Trigger an on-demand self-tuning optimize
curl --request POST \
--url https://{host}/api/contexts/{slug}/optimize \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"eval_pass_rate_threshold": 123,
"retrieval_p90_latency_ms": 123,
"optimize_timeout_seconds": 123,
"max_iterations": 123,
"max_tool_turns": 123,
"models": [
"<string>"
],
"candidate_queries": [
{
"ask": "<string>",
"answer": "<string>",
"fallback_to_chunks": true,
"latency_ms": 123
}
],
"pinecone_api_key": "<string>"
}
'import requests
url = "https://{host}/api/contexts/{slug}/optimize"
payload = {
"eval_pass_rate_threshold": 123,
"retrieval_p90_latency_ms": 123,
"optimize_timeout_seconds": 123,
"max_iterations": 123,
"max_tool_turns": 123,
"models": ["<string>"],
"candidate_queries": [
{
"ask": "<string>",
"answer": "<string>",
"fallback_to_chunks": True,
"latency_ms": 123
}
],
"pinecone_api_key": "<string>"
}
headers = {
"Authorization": "Bearer <token>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
body: JSON.stringify({
eval_pass_rate_threshold: 123,
retrieval_p90_latency_ms: 123,
optimize_timeout_seconds: 123,
max_iterations: 123,
max_tool_turns: 123,
models: ['<string>'],
candidate_queries: [
{ask: '<string>', answer: '<string>', fallback_to_chunks: true, latency_ms: 123}
],
pinecone_api_key: '<string>'
})
};
fetch('https://{host}/api/contexts/{slug}/optimize', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));<?php
$curl = curl_init();
curl_setopt_array($curl, [
CURLOPT_URL => "https://{host}/api/contexts/{slug}/optimize",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "POST",
CURLOPT_POSTFIELDS => json_encode([
'eval_pass_rate_threshold' => 123,
'retrieval_p90_latency_ms' => 123,
'optimize_timeout_seconds' => 123,
'max_iterations' => 123,
'max_tool_turns' => 123,
'models' => [
'<string>'
],
'candidate_queries' => [
[
'ask' => '<string>',
'answer' => '<string>',
'fallback_to_chunks' => true,
'latency_ms' => 123
]
],
'pinecone_api_key' => '<string>'
]),
CURLOPT_HTTPHEADER => [
"Authorization: Bearer <token>",
"Content-Type: application/json"
],
]);
$response = curl_exec($curl);
$err = curl_error($curl);
curl_close($curl);
if ($err) {
echo "cURL Error #:" . $err;
} else {
echo $response;
}package main
import (
"fmt"
"strings"
"net/http"
"io"
)
func main() {
url := "https://{host}/api/contexts/{slug}/optimize"
payload := strings.NewReader("{\n \"eval_pass_rate_threshold\": 123,\n \"retrieval_p90_latency_ms\": 123,\n \"optimize_timeout_seconds\": 123,\n \"max_iterations\": 123,\n \"max_tool_turns\": 123,\n \"models\": [\n \"<string>\"\n ],\n \"candidate_queries\": [\n {\n \"ask\": \"<string>\",\n \"answer\": \"<string>\",\n \"fallback_to_chunks\": true,\n \"latency_ms\": 123\n }\n ],\n \"pinecone_api_key\": \"<string>\"\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("Authorization", "Bearer <token>")
req.Header.Add("Content-Type", "application/json")
res, _ := http.DefaultClient.Do(req)
defer res.Body.Close()
body, _ := io.ReadAll(res.Body)
fmt.Println(string(body))
}HttpResponse<String> response = Unirest.post("https://{host}/api/contexts/{slug}/optimize")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"eval_pass_rate_threshold\": 123,\n \"retrieval_p90_latency_ms\": 123,\n \"optimize_timeout_seconds\": 123,\n \"max_iterations\": 123,\n \"max_tool_turns\": 123,\n \"models\": [\n \"<string>\"\n ],\n \"candidate_queries\": [\n {\n \"ask\": \"<string>\",\n \"answer\": \"<string>\",\n \"fallback_to_chunks\": true,\n \"latency_ms\": 123\n }\n ],\n \"pinecone_api_key\": \"<string>\"\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://{host}/api/contexts/{slug}/optimize")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"eval_pass_rate_threshold\": 123,\n \"retrieval_p90_latency_ms\": 123,\n \"optimize_timeout_seconds\": 123,\n \"max_iterations\": 123,\n \"max_tool_turns\": 123,\n \"models\": [\n \"<string>\"\n ],\n \"candidate_queries\": [\n {\n \"ask\": \"<string>\",\n \"answer\": \"<string>\",\n \"fallback_to_chunks\": true,\n \"latency_ms\": 123\n }\n ],\n \"pinecone_api_key\": \"<string>\"\n}"
response = http.request(request)
puts response.read_body{
"task_id": "<string>",
"state": "<string>",
"exploring": true,
"profiling": true,
"importing": true
}{
"message": "<string>",
"code": "<string>"
}Contexts
Trigger an on-demand self-tuning optimize
Tunes the manifest from real query traffic, then chains a forced re-curate. Every field of the required body is optional, so {} is valid — and a no-op without candidate_queries. The context must be curated, and only one optimize runs at a time.
POST
/
contexts
/
{slug}
/
optimize
Trigger an on-demand self-tuning optimize
curl --request POST \
--url https://{host}/api/contexts/{slug}/optimize \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"eval_pass_rate_threshold": 123,
"retrieval_p90_latency_ms": 123,
"optimize_timeout_seconds": 123,
"max_iterations": 123,
"max_tool_turns": 123,
"models": [
"<string>"
],
"candidate_queries": [
{
"ask": "<string>",
"answer": "<string>",
"fallback_to_chunks": true,
"latency_ms": 123
}
],
"pinecone_api_key": "<string>"
}
'import requests
url = "https://{host}/api/contexts/{slug}/optimize"
payload = {
"eval_pass_rate_threshold": 123,
"retrieval_p90_latency_ms": 123,
"optimize_timeout_seconds": 123,
"max_iterations": 123,
"max_tool_turns": 123,
"models": ["<string>"],
"candidate_queries": [
{
"ask": "<string>",
"answer": "<string>",
"fallback_to_chunks": True,
"latency_ms": 123
}
],
"pinecone_api_key": "<string>"
}
headers = {
"Authorization": "Bearer <token>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
body: JSON.stringify({
eval_pass_rate_threshold: 123,
retrieval_p90_latency_ms: 123,
optimize_timeout_seconds: 123,
max_iterations: 123,
max_tool_turns: 123,
models: ['<string>'],
candidate_queries: [
{ask: '<string>', answer: '<string>', fallback_to_chunks: true, latency_ms: 123}
],
pinecone_api_key: '<string>'
})
};
fetch('https://{host}/api/contexts/{slug}/optimize', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));<?php
$curl = curl_init();
curl_setopt_array($curl, [
CURLOPT_URL => "https://{host}/api/contexts/{slug}/optimize",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "POST",
CURLOPT_POSTFIELDS => json_encode([
'eval_pass_rate_threshold' => 123,
'retrieval_p90_latency_ms' => 123,
'optimize_timeout_seconds' => 123,
'max_iterations' => 123,
'max_tool_turns' => 123,
'models' => [
'<string>'
],
'candidate_queries' => [
[
'ask' => '<string>',
'answer' => '<string>',
'fallback_to_chunks' => true,
'latency_ms' => 123
]
],
'pinecone_api_key' => '<string>'
]),
CURLOPT_HTTPHEADER => [
"Authorization: Bearer <token>",
"Content-Type: application/json"
],
]);
$response = curl_exec($curl);
$err = curl_error($curl);
curl_close($curl);
if ($err) {
echo "cURL Error #:" . $err;
} else {
echo $response;
}package main
import (
"fmt"
"strings"
"net/http"
"io"
)
func main() {
url := "https://{host}/api/contexts/{slug}/optimize"
payload := strings.NewReader("{\n \"eval_pass_rate_threshold\": 123,\n \"retrieval_p90_latency_ms\": 123,\n \"optimize_timeout_seconds\": 123,\n \"max_iterations\": 123,\n \"max_tool_turns\": 123,\n \"models\": [\n \"<string>\"\n ],\n \"candidate_queries\": [\n {\n \"ask\": \"<string>\",\n \"answer\": \"<string>\",\n \"fallback_to_chunks\": true,\n \"latency_ms\": 123\n }\n ],\n \"pinecone_api_key\": \"<string>\"\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("Authorization", "Bearer <token>")
req.Header.Add("Content-Type", "application/json")
res, _ := http.DefaultClient.Do(req)
defer res.Body.Close()
body, _ := io.ReadAll(res.Body)
fmt.Println(string(body))
}HttpResponse<String> response = Unirest.post("https://{host}/api/contexts/{slug}/optimize")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"eval_pass_rate_threshold\": 123,\n \"retrieval_p90_latency_ms\": 123,\n \"optimize_timeout_seconds\": 123,\n \"max_iterations\": 123,\n \"max_tool_turns\": 123,\n \"models\": [\n \"<string>\"\n ],\n \"candidate_queries\": [\n {\n \"ask\": \"<string>\",\n \"answer\": \"<string>\",\n \"fallback_to_chunks\": true,\n \"latency_ms\": 123\n }\n ],\n \"pinecone_api_key\": \"<string>\"\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://{host}/api/contexts/{slug}/optimize")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"eval_pass_rate_threshold\": 123,\n \"retrieval_p90_latency_ms\": 123,\n \"optimize_timeout_seconds\": 123,\n \"max_iterations\": 123,\n \"max_tool_turns\": 123,\n \"models\": [\n \"<string>\"\n ],\n \"candidate_queries\": [\n {\n \"ask\": \"<string>\",\n \"answer\": \"<string>\",\n \"fallback_to_chunks\": true,\n \"latency_ms\": 123\n }\n ],\n \"pinecone_api_key\": \"<string>\"\n}"
response = http.request(request)
puts response.read_body{
"task_id": "<string>",
"state": "<string>",
"exploring": true,
"profiling": true,
"importing": true
}{
"message": "<string>",
"code": "<string>"
}Authorizations
bearerAuthapiKey
Session token from POST /auth/login, sent as Authorization: Bearer <token>.
Headers
Date-based contract version, echoed back on the same header. Omit for the default (2026-07); send unstable for the in-development surface. An unrecognized value is rejected with 400 unsupported_api_version.
Path Parameters
Context slug or UUID.
Body
application/json
Optional overrides for the tuning loop. {} is valid and is a no-op.
Pass rate a candidate manifest must clear to count as ready.
The p90 latency bar a candidate must stay under.
Default 7200
Default 20
Default 200
Model-id overrides passed to the optimize runtime
A tier name or catalog id.
Recent query records to tune toward (absent = no-op)
Show child attributes
Show child attributes
Task-token override; normally not needed
Response
Optimize enqueued (state: optimizing)
What every context-workflow trigger returns. The work is asynchronous: poll GET /tasks/{task_id}. The per-workflow booleans duplicate state and appear only where a workflow's contract names one.
The enqueued task. Poll it at GET /tasks/{id}.
The forward-looking status the trigger put the context into.
Duplicates state; present only for explore
Duplicates state; present only for profile
Duplicates state; present only for the import/curate triggers
Was this page helpful?