@juspay/neurolink/dist/providers/googleVertex/client.d.ts

The pipe layer of an AI nervous system: one interface connecting provider neurons to your application, across three inference types — generate, stream and decide. `decide` returns typed, calibrated judgements from a non-generative model (~400ms, ~$0.00002

import type { ZodType } from "zod";
import { AIProviderName } from "../../constants/enums.js";
import { BaseProvider } from "../../core/baseProvider.js";
import type { EmbedInput, EnhancedGenerateResult, TextGenerationOptions, StreamOptions, StreamResult, VertexAnthropicMessage, ChatMessage, MinimalChatMessage } from "../../types/index.js";
import type { Schema, LanguageModel } from "../../types/index.js";
export declare function buildAnthropicHistoryMessages(conversationMessages: Array<ChatMessage | MinimalChatMessage>): VertexAnthropicMessage[];
export declare function appendUserMessage(messages: VertexAnthropicMessage[], content: VertexAnthropicMessage["content"]): void;
/**
 * Recursively strip JSON-schema fields that Vertex Gemini's function-call AND
 * `responseSchema` (structured output) validators reject with 400
 * INVALID_ARGUMENT. Vertex implements OpenAPI 3.0 Schema strictly and rejects
 * extension fields that the broader JSON Schema spec allows. The fields
 * stripped here have no semantic meaning for the model, so removing them is
 * safe for every caller.
 *
 * Fields removed:
 * - `additionalProperties` — extension; Vertex rejects on any nested object.
 * - `default` — Vertex rejects defaults on object/array-typed properties and
 *   on properties that are also marked `required`. Safest to strip globally
 *   because the model never inspects them.
 * - `$schema`, `$id`, `$ref`, `definitions`, `$defs` — JSON-Schema-meta
 *   fields that Vertex doesn't recognise.
 * - `examples` — accepted by some Gemini variants but not 2.5-flash; strip
 *   to avoid the model rejecting tool schemas under that path.
 * - `errorMessage` — emitted by `convertZodToJsonSchema` (which enables
 *   zod-to-json-schema's `errorMessages: true`) for any field carrying a
 *   custom message, e.g. `z.string().regex(re, { message })`. Vertex's
 *   `response_schema` validator rejects it with `Unknown name "errorMessage"
 *   … Cannot find field`, failing the whole structured-output request.
 *
 * Exported for deterministic unit testing of the sanitization contract.
 */
export declare function stripAdditionalPropertiesDeep(schema: Record<string, unknown> | undefined): void;
/**
 * Resolve the effective Vertex region for a given model.
 *
 * Policy (matches the bugfixes-suite contract):
 *  - Every Gemini model (`gemini-*`) is force-routed to the `global` endpoint
 *    regardless of any caller-supplied region. Regional endpoints 404 for
 *    Gemini 3.x previews and the regional/global behaviour for 2.x is
 *    consistent enough that pinning all Gemini traffic to global is the
 *    right safe default. The legacy `GLOBAL_LOCATION_MODELS` allowlist is
 *    kept as a defence-in-depth fallback so any non-`gemini-` identifiers
 *    that still need global (e.g. image-gen aliases) keep working.
 *  - Non-Gemini models (Claude on Vertex, embeddings, custom models) keep
 *    the caller-supplied region or fall back to env-derived defaults.
 *
 * @param modelName - The target model identifier.
 * @param configuredLocation - Caller-provided region (e.g. options.region).
 *   Used as the fallback for non-Gemini models; ignored for Gemini.
 * @returns The region string to pass to the @google/genai client.
 */
export declare const resolveVertexLocation: (modelName: string | undefined, configuredLocation?: string) => string;
export declare class GoogleVertexProvider extends BaseProvider {
    private projectId;
    private location;
    /**
     * Vertex AI Express Mode credentials.
     *
     * Vertex supports two authentication modes. The long-standing one pairs a
     * project and location with Application Default Credentials, which makes
     * the SDK mint an OAuth token through google-auth-library before every
     * request. Express Mode instead authenticates with an API key alone.
     *
     * Express is used only when an apiKey is supplied WITHOUT an explicit
     * project or location, so existing ADC callers — including those already
     * passing an apiKey alongside a project — keep exactly the behaviour they
     * have today.
     */
    private expressApiKey?;
    /**
     * Optional endpoint override, mirroring AI Studio's
     * `credentials.googleAiStudio.baseURL`: per-request credential first, then
     * the environment, then unset so the SDK applies its own default. Blank
     * values count as unset so an empty override cannot clobber that default.
     */
    private baseURL?;
    private registeredTools;
    private toolContext;
    private static modelConfigCache;
    private static modelConfigCacheTime;
    private static readonly CACHE_DURATION;
    private static readonly MAX_CACHE_SIZE;
    private static maxTokensCache;
    private static maxTokensCacheTime;
    constructor(modelName?: string, _providerName?: string, sdk?: unknown, region?: string, credentials?: Record<string, unknown>);
    protected getProviderName(): AIProviderName;
    protected getDefaultModel(): string;
    /**
     * Returns the Vercel AI SDK model instance for Google Vertex
     * Creates fresh model instances for each request
     */
    protected getAISDKModel(): Promise<LanguageModel>;
    /**
     * Validate stream options
     */
    private validateStreamOptionsOnly;
    /**
     * Preprocess file input before routing to the native SDKs.
     *
     * BaseProvider runs this via `buildMultimodalMessagesArray`, but Vertex
     * overrides both `generate()` and `executeStream()` to reach the native
     * @google/genai / @anthropic-ai/vertex-sdk clients directly, so neither
     * inherits it. Without this the file content never reaches the model and
     * the reply is an entirely plausible "no document is attached" — a silent
     * wrong answer rather than an error.
     *
     * #1258: only `generate()` used to call this, so the same document that
     * `generate()` read back correctly came back as "no documents attached"
     * through `stream()`. Sharing one method is what keeps the two paths from
     * drifting apart again.
     *
     * #1259: the alias fold has to happen *before* the `files` check, or
     * requests carrying only `audioFiles`/`videoFiles` look empty here and skip
     * preprocessing entirely.
     */
    private preprocessNativeFileInput;
    protected executeStream(options: StreamOptions, _analysisSchema?: ZodType<unknown> | Schema<unknown>): Promise<StreamResult>;
    /**
     * Emit `stream:end` so the Pipeline B observability listener creates a
     * `model.generation` span for native Vertex stream traffic. Mirrors
     * `emitGenerationEnd` (used by `generate()`).
     */
    private emitStreamEnd;
    /**
     * Create @google/genai client configured for Vertex AI
     */
    private createVertexGenAIClient;
    /** Endpoint override: credential, then environment, then unset. */
    private resolveBaseURL;
    /**
     * Express Mode key, if this provider should use it.
     *
     * Deliberately NOT read from GOOGLE_API_KEY: that variable is already set
     * by callers who also configure a project, and treating it as an Express
     * opt-in would silently switch their authentication mode. Express is opted
     * into per request, or through GOOGLE_VERTEX_API_KEY which exists only for
     * this purpose.
     */
    private resolveExpressApiKey;
    /**
     * Convert one AI-SDK tool into an Anthropic (Claude-on-Vertex) tool
     * declaration. Single source for the pre-loop snapshot AND the mid-turn
     * discovery refresh — Anthropic validates input_schema as JSON Schema
     * draft 2020-12 and rejects OpenAPI-3 dialect (`nullable: true`), so this
     * uses the default JSON Schema target, matching the direct anthropic
     * provider. The Gemini paths keep "openApi3".
     */
    private buildAnthropicToolDeclaration;
    /**
     * Mid-turn tool sync for the Claude-on-Vertex loops. Claude only calls tools
     * present in the request's `tools` array, so without this per-step refresh
     * a tool discovered via search_tools is unreachable for the rest of the
     * turn. Mutates the array in place (requestParams holds it by reference).
     */
    private refreshAnthropicToolDeclarations;
    /**
     * Dispatch-miss recovery for the Claude-on-Vertex loops.
     */
    private resolveAnthropicToolOnMiss;
    /**
     * Build the synthetic `final_result` tool used to force structured output
     * on Claude-on-Vertex. Anthropic has no native responseSchema, so a schema
     * is instead enforced by requiring the model to call this tool with
     * matching arguments. Single source for the non-streaming and streaming
     * paths — both previously built this object independently from their own
     * schema variable, byte-identical apart from that variable's name.
     */
    private buildFinalResultTool;
    /**
     * Execute stream using native @google/genai SDK for Gemini 3 models on Vertex AI
     * This bypasses @ai-sdk/google-vertex to properly handle thought_signature
     */
    private executeNativeGemini3Stream;
    /**
     * Resolve the text a native Vertex *generate* call actually sends, for
     * both `executeNativeGemini3Generate` and `executeNativeAnthropicGenerate`.
     *
     * The baseline here is the same `input.text || prompt || "Please
     * respond."` chain both call sites have always used — `input.text` wins
     * when set because the file preprocessors (`processUnifiedFilesArray`,
     * `processCSVFilesForNativeSDK`) append attached-file content to it while
     * `options.prompt` stays the pre-attachment snapshot; `prompt` is the
     * fallback for the legacy prompt-only `generateText()` convention, which
     * never sets `input` at all; the literal is the last resort when neither
     * is set.
     *
     * That `||` chain alone has a gap model middleware falls into:
     * `applyTurnParamsRewrite` writes every rewritten turn back onto
     * `options.input.text`, including an *emptied* one (a redaction). `||`
     * treats that empty string exactly like an unset `input.text` and falls
     * through to `options.prompt` — which middleware never touched, since it
     * is a plain snapshot taken before middleware ran — so a redaction a
     * middleware applied is silently discarded and the ORIGINAL text still
     * reaches Vertex.
     *
     * The fix is narrow: when `input.text` is *set* (not undefined) and
     * differs from `prompt`, something deliberately changed it since the
     * snapshot was taken — a middleware rewrite, or a file preprocessor's
     * attachment-content append — and that divergence itself is the signal to
     * trust `input.text` outright, empty string included. When the two agree
     * (the untouched, no-middleware case, including the STT-silence
     * `input.text === prompt === ""` placeholder) there is no divergence to
     * trust, so the original fallback chain still applies unchanged.
     */
    private resolveNativeGenerateText;
    /**
     * Execute generate using native @google/genai SDK for Gemini 3 models on Vertex AI
     * This bypasses @ai-sdk/google-vertex to properly handle thought_signature
     */
    private executeNativeGemini3Generate;
    /**
     * One-shot, tools-disabled model call used when a native Gemini agentic loop
     * is force-terminated by the step cap with no text produced. Lets the model
     * synthesize a final answer from the function results already in `contents`
     * instead of returning a canned placeholder (Bug 1, part b).
     *
     * Tools are disabled by OMITTING `config.tools` — the codebase's established
     * mechanism. `@google/genai`'s `FunctionCallingConfigMode.NONE` is documented
     * as equivalent to passing no function declarations, and `functionCallingConfig`
     * is not used anywhere in this codebase. When the structured-output
     * (`final_result`) pattern was active, a trailing instruction countermands the
     * earlier "you MUST call final_result" directive so the model answers in plain
     * text. Never throws — returns empty text so the caller falls back to the
     * graceful cap message (buildToolLoopCapMessage), guaranteeing no new failure
     * path.
     */
    private synthesizeFinalAnswerWithoutTools;
    /**
     * Create native AnthropicVertex client for Claude models
     */
    private createAnthropicVertexClient;
    /**
     * Execute stream using native @anthropic-ai/vertex-sdk for Claude models on Vertex AI
     * This bypasses @ai-sdk/google-vertex completely and uses Anthropic's native SDK
     */
    /**
     * Extended thinking for Claude-on-Vertex.
     *
     * The direct Anthropic provider has always translated `thinkingConfig` into
     * the Messages API's `thinking` field (anthropic/client.ts). This path never
     * did — it built the request without one — so `thinkingConfig` was accepted
     * and silently ignored here: no error, `usage.reasoning` 0, no reasoning
     * content. Measured against the raw @anthropic-ai/vertex-sdk with the same
     * project, region, credentials and model, `thinking` is supported and
     * returns a real thinking block, so the capability was ours to send.
     *
     * `thinkingLevel` is deliberately not mapped to a budget: the option's
     * contract reserves `budgetTokens` for Anthropic models and `thinkingLevel`
     * for Gemini 3, and inventing a conversion here would be guessing at the
     * caller's intent.
     *
     * The budget must leave room inside `max_tokens` for an answer, so it is
     * clamped below the ceiling rather than passed through — an over-large
     * budget is a 400 from the API.
     *
     * `forcesToolChoice` (schema mode on a model that accepts a forced choice)
     * pairs with a forced `tool_choice:{type:"any"}` in the request built right
     * after this call — Anthropic hard-rejects `thinking` combined with a `tool_choice`
     * that forces tool use: a live 400, "Thinking may not be enabled when
     * tool_choice forces tool use." So `thinking` is omitted entirely in that
     * mode, preserving the prior (pre-thinking-fix) behaviour of silently
     * ignoring `thinkingConfig` for schema calls instead of hard-failing them —
     * mirrors the same guard already applied to the OAuth proxy path in
     * `src/lib/proxy/oauthFetch.ts` (`delete parsed.thinking` when
     * `tool_choice.type` is `"any"` or `"tool"`). The step/context-cap
     * finalization backstop reuses this same omission for free since it spreads
     * `...requestParams`. `tool_choice:{type:"none"}` (the separate
     * tools-disabled backstop, used only outside schema mode) does not force
     * tool use — it forces the opposite — so it is not gated here, consistent
     * with oauthFetch.ts leaving `"none"` alone too.
     */
    private buildClaudeThinkingParam;
    private executeNativeAnthropicStream;
    /**
     * Execute generate using native @anthropic-ai/vertex-sdk for Claude models on Vertex AI
     */
    private executeNativeAnthropicGenerate;
    /**
     * Process CSV files and append content to options.input.text
     * This ensures CSV data is available in the prompt for native Gemini 3 SDK calls
     * Returns a new options object with modified input (immutable pattern)
     */
    private processCSVFilesForNativeSDK;
    /**
     * Override stream to handle image generation models
     * Image models don't support streaming, so we fall back to generate
     */
    stream(optionsOrPrompt: StreamOptions | string): Promise<StreamResult>;
    private observeMediaGeneration;
    /**
     * Override generate to route ALL models to native SDKs
     * No more @ai-sdk/google-vertex dependency
     */
    generate(optionsOrPrompt: TextGenerationOptions | string): Promise<EnhancedGenerateResult | null>;
    /**
     * Invoke `options.onError` with the lifecycle payload shape consumers
     * (and `test:middleware`) expect. Mirrors {@link fireGenerateOnFinish}.
     */
    private fireGenerateOnError;
    /**
     * Wrap a {@link StreamResult} so each text chunk drives `options.onChunk`
     * and the final yield drives `options.onFinish`. Pipeline A providers get
     * this for free via the AI SDK `wrapStream` middleware; native @google/genai
     * bypasses that wrapper, so native consumers need their lifecycle
     * callbacks invoked from here.
     *
     * `BaseProvider.stream()` always passes the result this method returns
     * through `wrapStreamWithLifecycleCallbacks` afterwards too (that wrapper
     * has "no early return when there are no callbacks" — see its own doc
     * comment) — so unconditionally firing here double-fires onChunk/onFinish
     * for every native Vertex stream. `isLifecycleStreamCallbacksOwnedByBaseProvider`
     * reads the SAME nested lifecycle config off the SAME `options` object
     * `wrapStreamWithLifecycleCallbacks` reads from (NeuroLink.applyStreamLifecycleMiddleware
     * stamps it before either method runs), so both sites agree on which one
     * actually fires without a second, Vertex-specific marker — and without
     * relying on a Symbol on the `StreamResult` itself, which would not
     * survive `withStreamModelFallback`'s rebuild of a plain forwarding object
     * between this method and `wrapStreamWithLifecycleCallbacks`.
     *
     * onError is deliberately NOT gated by that marker — same precedent as
     * `middleware/builtin/lifecycle.ts`'s `wrapStream` ("onError is NOT
     * covered by this flag: it keeps its own, independent dedup via
     * fireOnErrorOnce's shared fired-marker"). `fireOnErrorOnce` stamps the
     * error so `BaseProvider`'s own catch (which checks
     * `hasLifecycleErrorFired`) skips its own fire for the same failure.
     */
    private wrapStreamResultWithLifecycle;
    /**
     * The text a native Vertex turn is built from before any model middleware
     * rewrite — `options.input.text` when the caller set it (the normal
     * `generate()`/`stream()` convention), else `options.prompt` (the legacy
     * prompt-only `generateText()` convention, where `input` is never
     * populated — see `generateTextInInstanceScope` in `src/lib/neurolink.ts`,
     * which validates `options.prompt` and never touches `options.input`).
     *
     * `buildTurnPromptForMiddleware` and `applyTurnParamsRewrite` both read
     * this so they agree on one baseline: the first so a prompt-only caller
     * shows middleware its real text instead of an empty turn, the second so
     * a middleware-rewritten turn is compared against what middleware actually
     * started from — not a baseline that ignores `prompt` entirely, which
     * would make a prompt-only call look "unedited" no matter what middleware
     * did to it. `StreamOptions` carries no top-level `prompt` field, hence
     * the `"prompt" in options` guard instead of a cast.
     */
    private vertexTurnBaselineText;
    /**
     * Build the V3 entry-turn prompt middleware sees for a native call.
     * Native Vertex loops build their own multi-turn conversation internally
     * once they run — this is only the caller's system prompt + text input,
     * the one turn middleware is given visibility into before that loop
     * starts.
     *
     * The user turn is an array of text parts rather than a bare string. That
     * is the V3 prompt shape, and prompt-editing middleware is written against
     * it: one that spreads `content` into a longer array turns a string into
     * one element per character, and one that calls `.map` / `.filter` on it
     * throws. The AI Studio path already hands its middleware parts
     * (`geminiContentsToV3Prompt`); this makes Vertex agree with it.
     *
     * The text itself comes from `vertexTurnBaselineText`, not
     * `options.input?.text` alone — a prompt-only `generateText()` caller
     * never sets `input`, and without the `options.prompt` fallback middleware
     * would be shown an empty turn and have nothing of the caller's to inspect
     * or build on.
     */
    private buildTurnPromptForMiddleware;
    /** Sampling params a native call already honors, carried onto the V3 view. */
    private buildTurnV3Params;
    /**
     * Read a middleware-transformed prompt back into the two things a native
     * Vertex turn can carry: one system instruction and one user text.
     *
     * Every system message counts (joined with a blank line, the way
     * `v3PromptToGeminiContents` joins them for AI Studio) and so does every
     * user message, not just the last. A middleware that appends or prepends
     * context leaves the caller's own text in the prompt beside it; reading
     * only the last user message would send the addition without the question
     * it was meant to qualify, or drop it and send the question bare. Text
     * blocks — across messages and across the parts of one message — are joined
     * with a blank line for the same reason: they are separate blocks, and
     * gluing them runs the last word of one into the first of the next.
     *
     * `unmapped` counts what a native turn has no place for — non-text user
     * parts (files, images) and assistant or tool messages — so the caller can
     * say it was dropped rather than drop it silently.
     */
    private readTurnFromPrompt;
    /**
     * Apply a middleware-transformed turn back onto the native call options.
     *
     * The system instruction and the user text are each written back only when
     * they differ from what middleware actually started from — `systemPrompt`
     * against `options.systemPrompt`, user text against
     * `vertexTurnBaselineText(options)`, not `options.input?.text` alone — so a
     * middleware that touches neither leaves both exactly as they were. An
     * edit is honoured in every direction — a changed, added or removed system
     * message, an appended or prepended user message, a user message emptied
     * outright (a redaction) — because every native generate/stream executor
     * resolves its wire text through `options.input.text` once this write-back
     * has run (`resolveNativeGenerateText` on the generate paths, which
     * special-cases exactly this divergence so an emptied `input.text` is not
     * mistaken for an unset one and does not fall back to the stale
     * `options.prompt` snapshot; a direct `options.input.text` read on the
     * stream paths, which have no such fallback to fall into). Comparing
     * against `options.input?.text` alone — ignoring `options.prompt` — would
     * make a prompt-only `generateText()` caller's untouched turn look
     * "changed" the first time middleware ran (nothing to compare `turn.text`
     * against but `""`), writing the real prompt into `input.text` as a
     * spurious edit on every such call even when no middleware did anything.
     *
     * Sampling params are written back the same way and can be removed as well
     * as changed: a middleware that drops `temperature` or `topP` from the
     * params must reach the wire as "not sent", not as the caller's original
     * value kept because the key went missing.
     *
     * `tools` is offered to middleware read-only — a middleware that rewrites
     * it gets a WARN rather than a silent drop, matching the OpenAI-compatible
     * streaming path's contract: native tool wiring is derived independently
     * of this V3 view, and re-deriving it here would diverge from it.
     */
    private applyTurnParamsRewrite;
    /**
     * Strip the lifecycle middleware from the options handed to
     * `applyMiddlewareToModel` for a native Vertex call, when something else is
     * already firing the same callbacks.
     *
     * NeuroLink's `applyGenerateLifecycleMiddleware` /
     * `applyStreamLifecycleMiddleware` (neurolink.ts) mirror a caller's
     * top-level `onFinish` / `onError` / `onChunk` into
     * `options.middleware.middlewareConfig.lifecycle.config` — the exact same
     * callback references — before this provider sees `options`. Left enabled,
     * the built-in lifecycle middleware would fire them again from inside the
     * bridge, and with malformed payloads: it reads the legacy `textDelta` chunk
     * field and a bare `finishReason`, neither of which a V3 model produces.
     *
     * Who else fires them differs by path, so the exclusion does too:
     *
     * - generate: only `fireGenerateOnFinish` / `fireGenerateOnError`, which read
     *   the TOP-LEVEL callbacks. The entry is stripped only when one is present.
     *   A caller who configures `middlewareConfig.lifecycle` directly has no
     *   other firer here, so that middleware applies exactly once, unmodified.
     * - stream: `BaseProvider.stream()` wraps every stream in
     *   `wrapStreamWithLifecycleCallbacks`, which fires whatever sits in
     *   `lifecycle.config` however it got there — top-level shorthand or direct
     *   config. The entry is stripped whenever it exists, or a direct-config
     *   caller would get every callback twice (and `onChunk` a third time, for
     *   the `finish` part the middleware also reports).
     *
     * Only the `lifecycle` entry is disabled, so every other configured
     * middleware (guardrails, transformParams, custom hooks, analytics, ...)
     * applies normally.
     */
    private excludeAutoLifecycleMiddleware;
    /**
     * Run the native Gemini generate loop and, when Vertex rejects an
     * over-constrained `responseSchema`, retry once without it.
     *
     * The retry sits inside the function `runNativeGenerateWithMiddleware` hands
     * to the model bridge rather than around the bridge, because it is
     * provider-internal recovery: model middleware must see one `doGenerate`
     * that succeeds. Retrying outside would show every middleware the failed
     * first call — the lifecycle middleware would report an `onError` for a
     * request that then succeeded, and `transformParams` would run twice.
     */
    private executeNativeGemini3GenerateWithSchemaFallback;
    /**
     * Apply the configured middleware chain around a native Vertex generate
     * loop. `callNative` is `executeNativeAnthropicGenerate` or
     * `executeNativeGemini3Generate` — a self-contained black box that runs
     * its own multi-step tool loop and returns a fully-resolved
     * `EnhancedGenerateResult`. Wrapping happens around that call, not inside
     * it: `transformParams` can rewrite the entry turn before the loop starts,
     * and `wrapGenerate` can observe the result or replace it outright (a
     * guardrail that blocks the call entirely never reaches `callNative`, so
     * `nativeResult` stays unset and a settled result is synthesized purely
     * from what middleware produced, then run through `enhanceResult` like any
     * other result so `enableAnalytics` / `enableEvaluation` still apply).
     */
    private runNativeGenerateWithMiddleware;
    /**
     * Apply the configured middleware chain around a native Vertex stream
     * loop. `callNative` is `executeNativeAnthropicStream` or
     * `executeNativeGemini3Stream`. Both are bridged through the same lazy V3
     * `ReadableStream` (`nativeChunksToV3Stream` / `v3StreamToNativeChunks`)
     * regardless of whether the underlying loop is genuinely live (Anthropic)
     * or already fully resolved (Gemini3) by the time it returns — pulling one
     * item at a time is correct for both, and never turns a live stream into
     * collect-then-replay.
     *
     * A guardrail that blocks the call never invokes `doStream`, so
     * `nativeResult` stays unset; a `StreamResult` is synthesized instead,
     * with `usage` / `finishReason` resolving once the merged stream is fully
     * drained (the same late-resolving-getter contract
     * `preserveStreamResultAccessors` already exists for).
     */
    private runNativeStreamWithMiddleware;
    /**
     * Re-apply getter-based accessor properties from a source StreamResult onto
     * a wrapper copy. Wrapper spreads (`{ ...result }`) invoke and SNAPSHOT
     * enumerable getters at wrap time — for background-loop streams (the native
     * Anthropic path) that resolve finishReason / structuredOutput / toolCalls
     * / usage only as the consumer drains, the snapshot is permanently
     * undefined/empty. Copying the accessor descriptors keeps the wrapped
     * result live. Results built from plain data properties (the buffered
     * Gemini paths, and the native Anthropic stream's own `usage` — a mutable
     * object reference rather than a getter, so a spread keeps its identity
     * and later mutations stay visible) have no matching getter here and pass
     * through untouched.
     *
     * The re-applied property also accepts a direct write: NeuroLink.stream()
     * backstops a missing `usage` from analytics once the outer stream drains
     * by assigning `mcpStreamOutcome.usage = resolvedUsage` on whatever result
     * object it was handed. Copying the bare getter-only descriptor verbatim
     * would turn that assignment into a TypeError ("Cannot set property usage
     * of #<Object> which has only a getter"), so each re-applied accessor is
     * rebuilt with a setter that remembers an override and prefers it over the
     * live source getter once one has been written.
     */
    private preserveStreamResultAccessors;
    private withClaudeGeneration;
    /**
     * Emit `generation:end` so the Pipeline B observability listener creates
     * the corresponding `model.generation` span. Vertex bypasses the AI SDK
     * (and therefore the experimental_telemetry plumbing), so this hand-off
     * is the only way native Vertex calls show up in Langfuse / Pipeline B
     * exporters. Mirrors the Bedrock + Ollama pattern.
     */
    private emitGenerationEnd;
    /**
     * Turn-clock-shaped adapter over the shared {@link buildLoopExitMessage}.
     * Every call site in this file holds a clock, so the mapping lives here
     * rather than at ten call sites; the decision itself is the shared one.
     */
    private buildLoopExitMessage;
    protected formatProviderError(error: unknown): Error;
    /**
     * Memory-safe cache management for model configurations
     * Implements LRU eviction to prevent memory leaks in long-running processes
     */
    private static evictLRUCacheEntries;
    /**
     * Access and refresh cache entry (moves to end for LRU)
     */
    private static accessCacheEntry;
    /**
     * Memory-safe cached check for whether maxTokens should be set for the given model
     * Optimized for streaming performance with LRU eviction to prevent memory leaks
     */
    private shouldSetMaxTokensCached;
    /**
     * Memory-safe check if model has maxTokens issues using configuration-based approach
     * This replaces hardcoded model-specific logic with configurable behavior
     * Includes LRU caching to avoid repeated configuration lookups during streaming
     */
    private modelHasMaxTokensIssues;
    /**
     * Check if Anthropic models are available
     * @returns Promise<boolean> indicating if Anthropic support is available
     */
    hasAnthropicSupport(): Promise<boolean>;
    /**
     * Register a tool with the AI provider
     * @param name The name of the tool
     * @param schema The Zod schema defining the tool's parameters
     * @param description A description of what the tool does
     * @param handler The function to execute when the tool is called
     */
    registerTool(name: string, schema: ZodType<unknown>, description: string, handler: (params: Record<string, unknown>) => Promise<unknown>): void;
    /**
     * Set the context for tool execution
     * @param context The context to use for tool execution
     */
    setToolContext(context: Record<string, unknown>): void;
    /**
     * Get the current tool execution context
     * @returns The current tool execution context
     */
    getToolContext(): Record<string, unknown>;
    /**
     * Set the tool executor function for custom tool execution
     * This method is called by BaseProvider.setupToolExecutor()
     * @param executor Function to execute tools by name
     */
    setToolExecutor(executor: (toolName: string, params: unknown) => Promise<unknown>): void;
    /**
     * Clear all static caches - useful for testing and memory cleanup
     * Public method to allow external cache management
     */
    static clearCaches(): void;
    /**
     * Get cache statistics for monitoring and debugging
     */
    static getCacheStats(): {
        modelConfigCacheSize: number;
        maxTokensCacheSize: number;
        maxCacheSize: number;
        cacheAge: {
            modelConfig: number;
            maxTokens: number;
        };
    };
    /**
     * Detect image MIME type from buffer
     */
    private detectImageType;
    /**
     * Estimate token count from text (simple character-based estimation)
     */
    private estimateTokenCount;
    /**
     * Build image parts for multimodal content
     */
    /**
     * Overrides the BaseProvider's image generation method to implement it for Vertex AI.
     * Uses REST API approach with google-auth-library for authentication.
     * Supports PDF input for image generation with gemini-3-pro-image-preview (Nano Banana Pro).
     * @param options The generation options containing the prompt and optional PDF files.
     * @returns A promise that resolves to the generation result, including the image data.
     */
    protected executeImageGeneration(options: TextGenerationOptions): Promise<EnhancedGenerateResult>;
    /**
     * Get model suggestions when a model is not found
     */
    /**
     * Candidate model ids for a "model not available" error.
     *
     * This list is static. It cannot know what the caller's project and region
     * actually serve, so it must not claim to: it previously announced
     * "always available" and included the requested model itself, which
     * produced errors that recommended the very id that had just failed —
     * `gemini-3-pro-preview-11-2025` suggesting `gemini-3-pro-preview-11-2025`.
     * The requested model is now filtered out, and the wording says these are
     * ids to try rather than ids known to work.
     */
    private getModelSuggestions;
    /**
     * Generate an embedding for `text` using Vertex via @google/genai.
     *
     * Replaces the previous `@ai-sdk/google-vertex` text embedding model
     * path. Without this, RAG indexing falls through to BaseProvider.embed()
     * which throws "Embedding generation is not supported by the vertex
     * provider", and `neurolink rag index --provider=vertex` fails even
     * though the SDK conceptually supports it.
     */
    embed(input: string | EmbedInput, modelName?: string): Promise<number[]>;
    /**
     * Batch-embed an array of strings via Vertex @google/genai.
     * Mirrors {@link embed} but returns one vector per input string.
     */
    embedMany(texts: string[], modelName?: string): Promise<number[][]>;
}
export default GoogleVertexProvider;
export { GoogleVertexProvider as GoogleVertexAI };