Parallel · OpenAPI Overlay 1.0.0
API Evangelist conversational phrasing for Parallel Tasks API
13 actions
13 updates
phrasing
extends
openapi/parallel-tasks-api-openapi.yml
Generated by API Evangelist
Written by API Evangelist tooling for Parallel's API. It is a proposal applied on top of the contract, not a document Parallel publishes.
What the actions change
x-apievangelist-phrasing
Targets 13
$.info
$.paths['/v1/tasks/groups'].post
$.paths['/v1/tasks/groups/{taskgroup_id}'].get
$.paths['/v1/tasks/groups/{taskgroup_id}/events'].get
$.paths['/v1/tasks/groups/{taskgroup_id}/runs'].get
$.paths['/v1/tasks/groups/{taskgroup_id}/runs'].post
$.paths['/v1/tasks/groups/{taskgroup_id}/runs/{run_id}'].get
$.paths['/v1/tasks/runs'].post
$.paths['/v1/tasks/runs/{run_id}'].get
$.paths['/v1/tasks/runs/{run_id}/events'].get
$.paths['/v1/tasks/runs/{run_id}/input'].get
$.paths['/v1/tasks/runs/{run_id}/result'].get
$.paths['/v1beta/tasks/runs/{run_id}/events'].get
OpenAPI Overlay
# Generated by API Evangelist (build-phrasing.py). Our phrasing, not observed demand.
overlay: 1.0.0
info:
title: API Evangelist conversational phrasing for Parallel Tasks API
version: 1.0.0
extends: openapi/parallel-tasks-api-openapi.yml
actions:
- target: $.info
update:
x-apievangelist-phrasing:
method: generated
generated: '2026-10-01'
generator: build-phrasing.py
label: Generated by API Evangelist
operations: 12
- target: $.paths['/v1/tasks/groups'].post
update:
x-apievangelist-phrasing:
intent: Create a task group to batch runs
effect: write
questions:
- How do I group many task runs together so I can track them as one batch?
- Can I attach my own metadata to a task group when I create it?
instructions:
- text: Create a new task group.
- text: Create a task group tagged with metadata {metadata}.
slots:
metadata: requestBody.metadata
method: generated
generated: '2026-10-01'
- target: $.paths['/v1/tasks/groups/{taskgroup_id}'].get
update:
x-apievangelist-phrasing:
intent: Get aggregated status of a task group
effect: read
questions:
- How many runs in my task group have finished versus are still running?
- Can I see the overall progress of a batch of task runs at a glance?
instructions:
- text: Show the aggregated status of task group {taskgroup_id}.
slots:
taskgroup_id: path.taskgroup_id
- text: Summarize progress across all runs in task group {taskgroup_id}.
slots:
taskgroup_id: path.taskgroup_id
method: generated
generated: '2026-10-01'
- target: $.paths['/v1/tasks/groups/{taskgroup_id}/events'].get
update:
x-apievangelist-phrasing:
intent: Stream status events for a task group
effect: read
questions:
- Can I get live notifications as runs in a task group complete?
- How long does a task group event stream stay open?
instructions:
- text: Stream status updates and run completions for task group {taskgroup_id}.
slots:
taskgroup_id: path.taskgroup_id
- text: Resume task group {taskgroup_id} events after event {last_event_id}.
slots:
taskgroup_id: path.taskgroup_id
last_event_id: query.last_event_id
method: generated
generated: '2026-10-01'
- target: $.paths['/v1/tasks/groups/{taskgroup_id}/runs'].get
update:
x-apievangelist-phrasing:
intent: Fetch the runs in a task group
effect: read
questions:
- How do I get every run in a task group along with its inputs and outputs?
- Can I fetch only the task group runs with a particular status?
- Is the stream of task group runs resumable if it gets interrupted?
instructions:
- text: Fetch all runs in task group {taskgroup_id} with their outputs.
slots:
taskgroup_id: path.taskgroup_id
- text: List the {status} runs in task group {taskgroup_id}.
slots:
status: query.status
taskgroup_id: path.taskgroup_id
method: generated
generated: '2026-10-01'
- target: $.paths['/v1/tasks/groups/{taskgroup_id}/runs'].post
update:
x-apievangelist-phrasing:
intent: Add a batch of task runs to a group
effect: write
questions:
- How many task runs can I add to a task group in a single request?
- Can I set a default task spec for all the runs I add to a group?
instructions:
- text: 'Add these runs to task group {taskgroup_id}: {inputs}.'
slots:
taskgroup_id: path.taskgroup_id
inputs: requestBody.inputs
- text: Queue {inputs} in task group {taskgroup_id} using default spec {default_task_spec}.
slots:
inputs: requestBody.inputs
taskgroup_id: path.taskgroup_id
default_task_spec: requestBody.default_task_spec
method: generated
generated: '2026-10-01'
- target: $.paths['/v1/tasks/groups/{taskgroup_id}/runs/{run_id}'].get
update:
x-apievangelist-phrasing:
intent: Check one run inside a task group
effect: read
questions:
- Can I look up the status of a single run within a specific task group?
- Where do I check one run's status when I only know its group and run IDs?
instructions:
- text: Check the status of run {run_id} in task group {taskgroup_id}.
slots:
run_id: path.run_id
taskgroup_id: path.taskgroup_id
- text: Look up group {taskgroup_id} member run {run_id}.
slots:
taskgroup_id: path.taskgroup_id
run_id: path.run_id
method: generated
generated: '2026-10-01'
- target: $.paths['/v1/tasks/runs'].post
update:
x-apievangelist-phrasing:
intent: Start a web research task run
effect: write
questions:
- How do I start a single research task with Parallel and get structured output?
- Which processor should a task run use, and can I restrict which domains it searches?
- Can a task run call my own MCP servers or notify a webhook when it's done?
instructions:
- text: Start a task run on the {processor} processor with input {input}.
slots:
processor: requestBody.processor
input: requestBody.input
- text: Run {input} with processor {processor} using task spec {task_spec}.
slots:
input: requestBody.input
processor: requestBody.processor
task_spec: requestBody.task_spec
- text: Launch a {processor} task for {input} and call {webhook} when it completes.
slots:
processor: requestBody.processor
input: requestBody.input
webhook: requestBody.webhook
method: generated
generated: '2026-10-01'
- target: $.paths['/v1/tasks/runs/{run_id}'].get
update:
x-apievangelist-phrasing:
intent: Check a task run's status
effect: read
questions:
- Is my task run still queued or has it finished?
- How can I poll a task run's status without waiting for the result?
instructions:
- text: Check the status of task run {run_id}.
slots:
run_id: path.run_id
- text: Tell me if task run {run_id} is done yet.
slots:
run_id: path.run_id
method: generated
generated: '2026-10-01'
- target: $.paths['/v1/tasks/runs/{run_id}/events'].get
update:
x-apievangelist-phrasing:
intent: Stream progress events for a task run
effect: read
questions:
- Can I watch a task run's progress updates as they happen on the current v1 endpoint?
- Will I get fewer progress events if I didn't enable events when creating the run?
instructions:
- text: Stream progress events for task run {run_id} using the v1 endpoint.
slots:
run_id: path.run_id
- text: Follow task run {run_id} state changes live via v1.
slots:
run_id: path.run_id
method: generated
generated: '2026-10-01'
- target: $.paths['/v1/tasks/runs/{run_id}/input'].get
update:
x-apievangelist-phrasing:
intent: Get the input a task run was given
effect: read
questions:
- What input did I submit for a particular task run?
- Can I retrieve the original prompt or JSON a task run started with?
instructions:
- text: Show the input of task run {run_id}.
slots:
run_id: path.run_id
- text: Get what task run {run_id} was asked to research.
slots:
run_id: path.run_id
method: generated
generated: '2026-10-01'
- target: $.paths['/v1/tasks/runs/{run_id}/result'].get
update:
x-apievangelist-phrasing:
intent: Get the output of a completed task run
effect: read
questions:
- How do I get the final output of a task run once it completes?
- Does fetching a task run's result block until it's finished, and can I set a timeout?
instructions:
- text: Get the result of task run {run_id}.
slots:
run_id: path.run_id
- text: Wait up to {timeout} seconds for task run {run_id} output.
slots:
timeout: query.timeout
run_id: path.run_id
method: generated
generated: '2026-10-01'
- target: $.paths['/v1beta/tasks/runs/{run_id}/events'].get
update:
x-apievangelist-phrasing:
intent: Stream task run events (legacy v1beta)
effect: read
questions:
- Is there still a v1beta endpoint for streaming task run events?
- Can older beta integrations keep streaming task run progress from the beta path?
instructions:
- text: Stream events for task run {run_id} from the v1beta endpoint.
slots:
run_id: path.run_id
- text: Use the legacy beta stream to follow task run {run_id}.
slots:
run_id: path.run_id
method: generated
generated: '2026-10-01'