Issue Station
Sign In
Tools hereToolbox

openclaw - 💡(How to fix) Fix [Bug]: openai-codex/gpt-5.4 works via infer model run, but embedded chat runs fail with "terminated" on 2026.4.21 [2 comments, 2 participants]

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…
GitHub stats
openclaw/openclaw#70627•Fetched 2026-04-24 05:55:28
View on GitHub
Comments
2
Participants
2
Timeline
7
Reactions
3
Author
LFArceLFArce
Participants
LFArceLFArcesteipetesteipete
Timeline (top)
closed ×2commented ×2labeled ×1reopened ×1

On OpenClaw 2026.4.21, openai-codex/gpt-5.4 works when called directly with openclaw infer model run, and openclaw models status --probe reports the model/profile as healthy, but normal chat/embedded runs fail with a generic terminated error. This makes simple prompts like hello fail in the normal chat path even though the direct model route succeeds.

Error Message

On OpenClaw 2026.4.21, openai-codex/gpt-5.4 works when called directly with openclaw infer model run, and openclaw models status --probe reports the model/profile as healthy, but normal chat/embedded runs fail with a generic terminated error.

  • error: "terminated" warn agent/embedded {"subsystem":"agent/embedded"} {"event":"embedded_run_agent_end","tags":["error_handling","lifecycle","agent_end","assistant_error"],"runId":"9077acfc-99ef-4605-bb73-0062a7dd1f51","isError":true,"error":"terminated","failoverReason":null,"model":"gpt-5.4","provider":"openai-codex","rawErrorPreview":"terminated","rawErrorHash":"sha256:e8c95a2a7271","providerRuntimeFailureKind":"unknown"} embedded run agent end

Root Cause

On OpenClaw 2026.4.21, openai-codex/gpt-5.4 works when called directly with openclaw infer model run, and openclaw models status --probe reports the model/profile as healthy, but normal chat/embedded runs fail with a generic terminated error. This makes simple prompts like hello fail in the normal chat path even though the direct model route succeeds.

Code Example

`openclaw models status --probe` showed the `openai-codex/gpt-5.4` auth probe as healthy (`ok`).

Direct model test succeeded:
json
{
  "ok": true,
  "capability": "model.run",
  "transport": "local",
  "provider": "openai-codex",
  "model": "gpt-5.4",
:thumbsup:
Haz clic para reaccionar
:lobster:
Haz clic para reaccionar
:100:
Haz clic para reaccionar
Agregar reacción
Responder
Reenviar
Más
[16:02]jueves, 23 de abril de 2026 16:02
"attempts": [],
  "outputs": [
    {
      "text": "ping ",
      "mediaUrl": null
    }
  ]
}
But the embedded chat path logged:
text
warn agent/embedded {"subsystem":"agent/embedded"} {"event":"embedded_run_agent_end","tags":["error_handling","lifecycle","agent_end","assistant_error"],"runId":"9077acfc-99ef-4605-bb73-0062a7dd1f51","isError":true,"error":"terminated","failoverReason":null,"model":"gpt-5.4","provider":"openai-codex","rawErrorPreview":"terminated","rawErrorHash":"sha256:e8c95a2a7271","providerRuntimeFailureKind":"unknown"} embedded run agent end
RAW_BUFFERClick to expand / collapse

Bug type

Behavior bug (incorrect output/state without crash)

Beta release blocker

No

Summary

On OpenClaw 2026.4.21, openai-codex/gpt-5.4 works when called directly with openclaw infer model run, and openclaw models status --probe reports the model/profile as healthy, but normal chat/embedded runs fail with a generic terminated error. This makes simple prompts like hello fail in the normal chat path even though the direct model route succeeds.

Steps to reproduce

  1. Configure OpenClaw to use openai-codex/gpt-5.4 as the default model.
  2. Verify model health: openclaw models status --probe
  3. Verify direct inference works: openclaw infer model run --local --model "openai-codex/gpt-5.4" --prompt "pong" --json
  4. Send a simple prompt like hello through a normal chat/thread conversation.
  5. Observe that the embedded agent run fails with terminated.

Expected behavior

If openai-codex/gpt-5.4 is healthy and openclaw infer model run succeeds, normal embedded chat runs should also complete and return a normal assistant reply.

Actual behavior

  • openclaw models status --probe reports the auth probe as ok
  • direct infer model run succeeds
  • normal embedded chat runs fail with:
    • error: "terminated"
    • providerRuntimeFailureKind: "unknown"

OpenClaw version

2026.4.21 (f788c88)

Operating system

Win11+WLS

Install method

npm global

Model

openai-codex/gpt-5.4

Provider / routing chain

normal embedded chat run -> openai-codex/gpt-5.4

Additional provider/model setup details

No response

Logs, screenshots, and evidence

`openclaw models status --probe` showed the `openai-codex/gpt-5.4` auth probe as healthy (`ok`).

Direct model test succeeded:
json
{
  "ok": true,
  "capability": "model.run",
  "transport": "local",
  "provider": "openai-codex",
  "model": "gpt-5.4",
:thumbsup:
Haz clic para reaccionar
:lobster:
Haz clic para reaccionar
:100:
Haz clic para reaccionar
Agregar reacción
Responder
Reenviar
Más
[16:02]jueves, 23 de abril de 2026 16:02
"attempts": [],
  "outputs": [
    {
      "text": "ping ",
      "mediaUrl": null
    }
  ]
}
But the embedded chat path logged:
text
warn agent/embedded {"subsystem":"agent/embedded"} {"event":"embedded_run_agent_end","tags":["error_handling","lifecycle","agent_end","assistant_error"],"runId":"9077acfc-99ef-4605-bb73-0062a7dd1f51","isError":true,"error":"terminated","failoverReason":null,"model":"gpt-5.4","provider":"openai-codex","rawErrorPreview":"terminated","rawErrorHash":"sha256:e8c95a2a7271","providerRuntimeFailureKind":"unknown"} embedded run agent end

Impact and severity

No response

Additional information

No response

extent analysis

TL;DR

The issue might be resolved by investigating the differences in configuration or environment between the direct openclaw infer model run and the normal embedded chat run, as the model is reported healthy and direct inference works.

Guidance

  • Verify that the openai-codex/gpt-5.4 model is correctly configured for both direct and embedded runs, checking for any differences in settings or parameters.
  • Compare the environment and dependencies used for direct openclaw infer model run and normal embedded chat runs to identify potential discrepancies.
  • Check the OpenClaw documentation for any specific requirements or recommendations for running openai-codex/gpt-5.4 in an embedded context.
  • Review the logs for any additional error details or hints beyond the generic terminated error, focusing on differences between successful direct runs and failed embedded runs.

Example

No specific code example can be provided without more details on the configuration or code differences between the direct and embedded runs.

Notes

The solution may depend on specifics of the OpenClaw version, the openai-codex/gpt-5.4 model, and the environment in which they are running. The generic terminated error suggests a need for more detailed logging or error handling to diagnose the root cause.

Recommendation

Apply workaround: Investigate and reconcile any configuration or environmental differences between direct and embedded runs to ensure consistency, as this might resolve the issue without requiring an upgrade or more invasive changes.

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…

FAQ

Expected behavior

If openai-codex/gpt-5.4 is healthy and openclaw infer model run succeeds, normal embedded chat runs should also complete and return a normal assistant reply.

#orchestration issue#cache issue#memory leak#API versioning#request timeout

Still need to ship something?

×6

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

Back to top recommendations

TRENDING

openclaw - 💡(How to fix) Fix [Bug]: openai-codex/gpt-5.4 works via infer model run, but embedded chat runs fail with "terminated" on 2026.4.21 [2 comments, 2 participants]