0.155.0 broke AWS Bedrock Runtime
Open
Nobody has claimed this yet.
aws-bedrock
bug
CLI
- Dominant language
- Rust
- Stars
- 125k
- Forks
- 19.4k
- PR merge metrics
- PR metrics pending
Description
What version of Codex CLI is running?
0.155.0
What subscription do you have?
AWS Bedrock Runtime
Which model were you using?
global.openai.gpt-5.6-luna
What platform is your computer?
macOS
What terminal emulator and version are you using (if applicable)?
No response
Codex doctor report
What issue are you seeing?
{"error":{"message":"Unsupported parameter: 'reasoning.summary' is not supported with the 'global.openai.gpt-5.6-luna'
model.","type":"invalid_request_error","param":"reasoning.summary","code":"unsupported_parameter"}}
What steps can reproduce the bug?
Hi
What is the expected behavior?
No response
Additional information
Looks like related to this release notes:
The TUI now shows live reasoning summaries in the status row and completion timestamps after successful turns. (https://github.com/openai/codex/pull/43558, https://github.com/openai/codex/pull/43921)
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Reproduce the failure in Codex CLI 0.155.0 with AWS Bedrock Runtime and model global.openai.gpt-5.6-luna, then inspect the changes referenced in PRs 43558 and 43921. Trace where the reasoning.summary parameter is sent and verify the request succeeds for this model without breaking live reasoning summaries for supported models.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- aws, rust
- Domain
- api, backend, cloud
- Issue type
- Bug
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Active
- Clarity
- Needs clarification
- Newbie friendliness
- 42/100