Archive 688 GPU self-heal logs from shared memory

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}}