> ## Documentation Index
> Fetch the complete documentation index at: https://braintrust.dev/docs/llms.txt
> Use this file to discover all available pages before exploring further.
# Braintrust TypeScript SDK
> TypeScript API reference for Braintrust SDK v3.7.1
This page provides a complete, auto-generated reference for the Braintrust TypeScript SDK. For usage guidance on important APIs, see the [API Reference](/sdks/typescript/api-reference). Also see the [Braintrust TypeScript SDK](https://github.com/braintrustdata/braintrust-sdk-javascript) on GitHub.
## Installation
```bash npm theme={"theme":{"light":"github-light","dark":"github-dark-dimmed"}}
npm install braintrust
```
```bash pnpm theme={"theme":{"light":"github-light","dark":"github-dark-dimmed"}}
pnpm add braintrust
```
Starting with v2.0.0, if you're using the Vercel AI SDK integration or other features that require schema validation, you must install `zod` as a peer dependency: `npm install zod`
## Functions
### addAzureBlobHeaders
addAzureBlobHeaders function
### BaseExperiment
Use this to specify that the dataset should actually be the data from a previous (base) experiment.
If you do not specify a name, Braintrust will automatically figure out the best base experiment to
use based on your git history (or fall back to timestamps).
The name of the base experiment to use. If unspecified, Braintrust will automatically figure out the best base
using your git history (or fall back to timestamps).
### BraintrustMiddleware
Creates a Braintrust middleware for AI SDK v2 that automatically traces
generateText and streamText calls with comprehensive metadata and metrics.
Configuration options for the middleware
### buildLocalSummary
buildLocalSummary function
An optional experiment id to use as a base. If specified, the new experiment will be summarized
and compared to this experiment. This takes precedence over `baseExperimentName` if specified.
An optional experiment name to use as a base. If specified, the new experiment will be summarized
and compared to this experiment.
A function that returns a list of inputs, expected outputs, and metadata.
An optional description for the experiment.
Optionally supply a custom function to specifically handle score values when tasks or scoring functions have errored.
A default implementation is exported as `defaultErrorScoreHandler` which will log a 0 score to the root span for any scorer that was not run.
An optional name for the experiment.
Flushes spans before calling scoring functions
Optional settings for collecting git metadata. By default, will collect all git metadata fields allowed in org-level settings.
Whether the experiment should be public. Defaults to false.
The maximum number of tasks/scorers that will be run concurrently.
Defaults to undefined, in which case there is no max concurrency.
Optional additional metadata for the experiment.
A set of parameters that will be passed to the evaluator.
Can be:
* A raw EvalParameters schema (Zod schemas)
* A Parameters instance from loadParameters()
* A Promise\ from loadParameters()
If specified, uses the given project ID instead of the evaluator's name to identify the project.
Optionally explicitly specify the git metadata for this experiment. This takes precedence over `gitMetadataSettings` if specified.
A set of functions that take an input, output, and expected value and return a score.
An abort signal that can be used to stop the evaluation.
If specified, uses the logger state to initialize Braintrust objects. If unspecified, falls back
to the global state (initialized using your API key).
Whether to summarize the scores of the experiment after it has run.
Defaults to true.
Optional tags for the experiment.
A function that takes an input and returns an output.
The duration, in milliseconds, after which to time out the evaluation.
Defaults to undefined, in which case there is no timeout.
The number of times to run the evaluator per input. This is useful for evaluating applications that
have non-deterministic behavior and gives you both a stronger aggregate measure and a sense of the
variance in the results.
Whether to update an existing experiment with `experiment_name` if one exists. Defaults to false.
### configureInstrumentation
Configure auto-instrumentation.
This must be called before importing any AI SDKs to take effect.
Configuration for individual SDK integrations.
Set to false to disable instrumentation for that SDK.
### constructLogs3OverflowRequest
constructLogs3OverflowRequest function
### createFinalValuePassThroughStream
Create a stream that passes through the final value of the stream. This is
used to implement `BraintrustStream.finalValue()`.
A function to call with the final value of the stream.
### currentExperiment
Returns the currently-active experiment (set by [`init`](#init)). Returns undefined if no current experiment has been set.
### currentLogger
Returns the currently-active logger (set by [`initLogger`](#initlogger)). Returns undefined if no current logger has been set.
### currentSpan
Return the currently-active span for logging (set by one of the `traced` methods). If there is no active span, returns a no-op span object, which supports the same interface as spans but does no logging.
See [`Span`](#span) for full details.
### defaultErrorScoreHandler
defaultErrorScoreHandler function
### deserializePlainStringAsJSON
deserializePlainStringAsJSON function
### devNullWritableStream
devNullWritableStream function
### Eval
Eval function
An optional experiment id to use as a base. If specified, the new experiment will be summarized
and compared to this experiment. This takes precedence over `baseExperimentName` if specified.
An optional experiment name to use as a base. If specified, the new experiment will be summarized
and compared to this experiment.
A function that returns a list of inputs, expected outputs, and metadata.
An optional description for the experiment.
Optionally supply a custom function to specifically handle score values when tasks or scoring functions have errored.
A default implementation is exported as `defaultErrorScoreHandler` which will log a 0 score to the root span for any scorer that was not run.
An optional name for the experiment.
Flushes spans before calling scoring functions
Optional settings for collecting git metadata. By default, will collect all git metadata fields allowed in org-level settings.
Whether the experiment should be public. Defaults to false.
The maximum number of tasks/scorers that will be run concurrently.
Defaults to undefined, in which case there is no max concurrency.
Optional additional metadata for the experiment.
A set of parameters that will be passed to the evaluator.
Can be:
* A raw EvalParameters schema (Zod schemas)
* A Parameters instance from loadParameters()
* A Promise\ from loadParameters()
If specified, uses the given project ID instead of the evaluator's name to identify the project.
Optionally explicitly specify the git metadata for this experiment. This takes precedence over `gitMetadataSettings` if specified.
A set of functions that take an input, output, and expected value and return a score.
An abort signal that can be used to stop the evaluation.
If specified, uses the logger state to initialize Braintrust objects. If unspecified, falls back
to the global state (initialized using your API key).
Whether to summarize the scores of the experiment after it has run.
Defaults to true.
Optional tags for the experiment.
A function that takes an input and returns an output.
The duration, in milliseconds, after which to time out the evaluation.
Defaults to undefined, in which case there is no timeout.
The number of times to run the evaluator per input. This is useful for evaluating applications that
have non-deterministic behavior and gives you both a stronger aggregate measure and a sense of the
variance in the results.
Whether to update an existing experiment with `experiment_name` if one exists. Defaults to false.
### flush
Flush any pending rows to the server.
### getContextManager
getContextManager function
### getIdGenerator
Factory function that creates a new ID generator instance each time.
This eliminates global state and makes tests parallelizable.
Each caller gets their own generator instance.
### getPromptVersions
Get the versions for a prompt.
The ID of the project to query
The ID of the prompt to get versions for
### getSpanParentObject
Mainly for internal use. Return the parent object for starting a span in a global context.
Applies precedence: current span > propagated parent string > experiment > logger.
### getTemplateRenderer
Gets an active template renderer by name.
Returns `undefined` if the renderer is not active.
Name of the renderer to retrieve
### init
Log in, and then initialize a new experiment in a specified project. If the project does not exist, it will be created.
Options for configuring init().
The API key to use. If the parameter is not specified, will try to use the `BRAINTRUST_API_KEY` environment variable.
The URL of the Braintrust App. Defaults to [https://www.braintrust.dev](https://www.braintrust.dev). You should not need
to change this unless you are doing the "Full" deployment.
Controls internal Braintrust SDK troubleshooting output.
Use `"error"`, `"warn"`, `"info"`, or `"debug"` to control how much
internal SDK troubleshooting output is emitted. Use `false` to explicitly
disable this output.
When omitted, the SDK remains silent unless
`BRAINTRUST_DEBUG_LOG_LEVEL` is set to `"error"`, `"warn"`, `"info"`, or
`"debug"`. This option only affects local console output; it does not
change what data is logged to Braintrust.
If true, disables the local span cache used to optimize scorer access
to trace data. When disabled, scorers will always fetch spans from the
server. Defaults to false.
A custom fetch implementation to use.
By default, the SDK installs an event handler that flushes pending writes on the `beforeExit` event.
If true, this event handler will *not* be installed.
Calls this function if there's an error in the background flusher.
The name of a specific organization to connect to. Since API keys are scoped to organizations, this parameter is usually
unnecessary unless you are logging in with a JWT.
### initDataset
Create a new dataset in a specified project. If the project does not exist, it will be created.
Options for configuring initDataset().
The API key to use. If the parameter is not specified, will try to use the `BRAINTRUST_API_KEY` environment variable.
The URL of the Braintrust App. Defaults to [https://www.braintrust.dev](https://www.braintrust.dev). You should not need
to change this unless you are doing the "Full" deployment.
Controls internal Braintrust SDK troubleshooting output.
Use `"error"`, `"warn"`, `"info"`, or `"debug"` to control how much
internal SDK troubleshooting output is emitted. Use `false` to explicitly
disable this output.
When omitted, the SDK remains silent unless
`BRAINTRUST_DEBUG_LOG_LEVEL` is set to `"error"`, `"warn"`, `"info"`, or
`"debug"`. This option only affects local console output; it does not
change what data is logged to Braintrust.
If true, disables the local span cache used to optimize scorer access
to trace data. When disabled, scorers will always fetch spans from the
server. Defaults to false.
A custom fetch implementation to use.
By default, the SDK installs an event handler that flushes pending writes on the `beforeExit` event.
If true, this event handler will *not* be installed.
Calls this function if there's an error in the background flusher.
The name of a specific organization to connect to. Since API keys are scoped to organizations, this parameter is usually
unnecessary unless you are logging in with a JWT.
### initExperiment
Alias for init(options).
The API key to use. If the parameter is not specified, will try to use the `BRAINTRUST_API_KEY` environment variable.
The URL of the Braintrust App. Defaults to [https://www.braintrust.dev](https://www.braintrust.dev). You should not need
to change this unless you are doing the "Full" deployment.
Controls internal Braintrust SDK troubleshooting output.
Use `"error"`, `"warn"`, `"info"`, or `"debug"` to control how much
internal SDK troubleshooting output is emitted. Use `false` to explicitly
disable this output.
When omitted, the SDK remains silent unless
`BRAINTRUST_DEBUG_LOG_LEVEL` is set to `"error"`, `"warn"`, `"info"`, or
`"debug"`. This option only affects local console output; it does not
change what data is logged to Braintrust.
If true, disables the local span cache used to optimize scorer access
to trace data. When disabled, scorers will always fetch spans from the
server. Defaults to false.
A custom fetch implementation to use.
By default, the SDK installs an event handler that flushes pending writes on the `beforeExit` event.
If true, this event handler will *not* be installed.
Calls this function if there's an error in the background flusher.
The name of a specific organization to connect to. Since API keys are scoped to organizations, this parameter is usually
unnecessary unless you are logging in with a JWT.
### initFunction
Creates a function that can be used as a task or scorer in the Braintrust evaluation framework.
The returned function wraps a Braintrust function and can be passed directly to Eval().
When used as a task:
```ts theme={"theme":{"light":"github-light","dark":"github-dark-dimmed"}}
const myFunction = initFunction({projectName: "myproject", slug: "myfunction"});
await Eval("test", {
task: myFunction,
data: testData,
scores: [...]
});
```
When used as a scorer:
```ts theme={"theme":{"light":"github-light","dark":"github-dark-dimmed"}}
const myScorer = initFunction({projectName: "myproject", slug: "myscorer"});
await Eval("test", {
task: someTask,
data: testData,
scores: [myScorer]
});
```
Options for the function.
The project name containing the function.
The slug of the function to invoke.
Optional Braintrust state to use.
Optional version of the function to use. Defaults to latest.
### initLogger
Create a new logger in a specified project. If the project does not exist, it will be created.
Additional options for configuring init().
The API key to use. If the parameter is not specified, will try to use the `BRAINTRUST_API_KEY` environment variable.
The URL of the Braintrust App. Defaults to [https://www.braintrust.dev](https://www.braintrust.dev). You should not need
to change this unless you are doing the "Full" deployment.
Controls internal Braintrust SDK troubleshooting output.
Use `"error"`, `"warn"`, `"info"`, or `"debug"` to control how much
internal SDK troubleshooting output is emitted. Use `false` to explicitly
disable this output.
When omitted, the SDK remains silent unless
`BRAINTRUST_DEBUG_LOG_LEVEL` is set to `"error"`, `"warn"`, `"info"`, or
`"debug"`. This option only affects local console output; it does not
change what data is logged to Braintrust.
If true, disables the local span cache used to optimize scorer access
to trace data. When disabled, scorers will always fetch spans from the
server. Defaults to false.
A custom fetch implementation to use.
By default, the SDK installs an event handler that flushes pending writes on the `beforeExit` event.
If true, this event handler will *not* be installed.
Calls this function if there's an error in the background flusher.
The name of a specific organization to connect to. Since API keys are scoped to organizations, this parameter is usually
unnecessary unless you are logging in with a JWT.
### initNodeTestSuite
Creates a new Node.js test suite with Braintrust experiment tracking.
### invoke
Invoke a Braintrust function, returning a `BraintrustStream` or the value as a plain
Javascript object.
The arguments for the function (see [`InvokeFunctionArgs`](#invokefunctionargs) for more details).
The type of the global function to invoke. If unspecified, defaults to 'scorer' for backward compatibility.
The ID of the function to invoke.
The name of the global function to invoke.
The input to the function. This will be logged as the `input` field in the span.
Additional OpenAI-style messages to add to the prompt (only works for llm functions).
Additional metadata to add to the span. This will be logged as the `metadata` field in the span.
It will also be available as the \{\{metadata}} field in the prompt and as the `metadata` argument
to the function.
The mode of the function. If "auto", will return a string if the function returns a string,
and a JSON object otherwise. If "parallel", will return an array of JSON objects with one
object per tool call.
The parent of the function. This can be an existing span, logger, or experiment, or
the output of `.export()` if you are distributed tracing. If unspecified, will use
the same semantics as `traced()` to determine the parent and no-op if not in a tracing
context.
The ID of the project to use for execution context (API keys, project defaults, etc.).
This is not the project the function belongs to, but the project context for the invocation.
The name of the project containing the function to invoke.
The ID of the function in the prompt session to invoke.
The ID of the prompt session to invoke the function from.
A Zod schema to validate the output of the function and return a typed value. This
is only used if `stream` is false.
The slug of the function to invoke.
(Advanced) This parameter allows you to pass in a custom login state. This is useful
for multi-tenant environments where you are running functions from different Braintrust
organizations.
Whether to stream the function's output. If true, the function will return a
`BraintrustStream`, otherwise it will return the output of the function as a JSON
object.
Whether to use strict mode for the function. If true, the function will throw an error
if the variable names in the prompt do not match the input keys.
Tags to add to the span. This will be logged as the `tags` field in the span.
The version of the function to invoke.
The API key to use. If the parameter is not specified, will try to use the `BRAINTRUST_API_KEY` environment variable.
The URL of the Braintrust App. Defaults to [https://www.braintrust.dev](https://www.braintrust.dev). You should not need
to change this unless you are doing the "Full" deployment.
Controls internal Braintrust SDK troubleshooting output.
Use `"error"`, `"warn"`, `"info"`, or `"debug"` to control how much
internal SDK troubleshooting output is emitted. Use `false` to explicitly
disable this output.
When omitted, the SDK remains silent unless
`BRAINTRUST_DEBUG_LOG_LEVEL` is set to `"error"`, `"warn"`, `"info"`, or
`"debug"`. This option only affects local console output; it does not
change what data is logged to Braintrust.
If true, disables the local span cache used to optimize scorer access
to trace data. When disabled, scorers will always fetch spans from the
server. Defaults to false.
A custom fetch implementation to use.
By default, the SDK installs an event handler that flushes pending writes on the `beforeExit` event.
If true, this event handler will *not* be installed.
Calls this function if there's an error in the background flusher.
The name of a specific organization to connect to. Since API keys are scoped to organizations, this parameter is usually
unnecessary unless you are logging in with a JWT.
### isTemplateFormat
isTemplateFormat function
### loadParameters
Load parameters from the specified project.
Options for configuring loadParameters().
### loadPrompt
Load a prompt from the specified project.
Options for configuring loadPrompt().
The API key to use. If the parameter is not specified, will try to use the `BRAINTRUST_API_KEY` environment variable.
The URL of the Braintrust App. Defaults to [https://www.braintrust.dev](https://www.braintrust.dev). You should not need
to change this unless you are doing the "Full" deployment.
Controls internal Braintrust SDK troubleshooting output.
Use `"error"`, `"warn"`, `"info"`, or `"debug"` to control how much
internal SDK troubleshooting output is emitted. Use `false` to explicitly
disable this output.
When omitted, the SDK remains silent unless
`BRAINTRUST_DEBUG_LOG_LEVEL` is set to `"error"`, `"warn"`, `"info"`, or
`"debug"`. This option only affects local console output; it does not
change what data is logged to Braintrust.
If true, disables the local span cache used to optimize scorer access
to trace data. When disabled, scorers will always fetch spans from the
server. Defaults to false.
A custom fetch implementation to use.
By default, the SDK installs an event handler that flushes pending writes on the `beforeExit` event.
If true, this event handler will *not* be installed.
Calls this function if there's an error in the background flusher.
The name of a specific organization to connect to. Since API keys are scoped to organizations, this parameter is usually
unnecessary unless you are logging in with a JWT.
### log
Log a single event to the current experiment. The event will be batched and uploaded behind the scenes.
The event to log. See `Experiment.log` for full details.
### logError
logError function
Row ID of the span.
Root span ID of the span.
Span ID of the span.
Parent span IDs of the span.
### login
Log into Braintrust. This will prompt you for your API token, which you can find at
[https://www.braintrust.dev/app/token](https://www.braintrust.dev/app/token). This method is called automatically by `init()`.
Options for configuring login().
The API key to use. If the parameter is not specified, will try to use the `BRAINTRUST_API_KEY` environment variable.
The URL of the Braintrust App. Defaults to [https://www.braintrust.dev](https://www.braintrust.dev). You should not need
to change this unless you are doing the "Full" deployment.
Controls internal Braintrust SDK troubleshooting output.
Use `"error"`, `"warn"`, `"info"`, or `"debug"` to control how much
internal SDK troubleshooting output is emitted. Use `false` to explicitly
disable this output.
When omitted, the SDK remains silent unless
`BRAINTRUST_DEBUG_LOG_LEVEL` is set to `"error"`, `"warn"`, `"info"`, or
`"debug"`. This option only affects local console output; it does not
change what data is logged to Braintrust.
If true, disables the local span cache used to optimize scorer access
to trace data. When disabled, scorers will always fetch spans from the
server. Defaults to false.
A custom fetch implementation to use.
By default, the SDK installs an event handler that flushes pending writes on the `beforeExit` event.
If true, this event handler will *not* be installed.
Calls this function if there's an error in the background flusher.
The name of a specific organization to connect to. Since API keys are scoped to organizations, this parameter is usually
unnecessary unless you are logging in with a JWT.
Login again, even if you have already logged in (by default, this function will exit quickly if you have already logged in)
### loginToState
loginToState function
The API key to use. If the parameter is not specified, will try to use the `BRAINTRUST_API_KEY` environment variable.
The URL of the Braintrust App. Defaults to [https://www.braintrust.dev](https://www.braintrust.dev). You should not need
to change this unless you are doing the "Full" deployment.
Controls internal Braintrust SDK troubleshooting output.
Use `"error"`, `"warn"`, `"info"`, or `"debug"` to control how much
internal SDK troubleshooting output is emitted. Use `false` to explicitly
disable this output.
When omitted, the SDK remains silent unless
`BRAINTRUST_DEBUG_LOG_LEVEL` is set to `"error"`, `"warn"`, `"info"`, or
`"debug"`. This option only affects local console output; it does not
change what data is logged to Braintrust.
If true, disables the local span cache used to optimize scorer access
to trace data. When disabled, scorers will always fetch spans from the
server. Defaults to false.
A custom fetch implementation to use.
By default, the SDK installs an event handler that flushes pending writes on the `beforeExit` event.
If true, this event handler will *not* be installed.
Calls this function if there's an error in the background flusher.
The name of a specific organization to connect to. Since API keys are scoped to organizations, this parameter is usually
unnecessary unless you are logging in with a JWT.
### newId
newId function
### parseCachedHeader
parseCachedHeader function
### parseTemplateFormat
parseTemplateFormat function
### permalink
Format a permalink to the Braintrust application for viewing the span
represented by the provided `slug`.
Links can be generated at any time, but they will only become viewable after
the span and its root have been flushed to the server and ingested.
If you have a `Span` object, use `Span.link` instead.
The identifier generated from `Span.export`.
Optional arguments.
The app URL to use. If not provided, the app URL will be inferred from the state.
The org name to use. If not provided, the org name will be inferred from the state.
The login state to use. If not provided, the global state will be used.
### pickLogs3OverflowObjectIds
pickLogs3OverflowObjectIds function
### promptDefinitionToPromptData
promptDefinitionToPromptData function
### registerOtelFlush
Register a callback to flush OTEL spans. This is called by @braintrust/otel
when it initializes a BraintrustSpanProcessor/Exporter.
When ensureSpansFlushed is called (e.g., before a BTQL query in scorers),
this callback will be invoked to ensure OTEL spans are flushed to the server.
Also disables the span cache, since OTEL spans aren't in the local cache
and we need BTQL to see the complete span tree (both native + OTEL spans).
### registerTemplatePlugin
Register a template plugin and optionally activate it
If `options` is provided it will be used to create the active renderer.
If `options` is omitted but the plugin defines `defaultOptions`, the
registry will activate the renderer using those defaults.
Factory function that creates a renderer instance.
Default configuration options for this plugin.
Unique identifier for this plugin.
Must match the format string used in `templateFormat` option.
### renderMessage
renderMessage function
### renderPromptParams
renderPromptParams function
### renderTemplateContent
renderTemplateContent function
### Reporter
Reporter function
### reportFailures
reportFailures function
An optional experiment id to use as a base. If specified, the new experiment will be summarized
and compared to this experiment. This takes precedence over `baseExperimentName` if specified.
An optional experiment name to use as a base. If specified, the new experiment will be summarized
and compared to this experiment.
A function that returns a list of inputs, expected outputs, and metadata.
An optional description for the experiment.
Optionally supply a custom function to specifically handle score values when tasks or scoring functions have errored.
A default implementation is exported as `defaultErrorScoreHandler` which will log a 0 score to the root span for any scorer that was not run.
An optional name for the experiment.
Flushes spans before calling scoring functions
Optional settings for collecting git metadata. By default, will collect all git metadata fields allowed in org-level settings.
Whether the experiment should be public. Defaults to false.
The maximum number of tasks/scorers that will be run concurrently.
Defaults to undefined, in which case there is no max concurrency.
Optional additional metadata for the experiment.
A set of parameters that will be passed to the evaluator.
Can be:
* A raw EvalParameters schema (Zod schemas)
* A Parameters instance from loadParameters()
* A Promise\ from loadParameters()
If specified, uses the given project ID instead of the evaluator's name to identify the project.
Optionally explicitly specify the git metadata for this experiment. This takes precedence over `gitMetadataSettings` if specified.
A set of functions that take an input, output, and expected value and return a score.
An abort signal that can be used to stop the evaluation.
If specified, uses the logger state to initialize Braintrust objects. If unspecified, falls back
to the global state (initialized using your API key).
Whether to summarize the scores of the experiment after it has run.
Defaults to true.
Optional tags for the experiment.
A function that takes an input and returns an output.
The duration, in milliseconds, after which to time out the evaluation.
Defaults to undefined, in which case there is no timeout.
The number of times to run the evaluator per input. This is useful for evaluating applications that
have non-deterministic behavior and gives you both a stronger aggregate measure and a sense of the
variance in the results.
Whether to update an existing experiment with `experiment_name` if one exists. Defaults to false.
### runEvaluator
runEvaluator function
An optional experiment id to use as a base. If specified, the new experiment will be summarized
and compared to this experiment. This takes precedence over `baseExperimentName` if specified.
An optional experiment name to use as a base. If specified, the new experiment will be summarized
and compared to this experiment.
A function that returns a list of inputs, expected outputs, and metadata.
An optional description for the experiment.
Optionally supply a custom function to specifically handle score values when tasks or scoring functions have errored.
A default implementation is exported as `defaultErrorScoreHandler` which will log a 0 score to the root span for any scorer that was not run.
An optional name for the experiment.
Flushes spans before calling scoring functions
Optional settings for collecting git metadata. By default, will collect all git metadata fields allowed in org-level settings.
Whether the experiment should be public. Defaults to false.
The maximum number of tasks/scorers that will be run concurrently.
Defaults to undefined, in which case there is no max concurrency.
Optional additional metadata for the experiment.
A set of parameters that will be passed to the evaluator.
Can be:
* A raw EvalParameters schema (Zod schemas)
* A Parameters instance from loadParameters()
* A Promise\ from loadParameters()
If specified, uses the given project ID instead of the evaluator's name to identify the project.
Optionally explicitly specify the git metadata for this experiment. This takes precedence over `gitMetadataSettings` if specified.
A set of functions that take an input, output, and expected value and return a score.
An abort signal that can be used to stop the evaluation.
If specified, uses the logger state to initialize Braintrust objects. If unspecified, falls back
to the global state (initialized using your API key).
Whether to summarize the scores of the experiment after it has run.
Defaults to true.
Optional tags for the experiment.
A function that takes an input and returns an output.
The duration, in milliseconds, after which to time out the evaluation.
Defaults to undefined, in which case there is no timeout.
The number of times to run the evaluator per input. This is useful for evaluating applications that
have non-deterministic behavior and gives you both a stronger aggregate measure and a sense of the
variance in the results.
Whether to update an existing experiment with `experiment_name` if one exists. Defaults to false.
### setFetch
Set the fetch implementation to use for requests. You can specify it here,
or when you call `login`.
The fetch implementation to use.
### setMaskingFunction
Set a global masking function that will be applied to all logged data before sending to Braintrust.
The masking function will be applied after records are merged but before they are sent to the backend.
A function that takes a JSON-serializable object and returns a masked version.
Set to null to disable masking.
### spanComponentsToObjectId
spanComponentsToObjectId function
### startSpan
Lower-level alternative to `traced`. This allows you to start a span yourself, and can be useful in situations
where you cannot use callbacks. However, spans started with `startSpan` will not be marked as the "current span",
so `currentSpan()` and `traced()` will be no-ops. If you want to mark a span as current, use `traced` instead.
See [`traced`](#traced) for full details.
### summarize
Summarize the current experiment, including the scores (compared to the closest reference experiment) and metadata.
Options for summarizing the experiment.
The experiment to compare against. If None, the most recent experiment on the origin's main branch will be used.
Whether to summarize the scores. If False, only the metadata will be returned.
### traceable
A synonym for `wrapTraced`. If you're porting from systems that use `traceable`, you can use this to
make your codebase more consistent.
### traced
Toplevel function for starting a span. It checks the following (in precedence order):
* Currently-active span
* Currently-active experiment
* Currently-active logger
and creates a span under the first one that is active. Alternatively, if `parent` is specified, it creates a span under the specified parent row. If none of these are active, it returns a no-op span object.
See `Span.traced` for full details.
### updateSpan
Update a span using the output of `span.export()`. It is important that you only resume updating
to a span once the original span has been fully written and flushed, since otherwise updates to
the span may conflict with the original span.
### uploadLogs3OverflowPayload
Upload a logs3 overflow payload to the signed URL.
This is a standalone function that can be used by both SDK and app code.
The overflow upload metadata from the API
The JSON payload string to upload
Optional custom fetch function (defaults to global fetch)
### utf8ByteLength
utf8ByteLength function
### withCurrent
Runs the provided callback with the span as the current span.
Row ID of the span.
Root span ID of the span.
Span ID of the span.
Parent span IDs of the span.
### withDataset
withDataset function
The API key to use. If the parameter is not specified, will try to use the `BRAINTRUST_API_KEY` environment variable.
The URL of the Braintrust App. Defaults to [https://www.braintrust.dev](https://www.braintrust.dev). You should not need
to change this unless you are doing the "Full" deployment.
Controls internal Braintrust SDK troubleshooting output.
Use `"error"`, `"warn"`, `"info"`, or `"debug"` to control how much
internal SDK troubleshooting output is emitted. Use `false` to explicitly
disable this output.
When omitted, the SDK remains silent unless
`BRAINTRUST_DEBUG_LOG_LEVEL` is set to `"error"`, `"warn"`, `"info"`, or
`"debug"`. This option only affects local console output; it does not
change what data is logged to Braintrust.
If true, disables the local span cache used to optimize scorer access
to trace data. When disabled, scorers will always fetch spans from the
server. Defaults to false.
A custom fetch implementation to use.
By default, the SDK installs an event handler that flushes pending writes on the `beforeExit` event.
If true, this event handler will *not* be installed.
Calls this function if there's an error in the background flusher.
The name of a specific organization to connect to. Since API keys are scoped to organizations, this parameter is usually
unnecessary unless you are logging in with a JWT.
### withExperiment
withExperiment function
The API key to use. If the parameter is not specified, will try to use the `BRAINTRUST_API_KEY` environment variable.
The URL of the Braintrust App. Defaults to [https://www.braintrust.dev](https://www.braintrust.dev). You should not need
to change this unless you are doing the "Full" deployment.
Controls internal Braintrust SDK troubleshooting output.
Use `"error"`, `"warn"`, `"info"`, or `"debug"` to control how much
internal SDK troubleshooting output is emitted. Use `false` to explicitly
disable this output.
When omitted, the SDK remains silent unless
`BRAINTRUST_DEBUG_LOG_LEVEL` is set to `"error"`, `"warn"`, `"info"`, or
`"debug"`. This option only affects local console output; it does not
change what data is logged to Braintrust.
If true, disables the local span cache used to optimize scorer access
to trace data. When disabled, scorers will always fetch spans from the
server. Defaults to false.
A custom fetch implementation to use.
By default, the SDK installs an event handler that flushes pending writes on the `beforeExit` event.
If true, this event handler will *not* be installed.
Calls this function if there's an error in the background flusher.
The name of a specific organization to connect to. Since API keys are scoped to organizations, this parameter is usually
unnecessary unless you are logging in with a JWT.
### withLogger
withLogger function
The API key to use. If the parameter is not specified, will try to use the `BRAINTRUST_API_KEY` environment variable.
The URL of the Braintrust App. Defaults to [https://www.braintrust.dev](https://www.braintrust.dev). You should not need
to change this unless you are doing the "Full" deployment.
Controls internal Braintrust SDK troubleshooting output.
Use `"error"`, `"warn"`, `"info"`, or `"debug"` to control how much
internal SDK troubleshooting output is emitted. Use `false` to explicitly
disable this output.
When omitted, the SDK remains silent unless
`BRAINTRUST_DEBUG_LOG_LEVEL` is set to `"error"`, `"warn"`, `"info"`, or
`"debug"`. This option only affects local console output; it does not
change what data is logged to Braintrust.
If true, disables the local span cache used to optimize scorer access
to trace data. When disabled, scorers will always fetch spans from the
server. Defaults to false.
A custom fetch implementation to use.
By default, the SDK installs an event handler that flushes pending writes on the `beforeExit` event.
If true, this event handler will *not* be installed.
Calls this function if there's an error in the background flusher.
The name of a specific organization to connect to. Since API keys are scoped to organizations, this parameter is usually
unnecessary unless you are logging in with a JWT.
### withParent
withParent function
### wrapAgentClass
wrapAgentClass function
### wrapAISDK
Wraps Vercel AI SDK methods with Braintrust tracing.
### wrapAISDKModel
Wrap an ai-sdk model (created with `.chat()`, `.completion()`, etc.) to add tracing. If Braintrust is
not configured, this is a no-op
### wrapAnthropic
Wrap an `Anthropic` object (created with `new Anthropic(...)`) so calls emit
tracing-channel events that Braintrust plugins can consume.
Currently, this only supports the `v4` API.
### wrapClaudeAgentSDK
Wraps the Claude Agent SDK with Braintrust tracing. Query calls only publish
tracing-channel events; the Claude Agent SDK plugin owns all span lifecycle
work, including root/task spans, LLM spans, tool spans, and sub-agent spans.
The Claude Agent SDK module
### wrapGoogleGenAI
Wrap a Google GenAI module (imported with `import * as googleGenAI from '@google/genai'`) to add tracing.
If Braintrust is not configured, nothing will be traced.
The Google GenAI module
### wrapMastraAgent
wrapMastraAgent function
### wrapOpenAI
Wrap an `OpenAI` object (created with `new OpenAI(...)`) to add tracing. If Braintrust is
not configured, nothing will be traced. If this is not an `OpenAI` object, this function is
a no-op.
Currently, this supports the `v4`, `v5`, and `v6` API.
### wrapOpenAIv4
wrapOpenAIv4 function
### wrapOpenRouter
Wrap an OpenRouter client (created with `new OpenRouter(...)`) so calls emit
diagnostics-channel events that Braintrust plugins can consume.
### wrapTraced
Wrap a function with `traced`, using the arguments as `input` and return value as `output`.
Any functions wrapped this way will automatically be traced, similar to the `@traced` decorator
in Python. If you want to correctly propagate the function's name and define it in one go, then
you can do so like this:
```ts theme={"theme":{"light":"github-light","dark":"github-dark-dimmed"}}
const myFunc = wrapTraced(async function myFunc(input) {
const result = await client.chat.completions.create({
model: "gpt-3.5-turbo",
messages: [{ role: "user", content: input }],
});
return result.choices[0].message.content ?? "unknown";
},
// Optional: if you're using a framework like NextJS that minifies your code, specify the function name and it will be used for the span name
{ name: "myFunc" },
);
```
Now, any calls to `myFunc` will be traced, and the input and output will be logged automatically.
If tracing is inactive, i.e. there is no active logger or experiment, it's just a no-op.
The function to wrap.
Span-level arguments (e.g. a custom name or type) to pass to `traced`.
### wrapVitest
Wraps Vitest methods with Braintrust experiment tracking. This automatically creates
datasets and experiments from your Vitest tests, tracking pass/fail rates and evaluation metrics.
Experiments are automatically flushed after all tests complete.
Object containing Vitest methods (test, describe, expect, etc.)
Optional configuration object
## Classes
### Attachment
Represents an attachment to be uploaded and the associated metadata.
`Attachment` objects can be inserted anywhere in an event, allowing you to
log arbitrary file data. The SDK will asynchronously upload the file to
object storage and replace the `Attachment` object with an
`AttachmentReference`.
Properties
The object that replaces this `Attachment` at upload time.
Methods
`data()`, `debugInfo()`, `upload()`
### BaseAttachment
BaseAttachment class
Properties
Methods
`data()`, `debugInfo()`, `upload()`
### BraintrustState
BraintrustState class
Properties
Methods
`[RESET_CONTEXT_MANAGER_STATE]()`, `apiConn()`, `appConn()`, `bgLogger()`, `copyLoginInfo()`, `disable()`, `enforceQueueSizeLimit()`, `flushOtel()`, `getDebugLogLevel()`, `hasDebugLogLevelOverride()`, `httpLogger()`, `login()`, `loginReplaceApiConn()`, `proxyConn()`, `registerOtelFlush()`, `resetIdGenState()`, `resetLoginInfo()`, `serialize()`, `setDebugLogLevel()`, `setFetch()`, `setMaskingFunction()`, `setOverrideBgLogger()`, `toJSON()`, `toString()`, `deserialize()`
### BraintrustStream
A Braintrust stream. This is a wrapper around a ReadableStream of `BraintrustStreamChunk`,
with some utility methods to make them easy to log and convert into various formats.
Methods
`[asyncIterator]()`, `copy()`, `finalValue()`, `toReadableStream()`, `parseRawEvent()`, `serializeRawEvent()`
### CachedSpanFetcher
Cached span fetcher that handles fetching and caching spans by type.
Caching strategy:
* Cache spans by span type (Map\)
* Track if all spans have been fetched (allFetched flag)
* When filtering by spanType, only fetch types not already in cache
Methods
`getSpans()`
### CodeFunction
CodeFunction class
Properties
Methods
`key()`
### CodePrompt
CodePrompt class
Properties
Methods
`toFunctionDefinition()`
### ContextManager
ContextManager class
Methods
`getCurrentSpan()`, `getParentSpanIds()`, `runInContext()`
### Dataset
A dataset is a collection of records, such as model inputs and expected outputs, which represent
data you can use to evaluate and fine-tune models. You can log production data to datasets,
curate them with interesting examples, edit/delete records, and run evaluations against them.
You should not create `Dataset` objects directly. Instead, use the `braintrust.initDataset()` method.
Properties
Methods
`[asyncIterator]()`, `clearCache()`, `close()`, `delete()`, `fetch()`, `fetchedData()`, `flush()`, `getState()`, `insert()`, `summarize()`, `update()`, `version()`, `isDataset()`
### EvalResultWithSummary
EvalResultWithSummary class
Properties
Methods
`toJSON()`, `toString()`
### Experiment
An experiment is a collection of logged events, such as model inputs and outputs, which represent
a snapshot of your application at a particular point in time. An experiment is meant to capture more
than just the model you use, and includes the data you use to test, pre- and post- processing code,
comparison metrics (scores), and any other metadata you want to include.
Experiments are associated with a project, and two experiments are meant to be easily comparable via
their `inputs`. You can change the attributes of the experiments in a project (e.g. scoring functions)
over time, simply by changing what you log.
You should not create `Experiment` objects directly. Instead, use the `braintrust.init()` method.
Properties
Methods
`[asyncIterator]()`, `clearCache()`, `close()`, `export()`, `fetch()`, `fetchBaseExperiment()`, `fetchedData()`, `flush()`, `getState()`, `log()`, `logFeedback()`, `startSpan()`, `summarize()`, `traced()`, `updateSpan()`, `version()`
### ExternalAttachment
Represents an attachment that resides in an external object store and the associated metadata.
`ExternalAttachment` objects can be inserted anywhere in an event, similar to
`Attachment` objects, but they reference files that already exist in an external
object store rather than requiring upload. The SDK will replace the `ExternalAttachment`
object with an `AttachmentReference` during logging.
Properties
The object that replaces this `ExternalAttachment` at upload time.
Methods
`data()`, `debugInfo()`, `upload()`
### FailedHTTPResponse
FailedHTTPResponse class
Properties
### IDGenerator
Abstract base class for ID generators
Methods
`getSpanId()`, `getTraceId()`, `shareRootSpanId()`
### JSONAttachment
Represents a JSON object that should be stored as an attachment.
`JSONAttachment` is a convenience function that creates an `Attachment`
from JSON data. It's particularly useful for large JSON objects that
would otherwise bloat the trace size.
The JSON data is automatically serialized and stored as an attachment
with content type "application/json".
Properties
The object that replaces this `Attachment` at upload time.
Methods
`data()`, `debugInfo()`, `upload()`
### LazyValue
LazyValue class
Properties
Methods
`get()`, `getSync()`
### Logger
Logger class
Properties
Methods
`export()`, `flush()`, `log()`, `logFeedback()`, `startSpan()`, `traced()`, `updateSpan()`
### LoginInvalidOrgError
LoginInvalidOrgError class
Properties
### NoopSpan
A fake implementation of the Span API which does nothing. This can be used as the default span.
Properties
Row ID of the span.
Root span ID of the span.
Span ID of the span.
Parent span IDs of the span.
Methods
`close()`, `end()`, `export()`, `flush()`, `getParentInfo()`, `link()`, `log()`, `logFeedback()`, `permalink()`, `setAttributes()`, `startSpan()`, `startSpanWithParents()`, `state()`, `toString()`, `traced()`
### ObjectFetcher
ObjectFetcher class
Properties
Methods
`[asyncIterator]()`, `clearCache()`, `fetch()`, `fetchedData()`, `getState()`, `version()`
### Project
Project class
Properties
Methods
`addCodeFunction()`, `addParameters()`, `addPrompt()`, `publish()`
### ProjectNameIdMap
ProjectNameIdMap class
Methods
`getId()`, `getName()`, `resolve()`
### Prompt
Prompt class
Properties
Methods
`build()`, `buildWithAttachments()`, `fromPromptData()`, `isPrompt()`, `renderPrompt()`
### PromptBuilder
PromptBuilder class
Methods
`create()`
### ReadonlyAttachment
A readonly alternative to `Attachment`, which can be used for fetching
already-uploaded Attachments.
Properties
Attachment metadata.
Methods
`asBase64Url()`, `data()`, `metadata()`, `status()`
### ReadonlyExperiment
A read-only view of an experiment, initialized by passing `open: true` to `init()`.
Properties
Methods
`[asyncIterator]()`, `asDataset()`, `clearCache()`, `fetch()`, `fetchedData()`, `getState()`, `version()`
### ScorerBuilder
ScorerBuilder class
Methods
`create()`
### SpanFetcher
Fetcher for spans by root\_span\_id, using the ObjectFetcher pattern.
Handles pagination automatically via cursor-based iteration.
Properties
Methods
`[asyncIterator]()`, `clearCache()`, `fetch()`, `fetchedData()`, `getState()`, `version()`
### SpanImpl
Primary implementation of the `Span` interface. See [`Span`](#span) for full details on each method.
We suggest using one of the various `traced` methods, instead of creating Spans directly. See `Span.startSpan` for full details.
Properties
Row ID of the span.
Root span ID of the span.
Span ID of the span.
Parent span IDs of the span.
Methods
`close()`, `end()`, `export()`, `flush()`, `getParentInfo()`, `link()`, `log()`, `logFeedback()`, `permalink()`, `setAttributes()`, `setSpanParents()`, `startSpan()`, `startSpanWithParents()`, `state()`, `toString()`, `traced()`
### TestBackgroundLogger
TestBackgroundLogger class
Methods
`drain()`, `flush()`, `flushBackpressureBytes()`, `log()`, `pendingFlushBytes()`, `setMaskingFunction()`
### ToolBuilder
ToolBuilder class
Methods
`create()`
### UUIDGenerator
ID generator that uses UUID4 for both span and trace IDs
Methods
`getSpanId()`, `getTraceId()`, `shareRootSpanId()`
## Interfaces
### AttachmentParams
AttachmentParams interface
Properties
### BackgroundLoggerOpts
BackgroundLoggerOpts interface
Properties
### ContextParentSpanIds
ContextParentSpanIds interface
Properties
### DatasetSummary
Summary of a dataset's scores and metadata.
Properties
Summary of the dataset's data.
Name of the dataset.
URL to the experiment's page in the Braintrust app.
Name of the project that the dataset belongs to.
URL to the project's page in the Braintrust app.
### DataSummary
Summary of a dataset's data.
Properties
New or updated records added in this session.
Total records in the dataset.
### EvalHooks
EvalHooks interface
Properties
The expected output for the current evaluation.
The metadata object for the current evaluation. You can mutate this object to add or remove metadata.
The current parameters being used for this specific task execution.
Array parameters are converted to single values.
Report progress that will show up in the playground.
The task's span.
The tags for the current evaluation.
The index of the current trial (0-based). This is useful when trialCount > 1.
### Evaluator
Evaluator interface
Properties
An optional experiment id to use as a base. If specified, the new experiment will be summarized
and compared to this experiment. This takes precedence over `baseExperimentName` if specified.
An optional experiment name to use as a base. If specified, the new experiment will be summarized
and compared to this experiment.
A function that returns a list of inputs, expected outputs, and metadata.
An optional description for the experiment.
Optionally supply a custom function to specifically handle score values when tasks or scoring functions have errored.
A default implementation is exported as `defaultErrorScoreHandler` which will log a 0 score to the root span for any scorer that was not run.
An optional name for the experiment.
Flushes spans before calling scoring functions
Optional settings for collecting git metadata. By default, will collect all git metadata fields allowed in org-level settings.
Whether the experiment should be public. Defaults to false.
The maximum number of tasks/scorers that will be run concurrently.
Defaults to undefined, in which case there is no max concurrency.
Optional additional metadata for the experiment.
A set of parameters that will be passed to the evaluator.
Can be:
* A raw EvalParameters schema (Zod schemas)
* A Parameters instance from loadParameters()
* A Promise\ from loadParameters()
If specified, uses the given project ID instead of the evaluator's name to identify the project.
Optionally explicitly specify the git metadata for this experiment. This takes precedence over `gitMetadataSettings` if specified.
A set of functions that take an input, output, and expected value and return a score.
An abort signal that can be used to stop the evaluation.
If specified, uses the logger state to initialize Braintrust objects. If unspecified, falls back
to the global state (initialized using your API key).
Whether to summarize the scores of the experiment after it has run.
Defaults to true.
Optional tags for the experiment.
A function that takes an input and returns an output.
The duration, in milliseconds, after which to time out the evaluation.
Defaults to undefined, in which case there is no timeout.
The number of times to run the evaluator per input. This is useful for evaluating applications that
have non-deterministic behavior and gives you both a stronger aggregate measure and a sense of the
variance in the results.
Whether to update an existing experiment with `experiment_name` if one exists. Defaults to false.
### ExperimentSummary
Summary of an experiment's scores and metadata.
Properties
The experiment scores are baselined against.
ID of the experiment. May be `undefined` if the eval was run locally.
Name of the experiment.
URL to the experiment's page in the Braintrust app.
Name of the project that the experiment belongs to.
URL to the project's page in the Braintrust app.
Summary of the experiment's scores.
### Exportable
Exportable interface
### ExternalAttachmentParams
ExternalAttachmentParams interface
Properties
### FunctionEvent
FunctionEvent interface
Properties
### GetThreadOptions
Options for getThread().
Properties
The preprocessor to use for extracting the thread.
If not specified, uses the project default preprocessor,
falling back to the global "thread" preprocessor.
### InstrumentationConfig
InstrumentationConfig interface
Properties
Configuration for individual SDK integrations.
Set to false to disable instrumentation for that SDK.
### InvokeFunctionArgs
Arguments for the `invoke` function.
Properties
The type of the global function to invoke. If unspecified, defaults to 'scorer' for backward compatibility.
The ID of the function to invoke.
The name of the global function to invoke.
The input to the function. This will be logged as the `input` field in the span.
Additional OpenAI-style messages to add to the prompt (only works for llm functions).
Additional metadata to add to the span. This will be logged as the `metadata` field in the span.
It will also be available as the \{\{metadata}} field in the prompt and as the `metadata` argument
to the function.
The mode of the function. If "auto", will return a string if the function returns a string,
and a JSON object otherwise. If "parallel", will return an array of JSON objects with one
object per tool call.
The parent of the function. This can be an existing span, logger, or experiment, or
the output of `.export()` if you are distributed tracing. If unspecified, will use
the same semantics as `traced()` to determine the parent and no-op if not in a tracing
context.
The ID of the project to use for execution context (API keys, project defaults, etc.).
This is not the project the function belongs to, but the project context for the invocation.
The name of the project containing the function to invoke.
The ID of the function in the prompt session to invoke.
The ID of the prompt session to invoke the function from.
A Zod schema to validate the output of the function and return a typed value. This
is only used if `stream` is false.
The slug of the function to invoke.
(Advanced) This parameter allows you to pass in a custom login state. This is useful
for multi-tenant environments where you are running functions from different Braintrust
organizations.
Whether to stream the function's output. If true, the function will return a
`BraintrustStream`, otherwise it will return the output of the function as a JSON
object.
Whether to use strict mode for the function. If true, the function will throw an error
if the variable names in the prompt do not match the input keys.
Tags to add to the span. This will be logged as the `tags` field in the span.
The version of the function to invoke.
### LoginOptions
Options for logging in to Braintrust.
Properties
The API key to use. If the parameter is not specified, will try to use the `BRAINTRUST_API_KEY` environment variable.
The URL of the Braintrust App. Defaults to [https://www.braintrust.dev](https://www.braintrust.dev). You should not need
to change this unless you are doing the "Full" deployment.
Controls internal Braintrust SDK troubleshooting output.
Use `"error"`, `"warn"`, `"info"`, or `"debug"` to control how much
internal SDK troubleshooting output is emitted. Use `false` to explicitly
disable this output.
When omitted, the SDK remains silent unless
`BRAINTRUST_DEBUG_LOG_LEVEL` is set to `"error"`, `"warn"`, `"info"`, or
`"debug"`. This option only affects local console output; it does not
change what data is logged to Braintrust.
If true, disables the local span cache used to optimize scorer access
to trace data. When disabled, scorers will always fetch spans from the
server. Defaults to false.
A custom fetch implementation to use.
By default, the SDK installs an event handler that flushes pending writes on the `beforeExit` event.
If true, this event handler will *not* be installed.
Calls this function if there's an error in the background flusher.
The name of a specific organization to connect to. Since API keys are scoped to organizations, this parameter is usually
unnecessary unless you are logging in with a JWT.
### LogOptions
LogOptions interface
Properties
### MetricSummary
Summary of a metric's performance.
Properties
Difference in metric between the current and reference experiment.
Number of improvements in the metric.
Average metric across all examples.
Name of the metric.
Number of regressions in the metric.
Unit label for the metric.
### ObjectMetadata
ObjectMetadata interface
Properties
### ParentExperimentIds
ParentExperimentIds interface
Properties
### ParentProjectLogIds
ParentProjectLogIds interface
Properties
### ReporterBody
ReporterBody interface
### ScoreSummary
Summary of a score's performance.
Properties
Difference in score between the current and reference experiment.
Number of improvements in the score.
Name of the score.
Number of regressions in the score.
Average score across all examples.
### Span
A Span encapsulates logged data and metrics for a unit of work. This interface is shared by all span implementations.
We suggest using one of the various `traced` methods, instead of creating Spans directly. See `Span.traced` for full details.
Properties
Row ID of the span.
Root span ID of the span.
Span ID of the span.
Parent span IDs of the span.
### SpanData
Span data returned by getSpans().
Properties
### TemplateRenderer
TemplateRenderer interface
Properties
### TemplateRendererPlugin
A template renderer plugin that can be registered with Braintrust.
Plugins provide support for different template engines (e.g., Nunjucks).
They use a factory pattern where the plugin is registered once, then activated with specific
configuration options when needed.
Properties
Factory function that creates a renderer instance.
Default configuration options for this plugin.
Unique identifier for this plugin.
Must match the format string used in `templateFormat` option.
### Trace
Interface for trace objects that can be used by scorers.
Both the SDK's LocalTrace class and the API wrapper's WrapperTrace implement this.