| FazBrowse GitHub Viewer | Trending | | Home |
| Tools: [Download Repo ZIP] [Original HTTPS Page] |
normalizeMessages strips cachePoint and reasoning for amazon-bedrock models without anthropic/mistral ids; placeholder if assistant empty. Map adaptive xhigh reasoning effort to max for Bedrock; test expects max + display summarized for opus 4.7.
|
Hey! Your PR title provider: Bedrock non-Anthropic message cleanup and xhigh→max doesn't follow conventional commit format. Please update it to start with one of:
Where scope is the package name (e.g., app, desktop, opencode). See CONTRIBUTING.md for details. |
Sorry, something went wrong.
|
This PR doesn't fully meet our contributing guidelines and PR template. What needs to be fixed:
Please edit this PR description to address the above within 2 hours, or it will be automatically closed. If you believe this was flagged incorrectly, please let a maintainer know. |
Sorry, something went wrong.
|
The following comment was made by an LLM, it may be inaccurate: Based on my search, I found several related PRs that address similar concerns around Bedrock message handling and reasoning effort configuration: Related PRs
However, none of these appear to be exact duplicates of the current PR. They address related but distinct issues in the Bedrock provider implementation. |
Sorry, something went wrong.
|
Closing to reopen with a linked issue and the repo PR template per CONTRIBUTING. |
Sorry, something went wrong.
| Back | FazBrowse Home | New Git URL |
Summary
Some Amazon Bedrock models are not the Anthropic Claude adapter: they use different wire shapes. Sending them Anthropic-style extras—reasoning blocks from another stack, or cache breakpoints their stack does not understand—causes failures or empty turns. Separately, Bedrock’s adaptive “extra high” reasoning knob must map to a value the SDK accepts. This PR tightens Bedrock message shaping and variant config for those cases.
Problem (plain language)
Technical breakdown
Solution
Files
How to test
From packages/opencode:
bun typecheck bun test test/provider/transform.test.tsMerge order
Best reviewed after PR #25186 (catalog 200K / 1M split), since users pick the -1m rows this transform complements. Still compiles independently if merged out of order.