[orbitingflea]

This pull request resolves the merge of upstream 37714a8 into the fork: commit A (41919f8) left conflict markers in 11 files. The fork now differs from upstream in 364 files, 2 more than before, and adds no lint suppression.

改了什么行为

Behaviour change: yes, in a Normal-mode thread Claude is told to send drafts and code blocks mid-turn with send_to_user, which then takes upstream's 4000-character limit, and web and mobile show the sent text as the agent's words; threads in Messages only, Messages + Dashboard and Chat + Replies keep the fork's 1000-byte send_to_user and get no such instruction.

Upstream added its own send_to_user (pingdotgg#36384). The fork's tool stays registered, because display modes read its calls, and follows upstream's design in Normal. A Claude conversation keeps its first system prompt, so the instruction comes from a prompt hook while the thread is in Normal. In Normal a sent code block now shows above the final reply instead of inside the folded work. send_to_user is pre-approved in plan mode, as upstream does. After sudo t3 browser setup, a profile an older T3 wrote is replaced, so full Chrome keeps its sandbox; an administrator's profile is kept.

Why

Upstream's changes reach the fork, and each fork feature keeps working on upstream's new code.

Undo

Revert this commit and commit A together.

Files

• SendToUser.ts: Normal takes 4000 UTF-16 units and returns sentMessage; the other modes keep 1000 bytes. Stored sends count by their display event, so a Normal send's ignored reply_to or ack changes nothing after a mode switch.
• DisplayModeCompactionNote.ts, ClaudeAdapterV2.ts: the hook gives upstream's section on the first Normal prompt, after a compaction, and after a return to Normal; the system prompt leaves it out.
• displayModeTimeline.ts: Normal sends show in upstream's row, and as replies in the other modes.
• fork/previewChrome.ts: the older profile is a literal, and setup and sandboxBlocked call its check; setup rewrites only that profile.
• Upstream tests: browser.test.ts gets Xvfb in its fake host and a row for the older profile. Upstream's unregistered message/handlers.ts is deleted; the eval lists the registered tools.
• agentContextBudget.json: the tool list grows 1714 bytes, 1240 from upstream's theme tools and 474 from the fork's Normal wording; the Claude append is measured with upstream's layout.
• Not run here: model evals (no key) and the native mobile app.

[github-actions]

Thread transfer impact

✅ Thread transfer remains within every enforced ceiling.

ℹ️ No successful main baseline artifact is available yet. This run establishes the initial measurement.

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

Other scenarios

No main baseline exists yet for these 64 scenario measurements.

All 64 scenario measurements

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

Baseline: unavailable · PR result: 430a441 · 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.