-
-
Notifications
You must be signed in to change notification settings - Fork 79.1k
Codex app-server: long agent replies silently truncated at ~1000-1100 chars (stop=null, aborted=false) #84516
Copy link
Copy link
Open
Labels
P1High-priority user-facing bug, regression, or broken workflow.High-priority user-facing bug, regression, or broken workflow.clawsweeper:needs-live-reproClawSweeper needs live local, crabbox, or manual validation to confirm this issue.ClawSweeper needs live local, crabbox, or manual validation to confirm this issue.clawsweeper:needs-maintainer-reviewClawSweeper marked this issue as needing maintainer review before automation.ClawSweeper marked this issue as needing maintainer review before automation.clawsweeper:needs-product-decisionClawSweeper marked this issue as needing a product or behavior decision.ClawSweeper marked this issue as needing a product or behavior decision.clawsweeper:no-new-fix-prClawSweeper does not recommend queueing a new automated fix PR for this issue.ClawSweeper does not recommend queueing a new automated fix PR for this issue.impact:message-lossChannel message delivery can be lost, duplicated, or misrouted.Channel message delivery can be lost, duplicated, or misrouted.issue-rating: 🐚 platinum hermitGood issue quality with a plausible reproduction path needing some confirmation.Good issue quality with a plausible reproduction path needing some confirmation.
Metadata
Metadata
Assignees
Labels
P1High-priority user-facing bug, regression, or broken workflow.High-priority user-facing bug, regression, or broken workflow.clawsweeper:needs-live-reproClawSweeper needs live local, crabbox, or manual validation to confirm this issue.ClawSweeper needs live local, crabbox, or manual validation to confirm this issue.clawsweeper:needs-maintainer-reviewClawSweeper marked this issue as needing maintainer review before automation.ClawSweeper marked this issue as needing maintainer review before automation.clawsweeper:needs-product-decisionClawSweeper marked this issue as needing a product or behavior decision.ClawSweeper marked this issue as needing a product or behavior decision.clawsweeper:no-new-fix-prClawSweeper does not recommend queueing a new automated fix PR for this issue.ClawSweeper does not recommend queueing a new automated fix PR for this issue.impact:message-lossChannel message delivery can be lost, duplicated, or misrouted.Channel message delivery can be lost, duplicated, or misrouted.issue-rating: 🐚 platinum hermitGood issue quality with a plausible reproduction path needing some confirmation.Good issue quality with a plausible reproduction path needing some confirmation.
Type
Fields
Give feedbackNo fields configured for issues without a type.
Summary
Configured Codex/OAuth agent (gpt-5.5) replies are silently truncated at ~1000–1100 chars when invoked headlessly via
openclaw message. The model is not aborted:data.aborted: false,stopReason/finishReason/errorMessageallnull, yetassistantTexts[0]ends mid-sentence and the CLI wrapper reportsstatus=timeout.This is not the webchat
DEFAULT_CHUNK_LIMIT = 4000truncation — the number (1100 vs 4000) and the codepath (codex app-server stdio vs webchat outbound) are different.Environment
openclaw message), not Telegram/DiscordSymptom — last 10 invocations
abortedstopReasonerrorMessageReplies above ~1000 chars cut mid-sentence; replies below complete cleanly.
Reproduction
*.trajectory.jsonl:Length lands 800–1100 chars; sentence is incomplete;
aborted=false,stopReason=None.Tested on 2026.5.19-beta.2 — worse, not better
Same prompt, same install, gateway restarted:
Rolled back to 5.18.
What this is NOT
errorMessage, no codex 5xx).DEFAULT_CHUNK_LIMIT(different number, different codepath).Asks
stopReason("buffer_full" / "stream_cutoff") when this happens — currentlynullmakes the internally-inconsistent state hard to detect from the outside.Full trajectory
.jsonlfiles and additional repros available on request.