Merge branch 'master' into fm/infra-maint-contract

Reviewed-on: #23

AGENTS.md

@@ -128,3 +128,10 @@ safe-mutate --verify "CMD" [--expect "PATTERN"] --mutate "CMD" [--reason "WHY"]
 Read the [Authoring Guide](docs/AUTHORING-GUIDE.md) before writing any new contract.
 It covers the full process: verify → draft → lint → review → ship, with templates
 and style rules.
+
+## Maintaining this file
+
+Keep this file for knowledge useful to almost every future agent session in this project.
+Do not repeat what the codebase already shows; point to the authoritative file or command instead.
+Prefer rewriting or pruning existing entries over appending new ones.
+When updating this file, preserve this bar for all agents and keep entries concise.

CLAUDE.md

@@ -0,0 +1 @@
+AGENTS.md

contract-registry.yaml

@@ -22,6 +22,7 @@ owners:
 - abiba
 - mumuni
 - kwame
+- ops
 trigger_types:
 - scheduled
 - event_driven
@@ -58,6 +59,7 @@ index:
     - memory-audit-maintenance
     - gpu-fleet
     - infrastructure-update
+    - infrastructure-maintenance
     reference:
     - infrastructure-control
     - ra-h-os-custodianship-contract
@@ -90,6 +92,7 @@ index:
     - infrastructure-control
     - infrastructure-monitoring
     - infrastructure-update
+    - infrastructure-maintenance
     - pm2-self-heal
     - disk-gc-threat-response
     gpu:
@@ -130,7 +133,6 @@ index:
     - build-zulip-plugin
     - stirling-pdf-agent-access
     - gpu-fleet
-    - infrastructure-update
     - infrastructure-control
     - zulip-adapter-lessons
     - pi-approval-architecture
@@ -144,6 +146,9 @@ index:
     - mumuni-delegation
     kwame:
     - hello-world
+    ops:
+    - infrastructure-maintenance
+    - infrastructure-update
   by_trigger:
     scheduled:
     - hermes-key-enforcement
@@ -156,6 +161,7 @@ index:
     - litellm-health
     - memory-audit-maintenance
     - infrastructure-update
+    - infrastructure-maintenance
     event_driven:
     - litellm-self-heal
     - pm2-self-heal
@@ -197,6 +203,7 @@ index:
     - hermes-zulip-plugin
     - build-zulip-plugin
     - infrastructure-update
+    - infrastructure-maintenance
     - ra-h-os-custodianship-contract
     - mumuni-delegation
     normal:
@@ -1256,13 +1263,108 @@ contracts:
   last_run: null
   last_status: null
   drift_alerts: []
+- name: infrastructure-maintenance
+  file: infrastructure-maintenance.prose.md
+  kind: responsibility
+  category: maintenance
+  sensitivity: high
+  status: active
+  owner: ops
+  version: 1.0.0
+  trigger:
+    type: scheduled
+    cadence: 0 2 * * 0
+    description: Weekly host-level maintenance Sunday at 2am ET (replaces infrastructure-update
+      build-phase role; infra-update moves to ops)
+    cron_job_id: null
+  execution:
+    agent: ops
+    timeout: 3600
+    requires:
+    - infrastructure-monitoring run within last 30 minutes (pre-update health baseline)
+    - Proxmox snapshot of primary host OR /tmp backup dir created this run
+    - LiteLLM master key from Infisical vault for health verification
+    protocol:
+    - Load contract from prose-contracts/main
+    - Phase 0 preflight — capture health baseline, backup check, record image baseline
+    - Phase 1 apt update && apt upgrade -y on primary host
+    - Phase 2 docker compose pull for LiteLLM, SearXNG, and other running containers
+    - Phase 3 restart stacks one at a time with per-stack health verification
+    - Phase 4 verify every critical service (LiteLLM, SearXNG, Zulip, Gitea, PM2, Hermes gateways)
+    - On failure — rollback per protocol, escalate, do not loop beyond circuit breaker
+    - Log actions to ~/.hermes/runs/infrastructure-maintenance/
+  verification:
+    postconditions:
+    - check: all critical services running after update
+      verify: 'curl -sf http://192.168.68.116/litellm/v1/models && curl -sf https://chat.sysloggh.net/api/v1/server_settings && curl -sf https://git.sysloggh.net/api/v1/version && curl -sf http://192.168.68.7:8888 && pm2 jlist'
+      expect: all probes 200 OK / processes online
+    - check: no regressions from pre-update health baseline
+      verify: diff Phase 0 health-baseline against Phase 4 results
+      expect: no GREEN service turned RED
+    - check: docker containers on latest stable tags
+      verify: docker inspect --format '{{.Config.Image}}' <container> per service matches image-baseline.pulled_tag
+      expect: all containers running pulled tags
+    - check: APT packages up to date with no held broken packages
+      verify: apt list --upgradable 2>/dev/null | wc -l and apt-get -s upgrade | grep -ci broken
+      expect: upgradable == 0, broken == 0
+    artifact: maintenance run report with phase results and any rollback/escalation
+    verify_commands:
+    - curl -sf http://192.168.68.116/litellm/v1/models
+    - curl -sf http://192.168.68.7:8888
+    - curl -sf https://chat.sysloggh.net/api/v1/server_settings
+    - curl -sf https://git.sysloggh.net/api/v1/version
+    - pm2 jlist
+  receipt:
+    format: json
+    storage: ~/.hermes/runs/infrastructure-maintenance/
+    graph_node: true
+    schema:
+      contract: string
+      run_id: string
+      timestamp: ISO 8601
+      agent: string
+      status: pass|fail|escalated
+      phase: preflight|apt|images|restarts|verify|rollback|done|failed
+      actions_taken: array
+      postconditions: array
+      drift_alerts: array
+      evidence_path: string
+  escalation:
+    info:
+      action: log_to_receipt
+      notify: []
+    warning:
+      action: relay_alert
+      notify:
+      - abiba
+      - mumuni
+    critical:
+      action: relay_alert
+      notify:
+      - abiba
+      - mumuni
+    fatal:
+      action: relay_alert + pause + human_required
+      notify:
+      - abiba
+      - mumuni
+      - kwame
+  circuit_breaker:
+    max_retries: 2
+    window: 7200
+    trip_action: escalate_to_fatal
+  depends_on:
+  - infrastructure-monitoring
+  last_run: null
+  last_status: null
+  drift_alerts: []
 - name: infrastructure-update
   file: infrastructure-update.prose.md
   kind: responsibility
   category: maintenance
   sensitivity: high
   status: active
-  owner: abiba
+  owner: ops
   version: 1.0.0
   trigger:
     type: scheduled

gpu-self-heal.prose.md

@@ -6,10 +6,15 @@ description: >
   benchmarks, and predicts failures before they happen. Extends gpu-monitor
   (v2.1.0) with active remediation rules, Prometheus metrics consumption,
   VRAM trend analysis, and predictive alerting.
+  UPDATED 2026-07-18: Model assignments synced to 2026-07-17 swaps.
+  Router (port 9000) references replaced with direct GPU routing.
+  Benchmark baselines refreshed to live values.
+  Prometheus exporters removed — not deployed; fall back to direct sidecar probes.
+  Stable role-based aliases (strix-moe, gpu-dense, gpu-light) from gpu-fleet.
 agent: abiba
 depends_on:
   - gpu-monitor.prose.md (live data source on .24:9100)
-  - gpu-fleet.prose.md (source of truth for topology)
+  - gpu-fleet.prose.md (source of truth for topology, aliases, model assignments)
 ---
 
 ## Maintains
@@ -22,8 +27,8 @@ depends_on:
 
 ## Requires
 
-- gpu-monitor:function — Live fleet data from .24:9100/gpu-data
+- gpu-monitor:function — Live fleet data from localhost:9100/gpu-data
-- Prometheus exporters on all 3 GPUs (:9400/metrics)
+- Direct sidecar probe access to all GPU hosts (:8080/health)
 - SSH access to GPU hosts for restart operations
 
 ## Continuity
@@ -35,21 +40,37 @@ depends_on:
 
 ---
 
+## Current Fleet Baseline (2026-07-18)
+
+| Alias | GPU | Host | Model | VRAM | Ctx | tok/s | Role |
+|-------|-----|------|-------|------|-----|-------|------|
+| `gpu-dense` | RTX 3090 24GB | ct8 (.8:8080) | ThinkingCap Qwen3.6-27B Q4_K_M + MTP + vision | 21.6/24.6GB (88%) | 128K | 74.9 | Heavy reasoning, code gen |
+| `gpu-light` | RTX 5070 12GB | ct110 (.110:8080) | 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) | Genesis Hermes V3 APEX (LuffyTheFox, 24GB) | ~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.
+- 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).
+
 ## Remediation Rules
 
 ### Rule 1: GPU Temperature Critical (>85°C for >2 min)
 - **Detect**: Any GPU temp >85°C sustained for 2+ consecutive polls
 - **Fix**: 
   1. Reduce inference concurrency on that GPU (load-side cooling only — NO fan control)
-  2. Redirect new requests to cooler GPUs via LiteLLM fallback chains
+  2. Redirect new requests to cooler GPUs via LiteLLM fallback chains (gemma → qwen, qwen → gemma)
   3. If all GPUs hot, alert about cooling infrastructure
 - **Verify**: Temp drops below 80°C within 5 minutes
 - **Escalate after**: 3 verification failures → Zulip alert
 
 ### Rule 2: VRAM Leak Detection (tiered by GPU capacity)
 - **Detect**: VRAM growing at sustained rate over 6+ hour window
-  - RTX 3090 (24GB): ≥100MB/hour
+  - RTX 3090 (24GB): ≥300MB/hour
-  - RTX 5070 (12GB): ≥50MB/hour
+  - RTX 5070 (12GB): ≥300MB/hour
   - Strix Halo (64GB UMA): ≥200MB/hour
 - **Fix**: 
   1. Log VRAM snapshot with process list (nvidia-smi/rocm-smi + ps aux)
@@ -69,6 +90,9 @@ depends_on:
 
 ### Rule 4: Benchmark Regression (>20% drop)
 - **Detect**: gen_tok_per_sec drops >20% below baseline over 3+ benchmarks
+  - RTX 3090 baseline: 74.8 tok/s → alert at <59.8 tok/s
+  - RTX 5070 baseline: 165.2 tok/s → alert at <132.2 tok/s
+  - Strix Halo baseline: 70.5 tok/s → alert at <56.4 tok/s
 - **Fix**:
   1. Check GPU utilization — if >90%, other process is competing
   2. Check power limit — if throttled, restore to max
@@ -78,32 +102,31 @@ depends_on:
 
 ### Rule 5: Circuit Breaker Stuck Open
 - **Detect**: Circuit breaker open >10 minutes with GPU reporting healthy
+- **Note**: Router (port 9000) is deprecated. If circuit breakers are reported by gpu-monitor, they come from LiteLLM's internal tracking, not the old router.
 - **Fix**: 
-  1. Verify GPU /health returns 200
+  1. Verify GPU /health returns 200 on direct port (:8080)
-  2. If GPU healthy, send 1 test inference
+  2. If GPU healthy, alert but do NOT reset via router API (deprecated)
-  3. If test succeeds → reset circuit breaker via router API
+  3. Check LiteLLM health directly: http://192.168.68.116/litellm/health/liveliness
-  4. 60s cooldown — if CB re-opens immediately, it was legitimate, do NOT re-reset
+  4. Restart LiteLLM container on CT 116 if circuit breakers are stuck
-  5. Max 1 auto-reset per GPU per hour
+- **Verify**: LiteLLM returns healthy, circuit breaker clears within 60s
-- **Verify**: CB closes, inference succeeds, CB stays closed for 60s+
+- **Escalate after**: LiteLLM restart doesn't clear → human investigation
-- **Escalate after**: CB won't close after reset → router issue
 
 ### Rule 6: Strix Halo Unreachable
 - **Detect**: Strix not responding — probe .15:8080 directly (firewall opened .24→.15)
 - **Fix**: 
   1. SSH to .15 → check llama-server process
   2. Restart llama-server if not running
-  3. Verify through both direct probe AND router
+  3. Verify through both direct probe AND LiteLLM health
-- **Verify**: Direct health probe returns 200, router reports Strix healthy
+- **Verify**: Direct health probe returns 200, LiteLLM reports model healthy
 - **Escalate**: If host .15 itself is unreachable → infrastructure alert
 
-### Rule 7: Prometheus Exporter Down
+### Rule 7: GPU Data Source Unreachable (replaces old Prometheus rule)
-- **Detect**: Any GPU :9400/metrics unreachable for >2 polls
+- **Detect**: gpu-monitor endpoint (localhost:9100/gpu-data) or sidecar port (:8080) on any GPU unreachable for >2 polls
 - **Fix**:
-  1. SSH to GPU host → check prometheus-exporter process
+  1. If gpu-monitor is down: restart systemd service `gpu-monitor.service` on this host
-  2. Restart exporter if dead
+  2. If sidecar is down: SSH to GPU host → check llama-server process → restart systemd service
-  3. While exporter is down, fall back to nvidia-smi/rocm-smi direct probes
+  3. Fall back to direct nvidia-smi/rocm-smi probe via SSH if all API paths fail
-  4. If exporter is running but unreachable → check firewall/host networking
+- **Verify**: gpu-monitor returns healthy + all sidecars reachable
-- **Verify**: :9400/metrics returns 200
 - **Escalate after**: 3 failed restarts → networking issue
 
 ### Rule 8: Predictive Thermal Warning (two-tier)
@@ -117,29 +140,31 @@ depends_on:
 - **Escalate**: If Tier 2 triggers and temp still rising after 5 min → possible hardware failure
 
 ### Rule 9: Context Window Optimization
-- **Detect**: Benchmark tok/s vs baseline for each GPU at current context
+- **Detect**: Benchmark tok/s vs baseline for each GPU at current context (all 128K)
-  - RTX 3090 (128K ctx, qwen3.6-27B-code): target 75+ tok/s — currently at baseline
+  - RTX 3090 (128K ctx, ThinkingCap): baseline 74.8 tok/s — currently at 74.9 (100%)
-  - RTX 5070 (128K ctx, gemma-4-12b): target 76+ tok/s — optimal for vision/web role
+  - RTX 5070 (128K ctx, HauhauCS QAT): baseline 165.2 tok/s — currently at 169.6 (103%)
-  - Strix Halo (128K ctx, strix-moe / qwen3.6-35B-udq4): target 70+ tok/s — currently above baseline
+  - Strix Halo (128K ctx, Genesis Hermes V3): baseline 70.5 tok/s — currently at 62.9 (89%)
 - **Fix**:
   - If tok/s > baseline → context has headroom, consider increasing
   - If tok/s < 90% baseline → reduce context by 25% and retest
   - If tok/s within 10% of baseline → optimal, no change
+  - Strix Halo at 89% of baseline → MONITOR but do not reduce yet (recent model swap may still be settling)
 - **Verify**: Re-benchmark after context change, confirm within 10% of target
 - **Escalate**: If context can't be adjusted without significant perf loss
 
-### Rule 10: Workload Distribution Optimization
+### Rule 10: Workload Distribution Optimization (updated 2026-07-18)
 - **Detect**: GPU roles misaligned with hardware capabilities
 - **Target distribution**:
-  - RTX 3090 (24GB, 128K, 75 tok/s) → Heavy reasoning, code gen, long conversations
+  - 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 (12GB, 128K, 76 tok/s) → Vision/image, web search, quick lightweight tasks
+  - RTX 5070 (gpu-light, 12GB, 169.6 tok/s) → Vision/image, web search, lightweight tasks (2.3x faster than 3090 per token). Weight: 0.15 (LiteLLM).
-  - Strix Halo (64GB, 128K, 72 tok/s) → Context compression, summarization, long docs
+  - 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**:
   - Alert if any GPU is handling workload outside its designated role
-  - Recommend Hermes agent profile updates to match workload to GPU
+  - Recommend agent alias updates to match workload to GPU role (use stable aliases: gpu-dense, gpu-light, strix-moe)
   - Track per-GPU request distribution via LiteLLM spend logs
 - **Verify**: Each GPU's request pattern matches its designated role within 24h
-- **Escalate**: If role mismatch persists >48h → agent profile audit needed
+- **Escalate**: If role mismatch persists >48h → agent alias audit needed
 
 ---
 
@@ -148,7 +173,7 @@ depends_on:
 ```prose
 -- Phase 1: Fetch live GPU data
 let fleet = call gpu-monitor
-  endpoint: "http://192.168.68.24:9100/gpu-data"
+  endpoint: "http://localhost:9100/gpu-data"
 
 -- Phase 2: Evaluate each GPU against remediation rules
 let actions = []
@@ -164,27 +189,25 @@ for gpu in fleet.gpus:
   
   -- Rule 4: Benchmark regression
   let bench = fleet.benchmarks[gpu.hostname]
-  if bench.current_tok_sec < bench.baseline_tok_sec * 0.8:
+  if bench.current_tok_s < bench.baseline_tok_s * 0.8:
     push actions apply-benchmark-fix(gpu, bench)
 
 -- Rule 3: Model stuck
-for model in fleet.router.available_models:
+for model in fleet.summary.available_models:
   if model.consecutive_timeouts >= 3:
     push actions apply-model-restart(model)
 
--- Rule 5: Circuit breaker
+-- Rule 5: Circuit breaker check via LiteLLM (router deprecated)
-for cb in fleet.router.circuit_breaker:
+if fleet.summary.circuit_breakers_open > 0:
-  if cb.open and cb.open_duration > 600 and gpu_is_healthy(cb.gpu):
+  push actions check-litellm-circuit-breakers()
-    push actions apply-cb-reset(cb)
 
 -- Rule 6: Strix Halo
 if not fleet.strix.running and pingable("192.168.68.15"):
   push actions apply-strix-restart()
 
--- Rule 7: Prometheus exporters
+-- Rule 7: GPU data source
-for gpu in fleet.gpus:
+if not fleet.gpus or len(fleet.gpus) < 2:
-  if not prometheus_reachable(gpu.hostname, 9400):
+  push actions check-gpu-monitor-service()
-    push actions apply-exporter-restart(gpu)
 
 -- Rule 8: Predictive thermal
 for gpu in fleet.gpus:
@@ -212,12 +235,12 @@ call update-gpu-health
 
 ```json
 {
-  "run_id": "gpu-self-heal-20260712-001",
+  "run_id": "gpu-self-heal-20260718-001",
-  "timestamp": "2026-07-12T16:00:00Z",
+  "timestamp": "2026-07-18T08:00:00Z",
   "gpu": "ct8-rtx3090",
   "issue": "thermal-critical",
   "detected": { "temp_c": 87, "duration_s": 180 },
-  "action": "set-fan-100pct",
+  "action": "load-shedding",
   "result": "resolved",
   "verification": { "temp_c": 76, "after_s": 300 },
   "escalated": false
@@ -236,52 +259,53 @@ Every action logged as `[GPU-SELF-HEAL] <run_id>` node with full audit trail.
 - `issues_escalated > 0` → "⚠ GPU Self-Heal — <gpu> needs attention"
 - Every 100th clean cycle → "✅ GPU Fleet: All Clear"
 
-### 3. Prometheus/Grafana Integration
+### 3. Weekly Benchmark Report
-- GPU self-heal actions exposed as Prometheus counter metrics
-- Dashboard panel: "GPU Interventions (24h)" showing count/type/result
-
-### 4. Weekly Benchmark Report
 - Per-GPU tok/s trend over 7 days
 - Regression alerts if any GPU degrades >10% week-over-week
 
 ---
 
-## Design Decisions (Grilled & Confirmed — 2026-07-12)
+## Design Decisions (Verified 2026-07-12, Reaffirmed 2026-07-18)
 
 1. **Fan control**: ❌ NO auto fan control. Load-side cooling only (reduce concurrency, redirect).
 2. **Model restart**: ✅ Only if >50% failure rate over 60s + 30s grace period. Not on single stuck request.
 3. **Strix direct access**: ✅ Open firewall .15:8080 → .24 for direct health probe + restart.
-4. **VRAM thresholds**: Tiered — 100MB/h (RTX 3090), 50MB/h (RTX 5070), 200MB/h (Strix).
+4. **VRAM thresholds**: Tiered — **300MB/h** (RTX 3090), **300MB/h** (RTX 5070), 200MB/h (Strix). Previous values (100/50) were too sensitive; raised 2026-07-18 based on operational data.
-5. **CB auto-reset**: ✅ With rate limit — 1 test inference + 60s cooldown + max 1/hour per GPU.
+5. **CB auto-reset**: ✅ Router deprecated — circuit breakers go through LiteLLM health check + container restart if needed. No per-GPU auto-reset.
-6. **Benchmark baseline**: Rolling 30-day average, recalculated weekly. Original baseline kept in Grafana.
+6. **Benchmark baseline**: Rolling 30-day average, recalculated weekly. Current baselines live in gpu-monitor.
 7. **Predictive alerts**: Two-tier — warn at >70°C+rising (>2°C/min), critical at >80°C+rising.
-8. **Prometheus**: Primary source. Fall back to nvidia-smi/rocm-smi direct probes if exporter down.
+8. **Prometheus**: ❌ Not deployed. Use direct sidecar probes (:8080/health) and gpu-monitor API. Prometheus integration deferred until exporters are running on GPU hosts.
 
-## Lessons Learned (2026-07-12)
+## Lessons Learned (2026-07-12, Updated 2026-07-18)
 
 ### L1: API Key Standardization Is Critical
 - All GPU llama-servers MUST use the same api-key as the LiteLLM config.
 - RTX 5070 had `--api-key sk-loc...5678` while LiteLLM sent `not-needed`.
-  This caused cascading 401 → fallback → timeout → 401 loops, burning all retries.
+  This caused cascading 401 → fallback → timeout → 401 loops.
-- **Rule**: Any new GPU or model restart MUST verify api-key matches LiteLLM config.
+- **Rule**: Any new GPU or model restart MUST verify api-key matches LiteLLM config (`not-needed` for direct routing).
 
 ### L2: Fallback Chain Cascading Failures
 - When one model returns 401 (auth) and another is slow (timeout), the fallback
-  chain creates an infinite loop: gemma 401 → qwen timeout → gemma 401 → ...
+  chain creates an infinite loop.
 - **Rule**: If a model returns 401 (auth error), do NOT fall back to it again.
   Mark it as permanently failed for this request.
 
 ### L3: Verify Running State, Not Docs
-- RTX 3090 was documented at 128K context. Actually running at 256K.
+- RTX 3090 was documented at 128K context. Running at 128K (verified 2026-07-18).
-- Parallel count wrong (docs said 2, actual is 1 on RTX 3090).
+- Parallel count: 1 on both RTX 3090 and RTX 5070 (matches docs for current models).
 - **Rule**: Before making decisions, check `/proc/PID/cmdline` on GPU hosts.
 
 ### L4: Infisical Is Not Always Available
-- Tanko's Infisical service token was 404 — gateway ran without API key for hours.
+- Keep a local `.env` fallback for `LITELLM_API_KEY`.
-- **Rule**: Always keep a local `.env` fallback for `LITELLM_API_KEY`.
+- **Rule**: Always verify credential source is reachable before relying on it.
-- Contract hermes-config-template Rule 3 updated.
 
-### L5: Zulip Event Queue Can Silently Die
+### L5: GPU Monitor Response Size Can Cause Self-Heal Crash
-- Mumuni's queue accumulated 41 errors/reconnects then stopped polling.
+- gpu-self-heal crashed with KeyboardInterrupt during json.loads() of 20MB response.
-  Gateway was running but ignoring all messages.
+- Root cause: router poll returns accumulated data → cache balloons.
-- **Rule**: litellm-health-check now monitors gateway responsiveness via Zulip API.
+- **Rule**: Self-heal must enforce a read timeout AND max response size on every poll.
+  If monitor response > 1MB, log a warning and skip the cycle rather than crashing.
+
+### L6: Stable Aliases Replace Model Names
+- gpu-fleet introduced stable aliases (strix-moe, gpu-dense, gpu-light) on 2026-07-15.
+- Self-heal must use aliases for reporting and alerting, not model-specific names.
+- **Rule**: All alert messages and KG nodes use the stable alias as the GPU identifier.

hermes-agent-baseline.prose.md

@@ -193,6 +193,8 @@ Key is injected via `infisical run --` wrapper at PM2 startup:
       "models": [
         { "id": "syslog-auto" },
         { "id": "strix-moe" },
+        { "id": "gpu-dense" },
+        { "id": "gpu-light" },
         { "id": "qwen3.6-27B-code" },
         { "id": "gemma-4-12b" }
       ]

hermes-config-template.prose.md

@@ -325,7 +325,8 @@ verify ALL FOUR of these against the live config. They are the only root causes
 
 One-line agent health check (run on the agent host):
 ```bash
-PID=$(pgrep -f "python -m hermes_cli.main gateway run" | head -1)
+# Use grep -v infisical to avoid matching the bash wrapper that contains the same string
+PID=$(pgrep -f "python -m hermes_cli.main gateway run" | grep -v infisical | head -1)
 cat /proc/$PID/environ | tr '\0' '\n' | grep ^LITELLM_API_KEY= | sed 's/=.*/<set>/'
 curl -s -o /dev/null -w 'key_health: %{http_code}\n' -H "Authorization: Bearer $(cat /proc/$PID/environ | tr '\0' '\n' | grep ^LITELLM_API_KEY= | cut -d= -f2)" http://192.168.68.116/v1/models
 ```
@@ -351,9 +352,19 @@ directly (no infisical). Apply with `systemctl daemon-reload && systemctl restar
 The wrapper sources `~/.hermes/.env` then exports `LITELLM_API_KEY="$<AGENT>_LITELLM_API_KEY"`.
 See litellm-api-keys.prose.md § Machine Identity for Vault Writes for vault sync.
 
+**⚠️ Vault empty-key guard:** If the vault stores the secret as an empty string,
+the wrapper will inject an empty key and the gateway will silently get 401 errors
+on all LiteLLM requests (triggering silent DeepSeek fallback). The `.env` fallback
+is present but the vault takes precedence when the secret key exists (even if empty).
+
+**Fix:** The wrapper MUST validate the key length after injection. If LITELLM_API_KEY
+is empty or shorter than 20 chars, log a warning and either fail with a clear error
+message or fall back to the `.env` value before starting the gateway.
+
 **Verification (all agents):**
 ```bash
-GP=$(pgrep -f "python -m hermes_cli.main gateway run" | head -1)
+# Use grep -v infisical to avoid matching the bash wrapper that contains the same string
+GP=$(pgrep -f "python -m hermes_cli.main gateway run" | grep -v infisical | head -1)
 K=$(cat /proc/$GP/environ | tr '\0' '\n' | grep '^LITELLM_API_KEY=' | cut -d= -f2)
 curl -s -o /dev/null -w '%{http_code}' -H "Authorization: Bearer $K" http://192.168.68.116/v1/models  # must be 200
 ```

infrastructure-maintenance.prose.md

@@ -0,0 +1,200 @@
+---
+kind: responsibility
+name: infrastructure-maintenance
+description: >
+  Weekly system-level maintenance for the Syslog inference fleet: OS package
+  updates on the primary host, Docker image pulls for LiteLLM/SearXNG and other
+  running containers, container restarts with health verification, post-update
+  verification of every critical service (LiteLLM proxy, SearXNG, Zulip, Gitea,
+  PM2 processes, Hermes gateways), and rollback on failure. Consolidates the
+  raw shell scripts that previously did this piecemeal. This contract owns the
+  HOST-LEVEL weekly maintenance loop on the primary host plus Docker image
+  pulls ONLY for .116 and .7, while infrastructure-update owns the FULL-FLEET
+  cluster-wide wave (apt across the full PVE cluster + CTs/VMs AND its Docker
+  image Wave 3 across all stacks). Runs Sunday 2am ET. Owner:
+  ops (firstmate secondmate). Blast radius: an unverified image pull can break
+  LiteLLM (all agents lose inference) or SearXNG (search-stack down); a bad apt
+  upgrade can leave the host in a half-upgraded state. Pre-update backup check
+  and rollback are mandatory for this reason.
+agent: ops
+triggers:
+  - weekly (Sunday 02:00 ET) via cron
+  - on demand when ops/abiba triggers "infra maintenance"
+version: 1.0.0
+---
+
+## Maintains
+
+- maintenance-status: { phase: idle|preflight|apt|images|restarts|verify|rollback|done|failed, host, step, result, timestamp }
+- image-baseline: { service, current_tag, pulled_tag, digest, updated_at } — last known-good image per container
+- apt-state: { upgradable_before, upgradable_after, held_broken, kernel_reboot_required }
+- health-baseline: snapshot of critical-service health captured pre-update (used for regression check post-update)
+- rollback-snapshot: { backup_path, configs, image_digests, timestamp } — restore point created in preflight
+- maintenance-history: array of past runs with phase results and any escalations
+
+## Scope
+
+Primary host is the maintenance host where apt updates apply. Docker image pulls
+span the two Docker ecosystems that run critical services. infrastructure-update
+runs the full-fleet cluster-wide wave (including its Wave 3 Docker pulls across
+all stacks/hosts); this contract runs a narrower host-level weekly pull limited
+to .116 and .7. Topology, CT IDs, and IPs are live-state fields — verify against
+`infrastructure-control.prose.md` (the source of truth) and the live system
+before mutating.
+
+| Host | IP | Role | Trust |
+|------|----|------|-------|
+| CT 116 (syslog-api) | 192.168.68.116 | LiteLLM proxy + Grafana + Prometheus (inference harness) | ⚠️ VERIFY-BEFORE-USE |
+| VM 109 (docker-vm) | 192.168.68.7 | SearXNG + Firecrawl + home stack (Docker host) | ⚠️ VERIFY-BEFORE-USE |
+| CT 117 (zulip) | 192.168.68.19 | Zulip (storepve bridge IP .19) | ⚠️ VERIFY-BEFORE-USE |
+| Gitea | https://git.sysloggh.net | Prose-contracts + agent configs source control | ⚠️ VERIFY-BEFORE-USE |
+| CT 100 (abiba/pi) | 192.168.68.24 | PM2 processes (pi agent harness) | ⚠️ VERIFY-BEFORE-USE |
+
+> "Primary host" for the apt phase is the host the ops agent runs maintenance
+> from. Confirm which host that is against infrastructure-control before
+> running; do not assume. If the ops agent is containerized/CT-based, apt runs
+> inside that CT.
+
+## Requires
+
+- SSH/exec access to CT 116 (.116) and VM 109 (.7) for Docker operations
+- `apt`, `docker`, `docker compose` available on target hosts
+- LiteLLM master key available (Infisical vault, `LITELLM_API_KEY`) for health verification
+- `infrastructure-monitoring` run completed within the last 30 minutes — provides the pre-update health baseline used by the regression check
+- Writable backup directory `/tmp/infra-maintenance-backup-<date>/` on each mutated host
+- Proxmox snapshot of the primary host available (or confirmed not required) before apt phase
+
+## Continuity
+
+- Self-driven: weekly cron `0 2 * * 0` (Sunday 02:00 ET)
+- Also wakes on: explicit "infra maintenance" trigger from ops/abiba
+- Depends on `infrastructure-monitoring` for the pre-update health baseline — do not run if the last monitoring run is stale (>30 min) or RED; abort and escalate instead
+
+## Execution
+
+### Phase 0 — Preflight (snapshot/backup check + health baseline)
+
+1. **Capture health baseline** — run the `infrastructure-monitoring` postcondition checks (LiteLLM, Zulip, Gitea, SearXNG, Proxmox API) and record results as `health-baseline`. If any critical service is already down, **abort**: maintenance must not run on a degraded fleet.
+2. **Backup check** — confirm a Proxmox snapshot of the primary host exists OR `/tmp/infra-maintenance-backup-<date>/` was created this run. Snapshot critical config files into the backup dir:
+   - `/opt/inference-harness/docker-compose.yml`, `/opt/inference-harness/litellm_config.yaml` (CT 116)
+   - `/opt/search-stack/searxng/docker-compose.yml`, `/opt/search-stack/firecrawl-source/docker-compose.yaml` (VM 109)
+3. **Record image baseline** — `docker inspect --format '{{.Image}} {{.Config.Image}}' <container>` for every running container on .116 and .7; store digests in `image-baseline` so rollback can restore them.
+4. **Disk check** — `df -h` on each mutated host; abort if free space <20% (apt upgrade + image pulls need headroom).
+
+### Phase 1 — OS package updates (primary host)
+
+```bash
+# On the primary host only (VERIFY host against infrastructure-control first)
+apt update
+apt upgrade -y
+```
+
+- Capture `apt list --upgradable` before and after → store in `apt-state`.
+- If apt reports held/broken packages (`apt-get -s upgrade | grep -i broken`, or non-zero exit), **stop** — do not force. Record `held_broken` and go to rollback/escalate.
+- If `/var/run/reboot-required` exists after upgrade, flag `kernel_reboot_required: true` in `apt-state` but **do not reboot automatically** — that's a separate coordinated action (see infra-update Wave 4). Note it in the report.
+
+### Phase 2 — Docker image pulls
+
+Pull latest stable tags for every running container. Do NOT pin to `:main`/`:nightly` — use stable tags where the compose file specifies them; otherwise `latest`.
+
+```bash
+# CT 116 (.116) — inference harness
+cd /opt/inference-harness && docker compose pull
+
+# VM 109 (.7) — search + home stacks
+cd /opt/search-stack/searxng && docker compose pull
+cd /opt/search-stack/firecrawl-source && docker compose pull
+# any other running stacks on .7 (home stack, audiobookshelf) — pull per their compose files
+```
+
+- LiteLLM and SearXNG are the two explicitly required pulls; "any other running containers" means every stack with a compose file on .116 and .7.
+- Record pulled tag + digest per service in `image-baseline`.
+
+### Phase 3 — Container restarts with health verification
+
+Restart one stack at a time, verify health before moving to the next. Do not restart everything at once — a failure mid-wave must leave the rest running.
+
+```bash
+# CT 116
+cd /opt/inference-harness && docker compose up -d
+# VM 109
+cd /opt/search-stack/searxng && docker compose up -d
+cd /opt/search-stack/firecrawl-source && docker compose up -d
+```
+
+After each stack comes up, wait for health (max 120s):
+- `docker ps` shows the container `Up` (and `healthy` if a healthcheck is defined)
+- Service-specific probe passes (see Phase 4 probes)
+
+If a stack fails to come up within 120s, **stop the wave** and go to rollback for that stack only; do not proceed to the next.
+
+### Phase 4 — Post-update service verification
+
+After ALL updates (apt + images + restarts), verify every critical service is back up and matches the pre-update baseline. This is the regression gate.
+
+| Service | Probe | Expect |
+|---------|-------|--------|
+| LiteLLM proxy | `curl -sf http://192.168.68.116/litellm/v1/models` | 200 OK, models returned |
+| LiteLLM MCP gateway | `curl -sf http://192.168.68.116:4000/mcp-rest/tools/list -H "Authorization: Bearer $MASTER_KEY"` | 90 tools (23 RA-H OS + 67 GitHub) |
+| SearXNG | `curl -sf http://192.168.68.7:8888` | 200 OK |
+| 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 114, Tanko CT 112; `systemctl is-active hermes-gateway` | `active` for each |
+
+Regression check: every service that was GREEN in `health-baseline` must still be GREEN. A service that was already RED (and caused a preflight abort) is excluded — but Phase 0 should have aborted before we got here.
+
+## Rollback Protocol
+
+If ANY service in Phase 4 fails to come back up (or regresses vs baseline):
+
+1. **Image rollback** — for the failing stack, restore the previous image:
+   ```bash
+   # Restore from recorded image-baseline digest
+   docker compose down
+   # Pin the service image to the recorded digest in compose, then recreate
+   #   image: <name>@sha256:<previous_digest>
+   docker compose pull && docker compose up -d
+   ```
+2. **APT rollback** — restore the primary host from the Proxmox snapshot taken/confirmed in Phase 0. If no snapshot, `apt install <pkg>=<old_version>` per package using apt history (`/var/log/apt/history.log`).
+3. **Config rollback** — restore configs from `/tmp/infra-maintenance-backup-<date>/`.
+4. **Re-verify** — re-run the Phase 4 probes on the rolled-back service. If still failing, escalate (do not loop — circuit breaker below).
+5. **Escalate** — send a Zulip DM to abiba + mumuni with: failing service, phase, baseline vs current, rollback actions taken, backup path.
+
+## Circuit Breaker
+
+- `max_retries: 2` per failing phase — after 2 rollback attempts on the same service, stop and escalate.
+- `window: 7200` seconds — no more than 2 retries within a 2-hour window.
+- `trip_action: escalate_to_fatal` — when tripped, escalate to fatal (abiba + mumuni + kwame) and pause; a human must clear before the next scheduled run.
+
+## Report
+
+After completion (or on abort), emit a receipt (JSON) to `~/.hermes/runs/infrastructure-maintenance/` and send a Zulip DM summary:
+
+```
+🛠 Infrastructure Maintenance — YYYY-MM-DD
+
+Phase: apt | images | restarts | verify | rollback
+Primary host: <host>
+APT: <N> packages upgraded, <M> held/broken, kernel_reboot_required=<bool>
+Images pulled: LiteLLM <tag>, SearXNG <tag>, <others>
+Services: all GREEN | <service> FAILED (rolled back)
+Baseline regression: none | <details>
+Backup: /tmp/infra-maintenance-backup-YYYYMMDD/
+Escalation: none | warning | critical | fatal
+```
+
+## Verification Postconditions
+
+- All critical services running after update (Phase 4 all GREEN)
+- No regressions from pre-update health baseline (Phase 0 baseline)
+- Docker containers on latest stable tags (`image-baseline.pulled_tag` recorded)
+- APT packages up to date with no held broken packages (`apt-state.held_broken == 0`)
+
+## Related Contracts
+
+- `infrastructure-update.prose.md` — owns the full-fleet cluster-wide wave INCLUDING its Wave 3 Docker image updates across all stacks (SearXNG, Firecrawl, Inference Harness on .116, home stack, audiobookshelf); infrastructure-maintenance is a deliberately narrower host-level weekly pull scoped to .116 and .7.
+- `infrastructure-monitoring.prose.md` — provides the pre-update health baseline (depends_on).
+- `infrastructure-control.prose.md` — topology source of truth (CT IDs, IPs, hostnames).
+- `litellm-health.prose.md` — LiteLLM probe details.
+- `proxmox-monitor.prose.md` — Docker stats + monitoring stack health.

litellm-api-keys.prose.md

@@ -8,18 +8,18 @@ description: >
   Ensures agents never use the master key directly. Rotation is event-driven,
   not calendar-driven — rotate only on compromise, personnel change, or
   periodic security hygiene (quarterly/annually).
-  
+
   UPDATED 2026-07-12: Keys are stored in Infisical vault (project=agents, env=production)
   BUT each agent host MUST keep a local .env fallback. Infisical service tokens can
   expire/404. The .env fallback prevents agents from running without keys.
   Tanko incident: token 404 → gateway had no LITELLM_API_KEY for hours.
-  
+
   UPDATED 2026-07-16: Vault is SYNCED (session-13 keys written to vault via abiba service
   token, all validate 200). Koby/Koonimo migrated from hardcoded drop-ins to the
   infisical-gateway.sh wrapper (live vault injection). 4/5 agents now vault-backed.
   Canonical process: see § Production Vault Access Process. Tanko (user jerome) pending.
   Abiba's key is now a proper agent key (NOT the master key — stale note removed).
-  
+
   UPDATED 2026-07-17: FLEET-WIDE STANDARDIZATION. All 4 agents (Mumuni, Tanko, Koby, Koonimo)
   standardized on a single pattern: systemd drop-in (ExecStart= reset + wrapper path) →
   infisical-gateway.sh while-true loop → /usr/bin/infisical run --token → bash -c key
@@ -30,7 +30,7 @@ description: >
   Critical lessons: (1) NEVER use shell variables inside single-quoted bash -c in wrappers
   — hardcode absolute paths. (2) Drop-ins override unit file ExecStart permanently.
   (3) Capture /proc/<pid>/environ before gateway restarts to preserve running env set.
-  
+
   Current key inventory and agent list: see gpu-fleet.prose.md § Agent Keys.
   Source of truth for LiteLLM config: /opt/inference-harness/litellm_config.yaml
   on CT 116. Last verified: 2026-07-17.
@@ -154,7 +154,7 @@ through its agent wrapper.
    The `ExecStart=` (empty reset) clears any ExecStart from the main unit file,
    then the second `ExecStart=` sets the wrapper. This drop-in **survives unit file
    regeneration** by `hermes gateway install` — the drop-in always wins.
-   
+
    **Why a drop-in instead of editing the unit file:** `hermes gateway install`
    (called during Hermes updates and some self-heal operations) regenerates the
    systemd unit file with `ExecStart=/path/to/python -m hermes_cli.main gateway run`.
@@ -171,7 +171,7 @@ through its agent wrapper.
 - **Survives gateway crash**: the wrapper's `while true` + systemd `Restart=always` revive the gateway. Two-layer defense.
 - **Survives Hermes updates**: systemd drop-in overrides unit file ExecStart — `hermes gateway install` cannot break the vault injection.
 - **Survives reboot**: systemd user service + `loginctl enable-linger` ensures gateway starts at boot without a login session.
-- **Auditable**: `cat /proc/$(pgrep hermes_cli)/environ` shows all injected keys; `infisical secrets` shows the vault source.
+- **Auditable**: `cat /proc/$(pgrep -f 'python.*hermes_cli.main.gateway.run' | grep -v infisical | head -1)/environ` shows all injected keys (note: pipe through grep -v infisical to avoid matching the bash wrapper); `infisical secrets` shows the vault source.
 
 ### Migration status (2026-07-17)
 

scripts/agent-health-check.py

@@ -184,8 +184,8 @@ def check_agents():
             print(f"  ⬜ {name} (CT {ct}): cannot SSH — skip liveness check")
             continue
 
-        # Gateway process
+        # Gateway process (exclude the infisical bash wrapper that contains the same string)
-        pid = ssh(host, "pgrep -f 'hermes_cli.main gateway run' | head -1", user=user)
+        pid = ssh(host, "pgrep -f 'hermes_cli.main gateway run' | grep -v infisical | head -1", user=user)
         if not pid:
             print(f"  ❌ {name}: GATEWAY NOT RUNNING")
             FAIL.append(f"gateway-down:{name}")

zulip-resilience-v3.prose.md

@@ -409,3 +409,68 @@ Backup v2 before starting: `cp index.js index.js.v2-backup-$(date +%Y%m%d-%H%M%S
 | Queue expiry handling | Crash | Auto re-register |
 | Busy worker deadlock | Router death | Worker SIGKILL + error DM |
 | PM2 restart exhaustion | Yes (max_restarts=10) | No (max_restarts=100 + watchdog) |
+
+---
+
+## Incident Log — 2026-07-18 Fleet-Wide Audit
+
+### Fleet State After Audit
+
+| Agent | Platform | Zulip State | Issues Found | Fix Applied |
+|-------|----------|-------------|--------------|-------------|
+| **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 (CT 114) | ✅ Connected | No issues found | None needed |
+
+### Key Fixes Applied
+
+**1. Abiba — Credential Fallback (L4 Pattern)**
+- Root cause: `zulip.api_key` in config.yaml is `""` (expected from Infisical). Infisical vault `ABIBA_ZULIP_API_KEY` wasn't being injected into the process environment.
+- Fix: Added `.env` file fallback at `/root/.pi/agent/extensions/zulip/.env` with known-working key, sourced before the Infisical `exec`.
+- Lesson: Per L4 from gpu-self-heal, Infisical is not always available — always keep a local `.env` fallback.
+
+**2. Abiba — Poll Timeout Handling**
+- Root cause: Zulip long-poll uses `AbortSignal.timeout(65000)`. Zulip's default `event_queue_longpoll_timeout_seconds` can exceed 65s. When the signal fires, an `AbortError` is thrown and caught by the circuit breaker as a failure.
+- Fix: Caught `AbortError` inside `poll()` and return empty array (no events) instead of throwing. Extended timeout to 90s to match Zulip server default.
+- Reference: [Zulip Events System — long-poll timeout](https://zulip.readthedocs.io/en/11.6/subsystems/events-system.html)
+
+**3. Tanko — Gateway Restart**
+- Root cause: Gateway process was running but Zulip platform stayed in "disconnected" state since Jul 11, 2026. The wrapper script (`infisical-gateway.sh`) restarts on crash but the gateway wasn't re-establishing Zulip on restart.
+- Fix: Killed gateway PID to trigger wrapper restart. New gateway (PID 331991) established Zulip connection successfully.
+
+### Fleet-Wide Zulip Health Metrics (as of 2026-07-18)
+
+| Metric | Value |
+|--------|-------|
+| Zulip server | ✅ HTTP 200 |
+| Agents connected | 3/3 (Abiba, Tanko, Mumuni) |
+| Abiba circuit breaker | CLOSED (0 failures) |
+| Abiba uptime | 2D (post-restart) |
+| Tanko gateway uptime | Ongoing |
+| Mumuni gateway uptime | Ongoing |
+| Watchdog status | ✅ Online (2D uptime) |
+
+### Hermes Agent Zulip Plugin Improvements
+
+Based on the audit, improvements that should be ported to all Hermes Zulip adapters:
+
+1. **Circuit breaker pattern** — Already in Abiba's pi extension. Hermes adapters should add the same CLOSED→OPEN→HALF_OPEN state machine with exponential backoff.
+2. **Credential fallback** — All Hermes agents use Infisical for credentials. Add `.env` local fallback per L4 pattern for `ZULIP_API_KEY`.
+3. **Queue re-registration** — Handle `BAD_EVENT_QUEUE_ID` with automatic re-registration instead of gateway restart.
+4. **Supervisor watchdog** — Hermes uses PM2 which auto-restarts on crash, but has no health-check watchdog. Add lightweight external health checks.
+5. **Streaming** — All agents have `streaming: true` in their zulip config. Verify `edit_message()` is implemented in each adapter.
+
+### Abiba pi Zulip Extension v2 — Implemented Resilience Summary
+
+| Feature | Status | Notes |
+|---------|--------|-------|
+| Circuit breaker | ✅ | CLOSED→OPEN→HALF_OPEN; 50% failure threshold; 30s reset timeout |
+| Retry with jitter | ✅ | 2 attempts, 200ms base, 50-100% jitter |
+| Queue lifecycle | ✅ | 10min idle_queue_timeout; BAD_EVENT_QUEUE_ID handling |
+| Crash prevention | ✅ | uncaughtException + unhandledRejection recovery |
+| Worker timeout | ✅ | 5min busy timeout → SIGKILL + error DM |
+| Health endpoint | ✅ | :9200 with circuit breaker metrics |
+| Echo prevention | ✅ | Dynamic bot user resolution |
+| Poll timeout (AbortError) | ✅ v2.1 | Normal timeout returns [] instead of error |
+| Credential fallback | ✅ v2.1 | .env file before Infisical exec |
+| Provider auto-fix | ✅ | Detects reasoning_content models, switches to compatible |