Flash sends effort=low — omit still thinks; stream -p hang fix - #671
Merged
Conversation
Pi's glm-5.3-flash SWE first/wall win was no thinking, not four tools. Codegraff takes_effort sent default medium on every flash request — seconds of silent TTFT and 3–7k thinking tokens (ADR 0045 timeouts). Same Gemini skip, now any *flash* name. Lean -p shortens tool prose only. Catalog glm-5.3-flash. Do not shrink the keep-list (ADR 0024).
Eval first=6.7s was turn chrome on stdout at model call 2, not boot (boot is 7ms; gateway TTFT is ~6s). Drop the pulse when unattended so stdout stays the answer, and print `calling <model>` on stderr at oneshot start — same class of signal as Pi's session JSON.
justrach/codegraff is repository 84216 on trendshift.io.
json-stream and cookie-store SIGKILL'd at 300s because -p gated live transport on out!=null. A hung/5xx second call sat in postWatched until the deadline, then retried, then the eval cap killed the process. Root one-shots now postLive so the 30s head-stall fires. Paint stays off (out=null / stream_quiet). graff-dev also caps postWatched at 90s for subagents.
json-stream passed (280s). cookie-store / label-sort still hit the 300s cap on live streams, not the old 5-minute watched POST.
Codegraff glm-5.3-flash bills reasoning_tokens when reasoning_effort is absent (27 on a pong; SWE streamed 1.9MB reasoning_content). thinking.disabled still thinks. low bills 0. none is a 400. That is the wall gap with Pi, not Zig vs JS. /effort high still sends high. Do not shrink the keep-list.
Beats Pi's 758s on the same model. Same miss (label-sort). Out tokens 29k → 4.7k — the wall was thinking novels, not Zig vs JS.
cursor Bot
pushed a commit
that referenced
this pull request
Aug 29, 2026
GLM SWE 5/6 in 286s vs Pi 758s. Same miss (label-sort). No tag.
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
2 participants
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.
Follow-up to ADR 0045 / the 281 GLM row. The wall gap with Pi was not Zig vs JS.
Trendshift README is already on main via #672.
Why wall was 2× Pi
json-stream’s third call streamed 1.9MB of
reasoning_contentin 212s. Omittingreasoning_effortstill bills thinking: apongwas 27reasoning_tokens.thinking: {type: disabled}still thinks.reasoning_effort: lowbills 0.noneis a 400.Pi’s
models.jsonsetsreasoning: false. We now sendlowfor the flash / Gemini default./effort highstill sends high. Same 8-tool keep-list.Also in this PR
-pusespostLiveso a hung POST dies on the 30s head-stall, not a 5-minutepostWatched.glm-5.3-flash. No call-2 stdout pulse.ADR 0046.
Confirm (
run-20260829-045547.jsonl)lowSame miss as Pi (
label-sort).cookie-store115s (Pi 301s).json-stream36s (Pi 117s). Do not steal Pi’s heap or four-tool catalog.