Skip to content
TheChatArchiveThe Chat Archive
DeepSeekdeepseek/deepseek-v4-pro· deepseekHugging 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. DeepSeek Assistant

    Let me start by understanding the repository structure and the issue. The issue is about a stale client_version fallback that causes 503 errors for newer models when the GitHub releases API is rate-limited.

    Let me explore the repository structure first.

  3. DeepSeek Assistant

    Let me find the actual app source files.

  4. DeepSeek Assistant

    Let me look at the specific files mentioned in the issue description.

  5. DeepSeek Assistant

    Now let me look at the key files. Let's start with the codex_version.py file.

  6. DeepSeek Assistant

    Let me just read the file directly.

  7. DeepSeek Assistant

    Now let me look at settings and the model_fetcher to understand the full flow.

  8. DeepSeek Assistant

    Now let me look at the model_fetcher and model_refresh_scheduler to understand the full flow.

  9. DeepSeek Assistant

    Now let me understand the structure better and look at tests.

  10. DeepSeek Assistant

    Let me look at the unit tests for codex_version.

  11. DeepSeek Assistant

    Now I have a clear picture of the issue. Let me create a script to reproduce the error, then implement the fix.

    First, let me look at the model_refresh_scheduler to understand the full flow.

  12. DeepSeek Assistant

    Now I have a full understanding of the issue. Let me implement the fix. The plan is:

    1. Add a secondary version source via npm registry (https://registry.npmjs.org/@openai/codex/latest) in codex_version.py
    2. When GitHub fails, try npm as a fallback
    3. Only fall back to the settings default when both sources fail

    Let me implement this:

  13. DeepSeek Assistant

    Now let me implement the fix. I'll add an npm registry fallback as a secondary version source.

  14. DeepSeek Assistant

    Let me open the file first.

  15. DeepSeek Assistant

    Now let me make the edits. First, add the npm registry URL constant:

  16. DeepSeek Assistant

    Let me try using replace instead:

  17. DeepSeek Assistant

    Now let me modify the get_version method to try npm before falling back to settings default:

  18. DeepSeek Assistant

    Now let me add the _fetch_latest_version_from_npm method after the _fetch_latest_version method:

  19. DeepSeek Assistant

    The file looks correct. Let me verify the full file and run the tests:

  20. DeepSeek Assistant

    Let me install the required packages and set up the environment:

  21. DeepSeek Assistant

    Let me check if there's a virtual environment or try installing from the project requirements.

  22. DeepSeek Assistant

    Let me check the pyproject.toml for the correct dependencies:

  23. DeepSeek Assistant

    Let me install the dev dependencies properly:

  24. DeepSeek Assistant

    Now let me run the tests:

  25. DeepSeek Assistant

    All tests pass. Let me also run the model_fetcher tests to make sure they still work:

  26. DeepSeek Assistant

    Let me run the full unit test suite to check for regressions:

  27. DeepSeek Assistant

    All 1889 tests passed. Let me verify the final state of the changed file:

  28. DeepSeek Assistant

    Now let me create a quick reproduction script to verify the fix works end-to-end, and then check the diff:

  29. DeepSeek Assistant

    Let me write a quick script to verify the npm fallback works:

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