Repository navigation
Description
Summary
Sending a regular message with Astra in T3 Code repeatedly fails with subscription_sharing_unsupported_capability. Sol works in T3 Code. The reporter confirms that the same prompt with the same Astra model works when running Codex directly from the terminal.
This is occurring on T3 Code 0.1.1-nightly.20261018.3285 on Windows. Local protocol logs show two newly started Astra conversations failing after native subagent activity, followed by a text-only retry failing in the first conversation.
Area
apps/server — managed Codex / Connect with ChatGPT subscription-sharing integration.
Steps to reproduce
Reporter-observed sequence; the exact private prompt is omitted:
- Send regular messages using Sol in T3 Code; this works.
- Select Astra and send a regular message.
- Observe
subscription_sharing_unsupported_capability. - Run Codex directly in the terminal with the same prompt and the same Astra model; the reporter confirms this works.
The user-visible trigger is a regular message. The captured T3 Astra runs start native subAgentActivity internally before the rejection. A text-only follow-up in an affected conversation also fails, and a second newly started Astra conversation reproduces the child/parent failure sequence.
Expected behavior
The same prompt and Astra model should work in T3 Code as they do in terminal Codex. Internal subagent execution should use a mechanism compatible with the configured authentication route, and a child failure should not prevent ordinary follow-up messages.
Actual behavior
The Astra child fails, then its parent fails with the same provider rejection. A subsequent text-only follow-up also fails. All five captured error notifications have willRetry: false, type: invalid_request_error, and param: input; the corresponding turns end with status: failed.
Exact error supplied by the reporter:
{
"error": {
"message": "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.",
"type": "invalid_request_error",
"param": "input",
"code": "subscription_sharing_unsupported_capability"
}
}Impact
Frequent failures prevent the reporter from using Astra in T3 Code, even though the same prompt/model works in terminal Codex. An affected conversation also rejects ordinary text follow-ups.
Version or commit
0.1.1-nightly.20261018.3285, confirmed by the live T3 server and the affected Codex initialize request.
Environment
- Windows x64; Codex initialize response reports Windows
10.0.26300. - T3-managed Codex app-server initialize response reports
0.163.0. - Affected conversations:
gpt-6-astra;thread/startresults reportmodelProvider: openai_token_sharing. - Native children use Astra /
xhigh; the captured failed follow-up also uses Astra /xhigh. - Sol (
gpt-6.1-sol) works for the reporter in T3 Code. The investigation session uses Sol on the same subscription-sharing route and can run tools successfully. - Terminal Codex success with the same prompt and Astra model is reporter-confirmed. The terminal CLI version and authentication route were not independently captured, so this comparison does not isolate model selection from authentication/integration differences.
Logs or stack traces
Read-only local protocol evidence. All timestamps are UTC on 2026-10-18; identifiers and private message contents are omitted.
01:29:00.922 first Astra conversation starts; openai_token_sharing
01:29:30.284 parent: subAgentActivity started, gpt-6-astra / xhigh
01:29:32.760 child: subscription_sharing_unsupported_capability
01:29:43.631 parent: same error
01:33:04.070 parent: text-only follow-up, Astra / xhigh
01:33:05.929 follow-up: same error
01:35:39.246 second Astra conversation starts; openai_token_sharing
01:36:05.924 parent: subAgentActivity started, gpt-6-astra / xhigh
01:36:08.345 child: subscription_sharing_unsupported_capability
01:36:16.175 parent: same error
The outgoing Responses HTTP body was not captured, so the exact unsupported wire item is unconfirmed.
Related reports and proposed fix
- Connect with ChatGPT rejects Codex subagents and leaves the chat unable to continue #17679 tracks the same subscription-sharing error and child -> parent -> failed follow-up sequence, but is closed. This new report records the current Windows nightly recurrence and the reporter's Astra-versus-Sol and terminal-Codex comparison.
- fix(codex): disable agents for ChatGPT sharing #20270 proposes an additional native-agent compatibility restriction and is still open at filing time. It has not been tested here.
Workaround
Use Sol in T3 Code, or run the same prompt and Astra model directly with terminal Codex, both of which the reporter confirms work. A second new Astra conversation in T3 Code still failed in the captured logs.
No configuration, credentials, installed code, or conversation history was modified during this investigation.
Prepared with Codex assistance (GPT-6.1 Sol) from the reporter's description and read-only local protocol evidence. Raw logs, private prompts, credentials, local paths and conversation identifiers are omitted.
Activity
DannyMarkus commentedon Oct 20, 2026
Additional independent reproduction on Windows (2026-10-20), with a more specific rejection than the one in this issue.
Environment
modelProvider: openai_token_sharing)gpt-6-astra, reasoningmediumandxhighMinimal reproduction: Start a new T3 Code conversation with Astra/medium and send:
Antworte ausschließlich mit OK. Verwende keine Werkzeuge.("Reply only OK. Do not use tools."). Reproduces even with No project selected, no subagent request and no tool use in the user message. The turn fails before any assistant reply, with:Controls
codex.exe(0.156.1) invoked directly viacodex exec --model gpt-6-astra -c 'model_reasoning_effort="medium"' --sandbox read-only --skip-git-repo-check "Antworte ausschließlich mit OK. Verwende keine Werkzeuge."succeeds (OK).Redacted app-server trace of the failed T3 turn (UTC):
The T3
turn/startalso includes extensiveadditionalContextorchestration instructions andsandboxPolicy: dangerFullAccess, unlike the direct read-only CLI control. Neither is established as causal. The log doesn't contain the full upstream Responses request, so the component that insertstool_searchis still unconfirmed.Potentially useful distinction from the original report: here a brand-new, text-only Astra conversation fails without any observed native subagent activity. Please investigate why the T3-managed Codex app-server request advertises
tool_searchon the ChatGPT subscription-sharing route and whether that tool can be omitted for this route.Only redacted evidence included; no raw logs, internal paths, prompts beyond the minimal reproduction, IDs, credentials or private project information.
marketing-namou commentedon Oct 30, 2026
Removed — posted from the wrong account.
matt2102 commentedon Oct 30, 2026
Fresh repro on current stable (0.1.5) — and evidence the #17499 fix isn't effective
Hit the exact same failure today on a brand-new thread, on the current stable release (not a nightly), which suggests this isn't just a lingering nightly regression.
What happened
A new top-level Codex thread (model
gpt-6-astra, provideropenai_token_sharing) started a native Codex subagent (subAgentActivity, not a T3delegate_task) partway through its first turn. The spawned child thread failed immediately withsubscription_sharing_unsupported_capability; ~10s later the parent turn failed with the identical error.Repro sequence (UTC, from local protocol logs)
Both errors carry
"param":"input","willRetry":false, and the same message as in the issue description ("User subscription sharing currently supports only text, image, and file messages... Remove unsupported input items or use an API key instead.").Why I don't think the PR #17499 fix is landing
CodexManagedRuntime.tsonv0.1.5still sets the launch overrides from that PR:But the trace above shows native
subAgentActivityfiring anyway for anopenai_token_sharingsession, on Codex CLI0.156.1. The PR's own verification notes flagged this gap: "A live managed-provider request has not been verified." That appears to be exactly what's biting here — the config override doesn't seem to actually suppress native subagent dispatch in this Codex CLI build, so the original failure mode is unchanged.Environment
0.1.5(stable)0.156.1gpt-6-astra0.1.5Produced by Claude (Opus 4.8) via T3 Code triage (
t3 triage).juliusmarminge commentedon Nov 12, 2026
I tried to reproduce this on the current build and could not.
Commit 3b732f4 (origin/main), real Codex CLI 0.167.2. A full T3 run under Connect with ChatGPT (openai_token_sharing) is not possible on a worker (no first-party ChatGPT OAuth), so the provider rejection itself was not seen. Root-cause check: ran
codex execwith an empty CODEX_HOME, --ignore-user-config, --model gpt-6-astra, and main's exact managed launch args from CodexManagedRuntime.ts (model_provider=openai_token_sharing, features.api_key_model_discovery=true, features.multi_agent=false, features.multi_agent_v2=false). The provider base_url pointed at a loopback mock that served Codex's bundled model catalog (gpt-6-astra has multi_agent_version "v2") and recorded requests. The first /v1/responses request carried an additional_tools input item with acollaborationnamespace: spawn_agent, wait_agent, send_message, list_agents, followup_task, interrupt_agent. Re-running with-c agents.enabled=falseadded removed that namespace and nothing else. A run with a dummy MCP server also offered the agent tools but notool_search, so the tool_search variant in one comment was not reproduced. Failing test: one assertion that the managed launch args include agents.enabled=false, added to the existing case in apps/server/src/provider/CodexManagedRuntime.test.ts. All 4 parameterised cases fail on that assertion only.Closing as not planned. If it still happens for you, reply with the exact steps and the version you are on and it will be looked at again.