Repository navigation
Conversation
…allowing them The executor discarded every candidate rejection, so a context-budget guard or a post-fetch parse failure left only a bare tN:error with no warn line, and the compress failure text blamed maxSummaryLength for every failure. Capture the safe cause for our own fixed error strings (unknown provider errors stay opaque), log it once, and branch the failure advice by the batch's own stop reason: budget on deadline, maxSummaryLength only for over-cap replies. Fixes ranxianglei#6885
[bot] 🏷 (ai: vllm-qwen/qwen3.8-27b) Duplicate screening: not a duplicate. #6890 is the only open PR fixing #6885. Searched open PRs + issues: no other PR targets the same issue. The related external-summary PRs (#5564 / #3659 / #3660 / #3735 / #5105 / #5545) are different issues (different symptom/mechanism) — #3659/#4833 added the outcome classification (timeout/error/invalid_summary); #6890 adds the named cause ( Base: I read the full diff against the surrounding code (
代码审查八问
Key caveat for the ownerThis PR does NOT fix #6885 problem 1 (the actual 100% failure). Problem 1 is the default 25s/50s budget + serial attempts: t0 eats 25s → t1 is killed by the 50s batch deadline → t2 never even sends a request, so the chain fails 100% on 30–365KB payloads. The PR only makes the failure diagnosable (you can now see it's a budget problem); it does not change the default budget behavior. Changing defaults is a product decision the author explicitly deferred. So after merging, long-payload compress still fails 100% — only the cause is now readable. Root-fixing problem 1 (budget defaults / Minor nits (non-blocking)
CI statusStatic gates all green (static-gates/ubuntu, mysql-contract, config-surface-guard, lifecycle-ledger-guard, lock-sync, plan, docs-coverage); test shards still running (ubuntu/windows × node 22/24). Final mergeable verdict pending the test shards. VerdictCode review is clean; direction is correct. This is a solid "stabilize" PR: it fixes #6885 problem 2 (silent failures) and problem 3 (misdirected advice), making the failure diagnosable; problems 1 (100% failure) and 4 (docs) are deliberately deferred. Merge once CI is green — but the owner should note: after merge, long-payload compress still fails 100% (problem 1 unfixed); the budget-default decision is separate. |
[bot] 🏷 CI progress update: the first two ubuntu test shards are green — |
What broke
compresswith external summaries failed every range on long payloads, and the failure gave nothing to work with: every candidate showed up as a baretN:errorwith no warn line, and the result always blamedcompress.maxSummaryLength, a knob that cannot help a budget or parse failure.What changed
t0:error (External summary input exceeds the target context budget)) and logs it once. Only our own fixed error strings are named; unknown provider errors stay opaque, so no provider text leaks into results.maxSummaryLengthonly for over-cap replies, and the named cause otherwise.Not changed on purpose: the 25s/50s default budgets. Those are the other half of #6885's problem 1, but changing defaults is a product decision for the owner, so this PR only makes the failure diagnosable instead of misattributed.
How verified
errorattempts (HTTP 503/400 rejection, incomplete responses).Fixes #6885