learning family
Evaluates dream-sourced hypotheses against new deal signals, updating confidence and status
One click hands your coding agent a prompt that registers the substrate, reads this contract, and makes the call. Launch opens the app; the others copy the prompt.
curl -X POST https://one.ie/api/ask/learning:eval \
-H "Authorization: Bearer $ONE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"data": {}}'The key is never in a link. npx -y @oneie/cli login writes it to ~/.config/oneie/key on your machine.
Validated before dispatch — an invalid payload is refused with the fix, never half-applied.
Takes no arguments.
What comes back from the call.
No declared fields.
Every call to learning:eval, counted where it is dispatched — over HTTP or in-process alike. Aggregate only — no actor, no payload, no workspace.
Counting…
Every place in the open source that names learning:eval, and the file that
answers it. Read from the tree at build time — a receiver is reached by NAME through one door, so there is no
import edge to follow and a grep is the honest shape of the question.
Structure, not volume — the count is in Traffic above.
Called from
Answered by
POST /api/ask/learning:eval, after the envelope
validates the payload.
learning family · 2 more
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"type": "object",
"properties": {},
"additionalProperties": {}
} {
"$schema": "https://json-schema.org/draft/2020-12/schema"
}