@autorag/librarian 2.4.1 → 2.4.2

package/README.md

@@ -465,7 +465,7 @@ installations in `PATH` (or set `JAVA_HOME` to the Java 11+ installation and
 start a new shell). Java 8 is not supported by the PDF parser.
 
 Git-based installs build `dist/` via the `prepare` script and require Bun on the installing machine.
-External tool binaries auto-install on first use into `<workspace>/.autorag/bin`: **MinSync** downloads a verified GitHub release asset (on by default; `minSync.autoInstall: false` to opt out), and **Jikji** compiles the [`jikji-cli`](https://crates.io/crates/jikji-cli) crate via cargo (requires the [Rust toolchain](https://rustup.rs); `jikji.autoInstall: false` to opt out). New `autorag init` configs enable Jikji find-first discovery by default. KakaoTalk (`katok`) and Discord (`discrawl`) stay manual, optional installs. All of them degrade gracefully when missing — core BM25 search works without any of them.
+External tool binaries auto-install on first use into `<workspace>/.autorag/bin`: **MinSync** installs from crates.io via `cargo install minsync` first (on by default; verified GitHub release assets are the fallback when cargo is unavailable; `minSync.autoInstall: false` to opt out), and **Jikji** compiles the [`jikji-cli`](https://crates.io/crates/jikji-cli) crate via cargo (requires the [Rust toolchain](https://rustup.rs); `jikji.autoInstall: false` to opt out). New `autorag init` configs enable Jikji find-first discovery by default. KakaoTalk (`katok`) and Discord (`discrawl`) stay manual, optional installs. All of them degrade gracefully when missing — core BM25 search works without any of them.
 
 ### Experimental TUI (beta)
 

package/dist/agent/agent.d.ts

@@ -8,6 +8,7 @@ import type { ResultFeedback } from "../memory/memory.js";
 import { type MinSyncSyncResult, type MinSyncVectorMethodOptions } from "../minsync/index.js";
 import { type ParsedMirrorSyncResult } from "../mirror/sync.js";
 import type { DefaultParserRegistryOptions } from "../parser/index.js";
+import { RetrievalEngine } from "../retrieval/engine.js";
 import { RetrievalMethodRegistry } from "../retrieval/registry.js";
 import type { CuratedResult, RetrievalDiagnostic, RetrievalOptions, RetrievalResult } from "../retrieval/types.js";
 import { type ScanDuplicateDocumentsDetails } from "./dupey-tool.js";
@@ -236,7 +237,7 @@ export declare class AutoRAGAgent {
      */
     private scanMirrorStaleness;
     private exactDuplicateExclusions;
-    syncMinSync(): Promise<MinSyncSyncResult | undefined>;
+    syncMinSync(force?: boolean): Promise<MinSyncSyncResult | undefined>;
     prepareJikji(): Promise<readonly AutoRAGJikjiPrepareResult[] | undefined>;
     private executeJikjiPrepare;
     /**
@@ -305,6 +306,13 @@ export declare class AutoRAGAgent {
     }>;
     /** The retrieval method registry (posix, MinSync, and datasource methods). */
     getMethodRegistry(): RetrievalMethodRegistry;
+    /**
+     * The standalone retrieval engine for this agent's method pipeline.
+     * Built on first access using the agent's registered methods and configured
+     * datasource access context. Model-free — no agent state required.
+     */
+    private retrievalEngine;
+    getRetrievalEngine(): RetrievalEngine;
     getSystemPrompt(): string;
     private rerankWithMemory;
     private normalizeRetrievalOptions;

package/dist/agent/emit-results-tool.d.ts

@@ -1,7 +1,7 @@
 import type { AgentTool } from "@earendil-works/pi-agent-core";
 import { Type } from "typebox";
 export declare const EMIT_AUTORAG_RESULTS_TOOL_NAME = "emit_autorag_results";
-declare const emitResultsSchema: Type.TObject<{
+export declare const emitResultsSchema: Type.TObject<{
     answer: Type.TString;
     results: Type.TArray<Type.TObject<{
         number: Type.TInteger;
@@ -86,4 +86,3 @@ export interface AutoRAGResultsDetails {
  * assistant-text parsing involved.
  */
 export declare function createEmitResultsTool(capture: (details: AutoRAGResultsDetails) => void): AgentTool<typeof emitResultsSchema, AutoRAGResultsDetails>;
-export {};

package/dist/agent/index.d.ts

@@ -3,7 +3,7 @@ export { AutoRAGAgent } from "./agent.js";
 export { buildDatasourceSkillsPrompt, createLoadDatasourceSkillTool, type DatasourceSkillProvider, datasourceSkillLocation, formatDatasourceSkillInvocation, LOAD_DATASOURCE_SKILL_TOOL_NAME, type LoadDatasourceSkillDetails, toDatasourceAgentSkill, } from "./datasource-skill.js";
 export { createScanDuplicateDocumentsTool, SCAN_DUPLICATE_DOCUMENTS_TOOL_NAME, type ScanDuplicateDocumentsDetails, type ScanDuplicateDocumentsProvider, } from "./dupey-tool.js";
 export type { AutoRAGEmittedResult, AutoRAGMappingEntry, AutoRAGResultsDetails, } from "./emit-results-tool.js";
-export { createEmitResultsTool, EMIT_AUTORAG_RESULTS_TOOL_NAME } from "./emit-results-tool.js";
+export { createEmitResultsTool, EMIT_AUTORAG_RESULTS_TOOL_NAME, emitResultsSchema, } from "./emit-results-tool.js";
 export { createJikjiFindTool, JIKJI_FIND_TOOL_NAME, type JikjiFindDetails, type JikjiFindPerRootPolicy, type JikjiFindProvider, type JikjiFindProviderResult, type MergedJikjiPolicy, } from "./jikji-find-tool.js";
 export { createSearchAllDocumentsTool, SEARCH_ALL_DOCUMENTS_TOOL_NAME, type SearchAllDocumentsDetails, type SearchAllDocumentsProvider, type SearchAllDocumentsResult, } from "./search-all-tool.js";
 export { createSearchDatasourceDocumentsTool, type DatasourceSearchProvider, SEARCH_DATASOURCE_DOCUMENTS_TOOL_NAME, type SearchDatasourceDocumentsDetails, } from "./search-datasource-tool.js";

package/dist/cli/commands/duplicates.d.ts

@@ -1,4 +1,10 @@
 import type { DupeyScanResult } from "../../dupey/index.js";
 import type { CommandContext } from "./types.js";
 export type DuplicateScanner = (path: string) => Promise<DupeyScanResult>;
+/**
+ * `autorag duplicates` — scan configured roots for exact and near duplicate
+ * document families. Never deletes or moves source files.
+ *
+ * Exit codes: 0 on success, 2 on config error, 1 on runtime error.
+ */
 export declare function runDuplicates(ctx: CommandContext, scanner?: DuplicateScanner): Promise<number>;

package/dist/cli/commands/lite-refresh.d.ts

@@ -0,0 +1,10 @@
+import type { CommandContext } from "./types.js";
+/**
+ * `autorag lite refresh` — model-free index refresh using AutoRAGLite.
+ *
+ * Delegates to the agent's refresh pipeline (parsed mirrors, MinSync,
+ * datasources, Jikji) without requiring any model configuration.
+ *
+ * Exit codes: 0 on success, 2 on config error, 1 on runtime error.
+ */
+export declare function runLiteRefresh(ctx: CommandContext): Promise<number>;

package/dist/cli/commands/lite-retrieve.d.ts

@@ -0,0 +1,33 @@
+import type { CommandContext } from "./types.js";
+export interface LiteRetrieveEnvelope {
+    readonly ok: true;
+    readonly query: string;
+    readonly results: readonly LiteRetrieveResultItem[];
+    readonly diagnostics: readonly LiteRetrieveDiagnostic[];
+}
+export interface LiteRetrieveResultItem {
+    readonly number: number;
+    readonly source: string;
+    readonly method: string;
+    readonly score: number;
+    readonly metadata: Record<string, unknown>;
+    readonly content: string;
+}
+export interface LiteRetrieveDiagnostic {
+    readonly code: string;
+    readonly severity: string;
+    readonly message: string;
+    readonly source?: string;
+}
+/**
+ * Run the `autorag lite retrieve` command.
+ *
+ * Returns exit code 2 for:
+ *  - Empty query
+ *  - Config resolution failure
+ *  - Index not ready (never refreshed)
+ *
+ * Returns exit code 0 on successful retrieval (results may be empty).
+ * Returns exit code 1 for runtime errors.
+ */
+export declare function runLiteRetrieve(ctx: CommandContext): Promise<number>;

package/dist/cli/commands/lite.d.ts

@@ -0,0 +1,3 @@
+import type { CommandContext } from "./types.js";
+export declare function liteUsage(): string;
+export declare function runLite(ctx: CommandContext): Promise<number>;

package/dist/cli/commands/report.d.ts

@@ -0,0 +1,3 @@
+import type { CommandContext } from "./types.js";
+/** Persist a structured report submitted by an external curator. */
+export declare function runReport(ctx: CommandContext): Promise<number>;

package/dist/cli/commands/status.d.ts

@@ -3,5 +3,7 @@ import type { CommandContext } from "./types.js";
  * `autorag status` — path-opaque snapshot of corpus freshness and index health.
  * Runs a cheap parse-free staleness scan plus the cached last-refresh outcome.
  * Model-free. Never emits filesystem paths; only the renderered status text.
+ *
+ * Exit codes: 0 on success, 2 on config error, 1 on runtime error.
  */
 export declare function runStatus(ctx: CommandContext): Promise<number>;

package/dist/cli/commands/watch.d.ts

@@ -4,5 +4,7 @@ import type { CommandContext } from "./types.js";
  *
  * - default: long-running recursive fs watch with debounced refresh
  * - `--once`: single refresh tick (for cron / launchd / Task Scheduler)
+ *
+ * Exit codes: 0 on success, 2 on config error, 1 on runtime error.
  */
 export declare function runWatch(ctx: CommandContext): Promise<number>;