Repository navigation
Description
What happened
My Codex threads on one machine started compacting constantly, several times within a few minutes, even in brand-new threads. Claude threads on the same machine and Codex on my other machine were fine.
Diagnosis
T3 launches managed Codex with auth={…,refresh_interval_ms=0} (apps/server/src/provider/CodexManagedRuntime.ts, unchanged on main). In Codex, 0 means no interval: login/src/auth/external_bearer.rs resolve() reuses the first helper token forever (None => true). Only refresh() re-runs the helper, and only the Responses 401-recovery path calls it, for its own auth manager. The catalog request (OpenAiModelsEndpoint::list_models) keeps its own cached token and has no 401 recovery.
Once the launch token expires, every /v1/models refresh returns 401. After the 5-minute cache TTL, new turns hit Unknown model gpt-6.1-sol and use fallback metadata: 272k window (258,400 usable) and supports_search_tool=false. Every MCP/app tool schema then goes inline on each request (~215k tokens here). That overhead survives compaction, so threads compact after nearly every tool call.
The credential itself is fine: the current token from the same __managed-chatgpt-token helper gets 200 from GET /v1/models, including gpt-6.1-sol metadata. Proxies, env overrides and ~/.codex/auth.json (unused in managed mode) are ruled out. The same code is in Codex 0.166.0, 0.167.0 and main.
Likely fix: set refresh_interval_ms well under the token lifetime (e.g. 300000, as Codex's own command-auth tests use). Untested here (verifying needs a run of over an hour). Catalog retry on 401 is a separate upstream Codex improvement.
Steps to reproduce
- Desktop app, Codex provider in managed (Connect with ChatGPT) mode, model gpt-6.1-sol, app/MCP integrations enabled.
- Leave the Codex app-server running until the managed token it launched with expires. Here that was ~30 min after launch, because the process inherited an already-issued token.
- Make sure nothing else (e.g. the Codex desktop app) rewrites
~/.codex/models_cache.jsonwithin 5 minutes. Then start a new Codex thread and send a short prompt. - Codex logs a catalog 401 and
Unknown model … fallback model metadata. The first request reports ~230k input tokens and a 258,400 window, and the thread compacts every few tool calls.
Version
0.1.9-nightly.20261109.4443
Environment
macOS 27.2 arm64, T3 Code (Nightly) desktop with local server, Codex app-server 0.163.0, provider openai_token_sharing, gpt-6.1-sol
Evidence
# one Codex app-server process, launched at T+0
T+23m last successful catalog fetch (models_cache.json fetched_at)
T+30m WARN get_model_info: Unknown model gpt-6.1-sol is used. This will use fallback model metadata.
T+30m ERROR failed to refresh available models: unexpected status 401 Unauthorized: Unknown error (every refresh after this)
T+80m feedback_tags auth_401_error_code="token_expired" auth_recovery_outcome="recovery_succeeded" (Responses path)
T+80m+ ERROR failed to refresh available models: unexpected status 401 Unauthorized (catalog still failing)
sessions in that process first request window compactions
before catalog 401s ~25k 475,000 0
after (5 sessions) 232k-400k 258,400 3-18 each
after T3 restart + workaround: 25.4k, 475,000, 0 catalog errorsRelated issues
#27939 (closed for the outdated-runtime cause; maintainer asked to track the catalog-refresh 401 separately, and 3 of its comments describe it). #25891 (same compaction symptom, undiagnosed). #24536 (expired-token family). #29946/#29950 fix Responses-path renewal only, not the catalog request.
Fix applied or workaround
Restarting T3 gets a fresh token but the problem recurs. Durable workaround applied: top-level model_catalog_json = "<saved {\"models\":[…]} file>" in ~/.codex/config.toml. Codex then uses StaticModelsManager and never calls /v1/models. Downside: the model list stays frozen until the file is re-saved.
Filed by
Claude Code (claude-opus-5-5) with a GPT-6.1-Sol subagent; triage playbook followed manually, not via t3 triage
Activity
everywhereautorepair-hue commentedon Nov 11, 2026
Windows corroboration and a working workaround, reported with the affected user's authorization.
I checked the local Codex session telemetry and the prior repair record. The historical symptom matches this issue:
The earlier repair switched the provider from managed to existing, pointing to the Codex desktop executable and using its existing ChatGPT sign-in. Its recorded verification was 25,715 first-request input tokens, model_context_window=475000, with code mode enabled.
Current state, checked on 2026-11-11 UTC:
A practical caveat to the workaround: the desktop executable path included an update-specific directory. That executable later disappeared, preventing Codex from starting in T3. Repointing existing mode to T3's already-installed Codex 0.166.0 executable restored the connection while retaining the existing login and the 475000 usable window. No return to managed mode was needed.
I have not independently reproduced or validated the exact token-renewal root cause proposed above, and have not tested a managed-mode code fix over a token-expiry interval. This comment corroborates the observed fallback/startup symptom and the existing-mode workaround. No credentials, account identifiers, private prompts, or raw session logs are attached.
Filed by Codex (GPT-6.1 Sol High) on the affected user's behalf.
iamsoft-tech commentedon Nov 14, 2026
Windows corroboration, with a different visible symptom.
Environment: Windows 11, T3 Code (Beta) desktop 0.1.6 with local server, Codex in managed "Connect with ChatGPT" mode (
openai_token_sharing), Codex 0.167.0 (version recorded in the affected rollouts), models gpt-6-astra and gpt-6.1-sol.What we saw: instead of constant compaction, every new Codex turn failed with
Incomplete response returned, reason: max_output_tokens, with zero token usage recorded. It read as "Codex hit its output limit", which sent us in the wrong direction for a while.Evidence from the Codex log database (
logs_2.sqlite, targetcodex_models_manager), 8 to 14 November:failed to refresh available models: 401came 23 to 41 minutes after the process started, followed byUnknown model ... fallback model metadata.comp_hashinturn_context.Pull request 33713 applied cleanly to a fork based on
09a54f01bc.CodexChatGptAuth.test.tspasses there.CodexManagedRuntime.test.tspasses 2 of 4 cases on Windows with or without the change (the other 2 fail on symlink creation, unrelated). We have not run the patched build past a token expiry.Workaround in use:
setupMode: "existing"with a stable Codex executable path.Investigated and written with Claude (Fable 5.2) in T3 Code, posted at the user's request.
asmither commentedon Nov 14, 2026
Note
🤖 Claude Opus 5.5 responding on behalf of asmither
This still happens on 0.1.10-nightly.20261113.4643 (macOS 27.2 arm64, managed Codex app-server 0.166.0). It affects gpt-6-astra as well as gpt-6.1-sol.
What I saw:
delegate_task(gpt-6-astra and gpt-6.1-sol, reasoning high) began their first request at 264k–310k input tokens.codex execon the same machine, run at the same time, started at about 19k.~/.codex/config.tomldid not help.codex app-serverprocess (T3 respawns it) cleared the problem. It returned in later runs, so I killed the process before every run.I did not check the catalog 401 in the logs, so the cause above is not independently confirmed here. The symptoms, the recovery after a restart and the recurrence all match it.
coreylubo commentedon Nov 14, 2026
Note
Claude Opus 5.5 responding on behalf of coreylubo
Another macOS reproduction. The cost here was large: within about 5 hours of the weekly reset, this bug had used at least 82% of the new weekly Codex limit, because nothing stopped the loop.
Setup: T3 Code (Beta) 0.1.9 desktop with local server, macOS 27.2 arm64. Managed Codex app-server 0.167.0. Five
delegate_taskreview children on gpt-5.6-terra (medium).What the logs show (
~/.codex/logs_2.sqlite)failed to refresh available models: unexpected status 401 Unauthorizedrecurs from 2026-11-13 08:55Z onward. That is the earliest row the log keeps.Unknown model gpt-5.6-terra is used. This will use fallback model metadata.appears 418 times over the same period.What it cost
Workarounds applied
model_catalog_jsonworkaround from the report above.codex debug modelsthen lists gpt-5.6-terra withsupports_search_tool: true.The
delegate_taskchildren had no timeout, token budget or compaction cap, so this ran unattended. That part is filed as issue #36982.Falkicon commentedon Nov 15, 2026
Windows corroboration on 0.1.9 (Codex 0.167.2, managed, gpt-6.1-sol), with two details the thread doesn't have yet:
delegate_taskchildren. Five threads, including one started directly by the user, compacted 391–1,735 times each. The longest ran about 24 hours until the account hit its usage limit.Logs show the same
401 UnauthorizedandUnknown model … fallback model metadatapair in every affected thread. A Codex Desktop session on the same machine stayed at 475,000 with no compactions.Investigated with Claude (Opus 5.5) in T3 Code, posted at the user's request.
xuli500177 commentedon Nov 17, 2026
Windows confirmation on Codex 0.169.0 — please prioritize human review and an official fix
I am also affected in managed ("Connect with ChatGPT") mode. This makes unattended, long-running work unreliable: a healthy top-level thread can fall into repeated compaction/read cycles without advancing, wasting usage until I notice and stop it. Restarting or sending another message is not a satisfactory remedy for unattended work. I want to keep using managed mode, not maintain a private patch or switch authentication modes permanently.
Sanitized local evidence from November 17, 2026:
0.1.10-nightly.20261116.4787, Codex0.169.0,gpt-6.1-sol. The same run's reported context window changed from 475,000 to 258,400. After two compactions, history estimates were about 25.9k/24.5k, but the next full requests had 291,703/289,838 input tokens, immediately triggering compaction again. Those history estimates and request-input measurements are different metrics, not proof of an exact tool-schema size.loaded cache file, thencache is stale ... cache_ttl_secs=300,models cache: no usable cache entry, andmodel catalog refresh after auth change failed or timed out, followed by unknown-model fallback. This incident's captured trigger was timeout/cache ineligibility; I am not retroactively attributing it to an unobserved 401.0.1.11-nightly.20261117.4838with managed Codex0.169.0, one running app-server logged repeated catalog 401 Unauthorized responses. Its actual launch arguments still specifiedrefresh_interval_ms=0.gpt-6.1-sol,context_window=500000, andsupports_search_tool=true. Helper retrieval took about 116–147 ms. This supports a stale-auth/cache-path problem; it does not independently prove the precise expiry reason or validate a proposed patch across token expiry.api.openai.comrouted through the intended overseas VPS, not DIRECT.Could a maintainer please take ownership of the human-review step for #33713 and #31903, or explain what remaining technical change or evidence is needed?
I am not asking to bypass authentication/security review or claiming that either patch alone fixes every timeout or early-token-rejection case. I am asking for a prioritized, official resolution: if these approaches are correct, please review and merge the appropriate changes; if not, please identify the preferred fix and a practical verification path. In particular, what sanitized evidence can an affected user provide without publishing OAuth flows, tokens, or private conversations?
Several independent users above already report the same default-managed-mode failure, including very large unattended usage losses. Users should not have to patch packaged authentication code themselves to make the default mode safe for long-running tasks. If a full fix needs more time, an official warning or supported interim mitigation would help.
Posted at the affected user's explicit request with AI assistance. No credentials, account identifiers, raw session exports, or private project content are included. No local patch has been applied, so this is corroboration of the failure, not a claim that either proposed fix has passed on this installation.
realsamrat commentedon Nov 19, 2026
Confirmed on
0.1.11-nightly.20261119.4941: a managed Codexdelegate_taskchild hit fallback metadata mid-process and looped through 190 compactions over 3h16m until interrupted.Environment
0.1.11-nightly.20261119.4941desktop (local server), macOS 27.0 arm64.openai_token_sharing, shadow Codex home), app-server0.170.0,gpt-6.1-sol(highreasoning), ~25 MCP servers (some with hundreds of tools).v0.1.11-nightly.20261119.4941andmainstill launch managed Codex withrefresh_interval_ms=0(apps/server/src/provider/CodexManagedRuntime.ts:26). PR fix(server): managed Codex renews the token its model catalog uses #33713 is still open.What happened (2026-11-19)
delegate_taskchild (code-review council member) ran 16:18–19:35 UTC (durationMs: 11,799,858, statusinterrupted). Its first request was 264,828 input tokens against a 258,400 window. It ran 190 compactions in one turn, stayed near ~265k input tokens after each, re-ran the same brief-file read command ~160+ times, and produced no final answer.gpt-6.1-solnormally at 20:46 and 21:01 UTC, then fell back on a new thread at 21:14 UTC, confirming mid-life degradation.Log evidence
The
/responsespath recovers its token, but the turn stays on fallback metadata for the whole turn. Becauselogs_2.sqlitedoes not retain rows for every case, the catalog 401 is not logged for all 7 incidents.Maintainer notes and workaround
Found via the
t3 triageplaybook. Investigated by Claude Code (claude-opus-5-5); comment drafted by Gemini 4 Neon (Antigravity).jankalasnikov47 commentedon Nov 20, 2026
Another macOS data point (T3 Code Beta 0.1.10 desktop with local server, macOS 26.5 arm64, managed Codex 0.166.0, gpt-6.2-astra and gpt-6.2-sol), plus one measurement this thread does not have yet: most of the fallback overhead is the
codex_appscatalog.Where the tokens go
One-word prompt through
codex execwith the managed 0.166.0 binary and gpt-6.2-astra. Fallback was forced with amodel_catalog_jsonthat lacks the model.features.apps=falseThe
codex_appstool cache on this machine holds 889 tools. With[features] apps = falsein~/.codex/config.toml, a first request under fallback is about 72k instead of over the 258,400 window. The thread still runs on fallback metadata (generic prompt, 258,400 window, no tool search) and loses the ChatGPT connectors, so this is a lighter stopgap than the staticmodel_catalog_jsonabove, not a fix.What it looked like here
Heisenberg77528 commentedon Nov 21, 2026
Another macOS corroboration on T3 Code Beta 0.1.11 (still launching managed Codex with
refresh_interval_ms=0), withgpt-6.2-soland an additional compounding trigger when Codex Desktop runs alongside T3.Environment
0.1.11desktop with local serversetupMode: "managed",openai_token_sharing), Codex app-server0.166.0, modelgpt-6.2-solcodex-cli 0.171.0-alpha.13) also running on the same machine, sharing~/.codex/models_cache.jsonObserved behavior (2026-11-20 UTC)
gpt-6.2-solthreads started healthy withmodel_context_window = 475,000.Model metadata for 'gpt-6.2-sol' not found. Defaulting to fallback metadataandUnknown model gpt-6.2-sol is used. This will use fallback model metadata.model_context_windowdropped mid-thread from475,000to258,400(272,000 × 95%).188,765to366,751(+178k inline tool-schema overhead once fallback disabled tool search), immediately exceeding258,400and triggeringcontextCompactionon the next turn. A second thread similarly jumped to336,319against258,400and compacted immediately.~/.codex/logs_2.sqlite:failed to refresh available models: unexpected status 401 Unauthorized: Unknown error.0.171.0) refreshes/backend-api/codex/models?client_version=0.171.0every ~4.5 minutes and overwrites the shared~/.codex/models_cache.json. T3's managed0.166.0then logscache version mismatch (expected_version="0.166.0", cached_version=Some("0.171.0")), cannot reuse the cache, and immediately hits the 401 refresh failure.0.1.11app.asarthat managed Codex is still spawned withrefresh_interval_ms=0.Adding this data point to help prioritize review/merge of #33713 (and #31903).
(Investigated and drafted with AI assistance at the user's request; no credentials, account IDs, or private prompts included.)