@autorag/librarian 2.13.2 → 2.13.4

package/NOTICE

@@ -36,6 +36,9 @@ License: Apache-2.0
 fast-xml-parser@5.11.2
 License: MIT
 
+gpt-tokenizer@4.1.0
+License: MIT
+
 iconv-lite@0.7.3
 License: MIT
 

package/README.md

@@ -667,7 +667,6 @@ AutoRAG Agent connects to external tools and communication platforms using dedic
 | **Cloud Drives** | `cloud-drive` | [`rclone`](https://rclone.org) CLI | Google Drive (Tier-1), OneDrive, Dropbox, etc. | Incremental Mirror + BM25 |
 | **Photos & Shots** | `clawgallery` | `clawgallery` CLI | Local screenshot and photo store | Hybrid OCR/Visual Search |
 | **RSS / News** | `rss` | Native HTTP Poller | RSS 2.0 & Atom feeds (24h deduplication) | Lexical |
-| **macOS Spotlight** | `spotlight` | Native `mdfind` CLI | macOS system metadata and content index | System Native |
 | **Browser History** | `hister` | [Hister](https://github.com/asciimoo/hister) server (AGPL-3.0-or-later, separate program, HTTP API) | Pages visited in Chrome/Chromium/Firefox, captured by Hister's own extension and indexed by Hister (web pages only; its local-file indexing is never used) | Lexical full-text; optional Semantic via Hister's own embedding endpoint |
 
 For configuration syntax and connector details, see [docs/datasource-skills.md](docs/datasource-skills.md). Non-interactive `sync`/`index` steps get a one-hour per-connector budget (`connector.indexTimeoutMs`) because first-run imports routinely take minutes; interactive search keeps its 60-second default.

package/dist/agent/context-token-guard.d.ts

@@ -20,15 +20,20 @@ export declare function createContextTokenGuardedTransform(model: ContextTokenGu
 /** The model with its output limit held to {@link MAX_OUTPUT_TOKENS}; the same model when already within it, or when absent. */
 export declare function withBoundedOutput<T extends Model<any> | undefined>(model: T): T;
 /**
- * Keep complete retrieval candidates while the assembled request fits the
- * model budget. Removing a per-chunk cut is only safe because this drops whole
- * lower-ranked candidates (with an explicit marker) instead of hiding text.
+ * Keep the request inside the model budget by dropping retrieval chunks only: the
+ * lowest-ranked ones go first, across every ranked list in the transcript (every
+ * list's best chunk stays before any list's second), each with an explicit marker.
+ * The user's query, earlier turns, and the system prompt are never edited. When no
+ * chunk is left to drop, only the newest tool result is shortened; anything still
+ * too large is left for the provider to reject and pi's compaction to recover.
  */
 export declare function guardAgentContextMessages(model: Model<any> | undefined, messages: AgentMessage[], useReportedUsage?: boolean, fixedOverheadTokens?: number): AgentMessage[];
 /**
- * Estimate the current transcript with pi-coding-agent's conservative chars/4
- * counter. `useReportedUsage` adds the last assistant turn's provider-reported
- * usage for the settled prefix; pass false when the messages were just edited.
+ * Estimate the current transcript: pi-coding-agent's chars/4 counter as the
+ * floor, raised by a real BPE count for text that chars/4 undercounts (see
+ * `token-count.ts`). `useReportedUsage` adds the last assistant turn's
+ * provider-reported usage for the settled prefix; pass false when the messages
+ * were just edited.
  */
 export declare function estimateContextMessageTokens(messages: readonly AgentMessage[], useReportedUsage?: boolean): number;
 export {};

package/dist/agent/token-count.d.ts

@@ -0,0 +1,4 @@
+/** Tokens in `text`, never fewer than the chars/4 guess so prose keeps the budget it had. */
+export declare function estimateTextTokens(text: string): number;
+/** How many tokens the pieces add beyond their chars/4 guesses; zero for prose. */
+export declare function tokensBeyondCharGuess(parts: readonly string[]): number;