Merge pull request 'Fix benchmark log extraction: first tier match, increase log tail to 300' (#12) from fix/benchmark-log-extraction into main

Reviewed-on: #12

benchmarks/run_benchmark.py

@@ -120,7 +120,7 @@ def extract_tier_from_logs(logs_before: str, logs_after: str) -> str | None:
     """Find new tier= lines that appeared after we sent the query."""
     before_lines = set(logs_before.splitlines())
     new_lines = [l for l in logs_after.splitlines() if l not in before_lines]
-    for line in reversed(new_lines):
+    for line in new_lines:
         m = re.search(r"tier=(\w+(?:\s*\(dry-run\))?)", line)
         if m:
             tier_raw = m.group(1)
@@ -203,7 +203,7 @@ async def run(queries: list[dict], dry_run: bool = False) -> list[dict]:
 
             print(f"{qid:>3}  {expected:8}  ", end="", flush=True)
 
-            logs_before = get_log_tail(80)
+            logs_before = get_log_tail(300)
             t0 = time.monotonic()
 
             ok_post = await post_message(client, qid, query_text, dry_run=send_dry)
@@ -225,7 +225,7 @@ async def run(queries: list[dict], dry_run: bool = False) -> list[dict]:
 
             # Now the query is done — check logs for tier
             await asyncio.sleep(0.3)
-            logs_after = get_log_tail(80)
+            logs_after = get_log_tail(300)
             actual = extract_tier_from_logs(logs_before, logs_after)
 
             elapsed = time.monotonic() - t0