Repository navigation
Description
Before submitting
- I searched existing issues. This is the same root cause as [Bug]: Codex native sub-agents still kill the parent turn under ChatGPT sharing (0.1.10 nightly), and T3's orchestration prompt tells Codex to use them #37386 (closed as not reproduced), [Bug]: Connect with ChatGPT still rejects Codex sub-agents (forked sub-agent) and the thread can't continue (0.1.6) #29992, [Bug]: Gateway Explore sub-agent fails under ChatGPT sharing and blocks subsequent messages #31852, [Bug]: Erroring out while launching a subagent when provider is using the "ChatGPT Sign In via sharing usage limits" #17708 and Connect with ChatGPT rejects Codex subagents and leaves the chat unable to continue #17679. It still reproduces on 0.1.10 stable, in a top-level thread, with no
delegate_task. Currentmainstill lacks the fix the maintainer identified on [Bug]: Codex native sub-agents still kill the parent turn under ChatGPT sharing (0.1.10 nightly), and T3's orchestration prompt tells Codex to use them #37386. - I included enough detail to reproduce or investigate the problem.
Area
apps/server
Steps to reproduce
- Use Codex through Connect with ChatGPT (subscription sharing). The rollout shows
model_provider_id: "openai_token_sharing", Codex CLI 0.170.0 andgpt-6.2-astraat high effort. - Start a normal top-level thread. Don't use
delegate_task, and don't ask for sub-agents. - Have the thread load a skill whose text says "prefer spawning the log-analysis agent". Any skill or AGENTS.md that recommends a helper agent will do.
- Codex calls
collaboration.spawn_agent(task_name: "log_analysis").
Expected behavior
Under subscription sharing, Codex should not be offered native sub-agents at all, because the backend rejects them. If a spawn does slip through, it should come back as a tool error the turn can recover from, and the thread should stay usable.
Actual behavior
-
T3 injects
<multi_agent_mode>… Do not spawn sub-agents unless the user or applicable AGENTS.md/skill instructions explicitly ask for sub-agents…</multi_agent_mode>. That is a soft instruction, andspawn_agentis still in the tool list. The skill text counted as "explicitly asked", so the model spawned. -
The child session forks, receives its
agent_message(NEW_TASK) and fails on its first request. -
The parent turn then fails with a terminal error:
subscription_sharing_unsupported_capability, "User subscription sharing currently supports only text, image, and file messages, item references, additional tools, compaction summaries, reasoning items, Web Search call items, developer function and custom tool call items, and programmatic tool calling items. Remove unsupported input items or use an API key instead." T3 shows this as "Codex used a feature that ChatGPT sharing does not support." -
The thread is then permanently poisoned. The child's FINAL_ANSWER is stored as an
agent_messageresponse item in the parent history, and that item type is not on the allowed list. Every later turn re-sends it and fails within 2–3 seconds. That includes:- the answer to a pending
request_user_input_asyncquestion that Codex had asked earlier in the same turn; - a plain follow-up message;
- a follow-up after switching the model (
gpt-6.2-astra→gpt-6.2-sol).
The only way out was to hand the thread off to a different provider.
- the answer to a pending
Root cause (already identified on #37386)
On #37386 the maintainer reproduced the root cause with Codex 0.169.0. The managed launch args set features.multi_agent=false and features.multi_agent_v2=false. But gpt-6-* models declare multi_agent_version: "v2" in the model catalog, so spawn_agent, wait_agent, send_message and the rest are still offered. Adding -c agents.enabled=false removed them. A failing test was written in apps/server/src/provider/CodexManagedRuntime.test.ts.
The issue was then closed as "not planned / no repro" because no worker has a Connect with ChatGPT login. As of today, CodexManagedRuntime.ts on main still sets only the two features.* flags (lines 28–29), not agents.enabled=false.
Suggested fixes
- Add
agents.enabled=falseto the managed launch args foropenai_token_sharing. This is the one-line fix already identified on [Bug]: Codex native sub-agents still kill the parent turn under ChatGPT sharing (0.1.10 nightly), and T3's orchestration prompt tells Codex to use them #37386. - Make the thread recoverable. When a turn fails with
subscription_sharing_unsupported_capability, the poisoningagent_messageitems stay in the Codex history forever. T3 could offer a "continue in a fresh Codex thread" handoff, as it already does for cross-provider handoff. It could also tell the user that switching models within Codex will not help. - Make the error say why. Currently it reads "Codex used a feature…". Naming the cause ("Codex started a sub-agent, which ChatGPT sharing does not support; this thread can't continue on Codex") would save users from retrying.
Impact
Blocks work completely
Version or commit
T3 Code 0.1.10 (desktop), Codex CLI 0.170.0
Environment
Windows 11, local server, Codex via Connect with ChatGPT (subscription sharing), gpt-6.2-astra (high), full-access runtime, top-level thread (not delegated)
Logs or stack traces
parent rollout (one top-level thread):
turn_context model gpt-6.2-astra, model_provider_id openai_token_sharing
developer message <multi_agent_mode>… Do not spawn sub-agents unless …</multi_agent_mode>
function_call collaboration.spawn_agent {"task_name":"log_analysis", "message": <encrypted>}
event SubAgentActivity started, agent_path /root/log_analysis
response_item agent_message author /root/log_analysis -> /root
"FINAL_ANSWER … Agent errored: subscription_sharing_unsupported_capability"
task_complete error.code subscription_sharing_unsupported_capability (turn 1)
task_complete same error, 2 s after request_user_input_async answer (turn 2)
task_complete same error after model switch to gpt-6.2-sol (turn 3)
child rollout (forked_from parent): session_meta, turn_context, agent_message (NEW_TASK),
then task_complete with the same error on its first request
Full rollouts are not attached because they contain private project material. I can share specific fields on request.
Workaround
Hand the thread off to another provider (Claude in this case). Starting a fresh Codex thread also works. Retrying or switching Codex models in the same thread does not.
Activity
aviadr1 commentedon Nov 19, 2026
The launch-args fix for this is already open as #28143 (
agents.enabled=false, with a test). I checked it on Windows and posted the results there. #28962 looks like the separate fix for recovering a session that has already been poisoned.vickylid commentedon Nov 19, 2026
Confirming this also reproduces on
0.1.10(macOS) directly from T3 Code's own orchestration prompt — without any skill orAGENTS.mdasking for sub-agents:codex:shared(gpt-6.2-astra) thread, T3 Code's injectedt3_code_orchestration_01instructions tell the model:gpt-6.2-sol), the coordinator followedt3_code_orchestration_01and emitted a nativesubAgentActivity/spawn_agentcall, which failed withsubscription_sharing_unsupported_capability.subscription_sharing_unsupported_capabilityas well, until T3 Code issuedthread/reverted(rolled_backon both runs).So in addition to disabling
agents.enabledunder subscription sharing,t3_code_orchestration_01should also avoid instructing Codex to usespawn_agent(and route same-provider handoffs throughdelegate_taskinstead).felix-thinkingdata commentedon Nov 21, 2026
I can reproduce this in a fresh conversation on T3 Code Desktop 0.1.12-nightly.20261121.5024, macOS 26.2 (Apple Silicon). The parent and child session records both show T3 Code as the originator, Codex CLI 0.171.0, and model provider
openai_token_sharing.testand got a normal reply. The successful turn also showed startup warnings for the optionalcomputer-useandpinepaperMCP servers.agent_messageand failed. The parent then received anagent_messageand failed with the same error. The backend identified the rejected parameter asinputwithout naming the individual item.Redacted sequence (UTC, 2026-11-21):
Opening that same conversation in the standalone Codex desktop UI also reproduces the symptom in #34303 on macOS. The child is labeled “completed” there, while T3 labels it failed. The desktop UI shows the underlying sharing error and a separate banner saying that
openai_token_sharingis unavailable to continue the chat. The “completed” label is confusing given that both requests returned HTTP 400.Could T3 disable native subagent calls for managed sharing sessions until supported, or recover from the rejection so the parent can finish the task?