Files
OmniRoute/open-sse/executors/vertex.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

197 lines
6.7 KiB
TypeScript

import { SignJWT, importPKCS8 } from "jose";
import { BaseExecutor, ExecuteInput } from "./base.ts";
import { PROVIDERS } from "../config/constants.ts";
interface ServiceAccount {
type: string;
project_id: string;
private_key_id: string;
private_key: string;
client_email: string;
[key: string]: unknown;
}
const TOKEN_CACHE = new Map<string, { token: string; expiresAt: number }>();
export function parseSAFromApiKey(apiKey: string): ServiceAccount {
try {
return JSON.parse(apiKey);
} catch {
throw new Error("Vertex AI requires a valid Service Account JSON as the API key");
}
}
/**
* A Service Account credential is a JSON object (type/client_email/private_key). A Vertex AI
* Express-mode API key is an opaque non-JSON string. Distinguishing them lets the executor
* support BOTH: Service Account JSON (JWT → OAuth → project-scoped endpoint + Bearer auth) and
* Express keys (project-less publisher endpoint + x-goog-api-key auth), instead of failing every
* Express key with "requires a valid Service Account JSON".
*/
export function looksLikeServiceAccountJson(apiKey: string): boolean {
if (!apiKey || typeof apiKey !== "string") return false;
try {
const parsed = JSON.parse(apiKey);
return !!parsed && typeof parsed === "object" && !Array.isArray(parsed);
} catch {
return false;
}
}
/** True for a Vertex AI Express-mode API key (a non-empty, non-JSON, non-OAuth credential). */
export function isExpressApiKey(apiKey?: string | null): boolean {
return typeof apiKey === "string" && apiKey.trim().length > 0 && !looksLikeServiceAccountJson(apiKey);
}
export async function getAccessToken(sa: ServiceAccount): Promise<string> {
if (!sa.client_email || !sa.private_key) {
throw new Error(
"Service Account JSON is missing required fields (client_email or private_key)"
);
}
const cacheKey = sa.client_email;
const cached = TOKEN_CACHE.get(cacheKey);
// Buffer of 60 seconds
if (cached && Date.now() < cached.expiresAt - 60_000) {
return cached.token;
}
const privateKey = await importPKCS8(sa.private_key, "RS256");
const now = Math.floor(Date.now() / 1000);
const jwt = await new SignJWT({
iss: sa.client_email,
sub: sa.client_email,
aud: "https://oauth2.googleapis.com/token",
iat: now,
exp: now + 3600,
scope: "https://www.googleapis.com/auth/cloud-platform",
})
.setProtectedHeader({ alg: "RS256", kid: sa.private_key_id })
.sign(privateKey);
const tokenRes = await fetch("https://oauth2.googleapis.com/token", {
method: "POST",
headers: { "Content-Type": "application/x-www-form-urlencoded" },
body: new URLSearchParams({
grant_type: "urn:ietf:params:oauth:grant-type:jwt-bearer",
assertion: jwt,
}),
});
if (!tokenRes.ok) {
const errorText = await tokenRes.text();
throw new Error(
`Failed to exchange JWT for Vertex access token: ${tokenRes.status} ${errorText}`
);
}
const tokenData = await tokenRes.json();
const accessToken = tokenData.access_token;
if (!accessToken) {
throw new Error("Vertex AI token exchange succeeded but no access_token found");
}
TOKEN_CACHE.set(cacheKey, {
token: accessToken,
expiresAt: (now + 3600) * 1000,
});
return accessToken;
}
const PARTNER_MODELS = new Set([
"claude-3-5-sonnet",
"claude-3-opus",
"claude-3-haiku",
"deepseek-v3",
"deepseek-v3.2",
"deepseek-v4",
"deepseek-deepseek-r1",
"qwen3-next-80b",
"qwen3.6-",
"llama-3.1",
"mistral-",
"glm-5",
"glm-5.1",
"meta/llama",
]);
function isPartnerModel(model: string) {
const normalizedModel = model.toLowerCase();
return [...PARTNER_MODELS].some((prefix) => normalizedModel.startsWith(prefix));
}
export class VertexExecutor extends BaseExecutor {
constructor() {
super("vertex", PROVIDERS.vertex);
}
async execute(input: ExecuteInput) {
const { credentials, log } = input;
// Defensive: trim stray surrounding whitespace from a pasted credential.
if (typeof credentials.apiKey === "string") {
credentials.apiKey = credentials.apiKey.trim();
}
// Service Account JSON → mint a short-lived OAuth token (Bearer). An Express-mode API key is
// sent as-is via x-goog-api-key (see buildHeaders), so no token exchange is needed for it.
if (credentials.apiKey && !credentials.accessToken && looksLikeServiceAccountJson(credentials.apiKey)) {
try {
const sa = parseSAFromApiKey(credentials.apiKey);
credentials.accessToken = await getAccessToken(sa);
} catch (err: any) {
log?.error?.("VERTEX", `Failed to generate JWT token: ${err.message}`);
throw err;
}
}
return super.execute(input);
}
buildUrl(model: string, stream: boolean, urlIndex = 0, credentials: any = null) {
// Vertex AI Express mode: project-less v1 publisher endpoint with the API key passed as a
// ?key= query parameter (verified working contract — same as the CaptionAI GeminiClient). The
// Express key is NOT accepted as a Bearer/OAuth credential or via x-goog-api-key on this API.
if (isExpressApiKey(credentials?.apiKey) && !credentials?.accessToken) {
const expressKey = encodeURIComponent(String(credentials.apiKey).trim());
if (isPartnerModel(model)) {
// Partner (Anthropic/etc.) models are not available via Express keys; best-effort.
return `https://aiplatform.googleapis.com/v1/publishers/openapi/chat/completions?key=${expressKey}`;
}
const op = stream ? "streamGenerateContent?alt=sse&" : "generateContent?";
return `https://aiplatform.googleapis.com/v1/publishers/google/models/${model}:${op}key=${expressKey}`;
}
const region = credentials?.providerSpecificData?.region || "us-central1";
let project = "unknown-project";
if (credentials?.apiKey) {
try {
const sa = parseSAFromApiKey(credentials.apiKey);
if (sa.project_id) project = sa.project_id;
} catch {
// Ignored, handled in execute
}
}
if (isPartnerModel(model)) {
return `https://aiplatform.googleapis.com/v1/projects/${project}/locations/global/endpoints/openapi/chat/completions`;
}
return `https://aiplatform.googleapis.com/v1/projects/${project}/locations/${region}/publishers/google/models/${model}:${stream ? "streamGenerateContent?alt=sse" : "generateContent"}`;
}
buildHeaders(credentials: any, stream = true) {
const headers: Record<string, string> = { "Content-Type": "application/json" };
if (credentials.accessToken) {
headers["Authorization"] = `Bearer ${credentials.accessToken}`;
}
// Express-mode keys are carried in the ?key= query parameter (see buildUrl), not a header.
if (stream) {
headers["Accept"] = "text/event-stream";
}
return headers;
}
}