auto: save WIP progress from rcc session

.claude.json

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

.gitignore

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

CLAUDE.md

@@ -1,21 +0,0 @@
-# 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

@@ -1 +0,0 @@
-{"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

@@ -1 +0,0 @@
-{"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

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

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

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

rust/.claude/sessions/session-1775012674485.json

@@ -1 +0,0 @@
-{"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

@@ -1 +0,0 @@
-{"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

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

rust/.clawd-todos.json

@@ -1,27 +0,0 @@
-[
-  {
-    "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

@@ -1,221 +0,0 @@
-# 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

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

rust/Cargo.lock

@@ -111,7 +111,6 @@ dependencies = [
 name = "commands"
 version = "0.1.0"
 dependencies = [
- "plugins",
  "runtime",
 ]
 
@@ -826,14 +825,6 @@ dependencies = [
  "time",
 ]
 
-[[package]]
-name = "plugins"
-version = "0.1.0"
-dependencies = [
- "serde",
- "serde_json",
-]
-
 [[package]]
 name = "potential_utf"
 version = "0.1.4"
@@ -1101,7 +1092,6 @@ name = "runtime"
 version = "0.1.0"
 dependencies = [
  "glob",
- "plugins",
  "regex",
  "serde",
  "serde_json",
@@ -1191,7 +1181,6 @@ dependencies = [
  "commands",
  "compat-harness",
  "crossterm",
- "plugins",
  "pulldown-cmark",
  "runtime",
  "rustyline",
@@ -1557,7 +1546,6 @@ name = "tools"
 version = "0.1.0"
 dependencies = [
  "api",
- "plugins",
  "reqwest",
  "runtime",
  "serde",

rust/README.md

@@ -1,149 +1,230 @@
-# 🦞 Claw Code — Rust Implementation
+# Rusty Claude CLI
 
-A high-performance Rust rewrite of the Claw Code CLI agent harness. Built for speed, safety, and native tool execution.
+`rust/` contains the Rust workspace for the integrated `rusty-claude-cli` deliverable.
+It is intended to be something you can clone, build, and run directly.
 
-## Quick Start
+## Workspace layout
 
-```bash
+```text
-# 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              # Workspace root
+├── Cargo.toml
 ├── Cargo.lock
+├── README.md
 └── crates/
-    ├── api/                # Anthropic API client + SSE streaming
+    ├── api/               # Anthropic API client + SSE streaming support
-    ├── commands/           # Shared slash-command registry
+    ├── commands/          # Shared slash-command metadata/help surfaces
-    ├── compat-harness/     # TS manifest extraction harness
+    ├── compat-harness/    # Upstream TS manifest extraction harness
-    ├── runtime/            # Session, config, permissions, MCP, prompts
+    ├── runtime/           # Session/runtime/config/prompt orchestration
-    ├── rusty-claude-cli/   # Main CLI binary (`claw`)
+    ├── rusty-claude-cli/  # Main CLI binary
     └── tools/             # Built-in tool implementations
 ```
 
-### Crate Responsibilities
+## Prerequisites
 
-- **api** — HTTP client, SSE stream parser, request/response types, auth (API key + OAuth bearer)
+- Rust toolchain installed (`rustup`, stable toolchain)
-- **commands** — Slash command definitions and help text generation
+- Network access and Anthropic credentials for live prompt/REPL usage
-- **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
 
-## Stats
+## Build
 
-- **~20K lines** of Rust
+From the repository root:
-- **6 crates** in workspace
-- **Binary name:** `claw`
-- **Default model:** `claude-opus-4-6`
-- **Default permissions:** `danger-full-access`
 
-## License
+```bash
+cd rust
+cargo build --release -p rusty-claude-cli
+```
 
-See repository root.
+The optimized binary will be written to:
+
+```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

@@ -1,221 +0,0 @@
-# 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/sse.rs

@@ -216,64 +216,4 @@ mod tests {
             ))
         );
     }
-
-    #[test]
-    fn parses_thinking_content_block_start() {
-        let frame = concat!(
-            "event: content_block_start\n",
-            "data: {\"type\":\"content_block_start\",\"index\":0,\"content_block\":{\"type\":\"thinking\",\"thinking\":\"\",\"signature\":null}}\n\n"
-        );
-
-        let event = parse_frame(frame).expect("frame should parse");
-        assert_eq!(
-            event,
-            Some(StreamEvent::ContentBlockStart(
-                crate::types::ContentBlockStartEvent {
-                    index: 0,
-                    content_block: OutputContentBlock::Thinking {
-                        thinking: String::new(),
-                        signature: None,
-                    },
-                },
-            ))
-        );
-    }
-
-    #[test]
-    fn parses_thinking_related_deltas() {
-        let thinking = concat!(
-            "event: content_block_delta\n",
-            "data: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\"step 1\"}}\n\n"
-        );
-        let signature = concat!(
-            "event: content_block_delta\n",
-            "data: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"signature_delta\",\"signature\":\"sig_123\"}}\n\n"
-        );
-
-        let thinking_event = parse_frame(thinking).expect("thinking delta should parse");
-        let signature_event = parse_frame(signature).expect("signature delta should parse");
-
-        assert_eq!(
-            thinking_event,
-            Some(StreamEvent::ContentBlockDelta(
-                crate::types::ContentBlockDeltaEvent {
-                    index: 0,
-                    delta: ContentBlockDelta::ThinkingDelta {
-                        thinking: "step 1".to_string(),
-                    },
-                }
-            ))
-        );
-        assert_eq!(
-            signature_event,
-            Some(StreamEvent::ContentBlockDelta(
-                crate::types::ContentBlockDeltaEvent {
-                    index: 0,
-                    delta: ContentBlockDelta::SignatureDelta {
-                        signature: "sig_123".to_string(),
-                    },
-                }
-            ))
-        );
-    }
 }

rust/crates/api/src/types.rs

@@ -135,15 +135,6 @@ pub enum OutputContentBlock {
         name: String,
         input: Value,
     },
-    Thinking {
-        #[serde(default)]
-        thinking: String,
-        #[serde(default, skip_serializing_if = "Option::is_none")]
-        signature: Option<String>,
-    },
-    RedactedThinking {
-        data: Value,
-    },
 }
 
 #[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
@@ -199,8 +190,6 @@ pub struct ContentBlockDeltaEvent {
 pub enum ContentBlockDelta {
     TextDelta { text: String },
     InputJsonDelta { partial_json: String },
-    ThinkingDelta { thinking: String },
-    SignatureDelta { signature: String },
 }
 
 #[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]

rust/crates/api/tests/client_integration.rs

@@ -75,48 +75,6 @@ async fn send_message_posts_json_and_parses_response() {
     assert_eq!(body["tool_choice"]["type"], json!("auto"));
 }
 
-#[tokio::test]
-async fn send_message_parses_response_with_thinking_blocks() {
-    let state = Arc::new(Mutex::new(Vec::<CapturedRequest>::new()));
-    let body = concat!(
-        "{",
-        "\"id\":\"msg_thinking\",",
-        "\"type\":\"message\",",
-        "\"role\":\"assistant\",",
-        "\"content\":[",
-        "{\"type\":\"thinking\",\"thinking\":\"step 1\",\"signature\":\"sig_123\"},",
-        "{\"type\":\"text\",\"text\":\"Final answer\"}",
-        "],",
-        "\"model\":\"claude-3-7-sonnet-latest\",",
-        "\"stop_reason\":\"end_turn\",",
-        "\"stop_sequence\":null,",
-        "\"usage\":{\"input_tokens\":12,\"output_tokens\":4}",
-        "}"
-    );
-    let server = spawn_server(
-        state,
-        vec![http_response("200 OK", "application/json", body)],
-    )
-    .await;
-
-    let client = AnthropicClient::new("test-key").with_base_url(server.base_url());
-    let response = client
-        .send_message(&sample_request(false))
-        .await
-        .expect("request should succeed");
-
-    assert_eq!(response.content.len(), 2);
-    assert!(matches!(
-        &response.content[0],
-        OutputContentBlock::Thinking { thinking, signature }
-            if thinking == "step 1" && signature.as_deref() == Some("sig_123")
-    ));
-    assert!(matches!(
-        &response.content[1],
-        OutputContentBlock::Text { text } if text == "Final answer"
-    ));
-}
-
 #[tokio::test]
 async fn stream_message_parses_sse_events_with_tool_use() {
     let state = Arc::new(Mutex::new(Vec::<CapturedRequest>::new()));
@@ -204,85 +162,6 @@ async fn stream_message_parses_sse_events_with_tool_use() {
     assert!(request.body.contains("\"stream\":true"));
 }
 
-#[tokio::test]
-async fn stream_message_parses_sse_events_with_thinking_blocks() {
-    let state = Arc::new(Mutex::new(Vec::<CapturedRequest>::new()));
-    let sse = concat!(
-        "event: message_start\n",
-        "data: {\"type\":\"message_start\",\"message\":{\"id\":\"msg_stream_thinking\",\"type\":\"message\",\"role\":\"assistant\",\"content\":[],\"model\":\"claude-3-7-sonnet-latest\",\"stop_reason\":null,\"stop_sequence\":null,\"usage\":{\"input_tokens\":8,\"output_tokens\":0}}}\n\n",
-        "event: content_block_start\n",
-        "data: {\"type\":\"content_block_start\",\"index\":0,\"content_block\":{\"type\":\"thinking\",\"thinking\":\"\"}}\n\n",
-        "event: content_block_delta\n",
-        "data: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\"step 1\"}}\n\n",
-        "event: content_block_delta\n",
-        "data: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"signature_delta\",\"signature\":\"sig_123\"}}\n\n",
-        "event: content_block_stop\n",
-        "data: {\"type\":\"content_block_stop\",\"index\":0}\n\n",
-        "event: content_block_start\n",
-        "data: {\"type\":\"content_block_start\",\"index\":1,\"content_block\":{\"type\":\"text\",\"text\":\"Final answer\"}}\n\n",
-        "event: content_block_stop\n",
-        "data: {\"type\":\"content_block_stop\",\"index\":1}\n\n",
-        "event: message_delta\n",
-        "data: {\"type\":\"message_delta\",\"delta\":{\"stop_reason\":\"end_turn\",\"stop_sequence\":null},\"usage\":{\"input_tokens\":8,\"output_tokens\":1}}\n\n",
-        "event: message_stop\n",
-        "data: {\"type\":\"message_stop\"}\n\n",
-        "data: [DONE]\n\n"
-    );
-    let server = spawn_server(
-        state,
-        vec![http_response("200 OK", "text/event-stream", sse)],
-    )
-    .await;
-
-    let client = AnthropicClient::new("test-key").with_base_url(server.base_url());
-    let mut stream = client
-        .stream_message(&sample_request(false))
-        .await
-        .expect("stream should start");
-
-    let mut events = Vec::new();
-    while let Some(event) = stream
-        .next_event()
-        .await
-        .expect("stream event should parse")
-    {
-        events.push(event);
-    }
-
-    assert_eq!(events.len(), 9);
-    assert!(matches!(
-        &events[1],
-        StreamEvent::ContentBlockStart(ContentBlockStartEvent {
-            content_block: OutputContentBlock::Thinking { thinking, signature },
-            ..
-        }) if thinking.is_empty() && signature.is_none()
-    ));
-    assert!(matches!(
-        &events[2],
-        StreamEvent::ContentBlockDelta(ContentBlockDeltaEvent {
-            delta: ContentBlockDelta::ThinkingDelta { thinking },
-            ..
-        }) if thinking == "step 1"
-    ));
-    assert!(matches!(
-        &events[3],
-        StreamEvent::ContentBlockDelta(ContentBlockDeltaEvent {
-            delta: ContentBlockDelta::SignatureDelta { signature },
-            ..
-        }) if signature == "sig_123"
-    ));
-    assert!(matches!(
-        &events[5],
-        StreamEvent::ContentBlockStart(ContentBlockStartEvent {
-            content_block: OutputContentBlock::Text { text },
-            ..
-        }) if text == "Final answer"
-    ));
-    assert!(matches!(events[6], StreamEvent::ContentBlockStop(_)));
-    assert!(matches!(events[7], StreamEvent::MessageDelta(_)));
-    assert!(matches!(events[8], StreamEvent::MessageStop(_)));
-}
-
 #[tokio::test]
 async fn retries_retryable_failures_before_succeeding() {
     let state = Arc::new(Mutex::new(Vec::<CapturedRequest>::new()));

rust/crates/commands/Cargo.toml

@@ -9,5 +9,4 @@ publish.workspace = true
 workspace = true
 
 [dependencies]
-plugins = { path = "../plugins" }
 runtime = { path = "../runtime" }

rust/crates/compat-harness/src/lib.rs

@@ -70,12 +70,16 @@ fn upstream_repo_candidates(primary_repo_root: &Path) -> Vec<PathBuf> {
     }
 
     for ancestor in primary_repo_root.ancestors().take(4) {
-        candidates.push(ancestor.join("claw-code"));
+        candidates.push(ancestor.join("claude-code"));
         candidates.push(ancestor.join("clawd-code"));
     }
 
-    candidates.push(primary_repo_root.join("reference-source").join("claw-code"));
+    candidates.push(
-    candidates.push(primary_repo_root.join("vendor").join("claw-code"));
+        primary_repo_root
+            .join("reference-source")
+            .join("claude-code"),
+    );
+    candidates.push(primary_repo_root.join("vendor").join("claude-code"));
 
     let mut deduped = Vec::new();
     for candidate in candidates {

rust/crates/plugins/Cargo.toml

@@ -1,13 +0,0 @@
-[package]
-name = "plugins"
-version.workspace = true
-edition.workspace = true
-license.workspace = true
-publish.workspace = true
-
-[dependencies]
-serde = { version = "1", features = ["derive"] }
-serde_json = "1"
-
-[lints]
-workspace = true

rust/crates/plugins/bundled/example-bundled/.claude-plugin/plugin.json

@@ -1,10 +0,0 @@
-{
-  "name": "example-bundled",
-  "version": "0.1.0",
-  "description": "Example bundled plugin scaffold for the Rust plugin system",
-  "defaultEnabled": false,
-  "hooks": {
-    "PreToolUse": ["./hooks/pre.sh"],
-    "PostToolUse": ["./hooks/post.sh"]
-  }
-}

rust/crates/plugins/bundled/example-bundled/hooks/post.sh

@@ -1,2 +0,0 @@
-#!/bin/sh
-printf '%s\n' 'example bundled post hook'

rust/crates/plugins/bundled/example-bundled/hooks/pre.sh

@@ -1,2 +0,0 @@
-#!/bin/sh
-printf '%s\n' 'example bundled pre hook'

rust/crates/plugins/bundled/sample-hooks/.claude-plugin/plugin.json

@@ -1,10 +0,0 @@
-{
-  "name": "sample-hooks",
-  "version": "0.1.0",
-  "description": "Bundled sample plugin scaffold for hook integration tests.",
-  "defaultEnabled": false,
-  "hooks": {
-    "PreToolUse": ["./hooks/pre.sh"],
-    "PostToolUse": ["./hooks/post.sh"]
-  }
-}

rust/crates/plugins/bundled/sample-hooks/hooks/post.sh

@@ -1,2 +0,0 @@
-#!/bin/sh
-printf 'sample bundled post hook'

rust/crates/plugins/bundled/sample-hooks/hooks/pre.sh

@@ -1,2 +0,0 @@
-#!/bin/sh
-printf 'sample bundled pre hook'

rust/crates/plugins/src/hooks.rs

@@ -1,395 +0,0 @@
-use std::ffi::OsStr;
-use std::path::Path;
-use std::process::Command;
-
-use serde_json::json;
-
-use crate::{PluginError, PluginHooks, PluginRegistry};
-
-#[derive(Debug, Clone, Copy, PartialEq, Eq)]
-pub enum HookEvent {
-    PreToolUse,
-    PostToolUse,
-}
-
-impl HookEvent {
-    fn as_str(self) -> &'static str {
-        match self {
-            Self::PreToolUse => "PreToolUse",
-            Self::PostToolUse => "PostToolUse",
-        }
-    }
-}
-
-#[derive(Debug, Clone, PartialEq, Eq)]
-pub struct HookRunResult {
-    denied: bool,
-    messages: Vec<String>,
-}
-
-impl HookRunResult {
-    #[must_use]
-    pub fn allow(messages: Vec<String>) -> Self {
-        Self {
-            denied: false,
-            messages,
-        }
-    }
-
-    #[must_use]
-    pub fn is_denied(&self) -> bool {
-        self.denied
-    }
-
-    #[must_use]
-    pub fn messages(&self) -> &[String] {
-        &self.messages
-    }
-}
-
-#[derive(Debug, Clone, PartialEq, Eq, Default)]
-pub struct HookRunner {
-    hooks: PluginHooks,
-}
-
-impl HookRunner {
-    #[must_use]
-    pub fn new(hooks: PluginHooks) -> Self {
-        Self { hooks }
-    }
-
-    pub fn from_registry(plugin_registry: &PluginRegistry) -> Result<Self, PluginError> {
-        Ok(Self::new(plugin_registry.aggregated_hooks()?))
-    }
-
-    #[must_use]
-    pub fn run_pre_tool_use(&self, tool_name: &str, tool_input: &str) -> HookRunResult {
-        self.run_commands(
-            HookEvent::PreToolUse,
-            &self.hooks.pre_tool_use,
-            tool_name,
-            tool_input,
-            None,
-            false,
-        )
-    }
-
-    #[must_use]
-    pub fn run_post_tool_use(
-        &self,
-        tool_name: &str,
-        tool_input: &str,
-        tool_output: &str,
-        is_error: bool,
-    ) -> HookRunResult {
-        self.run_commands(
-            HookEvent::PostToolUse,
-            &self.hooks.post_tool_use,
-            tool_name,
-            tool_input,
-            Some(tool_output),
-            is_error,
-        )
-    }
-
-    fn run_commands(
-        &self,
-        event: HookEvent,
-        commands: &[String],
-        tool_name: &str,
-        tool_input: &str,
-        tool_output: Option<&str>,
-        is_error: bool,
-    ) -> HookRunResult {
-        if commands.is_empty() {
-            return HookRunResult::allow(Vec::new());
-        }
-
-        let payload = json!({
-            "hook_event_name": event.as_str(),
-            "tool_name": tool_name,
-            "tool_input": parse_tool_input(tool_input),
-            "tool_input_json": tool_input,
-            "tool_output": tool_output,
-            "tool_result_is_error": is_error,
-        })
-        .to_string();
-
-        let mut messages = Vec::new();
-
-        for command in commands {
-            match self.run_command(
-                command,
-                event,
-                tool_name,
-                tool_input,
-                tool_output,
-                is_error,
-                &payload,
-            ) {
-                HookCommandOutcome::Allow { message } => {
-                    if let Some(message) = message {
-                        messages.push(message);
-                    }
-                }
-                HookCommandOutcome::Deny { message } => {
-                    messages.push(message.unwrap_or_else(|| {
-                        format!("{} hook denied tool `{tool_name}`", event.as_str())
-                    }));
-                    return HookRunResult {
-                        denied: true,
-                        messages,
-                    };
-                }
-                HookCommandOutcome::Warn { message } => messages.push(message),
-            }
-        }
-
-        HookRunResult::allow(messages)
-    }
-
-    #[allow(clippy::too_many_arguments, clippy::unused_self)]
-    fn run_command(
-        &self,
-        command: &str,
-        event: HookEvent,
-        tool_name: &str,
-        tool_input: &str,
-        tool_output: Option<&str>,
-        is_error: bool,
-        payload: &str,
-    ) -> HookCommandOutcome {
-        let mut child = shell_command(command);
-        child.stdin(std::process::Stdio::piped());
-        child.stdout(std::process::Stdio::piped());
-        child.stderr(std::process::Stdio::piped());
-        child.env("HOOK_EVENT", event.as_str());
-        child.env("HOOK_TOOL_NAME", tool_name);
-        child.env("HOOK_TOOL_INPUT", tool_input);
-        child.env("HOOK_TOOL_IS_ERROR", if is_error { "1" } else { "0" });
-        if let Some(tool_output) = tool_output {
-            child.env("HOOK_TOOL_OUTPUT", tool_output);
-        }
-
-        match child.output_with_stdin(payload.as_bytes()) {
-            Ok(output) => {
-                let stdout = String::from_utf8_lossy(&output.stdout).trim().to_string();
-                let stderr = String::from_utf8_lossy(&output.stderr).trim().to_string();
-                let message = (!stdout.is_empty()).then_some(stdout);
-                match output.status.code() {
-                    Some(0) => HookCommandOutcome::Allow { message },
-                    Some(2) => HookCommandOutcome::Deny { message },
-                    Some(code) => HookCommandOutcome::Warn {
-                        message: format_hook_warning(
-                            command,
-                            code,
-                            message.as_deref(),
-                            stderr.as_str(),
-                        ),
-                    },
-                    None => HookCommandOutcome::Warn {
-                        message: format!(
-                            "{} hook `{command}` terminated by signal while handling `{tool_name}`",
-                            event.as_str()
-                        ),
-                    },
-                }
-            }
-            Err(error) => HookCommandOutcome::Warn {
-                message: format!(
-                    "{} hook `{command}` failed to start for `{tool_name}`: {error}",
-                    event.as_str()
-                ),
-            },
-        }
-    }
-}
-
-enum HookCommandOutcome {
-    Allow { message: Option<String> },
-    Deny { message: Option<String> },
-    Warn { message: String },
-}
-
-fn parse_tool_input(tool_input: &str) -> serde_json::Value {
-    serde_json::from_str(tool_input).unwrap_or_else(|_| json!({ "raw": tool_input }))
-}
-
-fn format_hook_warning(command: &str, code: i32, stdout: Option<&str>, stderr: &str) -> String {
-    let mut message =
-        format!("Hook `{command}` exited with status {code}; allowing tool execution to continue");
-    if let Some(stdout) = stdout.filter(|stdout| !stdout.is_empty()) {
-        message.push_str(": ");
-        message.push_str(stdout);
-    } else if !stderr.is_empty() {
-        message.push_str(": ");
-        message.push_str(stderr);
-    }
-    message
-}
-
-fn shell_command(command: &str) -> CommandWithStdin {
-    #[cfg(windows)]
-    let command_builder = {
-        let mut command_builder = Command::new("cmd");
-        command_builder.arg("/C").arg(command);
-        CommandWithStdin::new(command_builder)
-    };
-
-    #[cfg(not(windows))]
-    let command_builder = if Path::new(command).exists() {
-        let mut command_builder = Command::new("sh");
-        command_builder.arg(command);
-        CommandWithStdin::new(command_builder)
-    } else {
-        let mut command_builder = Command::new("sh");
-        command_builder.arg("-lc").arg(command);
-        CommandWithStdin::new(command_builder)
-    };
-
-    command_builder
-}
-
-struct CommandWithStdin {
-    command: Command,
-}
-
-impl CommandWithStdin {
-    fn new(command: Command) -> Self {
-        Self { command }
-    }
-
-    fn stdin(&mut self, cfg: std::process::Stdio) -> &mut Self {
-        self.command.stdin(cfg);
-        self
-    }
-
-    fn stdout(&mut self, cfg: std::process::Stdio) -> &mut Self {
-        self.command.stdout(cfg);
-        self
-    }
-
-    fn stderr(&mut self, cfg: std::process::Stdio) -> &mut Self {
-        self.command.stderr(cfg);
-        self
-    }
-
-    fn env<K, V>(&mut self, key: K, value: V) -> &mut Self
-    where
-        K: AsRef<OsStr>,
-        V: AsRef<OsStr>,
-    {
-        self.command.env(key, value);
-        self
-    }
-
-    fn output_with_stdin(&mut self, stdin: &[u8]) -> std::io::Result<std::process::Output> {
-        let mut child = self.command.spawn()?;
-        if let Some(mut child_stdin) = child.stdin.take() {
-            use std::io::Write as _;
-            child_stdin.write_all(stdin)?;
-        }
-        child.wait_with_output()
-    }
-}
-
-#[cfg(test)]
-mod tests {
-    use super::{HookRunResult, HookRunner};
-    use crate::{PluginManager, PluginManagerConfig};
-    use std::fs;
-    use std::path::{Path, PathBuf};
-    use std::time::{SystemTime, UNIX_EPOCH};
-
-    fn temp_dir(label: &str) -> PathBuf {
-        let nanos = SystemTime::now()
-            .duration_since(UNIX_EPOCH)
-            .expect("time should be after epoch")
-            .as_nanos();
-        std::env::temp_dir().join(format!("plugins-hook-runner-{label}-{nanos}"))
-    }
-
-    fn write_hook_plugin(root: &Path, name: &str, pre_message: &str, post_message: &str) {
-        fs::create_dir_all(root.join(".claude-plugin")).expect("manifest dir");
-        fs::create_dir_all(root.join("hooks")).expect("hooks dir");
-        fs::write(
-            root.join("hooks").join("pre.sh"),
-            format!("#!/bin/sh\nprintf '%s\\n' '{pre_message}'\n"),
-        )
-        .expect("write pre hook");
-        fs::write(
-            root.join("hooks").join("post.sh"),
-            format!("#!/bin/sh\nprintf '%s\\n' '{post_message}'\n"),
-        )
-        .expect("write post hook");
-        fs::write(
-            root.join(".claude-plugin").join("plugin.json"),
-            format!(
-                "{{\n  \"name\": \"{name}\",\n  \"version\": \"1.0.0\",\n  \"description\": \"hook plugin\",\n  \"hooks\": {{\n    \"PreToolUse\": [\"./hooks/pre.sh\"],\n    \"PostToolUse\": [\"./hooks/post.sh\"]\n  }}\n}}"
-            ),
-        )
-        .expect("write plugin manifest");
-    }
-
-    #[test]
-    fn collects_and_runs_hooks_from_enabled_plugins() {
-        let config_home = temp_dir("config");
-        let first_source_root = temp_dir("source-a");
-        let second_source_root = temp_dir("source-b");
-        write_hook_plugin(
-            &first_source_root,
-            "first",
-            "plugin pre one",
-            "plugin post one",
-        );
-        write_hook_plugin(
-            &second_source_root,
-            "second",
-            "plugin pre two",
-            "plugin post two",
-        );
-
-        let mut manager = PluginManager::new(PluginManagerConfig::new(&config_home));
-        manager
-            .install(first_source_root.to_str().expect("utf8 path"))
-            .expect("first plugin install should succeed");
-        manager
-            .install(second_source_root.to_str().expect("utf8 path"))
-            .expect("second plugin install should succeed");
-        let registry = manager.plugin_registry().expect("registry should build");
-
-        let runner = HookRunner::from_registry(&registry).expect("plugin hooks should load");
-
-        assert_eq!(
-            runner.run_pre_tool_use("Read", r#"{"path":"README.md"}"#),
-            HookRunResult::allow(vec![
-                "plugin pre one".to_string(),
-                "plugin pre two".to_string(),
-            ])
-        );
-        assert_eq!(
-            runner.run_post_tool_use("Read", r#"{"path":"README.md"}"#, "ok", false),
-            HookRunResult::allow(vec![
-                "plugin post one".to_string(),
-                "plugin post two".to_string(),
-            ])
-        );
-
-        let _ = fs::remove_dir_all(config_home);
-        let _ = fs::remove_dir_all(first_source_root);
-        let _ = fs::remove_dir_all(second_source_root);
-    }
-
-    #[test]
-    fn pre_tool_use_denies_when_plugin_hook_exits_two() {
-        let runner = HookRunner::new(crate::PluginHooks {
-            pre_tool_use: vec!["printf 'blocked by plugin'; exit 2".to_string()],
-            post_tool_use: Vec::new(),
-        });
-
-        let result = runner.run_pre_tool_use("Bash", r#"{"command":"pwd"}"#);
-
-        assert!(result.is_denied());
-        assert_eq!(result.messages(), &["blocked by plugin".to_string()]);
-    }
-}

rust/crates/runtime/Cargo.toml

@@ -8,7 +8,6 @@ publish.workspace = true
 [dependencies]
 sha2 = "0.10"
 glob = "0.3"
-plugins = { path = "../plugins" }
 regex = "1"
 serde = { version = "1", features = ["derive"] }
 serde_json = "1"

rust/crates/runtime/src/compact.rs

@@ -1,10 +1,5 @@
 use crate::session::{ContentBlock, ConversationMessage, MessageRole, Session};
 
-const COMPACT_CONTINUATION_PREAMBLE: &str =
-    "This session is being continued from a previous conversation that ran out of context. The summary below covers the earlier portion of the conversation.\n\n";
-const COMPACT_RECENT_MESSAGES_NOTE: &str = "Recent messages are preserved verbatim.";
-const COMPACT_DIRECT_RESUME_INSTRUCTION: &str = "Continue the conversation from where it left off without asking the user any further questions. Resume directly — do not acknowledge the summary, do not recap what was happening, and do not preface with continuation text.";
-
 #[derive(Debug, Clone, Copy, PartialEq, Eq)]
 pub struct CompactionConfig {
     pub preserve_recent_messages: usize,
@@ -35,15 +30,8 @@ pub fn estimate_session_tokens(session: &Session) -> usize {
 
 #[must_use]
 pub fn should_compact(session: &Session, config: CompactionConfig) -> bool {
-    let start = compacted_summary_prefix_len(session);
+    session.messages.len() > config.preserve_recent_messages
-    let compactable = &session.messages[start..];
+        && estimate_session_tokens(session) >= config.max_estimated_tokens
-
-    compactable.len() > config.preserve_recent_messages
-        && compactable
-            .iter()
-            .map(estimate_message_tokens)
-            .sum::<usize>()
-            >= config.max_estimated_tokens
 }
 
 #[must_use]
@@ -68,18 +56,16 @@ pub fn get_compact_continuation_message(
     recent_messages_preserved: bool,
 ) -> String {
     let mut base = format!(
-        "{COMPACT_CONTINUATION_PREAMBLE}{}",
+        "This session is being continued from a previous conversation that ran out of context. The summary below covers the earlier portion of the conversation.\n\n{}",
         format_compact_summary(summary)
     );
 
     if recent_messages_preserved {
-        base.push_str("\n\n");
+        base.push_str("\n\nRecent messages are preserved verbatim.");
-        base.push_str(COMPACT_RECENT_MESSAGES_NOTE);
     }
 
     if suppress_follow_up_questions {
-        base.push('\n');
+        base.push_str("\nContinue the conversation from where it left off without asking the user any further questions. Resume directly — do not acknowledge the summary, do not recap what was happening, and do not preface with continuation text.");
-        base.push_str(COMPACT_DIRECT_RESUME_INSTRUCTION);
     }
 
     base
@@ -96,19 +82,13 @@ pub fn compact_session(session: &Session, config: CompactionConfig) -> Compactio
         };
     }
 
-    let existing_summary = session
-        .messages
-        .first()
-        .and_then(extract_existing_compacted_summary);
-    let compacted_prefix_len = usize::from(existing_summary.is_some());
     let keep_from = session
         .messages
         .len()
         .saturating_sub(config.preserve_recent_messages);
-    let removed = &session.messages[compacted_prefix_len..keep_from];
+    let removed = &session.messages[..keep_from];
     let preserved = session.messages[keep_from..].to_vec();
-    let summary =
+    let summary = summarize_messages(removed);
-        merge_compact_summaries(existing_summary.as_deref(), &summarize_messages(removed));
     let formatted_summary = format_compact_summary(&summary);
     let continuation = get_compact_continuation_message(&summary, true, !preserved.is_empty());
 
@@ -130,16 +110,6 @@ pub fn compact_session(session: &Session, config: CompactionConfig) -> Compactio
     }
 }
 
-fn compacted_summary_prefix_len(session: &Session) -> usize {
-    usize::from(
-        session
-            .messages
-            .first()
-            .and_then(extract_existing_compacted_summary)
-            .is_some(),
-    )
-}
-
 fn summarize_messages(messages: &[ConversationMessage]) -> String {
     let user_messages = messages
         .iter()
@@ -227,41 +197,6 @@ fn summarize_messages(messages: &[ConversationMessage]) -> String {
     lines.join("\n")
 }
 
-fn merge_compact_summaries(existing_summary: Option<&str>, new_summary: &str) -> String {
-    let Some(existing_summary) = existing_summary else {
-        return new_summary.to_string();
-    };
-
-    let previous_highlights = extract_summary_highlights(existing_summary);
-    let new_formatted_summary = format_compact_summary(new_summary);
-    let new_highlights = extract_summary_highlights(&new_formatted_summary);
-    let new_timeline = extract_summary_timeline(&new_formatted_summary);
-
-    let mut lines = vec!["<summary>".to_string(), "Conversation summary:".to_string()];
-
-    if !previous_highlights.is_empty() {
-        lines.push("- Previously compacted context:".to_string());
-        lines.extend(
-            previous_highlights
-                .into_iter()
-                .map(|line| format!("  {line}")),
-        );
-    }
-
-    if !new_highlights.is_empty() {
-        lines.push("- Newly compacted context:".to_string());
-        lines.extend(new_highlights.into_iter().map(|line| format!("  {line}")));
-    }
-
-    if !new_timeline.is_empty() {
-        lines.push("- Key timeline:".to_string());
-        lines.extend(new_timeline.into_iter().map(|line| format!("  {line}")));
-    }
-
-    lines.push("</summary>".to_string());
-    lines.join("\n")
-}
-
 fn summarize_block(block: &ContentBlock) -> String {
     let raw = match block {
         ContentBlock::Text { text } => text.clone(),
@@ -439,71 +374,11 @@ fn collapse_blank_lines(content: &str) -> String {
     result
 }
 
-fn extract_existing_compacted_summary(message: &ConversationMessage) -> Option<String> {
-    if message.role != MessageRole::System {
-        return None;
-    }
-
-    let text = first_text_block(message)?;
-    let summary = text.strip_prefix(COMPACT_CONTINUATION_PREAMBLE)?;
-    let summary = summary
-        .split_once(&format!("\n\n{COMPACT_RECENT_MESSAGES_NOTE}"))
-        .map_or(summary, |(value, _)| value);
-    let summary = summary
-        .split_once(&format!("\n{COMPACT_DIRECT_RESUME_INSTRUCTION}"))
-        .map_or(summary, |(value, _)| value);
-    Some(summary.trim().to_string())
-}
-
-fn extract_summary_highlights(summary: &str) -> Vec<String> {
-    let mut lines = Vec::new();
-    let mut in_timeline = false;
-
-    for line in format_compact_summary(summary).lines() {
-        let trimmed = line.trim_end();
-        if trimmed.is_empty() || trimmed == "Summary:" || trimmed == "Conversation summary:" {
-            continue;
-        }
-        if trimmed == "- Key timeline:" {
-            in_timeline = true;
-            continue;
-        }
-        if in_timeline {
-            continue;
-        }
-        lines.push(trimmed.to_string());
-    }
-
-    lines
-}
-
-fn extract_summary_timeline(summary: &str) -> Vec<String> {
-    let mut lines = Vec::new();
-    let mut in_timeline = false;
-
-    for line in format_compact_summary(summary).lines() {
-        let trimmed = line.trim_end();
-        if trimmed == "- Key timeline:" {
-            in_timeline = true;
-            continue;
-        }
-        if !in_timeline {
-            continue;
-        }
-        if trimmed.is_empty() {
-            break;
-        }
-        lines.push(trimmed.to_string());
-    }
-
-    lines
-}
-
 #[cfg(test)]
 mod tests {
     use super::{
         collect_key_files, compact_session, estimate_session_tokens, format_compact_summary,
-        get_compact_continuation_message, infer_pending_work, should_compact, CompactionConfig,
+        infer_pending_work, should_compact, CompactionConfig,
     };
     use crate::session::{ContentBlock, ConversationMessage, MessageRole, Session};
 
@@ -578,98 +453,6 @@ mod tests {
         );
     }
 
-    #[test]
-    fn keeps_previous_compacted_context_when_compacting_again() {
-        let initial_session = Session {
-            version: 1,
-            messages: vec![
-                ConversationMessage::user_text("Investigate rust/crates/runtime/src/compact.rs"),
-                ConversationMessage::assistant(vec![ContentBlock::Text {
-                    text: "I will inspect the compact flow.".to_string(),
-                }]),
-                ConversationMessage::user_text(
-                    "Also update rust/crates/runtime/src/conversation.rs",
-                ),
-                ConversationMessage::assistant(vec![ContentBlock::Text {
-                    text: "Next: preserve prior summary context during auto compact.".to_string(),
-                }]),
-            ],
-        };
-        let config = CompactionConfig {
-            preserve_recent_messages: 2,
-            max_estimated_tokens: 1,
-        };
-
-        let first = compact_session(&initial_session, config);
-        let mut follow_up_messages = first.compacted_session.messages.clone();
-        follow_up_messages.extend([
-            ConversationMessage::user_text("Please add regression tests for compaction."),
-            ConversationMessage::assistant(vec![ContentBlock::Text {
-                text: "Working on regression coverage now.".to_string(),
-            }]),
-        ]);
-
-        let second = compact_session(
-            &Session {
-                version: 1,
-                messages: follow_up_messages,
-            },
-            config,
-        );
-
-        assert!(second
-            .formatted_summary
-            .contains("Previously compacted context:"));
-        assert!(second
-            .formatted_summary
-            .contains("Scope: 2 earlier messages compacted"));
-        assert!(second
-            .formatted_summary
-            .contains("Newly compacted context:"));
-        assert!(second
-            .formatted_summary
-            .contains("Also update rust/crates/runtime/src/conversation.rs"));
-        assert!(matches!(
-            &second.compacted_session.messages[0].blocks[0],
-            ContentBlock::Text { text }
-                if text.contains("Previously compacted context:")
-                    && text.contains("Newly compacted context:")
-        ));
-        assert!(matches!(
-            &second.compacted_session.messages[1].blocks[0],
-            ContentBlock::Text { text } if text.contains("Please add regression tests for compaction.")
-        ));
-    }
-
-    #[test]
-    fn ignores_existing_compacted_summary_when_deciding_to_recompact() {
-        let summary = "<summary>Conversation summary:\n- Scope: earlier work preserved.\n- Key timeline:\n  - user: large preserved context\n</summary>";
-        let session = Session {
-            version: 1,
-            messages: vec![
-                ConversationMessage {
-                    role: MessageRole::System,
-                    blocks: vec![ContentBlock::Text {
-                        text: get_compact_continuation_message(summary, true, true),
-                    }],
-                    usage: None,
-                },
-                ConversationMessage::user_text("tiny"),
-                ConversationMessage::assistant(vec![ContentBlock::Text {
-                    text: "recent".to_string(),
-                }]),
-            ],
-        };
-
-        assert!(!should_compact(
-            &session,
-            CompactionConfig {
-                preserve_recent_messages: 2,
-                max_estimated_tokens: 1,
-            }
-        ));
-    }
-
     #[test]
     fn truncates_long_blocks_in_summary() {
         let summary = super::summarize_block(&ContentBlock::Text {

rust/crates/runtime/src/config.rs

@@ -35,19 +35,8 @@ pub struct RuntimeConfig {
     feature_config: RuntimeFeatureConfig,
 }
 
-#[derive(Debug, Clone, PartialEq, Eq, Default)]
-pub struct RuntimePluginConfig {
-    enabled_plugins: BTreeMap<String, bool>,
-    external_directories: Vec<String>,
-    install_root: Option<String>,
-    registry_path: Option<String>,
-    bundled_root: Option<String>,
-}
-
 #[derive(Debug, Clone, PartialEq, Eq, Default)]
 pub struct RuntimeFeatureConfig {
-    hooks: RuntimeHookConfig,
-    plugins: RuntimePluginConfig,
     mcp: McpConfigCollection,
     oauth: Option<OAuthConfig>,
     model: Option<String>,
@@ -55,12 +44,6 @@ pub struct RuntimeFeatureConfig {
     sandbox: SandboxConfig,
 }
 
-#[derive(Debug, Clone, PartialEq, Eq, Default)]
-pub struct RuntimeHookConfig {
-    pre_tool_use: Vec<String>,
-    post_tool_use: Vec<String>,
-}
-
 #[derive(Debug, Clone, PartialEq, Eq, Default)]
 pub struct McpConfigCollection {
     servers: BTreeMap<String, ScopedMcpServerConfig>,
@@ -184,15 +167,13 @@ impl ConfigLoader {
     #[must_use]
     pub fn default_for(cwd: impl Into<PathBuf>) -> Self {
         let cwd = cwd.into();
-        let config_home = default_config_home();
+        let config_home = std::env::var_os("CLAUDE_CONFIG_HOME")
+            .map(PathBuf::from)
+            .or_else(|| std::env::var_os("HOME").map(|home| PathBuf::from(home).join(".claude")))
+            .unwrap_or_else(|| PathBuf::from(".claude"));
         Self { cwd, config_home }
     }
 
-    #[must_use]
-    pub fn config_home(&self) -> &Path {
-        &self.config_home
-    }
-
     #[must_use]
     pub fn discover(&self) -> Vec<ConfigEntry> {
         let user_legacy_path = self.config_home.parent().map_or_else(
@@ -240,8 +221,6 @@ impl ConfigLoader {
         let merged_value = JsonValue::Object(merged.clone());
 
         let feature_config = RuntimeFeatureConfig {
-            hooks: parse_optional_hooks_config(&merged_value)?,
-            plugins: parse_optional_plugin_config(&merged_value)?,
             mcp: McpConfigCollection {
                 servers: mcp_servers,
             },
@@ -299,16 +278,6 @@ impl RuntimeConfig {
         &self.feature_config.mcp
     }
 
-    #[must_use]
-    pub fn hooks(&self) -> &RuntimeHookConfig {
-        &self.feature_config.hooks
-    }
-
-    #[must_use]
-    pub fn plugins(&self) -> &RuntimePluginConfig {
-        &self.feature_config.plugins
-    }
-
     #[must_use]
     pub fn oauth(&self) -> Option<&OAuthConfig> {
         self.feature_config.oauth.as_ref()
@@ -331,28 +300,6 @@ impl RuntimeConfig {
 }
 
 impl RuntimeFeatureConfig {
-    #[must_use]
-    pub fn with_hooks(mut self, hooks: RuntimeHookConfig) -> Self {
-        self.hooks = hooks;
-        self
-    }
-
-    #[must_use]
-    pub fn with_plugins(mut self, plugins: RuntimePluginConfig) -> Self {
-        self.plugins = plugins;
-        self
-    }
-
-    #[must_use]
-    pub fn hooks(&self) -> &RuntimeHookConfig {
-        &self.hooks
-    }
-
-    #[must_use]
-    pub fn plugins(&self) -> &RuntimePluginConfig {
-        &self.plugins
-    }
-
     #[must_use]
     pub fn mcp(&self) -> &McpConfigCollection {
         &self.mcp
@@ -379,85 +326,6 @@ impl RuntimeFeatureConfig {
     }
 }
 
-impl RuntimePluginConfig {
-    #[must_use]
-    pub fn enabled_plugins(&self) -> &BTreeMap<String, bool> {
-        &self.enabled_plugins
-    }
-
-    #[must_use]
-    pub fn external_directories(&self) -> &[String] {
-        &self.external_directories
-    }
-
-    #[must_use]
-    pub fn install_root(&self) -> Option<&str> {
-        self.install_root.as_deref()
-    }
-
-    #[must_use]
-    pub fn registry_path(&self) -> Option<&str> {
-        self.registry_path.as_deref()
-    }
-
-    #[must_use]
-    pub fn bundled_root(&self) -> Option<&str> {
-        self.bundled_root.as_deref()
-    }
-
-    pub fn set_plugin_state(&mut self, plugin_id: String, enabled: bool) {
-        self.enabled_plugins.insert(plugin_id, enabled);
-    }
-
-    #[must_use]
-    pub fn state_for(&self, plugin_id: &str, default_enabled: bool) -> bool {
-        self.enabled_plugins
-            .get(plugin_id)
-            .copied()
-            .unwrap_or(default_enabled)
-    }
-}
-
-#[must_use]
-pub fn default_config_home() -> PathBuf {
-    std::env::var_os("CLAUDE_CONFIG_HOME")
-        .map(PathBuf::from)
-        .or_else(|| std::env::var_os("HOME").map(|home| PathBuf::from(home).join(".claude")))
-        .unwrap_or_else(|| PathBuf::from(".claude"))
-}
-
-impl RuntimeHookConfig {
-    #[must_use]
-    pub fn new(pre_tool_use: Vec<String>, post_tool_use: Vec<String>) -> Self {
-        Self {
-            pre_tool_use,
-            post_tool_use,
-        }
-    }
-
-    #[must_use]
-    pub fn pre_tool_use(&self) -> &[String] {
-        &self.pre_tool_use
-    }
-
-    #[must_use]
-    pub fn post_tool_use(&self) -> &[String] {
-        &self.post_tool_use
-    }
-
-    #[must_use]
-    pub fn merged(&self, other: &Self) -> Self {
-        let mut merged = self.clone();
-        merged.extend(other);
-        merged
-    }
-
-    pub fn extend(&mut self, other: &Self) {
-        extend_unique(&mut self.pre_tool_use, other.pre_tool_use());
-        extend_unique(&mut self.post_tool_use, other.post_tool_use());
-    }
-}
-
 impl McpConfigCollection {
     #[must_use]
     pub fn servers(&self) -> &BTreeMap<String, ScopedMcpServerConfig> {
@@ -556,52 +424,6 @@ fn parse_optional_model(root: &JsonValue) -> Option<String> {
         .map(ToOwned::to_owned)
 }
 
-fn parse_optional_hooks_config(root: &JsonValue) -> Result<RuntimeHookConfig, ConfigError> {
-    let Some(object) = root.as_object() else {
-        return Ok(RuntimeHookConfig::default());
-    };
-    let Some(hooks_value) = object.get("hooks") else {
-        return Ok(RuntimeHookConfig::default());
-    };
-    let hooks = expect_object(hooks_value, "merged settings.hooks")?;
-    Ok(RuntimeHookConfig {
-        pre_tool_use: optional_string_array(hooks, "PreToolUse", "merged settings.hooks")?
-            .unwrap_or_default(),
-        post_tool_use: optional_string_array(hooks, "PostToolUse", "merged settings.hooks")?
-            .unwrap_or_default(),
-    })
-}
-
-fn parse_optional_plugin_config(root: &JsonValue) -> Result<RuntimePluginConfig, ConfigError> {
-    let Some(object) = root.as_object() else {
-        return Ok(RuntimePluginConfig::default());
-    };
-
-    let mut config = RuntimePluginConfig::default();
-    if let Some(enabled_plugins) = object.get("enabledPlugins") {
-        config.enabled_plugins = parse_bool_map(enabled_plugins, "merged settings.enabledPlugins")?;
-    }
-
-    let Some(plugins_value) = object.get("plugins") else {
-        return Ok(config);
-    };
-    let plugins = expect_object(plugins_value, "merged settings.plugins")?;
-
-    if let Some(enabled_value) = plugins.get("enabled") {
-        config.enabled_plugins = parse_bool_map(enabled_value, "merged settings.plugins.enabled")?;
-    }
-    config.external_directories =
-        optional_string_array(plugins, "externalDirectories", "merged settings.plugins")?
-            .unwrap_or_default();
-    config.install_root =
-        optional_string(plugins, "installRoot", "merged settings.plugins")?.map(str::to_string);
-    config.registry_path =
-        optional_string(plugins, "registryPath", "merged settings.plugins")?.map(str::to_string);
-    config.bundled_root =
-        optional_string(plugins, "bundledRoot", "merged settings.plugins")?.map(str::to_string);
-    Ok(config)
-}
-
 fn parse_optional_permission_mode(
     root: &JsonValue,
 ) -> Result<Option<ResolvedPermissionMode>, ConfigError> {
@@ -834,24 +656,6 @@ fn optional_u16(
     }
 }
 
-fn parse_bool_map(value: &JsonValue, context: &str) -> Result<BTreeMap<String, bool>, ConfigError> {
-    let Some(map) = value.as_object() else {
-        return Err(ConfigError::Parse(format!(
-            "{context}: expected JSON object"
-        )));
-    };
-    map.iter()
-        .map(|(key, value)| {
-            value
-                .as_bool()
-                .map(|enabled| (key.clone(), enabled))
-                .ok_or_else(|| {
-                    ConfigError::Parse(format!("{context}: field {key} must be a boolean"))
-                })
-        })
-        .collect()
-}
-
 fn optional_string_array(
     object: &BTreeMap<String, JsonValue>,
     key: &str,
@@ -926,18 +730,6 @@ fn deep_merge_objects(
     }
 }
 
-fn extend_unique(target: &mut Vec<String>, values: &[String]) {
-    for value in values {
-        push_unique(target, value.clone());
-    }
-}
-
-fn push_unique(target: &mut Vec<String>, value: String) {
-    if !target.iter().any(|existing| existing == &value) {
-        target.push(value);
-    }
-}
-
 #[cfg(test)]
 mod tests {
     use super::{
@@ -1044,8 +836,6 @@ mod tests {
             .and_then(JsonValue::as_object)
             .expect("hooks object")
             .contains_key("PostToolUse"));
-        assert_eq!(loaded.hooks().pre_tool_use(), &["base".to_string()]);
-        assert_eq!(loaded.hooks().post_tool_use(), &["project".to_string()]);
         assert!(loaded.mcp().get("home").is_some());
         assert!(loaded.mcp().get("project").is_some());
 
@@ -1181,96 +971,6 @@ mod tests {
         fs::remove_dir_all(root).expect("cleanup temp dir");
     }
 
-    #[test]
-    fn parses_plugin_config_from_enabled_plugins() {
-        let root = temp_dir();
-        let cwd = root.join("project");
-        let home = root.join("home").join(".claude");
-        fs::create_dir_all(cwd.join(".claude")).expect("project config dir");
-        fs::create_dir_all(&home).expect("home config dir");
-
-        fs::write(
-            home.join("settings.json"),
-            r#"{
-              "enabledPlugins": {
-                "tool-guard@builtin": true,
-                "sample-plugin@external": false
-              }
-            }"#,
-        )
-        .expect("write user settings");
-
-        let loaded = ConfigLoader::new(&cwd, &home)
-            .load()
-            .expect("config should load");
-
-        assert_eq!(
-            loaded.plugins().enabled_plugins().get("tool-guard@builtin"),
-            Some(&true)
-        );
-        assert_eq!(
-            loaded
-                .plugins()
-                .enabled_plugins()
-                .get("sample-plugin@external"),
-            Some(&false)
-        );
-
-        fs::remove_dir_all(root).expect("cleanup temp dir");
-    }
-
-    #[test]
-    fn parses_plugin_config() {
-        let root = temp_dir();
-        let cwd = root.join("project");
-        let home = root.join("home").join(".claude");
-        fs::create_dir_all(cwd.join(".claude")).expect("project config dir");
-        fs::create_dir_all(&home).expect("home config dir");
-
-        fs::write(
-            home.join("settings.json"),
-            r#"{
-              "enabledPlugins": {
-                "core-helpers@builtin": true
-              },
-              "plugins": {
-                "externalDirectories": ["./external-plugins"],
-                "installRoot": "plugin-cache/installed",
-                "registryPath": "plugin-cache/installed.json",
-                "bundledRoot": "./bundled-plugins"
-              }
-            }"#,
-        )
-        .expect("write plugin settings");
-
-        let loaded = ConfigLoader::new(&cwd, &home)
-            .load()
-            .expect("config should load");
-
-        assert_eq!(
-            loaded
-                .plugins()
-                .enabled_plugins()
-                .get("core-helpers@builtin"),
-            Some(&true)
-        );
-        assert_eq!(
-            loaded.plugins().external_directories(),
-            &["./external-plugins".to_string()]
-        );
-        assert_eq!(
-            loaded.plugins().install_root(),
-            Some("plugin-cache/installed")
-        );
-        assert_eq!(
-            loaded.plugins().registry_path(),
-            Some("plugin-cache/installed.json")
-        );
-        assert_eq!(loaded.plugins().bundled_root(), Some("./bundled-plugins"));
-
-        fs::remove_dir_all(root).expect("cleanup temp dir");
-    }
-
     #[test]
     fn rejects_invalid_mcp_server_shapes() {
         let root = temp_dir();

rust/crates/runtime/src/conversation.rs

@@ -1,20 +1,13 @@
 use std::collections::BTreeMap;
 use std::fmt::{Display, Formatter};
 
-use plugins::{HookRunner as PluginHookRunner, PluginRegistry};
-
 use crate::compact::{
     compact_session, estimate_session_tokens, CompactionConfig, CompactionResult,
 };
-use crate::config::RuntimeFeatureConfig;
-use crate::hooks::HookRunner;
 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 = 200_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>,
@@ -91,12 +84,6 @@ 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> {
@@ -107,26 +94,6 @@ pub struct ConversationRuntime<C, T> {
     system_prompt: Vec<String>,
     max_iterations: usize,
     usage_tracker: UsageTracker,
-    hook_runner: HookRunner,
-    auto_compaction_input_tokens_threshold: u32,
-    plugin_hook_runner: Option<PluginHookRunner>,
-    plugin_registry: Option<PluginRegistry>,
-    plugins_shutdown: bool,
-}
-
-impl<C, T> ConversationRuntime<C, T> {
-    fn shutdown_registered_plugins(&mut self) -> Result<(), RuntimeError> {
-        if self.plugins_shutdown {
-            return Ok(());
-        }
-        if let Some(registry) = &self.plugin_registry {
-            registry
-                .shutdown()
-                .map_err(|error| RuntimeError::new(format!("plugin shutdown failed: {error}")))?;
-        }
-        self.plugins_shutdown = true;
-        Ok(())
-    }
 }
 
 impl<C, T> ConversationRuntime<C, T>
@@ -141,26 +108,6 @@ where
         tool_executor: T,
         permission_policy: PermissionPolicy,
         system_prompt: Vec<String>,
-    ) -> Self {
-        Self::new_with_features(
-            session,
-            api_client,
-            tool_executor,
-            permission_policy,
-            system_prompt,
-            RuntimeFeatureConfig::default(),
-        )
-    }
-
-    #[must_use]
-    #[allow(clippy::needless_pass_by_value)]
-    pub fn new_with_features(
-        session: Session,
-        api_client: C,
-        tool_executor: T,
-        permission_policy: PermissionPolicy,
-        system_prompt: Vec<String>,
-        feature_config: RuntimeFeatureConfig,
     ) -> Self {
         let usage_tracker = UsageTracker::from_session(&session);
         Self {
@@ -171,57 +118,15 @@ where
             system_prompt,
             max_iterations: usize::MAX,
             usage_tracker,
-            hook_runner: HookRunner::from_feature_config(&feature_config),
-            auto_compaction_input_tokens_threshold: auto_compaction_threshold_from_env(),
-            plugin_hook_runner: None,
-            plugin_registry: None,
-            plugins_shutdown: false,
         }
     }
 
-    #[allow(clippy::needless_pass_by_value)]
-    pub fn new_with_plugins(
-        session: Session,
-        api_client: C,
-        tool_executor: T,
-        permission_policy: PermissionPolicy,
-        system_prompt: Vec<String>,
-        feature_config: RuntimeFeatureConfig,
-        plugin_registry: PluginRegistry,
-    ) -> Result<Self, RuntimeError> {
-        let plugin_hook_runner =
-            PluginHookRunner::from_registry(&plugin_registry).map_err(|error| {
-                RuntimeError::new(format!("plugin hook registration failed: {error}"))
-            })?;
-        plugin_registry
-            .initialize()
-            .map_err(|error| RuntimeError::new(format!("plugin initialization failed: {error}")))?;
-        let mut runtime = Self::new_with_features(
-            session,
-            api_client,
-            tool_executor,
-            permission_policy,
-            system_prompt,
-            feature_config,
-        );
-        runtime.plugin_hook_runner = Some(plugin_hook_runner);
-        runtime.plugin_registry = Some(plugin_registry);
-        Ok(runtime)
-    }
-
     #[must_use]
     pub fn with_max_iterations(mut self, max_iterations: usize) -> Self {
         self.max_iterations = max_iterations;
         self
     }
 
-    #[must_use]
-    pub fn with_auto_compaction_input_tokens_threshold(mut self, threshold: u32) -> Self {
-        self.auto_compaction_input_tokens_threshold = threshold;
-        self
-    }
-
-    #[allow(clippy::too_many_lines)]
     pub fn run_turn(
         &mut self,
         user_input: impl Into<String>,
@@ -234,7 +139,6 @@ where
         let mut assistant_messages = Vec::new();
         let mut tool_results = Vec::new();
         let mut iterations = 0;
-        let mut max_turn_input_tokens = 0;
 
         loop {
             iterations += 1;
@@ -251,7 +155,6 @@ where
             let events = self.api_client.stream(request)?;
             let (assistant_message, usage) = build_assistant_message(events)?;
             if let Some(usage) = usage {
-                max_turn_input_tokens = max_turn_input_tokens.max(usage.input_tokens);
                 self.usage_tracker.record(usage);
             }
             let pending_tool_uses = assistant_message
@@ -282,80 +185,19 @@ where
 
                 let result_message = match permission_outcome {
                     PermissionOutcome::Allow => {
-                        let pre_hook_result = self.hook_runner.run_pre_tool_use(&tool_name, &input);
-                        if pre_hook_result.is_denied() {
-                            let deny_message = format!("PreToolUse hook denied tool `{tool_name}`");
-                            ConversationMessage::tool_result(
-                                tool_use_id,
-                                tool_name,
-                                format_hook_message(pre_hook_result.messages(), &deny_message),
-                                true,
-                            )
-                        } else {
-                            let plugin_pre_hook_result =
-                                self.run_plugin_pre_tool_use(&tool_name, &input);
-                            if plugin_pre_hook_result.is_denied() {
-                                let deny_message =
-                                    format!("PreToolUse hook denied tool `{tool_name}`");
-                                let mut messages = pre_hook_result.messages().to_vec();
-                                messages.extend(plugin_pre_hook_result.messages().iter().cloned());
-                                ConversationMessage::tool_result(
-                                    tool_use_id,
-                                    tool_name,
-                                    format_hook_message(&messages, &deny_message),
-                                    true,
-                                )
-                            } else {
-                                let (mut output, mut is_error) =
                         match self.tool_executor.execute(&tool_name, &input) {
-                                        Ok(output) => (output, false),
+                            Ok(output) => ConversationMessage::tool_result(
-                                        Err(error) => (error.to_string(), true),
+                                tool_use_id,
-                                    };
+                                tool_name,
-                                output =
-                                    merge_hook_feedback(pre_hook_result.messages(), output, false);
-                                output = merge_hook_feedback(
-                                    plugin_pre_hook_result.messages(),
                                 output,
                                 false,
-                                );
+                            ),
-
+                            Err(error) => ConversationMessage::tool_result(
-                                let hook_output = output.clone();
-                                let post_hook_result = self.hook_runner.run_post_tool_use(
-                                    &tool_name,
-                                    &input,
-                                    &hook_output,
-                                    is_error,
-                                );
-                                let plugin_post_hook_result = self.run_plugin_post_tool_use(
-                                    &tool_name,
-                                    &input,
-                                    &hook_output,
-                                    is_error,
-                                );
-                                if post_hook_result.is_denied() {
-                                    is_error = true;
-                                }
-                                if plugin_post_hook_result.is_denied() {
-                                    is_error = true;
-                                }
-                                output = merge_hook_feedback(
-                                    post_hook_result.messages(),
-                                    output,
-                                    post_hook_result.is_denied(),
-                                );
-                                output = merge_hook_feedback(
-                                    plugin_post_hook_result.messages(),
-                                    output,
-                                    plugin_post_hook_result.is_denied(),
-                                );
-
-                                ConversationMessage::tool_result(
                                 tool_use_id,
                                 tool_name,
-                                    output,
+                                error.to_string(),
-                                    is_error,
+                                true,
-                                )
+                            ),
-                            }
                         }
                     }
                     PermissionOutcome::Deny { reason } => {
@@ -367,14 +209,11 @@ where
             }
         }
 
-        let auto_compaction = self.maybe_auto_compact(max_turn_input_tokens);
-
         Ok(TurnSummary {
             assistant_messages,
             tool_results,
             iterations,
             usage: self.usage_tracker.cumulative_usage(),
-            auto_compaction,
         })
     }
 
@@ -399,81 +238,9 @@ where
     }
 
     #[must_use]
-    pub fn into_session(mut self) -> Session {
+    pub fn into_session(self) -> Session {
-        let _ = self.shutdown_registered_plugins();
+        self.session
-        std::mem::take(&mut self.session)
     }
-
-    pub fn shutdown_plugins(&mut self) -> Result<(), RuntimeError> {
-        self.shutdown_registered_plugins()
-    }
-
-    fn run_plugin_pre_tool_use(&self, tool_name: &str, input: &str) -> plugins::HookRunResult {
-        self.plugin_hook_runner.as_ref().map_or_else(
-            || plugins::HookRunResult::allow(Vec::new()),
-            |runner| runner.run_pre_tool_use(tool_name, input),
-        )
-    }
-
-    fn run_plugin_post_tool_use(
-        &self,
-        tool_name: &str,
-        input: &str,
-        output: &str,
-        is_error: bool,
-    ) -> plugins::HookRunResult {
-        self.plugin_hook_runner.as_ref().map_or_else(
-            || plugins::HookRunResult::allow(Vec::new()),
-            |runner| runner.run_post_tool_use(tool_name, input, output, is_error),
-        )
-    }
-
-    fn maybe_auto_compact(&mut self, turn_input_tokens: u32) -> Option<AutoCompactionEvent> {
-        if turn_input_tokens < self.auto_compaction_input_tokens_threshold {
-            return None;
-        }
-
-        let result = compact_session(
-            &self.session,
-            CompactionConfig {
-                max_estimated_tokens: usize::try_from(self.auto_compaction_input_tokens_threshold)
-                    .unwrap_or(usize::MAX),
-                ..CompactionConfig::default()
-            },
-        );
-
-        if result.removed_message_count == 0 {
-            return None;
-        }
-
-        self.session = result.compacted_session;
-        Some(AutoCompactionEvent {
-            removed_message_count: result.removed_message_count,
-        })
-    }
-}
-
-impl<C, T> Drop for ConversationRuntime<C, T> {
-    fn drop(&mut self) {
-        let _ = self.shutdown_registered_plugins();
-    }
-}
-
-#[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(
@@ -523,32 +290,6 @@ fn flush_text_block(text: &mut String, blocks: &mut Vec<ContentBlock>) {
     }
 }
 
-fn format_hook_message(messages: &[String], fallback: &str) -> String {
-    if messages.is_empty() {
-        fallback.to_string()
-    } else {
-        messages.join("\n")
-    }
-}
-
-fn merge_hook_feedback(messages: &[String], output: String, denied: bool) -> String {
-    if messages.is_empty() {
-        return output;
-    }
-
-    let mut sections = Vec::new();
-    if !output.trim().is_empty() {
-        sections.push(output);
-    }
-    let label = if denied {
-        "Hook feedback (denied)"
-    } else {
-        "Hook feedback"
-    };
-    sections.push(format!("{label}:\n{}", messages.join("\n")));
-    sections.join("\n\n")
-}
-
 type ToolHandler = Box<dyn FnMut(&str) -> Result<String, ToolError>>;
 
 #[derive(Default)]
@@ -584,12 +325,10 @@ impl ToolExecutor for StaticToolExecutor {
 #[cfg(test)]
 mod tests {
     use super::{
-        parse_auto_compaction_threshold, ApiClient, ApiRequest, AssistantEvent,
+        ApiClient, ApiRequest, AssistantEvent, ConversationRuntime, RuntimeError,
-        AutoCompactionEvent, ConversationRuntime, RuntimeError, StaticToolExecutor,
+        StaticToolExecutor,
-        DEFAULT_AUTO_COMPACTION_INPUT_TOKENS_THRESHOLD,
     };
     use crate::compact::CompactionConfig;
-    use crate::config::{RuntimeFeatureConfig, RuntimeHookConfig};
     use crate::permissions::{
         PermissionMode, PermissionPolicy, PermissionPromptDecision, PermissionPrompter,
         PermissionRequest,
@@ -597,13 +336,7 @@ mod tests {
     use crate::prompt::{ProjectContext, SystemPromptBuilder};
     use crate::session::{ContentBlock, MessageRole, Session};
     use crate::usage::TokenUsage;
-    use plugins::{PluginManager, PluginManagerConfig};
-    use std::fs;
-    #[cfg(unix)]
-    use std::os::unix::fs::PermissionsExt;
-    use std::path::Path;
     use std::path::PathBuf;
-    use std::time::{SystemTime, UNIX_EPOCH};
 
     struct ScriptedApiClient {
         call_count: usize,
@@ -665,68 +398,6 @@ mod tests {
         }
     }
 
-    fn temp_dir(label: &str) -> PathBuf {
-        let nanos = SystemTime::now()
-            .duration_since(UNIX_EPOCH)
-            .expect("time should be after epoch")
-            .as_nanos();
-        std::env::temp_dir().join(format!("runtime-plugin-{label}-{nanos}"))
-    }
-
-    fn write_lifecycle_plugin(root: &Path, name: &str) -> PathBuf {
-        fs::create_dir_all(root.join(".claude-plugin")).expect("manifest dir");
-        fs::create_dir_all(root.join("lifecycle")).expect("lifecycle dir");
-        let log_path = root.join("lifecycle.log");
-        fs::write(
-            root.join("lifecycle").join("init.sh"),
-            "#!/bin/sh\nprintf 'init\\n' >> lifecycle.log\n",
-        )
-        .expect("write init script");
-        fs::write(
-            root.join("lifecycle").join("shutdown.sh"),
-            "#!/bin/sh\nprintf 'shutdown\\n' >> lifecycle.log\n",
-        )
-        .expect("write shutdown script");
-        fs::write(
-            root.join(".claude-plugin").join("plugin.json"),
-            format!(
-                "{{\n  \"name\": \"{name}\",\n  \"version\": \"1.0.0\",\n  \"description\": \"runtime lifecycle plugin\",\n  \"lifecycle\": {{\n    \"Init\": [\"./lifecycle/init.sh\"],\n    \"Shutdown\": [\"./lifecycle/shutdown.sh\"]\n  }}\n}}"
-            ),
-        )
-        .expect("write plugin manifest");
-        log_path
-    }
-
-    fn write_hook_plugin(root: &Path, name: &str, pre_message: &str, post_message: &str) {
-        fs::create_dir_all(root.join(".claude-plugin")).expect("manifest dir");
-        fs::create_dir_all(root.join("hooks")).expect("hooks dir");
-        fs::write(
-            root.join("hooks").join("pre.sh"),
-            format!("#!/bin/sh\nprintf '%s\\n' '{pre_message}'\n"),
-        )
-        .expect("write pre hook");
-        fs::write(
-            root.join("hooks").join("post.sh"),
-            format!("#!/bin/sh\nprintf '%s\\n' '{post_message}'\n"),
-        )
-        .expect("write post hook");
-        #[cfg(unix)]
-        {
-            let exec_mode = fs::Permissions::from_mode(0o755);
-            fs::set_permissions(root.join("hooks").join("pre.sh"), exec_mode.clone())
-                .expect("chmod pre hook");
-            fs::set_permissions(root.join("hooks").join("post.sh"), exec_mode)
-                .expect("chmod post hook");
-        }
-        fs::write(
-            root.join(".claude-plugin").join("plugin.json"),
-            format!(
-                "{{\n  \"name\": \"{name}\",\n  \"version\": \"1.0.0\",\n  \"description\": \"runtime hook plugin\",\n  \"hooks\": {{\n    \"PreToolUse\": [\"./hooks/pre.sh\"],\n    \"PostToolUse\": [\"./hooks/post.sh\"]\n  }}\n}}"
-            ),
-        )
-        .expect("write plugin manifest");
-    }
-
     #[test]
     fn runs_user_to_tool_to_result_loop_end_to_end_and_tracks_usage() {
         let api_client = ScriptedApiClient { call_count: 0 };
@@ -765,7 +436,6 @@ 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 { .. }
@@ -833,288 +503,6 @@ mod tests {
         ));
     }
 
-    #[test]
-    fn denies_tool_use_when_pre_tool_hook_blocks() {
-        struct SingleCallApiClient;
-        impl ApiClient for SingleCallApiClient {
-            fn stream(&mut self, request: ApiRequest) -> Result<Vec<AssistantEvent>, RuntimeError> {
-                if request
-                    .messages
-                    .iter()
-                    .any(|message| message.role == MessageRole::Tool)
-                {
-                    return Ok(vec![
-                        AssistantEvent::TextDelta("blocked".to_string()),
-                        AssistantEvent::MessageStop,
-                    ]);
-                }
-                Ok(vec![
-                    AssistantEvent::ToolUse {
-                        id: "tool-1".to_string(),
-                        name: "blocked".to_string(),
-                        input: r#"{"path":"secret.txt"}"#.to_string(),
-                    },
-                    AssistantEvent::MessageStop,
-                ])
-            }
-        }
-
-        let mut runtime = ConversationRuntime::new_with_features(
-            Session::new(),
-            SingleCallApiClient,
-            StaticToolExecutor::new().register("blocked", |_input| {
-                panic!("tool should not execute when hook denies")
-            }),
-            PermissionPolicy::new(PermissionMode::DangerFullAccess),
-            vec!["system".to_string()],
-            RuntimeFeatureConfig::default().with_hooks(RuntimeHookConfig::new(
-                vec![shell_snippet("printf 'blocked by hook'; exit 2")],
-                Vec::new(),
-            )),
-        );
-
-        let summary = runtime
-            .run_turn("use the tool", None)
-            .expect("conversation should continue after hook denial");
-
-        assert_eq!(summary.tool_results.len(), 1);
-        let ContentBlock::ToolResult {
-            is_error, output, ..
-        } = &summary.tool_results[0].blocks[0]
-        else {
-            panic!("expected tool result block");
-        };
-        assert!(
-            *is_error,
-            "hook denial should produce an error result: {output}"
-        );
-        assert!(
-            output.contains("denied tool") || output.contains("blocked by hook"),
-            "unexpected hook denial output: {output:?}"
-        );
-    }
-
-    #[test]
-    fn appends_post_tool_hook_feedback_to_tool_result() {
-        struct TwoCallApiClient {
-            calls: usize,
-        }
-
-        impl ApiClient for TwoCallApiClient {
-            fn stream(&mut self, request: ApiRequest) -> Result<Vec<AssistantEvent>, RuntimeError> {
-                self.calls += 1;
-                match self.calls {
-                    1 => Ok(vec![
-                        AssistantEvent::ToolUse {
-                            id: "tool-1".to_string(),
-                            name: "add".to_string(),
-                            input: r#"{"lhs":2,"rhs":2}"#.to_string(),
-                        },
-                        AssistantEvent::MessageStop,
-                    ]),
-                    2 => {
-                        assert!(request
-                            .messages
-                            .iter()
-                            .any(|message| message.role == MessageRole::Tool));
-                        Ok(vec![
-                            AssistantEvent::TextDelta("done".to_string()),
-                            AssistantEvent::MessageStop,
-                        ])
-                    }
-                    _ => Err(RuntimeError::new("unexpected extra API call")),
-                }
-            }
-        }
-
-        let mut runtime = ConversationRuntime::new_with_features(
-            Session::new(),
-            TwoCallApiClient { calls: 0 },
-            StaticToolExecutor::new().register("add", |_input| Ok("4".to_string())),
-            PermissionPolicy::new(PermissionMode::DangerFullAccess),
-            vec!["system".to_string()],
-            RuntimeFeatureConfig::default().with_hooks(RuntimeHookConfig::new(
-                vec![shell_snippet("printf 'pre hook ran'")],
-                vec![shell_snippet("printf 'post hook ran'")],
-            )),
-        );
-
-        let summary = runtime
-            .run_turn("use add", None)
-            .expect("tool loop succeeds");
-
-        assert_eq!(summary.tool_results.len(), 1);
-        let ContentBlock::ToolResult {
-            is_error, output, ..
-        } = &summary.tool_results[0].blocks[0]
-        else {
-            panic!("expected tool result block");
-        };
-        assert!(
-            !*is_error,
-            "post hook should preserve non-error result: {output:?}"
-        );
-        assert!(
-            output.contains('4'),
-            "tool output missing value: {output:?}"
-        );
-        assert!(
-            output.contains("pre hook ran"),
-            "tool output missing pre hook feedback: {output:?}"
-        );
-        assert!(
-            output.contains("post hook ran"),
-            "tool output missing post hook feedback: {output:?}"
-        );
-    }
-
-    #[test]
-    fn initializes_and_shuts_down_plugins_with_runtime_lifecycle() {
-        let config_home = temp_dir("config");
-        let source_root = temp_dir("source");
-        let _ = write_lifecycle_plugin(&source_root, "runtime-lifecycle");
-
-        let mut manager = PluginManager::new(PluginManagerConfig::new(&config_home));
-        let install = manager
-            .install(source_root.to_str().expect("utf8 path"))
-            .expect("install should succeed");
-        let log_path = install.install_path.join("lifecycle.log");
-        let registry = manager.plugin_registry().expect("registry should load");
-
-        {
-            let runtime = ConversationRuntime::new_with_plugins(
-                Session::new(),
-                ScriptedApiClient { call_count: 0 },
-                StaticToolExecutor::new().register("add", |_input| Ok("4".to_string())),
-                PermissionPolicy::new(PermissionMode::WorkspaceWrite),
-                vec!["system".to_string()],
-                RuntimeFeatureConfig::default(),
-                registry,
-            )
-            .expect("runtime should initialize plugins");
-
-            let log = fs::read_to_string(&log_path).expect("init log should exist");
-            assert_eq!(log, "init\n");
-            drop(runtime);
-        }
-
-        let log = fs::read_to_string(&log_path).expect("shutdown log should exist");
-        assert_eq!(log, "init\nshutdown\n");
-
-        let _ = fs::remove_dir_all(config_home);
-        let _ = fs::remove_dir_all(source_root);
-    }
-
-    #[test]
-    fn executes_hooks_from_installed_plugins_during_tool_use() {
-        struct TwoCallApiClient {
-            calls: usize,
-        }
-
-        impl ApiClient for TwoCallApiClient {
-            fn stream(&mut self, request: ApiRequest) -> Result<Vec<AssistantEvent>, RuntimeError> {
-                self.calls += 1;
-                match self.calls {
-                    1 => Ok(vec![
-                        AssistantEvent::ToolUse {
-                            id: "tool-1".to_string(),
-                            name: "add".to_string(),
-                            input: r#"{"lhs":2,"rhs":2}"#.to_string(),
-                        },
-                        AssistantEvent::MessageStop,
-                    ]),
-                    2 => {
-                        assert!(request
-                            .messages
-                            .iter()
-                            .any(|message| message.role == MessageRole::Tool));
-                        Ok(vec![
-                            AssistantEvent::TextDelta("done".to_string()),
-                            AssistantEvent::MessageStop,
-                        ])
-                    }
-                    _ => Err(RuntimeError::new("unexpected extra API call")),
-                }
-            }
-        }
-
-        let config_home = temp_dir("hook-config");
-        let first_source_root = temp_dir("hook-source-a");
-        let second_source_root = temp_dir("hook-source-b");
-        write_hook_plugin(
-            &first_source_root,
-            "first",
-            "plugin pre one",
-            "plugin post one",
-        );
-        write_hook_plugin(
-            &second_source_root,
-            "second",
-            "plugin pre two",
-            "plugin post two",
-        );
-
-        let mut manager = PluginManager::new(PluginManagerConfig::new(&config_home));
-        manager
-            .install(first_source_root.to_str().expect("utf8 path"))
-            .expect("first plugin install should succeed");
-        manager
-            .install(second_source_root.to_str().expect("utf8 path"))
-            .expect("second plugin install should succeed");
-        let registry = manager.plugin_registry().expect("registry should load");
-
-        let mut runtime = ConversationRuntime::new_with_plugins(
-            Session::new(),
-            TwoCallApiClient { calls: 0 },
-            StaticToolExecutor::new().register("add", |_input| Ok("4".to_string())),
-            PermissionPolicy::new(PermissionMode::DangerFullAccess),
-            vec!["system".to_string()],
-            RuntimeFeatureConfig::default(),
-            registry,
-        )
-        .expect("runtime should load plugin hooks");
-
-        let summary = runtime
-            .run_turn("use add", None)
-            .expect("tool loop succeeds");
-
-        assert_eq!(summary.tool_results.len(), 1);
-        let ContentBlock::ToolResult {
-            is_error, output, ..
-        } = &summary.tool_results[0].blocks[0]
-        else {
-            panic!("expected tool result block");
-        };
-        assert!(
-            !*is_error,
-            "plugin hooks should not force an error: {output:?}"
-        );
-        assert!(
-            output.contains('4'),
-            "tool output missing value: {output:?}"
-        );
-        assert!(
-            output.contains("plugin pre one"),
-            "tool output missing first pre hook feedback: {output:?}"
-        );
-        assert!(
-            output.contains("plugin pre two"),
-            "tool output missing second pre hook feedback: {output:?}"
-        );
-        assert!(
-            output.contains("plugin post one"),
-            "tool output missing first post hook feedback: {output:?}"
-        );
-        assert!(
-            output.contains("plugin post two"),
-            "tool output missing second post hook feedback: {output:?}"
-        );
-
-        let _ = fs::remove_dir_all(config_home);
-        let _ = fs::remove_dir_all(first_source_root);
-        let _ = fs::remove_dir_all(second_source_root);
-    }
-
     #[test]
     fn reconstructs_usage_tracker_from_restored_session() {
         struct SimpleApi;
@@ -1193,187 +581,4 @@ mod tests {
             MessageRole::System
         );
     }
-
-    #[cfg(windows)]
-    fn shell_snippet(script: &str) -> String {
-        script.replace('\'', "\"")
-    }
-
-    #[cfg(not(windows))]
-    fn shell_snippet(script: &str) -> String {
-        script.to_string()
-    }
-
-    #[test]
-    fn auto_compacts_when_turn_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 ".repeat(30_000)),
-                crate::session::ConversationMessage::assistant(vec![ContentBlock::Text {
-                    text: "two ".repeat(30_000),
-                }]),
-                crate::session::ConversationMessage::user_text("three ".repeat(30_000)),
-                crate::session::ConversationMessage::assistant(vec![ContentBlock::Text {
-                    text: "four ".repeat(30_000),
-                }]),
-            ],
-        };
-
-        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 auto_compaction_does_not_repeat_after_context_is_already_compacted() {
-        struct SequentialUsageApi {
-            call_count: usize,
-        }
-
-        impl ApiClient for SequentialUsageApi {
-            fn stream(
-                &mut self,
-                _request: ApiRequest,
-            ) -> Result<Vec<AssistantEvent>, RuntimeError> {
-                self.call_count += 1;
-                let input_tokens = if self.call_count == 1 { 120_000 } else { 64 };
-                Ok(vec![
-                    AssistantEvent::TextDelta("done".to_string()),
-                    AssistantEvent::Usage(TokenUsage {
-                        input_tokens,
-                        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 ".repeat(30_000)),
-                crate::session::ConversationMessage::assistant(vec![ContentBlock::Text {
-                    text: "two ".repeat(30_000),
-                }]),
-                crate::session::ConversationMessage::user_text("three ".repeat(30_000)),
-                crate::session::ConversationMessage::assistant(vec![ContentBlock::Text {
-                    text: "four ".repeat(30_000),
-                }]),
-            ],
-        };
-
-        let mut runtime = ConversationRuntime::new(
-            session,
-            SequentialUsageApi { call_count: 0 },
-            StaticToolExecutor::new(),
-            PermissionPolicy::new(PermissionMode::DangerFullAccess),
-            vec!["system".to_string()],
-        )
-        .with_auto_compaction_input_tokens_threshold(100_000);
-
-        let first = runtime
-            .run_turn("trigger", None)
-            .expect("first turn should succeed");
-        assert_eq!(
-            first.auto_compaction,
-            Some(AutoCompactionEvent {
-                removed_message_count: 2,
-            })
-        );
-
-        let second = runtime
-            .run_turn("continue", None)
-            .expect("second turn should succeed");
-        assert_eq!(second.auto_compaction, None);
-        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/hooks.rs

@@ -1,355 +0,0 @@
-use std::ffi::OsStr;
-use std::path::Path;
-use std::process::Command;
-
-use serde_json::json;
-
-use crate::config::{RuntimeFeatureConfig, RuntimeHookConfig};
-
-#[derive(Debug, Clone, Copy, PartialEq, Eq)]
-pub enum HookEvent {
-    PreToolUse,
-    PostToolUse,
-}
-
-impl HookEvent {
-    fn as_str(self) -> &'static str {
-        match self {
-            Self::PreToolUse => "PreToolUse",
-            Self::PostToolUse => "PostToolUse",
-        }
-    }
-}
-
-#[derive(Debug, Clone, PartialEq, Eq)]
-pub struct HookRunResult {
-    denied: bool,
-    messages: Vec<String>,
-}
-
-impl HookRunResult {
-    #[must_use]
-    pub fn allow(messages: Vec<String>) -> Self {
-        Self {
-            denied: false,
-            messages,
-        }
-    }
-
-    #[must_use]
-    pub fn is_denied(&self) -> bool {
-        self.denied
-    }
-
-    #[must_use]
-    pub fn messages(&self) -> &[String] {
-        &self.messages
-    }
-}
-
-#[derive(Debug, Clone, PartialEq, Eq, Default)]
-pub struct HookRunner {
-    config: RuntimeHookConfig,
-}
-
-impl HookRunner {
-    #[must_use]
-    pub fn new(config: RuntimeHookConfig) -> Self {
-        Self { config }
-    }
-
-    #[must_use]
-    pub fn from_feature_config(feature_config: &RuntimeFeatureConfig) -> Self {
-        Self::new(feature_config.hooks().clone())
-    }
-
-    #[must_use]
-    pub fn run_pre_tool_use(&self, tool_name: &str, tool_input: &str) -> HookRunResult {
-        self.run_commands(
-            HookEvent::PreToolUse,
-            self.config.pre_tool_use(),
-            tool_name,
-            tool_input,
-            None,
-            false,
-        )
-    }
-
-    #[must_use]
-    pub fn run_post_tool_use(
-        &self,
-        tool_name: &str,
-        tool_input: &str,
-        tool_output: &str,
-        is_error: bool,
-    ) -> HookRunResult {
-        self.run_commands(
-            HookEvent::PostToolUse,
-            self.config.post_tool_use(),
-            tool_name,
-            tool_input,
-            Some(tool_output),
-            is_error,
-        )
-    }
-
-    fn run_commands(
-        &self,
-        event: HookEvent,
-        commands: &[String],
-        tool_name: &str,
-        tool_input: &str,
-        tool_output: Option<&str>,
-        is_error: bool,
-    ) -> HookRunResult {
-        if commands.is_empty() {
-            return HookRunResult::allow(Vec::new());
-        }
-
-        let payload = json!({
-            "hook_event_name": event.as_str(),
-            "tool_name": tool_name,
-            "tool_input": parse_tool_input(tool_input),
-            "tool_input_json": tool_input,
-            "tool_output": tool_output,
-            "tool_result_is_error": is_error,
-        })
-        .to_string();
-
-        let mut messages = Vec::new();
-
-        for command in commands {
-            match self.run_command(
-                command,
-                event,
-                tool_name,
-                tool_input,
-                tool_output,
-                is_error,
-                &payload,
-            ) {
-                HookCommandOutcome::Allow { message } => {
-                    if let Some(message) = message {
-                        messages.push(message);
-                    }
-                }
-                HookCommandOutcome::Deny { message } => {
-                    let message = message.unwrap_or_else(|| {
-                        format!("{} hook denied tool `{tool_name}`", event.as_str())
-                    });
-                    messages.push(message);
-                    return HookRunResult {
-                        denied: true,
-                        messages,
-                    };
-                }
-                HookCommandOutcome::Warn { message } => messages.push(message),
-            }
-        }
-
-        HookRunResult::allow(messages)
-    }
-
-    #[allow(clippy::too_many_arguments, clippy::unused_self)]
-    fn run_command(
-        &self,
-        command: &str,
-        event: HookEvent,
-        tool_name: &str,
-        tool_input: &str,
-        tool_output: Option<&str>,
-        is_error: bool,
-        payload: &str,
-    ) -> HookCommandOutcome {
-        let mut child = shell_command(command);
-        child.stdin(std::process::Stdio::piped());
-        child.stdout(std::process::Stdio::piped());
-        child.stderr(std::process::Stdio::piped());
-        child.env("HOOK_EVENT", event.as_str());
-        child.env("HOOK_TOOL_NAME", tool_name);
-        child.env("HOOK_TOOL_INPUT", tool_input);
-        child.env("HOOK_TOOL_IS_ERROR", if is_error { "1" } else { "0" });
-        if let Some(tool_output) = tool_output {
-            child.env("HOOK_TOOL_OUTPUT", tool_output);
-        }
-
-        match child.output_with_stdin(payload.as_bytes()) {
-            Ok(output) => {
-                let stdout = String::from_utf8_lossy(&output.stdout).trim().to_string();
-                let stderr = String::from_utf8_lossy(&output.stderr).trim().to_string();
-                let message = (!stdout.is_empty()).then_some(stdout);
-                match output.status.code() {
-                    Some(0) => HookCommandOutcome::Allow { message },
-                    Some(2) => HookCommandOutcome::Deny { message },
-                    Some(code) => HookCommandOutcome::Warn {
-                        message: format_hook_warning(
-                            command,
-                            code,
-                            message.as_deref(),
-                            stderr.as_str(),
-                        ),
-                    },
-                    None => HookCommandOutcome::Warn {
-                        message: format!(
-                            "{} hook `{command}` terminated by signal while handling `{tool_name}`",
-                            event.as_str()
-                        ),
-                    },
-                }
-            }
-            Err(error) => HookCommandOutcome::Warn {
-                message: format!(
-                    "{} hook `{command}` failed to start for `{tool_name}`: {error}",
-                    event.as_str()
-                ),
-            },
-        }
-    }
-}
-
-enum HookCommandOutcome {
-    Allow { message: Option<String> },
-    Deny { message: Option<String> },
-    Warn { message: String },
-}
-
-fn parse_tool_input(tool_input: &str) -> serde_json::Value {
-    serde_json::from_str(tool_input).unwrap_or_else(|_| json!({ "raw": tool_input }))
-}
-
-fn format_hook_warning(command: &str, code: i32, stdout: Option<&str>, stderr: &str) -> String {
-    let mut message =
-        format!("Hook `{command}` exited with status {code}; allowing tool execution to continue");
-    if let Some(stdout) = stdout.filter(|stdout| !stdout.is_empty()) {
-        message.push_str(": ");
-        message.push_str(stdout);
-    } else if !stderr.is_empty() {
-        message.push_str(": ");
-        message.push_str(stderr);
-    }
-    message
-}
-
-fn shell_command(command: &str) -> CommandWithStdin {
-    #[cfg(windows)]
-    let mut command_builder = {
-        let mut command_builder = Command::new("cmd");
-        command_builder.arg("/C").arg(command);
-        CommandWithStdin::new(command_builder)
-    };
-
-    #[cfg(not(windows))]
-    let command_builder = if Path::new(command).exists() {
-        let mut command_builder = Command::new("sh");
-        command_builder.arg(command);
-        CommandWithStdin::new(command_builder)
-    } else {
-        let mut command_builder = Command::new("sh");
-        command_builder.arg("-lc").arg(command);
-        CommandWithStdin::new(command_builder)
-    };
-
-    command_builder
-}
-
-struct CommandWithStdin {
-    command: Command,
-}
-
-impl CommandWithStdin {
-    fn new(command: Command) -> Self {
-        Self { command }
-    }
-
-    fn stdin(&mut self, cfg: std::process::Stdio) -> &mut Self {
-        self.command.stdin(cfg);
-        self
-    }
-
-    fn stdout(&mut self, cfg: std::process::Stdio) -> &mut Self {
-        self.command.stdout(cfg);
-        self
-    }
-
-    fn stderr(&mut self, cfg: std::process::Stdio) -> &mut Self {
-        self.command.stderr(cfg);
-        self
-    }
-
-    fn env<K, V>(&mut self, key: K, value: V) -> &mut Self
-    where
-        K: AsRef<OsStr>,
-        V: AsRef<OsStr>,
-    {
-        self.command.env(key, value);
-        self
-    }
-
-    fn output_with_stdin(&mut self, stdin: &[u8]) -> std::io::Result<std::process::Output> {
-        let mut child = self.command.spawn()?;
-        if let Some(mut child_stdin) = child.stdin.take() {
-            use std::io::Write;
-            child_stdin.write_all(stdin)?;
-        }
-        child.wait_with_output()
-    }
-}
-
-#[cfg(test)]
-mod tests {
-    use super::{HookRunResult, HookRunner};
-    use crate::config::{RuntimeFeatureConfig, RuntimeHookConfig};
-
-    #[test]
-    fn allows_exit_code_zero_and_captures_stdout() {
-        let runner = HookRunner::new(RuntimeHookConfig::new(
-            vec![shell_snippet("printf 'pre ok'")],
-            Vec::new(),
-        ));
-
-        let result = runner.run_pre_tool_use("Read", r#"{"path":"README.md"}"#);
-
-        assert_eq!(result, HookRunResult::allow(vec!["pre ok".to_string()]));
-    }
-
-    #[test]
-    fn denies_exit_code_two() {
-        let runner = HookRunner::new(RuntimeHookConfig::new(
-            vec![shell_snippet("printf 'blocked by hook'; exit 2")],
-            Vec::new(),
-        ));
-
-        let result = runner.run_pre_tool_use("Bash", r#"{"command":"pwd"}"#);
-
-        assert!(result.is_denied());
-        assert_eq!(result.messages(), &["blocked by hook".to_string()]);
-    }
-
-    #[test]
-    fn warns_for_other_non_zero_statuses() {
-        let runner = HookRunner::from_feature_config(&RuntimeFeatureConfig::default().with_hooks(
-            RuntimeHookConfig::new(
-                vec![shell_snippet("printf 'warning hook'; exit 1")],
-                Vec::new(),
-            ),
-        ));
-
-        let result = runner.run_pre_tool_use("Edit", r#"{"file":"src/lib.rs"}"#);
-
-        assert!(!result.is_denied());
-        assert!(result
-            .messages()
-            .iter()
-            .any(|message| message.contains("allowing tool execution to continue")));
-    }
-
-    #[cfg(windows)]
-    fn shell_snippet(script: &str) -> String {
-        script.replace('\'', "\"")
-    }
-
-    #[cfg(not(windows))]
-    fn shell_snippet(script: &str) -> String {
-        script.to_string()
-    }
-}

rust/crates/runtime/src/lib.rs

@@ -4,7 +4,6 @@ mod compact;
 mod config;
 mod conversation;
 mod file_ops;
-mod hooks;
 mod json;
 mod mcp;
 mod mcp_client;
@@ -27,19 +26,18 @@ pub use config::{
     ConfigEntry, ConfigError, ConfigLoader, ConfigSource, McpClaudeAiProxyServerConfig,
     McpConfigCollection, McpOAuthConfig, McpRemoteServerConfig, McpSdkServerConfig,
     McpServerConfig, McpStdioServerConfig, McpTransport, McpWebSocketServerConfig, OAuthConfig,
-    ResolvedPermissionMode, RuntimeConfig, RuntimeFeatureConfig, RuntimeHookConfig,
+    ResolvedPermissionMode, RuntimeConfig, RuntimeFeatureConfig, ScopedMcpServerConfig,
-    RuntimePluginConfig, ScopedMcpServerConfig, CLAUDE_CODE_SETTINGS_SCHEMA_NAME,
+    CLAUDE_CODE_SETTINGS_SCHEMA_NAME,
 };
 pub use conversation::{
-    auto_compaction_threshold_from_env, ApiClient, ApiRequest, AssistantEvent, AutoCompactionEvent,
+    ApiClient, ApiRequest, AssistantEvent, ConversationRuntime, RuntimeError, StaticToolExecutor,
-    ConversationRuntime, RuntimeError, StaticToolExecutor, ToolError, ToolExecutor, TurnSummary,
+    ToolError, ToolExecutor, TurnSummary,
 };
 pub use file_ops::{
     edit_file, glob_search, grep_search, read_file, write_file, EditFileOutput, GlobSearchOutput,
     GrepSearchInput, GrepSearchOutput, ReadFileOutput, StructuredPatchHunk, TextFilePayload,
     WriteFileOutput,
 };
-pub use hooks::{HookEvent, HookRunResult, HookRunner};
 pub use mcp::{
     mcp_server_signature, mcp_tool_name, mcp_tool_prefix, normalize_name_for_mcp,
     scoped_mcp_config_hash, unwrap_ccr_proxy_url,

rust/crates/runtime/src/prompt.rs

@@ -421,7 +421,7 @@ fn render_config_section(config: &RuntimeConfig) -> String {
     let mut lines = vec!["# Runtime config".to_string()];
     if config.loaded_entries().is_empty() {
         lines.extend(prepend_bullets(vec![
-            "No Claw Code settings files loaded.".to_string()
+            "No Claude Code settings files loaded.".to_string(),
         ]));
         return lines.join("\n");
     }

rust/crates/rusty-claude-cli/Cargo.toml

@@ -17,7 +17,6 @@ crossterm = "0.28"
 pulldown-cmark = "0.13"
 rustyline = "15"
 runtime = { path = "../runtime" }
-plugins = { path = "../plugins" }
 serde_json = "1"
 syntect = "5"
 tokio = { version = "1", features = ["rt-multi-thread", "time"] }

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

@@ -8,7 +8,7 @@ const STARTER_CLAUDE_JSON: &str = concat!(
     "  }\n",
     "}\n",
 );
-const GITIGNORE_COMMENT: &str = "# Claw Code local artifacts";
+const GITIGNORE_COMMENT: &str = "# Claude Code local artifacts";
 const GITIGNORE_ENTRIES: [&str; 2] = [".claude/settings.local.json", ".claude/sessions/"];
 
 #[derive(Debug, Clone, Copy, PartialEq, Eq)]
@@ -164,7 +164,7 @@ pub(crate) fn render_init_claude_md(cwd: &Path) -> String {
     let mut lines = vec![
         "# CLAUDE.md".to_string(),
         String::new(),
-        "This file provides guidance to Claw Code (clawcode.dev) when working with code in this repository.".to_string(),
+        "This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.".to_string(),
         String::new(),
     ];
 

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

@@ -1,5 +1,7 @@
 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};
@@ -20,7 +22,6 @@ pub struct ColorTheme {
     link: Color,
     quote: Color,
     table_border: Color,
-    code_block_border: Color,
     spinner_active: Color,
     spinner_done: Color,
     spinner_failed: Color,
@@ -36,7 +37,6 @@ 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,
@@ -154,64 +154,33 @@ 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 style = text.stylize();
+        let mut styled = text.to_string();
-
+        if self.strong > 0 {
-        if matches!(self.heading_level, Some(1 | 2)) || self.strong > 0 {
+            styled = format!("{}", styled.bold().with(theme.strong));
-            style = style.bold();
         }
         if self.emphasis > 0 {
-            style = style.italic();
+            styled = format!("{}", styled.italic().with(theme.emphasis));
         }
-
-        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 {
-            style = style.with(theme.quote);
+            styled = format!("{}", styled.with(theme.quote));
+        }
+        styled
     }
 
-        format!("{style}")
+    fn capture_target_mut<'a>(&'a mut self, output: &'a mut String) -> &'a mut String {
-    }
+        if let Some(table) = self.table.as_mut() {
-
+            &mut table.current_cell
-    fn append_raw(&mut self, output: &mut String, text: &str) {
-        if let Some(link) = self.link_stack.last_mut() {
-            link.text.push_str(text);
-        } else if let Some(table) = self.table.as_mut() {
-            table.current_cell.push_str(text);
         } else {
-            output.push_str(text);
+            output
         }
     }
-
-    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)]
@@ -269,11 +238,6 @@ 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,
@@ -285,21 +249,15 @@ impl TerminalRenderer {
         in_code_block: &mut bool,
     ) {
         match event {
-            Event::Start(Tag::Heading { level, .. }) => {
+            Event::Start(Tag::Heading { level, .. }) => self.start_heading(level as u8, output),
-                self.start_heading(state, level as u8, output);
+            Event::End(TagEnd::Heading(..) | TagEnd::Paragraph) => output.push_str("\n\n"),
-            }
-            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.append_raw(output, "\n");
+                state.capture_target_mut(output).push('\n');
             }
             Event::Start(Tag::List(first_item)) => {
                 let kind = match first_item {
@@ -335,52 +293,41 @@ impl TerminalRenderer {
             Event::Code(code) => {
                 let rendered =
                     format!("{}", format!("`{code}`").with(self.color_theme.inline_code));
-                state.append_raw(output, &rendered);
+                state.capture_target_mut(output).push_str(&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.append_raw(output, &html);
+                state.capture_target_mut(output).push_str(&html);
             }
             Event::FootnoteReference(reference) => {
-                state.append_raw(output, &format!("[{reference}]"));
+                let _ = write!(state.capture_target_mut(output), "[{reference}]");
             }
             Event::TaskListMarker(done) => {
-                state.append_raw(output, if done { "[x] " } else { "[ ] " });
+                state
+                    .capture_target_mut(output)
+                    .push_str(if done { "[x] " } else { "[ ] " });
             }
             Event::InlineMath(math) | Event::DisplayMath(math) => {
-                state.append_raw(output, &math);
+                state.capture_target_mut(output).push_str(&math);
             }
             Event::Start(Tag::Link { dest_url, .. }) => {
-                state.link_stack.push(LinkState {
-                    destination: dest_url.to_string(),
-                    text: String::new(),
-                });
-            }
-            Event::End(TagEnd::Link) => {
-                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)
+                    format!("[{dest_url}]")
                         .underlined()
                         .with(self.color_theme.link)
                 );
-                    state.append_raw(output, &rendered);
+                state.capture_target_mut(output).push_str(&rendered);
-                }
             }
             Event::Start(Tag::Image { dest_url, .. }) => {
                 let rendered = format!(
                     "{}",
                     format!("[image:{dest_url}]").with(self.color_theme.link)
                 );
-                state.append_raw(output, &rendered);
+                state.capture_target_mut(output).push_str(&rendered);
             }
             Event::Start(Tag::Table(..)) => state.table = Some(TableState::default()),
             Event::End(TagEnd::Table) => {
@@ -422,16 +369,19 @@ impl TerminalRenderer {
                 }
             }
             Event::Start(Tag::Paragraph | Tag::MetadataBlock(..) | _)
-            | Event::End(TagEnd::Image | TagEnd::MetadataBlock(..) | _) => {}
+            | Event::End(TagEnd::Link | TagEnd::Image | TagEnd::MetadataBlock(..) | _) => {}
         }
     }
 
-    #[allow(clippy::unused_self)]
+    fn start_heading(&self, level: u8, output: &mut String) {
-    fn start_heading(&self, state: &mut RenderState, level: u8, output: &mut String) {
-        state.heading_level = Some(level);
-        if !output.is_empty() {
         output.push('\n');
-        }
+        let prefix = match level {
+            1 => "# ",
+            2 => "## ",
+            3 => "### ",
+            _ => "#### ",
+        };
+        let _ = write!(output, "{}", prefix.bold().with(self.color_theme.heading));
     }
 
     fn start_quote(&self, state: &mut RenderState, output: &mut String) {
@@ -455,27 +405,20 @@ impl TerminalRenderer {
     }
 
     fn start_code_block(&self, code_language: &str, output: &mut String) {
-        let label = if code_language.is_empty() {
+        if !code_language.is_empty() {
-            "code".to_string()
-        } else {
-            code_language.to_string()
-        };
             let _ = writeln!(
                 output,
                 "{}",
-            format!("╭─ {label}")
+                format!("╭─ {code_language}").with(self.color_theme.heading)
-                .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));
-        let _ = write!(
+        if !code_language.is_empty() {
-            output,
+            let _ = write!(output, "{}", "╰─".with(self.color_theme.heading));
-            "{}",
+        }
-            "╰─".bold().with(self.color_theme.code_block_border)
-        );
         output.push_str("\n\n");
     }
 
@@ -490,7 +433,8 @@ impl TerminalRenderer {
         if in_code_block {
             code_buffer.push_str(text);
         } else {
-            state.append_styled(output, text, &self.color_theme);
+            let rendered = state.style_text(text, &self.color_theme);
+            state.capture_target_mut(output).push_str(&rendered);
         }
     }
 
@@ -577,10 +521,9 @@ impl TerminalRenderer {
         for line in LinesWithEndings::from(code) {
             match syntax_highlighter.highlight_line(line, &self.syntax_set) {
                 Ok(ranges) => {
-                    let escaped = as_24_bit_terminal_escaped(&ranges[..], false);
+                    colored_output.push_str(&as_24_bit_terminal_escaped(&ranges[..], false));
-                    colored_output.push_str(&apply_code_block_background(&escaped));
                 }
-                Err(_) => colored_output.push_str(&apply_code_block_background(line)),
+                Err(_) => colored_output.push_str(line),
             }
         }
 
@@ -588,83 +531,16 @@ impl TerminalRenderer {
     }
 
     pub fn stream_markdown(&self, markdown: &str, out: &mut impl Write) -> io::Result<()> {
-        let rendered_markdown = self.markdown_to_ansi(markdown);
+        let rendered_markdown = self.render_markdown(markdown);
-        write!(out, "{rendered_markdown}")?;
+        for chunk in rendered_markdown.split_inclusive(char::is_whitespace) {
-        if !rendered_markdown.ends_with('\n') {
+            write!(out, "{chunk}")?;
-            writeln!(out)?;
+            out.flush()?;
+            thread::sleep(Duration::from_millis(8));
         }
-        out.flush()
+        writeln!(out)
     }
 }
 
-#[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()
 }
@@ -693,7 +569,7 @@ fn strip_ansi(input: &str) -> String {
 
 #[cfg(test)]
 mod tests {
-    use super::{strip_ansi, MarkdownStreamState, Spinner, TerminalRenderer};
+    use super::{strip_ansi, Spinner, TerminalRenderer};
 
     #[test]
     fn renders_markdown_with_styling_and_lists() {
@@ -707,28 +583,16 @@ 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.markdown_to_ansi("```rust\nfn hi() { println!(\"hi\"); }\n```");
+            terminal_renderer.render_markdown("```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]
@@ -759,26 +623,6 @@ 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

@@ -7,7 +7,6 @@ publish.workspace = true
 
 [dependencies]
 api = { path = "../api" }
-plugins = { path = "../plugins" }
 runtime = { path = "../runtime" }
 reqwest = { version = "0.12", default-features = false, features = ["blocking", "rustls-tls"] }
 serde = { version = "1", features = ["derive"] }

rust/crates/tools/src/lib.rs

@@ -8,13 +8,12 @@ use api::{
     MessageRequest, MessageResponse, OutputContentBlock, StreamEvent as ApiStreamEvent, ToolChoice,
     ToolDefinition, ToolResultContentBlock,
 };
-use plugins::{PluginManager, PluginManagerConfig, PluginTool};
 use reqwest::blocking::Client;
 use runtime::{
     edit_file, execute_bash, glob_search, grep_search, load_system_prompt, read_file, write_file,
-    ApiClient, ApiRequest, AssistantEvent, BashCommandInput, ConfigLoader, ContentBlock,
+    ApiClient, ApiRequest, AssistantEvent, BashCommandInput, ContentBlock, ConversationMessage,
-    ConversationMessage, ConversationRuntime, GrepSearchInput, MessageRole, PermissionMode,
+    ConversationRuntime, GrepSearchInput, MessageRole, PermissionMode, PermissionPolicy,
-    PermissionPolicy, RuntimeConfig, RuntimeError, Session, TokenUsage, ToolError, ToolExecutor,
+    RuntimeError, Session, TokenUsage, ToolError, ToolExecutor,
 };
 use serde::{Deserialize, Serialize};
 use serde_json::{json, Value};
@@ -56,239 +55,6 @@ pub struct ToolSpec {
     pub required_permission: PermissionMode,
 }
 
-#[derive(Debug, Clone, PartialEq)]
-pub struct RegisteredTool {
-    pub definition: ToolDefinition,
-    pub required_permission: PermissionMode,
-    handler: RegisteredToolHandler,
-}
-
-#[allow(clippy::large_enum_variant)]
-#[derive(Debug, Clone, PartialEq)]
-enum RegisteredToolHandler {
-    Builtin,
-    Plugin(PluginTool),
-}
-
-#[derive(Debug, Clone, PartialEq)]
-pub struct GlobalToolRegistry {
-    entries: Vec<RegisteredTool>,
-}
-
-impl GlobalToolRegistry {
-    #[must_use]
-    pub fn builtin() -> Self {
-        Self {
-            entries: mvp_tool_specs()
-                .into_iter()
-                .map(|spec| RegisteredTool {
-                    definition: ToolDefinition {
-                        name: spec.name.to_string(),
-                        description: Some(spec.description.to_string()),
-                        input_schema: spec.input_schema,
-                    },
-                    required_permission: spec.required_permission,
-                    handler: RegisteredToolHandler::Builtin,
-                })
-                .collect(),
-        }
-    }
-
-    pub fn with_plugin_tools(plugin_tools: Vec<PluginTool>) -> Result<Self, String> {
-        let mut registry = Self::builtin();
-        let mut seen = registry
-            .entries
-            .iter()
-            .map(|entry| {
-                (
-                    normalize_registry_tool_name(&entry.definition.name),
-                    entry.definition.name.clone(),
-                )
-            })
-            .collect::<BTreeMap<_, _>>();
-
-        for tool in plugin_tools {
-            let normalized = normalize_registry_tool_name(&tool.definition().name);
-            if let Some(existing) = seen.get(&normalized) {
-                return Err(format!(
-                    "plugin tool `{}` from `{}` conflicts with already-registered tool `{existing}`",
-                    tool.definition().name,
-                    tool.plugin_id()
-                ));
-            }
-            seen.insert(normalized, tool.definition().name.clone());
-            registry.entries.push(RegisteredTool {
-                definition: ToolDefinition {
-                    name: tool.definition().name.clone(),
-                    description: tool.definition().description.clone(),
-                    input_schema: tool.definition().input_schema.clone(),
-                },
-                required_permission: permission_mode_from_plugin_tool(tool.required_permission())?,
-                handler: RegisteredToolHandler::Plugin(tool),
-            });
-        }
-
-        Ok(registry)
-    }
-
-    #[must_use]
-    pub fn entries(&self) -> &[RegisteredTool] {
-        &self.entries
-    }
-
-    fn find_entry(&self, name: &str) -> Option<&RegisteredTool> {
-        let normalized = normalize_registry_tool_name(name);
-        self.entries.iter().find(|entry| {
-            normalize_registry_tool_name(entry.definition.name.as_str()) == normalized
-        })
-    }
-
-    #[must_use]
-    pub fn definitions(&self, allowed_tools: Option<&BTreeSet<String>>) -> Vec<ToolDefinition> {
-        self.entries
-            .iter()
-            .filter(|entry| {
-                allowed_tools.is_none_or(|allowed| allowed.contains(entry.definition.name.as_str()))
-            })
-            .map(|entry| entry.definition.clone())
-            .collect()
-    }
-
-    #[must_use]
-    pub fn permission_specs(
-        &self,
-        allowed_tools: Option<&BTreeSet<String>>,
-    ) -> Vec<(String, PermissionMode)> {
-        self.entries
-            .iter()
-            .filter(|entry| {
-                allowed_tools.is_none_or(|allowed| allowed.contains(entry.definition.name.as_str()))
-            })
-            .map(|entry| (entry.definition.name.clone(), entry.required_permission))
-            .collect()
-    }
-
-    pub fn normalize_allowed_tools(
-        &self,
-        values: &[String],
-    ) -> Result<Option<BTreeSet<String>>, String> {
-        if values.is_empty() {
-            return Ok(None);
-        }
-
-        let canonical_names = self
-            .entries
-            .iter()
-            .map(|entry| entry.definition.name.clone())
-            .collect::<Vec<_>>();
-        let mut name_map = canonical_names
-            .iter()
-            .map(|name| (normalize_registry_tool_name(name), name.clone()))
-            .collect::<BTreeMap<_, _>>();
-
-        for (alias, canonical) in [
-            ("read", "read_file"),
-            ("write", "write_file"),
-            ("edit", "edit_file"),
-            ("glob", "glob_search"),
-            ("grep", "grep_search"),
-        ] {
-            if canonical_names.iter().any(|name| name == canonical) {
-                name_map.insert(alias.to_string(), canonical.to_string());
-            }
-        }
-
-        let mut allowed = BTreeSet::new();
-        for value in values {
-            for token in value
-                .split(|ch: char| ch == ',' || ch.is_whitespace())
-                .filter(|token| !token.is_empty())
-            {
-                let normalized = normalize_registry_tool_name(token);
-                let canonical = name_map.get(&normalized).ok_or_else(|| {
-                    format!(
-                        "unsupported tool in --allowedTools: {token} (expected one of: {})",
-                        canonical_names.join(", ")
-                    )
-                })?;
-                allowed.insert(canonical.clone());
-            }
-        }
-
-        Ok(Some(allowed))
-    }
-
-    pub fn execute(&self, name: &str, input: &Value) -> Result<String, String> {
-        let entry = self
-            .find_entry(name)
-            .ok_or_else(|| format!("unsupported tool: {name}"))?;
-        match &entry.handler {
-            RegisteredToolHandler::Builtin => execute_tool(&entry.definition.name, input),
-            RegisteredToolHandler::Plugin(tool) => {
-                tool.execute(input).map_err(|error| error.to_string())
-            }
-        }
-    }
-}
-
-impl Default for GlobalToolRegistry {
-    fn default() -> Self {
-        Self::builtin()
-    }
-}
-
-fn normalize_registry_tool_name(value: &str) -> String {
-    let trimmed = value.trim();
-    let chars = trimmed.chars().collect::<Vec<_>>();
-    let mut normalized = String::new();
-
-    for (index, ch) in chars.iter().copied().enumerate() {
-        if matches!(ch, '-' | ' ' | '\t' | '\n') {
-            if !normalized.ends_with('_') {
-                normalized.push('_');
-            }
-            continue;
-        }
-
-        if ch == '_' {
-            if !normalized.ends_with('_') {
-                normalized.push('_');
-            }
-            continue;
-        }
-
-        if ch.is_uppercase() {
-            let prev = chars.get(index.wrapping_sub(1)).copied();
-            let next = chars.get(index + 1).copied();
-            let needs_separator = index > 0
-                && !normalized.ends_with('_')
-                && (prev.is_some_and(|prev| prev.is_lowercase() || prev.is_ascii_digit())
-                    || (prev.is_some_and(char::is_uppercase)
-                        && next.is_some_and(char::is_lowercase)));
-            if needs_separator {
-                normalized.push('_');
-            }
-            normalized.extend(ch.to_lowercase());
-            continue;
-        }
-
-        normalized.push(ch.to_ascii_lowercase());
-    }
-
-    normalized.trim_matches('_').to_string()
-}
-
-fn permission_mode_from_plugin_tool(value: &str) -> Result<PermissionMode, String> {
-    match value {
-        "read-only" => Ok(PermissionMode::ReadOnly),
-        "workspace-write" => Ok(PermissionMode::WorkspaceWrite),
-        "danger-full-access" => Ok(PermissionMode::DangerFullAccess),
-        other => Err(format!(
-            "unsupported plugin tool permission `{other}` (expected read-only, workspace-write, or danger-full-access)"
-        )),
-    }
-}
-
 #[must_use]
 #[allow(clippy::too_many_lines)]
 pub fn mvp_tool_specs() -> Vec<ToolSpec> {
@@ -557,7 +323,7 @@ pub fn mvp_tool_specs() -> Vec<ToolSpec> {
         },
         ToolSpec {
             name: "Config",
-            description: "Get or set Claw Code settings.",
+            description: "Get or set Claude Code settings.",
             input_schema: json!({
                 "type": "object",
                 "properties": {
@@ -1514,7 +1280,15 @@ fn validate_todos(todos: &[TodoItem]) -> Result<(), String> {
     if todos.is_empty() {
         return Err(String::from("todos must not be empty"));
     }
-    // Allow multiple in_progress items for parallel workflows
+    let in_progress = todos
+        .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"));
     }
@@ -1700,15 +1474,13 @@ fn build_agent_runtime(
         .clone()
         .unwrap_or_else(|| DEFAULT_AGENT_MODEL.to_string());
     let allowed_tools = job.allowed_tools.clone();
-    let tool_registry = current_tool_registry()?;
+    let api_client = AnthropicRuntimeClient::new(model, allowed_tools.clone())?;
-    let api_client =
+    let tool_executor = SubagentToolExecutor::new(allowed_tools);
-        AnthropicRuntimeClient::new(model, allowed_tools.clone(), tool_registry.clone())?;
-    let tool_executor = SubagentToolExecutor::new(allowed_tools, tool_registry.clone());
     Ok(ConversationRuntime::new(
         Session::new(),
         api_client,
         tool_executor,
-        agent_permission_policy(&tool_registry),
+        agent_permission_policy(),
         job.system_prompt.clone(),
     ))
 }
@@ -1773,7 +1545,7 @@ fn allowed_tools_for_subagent(subagent_type: &str) -> BTreeSet<String> {
             "SendUserMessage",
             "PowerShell",
         ],
-        "claw-code-guide" => vec![
+        "claude-code-guide" => vec![
             "read_file",
             "glob_search",
             "grep_search",
@@ -1817,12 +1589,10 @@ fn allowed_tools_for_subagent(subagent_type: &str) -> BTreeSet<String> {
     tools.into_iter().map(str::to_string).collect()
 }
 
-fn agent_permission_policy(tool_registry: &GlobalToolRegistry) -> PermissionPolicy {
+fn agent_permission_policy() -> PermissionPolicy {
-    tool_registry.permission_specs(None).into_iter().fold(
+    mvp_tool_specs().into_iter().fold(
         PermissionPolicy::new(PermissionMode::DangerFullAccess),
-        |policy, (name, required_permission)| {
+        |policy, spec| policy.with_tool_requirement(spec.name, spec.required_permission),
-            policy.with_tool_requirement(name, required_permission)
-        },
     )
 }
 
@@ -1878,15 +1648,10 @@ struct AnthropicRuntimeClient {
     client: AnthropicClient,
     model: String,
     allowed_tools: BTreeSet<String>,
-    tool_registry: GlobalToolRegistry,
 }
 
 impl AnthropicRuntimeClient {
-    fn new(
+    fn new(model: String, allowed_tools: BTreeSet<String>) -> Result<Self, String> {
-        model: String,
-        allowed_tools: BTreeSet<String>,
-        tool_registry: GlobalToolRegistry,
-    ) -> Result<Self, String> {
         let client = AnthropicClient::from_env()
             .map_err(|error| error.to_string())?
             .with_base_url(read_base_url());
@@ -1895,14 +1660,20 @@ impl AnthropicRuntimeClient {
             client,
             model,
             allowed_tools,
-            tool_registry,
         })
     }
 }
 
 impl ApiClient for AnthropicRuntimeClient {
     fn stream(&mut self, request: ApiRequest) -> Result<Vec<AssistantEvent>, RuntimeError> {
-        let tools = self.tool_registry.definitions(Some(&self.allowed_tools));
+        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,
@@ -1953,8 +1724,6 @@ impl ApiClient for AnthropicRuntimeClient {
                                 input.push_str(&partial_json);
                             }
                         }
-                        ContentBlockDelta::ThinkingDelta { .. }
-                        | ContentBlockDelta::SignatureDelta { .. } => {}
                     },
                     ApiStreamEvent::ContentBlockStop(_) => {
                         if let Some((id, name, input)) = pending_tool.take() {
@@ -2007,82 +1776,32 @@ impl ApiClient for AnthropicRuntimeClient {
 
 struct SubagentToolExecutor {
     allowed_tools: BTreeSet<String>,
-    tool_registry: GlobalToolRegistry,
 }
 
 impl SubagentToolExecutor {
-    fn new(allowed_tools: BTreeSet<String>, tool_registry: GlobalToolRegistry) -> Self {
+    fn new(allowed_tools: BTreeSet<String>) -> Self {
-        Self {
+        Self { allowed_tools }
-            allowed_tools,
-            tool_registry,
-        }
     }
 }
 
 impl ToolExecutor for SubagentToolExecutor {
     fn execute(&mut self, tool_name: &str, input: &str) -> Result<String, ToolError> {
-        let entry = self
+        if !self.allowed_tools.contains(tool_name) {
-            .tool_registry
-            .find_entry(tool_name)
-            .ok_or_else(|| ToolError::new(format!("unsupported tool: {tool_name}")))?;
-        if !self.allowed_tools.contains(entry.definition.name.as_str()) {
             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}")))?;
-        self.tool_registry
+        execute_tool(tool_name, &value).map_err(ToolError::new)
-            .execute(tool_name, &value)
-            .map_err(ToolError::new)
     }
 }
 
-fn current_tool_registry() -> Result<GlobalToolRegistry, String> {
+fn tool_specs_for_allowed_tools(allowed_tools: Option<&BTreeSet<String>>) -> Vec<ToolSpec> {
-    let cwd = std::env::current_dir().map_err(|error| error.to_string())?;
+    mvp_tool_specs()
-    let loader = ConfigLoader::default_for(&cwd);
+        .into_iter()
-    let runtime_config = loader.load().map_err(|error| error.to_string())?;
+        .filter(|spec| allowed_tools.is_none_or(|allowed| allowed.contains(spec.name)))
-    let plugin_manager = build_plugin_manager(&cwd, &loader, &runtime_config);
+        .collect()
-    let plugin_tools = plugin_manager
-        .aggregated_tools()
-        .map_err(|error| error.to_string())?;
-    GlobalToolRegistry::with_plugin_tools(plugin_tools)
-}
-
-fn build_plugin_manager(
-    cwd: &Path,
-    loader: &ConfigLoader,
-    runtime_config: &RuntimeConfig,
-) -> PluginManager {
-    let plugin_settings = runtime_config.plugins();
-    let mut plugin_config = PluginManagerConfig::new(loader.config_home().to_path_buf());
-    plugin_config.enabled_plugins = plugin_settings.enabled_plugins().clone();
-    plugin_config.external_dirs = plugin_settings
-        .external_directories()
-        .iter()
-        .map(|path| resolve_plugin_path(cwd, loader.config_home(), path))
-        .collect();
-    plugin_config.install_root = plugin_settings
-        .install_root()
-        .map(|path| resolve_plugin_path(cwd, loader.config_home(), path));
-    plugin_config.registry_path = plugin_settings
-        .registry_path()
-        .map(|path| resolve_plugin_path(cwd, loader.config_home(), path));
-    plugin_config.bundled_root = plugin_settings
-        .bundled_root()
-        .map(|path| resolve_plugin_path(cwd, loader.config_home(), path));
-    PluginManager::new(plugin_config)
-}
-
-fn resolve_plugin_path(cwd: &Path, config_home: &Path, value: &str) -> PathBuf {
-    let path = PathBuf::from(value);
-    if path.is_absolute() {
-        path
-    } else if value.starts_with('.') {
-        cwd.join(path)
-    } else {
-        config_home.join(path)
-    }
 }
 
 fn convert_messages(messages: &[ConversationMessage]) -> Vec<InputMessage> {
@@ -2149,7 +1868,6 @@ fn push_output_block(
             };
             *pending_tool = Some((id, name, initial_input));
         }
-        OutputContentBlock::Thinking { .. } | OutputContentBlock::RedactedThinking { .. } => {}
     }
 }
 
@@ -2377,7 +2095,7 @@ fn normalize_subagent_type(subagent_type: Option<&str>) -> String {
         "verification" | "verificationagent" | "verify" | "verifier" => {
             String::from("Verification")
         }
-        "claudecodeguide" | "claudecodeguideagent" | "guide" => String::from("claw-code-guide"),
+        "claudecodeguide" | "claudecodeguideagent" | "guide" => String::from("claude-code-guide"),
         "statusline" | "statuslinesetup" => String::from("statusline-setup"),
         _ => trimmed.to_string(),
     }
@@ -3195,13 +2913,9 @@ mod tests {
     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,
-        response_to_events, AgentInput, AgentJob, GlobalToolRegistry, SubagentToolExecutor,
+        AgentInput, AgentJob, SubagentToolExecutor,
-    };
-    use api::{MessageResponse, OutputContentBlock, Usage};
-    use plugins::{PluginTool, PluginToolDefinition, PluginToolPermission};
-    use runtime::{
-        ApiRequest, AssistantEvent, ConversationRuntime, RuntimeError, Session, ToolExecutor,
     };
+    use runtime::{ApiRequest, AssistantEvent, ConversationRuntime, RuntimeError, Session};
     use serde_json::json;
 
     fn env_lock() -> &'static Mutex<()> {
@@ -3217,17 +2931,6 @@ mod tests {
         std::env::temp_dir().join(format!("clawd-tools-{unique}-{name}"))
     }
 
-    fn make_executable(path: &PathBuf) {
-        #[cfg(unix)]
-        {
-            use std::os::unix::fs::PermissionsExt;
-
-            let mut permissions = std::fs::metadata(path).expect("metadata").permissions();
-            permissions.set_mode(0o755);
-            std::fs::set_permissions(path, permissions).expect("chmod");
-        }
-    }
-
     #[test]
     fn exposes_mvp_tools() {
         let names = mvp_tool_specs()
@@ -3257,170 +2960,6 @@ mod tests {
         assert!(error.contains("unsupported tool"));
     }
 
-    #[test]
-    fn global_registry_registers_and_executes_plugin_tools() {
-        let script = temp_path("plugin-tool.sh");
-        std::fs::write(
-            &script,
-            "#!/bin/sh\nINPUT=$(cat)\nprintf '{\"plugin\":\"%s\",\"tool\":\"%s\",\"input\":%s}\\n' \"$CLAWD_PLUGIN_ID\" \"$CLAWD_TOOL_NAME\" \"$INPUT\"\n",
-        )
-        .expect("write script");
-        make_executable(&script);
-
-        let registry = GlobalToolRegistry::with_plugin_tools(vec![PluginTool::new(
-            "demo@external",
-            "demo",
-            PluginToolDefinition {
-                name: "plugin_echo".to_string(),
-                description: Some("Echo plugin input".to_string()),
-                input_schema: json!({
-                    "type": "object",
-                    "properties": { "message": { "type": "string" } },
-                    "required": ["message"],
-                    "additionalProperties": false
-                }),
-            },
-            "sh".to_string(),
-            vec![script.display().to_string()],
-            PluginToolPermission::WorkspaceWrite,
-            script.parent().map(PathBuf::from),
-        )])
-        .expect("registry should build");
-
-        let names = registry
-            .definitions(None)
-            .into_iter()
-            .map(|definition| definition.name)
-            .collect::<Vec<_>>();
-        assert!(names.contains(&"bash".to_string()));
-        assert!(names.contains(&"plugin_echo".to_string()));
-
-        let output = registry
-            .execute("plugin_echo", &json!({ "message": "hello" }))
-            .expect("plugin tool should execute");
-        let payload: serde_json::Value = serde_json::from_str(&output).expect("valid json");
-        assert_eq!(payload["plugin"], "demo@external");
-        assert_eq!(payload["tool"], "plugin_echo");
-        assert_eq!(payload["input"]["message"], "hello");
-
-        let _ = std::fs::remove_file(script);
-    }
-
-    #[test]
-    fn global_registry_normalizes_plugin_tool_names_for_allowlists_and_execution() {
-        let script = temp_path("plugin-tool-normalized.sh");
-        std::fs::write(
-            &script,
-            "#!/bin/sh\nINPUT=$(cat)\nprintf '{\"tool\":\"%s\",\"input\":%s}\\n' \"$CLAWD_TOOL_NAME\" \"$INPUT\"\n",
-        )
-        .expect("write script");
-        make_executable(&script);
-
-        let registry = GlobalToolRegistry::with_plugin_tools(vec![PluginTool::new(
-            "demo@external",
-            "demo",
-            PluginToolDefinition {
-                name: "plugin_echo".to_string(),
-                description: Some("Echo plugin input".to_string()),
-                input_schema: json!({
-                    "type": "object",
-                    "properties": { "message": { "type": "string" } },
-                    "required": ["message"],
-                    "additionalProperties": false
-                }),
-            },
-            script.display().to_string(),
-            Vec::new(),
-            PluginToolPermission::WorkspaceWrite,
-            script.parent().map(PathBuf::from),
-        )])
-        .expect("registry should build");
-
-        let allowed = registry
-            .normalize_allowed_tools(&[String::from("PLUGIN-ECHO")])
-            .expect("plugin tool allowlist should normalize")
-            .expect("allowlist should be present");
-        assert!(allowed.contains("plugin_echo"));
-
-        let output = registry
-            .execute("plugin-echo", &json!({ "message": "hello" }))
-            .expect("normalized plugin tool name should execute");
-        let payload: serde_json::Value = serde_json::from_str(&output).expect("valid json");
-        assert_eq!(payload["tool"], "plugin_echo");
-        assert_eq!(payload["input"]["message"], "hello");
-
-        let builtin_output = GlobalToolRegistry::builtin()
-            .execute("structured-output", &json!({ "ok": true }))
-            .expect("normalized builtin tool name should execute");
-        let builtin_payload: serde_json::Value =
-            serde_json::from_str(&builtin_output).expect("valid json");
-        assert_eq!(builtin_payload["structured_output"]["ok"], true);
-
-        let _ = std::fs::remove_file(script);
-    }
-
-    #[test]
-    fn subagent_executor_executes_allowed_plugin_tools() {
-        let script = temp_path("subagent-plugin-tool.sh");
-        std::fs::write(
-            &script,
-            "#!/bin/sh\nINPUT=$(cat)\nprintf '{\"tool\":\"%s\",\"input\":%s}\\n' \"$CLAWD_TOOL_NAME\" \"$INPUT\"\n",
-        )
-        .expect("write script");
-        make_executable(&script);
-
-        let registry = GlobalToolRegistry::with_plugin_tools(vec![PluginTool::new(
-            "demo@external",
-            "demo",
-            PluginToolDefinition {
-                name: "plugin_echo".to_string(),
-                description: Some("Echo plugin input".to_string()),
-                input_schema: json!({
-                    "type": "object",
-                    "properties": { "message": { "type": "string" } },
-                    "required": ["message"],
-                    "additionalProperties": false
-                }),
-            },
-            script.display().to_string(),
-            Vec::new(),
-            PluginToolPermission::WorkspaceWrite,
-            script.parent().map(PathBuf::from),
-        )])
-        .expect("registry should build");
-
-        let mut executor =
-            SubagentToolExecutor::new(BTreeSet::from([String::from("plugin_echo")]), registry);
-        let output = executor
-            .execute("plugin-echo", r#"{"message":"hello"}"#)
-            .expect("plugin tool should execute for subagent");
-        let payload: serde_json::Value = serde_json::from_str(&output).expect("valid json");
-        assert_eq!(payload["tool"], "plugin_echo");
-        assert_eq!(payload["input"]["message"], "hello");
-
-        let _ = std::fs::remove_file(script);
-    }
-
-    #[test]
-    fn global_registry_rejects_conflicting_plugin_tool_names() {
-        let error = GlobalToolRegistry::with_plugin_tools(vec![PluginTool::new(
-            "demo@external",
-            "demo",
-            PluginToolDefinition {
-                name: "read-file".to_string(),
-                description: Some("Conflicts with builtin".to_string()),
-                input_schema: json!({ "type": "object" }),
-            },
-            "echo".to_string(),
-            Vec::new(),
-            PluginToolPermission::ReadOnly,
-            None,
-        )])
-        .expect_err("conflicting plugin tool should fail");
-
-        assert!(error.contains("conflicts with already-registered tool `read_file`"));
-    }
-
     #[test]
     fn web_fetch_returns_prompt_aware_summary() {
         let server = TestServer::spawn(Arc::new(|request_line: &str| {
@@ -3649,8 +3188,7 @@ mod tests {
             .expect_err("empty todos should fail");
         assert!(empty.contains("todos must not be empty"));
 
-        // Multiple in_progress items are now allowed for parallel workflows
+        let too_many_active = execute_tool(
-        let _multi_active = execute_tool(
             "TodoWrite",
             &json!({
                 "todos": [
@@ -3659,7 +3197,8 @@ mod tests {
                 ]
             }),
         )
-        .expect("multiple in-progress todos should succeed");
+        .expect_err("multiple in-progress todos should fail");
+        assert!(too_many_active.contains("zero or one todo items may be in_progress"));
 
         let blank_content = execute_tool(
             "TodoWrite",
@@ -4000,11 +3539,8 @@ mod tests {
                 calls: 0,
                 input_path: path.display().to_string(),
             },
-            SubagentToolExecutor::new(
+            SubagentToolExecutor::new(BTreeSet::from([String::from("read_file")])),
-                BTreeSet::from([String::from("read_file")]),
+            agent_permission_policy(),
-                GlobalToolRegistry::builtin(),
-            ),
-            agent_permission_policy(&GlobalToolRegistry::builtin()),
             vec![String::from("system prompt")],
         );
 
@@ -4030,42 +3566,6 @@ mod tests {
         let _ = std::fs::remove_file(path);
     }
 
-    #[test]
-    fn response_to_events_ignores_thinking_blocks() {
-        let events = response_to_events(MessageResponse {
-            id: "msg-1".to_string(),
-            kind: "message".to_string(),
-            model: "claude-opus-4-6".to_string(),
-            role: "assistant".to_string(),
-            content: vec![
-                OutputContentBlock::Thinking {
-                    thinking: "step 1".to_string(),
-                    signature: Some("sig_123".to_string()),
-                },
-                OutputContentBlock::Text {
-                    text: "Final answer".to_string(),
-                },
-            ],
-            stop_reason: Some("end_turn".to_string()),
-            stop_sequence: None,
-            usage: Usage {
-                input_tokens: 1,
-                output_tokens: 1,
-                cache_creation_input_tokens: 0,
-                cache_read_input_tokens: 0,
-            },
-            request_id: None,
-        });
-
-        assert!(matches!(
-            &events[0],
-            AssistantEvent::TextDelta(text) if text == "Final answer"
-        ));
-        assert!(!events
-            .iter()
-            .any(|event| matches!(event, AssistantEvent::ToolUse { .. })));
-    }
-
     #[test]
     fn agent_rejects_blank_required_fields() {
         let missing_description = execute_tool(