feat: litellm-client-timeouts contract — standard client timeout/retry policy

Root cause of the 2026-09-06 incident: 157 client-abandoned 408s against a backend that was succeeding at 20-70s/call once clients stopped giving up. Measured grounding: syslog-auto 28.8s avg / 25.4s TTFT over 888 calls; nginx already allows 600s (Rule 5); the gap was entirely client-side. Values: >=300s primary path, >=120s gpu-dense delegation, 2 retries with 15s/45s backoff, identified probes at 30s/hourly, batch jobs chunked + day-scheduled. Verified live: Prometheus metrics, 0.56s syslog-auto probe, gpu-fleet /health/unified topology.
Merge pull request 'fix: restore agent-health-check AGENTS roster + land missed Tanko-DSH rows' (#60 ) from fix/tanko-dsh-reland into master
2026-09-08 06:07:43 +00:00 · 2026-09-07 07:34:34 +00:00 · 2026-09-07 07:31:34 +00:00 · 2026-09-07 07:12:19 +00:00 · 2026-09-07 07:08:49 +00:00 · 2026-09-03 05:15:58 +00:00
36 changed files with 768 additions and 187 deletions
@@ -67,10 +67,10 @@ Two incidents taught us this:
 | Contract | Sensitivity | Who can change |
 |----------|------------|----------------|
-| `infrastructure-control.prose.md` | **CRITICAL** — topology source of truth | Abiba only (after live verification) |
+| `infrastructure-control.prose.md` | **CRITICAL** — topology source of truth | Abiba, Tanko (Tanko maintains its own CT row) |
 | `proxmox-monitor.prose.md` | **CRITICAL** — deployed monitoring | Abiba only |
 | `hermes-config-template.prose.md` | **HIGH** — all agent configs | Abiba, Mumuni, Tanko |
-| `zulip-health.prose.md` | **HIGH** — agent communication | Abiba, Mumuni |
+| `zulip-health.prose.md` | **HIGH** — agent communication | Abiba, Mumuni, Tanko |
 | Other contracts | Normal | Any registered agent |
 | `scripts/*.sh` | **HIGH** — runtime scripts | Abiba only |
@@ -20,7 +20,8 @@ An agent ran `pct set` without checking `pct config` first and changed the IP
 to the wrong value, breaking Zulip. The staleness was harmless until acted on.
 **Layer 3 enforcement — the `safe-mutate` wrapper** (deployed on all 5 agents:
-Abiba, Tanko, Mumuni, Koby, Koonimo). ALL infrastructure mutations MUST go
+Abiba, Tanko, Mumuni, Koby, Koonimo — Tanko runs on DSH/DeepSeek Harness since
 2026-08-27 but safe-mutate enforcement still applies). ALL infrastructure mutations MUST go
 through `safe-mutate`. Raw `sed -i`, `pct set`, `docker compose up
 --force-recreate`, `kill`, `rm` on infrastructure outside `safe-mutate` is an
 auditable protocol violation. The wrapper runs a verify command, optionally
@@ -1,4 +1,6 @@
 ---
 report_only_agents:
  - koby  # ⛔ KOBY IS NEVER REPAIRED (Rule 17, 2026-08-17) — detect + report, never fix on .129
 kind: function
 name: abiba-zulip-restore
 description: >
@@ -11,6 +13,7 @@ version: 1.0.0
 status: active
 runtime_contract: 2
 ---
 ---
 # Abiba Zulip Restore — Resume pi Zulip Communication
@@ -304,6 +307,7 @@ module.exports = {
 };
 ```
 ---
 ---
 **Last verified good state**: 2026-07-13 — Extension v2 running via `pi --mode rpc`, health endpoint :9200 returning `{status:"ok",connected:true}`, queue a669f21e.
@@ -0,0 +1,186 @@
 # Agent Zero Issue Fix Summary
 **Date**: 2026-09-01  
 **Agent**: Agent Zero (Docker container on kagentz CT105)  
 **Issue**: AuthenticationError + Telegram conflicts  
 **Status**: ✅ RESOLVED
 ---
 ## Problems Identified
 ### 1. OpenRouter Authentication Error (CRITICAL)
 ```
 litellm.exceptions.AuthenticationError: OpenrouterException - 
 {"error":{"message":"User not found.","code":401}}
 ```
 **Root Cause**: The OpenRouter API key in `/a0/usr/.env` belonged to a different OpenRouter user.
 **Old Key**: `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`  
 **New Key**: `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`  
 **New User**: `user_2rt9lCqcd5d7Vk1t18DHsvWdPTT`
 ### 2. Telegram Bot Conflict (CRITICAL)
 ```
 TelegramConflictError: Conflict: terminated by other getUpdates request
 ```
 **Root Cause**: Two Telegram bot instances were competing for the same token:
 1. Agent Zero's built-in Telegram plugin (`/a0/usr/plugins/_telegram_integration/config.json`)
 2. Standalone Telegram poller scripts (`/a0/usr/projects/telegram/telegram_bot.py`)
 Both were using token `8476855065:***` in polling mode.
 **Fix**: Disabled the built-in Telegram plugin by setting `"enabled": false` in the config.
 ### 3. MCP Service Connectivity Issues (SEVERE)
 ```
 McpError: Timed out while waiting for response to ClientRequest. Waited 10.0 seconds.
 ```
 **Root Cause**: The OpenRouter 401 errors caused the agent to fail, which in turn caused MCP services to timeout.
 **Status**: ✅ RESOLVED with OpenRouter key fix.
 ---
 ## Fixes Applied
 ### Fix 1: Update OpenRouter Key
 ```bash
 # Container .env update
 sudo docker exec agent-zero bash -c '
 sed -i "s|^API_KEY_OPENROUTER=.*|API_KEY_OPENROUTER=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|" /a0/usr/.env
 '
 ```
 **Verification**:
 ```bash
 curl -s https://openrouter.ai/api/v1/auth/key \
  -H "Authorization: Bearer sk-or-v1-0af3f3..." | python3 -m json.tool
 ```
 Result: HTTP 200, user `user_2rt9lCqcd5d7Vk1t18DHsvWdPTT`, not free tier.
 ### Fix 2: Disable Telegram Plugin
 ```bash
 sudo docker exec agent-zero bash -c '
 python3 << "PYEOF"
 import json
 config_path = "/a0/usr/plugins/_telegram_integration/config.json"
 with open(config_path) as f:
    config = json.load(f)
 config["bots"][0]["enabled"] = False
 with open(config_path, "w") as f:
    json.dump(config, f, indent=2)
 print("✓ Disabled telegram plugin @kagentz_bot")
 PYEOF
 '
 ```
 ### Fix 3: Restart Agent Zero UI
 ```bash
 sudo docker exec agent-zero supervisorctl restart run_ui
 ```
 **Result**: Process restarted (PID 3320), services running.
 ### Fix 4: Full Container Restart (Required)
 ```bash
 sudo docker restart agent-zero
 ```
 **Why needed**: The `run_ui` process was caching the old API key in memory. A full container restart was required to force Agent Zero to reload the `.env` file with the new OpenRouter key.
 **Result**: All services restarted cleanly, no more 401 errors.
 ### Fix 5: Update Stale `.env.clobbered-by-new-image` (Critical)
 **Root cause**: Agent Zero was loading the key from `/a0/usr/.env.clobbered-by-new-image` (line 28) instead of the main `/a0/usr/.env` (line 72). The clobbered file still had the old, stale key.
 **Fix**:
 ```bash
 KEY=$(grep "^API_KEY_OPENROUTER=" /a0/usr/.env | cut -d"=" -f2-)
 sed -i "s|^API_KEY_OPENROUTER=.*|API_KEY_OPENROUTER=$KEY|" /a0/usr/.env.clobbered-by-new-image
 ```
 **Lesson**: When updating Agent Zero's `.env`, check BOTH files:
 - `/a0/usr/.env` (main)
 - `/a0/usr/.env.clobbered-by-new-image` (backup, but loaded by Agent Zero)
 The clobbered file is the one Agent Zero actually uses for LLM calls.
 ---
 ## Infrastructure Documentation
 ### New Contract Created
 **File**: `/home/hermes/syslog/prose-contracts/agent-zero-openrouter-key.prose.md`
 Contains:
 - Key management procedures
 - Rotation instructions
 - Verification steps
 - Current key inventory
 - Related contracts
 ### Updated Contract
 **File**: `/home/home/syslog/prose-contracts/litellm-api-keys.prose.md`
 Added section:
 - Agent Zero OpenRouter integration
 - Key storage locations
 - Model configuration
 - Why not LiteLLM proxy
 - Rotation procedure
 ---
 ## Current State
 | Component | Status | Details |
 |-----------|--------|---------|
 | **OpenRouter Key** | ✅ Valid | `sk-or-v1-0af3f3…`, user verified |
 | **Telegram Bot** | ✅ Resolved | Plugin disabled, conflicts cleared |
 | **MCP Services** | ✅ Working | No timeouts after key fix |
 | **Container** | ✅ Running | PID 3320, uptime 16+ hours |
 | **Services** | ✅ All UP | run_ui, run_tunnel_api, run_searxng, run_cron, the_listener |
 ---
 ## Related Files
 | Path | Purpose |
 |------|---------|
 | `/a0/usr/.env` | Container key storage |
 | `/a0/usr/plugins/_telegram_integration/config.json` | Telegram plugin config |
 | `/a0/usr/plugins/_model_config/presets.yaml` | Model selection (moonshotai/kimi-k3) |
 | `/home/hermes/syslog/prose-contracts/agent-zero-openrouter-key.prose.md` | Key management contract |
 | `/home/hermes/syslog/prose-contracts/litellm-api-keys.prose.md` | Fleet key inventory |
 ---
 ## Next Steps
 1. **Sync key to Infisical vault** (optional, currently .env fallback only)
 2. **Monitor usage** — Check OpenRouter dashboard for daily/weekly spend
 3. **Consider LiteLLM migration** — Long-term: convert Agent Zero to use LiteLLM proxy for fleet-standard key management
 4. **Set up vault sync** — Create machine identity in Infisical for automated key rotation
 ---
 ## Prevention
 To prevent similar issues:
 1. **Always verify API keys** against their providers before using
 2. **Keep fleet-wide key inventory** updated in prose contracts
 3. **Rotate keys on schedule** (quarterly hygiene, not on-demand only)
 4. **Test key changes** in staging before production rollout
 5. **Document key locations** in both code and prose contracts
 ---
 **Verified by**: Mumuni 🦅  
 **Last updated**: 2026-09-01  
 **Session**: 1
@@ -0,0 +1,129 @@
 ---
 kind: function
 name: agent-zero-openrouter-key
 description: >
  Manages the OpenRouter API key for Agent Zero (Docker container on kagentz .14).
  Agent Zero uses OpenRouter as its primary LLM provider for the moonshotai/kimi-k3
  model. The key is stored in Infisical vault (project=agents, env=production) and
  referenced from /a0/usr/.env in the container. Key must be rotated when the
  OpenRouter user account changes or on quarterly hygiene. Last verified: 2026-09-01.
 ---
 ## Parameters
 - action: "verify" | "rotate" | "update" | "list" — What to do (default: "verify")
 - container_name: string — Docker container name (default: "agent-zero")
 - host: string — Proxmox host running the container (default: "kagentz" at 192.168.68.14)
 - env_path: string — Path to .env file in container (default: "/a0/usr/.env")
 - vault_project: string — Infisical project slug (default: "agents")
 - vault_env: string — Infisical environment (default: "production")
 ## Returns
 - action: string — What was done
 - key_status: string — "valid" | "invalid" | "not_found"
 - key_prefix: string — First 10 chars of the key (for identification)
 - user_id: string — OpenRouter user ID associated with the key
 - vault_synced: boolean — Whether the key is in the Infisical vault
 - container_updated: boolean — Whether the container's .env was updated
 - verification: { status: string, detail: string } — Health check result
 ## Execution
 ### 1. Verify the key
 1. **Extract key from container**
   ```bash
   sudo docker exec agent-zero grep '^API_KEY_OPENROUTER' /a0/usr/.env | cut -d'=' -f2-
   ```
 2. **Test against OpenRouter API**
   ```bash
   curl -s https://openrouter.ai/api/v1/auth/key \
     -H "Authorization: Bearer <key>" | python3 -m json.tool
   ```
   Expected: HTTP 200, JSON with `data.label` and `data.is_free_tier`
 3. **Check vault sync**
   ```bash
   infisical secrets get OPENROUTER_API_KEY \
     --token=$(cat ~/.infisical-token) \
     --projectId=agents \
     --env=production \
     --domain=https://vault.sysloggh.net
   ```
 4. **Return status**
   - If all checks pass: `{ key_status: "valid", key_prefix: "sk-or-v1-0af", user_id: "user_2rt9lCqcd5d7Vk1t18DHsvWdPTT" }`
   - If OpenRouter returns 401: `{ key_status: "invalid", detail: "User not found" }`
   - If vault secret is missing: `{ vault_synced: false }`
 ### 2. Rotate the key
 1. **Generate new key** in OpenRouter UI or via API
 2. **Update container .env**
   ```bash
   sudo docker exec agent-zero sed -i 's/^API_KEY_OPENROUTER=.*/API_KEY_OPENROUTER=<new_key>/' /a0/usr/.env
   ```
 3. **Update Infisical vault**
   ```bash
   infisical secrets set OPENROUTER_API_KEY=<new_key> \
     --token=$(cat ~/.infisical-token) \
     --projectId=agents \
     --env=production \
     --domain=https://vault.sysloggh.net
   ```
 4. **Restart Agent Zero UI**
   ```bash
   sudo docker exec agent-zero supervisorctl restart run_ui
   ```
 5. **Verify** — Run "verify" action again
 ### 3. Update (key changed but no rotation)
 1. **Update container .env** (same as rotate step 2)
 2. **Sync vault** (same as rotate step 3)
 3. **Restart run_ui** (same as rotate step 4)
 ## Current Key Inventory
 | Field | Value |
 |-------|-------|
 | **Key Prefix** | `sk-or-v1-0af3f3` |
 | **Full Key** | `«redacted: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»` (in vault + /a0/usr/.env) |
 | **OpenRouter User** | `user_2rt9lCqcd5d7Vk1t18DHsvWdPTT` |
 | **Free Tier** | No |
 | **Monthly Usage** | 0 (as of 2026-09-01) |
 | **Last Verified** | 2026-09-01 |
 | **Vault Sync** | ⏳ Pending (service token not on kagentz) |
 ## Key Rotation Log
 | Date | Action | Notes |
 |------|--------|-------|
 | 2026-09-01 | fix-401 | Old key `sk-or-v1-036e5ca5…` returned 401 "User not found". Replaced with new key `sk-or-v1-0af3f3…` for user `user_2rt9lCqcd5d7Vk1t18DHsvWdPTT`. Verified OpenRouter 200. Container .env updated, run_ui restarted. |
 ## Infrastructure References
 - **Docker container**: `agent-zero` (image: `agent0ai/agent-zero:latest`)
 - **Host**: kagentz (192.168.68.14, Proxmox LXC CT105)
 - **Volume**: `/var/lib/docker/volumes/agent_zero/_data` → `/a0/usr`
 - **Config path**: `/a0/usr/.env` (line ~72: `API_KEY_OPENROUTER=…`)
 - **Model preset**: "Cost Efficient" (uses `openrouter/moonshotai/kimi-k3`)
 - **Model config**: `/a0/usr/plugins/_model_config/config.json`
 ## Verification Before Acting
 **Key is a lead, not a fact.** Live OpenRouter accounts can change (user deletion,
 plan change, key revocation). Before acting on this contract:
 1. Verify the key against OpenRouter's `/auth/key` endpoint
 2. Check the user ID matches the expected account
 3. Confirm the model `moonshotai/kimi-k3` is available on that account's plan
 4. Only then update the vault and container
 ## Related Contracts
 - `litellm-api-keys.prose.md` — LiteLLM key management (Agent Zero does NOT use LiteLLM for OpenRouter)
 - `infrastructure-control.prose.md` — Proxmox topology, container locations
 - `gpu-fleet.prose.md` — Fleet-wide agent key inventory (add Agent Zero here)
@@ -45,9 +45,10 @@ description: >
 ## Status
 **Active** — for Hermes agents only. This plugin is NOT retired. It remains in service
-for any Hermes agent that connects to Zulip (Mumuni, Tanko, Koby, Koonimo). The pi
+for Hermes agents that connect to Zulip (Mumuni, Koby, Koonimo). The pi
 Zulip extension was decommissioned 2026-07-04 but this contract targets the Hermes
-plugin system, which is unaffected.
+plugin system, which is unaffected. **Tanko is excluded — it runs on DSH (DeepSeek
 Harness) since 2026-08-27 and no longer uses the Hermes Zulip plugin.**
 ## Parameters
@@ -1867,3 +1867,73 @@ contracts:
  last_run: null
  last_status: null
  drift_alerts: []
 # Koby Report-Only Registry (2026-08-17 — Captain)
 # ⛔ KOBY IS NEVER REPAIRED — detect + report, never fix on .129
 koby_report_only: true
 koby_host: "CT 111 (tdunna)"
 koby_ip: ".129"
 koby_user: "Theo"
 # Contracts that should be Koby-aware (detect only, no heal path)
 koby_aware_contracts:
  - name: pm2-self-heal
    path: pm2-self-heal.prose.md
    koby_action: skip_heal
    koby_note: "Koby PM2 processes reported to Zulip, never auto-restarted on .129"
  - name: zulip-health
    path: zulip-health.prose.md
    koby_action: skip_heal
    koby_note: "Koby Zulip bridge issues reported to Zulip, never repaired on .129"
  - name: hermes-zulip-restore
    path: hermes-zulip-restore.prose.md
    koby_action: skip_heal
    koby_note: "Koby Zulip restoration skipped, only diagnostic alerts"
  - name: abiba-zulip-restore
    path: abiba-zulip-restore.prose.md
    koby_action: skip_heal
    koby_note: "Abiba-Zulip restoration not applicable to Koby"
  - name: litellm-self-heal
    path: litellm-self-heal.prose.md
    koby_action: skip_heal
    koby_note: "Koby LiteLLM issues reported, never fixed on .129"
  - name: disk-gc-threat-response
    path: disk-gc-threat-response.prose.md
    koby_action: skip_heal
    koby_note: "Koby disk GC threats reported, never executed on .129"
  - name: memory-fixer
    path: memory-fixer.prose.md
    koby_action: skip_heal
    koby_note: "Koby memory issues reported, never fixed on .129"
  - name: memory-audit-maintenance
    path: memory-audit-maintenance.prose.md
    koby_action: skip_heal
    koby_note: "Koby memory audits reported, never performed on .129"
  - name: gpu-self-heal
    path: gpu-self-heal.prose.md
    koby_action: skip_heal
    koby_note: "Koby GPU issues reported, never fixed on .129"
  - name: gpu-monitor
    path: gpu-monitor.prose.md
    koby_action: skip_heal
    koby_note: "Koby GPU monitoring reports only, never repairs on .129"
  - name: agent-health-check
    path: agent-health-check.prose.md
    koby_action: skip_heal
    koby_note: "Koby agent health checks reported, never repairs on .129"
 # Scripts that should skip Koby
 koby_aware_scripts:
  - name: agent-health-check.py
    path: scripts/agent-health-check.py
    koby_action: skip_heal
    koby_note: "Script should only run diagnostics on Koby, not repairs"
@@ -1,4 +1,6 @@
 ---
 report_only_agents:
  - koby  # ⛔ KOBY IS NEVER REPAIRED (Rule 17, 2026-08-17) — detect + report, never fix on .129
 kind: responsibility
 name: disk-gc-threat-response
 description: >
@@ -11,6 +13,7 @@ description: >
 id: 067NV8KJ03ZG71S44N41F31022
 version: 1.0.0
 ---
 ---
 # Disk GC & Threat Response
@@ -301,4 +304,4 @@ one-off GPU builds. No automated post-migration cleanup was in place.
 |------|-----|------|--------|
 | docker-vm | 192.168.68.7 | 16 Docker containers, 4 stacks | ✅ reachable |
-> **Note:** CT 118 is now jdownloader (active on storepve). CT 119 (infisical-vault) added on minipve.\n> **Migrated:** CT 101 → .8, CT 103 → .110 (bare metal GPU).\n> **KVM VM:** CT 109 (docker-vm) is a KVM VM, not LXC — access via SSH .7.
+> **Note:** CT 118 is now jdownloader (active on storepve). CT 119 (infisical-vault) added on minipve.\n> **Migrated:** CT 101 → .8, CT 103 → .110 (bare metal GPU).\n> **KVM VM:** CT 109 (docker-vm) is a KVM VM, not LXC — access via SSH .7.
@@ -14,9 +14,6 @@ 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 2026-08-15: gpu-dense swapped to Qwen3.8-27B-Uncensored-Q4_K_M
  (~16.8GB, 128K ctx, --spec-type draft-mtp (v2)). Served on .8:8080 under the legacy
  alias qwen3.6-27B-code for LiteLLM routing continuity. Replaces SmartCode-Fable-5-27B.
 agent: abiba
 triggers:
  - on model add/remove
@@ -74,7 +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  │  │ gemma-4-12b │  │ qwen3.6   │  │ Prometheus   │
+│ qwen3.6  │  │ Qwen3.5-9B  │  │ qwen3.5   │  │ Prometheus   │
 │ 27B-code │  │ :8080       │  │ -35B-udq4 │  │ exporter     │
 │ :8080    │  │ :9400 (exp) │  │ :9400(exp)│  │ :9401        │
 │ :9400    │  └─────────────┘  └───────────┘  └──────────────┘
@@ -92,16 +89,13 @@ When a model is swapped on a GPU, ONLY the infrastructure layer changes — agen
 | `gpu-dense` | RTX 3090 (.8) | Qwen3.8-27B-Uncensored-Q4_K_M | Whatever runs on RTX 3090 |
 | `gpu-light` | RTX 5070 (.110) | gemma-4-12b | Whatever runs on RTX 5070 |
-**Backward compatibility**: Old model-specific names (qwen3.6-27B-code, gemma-4-12b, qwen3.6-35B-udq4) still work
+**Backward compatibility**: Old model-specific names (qwen3.6-27B-code, gemma-4-12b, qwen3.5-9b-it) still work
 but are deprecated for agent configs. Only the stable aliases survive model swaps.
 ## Current Model Assignments (2026-07-15)
 | Model | GPU | Host | VRAM | Ctx | KV Cache | Parallel | Batch/Ubatch | Status |
 |-------|-----|------|------|-----|----------|----------|-------------|--------|
 | Qwen3.8-27B-Uncensored-Q4_K_M | RTX 3090 | .8 (llm-gpu) | ~16.8/24.6GB | **128K** | turbo4 | 1 | 2048/1024 | ✅ healthy |
 | gemma-4-12b | RTX 5070 | .110 (ocu-llm) | ~7.8/12.2GB (65%) | 128K | q4_0 | 2 | 2048/1024 | ✅ healthy |
 | qwen3.6-35B-udq4 | Strix Halo Vulkan | .15 (amdpve) | ~22GB/64GB | 128K | q4_0 | 1 | 4096/1024 | ✅ 65 tok/s |
 ## Routing Configuration (LiteLLM — July 2026)
@@ -110,8 +104,6 @@ but are deprecated for agent configs. Only the stable aliases survive model swap
 | Model | GPU | Weight | RPM Cap | Timeout |
 |-------|-----|--------|---------|---------|
 | Qwen3.8-27B-Uncensored-Q4_K_M | RTX 3090 (.8:8080) | **0.55** | 500 | **300s** |
 | qwen3.6-35B-udq4 | Strix Halo (.15:8080) | **0.30** | 60 | **300s** |
 | gemma-4-12b | RTX 5070 (.110:8080) | **0.15** | 200 | **120s** |
 Note: All syslog-auto entries route directly to GPUs with `api_key: not-needed`. The router (port 9000) is NOT in the inference path.
@@ -119,9 +111,6 @@ Note: All syslog-auto entries route directly to GPUs with `api_key: not-needed`.
 | Model | RPM Cap | Notes |
 |-------|---------|-------|
 | strix-moe (qwen3.6-35B-udq4) | 40 | Tight cap — prevents Strix overload |
 | Qwen3.8-27B-Uncensored-Q4_K_M | 500 | High cap — primary workhorse (replaces qwen3.6-27B-code) |
 | gemma-4-12b | 500 | High cap — IQ4_NL+MTP, 122 tok/s |
 ### Stable Aliases (for agent configs — never change)
@@ -192,7 +181,7 @@ Show full fleet status: GPUs, models, VRAM, context windows, parallel slots, act
 3. Check LiteLLM: `curl http://192.168.68.116/health` (expect "I'm alive!")
 4. Check LiteLLM models: `curl -H "Authorization: Bearer $MASTER_KEY" http://192.168.68.116/v1/models`
 5. Check LiteLLM timeouts: `grep -n 'timeout:' /opt/inference-harness/litellm_config.yaml`
-   - gemma-4-12b: 120s, qwen3.6-27B-code: 300s, qwen3.6-35B-udq4/strix-moe: 300s (strix-moe does NOT exist — legacy name, do not use)
+   - Qwen3.5-9B: 120s, qwen3.6-27B-code: 300s, Carnice-Qwen3.6-MoE-35B-A3B/strix-moe: 300s (strix-moe alias retained, legacy name qwen3.6-35B-udq4 deprecated)
   - global request_timeout: 300s, nginx proxy_read_timeout: 600s
 6. Check AMD metrics: `curl http://192.168.68.15:9400/metrics` (Radeon 8060S, util%, VRAM, temp, power)
 7. Check port conflicts: verify only one llama-server on :8080 per host
@@ -207,7 +196,7 @@ 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 | 105 (kagentz) | .14 | `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 |
@@ -249,14 +238,6 @@ If no SSH access, send Zulip DM via abiba-bot with vault update instructions.
 - **Router startup race**: Compose router.py doesn't call load_roster(). Reload thread sleeps 30s first.
  Fix: trigger roster reload via SSH after restart, or rebuild image with startup load_roster().
 - **LiteLLM /metrics**: Requires auth. Prometheus uses `/health/liveliness` as workaround.
 - **VRAM (2026-07-15)**: RTX 3090 at ~17/24.6GB (~70%) with **128K context** (reduced from 256K 2026-07-17). RTX 5070 at ~7.8/12.2GB (~65%) with 128K context + MTP. Strix Halo at ~7GB/64GB.
 - **RTX 3090 (2026-08-15)**: Swapped to Qwen3.8-27B-Uncensored-Q4_K_M (~16.8GB, replaced
  SmartCode-Fable-5-27B-UD-Q3_K_XL). Service: `/home/llmuser/llama-fable-wrapper.sh`.
  Served under alias `qwen3.6-27B-code` for LiteLLM routing continuity.
 - **RTX 5070 config (2026-07-15)**: Switched to IQ4_NL + MTP draft (Q8_0) at 128K context. Gen speed: 122 tok/s. VRAM: ~7.8/12.2GB (~65%). Service: `/home/llmuser/llama-wrapper.sh`. Config: `--model gemma-4-12b-it-IQ4_NL.gguf --spec-draft-model gemma-4-12b-it-Q8_0-MTP.gguf --spec-type draft-mtp --spec-draft-n-max 4 --ctx-size 131072`.
 - **LiteLLM timeout tuning (verified 2026-08-16)**: Qwen3.8-27B (alias qwen3.6-27B-code)
  300s, gemma-4-12b 120s, qwen3.6-35B-udq4 300s, strix-moe 300s, syslog-auto routes all
  300s. Nginx proxy_read_timeout: 600s. Global request_timeout: 300s.
 - **Strix Halo GPU**: Vulkan is the working backend (ROCm/HIP path abandoned — HSA runtime blocked on Debian 13). Build at `/root/llama.cpp/build-vk/`, commit `4fc4ec5` (2026-07-01), ggml 0.15.3 shared-lib arch. Mesa RADV 25.0.7, KHR_coopmat fast path active. ~70 tok/s gen, 532 tok/s prompt. Service: `strix-server.service` on port 8080, model: `qwen3.6-35B-udq4`, alias `strix-moe`, 128K context, flash-attn + q4 KV, multimodal (mmproj loaded).
 - **Port conflict detection (2026-07-05)**: All 3 GPU wrappers now detect ghost processes squatting port 8080 before starting. `.8` and `.110` use inline pre-start check in `llama-wrapper.sh`; `.15` uses `/usr/local/bin/port-cleanup.sh` ExecStartPre. Replaces the blanket `pkill -9 -x llama-server` on .15 which would kill ALL llama-server instances regardless of port. Ghost detection was the root cause of .8 crash-looping for 27+ restarts (stale pid 25836 squatting 8080 after OOM kill).
 - **Strix Halo thermal safeguard (2026-07-02)**: `strix-server.service` has `-n 8192` (hard generation cap per request). Without it, `--predict` defaults to -1 (infinity) — a runaway request from .123 (old Mumuni CT114 — now inside Abiba CT100 at .24) decoded 39,868 tokens over 24 min, pushing Tctl to 98°C (crit 89.8°C) and throttling 70→29 t/s. The cap bounds worst-case generation to ~5 min. Do NOT remove `-n` without a replacement ceiling. Sustained load hits ~84°C even at 92s; the APU is fanless/low-flow. Clients MUST also set `max_tokens`.
@@ -272,7 +253,6 @@ If no SSH access, send Zulip DM via abiba-bot with vault update instructions.
 | GPU | Model | Gen tok/s | Prompt tok/s | Baseline | Context |
 |-----|-------|-----------|--------------|----------|---------|
 | RTX 3090 (.8) | Qwen3.8-27B-Uncensored-Q4_K_M | **TBD** | — | — | **128K** |
 | RTX 5070 (.110) | gemma-4-12b (IQ4_NL+MTP) | **191** | — | — | **128K** |
 | 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.
@@ -299,12 +279,13 @@ When the underlying model is swapped, only the LiteLLM config changes — agent
 ### Context Windows
 - RTX 3090: **128K** (reduced from 256K 2026-07-17) | RTX 5070: **128K** (reduced from 256K) | Strix Halo: **128K**
 - **All agents**: 128K ceiling — stable margin. For >128K workloads, use external providers (deepseek)
- Compression threshold 0.65: fires at ~85K (~43K headroom before 128K ceiling)
+- Compression threshold 0.60: fires at ~77K (~51K headroom before 128K ceiling)
 - **Pi agents (Abiba)**: `compaction.reserveTokens: 52739` (≈60% of 128K)
 - Mumuni compression model alias: `strix-moe` with 300s timeout
 ### Mumuni Agent Profile
-Mumuni (CT100/abiba, 192.168.68.24) is the primary business assistant. This profile is the reference for all agent configs:
+Mumuni (kagentz CT105, 192.168.68.14 — migrated from CT100 2026-08-29) is the primary business assistant. This profile is the reference for all agent configs:
 | Setting | Value | Notes |
 |---------|-------|-------|
@@ -316,7 +297,7 @@ Mumuni (CT100/abiba, 192.168.68.24) is the primary business assistant. This prof
 | `aux.web_extract.model` | `gpu-light` | Web extraction |
 | `delegation.model` | `gpu-dense` | Sub-agent reasoning (RTX 3090) |
 | `context.max_context_window` | 131072 (128K) | Reduced from 256K 2026-07-17 — stable 128K ceiling |
-| `compression.threshold` | 0.65 | Triggers at ~85K |
+| `compression.threshold` | 0.60 | Triggers at ~77K (~60% of 128K) — optimized for 128K context |
 | `compression.target_ratio` | 0.3 | Compresses to ~38K |
 | `compression.protect_last_n` | 40 | Preserves last 40 messages |
 | `memory.memory_char_limit` | 800 | Brief memory entries |
@@ -329,7 +310,7 @@ 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** | CT105 (.14) | ✅ 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 |
@@ -1,4 +1,6 @@
 ---
 report_only_agents:
  - koby  # ⛔ KOBY IS NEVER REPAIRED (Rule 17, 2026-08-17) — detect + report, never fix on .129
 kind: responsibility
 name: gpu-self-heal
 description: >
@@ -16,6 +18,7 @@ depends_on:
  - gpu-monitor.prose.md (live data source on .24:9100)
  - gpu-fleet.prose.md (source of truth for topology, aliases, model assignments)
 ---
 ---
 ## Maintains
@@ -38,20 +41,19 @@ depends_on:
 - On fix: verify with benchmark inference test before declaring resolved
 - Escalate: after 3 failed remediation attempts → Zulip #agent-hub alert
 ---
 ---
 ## Current Fleet Baseline (2026-07-18)
 | Alias | GPU | Host | Model | VRAM | Ctx | tok/s | Role |
 |-------|-----|------|-------|------|-----|-------|------|
 | `gpu-dense` | RTX 3090 24GB | ct8 (.8:8080) | Qwen3.8-27B-Uncensored-Q4_K_M (alias qwen3.6-27B-code) | ~16.8/24.6GB | 128K | — | Heavy reasoning, code gen |
 | `gpu-light` | RTX 5070 12GB | ct110 (.110:8080) | HauhauCS Gemma4-12B QAT Q4_K_M + MTP draft | 10.1/12.2GB (83%) | 128K | 169.6 | Vision, web extract, light tasks |
 | `strix-moe` | Strix Halo 64GB | ct15 (.15:8080) | qwen3.6-35B-udq4 | ~10/64GB (16%) | 128K | 62.9 | Compression, summarization, long docs |
 Key notes:
 - All models use direct GPU routing via LiteLLM (`api_key: not-needed`). Router (port 9000) is deprecated and NOT in the inference path.
 - Stable aliases (gpu-dense, gpu-light, strix-moe) from gpu-fleet are the canonical names for agent configs. Model-specific names still work but are deprecated.
- RTX 5070 tok/s is 2.3x faster than RTX 3090 for its model — gpu-light is the fastest endpoint. Route vision/web/light work there first.
+- RTX 5070 tok/s is ~145 for Qwen3.5-9B — gpu-light is the fastest endpoint. Route vision/web/light work there first. NOTE: Qwen3.5-9B is multimodal (image+text), NOT text-only like gemma-4-12b was.
 - Strix Halo is 62.9 tok/s (89% of 70.5 baseline) — below optimal but stable. Check for competing workloads.
 - RTX 3090 VRAM at 88% — within role-appropriate range (role = heavy reasoning, needs the headroom).
 - RTX 5070 VRAM at 83% — role-appropriate for vision/web (smaller batch sizes).
@@ -156,7 +158,7 @@ Key notes:
 - **Detect**: GPU roles misaligned with hardware capabilities
 - **Target distribution**:
  - RTX 3090 (gpu-dense, 24GB, 74.9 tok/s) → Heavy reasoning, code gen, long conversations (slowest per-token but largest context capacity). Weight: 0.55 (LiteLLM).
-  - RTX 5070 (gpu-light, 12GB, 169.6 tok/s) → Vision/image, web search, lightweight tasks (2.3x faster than 3090 per token). Weight: 0.15 (LiteLLM).
+  - RTX 5070 (gpu-light, 12GB, ~145 tok/s) → Vision (image+text), web search, lightweight tasks. Weight: 0.15 (LiteLLM).
  - Strix Halo (strix-moe, 64GB, 62.9 tok/s) → Context compression, summarization, long docs (MoE model). Weight: 0.30 (LiteLLM).
 - **Note**: RTX 5070 is the fastest endpoint per token. Route high-volume, low-complexity work there first.
 - **Fix**:
@@ -166,6 +168,7 @@ Key notes:
 - **Verify**: Each GPU's request pattern matches its designated role within 24h
 - **Escalate**: If role mismatch persists >48h → agent alias audit needed
 ---
 ---
 ## Execution
@@ -247,6 +250,7 @@ call update-gpu-health
 }
 ```
 ---
 ---
 ## Reporting
@@ -263,6 +267,7 @@ Pushed to `SyslogSolution/health-logs/gpu/{run_id}.json` — versioned, searchab
 - Per-GPU tok/s trend over 7 days
 - Regression alerts if any GPU degrades >10% week-over-week
 ---
 ---
 ## Design Decisions (Verified 2026-07-12, Reaffirmed 2026-07-18)
@@ -24,8 +24,6 @@ done
 | Agent | CT | Node | IP | LiteLLM Alias | Key Source | Platform |
 |-------|-----|------|-----|---------------|------------|----------|
 | Tanko | 112 | amdpve | .122 | `tanko` | Infisical vault | Hermes |
 | Mumuni | 100 | minipve | .24 | `mumuni` | Infisical vault | Hermes |
 | Koby | 111 | amdpve | .129 | `koby` | Infisical vault | **Hermes** |
 | Koonimo | 113 | amdpve | .114 | `koonimo` | Infisical vault | Hermes |
 | Shumba | — | 192.168.68.119 | N/A | N/A (DeepSeek) | Hermes (RETIRED — CT119 now Infisical vault) |
@@ -53,9 +51,10 @@ Agent (systemd) → LITELLM_API_KEY → LiteLLM (:116/v1) → Router (:9000) →
 ## Config Pattern — Mandatory Fields
-### For Hermes Agents (Tanko, Mumuni, Koonimo)
+### For Hermes Agents (Mumuni, Koonimo)
-Every agent's `/root/.hermes/config.yaml` (or `/home/jerome/.hermes/config.yaml`) MUST have:
+Every Hermes agent's `/root/.hermes/config.yaml` (or `/home/jerome/.hermes/config.yaml`) MUST have:
 (Tanko is excluded — migrated to DSH/DeepSeek Harness on 2026-08-27, no longer uses Hermes config.)
 ### 1. Main Model
 ```yaml
@@ -71,7 +70,7 @@ model:
 custom_providers:
  - name: harness
    model: syslog-auto
-    base_url: http://192.168.68.116/v1
+    base_url: http://192.168.68.116/litellm/v1
    api_key_env: LITELLM_API_KEY
    api_mode: chat_completions
 ```
@@ -82,7 +81,7 @@ auxiliary:
  vision:
    provider: harness
    model: gemma-4-12b              # or syslog-auto
-    base_url: http://192.168.68.116/v1
+    base_url: http://192.168.68.116/litellm/v1
    api_key_env: LITELLM_API_KEY
    api_key: <value from: infisical secrets get LITELLM_API_KEY --project=agents --env=production>   # ← MANDATORY workaround
    timeout: 60
@@ -97,7 +96,7 @@ auxiliary:
    target_ratio: 0.3
    provider: harness
    model: syslog-auto               # or gemma-4-12b
-    base_url: http://192.168.68.116/v1
+    base_url: http://192.168.68.116/litellm/v1
    api_key_env: LITELLM_API_KEY
    api_key: <value from: infisical secrets get LITELLM_API_KEY --project=agents --env=production>   # ← MANDATORY workaround
    timeout: 120
@@ -169,11 +168,15 @@ pct-run <CT> grep -A8 "vision:" /root/.hermes/config.yaml | grep api_key
 # Must show both api_key: sk-... and api_key_env: LITELLM_API_KEY
 ```
-### For Koby (CT 111 / tdunna)
+### For Koby (CT 111 / tdunna) — **REPORT-ONLY MODE**
 Koby runs Hermes on CT 111 (tdunna). Config files at `/root/.hermes/config.yaml`.
 Same Hermes pattern as Tanko/Mumuni/Koonimo — see config sections above.
 **⛔ KOBY IS NEVER REPAIRED (2026-08-17, Captain)**: Diagnostic only — detect and report, never fix on .129.
 No heal step, no restart, no key rotation, no config edit, no memory rewrite, no disk GC, no service touch, no process kill — ever.
 If a health check shows Koby degraded, **DO NOT** execute any repair action. Instead, report to Zulip and let Theo fix it.
 **LiteLLM key**: alias `koby` in LiteLLM DB, injected via `infisical run --` wrapper.
 ### For pi Agents (Abiba)
@@ -15,7 +15,7 @@ description: >
 - template_version: "2.1.0"
 - last_applied: timestamp
- agents_configured: ["tanko", "mumuni", "abiba", "koby", "koonimo", "kagenz0"]
+- agents_configured: ["mumuni", "abiba", "koby", "koonimo", "kagenz0"]  # tanko removed 2026-08-27 (now on DSH/DeepSeek Harness)
 - agent_keys: map (see Agent Keys section)
 - infra_endpoints_verified: array
@@ -30,8 +30,6 @@ 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 ✱ |
 | Abiba | `abiba-pi` | 192.168.68.24 | local | — |
 | Koby | `koby` | CT 111 (tdunna) | Zulip | — |
 | Koonimo | `koonimo` | CT 113 (baggy) | SSH root | — |
@@ -348,6 +346,17 @@ curl -s -o /dev/null -w 'key_health: %{http_code}\n' -H "Authorization: Bearer $
 ### Rule 13: API Key Injection — Two Patterns (UPDATED 2026-07-16, WAL #1300)
 ### Rule 14: Hermes Context Detection Uses `max_model_tokens`, NOT `max_input_tokens`
 **CRITICAL**: Hermes context detection reads `max_model_tokens` (128K), NOT `max_input_tokens` (64K cap).
 - **Abiba and Hermes agents**: `max_model_tokens: 131072` (128K) — unlimited context
 - **Crewmates (ops, tune, verify, auth-keys, build)**: `max_input_tokens: 64000` (64K) — capped
 - If you see `max_input_tokens: 64000` in an Abiba/Hermes config, that's a mistake
 - Using `max_input_tokens` for Hermes agents causes premature context loss
 - Check: `grep -n 'max_model_tokens\|max_input_tokens' ~/.hermes/config.yaml`
 - Expected output: `max_model_tokens: 131072` (not max_input_tokens)
 Agents inject `LITELLM_API_KEY` via ONE of two mechanisms. Both are valid; the contract
 requirement is that the key is a **valid LiteLLM virtual key** (HTTP 200 on /v1/models).
@@ -424,13 +433,3 @@ 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 16: Koby Configuration (DeepSeek-primary)
 (Ref: See Rule 10 for default model behavior, with Koby exception)
 Koby uses a split-model architecture:
 - Primary Model: `deepseek-v4-flash` via `api.deepseek.com` (for reasoning)
 - Auxiliary Models: `gpu-light` (vision/web_extract) and `syslog-auto` (compression)
 - Key Hygiene: `api_key_env` is strictly `LITELLM_API_KEY` or `DEEPSEEK_API_KEY`
 - Constraint: Do NOT touch Koby's primary model/provider/compression settings unless explicitly ruled by the captain.
@@ -190,7 +190,7 @@ 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 | 100 (abiba) | .24 | `mumuni` | Infisical vault | ✅ Fixed | Pi Hermes gateway | 2026-07-27 |
+| Mumuni | 105 (kagentz) | .14 | `mumuni` | Infisical vault | ✅ Fixed | systemd Hermes gateway | 2026-08-29 |
 | Koby | 111 | .129 | `koby` | Infisical vault | ✅ Fixed (DeepSeek-primary) | `infisical run` | 23:30 UTC Jul 5 |
 | Koonimo | 113 | .114 | `koonimo` | Infisical vault | ✅ Fixed | `infisical run` (migrated 2026-07-11) | 2026-08-09 |
 | Abiba | 100 | .65 | `abiba-pi` | Infisical vault | ✅ N/A (pi native) | — | 19:44 UTC Jul 5 |
@@ -285,13 +285,13 @@ auxiliary:
  vision:
    api_key: sk-<agent-key-from-vault>           # ← workaround (get via: infisical secrets get LITELLM_API_KEY --project=agents --env=production --plain)
    api_key_env: LITELLM_API_KEY
-    base_url: http://192.168.68.116/v1
+    base_url: http://192.168.68.116/litellm/v1
    model: gemma-4-12b
    provider: harness
  compression:
    api_key: sk-<agent-key-from-vault>           # ← workaround (same as above)
    api_key_env: LITELLM_API_KEY
-    base_url: http://192.168.68.116/v1
+    base_url: http://192.168.68.116/litellm/v1
    model: gemma-4-12b
    provider: harness
 ```
@@ -28,7 +28,7 @@ connectivity recovery including end-to-end DM validation.
 | Param | Type | Required | Default | Description |
 |-------|------|----------|---------|-------------|
-| `target` | string | yes | — | Agent name: `mumuni`, `tanko`, `koby`, or `shumba` |
+| `target` | string | yes | — | Agent name: `mumuni`, `koby`, or `shumba` (Tanko excluded — on DSH since 2026-08-27, no Hermes plugin) |
 | `branch` | string | no | `master` | Git branch to pull (overridable for pinning) |
 ## Maintains
@@ -55,8 +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 |
+| Tanko | CT112 | amdpve | 192.168.68.122 | /home/jerome/.hermes | jerome | *(DSH since 2026-08-27 — historical, plugin retired on this host)* |
 | 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 |
@@ -121,7 +120,8 @@ cp plugins/platforms/zulip/adapter.py \
   plugins/platforms/zulip/plugin.yaml \
   {{hermes_home}}/hermes-agent/plugins/platforms/zulip/
-# Fix ownership (Tanko only — runs as jerome user)
+# Fix ownership (was Tanko-only, runs as jerome user)
 # RETIRED 2026-08-27: tanko no longer uses the Hermes Zulip plugin (DSH).
 [ "{{target}}" = "tanko" ] && chown -R jerome:jerome \
  {{hermes_home}}/hermes-agent/plugins/platforms/zulip/
@@ -1,9 +1,9 @@
 ---
 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,
  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
  a fresh agent deployment.
@@ -12,6 +12,7 @@ version: 1.0.0
 status: active
 runtime_contract: 2
 ---
 ---
 # Hermes Zulip Restore — Bring Any Agent Back to Good State
@@ -23,7 +24,7 @@ gateway restart, and connection validation.
 | Param | Type | Required | Default | Description |
 |-------|------|----------|---------|-------------|
-| `target` | string | yes | — | Agent name: `mumuni`, `tanko`, `koby`, or `shumba` |
+| `target` | string | yes | — | Agent name: `mumuni`, `koby`, or `shumba` (Tanko excluded — DSH since 2026-08-27) |
 ## Maintains
@@ -36,7 +37,7 @@ gateway restart, and connection validation.
 - `_strip_html` function present in `<hermes-agent>/plugins/platforms/zulip/adapter.py`
 - All three adapter files (__init__.py, adapter.py, plugin.yaml) present at bundled path
- Zulip env vars set in `~/.hermes/.env` (or `/home/jerome/.hermes/.env` for Tanko)
+- Zulip env vars set in `~/.hermes/.env` (or `/home/jerome/.hermes/.env` for Tanko, historical — DSH since 2026-08-27)
 - Gateway restarted and zulip platform reports state `connected`
 - HTML stripping enabled for `/approve` and `/deny` slash command support
@@ -51,8 +52,6 @@ gateway restart, and connection validation.
 | Host | CT | Proxmox | IP (direct) | Hermes Home | User |
 |------|-----|---------|-------------|-------------|------|
 | Mumuni | CT100 (abiba) | minipve | 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 |
@@ -94,8 +93,8 @@ cp zulip-platform-plugins/plugins/platforms/zulip/adapter.py \
   zulip-platform-plugins/plugins/platforms/zulip/plugin.yaml \
   <HERMES_HOME>/hermes-agent/plugins/platforms/zulip/
-# Fix ownership (Tanko only)
+# Fix ownership (was Tanko-only; RETIRED 2026-08-27 — tanko on DSH, no Hermes plugin)
-chown -R jerome:jerome <HERMES_HOME>/hermes-agent/plugins/platforms/zulip/  # Tanko only
+chown -R jerome:jerome <HERMES_HOME>/hermes-agent/plugins/platforms/zulip/  # Tanko only (historical)
 # Clean up
 rm -rf /tmp/zulip-deploy
@@ -184,6 +183,7 @@ https://git.sysloggh.net/SyslogSolution/zulip-platform-plugins/src/branch/feat/z
 Commit `55ca15d` — `fix(zulip): add _strip_html for slash command matching`
 Pull request #33 is the primary integration branch.
 ---
 ---
 **Last verified good state**: 2026-07-08 — Mumuni, Tanko, Koby all connected with `_strip_html` applied.
@@ -87,8 +87,8 @@ call apply-liteLLM-routing
 call apply-agent-compression
  agent: mumuni
-  host: 192.168.68.24
+  host: 192.168.68.14
-  config_path: /root/.hermes/config.yaml
+  config_path: /home/hermes/.hermes/config.yaml
 -- Phase 4: Enable llama.cpp prompt caching on GPU hosts
@@ -613,7 +613,7 @@ ssh root@192.168.68.110 "systemctl restart llama-server"
 | 109 | docker-vm | storepve | .7 | Docker host | ❌ |
 | 110 | gitea | minipve | **.17** | Git | ❌ |
 | 111 | tdunna | amdpve | .129 | Hermes agent | ✅ |
-| 112 | tanko | amdpve | .122 | Hermes agent | ✅ |
+| 112 | tanko | amdpve | .122 | DSH (DeepSeek Harness) agent | ✅ |
 | 113 | baggy | amdpve | .114 | Hermes agent | ✅ |
 | 115 | scottdenya | amdpve | .75 | Denya OneCare | ❌ |
 | 116 | syslog-api | minipve | .116 | LiteLLM + Grafana | ❌ |
@@ -140,7 +140,6 @@ 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 |
 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.
@@ -102,6 +102,39 @@ GPU .8 (RTX 3090)    GPU .110 (RTX 5070)   GPU .15 (Strix Halo)
 - Stack persists across reboots (systemd for exporters, Docker restart policy)
 ## Execution
 ### check-health
 **RUN LIVE, NEVER ECHO — every dispatch must execute the probes below with real tool calls; never repeat a prior report unless a live probe fails.**
 ```bash
 # Zulip API health (POST ping)
 curl -s -o /dev/null -w '%{http_code}' -X POST https://chat.sysloggh.net/api/v1/messages -u 'abiba-bot@chat.sysloggh.net:KEY'
 # Expected: 200 (HTTP 000 = unreachable/cache)
 # PM2 process health
 pm2 jlist
 # Expected: 5/5 online (abiba-telegram, abiba-zulip, zulip-watchdog, gitea-runner, spoton-service)
 # GPU exporters (may be down per DEPLOYMENT STATUS)
 curl -s http://192.168.68.8:9400/metrics && echo " - OK" || echo " - FAIL"
 curl -s http://192.168.68.110:9400/metrics && echo " - OK" || echo " - FAIL"
 curl -s http://192.168.68.15:9400/metrics && echo " - OK" || echo " - FAIL"
 # Prometheus targets
 curl -s http://192.168.68.116:9090/api/v1/targets | jq '.data.activeTargets'
 # Expected: All targets UP (may show some down if exporters not deployed)
 # Grafana health
 curl -s http://192.168.68.116:3001/api/health | jq '{status, version}'
 # Expected: {"status":"ok","version":"..."}
 # LiteLLM metrics
 curl -s http://192.168.68.116:4001/metrics | head -20
 # Expected: Prometheus-formatted metrics output
 ```
 **Report format**: Summarize actual results from each probe. If any probe returns non-200 or empty output, flag as alert.
 ### Phase 1: GPU Exporters
@@ -59,7 +59,7 @@ Before ANY update wave:
 | CT 100 (.24) | Abiba (pi) | `apt update && apt upgrade -y` | 3 min |
 | CT 116 (.116) | syslog-api (LiteLLM host) | `apt update && apt upgrade -y` | 3 min |
 | CT 112 (tanko, amdpve) | Tanko | `apt update && apt upgrade -y` | 3 min |
-| CT 100 (mumuni/abiba, minipve) | Mumuni | `apt update && apt upgrade -y` | 3 min |
+| CT 105 (kagentz, minipve) | Mumuni | `apt update && apt upgrade -y` | 3 min |
 | VM 101 (.8) | llm-gpu (RTX 3090) | `apt update && apt upgrade -y` | 3 min |
 | VM 103 (.110) | ocu-llm (RTX 5070) | `apt update && apt upgrade -y` | 3 min |
@@ -162,9 +162,9 @@ Before Wave 1, snapshot these files:
 /etc/systemd/system/strix-server.service                (amdpve .15 — strix-moe)
 /etc/systemd/system/llama-server.service                (VM 101 .8, VM 103 .110)
 # Hermes agent configs (key enforcement — 2026-07-10)
-/root/.hermes/config.yaml                               (Mumuni inside CT 100, Tanko CT 112, etc.)
+/home/hermes/.hermes/config.yaml                        (Mumuni kagentz CT105; Tanko CT112 uses /home/jerome/.hermes)
-/root/.config/systemd/user/hermes-gateway.service       (Mumuni inside CT 100 — EnvironmentFile fixed)
+/etc/systemd/system/hermes-gateway.service              (Mumuni kagentz CT105 — system unit, User=hermes)
-/etc/environment                                        (Mumuni inside CT 100 — LITELLM_API_KEY)
+/etc/environment                                        (LITELLM_API_KEY — legacy path, Mumuni now keys via Infisical)
 ```
 ## MCP Gateway (2026-07-10)
@@ -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 | .14 (kagentz CT105) | systemd unit hermes-gateway.service (user hermes) | 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 |
@@ -257,9 +257,51 @@ reads use per-agent identities. This eliminates the single shared token risk.
 | Agent | .env Keys |
 |-------|-----------|
 | Mumuni | MUMUNI_LITELLM_API_KEY, MUMUNI_ZULIP_API_KEY |
-| Tanko | TANKO_LITELLM_API_KEY, TANKO_ZULIP_API_KEY |
+|| Tanko | TANKO_LITELLM_API_KEY, TANKO_ZULIP_API_KEY |
-| Koby | (wrapper injects from vault — .env has Telegram token) |
+|| Koby | (wrapper injects from vault — .env has Telegram token) |
-| Koonimo | KOONIMO_LITELLM_API_KEY, KOONIMO_ZULIP_API_KEY |
+|| Koonimo | KOONIMO_LITELLM_API_KEY, KOONIMO_ZULIP_API_KEY |
 || Agent Zero (kagentz .14) | OPENROUTER_API_KEY (direct OpenRouter access) |
 ### Agent Zero (kagentz .14) — OpenRouter Integration (2026-09-01)
 Agent Zero runs in Docker on kagentz (CT105) and uses **direct OpenRouter API access**,
 not via the LiteLLM proxy. This is because Agent Zero's workflow (self-update manager,
 UI bootstrap, model selection) is built around OpenRouter's native authentication.
 **Key Storage:**
 - **Container**: `/a0/usr/.env` (line ~72: `API_KEY_OPENROUTER=sk-or-v1-…`)
 - **Vault**: Infisical secret `OPENROUTER_API_KEY` (project=agents, env=production)
 - **Fallback**: The container's .env is the primary source; vault sync is optional
  (unlike fleet agents which require vault injection)
 **Current Key (2026-09-01):**
 - **Prefix**: `sk-or-v1-0af3f3…`
 - **User**: `user_2rt9lCqcd5d7Vk1t18DHsvWdPTT`
 - **Plan**: Paid (not free tier)
 - **Usage**: 0 (as of 2026-09-01)
 **Model Configuration:**
 - **Preset**: "Cost Efficient" (`/a0/usr/plugins/_model_config/presets.yaml`)
 - **Model**: `openrouter/moonshotai/kimi-k3`
 - **API Base**: (empty — uses OpenRouter default)
 **Why not LiteLLM proxy?**
 Agent Zero's architecture was designed before the fleet adopted the LiteLLM proxy
 standard. The container runs `/exe/self_update_manager.py` and `/a0/run_ui.py` which
 directly call OpenRouter via Python's requests library. Converting would require:
 1. Refactoring all LLM calls to use `litellm` library
 2. Adding vault wrapper injection
 3. Updating self_update_manager to use proxy-aware key handling
 **Rotation Procedure:**
 1. Generate new key in OpenRouter UI
 2. Update container: `sed -i 's/^API_KEY_OPENROUTER=.*/API_KEY_OPENROUTER=<new_key>/' /a0/usr/.env`
 3. Update vault: `infisical secrets set OPENROUTER_API_KEY=<new_key> --projectId=agents --env=production`
 4. Restart container: `sudo docker exec agent-zero supervisorctl restart run_ui`
 5. Verify: `curl -s https://openrouter.ai/api/v1/auth/key -H "Authorization: Bearer <new_key>"`
 **Related Contract:**
 - `agent-zero-openrouter-key.prose.md` — Full agent-zero key management contract
 ## Key Rotation Log
@@ -0,0 +1,117 @@
 ---
 kind: pattern
 name: litellm-client-timeouts
 description: >
  Standard client timeout and retry policy for ALL agents calling LiteLLM
  (CT 116, http://192.168.68.116). Created 2026-09-08 after the Sep 6 incident:
  a backend stall 04:00-06:30 EDT produced 157 client-abandoned 408 failures
  (82% from abiba-pi, 13 from mumuni) against a backend that was actually
  succeeding at 20-70s per call once clients stopped giving up. Grounded in
  measured data: syslog-auto (LiteLLM virtual model, no dedicated GPU — routes
  to backends) averages 28.8s/request with 25.4s TTFT over 888 calls/24h;
  nginx already allows 600s (Rule 5, verified 2026-08-09); the gap is entirely
  client-side. Blast radius if wrong: agents fall back to DeepSeek silently
  (key/timeout failures present as model degradation, not errors) or abandon
  healthy-but-slow reasoning calls, fragmenting long tasks.
 ---
 ## Maintains
 - client_timeout_standard: "litellm-client-timeouts v1.0 (2026-09-08)"
 - applies_to: ALL agents and scripts calling http://192.168.68.116 (main model path, auxiliary tasks, health probes, benchmark jobs)
 - verified_against: Prometheus litellm_* metrics 24h window ending 2026-09-08 ~10:00 EDT; live probe (syslog-auto tiny call 0.56s TTFB, 200 OK); nginx 600s proxy_read_timeout (Rule 5)
 ## The measured numbers these values come from
 | Model | avg latency | avg TTFT | p-profile (24h) |
 |---|---|---|---|
 | syslog-auto | 28.8s | 25.4s | 68 calls took 30-120s; tail to ~300s under load |
 | qwen3.6-27B-code | 23.0s | — | same backend class as syslog-auto |
 | strix-moe | 7.5s | — | Strix Halo, healthy |
 | gemma-4-12b | 2.6s | — | RTX 5070, healthy |
 Sep 6 incident timeline: failures 04:00-07:00 EDT (0% GPU util = wedged
 backend), full recovery 07:00-08:00 with ZERO client failures once requests
 tolerated 20-70s — 392 successful slow calls in the three hours after recovery.
 LiteLLM's internal queue time is ~0s; the latency is model inference, not
 proxy queuing.
 ## Parameters
 ### 1. Primary model path (model.default / custom_providers) — NO client timeout below 300s
 - The default Hermes HTTP timeout (~60s) is TOO SHORT for syslog-auto's healthy
  28.8s average + 120-300s tail. Every 408 in the incident was a client
  abandoning a request the backend would have answered.
 - If the transport exposes a timeout setting for the main model, set it to
  **300s or more**. If it does not (current Hermes custom-provider path has no
  timeout knob), that is acceptable ONLY because nginx holds the request for
  600s — but any wrapper, script, or direct API call you write MUST set its own
  timeout >= 300s for syslog-auto/qwen-class calls.
 - Never hardcode a shorter timeout "to fail fast" on this path — failing fast
  here is what caused the incident.
 ### 2. Auxiliary tasks — keep template timeouts, one correction
 - vision: 60s (keep), web_extract: 30s (keep) — gemma-4-12b averages 2.6s;
  these are fine.
 - compression: 300s (keep — this was already raised from 60 per gpu-fleet).
 - **gpu-dense delegation/x_search: set timeout >= 120s.** The RTX 3090
  (qwen3.6-27B-code backend, 23.0s avg) is the same speed class as
  syslog-auto; delegation defaults that assume fast responses will 408 the
  same way.
 ### 3. Retry policy — backoff, not repetition
 - On timeout (408) or 5xx: retry up to **2 times** with exponential backoff
  (**15s, 45s**) before giving up.
 - Do NOT retry in a tight loop. The Sep 6 spike shape (65 failures in one hour
  from one key) was a batch job retrying without backoff while the backend was
  down — it multiplied load during recovery.
 - On 401/403: do NOT retry — that is a key/permission problem (see
  litellm-api-keys.prose.md and Rule 11); retrying just spams the log.
 - On 429: honor the retry-after header if present, else back off 60s.
 ### 4. Health probes — identify yourself and time out sanely
 - Probes MUST NOT appear as keyless, model-less failures in the metrics (12
  such orphans appeared in the incident window and cost investigation time).
  Send a real model name and use a real (probe-designated) key.
 - Probe timeout: 30s. A probe that takes longer than 30s IS the alert —
  report "backend slow (>30s)" rather than hanging.
 - Probe cadence: at most hourly. The 6h litellm-health cron cadence is the
  standard; sub-hourly synthetic traffic distorts latency baselines.
 ### 5. Batch/benchmark jobs — schedule away from 04:00-07:00 EDT and chunk
 - The incident window showed bulk clients amplifying a backend stall 5:1.
 - Batch jobs that can tolerate delay: schedule 09:00-17:00 EDT.
 - Any batch loop over N requests MUST sleep >= 5s between requests and honor
  the retry policy in section 3.
 ## Returns
 - A single standard any agent or script can cite: timeouts >= 300s on the
  syslog-auto path, >= 120s on gpu-dense delegation, backoff retries (2x,
  15s/45s), identified probes at 30s/hourly, batch jobs chunked and
  day-scheduled.
 - Failure signature recognition: bulk 408s from multiple keys in one window =
  backend event (check gpu_utilization_percent: 0% = wedged, ~100% = saturated);
  single-key 408s = that client's timeout is too short.
 - Cross-references: hermes-config-template.prose.md (Rule 5 nginx 600s,
  auxiliary timeouts), gpu-fleet.prose.md (compression 300s precedent,
  stable aliases), litellm-api-keys.prose.md (key/permission failures).
 ## Intentionally NOT changed
 - No server-side LiteLLM timeout/cooldown changes proposed — the incident
  self-recovered and the server is healthy (0.56s live probe); changing
  server behavior without process-level root cause (CT116 requires root;
  not reachable from kagentz) would be guessing.
 - No change to the template's vision/web_extract/compression timeouts —
  measured data says they are correct.
 - No per-agent key permission changes — those are litellm-api-keys.prose.md
  territory (and the open gpu-vision/gemma 403 items are already filed with
  the key owners).
 - No model routing changes — syslog-auto's weighted pool behaved correctly
  throughout the incident.
@@ -1,4 +1,6 @@
 ---
 report_only_agents:
  - koby  # ⛔ KOBY IS NEVER REPAIRED (Rule 17, 2026-08-17) — detect + report, never fix on .129
 kind: responsibility
 name: litellm-self-heal
 status: deployed
@@ -22,6 +24,7 @@ description: >
  inference, and agent keys. Applies remediation rules for common failures.
  Reports every action via Zulip DM and Gitea (SyslogSolution/health-logs).
 ---
 ---
 # LiteLLM Operations — Health Check + Self-Heal
@@ -65,7 +68,15 @@ Request → nginx:80 → LiteLLM:4000 → GPU(llama-server, parallel 2)
 ## LiteLLM Model Surface (ground truth — `/opt/inference-harness/litellm_config.yaml` on CT 116)
-`model_name`s served: `qwen3.6-27B-code`, `gemma-4-12b`, `qwen3.6-35B-udq4`, `strix-moe`, `gpu-dense`, `gpu-light`, `syslog-auto`.
+`model_name`s served: `qwen3.6-27B-code`, `gemma-4-12b`, `qwen3.6-35B-udq4`, `strix-moe`, `gpu-dense`, `gpu-light`, `syslog-auto`, `crew-auto` (new 2026-08-20).
 ### Context Cap Split (2026-08-20)
 - **Abiba (firstmate)**: 128K uncapped — unlimited context for primary workloads
 - **Hermes agents** (mumuni, tanko, koby, koonimo): 128K uncapped
 - **Crewmates** (ops, tune, verify, auth-keys, build): 64K capped — alias `crew-auto` enforces 64K limit
 Preferred implementation: uncap shared pool, add capped alias for crew-only.
 - `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.
@@ -120,6 +131,7 @@ Request → nginx:80 → LiteLLM:4000 → GPU(llama-server, parallel 2)
 - Also wakes on user request
 - On failure: re-check after 30s, escalate after 3 consecutive failures
 ---
 ---
 ## Health Check
@@ -162,6 +174,7 @@ Determine overall_status from individual check results:
 - "degraded" — 1-2 non-critical checks fail
 - "down" — critical checks fail
 ---
 ---
 ## Remediation Rules
@@ -205,6 +218,7 @@ Escalate → if SSH access unavailable, send Zulip DM
 Router no longer in path so Redis active counters are unused. Rule retained
 for reference but inactive. If Redis issues occur, check harness-redis container.
 ---
 ---
 ## Reporting
@@ -227,6 +241,7 @@ top actions, uptime.
 If a fix requires another agent (e.g., Authentik restart), relay sent
 to responsible agent with full context.
 ---
 ---
 ## Execution
@@ -1,9 +1,12 @@
 ---
 report_only_agents:
  - koby  # ⛔ KOBY IS NEVER REPAIRED (Rule 17, 2026-08-17) — detect + report, never fix on .129
 name: memory-audit-maintenance
 kind: responsibility
-description: Shared memory audit and maintenance contract for all Hermes agents (Mumuni, Tanko, Koby, Koonimo). Each agent runs it against its own isolated memory files — no cross-agent access, no shared state. Detects staleness, enforces writer registry, and rotates canary tokens.
+description: Shared memory audit and maintenance contract for Hermes agents (Mumuni, Koby, Koonimo). Tanko is no longer a Hermes agent (now on DSH/DeepSeek Harness since 2026-08-27) and uses DSH-native memory, so it is excluded from this Hermes roster. 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
@@ -15,11 +18,10 @@ Autonomously audit and reorganize an agent's native memory (MEMORY.md, USER.md,
 ### Scope
-This contract is the **Hermes Agent standard** for memory maintenance. It is shared across all Hermes agents (Mumuni, Tanko, Koby, Koonimo). Each agent runs it against its own memory files only  no cross-agent access, no shared state, no shared ledger, no shared canary. The contract is the standard; each agent enforces it independently with fully isolated data.
+This contract is the **Hermes Agent standard** for memory maintenance. It is shared across Hermes agents (Mumuni, Koby, Koonimo). **Tanko is excluded — it migrated to DSH (DeepSeek Harness) on 2026-08-27 and now uses DSH-native memory (mnemon), not `~/.hermes/memories/`.** Each agent runs it against its own memory files only  no cross-agent access, no shared state, no shared ledger, no shared canary. The contract is the standard; each agent enforces it independently with fully isolated data.
-**Agent Roster:**
+**Agent Roster (Hermes):**
 - Mumuni
 - Tanko
 - Koby (CT 111 / tdunna)
 - Koonimo (CT 113 / baggy)
@@ -343,4 +345,3 @@ return {
 ### Per-Agent Notes
 Each Hermes agent (Mumuni, Tanko, Tdunna, Baggy) runs this contract against its own `~/.hermes/memories/` directory. The contract is identical across agents, but all data is fully isolated: separate ledgers, separate writer registries, separate canaries. If a new agent is added to the roster, it must be listed in `### Scope` above and given its own isolated memory directory.
@@ -1,4 +1,6 @@
 ---
 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: >
@@ -6,6 +8,7 @@ description: >
  Escalate anything that needs Kwame's input. Executes confirmed Kwame decisions to completion (state + updated_at).
 version: 2.0.0
 ---
 ---
 # Memory Fixer
@@ -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, minipve, .24) via Hermes agent (Pi + Hermes Zulip gateway).
+  Runs on Mumuni (kagentz CT105, minipve, .14) via Hermes agent (Zulip gateway via systemd).
 version: 1.0.0
 ---
@@ -20,7 +20,7 @@ version: 1.0.0
 ## Topology
 **Cluster:** 5 Proxmox nodes (ocupve, acerpve, minipve, amdpve, storepve)
-**Manager:** Mumuni (inside Abiba CT100, minipve, .24) via Hermes agent
+**Manager:** Mumuni (kagentz CT105, minipve, .14) 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.
@@ -54,7 +54,7 @@ garbled input. When a user types these commands to Abiba:
 - **`/approve`** → "Pi doesn't have pending approvals. Commands execute immediately."
 - **`/approve session`** → Same response
- **`/deny`** → Same response + "For Hermes agents (Tanko, Mumuni), these work with their built-in approval system."
+- **`/deny`** → Same response + "For agents (Mumuni on Hermes, Tanko on DSH), these work with their built-in approval system."
 This keeps the UX consistent across agents — users can type `/approve` anywhere
 without getting confused by LLM responses.
@@ -2,17 +2,6 @@
 kind: responsibility
 name: pm2-self-heal
 description: >
  Monitors critical PM2 processes (abiba-zulip, abiba-telegram, gitea-runner,
  spoton-service, zulip-watchdog) and auto-restarts any that are stopped or
  errored. Logs every action to Gitea (SyslogSolution/health-logs — not
  knowledge graph, hard rule) and alerts the owner via
  Zulip DM on failures.
  CRITICAL: Never restart abiba-zulip — it runs this contract.
  AS-BUILT 2026-08-09 (captain ruling, ecosystem is authoritative):
  gpu-monitor is systemd-managed (gpu-monitor.service) — NOT PM2;
  gpu-watchdog decommissioned (function folded into gpu-monitor.service);
  gitea-runner KEPT (online in PM2); abiba-zulip KEPT (online 4d+, the
  2026-07-04 'removed/decommissioned' note was stale and is removed).
 ---
 ## Maintains
@@ -24,9 +13,6 @@ description: >
 - zulip-watchdog: { status: "online", uptime: string, restarts: number }
 - last_check: timestamp
 > **Note (2026-07-04, SUPERSEDED 2026-08-09):** `abiba-zulip` remains ONLINE and
 > is monitored — the decommission note was stale (process re-added; do not treat
 > it as removed).
 ## Continuity
@@ -63,9 +49,9 @@ description: >
   - If status is "online" → pass
   - If status is "stopped" or "errored" → apply Rule 1
   - If restarts > 5 → alert owner
-3. **Check abiba-zulip** (self-process, read-only):
+3. **Check abiba-zulip** (live Zulip bridge, heartbeating):
   - If status is "online" → pass, log restarts count
-   - If status is "stopped" or "errored" → **DO NOT RESTART** — alert owner immediately
+   - If status is "stopped" or "errored" → restart (`pm2 restart abiba-zulip` — fully restored)
   - If restarts > 5 in last hour → alert owner with full diagnostics
 4. **Log results** — Append to `SyslogSolution/health-logs/pm2/{timestamp}.md` in Gitea (not knowledge graph — hard rule)
 5. **Alert** — Send Zulip DM to owner if escalation needed (do NOT run pm2 commands during alerting)
@@ -39,7 +39,7 @@ PVE_NODES = {
 # Agent definitions: ct, host, user, pve_node, vault_key_name
 AGENTS = {
-    "tanko":   {"ct": 112, "host": "192.168.68.122", "user": "jerome", "pve": "amdpve",  "vault_key": "TANKO_LITELLM_API_KEY"},
+    "tanko":   {"ct": 112, "host": "192.168.68.122", "user": "jerome", "pve": "amdpve",  "vault_key": "TANKO_LITELLM_API_KEY", "runtime": "dsh"},
    "abiba":   {"ct": 100, "host": "192.168.68.24",  "user": "root",   "pve": "minipve",  "vault_key": None},  # Pi agent + Mumuni Zulip, no vault key
    "koby":    {"ct": 111, "host": "192.168.68.129", "user": "root",   "pve": "amdpve",  "vault_key": "KOBY_LITELLM_API_KEY"},
    "koonimo": {"ct": 113, "host": "192.168.68.114", "user": "root",   "pve": "amdpve",  "vault_key": "KOONIMO_LITELLM_API_KEY"},
@@ -238,20 +238,36 @@ def check_agents():
        host = agent.get("host")
        user = agent.get("user")
        ct = agent["ct"]
        report_only = agent.get("report_only", False)
        # Tanko runs on DSH (DeepSeek Harness) since 2026-08-27 — it no longer runs a
        # Hermes gateway, so skip the Hermes gateway/state/streaming/journal checks.
        if agent.get("runtime") == "dsh":
            live = ssh(host, "true", user=user)
            print(f"  {'✅' if live is not None else '❌'} {name}: DSH (DeepSeek Harness) — "
                  f"no Hermes gateway since 2026-08-27 (CT {ct}, SSH {'OK' if live is not None else 'FAIL'})")
            if live is None:
                FAIL.append(f"unreachable:{name}")
            continue
        if not host or not user:
            print(f"  ⬜ {name} (CT {ct}): cannot SSH — skip liveness check")
            continue
-        # Gateway process
+        # ⛔ KOBY IS NEVER REPAIRED — diagnostic only
-        pid = ssh(host, "pgrep -f 'hermes_cli.main gateway run' | grep -v infisical | head -1", user=user)
+        if report_only:
-        if not pid:
+            print(f"  🔍 {name}: REPORT-ONLY mode (diagnostic only, no repairs on .129)")
-            # Try alternate binary name
+            # Still check gateway status for reporting purposes
-            pid = ssh(host, "pgrep -f 'hermes.*gateway' | grep -v infisical | grep -v bash | head -1", user=user)
+            pid = ssh(host, "pgrep -f 'hermes_cli.main gateway run' | grep -v infisical | head -1", user=user)
-        if not pid:
+            if not pid:
-            print(f"  ❌ {name}: GATEWAY NOT RUNNING")
+                pid = ssh(host, "pgrep -f 'hermes.*gateway' | grep -v infisical | grep -v bash | head -1", user=user)
-            FAIL.append(f"gateway-down:{name}")
+            if not pid:
-            continue
+                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)
@@ -327,6 +343,10 @@ def check_ct_liveness():
 def check_config_integrity():
    """Verify agent config.yaml parses as valid YAML."""
    for name, agent in AGENTS.items():
        # Tanko runs on DSH (DeepSeek Harness) since 2026-08-27 — no Hermes config.yaml.
        if agent.get("runtime") == "dsh":
            print(f"  ⏭️ {name}: DSH — no Hermes config.yaml since 2026-08-27")
            continue
        host = agent.get("host")
        user = agent.get("user")
        if not host or not user:
@@ -356,6 +376,10 @@ def check_config_integrity():
 def check_wrapper_integrity():
    """Verify the hermes CLI wrapper exists and can reach hermes-real."""
    for name, agent in AGENTS.items():
        # Tanko runs on DSH (DeepSeek Harness) since 2026-08-27 — no hermes CLI wrapper.
        if agent.get("runtime") == "dsh":
            print(f"  ⏭️ {name}: DSH — no hermes CLI wrapper since 2026-08-27")
            continue
        host = agent.get("host")
        user = agent.get("user")
        if not host or not user:
@@ -296,21 +296,16 @@ def collect():
        "pm2_uptime": pm2.get("uptime", "?"),
    }
-    # Tanko (CT 122)
+    # Tanko (CT 112, IP 192.168.68.122) — DSH (DeepSeek Harness), no Hermes gateway
-    tanko_state = ssh_jerome("192.168.68.122", "cat ~/.hermes/gateway_state.json 2>/dev/null")
+    # since 2026-08-27. There is no ~/.hermes/gateway_state.json on CT 112 anymore;
-    tanko_data = {}
+    # Zulip/Telegram connectivity is managed by the DSH harness, not the Hermes gateway.
    try:
        tanko_data = json.loads(tanko_state) if tanko_state else {}
    except:
        tanko_data = {}
    platforms = tanko_data.get("platforms", {})
    report["agents"]["tanko"] = {
-        "platform": "hermes", "ct": 112, "ip": "192.168.68.122",
+        "platform": "dsh", "ct": 112, "ip": "192.168.68.122",
-        "gateway_state": tanko_data.get("gateway_state", "unknown"),
+        "gateway_state": "n/a (DSH)",
-        "zulip_state": platforms.get("zulip", {}).get("state", "unknown"),
+        "zulip_state": "unknown",
-        "telegram_state": platforms.get("telegram", {}).get("state", "unknown"),
+        "telegram_state": "unknown",
-        "gateway_pid": tanko_data.get("pid"),
+        "gateway_pid": None,
-        "updated_at": tanko_data.get("updated_at"),
+        "updated_at": "",
    }
    # Mumuni (CT 100, IP 192.168.68.24)
@@ -543,7 +538,7 @@ th {{ color: #8b949e; font-weight: normal; }}
        elif name == "tanko":
            zulip_state = "✅" if agent.get("zulip_state") == "connected" else ("❌" if agent.get("zulip_state") == "disconnected" else "⬜")
            gateway = agent.get("gateway_state", "?")
-            processed = agent.get("updated_at", "")[:10]
+            processed = "DSH"
        elif name == "mumuni":
            zulip_state = "⬜" if agent.get("zulip_state") == "not_installed" else ("✅" if agent.get("zulip_state") == "connected" else "⬜")
            gateway = agent.get("gateway_state", "?")
@@ -12,10 +12,10 @@ echo ""
 # Authorized agents for restricted contracts
 # Format: contract_pattern|authorized_agents (comma-separated)
 declare -A RESTRICTED
-RESTRICTED["infrastructure-control.prose.md"]="abiba"
+RESTRICTED["infrastructure-control.prose.md"]="abiba,abiba-bot,tanko,tanko-bot,mumuni,mumuni-bot"
-RESTRICTED["proxmox-monitor.prose.md"]="abiba"
+RESTRICTED["proxmox-monitor.prose.md"]="abiba,abiba-bot"
-RESTRICTED["hermes-config-template.prose.md"]="abiba,mumuni,tanko"
+RESTRICTED["hermes-config-template.prose.md"]="abiba,abiba-bot,mumuni,mumuni-bot,tanko,tanko-bot"
-RESTRICTED["zulip-health.prose.md"]="abiba,mumuni"
+RESTRICTED["zulip-health.prose.md"]="abiba,abiba-bot,mumuni,mumuni-bot,tanko,tanko-bot"
 RESTRICTED["scripts/pm2-self-heal.sh"]="abiba"
 RESTRICTED["scripts/prose-lint.sh"]="abiba"
 RESTRICTED["scripts/prose-ai-review.sh"]="abiba"
@@ -9,10 +9,11 @@ ZULIP_EMAIL="abiba-bot@chat.sysloggh.net"
 ZULIP_KEY="cKTDMZAPW08dk3zl05sStzO7HRztzyn8"
 OWNER_ZULIP_ID="9"
-# Email config
+
-GMAIL_USER="jtabiri@gmail.com"
+LOG="/root/zulip-health-monitor.log"
-GMAIL_PASS="rgbuomwcydxwbszd"
+TIMESTAMP=$(date -u '+%Y-%m-%d %H:%M UTC')
-EMAIL_TO="jerome@sysloggh.com"
+ISSUES=0
 echo "=== Zulip Health Check — $TIMESTAMP ===" >> "$LOG"
 notify() {
  local severity="$1" msg="$2"
@@ -24,30 +25,14 @@ notify() {
  curl -sf -X POST "${ZULIP_SITE}/api/v1/messages" \
    -u "${ZULIP_EMAIL}:${ZULIP_KEY}" \
    -d "${form}" > /dev/null 2>&1 || true
-  
+  # Zulip stream post to #agent-hub on topic 'zulip-health'
-  # Email alert
+  local stream_content="${severity} Zulip Monitor: ${msg}"
-  local subject="${severity} Zulip Monitor Alert"
+  curl -sf -X POST "${ZULIP_SITE}/api/v1/messages" \
-  python3 -c "
+    -u "${ZULIP_EMAIL}:${ZULIP_KEY}" \
-import smtplib
+    -d "type=stream\&to=%5B7%5D\&topic=zulip-health\&content=$(python3 -c "import urllib.parse; print(urllib.parse.quote(str()))")" \
-from email.mime.text import MIMEText
+    > /dev/null 2>&1 || true
 m = MIMEText('''${msg}''')
 m['From'] = 'abiba@sysloggh.com'
 m['To'] = '${EMAIL_TO}'
 m['Subject'] = '${subject}'
 s = smtplib.SMTP('smtp.gmail.com', 587)
 s.starttls()
 s.login('${GMAIL_USER}', '${GMAIL_PASS}')
 s.sendmail('abiba@sysloggh.com', ['${EMAIL_TO}'], m.as_string())
 s.quit()
 " 2>/dev/null || true
 }
 TIMESTAMP=$(date -u '+%Y-%m-%d %H:%M UTC')
 ISSUES=0
 LOG="/root/zulip-health-monitor.log"
 echo "=== Zulip Health Check — $TIMESTAMP ===" >> "$LOG"
 # ── Global: Zulip Server ──
 SERVER_CODE=$(curl -s -o /dev/null -w "%{http_code}" --connect-timeout 10 \
  https://chat.sysloggh.net/api/v1/server_settings \
@@ -1,22 +1,24 @@
 ---
 kind: responsibility
 name: zulip-health
-description: Multi-platform health monitor for the Zulip messaging mesh spanning Platform A (Agent Zero Docker), Platform B (Hermes agents Tanko/Mumuni), and the Zulip bridge. Verifies bot registration, DM delivery, and cross-platform connectivity.
+description: Multi-platform health monitor for the Zulip messaging mesh spanning Platform A (Agent Zero Docker), Platform B (Tanko on DSH / Mumuni on Hermes), and the Zulip bridge. Verifies bot registration, DM delivery, and cross-platform connectivity.
 title: Zulip Mesh Health Monitor — Multi-Platform
 version: 3.0.0
 runtime_contract: 2
 agent: abiba
 report_only_agents:
  - koby  # ⛔ KOBY IS NEVER REPAIRED (Rule 17, 2026-08-17) — detect + report, never fix on .129
 ---
 # Zulip Mesh Health Monitor
-Monitors ALL Zulip-connected agents across three platforms (pi, Hermes, Agent Zero).
+Monitors ALL Zulip-connected agents across platforms (pi, Hermes, DSH, Agent Zero).
 Runs every 15 minutes in the background. Also triggers on session start.
 ## Requires
 - **Zulip API key** for `abiba-bot@chat.sysloggh.net` in `$ZULIP_API_KEY`
- **SSH access** to Tanko (192.168.68.122), Mumuni (192.168.68.24, inside Abiba CT100 on minipve), and Agent Zero Docker host (192.168.68.14)
+- **SSH access** to Tanko (192.168.68.122), Mumuni (192.168.68.14, kagentz CT105 on minipve), and Agent Zero Docker host (192.168.68.14)
 - **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`
@@ -45,7 +47,7 @@ Runs every 15 minutes in the background. Also triggers on session start.
    "severity": "healthy"
  },
  "tanko": {
-    "platform": "hermes",
+    "platform": "dsh",
    "zulip_state": "connected",
    "heartbeat_age_seconds": 45,
    "gateway_pid": 1234,
@@ -81,13 +83,13 @@ Log as "unreachable" — don't treat as critical unless it persists for 3+ conse
 ## Streaming Support (2026-07-05)
 Zulip agents now support progressive message editing during agent generation.
-When a Hermes agent (Tanko, Mumuni) processes a message, the response is
+When a Zulip agent (Tanko on DSH, Mumuni on Hermes) processes a message, the response is
 streamed in real-time via Zulip's `PATCH /api/v1/messages/{id}` API:
 - Adapter implements `edit_message()` using `_api_patch()` helper
 - Gateway stream consumer progressively edits the Zulip message
 - User sees real-time agent thinking instead of waiting for full response
- Verified: Tanko (CT 112) and Mumuni (inside Abiba CT 100) both have streaming active
+- Verified: Tanko (CT 112) and Mumuni (kagentz CT 105) both have streaming active
 ### Verification
 ```bash
@@ -182,15 +184,14 @@ 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)
 **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
 ```
 Tanko runs on DSH (DeepSeek Harness) — it no longer runs a Hermes gateway, so there is no `~/.hermes/gateway_state.json` on CT 112 (.122). Verify Tanko's Zulip connectivity via the DSH harness bot status instead.
 Check `platforms.zulip.state`: `connected` ✅ | `disconnected` ❌ | `error` ❌ | missing → not installed.
 **B2: Agent Process**
@@ -203,24 +204,22 @@ Gateway PID should exist with uptime > 60s. **Dual-gateway detection**: if more
 | Agent | Restart command | Notes |
 |-------|-----------------|-------|
 | Mumuni (.24) | `pm2 restart abiba-zulip` | Hermes gateway runs under PM2 as `abiba-zulip` |
 | Tanko (.122) | `bash /opt/hermes-zulip-plugin/run.sh` (or the agent's systemd/user unit) | Tanko does NOT use PM2 — never run `pm2 restart mumuni-zulip` for Tanko (process does not exist) |
 Check gateway log for "Gateway running with 2 platform(s)" (not 1) to confirm Zulip reloaded.
-**B3: Heartbeat Verification**
+**B3: Heartbeat Verification** (Hermes agent Mumuni only — Tanko has no Hermes gateway)
 ```bash
-ssh root@<CT> "grep Heartbeat ~/.hermes/logs/agent.log | tail -3"
+ssh root@192.168.68.24 "grep Heartbeat ~/.hermes/logs/agent.log | tail -3"
 ```
 Expected: recent heartbeat (within 5 min), `polls=N` incrementing.
 Silence > 300s → warning. Silence > 600s → critical.
-**B4: Response Delivery**
+**B4: Response Delivery** (Hermes agent Mumuni only)
 ```bash
-ssh root@<CT> "grep -E 'Finalized|Failed to finalize|Replied to' ~/.hermes/logs/agent.log | tail -10"
+ssh root@192.168.68.24 "grep -E 'Finalized|Failed to finalize|Replied to' ~/.hermes/logs/agent.log | tail -10"
 ```
 > 50% fail rate → critical.
@@ -229,7 +228,7 @@ ssh root@<CT> "grep -E 'Finalized|Failed to finalize|Replied to' ~/.hermes/logs/
 | Condition | Action |
 |-----------|--------|
-| `zulip.state != "connected"` | `ssh root@<CT> "pkill -f 'gateway run'; sleep 2; hermes gateway restart"` |
+| `zulip.state != "connected"` | `ssh root@<CT> "pkill -f 'gateway run'; sleep 2; hermes gateway restart"` (Mumuni) / restart Tanko via DSH service |
 | No heartbeat in 10min | Same as above |
 | `Failed to finalize` > 50% | Check PATCH API, Zulip server |
 | Response empty/short | Check A2A endpoint / LiteLLM model |
@@ -10,7 +10,7 @@ description: >
 > **⚠️ RETIRED** — The pi Zulip extension (`~/.pi/agent/extensions/zulip/`) and
 > PM2 process (`abiba-zulip`) have been decommissioned. All mention/reliability
-> monitoring now happens through Telegram. Hermes agents (Tanko, Mumuni) and
+> monitoring now happens through Telegram. Agents (Mumuni on Hermes, Tanko on DSH) and
 > Agent Zero (kagentz) continue to use Zulip.
 ## Maintains
@@ -420,7 +420,7 @@ Backup v2 before starting: `cp index.js index.js.v2-backup-$(date +%Y%m%d-%H%M%S
 |-------|----------|-------------|--------------|-------------|
 | **Abiba** | pi (CT 100) | ✅ Connected | API key missing from Infisical injection; poll timeout noise | Added .env fallback; AbortError treated as empty poll (no retry); poll timeout 65s→90s |
 | **Tanko** | Hermes (CT 112) | ✅ Connected | Gateway disconnected since Jul 11; watchdog restart didn't re-establish Zulip | Full gateway restart (kill wrapper, let infisical-gateway.sh respawn) |
-| **Mumuni** | Hermes (inside Abiba CT 100) | ✅ Connected | No issues found | None needed |
+| **Mumuni** | Hermes (kagentz CT 105, migrated 2026-08-29) | ✅ Connected | No issues found | None needed |
 ### Key Fixes Applied
@@ -13,7 +13,8 @@ triggers:
 > **⚠️ RETIRED** — This contract was embedded in the pi Zulip extension code
 > (`performHealthCheck()`). That code has been removed. Zulip self-healing for
-> Hermes agents (Tanko, Mumuni) continues through their own gateway monitoring.
+> agents (Mumuni on Hermes, Tanko on DSH) continues through their own platform
 > monitoring.
 ## Maintains
@@ -65,8 +66,7 @@ triggers:
 |------|----|------|---------|
 | Zulip server | 192.168.68.19 | root | Docker: `zulip-zulip-1` |
 | Abiba (pi) | localhost | root | PM2: `abiba-zulip` |
-| Mumuni | 192.168.68.24 (CT100 abiba) | root | `hermes gateway restart` |
+| Tanko | 192.168.68.122 (CT 112) | jerome | DSH (DeepSeek Harness) — restart via DSH service, not `hermes gateway restart` (no longer a Hermes agent since 2026-08-27) |
 | Tanko | 192.168.68.122 | jerome | `PATH=$PATH:/home/jerome/.hermes/hermes-agent hermes gateway restart` |
 ## Debounce