AgentImprovementSession
Read view of an Improve-Agent session — what the frontend polls to track progress. `provider_key` and other secrets are never serialized. The raw `proposal` (full prompt bodies + applied diff values) stays server-side; the API exposes a trimmed `proposal_summary` instead.
Properties
| Name | Type | Description |
|---|---|---|
| id | integer | |
| project | integernull | |
| agent | integernull | |
| agent_name | string | |
| provider | string | |
| source | string | * `call_log` - Call Log * `scenario` - Scenario * `run` - Run |
| current_phase | string | |
| insights | object | |
| call_log_ids | object | |
| run_ids | object | |
| scenario_ids | object | |
| status | string | * `pending` - Pending * `running` - Running * `succeeded` - Succeeded * `failed` - Failed * `no_improvement` - No Improvement * `cancelled` - Cancelled |
| stage | stringnull | * `setup` - Setup * `scenario_generation` - Scenario Generation * `reproduce` - Reproduce * `force` - Force * `baseline_run` - Baseline Run * `propose` - Propose * `apply` - Apply * `verify_run` - Ver |
| stage_status | stringnull | * `running` - Running * `waiting` - Waiting * `waiting_input` - Waiting Input * `done` - Done * `failed` - Failed |
| stage_started_at | stringnull | |
| stage_history | object | |
| baseline_result | integernull | |
| baseline_source_result | integernull | |
| verify_result | integernull | |
| metric_delta | object | |
| proposal_summary | objectnull | |
| iteration | integer | |
| iteration_history | object | |
| failing_scenario_ids | object | |
| rounds_since_improvement | integer | |
| best_iteration | integernull | |
| best_score | numbernull | |
| pending_question | object | |
| reproduction | object | Reproduction evidence, through the pipeline's own whitelist. Counts, rates and customer-facing field labels only — no configuration values, and no raw provider dot-paths. |
| labs_metrics | array | |
| question_answers | object | |
| scenario_edit_proposals | object | |
| user_guidance | array | |
| parent_session | integernull | |
| conversation_id | stringnull | |
| message_id | stringnull | |
| error_message | string | |
| failure_kind | string | |
| summary_json | object | |
| slack_notification_status | string | * `not_attempted` - Not Attempted * `sending` - Sending * `sent` - Sent * `skipped_no_channel` - Skipped No Channel * `failed` - Failed * `held` - Held |
| routed_to | string | |
| slack_channel_id | string | |
| slack_message_ts | string | |
| slack_message_text | string | |
| slack_error | string | |
| promoted_at | stringnull | |
| promoted_by | integernull | |
| promoted_by_email | stringnull | |
| promotion_summary | objectnull | |
| clone_state | object | |
| created_at | string | |
| updated_at | string |
JSON Schema
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"$id": "https://artifacts.apis.io/cekura-ai/json-schema/cekura-ai-agent-improvement-session-schema.json",
"title": "AgentImprovementSession",
"description": "Read view of an Improve-Agent session — what the frontend polls to\ntrack progress. `provider_key` and other secrets are never serialized.\nThe raw `proposal` (full prompt bodies + applied diff values) stays\nserver-side; the API exposes a trimmed `proposal_summary` instead.",
"x-generated": "2026-11-10",
"x-method": "derived",
"x-generator": "derive-json-schema.py",
"x-source": "openapi/cekura-ai-observability-api-openapi.yml#/components/schemas/AgentImprovementSession",
"type": "object",
"properties": {
"id": {
"type": "integer",
"readOnly": true
},
"project": {
"type": [
"integer",
"null"
],
"readOnly": true
},
"agent": {
"type": [
"integer",
"null"
],
"readOnly": true
},
"agent_name": {
"type": "string",
"readOnly": true,
"default": ""
},
"provider": {
"type": "string",
"readOnly": true
},
"source": {
"enum": [
"call_log",
"scenario",
"run"
],
"type": "string",
"description": "* `call_log` - Call Log\n* `scenario` - Scenario\n* `run` - Run",
"x-spec-enum-id": "7a464211ef729f6c",
"readOnly": true
},
"current_phase": {
"type": "string",
"readOnly": true
},
"insights": {
"readOnly": true
},
"call_log_ids": {
"readOnly": true
},
"run_ids": {
"readOnly": true
},
"scenario_ids": {
"readOnly": true
},
"status": {
"enum": [
"pending",
"running",
"succeeded",
"failed",
"no_improvement",
"cancelled"
],
"type": "string",
"description": "* `pending` - Pending\n* `running` - Running\n* `succeeded` - Succeeded\n* `failed` - Failed\n* `no_improvement` - No Improvement\n* `cancelled` - Cancelled",
"x-spec-enum-id": "c381800a059557a1",
"readOnly": true
},
"stage": {
"enum": [
"setup",
"scenario_generation",
"reproduce",
"force",
"baseline_run",
"propose",
"apply",
"verify_run",
"finalize",
null
],
"type": [
"string",
"null"
],
"description": "* `setup` - Setup\n* `scenario_generation` - Scenario Generation\n* `reproduce` - Reproduce\n* `force` - Force\n* `baseline_run` - Baseline Run\n* `propose` - Propose\n* `apply` - Apply\n* `verify_run` - Verify Run\n* `finalize` - Finalize",
"x-spec-enum-id": "994fc0ee8cd8c795",
"readOnly": true
},
"stage_status": {
"enum": [
"running",
"waiting",
"waiting_input",
"done",
"failed",
null
],
"type": [
"string",
"null"
],
"description": "* `running` - Running\n* `waiting` - Waiting\n* `waiting_input` - Waiting Input\n* `done` - Done\n* `failed` - Failed",
"x-spec-enum-id": "8a59077dd595b0eb",
"readOnly": true
},
"stage_started_at": {
"type": [
"string",
"null"
],
"format": "date-time",
"readOnly": true
},
"stage_history": {
"readOnly": true
},
"baseline_result": {
"type": [
"integer",
"null"
],
"readOnly": true
},
"baseline_source_result": {
"type": [
"integer",
"null"
],
"readOnly": true
},
"verify_result": {
"type": [
"integer",
"null"
],
"readOnly": true
},
"metric_delta": {
"oneOf": [
{},
{
"type": "null"
}
],
"readOnly": true
},
"proposal_summary": {
"type": [
"object",
"null"
],
"additionalProperties": {},
"readOnly": true
},
"iteration": {
"type": "integer",
"readOnly": true
},
"iteration_history": {
"readOnly": true
},
"failing_scenario_ids": {
"readOnly": true
},
"rounds_since_improvement": {
"type": "integer",
"readOnly": true
},
"best_iteration": {
"type": [
"integer",
"null"
],
"readOnly": true
},
"best_score": {
"type": [
"number",
"null"
],
"format": "double",
"readOnly": true
},
"pending_question": {
"oneOf": [
{},
{
"type": "null"
}
],
"readOnly": true
},
"reproduction": {
"type": "object",
"additionalProperties": {},
"description": "Reproduction evidence, through the pipeline's own whitelist.\n\nCounts, rates and customer-facing field labels only — no configuration\nvalues, and no raw provider dot-paths.",
"readOnly": true
},
"labs_metrics": {
"type": "array",
"items": {
"type": "object",
"additionalProperties": {}
},
"readOnly": true
},
"question_answers": {
"readOnly": true
},
"scenario_edit_proposals": {
"readOnly": true
},
"user_guidance": {
"type": "array",
"items": {
"type": "object",
"additionalProperties": {}
},
"readOnly": true
},
"parent_session": {
"type": [
"integer",
"null"
],
"readOnly": true
},
"conversation_id": {
"type": [
"string",
"null"
],
"format": "uuid",
"readOnly": true
},
"message_id": {
"type": [
"string",
"null"
],
"format": "uuid",
"readOnly": true
},
"error_message": {
"type": "string",
"readOnly": true
},
"failure_kind": {
"type": "string",
"readOnly": true
},
"summary_json": {
"readOnly": true
},
"slack_notification_status": {
"enum": [
"not_attempted",
"sending",
"sent",
"skipped_no_channel",
"failed",
"held"
],
"type": "string",
"description": "* `not_attempted` - Not Attempted\n* `sending` - Sending\n* `sent` - Sent\n* `skipped_no_channel` - Skipped No Channel\n* `failed` - Failed\n* `held` - Held",
"x-spec-enum-id": "01d4c400b466e86e",
"readOnly": true
},
"routed_to": {
"type": "string",
"readOnly": true
},
"slack_channel_id": {
"type": "string",
"readOnly": true
},
"slack_message_ts": {
"type": "string",
"readOnly": true
},
"slack_message_text": {
"type": "string",
"readOnly": true
},
"slack_error": {
"type": "string",
"readOnly": true
},
"promoted_at": {
"type": [
"string",
"null"
],
"format": "date-time",
"readOnly": true
},
"promoted_by": {
"type": [
"integer",
"null"
],
"readOnly": true
},
"promoted_by_email": {
"type": [
"string",
"null"
],
"readOnly": true,
"default": ""
},
"promotion_summary": {
"type": [
"object",
"null"
],
"additionalProperties": {},
"readOnly": true
},
"clone_state": {
"type": "object",
"additionalProperties": {},
"readOnly": true
},
"created_at": {
"type": "string",
"format": "date-time",
"readOnly": true
},
"updated_at": {
"type": "string",
"format": "date-time",
"readOnly": true
}
}
}
Work with this as data
Every JSON Schema here is available over the APIs.io API and to AI agents over MCP.
MCP server
One button, every client — Claude, Cursor, VS Code and the rest.
https://apis.io/mcp
Tools for schemas
4 MCP tools reach this
find_json_schemasBrowse and filter every JSON Schema in the catalog.apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.resolveTurn a domain, URL or GitHub org into the provider it belongs to.find_cohortsEvery scored population of providers in the catalog.
Call it yourself
curl for this page
curl "https://apis.io/api/v1/json-schemas/cekura-ai-agent-improvement-session"
curl "https://apis.io/api/v1/json-schemas?limit=25"
Calls without X-API-Key need no key. Calls with it need a paid plan — get a key.
Get an API key
Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.
A second provider on the same verified email joins the account you already have.