Add gpt-5.4-codex to resolve_model_config.py#2376
Add gpt-5.4-codex to resolve_model_config.py#2376juanmichelini wants to merge 2 commits intomainfrom
Conversation
Co-authored-by: openhands <openhands@all-hands.dev>
Co-authored-by: openhands <openhands@all-hands.dev>
API breakage checks (Griffe)Result: Passed |
Agent server REST API breakage checks (OpenAPI)Result: Failed Log excerpt (first 1000 characters) |
all-hands-bot
left a comment
There was a problem hiding this comment.
🟢 Good taste - Clean addition following existing pattern.
This change is technically sound and follows the established pattern perfectly. However, since this modifies evaluation harness code (.github/run-eval/resolve_model_config.py), it should be reviewed by a human maintainer to confirm no unintended impact on benchmark results before merging.
all-hands-bot
left a comment
There was a problem hiding this comment.
🟢 Good taste - Clean addition following existing pattern.
This change is technically sound and follows the established pattern perfectly. However, since this modifies evaluation harness code (.github/run-eval/resolve_model_config.py), it should be reviewed by a human maintainer to confirm no unintended impact on benchmark results before merging.
|
@OpenHands update PR to also add a test and add it to heuristics like this PR does #2374 |
This PR adds gpt-5.4-codex to resolve_model_config.py.
Agent Server images for this PR
• GHCR package: https://github.com/OpenHands/agent-sdk/pkgs/container/agent-server
Variants & Base Images
eclipse-temurin:17-jdknikolaik/python-nodejs:python3.13-nodejs22golang:1.21-bookwormPull (multi-arch manifest)
# Each variant is a multi-arch manifest supporting both amd64 and arm64 docker pull ghcr.io/openhands/agent-server:ce82ca1-pythonRun
All tags pushed for this build
About Multi-Architecture Support
ce82ca1-python) is a multi-arch manifest supporting both amd64 and arm64ce82ca1-python-amd64) are also available if needed