API Reference
API Reference

Get Prompt History

Get a list of historical versions of a prompt by its ID

GET/api/v1/prompts/{prompt_id}/history

Authentication

Syllable-API-Keyrequired

Send Syllable-API-Key in the header.

Need a credential? Create or manage an API token in the Syllable Console.

Parameters

Path parameters

prompt_id integer path required

Responses

200Successful Response

application/json

response PromptHistoryResponse[] required
Item schema
itemsPromptHistoryResponserequired

A historical prompt version, with the lifecycle of the model it was pinned to.

Agents pinned to an old version run that version's model, so a retired model in the history is as much of a problem as one on the current version.

13 fields
timestampstring (date-time)required

Timestamp of the change resulting in this version

prompt_idstringrequired

ID of the prompt

version_numberintegerrequired

Version number of this version. Starts at 1 when prompt is created, and incremented on each change.

prompt_textstringrequired

Text of the prompt at this version

prompt_descriptionstring | nulloptional

Description of the prompt at this version

prompt_namestringrequired

Name of the prompt at this version

llm_configPromptLlmConfig | nulloptional

String representation of LLM config for the prompt at this version

6 options
providerenum<string>optional

Provider of the LLM model.

Allowed values ["anthropic","azure_openai","google","openai"]Default azure_openai
modelstringoptional

Name of the model. Must match the deployment name in Azure AI Studio.

Default gpt-4o
versionstring | nulloptional

Deprecated model version. This value is ignored and resolved automatically.

api_versionstring | nulloptional

Version of the provider's API.

temperaturenumber | nulloptional

Temperature parameter for the model. Determines randomness of responses - higher is more random, lower is more focused. Must be between 0.0 and 2.0, inclusive.

seedinteger | nulloptional

Controls the reproducibility of the job. The LLM will give the same or similar responses given the same inputs in multiple conversations with the same seed.

commentsstring | nulloptional

Comments describing the change that resulted in this version

user_emailstringrequired

Email address of the user who made the change that resulted in this version

linked_toolsPromptHistoryLinkedTool[]optional

Tools that were linked to this version of the prompt

Default []
Item schema
itemsPromptHistoryLinkedToolrequired

Record of a tool linked to a previous prompt version in the prompt history.

4 fields
tool_idintegerrequired

ID of the tool

current_tool_namestringrequired

Current name of the tool (may have been different at the time the given version of the prompt was created)

out_of_datebooleanrequired

Whether the tool has changed (not including being deleted) since the given version of the prompt was created

deletedbooleanrequired

Whether the tool has been deleted since the given version of the prompt was created

session_end_toolPromptHistoryLinkedTool | nullreference defined above

Session end tool that was configured on this version of the prompt, if any

is_pre_enhancementsbooleanrequired

Whether this version of the prompt was created before history of tool-prompt linking was tracked

validation_issuesValidationIssue[] | nulloptional

Lifecycle findings for the model this version was saved on.

Item schema
itemsValidationIssuerequired

A single validation finding with severity, location, and description.

5 fields
idstringrequired

Stable machine-readable identifier (kebab-case)

severityenum<string>optional
Allowed values ["info","warning","error"]Default error
messagestringrequired

Human-readable description

pathstring | nulloptional

JSONPath-style location (e.g. $.context.task.steps[2])

valuestring | nulloptional

The offending value, when it adds clarity

Response example
[
  {
    "timestamp": "string",
    "prompt_id": "string",
    "version_number": 0,
    "prompt_text": "string",
    "prompt_description": "string",
    "prompt_name": "string",
    "llm_config": "string",
    "comments": "string",
    "user_email": "string",
    "linked_tools": [],
    "session_end_tool": "string",
    "is_pre_enhancements": true,
    "validation_issues": "string"
  }
]
422Validation Error

application/json

response HTTPValidationError required
1 field
detailValidationError[]optional
Item schema
itemsValidationErrorrequired
3 fields
locstring | integer[]required
Item schema
itemsstring | integerrequired
2 options
Option 1stringrequired
Option 2integerrequired
msgstringrequired
typestringrequired
Response example
{
  "detail": [
    {
      "loc": [
        "string"
      ],
      "msg": "string",
      "type": "string"
    }
  ]
}