🤖 fix: reconcile GPT-5.6 Codex OAuth context caps with the Codex catalog

[ThomasK33]

Summary

The Codex OAuth context cap for the GPT-5.6 family (gpt-5.6, gpt-5.6-sol, gpt-5.6-terra, gpt-5.6-luna) goes from 372K to 272K, matching the first-party Codex catalog. API-key requests keep the public 1.05M window.

Background

#4683 asked where #3730's 372K came from before changing it.

• [openai] 🤖 fix: use 372K GPT-5.6 OAuth context #3730 (merged 2026-07-15) says it copied the openai/codex catalog, which "lists context_window: 372000 for Sol, Terra, and Luna". That PR has no discussion of observed Codex behavior and no deliberate override.
• Catalog history (codex-rs/models-manager/models.json):
  • c38c30ef (2026-07-14): Sol/Terra/Luna context_window: 372000, max_context_window: 372000.
  • 2eee483e (Raise the GPT-5.6 maximum context window openai/codex#39102, "Raise the GPT-5.6 maximum context window", 2026-08-17): context_window: 272000, max_context_window: 872000.
  • The pin the repo already cites (04fc75ad) and main (checked 2026-09-26) both still have 272000 / 872000.

So 372K came only from an older catalog. This PR uses the default context_window, the same convention as GPT-5.5 and the GPT-6 Astra/Sol/Luna entries (#4259, #4684).

Validation

The routing and meter expectations were updated first and failed on main: codexOAuth.test.ts (GPT-5.6 family overrides), contextLimit.test.ts (OAuth-routed effective limit per tier), and tokenMeterUtils.test.ts (OAuth meter max and percentage for Sol). The API-key → 1.05M assertions in those files are unchanged and still pass.

Pre-fix failures

Expected: 272000
Received: 372000
(fail) codexOAuth model gating > allows the GPT-5.6 family through Codex OAuth without requiring it
(fail) calculateTokenMeterData > uses the Codex OAuth cap for GPT-5.6 token meter percentages
(fail) getEffectiveContextLimit > caps the GPT-5.6 family at each tier's Codex OAuth context window
 36 pass
 3 fail

Risks

Low. Only direct OpenAI requests routed through Codex OAuth are affected. They now start limit-driven compaction at 272K instead of 372K, which is the documented default window. API-key, gateway and Coder routes are unchanged.

Fixes #4683

---

Generated with xum • Model: anthropic:claude-opus-5-5 • Thinking: high

[ThomasK33]

@codex review

[ThomasK33]

@codex security review

[chatgpt-codex-connector]

Codex Review Summary

This comment shows the latest Codex review activity on this pull request.

Review	Status	Commit	Review trigger
📝 Code Review	✅ Completed 2026-09-26T19:03:15.910407Z	12aebc0	Manual request
🔒 Security Review	✅ Completed 2026-09-26T19:02:58.437731Z	12aebc0	Manual request

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

• Open a pull request for review
• Mark a draft as ready
• Comment "@codex review" or "@codex security review".

Codex reacts with 👀 while any review is running, comments if it has suggestions, and reacts with 👍 once all reviews finish with no findings.

[chatgpt-codex-connector]

🛡️ Codex Security Review

Security review completed. No security issues were found in this pull request.

Reviewed commit: 12aebc028f

View security finding report

Only the user who started this review can view the report in Codex.

ℹ️ About Codex security reviews in GitHub

This is an experimental Codex feature. Security reviews are triggered when:

• You comment "@codex security review"
• A regular code review gets triggered (for example, "@codex review" or when a PR is opened), and you’re opted in so security review runs alongside code review

Once complete, Codex will leave suggestions, or a comment if no findings are found.

[chatgpt-codex-connector]

Codex Review: Didn't find any major issues. What shall we delve into next?

Reviewed commit: 12aebc028f

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

• Open a pull request for review
• Mark a draft as ready
• Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".