Skip to content

fix(bedrock): expose Opus 5.5 output token limit #1903

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
edelauna merged 1 commit into from
Oct 4, 2026
+6 −3
Merged

fix(bedrock): expose Opus 5.5 output token limit #1903

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions packages/types/src/providers/bedrock.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -258,6 +258,7 @@ export const bedrockModels = {
// 128K max output tokens per the AWS Bedrock model card:
// https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-opus-5-5.html
maxTokens: 128_000,
supportsMaxTokens: true,
contextWindow: 1_000_000, // 1M context window native (no beta header required)
supportsImages: true,
supportsPromptCache: true,
Expand Down
7 changes: 4 additions & 3 deletions src/api/providers/__tests__/bedrock.spec.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -141,16 +141,17 @@ describe("AwsBedrockHandler", () => {
["anthropic.claude-opus-4-7", 128_000],
["anthropic.claude-opus-4-8", 128_000],
["anthropic.claude-opus-5", 128_000],
["anthropic.claude-opus-5-5", 128_000],
] as const)("exposes %s output ceiling without raising request defaults", async (apiModelId, ceiling) => {
for (const enableReasoningEffort of [true, false]) {
for (const modelMaxTokens of [undefined, ceiling]) {
const provider = new AwsBedrockHandler({ apiModelId, enableReasoningEffort, modelMaxTokens })
expect(provider.getModel().info.maxTokens).toBe(ceiling)
const modelInfo = provider.getModel().info
expect(modelInfo.maxTokens).toBe(ceiling)
provider["client"].send = vi.fn().mockResolvedValue({ stream: asyncStreamFrom([]) })
await collectStream(provider.createMessage("system", [{ role: "user", content: "hello" }]))
const configurableWithoutReasoning = apiModelId.endsWith("-5")
const expected =
modelMaxTokens && (enableReasoningEffort || configurableWithoutReasoning)
modelMaxTokens && (enableReasoningEffort || modelInfo.supportsMaxTokens)
? ceiling
: enableReasoningEffort
? 16_384
Expand Down
1 change: 1 addition & 0 deletions webview-ui/src/components/settings/__tests__/ThinkingBudget.spec.tsx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -84,6 +84,7 @@ describe("ThinkingBudget", () => {
["anthropic.claude-opus-4-8", 128_000],
["anthropic.claude-sonnet-5", 128_000],
["anthropic.claude-opus-5", 128_000],
["anthropic.claude-opus-5-5", 128_000],
] as const)("allows selecting the documented Bedrock output ceiling for %s", (apiModelId, ceiling) => {
render(
<ThinkingBudget
Expand Down
Loading