Changelog

Developer-facing Sapient CLI and public API changes.

Changelog

2026-05-26

Sapient added public eval-run orchestration and custom eval history access to the CLI and public API. You can now start durable eval jobs, poll progress, and list the history rows shown in the custom eval dashboard.

Sapient also updated API Performance commands to resolve organization scope from the API key. Generated CLI commands no longer require a brand selector, and public responses no longer expose brand IDs.

CLI

• Added sapient eval-runs create.
• Added sapient eval-runs retrieve.
• Added sapient api-performance custom-evals history list.
• Removed --brand from generated API Performance commands.

API

View API changes

New endpoints

Area	Endpoint
Eval runs	POST /v1/eval-runs, GET /v1/eval-runs/{eval_run_id}
API Performance custom eval history	GET /v1/api-performance/custom-evals/history

Updated endpoints and schemas

• Added PublicPromptEvalRunRequest for starting prompt eval jobs.
• Added PublicApiPerformanceEvalRunRequest for starting API Performance jobs, including source_type: "custom_evals".
• Added PublicEvalRunResponse with job ID, status, stage, dispatch ID, progress, counts, cost estimate, and timestamps.
• Added custom eval history response fields for run IDs, prompts, targets, pass/fail result, score, tool call count, latency, run time, and facets.
• Removed public brand selector parameters and request fields from API Performance endpoints.
• Removed brand ID fields from public API Performance response schemas.
• Removed the legacy include_brand_docs eval field. Use docs_mode instead.

SDK/OpenAPI

• Regenerated the public OpenAPI contract for the new eval-runs and custom eval history operations.
• Regenerated the public OpenAPI contract without brand selectors or public brand ID fields.

Migration notes

• Use sapient eval-runs create when you need to trigger prompt, API Performance, or custom eval jobs from automation.
• Use sapient eval-runs retrieve --eval-run-id <eval_run_id> to poll job progress.
• Use sapient api-performance custom-evals history list --custom-eval-id <custom_eval_id> to list evaluated custom eval rows before retrieving a specific run.
• Remove --brand from API Performance CLI calls. Sapient now resolves the organization scope from SAPIENT_API_KEY.
• Replace include_brand_docs with docs_mode when updating eval context.

2026-05-23

Sapient updated the public API and generated CLI contract for API Performance. This release introduces resource-shaped commands, API Performance actions, skill discovery, starter projects, custom evals, environment profiles, eval runtime selection fields, and source metadata for API, SDK, and CLI runs.

CLI

• Added sapient prompts actions list.
• Added sapient api-performance diagnose.
• Added sapient api-performance targets list.
• Added sapient api-performance config retrieve and update.
• Added sapient api-performance sources list.
• Added sapient api-performance skills list.
• Added sapient api-performance evals list, retrieve, and update.
• Added sapient api-performance custom-evals list, create, retrieve, update, and delete.
• Added sapient api-performance starter-projects list, create, retrieve, update, and delete.
• Added sapient api-performance actions list, refresh, retrieve, update, and verify.

API

View API changes

New endpoints

Area	Endpoint
Prompt config	GET /v1/prompts/config
Prompt actions	GET /v1/prompts/actions
API Performance diagnosis	POST /v1/api-performance/diagnose
API Performance targets	GET /v1/api-performance/targets
API Performance sources	GET /v1/api-performance/sources
API Performance skills	GET /v1/api-performance/skills
API Performance eval definitions	GET /v1/api-performance/evals, GET /v1/api-performance/evals/{eval_id}, PATCH /v1/api-performance/evals/{eval_id}
API Performance custom evals	GET /v1/api-performance/custom-evals, POST /v1/api-performance/custom-evals, GET /v1/api-performance/custom-evals/{custom_eval_id}, PATCH /v1/api-performance/custom-evals/{custom_eval_id}, DELETE /v1/api-performance/custom-evals/{custom_eval_id}
API Performance starter projects	GET /v1/api-performance/starter-projects, POST /v1/api-performance/starter-projects, GET /v1/api-performance/starter-projects/{starter_project_id}, PATCH /v1/api-performance/starter-projects/{starter_project_id}, DELETE /v1/api-performance/starter-projects/{starter_project_id}
API Performance actions	GET /v1/api-performance/actions, POST /v1/api-performance/actions/refresh, GET /v1/api-performance/actions/{action_id}, PATCH /v1/api-performance/actions/{action_id}, POST /v1/api-performance/actions/{action_id}/verify

Updated endpoints and schemas

• Updated GET /v1/prompts and POST /v1/prompts with Stainless method hints for generated CLI commands.
• Updated GET /v1/prompts/actions with a tag selector for cited_pages, opportunities, or all.
• Updated prompt topic, prompt retrieve, prompt update, and prompt delete operations with Stainless method hints.
• Updated /v1/api-performance/config to include env_profiles and default_env_profile_id.
• Updated GET /v1/api-performance/runs and GET /v1/api-performance/runs/{run_id} run summaries to include a sanitized source object with source id, type, label, and public metadata.
• Updated API Performance eval definitions with docs_mode, env_profile_ids, skills_mode, skill_ids, and compare_skills.
• Updated environment profile responses to return environment variable keys instead of secret values.

Replaced endpoint groups

• Replaced /v1/api-performance/evaluation-config with /v1/api-performance/config.
• Replaced /v1/api-performance/interfaces with /v1/api-performance/sources.
• Replaced /v1/api-performance/operations and operation prompt routes with /v1/api-performance/evals and /v1/api-performance/custom-evals.
• Replaced /v1/api-performance/use-cases with /v1/api-performance/custom-evals.
• Removed prompt platform and prompt cost-estimate endpoints from the current public contract.

Migration notes

• Use sapient api-performance config retrieve and update instead of sapient api-performance evaluation-config.
• Use sapient api-performance sources list instead of sapient api-performance interfaces list.
• Use sapient api-performance evals and custom-evals instead of the previous operations, operation-prompts, prompts, and use-cases command groups.
• Use sapient api-performance skills list to discover skill IDs before setting skills_mode selected.
• Use docs_mode when controlling docs context for evals.
• Use skills_mode selected with one or more skill IDs to attach specific skill context to an eval.

2026-05-15

Sapient’s public API and generated CLI exposed the original prompt management and API Performance operation-management contract.

CLI

• sapient status get
• sapient auth status
• sapient prompts list, create, retrieve, update, and delete
• sapient prompts topics list, create, update, and delete
• sapient prompts platforms list
• sapient prompts estimate-cost
• sapient api-performance runs list and retrieve
• sapient api-performance evaluation-config retrieve and update
• sapient api-performance interfaces list
• sapient api-performance platforms list and estimate-cost
• sapient api-performance operations list, create, retrieve, update, and delete
• sapient api-performance operations prompts list and create
• sapient api-performance prompts retrieve, update, and delete
• sapient api-performance use-cases list, create, retrieve, update, and delete

API

View API baseline

Public endpoints

Area	Endpoint
Status and auth	GET /v1/status, GET /v1/auth/status
Prompts	GET /v1/prompts, POST /v1/prompts, GET /v1/prompts/{prompt_id}, PATCH /v1/prompts/{prompt_id}, DELETE /v1/prompts/{prompt_id}
Prompt topics	GET /v1/prompts/topics, POST /v1/prompts/topics, PATCH /v1/prompts/topics/{topic_id}, DELETE /v1/prompts/topics/{topic_id}
Prompt catalog and cost	GET /v1/prompts/platforms, GET /v1/prompts/estimate-cost
API Performance runs	GET /v1/api-performance/runs, GET /v1/api-performance/runs/{run_id}
API Performance config	GET /v1/api-performance/evaluation-config, PUT /v1/api-performance/evaluation-config
API Performance interfaces and platforms	GET /v1/api-performance/interfaces, GET /v1/api-performance/platforms, GET /v1/api-performance/platforms/estimate-cost
API Performance operations	GET /v1/api-performance/operations, POST /v1/api-performance/operations, GET /v1/api-performance/operations/{operation_id}, PATCH /v1/api-performance/operations/{operation_id}, DELETE /v1/api-performance/operations/{operation_id}
API Performance operation prompts	GET /v1/api-performance/operations/{operation_id}/prompts, POST /v1/api-performance/operations/{operation_id}/prompts, GET /v1/api-performance/prompts/{prompt_id}, PATCH /v1/api-performance/prompts/{prompt_id}, DELETE /v1/api-performance/prompts/{prompt_id}
API Performance use cases	GET /v1/api-performance/use-cases, POST /v1/api-performance/use-cases, GET /v1/api-performance/use-cases/{use_case_id}, PATCH /v1/api-performance/use-cases/{use_case_id}, DELETE /v1/api-performance/use-cases/{use_case_id}