Bernstein Observability API

The Observability API from Bernstein — 22 operation(s) for observability.

Operations 22

GET /observability/agents Observability Agents #
GET /observability/effectiveness Observability Effectiveness #
GET /observability/recommendations Observability Recommendations #
GET /observability/budget Observability Budget #
GET /observability/deps Observability Deps #
GET /observability/token-histogram Token Histogram #
GET /observability/queue-depth Get Queue Depth #
GET /observability/timeline Get Timeline #
GET /observability/incidents List Incidents #
GET /observability/incident-timeline/{incident_id} Get Incident Timeline #
GET /observability/token-breakdown Token Breakdown #
GET /api/v1/observability/agents Observability Agents #
GET /api/v1/observability/effectiveness Observability Effectiveness #
GET /api/v1/observability/recommendations Observability Recommendations #
GET /api/v1/observability/budget Observability Budget #
GET /api/v1/observability/deps Observability Deps #
GET /api/v1/observability/token-histogram Token Histogram #
GET /api/v1/observability/queue-depth Get Queue Depth #
GET /api/v1/observability/timeline Get Timeline #
GET /api/v1/observability/incidents List Incidents #
GET /api/v1/observability/incident-timeline/{incident_id} Get Incident Timeline #
GET /api/v1/observability/token-breakdown Token Breakdown #

Work with this as data

Every API 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 apis

7 MCP tools reach this
  • find_apisBrowse and filter every API in the catalog.
  • get_api_artifactsOne API's artifacts, grouped by type.
  • get_openapiThe primary OpenAPI for this API.
  • find_similar_apisAPIs that look like this one.
  • 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.
All 92 tools →

Call it yourself

curl for this page
This API
curl "https://apis.io/api/v1/apis/bernstein-run:bernstein-run-observability-api"
All apis
curl "https://apis.io/api/v1/apis?limit=25"

Discovery needs no key. Ratings and market analysis are Pro.

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.

OpenAPI Specification

bernstein-run-observability-api-openapi.yml Raw ↑
openapi: 3.2.0
info:
  title: Bernstein Task Server Observability API
  description: 'Bernstein REST API - the open-source governance layer for AI agents, one git worktree per task.


    ## Authentication


    Authentication is ENABLED by default. Include a Bearer token in all requests:


    ```

    Authorization: Bearer

    ```


    To run without auth (development only), set `BERNSTEIN_AUTH_DISABLED=1` - this logs a loud warning and passes every request through.


    Public endpoints (no auth required): `/health`, `/health/ready`, `/health/live`, `/ready`, `/alive`, `/.well-known/agent.json`, `/docs`, `/openapi.json`, and the auth-flow endpoints (`/auth/login`, `/auth/oidc/callback`, etc.).


    Webhook and hook endpoints (`/webhook`, `/webhooks/*`, `/hooks/{session_id}`) authenticate via HMAC-SHA256 signatures - they do NOT accept Bearer tokens.


    ## Base URL


    Default: `http://127.0.0.1:8052`. Override with env vars `BERNSTEIN_HOST` and `BERNSTEIN_PORT`.


    ## Error Format


    All errors return JSON with a `detail` field:


    ```json

    {"detail": "Task not found: task-xyz"}

    ```


    | Status | Meaning |

    |--------|---------|

    | 400 | Bad request (validation error) |

    | 401 | Unauthorized (missing/invalid token) |

    | 403 | Forbidden (IP not in allowlist) |

    | 404 | Resource not found |

    | 409 | Conflict (task already in terminal state) |

    | 429 | Rate limited - respect the `Retry-After` header |

    | 500 | Internal server error |'
  version: 3.22.0
  license:
    name: Apache 2.0
    url: https://www.apache.org/licenses/LICENSE-2.0
  contact:
    name: Alex Chernysh
    url: https://github.com/sipyourdrink-ltd/bernstein
servers:
- url: http://{host}:{port}
  description: Task server started by the Bernstein CLI on the operator's own machine. There is no hosted instance; substitute the host and port of your install.
  variables:
    host:
      default: 127.0.0.1
      description: Interface the task server binds to. Loopback by default.
    port:
      default: '8052'
      description: Task server port. Override with BERNSTEIN_PORT.
tags:
- name: Observability
paths:
  /observability/agents:
    get:
      summary: Observability Agents
      description: Return runtime heartbeat, stall-profile, and log-summary data per agent.
      operationId: observability_agents_observability_agents_get
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                additionalProperties: true
                type: object
                title: Response Observability Agents Observability Agents Get
      tags:
      - Observability
  /observability/effectiveness:
    get:
      summary: Observability Effectiveness
      description: Return recent effectiveness data, role trends, and best configs.
      operationId: observability_effectiveness_observability_effectiveness_get
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                additionalProperties: true
                type: object
                title: Response Observability Effectiveness Observability Effectiveness Get
      tags:
      - Observability
  /observability/recommendations:
    get:
      summary: Observability Recommendations
      description: Return the current recommendation set and delivery hit counts.
      operationId: observability_recommendations_observability_recommendations_get
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                additionalProperties: true
                type: object
                title: Response Observability Recommendations Observability Recommendations Get
      tags:
      - Observability
  /observability/budget:
    get:
      summary: Observability Budget
      description: Return completion-budget status per lineage.
      operationId: observability_budget_observability_budget_get
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                additionalProperties: true
                type: object
                title: Response Observability Budget Observability Budget Get
      tags:
      - Observability
  /observability/deps:
    get:
      summary: Observability Deps
      description: 'Return dependency-graph validation status for current tasks.


        The response names the ids it walked - the ready set, the critical path,

        and both broken-edge lists - so the walk is narrowed to the caller''s

        tenant scope rather than the whole store.'
      operationId: observability_deps_observability_deps_get
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                additionalProperties: true
                type: object
                title: Response Observability Deps Observability Deps Get
      tags:
      - Observability
  /observability/token-histogram:
    get:
      summary: Token Histogram
      description: 'Return histogram of token usage by task complexity.


        Shows average tokens consumed for small, medium, large tasks.

        Helps understand token consumption patterns.'
      operationId: token_histogram_observability_token_histogram_get
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                additionalProperties: true
                type: object
                title: Response Token Histogram Observability Token Histogram Get
      tags:
      - Observability
  /observability/queue-depth:
    get:
      summary: Get Queue Depth
      description: 'Return task queue depth over time.


        Returns last N records of queue depth snapshots.


        Args:

        request: FastAPI request.

        limit: Maximum number of records to return (default 100).


        Returns:

        List of queue depth snapshots with timestamps.'
      operationId: get_queue_depth_observability_queue_depth_get
      parameters:
      - name: limit
        in: query
        required: false
        schema:
          type: integer
          default: 100
          title: Limit
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                type: object
                additionalProperties: true
                title: Response Get Queue Depth Observability Queue Depth Get
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
      tags:
      - Observability
  /observability/timeline:
    get:
      summary: Get Timeline
      description: 'Return task timing data for timeline visualization.


        Returns start and end times for all tasks tracked in metrics.'
      operationId: get_timeline_observability_timeline_get
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                additionalProperties: true
                type: object
                title: Response Get Timeline Observability Timeline Get
      tags:
      - Observability
  /observability/incidents:
    get:
      summary: List Incidents
      description: 'List all known incidents.


        Returns:

        Dict with ''incidents'' list.'
      operationId: list_incidents_observability_incidents_get
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                additionalProperties: true
                type: object
                title: Response List Incidents Observability Incidents Get
      tags:
      - Observability
  /observability/incident-timeline/{incident_id}:
    get:
      summary: Get Incident Timeline
      description: 'Build a correlated incident timeline from logs, metrics, and traces.


        Args:

        request: FastAPI request.

        incident_id: The incident ID to build a timeline for.

        window_before: Seconds before incident to include (default 600).

        window_after: Seconds after incident to include (default 300).


        Returns:

        Dict with incident metadata and sorted timeline events.'
      operationId: get_incident_timeline_observability_incident_timeline__incident_id__get
      parameters:
      - name: incident_id
        in: path
        required: true
        schema:
          type: string
          title: Incident Id
      - name: window_before
        in: query
        required: false
        schema:
          type: integer
          default: 600
          title: Window Before
      - name: window_after
        in: query
        required: false
        schema:
          type: integer
          default: 300
          title: Window After
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                type: object
                additionalProperties: true
                title: Response Get Incident Timeline Observability Incident Timeline  Incident Id  Get
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
      tags:
      - Observability
  /observability/token-breakdown:
    get:
      summary: Token Breakdown
      description: 'Return per-session token consumption breakdown.


        For each agent session with a ``.tokens`` sidecar file, breaks down

        token usage into estimated categories:


        - ``system_prompt_estimated``: overhead from Bernstein role templates

        - ``task_description_estimated``: tokens for the task title + description

        - ``context_estimated``: remaining input tokens (context files, tool results,

        prior conversation history, etc.)

        - ``output_tokens``: actual assistant output tokens


        Also reports ``optimization_opportunities`` - a list of human-readable

        insights when a category accounts for an unusually large share of tokens

        (e.g. "context files are 60% of input").


        Token sidecar files live at ``.sdd/runtime/{session_id}.tokens``.

        Breakdown percentages use a 4-chars/token heuristic for size estimates.


        Returns:

        Dict with ``sessions`` list and aggregate ``summary``.'
      operationId: token_breakdown_observability_token_breakdown_get
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                additionalProperties: true
                type: object
                title: Response Token Breakdown Observability Token Breakdown Get
      tags:
      - Observability
  /api/v1/observability/agents:
    get:
      summary: Observability Agents
      description: Return runtime heartbeat, stall-profile, and log-summary data per agent.
      operationId: observability_agents_api_v1_observability_agents_get
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                additionalProperties: true
                type: object
                title: Response Observability Agents Api V1 Observability Agents Get
      tags:
      - Observability
  /api/v1/observability/effectiveness:
    get:
      summary: Observability Effectiveness
      description: Return recent effectiveness data, role trends, and best configs.
      operationId: observability_effectiveness_api_v1_observability_effectiveness_get
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                additionalProperties: true
                type: object
                title: Response Observability Effectiveness Api V1 Observability Effectiveness Get
      tags:
      - Observability
  /api/v1/observability/recommendations:
    get:
      summary: Observability Recommendations
      description: Return the current recommendation set and delivery hit counts.
      operationId: observability_recommendations_api_v1_observability_recommendations_get
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                additionalProperties: true
                type: object
                title: Response Observability Recommendations Api V1 Observability Recommendations Get
      tags:
      - Observability
  /api/v1/observability/budget:
    get:
      summary: Observability Budget
      description: Return completion-budget status per lineage.
      operationId: observability_budget_api_v1_observability_budget_get
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                additionalProperties: true
                type: object
                title: Response Observability Budget Api V1 Observability Budget Get
      tags:
      - Observability
  /api/v1/observability/deps:
    get:
      summary: Observability Deps
      description: 'Return dependency-graph validation status for current tasks.


        The response names the ids it walked - the ready set, the critical path,

        and both broken-edge lists - so the walk is narrowed to the caller''s

        tenant scope rather than the whole store.'
      operationId: observability_deps_api_v1_observability_deps_get
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                additionalProperties: true
                type: object
                title: Response Observability Deps Api V1 Observability Deps Get
      tags:
      - Observability
  /api/v1/observability/token-histogram:
    get:
      summary: Token Histogram
      description: 'Return histogram of token usage by task complexity.


        Shows average tokens consumed for small, medium, large tasks.

        Helps understand token consumption patterns.'
      operationId: token_histogram_api_v1_observability_token_histogram_get
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                additionalProperties: true
                type: object
                title: Response Token Histogram Api V1 Observability Token Histogram Get
      tags:
      - Observability
  /api/v1/observability/queue-depth:
    get:
      summary: Get Queue Depth
      description: 'Return task queue depth over time.


        Returns last N records of queue depth snapshots.


        Args:

        request: FastAPI request.

        limit: Maximum number of records to return (default 100).


        Returns:

        List of queue depth snapshots with timestamps.'
      operationId: get_queue_depth_api_v1_observability_queue_depth_get
      parameters:
      - name: limit
        in: query
        required: false
        schema:
          type: integer
          default: 100
          title: Limit
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                type: object
                additionalProperties: true
                title: Response Get Queue Depth Api V1 Observability Queue Depth Get
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
      tags:
      - Observability
  /api/v1/observability/timeline:
    get:
      summary: Get Timeline
      description: 'Return task timing data for timeline visualization.


        Returns start and end times for all tasks tracked in metrics.'
      operationId: get_timeline_api_v1_observability_timeline_get
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                additionalProperties: true
                type: object
                title: Response Get Timeline Api V1 Observability Timeline Get
      tags:
      - Observability
  /api/v1/observability/incidents:
    get:
      summary: List Incidents
      description: 'List all known incidents.


        Returns:

        Dict with ''incidents'' list.'
      operationId: list_incidents_api_v1_observability_incidents_get
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                additionalProperties: true
                type: object
                title: Response List Incidents Api V1 Observability Incidents Get
      tags:
      - Observability
  /api/v1/observability/incident-timeline/{incident_id}:
    get:
      summary: Get Incident Timeline
      description: 'Build a correlated incident timeline from logs, metrics, and traces.


        Args:

        request: FastAPI request.

        incident_id: The incident ID to build a timeline for.

        window_before: Seconds before incident to include (default 600).

        window_after: Seconds after incident to include (default 300).


        Returns:

        Dict with incident metadata and sorted timeline events.'
      operationId: get_incident_timeline_api_v1_observability_incident_timeline__incident_id__get
      parameters:
      - name: incident_id
        in: path
        required: true
        schema:
          type: string
          title: Incident Id
      - name: window_before
        in: query
        required: false
        schema:
          type: integer
          default: 600
          title: Window Before
      - name: window_after
        in: query
        required: false
        schema:
          type: integer
          default: 300
          title: Window After
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                type: object
                additionalProperties: true
                title: Response Get Incident Timeline Api V1 Observability Incident Timeline  Incident Id  Get
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
      tags:
      - Observability
  /api/v1/observability/token-breakdown:
    get:
      summary: Token Breakdown
      description: 'Return per-session token consumption breakdown.


        For each agent session with a ``.tokens`` sidecar file, breaks down

        token usage into estimated categories:


        - ``system_prompt_estimated``: overhead from Bernstein role templates

        - ``task_description_estimated``: tokens for the task title + description

        - ``context_estimated``: remaining input tokens (context files, tool results,

        prior conversation history, etc.)

        - ``output_tokens``: actual assistant output tokens


        Also reports ``optimization_opportunities`` - a list of human-readable

        insights when a category accounts for an unusually large share of tokens

        (e.g. "context files are 60% of input").


        Token sidecar files live at ``.sdd/runtime/{session_id}.tokens``.

        Breakdown percentages use a 4-chars/token heuristic for size estimates.


        Returns:

        Dict with ``sessions`` list and aggregate ``summary``.'
      operationId: token_breakdown_api_v1_observability_token_breakdown_get
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                additionalProperties: true
                type: object
                title: Response Token Breakdown Api V1 Observability Token Breakdown Get
      tags:
      - Observability
components:
  schemas:
    HTTPValidationError:
      properties:
        detail:
          items:
            $ref: '#/components/schemas/ValidationError'
          type: array
          title: Detail
      type: object
      title: HTTPValidationError
    ValidationError:
      properties:
        loc:
          items:
            anyOf:
            - type: string
            - type: integer
          type: array
          title: Location
        msg:
          type: string
          title: Message
        type:
          type: string
          title: Error Type
        input:
          title: Input
        ctx:
          type: object
          title: Context
      type: object
      required:
      - loc
      - msg
      - type
      title: ValidationError