CI (node 24/26) failed on the exact-boundary construction: advanceTimersByTime(100)
then an immediate upstream.abort() let the manual abort win the race on some
runtimes, so timeoutOf returned undefined. Advance unambiguously past the deadline
and assert the timeout classification before firing the late abort — that late
abort is now asserted as a no-op, which is the real first-cause-wins invariant.
Round 2 P2: timeoutOf() accepted ANY TimeoutReason, so under nesting — when
the upstream handed to deadline() is itself a deadline (the RFC's named
tools/execute middleware follow-up) and its outer timer fires first —
AbortSignal.any preserves the outer reason and the inner bash/web would report
the outer timeout as their own (timedOut / WEB_FETCH_TIMEOUT) though their local
timer never expired. Add an optional code to timeoutOf; bash and web pass their
own code, so a foreign timeout falls through to the upstream-cancel path.
Timeout timing/classification was re-implemented three ways across the
tool-bearing capabilities, with the fusion of timeout+cancel and the
timeout-vs-cancel reason recovery being the error-prone parts. Extract that
shared half into a zero-dependency @deepseek-ai/dsh-timeout library
(clampTimeout/deadline/timeoutOf/TimeoutReason) and leave the non-shareable
hard-kill in each capability, per the timeout-library RFC.
bash: run() owns the deadline; runBash drops its killTimer and no longer
classifies (SpawnSpec/SpawnOutcome lose timeoutMs/timedOut/aborted), so the
public timedOut/aborted booleans become mutually-exclusive first-abort
classifications. web_fetch: the hand-rolled controller/timer/listener/
signal.reason dance is replaced by provider-owned deadline/timeoutOf, keeping
the WEB_FETCH_TIMEOUT / WEB_ABORTED contract. fs stays timeout-free (README
states why).
Dudu-0223