alvis/adolf
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Compare commits

base: alvis:fix/tier-logging
Branches Tags
alvis:main alvis:fix/benchmark-log-extraction alvis:fix/tier-logging
..
compare: alvis:186e16284b510126e8c190945e58715452cde6ca
Branches Tags
alvis:main alvis:fix/benchmark-log-extraction alvis:fix/tier-logging

3 Commits
fix/tier-l ... 186e16284b

Author SHA1 Message Date
alvis
186e16284b Merge pull request 'Fix tier logging: capture actual_tier, fix parse_run_block regex, remove reply_text truncation' (#11) from fix/tier-logging into main 
Reviewed-on: #11
 2026-03-24 02:44:35 +00:00
alvis
0b428e4ada 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
 2026-03-24 02:43:26 +00:00
alvis
98095679be Fix benchmark log extraction: first tier match, increase log tail to 300 
- Remove reversed() from extract_tier_from_logs: first match = routing decision
  (dry-run complex logs tier=complex early, then overwrites with tier=medium at done)
- Increase log tail from 80→300 to handle concurrent log activity

Fixes #7, #10

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-03-24 02:42:27 +00:00
1 changed files with 3 additions and 3 deletions
Expand all files Collapse all files

6
benchmarks/run_benchmark.py
View File

@@ -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.""" """Find new tier= lines that appeared after we sent the query."""
before_lines = set(logs_before.splitlines()) before_lines = set(logs_before.splitlines())
new_lines = [l for l in logs_after.splitlines() if l not in before_lines] 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) m = re.search(r"tier=(\w+(?:\s*\(dry-run\))?)", line)
if m: if m:
tier_raw = m.group(1) 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) print(f"{qid:>3} {expected:8} ", end="", flush=True)
logs_before = get_log_tail(80) logs_before = get_log_tail(300)
t0 = time.monotonic() t0 = time.monotonic()
ok_post = await post_message(client, qid, query_text, dry_run=send_dry) 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 # Now the query is done — check logs for tier
await asyncio.sleep(0.3) 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) actual = extract_tier_from_logs(logs_before, logs_after)
elapsed = time.monotonic() - t0 elapsed = time.monotonic() - t0