ripperdoc 0.2.10__tar.gz → 0.3.0__tar.gz

{ripperdoc-0.2.10 → ripperdoc-0.3.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ripperdoc
-Version: 0.2.10
+Version: 0.3.0
 Summary: AI-powered terminal assistant for coding tasks
 Author: Ripperdoc Team
 License: Apache-2.0
@@ -23,10 +23,11 @@ Requires-Dist: python-dotenv>=1.0.0
 Requires-Dist: aiofiles>=23.0.0
 Requires-Dist: prompt-toolkit>=3.0.0
 Requires-Dist: PyYAML>=6.0.0
-Requires-Dist: mcp[cli]>=1.22.0
+Requires-Dist: mcp[cli]>=1.25.0
 Requires-Dist: json_repair>=0.54.2
 Requires-Dist: tiktoken>=0.7.0
 Requires-Dist: google-genai>=0.3.0
+Requires-Dist: charset-normalizer>=3.0.0
 Provides-Extra: dev
 Requires-Dist: pytest>=7.0.0; extra == "dev"
 Requires-Dist: pytest-asyncio>=0.21.0; extra == "dev"
@@ -99,27 +100,22 @@ pip install git+https://github.com/quantmew/ripperdoc.git
 Or install from source:
 ```bash
 # Clone the repository
-git clone <repository-url>
-cd Ripperdoc
+git clone https://github.com/quantmew/ripperdoc.git
+cd ripperdoc
 
 # Install from source
 pip install -e .
 ```
 
-### Configuration
 
-Set your API key as an environment variable:
-```bash
-export OPENAI_API_KEY="your-api-key-here"
-# or for Anthropic Claude
-export ANTHROPIC_API_KEY="your-api-key-here"
-```
 
 ## Usage
 
 ### Interactive Mode (Recommended)
 ```bash
 ripperdoc
+# or use the short alias
+rd
 ```
 
 This launches an interactive session where you can:
@@ -128,6 +124,13 @@ This launches an interactive session where you can:
 - Execute commands
 - Navigate and explore files
 
+**Options:**
+- `--yolo` - Skip permission prompts (safe mode is on by default)
+- `--model <model_name>` - Specify a model (e.g., `claude-sonnet-4-20250514`, `gpt-4o`)
+- `--tools <tool_list>` - Filter available tools (comma-separated, or "" for none)
+- `--no-mcp` - Disable MCP server integration
+- `--verbose` - Enable verbose logging
+
 ### Python SDK (headless)
 
 Use Ripperdoc without the terminal UI via the new Python SDK. See [docs/SDK_USAGE.md](docs/SDK_USAGE.md) for examples of the one-shot `query` helper and the session-based `RipperdocClient`. 中文指南见 [docs/SDK_USAGE_CN.md](docs/SDK_USAGE_CN.md)。
@@ -143,38 +146,67 @@ See the [examples/](examples/) directory for complete SDK usage examples.
 
 ### Safe Mode Permissions
 
-Safe mode is the default. Use `--yolo` to skip permission prompts. Choose `a`/`always` to allow a tool for the current session (not persisted across sessions).
+Safe mode is enabled by default. When prompted:
+- Type `y` or `yes` to allow a single operation
+- Type `a` or `always` to allow all operations of that type for the session
+- Type `n` or `no` to deny the operation
+
+Use `--yolo` flag to skip all permission prompts:
+```bash
+ripperdoc --yolo
+```
 
 ### Agent Skills
 
 Extend Ripperdoc with reusable Skill bundles:
 
-- Personal skills live in `~/.ripperdoc/skills/<skill-name>/SKILL.md`
-- Project skills live in `.ripperdoc/skills/<skill-name>/SKILL.md` and can be checked into git
-- Each `SKILL.md` starts with YAML frontmatter (`name`, `description`, optional `allowed-tools`, `model`, `max-thinking-tokens`, `disable-model-invocation`) followed by the instructions; add supporting files alongside it
-- Model and max-thinking-token hints from skills are applied automatically for the rest of the session after you load them with the `Skill` tool
-- Ripperdoc exposes skill names/descriptions in the system prompt and loads full content on demand via the `Skill` tool
+- **Personal skills**: `~/.ripperdoc/skills/<skill-name>/SKILL.md`
+- **Project skills**: `.ripperdoc/skills/<skill-name>/SKILL.md` (can be checked into git)
+- Each `SKILL.md` starts with YAML frontmatter:
+  - `name` - Skill identifier
+  - `description` - What the skill does
+  - `allowed-tools` (optional) - Restrict which tools the skill can use
+  - `model` (optional) - Suggest a specific model for this skill
+  - `max-thinking-tokens` (optional) - Control thinking budget
+  - `disable-model-invocation` (optional) - Use skill without calling the model
+- Add supporting files alongside `SKILL.md` as needed
+- Skills are auto-discovered and loaded on demand via the `Skill` tool
+
+**Built-in skills:** PDF manipulation (`pdf`), PowerPoint (`pptx`), Excel (`xlsx`)
 
 ## Examples
 
 ### Code Analysis
 ```
 > Can you explain what this function does?
+> Find all references to the `parse_config` function
 ```
 
 ### File Operations
 ```
 > Read the main.py file and suggest improvements
+> Create a new component called UserProfile.tsx
+> Update all imports to use the new package structure
 ```
 
 ### Code Generation
 ```
 > Create a new Python script that implements a REST API client
+> Generate unit tests for the auth module
+> Add error handling to the database connection code
 ```
 
 ### Project Navigation
 ```
 > Show me all the Python files in the project
+> Find where the user authentication logic is implemented
+> List all API endpoints in the project
+```
+
+### MCP Integration
+```
+> What MCP servers are available?
+> Query the context7 documentation for React hooks
 ```
 
 ## Development

{ripperdoc-0.2.10 → ripperdoc-0.3.0}/README.md

@@ -56,27 +56,22 @@ pip install git+https://github.com/quantmew/ripperdoc.git
 Or install from source:
 ```bash
 # Clone the repository
-git clone <repository-url>
-cd Ripperdoc
+git clone https://github.com/quantmew/ripperdoc.git
+cd ripperdoc
 
 # Install from source
 pip install -e .
 ```
 
-### Configuration
 
-Set your API key as an environment variable:
-```bash
-export OPENAI_API_KEY="your-api-key-here"
-# or for Anthropic Claude
-export ANTHROPIC_API_KEY="your-api-key-here"
-```
 
 ## Usage
 
 ### Interactive Mode (Recommended)
 ```bash
 ripperdoc
+# or use the short alias
+rd
 ```
 
 This launches an interactive session where you can:
@@ -85,6 +80,13 @@ This launches an interactive session where you can:
 - Execute commands
 - Navigate and explore files
 
+**Options:**
+- `--yolo` - Skip permission prompts (safe mode is on by default)
+- `--model <model_name>` - Specify a model (e.g., `claude-sonnet-4-20250514`, `gpt-4o`)
+- `--tools <tool_list>` - Filter available tools (comma-separated, or "" for none)
+- `--no-mcp` - Disable MCP server integration
+- `--verbose` - Enable verbose logging
+
 ### Python SDK (headless)
 
 Use Ripperdoc without the terminal UI via the new Python SDK. See [docs/SDK_USAGE.md](docs/SDK_USAGE.md) for examples of the one-shot `query` helper and the session-based `RipperdocClient`. 中文指南见 [docs/SDK_USAGE_CN.md](docs/SDK_USAGE_CN.md)。
@@ -100,38 +102,67 @@ See the [examples/](examples/) directory for complete SDK usage examples.
 
 ### Safe Mode Permissions
 
-Safe mode is the default. Use `--yolo` to skip permission prompts. Choose `a`/`always` to allow a tool for the current session (not persisted across sessions).
+Safe mode is enabled by default. When prompted:
+- Type `y` or `yes` to allow a single operation
+- Type `a` or `always` to allow all operations of that type for the session
+- Type `n` or `no` to deny the operation
+
+Use `--yolo` flag to skip all permission prompts:
+```bash
+ripperdoc --yolo
+```
 
 ### Agent Skills
 
 Extend Ripperdoc with reusable Skill bundles:
 
-- Personal skills live in `~/.ripperdoc/skills/<skill-name>/SKILL.md`
-- Project skills live in `.ripperdoc/skills/<skill-name>/SKILL.md` and can be checked into git
-- Each `SKILL.md` starts with YAML frontmatter (`name`, `description`, optional `allowed-tools`, `model`, `max-thinking-tokens`, `disable-model-invocation`) followed by the instructions; add supporting files alongside it
-- Model and max-thinking-token hints from skills are applied automatically for the rest of the session after you load them with the `Skill` tool
-- Ripperdoc exposes skill names/descriptions in the system prompt and loads full content on demand via the `Skill` tool
+- **Personal skills**: `~/.ripperdoc/skills/<skill-name>/SKILL.md`
+- **Project skills**: `.ripperdoc/skills/<skill-name>/SKILL.md` (can be checked into git)
+- Each `SKILL.md` starts with YAML frontmatter:
+  - `name` - Skill identifier
+  - `description` - What the skill does
+  - `allowed-tools` (optional) - Restrict which tools the skill can use
+  - `model` (optional) - Suggest a specific model for this skill
+  - `max-thinking-tokens` (optional) - Control thinking budget
+  - `disable-model-invocation` (optional) - Use skill without calling the model
+- Add supporting files alongside `SKILL.md` as needed
+- Skills are auto-discovered and loaded on demand via the `Skill` tool
+
+**Built-in skills:** PDF manipulation (`pdf`), PowerPoint (`pptx`), Excel (`xlsx`)
 
 ## Examples
 
 ### Code Analysis
 ```
 > Can you explain what this function does?
+> Find all references to the `parse_config` function
 ```
 
 ### File Operations
 ```
 > Read the main.py file and suggest improvements
+> Create a new component called UserProfile.tsx
+> Update all imports to use the new package structure
 ```
 
 ### Code Generation
 ```
 > Create a new Python script that implements a REST API client
+> Generate unit tests for the auth module
+> Add error handling to the database connection code
 ```
 
 ### Project Navigation
 ```
 > Show me all the Python files in the project
+> Find where the user authentication logic is implemented
+> List all API endpoints in the project
+```
+
+### MCP Integration
+```
+> What MCP servers are available?
+> Query the context7 documentation for React hooks
 ```
 
 ## Development

{ripperdoc-0.2.10 → ripperdoc-0.3.0}/pyproject.toml

@@ -32,10 +32,11 @@ dependencies = [
     "aiofiles>=23.0.0",
     "prompt-toolkit>=3.0.0",
     "PyYAML>=6.0.0",
-    "mcp[cli]>=1.22.0",
+    "mcp[cli]>=1.25.0",  # Fixed stdio_client async generator cleanup issue
     "json_repair>=0.54.2",
     "tiktoken>=0.7.0",
     "google-genai>=0.3.0",
+    "charset-normalizer>=3.0.0",
 ]
 
 [project.optional-dependencies]

{ripperdoc-0.2.10 → ripperdoc-0.3.0}/ripperdoc/__init__.py

@@ -1,3 +1,3 @@
 """Ripperdoc - AI-powered coding agent."""
 
-__version__ = "0.2.10"
+__version__ = "0.3.0"

{ripperdoc-0.2.10 → ripperdoc-0.3.0}/ripperdoc/cli/cli.py

@@ -44,7 +44,6 @@ from ripperdoc.utils.log import enable_session_file_logging, get_logger
 
 from rich.console import Console
 from rich.markdown import Markdown
-from rich.panel import Panel
 from rich.markup import escape
 
 console = Console()
@@ -98,7 +97,6 @@ async def run_query(
     model: Optional[str] = None,
 ) -> None:
     """Run a single query and print the response."""
-
     logger.info(
         "[cli] Running single prompt session",
         extra={
@@ -212,55 +210,37 @@ async def run_query(
                 mcp_instructions=mcp_instructions,
             )
 
-        # Run the query
+        # Run the query - collect final response text
+        final_response_parts: List[str] = []
         try:
             async for message in query(
                 messages, system_prompt, context, query_context, can_use_tool
             ):
                 if message.type == "assistant" and hasattr(message, "message"):
-                    # Print assistant message
+                    # Collect assistant message text for final output
                     if isinstance(message.message.content, str):
-                        console.print(
-                            Panel(
-                                Markdown(message.message.content),
-                                title="Ripperdoc",
-                                border_style="cyan",
-                                padding=(0, 1),
-                            )
-                        )
+                        final_response_parts.append(message.message.content)
                     else:
                         # Handle structured content
                         for block in message.message.content:
                             if isinstance(block, dict):
                                 if block.get("type") == "text":
-                                    console.print(
-                                        Panel(
-                                            Markdown(block["text"]),
-                                            title="Ripperdoc",
-                                            border_style="cyan",
-                                            padding=(0, 1),
-                                        )
-                                    )
+                                    final_response_parts.append(block["text"])
                             else:
                                 if hasattr(block, "type") and block.type == "text":
-                                    console.print(
-                                        Panel(
-                                            Markdown(block.text or ""),
-                                            title="Ripperdoc",
-                                            border_style="cyan",
-                                            padding=(0, 1),
-                                        )
-                                    )
-
-                elif message.type == "progress" and hasattr(message, "content"):
-                    # Print progress
-                    if verbose:
-                        console.print(f"[dim]Progress: {escape(str(message.content))}[/dim]")
+                                    final_response_parts.append(block.text or "")
+
+                # Skip progress messages entirely for -p mode
 
                 # Add message to history
                 messages.append(message)  # type: ignore[arg-type]
                 session_history.append(message)  # type: ignore[arg-type]
 
+            # Print final response as clean markdown (no panel, no decoration)
+            if final_response_parts:
+                final_text = "\n".join(final_response_parts)
+                console.print(Markdown(final_text))
+
         except KeyboardInterrupt:
             console.print("\n[yellow]Interrupted by user[/yellow]")
         except asyncio.CancelledError:
@@ -308,7 +288,6 @@ async def run_query(
         logger.debug("[cli] Shutdown MCP runtime", extra={"session_id": session_id})
 
 
-
 @click.group(invoke_without_command=True)
 @click.version_option(version=__version__)
 @click.option("--cwd", type=click.Path(exists=True), help="Working directory")
@@ -374,19 +353,51 @@ def cli(
 ) -> None:
     """Ripperdoc - AI-powered coding agent"""
     session_id = str(uuid.uuid4())
+    cwd_changed: Optional[str] = None
 
     # Set working directory
     if cwd:
         import os
 
         os.chdir(cwd)
+        cwd_changed = cwd
+
+    project_path = Path.cwd()
+
+    # Handle --continue option: load the most recent session
+    resume_messages = None
+    most_recent = None
+    if continue_session:
+        summaries = list_session_summaries(project_path)
+        if summaries:
+            most_recent = summaries[0]
+            session_id = most_recent.session_id
+            resume_messages = load_session_messages(project_path, session_id)
+            console.print(f"[dim]Continuing session: {most_recent.last_prompt}[/dim]")
+        else:
+            console.print("[yellow]No previous sessions found in this directory.[/yellow]")
+
+    log_file = enable_session_file_logging(project_path, session_id)
+
+    if cwd_changed:
         logger.debug(
             "[cli] Changed working directory via --cwd",
-            extra={"cwd": cwd, "session_id": session_id},
+            extra={"cwd": cwd_changed, "session_id": session_id},
         )
 
-    project_path = Path.cwd()
-    log_file = enable_session_file_logging(project_path, session_id)
+    if most_recent:
+        logger.info(
+            "[cli] Continuing session",
+            extra={
+                "session_id": session_id,
+                "message_count": len(resume_messages) if resume_messages else 0,
+                "last_prompt": most_recent.last_prompt,
+                "log_file": str(log_file),
+            },
+        )
+    elif continue_session:
+        logger.warning("[cli] No previous sessions found to continue")
+
     logger.info(
         "[cli] Starting CLI invocation",
         extra={
@@ -412,26 +423,39 @@ def cli(
     # Parse --tools option
     allowed_tools = parse_tools_option(tools)
 
-    # Handle --continue option: load the most recent session
-    resume_messages = None
-    if continue_session:
-        summaries = list_session_summaries(project_path)
-        if summaries:
-            most_recent = summaries[0]
-            session_id = most_recent.session_id
-            resume_messages = load_session_messages(project_path, session_id)
-            logger.info(
-                "[cli] Continuing session",
-                extra={
-                    "session_id": session_id,
-                    "message_count": len(resume_messages),
-                    "last_prompt": most_recent.last_prompt,
-                },
-            )
-            console.print(f"[dim]Continuing session: {most_recent.last_prompt}[/dim]")
-        else:
-            logger.warning("[cli] No previous sessions found to continue")
-            console.print("[yellow]No previous sessions found in this directory.[/yellow]")
+    # Handle piped stdin input
+    # - With -p flag: Not applicable (prompt comes from -p argument)
+    # - Without -p: stdin becomes the initial query in interactive mode
+    initial_query: Optional[str] = None
+    if prompt is None and ctx.invoked_subcommand is None:
+        stdin_stream = click.get_text_stream("stdin")
+        try:
+            stdin_is_tty = stdin_stream.isatty()
+        except Exception:
+            stdin_is_tty = True
+
+        if not stdin_is_tty:
+            try:
+                stdin_data = stdin_stream.read()
+            except (OSError, ValueError) as exc:
+                logger.warning(
+                    "[cli] Failed to read stdin for initial query: %s: %s",
+                    type(exc).__name__,
+                    exc,
+                    extra={"session_id": session_id},
+                )
+            else:
+                trimmed = stdin_data.rstrip("\n")
+                if trimmed.strip():
+                    initial_query = trimmed
+                    logger.info(
+                        "[cli] Received initial query from stdin",
+                        extra={
+                            "session_id": session_id,
+                            "query_length": len(initial_query),
+                            "query_preview": initial_query[:200],
+                        },
+                    )
 
     logger.debug(
         "[cli] Configuration initialized",
@@ -480,6 +504,7 @@ def cli(
             append_system_prompt=append_system_prompt,
             model=model,
             resume_messages=resume_messages,
+            initial_query=initial_query,
         )
         return
 
@@ -507,6 +532,88 @@ def config_cmd() -> None:
         console.print()
 
 
+@cli.command(name="stdio")
+@click.option(
+    "--input-format",
+    type=click.Choice(["stream-json", "auto"]),
+    default="stream-json",
+    help="Input format for messages.",
+)
+@click.option(
+    "--output-format",
+    type=click.Choice(["stream-json"]),
+    default="stream-json",
+    help="Output format for messages.",
+)
+@click.option(
+    "--model",
+    type=str,
+    default=None,
+    help="Model profile for the current session.",
+)
+@click.option(
+    "--permission-mode",
+    type=click.Choice(["default", "acceptEdits", "plan", "bypassPermissions"]),
+    default="default",
+    help="Permission mode for tool usage.",
+)
+@click.option(
+    "--max-turns",
+    type=int,
+    default=None,
+    help="Maximum number of conversation turns.",
+)
+@click.option(
+    "--system-prompt",
+    type=str,
+    default=None,
+    help="System prompt to use for the session.",
+)
+@click.option(
+    "--print",
+    "-p",
+    is_flag=True,
+    help="Print mode (for single prompt queries).",
+)
+@click.option(
+    "--",
+    "prompt",
+    type=str,
+    default=None,
+    help="Direct prompt (for print mode).",
+)
+def stdio_cmd(
+    input_format: str,
+    output_format: str,
+    model: str | None,
+    permission_mode: str,
+    max_turns: int | None,
+    system_prompt: str | None,
+    print: bool,
+    prompt: str | None,
+) -> None:
+    """Stdio mode for SDK subprocess communication.
+
+    This command enables Ripperdoc to communicate with SDKs via JSON Control
+    Protocol over stdin/stdout.
+    """
+    from ripperdoc.protocol.stdio import _run_stdio
+    import asyncio
+
+    asyncio.run(
+        _run_stdio(
+            input_format=input_format,
+            output_format=output_format,
+            model=model,
+            permission_mode=permission_mode,
+            max_turns=max_turns,
+            system_prompt=system_prompt,
+            print_mode=print,
+            prompt=prompt,
+        )
+    )
+
+
 @cli.command(name="version")
 def version_cmd() -> None:
     """Show version information"""

{ripperdoc-0.2.10 → ripperdoc-0.3.0}/ripperdoc/cli/commands/__init__.py

@@ -21,9 +21,11 @@ from .mcp_cmd import command as mcp_command
 from .models_cmd import command as models_command
 from .permissions_cmd import command as permissions_command
 from .resume_cmd import command as resume_command
+from .skills_cmd import command as skills_command
 from .stats_cmd import command as stats_command
 from .tasks_cmd import command as tasks_command
 from .status_cmd import command as status_command
+from .themes_cmd import command as themes_command
 from .todos_cmd import command as todos_command
 from .tools_cmd import command as tools_command
 
@@ -64,7 +66,9 @@ ALL_COMMANDS: List[SlashCommand] = [
     context_command,
     compact_command,
     resume_command,
+    skills_command,
     agents_command,
+    themes_command,
 ]
 
 COMMAND_REGISTRY: Dict[str, SlashCommand] = _build_registry(ALL_COMMANDS)

{ripperdoc-0.2.10 → ripperdoc-0.3.0}/ripperdoc/cli/commands/agents_cmd.py

@@ -18,7 +18,7 @@ from ripperdoc.tools.task_tool import (
 )
 from ripperdoc.utils.log import get_logger
 
-from typing import Any, Dict, Optional
+from typing import Any, Dict
 from .base import SlashCommand
 
 logger = get_logger()
@@ -101,9 +101,7 @@ def _handle(ui: Any, trimmed_arg: str) -> bool:
         for run_id in sorted(run_ids):
             snapshot: Dict[Any, Any] = get_agent_run_snapshot(run_id) or {}
             result_text = snapshot.get("result_text") or snapshot.get("error") or ""
-            result_preview = (
-                result_text if len(result_text) <= 80 else result_text[:77] + "..."
-            )
+            result_preview = result_text if len(result_text) <= 80 else result_text[:77] + "..."
             table.add_row(
                 escape(run_id),
                 escape(snapshot.get("status") or "unknown"),
@@ -136,9 +134,7 @@ def _handle(ui: Any, trimmed_arg: str) -> bool:
         details.add_row("Status", escape(snapshot.get("status") or "unknown"))
         details.add_row("Agent", escape(snapshot.get("agent_type") or "unknown"))
         details.add_row("Duration", _format_duration(snapshot.get("duration_ms")))
-        details.add_row(
-            "Background", "yes" if snapshot.get("is_background") else "no"
-        )
+        details.add_row("Background", "yes" if snapshot.get("is_background") else "no")
         if snapshot.get("model_used"):
             details.add_row("Model", escape(str(snapshot.get("model_used"))))
         if snapshot.get("tool_use_count"):