Build walkthroughs from your own code
Everything this app does goes through the SkillSafe App API — plain JSON over HTTPS with optional streaming. Send a unified diff (plus the PR title, description and audience) and get back the presenter-ready walkthrough in the app's tagged plain-text shape, with examples in cURL, Python, JavaScript, Go, Java, Ruby, PHP and C#.
Basics
Base URL: https://api.skillsafe.ai/v1/app-api. Every request sends
Authorization: Bearer <token> and JSON bodies with
Content-Type: application/json. Responses are wrapped in an envelope:
{"data": …} on success, {"error": {"code", "message"}} on
failure. Runs execute the app's agent (model gpt-terra) and are billed in
SkillSafe credits to the calling token, with a worst-case hold up front and the actual cost
settled when the job finishes.
| Status | Meaning |
|---|---|
401 | Missing or expired token — create a new session. |
402 | Not enough credits — top up at skillsafe.ai/account/billing. |
403 | The token isn't allowed to do this. |
404 | Unknown job or record id. |
5xx | Transient platform error — retry with backoff. |
Browsers enforce CORS for this API, so run these examples from a server, script or terminal — not from another website's frontend. The in-browser diff scan on the app's front page is purely local convenience; the API run does its own reading of the diff.
Step 0 — A tiny client
Every step below is one or two HTTP calls, so start with a small helper that adds the auth
header, sends JSON and unwraps the data envelope. The later steps reuse this
helper.
export API="https://api.skillsafe.ai/v1/app-api"
export TOKEN="YOUR_TOKEN" # see step 1
# every call looks like:
# curl -s "$API/…" -H "Authorization: Bearer $TOKEN" [-d '{json}']
# jq is used below to pull fields out of the {"data": …} envelope
import json, requests
API = "https://api.skillsafe.ai/v1/app-api"
TOKEN = "YOUR_TOKEN" # see step 1 - read it from your environment in real code
def api(method, path, body=None, **headers):
res = requests.request(method, API + path, json=body,
headers={"Authorization": f"Bearer {TOKEN}", **headers})
payload = res.json()
if not res.ok:
raise RuntimeError(payload.get("error", {}).get("message", res.reason))
return payload["data"]
// Node 18+ (built-in fetch)
const API = "https://api.skillsafe.ai/v1/app-api";
const TOKEN = "YOUR_TOKEN"; // see step 1 - read it from your environment in real code
async function api(method, path, body, extraHeaders = {}) {
const res = await fetch(API + path, {
method,
headers: { Authorization: `Bearer ${TOKEN}`, "Content-Type": "application/json", ...extraHeaders },
body: body === undefined ? undefined : JSON.stringify(body),
});
const json = await res.json();
if (!res.ok) throw new Error(json.error?.message ?? res.statusText);
return json.data;
}
package main
import (
"bytes"
"encoding/json"
"fmt"
"net/http"
"os"
)
const API = "https://api.skillsafe.ai/v1/app-api"
var token = os.Getenv("SKILLSAFE_TOKEN") // see step 1
func call(method, path string, body, out any) error {
var buf bytes.Buffer
if body != nil {
json.NewEncoder(&buf).Encode(body)
}
req, _ := http.NewRequest(method, API+path, &buf)
req.Header.Set("Authorization", "Bearer "+token)
req.Header.Set("Content-Type", "application/json")
res, err := http.DefaultClient.Do(req)
if err != nil {
return err
}
defer res.Body.Close()
var env struct {
Data json.RawMessage `json:"data"`
Error *struct{ Message string `json:"message"` } `json:"error"`
}
json.NewDecoder(res.Body).Decode(&env)
if res.StatusCode >= 400 {
return fmt.Errorf("api %s %s: %s", method, path, env.Error.Message)
}
if out == nil {
return nil
}
return json.Unmarshal(env.Data, out)
}
// Java 17+, no dependencies. Pair with your JSON library (Jackson, Gson…)
// to read fields out of the returned envelope.
import java.net.URI;
import java.net.http.HttpClient;
import java.net.http.HttpRequest;
import java.net.http.HttpResponse;
public class SkillSafe {
static final String API = "https://api.skillsafe.ai/v1/app-api";
static final String TOKEN = System.getenv("SKILLSAFE_TOKEN"); // see step 1
static final HttpClient HTTP = HttpClient.newHttpClient();
static String api(String method, String path, String jsonBody) throws Exception {
var req = HttpRequest.newBuilder(URI.create(API + path))
.header("Authorization", "Bearer " + TOKEN)
.header("Content-Type", "application/json")
.method(method, jsonBody == null
? HttpRequest.BodyPublishers.noBody()
: HttpRequest.BodyPublishers.ofString(jsonBody))
.build();
var res = HTTP.send(req, HttpResponse.BodyHandlers.ofString());
if (res.statusCode() >= 400) throw new RuntimeException(res.body());
return res.body(); // envelope: {"data": …}
}
}
require "net/http"
require "json"
API = "https://api.skillsafe.ai/v1/app-api"
TOKEN = ENV.fetch("SKILLSAFE_TOKEN") # see step 1
def api(method, path, body = nil)
uri = URI(API + path)
req = Net::HTTP.const_get(method.capitalize).new(uri)
req["Authorization"] = "Bearer #{TOKEN}"
req["Content-Type"] = "application/json"
req.body = body.to_json if body
res = Net::HTTP.start(uri.host, uri.port, use_ssl: true) { |h| h.request(req) }
payload = JSON.parse(res.body)
raise (payload.dig("error", "message") || res.message) unless res.is_a?(Net::HTTPSuccess)
payload["data"]
end
<?php
const API = "https://api.skillsafe.ai/v1/app-api";
$TOKEN = getenv("SKILLSAFE_TOKEN"); // see step 1
function api(string $method, string $path, ?array $body = null): mixed {
global $TOKEN;
$ch = curl_init(API . $path);
curl_setopt_array($ch, [
CURLOPT_CUSTOMREQUEST => $method,
CURLOPT_RETURNTRANSFER => true,
CURLOPT_HTTPHEADER => [
"Authorization: Bearer $TOKEN",
"Content-Type: application/json",
],
CURLOPT_POSTFIELDS => $body === null ? null : json_encode($body),
]);
$payload = json_decode(curl_exec($ch), true);
$status = curl_getinfo($ch, CURLINFO_RESPONSE_CODE);
curl_close($ch);
if ($status >= 400) {
throw new Exception($payload["error"]["message"] ?? "HTTP $status");
}
return $payload["data"];
}
// .NET 8+
using System.Net.Http.Json;
using System.Text.Json;
static class SkillSafe
{
const string Api = "https://api.skillsafe.ai/v1/app-api";
static readonly HttpClient Http = new();
static SkillSafe() =>
Http.DefaultRequestHeaders.Authorization =
new("Bearer", Environment.GetEnvironmentVariable("SKILLSAFE_TOKEN")); // see step 1
public static async Task<JsonElement> ApiAsync(HttpMethod method, string path, object? body = null)
{
var req = new HttpRequestMessage(method, Api + path);
if (body != null) req.Content = JsonContent.Create(body);
var res = await Http.SendAsync(req);
var json = await res.Content.ReadFromJsonAsync<JsonElement>();
if (!res.IsSuccessStatusCode)
throw new Exception(json.GetProperty("error").GetProperty("message").GetString());
return json.GetProperty("data");
}
}
Step 1 — Get a token
For scripted use, the simplest reliable path is your personal token: open the
token page, sign in, and hit
"Copy shell export" — it puts export SKILLSAFE_TOKEN="…" on your
clipboard, which every example below reads. Treat the token like a password — it can
spend your credits. For fully headless scripts, POST /guest (below) mints a
guest token with no browser involved; guests can always call /me and
/estimate, but whether a guest can afford an actual run depends on the app's
daily sponsorship budget, so don't build on it.
curl -s -X POST "$API/guest" \
-H "Content-Type: application/json" \
-d '{"slug":"pr-tour"}' | jq -r '.data.token'
token = api("POST", "/guest", {"slug": "pr-tour"})["token"]
const { token } = await api("POST", "/guest", { slug: "pr-tour" });
var guest struct{ Token string `json:"token"` }
err := call("POST", "/guest", map[string]string{"slug": "pr-tour"}, &guest)
String envelope = api("POST", "/guest", """
{"slug":"pr-tour"}""");
// token is at data.token in the returned JSON
token = api("POST", "/guest", { slug: "pr-tour" })["token"]
$token = api("POST", "/guest", ["slug" => "pr-tour"])["token"];
var guest = await SkillSafe.ApiAsync(HttpMethod.Post, "/guest",
new { slug = "pr-tour" });
var token = guest.GetProperty("token").GetString();
Step 2 — Check who you are and your balance
Returns subject_type ("user" or "guest"),
subject_id and your credits balance. Check this before an
expensive run — the app itself does exactly that before starting one.
curl -s "$API/me" -H "Authorization: Bearer $TOKEN" | jq '.data'
me = api("GET", "/me")
print(me["subject_type"], me["credits"])
const me = await api("GET", "/me");
console.log(me.subject_type, me.credits);
var me struct {
SubjectType string `json:"subject_type"`
Credits int64 `json:"credits"`
}
err := call("GET", "/me", nil, &me)
String envelope = api("GET", "/me", null);
// data.subject_type, data.credits
me = api("GET", "/me")
puts "#{me["subject_type"]}: #{me["credits"]} credits"
$me = api("GET", "/me");
echo "{$me['subject_type']}: {$me['credits']} credits\n";
var me = await SkillSafe.ApiAsync(HttpMethod.Get, "/me");
Console.WriteLine($"{me.GetProperty("subject_type")}: {me.GetProperty("credits")} credits");
Step 3 — Estimate the cost
Send the same input you would send to a run; the response's hold_credits is
the worst-case cost and min_credits the floor. Nothing is charged and no job
is created. The response also reports the resolved model and whether
sponsorship is active.
curl -s -X POST "$API/estimate" \
-H "Authorization: Bearer $TOKEN" -H "Content-Type: application/json" \
-d '{"title":"Add retry to dispatcher","diff":"…the unified diff…","audience":"Teammates"}' | jq '.data'
est = api("POST", "/estimate", {"title": title, "diff": diff, "audience": "Teammates"})
print("worst case:", est["hold_credits"], "credits on", est["model"])
const est = await api("POST", "/estimate", { title, diff, audience: "Teammates" });
console.log("worst case:", est.hold_credits, "credits on", est.model);
var est struct {
HoldCredits int64 `json:"hold_credits"`
Model string `json:"model"`
}
err := call("POST", "/estimate", map[string]string{
"title": title, "diff": diff, "audience": "Teammates",
}, &est)
String envelope = api("POST", "/estimate", """
{"title": %s, "diff": %s, "audience": "Teammates"}
""".formatted(toJsonString(title), toJsonString(diff)));
// worst-case cost is at data.hold_credits
est = api("POST", "/estimate", { title: title, diff: diff, audience: "Teammates" })
puts "worst case: #{est["hold_credits"]} credits on #{est["model"]}"
$est = api("POST", "/estimate", [
"title" => $title,
"diff" => $diff,
"audience" => "Teammates",
]);
echo "worst case: {$est['hold_credits']} credits on {$est['model']}\n";
var est = await SkillSafe.ApiAsync(HttpMethod.Post, "/estimate", new {
title, diff, audience = "Teammates" });
Console.WriteLine($"worst case: {est.GetProperty("hold_credits")} credits");
Step 4 — Build the walkthrough: run it and wait
/run places a credit hold and returns a job_id; poll
/jobs/{job_id} every 1–2 seconds until status is
succeeded or failed. Always send an Idempotency-Key
header so a network retry can't start a second, double-charged run. The input fields are
exactly what the app's form sends:
| Input field | Type | Notes |
|---|---|---|
title | string, optional | The PR title, up to 300 chars. |
description | string, optional | The PR description or commit messages — where the "why" lives. Over 12,000 chars the app drops whole lines from the MIDDLE, keeps the opening and closing lines, and inserts a [description truncated] marker line saying how many lines went. |
diff | string, required in practice | The unified diff (git diff output or the GitHub .diff view). Over 60,000 chars the app drops whole files from the middle on diff --git boundaries, keeps the first and last files intact, and inserts a [diff truncated] marker line naming what was dropped. Do the same, and keep the marker — it is how the agent knows the paste is partial, and it forces COVERAGE below Complete walkthrough. |
notes | string, optional | Presenter context: audience familiarity, what to emphasize, review comments already made. Up to 6,000 chars, middle-clipped the same way past that. |
audience | string, optional | One of "Teammates", "New contributor", "Reviewer in a hurry", "Non-engineer stakeholder". Defaults to Teammates. |
facts | string, optional | A mechanical scan summary of the diff (file/hunk/line counts). The app generates this in the browser; from your own code, omit it — the agent reads the diff itself. |
retry_note | string, optional | Present only on a reformat retry. An authoritative restatement of the output format after a malformed reply; the agent obeys it exactly, does not change its reading of the diff, and never mentions it in the output. Omit it on a first attempt. |
$model | string, optional | Per-run model override (allowlisted models only). |
# input.json: {"title":"…","description":"…","diff":"…","audience":"Teammates"}
JOB_ID=$(curl -s -X POST "$API/run" \
-H "Authorization: Bearer $TOKEN" -H "Content-Type: application/json" \
-H "Idempotency-Key: tour-$(date +%s)" \
-d @input.json | jq -r '.data.job_id')
while :; do
JOB=$(curl -s "$API/jobs/$JOB_ID" -H "Authorization: Bearer $TOKEN")
STATUS=$(echo "$JOB" | jq -r '.data.status')
[ "$STATUS" = "succeeded" ] || [ "$STATUS" = "failed" ] && break
sleep 2
done
# the walkthrough is plain tagged text at data.output.output
echo "$JOB" | jq -r '.data.output.output'
import time
job_id = api("POST", "/run", {
"title": title,
"description": description,
"diff": diff,
"audience": "Teammates",
}, **{"Idempotency-Key": "tour-001"})["job_id"]
while True:
job = api("GET", f"/jobs/{job_id}")
if job["status"] in ("succeeded", "failed"):
break
time.sleep(1.5)
if job["status"] == "failed":
raise RuntimeError(job.get("error", "run failed"))
raw = job["output"]
text = raw["output"] if isinstance(raw, dict) and "output" in raw else raw
print(text) # plain tagged text - COVERAGE:/CHANGE TYPE:/CONFIDENCE:/SUMMARY: + five sections
coverage = text.splitlines()[0].split(":", 1)[1].strip()
const { job_id } = await api("POST", "/run", {
title,
description,
diff,
audience: "Teammates",
}, { "Idempotency-Key": crypto.randomUUID() });
let job;
do {
await new Promise((r) => setTimeout(r, 1500));
job = await api("GET", `/jobs/${job_id}`);
} while (job.status !== "succeeded" && job.status !== "failed");
if (job.status === "failed") throw new Error(job.error ?? "run failed");
const text = job.output?.output ?? job.output; // plain tagged text, not JSON
const coverage = text.split("\n")[0].split(":").slice(1).join(":").trim();
console.log(coverage);
console.log(text);
var started struct{ JobID string `json:"job_id"` }
err := call("POST", "/run", map[string]string{
"title": title, "diff": diff, "audience": "Teammates",
}, &started)
if err != nil {
log.Fatal(err)
}
var job struct {
Status string `json:"status"`
Error string `json:"error"`
Output struct {
Output string `json:"output"`
} `json:"output"`
}
for {
if err := call("GET", "/jobs/"+started.JobID, nil, &job); err != nil {
log.Fatal(err)
}
if job.Status == "succeeded" || job.Status == "failed" {
break
}
time.Sleep(1500 * time.Millisecond)
}
// job.Output.Output is plain tagged text - print it or parse the header lines
fmt.Println(job.Output.Output)
String envelope = api("POST", "/run", """
{"title": %s, "diff": %s, "audience": "Teammates"}
""".formatted(toJsonString(title), toJsonString(diff)));
String jobId = /* data.job_id via your JSON library */;
while (true) {
String job = api("GET", "/jobs/" + jobId, null);
String status = /* data.status */;
if (status.equals("succeeded") || status.equals("failed")) break;
Thread.sleep(1500);
}
// the walkthrough is the plain-text *string* at data.output.output -
// no second JSON parse needed, just read the tagged lines and sections
started = api("POST", "/run", { title: title, diff: diff, audience: "Teammates" })
job = nil
loop do
job = api("GET", "/jobs/#{started["job_id"]}")
break if %w[succeeded failed].include?(job["status"])
sleep 1.5
end
raise (job["error"] || "run failed") if job["status"] == "failed"
text = job["output"].is_a?(Hash) ? job["output"].fetch("output", job["output"]) : job["output"]
puts text # plain tagged text
coverage = text.lines.first.split(":", 2).last.strip
$started = api("POST", "/run", [
"title" => $title,
"diff" => $diff,
"audience" => "Teammates",
]);
do {
sleep(2);
$job = api("GET", "/jobs/" . $started["job_id"]);
} while (!in_array($job["status"], ["succeeded", "failed"]));
if ($job["status"] === "failed") {
throw new Exception($job["error"] ?? "run failed");
}
$text = is_array($job["output"]) ? ($job["output"]["output"] ?? $job["output"]) : $job["output"];
echo $text; // plain tagged text - COVERAGE:/CHANGE TYPE:/… + five sections
var started = await SkillSafe.ApiAsync(HttpMethod.Post, "/run", new {
title, diff, audience = "Teammates" });
var jobId = started.GetProperty("job_id").GetString();
JsonElement job;
while (true)
{
job = await SkillSafe.ApiAsync(HttpMethod.Get, $"/jobs/{jobId}");
var status = job.GetProperty("status").GetString();
if (status is "succeeded" or "failed") break;
await Task.Delay(1500);
}
// plain tagged text - print it or split on the header lines
var text = job.GetProperty("output").GetProperty("output").GetString();
Console.WriteLine(text);
The reply is plain text, not JSON, in exactly this shape:
COVERAGE: Complete walkthrough | Partial walkthrough | Not walkable
CHANGE TYPE: Feature | Bug fix | Refactor | Performance | Docs or chore | Mixed | Unknown
CONFIDENCE: <integer 0-100>
SUMMARY: <2-4 sentences, may wrap; ends at the first blank line>
## Context
- <bullets: what motivated the change>
## Segments
- <title> | <Intro|Context|Code|Summary> | <files, comma separated, or -> | <what is on screen>
## Narration
- <exactly one bullet per segment, same order: the words to speak, author's voice>
## Not shown
- <generated files left out, with reasons, or - None.>
## Open questions
- <what the paste does not settle, or - None.>
Parsing rules the app itself enforces: all four header lines are required;
all five ## sections appear in that order; every ## Segments
bullet has exactly four |-separated fields; ## Narration has one
bullet per segment; unless COVERAGE is Not walkable, there are at least 3
segments, the first is an Intro and the last a Summary. A section
with nothing to report is the single bullet - None.
If a reply ever breaks that shape, retry once with the same input plus a
retry_note field describing the problem — the agent is instructed to
obey it. That's exactly what the app itself does (and the retry is billed as its own run,
so keep it to one).
Step 5 — The same run, streamed
Identical input to /run, but the response is
text/event-stream, so you can show the walkthrough as it generates —
the app's own progress panel does exactly this. Events:
| Event | Data |
|---|---|
job | {job_id} — the run was accepted. |
delta | {text} — the next chunk of agent output. |
done / pending | Final payload: {job_id, status, charged_credits, output}. Authoritative — deltas can drop the tail, so always read the result from here. |
error | {code, message, job_id}. |
curl -sN -X POST "$API/run-stream" \
-H "Authorization: Bearer $TOKEN" -H "Content-Type: application/json" \
-d @input.json
# event: job data: {"job_id":"job_…"}
# event: delta data: {"text":"COVERAGE: Complete walkthrough\n"}
# …
# event: done data: {"job_id":"…","status":"succeeded","charged_credits":412,
# "output":{"output":"…the full tagged text…"}}
res = requests.post(API + "/run-stream", json=payload, stream=True,
headers={"Authorization": f"Bearer {TOKEN}"})
event, done = None, None
for line in res.iter_lines(decode_unicode=True):
if line.startswith("event:"):
event = line[6:].strip()
elif line.startswith("data:"):
data = json.loads(line[5:])
if event == "delta":
print(data.get("text", ""), end="", flush=True)
elif event in ("done", "pending"):
done = data
elif event == "error":
raise RuntimeError(data.get("message"))
text = done["output"]["output"] # authoritative full walkthrough
const res = await fetch(API + "/run-stream", {
method: "POST",
headers: { Authorization: `Bearer ${TOKEN}`, "Content-Type": "application/json" },
body: JSON.stringify(payload),
});
const reader = res.body.getReader();
const decoder = new TextDecoder();
let buf = "", event = "message", done, out = "";
for (;;) {
const chunk = await reader.read();
if (chunk.done) break;
buf += decoder.decode(chunk.value, { stream: true });
let i;
while ((i = buf.indexOf("\n")) >= 0) {
const line = buf.slice(0, i); buf = buf.slice(i + 1);
if (line.startsWith("event:")) event = line.slice(6).trim();
else if (line.startsWith("data:")) {
const data = JSON.parse(line.slice(5));
if (event === "delta") out += data.text ?? "";
else if (event === "done" || event === "pending") done = data;
else if (event === "error") throw new Error(data.message);
}
}
}
const text = done.output.output; // authoritative - deltas can drop the tail
req, _ := http.NewRequest("POST", API+"/run-stream", bytes.NewReader(body))
req.Header.Set("Authorization", "Bearer "+token)
req.Header.Set("Content-Type", "application/json")
res, err := http.DefaultClient.Do(req)
if err != nil {
log.Fatal(err)
}
defer res.Body.Close()
sc := bufio.NewScanner(res.Body)
sc.Buffer(make([]byte, 0, 1<<20), 1<<20)
event, done := "", []byte(nil)
for sc.Scan() {
line := sc.Text()
if strings.HasPrefix(line, "event:") {
event = strings.TrimSpace(line[6:])
} else if strings.HasPrefix(line, "data:") {
data := strings.TrimSpace(line[5:])
if event == "delta" {
// unmarshal {"text": …} and print it as it arrives
} else if event == "done" || event == "pending" {
done = []byte(data)
}
}
}
// unmarshal done -> .output.output (the plain tagged text)
var req = HttpRequest.newBuilder(URI.create(API + "/run-stream"))
.header("Authorization", "Bearer " + TOKEN)
.header("Content-Type", "application/json")
.POST(HttpRequest.BodyPublishers.ofString(payloadJson))
.build();
var lines = HTTP.send(req, HttpResponse.BodyHandlers.ofLines()).body();
final String[] event = {""};
StringBuilder doneData = new StringBuilder();
lines.forEach(line -> {
if (line.startsWith("event:")) event[0] = line.substring(6).trim();
else if (line.startsWith("data:")) {
if (event[0].equals("delta")) { /* parse {"text"} and print */ }
else if (event[0].equals("done")) doneData.append(line.substring(5).trim());
}
});
// parse doneData -> output.output (the plain tagged text)
uri = URI(API + "/run-stream")
req = Net::HTTP::Post.new(uri)
req["Authorization"] = "Bearer #{TOKEN}"
req["Content-Type"] = "application/json"
req.body = payload.to_json
event, done, buf = nil, nil, ""
Net::HTTP.start(uri.host, uri.port, use_ssl: true) do |http|
http.request(req) do |res|
res.read_body do |chunk|
buf << chunk
while (i = buf.index("\n"))
line = buf.slice!(0..i).chomp
if line.start_with?("event:") then event = line[6..].strip
elsif line.start_with?("data:")
data = JSON.parse(line[5..])
print data["text"] if event == "delta"
done = data if %w[done pending].include?(event)
end
end
end
end
end
text = done["output"]["output"] # the plain tagged text
$event = ""; $done = null; $buf = "";
$ch = curl_init(API . "/run-stream");
curl_setopt_array($ch, [
CURLOPT_POST => true,
CURLOPT_HTTPHEADER => ["Authorization: Bearer $TOKEN", "Content-Type: application/json"],
CURLOPT_POSTFIELDS => json_encode($payload),
CURLOPT_WRITEFUNCTION => function ($ch, $chunk) use (&$event, &$done, &$buf) {
$buf .= $chunk;
while (($i = strpos($buf, "\n")) !== false) {
$line = rtrim(substr($buf, 0, $i)); $buf = substr($buf, $i + 1);
if (str_starts_with($line, "event:")) $event = trim(substr($line, 6));
elseif (str_starts_with($line, "data:")) {
$data = json_decode(substr($line, 5), true);
if ($event === "delta") echo $data["text"] ?? "";
if ($event === "done" || $event === "pending") $done = $data;
}
}
return strlen($chunk);
},
]);
curl_exec($ch);
curl_close($ch);
$text = $done["output"]["output"]; // the plain tagged text
var req = new HttpRequestMessage(HttpMethod.Post, Api + "/run-stream")
{ Content = JsonContent.Create(payload) };
var res = await Http.SendAsync(req, HttpCompletionOption.ResponseHeadersRead);
using var reader = new StreamReader(await res.Content.ReadAsStreamAsync());
string? line; string ev = ""; JsonElement doneEl = default;
while ((line = await reader.ReadLineAsync()) != null)
{
if (line.StartsWith("event:")) ev = line[6..].Trim();
else if (line.StartsWith("data:"))
{
var data = JsonDocument.Parse(line[5..]).RootElement.Clone();
if (ev == "delta") Console.Write(
data.TryGetProperty("text", out var t) ? t.GetString() : "");
else if (ev is "done" or "pending") doneEl = data;
}
}
var text = doneEl.GetProperty("output").GetProperty("output").GetString();
The grounding contract applies over the API exactly as in the app: every file, function
and hunk the walkthrough names must appear in the diff you sent, inferred motivation is
phrased as inference, and generated files (lockfiles, API reports, snapshots) land under
## Not shown rather than getting segments. A truncated diff can never come
back as a Complete walkthrough — that honesty is the product.