You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
Repository navigation
experimental feature "collab" is broken on main for API/free/plus/go users #11764
What terminal emulator and version are you using (if applicable)?
N/A
What issue are you seeing?
After @jif-oai merged #11745, hardcoding the Explorer AgentRole to have a fixed model override of gpt-5.3-codex-spark where it used to be gpt-5.1-codex-mini, trying to use the Experimental collab feature no longer works for users on a Free or Plus subscription as they don't have access to Codex Spark, as well as people using Codex CLI via API.
What steps can reproduce the bug?
Enable collab via /experimental or via editing ~/.codex/config.toml, and watch as it fails to explore due to model unavailability.
› Hey, use the explorer subagents to explain what models are used for exploring.
• Agent spawned
└ call: call_9DPDLA2CS27lsprBo65AphhM
agent: 019c5844-deb4-78e3-aa34-cffbb4be15e7
status: pending init
prompt: Find and explain which models are used for explorer subagents in this repo or docs. Look for any configuration/docs about explorer model selection.
• Waiting for agents
└ call: call_ZR2b8AqVEiBggFUhdilh1PC1
receivers: 019c5844-deb4-78e3-aa34-cffbb4be15e7
• Wait complete
└ call: call_ZR2b8AqVEiBggFUhdilh1PC1
agents: 1 total · 1 errored
019c5844-deb4-78e3-aa34-cffbb4be15e7 errored: { "error": { "message": "The requested model 'gpt-5.3-codex-spark' does not exist.", "type": "invalid_request_error", "param": "model", "code": "model_not_fo...
What is the expected behavior?
I'd expect that if something is exposed via /experimental it wouldn't regress in such a way.
I'd completely understand this happening (but would still be bummed) if this was marked as Stage.UnderDevelopment.
Activity
github-actions commentedon Feb 13, 2026
Potential duplicates detected. Please review them and close your issue if it is a duplicate.
Powered by Codex Action
lattwood commentedon Feb 13, 2026
They're similar but not duplicates
chore: mini (#11772)
lattwood commentedon Feb 13, 2026
<3 ty
Szpadel commentedon Feb 13, 2026
@jif-oai could we maybe get configuration option for this? Or have spark with mini as a fallback?
lattwood commentedon Feb 13, 2026
@Szpadel I'm planning to compile it myself to use this exact change this weekend on my personal pro account
MrLightspeed commentedon Feb 14, 2026
Pro level options would be ideal. If someone qualifies for a higher tier, let them benefit.
jif-oai commentedon Feb 16, 2026
Would this be sufficient? #11899
Szpadel commentedon Feb 16, 2026
@jif-oai that is perfect, thank you
feat: switch kontext integration to direct injected tool runtime (#4)
chore: mini (#11772)
chore: mini (openai#11772)
chore: mini (#11772)