mirror of
https://github.com/diegosouzapw/OmniRoute.git
synced 2026-08-13 18:52:18 +03:00
* fix(ci): clear base-reds on release/v3.8.50 (round 3) - CHANGELOG.md: restore the top [Unreleased] section dropped by the #10189 reconcile (docs-sync gate: first section must be Unreleased) - env-doc-sync: document CONDUCTOR_ORCHESTRATOR_TOKEN + CONDUCTOR_SPOKESPERSON_URL in .env.example/ENVIRONMENT.md; allowlist the CI-only GITHUB_STEP_SUMMARY and TS7_BASE_REF (ts7 ratchet signals); drop a stray merge artifact line - providers: restore the audited chatanywhere metadata entry that base-reds round 2 dropped together with its duplicate — the provider was half-wired (registry+endpoint without APIKEY metadata), which is what the wave3 test catches; re-pin providers-constants-split at the measured 228 - docs counts: 338 -> 339 (today's +2 void-ai/helixmind, -1 Puter) via gen:provider-reference + README/AGENTS/llm.txt/package.json/diagrams/i18n mirrors - file-size ratchet: annotated rebaseline for the two pre-existing drifts (ModelSelectModal 1138, gateways 1250) following the 2026-08-11 precedent Refs #9985 * fix(ci): base-reds round 3b — stale sibling tests + mode-pack weight contract - check-docs-counts-sync.test.ts: drop the imports/subtests of the four helpers #10196 removed from the gate script (readMcpFactsFromSource, listLocalizedDocs, makeRequiredCountsValidator, checkFreeTierInventory) — the new-API tests that #10196 added stay; the file now loads again under the node runner - quota-connection-recovery.test.ts: convert from vitest APIs to node:test — the file lives in tests/unit/*.test.ts (node-runner glob) and the vitest runtime crashes when imported outside vitest, killing the whole shard entry - modePacks.ts: re-normalize all six mode packs to sum 1.0 — #8940 added sessionAvailability: 0.05 to every pack without rebalancing (1.05 total); ratios preserved exactly (÷1.05), so post-normalizeScoringWeights behavior is unchanged; restores the declared sum-to-1.0 contract the 4235 test pins Refs #9985 * fix(ci): base-reds round 3c — vitest siblings, weights default, secrets FP, mutation tap - DistributeProxiesButton.test.tsx: wrap renders in NextIntlClientProvider — #9245 localized the component (useTranslations) and left the test without the intl context, failing all 14 cases - scoring.ts: re-normalize DEFAULT_WEIGHTS to sum 1.0 (same #8940 class as the mode packs — sessionAvailability added without rebalancing; ratios preserved) - .gitleaks.toml: generalize the kimi sponsor-banner localStorage-key allowlist to -v\d+ — #10200 bumped v1→v2 and the stale regex regressed the secrets ratchet with a false positive - stryker.conf.json: register 6 covering unit tests in tap.testFiles (4 modules) so their mutant kills count — unblocks check:mutation-test-coverage --strict Refs #9985 * fix(ci): base-reds round 3d — inspector factor gap, stale registry/gap tests, i18n key sync - comboScoringInspector: add cacheAffinity/sessionAvailability/connectionDensity to FACTOR_KEYS + the factor-key type — calculateScore() weighs them but the breakdown omitted them, so the explained contributions never summed to the reported score (inspector bug, red on the pure tip) - combo-scoring-inspector.test: make the explicit-weights override sum-neutral (±0.05 shift) so it stays valid for any DEFAULT_WEIGHTS values — the hardcoded override only summed to 1.0 against the pre-#8940 defaults, which is also why explicit weights silently fell back to 'default' on the tip - unorouter-registry.test: align to the canonical .com host (api.unorouter.ai 301-redirects there, verified live) and to wave4's live model discovery (passthrough, no static seed) — the .ai/auto-model expectations were stale - check-migration-numbering.test: 147 left KNOWN_GAPS when 147_api_keys_model_access_mode.sql landed — assert absent (same as 143) - i18n: sync-ui pass — 35,914 missing UI keys stamped as __MISSING__ placeholders across 42 locales (mechanical; greens the pt-BR key-presence integrity test; coverage pct unchanged by design — translation is a separate workstream) Refs #9985 * fix(ci): base-reds round 3e — 2 real defects + 14 stale sibling tests (waves A-E) Real defects fixed: - src/lib/db/apiKeys.ts: #9313's empty-allowlist early return bypassed the group permission check, silently disabling group deny rules (#8817) for every key without a per-key allowlist; fall-through restored, restricted+[] deny-all kept - open-sse/utils/proxyFetch.ts: #10032 re-appended the raw transport error to the propagated message, reintroducing the proxy user:password leak #9837 closed; new redactProxyDetailsInMessage() keeps the reason, redacts URL/credentials - .github/workflows/quality.yml: #10134 added the TS7 ratchet as a separate blocking step AFTER the aggregated gates — the exact #8542 masking mechanism; folded into the non-fail-fast loop (still blocking, still PR-only) ⚠️ CI edit, gate-strengthening — explicit owner sign-off requested on the PR - src/i18n/messages/ko.json: 3 machine-mistranslation regressions caught by the #8244 glossary checker (장애인→비활성화됨, 양말5://→socks5://, 비클로드→Claude가 아닌) Stale sibling tests aligned to deliberately-moved contracts (each cites its mover): request-log-detail-layout + -stream (#9245 intl provider), repro-8542 pin update, quality-rail-gate-membership (#10134 shape), agentSkills-routes 45→46 (#9058), cloudflare-ai-catalog-8717 (#8804 supersedes #8808), executor-xai (#9994), vision-bridge-claude-wire (#9463 minimax→openai), sse-auth forced-pin (#8893), tls-proxy-context (strengthened leak guards), rate-limit-local-error-classification (#9164/#9342), minimax-thinking-signature (#9463), codebuddy-cn (#9723 +1 test), github-copilot-custom-model (#9050), providers-g4f-batch3 (#9584), synced-capability-warmup (#9199, stricter), sidebar-tools-group (#8221), oauth-modal-grok-cli-paste (#9245); agentSkills/catalog.ts comment 45→46; file-size rebaseline for proxyFetch (+19, annotated) Refs #9985 * fix(ci): base-reds round 3f — waves F-J: 9 more real defects + stale sibling sweep Real production defects fixed (all red on the pure tip, each with its origin): - routeGuard.ts: #8949 accidentally DELETED the /api/providers/[id]/login local-only pattern — the route spawns a browser, so the loopback gate for a process-spawning route was gone (Hard Rules #15/#17); restored (314 guard tests green) - agentSkills generator: #9058's category dispatch gave the config category an empty body, wiping skills/config-codex-cli/SKILL.md at the #10131 sync; fixed + SKILL.md regenerated via the official generator - imageRegistry: #9982 broke same-provider bare aliasing (antigravity preview id sent upstream unresolved); new resolveSameProviderBareAlias() keeps the fal cross-provider fix intact - imageRegistry: #9982's prefix strip handed the bare nano-banana ids to fal-ai, violating the pinned 2026-07-31 operator decision (adobe-firefly owns them); fal entries made prefix-only (dispatch already re-prefixes) - mediaGeneration/fal.ts: the missing-credential 401 guard was lost when #10198 deleted the superseded falHandler — tests were hitting the live network - bottleneckPatch/rateLimitManager: #9041's merge clobbered #9604, resurrecting the Bottleneck v2.19.5 heartbeat bug (reservoir never refills); patched the library defect at the root and re-aligned chat-rate-limit-body-lock to the working reservoir contract - processSupervisor.mjs: #9761 regressed the Node spawn to bare "node" (the #9156 launchd bug) and dropped #9209's ipv4first args; both restored - openai-responses/pureHelpers: #9423's Agent null-sentinel was unreachable on the schemaless JSON-string path; gate extended - i18n en.json: #8222's regen reverted the #9976 unclosed-tag fix and #8559's combo-cooldown copy; #9038 shipped 40 t() calls with no messages (runtime MISSING_MESSAGE); all restored/added + official sync-ui stamps, and vi's zero-marker policy re-established via the sanctioned translation backend Stale sibling tests aligned (movers cited inline): chat-helpers (#9447), executor-antigravity (#9351), video-fal-grok (#9982), visionBridge (#9759), web-session-credentials (#8974), production-build-module-integrity (positive anchor added), agentSkills-generator/skillManifestsLint/skills-injection/ agentSkillTools-mcp/listCapabilities-a2a (#9058), memory-settings (#10010), model-catalog-policy-invalidation (#8906), model-alias-seed (#9485), reactive-context-compaction (#8949), combo-provider-wildcard (broken upsert helper), oauth-google-loopback (43-locale resurrected-key removal) Validation: 501/501 across the 47 touched test files; typecheck:core, lint, file-size, docs-sync all green. Refs #9985 * fix(ci): base-reds round 3g — wave K/L: 4 more real defects + stale alignments Real defects: - base/reasoningEffort.ts: the stale duplicate cherry-pick #9612 re-added the codex minimal→low rewrite that #9883 had deliberately removed (OMP minimal passthrough); block removed again - cursorImages.ts: #9840 wired prepareCursorImageForWire (sharp re-encode, fail-closed) into the SHARED resolveCursorImages, breaking zai-web and conol-web image uploads (HTTP 400 'undecodable'); new prepareForWire opt-out, Cursor default path unchanged (8 cursor suites green) - modelCapabilities/snapshot: catalog prepare still issued 323 per-model reads of model_context_overrides + max_input_tokens overrides, violating #9199's bulk-load contract; both now resolve from the snapshot single pass - v1-models-discovery-conformance: re-pinned to the bounded 30s SWR window (#9199/#10198) — the old 'stale-first regardless of age' contract is gone Stale tests aligned (movers cited inline): codex-tools-strict-default (#9828 redundant-oneOf strip), devin-providers (#9245 i18n), db-migrationrunner- constants-split (147→151 renumber #8228), gitlab-duo-oauth-setup (#9245), chatcore-extracted-modules (#9161 outbound-protocol keying) compression-api CI failures were cascade artifacts of codex-tools-strict-default failing in the same force-exit shard process — no own defect (171/171 local). Refs #9985 * fix(test): compression-api — register both describes before the runner starts The DATA_DIR setup + route/db top-level awaits sat BETWEEN the two describes; under --test-force-exit (the CI unit-runner flag) the process exits once the already-registered tests finish, so on slow CI machines the whole second describe died as 'Promise resolution is still pending' — the recurring CI-only shard-2 failure that never reproduced locally without the flag. Moved to the top of the file; 10/10 under --test-force-exit locally. Refs #9985 * fix(quality): freeze modelCapabilities.ts at 1006 (annotated) — snapshot routing growth Refs #9985 * fix(quality): move the modelCapabilities freeze into the frozen map (nested schema) Refs #9985 * fix(i18n): translate all 39,718 pending UI keys across 42 locales (owner-approved) Mass-translated every __MISSING__ placeholder via the official i18n:sync-ui --translate-markers pipeline (operator backend), restoring i18nUiCoverage to the 100 baseline (was 89.9 after the merge-storm UI landings + the 42 keys #9038 never shipped). Post-pass repairs, all caught by the existing gates: - glossary: retired renderings the machine reintroduced normalized again (提供商→提供者 zh-CN/zh-TW, 鏈接→連結, 文檔→文件, 調用→呼叫, 供應商→提供者, 響應→回應, 不活躍→未啟用 zh-TW; 클로드→Claude, 옴니루트→OmniRoute ko); DATA_DIR forbidden rendering avoided via 数据文件夹 rephrase - ICU integrity: 120 values with renamed/dropped {params} repaired (39 positional renames, 81 reset to the en source — functional over fluent) Validation: glossary/pt-BR/vi/deno-relay/settings-keys/value-drift/google- loopback suites 76/76; placeholder diff en×42 locales = 0; worst-locale coverage = 100.0%. Refs #9985 --------- Co-authored-by: backryun <bakryun0718@proton.me>
599 lines
19 KiB
TypeScript
599 lines
19 KiB
TypeScript
/**
|
|
* ZaiWebExecutor — Z.ai consumer chat (chat.z.ai).
|
|
*
|
|
* The consumer frontend stores a Bearer JWT in localStorage and requires a
|
|
* browser-issued CAPTCHA proof for chat completions. The browser transport is
|
|
* the default; callers with a short-lived proof can use the direct HTTP path.
|
|
*
|
|
* Completions go to /api/v2/chat/completions; the older unversioned
|
|
* /api/chat/completions path is stale and 404s model-independently (#8014).
|
|
*/
|
|
import { createHash, randomUUID } from "node:crypto";
|
|
import { BaseExecutor, type ExecuteInput } from "./base.ts";
|
|
import { configureZaiBrowserRequest } from "./zai-web/browserAutomation.ts";
|
|
import {
|
|
asRecord,
|
|
browserModelName,
|
|
browserPrompt,
|
|
buildZaiCompletionUrl,
|
|
buildZaiHeaders,
|
|
buildZaiNewChatBody,
|
|
buildZaiRequestBody,
|
|
buildZaiSignature,
|
|
collectZaiImageUrls,
|
|
describeZaiBrowserFailure,
|
|
extractZaiToken,
|
|
extractZaiUserId,
|
|
foldMessages,
|
|
getZaiModelCapabilities,
|
|
latestUserPrompt,
|
|
parseZaiFrontendVersion,
|
|
resolveZaiCaptchaVerifyParam,
|
|
resolveZaiThinkingConfig,
|
|
resolveZaiVlmConfig,
|
|
unprefixedModelId,
|
|
zaiImageFileName,
|
|
ZAI_BASE_URL,
|
|
ZAI_CHAT_URL,
|
|
ZAI_DEFAULT_FE_VERSION,
|
|
ZAI_DEFAULT_MODEL,
|
|
ZAI_FE_VERSION_CACHE_TTL_MS,
|
|
ZAI_NEW_CHAT_URL,
|
|
ZAI_USER_AGENT,
|
|
type ZaiReasoningEffort,
|
|
type ZaiThinkingConfig,
|
|
type ZaiVlmConfig,
|
|
} from "./zai-web/protocol.ts";
|
|
import {
|
|
buildZaiStreamingBody,
|
|
collectZaiNonStreaming,
|
|
makeZaiChunkEmitter,
|
|
} from "./zai-web/stream.ts";
|
|
import { browserBackedChat } from "../services/browserBackedChat.ts";
|
|
import { CursorImageError, resolveCursorImages } from "../utils/cursorImages.ts";
|
|
import {
|
|
makeExecutorErrorResult as makeErrorResult,
|
|
sanitizeErrorMessage,
|
|
} from "../utils/error.ts";
|
|
|
|
export {
|
|
buildZaiSignature,
|
|
describeZaiBrowserFailure,
|
|
extractZaiCaptchaVerifyParam,
|
|
extractZaiToken,
|
|
extractZaiUserId,
|
|
foldMessages,
|
|
getZaiModelCapabilities,
|
|
parseZaiFrontendVersion,
|
|
resolveZaiThinkingConfig,
|
|
resolveZaiVlmConfig,
|
|
} from "./zai-web/protocol.ts";
|
|
export type {
|
|
ZaiModelCapabilities,
|
|
ZaiReasoningEffort,
|
|
ZaiThinkingConfig,
|
|
ZaiVlmConfig,
|
|
} from "./zai-web/protocol.ts";
|
|
export { parseZaiFrame } from "./zai-web/stream.ts";
|
|
export type { ZaiDelta } from "./zai-web/stream.ts";
|
|
|
|
let cachedFeVersion: { value: string; expiresAt: number } | null = null;
|
|
|
|
type ZaiBrowserAttachments = NonNullable<Parameters<typeof browserBackedChat>[0]["attachments"]>;
|
|
|
|
/** Decode the request's image URLs into browser upload attachments. */
|
|
async function resolveZaiBrowserAttachments(
|
|
imageUrls: string[],
|
|
body: unknown
|
|
): Promise<
|
|
{ attachments: ZaiBrowserAttachments } | { errorResult: ReturnType<typeof makeErrorResult> }
|
|
> {
|
|
try {
|
|
// Browser-page upload: keep the original bytes/mimeType (no Cursor wire prep).
|
|
const images = await resolveCursorImages(imageUrls, { prepareForWire: false });
|
|
return {
|
|
attachments: images.map((image, index) => ({
|
|
name: zaiImageFileName(image.mimeType, index),
|
|
mimeType: image.mimeType,
|
|
buffer: image.data,
|
|
})),
|
|
};
|
|
} catch (error) {
|
|
const message =
|
|
error instanceof CursorImageError
|
|
? error.message
|
|
: sanitizeErrorMessage(error instanceof Error ? error.message : "invalid image input");
|
|
return {
|
|
errorResult: makeErrorResult(
|
|
error instanceof CursorImageError ? error.status : 400,
|
|
`Z.ai image input error: ${message}`,
|
|
body,
|
|
ZAI_CHAT_URL
|
|
),
|
|
};
|
|
}
|
|
}
|
|
|
|
/**
|
|
* The call-log body for a browser-transport turn. There is no real upstream
|
|
* request payload to record here, so this reconstructs the equivalent shape the
|
|
* signed-API path logs, from the settings the browser UI was driven with.
|
|
*/
|
|
function buildZaiBrowserAuditBody(input: {
|
|
messages: Array<{ role: string; content: unknown }>;
|
|
modelId: string;
|
|
thinkingConfig: ZaiThinkingConfig;
|
|
vlmConfig: ZaiVlmConfig;
|
|
imageCount: number;
|
|
}): Record<string, unknown> {
|
|
const { thinkingConfig: thinking, vlmConfig: vlm } = input;
|
|
return {
|
|
browser_backed: true,
|
|
image_count: input.imageCount,
|
|
model: input.modelId,
|
|
messages: foldMessages(input.messages),
|
|
enable_thinking: thinking.enabled,
|
|
auto_web_search: vlm.websiteModeEnabled ? false : vlm.webSearchEnabled,
|
|
vlm_tools_enable: vlm.toolsEnabled,
|
|
vlm_web_search_enable: vlm.websiteModeEnabled && vlm.webSearchEnabled,
|
|
vlm_website_mode: vlm.websiteModeEnabled,
|
|
...(thinking.enabled && thinking.effortSupported ? { reasoning_effort: thinking.effort } : {}),
|
|
};
|
|
}
|
|
|
|
/**
|
|
* Drive-the-real-UI options for chat.z.ai: which selectors to type into and click,
|
|
* and the localStorage token the page reads at boot. `beforeSubmit` flips the
|
|
* Deep Think / web-search / tools switches to match the request.
|
|
*/
|
|
function buildZaiBrowserChatOptions(input: {
|
|
attachments: ZaiBrowserAttachments;
|
|
messages: Array<{ role: string; content: unknown }>;
|
|
modelId: string;
|
|
signal?: AbortSignal | null;
|
|
thinkingConfig: ZaiThinkingConfig;
|
|
token: string;
|
|
vlmConfig: ZaiVlmConfig;
|
|
}): Parameters<typeof browserBackedChat>[0] {
|
|
const poolKey = `zai-web:${createHash("sha256").update(input.token).digest("hex").slice(0, 24)}`;
|
|
return {
|
|
poolKey,
|
|
chatUrl: ZAI_CHAT_URL,
|
|
chatPageUrl: `${ZAI_BASE_URL}/?model=${encodeURIComponent(browserModelName(input.modelId))}`,
|
|
userMessage: browserPrompt(input.messages),
|
|
localStorage: { token: input.token },
|
|
localStorageOrigin: ZAI_BASE_URL,
|
|
cookieDomain: "chat.z.ai",
|
|
chatUrlMatchDomain: "chat.z.ai",
|
|
userAgent: ZAI_USER_AGENT,
|
|
locale: "en-US",
|
|
timezone: "Asia/Seoul",
|
|
inputSelector: "#chat-input",
|
|
submitButtonSelector: '[aria-label="Send Message"] button:not([disabled])',
|
|
submitButtonMode: "dom",
|
|
attachments: input.attachments,
|
|
beforeSubmit: (page) =>
|
|
configureZaiBrowserRequest(page, {
|
|
modelId: input.modelId,
|
|
thinking: input.thinkingConfig,
|
|
vlm: input.vlmConfig,
|
|
}),
|
|
postSubmitWaitMs: 30_000,
|
|
signal: input.signal,
|
|
reuseContext: true,
|
|
};
|
|
}
|
|
|
|
/** What either transport hands back: the upstream stream plus its call-log pair. */
|
|
type ZaiTransportResult = {
|
|
upstream: Response;
|
|
auditHeaders: Record<string, string>;
|
|
auditBody: Record<string, unknown>;
|
|
};
|
|
|
|
type ZaiResolvedRequest = {
|
|
captchaVerifyParam: string;
|
|
imageUrls: string[];
|
|
messages: Array<{ role: string; content: unknown }>;
|
|
modelId: string;
|
|
prompt: string;
|
|
thinkingConfig: ZaiThinkingConfig;
|
|
token: string;
|
|
userId: string;
|
|
vlmConfig: ZaiVlmConfig;
|
|
};
|
|
|
|
/**
|
|
* Validate the credential and body, and resolve everything both transports need.
|
|
*
|
|
* All four rejections are client errors that must never reach the upstream: no
|
|
* usable session token, no user turn, an image sent to a text-only model, and a
|
|
* JWT with no user id (which the signed-API path needs to build its signature).
|
|
*/
|
|
function resolveZaiRequest(
|
|
input: ExecuteInput
|
|
): { request: ZaiResolvedRequest } | { errorResult: ReturnType<typeof makeErrorResult> } {
|
|
const { body, credentials, model } = input;
|
|
const bodyObj = (body || {}) as Record<string, unknown>;
|
|
const fail = (message: string) => ({
|
|
errorResult: makeErrorResult(400, message, body, ZAI_CHAT_URL),
|
|
});
|
|
|
|
const rawCredential = String(credentials?.apiKey ?? credentials?.accessToken ?? "").trim();
|
|
const token = extractZaiToken(rawCredential);
|
|
if (!token) {
|
|
return fail(
|
|
'Missing Z.ai web-session credential — copy the "token" value from chat.z.ai Local Storage.'
|
|
);
|
|
}
|
|
|
|
const messages = (bodyObj.messages as Array<{ role: string; content: unknown }>) || [];
|
|
const prompt = latestUserPrompt(messages);
|
|
const imageUrls = collectZaiImageUrls(messages);
|
|
if (!prompt && imageUrls.length === 0) {
|
|
return fail("Z.ai requires at least one user message");
|
|
}
|
|
|
|
const modelId = (bodyObj.model as string) || model || ZAI_DEFAULT_MODEL;
|
|
if (imageUrls.length > 0 && !getZaiModelCapabilities(modelId).vision) {
|
|
return fail(
|
|
`Z.ai model ${unprefixedModelId(modelId)} does not accept image input; use GLM-5V-Turbo.`
|
|
);
|
|
}
|
|
|
|
const userId = extractZaiUserId(token);
|
|
if (!userId) {
|
|
return fail(
|
|
"Invalid Z.ai web-session credential — its JWT payload does not contain the required user id."
|
|
);
|
|
}
|
|
|
|
return {
|
|
request: {
|
|
captchaVerifyParam: resolveZaiCaptchaVerifyParam(credentials, bodyObj),
|
|
imageUrls,
|
|
messages,
|
|
modelId,
|
|
prompt,
|
|
thinkingConfig: resolveZaiThinkingConfig(modelId, bodyObj),
|
|
token,
|
|
userId,
|
|
vlmConfig: resolveZaiVlmConfig(modelId, bodyObj),
|
|
},
|
|
};
|
|
}
|
|
|
|
export class ZaiWebExecutor extends BaseExecutor {
|
|
constructor() {
|
|
super("zai-web", { id: "zai-web", baseUrl: ZAI_BASE_URL });
|
|
}
|
|
|
|
private async resolveFrontendVersion(signal?: AbortSignal | null): Promise<string> {
|
|
if (cachedFeVersion && cachedFeVersion.expiresAt > Date.now()) {
|
|
return cachedFeVersion.value;
|
|
}
|
|
let version = ZAI_DEFAULT_FE_VERSION;
|
|
try {
|
|
const response = await fetch(`${ZAI_BASE_URL}/`, {
|
|
headers: { Accept: "text/html", "User-Agent": ZAI_USER_AGENT },
|
|
signal,
|
|
});
|
|
if (response.ok) {
|
|
version = parseZaiFrontendVersion(await response.text()) ?? version;
|
|
}
|
|
} catch {
|
|
// The current verified version remains a safe fallback when homepage probing fails.
|
|
}
|
|
cachedFeVersion = {
|
|
value: version,
|
|
expiresAt: Date.now() + ZAI_FE_VERSION_CACHE_TTL_MS,
|
|
};
|
|
return version;
|
|
}
|
|
|
|
private async createRemoteChat(input: {
|
|
messages: Array<{ role: string; content: unknown }>;
|
|
modelId: string;
|
|
token: string;
|
|
enableThinking: boolean;
|
|
reasoningEffort: ZaiReasoningEffort;
|
|
vlmConfig: ZaiVlmConfig;
|
|
signal?: AbortSignal | null;
|
|
originalBody: unknown;
|
|
}): Promise<
|
|
{ chatId: string; userMessageId: string } | { errorResult: ReturnType<typeof makeErrorResult> }
|
|
> {
|
|
const { userMessageId, payload } = buildZaiNewChatBody(
|
|
input.messages,
|
|
input.modelId,
|
|
input.enableThinking,
|
|
input.reasoningEffort,
|
|
input.vlmConfig
|
|
);
|
|
let response: Response;
|
|
try {
|
|
response = await fetch(ZAI_NEW_CHAT_URL, {
|
|
method: "POST",
|
|
headers: buildZaiHeaders(input.token, {
|
|
accept: "application/json",
|
|
}),
|
|
body: JSON.stringify(payload),
|
|
signal: input.signal,
|
|
});
|
|
} catch (error) {
|
|
const message = sanitizeErrorMessage(
|
|
error instanceof Error ? error.message : "unknown network error"
|
|
);
|
|
return {
|
|
errorResult: makeErrorResult(
|
|
502,
|
|
`Z.ai chat creation failed: ${message}`,
|
|
input.originalBody,
|
|
ZAI_NEW_CHAT_URL
|
|
),
|
|
};
|
|
}
|
|
if (!response.ok) {
|
|
const errorText = await response.text().catch(() => "");
|
|
return {
|
|
errorResult: makeErrorResult(
|
|
response.status,
|
|
`Z.ai chat creation error: ${sanitizeErrorMessage(errorText)}`,
|
|
input.originalBody,
|
|
ZAI_NEW_CHAT_URL
|
|
),
|
|
};
|
|
}
|
|
const result = asRecord(await response.json().catch(() => null));
|
|
const chatId = typeof result?.id === "string" ? result.id : "";
|
|
if (!chatId) {
|
|
return {
|
|
errorResult: makeErrorResult(
|
|
502,
|
|
"Z.ai chat creation returned no chat id",
|
|
input.originalBody,
|
|
ZAI_NEW_CHAT_URL
|
|
),
|
|
};
|
|
}
|
|
return { chatId, userMessageId };
|
|
}
|
|
|
|
private async fetchUpstream(
|
|
completionUrl: string,
|
|
reqHeaders: Record<string, string>,
|
|
reqBody: Record<string, unknown>,
|
|
body: unknown,
|
|
signal: AbortSignal | null | undefined
|
|
): Promise<{ upstream: Response } | { errorResult: ReturnType<typeof makeErrorResult> }> {
|
|
let upstream: Response;
|
|
try {
|
|
upstream = await fetch(completionUrl, {
|
|
method: "POST",
|
|
headers: reqHeaders,
|
|
body: JSON.stringify(reqBody),
|
|
signal,
|
|
});
|
|
} catch (error) {
|
|
const message = sanitizeErrorMessage(
|
|
error instanceof Error ? error.message : "unknown network error"
|
|
);
|
|
return {
|
|
errorResult: makeErrorResult(502, `Z.ai fetch failed: ${message}`, body, ZAI_CHAT_URL),
|
|
};
|
|
}
|
|
|
|
if (!upstream.ok) {
|
|
const errorText = await upstream.text().catch(() => "");
|
|
return {
|
|
errorResult: makeErrorResult(
|
|
upstream.status,
|
|
`Z.ai error: ${sanitizeErrorMessage(errorText)}`,
|
|
body,
|
|
ZAI_CHAT_URL
|
|
),
|
|
};
|
|
}
|
|
return { upstream };
|
|
}
|
|
|
|
private async fetchThroughBrowser(input: {
|
|
body: unknown;
|
|
messages: Array<{ role: string; content: unknown }>;
|
|
modelId: string;
|
|
imageUrls: string[];
|
|
signal?: AbortSignal | null;
|
|
thinkingConfig: ZaiThinkingConfig;
|
|
token: string;
|
|
vlmConfig: ZaiVlmConfig;
|
|
}): Promise<ZaiTransportResult | { errorResult: ReturnType<typeof makeErrorResult> }> {
|
|
const resolved = await resolveZaiBrowserAttachments(input.imageUrls, input.body);
|
|
if ("errorResult" in resolved) return resolved;
|
|
const { attachments } = resolved;
|
|
|
|
let result: Awaited<ReturnType<typeof browserBackedChat>>;
|
|
try {
|
|
result = await browserBackedChat(buildZaiBrowserChatOptions({ ...input, attachments }));
|
|
} catch (error) {
|
|
const message = sanitizeErrorMessage(
|
|
error instanceof Error ? error.message : "browser transport unavailable"
|
|
);
|
|
return {
|
|
errorResult: makeErrorResult(
|
|
502,
|
|
`Z.ai browser transport failed: ${message}`,
|
|
input.body,
|
|
ZAI_CHAT_URL
|
|
),
|
|
};
|
|
}
|
|
|
|
if (result.status < 200 || result.status >= 300) {
|
|
return {
|
|
errorResult: makeErrorResult(
|
|
result.status || 502,
|
|
describeZaiBrowserFailure(result),
|
|
input.body,
|
|
ZAI_CHAT_URL
|
|
),
|
|
};
|
|
}
|
|
|
|
return {
|
|
upstream: new Response(new Uint8Array(result.body), {
|
|
status: result.status,
|
|
headers: {
|
|
"Content-Type": result.contentType || "text/event-stream",
|
|
},
|
|
}),
|
|
auditHeaders: {
|
|
Authorization: "Bearer [REDACTED]",
|
|
"X-OmniRoute-Transport": "browser",
|
|
},
|
|
auditBody: buildZaiBrowserAuditBody({
|
|
messages: input.messages,
|
|
modelId: input.modelId,
|
|
thinkingConfig: input.thinkingConfig,
|
|
vlmConfig: input.vlmConfig,
|
|
imageCount: attachments.length,
|
|
}),
|
|
};
|
|
}
|
|
|
|
/**
|
|
* Signed-API transport: create a chat server-side, then POST the completion with
|
|
* a CAPTCHA proof and a per-request signature. Only reachable when the caller
|
|
* supplied a proof and sent no images.
|
|
*/
|
|
private async fetchViaSignedApi(
|
|
request: ZaiResolvedRequest,
|
|
input: ExecuteInput
|
|
): Promise<ZaiTransportResult | { errorResult: ReturnType<typeof makeErrorResult> }> {
|
|
const { body, signal } = input;
|
|
const bodyObj = (body || {}) as Record<string, unknown>;
|
|
const { messages, modelId, prompt, thinkingConfig, token, userId, vlmConfig } = request;
|
|
|
|
const frontendVersion = await this.resolveFrontendVersion(signal);
|
|
const createdChat = await this.createRemoteChat({
|
|
messages,
|
|
modelId,
|
|
token,
|
|
enableThinking: thinkingConfig.enabled,
|
|
reasoningEffort: thinkingConfig.effort,
|
|
vlmConfig,
|
|
signal,
|
|
originalBody: body,
|
|
});
|
|
if ("errorResult" in createdChat) return createdChat;
|
|
|
|
const timestamp = Date.now();
|
|
const requestId = randomUUID();
|
|
const signature = buildZaiSignature({ prompt, requestId, timestamp, userId });
|
|
const completionUrl = buildZaiCompletionUrl({ requestId, timestamp, token, userId });
|
|
const reqHeaders = buildZaiHeaders(token, {
|
|
accept: "text/event-stream",
|
|
frontendVersion,
|
|
signature,
|
|
});
|
|
const reqBody = buildZaiRequestBody({
|
|
body: bodyObj,
|
|
captchaVerifyParam: request.captchaVerifyParam,
|
|
chatId: createdChat.chatId,
|
|
messages,
|
|
modelId,
|
|
prompt,
|
|
userMessageId: createdChat.userMessageId,
|
|
enableThinking: thinkingConfig.enabled,
|
|
reasoningEffort: thinkingConfig.effort,
|
|
reasoningEffortSupported: thinkingConfig.effortSupported,
|
|
vlmConfig,
|
|
});
|
|
const fetched = await this.fetchUpstream(completionUrl, reqHeaders, reqBody, body, signal);
|
|
if ("errorResult" in fetched) return fetched;
|
|
|
|
return {
|
|
upstream: fetched.upstream,
|
|
auditHeaders: {
|
|
...reqHeaders,
|
|
Authorization: "Bearer [REDACTED]",
|
|
"X-Signature": "[REDACTED]",
|
|
},
|
|
auditBody: { ...reqBody, captcha_verify_param: "[REDACTED]" },
|
|
};
|
|
}
|
|
|
|
async execute(input: ExecuteInput) {
|
|
const { body, signal, stream: wantStream } = input;
|
|
|
|
const resolved = resolveZaiRequest(input);
|
|
if ("errorResult" in resolved) return resolved.errorResult;
|
|
const request = resolved.request;
|
|
const { imageUrls, messages, modelId, thinkingConfig, token, vlmConfig } = request;
|
|
|
|
const useSignedApi = Boolean(request.captchaVerifyParam) && imageUrls.length === 0;
|
|
const fetched = useSignedApi
|
|
? await this.fetchViaSignedApi(request, input)
|
|
: await this.fetchThroughBrowser({
|
|
body,
|
|
imageUrls,
|
|
messages,
|
|
modelId,
|
|
signal,
|
|
thinkingConfig,
|
|
token,
|
|
vlmConfig,
|
|
});
|
|
if ("errorResult" in fetched) return fetched.errorResult;
|
|
const { upstream, auditHeaders, auditBody } = fetched;
|
|
|
|
const id = `chatcmpl-zai-${Date.now()}`;
|
|
const created = Math.floor(Date.now() / 1000);
|
|
const sourceBody =
|
|
upstream.body ?? new ReadableStream({ start: (controller) => controller.close() });
|
|
const emitChunk = makeZaiChunkEmitter(id, created, modelId);
|
|
if (wantStream) {
|
|
const outStream = buildZaiStreamingBody(sourceBody, emitChunk, signal);
|
|
return {
|
|
response: new Response(outStream, {
|
|
headers: {
|
|
"Content-Type": "text/event-stream",
|
|
"Cache-Control": "no-cache",
|
|
Connection: "keep-alive",
|
|
},
|
|
}),
|
|
url: ZAI_CHAT_URL,
|
|
headers: auditHeaders,
|
|
transformedBody: auditBody,
|
|
};
|
|
}
|
|
|
|
let answer: string;
|
|
let reasoning: string;
|
|
try {
|
|
({ answer, reasoning } = await collectZaiNonStreaming(sourceBody));
|
|
} catch (error) {
|
|
const message = sanitizeErrorMessage(
|
|
error instanceof Error ? error.message : "invalid upstream stream"
|
|
);
|
|
return makeErrorResult(502, `Z.ai stream failed: ${message}`, body, ZAI_CHAT_URL);
|
|
}
|
|
const message: Record<string, unknown> = { role: "assistant", content: answer };
|
|
if (reasoning) message.reasoning_content = reasoning;
|
|
const completion = {
|
|
id,
|
|
object: "chat.completion",
|
|
created,
|
|
model: modelId,
|
|
choices: [{ index: 0, message, finish_reason: "stop" }],
|
|
};
|
|
return {
|
|
response: new Response(JSON.stringify(completion), {
|
|
headers: { "Content-Type": "application/json" },
|
|
}),
|
|
url: ZAI_CHAT_URL,
|
|
headers: auditHeaders,
|
|
transformedBody: auditBody,
|
|
};
|
|
}
|
|
}
|