Skip to content

fix(fork): one agent message in a row in the Chat + Replies main list - #151

Merged
orbitingflea merged 2 commits into
mainfrom
fix/subthread-reply-and-multisend
Nov 14, 2026
Merged

fix(fork): one agent message in a row in the Chat + Replies main list#151
orbitingflea merged 2 commits into
mainfrom
fix/subthread-reply-and-multisend

Conversation

@orbitingflea

@orbitingflea orbitingflea commented Nov 14, 2026

Copy link
Copy Markdown
Owner

This pull request makes Chat + Replies refuse a second agent message in a row in the main list, and stops the desktop Reply button from being cut off.

改了什么行为

Behaviour change: yes, agents in Chat + Replies are refused a second new main-list message until the user writes in the main list; desktop users see the whole Reply button.

  • An agent message in the main list now waits for a user message in the main list before the next one. A reply inside a sub-thread does not reopen the main list. The refusal says how to change the message or what to answer instead.
  • With a mouse, the Reply button under a message with no replies now shows in full. Under a message followed directly by the next message, the gap grows to 16px. Phones do not change.

Why

Each sub-thread already took one answer per user message, but nothing checked new main-list messages, so an agent could post several in a row. The message list clips each row, so the Reply button, which hung below its row, lost its lower half.

Checks

New tests fail on the first commit and pass on the second. The repo's checks for changed files pass. In the web app, a live agent asked for three new messages got the first and a refusal for the second; on the old code all three went out. Desktop and phone screenshots show the button in full.

How to undo

Revert both commits. Nothing is stored.

Design notes
  • Counted as sent: a delivered send_to_user with no reply_to, a Claude call still running before the caller that the handler would accept as a new message, and, for providers whose calls do not name themselves, an accepted send held for 10 seconds under its own main-list key. Replaces, acks and replies do not count.
  • For a new main-list message, the tool reads history back to the main list's latest message, not only the latest 120 messages, so a long sub-thread cannot hide it. Answers and replaces keep the 120-message read.
  • The mode's rules text is unchanged; the refusal teaches the rule.
  • The Reply slot tops up the row's bottom padding to the button's 16px, so the button sits inside the row and hovering never resizes it. It mirrors the row padding rule in MessagesTimeline.tsx; if that rule changes, the slot must follow.
  • Upstream files: MessagesTimeline.tsx +1 −3, in the fork's existing Reply button line. All other changes are in fork files.
  • Mobile shows no display mode, so only the server rule applies there.

orbitingflea and others added 2 commits November 14, 2026 13:35
@orbitingflea @claude
test(server): cover one new main-list message per user message in Cha…
9ff7da5 
…t + Replies

In Chat + Replies the agent may not send two messages in a row in the
main list, but send_to_user accepts every new_sub_thread call. These
cases fail on the current code: a second new message is accepted, and
the tools' history read stops 120 messages back, before the main
list's latest message.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
@orbitingflea @claude
fix(fork): one agent message in a row in the Chat + Replies main list
d7515a1 
The agent could send any number of new main-list messages in a row,
and on desktop the hover Reply button under such a message was cut off.

send_to_user now refuses a new main-list message while the agent's
last one there has no user message after it, counting sends still
running or not yet stored. User replies in sub-threads do not reopen
the main list. The tools read history back to the main list's latest
message, so a long sub-thread cannot hide it.

The list clips each row, so the Reply button now sits inside its row:
with a mouse its slot tops up the row's bottom padding to the
button's height.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
@github-actions github-actions Bot added vouch:trusted Author is trusted by repo permissions or the VOUCHED list. size:L labels Nov 14, 2026
@github-actions

github-actions Bot commented Nov 14, 2026

Copy link
Copy Markdown

Thread transfer impact

✅ Thread transfer remains within every enforced ceiling.

Provider Metric Main baseline This PR Impact PR ceiling
Codex Total thread wire 5.0 KiB 5.0 KiB 0 B (0.0%) 6.8 KiB ✅
Codex Thread snapshot wire 3.8 KiB 3.8 KiB 0 B (0.0%) 4.9 KiB ✅
Codex Live turn WebSocket wire 1.2 KiB 1.2 KiB 0 B (0.0%) 2.0 KiB ✅
Codex Live turn WebSocket decoded 21.5 KiB 21.5 KiB 0 B (0.0%) 24.4 KiB ✅
Codex Live turn messages 1 1 0 (0.0%) 8 ✅
Claude Total thread wire 5.0 KiB 5.0 KiB 0 B (0.0%) 6.8 KiB ✅
Claude Thread snapshot wire 3.8 KiB 3.8 KiB 0 B (0.0%) 4.9 KiB ✅
Claude Live turn WebSocket wire 1.2 KiB 1.2 KiB 0 B (0.0%) 2.0 KiB ✅
Claude Live turn WebSocket decoded 21.9 KiB 21.9 KiB 0 B (0.0%) 24.4 KiB ✅
Claude Live turn messages 1 1 0 (0.0%) 8 ✅

Other scenarios

All 64 scenario measurements match main.

All 64 scenario measurements
Provider Scenario Metric Main baseline This PR Impact PR ceiling
Codex short turn resume WebSocket decoded 10.5 KiB 10.5 KiB 0 B (0.0%) 12.7 KiB ✅
Codex short turn resume WebSocket messages 2 2 0 (0.0%) 2 ✅
Codex long turn running, cold open HTTP decoded 281.7 KiB 281.7 KiB 0 B (0.0%) 302.7 KiB ✅
Codex long turn running, cold open rows 75 75 0 (0.0%) 75 ✅
Codex long turn running, history page HTTP decoded 92.4 KiB 92.4 KiB 0 B (0.0%) 107.4 KiB ✅
Codex long turn running, history page rows 75 75 0 (0.0%) 75 ✅
Codex long turn finished, cold open HTTP decoded 381.5 KiB 381.5 KiB 0 B (0.0%) 410.2 KiB ✅
Codex long turn finished, cold open rows 151 151 0 (0.0%) 151 ✅
Codex long turn finished, socket cold open WebSocket decoded 381.6 KiB 381.6 KiB 0 B (0.0%) 410.2 KiB ✅
Codex long turn finished, socket cold open WebSocket messages 2 2 0 (0.0%) 2 ✅
Codex long turn finished, socket cold open rows 151 151 0 (0.0%) 151 ✅
Codex long turn finished, work page HTTP decoded 186.2 KiB 186.2 KiB 0 B (0.0%) 200.2 KiB ✅
Codex long turn finished, work page rows 150 150 0 (0.0%) 150 ✅
Codex idle thread resume WebSocket decoded 65 B 65 B 0 B (0.0%) 200 B ✅
Codex idle thread resume WebSocket messages 1 1 0 (0.0%) 1 ✅
Codex fleet shell snapshot HTTP decoded 42.4 KiB 42.4 KiB 0 B (0.0%) 53.7 KiB ✅
Codex fleet shell snapshot rows 27 27 0 (0.0%) 27 ✅
Codex fleet shell subscribe WebSocket decoded 65 B 65 B 0 B (0.0%) 200 B ✅
Codex fleet shell subscribe WebSocket messages 1 1 0 (0.0%) 1 ✅
Codex fleet shell resume check HTTP decoded 18 B 18 B 0 B (0.0%) 100 B ✅
Codex fleet shell resume check rows 0 0 0 0 ✅
Codex stale shell reload HTTP decoded 42.4 KiB 42.4 KiB 0 B (0.0%) 53.7 KiB ✅
Codex stale shell reload rows 27 27 0 (0.0%) 27 ✅
Codex stale shell resume WebSocket decoded 140 B 140 B 0 B (0.0%) 400 B ✅
Codex stale shell resume WebSocket messages 2 2 0 (0.0%) 2 ✅
Codex stale todo list cold open HTTP decoded 72.4 KiB 72.4 KiB 0 B (0.0%) 83.0 KiB ✅
Codex stale todo list cold open rows 75 75 0 (0.0%) 75 ✅
Codex stale todo list cold open nodes 2 2 0 (0.0%) 4 ✅
Codex stale todo list cold open subagents 2 2 0 (0.0%) 4 ✅
Codex stale todo list cold open plans 1 1 0 (0.0%) 2 ✅
Codex stale todo list cold open providerTurns 1 1 0 (0.0%) 2 ✅
Codex stale todo list cold open checkpoints 1 1 0 (0.0%) 2 ✅
Claude short turn resume WebSocket decoded 10.6 KiB 10.6 KiB 0 B (0.0%) 12.7 KiB ✅
Claude short turn resume WebSocket messages 2 2 0 (0.0%) 2 ✅
Claude long turn running, cold open HTTP decoded 283.3 KiB 283.3 KiB 0 B (0.0%) 302.7 KiB ✅
Claude long turn running, cold open rows 75 75 0 (0.0%) 75 ✅
Claude long turn running, history page HTTP decoded 93.4 KiB 93.4 KiB 0 B (0.0%) 107.4 KiB ✅
Claude long turn running, history page rows 75 75 0 (0.0%) 75 ✅
Claude long turn finished, cold open HTTP decoded 384.2 KiB 384.2 KiB 0 B (0.0%) 410.2 KiB ✅
Claude long turn finished, cold open rows 151 151 0 (0.0%) 151 ✅
Claude long turn finished, socket cold open WebSocket decoded 384.3 KiB 384.3 KiB 0 B (0.0%) 410.2 KiB ✅
Claude long turn finished, socket cold open WebSocket messages 2 2 0 (0.0%) 2 ✅
Claude long turn finished, socket cold open rows 151 151 0 (0.0%) 151 ✅
Claude long turn finished, work page HTTP decoded 188.1 KiB 188.1 KiB 0 B (0.0%) 200.2 KiB ✅
Claude long turn finished, work page rows 150 150 0 (0.0%) 150 ✅
Claude idle thread resume WebSocket decoded 66 B 66 B 0 B (0.0%) 200 B ✅
Claude idle thread resume WebSocket messages 1 1 0 (0.0%) 1 ✅
Claude fleet shell snapshot HTTP decoded 43.0 KiB 43.0 KiB 0 B (0.0%) 53.7 KiB ✅
Claude fleet shell snapshot rows 27 27 0 (0.0%) 27 ✅
Claude fleet shell subscribe WebSocket decoded 66 B 66 B 0 B (0.0%) 200 B ✅
Claude fleet shell subscribe WebSocket messages 1 1 0 (0.0%) 1 ✅
Claude fleet shell resume check HTTP decoded 18 B 18 B 0 B (0.0%) 100 B ✅
Claude fleet shell resume check rows 0 0 0 0 ✅
Claude stale shell reload HTTP decoded 43.0 KiB 43.0 KiB 0 B (0.0%) 53.7 KiB ✅
Claude stale shell reload rows 27 27 0 (0.0%) 27 ✅
Claude stale shell resume WebSocket decoded 140 B 140 B 0 B (0.0%) 400 B ✅
Claude stale shell resume WebSocket messages 2 2 0 (0.0%) 2 ✅
Claude stale todo list cold open HTTP decoded 73.4 KiB 73.4 KiB 0 B (0.0%) 83.0 KiB ✅
Claude stale todo list cold open rows 75 75 0 (0.0%) 75 ✅
Claude stale todo list cold open nodes 2 2 0 (0.0%) 4 ✅
Claude stale todo list cold open subagents 2 2 0 (0.0%) 4 ✅
Claude stale todo list cold open plans 1 1 0 (0.0%) 2 ✅
Claude stale todo list cold open providerTurns 1 1 0 (0.0%) 2 ✅
Claude stale todo list cold open checkpoints 1 1 0 (0.0%) 2 ✅

Baseline: 48386e9 · PR result: d7515a1 · Source CI: failure

Scenario and decoded snapshot size

10 historical turns, 5 command tools per turn, 878.9 KiB retained MCP result per historical turn, and a 1.05 MiB retained result in the measured turn.

  • Codex decoded thread snapshot: 108.5 KiB
  • Claude decoded thread snapshot: 108.8 KiB

Updated in place by a trusted workflow. PR artifacts are strictly validated and never executed.

@orbitingflea
orbitingflea merged commit 15c4229 into main Nov 14, 2026
25 of 27 checks passed
@orbitingflea orbitingflea mentioned this pull request Nov 14, 2026
Open
1 task
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

No reviews

Assignees

No one assigned

Labels

size:L vouch:trusted Author is trusted by repo permissions or the VOUCHED list.

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

1 participant

@orbitingflea