feat: allow multiple in_progress todos for parallel workflows

rust/.claude/sessions/session-1775010333630.json

@@ -0,0 +1 @@
+{"messages":[{"blocks":[{"text":"hello use bash tool for testing","type":"text"}],"role":"user"},{"blocks":[{"text":"\n\nHello! I'm ready to help. Let me run a quick bash command to confirm everything is working:","type":"text"},{"id":"toolu_01EuTzVfUK7iPRBvjZAovzfV","input":"{\"command\": \"echo \\\"Hello! Bash tool is working. 🎉\\\" && date && pwd\"}","name":"bash","type":"tool_use"}],"role":"assistant","usage":{"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"input_tokens":4277,"output_tokens":92}},{"blocks":[{"is_error":false,"output":"{\n  \"stdout\": \"Hello! Bash tool is working. 🎉\\nWed Apr  1 02:25:46 AM UTC 2026\\n/home/bellman/Workspace/clawd-code/rust\\n\",\n  \"stderr\": \"\",\n  \"rawOutputPath\": null,\n  \"interrupted\": false,\n  \"isImage\": null,\n  \"backgroundTaskId\": null,\n  \"backgroundedByUser\": null,\n  \"assistantAutoBackgrounded\": null,\n  \"dangerouslyDisableSandbox\": null,\n  \"returnCodeInterpretation\": null,\n  \"noOutputExpected\": false,\n  \"structuredContent\": null,\n  \"persistedOutputPath\": null,\n  \"persistedOutputSize\": null,\n  \"sandboxStatus\": {\n    \"enabled\": true,\n    \"requested\": {\n      \"enabled\": true,\n      \"namespace_restrictions\": true,\n      \"network_isolation\": false,\n      \"filesystem_mode\": \"workspace-only\",\n      \"allowed_mounts\": []\n    },\n    \"supported\": true,\n    \"active\": true,\n    \"namespace_supported\": true,\n    \"namespace_active\": true,\n    \"network_supported\": true,\n    \"network_active\": false,\n    \"filesystem_mode\": \"workspace-only\",\n    \"filesystem_active\": true,\n    \"allowed_mounts\": [],\n    \"in_container\": false,\n    \"container_markers\": [],\n    \"fallback_reason\": null\n  }\n}","tool_name":"bash","tool_use_id":"toolu_01EuTzVfUK7iPRBvjZAovzfV","type":"tool_result"}],"role":"tool"},{"blocks":[{"text":"Bash tool is working perfectly! ✅\n\nHere's a quick summary:\n- **Status**: Operational 🎉\n- **Date**: Wed Apr 1, 2026\n- **Working directory**: `/home/bellman/Workspace/clawd-code/rust`\n- **Sandbox**: Enabled and active\n\nHow can I help you today?","type":"text"}],"role":"assistant","usage":{"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"input_tokens":4746,"output_tokens":84}}],"version":1}

rust/.claude/sessions/session-1775010384918.json

@@ -0,0 +1 @@
+{"messages":[{"blocks":[{"text":"who are you?","type":"text"}],"role":"user"},{"blocks":[{"text":"I'm **Claude**, an AI assistant built by Anthropic, currently running as a **Claude Code agent** (Claude Opus 4.6). I'm set up in your workspace at `/home/bellman/Workspace/clawd-code/rust` with the **oh-my-claudecode (OMC)** orchestration layer active.\n\nHere's what I can help you with:\n\n- **Software engineering tasks** — reading, writing, and refactoring code\n- **Debugging** — diagnosing issues, running tests, tracing errors\n- **Research & planning** — exploring codebases, understanding architecture, planning changes\n- **Shell commands** — building, testing, running tools in your environment\n- **Multi-agent workflows** — delegating specialized work (reviews, deep analysis, etc.) via OMC\n\nI have access to your local filesystem, can execute shell commands, search the web, and coordinate specialized sub-agents for complex tasks.\n\nWhat can I help you with today?","type":"text"}],"role":"assistant","usage":{"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"input_tokens":4292,"output_tokens":220}}],"version":1}

rust/.claude/sessions/session-1775010909274.json

@@ -0,0 +1 @@
+{"messages":[],"version":1}

rust/.claude/sessions/session-1775011146355.json

@@ -0,0 +1 @@
+{"messages":[],"version":1}

rust/.clawd-todos.json

@@ -0,0 +1,22 @@
+[
+  {
+    "content": "Phase 0: Structural Cleanup — spawn 4 agents for 0.1-0.4",
+    "activeForm": "Executing Phase 0: Structural Cleanup via sub-agents",
+    "status": "in_progress"
+  },
+  {
+    "content": "Phase 1.1-1.2: Status bar with live HUD and token counter",
+    "activeForm": "Awaiting Phase 0",
+    "status": "pending"
+  },
+  {
+    "content": "Phase 2.4: Remove artificial 8ms stream delay",
+    "activeForm": "Awaiting Phase 0",
+    "status": "pending"
+  },
+  {
+    "content": "Phase 3.1: Collapsible tool output",
+    "activeForm": "Awaiting Phase 0",
+    "status": "pending"
+  }
+]

rust/.omc/plans/tui-enhancement-plan.md

@@ -0,0 +1,221 @@
+# TUI Enhancement Plan — Claw Code (`rusty-claude-cli`)
+
+## Executive Summary
+
+This plan covers a comprehensive analysis of the current terminal user interface and proposes phased enhancements that will transform the existing REPL/prompt CLI into a polished, modern TUI experience — while preserving the existing clean architecture and test coverage.
+
+---
+
+## 1. Current Architecture Analysis
+
+### Crate Map
+
+| Crate | Purpose | Lines | TUI Relevance |
+|---|---|---|---|
+| `rusty-claude-cli` | Main binary: REPL loop, arg parsing, rendering, API bridge | ~3,600 | **Primary TUI surface** |
+| `runtime` | Session, conversation loop, config, permissions, compaction | ~5,300 | Provides data/state |
+| `api` | Anthropic HTTP client + SSE streaming | ~1,500 | Provides stream events |
+| `commands` | Slash command metadata/parsing/help | ~470 | Drives command dispatch |
+| `tools` | 18 built-in tool implementations | ~3,500 | Tool execution display |
+
+### Current TUI Components
+
+| Component | File | What It Does Today | Quality |
+|---|---|---|---|
+| **Input** | `input.rs` (269 lines) | `rustyline`-based line editor with slash-command tab completion, Shift+Enter newline, history | ✅ Solid |
+| **Rendering** | `render.rs` (641 lines) | Markdown→terminal rendering (headings, lists, tables, code blocks with syntect highlighting, blockquotes), spinner widget | ✅ Good |
+| **App/REPL loop** | `main.rs` (3,159 lines) | The monolithic `LiveCli` struct: REPL loop, all slash command handlers, streaming output, tool call display, permission prompting, session management | ⚠️ Monolithic |
+| **Alt App** | `app.rs` (398 lines) | An earlier `CliApp` prototype with `ConversationClient`, stream event handling, `TerminalRenderer`, output format support | ⚠️ Appears unused/legacy |
+
+### Key Dependencies
+
+- **crossterm 0.28** — terminal control (cursor, colors, clear)
+- **pulldown-cmark 0.13** — Markdown parsing
+- **syntect 5** — syntax highlighting
+- **rustyline 15** — line editing with completion
+- **serde_json** — tool I/O formatting
+
+### Strengths
+
+1. **Clean rendering pipeline**: Markdown rendering is well-structured with state tracking, table rendering, code highlighting
+2. **Rich tool display**: Tool calls get box-drawing borders (`╭─ name ─╮`), results show ✓/✗ icons
+3. **Comprehensive slash commands**: 15 commands covering model switching, permissions, sessions, config, diff, export
+4. **Session management**: Full persistence, resume, list, switch, compaction
+5. **Permission prompting**: Interactive Y/N approval for restricted tool calls
+6. **Thorough tests**: Every formatting function, every parse path has unit tests
+
+### Weaknesses & Gaps
+
+1. **`main.rs` is a 3,159-line monolith** — all REPL logic, formatting, API bridging, session management, and tests in one file
+2. **No alternate-screen / full-screen layout** — everything is inline scrolling output
+3. **No progress bars** — only a single braille spinner; no indication of streaming progress or token counts during generation
+4. **No visual diff rendering** — `/diff` just dumps raw git diff text
+5. **No syntax highlighting in streamed output** — markdown rendering only applies to tool results, not to the main assistant response stream
+6. **No status bar / HUD** — model, tokens, session info not visible during interaction
+7. **No image/attachment preview** — `SendUserMessage` resolves attachments but never displays them
+8. **Streaming is char-by-char with artificial delay** — `stream_markdown` sleeps 8ms per whitespace-delimited chunk
+9. **No color theme customization** — hardcoded `ColorTheme::default()`
+10. **No resize handling** — no terminal size awareness for wrapping, truncation, or layout
+11. **Dual app structs** — `app.rs` has a separate `CliApp` that duplicates `LiveCli` from `main.rs`
+12. **No pager for long outputs** — `/status`, `/config`, `/memory` can overflow the viewport
+13. **Tool results not collapsible** — large bash outputs flood the screen
+14. **No thinking/reasoning indicator** — when the model is in "thinking" mode, no visual distinction
+15. **No auto-complete for tool arguments** — only slash command names complete
+
+---
+
+## 2. Enhancement Plan
+
+### Phase 0: Structural Cleanup (Foundation)
+
+**Goal**: Break the monolith, remove dead code, establish the module structure for TUI work.
+
+| Task | Description | Effort |
+|---|---|---|
+| 0.1 | **Extract `LiveCli` into `app.rs`** — Move the entire `LiveCli` struct, its impl, and helpers (`format_*`, `render_*`, session management) out of `main.rs` into focused modules: `app.rs` (core), `format.rs` (report formatting), `session_manager.rs` (session CRUD) | M |
+| 0.2 | **Remove or merge the legacy `CliApp`** — The existing `app.rs` has an unused `CliApp` with its own `ConversationClient`-based rendering. Either delete it or merge its unique features (stream event handler pattern) into the active `LiveCli` | S |
+| 0.3 | **Extract `main.rs` arg parsing** — The current `parse_args()` is a hand-rolled parser that duplicates the clap-based `args.rs`. Consolidate on the hand-rolled parser (it's more feature-complete) and move it to `args.rs`, or adopt clap fully | S |
+| 0.4 | **Create a `tui/` module** — Introduce `crates/rusty-claude-cli/src/tui/mod.rs` as the namespace for all new TUI components: `status_bar.rs`, `layout.rs`, `tool_panel.rs`, etc. | S |
+
+### Phase 1: Status Bar & Live HUD
+
+**Goal**: Persistent information display during interaction.
+
+| Task | Description | Effort |
+|---|---|---|
+| 1.1 | **Terminal-size-aware status line** — Use `crossterm::terminal::size()` to render a bottom-pinned status bar showing: model name, permission mode, session ID, cumulative token count, estimated cost | M |
+| 1.2 | **Live token counter** — Update the status bar in real-time as `AssistantEvent::Usage` and `AssistantEvent::TextDelta` events arrive during streaming | M |
+| 1.3 | **Turn duration timer** — Show elapsed time for the current turn (the `showTurnDuration` config already exists in Config tool but isn't wired up) | S |
+| 1.4 | **Git branch indicator** — Display the current git branch in the status bar (already parsed via `parse_git_status_metadata`) | S |
+
+### Phase 2: Enhanced Streaming Output
+
+**Goal**: Make the main response stream visually rich and responsive.
+
+| Task | Description | Effort |
+|---|---|---|
+| 2.1 | **Live markdown rendering** — Instead of raw text streaming, buffer text deltas and incrementally render Markdown as it arrives (heading detection, bold/italic, inline code). The existing `TerminalRenderer::render_markdown` can be adapted for incremental use | L |
+| 2.2 | **Thinking indicator** — When extended thinking/reasoning is active, show a distinct animated indicator (e.g., `🧠 Reasoning...` with pulsing dots or a different spinner) instead of the generic `🦀 Thinking...` | S |
+| 2.3 | **Streaming progress bar** — Add an optional horizontal progress indicator below the spinner showing approximate completion (based on max_tokens vs. output_tokens so far) | M |
+| 2.4 | **Remove artificial stream delay** — The current `stream_markdown` sleeps 8ms per chunk. For tool results this is fine, but for the main response stream it should be immediate or configurable | S |
+
+### Phase 3: Tool Call Visualization
+
+**Goal**: Make tool execution legible and navigable.
+
+| Task | Description | Effort |
+|---|---|---|
+| 3.1 | **Collapsible tool output** — For tool results longer than N lines (configurable, default 15), show a summary with `[+] Expand` hint; pressing a key reveals the full output. Initially implement as truncation with a "full output saved to file" fallback | M |
+| 3.2 | **Syntax-highlighted tool results** — When tool results contain code (detected by tool name — `bash` stdout, `read_file` content, `REPL` output), apply syntect highlighting rather than rendering as plain text | M |
+| 3.3 | **Tool call timeline** — For multi-tool turns, show a compact summary: `🔧 bash → ✓ | read_file → ✓ | edit_file → ✓ (3 tools, 1.2s)` after all tool calls complete | S |
+| 3.4 | **Diff-aware edit_file display** — When `edit_file` succeeds, show a colored unified diff of the change instead of just `✓ edit_file: path` | M |
+| 3.5 | **Permission prompt enhancement** — Style the approval prompt with box drawing, color the tool name, show a one-line summary of what the tool will do | S |
+
+### Phase 4: Enhanced Slash Commands & Navigation
+
+**Goal**: Improve information display and add missing features.
+
+| Task | Description | Effort |
+|---|---|---|
+| 4.1 | **Colored `/diff` output** — Parse the git diff and render it with red/green coloring for removals/additions, similar to `delta` or `diff-so-fancy` | M |
+| 4.2 | **Pager for long outputs** — When `/status`, `/config`, `/memory`, or `/diff` produce output longer than the terminal height, pipe through an internal pager (scroll with j/k/q) or external `$PAGER` | M |
+| 4.3 | **`/search` command** — Add a new command to search conversation history by keyword | M |
+| 4.4 | **`/undo` command** — Undo the last file edit by restoring from the `originalFile` data in `write_file`/`edit_file` tool results | M |
+| 4.5 | **Interactive session picker** — Replace the text-based `/session list` with an interactive fuzzy-filterable list (up/down arrows to select, enter to switch) | L |
+| 4.6 | **Tab completion for tool arguments** — Extend `SlashCommandHelper` to complete file paths after `/export`, model names after `/model`, session IDs after `/session switch` | M |
+
+### Phase 5: Color Themes & Configuration
+
+**Goal**: User-customizable visual appearance.
+
+| Task | Description | Effort |
+|---|---|---|
+| 5.1 | **Named color themes** — Add `dark` (current default), `light`, `solarized`, `catppuccin` themes. Wire to the existing `Config` tool's `theme` setting | M |
+| 5.2 | **ANSI-256 / truecolor detection** — Detect terminal capabilities and fall back gracefully (no colors → 16 colors → 256 → truecolor) | M |
+| 5.3 | **Configurable spinner style** — Allow choosing between braille dots, bar, moon phases, etc. | S |
+| 5.4 | **Banner customization** — Make the ASCII art banner optional or configurable via settings | S |
+
+### Phase 6: Full-Screen TUI Mode (Stretch)
+
+**Goal**: Optional alternate-screen layout for power users.
+
+| Task | Description | Effort |
+|---|---|---|
+| 6.1 | **Add `ratatui` dependency** — Introduce `ratatui` (terminal UI framework) as an optional dependency for the full-screen mode | S |
+| 6.2 | **Split-pane layout** — Top pane: conversation with scrollback; Bottom pane: input area; Right sidebar (optional): tool status/todo list | XL |
+| 6.3 | **Scrollable conversation view** — Navigate past messages with PgUp/PgDn, search within conversation | L |
+| 6.4 | **Keyboard shortcuts panel** — Show `?` help overlay with all keybindings | M |
+| 6.5 | **Mouse support** — Click to expand tool results, scroll conversation, select text for copy | L |
+
+---
+
+## 3. Priority Recommendation
+
+### Immediate (High Impact, Moderate Effort)
+
+1. **Phase 0** — Essential cleanup. The 3,159-line `main.rs` is the #1 maintenance risk and blocks clean TUI additions.
+2. **Phase 1.1–1.2** — Status bar with live tokens. Highest-impact UX win: users constantly want to know token usage.
+3. **Phase 2.4** — Remove artificial delay. Low effort, immediately noticeable improvement.
+4. **Phase 3.1** — Collapsible tool output. Large bash outputs currently wreck readability.
+
+### Near-Term (Next Sprint)
+
+5. **Phase 2.1** — Live markdown rendering. Makes the core interaction feel polished.
+6. **Phase 3.2** — Syntax-highlighted tool results.
+7. **Phase 3.4** — Diff-aware edit display.
+8. **Phase 4.1** — Colored diff for `/diff`.
+
+### Longer-Term
+
+9. **Phase 5** — Color themes (user demand-driven).
+10. **Phase 4.2–4.6** — Enhanced navigation and commands.
+11. **Phase 6** — Full-screen mode (major undertaking, evaluate after earlier phases ship).
+
+---
+
+## 4. Architecture Recommendations
+
+### Module Structure After Phase 0
+
+```
+crates/rusty-claude-cli/src/
+├── main.rs              # Entrypoint, arg dispatch only (~100 lines)
+├── args.rs              # CLI argument parsing (consolidate existing two parsers)
+├── app.rs               # LiveCli struct, REPL loop, turn execution
+├── format.rs            # All report formatting (status, cost, model, permissions, etc.)
+├── session_mgr.rs       # Session CRUD: create, resume, list, switch, persist
+├── init.rs              # Repo initialization (unchanged)
+├── input.rs             # Line editor (unchanged, minor extensions)
+├── render.rs            # TerminalRenderer, Spinner (extended)
+└── tui/
+    ├── mod.rs           # TUI module root
+    ├── status_bar.rs    # Persistent bottom status line
+    ├── tool_panel.rs    # Tool call visualization (boxes, timelines, collapsible)
+    ├── diff_view.rs     # Colored diff rendering
+    ├── pager.rs         # Internal pager for long outputs
+    └── theme.rs         # Color theme definitions and selection
+```
+
+### Key Design Principles
+
+1. **Keep the inline REPL as the default** — Full-screen TUI should be opt-in (`--tui` flag)
+2. **Everything testable without a terminal** — All formatting functions take `&mut impl Write`, never assume stdout directly
+3. **Streaming-first** — Rendering should work incrementally, not buffering the entire response
+4. **Respect `crossterm` for all terminal control** — Don't mix raw ANSI escape codes with crossterm (the current codebase does this in the startup banner)
+5. **Feature-gate heavy dependencies** — `ratatui` should be behind a `full-tui` feature flag
+
+---
+
+## 5. Risk Assessment
+
+| Risk | Mitigation |
+|---|---|
+| Breaking the working REPL during refactor | Phase 0 is pure restructuring with existing test coverage as safety net |
+| Terminal compatibility issues (tmux, SSH, Windows) | Rely on crossterm's abstraction; test in degraded environments |
+| Performance regression with rich rendering | Profile before/after; keep the fast path (raw streaming) always available |
+| Scope creep into Phase 6 | Ship Phases 0–3 as a coherent release before starting Phase 6 |
+| `app.rs` vs `main.rs` confusion | Phase 0.2 explicitly resolves this by removing the legacy `CliApp` |
+
+---
+
+*Generated: 2026-03-31 | Workspace: `rust/` | Branch: `dev/rust`*

rust/.sandbox-home/.rustup/settings.toml

@@ -0,0 +1,3 @@
+version = "12"
+
+[overrides]

rust/TUI-ENHANCEMENT-PLAN.md

@@ -0,0 +1,221 @@
+# TUI Enhancement Plan — Claw Code (`rusty-claude-cli`)
+
+## Executive Summary
+
+This plan covers a comprehensive analysis of the current terminal user interface and proposes phased enhancements that will transform the existing REPL/prompt CLI into a polished, modern TUI experience — while preserving the existing clean architecture and test coverage.
+
+---
+
+## 1. Current Architecture Analysis
+
+### Crate Map
+
+| Crate | Purpose | Lines | TUI Relevance |
+|---|---|---|---|
+| `rusty-claude-cli` | Main binary: REPL loop, arg parsing, rendering, API bridge | ~3,600 | **Primary TUI surface** |
+| `runtime` | Session, conversation loop, config, permissions, compaction | ~5,300 | Provides data/state |
+| `api` | Anthropic HTTP client + SSE streaming | ~1,500 | Provides stream events |
+| `commands` | Slash command metadata/parsing/help | ~470 | Drives command dispatch |
+| `tools` | 18 built-in tool implementations | ~3,500 | Tool execution display |
+
+### Current TUI Components
+
+| Component | File | What It Does Today | Quality |
+|---|---|---|---|
+| **Input** | `input.rs` (269 lines) | `rustyline`-based line editor with slash-command tab completion, Shift+Enter newline, history | ✅ Solid |
+| **Rendering** | `render.rs` (641 lines) | Markdown→terminal rendering (headings, lists, tables, code blocks with syntect highlighting, blockquotes), spinner widget | ✅ Good |
+| **App/REPL loop** | `main.rs` (3,159 lines) | The monolithic `LiveCli` struct: REPL loop, all slash command handlers, streaming output, tool call display, permission prompting, session management | ⚠️ Monolithic |
+| **Alt App** | `app.rs` (398 lines) | An earlier `CliApp` prototype with `ConversationClient`, stream event handling, `TerminalRenderer`, output format support | ⚠️ Appears unused/legacy |
+
+### Key Dependencies
+
+- **crossterm 0.28** — terminal control (cursor, colors, clear)
+- **pulldown-cmark 0.13** — Markdown parsing
+- **syntect 5** — syntax highlighting
+- **rustyline 15** — line editing with completion
+- **serde_json** — tool I/O formatting
+
+### Strengths
+
+1. **Clean rendering pipeline**: Markdown rendering is well-structured with state tracking, table rendering, code highlighting
+2. **Rich tool display**: Tool calls get box-drawing borders (`╭─ name ─╮`), results show ✓/✗ icons
+3. **Comprehensive slash commands**: 15 commands covering model switching, permissions, sessions, config, diff, export
+4. **Session management**: Full persistence, resume, list, switch, compaction
+5. **Permission prompting**: Interactive Y/N approval for restricted tool calls
+6. **Thorough tests**: Every formatting function, every parse path has unit tests
+
+### Weaknesses & Gaps
+
+1. **`main.rs` is a 3,159-line monolith** — all REPL logic, formatting, API bridging, session management, and tests in one file
+2. **No alternate-screen / full-screen layout** — everything is inline scrolling output
+3. **No progress bars** — only a single braille spinner; no indication of streaming progress or token counts during generation
+4. **No visual diff rendering** — `/diff` just dumps raw git diff text
+5. **No syntax highlighting in streamed output** — markdown rendering only applies to tool results, not to the main assistant response stream
+6. **No status bar / HUD** — model, tokens, session info not visible during interaction
+7. **No image/attachment preview** — `SendUserMessage` resolves attachments but never displays them
+8. **Streaming is char-by-char with artificial delay** — `stream_markdown` sleeps 8ms per whitespace-delimited chunk
+9. **No color theme customization** — hardcoded `ColorTheme::default()`
+10. **No resize handling** — no terminal size awareness for wrapping, truncation, or layout
+11. **Dual app structs** — `app.rs` has a separate `CliApp` that duplicates `LiveCli` from `main.rs`
+12. **No pager for long outputs** — `/status`, `/config`, `/memory` can overflow the viewport
+13. **Tool results not collapsible** — large bash outputs flood the screen
+14. **No thinking/reasoning indicator** — when the model is in "thinking" mode, no visual distinction
+15. **No auto-complete for tool arguments** — only slash command names complete
+
+---
+
+## 2. Enhancement Plan
+
+### Phase 0: Structural Cleanup (Foundation)
+
+**Goal**: Break the monolith, remove dead code, establish the module structure for TUI work.
+
+| Task | Description | Effort |
+|---|---|---|
+| 0.1 | **Extract `LiveCli` into `app.rs`** — Move the entire `LiveCli` struct, its impl, and helpers (`format_*`, `render_*`, session management) out of `main.rs` into focused modules: `app.rs` (core), `format.rs` (report formatting), `session_manager.rs` (session CRUD) | M |
+| 0.2 | **Remove or merge the legacy `CliApp`** — The existing `app.rs` has an unused `CliApp` with its own `ConversationClient`-based rendering. Either delete it or merge its unique features (stream event handler pattern) into the active `LiveCli` | S |
+| 0.3 | **Extract `main.rs` arg parsing** — The current `parse_args()` is a hand-rolled parser that duplicates the clap-based `args.rs`. Consolidate on the hand-rolled parser (it's more feature-complete) and move it to `args.rs`, or adopt clap fully | S |
+| 0.4 | **Create a `tui/` module** — Introduce `crates/rusty-claude-cli/src/tui/mod.rs` as the namespace for all new TUI components: `status_bar.rs`, `layout.rs`, `tool_panel.rs`, etc. | S |
+
+### Phase 1: Status Bar & Live HUD
+
+**Goal**: Persistent information display during interaction.
+
+| Task | Description | Effort |
+|---|---|---|
+| 1.1 | **Terminal-size-aware status line** — Use `crossterm::terminal::size()` to render a bottom-pinned status bar showing: model name, permission mode, session ID, cumulative token count, estimated cost | M |
+| 1.2 | **Live token counter** — Update the status bar in real-time as `AssistantEvent::Usage` and `AssistantEvent::TextDelta` events arrive during streaming | M |
+| 1.3 | **Turn duration timer** — Show elapsed time for the current turn (the `showTurnDuration` config already exists in Config tool but isn't wired up) | S |
+| 1.4 | **Git branch indicator** — Display the current git branch in the status bar (already parsed via `parse_git_status_metadata`) | S |
+
+### Phase 2: Enhanced Streaming Output
+
+**Goal**: Make the main response stream visually rich and responsive.
+
+| Task | Description | Effort |
+|---|---|---|
+| 2.1 | **Live markdown rendering** — Instead of raw text streaming, buffer text deltas and incrementally render Markdown as it arrives (heading detection, bold/italic, inline code). The existing `TerminalRenderer::render_markdown` can be adapted for incremental use | L |
+| 2.2 | **Thinking indicator** — When extended thinking/reasoning is active, show a distinct animated indicator (e.g., `🧠 Reasoning...` with pulsing dots or a different spinner) instead of the generic `🦀 Thinking...` | S |
+| 2.3 | **Streaming progress bar** — Add an optional horizontal progress indicator below the spinner showing approximate completion (based on max_tokens vs. output_tokens so far) | M |
+| 2.4 | **Remove artificial stream delay** — The current `stream_markdown` sleeps 8ms per chunk. For tool results this is fine, but for the main response stream it should be immediate or configurable | S |
+
+### Phase 3: Tool Call Visualization
+
+**Goal**: Make tool execution legible and navigable.
+
+| Task | Description | Effort |
+|---|---|---|
+| 3.1 | **Collapsible tool output** — For tool results longer than N lines (configurable, default 15), show a summary with `[+] Expand` hint; pressing a key reveals the full output. Initially implement as truncation with a "full output saved to file" fallback | M |
+| 3.2 | **Syntax-highlighted tool results** — When tool results contain code (detected by tool name — `bash` stdout, `read_file` content, `REPL` output), apply syntect highlighting rather than rendering as plain text | M |
+| 3.3 | **Tool call timeline** — For multi-tool turns, show a compact summary: `🔧 bash → ✓ | read_file → ✓ | edit_file → ✓ (3 tools, 1.2s)` after all tool calls complete | S |
+| 3.4 | **Diff-aware edit_file display** — When `edit_file` succeeds, show a colored unified diff of the change instead of just `✓ edit_file: path` | M |
+| 3.5 | **Permission prompt enhancement** — Style the approval prompt with box drawing, color the tool name, show a one-line summary of what the tool will do | S |
+
+### Phase 4: Enhanced Slash Commands & Navigation
+
+**Goal**: Improve information display and add missing features.
+
+| Task | Description | Effort |
+|---|---|---|
+| 4.1 | **Colored `/diff` output** — Parse the git diff and render it with red/green coloring for removals/additions, similar to `delta` or `diff-so-fancy` | M |
+| 4.2 | **Pager for long outputs** — When `/status`, `/config`, `/memory`, or `/diff` produce output longer than the terminal height, pipe through an internal pager (scroll with j/k/q) or external `$PAGER` | M |
+| 4.3 | **`/search` command** — Add a new command to search conversation history by keyword | M |
+| 4.4 | **`/undo` command** — Undo the last file edit by restoring from the `originalFile` data in `write_file`/`edit_file` tool results | M |
+| 4.5 | **Interactive session picker** — Replace the text-based `/session list` with an interactive fuzzy-filterable list (up/down arrows to select, enter to switch) | L |
+| 4.6 | **Tab completion for tool arguments** — Extend `SlashCommandHelper` to complete file paths after `/export`, model names after `/model`, session IDs after `/session switch` | M |
+
+### Phase 5: Color Themes & Configuration
+
+**Goal**: User-customizable visual appearance.
+
+| Task | Description | Effort |
+|---|---|---|
+| 5.1 | **Named color themes** — Add `dark` (current default), `light`, `solarized`, `catppuccin` themes. Wire to the existing `Config` tool's `theme` setting | M |
+| 5.2 | **ANSI-256 / truecolor detection** — Detect terminal capabilities and fall back gracefully (no colors → 16 colors → 256 → truecolor) | M |
+| 5.3 | **Configurable spinner style** — Allow choosing between braille dots, bar, moon phases, etc. | S |
+| 5.4 | **Banner customization** — Make the ASCII art banner optional or configurable via settings | S |
+
+### Phase 6: Full-Screen TUI Mode (Stretch)
+
+**Goal**: Optional alternate-screen layout for power users.
+
+| Task | Description | Effort |
+|---|---|---|
+| 6.1 | **Add `ratatui` dependency** — Introduce `ratatui` (terminal UI framework) as an optional dependency for the full-screen mode | S |
+| 6.2 | **Split-pane layout** — Top pane: conversation with scrollback; Bottom pane: input area; Right sidebar (optional): tool status/todo list | XL |
+| 6.3 | **Scrollable conversation view** — Navigate past messages with PgUp/PgDn, search within conversation | L |
+| 6.4 | **Keyboard shortcuts panel** — Show `?` help overlay with all keybindings | M |
+| 6.5 | **Mouse support** — Click to expand tool results, scroll conversation, select text for copy | L |
+
+---
+
+## 3. Priority Recommendation
+
+### Immediate (High Impact, Moderate Effort)
+
+1. **Phase 0** — Essential cleanup. The 3,159-line `main.rs` is the #1 maintenance risk and blocks clean TUI additions.
+2. **Phase 1.1–1.2** — Status bar with live tokens. Highest-impact UX win: users constantly want to know token usage.
+3. **Phase 2.4** — Remove artificial delay. Low effort, immediately noticeable improvement.
+4. **Phase 3.1** — Collapsible tool output. Large bash outputs currently wreck readability.
+
+### Near-Term (Next Sprint)
+
+5. **Phase 2.1** — Live markdown rendering. Makes the core interaction feel polished.
+6. **Phase 3.2** — Syntax-highlighted tool results.
+7. **Phase 3.4** — Diff-aware edit display.
+8. **Phase 4.1** — Colored diff for `/diff`.
+
+### Longer-Term
+
+9. **Phase 5** — Color themes (user demand-driven).
+10. **Phase 4.2–4.6** — Enhanced navigation and commands.
+11. **Phase 6** — Full-screen mode (major undertaking, evaluate after earlier phases ship).
+
+---
+
+## 4. Architecture Recommendations
+
+### Module Structure After Phase 0
+
+```
+crates/rusty-claude-cli/src/
+├── main.rs              # Entrypoint, arg dispatch only (~100 lines)
+├── args.rs              # CLI argument parsing (consolidate existing two parsers)
+├── app.rs               # LiveCli struct, REPL loop, turn execution
+├── format.rs            # All report formatting (status, cost, model, permissions, etc.)
+├── session_mgr.rs       # Session CRUD: create, resume, list, switch, persist
+├── init.rs              # Repo initialization (unchanged)
+├── input.rs             # Line editor (unchanged, minor extensions)
+├── render.rs            # TerminalRenderer, Spinner (extended)
+└── tui/
+    ├── mod.rs           # TUI module root
+    ├── status_bar.rs    # Persistent bottom status line
+    ├── tool_panel.rs    # Tool call visualization (boxes, timelines, collapsible)
+    ├── diff_view.rs     # Colored diff rendering
+    ├── pager.rs         # Internal pager for long outputs
+    └── theme.rs         # Color theme definitions and selection
+```
+
+### Key Design Principles
+
+1. **Keep the inline REPL as the default** — Full-screen TUI should be opt-in (`--tui` flag)
+2. **Everything testable without a terminal** — All formatting functions take `&mut impl Write`, never assume stdout directly
+3. **Streaming-first** — Rendering should work incrementally, not buffering the entire response
+4. **Respect `crossterm` for all terminal control** — Don't mix raw ANSI escape codes with crossterm (the current codebase does this in the startup banner)
+5. **Feature-gate heavy dependencies** — `ratatui` should be behind a `full-tui` feature flag
+
+---
+
+## 5. Risk Assessment
+
+| Risk | Mitigation |
+|---|---|
+| Breaking the working REPL during refactor | Phase 0 is pure restructuring with existing test coverage as safety net |
+| Terminal compatibility issues (tmux, SSH, Windows) | Rely on crossterm's abstraction; test in degraded environments |
+| Performance regression with rich rendering | Profile before/after; keep the fast path (raw streaming) always available |
+| Scope creep into Phase 6 | Ship Phases 0–3 as a coherent release before starting Phase 6 |
+| `app.rs` vs `main.rs` confusion | Phase 0.2 explicitly resolves this by removing the legacy `CliApp` |
+
+---
+
+*Generated: 2026-03-31 | Workspace: `rust/` | Branch: `dev/rust`*

rust/crates/tools/src/lib.rs

@@ -1259,15 +1259,7 @@ fn validate_todos(todos: &[TodoItem]) -> Result<(), String> {
     if todos.is_empty() {
         return Err(String::from("todos must not be empty"));
     }
-    let in_progress = todos
+    // Allow multiple in_progress items for parallel workflows
-        .iter()
-        .filter(|todo| matches!(todo.status, TodoStatus::InProgress))
-        .count();
-    if in_progress > 1 {
-        return Err(String::from(
-            "exactly zero or one todo items may be in_progress",
-        ));
-    }
     if todos.iter().any(|todo| todo.content.trim().is_empty()) {
         return Err(String::from("todo content must not be empty"));
     }
@@ -2654,7 +2646,8 @@ mod tests {
             .expect_err("empty todos should fail");
         assert!(empty.contains("todos must not be empty"));
 
-        let too_many_active = execute_tool(
+        // Multiple in_progress items are now allowed for parallel workflows
+        let _multi_active = execute_tool(
             "TodoWrite",
             &json!({
                 "todos": [
@@ -2663,8 +2656,7 @@ mod tests {
                 ]
             }),
         )
-        .expect_err("multiple in-progress todos should fail");
+        .expect("multiple in-progress todos should succeed");
-        assert!(too_many_active.contains("zero or one todo items may be in_progress"));
 
         let blank_content = execute_tool(
             "TodoWrite",