Files
coder/scripts/metricsdocgen/metrics
T
Paweł Banaszewski f1ce1013c4 chore: export AI Gateway metrics under new branding + keep old as alias (#26413)
> AI Tools where used in this request.

Registers `coder_aibridged_*` and `coder_aibridgeproxyd_*` metrics under
new prefixes: `coder_ai_gateway_*` and `coder_ai_gateway_proxy_*`.
Old prefix is still exported. Will be removed in later release.

Also updated the `metricsdocgen` static fixture. Added 4
previously-undocumented metrics `key_pool_state`,
`key_pool_state_transitions_total`, `key_pool_exhaustions_total`,
`key_pool_failover_attempts` added the `client` label to the existing
interception, prompt, and token counter samples.

Updated AI Gateway documentation.
2026-06-17 13:10:53 +02:00

252 lines
19 KiB
Plaintext

# HELP agent_scripts_executed_total Total number of scripts executed by the Coder agent. Includes cron scheduled scripts.
# TYPE agent_scripts_executed_total counter
agent_scripts_executed_total{agent_name="main",success="true",template_name="docker",username="admin",workspace_name="workspace-1"} 1
# HELP coderd_agentstats_startup_script_seconds The number of seconds the startup script took to execute.
# TYPE coderd_agentstats_startup_script_seconds gauge
coderd_agentstats_startup_script_seconds{agent_name="main",success="true",template_name="docker",username="admin",workspace_name="workspace-1"} 1.969900304
# HELP coderd_agentstats_connection_count The number of established connections by agent
# TYPE coderd_agentstats_connection_count gauge
coderd_agentstats_connection_count{agent_name="main",username="admin",workspace_name="workspace1"} 2
# HELP coderd_agentstats_connection_median_latency_seconds The median agent connection latency
# TYPE coderd_agentstats_connection_median_latency_seconds gauge
coderd_agentstats_connection_median_latency_seconds{agent_name="main",username="admin",workspace_name="workspace1"} 0.001784
# HELP coderd_agentstats_currently_reachable_peers The number of peers (e.g. clients) that are currently reachable over the encrypted network.
# TYPE coderd_agentstats_currently_reachable_peers gauge
coderd_agentstats_currently_reachable_peers{agent_name="main",connection_type="derp",template_name="docker",username="admin",workspace_name="workspace1"} 0
# HELP coderd_agentstats_rx_bytes Agent Rx bytes
# TYPE coderd_agentstats_rx_bytes gauge
coderd_agentstats_rx_bytes{agent_name="main",username="admin",workspace_name="workspace1"} 7731
# HELP coderd_agentstats_session_count_jetbrains The number of session established by JetBrains
# TYPE coderd_agentstats_session_count_jetbrains gauge
coderd_agentstats_session_count_jetbrains{agent_name="main",username="admin",workspace_name="workspace1"} 0
# HELP coderd_agentstats_session_count_reconnecting_pty The number of session established by reconnecting PTY
# TYPE coderd_agentstats_session_count_reconnecting_pty gauge
coderd_agentstats_session_count_reconnecting_pty{agent_name="main",username="admin",workspace_name="workspace1"} 1
# HELP coderd_agentstats_session_count_ssh The number of session established by SSH
# TYPE coderd_agentstats_session_count_ssh gauge
coderd_agentstats_session_count_ssh{agent_name="main",username="admin",workspace_name="workspace1"} 0
# HELP coderd_agentstats_session_count_vscode The number of session established by VSCode
# TYPE coderd_agentstats_session_count_vscode gauge
coderd_agentstats_session_count_vscode{agent_name="main",username="admin",workspace_name="workspace1"} 0
# HELP coderd_agentstats_tx_bytes Agent Tx bytes
# TYPE coderd_agentstats_tx_bytes gauge
coderd_agentstats_tx_bytes{agent_name="main",username="admin",workspace_name="workspace1"} 6643
# HELP go_gc_duration_seconds A summary of the pause duration of garbage collection cycles.
# TYPE go_gc_duration_seconds summary
go_gc_duration_seconds{quantile="0"} 2.4056e-05
go_gc_duration_seconds{quantile="0.25"} 7.4116e-05
go_gc_duration_seconds{quantile="0.5"} 0.000104901
go_gc_duration_seconds{quantile="0.75"} 0.000201704
go_gc_duration_seconds{quantile="1"} 0.017164708
go_gc_duration_seconds_sum 0.026439568
go_gc_duration_seconds_count 42
# HELP go_goroutines Number of goroutines that currently exist.
# TYPE go_goroutines gauge
go_goroutines 125
# HELP go_info Information about the Go environment.
# TYPE go_info gauge
go_info{version="go1.19.1"} 1
# HELP go_memstats_alloc_bytes Number of bytes allocated and still in use.
# TYPE go_memstats_alloc_bytes gauge
go_memstats_alloc_bytes 6.3568392e+07
# HELP go_memstats_alloc_bytes_total Total number of bytes allocated, even if freed.
# TYPE go_memstats_alloc_bytes_total counter
go_memstats_alloc_bytes_total 1.139801264e+09
# HELP go_memstats_buck_hash_sys_bytes Number of bytes used by the profiling bucket hash table.
# TYPE go_memstats_buck_hash_sys_bytes gauge
go_memstats_buck_hash_sys_bytes 1.53062e+06
# HELP go_memstats_frees_total Total number of frees.
# TYPE go_memstats_frees_total counter
go_memstats_frees_total 1.29308e+06
# HELP go_memstats_gc_sys_bytes Number of bytes used for garbage collection system metadata.
# TYPE go_memstats_gc_sys_bytes gauge
go_memstats_gc_sys_bytes 2.5494696e+07
# HELP go_memstats_heap_alloc_bytes Number of heap bytes allocated and still in use.
# TYPE go_memstats_heap_alloc_bytes gauge
go_memstats_heap_alloc_bytes 6.3568392e+07
# HELP go_memstats_heap_idle_bytes Number of heap bytes waiting to be used.
# TYPE go_memstats_heap_idle_bytes gauge
go_memstats_heap_idle_bytes 4.14302208e+08
# HELP go_memstats_heap_inuse_bytes Number of heap bytes that are in use.
# TYPE go_memstats_heap_inuse_bytes gauge
go_memstats_heap_inuse_bytes 6.971392e+07
# HELP go_memstats_heap_objects Number of allocated objects.
# TYPE go_memstats_heap_objects gauge
go_memstats_heap_objects 62042
# HELP go_memstats_heap_released_bytes Number of heap bytes released to OS.
# TYPE go_memstats_heap_released_bytes gauge
go_memstats_heap_released_bytes 3.59923712e+08
# HELP go_memstats_heap_sys_bytes Number of heap bytes obtained from system.
# TYPE go_memstats_heap_sys_bytes gauge
go_memstats_heap_sys_bytes 4.84016128e+08
# HELP go_memstats_last_gc_time_seconds Number of seconds since 1970 of last garbage collection.
# TYPE go_memstats_last_gc_time_seconds gauge
go_memstats_last_gc_time_seconds 1.6736263118982203e+09
# HELP go_memstats_lookups_total Total number of pointer lookups.
# TYPE go_memstats_lookups_total counter
go_memstats_lookups_total 0
# HELP go_memstats_mallocs_total Total number of mallocs.
# TYPE go_memstats_mallocs_total counter
go_memstats_mallocs_total 1.355122e+06
# HELP go_memstats_mcache_inuse_bytes Number of bytes in use by mcache structures.
# TYPE go_memstats_mcache_inuse_bytes gauge
go_memstats_mcache_inuse_bytes 9600
# HELP go_memstats_mcache_sys_bytes Number of bytes used for mcache structures obtained from system.
# TYPE go_memstats_mcache_sys_bytes gauge
go_memstats_mcache_sys_bytes 15600
# HELP go_memstats_mspan_inuse_bytes Number of bytes in use by mspan structures.
# TYPE go_memstats_mspan_inuse_bytes gauge
go_memstats_mspan_inuse_bytes 251736
# HELP go_memstats_mspan_sys_bytes Number of bytes used for mspan structures obtained from system.
# TYPE go_memstats_mspan_sys_bytes gauge
go_memstats_mspan_sys_bytes 620160
# HELP go_memstats_next_gc_bytes Number of heap bytes when next garbage collection will take place.
# TYPE go_memstats_next_gc_bytes gauge
go_memstats_next_gc_bytes 1.26085704e+08
# HELP go_memstats_other_sys_bytes Number of bytes used for other system allocations.
# TYPE go_memstats_other_sys_bytes gauge
go_memstats_other_sys_bytes 1.898084e+06
# HELP go_memstats_stack_inuse_bytes Number of bytes in use by the stack allocator.
# TYPE go_memstats_stack_inuse_bytes gauge
go_memstats_stack_inuse_bytes 2.523136e+06
# HELP go_memstats_stack_sys_bytes Number of bytes obtained from system for stack allocator.
# TYPE go_memstats_stack_sys_bytes gauge
go_memstats_stack_sys_bytes 2.523136e+06
# HELP go_memstats_sys_bytes Number of bytes obtained from system.
# TYPE go_memstats_sys_bytes gauge
go_memstats_sys_bytes 5.16098424e+08
# HELP go_threads Number of OS threads created.
# TYPE go_threads gauge
go_threads 13
# HELP process_cpu_seconds_total Total user and system CPU time spent in seconds.
# TYPE process_cpu_seconds_total counter
process_cpu_seconds_total 17.8
# HELP process_max_fds Maximum number of open file descriptors.
# TYPE process_max_fds gauge
process_max_fds 1.048576e+06
# HELP process_open_fds Number of open file descriptors.
# TYPE process_open_fds gauge
process_open_fds 28
# HELP process_resident_memory_bytes Resident memory size in bytes.
# TYPE process_resident_memory_bytes gauge
process_resident_memory_bytes 3.06302976e+08
# 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 1.67362454586e+09
# HELP process_virtual_memory_bytes Virtual memory size in bytes.
# TYPE process_virtual_memory_bytes gauge
process_virtual_memory_bytes 1.406291968e+09
# HELP process_virtual_memory_max_bytes Maximum amount of virtual memory available in bytes.
# TYPE process_virtual_memory_max_bytes gauge
process_virtual_memory_max_bytes 1.8446744073709552e+19
# HELP promhttp_metric_handler_requests_in_flight Current number of scrapes being served.
# TYPE promhttp_metric_handler_requests_in_flight gauge
promhttp_metric_handler_requests_in_flight 1
# HELP promhttp_metric_handler_requests_total Total number of scrapes by HTTP status code.
# TYPE promhttp_metric_handler_requests_total counter
promhttp_metric_handler_requests_total{code="200"} 2
promhttp_metric_handler_requests_total{code="500"} 0
promhttp_metric_handler_requests_total{code="503"} 0
# HELP coder_ai_gateway_injected_tool_invocations_total The number of times an injected MCP tool was invoked by AI Gateway.
# TYPE coder_ai_gateway_injected_tool_invocations_total counter
coder_ai_gateway_injected_tool_invocations_total{model="gpt-5-nano",name="coder_list_templates",provider="openai",server="https://xxx.pit-1.try.coder.app/api/experimental/mcp/http"} 1
# HELP coder_ai_gateway_interceptions_duration_seconds The total duration of intercepted requests, in seconds. The majority of this time will be the upstream processing of the request. AI Gateway has no control over upstream processing time, so it's just an illustrative metric.
# TYPE coder_ai_gateway_interceptions_duration_seconds histogram
coder_ai_gateway_interceptions_duration_seconds_bucket{model="gpt-5-nano",provider="openai",le="0.5"} 0
coder_ai_gateway_interceptions_duration_seconds_bucket{model="gpt-5-nano",provider="openai",le="2"} 0
coder_ai_gateway_interceptions_duration_seconds_bucket{model="gpt-5-nano",provider="openai",le="5"} 3
coder_ai_gateway_interceptions_duration_seconds_bucket{model="gpt-5-nano",provider="openai",le="15"} 6
coder_ai_gateway_interceptions_duration_seconds_bucket{model="gpt-5-nano",provider="openai",le="30"} 6
coder_ai_gateway_interceptions_duration_seconds_bucket{model="gpt-5-nano",provider="openai",le="60"} 6
coder_ai_gateway_interceptions_duration_seconds_bucket{model="gpt-5-nano",provider="openai",le="120"} 6
coder_ai_gateway_interceptions_duration_seconds_bucket{model="gpt-5-nano",provider="openai",le="+Inf"} 6
coder_ai_gateway_interceptions_duration_seconds_sum{model="gpt-5-nano",provider="openai"} 34.120188692
coder_ai_gateway_interceptions_duration_seconds_count{model="gpt-5-nano",provider="openai"} 6
# HELP coder_ai_gateway_interceptions_inflight The number of intercepted requests which are being processed.
# TYPE coder_ai_gateway_interceptions_inflight gauge
coder_ai_gateway_interceptions_inflight{model="gpt-5-nano",provider="openai",route="/v1/chat/completions"} 0
# HELP coder_ai_gateway_interceptions_total The count of intercepted requests.
# TYPE coder_ai_gateway_interceptions_total counter
coder_ai_gateway_interceptions_total{client="Codex",initiator_id="95f6752b-08cc-4cf1-97f7-c2165e3519c5",method="POST",model="gpt-5-nano",provider="openai",route="/v1/chat/completions",status="completed"} 6
# HELP coder_ai_gateway_key_pool_state The number of keys currently in each state (state: valid, temporary, permanent).
# TYPE coder_ai_gateway_key_pool_state gauge
coder_ai_gateway_key_pool_state{provider="openai",state="valid"} 2
coder_ai_gateway_key_pool_state{provider="openai",state="temporary"} 0
coder_ai_gateway_key_pool_state{provider="openai",state="permanent"} 0
# HELP coder_ai_gateway_key_pool_state_transitions_total The number of API key state transitions during failover (reason: rate_limited, unauthorized, forbidden).
# TYPE coder_ai_gateway_key_pool_state_transitions_total counter
coder_ai_gateway_key_pool_state_transitions_total{provider="openai",reason="rate_limited"} 1
# HELP coder_ai_gateway_key_pool_exhaustions_total The number of times the key pool was exhausted with no usable key (outcome: rate_limited, auth_failed).
# TYPE coder_ai_gateway_key_pool_exhaustions_total counter
coder_ai_gateway_key_pool_exhaustions_total{provider="openai",outcome="rate_limited"} 1
# HELP coder_ai_gateway_key_pool_failover_attempts The number of keys attempted before success or exhaustion, per interception for bridged requests and per request for passthrough requests.
# TYPE coder_ai_gateway_key_pool_failover_attempts histogram
coder_ai_gateway_key_pool_failover_attempts_bucket{provider="openai",le="1"} 0
coder_ai_gateway_key_pool_failover_attempts_bucket{provider="openai",le="2"} 1
coder_ai_gateway_key_pool_failover_attempts_bucket{provider="openai",le="3"} 1
coder_ai_gateway_key_pool_failover_attempts_bucket{provider="openai",le="4"} 1
coder_ai_gateway_key_pool_failover_attempts_bucket{provider="openai",le="5"} 1
coder_ai_gateway_key_pool_failover_attempts_bucket{provider="openai",le="10"} 1
coder_ai_gateway_key_pool_failover_attempts_bucket{provider="openai",le="25"} 1
coder_ai_gateway_key_pool_failover_attempts_bucket{provider="openai",le="+Inf"} 1
coder_ai_gateway_key_pool_failover_attempts_sum{provider="openai"} 2
coder_ai_gateway_key_pool_failover_attempts_count{provider="openai"} 1
# HELP coder_ai_gateway_non_injected_tool_selections_total The number of times an AI model selected a tool to be invoked by the client.
# TYPE coder_ai_gateway_non_injected_tool_selections_total counter
coder_ai_gateway_non_injected_tool_selections_total{model="gpt-5-nano",name="read_file",provider="openai"} 2
# HELP coder_ai_gateway_prompts_total The number of prompts issued by users (initiators).
# TYPE coder_ai_gateway_prompts_total counter
coder_ai_gateway_prompts_total{client="Codex",initiator_id="95f6752b-08cc-4cf1-97f7-c2165e3519c5",model="gpt-5-nano",provider="openai"} 4
# HELP coder_ai_gateway_tokens_total The number of tokens used by intercepted requests.
# TYPE coder_ai_gateway_tokens_total counter
coder_ai_gateway_tokens_total{client="Codex",initiator_id="95f6752b-08cc-4cf1-97f7-c2165e3519c5",model="gpt-5-nano",provider="openai",type="completion_accepted_prediction"} 0
coder_ai_gateway_tokens_total{client="Codex",initiator_id="95f6752b-08cc-4cf1-97f7-c2165e3519c5",model="gpt-5-nano",provider="openai",type="completion_audio"} 0
coder_ai_gateway_tokens_total{client="Codex",initiator_id="95f6752b-08cc-4cf1-97f7-c2165e3519c5",model="gpt-5-nano",provider="openai",type="completion_reasoning"} 1664
coder_ai_gateway_tokens_total{client="Codex",initiator_id="95f6752b-08cc-4cf1-97f7-c2165e3519c5",model="gpt-5-nano",provider="openai",type="completion_rejected_prediction"} 0
coder_ai_gateway_tokens_total{client="Codex",initiator_id="95f6752b-08cc-4cf1-97f7-c2165e3519c5",model="gpt-5-nano",provider="openai",type="input"} 13823
coder_ai_gateway_tokens_total{client="Codex",initiator_id="95f6752b-08cc-4cf1-97f7-c2165e3519c5",model="gpt-5-nano",provider="openai",type="output"} 2014
coder_ai_gateway_tokens_total{client="Codex",initiator_id="95f6752b-08cc-4cf1-97f7-c2165e3519c5",model="gpt-5-nano",provider="openai",type="prompt_audio"} 0
coder_ai_gateway_tokens_total{client="Codex",initiator_id="95f6752b-08cc-4cf1-97f7-c2165e3519c5",model="gpt-5-nano",provider="openai",type="prompt_cached"} 31872
# HELP coder_ai_gateway_circuit_breaker_rejects_total Total number of requests rejected due to open circuit breaker.
# TYPE coder_ai_gateway_circuit_breaker_rejects_total counter
coder_ai_gateway_circuit_breaker_rejects_total{provider="",endpoint="",model=""} 0
# HELP coder_ai_gateway_circuit_breaker_state Current state of the circuit breaker (0=closed, 0.5=half-open, 1=open).
# TYPE coder_ai_gateway_circuit_breaker_state gauge
coder_ai_gateway_circuit_breaker_state{provider="",endpoint="",model=""} 0
# HELP coder_ai_gateway_circuit_breaker_trips_total Total number of times the circuit breaker transitioned to open state.
# TYPE coder_ai_gateway_circuit_breaker_trips_total counter
coder_ai_gateway_circuit_breaker_trips_total{provider="",endpoint="",model=""} 0
# HELP coder_ai_gateway_passthrough_total The count of requests which were not intercepted but passed through to the upstream.
# TYPE coder_ai_gateway_passthrough_total counter
coder_ai_gateway_passthrough_total{provider="",route="",method=""} 0
# HELP coder_ai_gateway_proxy_connect_sessions_total Total number of CONNECT sessions established.
# TYPE coder_ai_gateway_proxy_connect_sessions_total counter
coder_ai_gateway_proxy_connect_sessions_total{type=""} 0
# HELP coder_ai_gateway_proxy_inflight_mitm_requests Number of MITM requests currently being processed.
# TYPE coder_ai_gateway_proxy_inflight_mitm_requests gauge
coder_ai_gateway_proxy_inflight_mitm_requests{provider=""} 0
# HELP coder_ai_gateway_proxy_mitm_requests_total Total number of MITM requests handled by the proxy.
# TYPE coder_ai_gateway_proxy_mitm_requests_total counter
coder_ai_gateway_proxy_mitm_requests_total{provider=""} 0
# HELP coder_ai_gateway_proxy_mitm_responses_total Total number of MITM responses by HTTP status code class.
# TYPE coder_ai_gateway_proxy_mitm_responses_total counter
coder_ai_gateway_proxy_mitm_responses_total{code="",provider=""} 0
# HELP coder_ai_gateway_provider_info One series per configured AI provider. Value is always 1; the status label (enabled, disabled, error) carries the alertable signal.
# TYPE coder_ai_gateway_provider_info gauge
coder_ai_gateway_provider_info{provider_name="",provider_type="",status=""} 0
# HELP coder_ai_gateway_providers_last_reload_timestamp_seconds Unix timestamp of the last provider reload attempt, success or failure.
# TYPE coder_ai_gateway_providers_last_reload_timestamp_seconds gauge
coder_ai_gateway_providers_last_reload_timestamp_seconds 0
# HELP coder_ai_gateway_providers_last_reload_success_timestamp_seconds Unix timestamp of the last provider reload that successfully refreshed the pool. A gap against the providers_last_reload_timestamp_seconds gauge means the loop is firing but the refresh function is failing.
# TYPE coder_ai_gateway_providers_last_reload_success_timestamp_seconds gauge
coder_ai_gateway_providers_last_reload_success_timestamp_seconds 0
# HELP coder_ai_gateway_proxy_provider_info One series per configured AI provider. Value is always 1; the status label (enabled, disabled, error) carries the alertable signal.
# TYPE coder_ai_gateway_proxy_provider_info gauge
coder_ai_gateway_proxy_provider_info{provider_name="",provider_type="",status=""} 0
# HELP coder_ai_gateway_proxy_providers_last_reload_timestamp_seconds Unix timestamp of the last provider reload attempt, success or failure.
# TYPE coder_ai_gateway_proxy_providers_last_reload_timestamp_seconds gauge
coder_ai_gateway_proxy_providers_last_reload_timestamp_seconds 0
# HELP coder_ai_gateway_proxy_providers_last_reload_success_timestamp_seconds Unix timestamp of the last provider reload that successfully refreshed the router. A gap against the providers_last_reload_timestamp_seconds gauge means the loop is firing but the refresh function is failing.
# TYPE coder_ai_gateway_proxy_providers_last_reload_success_timestamp_seconds gauge
coder_ai_gateway_proxy_providers_last_reload_success_timestamp_seconds 0