Beverly621 0464502af1
fix(frontend): keep human input cards with their turn (#4892)
* fix(frontend): keep human input cards with their turn

* fix(frontend): keep human input cards with the correct turn

Multi-turn ordering in restoreLocalTurnMessageOrder could place an
`ask_clarification` (needYourHelp) card on the wrong side of a newly
submitted human message, and after an interrupt/stop it could move the
current run's own already-executed steps above the human that started them.

- Restore established messages that a live checkpoint tail wove after the
  new human (displacedBaselineMessages).
- Treat cards/messages confirmed only by the REST history page as
  established-past-turn too (confirmedHistoryIdentities), not as in-flight
  pending steps (displacedHistoryMessages).
- Never displace the CURRENT run's own steps after an interrupt/stop; they
  belong after the human even once canonical history confirms them
  (currentTurnRunIds, anchored by the pending human's run_id).

Fixes #4889

* fix(frontend): preserve ordering across displaced messages

* fix(frontend): close canonical history ordering gaps

* fix(frontend): preserve current turn anchor after compaction

* fix(frontend): anchor the local turn on the submitted human identity

Follow-up to #4892. R2 is reachable through the full hook chain: when the
checkpoint baseline covers only the latest turn, the server echo of the
submitted human confirms the optimistic copy against the unthrottled SDK
state while the ~80ms render snapshot cannot show it yet; the baseline-only
anchor scan then promoted an older history-only human into the current
turn's anchor and moved established history behind it.

- Record a LocalTurnAnchor at dispatch: one client-generated human id is
  shared by the optimistic display copy and the submitted message, so the
  server X__user echo confirms the exact identity already on screen.
- restoreLocalTurnMessageOrder repairs only when that identity is present
  in the display; a null anchor (hidden human-input reply, regenerate
  replay) or a not-yet-rendered identity keeps established history
  untouched.
- Optimistic confirmation now observes the same coalesced render snapshot
  (identity match first, rendered human-count growth as fallback for
  runtime-re-keyed first turns) instead of the per-chunk array.
- Edit replays adopt the prepare response's replacement identity; the
  render ledger excludes unconfirmed optimistic copies by identity now
  that the local input no longer uses an opt- prefix, so a failed send
  cannot pin a message the server never saw.
- Anchor lifecycle matches the previous baseline: kept across
  finish/stop/error until canonical data takes over, replaced by the next
  local submit, cleared on send failure, thread switch, and replay gaps.

* test(threads): type submit mock calls in local-turn-order dom tests

* fix(frontend): bound local turn repair to pre-submit history

* fix(frontend): preserve pre-submit bridge ordering

---------

Co-authored-by: 肘子香香 <hyh112300@163.com>
Co-authored-by: 霍英豪 <huoyinghao250707@credithc.com>
Co-authored-by: wangzeren <1004695029@qq.com>
2026-09-12 17:27:04 +08:00
..