Record failed latency improvement and timed replay scope

This commit is contained in:
pewdiepie-archdaemon
2026-09-17 21:22:22 +00:00
parent 6d8c21b334
commit 51feedea6b
+2
View File
@@ -75,6 +75,8 @@ Further provider inspection found that the news-to-general fallback dropped the
### Additional informal/multi-part live checks
`reports/clean-v3-search-quality-2026-09-17T21-20-16-154Z.json`: rejecting fabricated follow-up queries did not yield a latency win; typo-news used eight rounds/57.6 seconds and still lacked source URLs. Natural weekly-news request returned a failure in 27.0 seconds. Do not claim speed improvement. `7a3e1567` exposes measured execution time per tool (separate from total runtime) in live reports, and recognizes explicit imperative source requests such as “link the instructions” that the prior link-noun patterns missed. Related suites: 1,226 passed; timed news/privacy replay running. Additional completion retries are not a substitute for auditing the underlying answer generation.
`reports/clean-v3-search-quality-2026-09-17T21-18-22-350Z.json` remains unsatisfactory: Mozilla lookup 13.9s failed to locate documentation, multi-part privacy request 22.0s omitted requested links and details, Chrome follow-up 28.8s supplied generic homepages instead of comparison. Do not promote based on mechanics.
News trace inspection found another synthetic harness distortion: a missing follow-up query was filled with the original user text plus “corroborating analysis authoritative sources.” This reintroduced misspellings and returned no evidence. `63488776` instead raises an explicit argument error asking for an evidence-based follow-up. This avoids an invented network query but does not yet prove reduced total latency or successful model repair. Related suites: 371 passed; live typo-news and natural-news replay launched.