> ## Documentation Index
> Fetch the complete documentation index at: https://composio-preview.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Langfuse

> Open source LLM engineering platform. Traces, evals, prompt management and metrics to debug and improve your LLM application.

![Langfuse logo](https://mintcdn.com/composio-preview/tIuAovF9-7pXq2wA/images/toolkits/langfuse.svg?fit=max\&auto=format\&n=tIuAovF9-7pXq2wA\&q=85\&s=32610a0005392c3ee823bc05c47c6cbe)

* **Category:** developer tools
* **Auth:** API\_KEY
* **Composio-managed OAuth available?** N/A
* **Tools:** 13
* **Triggers:** 0
* **Slug:** `LANGFUSE`
* **Version:** 20261101\_00

## Tools

> [accordion] Add Annotation Queue Item
>
> **Slug:** `LANGFUSE_ADD_ANNOTATION_QUEUE_ITEM`
>
> Add a trace, observation, or session to a Langfuse annotation queue by queue ID and object ID. Optionally set the item's annotation status.
>
> #### Input Parameters
>
> **status** `string ("PENDING" | "COMPLETED")`
>
> Item status. Defaults to PENDING for new queue items.
>
> **queueId** `string` *required*
>
> Unique identifier of the annotation queue to add the item to.
>
> **objectId** `string` *required*
>
> ID of the trace, observation, or session to annotate.
>
> **objectType** `string ("TRACE" | "OBSERVATION" | "SESSION")` *required*
>
> Type of the object to add to the annotation queue.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Assign Annotation Queue User
>
> **Slug:** `LANGFUSE_ASSIGN_ANNOTATION_QUEUE_USER`
>
> Assign a user to a Langfuse annotation queue by queue ID and user ID. Returns the user, queue, and project IDs for the created assignment.
>
> #### Input Parameters
>
> **userId** `string` *required*
>
> Unique identifier of the user to assign to the queue.
>
> **queueId** `string` *required*
>
> Unique identifier of the annotation queue to assign the user to.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Check Health
>
> **Slug:** `LANGFUSE_CHECK_HEALTH`
>
> Check the health of the Langfuse API and database. Returns the server version and health status.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Create annotation queue
>
> **Slug:** `LANGFUSE_CREATE_ANNOTATION_QUEUE`
>
> Create an annotation queue in the authenticated Langfuse project for human evaluation, using the supplied score configuration IDs. Returns the created queue and its ID.
>
> #### Input Parameters
>
> **name** `string` *required*
>
> Name of the annotation queue to create.
>
> **description** `string`
>
> Optional description of the annotation queue.
>
> **scoreConfigIds** `array` *required*
>
> Score configuration IDs to use for human evaluation in this queue.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Create comment
>
> **Slug:** `LANGFUSE_CREATE_COMMENT`
>
> Create a comment on an existing Langfuse trace, observation, session, or prompt in the specified project. Supports Markdown content and an optional author who belongs to the project's organization. Returns the created comment ID.
>
> #### Input Parameters
>
> **content** `string` *required*
>
> Comment content, optionally including Markdown; limited to 5000 characters.
>
> **objectId** `string` *required*
>
> ID of an existing object to attach the comment to; invalid IDs cause an error.
>
> **projectId** `string` *required*
>
> ID of the project to attach the comment to.
>
> **objectType** `string` *required*
>
> Type of object to attach the comment to: TRACE, OBSERVATION, SESSION, or PROMPT (uppercase).
>
> **authorUserId** `string`
>
> Optional ID of the comment author. The user must belong to the organization that owns the project, otherwise an error is returned.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Create Dataset
>
> **Slug:** `LANGFUSE_CREATE_DATASET`
>
> Create a dataset in the connected Langfuse project, optionally with a description, metadata, and JSON Schemas for item inputs and expected outputs. This creates the dataset container; add dataset items separately.
>
> #### Input Parameters
>
> **name** `string` *required*
>
> Name of the dataset to create.
>
> **metadata** `string`
>
> Arbitrary JSON metadata associated with the dataset.
>
> **description** `string`
>
> Optional dataset description.
>
> **inputSchema** `string`
>
> JSON Schema for validating dataset item inputs. When set, all new and existing dataset items are validated against it.
>
> **expectedOutputSchema** `string`
>
> JSON Schema for validating dataset item expected outputs. When set, all new and existing dataset items are validated against it.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Create Dataset Item
>
> **Slug:** `LANGFUSE_CREATE_DATASET_ITEM`
>
> Create a Langfuse dataset item with input, expected output, and metadata. Providing an existing item ID updates that item in the same dataset.
>
> #### Input Parameters
>
> **id** `string`
>
> Optional item ID for upsert. Must be unique within the project and cannot be reused across datasets; at most 255 characters.
>
> **input** `string`
>
> Arbitrary JSON input for the dataset item.
>
> **status** `string ("ACTIVE" | "ARCHIVED")`
>
> Item status. Defaults to ACTIVE for newly created items.
>
> **metadata** `string`
>
> Arbitrary JSON metadata associated with the dataset item.
>
> **datasetName** `string` *required*
>
> Name of the dataset to contain the item.
>
> **sourceTraceId** `string`
>
> ID of the trace that sourced this dataset item.
>
> **expectedOutput** `string`
>
> Arbitrary JSON expected output for the dataset item.
>
> **sourceObservationId** `string`
>
> ID of the observation that sourced this dataset item.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Create Evaluation Rule
>
> **Slug:** `LANGFUSE_CREATE_EVALUATION_RULE`
>
> Create a Langfuse evaluation rule for incoming observations, using stable evaluator IDs and their latest versions. Explicitly choose enabled: true starts automatic evaluations and may incur model costs; false creates a disabled draft. Omitted filters match all observations and omitted sampling evaluates every match. Rule names need not be unique.
>
> #### Input Parameters
>
> **name** `string` *required*
>
> Human-readable rule name; need not be unique.
>
> **filter** `array`
>
> AND-combined observation filters. Omit for all observations. Select experiment datasets using datasetId/stringOptions with dataset IDs, and experiment roots using isExperimentItemRootSpan/boolean. Metadata uses stringObject with key; tags and calledToolNames use arrayOptions; parentObservationId uses null; toolCalls uses number.
>
> **enabled** `boolean` *required*
>
> Required explicit choice: true starts live evaluations immediately and may incur model costs; false creates a disabled draft. True requires evaluators.
>
> **sampling** `number`
>
> Fraction of matches to evaluate (0–1). Omit for provider default 1 (every match); explicit null is not accepted.
>
> **evaluatorAssignments** `array` *required*
>
> Evaluators to attach. An empty list is allowed only for a disabled draft.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Create evaluator
>
> **Slug:** `LANGFUSE_CREATE_EVALUATOR`
>
> Create a version-1 evaluator in the authenticated Langfuse project. Choose llm\_as\_judge with a prompt and structured score output, or code with source code and runtime language. Names need not be unique. An evaluator defines how to score data; evaluation rules separately determine which data to evaluate.
>
> #### Input Parameters
>
> **name** `string` *required*
>
> Human-readable evaluator name; need not be unique.
>
> **type** `string ("llm_as_judge" | "code")` *required*
>
> Evaluator definition type.
>
> **prompt** `string`
>
> Required for llm\_as\_judge: user prompt string or ordered messages. A system message is allowed only first. Omit for code.
>
> **sourceCode** `string`
>
> Required for code: source code executed for matched observations. Omit for llm\_as\_judge.
>
> **description** `string`
>
> Optional evaluator description.
>
> **modelConfig** `object`
>
> LLM model configuration; null or omission uses the project's default evaluation model. Omit for code.
>
> **variableMapping** `array`
>
> LLM default prompt-variable mappings, or null for no default. Map each prompt variable exactly once. Omit for code.
>
> **outputDefinition** `string`
>
> Required for llm\_as\_judge: flat structured score definition. Omit for code.
>
> **sourceCodeLanguage** `string ("PYTHON" | "TYPESCRIPT")`
>
> Required for code: source runtime language. Omit for llm\_as\_judge.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Create media upload URL
>
> **Slug:** `LANGFUSE_CREATE_MEDIA_UPLOAD_URL`
>
> Obtain a presigned upload URL and media ID for Langfuse media associated with either a trace (optionally an observation) or a dataset item. Requires the media MIME type, byte length, SHA-256 hash, and containing field. Only requests the URL; does not upload a file. The URL can be null if already uploaded.
>
> #### Input Parameters
>
> **field** `string ("input" | "output" | "expectedOutput" | "metadata")` *required*
>
> Field containing the media: input/output/metadata for a trace, or input/expectedOutput/metadata for a dataset item.
>
> **traceId** `string`
>
> Associated trace ID. Null for dataset item media uploads.
>
> **datasetId** `string`
>
> Associated dataset ID. Null for trace/observation uploads.
>
> **sha256Hash** `string` *required*
>
> Base64-encoded SHA-256 digest of the media bytes (44 characters), not a hex digest.
>
> **contentType** `string ("image/png" | "image/jpeg" | "image/jpg" | "image/webp" | "image/gif" | "image/svg+xml" | "image/tiff" | "image/bmp" | "image/avif" | "image/heic" | "audio/mpeg" | "audio/mp3" | "audio/wav" | "audio/ogg" | "audio/oga" | "audio/aac" | "audio/mp4" | "audio/flac" | "audio/opus" | "audio/webm" | "video/mp4" | "video/webm" | "video/ogg" | "video/mpeg" | "video/quicktime" | "video/x-msvideo" | "video/x-matroska" | "text/plain" | "text/html" | "text/css" | "text/csv" | "text/markdown" | "text/x-python" | "application/javascript" | "text/x-typescript" | "application/x-yaml" | "application/pdf" | "application/msword" | "application/vnd.ms-excel" | "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet" | "application/zip" | "application/json" | "application/xml" | "application/octet-stream" | "application/vnd.openxmlformats-officedocument.wordprocessingml.document" | "application/vnd.openxmlformats-officedocument.presentationml.presentation" | "application/rtf" | "application/x-ndjson" | "application/vnd.apache.parquet" | "application/gzip" | "application/x-tar" | "application/x-7z-compressed")` *required*
>
> MIME type of the media record.
>
> **contentLength** `integer` *required*
>
> Size of the media record in bytes.
>
> **datasetItemId** `string`
>
> Associated dataset item ID; the item need not exist yet. Pair with datasetId.
>
> **observationId** `string`
>
> Associated observation ID within the trace; null for trace-level media.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Create model
>
> **Slug:** `LANGFUSE_CREATE_MODEL`
>
> Create a custom Langfuse model definition for usage-to-USD cost calculation and optional tokenization. Supply a model name, matching regex, usage unit, and either pricing tiers (recommended) or legacy flat prices. Each tiered model needs exactly one default tier with priority 0 and no conditions.
>
> #### Input Parameters
>
> **unit** `string ("CHARACTERS" | "TOKENS" | "MILLISECONDS" | "SECONDS" | "IMAGES" | "REQUESTS")` *required*
>
> Unit of usage for this model.
>
> **modelName** `string` *required*
>
> Model definition name. Custom definitions override built-ins; newer applicable definitions take precedence.
>
> **startDate** `string`
>
> ISO date-time; apply only to generations newer than this date.
>
> **inputPrice** `number`
>
> Deprecated flat USD price per input unit. Use pricingTiers instead.
>
> **totalPrice** `number`
>
> Deprecated flat USD price per total unit; cannot coexist with inputPrice or outputPrice. Use pricingTiers instead.
>
> **outputPrice** `number`
>
> Deprecated flat USD price per output unit. Use pricingTiers instead.
>
> **tokenizerId** `string ("openai" | "claude")`
>
> Tokenizer applied to matching observations.
>
> **matchPattern** `string` *required*
>
> Regex matching generation.model; use (?i)^modelname\$ for an exact case-insensitive match.
>
> **pricingTiers** `array`
>
> Pricing tiers, mutually exclusive with flat prices. Include exactly one default tier with priority 0 and no conditions. Names and priorities must be unique. If omitted, provide flat prices to create a Standard tier.
>
> **tokenizerConfig** `string`
>
> JSON configuration for the selected tokenizer.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Create Prompt
>
> **Slug:** `LANGFUSE_CREATE_PROMPT`
>
> Create a new version of a named Langfuse text or chat prompt. Chat prompts require type='chat' and support messages and named placeholders. Optionally attach arbitrary JSON configuration, deployment labels, tags, and a commit message.
>
> #### Input Parameters
>
> **name** `string` *required*
>
> Full prompt name, including any folder path; at most 255 characters.
>
> **tags** `array`
>
> Tags to apply to all versions of this prompt.
>
> **type** `string ("text" | "chat")`
>
> Prompt type. Required for chat prompts; text prompts may omit this field or supply null.
>
> **config** `string`
>
> Arbitrary JSON configuration attached to this prompt version.
>
> **labels** `array`
>
> Deployment labels for this prompt version.
>
> **prompt** `string` *required*
>
> Text template, or ordered chat messages and named placeholders when type is chat.
>
> **commitMessage** `string`
>
> Commit message for this prompt version.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Create Score
>
> **Slug:** `LANGFUSE_CREATE_SCORE`
>
> Attach an evaluation score to exactly one Langfuse trace, session, or dataset run, optionally narrowing a trace score to an observation.
>
> #### Input Parameters
>
> **name** `string` *required*
>
> Score name.
>
> **value** `string` *required*
>
> Numeric value for NUMERIC or BOOLEAN scores (BOOLEAN uses 1 or 0), or a string for CATEGORICAL, TEXT, or CORRECTION scores.
>
> **source** `string ("API" | "ANNOTATION")`
>
> Score source. ANNOTATION requires config\_id unless data\_type is CORRECTION.
>
> **comment** `string`
>
> Human-readable explanation of the score.
>
> **metadata** `object`
>
> Arbitrary JSON metadata to associate with the score.
>
> **queue\_id** `string`
>
> Annotation queue associated with this score.
>
> **score\_id** `string`
>
> Optional caller-supplied score ID.
>
> **trace\_id** `string`
>
> Trace target. May be combined with observation\_id.
>
> **config\_id** `string`
>
> Score configuration ID used to validate and infer compatible score fields.
>
> **data\_type** `string ("NUMERIC" | "BOOLEAN" | "CATEGORICAL" | "TEXT" | "CORRECTION")`
>
> Score data type. Langfuse infers it when config\_id is set; otherwise it defaults to NUMERIC.
>
> **session\_id** `string`
>
> Session target.
>
> **environment** `string`
>
> Lowercase alphanumeric environment with hyphens or underscores; must not start with 'langfuse'.
>
> **dataset\_run\_id** `string`
>
> Dataset run or experiment target.
>
> **observation\_id** `string`
>
> Observation target within trace\_id. Cannot be used alone.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Create score config
>
> **Slug:** `LANGFUSE_CREATE_SCORE_CONFIG`
>
> Create a score configuration in the authenticated Langfuse project to define numeric bounds, categorical label/value pairs, boolean scores, or text scores. Boolean categories are autogenerated; omit categories for BOOLEAN configs. Use the returned config ID when creating scores validated against this configuration.
>
> #### Input Parameters
>
> **name** `string` *required*
>
> Score config name, at most 80 characters. Only letters, numbers, underscores, spaces, periods, parentheses, and hyphens are allowed.
>
> **dataType** `string ("NUMERIC" | "BOOLEAN" | "CATEGORICAL" | "TEXT")` *required*
>
> Type of scores this config defines.
>
> **maxValue** `number`
>
> Maximum numerical score value; defaults to positive infinity when not set.
>
> **minValue** `number`
>
> Minimum numerical score value; defaults to negative infinity when not set.
>
> **categories** `array`
>
> Custom label/value categories for categorical scores. Boolean categories are autogenerated and cannot be passed.
>
> **description** `string`
>
> Description shown in the Langfuse UI explaining categories, numeric bounds, or config usage.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Delete Dataset Item
>
> **Slug:** `LANGFUSE_DELETE_DATASET_ITEM`
>
> Delete a Langfuse dataset item by its ID and all its run items. This action is irreversible.
>
> #### Input Parameters
>
> **id** `string` *required*
>
> Unique ID of the dataset item to delete.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Delete Evaluation Rule
>
> **Slug:** `LANGFUSE_DELETE_EVALUATION_RULE`
>
> Delete a Langfuse evaluation rule by its stable ID, including legacy trace and dataset rules. This removes the live-ingestion rule only; associated evaluators and previously produced scores are preserved.
>
> #### Input Parameters
>
> **evaluationRuleId** `string` *required*
>
> Stable evaluation-rule identifier returned by the evaluation-rule endpoints.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Delete Evaluator
>
> **Slug:** `LANGFUSE_DELETE_EVALUATOR`
>
> Delete a Langfuse evaluator and all of its stored versions by its stable ID. Associated evaluation-rule assignments are also removed. Scores already produced by the evaluator are preserved.
>
> #### Input Parameters
>
> **evaluatorId** `string` *required*
>
> Stable evaluator identifier returned by the evaluator endpoints.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Delete LLM Connection
>
> **Slug:** `LANGFUSE_DELETE_LLM_CONNECTION`
>
> Delete a Langfuse LLM connection by its ID. Evaluators that depend on the deleted connection are automatically paused.
>
> #### Input Parameters
>
> **id** `string` *required*
>
> Identifier of the LLM connection to delete.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Delete Model
>
> **Slug:** `LANGFUSE_DELETE_MODEL`
>
> Delete a project-owned Langfuse model by its ID. Models managed by Langfuse cannot be deleted; create your own definition with the same modelName to override a managed definition instead. Returns an empty response on success.
>
> #### Input Parameters
>
> **id** `string` *required*
>
> The unique identifier of the model to delete.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Delete Prompt
>
> **Slug:** `LANGFUSE_DELETE_PROMPT`
>
> Delete Langfuse prompt versions by prompt name. Optionally filter deletion by label or version. If neither label nor version is specified, all versions of the prompt are deleted. Returns an empty response on success.
>
> #### Input Parameters
>
> **label** `string`
>
> Delete all prompt versions that have this label, when specified.
>
> **version** `integer`
>
> Delete only this specific prompt version, when specified.
>
> **promptName** `string` *required*
>
> Single-segment prompt name; slashes, URLs, and dot segments are rejected.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Delete Score
>
> **Slug:** `LANGFUSE_DELETE_SCORE`
>
> Delete a Langfuse score by its ID. Supports both trace and session scores. Returns an empty response on success.
>
> #### Input Parameters
>
> **scoreId** `string` *required*
>
> The unique Langfuse identifier of the score to delete.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Delete Trace
>
> **Slug:** `LANGFUSE_DELETE_TRACE`
>
> Delete a specific Langfuse trace by its unique trace ID.
>
> #### Input Parameters
>
> **traceId** `string` *required*
>
> The unique Langfuse identifier of the trace to delete.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Delete Traces
>
> **Slug:** `LANGFUSE_DELETE_TRACES`
>
> Delete multiple Langfuse traces by their trace IDs.
>
> #### Input Parameters
>
> **traceIds** `array` *required*
>
> List of trace IDs to delete.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Annotation Queue
>
> **Slug:** `LANGFUSE_GET_ANNOTATION_QUEUE`
>
> Retrieve one Langfuse annotation queue by its ID.
>
> #### Input Parameters
>
> **queue\_id** `string` *required*
>
> Unique identifier of the annotation queue to retrieve.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Annotation Queue Item
>
> **Slug:** `LANGFUSE_GET_ANNOTATION_QUEUE_ITEM`
>
> Get a specific item from a Langfuse annotation queue by queue ID and queue item ID. Returns the associated object, annotation status, and timestamps.
>
> #### Input Parameters
>
> **itemId** `string` *required*
>
> Unique identifier of the annotation queue item, not the annotated object ID.
>
> **queueId** `string` *required*
>
> Unique identifier of the annotation queue containing the item.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get comment
>
> **Slug:** `LANGFUSE_GET_COMMENT`
>
> Retrieve one comment by its unique Langfuse ID in the authenticated project. Returns the comment content, associated object type and ID, timestamps, and author user ID when available.
>
> #### Input Parameters
>
> **commentId** `string` *required*
>
> The unique Langfuse identifier of the comment to retrieve.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Dataset
>
> **Slug:** `LANGFUSE_GET_DATASET`
>
> Retrieve a Langfuse dataset by name, including its metadata and JSON Schemas for dataset item inputs and expected outputs.
>
> #### Input Parameters
>
> **datasetName** `string` *required*
>
> Single-segment dataset name; slashes, URLs, and dot segments are rejected.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Dataset Item
>
> **Slug:** `LANGFUSE_GET_DATASET_ITEM`
>
> Retrieve a single Langfuse dataset item by its ID, including its input, expected output, metadata, source IDs, and resolved media references.
>
> #### Input Parameters
>
> **id** `string` *required*
>
> Unique ID of the dataset item to retrieve.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Evaluation Rule
>
> **Slug:** `LANGFUSE_GET_EVALUATION_RULE`
>
> Get one Langfuse evaluation rule by its stable identifier, including legacy trace or dataset rules. Returns its enabled state, sampling, stored filters, evaluator assignments, variable mappings, creator, and timestamps.
>
> #### Input Parameters
>
> **evaluationRuleId** `string` *required*
>
> Stable evaluation-rule identifier returned by evaluation-rule endpoints.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get evaluator
>
> **Slug:** `LANGFUSE_GET_EVALUATOR`
>
> Get one evaluator by its stable identifier in the authenticated Langfuse project. Returns its latest definition, version metadata, effective runtime status, and associated evaluation-rule assignments. Use version history for older definitions.
>
> #### Input Parameters
>
> **evaluatorId** `string` *required*
>
> Stable evaluator identifier returned by the evaluator endpoints.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get media
>
> **Slug:** `LANGFUSE_GET_MEDIA`
>
> Retrieve one media record by its unique Langfuse ID in the authenticated project. Returns the MIME type, size in bytes, upload timestamp, and download URL with its expiry. Does not download the media content.
>
> #### Input Parameters
>
> **mediaId** `string` *required*
>
> The unique Langfuse identifier of the media record to retrieve.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get model
>
> **Slug:** `LANGFUSE_GET_MODEL`
>
> Retrieve one Langfuse-managed or project-custom model definition by ID. Returns model matching rules, tokenizer configuration, usage unit, legacy prices, and conditional pricing tiers used for cost calculation.
>
> #### Input Parameters
>
> **id** `string` *required*
>
> Unique model definition ID, as returned by listing models.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Project
>
> **Slug:** `LANGFUSE_GET_PROJECT`
>
> Get the project associated with the connected project-scoped API key, returned in a data list with its organization, metadata, and retention configuration. No project ID is required. To get all projects using an organization-scoped API key, use the provider's organization API separately.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Prompt
>
> **Slug:** `LANGFUSE_GET_PROMPT`
>
> Retrieve a Langfuse text or chat prompt by name, optionally selecting a deployment label or exact version and resolving dependencies.
>
> #### Input Parameters
>
> **label** `string`
>
> Deployment label. Cannot be combined with version; defaults upstream to production when neither selector is set.
>
> **resolve** `boolean`
>
> Resolve prompt dependencies. Set false only to inspect the raw stored prompt.
>
> **version** `integer`
>
> Exact prompt version. Cannot be combined with label.
>
> **prompt\_name** `string` *required*
>
> Prompt name, including any folder path. Folder separators are URL-encoded as part of the path value.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get score configuration
>
> **Slug:** `LANGFUSE_GET_SCORE_CONFIG`
>
> Retrieve one score configuration by ID in the authenticated Langfuse project. Returns its score data type, numeric bounds, categorical labels, description, timestamps, and archive status.
>
> #### Input Parameters
>
> **configId** `string` *required*
>
> Unique Langfuse score configuration ID, as returned by listing or creating score configurations.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Ingest Traces
>
> **Slug:** `LANGFUSE_INGEST_TRACES`
>
> Export OpenTelemetry traces to Langfuse using OTLP HTTP/JSON with real-time v4 ingestion. Supply resourceSpans containing scopeSpans and spans. Acceptance is asynchronous. Inspect partialSuccess: HTTP 200 can include rejected spans or warnings; do not retry partially accepted batches. This action supports JSON, not binary protobuf or gzip.
>
> #### Input Parameters
>
> **resourceSpans** `array` *required*
>
> OTLP ExportTraceServiceRequest resource spans. Use hex trace/span IDs and send both timestamps.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List Annotation Queue Items
>
> **Slug:** `LANGFUSE_LIST_ANNOTATION_QUEUE_ITEMS`
>
> List one page of items in a Langfuse annotation queue, optionally filtered by PENDING or COMPLETED status. Increment page while meta.page is less than meta.totalPages to retrieve subsequent pages.
>
> #### Input Parameters
>
> **page** `integer`
>
> Page number to retrieve, starting at 1.
>
> **limit** `integer`
>
> Number of items per page.
>
> **status** `string ("PENDING" | "COMPLETED")`
>
> Filter items by annotation status.
>
> **queueId** `string` *required*
>
> Unique identifier of the annotation queue.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List Annotation Queues
>
> **Slug:** `LANGFUSE_LIST_ANNOTATION_QUEUES`
>
> List annotation queues configured for human evaluation in the connected Langfuse project.
>
> #### Input Parameters
>
> **limit** `integer`
>
> Maximum queues in this page.
>
> **next\_cursor** `string`
>
> Continuation token returned by the previous call; do not construct it manually.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List comments
>
> **Slug:** `LANGFUSE_LIST_COMMENTS`
>
> List one page of comments in the authenticated Langfuse project. Optionally filter by object type, object ID, or author user ID. Filtering by object ID requires objectType. To retrieve another page, increment page while page is less than meta.totalPages.
>
> #### Input Parameters
>
> **page** `integer`
>
> Page number, starting at 1.
>
> **limit** `integer`
>
> Items per page. Reduce this value if large pages cause API issues.
>
> **objectId** `string`
>
> Filter by object ID. Also provide objectType or the API returns an error.
>
> **objectType** `string`
>
> Filter by object type (trace, observation, session, prompt).
>
> **authorUserId** `string`
>
> Filter by the comment author's user ID.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List Dataset Items
>
> **Slug:** `LANGFUSE_LIST_DATASET_ITEMS`
>
> List dataset items, optionally scoped to a dataset, source trace or observation, or historical dataset version.
>
> #### Input Parameters
>
> **limit** `integer`
>
> Maximum dataset items in this page.
>
> **version** `string`
>
> Return the dataset state at this UTC RFC 3339 timestamp. Requires dataset\_name.
>
> **next\_cursor** `string`
>
> Continuation token returned by the previous call. Omit for the first page and do not construct it manually.
>
> **dataset\_name** `string`
>
> Dataset name to list items from.
>
> **source\_trace\_id** `string`
>
> Filter by source trace ID.
>
> **source\_observation\_id** `string`
>
> Filter by source observation ID.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List Dataset Run Items
>
> **Slug:** `LANGFUSE_LIST_DATASET_RUN_ITEMS`
>
> List run items for a specific Langfuse dataset and run name.
>
> #### Input Parameters
>
> **page** `integer`
>
> Provider page number, starting at 1.
>
> **limit** `integer`
>
> Maximum run items to return on this page.
>
> **runName** `string` *required*
>
> Dataset run name to filter by.
>
> **datasetId** `string` *required*
>
> Unique identifier of the dataset to filter by.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List Datasets
>
> **Slug:** `LANGFUSE_LIST_DATASETS`
>
> List datasets available to the connected Langfuse project.
>
> #### Input Parameters
>
> **limit** `integer`
>
> Maximum datasets in this page.
>
> **next\_cursor** `string`
>
> Continuation token returned by the previous call; do not construct it manually.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List evaluation rules
>
> **Slug:** `LANGFUSE_LIST_EVALUATION_RULES`
>
> List one page of evaluation rules in the authenticated Langfuse project, newest creation first. Includes legacy trace and dataset rules for inspection and migration, with stored filters and evaluator assignments. Pass meta.cursor unchanged as cursor to retrieve the next page; an absent or null cursor means there are no more pages.
>
> #### Input Parameters
>
> **limit** `integer`
>
> Maximum rules to return; defaults to 50 and cannot exceed 100.
>
> **cursor** `string`
>
> Opaque cursor from the previous page's meta.cursor; pass it unchanged.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List evaluators
>
> **Slug:** `LANGFUSE_LIST_EVALUATORS`
>
> List one page of evaluators in the authenticated Langfuse project, newest creation first. Each evaluator includes its latest definition, version metadata and evaluation-rule assignments. Pass meta.cursor unchanged as cursor to retrieve the next page; an absent or null cursor means there are no more pages.
>
> #### Input Parameters
>
> **limit** `integer`
>
> Maximum evaluators to return; defaults to 50 and cannot exceed 100.
>
> **cursor** `string`
>
> Opaque cursor from the previous page's meta.cursor; pass it unchanged.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List evaluator versions
>
> **Slug:** `LANGFUSE_LIST_EVALUATOR_VERSIONS`
>
> List one page of an evaluator's version history, newest first, for history and audit use cases. Returns each version's definition and creator metadata. Pass meta.cursor unchanged as cursor for the next page; an absent or null cursor means there are no more pages. For only the latest definition, use Get evaluator.
>
> #### Input Parameters
>
> **limit** `integer`
>
> Maximum versions to return; defaults to 50 and cannot exceed 100.
>
> **cursor** `string`
>
> Opaque cursor from the previous page's meta.cursor; pass it unchanged.
>
> **evaluatorId** `string` *required*
>
> Stable evaluator identifier returned by the evaluator endpoints.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List Experiment Items
>
> **Slug:** `LANGFUSE_LIST_EXPERIMENT_ITEMS`
>
> List Langfuse experiment items started on or after a required datetime, ordered by time descending. Export inputs, outputs, expected outputs, metadata, and optional item/trace scores by selecting field groups. Returns one page; pass meta.cursor with the same filters to fetch the next.
>
> #### Input Parameters
>
> **limit** `integer`
>
> Items per page (maximum 100; provider default 50).
>
> **cursor** `string`
>
> Versioned base64url cursor from meta.cursor in the previous response. Omit for the first page and repeat the same filters for subsequent pages.
>
> **fields** `string`
>
> Comma-separated field groups: core, dataset, io, metadata, itemMetadata, experimentMetadata, scores. Defaults to core,dataset when omitted.
>
> **dataset\_id** `string`
>
> Comma-separated dataset IDs to include.
>
> **filter\_json** `string`
>
> JSON-encoded array of structured filter conditions. Supported columns: experimentId, experimentName, experimentItemId, datasetId.
>
> **score\_limit** `integer`
>
> Scores per item when scores are requested (maximum and default 50).
>
> **experiment\_id** `string`
>
> Comma-separated experiment IDs to include.
>
> **to\_start\_time** `string`
>
> Include experiment items started before this ISO 8601 datetime.
>
> **experiment\_name** `string`
>
> Comma-separated experiment names to include.
>
> **from\_start\_time** `string` *required*
>
> Include experiment items started on or after this ISO 8601 datetime.
>
> **experiment\_item\_id** `string`
>
> Comma-separated experiment item IDs to include.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List Experiments
>
> **Slug:** `LANGFUSE_LIST_EXPERIMENTS`
>
> List Langfuse experiments active from a required start time, optionally specifying an end time and including metadata and directly attached scores.
>
> #### Input Parameters
>
> **limit** `integer`
>
> Maximum experiments in this page (1-100).
>
> **names** `string`
>
> Comma-separated experiment names.
>
> **fields** `string`
>
> Comma-separated field groups to return: core, metadata, scores.
>
> **dataset\_ids** `string`
>
> Comma-separated dataset IDs.
>
> **filter\_json** `string`
>
> JSON-encoded structured filters over id, name, and datasetId.
>
> **next\_cursor** `string`
>
> Continuation cursor returned by the previous call. Omit for the first page.
>
> **score\_limit** `integer`
>
> Maximum attached scores per experiment when fields includes scores (1-50).
>
> **to\_start\_time** `string`
>
> Include experiments starting before this ISO 8601 timestamp.
>
> **experiment\_ids** `string`
>
> Comma-separated experiment IDs.
>
> **from\_start\_time** `string` *required*
>
> Include experiments active on or after this ISO 8601 timestamp.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List LLM connections
>
> **Slug:** `LANGFUSE_LIST_LLM_CONNECTIONS`
>
> List one page of LLM provider connections in the authenticated Langfuse project, including model configuration and masked secrets. To retrieve another page, increment page while page is less than meta.totalPages.
>
> #### Input Parameters
>
> **page** `integer`
>
> Page number, starting at 1.
>
> **limit** `integer`
>
> Number of LLM connections per page.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List Models
>
> **Slug:** `LANGFUSE_LIST_MODELS`
>
> List Langfuse-managed and project-custom model pricing definitions used for usage and cost calculation.
>
> #### Input Parameters
>
> **limit** `integer`
>
> Maximum model definitions in this page.
>
> **next\_cursor** `string`
>
> Continuation token returned by the previous call. Omit for the first page and do not construct this token manually.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List Observations
>
> **Slug:** `LANGFUSE_LIST_OBSERVATIONS`
>
> Search Langfuse observations such as generations, spans, events, agents, and tool calls, selecting only the field groups needed.
>
> #### Input Parameters
>
> **name** `string`
>
> Filter by observation name.
>
> **level** `string ("DEBUG" | "DEFAULT" | "WARNING" | "ERROR")`
>
> Filter by observation level.
>
> **limit** `integer`
>
> Maximum observations in this page (1-1000).
>
> **fields** `string`
>
> Comma-separated field groups to return: core, basic, time, io, metadata, model, usage, prompt, metrics, trace\_context.
>
> **user\_id** `string`
>
> Filter by associated user ID.
>
> **version** `string`
>
> Filter by observation version.
>
> **trace\_id** `string`
>
> Filter by trace ID.
>
> **session\_id** `string`
>
> Filter by session ID.
>
> **filter\_json** `string`
>
> JSON-encoded structured filter array. When set, it takes precedence over individual filters.
>
> **next\_cursor** `string`
>
> Continuation cursor returned by the previous call. Omit for the first page.
>
> **environments** `array`
>
> Return observations from any of these environments.
>
> **to\_start\_time** `string`
>
> Include observations starting before this ISO 8601 timestamp.
>
> **expand\_metadata** `string`
>
> Comma-separated metadata keys whose values should not be truncated.
>
> **from\_start\_time** `string`
>
> Include observations starting at or after this ISO 8601 timestamp.
>
> **observation\_type** `string ("GENERATION" | "SPAN" | "EVENT" | "AGENT" | "TOOL" | "CHAIN" | "RETRIEVER" | "EVALUATOR" | "EMBEDDING" | "GUARDRAIL")`
>
> Filter by observation type.
>
> **is\_root\_observation** `boolean`
>
> Filter by logical root status.
>
> **parent\_observation\_id** `string`
>
> Filter by physical parent observation ID.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List prompts
>
> **Slug:** `LANGFUSE_LIST_PROMPTS`
>
> List one page of prompt names, types, versions, labels, tags and latest matching configuration in the authenticated Langfuse project. Optionally filter by name, label, tag, update dates or advanced JSON conditions. Returns metadata rather than prompt content; use Get Prompt to retrieve a template. Increment page while meta.page is less than meta.totalPages to retrieve subsequent pages.
>
> #### Input Parameters
>
> **tag** `string`
>
> Filter by prompt tag.
>
> **name** `string`
>
> Filter by prompt name.
>
> **page** `integer`
>
> Page number, starting at 1.
>
> **label** `string`
>
> Filter by prompt deployment label.
>
> **limit** `integer`
>
> Number of items per page.
>
> **filter** `string`
>
> JSON string of AND-combined conditions, each with type, column, operator, and value. Overrides name, label, tag and date filters; \[] applies no filters. Types: string (id/name/type; =, contains, does not contain, starts with, ends with, is not empty); stringOptions (id/name/type; any of, none of; non-empty string array); number (version; =, >, \<, >=, \<=); datetime (createdAt/updatedAt; >, \<, >=, \<=; ISO 8601 value); arrayOptions (labels/tags; any of, all of, none of; non-empty string array); stringObject (config; also requires key; =, contains, does not contain, starts with, ends with, is set, is not set; string value, empty for presence checks). Equality is case-sensitive; searches are case-insensitive SQL patterns (% and \_ are wildcards, backslash escapes them and must be JSON-escaped; asterisks are literal). Empty config searches mean is set. Filters apply to versions before aggregation, affecting returned versions, labels and lastConfig.
>
> **toUpdatedAt** `string`
>
> Include prompt versions created or updated before this ISO 8601 datetime.
>
> **fromUpdatedAt** `string`
>
> Include prompt versions created or updated on or after this ISO 8601 datetime.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List score configurations
>
> **Slug:** `LANGFUSE_LIST_SCORE_CONFIGS`
>
> List one page of score configurations in the authenticated Langfuse project, including score types, numeric bounds, categorical labels, and archive status. To retrieve another page, increment page while page is less than meta.totalPages.
>
> #### Input Parameters
>
> **page** `integer`
>
> Page number, starting at 1. Omit for the first page.
>
> **limit** `integer`
>
> Items per page. Reduce this value if large pages cause API issues.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List Scores
>
> **Slug:** `LANGFUSE_LIST_SCORES`
>
> Search numeric, boolean, categorical, text, and correction scores with subject and annotation context.
>
> #### Input Parameters
>
> **limit** `integer`
>
> Maximum scores in this page (1-100); larger values are rejected.
>
> **names** `array`
>
> Score names to return.
>
> **fields** `array`
>
> Optional score field groups to include.
>
> **values** `array`
>
> Exact score values to match; requires one compatible data type.
>
> **sources** `array`
>
> Score sources to return.
>
> **queue\_ids** `array`
>
> Annotation queue IDs to return.
>
> **score\_ids** `array`
>
> Score IDs to return.
>
> **trace\_ids** `array`
>
> Trace IDs to return; mutually exclusive with session and experiment IDs.
>
> **value\_max** `number`
>
> Inclusive numeric upper bound; requires data\_types=NUMERIC.
>
> **value\_min** `number`
>
> Inclusive numeric lower bound; requires data\_types=NUMERIC.
>
> **config\_ids** `array`
>
> Score configuration IDs to return.
>
> **data\_types** `array`
>
> Score data types to return.
>
> **next\_cursor** `string`
>
> Continuation cursor returned by the previous call.
>
> **session\_ids** `array`
>
> Session IDs to return; mutually exclusive with trace, observation, and experiment IDs.
>
> **environments** `array`
>
> Environments to return.
>
> **to\_timestamp** `string`
>
> Exclusive score timestamp upper bound.
>
> **experiment\_ids** `array`
>
> Dataset run or experiment IDs to return; mutually exclusive with other subject filters.
>
> **from\_timestamp** `string`
>
> Inclusive score timestamp lower bound.
>
> **author\_user\_ids** `array`
>
> Annotation author user IDs to return.
>
> **observation\_ids** `array`
>
> Observation IDs to return; requires trace\_ids.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Query Metrics
>
> **Slug:** `LANGFUSE_QUERY_METRICS`
>
> Run an aggregate Langfuse metrics query over observations or numeric, boolean, or categorical scores.
>
> #### Input Parameters
>
> **view** `string ("observations" | "scores-numeric" | "scores-boolean" | "scores-categorical")` *required*
>
> Langfuse data view to aggregate.
>
> **filters** `array`
>
> Optional typed conditions used to restrict source rows.
>
> **metrics** `array` *required*
>
> One or more measures and aggregations to calculate.
>
> **order\_by** `array`
>
> Optional ordered list of result sort rules.
>
> **row\_limit** `integer`
>
> Maximum aggregate rows to return (1-1000).
>
> **dimensions** `array`
>
> Optional low-cardinality fields by which to group results.
>
> **to\_timestamp** `string` *required*
>
> Exclusive ISO 8601 end of the metrics time range; must be after from\_timestamp.
>
> **from\_timestamp** `string` *required*
>
> Inclusive ISO 8601 start of the metrics time range.
>
> **histogram\_bins** `integer`
>
> Number of histogram bins when using histogram aggregation (1-100).
>
> **time\_granularity** `string ("auto" | "minute" | "hour" | "day" | "week" | "month")`
>
> Optional time bucket granularity for grouping results.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Remove Annotation Queue Assignment
>
> **Slug:** `LANGFUSE_REMOVE_ANNOTATION_QUEUE_ASSIGNMENT`
>
> Remove a user's assignment to a Langfuse annotation queue by queue ID and user ID. Returns whether the assignment was removed.
>
> #### Input Parameters
>
> **userId** `string` *required*
>
> Unique identifier of the user whose assignment to the queue is removed.
>
> **queueId** `string` *required*
>
> Unique identifier of the annotation queue.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Remove Annotation Queue Item
>
> **Slug:** `LANGFUSE_REMOVE_ANNOTATION_QUEUE_ITEM`
>
> Remove an item from a Langfuse annotation queue using the queue ID and annotation queue item ID.
>
> #### Input Parameters
>
> **itemId** `string` *required*
>
> Unique identifier of the annotation queue item to remove.
>
> **queueId** `string` *required*
>
> Unique identifier of the annotation queue containing the item.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Submit feedback
>
> **Slug:** `LANGFUSE_SUBMIT_FEEDBACK`
>
> Submit feedback to Langfuse about its skills, MCP tools, CLI, docs, or public API. Only call after the user has explicitly approved the feedback content for submission; any supplied goal must also be user-approved. Do not include secrets, credentials, customer data, trace payloads, or unrelated use-case details. Not available in the HIPAA cloud region. Returns a feedback correlation ID.
>
> #### Input Parameters
>
> **goal** `string`
>
> Optional user-approved goal or use case (1–1500 characters when provided). Do not include secrets, customer data, trace payloads, or broad unrelated context.
>
> **target** `string` *required*
>
> Specific skill name, MCP tool name, CLI command, API endpoint path, or docs page path. Use an identifier, not a sentence (1–200 characters).
>
> **feedback** `string` *required*
>
> Concise feedback text explicitly approved by the user for submission to Langfuse (1–3000 characters). Do not include secrets, credentials, customer data, trace payloads, or unrelated use-case details.
>
> **targetType** `string ("skill" | "mcp-tool" | "cli" | "docs" | "public-api" | "other")` *required*
>
> Category of the thing the feedback is about.
>
> **referenceUrl** `string`
>
> Optional HTTP(S) reference URL; Langfuse stores it as text and does not fetch it.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Update Annotation Queue Item
>
> **Slug:** `LANGFUSE_UPDATE_ANNOTATION_QUEUE_ITEM`
>
> Update a Langfuse annotation queue item's status to PENDING or COMPLETED using its queue ID and item ID. Returns the updated queue item.
>
> #### Input Parameters
>
> **itemId** `string` *required*
>
> Unique identifier of the annotation queue item to update.
>
> **status** `string ("PENDING" | "COMPLETED")`
>
> New annotation status for the queue item.
>
> **queueId** `string` *required*
>
> Unique identifier of the annotation queue.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Update Evaluation Rule
>
> **Slug:** `LANGFUSE_UPDATE_EVALUATION_RULE`
>
> Update a Langfuse evaluation rule by its stable ID. Supply only fields to change; explicit nulls are forwarded. Filters and evaluator assignments replace their complete lists. An empty assignment list disables the rule; enabling requires a nonempty resulting list and may incur model costs. Legacy trace and dataset rules only allow deactivation with enabled=false; their name, filters, sampling, and assignments cannot change.
>
> #### Input Parameters
>
> **name** `string`
>
> New human-readable rule name.
>
> **filter** `array`
>
> Complete replacement AND-combined observation filters. An empty list matches every incoming observation. Omit to keep the current filters.
>
> **enabled** `boolean`
>
> New live-execution state. Enabling may incur model costs and requires a nonempty resulting evaluator assignment list.
>
> **sampling** `number`
>
> New fraction of matches to evaluate. Omit to retain the current value.
>
> **evaluationRuleId** `string` *required*
>
> Stable evaluation-rule identifier.
>
> **evaluatorAssignments** `array`
>
> Complete replacement evaluator list; an empty list disables the rule. Omit to keep current assignments. Null/omitted variableMapping inherits the evaluator's latest defaults.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Update evaluator
>
> **Slug:** `LANGFUSE_UPDATE_EVALUATOR`
>
> Update a Langfuse evaluator by stable identifier. Supply name or description for a metadata-only change without creating a version. To replace a definition, include type and all required definition fields; definitions are replaced, not merged. The evaluator type cannot change. Null description clears it; null or omitted modelConfig selects the project default model. Definition replacement may reactivate evaluators paused for invalid or missing model configuration; other pause reasons require an explicit reactivation check.
>
> #### Input Parameters
>
> **name** `string`
>
> New human-readable evaluator name.
>
> **type** `string ("llm_as_judge" | "code")`
>
> Required for a complete definition replacement; must match the existing evaluator type. Omit for metadata-only changes.
>
> **prompt** `string`
>
> Required for llm\_as\_judge replacement: complete prompt string or ordered messages. A system message is allowed only first.
>
> **sourceCode** `string`
>
> Required for code replacement: complete source code.
>
> **description** `string`
>
> New description; explicitly set null to clear it.
>
> **evaluatorId** `string` *required*
>
> Stable evaluator identifier.
>
> **modelConfig** `object`
>
> LLM model configuration; null or omission selects the project's default evaluation model. Omit for code.
>
> **variableMapping** `array`
>
> Complete replacement LLM default mappings, or null for no default. Map each prompt variable exactly once. Omit for code.
>
> **outputDefinition** `string`
>
> Required for llm\_as\_judge replacement: complete structured score output definition. Omit for code.
>
> **sourceCodeLanguage** `string ("PYTHON" | "TYPESCRIPT")`
>
> Required for code replacement: source runtime language.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Update media
>
> **Slug:** `LANGFUSE_UPDATE_MEDIA`
>
> Update an existing Langfuse media record with its upload timestamp and HTTP status, and optionally the upload error message and elapsed time. This records the upload result; it does not upload media content. Omitted optional fields are not sent; explicitly supplied null values are forwarded. Returns an empty response on success.
>
> #### Input Parameters
>
> **mediaId** `string` *required*
>
> The unique Langfuse identifier of the media record.
>
> **uploadedAt** `string` *required*
>
> The date and time when the media record was uploaded (ISO 8601).
>
> **uploadTimeMs** `integer`
>
> The time in milliseconds it took to upload the media record, or null.
>
> **uploadHttpError** `string`
>
> The HTTP error message of the upload, or null.
>
> **uploadHttpStatus** `integer` *required*
>
> The HTTP status code of the upload.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Update Prompt Labels
>
> **Slug:** `LANGFUSE_UPDATE_PROMPT_LABELS`
>
> Update deployment labels for a specific Langfuse prompt version by name and version. Labels are unique across versions of a prompt; the latest label is reserved and managed by Langfuse. Returns the updated text or chat prompt version.
>
> #### Input Parameters
>
> **name** `string` *required*
>
> Single-segment prompt name; slashes, URLs, and dot segments are rejected.
>
> **version** `integer` *required*
>
> Version of the prompt to update.
>
> **newLabels** `array` *required*
>
> New labels for this prompt version. Labels are unique across versions. The "latest" label is reserved and managed by Langfuse.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Update score config
>
> **Slug:** `LANGFUSE_UPDATE_SCORE_CONFIG`
>
> Update an existing Langfuse score configuration by config ID. Change its name, description, archive status, numerical bounds, or categorical label/value pairs. Omitted fields are not sent; explicitly supplied null values are forwarded. Boolean categories are autogenerated and cannot be passed. Returns the updated configuration.
>
> #### Input Parameters
>
> **name** `string`
>
> New name, at most 80 characters. Only letters, numbers, underscores, spaces, periods, parentheses, and hyphens are allowed.
>
> **configId** `string` *required*
>
> Unique Langfuse score config identifier.
>
> **maxValue** `number`
>
> Maximum numerical score value; defaults to positive infinity when not set.
>
> **minValue** `number`
>
> Minimum numerical score value; defaults to negative infinity when not set.
>
> **categories** `array`
>
> Custom label/value categories for categorical scores. Boolean categories are autogenerated and cannot be passed.
>
> **isArchived** `boolean`
>
> Whether the score config is archived.
>
> **description** `string`
>
> Description shown in the Langfuse UI explaining categories, numeric bounds, or config usage.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Upsert LLM Connection
>
> **Slug:** `LANGFUSE_UPSERT_LLM_CONNECTION`
>
> Create or update a Langfuse LLM provider connection by provider name.
>
> #### Input Parameters
>
> **config** `object`
>
> Adapter-specific configuration, such as a Bedrock region or Vertex AI location.
>
> **adapter** `string ("anthropic" | "openai" | "azure" | "bedrock" | "google-vertex-ai" | "google-ai-studio")` *required*
>
> Adapter used to call the LLM provider.
>
> **baseURL** `string`
>
> Optional custom LLM provider or gateway base URL.
>
> **provider** `string` *required*
>
> Unique provider name used to create or update the connection.
>
> **secretKey** `string` *required*
>
> Secret credential Langfuse stores for the LLM provider.
>
> **customModels** `array`
>
> Custom model names exposed through this connection.
>
> **extraHeaders** `object`
>
> Additional headers sent to the LLM provider.
>
> **withDefaultModels** `boolean`
>
> Whether to include the adapter's default models.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Upsert Model
>
> **Slug:** `LANGFUSE_UPSERT_MODEL`
>
> Create or replace a project-owned Langfuse model definition by ID for usage cost calculation and optional tokenization. Built-in models cannot be modified. This replaces the model definition; supply its desired configuration.
>
> #### Input Parameters
>
> **id** `string` *required*
>
> ID of the project-owned model to create or replace.
>
> **unit** `string ("CHARACTERS" | "TOKENS" | "MILLISECONDS" | "SECONDS" | "IMAGES" | "REQUESTS")` *required*
>
> Usage unit to which model prices apply.
>
> **modelName** `string` *required*
>
> Model definition name. Custom definitions override built-ins; the newest applicable start date wins.
>
> **startDate** `string`
>
> Apply only to generations newer than this ISO 8601 date.
>
> **inputPrice** `number`
>
> Deprecated: USD per input unit. Prefer pricingTiers.
>
> **totalPrice** `number`
>
> Deprecated: USD per total unit; cannot accompany input/output prices. Prefer pricingTiers.
>
> **outputPrice** `number`
>
> Deprecated: USD per output unit. Prefer pricingTiers.
>
> **tokenizerId** `string ("openai" | "claude")`
>
> Tokenizer applied to matching observations, if configured.
>
> **matchPattern** `string` *required*
>
> Regex matching generation.model. Use (?i)^modelname\$ for an exact case-insensitive match.
>
> **pricingTiers** `array`
>
> Pricing tiers, mutually exclusive with flat prices. Include exactly one default tier with isDefault=true, priority=0 and conditions=\[]. Names and priorities must be unique and each tier needs a price. If omitted, provide flat prices; Langfuse creates a Standard default tier.
>
> **tokenizerConfig** `string`
>
> Arbitrary JSON configuration for the selected tokenizer.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not
