Repository navigation
Desktop: defer built-in engine titles until the foreground run settles - #4072
Merged
ashhart merged 5 commits intoNov 20, 2026
Merged
Conversation
Open
1 task done
Owner
|
Thanks @AIFlowML. The request-order regression is clear and the fix keeps the title off the engine until the foreground run settles, with renames, cancellation and custom providers untouched. Your follow-up arm is honestly reported: the draft-width collapse did not reproduce there, so the landed evidence is the order fix itself, which stands on its own. It applies cleanly to today's main. The head checks are the last thing we watch; nothing is needed from you.
|
ashhart
force-pushed
the
codex/fix-3606-defer-local-thread-title
branch
from
November 20, 2026 08:27
6138ef4 to
c2ac507
Compare
ashhart
added a commit
that referenced
this pull request
Nov 20, 2026
Owner
|
Thank you @AIFlowML. This is merged into main with your commits under your own name, so you're listed as a TensorFold contributor. It ships in the next release, credited to you in the changelog and the release notes. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What this changes
A new Desktop conversation used to start a background title request on the built-in TensorFold engine before starting its first foreground run. The title now starts after the foreground run settles successfully and releases its engine lease. Cancelling the run or renaming the conversation while it is running prevents the deferred request. Custom providers keep their existing title timing.
min_rows1 (vs 8 standalone) — ~10 tok/s vs ~60 tok/s on M1 Max #3606. Removes the automatic title as a source of contention during its own foreground run. The native scheduler and concurrency between independently started runs stay outside this change.mainata2f4c9dd123860754058dcbfc0ddf252c886528f.atc overlap --json: ATC reported partial coverage. The independent audit paginated 460 open PRs. Allow a saved bot to be assigned to a Solo Kanban task #3737 merged cleanly with the candidate and its related title tests passed in the combined tree. qwen27 Metal: plain greedy picks ride the verify's last command buffer (#2930) #2936 already conflicted in the same Metal files on the comparison base, with identical conflict stages after adding this change. The two old local heads reported by ATC correspond to app: give bots independent reasoning effort #3500 and app: preserve per-agent reasoning effort in Rooms #3514, whose merge commits are already contained in main. All four remaining open AIFlowML heads also composed cleanly. Final live-main merge check passed at5d43ad587548644983f40cf61d18d11ccc9436f1, and its app tree matches the tested head.Checks on this head
6138ef456fe8f0467f5f5ebd7b9e5639d5e731ea.git diff --checkpassed.npm testpassed 892/892 test files on this tree. Typecheck, build, mobile verification and the private-leak check passed.zig fmt --check build.zig zigpassed.zig build test test-golden -Dcpu=apple_m1 -j8 --summary allpassed 921/921 steps and 15,518 tests, with 136 skipped and zero unexpected golden differences on the native input tree at the pinned base. The live-main merge check includes newer unrelated native changes.4890e89b9aea23fe70034eeeb2235f53bb9bffa7over5d43ad587548644983f40cf61d18d11ccc9436f1. That exact diff is limited to the three Desktop TypeScript files. On Linux x86-64 with Zig 0.17.0,zig build -Dfixed-cpu test-benchmark-routing-hostpassed 30/30 on both trees. Thetest-server-cpureplay had identical counts on both trees (1,659 passed, 15 skipped, one failed), with a different failure in the config fixture under umask 002, tracked in Serve config host test fails under a group-friendly umask #4113. With umask 022, the full Linux server CPU suite passed on both trees (5/5 build steps, 1,655 tests passed and 15 skipped on each run). The hosted routing failure has not reproduced locally.Follow-up Metal measurement
On an M5 Max with 128 GiB, the published 1.2.10 Metal engine served the reporter's pinned Qwen3.8-27B and DFlash2 revisions (
22d8d538154e0e5b6f8dcb1fcc74a60a0798104cand50307d4c4cde6860d4eee73e2547cd786fe8e8a4). I alternated three runs per arm at context 8,192 and two configured streams, with the same 600-token greedy counting request and zero cached prompt tokens. In the overlap arm, the 24-token title request was sent first. In the deferred arm, it was sent after the foreground reply.All six foreground replies produced the same token hash, reported
min_rows=16, and used 59 draft rounds. Median foreground decode was 164.7 tok/s with overlapping HTTP requests and 167.9 tok/s when deferred. The M5 engine queued each overlapping title for 3.58–3.90 seconds. The reported draft-width collapse did not reproduce on this M5 Max arm, so the evidence for the PR remains the Desktop request-order regression. The title test request reached its token cap while thinking, so this run measured timing and order only.Receipt
N/A. This changes when Desktop requests a conversation title. The patch is confined to Desktop host scheduling.
Checklist
Igor Lessio - AIFLOW LABS