Review follow-up on the watchdog rewrite:
- Register the deadline reaction inside `next()` and detach it when the
demand settles. Racing against one watchdog-lifetime promise kept every
settled race reachable through that promise's reactions, retaining each
resolved `StreamChunk` for the length of the stream: a 10,000-value probe
kept 100/100 sampled values before this change and 0/100 after.
- Take the neighboring stall case's 1,000ms idle budget in the new
transport-recovery case: the retry performs a real local HTTP/SSE round
trip, and a 50ms budget would let coverage-lane scheduling decide it.
- Document the contract where it is described: `packages/util/timeout/README`
(both languages) and the bounded-recovery and timeout-library notes no
longer claim that only the transport observes the watchdog signal.
An aborted read can stay pending forever: undici drops the error when the
abort lands on an in-flight response-body read (observed on the coverage
lane's Node v24.13.0), and the stalled body of
`llm-retry/tests/transport-recovery.spec.ts` then never settles. The idle
watchdog delegated termination to the iterator observing its signal, so the
request outlived its own deadline and the agent stayed `running` until
Vitest's 90s budget; awaiting the abandoned request generator's `return()`
queued behind that demand and would have re-hung the settled outcome.
`idleWatchdog.next` now races its demand against its own deadline and
rejects with the watchdog's TimeoutReason, so the deadline — not the
transport — decides when an outstanding demand ends. Both adapters that
consume the watchdog stop awaiting the abandoned generator's drain; the
abort they already issue owns socket and SDK teardown.
Evidence: instrumented stress harness at ~1s idle on Node v24.13.0 hung 4/160
iterations before this change (each with the abort delivered at ~1002ms and
the underlying read never settling) and 0/160 after; Node v24.19.0 never
hung. The new case in transport-recovery.spec.ts pins the behavior
deterministically: it fails (times out) with the watchdog change alone and
with no product change at all.
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).
Tianyi Cui