juno-code 1.0.47 → 1.0.49

package/README.md

@@ -17,12 +17,17 @@
 
 ```bash
 npm install -g juno-code
+
+# For Pi agent support (optional - multi-provider coding agent)
+npm install -g @mariozechner/pi-coding-agent
 ```
 
 After installation, initialize your project:
 
 ```bash
 juno-code init --task "Your task description" --subagent claude
+# Or with Pi (multi-provider agent)
+juno-code init --task "Your task description" --subagent pi
 ```
 
 ---
@@ -52,7 +57,7 @@ Run the AI in a loop. Let it iterate. Watch it solve problems, fix bugs, and add
 | **Overcooking** | Loop runs too long, AI adds features nobody asked for | You get bloated code and wasted tokens |
 | **Undercooking** | You Ctrl+C too early, work is incomplete | Features half-done, bugs half-fixed |
 | **Fragile state** | Markdown files (TASKS.md, PLANNING.md) as source of truth | LLMs can corrupt format; no strict schema |
-| **Vendor lock-in** | Ralph was built for Claude Code | Can't easily switch to Codex, Gemini, or others |
+| **Vendor lock-in** | Ralph was built for Claude Code | Can't easily switch to Codex, Gemini, Pi, or others |
 | **No traceability** | Changes blend together | Hard to debug, impossible to time-travel |
 
 ## juno-code: Ralph, But Better
@@ -85,12 +90,13 @@ Built-in kanban via [juno-kanban](https://pypi.org/project/juno-kanban/). Unlike
 ```
 
 ### Backend Choice: Use Any AI
-Switch between Claude, Codex, Gemini, or Cursor with one flag:
+Switch between Claude, Codex, Gemini, Pi, or Cursor with one flag:
 ```bash
 # Stuck on a bug? Try different models
-juno-code -b shell -s claude -m :opus-i 1 -v
+juno-code -b shell -s claude -m :opus -i 1 -v
 juno-code -b shell -s codex -m :codex -i 1 -v
 juno-code -b shell -s gemini -m :flash -i 1 -v
+juno-code -b shell -s pi -m :sonnet -i 1 -v
 ```
 
 ### Full Traceability: Every Change Tracked
@@ -116,6 +122,16 @@ juno-code -b shell -s claude -i 5 -v
 # Clean, readable progress instead of wall of JSON
 ```
 
+### Quota Limit Handling
+Auto-wait when you hit API rate limits instead of failing:
+```bash
+# Wait automatically when hitting hourly limits
+juno-code -b shell -s claude -i 10 --on-hourly-limit wait
+
+# Or exit immediately (default)
+juno-code -b shell -s claude -i 10 --on-hourly-limit raise
+```
+
 ## Quick Start
 
 ```bash
@@ -157,6 +173,10 @@ juno-code -b shell -s claude -i 3 -p "your prompt"
 juno-code claude "your task"
 juno-code codex "your task"
 juno-code gemini "your task"
+juno-code pi "your task"
+
+# View and parse log files
+juno-code view-log .juno_task/logs/claude_shell_*.log --output json-only --limit 50
 ```
 
 ### Global Options
@@ -164,13 +184,19 @@ juno-code gemini "your task"
 | Flag | Description |
 |------|-------------|
 | `-b, --backend <type>` | Backend: `mcp`, `shell` |
-| `-s, --subagent <name>` | Service: `claude`, `codex`, `gemini`, `cursor` |
+| `-s, --subagent <name>` | Service: `claude`, `codex`, `gemini`, `pi`, `cursor` |
 | `-m, --model <name>` | Model (supports shorthands like `:opus`, `:haiku`) |
 | `-i, --max-iterations <n>` | Iteration limit (-1 for unlimited) |
 | `-p, --prompt <text>` | Prompt text (if omitted with `start`, uses prompt.md) |
+| `-f, --prompt-file <path>` | Read prompt from a file instead of `-p` |
 | `-v, --verbose` | Human-readable verbose output |
 | `-r, --resume <id>` | Resume specific session |
 | `--continue` | Continue most recent session |
+| `--no-hooks` | Skip lifecycle hooks |
+| `--on-hourly-limit <action>` | Quota limit behavior: `wait` (auto-retry) or `raise` (exit) |
+| `--force-update` | Force reinstall all scripts and services |
+| `--til-completion` | Loop until all kanban tasks are done |
+| `--pre-run-hook <name>` | Execute named hooks before loop |
 
 ### Session Management
 
@@ -486,9 +512,13 @@ The kanban.sh script wraps juno-kanban. Here are the actual commands:
 
 | Service | Default Model | Shorthands |
 |---------|---------------|------------|
-| claude | `claude-sonnet-4-5-20250929` | `:haiku`, `:sonnet`, `:opus` |
-| codex | `gpt-5.3-codex` | `:codex`, `:gpt-5`, `:mini` |
+| claude | `claude-sonnet-4-6` | `:haiku`, `:sonnet`, `:opus` |
+| codex | `gpt-5.3-codex` | `:codex`, `:codex-mini`, `:gpt-5`, `:mini` |
 | gemini | `gemini-2.5-pro` | `:pro`, `:flash`, `:pro-3`, `:flash-3` |
+| pi | `anthropic/claude-sonnet-4-6` | `:pi`, `:sonnet`, `:opus`, `:gpt-5`, `:codex`, `:gemini-pro` |
+
+> **Pi** is a multi-provider coding agent that supports Anthropic, OpenAI, Google, Groq, xAI, and more.
+> It requires separate installation: `npm install -g @mariozechner/pi-coding-agent`
 
 ### Custom Backends
 
@@ -541,6 +571,9 @@ export JUNO_CODE_MAX_ITERATIONS=10
 export CODEX_HIDE_STREAM_TYPES="turn_diff,token_count"
 export GEMINI_API_KEY=your-key
 export CLAUDE_USER_MESSAGE_PRETTY_TRUNCATE=4
+
+# Pi requires the pi-coding-agent CLI installed globally
+# npm install -g @mariozechner/pi-coding-agent
 ```
 
 ## Examples
@@ -566,6 +599,9 @@ juno-code -b shell -s claude -m :opus -p "Investigate CI failures" -i 3
 
 # Stuck? Try Codex perspective
 juno-code -b shell -s codex -p "Same investigation" -i 3
+
+# Or use Pi with any provider's model
+juno-code -b shell -s pi -m :sonnet -p "Same investigation" -i 3
 ```
 
 ### Iterative Feature Development
@@ -590,7 +626,7 @@ git log --oneline
 | **Stopping** | Ctrl+C (guesswork) | `-i N` or "until tasks done" |
 | **Source of Truth** | Markdown files (TASKS.md, PLANNING.md) | Structured kanban over bash |
 | **Format Integrity** | Relies on LLM instruction-following | Strict format, always parseable |
-| **Multiple AIs** | Claude only | Claude, Codex, Gemini, Cursor |
+| **Multiple AIs** | Claude only | Claude, Codex, Gemini, Pi, Cursor |
 | **Traceability** | None | Every task → git commit |
 | **Hooks** | Claude-specific | Works with any backend |
 | **Verbose** | Raw JSON | Human-readable + jq-friendly |
@@ -633,7 +669,7 @@ juno-code services install --force
 ```bash
 # Verify with verbose
 juno-code -v -b shell -s codex -m :codex -p "test"
-# Check stderr for: "Executing: python3 ~/.juno_code/services/codex.py ... -m codex-5.2-codex-max"
+# Check stderr for: "Executing: python3 ~/.juno_code/services/codex.py ... -m gpt-5.3-codex"
 ```
 
 ### Kanban not finding tasks

package/dist/bin/cli.d.mts

@@ -0,0 +1,17 @@
+/**
+ * CLI entry point for juno-code
+ *
+ * Comprehensive TypeScript CLI implementation with full functionality parity
+ * to the Python budi-cli. Provides all core commands with interactive and
+ * headless support, comprehensive error handling, and real-time progress tracking.
+ */
+/**
+ * Global error handler for CLI operations
+ */
+declare function handleCLIError(error: unknown, verbose?: boolean): void;
+/**
+ * Main CLI function
+ */
+declare function main(): Promise<void>;
+
+export { handleCLIError, main };

package/dist/bin/cli.d.ts

@@ -0,0 +1,17 @@
+/**
+ * CLI entry point for juno-code
+ *
+ * Comprehensive TypeScript CLI implementation with full functionality parity
+ * to the Python budi-cli. Provides all core commands with interactive and
+ * headless support, comprehensive error handling, and real-time progress tracking.
+ */
+/**
+ * Global error handler for CLI operations
+ */
+declare function handleCLIError(error: unknown, verbose?: boolean): void;
+/**
+ * Main CLI function
+ */
+declare function main(): Promise<void>;
+
+export { handleCLIError, main };