feat(xiaomi-mimo): server-assisted desktop login, five account clusters, v2.6 models

Reproduce the MiMo Desktop login surface server-side so headless/Docker
deployments can link a Xiaomi account without the Desktop client. The
account session (passToken) is captured during the proxied login and
stored per connection.

- Five account clusters (cn/sgp/ams/ru/in): per-region mimo-server host
  and SSO sid, unknown region falls back to sgp
- mimo-v2.6-pro/flash/pro-ultraspeed dual-route models: account-service
  route when desktop credentials exist, cloud API (sk- key) otherwise;
  drops obsolete mimo-x-*-preview ids
- Desktop ServiceTokenManager 2-phase handshake (single serviceLogin with
  target sid, raw 64-bit nonce preserved), per-region session cache
- reasoning_effort bridged to output_config.effort; i18n runtime now
  observes characterData mutations so React text rewrites get translated
- Security hardening on the login proxy: session travels only in the
  httpOnly cookie (never in the URL), proxy branch requires dashboard
  auth, authorization/proxy-authorization never forwarded upstream, and
  upstream Set-Cookie is not replayed onto the app origin
This commit is contained in:
wismyzhizi
2026-09-23 09:43:39 +07:00
committed by decolua
parent 6af26a9ee8
commit 910db749aa
16 changed files with 1687 additions and 352 deletions

View File

@@ -14,9 +14,6 @@ const STRIP_RULES = [
{ provider: "github", match: (m) => /claude/i.test(m) && !/claude.*(opus|sonnet).*4\.6/i.test(m), drop: ["thinking", "reasoning_effort"] },
// Cloudflare Workers AI: content must be plain string, rejects OpenAI content-part array (#1926)
{ provider: "cloudflare-ai", flattenContent: true },
// MiMo Desktop Preview models (account-service route): content must be plain string,
// rejects OpenAI content-part array. Cloud models keep their parts (mimo-v2-omni is multi-modal).
{ provider: "xiaomi-mimo", match: /preview/i, flattenContent: true },
{ provider: "volcengine-ark", match: /glm-5/i, clampToModelMaxOutput: true },
// VolcEngine Ark caps the Kimi family at max_tokens <= 32768, but the model's
// advertised ceiling is far higher (Kimi-K2.7-Code resolves to maxOutput 262144),