Review your Claude API integration from your own scripts
Send the integration — client construction, messages.create and
messages.stream calls, tool definitions and tool loops, batch jobs, token
counting and the error handling around them, each file preceded by a
# file: bot.py comment — and get back one JSON object: an API posture,
the inventory of every client, call, model, parameter, tool, feature, dependency and config
with its role, prioritized findings across model drift, deprecated usage, correctness,
caching, cost, reliability and hygiene, each with a corrected fragment in the language you
pasted, the ordered modernization plan, quick wins, and the focus areas to work through
first. Everything this app does goes through the SkillSafe App API — plain JSON over
HTTPS — so you can hang a review off any pull request that touches a
messages.create call or a model id. Wire it into whatever ships your service: a
pre-merge check, a scheduled sweep for retired model ids, or an editor command. Pick a
language once and the whole page follows.
Basics
Base URL: https://api.skillsafe.ai/v1/app-api, app slug
claude-api-clinic. 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.
The review itself is produced by the gpt-terra model. Estimates are free;
runs are metered against your credit balance. There is a single run task — one bundle of
pasted source files in, one review out, no follow-up calls and no session state to carry.
This is the SkillSafe App API that drives this reviewer; it is not Anthropic's
Claude API, which is the subject the reviewer reads your code against.
| Status | Meaning |
|---|---|
401 | Missing or expired token — create a new session. |
402 | Not enough credits — top up at skillsafe.ai/account/credits. |
403 | The token isn't allowed to do this (e.g. a guest reviewing a very large paste). |
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.
Step 0 — A tiny client
Every task below is a single HTTP call, so start with a short helper that adds the auth
header, sends JSON and unwraps the data envelope. The later steps reuse it.
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 shell 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 shell 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 $payload["data"];
}
// .NET 8+
using System.Net.Http.Json;
using System.Text.Json;
static class SkillSafe
{
const string Api = "https://api.skillsafe.ai/v1/app-api";
static readonly HttpClient Http = new();
static SkillSafe() =>
Http.DefaultRequestHeaders.Authorization =
new("Bearer", Environment.GetEnvironmentVariable("SKILLSAFE_TOKEN")); // see step 1
public static async Task<JsonElement> ApiAsync(HttpMethod method, string path, object? body = null)
{
var req = new HttpRequestMessage(method, Api + path);
if (body != null) req.Content = JsonContent.Create(body);
var res = await Http.SendAsync(req);
var json = await res.Content.ReadFromJsonAsync<JsonElement>();
if (!res.IsSuccessStatusCode)
throw new Exception(json.GetProperty("error").GetProperty("message").GetString());
return json.GetProperty("data");
}
}
Step 1 — Get a token
A guest token lets you check balances and estimate costs for free. For metered review runs
billed to your own account, use your personal token: open the
token page, sign in with SkillSafe, and press
Copy shell export — it puts export SKILLSAFE_TOKEN="…" on your
clipboard, which every example below reads. Treat the token like a password: it can spend
your credits. For fully headless scripts, POST /guest mints a guest token with
no browser involved.
curl -s -X POST "$API/guest" \
-H "Content-Type: application/json" \
-d '{"slug":"claude-api-clinic"}' | jq -r '.data.token'
token = api("POST", "/guest", {"slug": "claude-api-clinic"})["token"]
const { token } = await api("POST", "/guest", { slug: "claude-api-clinic" });
var guest struct{ Token string `json:"token"` }
err := call("POST", "/guest", map[string]string{"slug": "claude-api-clinic"}, &guest)
String envelope = api("POST", "/guest", """
{"slug":"claude-api-clinic"}""");
// token is at data.token in the returned JSON
token = api("POST", "/guest", { slug: "claude-api-clinic" })["token"]
$token = api("POST", "/guest", ["slug" => "claude-api-clinic"])["token"];
var guest = await SkillSafe.ApiAsync(HttpMethod.Post, "/guest",
new { slug = "claude-api-clinic" });
var token = guest.GetProperty("token").GetString();
The app stores this browser's token under the localStorage key
skillsafe_app_token:claude-api-clinic, on the app's own origin. The
token page reads and manages it for you — you never need
to open developer tools.
Step 2 — Check who you are and your balance
Returns subject_type ("user" or "guest"),
subject_id and your credits balance. Check this before reviewing a
large paste.
curl -s "$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 exactly the input you would send to /run; the response's
hold_credits is the worst-case cost. Nothing is charged and no job is created,
so estimating is free — useful when you are piping every module that touches the
Anthropic SDK across a service and want a ceiling before spending credits.
| Input field | Type | Notes |
|---|---|---|
sources | string, required | The pasted Claude API / Anthropic SDK integration: client setup, messages.create / messages.stream calls, tool definitions and tool loops, batch jobs, token counting and the configuration around them, in Python, TypeScript/JavaScript, Java/Kotlin, Go, Ruby, C#, PHP or raw HTTP. One file or several concatenated, each preceded by a # file: bot.py (or // file: bot.ts) comment. This is the model's only evidence — nothing is installed, run or called out to. Inputs longer than 100,000 characters are clipped middle-out, with a // [... clipped ...] comment showing where. At least 60 characters are needed for a review. |
sdk_lang | string | python | typescript | java | go | ruby | csharp | php | curl | unknown — changes what is idiomatic: TypeScript timeouts are milliseconds where Python's are seconds, Go reaches the tool runner through its own package, and the corrected snippets come back in the language you name. |
concern | string | general | migration | caching | cost | reliability | tools — the review emphasis. It weights the findings and the summary, but it is emphasis and not exclusivity: a high-severity finding from another category is never suppressed. |
context | string, optional | Extra context: what the integration does, traffic volume, what the monthly bill looks like, measured latencies, which model tier you want to land on, what has already been tried, and any constraint you cannot move (a pinned SDK version, a latency budget, a compliance rule). Clipped at 20,000 characters. |
prescan_facts | object, optional | What a client-side scanner mechanically matched in the code: {"resources": [], "flags": []}. Each entry is {id, label}. Resource ids look like res:model/claude-opus-5, res:sdk/python-anthropic, res:call/messages-create, res:tool/web_search_20260209, res:beta/fast-mode-2026-02-01 or res:file/bot.py; flag ids are <check>:<name>, one per check — retired-model:claude-3-5-sonnet-20241022, dated-model-id:claude-sonnet-4-6-20251114, budget-tokens:bot.py, deprecated-output-format:bot.py, sampling-param:temperature, assistant-prefill:bot.py, no-caching:all, tiktoken:bot.py, old-web-tool:web_search_20250305, fast-mode:on-4-7, thinking-disabled:bot.py, big-max-no-stream:100000, hardcoded-key:9, broad-catch:bot.py-33, legacy-tool-result:57, provider-mix:openai. Every flag id you send comes back in coverage_check. The web UI fills this from its own prescan; API callers may omit the field entirely (then coverage_check simply comes back empty) or send the two empty arrays. |
retry_note | string, optional | Only set by the app's automatic reformat retry when a first reply was not valid JSON. Leave it out. |
cat > sources.txt <<'FILES'
# file: bot.py
import anthropic
client = anthropic.Anthropic()
resp = client.messages.create(
model="claude-3-5-sonnet-20241022",
max_tokens=100000,
temperature=0.7,
thinking={"type": "enabled", "budget_tokens": 8000},
system=SYSTEM_PROMPT,
messages=[{"role": "user", "content": thread}],
)
FILES
jq -n --rawfile sources sources.txt \
'{sources: $sources,
sdk_lang: "python",
concern: "migration",
context: "Support bot, ~2,000 threads a day; we want to land on claude-sonnet-5.",
prescan_facts: {resources: [], flags: []}}' > input.json
curl -s -X POST "$API/estimate" \
-H "Authorization: Bearer $TOKEN" -H "Content-Type: application/json" \
-d @input.json | jq '.data.hold_credits'
SOURCES = r"""# file: bot.py
import anthropic
client = anthropic.Anthropic()
resp = client.messages.create(
model="claude-3-5-sonnet-20241022",
max_tokens=100000,
temperature=0.7,
thinking={"type": "enabled", "budget_tokens": 8000},
system=SYSTEM_PROMPT,
messages=[{"role": "user", "content": thread}],
)
"""
payload = {
"sources": SOURCES,
"sdk_lang": "python",
"concern": "migration",
"context": "Support bot, ~2,000 threads a day; we want to land on claude-sonnet-5.",
"prescan_facts": {"resources": [], "flags": []},
}
est = api("POST", "/estimate", payload)
print("worst case:", est.get("hold_credits", est.get("credits")), "credits")
// String.raw keeps the pasted code exactly as written, escapes and all
const sources = String.raw`# file: bot.py
import anthropic
client = anthropic.Anthropic()
resp = client.messages.create(
model="claude-3-5-sonnet-20241022",
max_tokens=100000,
temperature=0.7,
thinking={"type": "enabled", "budget_tokens": 8000},
system=SYSTEM_PROMPT,
messages=[{"role": "user", "content": thread}],
)
`;
const payload = {
sources,
sdk_lang: "python",
concern: "migration",
context: "Support bot, ~2,000 threads a day; we want to land on claude-sonnet-5.",
prescan_facts: { resources: [], flags: [] },
};
const est = await api("POST", "/estimate", payload);
console.log("worst case:", est.hold_credits ?? est.credits, "credits");
const sources = `# file: bot.py
import anthropic
client = anthropic.Anthropic()
resp = client.messages.create(
model="claude-3-5-sonnet-20241022",
max_tokens=100000,
temperature=0.7,
thinking={"type": "enabled", "budget_tokens": 8000},
system=SYSTEM_PROMPT,
messages=[{"role": "user", "content": thread}],
)
`
payload := map[string]any{
"sources": sources,
"sdk_lang": "python",
"concern": "migration",
"context": "Support bot, ~2,000 threads a day; we want to land on claude-sonnet-5.",
"prescan_facts": map[string]any{
"resources": []any{}, "flags": []any{},
},
}
var est struct{ HoldCredits int64 `json:"hold_credits"` }
err := call("POST", "/estimate", payload, &est)
// A text block keeps the pasted code readable; the common indent is stripped.
String sources = """
# file: bot.py
import anthropic
client = anthropic.Anthropic()
resp = client.messages.create(
model="claude-3-5-sonnet-20241022",
max_tokens=100000,
temperature=0.7,
thinking={"type": "enabled", "budget_tokens": 8000},
system=SYSTEM_PROMPT,
messages=[{"role": "user", "content": thread}],
)
""";
String jsonPayload = """
{"sources": %s,
"sdk_lang": "python",
"concern": "migration",
"context": "Support bot, ~2,000 threads a day; we want to land on claude-sonnet-5.",
"prescan_facts": {"resources": [], "flags": []}}
""".formatted(toJsonString(sources));
String envelope = api("POST", "/estimate", jsonPayload);
// worst-case cost is at data.hold_credits
# the single-quoted heredoc keeps the pasted code literal - no interpolation
SOURCES = <<~'FILES'
# file: bot.py
import anthropic
client = anthropic.Anthropic()
resp = client.messages.create(
model="claude-3-5-sonnet-20241022",
max_tokens=100000,
temperature=0.7,
thinking={"type": "enabled", "budget_tokens": 8000},
system=SYSTEM_PROMPT,
messages=[{"role": "user", "content": thread}],
)
FILES
payload = { sources: SOURCES,
sdk_lang: "python",
concern: "migration",
context: "Support bot, ~2,000 threads a day; we want to land on claude-sonnet-5.",
prescan_facts: { resources: [], flags: [] } }
est = api("POST", "/estimate", payload)
puts "worst case: #{est["hold_credits"] || est["credits"]} credits"
$sources = <<<'FILES'
# file: bot.py
import anthropic
client = anthropic.Anthropic()
resp = client.messages.create(
model="claude-3-5-sonnet-20241022",
max_tokens=100000,
temperature=0.7,
thinking={"type": "enabled", "budget_tokens": 8000},
system=SYSTEM_PROMPT,
messages=[{"role": "user", "content": thread}],
)
FILES;
$payload = [
"sources" => $sources,
"sdk_lang" => "python",
"concern" => "migration",
"context" => "Support bot, ~2,000 threads a day; we want to land on claude-sonnet-5.",
"prescan_facts" => ["resources" => [], "flags" => []],
];
$est = api("POST", "/estimate", $payload);
echo "worst case: " . ($est["hold_credits"] ?? $est["credits"]) . " credits\n";
// a raw string literal keeps the pasted code exactly as written, quotes and all
var sources = """
# file: bot.py
import anthropic
client = anthropic.Anthropic()
resp = client.messages.create(
model="claude-3-5-sonnet-20241022",
max_tokens=100000,
temperature=0.7,
thinking={"type": "enabled", "budget_tokens": 8000},
system=SYSTEM_PROMPT,
messages=[{"role": "user", "content": thread}],
)
""";
var payload = new {
sources,
sdk_lang = "python",
concern = "migration",
context = "Support bot, ~2,000 threads a day; we want to land on claude-sonnet-5.",
prescan_facts = new {
resources = Array.Empty<object>(), flags = Array.Empty<object>(),
},
};
var est = await SkillSafe.ApiAsync(HttpMethod.Post, "/estimate", payload);
Console.WriteLine($"worst case: {est.GetProperty("hold_credits")} credits");
prescan_facts.flags is how you make the review answer for things you already
know about. Send {"resources": [{"id": "res:model/claude-3-5-sonnet-20241022",
"label": "Model/claude-3-5-sonnet-20241022"}], "flags": [{"id": "budget-tokens:bot.py",
"label": "a fixed thinking budget in bot.py"}]}
and every flag id comes back in coverage_check — addressed by a finding, or
set aside with the reason. Nothing you flag is silently dropped, which makes it the field to
assert on in a CI check. Omit the field and coverage_check comes back empty;
the rest of the review is unaffected.
Step 4 — Run the review and wait for the result
/run takes the same input as /estimate, places a credit hold and
returns a job_id. Poll /jobs/{job_id} every 1–2 seconds
until status is succeeded or failed (a run typically
takes 30–90 s, since every finding carries a corrected code fragment and
the plan is ordered afterwards). Always send an Idempotency-Key header so a
network retry can't start a second, double-charged run. The review is in
output — usually nested as output.output, and as a JSON
string, so parse defensively. The samples below print the posture, the inventory,
the prioritized findings and the ordered plan, then save the whole object to
review.json.
JOB_ID=$(curl -s -X POST "$API/run" \
-H "Authorization: Bearer $TOKEN" -H "Content-Type: application/json" \
-H "Idempotency-Key: cac-$(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" ] || [ "$STATUS" = "failed" ] && break
sleep 2
done
# unwrap the review once, then read it
echo "$JOB" | jq -r '.data.output.output' > review.json
jq -r '
"\(.review_name) [\(.posture)]: \(.verdict)",
"",
"INVENTORY",
(.inventory[] | " \(.kind)/\(.name) in \(.scope) - \(.role)"),
"",
"FINDINGS",
(.findings[] | " [\(.priority)] \(.id) \(.category) \(.resource): \(.problem)"),
"",
"PLAN",
(.migration_steps[] | " \(.step) - \(.action) [\(.command)]"),
"",
"QUICK WINS",
(.quick_wins[] | " - \(.)"),
"",
"FOCUS AREAS",
(.focus_areas[] | " \(.area) - \(.why)"),
"",
"COVERAGE",
(.coverage_check[] | " \(.id): \(if .addressed then "ok" else "SET ASIDE" end) - \(.note)")' \
review.json
# fail the pipeline on anything critical
jq -e '[.findings[] | select(.priority == "critical")] | length == 0' review.json > /dev/null \
|| { echo "critical findings present"; exit 1; }
import time
job_id = api("POST", "/run", payload,
**{"Idempotency-Key": "cac-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"]
if isinstance(raw, dict) and "output" in raw:
raw = raw["output"]
review = json.loads(raw) if isinstance(raw, str) else raw
print(f'{review["review_name"]} [{review["posture"]}]: {review["verdict"]}')
for r in review["inventory"]:
print(f' {r["kind"]}/{r["name"]:<24} in={r["scope"] or "-":<20} {r["role"]}')
for f in review["findings"]:
print(f' [{f["priority"]:>8}] {f["id"]} {f["category"]} {f["resource"]}')
print(f' L:{f["likelihood"]}/S:{f["severity"]} {f["problem"]}')
print(f' fix: {f["fix"]}')
if f["snippet"]:
print(" snippet:", f["snippet"].splitlines()[0], "...")
for i, s in enumerate(review["migration_steps"], 1):
print(f' {i}. {s["step"]} - {s["action"]}')
if s["command"]:
print(f' $ {s["command"]}')
for w in review["quick_wins"]:
print(" win:", w)
for a in review["focus_areas"]:
print(f' focus {a["area"]} {a["finding_ids"]} - {a["why"]}')
for c in review["coverage_check"]:
print(f' {c["id"]}: {"ok" if c["addressed"] else "SET ASIDE"} - {c["note"]}')
with open("review.json", "w", encoding="utf-8") as fh:
json.dump(review, fh, indent=2)
critical = [f for f in review["findings"] if f["priority"] == "critical"]
if critical:
raise SystemExit(f"{len(critical)} critical finding(s)")
import { writeFileSync } from "node:fs";
const { job_id } = await api("POST", "/run", payload,
{ "Idempotency-Key": crypto.randomUUID() });
let job;
do {
await new Promise((r) => setTimeout(r, 1500));
job = await api("GET", `/jobs/${job_id}`);
} while (job.status !== "succeeded" && job.status !== "failed");
if (job.status === "failed") throw new Error(job.error ?? "run failed");
const raw = job.output?.output ?? job.output;
const review = typeof raw === "string" ? JSON.parse(raw) : raw;
console.log(`${review.review_name} [${review.posture}]: ${review.verdict}`);
for (const r of review.inventory) {
console.log(` ${r.kind}/${r.name} (${r.scope || "-"}): ${r.role}`);
}
for (const f of review.findings) {
console.log(` [${f.priority}] ${f.id} ${f.category} ${f.resource}`);
console.log(` L:${f.likelihood}/S:${f.severity} - ${f.fix}`);
}
review.migration_steps.forEach((s, i) => {
console.log(` ${i + 1}. ${s.step} - ${s.action}${s.command ? `\n $ ${s.command}` : ""}`);
});
for (const w of review.quick_wins) console.log(` win: ${w}`);
for (const a of review.focus_areas) {
console.log(` focus ${a.area} (${a.finding_ids.join(", ")}): ${a.why}`);
}
for (const c of review.coverage_check) {
console.log(` ${c.id}: ${c.addressed ? "ok" : "SET ASIDE"} - ${c.note}`);
}
writeFileSync("review.json", JSON.stringify(review, null, 2));
const critical = review.findings.filter((f) => f.priority === "critical");
if (critical.length) process.exitCode = 1;
var started struct{ JobID string `json:"job_id"` }
if err := call("POST", "/run", payload, &started); err != nil {
log.Fatal(err)
}
var job struct {
Status string `json:"status"`
Error string `json:"error"`
Output json.RawMessage `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 is {"output": "<json string>"} — unwrap, then unmarshal:
type Review struct {
ReviewName string `json:"review_name"`
Posture string `json:"posture"`
Verdict string `json:"verdict"`
ExecSummary string `json:"exec_summary"`
Assumptions []string `json:"assumptions"`
OpenQuestions []string `json:"open_questions"`
Inventory []struct {
Kind, Name, Scope, Role string
} `json:"inventory"`
Findings []struct {
ID, Category, Severity, Likelihood, Priority string
Resource, Problem, Impact, Fix, Snippet string
} `json:"findings"`
MigrationSteps []struct {
Step, Action, Why, Command string
} `json:"migration_steps"`
CoverageCheck []struct {
ID, Note string
Addressed bool
} `json:"coverage_check"`
QuickWins []string `json:"quick_wins"`
FocusAreas []struct {
Area, Why string
FindingIDs []string `json:"finding_ids"`
} `json:"focus_areas"`
Summary string `json:"summary"`
}
var wrapper struct{ Output string `json:"output"` }
json.Unmarshal(job.Output, &wrapper)
var review Review
json.Unmarshal([]byte(wrapper.Output), &review)
fmt.Printf("%s [%s]: %s\n", review.ReviewName, review.Posture, review.Verdict)
for _, r := range review.Inventory {
fmt.Printf(" %s/%s (%s): %s\n", r.Kind, r.Name, r.Scope, r.Role)
}
for _, f := range review.Findings {
fmt.Printf(" [%s] %s %s %s: %s\n", f.Priority, f.ID, f.Category, f.Resource, f.Problem)
}
for i, s := range review.MigrationSteps {
fmt.Printf(" %d. %s - %s [%s]\n", i+1, s.Step, s.Action, s.Command)
}
for _, a := range review.FocusAreas {
fmt.Printf(" focus %s %v: %s\n", a.Area, a.FindingIDs, a.Why)
}
os.WriteFile("review.json", []byte(wrapper.Output), 0o644)
String envelope = api("POST", "/run", jsonPayload);
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 review is at data.output.output as a JSON string — parse it again, then read
// review_name, posture, verdict, exec_summary, assumptions[], open_questions[],
// inventory[] (kind/name/scope/role),
// findings[] (id/category/severity/likelihood/priority/resource/problem/impact/fix/snippet),
// migration_steps[] (step/action/why/command), coverage_check[] (id/addressed/note),
// quick_wins[], focus_areas[] (area/why/finding_ids[]) and summary.
// Finally keep the review on disk:
// Files.writeString(Path.of("review.json"), reviewJson);
started = api("POST", "/run", payload)
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"
raw = job["output"].is_a?(Hash) ? job["output"].fetch("output", job["output"]) : job["output"]
review = raw.is_a?(String) ? JSON.parse(raw) : raw
puts "#{review["review_name"]} [#{review["posture"]}]: #{review["verdict"]}"
review["inventory"].each { |r| puts " #{r["kind"]}/#{r["name"]} (#{r["scope"]}): #{r["role"]}" }
review["findings"].each do |f|
puts " [#{f["priority"]}] #{f["id"]} #{f["category"]} #{f["resource"]}"
puts " L:#{f["likelihood"]}/S:#{f["severity"]} - #{f["fix"]}"
end
review["migration_steps"].each_with_index do |s, i|
puts " #{i + 1}. #{s["step"]} - #{s["action"]}"
puts " $ #{s["command"]}" unless s["command"].to_s.empty?
end
review["quick_wins"].each { |w| puts " win: #{w}" }
review["focus_areas"].each { |a| puts " focus #{a["area"]} #{a["finding_ids"].join(", ")}" }
review["coverage_check"].each { |c| puts " #{c["id"]}: #{c["addressed"] ? "ok" : "SET ASIDE"}" }
File.write("review.json", JSON.pretty_generate(review))
exit 1 if review["findings"].any? { |f| f["priority"] == "critical" }
$started = api("POST", "/run", $payload);
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");
}
$raw = is_array($job["output"]) ? ($job["output"]["output"] ?? $job["output"]) : $job["output"];
$review = is_string($raw) ? json_decode($raw, true) : $raw;
echo "{$review['review_name']} [{$review['posture']}]: {$review['verdict']}\n";
foreach ($review["inventory"] as $r) {
echo " {$r['kind']}/{$r['name']} ({$r['scope']}): {$r['role']}\n";
}
foreach ($review["findings"] as $f) {
echo " [{$f['priority']}] {$f['id']} {$f['category']} {$f['resource']}\n";
echo " L:{$f['likelihood']}/S:{$f['severity']} - {$f['fix']}\n";
}
foreach ($review["migration_steps"] as $i => $s) {
echo " " . ($i + 1) . ". {$s['step']} - {$s['action']}\n";
if ($s["command"] !== "") { echo " $ {$s['command']}\n"; }
}
foreach ($review["quick_wins"] as $w) {
echo " win: $w\n";
}
foreach ($review["focus_areas"] as $a) {
echo " focus {$a['area']}: " . implode(", ", $a["finding_ids"]) . "\n";
}
foreach ($review["coverage_check"] as $c) {
echo " {$c['id']}: " . ($c["addressed"] ? "ok" : "SET ASIDE") . "\n";
}
file_put_contents("review.json", json_encode($review, JSON_PRETTY_PRINT));
var started = await SkillSafe.ApiAsync(HttpMethod.Post, "/run", payload);
var jobId = started.GetProperty("job_id").GetString();
JsonElement job;
while (true)
{
job = await SkillSafe.ApiAsync(HttpMethod.Get, $"/jobs/{jobId}");
var status = job.GetProperty("status").GetString();
if (status is "succeeded" or "failed") break;
await Task.Delay(1500);
}
var rawText = job.GetProperty("output").GetProperty("output").GetString();
using var doc = JsonDocument.Parse(rawText!);
var review = doc.RootElement;
Console.WriteLine($"{review.GetProperty("review_name")} " +
$"[{review.GetProperty("posture")}]: {review.GetProperty("verdict")}");
foreach (var r in review.GetProperty("inventory").EnumerateArray())
{
Console.WriteLine($" {r.GetProperty("kind")}/{r.GetProperty("name")}: {r.GetProperty("role")}");
}
foreach (var f in review.GetProperty("findings").EnumerateArray())
{
Console.WriteLine($" [{f.GetProperty("priority")}] {f.GetProperty("id")} " +
$"{f.GetProperty("category")} {f.GetProperty("resource")} " +
$"(L:{f.GetProperty("likelihood")}/S:{f.GetProperty("severity")})");
}
foreach (var s in review.GetProperty("migration_steps").EnumerateArray())
{
Console.WriteLine($" {s.GetProperty("step")}: {s.GetProperty("action")} " +
$"[{s.GetProperty("command")}]");
}
foreach (var a in review.GetProperty("focus_areas").EnumerateArray())
{
Console.WriteLine($" focus {a.GetProperty("area")}: {a.GetProperty("why")}");
}
await File.WriteAllTextAsync("review.json", rawText!);
The model is asked for one JSON object and nothing else, but a stray code fence or preamble
is always possible. Strip a leading ```json fence, take the text between the
first { and the last }, and only then parse — that is what
the app does before it falls back to a retry_note reformat run.
The review object — output schema
One JSON object, always the same shape. Every array is present, and the review is grounded in
the pasted code alone: findings cite only files, calls, models, parameters, tools and
dependencies that actually appear in sources, and something that is simply
absent (no error handling, no cache_control on a large stable system
prompt, no streaming on a 128K request) is reported against the closest real construct or
against (missing from the pasted code). Where the code is
silent on something that changes the verdict you get an entry in assumptions
and, if it would change the ranking, in open_questions. Expect five to fifteen
findings on a typical integration — a well-maintained one may honestly yield two or
three, and findings is never empty.
| Field | Type | Meaning |
|---|---|---|
review_name | string | A short title naming the integration, taken from the code's own naming — e.g. support-bot — Claude API review. |
posture | string | api-current | update-recommended | breakage-risk. See the table below. |
verdict | string | One sentence justifying the posture and naming the single most important change. |
exec_summary | string | Two or three paragraphs, separated by blank lines, on the dominant themes across the integration. |
assumptions | string[] | Explicit assumptions filling gaps the code left open. Read these first — a wrong assumption invalidates the findings built on it. |
open_questions | string[] | Questions whose answers would change the ranking. |
inventory | array | {kind, name, scope, role} — every Client, Call, Model, Param, Tool, Feature, Dependency and Config the review parsed out of the code and the part it plays. scope is the file or call site it appears in. |
findings | array | The prioritized findings table — ids AC-001, AC-002, … in sequence, at least one entry. Columns are listed below. |
migration_steps | array | {step, action, why, command} — the ordered modernization plan from where the integration is to where the review says it should be, first step first, each independently deployable. Two to eight steps. For an api-current integration these are the next improvements, not migration chores. |
coverage_check | array | {id, addressed, note} — one entry per prescan_facts.flags id you sent, each appearing exactly once. See the semantics below. |
quick_wins | string[] | One-line changes worth doing immediately, ahead of any planning. May be empty when nothing here is a one-liner. |
focus_areas | array | {area, why, finding_ids} — what to work through first, one sentence tied to the review, and the finding ids that motivate it. Every id in finding_ids exists in findings. |
summary | string | Closing paragraph: what to fix first, and what risk remains after that. |
The three posture values:
| posture | What it means |
|---|---|
api-current | Current model ids, no removed parameters, caching and streaming where they belong. Findings still exist, but they are improvements — placing a cache_control breakpoint better, tuning output_config.effort, moving offline work to the Batches API, adding server-side fallbacks — not breakage. Genuinely well-maintained integrations land here rather than having severity manufactured for them. |
update-recommended | Nothing returns an error today, but named costs should be addressed: a stale model tier, a large stable system prompt re-sent with no cache_control, non-latency-sensitive work paying full price instead of running on batches, weak error handling that retries what retrying cannot fix. |
breakage-risk | Something in the code returns an error on the model in use or on the stated migration target — a retired model id, budget_tokens or a sampling param on a model that removed it, an assistant prefill turn, speed: "fast" on 4.7 — or a credential is exposed in source. This is the posture to gate a pipeline on. |
Each entry in findings:
| Column | Meaning |
|---|---|
id | Sequential AC-001, AC-002, … — the stable handle referenced from focus_areas[].finding_ids. |
category | model-drift | deprecated-usage | correctness | caching | cost | reliability | hygiene. Weighted by the concern you sent, but never restricted to it. The categories keep the three kinds of problem apart on purpose: what will break (a 400 on the model in use), what costs money (missing caching, the wrong tier, no batches) and what mis-handles an edge (an unguarded refusal, a broad catch, string-matched tool input). |
severity | low | medium | high — how bad it is when it bites. |
likelihood | low | medium | high — how likely it is to bite. |
priority | critical | high | medium | low — severity by likelihood. critical is reserved for something that returns an error on the model in use, silently corrupts results (a dropped tool_result, string-matched tool input) or exposes a credential, so sort on this field and work top-down. This is also a field to gate a pipeline on. |
resource | The Model/claude-3-5-sonnet-20241022, Call/messages.create (bot.py), Param/budget_tokens, Tool/web_search_20250305 or file this is about — always something that appears in sources, or the literal (missing from the pasted code) when the finding is about something absent. |
problem | What is wrong, in this code specifically. |
impact | What it costs — a 400 on the next deploy, dollars per million tokens, a dropped tool result, a leaked key. |
fix | The concrete change to make — not "modernize the call". |
snippet | A corrected fragment in the language of the pasted code you can paste: the fixed block, correctly indented, matching the file it belongs to, not the whole file. Empty string when a snippet would add nothing. Secret values are never echoed — a placeholder appears instead. |
Each entry in migration_steps:
| Column | Meaning |
|---|---|
step | The short name of the step, e.g. Move to a current model id. |
action | What to actually do, in this integration's files. |
why | One sentence tying the step to the findings. |
command | A real shell command when one exists (pip install -U anthropic, npm i @anthropic-ai/sdk@latest), and the empty string when the step is a code edit. This is what the app's "plan as a shell script" export is built from — code-edit steps become comments. |
coverage_check semantics:
| Case | What you get |
|---|---|
| Every flag id you sent | Each prescan_facts.flags id appears in coverage_check exactly once. Nothing you flagged is silently dropped, which makes this the field to assert on in a CI check. Ids in prescan_facts.resources are not reconciled here — they shape the inventory instead. |
addressed: true | The flag is covered by the review; note names the finding id that covers it. |
addressed: false | The flag was deliberately set aside; note gives the reason — a check that fired but is not a real problem for this integration (a temperature on the one path that legitimately still runs on the 4.6 pair, an assistant message that is echoed history rather than a prefill). |
| Nothing sent | Omit prescan_facts, or send the two empty arrays, and coverage_check comes back empty. The rest of the review is unaffected. |
A small, realistic result for the input above, trimmed for length:
{
"review_name": "support-bot — Claude API review",
"posture": "breakage-risk",
"verdict": "The one call site names a retired model and carries two parameters the stated target
rejects; land on claude-sonnet-5 with adaptive thinking and the rest is tuning.",
"exec_summary": "bot.py calls claude-3-5-sonnet-20241022, a retired model line, so the request
shape around it was written for behaviour current models no longer have. The
stated target is claude-sonnet-5, and two of the parameters on this call are
removed there: temperature and the fixed thinking budget.
The rest is cost and plumbing. A ~6k-token system prompt is re-sent on every
request with no cache_control breakpoint, and max_tokens is 100000 on a
non-streaming call, which the SDKs cannot hold inside one request-response.",
"assumptions": [
"SYSTEM_PROMPT is the stable policy text it looks like, not per-request content.",
"No wrapper module outside the pasted file adds retries or a different model id."
],
"open_questions": [
"Do replies actually approach 100000 tokens, or was the cap copied in as a ceiling?",
"Is any traffic latency-sensitive, or could the bulk of it run on the Batches API?"
],
"inventory": [
{ "kind": "Model", "name": "claude-3-5-sonnet-20241022", "scope": "bot.py",
"role": "Answers support threads; a retired, date-suffixed id." },
{ "kind": "Call", "name": "messages.create", "scope": "bot.py",
"role": "The single non-streaming request path." },
{ "kind": "Param", "name": "thinking.budget_tokens", "scope": "bot.py",
"role": "Fixed thinking budget, copied from a 2024-era example." },
{ "kind": "Client", "name": "anthropic.Anthropic", "scope": "bot.py",
"role": "Default client; credentials resolved from the environment." }
],
"findings": [
{ "id": "AC-001", "category": "model-drift",
"severity": "high", "likelihood": "high", "priority": "critical",
"resource": "Model/claude-3-5-sonnet-20241022 (bot.py)",
"problem": "The model id names the retired claude-3 line and carries a date suffix; current
ids are complete as-is.",
"impact": "Requests naming it fail outright once the line is fully withdrawn — and every
other choice on this call was tuned for a model that no longer behaves that way.",
"fix": "Move to claude-sonnet-5, the stated target, and re-read the request shape around it.",
"snippet": "MODEL = \"claude-sonnet-5\"" },
{ "id": "AC-002", "category": "deprecated-usage",
"severity": "high", "likelihood": "high", "priority": "critical",
"resource": "Param/budget_tokens (bot.py)",
"problem": "thinking is configured as {\"type\": \"enabled\", \"budget_tokens\": 8000}, and
budget_tokens is rejected with a 400 on Sonnet 5.",
"impact": "The very deploy that fixes the model id starts 400ing on every request unless
this changes in the same commit.",
"fix": "Send adaptive thinking; tune depth with output_config.effort if it is a lever here.",
"snippet": "resp = client.messages.create(\n model=MODEL,\n max_tokens=16000,\n thinking={\"type\": \"adaptive\"},\n messages=messages,\n)" },
{ "id": "AC-003", "category": "deprecated-usage",
"severity": "medium", "likelihood": "high", "priority": "high",
"resource": "Param/temperature (bot.py)",
"problem": "temperature=0.7 is sent alongside a migration target that removed sampling
params.",
"impact": "A second 400 on the same request, from the same deploy as AC-002.",
"fix": "Drop temperature; if reply variety is the goal, ask for it in the system prompt.",
"snippet": "" },
{ "id": "AC-004", "category": "caching",
"severity": "medium", "likelihood": "high", "priority": "high",
"resource": "Param/system (bot.py)",
"problem": "A large stable system prompt is re-sent on every call and no cache_control
breakpoint appears anywhere in the pasted code.",
"impact": "Full input price on the same ~6k tokens for every one of the ~2,000 daily threads
— the single biggest unused cost lever here.",
"fix": "Put an ephemeral cache_control breakpoint on the system block and watch
usage.cache_read_input_tokens to confirm it hits.",
"snippet": "system=[{\n \"type\": \"text\",\n \"text\": SYSTEM_PROMPT,\n \"cache_control\": {\"type\": \"ephemeral\"},\n}]" },
{ "id": "AC-005", "category": "reliability",
"severity": "medium", "likelihood": "medium", "priority": "medium",
"resource": "Param/max_tokens (bot.py)",
"problem": "max_tokens is 100000 on a non-streaming call.",
"impact": "Output caps this large sit inside one HTTP request-response and hit the SDK
timeout; the practical ceiling is ~16K non-streaming, ~64K streaming.",
"fix": "Either lower the cap to what replies actually need, or switch to .stream() and read
the result with get_final_message().",
"snippet": "with client.messages.stream(\n model=MODEL,\n max_tokens=64000,\n messages=messages,\n) as stream:\n resp = stream.get_final_message()" }
],
"migration_steps": [
{ "step": "Move to a current model id",
"action": "Set MODEL to claude-sonnet-5 in bot.py.",
"why": "The retired line is the root of every other finding on this call.",
"command": "pip install -U anthropic" },
{ "step": "Fix the request shape in the same commit",
"action": "Replace the budget_tokens config with {\"type\": \"adaptive\"} and delete
temperature, as in AC-002 and AC-003.",
"why": "Both parameters are 400s on the new model, so they cannot ship a deploy later.",
"command": "" },
{ "step": "Cache the system prompt",
"action": "Send system as a block list with an ephemeral cache_control breakpoint and log
usage.cache_read_input_tokens for a day.",
"why": "It is the same ~6k tokens on every request at full price today.",
"command": "" },
{ "step": "Right-size the output cap",
"action": "Lower max_tokens to what replies need, or move the call to .stream().",
"why": "100000 on a non-streaming call cannot complete inside one request-response.",
"command": "" }
],
"coverage_check": [
{ "id": "retired-model:claude-3-5-sonnet-20241022", "addressed": true, "note": "AC-001." },
{ "id": "budget-tokens:bot.py", "addressed": true, "note": "AC-002." },
{ "id": "sampling-param:temperature", "addressed": true, "note": "AC-003." },
{ "id": "no-caching:all", "addressed": true, "note": "AC-004." },
{ "id": "big-max-no-stream:100000", "addressed": true, "note": "AC-005." }
],
"quick_wins": [
"Delete temperature=0.7 — it is a 400 on the target model, not a tuning knob.",
"Put a cache_control breakpoint on the system prompt before touching anything else."
],
"focus_areas": [
{ "area": "Unbreak the call on the target model",
"why": "The model id and two parameters have to move in one commit or the deploy 400s.",
"finding_ids": ["AC-001", "AC-002", "AC-003"] },
{ "area": "Stop paying for the same prefix twice a second",
"why": "The stable system prompt is re-sent uncached on every thread.",
"finding_ids": ["AC-004"] }
],
"summary": "Move the model id, the thinking config and temperature together, and this bot is on a
current model within one commit. Cache the system prompt next — it is the largest
recurring cost visible here. Error handling was not judged: only the one call site
was pasted, so send the wrapper module if retry behaviour is the question."
}
This is AI-generated review from source text, not a sign-off: it sees only what you
sent, never a real request, a real bill or the rest of the repository. Check
assumptions and open_questions before you act on the rankings,
run every snippet against your own tests and staging keys, and keep a human reviewer in
the loop.
Step 5 — Stream the review as it is written
/run-stream takes exactly the same body as /run but answers with
server-sent events, so you can show progress instead of a spinner — useful here
because a full findings table with corrected code plus an ordered plan makes for a long
reply. This app's own progress panel is this endpoint. Events are separated by a blank line;
each has an event: line and a data: line carrying JSON.
| Event | Payload | Meaning |
|---|---|---|
job | {job_id, status} | Sent once, when the job is accepted — show "starting". |
delta | {text} | A chunk of the reply, in order. Append it; the accumulated length is your only progress signal (the total is not known in advance). The app advances its step list by watching for the "review_name", "inventory", "findings", "migration_steps", "coverage_check" and "focus_areas" keys as they arrive. |
done | {job_id, status, charged_credits, output} | The final, authoritative result — read the review from output.output rather than trusting concatenated deltas, and the settled price from charged_credits. |
error | {code, message} | Replaces done when the run fails. |
# -N disables buffering so events print as they arrive
curl -N -s -X POST "$API/run-stream" \
-H "Authorization: Bearer $TOKEN" -H "Content-Type: application/json" \
-H "Idempotency-Key: cac-$(date +%s)" \
-d @input.json
# event: job
# data: {"job_id":"job_...","status":"running"}
#
# event: delta
# data: {"text":"{\"review_name\":\"supp"}
# ...
# event: done
# data: {"job_id":"job_...","status":"succeeded","charged_credits":648,"output":{"output":"{...}"}}
import json, requests
result = None
with requests.post(
API + "/run-stream",
headers={"Authorization": f"Bearer {TOKEN}",
"Idempotency-Key": "cac-001"},
json=payload,
stream=True,
) as r:
r.raise_for_status()
event = None
for line in r.iter_lines(decode_unicode=True):
if not line:
continue
if line.startswith("event:"):
event = line[len("event:"):].strip()
elif line.startswith("data:"):
data = json.loads(line[len("data:"):].strip())
if event == "delta":
print(".", end="", flush=True) # live progress
elif event == "done":
result = data
elif event == "error":
raise RuntimeError(data.get("message", "run failed"))
review = json.loads(result["output"]["output"]) # authoritative
print("charged:", result["charged_credits"], "-", review["review_name"])
print("posture:", review["posture"])
for f in review["findings"]:
print(f' [{f["priority"]}] {f["id"]} {f["resource"]}: {f["problem"]}')
with open("review.json", "w", encoding="utf-8") as fh:
json.dump(review, fh, indent=2)
const res = await fetch(API + "/run-stream", {
method: "POST",
headers: {
Authorization: `Bearer ${TOKEN}`,
"Content-Type": "application/json",
"Idempotency-Key": crypto.randomUUID(),
},
body: JSON.stringify(payload),
});
const reader = res.body.getReader();
const decoder = new TextDecoder();
let buf = "", done = null;
for (;;) {
const chunk = await reader.read();
if (chunk.done) break;
buf += decoder.decode(chunk.value, { stream: true });
const frames = buf.split("\n\n");
buf = frames.pop();
for (const frame of frames) {
const name = /^event:\s*(.+)$/m.exec(frame)?.[1];
const body = /^data:\s*(.+)$/m.exec(frame)?.[1];
if (!name || !body) continue;
const data = JSON.parse(body);
if (name === "delta") process.stdout.write("."); // live progress
if (name === "done") done = data;
if (name === "error") throw new Error(data.message ?? "run failed");
}
}
const review = JSON.parse(done.output.output);
console.log(`\n${done.charged_credits} credits - ${review.review_name} [${review.posture}]`);
for (const f of review.findings) console.log(` [${f.priority}] ${f.id} ${f.resource}`);
writeFileSync("review.json", JSON.stringify(review, null, 2));
body, _ := json.Marshal(payload)
req, _ := http.NewRequest("POST", API+"/run-stream", bytes.NewReader(body))
req.Header.Set("Authorization", "Bearer "+token)
req.Header.Set("Content-Type", "application/json")
req.Header.Set("Idempotency-Key", "cac-001")
res, err := http.DefaultClient.Do(req)
if err != nil {
log.Fatal(err)
}
defer res.Body.Close()
var event string
var final map[string]any
sc := bufio.NewScanner(res.Body)
sc.Buffer(make([]byte, 0, 64*1024), 4*1024*1024)
for sc.Scan() {
line := sc.Text()
switch {
case strings.HasPrefix(line, "event:"):
event = strings.TrimSpace(strings.TrimPrefix(line, "event:"))
case strings.HasPrefix(line, "data:"):
var data map[string]any
json.Unmarshal([]byte(strings.TrimPrefix(line, "data:")), &data)
switch event {
case "delta":
fmt.Print(".") // live progress
case "done":
final = data
case "error":
log.Fatal(data["message"])
}
}
}
// final["output"].(map[string]any)["output"].(string) is the review JSON —
// unmarshal it into the Review struct from step 4, then write it to review.json.
// Java 17+ — read the stream line by line instead of buffering the body.
var req = HttpRequest.newBuilder(URI.create(API + "/run-stream"))
.header("Authorization", "Bearer " + TOKEN)
.header("Content-Type", "application/json")
.header("Idempotency-Key", "cac-001")
.POST(HttpRequest.BodyPublishers.ofString(jsonPayload))
.build();
var res = HTTP.send(req, HttpResponse.BodyHandlers.ofLines());
String event = null, done = null;
for (String line : (Iterable<String>) res.body()::iterator) {
if (line.startsWith("event:")) {
event = line.substring(6).trim();
} else if (line.startsWith("data:")) {
String data = line.substring(5).trim();
if ("delta".equals(event)) System.out.print("."); // live progress
else if ("done".equals(event)) done = data;
else if ("error".equals(event)) throw new RuntimeException(data);
}
}
// parse `done`, then parse data.output.output again — it is a JSON string holding
// review_name, posture, verdict, inventory[], findings[], migration_steps[],
// coverage_check[], quick_wins[], focus_areas[] and the rest.
require "net/http"
require "json"
uri = URI(API + "/run-stream")
req = Net::HTTP::Post.new(uri)
req["Authorization"] = "Bearer #{TOKEN}"
req["Content-Type"] = "application/json"
req["Idempotency-Key"] = "cac-001"
req.body = payload.to_json
event = nil
done = nil
Net::HTTP.start(uri.host, uri.port, use_ssl: true) do |http|
http.request(req) do |res|
res.read_body do |chunk|
chunk.each_line do |line|
line = line.strip
if line.start_with?("event:")
event = line.delete_prefix("event:").strip
elsif line.start_with?("data:")
data = JSON.parse(line.delete_prefix("data:").strip)
case event
when "delta" then print "." # live progress
when "done" then done = data
when "error" then raise (data["message"] || "run failed")
end
end
end
end
end
end
review = JSON.parse(done["output"]["output"])
puts "\n#{done["charged_credits"]} credits - #{review["review_name"]} [#{review["posture"]}]"
review["findings"].each { |f| puts " [#{f["priority"]}] #{f["id"]} #{f["resource"]}" }
File.write("review.json", JSON.pretty_generate(review))
$event = null;
$done = null;
$ch = curl_init(API . "/run-stream");
curl_setopt_array($ch, [
CURLOPT_POST => true,
CURLOPT_HTTPHEADER => [
"Authorization: Bearer $TOKEN",
"Content-Type: application/json",
"Idempotency-Key: cac-001",
],
CURLOPT_POSTFIELDS => json_encode($payload),
CURLOPT_WRITEFUNCTION => function ($ch, $chunk) use (&$event, &$done) {
foreach (explode("\n", $chunk) as $line) {
$line = trim($line);
if (str_starts_with($line, "event:")) {
$event = trim(substr($line, 6));
} elseif (str_starts_with($line, "data:")) {
$data = json_decode(trim(substr($line, 5)), true);
if ($event === "delta") { echo "."; } // live progress
elseif ($event === "done") { $done = $data; }
elseif ($event === "error") { throw new Exception($data["message"] ?? "run failed"); }
}
}
return strlen($chunk);
},
]);
curl_exec($ch);
curl_close($ch);
$review = json_decode($done["output"]["output"], true);
echo "\n{$done['charged_credits']} credits - {$review['review_name']} [{$review['posture']}]\n";
foreach ($review["findings"] as $f) {
echo " [{$f['priority']}] {$f['id']} {$f['resource']}\n";
}
file_put_contents("review.json", json_encode($review, JSON_PRETTY_PRINT));
var req = new HttpRequestMessage(HttpMethod.Post, Api + "/run-stream") {
Content = JsonContent.Create(payload),
};
req.Headers.Add("Idempotency-Key", "cac-001");
using var res = await Http.SendAsync(req, HttpCompletionOption.ResponseHeadersRead);
using var reader = new StreamReader(await res.Content.ReadAsStreamAsync());
string? evt = null, done = null;
while (await reader.ReadLineAsync() is { } line)
{
if (line.StartsWith("event:")) evt = line[6..].Trim();
else if (line.StartsWith("data:"))
{
var data = line[5..].Trim();
if (evt == "delta") Console.Write("."); // live progress
else if (evt == "done") done = data;
else if (evt == "error") throw new Exception(data);
}
}
using var final = JsonDocument.Parse(done!);
var text = final.RootElement.GetProperty("output").GetProperty("output").GetString();
using var reviewDoc = JsonDocument.Parse(text!);
var review = reviewDoc.RootElement;
Console.WriteLine($"{review.GetProperty("review_name")} [{review.GetProperty("posture")}]");
foreach (var f in review.GetProperty("findings").EnumerateArray())
Console.WriteLine($" [{f.GetProperty("priority")}] {f.GetProperty("id")} {f.GetProperty("resource")}");
await File.WriteAllTextAsync("review.json", text!);
In a browser, the native EventSource only speaks GET, and this endpoint is a
POST — read the fetch response body incrementally, as the JavaScript
sample above does. On an idempotent replay the server may answer with a plain JSON
envelope instead of an event stream; check the Content-Type before you start
parsing frames.
Step 6 — A CI gate on the posture
The last mile: read the review JSON and turn it into an exit code. The rule below fails the
job when posture is breakage-risk — something in the
code returns an error on the model in use or on the stated migration target, or a
credential is exposed
— or when any finding is critical, and warns without failing on
update-recommended. If you send prescan_facts.flags, also assert
that every id you sent came back in coverage_check: that is your guarantee that
nothing you already knew about was quietly dropped.
The Idempotency-Key here is derived from the input — a
hash of the exact payload — rather than a timestamp or a random UUID. The same
bot.py and the same context therefore produce the same key, so a
re-run of a red CI job, a retried flaky step or two jobs racing on the same commit all
replay the first result instead of paying for a second review. Change a byte of the
input and the key changes with it, which is exactly when you do want a fresh run.
# input.json is the payload built in step 3
KEY="cac-$(shasum -a 256 input.json | cut -c1-32)" # same input, same key, no double charge
JOB_ID=$(curl -s -X POST "$API/run" \
-H "Authorization: Bearer $TOKEN" -H "Content-Type: application/json" \
-H "Idempotency-Key: $KEY" \
-d @input.json | jq -r '.data.job_id')
while :; do
JOB=$(curl -s "$API/jobs/$JOB_ID" -H "Authorization: Bearer $TOKEN")
STATUS=$(echo "$JOB" | jq -r '.data.status')
[ "$STATUS" = "succeeded" ] || [ "$STATUS" = "failed" ] && break
sleep 2
done
[ "$STATUS" = "succeeded" ] || { echo "run failed"; exit 2; }
echo "$JOB" | jq -r '.data.output.output' > review.json
POSTURE=$(jq -r '.posture' review.json)
CRIT=$(jq '[.findings[] | select(.priority == "critical")] | length' review.json)
UNSEEN=$(jq -r '[.coverage_check[] | select(.addressed | not) | .id] | join(", ")' review.json)
echo "posture: $POSTURE critical: $CRIT"
[ -n "$UNSEEN" ] && echo "set aside: $UNSEEN"
jq -r '.migration_steps[] | "next: \(.step) - \(.action)"' review.json | head -3
if [ "$POSTURE" = "breakage-risk" ] || [ "$CRIT" -gt 0 ]; then
jq -r '"BLOCKED: \(.verdict)"' review.json
exit 1
fi
[ "$POSTURE" = "update-recommended" ] && jq -r '"warning: \(.verdict)"' review.json
exit 0
import hashlib, json, sys, time
# The key is a hash of the payload itself: identical input replays, changed input re-runs.
canonical = json.dumps(payload, sort_keys=True, separators=(",", ":"))
key = "cac-" + hashlib.sha256(canonical.encode("utf-8")).hexdigest()[:32]
job_id = api("POST", "/run", payload, **{"Idempotency-Key": key})["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"] != "succeeded":
sys.exit(2)
raw = job["output"]
if isinstance(raw, dict) and "output" in raw:
raw = raw["output"]
review = json.loads(raw) if isinstance(raw, str) else raw
critical = [f for f in review["findings"] if f["priority"] == "critical"]
set_aside = [c["id"] for c in review["coverage_check"] if not c["addressed"]]
sent = {f["id"] for f in payload["prescan_facts"]["flags"]}
missing = sent - {c["id"] for c in review["coverage_check"]}
print(f'posture: {review["posture"]} critical: {len(critical)}')
if set_aside:
print("set aside:", ", ".join(set_aside))
if missing:
print("NOT RECONCILED:", ", ".join(sorted(missing)))
for s in review["migration_steps"][:3]:
print(f'next: {s["step"]} - {s["action"]}')
if review["posture"] == "breakage-risk" or critical or missing:
sys.exit(f'BLOCKED: {review["verdict"]}')
if review["posture"] == "update-recommended":
print("warning:", review["verdict"])
import { createHash } from "node:crypto";
// The key is a hash of the payload itself: identical input replays, changed input re-runs.
const canonical = JSON.stringify(payload, Object.keys(payload).sort());
const key = "cac-" + createHash("sha256").update(canonical).digest("hex").slice(0, 32);
const { job_id } = await api("POST", "/run", payload, { "Idempotency-Key": key });
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 !== "succeeded") process.exit(2);
const raw = job.output?.output ?? job.output;
const review = typeof raw === "string" ? JSON.parse(raw) : raw;
const critical = review.findings.filter((f) => f.priority === "critical");
const setAside = review.coverage_check.filter((c) => !c.addressed).map((c) => c.id);
const seen = new Set(review.coverage_check.map((c) => c.id));
const missing = payload.prescan_facts.flags.map((f) => f.id).filter((id) => !seen.has(id));
console.log(`posture: ${review.posture} critical: ${critical.length}`);
if (setAside.length) console.log("set aside:", setAside.join(", "));
if (missing.length) console.log("NOT RECONCILED:", missing.join(", "));
for (const s of review.migration_steps.slice(0, 3)) {
console.log(`next: ${s.step} - ${s.action}`);
}
if (review.posture === "breakage-risk" || critical.length || missing.length) {
console.error(`BLOCKED: ${review.verdict}`);
process.exit(1);
}
if (review.posture === "update-recommended") console.warn(`warning: ${review.verdict}`);
// The key is a hash of the payload itself: identical input replays, changed input re-runs.
raw, _ := json.Marshal(payload)
sum := sha256.Sum256(raw)
key := "cac-" + hex.EncodeToString(sum[:])[:32]
body := bytes.NewReader(raw)
req, _ := http.NewRequest("POST", API+"/run", body)
req.Header.Set("Authorization", "Bearer "+token)
req.Header.Set("Content-Type", "application/json")
req.Header.Set("Idempotency-Key", key)
// ...send it, read data.job_id, then poll /jobs/{id} exactly as in step 4.
// review is the Review struct from step 4:
critical := 0
for _, f := range review.Findings {
if f.Priority == "critical" {
critical++
}
}
for _, c := range review.CoverageCheck {
if !c.Addressed {
fmt.Println("set aside:", c.ID, "-", c.Note)
}
}
fmt.Printf("posture: %s critical: %d\n", review.Posture, critical)
for i, s := range review.MigrationSteps {
if i < 3 {
fmt.Printf("next: %s - %s\n", s.Step, s.Action)
}
}
if review.Posture == "breakage-risk" || critical > 0 {
fmt.Fprintln(os.Stderr, "BLOCKED: "+review.Verdict)
os.Exit(1)
}
// The key is a hash of the payload itself: identical input replays, changed input re-runs.
import java.security.MessageDigest;
import java.util.HexFormat;
byte[] digest = MessageDigest.getInstance("SHA-256")
.digest(jsonPayload.getBytes(java.nio.charset.StandardCharsets.UTF_8));
String key = "cac-" + HexFormat.of().formatHex(digest).substring(0, 32);
var req = HttpRequest.newBuilder(URI.create(API + "/run"))
.header("Authorization", "Bearer " + TOKEN)
.header("Content-Type", "application/json")
.header("Idempotency-Key", key)
.POST(HttpRequest.BodyPublishers.ofString(jsonPayload))
.build();
// send it, read data.job_id, poll /jobs/{id} as in step 4, then parse data.output.output.
// With the review parsed (your JSON library of choice):
// String posture = review.get("posture");
// long critical = count of findings[] whose priority equals "critical";
// every coverage_check[] entry with addressed == false is a set-aside prescan flag.
// if (posture.equals("breakage-risk") || critical > 0) {
// System.err.println("BLOCKED: " + review.get("verdict"));
// System.exit(1);
// }
// migration_steps[] is the ordered to-do list to print above the failure.
require "digest"
# The key is a hash of the payload itself: identical input replays, changed input re-runs.
key = "cac-" + Digest::SHA256.hexdigest(JSON.generate(payload))[0, 32]
started = api("POST", "/run", payload) # add the header in your api() helper:
# req["Idempotency-Key"] = key
job = nil
loop do
job = api("GET", "/jobs/#{started["job_id"]}")
break if %w[succeeded failed].include?(job["status"])
sleep 1.5
end
exit 2 unless job["status"] == "succeeded"
raw = job["output"].is_a?(Hash) ? job["output"].fetch("output", job["output"]) : job["output"]
review = raw.is_a?(String) ? JSON.parse(raw) : raw
critical = review["findings"].count { |f| f["priority"] == "critical" }
set_aside = review["coverage_check"].reject { |c| c["addressed"] }.map { |c| c["id"] }
seen = review["coverage_check"].map { |c| c["id"] }
missing = payload[:prescan_facts][:flags].map { |f| f[:id] } - seen
puts "posture: #{review["posture"]} critical: #{critical}"
puts "set aside: #{set_aside.join(", ")}" unless set_aside.empty?
puts "NOT RECONCILED: #{missing.join(", ")}" unless missing.empty?
review["migration_steps"].first(3).each { |s| puts "next: #{s["step"]} - #{s["action"]}" }
if review["posture"] == "breakage-risk" || critical > 0 || !missing.empty?
warn "BLOCKED: #{review["verdict"]}"
exit 1
end
warn "warning: #{review["verdict"]}" if review["posture"] == "update-recommended"
<?php
// The key is a hash of the payload itself: identical input replays, changed input re-runs.
$key = "cac-" . substr(hash("sha256", json_encode($payload)), 0, 32);
// pass $key through to the request as the Idempotency-Key header, then poll as in step 4
$started = api("POST", "/run", $payload);
do {
sleep(2);
$job = api("GET", "/jobs/" . $started["job_id"]);
} while (!in_array($job["status"], ["succeeded", "failed"]));
if ($job["status"] !== "succeeded") { exit(2); }
$raw = is_array($job["output"]) ? ($job["output"]["output"] ?? $job["output"]) : $job["output"];
$review = is_string($raw) ? json_decode($raw, true) : $raw;
$critical = count(array_filter($review["findings"], fn($f) => $f["priority"] === "critical"));
$setAside = array_column(array_filter($review["coverage_check"], fn($c) => !$c["addressed"]), "id");
$seen = array_column($review["coverage_check"], "id");
$missing = array_diff(array_column($payload["prescan_facts"]["flags"], "id"), $seen);
echo "posture: {$review['posture']} critical: $critical\n";
if ($setAside) { echo "set aside: " . implode(", ", $setAside) . "\n"; }
if ($missing) { echo "NOT RECONCILED: " . implode(", ", $missing) . "\n"; }
foreach (array_slice($review["migration_steps"], 0, 3) as $s) {
echo "next: {$s['step']} - {$s['action']}\n";
}
if ($review["posture"] === "breakage-risk" || $critical > 0 || $missing) {
fwrite(STDERR, "BLOCKED: {$review['verdict']}\n");
exit(1);
}
if ($review["posture"] === "update-recommended") {
fwrite(STDERR, "warning: {$review['verdict']}\n");
}
using System.Security.Cryptography;
// The key is a hash of the payload itself: identical input replays, changed input re-runs.
var bytes = JsonSerializer.SerializeToUtf8Bytes(payload);
var key = "cac-" + Convert.ToHexString(SHA256.HashData(bytes)).ToLowerInvariant()[..32];
var run = new HttpRequestMessage(HttpMethod.Post, Api + "/run") {
Content = JsonContent.Create(payload),
};
run.Headers.Add("Idempotency-Key", key);
// send it, read data.job_id, poll /jobs/{id} as in step 4, then:
var reviewText = job.GetProperty("output").GetProperty("output").GetString();
using var reviewDoc = JsonDocument.Parse(reviewText!);
var review = reviewDoc.RootElement;
var posture = review.GetProperty("posture").GetString();
var critical = review.GetProperty("findings").EnumerateArray()
.Count(f => f.GetProperty("priority").GetString() == "critical");
Console.WriteLine($"posture: {posture} critical: {critical}");
foreach (var c in review.GetProperty("coverage_check").EnumerateArray())
if (!c.GetProperty("addressed").GetBoolean())
Console.WriteLine($"set aside: {c.GetProperty("id")} - {c.GetProperty("note")}");
foreach (var s in review.GetProperty("migration_steps").EnumerateArray().Take(3))
Console.WriteLine($"next: {s.GetProperty("step")} - {s.GetProperty("action")}");
if (posture == "breakage-risk" || critical > 0)
{
Console.Error.WriteLine($"BLOCKED: {review.GetProperty("verdict")}");
Environment.Exit(1);
}
Gate on posture and priority, not on the finding count — a
thorough review of a healthy integration can list a dozen improvements and still be
api-current. And keep the review artifact: review.json plus
migration_steps is the ticket description for whatever the gate just blocked.