aether-code 0.32.2 → 0.33.0

package/bin/aether-code.js

@@ -28,7 +28,7 @@ import {
 import readline from "node:readline";
 import { c, errorLine, divider, setTerminalTitle } from "../src/render.js";
 
-const VERSION = "0.32.0";
+const VERSION = "0.33.0";
 
 /**
  * Try to start MCP servers from ~/.aether/mcp.json. Returns a started

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "aether-code",
-  "version": "0.32.2",
+  "version": "0.33.0",
   "description": "Uncensored AI coding agent for your terminal — Claude Code alternative with MCP support. Reads code, writes files, runs commands. Drives IDA Pro, Roblox Studio, Wireshark, Blender, and any MCP server. No refusal layer.",
   "homepage": "https://trynoguard.com",
   "repository": {

package/src/agent.js

@@ -3,12 +3,78 @@
 // tool calls (task done) or max-turns is reached.
 
 import os from "node:os";
+import fs from "node:fs";
 import path from "node:path";
 import { agentTurnStream, AetherError } from "./api.js";
 import { TOOL_DEFINITIONS, executeTool } from "./tools.js";
 import { unnamespaceToolName } from "./mcp.js";
 import { loadAllSkills, selectSkills, renderSkillsBlock } from "./skills.js";
-import { c, divider, turn, toolLabel, toolSummary, makeTokenStripper, errorLine, startSpinner } from "./render.js";
+import { c, divider, turn, toolLabel, toolSummary, makeTokenStripper, errorLine, startSpinner, turnStats, fmtTokens } from "./render.js";
+
+/* ─────────────────────── Image attachment parsing ─────────────────────── */
+
+const IMAGE_EXTS = new Set([".png", ".jpg", ".jpeg", ".gif", ".webp", ".bmp"]);
+const MIME_MAP = {
+  ".png": "image/png",
+  ".jpg": "image/jpeg",
+  ".jpeg": "image/jpeg",
+  ".gif": "image/gif",
+  ".webp": "image/webp",
+  ".bmp": "image/bmp",
+};
+
+// Parse @path/to/image references from user input. Supports quoted paths for
+// spaces: @"C:\Users\me\my screenshot.png". Returns { text, images }.
+function parseImages(prompt, cwd) {
+  const re = /@("(?:[^"\\]|\\.)*"|[^\s]+)/g;
+  const images = [];
+  let cleaned = prompt;
+
+  for (const m of [...prompt.matchAll(re)]) {
+    const raw = m[1].replace(/^"|"$/g, "");
+    const ext = path.extname(raw).toLowerCase();
+    if (!IMAGE_EXTS.has(ext)) continue;
+
+    const abs = path.isAbsolute(raw) ? raw : path.resolve(cwd, raw);
+    try {
+      const buf = fs.readFileSync(abs);
+      if (buf.length > 20 * 1024 * 1024) {
+        console.log(c.yellow(`  ⚠ Image too large (>20MB), skipping: ${raw}`));
+        continue;
+      }
+      const mime = MIME_MAP[ext] || "image/png";
+      images.push({
+        url: `data:${mime};base64,${buf.toString("base64")}`,
+        name: path.basename(raw),
+        size: buf.length,
+      });
+      cleaned = cleaned.replace(m[0], "");
+    } catch (e) {
+      console.log(c.yellow(`  ⚠ Could not read image: ${raw} — ${e.code === "ENOENT" ? "file not found" : e.message}`));
+    }
+  }
+
+  return { text: cleaned.replace(/\s{2,}/g, " ").trim() || prompt.trim(), images };
+}
+
+// Build OpenAI-compatible content array with text + images, or plain string
+// when no images are attached.
+function buildContent(text, images) {
+  if (images.length === 0) return text;
+  const parts = [];
+  for (const img of images) {
+    parts.push({ type: "image_url", image_url: { url: img.url } });
+  }
+  parts.push({ type: "text", text });
+  return parts;
+}
+
+// Friendly file size: 1.2MB, 450KB, 128B
+function fmtSize(bytes) {
+  if (bytes >= 1_048_576) return (bytes / 1_048_576).toFixed(1) + "MB";
+  if (bytes >= 1024) return (bytes / 1024).toFixed(0) + "KB";
+  return bytes + "B";
+}
 
 const DEFAULT_MAX_TURNS = 25;
 
@@ -76,6 +142,15 @@ export async function runAgent({
     process.stderr.write(c.yellow(`(skill load failed: ${e.message})\n`));
   }
   const referencedPaths = [];
+
+  // Parse image attachments (@path/to/image.png) from the user's prompt.
+  const { text: cleanPrompt, images: attachedImages } = parseImages(initialPrompt, cwd);
+  if (attachedImages.length > 0) {
+    for (const img of attachedImages) {
+      console.log(`\n${c.cyan("●")} ${c.cyan(c.bold("image"))} ${c.gray(img.name)} ${c.gray(`(${fmtSize(img.size)})`)}`);
+    }
+  }
+
   // Two callers: one-shot (initialPrompt only, fresh conversation) and REPL
   // (priorMessages + initialPrompt to continue an ongoing chat).
   // On the FIRST message of a session, prepend an environment block so the
@@ -83,9 +158,11 @@ export async function runAgent({
   // X on my desktop" became `mkdir X` in whatever dir aether was launched from
   // (e.g. C:\WINDOWS\system32). Only prepended once — later turns carry it in
   // history.
+  const firstText = priorMessages ? cleanPrompt : envContext(cwd) + cleanPrompt;
+  const firstContent = buildContent(firstText, attachedImages);
   const messages = priorMessages
-    ? [...priorMessages, { role: "user", content: initialPrompt }]
-    : [{ role: "user", content: envContext(cwd) + initialPrompt }];
+    ? [...priorMessages, { role: "user", content: firstContent }]
+    : [{ role: "user", content: firstContent }];
   let totalCredits = 0;
   let totalIn = 0;
   let totalOut = 0;
@@ -108,15 +185,14 @@ export async function runAgent({
   let appliedNothingNudges = 0;
 
   for (let i = 0; i < maxTurns; i++) {
-    // No turn header and no leading blank here — each step (assistant text and
-    // each tool label) begins with its own "\n● ", so spacing stays exactly one
-    // blank line per step instead of stacking up.
+    const turnStart = Date.now();
 
     // Stream the assistant's response. Print text deltas as they arrive,
     // along with tool-call announcements as soon as the model commits to
     // calling a particular tool (i.e. the `name` arrives in the stream).
     const announced = new Set();
     let lastWasText = false;
+    let streamedChars = 0;
     const stripper = makeTokenStripper();
 
     // Select skills for this turn against the current user prompt + any
@@ -138,6 +214,8 @@ export async function runAgent({
         tools,
         model,
         onDelta: (text) => {
+          streamedChars += text.length;
+          spinner.update({ tokens: Math.ceil(streamedChars / 3.5) });
           // Buffered strip of leaked model channel/control tokens (which can
           // be split across stream chunks) before display.
           const clean = stripper.push(text);
@@ -180,13 +258,13 @@ export async function runAgent({
       process.stdout.write(tail);
     }
     if (lastWasText) process.stdout.write("\n");
+    const turnIn = res.usage?.prompt_tokens ?? 0;
+    const turnOut = res.usage?.completion_tokens ?? 0;
     totalCredits += res.creditsCharged ?? 0;
-    totalIn += res.usage?.prompt_tokens ?? 0;
-    totalOut += res.usage?.completion_tokens ?? 0;
+    totalIn += turnIn;
+    totalOut += turnOut;
     if (typeof res.balanceAfter === "number") lastBalance = res.balanceAfter;
     onTokens({ totalCredits, totalIn, totalOut, balance: lastBalance });
-    // Per-turn cost line removed for a cleaner look — the session summary at the
-    // end carries the totals.
 
     // Push assistant message into history
     messages.push({
@@ -289,6 +367,16 @@ export async function runAgent({
         content: result.output ?? (result.ok ? "(no output)" : "Failed."),
       });
     }
+
+    // Per-turn stats line — shows elapsed time, token flow, and tool count.
+    const stats = turnStats({
+      elapsed: Date.now() - turnStart,
+      tokensIn: turnIn,
+      tokensOut: turnOut,
+      tools: toolCalls.length,
+      credits: res.creditsCharged ?? 0,
+    });
+    if (stats) console.log(stats);
   }
 
   console.log(c.yellow(`\nReached max turns (${maxTurns}). Stopping.`));
@@ -317,16 +405,30 @@ function buildTurnMessages(messages, allSkills, referencedPaths) {
     if (messages[i].role === "user") { lastUserIdx = i; break; }
   }
   if (lastUserIdx === -1) return messages;
-  const prompt = typeof messages[lastUserIdx].content === "string"
-    ? messages[lastUserIdx].content
-    : "";
+  // Content can be a string or a multimodal array (when images are attached).
+  // Extract the text portion for skill selection; prepend skills to text only.
+  const rawContent = messages[lastUserIdx].content;
+  let prompt;
+  if (typeof rawContent === "string") {
+    prompt = rawContent;
+  } else if (Array.isArray(rawContent)) {
+    const textPart = rawContent.find((p) => p.type === "text");
+    prompt = textPart?.text ?? "";
+  } else {
+    prompt = "";
+  }
   const active = selectSkills({ skills: allSkills, prompt, referencedPaths });
   if (active.length === 0) return messages;
   const block = renderSkillsBlock(active);
   const cloned = [...messages];
-  cloned[lastUserIdx] = {
-    ...cloned[lastUserIdx],
-    content: `${block}\n\n---\n\n${prompt}`,
-  };
+  // Inject skill block into the text portion of the content.
+  if (typeof rawContent === "string") {
+    cloned[lastUserIdx] = { ...cloned[lastUserIdx], content: `${block}\n\n---\n\n${prompt}` };
+  } else if (Array.isArray(rawContent)) {
+    const newParts = rawContent.map((p) =>
+      p.type === "text" ? { ...p, text: `${block}\n\n---\n\n${p.text}` } : p,
+    );
+    cloned[lastUserIdx] = { ...cloned[lastUserIdx], content: newParts };
+  }
   return cloned;
 }

package/src/box-input.js

@@ -64,7 +64,7 @@ export function promptBox({ history = [], placeholder = "type a message…  /hel
       const top = c.magenta("╭" + "─".repeat(W + 4) + "╮");
       const mid = c.magenta("│") + " " + c.magenta("›") + " " + content + " " + c.magenta("│");
       const bot = c.magenta("╰" + "─".repeat(W + 4) + "╯");
-      const hint = c.dim("  Enter send · ↑↓ history · /help · /exit");
+      const hint = c.dim("  Enter send · ↑↓ history · @file for images · /help · /exit");
 
       process.stdout.write(top + "\n" + mid + "\n" + bot + "\n" + hint + "\n");
       drawn = 4;

package/src/render.js

@@ -98,33 +98,69 @@ export function setTerminalTitle(title) {
   if (process.stdout.isTTY) process.stdout.write(`\x1b]0;${title}\x07`);
 }
 
-// Live "working…" spinner. Rewrites a single line in place (\r) with a rotating
-// half-circle (Geometric Shapes — same block as ●, so cmd.exe-safe) + elapsed
-// seconds, so the user sees the agent is alive while the model thinks or a slow
-// tool runs. stop() clears the line and restores the cursor. No-op in non-TTY.
+// Live "working…" spinner with optional live metrics (token count, status).
+// Rewrites a single line in place (\r) with a rotating half-circle + elapsed
+// time (mm:ss when > 60s) + any metrics fed via update(). stop() clears the
+// line and restores the cursor. No-op in non-TTY.
 export function startSpinner(label) {
-  if (!process.stdout.isTTY) return { stop: () => {} };
+  if (!process.stdout.isTTY) return { stop: () => {}, update: () => {} };
   const frames = ["◐", "◓", "◑", "◒"];
   const t0 = Date.now();
   let i = 0;
+  let tokenCount = 0;
+  let statusText = "";
   process.stdout.write("\x1b[?25l"); // hide cursor
   const render = () => {
-    const s = Math.floor((Date.now() - t0) / 1000);
-    const tail = s > 0 ? c.gray(`  ${s}s`) : "";
-    process.stdout.write(`\r\x1b[K${c.cyan(frames[i % frames.length])} ${c.gray(label + "…")}${tail}`);
+    const ms = Date.now() - t0;
+    const secs = Math.floor(ms / 1000);
+    const timeFmt = secs >= 60
+      ? `${Math.floor(secs / 60)}m ${String(secs % 60).padStart(2, "0")}s`
+      : `${secs}s`;
+    const parts = [];
+    if (secs > 0) parts.push(timeFmt);
+    if (tokenCount > 0) parts.push(`↓ ${fmtTokens(tokenCount)} tokens`);
+    if (statusText) parts.push(statusText);
+    const metrics = parts.length > 0 ? c.gray(` (${parts.join(" · ")})`) : "";
+    process.stdout.write(`\r\x1b[K${c.cyan(frames[i % frames.length])} ${c.gray(label + "…")}${metrics}`);
     i++;
   };
   render();
   const timer = setInterval(render, 120);
   if (typeof timer.unref === "function") timer.unref(); // don't keep the process alive
   return {
-    stop: () => {
+    update(data) {
+      if (data.tokens != null) tokenCount = data.tokens;
+      if (data.status != null) statusText = data.status;
+    },
+    stop() {
       clearInterval(timer);
       process.stdout.write("\r\x1b[K\x1b[?25h"); // clear line + show cursor
     },
   };
 }
 
+// Human-friendly token count (14.2k, 1.3M, etc.)
+export function fmtTokens(n) {
+  if (n >= 1_000_000) return (n / 1_000_000).toFixed(1) + "M";
+  if (n >= 1_000) return (n / 1_000).toFixed(1) + "k";
+  return String(n);
+}
+
+// Compact one-line turn summary printed after each agent turn completes.
+export function turnStats({ elapsed, tokensIn, tokensOut, tools, credits }) {
+  const parts = [];
+  if (elapsed > 0) {
+    const s = Math.floor(elapsed / 1000);
+    parts.push(s >= 60 ? `${Math.floor(s / 60)}m ${String(s % 60).padStart(2, "0")}s` : `${s}s`);
+  }
+  if (tokensIn > 0 || tokensOut > 0) {
+    parts.push(`${fmtTokens(tokensIn)}→${fmtTokens(tokensOut)} tokens`);
+  }
+  if (tools > 0) parts.push(`${tools} tool call${tools === 1 ? "" : "s"}`);
+  if (credits > 0) parts.push(`${credits} cr`);
+  return parts.length > 0 ? c.dim(`  ── ${parts.join(" · ")}`) : "";
+}
+
 // Terse one-line result summary instead of dumping raw JSON / file contents.
 // Tools whose handlers already render rich output (diffs, the shell stream, the
 // plan) just get a check — the detail was already printed.

package/src/repl.js

@@ -16,7 +16,7 @@ import { c, errorLine, boxLines, sideBySide } from "./render.js";
 import { checkForUpdate } from "./update-check.js";
 import { promptBox, EXIT_SIGNAL } from "./box-input.js";
 
-const VERSION = "0.32.0";
+const VERSION = "0.33.0";
 const MODEL_NAME = "Aether Core";
 
 // /model aliases → { id, name }. id=null = server default (gemma / Aether Core).
@@ -245,9 +245,9 @@ const shortenPath = (p, max) => (p.length <= max ? p : "..." + p.slice(p.length
 // Short, hand-curated highlights shown in the "What's new" box. Update with
 // notable releases — keep it to ~3 lines so it balances the banner height.
 const WHATS_NEW = [
-  "Files now save to your Desktop",
-  "Live thinking spinner + loop guard",
-  "Asks you when a task is unclear",
+  "Image support — @file.png in your prompt",
+  "Live token counter + turn stats",
+  "Enhanced spinner with mm:ss timing",
 ];
 
 function printBanner(state) {