fix: reduce cost of prebuild failure (#17697)

Relates to https://github.com/coder/coder/issues/17432

### Part 1:

Notes:
- `GetPresetsAtFailureLimit` SQL query is added, which is similar to
`GetPresetsBackoff`, they use same CTEs: `filtered_builds`,
`time_sorted_builds`, but they are still different.

- Query is executed on every loop iteration. We can consider marking
specific preset as permanently failed as an optimization to avoid
executing query on every loop iteration. But I decided don't do it for
now.

- By default `FailureHardLimit` is set to 3.

- `FailureHardLimit` is configurable. Setting it to zero - means that
hard limit is disabled.

### Part 2

Notes:
- `PrebuildFailureLimitReached` notification is added.
- Notification is sent to template admins.
- Notification is sent only the first time, when hard limit is reached.
But it will `log.Warn` on every loop iteration.
- I introduced this enum:
```sql
CREATE TYPE prebuild_status AS ENUM (
  'normal',           -- Prebuilds are working as expected; this is the default, healthy state.
  'hard_limited',     -- Prebuilds have failed repeatedly and hit the configured hard failure limit; won't be retried anymore.
  'validation_failed' -- Prebuilds failed due to a non-retryable validation error (e.g. template misconfiguration); won't be retried.
);
```
`validation_failed` not used in this PR, but I think it will be used in
next one, so I wanted to save us an extra migration.

- Notification looks like this:
<img width="472" alt="image"
src="https://github.com/user-attachments/assets/e10efea0-1790-4e7f-a65c-f94c40fced27"
/>

### Latest notification views:
<img width="463" alt="image"
src="https://github.com/user-attachments/assets/11310c58-68d1-4075-a497-f76d854633fe"
/>
<img width="725" alt="image"
src="https://github.com/user-attachments/assets/6bbfe21a-91ac-47c3-a9d1-21807bb0c53a"
/>

coderd/database/dbmetrics/querymetrics.go

@@ -1138,6 +1138,13 @@ func (m queryMetricsStore) GetPresetParametersByTemplateVersionID(ctx context.Co
 	return r0, r1
 }
 
+func (m queryMetricsStore) GetPresetsAtFailureLimit(ctx context.Context, hardLimit int64) ([]database.GetPresetsAtFailureLimitRow, error) {
+	start := time.Now()
+	r0, r1 := m.s.GetPresetsAtFailureLimit(ctx, hardLimit)
+	m.queryLatencies.WithLabelValues("GetPresetsAtFailureLimit").Observe(time.Since(start).Seconds())
+	return r0, r1
+}
+
 func (m queryMetricsStore) GetPresetsBackoff(ctx context.Context, lookback time.Time) ([]database.GetPresetsBackoffRow, error) {
 	start := time.Now()
 	r0, r1 := m.s.GetPresetsBackoff(ctx, lookback)
@@ -2692,6 +2699,13 @@ func (m queryMetricsStore) UpdateOrganizationDeletedByID(ctx context.Context, ar
 	return r0
 }
 
+func (m queryMetricsStore) UpdatePresetPrebuildStatus(ctx context.Context, arg database.UpdatePresetPrebuildStatusParams) error {
+	start := time.Now()
+	r0 := m.s.UpdatePresetPrebuildStatus(ctx, arg)
+	m.queryLatencies.WithLabelValues("UpdatePresetPrebuildStatus").Observe(time.Since(start).Seconds())
+	return r0
+}
+
 func (m queryMetricsStore) UpdateProvisionerDaemonLastSeenAt(ctx context.Context, arg database.UpdateProvisionerDaemonLastSeenAtParams) error {
 	start := time.Now()
 	r0 := m.s.UpdateProvisionerDaemonLastSeenAt(ctx, arg)