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-quality-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.

GitHub Google LinkedIn

A second provider on the same verified email joins the account you already have.

OpenAPI Specification

openapi: 3.2.0
info:
  title: Bernstein Task Server Quality 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: Quality
paths:
  /quality:
    get:
      summary: Get Quality Metrics
      description: 'Return aggregated internal quality metrics (last 7 days).


        Reads from ``.sdd/metrics/`` JSONL files to compute:


        - ``per_model``: per-model success rate, avg tokens, and completion

        time distribution (p50/p90/p99).

        - ``overall``: aggregate across all models.

        - ``gate_stats``: per-gate pass/blocked/flagged counts (last 30 days).

        - ``guardrail_pass_rate``: fraction of gate checks that passed.

        - ``review_rejection_rate``: fraction of tasks that failed overall.


        Returns an empty structure when no metric data exists yet.'
      operationId: get_quality_metrics_quality_get
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema: {}
      tags:
      - Quality
  /quality/budget-forecast:
    get:
      summary: Get Budget Forecast
      description: Return projected spend for the active planned backlog.
      operationId: get_budget_forecast_quality_budget_forecast_get
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema: {}
      tags:
      - Quality
  /quality/trend:
    get:
      summary: Get Quality Trend
      description: 'Return time-series quality metrics for trend visualization.


        Buckets quality data by day (default) or week and returns per-bucket

        success rates, gate pass rates, and average quality scores. Covers the

        last 90 days by default so dashboards can show weeks-to-months trends.


        Query parameters:

        - ``days``: lookback window in days (default 90, max 365).

        - ``granularity``: ``"day"`` (default) or ``"week"``.


        Returns a ``series`` list ordered by date, each entry containing:

        - ``date``: ISO date string (bucket start).

        - ``ts``: Unix timestamp of the bucket start.

        - ``tasks_total``, ``tasks_success``: raw task counts.

        - ``success_rate``: fraction of tasks that succeeded (omitted if no tasks).

        - ``gate_pass_rates``: dict of gate name → pass rate for that bucket.

        - ``avg_quality_score``: mean quality score 0-100 (omitted if no scores).'
      operationId: get_quality_trend_quality_trend_get
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema: {}
      tags:
      - Quality
  /quality/models:
    get:
      summary: Get Quality By Model
      description: 'Return per-model quality breakdown (last 30 days).


        Extended view of model performance for routing configuration and cost

        analysis. Covers a longer window than the default ``/quality`` summary.'
      operationId: get_quality_by_model_quality_models_get
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema: {}
      tags:
      - Quality
  /quality/file-health:
    get:
      summary: List File Health
      description: 'Return per-file code health scores, worst files first.


        Query parameters:

        - ``limit``: max results (default 50, max 500).

        - ``min_score``: only return files at or below this score.

        - ``grade``: filter by grade (A/B/C/D/F).


        Returns a JSON object with ``files`` list and summary statistics.'
      operationId: list_file_health_quality_file_health_get
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema: {}
      tags:
      - Quality
  /quality/file-health/flagged:
    get:
      summary: List Flagged Files
      description: 'Return files currently flagged for human review due to health degradation.


        A file is flagged when:

        - A task dropped its health score by ≥10 points, OR

        - Its total health score is below 60 (grade D or F).


        Returns ``files`` list with detailed health scores and degradation context.'
      operationId: list_flagged_files_quality_file_health_flagged_get
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema: {}
      tags:
      - Quality
  /quality/file-health/{file_path}:
    get:
      summary: Get File Health
      description: 'Return the current health score for a single file.


        Args:

        file_path: File path relative to repository root (URL-encoded).


        Returns 404 if the file has never been tracked.'
      operationId: get_file_health_quality_file_health__file_path__get
      parameters:
      - name: file_path
        in: path
        required: true
        schema:
          type: string
          title: File Path
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema: {}
        '404':
          description: File not tracked yet
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
      tags:
      - Quality
  /api/v1/quality:
    get:
      summary: Get Quality Metrics
      description: 'Return aggregated internal quality metrics (last 7 days).


        Reads from ``.sdd/metrics/`` JSONL files to compute:


        - ``per_model``: per-model success rate, avg tokens, and completion

        time distribution (p50/p90/p99).

        - ``overall``: aggregate across all models.

        - ``gate_stats``: per-gate pass/blocked/flagged counts (last 30 days).

        - ``guardrail_pass_rate``: fraction of gate checks that passed.

        - ``review_rejection_rate``: fraction of tasks that failed overall.


        Returns an empty structure when no metric data exists yet.'
      operationId: get_quality_metrics_api_v1_quality_get
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema: {}
      tags:
      - Quality
  /api/v1/quality/budget-forecast:
    get:
      summary: Get Budget Forecast
      description: Return projected spend for the active planned backlog.
      operationId: get_budget_forecast_api_v1_quality_budget_forecast_get
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema: {}
      tags:
      - Quality
  /api/v1/quality/trend:
    get:
      summary: Get Quality Trend
      description: 'Return time-series quality metrics for trend visualization.


        Buckets quality data by day (default) or week and returns per-bucket

        success rates, gate pass rates, and average quality scores. Covers the

        last 90 days by default so dashboards can show weeks-to-months trends.


        Query parameters:

        - ``days``: lookback window in days (default 90, max 365).

        - ``granularity``: ``"day"`` (default) or ``"week"``.


        Returns a ``series`` list ordered by date, each entry containing:

        - ``date``: ISO date string (bucket start).

        - ``ts``: Unix timestamp of the bucket start.

        - ``tasks_total``, ``tasks_success``: raw task counts.

        - ``success_rate``: fraction of tasks that succeeded (omitted if no tasks).

        - ``gate_pass_rates``: dict of gate name → pass rate for that bucket.

        - ``avg_quality_score``: mean quality score 0-100 (omitted if no scores).'
      operationId: get_quality_trend_api_v1_quality_trend_get
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema: {}
      tags:
      - Quality
  /api/v1/quality/models:
    get:
      summary: Get Quality By Model
      description: 'Return per-model quality breakdown (last 30 days).


        Extended view of model performance for routing configuration and cost

        analysis. Covers a longer window than the default ``/quality`` summary.'
      operationId: get_quality_by_model_api_v1_quality_models_get
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema: {}
      tags:
      - Quality
  /api/v1/quality/file-health:
    get:
      summary: List File Health
      description: 'Return per-file code health scores, worst files first.


        Query parameters:

        - ``limit``: max results (default 50, max 500).

        - ``min_score``: only return files at or below this score.

        - ``grade``: filter by grade (A/B/C/D/F).


        Returns a JSON object with ``files`` list and summary statistics.'
      operationId: list_file_health_api_v1_quality_file_health_get
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema: {}
      tags:
      - Quality
  /api/v1/quality/file-health/flagged:
    get:
      summary: List Flagged Files
      description: 'Return files currently flagged for human review due to health degradation.


        A file is flagged when:

        - A task dropped its health score by ≥10 points, OR

        - Its total health score is below 60 (grade D or F).


        Returns ``files`` list with detailed health scores and degradation context.'
      operationId: list_flagged_files_api_v1_quality_file_health_flagged_get
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema: {}
      tags:
      - Quality
  /api/v1/quality/file-health/{file_path}:
    get:
      summary: Get File Health
      description: 'Return the current health score for a single file.


        Args:

        file_path: File path relative to repository root (URL-encoded).


        Returns 404 if the file has never been tracked.'
      operationId: get_file_health_api_v1_quality_file_health__file_path__get
      parameters:
      - name: file_path
        in: path
        required: true
        schema:
          type: string
          title: File Path
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema: {}
        '404':
          description: File not tracked yet
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
      tags:
      - Quality
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