🦾 Agent! 1.0.68 (Build 156)

✨ 🦾 Agent! What's New in 1.0.68?

🔧 diff_apply Reliability

• Fixed truncation bug: source is now spliced into the file instead of replacing entire content
• Fixed LLMs sending diff-formatted input to diff_apply
• Replaced force-unwrap with safe if-let in range note parsing
• Updated AgentTools to 2.50.7 with truncation fix
• Bumped prompt revision to 86 for improved diff_apply prompting

🧠 Apple Intelligence Fixes

• Fixed non-agent tool names being misrouted to run_agent
• Tightened run_agent trigger to exact phrase match only
• Fixed duplicate log entries for accessibility tasks

🖥️ UI Improvements

• Paste chips: Long Cmd+V pastes now appear as removable preview chips instead of flooding the text field
• Tab labels: Main tab shows current model name; LLM tabs preserve raw model casing
• Per-tab usage: Added individual usage breakdown to each LLM tab
• Log formatting: Multi-line messages now drop below the timestamp on their own line

🧹 Code Quality

• Consolidated vision model detection into shared isVisionModel() (removed two duplicate private methods)
• Summarized verbose comments across 10 source files
• Skipped suggestion matching for long inputs to prevent main-thread stalls
• Fixed tool output formatting (newline prefix and :0:0 warning cleanup)
• Added iteration cap enforcement

🚀 Agent! v1.0.67 (Build 155)

What's Changed

🤖 Apple Intelligence

• Use Apple AI itself to classify follow-up prompts
• Persist accessibility agent session across turns
• Disable shell and applescript tools for Apple AI — accessibility only
• Better app name recognition — fixes Photo Booth confusion
• Teach Apple AI accessibility agent to discover button labels before clicking
• Verify Apple AI tool outputs before claiming success — forward to LLM on failure
• Log Apple AI tool actions to activity log — expose what Apple AI does
• Harden Apple AI triage — never claim completion on failure or uncertainty
• Fix Apple Intelligence isEnabled defaulting to false
• Fix: inject previous conversation turn into Apple Intelligence rephrase prompt

🛠️ Agent Scripts

• Fix agent script run routing: script tabs run on same tab, main tab spawns separate tab
• Fix AgentScript.swift: restore missing function declaration, compileCmd guards, and closing braces
• Route Apple Intelligence tool logs to correct script tab
• Pass project folder to Apple AI shell tool — fixes "not a git repository"

🔒 Security & Guardrails

• Add action_not_performed guardrail at app and prompt layers
• README + SECURITY.md: document action_not_performed three-layer defense
• README: add Tool Execution Gating to Defense Layers

⚙️ Internal

• Bump version to 1.0.67 (build 155)
• Version bump to 1.0.65 (build 153)
• Version bump to 1.0.64 (build 152)
• Fix bump_version/get_version to use selected project instead of Xcode open documents
• README updates and improvements
  Full Changelog: 1.0.61.149...1.0.67.155

🚀 Agent! v1.0.65 (Build 153)

What's Changed

Version Management

• Bump version fixes — bump_version/get_version now correctly uses the selected project instead of Xcode open documents
• Version bumps: 1.0.64 (152) → 1.0.65 (153)

Security & Safety

• action_not_performed guardrail — three-layer defense against false-action claims (app layer, prompt layer, documentation)
• README + SECURITY.md updated to document the action_not_performed defense layers

Apple Intelligence Hardening

• Verify Apple AI tool outputs before claiming success — forwards to LLM on failure
• Log Apple AI tool actions to activity log for transparency
• Harden Apple AI triage — never claim completion on failure or uncertainty

Documentation

• README: Tool Execution Gating added to Defense Layers section
• README: Tip Jar section added

Full Changelog: https://github.com/toddbruss/Agent/compare/1.0.61.149...1.0.65.153

🚀 Agent! v1.0.61 (Build 149)

🦾 Agent! Agentic AI for your  Mac Desktop (or Laptop)

Agent! Requires macOS 26.4 or later. M series preferred for Apple Intelligence. We don't know if Apple AI works on Intel. Also Apple AI is not supported inside a Mac VM. It's optional, but does help move things along by doing several tasks locally, saving you some tokens.

🔧 Bug Fixes

• Fix double echo — skip appendLog for shell commands that already streamed output
• Remove tool result cache — eliminate read loop blocker that caused stale responses
• Remove file read dedup cache — LLMs work around stub responses anyway; cleaner tool flow

🧠 Apple AI Improvements

• Skip accessibility triage for file-path and coding prompts — faster task routing
• Add ! bypass prefix — force Apple AI to skip triage when you know what you want
• Add AppleScript + shell tools alongside accessibility for Apple AI agent

🖥️ UI & UX

• Propagate parent tab project folder to spawned script tabs — scripts inherit the right working directory
• Add provider tooltip to LLM Usage popup model rows — see which provider serves each model

📖 Documentation

• Add Defense Layers section to README covering security features
• Add build-without-developer-account instructions + build.sh script
• Add emojis to toolbar icon table, remove SF Symbol text names
• Fix GLM model sizes — 744B/754B MoE, not 32B
• Clarify GLM-5/5.1 are cloud-only (may be possible to run FP8 locally); GLM-4.7-Turbo (32B) runs locally

⬆️ Upgrade Notes

• If upgrading from v1.0.60, no migration needed — settings and tabs are preserved.

Agent! v1.0.60

🦾 Agent! Agentic AI for macOS 26.4+  Mac

🖥️ Agentic Ai for your Apple Mac Desktop or Laptop

🍎 Works with macOS 26.4+

⚡ Improvements

🔄 Fallback chain: trigger after 2 failures instead of 3 for faster recovery
🚦 429 handling: record every failure with fallback chain, flat 10s retry (3 attempts × 10s)
📝 429 logging: log actual API response body + add clearRetryAfter helper
🤖 Z.ai: proper dual-API URLs — code and vision endpoints registered separately
🧠 BigModel: same dual-API URLs as Z.ai (code + vision endpoints)
🍎 Apple AI triage: don't intercept shell commands (open, ls, git, etc.)
🖥️ FallbackChainView: show model display name (with -Code suffix for Z.ai)
🔀 Per-tab provider: sync Settings picker to active tab's LLMConfig
🔧 Model refresh: consolidate 3 model-refresh functions into 1 fetchModelsIfNeeded(for:force:)

🐛 Bug Fixes

🍎 Apple AI refusal: fix not falling through to cloud LLM
📦 batch_commands: remove per-step delimiters, run as single script
🔄 batch: fix duplicate output + guard empty git branch name
📱 manage_app: fix action overwrite + read app from input[app] too
✏️ edit_file: show line numbers in activity log status line

🏗️ Refactoring

📂 Organize AgentViewModel + Views into subfolders, strip redundant prefixes
✂️ Shorten multi-line comments across 94 files (-460 lines)
📏 Wrap long lines across project with SwiftFormat
⬆️ Bump to macOS 26.4+ with 5 new Apple FoundationModels features
🔨 Upgrade to Xcode version bump docs

🚀 Agent! 1.0.59 (Build 147)

🚀 Agent! 1.0.59 (Build 147)

LLM / Provider Improvements

• 429 Fallback Chain Overhaul: Fallback now triggers after 2 failures (down from 3) with a flat 10s retry, so the chain fires within ~30s instead of retrying forever
• 429 handling: Every 429 failure is now recorded against the fallback chain, not just after 3 consecutive failures
• 429 debugging: Log the actual API response body on 429 errors and add clearRetryAfter helper
• BigModel: Same dual-API URLs as Z.ai — code and vision endpoints registered separately
• Z.ai: Proper dual-API URLs for code and vision endpoints
• Apple AI triage: Don't intercept shell commands (open ., open /path, ls, git, etc.) — let them pass through to the shell handler
• Per-tab provider: Sync Settings picker to the active tab's LLMConfig so each tab can use a different provider
• Model refresh consolidation: Route all model-refresh calls through a single fetchModelsIfNeeded(for:force:), replacing 3 separate functions
• FallbackChainView: Show model display name (with -Code suffix for Z.ai)

Tool / Infrastructure

• batch: Fix duplicate output and guard empty git branch name
• batch_commands: Remove per-step delimiters, run as a single script for cleaner output
• Remove read guard snap-out: LLMs need unlimited reads for project research

Version

• Version bump to 1.0.59 (Build 147)

🚀 Agent! 1.0.57.145

What's new with Agent!

🧠 Apple Intelligence & Foundation Models

• macOS 26.4+ Upgrade — Deployment target bumped to macOS 26.4 with 5 new Apple FoundationModels features:
  • 🔢 contextSize — Dynamic context window from SystemLanguageModel (replaces hardcoded 4096)
  • 📊 tokenCount(for:) — Precise token counting for tiered compaction (replaces ~4 chars/token estimate)
  • 🔥 prewarm() — Pre-warm on-device model at app launch for instant first response
  • 🎛️ GenerationOptions — Greedy sampling for triage, low temp for annotations
  • 📝 Transcript — Expose session transcript for context inspection
• 🔄 Refusal Fallback — When Apple Intelligence responds with "I'm sorry" or "I'm unable" after calling the accessibility tool, it now falls through to the cloud LLM instead of showing the refusal as a successful result

🏗️ Architecture & Codebase

• 📂 ViewModel Reorganization — AgentViewModel split into 9 subfolders (Core, Helpers, Messages, NativeToolHandlers, TabHandlers, TabTask, TaskExecution, TaskUtilities, Features)
• 🎨 Views Reorganization — Views split into 9 subfolders (ContentView, ActivityLog, Input, Settings, Header, Tabs, Output, Shared, Tools)
• ✂️ Naming Cleanup — Stripped AgentViewModel+ prefix from 57 files, ActivityLogView+ from 8 files
• 🗑️ Removed Duplicates — Deleted 2 duplicate files (ContentView+Popovers, ContentView+Tabs)
• 📜 Script Service — New script service infrastructure

🐛 Bug Fixes

• 🔧 manage_app Fix — Fixed action overwrite bug where the ax_ prefix handler destroyed the list default. Both handlers now read sub_action first, then fall back to action. Also reads app name from both input[app] and input[name] since models pass it either way

📚 Documentation

• 📖 Xcode Version Bump Tools — Added version bump tool documentation to README

---

Full Changelog: v1.0.55-release...1.0.57.145

Agent! 1.0.52.139

🦾 Agent! 1.0.52 Agentic AI for your  Apple Mac Desktop

🛡️ Anti-Confabulation & Reliability

• 🧠 Anti-confabulation: dedup tool names, prune aliases, harden read guard, add prompt rule
• ✏️ Edit reliability: drop truncation guard, add cache invalidate + no-op detect
• ✂️ Diff truncation guard + plan-mode unblock
• 🔧 Stuck-edit nudge: lower threshold to 3, make it actionable, cover tab tasks

✨ Code Quality

• 📏 Break long code lines across ToolsView, ScriptService, Models, OpenAICompatible, Ollama, CodingService, AgentViewModel, FileTools, TabHandlers+Core
• 📏 Break long code lines in AgentViewModel+SubAgent, +TaskExecution, +TabTask
• 📏 Break long Set literal in ToolPreferencesService, paragraph in AboutSelf, signature in ChatModels
• 🧹 Drop dead planActive variable from main + tab task loops
• 🧹 Cleanup: dead mode handlers + drop empty Copy Agent Resources build phase

🖥️ UI Improvements

• 📋 ToolStepsView: persist expanded state across Cmd+B and new steps
• 📜 LLMOutputTextView: don't snap to bottom on mouse-exit when not streaming

♿ Accessibility

• 🎯 AXorcist-only — drop every coordinate-based caller in the Agent app
• 📸 AgentAccess — screenshots no longer block main thread
• 🚀 AgentAccess — openApp now calls forceLaunchAndActivate
• ⏪ AgentAccess — byte-for-byte revert to working 2.6.0 launchIfNeeded
• 🔙 Pin AgentAccess — restore NSRunningApplication.activate for docked apps
• 🔧 Pin AgentAccess — launchIfNeeded uses Element.showWindow()

📜 Agent Scripts

• ⚙️ agent_script compile: route through executeTCC (in-process), never the Launch Agent
• ⚙️ compileCommand: drop 'touch Package.swift' (TCC-blocked, also a no-op)

⚡ System Changes

• 🔨 Rip out mode system entirely — coding/automation/standard modes are gone
• ⏪ Revert: full system prompt + full tool descriptions on every turn
• 📸 Vision auto-screenshot: opt-in via visionAutoScreenshotEnabled (default OFF)
• ✏️ edit_file: route through CodingService.editFile (d1f-powered) + read_file fix
• 🔄 batch_commands: persist env vars / cwd / functions across steps + fix gitignore
• 📝 .gitignore: clean rewrite for current repo layout
• 📂 Restore tracked Agent / Agent.xcodeproj / AgentHelper trees

📚 Docs

• 📖 Document all 15 toolbar features with icons, descriptions, and detailed behavior
• 📝 Update README.md (multiple updates)

---

💾 DMG attached.

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