Responses using GPT-5.3-Codex (from OpenAI Codex) terminate early #8765

Open
opened 2026-02-16 18:10:47 -05:00 by yindo · 3 comments
Owner

Originally created by @kanishkasahoo on GitHub (Feb 6, 2026).

Originally assigned to: @rekram1-node on GitHub.

Description

When responding, the model makes one or two subagent calls, and stops before providing the next run. This behavior is absent from 5.2 on the same provider and task, and from other models like Opus 4.6

Plugins

None

OpenCode version

1.1.53

Steps to reproduce

  1. Select 5.3-Codex model from the picker (tested with OpenAI Codex as provider)
  2. Provide a prompt which causes multiple subagents to be invoked in sequence
  3. Observe that runs complete early (model ends its turn early before properly completinh task

Screenshot and/or share link

Image

Operating System

MacOS 26.2

Terminal

iTerm2

Originally created by @kanishkasahoo on GitHub (Feb 6, 2026). Originally assigned to: @rekram1-node on GitHub. ### Description When responding, the model makes one or two subagent calls, and stops before providing the next run. This behavior is absent from 5.2 on the same provider and task, and from other models like Opus 4.6 ### Plugins None ### OpenCode version 1.1.53 ### Steps to reproduce 1. Select 5.3-Codex model from the picker (tested with OpenAI Codex as provider) 2. Provide a prompt which causes multiple subagents to be invoked in sequence 3. Observe that runs complete early (model ends its turn early before properly completinh task ### Screenshot and/or share link <img width="1664" height="994" alt="Image" src="https://github.com/user-attachments/assets/435364aa-5744-4f43-9cdf-b1e5b993a54d" /> ### Operating System MacOS 26.2 ### Terminal iTerm2
yindo added the bugzen labels 2026-02-16 18:10:47 -05:00
Author
Owner

@github-actions[bot] commented on GitHub (Feb 6, 2026):

This issue might be a duplicate of existing issues. Please check:

  • #11865: Tasks/Subagents with Codex / OpenAI are frequently getting stuck with no timeout/retry - also specifically mentions Codex/OpenAI subagent issues
  • #6244: Response terminates prematurely when using Gemini 3 via LiteLLM - similar pattern of responses terminating early during subagent/tool calls

Feel free to ignore if your specific case (GPT-5.3-Codex early termination) doesn't match these.

@github-actions[bot] commented on GitHub (Feb 6, 2026): This issue might be a duplicate of existing issues. Please check: - #11865: Tasks/Subagents with Codex / OpenAI are frequently getting stuck with no timeout/retry - also specifically mentions Codex/OpenAI subagent issues - #6244: Response terminates prematurely when using Gemini 3 via LiteLLM - similar pattern of responses terminating early during subagent/tool calls Feel free to ignore if your specific case (GPT-5.3-Codex early termination) doesn't match these.
Author
Owner

@DxTa commented on GitHub (Feb 7, 2026):

I noticed similar behaviour as well

@DxTa commented on GitHub (Feb 7, 2026): I noticed similar behaviour as well
Author
Owner

@zkytech commented on GitHub (Feb 9, 2026):

same problem

@zkytech commented on GitHub (Feb 9, 2026): same problem
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: anomalyco/opencode#8765