feat: add Bedrock fallback models, HIPAA role, and knowledge base event - #49
Open
fern-api[bot] wants to merge 3 commits into
Open
feat: add Bedrock fallback models, HIPAA role, and knowledge base event#49fern-api[bot] wants to merge 3 commits into
fern-api[bot] wants to merge 3 commits into
Conversation
fern-api
Bot
force-pushed
the
fern-bot/2026-09-10_21-49-32_753
branch
2 times, most recently
from
September 10, 2026 23:04
dba93cf to
db50444
Compare
fern-api
Bot
force-pushed
the
fern-bot/2026-09-10_21-49-32_753
branch
2 times, most recently
from
September 10, 2026 23:47
e82cb5c to
f21c240
Compare
fern-api
Bot
force-pushed
the
fern-bot/2026-09-10_21-49-32_753
branch
3 times, most recently
from
September 11, 2026 18:16
fca1bd2 to
7a6715b
Compare
Generated by Fern CLI Version: unknown Generators: - fernapi/fern-typescript-sdk: 3.63.0
… knowledge base event Expand the SDK with several new capabilities: Anthropic Bedrock models now support an optional `fallbackModels` field for same-provider failover, user role enums gain a `hipaa-special` value, and the events table gains an `assistant.knowledgeBase.requestSucceeded` event type. Documentation for `StructuredOutput` regex fields is also enriched with simulation evaluation transcript semantics. Key changes: - Add `AnthropicBedrockModelFallbackModelsItem` enum and export it from the types index - Add optional `fallbackModels` field to `AnthropicBedrockModel` - Add `HipaaSpecial` value to `InviteUserDtoRoleZero` and `UpdateUserRoleDtoRoleZero` - Add `AssistantKnowledgeBaseRequestSucceeded` to `JsonQueryOnEventsTableOn` - Enrich JSDoc on `StructuredOutput`, `CreateStructuredOutputDto`, and `UpdateStructuredOutputDto` with simulation transcript semantics - Update `EvalRun` field descriptions to clarify individual-eval semantics 🌿 Generated with Fern
fern-api
Bot
force-pushed
the
fern-bot/2026-09-10_21-49-32_753
branch
from
September 11, 2026 19:53
7a6715b to
ee21e10
Compare
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
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.
2.0.1 → 2.1.0
Added
AnthropicBedrockModelFallbackModelsItem— new enum listing all supported Claude models that can be used as a same-provider Bedrock fallback.AnthropicBedrockModel.fallbackModels— new optional field accepting up to oneAnthropicBedrockModelFallbackModelsItemfallback model, tried automatically if the primary model fails.HipaaSpecial— new"hipaa-special"value added toInviteUserDtoRoleZeroandUpdateUserRoleDtoRoleZerorole enums.JsonQueryOnEventsTableOn.AssistantKnowledgeBaseRequestSucceeded— new"assistant.knowledgeBase.requestSucceeded"event type available for event-table queries.Changed
StructuredOutput,CreateStructuredOutputDto, andUpdateStructuredOutputDto—regexPatternfield documentation expanded to describe how simulation evaluations build their canonical transcript, including tool call/result handling and fallback behavior.EvalRun—results,cost, andcostsfield descriptions updated to clarify they apply to individual Eval runs rather than suites.See full changelog