@juspay/neurolink/dist/constants/contextWindows.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

/**
 * Context Window Registry
 *
 * Accurate per-provider, per-model context window sizes (INPUT token limits).
 * These are distinct from OUTPUT token limits in tokens.ts.
 *
 * Sources:
 * - Anthropic: https://docs.anthropic.com/en/docs/about-claude/models
 * - OpenAI: https://platform.openai.com/docs/models
 * - Google: https://ai.google.dev/gemini-api/docs/models
 * - Others: Provider documentation as of Feb 2026
 */
/** Default context window when provider/model is unknown */
export declare const DEFAULT_CONTEXT_WINDOW = 128000;
/** Maximum output reserve when maxTokens not specified */
export declare const MAX_DEFAULT_OUTPUT_RESERVE = 64000;
/** Default output reserve ratio (35% of context) */
export declare const DEFAULT_OUTPUT_RESERVE_RATIO = 0.35;
/**
 * Per-provider, per-model context window sizes.
 * The "_default" key is the fallback for unknown models within a provider.
 */
export declare const MODEL_CONTEXT_WINDOWS: Record<string, Record<string, number>>;
/**
 * Register a runtime-discovered context window for a provider/model pair.
 * Later registrations overwrite earlier ones (rediscovery refreshes values).
 * Non-positive/non-finite windows are ignored so a malformed discovery source
 * can never shrink a budget to zero.
 */
export declare function registerRuntimeContextWindow(provider: string, model: string, contextWindow: number): void;
/** Test hook: clear runtime-discovered windows (state is module-global). */
export declare function clearRuntimeContextWindows(): void;
/**
 * Runtime-discovered window for an exact provider/model pair, or undefined.
 *
 * Unlike {@link getContextWindowSize} this NEVER falls back to static table
 * values. Callers use it to distinguish "the serving infrastructure told us
 * the real window" (safe to hard-enforce: clamp max_tokens, fail fast) from
 * "static guess" (advisory only — hard-enforcing a guessed window would
 * falsely reject requests that the real deployment accepts).
 */
export declare function getRuntimeContextWindow(provider: string, model?: string): number | undefined;
/**
 * Register a runtime-discovered output-token ceiling for a provider/model
 * pair. Later registrations overwrite earlier ones (rediscovery refreshes
 * values). Non-positive/non-finite ceilings are ignored so a malformed
 * discovery source can never shrink an output budget to zero.
 */
export declare function registerRuntimeOutputCeiling(provider: string, model: string, maxOutputTokens: number): void;
/**
 * Runtime-discovered output ceiling for an exact provider/model pair, or
 * undefined when the serving infrastructure has not advertised one.
 */
export declare function getRuntimeOutputCeiling(provider: string, model?: string): number | undefined;
/** Remove a model ceiling that discovery no longer advertises as valid. */
export declare function clearRuntimeOutputCeiling(provider: string, model: string): void;
/** Test hook: clear runtime-discovered output ceilings (state is module-global). */
export declare function clearRuntimeOutputCeilings(): void;
/**
 * Resolve context window size for a provider/model combination.
 *
 * Priority:
 *  0. Dynamic model registry (DynamicModelProvider) — resolves cross-provider
 *     models (e.g. Claude on Vertex) that the static table cannot handle
 *  0.5 Runtime-discovered windows (registerRuntimeContextWindow) — real
 *      per-model limits fetched from the serving infrastructure (LiteLLM
 *      `/model/info`)
 *  1. Manifest exact/alias match ONLY (resolveManifestEntryStrict — no prefix, see
 *     src/lib/models/manifestRegistry.ts) — the emerging single source of
 *     truth for per-model metadata. Deliberately consulted for a REAL match
 *     only (never the manifest's synthesized/generic default): most provider
 *     manifests are still "minimal" stubs holding nothing but a provider-wide
 *     default (e.g. vertex.ts, together-ai.ts) and none of the per-model
 *     overrides — including Vertex's Claude "claude-" prefix catch-all below,
 *     which exists specifically to stop an unlisted Claude-on-Vertex model
 *     from inheriting Gemini's 1,048,576 default — that still live only in
 *     MODEL_CONTEXT_WINDOWS. Falling back to a manifest-wide default here
 *     would silently drop that coverage. When a manifest DOES carry a real
 *     entry for this model, it wins even if it disagrees with the legacy
 *     table (e.g. Mistral's manifest supersedes the coarser, older
 *     MODEL_CONTEXT_WINDOWS.mistral values).
 *  2. Exact model match under provider in static registry
 *  3. Prefix match under provider in static registry
 *  4. Provider's _default in static registry
 *  5. Global DEFAULT_CONTEXT_WINDOW
 */
export declare function getContextWindowSize(provider: string, model?: string): number;
/**
 * Calculate output token reserve for a given context window.
 *
 * Returns the *real* token count that will be reserved for output so callers
 * (`getAvailableInputTokens`, `BudgetChecker`, conversation-memory pruning, file
 * summarisation) compute input budget against the actual outgoing maxTokens.
 *
 * @param contextWindow - Total context window size
 * @param maxTokens - Explicit maxTokens from user config (if set)
 * @returns Number of tokens reserved for output (matches what's sent upstream)
 */
export declare function getOutputReserve(contextWindow: number, maxTokens?: number): number;
/**
 * Calculate available input tokens for a given provider/model.
 *
 * available = contextWindow - outputReserve
 */
export declare function getAvailableInputTokens(provider: string, model?: string, maxTokens?: number): number;