Agent! 1.0.41 (Build 126)

Agent! 1.0.41

🛠 Tool System

• Consolidated tool naming — all tools renamed with _tool suffix, auto-stripped after first turn
• mkdir and cd actions added to file_manager
• Condensed tools — strip _tool suffix after first turn, auto-revert on failure
• AgentTools 2.31.0 — synced all tool action lists with new naming
• Run agent — support both run agent X and agent run X for direct execution
• Fix run_agent — compile then dlopen/run dylib instead of just compiling

📺 LLM Output Overhaul

• NSTextTable inline rendering — tables render inline with proper padding and sizing
• AgentTerminalNeo integration — native auto-scroll, smooth streaming, cursor blink
• Auto-grow output — LLM Output grows with content, capped at 50% window height
• Draggable resize handle — resize LLM Output panel with drag, respects max height
• Live token counts — estimate input/output tokens during streaming
• Always-blinking cursor — seamless streaming to idle, AGENT! prompt blinks too
• Line-count-based height — eliminates NSTextTable overestimation and jitter
• Fix streaming jitter — height only grows, never shrinks

🧠 Fallback Chain

• Fallback Chain UI — configure backup models in toolbar, auto-switch on failure
• Model picker dropdowns — shows fetched models from all providers
• Eye icon for vision models in pickers and fallback entries
• Wire fallback chain into error handler — auto-switch on provider failure

🎨 UI Improvements

• Status icons and colors — 🧠/blue Thinking, ▶/green Running, 🖥/orange Executing, 🛡/red Root
• Coding Preferences icon turns green when any feature is on
• Agents menu retry — longer initial delay, 10 insertion attempts
• Window frame persistence — retains size after tiling
• Fix double overlay — tab selected shows only its own indicator
• Cmd+B toggles overlay on all tabs including running ones

🔧 Fixes

• batch_commands — run all in single shell session so variables persist
• Fix token accuracy — live output estimate, no double-counting
• Fix timer — 0.25s refresh for live tokens, freeze on cancel
• Fix elapsed time — freeze at actual value when done
• Fix duplicate recordFailure — was double-counting failures
• Fix drag jitter — global coordinate space for handle gesture
• Fix window resizing on drag — prevent window resize from LLM Output handle

🤖 Z.ai / Model Providers

• Dynamic model fetching — Z.ai models 100% from OpenAPI spec, zero hardcoding
• Two endpoints — coding (no vision) and general (vision), URL routing with :v tag
• Fetch models for ALL providers — Z.ai, Gemini, Grok, Mistral, etc.
• Coding endpoint models tagged with -Code suffix

🏗 Architecture

• Xcode-only gating — block xc tools when no .xcodeproj detected
• Verify gate — build must pass before task_complete allowed
• Remove Claude Code references from source comments
• AgentTools pinned to 2.31.0, prompt revision 62

Agent! for macOS26 1.0.33

Agent! Agentic AI for your  Apple Mac Desktop

⏱️ Timer Improvements

• Background timers — elapsed computed from taskStartDate, ticks even when tab is not visible
• Per-tab timers — elapsed stored on ScriptTab/ViewModel, no shared @State bleeding
• Fix timer for direct script runs — set taskStartDate on start, freeze on stop
• Always show elapsed time — remembers where task stopped
• Reset timer when new task starts — no stale elapsed time from previous run
• Fix timer reset on tab switch — persist taskElapsed on ScriptTab, restore on appear

🖥️ UI / Overlay

• LLM Output overlay — overlaid on activity log instead of pushing it down
• Overlay background refinements: dark mode blur material, light mode white background
• Cmd+Shift+D toggles LLM overlay on/off
• Auto-scroll activity log to bottom when new task starts

🧠 LLM Behavior

• Prefix every new task with NEW TASK instruction — overrides previous context
• Extract shared newTaskPrefix — single source of truth for task prompt prefix
• Loop detection + no-reread rule — prevents LLMs from reading the same file in loops
• Smarter loop detection — only break on consecutive identical reads with no write between
• Allow 2 reads of same file, then return error telling LLM to use cached content
• Remove unused recentToolCalls from main task path

🏗️ Architecture

• Extract shared DaemonCore.swift — common command execution for Helper and User daemons
• Wire DaemonCore.swift into both AgentHelper and AgentUser targets
• Main tab doesn't wait for agent scripts — fire and forget into script tab

📦 Version Bumps

• Bumped build number to 117, then 118, then 119
• Version bump to 1.0.33

Full Changelog: 1.0.32.118...1.0.33

Agent! for macOS26 1.0.32

Agent! for macOS 26

🚀 New Features & Improvements

Version Bump: Updated to 1.0.31 with build number 115
Improved UI Responsiveness: Fixed menu spinner by deferring agent runs to next run loop
Enhanced Audit Logging: Added audit log entry for direct agent execution
Better File Management: Updated .gitignore to ignore temporary files and logs
Documentation Update: Clarified Claude reference in README to avoid confusion
🐞 Bug Fixes

Script Tab Management: Always close old script tab before re-running to prevent spinner block
Xcode Project Configuration: Fixed project versioning and deployment target settings
📦 Infrastructure

Added .mailmap: Standardized author names across commits
Created Applications Symlink: Added symlink for dmg packaging
🛠️ Development Enhancements

Code Organization: Added missing import for AgentAudit in TaskUtilities
Build System: Ensured untracked files are added before push
This release focuses on stability, performance, and documentation clarity. The agent is now more responsive and better documented for users and contributors alike.

Agent 1.0.21

Agent 1.0.21 Release

What's Changed

• AgentAccess 2.3.1: unminimize docked windows before activating
• AgentAccess 2.3.0: always activate app, handles docked/minimized
• Graph improvements

- Token badge: always show, today's total, blue+green lines only - Token chart: add AreaMark fills so green received line is visible

Installation

Download the DMG below, open it, and drag Agent! to your Applications folder.