# HELP process_cpu_user_seconds_total Total user CPU time spent in seconds. # TYPE process_cpu_user_seconds_total counter process_cpu_user_seconds_total 7.308874 # HELP process_cpu_system_seconds_total Total system CPU time spent in seconds. # TYPE process_cpu_system_seconds_total counter process_cpu_system_seconds_total 0.607706 # HELP process_cpu_seconds_total Total user and system CPU time spent in seconds. # TYPE process_cpu_seconds_total counter process_cpu_seconds_total 7.91658 # HELP process_start_time_seconds Start time of the process since unix epoch in seconds. # TYPE process_start_time_seconds gauge process_start_time_seconds 1776697629 # HELP process_resident_memory_bytes Resident memory size in bytes. # TYPE process_resident_memory_bytes gauge process_resident_memory_bytes 515731456 # HELP process_virtual_memory_bytes Virtual memory size in bytes. # TYPE process_virtual_memory_bytes gauge process_virtual_memory_bytes 29157982208 # HELP process_heap_bytes Process heap size in bytes. # TYPE process_heap_bytes gauge process_heap_bytes 2259820544 # HELP process_open_fds Number of open file descriptors. # TYPE process_open_fds gauge process_open_fds 42 # HELP process_max_fds Maximum number of open file descriptors. # TYPE process_max_fds gauge process_max_fds 1048576 # HELP nodejs_eventloop_lag_seconds Lag of event loop in seconds. # TYPE nodejs_eventloop_lag_seconds gauge nodejs_eventloop_lag_seconds 0 # HELP nodejs_eventloop_lag_min_seconds The minimum recorded event loop delay. # TYPE nodejs_eventloop_lag_min_seconds gauge nodejs_eventloop_lag_min_seconds 0.006467584 # HELP nodejs_eventloop_lag_max_seconds The maximum recorded event loop delay. # TYPE nodejs_eventloop_lag_max_seconds gauge nodejs_eventloop_lag_max_seconds 1.047527423 # HELP nodejs_eventloop_lag_mean_seconds The mean of the recorded event loop delays. # TYPE nodejs_eventloop_lag_mean_seconds gauge nodejs_eventloop_lag_mean_seconds 0.010312628531427163 # HELP nodejs_eventloop_lag_stddev_seconds The standard deviation of the recorded event loop delays. # TYPE nodejs_eventloop_lag_stddev_seconds gauge nodejs_eventloop_lag_stddev_seconds 0.011873002335911684 # HELP nodejs_eventloop_lag_p50_seconds The 50th percentile of the recorded event loop delays. # TYPE nodejs_eventloop_lag_p50_seconds gauge nodejs_eventloop_lag_p50_seconds 0.010092543 # HELP nodejs_eventloop_lag_p90_seconds The 90th percentile of the recorded event loop delays. # TYPE nodejs_eventloop_lag_p90_seconds gauge nodejs_eventloop_lag_p90_seconds 0.010141695 # HELP nodejs_eventloop_lag_p99_seconds The 99th percentile of the recorded event loop delays. # TYPE nodejs_eventloop_lag_p99_seconds gauge nodejs_eventloop_lag_p99_seconds 0.012050431 # HELP nodejs_active_resources Number of active resources that are currently keeping the event loop alive, grouped by async resource type. # TYPE nodejs_active_resources gauge nodejs_active_resources{type="PipeWrap"} 2 nodejs_active_resources{type="TCPSocketWrap"} 12 nodejs_active_resources{type="MessagePort"} 2 nodejs_active_resources{type="TCPServerWrap"} 1 nodejs_active_resources{type="Timeout"} 9 nodejs_active_resources{type="Immediate"} 1 # HELP nodejs_active_resources_total Total number of active resources. # TYPE nodejs_active_resources_total gauge nodejs_active_resources_total 27 # HELP nodejs_active_handles Number of active libuv handles grouped by handle type. Every handle type is C++ class name. # TYPE nodejs_active_handles gauge nodejs_active_handles{type="Socket"} 14 nodejs_active_handles{type="MessagePort"} 2 nodejs_active_handles{type="Server"} 1 # HELP nodejs_active_handles_total Total number of active handles. # TYPE nodejs_active_handles_total gauge nodejs_active_handles_total 17 # HELP nodejs_active_requests Number of active libuv requests grouped by request type. Every request type is C++ class name. # TYPE nodejs_active_requests gauge # HELP nodejs_active_requests_total Total number of active requests. # TYPE nodejs_active_requests_total gauge nodejs_active_requests_total 0 # HELP nodejs_heap_size_total_bytes Process heap size from Node.js in bytes. # TYPE nodejs_heap_size_total_bytes gauge nodejs_heap_size_total_bytes 126332928 # HELP nodejs_heap_size_used_bytes Process heap size used from Node.js in bytes. # TYPE nodejs_heap_size_used_bytes gauge nodejs_heap_size_used_bytes 111387424 # HELP nodejs_external_memory_bytes Node.js external memory size in bytes. # TYPE nodejs_external_memory_bytes gauge nodejs_external_memory_bytes 30487797 # HELP nodejs_heap_space_size_total_bytes Process heap space size total from Node.js in bytes. # TYPE nodejs_heap_space_size_total_bytes gauge nodejs_heap_space_size_total_bytes{space="read_only"} 0 nodejs_heap_space_size_total_bytes{space="new"} 16777216 nodejs_heap_space_size_total_bytes{space="old"} 76062720 nodejs_heap_space_size_total_bytes{space="code"} 6815744 nodejs_heap_space_size_total_bytes{space="shared"} 0 nodejs_heap_space_size_total_bytes{space="trusted"} 6590464 nodejs_heap_space_size_total_bytes{space="shared_trusted"} 0 nodejs_heap_space_size_total_bytes{space="new_large_object"} 0 nodejs_heap_space_size_total_bytes{space="large_object"} 19718144 nodejs_heap_space_size_total_bytes{space="code_large_object"} 163840 nodejs_heap_space_size_total_bytes{space="shared_large_object"} 0 nodejs_heap_space_size_total_bytes{space="shared_trusted_large_object"} 0 nodejs_heap_space_size_total_bytes{space="trusted_large_object"} 204800 # HELP nodejs_heap_space_size_used_bytes Process heap space size used from Node.js in bytes. # TYPE nodejs_heap_space_size_used_bytes gauge nodejs_heap_space_size_used_bytes{space="read_only"} 0 nodejs_heap_space_size_used_bytes{space="new"} 4209056 nodejs_heap_space_size_used_bytes{space="old"} 75167760 nodejs_heap_space_size_used_bytes{space="code"} 5889216 nodejs_heap_space_size_used_bytes{space="shared"} 0 nodejs_heap_space_size_used_bytes{space="trusted"} 5834592 nodejs_heap_space_size_used_bytes{space="shared_trusted"} 0 nodejs_heap_space_size_used_bytes{space="new_large_object"} 0 nodejs_heap_space_size_used_bytes{space="large_object"} 19672328 nodejs_heap_space_size_used_bytes{space="code_large_object"} 163584 nodejs_heap_space_size_used_bytes{space="shared_large_object"} 0 nodejs_heap_space_size_used_bytes{space="shared_trusted_large_object"} 0 nodejs_heap_space_size_used_bytes{space="trusted_large_object"} 200736 # HELP nodejs_heap_space_size_available_bytes Process heap space size available from Node.js in bytes. # TYPE nodejs_heap_space_size_available_bytes gauge nodejs_heap_space_size_available_bytes{space="read_only"} 0 nodejs_heap_space_size_available_bytes{space="new"} 4179040 nodejs_heap_space_size_available_bytes{space="old"} 695144 nodejs_heap_space_size_available_bytes{space="code"} 925696 nodejs_heap_space_size_available_bytes{space="shared"} 0 nodejs_heap_space_size_available_bytes{space="trusted"} 736960 nodejs_heap_space_size_available_bytes{space="shared_trusted"} 0 nodejs_heap_space_size_available_bytes{space="new_large_object"} 8388608 nodejs_heap_space_size_available_bytes{space="large_object"} 0 nodejs_heap_space_size_available_bytes{space="code_large_object"} 0 nodejs_heap_space_size_available_bytes{space="shared_large_object"} 0 nodejs_heap_space_size_available_bytes{space="shared_trusted_large_object"} 0 nodejs_heap_space_size_available_bytes{space="trusted_large_object"} 0 # HELP nodejs_version_info Node.js version info. # TYPE nodejs_version_info gauge nodejs_version_info{version="v24.14.1",major="24",minor="14",patch="1"} 1 # HELP nodejs_gc_duration_seconds Garbage collection duration by kind, one of major, minor, incremental or weakcb. # TYPE nodejs_gc_duration_seconds histogram nodejs_gc_duration_seconds_bucket{le="0.001",kind="incremental"} 12 nodejs_gc_duration_seconds_bucket{le="0.01",kind="incremental"} 12 nodejs_gc_duration_seconds_bucket{le="0.1",kind="incremental"} 12 nodejs_gc_duration_seconds_bucket{le="1",kind="incremental"} 12 nodejs_gc_duration_seconds_bucket{le="2",kind="incremental"} 12 nodejs_gc_duration_seconds_bucket{le="5",kind="incremental"} 12 nodejs_gc_duration_seconds_bucket{le="+Inf",kind="incremental"} 12 nodejs_gc_duration_seconds_sum{kind="incremental"} 0.009573336601257325 nodejs_gc_duration_seconds_count{kind="incremental"} 12 nodejs_gc_duration_seconds_bucket{le="0.001",kind="major"} 0 nodejs_gc_duration_seconds_bucket{le="0.01",kind="major"} 7 nodejs_gc_duration_seconds_bucket{le="0.1",kind="major"} 13 nodejs_gc_duration_seconds_bucket{le="1",kind="major"} 13 nodejs_gc_duration_seconds_bucket{le="2",kind="major"} 13 nodejs_gc_duration_seconds_bucket{le="5",kind="major"} 13 nodejs_gc_duration_seconds_bucket{le="+Inf",kind="major"} 13 nodejs_gc_duration_seconds_sum{kind="major"} 0.16782459163665772 nodejs_gc_duration_seconds_count{kind="major"} 13 nodejs_gc_duration_seconds_bucket{le="0.001",kind="minor"} 29 nodejs_gc_duration_seconds_bucket{le="0.01",kind="minor"} 49 nodejs_gc_duration_seconds_bucket{le="0.1",kind="minor"} 49 nodejs_gc_duration_seconds_bucket{le="1",kind="minor"} 49 nodejs_gc_duration_seconds_bucket{le="2",kind="minor"} 49 nodejs_gc_duration_seconds_bucket{le="5",kind="minor"} 49 nodejs_gc_duration_seconds_bucket{le="+Inf",kind="minor"} 49 nodejs_gc_duration_seconds_sum{kind="minor"} 0.05369372367858887 nodejs_gc_duration_seconds_count{kind="minor"} 49 # HELP http_request_duration_seconds Duration of HTTP requests in seconds # TYPE http_request_duration_seconds histogram http_request_duration_seconds_bucket{le="0.001",method="GET",route="/livez",status_code="200"} 0 http_request_duration_seconds_bucket{le="0.005",method="GET",route="/livez",status_code="200"} 0 http_request_duration_seconds_bucket{le="0.015",method="GET",route="/livez",status_code="200"} 0 http_request_duration_seconds_bucket{le="0.05",method="GET",route="/livez",status_code="200"} 1 http_request_duration_seconds_bucket{le="0.1",method="GET",route="/livez",status_code="200"} 1 http_request_duration_seconds_bucket{le="0.2",method="GET",route="/livez",status_code="200"} 1 http_request_duration_seconds_bucket{le="0.3",method="GET",route="/livez",status_code="200"} 1 http_request_duration_seconds_bucket{le="0.4",method="GET",route="/livez",status_code="200"} 1 http_request_duration_seconds_bucket{le="0.5",method="GET",route="/livez",status_code="200"} 1 http_request_duration_seconds_bucket{le="1",method="GET",route="/livez",status_code="200"} 1 http_request_duration_seconds_bucket{le="2",method="GET",route="/livez",status_code="200"} 1 http_request_duration_seconds_bucket{le="5",method="GET",route="/livez",status_code="200"} 1 http_request_duration_seconds_bucket{le="+Inf",method="GET",route="/livez",status_code="200"} 1 http_request_duration_seconds_sum{method="GET",route="/livez",status_code="200"} 0.017 http_request_duration_seconds_count{method="GET",route="/livez",status_code="200"} 1 http_request_duration_seconds_bucket{le="0.001",method="POST",route="/v1/chat/completions",status_code="200"} 0 http_request_duration_seconds_bucket{le="0.005",method="POST",route="/v1/chat/completions",status_code="200"} 0 http_request_duration_seconds_bucket{le="0.015",method="POST",route="/v1/chat/completions",status_code="200"} 0 http_request_duration_seconds_bucket{le="0.05",method="POST",route="/v1/chat/completions",status_code="200"} 0 http_request_duration_seconds_bucket{le="0.1",method="POST",route="/v1/chat/completions",status_code="200"} 0 http_request_duration_seconds_bucket{le="0.2",method="POST",route="/v1/chat/completions",status_code="200"} 0 http_request_duration_seconds_bucket{le="0.3",method="POST",route="/v1/chat/completions",status_code="200"} 0 http_request_duration_seconds_bucket{le="0.4",method="POST",route="/v1/chat/completions",status_code="200"} 0 http_request_duration_seconds_bucket{le="0.5",method="POST",route="/v1/chat/completions",status_code="200"} 0 http_request_duration_seconds_bucket{le="1",method="POST",route="/v1/chat/completions",status_code="200"} 0 http_request_duration_seconds_bucket{le="2",method="POST",route="/v1/chat/completions",status_code="200"} 0 http_request_duration_seconds_bucket{le="5",method="POST",route="/v1/chat/completions",status_code="200"} 2 http_request_duration_seconds_bucket{le="+Inf",method="POST",route="/v1/chat/completions",status_code="200"} 4 http_request_duration_seconds_sum{method="POST",route="/v1/chat/completions",status_code="200"} 34.714 http_request_duration_seconds_count{method="POST",route="/v1/chat/completions",status_code="200"} 4 http_request_duration_seconds_bucket{le="0.001",method="POST",route="/v1/chat/completions",status_code="429"} 0 http_request_duration_seconds_bucket{le="0.005",method="POST",route="/v1/chat/completions",status_code="429"} 0 http_request_duration_seconds_bucket{le="0.015",method="POST",route="/v1/chat/completions",status_code="429"} 0 http_request_duration_seconds_bucket{le="0.05",method="POST",route="/v1/chat/completions",status_code="429"} 2 http_request_duration_seconds_bucket{le="0.1",method="POST",route="/v1/chat/completions",status_code="429"} 2 http_request_duration_seconds_bucket{le="0.2",method="POST",route="/v1/chat/completions",status_code="429"} 2 http_request_duration_seconds_bucket{le="0.3",method="POST",route="/v1/chat/completions",status_code="429"} 2 http_request_duration_seconds_bucket{le="0.4",method="POST",route="/v1/chat/completions",status_code="429"} 2 http_request_duration_seconds_bucket{le="0.5",method="POST",route="/v1/chat/completions",status_code="429"} 2 http_request_duration_seconds_bucket{le="1",method="POST",route="/v1/chat/completions",status_code="429"} 2 http_request_duration_seconds_bucket{le="2",method="POST",route="/v1/chat/completions",status_code="429"} 2 http_request_duration_seconds_bucket{le="5",method="POST",route="/v1/chat/completions",status_code="429"} 4 http_request_duration_seconds_bucket{le="+Inf",method="POST",route="/v1/chat/completions",status_code="429"} 18 http_request_duration_seconds_sum{method="POST",route="/v1/chat/completions",status_code="429"} 94.683 http_request_duration_seconds_count{method="POST",route="/v1/chat/completions",status_code="429"} 18 http_request_duration_seconds_bucket{le="0.001",method="POST",route="/api/v1/dashboard/auth/logout",status_code="200"} 0 http_request_duration_seconds_bucket{le="0.005",method="POST",route="/api/v1/dashboard/auth/logout",status_code="200"} 0 http_request_duration_seconds_bucket{le="0.015",method="POST",route="/api/v1/dashboard/auth/logout",status_code="200"} 1 http_request_duration_seconds_bucket{le="0.05",method="POST",route="/api/v1/dashboard/auth/logout",status_code="200"} 1 http_request_duration_seconds_bucket{le="0.1",method="POST",route="/api/v1/dashboard/auth/logout",status_code="200"} 1 http_request_duration_seconds_bucket{le="0.2",method="POST",route="/api/v1/dashboard/auth/logout",status_code="200"} 1 http_request_duration_seconds_bucket{le="0.3",method="POST",route="/api/v1/dashboard/auth/logout",status_code="200"} 1 http_request_duration_seconds_bucket{le="0.4",method="POST",route="/api/v1/dashboard/auth/logout",status_code="200"} 1 http_request_duration_seconds_bucket{le="0.5",method="POST",route="/api/v1/dashboard/auth/logout",status_code="200"} 1 http_request_duration_seconds_bucket{le="1",method="POST",route="/api/v1/dashboard/auth/logout",status_code="200"} 1 http_request_duration_seconds_bucket{le="2",method="POST",route="/api/v1/dashboard/auth/logout",status_code="200"} 1 http_request_duration_seconds_bucket{le="5",method="POST",route="/api/v1/dashboard/auth/logout",status_code="200"} 1 http_request_duration_seconds_bucket{le="+Inf",method="POST",route="/api/v1/dashboard/auth/logout",status_code="200"} 1 http_request_duration_seconds_sum{method="POST",route="/api/v1/dashboard/auth/logout",status_code="200"} 0.008 http_request_duration_seconds_count{method="POST",route="/api/v1/dashboard/auth/logout",status_code="200"} 1 http_request_duration_seconds_bucket{le="0.001",method="GET",route="/api/v1/dashboard/auth/me",status_code="401"} 0 http_request_duration_seconds_bucket{le="0.005",method="GET",route="/api/v1/dashboard/auth/me",status_code="401"} 0 http_request_duration_seconds_bucket{le="0.015",method="GET",route="/api/v1/dashboard/auth/me",status_code="401"} 1 http_request_duration_seconds_bucket{le="0.05",method="GET",route="/api/v1/dashboard/auth/me",status_code="401"} 2 http_request_duration_seconds_bucket{le="0.1",method="GET",route="/api/v1/dashboard/auth/me",status_code="401"} 2 http_request_duration_seconds_bucket{le="0.2",method="GET",route="/api/v1/dashboard/auth/me",status_code="401"} 2 http_request_duration_seconds_bucket{le="0.3",method="GET",route="/api/v1/dashboard/auth/me",status_code="401"} 2 http_request_duration_seconds_bucket{le="0.4",method="GET",route="/api/v1/dashboard/auth/me",status_code="401"} 2 http_request_duration_seconds_bucket{le="0.5",method="GET",route="/api/v1/dashboard/auth/me",status_code="401"} 2 http_request_duration_seconds_bucket{le="1",method="GET",route="/api/v1/dashboard/auth/me",status_code="401"} 2 http_request_duration_seconds_bucket{le="2",method="GET",route="/api/v1/dashboard/auth/me",status_code="401"} 2 http_request_duration_seconds_bucket{le="5",method="GET",route="/api/v1/dashboard/auth/me",status_code="401"} 2 http_request_duration_seconds_bucket{le="+Inf",method="GET",route="/api/v1/dashboard/auth/me",status_code="401"} 2 http_request_duration_seconds_sum{method="GET",route="/api/v1/dashboard/auth/me",status_code="401"} 0.03 http_request_duration_seconds_count{method="GET",route="/api/v1/dashboard/auth/me",status_code="401"} 2 http_request_duration_seconds_bucket{le="0.001",method="GET",route="/api/v1/dashboard/activity",status_code="200"} 0 http_request_duration_seconds_bucket{le="0.005",method="GET",route="/api/v1/dashboard/activity",status_code="200"} 0 http_request_duration_seconds_bucket{le="0.015",method="GET",route="/api/v1/dashboard/activity",status_code="200"} 0 http_request_duration_seconds_bucket{le="0.05",method="GET",route="/api/v1/dashboard/activity",status_code="200"} 0 http_request_duration_seconds_bucket{le="0.1",method="GET",route="/api/v1/dashboard/activity",status_code="200"} 0 http_request_duration_seconds_bucket{le="0.2",method="GET",route="/api/v1/dashboard/activity",status_code="200"} 0 http_request_duration_seconds_bucket{le="0.3",method="GET",route="/api/v1/dashboard/activity",status_code="200"} 0 http_request_duration_seconds_bucket{le="0.4",method="GET",route="/api/v1/dashboard/activity",status_code="200"} 0 http_request_duration_seconds_bucket{le="0.5",method="GET",route="/api/v1/dashboard/activity",status_code="200"} 0 http_request_duration_seconds_bucket{le="1",method="GET",route="/api/v1/dashboard/activity",status_code="200"} 1 http_request_duration_seconds_bucket{le="2",method="GET",route="/api/v1/dashboard/activity",status_code="200"} 1 http_request_duration_seconds_bucket{le="5",method="GET",route="/api/v1/dashboard/activity",status_code="200"} 1 http_request_duration_seconds_bucket{le="+Inf",method="GET",route="/api/v1/dashboard/activity",status_code="200"} 1 http_request_duration_seconds_sum{method="GET",route="/api/v1/dashboard/activity",status_code="200"} 0.741 http_request_duration_seconds_count{method="GET",route="/api/v1/dashboard/activity",status_code="200"} 1 http_request_duration_seconds_bucket{le="0.001",method="GET",route="/api/v1/dashboard/usage-log",status_code="200"} 0 http_request_duration_seconds_bucket{le="0.005",method="GET",route="/api/v1/dashboard/usage-log",status_code="200"} 0 http_request_duration_seconds_bucket{le="0.015",method="GET",route="/api/v1/dashboard/usage-log",status_code="200"} 0 http_request_duration_seconds_bucket{le="0.05",method="GET",route="/api/v1/dashboard/usage-log",status_code="200"} 0 http_request_duration_seconds_bucket{le="0.1",method="GET",route="/api/v1/dashboard/usage-log",status_code="200"} 0 http_request_duration_seconds_bucket{le="0.2",method="GET",route="/api/v1/dashboard/usage-log",status_code="200"} 0 http_request_duration_seconds_bucket{le="0.3",method="GET",route="/api/v1/dashboard/usage-log",status_code="200"} 0 http_request_duration_seconds_bucket{le="0.4",method="GET",route="/api/v1/dashboard/usage-log",status_code="200"} 0 http_request_duration_seconds_bucket{le="0.5",method="GET",route="/api/v1/dashboard/usage-log",status_code="200"} 0 http_request_duration_seconds_bucket{le="1",method="GET",route="/api/v1/dashboard/usage-log",status_code="200"} 1 http_request_duration_seconds_bucket{le="2",method="GET",route="/api/v1/dashboard/usage-log",status_code="200"} 1 http_request_duration_seconds_bucket{le="5",method="GET",route="/api/v1/dashboard/usage-log",status_code="200"} 1 http_request_duration_seconds_bucket{le="+Inf",method="GET",route="/api/v1/dashboard/usage-log",status_code="200"} 1 http_request_duration_seconds_sum{method="GET",route="/api/v1/dashboard/usage-log",status_code="200"} 0.852 http_request_duration_seconds_count{method="GET",route="/api/v1/dashboard/usage-log",status_code="200"} 1 http_request_duration_seconds_bucket{le="0.001",method="GET",route="/api/v1/dashboard/presets",status_code="200"} 0 http_request_duration_seconds_bucket{le="0.005",method="GET",route="/api/v1/dashboard/presets",status_code="200"} 0 http_request_duration_seconds_bucket{le="0.015",method="GET",route="/api/v1/dashboard/presets",status_code="200"} 0 http_request_duration_seconds_bucket{le="0.05",method="GET",route="/api/v1/dashboard/presets",status_code="200"} 1 http_request_duration_seconds_bucket{le="0.1",method="GET",route="/api/v1/dashboard/presets",status_code="200"} 1 http_request_duration_seconds_bucket{le="0.2",method="GET",route="/api/v1/dashboard/presets",status_code="200"} 1 http_request_duration_seconds_bucket{le="0.3",method="GET",route="/api/v1/dashboard/presets",status_code="200"} 1 http_request_duration_seconds_bucket{le="0.4",method="GET",route="/api/v1/dashboard/presets",status_code="200"} 1 http_request_duration_seconds_bucket{le="0.5",method="GET",route="/api/v1/dashboard/presets",status_code="200"} 1 http_request_duration_seconds_bucket{le="1",method="GET",route="/api/v1/dashboard/presets",status_code="200"} 1 http_request_duration_seconds_bucket{le="2",method="GET",route="/api/v1/dashboard/presets",status_code="200"} 1 http_request_duration_seconds_bucket{le="5",method="GET",route="/api/v1/dashboard/presets",status_code="200"} 1 http_request_duration_seconds_bucket{le="+Inf",method="GET",route="/api/v1/dashboard/presets",status_code="200"} 1 http_request_duration_seconds_sum{method="GET",route="/api/v1/dashboard/presets",status_code="200"} 0.026 http_request_duration_seconds_count{method="GET",route="/api/v1/dashboard/presets",status_code="200"} 1 http_request_duration_seconds_bucket{le="0.001",method="GET",route="/api/v1/dashboard/plugins",status_code="200"} 0 http_request_duration_seconds_bucket{le="0.005",method="GET",route="/api/v1/dashboard/plugins",status_code="200"} 0 http_request_duration_seconds_bucket{le="0.015",method="GET",route="/api/v1/dashboard/plugins",status_code="200"} 0 http_request_duration_seconds_bucket{le="0.05",method="GET",route="/api/v1/dashboard/plugins",status_code="200"} 0 http_request_duration_seconds_bucket{le="0.1",method="GET",route="/api/v1/dashboard/plugins",status_code="200"} 1 http_request_duration_seconds_bucket{le="0.2",method="GET",route="/api/v1/dashboard/plugins",status_code="200"} 1 http_request_duration_seconds_bucket{le="0.3",method="GET",route="/api/v1/dashboard/plugins",status_code="200"} 1 http_request_duration_seconds_bucket{le="0.4",method="GET",route="/api/v1/dashboard/plugins",status_code="200"} 1 http_request_duration_seconds_bucket{le="0.5",method="GET",route="/api/v1/dashboard/plugins",status_code="200"} 1 http_request_duration_seconds_bucket{le="1",method="GET",route="/api/v1/dashboard/plugins",status_code="200"} 1 http_request_duration_seconds_bucket{le="2",method="GET",route="/api/v1/dashboard/plugins",status_code="200"} 1 http_request_duration_seconds_bucket{le="5",method="GET",route="/api/v1/dashboard/plugins",status_code="200"} 1 http_request_duration_seconds_bucket{le="+Inf",method="GET",route="/api/v1/dashboard/plugins",status_code="200"} 1 http_request_duration_seconds_sum{method="GET",route="/api/v1/dashboard/plugins",status_code="200"} 0.075 http_request_duration_seconds_count{method="GET",route="/api/v1/dashboard/plugins",status_code="200"} 1 http_request_duration_seconds_bucket{le="0.001",method="GET",route="/api/v1/public/pricing",status_code="200"} 0 http_request_duration_seconds_bucket{le="0.005",method="GET",route="/api/v1/public/pricing",status_code="200"} 0 http_request_duration_seconds_bucket{le="0.015",method="GET",route="/api/v1/public/pricing",status_code="200"} 0 http_request_duration_seconds_bucket{le="0.05",method="GET",route="/api/v1/public/pricing",status_code="200"} 1 http_request_duration_seconds_bucket{le="0.1",method="GET",route="/api/v1/public/pricing",status_code="200"} 1 http_request_duration_seconds_bucket{le="0.2",method="GET",route="/api/v1/public/pricing",status_code="200"} 1 http_request_duration_seconds_bucket{le="0.3",method="GET",route="/api/v1/public/pricing",status_code="200"} 2 http_request_duration_seconds_bucket{le="0.4",method="GET",route="/api/v1/public/pricing",status_code="200"} 2 http_request_duration_seconds_bucket{le="0.5",method="GET",route="/api/v1/public/pricing",status_code="200"} 2 http_request_duration_seconds_bucket{le="1",method="GET",route="/api/v1/public/pricing",status_code="200"} 2 http_request_duration_seconds_bucket{le="2",method="GET",route="/api/v1/public/pricing",status_code="200"} 2 http_request_duration_seconds_bucket{le="5",method="GET",route="/api/v1/public/pricing",status_code="200"} 2 http_request_duration_seconds_bucket{le="+Inf",method="GET",route="/api/v1/public/pricing",status_code="200"} 2 http_request_duration_seconds_sum{method="GET",route="/api/v1/public/pricing",status_code="200"} 0.26 http_request_duration_seconds_count{method="GET",route="/api/v1/public/pricing",status_code="200"} 2 # HELP http_requests_total Total number of HTTP requests # TYPE http_requests_total counter http_requests_total{method="GET",route="/livez",status_code="200"} 1 http_requests_total{method="POST",route="/v1/chat/completions",status_code="200"} 4 http_requests_total{method="POST",route="/v1/chat/completions",status_code="429"} 18 http_requests_total{method="POST",route="/api/v1/dashboard/auth/logout",status_code="200"} 1 http_requests_total{method="GET",route="/api/v1/dashboard/auth/me",status_code="401"} 2 http_requests_total{method="GET",route="/api/v1/dashboard/activity",status_code="200"} 1 http_requests_total{method="GET",route="/api/v1/dashboard/usage-log",status_code="200"} 1 http_requests_total{method="GET",route="/api/v1/dashboard/presets",status_code="200"} 1 http_requests_total{method="GET",route="/api/v1/dashboard/plugins",status_code="200"} 1 http_requests_total{method="GET",route="/api/v1/public/pricing",status_code="200"} 2 # HELP http_requests_in_progress Number of HTTP requests in progress # TYPE http_requests_in_progress gauge http_requests_in_progress{method="GET"} 1 http_requests_in_progress{method="POST"} 2 # HELP gonka_payload_rejections_total Total number of payload rejections # TYPE gonka_payload_rejections_total counter # HELP gonka_circuit_breaker_scoped_state Scoped circuit breaker state (0=closed, 1=open, 2=half-open) # TYPE gonka_circuit_breaker_scoped_state gauge # HELP gonka_circuit_breaker_scoped_failures_total Total scoped circuit breaker recorded failures # TYPE gonka_circuit_breaker_scoped_failures_total counter # HELP gonka_circuit_breaker_scoped_opened_total Number of times scoped circuit breaker opened # TYPE gonka_circuit_breaker_scoped_opened_total counter # HELP gonka_source_url_fallback_total Number of times switched to fallback source URL # TYPE gonka_source_url_fallback_total counter gonka_source_url_fallback_total 0 # HELP gonka_health_check_status Last health check result (0=unhealthy, 1=healthy) # TYPE gonka_health_check_status gauge gonka_health_check_status 1 # HELP gonka_health_check_latency_seconds Health check latency # TYPE gonka_health_check_latency_seconds histogram gonka_health_check_latency_seconds_bucket{le="0.1"} 2 gonka_health_check_latency_seconds_bucket{le="0.5"} 2 gonka_health_check_latency_seconds_bucket{le="1"} 2 gonka_health_check_latency_seconds_bucket{le="2"} 2 gonka_health_check_latency_seconds_bucket{le="5"} 2 gonka_health_check_latency_seconds_bucket{le="+Inf"} 2 gonka_health_check_latency_seconds_sum 0.001 gonka_health_check_latency_seconds_count 2 # HELP gonka_health_check_aggregate_status Aggregate routability status (0=healthy, 1=degraded, 2=catastrophic, 3=unknown) # TYPE gonka_health_check_aggregate_status gauge gonka_health_check_aggregate_status 0 # HELP gonka_health_check_reason_total Health monitor decision reasons by aggregate status # TYPE gonka_health_check_reason_total counter gonka_health_check_reason_total{status="healthy",reason_kind="unknown"} 2 # HELP gonka_service_gate_owner_state Service gate owner state (0=none, 1=monitor, 2=admin) # TYPE gonka_service_gate_owner_state gauge gonka_service_gate_owner_state 0 # HELP gonka_service_gate_transition_total Service gate ownership transitions # TYPE gonka_service_gate_transition_total counter # HELP gonka_idempotency_cache_hits_total Idempotency cache hit count # TYPE gonka_idempotency_cache_hits_total counter gonka_idempotency_cache_hits_total 0 # HELP gonka_idempotency_cache_size Current idempotency cache size # TYPE gonka_idempotency_cache_size gauge gonka_idempotency_cache_size 0 # HELP gonka_idempotency_lock_waiting_total Number of requests that waited for in-flight idempotent request # TYPE gonka_idempotency_lock_waiting_total counter gonka_idempotency_lock_waiting_total 0 # HELP gonka_idempotency_lock_timeout_total Number of idempotency lock timeouts (stale locks) # TYPE gonka_idempotency_lock_timeout_total counter gonka_idempotency_lock_timeout_total 0 # HELP gonka_idempotency_pending_size Current number of in-flight idempotent requests # TYPE gonka_idempotency_pending_size gauge gonka_idempotency_pending_size 0 # HELP gonka_response_healing_activation_total Total number of response-healing strict activation attempts # TYPE gonka_response_healing_activation_total counter gonka_response_healing_activation_total 0 # HELP gonka_response_healing_applied_total Total number of response healing attempts # TYPE gonka_response_healing_applied_total counter gonka_response_healing_applied_total 0 # HELP gonka_response_healing_success_total Total number of successful response healing attempts # TYPE gonka_response_healing_success_total counter gonka_response_healing_success_total 0 # HELP gonka_response_healing_failed_total Total number of failed response healing attempts # TYPE gonka_response_healing_failed_total counter gonka_response_healing_failed_total 0 # HELP gonka_response_healing_schema_invalid_total Total number of response healing schema validation failures # TYPE gonka_response_healing_schema_invalid_total counter gonka_response_healing_schema_invalid_total 0 # HELP gonka_response_healing_strict_abort_total Total number of strict response-healing aborts (502) # TYPE gonka_response_healing_strict_abort_total counter gonka_response_healing_strict_abort_total 0 # HELP gonka_response_healing_skipped_streaming_total Response healing skipped due to streaming requests # TYPE gonka_response_healing_skipped_streaming_total counter gonka_response_healing_skipped_streaming_total 0 # HELP gonka_response_healing_skipped_no_response_format_total Response healing skipped due to missing structured response_format # TYPE gonka_response_healing_skipped_no_response_format_total counter gonka_response_healing_skipped_no_response_format_total 0 # HELP gonka_response_healing_skipped_oversize_total Response healing skipped due to oversized input # TYPE gonka_response_healing_skipped_oversize_total counter gonka_response_healing_skipped_oversize_total 0 # HELP gonka_response_healing_skipped_overload_total Response healing skipped due to overload protection # TYPE gonka_response_healing_skipped_overload_total counter gonka_response_healing_skipped_overload_total 0 # HELP gonka_response_healing_duration_ms Response healing duration in milliseconds # TYPE gonka_response_healing_duration_ms histogram gonka_response_healing_duration_ms_bucket{le="0.1"} 0 gonka_response_healing_duration_ms_bucket{le="0.5"} 0 gonka_response_healing_duration_ms_bucket{le="1"} 0 gonka_response_healing_duration_ms_bucket{le="2"} 0 gonka_response_healing_duration_ms_bucket{le="5"} 0 gonka_response_healing_duration_ms_bucket{le="10"} 0 gonka_response_healing_duration_ms_bucket{le="25"} 0 gonka_response_healing_duration_ms_bucket{le="50"} 0 gonka_response_healing_duration_ms_bucket{le="+Inf"} 0 gonka_response_healing_duration_ms_sum 0 gonka_response_healing_duration_ms_count 0 # HELP gonka_response_healing_input_chars Input size for response healing in characters # TYPE gonka_response_healing_input_chars histogram gonka_response_healing_input_chars_bucket{le="100"} 0 gonka_response_healing_input_chars_bucket{le="500"} 0 gonka_response_healing_input_chars_bucket{le="1000"} 0 gonka_response_healing_input_chars_bucket{le="5000"} 0 gonka_response_healing_input_chars_bucket{le="10000"} 0 gonka_response_healing_input_chars_bucket{le="50000"} 0 gonka_response_healing_input_chars_bucket{le="100000"} 0 gonka_response_healing_input_chars_bucket{le="200000"} 0 gonka_response_healing_input_chars_bucket{le="+Inf"} 0 gonka_response_healing_input_chars_sum 0 gonka_response_healing_input_chars_count 0 # HELP gonka_tools_emulation_triggered_total Total number of tools-emulation fallback attempts started. # TYPE gonka_tools_emulation_triggered_total counter # HELP gonka_tools_emulation_handled_total Total number of requests handled by tools-emulation fallback. # TYPE gonka_tools_emulation_handled_total counter # HELP gonka_tools_emulation_failed_total Total number of failed tools-emulation fallback attempts. # TYPE gonka_tools_emulation_failed_total counter # HELP gonka_tools_emulation_skipped_total Total number of skipped tools-emulation fallback attempts. # TYPE gonka_tools_emulation_skipped_total counter gonka_tools_emulation_skipped_total{mode="non_streaming",reason="upstream-error-not-matching"} 16 # HELP gonka_node_pool_healthy_count Current number of healthy nodes in pool # TYPE gonka_node_pool_healthy_count gauge gonka_node_pool_healthy_count 0 # HELP gonka_node_pool_quarantine_count Current number of quarantined nodes # TYPE gonka_node_pool_quarantine_count gauge gonka_node_pool_quarantine_count 0 # HELP gonka_node_pool_hits_total Endpoint selections from pool (proven healthy) # TYPE gonka_node_pool_hits_total counter # HELP gonka_node_pool_misses_total Endpoint selections from cache (pool was empty) # TYPE gonka_node_pool_misses_total counter # HELP gonka_node_pool_endpoint_latency_seconds Latency of successful endpoint requests # TYPE gonka_node_pool_endpoint_latency_seconds histogram # HELP gonka_node_pool_quarantine_events_total Number of times endpoints were quarantined # TYPE gonka_node_pool_quarantine_events_total counter # HELP gonka_node_pool_slow_requests_total Requests above slow latency threshold # TYPE gonka_node_pool_slow_requests_total counter # HELP gonka_node_pool_latency_quarantine_total Endpoints quarantined due to high latency (consecutive slow requests) # TYPE gonka_node_pool_latency_quarantine_total counter # HELP gonka_node_pool_quality_gate_pass_total Endpoints that passed quality gate # TYPE gonka_node_pool_quality_gate_pass_total counter # HELP gonka_node_pool_quality_gate_fail_total Endpoints that failed quality gate # TYPE gonka_node_pool_quality_gate_fail_total counter # HELP gonka_node_pool_quarantine_duration_seconds Quarantine duration distribution # TYPE gonka_node_pool_quarantine_duration_seconds histogram # HELP gonka_node_pool_ttfb_failures_total Requests where TTFB exceeded failure threshold (10s) # TYPE gonka_node_pool_ttfb_failures_total counter # HELP gonka_node_pool_cancellations_total User-cancelled requests # TYPE gonka_node_pool_cancellations_total counter # HELP gonka_node_pool_low_score_evictions_total Nodes evicted due to score below threshold # TYPE gonka_node_pool_low_score_evictions_total counter # HELP gonka_node_pool_periodic_cleanup_evictions_total Nodes evicted during periodic cleanup (worst 10%) # TYPE gonka_node_pool_periodic_cleanup_evictions_total counter # HELP gonka_node_pool_discoveries_total New nodes discovered and added to pool via quality gate # TYPE gonka_node_pool_discoveries_total counter # HELP gonka_node_pool_cleanup_cycles_total Number of cleanup cycles executed # TYPE gonka_node_pool_cleanup_cycles_total counter # HELP gonka_ta_selection_count Number of transfer-agent selections # TYPE gonka_ta_selection_count counter gonka_ta_selection_count{model="qwen/qwen3-235b-a22b-instruct-2507-fp8",ta="gonka1kx9mca3xm8u8ypzfuhmxey66u0ufxhs7nm6wc5"} 26 gonka_ta_selection_count{model="qwen/qwen3-235b-a22b-instruct-2507-fp8",ta="gonka1dkl4mah5erqggvhqkpc8j3qs5tyuetgdy552cp"} 24 gonka_ta_selection_count{model="qwen/qwen3-235b-a22b-instruct-2507-fp8",ta="gonka1y2a9p56kv044327uycmqdexl7zs82fs5ryv5le"} 31 # HELP gonka_ta_retry_count Number of retries scheduled after transfer-agent attempt failures # TYPE gonka_ta_retry_count counter gonka_ta_retry_count{model="qwen/qwen3-235b-a22b-instruct-2507-fp8",ta="gonka1kx9mca3xm8u8ypzfuhmxey66u0ufxhs7nm6wc5",reason="rate-limit"} 16 gonka_ta_retry_count{model="qwen/qwen3-235b-a22b-instruct-2507-fp8",ta="gonka1dkl4mah5erqggvhqkpc8j3qs5tyuetgdy552cp",reason="rate-limit"} 19 gonka_ta_retry_count{model="qwen/qwen3-235b-a22b-instruct-2507-fp8",ta="gonka1y2a9p56kv044327uycmqdexl7zs82fs5ryv5le",reason="rate-limit"} 14 # HELP gonka_ta_ttfb_ms Transfer-agent first token latency in milliseconds # TYPE gonka_ta_ttfb_ms histogram gonka_ta_ttfb_ms_bucket{le="50",model="qwen/qwen3-235b-a22b-instruct-2507-fp8",ta="gonka1dkl4mah5erqggvhqkpc8j3qs5tyuetgdy552cp"} 0 gonka_ta_ttfb_ms_bucket{le="100",model="qwen/qwen3-235b-a22b-instruct-2507-fp8",ta="gonka1dkl4mah5erqggvhqkpc8j3qs5tyuetgdy552cp"} 0 gonka_ta_ttfb_ms_bucket{le="250",model="qwen/qwen3-235b-a22b-instruct-2507-fp8",ta="gonka1dkl4mah5erqggvhqkpc8j3qs5tyuetgdy552cp"} 0 gonka_ta_ttfb_ms_bucket{le="500",model="qwen/qwen3-235b-a22b-instruct-2507-fp8",ta="gonka1dkl4mah5erqggvhqkpc8j3qs5tyuetgdy552cp"} 1 gonka_ta_ttfb_ms_bucket{le="1000",model="qwen/qwen3-235b-a22b-instruct-2507-fp8",ta="gonka1dkl4mah5erqggvhqkpc8j3qs5tyuetgdy552cp"} 1 gonka_ta_ttfb_ms_bucket{le="2000",model="qwen/qwen3-235b-a22b-instruct-2507-fp8",ta="gonka1dkl4mah5erqggvhqkpc8j3qs5tyuetgdy552cp"} 1 gonka_ta_ttfb_ms_bucket{le="5000",model="qwen/qwen3-235b-a22b-instruct-2507-fp8",ta="gonka1dkl4mah5erqggvhqkpc8j3qs5tyuetgdy552cp"} 1 gonka_ta_ttfb_ms_bucket{le="10000",model="qwen/qwen3-235b-a22b-instruct-2507-fp8",ta="gonka1dkl4mah5erqggvhqkpc8j3qs5tyuetgdy552cp"} 1 gonka_ta_ttfb_ms_bucket{le="20000",model="qwen/qwen3-235b-a22b-instruct-2507-fp8",ta="gonka1dkl4mah5erqggvhqkpc8j3qs5tyuetgdy552cp"} 1 gonka_ta_ttfb_ms_bucket{le="+Inf",model="qwen/qwen3-235b-a22b-instruct-2507-fp8",ta="gonka1dkl4mah5erqggvhqkpc8j3qs5tyuetgdy552cp"} 1 gonka_ta_ttfb_ms_sum{model="qwen/qwen3-235b-a22b-instruct-2507-fp8",ta="gonka1dkl4mah5erqggvhqkpc8j3qs5tyuetgdy552cp"} 412 gonka_ta_ttfb_ms_count{model="qwen/qwen3-235b-a22b-instruct-2507-fp8",ta="gonka1dkl4mah5erqggvhqkpc8j3qs5tyuetgdy552cp"} 1 # HELP gonka_ta_transport_error_count Transport-level errors per transfer-agent # TYPE gonka_ta_transport_error_count counter # HELP gonka_ta_short_suppression_count Short suppression activations for transfer-agent endpoints # TYPE gonka_ta_short_suppression_count counter gonka_ta_short_suppression_count{model="qwen/qwen3-235b-a22b-instruct-2507-fp8",ta="gonka1kx9mca3xm8u8ypzfuhmxey66u0ufxhs7nm6wc5",reason="rate-limit"} 26 gonka_ta_short_suppression_count{model="qwen/qwen3-235b-a22b-instruct-2507-fp8",ta="gonka1dkl4mah5erqggvhqkpc8j3qs5tyuetgdy552cp",reason="rate-limit"} 22 gonka_ta_short_suppression_count{model="qwen/qwen3-235b-a22b-instruct-2507-fp8",ta="gonka1y2a9p56kv044327uycmqdexl7zs82fs5ryv5le",reason="rate-limit"} 17 # HELP gonka_ta_quarantine_count Transport quarantine activations for transfer-agent endpoints # TYPE gonka_ta_quarantine_count counter # HELP gonka_ta_scheduler_score Sampled scheduler score for selected transfer-agents # TYPE gonka_ta_scheduler_score gauge gonka_ta_scheduler_score{model="qwen/qwen3-235b-a22b-instruct-2507-fp8",ta="gonka1kx9mca3xm8u8ypzfuhmxey66u0ufxhs7nm6wc5"} 0.6405845331388554 gonka_ta_scheduler_score{model="qwen/qwen3-235b-a22b-instruct-2507-fp8",ta="gonka1dkl4mah5erqggvhqkpc8j3qs5tyuetgdy552cp"} 0.5779953852337221 gonka_ta_scheduler_score{model="qwen/qwen3-235b-a22b-instruct-2507-fp8",ta="gonka1y2a9p56kv044327uycmqdexl7zs82fs5ryv5le"} 0.675091297592094 # HELP gonka_ta_policy_refresh_count Policy refresh executions by reason # TYPE gonka_ta_policy_refresh_count counter gonka_ta_policy_refresh_count{model="__unknown__",reason="discovery"} 6 gonka_ta_policy_refresh_count{model="__unknown__",reason="periodic"} 2 # HELP gonka_ta_endpoint_rebind_count Endpoint URL rebind events to transfer-agent identities # TYPE gonka_ta_endpoint_rebind_count counter # HELP gonka_ta_identity_unresolved_count Attempts where unresolved transfer-agent identities were observed # TYPE gonka_ta_identity_unresolved_count counter # HELP gonka_ta_identity_degraded_mode_count Attempts executed in identity degraded mode # TYPE gonka_ta_identity_degraded_mode_count counter # HELP gonka_ta_same_ta_retries_per_request Repeated retries on the same transfer-agent per request # TYPE gonka_ta_same_ta_retries_per_request histogram gonka_ta_same_ta_retries_per_request_bucket{le="0",model="qwen/qwen3-235b-a22b-instruct-2507-fp8"} 81 gonka_ta_same_ta_retries_per_request_bucket{le="1",model="qwen/qwen3-235b-a22b-instruct-2507-fp8"} 81 gonka_ta_same_ta_retries_per_request_bucket{le="2",model="qwen/qwen3-235b-a22b-instruct-2507-fp8"} 81 gonka_ta_same_ta_retries_per_request_bucket{le="3",model="qwen/qwen3-235b-a22b-instruct-2507-fp8"} 81 gonka_ta_same_ta_retries_per_request_bucket{le="4",model="qwen/qwen3-235b-a22b-instruct-2507-fp8"} 81 gonka_ta_same_ta_retries_per_request_bucket{le="6",model="qwen/qwen3-235b-a22b-instruct-2507-fp8"} 81 gonka_ta_same_ta_retries_per_request_bucket{le="8",model="qwen/qwen3-235b-a22b-instruct-2507-fp8"} 81 gonka_ta_same_ta_retries_per_request_bucket{le="+Inf",model="qwen/qwen3-235b-a22b-instruct-2507-fp8"} 81 gonka_ta_same_ta_retries_per_request_sum{model="qwen/qwen3-235b-a22b-instruct-2507-fp8"} 0 gonka_ta_same_ta_retries_per_request_count{model="qwen/qwen3-235b-a22b-instruct-2507-fp8"} 81 # HELP gonka_ta_allowlist_refresh_result_count Allowlist refresh result counts # TYPE gonka_ta_allowlist_refresh_result_count counter gonka_ta_allowlist_refresh_result_count{result="ok"} 8 # HELP gonka_ta_allowlist_active_request_count Attempt counts by effective allowlist state # TYPE gonka_ta_allowlist_active_request_count counter gonka_ta_allowlist_active_request_count{model="qwen/qwen3-235b-a22b-instruct-2507-fp8",state="active"} 81 # HELP gonka_ta_saturation_skip_count TA candidates skipped by saturation guard # TYPE gonka_ta_saturation_skip_count counter # HELP gonka_ta_retry_after_block_count TA candidates skipped by retry-after guard # TYPE gonka_ta_retry_after_block_count counter # HELP gonka_ta_rate_limit_penalty_applied_count Selected attempts where rate-limit penalty was applied # TYPE gonka_ta_rate_limit_penalty_applied_count counter gonka_ta_rate_limit_penalty_applied_count{model="qwen/qwen3-235b-a22b-instruct-2507-fp8",ta="gonka1kx9mca3xm8u8ypzfuhmxey66u0ufxhs7nm6wc5"} 26 gonka_ta_rate_limit_penalty_applied_count{model="qwen/qwen3-235b-a22b-instruct-2507-fp8",ta="gonka1dkl4mah5erqggvhqkpc8j3qs5tyuetgdy552cp"} 22 gonka_ta_rate_limit_penalty_applied_count{model="qwen/qwen3-235b-a22b-instruct-2507-fp8",ta="gonka1y2a9p56kv044327uycmqdexl7zs82fs5ryv5le"} 29 # HELP gonka_ta_inflight_requests_gauge In-flight requests observed at TA selection time # TYPE gonka_ta_inflight_requests_gauge gauge gonka_ta_inflight_requests_gauge{model="qwen/qwen3-235b-a22b-instruct-2507-fp8",ta="gonka1kx9mca3xm8u8ypzfuhmxey66u0ufxhs7nm6wc5"} 0 gonka_ta_inflight_requests_gauge{model="qwen/qwen3-235b-a22b-instruct-2507-fp8",ta="gonka1dkl4mah5erqggvhqkpc8j3qs5tyuetgdy552cp"} 0 gonka_ta_inflight_requests_gauge{model="qwen/qwen3-235b-a22b-instruct-2507-fp8",ta="gonka1y2a9p56kv044327uycmqdexl7zs82fs5ryv5le"} 1 # HELP gonka_rate_limit_checks_total Total number of rate limit checks # TYPE gonka_rate_limit_checks_total counter gonka_rate_limit_checks_total{scope="completions"} 22 # HELP gonka_rate_limit_hits_total Total number of rate limit blocks # TYPE gonka_rate_limit_hits_total counter # HELP gonka_rate_limit_redis_errors_total Total number of Redis errors during rate limit checks # TYPE gonka_rate_limit_redis_errors_total counter gonka_rate_limit_redis_errors_total 0 # HELP gonka_rate_limit_inflight Number of in-flight requests tracked by the rate limiter # TYPE gonka_rate_limit_inflight gauge gonka_rate_limit_inflight{scope="key"} 2 gonka_rate_limit_inflight{scope="user"} 2 # HELP gonka_rate_limit_degraded_mode Rate limiter degraded mode state (1=degraded, 0=healthy) # TYPE gonka_rate_limit_degraded_mode gauge gonka_rate_limit_degraded_mode{scope="public_ip_window"} 0 gonka_rate_limit_degraded_mode{scope="public_principal_window"} 0 gonka_rate_limit_degraded_mode{scope="public_global"} 0 gonka_rate_limit_degraded_mode{scope="public_principal_concurrency"} 0 # HELP gonka_abuse_detection_checks_total Total number of anti-abuse block checks # TYPE gonka_abuse_detection_checks_total counter # HELP gonka_abuse_detection_signals_total Total number of anti-abuse behavioral signal emissions # TYPE gonka_abuse_detection_signals_total counter gonka_abuse_detection_signals_total{model="qwen/qwen3-235b-a22b-instruct-2507-fp8"} 1 # HELP gonka_abuse_detection_blocks_total Total number of anti-abuse blocks by scope and reason # TYPE gonka_abuse_detection_blocks_total counter gonka_abuse_detection_blocks_total{scope="user_model",reason="behavior_prompt_token_repeat"} 1 gonka_abuse_detection_blocks_total{scope="key",reason="behavior_prompt_token_repeat_escalated"} 1 # HELP gonka_abuse_detection_redis_errors_total Total number of Redis errors during anti-abuse checks/updates # TYPE gonka_abuse_detection_redis_errors_total counter gonka_abuse_detection_redis_errors_total 0 # HELP gonka_under_pressure_event_loop_delay_ms Event loop delay in milliseconds # TYPE gonka_under_pressure_event_loop_delay_ms gauge gonka_under_pressure_event_loop_delay_ms 0.10968032653061321 # HELP gonka_under_pressure_heap_used_bytes Heap used bytes # TYPE gonka_under_pressure_heap_used_bytes gauge gonka_under_pressure_heap_used_bytes 109682072 # HELP gonka_under_pressure_rss_bytes RSS bytes # TYPE gonka_under_pressure_rss_bytes gauge gonka_under_pressure_rss_bytes 509497344 # HELP gonka_under_pressure_event_loop_utilization Event loop utilization (0-1) # TYPE gonka_under_pressure_event_loop_utilization gauge gonka_under_pressure_event_loop_utilization 0.049843014429897824 # HELP gonka_under_pressure_overloaded Under-pressure overload state (1=overloaded, 0=normal) # TYPE gonka_under_pressure_overloaded gauge gonka_under_pressure_overloaded 0 # HELP gonka_pdf_inputs_requests_total Total number of PDF-input request handling attempts # TYPE gonka_pdf_inputs_requests_total counter # HELP gonka_pdf_inputs_failures_total Total number of PDF-input processing failures by reason # TYPE gonka_pdf_inputs_failures_total counter # HELP gonka_pdf_inputs_fetch_duration_ms PDF URL fetch duration in milliseconds # TYPE gonka_pdf_inputs_fetch_duration_ms histogram gonka_pdf_inputs_fetch_duration_ms_bucket{le="1"} 0 gonka_pdf_inputs_fetch_duration_ms_bucket{le="5"} 0 gonka_pdf_inputs_fetch_duration_ms_bucket{le="10"} 0 gonka_pdf_inputs_fetch_duration_ms_bucket{le="25"} 0 gonka_pdf_inputs_fetch_duration_ms_bucket{le="50"} 0 gonka_pdf_inputs_fetch_duration_ms_bucket{le="100"} 0 gonka_pdf_inputs_fetch_duration_ms_bucket{le="250"} 0 gonka_pdf_inputs_fetch_duration_ms_bucket{le="500"} 0 gonka_pdf_inputs_fetch_duration_ms_bucket{le="1000"} 0 gonka_pdf_inputs_fetch_duration_ms_bucket{le="2500"} 0 gonka_pdf_inputs_fetch_duration_ms_bucket{le="5000"} 0 gonka_pdf_inputs_fetch_duration_ms_bucket{le="10000"} 0 gonka_pdf_inputs_fetch_duration_ms_bucket{le="+Inf"} 0 gonka_pdf_inputs_fetch_duration_ms_sum 0 gonka_pdf_inputs_fetch_duration_ms_count 0 # HELP gonka_pdf_inputs_parse_duration_ms PDF parse duration in milliseconds # TYPE gonka_pdf_inputs_parse_duration_ms histogram gonka_pdf_inputs_parse_duration_ms_bucket{le="1"} 0 gonka_pdf_inputs_parse_duration_ms_bucket{le="5"} 0 gonka_pdf_inputs_parse_duration_ms_bucket{le="10"} 0 gonka_pdf_inputs_parse_duration_ms_bucket{le="25"} 0 gonka_pdf_inputs_parse_duration_ms_bucket{le="50"} 0 gonka_pdf_inputs_parse_duration_ms_bucket{le="100"} 0 gonka_pdf_inputs_parse_duration_ms_bucket{le="250"} 0 gonka_pdf_inputs_parse_duration_ms_bucket{le="500"} 0 gonka_pdf_inputs_parse_duration_ms_bucket{le="1000"} 0 gonka_pdf_inputs_parse_duration_ms_bucket{le="2500"} 0 gonka_pdf_inputs_parse_duration_ms_bucket{le="5000"} 0 gonka_pdf_inputs_parse_duration_ms_bucket{le="10000"} 0 gonka_pdf_inputs_parse_duration_ms_bucket{le="+Inf"} 0 gonka_pdf_inputs_parse_duration_ms_sum 0 gonka_pdf_inputs_parse_duration_ms_count 0 # HELP gonka_pdf_inputs_parse_queue_depth Current number of waiting tasks in PDF parse queue # TYPE gonka_pdf_inputs_parse_queue_depth gauge gonka_pdf_inputs_parse_queue_depth 0 # HELP gonka_pdf_inputs_parse_queue_rejections_total Number of requests rejected because PDF parse queue is full # TYPE gonka_pdf_inputs_parse_queue_rejections_total counter gonka_pdf_inputs_parse_queue_rejections_total 0 # HELP gonka_pdf_inputs_bytes PDF bytes size processed by PDF inputs # TYPE gonka_pdf_inputs_bytes histogram gonka_pdf_inputs_bytes_bucket{le="1024"} 0 gonka_pdf_inputs_bytes_bucket{le="10240"} 0 gonka_pdf_inputs_bytes_bucket{le="102400"} 0 gonka_pdf_inputs_bytes_bucket{le="1048576"} 0 gonka_pdf_inputs_bytes_bucket{le="5242880"} 0 gonka_pdf_inputs_bytes_bucket{le="10485760"} 0 gonka_pdf_inputs_bytes_bucket{le="20971520"} 0 gonka_pdf_inputs_bytes_bucket{le="+Inf"} 0 gonka_pdf_inputs_bytes_sum 0 gonka_pdf_inputs_bytes_count 0 # HELP gonka_pdf_inputs_pages Page count processed by PDF inputs parser # TYPE gonka_pdf_inputs_pages histogram gonka_pdf_inputs_pages_bucket{le="1"} 0 gonka_pdf_inputs_pages_bucket{le="2"} 0 gonka_pdf_inputs_pages_bucket{le="5"} 0 gonka_pdf_inputs_pages_bucket{le="10"} 0 gonka_pdf_inputs_pages_bucket{le="20"} 0 gonka_pdf_inputs_pages_bucket{le="50"} 0 gonka_pdf_inputs_pages_bucket{le="100"} 0 gonka_pdf_inputs_pages_bucket{le="200"} 0 gonka_pdf_inputs_pages_bucket{le="+Inf"} 0 gonka_pdf_inputs_pages_sum 0 gonka_pdf_inputs_pages_count 0 # HELP gonka_pdf_inputs_cache_hits_total Number of PDF parse cache hits # TYPE gonka_pdf_inputs_cache_hits_total counter gonka_pdf_inputs_cache_hits_total 0 # HELP gonka_pdf_inputs_cache_misses_total Number of PDF parse cache misses # TYPE gonka_pdf_inputs_cache_misses_total counter gonka_pdf_inputs_cache_misses_total 0 # HELP gonka_pdf_inputs_worker_tasks_total Total number of PDF worker tasks by task/result # TYPE gonka_pdf_inputs_worker_tasks_total counter gonka_pdf_inputs_worker_tasks_total{task="ping",result="success"} 2 # HELP gonka_pdf_inputs_worker_task_duration_ms PDF worker task duration in milliseconds # TYPE gonka_pdf_inputs_worker_task_duration_ms histogram gonka_pdf_inputs_worker_task_duration_ms_bucket{le="1",task="ping",result="success"} 0 gonka_pdf_inputs_worker_task_duration_ms_bucket{le="5",task="ping",result="success"} 0 gonka_pdf_inputs_worker_task_duration_ms_bucket{le="10",task="ping",result="success"} 0 gonka_pdf_inputs_worker_task_duration_ms_bucket{le="25",task="ping",result="success"} 0 gonka_pdf_inputs_worker_task_duration_ms_bucket{le="50",task="ping",result="success"} 0 gonka_pdf_inputs_worker_task_duration_ms_bucket{le="100",task="ping",result="success"} 0 gonka_pdf_inputs_worker_task_duration_ms_bucket{le="250",task="ping",result="success"} 2 gonka_pdf_inputs_worker_task_duration_ms_bucket{le="500",task="ping",result="success"} 2 gonka_pdf_inputs_worker_task_duration_ms_bucket{le="1000",task="ping",result="success"} 2 gonka_pdf_inputs_worker_task_duration_ms_bucket{le="2500",task="ping",result="success"} 2 gonka_pdf_inputs_worker_task_duration_ms_bucket{le="5000",task="ping",result="success"} 2 gonka_pdf_inputs_worker_task_duration_ms_bucket{le="10000",task="ping",result="success"} 2 gonka_pdf_inputs_worker_task_duration_ms_bucket{le="+Inf",task="ping",result="success"} 2 gonka_pdf_inputs_worker_task_duration_ms_sum{task="ping",result="success"} 408 gonka_pdf_inputs_worker_task_duration_ms_count{task="ping",result="success"} 2 # HELP gonka_pdf_inputs_worker_queue_depth Current number of waiting tasks in PDF worker queue # TYPE gonka_pdf_inputs_worker_queue_depth gauge gonka_pdf_inputs_worker_queue_depth 0 # HELP gonka_pdf_inputs_worker_restarts_total Number of PDF worker restarts after crash/timeout # TYPE gonka_pdf_inputs_worker_restarts_total counter # HELP gonka_pdf_inputs_worker_token_fallback_total Number of PDF worker tokenization fallback activations # TYPE gonka_pdf_inputs_worker_token_fallback_total counter # HELP gonka_plugin_settings_defaults_applied_total Total number of plugin defaults applied by runtime policy # TYPE gonka_plugin_settings_defaults_applied_total counter # HELP gonka_plugin_settings_overrides_applied_total Total number of request plugin overrides allowed by runtime policy # TYPE gonka_plugin_settings_overrides_applied_total counter # HELP gonka_plugin_settings_overrides_blocked_total Total number of request plugin overrides blocked by runtime policy # TYPE gonka_plugin_settings_overrides_blocked_total counter # HELP gonka_streaming_sse_backpressure_waits_total Number of SSE writes that waited for socket drain due to backpressure # TYPE gonka_streaming_sse_backpressure_waits_total counter gonka_streaming_sse_backpressure_waits_total 0 # HELP gonka_streaming_sse_backpressure_wait_duration_ms Duration in milliseconds spent waiting for SSE socket drain # TYPE gonka_streaming_sse_backpressure_wait_duration_ms histogram gonka_streaming_sse_backpressure_wait_duration_ms_bucket{le="1"} 0 gonka_streaming_sse_backpressure_wait_duration_ms_bucket{le="5"} 0 gonka_streaming_sse_backpressure_wait_duration_ms_bucket{le="10"} 0 gonka_streaming_sse_backpressure_wait_duration_ms_bucket{le="25"} 0 gonka_streaming_sse_backpressure_wait_duration_ms_bucket{le="50"} 0 gonka_streaming_sse_backpressure_wait_duration_ms_bucket{le="100"} 0 gonka_streaming_sse_backpressure_wait_duration_ms_bucket{le="250"} 0 gonka_streaming_sse_backpressure_wait_duration_ms_bucket{le="500"} 0 gonka_streaming_sse_backpressure_wait_duration_ms_bucket{le="1000"} 0 gonka_streaming_sse_backpressure_wait_duration_ms_bucket{le="2500"} 0 gonka_streaming_sse_backpressure_wait_duration_ms_bucket{le="5000"} 0 gonka_streaming_sse_backpressure_wait_duration_ms_bucket{le="+Inf"} 0 gonka_streaming_sse_backpressure_wait_duration_ms_sum 0 gonka_streaming_sse_backpressure_wait_duration_ms_count 0 # HELP gonka_chat_completion_requests_total Total authenticated chat completion requests grouped by request characteristics # TYPE gonka_chat_completion_requests_total counter gonka_chat_completion_requests_total{stream="true",feature_profile="baseline",preset="false",app_attribution="false"} 1 gonka_chat_completion_requests_total{stream="false",feature_profile="baseline",preset="false",app_attribution="false"} 21 # HELP gonka_chat_history_requests_total Total chat history execution requests grouped by route family, operation, transport, and targeting mode # TYPE gonka_chat_history_requests_total counter # HELP gonka_chat_history_execution_readback_total Total assistant execution readback projections grouped by source and snapshot version # TYPE gonka_chat_history_execution_readback_total counter # HELP gonka_chat_history_reconciliation_runs_total Total startup reconciliation runs for stranded in-progress assistant messages # TYPE gonka_chat_history_reconciliation_runs_total counter gonka_chat_history_reconciliation_runs_total{result="success"} 1 # HELP gonka_chat_history_reconciled_assistants_total Total stranded assistant messages reconciled by reason # TYPE gonka_chat_history_reconciled_assistants_total counter # HELP gonka_api_key_auth_mode_total API key auth outcome mode counts for migration tracking # TYPE gonka_api_key_auth_mode_total counter gonka_api_key_auth_mode_total{mode="v2_hit"} 24 # HELP gonka_api_key_auth_verify_duration_ms API key auth verification duration in milliseconds by verification path # TYPE gonka_api_key_auth_verify_duration_ms histogram gonka_api_key_auth_verify_duration_ms_bucket{le="0.5",path="v2",outcome="hit"} 0 gonka_api_key_auth_verify_duration_ms_bucket{le="1",path="v2",outcome="hit"} 0 gonka_api_key_auth_verify_duration_ms_bucket{le="2",path="v2",outcome="hit"} 0 gonka_api_key_auth_verify_duration_ms_bucket{le="5",path="v2",outcome="hit"} 0 gonka_api_key_auth_verify_duration_ms_bucket{le="10",path="v2",outcome="hit"} 0 gonka_api_key_auth_verify_duration_ms_bucket{le="25",path="v2",outcome="hit"} 23 gonka_api_key_auth_verify_duration_ms_bucket{le="50",path="v2",outcome="hit"} 23 gonka_api_key_auth_verify_duration_ms_bucket{le="100",path="v2",outcome="hit"} 24 gonka_api_key_auth_verify_duration_ms_bucket{le="250",path="v2",outcome="hit"} 24 gonka_api_key_auth_verify_duration_ms_bucket{le="500",path="v2",outcome="hit"} 24 gonka_api_key_auth_verify_duration_ms_bucket{le="1000",path="v2",outcome="hit"} 24 gonka_api_key_auth_verify_duration_ms_bucket{le="2500",path="v2",outcome="hit"} 24 gonka_api_key_auth_verify_duration_ms_bucket{le="+Inf",path="v2",outcome="hit"} 24 gonka_api_key_auth_verify_duration_ms_sum{path="v2",outcome="hit"} 432 gonka_api_key_auth_verify_duration_ms_count{path="v2",outcome="hit"} 24 # HELP gonka_api_key_auth_legacy_upgrade_total Legacy API key lazy-upgrade attempts and outcomes # TYPE gonka_api_key_auth_legacy_upgrade_total counter # HELP gonka_management_auth_verify_duration_ms Management auth verification duration in milliseconds # TYPE gonka_management_auth_verify_duration_ms histogram # HELP gonka_management_auth_failure_total Management auth failures by normalized reason # TYPE gonka_management_auth_failure_total counter # HELP gonka_privacy_sanitization_requests_total Total number of privacy sanitization request outcomes by mode # TYPE gonka_privacy_sanitization_requests_total counter # HELP gonka_privacy_sanitization_fail_policy_total Total number of privacy sanitization fail-policy branch activations # TYPE gonka_privacy_sanitization_fail_policy_total counter # HELP gonka_privacy_sanitization_restore_total Total number of privacy sanitization restore outcomes # TYPE gonka_privacy_sanitization_restore_total counter # HELP gonka_privacy_sanitization_history_writeback_total Total number of privacy history writeback transport outcomes # TYPE gonka_privacy_sanitization_history_writeback_total counter # HELP gonka_web_search_requests_total Total number of web-search request outcomes by provider and result # TYPE gonka_web_search_requests_total counter # HELP gonka_web_search_request_duration_ms Web-search request duration in milliseconds by provider and result # TYPE gonka_web_search_request_duration_ms histogram # HELP gonka_web_search_health_status Web-search sidecar health status by provider (1=healthy, 0=unhealthy) # TYPE gonka_web_search_health_status gauge # HELP gonka_web_search_observation_imports_total Proxy observation-import outcomes by source, decision, and execution state # TYPE gonka_web_search_observation_imports_total counter # HELP gonka_web_search_proxy_finalizations_total Proxy web-search request finalization outcomes by response mode # TYPE gonka_web_search_proxy_finalizations_total counter # HELP gonka_web_search_closure_transitions_total Proxy web-search closure transitions by destination state and reason # TYPE gonka_web_search_closure_transitions_total counter # HELP gonka_web_search_settled_charge_usd_total Settled logical web-search charges frozen by proxy closure transitions # TYPE gonka_web_search_settled_charge_usd_total counter gonka_web_search_settled_charge_usd_total 0 # HELP gonka_tokenization_requests_total Tokenization request attempts by surface, strategy, and mode # TYPE gonka_tokenization_requests_total counter # HELP gonka_tokenization_fallback_total Tokenization fallback activations by reason and preferred strategy # TYPE gonka_tokenization_fallback_total counter