fix(ci): collect valid Warp tail and error evidence

scripts/run_object_batch_bench_enhanced.sh

@@ -672,7 +672,7 @@ extract_report_line() {
   local regex="$1"
   local file="$2"
   awk -v regex="$regex" '
-    /^Report:/ {
+    /^(Report|Operation):/ {
       in_report = 1
       next
     }
@@ -703,9 +703,9 @@ normalize_duration_metric() {
 extract_metrics() {
   local log_file="$1"
 
-  local average_line reqs_line throughput reqps latency req_p90 req_p99 reqps_num
+  local average_line request_line throughput reqps latency req_p90 req_p99 reqps_num
   average_line="$(extract_report_line '^[[:space:]]*[*][[:space:]]+Average:' "$log_file")"
-  reqs_line="$(extract_report_line '^[[:space:]]*[*][[:space:]]+Reqs:' "$log_file")"
+  request_line="$(extract_report_line '^[[:space:]]*[*][[:space:]]+(Reqs:[[:space:]]+)?Avg:' "$log_file")"
 
   if [[ -n "$average_line" ]]; then
     throughput="$(echo "$average_line" | sed -E 's/^.*Average:[[:space:]]*//; s/,[[:space:]]*.*$//')"
@@ -715,20 +715,16 @@ extract_metrics() {
     reqps="$(extract_first '[0-9]+(\.[0-9]+)?[[:space:]]*(obj/s|req/s|ops/s|requests/s)' "$log_file")"
   fi
 
-  if [[ -n "$reqs_line" ]]; then
+  if [[ -n "$request_line" ]]; then
-    latency="$(echo "$reqs_line" | rg -o 'Avg:[[:space:]]+[0-9]+(\.[0-9]+)?(ms|us|µs|s)' | sed -E 's/^Avg:[[:space:]]+//')"
+    latency="$(echo "$request_line" | rg -o 'Avg:[[:space:]]+[0-9]+(\.[0-9]+)?(ms|us|µs|s)' | sed -E 's/^Avg:[[:space:]]+//')"
-    req_p90="$(echo "$reqs_line" | rg -o '90%:[[:space:]]+[0-9]+(\.[0-9]+)?(ms|us|µs|s)' | sed -E 's/^90%:[[:space:]]+//')"
+    req_p90="$(echo "$request_line" | rg -o '90%:[[:space:]]+[0-9]+(\.[0-9]+)?(ms|us|µs|s)' | sed -E 's/^90%:[[:space:]]+//')"
-    req_p99="$(echo "$reqs_line" | rg -o '99%:[[:space:]]+[0-9]+(\.[0-9]+)?(ms|us|µs|s)' | sed -E 's/^99%:[[:space:]]+//')"
+    req_p99="$(echo "$request_line" | rg -o '99%:[[:space:]]+[0-9]+(\.[0-9]+)?(ms|us|µs|s)' | sed -E 's/^99%:[[:space:]]+//')"
   else
     latency="$(rg -o 'Reqs:[[:space:]]+Avg:[[:space:]]+[0-9]+(\.[0-9]+)?(ms|us|µs|s)' "$log_file" | head -n1 | sed -E 's/^Reqs:[[:space:]]+Avg:[[:space:]]+//')"
     req_p90="$(rg -o '90%:[[:space:]]+[0-9]+(\.[0-9]+)?(ms|us|µs|s)' "$log_file" | head -n1 | sed -E 's/^90%:[[:space:]]+//')"
     req_p99="$(rg -o '99%:[[:space:]]+[0-9]+(\.[0-9]+)?(ms|us|µs|s)' "$log_file" | head -n1 | sed -E 's/^99%:[[:space:]]+//')"
   fi
 
-  if [[ -z "$latency" ]]; then
-    latency="$(extract_first '[0-9]+(\.[0-9]+)?[[:space:]]*(ms|us|µs|s)' "$log_file")"
-  fi
-
   throughput="$(trim "${throughput:-N/A}")"
   reqps="$(trim "${reqps:-N/A}")"
   latency="$(trim "${latency:-N/A}")"
@@ -1128,6 +1124,8 @@ run_one_attempt() {
       "--concurrent" "$CONCURRENCY"
       "--duration" "$DURATION"
       "--region" "$REGION"
+      "--no-color"
+      "--analyze.v"
     )
     if [[ "$INSECURE" == "true" ]]; then
       cmd+=("--insecure")
@@ -1212,6 +1210,12 @@ run_one_attempt() {
     req_p99_ms="$(to_ms "$req_p99_human")"
   fi
 
+  if [[ "$DRY_RUN" != "true" && "$TOOL" == "warp" && "$status" == "ok" ]] \
+    && rg -q '^[[:space:]]*(Total[[:space:]]+)?Errors:[[:space:]]+[1-9][0-9]*[.]?([[:space:]]|$)' "$log_file"; then
+    status="failed"
+    exit_code=1
+  fi
+
   if [[ "$DRY_RUN" != "true" && "$status" == "ok" ]]; then
     if [[ "$throughput_bps" == "N/A" && "$reqps" == "N/A" ]]; then
       status="failed"

scripts/test_object_batch_bench_enhanced.sh

@@ -74,13 +74,19 @@ FAKE_WARP="${TMP_DIR}/fake-warp"
 cat >"$FAKE_WARP" <<'EOF'
 #!/usr/bin/env bash
 set -euo pipefail
+[[ " $* " == *" --analyze.v "* ]]
+[[ " $* " == *" --no-color "* ]]
 cat <<'LOG'
  -       PUT Average: 161 Obj/s, 5.0MiB/s; Current 161 Obj/s, 5.0MiB/s.
-Report: GET. Concurrency: 64. Ran: 7s
+Operation: GET. Concurrency: 64. Ran: 7s
+Requests considered: 1000:
  * Average: 653.90 MiB/s, 20925.58 obj/s
- * Reqs: Avg: 3.5ms, 50%: 2.0ms, 90%: 3.6ms, 99%: 24.1ms, Fastest: 0.2ms, Slowest: 607.7ms, StdDev: 20.6ms
+ * Avg: 3.5ms, 50%: 2.0ms, 90%: 3.6ms, 99%: 24.1ms, Fastest: 0.2ms, Slowest: 607.7ms, StdDev: 20.6ms
 Throughput, split into 7 x 1s:
 LOG
+if [[ "${FAKE_WARP_ERRORS:-0}" == "1" ]]; then
+  echo 'Total Errors: 1.'
+fi
 EOF
 chmod +x "$FAKE_WARP"
 
@@ -103,6 +109,32 @@ chmod +x "$FAKE_WARP"
 
 rg -q '^32767B,warp,1,1,128,ok,0,[^,]+,[^,]+,653.90 MiB/s,685663846.400000,20925.58,3.5 ms,3.500000,[^,]+,3.6 ms,3.600000,24.1 ms,24.100000$' "${TMP_DIR}/fake-warp-run/round_results.csv"
 
+cat >"${TMP_DIR}/warp-no-details.log" <<'EOF'
+warp: Starting benchmark in 3s...
+Operation: PUT. Concurrency: 8
+ * Average: 2.76 MiB/s, 707.03 obj/s
+EOF
+"$RUNNER" --extract-metrics-from-log "${TMP_DIR}/warp-no-details.log" >"${TMP_DIR}/warp-no-details.csv"
+rg -qx '2.76 MiB/s,2894069.760000,707.03,N/A,N/A,N/A,N/A,N/A,N/A' "${TMP_DIR}/warp-no-details.csv"
+
+if FAKE_WARP_ERRORS=1 "$RUNNER" \
+  --tool warp \
+  --endpoint http://127.0.0.1:9000 \
+  --access-key test-access \
+  --secret-key test-secret \
+  --sizes 32767B \
+  --rounds 1 \
+  --retry-per-round 1 \
+  --retry-sleep-secs 1 \
+  --cooldown-secs 0 \
+  --duration 1s \
+  --out-dir "${TMP_DIR}/fake-warp-errors" \
+  --warp-bin "$FAKE_WARP" >/dev/null 2>&1; then
+  echo "expected Warp request errors to fail the benchmark" >&2
+  exit 1
+fi
+rg -q ',failed,1,' "${TMP_DIR}/fake-warp-errors/round_results.csv"
+
 "$RUNNER" \
   --tool warp \
   --endpoint http://127.0.0.1:9000 \