mirror of
https://github.com/coder/coder.git
synced 2026-09-24 15:04:27 +08:00
feat: add key pool failover metrics to aibridge (#25901)
## Description This PR adds Prometheus metrics for aibridge's API-key failover, giving visibility into key pool health and failover behavior per provider. The following metrics are introduced: - **`key_pool_state`** (gauge): number of keys currently in each state (`valid`, `temporary`, `permanent`) per provider, sampled at scrape time. - **`key_pool_state_transitions_total`** (counter): key state transitions during failover, labeled by `reason` (`rate_limited`, `unauthorized`, `forbidden`). - **`key_pool_exhaustions_total`** (counter): times a pool ran out of usable keys, labeled by `outcome` (`rate_limited`, `auth_failed`). - **`key_pool_failover_attempts`** (histogram): keys attempted before success or exhaustion (per interception for bridged requests, per request for passthrough). ## Changes - Moves `MarkKeyOnStatus` and key-pool error handling onto `*keypool.Pool`. - Attaches metrics to each provider's key pool at install time, on construction and on provider reload. - Adds a scrape-time state collector and a `KeyPools()` accessor on the bridge pool to feed it. - Tracks per-request key attempts in the bridged and passthrough failover paths. - Adds test coverage for the new metrics across the keypool unit tests, the bridged intercept failover tests, and the passthrough failover test. Closes https://github.com/coder/internal/issues/1447 Closes https://linear.app/codercom/issue/AIGOV-198/aibridge-key-failover-observability > [!NOTE] > Initially generated by Claude Opus 4.7, modified and reviewed by @ssncferreira
This commit is contained in:
@@ -64,7 +64,7 @@ func startTestAIBridgeDaemon(t *testing.T, api *coderd.API) *aibridged.Metrics {
|
||||
cfg := api.DeploymentValues.AI.BridgeConfig
|
||||
tracer := otel.Tracer("aibridge-reload-test")
|
||||
|
||||
providers, _, err := cli.BuildProviders(ctx, api.Database, cfg, logger)
|
||||
providers, _, err := cli.BuildProviders(ctx, api.Database, cfg, logger, nil)
|
||||
require.NoError(t, err)
|
||||
|
||||
pool, err := aibridged.NewCachedBridgePool(aibridged.DefaultPoolOptions, providers, logger.Named("pool"), nil, tracer)
|
||||
@@ -97,7 +97,7 @@ type testPoolReloader struct {
|
||||
|
||||
func (r *testPoolReloader) Reload(ctx context.Context) error {
|
||||
defer r.metrics.RecordReloadAttempt()
|
||||
providers, outcomes, err := cli.BuildProviders(ctx, r.db, r.cfg, r.logger)
|
||||
providers, outcomes, err := cli.BuildProviders(ctx, r.db, r.cfg, r.logger, nil)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user