Skip to content

Start the built-in mission agent

POST
/v1/missions/{id}/agent
curl --request POST \
--url https://beta-api.plune.ai/v1/missions/example/agent \
--header 'Content-Type: application/json' \
--cookie plune_session=<plune_session> \
--data '{ "budgetUsd": 2 }'

The project’s own model works the mission in stages — questions to a person (test analysis), a strategy (test planning), case proposals (test design) — through the same tools an MCP agent calls; everything it writes waits in the review queue. A person in a session only: a token is refused (403 session_required), so a leaked token cannot spend the owner’s key. Queued, 202. On a paused run the same call resumes it with the new budget (400 budget_too_low when it is not above what the run spent). 409 price_unknown for a model without a price, ai_not_connected / ai_disabled, mission_done, agent_running; 400 budget_over_cap over the monthly limit; 429 ai_budget_spent once the month is used up. Ten a minute.

id
required
string

The mission’s id

Media type application/json
object
budgetUsd
required

What the run may spend on the project’s key, in USD

number
> 0 <= 1000000
Example
{
"budgetUsd": 2
}

The run, queued

Media type application/json
object
id
required
string
missionId
required
string
state
required

paused: a call would pass the mission budget or the project’s monthly limit; starting it again resumes it

string
Allowed values: queued running paused done failed
stage
required

The stage the run works next: questions (test analysis), strategy (test planning), cases (test design)

string
Allowed values: questions strategy cases done
budgetUsd
required
number
spend
required
object
calls
required
integer
inputTokens
required
integer
outputTokens
required
integer
costUsd
required
number
questionsWaiting
required

Questions of the mission still pending in the review queue

integer
outputs
required
object
questionIds
required
Array<string>
strategyItemId
string
proposed
integer
pauseReason
string
Allowed values: mission_budget monthly_cap
failureKind
string
failure
object
tool
required
string
code
required
string
provider
string
model
string
requestedBy
required
string
createdAt
required
string format: date-time
startedAt
required
string format: date-time
nullable
finishedAt
required
string format: date-time
nullable
Example
{
"id": "0b6f3c2e-7d1a-4f0e-9a51-2c8e4b7d9f10",
"missionId": "6f1c2b3a-0000-4000-8000-000000002188",
"state": "queued",
"stage": "questions",
"budgetUsd": 2,
"spend": {
"calls": 0,
"inputTokens": 0,
"outputTokens": 0,
"costUsd": 0
},
"questionsWaiting": 0,
"outputs": {
"questionIds": []
},
"requestedBy": "6f1c2b3a-0000-4000-8000-0000000000a2",
"createdAt": "2026-11-12T09:00:00.000Z",
"startedAt": null,
"finishedAt": null
}

Invalid JSON or budget; budget_over_cap; budget_too_low

Media type application/json
object
error
required
string
Example generated
{
"error": "example"
}

No / invalid token or session

A token (session_required), or a reader

Media type application/json
object
error
required
string
Example generated
{
"error": "example"
}

No such mission in your project

Media type application/json
object
error
required
string
Example generated
{
"error": "example"
}

price_unknown, ai_not_connected, ai_disabled, mission_done, agent_running

Media type application/json
object
error
required
string
Example generated
{
"error": "example"
}

Rate-limited: the per-route throttle, or the per-minute request limit of the plan an API token counts by (#1442; the body names the plan, #2092). Retry-After carries the seconds until the window rolls over.

Media type application/json
object
error
required
string
Example generated
{
"error": "example"
}
Retry-After
integer

Seconds until the window rolls over

The platform has no AI key (platform_not_configured)

Media type application/json
object
error
required
string
Example generated
{
"error": "example"
}