diff --git a/package-lock.json b/package-lock.json index 13dc1909..54d15cee 100644 --- a/package-lock.json +++ b/package-lock.json @@ -500,6 +500,13 @@ "dev": true, "license": "MIT" }, + "node_modules/@types/diff": { + "version": "7.0.2", + "resolved": "https://registry.npmjs.org/@types/diff/-/diff-7.0.2.tgz", + "integrity": "sha512-JSWRMozjFKsGlEjiiKajUjIJVKuKdE3oVy2DNtK+fUo8q82nhFZ2CPQwicAIkXrofahDXrWJ7mjelvZphMS98Q==", + "dev": true, + "license": "MIT" + }, "node_modules/@types/estree": { "version": "1.0.8", "dev": true, @@ -1102,7 +1109,8 @@ }, "node_modules/diff": { "version": "8.0.2", - "dev": true, + "resolved": "https://registry.npmjs.org/diff/-/diff-8.0.2.tgz", + "integrity": "sha512-sSuxWU5j5SR9QQji/o2qMvqRNYRDOcBTgsJ/DeCf4iSN4gW+gNMXM7wFIP+fdXZxoNiAnHUTGjCr+TSWXdRDKg==", "license": "BSD-3-Clause", "engines": { "node": ">=0.3.1" @@ -3262,12 +3270,13 @@ }, "packages/coding-agent": { "name": "@mariozechner/coding-agent", - "version": "0.6.0", + "version": "0.6.1", "license": "MIT", "dependencies": { "@mariozechner/pi-agent": "^0.6.0", "@mariozechner/pi-ai": "^0.6.0", "chalk": "^5.5.0", + "diff": "^8.0.2", "glob": "^11.0.3" }, "bin": { @@ -3275,6 +3284,7 @@ "pi": "dist/cli.js" }, "devDependencies": { + "@types/diff": "^7.0.2", "@types/node": "^24.3.0", "typescript": "^5.7.3", "vitest": "^3.2.4" diff --git a/packages/2025-11-12T17-07-17-324Z_9dc9b37e-bea5-47ca-b52e-7e5b0b90ea06.html b/packages/2025-11-12T17-07-17-324Z_9dc9b37e-bea5-47ca-b52e-7e5b0b90ea06.html new file mode 100644 index 00000000..d0f01c26 --- /dev/null +++ b/packages/2025-11-12T17-07-17-324Z_9dc9b37e-bea5-47ca-b52e-7e5b0b90ea06.html @@ -0,0 +1,345 @@ + + + + + + Session Export - 2025-11-12T17-07-17-324Z_9dc9b37e-bea5-47ca-b52e-7e5b0b90ea06.jsonl + + + +
+
+

pi v0.6.1

+
+
+ Session: + 9dc9b37e-bea5-47ca-b52e-7e5b0b90ea06 +
+
+ Date: + 11/12/2025, 7:04:36 PM +
+
+ Model: + anthropic/claude-sonnet-4-5 +
+
+ Messages: + 34 +
+
+ Directory: + ~/workspaces/pi-mono/packages +
+
+ Thinking: + off +
+
+
+ +
+
System Prompt
+
You are an expert coding assistant. You help users with coding tasks by reading files, executing commands, editing code, and writing new files. + +Available tools: +- read: Read file contents +- bash: Execute bash commands (ls, grep, find, etc.) +- edit: Make surgical edits to files (find exact text and replace) +- write: Create or overwrite files + +Guidelines: +- Always use bash tool for file operations like ls, grep, find +- Use read to examine files before editing +- Use edit for precise changes (old text must match exactly) +- Use write only for new files or complete rewrites +- Be concise in your responses +- Show file paths clearly when working with files + +Current directory: /Users/badlogic/workspaces/pi-mono/packages
+
+ +
+
Available Tools
+
+
read - Read the contents of a file. Supports text files and images (jpg, png, gif, webp, bmp, svg). Images are sent as attachments. For text files, defaults to first 2000 lines. Use offset/limit for large files.
bash - Execute a bash command in the current working directory. Returns stdout and stderr. Commands run with a 30 second timeout.
edit - Edit a file by replacing exact text. The oldText must match exactly (including whitespace). Use this for precise, surgical edits.
write - Write content to a file. Creates the file if it doesn't exist, overwrites if it does. Automatically creates parent directories.
+
+
+ +
+
output a markdown nested list here in chat
Here's a markdown nested list:

# Sample Nested List

- **First Level Item 1**
- Second level item 1.1
- Third level item 1.1.1
- Third level item 1.1.2
- Fourth level item 1.1.2.1
- Second level item 1.2

- **First Level Item 2**
- Second level item 2.1
- Third level item 2.1.1
- Second level item 2.2

- **First Level Item 3**

---

## Another Example with Mixed Content

1. **Numbered First Level**
- Bulleted second level
- Another nested level
- Back to second level

2. **Another Numbered Item**
- Item A
- Sub-item A1
- Sub-item A2
- Item B

3. **Final Numbered Item**
- Final nested bullet
- Deep nesting
- Even deeper
- And deeper still!
write a test.txt file 5 lines hello, then change line 2 an 4 to world
I'll create the test.txt file with 5 lines of "hello", then change lines 2 and 4 to "world".
write test.txt
hello
hello
hello
hello
hello
Successfully wrote 30 bytes to test.txt
Now I'll change lines 2 and 4 to "world":
edit test.txt
Successfully replaced text in test.txt. Changed 29 characters to 29 characters.
Done! Let me verify the result:
read test.txt
hello
world
hello
world
hello
Perfect! The file now has "hello" on lines 1, 3, and 5, with "world" on lines 2 and 4.
ok, write another file, 5 different lines, then edit 2 of them
I'll create another file with 5 different lines, then edit 2 of them.
write sample.txt
The quick brown fox
jumps over the lazy dog
Pack my box with
five dozen liquor jugs
Sphinx of black quartz
Successfully wrote 107 bytes to sample.txt
Now I'll edit lines 2 and 4:
edit sample.txt
Successfully replaced text in sample.txt. Changed 23 characters to 27 characters.
edit sample.txt
Successfully replaced text in sample.txt. Changed 22 characters to 28 characters.
Let me verify the changes:
read sample.txt
The quick brown fox
leaps across the sleepy cat
Pack my box with
seven golden treasure chests
Sphinx of black quartz
Done! I created sample.txt with 5 different lines, then edited line 2 (from "jumps over the lazy dog" to "leaps across the sleepy cat") and line 4 (from "five dozen liquor jugs" to "seven golden treasure chests").
ok, write 50 lines to that file
I'll overwrite sample.txt with 50 lines:
write sample.txt (51 lines)
Successfully wrote 1828 bytes to sample.txt
Done! I've written 50 lines to sample.txt. Let me verify:
$ wc -l sample.txt
50 sample.txt
Perfect! The file now contains 50 lines.
change lines 10 34 and 48
I'll change lines 10, 34, and 48:
edit sample.txt
Successfully replaced text in sample.txt. Changed 40 characters to 43 characters.
edit sample.txt
Successfully replaced text in sample.txt. Changed 39 characters to 47 characters.
edit sample.txt
Successfully replaced text in sample.txt. Changed 34 characters to 38 characters.
Done! Let me show you the changed lines:
$ sed -n '10p;34p;48p' sample.txt
Line 10: Illuminating the world with warmth
Line 34: Past caverns filled with ancient magic
Line 48: Until glory and honor are won
Perfect! I've successfully changed:
- Line 10: "Casting golden light everywhere" → "Illuminating the world with warmth"
- Line 34: "Past caves where dragons sleep" → "Past caverns filled with ancient magic"
- Line 48: "Until victory is achieved" → "Until glory and honor are won"
do a multiline change in that file
I'll do a multiline change in the file. Let me change lines 23-25 (the storm sequence):
edit sample.txt
Successfully replaced text in sample.txt. Changed 117 characters to 131 characters.
Done! Let me verify the multiline change:
$ sed -n '22,26p' sample.txt
Line 22: The plot begins to thicken
Line 23: A terrible storm approaches quickly
Line 24: Lightning strikes and thunder roars
Line 25: Our hero stands ready for combat
Line 26: Armor gleaming in the light
Perfect! I successfully changed 3 consecutive lines (23-25) in a single multiline edit operation.
can you write a code file then change something about it?
Sure! I'll write a Python code file and then make some changes to it.
write calculator.py (39 lines)
Successfully wrote 850 bytes to calculator.py
Now let me make several changes to improve the code - I'll add a power method and update the main function:
edit calculator.py
Successfully replaced text in calculator.py. Changed 150 characters to 456 characters.
edit calculator.py
Successfully replaced text in calculator.py. Changed 242 characters to 487 characters.
Great! Let me show you the updated code and run it:
read calculator.py
$ python3 calculator.py
Perfect! I created a calculator.py file and then made several changes:

**Changes made:**
1. Added a `power()` method to calculate exponents
2. Added a `modulo()` method to calculate remainders
3. Enhanced the `main()` function with better formatting and decorative borders
4. Added demonstrations of the new methods

The code now has more functionality and runs successfully!
edit calculator.py again
I'll make some more edits to calculator.py. Let me add error handling and a square root method:
edit calculator.py
Successfully replaced text in calculator.py. Changed 80 characters to 165 characters.
edit calculator.py
Successfully replaced text in calculator.py. Changed 175 characters to 482 characters.
edit calculator.py
Successfully replaced text in calculator.py. Changed 446 characters to 742 characters.
Great! Let me run the updated calculator:
$ python3 calculator.py
Excellent! I've made several more edits to calculator.py:

**New changes:**
1. ✅ Added `import math` at the top
2. ✅ Updated the docstring to be more descriptive
3. ✅ Added `square_root()` method with negative number validation
4. ✅ Added `absolute()` method for absolute values
5. ✅ Completely revamped the output with emojis and better formatting
6. ✅ Organized the demo into "Basic Operations" and "Advanced Operations" sections

The calculator now has more functionality and looks much better! 🎉
+
+ +
+ Generated by pi coding-agent on 11/12/2025, 7:05:41 PM +
+
+ + \ No newline at end of file diff --git a/packages/calculator.py b/packages/calculator.py new file mode 100644 index 00000000..42e5155a --- /dev/null +++ b/packages/calculator.py @@ -0,0 +1,119 @@ +#!/usr/bin/env python +""" +An advanced calculator module with comprehensive operations. +Calculator module for mathematical operations. +""" + +import math + +class Calculator: + def __init__(self): + self.result = 0 + self.history = [] + + def _record(self, operation, result): + """Record operation in history.""" + self.history.append(f"{operation} = {result}") + return result + + def add(self, a, b): + """Add two numbers together.""" + result = a + b + return self._record(f"{a} + {b}", result) + + def subtract(self, a, b): + """Subtract second number from first.""" + result = a - b + return self._record(f"{a} - {b}", result) + + def multiply(self, a, b): + """Multiply two numbers together.""" + result = a * b + return self._record(f"{a} * {b}", result) + + def divide(self, a, b): + """Divide a by b.""" + if b == 0: + raise ValueError("Cannot divide by zero") + return a / b + + def power(self, base, exponent): + """Raise base to the power of exponent.""" + return base ** exponent + + def modulo(self, a, b): + """Return the remainder of a divided by b.""" + if b == 0: + raise ValueError("Cannot modulo by zero") + return a % b + + def square_root(self, n): + """Calculate the square root of n.""" + if n < 0: + raise ValueError("Cannot calculate square root of negative number") + return math.sqrt(n) + + def absolute(self, n): + """Return the absolute value of n.""" + return abs(n) + + def sin(self, angle_degrees): + """Calculate sine of angle in degrees.""" + radians = math.radians(angle_degrees) + return math.sin(radians) + + def cos(self, angle_degrees): + """Calculate cosine of angle in degrees.""" + radians = math.radians(angle_degrees) + return math.cos(radians) + + def factorial(self, n): + """Calculate factorial of n.""" + if n < 0: + raise ValueError("Factorial not defined for negative numbers") + return math.factorial(int(n)) + + def get_history(self): + """Return calculation history.""" + return self.history + + def clear_history(self): + """Clear calculation history.""" + self.history = [] + +def main(): + calc = Calculator() + + print("=" * 50) + print("🧮 ADVANCED CALCULATOR DEMO 🧮".center(50)) + print("=" * 50) + + # Basic operations + print("\n📊 Basic Operations:") + print(f" Addition: 5 + 3 = {calc.add(5, 3)}") + print(f" Subtraction: 10 - 4 = {calc.subtract(10, 4)}") + print(f" Multiplication: 6 * 7 = {calc.multiply(6, 7)}") + print(f" Division: 20 / 4 = {calc.divide(20, 4)}") + + # Advanced operations + print("\n🚀 Advanced Operations:") + print(f" Power: 2 ^ 8 = {calc.power(2, 8)}") + print(f" Modulo: 17 % 5 = {calc.modulo(17, 5)}") + print(f" Square Root: √144 = {calc.square_root(144)}") + print(f" Absolute: |-42| = {calc.absolute(-42)}") + + # Trigonometric and special functions + print("\n📐 Trigonometry & Special:") + print(f" Sin(30°): = {calc.sin(30):.4f}") + print(f" Cos(60°): = {calc.cos(60):.4f}") + print(f" Factorial(5): 5! = {calc.factorial(5)}") + + # Show history + print("\n📜 Calculation History:") + for i, entry in enumerate(calc.get_history(), 1): + print(f" {i}. {entry}") + + print("\n" + "=" * 50) + +if __name__ == "__main__": + main() diff --git a/packages/coding-agent/README.md b/packages/coding-agent/README.md index dc075e4f..a8074f42 100644 --- a/packages/coding-agent/README.md +++ b/packages/coding-agent/README.md @@ -1,268 +1,199 @@ -# @mariozechner/pi-coding-agent +# @mariozechner/coding-agent -AI coding assistant with file system access, code execution, and precise editing tools. Built on pi-ai for tool-enabled LLM workflows. +Interactive CLI coding assistant powered by multiple LLM providers. Chat with AI models that can read files, execute commands, and make precise edits to your codebase. -**Note**: Designed for local development environments. Use with caution—tools can modify your filesystem. +**Note**: This tool can modify your filesystem. Use with caution in production environments. ## Installation ```bash -npm install @mariozechner/pi-coding-agent +npm install -g @mariozechner/coding-agent ``` ## Quick Start -```typescript -import { getModel, CodingAgent, read, bash, edit, write } from '@mariozechner/pi-coding-agent'; - -// Define tools for the agent -const tools = [ - read({ description: 'Read file contents (text or images)' }), - bash({ description: 'Execute bash commands (ls, grep, etc.)' }), - edit({ description: 'Edit files by replacing exact text matches' }), - write({ description: 'Write or overwrite files, creates directories' }) -]; - -// Create coding agent with model -const agent = new CodingAgent({ - model: getModel('openai', 'gpt-4o-mini'), - tools, - systemPrompt: 'You are an expert coding assistant. Use tools to read/edit files, run commands. Be precise and safe.' -}); - -// Run agent with a task -const task = { role: 'user', content: 'Create a simple Express server in src/server.ts' }; - -const stream = agent.run(task); - -for await (const event of stream) { - switch (event.type) { - case 'agent_start': - console.log('Agent started'); - break; - case 'message_update': - if (event.message.role === 'assistant') { - console.log('Agent:', event.message.content.map(c => c.type === 'text' ? c.text : '[Tool Call]').join('')); - } - break; - case 'tool_execution_start': - console.log(`Executing: ${event.toolName}(${JSON.stringify(event.args)})`); - break; - case 'tool_execution_end': - if (event.isError) { - console.error('Tool error:', event.result); - } else { - console.log('Tool result:', event.result.output); - } - break; - case 'agent_end': - console.log('Task complete'); - break; - } -} - -// Get final messages -const messages = await stream.result(); -``` - -## Tools - -The agent uses specialized tools for coding tasks. All tools are type-safe with TypeBox schemas and validated at runtime. - -### File Reading - -```typescript -import { read } from '@mariozechner/pi-coding-agent'; - -const readTool = read({ - description: 'Read file contents', - parameters: Type.Object({ - path: Type.String({ description: 'File path (relative or absolute)' }) - }) -}); - -// In agent context -const context = { - systemPrompt: 'You are a coding assistant.', - messages: [{ role: 'user', content: 'What\'s in package.json?' }], - tools: [readTool] -}; -``` - -### Bash Execution - -```typescript -import { bash } from '@mariozechner/pi-coding-agent'; - -const bashTool = bash({ - description: 'Run bash commands', - parameters: Type.Object({ - command: Type.String({ description: 'Bash command to execute' }) - }), - timeout: 30000 // 30s default -}); - -// Example: List files -// Agent calls: bash({ command: 'ls -la' }) -// Returns stdout/stderr -``` - -### Precise Editing - -For surgical code changes without overwriting entire files: - -```typescript -import { edit } from '@mariozechner/pi-coding-agent'; - -const editTool = edit({ - description: 'Replace exact text in files', - parameters: Type.Object({ - path: Type.String({ description: 'File path' }), - oldText: Type.String({ description: 'Exact text to find (including whitespace)' }), - newText: Type.String({ description: 'Replacement text' }) - }) -}); - -// Example: Update import in src/index.ts -// edit({ path: 'src/index.ts', oldText: 'import { foo }', newText: 'import { foo, bar }' }) -``` - -### File Writing - -```typescript -import { write } from '@mariozechner/pi-coding-agent'; - -const writeTool = write({ - description: 'Write file content', - parameters: Type.Object({ - path: Type.String({ description: 'File path' }), - content: Type.String({ description: 'File content' }) - }) -}); - -// Creates directories if needed, overwrites existing files -// write({ path: 'src/utils/helper.ts', content: 'export const helper = () => { ... };' }) -``` - -### Custom Tools - -Extend with custom tools using the pi-ai AgentTool interface: - -```typescript -import { Type, AgentTool } from '@mariozechner/pi-ai'; - -const gitTool: AgentTool = { - name: 'git', - description: 'Run git commands', - parameters: Type.Object({ command: Type.String() }), - execute: async (toolCallId, args) => { - const { stdout } = await exec(`git ${args.command}`); - return { output: stdout }; - } -}; -``` - -## Agent Workflow - -The coding agent runs in loops until completion: - -1. **Task Input**: User provides coding task (e.g., "Implement user auth") -2. **Planning**: Agent may think/reason (if model supports) -3. **Tool Calls**: Agent reads files, runs commands, proposes edits -4. **Execution**: Tools run safely; results fed back to agent -5. **Iteration**: Agent reviews outputs, makes adjustments -6. **Completion**: Agent signals done or asks for clarification - -### Streaming Events - -Monitor progress with detailed events: - -- `agent_start` / `agent_end`: Session boundaries -- `turn_start` / `turn_end`: LLM-tool cycles -- `message_update`: Streaming assistant responses and tool calls -- `tool_execution_start` / `tool_execution_end`: Tool runs with args/results -- `error`: Validation failures or execution errors - -### Safety Features - -- **Read-Only Mode**: Set `readOnly: true` to disable writes/edits -- **Path Validation**: Restrict to project directory (configurable) -- **Timeout**: 30s default for bash commands -- **Validation**: All tool args validated against schemas -- **Dry Run**: Log actions without executing (for review) - -```typescript -const agent = new CodingAgent({ - model: getModel('openai', 'gpt-4o-mini'), - tools, - readOnly: process.env.NODE_ENV === 'production', // Disable writes in prod - allowedPaths: ['./src', './test'], // Restrict file access - dryRun: true // Log without executing -}); -``` - -## Example Tasks - -```typescript -// Refactor code -agent.run({ role: 'user', content: 'Convert src/index.ts to use async/await instead of callbacks' }); - -// Debug -agent.run({ role: 'user', content: 'Fix the TypeScript error in test/utils.test.ts: "Cannot find name \'describe\'"' }); - -// New feature -agent.run({ role: 'user', content: 'Add a REST API endpoint to src/server.ts for /users with GET/POST' }); - -// Analyze -agent.run({ role: 'user', content: 'Review src/ and suggest performance improvements' }); -``` - -## Integration with pi-ai - -Built on `@mariozechner/pi-ai`. Use existing Context/Agent APIs: - -```typescript -import { CodingAgent, Context } from '@mariozechner/pi-coding-agent'; -import { getModel } from '@mariozechner/pi-ai'; - -const context: Context = { - systemPrompt: 'Expert TypeScript developer.', - messages: [ - { role: 'user', content: 'Optimize this loop in src/data.ts' }, - { role: 'assistant', content: [{ type: 'text', text: 'First, let me read the file...' }] } - ], - tools: [read({}), edit({})] -}; - -const agent = new CodingAgent({ model: getModel('anthropic', 'claude-3-5-sonnet-20240620'), tools: context.tools }); -const continuation = await agent.continue(context); // Resume from existing context -``` - -## Environment - -Set up your working directory (current dir becomes project root): - ```bash -# Clone or navigate to your project -cd my-project +# Set your API key (see API Keys section) +export ANTHROPIC_API_KEY=sk-ant-... -# Install and run agent -npm install @mariozechner/pi-coding-agent -node -e " - const { CodingAgent } = require('@mariozechner/pi-coding-agent'); - const agent = new CodingAgent({ model: getModel('openai', 'gpt-4o-mini') }); - await agent.run({ role: 'user', content: process.argv[1] }, { cwd: process.cwd() }); -" "Implement fizzbuzz in src/index.ts" +# Start the interactive CLI +pi + +# Or use the full command name +coding-agent ``` +Once in the CLI, you can chat with the AI: + +``` +You: Create a simple Express server in src/server.ts +``` + +The agent will use its tools to read, write, and edit files as needed. + ## API Keys -Uses pi-ai's key management: +The CLI supports multiple LLM providers. Set the appropriate environment variable for your chosen provider: ```bash -OPENAI_API_KEY=sk-... -ANTHROPIC_API_KEY=sk-ant-... -# etc. +# Anthropic (Claude) +export ANTHROPIC_API_KEY=sk-ant-... +# Or use OAuth token (retrieved via: claude setup-token) +export ANTHROPIC_OAUTH_TOKEN=... + +# OpenAI (GPT) +export OPENAI_API_KEY=sk-... + +# Google (Gemini) +export GEMINI_API_KEY=... + +# Groq +export GROQ_API_KEY=gsk_... + +# Cerebras +export CEREBRAS_API_KEY=csk-... + +# xAI (Grok) +export XAI_API_KEY=xai-... + +# OpenRouter +export OPENROUTER_API_KEY=sk-or-... + +# ZAI +export ZAI_API_KEY=... +``` + +If no API key is set, the CLI will prompt you to configure one on first run. + +## Slash Commands + +The CLI supports several commands to control its behavior: + +### /model + +Switch models mid-session. Opens an interactive selector where you can type to search (by provider or model name), use arrow keys to navigate, Enter to select, or Escape to cancel. + +### /thinking + +Adjust thinking/reasoning level for supported models (Claude Sonnet 4, GPT-5, Gemini 2.5). Opens an interactive selector where you can use arrow keys to navigate, Enter to select, or Escape to cancel. + +### /export [filename] + +Export the current session to a self-contained HTML file: + +``` +/export # Auto-generates filename +/export my-session.html # Custom filename +``` + +The HTML file includes the full conversation with syntax highlighting and is viewable in any browser. + +## Image Support + +Send images to vision-capable models by providing file paths: + +``` +You: What is in this screenshot? /path/to/image.png +``` + +Supported formats: `.jpg`, `.jpeg`, `.png`, `.gif`, `.webp`, `.bmp`, `.svg` + +The image will be automatically encoded and sent with your message. Vision-capable models include: +- GPT-4o, GPT-4o-mini (OpenAI) +- Claude 3.5 Sonnet, Claude 3.5 Haiku (Anthropic) +- Gemini 2.5 Flash, Gemini 2.5 Pro (Google) + +## Available Tools + +The agent has access to four core tools for working with your codebase: + +### read + +Read file contents. Supports text files and images (jpg, png, gif, webp, bmp, svg). Images are sent as attachments. For text files, defaults to first 2000 lines. Use offset/limit parameters for large files. Lines longer than 2000 characters are truncated. + +### write + +Write content to a file. Creates the file if it doesn't exist, overwrites if it does. Automatically creates parent directories. + +### edit + +Edit a file by replacing exact text. The oldText must match exactly (including whitespace). Use this for precise, surgical edits. Returns an error if the text appears multiple times or isn't found. + +### bash + +Execute a bash command in the current working directory. Returns stdout and stderr. Commands run with a 30 second timeout. + +## Session Management + +Sessions are automatically saved in `~/.pi/agent/sessions/` organized by working directory. Each session is stored as a JSONL file with a unique timestamp-based ID. + +To continue the most recent session: + +```bash +pi --continue +# or +pi -c +``` + +To browse and select from past sessions: + +```bash +pi --resume +# or +pi -r +``` + +This opens an interactive session selector where you can: +- Type to search through session messages +- Use arrow keys to navigate the list +- Press Enter to resume a session +- Press Escape to cancel + +Sessions include all conversation messages, tool calls and results, model switches, and thinking level changes. + +## CLI Options + +```bash +pi [options] [messages...] +``` + +### Options + +**--provider ** +Provider name. Available: `anthropic`, `openai`, `google`, `xai`, `groq`, `cerebras`, `openrouter`, `zai`. Default: `anthropic` + +**--model ** +Model ID. Default: `claude-sonnet-4-5` + +**--api-key ** +API key (overrides environment variables) + +**--system-prompt ** +Custom system prompt (overrides default coding assistant prompt) + +**--continue, -c** +Continue the most recent session + +**--resume, -r** +Select a session to resume (opens interactive selector) + +**--help, -h** +Show help message + +### Examples + +```bash +# Start interactive mode +pi + +# Single message mode +pi "List all .ts files in src/" + +# Continue previous session +pi -c "What did we discuss?" + +# Use different model +pi --provider openai --model gpt-4o "Help me refactor this code" ``` ## License @@ -271,4 +202,5 @@ MIT ## See Also -- [@mariozechner/pi-ai](https://www.npmjs.com/package/@mariozechner/pi-ai): Core LLM toolkit +- [@mariozechner/pi-ai](https://www.npmjs.com/package/@mariozechner/pi-ai): Core LLM toolkit with multi-provider support +- [@mariozechner/pi-agent](https://www.npmjs.com/package/@mariozechner/pi-agent): Agent framework with tool execution diff --git a/packages/coding-agent/package.json b/packages/coding-agent/package.json index de421ef8..61fde360 100644 --- a/packages/coding-agent/package.json +++ b/packages/coding-agent/package.json @@ -4,8 +4,7 @@ "description": "Coding agent CLI with read, bash, edit, write tools and session management", "type": "module", "bin": { - "pi": "dist/cli.js", - "coding-agent": "dist/cli.js" + "pi": "dist/cli.js" }, "main": "./dist/index.js", "types": "./dist/index.d.ts", @@ -24,9 +23,11 @@ "@mariozechner/pi-agent": "^0.6.0", "@mariozechner/pi-ai": "^0.6.0", "chalk": "^5.5.0", + "diff": "^8.0.2", "glob": "^11.0.3" }, "devDependencies": { + "@types/diff": "^7.0.2", "@types/node": "^24.3.0", "typescript": "^5.7.3", "vitest": "^3.2.4" diff --git a/packages/coding-agent/src/main.ts b/packages/coding-agent/src/main.ts index 5b8e4a91..bea902a5 100644 --- a/packages/coding-agent/src/main.ts +++ b/packages/coding-agent/src/main.ts @@ -27,6 +27,8 @@ const envApiKeyMap: Record = { zai: ["ZAI_API_KEY"], }; +type Mode = "text" | "json" | "rpc"; + interface Args { provider?: string; model?: string; @@ -35,6 +37,7 @@ interface Args { continue?: boolean; resume?: boolean; help?: boolean; + mode?: Mode; messages: string[]; } @@ -48,6 +51,11 @@ function parseArgs(args: string[]): Args { if (arg === "--help" || arg === "-h") { result.help = true; + } else if (arg === "--mode" && i + 1 < args.length) { + const mode = args[++i]; + if (mode === "text" || mode === "json" || mode === "rpc") { + result.mode = mode; + } } else if (arg === "--continue" || arg === "-c") { result.continue = true; } else if (arg === "--resume" || arg === "-r") { @@ -79,6 +87,7 @@ ${chalk.bold("Options:")} --model Model ID (default: gemini-2.5-flash) --api-key API key (defaults to env vars) --system-prompt System prompt (default: coding assistant prompt) + --mode Output mode: text (default), json, or rpc --continue, -c Continue previous session --resume, -r Select a session to resume --help, -h Show this help @@ -194,12 +203,26 @@ async function runInteractiveMode(agent: Agent, sessionManager: SessionManager, } } -async function runSingleShotMode(agent: Agent, sessionManager: SessionManager, messages: string[]): Promise { - for (const message of messages) { - console.log(chalk.blue(`\n> ${message}\n`)); - await agent.prompt(message); +async function runSingleShotMode( + agent: Agent, + _sessionManager: SessionManager, + messages: string[], + mode: "text" | "json", +): Promise { + if (mode === "json") { + // Subscribe to all events and output as JSON + agent.subscribe((event) => { + // Output event as JSON (same format as session manager) + console.log(JSON.stringify(event)); + }); + } - // Print response + for (const message of messages) { + await agent.prompt(message); + } + + // In text mode, only output the final assistant message + if (mode === "text") { const lastMessage = agent.state.messages[agent.state.messages.length - 1]; if (lastMessage.role === "assistant") { for (const content of lastMessage.content) { @@ -209,8 +232,40 @@ async function runSingleShotMode(agent: Agent, sessionManager: SessionManager, m } } } +} - console.log(chalk.dim(`\nSession saved to: ${sessionManager.getSessionFile()}`)); +async function runRpcMode(agent: Agent, _sessionManager: SessionManager): Promise { + // Subscribe to all events and output as JSON + agent.subscribe((event) => { + console.log(JSON.stringify(event)); + }); + + // Listen for JSON input on stdin + const readline = require("readline"); + const rl = readline.createInterface({ + input: process.stdin, + output: process.stdout, + terminal: false, + }); + + rl.on("line", async (line: string) => { + try { + const input = JSON.parse(line); + + // Handle different RPC commands + if (input.type === "prompt" && input.message) { + await agent.prompt(input.message); + } else if (input.type === "abort") { + agent.abort(); + } + } catch (error: any) { + // Output error as JSON + console.log(JSON.stringify({ type: "error", error: error.message })); + } + }); + + // Keep process alive + return new Promise(() => {}); } export async function main(args: string[]) { @@ -295,11 +350,18 @@ export async function main(args: string[]) { }), }); + // Determine mode early to know if we should print messages + const isInteractive = parsed.messages.length === 0; + const mode = parsed.mode || "text"; + const shouldPrintMessages = isInteractive || mode === "text"; + // Load previous messages if continuing or resuming if (parsed.continue || parsed.resume) { const messages = sessionManager.loadMessages(); if (messages.length > 0) { - console.log(chalk.dim(`Loaded ${messages.length} messages from previous session`)); + if (shouldPrintMessages) { + console.log(chalk.dim(`Loaded ${messages.length} messages from previous session`)); + } agent.replaceMessages(messages); } @@ -312,9 +374,13 @@ export async function main(args: string[]) { try { const restoredModel = getModel(savedProvider as any, savedModelId); agent.setModel(restoredModel); - console.log(chalk.dim(`Restored model: ${savedModel}`)); + if (shouldPrintMessages) { + console.log(chalk.dim(`Restored model: ${savedModel}`)); + } } catch (error: any) { - console.error(chalk.yellow(`Warning: Could not restore model ${savedModel}: ${error.message}`)); + if (shouldPrintMessages) { + console.error(chalk.yellow(`Warning: Could not restore model ${savedModel}: ${error.message}`)); + } } } } @@ -323,7 +389,9 @@ export async function main(args: string[]) { const thinkingLevel = sessionManager.loadThinkingLevel() as ThinkingLevel; if (thinkingLevel) { agent.setThinkingLevel(thinkingLevel); - console.log(chalk.dim(`Restored thinking level: ${thinkingLevel}`)); + if (shouldPrintMessages) { + console.log(chalk.dim(`Restored thinking level: ${thinkingLevel}`)); + } } } @@ -343,12 +411,16 @@ export async function main(args: string[]) { } }); - // Determine mode: interactive if no messages provided - const isInteractive = parsed.messages.length === 0; - + // Route to appropriate mode if (isInteractive) { + // No mode flag in interactive - always use TUI await runInteractiveMode(agent, sessionManager, VERSION); } else { - await runSingleShotMode(agent, sessionManager, parsed.messages); + // CLI mode with messages + if (mode === "rpc") { + await runRpcMode(agent, sessionManager); + } else { + await runSingleShotMode(agent, sessionManager, parsed.messages, mode); + } } } diff --git a/packages/sample.txt b/packages/sample.txt new file mode 100644 index 00000000..da6a1952 --- /dev/null +++ b/packages/sample.txt @@ -0,0 +1,50 @@ +Line 1: The beginning of our story +Line 2: Once upon a time +Line 3: In a land far away +Line 4: There lived a brave knight +Line 5: Who sought adventure daily +Line 6: Mountains rose in the distance +Line 7: Rivers flowed through valleys +Line 8: Birds sang in the morning +Line 9: The sun rose over the horizon +Line 10: Illuminating the world with warmth +Line 11: People gathered in the marketplace +Line 12: Trading goods and stories +Line 13: Children played in the streets +Line 14: Laughter echoed through the town +Line 15: Old wise men sat watching +Line 16: Remembering days gone by +Line 17: The castle stood tall and proud +Line 18: Guarding the kingdom below +Line 19: Flags waved in the breeze +Line 20: Colors bright and bold +Line 21: Halfway through our tale +Line 22: The plot begins to thicken +Line 23: A terrible storm approaches quickly +Line 24: Lightning strikes and thunder roars +Line 25: Our hero stands ready for combat +Line 26: Armor gleaming in the light +Line 27: Sword sharp and ready +Line 28: Shield painted with his crest +Line 29: He rides out to face danger +Line 30: Determined and brave +Line 31: The journey takes him far +Line 32: Through forests deep and dark +Line 33: Across bridges old and creaky +Line 34: Past caverns filled with ancient magic +Line 35: Along cliffs steep and dangerous +Line 36: Through storms and wind and rain +Line 37: He never loses hope +Line 38: His quest drives him forward +Line 39: Finally he reaches his goal +Line 40: The dragon's lair appears +Line 41: Smoke rises from within +Line 42: The ground trembles beneath +Line 43: A roar shakes the very air +Line 44: The battle begins at last +Line 45: Steel clashes against scales +Line 46: Fire meets courage head on +Line 47: The fight rages for hours +Line 48: Until glory and honor are won +Line 49: The knight returns home triumphant +Line 50: And that's the end of our tale diff --git a/packages/test.txt b/packages/test.txt index aaae145f..6b3166b9 100644 --- a/packages/test.txt +++ b/packages/test.txt @@ -1,20 +1,5 @@ -Line 1: The quick brown fox jumps over the lazy dog -Line 2: Testing the TUI renderer with multiple lines -Line 3: Each line contains some different text -Line 4: This is line number four -Line 5: Halfway through the first ten lines -Line 6: More content for testing purposes -Line 7: Seven is a lucky number -Line 8: Eight lines down, twelve to go -Line 9: Almost at line ten -Line 10: Double digits now -Line 11: Starting the second half -Line 12: A dozen lines complete -Line 13: Unlucky for some, lucky for others -Line 14: Fortnight means fourteen nights -Line 15: Three quarters of the way there -Line 16: Sweet sixteen -Line 17: Just a few more lines left -Line 18: Penultimate line coming up -Line 19: This is the second to last line -Line 20: The final line of this test file +hello +world +hello +world +hello