> ## Documentation Index
> Fetch the complete documentation index at: https://docs.getoneprofile.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Keep the business context as it was before a run

> The review's "Keep everything as it was" (run 23): put back every section and choice a website run replaced, who last wrote each, and the website it was last generated from, exactly as they stood, so nothing records the run. Refused (422, `nothing_to_keep`) when the run replaced nothing or something was written since; 404 when the run is not this workspace's. Only a workspace admin can, never with an API key. With `dry_run` it answers the business context as it would be put back, and puts nothing back.



## OpenAPI

````yaml /openapi.json post /ai-context/runs/{job_id}/revert/
openapi: 3.1.0
info:
  contact:
    email: support@getoneprofile.ai
    name: Oneprofile Support
  description: >-
    REST API reference for Oneprofile, the GTM data layer for your CRM. Manage
    tables, enrichments, and integrations. Authenticate with an API key to get
    started.
  termsOfService: https://www.getoneprofile.ai/terms
  title: API Reference | Oneprofile
  version: '0.0'
servers:
  - url: https://api.getoneprofile.ai
security: []
tags:
  - description: >-
      The docked AI Assistant: its general chat about the workspace and the
      product, streamed as Server-Sent Events, and the one list of a person's
      threads across every assistant, with pin, rename, delete and the
      search-to-table link, and the read of a web page a person links.
    name: assistant
  - description: >-
      The messages a person keeps to send the assistant again: the ones the
      workspace saved and the ones that ship with the product, with save,
      rename, edit and delete.
    name: assistant-prompt
  - description: >-
      Granted workspace actions: what the AI Assistant proposed or applied in a
      conversation, the approve and dismiss decisions on each card, the
      workspace's spend threshold and default grants, and the eight verbs.
    name: workspace-actions
  - description: >-
      The Getting started checklist: a workspace's progress through the six
      steps from its first people search to its first launched sequence.
    name: onboarding
  - description: Senders, connected mailboxes, tags, and the Google connect flow.
    name: senders
  - description: The workspace do-not-contact list, enforced before every send.
    name: suppression
  - description: >-
      The workspace's recontact rule: how long before anyone hears from us
      again.
    name: contact_cooldown
  - description: 'Sequence authoring: the graph, the table-backed audience, previews.'
    name: sequences
  - description: >-
      The outbound agent behind a sequence: the voice it writes in, its
      per-message prompts, what it wrote and what people told it.
    name: outbound-agents
  - description: >-
      The LinkedIn channel: connecting an account to a sender, its safety limits
      and history, and the protocol the browser extension speaks.
    name: linkedin
  - description: >-
      The approval queue: everything waiting on a person across every sender and
      channel, and the workspace's manual or automatic modes per channel.
    name: outreach
  - description: 'The unified outreach inbox: threads, replies, labels, events.'
    name: inbox
  - description: 'The AI reply layer: workspace settings, drafts, and approval.'
    name: inbox-ai
  - description: Notification rules, per-user preferences, and the Slack connection.
    name: notifications
  - description: Endpoints for seeing all available integration types.
    name: integration-types
  - description: Endpoints for listing, checking and deleting integrations.
    name: integrations
  - description: >-
      Create, preview and update an integration of any type: the body's
      integration_type picks the config and credentials it takes.
    name: integration-specific
  - description: Endpoints for the generic OAuth install/claim app-listings engine.
    name: app-listings
  - description: Endpoints for creating and managing API keys.
    name: apikey
  - description: >-
      AI apps connected to the workspace: Claude, ChatGPT, Claude Code or any
      other MCP client a person signed in to Oneprofile's MCP server with.
    name: ai_apps
  - description: Endpoints for managing billing and subscription information.
    name: billing
  - description: >-
      Accounts: every company the workspace's tables name, with the people at
      it, its key facts, its tables, its org chart and what went to its people;
      the tables that feed it (Sources) and the merges a person made.
    name: accounts
  - description: Endpoints for creating and managing tables.
    name: tables
  - description: Endpoints for table columns, formula previews, and on-demand column runs.
    name: table-columns
  - description: Endpoints for table rows and manual cell edits.
    name: table-rows
  - description: Endpoints for observing and cancelling table recompute runs.
    name: table-runs
  - description: >-
      Endpoints for org-shared per-column display preferences: hidden, pinned,
      width, and color tint.
    name: table-ui-prefs
  - description: >-
      Endpoints for the org-shared names given to the column tint palette: what
      this organization calls each color. Org-level, not per-table.
    name: table-column-color-labels
  - description: >-
      Endpoints for the enrichment action catalog, model list, presets, draft
      generation, and saved agents.
    name: table-enrichments
  - description: >-
      Endpoints for an agent's Preview: example rows run one at a time, and a
      Looks good on each. Needs work lives under agent-learnings.
    name: agent-training
  - description: >-
      An agent's learnings, the one-line rules it follows on every output, and
      the thumbs down that teaches them: give one with what was wrong, list the
      ones on a subject, Undo one, and price the redo it would run.
    name: agent-learnings
  - description: >-
      The durable audit trail of a table's enrichment actions: configured,
      edited, run, cancelled, and settled cost.
    name: table-enrichment-audit-logs
  - description: Endpoints for saving and applying column templates.
    name: table-templates
  - description: Server-sent change feed for a table's grid.
    name: table-events
  - description: 'Endpoints for org-shared saved table views: sort, filters, hidden columns.'
    name: table-views
  - description: >-
      Endpoints for PER-USER table preferences: favorites and recently opened.
      Unlike the rest of the table surface these are personal, so two members of
      one organization legitimately see different answers.
    name: table-user-prefs
  - description: >-
      Endpoints for building a table from an uploaded CSV: upload and preview
      the inferred columns, commit the reviewed mapping, then poll the row load.
    name: table-imports
  - description: Endpoint for downloading a table's rows as CSV.
    name: table-export
  - description: >-
      Endpoints for the integration a table imports from: attach and preview it,
      promote imported fields into columns, and run the import on demand.
    name: table-sources
  - description: >-
      Endpoints for the webhook URL an app or a tool of your own sends records
      to: what can send them, make the URL, show it again, replace it, revoke
      it, save the app's secrets, resume a paused feed, and read and retry the
      deliveries that did not fit.
    name: table-webhooks
  - description: >-
      Endpoints for a table's recurring import cadence: set it, pause it, and
      read the next fire times.
    name: table-schedules
  - description: >-
      Endpoints for pushing a table's rows out to a connected integration: list
      writable destinations, derive their write capabilities, and map export
      columns.
    name: table-writeback
  - description: >-
      Endpoints backing a lookup column's setup: the connections whose records a
      column could read, and the identity fields one record type can be looked
      up by.
    name: table-integration-lookup
  - description: >-
      Endpoints for sourcing leads from the lead database: count and preview
      matches, land them in a table, and keep saved searches. Alongside people
      and company searches, leads can be sourced from buying signals (what a
      company or person just did), with a catalog endpoint behind the picker
      that builds them.
    name: find-leads
  - description: >-
      Endpoints for discovering a domain's subdomains from public certificate
      logs and landing the results in a table.
    name: find-subdomains
  - description: Endpoints for the credit balance meter and usage reporting.
    name: credits
  - description: >-
      Endpoints for the workspace referral program: the shareable link, the
      friends who joined through it, and claiming a code after signup.
    name: referral
  - description: >-
      Endpoints for the affiliate program's own dashboard: enrolling and
      claiming a code, the summary, stats and activity feed, the commission
      ledger, and identity verification and payouts.
    name: affiliate
  - description: >-
      Endpoints for recording where a new workspace came from: the marketing
      page or campaign its signup link carried, sent once after signup.
    name: attribution
  - description: >-
      Endpoints for the design partner program's customer surface: whether this
      workspace is a design partner, the badges its feedback has earned, and
      sending and reading that feedback.
    name: design-partner
  - description: >-
      Endpoints for the org-level AI business context (company description,
      ideal customer profile, buyer personas, interest signals and social
      proof), plus domain-based generation and the reference documents whose
      summaries ride alongside those fields.
    name: ai-context
  - description: >-
      Endpoints for the signed-in user's Google Drive connection: starting and
      finishing the OAuth grant, checking or dropping it, and minting the
      short-lived token the Google Picker needs.
    name: google-drive
paths:
  /ai-context/runs/{job_id}/revert/:
    post:
      tags:
        - ai-context
      summary: Keep the business context as it was before a run
      description: >-
        The review's "Keep everything as it was" (run 23): put back every
        section and choice a website run replaced, who last wrote each, and the
        website it was last generated from, exactly as they stood, so nothing
        records the run. Refused (422, `nothing_to_keep`) when the run replaced
        nothing or something was written since; 404 when the run is not this
        workspace's. Only a workspace admin can, never with an API key. With
        `dry_run` it answers the business context as it would be put back, and
        puts nothing back.
      operationId: revert_ai_context_run
      parameters:
        - in: path
          name: job_id
          required: true
          schema:
            format: uuid
            title: Job Id
            type: string
        - description: Answer the context as it would be put back, and change nothing.
          in: query
          name: dry_run
          required: false
          schema:
            default: false
            description: Answer the context as it would be put back, and change nothing.
            title: Dry Run
            type: boolean
      responses:
        '200':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/AiContextReadSchema'
          description: Successful Response
        '401':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/UnauthorizedResponse'
          description: Unauthorized
        '403':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ForbiddenResponse'
          description: >-
            Only a workspace admin can change the business context, and never
            with an API key.
        '404':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/NotFoundResponse'
          description: Run not found
        '409':
          description: Someone else kept changing the business context while it was read.
        '422':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/UnprocessableEntityResponse'
          description: The run replaced nothing, or something was written since.
        '500':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ServerErrorResponse'
          description: Internal server error.
        '502':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ServerErrorResponse'
          description: Bad gateway error.
        '503':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ServerErrorResponse'
          description: Service unavailable.
      security:
        - APIKeyHeader: []
        - HTTPBearer: []
components:
  schemas:
    AiContextReadSchema:
      description: The org's business context, plus its latest generation job for resume.
      properties:
        company_description:
          anyOf:
            - type: string
            - type: 'null'
          title: Company Description
        company_type:
          anyOf:
            - $ref: '#/components/schemas/CompanyType'
            - type: 'null'
          description: >-
            How the company makes money. Descriptive context shown to the AI
            Assistant and MCP clients; no writer reads it yet.
        company_type_choices:
          description: Every `company_type` value, in the order a picker lists them.
          items:
            $ref: '#/components/schemas/AiContextChoiceSchema'
          title: Company Type Choices
          type: array
        company_type_label:
          anyOf:
            - type: string
            - type: 'null'
          description: '`company_type` as a page shows it.'
          title: Company Type Label
        created_at:
          format: date-time
          title: Created At
          type: string
        field_changes:
          additionalProperties:
            $ref: '#/components/schemas/AiContextFieldChangeSchema'
          description: >-
            Who last wrote each section and choice, by its field name, as each
            section's Last changed by line shows it. A section nobody has
            written since this was kept is absent. Only a workspace admin can
            change the business context.
          title: Field Changes
          type: object
        first_run_available:
          description: >-
            Whether `POST /ai-context/runs/` with no domain would start a first
            run now: the signed-in user created the workspace with a company
            email address, no field has text, and no run has been made. Ask for
            that run only when this is true; otherwise it is refused (422,
            `domain_required`). Always false for an API key.
          title: First Run Available
          type: boolean
        id:
          format: uuid
          title: Id
          type: string
        ideal_buyer_personas:
          anyOf:
            - type: string
            - type: 'null'
          title: Ideal Buyer Personas
        ideal_customer_profile:
          anyOf:
            - type: string
            - type: 'null'
          title: Ideal Customer Profile
        interest_signals:
          anyOf:
            - type: string
            - type: 'null'
          title: Interest Signals
        last_generated_at:
          anyOf:
            - format: date-time
              type: string
            - type: 'null'
          title: Last Generated At
        latest_generation_job:
          anyOf:
            - $ref: '#/components/schemas/AiContextGenerationJobReadSchema'
            - type: 'null'
          description: >-
            The org's most recent generation job, if any. Lets a reloaded page
            resume polling a job that is still running.
        max_context_chars:
          description: >-
            How many characters of included reference document summaries one
            prompt reads, oldest document first. Documents past that line report
            `in_prompt_budget: false`.
          title: Max Context Chars
          type: integer
        max_documents:
          description: How many reference documents this workspace may keep.
          title: Max Documents
          type: integer
        max_qa_answer_chars:
          description: The longest a Q&A answer may be.
          title: Max Qa Answer Chars
          type: integer
        max_qa_context_chars:
          description: >-
            How many characters of the Q&A one reply's prompt reads, the newest
            answers first. Answers past that line report `in_prompt: false` on
            GET /ai-context/qa/.
          title: Max Qa Context Chars
          type: integer
        max_qa_entries:
          description: How many questions this workspace's Q&A may hold.
          title: Max Qa Entries
          type: integer
        max_qa_question_chars:
          description: The longest a Q&A question may be.
          title: Max Qa Question Chars
          type: integer
        messages_held_for_never_say:
          default: 0
          description: >-
            On a save that added phrases to Never say: how many messages written
            before and still waiting to go out say one of them, now held in
            Tasks for a person (each needs Approve anyway). 0 on every other
            answer.
          title: Messages Held For Never Say
          type: integer
        never_say:
          description: >-
            Never say: phrases and claims no AI message may use, in the order an
            admin wrote them. Every message the agent drafts is checked against
            them: written once more without the phrase, then held in Tasks for a
            person if it is still there.
          items:
            type: string
          title: Never Say
          type: array
        pilot_offer:
          anyOf:
            - type: string
            - type: 'null'
          description: >-
            What the company gives a new customer free to start, such as a free
            trial, plan or pilot, in a line. Every generation reads it off the
            company's own site and leaves it null where the site offers nothing
            free. The Introduce your company sequence template offers it, and
            asks for a short call while it is null.
          title: Pilot Offer
        previous_company:
          anyOf:
            - $ref: '#/components/schemas/AiContextPreviousCompanySchema'
            - type: 'null'
          description: >-
            The company a run for another website replaced, kept for 30 days so
            a workspace admin can put it back with `POST
            /ai-context/previous-company/restore/`; null when none was replaced
            or the 30 days have passed.
        run_review:
          anyOf:
            - $ref: '#/components/schemas/AiContextRunReviewSchema'
            - type: 'null'
          description: >-
            The latest website run's review while it is still open: what the run
            replaced, so a page reloaded mid review shows it again and Keep
            everything as it was still works. Null once it is put back, applied
            (a save with `settles_run`), or when the run replaced nothing.
        sells_to:
          anyOf:
            - $ref: '#/components/schemas/SellsTo'
            - type: 'null'
          description: >-
            Who buys from the company. Descriptive context shown to the AI
            Assistant and MCP clients; no writer reads it yet.
        sells_to_choices:
          description: Every `sells_to` value, in the order a picker lists them.
          items:
            $ref: '#/components/schemas/AiContextChoiceSchema'
          title: Sells To Choices
          type: array
        sells_to_label:
          anyOf:
            - type: string
            - type: 'null'
          description: '`sells_to` as a page shows it.'
          title: Sells To Label
        social_proof:
          anyOf:
            - type: string
            - type: 'null'
          title: Social Proof
        source_domain:
          anyOf:
            - type: string
            - type: 'null'
          description: >-
            The domain last used to generate these fields; null until a
            generation succeeds.
          title: Source Domain
        source_url:
          anyOf:
            - type: string
            - type: 'null'
          description: >-
            The page the last generation's company description came from, one of
            the pages it read; null when it named none. Read-only.
          title: Source Url
        updated_at:
          format: date-time
          title: Updated At
          type: string
        voice:
          anyOf:
            - type: string
            - type: 'null'
          description: >-
            How the company words things: spelling, formality, what it calls its
            product and its buyers, jargon it avoids. The outbound agent matches
            it in every message.
          title: Voice
      required:
        - id
        - company_description
        - ideal_customer_profile
        - ideal_buyer_personas
        - interest_signals
        - social_proof
        - voice
        - company_type
        - company_type_label
        - sells_to
        - sells_to_label
        - company_type_choices
        - sells_to_choices
        - source_url
        - source_domain
        - last_generated_at
        - latest_generation_job
        - first_run_available
        - max_documents
        - max_context_chars
        - max_qa_entries
        - max_qa_context_chars
        - max_qa_question_chars
        - max_qa_answer_chars
        - field_changes
        - created_at
        - updated_at
      title: AiContextReadSchema
      type: object
    UnauthorizedResponse:
      properties:
        detail:
          description: The detail of why the request is unauthorized.
          title: Detail
          type: string
      required:
        - detail
      title: UnauthorizedResponse
      type: object
    ForbiddenResponse:
      properties:
        detail:
          description: The detail of why the request is forbidden.
          title: Detail
          type: string
      required:
        - detail
      title: ForbiddenResponse
      type: object
    NotFoundResponse:
      properties:
        detail:
          description: The detail of why the resource was not found.
          title: Detail
          type: string
      required:
        - detail
      title: NotFoundResponse
      type: object
    UnprocessableEntityResponse:
      properties:
        detail:
          description: >-
            The detail of the error. This is the error message to show to the
            user. You should also use the issues field to show more detailed
            error messages per field. Use this field for a single liner error
            message.
          title: Detail
          type: string
        issues:
          description: >-
            The issues that caused the error. There can be multiple issues. Each
            issue is a user-facing error message.
          items:
            $ref: '#/components/schemas/UnprocessableEntityIssue'
          title: Issues
          type: array
      required:
        - detail
        - issues
      title: UnprocessableEntityResponse
      type: object
    ServerErrorResponse:
      properties:
        detail:
          description: The detail of why the server returned an error.
          title: Detail
          type: string
      required:
        - detail
      title: ServerErrorResponse
      type: object
    CompanyType:
      description: >-
        How a company makes money: the catalog's ``company_type`` choices, one
        for one.
      enum:
        - b2b_saas
        - b2c_saas
        - agency_services
        - ecommerce_dtc
        - marketplace
        - manufacturing
        - financial_services
        - healthcare
        - education
        - nonprofit
        - government
        - media_publishing
        - real_estate
        - hospitality
        - logistics
        - other
      title: CompanyType
      type: string
    AiContextChoiceSchema:
      description: >-
        One option of a business-context choice field: the stored value and how
        it reads.
      properties:
        label:
          title: Label
          type: string
        value:
          title: Value
          type: string
      required:
        - value
        - label
      title: AiContextChoiceSchema
      type: object
    AiContextFieldChangeSchema:
      description: >-
        Who last wrote one section of the business context, how, and when (run
        20, B1).
      properties:
        at:
          description: When it was written.
          format: date-time
          title: At
          type: string
        by_user_id:
          anyOf:
            - type: string
            - type: 'null'
          description: >-
            The person who wrote it, or who started the website run that wrote
            it; null for an API key.
          title: By User Id
        via:
          $ref: '#/components/schemas/ContextChangeVia'
          description: >-
            How it was written: `person` on the dashboard, `assistant` for the
            AI Assistant or an MCP client working for one, `api` for an API key,
            `run` for a website run.
      required:
        - by_user_id
        - via
        - at
      title: AiContextFieldChangeSchema
      type: object
    AiContextGenerationJobReadSchema:
      description: A generation job's current state. Poll this until `status` is terminal.
      properties:
        created_at:
          format: date-time
          title: Created At
          type: string
        domain:
          description: The domain this job is researching.
          title: Domain
          type: string
        error:
          anyOf:
            - type: string
            - type: 'null'
          description: 'Why generation failed: infra trouble, or too little public content.'
          title: Error
        id:
          format: uuid
          title: Id
          type: string
        status:
          $ref: '#/components/schemas/AiContextGenerationStatus'
        steps:
          description: >-
            What the research did, one step per piece of work once it is done:
            the documents and pages it read, the sections it wrote. Grows while
            the job runs; kept once it finishes.
          items:
            $ref: '#/components/schemas/AiStep'
          maxItems: 40
          title: Steps
          type: array
        updated_at:
          format: date-time
          title: Updated At
          type: string
      required:
        - id
        - domain
        - status
        - error
        - created_at
        - updated_at
      title: AiContextGenerationJobReadSchema
      type: object
    AiContextPreviousCompanySchema:
      description: >-
        The company a run for another website replaced, which an admin can put
        back (run 22).
      properties:
        domain:
          anyOf:
            - type: string
            - type: 'null'
          description: The website it had been written from; null when it named none.
          title: Domain
        replaced_at:
          description: When a run for another website replaced it.
          format: date-time
          title: Replaced At
          type: string
        replaced_by_user_id:
          anyOf:
            - type: string
            - type: 'null'
          description: Who chose to rewrite the business context; null for nobody nameable.
          title: Replaced By User Id
        restorable_until:
          description: >-
            Until when `POST /ai-context/previous-company/restore/` puts it
            back: 30 days after it was replaced.
          format: date-time
          title: Restorable Until
          type: string
      required:
        - domain
        - replaced_at
        - replaced_by_user_id
        - restorable_until
      title: AiContextPreviousCompanySchema
      type: object
    AiContextRunReviewSchema:
      description: >-
        The open review of the latest website run: what it replaced (run 23
        walk).
      properties:
        before:
          additionalProperties:
            anyOf:
              - type: string
              - type: 'null'
          description: >-
            Every section and choice as it stood before the run, by its field
            name (a choice as its value); null for an empty one. What the
            review's Keep everything as it was puts back, with `POST
            /ai-context/runs/{job_id}/revert/`.
          title: Before
          type: object
        domain:
          anyOf:
            - type: string
            - type: 'null'
          description: The website the run read.
          title: Domain
        run_id:
          description: The website run the review is of.
          format: uuid
          title: Run Id
          type: string
      required:
        - run_id
        - domain
        - before
      title: AiContextRunReviewSchema
      type: object
    SellsTo:
      description: >-
        Who a company's buyer is: the catalog's ``sells_to`` choices, one for
        one.
      enum:
        - businesses
        - consumers
        - both
      title: SellsTo
      type: string
    UnprocessableEntityIssue:
      properties:
        input:
          anyOf:
            - type: string
            - type: integer
            - type: number
            - type: boolean
            - items: {}
              type: array
            - additionalProperties: true
              type: object
          description: The user's input that caused the error.
          title: Input
        loc:
          description: >-
            The location of the error. Always contains 1 or 2 elements. The
            first element is the type of location (e.g. 'body', 'query', 'path',
            'header'). The second element is the name of the field that caused
            the error. If the error is not related to a specific field, the
            second element is not present.
          items:
            type: string
          title: Loc
          type: array
        msg:
          description: The message of the error. The error message to show to the user.
          title: Msg
          type: string
        type:
          description: >-
            The type of the error. Useful for frontend code to handle different
            types of errors.
          title: Type
          type: string
      required:
        - loc
        - msg
        - type
        - input
      title: UnprocessableEntityIssue
      type: object
    ContextChangeVia:
      description: >-
        How a business context section was last written (run 20, B1).


        A person on the dashboard, an AI assistant working for one (the
        in-product Assistant

        or an MCP client), an API key with nobody behind it, or a website run a
        person

        started.
      enum:
        - person
        - assistant
        - api
        - run
      title: ContextChangeVia
      type: string
    AiContextGenerationStatus:
      description: >-
        Where a context-generation job has got to.


        Jobs are stored ``PENDING``: committed, with the workflow that will work
        on

        them not yet started, which a crash between the two can leave for ever.
        The

        research's first step claims the job (``RUNNING``), and the deadline
        sweep

        fails one nothing ever claimed. A reader never sees ``PENDING``: to
        everyone

        outside the repository a job waiting for its workflow is already
        running.

        The two terminal states are absorbing: a job never leaves them.
      enum:
        - pending
        - running
        - succeeded
        - failed
      title: AiContextGenerationStatus
      type: string
    AiStep:
      additionalProperties: false
      description: >-
        One thing an AI turn did, as the wire spells it.


        Field-for-field identical to
        ``table_live_updates.TableCellActivityStepSchema``

        ON PURPOSE, and the duplication is the design. That schema sits in the
        table

        stratum's kernel, which the lead search, inbox and sequence surfaces
        have no

        business importing; this one sits under every surface equally. Because
        the

        two agree exactly, the frontend's ``TimelineStep`` renders both with no

        conversion and no second component, which is the property worth
        protecting.

        ``test_ai_step_mirrors_the_cell_activity_step`` pins them together.


        Plain strings rather than enums, for the same reason the cell schema
        uses

        them: the vocabulary is open, clients must tolerate tokens they have not

        learned yet, and a new action should never be able to break a running

        dashboard.
      properties:
        action:
          description: >-
            What kind of move this was, e.g. `read_table`, `plan`,
            `write_column`.
          title: Action
          type: string
        detail:
          default: ''
          description: >-
            The step's input: the instruction, the column it read, the query it
            ran.
          title: Detail
          type: string
        duration_ms:
          anyOf:
            - type: integer
            - type: 'null'
          description: Wall clock for the work this step describes, never an estimate.
          title: Duration Ms
        observation:
          default: ''
          description: >-
            One line on what came back. The half that makes a step worth
            reading.
          maxLength: 500
          title: Observation
          type: string
        outcome:
          default: completed
          description: >-
            `completed`, `failed`, `refused` or `stopped`. Clients must tolerate
            new tokens.
          title: Outcome
          type: string
        thought:
          anyOf:
            - type: string
            - type: 'null'
          description: >-
            The model's stated reasoning for choosing this step. Set by the
            agent loop; the assistant surfaces leave it null, and the renderer
            simply omits the rung.
          title: Thought
      required:
        - action
      title: AiStep
      type: object
  securitySchemes:
    APIKeyHeader:
      in: header
      name: X-API-Key
      type: apiKey
    HTTPBearer:
      scheme: bearer
      type: http

````

This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.