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 issue is about a stale fallback for
client_versioninapp/core/clients/codex_version.py. When GitHub releases API is rate-limited (returns 403), the system falls back to a default0.101.0which is too old and causes newer models likegpt-5.5to be rejected.Let me explore the repository structure first.
Assistant
Let me look at the key files mentioned in the issue.
Assistant
Let me look at the key files:
Assistant
The
opencommand needs to be invoked via the bash terminal. Let me use the correct approach.Assistant
Now let me look at the settings file to see the default for
model_registry_client_version:Assistant
Let me see the context around line 206 in settings.py
Assistant
Now let me look at how
client_versionis used in the model fetcher:Assistant
Let me scroll down to see the rest of the function:
Assistant
Now let me look at the existing tests for codex_version
Assistant
Let me see the rest:
Assistant
Let me also check related scripts and the cache invalidation mechanism
Assistant
Now I have a clear picture. Let me implement the fix. I'll add an npm registry fallback as a secondary version source (suggested fix #2). This is the most robust approach since the npm registry is not rate-limited the way the GitHub anonymous API is.
Let me first run the existing tests to make sure they pass before making changes:
Assistant
Let me install the missing test dependencies:
Assistant
Let me run the test again:
Assistant
Let me install all project dependencies:
Assistant
Now let me run the tests:
Assistant
All existing tests pass. Now let me implement the fix. I'll add an npm registry fallback as a secondary version source.
Assistant
I need to use the bash terminal for the
opencommand:Assistant
Now let me implement the fix. I'll modify the
_fetch_latest_versionto try GitHub first, then npm as a secondary source, and update theget_versionfallback chain:Assistant
Now let me modify
_fetch_latest_versionto try npm as a fallback when GitHub fails, and also update the fallback messages inget_version:Assistant
Now let me also update the fallback log messages to be more accurate:
Assistant
Let me use
replaceinstead:Assistant
Now update the final fallback message too:
Assistant
Let me verify the final state of the file:
Assistant
Now let me run the existing tests to see if they still pass:
Assistant
I see the issue - I accidentally dropped
_VERSION_REwhen editing. Let me fix that:Assistant
Now let me run the tests again:
Assistant
All existing tests pass. Now let me also verify the model_fetcher tests still pass:
Assistant
Let me also run model_refresh_scheduler and model_registry tests:
Assistant
Let me also check if there are any other files referencing the old log messages or behavior that might need updating:
Assistant
Good, no other references. Let me run a wider set of tests to make sure nothing is broken:
Assistant
All tests pass. Let me verify the final state of my changes:
Assistant
The changes look clean and correct. Let me also verify the Python syntax is valid:
Assistant
Let me also run a broader test to make sure nothing else is affected:
Assistant
All 45 tests pass. Let me do a final review of the complete 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 →