feat(routing): move sticky-key retries into routing policy with lazy attempts

Replace the provider/endpoint max_retries fields as the source of same-key
retries with a routing policy setting, sticky_key_attempts (default 2). Only
the first-ranked candidate is retried on the same key; every failover
candidate gets a single attempt so failover keeps advancing instead of
retrying each fallback key.

Materialize exactly one attempt per candidate and derive same-key retries in
the attempt loop after a candidate-scoped failure, so the retry budget no
longer inflates up-front materialization and needs no upper bound. The budget
travels in the report context; retries reuse the plan with a fresh candidate
id and incremented retry index. Pool groups only retry their first key within
the retry-index stride.

Expose the setting in the routing profile editor and the set_scheduling rule
action, and drop the max_retries input from the provider form.

apps/aether-gateway/src/ai_serving/planner/report_context.rs

@@ -4,7 +4,7 @@ use aether_ai_serving::{
     build_ai_execution_report_context,
     insert_provider_stream_event_api_format as insert_ai_provider_stream_event_api_format,
     provider_stream_event_api_format_for_provider_type as ai_provider_stream_event_api_format_for_provider_type,
-    AiExecutionReportContextParts, AiRequestOrigin,
+    AiExecutionReportContextParts, AiRequestOrigin, STICKY_KEY_ATTEMPTS_REPORT_FIELD,
 };
 use aether_routing_core::ResolvedRoutingPolicy;
 use aether_runtime_state::RuntimeLockLease;
@@ -59,6 +59,9 @@ pub(crate) struct LocalExecutionReportContextParts<'a> {
     pub(crate) client_session_affinity: Option<&'a ClientSessionAffinity>,
     pub(crate) routing_policy: Option<&'a ResolvedRoutingPolicy>,
     pub(crate) scheduler_affinity_epoch: Option<u64>,
+    /// Routing policy sticky-key attempt budget; read back by the attempt
+    /// loop to derive same-key retries lazily.
+    pub(crate) sticky_key_attempts: Option<u32>,
     pub(crate) client_requested_stream: bool,
     pub(crate) upstream_is_stream: bool,
     pub(crate) has_envelope: bool,
@@ -124,6 +127,12 @@ pub(crate) fn build_local_execution_report_context(
             Value::Number(epoch.into()),
         );
     }
+    if let Some(sticky_key_attempts) = parts.sticky_key_attempts {
+        extra_fields.insert(
+            STICKY_KEY_ATTEMPTS_REPORT_FIELD.to_string(),
+            Value::Number(sticky_key_attempts.into()),
+        );
+    }
     insert_request_path_fields(
         &mut extra_fields,
         parts.request_path,
@@ -330,6 +339,7 @@ mod tests {
                 client_session_affinity: Some(&client_session_affinity),
                 routing_policy: None,
                 scheduler_affinity_epoch: None,
+                sticky_key_attempts: None,
                 client_requested_stream: false,
                 upstream_is_stream: false,
                 has_envelope: false,
@@ -413,6 +423,7 @@ mod tests {
                 client_session_affinity: None,
                 routing_policy: None,
                 scheduler_affinity_epoch: None,
+                sticky_key_attempts: None,
                 client_requested_stream: false,
                 upstream_is_stream: true,
                 has_envelope: false,
@@ -480,6 +491,7 @@ mod tests {
                 client_session_affinity: None,
                 routing_policy: None,
                 scheduler_affinity_epoch: None,
+                sticky_key_attempts: None,
                 client_requested_stream: false,
                 upstream_is_stream: false,
                 has_envelope: false,