Prevent long sessions from stalling and expose the requested internal command surface

The runtime now auto-compacts completed conversations once cumulative input usage
crosses a configurable threshold, preserving recent context while surfacing an
explicit user notice. The CLI also publishes the requested ant-only slash
commands through the shared commands crate and main dispatch, using meaningful
local implementations for commit/PR/issue/teleport/debug workflows.

Constraint: Reuse the existing Rust compaction pipeline instead of introducing a new summarization stack
Constraint: No new dependencies or broad command-framework rewrite
Rejected: Implement API-driven compaction inside ConversationRuntime now | too much new plumbing for this delivery
Rejected: Expose new commands as parse-only stubs | would not satisfy the requested command availability
Confidence: medium
Scope-risk: moderate
Reversibility: clean
Directive: If runtime later gains true API-backed compaction, preserve the TurnSummary auto-compaction metadata shape so CLI call sites stay stable
Tested: cargo test; cargo build --release; cargo fmt --all; git diff --check; LSP diagnostics directory check
Not-tested: Live Anthropic-backed specialist command flows; gh-authenticated PR/issue creation in a real repo

.claude.json

@@ -0,0 +1,5 @@
+{
+  "permissions": {
+    "defaultMode": "dontAsk"
+  }
+}

.gitignore

@@ -2,3 +2,6 @@ __pycache__/
 archive/
 .omx/
 .clawd-agents/
+# Claude Code local artifacts
+.claude/settings.local.json
+.claude/sessions/

CLAUDE.md

@@ -0,0 +1,21 @@
+# CLAUDE.md
+
+This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
+
+## Detected stack
+- Languages: Rust.
+- Frameworks: none detected from the supported starter markers.
+
+## Verification
+- Run Rust verification from `rust/`: `cargo fmt`, `cargo clippy --workspace --all-targets -- -D warnings`, `cargo test --workspace`
+- `src/` and `tests/` are both present; update both surfaces together when behavior changes.
+
+## Repository shape
+- `rust/` contains the Rust workspace and active CLI/runtime implementation.
+- `src/` contains source files that should stay consistent with generated guidance and tests.
+- `tests/` contains validation surfaces that should be reviewed alongside code changes.
+
+## Working agreement
+- Prefer small, reviewable changes and keep generated bootstrap files aligned with actual repo workflows.
+- Keep shared defaults in `.claude.json`; reserve `.claude/settings.local.json` for machine-local overrides.
+- Do not overwrite existing `CLAUDE.md` content automatically; update it intentionally when repo workflows change.

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/.claude/sessions/session-1775012674485.json

@@ -0,0 +1 @@
+{"messages":[{"blocks":[{"text":"clear","type":"text"}],"role":"user"},{"blocks":[{"text":"\n\nI've cleared the conversation. How can I help you today?","type":"text"}],"role":"assistant","usage":{"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"input_tokens":4272,"output_tokens":17}}],"version":1}

rust/.claude/sessions/session-1775012687059.json

@@ -0,0 +1 @@
+{"messages":[{"blocks":[{"text":"exit","type":"text"}],"role":"user"},{"blocks":[{"text":"\n\nGoodbye! 👋","type":"text"}],"role":"assistant","usage":{"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"input_tokens":4272,"output_tokens":10}}],"version":1}

rust/.claude/sessions/session-1775013221875.json

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

rust/.clawd-todos.json

@@ -0,0 +1,27 @@
+[
+  {
+    "content": "Architecture & dependency analysis",
+    "activeForm": "Complete",
+    "status": "completed"
+  },
+  {
+    "content": "Runtime crate deep analysis",
+    "activeForm": "Complete",
+    "status": "completed"
+  },
+  {
+    "content": "CLI & Tools analysis",
+    "activeForm": "Complete",
+    "status": "completed"
+  },
+  {
+    "content": "Code quality verification",
+    "activeForm": "Complete",
+    "status": "completed"
+  },
+  {
+    "content": "Synthesize findings into unified report",
+    "activeForm": "Writing report",
+    "status": "in_progress"
+  }
+]

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/Cargo.lock

@@ -1545,10 +1545,12 @@ dependencies = [
 name = "tools"
 version = "0.1.0"
 dependencies = [
+ "api",
  "reqwest",
  "runtime",
  "serde",
  "serde_json",
+ "tokio",
 ]
 
 [[package]]

rust/README.md

@@ -1,230 +1,149 @@
-# Rusty Claude CLI
+# 🦞 Claw Code — Rust Implementation
 
-`rust/` contains the Rust workspace for the integrated `rusty-claude-cli` deliverable.
+A high-performance Rust rewrite of the Claude Code CLI agent harness. Built for speed, safety, and native tool execution.
-It is intended to be something you can clone, build, and run directly.
 
-## Workspace layout
+## Quick Start
 
-```text
+```bash
+# Build
+cd rust/
+cargo build --release
+
+# Run interactive REPL
+./target/release/claw
+
+# One-shot prompt
+./target/release/claw prompt "explain this codebase"
+
+# With specific model
+./target/release/claw --model sonnet prompt "fix the bug in main.rs"
+```
+
+## Configuration
+
+Set your API credentials:
+
+```bash
+export ANTHROPIC_API_KEY="sk-ant-..."
+# Or use a proxy
+export ANTHROPIC_BASE_URL="https://your-proxy.com"
+```
+
+Or authenticate via OAuth:
+
+```bash
+claw login
+```
+
+## Features
+
+| Feature | Status |
+|---------|--------|
+| Anthropic API + streaming | ✅ |
+| OAuth login/logout | ✅ |
+| Interactive REPL (rustyline) | ✅ |
+| Tool system (bash, read, write, edit, grep, glob) | ✅ |
+| Web tools (search, fetch) | ✅ |
+| Sub-agent orchestration | ✅ |
+| Todo tracking | ✅ |
+| Notebook editing | ✅ |
+| CLAUDE.md / project memory | ✅ |
+| Config file hierarchy (.claude.json) | ✅ |
+| Permission system | ✅ |
+| MCP server lifecycle | ✅ |
+| Session persistence + resume | ✅ |
+| Extended thinking (thinking blocks) | ✅ |
+| Cost tracking + usage display | ✅ |
+| Git integration | ✅ |
+| Markdown terminal rendering (ANSI) | ✅ |
+| Model aliases (opus/sonnet/haiku) | ✅ |
+| Slash commands (/status, /compact, /clear, etc.) | ✅ |
+| Hooks (PreToolUse/PostToolUse) | 🔧 Config only |
+| Plugin system | 📋 Planned |
+| Skills registry | 📋 Planned |
+
+## Model Aliases
+
+Short names resolve to the latest model versions:
+
+| Alias | Resolves To |
+|-------|------------|
+| `opus` | `claude-opus-4-6` |
+| `sonnet` | `claude-sonnet-4-6` |
+| `haiku` | `claude-haiku-4-5-20251213` |
+
+## CLI Flags
+
+```
+claw [OPTIONS] [COMMAND]
+
+Options:
+  --model MODEL                    Set the model (alias or full name)
+  --dangerously-skip-permissions   Skip all permission checks
+  --permission-mode MODE           Set read-only, workspace-write, or danger-full-access
+  --allowedTools TOOLS             Restrict enabled tools
+  --output-format FORMAT           Output format (text or json)
+  --version, -V                    Print version info
+
+Commands:
+  prompt <text>      One-shot prompt (non-interactive)
+  login              Authenticate via OAuth
+  logout             Clear stored credentials
+  init               Initialize project config
+  doctor             Check environment health
+  self-update        Update to latest version
+```
+
+## Slash Commands (REPL)
+
+| Command | Description |
+|---------|-------------|
+| `/help` | Show help |
+| `/status` | Show session status (model, tokens, cost) |
+| `/cost` | Show cost breakdown |
+| `/compact` | Compact conversation history |
+| `/clear` | Clear conversation |
+| `/model [name]` | Show or switch model |
+| `/permissions` | Show or switch permission mode |
+| `/config [section]` | Show config (env, hooks, model) |
+| `/memory` | Show CLAUDE.md contents |
+| `/diff` | Show git diff |
+| `/export [path]` | Export conversation |
+| `/session [id]` | Resume a previous session |
+| `/version` | Show version |
+
+## Workspace Layout
+
+```
 rust/
-├── Cargo.toml
+├── Cargo.toml              # Workspace root
 ├── Cargo.lock
-├── README.md
 └── crates/
-    ├── api/               # Anthropic API client + SSE streaming support
+    ├── api/                # Anthropic API client + SSE streaming
-    ├── commands/          # Shared slash-command metadata/help surfaces
+    ├── commands/           # Shared slash-command registry
-    ├── compat-harness/    # Upstream TS manifest extraction harness
+    ├── compat-harness/     # TS manifest extraction harness
-    ├── runtime/           # Session/runtime/config/prompt orchestration
+    ├── runtime/            # Session, config, permissions, MCP, prompts
-    ├── rusty-claude-cli/  # Main CLI binary
+    ├── rusty-claude-cli/   # Main CLI binary (`claw`)
-    └── tools/             # Built-in tool implementations
+    └── tools/              # Built-in tool implementations
 ```
 
-## Prerequisites
+### Crate Responsibilities
 
-- Rust toolchain installed (`rustup`, stable toolchain)
+- **api** — HTTP client, SSE stream parser, request/response types, auth (API key + OAuth bearer)
-- Network access and Anthropic credentials for live prompt/REPL usage
+- **commands** — Slash command definitions and help text generation
+- **compat-harness** — Extracts tool/prompt manifests from upstream TS source
+- **runtime** — `ConversationRuntime` agentic loop, `ConfigLoader` hierarchy, `Session` persistence, permission policy, MCP client, system prompt assembly, usage tracking
+- **rusty-claude-cli** — REPL, one-shot prompt, streaming display, tool call rendering, CLI argument parsing
+- **tools** — Tool specs + execution: Bash, ReadFile, WriteFile, EditFile, GlobSearch, GrepSearch, WebSearch, WebFetch, Agent, TodoWrite, NotebookEdit, Skill, ToolSearch, REPL runtimes
 
-## Build
+## Stats
 
-From the repository root:
+- **~20K lines** of Rust
+- **6 crates** in workspace
+- **Binary name:** `claw`
+- **Default model:** `claude-opus-4-6`
+- **Default permissions:** `danger-full-access`
 
-```bash
+## License
-cd rust
-cargo build --release -p rusty-claude-cli
-```
 
-The optimized binary will be written to:
+See repository root.
-
-```bash
-./target/release/rusty-claude-cli
-```
-
-## Test
-
-Run the verified workspace test suite used for release-readiness:
-
-```bash
-cd rust
-cargo test --workspace --exclude compat-harness
-```
-
-## Quick start
-
-### Show help
-
-```bash
-cd rust
-cargo run -p rusty-claude-cli -- --help
-```
-
-### Print version
-
-```bash
-cd rust
-cargo run -p rusty-claude-cli -- --version
-```
-
-### Login with OAuth
-
-Configure `settings.json` with an `oauth` block containing `clientId`, `authorizeUrl`, `tokenUrl`, optional `callbackPort`, and optional `scopes`, then run:
-
-```bash
-cd rust
-cargo run -p rusty-claude-cli -- login
-```
-
-This opens the browser, listens on the configured localhost callback, exchanges the auth code for tokens, and stores OAuth credentials in `~/.claude/credentials.json` (or `$CLAUDE_CONFIG_HOME/credentials.json`).
-
-### Logout
-
-```bash
-cd rust
-cargo run -p rusty-claude-cli -- logout
-```
-
-This removes only the stored OAuth credentials and preserves unrelated JSON fields in `credentials.json`.
-
-### Self-update
-
-```bash
-cd rust
-cargo run -p rusty-claude-cli -- self-update
-```
-
-The command checks the latest GitHub release for `instructkr/clawd-code`, compares it to the current binary version, downloads the matching binary asset plus checksum manifest, verifies SHA-256, replaces the current executable, and prints the release changelog. If no published release or matching asset exists, it exits safely with an explanatory message.
-
-## Usage examples
-
-### 1) Prompt mode
-
-Send one prompt, stream the answer, then exit:
-
-```bash
-cd rust
-cargo run -p rusty-claude-cli -- prompt "Summarize the architecture of this repository"
-```
-
-Use a specific model:
-
-```bash
-cd rust
-cargo run -p rusty-claude-cli -- --model claude-sonnet-4-20250514 prompt "List the key crates in this workspace"
-```
-
-Restrict enabled tools in an interactive session:
-
-```bash
-cd rust
-cargo run -p rusty-claude-cli -- --allowedTools read,glob
-```
-
-Bootstrap Claude project files for the current repo:
-
-```bash
-cd rust
-cargo run -p rusty-claude-cli -- init
-```
-
-### 2) REPL mode
-
-Start the interactive shell:
-
-```bash
-cd rust
-cargo run -p rusty-claude-cli --
-```
-
-Inside the REPL, useful commands include:
-
-```text
-/help
-/status
-/model claude-sonnet-4-20250514
-/permissions workspace-write
-/cost
-/compact
-/memory
-/config
-/init
-/diff
-/version
-/export notes.txt
-/sessions
-/session list
-/exit
-```
-
-### 3) Resume an existing session
-
-Inspect or maintain a saved session file without entering the REPL:
-
-```bash
-cd rust
-cargo run -p rusty-claude-cli -- --resume session-123456 /status /compact /cost
-```
-
-You can also inspect memory/config state for a restored session:
-
-```bash
-cd rust
-cargo run -p rusty-claude-cli -- --resume ~/.claude/sessions/session-123456.json /memory /config
-```
-
-## Available commands
-
-### Top-level CLI commands
-
-- `prompt <text...>` — run one prompt non-interactively
-- `--resume <session-id-or-path> [/commands...]` — inspect or maintain a saved session stored under `~/.claude/sessions/`
-- `dump-manifests` — print extracted upstream manifest counts
-- `bootstrap-plan` — print the current bootstrap skeleton
-- `system-prompt [--cwd PATH] [--date YYYY-MM-DD]` — render the synthesized system prompt
-- `self-update` — update the installed binary from the latest GitHub release when a matching asset is available
-- `--help` / `-h` — show CLI help
-- `--version` / `-V` — print the CLI version and build info locally (no API call)
-- `--output-format text|json` — choose non-interactive prompt output rendering
-- `--allowedTools <tool[,tool...]>` — restrict enabled tools for interactive sessions and prompt-mode tool use
-
-### Interactive slash commands
-
-- `/help` — show command help
-- `/status` — show current session status
-- `/compact` — compact local session history
-- `/model [model]` — inspect or switch the active model
-- `/permissions [read-only|workspace-write|danger-full-access]` — inspect or switch permissions
-- `/clear [--confirm]` — clear the current local session
-- `/cost` — show token usage totals
-- `/resume <session-id-or-path>` — load a saved session into the REPL
-- `/config [env|hooks|model]` — inspect discovered Claude config
-- `/memory` — inspect loaded instruction memory files
-- `/init` — bootstrap `.claude.json`, `.claude/`, `CLAUDE.md`, and local ignore rules
-- `/diff` — show the current git diff for the workspace
-- `/version` — print version and build metadata locally
-- `/export [file]` — export the current conversation transcript
-- `/sessions` — list recent managed local sessions from `~/.claude/sessions/`
-- `/session [list|switch <session-id>]` — inspect or switch managed local sessions
-- `/exit` — leave the REPL
-
-## Environment variables
-
-### Anthropic/API
-
-- `ANTHROPIC_API_KEY` — highest-precedence API credential
-- `ANTHROPIC_AUTH_TOKEN` — bearer-token override used when no API key is set
-- Persisted OAuth credentials in `~/.claude/credentials.json` — used when neither env var is set
-- `ANTHROPIC_BASE_URL` — override the Anthropic API base URL
-- `ANTHROPIC_MODEL` — default model used by selected live integration tests
-
-### CLI/runtime
-
-- `RUSTY_CLAUDE_PERMISSION_MODE` — default REPL permission mode (`read-only`, `workspace-write`, or `danger-full-access`)
-- `CLAUDE_CONFIG_HOME` — override Claude config discovery root
-- `CLAUDE_CODE_REMOTE` — enable remote-session bootstrap handling when supported
-- `CLAUDE_CODE_REMOTE_SESSION_ID` — remote session identifier when using remote mode
-- `CLAUDE_CODE_UPSTREAM` — override the upstream TS source path for compat-harness extraction
-- `CLAWD_WEB_SEARCH_BASE_URL` — override the built-in web search service endpoint used by tooling
-
-## Notes
-
-- `compat-harness` exists to compare the Rust port against the upstream TypeScript codebase and is intentionally excluded from the requested release test run.
-- The CLI currently focuses on a practical integrated workflow: prompt execution, REPL operation, session inspection/resume, config discovery, and tool/runtime plumbing.

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/api/src/lib.rs

@@ -4,8 +4,8 @@ mod sse;
 mod types;
 
 pub use client::{
-    oauth_token_is_expired, read_base_url, resolve_saved_oauth_token,
+    oauth_token_is_expired, read_base_url, resolve_saved_oauth_token, resolve_startup_auth_source,
-    resolve_startup_auth_source, AnthropicClient, AuthSource, MessageStream, OAuthTokenSet,
+    AnthropicClient, AuthSource, MessageStream, OAuthTokenSet,
 };
 pub use error::ApiError;
 pub use sse::{parse_frame, SseParser};

rust/crates/commands/src/lib.rs

@@ -117,6 +117,48 @@ const SLASH_COMMAND_SPECS: &[SlashCommandSpec] = &[
         argument_hint: None,
         resume_supported: true,
     },
+    SlashCommandSpec {
+        name: "bughunter",
+        summary: "Inspect the codebase for likely bugs",
+        argument_hint: Some("[scope]"),
+        resume_supported: false,
+    },
+    SlashCommandSpec {
+        name: "commit",
+        summary: "Generate a commit message and create a git commit",
+        argument_hint: None,
+        resume_supported: false,
+    },
+    SlashCommandSpec {
+        name: "pr",
+        summary: "Draft or create a pull request from the conversation",
+        argument_hint: Some("[context]"),
+        resume_supported: false,
+    },
+    SlashCommandSpec {
+        name: "issue",
+        summary: "Draft or create a GitHub issue from the conversation",
+        argument_hint: Some("[context]"),
+        resume_supported: false,
+    },
+    SlashCommandSpec {
+        name: "ultraplan",
+        summary: "Run a deep planning prompt with multi-step reasoning",
+        argument_hint: Some("[task]"),
+        resume_supported: false,
+    },
+    SlashCommandSpec {
+        name: "teleport",
+        summary: "Jump to a file or symbol by searching the workspace",
+        argument_hint: Some("<symbol-or-path>"),
+        resume_supported: false,
+    },
+    SlashCommandSpec {
+        name: "debug-tool-call",
+        summary: "Replay the last tool call with debug details",
+        argument_hint: None,
+        resume_supported: false,
+    },
     SlashCommandSpec {
         name: "export",
         summary: "Export the current conversation to a file",
@@ -136,6 +178,23 @@ pub enum SlashCommand {
     Help,
     Status,
     Compact,
+    Bughunter {
+        scope: Option<String>,
+    },
+    Commit,
+    Pr {
+        context: Option<String>,
+    },
+    Issue {
+        context: Option<String>,
+    },
+    Ultraplan {
+        task: Option<String>,
+    },
+    Teleport {
+        target: Option<String>,
+    },
+    DebugToolCall,
     Model {
         model: Option<String>,
     },
@@ -180,6 +239,23 @@ impl SlashCommand {
             "help" => Self::Help,
             "status" => Self::Status,
             "compact" => Self::Compact,
+            "bughunter" => Self::Bughunter {
+                scope: remainder_after_command(trimmed, command),
+            },
+            "commit" => Self::Commit,
+            "pr" => Self::Pr {
+                context: remainder_after_command(trimmed, command),
+            },
+            "issue" => Self::Issue {
+                context: remainder_after_command(trimmed, command),
+            },
+            "ultraplan" => Self::Ultraplan {
+                task: remainder_after_command(trimmed, command),
+            },
+            "teleport" => Self::Teleport {
+                target: remainder_after_command(trimmed, command),
+            },
+            "debug-tool-call" => Self::DebugToolCall,
             "model" => Self::Model {
                 model: parts.next().map(ToOwned::to_owned),
             },
@@ -212,6 +288,15 @@ impl SlashCommand {
     }
 }
 
+fn remainder_after_command(input: &str, command: &str) -> Option<String> {
+    input
+        .trim()
+        .strip_prefix(&format!("/{command}"))
+        .map(str::trim)
+        .filter(|value| !value.is_empty())
+        .map(ToOwned::to_owned)
+}
+
 #[must_use]
 pub fn slash_command_specs() -> &'static [SlashCommandSpec] {
     SLASH_COMMAND_SPECS
@@ -279,6 +364,13 @@ pub fn handle_slash_command(
             session: session.clone(),
         }),
         SlashCommand::Status
+        | SlashCommand::Bughunter { .. }
+        | SlashCommand::Commit
+        | SlashCommand::Pr { .. }
+        | SlashCommand::Issue { .. }
+        | SlashCommand::Ultraplan { .. }
+        | SlashCommand::Teleport { .. }
+        | SlashCommand::DebugToolCall
         | SlashCommand::Model { .. }
         | SlashCommand::Permissions { .. }
         | SlashCommand::Clear { .. }
@@ -307,6 +399,41 @@ mod tests {
     fn parses_supported_slash_commands() {
         assert_eq!(SlashCommand::parse("/help"), Some(SlashCommand::Help));
         assert_eq!(SlashCommand::parse(" /status "), Some(SlashCommand::Status));
+        assert_eq!(
+            SlashCommand::parse("/bughunter runtime"),
+            Some(SlashCommand::Bughunter {
+                scope: Some("runtime".to_string())
+            })
+        );
+        assert_eq!(SlashCommand::parse("/commit"), Some(SlashCommand::Commit));
+        assert_eq!(
+            SlashCommand::parse("/pr ready for review"),
+            Some(SlashCommand::Pr {
+                context: Some("ready for review".to_string())
+            })
+        );
+        assert_eq!(
+            SlashCommand::parse("/issue flaky test"),
+            Some(SlashCommand::Issue {
+                context: Some("flaky test".to_string())
+            })
+        );
+        assert_eq!(
+            SlashCommand::parse("/ultraplan ship both features"),
+            Some(SlashCommand::Ultraplan {
+                task: Some("ship both features".to_string())
+            })
+        );
+        assert_eq!(
+            SlashCommand::parse("/teleport conversation.rs"),
+            Some(SlashCommand::Teleport {
+                target: Some("conversation.rs".to_string())
+            })
+        );
+        assert_eq!(
+            SlashCommand::parse("/debug-tool-call"),
+            Some(SlashCommand::DebugToolCall)
+        );
         assert_eq!(
             SlashCommand::parse("/model claude-opus"),
             Some(SlashCommand::Model {
@@ -374,6 +501,13 @@ mod tests {
         assert!(help.contains("/help"));
         assert!(help.contains("/status"));
         assert!(help.contains("/compact"));
+        assert!(help.contains("/bughunter [scope]"));
+        assert!(help.contains("/commit"));
+        assert!(help.contains("/pr [context]"));
+        assert!(help.contains("/issue [context]"));
+        assert!(help.contains("/ultraplan [task]"));
+        assert!(help.contains("/teleport <symbol-or-path>"));
+        assert!(help.contains("/debug-tool-call"));
         assert!(help.contains("/model [model]"));
         assert!(help.contains("/permissions [read-only|workspace-write|danger-full-access]"));
         assert!(help.contains("/clear [--confirm]"));
@@ -386,7 +520,7 @@ mod tests {
         assert!(help.contains("/version"));
         assert!(help.contains("/export [file]"));
         assert!(help.contains("/session [list|switch <session-id>]"));
-        assert_eq!(slash_command_specs().len(), 15);
+        assert_eq!(slash_command_specs().len(), 22);
         assert_eq!(resume_supported_slash_commands().len(), 11);
     }
 
@@ -434,6 +568,22 @@ mod tests {
         let session = Session::new();
         assert!(handle_slash_command("/unknown", &session, CompactionConfig::default()).is_none());
         assert!(handle_slash_command("/status", &session, CompactionConfig::default()).is_none());
+        assert!(
+            handle_slash_command("/bughunter", &session, CompactionConfig::default()).is_none()
+        );
+        assert!(handle_slash_command("/commit", &session, CompactionConfig::default()).is_none());
+        assert!(handle_slash_command("/pr", &session, CompactionConfig::default()).is_none());
+        assert!(handle_slash_command("/issue", &session, CompactionConfig::default()).is_none());
+        assert!(
+            handle_slash_command("/ultraplan", &session, CompactionConfig::default()).is_none()
+        );
+        assert!(
+            handle_slash_command("/teleport foo", &session, CompactionConfig::default()).is_none()
+        );
+        assert!(
+            handle_slash_command("/debug-tool-call", &session, CompactionConfig::default())
+                .is_none()
+        );
         assert!(
             handle_slash_command("/model claude", &session, CompactionConfig::default()).is_none()
         );

rust/crates/runtime/src/conversation.rs

@@ -8,6 +8,9 @@ use crate::permissions::{PermissionOutcome, PermissionPolicy, PermissionPrompter
 use crate::session::{ContentBlock, ConversationMessage, Session};
 use crate::usage::{TokenUsage, UsageTracker};
 
+const DEFAULT_AUTO_COMPACTION_INPUT_TOKENS_THRESHOLD: u32 = 100_000;
+const AUTO_COMPACTION_THRESHOLD_ENV_VAR: &str = "CLAUDE_CODE_AUTO_COMPACT_INPUT_TOKENS";
+
 #[derive(Debug, Clone, PartialEq, Eq)]
 pub struct ApiRequest {
     pub system_prompt: Vec<String>,
@@ -84,6 +87,12 @@ pub struct TurnSummary {
     pub tool_results: Vec<ConversationMessage>,
     pub iterations: usize,
     pub usage: TokenUsage,
+    pub auto_compaction: Option<AutoCompactionEvent>,
+}
+
+#[derive(Debug, Clone, Copy, PartialEq, Eq)]
+pub struct AutoCompactionEvent {
+    pub removed_message_count: usize,
 }
 
 pub struct ConversationRuntime<C, T> {
@@ -94,6 +103,7 @@ pub struct ConversationRuntime<C, T> {
     system_prompt: Vec<String>,
     max_iterations: usize,
     usage_tracker: UsageTracker,
+    auto_compaction_input_tokens_threshold: u32,
 }
 
 impl<C, T> ConversationRuntime<C, T>
@@ -118,6 +128,7 @@ where
             system_prompt,
             max_iterations: usize::MAX,
             usage_tracker,
+            auto_compaction_input_tokens_threshold: auto_compaction_threshold_from_env(),
         }
     }
 
@@ -127,6 +138,12 @@ where
         self
     }
 
+    #[must_use]
+    pub fn with_auto_compaction_input_tokens_threshold(mut self, threshold: u32) -> Self {
+        self.auto_compaction_input_tokens_threshold = threshold;
+        self
+    }
+
     pub fn run_turn(
         &mut self,
         user_input: impl Into<String>,
@@ -209,11 +226,14 @@ where
             }
         }
 
+        let auto_compaction = self.maybe_auto_compact();
+
         Ok(TurnSummary {
             assistant_messages,
             tool_results,
             iterations,
             usage: self.usage_tracker.cumulative_usage(),
+            auto_compaction,
         })
     }
 
@@ -241,6 +261,48 @@ where
     pub fn into_session(self) -> Session {
         self.session
     }
+
+    fn maybe_auto_compact(&mut self) -> Option<AutoCompactionEvent> {
+        if self.usage_tracker.cumulative_usage().input_tokens
+            < self.auto_compaction_input_tokens_threshold
+        {
+            return None;
+        }
+
+        let result = compact_session(
+            &self.session,
+            CompactionConfig {
+                max_estimated_tokens: 0,
+                ..CompactionConfig::default()
+            },
+        );
+
+        if result.removed_message_count == 0 {
+            return None;
+        }
+
+        self.session = result.compacted_session;
+        Some(AutoCompactionEvent {
+            removed_message_count: result.removed_message_count,
+        })
+    }
+}
+
+#[must_use]
+pub fn auto_compaction_threshold_from_env() -> u32 {
+    parse_auto_compaction_threshold(
+        std::env::var(AUTO_COMPACTION_THRESHOLD_ENV_VAR)
+            .ok()
+            .as_deref(),
+    )
+}
+
+#[must_use]
+fn parse_auto_compaction_threshold(value: Option<&str>) -> u32 {
+    value
+        .and_then(|raw| raw.trim().parse::<u32>().ok())
+        .filter(|threshold| *threshold > 0)
+        .unwrap_or(DEFAULT_AUTO_COMPACTION_INPUT_TOKENS_THRESHOLD)
 }
 
 fn build_assistant_message(
@@ -325,8 +387,9 @@ impl ToolExecutor for StaticToolExecutor {
 #[cfg(test)]
 mod tests {
     use super::{
-        ApiClient, ApiRequest, AssistantEvent, ConversationRuntime, RuntimeError,
+        parse_auto_compaction_threshold, ApiClient, ApiRequest, AssistantEvent,
-        StaticToolExecutor,
+        AutoCompactionEvent, ConversationRuntime, RuntimeError, StaticToolExecutor,
+        DEFAULT_AUTO_COMPACTION_INPUT_TOKENS_THRESHOLD,
     };
     use crate::compact::CompactionConfig;
     use crate::permissions::{
@@ -436,6 +499,7 @@ mod tests {
         assert_eq!(summary.tool_results.len(), 1);
         assert_eq!(runtime.session().messages.len(), 4);
         assert_eq!(summary.usage.output_tokens, 10);
+        assert_eq!(summary.auto_compaction, None);
         assert!(matches!(
             runtime.session().messages[1].blocks[1],
             ContentBlock::ToolUse { .. }
@@ -581,4 +645,111 @@ mod tests {
             MessageRole::System
         );
     }
+
+    #[test]
+    fn auto_compacts_when_cumulative_input_threshold_is_crossed() {
+        struct SimpleApi;
+        impl ApiClient for SimpleApi {
+            fn stream(
+                &mut self,
+                _request: ApiRequest,
+            ) -> Result<Vec<AssistantEvent>, RuntimeError> {
+                Ok(vec![
+                    AssistantEvent::TextDelta("done".to_string()),
+                    AssistantEvent::Usage(TokenUsage {
+                        input_tokens: 120_000,
+                        output_tokens: 4,
+                        cache_creation_input_tokens: 0,
+                        cache_read_input_tokens: 0,
+                    }),
+                    AssistantEvent::MessageStop,
+                ])
+            }
+        }
+
+        let session = Session {
+            version: 1,
+            messages: vec![
+                crate::session::ConversationMessage::user_text("one"),
+                crate::session::ConversationMessage::assistant(vec![ContentBlock::Text {
+                    text: "two".to_string(),
+                }]),
+                crate::session::ConversationMessage::user_text("three"),
+                crate::session::ConversationMessage::assistant(vec![ContentBlock::Text {
+                    text: "four".to_string(),
+                }]),
+            ],
+        };
+
+        let mut runtime = ConversationRuntime::new(
+            session,
+            SimpleApi,
+            StaticToolExecutor::new(),
+            PermissionPolicy::new(PermissionMode::DangerFullAccess),
+            vec!["system".to_string()],
+        )
+        .with_auto_compaction_input_tokens_threshold(100_000);
+
+        let summary = runtime
+            .run_turn("trigger", None)
+            .expect("turn should succeed");
+
+        assert_eq!(
+            summary.auto_compaction,
+            Some(AutoCompactionEvent {
+                removed_message_count: 2,
+            })
+        );
+        assert_eq!(runtime.session().messages[0].role, MessageRole::System);
+    }
+
+    #[test]
+    fn skips_auto_compaction_below_threshold() {
+        struct SimpleApi;
+        impl ApiClient for SimpleApi {
+            fn stream(
+                &mut self,
+                _request: ApiRequest,
+            ) -> Result<Vec<AssistantEvent>, RuntimeError> {
+                Ok(vec![
+                    AssistantEvent::TextDelta("done".to_string()),
+                    AssistantEvent::Usage(TokenUsage {
+                        input_tokens: 99_999,
+                        output_tokens: 4,
+                        cache_creation_input_tokens: 0,
+                        cache_read_input_tokens: 0,
+                    }),
+                    AssistantEvent::MessageStop,
+                ])
+            }
+        }
+
+        let mut runtime = ConversationRuntime::new(
+            Session::new(),
+            SimpleApi,
+            StaticToolExecutor::new(),
+            PermissionPolicy::new(PermissionMode::DangerFullAccess),
+            vec!["system".to_string()],
+        )
+        .with_auto_compaction_input_tokens_threshold(100_000);
+
+        let summary = runtime
+            .run_turn("trigger", None)
+            .expect("turn should succeed");
+        assert_eq!(summary.auto_compaction, None);
+        assert_eq!(runtime.session().messages.len(), 2);
+    }
+
+    #[test]
+    fn auto_compaction_threshold_defaults_and_parses_values() {
+        assert_eq!(
+            parse_auto_compaction_threshold(None),
+            DEFAULT_AUTO_COMPACTION_INPUT_TOKENS_THRESHOLD
+        );
+        assert_eq!(parse_auto_compaction_threshold(Some("4321")), 4321);
+        assert_eq!(
+            parse_auto_compaction_threshold(Some("not-a-number")),
+            DEFAULT_AUTO_COMPACTION_INPUT_TOKENS_THRESHOLD
+        );
+    }
 }

rust/crates/runtime/src/lib.rs

@@ -30,8 +30,8 @@ pub use config::{
     CLAUDE_CODE_SETTINGS_SCHEMA_NAME,
 };
 pub use conversation::{
-    ApiClient, ApiRequest, AssistantEvent, ConversationRuntime, RuntimeError, StaticToolExecutor,
+    auto_compaction_threshold_from_env, ApiClient, ApiRequest, AssistantEvent, AutoCompactionEvent,
-    ToolError, ToolExecutor, TurnSummary,
+    ConversationRuntime, RuntimeError, StaticToolExecutor, ToolError, ToolExecutor, TurnSummary,
 };
 pub use file_ops::{
     edit_file, glob_search, grep_search, read_file, write_file, EditFileOutput, GlobSearchOutput,

rust/crates/rusty-claude-cli/src/main.rs

@@ -22,12 +22,12 @@ use commands::{
 };
 use compat_harness::{extract_manifest, UpstreamPaths};
 use init::initialize_repo;
-use render::{Spinner, TerminalRenderer};
+use render::{MarkdownStreamState, Spinner, TerminalRenderer};
 use runtime::{
     clear_oauth_credentials, generate_pkce_pair, generate_state, load_system_prompt,
     parse_oauth_callback_request_target, save_oauth_credentials, ApiClient, ApiRequest,
     AssistantEvent, CompactionConfig, ConfigLoader, ConfigSource, ContentBlock,
-    ConversationMessage, ConversationRuntime, MessageRole, OAuthAuthorizationRequest,
+    ConversationMessage, ConversationRuntime, MessageRole, OAuthAuthorizationRequest, OAuthConfig,
     OAuthTokenExchangeRequest, PermissionMode, PermissionPolicy, ProjectContext, RuntimeError,
     Session, TokenUsage, ToolError, ToolExecutor, UsageTracker,
 };
@@ -196,6 +196,25 @@ fn parse_args(args: &[String]) -> Result<CliAction, String> {
                 permission_mode = PermissionMode::DangerFullAccess;
                 index += 1;
             }
+            "-p" => {
+                // Claude Code compat: -p "prompt" = one-shot prompt
+                let prompt = args[index + 1..].join(" ");
+                if prompt.trim().is_empty() {
+                    return Err("-p requires a prompt string".to_string());
+                }
+                return Ok(CliAction::Prompt {
+                    prompt,
+                    model: resolve_model_alias(&model).to_string(),
+                    output_format,
+                    allowed_tools: normalize_allowed_tools(&allowed_tool_values)?,
+                    permission_mode,
+                });
+            }
+            "--print" => {
+                // Claude Code compat: --print makes output non-interactive
+                output_format = CliOutputFormat::Text;
+                index += 1;
+            }
             "--allowedTools" | "--allowed-tools" => {
                 let value = args
                     .get(index + 1)
@@ -428,15 +447,26 @@ fn print_bootstrap_plan() {
     }
 }
 
+fn default_oauth_config() -> OAuthConfig {
+    OAuthConfig {
+        client_id: String::from("9d1c250a-e61b-44d9-88ed-5944d1962f5e"),
+        authorize_url: String::from("https://platform.claude.com/oauth/authorize"),
+        token_url: String::from("https://platform.claude.com/v1/oauth/token"),
+        callback_port: None,
+        manual_redirect_url: None,
+        scopes: vec![
+            String::from("user:profile"),
+            String::from("user:inference"),
+            String::from("user:sessions:claude_code"),
+        ],
+    }
+}
+
 fn run_login() -> Result<(), Box<dyn std::error::Error>> {
     let cwd = env::current_dir()?;
     let config = ConfigLoader::default_for(&cwd).load()?;
-    let oauth = config.oauth().ok_or_else(|| {
+    let default_oauth = default_oauth_config();
-        io::Error::new(
+    let oauth = config.oauth().unwrap_or(&default_oauth);
-            io::ErrorKind::NotFound,
-            "OAuth config is missing. Add settings.oauth.clientId/authorizeUrl/tokenUrl first.",
-        )
-    })?;
     let callback_port = oauth.callback_port.unwrap_or(DEFAULT_OAUTH_CALLBACK_PORT);
     let redirect_uri = runtime::loopback_redirect_uri(callback_port);
     let pkce = generate_pkce_pair()?;
@@ -745,6 +775,10 @@ fn format_compact_report(removed: usize, resulting_messages: usize, skipped: boo
     }
 }
 
+fn format_auto_compaction_notice(removed: usize) -> String {
+    format!("[auto-compacted: removed {removed} messages]")
+}
+
 fn parse_git_status_metadata(status: Option<&str>) -> (Option<PathBuf>, Option<String>) {
     let Some(status) = status else {
         return (None, None);
@@ -883,7 +917,14 @@ fn run_resume_command(
                 )),
             })
         }
-        SlashCommand::Resume { .. }
+        SlashCommand::Bughunter { .. }
+        | SlashCommand::Commit
+        | SlashCommand::Pr { .. }
+        | SlashCommand::Issue { .. }
+        | SlashCommand::Ultraplan { .. }
+        | SlashCommand::Teleport { .. }
+        | SlashCommand::DebugToolCall
+        | SlashCommand::Resume { .. }
         | SlashCommand::Model { .. }
         | SlashCommand::Permissions { .. }
         | SlashCommand::Session { .. }
@@ -1020,13 +1061,19 @@ impl LiveCli {
         let mut permission_prompter = CliPermissionPrompter::new(self.permission_mode);
         let result = self.runtime.run_turn(input, Some(&mut permission_prompter));
         match result {
-            Ok(_) => {
+            Ok(summary) => {
                 spinner.finish(
                     "✨ Done",
                     TerminalRenderer::new().color_theme(),
                     &mut stdout,
                 )?;
                 println!();
+                if let Some(event) = summary.auto_compaction {
+                    println!(
+                        "{}",
+                        format_auto_compaction_notice(event.removed_message_count)
+                    );
+                }
                 self.persist_session()?;
                 Ok(())
             }
@@ -1073,6 +1120,10 @@ impl LiveCli {
                 "message": final_assistant_text(&summary),
                 "model": self.model,
                 "iterations": summary.iterations,
+                "auto_compaction": summary.auto_compaction.map(|event| json!({
+                    "removed_messages": event.removed_message_count,
+                    "notice": format_auto_compaction_notice(event.removed_message_count),
+                })),
                 "tool_uses": collect_tool_uses(&summary),
                 "tool_results": collect_tool_results(&summary),
                 "usage": {
@@ -1099,6 +1150,34 @@ impl LiveCli {
                 self.print_status();
                 false
             }
+            SlashCommand::Bughunter { scope } => {
+                self.run_bughunter(scope.as_deref())?;
+                false
+            }
+            SlashCommand::Commit => {
+                self.run_commit()?;
+                true
+            }
+            SlashCommand::Pr { context } => {
+                self.run_pr(context.as_deref())?;
+                false
+            }
+            SlashCommand::Issue { context } => {
+                self.run_issue(context.as_deref())?;
+                false
+            }
+            SlashCommand::Ultraplan { task } => {
+                self.run_ultraplan(task.as_deref())?;
+                false
+            }
+            SlashCommand::Teleport { target } => {
+                self.run_teleport(target.as_deref())?;
+                false
+            }
+            SlashCommand::DebugToolCall => {
+                self.run_debug_tool_call()?;
+                false
+            }
             SlashCommand::Compact => {
                 self.compact()?;
                 false
@@ -1418,6 +1497,160 @@ impl LiveCli {
         println!("{}", format_compact_report(removed, kept, skipped));
         Ok(())
     }
+
+    fn run_internal_prompt_text(
+        &self,
+        prompt: &str,
+        enable_tools: bool,
+    ) -> Result<String, Box<dyn std::error::Error>> {
+        let session = self.runtime.session().clone();
+        let mut runtime = build_runtime(
+            session,
+            self.model.clone(),
+            self.system_prompt.clone(),
+            enable_tools,
+            false,
+            self.allowed_tools.clone(),
+            self.permission_mode,
+        )?;
+        let mut permission_prompter = CliPermissionPrompter::new(self.permission_mode);
+        let summary = runtime.run_turn(prompt, Some(&mut permission_prompter))?;
+        Ok(final_assistant_text(&summary).trim().to_string())
+    }
+
+    fn run_bughunter(&self, scope: Option<&str>) -> Result<(), Box<dyn std::error::Error>> {
+        let scope = scope.unwrap_or("the current repository");
+        let prompt = format!(
+            "You are /bughunter. Inspect {scope} and identify the most likely bugs or correctness issues. Prioritize concrete findings with file paths, severity, and suggested fixes. Use tools if needed."
+        );
+        println!("{}", self.run_internal_prompt_text(&prompt, true)?);
+        Ok(())
+    }
+
+    fn run_ultraplan(&self, task: Option<&str>) -> Result<(), Box<dyn std::error::Error>> {
+        let task = task.unwrap_or("the current repo work");
+        let prompt = format!(
+            "You are /ultraplan. Produce a deep multi-step execution plan for {task}. Include goals, risks, implementation sequence, verification steps, and rollback considerations. Use tools if needed."
+        );
+        println!("{}", self.run_internal_prompt_text(&prompt, true)?);
+        Ok(())
+    }
+
+    fn run_teleport(&self, target: Option<&str>) -> Result<(), Box<dyn std::error::Error>> {
+        let Some(target) = target.map(str::trim).filter(|value| !value.is_empty()) else {
+            println!("Usage: /teleport <symbol-or-path>");
+            return Ok(());
+        };
+
+        println!("{}", render_teleport_report(target)?);
+        Ok(())
+    }
+
+    fn run_debug_tool_call(&self) -> Result<(), Box<dyn std::error::Error>> {
+        println!("{}", render_last_tool_debug_report(self.runtime.session())?);
+        Ok(())
+    }
+
+    fn run_commit(&mut self) -> Result<(), Box<dyn std::error::Error>> {
+        let status = git_output(&["status", "--short"])?;
+        if status.trim().is_empty() {
+            println!("Commit\n  Result           skipped\n  Reason           no workspace changes");
+            return Ok(());
+        }
+
+        git_status_ok(&["add", "-A"])?;
+        let staged_stat = git_output(&["diff", "--cached", "--stat"])?;
+        let prompt = format!(
+            "Generate a git commit message in plain text Lore format only. Base it on this staged diff summary:\n\n{}\n\nRecent conversation context:\n{}",
+            truncate_for_prompt(&staged_stat, 8_000),
+            recent_user_context(self.runtime.session(), 6)
+        );
+        let message = sanitize_generated_message(&self.run_internal_prompt_text(&prompt, false)?);
+        if message.trim().is_empty() {
+            return Err("generated commit message was empty".into());
+        }
+
+        let path = write_temp_text_file("claw-commit-message.txt", &message)?;
+        let output = Command::new("git")
+            .args(["commit", "--file"])
+            .arg(&path)
+            .current_dir(env::current_dir()?)
+            .output()?;
+        if !output.status.success() {
+            let stderr = String::from_utf8_lossy(&output.stderr).trim().to_string();
+            return Err(format!("git commit failed: {stderr}").into());
+        }
+
+        println!(
+            "Commit\n  Result           created\n  Message file     {}\n\n{}",
+            path.display(),
+            message.trim()
+        );
+        Ok(())
+    }
+
+    fn run_pr(&self, context: Option<&str>) -> Result<(), Box<dyn std::error::Error>> {
+        let staged = git_output(&["diff", "--stat"])?;
+        let prompt = format!(
+            "Generate a pull request title and body from this conversation and diff summary. Output plain text in this format exactly:\nTITLE: <title>\nBODY:\n<body markdown>\n\nContext hint: {}\n\nDiff summary:\n{}",
+            context.unwrap_or("none"),
+            truncate_for_prompt(&staged, 10_000)
+        );
+        let draft = sanitize_generated_message(&self.run_internal_prompt_text(&prompt, false)?);
+        let (title, body) = parse_titled_body(&draft)
+            .ok_or_else(|| "failed to parse generated PR title/body".to_string())?;
+
+        if command_exists("gh") {
+            let body_path = write_temp_text_file("claw-pr-body.md", &body)?;
+            let output = Command::new("gh")
+                .args(["pr", "create", "--title", &title, "--body-file"])
+                .arg(&body_path)
+                .current_dir(env::current_dir()?)
+                .output()?;
+            if output.status.success() {
+                let stdout = String::from_utf8_lossy(&output.stdout).trim().to_string();
+                println!(
+                    "PR\n  Result           created\n  Title            {title}\n  URL              {}",
+                    if stdout.is_empty() { "<unknown>" } else { &stdout }
+                );
+                return Ok(());
+            }
+        }
+
+        println!("PR draft\n  Title            {title}\n\n{body}");
+        Ok(())
+    }
+
+    fn run_issue(&self, context: Option<&str>) -> Result<(), Box<dyn std::error::Error>> {
+        let prompt = format!(
+            "Generate a GitHub issue title and body from this conversation. Output plain text in this format exactly:\nTITLE: <title>\nBODY:\n<body markdown>\n\nContext hint: {}\n\nConversation context:\n{}",
+            context.unwrap_or("none"),
+            truncate_for_prompt(&recent_user_context(self.runtime.session(), 10), 10_000)
+        );
+        let draft = sanitize_generated_message(&self.run_internal_prompt_text(&prompt, false)?);
+        let (title, body) = parse_titled_body(&draft)
+            .ok_or_else(|| "failed to parse generated issue title/body".to_string())?;
+
+        if command_exists("gh") {
+            let body_path = write_temp_text_file("claw-issue-body.md", &body)?;
+            let output = Command::new("gh")
+                .args(["issue", "create", "--title", &title, "--body-file"])
+                .arg(&body_path)
+                .current_dir(env::current_dir()?)
+                .output()?;
+            if output.status.success() {
+                let stdout = String::from_utf8_lossy(&output.stdout).trim().to_string();
+                println!(
+                    "Issue\n  Result           created\n  Title            {title}\n  URL              {}",
+                    if stdout.is_empty() { "<unknown>" } else { &stdout }
+                );
+                return Ok(());
+            }
+        }
+
+        println!("Issue draft\n  Title            {title}\n\n{body}");
+        Ok(())
+    }
 }
 
 fn sessions_dir() -> Result<PathBuf, Box<dyn std::error::Error>> {
@@ -1769,6 +2002,206 @@ fn render_diff_report() -> Result<String, Box<dyn std::error::Error>> {
     Ok(format!("Diff\n\n{}", diff.trim_end()))
 }
 
+fn render_teleport_report(target: &str) -> Result<String, Box<dyn std::error::Error>> {
+    let cwd = env::current_dir()?;
+
+    let file_list = Command::new("rg")
+        .args(["--files"])
+        .current_dir(&cwd)
+        .output()?;
+    let file_matches = if file_list.status.success() {
+        String::from_utf8(file_list.stdout)?
+            .lines()
+            .filter(|line| line.contains(target))
+            .take(10)
+            .map(ToOwned::to_owned)
+            .collect::<Vec<_>>()
+    } else {
+        Vec::new()
+    };
+
+    let content_output = Command::new("rg")
+        .args(["-n", "-S", "--color", "never", target, "."])
+        .current_dir(&cwd)
+        .output()?;
+
+    let mut lines = vec![format!("Teleport\n  Target           {target}")];
+    if !file_matches.is_empty() {
+        lines.push(String::new());
+        lines.push("File matches".to_string());
+        lines.extend(file_matches.into_iter().map(|path| format!("  {path}")));
+    }
+
+    if content_output.status.success() {
+        let matches = String::from_utf8(content_output.stdout)?;
+        if !matches.trim().is_empty() {
+            lines.push(String::new());
+            lines.push("Content matches".to_string());
+            lines.push(truncate_for_prompt(&matches, 4_000));
+        }
+    }
+
+    if lines.len() == 1 {
+        lines.push("  Result           no matches found".to_string());
+    }
+
+    Ok(lines.join("\n"))
+}
+
+fn render_last_tool_debug_report(session: &Session) -> Result<String, Box<dyn std::error::Error>> {
+    let last_tool_use = session
+        .messages
+        .iter()
+        .rev()
+        .find_map(|message| {
+            message.blocks.iter().rev().find_map(|block| match block {
+                ContentBlock::ToolUse { id, name, input } => {
+                    Some((id.clone(), name.clone(), input.clone()))
+                }
+                _ => None,
+            })
+        })
+        .ok_or_else(|| "no prior tool call found in session".to_string())?;
+
+    let tool_result = session.messages.iter().rev().find_map(|message| {
+        message.blocks.iter().rev().find_map(|block| match block {
+            ContentBlock::ToolResult {
+                tool_use_id,
+                tool_name,
+                output,
+                is_error,
+            } if tool_use_id == &last_tool_use.0 => {
+                Some((tool_name.clone(), output.clone(), *is_error))
+            }
+            _ => None,
+        })
+    });
+
+    let mut lines = vec![
+        "Debug tool call".to_string(),
+        format!("  Tool id          {}", last_tool_use.0),
+        format!("  Tool name        {}", last_tool_use.1),
+        "  Input".to_string(),
+        indent_block(&last_tool_use.2, 4),
+    ];
+
+    match tool_result {
+        Some((tool_name, output, is_error)) => {
+            lines.push("  Result".to_string());
+            lines.push(format!("    name           {tool_name}"));
+            lines.push(format!(
+                "    status         {}",
+                if is_error { "error" } else { "ok" }
+            ));
+            lines.push(indent_block(&output, 4));
+        }
+        None => lines.push("  Result           missing tool result".to_string()),
+    }
+
+    Ok(lines.join("\n"))
+}
+
+fn indent_block(value: &str, spaces: usize) -> String {
+    let indent = " ".repeat(spaces);
+    value
+        .lines()
+        .map(|line| format!("{indent}{line}"))
+        .collect::<Vec<_>>()
+        .join("\n")
+}
+
+fn git_output(args: &[&str]) -> Result<String, Box<dyn std::error::Error>> {
+    let output = Command::new("git")
+        .args(args)
+        .current_dir(env::current_dir()?)
+        .output()?;
+    if !output.status.success() {
+        let stderr = String::from_utf8_lossy(&output.stderr).trim().to_string();
+        return Err(format!("git {} failed: {stderr}", args.join(" ")).into());
+    }
+    Ok(String::from_utf8(output.stdout)?)
+}
+
+fn git_status_ok(args: &[&str]) -> Result<(), Box<dyn std::error::Error>> {
+    let output = Command::new("git")
+        .args(args)
+        .current_dir(env::current_dir()?)
+        .output()?;
+    if !output.status.success() {
+        let stderr = String::from_utf8_lossy(&output.stderr).trim().to_string();
+        return Err(format!("git {} failed: {stderr}", args.join(" ")).into());
+    }
+    Ok(())
+}
+
+fn command_exists(name: &str) -> bool {
+    Command::new("which")
+        .arg(name)
+        .output()
+        .map(|output| output.status.success())
+        .unwrap_or(false)
+}
+
+fn write_temp_text_file(
+    filename: &str,
+    contents: &str,
+) -> Result<PathBuf, Box<dyn std::error::Error>> {
+    let path = env::temp_dir().join(filename);
+    fs::write(&path, contents)?;
+    Ok(path)
+}
+
+fn recent_user_context(session: &Session, limit: usize) -> String {
+    let requests = session
+        .messages
+        .iter()
+        .filter(|message| message.role == MessageRole::User)
+        .filter_map(|message| {
+            message.blocks.iter().find_map(|block| match block {
+                ContentBlock::Text { text } => Some(text.trim().to_string()),
+                _ => None,
+            })
+        })
+        .rev()
+        .take(limit)
+        .collect::<Vec<_>>();
+
+    if requests.is_empty() {
+        "<no prior user messages>".to_string()
+    } else {
+        requests
+            .into_iter()
+            .rev()
+            .enumerate()
+            .map(|(index, text)| format!("{}. {}", index + 1, text))
+            .collect::<Vec<_>>()
+            .join("\n")
+    }
+}
+
+fn truncate_for_prompt(value: &str, limit: usize) -> String {
+    if value.chars().count() <= limit {
+        value.trim().to_string()
+    } else {
+        let truncated = value.chars().take(limit).collect::<String>();
+        format!("{}\n…[truncated]", truncated.trim_end())
+    }
+}
+
+fn sanitize_generated_message(value: &str) -> String {
+    value.trim().trim_matches('`').trim().replace("\r\n", "\n")
+}
+
+fn parse_titled_body(value: &str) -> Option<(String, String)> {
+    let normalized = sanitize_generated_message(value);
+    let title = normalized
+        .lines()
+        .find_map(|line| line.strip_prefix("TITLE:").map(str::trim))?;
+    let body_start = normalized.find("BODY:")?;
+    let body = normalized[body_start + "BODY:".len()..].trim();
+    Some((title.to_string(), body.to_string()))
+}
+
 fn render_version_report() -> String {
     let git_sha = GIT_SHA.unwrap_or("unknown");
     let target = BUILD_TARGET.unwrap_or("unknown");
@@ -2011,6 +2444,8 @@ impl ApiClient for AnthropicRuntimeClient {
             } else {
                 &mut sink
             };
+            let renderer = TerminalRenderer::new();
+            let mut markdown_stream = MarkdownStreamState::default();
             let mut events = Vec::new();
             let mut pending_tool: Option<(String, String, String)> = None;
             let mut saw_stop = false;
@@ -2038,9 +2473,11 @@ impl ApiClient for AnthropicRuntimeClient {
                     ApiStreamEvent::ContentBlockDelta(delta) => match delta.delta {
                         ContentBlockDelta::TextDelta { text } => {
                             if !text.is_empty() {
-                                write!(out, "{text}")
+                                if let Some(rendered) = markdown_stream.push(&renderer, &text) {
-                                    .and_then(|()| out.flush())
+                                    write!(out, "{rendered}")
-                                    .map_err(|error| RuntimeError::new(error.to_string()))?;
+                                        .and_then(|()| out.flush())
+                                        .map_err(|error| RuntimeError::new(error.to_string()))?;
+                                }
                                 events.push(AssistantEvent::TextDelta(text));
                             }
                         }
@@ -2051,6 +2488,11 @@ impl ApiClient for AnthropicRuntimeClient {
                         }
                     },
                     ApiStreamEvent::ContentBlockStop(_) => {
+                        if let Some(rendered) = markdown_stream.flush(&renderer) {
+                            write!(out, "{rendered}")
+                                .and_then(|()| out.flush())
+                                .map_err(|error| RuntimeError::new(error.to_string()))?;
+                        }
                         if let Some((id, name, input)) = pending_tool.take() {
                             // Display tool call now that input is fully accumulated
                             writeln!(out, "\n{}", format_tool_call_start(&name, &input))
@@ -2069,6 +2511,11 @@ impl ApiClient for AnthropicRuntimeClient {
                     }
                     ApiStreamEvent::MessageStop(_) => {
                         saw_stop = true;
+                        if let Some(rendered) = markdown_stream.flush(&renderer) {
+                            write!(out, "{rendered}")
+                                .and_then(|()| out.flush())
+                                .map_err(|error| RuntimeError::new(error.to_string()))?;
+                        }
                         events.push(AssistantEvent::MessageStop);
                     }
                 }
@@ -2171,56 +2618,49 @@ fn format_tool_call_start(name: &str, input: &str) -> String {
         serde_json::from_str(input).unwrap_or(serde_json::Value::String(input.to_string()));
 
     let detail = match name {
-        "bash" | "Bash" => parsed
+        "bash" | "Bash" => format_bash_call(&parsed),
-            .get("command")
+        "read_file" | "Read" => {
-            .and_then(|v| v.as_str())
+            let path = extract_tool_path(&parsed);
-            .map(|cmd| truncate_for_summary(cmd, 120))
+            format!("\x1b[2m📄 Reading {path}…\x1b[0m")
-            .unwrap_or_default(),
+        }
-        "read_file" | "Read" => parsed
-            .get("file_path")
-            .or_else(|| parsed.get("path"))
-            .and_then(|v| v.as_str())
-            .unwrap_or("?")
-            .to_string(),
         "write_file" | "Write" => {
-            let path = parsed
+            let path = extract_tool_path(&parsed);
-                .get("file_path")
-                .or_else(|| parsed.get("path"))
-                .and_then(|v| v.as_str())
-                .unwrap_or("?");
             let lines = parsed
                 .get("content")
-                .and_then(|v| v.as_str())
+                .and_then(|value| value.as_str())
-                .map_or(0, |c| c.lines().count());
+                .map_or(0, |content| content.lines().count());
-            format!("{path} ({lines} lines)")
+            format!("\x1b[1;32m✏️ Writing {path}\x1b[0m \x1b[2m({lines} lines)\x1b[0m")
         }
         "edit_file" | "Edit" => {
-            let path = parsed
+            let path = extract_tool_path(&parsed);
-                .get("file_path")
+            let old_value = parsed
-                .or_else(|| parsed.get("path"))
+                .get("old_string")
-                .and_then(|v| v.as_str())
+                .or_else(|| parsed.get("oldString"))
-                .unwrap_or("?");
+                .and_then(|value| value.as_str())
-            path.to_string()
+                .unwrap_or_default();
+            let new_value = parsed
+                .get("new_string")
+                .or_else(|| parsed.get("newString"))
+                .and_then(|value| value.as_str())
+                .unwrap_or_default();
+            format!(
+                "\x1b[1;33m📝 Editing {path}\x1b[0m{}",
+                format_patch_preview(old_value, new_value)
+                    .map(|preview| format!("\n{preview}"))
+                    .unwrap_or_default()
+            )
         }
-        "glob_search" | "Glob" => parsed
+        "glob_search" | "Glob" => format_search_start("🔎 Glob", &parsed),
-            .get("pattern")
+        "grep_search" | "Grep" => format_search_start("🔎 Grep", &parsed),
-            .and_then(|v| v.as_str())
-            .unwrap_or("?")
-            .to_string(),
-        "grep_search" | "Grep" => parsed
-            .get("pattern")
-            .and_then(|v| v.as_str())
-            .unwrap_or("?")
-            .to_string(),
         "web_search" | "WebSearch" => parsed
             .get("query")
-            .and_then(|v| v.as_str())
+            .and_then(|value| value.as_str())
             .unwrap_or("?")
             .to_string(),
         _ => summarize_tool_payload(input),
     };
 
-    let border = "─".repeat(name.len() + 6);
+    let border = "─".repeat(name.len() + 8);
     format!(
         "\x1b[38;5;245m╭─ \x1b[1;36m{name}\x1b[0;38;5;245m ─╮\x1b[0m\n\x1b[38;5;245m│\x1b[0m {detail}\n\x1b[38;5;245m╰{border}╯\x1b[0m"
     )
@@ -2232,8 +2672,269 @@ fn format_tool_result(name: &str, output: &str, is_error: bool) -> String {
     } else {
         "\x1b[1;32m✓\x1b[0m"
     };
-    let summary = truncate_for_summary(output.trim(), 200);
+    if is_error {
-    format!("{icon} \x1b[38;5;245m{name}:\x1b[0m {summary}")
+        let summary = truncate_for_summary(output.trim(), 160);
+        return if summary.is_empty() {
+            format!("{icon} \x1b[38;5;245m{name}\x1b[0m")
+        } else {
+            format!("{icon} \x1b[38;5;245m{name}\x1b[0m\n\x1b[38;5;203m{summary}\x1b[0m")
+        };
+    }
+
+    let parsed: serde_json::Value =
+        serde_json::from_str(output).unwrap_or(serde_json::Value::String(output.to_string()));
+    match name {
+        "bash" | "Bash" => format_bash_result(icon, &parsed),
+        "read_file" | "Read" => format_read_result(icon, &parsed),
+        "write_file" | "Write" => format_write_result(icon, &parsed),
+        "edit_file" | "Edit" => format_edit_result(icon, &parsed),
+        "glob_search" | "Glob" => format_glob_result(icon, &parsed),
+        "grep_search" | "Grep" => format_grep_result(icon, &parsed),
+        _ => {
+            let summary = truncate_for_summary(output.trim(), 200);
+            format!("{icon} \x1b[38;5;245m{name}:\x1b[0m {summary}")
+        }
+    }
+}
+
+fn extract_tool_path(parsed: &serde_json::Value) -> String {
+    parsed
+        .get("file_path")
+        .or_else(|| parsed.get("filePath"))
+        .or_else(|| parsed.get("path"))
+        .and_then(|value| value.as_str())
+        .unwrap_or("?")
+        .to_string()
+}
+
+fn format_search_start(label: &str, parsed: &serde_json::Value) -> String {
+    let pattern = parsed
+        .get("pattern")
+        .and_then(|value| value.as_str())
+        .unwrap_or("?");
+    let scope = parsed
+        .get("path")
+        .and_then(|value| value.as_str())
+        .unwrap_or(".");
+    format!("{label} {pattern}\n\x1b[2min {scope}\x1b[0m")
+}
+
+fn format_patch_preview(old_value: &str, new_value: &str) -> Option<String> {
+    if old_value.is_empty() && new_value.is_empty() {
+        return None;
+    }
+    Some(format!(
+        "\x1b[38;5;203m- {}\x1b[0m\n\x1b[38;5;70m+ {}\x1b[0m",
+        truncate_for_summary(first_visible_line(old_value), 72),
+        truncate_for_summary(first_visible_line(new_value), 72)
+    ))
+}
+
+fn format_bash_call(parsed: &serde_json::Value) -> String {
+    let command = parsed
+        .get("command")
+        .and_then(|value| value.as_str())
+        .unwrap_or_default();
+    if command.is_empty() {
+        String::new()
+    } else {
+        format!(
+            "\x1b[48;5;236;38;5;255m $ {} \x1b[0m",
+            truncate_for_summary(command, 160)
+        )
+    }
+}
+
+fn first_visible_line(text: &str) -> &str {
+    text.lines()
+        .find(|line| !line.trim().is_empty())
+        .unwrap_or(text)
+}
+
+fn format_bash_result(icon: &str, parsed: &serde_json::Value) -> String {
+    let mut lines = vec![format!("{icon} \x1b[38;5;245mbash\x1b[0m")];
+    if let Some(task_id) = parsed
+        .get("backgroundTaskId")
+        .and_then(|value| value.as_str())
+    {
+        lines[0].push_str(&format!(" backgrounded ({task_id})"));
+    } else if let Some(status) = parsed
+        .get("returnCodeInterpretation")
+        .and_then(|value| value.as_str())
+        .filter(|status| !status.is_empty())
+    {
+        lines[0].push_str(&format!(" {status}"));
+    }
+
+    if let Some(stdout) = parsed.get("stdout").and_then(|value| value.as_str()) {
+        if !stdout.trim().is_empty() {
+            lines.push(stdout.trim_end().to_string());
+        }
+    }
+    if let Some(stderr) = parsed.get("stderr").and_then(|value| value.as_str()) {
+        if !stderr.trim().is_empty() {
+            lines.push(format!("\x1b[38;5;203m{}\x1b[0m", stderr.trim_end()));
+        }
+    }
+
+    lines.join("\n\n")
+}
+
+fn format_read_result(icon: &str, parsed: &serde_json::Value) -> String {
+    let file = parsed.get("file").unwrap_or(parsed);
+    let path = extract_tool_path(file);
+    let start_line = file
+        .get("startLine")
+        .and_then(|value| value.as_u64())
+        .unwrap_or(1);
+    let num_lines = file
+        .get("numLines")
+        .and_then(|value| value.as_u64())
+        .unwrap_or(0);
+    let total_lines = file
+        .get("totalLines")
+        .and_then(|value| value.as_u64())
+        .unwrap_or(num_lines);
+    let content = file
+        .get("content")
+        .and_then(|value| value.as_str())
+        .unwrap_or_default();
+    let end_line = start_line.saturating_add(num_lines.saturating_sub(1));
+
+    format!(
+        "{icon} \x1b[2m📄 Read {path} (lines {}-{} of {})\x1b[0m\n{}",
+        start_line,
+        end_line.max(start_line),
+        total_lines,
+        content
+    )
+}
+
+fn format_write_result(icon: &str, parsed: &serde_json::Value) -> String {
+    let path = extract_tool_path(parsed);
+    let kind = parsed
+        .get("type")
+        .and_then(|value| value.as_str())
+        .unwrap_or("write");
+    let line_count = parsed
+        .get("content")
+        .and_then(|value| value.as_str())
+        .map(|content| content.lines().count())
+        .unwrap_or(0);
+    format!(
+        "{icon} \x1b[1;32m✏️ {} {path}\x1b[0m \x1b[2m({line_count} lines)\x1b[0m",
+        if kind == "create" { "Wrote" } else { "Updated" },
+    )
+}
+
+fn format_structured_patch_preview(parsed: &serde_json::Value) -> Option<String> {
+    let hunks = parsed.get("structuredPatch")?.as_array()?;
+    let mut preview = Vec::new();
+    for hunk in hunks.iter().take(2) {
+        let lines = hunk.get("lines")?.as_array()?;
+        for line in lines.iter().filter_map(|value| value.as_str()).take(6) {
+            match line.chars().next() {
+                Some('+') => preview.push(format!("\x1b[38;5;70m{line}\x1b[0m")),
+                Some('-') => preview.push(format!("\x1b[38;5;203m{line}\x1b[0m")),
+                _ => preview.push(line.to_string()),
+            }
+        }
+    }
+    if preview.is_empty() {
+        None
+    } else {
+        Some(preview.join("\n"))
+    }
+}
+
+fn format_edit_result(icon: &str, parsed: &serde_json::Value) -> String {
+    let path = extract_tool_path(parsed);
+    let suffix = if parsed
+        .get("replaceAll")
+        .and_then(|value| value.as_bool())
+        .unwrap_or(false)
+    {
+        " (replace all)"
+    } else {
+        ""
+    };
+    let preview = format_structured_patch_preview(parsed).or_else(|| {
+        let old_value = parsed
+            .get("oldString")
+            .and_then(|value| value.as_str())
+            .unwrap_or_default();
+        let new_value = parsed
+            .get("newString")
+            .and_then(|value| value.as_str())
+            .unwrap_or_default();
+        format_patch_preview(old_value, new_value)
+    });
+
+    match preview {
+        Some(preview) => format!("{icon} \x1b[1;33m📝 Edited {path}{suffix}\x1b[0m\n{preview}"),
+        None => format!("{icon} \x1b[1;33m📝 Edited {path}{suffix}\x1b[0m"),
+    }
+}
+
+fn format_glob_result(icon: &str, parsed: &serde_json::Value) -> String {
+    let num_files = parsed
+        .get("numFiles")
+        .and_then(|value| value.as_u64())
+        .unwrap_or(0);
+    let filenames = parsed
+        .get("filenames")
+        .and_then(|value| value.as_array())
+        .map(|files| {
+            files
+                .iter()
+                .filter_map(|value| value.as_str())
+                .take(8)
+                .collect::<Vec<_>>()
+                .join("\n")
+        })
+        .unwrap_or_default();
+    if filenames.is_empty() {
+        format!("{icon} \x1b[38;5;245mglob_search\x1b[0m matched {num_files} files")
+    } else {
+        format!("{icon} \x1b[38;5;245mglob_search\x1b[0m matched {num_files} files\n{filenames}")
+    }
+}
+
+fn format_grep_result(icon: &str, parsed: &serde_json::Value) -> String {
+    let num_matches = parsed
+        .get("numMatches")
+        .and_then(|value| value.as_u64())
+        .unwrap_or(0);
+    let num_files = parsed
+        .get("numFiles")
+        .and_then(|value| value.as_u64())
+        .unwrap_or(0);
+    let content = parsed
+        .get("content")
+        .and_then(|value| value.as_str())
+        .unwrap_or_default();
+    let filenames = parsed
+        .get("filenames")
+        .and_then(|value| value.as_array())
+        .map(|files| {
+            files
+                .iter()
+                .filter_map(|value| value.as_str())
+                .take(8)
+                .collect::<Vec<_>>()
+                .join("\n")
+        })
+        .unwrap_or_default();
+    let summary = format!(
+        "{icon} \x1b[38;5;245mgrep_search\x1b[0m {num_matches} matches across {num_files} files"
+    );
+    if !content.trim().is_empty() {
+        format!("{summary}\n{}", content.trim_end())
+    } else if !filenames.is_empty() {
+        format!("{summary}\n{filenames}")
+    } else {
+        summary
+    }
 }
 
 fn summarize_tool_payload(payload: &str) -> String {
@@ -2264,7 +2965,8 @@ fn push_output_block(
     match block {
         OutputContentBlock::Text { text } => {
             if !text.is_empty() {
-                write!(out, "{text}")
+                let rendered = TerminalRenderer::new().markdown_to_ansi(&text);
+                write!(out, "{rendered}")
                     .and_then(|()| out.flush())
                     .map_err(|error| RuntimeError::new(error.to_string()))?;
                 events.push(AssistantEvent::TextDelta(text));
@@ -3056,9 +3758,35 @@ mod tests {
         assert!(start.contains("read_file"));
         assert!(start.contains("src/main.rs"));
 
-        let done = format_tool_result("read_file", r#"{"contents":"hello"}"#, false);
+        let done = format_tool_result(
-        assert!(done.contains("read_file:"));
+            "read_file",
-        assert!(done.contains("contents"));
+            r#"{"file":{"filePath":"src/main.rs","content":"hello","numLines":1,"startLine":1,"totalLines":1}}"#,
+            false,
+        );
+        assert!(done.contains("📄 Read src/main.rs"));
+        assert!(done.contains("hello"));
+    }
+
+    #[test]
+    fn push_output_block_renders_markdown_text() {
+        let mut out = Vec::new();
+        let mut events = Vec::new();
+        let mut pending_tool = None;
+
+        push_output_block(
+            OutputContentBlock::Text {
+                text: "# Heading".to_string(),
+            },
+            &mut out,
+            &mut events,
+            &mut pending_tool,
+            false,
+        )
+        .expect("text block should render");
+
+        let rendered = String::from_utf8(out).expect("utf8");
+        assert!(rendered.contains("Heading"));
+        assert!(rendered.contains('\u{1b}'));
     }
 
     #[test]

rust/crates/rusty-claude-cli/src/render.rs

@@ -1,7 +1,5 @@
 use std::fmt::Write as FmtWrite;
 use std::io::{self, Write};
-use std::thread;
-use std::time::Duration;
 
 use crossterm::cursor::{MoveToColumn, RestorePosition, SavePosition};
 use crossterm::style::{Color, Print, ResetColor, SetForegroundColor, Stylize};
@@ -22,6 +20,7 @@ pub struct ColorTheme {
     link: Color,
     quote: Color,
     table_border: Color,
+    code_block_border: Color,
     spinner_active: Color,
     spinner_done: Color,
     spinner_failed: Color,
@@ -37,6 +36,7 @@ impl Default for ColorTheme {
             link: Color::Blue,
             quote: Color::DarkGrey,
             table_border: Color::DarkCyan,
+            code_block_border: Color::DarkGrey,
             spinner_active: Color::Blue,
             spinner_done: Color::Green,
             spinner_failed: Color::Red,
@@ -154,33 +154,64 @@ impl TableState {
 struct RenderState {
     emphasis: usize,
     strong: usize,
+    heading_level: Option<u8>,
     quote: usize,
     list_stack: Vec<ListKind>,
+    link_stack: Vec<LinkState>,
     table: Option<TableState>,
 }
 
+#[derive(Debug, Clone, PartialEq, Eq)]
+struct LinkState {
+    destination: String,
+    text: String,
+}
+
 impl RenderState {
     fn style_text(&self, text: &str, theme: &ColorTheme) -> String {
-        let mut styled = text.to_string();
+        let mut style = text.stylize();
-        if self.strong > 0 {
+
-            styled = format!("{}", styled.bold().with(theme.strong));
+        if matches!(self.heading_level, Some(1 | 2)) || self.strong > 0 {
+            style = style.bold();
         }
         if self.emphasis > 0 {
-            styled = format!("{}", styled.italic().with(theme.emphasis));
+            style = style.italic();
         }
+
+        if let Some(level) = self.heading_level {
+            style = match level {
+                1 => style.with(theme.heading),
+                2 => style.white(),
+                3 => style.with(Color::Blue),
+                _ => style.with(Color::Grey),
+            };
+        } else if self.strong > 0 {
+            style = style.with(theme.strong);
+        } else if self.emphasis > 0 {
+            style = style.with(theme.emphasis);
+        }
+
         if self.quote > 0 {
-            styled = format!("{}", styled.with(theme.quote));
+            style = style.with(theme.quote);
         }
-        styled
+
+        format!("{style}")
     }
 
-    fn capture_target_mut<'a>(&'a mut self, output: &'a mut String) -> &'a mut String {
+    fn append_raw(&mut self, output: &mut String, text: &str) {
-        if let Some(table) = self.table.as_mut() {
+        if let Some(link) = self.link_stack.last_mut() {
-            &mut table.current_cell
+            link.text.push_str(text);
+        } else if let Some(table) = self.table.as_mut() {
+            table.current_cell.push_str(text);
         } else {
-            output
+            output.push_str(text);
         }
     }
+
+    fn append_styled(&mut self, output: &mut String, text: &str, theme: &ColorTheme) {
+        let styled = self.style_text(text, theme);
+        self.append_raw(output, &styled);
+    }
 }
 
 #[derive(Debug)]
@@ -238,6 +269,11 @@ impl TerminalRenderer {
         output.trim_end().to_string()
     }
 
+    #[must_use]
+    pub fn markdown_to_ansi(&self, markdown: &str) -> String {
+        self.render_markdown(markdown)
+    }
+
     #[allow(clippy::too_many_lines)]
     fn render_event(
         &self,
@@ -249,15 +285,21 @@ impl TerminalRenderer {
         in_code_block: &mut bool,
     ) {
         match event {
-            Event::Start(Tag::Heading { level, .. }) => self.start_heading(level as u8, output),
+            Event::Start(Tag::Heading { level, .. }) => {
-            Event::End(TagEnd::Heading(..) | TagEnd::Paragraph) => output.push_str("\n\n"),
+                self.start_heading(state, level as u8, output)
+            }
+            Event::End(TagEnd::Paragraph) => output.push_str("\n\n"),
             Event::Start(Tag::BlockQuote(..)) => self.start_quote(state, output),
             Event::End(TagEnd::BlockQuote(..)) => {
                 state.quote = state.quote.saturating_sub(1);
                 output.push('\n');
             }
+            Event::End(TagEnd::Heading(..)) => {
+                state.heading_level = None;
+                output.push_str("\n\n");
+            }
             Event::End(TagEnd::Item) | Event::SoftBreak | Event::HardBreak => {
-                state.capture_target_mut(output).push('\n');
+                state.append_raw(output, "\n");
             }
             Event::Start(Tag::List(first_item)) => {
                 let kind = match first_item {
@@ -293,41 +335,52 @@ impl TerminalRenderer {
             Event::Code(code) => {
                 let rendered =
                     format!("{}", format!("`{code}`").with(self.color_theme.inline_code));
-                state.capture_target_mut(output).push_str(&rendered);
+                state.append_raw(output, &rendered);
             }
             Event::Rule => output.push_str("---\n"),
             Event::Text(text) => {
                 self.push_text(text.as_ref(), state, output, code_buffer, *in_code_block);
             }
             Event::Html(html) | Event::InlineHtml(html) => {
-                state.capture_target_mut(output).push_str(&html);
+                state.append_raw(output, &html);
             }
             Event::FootnoteReference(reference) => {
-                let _ = write!(state.capture_target_mut(output), "[{reference}]");
+                state.append_raw(output, &format!("[{reference}]"));
             }
             Event::TaskListMarker(done) => {
-                state
+                state.append_raw(output, if done { "[x] " } else { "[ ] " });
-                    .capture_target_mut(output)
-                    .push_str(if done { "[x] " } else { "[ ] " });
             }
             Event::InlineMath(math) | Event::DisplayMath(math) => {
-                state.capture_target_mut(output).push_str(&math);
+                state.append_raw(output, &math);
             }
             Event::Start(Tag::Link { dest_url, .. }) => {
-                let rendered = format!(
+                state.link_stack.push(LinkState {
-                    "{}",
+                    destination: dest_url.to_string(),
-                    format!("[{dest_url}]")
+                    text: String::new(),
-                        .underlined()
+                });
-                        .with(self.color_theme.link)
+            }
-                );
+            Event::End(TagEnd::Link) => {
-                state.capture_target_mut(output).push_str(&rendered);
+                if let Some(link) = state.link_stack.pop() {
+                    let label = if link.text.is_empty() {
+                        link.destination.clone()
+                    } else {
+                        link.text
+                    };
+                    let rendered = format!(
+                        "{}",
+                        format!("[{label}]({})", link.destination)
+                            .underlined()
+                            .with(self.color_theme.link)
+                    );
+                    state.append_raw(output, &rendered);
+                }
             }
             Event::Start(Tag::Image { dest_url, .. }) => {
                 let rendered = format!(
                     "{}",
                     format!("[image:{dest_url}]").with(self.color_theme.link)
                 );
-                state.capture_target_mut(output).push_str(&rendered);
+                state.append_raw(output, &rendered);
             }
             Event::Start(Tag::Table(..)) => state.table = Some(TableState::default()),
             Event::End(TagEnd::Table) => {
@@ -369,19 +422,15 @@ impl TerminalRenderer {
                 }
             }
             Event::Start(Tag::Paragraph | Tag::MetadataBlock(..) | _)
-            | Event::End(TagEnd::Link | TagEnd::Image | TagEnd::MetadataBlock(..) | _) => {}
+            | Event::End(TagEnd::Image | TagEnd::MetadataBlock(..) | _) => {}
         }
     }
 
-    fn start_heading(&self, level: u8, output: &mut String) {
+    fn start_heading(&self, state: &mut RenderState, level: u8, output: &mut String) {
-        output.push('\n');
+        state.heading_level = Some(level);
-        let prefix = match level {
+        if !output.is_empty() {
-            1 => "# ",
+            output.push('\n');
-            2 => "## ",
+        }
-            3 => "### ",
-            _ => "#### ",
-        };
-        let _ = write!(output, "{}", prefix.bold().with(self.color_theme.heading));
     }
 
     fn start_quote(&self, state: &mut RenderState, output: &mut String) {
@@ -405,20 +454,27 @@ impl TerminalRenderer {
     }
 
     fn start_code_block(&self, code_language: &str, output: &mut String) {
-        if !code_language.is_empty() {
+        let label = if code_language.is_empty() {
-            let _ = writeln!(
+            "code".to_string()
-                output,
+        } else {
-                "{}",
+            code_language.to_string()
-                format!("╭─ {code_language}").with(self.color_theme.heading)
+        };
-            );
+        let _ = writeln!(
-        }
+            output,
+            "{}",
+            format!("╭─ {label}")
+                .bold()
+                .with(self.color_theme.code_block_border)
+        );
     }
 
     fn finish_code_block(&self, code_buffer: &str, code_language: &str, output: &mut String) {
         output.push_str(&self.highlight_code(code_buffer, code_language));
-        if !code_language.is_empty() {
+        let _ = write!(
-            let _ = write!(output, "{}", "╰─".with(self.color_theme.heading));
+            output,
-        }
+            "{}",
+            "╰─".bold().with(self.color_theme.code_block_border)
+        );
         output.push_str("\n\n");
     }
 
@@ -433,8 +489,7 @@ impl TerminalRenderer {
         if in_code_block {
             code_buffer.push_str(text);
         } else {
-            let rendered = state.style_text(text, &self.color_theme);
+            state.append_styled(output, text, &self.color_theme);
-            state.capture_target_mut(output).push_str(&rendered);
         }
     }
 
@@ -521,9 +576,10 @@ impl TerminalRenderer {
         for line in LinesWithEndings::from(code) {
             match syntax_highlighter.highlight_line(line, &self.syntax_set) {
                 Ok(ranges) => {
-                    colored_output.push_str(&as_24_bit_terminal_escaped(&ranges[..], false));
+                    let escaped = as_24_bit_terminal_escaped(&ranges[..], false);
+                    colored_output.push_str(&apply_code_block_background(&escaped));
                 }
-                Err(_) => colored_output.push_str(line),
+                Err(_) => colored_output.push_str(&apply_code_block_background(line)),
             }
         }
 
@@ -531,16 +587,83 @@ impl TerminalRenderer {
     }
 
     pub fn stream_markdown(&self, markdown: &str, out: &mut impl Write) -> io::Result<()> {
-        let rendered_markdown = self.render_markdown(markdown);
+        let rendered_markdown = self.markdown_to_ansi(markdown);
-        for chunk in rendered_markdown.split_inclusive(char::is_whitespace) {
+        write!(out, "{rendered_markdown}")?;
-            write!(out, "{chunk}")?;
+        if !rendered_markdown.ends_with('\n') {
-            out.flush()?;
+            writeln!(out)?;
-            thread::sleep(Duration::from_millis(8));
         }
-        writeln!(out)
+        out.flush()
     }
 }
 
+#[derive(Debug, Default, Clone, PartialEq, Eq)]
+pub struct MarkdownStreamState {
+    pending: String,
+}
+
+impl MarkdownStreamState {
+    #[must_use]
+    pub fn push(&mut self, renderer: &TerminalRenderer, delta: &str) -> Option<String> {
+        self.pending.push_str(delta);
+        let split = find_stream_safe_boundary(&self.pending)?;
+        let ready = self.pending[..split].to_string();
+        self.pending.drain(..split);
+        Some(renderer.markdown_to_ansi(&ready))
+    }
+
+    #[must_use]
+    pub fn flush(&mut self, renderer: &TerminalRenderer) -> Option<String> {
+        if self.pending.trim().is_empty() {
+            self.pending.clear();
+            None
+        } else {
+            let pending = std::mem::take(&mut self.pending);
+            Some(renderer.markdown_to_ansi(&pending))
+        }
+    }
+}
+
+fn apply_code_block_background(line: &str) -> String {
+    let trimmed = line.trim_end_matches('\n');
+    let trailing_newline = if trimmed.len() == line.len() {
+        ""
+    } else {
+        "\n"
+    };
+    let with_background = trimmed.replace("\u{1b}[0m", "\u{1b}[0;48;5;236m");
+    format!("\u{1b}[48;5;236m{with_background}\u{1b}[0m{trailing_newline}")
+}
+
+fn find_stream_safe_boundary(markdown: &str) -> Option<usize> {
+    let mut in_fence = false;
+    let mut last_boundary = None;
+
+    for (offset, line) in markdown.split_inclusive('\n').scan(0usize, |cursor, line| {
+        let start = *cursor;
+        *cursor += line.len();
+        Some((start, line))
+    }) {
+        let trimmed = line.trim_start();
+        if trimmed.starts_with("```") || trimmed.starts_with("~~~") {
+            in_fence = !in_fence;
+            if !in_fence {
+                last_boundary = Some(offset + line.len());
+            }
+            continue;
+        }
+
+        if in_fence {
+            continue;
+        }
+
+        if trimmed.is_empty() {
+            last_boundary = Some(offset + line.len());
+        }
+    }
+
+    last_boundary
+}
+
 fn visible_width(input: &str) -> usize {
     strip_ansi(input).chars().count()
 }
@@ -569,7 +692,7 @@ fn strip_ansi(input: &str) -> String {
 
 #[cfg(test)]
 mod tests {
-    use super::{strip_ansi, Spinner, TerminalRenderer};
+    use super::{strip_ansi, MarkdownStreamState, Spinner, TerminalRenderer};
 
     #[test]
     fn renders_markdown_with_styling_and_lists() {
@@ -583,16 +706,28 @@ mod tests {
         assert!(markdown_output.contains('\u{1b}'));
     }
 
+    #[test]
+    fn renders_links_as_colored_markdown_labels() {
+        let terminal_renderer = TerminalRenderer::new();
+        let markdown_output =
+            terminal_renderer.render_markdown("See [Claw](https://example.com/docs) now.");
+        let plain_text = strip_ansi(&markdown_output);
+
+        assert!(plain_text.contains("[Claw](https://example.com/docs)"));
+        assert!(markdown_output.contains('\u{1b}'));
+    }
+
     #[test]
     fn highlights_fenced_code_blocks() {
         let terminal_renderer = TerminalRenderer::new();
         let markdown_output =
-            terminal_renderer.render_markdown("```rust\nfn hi() { println!(\"hi\"); }\n```");
+            terminal_renderer.markdown_to_ansi("```rust\nfn hi() { println!(\"hi\"); }\n```");
         let plain_text = strip_ansi(&markdown_output);
 
         assert!(plain_text.contains("╭─ rust"));
         assert!(plain_text.contains("fn hi"));
         assert!(markdown_output.contains('\u{1b}'));
+        assert!(markdown_output.contains("[48;5;236m"));
     }
 
     #[test]
@@ -623,6 +758,26 @@ mod tests {
         assert!(markdown_output.contains('\u{1b}'));
     }
 
+    #[test]
+    fn streaming_state_waits_for_complete_blocks() {
+        let renderer = TerminalRenderer::new();
+        let mut state = MarkdownStreamState::default();
+
+        assert_eq!(state.push(&renderer, "# Heading"), None);
+        let flushed = state
+            .push(&renderer, "\n\nParagraph\n\n")
+            .expect("completed block");
+        let plain_text = strip_ansi(&flushed);
+        assert!(plain_text.contains("Heading"));
+        assert!(plain_text.contains("Paragraph"));
+
+        assert_eq!(state.push(&renderer, "```rust\nfn main() {}\n"), None);
+        let code = state
+            .push(&renderer, "```\n")
+            .expect("closed code fence flushes");
+        assert!(strip_ansi(&code).contains("fn main()"));
+    }
+
     #[test]
     fn spinner_advances_frames() {
         let terminal_renderer = TerminalRenderer::new();

rust/crates/tools/Cargo.toml

@@ -6,10 +6,12 @@ license.workspace = true
 publish.workspace = true
 
 [dependencies]
+api = { path = "../api" }
 runtime = { path = "../runtime" }
 reqwest = { version = "0.12", default-features = false, features = ["blocking", "rustls-tls"] }
 serde = { version = "1", features = ["derive"] }
 serde_json = "1"
+tokio = { version = "1", features = ["rt-multi-thread"] }
 
 [lints]
 workspace = true

rust/crates/tools/src/lib.rs

@@ -3,10 +3,17 @@ use std::path::{Path, PathBuf};
 use std::process::Command;
 use std::time::{Duration, Instant};
 
+use api::{
+    read_base_url, AnthropicClient, ContentBlockDelta, InputContentBlock, InputMessage,
+    MessageRequest, MessageResponse, OutputContentBlock, StreamEvent as ApiStreamEvent, ToolChoice,
+    ToolDefinition, ToolResultContentBlock,
+};
 use reqwest::blocking::Client;
 use runtime::{
-    edit_file, execute_bash, glob_search, grep_search, read_file, write_file, BashCommandInput,
+    edit_file, execute_bash, glob_search, grep_search, load_system_prompt, read_file, write_file,
-    GrepSearchInput, PermissionMode,
+    ApiClient, ApiRequest, AssistantEvent, BashCommandInput, ContentBlock, ConversationMessage,
+    ConversationRuntime, GrepSearchInput, MessageRole, PermissionMode, PermissionPolicy,
+    RuntimeError, Session, TokenUsage, ToolError, ToolExecutor,
 };
 use serde::{Deserialize, Serialize};
 use serde_json::{json, Value};
@@ -702,7 +709,7 @@ struct SkillOutput {
     prompt: String,
 }
 
-#[derive(Debug, Serialize, Deserialize)]
+#[derive(Debug, Clone, Serialize, Deserialize)]
 struct AgentOutput {
     #[serde(rename = "agentId")]
     agent_id: String,
@@ -718,6 +725,20 @@ struct AgentOutput {
     manifest_file: String,
     #[serde(rename = "createdAt")]
     created_at: String,
+    #[serde(rename = "startedAt", skip_serializing_if = "Option::is_none")]
+    started_at: Option<String>,
+    #[serde(rename = "completedAt", skip_serializing_if = "Option::is_none")]
+    completed_at: Option<String>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    error: Option<String>,
+}
+
+#[derive(Debug, Clone)]
+struct AgentJob {
+    manifest: AgentOutput,
+    prompt: String,
+    system_prompt: Vec<String>,
+    allowed_tools: BTreeSet<String>,
 }
 
 #[derive(Debug, Serialize)]
@@ -1259,15 +1280,7 @@ 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"));
     }
@@ -1323,7 +1336,18 @@ fn resolve_skill_path(skill: &str) -> Result<std::path::PathBuf, String> {
     Err(format!("unknown skill: {requested}"))
 }
 
+const DEFAULT_AGENT_MODEL: &str = "claude-opus-4-6";
+const DEFAULT_AGENT_SYSTEM_DATE: &str = "2026-03-31";
+const DEFAULT_AGENT_MAX_ITERATIONS: usize = 32;
+
 fn execute_agent(input: AgentInput) -> Result<AgentOutput, String> {
+    execute_agent_with_spawn(input, spawn_agent_job)
+}
+
+fn execute_agent_with_spawn<F>(input: AgentInput, spawn_fn: F) -> Result<AgentOutput, String>
+where
+    F: FnOnce(AgentJob) -> Result<(), String>,
+{
     if input.description.trim().is_empty() {
         return Err(String::from("description must not be empty"));
     }
@@ -1337,6 +1361,7 @@ fn execute_agent(input: AgentInput) -> Result<AgentOutput, String> {
     let output_file = output_dir.join(format!("{agent_id}.md"));
     let manifest_file = output_dir.join(format!("{agent_id}.json"));
     let normalized_subagent_type = normalize_subagent_type(input.subagent_type.as_deref());
+    let model = resolve_agent_model(input.model.as_deref());
     let agent_name = input
         .name
         .as_deref()
@@ -1344,6 +1369,8 @@ fn execute_agent(input: AgentInput) -> Result<AgentOutput, String> {
         .filter(|name| !name.is_empty())
         .unwrap_or_else(|| slugify_agent_name(&input.description));
     let created_at = iso8601_now();
+    let system_prompt = build_agent_system_prompt(&normalized_subagent_type)?;
+    let allowed_tools = allowed_tools_for_subagent(&normalized_subagent_type);
 
     let output_contents = format!(
         "# Agent Task
@@ -1367,21 +1394,514 @@ fn execute_agent(input: AgentInput) -> Result<AgentOutput, String> {
         name: agent_name,
         description: input.description,
         subagent_type: Some(normalized_subagent_type),
-        model: input.model,
+        model: Some(model),
-        status: String::from("queued"),
+        status: String::from("running"),
         output_file: output_file.display().to_string(),
         manifest_file: manifest_file.display().to_string(),
-        created_at,
+        created_at: created_at.clone(),
+        started_at: Some(created_at),
+        completed_at: None,
+        error: None,
     };
-    std::fs::write(
+    write_agent_manifest(&manifest)?;
-        &manifest_file,
+
-        serde_json::to_string_pretty(&manifest).map_err(|error| error.to_string())?,
+    let manifest_for_spawn = manifest.clone();
-    )
+    let job = AgentJob {
-    .map_err(|error| error.to_string())?;
+        manifest: manifest_for_spawn,
+        prompt: input.prompt,
+        system_prompt,
+        allowed_tools,
+    };
+    if let Err(error) = spawn_fn(job) {
+        let error = format!("failed to spawn sub-agent: {error}");
+        persist_agent_terminal_state(&manifest, "failed", None, Some(error.clone()))?;
+        return Err(error);
+    }
 
     Ok(manifest)
 }
 
+fn spawn_agent_job(job: AgentJob) -> Result<(), String> {
+    let thread_name = format!("clawd-agent-{}", job.manifest.agent_id);
+    std::thread::Builder::new()
+        .name(thread_name)
+        .spawn(move || {
+            let result =
+                std::panic::catch_unwind(std::panic::AssertUnwindSafe(|| run_agent_job(&job)));
+            match result {
+                Ok(Ok(())) => {}
+                Ok(Err(error)) => {
+                    let _ =
+                        persist_agent_terminal_state(&job.manifest, "failed", None, Some(error));
+                }
+                Err(_) => {
+                    let _ = persist_agent_terminal_state(
+                        &job.manifest,
+                        "failed",
+                        None,
+                        Some(String::from("sub-agent thread panicked")),
+                    );
+                }
+            }
+        })
+        .map(|_| ())
+        .map_err(|error| error.to_string())
+}
+
+fn run_agent_job(job: &AgentJob) -> Result<(), String> {
+    let mut runtime = build_agent_runtime(job)?.with_max_iterations(DEFAULT_AGENT_MAX_ITERATIONS);
+    let summary = runtime
+        .run_turn(job.prompt.clone(), None)
+        .map_err(|error| error.to_string())?;
+    let final_text = final_assistant_text(&summary);
+    persist_agent_terminal_state(&job.manifest, "completed", Some(final_text.as_str()), None)
+}
+
+fn build_agent_runtime(
+    job: &AgentJob,
+) -> Result<ConversationRuntime<AnthropicRuntimeClient, SubagentToolExecutor>, String> {
+    let model = job
+        .manifest
+        .model
+        .clone()
+        .unwrap_or_else(|| DEFAULT_AGENT_MODEL.to_string());
+    let allowed_tools = job.allowed_tools.clone();
+    let api_client = AnthropicRuntimeClient::new(model, allowed_tools.clone())?;
+    let tool_executor = SubagentToolExecutor::new(allowed_tools);
+    Ok(ConversationRuntime::new(
+        Session::new(),
+        api_client,
+        tool_executor,
+        agent_permission_policy(),
+        job.system_prompt.clone(),
+    ))
+}
+
+fn build_agent_system_prompt(subagent_type: &str) -> Result<Vec<String>, String> {
+    let cwd = std::env::current_dir().map_err(|error| error.to_string())?;
+    let mut prompt = load_system_prompt(
+        cwd,
+        DEFAULT_AGENT_SYSTEM_DATE.to_string(),
+        std::env::consts::OS,
+        "unknown",
+    )
+    .map_err(|error| error.to_string())?;
+    prompt.push(format!(
+        "You are a background sub-agent of type `{subagent_type}`. Work only on the delegated task, use only the tools available to you, do not ask the user questions, and finish with a concise result."
+    ));
+    Ok(prompt)
+}
+
+fn resolve_agent_model(model: Option<&str>) -> String {
+    model
+        .map(str::trim)
+        .filter(|model| !model.is_empty())
+        .unwrap_or(DEFAULT_AGENT_MODEL)
+        .to_string()
+}
+
+fn allowed_tools_for_subagent(subagent_type: &str) -> BTreeSet<String> {
+    let tools = match subagent_type {
+        "Explore" => vec![
+            "read_file",
+            "glob_search",
+            "grep_search",
+            "WebFetch",
+            "WebSearch",
+            "ToolSearch",
+            "Skill",
+            "StructuredOutput",
+        ],
+        "Plan" => vec![
+            "read_file",
+            "glob_search",
+            "grep_search",
+            "WebFetch",
+            "WebSearch",
+            "ToolSearch",
+            "Skill",
+            "TodoWrite",
+            "StructuredOutput",
+            "SendUserMessage",
+        ],
+        "Verification" => vec![
+            "bash",
+            "read_file",
+            "glob_search",
+            "grep_search",
+            "WebFetch",
+            "WebSearch",
+            "ToolSearch",
+            "TodoWrite",
+            "StructuredOutput",
+            "SendUserMessage",
+            "PowerShell",
+        ],
+        "claude-code-guide" => vec![
+            "read_file",
+            "glob_search",
+            "grep_search",
+            "WebFetch",
+            "WebSearch",
+            "ToolSearch",
+            "Skill",
+            "StructuredOutput",
+            "SendUserMessage",
+        ],
+        "statusline-setup" => vec![
+            "bash",
+            "read_file",
+            "write_file",
+            "edit_file",
+            "glob_search",
+            "grep_search",
+            "ToolSearch",
+        ],
+        _ => vec![
+            "bash",
+            "read_file",
+            "write_file",
+            "edit_file",
+            "glob_search",
+            "grep_search",
+            "WebFetch",
+            "WebSearch",
+            "TodoWrite",
+            "Skill",
+            "ToolSearch",
+            "NotebookEdit",
+            "Sleep",
+            "SendUserMessage",
+            "Config",
+            "StructuredOutput",
+            "REPL",
+            "PowerShell",
+        ],
+    };
+    tools.into_iter().map(str::to_string).collect()
+}
+
+fn agent_permission_policy() -> PermissionPolicy {
+    mvp_tool_specs().into_iter().fold(
+        PermissionPolicy::new(PermissionMode::DangerFullAccess),
+        |policy, spec| policy.with_tool_requirement(spec.name, spec.required_permission),
+    )
+}
+
+fn write_agent_manifest(manifest: &AgentOutput) -> Result<(), String> {
+    std::fs::write(
+        &manifest.manifest_file,
+        serde_json::to_string_pretty(manifest).map_err(|error| error.to_string())?,
+    )
+    .map_err(|error| error.to_string())
+}
+
+fn persist_agent_terminal_state(
+    manifest: &AgentOutput,
+    status: &str,
+    result: Option<&str>,
+    error: Option<String>,
+) -> Result<(), String> {
+    append_agent_output(
+        &manifest.output_file,
+        &format_agent_terminal_output(status, result, error.as_deref()),
+    )?;
+    let mut next_manifest = manifest.clone();
+    next_manifest.status = status.to_string();
+    next_manifest.completed_at = Some(iso8601_now());
+    next_manifest.error = error;
+    write_agent_manifest(&next_manifest)
+}
+
+fn append_agent_output(path: &str, suffix: &str) -> Result<(), String> {
+    use std::io::Write as _;
+
+    let mut file = std::fs::OpenOptions::new()
+        .append(true)
+        .open(path)
+        .map_err(|error| error.to_string())?;
+    file.write_all(suffix.as_bytes())
+        .map_err(|error| error.to_string())
+}
+
+fn format_agent_terminal_output(status: &str, result: Option<&str>, error: Option<&str>) -> String {
+    let mut sections = vec![format!("\n## Result\n\n- status: {status}\n")];
+    if let Some(result) = result.filter(|value| !value.trim().is_empty()) {
+        sections.push(format!("\n### Final response\n\n{}\n", result.trim()));
+    }
+    if let Some(error) = error.filter(|value| !value.trim().is_empty()) {
+        sections.push(format!("\n### Error\n\n{}\n", error.trim()));
+    }
+    sections.join("")
+}
+
+struct AnthropicRuntimeClient {
+    runtime: tokio::runtime::Runtime,
+    client: AnthropicClient,
+    model: String,
+    allowed_tools: BTreeSet<String>,
+}
+
+impl AnthropicRuntimeClient {
+    fn new(model: String, allowed_tools: BTreeSet<String>) -> Result<Self, String> {
+        let client = AnthropicClient::from_env()
+            .map_err(|error| error.to_string())?
+            .with_base_url(read_base_url());
+        Ok(Self {
+            runtime: tokio::runtime::Runtime::new().map_err(|error| error.to_string())?,
+            client,
+            model,
+            allowed_tools,
+        })
+    }
+}
+
+impl ApiClient for AnthropicRuntimeClient {
+    fn stream(&mut self, request: ApiRequest) -> Result<Vec<AssistantEvent>, RuntimeError> {
+        let tools = tool_specs_for_allowed_tools(Some(&self.allowed_tools))
+            .into_iter()
+            .map(|spec| ToolDefinition {
+                name: spec.name.to_string(),
+                description: Some(spec.description.to_string()),
+                input_schema: spec.input_schema,
+            })
+            .collect::<Vec<_>>();
+        let message_request = MessageRequest {
+            model: self.model.clone(),
+            max_tokens: 32_000,
+            messages: convert_messages(&request.messages),
+            system: (!request.system_prompt.is_empty()).then(|| request.system_prompt.join("\n\n")),
+            tools: (!tools.is_empty()).then_some(tools),
+            tool_choice: (!self.allowed_tools.is_empty()).then_some(ToolChoice::Auto),
+            stream: true,
+        };
+
+        self.runtime.block_on(async {
+            let mut stream = self
+                .client
+                .stream_message(&message_request)
+                .await
+                .map_err(|error| RuntimeError::new(error.to_string()))?;
+            let mut events = Vec::new();
+            let mut pending_tool: Option<(String, String, String)> = None;
+            let mut saw_stop = false;
+
+            while let Some(event) = stream
+                .next_event()
+                .await
+                .map_err(|error| RuntimeError::new(error.to_string()))?
+            {
+                match event {
+                    ApiStreamEvent::MessageStart(start) => {
+                        for block in start.message.content {
+                            push_output_block(block, &mut events, &mut pending_tool, true);
+                        }
+                    }
+                    ApiStreamEvent::ContentBlockStart(start) => {
+                        push_output_block(
+                            start.content_block,
+                            &mut events,
+                            &mut pending_tool,
+                            true,
+                        );
+                    }
+                    ApiStreamEvent::ContentBlockDelta(delta) => match delta.delta {
+                        ContentBlockDelta::TextDelta { text } => {
+                            if !text.is_empty() {
+                                events.push(AssistantEvent::TextDelta(text));
+                            }
+                        }
+                        ContentBlockDelta::InputJsonDelta { partial_json } => {
+                            if let Some((_, _, input)) = &mut pending_tool {
+                                input.push_str(&partial_json);
+                            }
+                        }
+                    },
+                    ApiStreamEvent::ContentBlockStop(_) => {
+                        if let Some((id, name, input)) = pending_tool.take() {
+                            events.push(AssistantEvent::ToolUse { id, name, input });
+                        }
+                    }
+                    ApiStreamEvent::MessageDelta(delta) => {
+                        events.push(AssistantEvent::Usage(TokenUsage {
+                            input_tokens: delta.usage.input_tokens,
+                            output_tokens: delta.usage.output_tokens,
+                            cache_creation_input_tokens: 0,
+                            cache_read_input_tokens: 0,
+                        }));
+                    }
+                    ApiStreamEvent::MessageStop(_) => {
+                        saw_stop = true;
+                        events.push(AssistantEvent::MessageStop);
+                    }
+                }
+            }
+
+            if !saw_stop
+                && events.iter().any(|event| {
+                    matches!(event, AssistantEvent::TextDelta(text) if !text.is_empty())
+                        || matches!(event, AssistantEvent::ToolUse { .. })
+                })
+            {
+                events.push(AssistantEvent::MessageStop);
+            }
+
+            if events
+                .iter()
+                .any(|event| matches!(event, AssistantEvent::MessageStop))
+            {
+                return Ok(events);
+            }
+
+            let response = self
+                .client
+                .send_message(&MessageRequest {
+                    stream: false,
+                    ..message_request.clone()
+                })
+                .await
+                .map_err(|error| RuntimeError::new(error.to_string()))?;
+            Ok(response_to_events(response))
+        })
+    }
+}
+
+struct SubagentToolExecutor {
+    allowed_tools: BTreeSet<String>,
+}
+
+impl SubagentToolExecutor {
+    fn new(allowed_tools: BTreeSet<String>) -> Self {
+        Self { allowed_tools }
+    }
+}
+
+impl ToolExecutor for SubagentToolExecutor {
+    fn execute(&mut self, tool_name: &str, input: &str) -> Result<String, ToolError> {
+        if !self.allowed_tools.contains(tool_name) {
+            return Err(ToolError::new(format!(
+                "tool `{tool_name}` is not enabled for this sub-agent"
+            )));
+        }
+        let value = serde_json::from_str(input)
+            .map_err(|error| ToolError::new(format!("invalid tool input JSON: {error}")))?;
+        execute_tool(tool_name, &value).map_err(ToolError::new)
+    }
+}
+
+fn tool_specs_for_allowed_tools(allowed_tools: Option<&BTreeSet<String>>) -> Vec<ToolSpec> {
+    mvp_tool_specs()
+        .into_iter()
+        .filter(|spec| allowed_tools.is_none_or(|allowed| allowed.contains(spec.name)))
+        .collect()
+}
+
+fn convert_messages(messages: &[ConversationMessage]) -> Vec<InputMessage> {
+    messages
+        .iter()
+        .filter_map(|message| {
+            let role = match message.role {
+                MessageRole::System | MessageRole::User | MessageRole::Tool => "user",
+                MessageRole::Assistant => "assistant",
+            };
+            let content = message
+                .blocks
+                .iter()
+                .map(|block| match block {
+                    ContentBlock::Text { text } => InputContentBlock::Text { text: text.clone() },
+                    ContentBlock::ToolUse { id, name, input } => InputContentBlock::ToolUse {
+                        id: id.clone(),
+                        name: name.clone(),
+                        input: serde_json::from_str(input)
+                            .unwrap_or_else(|_| serde_json::json!({ "raw": input })),
+                    },
+                    ContentBlock::ToolResult {
+                        tool_use_id,
+                        output,
+                        is_error,
+                        ..
+                    } => InputContentBlock::ToolResult {
+                        tool_use_id: tool_use_id.clone(),
+                        content: vec![ToolResultContentBlock::Text {
+                            text: output.clone(),
+                        }],
+                        is_error: *is_error,
+                    },
+                })
+                .collect::<Vec<_>>();
+            (!content.is_empty()).then(|| InputMessage {
+                role: role.to_string(),
+                content,
+            })
+        })
+        .collect()
+}
+
+fn push_output_block(
+    block: OutputContentBlock,
+    events: &mut Vec<AssistantEvent>,
+    pending_tool: &mut Option<(String, String, String)>,
+    streaming_tool_input: bool,
+) {
+    match block {
+        OutputContentBlock::Text { text } => {
+            if !text.is_empty() {
+                events.push(AssistantEvent::TextDelta(text));
+            }
+        }
+        OutputContentBlock::ToolUse { id, name, input } => {
+            let initial_input = if streaming_tool_input
+                && input.is_object()
+                && input.as_object().is_some_and(serde_json::Map::is_empty)
+            {
+                String::new()
+            } else {
+                input.to_string()
+            };
+            *pending_tool = Some((id, name, initial_input));
+        }
+    }
+}
+
+fn response_to_events(response: MessageResponse) -> Vec<AssistantEvent> {
+    let mut events = Vec::new();
+    let mut pending_tool = None;
+
+    for block in response.content {
+        push_output_block(block, &mut events, &mut pending_tool, false);
+        if let Some((id, name, input)) = pending_tool.take() {
+            events.push(AssistantEvent::ToolUse { id, name, input });
+        }
+    }
+
+    events.push(AssistantEvent::Usage(TokenUsage {
+        input_tokens: response.usage.input_tokens,
+        output_tokens: response.usage.output_tokens,
+        cache_creation_input_tokens: response.usage.cache_creation_input_tokens,
+        cache_read_input_tokens: response.usage.cache_read_input_tokens,
+    }));
+    events.push(AssistantEvent::MessageStop);
+    events
+}
+
+fn final_assistant_text(summary: &runtime::TurnSummary) -> String {
+    summary
+        .assistant_messages
+        .last()
+        .map(|message| {
+            message
+                .blocks
+                .iter()
+                .filter_map(|block| match block {
+                    ContentBlock::Text { text } => Some(text.as_str()),
+                    _ => None,
+                })
+                .collect::<Vec<_>>()
+                .join("")
+        })
+        .unwrap_or_default()
+}
+
 #[allow(clippy::needless_pass_by_value)]
 fn execute_tool_search(input: ToolSearchInput) -> ToolSearchOutput {
     let deferred = deferred_tool_specs();
@@ -2215,7 +2735,7 @@ fn execute_shell_command(
             persisted_output_path: None,
             persisted_output_size: None,
             sandbox_status: None,
-});
+        });
     }
 
     let mut process = std::process::Command::new(shell);
@@ -2284,7 +2804,7 @@ Command exceeded timeout of {timeout_ms} ms",
                     persisted_output_path: None,
                     persisted_output_size: None,
                     sandbox_status: None,
-});
+                });
             }
             std::thread::sleep(Duration::from_millis(10));
         }
@@ -2373,6 +2893,7 @@ fn parse_skill_description(contents: &str) -> Option<String> {
 
 #[cfg(test)]
 mod tests {
+    use std::collections::BTreeSet;
     use std::fs;
     use std::io::{Read, Write};
     use std::net::{SocketAddr, TcpListener};
@@ -2381,7 +2902,12 @@ mod tests {
     use std::thread;
     use std::time::Duration;
 
-    use super::{execute_tool, mvp_tool_specs};
+    use super::{
+        agent_permission_policy, allowed_tools_for_subagent, execute_agent_with_spawn,
+        execute_tool, final_assistant_text, mvp_tool_specs, persist_agent_terminal_state,
+        AgentInput, AgentJob, SubagentToolExecutor,
+    };
+    use runtime::{ApiRequest, AssistantEvent, ConversationRuntime, RuntimeError, Session};
     use serde_json::json;
 
     fn env_lock() -> &'static Mutex<()> {
@@ -2654,7 +3180,8 @@ 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 +3190,7 @@ 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",
@@ -2773,32 +3299,48 @@ mod tests {
             .unwrap_or_else(std::sync::PoisonError::into_inner);
         let dir = temp_path("agent-store");
         std::env::set_var("CLAWD_AGENT_STORE", &dir);
+        let captured = Arc::new(Mutex::new(None::<AgentJob>));
+        let captured_for_spawn = Arc::clone(&captured);
 
-        let result = execute_tool(
+        let manifest = execute_agent_with_spawn(
-            "Agent",
+            AgentInput {
-            &json!({
+                description: "Audit the branch".to_string(),
-                "description": "Audit the branch",
+                prompt: "Check tests and outstanding work.".to_string(),
-                "prompt": "Check tests and outstanding work.",
+                subagent_type: Some("Explore".to_string()),
-                "subagent_type": "Explore",
+                name: Some("ship-audit".to_string()),
-                "name": "ship-audit"
+                model: None,
-            }),
+            },
+            move |job| {
+                *captured_for_spawn
+                    .lock()
+                    .unwrap_or_else(std::sync::PoisonError::into_inner) = Some(job);
+                Ok(())
+            },
         )
         .expect("Agent should succeed");
         std::env::remove_var("CLAWD_AGENT_STORE");
 
-        let output: serde_json::Value = serde_json::from_str(&result).expect("valid json");
+        assert_eq!(manifest.name, "ship-audit");
-        assert_eq!(output["name"], "ship-audit");
+        assert_eq!(manifest.subagent_type.as_deref(), Some("Explore"));
-        assert_eq!(output["subagentType"], "Explore");
+        assert_eq!(manifest.status, "running");
-        assert_eq!(output["status"], "queued");
+        assert!(!manifest.created_at.is_empty());
-        assert!(output["createdAt"].as_str().is_some());
+        assert!(manifest.started_at.is_some());
-        let manifest_file = output["manifestFile"].as_str().expect("manifest file");
+        assert!(manifest.completed_at.is_none());
-        let output_file = output["outputFile"].as_str().expect("output file");
+        let contents = std::fs::read_to_string(&manifest.output_file).expect("agent file exists");
-        let contents = std::fs::read_to_string(output_file).expect("agent file exists");
         let manifest_contents =
-            std::fs::read_to_string(manifest_file).expect("manifest file exists");
+            std::fs::read_to_string(&manifest.manifest_file).expect("manifest file exists");
         assert!(contents.contains("Audit the branch"));
         assert!(contents.contains("Check tests and outstanding work."));
         assert!(manifest_contents.contains("\"subagentType\": \"Explore\""));
+        assert!(manifest_contents.contains("\"status\": \"running\""));
+        let captured_job = captured
+            .lock()
+            .unwrap_or_else(std::sync::PoisonError::into_inner)
+            .clone()
+            .expect("spawn job should be captured");
+        assert_eq!(captured_job.prompt, "Check tests and outstanding work.");
+        assert!(captured_job.allowed_tools.contains("read_file"));
+        assert!(!captured_job.allowed_tools.contains("Agent"));
 
         let normalized = execute_tool(
             "Agent",
@@ -2827,6 +3369,195 @@ mod tests {
         let _ = std::fs::remove_dir_all(dir);
     }
 
+    #[test]
+    fn agent_fake_runner_can_persist_completion_and_failure() {
+        let _guard = env_lock()
+            .lock()
+            .unwrap_or_else(std::sync::PoisonError::into_inner);
+        let dir = temp_path("agent-runner");
+        std::env::set_var("CLAWD_AGENT_STORE", &dir);
+
+        let completed = execute_agent_with_spawn(
+            AgentInput {
+                description: "Complete the task".to_string(),
+                prompt: "Do the work".to_string(),
+                subagent_type: Some("Explore".to_string()),
+                name: Some("complete-task".to_string()),
+                model: Some("claude-sonnet-4-6".to_string()),
+            },
+            |job| {
+                persist_agent_terminal_state(
+                    &job.manifest,
+                    "completed",
+                    Some("Finished successfully"),
+                    None,
+                )
+            },
+        )
+        .expect("completed agent should succeed");
+
+        let completed_manifest = std::fs::read_to_string(&completed.manifest_file)
+            .expect("completed manifest should exist");
+        let completed_output =
+            std::fs::read_to_string(&completed.output_file).expect("completed output should exist");
+        assert!(completed_manifest.contains("\"status\": \"completed\""));
+        assert!(completed_output.contains("Finished successfully"));
+
+        let failed = execute_agent_with_spawn(
+            AgentInput {
+                description: "Fail the task".to_string(),
+                prompt: "Do the failing work".to_string(),
+                subagent_type: Some("Verification".to_string()),
+                name: Some("fail-task".to_string()),
+                model: None,
+            },
+            |job| {
+                persist_agent_terminal_state(
+                    &job.manifest,
+                    "failed",
+                    None,
+                    Some(String::from("simulated failure")),
+                )
+            },
+        )
+        .expect("failed agent should still spawn");
+
+        let failed_manifest =
+            std::fs::read_to_string(&failed.manifest_file).expect("failed manifest should exist");
+        let failed_output =
+            std::fs::read_to_string(&failed.output_file).expect("failed output should exist");
+        assert!(failed_manifest.contains("\"status\": \"failed\""));
+        assert!(failed_manifest.contains("simulated failure"));
+        assert!(failed_output.contains("simulated failure"));
+
+        let spawn_error = execute_agent_with_spawn(
+            AgentInput {
+                description: "Spawn error task".to_string(),
+                prompt: "Never starts".to_string(),
+                subagent_type: None,
+                name: Some("spawn-error".to_string()),
+                model: None,
+            },
+            |_| Err(String::from("thread creation failed")),
+        )
+        .expect_err("spawn errors should surface");
+        assert!(spawn_error.contains("failed to spawn sub-agent"));
+        let spawn_error_manifest = std::fs::read_dir(&dir)
+            .expect("agent dir should exist")
+            .filter_map(Result::ok)
+            .map(|entry| entry.path())
+            .filter(|path| path.extension().and_then(|ext| ext.to_str()) == Some("json"))
+            .find_map(|path| {
+                let contents = std::fs::read_to_string(&path).ok()?;
+                contents
+                    .contains("\"name\": \"spawn-error\"")
+                    .then_some(contents)
+            })
+            .expect("failed manifest should still be written");
+        assert!(spawn_error_manifest.contains("\"status\": \"failed\""));
+        assert!(spawn_error_manifest.contains("thread creation failed"));
+
+        std::env::remove_var("CLAWD_AGENT_STORE");
+        let _ = std::fs::remove_dir_all(dir);
+    }
+
+    #[test]
+    fn agent_tool_subset_mapping_is_expected() {
+        let general = allowed_tools_for_subagent("general-purpose");
+        assert!(general.contains("bash"));
+        assert!(general.contains("write_file"));
+        assert!(!general.contains("Agent"));
+
+        let explore = allowed_tools_for_subagent("Explore");
+        assert!(explore.contains("read_file"));
+        assert!(explore.contains("grep_search"));
+        assert!(!explore.contains("bash"));
+
+        let plan = allowed_tools_for_subagent("Plan");
+        assert!(plan.contains("TodoWrite"));
+        assert!(plan.contains("StructuredOutput"));
+        assert!(!plan.contains("Agent"));
+
+        let verification = allowed_tools_for_subagent("Verification");
+        assert!(verification.contains("bash"));
+        assert!(verification.contains("PowerShell"));
+        assert!(!verification.contains("write_file"));
+    }
+
+    #[derive(Debug)]
+    struct MockSubagentApiClient {
+        calls: usize,
+        input_path: String,
+    }
+
+    impl runtime::ApiClient for MockSubagentApiClient {
+        fn stream(&mut self, request: ApiRequest) -> Result<Vec<AssistantEvent>, RuntimeError> {
+            self.calls += 1;
+            match self.calls {
+                1 => {
+                    assert_eq!(request.messages.len(), 1);
+                    Ok(vec![
+                        AssistantEvent::ToolUse {
+                            id: "tool-1".to_string(),
+                            name: "read_file".to_string(),
+                            input: json!({ "path": self.input_path }).to_string(),
+                        },
+                        AssistantEvent::MessageStop,
+                    ])
+                }
+                2 => {
+                    assert!(request.messages.len() >= 3);
+                    Ok(vec![
+                        AssistantEvent::TextDelta("Scope: completed mock review".to_string()),
+                        AssistantEvent::MessageStop,
+                    ])
+                }
+                _ => panic!("unexpected mock stream call"),
+            }
+        }
+    }
+
+    #[test]
+    fn subagent_runtime_executes_tool_loop_with_isolated_session() {
+        let _guard = env_lock()
+            .lock()
+            .unwrap_or_else(std::sync::PoisonError::into_inner);
+        let path = temp_path("subagent-input.txt");
+        std::fs::write(&path, "hello from child").expect("write input file");
+
+        let mut runtime = ConversationRuntime::new(
+            Session::new(),
+            MockSubagentApiClient {
+                calls: 0,
+                input_path: path.display().to_string(),
+            },
+            SubagentToolExecutor::new(BTreeSet::from([String::from("read_file")])),
+            agent_permission_policy(),
+            vec![String::from("system prompt")],
+        );
+
+        let summary = runtime
+            .run_turn("Inspect the delegated file", None)
+            .expect("subagent loop should succeed");
+
+        assert_eq!(
+            final_assistant_text(&summary),
+            "Scope: completed mock review"
+        );
+        assert!(runtime
+            .session()
+            .messages
+            .iter()
+            .flat_map(|message| message.blocks.iter())
+            .any(|block| matches!(
+                block,
+                runtime::ContentBlock::ToolResult { output, .. }
+                    if output.contains("hello from child")
+            )));
+
+        let _ = std::fs::remove_file(path);
+    }
+
     #[test]
     fn agent_rejects_blank_required_fields() {
         let missing_description = execute_tool(