fix: remove unsupported fields from requests to Bedrock#225
Open
pawbana wants to merge 1 commit intopb/messages-remove-paramswrapfrom
Open
fix: remove unsupported fields from requests to Bedrock#225pawbana wants to merge 1 commit intopb/messages-remove-paramswrapfrom
pawbana wants to merge 1 commit intopb/messages-remove-paramswrapfrom
Conversation
This was referenced Mar 19, 2026
Merged
Contributor
Author
|
Warning This pull request is not mergeable via GitHub because a downstack PR is open. Once all requirements are satisfied, merge this PR as a stack on Graphite.
This stack of pull requests is managed by Graphite. Learn more about stacking. |
This was referenced Mar 19, 2026
pawbana
force-pushed
the
pb/bedrock-adaptive-thinking-fix
branch
from
7d8c1ae to
dcc3668
Compare
pawbana
changed the title
| // supports the "adaptive" thinking type natively (i.e. Claude 4.6 models). | ||
| // See https://docs.aws.amazon.com/bedrock/latest/userguide/claude-messages-adaptive-thinking.html | ||
| func bedrockModelSupportsAdaptiveThinking(model string) bool { | ||
| return strings.Contains(model, "anthropic.claude-opus-4-6") || |
Collaborator
There was a problem hiding this comment.
This doesn't match what the docs say:
Suggested change
| return strings.Contains(model, "anthropic.claude-opus-4-6") || | |
| return strings.Contains(model, "anthropic.claude-opus-4-6-v1") || |
|
|
||
| effort := gjson.GetBytes(p, messagesReqPathOutputConfigEffort).String() | ||
|
|
||
| // Effort-to-ratio mapping adapted from OpenRouter: |
Collaborator
There was a problem hiding this comment.
This explains the what, but not the why.
Can you please add more detail about why we're augmenting this value?
|
|
||
| func (p MessagesRequestPayload) delete(path string) (MessagesRequestPayload, error) { | ||
| out, err := sjson.DeleteBytes(p, path) | ||
| return MessagesRequestPayload(out), err |
| var err error | ||
| result, err = result.delete(field) | ||
| if err != nil { | ||
| return p, fmt.Errorf("removing %q: %w", field, err) |
Collaborator
There was a problem hiding this comment.
This isn't enough explanatory detail.
Suggested change
| return p, fmt.Errorf("removing %q: %w", field, err) | |
| return p, fmt.Errorf("removing %q field for Bedrock compatibility: %w", field, err) |
| result := p | ||
| for _, field := range bedrockUnsupportedFields { | ||
| var err error | ||
| result, err = result.delete(field) |
Collaborator
There was a problem hiding this comment.
Nit: doing this once per field means we have to parse the JSON each time.
Probably not a huge problem but I worry about memory usage since this will spill to the heap.
You could consider unmarshaling once into a map, deleting there, and remarshaling.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
This PR removes unsupported fields from requests to Bedrock.
Adaptive thinking field is replaced for models that don't support with
type: enabled+budget_tokens: Ncombination.budget_tokensvalue is calculated as a ratio ofmax_tokens.Ratio depends on
output_config.effortvalue, used the same ratio values as OpenRouter does: https://openrouter.ai/docs/guides/best-practices/reasoning-tokens#reasoning-effort-levelFixes: #219