crates/gateway/src/v1/mod.rs

@@ -579,22 +579,12 @@ async fn usage(State(state): State<V1State>) -> impl IntoResponse {
 /// gates. A monitoring tool should evaluate the booleans + counts
 /// against its own thresholds.
 async fn health(State(state): State<V1State>) -> impl IntoResponse {
-    let workers_loaded = {
-        // Use a lookup with an obviously-fake id to probe — None
-        // could mean empty roster OR healthy roster without that id.
-        // We don't have a count() method on the trait; use a sample
-        // probe + treat presence of workers as a yes/no signal.
-        let probe = state.validate_workers.find("__healthcheck_probe__");
-        // probe is always None for the synthetic id, so this isn't
-        // useful. Better: rely on the fact that an empty-fallback
-        // InMemoryWorkerLookup ALSO returns None — there's no way
-        // to distinguish "loaded, just doesn't have this id" from
-        // "empty fallback". We'd need a count() method on WorkerLookup
-        // to report honestly. For now report the load attempt was
-        // performed (boot logs are the source of truth on rows count).
-        let _ = probe;
-        true
-    };
+    // Honest worker count via WorkerLookup::len. Production switchover
+    // verification: after swapping workers_500k.parquet → real Chicago
+    // data and restarting, this number should match the row count of
+    // the new file. 0 means the file was missing / unreadable / had a
+    // schema mismatch and the gateway booted with the empty fallback.
+    let workers_count = state.validate_workers.len();
     let providers_configured = serde_json::json!({
         "ollama_cloud": state.ollama_cloud_key.is_some(),
         "openrouter": state.openrouter_key.is_some(),
@@ -607,7 +597,8 @@ async fn health(State(state): State<V1State>) -> impl IntoResponse {
     let usage_snapshot = state.usage.read().await.clone();
     Json(serde_json::json!({
         "status": "ok",
-        "workers_loaded": workers_loaded,
+        "workers_count": workers_count,
+        "workers_loaded": workers_count > 0,
         "providers_configured": providers_configured,
         "langfuse_configured": langfuse_configured,
         "usage_total_requests": usage_snapshot.requests,

crates/validator/src/lib.rs

@@ -130,6 +130,16 @@ pub struct WorkerRecord {
 /// hold an in-memory snapshot, not perform per-call I/O.
 pub trait WorkerLookup: Send + Sync {
     fn find(&self, candidate_id: &str) -> Option<WorkerRecord>;
+    /// Number of workers in the snapshot. Default 0 for impls that
+    /// genuinely don't know (e.g. a future SQL-backed lookup that
+    /// counts on demand). InMemoryWorkerLookup overrides with the
+    /// HashMap size; ParquetWorkerLookup constructs an
+    /// InMemoryWorkerLookup so it inherits the override. Used by
+    /// /v1/health to report data-load status during production
+    /// switchover (the Chicago dataset replaces synthetic test data;
+    /// the health endpoint is how operators verify the new file
+    /// loaded correctly without restart-and-pray).
+    fn len(&self) -> usize { 0 }
 }
 
 /// HashMap-backed lookup. Used by validator unit tests + as a
@@ -165,4 +175,7 @@ impl WorkerLookup for InMemoryWorkerLookup {
     fn find(&self, candidate_id: &str) -> Option<WorkerRecord> {
         self.rows.get(candidate_id).cloned()
     }
+    fn len(&self) -> usize {
+        self.rows.len()
+    }
 }