ISSUE DESCRIPTION Stale 'clientversion' fallback causes 503 'noplansupportformodel' for…
- 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.pycannot fetch the latest codex release fromapi.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 0.101.0and falls back to
Settings.model_registry_client_version(default0.101.0). 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_plansnever gets agpt-5.5entry,_filter_accounts_for_modelinmodules/proxy/load_balancer.py:1168returns an empty set, and every Codex request forgpt-5.5is 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
0.130.0and the account's ChatGPT subscription does support the model (calling/backend-api/codex/models?client_version=0.130.0through the LB returns 200 with the model present).Reproduction
- Run
ghcr.io/soju06/codex-lb:1.17.0on a host where anonymous GitHub API requests are 403'ed. - Connect a current Codex CLI (e.g.
@openai/codex@0.130.0) configured withmodel = \"gpt-5.5\". - Observe startup log line:
GitHub fetch failed and no cached version; falling back to settings default 0.101.0
- Every
POST /backend-api/codex/responsesreturns 503 with codeno_plan_support_for_model.
Setting
CODEX_LB_MODEL_REGISTRY_CLIENT_VERSION=0.130.0and recreating the container fully resolves the symptom.Suggested fixes
A few low-effort options, any one would help:
- Bump the baked-in default
model_registry_client_versionon each release so it tracks the recent@openai/codexversion (or read it from a generated file at build time). - Add a secondary version source.
npm view @openai/codex versionagainsthttps://registry.npmjs.orgis not rate-limited the way the GitHub anonymous API is, and a static fetch ofhttps://registry.npmjs.org/@openai/codex/latestreturns JSON containing\"version\". - 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.
- Honor the client's own
client_versionquery 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>todocker 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:1.17.0Environment
- 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, allplan_type=proinstore.db)
Related: #480 ("Model metadata for
gpt-5.5not 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 usinggit reset --hardcommand. Additionally, you can usegit stashandgit stash popto temporarily save your changes and restore them later. Finally, you can see the changes that you've made (which will be submitted when you callsubmit) usinggit statusorgit diffcommands. However you don't need to usegit addorgit commitbefore submitting your changes. In fact,submitonly submits currently unstaged changes because it usesgit diffto 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-$
- Run
Assistant
Let me start by understanding the repository structure and the issue. The problem is:
- When
app/core/clients/codex_version.pycannot fetch the latest codex release from GitHub API (rate-limited with 403), it falls back to a hardcoded default0.101.0 - This old version causes the model registry to miss newer models like
gpt-5.5 - This results in 503 errors for those models
The suggested fixes include:
- Bump the baked-in default
model_registry_client_version - Add a secondary version source (npm registry)
- Cache the fetched version on disk
- Honor the client's own
client_versionquery string
Let me explore the codebase first.
- When
Assistant
Let me look at the key files mentioned in the issue
Assistant
Let me just run one command at a time.
Assistant
Let me read the key files: codex_version.py and model_fetcher.py
Assistant
Let me use the bash_terminal to cat the file.
Assistant
Now let me look at the model_fetcher.py and the settings.
Assistant
Now let me find the settings file to see the default value for
model_registry_client_version.Assistant
Let me look at the settings file to understand the configuration better
Assistant
Let me look for existing tests related to this functionality
Assistant
Let me search for tests related to codex_version specifically.
Assistant
Let me look at the unit test for codex_version
Assistant
Now I have a good understanding of the codebase. Let me look at the structure more closely and plan my implementation.
The issue is clear:
- GitHub API rate-limits anonymous requests (403), causing fallback to
0.101.0 - This old version means upstream doesn't return newer models like
gpt-5.5 - Leading to 503 errors
My plan: Add npm registry as a secondary version source AND add disk caching so a successful lookup persists across container restarts. This addresses both options 2 and 3 from the suggested fixes.
Let me first look at the directory structure to understand where to store the cache:
- GitHub API rate-limits anonymous requests (403), causing fallback to
Assistant
Let me now implement the solution. I'll modify
codex_version.pyto add npm registry fallback and disk caching. Let me first check what's available for async file I/O:Assistant
Now let me implement the changes. I'll modify
codex_version.pyto add npm registry fallback and disk caching.Assistant
Now I'll implement the changes. Let me create the updated `codex_version
Assistant
Let me verify the file and then run the existing tests to see if they pass:
Assistant
Good. Now let me run the existing unit tests:
Assistant
Let me install the test dependencies:
Assistant
Let me check if there's a requirements file or if the project uses poetry/pipenv.
Assistant
Let me check pyproject.toml for test dependencies
Assistant
Let me check if there's a virtual environment
Assistant
Let me use the virtual environment to run the tests.
Assistant
I see the issue - the disk cache from other tests is polluting the results. Let me simplify the approach: just add npm registry as a secondary version source without disk caching. The npm registry is not rate-limited the way GitHub anonymous API is, so this alone solves the problem
Assistant
Now let me run the tests again:
Assistant
All 11 tests pass. Let me also run the related tests to make sure nothing is broken:
Assistant
Let me run all unit tests to make sure nothing else is broken:
Assistant
All 1889 unit tests passed with 0 failures. Let me now verify the npm registry endpoint works correctly in
Assistant
The npm registry returns
"version": "0.144.5"which is a valid version string matching the regex pattern. Let me also clean up any disk cache file left from the earlier test runs:Assistant
Let me run the codex_version tests once more to confirm everything is clean:
Assistant
All 11 tests pass. Let me verify the final state of the changed file:
Other models, same or similar prompt
Responses were produced in different, uncontrolled contexts (system prompts, settings, prior turns). This is not a benchmark.
Identical first prompt
Qwen/Qwen3.6-27BCompare side by side →
Qwen/Qwen3.6-27BCompare side by side →
Qwen/Qwen3.6-27BCompare side by side →
Qwen/Qwen3.6-27BCompare side by side →
Qwen/Qwen3.6-27BCompare side by side →
- xiaomi/mimo-v2.5-proCompare side by side →
- xiaomi/mimo-v2.5-proCompare side by side →
- xiaomi/mimo-v2.5-proCompare side by side →
- xiaomi/mimo-v2.5-proCompare side by side →
- gpt-5.6-solCompare side by side →
- gpt-5.6-solCompare side by side →
- gpt-5.6-solCompare side by side →