Add gpt-5-3-codex model to resolve_model_config.py

[juanmichelini]

Summary

Adds the gpt-5-3-codex model to resolve_model_config.py for evaluation purposes.

This PR follows the guidelines in .github/run-eval/ADDINGMODEL.md by:

• Only adding new content - No existing code was modified
• Adding a test_model alias for backward compatibility instead of modifying existing test imports
• Not modifying any existing test assertions or mock configurations
• Adding only the necessary model configuration and test

Changes

• Added gpt-5-3-codex to the MODELS dictionary in resolve_model_config.py
• Added test_gpt_5_3_codex_config() test function in tests/github_workflows/test_resolve_model_config.py
• Added test_model = check_model alias for backward compatibility with existing test imports

Configuration

• Model ID: gpt-5-3-codex
• Display Name: GPT-5.3 Codex
• Model Path: litellm_proxy/gpt-5-3-codex
• Special Parameters: None (uses default configuration)
• Temperature: Not specified (uses provider default)

Why This Approach?

The existing branch openhands/add-gpt-5-3-codex violated the ADDINGMODEL.md guidelines by:

1. Changing test_model to check_model in imports (explicitly forbidden in line 197)
2. Modifying existing test assertions (explicitly forbidden in lines 11-13)
3. Renaming test classes from TestTestModel to TestCheckModel (modifying existing code)

This PR takes a cleaner approach by:

1. Adding a test_model alias to maintain backward compatibility
2. Not modifying any existing tests or assertions
3. Only adding new content as required by the guidelines

Additional Notes

• Variant Detection: gpt-5.3-codex is already included in the GPT-5 codex variant patterns in model_prompt_spec.py (line 2)
• Model Features: Pattern matching for "gpt-5" in model_features.py already covers this model, so no explicit additions needed

Test Results

$ uv run pytest tests/github_workflows/test_resolve_model_config.py::test_gpt_5_3_codex_config -v
tests/github_workflows/test_resolve_model_config.py::test_gpt_5_3_codex_config PASSED [100%]

$ uv run pytest tests/github_workflows/test_resolve_model_config.py::test_all_models_valid_with_pydantic -v
tests/github_workflows/test_resolve_model_config.py::test_all_models_valid_with_pydantic PASSED [100%]

Checklist

• If the PR is changing/adding functionality, are there tests to reflect this? ✅ Added test_gpt_5_3_codex_config()
• If there is an example, have you run the example to make sure that it works? N/A - No examples affected
• If there are instructions on how to run the code, have you followed the instructions and made sure that it works? ✅ Ran manual verification with resolve_model_config.py
• If the feature is significant enough to require documentation, is there a PR open on the OpenHands/docs repository with the same branch name? N/A - Internal model configuration
• Is the github CI passing? ⏳ Waiting for CI

Fixes #2289

---

Agent Server images for this PR

• GHCR package: https://github.com/OpenHands/agent-sdk/pkgs/container/agent-server

Variants & Base Images

Variant	Architectures	Base Image	Docs / Tags
java	amd64, arm64	eclipse-temurin:17-jdk	Link
python	amd64, arm64	nikolaik/python-nodejs:python3.12-nodejs22	Link
golang	amd64, arm64	golang:1.21-bookworm	Link

Pull (multi-arch manifest)

# Each variant is a multi-arch manifest supporting both amd64 and arm64
docker pull ghcr.io/openhands/agent-server:d872b05-python

Run

docker run -it --rm \
  -p 8000:8000 \
  --name agent-server-d872b05-python \
  ghcr.io/openhands/agent-server:d872b05-python

All tags pushed for this build

ghcr.io/openhands/agent-server:d872b05-golang-amd64
ghcr.io/openhands/agent-server:d872b05-golang_tag_1.21-bookworm-amd64
ghcr.io/openhands/agent-server:d872b05-golang-arm64
ghcr.io/openhands/agent-server:d872b05-golang_tag_1.21-bookworm-arm64
ghcr.io/openhands/agent-server:d872b05-java-amd64
ghcr.io/openhands/agent-server:d872b05-eclipse-temurin_tag_17-jdk-amd64
ghcr.io/openhands/agent-server:d872b05-java-arm64
ghcr.io/openhands/agent-server:d872b05-eclipse-temurin_tag_17-jdk-arm64
ghcr.io/openhands/agent-server:d872b05-python-amd64
ghcr.io/openhands/agent-server:d872b05-nikolaik_s_python-nodejs_tag_python3.12-nodejs22-amd64
ghcr.io/openhands/agent-server:d872b05-python-arm64
ghcr.io/openhands/agent-server:d872b05-nikolaik_s_python-nodejs_tag_python3.12-nodejs22-arm64
ghcr.io/openhands/agent-server:d872b05-golang
ghcr.io/openhands/agent-server:d872b05-java
ghcr.io/openhands/agent-server:d872b05-python

About Multi-Architecture Support

• Each variant tag (e.g., d872b05-python) is a multi-arch manifest supporting both amd64 and arm64
• Docker automatically pulls the correct architecture for your platform
• Individual architecture tags (e.g., d872b05-python-amd64) are also available if needed

[github-actions]

API breakage checks (Griffe)

Result: Failed

Log excerpt (first 1000 characters)

============================================================
Checking openhands-sdk (openhands.sdk)
============================================================
Comparing openhands-sdk 1.11.5 against 1.11.4
::notice title=openhands-sdk API::Ignoring Field metadata-only change (non-breaking): load_public_skills
::notice title=openhands-sdk API::Ignoring Field metadata-only change (non-breaking): temperature
::warning file=openhands-sdk/openhands/sdk/llm/llm.py,line=196,title=LLM.top_p::Attribute value was changed: `Field(default=1.0, ge=0, le=1)` -> `Field(default=None, ge=0, le=1, description='Nucleus sampling parameter. Defaults to None (uses provider default). Set to a value between 0 and 1 to control diversity of outputs.')`
::error title=SemVer::Breaking changes detected (1); require at least minor version bump from 1.11.x, but new is 1.11.5

============================================================
Checking openhands-workspace (openhands.workspace)
============================

Action log

[github-actions]

Agent server REST API breakage checks (OpenAPI)

Result: Passed

Action log

[all-hands-bot]

🟢 Good taste - Clean addition following existing patterns.

Assessment:

• Model config follows the exact pattern of gpt-5.2-codex - no surprises
• The test_model = check_model alias is correctly preserving backward compatibility with existing test imports (used in TestTestModel class)
• Test coverage mirrors other model tests - sufficient for a config entry

Verdict: ✅ LGTM - straightforward config addition with proper backward compatibility handling.

[github-actions]

🧪 Integration Tests Results

Overall Success Rate: 0.0%
Total Cost: $0.00
Models Tested: 1
Timestamp: 2026-03-03 23:38:36 UTC

📊 Summary

Model	Overall	Tests Passed	Skipped	Total	Cost	Tokens
litellm_proxy_gpt_5_3_codex	0.0%	0/16	2	18	$0.00	0

📋 Detailed Results

litellm_proxy_gpt_5_3_codex

• Success Rate: 0.0% (0/16)
• Total Cost: $0.00
• Token Usage: 0
• Run Suffix: litellm_proxy_gpt_5_3_codex_10ccfad_gpt_5_3_codex_run_N18_20260303_233749
• Skipped Tests: 2

Skipped Tests:

• t08_image_file_viewing: This test requires a vision-capable LLM model. Please use a model that supports image input.
• c01_thinking_block_condenser: Model litellm_proxy/gpt-5-3-codex does not support extended thinking or reasoning effort

Failed Tests:

• t01_fix_simple_typo: Test execution failed: Conversation run failed for id=113db401-5498-41c1-a54b-b3054dea8dc5: litellm.BadRequestError: {"error":{"message":"litellm.BadRequestError: You passed in model=gpt-5-3-codex. There are no healthy deployments for this modelNo fallback model group found for original model_group=gpt-5-3-codex. Fallbacks=[{'minimax-m2.5': ['minimax-m2.5-api']}]. Received Model Group=gpt-5-3-codex\nAvailable Model Group Fallbacks=None\nError doing the fallback: litellm.BadRequestError: You passed in model=gpt-5-3-codex. There are no healthy deployments for this modelNo fallback model group found for original model_group=gpt-5-3-codex. Fallbacks=[{'minimax-m2.5': ['minimax-m2.5-api']}]","type":null,"param":null,"code":"400"}} (Cost: $0.00)
• c02_hard_context_reset: Test execution failed: Conversation run failed for id=f1d6042e-dc63-4a2d-8cb7-9ef2180c8230: litellm.BadRequestError: {"error":{"message":"litellm.BadRequestError: You passed in model=gpt-5-3-codex. There are no healthy deployments for this modelNo fallback model group found for original model_group=gpt-5-3-codex. Fallbacks=[{'minimax-m2.5': ['minimax-m2.5-api']}]. Received Model Group=gpt-5-3-codex\nAvailable Model Group Fallbacks=None\nError doing the fallback: litellm.BadRequestError: You passed in model=gpt-5-3-codex. There are no healthy deployments for this modelNo fallback model group found for original model_group=gpt-5-3-codex. Fallbacks=[{'minimax-m2.5': ['minimax-m2.5-api']}]","type":null,"param":null,"code":"400"}} (Cost: $0.00)
• t07_interactive_commands: Test execution failed: Conversation run failed for id=70f0bb12-1cff-4880-88ea-e3839b7cfd6d: litellm.BadRequestError: {"error":{"message":"litellm.BadRequestError: You passed in model=gpt-5-3-codex. There are no healthy deployments for this modelNo fallback model group found for original model_group=gpt-5-3-codex. Fallbacks=[{'minimax-m2.5': ['minimax-m2.5-api']}]. Received Model Group=gpt-5-3-codex\nAvailable Model Group Fallbacks=None\nError doing the fallback: litellm.BadRequestError: You passed in model=gpt-5-3-codex. There are no healthy deployments for this modelNo fallback model group found for original model_group=gpt-5-3-codex. Fallbacks=[{'minimax-m2.5': ['minimax-m2.5-api']}]","type":null,"param":null,"code":"400"}} (Cost: $0.00)
• t06_github_pr_browsing: Test execution failed: Conversation run failed for id=79888d24-e91f-4aa5-91f6-5d9fdd7a0ebd: litellm.BadRequestError: {"error":{"message":"litellm.BadRequestError: You passed in model=gpt-5-3-codex. There are no healthy deployments for this modelNo fallback model group found for original model_group=gpt-5-3-codex. Fallbacks=[{'minimax-m2.5': ['minimax-m2.5-api']}]. Received Model Group=gpt-5-3-codex\nAvailable Model Group Fallbacks=None\nError doing the fallback: litellm.BadRequestError: You passed in model=gpt-5-3-codex. There are no healthy deployments for this modelNo fallback model group found for original model_group=gpt-5-3-codex. Fallbacks=[{'minimax-m2.5': ['minimax-m2.5-api']}]","type":null,"param":null,"code":"400"}} (Cost: $0.00)
• c05_size_condenser: Test execution failed: Conversation run failed for id=bace673e-94ef-477b-8b83-dac4ad8ea67d: litellm.BadRequestError: {"error":{"message":"litellm.BadRequestError: You passed in model=gpt-5-3-codex. There are no healthy deployments for this modelNo fallback model group found for original model_group=gpt-5-3-codex. Fallbacks=[{'minimax-m2.5': ['minimax-m2.5-api']}]. Received Model Group=gpt-5-3-codex\nAvailable Model Group Fallbacks=None\nError doing the fallback: litellm.BadRequestError: You passed in model=gpt-5-3-codex. There are no healthy deployments for this modelNo fallback model group found for original model_group=gpt-5-3-codex. Fallbacks=[{'minimax-m2.5': ['minimax-m2.5-api']}]","type":null,"param":null,"code":"400"}} (Cost: $0.00)
• b04_each_tool_call_has_a_concise_explanation: Test execution failed: Conversation run failed for id=40d8e4e2-202c-4b8b-8910-fdcb47761e4a: litellm.BadRequestError: {"error":{"message":"litellm.BadRequestError: You passed in model=gpt-5-3-codex. There are no healthy deployments for this modelNo fallback model group found for original model_group=gpt-5-3-codex. Fallbacks=[{'minimax-m2.5': ['minimax-m2.5-api']}]. Received Model Group=gpt-5-3-codex\nAvailable Model Group Fallbacks=None\nError doing the fallback: litellm.BadRequestError: You passed in model=gpt-5-3-codex. There are no healthy deployments for this modelNo fallback model group found for original model_group=gpt-5-3-codex. Fallbacks=[{'minimax-m2.5': ['minimax-m2.5-api']}]","type":null,"param":null,"code":"400"}} (Cost: $0.00)
• t04_git_staging: Test execution failed: Conversation run failed for id=f73d14fb-550d-4805-a56c-a4176d22a258: litellm.BadRequestError: {"error":{"message":"litellm.BadRequestError: You passed in model=gpt-5-3-codex. There are no healthy deployments for this modelNo fallback model group found for original model_group=gpt-5-3-codex. Fallbacks=[{'minimax-m2.5': ['minimax-m2.5-api']}]. Received Model Group=gpt-5-3-codex\nAvailable Model Group Fallbacks=None\nError doing the fallback: litellm.BadRequestError: You passed in model=gpt-5-3-codex. There are no healthy deployments for this modelNo fallback model group found for original model_group=gpt-5-3-codex. Fallbacks=[{'minimax-m2.5': ['minimax-m2.5-api']}]","type":null,"param":null,"code":"400"}} (Cost: $0.00)
• t03_jupyter_write_file: Test execution failed: Conversation run failed for id=9fddad9d-d0b3-4bb7-8a34-b32d1becd31e: litellm.BadRequestError: {"error":{"message":"litellm.BadRequestError: You passed in model=gpt-5-3-codex. There are no healthy deployments for this modelNo fallback model group found for original model_group=gpt-5-3-codex. Fallbacks=[{'minimax-m2.5': ['minimax-m2.5-api']}]. Received Model Group=gpt-5-3-codex\nAvailable Model Group Fallbacks=None\nError doing the fallback: litellm.BadRequestError: You passed in model=gpt-5-3-codex. There are no healthy deployments for this modelNo fallback model group found for original model_group=gpt-5-3-codex. Fallbacks=[{'minimax-m2.5': ['minimax-m2.5-api']}]","type":null,"param":null,"code":"400"}} (Cost: $0.00)
• c03_delayed_condensation: Test execution failed: Conversation run failed for id=a5bfb73a-bebf-492e-adb7-5f5731259d85: litellm.BadRequestError: {"error":{"message":"litellm.BadRequestError: You passed in model=gpt-5-3-codex. There are no healthy deployments for this modelNo fallback model group found for original model_group=gpt-5-3-codex. Fallbacks=[{'minimax-m2.5': ['minimax-m2.5-api']}]. Received Model Group=gpt-5-3-codex\nAvailable Model Group Fallbacks=None\nError doing the fallback: litellm.BadRequestError: You passed in model=gpt-5-3-codex. There are no healthy deployments for this modelNo fallback model group found for original model_group=gpt-5-3-codex. Fallbacks=[{'minimax-m2.5': ['minimax-m2.5-api']}]","type":null,"param":null,"code":"400"}} (Cost: $0.00)
• t05_simple_browsing: Test execution failed: Conversation run failed for id=16726033-fd7d-416d-91b4-0c288b8c54e3: litellm.BadRequestError: {"error":{"message":"litellm.BadRequestError: You passed in model=gpt-5-3-codex. There are no healthy deployments for this modelNo fallback model group found for original model_group=gpt-5-3-codex. Fallbacks=[{'minimax-m2.5': ['minimax-m2.5-api']}]. Received Model Group=gpt-5-3-codex\nAvailable Model Group Fallbacks=None\nError doing the fallback: litellm.BadRequestError: You passed in model=gpt-5-3-codex. There are no healthy deployments for this modelNo fallback model group found for original model_group=gpt-5-3-codex. Fallbacks=[{'minimax-m2.5': ['minimax-m2.5-api']}]","type":null,"param":null,"code":"400"}} (Cost: $0.00)
• b02_no_oververification: Test execution failed: Conversation run failed for id=b35c94af-ec83-4151-90ca-8e63f45a668e: litellm.BadRequestError: {"error":{"message":"litellm.BadRequestError: You passed in model=gpt-5-3-codex. There are no healthy deployments for this modelNo fallback model group found for original model_group=gpt-5-3-codex. Fallbacks=[{'minimax-m2.5': ['minimax-m2.5-api']}]. Received Model Group=gpt-5-3-codex\nAvailable Model Group Fallbacks=None\nError doing the fallback: litellm.BadRequestError: You passed in model=gpt-5-3-codex. There are no healthy deployments for this modelNo fallback model group found for original model_group=gpt-5-3-codex. Fallbacks=[{'minimax-m2.5': ['minimax-m2.5-api']}]","type":null,"param":null,"code":"400"}} (Cost: $0.00)
• t02_add_bash_hello: Test execution failed: Conversation run failed for id=39ca1ff3-495d-4745-b2c2-d9fb5b75e76b: litellm.BadRequestError: {"error":{"message":"litellm.BadRequestError: You passed in model=gpt-5-3-codex. There are no healthy deployments for this modelNo fallback model group found for original model_group=gpt-5-3-codex. Fallbacks=[{'minimax-m2.5': ['minimax-m2.5-api']}]. Received Model Group=gpt-5-3-codex\nAvailable Model Group Fallbacks=None\nError doing the fallback: litellm.BadRequestError: You passed in model=gpt-5-3-codex. There are no healthy deployments for this modelNo fallback model group found for original model_group=gpt-5-3-codex. Fallbacks=[{'minimax-m2.5': ['minimax-m2.5-api']}]","type":null,"param":null,"code":"400"}} (Cost: $0.00)
• c04_token_condenser: Test execution failed: Conversation run failed for id=a231c2ec-80b4-49e7-9192-7f5f7981739a: litellm.BadRequestError: {"error":{"message":"litellm.BadRequestError: You passed in model=gpt-5-3-codex. There are no healthy deployments for this modelNo fallback model group found for original model_group=gpt-5-3-codex. Fallbacks=[{'minimax-m2.5': ['minimax-m2.5-api']}]. Received Model Group=gpt-5-3-codex\nAvailable Model Group Fallbacks=None\nError doing the fallback: litellm.BadRequestError: You passed in model=gpt-5-3-codex. There are no healthy deployments for this modelNo fallback model group found for original model_group=gpt-5-3-codex. Fallbacks=[{'minimax-m2.5': ['minimax-m2.5-api']}]","type":null,"param":null,"code":"400"}} (Cost: $0.00)
• b01_no_premature_implementation: Test execution failed: Conversation run failed for id=18bec4f5-03ab-4961-84a7-08dfd9608359: litellm.BadRequestError: {"error":{"message":"litellm.BadRequestError: You passed in model=gpt-5-3-codex. There are no healthy deployments for this modelNo fallback model group found for original model_group=gpt-5-3-codex. Fallbacks=[{'minimax-m2.5': ['minimax-m2.5-api']}]. Received Model Group=gpt-5-3-codex\nAvailable Model Group Fallbacks=None\nError doing the fallback: litellm.BadRequestError: You passed in model=gpt-5-3-codex. There are no healthy deployments for this modelNo fallback model group found for original model_group=gpt-5-3-codex. Fallbacks=[{'minimax-m2.5': ['minimax-m2.5-api']}]","type":null,"param":null,"code":"400"}} (Cost: $0.00)
• b03_no_useless_backward_compatibility: Test execution failed: Conversation run failed for id=01e3b8d7-d75b-4864-af31-a0b07917886d: litellm.BadRequestError: {"error":{"message":"litellm.BadRequestError: You passed in model=gpt-5-3-codex. There are no healthy deployments for this modelNo fallback model group found for original model_group=gpt-5-3-codex. Fallbacks=[{'minimax-m2.5': ['minimax-m2.5-api']}]. Received Model Group=gpt-5-3-codex\nAvailable Model Group Fallbacks=None\nError doing the fallback: litellm.BadRequestError: You passed in model=gpt-5-3-codex. There are no healthy deployments for this modelNo fallback model group found for original model_group=gpt-5-3-codex. Fallbacks=[{'minimax-m2.5': ['minimax-m2.5-api']}]","type":null,"param":null,"code":"400"}} (Cost: $0.00)
• b05_do_not_create_redundant_files: Test execution failed: Conversation run failed for id=5187f133-03cb-457f-bd35-c6f0f50b5940: litellm.BadRequestError: {"error":{"message":"litellm.BadRequestError: You passed in model=gpt-5-3-codex. There are no healthy deployments for this modelNo fallback model group found for original model_group=gpt-5-3-codex. Fallbacks=[{'minimax-m2.5': ['minimax-m2.5-api']}]. Received Model Group=gpt-5-3-codex\nAvailable Model Group Fallbacks=None\nError doing the fallback: litellm.BadRequestError: You passed in model=gpt-5-3-codex. There are no healthy deployments for this modelNo fallback model group found for original model_group=gpt-5-3-codex. Fallbacks=[{'minimax-m2.5': ['minimax-m2.5-api']}]","type":null,"param":null,"code":"400"}} (Cost: $0.00)