Skip to main content
POST
/
post-process
Rewrite text with AI post-processing
curl --request POST \
  --url http://127.0.0.1:{port}/post-process \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "text": "<string>",
  "mode_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "preset": "<string>",
  "prompt": "<string>",
  "provider": "<string>",
  "model": "<string>"
}
'
{
  "ok": true,
  "text": "<string>",
  "provider": "<string>",
  "model": "<string>",
  "preset": "<string>",
  "latency_ms": 123,
  "post_processed": true
}

Authorizations

​
Authorization
string
header
required

Token from the discovery file. Required on every endpoint except /health.

Body

application/json
​
text
string
required
​
mode_id
string<uuid>
​
preset
string

hyper | note | email | commit. Mutually exclusive with prompt.

​
prompt
string

Free-form system prompt. Sets preset=custom.

​
provider
string
​
model
string

Response

200 - application/json

Rewritten text or business error envelope

​
ok
boolean
​
text
string
​
provider
string
​
model
string
​
preset
string
​
latency_ms
integer
​
post_processed
boolean

true when an LLM actually ran and produced post-processed text; false when a failure path (bad key, model/network error, offline) returned the raw input unchanged. ok stays true for graceful degradation, so read this to know post-processing happened.