iobroker.ai-usage 0.13.0 → 0.15.0

package/README.md

@@ -84,7 +84,7 @@ ai-usage.0.
 │   ├── limitReached           — this account is at 100 % (bool)
 │   ├── info.unreach           — account is not delivering (bool) — drives the connection icon
 │   ├── info.error             — why there is no data; empty while all is well, "Unknown" while the adapter itself has nothing to report
-│   ├── info.lastUpdate        — time of the last successful read
+│   ├── info.lastUpdate        — when the current values were fetched
 │   ├── limits.<window>.*      — percent, reset time and whether this window is the limit in force
 │   └── credits.*              — where the provider reports a balance
 └── <name>-api                 — one node per key-based account
@@ -100,9 +100,14 @@ the reset time simply empties while no window is running, and a window or model
 tree only when the provider stops reporting it entirely.
 
 **The connection icon** sits next to each account, green while it delivers. A throttle keeps it
-green — the last values stay valid while the adapter waits. A rejected sign-in or a broken service
-switch it off at once, an unreachable service after three attempts, so a hiccup does not make it
-flap. `info.error` names the cause whenever the provider gave one.
+green — the last values stay valid while the adapter waits. A rejected sign-in, a broken service or
+an answer that cannot be processed switch it off at once, an unreachable service after three
+attempts, so a hiccup does not make it flap. `info.error` names the cause whenever the provider gave
+one, in the provider's own words where it sent any.
+
+**Signing out clears that account's alarms.** Its measured values stay in the tree, but `warning`,
+`limitReached` and every total that counts them drop it — an account nobody watches must not keep an
+automation waiting.
 
 **Which window is in force** is shown per window: with Claude the provider says so itself, elsewhere it
 is the window that speaks for the account. It tells you what you will run into next — a model window
@@ -148,9 +153,36 @@ so instead of pretending to be connected; signing in again is all it takes.
 
 <!--
     Placeholder for the next version (at the beginning of the line):
-    ### **WORK IN PROGRESS**
 -->
 
+### 0.15.0 (2026-09-16)
+
+- Fixed: Model channels of an organisation account no longer vanish at the turn of a month — a model with no usage yet was deleted with its history and re-created on its next use
+- Fixed: Stopping the instance right after it started no longer leaves the accounts showing as connected while the instance is switched off
+- Fixed: Failures that reached the log, the `info.error` datapoint and Sentry as `[object Object]` now name the actual error
+- Improved: A provider answer that keeps growing can no longer push the adapter towards running out of memory — it is cut off and reported as a service fault
+
+The month-boundary fix concerns OpenAI organisation accounts, which have no real account here; it is
+covered by tests and by the counter-test that limit windows are still cleaned up.
+
+### 0.14.0 (2026-09-15)
+
+- Fixed: A failed write of the token file after a refresh lost the sign-in for good — the provider had already rotated them, so the next poll reported a rejected sign-in
+- Fixed: Signing out no longer comes undone by itself — a sign-out that landed during a background token renewal could leave the account signed in
+- Fixed: The last-update stamp moved forward on a tolerated connection failure, dating values the round had never fetched
+- Fixed: An answer the adapter cannot process is reported as a service fault at once, instead of claiming for three rounds that the service is unreachable
+- Fixed: A failed cleanup of vanished windows or models no longer discards the round — the values were in the tree, but the account called them unstored and the totals froze
+- Fixed: A connection failure counter that a throttle or a rejected sign-in had interrupted no longer adds up to "not reachable"
+- Fixed: An account you signed out of drops its warning and limit alarms and leaves the adapter-wide totals — its measured values stay in the tree
+- Fixed: The reset time of the Claude session and week windows is filled from the plan-wide block when the window entry itself carries none
+- Improved: Window reset times, the next voucher expiry and the credit ceiling are written only when they change — announced facts, not measurements, so their timestamp stops moving every poll
+- Improved: Where a provider sends a reason of its own, `info.error` now says it ("invalid API key") instead of a bare status number
+- Improved: An access token the provider invalidated early is refreshed once and the request repeated, instead of reporting a rejected sign-in until it would have expired
+
+Only the Claude subscription runs against a real account here. The token-file fix, the early-refresh
+retry and the sign-out behaviour are covered by tests but were not seen on a real ChatGPT, Google,
+OpenRouter, DeepSeek, OpenAI or Anthropic account.
+
 ### 0.13.0 (2026-09-12)
 
 - Fixed: The costs of an Anthropic organisation account were a hundred times too high — the provider counts them in cents, the adapter read them as dollars
@@ -192,27 +224,6 @@ so instead of pretending to be connected; signing in again is all it takes.
 - Fixed: A per-model folder is now named in your ioBroker language as well, instead of carrying the provider's bare model identifier as its only name
 - New: The datapoints whose meaning is not obvious from their name now carry a short explanation in eleven languages, shown in the object tree
 
-### 0.11.0 (2026-09-05)
-
-- Fixed: Signing in from the instance settings works again — a leftover setting from an earlier version had silently closed the adapter's message channel, so none of the three flows reached it
-- Fixed: A subscription whose stored sign-in was rejected no longer claims to be signed in — the row now offers the sign-in again instead of showing a green check next to an error
-- Fixed: The status badge of an account no longer blanks out for a moment when a single status read is missed — a hiccup in the settings page is not an account without a status
-- Fixed: A stored credential whose name sorts high in the alphabet is no longer missing from the account list in the instance settings
-- Fixed: The settings page falls back to English for a browser language the adapter does not ship, instead of passing that language on unchecked
-- Improved: All object names are now available in eleven languages instead of English only, and a renamed object reaches installations that already exist
-- Improved: ChatGPT usage is read with the identity that endpoint expects, the way the Claude query already did — fewer rejected requests on that account
-- Improved: Monthly cost reports can no longer be cut short in silence — a report that does not fit is reported in the log instead of producing a figure that is too low
-- Changed: "Highest account utilisation" says what it always measured — the fullest limit window **or** the account's remaining budget
-
-### 0.10.0 (2026-09-01)
-
-- Fixed: The reset-time datapoint of a limit window no longer disappears and reappears — it stays and simply empties while no window is running
-- Fixed: The settings page no longer shows the sign-in screen to a signed-in account, and its rows load without waiting for the credential storage scan
-- Improved: Claude usage is read with far fewer rejections — the query now identifies itself the way the endpoint expects
-- Changed: New Claude sign-ins request only the profile permission — the stored access can no longer create API keys or run models
-- New: ChatGPT accounts show their purchasable limit-reset credits — how many are available and when the next one expires
-- Improved: An unreadable provider answer is now reported as a service fault instead of a missing connection
-
 [Older changelogs can be found there](CHANGELOG_OLD.md)
 
 ## Support

package/admin/i18n/de.json

@@ -51,7 +51,6 @@
   "nameModels": "Verbrauch je Modell",
   "nameModel": "Modell %s",
   "nameModelTokens": "%s Token heute",
-  "nameModelCosts": "%s Kosten heute",
   "nameAvailable": "Guthaben reicht für Anfragen",
   "nameWindowSession": "Sitzung (5 Std.)",
   "nameWindowWeek": "Woche (alle Modelle)",

package/admin/i18n/en.json

@@ -51,7 +51,6 @@
   "nameModels": "Per-model usage",
   "nameModel": "Model %s",
   "nameModelTokens": "%s tokens today",
-  "nameModelCosts": "%s costs today",
   "nameAvailable": "Balance sufficient for calls",
   "nameWindowSession": "Session (5 h)",
   "nameWindowWeek": "Week (all models)",

package/admin/i18n/es.json

@@ -51,7 +51,6 @@
   "nameModels": "Uso por modelo",
   "nameModel": "Modelo %s",
   "nameModelTokens": "%s tokens de hoy",
-  "nameModelCosts": "%s costes de hoy",
   "nameAvailable": "Saldo suficiente para las llamadas",
   "nameWindowSession": "Sesión (5 h)",
   "nameWindowWeek": "Semana (todos los modelos)",

package/admin/i18n/fr.json

@@ -51,7 +51,6 @@
   "nameModels": "Utilisation par modèle",
   "nameModel": "Modèle %s",
   "nameModelTokens": "%s jetons aujourd'hui",
-  "nameModelCosts": "%s coûts aujourd'hui",
   "nameAvailable": "Solde suffisant pour les appels",
   "nameWindowSession": "Session (5 h)",
   "nameWindowWeek": "Semaine (tous les modèles)",

package/admin/i18n/it.json

@@ -51,7 +51,6 @@
   "nameModels": "Utilizzo per modello",
   "nameModel": "Modello %s",
   "nameModelTokens": "%s token di oggi",
-  "nameModelCosts": "%s costi di oggi",
   "nameAvailable": "Saldo sufficiente per le chiamate",
   "nameWindowSession": "Sessione (5 h)",
   "nameWindowWeek": "Settimana (tutti i modelli)",

package/admin/i18n/nl.json

@@ -51,7 +51,6 @@
   "nameModels": "Verbruik per model",
   "nameModel": "Model %s",
   "nameModelTokens": "%s tokens vandaag",
-  "nameModelCosts": "%s kosten vandaag",
   "nameAvailable": "Tegoed voldoende voor aanvragen",
   "nameWindowSession": "Sessie (5 u)",
   "nameWindowWeek": "Week (alle modellen)",

package/admin/i18n/pl.json

@@ -51,7 +51,6 @@
   "nameModels": "Zużycie na model",
   "nameModel": "Model %s",
   "nameModelTokens": "%s tokenów dzisiaj",
-  "nameModelCosts": "%s koszty dzisiaj",
   "nameAvailable": "Środki wystarczają na zapytania",
   "nameWindowSession": "Sesja (5 godz.)",
   "nameWindowWeek": "Tydzień (wszystkie modele)",

package/admin/i18n/pt.json

@@ -51,7 +51,6 @@
   "nameModels": "Utilização por modelo",
   "nameModel": "Modelo %s",
   "nameModelTokens": "%s tokens hoje",
-  "nameModelCosts": "%s custos hoje",
   "nameAvailable": "Saldo suficiente para chamadas",
   "nameWindowSession": "Sessão (5 h)",
   "nameWindowWeek": "Semana (todos os modelos)",

package/admin/i18n/ru.json

@@ -51,7 +51,6 @@
   "nameModels": "Использование по моделям",
   "nameModel": "Модель %s",
   "nameModelTokens": "%s токенов сегодня",
-  "nameModelCosts": "%s расходы сегодня",
   "nameAvailable": "Баланса хватает для запросов",
   "nameWindowSession": "Сессия (5 ч)",
   "nameWindowWeek": "Неделя (все модели)",

package/admin/i18n/uk.json

@@ -51,7 +51,6 @@
   "nameModels": "Використання за моделями",
   "nameModel": "Модель %s",
   "nameModelTokens": "%s токенів сьогодні",
-  "nameModelCosts": "%s витрати сьогодні",
   "nameAvailable": "Балансу достатньо для запитів",
   "nameWindowSession": "Сесія (5 год)",
   "nameWindowWeek": "Тиждень (усі моделі)",

package/admin/i18n/zh-cn.json

@@ -51,7 +51,6 @@
   "nameModels": "各模型用量",
   "nameModel": "模型 %s",
   "nameModelTokens": "%s 今日 Token",
-  "nameModelCosts": "%s 今日费用",
   "nameAvailable": "余额足以发起调用",
   "nameWindowSession": "会话（5 小时）",
   "nameWindowWeek": "一周（所有模型）",

package/build/lib/error-text.js

@@ -0,0 +1,48 @@
+"use strict";
+var __defProp = Object.defineProperty;
+var __getOwnPropDesc = Object.getOwnPropertyDescriptor;
+var __getOwnPropNames = Object.getOwnPropertyNames;
+var __hasOwnProp = Object.prototype.hasOwnProperty;
+var __export = (target, all) => {
+  for (var name in all)
+    __defProp(target, name, { get: all[name], enumerable: true });
+};
+var __copyProps = (to, from, except, desc) => {
+  if (from && typeof from === "object" || typeof from === "function") {
+    for (let key of __getOwnPropNames(from))
+      if (!__hasOwnProp.call(to, key) && key !== except)
+        __defProp(to, key, { get: () => from[key], enumerable: !(desc = __getOwnPropDesc(from, key)) || desc.enumerable });
+  }
+  return to;
+};
+var __toCommonJS = (mod) => __copyProps(__defProp({}, "__esModule", { value: true }), mod);
+var error_text_exports = {};
+__export(error_text_exports, {
+  errorText: () => errorText
+});
+module.exports = __toCommonJS(error_text_exports);
+const MAX_OBJECT_CHARS = 200;
+function errorText(err) {
+  if (err instanceof Error) {
+    return err.message || err.name || "Error";
+  }
+  if (typeof err === "string") {
+    return err;
+  }
+  if (err === null || err === void 0 || typeof err !== "object") {
+    return String(err);
+  }
+  let json;
+  try {
+    json = JSON.stringify(err);
+  } catch {
+    json = void 0;
+  }
+  const text = json != null ? json : Object.prototype.toString.call(err);
+  return text.length > MAX_OBJECT_CHARS ? `${text.slice(0, MAX_OBJECT_CHARS)}\u2026` : text;
+}
+// Annotate the CommonJS export names for ESM import in node:
+0 && (module.exports = {
+  errorText
+});
+//# sourceMappingURL=error-text.js.map

package/build/lib/error-text.js.map

@@ -0,0 +1,7 @@
+{
+  "version": 3,
+  "sources": ["../../src/lib/error-text.ts"],
+  "sourcesContent": ["/**\n * One readable line for anything a `catch` can hand over.\n *\n * Deliberately without imports: every layer uses it, including `http.ts`, which\n * sits below the helper modules.\n */\n\n/** Longest text a stringified object may contribute before it is cut. */\nconst MAX_OBJECT_CHARS = 200;\n\n/**\n * Turn any thrown value into text a user can read.\n *\n * JavaScript lets code throw anything, and the inline\n * `e instanceof Error ? e.message : String(e)` this replaces rendered every plain\n * object as `[object Object]` \u2014 a rejected `{ code: \"ECONNRESET\" }` or an HTTP\n * client's error object reached the log and Sentry with nothing in it.\n *\n * The object branch is the point of the helper; `String()` already covers strings,\n * numbers and symbols. `JSON.stringify` is guarded twice because it is hostile in\n * exactly the situation this runs in: it THROWS on a circular structure (an error\n * carrying the response it came from) and RETURNS `undefined` for a value it\n * cannot represent at all.\n *\n * @param err the caught value\n * @returns a single-line description, never empty\n */\nexport function errorText(err: unknown): string {\n  if (err instanceof Error) {\n    // `message` can be empty on a hand-built error \u2014 the name still says something.\n    return err.message || err.name || \"Error\";\n  }\n  if (typeof err === \"string\") {\n    return err;\n  }\n  if (err === null || err === undefined || typeof err !== \"object\") {\n    // Numbers, booleans, symbols, bigint: `String()` is the readable form.\n    return String(err);\n  }\n  let json: string | undefined;\n  try {\n    json = JSON.stringify(err);\n  } catch {\n    // Circular, or a getter that throws \u2014 fall through to the tag below.\n    json = undefined;\n  }\n  const text = json ?? Object.prototype.toString.call(err);\n  return text.length > MAX_OBJECT_CHARS ? `${text.slice(0, MAX_OBJECT_CHARS)}\u2026` : text;\n}\n"],
+  "mappings": ";;;;;;;;;;;;;;;;;;AAAA;AAAA;AAAA;AAAA;AAAA;AAQA,MAAM,mBAAmB;AAmBlB,SAAS,UAAU,KAAsB;AAC9C,MAAI,eAAe,OAAO;AAExB,WAAO,IAAI,WAAW,IAAI,QAAQ;AAAA,EACpC;AACA,MAAI,OAAO,QAAQ,UAAU;AAC3B,WAAO;AAAA,EACT;AACA,MAAI,QAAQ,QAAQ,QAAQ,UAAa,OAAO,QAAQ,UAAU;AAEhE,WAAO,OAAO,GAAG;AAAA,EACnB;AACA,MAAI;AACJ,MAAI;AACF,WAAO,KAAK,UAAU,GAAG;AAAA,EAC3B,QAAQ;AAEN,WAAO;AAAA,EACT;AACA,QAAM,OAAO,sBAAQ,OAAO,UAAU,SAAS,KAAK,GAAG;AACvD,SAAO,KAAK,SAAS,mBAAmB,GAAG,KAAK,MAAM,GAAG,gBAAgB,CAAC,WAAM;AAClF;",
+  "names": []
+}

package/build/lib/http.js

@@ -23,29 +23,90 @@ __export(http_exports, {
   postJson: () => postJson
 });
 module.exports = __toCommonJS(http_exports);
+var import_error_text = require("./error-text");
 var import_provider = require("./provider");
 const REQUEST_TIMEOUT_MS = 15e3;
+const MAX_BODY_BYTES = 8 * 1024 * 1024;
+async function readCappedText(response) {
+  if (!response.body) {
+    return "";
+  }
+  const reader = response.body.getReader();
+  const decoder = new TextDecoder();
+  let text = "";
+  let bytes = 0;
+  try {
+    for (; ; ) {
+      const { done, value } = await reader.read();
+      if (done) {
+        break;
+      }
+      if (!value) {
+        continue;
+      }
+      bytes += value.byteLength;
+      if (bytes > MAX_BODY_BYTES) {
+        await reader.cancel();
+        throw new import_provider.FetchError("service", `response body exceeds ${MAX_BODY_BYTES} bytes`);
+      }
+      text += decoder.decode(value, { stream: true });
+    }
+  } finally {
+    reader.releaseLock();
+  }
+  return text + decoder.decode();
+}
 async function request(url, init, authOn400 = false) {
   let response;
   try {
     response = await fetch(url, { ...init, signal: AbortSignal.timeout(REQUEST_TIMEOUT_MS) });
   } catch (e) {
-    throw new import_provider.FetchError("network", e instanceof Error ? e.message : String(e));
-  }
-  if (response.status === 401 || response.status === 403 || authOn400 && response.status === 400) {
-    throw new import_provider.FetchError("auth", `HTTP ${response.status}`);
-  }
-  if (response.status === 429) {
-    throw new import_provider.FetchError("rate-limit", "HTTP 429");
+    throw new import_provider.FetchError("network", (0, import_error_text.errorText)(e));
   }
   if (!response.ok) {
-    throw new import_provider.FetchError("service", `HTTP ${response.status}`);
+    const detail = await errorDetail(response);
+    if (response.status === 401 || response.status === 403 || authOn400 && response.status === 400) {
+      throw new import_provider.FetchError("auth", `HTTP ${response.status}${detail}`);
+    }
+    if (response.status === 429) {
+      throw new import_provider.FetchError("rate-limit", `HTTP 429${detail}`);
+    }
+    throw new import_provider.FetchError("service", `HTTP ${response.status}${detail}`);
   }
+  let text;
   try {
-    return await response.json();
+    text = await readCappedText(response);
   } catch (e) {
-    throw new import_provider.FetchError("service", `invalid JSON: ${e instanceof Error ? e.message : String(e)}`);
+    throw e instanceof import_provider.FetchError ? e : new import_provider.FetchError("service", `unreadable body: ${(0, import_error_text.errorText)(e)}`);
+  }
+  try {
+    return JSON.parse(text);
+  } catch (e) {
+    throw new import_provider.FetchError("service", `invalid JSON: ${(0, import_error_text.errorText)(e)}`);
+  }
+}
+const MAX_DETAIL_CHARS = 200;
+async function errorDetail(response) {
+  var _a, _b;
+  let text;
+  try {
+    text = await readCappedText(response);
+  } catch {
+    return "";
+  }
+  let message;
+  try {
+    const body = JSON.parse(text);
+    const error = body.error;
+    message = typeof error === "string" ? error : (_b = (_a = error == null ? void 0 : error.message) != null ? _a : body.message) != null ? _b : void 0;
+  } catch {
+    message = text.trim().length > 0 && text.trim().length <= MAX_DETAIL_CHARS ? text.trim() : void 0;
+  }
+  if (typeof message !== "string" || message.trim().length === 0) {
+    return "";
   }
+  const trimmed = message.trim();
+  return ` \u2014 ${trimmed.length > MAX_DETAIL_CHARS ? `${trimmed.slice(0, MAX_DETAIL_CHARS)}\u2026` : trimmed}`;
 }
 async function getJson(url, headers) {
   return request(url, { headers });

package/build/lib/http.js.map

@@ -1,7 +1,7 @@
 {
   "version": 3,
   "sources": ["../../src/lib/http.ts"],
-  "sourcesContent": ["import { FetchError } from \"./provider\";\n\n/** Per-request timeout (ms). */\nconst REQUEST_TIMEOUT_MS = 15000;\n\n/** The JSON-GET seam the provider modules use \u2014 injectable for tests. */\nexport type JsonFetch = (url: string, headers: Record<string, string>) => Promise<unknown>;\n\n/**\n * Per-call options of the two POST seams.\n *\n * `authOn400` used to be baked into `postJson`/`postForm`, which made EVERY post\n * read a 400 as a rejected sign-in. That is right for the OAuth token endpoints\n * and wrong everywhere else: the ChatGPT device-code poll takes an auth failure\n * as \"the user has not confirmed yet\" and would have waited out the whole\n * fifteen minutes on a 400, and Google's Code-Assist call skipped its second\n * host because it thought the sign-in was gone. The flag belongs at the call.\n */\nexport interface PostOptions {\n  /** Extra request headers. */\n  headers?: Record<string, string>;\n  /** True only for OAuth token endpoints, which answer a dead code or refresh token with 400. */\n  authOn400?: boolean;\n}\n\n/** The JSON-POST seam \u2014 one definition for every provider module. */\nexport type JsonPost = (url: string, body: Record<string, unknown>, options?: PostOptions) => Promise<unknown>;\n\n/** The form-POST seam (OAuth code redemption). */\nexport type FormPost = (url: string, form: Record<string, string>, options?: PostOptions) => Promise<unknown>;\n\n/**\n * Run one request and turn its outcome into the shared failure classification:\n * 401/403 (and 400 where the provider answers a rejected grant that way) become an\n * auth error, 429 a rate-limit error, any other bad status or unparsable body a\n * SERVICE error (the service answered and is broken), and only a throw \u2014 refused\n * connection, DNS failure, timeout \u2014 a network error. The poll engine turns that\n * split into \"the AI service is down\" versus \"this host has no connection\".\n *\n * @param url the request URL\n * @param init the request options (method, headers, body)\n * @param authOn400 true when a 400 means a rejected grant rather than a service fault\n * @returns the parsed JSON body\n */\nasync function request(url: string, init: RequestInit, authOn400 = false): Promise<unknown> {\n  let response: Response;\n  try {\n    response = await fetch(url, { ...init, signal: AbortSignal.timeout(REQUEST_TIMEOUT_MS) });\n  } catch (e) {\n    throw new FetchError(\"network\", e instanceof Error ? e.message : String(e));\n  }\n  if (response.status === 401 || response.status === 403 || (authOn400 && response.status === 400)) {\n    throw new FetchError(\"auth\", `HTTP ${response.status}`);\n  }\n  if (response.status === 429) {\n    throw new FetchError(\"rate-limit\", \"HTTP 429\");\n  }\n  if (!response.ok) {\n    // 5xx = the service answered and is broken; anything else unexpected is treated\n    // the same way, because the service DID answer \u2014 only a throw above means we\n    // never reached it.\n    throw new FetchError(\"service\", `HTTP ${response.status}`);\n  }\n  try {\n    return await response.json();\n  } catch (e) {\n    throw new FetchError(\"service\", `invalid JSON: ${e instanceof Error ? e.message : String(e)}`);\n  }\n}\n\n/**\n * GET a JSON document.\n *\n * @param url the request URL\n * @param headers request headers (Authorization etc.)\n * @returns the parsed JSON body\n */\nexport async function getJson(url: string, headers: Record<string, string>): Promise<unknown> {\n  return request(url, { headers });\n}\n\n/**\n * POST a JSON document.\n *\n * @param url the request URL\n * @param body the JSON body\n * @param options extra headers, and whether a 400 means a rejected grant\n * @returns the parsed JSON response\n */\nexport async function postJson(\n  url: string,\n  body: Record<string, unknown>,\n  options: PostOptions = {},\n): Promise<unknown> {\n  return request(\n    url,\n    {\n      method: \"POST\",\n      headers: { \"Content-Type\": \"application/json\", ...options.headers },\n      body: JSON.stringify(body),\n    },\n    options.authOn400 === true,\n  );\n}\n\n/**\n * POST a form-encoded body and return the parsed JSON answer.\n *\n * OAuth code redemption uses form encoding while token refresh often uses JSON \u2014\n * ChatGPT/Codex needs BOTH, so the two shapes are separate helpers rather than one\n * guessing wrapper.\n *\n * @param url the request URL\n * @param form the form fields\n * @param options extra headers, and whether a 400 means a rejected grant\n * @returns the parsed JSON body\n */\nexport async function postForm(url: string, form: Record<string, string>, options: PostOptions = {}): Promise<unknown> {\n  return request(\n    url,\n    {\n      method: \"POST\",\n      headers: { \"Content-Type\": \"application/x-www-form-urlencoded\", ...options.headers },\n      body: new URLSearchParams(form).toString(),\n    },\n    options.authOn400 === true,\n  );\n}\n"],
-  "mappings": ";;;;;;;;;;;;;;;;;;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA,sBAA2B;AAG3B,MAAM,qBAAqB;AAyC3B,eAAe,QAAQ,KAAa,MAAmB,YAAY,OAAyB;AAC1F,MAAI;AACJ,MAAI;AACF,eAAW,MAAM,MAAM,KAAK,EAAE,GAAG,MAAM,QAAQ,YAAY,QAAQ,kBAAkB,EAAE,CAAC;AAAA,EAC1F,SAAS,GAAG;AACV,UAAM,IAAI,2BAAW,WAAW,aAAa,QAAQ,EAAE,UAAU,OAAO,CAAC,CAAC;AAAA,EAC5E;AACA,MAAI,SAAS,WAAW,OAAO,SAAS,WAAW,OAAQ,aAAa,SAAS,WAAW,KAAM;AAChG,UAAM,IAAI,2BAAW,QAAQ,QAAQ,SAAS,MAAM,EAAE;AAAA,EACxD;AACA,MAAI,SAAS,WAAW,KAAK;AAC3B,UAAM,IAAI,2BAAW,cAAc,UAAU;AAAA,EAC/C;AACA,MAAI,CAAC,SAAS,IAAI;AAIhB,UAAM,IAAI,2BAAW,WAAW,QAAQ,SAAS,MAAM,EAAE;AAAA,EAC3D;AACA,MAAI;AACF,WAAO,MAAM,SAAS,KAAK;AAAA,EAC7B,SAAS,GAAG;AACV,UAAM,IAAI,2BAAW,WAAW,iBAAiB,aAAa,QAAQ,EAAE,UAAU,OAAO,CAAC,CAAC,EAAE;AAAA,EAC/F;AACF;AASA,eAAsB,QAAQ,KAAa,SAAmD;AAC5F,SAAO,QAAQ,KAAK,EAAE,QAAQ,CAAC;AACjC;AAUA,eAAsB,SACpB,KACA,MACA,UAAuB,CAAC,GACN;AAClB,SAAO;AAAA,IACL;AAAA,IACA;AAAA,MACE,QAAQ;AAAA,MACR,SAAS,EAAE,gBAAgB,oBAAoB,GAAG,QAAQ,QAAQ;AAAA,MAClE,MAAM,KAAK,UAAU,IAAI;AAAA,IAC3B;AAAA,IACA,QAAQ,cAAc;AAAA,EACxB;AACF;AAcA,eAAsB,SAAS,KAAa,MAA8B,UAAuB,CAAC,GAAqB;AACrH,SAAO;AAAA,IACL;AAAA,IACA;AAAA,MACE,QAAQ;AAAA,MACR,SAAS,EAAE,gBAAgB,qCAAqC,GAAG,QAAQ,QAAQ;AAAA,MACnF,MAAM,IAAI,gBAAgB,IAAI,EAAE,SAAS;AAAA,IAC3C;AAAA,IACA,QAAQ,cAAc;AAAA,EACxB;AACF;",
+  "sourcesContent": ["import { errorText } from \"./error-text\";\nimport { FetchError } from \"./provider\";\n\n/** Per-request timeout (ms). */\nconst REQUEST_TIMEOUT_MS = 15000;\n\n/**\n * Largest response body this adapter will hold in memory (bytes).\n *\n * Generous on purpose: the biggest answer any provider sends is a month of daily\n * cost buckets grouped by model, which is orders of magnitude below this. The cap\n * is not a budget, it is a backstop.\n */\nconst MAX_BODY_BYTES = 8 * 1024 * 1024;\n\n/**\n * Read a response body as text, refusing to grow past {@link MAX_BODY_BYTES}.\n *\n * The request timeout bounds how LONG a body may take, not how BIG it may get \u2014 on\n * a fast link fifteen seconds is a lot of memory, and this runs in a process that\n * stays up for months. Counted while reading rather than from `Content-Length`: a\n * chunked answer carries no length at all, and a declared one is the server's claim,\n * not a measurement.\n *\n * @param response the response to read\n * @returns the decoded body\n * @throws {FetchError} `service` once the body passes the cap\n */\nasync function readCappedText(response: Response): Promise<string> {\n  if (!response.body) {\n    return \"\";\n  }\n  const reader = response.body.getReader();\n  const decoder = new TextDecoder();\n  let text = \"\";\n  let bytes = 0;\n  try {\n    for (;;) {\n      const { done, value } = await reader.read();\n      if (done) {\n        break;\n      }\n      if (!value) {\n        continue;\n      }\n      bytes += value.byteLength;\n      if (bytes > MAX_BODY_BYTES) {\n        // Stop the transfer instead of draining a body we have already refused.\n        await reader.cancel();\n        throw new FetchError(\"service\", `response body exceeds ${MAX_BODY_BYTES} bytes`);\n      }\n      text += decoder.decode(value, { stream: true });\n    }\n  } finally {\n    reader.releaseLock();\n  }\n  return text + decoder.decode();\n}\n\n/** The JSON-GET seam the provider modules use \u2014 injectable for tests. */\nexport type JsonFetch = (url: string, headers: Record<string, string>) => Promise<unknown>;\n\n/**\n * Per-call options of the two POST seams.\n *\n * `authOn400` used to be baked into `postJson`/`postForm`, which made EVERY post\n * read a 400 as a rejected sign-in. That is right for the OAuth token endpoints\n * and wrong everywhere else: the ChatGPT device-code poll takes an auth failure\n * as \"the user has not confirmed yet\" and would have waited out the whole\n * fifteen minutes on a 400, and Google's Code-Assist call skipped its second\n * host because it thought the sign-in was gone. The flag belongs at the call.\n */\nexport interface PostOptions {\n  /** Extra request headers. */\n  headers?: Record<string, string>;\n  /** True only for OAuth token endpoints, which answer a dead code or refresh token with 400. */\n  authOn400?: boolean;\n}\n\n/** The JSON-POST seam \u2014 one definition for every provider module. */\nexport type JsonPost = (url: string, body: Record<string, unknown>, options?: PostOptions) => Promise<unknown>;\n\n/** The form-POST seam (OAuth code redemption). */\nexport type FormPost = (url: string, form: Record<string, string>, options?: PostOptions) => Promise<unknown>;\n\n/**\n * Run one request and turn its outcome into the shared failure classification:\n * 401/403 (and 400 where the provider answers a rejected grant that way) become an\n * auth error, 429 a rate-limit error, any other bad status or unparsable body a\n * SERVICE error (the service answered and is broken), and only a throw \u2014 refused\n * connection, DNS failure, timeout \u2014 a network error. The poll engine turns that\n * split into \"the AI service is down\" versus \"this host has no connection\".\n *\n * @param url the request URL\n * @param init the request options (method, headers, body)\n * @param authOn400 true when a 400 means a rejected grant rather than a service fault\n * @returns the parsed JSON body\n */\nasync function request(url: string, init: RequestInit, authOn400 = false): Promise<unknown> {\n  let response: Response;\n  try {\n    response = await fetch(url, { ...init, signal: AbortSignal.timeout(REQUEST_TIMEOUT_MS) });\n  } catch (e) {\n    throw new FetchError(\"network\", errorText(e));\n  }\n  if (!response.ok) {\n    // The status alone reaches the user as `info.error`, and \"HTTP 401\" tells them\n    // nothing they can act on. OpenRouter, OpenAI and Anthropic all answer with\n    // `{ error: { message } }` \u2014 reading it turns the datapoint into \"invalid API\n    // key\". Best effort in the strictest sense: the status decides the class, the\n    // body only decorates the text, and a body that cannot be read changes nothing.\n    const detail = await errorDetail(response);\n    if (response.status === 401 || response.status === 403 || (authOn400 && response.status === 400)) {\n      throw new FetchError(\"auth\", `HTTP ${response.status}${detail}`);\n    }\n    if (response.status === 429) {\n      throw new FetchError(\"rate-limit\", `HTTP 429${detail}`);\n    }\n    // 5xx = the service answered and is broken; anything else unexpected is treated\n    // the same way, because the service DID answer \u2014 only a throw above means we\n    // never reached it.\n    throw new FetchError(\"service\", `HTTP ${response.status}${detail}`);\n  }\n  let text: string;\n  try {\n    text = await readCappedText(response);\n  } catch (e) {\n    // The cap's own verdict passes through unchanged; anything else here is a\n    // connection that died mid-body, which counts as a service fault exactly as an\n    // unreadable body always did.\n    throw e instanceof FetchError ? e : new FetchError(\"service\", `unreadable body: ${errorText(e)}`);\n  }\n  try {\n    return JSON.parse(text) as unknown;\n  } catch (e) {\n    throw new FetchError(\"service\", `invalid JSON: ${errorText(e)}`);\n  }\n}\n\n/** Longest provider message taken over into the error text. */\nconst MAX_DETAIL_CHARS = 200;\n\n/**\n * The provider's own words for a failed request, ready to append.\n *\n * Never throws and never rejects: a body that is missing, unreadable, not JSON or\n * shaped differently simply yields \"\" and the caller keeps the bare status. The\n * body of a failed response is consumed here either way, so nothing is left\n * dangling (measured 2026-09-12: the \"socket leak\" this used to be blamed on does\n * not exist).\n *\n * @param response the failed response\n * @returns \" \u2014 <message>\" or an empty string\n */\nasync function errorDetail(response: Response): Promise<string> {\n  let text: string;\n  try {\n    text = await readCappedText(response);\n  } catch {\n    // Unreadable, or an error page past the cap \u2014 the caller keeps the bare status.\n    return \"\";\n  }\n  let message: unknown;\n  try {\n    const body = JSON.parse(text) as { error?: unknown; message?: unknown };\n    const error = body.error;\n    message =\n      typeof error === \"string\" ? error : ((error as { message?: unknown })?.message ?? body.message ?? undefined);\n  } catch {\n    // Not JSON: a short plain-text body is still better than nothing, a long one\n    // (an HTML error page from a proxy) is noise.\n    message = text.trim().length > 0 && text.trim().length <= MAX_DETAIL_CHARS ? text.trim() : undefined;\n  }\n  if (typeof message !== \"string\" || message.trim().length === 0) {\n    return \"\";\n  }\n  const trimmed = message.trim();\n  return ` \u2014 ${trimmed.length > MAX_DETAIL_CHARS ? `${trimmed.slice(0, MAX_DETAIL_CHARS)}\u2026` : trimmed}`;\n}\n\n/**\n * GET a JSON document.\n *\n * @param url the request URL\n * @param headers request headers (Authorization etc.)\n * @returns the parsed JSON body\n */\nexport async function getJson(url: string, headers: Record<string, string>): Promise<unknown> {\n  return request(url, { headers });\n}\n\n/**\n * POST a JSON document.\n *\n * @param url the request URL\n * @param body the JSON body\n * @param options extra headers, and whether a 400 means a rejected grant\n * @returns the parsed JSON response\n */\nexport async function postJson(\n  url: string,\n  body: Record<string, unknown>,\n  options: PostOptions = {},\n): Promise<unknown> {\n  return request(\n    url,\n    {\n      method: \"POST\",\n      headers: { \"Content-Type\": \"application/json\", ...options.headers },\n      body: JSON.stringify(body),\n    },\n    options.authOn400 === true,\n  );\n}\n\n/**\n * POST a form-encoded body and return the parsed JSON answer.\n *\n * OAuth code redemption uses form encoding while token refresh often uses JSON \u2014\n * ChatGPT/Codex needs BOTH, so the two shapes are separate helpers rather than one\n * guessing wrapper.\n *\n * @param url the request URL\n * @param form the form fields\n * @param options extra headers, and whether a 400 means a rejected grant\n * @returns the parsed JSON body\n */\nexport async function postForm(url: string, form: Record<string, string>, options: PostOptions = {}): Promise<unknown> {\n  return request(\n    url,\n    {\n      method: \"POST\",\n      headers: { \"Content-Type\": \"application/x-www-form-urlencoded\", ...options.headers },\n      body: new URLSearchParams(form).toString(),\n    },\n    options.authOn400 === true,\n  );\n}\n"],
+  "mappings": ";;;;;;;;;;;;;;;;;;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA,wBAA0B;AAC1B,sBAA2B;AAG3B,MAAM,qBAAqB;AAS3B,MAAM,iBAAiB,IAAI,OAAO;AAelC,eAAe,eAAe,UAAqC;AACjE,MAAI,CAAC,SAAS,MAAM;AAClB,WAAO;AAAA,EACT;AACA,QAAM,SAAS,SAAS,KAAK,UAAU;AACvC,QAAM,UAAU,IAAI,YAAY;AAChC,MAAI,OAAO;AACX,MAAI,QAAQ;AACZ,MAAI;AACF,eAAS;AACP,YAAM,EAAE,MAAM,MAAM,IAAI,MAAM,OAAO,KAAK;AAC1C,UAAI,MAAM;AACR;AAAA,MACF;AACA,UAAI,CAAC,OAAO;AACV;AAAA,MACF;AACA,eAAS,MAAM;AACf,UAAI,QAAQ,gBAAgB;AAE1B,cAAM,OAAO,OAAO;AACpB,cAAM,IAAI,2BAAW,WAAW,yBAAyB,cAAc,QAAQ;AAAA,MACjF;AACA,cAAQ,QAAQ,OAAO,OAAO,EAAE,QAAQ,KAAK,CAAC;AAAA,IAChD;AAAA,EACF,UAAE;AACA,WAAO,YAAY;AAAA,EACrB;AACA,SAAO,OAAO,QAAQ,OAAO;AAC/B;AAyCA,eAAe,QAAQ,KAAa,MAAmB,YAAY,OAAyB;AAC1F,MAAI;AACJ,MAAI;AACF,eAAW,MAAM,MAAM,KAAK,EAAE,GAAG,MAAM,QAAQ,YAAY,QAAQ,kBAAkB,EAAE,CAAC;AAAA,EAC1F,SAAS,GAAG;AACV,UAAM,IAAI,2BAAW,eAAW,6BAAU,CAAC,CAAC;AAAA,EAC9C;AACA,MAAI,CAAC,SAAS,IAAI;AAMhB,UAAM,SAAS,MAAM,YAAY,QAAQ;AACzC,QAAI,SAAS,WAAW,OAAO,SAAS,WAAW,OAAQ,aAAa,SAAS,WAAW,KAAM;AAChG,YAAM,IAAI,2BAAW,QAAQ,QAAQ,SAAS,MAAM,GAAG,MAAM,EAAE;AAAA,IACjE;AACA,QAAI,SAAS,WAAW,KAAK;AAC3B,YAAM,IAAI,2BAAW,cAAc,WAAW,MAAM,EAAE;AAAA,IACxD;AAIA,UAAM,IAAI,2BAAW,WAAW,QAAQ,SAAS,MAAM,GAAG,MAAM,EAAE;AAAA,EACpE;AACA,MAAI;AACJ,MAAI;AACF,WAAO,MAAM,eAAe,QAAQ;AAAA,EACtC,SAAS,GAAG;AAIV,UAAM,aAAa,6BAAa,IAAI,IAAI,2BAAW,WAAW,wBAAoB,6BAAU,CAAC,CAAC,EAAE;AAAA,EAClG;AACA,MAAI;AACF,WAAO,KAAK,MAAM,IAAI;AAAA,EACxB,SAAS,GAAG;AACV,UAAM,IAAI,2BAAW,WAAW,qBAAiB,6BAAU,CAAC,CAAC,EAAE;AAAA,EACjE;AACF;AAGA,MAAM,mBAAmB;AAczB,eAAe,YAAY,UAAqC;AA1JhE;AA2JE,MAAI;AACJ,MAAI;AACF,WAAO,MAAM,eAAe,QAAQ;AAAA,EACtC,QAAQ;AAEN,WAAO;AAAA,EACT;AACA,MAAI;AACJ,MAAI;AACF,UAAM,OAAO,KAAK,MAAM,IAAI;AAC5B,UAAM,QAAQ,KAAK;AACnB,cACE,OAAO,UAAU,WAAW,SAAU,0CAAiC,YAAjC,YAA4C,KAAK,YAAjD,YAA4D;AAAA,EACtG,QAAQ;AAGN,cAAU,KAAK,KAAK,EAAE,SAAS,KAAK,KAAK,KAAK,EAAE,UAAU,mBAAmB,KAAK,KAAK,IAAI;AAAA,EAC7F;AACA,MAAI,OAAO,YAAY,YAAY,QAAQ,KAAK,EAAE,WAAW,GAAG;AAC9D,WAAO;AAAA,EACT;AACA,QAAM,UAAU,QAAQ,KAAK;AAC7B,SAAO,WAAM,QAAQ,SAAS,mBAAmB,GAAG,QAAQ,MAAM,GAAG,gBAAgB,CAAC,WAAM,OAAO;AACrG;AASA,eAAsB,QAAQ,KAAa,SAAmD;AAC5F,SAAO,QAAQ,KAAK,EAAE,QAAQ,CAAC;AACjC;AAUA,eAAsB,SACpB,KACA,MACA,UAAuB,CAAC,GACN;AAClB,SAAO;AAAA,IACL;AAAA,IACA;AAAA,MACE,QAAQ;AAAA,MACR,SAAS,EAAE,gBAAgB,oBAAoB,GAAG,QAAQ,QAAQ;AAAA,MAClE,MAAM,KAAK,UAAU,IAAI;AAAA,IAC3B;AAAA,IACA,QAAQ,cAAc;AAAA,EACxB;AACF;AAcA,eAAsB,SAAS,KAAa,MAA8B,UAAuB,CAAC,GAAqB;AACrH,SAAO;AAAA,IACL;AAAA,IACA;AAAA,MACE,QAAQ;AAAA,MACR,SAAS,EAAE,gBAAgB,qCAAqC,GAAG,QAAQ,QAAQ;AAAA,MACnF,MAAM,IAAI,gBAAgB,IAAI,EAAE,SAAS;AAAA,IAC3C;AAAA,IACA,QAAQ,cAAc;AAAA,EACxB;AACF;",
   "names": []
 }