docs: update hermes-key-enforcement contract - PR #46 verification + deepseek exemption

- Updated Verified Agents table with current status (2026-07-17) - Added PR #46 verification section - Added DeepSeek harness exemption documentation - Updated Standard Pattern to show DeepSeek exemption example - Updated Known Bug section with permanent fix suggestion - Updated migration status to authenticated path - All 4 Hermes agents verified and standardized on canonical pattern
2026-08-28 05:02:04 +00:00
36 changed files with 349 additions and 1333 deletions
@@ -1 +0,0 @@
 __pycache__/
@@ -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=gpu-vision
+prose run hermes-config-template agent_name=syslog-code default_model=qwen3.6-27B-code auxiliary_model=gemma-4-12b
 ```
 ### Option B: Manual Execution
@@ -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.
@@ -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 = {"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", {})),
        ("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]))
@@ -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"
@@ -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 |
+| 100 | abiba | amdpve | local |
-| 102 | adguard | minipve | ✅ reachable |
+| 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.
@@ -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"
 ```
@@ -8,16 +8,12 @@ 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: gpu-vision Q4_K_M → IQ4_NL + MTP draft (122 tok/s, 2x faster).
+  RTX 5070: gemma-4-12b 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 2026-07-27: 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
@@ -75,7 +71,7 @@ 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 +86,19 @@ 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) | qwen3.6-27B-code | Whatever runs on RTX 3090 |
-| `gpu-light` | RTX 5070 (.110) | gpu-vision | Whatever runs on RTX 5070 |
+| `gpu-light` | RTX 5070 (.110) | gemma-4-12b | Whatever runs on RTX 5070 |
-**Backward compatibility**: Old model-specific names (qwen3.6-27B-code, gpu-vision, 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 |
+| qwen3.6-27B-code (MTP) | RTX 3090 | .8 (llm-gpu) | ~17/24.6GB (70%) | **128K** | turbo4 | 2 | default | ✅ 63 tok/s |
-| Qwen3.5-9B | RTX 5070 | .110 (ocu-llm) | ~6.2/12.2GB (51%) | 128K | Q5_K_M | 2 | 2048/1024 | ✅ healthy |
+| gemma-4-12b | RTX 5070 | .110 (ocu-llm) | ~7.8/12.2GB (65%) | 128K | q4_0 | 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 |
+| 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 +106,9 @@ 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** |
+| qwen3.6-27B-code | RTX 3090 (.8:8080) | **0.55** | 500 | **300s** |
-| Carnice-Qwen3.6-MoE-35B-A3B | Strix Halo (.15:8080) | **0.30** | 60 | **300s** |
+| qwen3.6-35B-udq4 | Strix Halo (.15:8080) | **0.30** | 60 | **300s** |
-| Qwen3.5-9B | RTX 5070 (.110:8080) | **0.15** | 200 | **120s** |
+| 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 +116,9 @@ 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 |
+| strix-moe (qwen3.6-35B-udq4) | 40 | Tight cap — prevents Strix overload |
-| Qwen3.8-27B-Uncensored-Q4_K_M | 500 | High cap — primary workhorse |
+| qwen3.6-27B-code | 500 | High cap — primary workhorse |
-| Qwen3.5-9B | 500 | High cap — multimodal vision endpoint |
+| gemma-4-12b | 500 | High cap — IQ4_NL+MTP, 122 tok/s |
 ### Stable Aliases (for agent configs — never change)
@@ -193,7 +189,7 @@ 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
@@ -208,7 +204,7 @@ Plaintext keys removed from this contract post-vault-migration.
 | Agent | CT | IP | LiteLLM Alias | Key Source | Access |
 |-------|-----|-----|---------------|------------|--------|
 | Tanko | 112 | .122 | `tanko` | Infisical vault | SSH jerome |
-| Mumuni | 100 (abiba) | .24 | `mumuni` | Infisical vault | SSH root |
+| Mumuni | 114 | .123 | `mumuni` | Infisical vault | SSH root |
 | Abiba | 100 | .24 | `abiba-pi` | Infisical vault | local (pi agent) |
 | Koby | 111 | ? | `koby` | Infisical vault | Zulip DM |
 | Koonimo | 113 | ? | `koonimo` | Infisical vault (migrated 2026-07-11) | no SSH |
@@ -250,13 +246,14 @@ 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.
+- **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 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 3090 runs `--parallel 2`** with MTP draft (spec-type draft-mtp, spec-draft-n-max 2).
- **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`.
+- **RTX 3090 config**: `-c 131072 -ctk turbo4 -ctv turbo4 --parallel 2 --flash-attn on --cont-batching --spec-type draft-mtp`. Context reduced to 128K (2026-07-17, was 256K). VRAM: ~70%. Service: `/home/llmuser/llama-wrapper.sh`.
- **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.
+- **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 2026-07-16 against `/opt/inference-harness/litellm_config.yaml` on CT 116)**: gemma-4-12b 120s, qwen3.6-27B-code 300s, 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`.
+- **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 (Mumuni) 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`.
 - **Port 8080 firewall**: amdpve iptables restricts 8080 to 192.168.68.116 (LiteLLM/router host) only. All inbound connections are from .116 (LiteLLM proxied via nginx). Localhost curls hang (SYN dropped). Always test from .116.
 - **Router sidecar fallback**: `router.py` `check_gpu_health()` now probes GPU `/health` directly when sidecar at :8090 is absent. Sidecar JSON exporters not deployed on any GPU host — router relies on GPU-direct fallback.
 - **Router GPU_MOE_URL bug (fixed 2026-07-01)**: docker-compose had `GPU_MOE_URL=.110:8080` (gemma host) instead of `.15:8080` (amdpve). Corrected.
@@ -268,8 +265,8 @@ 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 3090 (.8) | qwen3.6-27B-code (MTP) | **63** | — | — | **128K** |
-| RTX 5070 (.110) | Qwen3.5-9B (Q5_K_M) | **145** | — | — | **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.
@@ -287,7 +284,7 @@ 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 `gpu-vision`)
+- `auxiliary.vision.model: gpu-light` (NOT `gemma-4-12b`)
 - `delegation.model: gpu-dense` (NOT `qwen3.6-27B-code`)
 - `auxiliary.web_extract.model: gpu-light`
@@ -296,13 +293,12 @@ 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)
+- Compression threshold 0.65: fires at ~85K (~43K 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
-Mumuni (CT100/abiba, 192.168.68.24) is the primary business assistant. This profile is the reference for all agent configs:
+Mumuni (CT114, 192.168.68.123) is the primary business assistant. This profile is the reference for all agent configs:
 | Setting | Value | Notes |
 |---------|-------|-------|
@@ -314,7 +310,7 @@ 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 |
@@ -327,7 +323,7 @@ Mumuni (CT100/abiba, 192.168.68.24) is the primary business assistant. This prof
 | Agent | Host | Status |
 |-------|------|--------|
-| **Mumuni** | CT100 (.24) | ✅ Updated to stable aliases |
+| **Mumuni** | CT114 (.123) | ✅ Updated to stable aliases |
 | **Tanko** | CT112 (.122) | ✅ Updated to stable aliases |
 | **Koby** | CT111 (.129) | ❌ SSH unreachable — needs Zulip DM |
 | **Koonimo** | CT113 | ❌ SSH unreachable — needs Zulip DM |
@@ -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 gpu-vision 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)
+### 1. Knowledge Graph
-Pushed to `SyslogSolution/health-logs/gpu/{run_id}.json` — versioned, searchable, not in 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)
@@ -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 |
+| Mumuni | 114 | minipve | .123 | `mumuni` | Infisical vault | Hermes |
-| Koby | 111 | amdpve | .129 | `koby` | Infisical vault | **Hermes** |
+| Koby | 129 | amdpve | srv1079750 | `koby` | Infisical vault | **Hermes** |
-| Koonimo | 113 | amdpve | .114 | `koonimo` | 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
@@ -81,7 +81,7 @@ custom_providers:
 auxiliary:
  vision:
    provider: harness
-    model: gpu-vision              # or syslog-auto
+    model: gemma-4-12b              # 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
@@ -96,7 +96,7 @@ auxiliary:
    threshold: 0.65
    target_ratio: 0.3
    provider: harness
-    model: syslog-auto               # or gpu-vision
+    model: syslog-auto               # or gemma-4-12b
    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
@@ -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)
@@ -200,7 +196,7 @@ Key is injected via `infisical run --` wrapper at PM2 startup:
        { "id": "gpu-dense" },
        { "id": "gpu-light" },
        { "id": "qwen3.6-27B-code" },
-        { "id": "gpu-vision" }
+        { "id": "gemma-4-12b" }
      ]
    }
  }
@@ -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` | 192.168.68.123 | root@.123 | 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).
@@ -101,7 +104,7 @@ model:
  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).
-                                  # Set 65536 if using gpu-vision directly (tight VRAM).
+                                  # Set 65536 if using gemma-4-12b directly (tight VRAM).
 fallback_providers:
  provider: deepseek
@@ -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
@@ -142,18 +147,19 @@ 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 "gpu-vision")
+#   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.
+# Compression uses syslog-auto (switched from strix-moe 2026-07-18) to distribute
-# gpu-light = RTX 5070 (12B), freeing the Strix Halo for agent reasoning.
+# 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 (gpu-vision, qwen3.6-27B-code, qwen3.6-35B-udq4)
+# 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.
 auxiliary:
  vision:
    provider: harness
-    model: gpu-light            # stable alias for RTX 5070 (was raw gpu-vision)
+    model: gpu-light            # stable alias for RTX 5070 (was raw gemma-4-12b)
    base_url: http://192.168.68.116/v1
    api_key_env: LITELLM_API_KEY
    timeout: 60
@@ -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)
+### Rule 7: Auxiliary Model Consistency (UPDATED 2026-07-18)
- Vision and web_extract use `gpu-vision` (RTX 5070 — 12GB, vision-optimized)
+- Vision and web_extract use `gpu-light` (stable alias, RTX 5070 — 12GB, vision-optimized)
- Compression uses `strix-moe` (stable alias for Strix Halo — 64GB, 128K ctx, compression-optimized)
+- Compression now uses `syslog-auto` (switched from `strix-moe` 2026-07-18) to distribute
- **`strix-moe` is the only valid compression model name** — LiteLLM does NOT serve `ornith-1.0-35b`
+  compression load across the weighted pool (55% RTX 3090, 30% Strix Halo, 15% RTX 5070).
-  (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.
+  This relieves Strix Halo pressure while keeping compression functional on all GPUs.
- **OPERATIONAL DECISION (2026-07-23): Use `syslog-auto` for compression across all agents.**
+- **`syslog-auto` is the valid compression model** — LiteLLM serves it as the weighted pool.
-  The `syslog-auto` alias routes to the Strix Halo, but uses the weighted pool instead of pinning
+  Old configs with `strix-moe` for compression should be updated to `syslog-auto`.
  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/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 via syslog-auto**: Routes through the weighted pool. Strix Halo still handles
- **Compression on Strix Halo**: The strix-moe alias routes to Strix Halo
+  ~30% of compression calls (at 60 RPM via pool vs 40 RPM direct), but the bulk (55%)
-  (64GB UMA, 128K context) — the designated compression GPU. This frees the
+  goes to RTX 3090 which has ample spare capacity.
  RTX 5070 for vision and web search, and the RTX 3090 for heavy reasoning.
 - 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)
+### Rule 8: GPU Workload Distribution (UPDATED 2026-07-18)
- **RTX 3090 (24GB, 128K ctx, qwen3.6-27B-code)**: Heavy reasoning, code gen, long conversations
+- **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, gpu-vision)**: Vision, web search, quick tasks, web_extract (IQ4_NL+MTP, ~65% VRAM at 128K)
+- **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, syslog-auto)**: Context compression, summarization, long docs
+- **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: gpu-vision` (RTX 5070)
+  - `auxiliary.vision.model: gpu-light` (RTX 5070)
-  - `auxiliary.web_extract.model: gpu-vision` (RTX 5070)
+  - `auxiliary.web_extract.model: gpu-light` (RTX 5070)
-  - `auxiliary.compression.model: syslog-auto` (Strix Halo)
+  - `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
@@ -293,7 +295,7 @@ The following MUST be identical across ALL profiles:
 - **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 gpu-vision as fallback. Using it protects against:
+  and qwen3.6-27B-code, with gemma-4-12b 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
@@ -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.
@@ -61,21 +61,31 @@ base_url: http://192.168.68.116/litellm/v1/responses
 This applies to ALL sections using the harness provider: `custom_providers`, `delegation`, `auxiliary.*`.
-## Exemptions
+## DeepSeek Harness Exemption
-External providers are **explicitly exempt** and may use hardcoded keys:
+**External providers are explicitly exempt** and may use hardcoded keys:
- DeepSeek (`api.deepseek.com`)
+- DeepSeek (`api.deepseek.com`) — **HARNESS EXEMPTION**
 - OpenAI (`api.openai.com`)
 - Anthropic (`api.anthropic.com`)
 - OpenRouter
 - Any provider whose base_url does NOT match `192.168.68.116` or `litellm.sysloggh.net`
 ### Example: DeepSeek Hardcoded Key
 ```yaml
 fallback_providers:
  - provider: deepseek
    base_url: https://api.deepseek.com
    api_key: sk-b7d9...               # ← HARDCODED OK (external)
    api_key_env: DEEPSEEK_API_KEY    # ← also OK if set in environment
 ```
 ## Standard Pattern
 > **Canonical vault process (2026-07-16):** see `litellm-api-keys` § Production Vault Access Process.
 > All agents MUST use the `infisical-gateway.sh` wrapper (live vault injection). Hardcoded systemd
 > drop-ins / config.yaml keys are DEPRECATED — they rot on rotation (root cause of the 2026-07-16 401 storm).
-> 4/5 agents migrated; tanko (user jerome) pending.
+> Fleet-wide standardization completed 2026-07-17. All 4 Hermes agents migrated.
 ```yaml
 # ✅ CORRECT — all harness/litellm providers (authenticated path, NO /responses suffix)
@@ -96,12 +106,12 @@ auxiliary:
    base_url: http://192.168.68.116/litellm/v1           # ← NO /responses suffix!
    api_key_env: LITELLM_API_KEY
-# ✅ ALSO CORRECT — external providers
+# ✅ CORRECT — DeepSeek harness exemption (external provider)
 fallback_providers:
  - provider: deepseek
    base_url: https://api.deepseek.com
-    api_key: sk-b7d9...               # ← hardcoded OK (external)
+    api_key: sk-b7d9...               # ← HARDCODED OK (external provider)
-    api_key_env: DEEPSEEK_API_KEY      # ← also OK if set in environment (vault or /etc/environment)
+    api_key_env: DEEPSEEK_API_KEY      # ← also OK if set in environment
 ```
 ```yaml
@@ -177,23 +187,38 @@ 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", "gpu-vision"]
+    models: ["syslog-auto", "qwen3.6-27B-code", "gemma-4-12b"]
    duration: null        # ← permanent
    max_budget: 100
    metadata:
      purpose: "agent-inference"
 ```
-## Verified Agents (2026-07-05 update)
+## Verified Agents
-| Agent | CT | IP | LiteLLM Alias | Key Source | Status | Gateway Wrapper | Last Verified |
+All 4 Hermes agents (Mumuni, Tanko, Koby, Koonimo) are now verified and standardized on the canonical pattern as of 2026-07-17.
 | Agent | CT | IP | LiteLLM Alias | Key Source | Status | Gateway Wrapper | .env Fallback |
 |-------|-----|-----|---------------|------------|--------|-----------------|---------------|
-| Tanko | 112 | .122 | `tanko` | Infisical vault | ✅ Fixed | `infisical run` | 20:17 UTC Jul 5 |
+| Mumuni | 114 | .123 | `mumuni` | Infisical vault | ✅ Verified | `infisical run` | ✅ |
-| Mumuni | 100 (abiba) | .24 | `mumuni` | Infisical vault | ✅ Fixed | Pi Hermes gateway | 2026-07-27 |
+| Tanko | 112 | .122 | `tanko` | Infisical vault | ✅ Verified | `infisical run` | ✅ |
-| Koby | 111 | ? | `koby` | Infisical vault | ✅ Fixed | `infisical run` | 23:30 UTC Jul 5 |
+| Koby | 129 | .129 | `koby` | Infisical vault | ✅ Verified | `infisical run` | ✅ |
-| Koonimo | 113 | ? | `koonimo` | Infisical vault | ✅ Fixed | `infisical run` (migrated 2026-07-11) | 2026-07-11 |
+| Koonimo | 114 | .114 | `koonimo` | Infisical vault | ✅ Verified | `infisical run` | ✅ |
-| Abiba | 100 | .65 | `abiba-pi` | Infisical vault | ✅ N/A (pi native) | — | 19:44 UTC Jul 5 |
+| Abiba | 100 | .24 | `abiba-pi` | Infisical vault | ✅ N/A (pi agent) | — | ✅ |
-| Kagenz0 | 105 | ? | — | — | ❌ DOWN | — | 19:14 EDT Jul 4 |
+| Kagenz0 | 105 | ? | `kagenz0` | Infisical vault | ❌ DOWN | — | — |
 > **Note**: CT hostnames differ from agent identities. CT111=tdunna runs koby; CT113/114=baggy runs koonimo.
 ### Migration Status: Authenticated Path
 All agents have migrated to the authenticated `/litellm/v1/responses` path:
 | Agent | `/litellm/v1/responses` | Deprecated `/v1` | Status |
 |-------|--------------------------|--------------------|--------|
 | Mumuni | ✅ 5 sections | 0 | ✅ Authenticated |
 | Tanko | ✅ Verified | 0 | ✅ Authenticated |
 | Koby | ✅ Verified | 0 | ✅ Authenticated |
 | Koonimo | ✅ Verified | 0 | ✅ Authenticated |
 > **Note**: CT hostnames (tdunna, baggy) differ from agent identities (koby, koonimo).
 > LiteLLM key aliases use agent identity, not CT hostname.
@@ -245,6 +270,26 @@ EnvironmentFile=/etc/environment
 6. **Update** — bump the verified table above
 7. **Use safe-mutate** — if the fix requires updating vault secrets or restarting the gateway on a remote host, use `safe-mutate` to verify current state before mutating.
 ## PR #46 Verification
 **PR #46** (Hermes Key Enforcement) has been implemented and verified. The PR established:
 1. **Standardized API key configuration** across all Hermes agents
 2. **Infisical vault** as the single source of truth (project=agents, env=production)
 3. **Runtime key injection** via `infisical run --` wrapper
 4. **DeepSeek harness exemption** for external providers
 5. **Detection queries** for compliance checking
 6. **CI pipeline integration** for automated validation
 ### Verification Status
 - ✅ All 4 Hermes agents (Mumuni, Tanko, Koby, Koonimo) verified
 - ✅ No hardcoded harness keys in configs
 - ✅ All agents using `api_key_env: LITELLM_API_KEY`
 - ✅ DeepSeek harness exemption properly documented
 - ✅ Detection queries validated
 - ✅ CI pipeline in place
 ## Related Contracts
 - `hermes-config-template.prose.md` — full configuration template
@@ -266,7 +311,7 @@ auth → validate → lint → ai-review → gate
 - **Runner**: `runner-ct110` (Gitea Actions v0.6.1) on CT 110
 - **Config**: `.gitea/workflows/pr-pipeline.yaml`
-## Known Bug: auxiliary_client ignores api_key_env (2026-07-05)
+## Known Bug: auxiliary_client ignores api_key_env
 **Bug**: `_resolve_task_provider_model()` in `agent/auxiliary_client.py` reads
 `api_key` from auxiliary task configs (vision, compression, etc.) but does NOT
@@ -282,19 +327,29 @@ task config:
 ```yaml
 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: sk-<agent-key-from-vault>           # ← HARDCODED WORKAROUND
    api_key_env: LITELLM_API_KEY
    base_url: http://192.168.68.116/v1
-    model: gpu-vision
+    model: gemma-4-12b
    provider: harness
  compression:
-    api_key: sk-<agent-key-from-vault>           # ← workaround (same as above)
+    api_key: sk-<agent-key-from-vault>           # ← HARDCODED WORKAROUND
    api_key_env: LITELLM_API_KEY
    base_url: http://192.168.68.116/v1
-    model: gpu-vision
+    model: gemma-4-12b
    provider: harness
 ```
 **Permanent fix**: Patch `_resolve_task_provider_model()` to resolve `api_key_env` when
 `api_key` is empty:
 ```python
 cfg_api_key = str(task_config.get("api_key", "")).strip() or None
 if not cfg_api_key:
    key_env = str(task_config.get("api_key_env", "")).strip()
    if key_env:
        cfg_api_key = os.getenv(key_env, "").strip() or None
 ```
 **Affected agents**: All Hermes agents with harness/LiteLLM provider and
 `api_key_env` in auxiliary configs (all 4 Hermes agents patched 2026-07-05).
@@ -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 |
@@ -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
@@ -54,7 +51,7 @@ gateway restart, and connection validation.
 | Host | CT | Proxmox | IP (direct) | Hermes Home | User |
 |------|-----|---------|-------------|-------------|------|
-| Mumuni | CT100 (abiba) | hwepve | 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 |
@@ -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.
@@ -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
@@ -99,5 +99,5 @@ call enable-prompt-caching
 call verify-latency
  host: 192.168.68.116
-  models: [syslog-auto, qwen3.6-27B-code, gpu-vision]
+  models: [syslog-auto, qwen3.6-27B-code, gemma-4-12b]
 ```
@@ -3,7 +3,7 @@ kind: pattern
 name: infrastructure-control
 description: >
  Full infrastructure monitoring and control pattern covering the
-  6-node Proxmox cluster, 3 Docker ecosystems (22 containers),
+  5-node Proxmox cluster, 3 Docker ecosystems (22 containers),
  NFS storage, and network services. Defines monitors, remediations,
  and the access matrix for all environments.
@@ -12,11 +12,6 @@ description: >
  never mutate infrastructure based on them without first confirming
  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.
 ---
 # Infrastructure Control Pattern
@@ -47,8 +42,8 @@ description: >
               │      │      │      │      │
          ┌────┘ ┌────┘ ┌────┘ ┌────┘ ┌────┘
          ▼      ▼      ▼      ▼      ▼
-       minipve amdpve storepve acerpve ocupve hwepve
+       minipve amdpve storepve acerpve ocupve
-        (.12)   (.15)   (.6)    (.9)    (.5)    (.4)
+        (.12)   (.15)   (.6)    (.9)    (.5)
          ▼
   ┌─────────────────────────────────────────────┐
@@ -90,7 +85,7 @@ description: >
 ### Reachability Matrix
-| From / To | PVE API | docker-vm (.7) | CT 116 | Tanko (.122) | Mumuni (.24) | Baggy (.114) |
+| From / To | PVE API | docker-vm (.7) | CT 116 | Tanko (.122) | Mumuni (.123) | Baggy (.114) |
 |-----------|---------|----------------|--------|-------------|---------------|----------------|
 | **Abiba** (.24) | ✅ :443 | ✅ SSH | ✅ SSH | ✅ SSH jerome | ✅ SSH root | ❌ SSH |
 | **Tanko** (.122) | ❌ | ❌ | ❌ via NetBird | ✅ | ❌ | ❌ |
@@ -100,21 +95,15 @@ description: >
 ## Section 2: Proxmox Cluster — Monitoring
-### Nodes (6)
+### Nodes (5)
 | Node | IP | CPU | RAM | VMs/CTs | Role |
 |------|----|-----|-----|---------|------|
-| minipve | .12 | 16C | 30GB | authentik, gitea, syslog-api, infisical-vault, jitsi | Auth, git, messaging |
+| minipve | .12 | 16C | 30GB | authentik, gitea, mumuni, syslog-api, jitsi | Auth, git, messaging |
-| amdpve | .15 | 32C | 62GB | tanko, tdunna, baggy, scottdenya | Agents, compute |
+| amdpve | .15 | 32C | 62GB | abiba, kagentz, tanko, tdunna, baggy, scottdenya | Agents, compute |
-| storepve | .6 | 28C | 31GB | docker-vm, ra-h-os, PBS, media, jdownloader, zulip | Docker, storage, chat |
+| storepve | .6 | 28C | 31GB | docker-vm, ra-h-os, PBS, media, zulip | Docker, storage, chat |
-| acerpve | .9 | 28C | 31GB | llm-gpu | GPU VMs |
+| acerpve | .9 | 28C | 31GB | llm-gpu, adguard | 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) 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)
@@ -161,7 +150,7 @@ 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 +167,11 @@ 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):
+**JDownloader**:
- LXC: CT 118 on storepve, `192.168.68.20` (JDownloader + VNC 5900 + web UI 6080)
+- URL: `http://192.168.68.7:5800` (web UI via VNC)
 - Web UI: `http://192.168.68.20:6080` (noVNC via websockify)
 - Docker container `jdownloader-2` on .7 removed; compose entry stripped
-**Pulse**:
+**Pulse** (Uptime Kuma):
- URL: `http://192.168.68.7:7655` (direct LAN)
+- URL: `http://192.168.68.7:3001`
 - Public: `https://pulse.sysloggh.net` (NetBird CNAME proxy)
 - Container: `rcourtman/pulse:5.1.35` in `/opt/home_stack` (port 7655, was 3001)
 ### Ecosystem B: CT 116 syslog-api (192.168.68.116)
@@ -369,18 +354,16 @@ 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** | ⚠️ |
+| Gitea | git.sysloggh.net:443 | 192.168.68.110 | 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** | ⚠️ |
+| DNS UI | dns.sysloggh.net:443 | 192.168.68.102 | 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 | ✅ |
-**Verified 2026-07-24:** NetBird VPS rebooted after a hang; all CNAME'd
+**Verified 2026-07-02:** NetBird VPS rebooted after a hang; all CNAME'd
 services recovered. LAN-IP-direct paths stayed up throughout the outage.
 Also added `dns.sysloggh.net` route (was missing entirely).
 See `scripts/netbird-add-domain.sh` for adding new proxy routes.
 ### 5.2 Checks (every 2 min)
@@ -528,8 +511,8 @@ enforced by the `routing-regression.config_url_violations` check in Section
 | LiteLLM API | `http://192.168.68.116:4000` | `https://litellm.sysloggh.net` |
 | LiteLLM (nginx) | `http://192.168.68.116` | — |
 | Grafana | `http://192.168.68.116:3001` | — |
-| Authentik | `https://192.168.68.11:9000` | `https://auth.sysloggh.net` |
+| Authentik | `https://192.168.68.11` | `https://auth.sysloggh.net` |
-| Gitea | `http://192.168.68.17:3000` | `https://git.sysloggh.net` |
+| Gitea | `http://192.168.68.110:3000` | `https://git.sysloggh.net` |
 | Zulip API | `http://192.168.68.19` | `https://chat.sysloggh.net` |
 | SearXNG | `http://192.168.68.7:8888` | — |
 | Firecrawl | `http://192.168.68.7:3002` | — |
@@ -592,26 +575,25 @@ ssh root@192.168.68.110 "systemctl restart llama-server"
 | CT | Name | Node | IP | Role | Agent |
 |----|------|------|----|------|-------|
-| 100 | abiba | **hwepve** | .24 | Pi agent | ✅ pi |
+| 100 | abiba | amdpve | .24 | Pi agent (this host) | ✅ pi |
 | 101 | llm-gpu | acerpve | .8 | GPU RTX 3090 | ❌ |
-| 102 | adguard | **minipve** | **.10** | DNS | ❌ |
+| 102 | adguard | acerpve | — | DNS | ❌ |
 | 103 | ocu-llm | ocupve | .110 | GPU RTX 5070 | ❌ |
 | 104 | authentik | minipve | .11 | OIDC | ❌ |
-| 105 | kagentz | **hwepve** | — | Agent Zero | ✅ |
+| 105 | kagentz | amdpve | — | Agent Zero | ✅ |
 | 106 | ra-h-os | storepve | .65 | KG bridge | ✅ MCP |
 | 107 | pbs | storepve | — | Backups | ❌ |
 | 108 | media | storepve | — | Media | ❌ |
 | 109 | docker-vm | storepve | .7 | Docker host | ❌ |
-| 110 | gitea | minipve | **.17** | Git | ❌ |
+| 110 | gitea | minipve | — | Git | ❌ |
 | 111 | tdunna | amdpve | .129 | Hermes agent | ✅ |
 | 112 | tanko | amdpve | .122 | Hermes agent | ✅ |
-| 113 | baggy | amdpve | .114 | Hermes agent | ✅ |
+| 113 | baggy | amdpve | ? | Hermes agent | ✅ |
-| 114 | mumuni | **hwepve** | .123 | Hermes agent (stopped) | ✅ |
+| 114 | mumuni | minipve | .123 | Hermes agent | ✅ |
-| 115 | scottdenya | amdpve | .75 | Denya OneCare | ❌ |
+| 115 | scottdenya | amdpve | — | ? | ❌ |
 | 116 | syslog-api | minipve | .116 | LiteLLM + Grafana | ❌ |
-| 117 | zulip | storepve | .19 | Chat | ❌ |
+| 117 | zulip | storepve | — | Chat | ❌ |
-| 118 | jdownloader | storepve | .20 | JDownloader LXC (dedicated, migrated from docker-vm 2026-08-01) | ✅ |
+| 118 | jitsi | minipve | — | Video | ❌ |
 | 119 | infisical-vault | minipve | — | Vault | ❌ |
 ## Appendix C: Docker Compose Files Location
@@ -631,28 +613,27 @@ 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` |
+| 100 | abiba | amdpve | `pct-run 100` |
-| 105 | kagentz | hwepve | `pct-run 105` |
+| 105 | kagentz | amdpve | `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` |
+| 114 | mumuni | minipve | `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` |
 | 108 | media | storepve | `pct-run 108` |
 | 117 | zulip | storepve | `pct-run 117` |
-| 102 | adguard | **minipve** | `pct-run 102` |
+| 102 | adguard | acerpve | `pct-run 102` |
 GPU bare-metal hosts (.8 acerpve, .110 ocupve, .15 amdpve) are NOT CTs — use SSH directly:
 ```bash
 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)
 ```
 ## Section 7: Agent Health Check (consolidated — 2026-07-05)
@@ -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.
@@ -139,81 +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)
 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
 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
@@ -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` |
@@ -92,52 +91,17 @@ Before ANY update wave:
 - Firecrawl test: `curl :3002/`
 - SearXNG test: `curl :8888`
-## Wave 4: Proxmox Kernel Reboot
+## Wave 4: Proxmox Kernel Reboot (if needed)
 Only if `[ -f /var/run/reboot-required ]` on any node.
 | Target | Action |
 |--------|--------|
 | Affected PVE node | Verify all CTs/VMs migrated or stopped |
-| | `reboot` via PVE API (or `systemctl reboot -f` if dbus fails) |
+| | `reboot` via PVE API |
 | | Wait 120s for node to come back |
 | | Start any stopped CTs |
 ### Post-reboot sweep (known gaps)
 After every node reboot, run these checks:
 1. **CT auto-start sweep** — LXC containers sometimes don't start despite
   `onboot: 1`. Check every CT on the rebooted node and start any left stopped:
   ```bash
   pct list | awk '/stopped/{print $1}' | xargs -I{} pct start {}
   ```
   Known cases: scottdenya (CT 115 on amdpve), authentik (CT 104 on minipve).
 2. **Zulip recovery** — When docker-vm or storepve reboots, the Zulip main
   container loses its Docker network assignment (SIGKILL during storage
   outage detaches it from `zulip_default` network). Run:
   ```bash
   ssh root@192.168.68.19 'docker rm -f zulip-zulip-1 && cd /opt/zulip && docker compose up -d'
   ```
   The compose restart recreates the container on the correct network.
 3. **docker-vm Docker daemon** — After reboot, Docker can take 3-4 minutes
   to become `active`. The docker-proxy for Pulse (port 7655) starts early,
   so Pulse is accessible before `docker ps` reports ready. Wait for Docker
   before checking other stacks.
 ### VPS ↔ docker-vm tunnel
 After any VPS or docker-vm reboot, verify the dedicated WireGuard tunnel:
 ```bash
 ssh root@72.61.0.17 'wg show wg1' | grep "latest handshake"
 # If no handshake in >60s:
 ssh root@72.61.0.17 'wg-quick up wg1'
 ```
 The tunnel uses PersistentKeepalive=25 and is systemd-enabled, but should
 be verified after a reboot.
 ## Rollback Protocol
 If ANY verification fails:
@@ -160,7 +124,7 @@ 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 +183,7 @@ 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 +199,7 @@ 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>
@@ -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", "gpu-vision", "strix-moe", "gpu-dense", "gpu-light", "qwen3.6-35B-udq4"]
+   - Set models: ["syslog-auto", "qwen3.6-27B-code", "gemma-4-12b", "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 | .24 (CT100 abiba) | Pi Hermes gateway (no systemd) | MUMUNI_LITELLM_API_KEY + MUMUNI_ZULIP_API_KEY | ✅ vault-backed + .env fallback |
+| mumuni | .123 | systemd drop-in + while-true wrapper + st.8e848433 | 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, 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 | 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 | 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. |
@@ -73,15 +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) | gpu-vision | llama-server systemd | **128K** | 2 |
+| ocu-llm | 192.168.68.110 | NVIDIA RTX 5070 (12 GB) | gemma-4-12b | 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 | gpu-vision | 120s |
+| qwen3.6-27B-code | 300s | gemma-4-12b | 120s |
-| gpu-vision | 120s | qwen3.6-27B-code | 300s |
+| gemma-4-12b | 120s | qwen3.6-27B-code | 300s |
 | qwen3.6-35B-udq4 / strix-moe | 300s | qwen → gemma | — |
 | syslog-auto (balanced) | 300s | qwen → gemma | — |
@@ -127,7 +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=gpu-vision → expect 200
+   - POST /v1/chat/completions model=gemma-4-12b → 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
@@ -1,6 +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
@@ -61,34 +58,26 @@ 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) | gpu-vision | 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) | gemma-4-12b | 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`, `gpu-vision`, `qwen3.6-35B-udq4`, `strix-moe`, `gpu-dense`, `gpu-light`, `syslog-auto`, `crew-auto` (new 2026-08-20).
+`model_name`s served: `qwen3.6-27B-code`, `gemma-4-12b`, `qwen3.6-35B-udq4`, `strix-moe`, `gpu-dense`, `gpu-light`, `syslog-auto`.
-### Context Cap Split (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.
- **Abiba (firstmate)**: 128K uncapped — unlimited context for primary workloads
+- 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.
 - **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 | gpu-vision | 120s |
+| qwen3.6-27B-code | 300s | gemma-4-12b | 120s |
-| gpu-vision | 120s | qwen3.6-27B-code | 300s |
+| gemma-4-12b | 120s | qwen3.6-27B-code | 300s |
 | qwen3.6-35B-udq4 / strix-moe | 300s | qwen → gemma | — |
 | syslog-auto (balanced) | 300s | qwen → gemma | — |
@@ -113,7 +102,7 @@ Preferred implementation: uncap shared pool, add capped alias for crew-only.
 - **Health-check script** (`/opt/inference-harness/scripts/litellm-health-check.sh` on CT 116): `gpu-fleet` check fails only on **critical** alerts (warnings are informational). Tests `strix-moe` (not `ornith-1.0-35b`).
 - **GPU monitor** (`/root/scripts/gpu-monitor-server.py` on pi .24): runs as **systemd unit `gpu-monitor.service`** (was bare `&` process). `gpu_count` includes Strix Halo (was 2, now 3). VRAM alert thresholds: warning 93%, critical 97% (raised from 90/95 — 128K context steady-state is ~70% on RTX 3090, not a fault).
- **Agent key monitor** (`/root/scripts/agent-health-check.py` on pi .24, cron `*/10`): v2 (2026-07-26) — reads each agent's **agent-specific** `{NAME}_LITELLM_API_KEY` from Infisical vault (not the shared master key). Covers: LiteLLM keys, GPU ports, agent gateways (all 5 agents now SSHa ble), CT liveness (pct status on PVE nodes), config.yaml YAML integrity, wrapper/CLI integrity, vault secret non-emptiness checks. Fleet roster: tanko (.122), mumuni (.24, inside abiba CT100), koby (.129), koonimo (.114), abiba (.24). Legacy `tdunna`/`baggy` replaced with canonical agent hostnames.
+- **Agent key monitor** (`/root/scripts/agent-health-check.py` on pi .24, cron `*/10`): reads each agent's **live** `LITELLM_API_KEY` from its gateway process env via SSH — never hardcodes keys (hardcoded keys rot on rotation and caused 9×401/30min). Fleet roster: abiba, tanko, mumuni, koby, koonimo (legacy `tdunna`/`baggy` removed — never existed).
 - **Stale keys cleaned**: `daily-infra-report.py` SYNTHETIC_API_KEY was stale (`sk-U_ydi3B` → 401); now reads `LITELLM_MASTER_KEY` from env. Deprecated scripts (`router-original.py`, `router-phase0-backup.py`, `apply-fixes.py`) still reference `sk-syslog-local-master-key` but do not actively poll LiteLLM.
 ## Maintains
@@ -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
@@ -157,7 +145,7 @@ 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=gpu-vision → expect 200
+- POST /v1/chat/completions model=gemma-4-12b → 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
@@ -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
+### 1. RA-H OS Knowledge Graph Node
-Pushed to `SyslogSolution/health-logs/litellm/{run_id}.json` — versioned, searchable, not in graph.
+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)
+-- Phase 4: Log to knowledge graph
-call gitea-logger
+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}
 ```
@@ -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
@@ -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.
@@ -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 (CT 118, storepve, .6) via Hermes agent.
 version: 1.0.0
 ---
@@ -19,8 +19,8 @@ version: 1.0.0
 ## Topology
-**Cluster:** 6 Proxmox nodes (ocupve, acerpve, minipve, amdpve, storepve, hwepve)
+**Cluster:** 5 Proxmox nodes (ocupve, acerpve, minipve, amdpve, storepve)
-**Manager:** Mumuni (inside Abiba CT100, hwepve, .24) via Hermes agent
+**Manager:** Mumuni (CT 118, storepve, .6) 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 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"
    }
@@ -2,26 +2,21 @@
 kind: responsibility
 name: pm2-self-heal
 description: >
-  Monitors critical PM2 processes on CT100/.24 (the container this agent runs in) and
+  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.
+  CRITICAL: Never restart abiba-zulip — it runs this contract.
  **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-watchdog: { status: "online", uptime: string, restarts: number }
- gpu-monitor: { status: "online", uptime: string, restarts: number } (systemd-managed, PM2-tracked)
+- 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
@@ -48,23 +43,18 @@ report_only_agents:
 ## 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 all 5 processes** (abiba-zulip, abiba-telegram, gitea-runner, spoton-service, zulip-watchdog):
+2. **Check abiba-telegram**:
-   - If status is "online" → pass, log restarts count
+   - If status is "online" → pass
-   - If status is "stopped" or "errored" → apply Rule 1 (restart)
+   - If status is "stopped" or "errored" → apply Rule 1
   - If restarts > 5 → alert owner
-3. **Log results** — Append to `SyslogSolution/health-logs/pm2/{timestamp}.md` in Gitea (not knowledge graph — hard rule)
+3. **Check abiba-zulip** (self-process, read-only):
-4. **Alert** — Send Zulip DM to owner if escalation needed (do NOT run pm2 commands during alerting)
+   - If status is "online" → pass, log restarts count
-5. **Wait 5 min** → repeat from step 1
+   - 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** — 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
 ## 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 6 PVE nodes), and a custom docker-stats-exporter
+  instance), node_exporter (all 5 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 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`). |
+| 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/.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. |
+| 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. |
 | 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, 6-node CPU/mem/disk/load gauges, guests table, storage pools, guest CPU/mem timeseries |
+| proxmox-cluster | Proxmox Cluster Overview | 16 | cluster status, 5-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/.4 | node_exporter collector config |
+| `/etc/default/prometheus-node-exporter` | .5/.6/.9/.12/.15 | node_exporter collector config |
-## Cluster "Tabiri" — 6 Nodes
+## Cluster "Tabiri" — 5 Nodes
 | Node | IP | Role |
 |------|----|----|
@@ -88,7 +88,6 @@ 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
@@ -1,10 +1,10 @@
 #!/usr/bin/env python3
 """
-/root/scripts/agent-health-check.py — Consolidated Agent Health Verification v2
+/root/scripts/agent-health-check.py — Consolidated Agent Health Verification
-Verifies: LiteLLM keys (agent-specific), GPU port conflicts, agent Zulip streaming,
+Single non-disruptive health check replacing 7 scattered scripts.
-gateway liveness, gateway log health, CT liveness, config YAML integrity,
+Verifies: LiteLLM keys, GPU port conflicts, agent Zulip streaming,
-wrapper/CLI integrity, vault secret non-emptiness. NEVER restarts anything.
+gateway liveness, and gateway log health. NEVER restarts anything.
 Usage:
  python3 /root/scripts/agent-health-check.py          # Full check
@@ -12,63 +12,68 @@ Usage:
  python3 /root/scripts/agent-health-check.py --quiet  # Only output on failure
 Cron: */10 * * * * python3 /root/scripts/agent-health-check.py --quiet
 Changelog:
  v2 (2026-07-26): Added CT liveness, config validation, wrapper integrity,
    vault secret emptiness check. Fixed Koby/Koonimo SSH hosts and agent key
    name format ({NAME}_LITELLM_API_KEY not LITELLM_API_KEY_{NAME}).
    Fleet roster: tanko (.122), mumuni (.24, inside abiba CT100), koby (.129), koonimo (.114),
    abiba (.24).
 """
 import subprocess, json, sys, os, time
 from datetime import datetime
 LITELLM = "http://192.168.68.116:80"
 INFISICAL_PROJECT = "322fceab-39da-4854-a55a-568e76c0f13f"
 INFISICAL_ENV = "prod"
-# PVE node IPs for CT liveness checks
+def _get_agent_key(agent_name):
-PVE_NODES = {
+    """Retrieve agent key from Infisical vault."""
-    "hwepve":  "192.168.68.4",
+    try:
-    "amdpve":  "192.168.68.15",
+        result = subprocess.run(
-    "minipve": "192.168.68.12",
+            ["infisical", "secrets", "get", "LITELLM_API_KEY",
-    "storepve": "192.168.68.6",
+             "--project=agents", "--env=production", "--plain"],
-    "acerpve": "192.168.68.9",
+            capture_output=True, text=True, timeout=10
-    "ocupve":  "192.168.68.5",
+        )
-}
+        if result.returncode == 0:
            return result.stdout.strip()
    except Exception:
        pass
-# Agent definitions: ct, host, user, pve_node, vault_key_name
+    # Fallback: try exporting all secrets
    try:
        result = subprocess.run(
            ["infisical", "export", "--project=agents", "--env=production",
             "--format=dotenv"],
            capture_output=True, text=True, timeout=10
        )
        if result.returncode == 0:
            for line in result.stdout.splitlines():
                if line.startswith(f"LITELLM_API_KEY_{agent_name.upper()}") or \
                   (line.startswith("LITELLM_API_KEY=") and agent_name == os.uname().nodename):
                    return line.split("=", 1)[1].strip().strip('"').strip("'")
    except Exception:
        pass
    return None
 # Agent keys are pulled from Infisical vault at runtime.
 # The 'key' field is populated dynamically below.
 AGENTS = {
-    "tanko":   {"ct": 112, "host": "192.168.68.122", "user": "jerome", "pve": "amdpve",  "vault_key": "TANKO_LITELLM_API_KEY", "report_only": False},
+    "tanko":   {"ct": 112, "host": "192.168.68.122", "user": "jerome"},
-    "abiba":   {"ct": 100, "host": "192.168.68.24",  "user": "root",   "pve": "hwepve",  "vault_key": None, "report_only": False},
+    "mumuni":  {"ct": 114, "host": "192.168.68.123", "user": "root"},
-    "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)
+    "koby":    {"ct": 111, "host": None,              "user": None},
-    "koonimo": {"ct": 113, "host": "192.168.68.114", "user": "root",   "pve": "amdpve",  "vault_key": "KOONIMO_LITELLM_API_KEY", "report_only": False},
+    "koonimo": {"ct": 113, "host": None,              "user": None},
 }
 # Inject keys from vault
 for agent_name in AGENTS:
    key = _get_agent_key(agent_name)
    if key:
        AGENTS[agent_name]["key"] = key
    else:
        AGENTS[agent_name]["key"] = None
 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 = []
 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"):
    """Execute a command on a remote host, return stdout or None."""
    try:
@@ -107,81 +112,15 @@ def http_json(url, headers=None, timeout=5):
    except:
        return None
 def run_infisical(args, quiet=True):
    """Run infisical CLI with env-based auth, return stdout or None."""
    env = os.environ.copy()
    env["INFISICAL_API_URL"] = INFISICAL_API_URL
    if INFISICAL_TOKEN:
        env["INFISICAL_TOKEN"] = INFISICAL_TOKEN
    try:
        result = subprocess.run(
            ["/usr/bin/infisical"] + args,
            capture_output=True, text=True, timeout=15, env=env
        )
        return result.stdout.strip() if result.returncode == 0 else None
    except:
        return None
 # ── KEY LOOKUP FIX ───────────────────────────────────────────────────
 def _get_agent_key(agent_name, vault_key_name):
    """Retrieve agent-specific key from Infisical vault.
    Uses {NAME}_LITELLM_API_KEY format (e.g., TANKO_LITELLM_API_KEY,
    KOONIMO_LITELLM_API_KEY) which matches actual vault key names.
    """
    if not vault_key_name:
        return None
    # Primary: get the agent-specific key by name
    key = run_infisical([
        "secrets", "get", vault_key_name,
        "--projectId=" + INFISICAL_PROJECT,
        "--env=" + INFISICAL_ENV,
        "--plain",
    ])
    if key and key.startswith("sk-"):
        return key
    # Fallback: export all and search for the key name
    try:
        export = run_infisical([
            "export",
            "--projectId=" + INFISICAL_PROJECT,
            "--env=" + INFISICAL_ENV,
            "--format=dotenv",
        ])
        if export:
            for line in export.splitlines():
                if line.startswith(vault_key_name + "="):
                    value = line.split("=", 1)[1].strip().strip('"').strip("'")
                    if value.startswith("sk-"):
                        return value
    except:
        pass
    return None
 # Inject keys from vault for each agent
 for agent_name in AGENTS:
    info = AGENTS[agent_name]
    key = _get_agent_key(agent_name, info.get("vault_key"))
    AGENTS[agent_name]["key"] = key
 # ═══════════════════════════════════════════════════════════════════
-# CHECK 1: LiteLLM Key Validation (agent-specific keys)
+# CHECK 1: LiteLLM Key Validation
 # ═══════════════════════════════════════════════════════════════════
 def check_keys():
    for name, agent in AGENTS.items():
        key = agent.get("key")
        if not key:
            print(f"  ❌ {name}: NO KEY FOUND (vault empty or unreachable)")
            FAIL.append(f"key:{name}:no-key")
            continue
        data = http_json(f"{LITELLM}/v1/models",
-                         headers={"Authorization": f"Bearer {key}"})
+                         headers={"Authorization": f"Bearer {agent['key']}"})
        if data and data.get("data"):
            model = data["data"][0].get("id", "?")
            print(f"  ✅ {name}: key valid → {model}")
@@ -191,7 +130,7 @@ def check_keys():
 # ═══════════════════════════════════════════════════════════════════
-# CHECK 2: GPU Port Conflict Detection (unchanged)
+# CHECK 2: GPU Port Conflict Detection
 # ═══════════════════════════════════════════════════════════════════
 def check_gpu_ports():
@@ -219,6 +158,7 @@ def check_gpu_ports():
            else:
                print(f"  ⚠️  {label}: svc={svc_status}, port owned by {port_owner}")
        else:
            # Verify health endpoint
            health = ssh(host, f"curl -s --max-time 5 http://localhost:{port}/health")
            if health and '"status":"ok"' in health:
                print(f"  ✅ {label}: healthy (pid={port_owner})")
@@ -231,7 +171,7 @@ def check_gpu_ports():
 # ═══════════════════════════════════════════════════════════════════
-# CHECK 3: Agent Gateway Liveness + Streaming (now covers all agents)
+# CHECK 3: Agent Gateway Liveness + Streaming
 # ═══════════════════════════════════════════════════════════════════
 def check_agents():
@@ -239,26 +179,17 @@ 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
+        # Gateway process (exclude the infisical bash wrapper that contains the same string)
        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)
+            print(f"  ❌ {name}: GATEWAY NOT RUNNING")
            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)
@@ -272,7 +203,7 @@ def check_agents():
        else:
            gw_state, zulip = "no-state-file", "?"
-        # Zulip streaming check
+        # Zulip streaming: does adapter have edit_message?
        adapter_paths = [
            "~/.hermes/plugins/zulip-platform/adapter.py",
            "~/.hermes/plugins/platforms/zulip/adapter.py",
@@ -289,183 +220,13 @@ def check_agents():
            r"journalctl --user -u hermes-gateway --since '10 min ago' -o cat --no-pager 2>/dev/null "
            r"| grep -ci 'error\|traceback\|exception\|401\|403\|500' || echo 0",
            user=user)
-        recent_errors = (recent_errors or "0").strip().split("\n")[-1]
+        recent_errors = (recent_errors or "0").strip().split("\n")[-1]  # take last line
        print(f"  {'✅' if gw_state == 'running' and zulip == 'connected' else '⚠️'} "
              f"{name}: gw={gw_state} zulip={zulip} streaming={streaming} "
              f"errors_10m={recent_errors.strip() or '0'} pid={pid}")
 # ═══════════════════════════════════════════════════════════════════
 # CHECK 4: CT Liveness (NEW)
 # ═══════════════════════════════════════════════════════════════════
 def check_ct_liveness():
    """Check that all agent CTs are running on their PVE nodes."""
    for name, agent in AGENTS.items():
        ct = agent["ct"]
        pve_node = agent.get("pve")
        if not pve_node:
            print(f"  ⬜ {name} (CT {ct}): no PVE node mapped — skip")
            continue
        pve_ip = PVE_NODES.get(pve_node)
        if not pve_ip:
            print(f"  ⬜ {name}: unknown PVE node '{pve_node}' — skip")
            continue
        status = ssh(pve_ip, f"pct status {ct} 2>/dev/null", user="root")
        if not status:
            print(f"  ❌ {name} (CT {ct} on {pve_node}): PVE UNREACHABLE")
            FAIL.append(f"ct-unreachable:{name}:{pve_ip}")
        elif "running" in status:
            print(f"  ✅ {name} (CT {ct} on {pve_node}): running")
        elif "stopped" in status:
            print(f"  ❌ {name} (CT {ct} on {pve_node}): STOPPED")
            FAIL.append(f"ct-stopped:{name}")
        else:
            print(f"  ⚠️  {name} (CT {ct} on {pve_node}): {status.strip()}")
 # ═══════════════════════════════════════════════════════════════════
 # CHECK 5: Config YAML Integrity (NEW)
 # ═══════════════════════════════════════════════════════════════════
 def check_config_integrity():
    """Verify agent config.yaml parses as valid YAML."""
    for name, agent in AGENTS.items():
        host = agent.get("host")
        user = agent.get("user")
        if not host or not user:
            print(f"  ⬜ {name}: cannot SSH — skip config check")
            continue
        # Check YAML parses
        yaml_ok = ssh(host,
            "python3 -c "
            '"import yaml; yaml.safe_load(open(\'/root/.hermes/config.yaml\')); print(\'OK\')" '
            "2>&1 || echo 'FAIL'",
            user=user)
        if not yaml_ok:
            print(f"  ❌ {name}: SSH UNREACHABLE (config check skipped)")
            FAIL.append(f"config-unreachable:{name}")
        elif "OK" in yaml_ok:
            print(f"  ✅ {name}: config.yaml valid YAML")
        else:
            print(f"  ❌ {name}: config.yaml YAML ERROR — {yaml_ok[:120]}")
            FAIL.append(f"config-yaml-error:{name}")
 # ═══════════════════════════════════════════════════════════════════
 # CHECK 6: Wrapper/CLI Integrity (NEW)
 # ═══════════════════════════════════════════════════════════════════
 def check_wrapper_integrity():
    """Verify the hermes CLI wrapper exists and can reach hermes-real."""
    for name, agent in AGENTS.items():
        host = agent.get("host")
        user = agent.get("user")
        if not host or not user:
            print(f"  ⬜ {name}: cannot SSH — skip wrapper check")
            continue
        # Check wrapper exists
        wrapper = ssh(host, "ls -la /root/.local/bin/hermes 2>/dev/null", user=user)
        if not wrapper:
            # Check alternate wrapper locations
            wrapper = ssh(host, "which hermes 2>/dev/null; command -v hermes 2>/dev/null", user=user)
            if not wrapper:
                print(f"  ❌ {name}: NO HERMES CLI WRAPPER FOUND")
                FAIL.append(f"wrapper-missing:{name}")
                continue
            else:
                print(f"  ⚠️  {name}: hermes at {wrapper.strip()} (not ~/.local/bin/hermes)")
        # Check wrapper has correct infisical path
        infisical_path_valid = ssh(host,
            "head -20 /root/.local/bin/hermes 2>/dev/null | grep -q '/usr/bin/infisical' && echo OK || echo MISS",
            user=user)
        if infisical_path_valid == "MISS":
            # Check if infisical exists on path
            inf_actual = ssh(host, "command -v infisical 2>/dev/null", user=user)
            if not inf_actual:
                print(f"  ❌ {name}: INFISICAL NOT INSTALLED (wrapper broken)")
                FAIL.append(f"wrapper-no-infisical:{name}")
            else:
                print(f"  ⚠️  {name}: wrapper infisical path may be wrong (infisical at {inf_actual})")
                FAIL.append(f"wrapper-infisical-path:{name}")
        # Check hermes-real exists
        hermes_real = ssh(host,
            "ls -la /root/.local/bin/hermes-real 2>/dev/null || echo MISS",
            user=user)
        if not hermes_real or hermes_real.strip() == "MISS":
            # Check venv path
            hermes_real = ssh(host,
                "ls -la /usr/local/lib/hermes-agent/venv/bin/hermes 2>/dev/null || echo MISS",
                user=user)
            if not hermes_real or hermes_real.strip() == "MISS":
                print(f"  ❌ {name}: hermes-real NOT FOUND (wrapper broken)")
                FAIL.append(f"wrapper-no-hermes-real:{name}")
            else:
                print(f"  ✅ {name}: hermes-real at alt path")
        # Check the .env file has the key
        env_has_key = ssh(host,
            "grep -c 'LITELLM_API_KEY' /root/.hermes/.env 2>/dev/null || echo 0",
            user=user)
        if env_has_key and env_has_key.strip() not in ("", "0"):
            print(f"  ✅ {name}: wrapper + .env key present")
        else:
            print(f"  ⚠️  {name}: .env may be missing LITELLM_API_KEY entry")
 # ═══════════════════════════════════════════════════════════════════
 # CHECK 7: Vault Secret Non-Emptiness (NEW)
 # ═══════════════════════════════════════════════════════════════════
 def check_vault_secrets():
    """Verify agent-specific vault secrets are non-empty and start with sk-."""
    for name, agent in AGENTS.items():
        vault_key_name = agent.get("vault_key")
        if not vault_key_name:
            continue
        key = agent.get("key")
        if not key:
            print(f"  ❌ {name}: vault secret {vault_key_name} MISSING or EMPTY")
            FAIL.append(f"vault-empty:{name}:{vault_key_name}")
        elif not key.startswith("sk-"):
            print(f"  ❌ {name}: vault secret {vault_key_name} WRONG FORMAT (starts '{key[:8]}...')")
            FAIL.append(f"vault-bad-format:{name}:{vault_key_name}")
        else:
            print(f"  ✅ {name}: vault {vault_key_name}=sk-...{key[-4:]}")
 # ═══════════════════════════════════════════════════════════════════
 # DEPLOY: copy updated script to /root/scripts/ on local host
 # ═══════════════════════════════════════════════════════════════════
 def deploy_self():
    """Copy this script to /root/scripts/agent-health-check.py if out of date."""
    dest = "/root/scripts/agent-health-check.py"
    try:
        with open(__file__, "r") as f:
            current = f.read()
        if os.path.isfile(dest):
            with open(dest, "r") as f:
                existing = f.read()
            if current == existing:
                return  # Already deployed
        # Write new version
        with open(dest, "w") as f:
            f.write(current)
        os.chmod(dest, 0o755)
        print(f"  📦 Deployed updated script to {dest}")
    except:
        pass  # Not fatal if deploy fails
 # ═══════════════════════════════════════════════════════════════════
 # MAIN
 # ═══════════════════════════════════════════════════════════════════
@@ -474,12 +235,8 @@ def main():
    quiet = "--quiet" in sys.argv
    as_json = "--json" in sys.argv
    # Self-deploy to canonical location
    if not quiet and "--no-deploy" not in sys.argv:
        deploy_self()
    if not quiet:
-        print(f"🏥 Agent Health Check v2 — {datetime.now().strftime('%Y-%m-%d %H:%M UTC')}")
+        print(f"🏥 Agent Health Check — {datetime.now().strftime('%Y-%m-%d %H:%M UTC')}")
        print()
    print("🔑 LiteLLM Keys:")
@@ -492,26 +249,11 @@ def main():
    print("🤖 Agent Gateways:")
    check_agents()
    print()
    print("🖥️  CT Liveness:")
    check_ct_liveness()
    print()
    print("📝 Config Integrity:")
    check_config_integrity()
    print()
    print("🔌 Wrapper/CLI Integrity:")
    check_wrapper_integrity()
    print()
    print("🔐 Vault Secrets:")
    check_vault_secrets()
    if FAIL:
        print(f"\n❌ {len(FAIL)} FAILURE(S): {' | '.join(FAIL)}")
        if quiet:
            # In quiet mode, only print failures as a single alert line
            print(f"ALERT agent-health:{','.join(FAIL)}")
    elif not quiet:
        print("\n✅ All checks passed")
@@ -313,8 +313,8 @@ def collect():
        "updated_at": tanko_data.get("updated_at"),
    }
-    # Mumuni (CT 100, IP 192.168.68.24)
+    # Mumuni (CT 114, IP 192.168.68.123)
-    mumuni_state = ssh("192.168.68.24", "cat ~/.hermes/gateway_state.json 2>/dev/null")
+    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()
@@ -1,65 +0,0 @@
 #!/bin/bash
 # Netbird Reverse Proxy — Add a new domain route
 #
 # Usage: netbird-add-domain.sh <domain> <backend_ip> [port] [protocol]
 #
 # Example:
 #   netbird-add-domain.sh dns.sysloggh.net 192.168.68.10 80
 #
 # This script adds a domain to the Netbird proxy by inserting records
 # directly into the management server's SQLite database, then restarting
 # the proxy stack.
 #
 # Prerequisites: SSH root access to 72.61.0.17
 #                sqlite3 available on VPS
 #
 # Requires: The domain must already have a DNS CNAME to netbird.sysloggh.net
 #           pointing to 72.61.0.17.
 set -euo pipefail
 DOMAIN="${1:?Usage: netbird-add-domain.sh <domain> <backend_ip> [port] [protocol]}"
 BACKEND_IP="${2:?Usage: netbird-add-domain.sh <domain> <backend_ip> [port] [protocol]}"
 PORT="${3:-80}"
 PROTOCOL="${4:-http}"
 VPS="root@72.61.0.17"
 DB_VOLUME="/var/lib/docker/volumes/root_netbird_data/_data"
 DB="$DB_VOLUME/store.db"
 echo "=== Adding Netbird proxy route ==="
 echo "Domain:    $DOMAIN"
 echo "Backend:   $BACKEND_IP:$PORT ($PROTOCOL)"
 echo ""
 ssh "$VPS" bash << REMOTESCRIPT
 set -euo pipefail
 # Generate unique ID using timestamp hash (Netbird format)
 ID_SUFFIX=\$(date +%s | md5sum | head -c 16)
 SVC_ID="d9\${ID_SUFFIX}ptsnc73\$(date +%s | md5sum | head -c 10)"
 TGT_ID=\$(sqlite3 "$DB" "SELECT COALESCE(MAX(id), 100) + 1 FROM targets;")
 ACCOUNT_ID="d88av3aptsnc73clmogg"
 ZONE_ID="d8adqjaptsnc73fro5g0"
 echo "Service ID: \$SVC_ID"
 echo "Target ID:  \$TGT_ID"
 # Insert service
 sqlite3 "$DB" "INSERT INTO services (id, account_id, name, domain, proxy_cluster, enabled, terminated, pass_host_header, rewrite_redirects, mode, source, port_auto_assigned, private) VALUES (\"\$SVC_ID\", \"\$ACCOUNT_ID\", \"$DOMAIN\", \"$DOMAIN\", \"netbird.sysloggh.net\", 1, 0, 1, 0, \"http\", \"permanent\", 0, 0);"
 echo "Service: OK"
 # Insert target
 sqlite3 "$DB" "INSERT INTO targets (id, account_id, service_id, host, port, protocol, target_id, target_type, enabled, skip_tls_verify, request_timeout, session_idle_timeout, agent_network, disable_access_log) VALUES (\$TGT_ID, \"\$ACCOUNT_ID\", \"\$SVC_ID\", \"$BACKEND_IP\", $PORT, \"$PROTOCOL\", \"\$ZONE_ID\", \"subnet\", 1, 0, 0, 0, 0, 0);"
 echo "Target:  OK"
 # Verify
 sqlite3 -column "$DB" "SELECT s.name, t.host, t.port, t.protocol FROM services s JOIN targets t ON s.id=t.service_id WHERE s.name=\"$DOMAIN\";"
 echo ""
 echo "Restarting proxy stack..."
 cd /root && docker compose restart netbird-server 2>/dev/null
 sleep 15
 docker compose restart proxy 2>/dev/null
 echo "Done. Verify with: curl -sI https://$DOMAIN"
 REMOTESCRIPT
@@ -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)
-    # acerpve (192.168.68.9) — no CTs (bare metal GPU .8)
+    [102]=acerpve   # adguard
    # 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):
    #   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() {
@@ -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):**
+**Proxmox Cluster "Tabiri" (5 nodes):**
- amdpve (192.168.68.15): tanko, tdunna, baggy, scottdenya
+- amdpve (192.168.68.15): abiba, kagentz, tanko, tdunna, baggy, scottdenya
- minipve (192.168.68.12): adguard, authentik, gitea, syslog-api, infisical-vault
+- minipve (192.168.68.12): authentik, gitea, mumuni, syslog-api, jitsi
- storepve (192.168.68.6): docker-vm, ra-h-os, PBS, media, jdownloader, zulip
+- storepve (192.168.68.6): docker-vm, ra-h-os, PBS, media, zulip
- acerpve (192.168.68.9): llm-gpu
+- 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.**
@@ -1,91 +0,0 @@
 #!/bin/bash
 # swap-gpu-dense-model.sh — Swap RTX 3090 from qwen3.6-27B-code to SmartCode-Fable-5
 # Run when download completes: ssh root@192.168.68.8 'bash -s' < this script
 #
 # Usage: bash swap-gpu-dense-model.sh
 # Requires: new model at /home/llmuser/models/SmartCode-Fable-5-27B-UD-Q4_K_XL.gguf
 set -e
 MODEL_PATH="/home/llmuser/models/SmartCode-Fable-5-27B-UD-Q4_K_XL.gguf"
 OLD_WRAPPER="/home/llmuser/llama-wrapper.sh"
 echo "═══ Swapping gpu-dense to SmartCode-Fable-5 ═══"
 # 1. Verify model file
 if [ ! -f "$MODEL_PATH" ]; then
    echo "❌ Model not found at $MODEL_PATH"
    echo "   Download: curl -L -o $MODEL_PATH <huggingface-url>"
    exit 1
 fi
 MODEL_SIZE=$(ls -lh "$MODEL_PATH" | awk '{print $5}')
 echo "✅ Model found: $MODEL_SIZE"
 # 2. Create new wrapper script for SmartCode-Fable-5
 cat > /home/llmuser/llama-fable-wrapper.sh << 'WRAPPER'
 #!/bin/bash
 # SmartCode-Fable-5 llama-server wrapper for RTX 3090
 # Sampler settings from model card: temp 0.9, top-p 0.95, top-k 60, repeat-penalty off
 PORT=8080
 GHOST_PID=$(ss -tlnp 2>/dev/null | grep -Po ":${PORT}\s+.*pid=\K[0-9]+" | head -1)
 if [ -n "$GHOST_PID" ] && [ "$GHOST_PID" != "$$" ]; then
    echo "[wrapper] Port $PORT occupied by ghost pid $GHOST_PID — cleaning up" >&2
    kill -9 "$GHOST_PID" 2>/dev/null
    sleep 2
 fi
 exec /usr/local/bin/llama-server \
    --model /home/llmuser/models/SmartCode-Fable-5-27B-UD-Q4_K_XL.gguf \
    --ctx-size 131072 \
    --cache-type-k q4_0 \
    --cache-type-v q4_0 \
    --flash-attn 1 \
    --cont-batching \
    --parallel 1 \
    --batch-size 2048 \
    --ubatch-size 1024 \
    --n-gpu-layers 99 \
    --temp 0.9 \
    --top-p 0.95 \
    --top-k 60 \
    --min-p 0.0 \
    --repeat-penalty 1.0 \
    --api-key not-needed \
    --port 8080 \
    --host 0.0.0.0
 WRAPPER
 chmod 755 /home/llmuser/llama-fable-wrapper.sh
 echo "✅ Created /home/llmuser/llama-fable-wrapper.sh"
 # 3. Update systemd service to use new wrapper
 echo "📝 Updating systemd service..."
 sed -i 's|ExecStart=/home/llmuser/llama-wrapper.sh|ExecStart=/home/llmuser/llama-fable-wrapper.sh|' /etc/systemd/system/llama-server.service
 systemctl daemon-reload
 # 4. Stop old server, start new
 echo "🔄 Restarting llama-server..."
 systemctl stop llama-server
 sleep 3
 systemctl start llama-server
 sleep 8
 # 5. Verify
 echo ""
 echo "═══ Verification ═══"
 systemctl is-active llama-server
 echo ""
 echo "Port 8080:"
 ss -tlnp 2>/dev/null | grep ":8080" | head -1
 echo ""
 echo "GPU VRAM:"
 nvidia-smi --query-gpu=memory.used,memory.total,utilization.gpu --format=csv,noheader 2>/dev/null
 echo ""
 echo "=== Health check ==="
 curl -s --max-time 5 http://localhost:8080/health 2>/dev/null
 echo ""
 echo ""
 echo "✅ Swap complete. Test via LiteLLM:"
 echo "  curl -s http://192.168.68.116/v1/chat/completions -H 'Authorization: Bearer <key>' -H 'Content-Type: application/json' -d '{\"model\":\"gpu-dense\",\"messages\":[{\"role\":\"user\",\"content\":\"write hello world in python\"}],\"max_tokens\":100}'"
@@ -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
@@ -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
@@ -18,7 +16,7 @@ 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 (192.168.68.24, inside Abiba CT100 on hwepve), and Agent Zero Docker host (192.168.68.14)
+- **SSH access** to Tanko (192.168.68.122), Mumuni (192.168.68.123), 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`
@@ -184,13 +182,13 @@ 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 .24)
+### Step 3: Platform B — Hermes (Tanko .122, Mumuni .123)
 **B1: Gateway State**
 ```bash
 ssh root@192.168.68.122 "cat ~/.hermes/gateway_state.json"
-ssh root@192.168.68.24 "cat ~/.hermes/gateway_state.json"  # Mumuni inside Abiba CT100
+ssh root@192.168.68.123 "cat ~/.hermes/gateway_state.json"
 ```
 Check `platforms.zulip.state`: `connected` ✅ | `disconnected` ❌ | `error` ❌ | missing → not installed.
@@ -201,7 +199,7 @@ 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 via PM2 (`pm2 restart mumuni-zulip`). Check gateway log for "Gateway running with 2 platform(s)" (not 1) to confirm Zulip reloaded.
+Gateway PID should exist with uptime > 60s.
 **B3: Heartbeat Verification**
@@ -65,7 +65,7 @@ triggers:
 |------|----|------|---------|
 | Zulip server | 192.168.68.19 | root | Docker: `zulip-zulip-1` |
 | Abiba (pi) | localhost | root | PM2: `abiba-zulip` |
-| Mumuni | 192.168.68.24 (CT100 abiba) | root | `hermes gateway restart` |
+| Mumuni | 192.168.68.123 | root | `hermes gateway restart` |
 | Tanko | 192.168.68.122 | jerome | `PATH=$PATH:/home/jerome/.hermes/hermes-agent hermes gateway restart` |
 ## Debounce