agent.libx.js 0.93.32 → 0.93.33

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (2) hide show
  1. package/README.md +2 -1
  2. package/package.json +1 -1
package/README.md CHANGED
@@ -44,7 +44,8 @@ console.log(res.finishReason, await fs.readFile('/src/x.ts'));
44
44
  - **`Edit`** — exact unique-substring replace, with a read-before-edit staleness guard.
45
45
  - **`Grep`/`Glob`/`Write`/`MultiEdit`** — structured, typed results straight from the VFS (no `bash` parsing). The selectable tool set the self-evolution loop mutates over.
46
46
  - **`TodoWrite`** — a planning scratchpad; **`Task`** — spawn a depth-limited child agent over the VFS (`subagents: true`); **`SlashCommand`** — reusable prompt templates from `<dir>/*.md` (`commandsDir`); plus a real **MCP client** (`src/mcp.client.ts`, node-only — stdio/HTTP JSON-RPC handshake + discovery) that feeds the edge-safe **MCP adapter** (`mcpToolsToAgentTools`), so any MCP server's tools become agent tools.
47
- - **`WebFetch`/`WebSearch`** — opt-in network tools (not in the default set): fetch a URL as readable text, or search via a configured provider (`TAVILY_API_KEY`). Enable per project with `tools: [...,'WebFetch']` in config. Factory-built with an injectable `fetch`, so they stay edge-portable and testable.
47
+ - **`WebFetch`/`WebSearch`** — fetch a URL as readable text, or search the web. **Keyless by default** (WebSearch uses DuckDuckGo; auto-upgrades to Tavily when `TAVILY_API_KEY` is set) and **auto-enabled in the CLI**. Factory-built with an injectable `fetch`, so they stay edge-portable and testable. (In the library they're opt-in by name: `tools: [...,'WebSearch']`.)
48
+ - **Oversized-output pagination** — any tool result over a byte ceiling (`maxToolResultBytes`, default 60k) is cropped to page 1 with a marker (refine the query / read further), so one big `Grep`/`Read`/MCP/web result can't blow the context window. In the CLI (**on by default**; `--no-scratch` to disable) the full output instead spills **losslessly** to a **scratch** file and the model recovers specifics via `Grep`/`Read` or **`Ask`** — a cheap, context-isolated peek that returns just the answer (the raw blob never re-enters context).
48
49
 
49
50
  ## Agentic subsystems
50
51
 
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "agent.libx.js",
3
- "version": "0.93.32",
3
+ "version": "0.93.33",
4
4
  "description": "Edge-native AI agent runtime — drives a virtual filesystem via any LLM (ai.libx.js). Same bytes run in node, browser, or edge.",
5
5
  "type": "module",
6
6
  "main": "./dist/index.js",