The promptWithModelSuggestionRetry async variant did not release the
post-dispatch reservation when the wrapped promptAsync threw. Callers
that immediately retry (such as sendSyncPrompt error toast paths) hit
the gate as reserved and surfaced 'promptAsync skipped by gate: reserved'
instead of the underlying error.
Mirrors the existing sync variant fix from ff1b15d53.
Closes regression introduced by BLOCKER-2 hardening
After BLOCKER-2's post-dispatch hold landed (the gate now keeps the
reservation through the hold window regardless of whether the dispatch
threw), the synchronous retry path inside promptSyncWithModelSuggestionRetry
hit 'reserved' on its own second attempt because the first attempt's
post-dispatch hold was still active.
The first attempt's failure is ProviderModelNotFoundError, which is a
synchronous SDK rejection - the prompt never reached the server, so
there is no durable session state worth protecting from a duplicate
injection. Release the post-dispatch reservation hold explicitly before
the suggested-model retry so the second attempt can dispatch immediately.
Fixes test regression introduced by the gate hardening (BLOCKER-2 fix).
Keep prompt reservations briefly after successful dispatch so rapid idle/message/error transitions cannot inject the same follow-up twice.
Route all production session prompt calls through the shared gate, restore skipped background resume state, release holds after abort/recovery paths, and preserve Ralph/ULW loop state when a dispatch is deferred.
Add regression coverage for session routing, static prompt route auditing, team-mode live messaging, model suggestion retries, call-omo-agent reuse, background parent wakes, runtime fallback, compaction recovery, Atlas, and Ralph/ULW loops.
PR #1620 migrated all prompt calls from session.prompt (blocking) to
session.promptAsync (fire-and-forget HTTP 204). This broke look_at which
needs the multimodal-looker response to be available immediately after
the prompt call returns.
Fix: add promptSyncWithModelSuggestionRetry() that uses session.prompt
(blocking) with model suggestion retry support. look_at now uses this
sync variant while all other callers keep using promptAsync.
- Add promptSyncWithModelSuggestionRetry to model-suggestion-retry.ts
- Switch look_at from promptWithModelSuggestionRetry to sync variant
- Add comprehensive tests for the new sync function
- No changes to other callers (delegate-task, background-agent)
YeonGyu-Kim