Merge PR #38: feat: add Level 0 auto-delete for heartbeat log orphans

Logs (LITELLM-HEALTH, GPU-SELF-HEAL, PM2) now pushed to SyslogSolution/health-logs
instead of creating orphan nodes in the shared knowledge graph.

- litellm-self-heal: Phase 4 now calls gitea-logger instead of kg-logger
- gpu-self-heal: Reporting section updated to Gitea path
- pm2-self-heal: Log step redirected to Gitea
- 271 existing orphan nodes remain in graph (no delete tool available)

.gitignore

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

audit-hermes-config.py

@@ -0,0 +1,230 @@
+#!/usr/bin/env python3
+"""
+Hermes Config Audit — validates a live config.yaml against the prose contract rules.
+
+Usage:
+    python3 audit-hermes-config.py <config.yaml>
+    python3 audit-hermes-config.py /root/.hermes/config.yaml
+
+Exit codes:
+    0 = all checks pass
+    1 = one or more contract violations found
+
+This script encodes every rule from hermes-config-template.prose.md so config
+changes can be verified before and after application. It is the single automated
+enforcement layer for the prose contract.
+
+Contract: /root/prose-contracts/hermes-config-template.prose.md
+"""
+
+import sys
+import yaml
+
+VIOLATIONS = []
+WARNINGS = []
+PASSES = []
+
+
+def check(condition, rule, message):
+    if condition:
+        PASSES.append(f"[{rule}] {message}")
+    else:
+        VIOLATIONS.append(f"[{rule}] {message}")
+
+
+def warn(rule, message):
+    WARNINGS.append(f"[{rule}] {message}")
+
+
+def audit(path):
+    with open(path) as f:
+        cfg = yaml.safe_load(f)
+
+    model = cfg.get("model", {})
+    fb = cfg.get("fallback_providers", {})
+    comp = cfg.get("compression", {})
+    aux = cfg.get("auxiliary", {})
+    deleg = cfg.get("delegation", {})
+    cps = cfg.get("custom_providers", [])
+    cp = cps[0] if cps else {}
+
+    # --- Rule 3: API Keys via Environment ---
+    check(
+        model.get("api_key") in ("", None),
+        "Rule 3",
+        f"model.api_key must be empty (got {model.get('api_key')!r}) — keys via env var, not hardcoded",
+    )
+    check(
+        model.get("api_key_env") == "LITELLM_API_KEY",
+        "Rule 3",
+        f"model.api_key_env must be LITELLM_API_KEY (got {model.get('api_key_env')!r})",
+    )
+
+    # --- Rule 5: Main Config Base URL ---
+    expected_base = "http://192.168.68.116/v1"
+    check(
+        model.get("base_url") == expected_base,
+        "Rule 5",
+        f"model.base_url must be {expected_base} (got {model.get('base_url')!r}) — /v1 not /litellm/v1",
+    )
+
+    # --- Rule 6: max_tokens Is Required ---
+    check(
+        isinstance(model.get("max_tokens"), int) and model.get("max_tokens") <= 8192,
+        "Rule 6",
+        f"model.max_tokens must be set and <= 8192 (got {model.get('max_tokens')!r}) — thermal safety",
+    )
+
+    # --- Rule 7: Auxiliary Model Consistency ---
+    check(
+        comp.get("model") == "syslog-auto",
+        "Rule 7",
+        f"compression.model must be syslog-auto (got {comp.get('model')!r}) — auto-routing to prevent Strix Halo overload",
+    )
+    aux_comp = aux.get("compression", {})
+    check(
+        aux_comp.get("model") == "syslog-auto",
+        "Rule 7",
+        f"auxiliary.compression.model must be syslog-auto (got {aux_comp.get('model')!r}) — must match compression.model",
+    )
+
+    # --- Rule 8: GPU Workload Distribution ---
+    check(
+        aux.get("vision", {}).get("model") == "gpu-light",
+        "Rule 8",
+        f"auxiliary.vision.model must be gpu-light (got {aux.get('vision', {}).get('model')!r}) — RTX 5070 stable alias",
+    )
+    check(
+        aux.get("web_extract", {}).get("model") == "gpu-light",
+        "Rule 8",
+        f"auxiliary.web_extract.model must be gpu-light (got {aux.get('web_extract', {}).get('model')!r}) — RTX 5070 stable alias",
+    )
+
+    # --- Rule 9: Compression Threshold ---
+    check(
+        comp.get("threshold") == 0.65,
+        "Rule 9",
+        f"compression.threshold must be 0.65 for 128K models (got {comp.get('threshold')!r})",
+    )
+    check(
+        comp.get("max_context_window") == 131072,
+        "Rule 9",
+        f"compression.max_context_window must be 131072 (got {comp.get('max_context_window')!r}) — matches 128K GPU capacity",
+    )
+
+    # --- Rule 10: Default Model Must Be syslog-auto ---
+    check(
+        model.get("default") == "syslog-auto",
+        "Rule 10",
+        f"model.default must be syslog-auto (got {model.get('default')!r}) — auto-routing default",
+    )
+
+    # --- Rule 14: Provider Name Must Match custom_providers Name ---
+    check(
+        model.get("provider") == "harness",
+        "Rule 14",
+        f"model.provider must be 'harness' (got {model.get('provider')!r}) — NOT 'custom'. "
+        f"provider: custom causes generic resolution path that ignores key_env → 'no-key-required' → 401",
+    )
+    check(
+        comp.get("provider") == "harness",
+        "Rule 14",
+        f"compression.provider must be 'harness' (got {comp.get('provider')!r})",
+    )
+    for aux_name in ("vision", "web_extract", "compression"):
+        aux_provider = aux.get(aux_name, {}).get("provider")
+        check(
+            aux_provider == "harness",
+            "Rule 14",
+            f"auxiliary.{aux_name}.provider must be 'harness' (got {aux_provider!r})",
+        )
+    check(
+        deleg.get("provider") == "harness",
+        "Rule 14",
+        f"delegation.provider must be 'harness' (got {deleg.get('provider')!r})",
+    )
+    check(
+        fb.get("provider") == "deepseek",
+        "Rule 14",
+        f"fallback_providers.provider must be 'deepseek' (got {fb.get('provider')!r}) — "
+        f"true fallback diversity, not same endpoint as primary",
+    )
+    check(
+        fb.get("model") == "deepseek-v4-flash",
+        "Rule 14",
+        f"fallback_providers.model must be 'deepseek-v4-flash' (got {fb.get('model')!r})",
+    )
+    check(
+        fb.get("api_key_env") == "DEEPSEEK_API_KEY",
+        "Rule 14",
+        f"fallback_providers.api_key_env must be DEEPSEEK_API_KEY (got {fb.get('api_key_env')!r})",
+    )
+
+    # --- custom_providers sanity ---
+    check(
+        cp.get("name") == "harness",
+        "custom_providers",
+        f"custom_providers[0].name must be 'harness' (got {cp.get('name')!r})",
+    )
+    check(
+        cp.get("key_env") == "LITELLM_API_KEY" or cp.get("api_key_env") == "LITELLM_API_KEY",
+        "custom_providers",
+        f"custom_providers[0] must have key_env or api_key_env = LITELLM_API_KEY "
+        f"(got key_env={cp.get('key_env')!r}, api_key_env={cp.get('api_key_env')!r})",
+    )
+    check(
+        cp.get("base_url", "").endswith("/v1"),
+        "custom_providers",
+        f"custom_providers[0].base_url must end with /v1 (got {cp.get('base_url')!r})",
+    )
+
+    # --- No raw model names (Rule 7/8 spirit) ---
+    raw_names = {"gemma-4-12b", "qwen3.6-27B-code", "qwen3.6-35B-udq4", "ornith-1.0-35b"}
+    for section_path, section_dict in [
+        ("model", model), ("compression", comp),
+        ("auxiliary.vision", aux.get("vision", {})),
+        ("auxiliary.web_extract", aux.get("web_extract", {})),
+        ("auxiliary.compression", aux.get("compression", {})),
+        ("delegation", deleg),
+    ]:
+        m = section_dict.get("model", "")
+        if m in raw_names:
+            warn(
+                "Rule 7/8",
+                f"{section_path}.model = {m!r} — raw model name, use stable alias instead "
+                f"(gpu-light, gpu-dense, strix-moe, syslog-auto)",
+            )
+
+    # --- Report ---
+    print(f"{'=' * 60}")
+    print(f"Hermes Config Audit: {path}")
+    print(f"{'=' * 60}")
+    print(f"\n✅ PASSED ({len(PASSES)}):")
+    for p in PASSES:
+        print(f"  ✅ {p}")
+
+    if WARNINGS:
+        print(f"\n⚠️  WARNINGS ({len(WARNINGS)}):")
+        for w in WARNINGS:
+            print(f"  ⚠️  {w}")
+
+    if VIOLATIONS:
+        print(f"\n❌ VIOLATIONS ({len(VIOLATIONS)}):")
+        for v in VIOLATIONS:
+            print(f"  ❌ {v}")
+        print(f"\n{'=' * 60}")
+        print(f"RESULT: FAIL — {len(VIOLATIONS)} violation(s) must be fixed")
+        print(f"{'=' * 60}")
+        return 1
+    else:
+        print(f"\n{'=' * 60}")
+        print(f"RESULT: PASS — all contract rules satisfied")
+        print(f"{'=' * 60}")
+        return 0
+
+
+if __name__ == "__main__":
+    if len(sys.argv) < 2:
+        print("Usage: python3 audit-hermes-config.py <config.yaml>")
+        sys.exit(2)
+    sys.exit(audit(sys.argv[1]))

disk-gc-threat-response.prose.md

@@ -35,8 +35,7 @@ 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 |
 
-> **Decommissioned:** CT 118 (jitsi) — intentionally stopped, not scanned.
+> **Note:** CT 118 is now jdownloader (active on storepve). CT 101 (llm-gpu) → bare metal .8, CT 103 (ocu-llm) → bare metal .110.
-> **Migrated:** CT 101 (llm-gpu) → bare metal .8, CT 103 (ocu-llm) → bare metal .110.
 
 ## Threat Levels
 
@@ -275,10 +274,10 @@ one-off GPU builds. No automated post-migration cleanup was in place.
 ### CT Access (via pct-run)
 | CT | Name | Node | Status |
 |----|------|------|--------|
-| 100 | abiba | amdpve | local |
+| 100 | abiba | hwepve | local |
-| 102 | adguard | acerpve | ✅ reachable |
+| 102 | adguard | minipve | ✅ reachable |
 | 104 | authentik | minipve | ✅ reachable |
-| 105 | kagentz | amdpve | ✅ reachable |
+| 105 | kagentz | hwepve | ✅ reachable |
 | 106 | ra-h-os | storepve | ✅ reachable |
 | 107 | pbs | storepve | ✅ reachable |
 | 108 | media | storepve | ✅ reachable |
@@ -286,7 +285,7 @@ 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 | minipve | ✅ reachable |
+| 114 | mumuni | hwepve | ✅ reachable |
 | 115 | scottdenya | amdpve | ✅ reachable |
 | 116 | syslog-api | minipve | ✅ reachable |
 | 117 | zulip | storepve | ✅ reachable |
@@ -303,4 +302,4 @@ one-off GPU builds. No automated post-migration cleanup was in place.
 |------|-----|------|--------|
 | docker-vm | 192.168.68.7 | 16 Docker containers, 4 stacks | ✅ reachable |
 
-> **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.
+> **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.

docs/AUTHORING-GUIDE.md

@@ -185,7 +185,7 @@ what, and why should I care?
 
 ```
 ❌ "Monitors infrastructure health"
-✅ "Scans all 5 Proxmox nodes and 19 CTs for disk pressure, checks Docker
+✅ "Scans all 6 Proxmox nodes and 19 CTs for disk pressure, checks Docker
    container health on .7/.116/.17, alerts via Telegram DM on RED/CRITICAL"
 ```
 

gpu-fleet.prose.md

@@ -14,6 +14,10 @@ description: >
   Instability observed near 100K at 256K (now all GPUs at 128K). 128K is the stable ceiling.
   For larger context needs → fall back to external providers (deepseek).
   VRAM headroom improved: RTX 3090 ~70%, RTX 5070 ~65%.
+  UPDATED 2026-07-27: gpu-dense swapped to SmartCode-Fable-5-CoT-Reasoning-QKVO-Qwen-3.6-27B-Distilled
+  (UD-Q3_K_XL, ~14.7GB — Q4 was too large for 24GB VRAM with 128K KV cache). ~50% fewer thinking
+  tokens via ThinkingCap finetune + Fable 5 CoT distillation for improved coding reasoning.
+  VRAM ~22.4/24.6GB (91%).
 agent: abiba
 triggers:
   - on model add/remove
@@ -86,7 +90,7 @@ 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) | qwen3.6-27B-code | Whatever runs on RTX 3090 |
+| `gpu-dense` | RTX 3090 (.8) | SmartCode-Fable-5-27B-UD-Q4_K_XL | Whatever runs on RTX 3090 |
 | `gpu-light` | RTX 5070 (.110) | gemma-4-12b | Whatever runs on RTX 5070 |
 
 **Backward compatibility**: Old model-specific names (qwen3.6-27B-code, gemma-4-12b, qwen3.6-35B-udq4) still work
@@ -96,7 +100,7 @@ but are deprecated for agent configs. Only the stable aliases survive model swap
 
 | Model | GPU | Host | VRAM | Ctx | KV Cache | Parallel | Batch/Ubatch | Status |
 |-------|-----|------|------|-----|----------|----------|-------------|--------|
-| qwen3.6-27B-code (MTP) | RTX 3090 | .8 (llm-gpu) | ~17/24.6GB (70%) | **128K** | turbo4 | 2 | default | ✅ 63 tok/s |
+| SmartCode-Fable-5-27B-UD-Q3_K_XL | RTX 3090 | .8 (llm-gpu) | ~22.4/24.6GB (91%) | **128K** | q4_0 | 1 | 2048/1024 | ✅ healthy |
 | gemma-4-12b | RTX 5070 | .110 (ocu-llm) | ~7.8/12.2GB (65%) | 128K | q4_0 | 2 | 2048/1024 | ✅ healthy |
 | qwen3.6-35B-udq4 | Strix Halo Vulkan | .15 (amdpve) | ~22GB/64GB | 128K | q4_0 | 1 | 4096/1024 | ✅ 65 tok/s |
 
@@ -106,7 +110,7 @@ but are deprecated for agent configs. Only the stable aliases survive model swap
 
 | Model | GPU | Weight | RPM Cap | Timeout |
 |-------|-----|--------|---------|---------|
-| qwen3.6-27B-code | RTX 3090 (.8:8080) | **0.55** | 500 | **300s** |
+| SmartCode-Fable-5-27B-UD-Q3_K_XL | RTX 3090 (.8:8080) | **0.55** | 500 | **300s** |
 | qwen3.6-35B-udq4 | Strix Halo (.15:8080) | **0.30** | 60 | **300s** |
 | gemma-4-12b | RTX 5070 (.110:8080) | **0.15** | 200 | **120s** |
 
@@ -117,7 +121,7 @@ Note: All syslog-auto entries route directly to GPUs with `api_key: not-needed`.
 | Model | RPM Cap | Notes |
 |-------|---------|-------|
 | strix-moe (qwen3.6-35B-udq4) | 40 | Tight cap — prevents Strix overload |
-| qwen3.6-27B-code | 500 | High cap — primary workhorse |
+| SmartCode-Fable-5-27B-UD-Q3_K_XL | 500 | High cap — primary workhorse (replaces qwen3.6-27B-code) |
 | gemma-4-12b | 500 | High cap — IQ4_NL+MTP, 122 tok/s |
 
 ### Stable Aliases (for agent configs — never change)
@@ -204,7 +208,7 @@ 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 | 114 | .123 | `mumuni` | Infisical vault | SSH root |
+| Mumuni | 100 (abiba) | .24 | `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 |
@@ -247,13 +251,12 @@ If no SSH access, send Zulip DM via abiba-bot with vault update instructions.
   Fix: trigger roster reload via SSH after restart, or rebuild image with startup load_roster().
 - **LiteLLM /metrics**: Requires auth. Prometheus uses `/health/liveliness` as workaround.
 - **VRAM (2026-07-15)**: RTX 3090 at ~17/24.6GB (~70%) with **128K context** (reduced from 256K 2026-07-17). RTX 5070 at ~7.8/12.2GB (~65%) with 128K context + MTP. Strix Halo at ~7GB/64GB.
-- **RTX 3090 runs `--parallel 2`** with MTP draft (spec-type draft-mtp, spec-draft-n-max 2).
+- **RTX 3090 (2026-07-27)**: Swapped to SmartCode-Fable-5-27B-UD-Q3_K_XL (14.7GB). Q4 was too large for 24GB VRAM with 128K context + KV cache overhead. Q3 fits at ~22.4GB (91%). Uses standard llama.cpp build b9190 (turboquant b9150 incompatible with qwen3_5 arch). Config: `-c 131072 -ctk q4_0 -ctv q4_0 --flash-attn on --cont-batching`. Sampler: `--temp 0.9 --top-p 0.95 --top-k 60 --min-p 0.0 --repeat-penalty 1.0`. Service: `/home/llmuser/llama-fable-wrapper.sh`.
-- **RTX 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`.
 - **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.
+- **LiteLLM timeout tuning (verified 2026-07-27)**: SmartCode-Fable-5-27B 300s, gemma-4-12b 120s, qwen3.6-27B-code 300s (legacy), qwen3.6-35B-udq4 300s, strix-moe 300s, syslog-auto routes all 300s. Nginx proxy_read_timeout: 600s. Global request_timeout: 300s.
 - **Strix Halo GPU**: Vulkan is the working backend (ROCm/HIP path abandoned — HSA runtime blocked on Debian 13). Build at `/root/llama.cpp/build-vk/`, commit `4fc4ec5` (2026-07-01), ggml 0.15.3 shared-lib arch. Mesa RADV 25.0.7, KHR_coopmat fast path active. ~70 tok/s gen, 532 tok/s prompt. Service: `strix-server.service` on port 8080, model: `qwen3.6-35B-udq4`, alias `strix-moe`, 128K context, flash-attn + q4 KV, multimodal (mmproj loaded).
 - **Port conflict detection (2026-07-05)**: All 3 GPU wrappers now detect ghost processes squatting port 8080 before starting. `.8` and `.110` use inline pre-start check in `llama-wrapper.sh`; `.15` uses `/usr/local/bin/port-cleanup.sh` ExecStartPre. Replaces the blanket `pkill -9 -x llama-server` on .15 which would kill ALL llama-server instances regardless of port. Ghost detection was the root cause of .8 crash-looping for 27+ restarts (stale pid 25836 squatting 8080 after OOM kill).
-- **Strix Halo thermal safeguard (2026-07-02)**: `strix-server.service` has `-n 8192` (hard generation cap per request). Without it, `--predict` defaults to -1 (infinity) — a runaway request from .123 (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`.
+- **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`.
 - **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.
@@ -265,7 +268,7 @@ If no SSH access, send Zulip DM via abiba-bot with vault update instructions.
 
 | GPU | Model | Gen tok/s | Prompt tok/s | Baseline | Context |
 |-----|-------|-----------|--------------|----------|---------|
-| RTX 3090 (.8) | qwen3.6-27B-code (MTP) | **63** | — | — | **128K** |
+| RTX 3090 (.8) | SmartCode-Fable-5-27B-UD-Q3_K_XL | **TBD** | — | — | **128K** |
 | RTX 5070 (.110) | gemma-4-12b (IQ4_NL+MTP) | **191** | — | — | **128K** |
 | Strix Halo (.15) | qwen3.6-35B-udq4 | **65** | 140 | — | **128K** |
 
@@ -298,7 +301,7 @@ When the underlying model is swapped, only the LiteLLM config changes — agent
 
 ### Mumuni Agent Profile
 
-Mumuni (CT114, 192.168.68.123) is the primary business assistant. This profile is the reference for all agent configs:
+Mumuni (CT100/abiba, 192.168.68.24) is the primary business assistant. This profile is the reference for all agent configs:
 
 | Setting | Value | Notes |
 |---------|-------|-------|
@@ -323,7 +326,7 @@ Mumuni (CT114, 192.168.68.123) is the primary business assistant. This profile i
 
 | Agent | Host | Status |
 |-------|------|--------|
-| **Mumuni** | CT114 (.123) | ✅ Updated to stable aliases |
+| **Mumuni** | CT100 (.24) | ✅ 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 |

gpu-self-heal.prose.md

@@ -251,8 +251,8 @@ call update-gpu-health
 
 ## Reporting
 
-### 1. Knowledge Graph
+### 1. Gitea Log (not knowledge graph — hard rule)
-Every action logged as `[GPU-SELF-HEAL] <run_id>` node with full audit trail.
+Pushed to `SyslogSolution/health-logs/gpu/{run_id}.json` — versioned, searchable, not in graph.
 
 ### 2. Zulip Alerts (#agent-hub → alerts-gpu)
 - `issues_fixed > 0` → "🛠 GPU Self-Heal — <gpu> <issue> resolved"

hermes-agent-baseline.prose.md

@@ -26,11 +26,11 @@ done
 |-------|-----|------|-----|---------------|------------|----------|
 | Tanko | 112 | amdpve | .122 | `tanko` | Infisical vault | Hermes |
 | Mumuni | 114 | hwepve | .123 | `mumuni` | Infisical vault | Hermes |
-| Koby | 129 | amdpve | srv1079750 | `koby` | Infisical vault | **Hermes** |
+| Koby | 111 | amdpve | srv1079750 | `koby` | Infisical vault | **Hermes** |
-| Koonimo | 114 | amdpve | ? | `koonimo` | Infisical vault | Hermes |
+| Koonimo | 113 | amdpve | .114 | `koonimo` | Infisical vault | Hermes |
 | Shumba | — | 192.168.68.119 | N/A | N/A (DeepSeek) | Hermes (RETIRED — CT119 now Infisical vault) |
 
-> **Note**: CT hostnames (tdunna→CT129, baggy→CT114) differ from agent identities (koby, koonimo).
+> **Note**: CT hostnames (tdunna→CT111, baggy→CT113) differ from agent identities (koby, koonimo).
 
 Access: `pct-run <CT_ID> <command>` — no IPs needed. GPU hosts (.8, .110, .15) use SSH.
 Keys are stored in Infisical vault (project=agents, env=production) and injected at
@@ -169,9 +169,9 @@ 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 129 / tdunna)
+### For Koby (CT 111 / tdunna)
 
-Koby runs Hermes on CT 129 (tdunna). Config files at `/root/.hermes/config.yaml`.
+Koby runs Hermes on CT 111 (tdunna). Config files at `/root/.hermes/config.yaml`.
 Same Hermes pattern as Tanko/Mumuni/Koonimo — see config sections above.
 
 **LiteLLM key**: alias `koby` in LiteLLM DB, injected via `infisical run --` wrapper.
@@ -253,7 +253,7 @@ EnvironmentFile=/etc/environment        # sources LITELLM_API_KEY
 
 Run the consolidated health check:
 ```bash
-python3 /root/scripts/agent-health-check.py  # v2: now checks all 5 agents including Koby/Koonimo SSH, CT liveness, config YAML, wrapper integrity, vault non-emptiness
+python3 /root/scripts/agent-health-check.py
 ```
 This validates all 4 LiteLLM keys, detects GPU port conflicts (ghost processes),
 verifies gateway liveness, confirms Zulip streaming (`edit_message` present),

hermes-config-template.prose.md

@@ -5,14 +5,11 @@ 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 2026-07-18: Compression model switched to `syslog-auto` (was `strix-moe`)
+  UPDATED 2026-07-16: Compression model is the stable alias `strix-moe` (NOT `ornith-1.0-35b`,
-  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 (later switched to syslog-auto 2026-07-18). RTX 3090 context verified at 128K. Infisical .env fallback required (Rule 3/13).
+  UPDATED 2026-07-12: GPU workload redistributed. Compression → Strix Halo. RTX 3090 context verified at 128K. Infisical .env fallback required (Rule 3/13).
 ---
 
 ## Maintains
@@ -133,9 +130,7 @@ mcp_servers:
 # ─── Compression ───
 compression:
   enabled: true
-  model: syslog-auto              # ⚠️ Switched from strix-moe 2026-07-18 to relieve Strix Halo.
+  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).
-                                  # 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
@@ -150,9 +145,8 @@ compression:
 #   model: gpu-light                 # stable alias (NOT raw "gemma-4-12b")
 #   base_url: http://192.168.68.116/v1
 #   api_key_env: LITELLM_API_KEY
-# Compression uses syslog-auto (switched from strix-moe 2026-07-18) to distribute
+# Do NOT use syslog-auto for auxiliary tasks — it routes to the primary GPU.
-# load across the weighted pool and relieve Strix Halo pressure.
+# gpu-light = RTX 5070 (12B), freeing the Strix Halo for agent reasoning.
-# Vision and web_extract use gpu-light = RTX 5070 (12B).
 # Heavy aux (delegation, x_search) use gpu-dense (RTX 3090) instead.
 # NEVER use raw model names (gemma-4-12b, qwen3.6-27B-code, qwen3.6-35B-udq4)
 # in agent configs — use the stable aliases so model swaps don't break agents.
@@ -172,7 +166,7 @@ auxiliary:
     timeout: 30
   compression:
     provider: harness
-    model: syslog-auto             # Switched from strix-moe 2026-07-18. Relieves Strix Halo pressure.
+    model: syslog-auto              # MUST match compression.model above. Stable alias for Strix Halo (weighted pool).
     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)
@@ -253,30 +247,34 @@ 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 2026-07-18)
+### Rule 7: Auxiliary Model Consistency (UPDATED 2026-07-16)
-- Vision and web_extract use `gpu-light` (stable alias, RTX 5070 — 12GB, vision-optimized)
+- Vision and web_extract use `gemma-4-12b` (RTX 5070 — 12GB, vision-optimized)
-- Compression now uses `syslog-auto` (switched from `strix-moe` 2026-07-18) to distribute
+- Compression uses `strix-moe` (stable alias for Strix Halo — 64GB, 128K ctx, compression-optimized)
-  compression load across the weighted pool (55% RTX 3090, 30% Strix Halo, 15% RTX 5070).
+- **`strix-moe` is the only valid compression model name** — LiteLLM does NOT serve `ornith-1.0-35b`
-  This relieves Strix Halo pressure while keeping compression functional on all GPUs.
+  (it serves `strix-moe`, `qwen3.6-35B-udq4`, `gpu-dense`, `gpu-light`, `syslog-auto`, `gemma-4-12b`, `qwen3.6-27B-code`). Old configs with `ornith-1.0-35b` cause 403/model-not-found on compression calls.
-- **`syslog-auto` is the valid compression model** — LiteLLM serves it as the weighted pool.
+- **OPERATIONAL DECISION (2026-07-23): Use `syslog-auto` for compression across all agents.**
-  Old configs with `strix-moe` for compression should be updated to `syslog-auto`.
+  The `syslog-auto` alias routes to the Strix Halo, but uses the weighted pool instead of pinning
+  to `strix-moe` directly. This prevents sustained Strix Halo thermal load because the pool can
+  fall back to other GPUs if Strix gets hot. Both `compression.model` and `auxiliary.compression.model`
+  MUST be `syslog-auto`.
 - All auxiliary services MUST use identical routing:
   - `base_url: http://192.168.68.116/v1`  (Rule 5: `/v1`, NOT `/litellm/v1`)
   - `api_key_env: LITELLM_API_KEY`
-- **Compression via syslog-auto**: Routes through the weighted pool. Strix Halo still handles
+- **Do NOT use `syslog-auto`** for auxiliary tasks — it routes unpredictably
-  ~30% of compression calls (at 60 RPM via pool vs 40 RPM direct), but the bulk (55%)
+- **Compression on Strix Halo**: The strix-moe alias routes to Strix Halo
-  goes to RTX 3090 which has ample spare capacity.
+  (64GB UMA, 128K context) — the designated compression GPU. This frees the
+  RTX 5070 for vision and web search, and the RTX 3090 for heavy reasoning.
 - 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 2026-07-18)
+### Rule 8: GPU Workload Distribution (UPDATED 2026-07-16)
-- **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 3090 (24GB, 128K ctx, qwen3.6-27B-code)**: Heavy reasoning, code gen, long conversations
-- **RTX 5070 (12GB, 128K ctx, gemma-4-12b)**: Vision, web search, quick tasks, web_extract — handles ~15% of compression via syslog-auto pool
+- **RTX 5070 (12GB, 128K ctx, gemma-4-12b)**: Vision, web search, quick tasks, web_extract (IQ4_NL+MTP, ~65% VRAM at 128K)
-- **Strix Halo (64GB, 128K ctx, qwen3.6-35B-udq4)**: Agent reasoning, compression (~30% via syslog-auto pool), fallback for other GPUs
+- **Strix Halo (64GB, 128K ctx, syslog-auto)**: Context compression, summarization, long docs
 - Agent profiles MUST route auxiliary tasks to the correct GPU:
-  - `auxiliary.vision.model: gpu-light` (RTX 5070)
+  - `auxiliary.vision.model: gemma-4-12b` (RTX 5070)
-  - `auxiliary.web_extract.model: gpu-light` (RTX 5070)
+  - `auxiliary.web_extract.model: gemma-4-12b` (RTX 5070)
-  - `auxiliary.compression.model: syslog-auto` (distributed pool, switched from strix-moe 2026-07-18)
+  - `auxiliary.compression.model: syslog-auto` (Strix Halo)
 - Default model (`model.default`) and custom_provider remain `syslog-auto` for auto-routing
 - For 128K context window: `threshold: 0.65` (fires at ~85K tokens)
 - Do NOT use `threshold: 0.25` — this fires at 65K, causing premature context loss
@@ -378,6 +376,26 @@ 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

hermes-key-enforcement.prose.md

@@ -189,7 +189,7 @@ litellm_settings:
 | Agent | CT | IP | LiteLLM Alias | Key Source | Status | Gateway Wrapper | Last Verified |
 |-------|-----|-----|---------------|------------|--------|-----------------|---------------|
 | Tanko | 112 | .122 | `tanko` | Infisical vault | ✅ Fixed | `infisical run` | 20:17 UTC Jul 5 |
-| Mumuni | 114 | .123 | `mumuni` | Infisical vault | ✅ Fixed | `infisical run` | 01:46 EDT Jul 10 |
+| Mumuni | 100 (abiba) | .24 | `mumuni` | Infisical vault | ✅ Fixed | Pi Hermes gateway | 2026-07-27 |
 | Koby | 111 | ? | `koby` | Infisical vault | ✅ Fixed | `infisical run` | 23:30 UTC Jul 5 |
 | Koonimo | 113 | ? | `koonimo` | Infisical vault | ✅ Fixed | `infisical run` (migrated 2026-07-11) | 2026-07-11 |
 | Abiba | 100 | .65 | `abiba-pi` | Infisical vault | ✅ N/A (pi native) | — | 19:44 UTC Jul 5 |

hermes-zulip-restore.prose.md

@@ -51,7 +51,7 @@ gateway restart, and connection validation.
 
 | Host | CT | Proxmox | IP (direct) | Hermes Home | User |
 |------|-----|---------|-------------|-------------|------|
-| Mumuni | CT114 | hwepve | 192.168.68.123 | /root/.hermes | root |
+| Mumuni | CT100 (abiba) | hwepve | 192.168.68.24 | /root/.hermes | root |
 | Tanko | CT112 | amdpve | 192.168.68.122 | /home/jerome/.hermes | jerome |
 | Koby | CT111 | amdpve | 192.168.68.129 | /root/.hermes | root |
 | Shumba | — | — | 192.168.68.119 | /home/lucky/.hermes | lucky |

infrastructure-control.prose.md

@@ -13,10 +13,10 @@ description: >
   against the live system. Policy fields are authoritative. See the
   `verify-before-mutate` skill.
 
-  **Last verified:** 2026-07-26 — CT 114 (mumuni) destroyed. Mumuni moved inside
+  **Last verified:** 2026-07-24 — corrected Gitea IP (.17 not .110),
-  CT 100 (abiba) — Zulip connected on .24. Verification protocol run: CT 118 set
+  AdGuard IP (.10 not .102), AdGuard placement (minipve not acerpve),
-  to static IP .20, llama-server on .110 restored. All PVE nodes, CT hostnames,
+  Abiba placement (hwepve not amdpve), added hwepve as 6th node,
-  and public endpoints confirmed. See data/learnings.md.
+  added dns.sysloggh.net route.
 ---
 
 # Infrastructure Control Pattern
@@ -109,12 +109,12 @@ description: >
 | storepve | .6 | 28C | 31GB | docker-vm, ra-h-os, PBS, media, jdownloader, zulip | Docker, storage, chat |
 | acerpve | .9 | 28C | 31GB | llm-gpu | GPU VMs |
 | ocupve | .5 | 12C | 14GB | ocu-llm | GPU VMs |
-| hwepve | .4 | ? | ? | abiba, (mumuni CT 114 stopped) | Agents (new node) |
+| 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 and now runs Mumuni
+> minipve at .10, not acerpve. Abiba (CT 100) is on hwepve, not amdpve. Mumuni
-> Zulip gateway internally. CT 114 (old mumuni container) destroyed 2026-07-26.
+> (CT 114) is on hwepve (currently stopped), not minipve. Mumuni also has a
-> Mumuni also has a second instance on minipve at .123 — distinguish by CT ID.
+> second instance on minipve at .123 — distinguish by CT ID, not hostname.
 
 ### Checks (every 5 min)
 
@@ -365,7 +365,7 @@ 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 | CNAME → netbird | **Yes** | ⚠️ |
+| Authentik | auth.sysloggh.net:443 | 192.168.68.11:9000 | CNAME → netbird | **Yes** | ⚠️ |
 | Gitea | git.sysloggh.net:443 | 192.168.68.17:3000 | CNAME → netbird | **Yes** | ⚠️ |
 | Zulip | chat.sysloggh.net:443 | 192.168.68.19 | CNAME → netbird | **Yes** | ⚠️ VERIFY-BEFORE-USE |
 | Pulse | pulse.sysloggh.net:443 | 192.168.68.7 | CNAME → netbird | **Yes** | ⚠️ |
@@ -586,8 +586,6 @@ ssh root@192.168.68.110 "systemctl restart llama-server"
 
 ## Appendix B: CT Inventory
 
-| CT | Name | Node | IP | Role | Agent |
-|----|------|------|----|------|-------|
 | CT | Name | Node | IP | Role | Agent |
 |----|------|------|----|------|-------|
 | 100 | abiba | **hwepve** | .24 | Pi agent | ✅ pi |
@@ -604,6 +602,7 @@ ssh root@192.168.68.110 "systemctl restart llama-server"
 | 111 | tdunna | amdpve | .129 | Hermes agent | ✅ |
 | 112 | tanko | amdpve | .122 | Hermes agent | ✅ |
 | 113 | baggy | amdpve | .114 | Hermes agent | ✅ |
+| 114 | mumuni | **hwepve** | .123 | Hermes agent (stopped) | ✅ |
 | 115 | scottdenya | amdpve | .75 | Denya OneCare | ❌ |
 | 116 | syslog-api | minipve | .116 | LiteLLM + Grafana | ❌ |
 | 117 | zulip | storepve | .19 | Chat | ❌ |
@@ -629,14 +628,14 @@ Source of truth: `/root/scripts/pct-run.sh` or `prose-contracts/scripts/pct-run.
 | CT | Name | Node | pct-run |
 |-----|------|------|---------|
 | 100 | abiba | hwepve | `pct-run 100` |
-| 105 | kagentz | **hwepve** | `pct-run 105` |
+| 105 | kagentz | hwepve | `pct-run 105` |
 | 111 | tdunna | amdpve | `pct-run 111` |
 | 112 | tanko | amdpve | `pct-run 112` |
 | 113 | baggy | amdpve | `pct-run 113` |
 | 115 | scottdenya | amdpve | `pct-run 115` |
 | 104 | authentik | minipve | `pct-run 104` |
 | 110 | gitea | minipve | `pct-run 110` |
-
+| 114 | mumuni | hwepve | `pct-run 114` |
 | 116 | syslog-api | minipve | `pct-run 116` |
 | 106 | ra-h-os | storepve | `pct-run 106` |
 | 107 | proxmox-backup | storepve | `pct-run 107` |
@@ -649,35 +648,27 @@ GPU bare-metal hosts (.8 acerpve, .110 ocupve, .15 amdpve) are NOT CTs — use S
 ssh root@192.168.68.8   # RTX 3090
 ssh root@192.168.68.110 # RTX 5070
 ssh root@192.168.68.15  # Strix Halo
-ssh root@192.168.68.4   # hwepve (abiba, kagentz) — Mumuni runs inside CT 100
+ssh root@192.168.68.4   # hwepve (abiba, kagentz, mumuni)
 ```
 
-## Section 7: Agent Health Check v2 (2026-07-26)
+## Section 7: Agent Health Check (consolidated — 2026-07-05)
 
-Single non-disruptive check running every 10 minutes via cron
+Replaces 7 scattered Zulip health scripts with a single non-disruptive check
-(`/root/scripts/agent-health-check.py`). v2 fixes critical gaps:
+running every 10 minutes via cron (`/root/scripts/agent-health-check.py`).
-- Koby (.129) and Koonimo (.114) now have SSH hosts — no longer skipped
-- Agent-specific vault keys (`{NAME}_LITELLM_API_KEY`) not shared master key
-- CT liveness check via `pct status` on PVE nodes
-- Config YAML integrity check
-- Wrapper/CLI integrity check
-- Vault secret non-emptiness check
 
 The script is **read-only** — it never restarts, kills, or modifies anything.
+Disruptive cron-based gateways restarts (like Mumuni's zulip-watchdog.sh,
+which was kill+nohup outside systemd) are banned by policy.
 
 ### Checks Performed
 
 | Check | Frequency | What It Detects |
 |-------|-----------|-----------------|
-| LiteLLM key validation | 10 min | All 5 agent-specific keys authenticate (not shared master key) |
+| LiteLLM key validation | 10 min | All 4 agent keys authenticate and return models |
 | GPU port conflict | 10 min | Ghost processes squatting port 8080 (ss vs systemd MainPID) |
-| Gateway liveness | 10 min | Gateway process running, state file readable (all 5 agents) |
+| Gateway liveness | 10 min | Gateway process running, state file readable |
 | Zulip streaming | 10 min | `edit_message` present in adapter (streaming supported) |
 | Recent errors | 10 min | Error count in journald for last 10 min |
-| CT liveness | 10 min | `pct status` on PVE nodes — catches stopped CTs |
-| Config YAML integrity | 10 min | Python `yaml.safe_load()` — catches syntax errors |
-| Wrapper/CLI integrity | 10 min | hermes wrapper exists, infisical path correct, hermes-real reachable |
-| Vault secrets | 10 min | Agent-specific vault keys are non-empty and start with `sk-` |
 
 ### Disabled Scripts
 

infrastructure-update.prose.md

@@ -2,7 +2,7 @@
 kind: responsibility
 name: infrastructure-update
 description: >
-  Autonomous system-wide update contract covering all 5 Proxmox nodes,
+  Autonomous system-wide update contract covering all 6 Proxmox nodes,
   15+ containers/VMs, and 4 Docker ecosystems. Updates apt packages,
   Docker images, and container stacks in safe waves with health checks
   and automatic rollback on failure.
@@ -56,10 +56,11 @@ Before ANY update wave:
 | amdpve (.15) | Proxmox node | `apt update && apt upgrade -y` | 5 min |
 | acerpve (.9) | Proxmox node | `apt update && apt upgrade -y` | 5 min |
 | ocupve (.5) | Proxmox node | `apt update && apt upgrade -y` | 5 min |
+| hwepve (.4) | Proxmox node | `apt update && apt upgrade -y` | 5 min |
 | CT 100 (.24) | Abiba (pi) | `apt update && apt upgrade -y` | 3 min |
 | CT 116 (.116) | syslog-api (LiteLLM host) | `apt update && apt upgrade -y` | 3 min |
 | CT 112 (tanko, amdpve) | Tanko | `apt update && apt upgrade -y` | 3 min |
-| CT 114 (mumuni, minipve) | Mumuni | `apt update && apt upgrade -y` | 3 min |
+| CT 114 (mumuni, hwepve) | Mumuni | `apt update && apt upgrade -y` | 3 min |
 | VM 101 (.8) | llm-gpu (RTX 3090) | `apt update && apt upgrade -y` | 3 min |
 | VM 103 (.110) | ocu-llm (RTX 5070) | `apt update && apt upgrade -y` | 3 min |
 
@@ -218,7 +219,7 @@ When LiteLLM is upgraded to a version supporting per-key MCP grants:
 
 ## Success Criteria
 
-- [ ] All 5 PVE nodes updated, no reboot-loop
+- [ ] All 6 PVE nodes updated, no reboot-loop
 - [ ] All VMs/CTs running post-update
 - [ ] All Docker containers healthy (VM 109 + CT 116 + CT 117)
 - [ ] LiteLLM inference passing (syslog-auto test)
@@ -234,7 +235,7 @@ After completion, send Zulip DM:
 ```
 📋 Infrastructure Update — YYYY-MM-DD
 
-Updated: 5 PVE nodes, 12 CTs/VMs, 30+ containers
+Updated: 6 PVE nodes, 12 CTs/VMs, 30+ containers
 Security fixes: N CVEs patched
 Downtime: <service> <duration>
 Failures: none / <details>

litellm-api-keys.prose.md

@@ -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 | .123 | systemd drop-in + while-true wrapper + st.8e848433 | MUMUNI_LITELLM_API_KEY + MUMUNI_ZULIP_API_KEY | ✅ vault-backed + .env fallback |
+| mumuni | .24 (CT100 abiba) | Pi Hermes gateway (no systemd) | MUMUNI_LITELLM_API_KEY + MUMUNI_ZULIP_API_KEY | ✅ vault-backed + .env fallback |
 | tanko | .122 | systemd drop-in + while-true wrapper + st.8e848433 (user jerome) | TANKO_LITELLM_API_KEY + TANKO_ZULIP_API_KEY | ✅ vault-backed + .env fallback |
 | koby | .129 | systemd drop-in + while-true wrapper + st.8e848433 | KOBY_LITELLM_API_KEY, shares TANKO_ZULIP_API_KEY (tanko-bot) | ✅ vault-backed |
 | koonimo | .114 | systemd drop-in + while-true wrapper + st.8e848433 | KOONIMO_LITELLM_API_KEY + KOONIMO_ZULIP_API_KEY | ✅ vault-backed |

litellm-self-heal.prose.md

@@ -7,7 +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 RA-H OS knowledge graph.
+  Reports to /var/log/litellm/health-*.json and Gitea (SyslogSolution/health-logs).
   GPU monitoring integrated from gpu-monitor on .24:9100.
   
   Consolidated from litellm-health + litellm-self-heal on 2026-07-09 to eliminate
@@ -20,7 +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 RA-H OS knowledge graph.
+  Reports every action via Zulip DM and Gitea (SyslogSolution/health-logs).
 ---
 
 # LiteLLM Operations — Health Check + Self-Heal
@@ -102,7 +102,7 @@ Request → nginx:80 → LiteLLM:4000 → GPU(llama-server, parallel 2)
 
 - **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 (.123), 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`): 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.
 - **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
@@ -211,8 +211,8 @@ for reference but inactive. If Redis issues occur, check harness-redis container
 
 Every remediation cycle produces a structured report:
 
-### 1. RA-H OS Knowledge Graph Node
+### 1. Gitea Log Entry
-Created as `[LEARN] litellm-self-heal: <run_id>` with full JSON report.
+Pushed to `SyslogSolution/health-logs/litellm/{run_id}.json` — versioned, searchable, not in graph.
 
 ### 2. Zulip DM to Owner
 - `issues_fixed > 0` — "🛠 LiteLLM Self-Heal — Fix Applied"
@@ -252,9 +252,11 @@ call report-generator
   health: health
   actions: actions
 
--- Phase 4: Log to knowledge graph
+-- Phase 4: Log to Gitea (not knowledge graph — hard rule)
-call kg-logger
+call gitea-logger
   run_id: run_id
+  repo: SyslogSolution/health-logs
+  path: litellm/{run_id}.json
   health: health
   actions: actions
 
@@ -300,3 +302,20 @@ With failures:
   ]
 }
 ```
+
+## gitea-logger Implementation
+
+When this step executes, write the report JSON to a temp file and push to Gitea:
+
+```bash
+REPO="https://abiba-bot:${GITEA_PAT}@git.sysloggh.net/SyslogSolution/health-logs"
+DIR="litellm"
+FILE="${run_id}.json"
+echo "${report_json}" > /tmp/${FILE}
+(cd /tmp && git clone --depth 1 "${REPO}" && 
+  cp ${FILE} health-logs/${DIR}/${FILE} && 
+  cd health-logs && git add ${DIR}/${FILE} && 
+  git commit -m "litellm-health: ${run_id}" && git push)
+rm -rf /tmp/health-logs /tmp/${FILE}
+```
+

memory-fixer.prose.md

@@ -0,0 +1,71 @@
+---
+kind: pattern
+name: memory-fixer
+description: >
+  Auto-fix low-hanging fruit in the graph. No judgment calls — only deterministic Level 1 operations. 
+  Escalate anything that needs Kwame's input.
+version: 1.1.0
+---
+
+# Memory Fixer
+
+## Purpose
+Auto-fix low-hanging fruit in the graph. No judgment calls — only deterministic Level 1 operations. Escalate anything that needs Kwame's input.
+
+## Level 0 Auto-Deletes (Allowed Without Approval)
+Ephemeral heartbeat and log nodes that violate "Logs NEVER go in the graph":
+
+- `[LITELLM-HEALTH]`, `[GPU-SELF-HEAL]`, `[PM2-SELF-HEAL]`
+- `[PROXMOX-MONITOR]`, `[GPU-MONITOR]`, `[INFRA-MONITOR]`, `[AGENT-HEALTH]`, `[DISK-GC]`
+- `[WAL]` entries older than 30 days
+
+**Condition:** node must be an orphan (no edges). Deleting a connected node risks breaking other nodes.
+
+**Method:** direct SQLite on `.65` (MCP has no delete tool):
+```bash
+ssh root@192.168.68.65 "sqlite3 /root/.local/share/RA-H/db/rah.sqlite \"
+DELETE FROM nodes WHERE id IN (
+  SELECT id FROM nodes WHERE id NOT IN (SELECT from_node_id FROM edges)
+  AND id NOT IN (SELECT to_node_id FROM edges)
+  AND title LIKE '[LITELLM-HEALTH]%' -- add more prefixes as needed
+);\""
+```
+
+## Level 1 Auto-Fixes (No Judgment Required)
+
+### 1. Missing `type` Field
+For nodes with content but no `metadata.type`:
+- Title contains "Proxmox" or "infrastructure" → `type: infrastructure`
+- Title contains "skill" or "how to" or "guide" → `type: skill`
+- Title contains "doc" or "template" or "brand" → `type: documentation`
+- Title starts with "WAL:" or "TASK:" → `type: note`
+- Title starts with "[LEARN]" → `type: documentation`
+- Otherwise → `type: note` (default)
+
+### 2. Missing `tenant` / `namespace`
+For any node with NULL tenant or namespace:
+```sql
+UPDATE nodes 
+SET metadata = json_set(
+  COALESCE(metadata, '{}'),
+  '$.tenant', 'syslogsolution',
+  '$.namespace', 'syslogsolution'
+)
+WHERE json_extract(metadata, '$.tenant') IS NULL 
+   OR json_extract(metadata, '$.namespace') IS NULL;
+```
+
+### 3. Staleness State Transitions
+Using the type-based windows from the memory-monitor contract:
+- Nodes stale > their window → transition to `state: review_pending`
+- Nodes in `review_pending` for >7 days → escalate to Kwame (Level 2)
+
+## Level 2 Escalations (Kwame Decision Required)
+1. **Nodes in `review_pending` >7 days** — Archive, refresh, or keep?
+2. **Orphan Nodes >90 days old** — Delete or Connect?
+3. **Potential Duplicate Nodes** — Same title or >70% overlap. Merge or Keep?
+4. **Conflicting Metadata** — Content suggests one tenant but metadata says another.
+
+## Logging
+Every Level 1 fix logged to `~/.hermes/logs/memory-fixer/YYYY-MM-DD.md`
+Every Level 2 escalation logged and delivered to Kwame.

mumuni-delegation-prose-contract.prose.md

@@ -6,7 +6,7 @@ description: >
   delegation, verification, and delivery. Defines when to delegate, which
   worker to use for what, how to handle failures, and the kanban board
   protocol. Enforces context-window discipline and separation of concerns.
-  Runs on Mumuni (lxc/114, hwepve, .123) via Hermes agent.
+  Runs on Mumuni (inside Abiba CT100, hwepve, .24) via Hermes agent (Pi + Hermes Zulip gateway).
 version: 1.0.0
 ---
 
@@ -20,7 +20,7 @@ version: 1.0.0
 ## Topology
 
 **Cluster:** 6 Proxmox nodes (ocupve, acerpve, minipve, amdpve, storepve, hwepve)
-**Manager:** Mumuni (lxc/114, hwepve, .123) via Hermes agent
+**Manager:** Mumuni (inside Abiba CT100, hwepve, .24) via Hermes agent
 **Workers:** 6 profiles, all running on the same agent — no separate hosts needed
 
 This contract is infrastructure-agnostic in terms of which nodes are used.
@@ -31,7 +31,7 @@ Workers execute tasks on whatever infrastructure they're given — SSH to .6,
 ## Why This Matters
 
 Without enforced delegation, the manager consumes the full iteration budget
-(60 calls) on single-turn tasks — SSH to 5 nodes, check each VM, read logs —
+(60 calls) on single-turn tasks — SSH to 6 nodes, check each VM, read logs —
 leaving no capacity for actual coordination. The result: context overflow
 (59K tokens in system prompt), iteration exhaustion, and degraded response
 quality. This contract exists because I blew through my budget checking
@@ -82,7 +82,7 @@ it asks the manager (via relay) — it doesn't go find it on its own.
 
 **This is a hard rule, not a recommendation.** Violating it produces the exact
 type of discrepancy the kanban pipeline exists to prevent: a review worker finds
-"5 nodes present" in the raw data but "5/5 online" in the report — even though
+"6 nodes present" in the raw data but "6/6 online" in the report — even though
 one of those nodes was unreachable. The report lied because it used data the
 raw data never provided.
 
@@ -137,7 +137,7 @@ delegate_task(
 ```
 delegate_task(
     tasks=[
-        {"goal": "Check all 5 Proxmox nodes for VM status", "context": "SSH to each node via 192.168.68.x, run 'qm list'"},
+        {"goal": "Check all 6 Proxmox nodes for VM status", "context": "SSH to each node via 192.168.68.x, run 'qm list'"},
         {"goal": "Check Docker container health on .7/.116/.17", "context": "SSH to each host, check container status"},
     ]
 )
@@ -191,7 +191,7 @@ Only verified results reach Kwame. Format per channel:
     {
       "lane_id": "devops-check",
       "worker": "syslog-devops",
-      "goal": "Check all 5 Proxmox nodes",
+      "goal": "Check all 6 Proxmox nodes",
       "status": "dispatched|completed|failed",
       "output_file": "/tmp/node-report.md"
     }

pm2-self-heal.prose.md

@@ -52,7 +52,7 @@ description: >
    - If status is "online" → pass, log restarts count
    - If status is "stopped" or "errored" → **DO NOT RESTART** — alert owner immediately
    - If restarts > 5 in last hour → alert owner with full diagnostics
-4. **Log results** — Create `[LEARN]` node in knowledge graph for any actions taken
+4. **Log results** — Append to `SyslogSolution/health-logs/pm2/{timestamp}.md` in Gitea (not knowledge graph — hard rule)
 5. **Alert** — Send Zulip DM to owner if escalation needed (do NOT run pm2 commands during alerting)
 6. **Wait 5 min** → repeat from step 1
 

proxmox-monitor.prose.md

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

scripts/agent-health-check.py

@@ -17,7 +17,7 @@ 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 (.123), koby (.129), koonimo (.114),
+    Fleet roster: tanko (.122), mumuni (.24, inside abiba CT100), koby (.129), koonimo (.114),
     abiba (.24).
 """
 

scripts/pct-run.sh

@@ -11,31 +11,33 @@ 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
-    # acerpve (192.168.68.9)
+    [118]=storepve  # jdownloader
-    [102]=acerpve   # adguard
+    # acerpve (192.168.68.9) — no CTs (bare metal GPU .8)
+    # hwepve (192.168.68.4)
+    [100]=hwepve    # abiba (was amdpve)
+    [105]=hwepve    # kagentz (was amdpve)
+    [114]=hwepve    # mumuni (was minipve)
     # 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
@@ -48,6 +50,7 @@ declare -A NODE_IPS=(
     [storepve]=192.168.68.6
     [acerpve]=192.168.68.9
     [ocupve]=192.168.68.5
+    [hwepve]=192.168.68.4
 )
 
 resolve_node() {

scripts/prose-ai-review.sh

@@ -46,17 +46,19 @@ You are a code reviewer for OpenProse infrastructure contracts in the Syslog Sol
 
 The infrastructure-control.prose.md contract is the canonical reference for the cluster topology:
 
-**Proxmox Cluster "Tabiri" (5 nodes):**
+**Proxmox Cluster "Tabiri" (6 nodes):**
-- amdpve (192.168.68.15): abiba, kagentz, tanko, tdunna, baggy, scottdenya
+- amdpve (192.168.68.15): tanko, tdunna, baggy, scottdenya
-- minipve (192.168.68.12): authentik, gitea, mumuni, syslog-api, jitsi
+- minipve (192.168.68.12): adguard, authentik, gitea, syslog-api, infisical-vault
-- storepve (192.168.68.6): docker-vm, ra-h-os, PBS, media, zulip
+- storepve (192.168.68.6): docker-vm, ra-h-os, PBS, media, jdownloader, zulip
-- acerpve (192.168.68.9): llm-gpu, adguard
+- acerpve (192.168.68.9): llm-gpu
 - ocupve (192.168.68.5): ocu-llm
+- hwepve (192.168.68.4): abiba, kagentz, mumuni
 
-**CT IDs (verified 2026-07-04 against PVE API):**
+**CT IDs (verified 2026-07-24 against PVE API):**
 100:abiba  102:adguard  104:authentik  105:kagentz  106:ra-h-os
 107:pbs    108:media    110:gitea      111:tdunna   112:tanko
 113:baggy  114:mumuni   115:scottdenya  116:syslog-api 117:zulip
+118:jdownloader  119:infisical-vault
 
 **NO CT 122, CT 123, or .19 exist in the cluster.**
 

scripts/swap-gpu-dense-model.sh

@@ -0,0 +1,91 @@
+#!/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}'"

zulip-health.prose.md

@@ -16,7 +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 (192.168.68.123, lxc/114 on hwepve since 2026-07-20), and Agent Zero Docker host (192.168.68.14)
+- **SSH access** to Tanko (192.168.68.122), Mumuni (192.168.68.24, inside Abiba CT100 on hwepve), and Agent Zero Docker host (192.168.68.14)
 - **PM2** on localhost for pi process management
 - **Network access** to `chat.sysloggh.net`, `localhost:9200`
 - **Write access** to `/root/zulip-health-monitor.log` and `/tmp/zulip-monitor-debounce`
@@ -182,13 +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 .123)
+### Step 3: Platform B — Hermes (Tanko .122, Mumuni .24)
 
 **B1: Gateway State**
 
 ```bash
 ssh root@192.168.68.122 "cat ~/.hermes/gateway_state.json"
-ssh root@192.168.68.123 "cat ~/.hermes/gateway_state.json"
+ssh root@192.168.68.24 "cat ~/.hermes/gateway_state.json"  # Mumuni inside Abiba CT100
 ```
 
 Check `platforms.zulip.state`: `connected` ✅ | `disconnected` ❌ | `error` ❌ | missing → not installed.

zulip-self-heal.prose.md

@@ -65,7 +65,7 @@ triggers:
 |------|----|------|---------|
 | Zulip server | 192.168.68.19 | root | Docker: `zulip-zulip-1` |
 | Abiba (pi) | localhost | root | PM2: `abiba-zulip` |
-| Mumuni | 192.168.68.123 | root | `hermes gateway restart` |
+| Mumuni | 192.168.68.24 (CT100 abiba) | root | `hermes gateway restart` |
 | Tanko | 192.168.68.122 | jerome | `PATH=$PATH:/home/jerome/.hermes/hermes-agent hermes gateway restart` |
 
 ## Debounce