- Persist Claude session context-usage percentage, surviving resumes and restarts 🧠
- New IPC/API: `claude:updateSessionContextUsage` to store live context stats 🔌
- Fix resumed sessions falsely showing 100% context from lifetime tokens 🧯
- Usage stats now preserve cost only; tokens intentionally zeroed 📉
- Resume now always fetches session origins to restore context usage 🧭
- Reconstruct context percent on resume by synthesizing equivalent input tokens 🧮
- Add `{{AGENT_HISTORY_PATH}}` template variable for prompts and commands 🧾
- System prompt gains Task Recall guidance using the history JSON file 🗂️
- Input processing now resolves history file path during prompt substitution 🧬
- Add Electron DevTools trace-export workarounds in performance docs 🛠️
- Fix PROJECT_NAME to handle both Unix and Windows paths using split(/[/\\]/)
- Fix trailing slash handling with .filter(Boolean)
- Update misleading "deprecated" comment to "aliases" since PROJECT_NAME is actively used in wizard prompts
- Update tests to verify the improved behavior
- Added custom tab name template variable {{TAB_NAME}} support 🏷️
- Enhanced AutoRun expanded modal with integrated controls header 🎛️
- Added template autocomplete to AI Commands panel editor 🤖
- Fixed modal z-index layering for proper isolation 🎨
- Updated achievement card timeline section with new title 🏆
- Added comprehensive test coverage for new autocomplete features ✅
- Improved AutoRun modal with mode toggle in header bar 🔄
- Added image upload button to expanded AutoRun edit mode 🖼️
- Added help button integration in expanded modal header ❓
- Maintained backwards compatibility with SESSION_NAME alias 🔗
