test: replace deprecated gpt-5-codex with gpt-5.3-codex

[yuneng-berri]

TLDR

Problem this solves:

• test_openai_gpt_5_codex_reasoning fails on every run
• OpenAI deprecated gpt-5-codex, so the API rejects the request

How it solves it:

• points the test at gpt-5.3-codex, the newest codex model

Relevant issues

Linear ticket

Pre-Submission checklist

Please complete all items before asking a LiteLLM maintainer to review your PR

• I have added meaningful tests
• My PR passes all CI/CD checks (e.g., lint, format, unit tests)
• My PR's scope is as isolated as possible; it only solves 1 specific problem
• I have received a Greptile Confidence Score of at least 4/5 before requesting a maintainer review (Greptile reviews automatically once the PR is opened; only comment @greptileai to re-request a review after pushing changes)

Screenshots / Proof of Fix

The test itself is the end-to-end call: it streams a real chat completion against the live OpenAI API (no mocks, real $). Before, with the test file at the branch point 5e98e8f (model still gpt-5-codex):

pytest tests/llm_translation/test_openai.py::test_openai_gpt_5_codex_reasoning -x -q

E           litellm.exceptions.APIError: litellm.APIError: The model `gpt-5-codex` has been deprecated, learn more here: https://platform.openai.com/docs/deprecations
FAILED tests/llm_translation/test_openai.py::test_openai_gpt_5_codex_reasoning
1 failed in 1.04s

After, at d6fd9d8 (this PR):

pytest tests/llm_translation/test_openai.py::test_openai_gpt_5_codex_reasoning -x -q

1 passed in 1.06s

gpt-5.3-codex is a drop-in replacement per model_prices_and_context_window.json: responses-only mode, streaming, function calling and reasoning, same as the old entry

Type

✅ Test

Changes

One line in tests/llm_translation/test_openai.py: the model string in test_openai_gpt_5_codex_reasoning goes from gpt-5-codex to gpt-5.3-codex

Final Attestation

• The tests check the right things, including the edge cases, and regressions in the respective real-world customer use-cases are not possible after this PR

[greptile-apps]

Greptile Summary

Updates the live OpenAI Codex reasoning test to use the supported gpt-5.3-codex model instead of deprecated gpt-5-codex.

• Preserves the test’s existing streaming, reasoning, and tool-calling exercise.
• Aligns the model identifier with repository metadata and existing test usage.

Confidence Score: 5/5

The PR appears safe to merge because the replacement model is registered with the required capabilities and follows the existing OpenAI Codex routing path.

The only change updates a live test’s model identifier, while repository metadata confirms that the replacement supports responses mode, reasoning, native streaming, and function calling.

Important Files Changed

Filename	Overview
tests/llm_translation/test_openai.py	Replaces the deprecated Codex model in one live API test with a registered replacement that supports the capabilities exercised by the test.

_{Reviews (1): Last reviewed commit: "Merge remote-tracking branch 'origin/lit..." | Re-trigger Greptile}

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.

📢 Thoughts on this report? Let us know!