Skyvern: Get run timeline

Skyvern runs.getRunTimeline: arguments, response, policy and SDK examples.

Operation skyvern.get_run_timeline_v1_runs_run_id_timeline_get

Provider route: GET /v1/runs/{run_id}/timeline. Alter supplies the connection’s credentials and routing.

Call through Alter

Install @alter-ai/sdk @alter-ai/skyvern with npm, or alter-sdk-skyvern with pip. Supply your connected customer’s grant ID and the arguments described below.

import { App } from "@alter-ai/sdk";
import { SkyvernIntegration } from "@alter-ai/skyvern";

async function execute(input: Parameters<SkyvernIntegration["runs"]["getRunTimeline"]>[0]) {
  const app = new App({ apiKey: process.env.ALTER_API_KEY! });
  try {
    const provider = new SkyvernIntegration(app, { grantId: process.env.PROVIDER_GRANT_ID! });
    const call = await provider.runs.getRunTimeline(input);
    const result = await call.wait();
    return result.bodyJson();
  } finally {
    await app.close();
  }
}

import os
from alter_sdk import App
from alter_sdk_skyvern import SkyvernIntegration

async def execute(arguments):
    async with App(api_key=os.environ["ALTER_API_KEY"]) as app:
        provider = SkyvernIntegration(app, {"grant_id": os.environ["PROVIDER_GRANT_ID"]})
        call = await provider.runs.get_run_timeline(arguments)
        result = await call.wait()
        return result.body_json()

Input

Field	Type	Presence	Description and constraints
`$`	object	Root	Additional keys: not allowed
`path`	object	Required within parent	Additional keys: not allowed
`path.run_id`	string	Required within parent	The id of the workflow run or task_v2 run.

Response

Response media type: application/json. The table describes the pinned successful response. Referenced models link to their complete fields.

Field	Type	Presence	Description and constraints
`$`	array	Root
`$[]`	Model	Each item	Expand Get run timeline — response body — item

Referenced models: Get run timeline — response body — item

Schemas

6 more schemas are linked from the tables above, on the schema pages.

Get run timeline — response body — item

Field	Type	Presence	Description and constraints
`$`	object	Root
`attempt`	JSON	Optional
`attempt (anyOf 1)`	integer	Alternative	Default: 1
`attempt (anyOf 2)`	string	Alternative	Pattern: ^-?[0-9]+(?:\.[0-9]+)?(?:[eE][+-]?[0-9]+)?$
`block`	JSON	Optional
`block (anyOf 1)`	Model	Alternative	Expand Get run timeline — response body — item block actions, attachments, attempt number, block type, block workflow run id, body, complete criterion, continue on failure, created at, current index, current value, data extraction goal, data schema, description, downloaded file count, duration, engine, error codes, executed branch expression, executed branch id, executed branch next block, executed branch result, failure reason, final url, finish reason, include action history in verification, include extracted text, instructions, label, loop values, modified at, navigation goal, navigation payload, negative descriptor, organization id, output, parent workflow run block id, positive descriptor, prompt, recipients, script run, status, subject, task id, terminate criterion, url, workflow run block id, workflow run id
`block (anyOf 2)`	null	Alternative
`children`	array	Optional	Default: []
`children[]`	Model	Each item	Expand Get run timeline — response body — item
`created_at`	string	Required within parent	Format: date-time
`modified_at`	string	Required within parent	Format: date-time
`thought`	JSON	Optional
`thought (anyOf 1)`	Model	Alternative	Expand Get run timeline — response body — item thought answer, cached token count, created at, input token count, last llm model, modified at, observation, organization id, output, output token count, reasoning token count, task id, thought, thought cost, thought id, thought scenario, thought type, user input, workflow id, workflow permanent id, workflow run block id, workflow run id
`thought (anyOf 2)`	null	Alternative
`type`	string	Required within parent	Known values: thought, block

Referenced models: Get run timeline — response body — item thought answer, cached token count, created at, input token count, last llm model, modified at, observation, organization id, output, output token count, reasoning token count, task id, thought, thought cost, thought id, thought scenario, thought type, user input, workflow id, workflow permanent id, workflow run block id, workflow run id, Get run timeline — response body — item block actions, attachments, attempt number, block type, block workflow run id, body, complete criterion, continue on failure, created at, current index, current value, data extraction goal, data schema, description, downloaded file count, duration, engine, error codes, executed branch expression, executed branch id, executed branch next block, executed branch result, failure reason, final url, finish reason, include action history in verification, include extracted text, instructions, label, loop values, modified at, navigation goal, navigation payload, negative descriptor, organization id, output, parent workflow run block id, positive descriptor, prompt, recipients, script run, status, subject, task id, terminate criterion, url, workflow run block id, workflow run id, Get run timeline — response body — item

Get run timeline — response body — item thought answer, cached token count, created at, input token count, last llm model, modified at, observation, organization id, output, output token count, reasoning token count, task id, thought, thought cost, thought id, thought scenario, thought type, user input, workflow id, workflow permanent id, workflow run block id, workflow run id

Field	Type	Presence	Description and constraints
`$`	object	Root
`answer`	JSON	Optional
`answer (anyOf 1)`	string	Alternative
`answer (anyOf 2)`	null	Alternative
`cached_token_count`	JSON	Optional
`cached_token_count (anyOf 1)`	JSON	Alternative
`cached_token_count (anyOf 1) (anyOf 1)`	integer	Alternative
`cached_token_count (anyOf 1) (anyOf 2)`	string	Alternative	Pattern: ^-?[0-9]+(?:\.[0-9]+)?(?:[eE][+-]?[0-9]+)?$
`cached_token_count (anyOf 2)`	null	Alternative
`created_at`	string	Required within parent	Format: date-time
`input_token_count`	JSON	Optional
`input_token_count (anyOf 1)`	JSON	Alternative
`input_token_count (anyOf 1) (anyOf 1)`	integer	Alternative
`input_token_count (anyOf 1) (anyOf 2)`	string	Alternative	Pattern: ^-?[0-9]+(?:\.[0-9]+)?(?:[eE][+-]?[0-9]+)?$
`input_token_count (anyOf 2)`	null	Alternative
`last_llm_model`	JSON	Optional
`last_llm_model (anyOf 1)`	string	Alternative
`last_llm_model (anyOf 2)`	null	Alternative
`modified_at`	string	Required within parent	Format: date-time
`observation`	JSON	Optional
`observation (anyOf 1)`	string	Alternative
`observation (anyOf 2)`	null	Alternative
`organization_id`	string	Required within parent
`output`	JSON	Optional
`output (anyOf 1)`	object	Alternative	Additional keys: allowed
`output (anyOf 2)`	null	Alternative
`output_token_count`	JSON	Optional
`output_token_count (anyOf 1)`	JSON	Alternative
`output_token_count (anyOf 1) (anyOf 1)`	integer	Alternative
`output_token_count (anyOf 1) (anyOf 2)`	string	Alternative	Pattern: ^-?[0-9]+(?:\.[0-9]+)?(?:[eE][+-]?[0-9]+)?$
`output_token_count (anyOf 2)`	null	Alternative
`reasoning_token_count`	JSON	Optional
`reasoning_token_count (anyOf 1)`	JSON	Alternative
`reasoning_token_count (anyOf 1) (anyOf 1)`	integer	Alternative
`reasoning_token_count (anyOf 1) (anyOf 2)`	string	Alternative	Pattern: ^-?[0-9]+(?:\.[0-9]+)?(?:[eE][+-]?[0-9]+)?$
`reasoning_token_count (anyOf 2)`	null	Alternative
`task_id`	string	Required within parent
`thought`	JSON	Optional
`thought (anyOf 1)`	string	Alternative
`thought (anyOf 2)`	null	Alternative
`thought_cost`	JSON	Optional
`thought_cost (anyOf 1)`	JSON	Alternative
`thought_cost (anyOf 1) (anyOf 1)`	number	Alternative
`thought_cost (anyOf 1) (anyOf 2)`	string	Alternative	Pattern: ^-?[0-9]+(?:\.[0-9]+)?(?:[eE][+-]?[0-9]+)?$
`thought_cost (anyOf 2)`	null	Alternative
`thought_id`	string	Required within parent
`thought_scenario`	JSON	Optional
`thought_scenario (anyOf 1)`	string	Alternative	Scenario in which a thought was generated. Note: Stored as VARCHAR in the database (not a PostgreSQL ENUM), so new values can be added without database migrations. See observer_thoughts.observer_thought_scenario column. Known values: generate_plan, user_goal_check, failure_describe, summarization, generate_metadata, extract_loop_values, generate_task_in_loop, generate_general_task, termination
`thought_scenario (anyOf 2)`	null	Alternative
`thought_type`	JSON	Optional	Default: plan
`thought_type (anyOf 1)`	string	Alternative	Type of thought recorded during task execution. Note: Stored as VARCHAR in the database (not a PostgreSQL ENUM), so new values can be added without database migrations. See observer_thoughts.observer_thought_type column. Known values: plan, metadata, user_goal_check, internal_plan, failure_describe, termination
`thought_type (anyOf 2)`	null	Alternative
`user_input`	JSON	Optional
`user_input (anyOf 1)`	string	Alternative
`user_input (anyOf 2)`	null	Alternative
`workflow_id`	JSON	Optional
`workflow_id (anyOf 1)`	string	Alternative
`workflow_id (anyOf 2)`	null	Alternative
`workflow_permanent_id`	JSON	Optional
`workflow_permanent_id (anyOf 1)`	string	Alternative
`workflow_permanent_id (anyOf 2)`	null	Alternative
`workflow_run_block_id`	JSON	Optional
`workflow_run_block_id (anyOf 1)`	string	Alternative
`workflow_run_block_id (anyOf 2)`	null	Alternative
`workflow_run_id`	JSON	Optional
`workflow_run_id (anyOf 1)`	string	Alternative
`workflow_run_id (anyOf 2)`	null	Alternative

Get run timeline — response body — item block actions, attachments, attempt number, block type, block workflow run id, body, complete criterion, continue on failure, created at, current index, current value, data extraction goal, data schema, description, downloaded file count, duration, engine, error codes, executed branch expression, executed branch id, executed branch next block, executed branch result, failure reason, final url, finish reason, include action history in verification, include extracted text, instructions, label, loop values, modified at, navigation goal, navigation payload, negative descriptor, organization id, output, parent workflow run block id, positive descriptor, prompt, recipients, script run, status, subject, task id, terminate criterion, url, workflow run block id, workflow run id block type

Field	Type	Presence	Description and constraints
`$`	string	Root	Known values: task, task_v2, for_loop, while_loop, conditional, code, text_prompt, download_to_s3, upload_to_s3, file_upload, send_email, file_url_parser, validation, action, navigation, extraction, login, wait, file_download, goto_url, pdf_parser, http_request, web_search, human_interaction, print_page, workflow_trigger, google_sheets_read, google_sheets_write, powerbi_query, pdf_fill, split_pdf, email_inbox, data_export, terminate, agent_step

Field	Type	Presence	Description and constraints
`$`	object	Root
`ai_fallback_triggered`	boolean	Optional	Default: false
`script_id`	JSON	Optional
`script_id (anyOf 1)`	string	Alternative
`script_id (anyOf 2)`	null	Alternative
`script_revision_id`	JSON	Optional
`script_revision_id (anyOf 1)`	string	Alternative
`script_revision_id (anyOf 2)`	null	Alternative

Policy, approvals and errors

SDK function policy ID: skyvern.get_run_timeline_v1_runs_run_id_timeline_get. Catalog operation: get_run_timeline_v1_runs__run_id__timeline_get. Rules can name either ID; function rules distinguish managed calls and conservatively cover raw calls sharing the route. Existing grant permissions and policy rules apply. wait() returns an immediate result or waits for a required approval; it never approves the request itself. Persist the approval ID to resume after a restart.

Provider errors retain their response; JSON decoding raises ProviderAPIError for provider failures. ManagedOperationError identifies contract/input/retention errors. See error handling and provider-specific behavior. Sensitive input may be refused before approval storage. A decoding error never resubmits a write.

Official provider source

Report an issue with this page