Celia Chen d19de6d150 fix: Bedrock GPT-5.4 reasoning levels (#19461) ...

## Why

When using the Amazon Bedrock provider with `openai.gpt-5.4-cmb`, the
model picker allowed `xhigh` because the CMB catalog entry was derived
from the bundled `gpt-5.4` reasoning metadata. Bedrock rejects that
effort level, causing the request to fail before the turn can run:

```text
{"error":{"code":"validation_error","message":"Failed to deserialize the JSON body into the target type: Invalid 'reasoning': Invalid 'effort': unknown variant `xhigh`, expected one of `high`, `low`, `medium`, `minimal` at line 1 column 77239","param":null,"type":"invalid_request_error"}}
```

## What Changed

- Replace the runtime lookup of bundled `gpt-5.4` metadata for
`openai.gpt-5.4-cmb` with an explicit Bedrock CMB `ModelInfo` entry.
- Advertise only the Bedrock-supported CMB reasoning levels: `minimal`,
`low`, `medium`, and `high`.
- Keep the existing GPT OSS Bedrock model metadata and reasoning levels
unchanged.
- Add catalog coverage for the hardcoded CMB metadata and
Bedrock-compatible reasoning level list.

2026-04-25 00:05:22 +00:00

..

src

fix: Bedrock GPT-5.4 reasoning levels (#19461)

2026-04-25 00:05:22 +00:00

BUILD.bazel

…

Cargo.toml

feat: let model providers own model discovery (#18950)

2026-04-24 04:28:25 +00:00