Files
OmniRoute/open-sse/executors/mimocode.ts
Diego Rodrigues de Sa e Souza de60b4b171 Release v3.8.23
* chore(release): open v3.8.23 development cycle

* fix(anthropic): strip top_p when temperature is set to avoid 400 (#3691)

Integrated into release/v3.8.23

* fix(vertex): support Vertex AI Express-mode API keys (#3690)

Integrated into release/v3.8.23

* fix(stream): error on empty Claude SSE instead of synthetic success (#3689)

Integrated into release/v3.8.23

* fix(oauth): stop token-refresh invalidation loop + harden proxy resolution (#3692)

Integrated into release/v3.8.23

* docs: add FUNDING.yml and Support section to README (#3698)

Integrated into release/v3.8.23

* feat: gemini - handle known ratelimits (#3686)

Integrated into release/v3.8.23

* fix: stream combo fails over on empty content-filtered response (#3685) (#3702)

Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* fix(antigravity): preserve gemini-3.1-pro high/low budget tiers (#3696) (#3703)

Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>

* feat(auto-combo): add auto-updating model intelligence scoring (#3660)

Integrated into release/v3.8.23

* fix(gemini): context-mode fallback for signatureless tool calls (#3688) (#3704)

* chore(quality-gate): reconcile file-size baseline (27 files + providerLimits.ts) (#3705)

* feat(vertex): dynamic model discovery via Generative Language models API (#3712)

Integrated into release/v3.8.23. Vertex dynamic model discovery — surfaces image models (imagen-*, gemini-*-image), embeddings and audio from the live Generative Language catalog, with cached→static fallback and the shared parseGeminiModelsList helper. Validated: parser test 5/5, typecheck:core clean.

* fix(combo): gate reasoning token buffer (#3700)

Integrated into release/v3.8.23. Makes the #3588 reasoning token buffer safe and configurable: only inflates max_tokens when the model has a known, non-default output cap and the buffered value fits inside it; otherwise preserves/clamps the client limit. Adds the reasoningTokenBufferEnabled kill switch (default ON). Validated: combo-routing-engine 81/81, combo-config 25/25, combo-quality-validator-reasoning 12/12, phase1f 10/10, typecheck:core clean.

* refactor(#3501): god-component Phase 1g-1j — client 4062→3408 LOC (-654) (#3717)

Phase 1g-1j of #3501: client 4062→3408 LOC. Pure extraction (ProviderPlaygroundPanel, useCommandCodeAuth, useExternalLinkFlow+ExternalLinkModal, useAuthFileHandlers) + loadConnProxies ReferenceError fix + phase1f test path fix.

Co-authored-by: oyi77 <14921983+oyi77@users.noreply.github.com>

* refactor(#3501): god-component Phase 1k-1m — client 3408→2553 LOC (-855) (#3721)

Phase 1k-1m of #3501: client 3408→2553 LOC. Pure extraction (useModelImportHandlers+ImportProgressModal, useModelVisibilityHandlers, ProviderModelsSection).

Co-authored-by: oyi77 <14921983+oyi77@users.noreply.github.com>

* docs(changelog): restore #3590 bullet lost on the v3.8.20 release branch

The fix itself reached main pre-tag via cherry-pick #3591, but its changelog
bullet (commit e33fdd4ab) only ever existed on release/v3.8.20 after the
squash-merge. Restored under [3.8.20] per the 2026-06-12 release-branch
leftover audit (_tasks/release-audit/release-leftovers-audit-2026-06-12.md).

* fix(kiro): resolve quota for IAM Identity Center accounts missing a profileArn (#3722)

Integrated into release/v3.8.23

* refactor(#3501): god-component Phase 1n-1s — client 2553→1376 LOC (-1177) (#3725)

Phase 1n-1s of #3501: client 2553→1376 LOC. Pure extraction (ConnectionsListPanel, ConnectionsHeaderToolbar, ZedImportCard, BatchTestResultsModal, AdaptaTutorialModal, useApiKeySave + helpers).

Co-authored-by: oyi77 <14921983+oyi77@users.noreply.github.com>

* feat(model-lockout): settings UI, backend integration, error classification, and success-decay recovery (#3629)

Integrated into release/v3.8.23

* refactor(#3501): god-component Phase 1t — client 1376→781 LOC (≤800 TARGET REACHED ) (#3727)

Phase 1t of #3501: client 1376→781 LOC (≤800 reached). Original god-component 12,882→781 (−94%).

Co-authored-by: oyi77 <14921983+oyi77@users.noreply.github.com>

* fix: bundle @omniroute/opencode-plugin inside omniroute + add 'setup opencode' CLI command (#3726)

Integrated into release/v3.8.23

* feat(vertex): self-tracked USD spend since account added (#3724)

Integrated into release/v3.8.23

* fix(qwen-web): migrate to v2 chat API with full cookie-jar replay (#3288) (#3723)

Integrated into release/v3.8.23

* fix(sse): make safeLogEvents async — 'await' in a sync function broke every chatHelpers import

#3692 added a lazy 'await import(proxyEgress)' for egress-IP visibility inside
safeLogEvents, which is a sync function — an ES syntax error. It went unnoticed
because typecheck:core does not cover src/sse and no test in the merge gates
loaded chatHelpers via tsx; any consumer that did (chat-context-relay and
chat-route-coverage suites, integration harnesses) failed at module load with
'await can only be used inside an async function'.

safeLogEvents is fire-and-forget logging with an outer try/catch, so making it
async (and 'void'-ing the single chat.ts call site) preserves behavior exactly.

Validation: tests/unit/chat-context-relay.test.ts + chat-route-coverage.test.ts
went from failing-at-load to green (+14 tests destravados).

* fix(sse): remove cross-provider credential leak in emergency fallback + combo/proxy audit fixes (#3699)

Integrated into release/v3.8.23

* fix(executors): inject MiMoCode anti-abuse marker so free endpoint stops 403ing (#3728)

Integrated into release/v3.8.23

* fix(dashboard): repair "Test all models" — toast crash, status icons, auto-hide (#3729)

Integrated into release/v3.8.23

* chore(deps): bump actions/upload-artifact from 4 to 7 (#3735)

Integrated into release/v3.8.23 — aligns upload-artifact to v7 (already used across ci.yml).

* chore(deps): bump actions/cache from 4 to 5 (#3734)

Integrated into release/v3.8.23 — actions/cache v4→v5.

* chore(deps): bump actions/download-artifact from 4 to 8 (#3733)

Integrated into release/v3.8.23 — download-artifact v4→v8.

* feat(fallback): add OMNIROUTE_EMERGENCY_FALLBACK env switch (#3741)

Adds an OMNIROUTE_EMERGENCY_FALLBACK env switch to disable the emergency budget-exhaustion fallback (reroute to free nvidia/gpt-oss-120b). Default unchanged (enabled). Closes #3739, related #2879.

Integrated into release/v3.8.23.

* i18n: comprehensive zh-CN translation improvements (#3736)

Aligns zh-CN to en (hundreds of entries), translates batch-action labels + settings sidebar menu, adds categoryConfig/endpointTokenSaver keys, resolves __MISSING__ stubs. Sidebar/SidebarTab hardcoded strings replaced with t(). en.json purely additive (8 new sidebar.* keys, 0 removed); cli-i18n gate green.

Integrated into release/v3.8.23.

* chore(release): v3.8.23 — 2026-06-12

- CHANGELOG: complete v3.8.23 section (28 bullets, 27 commits)
- fix(webdav): resolve promise on writeStream finish, not req end — eliminates
  intermittent 500 on PUT update (writeStream may not have flushed at rename time)
- test(autoCombo): stub DB calls from PR #3660 in tieredRotation.test.ts to prevent
  5s timeout in vitest (getModelIntelligenceBySource DB init path)
- chore(env-sync): add XDG_DATA_HOME + OMNIROUTE_OPENCODE_PLUGIN_DIR to IGNORE_FROM_CODE
  allowlist (introduced by PR #3726 setup-open-code.mjs, not OmniRoute config vars)
- chore(cli): regenerated bin/cli/api-commands/*.mjs (7 new, 27 updated)

* fix(model-family): fallback lookup also tries bare model name with dots

getNextFamilyFallback normalized dots-to-hyphens ("gemini-3.1-pro-high" →
"gemini-3-1-pro-high") but MODEL_FAMILIES keys use the literal dot form. The
lookup always missed, returning null for any model whose dots are part of the
name rather than a version separator.

Fallback: try MODEL_FAMILIES[lookupKey] ?? MODEL_FAMILIES[bareModel] so both
naming conventions are covered. Fixes T30 test (pre-existing since v3.8.22).

* feat: expose API key cost drilldown + quota % used (#3742)

Adds all-time USD cost per API key in the API Key Manager, a per-key deep-link into the Cost Explorer (filtered + grouped by model), URL-param hydration of range/groupBy/apiKeyIds, and a '% used' quota display. Review adjustments: extracted URL-param parsers to a tested module (Rule #18), i18n'd the new strings (en + zh-CN), dropped the redundant webdav-handler entry already on release.

Integrated into release/v3.8.23.

* feat: add provider display modes — All / Configured / Compact (#3743)

Replaces the Providers page configured-only toggle with All/Configured/Compact display modes (Compact = flat deduped grid, no-auth last). Persists the preference and migrates the legacy localStorage key. Rebased onto release/v3.8.23.

Integrated into release/v3.8.23.

* fix(cache): scope semantic-cache signature to API key (#3740)

Adds the api_key_id dimension to generateSignature's SHA-256 hash so two callers with different API keys never receive each other's cached responses. Threads apiKeyId through checkSemanticCache + both write sites; migration 098 clears pre-existing key-less entries; unauthenticated requests stay isolated from keyed ones. 3 TDD tests.

Integrated into release/v3.8.23.

* fix(responses): apply OpenAI Responses API stream=false spec default (#3708)

resolveStreamFlag now applies the stream=false-when-omitted default for sourceFormat=openai-responses (same as the existing claude path), so spec-compliant /v1/responses upstreams that return JSON no longer fall through to the wildcard-Accept heuristic and trigger STREAM_EARLY_EOF / 502. Codex CLI (stream:true) and explicit text/event-stream clients unaffected.

Integrated into release/v3.8.23.

* chore(release): reconcile CI gates for v3.8.23

- file-size baseline: re-freeze 8 files grown by PRs #3742/#3743/#3740
  (cost drilldown, provider display modes, cache key isolation)
- ARCHITECTURE.md: update executor count 55→60 (check:docs-counts drift)
- .env.example: add OMNIROUTE_EMERGENCY_FALLBACK (#3741, env-doc-sync)
- CHANGELOG: add formatted bullets for #3742, #3743, #3708, #3740,
  model-family-fallback fix; remove duplicate raw ### Fixed section

* test: restore assert count to satisfy check:test-masking gate

Three test files had net assertion removals after behavior-changing PRs:
- chatcore-translation-paths: emergency fallback moved to routing layer
  (#3699) — add body error assertion + model-name guard
- executor-vertex-extended: non-JSON is now Express API key (#3690) —
  add projects/-path guard to the express-key URL test
- stream-utils: empty streams now emit error (#3685) — add code/message/
  status/completePayload guards to both passthrough and translate variants

All new assertions are meaningful (code enum value, 5xx range, non-empty
message, onComplete must-not-fire contract).

* fix(ci): move rtl-logical-classes test to ui/ so vitest:ui runner collects it

---------

Co-authored-by: Felipe Almeman <4226997+zhiru@users.noreply.github.com>
Co-authored-by: NOXX - Commiter <artur1992123@mail.ru>
Co-authored-by: Nick Sullivan <142708+TechNickAI@users.noreply.github.com>
Co-authored-by: Markus Hartung <mail@hartmark.se>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-authored-by: PizzaV <103120356+pizzav-xyz@users.noreply.github.com>
Co-authored-by: Randi <55005611+rdself@users.noreply.github.com>
Co-authored-by: oyi77 <14921983+oyi77@users.noreply.github.com>
Co-authored-by: Chewji <126886556+Chewji9875@users.noreply.github.com>
Co-authored-by: Hernan Javier Ardila Sanchez <hjasgr@gmail.com>
Co-authored-by: Felipe Sartori <felipesartori.ti@gmail.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Zois Pagoulatos <zpagoulatos@hotmail.com>
Co-authored-by: sdfsdfw2 <167810361+sdfsdfw2@users.noreply.github.com>
Co-authored-by: Witroch4 <witalo_rocha@hotmail.com>
2026-06-12 23:49:22 -03:00

452 lines
15 KiB
TypeScript

/**
* MiMoCode Executor — Free-tier Xiaomi MiMo models via bootstrap JWT auth.
*
* Implements the auth flow from the official MiMo-Code repository:
* https://github.com/XiaomiMiMo/MiMo-Code/blob/main/packages/opencode/src/plugin/mimo-free.ts
*
* 1. Generate device fingerprint from hostname + OS + arch + CPU + username
* 2. POST /api/free-ai/bootstrap with fingerprint → JWT
* 3. Use JWT as Bearer token for chat requests
* 4. Custom endpoint: /api/free-ai/openai/chat (not /v1/chat/completions)
* 5. Custom header: X-Mimo-Source: mimocode-cli-free
*
* Only the "mimo-auto" model is supported (1M context, 128K output).
* Supports multiple accounts: N fingerprints → N JWTs → round-robin with cooldown.
* On 429, account enters cooldown (exponential backoff). On 401/403, JWT is re-bootstrapped.
*/
import * as crypto from "node:crypto";
import * as os from "node:os";
import { BaseExecutor, type ExecuteInput, type ProviderCredentials } from "./base.ts";
const BOOTSTRAP_PATH = "/api/free-ai/bootstrap";
const CHAT_PATH = "/api/free-ai/openai/chat";
const JWT_REFRESH_BUFFER_MS = 5 * 60 * 1000;
const BOOTSTRAP_TIMEOUT_MS = 15_000;
const COOLDOWN_BASE_MS = 5_000;
const COOLDOWN_MAX_MS = 60_000;
const MIMO_SOURCE = "mimocode-cli-free";
/**
* Anti-abuse gate marker required by the Xiaomi free endpoint.
*
* `/api/free-ai/openai/chat` returns `403 "Illegal access"` unless the request body
* contains a recognized MiMoCode prompt signature as a substring inside a `system`-role
* message (verified empirically — headers, fingerprint, and JWT are not what is checked).
* This is the canonical MiMoCode agent opener the official CLI sends, and it is on the
* upstream allowlist. We inject it as a leading system message so user requests pass the
* gate. The string MUST stay byte-for-byte identical — the check is case-sensitive and
* truncations are rejected.
*/
export const MIMO_SYSTEM_MARKER =
"You are MiMoCode, an interactive CLI tool that helps users with software engineering tasks.";
/**
* Ensure the outgoing body carries the MiMoCode anti-abuse marker in a system message.
* Idempotent: if any system message already contains the marker, the body is returned
* unchanged. Bodies without a `messages` array are left untouched.
*/
function injectSystemMarker(body: Record<string, unknown>): Record<string, unknown> {
const messages = body.messages;
if (!Array.isArray(messages)) return body;
const hasMarker = messages.some(
(m) =>
m != null &&
typeof m === "object" &&
(m as { role?: unknown }).role === "system" &&
typeof (m as { content?: unknown }).content === "string" &&
(m as { content: string }).content.includes(MIMO_SYSTEM_MARKER)
);
if (hasMarker) return body;
return { ...body, messages: [{ role: "system", content: MIMO_SYSTEM_MARKER }, ...messages] };
}
const USER_AGENTS = [
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36",
"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36",
"Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36",
];
// ── Account State ──────────────────────────────────────────────────────────
interface AccountState {
fingerprint: string;
jwt: string;
expiresAt: number;
cooldownUntil: number;
consecutiveFails: number;
}
function parseJwtExp(jwt: string): number {
try {
const parts = jwt.split(".");
if (parts.length < 2) return Date.now() + 50 * 60 * 1000;
const payload = JSON.parse(Buffer.from(parts[1], "base64url").toString());
return (payload.exp ?? Math.floor(Date.now() / 1000) + 3000) * 1000;
} catch {
return Date.now() + 50 * 60 * 1000;
}
}
function isAccountReady(account: AccountState): boolean {
if (account.cooldownUntil > Date.now()) return false;
if (account.jwt && account.expiresAt - Date.now() > JWT_REFRESH_BUFFER_MS) return true;
return false;
}
// ── Fingerprint Generation ─────────────────────────────────────────────────
function getCpuModel(): string {
try {
const cpus = os.cpus();
if (cpus.length > 0 && cpus[0].model) return cpus[0].model.trim();
} catch {
/* ignore */
}
return "unknown-cpu";
}
export function generateFingerprint(seed?: string): string {
if (seed) return crypto.createHash("sha256").update(seed).digest("hex");
const hostname = os.hostname();
const platform = os.platform();
const arch = os.arch();
const cpu = getCpuModel();
let username = "unknown-user";
try {
username = os.userInfo().username;
} catch {
/* ignore */
}
return crypto
.createHash("sha256")
.update(`${hostname}|${platform}|${arch}|${cpu}|${username}`)
.digest("hex");
}
// ── Bootstrap ──────────────────────────────────────────────────────────────
const bootstrapInflight = new Map<string, Promise<{ jwt: string; expiresAt: number }>>();
async function bootstrapJwt(
baseUrl: string,
fingerprint: string,
signal?: AbortSignal | null
): Promise<{ jwt: string; expiresAt: number }> {
const existing = bootstrapInflight.get(fingerprint);
if (existing) return existing;
const url = `${baseUrl}${BOOTSTRAP_PATH}`;
const controller = new AbortController();
const timer = setTimeout(() => controller.abort(), BOOTSTRAP_TIMEOUT_MS);
const onSignal = signal ? () => controller.abort(signal.reason) : null;
if (signal && onSignal) signal.addEventListener("abort", onSignal, { once: true });
const promise = (async () => {
try {
const resp = await fetch(url, {
method: "POST",
headers: { "Content-Type": "application/json" },
body: JSON.stringify({ client: fingerprint }),
signal: controller.signal,
});
if (!resp.ok) {
const body = await resp.text().catch(() => "");
throw new Error(`Bootstrap failed: ${resp.status} ${body.slice(0, 200)}`);
}
const data = (await resp.json()) as { jwt?: string };
if (!data.jwt) throw new Error("Bootstrap response missing jwt field");
return { jwt: data.jwt, expiresAt: parseJwtExp(data.jwt) };
} finally {
clearTimeout(timer);
if (signal && onSignal) signal.removeEventListener("abort", onSignal);
bootstrapInflight.delete(fingerprint);
}
})();
bootstrapInflight.set(fingerprint, promise);
return promise;
}
// ── Model Rewriting ────────────────────────────────────────────────────────
function rewriteModelName(model: string): string {
const idx = model.lastIndexOf("/");
return idx >= 0 ? model.slice(idx + 1) : model;
}
// ── Executor ───────────────────────────────────────────────────────────────
export class MimocodeExecutor extends BaseExecutor {
private accounts: AccountState[] = [];
private nextAccountIdx = 0;
private baseUrl: string;
private static encoder = new TextEncoder();
constructor() {
super("mimocode", { format: "openai" });
this.baseUrl = this.getBaseUrls()[0] || "https://api.xiaomimimo.com";
this.accounts.push({
fingerprint: generateFingerprint(),
jwt: "",
expiresAt: 0,
cooldownUntil: 0,
consecutiveFails: 0,
});
}
private syncAccountsFromCredentials(credentials: ProviderCredentials): void {
const fingerprints = credentials?.providerSpecificData?.fingerprints;
if (!Array.isArray(fingerprints)) return;
const existing = new Set(this.accounts.map((a) => a.fingerprint));
for (const fp of fingerprints) {
if (typeof fp === "string" && !existing.has(fp)) {
this.accounts.push({
fingerprint: fp,
jwt: "",
expiresAt: 0,
cooldownUntil: 0,
consecutiveFails: 0,
});
existing.add(fp);
}
}
}
private async getJwtForAccount(
account: AccountState,
signal?: AbortSignal | null
): Promise<string> {
if (isAccountReady(account)) return account.jwt;
const result = await bootstrapJwt(this.baseUrl, account.fingerprint, signal);
account.jwt = result.jwt;
account.expiresAt = result.expiresAt;
return account.jwt;
}
private pickAccount(): AccountState {
for (let i = 0; i < this.accounts.length; i++) {
const idx = (this.nextAccountIdx + i) % this.accounts.length;
const acct = this.accounts[idx];
if (isAccountReady(acct)) {
this.nextAccountIdx = (idx + 1) % this.accounts.length;
return acct;
}
}
const fallbackIdx = this.nextAccountIdx % this.accounts.length;
this.nextAccountIdx = (this.nextAccountIdx + 1) % this.accounts.length;
return this.accounts[fallbackIdx];
}
private markCooldown(account: AccountState): void {
account.consecutiveFails++;
const backoff = Math.min(
COOLDOWN_BASE_MS * Math.pow(2, account.consecutiveFails - 1),
COOLDOWN_MAX_MS
);
account.cooldownUntil = Date.now() + backoff + Math.random() * 1000;
}
private markSuccess(account: AccountState): void {
account.consecutiveFails = 0;
}
buildUrl(
_model: string,
_stream: boolean,
_urlIndex = 0,
_credentials?: ProviderCredentials | null
): string {
return `${this.baseUrl.replace(/\/$/, "")}${CHAT_PATH}`;
}
buildHeaders(
_credentials: ProviderCredentials,
stream = true,
_clientHeaders?: Record<string, string> | null,
_model?: string
): Record<string, string> {
const headers: Record<string, string> = {
"Content-Type": "application/json",
"X-Mimo-Source": MIMO_SOURCE,
"User-Agent": USER_AGENTS[Math.floor(Math.random() * USER_AGENTS.length)],
};
if (stream) headers["Accept"] = "text/event-stream, application/json";
return headers;
}
transformRequest(
model: string,
body: unknown,
_stream: boolean,
_credentials?: ProviderCredentials | null
): unknown {
if (typeof body === "object" && body !== null) {
const withModel = { ...(body as Record<string, unknown>), model: rewriteModelName(model) };
return injectSystemMarker(withModel);
}
return body;
}
async testConnection(
_credentials: ProviderCredentials,
_signal?: AbortSignal | null,
log?: ExecuteInput["log"]
): Promise<boolean> {
try {
const account = this.accounts[0];
const jwt = await this.getJwtForAccount(account, _signal);
const resp = await fetch(this.buildUrl("mimo-auto", false), {
method: "POST",
headers: {
"Content-Type": "application/json",
Authorization: `Bearer ${jwt}`,
"X-Mimo-Source": MIMO_SOURCE,
},
body: JSON.stringify(
injectSystemMarker({
model: "mimo-auto",
messages: [{ role: "user", content: "ping" }],
stream: false,
})
),
signal: _signal ?? undefined,
});
return resp.status === 200;
} catch {
log?.warn?.("MIMOCODE", "testConnection network error");
return false;
}
}
async execute(input: ExecuteInput): Promise<{
response: Response;
url: string;
headers: Record<string, string>;
transformedBody: unknown;
}> {
const { model, stream, body, signal, log } = input;
const encoder = MimocodeExecutor.encoder;
if (signal?.aborted) {
return {
response: new Response(
encoder.encode(
JSON.stringify({
error: { message: "Request aborted", type: "abort", code: "ABORTED" },
})
),
{ status: 499, headers: { "Content-Type": "application/json" } }
),
url: this.buildUrl(model, stream),
headers: this.buildHeaders(input.credentials, stream),
transformedBody: body,
};
}
const url = this.buildUrl(model, stream);
const reqBody = this.transformRequest(model, body, stream, input.credentials);
this.syncAccountsFromCredentials(input.credentials);
// Try each account, skip cooldown ones
for (let attempt = 0; attempt < this.accounts.length; attempt++) {
const account = this.pickAccount();
try {
const jwt = await this.getJwtForAccount(account, signal);
const headers = this.buildHeaders(input.credentials, stream);
headers["Authorization"] = `Bearer ${jwt}`;
let resp = await fetch(url, {
method: "POST",
headers,
body: JSON.stringify(reqBody),
signal: signal ?? undefined,
});
// On auth failure, re-bootstrap this account and retry once
if (resp.status === 401 || resp.status === 403) {
log?.warn?.(
"MIMOCODE",
`Auth failed (${resp.status}) on account ${account.fingerprint.slice(0, 8)}`
);
account.jwt = "";
account.expiresAt = 0;
account.consecutiveFails = 0;
const freshJwt = await this.getJwtForAccount(account, signal);
headers["Authorization"] = `Bearer ${freshJwt}`;
resp = await fetch(url, {
method: "POST",
headers,
body: JSON.stringify(reqBody),
signal: signal ?? undefined,
});
}
if (resp.status === 429) {
this.markCooldown(account);
log?.warn?.(
"MIMOCODE",
`Rate limited on account ${account.fingerprint.slice(0, 8)}, trying next…`
);
continue;
}
this.markSuccess(account);
const respHeaders: Record<string, string> = {};
resp.headers.forEach((v, k) => {
respHeaders[k] = v;
});
return {
response: resp as unknown as Response,
url,
headers: respHeaders,
transformedBody: reqBody,
};
} catch (err) {
this.markCooldown(account);
if (attempt === this.accounts.length - 1) {
const msg = err instanceof Error ? err.message : String(err);
log?.error?.("MIMOCODE", `Executor error: ${msg}`);
return {
response: new Response(
encoder.encode(
JSON.stringify({
error: { message: msg, type: "upstream_error", code: "EXECUTOR_ERROR" },
})
),
{ status: 502, headers: { "Content-Type": "application/json" } }
),
url,
headers: this.buildHeaders(input.credentials, stream),
transformedBody: body,
};
}
}
}
return {
response: new Response(
encoder.encode(
JSON.stringify({
error: {
message: "All accounts exhausted",
type: "upstream_error",
code: "NO_ACCOUNTS",
},
})
),
{ status: 502, headers: { "Content-Type": "application/json" } }
),
url,
headers: this.buildHeaders(input.credentials, stream),
transformedBody: body,
};
}
}
export default MimocodeExecutor;