Compare commits
2 Commits
rcc/ui-pol
...
rcc/subage
| Author | SHA1 | Date | |
|---|---|---|---|
|
b4e0579477 | ||
|
|
ba220d210e |
@@ -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}
|
||||
@@ -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}
|
||||
@@ -1 +0,0 @@
|
||||
{"messages":[],"version":1}
|
||||
@@ -1 +0,0 @@
|
||||
{"messages":[],"version":1}
|
||||
File diff suppressed because one or more lines are too long
@@ -1,22 +0,0 @@
|
||||
[
|
||||
{
|
||||
"content": "Phase 0: Structural Cleanup — spawn 4 agents for 0.1-0.4",
|
||||
"activeForm": "Executing Phase 0: Structural Cleanup via sub-agents",
|
||||
"status": "in_progress"
|
||||
},
|
||||
{
|
||||
"content": "Phase 1.1-1.2: Status bar with live HUD and token counter",
|
||||
"activeForm": "Awaiting Phase 0",
|
||||
"status": "pending"
|
||||
},
|
||||
{
|
||||
"content": "Phase 2.4: Remove artificial 8ms stream delay",
|
||||
"activeForm": "Awaiting Phase 0",
|
||||
"status": "pending"
|
||||
},
|
||||
{
|
||||
"content": "Phase 3.1: Collapsible tool output",
|
||||
"activeForm": "Awaiting Phase 0",
|
||||
"status": "pending"
|
||||
}
|
||||
]
|
||||
@@ -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`*
|
||||
@@ -1,3 +0,0 @@
|
||||
version = "12"
|
||||
|
||||
[overrides]
|
||||
2
rust/Cargo.lock
generated
2
rust/Cargo.lock
generated
@@ -1545,10 +1545,12 @@ dependencies = [
|
||||
name = "tools"
|
||||
version = "0.1.0"
|
||||
dependencies = [
|
||||
"api",
|
||||
"reqwest",
|
||||
"runtime",
|
||||
"serde",
|
||||
"serde_json",
|
||||
"tokio",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
|
||||
@@ -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`*
|
||||
@@ -4,8 +4,8 @@ mod sse;
|
||||
mod types;
|
||||
|
||||
pub use client::{
|
||||
oauth_token_is_expired, read_base_url, resolve_saved_oauth_token,
|
||||
resolve_startup_auth_source, AnthropicClient, AuthSource, MessageStream, OAuthTokenSet,
|
||||
oauth_token_is_expired, read_base_url, resolve_saved_oauth_token, resolve_startup_auth_source,
|
||||
AnthropicClient, AuthSource, MessageStream, OAuthTokenSet,
|
||||
};
|
||||
pub use error::ApiError;
|
||||
pub use sse::{parse_frame, SseParser};
|
||||
|
||||
@@ -22,7 +22,7 @@ use commands::{
|
||||
};
|
||||
use compat_harness::{extract_manifest, UpstreamPaths};
|
||||
use init::initialize_repo;
|
||||
use render::{MarkdownStreamState, Spinner, TerminalRenderer};
|
||||
use render::{Spinner, TerminalRenderer};
|
||||
use runtime::{
|
||||
clear_oauth_credentials, generate_pkce_pair, generate_state, load_system_prompt,
|
||||
parse_oauth_callback_request_target, save_oauth_credentials, ApiClient, ApiRequest,
|
||||
@@ -2011,8 +2011,6 @@ impl ApiClient for AnthropicRuntimeClient {
|
||||
} else {
|
||||
&mut sink
|
||||
};
|
||||
let renderer = TerminalRenderer::new();
|
||||
let mut markdown_stream = MarkdownStreamState::default();
|
||||
let mut events = Vec::new();
|
||||
let mut pending_tool: Option<(String, String, String)> = None;
|
||||
let mut saw_stop = false;
|
||||
@@ -2040,11 +2038,9 @@ impl ApiClient for AnthropicRuntimeClient {
|
||||
ApiStreamEvent::ContentBlockDelta(delta) => match delta.delta {
|
||||
ContentBlockDelta::TextDelta { text } => {
|
||||
if !text.is_empty() {
|
||||
if let Some(rendered) = markdown_stream.push(&renderer, &text) {
|
||||
write!(out, "{rendered}")
|
||||
.and_then(|()| out.flush())
|
||||
.map_err(|error| RuntimeError::new(error.to_string()))?;
|
||||
}
|
||||
write!(out, "{text}")
|
||||
.and_then(|()| out.flush())
|
||||
.map_err(|error| RuntimeError::new(error.to_string()))?;
|
||||
events.push(AssistantEvent::TextDelta(text));
|
||||
}
|
||||
}
|
||||
@@ -2055,11 +2051,6 @@ impl ApiClient for AnthropicRuntimeClient {
|
||||
}
|
||||
},
|
||||
ApiStreamEvent::ContentBlockStop(_) => {
|
||||
if let Some(rendered) = markdown_stream.flush(&renderer) {
|
||||
write!(out, "{rendered}")
|
||||
.and_then(|()| out.flush())
|
||||
.map_err(|error| RuntimeError::new(error.to_string()))?;
|
||||
}
|
||||
if let Some((id, name, input)) = pending_tool.take() {
|
||||
// Display tool call now that input is fully accumulated
|
||||
writeln!(out, "\n{}", format_tool_call_start(&name, &input))
|
||||
@@ -2078,11 +2069,6 @@ impl ApiClient for AnthropicRuntimeClient {
|
||||
}
|
||||
ApiStreamEvent::MessageStop(_) => {
|
||||
saw_stop = true;
|
||||
if let Some(rendered) = markdown_stream.flush(&renderer) {
|
||||
write!(out, "{rendered}")
|
||||
.and_then(|()| out.flush())
|
||||
.map_err(|error| RuntimeError::new(error.to_string()))?;
|
||||
}
|
||||
events.push(AssistantEvent::MessageStop);
|
||||
}
|
||||
}
|
||||
@@ -2185,49 +2171,56 @@ fn format_tool_call_start(name: &str, input: &str) -> String {
|
||||
serde_json::from_str(input).unwrap_or(serde_json::Value::String(input.to_string()));
|
||||
|
||||
let detail = match name {
|
||||
"bash" | "Bash" => format_bash_call(&parsed),
|
||||
"read_file" | "Read" => {
|
||||
let path = extract_tool_path(&parsed);
|
||||
format!("\x1b[2m📄 Reading {path}…\x1b[0m")
|
||||
}
|
||||
"bash" | "Bash" => parsed
|
||||
.get("command")
|
||||
.and_then(|v| v.as_str())
|
||||
.map(|cmd| truncate_for_summary(cmd, 120))
|
||||
.unwrap_or_default(),
|
||||
"read_file" | "Read" => parsed
|
||||
.get("file_path")
|
||||
.or_else(|| parsed.get("path"))
|
||||
.and_then(|v| v.as_str())
|
||||
.unwrap_or("?")
|
||||
.to_string(),
|
||||
"write_file" | "Write" => {
|
||||
let path = extract_tool_path(&parsed);
|
||||
let path = parsed
|
||||
.get("file_path")
|
||||
.or_else(|| parsed.get("path"))
|
||||
.and_then(|v| v.as_str())
|
||||
.unwrap_or("?");
|
||||
let lines = parsed
|
||||
.get("content")
|
||||
.and_then(|value| value.as_str())
|
||||
.map_or(0, |content| content.lines().count());
|
||||
format!("\x1b[1;32m✏️ Writing {path}\x1b[0m \x1b[2m({lines} lines)\x1b[0m")
|
||||
.and_then(|v| v.as_str())
|
||||
.map_or(0, |c| c.lines().count());
|
||||
format!("{path} ({lines} lines)")
|
||||
}
|
||||
"edit_file" | "Edit" => {
|
||||
let path = extract_tool_path(&parsed);
|
||||
let old_value = parsed
|
||||
.get("old_string")
|
||||
.or_else(|| parsed.get("oldString"))
|
||||
.and_then(|value| value.as_str())
|
||||
.unwrap_or_default();
|
||||
let new_value = parsed
|
||||
.get("new_string")
|
||||
.or_else(|| parsed.get("newString"))
|
||||
.and_then(|value| value.as_str())
|
||||
.unwrap_or_default();
|
||||
format!(
|
||||
"\x1b[1;33m📝 Editing {path}\x1b[0m{}",
|
||||
format_patch_preview(old_value, new_value)
|
||||
.map(|preview| format!("\n{preview}"))
|
||||
.unwrap_or_default()
|
||||
)
|
||||
let path = parsed
|
||||
.get("file_path")
|
||||
.or_else(|| parsed.get("path"))
|
||||
.and_then(|v| v.as_str())
|
||||
.unwrap_or("?");
|
||||
path.to_string()
|
||||
}
|
||||
"glob_search" | "Glob" => format_search_start("🔎 Glob", &parsed),
|
||||
"grep_search" | "Grep" => format_search_start("🔎 Grep", &parsed),
|
||||
"glob_search" | "Glob" => parsed
|
||||
.get("pattern")
|
||||
.and_then(|v| v.as_str())
|
||||
.unwrap_or("?")
|
||||
.to_string(),
|
||||
"grep_search" | "Grep" => parsed
|
||||
.get("pattern")
|
||||
.and_then(|v| v.as_str())
|
||||
.unwrap_or("?")
|
||||
.to_string(),
|
||||
"web_search" | "WebSearch" => parsed
|
||||
.get("query")
|
||||
.and_then(|value| value.as_str())
|
||||
.and_then(|v| v.as_str())
|
||||
.unwrap_or("?")
|
||||
.to_string(),
|
||||
_ => summarize_tool_payload(input),
|
||||
};
|
||||
|
||||
let border = "─".repeat(name.len() + 8);
|
||||
let border = "─".repeat(name.len() + 6);
|
||||
format!(
|
||||
"\x1b[38;5;245m╭─ \x1b[1;36m{name}\x1b[0;38;5;245m ─╮\x1b[0m\n\x1b[38;5;245m│\x1b[0m {detail}\n\x1b[38;5;245m╰{border}╯\x1b[0m"
|
||||
)
|
||||
@@ -2239,269 +2232,8 @@ fn format_tool_result(name: &str, output: &str, is_error: bool) -> String {
|
||||
} else {
|
||||
"\x1b[1;32m✓\x1b[0m"
|
||||
};
|
||||
if is_error {
|
||||
let summary = truncate_for_summary(output.trim(), 160);
|
||||
return if summary.is_empty() {
|
||||
format!("{icon} \x1b[38;5;245m{name}\x1b[0m")
|
||||
} else {
|
||||
format!("{icon} \x1b[38;5;245m{name}\x1b[0m\n\x1b[38;5;203m{summary}\x1b[0m")
|
||||
};
|
||||
}
|
||||
|
||||
let parsed: serde_json::Value =
|
||||
serde_json::from_str(output).unwrap_or(serde_json::Value::String(output.to_string()));
|
||||
match name {
|
||||
"bash" | "Bash" => format_bash_result(icon, &parsed),
|
||||
"read_file" | "Read" => format_read_result(icon, &parsed),
|
||||
"write_file" | "Write" => format_write_result(icon, &parsed),
|
||||
"edit_file" | "Edit" => format_edit_result(icon, &parsed),
|
||||
"glob_search" | "Glob" => format_glob_result(icon, &parsed),
|
||||
"grep_search" | "Grep" => format_grep_result(icon, &parsed),
|
||||
_ => {
|
||||
let summary = truncate_for_summary(output.trim(), 200);
|
||||
format!("{icon} \x1b[38;5;245m{name}:\x1b[0m {summary}")
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
fn extract_tool_path(parsed: &serde_json::Value) -> String {
|
||||
parsed
|
||||
.get("file_path")
|
||||
.or_else(|| parsed.get("filePath"))
|
||||
.or_else(|| parsed.get("path"))
|
||||
.and_then(|value| value.as_str())
|
||||
.unwrap_or("?")
|
||||
.to_string()
|
||||
}
|
||||
|
||||
fn format_search_start(label: &str, parsed: &serde_json::Value) -> String {
|
||||
let pattern = parsed
|
||||
.get("pattern")
|
||||
.and_then(|value| value.as_str())
|
||||
.unwrap_or("?");
|
||||
let scope = parsed
|
||||
.get("path")
|
||||
.and_then(|value| value.as_str())
|
||||
.unwrap_or(".");
|
||||
format!("{label} {pattern}\n\x1b[2min {scope}\x1b[0m")
|
||||
}
|
||||
|
||||
fn format_patch_preview(old_value: &str, new_value: &str) -> Option<String> {
|
||||
if old_value.is_empty() && new_value.is_empty() {
|
||||
return None;
|
||||
}
|
||||
Some(format!(
|
||||
"\x1b[38;5;203m- {}\x1b[0m\n\x1b[38;5;70m+ {}\x1b[0m",
|
||||
truncate_for_summary(first_visible_line(old_value), 72),
|
||||
truncate_for_summary(first_visible_line(new_value), 72)
|
||||
))
|
||||
}
|
||||
|
||||
fn format_bash_call(parsed: &serde_json::Value) -> String {
|
||||
let command = parsed
|
||||
.get("command")
|
||||
.and_then(|value| value.as_str())
|
||||
.unwrap_or_default();
|
||||
if command.is_empty() {
|
||||
String::new()
|
||||
} else {
|
||||
format!(
|
||||
"\x1b[48;5;236;38;5;255m $ {} \x1b[0m",
|
||||
truncate_for_summary(command, 160)
|
||||
)
|
||||
}
|
||||
}
|
||||
|
||||
fn first_visible_line(text: &str) -> &str {
|
||||
text.lines()
|
||||
.find(|line| !line.trim().is_empty())
|
||||
.unwrap_or(text)
|
||||
}
|
||||
|
||||
fn format_bash_result(icon: &str, parsed: &serde_json::Value) -> String {
|
||||
let mut lines = vec![format!("{icon} \x1b[38;5;245mbash\x1b[0m")];
|
||||
if let Some(task_id) = parsed
|
||||
.get("backgroundTaskId")
|
||||
.and_then(|value| value.as_str())
|
||||
{
|
||||
lines[0].push_str(&format!(" backgrounded ({task_id})"));
|
||||
} else if let Some(status) = parsed
|
||||
.get("returnCodeInterpretation")
|
||||
.and_then(|value| value.as_str())
|
||||
.filter(|status| !status.is_empty())
|
||||
{
|
||||
lines[0].push_str(&format!(" {status}"));
|
||||
}
|
||||
|
||||
if let Some(stdout) = parsed.get("stdout").and_then(|value| value.as_str()) {
|
||||
if !stdout.trim().is_empty() {
|
||||
lines.push(stdout.trim_end().to_string());
|
||||
}
|
||||
}
|
||||
if let Some(stderr) = parsed.get("stderr").and_then(|value| value.as_str()) {
|
||||
if !stderr.trim().is_empty() {
|
||||
lines.push(format!("\x1b[38;5;203m{}\x1b[0m", stderr.trim_end()));
|
||||
}
|
||||
}
|
||||
|
||||
lines.join("\n\n")
|
||||
}
|
||||
|
||||
fn format_read_result(icon: &str, parsed: &serde_json::Value) -> String {
|
||||
let file = parsed.get("file").unwrap_or(parsed);
|
||||
let path = extract_tool_path(file);
|
||||
let start_line = file
|
||||
.get("startLine")
|
||||
.and_then(|value| value.as_u64())
|
||||
.unwrap_or(1);
|
||||
let num_lines = file
|
||||
.get("numLines")
|
||||
.and_then(|value| value.as_u64())
|
||||
.unwrap_or(0);
|
||||
let total_lines = file
|
||||
.get("totalLines")
|
||||
.and_then(|value| value.as_u64())
|
||||
.unwrap_or(num_lines);
|
||||
let content = file
|
||||
.get("content")
|
||||
.and_then(|value| value.as_str())
|
||||
.unwrap_or_default();
|
||||
let end_line = start_line.saturating_add(num_lines.saturating_sub(1));
|
||||
|
||||
format!(
|
||||
"{icon} \x1b[2m📄 Read {path} (lines {}-{} of {})\x1b[0m\n{}",
|
||||
start_line,
|
||||
end_line.max(start_line),
|
||||
total_lines,
|
||||
content
|
||||
)
|
||||
}
|
||||
|
||||
fn format_write_result(icon: &str, parsed: &serde_json::Value) -> String {
|
||||
let path = extract_tool_path(parsed);
|
||||
let kind = parsed
|
||||
.get("type")
|
||||
.and_then(|value| value.as_str())
|
||||
.unwrap_or("write");
|
||||
let line_count = parsed
|
||||
.get("content")
|
||||
.and_then(|value| value.as_str())
|
||||
.map(|content| content.lines().count())
|
||||
.unwrap_or(0);
|
||||
format!(
|
||||
"{icon} \x1b[1;32m✏️ {} {path}\x1b[0m \x1b[2m({line_count} lines)\x1b[0m",
|
||||
if kind == "create" { "Wrote" } else { "Updated" },
|
||||
)
|
||||
}
|
||||
|
||||
fn format_structured_patch_preview(parsed: &serde_json::Value) -> Option<String> {
|
||||
let hunks = parsed.get("structuredPatch")?.as_array()?;
|
||||
let mut preview = Vec::new();
|
||||
for hunk in hunks.iter().take(2) {
|
||||
let lines = hunk.get("lines")?.as_array()?;
|
||||
for line in lines.iter().filter_map(|value| value.as_str()).take(6) {
|
||||
match line.chars().next() {
|
||||
Some('+') => preview.push(format!("\x1b[38;5;70m{line}\x1b[0m")),
|
||||
Some('-') => preview.push(format!("\x1b[38;5;203m{line}\x1b[0m")),
|
||||
_ => preview.push(line.to_string()),
|
||||
}
|
||||
}
|
||||
}
|
||||
if preview.is_empty() {
|
||||
None
|
||||
} else {
|
||||
Some(preview.join("\n"))
|
||||
}
|
||||
}
|
||||
|
||||
fn format_edit_result(icon: &str, parsed: &serde_json::Value) -> String {
|
||||
let path = extract_tool_path(parsed);
|
||||
let suffix = if parsed
|
||||
.get("replaceAll")
|
||||
.and_then(|value| value.as_bool())
|
||||
.unwrap_or(false)
|
||||
{
|
||||
" (replace all)"
|
||||
} else {
|
||||
""
|
||||
};
|
||||
let preview = format_structured_patch_preview(parsed).or_else(|| {
|
||||
let old_value = parsed
|
||||
.get("oldString")
|
||||
.and_then(|value| value.as_str())
|
||||
.unwrap_or_default();
|
||||
let new_value = parsed
|
||||
.get("newString")
|
||||
.and_then(|value| value.as_str())
|
||||
.unwrap_or_default();
|
||||
format_patch_preview(old_value, new_value)
|
||||
});
|
||||
|
||||
match preview {
|
||||
Some(preview) => format!("{icon} \x1b[1;33m📝 Edited {path}{suffix}\x1b[0m\n{preview}"),
|
||||
None => format!("{icon} \x1b[1;33m📝 Edited {path}{suffix}\x1b[0m"),
|
||||
}
|
||||
}
|
||||
|
||||
fn format_glob_result(icon: &str, parsed: &serde_json::Value) -> String {
|
||||
let num_files = parsed
|
||||
.get("numFiles")
|
||||
.and_then(|value| value.as_u64())
|
||||
.unwrap_or(0);
|
||||
let filenames = parsed
|
||||
.get("filenames")
|
||||
.and_then(|value| value.as_array())
|
||||
.map(|files| {
|
||||
files
|
||||
.iter()
|
||||
.filter_map(|value| value.as_str())
|
||||
.take(8)
|
||||
.collect::<Vec<_>>()
|
||||
.join("\n")
|
||||
})
|
||||
.unwrap_or_default();
|
||||
if filenames.is_empty() {
|
||||
format!("{icon} \x1b[38;5;245mglob_search\x1b[0m matched {num_files} files")
|
||||
} else {
|
||||
format!("{icon} \x1b[38;5;245mglob_search\x1b[0m matched {num_files} files\n{filenames}")
|
||||
}
|
||||
}
|
||||
|
||||
fn format_grep_result(icon: &str, parsed: &serde_json::Value) -> String {
|
||||
let num_matches = parsed
|
||||
.get("numMatches")
|
||||
.and_then(|value| value.as_u64())
|
||||
.unwrap_or(0);
|
||||
let num_files = parsed
|
||||
.get("numFiles")
|
||||
.and_then(|value| value.as_u64())
|
||||
.unwrap_or(0);
|
||||
let content = parsed
|
||||
.get("content")
|
||||
.and_then(|value| value.as_str())
|
||||
.unwrap_or_default();
|
||||
let filenames = parsed
|
||||
.get("filenames")
|
||||
.and_then(|value| value.as_array())
|
||||
.map(|files| {
|
||||
files
|
||||
.iter()
|
||||
.filter_map(|value| value.as_str())
|
||||
.take(8)
|
||||
.collect::<Vec<_>>()
|
||||
.join("\n")
|
||||
})
|
||||
.unwrap_or_default();
|
||||
let summary = format!(
|
||||
"{icon} \x1b[38;5;245mgrep_search\x1b[0m {num_matches} matches across {num_files} files"
|
||||
);
|
||||
if !content.trim().is_empty() {
|
||||
format!("{summary}\n{}", content.trim_end())
|
||||
} else if !filenames.is_empty() {
|
||||
format!("{summary}\n{filenames}")
|
||||
} else {
|
||||
summary
|
||||
}
|
||||
let summary = truncate_for_summary(output.trim(), 200);
|
||||
format!("{icon} \x1b[38;5;245m{name}:\x1b[0m {summary}")
|
||||
}
|
||||
|
||||
fn summarize_tool_payload(payload: &str) -> String {
|
||||
@@ -2532,8 +2264,7 @@ fn push_output_block(
|
||||
match block {
|
||||
OutputContentBlock::Text { text } => {
|
||||
if !text.is_empty() {
|
||||
let rendered = TerminalRenderer::new().markdown_to_ansi(&text);
|
||||
write!(out, "{rendered}")
|
||||
write!(out, "{text}")
|
||||
.and_then(|()| out.flush())
|
||||
.map_err(|error| RuntimeError::new(error.to_string()))?;
|
||||
events.push(AssistantEvent::TextDelta(text));
|
||||
@@ -3325,35 +3056,9 @@ mod tests {
|
||||
assert!(start.contains("read_file"));
|
||||
assert!(start.contains("src/main.rs"));
|
||||
|
||||
let done = format_tool_result(
|
||||
"read_file",
|
||||
r#"{"file":{"filePath":"src/main.rs","content":"hello","numLines":1,"startLine":1,"totalLines":1}}"#,
|
||||
false,
|
||||
);
|
||||
assert!(done.contains("📄 Read src/main.rs"));
|
||||
assert!(done.contains("hello"));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn push_output_block_renders_markdown_text() {
|
||||
let mut out = Vec::new();
|
||||
let mut events = Vec::new();
|
||||
let mut pending_tool = None;
|
||||
|
||||
push_output_block(
|
||||
OutputContentBlock::Text {
|
||||
text: "# Heading".to_string(),
|
||||
},
|
||||
&mut out,
|
||||
&mut events,
|
||||
&mut pending_tool,
|
||||
false,
|
||||
)
|
||||
.expect("text block should render");
|
||||
|
||||
let rendered = String::from_utf8(out).expect("utf8");
|
||||
assert!(rendered.contains("Heading"));
|
||||
assert!(rendered.contains('\u{1b}'));
|
||||
let done = format_tool_result("read_file", r#"{"contents":"hello"}"#, false);
|
||||
assert!(done.contains("read_file:"));
|
||||
assert!(done.contains("contents"));
|
||||
}
|
||||
|
||||
#[test]
|
||||
|
||||
@@ -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();
|
||||
|
||||
if matches!(self.heading_level, Some(1 | 2)) || self.strong > 0 {
|
||||
style = style.bold();
|
||||
let mut styled = text.to_string();
|
||||
if self.strong > 0 {
|
||||
styled = format!("{}", styled.bold().with(theme.strong));
|
||||
}
|
||||
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));
|
||||
}
|
||||
|
||||
format!("{style}")
|
||||
styled
|
||||
}
|
||||
|
||||
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);
|
||||
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
|
||||
} 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, .. }) => {
|
||||
self.start_heading(state, level as u8, output)
|
||||
}
|
||||
Event::End(TagEnd::Paragraph) => output.push_str("\n\n"),
|
||||
Event::Start(Tag::Heading { level, .. }) => self.start_heading(level as u8, output),
|
||||
Event::End(TagEnd::Heading(..) | 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)
|
||||
.underlined()
|
||||
.with(self.color_theme.link)
|
||||
);
|
||||
state.append_raw(output, &rendered);
|
||||
}
|
||||
let rendered = format!(
|
||||
"{}",
|
||||
format!("[{dest_url}]")
|
||||
.underlined()
|
||||
.with(self.color_theme.link)
|
||||
);
|
||||
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) => {
|
||||
@@ -422,15 +369,19 @@ impl TerminalRenderer {
|
||||
}
|
||||
}
|
||||
Event::Start(Tag::Paragraph | Tag::MetadataBlock(..) | _)
|
||||
| Event::End(TagEnd::Image | TagEnd::MetadataBlock(..) | _) => {}
|
||||
| Event::End(TagEnd::Link | TagEnd::Image | TagEnd::MetadataBlock(..) | _) => {}
|
||||
}
|
||||
}
|
||||
|
||||
fn start_heading(&self, state: &mut RenderState, level: u8, output: &mut String) {
|
||||
state.heading_level = Some(level);
|
||||
if !output.is_empty() {
|
||||
output.push('\n');
|
||||
}
|
||||
fn start_heading(&self, level: u8, output: &mut String) {
|
||||
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) {
|
||||
@@ -454,27 +405,20 @@ impl TerminalRenderer {
|
||||
}
|
||||
|
||||
fn start_code_block(&self, code_language: &str, output: &mut String) {
|
||||
let label = if code_language.is_empty() {
|
||||
"code".to_string()
|
||||
} else {
|
||||
code_language.to_string()
|
||||
};
|
||||
let _ = writeln!(
|
||||
output,
|
||||
"{}",
|
||||
format!("╭─ {label}")
|
||||
.bold()
|
||||
.with(self.color_theme.code_block_border)
|
||||
);
|
||||
if !code_language.is_empty() {
|
||||
let _ = writeln!(
|
||||
output,
|
||||
"{}",
|
||||
format!("╭─ {code_language}").with(self.color_theme.heading)
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
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!(
|
||||
output,
|
||||
"{}",
|
||||
"╰─".bold().with(self.color_theme.code_block_border)
|
||||
);
|
||||
if !code_language.is_empty() {
|
||||
let _ = write!(output, "{}", "╰─".with(self.color_theme.heading));
|
||||
}
|
||||
output.push_str("\n\n");
|
||||
}
|
||||
|
||||
@@ -489,7 +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);
|
||||
}
|
||||
}
|
||||
|
||||
@@ -576,10 +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(&apply_code_block_background(&escaped));
|
||||
colored_output.push_str(&as_24_bit_terminal_escaped(&ranges[..], false));
|
||||
}
|
||||
Err(_) => colored_output.push_str(&apply_code_block_background(line)),
|
||||
Err(_) => colored_output.push_str(line),
|
||||
}
|
||||
}
|
||||
|
||||
@@ -587,83 +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);
|
||||
write!(out, "{rendered_markdown}")?;
|
||||
if !rendered_markdown.ends_with('\n') {
|
||||
writeln!(out)?;
|
||||
let rendered_markdown = self.render_markdown(markdown);
|
||||
for chunk in rendered_markdown.split_inclusive(char::is_whitespace) {
|
||||
write!(out, "{chunk}")?;
|
||||
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()
|
||||
}
|
||||
@@ -692,7 +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() {
|
||||
@@ -706,28 +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]
|
||||
@@ -758,26 +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();
|
||||
|
||||
@@ -6,10 +6,12 @@ license.workspace = true
|
||||
publish.workspace = true
|
||||
|
||||
[dependencies]
|
||||
api = { path = "../api" }
|
||||
runtime = { path = "../runtime" }
|
||||
reqwest = { version = "0.12", default-features = false, features = ["blocking", "rustls-tls"] }
|
||||
serde = { version = "1", features = ["derive"] }
|
||||
serde_json = "1"
|
||||
tokio = { version = "1", features = ["rt-multi-thread"] }
|
||||
|
||||
[lints]
|
||||
workspace = true
|
||||
|
||||
@@ -3,10 +3,17 @@ use std::path::{Path, PathBuf};
|
||||
use std::process::Command;
|
||||
use std::time::{Duration, Instant};
|
||||
|
||||
use api::{
|
||||
read_base_url, AnthropicClient, ContentBlockDelta, InputContentBlock, InputMessage,
|
||||
MessageRequest, MessageResponse, OutputContentBlock, StreamEvent as ApiStreamEvent, ToolChoice,
|
||||
ToolDefinition, ToolResultContentBlock,
|
||||
};
|
||||
use reqwest::blocking::Client;
|
||||
use runtime::{
|
||||
edit_file, execute_bash, glob_search, grep_search, read_file, write_file, BashCommandInput,
|
||||
GrepSearchInput, PermissionMode,
|
||||
edit_file, execute_bash, glob_search, grep_search, load_system_prompt, read_file, write_file,
|
||||
ApiClient, ApiRequest, AssistantEvent, BashCommandInput, ContentBlock, ConversationMessage,
|
||||
ConversationRuntime, GrepSearchInput, MessageRole, PermissionMode, PermissionPolicy,
|
||||
RuntimeError, Session, TokenUsage, ToolError, ToolExecutor,
|
||||
};
|
||||
use serde::{Deserialize, Serialize};
|
||||
use serde_json::{json, Value};
|
||||
@@ -702,7 +709,7 @@ struct SkillOutput {
|
||||
prompt: String,
|
||||
}
|
||||
|
||||
#[derive(Debug, Serialize, Deserialize)]
|
||||
#[derive(Debug, Clone, Serialize, Deserialize)]
|
||||
struct AgentOutput {
|
||||
#[serde(rename = "agentId")]
|
||||
agent_id: String,
|
||||
@@ -718,6 +725,20 @@ struct AgentOutput {
|
||||
manifest_file: String,
|
||||
#[serde(rename = "createdAt")]
|
||||
created_at: String,
|
||||
#[serde(rename = "startedAt", skip_serializing_if = "Option::is_none")]
|
||||
started_at: Option<String>,
|
||||
#[serde(rename = "completedAt", skip_serializing_if = "Option::is_none")]
|
||||
completed_at: Option<String>,
|
||||
#[serde(skip_serializing_if = "Option::is_none")]
|
||||
error: Option<String>,
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone)]
|
||||
struct AgentJob {
|
||||
manifest: AgentOutput,
|
||||
prompt: String,
|
||||
system_prompt: Vec<String>,
|
||||
allowed_tools: BTreeSet<String>,
|
||||
}
|
||||
|
||||
#[derive(Debug, Serialize)]
|
||||
@@ -1259,7 +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"));
|
||||
}
|
||||
@@ -1315,7 +1344,18 @@ fn resolve_skill_path(skill: &str) -> Result<std::path::PathBuf, String> {
|
||||
Err(format!("unknown skill: {requested}"))
|
||||
}
|
||||
|
||||
const DEFAULT_AGENT_MODEL: &str = "claude-opus-4-6";
|
||||
const DEFAULT_AGENT_SYSTEM_DATE: &str = "2026-03-31";
|
||||
const DEFAULT_AGENT_MAX_ITERATIONS: usize = 32;
|
||||
|
||||
fn execute_agent(input: AgentInput) -> Result<AgentOutput, String> {
|
||||
execute_agent_with_spawn(input, spawn_agent_job)
|
||||
}
|
||||
|
||||
fn execute_agent_with_spawn<F>(input: AgentInput, spawn_fn: F) -> Result<AgentOutput, String>
|
||||
where
|
||||
F: FnOnce(AgentJob) -> Result<(), String>,
|
||||
{
|
||||
if input.description.trim().is_empty() {
|
||||
return Err(String::from("description must not be empty"));
|
||||
}
|
||||
@@ -1329,6 +1369,7 @@ fn execute_agent(input: AgentInput) -> Result<AgentOutput, String> {
|
||||
let output_file = output_dir.join(format!("{agent_id}.md"));
|
||||
let manifest_file = output_dir.join(format!("{agent_id}.json"));
|
||||
let normalized_subagent_type = normalize_subagent_type(input.subagent_type.as_deref());
|
||||
let model = resolve_agent_model(input.model.as_deref());
|
||||
let agent_name = input
|
||||
.name
|
||||
.as_deref()
|
||||
@@ -1336,6 +1377,8 @@ fn execute_agent(input: AgentInput) -> Result<AgentOutput, String> {
|
||||
.filter(|name| !name.is_empty())
|
||||
.unwrap_or_else(|| slugify_agent_name(&input.description));
|
||||
let created_at = iso8601_now();
|
||||
let system_prompt = build_agent_system_prompt(&normalized_subagent_type)?;
|
||||
let allowed_tools = allowed_tools_for_subagent(&normalized_subagent_type);
|
||||
|
||||
let output_contents = format!(
|
||||
"# Agent Task
|
||||
@@ -1359,21 +1402,514 @@ fn execute_agent(input: AgentInput) -> Result<AgentOutput, String> {
|
||||
name: agent_name,
|
||||
description: input.description,
|
||||
subagent_type: Some(normalized_subagent_type),
|
||||
model: input.model,
|
||||
status: String::from("queued"),
|
||||
model: Some(model),
|
||||
status: String::from("running"),
|
||||
output_file: output_file.display().to_string(),
|
||||
manifest_file: manifest_file.display().to_string(),
|
||||
created_at,
|
||||
created_at: created_at.clone(),
|
||||
started_at: Some(created_at),
|
||||
completed_at: None,
|
||||
error: None,
|
||||
};
|
||||
std::fs::write(
|
||||
&manifest_file,
|
||||
serde_json::to_string_pretty(&manifest).map_err(|error| error.to_string())?,
|
||||
)
|
||||
.map_err(|error| error.to_string())?;
|
||||
write_agent_manifest(&manifest)?;
|
||||
|
||||
let manifest_for_spawn = manifest.clone();
|
||||
let job = AgentJob {
|
||||
manifest: manifest_for_spawn,
|
||||
prompt: input.prompt,
|
||||
system_prompt,
|
||||
allowed_tools,
|
||||
};
|
||||
if let Err(error) = spawn_fn(job) {
|
||||
let error = format!("failed to spawn sub-agent: {error}");
|
||||
persist_agent_terminal_state(&manifest, "failed", None, Some(error.clone()))?;
|
||||
return Err(error);
|
||||
}
|
||||
|
||||
Ok(manifest)
|
||||
}
|
||||
|
||||
fn spawn_agent_job(job: AgentJob) -> Result<(), String> {
|
||||
let thread_name = format!("clawd-agent-{}", job.manifest.agent_id);
|
||||
std::thread::Builder::new()
|
||||
.name(thread_name)
|
||||
.spawn(move || {
|
||||
let result =
|
||||
std::panic::catch_unwind(std::panic::AssertUnwindSafe(|| run_agent_job(&job)));
|
||||
match result {
|
||||
Ok(Ok(())) => {}
|
||||
Ok(Err(error)) => {
|
||||
let _ =
|
||||
persist_agent_terminal_state(&job.manifest, "failed", None, Some(error));
|
||||
}
|
||||
Err(_) => {
|
||||
let _ = persist_agent_terminal_state(
|
||||
&job.manifest,
|
||||
"failed",
|
||||
None,
|
||||
Some(String::from("sub-agent thread panicked")),
|
||||
);
|
||||
}
|
||||
}
|
||||
})
|
||||
.map(|_| ())
|
||||
.map_err(|error| error.to_string())
|
||||
}
|
||||
|
||||
fn run_agent_job(job: &AgentJob) -> Result<(), String> {
|
||||
let mut runtime = build_agent_runtime(job)?.with_max_iterations(DEFAULT_AGENT_MAX_ITERATIONS);
|
||||
let summary = runtime
|
||||
.run_turn(job.prompt.clone(), None)
|
||||
.map_err(|error| error.to_string())?;
|
||||
let final_text = final_assistant_text(&summary);
|
||||
persist_agent_terminal_state(&job.manifest, "completed", Some(final_text.as_str()), None)
|
||||
}
|
||||
|
||||
fn build_agent_runtime(
|
||||
job: &AgentJob,
|
||||
) -> Result<ConversationRuntime<AnthropicRuntimeClient, SubagentToolExecutor>, String> {
|
||||
let model = job
|
||||
.manifest
|
||||
.model
|
||||
.clone()
|
||||
.unwrap_or_else(|| DEFAULT_AGENT_MODEL.to_string());
|
||||
let allowed_tools = job.allowed_tools.clone();
|
||||
let api_client = AnthropicRuntimeClient::new(model, allowed_tools.clone())?;
|
||||
let tool_executor = SubagentToolExecutor::new(allowed_tools);
|
||||
Ok(ConversationRuntime::new(
|
||||
Session::new(),
|
||||
api_client,
|
||||
tool_executor,
|
||||
agent_permission_policy(),
|
||||
job.system_prompt.clone(),
|
||||
))
|
||||
}
|
||||
|
||||
fn build_agent_system_prompt(subagent_type: &str) -> Result<Vec<String>, String> {
|
||||
let cwd = std::env::current_dir().map_err(|error| error.to_string())?;
|
||||
let mut prompt = load_system_prompt(
|
||||
cwd,
|
||||
DEFAULT_AGENT_SYSTEM_DATE.to_string(),
|
||||
std::env::consts::OS,
|
||||
"unknown",
|
||||
)
|
||||
.map_err(|error| error.to_string())?;
|
||||
prompt.push(format!(
|
||||
"You are a background sub-agent of type `{subagent_type}`. Work only on the delegated task, use only the tools available to you, do not ask the user questions, and finish with a concise result."
|
||||
));
|
||||
Ok(prompt)
|
||||
}
|
||||
|
||||
fn resolve_agent_model(model: Option<&str>) -> String {
|
||||
model
|
||||
.map(str::trim)
|
||||
.filter(|model| !model.is_empty())
|
||||
.unwrap_or(DEFAULT_AGENT_MODEL)
|
||||
.to_string()
|
||||
}
|
||||
|
||||
fn allowed_tools_for_subagent(subagent_type: &str) -> BTreeSet<String> {
|
||||
let tools = match subagent_type {
|
||||
"Explore" => vec![
|
||||
"read_file",
|
||||
"glob_search",
|
||||
"grep_search",
|
||||
"WebFetch",
|
||||
"WebSearch",
|
||||
"ToolSearch",
|
||||
"Skill",
|
||||
"StructuredOutput",
|
||||
],
|
||||
"Plan" => vec![
|
||||
"read_file",
|
||||
"glob_search",
|
||||
"grep_search",
|
||||
"WebFetch",
|
||||
"WebSearch",
|
||||
"ToolSearch",
|
||||
"Skill",
|
||||
"TodoWrite",
|
||||
"StructuredOutput",
|
||||
"SendUserMessage",
|
||||
],
|
||||
"Verification" => vec![
|
||||
"bash",
|
||||
"read_file",
|
||||
"glob_search",
|
||||
"grep_search",
|
||||
"WebFetch",
|
||||
"WebSearch",
|
||||
"ToolSearch",
|
||||
"TodoWrite",
|
||||
"StructuredOutput",
|
||||
"SendUserMessage",
|
||||
"PowerShell",
|
||||
],
|
||||
"claude-code-guide" => vec![
|
||||
"read_file",
|
||||
"glob_search",
|
||||
"grep_search",
|
||||
"WebFetch",
|
||||
"WebSearch",
|
||||
"ToolSearch",
|
||||
"Skill",
|
||||
"StructuredOutput",
|
||||
"SendUserMessage",
|
||||
],
|
||||
"statusline-setup" => vec![
|
||||
"bash",
|
||||
"read_file",
|
||||
"write_file",
|
||||
"edit_file",
|
||||
"glob_search",
|
||||
"grep_search",
|
||||
"ToolSearch",
|
||||
],
|
||||
_ => vec![
|
||||
"bash",
|
||||
"read_file",
|
||||
"write_file",
|
||||
"edit_file",
|
||||
"glob_search",
|
||||
"grep_search",
|
||||
"WebFetch",
|
||||
"WebSearch",
|
||||
"TodoWrite",
|
||||
"Skill",
|
||||
"ToolSearch",
|
||||
"NotebookEdit",
|
||||
"Sleep",
|
||||
"SendUserMessage",
|
||||
"Config",
|
||||
"StructuredOutput",
|
||||
"REPL",
|
||||
"PowerShell",
|
||||
],
|
||||
};
|
||||
tools.into_iter().map(str::to_string).collect()
|
||||
}
|
||||
|
||||
fn agent_permission_policy() -> PermissionPolicy {
|
||||
mvp_tool_specs().into_iter().fold(
|
||||
PermissionPolicy::new(PermissionMode::DangerFullAccess),
|
||||
|policy, spec| policy.with_tool_requirement(spec.name, spec.required_permission),
|
||||
)
|
||||
}
|
||||
|
||||
fn write_agent_manifest(manifest: &AgentOutput) -> Result<(), String> {
|
||||
std::fs::write(
|
||||
&manifest.manifest_file,
|
||||
serde_json::to_string_pretty(manifest).map_err(|error| error.to_string())?,
|
||||
)
|
||||
.map_err(|error| error.to_string())
|
||||
}
|
||||
|
||||
fn persist_agent_terminal_state(
|
||||
manifest: &AgentOutput,
|
||||
status: &str,
|
||||
result: Option<&str>,
|
||||
error: Option<String>,
|
||||
) -> Result<(), String> {
|
||||
append_agent_output(
|
||||
&manifest.output_file,
|
||||
&format_agent_terminal_output(status, result, error.as_deref()),
|
||||
)?;
|
||||
let mut next_manifest = manifest.clone();
|
||||
next_manifest.status = status.to_string();
|
||||
next_manifest.completed_at = Some(iso8601_now());
|
||||
next_manifest.error = error;
|
||||
write_agent_manifest(&next_manifest)
|
||||
}
|
||||
|
||||
fn append_agent_output(path: &str, suffix: &str) -> Result<(), String> {
|
||||
use std::io::Write as _;
|
||||
|
||||
let mut file = std::fs::OpenOptions::new()
|
||||
.append(true)
|
||||
.open(path)
|
||||
.map_err(|error| error.to_string())?;
|
||||
file.write_all(suffix.as_bytes())
|
||||
.map_err(|error| error.to_string())
|
||||
}
|
||||
|
||||
fn format_agent_terminal_output(status: &str, result: Option<&str>, error: Option<&str>) -> String {
|
||||
let mut sections = vec![format!("\n## Result\n\n- status: {status}\n")];
|
||||
if let Some(result) = result.filter(|value| !value.trim().is_empty()) {
|
||||
sections.push(format!("\n### Final response\n\n{}\n", result.trim()));
|
||||
}
|
||||
if let Some(error) = error.filter(|value| !value.trim().is_empty()) {
|
||||
sections.push(format!("\n### Error\n\n{}\n", error.trim()));
|
||||
}
|
||||
sections.join("")
|
||||
}
|
||||
|
||||
struct AnthropicRuntimeClient {
|
||||
runtime: tokio::runtime::Runtime,
|
||||
client: AnthropicClient,
|
||||
model: String,
|
||||
allowed_tools: BTreeSet<String>,
|
||||
}
|
||||
|
||||
impl AnthropicRuntimeClient {
|
||||
fn new(model: String, allowed_tools: BTreeSet<String>) -> Result<Self, String> {
|
||||
let client = AnthropicClient::from_env()
|
||||
.map_err(|error| error.to_string())?
|
||||
.with_base_url(read_base_url());
|
||||
Ok(Self {
|
||||
runtime: tokio::runtime::Runtime::new().map_err(|error| error.to_string())?,
|
||||
client,
|
||||
model,
|
||||
allowed_tools,
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
impl ApiClient for AnthropicRuntimeClient {
|
||||
fn stream(&mut self, request: ApiRequest) -> Result<Vec<AssistantEvent>, RuntimeError> {
|
||||
let tools = tool_specs_for_allowed_tools(Some(&self.allowed_tools))
|
||||
.into_iter()
|
||||
.map(|spec| ToolDefinition {
|
||||
name: spec.name.to_string(),
|
||||
description: Some(spec.description.to_string()),
|
||||
input_schema: spec.input_schema,
|
||||
})
|
||||
.collect::<Vec<_>>();
|
||||
let message_request = MessageRequest {
|
||||
model: self.model.clone(),
|
||||
max_tokens: 32_000,
|
||||
messages: convert_messages(&request.messages),
|
||||
system: (!request.system_prompt.is_empty()).then(|| request.system_prompt.join("\n\n")),
|
||||
tools: (!tools.is_empty()).then_some(tools),
|
||||
tool_choice: (!self.allowed_tools.is_empty()).then_some(ToolChoice::Auto),
|
||||
stream: true,
|
||||
};
|
||||
|
||||
self.runtime.block_on(async {
|
||||
let mut stream = self
|
||||
.client
|
||||
.stream_message(&message_request)
|
||||
.await
|
||||
.map_err(|error| RuntimeError::new(error.to_string()))?;
|
||||
let mut events = Vec::new();
|
||||
let mut pending_tool: Option<(String, String, String)> = None;
|
||||
let mut saw_stop = false;
|
||||
|
||||
while let Some(event) = stream
|
||||
.next_event()
|
||||
.await
|
||||
.map_err(|error| RuntimeError::new(error.to_string()))?
|
||||
{
|
||||
match event {
|
||||
ApiStreamEvent::MessageStart(start) => {
|
||||
for block in start.message.content {
|
||||
push_output_block(block, &mut events, &mut pending_tool, true);
|
||||
}
|
||||
}
|
||||
ApiStreamEvent::ContentBlockStart(start) => {
|
||||
push_output_block(
|
||||
start.content_block,
|
||||
&mut events,
|
||||
&mut pending_tool,
|
||||
true,
|
||||
);
|
||||
}
|
||||
ApiStreamEvent::ContentBlockDelta(delta) => match delta.delta {
|
||||
ContentBlockDelta::TextDelta { text } => {
|
||||
if !text.is_empty() {
|
||||
events.push(AssistantEvent::TextDelta(text));
|
||||
}
|
||||
}
|
||||
ContentBlockDelta::InputJsonDelta { partial_json } => {
|
||||
if let Some((_, _, input)) = &mut pending_tool {
|
||||
input.push_str(&partial_json);
|
||||
}
|
||||
}
|
||||
},
|
||||
ApiStreamEvent::ContentBlockStop(_) => {
|
||||
if let Some((id, name, input)) = pending_tool.take() {
|
||||
events.push(AssistantEvent::ToolUse { id, name, input });
|
||||
}
|
||||
}
|
||||
ApiStreamEvent::MessageDelta(delta) => {
|
||||
events.push(AssistantEvent::Usage(TokenUsage {
|
||||
input_tokens: delta.usage.input_tokens,
|
||||
output_tokens: delta.usage.output_tokens,
|
||||
cache_creation_input_tokens: 0,
|
||||
cache_read_input_tokens: 0,
|
||||
}));
|
||||
}
|
||||
ApiStreamEvent::MessageStop(_) => {
|
||||
saw_stop = true;
|
||||
events.push(AssistantEvent::MessageStop);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
if !saw_stop
|
||||
&& events.iter().any(|event| {
|
||||
matches!(event, AssistantEvent::TextDelta(text) if !text.is_empty())
|
||||
|| matches!(event, AssistantEvent::ToolUse { .. })
|
||||
})
|
||||
{
|
||||
events.push(AssistantEvent::MessageStop);
|
||||
}
|
||||
|
||||
if events
|
||||
.iter()
|
||||
.any(|event| matches!(event, AssistantEvent::MessageStop))
|
||||
{
|
||||
return Ok(events);
|
||||
}
|
||||
|
||||
let response = self
|
||||
.client
|
||||
.send_message(&MessageRequest {
|
||||
stream: false,
|
||||
..message_request.clone()
|
||||
})
|
||||
.await
|
||||
.map_err(|error| RuntimeError::new(error.to_string()))?;
|
||||
Ok(response_to_events(response))
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
struct SubagentToolExecutor {
|
||||
allowed_tools: BTreeSet<String>,
|
||||
}
|
||||
|
||||
impl SubagentToolExecutor {
|
||||
fn new(allowed_tools: BTreeSet<String>) -> Self {
|
||||
Self { allowed_tools }
|
||||
}
|
||||
}
|
||||
|
||||
impl ToolExecutor for SubagentToolExecutor {
|
||||
fn execute(&mut self, tool_name: &str, input: &str) -> Result<String, ToolError> {
|
||||
if !self.allowed_tools.contains(tool_name) {
|
||||
return Err(ToolError::new(format!(
|
||||
"tool `{tool_name}` is not enabled for this sub-agent"
|
||||
)));
|
||||
}
|
||||
let value = serde_json::from_str(input)
|
||||
.map_err(|error| ToolError::new(format!("invalid tool input JSON: {error}")))?;
|
||||
execute_tool(tool_name, &value).map_err(ToolError::new)
|
||||
}
|
||||
}
|
||||
|
||||
fn tool_specs_for_allowed_tools(allowed_tools: Option<&BTreeSet<String>>) -> Vec<ToolSpec> {
|
||||
mvp_tool_specs()
|
||||
.into_iter()
|
||||
.filter(|spec| allowed_tools.is_none_or(|allowed| allowed.contains(spec.name)))
|
||||
.collect()
|
||||
}
|
||||
|
||||
fn convert_messages(messages: &[ConversationMessage]) -> Vec<InputMessage> {
|
||||
messages
|
||||
.iter()
|
||||
.filter_map(|message| {
|
||||
let role = match message.role {
|
||||
MessageRole::System | MessageRole::User | MessageRole::Tool => "user",
|
||||
MessageRole::Assistant => "assistant",
|
||||
};
|
||||
let content = message
|
||||
.blocks
|
||||
.iter()
|
||||
.map(|block| match block {
|
||||
ContentBlock::Text { text } => InputContentBlock::Text { text: text.clone() },
|
||||
ContentBlock::ToolUse { id, name, input } => InputContentBlock::ToolUse {
|
||||
id: id.clone(),
|
||||
name: name.clone(),
|
||||
input: serde_json::from_str(input)
|
||||
.unwrap_or_else(|_| serde_json::json!({ "raw": input })),
|
||||
},
|
||||
ContentBlock::ToolResult {
|
||||
tool_use_id,
|
||||
output,
|
||||
is_error,
|
||||
..
|
||||
} => InputContentBlock::ToolResult {
|
||||
tool_use_id: tool_use_id.clone(),
|
||||
content: vec![ToolResultContentBlock::Text {
|
||||
text: output.clone(),
|
||||
}],
|
||||
is_error: *is_error,
|
||||
},
|
||||
})
|
||||
.collect::<Vec<_>>();
|
||||
(!content.is_empty()).then(|| InputMessage {
|
||||
role: role.to_string(),
|
||||
content,
|
||||
})
|
||||
})
|
||||
.collect()
|
||||
}
|
||||
|
||||
fn push_output_block(
|
||||
block: OutputContentBlock,
|
||||
events: &mut Vec<AssistantEvent>,
|
||||
pending_tool: &mut Option<(String, String, String)>,
|
||||
streaming_tool_input: bool,
|
||||
) {
|
||||
match block {
|
||||
OutputContentBlock::Text { text } => {
|
||||
if !text.is_empty() {
|
||||
events.push(AssistantEvent::TextDelta(text));
|
||||
}
|
||||
}
|
||||
OutputContentBlock::ToolUse { id, name, input } => {
|
||||
let initial_input = if streaming_tool_input
|
||||
&& input.is_object()
|
||||
&& input.as_object().is_some_and(serde_json::Map::is_empty)
|
||||
{
|
||||
String::new()
|
||||
} else {
|
||||
input.to_string()
|
||||
};
|
||||
*pending_tool = Some((id, name, initial_input));
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
fn response_to_events(response: MessageResponse) -> Vec<AssistantEvent> {
|
||||
let mut events = Vec::new();
|
||||
let mut pending_tool = None;
|
||||
|
||||
for block in response.content {
|
||||
push_output_block(block, &mut events, &mut pending_tool, false);
|
||||
if let Some((id, name, input)) = pending_tool.take() {
|
||||
events.push(AssistantEvent::ToolUse { id, name, input });
|
||||
}
|
||||
}
|
||||
|
||||
events.push(AssistantEvent::Usage(TokenUsage {
|
||||
input_tokens: response.usage.input_tokens,
|
||||
output_tokens: response.usage.output_tokens,
|
||||
cache_creation_input_tokens: response.usage.cache_creation_input_tokens,
|
||||
cache_read_input_tokens: response.usage.cache_read_input_tokens,
|
||||
}));
|
||||
events.push(AssistantEvent::MessageStop);
|
||||
events
|
||||
}
|
||||
|
||||
fn final_assistant_text(summary: &runtime::TurnSummary) -> String {
|
||||
summary
|
||||
.assistant_messages
|
||||
.last()
|
||||
.map(|message| {
|
||||
message
|
||||
.blocks
|
||||
.iter()
|
||||
.filter_map(|block| match block {
|
||||
ContentBlock::Text { text } => Some(text.as_str()),
|
||||
_ => None,
|
||||
})
|
||||
.collect::<Vec<_>>()
|
||||
.join("")
|
||||
})
|
||||
.unwrap_or_default()
|
||||
}
|
||||
|
||||
#[allow(clippy::needless_pass_by_value)]
|
||||
fn execute_tool_search(input: ToolSearchInput) -> ToolSearchOutput {
|
||||
let deferred = deferred_tool_specs();
|
||||
@@ -2207,7 +2743,7 @@ fn execute_shell_command(
|
||||
persisted_output_path: None,
|
||||
persisted_output_size: None,
|
||||
sandbox_status: None,
|
||||
});
|
||||
});
|
||||
}
|
||||
|
||||
let mut process = std::process::Command::new(shell);
|
||||
@@ -2276,7 +2812,7 @@ Command exceeded timeout of {timeout_ms} ms",
|
||||
persisted_output_path: None,
|
||||
persisted_output_size: None,
|
||||
sandbox_status: None,
|
||||
});
|
||||
});
|
||||
}
|
||||
std::thread::sleep(Duration::from_millis(10));
|
||||
}
|
||||
@@ -2365,6 +2901,7 @@ fn parse_skill_description(contents: &str) -> Option<String> {
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use std::collections::BTreeSet;
|
||||
use std::fs;
|
||||
use std::io::{Read, Write};
|
||||
use std::net::{SocketAddr, TcpListener};
|
||||
@@ -2373,7 +2910,12 @@ mod tests {
|
||||
use std::thread;
|
||||
use std::time::Duration;
|
||||
|
||||
use super::{execute_tool, mvp_tool_specs};
|
||||
use super::{
|
||||
agent_permission_policy, allowed_tools_for_subagent, execute_agent_with_spawn,
|
||||
execute_tool, final_assistant_text, mvp_tool_specs, persist_agent_terminal_state,
|
||||
AgentInput, AgentJob, SubagentToolExecutor,
|
||||
};
|
||||
use runtime::{ApiRequest, AssistantEvent, ConversationRuntime, RuntimeError, Session};
|
||||
use serde_json::json;
|
||||
|
||||
fn env_lock() -> &'static Mutex<()> {
|
||||
@@ -2646,8 +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 _multi_active = execute_tool(
|
||||
let too_many_active = execute_tool(
|
||||
"TodoWrite",
|
||||
&json!({
|
||||
"todos": [
|
||||
@@ -2656,7 +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",
|
||||
@@ -2765,32 +3307,48 @@ mod tests {
|
||||
.unwrap_or_else(std::sync::PoisonError::into_inner);
|
||||
let dir = temp_path("agent-store");
|
||||
std::env::set_var("CLAWD_AGENT_STORE", &dir);
|
||||
let captured = Arc::new(Mutex::new(None::<AgentJob>));
|
||||
let captured_for_spawn = Arc::clone(&captured);
|
||||
|
||||
let result = execute_tool(
|
||||
"Agent",
|
||||
&json!({
|
||||
"description": "Audit the branch",
|
||||
"prompt": "Check tests and outstanding work.",
|
||||
"subagent_type": "Explore",
|
||||
"name": "ship-audit"
|
||||
}),
|
||||
let manifest = execute_agent_with_spawn(
|
||||
AgentInput {
|
||||
description: "Audit the branch".to_string(),
|
||||
prompt: "Check tests and outstanding work.".to_string(),
|
||||
subagent_type: Some("Explore".to_string()),
|
||||
name: Some("ship-audit".to_string()),
|
||||
model: None,
|
||||
},
|
||||
move |job| {
|
||||
*captured_for_spawn
|
||||
.lock()
|
||||
.unwrap_or_else(std::sync::PoisonError::into_inner) = Some(job);
|
||||
Ok(())
|
||||
},
|
||||
)
|
||||
.expect("Agent should succeed");
|
||||
std::env::remove_var("CLAWD_AGENT_STORE");
|
||||
|
||||
let output: serde_json::Value = serde_json::from_str(&result).expect("valid json");
|
||||
assert_eq!(output["name"], "ship-audit");
|
||||
assert_eq!(output["subagentType"], "Explore");
|
||||
assert_eq!(output["status"], "queued");
|
||||
assert!(output["createdAt"].as_str().is_some());
|
||||
let manifest_file = output["manifestFile"].as_str().expect("manifest file");
|
||||
let output_file = output["outputFile"].as_str().expect("output file");
|
||||
let contents = std::fs::read_to_string(output_file).expect("agent file exists");
|
||||
assert_eq!(manifest.name, "ship-audit");
|
||||
assert_eq!(manifest.subagent_type.as_deref(), Some("Explore"));
|
||||
assert_eq!(manifest.status, "running");
|
||||
assert!(!manifest.created_at.is_empty());
|
||||
assert!(manifest.started_at.is_some());
|
||||
assert!(manifest.completed_at.is_none());
|
||||
let contents = std::fs::read_to_string(&manifest.output_file).expect("agent file exists");
|
||||
let manifest_contents =
|
||||
std::fs::read_to_string(manifest_file).expect("manifest file exists");
|
||||
std::fs::read_to_string(&manifest.manifest_file).expect("manifest file exists");
|
||||
assert!(contents.contains("Audit the branch"));
|
||||
assert!(contents.contains("Check tests and outstanding work."));
|
||||
assert!(manifest_contents.contains("\"subagentType\": \"Explore\""));
|
||||
assert!(manifest_contents.contains("\"status\": \"running\""));
|
||||
let captured_job = captured
|
||||
.lock()
|
||||
.unwrap_or_else(std::sync::PoisonError::into_inner)
|
||||
.clone()
|
||||
.expect("spawn job should be captured");
|
||||
assert_eq!(captured_job.prompt, "Check tests and outstanding work.");
|
||||
assert!(captured_job.allowed_tools.contains("read_file"));
|
||||
assert!(!captured_job.allowed_tools.contains("Agent"));
|
||||
|
||||
let normalized = execute_tool(
|
||||
"Agent",
|
||||
@@ -2819,6 +3377,195 @@ mod tests {
|
||||
let _ = std::fs::remove_dir_all(dir);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn agent_fake_runner_can_persist_completion_and_failure() {
|
||||
let _guard = env_lock()
|
||||
.lock()
|
||||
.unwrap_or_else(std::sync::PoisonError::into_inner);
|
||||
let dir = temp_path("agent-runner");
|
||||
std::env::set_var("CLAWD_AGENT_STORE", &dir);
|
||||
|
||||
let completed = execute_agent_with_spawn(
|
||||
AgentInput {
|
||||
description: "Complete the task".to_string(),
|
||||
prompt: "Do the work".to_string(),
|
||||
subagent_type: Some("Explore".to_string()),
|
||||
name: Some("complete-task".to_string()),
|
||||
model: Some("claude-sonnet-4-6".to_string()),
|
||||
},
|
||||
|job| {
|
||||
persist_agent_terminal_state(
|
||||
&job.manifest,
|
||||
"completed",
|
||||
Some("Finished successfully"),
|
||||
None,
|
||||
)
|
||||
},
|
||||
)
|
||||
.expect("completed agent should succeed");
|
||||
|
||||
let completed_manifest = std::fs::read_to_string(&completed.manifest_file)
|
||||
.expect("completed manifest should exist");
|
||||
let completed_output =
|
||||
std::fs::read_to_string(&completed.output_file).expect("completed output should exist");
|
||||
assert!(completed_manifest.contains("\"status\": \"completed\""));
|
||||
assert!(completed_output.contains("Finished successfully"));
|
||||
|
||||
let failed = execute_agent_with_spawn(
|
||||
AgentInput {
|
||||
description: "Fail the task".to_string(),
|
||||
prompt: "Do the failing work".to_string(),
|
||||
subagent_type: Some("Verification".to_string()),
|
||||
name: Some("fail-task".to_string()),
|
||||
model: None,
|
||||
},
|
||||
|job| {
|
||||
persist_agent_terminal_state(
|
||||
&job.manifest,
|
||||
"failed",
|
||||
None,
|
||||
Some(String::from("simulated failure")),
|
||||
)
|
||||
},
|
||||
)
|
||||
.expect("failed agent should still spawn");
|
||||
|
||||
let failed_manifest =
|
||||
std::fs::read_to_string(&failed.manifest_file).expect("failed manifest should exist");
|
||||
let failed_output =
|
||||
std::fs::read_to_string(&failed.output_file).expect("failed output should exist");
|
||||
assert!(failed_manifest.contains("\"status\": \"failed\""));
|
||||
assert!(failed_manifest.contains("simulated failure"));
|
||||
assert!(failed_output.contains("simulated failure"));
|
||||
|
||||
let spawn_error = execute_agent_with_spawn(
|
||||
AgentInput {
|
||||
description: "Spawn error task".to_string(),
|
||||
prompt: "Never starts".to_string(),
|
||||
subagent_type: None,
|
||||
name: Some("spawn-error".to_string()),
|
||||
model: None,
|
||||
},
|
||||
|_| Err(String::from("thread creation failed")),
|
||||
)
|
||||
.expect_err("spawn errors should surface");
|
||||
assert!(spawn_error.contains("failed to spawn sub-agent"));
|
||||
let spawn_error_manifest = std::fs::read_dir(&dir)
|
||||
.expect("agent dir should exist")
|
||||
.filter_map(Result::ok)
|
||||
.map(|entry| entry.path())
|
||||
.filter(|path| path.extension().and_then(|ext| ext.to_str()) == Some("json"))
|
||||
.find_map(|path| {
|
||||
let contents = std::fs::read_to_string(&path).ok()?;
|
||||
contents
|
||||
.contains("\"name\": \"spawn-error\"")
|
||||
.then_some(contents)
|
||||
})
|
||||
.expect("failed manifest should still be written");
|
||||
assert!(spawn_error_manifest.contains("\"status\": \"failed\""));
|
||||
assert!(spawn_error_manifest.contains("thread creation failed"));
|
||||
|
||||
std::env::remove_var("CLAWD_AGENT_STORE");
|
||||
let _ = std::fs::remove_dir_all(dir);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn agent_tool_subset_mapping_is_expected() {
|
||||
let general = allowed_tools_for_subagent("general-purpose");
|
||||
assert!(general.contains("bash"));
|
||||
assert!(general.contains("write_file"));
|
||||
assert!(!general.contains("Agent"));
|
||||
|
||||
let explore = allowed_tools_for_subagent("Explore");
|
||||
assert!(explore.contains("read_file"));
|
||||
assert!(explore.contains("grep_search"));
|
||||
assert!(!explore.contains("bash"));
|
||||
|
||||
let plan = allowed_tools_for_subagent("Plan");
|
||||
assert!(plan.contains("TodoWrite"));
|
||||
assert!(plan.contains("StructuredOutput"));
|
||||
assert!(!plan.contains("Agent"));
|
||||
|
||||
let verification = allowed_tools_for_subagent("Verification");
|
||||
assert!(verification.contains("bash"));
|
||||
assert!(verification.contains("PowerShell"));
|
||||
assert!(!verification.contains("write_file"));
|
||||
}
|
||||
|
||||
#[derive(Debug)]
|
||||
struct MockSubagentApiClient {
|
||||
calls: usize,
|
||||
input_path: String,
|
||||
}
|
||||
|
||||
impl runtime::ApiClient for MockSubagentApiClient {
|
||||
fn stream(&mut self, request: ApiRequest) -> Result<Vec<AssistantEvent>, RuntimeError> {
|
||||
self.calls += 1;
|
||||
match self.calls {
|
||||
1 => {
|
||||
assert_eq!(request.messages.len(), 1);
|
||||
Ok(vec![
|
||||
AssistantEvent::ToolUse {
|
||||
id: "tool-1".to_string(),
|
||||
name: "read_file".to_string(),
|
||||
input: json!({ "path": self.input_path }).to_string(),
|
||||
},
|
||||
AssistantEvent::MessageStop,
|
||||
])
|
||||
}
|
||||
2 => {
|
||||
assert!(request.messages.len() >= 3);
|
||||
Ok(vec![
|
||||
AssistantEvent::TextDelta("Scope: completed mock review".to_string()),
|
||||
AssistantEvent::MessageStop,
|
||||
])
|
||||
}
|
||||
_ => panic!("unexpected mock stream call"),
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn subagent_runtime_executes_tool_loop_with_isolated_session() {
|
||||
let _guard = env_lock()
|
||||
.lock()
|
||||
.unwrap_or_else(std::sync::PoisonError::into_inner);
|
||||
let path = temp_path("subagent-input.txt");
|
||||
std::fs::write(&path, "hello from child").expect("write input file");
|
||||
|
||||
let mut runtime = ConversationRuntime::new(
|
||||
Session::new(),
|
||||
MockSubagentApiClient {
|
||||
calls: 0,
|
||||
input_path: path.display().to_string(),
|
||||
},
|
||||
SubagentToolExecutor::new(BTreeSet::from([String::from("read_file")])),
|
||||
agent_permission_policy(),
|
||||
vec![String::from("system prompt")],
|
||||
);
|
||||
|
||||
let summary = runtime
|
||||
.run_turn("Inspect the delegated file", None)
|
||||
.expect("subagent loop should succeed");
|
||||
|
||||
assert_eq!(
|
||||
final_assistant_text(&summary),
|
||||
"Scope: completed mock review"
|
||||
);
|
||||
assert!(runtime
|
||||
.session()
|
||||
.messages
|
||||
.iter()
|
||||
.flat_map(|message| message.blocks.iter())
|
||||
.any(|block| matches!(
|
||||
block,
|
||||
runtime::ContentBlock::ToolResult { output, .. }
|
||||
if output.contains("hello from child")
|
||||
)));
|
||||
|
||||
let _ = std::fs::remove_file(path);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn agent_rejects_blank_required_fields() {
|
||||
let missing_description = execute_tool(
|
||||
|
||||
Reference in New Issue
Block a user