@zhongqian97-code/ecode 0.2.5 → 0.3.1

package/README.md

@@ -1,25 +1,20 @@
 # ecode
 
-A minimal [Claude Code](https://claude.ai/code) clone — REPL interface with streaming LLM responses and bash tool calling.
+A minimal [Claude Code](https://claude.ai/code) clone — fullscreen TUI with streaming LLM responses, bash tool calling, Emacs keybindings, and a skill system.
 
 ## Install
 
 ```bash
-npm install -g @zhongqian-code/ecode
+npm install -g @zhongqian97-code/ecode
 ```
 
-## Usage
+## Quick start
 
 ```bash
-# Set your API key (OpenAI-compatible endpoint)
 export ECODE_API_KEY=sk-...
-
-# Start the REPL
 ecode
 ```
 
-Type your message, press Enter. Type `exit` to quit.
-
 ## Configuration
 
 Priority: **env vars > config file > defaults**
@@ -31,19 +26,33 @@ Priority: **env vars > config file > defaults**
 | `ECODE_API_KEY` | *(required)* | API key |
 | `ECODE_BASE_URL` | `https://api.openai.com/v1` | Base URL (any OpenAI-compatible endpoint) |
 | `ECODE_MODEL` | `gpt-4o` | Model name |
+| `ECODE_LOG_DIR` | *(disabled)* | Directory for session logs (JSONL) |
 
 ### Config file
 
-`~/.ecode/config.json`
+`~/.ecode/config.json` — all fields are optional, only set what you need.
 
 ```json
 {
   "apiKey": "sk-...",
   "baseUrl": "https://api.openai.com/v1",
-  "model": "gpt-4o"
+  "model": "gpt-4o",
+  "logDir": "~/.ecode/logs",
+  "contextLimit": 128000,
+  "dangerousPatterns": [
+    "rm -rf", "sudo", "chmod", "chown",
+    "mkfs", "dd", "fdisk",
+    "kill", "pkill", "killall",
+    "reboot", "shutdown", "halt",
+    "curl -X DELETE", "wget --delete-after"
+  ]
 }
 ```
 
+**`contextLimit`** — override automatic context window detection (tokens). Useful for unlisted or self-hosted models.
+
+**`dangerousPatterns`** — list of command prefixes that require double confirmation. Setting this field replaces the entire default list.
+
 ### Using with other providers
 
 ```bash
@@ -53,6 +62,12 @@ export ECODE_API_KEY=sk-...
 export ECODE_MODEL=deepseek-chat
 ecode
 
+# Anthropic Claude (via proxy or compatible gateway)
+export ECODE_BASE_URL=https://your-openai-proxy/v1
+export ECODE_API_KEY=sk-ant-...
+export ECODE_MODEL=claude-sonnet-4-6
+ecode
+
 # Local Ollama
 export ECODE_BASE_URL=http://localhost:11434/v1
 export ECODE_API_KEY=ollama
@@ -60,15 +75,93 @@ export ECODE_MODEL=llama3
 ecode
 ```
 
+Context window sizes are pre-configured for common models (GPT-4o, Claude, DeepSeek, o1/o3). Unknown models default to 128K.
+
+## Keyboard shortcuts
+
+### Submitting and navigation
+
+| Key | Action |
+|---|---|
+| `Enter` | Submit message |
+| `Shift+Enter` | Insert newline (multi-line input) |
+| `Tab` | Toggle tool call / thinking expansion |
+| `PageUp` / `PageDown` | Scroll conversation history |
+| `Ctrl+V` | Scroll down (same as PageDown) |
+| `Alt+V` | Scroll up (same as PageUp) |
+| `Ctrl+P` | Previous command (input history) |
+| `Ctrl+N` | Next command (input history) |
+
+### Emacs cursor movement
+
+| Key | Action |
+|---|---|
+| `Ctrl+A` | Jump to start of line |
+| `Ctrl+E` | Jump to end of line |
+| `Ctrl+B` / `←` | Move left one character |
+| `Ctrl+F` / `→` | Move right one character |
+| `Alt+B` | Move left one word |
+| `Alt+F` | Move right one word |
+
+### Emacs editing
+
+| Key | Action |
+|---|---|
+| `Backspace` | Delete character before cursor |
+| `Ctrl+D` | Delete character at cursor |
+| `Ctrl+K` | Kill from cursor to end of line |
+| `Ctrl+U` | Kill from start of line to cursor |
+| `Ctrl+W` | Kill word backward |
+
 ## Bash tool calling
 
 ecode gives the LLM access to a bash tool. Commands are classified into three tiers:
 
 | Tier | Examples | Behavior |
 |---|---|---|
-| **Allow** | `ls`, `cat`, `pwd`, `echo` | Auto-execute, no prompt |
-| **Normal** | `git status`, `npm install` | Single confirmation |
-| **Danger** | `rm -rf`, `sudo`, `chmod` | Double confirmation |
+| **Allow** | `ls`, `cat`, `pwd`, `echo`, `head`, `tail`, `wc`, `date`, `whoami`, `which`, `env` | Auto-execute, no prompt |
+| **Normal** | `git status`, `npm install`, `grep` | Single confirmation |
+| **Danger** | `rm -rf`, `sudo`, `chmod`, `kill`, `reboot` | Double confirmation |
+
+The danger list is fully customizable via `dangerousPatterns` in the config file.
+
+## Skills (slash commands)
+
+Type `/` to see available skills with Tab autocomplete. Skills inject structured instructions into the LLM context.
+
+| Skill | Description |
+|---|---|
+| `/plan` | Restate requirements and create a step-by-step implementation plan |
+| `/tdd` | Test-driven development with red-green-refactor loop |
+| `/diagnose` | Disciplined debug loop: reproduce → minimise → hypothesise → instrument → fix |
+| `/grill-me` | Relentless interview to stress-test a plan or design |
+| `/grill-with-docs` | Grilling session that challenges plans against the project's domain model |
+| `/improve-codebase-architecture` | Find deepening opportunities and architectural friction |
+| `/security-review` | Security vulnerability scan of pending changes |
+| `/search-first` | Research-before-coding workflow |
+| `/zoom-out` | Get a higher-level map of the relevant modules and callers |
+| `/to-prd` | Turn current context into a PRD |
+| `/to-issues` | Break a plan into independently-grabbable issues |
+| `/triage` | Move issues through a triage state machine |
+| `/write-a-skill` | Create new agent skills |
+| `/caveman` | Ultra-compressed mode (~75% token reduction) |
+
+Run `/setup-matt-pocock-skills` once to configure the issue tracker and triage vocabulary for your repo.
+
+## Session logging
+
+Enable JSONL session logs to replay or analyze conversations:
+
+```bash
+# via env var
+export ECODE_LOG_DIR=~/.ecode/logs
+ecode
+
+# via config file
+# "logDir": "~/.ecode/logs"
+```
+
+Each session writes a timestamped `.jsonl` file. Each line is a JSON object with `role`, `content`, and `timestamp`.
 
 ## Requirements