codex - 💡(How to fix) Fix Codex App/CLI: subagent tasks trigger reconnect loop and stream disconnect

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…

Error Message

CLI error examples: stream disconnected before completion: An error occurred while processing your request. You can retry your request, or contact us through our help center at help.openai.com if the error persists. Please include the request ID 7e1187b0-7b0c-4f6b-94d9-28eb5613b417 in your message. ■ stream disconnected before completion: An error occurred while processing your request. You can retry your request, or contact us through our help center at help.openai.com if the error persists. Please include the request ID d072ff0c-9713-4fb6-9fc9-842194229a06 in your message. Codex App UI error from screenshot: stream disconnected before completion: An error occurred while processing your request. You can retry your request, or contact us through our help center at help.openai.com if the error persists. Please include the request ID 9876d607-bb69-41ab-9d68-eeaada464ab6 in your message. 2026-05-25T18:09:21.500Z error [electron-message-handler] Received turn/started for unknown conversation conversationId=019e6053-b939-7a82-856e-bdf3c7800d37 2026-05-25T18:09:22.148Z error [electron-message-handler] Request failed ... method=thread/read ... "failed to read thread ... rollout ... is empty" 2026-05-25T18:09:22.176Z error [electron-message-handler] Received turn/started for unknown conversation conversationId=019e6053-bd60-7821-a171-38c754cab6fa 2026-05-25T18:09:22.282Z error [electron-message-handler] Received turn/started for unknown conversation conversationId=019e6053-bde0-7032-9f51-2b3bc5077b21 I searched the local app logs under ~/Library/Logs/com.openai.codex/2026/05/25/. I did not find the UI/CLI request IDs (9876d607-bb69-41ab-9d68-eeaada464ab6, 7e1187b0-7b0c-4f6b-94d9-28eb5613b417, d072ff0c-9713-4fb6-9fc9-842194229a06) in those local logs, so those request IDs appear to be emitted only in the UI/CLI error messages.

Fix Action

Fix / Workaround

I am seeing persistent stream/reconnect failures when using Codex App with subagents/background agents. Normal single-agent Codex tasks generally work, but once a task starts dispatching subagents, the Codex App UI begins showing repeated reconnect attempts (Reconnecting... 1/5 through 5/5) and eventually fails.

  1. Open Codex App on macOS 26.5.
  2. Start a local task that uses subagents/background agents. In my case, Codex generated 3 agents/workers.
  3. Wait until subagent dispatch begins.
  4. Observe the app enter Reconnecting... 1/5 through Reconnecting... 5/5, then fail with stream disconnected before completion.
  5. Run a similar Codex CLI task on the same machine. The CLI also falls back from WebSockets to HTTPS and then fails with stream disconnected before completion.
  6. Try a normal task without subagents. In my usage, those are much more likely to complete normally.

Subagent/background-agent tasks should keep the stream alive or recover cleanly after transient disconnects. Subagent dispatch should not leave the UI with unknown conversation state, empty rollout files, or repeated reconnect attempts.

Code Example

### What subscription do you have?

ChatGPT Pro

### What platform is your computer?

macOS `26.5 (25F71)`, Darwin `25.5.0`, `arm64`.  Hardware:

---

### What issue are you seeing?

I am seeing persistent stream/reconnect failures when using Codex App with subagents/background agents. Normal single-agent Codex tasks generally work, but once a task starts dispatching subagents, the Codex App UI begins showing repeated reconnect attempts (`Reconnecting... 1/5` through `5/5`) and eventually fails.

I have tried disabling WebSocket transport and using HTTP/HTTPS instead. I also disabled all hooks. Neither change fixed the issue.

The same class of failure also happens in Codex CLI on the same machine.

CLI error examples:

---

Codex App UI error from screenshot:

---

<img width="878" height="922" alt="Image" src="https://github.com/user-attachments/assets/447c9867-5f46-4a20-8acb-f6ab80692320" />

The screenshot also shows the task had generated 3 agents. The UI text before failure was:

---

Around a subagent/multi-conversation launch window, the App logs show repeated conversation routing/state failures. This looks correlated with the moment where subagent distribution starts failing:

---

That same log contains 184 occurrences of unknown conversation / missing conversation state errors matching:

---

The local App transport itself appears to start normally using stdio, so the failure does not look like the local app-server failing to start:
RAW_BUFFERClick to expand / collapse

What version of the Codex App are you using (From “About Codex” dialog)?

Codex App 26.519.41501 (3044). Local evidence: text /Applications/Codex.app/Contents/Info.plist:19 <key>CFBundleShortVersionString</key> /Applications/Codex.app/Contents/Info.plist:20 <string>26.519.41501</string> /Applications/Codex.app/Contents/Info.plist:21 <key>CFBundleVersion</key> /Applications/Codex.app/Contents/Info.plist:22 <string>3044</string> The bundled app-server/runtime reports 0.133.0-alpha.1, while my standalone Codex CLI reports codex-cli 0.133.0. text codex-desktop-5b27d5ea-3243-4be8-9b32-8b1b716f5766-44076-t0-i1-172621-0.log:13 2026-05-25T17:26:22.328Z info [AppServerConnection] Current reported app-server version: currentVersion=0.133.0-alpha.1 hostId=local codex --version codex-cli 0.133.0

What subscription do you have?

ChatGPT Pro

What platform is your computer?

macOS 26.5 (25F71), Darwin 25.5.0, arm64. Hardware: text Model Name: MacBook Pro Model Identifier: MacBookPro18,1 Chip: Apple M1 Pro Total Number of Cores: 10 (8 Performance and 2 Efficiency) Memory: 32 GB

What issue are you seeing?

I am seeing persistent stream/reconnect failures when using Codex App with subagents/background agents. Normal single-agent Codex tasks generally work, but once a task starts dispatching subagents, the Codex App UI begins showing repeated reconnect attempts (Reconnecting... 1/5 through 5/5) and eventually fails.

I have tried disabling WebSocket transport and using HTTP/HTTPS instead. I also disabled all hooks. Neither change fixed the issue.

The same class of failure also happens in Codex CLI on the same machine.

CLI error examples:

⚠ Falling back from WebSockets to HTTPS transport.
stream disconnected before completion: An error occurred while processing your request. You can retry your request, or contact us through our help center at help.openai.com if the error persists. Please include the request ID 7e1187b0-7b0c-4f6b-94d9-28eb5613b417 in your message.

■ stream disconnected before completion: An error occurred while processing your request. You can retry your request, or contact us through our help center at help.openai.com if the error persists. Please include the request ID d072ff0c-9713-4fb6-9fc9-842194229a06 in your message.

Codex App UI error from screenshot:

Reconnecting... 1/5
Reconnecting... 2/5
Reconnecting... 3/5
Reconnecting... 4/5
Reconnecting... 5/5
stream disconnected before completion: An error occurred while processing your request. You can retry your request, or contact us through our help center at help.openai.com if the error persists. Please include the request ID 9876d607-bb69-41ab-9d68-eeaada464ab6 in your message.
<img width="878" height="922" alt="Image" src="https://github.com/user-attachments/assets/447c9867-5f46-4a20-8acb-f6ab80692320" />

The screenshot also shows the task had generated 3 agents. The UI text before failure was:

已生成3个智能体
三个 worker 已分发,写入范围分别是 provider、前端静态壳、service/workflow。
...                                                                                                                                                                                                                      Reconnecting... 1/5
...
Reconnecting... 5/5                                                                                                                                                                                                      ```

Around a subagent/multi-conversation launch window, the App logs show repeated conversation routing/state failures. This looks correlated with the moment where subagent distribution starts failing:

```text
codex-desktop-33ffe158-3b6c-45c2-acf9-6d8144fff068-94191-t0-i1-180614-0.log:245
2026-05-25T18:09:21.500Z error [electron-message-handler] Received turn/started for unknown conversation conversationId=019e6053-b939-7a82-856e-bdf3c7800d37

codex-desktop-33ffe158-3b6c-45c2-acf9-6d8144fff068-94191-t0-i1-180614-0.log:250
2026-05-25T18:09:22.148Z error [electron-message-handler] Request failed ... method=thread/read ... "failed to read thread ... rollout ... is empty"

codex-desktop-33ffe158-3b6c-45c2-acf9-6d8144fff068-94191-t0-i1-180614-0.log:254
2026-05-25T18:09:22.176Z error [electron-message-handler] Received turn/started for unknown conversation conversationId=019e6053-bd60-7821-a171-38c754cab6fa
codex-desktop-33ffe158-3b6c-45c2-acf9-6d8144fff068-94191-t0-i1-180614-0.log:261
2026-05-25T18:09:22.282Z error [electron-message-handler] Received turn/started for unknown conversation conversationId=019e6053-bde0-7032-9f51-2b3bc5077b21

That same log contains 184 occurrences of unknown conversation / missing conversation state errors matching:

Received turn/started for unknown conversation
Received item/started for unknown conversation
Received item/completed for unknown conversation
Conversation state not found
Received turn/completed for unknown conversation
                                                                                                                                                                                                                  The local App transport itself appears to start normally using stdio, so the failure does not look like the local app-server failing to start:
codex-desktop-5b27d5ea-3243-4be8-9b32-8b1b716f5766-44076-t0-i1-172621-0.log:5
2026-05-25T17:26:22.172Z info [AppServerConnection] Starting app-server connection hostId=local transport=stdio

codex-desktop-5b27d5ea-3243-4be8-9b32-8b1b716f5766-44076-t0-i1-172621-0.log:12
2026-05-25T17:26:22.181Z info [AppServerConnection] Transport start success connectionId=1 hostId=local transport=stdio

codex-desktop-5b27d5ea-3243-4be8-9b32-8b1b716f5766-44076-t0-i1-172621-0.log:57
2026-05-25T17:26:25.181Z info [electron-message-handler] browser_use_availability_resolved available=true browserPane=true platform=macOS reason=available release=26.519.41501

I searched the local app logs under ~/Library/Logs/com.openai.codex/2026/05/25/. I did not find the UI/CLI request IDs (9876d607-bb69-41ab-9d68-eeaada464ab6, 7e1187b0-7b0c-4f6b-94d9-28eb5613b417, d072ff0c-9713-4fb6-9fc9-842194229a06) in those local logs, so those request IDs appear to be emitted only in the UI/CLI error messages.

What steps can reproduce the bug?

  1. Open Codex App on macOS 26.5.
  2. Start a local task that uses subagents/background agents. In my case, Codex generated 3 agents/workers.
  3. Wait until subagent dispatch begins.
  4. Observe the app enter Reconnecting... 1/5 through Reconnecting... 5/5, then fail with stream disconnected before completion.
  5. Run a similar Codex CLI task on the same machine. The CLI also falls back from WebSockets to HTTPS and then fails with stream disconnected before completion.
  6. Try a normal task without subagents. In my usage, those are much more likely to complete normally.

What is the expected behavior?

Subagent/background-agent tasks should keep the stream alive or recover cleanly after transient disconnects. Subagent dispatch should not leave the UI with unknown conversation state, empty rollout files, or repeated reconnect attempts.

Additional information

I tried disabling WebSocket transport and using HTTP/HTTPS. I also disabled all hooks. The failures still occurred.

This appears specific to tasks involving subagents/background agents. Single-agent Codex App tasks generally work on the same machine and account.

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING