fix(benchmark): preserve terminal failure pressure

crates/switchyard-soak/examples/mock_server.rs

@@ -72,6 +72,10 @@ fn classifier_content(marker: Option<&str>) -> &'static str {
     r#"{"crux":"bounded task","primary_rule":"SUP-1","capability_boundary":"supported","p_solve":1.0}"#
 }
 
+fn should_inject_failure(name: &str, attempt: u64) -> bool {
+    name == "upstream_500" || attempt <= 2
+}
+
 fn completion(model: &str, content: &str) -> Value {
     json!({
         "id": "chatcmpl-switchyard-soak",
@@ -192,9 +196,11 @@ async fn chat(State(state): State<BackendState>, Json(body): Json<Value>) -> Res
                 *attempt += 1;
                 *attempt
             };
-            if attempt <= 2 {
+            if should_inject_failure(name, attempt) {
+                // Keep retry-exhaustion scenarios fast enough for local benchmarks.
                 return (
                     status,
+                    [("retry-after", "0")],
                     Json(
                         json!({"error": {"message": format!("injected {name} attempt {attempt}")}}),
                     ),
@@ -255,7 +261,7 @@ async fn run(args: Args) -> Result<(), String> {
 mod tests {
     use serde_json::json;
 
-    use super::requested_output_tokens;
+    use super::{requested_output_tokens, should_inject_failure};
 
     #[test]
     fn output_tokens_follow_openai_limits_and_stay_bounded() {
@@ -266,6 +272,13 @@ mod tests {
         );
         assert_eq!(requested_output_tokens(&json!({})), 2);
     }
+
+    #[test]
+    fn failure_pressure_recovers_429_but_not_500() {
+        assert!(should_inject_failure("upstream_429", 2));
+        assert!(!should_inject_failure("upstream_429", 3));
+        assert!(should_inject_failure("upstream_500", 11));
+    }
 }
 
 #[tokio::main]

crates/switchyard-soak/src/scenarios/failure_pressure.rs

@@ -28,7 +28,7 @@ pub fn build(options: ScenarioOptions<'_>) -> Scenario {
     Scenario::chat(
         "failure-pressure",
         ScenarioGroup::Resilience,
-        "Bounded 429, 500, malformed-classifier, and truncated-stream injections.",
+        "Transient 429, persistent 500, malformed-classifier, and truncated-stream injections.",
         "Retries recover transient failures; terminal failures remain explicit and bounded.",
         ErrorExpectation::MIXED,
         sessions,

docs/operations/soak_test.md

@@ -34,7 +34,7 @@ The scenario catalog covers these distinct pressure angles:
 | `stage-transitions` | One growing history across exploration, critical failure, and productive work | Stage-router tier changes and scorer output |
 | `classifier-mix` | Deterministic 80/20 then 50/50 easy/hard requests | Target share, classifier calls/errors, and classifier latency |
 | `context-overflow` | One target rejects a near-window request | Fallback to another eligible target |
-| `failure-pressure` | Bounded 429, 500, malformed verdict, and truncated stream | Retry recovery, explicit terminal errors, and connection health |
+| `failure-pressure` | Transient 429, persistent 500, malformed verdict, and truncated stream | Retry recovery, explicit terminal errors, and connection health |
 | `client-cancellation` | A client timeout during a delayed response | Teardown and recovery of later traffic |
 
 `standard` includes the core and agentic rows. Run `resilience` separately because expected
@@ -239,7 +239,7 @@ python3.12 scripts/benchmark_routing_algorithms.py \
   --profile-runs 1
 ```
 
-`context-overflow` checks target fallback, `failure-pressure` injects bounded 429, 500, malformed
+`context-overflow` checks target fallback, `failure-pressure` injects transient 429, persistent 500, malformed
 classifier, and truncated-stream cases, and `client-cancellation` uses a one-second client timeout
 against a delayed response. Their expected error-rate ranges appear in the report's Resilience
 section, and the command fails after writing the report when any row misses its range. The local