APIAgents

Update Monitoring

Activate and deactivate Evaluators for monitoring the Agent. An activated Evaluator will automatically be run on all new Logs within the Agent for monitoring purposes.

Path parameters

idstringRequired

Headers

X-API-KEYstringRequired

Request

This endpoint expects an object.
activatelist of objectsOptional
Evaluators to activate for Monitoring. These will be automatically run on new Logs.
deactivatelist of objectsOptional
Evaluators to deactivate. These will not be run on new Logs.

Response

Successful Response
pathstring
Path of the Agent, including the name, which is used as a unique identifier.
idstring
Unique identifier for the Agent.
modelstring

The model instance used, e.g. gpt-4. See supported models

toolslist of objects
List of tools that the Agent can call. These can be linked files or inline tools.
namestring
Name of the Agent.
version_idstring
Unique identifier for the specific Agent Version. If no query params provided, the default deployed Agent Version is returned.
created_atdatetime
updated_atdatetime
statusenum
The status of the Agent Version.
Allowed values:
last_used_atdatetime
version_logs_countinteger
The number of logs that have been generated for this Agent Version
total_logs_countinteger
The number of logs that have been generated across all Agent Versions
inputslist of objects
Inputs associated to the Agent. Inputs correspond to any of the variables used within the Agent template.
directory_idstringOptional
ID of the directory that the file is in on Humanloop.
endpointenumOptional
The provider model endpoint used.
Allowed values:
templatestring or list of objectsOptional

The template contains the main structure and instructions for the model, including input variables for dynamic values.

For chat models, provide the template as a ChatTemplate (a list of messages), e.g. a system message, followed by a user message with an input variable. For completion models, provide a prompt template as a string.

Input variables should be specified with double curly bracket syntax: {{input_name}}.

template_languageenumOptional
The template language to use for rendering the template.
Allowed values:
providerenumOptional
The company providing the underlying model service.
max_tokensintegerOptionalDefaults to -1

The maximum number of tokens to generate. Provide max_tokens=-1 to dynamically calculate the maximum number of tokens to generate given the length of the prompt

temperaturedoubleOptionalDefaults to 1
What sampling temperature to use when making a generation. Higher values means the model will be more creative.
top_pdoubleOptionalDefaults to 1

An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass.

stopstring or list of stringsOptional

The string (or list of strings) after which the model will stop generating. The returned text will not contain the stop sequence.

presence_penaltydoubleOptionalDefaults to 0

Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the generation so far.

frequency_penaltydoubleOptionalDefaults to 0

Number between -2.0 and 2.0. Positive values penalize new tokens based on how frequently they appear in the generation so far.

othermap from strings to anyOptional
Other parameter values to be passed to the provider call.
seedintegerOptional
If specified, model will make a best effort to sample deterministically, but it is not guaranteed.
response_formatobjectOptional

The format of the response. Only {"type": "json_object"} is currently supported for chat.

reasoning_effortenum or integerOptional

Guidance on how many reasoning tokens it should generate before creating a response to the prompt. OpenAI reasoning models (o1, o3-mini) expect a OpenAIReasoningEffort enum. Anthropic reasoning models expect an integer, which signifies the maximum token budget.

attributesmap from strings to anyOptional
Additional fields to describe the Prompt. Helpful to separate Prompt versions from each other with details on how they were created or used.
max_iterationsintegerOptional
The maximum number of iterations the Agent can run. This is used to limit the number of times the Agent model is called.
version_namestringOptional
Unique name for the Agent version. Version names must be unique for a given Agent.
version_descriptionstringOptional
Description of the version, e.g., the changes made in this version.
descriptionstringOptional
Description of the Agent.
tagslist of stringsOptional
List of tags associated with the file.
readmestringOptional
Long description of the file.
schemamap from strings to anyOptional
The JSON schema for the Prompt.
type"agent"OptionalDefaults to agent
environmentslist of objectsOptional
The list of environments the Agent Version is deployed to.
created_byanyOptional
The user who created the Agent.
committed_byanyOptional
The user who committed the Agent Version.
committed_atdatetimeOptional
The date and time the Agent Version was committed.
evaluatorslist of objectsOptional
Evaluators that have been attached to this Agent that are used for monitoring logs.
evaluator_aggregateslist of objectsOptional
Aggregation of Evaluator results for the Agent Version.
raw_file_contentstringOptional
The raw content of the Agent. Corresponds to the .agent file.

Errors