sparkecoder 0.1.99 → 0.1.100

package/README.md

@@ -5,75 +5,72 @@ A powerful coding agent CLI with HTTP API. Built with the [Vercel AI SDK](https:
 ## Features
 
 - 🤖 **Multi-Agent Sessions** - Run multiple agents simultaneously with isolated contexts
+- 🧭 **Personal Orchestrator** - Built-in supervisor agent that spawns workers, posts to Slack, fires on cron schedules, accepts webhooks, and edits its own config. See **[docs/ORCHESTRATOR.md](docs/ORCHESTRATOR.md)**.
+- 🔌 **MCP support** - Add Model Context Protocol servers via the Settings UI or by editing the config file. Hot-reloads on next agent turn.
+- 💬 **Slack integration** - Signed events, per-user/per-channel allowlist, canned denied-reply, in-thread responses. Setup wizard with copy-paste manifest in the Settings UI.
+- 🪝 **Inbound webhooks** - Token-protected URLs (`/api/inbox/<token>`) so external services can ping the orchestrator. Templated formatting.
+- ⏰ **Cron schedules** - Recurring prompts that wake the orchestrator with catch-up window.
+- 🧠 **Long-term memory** - Every turn mirrored to local JSONL files; orchestrator can `grep` across sessions via the `search-conversations` skill.
 - 🔄 **Streaming Responses** - Real-time SSE streaming following Vercel AI SDK data stream protocol
 - 🔧 **Powerful Tools** - Bash execution, file operations, planning, and skill loading
 - ✅ **Tool Approvals** - Configurable approval requirements for dangerous operations
 - 📚 **Skills System** - Load specialized knowledge documents into context
-- 💾 **SQLite Persistence** - Full session and message history storage
-- 🌐 **HTTP API** - RESTful API with auto-generated OpenAPI specification via hono-openapi
+- 💾 **Persistence** - Full session and message history storage (remote MongoDB by default)
+- 🌐 **HTTP API** - RESTful API with auto-generated OpenAPI specification
 - 🎯 **Context Management** - Automatic summarization for long conversations
 
 ## Installation
 
-### From GitHub Packages
-
 ```bash
-# Configure npm to use GitHub Packages for @gostudyfetchgo scope
-npm config set @gostudyfetchgo:registry https://npm.pkg.github.com
-
-# Install the package (no auth required - it's public!)
-npm install @gostudyfetchgo/sparkecoder
-
-# Or with pnpm
-pnpm add @gostudyfetchgo/sparkecoder
+# Global install (recommended)
+npm install -g sparkecoder
+# or
+pnpm add -g sparkecoder
 ```
 
 ### From Source
 
 ```bash
-# Clone the repository
 git clone https://github.com/gostudyfetchgo/sparkecoder.git
 cd sparkecoder
-
-# Install dependencies
 pnpm install
-
-# Set up environment variables
-export AI_GATEWAY_API_KEY=your_api_key_here
-
-# Start the server
 pnpm dev
 ```
 
-### Global CLI Installation
+## Quick Start (Personal Orchestrator)
 
 ```bash
-npm install -g @gostudyfetchgo/sparkecoder
-sparkecoder start
+sparkecoder server
 ```
 
-## Quick Start
+That's it — **no API key to configure**. On first boot sparkecoder auto-registers with the remote inference server. The first boot also:
 
-### Initialize Configuration
+- Starts the API at `http://127.0.0.1:3141` and the web UI at `http://localhost:6969`
+- Auto-creates the orchestrator session (always visible in the left sidebar)
+- Starts the per-orchestrator inbox, the daemon that drains it, the cron scheduler, and the MCP client pool
 
-```bash
-sparkecoder init
-```
+Open `http://localhost:6969` and you'll see:
+- **Orchestrator** in the sidebar — your long-lived supervisor chat
+- **Agents** — kanban of worker agents the orchestrator spawns
+- **Settings** — 6 tabs (General · Integrations · MCP · Schedules · Webhooks · Models · API Keys)
+
+**For end-to-end setup (Slack, cloudflared, MCP, schedules, webhooks, personality, long-term memory):** see **[docs/ORCHESTRATOR.md](docs/ORCHESTRATOR.md)**.
 
-This creates a `sparkecoder.config.json` file with default settings.
+### One-off task mode (no orchestrator)
 
-### Start the Server
+If you just want a one-shot autonomous task:
 
 ```bash
-sparkecoder start
+sparkecoder task --prompt "Refactor src/foo.ts to use async/await" \
+  --schema '{"type":"object","properties":{"summary":{"type":"string"}},"required":["summary"]}' \
+  --wait
 ```
 
-The server runs at `http://localhost:3141` by default.
+See [docs/TASK-MODE.md](docs/TASK-MODE.md).
 
-### Make Your First Request
+### Direct API call
 
 ```bash
-# Create a session and run a prompt
 curl -X POST http://localhost:3141/agents/quick \
   -H "Content-Type: application/json" \
   -d '{"prompt": "List the files in the current directory"}'
@@ -239,13 +236,16 @@ Built-in skills:
 ## CLI Commands
 
 ```bash
-sparkecoder start     # Start the HTTP server
-sparkecoder chat      # Interactive chat with the agent
-sparkecoder init      # Create config file
-sparkecoder sessions  # List all sessions
-sparkecoder status    # Check if server is running
-sparkecoder config    # Show current configuration
-sparkecoder info      # Show version and environment
+sparkecoder server              # Start the API + Web UI + orchestrator daemon + scheduler
+sparkecoder chat                # Interactive REPL chat with an agent
+sparkecoder task --prompt ... --schema ...   # Run a one-off autonomous task
+sparkecoder init                # Create a sparkecoder.config.json in cwd
+sparkecoder slack-setup         # Interactively configure Slack creds
+sparkecoder cloudflared-setup --hostname X --team Y   # Print public-tunnel + CF Access recipe
+sparkecoder sessions            # List all sessions on the running server
+sparkecoder status              # Check if the server is running
+sparkecoder config              # Show resolved configuration
+sparkecoder info                # Show version and environment
 ```
 
 ### Interactive Chat

package/dist/agent/index.js

@@ -7064,7 +7064,7 @@ You ALSO have the regular agent toolset (\`bash\`, \`read_file\`, \`write_file\`
 
 You manage your own configuration by editing files. Load the relevant skill first to get the file path and schema:
 
-- **MCP integrations** \u2014 load the \`manage-mcp\` skill. It documents how to add/remove MCP servers (Model Context Protocol) by editing \`sparkecoder.config.json\`. Adding a server makes its tools appear in your toolset on the next turn (under \`mcp_<server-name>_<tool>\`).
+- **MCP integrations** \u2014 load the \`manage-mcp\` skill. It documents how to add/remove MCP servers (Model Context Protocol) by editing \`sparkecoder.config.json\`. Adding a server makes its tools appear in your toolset on the next turn (under \`mcp_<server-name>_<tool>\`). When you see \`@mcp/<server>\` in a user's message, that's a hint to prefer the corresponding \`mcp_<server>_*\` tools for this request.
 - **Conversation history / long-term memory** \u2014 load the \`search-conversations\` skill. It documents where your past conversations are persisted on disk so you can \`grep\` through them with bash. Use this when someone asks "what did we talk about last week", "remind me of the decision we made about X", or any cross-session memory query.
 
 If the user asks "add the GitHub MCP" or "remember that I prefer Python", load the right skill first, then act on the documented file paths with bash/read_file/write_file.
@@ -7497,6 +7497,22 @@ ${summaryContent}`
       content
     };
     await messageQueries.create(this.sessionId, userMessage);
+    try {
+      const { appendTurn: appendTurn2, flattenContent: flattenContent2 } = await Promise.resolve().then(() => (init_conversation_archive(), conversation_archive_exports));
+      const { sessionQueries: sessionQueries2 } = await Promise.resolve().then(() => (init_db(), db_exports));
+      const session = await sessionQueries2.getById(this.sessionId).catch(() => void 0);
+      const text = flattenContent2(content).trim();
+      if (!text) return;
+      const channelMatch = text.match(/^\[([A-Z]+)/);
+      appendTurn2({
+        sessionId: this.sessionId,
+        sessionName: session?.name ?? void 0,
+        role: "user",
+        content: text,
+        channel: channelMatch ? channelMatch[1].toLowerCase() : void 0
+      });
+    } catch {
+    }
   }
   async addResponseMessages(messages) {
     await messageQueries.addMany(this.sessionId, messages);