opensource/coder
3
0
Fork 0
mirror of https://github.com/coder/coder.git synced 2026-09-24 15:04:27 +08:00
Code Issues Packages Projects Releases Wiki Activity

feat: add ai provider status and reload freshness metrics (#25770)

Browse Source 
Add metrics for `aibridged` and `aibridgeproxyd`'s provider statuses. AI providers can be modified, and possibly misconfigured, at runtime. These metrics help operators understand the state of these provider definitions in case unexpected behaviour is observed.
This commit is contained in:
Danny Kopping
2026-05-28 14:57:33 +02:00
committed by GitHub
parent 637855e276
commit 12520ee964
18 changed files with 704 additions and 125 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/admin/integrations/prometheus.md
+6
View File
@@ -120,11 +120,17 @@ deployment. They will always be available from the agent.
| `coder_aibridged_non_injected_tool_selections_total` | counter | The number of times an AI model selected a tool to be invoked by the client. | `model` `name` `provider` |
| `coder_aibridged_passthrough_total` | counter | The count of requests which were not intercepted but passed through to the upstream. | `method` `provider` `route` |
| `coder_aibridged_prompts_total` | counter | The number of prompts issued by users (initiators). | `initiator_id` `model` `provider` |
| `coder_aibridged_provider_info` | gauge | One series per configured AI provider. Value is always 1; the status label (enabled, disabled, error) carries the alertable signal. | `provider_name` `provider_type` `status` |
| `coder_aibridged_providers_last_reload_success_timestamp_seconds` | gauge | Unix timestamp of the last provider reload that successfully refreshed the pool. A gap against coder_aibridged_providers_last_reload_timestamp_seconds means the loop is firing but the refresh function is failing. | |
| `coder_aibridged_providers_last_reload_timestamp_seconds` | gauge | Unix timestamp of the last provider reload attempt, success or failure. | |
| `coder_aibridged_tokens_total` | counter | The number of tokens used by intercepted requests. | `initiator_id` `model` `provider` `type` |
| `coder_aibridgeproxyd_connect_sessions_total` | counter | Total number of CONNECT sessions established. | `type` |
| `coder_aibridgeproxyd_inflight_mitm_requests` | gauge | Number of MITM requests currently being processed. | `provider` |
| `coder_aibridgeproxyd_mitm_requests_total` | counter | Total number of MITM requests handled by the proxy. | `provider` |
| `coder_aibridgeproxyd_mitm_responses_total` | counter | Total number of MITM responses by HTTP status code class. | `code` `provider` |
| `coder_aibridgeproxyd_provider_info` | gauge | One series per configured AI provider. Value is always 1; the status label (enabled, disabled, error) carries the alertable signal. | `provider_name` `provider_type` `status` |
| `coder_aibridgeproxyd_providers_last_reload_success_timestamp_seconds` | gauge | Unix timestamp of the last provider reload that successfully refreshed the router. A gap against coder_aibridgeproxyd_providers_last_reload_timestamp_seconds means the loop is firing but the refresh function is failing. | |
| `coder_aibridgeproxyd_providers_last_reload_timestamp_seconds` | gauge | Unix timestamp of the last provider reload attempt, success or failure. | |
| `coder_derp_server_accepts_total` | counter | Total DERP connections accepted. | |
| `coder_derp_server_average_queue_duration_ms` | gauge | Average queue duration in milliseconds. | |
| `coder_derp_server_bytes_received_total` | counter | Total bytes received. | |