Skip to content
TheChatArchiveThe Chat Archive
QwenQwen/Qwen3.6-27B· alibabaHugging Face ibragim-bad/swe_rebench_07_2026_trajectories

ISSUE DESCRIPTION Stale 'clientversion' fallback causes 503 'noplansupportformodel' for…

  1. User

    ISSUE DESCRIPTION

    Stale 'client_version' fallback causes 503 'no_plan_support_for_model' for newer models (e.g. gpt-5.5) when GitHub releases API rate-limits

    Summary

    When app/core/clients/codex_version.py cannot fetch the latest codex release from api.github.com/repos/openai/codex/releases/latest (e.g. anonymous-rate-limited with HTTP 403), it logs:

    GitHub releases API returned HTTP 403
    GitHub fetch failed and no cached version; falling back to settings default 0.101.0
    

    and falls back to Settings.model_registry_client_version (default 0.101.0). The model registry refresh (app/core/openai/model_refresh_scheduler.py → clients/model_fetcher.fetch_models_for_plan) then asks upstream /codex/models?client_version=0.101.0. Upstream gates newer model slugs behind newer client versions, so the response excludes e.g. gpt-5.5.

    As a result, ModelRegistry.model_plans never gets a gpt-5.5 entry, _filter_accounts_for_model in modules/proxy/load_balancer.py:1168 returns an empty set, and every Codex request for gpt-5.5 is rejected with:

    proxy_error_response status=503 code=no_plan_support_for_model
      message=No accounts with a plan supporting model 'gpt-5.5'
    

    …even though the actual Codex CLI is on 0.130.0 and the account's ChatGPT subscription does support the model (calling /backend-api/codex/models?client_version=0.130.0 through the LB returns 200 with the model present).

    Reproduction

    1. Run ghcr.io/soju06/codex-lb:1.17.0 on a host where anonymous GitHub API requests are 403'ed.
    2. Connect a current Codex CLI (e.g. @openai/codex@0.130.0) configured with model = \"gpt-5.5\".
    3. Observe startup log line:
      • GitHub fetch failed and no cached version; falling back to settings default 0.101.0
    4. Every POST /backend-api/codex/responses returns 503 with code no_plan_support_for_model.

    Setting CODEX_LB_MODEL_REGISTRY_CLIENT_VERSION=0.130.0 and recreating the container fully resolves the symptom.

    Suggested fixes

    A few low-effort options, any one would help:

    1. Bump the baked-in default model_registry_client_version on each release so it tracks the recent @openai/codex version (or read it from a generated file at build time).
    2. Add a secondary version source. npm view @openai/codex version against https://registry.npmjs.org is not rate-limited the way the GitHub anonymous API is, and a static fetch of https://registry.npmjs.org/@openai/codex/latest returns JSON containing \"version\".
    3. Cache the fetched version on disk (e.g. inside the data volume) so a single successful lookup survives container restarts and survives transient 403s for the cache TTL.
    4. Honor the client's own client_version query string as a hint for which model list to refresh (only when greater than the configured default), so a newer client effectively bootstraps the registry.

    Workaround

    For anyone hitting this, pass -e CODEX_LB_MODEL_REGISTRY_CLIENT_VERSION=<your-codex-cli-version> to docker run:

    docker run -d \\
      -e CODEX_LB_DASHBOARD_BOOTSTRAP_TOKEN=... \\
      -e CODEX_LB_MODEL_REGISTRY_CLIENT_VERSION=0.130.0 \\
      -p 2455:2455 -p 1455:1455 \\
      -v codex-lb-data:/var/lib/codex-lb \\
      ghcr.io/soju06/codex-lb:1.17.0
    

    Environment

    • codex-lb image: ghcr.io/soju06/codex-lb:1.17.0
    • Codex CLI: @openai/codex@0.130.0
    • Host: macOS, Docker Desktop / Colima
    • Account plan: pro (3 accounts, all plan_type=pro in store.db)

    Related: #480 ("Model metadata for gpt-5.5 not found. Defaulting to fallback metadata") looks like the same underlying cause.

    ADDITIONAL ADVICE

    Since you are given a git repository, you can use git commands to simplify your work. For example, if you made a mistake and want to revert your changes, you can use git checkout <file> to restore the file to its original state. You can also reset all changes in the repository using git reset --hard command. Additionally, you can use git stash and git stash pop to temporarily save your changes and restore them later. Finally, you can see the changes that you've made (which will be submitted when you call submit) using git status or git diff commands. However you don't need to use git add or git commit before submitting your changes. In fact, submit only submits currently unstaged changes because it uses git diff to get the changes that need to be submitted.

    CHECKLIST

    Before submitting your solution, please go over the following checklist and make sure you've done everything:

    • If an error was reported in the issue description, I have successfully reproduced it.
    • If an error was reported in the issue description, I have confirmed that my fix resolves the error.
    • I have thought about edge cases and made sure my fix handles them as well.
    • I have run existing tests in the repository that might have been affected by the change I made and confirmed that they pass. I want you to list every bullet from this checklist and write your reasoning for why you think you did it or didn't need to.

    Repository has been uploaded and your shell is currently at the repository root. Time to solve the issue!

    (Current directory: /codex-lb, current file: none) bash-$

  2. Qwen Assistant

    I'll start by exploring the repository structure to understand the codebase and then locate the relevant files mentioned in the issue.

  3. Qwen Assistant

    Let me explore the directory structure more systematically.

  4. Qwen Assistant

    Now let me look at the key files mentioned in the issue:

  5. Qwen Assistant

    I need to use the proper syntax for opening a file.

  6. Qwen Assistant

    Now let me look at the model refresh scheduler and model fetcher:

  7. Qwen Assistant

    Now I understand the issue. Let me check the tests to understand how the existing code is tested:

  8. Qwen Assistant

    Now I have a clear understanding of the issue. Let me check what the NPM registry approach would look like and then implement a fix. The issue suggests several approaches - I'll implement option 2 (secondary version source from NPM registry) as it provides a robust fallback:

  9. Qwen Assistant

    Let me continue working on the fix. I'll implement the NPM registry fallback as suggested in the issue.

  10. Qwen Assistant

    Now let me create a reproduction script to understand the issue better, then implement the fix:

  11. Qwen Assistant

    I need to use the virtual environment that's set up in the repository.

  12. Qwen Assistant

    I've confirmed the issue. Now let me implement the fix. According to the issue, I'll implement option 2: add a secondary version source using the NPM registry. This is a good approach because:

    1. The NPM registry (https://registry.npmjs.org) is less likely to be rate-limited
    2. It provides the latest published version of @openai/codex
    3. It's a static JSON endpoint that's easy to parse

    Let me implement the fix:

  13. Qwen Assistant

    Now I'll implement the fix by adding an NPM registry fallback. The strategy is:

    1. First try GitHub releases API (existing behavior)
    2. If GitHub fails, try the NPM registry as a secondary source
    3. If both fail, fall back to stale cache or settings default
  14. Qwen Assistant

    Now let me run the reproduction script again to verify the fix works:

  15. Qwen Assistant

    All my tests pass. Now let me run the existing unit tests to make sure I haven't broken anything:

  16. Qwen Assistant

    All existing tests pass. Let me also check if there are any tests related to the model fetcher that might be affected:

  17. Qwen Assistant

    All related tests pass. Let me also run the full test suite to make sure nothing else is broken:

  18. Qwen Assistant

    I need to continue checking the test results to see if all tests pass.

  19. Qwen Assistant

    All 1889 unit tests pass (with 39 skipped that are expected). Now let me verify the file I modified looks correct:

  20. Qwen Assistant

    Let me also think about edge cases and add more comprehensive tests:

  21. Qwen Assistant

    All edge case tests pass. Now let me clean up the temporary test files and verify the git diff:

  22. Qwen Assistant

    Let me run the existing unit tests one more time to confirm everything passes:

    <tool_call> <function=bash_terminal> <parameter=command> cd /codex-lb && .venv/bin/python -m pytest tests/unit/test_codex_version.py tests/unit/test_model_fetcher.py tests/unit/test_model_refresh_scheduler.py -v </tool_call>

  23. Qwen Assistant

    I need to run the command properly.

Responses were produced in different, uncontrolled contexts (system prompts, settings, prior turns). This is not a benchmark.