Eval Configuration

Update Eval Configuration

Updates an eval configuration and returns the saved version. Omitted fields retain their existing values. Configurations with source_id set to null belong to user-created evals and can also be updated through the eval's eval field.

patch/v1/api-performance/evals/{eval_id}

Request

Base URL
https://api.lightsage.com
Auth
API key in header X-Lightsage-Api-Key

Path parameters

eval_idstring required

Request body

custom_promptstring

Overrides the stored prompt.

expected_behaviorstring

Deprecated compatibility alias for a judge criterion. Prefer graders; this value updates the primary judge grader.

starting_project_idstring

ID from GET /v1/api-performance/starter-projects. Empty string clears it.

docs_mode'default' | 'include' | 'exclude'

include adds the organization's docs to the agent's context; exclude withholds them.

include_env_varsboolean

Names only, never values.

env_profile_idsstring[] nullable

IDs from env_profiles in GET /v1/api-performance/config. Empty list clears the selection.

model_idsstring[] nullable

IDs from GET /v1/api-performance/targets. Empty list falls back to the config-level models.

compare_skillsboolean

Run an additional comparison with skill context enabled.

skills_mode'none' | 'all' | 'selected'

selected uses skill_ids; all uses every skill; none supplies no skill context.

skill_idsstring[] nullable

IDs from GET /v1/api-performance/skills; used when skills_mode is selected.

mcp_enabledboolean

search_grounding'disabled' | 'enabled' | 'default'

Requested web-retrieval behavior for an eval run.

grounding_enabledboolean

Allow native web search and URL retrieval tools during agent runs. When false, configured brand docs are also withheld.

run_contextobject nullable

enabledboolean

Response

Successful Response

idstring required

operation_idstring required

For a user-created eval, equals the eval ID when source_id is null.

source_idstring nullable

Null for a user-created eval configuration.

eval_typestring required

promptstring nullable

custom_promptstring nullable

Overrides prompt when set.

expected_behaviorstring nullable

Deprecated compatibility view of the primary judge criterion. Use graders for the canonical configuration.

starting_project_idstring nullable

docs_mode'default' | 'include' | 'exclude'

include adds the organization's docs to the agent's context; exclude withholds them.

include_env_varsboolean

Names only, never values.

env_profile_idsstring[]

model_idsstring[]

Empty means the config-level models are used.

compare_skillsboolean

Whether to run an additional comparison with skill context enabled.

skills_mode'none' | 'all' | 'selected'

selected uses skill_ids; all uses every skill; none supplies no skill context.

skills_enabledboolean

skill_idsstring[]

mcp_enabledboolean

search_grounding'disabled' | 'enabled' | 'default'

Requested web-retrieval behavior for an eval run.

grounding_enabledboolean

Whether native web search and URL retrieval tools are available to the agent. When false, configured brand docs are also withheld.

run_contextobject