ollanet 0.2.2 → 0.4.0

package/dist/prompt.js

@@ -1,4 +1,3 @@
-#!/usr/bin/env node
 /**
  * Run a prompt / continue a chat against an Ollama server on the network.
  *
@@ -14,11 +13,13 @@
  */
 import { stdin as stdinStream } from "node:process";
 import { appendMessage, cleanTopic, createChat, loadChat, saveChat, toApiMessages, topicFromPrompt, } from "./chat-store.js";
-import { configPath, defaultModelForHost, loadConfig, machineSettingsForHost, mergeSettings, parseFormat, settingsFromEnv, settingsSummary, } from "./config.js";
+import { configPath, defaultModelForHost, loadConfig, machineSettingsForHost, mergeSettings, parseFormat, settingsFromEnv, settingsSummary, configFromPartial, } from "./config.js";
 import { discoverHosts, envInt, findDiscoveredHost, ollamaBaseUrl, resolveHost, shortName, } from "./hosts.js";
 import { ollamaChat } from "./ollama-chat.js";
 /** Prompt/chat HTTP timeout (ms). 0 = no timeout. Separate from scan's OLLAMA_TIMEOUT_MS. */
-const PROMPT_TIMEOUT_MS = envInt("OLLAMA_PROMPT_TIMEOUT_MS", 600_000);
+function promptTimeoutMs() {
+    return envInt("OLLAMA_PROMPT_TIMEOUT_MS", 600_000);
+}
 function usage() {
     console.error(`Usage:
   ollanet prompt <machine> [model] <prompt...>
@@ -77,7 +78,7 @@ function modelNameMatches(available, candidate) {
 async function listModelNames(host) {
     const url = `${ollamaBaseUrl(host)}/api/tags`;
     const controller = new AbortController();
-    const timer = setTimeout(() => controller.abort(), Math.min(PROMPT_TIMEOUT_MS || 2500, 5000));
+    const timer = setTimeout(() => controller.abort(), Math.min(promptTimeoutMs() || 2500, 5000));
     try {
         const res = await fetch(url, {
             signal: controller.signal,
@@ -278,7 +279,7 @@ async function generateTopic(opts) {
             model: opts.model,
             stream: false,
             writeStdout: false,
-            timeoutMs: PROMPT_TIMEOUT_MS,
+            timeoutMs: promptTimeoutMs(),
             settings: mergeSettings(opts.settings, {
                 temperature: 0.2,
                 num_predict: 24,
@@ -308,62 +309,48 @@ function formatDuration(ns) {
         return `${ms.toFixed(0)}ms`;
     return `${(ms / 1000).toFixed(1)}s`;
 }
-export async function main() {
-    const parsed = parseArgs(process.argv.slice(2));
-    const { stream, json, save } = parsed;
-    let promptParts = parsed.promptParts;
-    const fromStdin = await readStdinIfPiped();
-    const config = await loadConfig();
+/** Programmatic prompt used by CLI `--json` and the MCP server. */
+export async function runPrompt(opts) {
+    const save = opts.save !== false;
+    const stream = opts.stream !== false && opts.writeStdout !== false;
+    const quiet = opts.quiet === true || opts.writeStdout === false;
+    const writeStdout = opts.writeStdout !== false;
+    let promptParts = opts.prompt ? [opts.prompt] : [];
+    const config = opts.config ? configFromPartial(opts.config) : await loadConfig();
     const { hosts: targets } = await discoverHosts({
         hosts: config.hosts,
         discovery: config.discovery,
     });
     let chat;
     let isNewChat = false;
-    let machineQuery = parsed.machine;
-    if (parsed.chatId) {
-        chat = await loadChat(parsed.chatId);
-        // Allow `ollanet prompt <host> --chat HASH "follow-up"` only when the
-        // leading token matches an already-discovered host (not direct-address fallback).
-        if (!machineQuery && promptParts.length >= 2) {
-            const hit = findDiscoveredHost(targets, promptParts[0]);
-            if (hit) {
-                machineQuery = promptParts[0];
-                promptParts = promptParts.slice(1);
-            }
-        }
+    let machineQuery = opts.machine;
+    if (opts.chatId) {
+        chat = await loadChat(opts.chatId);
     }
     machineQuery = machineQuery ?? chat?.machine;
     if (!machineQuery) {
-        console.error("Machine is required for a new chat (or use --chat <hash>).");
-        usage();
+        throw new Error("Machine is required for a new chat (or pass chatId).");
     }
     const host = resolveHost(targets, machineQuery);
     if (!host.online && !host.isSelf && host.source === "tailscale") {
         throw new Error(`Machine "${shortName(host)}" appears offline.`);
     }
     let peeledModel;
-    if (!parsed.chatId && !parsed.model) {
-        const peeled = await maybePeelModel(host, promptParts, fromStdin);
+    if (!opts.chatId && !opts.model) {
+        const peeled = await maybePeelModel(host, promptParts, "");
         peeledModel = peeled.model;
         promptParts = peeled.promptParts;
     }
-    const promptText = [promptParts.join(" ").trim(), fromStdin].filter(Boolean).join("\n\n").trim();
+    const promptText = promptParts.join(" ").trim();
     if (!promptText) {
-        console.error("No prompt provided (pass args and/or pipe stdin).");
-        usage();
+        throw new Error("No prompt provided.");
     }
-    const model = parsed.model ??
-        peeledModel ??
-        chat?.model ??
-        defaultModelForHost(config, host);
+    const model = opts.model ?? peeledModel ?? chat?.model ?? defaultModelForHost(config, host);
     if (!model) {
         throw new Error(`No model specified for "${shortName(host)}" and no default in ${configPath()}.\n` +
-            `Pass a model, use --model <name>, or add it under defaultModels.`);
+            `Pass a model or add it under defaultModels.`);
     }
-    const settings = mergeSettings(
-    // Thinking models otherwise spend the whole num_predict budget on hidden reasoning.
-    { think: false }, config.defaults, machineSettingsForHost(config, host), settingsFromEnv(), chat?.system ? { system: chat.system } : undefined, parsed.settings);
+    const settings = mergeSettings({ think: false }, config.defaults, machineSettingsForHost(config, host), settingsFromEnv(), chat?.system ? { system: chat.system } : undefined, opts.settings);
     if (!chat && save) {
         chat = createChat({
             machine: shortName(host),
@@ -374,7 +361,6 @@ export async function main() {
         isNewChat = true;
     }
     else if (!chat) {
-        // --no-save one-shot: ephemeral transcript for the API call only
         chat = createChat({
             machine: shortName(host),
             model,
@@ -383,27 +369,27 @@ export async function main() {
         isNewChat = true;
     }
     else {
-        if (parsed.settings.system && !chat.system) {
-            chat.system = parsed.settings.system;
+        if (opts.settings?.system && !chat.system) {
+            chat.system = opts.settings.system;
         }
         chat.model = model;
         chat.machine = shortName(host);
     }
     appendMessage(chat, { role: "user", content: promptText });
     const baseUrl = ollamaBaseUrl(host);
-    if (!json) {
-        const src = parsed.model ? "explicit" : chat && !isNewChat ? "chat" : "default";
+    if (!quiet) {
+        const src = opts.model ? "explicit" : chat && !isNewChat ? "chat" : "default";
         const extras = settingsSummary(settings);
-        const chatTag = parsed.chatId ? `  chat=${chat.id}` : "";
+        const chatTag = opts.chatId ? `  chat=${chat.id}` : "";
         console.error(`→ ${shortName(host)} (${host.ip})  model=${model}  [${src}]${chatTag}${extras ? `  ${extras}` : ""}`);
     }
     const { content, thinking, chunk } = await ollamaChat({
         baseUrl,
         model,
         messages: toApiMessages(chat),
-        stream: json ? false : stream,
-        writeStdout: !json,
-        timeoutMs: PROMPT_TIMEOUT_MS,
+        stream: writeStdout ? stream : false,
+        writeStdout,
+        timeoutMs: promptTimeoutMs(),
         settings,
     });
     appendMessage(chat, {
@@ -429,30 +415,100 @@ export async function main() {
     }
     if (save) {
         const file = await saveChat(chat);
-        if (!json) {
+        if (!quiet) {
             console.error(`chat ${chat.id}  topic: ${chat.topic}`);
             console.error(`saved ${file}`);
             console.error(`continue: ollanet prompt --chat ${chat.id} "your follow-up"`);
         }
     }
-    if (json) {
-        console.log(JSON.stringify({
-            chat_id: save ? chat.id : null,
-            topic: chat.topic,
-            content,
-            thinking: thinking || null,
-            ollama: chunk,
-        }, null, 2));
-        return;
+    return {
+        chat_id: save ? chat.id : null,
+        topic: chat.topic,
+        content,
+        thinking: thinking || null,
+        machine: shortName(host),
+        model,
+        ollama: chunk,
+    };
+}
+export async function main() {
+    const parsed = parseArgs(process.argv.slice(2));
+    const { stream, json, save } = parsed;
+    let promptParts = parsed.promptParts;
+    const fromStdin = await readStdinIfPiped();
+    const config = await loadConfig();
+    const { hosts: targets } = await discoverHosts({
+        hosts: config.hosts,
+        discovery: config.discovery,
+    });
+    let machineQuery = parsed.machine;
+    if (parsed.chatId) {
+        // Allow `ollanet prompt <host> --chat HASH "follow-up"` only when the
+        // leading token matches an already-discovered host (not direct-address fallback).
+        if (!machineQuery && promptParts.length >= 2) {
+            const hit = findDiscoveredHost(targets, promptParts[0]);
+            if (hit) {
+                machineQuery = promptParts[0];
+                promptParts = promptParts.slice(1);
+            }
+        }
     }
-    const stats = [
-        chunk.eval_count != null ? `${chunk.eval_count} tokens` : "",
-        chunk.eval_duration
-            ? `${((chunk.eval_count ?? 0) / (chunk.eval_duration / 1e9)).toFixed(1)} tok/s`
-            : "",
-        chunk.total_duration ? formatDuration(chunk.total_duration) : "",
-    ].filter(Boolean);
-    if (stats.length > 0) {
-        console.error(`(${stats.join(" · ")})`);
+    let peeledModel;
+    if (!parsed.chatId && !parsed.model) {
+        if (!machineQuery) {
+            console.error("Machine is required for a new chat (or use --chat <hash>).");
+            usage();
+        }
+        const host = resolveHost(targets, machineQuery);
+        const peeled = await maybePeelModel(host, promptParts, fromStdin);
+        peeledModel = peeled.model;
+        promptParts = peeled.promptParts;
+    }
+    const promptText = [promptParts.join(" ").trim(), fromStdin].filter(Boolean).join("\n\n").trim();
+    if (!promptText) {
+        console.error("No prompt provided (pass args and/or pipe stdin).");
+        usage();
+    }
+    try {
+        const result = await runPrompt({
+            machine: machineQuery,
+            model: parsed.model ?? peeledModel,
+            prompt: promptText,
+            chatId: parsed.chatId,
+            save,
+            settings: parsed.settings,
+            writeStdout: !json,
+            stream: json ? false : stream,
+            quiet: json,
+        });
+        if (json) {
+            console.log(JSON.stringify({
+                chat_id: result.chat_id,
+                topic: result.topic,
+                content: result.content,
+                thinking: result.thinking,
+                ollama: result.ollama,
+            }, null, 2));
+            return;
+        }
+        const chunk = result.ollama;
+        const stats = [
+            chunk.eval_count != null ? `${chunk.eval_count} tokens` : "",
+            chunk.eval_duration
+                ? `${((Number(chunk.eval_count) || 0) / (Number(chunk.eval_duration) / 1e9)).toFixed(1)} tok/s`
+                : "",
+            chunk.total_duration ? formatDuration(Number(chunk.total_duration)) : "",
+        ].filter(Boolean);
+        if (stats.length > 0) {
+            console.error(`(${stats.join(" · ")})`);
+        }
+    }
+    catch (err) {
+        const message = err instanceof Error ? err.message : String(err);
+        if (message.startsWith("Machine is required") || message.startsWith("No prompt")) {
+            console.error(message);
+            usage();
+        }
+        throw err;
     }
 }

package/dist/scan.d.ts

@@ -0,0 +1,44 @@
+/**
+ * Scan reachable networks for Ollama servers and list available models.
+ *
+ * Usage: ollanet scan [--lan] [--json] [--all]
+ */
+import { type AppConfig } from "./config.js";
+export interface ScanOptions {
+    includeOffline?: boolean;
+    /** TCP-scan local /24s. Opt-in; never the default. */
+    lanScan?: boolean;
+    /**
+     * In-memory config. When set, the config file (`~/.ollanet` / `OLLANET_CONFIG`)
+     * is not read. Omit to keep CLI/MCP file behavior.
+     */
+    config?: Partial<AppConfig>;
+}
+export interface ScannedServer {
+    hostname: string;
+    dnsName: string;
+    ip: string;
+    port: number;
+    os: string;
+    source: string;
+    self: boolean;
+    endpoint: string;
+    models: Array<{
+        name: string;
+        size?: number;
+        modified_at?: string;
+        parameter_size?: string;
+        quantization_level?: string;
+        family?: string;
+    }>;
+}
+export interface ScanPayload {
+    network: string;
+    sources: string[];
+    port: number;
+    scanned: number;
+    servers: ScannedServer[];
+}
+/** Programmatic scan used by CLI `--json`, MCP, and `import { scanNetwork } from "ollanet"`. */
+export declare function scanNetwork(options?: ScanOptions): Promise<ScanPayload>;
+export declare function main(): Promise<void>;

package/dist/scan.js

@@ -1,13 +1,16 @@
-#!/usr/bin/env node
 /**
  * Scan reachable networks for Ollama servers and list available models.
  *
  * Usage: ollanet scan [--lan] [--json] [--all]
  */
-import { loadConfig } from "./config.js";
-import { OLLAMA_PORT, discoverHosts, envInt, shortName, } from "./hosts.js";
-const TIMEOUT_MS = envInt("OLLAMA_TIMEOUT_MS", 2500);
-const CONCURRENCY = Math.max(1, envInt("OLLAMA_CONCURRENCY", 16));
+import { configFromPartial, loadConfig } from "./config.js";
+import { discoverHosts, envInt, ollamaPort, shortName, } from "./hosts.js";
+function scanTimeoutMs() {
+    return envInt("OLLAMA_TIMEOUT_MS", 2500);
+}
+function scanConcurrency() {
+    return Math.max(1, envInt("OLLAMA_CONCURRENCY", 16));
+}
 function formatBytes(bytes) {
     if (bytes == null || !Number.isFinite(bytes))
         return "";
@@ -22,8 +25,9 @@ function formatBytes(bytes) {
 }
 async function fetchModels(host) {
     const url = `http://${host.ip.includes(":") ? `[${host.ip}]` : host.ip}:${host.port}/api/tags`;
+    const timeoutMs = scanTimeoutMs();
     const controller = new AbortController();
-    const timer = setTimeout(() => controller.abort(), TIMEOUT_MS);
+    const timer = setTimeout(() => controller.abort(), timeoutMs);
     try {
         const res = await fetch(url, {
             signal: controller.signal,
@@ -66,7 +70,7 @@ async function scanHost(host) {
         const name = err instanceof Error ? err.name : "";
         const message = err instanceof Error ? err.message : String(err);
         const error = name === "AbortError" || message.toLowerCase().includes("abort")
-            ? `timeout after ${TIMEOUT_MS}ms`
+            ? `timeout after ${scanTimeoutMs()}ms`
             : message;
         return { host, ok: false, models: [], error, url };
     }
@@ -113,6 +117,49 @@ function printResults(results, networkLabel, sources) {
     }
     console.log(`Found ${found.length} Ollama server(s) with ${found.reduce((n, r) => n + r.models.length, 0)} model entrie(s).`);
 }
+function toPayload(results, networkLabel, sources) {
+    return {
+        network: networkLabel,
+        sources,
+        port: ollamaPort(),
+        scanned: results.length,
+        servers: results
+            .filter((r) => r.ok)
+            .map((r) => ({
+            hostname: r.host.hostname,
+            dnsName: r.host.dnsName,
+            ip: r.host.ip,
+            port: r.host.port,
+            os: r.host.os,
+            source: r.host.source,
+            self: r.host.isSelf,
+            endpoint: `http://${r.host.ip}:${r.host.port}`,
+            models: r.models.map((m) => ({
+                name: m.name,
+                size: m.size,
+                modified_at: m.modified_at,
+                parameter_size: m.details?.parameter_size,
+                quantization_level: m.details?.quantization_level,
+                family: m.details?.family,
+            })),
+        })),
+    };
+}
+/** Programmatic scan used by CLI `--json`, MCP, and `import { scanNetwork } from "ollanet"`. */
+export async function scanNetwork(options = {}) {
+    const config = options.config ? configFromPartial(options.config) : await loadConfig();
+    const { hosts, sources, networkLabel } = await discoverHosts({
+        hosts: config.hosts,
+        discovery: config.discovery,
+        includeOffline: options.includeOffline ?? false,
+        lanScan: options.lanScan ?? false,
+    });
+    if (hosts.length === 0) {
+        throw new Error("No hosts to scan. Add config.hosts, set OLLANET_HOSTS, or enable Tailscale/LAN discovery.");
+    }
+    const results = await mapPool(hosts, scanConcurrency(), scanHost);
+    return toPayload(results, networkLabel, sources);
+}
 export async function main() {
     const includeOffline = process.argv.includes("--all");
     const jsonOut = process.argv.includes("--json");
@@ -129,34 +176,9 @@ export async function main() {
         process.exitCode = 1;
         return;
     }
-    const results = await mapPool(hosts, CONCURRENCY, scanHost);
+    const results = await mapPool(hosts, scanConcurrency(), scanHost);
     if (jsonOut) {
-        console.log(JSON.stringify({
-            network: networkLabel,
-            sources,
-            port: OLLAMA_PORT,
-            scanned: results.length,
-            servers: results
-                .filter((r) => r.ok)
-                .map((r) => ({
-                hostname: r.host.hostname,
-                dnsName: r.host.dnsName,
-                ip: r.host.ip,
-                port: r.host.port,
-                os: r.host.os,
-                source: r.host.source,
-                self: r.host.isSelf,
-                endpoint: `http://${r.host.ip}:${r.host.port}`,
-                models: r.models.map((m) => ({
-                    name: m.name,
-                    size: m.size,
-                    modified_at: m.modified_at,
-                    parameter_size: m.details?.parameter_size,
-                    quantization_level: m.details?.quantization_level,
-                    family: m.details?.family,
-                })),
-            })),
-        }, null, 2));
+        console.log(JSON.stringify(toPayload(results, networkLabel, sources), null, 2));
         return;
     }
     printResults(results, networkLabel, sources);

package/package.json

@@ -1,28 +1,44 @@
 {
   "name": "ollanet",
-  "version": "0.2.2",
-  "description": "Chat with Ollama servers on any reachable network — scan hosts, prompt models, continue chats by hash",
+  "version": "0.4.0",
+  "description": "Discover and talk to Ollama on any reachable network — CLI, MCP, and a Node library",
   "type": "module",
   "bin": {
     "ollanet": "./dist/cli.js"
   },
+  "exports": {
+    ".": {
+      "types": "./dist/index.d.ts",
+      "import": "./dist/index.js"
+    },
+    "./scan": {
+      "types": "./dist/scan.d.ts",
+      "import": "./dist/scan.js"
+    },
+    "./package.json": "./package.json"
+  },
+  "types": "./dist/index.d.ts",
   "files": [
     "dist",
     "README.md",
     "LICENSE"
   ],
   "scripts": {
-    "build": "tsc -p tsconfig.build.json",
-    "prepare": "tsc -p tsconfig.build.json",
+    "build": "tsc -p tsconfig.build.json && node scripts/fix-dts-extensions.mjs",
+    "prepare": "tsc -p tsconfig.build.json && node scripts/fix-dts-extensions.mjs",
     "ollanet": "tsx src/cli.ts",
     "scan": "tsx src/cli.ts scan",
     "prompt": "tsx src/cli.ts prompt",
     "chats": "tsx src/cli.ts chats",
     "bench": "tsx src/cli.ts bench",
+    "mcp": "tsx src/cli.ts mcp",
     "start": "tsx src/cli.ts scan",
     "typecheck": "tsc --noEmit",
-    "test": "tsc -p tsconfig.build.json && node --test test/*.test.mjs",
-    "test:only": "node --test test/*.test.mjs"
+    "test": "tsc -p tsconfig.build.json && node scripts/fix-dts-extensions.mjs && node --test test/*.test.mjs",
+    "test:only": "node --test test/*.test.mjs",
+    "site:dev": "pnpm --dir site dev",
+    "site:build": "pnpm --dir site build",
+    "site:deploy": "pnpm --dir site deploy"
   },
   "keywords": [
     "ollama",
@@ -31,7 +47,10 @@
     "chat",
     "lan",
     "tailscale",
-    "network"
+    "network",
+    "mcp",
+    "model-context-protocol",
+    "library"
   ],
   "author": "Catalyst Forge LLC",
   "license": "MIT",
@@ -39,7 +58,7 @@
     "type": "git",
     "url": "git+https://github.com/Catalyst-Forge-LLC/ollanet.git"
   },
-  "homepage": "https://github.com/Catalyst-Forge-LLC/ollanet#readme",
+  "homepage": "https://ollanet.dev",
   "bugs": {
     "url": "https://github.com/Catalyst-Forge-LLC/ollanet/issues"
   },