-self-heal on 2026-07-09 to eliminate
@@ -22,8 +20,7 @@ description: >
   LiteLLM inference stack health monitoring + self-healing. Verifies the full
   nginx → LiteLLM → GPU chain, 8 containers on CT 116, 3 GPU hosts, model
   inference, and agent keys. Applies remediation rules for common failures.
-  Reports every action via Zulip DM and Gitea (SyslogSolution/health-logs).
----
+  Reports every action via Zulip DM and RA-H OS knowledge graph.
 ---
 
 # LiteLLM Operations — Health Check + Self-Heal
@@ -68,15 +65,7 @@ Request → nginx:80 → LiteLLM:4000 → GPU(llama-server, parallel 2)
 
 ## 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`, `crew-auto` (new 2026-08-20).
-
-### 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.
+`model_name`s served: `qwen3.6-27B-code`, `gemma-4-12b`, `qwen3.6-35B-udq4`, `strix-moe`, `gpu-dense`, `gpu-light`, `syslog-auto`.
 
 - `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.
@@ -131,7 +120,6 @@ Preferred implementation: uncap shared pool, add capped alias for crew-only.
 - Also wakes on user request
 - On failure: re-check after 30s, escalate after 3 consecutive failures
 
----
 ---
 
 ## Health Check
@@ -174,7 +162,6 @@ Determine overall_status from individual check results:
 - "degraded" — 1-2 non-critical checks fail
 - "down" — critical checks fail
 
----
 ---
 
 ## Remediation Rules
@@ -218,15 +205,14 @@ 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
 
 Every remediation cycle produces a structured report:
 
-### 1. Gitea Log Entry
-Pushed to `SyslogSolution/health-logs/litellm/{run_id}.json` — versioned, searchable, not in graph.
+### 1. RA-H OS Knowledge Graph Node
+Created as `[LEARN] litellm-self-heal: <run_id>` with full JSON report.
 
 ### 2. Zulip DM to Owner
 - `issues_fixed > 0` — "🛠 LiteLLM Self-Heal — Fix Applied"
@@ -241,7 +227,6 @@ top actions, uptime.
 If a fix requires another agent (e.g., Authentik restart), relay sent
 to responsible agent with full context.
 
----
 ---
 
 ## Execution
@@ -267,11 +252,9 @@ call report-generator
   health: health
   actions: actions
 
--- Phase 4: Log to Gitea (not knowledge graph — hard rule)
-call gitea-logger
+-- Phase 4: Log to knowledge graph
+call kg-logger
   run_id: run_id
-  repo: SyslogSolution/health-logs
-  path: litellm/{run_id}.json
   health: health
   actions: actions
 
@@ -317,20 +300,3 @@ With failures:
   ]
 }
 ```
-
-## gitea-logger Implementation
-
-When this step executes, write the report JSON to a temp file and push to Gitea:
-
-```bash
-REPO="https://abiba-bot:${GITEA_PAT}@git.sysloggh.net/SyslogSolution/health-logs"
-DIR="litellm"
-FILE="${run_id}.json"
-echo "${report_json}" > /tmp/${FILE}
-(cd /tmp && git clone --depth 1 "${REPO}" && 
-  cp ${FILE} health-logs/${DIR}/${FILE} && 
-  cd health-logs && git add ${DIR}/${FILE} && 
-  git commit -m "litellm-health: ${run_id}" && git push)
-rm -rf /tmp/health-logs /tmp/${FILE}
-```
-

memory-audit-maintenance.prose.md

@@ -1,12 +1,9 @@
 ---
-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
 
@@ -346,4 +343,4 @@ 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.

memory-fixer.prose.md

@@ -1,74 +0,0 @@
----
-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 graph. No judgment calls — only deterministic Level 1 operations. 
-  Escalate anything that needs Kwame's input.
-version: 1.1.0
----
----
-
-# Memory Fixer
-
-## Purpose
-Auto-fix low-hanging fruit in the graph. No judgment calls — only deterministic Level 1 operations. Escalate anything that needs Kwame's input.
-
-## Level 0 Auto-Deletes (Allowed Without Approval)
-Ephemeral heartbeat and log nodes that violate "Logs NEVER go in the graph":
-
-- `[LITELLM-HEALTH]`, `[GPU-SELF-HEAL]`, `[PM2-SELF-HEAL]`
-- `[PROXMOX-MONITOR]`, `[GPU-MONITOR]`, `[INFRA-MONITOR]`, `[AGENT-HEALTH]`, `[DISK-GC]`
-- `[WAL]` entries older than 30 days
-
-**Condition:** node must be an orphan (no edges). Deleting a connected node risks breaking other nodes.
-
-**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 Judgment Required)
-
-### 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
-UPDATE nodes 
-SET metadata = json_set(
-  COALESCE(metadata, '{}'),
-  '$.tenant', 'syslogsolution',
-  '$.namespace', 'syslogsolution'
-)
-WHERE json_extract(metadata, '$.tenant') IS NULL 
-   OR json_extract(metadata, '$.namespace') IS NULL;
-```
-
-### 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. **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`
-Every Level 2 escalation logged and delivered to Kwame.

mumuni-delegation-prose-contract.prose.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 (inside Abiba CT100, hwepve, .24) via Hermes agent (Pi + Hermes Zulip gateway).
+  Runs on Mumuni (inside Abiba CT100, hwepve, .24) via Hermes agent (Hermes Zulip gateway).
 version: 1.0.0
 ---
 
@@ -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 6 nodes, check each VM, read logs —
+(60 calls) on single-turn tasks — SSH to 5 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
-"6 nodes present" in the raw data but "6/6 online" in the report — even though
+"5 nodes present" in the raw data but "5/5 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 6 Proxmox nodes for VM status", "context": "SSH to each node via 192.168.68.x, run 'qm list'"},
+        {"goal": "Check all 5 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 6 Proxmox nodes",
+      "goal": "Check all 5 Proxmox nodes",
       "status": "dispatched|completed|failed",
       "output_file": "/tmp/node-report.md"
     }

pm2-self-heal.prose.md

@@ -5,20 +5,18 @@ description: >
   Monitors critical PM2 processes (abiba-zulip, abiba-telegram) 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.
-report_only_agents:
-  - koby  # ⛔ KOBY IS NEVER REPAIRED (Rule 17, 2026-08-17) — detect + report, never fix on .129
+  CRITICAL: Never restart abiba-zulip — it runs this contract.
 ---
 
 ## 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)
+- gpu-watchdog: { status: "online", uptime: string, restarts: number }
+- gpu-monitor: { status: "online", uptime: string, restarts: number }
 - gitea-runner: { status: "online", uptime: string, restarts: number }
 - last_check: timestamp
 
-> **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.
+> **Note (2026-07-04):** `abiba-zulip` removed — Zulip extension decommissioned.
 
 ## Continuity
 
@@ -50,11 +48,11 @@ report_only_agents:
    - If status is "online" → pass
    - If status is "stopped" or "errored" → apply Rule 1
    - If restarts > 5 → alert owner
-3. **Check abiba-zulip** (live Zulip bridge, heartbeating):
+3. **Check abiba-zulip** (self-process, read-only):
    - If status is "online" → pass, log restarts count
-   - If status is "stopped" or "errored" → restart (`pm2 restart abiba-zulip` — fully restored)
+   - 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)
+4. **Log results** — Create `[LEARN]` node in knowledge graph for any actions taken
 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
 

proxmox-monitor.prose.md

@@ -88,7 +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 |
+| hwepve | 192.168.68.4 | PVE (Huawei Matebook 16, 12C/15GB) — hosts Mumuni (lxc/114) migrated from minipve 2026-07-20 |
 
 ## Operations
 

scripts/agent-health-check.py

@@ -40,16 +40,16 @@ 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", "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},
+    "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": "hwepve",  "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"},
 }
 
 GPU_HOSTS = {
     "gpu-rtx3090 (.8)":     {"host": "192.168.68.8",   "port": 8080, "service": "llama-server"},
     "gpu-rtx5070 (.110)":   {"host": "192.168.68.110", "port": 8080, "service": "llama-server"},
-    "gpu-strixhalo (.15)":  {"host": "192.168.68.15",  "port": 8080, "service": "strix-server"},
+    "gpu-strixhalo (.15)":  {"host": "192.168.68.15",  "port": 8080, "service": "ornith-server"},
 }
 
 FAIL = []
@@ -57,16 +57,6 @@ FAIL = []
 INFISICAL_TOKEN = os.environ.get("INFISICAL_TOKEN")
 INFISICAL_API_URL = os.environ.get("INFISICAL_API_URL", "https://vault.sysloggh.net")
 
-# Fallback: if no env token, read the shared vault token file
-if not INFISICAL_TOKEN:
-    _token_path = os.path.expanduser("~/.infisical-token")
-    if os.path.isfile(_token_path):
-        try:
-            with open(_token_path) as _f:
-                INFISICAL_TOKEN = _f.read().strip()
-        except (OSError, UnicodeDecodeError):
-            pass
-
 # ── Helpers ──────────────────────────────────────────────────────────
 
 def ssh(host, cmd, user="root"):
@@ -239,26 +229,20 @@ 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
 
-        # ⛔ 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 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
 
         # Gateway state file
         state = ssh(host, "cat ~/.hermes/gateway_state.json 2>/dev/null", user=user)

scripts/daily-infra-report.py

@@ -313,8 +313,8 @@ def collect():
         "updated_at": tanko_data.get("updated_at"),
     }
     
-    # Mumuni (CT 100, IP 192.168.68.24)
-    mumuni_state = ssh("192.168.68.24", "cat ~/.hermes/gateway_state.json 2>/dev/null")
+    # Mumuni (CT 114, IP 192.168.68.123)
+    mumuni_state = ssh("192.168.68.123", "cat ~/.hermes/gateway_state.json 2>/dev/null")
     mumuni_data = {}
     try:
         mumuni_data = json.loads(mumuni_state) if mumuni_state else {}
@@ -322,7 +322,7 @@ def collect():
         mumuni_data = {}
     mumuni_platforms = mumuni_data.get("platforms", {})
     report["agents"]["mumuni"] = {
-        "platform": "hermes", "ct": 114, "ip": "192.168.68.24",
+        "platform": "hermes", "ct": 114, "ip": "192.168.68.123",
         "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"),
@@ -330,7 +330,7 @@ def collect():
         "hermes_version": "",
     }
     # Get Hermes version
-    ver = ssh("192.168.68.24", "hermes --version 2>/dev/null | head -1")
+    ver = ssh("192.168.68.123", "hermes --version 2>/dev/null | head -1")
     if ver:
         report["agents"]["mumuni"]["hermes_version"] = ver.split("·")[0].replace("Hermes Agent ","").strip()
     

scripts/pct-run.sh

@@ -11,33 +11,31 @@ set -euo pipefail
 # ── CT ID → PVE Node mapping (maintained HERE, not in prose contracts) ──
 declare -A CT_NODES=(
     # amdpve (192.168.68.15)
+    [100]=amdpve    # abiba
+    [105]=amdpve    # kagentz
     [111]=amdpve    # tdunna
     [112]=amdpve    # tanko
     [113]=amdpve    # baggy
     [115]=amdpve    # scottdenya
     # minipve (192.168.68.12)
-    [102]=minipve   # adguard (was acerpve)
     [104]=minipve   # authentik
     [110]=minipve   # gitea
+    [114]=minipve   # mumuni
     [116]=minipve   # syslog-api
-    [119]=minipve   # infisical-vault
     # storepve (192.168.68.6)
     [106]=storepve  # ra-h-os
     [107]=storepve  # proxmox-backup
     [108]=storepve  # media
     [117]=storepve  # zulip
-    [118]=storepve  # jdownloader
-    # acerpve (192.168.68.9) — no CTs (bare metal GPU .8)
-    # hwepve (192.168.68.4)
-    [100]=hwepve    # abiba (was amdpve)
-    [105]=hwepve    # kagentz (was amdpve)
-    [114]=hwepve    # mumuni (was minipve)
+    # acerpve (192.168.68.9)
+    [102]=acerpve   # adguard
     # ocupve (192.168.68.5) — no CTs (bare metal GPU .110)
     #
     # REMOVED CTs (migrated to bare metal, decommissioned, or VMs):
     #   101 llm-gpu   → bare metal 192.168.68.8   (RTX 3090)
     #   103 ocu-llm   → bare metal 192.168.68.110 (RTX 5070)
     #   109 docker-vm → KVM VM 192.168.68.7       (use direct SSH)
+    #   118 jitsi     → stopped, not in service
 )
 
 # Each node must be root-accessible via SSH hostname
@@ -50,7 +48,6 @@ 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() {

scripts/prose-ai-review.sh

@@ -46,19 +46,17 @@ 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" (6 nodes):**
-- amdpve (192.168.68.15): tanko, tdunna, baggy, scottdenya
-- 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
+**Proxmox Cluster "Tabiri" (5 nodes):**
+- amdpve (192.168.68.15): abiba, kagentz, tanko, tdunna, baggy, scottdenya
+- minipve (192.168.68.12): authentik, gitea, mumuni, syslog-api, jitsi
+- storepve (192.168.68.6): docker-vm, ra-h-os, PBS, media, zulip
+- acerpve (192.168.68.9): llm-gpu, adguard
 - ocupve (192.168.68.5): ocu-llm
-- hwepve (192.168.68.4): abiba, kagentz, mumuni
 
-**CT IDs (verified 2026-07-24 against PVE API):**
+**CT IDs (verified 2026-07-04 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  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.**
 

scripts/zulip-monitor.sh

@@ -100,7 +100,7 @@ else
 fi
 
 # ── Platform B: Hermes (Mumuni) ──
-MUMUNI_STATE=$(ssh -o StrictHostKeyChecking=no -o ConnectTimeout=5 root@192.168.68.24 \
+MUMUNI_STATE=$(ssh -o StrictHostKeyChecking=no -o ConnectTimeout=5 root@192.168.68.123 \
   "cat ~/.hermes/gateway_state.json 2>/dev/null" 2>/dev/null || echo "{}")
 MUMUNI_ZULIP=$(echo "$MUMUNI_STATE" | python3 -c "
 import sys,json

zulip-health.prose.md

@@ -6,8 +6,6 @@ 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