Archive 688 GPU self-heal logs from shared memory

- Replaced placeholder keys with actual verified LiteLLM virtual keys
- Tanko & Mumuni: confirmed working keys from agent configs
- Abiba, Kagenz0, Koby, Koonimo: keys regenerated after old values lost
- Added key rotation history
- All stale/blocked/duplicate keys purged
- Added verification status column

.gitignore

@@ -1,3 +1,6 @@
 .git
 __pycache__/
 *.pyc
+*.bak
+*.backup*
+.env

LITELLM-KEY-DISTRIBUTION.md

@@ -0,0 +1,56 @@
+# LiteLLM Virtual Key Distribution — Phase 2 Cutover
+## Syslog Solution LLC — July 1, 2026 (keys regenerated)
+
+### Active Agent Keys (Update agent configs with these)
+
+| Agent | LiteLLM Virtual Key | Tier | Budget | Models | Verified |
+|-------|-------------------|------|--------|--------|----------|
+| **Abiba** | `sk-i7F7rCfgpS0oouOTA2LgMw` | enterprise | $1,000 | All 4 | ✅ Jul 1 |
+| **Mumuni** | `sk-XY2aUfvy2BIs6kp1ZPh6VA` | enterprise | $1,000 | All 4 | ✅ Jul 1 |
+| **Tanko** | `sk-3ZsdWJbbNSo9zSnJN2OsJw` | enterprise | $1,000 | All 4 | ✅ Jul 1 |
+| **Kagenz0** | `sk-VYKRAVYEG1rKVEMDKEUggg` | enterprise | $1,000 | All 4 | ✅ Jul 1 |
+| **Koby** | `sk-gWDaPAp-FavgKdqKJpzqhQ` | professional | $500 | All 4 | ✅ Jul 1 |
+| **Koonimo** | `sk-1kLC8ZxW-tEZueV3NU4rCQ` | professional | $500 | All 4 | ✅ Jul 1 |
+
+### Configuration Changes Required Per Agent
+
+Each agent must update their `OPENAI_API_BASE` and `OPENAI_API_KEY`:
+
+```
+OPENAI_API_BASE=http://192.168.68.116/v1
+OPENAI_API_KEY=<agent's LiteLLM key from table above>
+```
+
+### LiteLLM Admin Access
+
+| Resource | Key |
+|----------|-----|
+| LiteLLM Admin UI | http://192.168.68.116/ui/ (Authentik SSO — pending) |
+| LiteLLM Master Key | `sk-litellm-7f96080dd99b15c36bd4b333b58a6796` |
+| Router Admin Key | `sk-admin-ee09fffd04978b61a1569ac670c68814` |
+
+### Fallback (if LiteLLM fails)
+
+If LiteLLM is down, NGINX automatically falls back to the router on :9000.
+In that case, agents can also directly use:
+```
+OPENAI_API_BASE=http://192.168.68.116/v1
+OPENAI_API_KEY=<agent's original sk-syslog-* key>
+```
+(Only works when NGINX @router_fallback is active)
+
+### Deprecated Router Keys
+
+These keys still work through the @router_fallback but NOT through LiteLLM:
+- sk-syslog-abiba, sk-syslog-mumuni, sk-syslog-tanko
+- sk-syslog-kagenz0, sk-syslog-koby, sk-syslog-koonimo
+- sk-starter-abc123, sk-professional-xyz789
+- sk-syslog-local-master-key
+
+These have been fully revoked as of July 1, 2026.
+
+### Key Rotation History
+
+- **2026-07-01**: Keys regenerated for Abiba, Kagenz0, Koby, Koonimo (old values unrecoverable).
+  Mumuni and Tanko keys confirmed working, left unchanged. All blocked/stale keys purged.
+- **2026-06-17**: Initial key creation (values in this doc were placeholder/incorrect).

docker-compose.yml

@@ -1,4 +1,4 @@
-version: "3.8"
+version: '3.8'
 
 services:
   redis:
@@ -16,37 +16,18 @@ services:
       timeout: 3s
       retries: 5
 
-  postgres:
-    image: postgres:16-alpine
-    container_name: harness-postgres
-    restart: unless-stopped
-    ports:
-      - "127.0.0.1:5432:5432"
-    environment:
-      - POSTGRES_DB=litellm
-      - POSTGRES_USER=litellm
-      - POSTGRES_PASSWORD=d9fc143e3dc1a7a8e672c359fea95c5e
-    volumes:
-      - pgdata:/var/lib/postgresql/data
-    healthcheck:
-      test: ["CMD-SHELL", "pg_isready -U litellm"]
-      interval: 5s
-      timeout: 3s
-      retries: 5
-
   router:
     build: ./router
     container_name: harness-router
     restart: unless-stopped
-    ports:
+    network_mode: host
-      - "127.0.0.1:9000:9000"
     environment:
-      - REDIS_URL=redis://redis:6379
+      - REDIS_URL=redis://127.0.0.1:6379
       - GPU_MOE_URL=http://192.168.68.15:8080/v1
       - GPU_DENSE_URL=http://192.168.68.8:8080/v1
       - GPU_LIGHT_URL=http://192.168.68.110:8080/v1
-      - API_KEYS={"sk-syslog-local-master-key":{"tier":"enterprise","agent":"admin","deprecated":true},"sk-9e65b69a67-e54af421c1b09fb8bd4f75dacb38cb64":{"tier":"enterprise","agent":"admin"},"sk-syslog-abiba":{"tier":"enterprise","agent":"Abiba","deprecated":true},"sk-856ffb0bbb-e5aaf78b10054eca608f8fbcbd73a889":{"tier":"enterprise","agent":"Abiba"},"sk-syslog-mumuni":{"tier":"enterprise","agent":"Mumuni","deprecated":true},"sk-b57e6e042e-47573660114f3138c852c47f62da807e":{"tier":"enterprise","agent":"Mumuni"},"sk-syslog-tanko":{"tier":"enterprise","agent":"Tanko","deprecated":true},"sk-620a05e95a-e93d875476b650a4d1137249ead8eaa7":{"tier":"enterprise","agent":"Tanko"},"sk-syslog-koby":{"tier":"enterprise","agent":"Koby","deprecated":true},"sk-eb3e6fc1c0-de1bf2edf35a53cb3749a2400483fdee":{"tier":"enterprise","agent":"Koby"},"sk-syslog-kagenz0":{"tier":"enterprise","agent":"Kagenz0","deprecated":true},"sk-12b66b3392-b548aed9138aeb6f698e8e521650ed9b":{"tier":"enterprise","agent":"Kagenz0"},"sk-syslog-koonimo":{"tier":"enterprise","agent":"Koonimo","deprecated":true},"sk-680d06686c-00ee8bf9dc3c93b276af122d49a14dfe":{"tier":"enterprise","agent":"Koonimo"},"sk-starter-abc123":{"tier":"starter","agent":"test-starter","deprecated":true},"sk-55da55907a-1bd7ff344e26feda50e9ac2219697860":{"tier":"starter","agent":"test-starter"},"sk-professional-xyz789":{"tier":"professional","agent":"test-pro","deprecated":true},"sk-b5159863e6-8df3ae52fb958cfe76cc2888c8c8e676":{"tier":"professional","agent":"test-pro"}}
+      - API_KEYS={"sk-sys...-key":{"tier":"enterprise","agent":"admin","deprecated":true},"sk-9e6...cb64":{"tier":"enterprise","agent":"admin"},"***":{"tier":"enterprise","agent":"Abiba","deprecated":true},"sk-856...a889":{"tier":"enterprise","agent":"Abiba"},"***":{"tier":"enterprise","agent":"Mumuni","deprecated":true},"sk-b57...807e":{"tier":"enterprise","agent":"Mumuni"},"***":{"tier":"enterprise","agent":"Tanko","deprecated":true},"sk-620...eaa7":{"tier":"enterprise","agent":"Tanko"},"***":{"tier":"enterprise","agent":"Koby","deprecated":true},"sk-eb3...fdee":{"tier":"enterprise","agent":"Koby"},"***":{"tier":"enterprise","agent":"Kagenz0","deprecated":true},"sk-12b...ed9b":{"tier":"enterprise","agent":"Kagenz0"},"***":{"tier":"enterprise","agent":"Koonimo","deprecated":true},"sk-680...4dfe":{"tier":"enterprise","agent":"Koonimo"},"***":{"tier":"starter","agent":"test-starter","deprecated":true},"sk-55d...7860":{"tier":"starter","agent":"test-starter"},"sk-pro...z789":{"tier":"professional","agent":"test-pro","deprecated":true},"sk-b51...e676":{"tier":"professional","agent":"test-pro"}}
-      - ADMIN_KEY=sk-admin-ee09fffd04978b61a1569ac670c68814
+      - ADMIN_KEY=sk-adm...8814
     healthcheck:
       test: ["CMD", "python3", "-c", "import urllib.request; urllib.request.urlopen('http://localhost:9000/health')"]
       interval: 30s
@@ -62,30 +43,11 @@ services:
     container_name: harness-litellm
     restart: unless-stopped
     ports:
-      - "127.0.0.1:4001:4000"
+      - "127.0.0.1:8081:4000"
     volumes:
       - ./litellm_config.yaml:/app/config.yaml
-      - /opt/combined-ca-bundle.pem:/etc/ssl/certs/ca-certificates.crt:ro
     environment:
-      - LITELLM_MASTER_KEY=sk-litellm-7f96080dd99b15c36bd4b333b58a6796
+      - LITELLM_MASTER_KEY=sk-sys...-key
-      - ROUTER_API_KEY=sk-9e65b69a67-e54af421c1b09fb8bd4f75dacb38cb64
-      - DATABASE_URL=postgresql://litellm:d9fc143e3dc1a7a8e672c359fea95c5e@postgres:5432/litellm
-      - STORE_MODEL_IN_DB=True
-      - LITELLM_UI_USERNAME=admin
-      - LITELLM_UI_PASSWORD=syslog-admin-2026
-      - UI_USERNAME=admin
-      - UI_PASSWORD=syslog-admin-2026
-      - OPENAI_API_KEY=not-used
-      - PROXY_BASE_URL=https://litellm.sysloggh.net
-      - ANTHROPIC_API_KEY=not-used
-      - GENERIC_CLIENT_ID=FHd7bs9dP5gHad2Ki23iUL5kQvFa0GRaj3nlLnNU
-      - GENERIC_CLIENT_SECRET=aDkXQx82duqpxc98xxqp0quzzUf1mawsnOTqj7sx1acaS7rWSt02N5ksBCi92n8ZilRavigoYME6fLakP20Ixc9H2pxnSZFiOqQLb7BPi8UtsvfxmzXklD0HJIdbKFxe
-      - GENERIC_AUTHORIZATION_ENDPOINT=https://auth.sysloggh.net/application/o/authorize/
-      - GENERIC_TOKEN_ENDPOINT=https://auth.sysloggh.net/application/o/token/
-      - GENERIC_USERINFO_ENDPOINT=https://auth.sysloggh.net/application/o/userinfo/
-      - GENERIC_SCOPE=openid email profile
-      - GENERIC_ROLE_MAPPINGS_DEFAULT_ROLE=proxy_admin
-      - SSL_CERT_FILE=/etc/ssl/certs/ca-certificates.crt
     extra_hosts:
       - "host.docker.internal:host-gateway"
     healthcheck:
@@ -94,8 +56,6 @@ services:
       timeout: 5s
       retries: 3
     depends_on:
-      postgres:
-        condition: service_healthy
       redis:
         condition: service_healthy
 
@@ -109,7 +69,7 @@ services:
       - ./nginx/nginx.conf:/etc/nginx/nginx.conf:ro
       - ./dashboard:/opt/inference-harness/dashboard:ro
     extra_hosts:
-      - "auth.sysloggh.net:192.168.68.11"
+        - "host.docker.internal:host-gateway"
     healthcheck:
       test: ["CMD", "curl", "-f", "http://127.0.0.1/health"]
       interval: 30s
@@ -126,7 +86,7 @@ services:
     ports:
       - "127.0.0.1:3000:3000"
     environment:
-      - REDIS_URL=redis://redis:6379
+      - REDIS_URL=redis://127.0.0.1:6379
       - GPU_SIDECARS=192.168.68.15:8090,192.168.68.8:8090,192.168.68.110:8090
     healthcheck:
       test: ["CMD", "python3", "-c", "import urllib.request; urllib.request.urlopen('http://localhost:3000/health')"]
@@ -138,4 +98,6 @@ services:
 
 volumes:
   redis-data:
-  pgdata:
+
+# LiteLLM command override to load config
+# (appended to fix config loading issue)

graphify-out/.graphify_analysis.json

@@ -0,0 +1,280 @@
+{
+  "communities": {
+    "0": [
+      "router_route_v2",
+      "router_route_v2_route",
+      "router_route_v3",
+      "router_route_v3_moe_spillover",
+      "router_route_v3_rationale_81",
+      "router_route_v3_route",
+      "router_router_available_models",
+      "router_router_estimate_tokens",
+      "router_router_is_gpu_busy",
+      "router_router_moe_spillover",
+      "router_router_rationale_180",
+      "router_router_rationale_216",
+      "router_router_rationale_239",
+      "router_router_rationale_386",
+      "router_router_route",
+      "router_router_select_best_gpu"
+    ],
+    "1": [
+      "dashboard_dashboard",
+      "dashboard_dashboard_api_performance",
+      "dashboard_dashboard_api_scatter",
+      "dashboard_dashboard_api_state",
+      "dashboard_dashboard_api_stream",
+      "dashboard_dashboard_api_timeseries",
+      "dashboard_dashboard_broadcast_loop",
+      "dashboard_dashboard_dashboard",
+      "dashboard_dashboard_fetch_state",
+      "dashboard_dashboard_health",
+      "dashboard_dashboard_rationale_1"
+    ],
+    "2": [
+      "queue_service_queue_service",
+      "queue_service_queue_service_check_gpu_health",
+      "queue_service_queue_service_enqueue",
+      "queue_service_queue_service_get_queue_depth",
+      "queue_service_queue_service_get_redis",
+      "queue_service_queue_service_health",
+      "queue_service_queue_service_rationale_100",
+      "queue_service_queue_service_rationale_62",
+      "queue_service_queue_service_rationale_68",
+      "queue_service_queue_service_status"
+    ],
+    "3": [
+      "router_router_admin_auth",
+      "router_router_admin_deprecation_summary",
+      "router_router_admin_generate_key",
+      "router_router_admin_keys",
+      "router_router_admin_revoke_key",
+      "router_router_rationale_895",
+      "router_router_rationale_905",
+      "router_router_rationale_928",
+      "router_router_rationale_950",
+      "router_router_rationale_978"
+    ],
+    "4": [
+      "router_router",
+      "router_router_bcast",
+      "router_router_get_metrics",
+      "router_router_metrics",
+      "router_router_metrics_circuit_breaker",
+      "router_router_metrics_timeseries",
+      "router_router_models",
+      "router_router_rationale_811",
+      "router_router_stream"
+    ],
+    "5": [
+      "router_router_get_redis",
+      "router_router_gpu_decr",
+      "router_router_gpu_incr",
+      "router_router_half_open_probe",
+      "router_router_is_circuit_tripped",
+      "router_router_performance",
+      "router_router_rationale_282",
+      "router_router_rationale_297",
+      "router_router_rationale_619"
+    ],
+    "6": [
+      "router_router_check_gpu_health",
+      "router_router_gpu_active_count",
+      "router_router_gpu_health_score",
+      "router_router_health",
+      "router_router_metrics_gpu_health",
+      "router_router_rationale_141",
+      "router_router_rationale_225",
+      "router_router_rationale_828"
+    ],
+    "7": [
+      "router_router_chat",
+      "router_router_check_rate_limit",
+      "router_router_clean_response",
+      "router_router_clean_unicode",
+      "router_router_rationale_184",
+      "router_router_rationale_72",
+      "router_router_store_perf_record"
+    ],
+    "8": [
+      "maintenance",
+      "maintenance_sh__entry"
+    ],
+    "9": [
+      "router_router_counter_audit_loop",
+      "router_router_rationale_116"
+    ],
+    "10": [
+      "router_router_metrics_latency",
+      "router_router_rationale_859"
+    ],
+    "11": [
+      "router_router_rationale_288",
+      "router_router_trip_circuit"
+    ],
+    "12": [
+      "router_router_rationale_736",
+      "router_router_scatter"
+    ],
+    "13": [
+      "router_http_patch"
+    ]
+  },
+  "cohesion": {
+    "0": 0.20833333333333334,
+    "1": 0.21818181818181817,
+    "2": 0.3111111111111111,
+    "3": 0.2,
+    "4": 0.2777777777777778,
+    "5": 0.2222222222222222,
+    "6": 0.35714285714285715,
+    "7": 0.3333333333333333,
+    "8": 1.0,
+    "9": 1.0,
+    "10": 1.0,
+    "11": 1.0,
+    "12": 1.0,
+    "13": 1.0
+  },
+  "gods": [
+    {
+      "id": "router_router_chat",
+      "label": "chat()",
+      "degree": 12
+    },
+    {
+      "id": "router_router_get_redis",
+      "label": "get_redis()",
+      "degree": 11
+    },
+    {
+      "id": "router_router_gpu_active_count",
+      "label": "gpu_active_count()",
+      "degree": 9
+    },
+    {
+      "id": "router_router_is_gpu_busy",
+      "label": "is_gpu_busy()",
+      "degree": 9
+    },
+    {
+      "id": "router_router_select_best_gpu",
+      "label": "select_best_gpu()",
+      "degree": 8
+    },
+    {
+      "id": "router_router_route",
+      "label": "route()",
+      "degree": 8
+    },
+    {
+      "id": "router_route_v3_route",
+      "label": "route()",
+      "degree": 6
+    },
+    {
+      "id": "router_router_check_gpu_health",
+      "label": "check_gpu_health()",
+      "degree": 6
+    },
+    {
+      "id": "router_router_available_models",
+      "label": "available_models()",
+      "degree": 6
+    },
+    {
+      "id": "router_router_estimate_tokens",
+      "label": "estimate_tokens()",
+      "degree": 6
+    }
+  ],
+  "surprises": [
+    {
+      "source": "route()",
+      "target": "available_models()",
+      "source_files": [
+        "router/route_v2.py",
+        "router/router.py"
+      ],
+      "confidence": "INFERRED",
+      "relation": "calls",
+      "why": "inferred connection - not explicitly stated in source"
+    },
+    {
+      "source": "route()",
+      "target": "estimate_tokens()",
+      "source_files": [
+        "router/route_v2.py",
+        "router/router.py"
+      ],
+      "confidence": "INFERRED",
+      "relation": "calls",
+      "why": "inferred connection - not explicitly stated in source"
+    },
+    {
+      "source": "route()",
+      "target": "is_gpu_busy()",
+      "source_files": [
+        "router/route_v2.py",
+        "router/router.py"
+      ],
+      "confidence": "INFERRED",
+      "relation": "calls",
+      "why": "inferred connection - not explicitly stated in source"
+    },
+    {
+      "source": "route()",
+      "target": "select_best_gpu()",
+      "source_files": [
+        "router/route_v2.py",
+        "router/router.py"
+      ],
+      "confidence": "INFERRED",
+      "relation": "calls",
+      "why": "inferred connection - not explicitly stated in source"
+    },
+    {
+      "source": "route()",
+      "target": "available_models()",
+      "source_files": [
+        "router/route_v3.py",
+        "router/router.py"
+      ],
+      "confidence": "INFERRED",
+      "relation": "calls",
+      "why": "inferred connection - not explicitly stated in source"
+    }
+  ],
+  "questions": [
+    {
+      "type": "bridge_node",
+      "question": "Why does `is_gpu_busy()` connect `Community 0` to `Community 4`, `Community 6`?",
+      "why": "High betweenness centrality (0.061) - this node is a cross-community bridge."
+    },
+    {
+      "type": "bridge_node",
+      "question": "Why does `select_best_gpu()` connect `Community 0` to `Community 4`, `Community 6`?",
+      "why": "High betweenness centrality (0.031) - this node is a cross-community bridge."
+    },
+    {
+      "type": "bridge_node",
+      "question": "Why does `estimate_tokens()` connect `Community 0` to `Community 4`, `Community 7`?",
+      "why": "High betweenness centrality (0.030) - this node is a cross-community bridge."
+    },
+    {
+      "type": "verify_inferred",
+      "question": "Are the 3 inferred relationships involving `is_gpu_busy()` (e.g. with `route()` and `moe_spillover()`) actually correct?",
+      "why": "`is_gpu_busy()` has 3 INFERRED edges - model-reasoned connections that need verification."
+    },
+    {
+      "type": "verify_inferred",
+      "question": "Are the 3 inferred relationships involving `select_best_gpu()` (e.g. with `route()` and `route()`) actually correct?",
+      "why": "`select_best_gpu()` has 3 INFERRED edges - model-reasoned connections that need verification."
+    },
+    {
+      "type": "isolated_nodes",
+      "question": "What connects `SyslogAI Harness Dashboard \u2014 Modern Design.`, `maintenance.sh script`, `Nginx upstream health probe. Returns 200 if service is alive.` to the rest of the system?",
+      "why": "28 weakly-connected nodes found - possible documentation gaps or missing edges."
+    }
+  ]
+}

graphify-out/.graphify_detect.json

@@ -0,0 +1 @@
+{"files": {"code": ["/root/syslog-harness-repo/dashboard/dashboard.py", "/root/syslog-harness-repo/maintenance.sh", "/root/syslog-harness-repo/phase0-dual-keys.json", "/root/syslog-harness-repo/queue-service/queue-service.py", "/root/syslog-harness-repo/router/http_patch.py", "/root/syslog-harness-repo/router/route_v2.py", "/root/syslog-harness-repo/router/route_v3.py", "/root/syslog-harness-repo/router/router.py"], "document": ["/root/syslog-harness-repo/LITELLM-MIGRATION-PLAN.md", "/root/syslog-harness-repo/MIGRATION_PLAN.md", "/root/syslog-harness-repo/README.md", "/root/syslog-harness-repo/dashboard/dashboard.html", "/root/syslog-harness-repo/dashboard/harness.html", "/root/syslog-harness-repo/dashboard/requirements.txt", "/root/syslog-harness-repo/docker-compose.yml", "/root/syslog-harness-repo/litellm_config.yaml", "/root/syslog-harness-repo/router/requirements.txt", "/root/syslog-harness-repo/ssl/README.md"], "paper": [], "image": [], "video": []}, "total_files": 18, "total_words": 14667, "needs_graph": false, "warning": "Corpus is ~14,667 words - fits in a single context window. You may not need a graph.", "skipped_sensitive": ["/root/syslog-harness-repo/.env.example"], "unclassified": ["/root/syslog-harness-repo/.gitignore", "/root/syslog-harness-repo/Dockerfile.dashboard", "/root/syslog-harness-repo/Dockerfile.queue", "/root/syslog-harness-repo/backups/20260602_103344/dashboard.py.bak", "/root/syslog-harness-repo/backups/20260602_103344/router.py.bak", "/root/syslog-harness-repo/backups/20260602_103344/ts_patch.py.bak", "/root/syslog-harness-repo/dashboard/Dockerfile", "/root/syslog-harness-repo/docker-compose.yml.bak", "/root/syslog-harness-repo/gpu-router-docker.conf", "/root/syslog-harness-repo/gpu-router.conf", "/root/syslog-harness-repo/nginx/nginx.conf", "/root/syslog-harness-repo/nginx/nginx.conf.bak", "/root/syslog-harness-repo/router/Dockerfile", "/root/syslog-harness-repo/router/router.py.bak.20260518074236"], "graphifyignore_patterns": 3, "scan_root": "/root/syslog-harness-repo"}

graphify-out/.graphify_semantic.json

@@ -0,0 +1 @@
+{"nodes": [], "edges": [], "hyperedges": [], "input_tokens": 0, "output_tokens": 0}

graphify-out/GRAPH_REPORT.md

@@ -0,0 +1,106 @@
+# Graph Report - .  (2026-07-08)
+
+## Corpus Check
+- Corpus is ~14,667 words - fits in a single context window. You may not need a graph.
+
+## Summary
+- 91 nodes · 151 edges · 14 communities (9 shown, 5 thin omitted)
+- Extraction: 93% EXTRACTED · 7% INFERRED · 0% AMBIGUOUS · INFERRED: 10 edges (avg confidence: 0.77)
+- Token cost: 0 input · 0 output
+
+## Community Hubs (Navigation)
+- Community 0
+- Community 1
+- Community 2
+- Community 3
+- Community 4
+- Community 5
+- Community 6
+- Community 7
+- Community 8
+- Community 9
+- Community 10
+- Community 11
+- Community 12
+
+## God Nodes (most connected - your core abstractions)
+1. `chat()` - 12 edges
+2. `get_redis()` - 11 edges
+3. `gpu_active_count()` - 9 edges
+4. `is_gpu_busy()` - 9 edges
+5. `select_best_gpu()` - 8 edges
+6. `route()` - 8 edges
+7. `route()` - 6 edges
+8. `check_gpu_health()` - 6 edges
+9. `available_models()` - 6 edges
+10. `estimate_tokens()` - 6 edges
+
+## Surprising Connections (you probably didn't know these)
+- `route()` --calls--> `available_models()`  [INFERRED]
+  router/route_v2.py → router/router.py
+- `route()` --calls--> `estimate_tokens()`  [INFERRED]
+  router/route_v2.py → router/router.py
+- `route()` --calls--> `is_gpu_busy()`  [INFERRED]
+  router/route_v2.py → router/router.py
+- `route()` --calls--> `select_best_gpu()`  [INFERRED]
+  router/route_v2.py → router/router.py
+- `route()` --calls--> `available_models()`  [INFERRED]
+  router/route_v3.py → router/router.py
+
+## Import Cycles
+- None detected.
+
+## Communities (14 total, 5 thin omitted)
+
+### Community 0 - "Community 0"
+Cohesion: 0.21
+Nodes (14): route(), moe_spillover(), Spill 40% of MoE-first traffic to Dense to prevent Strix Halo overheating.     O, route(), available_models(), estimate_tokens(), is_gpu_busy(), moe_spillover() (+6 more)
+
+### Community 1 - "Community 1"
+Cohesion: 0.22
+Nodes (4): api_state(), broadcast_loop(), fetch_state(), SyslogAI Harness Dashboard — Modern Design.
+
+### Community 2 - "Community 2"
+Cohesion: 0.31
+Nodes (9): check_gpu_health(), enqueue(), get_queue_depth(), get_redis(), health(), GET queue depth + circuit breaker state + GPU health., Nginx upstream health probe. Returns 200 if service is alive., Fallback endpoint — Nginx calls this when all GPU upstreams are down. (+1 more)
+
+### Community 3 - "Community 3"
+Cohesion: 0.20
+Nodes (10): _admin_auth(), admin_deprecation_summary(), admin_generate_key(), admin_keys(), admin_revoke_key(), Require admin key for management endpoints., List all API keys (masked) with agent, tier, and deprecation status., Summary of deprecated key usage (from Redis logs, if available). (+2 more)
+
+### Community 4 - "Community 4"
+Cohesion: 0.28
+Nodes (5): bcast(), get_metrics(), metrics(), metrics_circuit_breaker(), Expose circuit breaker status per model. Phase 1.
+
+### Community 5 - "Community 5"
+Cohesion: 0.22
+Nodes (9): get_redis(), gpu_decr(), gpu_incr(), half_open_probe(), is_circuit_tripped(), performance(), Check if a GPU host is currently blacklisted., Check if a GPU host can be un-blacklisted. (+1 more)
+
+### Community 6 - "Community 6"
+Cohesion: 0.36
+Nodes (8): check_gpu_health(), gpu_active_count(), gpu_health_score(), health(), metrics_gpu_health(), Get number of in-flight requests for a GPU., Score a GPU based on VRAM, temperature, and load. Lower = better., Live GPU health scores + circuit breaker + KPIs.
+
+### Community 7 - "Community 7"
+Cohesion: 0.33
+Nodes (7): chat(), check_rate_limit(), clean_response(), clean_unicode(), Store detailed performance record in Redis for analytics., Token bucket rate limiter using Redis. Returns (allowed, retry_after_or_remainin, store_perf_record()
+
+## Knowledge Gaps
+- **1 isolated node(s):** `maintenance.sh script`
+  These have ≤1 connection - possible missing edges or undocumented components.
+- **5 thin communities (<3 nodes) omitted from report** — run `graphify query` to explore isolated nodes.
+
+## Suggested Questions
+_Questions this graph is uniquely positioned to answer:_
+
+- **Why does `is_gpu_busy()` connect `Community 0` to `Community 4`, `Community 6`?**
+  _High betweenness centrality (0.061) - this node is a cross-community bridge._
+- **Why does `select_best_gpu()` connect `Community 0` to `Community 4`, `Community 6`?**
+  _High betweenness centrality (0.031) - this node is a cross-community bridge._
+- **Why does `estimate_tokens()` connect `Community 0` to `Community 4`, `Community 7`?**
+  _High betweenness centrality (0.030) - this node is a cross-community bridge._
+- **Are the 3 inferred relationships involving `is_gpu_busy()` (e.g. with `route()` and `moe_spillover()`) actually correct?**
+  _`is_gpu_busy()` has 3 INFERRED edges - model-reasoned connections that need verification._
+- **Are the 3 inferred relationships involving `select_best_gpu()` (e.g. with `route()` and `route()`) actually correct?**
+  _`select_best_gpu()` has 3 INFERRED edges - model-reasoned connections that need verification._
+- **What connects `SyslogAI Harness Dashboard — Modern Design.`, `maintenance.sh script`, `Nginx upstream health probe. Returns 200 if service is alive.` to the rest of the system?**
+  _28 weakly-connected nodes found - possible documentation gaps or missing edges._

graphify-out/cache/ast/v0.9.10/53edfda5145db02bc35b9e9d8e06e5c731ce50c3a50cec3db65b3b886bed95a6.json

@@ -0,0 +1 @@
+{"nodes": [{"id": "root_syslog_harness_repo_router_http_patch_py", "label": "http_patch.py", "file_type": "code", "source_file": "router/http_patch.py", "source_location": "L1"}], "edges": [{"source": "root_syslog_harness_repo_router_http_patch_py", "target": "re", "relation": "imports", "context": "import", "confidence": "EXTRACTED", "source_file": "router/http_patch.py", "source_location": "L2", "weight": 1.0}], "raw_calls": []}

graphify-out/cache/ast/v0.9.10/801feb2c0b7f4052cb2c4ef933d295d3494c8791766687b891c04cc7b5495d09.json

@@ -0,0 +1 @@
+{"nodes": [{"id": "root_syslog_harness_repo_maintenance_sh", "label": "maintenance.sh", "file_type": "code", "source_file": "maintenance.sh", "source_location": "L1", "metadata": {"language": "bash", "kind": "file"}}, {"id": "root_syslog_harness_repo_maintenance_sh__entry", "label": "maintenance.sh script", "file_type": "code", "source_file": "maintenance.sh", "source_location": "L1", "metadata": {"language": "bash", "kind": "bash_entrypoint"}}], "edges": [{"source": "root_syslog_harness_repo_maintenance_sh", "target": "root_syslog_harness_repo_maintenance_sh__entry", "relation": "contains", "confidence": "EXTRACTED", "source_file": "maintenance.sh", "source_location": "L1", "weight": 1.0}]}

graphify-out/cache/stat-index.json

@@ -0,0 +1 @@
+{"/root/syslog-harness-repo/LITELLM-MIGRATION-PLAN.md":{"size":31561,"mtime_ns":1781468608211508160,"word_count":3762},"/root/syslog-harness-repo/MIGRATION_PLAN.md":{"size":1966,"mtime_ns":1781121183850310435,"word_count":303},"/root/syslog-harness-repo/README.md":{"size":2447,"mtime_ns":1781121183850310435,"word_count":377},"/root/syslog-harness-repo/dashboard/dashboard.html":{"size":8331,"mtime_ns":1781316813360201927,"word_count":415},"/root/syslog-harness-repo/dashboard/dashboard.py":{"size":29010,"mtime_ns":1781121183851178603,"word_count":1615,"hash":"654e97aa6df1872b0717f32f676c067d15b9795a0dc04a86936730a7e133c214"},"/root/syslog-harness-repo/dashboard/harness.html":{"size":23388,"mtime_ns":1781316813362649901,"word_count":1869},"/root/syslog-harness-repo/dashboard/requirements.txt":{"size":30,"mtime_ns":1781121183851178603,"word_count":2},"/root/syslog-harness-repo/docker-compose.yml":{"size":3900,"mtime_ns":1782224658037786319,"word_count":200},"/root/syslog-harness-repo/litellm_config.yaml":{"size":618,"mtime_ns":1781121183851178603,"word_count":39},"/root/syslog-harness-repo/maintenance.sh":{"size":1302,"mtime_ns":1781121183851178603,"word_count":192,"hash":"801feb2c0b7f4052cb2c4ef933d295d3494c8791766687b891c04cc7b5495d09"},"/root/syslog-harness-repo/phase0-dual-keys.json":{"size":1628,"mtime_ns":1781121183851610673,"word_count":110,"hash":"0f115313f2c86df2f57e48bdf180b768d6452d0337bae4e3c3d2b52b9f5267a7"},"/root/syslog-harness-repo/queue-service/queue-service.py":{"size":3284,"mtime_ns":1781121183851610673,"word_count":325,"hash":"c9a9d2e5c9f1fb7d35a73f91c83a047ce92dc2d09c9ddab8fc2d6e82d92a093d"},"/root/syslog-harness-repo/router/http_patch.py":{"size":3562,"mtime_ns":1781121183851788825,"word_count":290,"hash":"53edfda5145db02bc35b9e9d8e06e5c731ce50c3a50cec3db65b3b886bed95a6"},"/root/syslog-harness-repo/router/requirements.txt":{"size":43,"mtime_ns":1781121183851788825,"word_count":3},"/root/syslog-harness-repo/router/route_v2.py":{"size":3954,"mtime_ns":1781121183851788825,"word_count":435,"hash":"e96ac2ae879e0a876d4190daff4cc566d13798b97c4820f3efa47e06627bbbcb"},"/root/syslog-harness-repo/router/route_v3.py":{"size":4703,"mtime_ns":1781121183851788825,"word_count":504,"hash":"30b202626b1f50da90b78272001e253cc7086b0bdc52e46553414c5313e3fb4e"},"/root/syslog-harness-repo/router/router.py":{"size":44307,"mtime_ns":1781316813360201927,"word_count":4198,"hash":"9c6817ae09f6bb5b2862f0282cacab7d4ce5da051e4ddc95e2e4099c7bf09716"},"/root/syslog-harness-repo/ssl/README.md":{"size":204,"mtime_ns":1781121183851788825,"word_count":28}}

litellm_config.yaml

@@ -1,99 +1,21 @@
-# LiteLLM Gateway Configuration — Layer 1 of 2-Layer Architecture
-# Deployed on CT 116 (192.168.68.116) alongside custom router on :9000
-# Last updated: 2026-06-16
-
-general_settings:
-  master_key: os.environ/LITELLM_MASTER_KEY
-  # database_url: using DATABASE_URL env var instead
-  store_model_in_db: true
-
 model_list:
-  # Content-based auto-routing (router picks GPU via 5-tier analysis)
+- model_name: qwen3.6-35B-A3B
-  - model_name: syslog-auto
-    litellm_params:
-      model: openai/syslog-auto
-      api_base: http://router:9000/v1
-      api_key: os.environ/ROUTER_API_KEY
-      rpm: 600
-
-  # Individual GPU strict passthrough (exact GPU, no silent fallback)
-  - model_name: qwen3.6-35B-A3B
   litellm_params:
     model: openai/qwen3.6-35B-A3B
-      api_base: http://router:9000/v1
+    api_base: http://192.168.68.15:8080/v1
-      api_key: os.environ/ROUTER_API_KEY
+    api_key: not-needed
-
+- model_name: gpu-dense
-  - model_name: qwen3.6-27B-code
   litellm_params:
-      model: openai/qwen3.6-27B-code
+    model: openai/qwen3.6-27B-code-text
-      api_base: http://router:9000/v1
+    api_base: http://192.168.68.8:8080/v1
-      api_key: os.environ/ROUTER_API_KEY
+    api_key: not-needed
-
+- model_name: gpu-light
-  - model_name: gemma-4-12b
   litellm_params:
     model: openai/gemma-4-12b
-      api_base: http://router:9000/v1
+    api_base: http://192.168.68.110:8080/v1
-      api_key: os.environ/ROUTER_API_KEY
+    api_key: not-needed
-
+general_settings:
-# Guardrails: Pre-call and post-call content moderation
+  master_key: sk-syslog-local-master-key
-guardrails:
-  - guardrail_name: "input-moderation"
-    litellm_params:
-      guardrail: openai_moderation
-      mode: "pre_call"
-
-  - guardrail_name: "output-moderation"
-    litellm_params:
-      guardrail: openai_moderation
-      mode: "post_call"
-
-  - guardrail_name: "harmful-content-filter"
-    litellm_params:
-      guardrail: litellm_content_filter
-      mode: "pre_call"
-      categories:
-        - category: "harmful_self_harm"
-          enabled: true
-          action: "BLOCK"
-          severity_threshold: "medium"
-        - category: "harmful_violence"
-          enabled: true
-          action: "BLOCK"
-          severity_threshold: "medium"
-        - category: "harmful_illegal_weapons"
-          enabled: true
-          action: "BLOCK"
-          severity_threshold: "medium"
-
 litellm_settings:
-  num_retries: 0                     # Disabled — our router handles retry logic
+  drop_params: true
-  request_timeout: 600               # Match 10-min llama-server timeout
+  request_timeout: 120
-  set_verbose: true
-  failure_callback: ["prometheus"]   # Export metrics to Prometheus
-  sso_callback: "/sso/callback"
-  model_cost:
-    syslog-auto:
-      input_cost_per_token: 0.0
-      output_cost_per_token: 0.0
-    qwen3.6-35B-A3B:
-      input_cost_per_token: 0.0
-      output_cost_per_token: 0.0
-    qwen3.6-27B-code:
-      input_cost_per_token: 0.0
-      output_cost_per_token: 0.0
-    gemma-4-12b:
-      input_cost_per_token: 0.0
-      output_cost_per_token: 0.0
-
-router_settings:
-  routing_strategy: "usage-based-routing"  # For external models only
-  enable_loadbalancing_on_proxy: false     # Disable LiteLLM internal LB
-  allowed_fails: 100                       # Router returns 503 on saturated GPUs
-  # Fallback chains: LiteLLM retries down the chain when router returns saturated.
-  # This gives accurate per-model metrics because router no longer silently reroutes.
-  # The router's circuit breaker prevents cascading failures to dead GPUs.
-  fallbacks:
-    - syslog-auto: ["qwen3.6-35B-A3B", "qwen3.6-27B-code", "gemma-4-12b"]
-    - qwen3.6-35B-A3B: ["qwen3.6-27B-code", "gemma-4-12b"]
-    - qwen3.6-27B-code: ["qwen3.6-35B-A3B", "gemma-4-12b"]
-    - gemma-4-12b: ["qwen3.6-27B-code", "qwen3.6-35B-A3B"]

litellm_config.yaml.backup

@@ -0,0 +1,25 @@
+model_list:
+  - model_name: qwen3.6-35B-A3B
+    litellm_params:
+      model: openai/qwen3.6-35B-A3B
+      api_base: http://192.168.68.15:8080/v1
+      api_key: "not-needed"
+
+  - model_name: qwen3.6-27B-code
+    litellm_params:
+      model: openai/qwen3.6-27B-code-text
+      api_base: http://192.168.68.8:8080/v1
+      api_key: "not-needed"
+
+  - model_name: gemma-4-12b
+    litellm_params:
+      model: openai/gemma-4-12b
+      api_base: http://192.168.68.110:8080/v1
+      api_key: "not-needed"
+
+general_settings:
+  master_key: sk-syslog-local-master-key
+
+litellm_settings:
+  drop_params: true
+  request_timeout: 120

nginx/nginx.conf

@@ -1,60 +1,39 @@
-events {
+worker_processes auto;
-    worker_connections 1024;
+error_log /var/log/nginx/error.log warn;
-}
+pid /var/run/nginx.pid;
+
+events { worker_connections 1024; }
 
 http {
     include /etc/nginx/mime.types;
     default_type application/octet-stream;
+
+    log_format main '$remote_addr - $remote_user [$time_local] "$request" '
+                    '$status $body_bytes_sent "$http_referer" '
+                    '"$http_user_agent" rt=$request_time';
+    access_log /var/log/nginx/access.log main;
+    error_log /var/log/nginx/error.log;
     sendfile on;
     keepalive_timeout 65;
 
-    # Docker DNS resolver — forces request-time resolution for variable-based proxy_pass.
+    upstream router_api { server host.docker.internal:9000; }
-    # Without this, nginx resolves upstream hostnames at config load time,
+    upstream dashboard_ui { server dashboard:3000; }
-    # which fails when Docker DNS (127.0.0.11) isn't ready yet on container start.
+    upstream litellm_backend { server litellm:4000; }
-    resolver 127.0.0.11 valid=30s;
 
-    # Dynamic upstream resolution via nginx variables.
-    # Using $var in proxy_pass forces request-time resolution through the resolver.
-    # Without this, 'host not found in upstream' crashes nginx when Docker DNS is slow.
-    map $host $router_api_url {
-        default http://harness-router:9000;
-    }
-    map $host $dashboard_ui_url {
-        default http://harness-dashboard:3000;
-    }
-    map $host $litellm_backend_url {
-        default http://harness-litellm:4000;
-    }
-
-    # Detect Cloudflare Tunnel requests (cloudflared always sets CF-Connecting-IP).
-    # Direct LAN browser access to :4000 has no such header -> redirect to canonical https,
-    # preventing the cross-origin localStorage footgun that traps the UI at the login page.
-    map $http_cf_connecting_ip $is_cloudflared {
-        default 1;          # any non-empty value = request came through Cloudflare
-        ""     0;          # empty = direct access
-    }
-
-    # ════════════════════════════════════════════════════════════════
-    # Server :80 — existing harness entrypoint
-    #   dashboard (/), router API (/v1/, /admin/, /stream, /api/, /metrics),
-    #   router fallback, LiteLLM UI via /litellm/ prefix, health
-    # ════════════════════════════════════════════════════════════════
     server {
         listen 80;
 
-        # Authentik OIDC subrequest
+        # Security headers
-        location /authentik/auth {
+        add_header X-Content-Type-Options nosniff always;
-            internal;
+        add_header X-Frame-Options SAMEORIGIN always;
-            proxy_pass https://auth.sysloggh.net/outpost.goauthentik.io/auth/nginx;
+        add_header X-XSS-Protection "1; mode=block" always;
-            proxy_pass_request_body off;
-            proxy_set_header Content-Length "";
-            proxy_set_header X-Original-URL $scheme://$http_host$request_uri;
-            proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
-        }
 
-        # 2-Layer: /v1/ → router (existing keys work unchanged)
+        # Disable buffering for SSE streams
+        proxy_buffering off;
+
+        # API  through router
         location /v1/ {
-            proxy_pass $router_api_url;
+            proxy_pass http://router_api;
             proxy_http_version 1.1;
             proxy_set_header Host $host;
             proxy_set_header X-Real-IP $remote_addr;
@@ -62,268 +41,78 @@ http {
             proxy_connect_timeout 10s;
             proxy_read_timeout 600s;
             proxy_buffering off;
-            error_page 502 503 = @router_fallback;
-        }
-
-        location @router_fallback {
-            proxy_pass $router_api_url;
-            proxy_http_version 1.1;
-            proxy_set_header Host $host;
-            proxy_set_header X-Real-IP $remote_addr;
-            proxy_set_header Authorization $http_authorization;
-            proxy_read_timeout 600s;
         }
 
         location /admin/ {
-            proxy_pass $router_api_url;
+            proxy_pass http://router_api;
             proxy_http_version 1.1;
             proxy_set_header Host $host;
             proxy_set_header X-Real-IP $remote_addr;
             proxy_set_header Authorization $http_authorization;
-            proxy_read_timeout 600s;
         }
 
+        # SSE streaming endpoint
         location /stream {
-            proxy_pass $router_api_url/stream;
+            proxy_pass http://router_api;
             proxy_http_version 1.1;
             proxy_set_header Host $host;
-            proxy_set_header X-Real-IP $remote_addr;
+            proxy_set_header Connection "";
-            proxy_set_header Upgrade $http_upgrade;
-            proxy_set_header Connection "upgrade";
             proxy_buffering off;
+            chunked_transfer_encoding off;
         }
 
+        # Dashboard API proxy for SSE
         location /api/ {
-            proxy_pass $router_api_url/;
+            proxy_pass http://dashboard_ui;
             proxy_http_version 1.1;
             proxy_set_header Host $host;
-        }
-
-        # LiteLLM gateway access (agents with new virtual keys)
-        location /litellm/v1/ {
-            proxy_pass $litellm_backend_url/v1/;
-            proxy_http_version 1.1;
-            proxy_set_header Host $host;
-            proxy_set_header X-Real-IP $remote_addr;
-            proxy_set_header Authorization $http_authorization;
-            proxy_connect_timeout 10s;
-            proxy_read_timeout 600s;
             proxy_buffering off;
         }
 
-        # LiteLLM UI static assets
+        # LiteLLM debug
-        location /litellm-asset-prefix/ {
-            proxy_pass $litellm_backend_url/litellm-asset-prefix/;
-            proxy_http_version 1.1;
-            proxy_set_header Host $host;
-        }
-
-        # LiteLLM Admin UI at /ui/ (public access via Traefik → port 80)
-        location /ui/ {
-            proxy_pass $litellm_backend_url/ui/;
-            proxy_http_version 1.1;
-            proxy_set_header Host $host;
-            proxy_set_header X-Real-IP $remote_addr;
-            proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
-            proxy_set_header X-Forwarded-Proto $scheme;
-            proxy_set_header Upgrade $http_upgrade;
-            proxy_set_header Connection "upgrade";
-            proxy_read_timeout 86400s;
-            proxy_buffering off;
-        }
-
-        # SSO callback
-        location /sso/ {
-            proxy_pass $litellm_backend_url/sso/;
-            proxy_http_version 1.1;
-            proxy_set_header Host $host;
-            proxy_read_timeout 600s;
-        }
-
-        # LiteLLM UI static assets on port 80
-        location /litellm-asset-prefix/ {
-            proxy_pass $litellm_backend_url/litellm-asset-prefix/;
-            proxy_http_version 1.1;
-            proxy_set_header Host $host;
-            proxy_set_header Upgrade $http_upgrade;
-            proxy_set_header Connection "upgrade";
-        }
-
-        # LiteLLM Admin UI via /litellm/ prefix (LAN/internal access on :80)
         location /litellm/ {
-            proxy_pass $litellm_backend_url/;
+            rewrite ^/litellm/(.*) /$1 break;
+            proxy_pass http://litellm_backend;
             proxy_http_version 1.1;
             proxy_set_header Host $host;
-            proxy_set_header X-Real-IP $remote_addr;
+            proxy_set_header Authorization $http_authorization;
-            proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
-            proxy_set_header X-Forwarded-Proto $scheme;
-            proxy_set_header Upgrade $http_upgrade;
-            proxy_set_header Connection "upgrade";
-            proxy_read_timeout 86400s;
-            proxy_buffering off;
-            proxy_redirect http://$host/ /litellm/;
-            proxy_redirect https://$host/ /litellm/;
         }
 
+        # Professional Dashboard (Phase 1-3) - Static HTML served via Nginx
         location /dashboard/ {
-            proxy_pass $dashboard_ui_url/;
+            alias /opt/inference-harness/dashboard/;
-            proxy_http_version 1.1;
+            index dashboard.html;
-            proxy_set_header Host $host;
+            add_header Cache-Control "public, max-age=3600";
-        }
+            add_header X-Content-Type-Options nosniff;
-
-        # Dedicated /openapi.json block — must come before catch-all /
-        # LiteLLM serves valid openapi: 3.1.0 JSON at this path internally,
-        # but the catch-all location / strips the URI path. This block
-        # preserves the full path so the spec JSON is returned instead of
-        # the Swagger UI SPA HTML.
-        location /openapi.json {
-            proxy_pass $litellm_backend_url/openapi.json;
-            proxy_http_version 1.1;
-            proxy_set_header Host $host;
-            proxy_set_header X-Real-IP $remote_addr;
-            proxy_set_header Authorization $http_authorization;
-            proxy_connect_timeout 10s;
-            proxy_read_timeout 600s;
-            proxy_buffering off;
         }
 
+        # Legacy Dashboard (root) - Proxy to Flask app
         location / {
-            proxy_pass $litellm_backend_url/;
+            proxy_pass http://dashboard_ui;
             proxy_http_version 1.1;
             proxy_set_header Host $host;
-            proxy_set_header X-Real-IP $remote_addr;
-            proxy_set_header Authorization $http_authorization;
-            proxy_connect_timeout 10s;
-            proxy_read_timeout 600s;
             proxy_buffering off;
         }
 
+        # Performance analytics
         location /metrics/ {
-            proxy_pass $router_api_url/metrics/;
+            proxy_pass http://router_api;
             proxy_http_version 1.1;
             proxy_set_header Host $host;
         }
 
+        # Circuit Breaker metrics (Phase 1)
         location /metrics/circuit-breaker {
-            proxy_pass $router_api_url/metrics/circuit-breaker;
+            proxy_pass http://router_api/metrics/circuit-breaker;
-            proxy_http_version 1.1;
-            proxy_set_header Host $host;
-        }
-
-        location /router/ {
-            proxy_pass $router_api_url/;
-            proxy_http_version 1.1;
-            proxy_set_header Host $host;
-        }
-
-        location /health/unified {
-            proxy_pass $router_api_url/health/unified;
             proxy_http_version 1.1;
             proxy_set_header Host $host;
         }
 
         location /health {
-            proxy_pass $router_api_url/health;
+            proxy_pass http://router_api/health;
             proxy_http_version 1.1;
             proxy_set_header Host $host;
-        }
-    }
-
-    # ════════════════════════════════════════════════════════════════
-    # Server :4000 — external LiteLLM entrypoint (cloudflared target)
-    #   Fixes the /ui redirect: forces correct Host + scheme so LiteLLM
-    #   builds external URLs instead of leaking 192.168.68.116:4000.
-    #   LiteLLM itself is now bound to 127.0.0.1 only (see compose).
-    # ════════════════════════════════════════════════════════════════
-    server {
-        listen 4000;
-
-        # Canonical external identity — overrides whatever Host cloudflared sends
-        proxy_set_header Host litellm.sysloggh.net;
-        proxy_set_header X-Forwarded-Host litellm.sysloggh.net;
-        proxy_set_header X-Forwarded-Proto https;
-        proxy_set_header X-Forwarded-Port 443;
-        proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
             proxy_set_header X-Real-IP $remote_addr;
-
-        # /ui → /ui/ — absolute redirect (cloudflared rewrites Host to origin IP,
-        # so a relative return would be absolutized to http://192.168.68.116:4000/).
-        location = /ui { return 301 https://litellm.sysloggh.net/ui/; }
-
-        # LiteLLM Admin UI + WebSocket
-        location /ui/ {
-            proxy_pass $litellm_backend_url/ui/;
-            proxy_http_version 1.1;
-            proxy_set_header Upgrade $http_upgrade;
-            proxy_set_header Connection "upgrade";
-            proxy_read_timeout 86400s;
-            proxy_buffering off;
-            proxy_redirect $litellm_backend_url/ https://litellm.sysloggh.net/;
-            proxy_redirect http://litellm.sysloggh.net:4000/ https://litellm.sysloggh.net/;
-        }
-
-        # UI static assets
-        location /litellm-asset-prefix/ {
-            proxy_pass $litellm_backend_url/litellm-asset-prefix/;
-            proxy_http_version 1.1;
-            proxy_set_header Upgrade $http_upgrade;
-            proxy_set_header Connection "upgrade";
-        }
-
-        # SSO callback
-        location /sso/ {
-            proxy_pass $litellm_backend_url/sso/;
-            proxy_http_version 1.1;
-            proxy_read_timeout 600s;
-        }
-
-        # API
-        location /v1/ {
-            proxy_pass $litellm_backend_url/v1/;
-            proxy_http_version 1.1;
-            proxy_set_header Authorization $http_authorization;
-            proxy_read_timeout 600s;
-            proxy_buffering off;
-        }
-
-        # Key management + admin API
-        location /key/ {
-            proxy_pass $litellm_backend_url/key/;
-            proxy_http_version 1.1;
-            proxy_set_header Authorization $http_authorization;
-        }
-        location /user/ {
-            proxy_pass $litellm_backend_url/user/;
-            proxy_http_version 1.1;
-            proxy_set_header Authorization $http_authorization;
-        }
-        location /model/ {
-            proxy_pass $litellm_backend_url/model/;
-            proxy_http_version 1.1;
-            proxy_set_header Authorization $http_authorization;
-        }
-        location /team/ {
-            proxy_pass $litellm_backend_url/team/;
-            proxy_http_version 1.1;
-            proxy_set_header Authorization $http_authorization;
-        }
-
-        # Health
-        location /health {
-            proxy_pass $litellm_backend_url/health;
-            proxy_http_version 1.1;
-        }
-
-        # Root + everything else → LiteLLM (UI index, /configs, /spend, etc.)
-        location / {
-            proxy_pass $litellm_backend_url/;
-            proxy_http_version 1.1;
-            proxy_set_header Upgrade $http_upgrade;
-            proxy_set_header Connection "upgrade";
-            proxy_read_timeout 86400s;
-            proxy_buffering off;
-            proxy_redirect http://192.168.68.116:4000/ https://litellm.sysloggh.net/;
-            proxy_redirect https://192.168.68.116:4000/ https://litellm.sysloggh.net/;
         }
     }
 }

router/router.py

@@ -70,7 +70,7 @@ GPU_LABELS = {
 }
 
 GPU_MAX_CONCURRENT = {
-    "qwen3.6-35B-A3B": 1,   # 2 slots (cross-agent spread prevents overheating)
+    "qwen3.6-35B-A3B": 2,   # 2 slots (cross-agent spread prevents overheating)
     "qwen3.6-27B-code": 2,  # 2 slots (128K context frees VRAM)
     "gemma-4-12b": 2,       # 2 slots (7.1GB VRAM)
 }
@@ -626,7 +626,7 @@ def chat():
             except Exception: pass
         start = time.time()
         resp = requests.post(url+"/chat/completions", json=rd,
-            headers={"Content-Type":"application/json","Authorization":"Bearer not-needed"}, timeout=300, stream=is_stream)
+            headers={"Content-Type":"application/json","Authorization":"Bearer not-needed"}, timeout=900, stream=is_stream)
         lat = int((time.time()-start)*1000)
         gpu_release_slot(model)
         

router/router.py.bak.20260518074236

@@ -1,342 +0,0 @@
-import os, json, time, logging, traceback, threading, queue
-import requests, redis
-from flask import Flask, request, jsonify, Response, stream_with_context
-
-REDIS_URL = os.environ.get("REDIS_URL", "redis://redis:6379")
-GPU_MOE_URL = os.environ.get("GPU_MOE_URL", "http://192.168.68.15:8080/v1")
-GPU_DENSE_URL = os.environ.get("GPU_DENSE_URL", "http://192.168.68.8:8080/v1")
-GPU_LIGHT_URL = os.environ.get("GPU_LIGHT_URL", "http://192.168.68.110:8080/v1")
-
-GPU_SIDECARS = {
-    "qwen3.6-35B-A3B": "http://192.168.68.15:8090",
-    "qwen3.6-27B-code": "http://192.168.68.8:8090",
-    "qwen3.5-9b-vlm": "http://192.168.68.110:8090",
-}
-GPU_URLS = {
-    "qwen3.6-35B-A3B": GPU_MOE_URL,
-    "qwen3.6-27B-code": GPU_DENSE_URL,
-    "qwen3.5-9b-vlm": GPU_LIGHT_URL,
-}
-# Max concurrent requests per GPU (based on llama.cpp --parallel)
-GPU_MAX_CONCURRENT = {
-    "qwen3.6-35B-A3B": 2,   # 2 slots
-    "qwen3.6-27B-code": 2,  # 2 slots
-    "qwen3.5-9b-vlm": 1,       # 1 slot
-}
-
-TIER_MODELS = {
-    "starter": ["qwen3.5-9b-vlm"],
-    "professional": ["qwen3.6-35B-A3B", "qwen3.6-27B-code", "qwen3.5-9b-vlm"],
-    "enterprise": ["qwen3.6-35B-A3B", "qwen3.6-27B-code", "qwen3.5-9b-vlm"],
-}
-API_KEYS = {
-    "sk-syslog-local-master-key": {"tier": "enterprise", "agent": "admin"},
-    "sk-syslog-abiba": {"tier": "enterprise", "agent": "Abiba"},
-    "sk-syslog-mumuni": {"tier": "enterprise", "agent": "Mumuni"},
-    "sk-syslog-tanko": {"tier": "enterprise", "agent": "Tanko"},
-    "sk-syslog-koby": {"tier": "enterprise", "agent": "Koby"},
-    "sk-syslog-kagenz0": {"tier": "enterprise", "agent": "Kagenz0"},
-    "sk-syslog-koonimo": {"tier": "enterprise", "agent": "Koonimo"},
-    "sk-starter-abc123": {"tier": "starter", "agent": "test-starter"},
-    "sk-professional-xyz789": {"tier": "professional", "agent": "test-pro"},
-}
-
-logging.basicConfig(level=logging.INFO, format="%(asctime)s [ROUTER] %(levelname)s %(message)s")
-log = logging.getLogger("router")
-try: r = redis.from_url(REDIS_URL, decode_responses=True); r.ping()
-except Exception: r = None
-
-
-def counter_audit_loop():
-    """Every 30s, check GPU slots and reset counters if all slots idle."""
-    while True:
-        time.sleep(30)
-        if not r: continue
-        for model, url in GPU_URLS.items():
-            try:
-                resp = requests.get(url.replace("/v1","") + "/slots",
-                    headers={"Authorization": "Bearer not-needed"}, timeout=5)
-                if resp.status_code == 200:
-                    slots = resp.json()
-                    all_idle = all(not s.get("is_processing", False) for s in slots)
-                    if all_idle:
-                        current = int(r.get("active:" + model) or 0)
-                        if current > 0:
-                            r.set("active:" + model, 0)
-                            log.info("AUDIT: Reset stuck counter for %s (was %d)", model, current)
-            except Exception:
-                pass
-
-threading.Thread(target=counter_audit_loop, daemon=True).start()
-
-app = Flask(__name__)
-sse_subscribers = []; sse_lock = threading.Lock()
-
-def gpu_active_count(model):
-    """Get number of in-flight requests for a GPU."""
-    if r:
-        return int(r.get("active:" + model) or 0)
-    return 0
-
-def gpu_incr(model):
-    if r: r.incr("active:" + model)
-
-def gpu_decr(model):
-    if r:
-        v = r.decr("active:" + model)
-        if v and int(v) < 0:
-            r.set("active:" + model, 0)  # never go negative
-
-def check_gpu_health(model):
-    url = GPU_SIDECARS.get(model)
-    if not url: return {"status": "unknown"}
-    try:
-        resp = requests.get(url, timeout=5)
-        if resp.status_code == 200:
-            d = resp.json()
-            pct = (d.get("vram_used_mb",0) / max(d.get("vram_total_mb",1), 1)) * 100
-            status = "healthy" if pct < 90 else "saturated"
-            # Also check if llama.cpp endpoint is actually responding
-            gpu_url = GPU_URLS.get(model, "")
-            try:
-                hr = requests.get(gpu_url.replace("/v1","") + "/health", headers={"Authorization": "Bearer not-needed"}, timeout=3)
-                if hr.status_code != 200:
-                    status = "down"
-            except Exception:
-                status = "down"
-            return {"status": status, "vram_used_mb": d.get("vram_used_mb"), "vram_total_mb": d.get("vram_total_mb"), "vram_pct": round(pct,1), "temp_c": d.get("temp_c"), "gpu_util_pct": d.get("gpu_util_pct"), "gpu_name": d.get("gpu_name"), "power_w": d.get("power_w"), "power_limit_w": d.get("power_limit_w")}
-    except Exception: pass
-    return {"status": "down"}
-
-def available_models(): return [m for m in GPU_URLS if check_gpu_health(m)["status"] in ("healthy","saturated")]
-
-def estimate_tokens(msgs): return sum(len(str(m.get("content",""))) for m in msgs) // 4
-
-def is_gpu_busy(model):
-    """Check if GPU is at or near max concurrent capacity."""
-    active = gpu_active_count(model)
-    max_c = GPU_MAX_CONCURRENT.get(model, 1)
-    return active >= max_c
-
-def select_best_gpu(candidates, reason):
-    """Pick the best GPU from candidates, preferring least-loaded."""
-    best = None
-    best_load = 999
-    for m in candidates:
-        load = gpu_active_count(m)
-        if load < best_load:
-            best_load = load
-            best = m
-    if best:
-        actual_reason = reason
-        if is_gpu_busy(best):
-            actual_reason = "load_balanced_" + reason
-        return {"model": best, "reason": actual_reason}
-    return None
-
-def route(rd, tier):
-    msgs = rd.get("messages",[]); t = estimate_tokens(msgs)
-    sys = any(m.get("role")=="system" for m in msgs)
-    turns = len([m for m in msgs if m.get("role") in ("user","assistant")])
-    hints = rd.get("routing_hints",{})
-    allowed = TIER_MODELS.get(tier, ["qwen3.5-9b-vlm"])
-    avail = [m for m in available_models() if m in allowed]
-    if not avail: return {"model": allowed[0], "reason": "all_saturated", "saturated": True}
-    
-    req = rd.get("model","auto")
-    if req != "auto":
-        target = req if req in avail else avail[0]
-        # If explicit model is busy, check if another can take it
-        if is_gpu_busy(target) and req in allowed:
-            alts = [m for m in avail if m != target and m in allowed]
-            if alts:
-                alt = select_best_gpu(alts, "explicit")
-                if alt: return alt
-        return {"model": target, "reason": "explicit"}
-    
-    if hints:
-        if hints.get("priority")=="speed" and "qwen3.5-9b-vlm" in avail:
-            return select_best_gpu(["qwen3.5-9b-vlm"], "hint_speed") or {"model":"qwen3.5-9b-vlm","reason":"hint_speed"}
-        if hints.get("priority")=="quality" and "qwen3.6-27B-code" in avail:
-            return select_best_gpu(["qwen3.6-27B-code"], "hint_quality") or {"model":"qwen3.6-27B-code","reason":"hint_quality"}
-    
-    # Heavy -> dense (but fall back to MoE if dense is busy)
-    if t > 4000 or sys or turns > 6:
-        candidates = ["qwen3.6-27B-code","qwen3.6-35B-A3B","qwen3.5-9b-vlm"]
-        candidates = [m for m in candidates if m in avail]
-        result = select_best_gpu(candidates, "heavy_reasoning")
-        if result: return result
-    
-    # Ultra-light -> VLM
-    first_msg = msgs[0].get("content","") if msgs else ""
-    words = len(first_msg.split()) if isinstance(first_msg, str) else 99
-    if words <= 3 and turns <= 1 and not sys and "qwen3.5-9b-vlm" in avail:
-        if not is_gpu_busy("qwen3.5-9b-vlm"):
-            return {"model":"qwen3.5-9b-vlm","reason":"ultra_light"}
-    
-    # Default: MoE, fall back to dense if MoE is busy
-    if "qwen3.6-35B-A3B" in avail:
-        if is_gpu_busy("qwen3.6-35B-A3B") and "qwen3.6-27B-code" in avail:
-            return {"model": "qwen3.6-27B-code", "reason": "load_balanced_default"}
-        return {"model":"qwen3.6-35B-A3B","reason":"default_moe"}
-    
-    return {"model":avail[0],"reason":"fallback"}
-
-def clean_unicode(text):
-    if not isinstance(text, str): return text
-    text = text.replace(chr(0x2014), "-"); text = text.replace(chr(0x2013), "-")
-    text = text.replace(chr(0x2018), "'"); text = text.replace(chr(0x2019), "'")
-    text = text.replace(chr(0x201C), '"'); text = text.replace(chr(0x201D), '"')
-    text = text.replace(chr(0x2026), "..."); text = text.replace(chr(0x00A0), " ")
-    return text.encode("ascii", "ignore").decode("ascii")
-
-def clean_response(d):
-    if isinstance(d, dict): return {k: clean_response(v) for k,v in d.items()}
-    if isinstance(d, list): return [clean_response(v) for v in d]
-    if isinstance(d, str): return clean_unicode(d)
-    return d
-
-def get_metrics():
-    d = {"gpus":[],"route_counts":{},"agent_counts":{},"tier_counts":{},"recent":[],"timestamp":time.time(),"active_requests":{}}
-    for m in GPU_URLS:
-        h = check_gpu_health(m)
-        d["gpus"].append({"id":m,"gpu_name":h.get("gpu_name",m),"status":h.get("status"),"vram_used_mb":h.get("vram_used_mb"),"vram_total_mb":h.get("vram_total_mb"),"vram_pct":h.get("vram_pct"),"temp_c":h.get("temp_c"),"gpu_util_pct":h.get("gpu_util_pct"),"power_w":h.get("power_w"),"power_limit_w":h.get("power_limit_w"),"active_requests":gpu_active_count(m), "max_concurrent": GPU_MAX_CONCURRENT.get(m, 1)})
-        d["active_requests"][m] = gpu_active_count(m)
-    if r:
-        try:
-            for m in GPU_URLS: d["route_counts"][m] = int(r.get("routes:"+m) or 0)
-            for k,v in API_KEYS.items():
-                c = int(r.get("routes:agent:"+v["agent"]) or 0)
-                if c>0: d["agent_counts"][v["agent"]] = c
-            for t in TIER_MODELS: d["tier_counts"][t] = int(r.get("routes:tier:"+t) or 0)
-            raw = r.lrange("routes:recent",0,49)
-            d["recent"] = [json.loads(x) for x in raw] if raw else []
-        except Exception: pass
-    return d
-
-def bcast():
-    data = get_metrics(); payload = json.dumps(data)
-    with sse_lock:
-        dead = []
-        for q in sse_subscribers:
-            try: q.put(payload)
-            except Exception: dead.append(q)
-        for q in dead: sse_subscribers.remove(q)
-
-@app.route("/v1/chat/completions", methods=["POST"])
-def chat():
-    try:
-        rd = request.get_json(force=True)
-        ak = request.headers.get("Authorization","").replace("Bearer ","")
-        ki = API_KEYS.get(ak, {"tier":"starter","agent":"unknown"})
-        tier, agent = ki["tier"], ki["agent"]
-        d = route(rd, tier)
-        if d.get("saturated"):
-            resp = jsonify({"error": "All GPUs saturated", "retry_after_s": 5})
-            resp.headers["Retry-After"] = "5"
-            return resp, 503
-        model, reason, url = d["model"], d["reason"], GPU_URLS[d["model"]]
-        is_stream = rd.get("stream", False)
-        
-        gpu_incr(model)
-        decremented = False
-        
-        log.info("ROUTE: %s -> %s (%s) stream=%s active=%d/%d", agent, model, reason, is_stream, gpu_active_count(model), GPU_MAX_CONCURRENT.get(model,1))
-        if r:
-            try:
-                r.incr("routes:"+model); r.incr("routes:tier:"+tier); r.incr("routes:agent:"+agent)
-                r.incr("ts:"+model+":"+time.strftime("%Y%m%d%H"))
-                r.lpush("routes:recent", json.dumps({"ts":time.time(),"model":model,"reason":reason,"tier":tier,"agent":agent}))
-                r.ltrim("routes:recent",0,999)
-            except Exception: pass
-        start = time.time()
-        resp = requests.post(url+"/chat/completions", json=rd,
-            headers={"Content-Type":"application/json","Authorization":"Bearer not-needed"}, timeout=300, stream=is_stream)
-        lat = int((time.time()-start)*1000)
-        gpu_decr(model)
-        decremented = True  # Release slot
-        
-        if resp.status_code != 200: return jsonify({"error":"GPU error "+str(resp.status_code)}), 502
-        if is_stream:
-            def gen():
-                for raw in resp.iter_content(chunk_size=None, decode_unicode=True):
-                    if raw: yield clean_unicode(raw)
-            bcast()
-            return Response(stream_with_context(gen()), mimetype="text/event-stream")
-        data = clean_response(resp.json())
-        for c in data.get("choices",[]):
-            msg = c.get("message",{})
-            if not msg.get("content") and msg.get("reasoning_content"):
-                msg["content"] = msg["reasoning_content"]
-        data["routing"] = {"model":model,"reason":reason,"gpu":url,"tier":tier,"agent":agent,"latency_ms":lat,"active_gpu":gpu_active_count(model)}
-        bcast()
-        return jsonify(data)
-        if not decremented:
-            try: gpu_decr(model)
-            except: pass
-    except requests.Timeout:
-        return jsonify({"error":"timeout"}), 504
-        log.error("Error: %s\n%s", e, traceback.format_exc())
-        return jsonify({"error":str(e)}), 500
-
-@app.route("/v1/models")
-def models(): return jsonify({"object":"list","data":[{"id":m,"object":"model","owned_by":"syslog","status":check_gpu_health(m).get("status"),"gpu":check_gpu_health(m).get("gpu_name")} for m in GPU_URLS]})
-
-@app.route("/health")
-def health():
-    gpus = {}
-    for m in GPU_URLS:
-        h = check_gpu_health(m)
-        h["active_requests"] = gpu_active_count(m)
-        h["max_concurrent"] = GPU_MAX_CONCURRENT.get(m, 1)
-        gpus[m] = h
-    return jsonify({"status":"healthy","redis":"connected" if r else "down","gpus":gpus,"available_models":available_models()})
-
-@app.route("/metrics")
-def metrics(): return jsonify(get_metrics())
-
-@app.route("/metrics/timeseries")
-def metrics_timeseries():
-    period = request.args.get("period", "day"); models_list = list(GPU_URLS.keys())
-    data = {"models": {}, "labels": []}
-    if period == "day":
-        buckets = [time.strftime("%Y%m%d%H", time.gmtime(time.time()-h*3600)) for h in range(23,-1,-1)]
-        data["labels"] = [time.strftime("%H:00", time.gmtime(time.time()-h*3600)) for h in range(23,-1,-1)]
-    elif period == "week":
-        buckets = [time.strftime("%Y%m%d", time.gmtime(time.time()-d*86400)) for d in range(6,-1,-1)]
-        data["labels"] = [time.strftime("%a", time.gmtime(time.time()-d*86400)) for d in range(6,-1,-1)]
-    else:
-        buckets = [time.strftime("%Y%m%d", time.gmtime(time.time()-d*86400)) for d in range(29,-1,-1)]
-        data["labels"] = [time.strftime("%m/%d", time.gmtime(time.time()-d*86400)) for d in range(29,-1,-1)]
-    if r:
-        for model in models_list:
-            counts = []
-            for bucket in buckets:
-                total = 0
-                if period in ("week","month"):
-                    for hh in range(24): total += int(r.get("ts:"+model+":"+bucket+"{:02d}".format(hh)) or 0)
-                else: total = int(r.get("ts:"+model+":"+bucket) or 0)
-                counts.append(total)
-            data["models"][model] = counts
-    return jsonify(data)
-
-@app.route("/stream")
-def stream():
-    def ev():
-        q = queue.Queue()
-        with sse_lock: sse_subscribers.append(q)
-        try:
-            yield "data: "+json.dumps(get_metrics())+"\n\n"
-            while True:
-                try: yield "data: "+q.get(timeout=3)+"\n\n"
-                except queue.Empty: yield "data: "+json.dumps(get_metrics())+"\n\n"
-        except GeneratorExit: pass
-        finally:
-            with sse_lock:
-                if q in sse_subscribers: sse_subscribers.remove(q)
-    return Response(stream_with_context(ev()), mimetype="text/event-stream",
-                    headers={"Cache-Control":"no-cache","X-Accel-Buffering":"no","Access-Control-Allow-Origin":"*"})
-
-if __name__ == "__main__":
-    log.info("Router on :9000 (load-aware)")
-    app.run(host="0.0.0.0", port=9000, debug=False)