llm-party-cli 0.1.1 → 0.1.2

package/README.md

@@ -4,8 +4,8 @@
     <strong>Bring your models. We'll bring the party.</strong>
   </p>
   <p align="center">
-    <a href="https://llm-party.party">Website</a> &middot;
-    <a href="https://www.npmjs.com/package/llm-party-cli">npm</a> &middot;
+    <a href="https://llm-party.party">Website</a> ·
+    <a href="https://www.npmjs.com/package/llm-party-cli">npm</a> ·
     <a href="https://github.com/aalasolutions/llm-party">GitHub</a>
   </p>
   <p align="center">
@@ -36,13 +36,13 @@ No MCP. No master/servant. No window juggling. Just peers at a terminal table.
 
 ## Why llm-party?
 
-| | Traditional multi-agent | llm-party |
-|---|---|---|
-| **Architecture** | MCP (master controls servants) | Peer orchestration (you control all) |
-| **Integration** | CLI wrapping, output scraping | Direct SDK adapters |
-| **Sessions** | Fresh each time | Persistent per provider |
-| **Context** | Agents are siloed | Every agent sees the full conversation |
-| **API tokens** | Separate keys per tool | Uses your existing CLI auth |
+|                        | Traditional multi-agent        | llm-party                              |
+| ---------------------- | ------------------------------ | -------------------------------------- |
+| **Architecture** | MCP (master controls servants) | Peer orchestration (you control all)   |
+| **Integration**  | CLI wrapping, output scraping  | Direct SDK adapters                    |
+| **Sessions**     | Fresh each time                | Persistent per provider                |
+| **Context**      | Agents are siloed              | Every agent sees the full conversation |
+| **API tokens**   | Separate keys per tool         | Uses your existing CLI auth            |
 
 <br/>
 
@@ -50,7 +50,7 @@ No MCP. No master/servant. No window juggling. Just peers at a terminal table.
 
 ### Prerequisites
 
-Node.js 20+ is required (22+ if using the Copilot provider, which depends on `node:sqlite`). Make sure at least one AI CLI is installed and authenticated:
+Bun runtime and Node.js 20+ are required (22+ if using the Copilot provider, which depends on `node:sqlite`). Make sure at least one AI CLI is installed and authenticated:
 
 ```bash
 claude --version        # Claude Code CLI
@@ -72,13 +72,7 @@ npm install -g llm-party-cli
 llm-party
 ```
 
-On first run, llm-party creates `~/.llm-party/` with a default config and base prompt. Your system username is detected automatically. A single Claude agent is configured out of the box.
-
-To re-run setup or reset your config:
-
-```bash
-llm-party --init
-```
+On first run, llm-party automatically creates `~/.llm-party/` with a default config and global memory structure. Your system username is detected automatically. No setup commands needed.
 
 ### Add more agents
 
@@ -126,11 +120,13 @@ That's it. No paths, no prompts, no usernames to configure. Just name, tag, prov
 
 Agents can pass the conversation to each other by ending their response with `@next:<tag>`. The orchestrator picks it up and dispatches automatically. Max 15 hops per cycle to prevent loops.
 
-<br/>
+## **WARNING: FULL AUTONOMY.**
+
+All agents run with full permissions. They can read, write, edit files and execute shell commands with zero approval gates. There is no confirmation step before any action. Run in a disposable environment. You are responsible for any changes, data loss, costs, or side effects. Do not run against production systems.
 
 ## Important notes
 
-**No extra API tokens.** llm-party uses the original CLIs and SDKs under the hood. Your existing authentication and subscriptions are used directly. Sessions created by agents appear in each tool's native session history (Claude Code sessions, Codex threads, etc.).
+**Uses your existing CLIs.** llm-party uses official SDKs that delegate to each provider's CLI binary. If `claude`, `codex`, or `copilot` commands work on your machine, llm-party works. Authentication is handled entirely by the provider's own tools.
 
 **Run in isolation.** Always run llm-party inside a disposable environment: a Docker container, a VM, or at minimum a throwaway git branch. Agents have full filesystem and shell access with zero approval gates.
 
@@ -142,26 +138,24 @@ Agents can pass the conversation to each other by ending their response with `@n
 
 llm-party uses **official, publicly available SDKs and CLIs** published by each provider. Nothing is reverse-engineered, patched, or bypassed.
 
-| Provider | Official SDK | Published by |
-|----------|-------------|-------------|
-| Claude | [`@anthropic-ai/claude-agent-sdk`](https://www.npmjs.com/package/@anthropic-ai/claude-agent-sdk) | Anthropic |
-| Codex | [`@openai/codex-sdk`](https://www.npmjs.com/package/@openai/codex-sdk) | OpenAI |
-| Copilot | [`@github/copilot-sdk`](https://www.npmjs.com/package/@github/copilot-sdk) | GitHub |
-
-All authentication flows through the provider's own CLI login. llm-party does not store, proxy, or intercept credentials.
+| Provider | Official SDK                                                                                    | Published by |
+| -------- | ----------------------------------------------------------------------------------------------- | ------------ |
+| Claude   | [`@anthropic-ai/claude-agent-sdk`](https://www.npmjs.com/package/@anthropic-ai/claude-agent-sdk) | Anthropic    |
+| Codex    | [`@openai/codex-sdk`](https://www.npmjs.com/package/@openai/codex-sdk)                           | OpenAI       |
+| Copilot  | [`@github/copilot-sdk`](https://www.npmjs.com/package/@github/copilot-sdk)                       | GitHub       |
 
-If any provider believes this project violates their terms of service, please [open an issue](https://github.com/aalasolutions/llm-party/issues) and we will address it immediately.
+All authentication flows through the provider's own CLI. llm-party does not implement its own auth flow, store credentials, or intercept authentication traffic.
 
 <br/>
 
 ## Supported providers
 
-| Provider | SDK | Session | Prompt Support |
-|----------|-----|---------|---------------|
-| **Claude** | `@anthropic-ai/claude-agent-sdk` | Persistent via session ID resume | Full control |
-| **Codex** | `@openai/codex-sdk` | Persistent thread with `run()` turns | Via `developer_instructions` (limitations below) |
-| **Copilot** | `@github/copilot-sdk` | Persistent via `sendAndWait()` | Full control |
-| **GLM** | Claude SDK + env proxy | Same as Claude | Full control |
+| Provider          | SDK                                | Session                                | Prompt Support                                     |
+| ----------------- | ---------------------------------- | -------------------------------------- | -------------------------------------------------- |
+| **Claude**  | `@anthropic-ai/claude-agent-sdk` | Persistent via session ID resume       | Full control                                       |
+| **Codex**   | `@openai/codex-sdk`              | Persistent thread with `run()` turns | Via `developer_instructions` (limitations below) |
+| **Copilot** | `@github/copilot-sdk`            | Persistent via `sendAndWait()`       | Full control                                       |
+| **GLM**     | Claude SDK + env proxy             | Same as Claude                         | Full control                                       |
 
 <br/>
 
@@ -190,9 +184,9 @@ Orchestrator
     +-- Transcript Writer (JSONL, append-only, per session)
 ```
 
-Each agent receives a rolling window of recent messages (default 16) plus any unseen messages since its last turn. Messages from other agents are included so everyone sees the full multi-party conversation.
+Each agent receives a rolling window of recent messages (configurable, default 16) plus any unseen messages since its last turn. Messages from other agents are included so everyone sees the full multi-party conversation.
 
-`~/.llm-party/config.json` is your global config. `base.md` is always loaded first for every agent. The `prompts` field in config adds extra prompt files on top of it.
+`~/.llm-party/config.json` is your global config. Every agent receives a base system prompt automatically. The `prompts` field in config adds extra prompt files on top of it.
 
 <br/>
 
@@ -200,41 +194,41 @@ Each agent receives a rolling window of recent messages (default 16) plus any un
 
 ### Claude
 
-| | |
-|---|---|
-| SDK | `@anthropic-ai/claude-agent-sdk` |
+|         |                                                                                                 |
+| ------- | ----------------------------------------------------------------------------------------------- |
+| SDK     | `@anthropic-ai/claude-agent-sdk`                                                              |
 | Session | Persistent via `resume: sessionId`. First call creates a session, subsequent calls resume it. |
-| Prompt | Passed directly to the SDK. Full control over personality, behavior, and workflow rules. |
-| Tools | Read, Write, Edit, Bash, Glob, Grep |
+| Prompt  | Passed directly to the SDK. Full control over personality, behavior, and workflow rules.        |
+| Tools   | Read, Write, Edit, Bash, Glob, Grep                                                             |
 
 ### Codex
 
-| | |
-|---|---|
-| SDK | `@openai/codex-sdk` |
-| Session | Persistent thread. `startThread()` creates it, `thread.run()` adds turns to the same conversation. |
-| Prompt | Injected via `developer_instructions` config key. Appended alongside Codex's built-in 13k token system prompt. |
-| Tools | exec_command, apply_patch, file operations |
+|         |                                                                                                                  |
+| ------- | ---------------------------------------------------------------------------------------------------------------- |
+| SDK     | `@openai/codex-sdk`                                                                                            |
+| Session | Persistent thread.`startThread()` creates it, `thread.run()` adds turns to the same conversation.            |
+| Prompt  | Injected via `developer_instructions` config key. Appended alongside Codex's built-in 13k token system prompt. |
+| Tools   | exec_command, apply_patch, file operations                                                                       |
 
 **Known limitation:** Codex's built-in system prompt cannot be overridden. Your instructions are appended alongside it. Action instructions (naming, formatting, workflow rules) work. Personality overrides do not.
 
 ### Copilot
 
-| | |
-|---|---|
-| SDK | `@github/copilot-sdk` |
-| Session | Persistent via `CopilotClient.createSession()`. |
-| Prompt | Set as `systemMessage` on session creation. Full control. |
-| Tools | Copilot built-in toolset |
+|         |                                                             |
+| ------- | ----------------------------------------------------------- |
+| SDK     | `@github/copilot-sdk`                                     |
+| Session | Persistent via `CopilotClient.createSession()`.           |
+| Prompt  | Set as `systemMessage` on session creation. Full control. |
+| Tools   | Copilot built-in toolset                                    |
 
 ### GLM
 
-| | |
-|---|---|
-| SDK | `@anthropic-ai/claude-agent-sdk` (same as Claude) |
+|         |                                                           |
+| ------- | --------------------------------------------------------- |
+| SDK     | `@anthropic-ai/claude-agent-sdk` (same as Claude)       |
 | Session | Same as Claude, routed through a proxy via env overrides. |
-| Prompt | Same as Claude. Full control. |
-| Tools | Same as Claude |
+| Prompt  | Same as Claude. Full control.                             |
+| Tools   | Same as Claude                                            |
 
 GLM uses the Claude SDK as a transport layer. The adapter routes API calls through a proxy by setting `ANTHROPIC_BASE_URL` and model aliases via the `env` config field.
 
@@ -242,38 +236,36 @@ GLM uses the Claude SDK as a transport layer. The adapter routes API calls throu
 
 ## Config reference
 
-Config file: `~/.llm-party/config.json` (created on first run).
+Config file: `~/.llm-party/config.json` (created automatically on first run).
 
 Override with `LLM_PARTY_CONFIG` env var to point to a different file.
 
 ### Top-level fields
 
-| Field | Required | Default | Description |
-|-------|----------|---------|-------------|
-| `humanName` | No | Your system username | Display name in the terminal prompt and passed to agents |
-| `humanTag` | No | derived from `humanName` | Tag for human handoff detection (`@next:you`) |
-| `maxAutoHops` | No | `15` | Max agent-to-agent handoffs per cycle. Use `"unlimited"` to remove the cap |
-| `timeout` | No | `600` | Default timeout in seconds for all agents |
-| `agents` | Yes | | Array of agent definitions |
+| Field           | Required | Default                    | Description                                                                  |
+| --------------- | -------- | -------------------------- | ---------------------------------------------------------------------------- |
+| `humanName`   | No       | Your system username       | Display name in the terminal prompt and passed to agents                     |
+| `humanTag`    | No       | derived from `humanName` | Tag for human handoff detection (`@next:you`)                              |
+| `maxAutoHops` | No       | `15`                     | Max agent-to-agent handoffs per cycle. Use `"unlimited"` to remove the cap |
+| `timeout`     | No       | `600`                    | Default timeout in seconds for all agents                                    |
+| `agents`      | Yes      |                            | Array of agent definitions                                                   |
 
 ### Agent fields
 
-| Field | Required | Default | Description |
-|-------|----------|---------|-------------|
-| `name` | Yes | | Display name shown in responses as `[AGENT NAME]` |
-| `tag` | No | derived from `name` | Routing tag for `@tag` targeting |
-| `provider` | Yes | | SDK adapter: `claude`, `codex`, `copilot`, or `glm` |
-| `model` | Yes | | Model ID passed to the provider. Examples: `opus`, `sonnet`, `gpt-5.2`, `gpt-4.1`, `glm-5` |
-| `prompts` | No | none | Array of extra prompt file paths, concatenated after `base.md`. Relative to project root |
-| `executablePath` | No | PATH lookup | Path to the CLI binary. Supports `~/`. Only needed if the CLI is not in your PATH |
-| `env` | No | inherits `process.env` | Environment variable overrides for this agent |
-| `timeout` | No | top-level value | Per-agent timeout override in seconds |
+| Field              | Required | Default                  | Description                                                                                         |
+| ------------------ | -------- | ------------------------ | --------------------------------------------------------------------------------------------------- |
+| `name`           | Yes      |                          | Display name shown in responses as `[AGENT NAME]`. Must be unique.                                |
+| `tag`            | No       | derived from `name`    | Routing tag for `@tag` targeting                                                                  |
+| `provider`       | Yes      |                          | SDK adapter:`claude`, `codex`, `copilot`, or `glm`                                          |
+| `model`          | Yes      |                          | Model ID passed to the provider. Examples:`opus`, `sonnet`, `gpt-5.2`, `gpt-4.1`, `glm-5` |
+| `prompts`        | No       | none                     | Array of extra prompt file paths, concatenated after `base.md`. Relative to project root          |
+| `executablePath` | No       | PATH lookup              | Path to the CLI binary. Supports `~/`. Only needed if the CLI is not in your PATH                 |
+| `env`            | No       | inherits `process.env` | Environment variable overrides for this agent                                                       |
+| `timeout`        | No       | top-level value          | Per-agent timeout override in seconds                                                               |
 
 ### Prompts
 
-`base.md` is always loaded first for every agent. It defines orchestrator rules, routing syntax, handoff protocol, and team context. It lives at `~/.llm-party/base.md` (copied from the package on first run).
-
-To add extra instructions per agent, use the `prompts` field:
+Every agent receives a base system prompt automatically. To add extra instructions per agent, use the `prompts` field:
 
 ```json
 {
@@ -285,23 +277,23 @@ To add extra instructions per agent, use the `prompts` field:
 }
 ```
 
-The final prompt sent to the agent is: `base.md` + `prompts[0]` + `prompts[1]` + ... joined with `---` separators. Template variables are rendered after concatenation:
+Template variables available in prompt files:
 
-| Variable | Description |
-|----------|-------------|
-| `{{agentName}}` | This agent's display name |
-| `{{agentTag}}` | This agent's routing tag |
-| `{{humanName}}` | Your display name |
-| `{{humanTag}}` | Your routing tag |
-| `{{agentCount}}` | Total number of active agents |
-| `{{allAgentNames}}` | All agent names |
-| `{{allAgentTags}}` | All agent tags as `@tag` |
-| `{{otherAgentList}}` | Other agents with their tags |
-| `{{validHandoffTargets}}` | Valid `@next:tag` targets |
+| Variable                    | Description                   |
+| --------------------------- | ----------------------------- |
+| `{{agentName}}`           | This agent's display name     |
+| `{{agentTag}}`            | This agent's routing tag      |
+| `{{humanName}}`           | Your display name             |
+| `{{humanTag}}`            | Your routing tag              |
+| `{{agentCount}}`          | Total number of active agents |
+| `{{allAgentNames}}`       | All agent names               |
+| `{{allAgentTags}}`        | All agent tags as `@tag`    |
+| `{{otherAgentList}}`      | Other agents with their tags  |
+| `{{validHandoffTargets}}` | Valid `@next:tag` targets   |
 
 ### GLM environment setup
 
-GLM requires environment overrides to route through a proxy. The adapter first tries to load env variables from your shell `glm` alias. Without the alias, provide everything in the `env` block:
+GLM requires environment overrides to route through a proxy. The adapter tries to load env variables from your shell `glm` alias automatically. Without the alias, provide everything in the `env` block:
 
 ```json
 {
@@ -330,14 +322,15 @@ File changes made by agents are detected via `git status` after each response. N
 
 ## Terminal commands
 
-| Command | What it does |
-|---------|-------------|
-| `/agents` | List active agents with tag, provider, model |
-| `/history` | Print full conversation history |
-| `/save <path>` | Export conversation as JSON |
-| `/session` | Show session ID and transcript path |
-| `/changes` | Show git-modified files |
-| `/exit` | Quit |
+| Command          | What it does                                 |
+| ---------------- | -------------------------------------------- |
+| `/agents`      | List active agents with tag, provider, model |
+| `/save <path>` | Export conversation as JSON                       |
+| `/session`     | Show session ID and transcript path               |
+| `/changes`     | Show git-modified files                           |
+| `/clear`       | Clear chat display (Ctrl+L also works)            |
+| `/exit`        | Quit (graceful shutdown, all adapters cleaned up) |
+| `Ctrl+C`       | Exit (or copy selected text if selection active)  |
 
 <br/>
 
@@ -346,21 +339,21 @@ File changes made by agents are detected via `git status` after each response. N
 ```bash
 git clone https://github.com/aalasolutions/llm-party.git
 cd llm-party
-npm install
-npm run dev
+bun install
+bun run dev
 ```
 
 Build and run:
 
 ```bash
-npm run build
-npm start
+bun run build
+bun start
 ```
 
 Override config:
 
 ```bash
-LLM_PARTY_CONFIG=/path/to/config.json npm run dev
+LLM_PARTY_CONFIG=/path/to/config.json bun run dev
 ```
 
 <br/>
@@ -373,6 +366,9 @@ Run `/agents` to see available tags. Tags match against agent `tag`, `name`, and
 **"Unsupported provider"**
 Valid providers: `claude`, `codex`, `copilot`, `glm`.
 
+**"Duplicate agent name"**
+Agent names must be unique (case-insensitive). Rename one of the duplicates in config.
+
 **Agent modifies source code unexpectedly**
 Expected with full permissions. Use git to review and revert.
 
@@ -388,6 +384,6 @@ Default is 600 seconds (10 minutes). Adjust with `timeout` in config (top-level
 <br/>
 
 <p align="center">
-  <a href="https://llm-party.party">llm-party.party</a> &middot;
+  <a href="https://llm-party.party">llm-party.party</a> ·
   Built by <a href="https://aalasolutions.com">AALA Solutions</a>
 </p>

package/configs/default.json

@@ -1,10 +1,37 @@
 {
+  "humanName": "AAMIR",
+  "humanTag": "aamir",
+  "maxAutoHops": 15,
   "agents": [
+    {
+      "name": "GLM",
+      "tag": "glm",
+      "provider": "glm",
+      "model": "glm-5",
+      "env": {
+        "ANTHROPIC_BASE_URL": "https://api.z.ai/api/anthropic",
+        "ANTHROPIC_DEFAULT_HAIKU_MODEL": "glm-4.5-air",
+        "ANTHROPIC_DEFAULT_SONNET_MODEL": "glm-4.5",
+        "ANTHROPIC_DEFAULT_OPUS_MODEL": "glm-5"
+      }
+    },
     {
       "name": "Claude",
       "tag": "claude",
       "provider": "claude",
-      "model": "sonnet"
+      "model": "opus"
+    },
+    {
+      "name": "Copilot",
+      "tag": "copilot",
+      "provider": "copilot",
+      "model": "gpt-4.1"
+    },
+    {
+      "name": "Codex",
+      "tag": "codex",
+      "provider": "codex",
+      "model": "gpt-5.2"
     }
   ]
 }

package/dist/config/loader.js

@@ -1,4 +1,4 @@
-import { readFile, access, mkdir, copyFile } from "node:fs/promises";
+import { readFile, writeFile, access, mkdir } from "node:fs/promises";
 import { homedir, userInfo } from "node:os";
 import path from "node:path";
 const VALID_PROVIDERS = ["claude", "codex", "copilot", "glm"];
@@ -60,50 +60,68 @@ export async function resolveConfigPath(appRoot) {
     return path.join(appRoot, "configs", "default.json");
 }
 export async function resolveBasePrompt(appRoot) {
-    const globalBase = path.join(LLM_PARTY_HOME, "base.md");
+    const bundledBase = path.join(appRoot, "prompts", "base.md");
+    return await readFile(bundledBase, "utf8");
+}
+export async function resolveArtifactsPrompt(appRoot) {
+    const bundledArtifacts = path.join(appRoot, "prompts", "artifacts.md");
+    return await readFile(bundledArtifacts, "utf8");
+}
+export async function initProjectFolder(cwd) {
+    const projectHome = path.join(cwd, ".llm-party");
+    const memoryDir = path.join(projectHome, "memory");
+    const skillsDir = path.join(projectHome, "skills");
+    await mkdir(memoryDir, { recursive: true });
+    await mkdir(skillsDir, { recursive: true });
+    const tasksFile = path.join(projectHome, "TASKS.md");
     try {
-        await access(globalBase);
-        return await readFile(globalBase, "utf8");
+        await access(tasksFile);
     }
     catch {
-        // fall through to bundled
+        await writeFile(tasksFile, "# Tasks\n", "utf8");
+    }
+    const projectMd = path.join(memoryDir, "project.md");
+    try {
+        await access(projectMd);
+    }
+    catch {
+        await writeFile(projectMd, "# Project Memory\n\n## Current State\n\nLast Updated:\nActive:\nBlockers:\nNext:\n\n---\n\n## Log\n", "utf8");
+    }
+    const decisionsMd = path.join(memoryDir, "decisions.md");
+    try {
+        await access(decisionsMd);
+    }
+    catch {
+        await writeFile(decisionsMd, "# Decisions\n", "utf8");
     }
-    const bundledBase = path.join(appRoot, "prompts", "base.md");
-    return await readFile(bundledBase, "utf8");
 }
 export async function initLlmPartyHome(appRoot) {
     await mkdir(LLM_PARTY_HOME, { recursive: true });
     await mkdir(path.join(LLM_PARTY_HOME, "sessions"), { recursive: true });
-    const globalBase = path.join(LLM_PARTY_HOME, "base.md");
+    await mkdir(path.join(LLM_PARTY_HOME, "network"), { recursive: true });
+    await mkdir(path.join(LLM_PARTY_HOME, "agents"), { recursive: true });
+    const projectsYml = path.join(LLM_PARTY_HOME, "network", "projects.yml");
     try {
-        await access(globalBase);
+        await access(projectsYml);
     }
     catch {
-        const bundledBase = path.join(appRoot, "prompts", "base.md");
-        await copyFile(bundledBase, globalBase);
+        await writeFile(projectsYml, "projects: []\n", "utf8");
+    }
+    const librariesYml = path.join(LLM_PARTY_HOME, "network", "libraries.yml");
+    try {
+        await access(librariesYml);
+    }
+    catch {
+        await writeFile(librariesYml, "libraries: []\n", "utf8");
     }
     const globalConfig = path.join(LLM_PARTY_HOME, "config.json");
     try {
         await access(globalConfig);
     }
     catch {
-        const username = userInfo().username || "USER";
-        const defaultConfig = {
-            humanName: username,
-            agents: [
-                {
-                    name: "Claude",
-                    tag: "claude",
-                    provider: "claude",
-                    model: "sonnet"
-                }
-            ]
-        };
-        const { writeFile } = await import("node:fs/promises");
-        await writeFile(globalConfig, JSON.stringify(defaultConfig, null, 2) + "\n", "utf8");
-    }
-    console.log(`Initialized ~/.llm-party/`);
-    console.log(`  config: ${globalConfig}`);
+        const bundledConfig = await readFile(path.join(appRoot, "configs", "default.json"), "utf8");
+        await writeFile(globalConfig, bundledConfig, "utf8");
+    }
 }
 export async function loadConfig(configPath) {
     const raw = await readFile(configPath, "utf8");