Generate a structured plan
const url = 'http://localhost:8000/api/agents/plans/';const options = { method: 'POST', headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'}, body: '{"agent":"rehab","subject":{"kind":"client","id":"3fa85f64-5717-4562-b3fc-2c963f66afa6"}}'};
try { const response = await fetch(url, options); const data = await response.json(); console.log(data);} catch (error) { console.error(error);}curl --request POST \ --url http://localhost:8000/api/agents/plans/ \ --header 'Authorization: Bearer <token>' \ --header 'Content-Type: application/json' \ --data '{ "agent": "rehab", "subject": { "kind": "client", "id": "3fa85f64-5717-4562-b3fc-2c963f66afa6" } }'Generate — or regenerate — the structured plan for one (agent, subject).
Returns 201 with the plan: ordered steps, each carrying a title, a rationale citing one of the subject’s measurements, and a prescription (the concrete thing the coach runs), plus the plan’s own title, summary and recheck_metric.
Not a stream: the caller needs a validated step list, so this is a single JSON-mode completion. Generated from the subject’s measurements, NOT from the conversation, so the same subject yields a comparable plan regardless of what was discussed.
Regenerating replaces the machine-written steps and keeps the ones the coach edited (step.edited), so correcting a step is never silently undone. One plan per (conversation, subject, lang) — regardless of persona, so regenerating after switching persona updates the same plan (and re-attributes it to whoever wrote it) rather than piling up versions.
With no model configured, a deterministic plan is built from the subject’s out-of-range measurements (mode: "stub"), so the shape is identical and nothing is invented.
Authorizations
Section titled “Authorizations”Parameters
Section titled “Parameters”Query Parameters
Section titled “Query Parameters”Plan language (en / ru / es). Defaults to en.
Request Bodyrequired
Section titled “Request Bodyrequired”Body of POST /api/agents/plans/ — which agent, about which subject, in
which conversation.
The STEPS still come from the subject’s measurements rather than the chat, so the same subject yields a comparable plan — but the plan is filed against the conversation, so a new thread starts with an empty panel instead of the last thread’s plan.
object
What the conversation is scoped to: the caller’s whole team, or one
athlete on it. id is the Client id and is required only for
kind="client" — a team subject is always the caller’s active team, never
an id from the body (that would be a tenancy hole).
object
team- teamclient- client
Examples
Plan for one athlete
{ "agent": "rehab", "subject": { "kind": "client", "id": "3fa85f64-5717-4562-b3fc-2c963f66afa6" }}Body of POST /api/agents/plans/ — which agent, about which subject, in
which conversation.
The STEPS still come from the subject’s measurements rather than the chat, so the same subject yields a comparable plan — but the plan is filed against the conversation, so a new thread starts with an empty panel instead of the last thread’s plan.
object
What the conversation is scoped to: the caller’s whole team, or one
athlete on it. id is the Client id and is required only for
kind="client" — a team subject is always the caller’s active team, never
an id from the body (that would be a tenancy hole).
object
team- teamclient- client
Body of POST /api/agents/plans/ — which agent, about which subject, in
which conversation.
The STEPS still come from the subject’s measurements rather than the chat, so the same subject yields a comparable plan — but the plan is filed against the conversation, so a new thread starts with an empty panel instead of the last thread’s plan.
object
What the conversation is scoped to: the caller’s whole team, or one
athlete on it. id is the Client id and is required only for
kind="client" — a team subject is always the caller’s active team, never
an id from the body (that would be a tenancy hole).
object
team- teamclient- client
Responses
Section titled “Responses”Read shape of a plan — the ordered steps plus the framing the agent
produced. is_edited tells the UI a regenerate would preserve coach work.
object
One step. edited is read-only — the service sets it from a text change
(ticking done deliberately does not count as authorship).
object
Example
{ "subject_kind": "team", "lang": "en"}object
Human-readable message, or a stable machine code for the cases a client branches on. The standard envelope for 400 (validation — a field-keyed object may appear instead), 401 (missing / invalid credentials), 403 (authenticated but not permitted), and 404 (absent — cross-team records are collapsed to 404 so the API never leaks the existence of another team’s data).
Examplegenerated
{ "detail": "example"}object
Human-readable message, or a stable machine code for the cases a client branches on. The standard envelope for 400 (validation — a field-keyed object may appear instead), 401 (missing / invalid credentials), 403 (authenticated but not permitted), and 404 (absent — cross-team records are collapsed to 404 so the API never leaks the existence of another team’s data).
Examplegenerated
{ "detail": "example"}The caller’s tier does not include the coaching agents.
object
One of five canonical strings. The front-end paywall switches copy + CTA on this value (exact string equality — do not localise). quota_exhausted / seat_limit_reached / client_limit_reached / feature_not_in_plan lead to an upgrade CTA; subscription_suspended leads to a Billing Portal CTA so the buyer can update their payment method.
quota_exhausted- Session quota for the period reached 0subscription_suspended- Stripe dunning in flight (past_due / unpaid)seat_limit_reached- Adding another team member would exceed plan.max_seatsclient_limit_reached- Adding another Client would exceed plan.max_client_profilesfeature_not_in_plan- The tier does not include this whole feature surface
ISO-8601 UTC timestamp the team’s current period ends. Null when the team has no live subscription (legacy un-migrated row). On Free + paid this is the renewal moment; quota refreshes to exactly plan.session_quota (NOT additive — leftover sessions don’t roll over).
The active plan’s role string (free, starter, professional, organization, strategic). Same value as current_role — kept as two separate fields for forward-compatibility with a future named-plan split where current_plan could carry an SKU and current_role the tier label.
The active plan’s role string. See current_plan.
Which feature surface is locked. Present ONLY on feature_not_in_plan, so one modal can name what’s gated without a detail string per feature (#773). The only value today is agents (aikynetix/agents/services.py::AGENTS_FEATURE).
Examples
Free team opens an agent conversation
{ "detail": "feature_not_in_plan", "reset_at": null, "current_plan": "free", "current_role": "free", "feature": "agents"}object
Human-readable message, or a stable machine code for the cases a client branches on. The standard envelope for 400 (validation — a field-keyed object may appear instead), 401 (missing / invalid credentials), 403 (authenticated but not permitted), and 404 (absent — cross-team records are collapsed to 404 so the API never leaks the existence of another team’s data).
Examplegenerated
{ "detail": "example"}object
Human-readable message, or a stable machine code for the cases a client branches on. The standard envelope for 400 (validation — a field-keyed object may appear instead), 401 (missing / invalid credentials), 403 (authenticated but not permitted), and 404 (absent — cross-team records are collapsed to 404 so the API never leaks the existence of another team’s data).
Examplegenerated
{ "detail": "example"}object
429 — rate limit exceeded. Honour the Retry-After response header (seconds to wait) before retrying; it is sent on every 429.
Examplegenerated
{ "detail": "example"}