Why: Q3 WP5 requires a same-batch dual-run harness (direct vs squad
compiled graph) that records differences without demanding byte-identical
output, feeding DecideSwitch evidence for the runtime.entry default-switch
decision.
Evidence: eval/ab_test.go mechanics (theme-based scoring, status/theme/
latency diff notes, P50, DecideSwitch wiring, RunFunc error tolerance,
empty batch); wfcompile TestABDemoBriefDualRun runs the demo.brief scenario
on both entries (direct = scripted single-agent answer; squad = real
RunCompiled with stub backend and judge) and logs the report: both sides
100/100, summary-form difference recorded, decision '切换条件已满足…合入前
需要产品确认'. Full backend suite green (SELF); CI authoritative (GATE).
Impact: new eval/ab.go harness (pure mechanics, no runtime dependency);
no product default is flipped - runtime.entry stays direct until product
confirmation per the DecideSwitch report semantics (evidence recorded in
the task card and PR).
Refs: Q3 plan WP5 (2026-10-07-agent-stack-q2q3-plans.md); task card
.task/feature-agent-stack-q3.md
weichen
merged commit 4791b2e760 into main2026-10-08 03:49:31 +00:00
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
Why
Q3 WP5:任务级 direct vs squad(编译图) 双跑 harness(扩 eval/switch.go),同批任务记录差异(不要求字节级相同),为 runtime.entry 默认切换产出 DecideSwitch 证据。
What
切换裁决(证据入卡,不翻默认)
harness 报告:「切换条件已满足:squad 100 不低于 direct 100,额外首字延迟 0s。可以把 runtime.entry 的默认值改为 squad,并保留 direct 作为回退。合入前需要产品确认。」——按 DecideSwitch 报告语义与双钥匙原则,本 PR 不改 settings 默认(runtime.entry 保持 direct),证据随任务卡与 PR 记录,待产品确认后另行切换。
Evidence
Refs