npm - clew-code - Versions diffs - 0.2.20 → 0.2.22 - Mend

clew-code 0.2.20 → 0.2.22

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Files changed (66) hide show

package/dist/main.js +1888 -1883
package/docs/architecture.html +91 -148
package/docs/assets/clew-agent-loop.png +0 -0
package/docs/assets/clew-general-architecture.png +0 -0
package/docs/assets/clew-mcp-architecture.png +0 -0
package/docs/assets/clew-p2p-swarm.png +0 -0
package/docs/changelog.html +150 -0
package/docs/cli-reference.html +90 -0
package/docs/commands.html +156 -265
package/docs/configuration.html +85 -147
package/docs/contributing.html +91 -0
package/docs/css/styles.css +425 -425
package/docs/daemon.html +62 -129
package/docs/features/bridge-mode.html +61 -66
package/docs/features/evals.html +57 -149
package/docs/features/searxng-search.html +58 -118
package/docs/features/sentry-setup.html +61 -124
package/docs/index.html +137 -125
package/docs/installation.html +77 -105
package/docs/internals/growthbook-ab-testing.html +69 -91
package/docs/internals/hidden-features.html +81 -143
package/docs/js/main.js +29 -0
package/docs/loop.html +69 -181
package/docs/mcp.html +99 -247
package/docs/models.html +69 -110
package/docs/permission-model.html +86 -102
package/docs/plugins.html +84 -102
package/docs/providers.html +87 -127
package/docs/quick-start.html +81 -93
package/docs/research-memory.html +71 -102
package/docs/security.html +71 -0
package/docs/skills.html +67 -117
package/docs/swarm.html +78 -236
package/docs/tools.html +152 -151
package/docs/troubleshooting.html +86 -106
package/docs/voice-mode.html +79 -0
package/package.json +1 -1
package/docs/architecture.th.html +0 -79
package/docs/clew-code-architecture.html +0 -1126
package/docs/commands.th.html +0 -269
package/docs/configuration.th.html +0 -108
package/docs/daemon.th.html +0 -73
package/docs/features/bridge-mode.th.html +0 -62
package/docs/features/evals.th.html +0 -62
package/docs/features/searxng-search.th.html +0 -67
package/docs/features/sentry-setup.th.html +0 -69
package/docs/features/swarm.html +0 -156
package/docs/generated/providers.html +0 -625
package/docs/generated/tools.html +0 -558
package/docs/index.th.html +0 -292
package/docs/installation.th.html +0 -105
package/docs/internals/growthbook-ab-testing.th.html +0 -60
package/docs/internals/hidden-features.th.html +0 -107
package/docs/loop.th.html +0 -227
package/docs/mcp.th.html +0 -207
package/docs/models.th.html +0 -61
package/docs/permission-model.th.html +0 -67
package/docs/plugins.th.html +0 -79
package/docs/prompts-and-features.html +0 -806
package/docs/providers.th.html +0 -81
package/docs/quick-start.th.html +0 -89
package/docs/research-memory.th.html +0 -72
package/docs/skills.th.html +0 -90
package/docs/swarm.th.html +0 -280
package/docs/tools.th.html +0 -84
package/docs/troubleshooting.th.html +0 -85

package/docs/providers.html CHANGED Viewed

@@ -1,127 +1,87 @@
-<!DOCTYPE html>
-<html lang="en">
-<head>
-  <meta charset="UTF-8">
-  <meta name="viewport" content="width=device-width, initial-scale=1.0">
-  <title>Providers — Clew</title>
-  <meta name="description" content="Complete AI provider reference for Clew — 29 supported providers with configuration and capabilities.">
-  <link rel="preconnect" href="https://fonts.googleapis.com">
-  <link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
-  <link href="https://fonts.googleapis.com/css2?family=DM+Sans:wght@400;500;600;700&family=JetBrains+Mono:wght@400;500;600;700&display=swap" rel="stylesheet">
-  <link rel="stylesheet" href="css/styles.css">
-  <link rel="icon" type="image/svg+xml" href="./assets/clew.svg">
-</head>
-<body>
-<header class="header"></header>
-<div class="app"><aside class="sidebar" id="sidebar"></aside><div class="sidebar-overlay" id="sidebarOverlay"></div>
-<div class="content-wrap"><main class="content">
-  <div class="breadcrumbs"><a href="index.html">Home</a><span class="sep">/</span><span>Providers</span></div>
-  <h1>Providers</h1>
-  <p class="section-subtitle">Clew supports <strong>29 AI providers</strong> with a unified adapter layer. Set your API keys as environment variables and switch between providers at runtime with <code>/model</code>.</p>
-  <p>Provider configuration is declared in <code>src/services/ai/providers.json</code>. The <strong>ProviderManager</strong> resolves API keys, selects models, and manages provider config. Non-Anthropic providers are normalized via the <strong>AnthropicAdapter</strong> or <strong>GoogleAdapter</strong>.</p>
-  <h2>All Providers</h2>
-  <table>
-    <tr><th>Provider</th><th>Env Key</th><th>Default Model</th><th>Notes</th></tr>
-    <tr><td>Clew Gateway</td><td><code>CLEW_GATEWAY_KEY</code></td><td>clew-code</td><td>Self-hosted AI proxy for provider fallback, model routing, and usage tracking across upstream providers. Set base URL with <code>CLEW_GATEWAY_URL</code>.</td></tr>
-    <tr><td>Custom (OpenAI-Compatible)</td><td><code>CUSTOM_API_KEY</code></td><td>—</td><td>Generic OpenAI-compatible provider. Set base URL with <code>CUSTOM_API_BASE_URL</code>.</td></tr>
-    <tr><td>Anthropic</td><td><code>ANTHROPIC_API_KEY</code></td><td>claude-sonnet-4-7</td><td>Native Claude support with full tool calling and reasoning. Context: 1M tokens.</td></tr>
-    <tr><td>OpenAI</td><td><code>OPENAI_API_KEY</code></td><td>gpt-5.5</td><td>GPT-5.5, GPT-5.5 Pro, GPT-5.4 Mini. Context: 1M+ tokens.</td></tr>
-    <tr><td>Google</td><td><code>GOOGLE_API_KEY</code></td><td>gemini-3.1-pro-preview</td><td>Gemini 3.1 Pro Preview &amp; Flash Lite. Context: up to 2M tokens. Uses GoogleAdapter.</td></tr>
-    <tr><td>OpenRouter</td><td><code>OPENROUTER_API_KEY</code></td><td>—</td><td>100+ models via routed API. OpenAI-compatible.</td></tr>
-    <tr><td>DeepSeek</td><td><code>DEEPSEEK_API_KEY</code></td><td>deepseek-v4-pro</td><td>DeepSeek V4 Pro, V4 Flash. Context: 1M tokens. MoE architecture.</td></tr>
-    <tr><td>OpenCode</td><td><code>OPENCODE_API_KEY</code></td><td>claude-opus-4-7</td><td>OpenCode AI gateway. OpenAI-compatible. Includes Claude, GPT, Gemini, Kimi, GLM, MiniMax.</td></tr>
-    <tr><td>OpenCode Go</td><td><code>OPENCODE_GO_API_KEY</code></td><td>minimax-m2.7</td><td>Low cost subscription tier for open coding models.</td></tr>
-    <tr><td>Cline API</td><td><code>CLINE_API_KEY</code></td><td>anthropic/claude-opus-4-7</td><td>OpenAI-compatible. Model IDs format: provider/model-name.</td></tr>
-    <tr><td>Groq</td><td><code>GROQ_API_KEY</code></td><td>llama-3.3-70b-versatile</td><td>Llama 3.3 70B, Llama 4 Scout. Fast inference. Context: 128K tokens.</td></tr>
-    <tr><td>xAI</td><td><code>XAI_API_KEY</code></td><td>grok-4.3</td><td>Grok 4.3. Context: 128K tokens. Vision and tool calling.</td></tr>
-    <tr><td>Mistral</td><td><code>MISTRAL_API_KEY</code></td><td>mistral-small-latest</td><td>Mistral Large 4, Small 4, Ministral 3 14B. Tool calling and vision support.</td></tr>
-    <tr><td>KiloCode</td><td><code>KILOCODE_API_KEY</code></td><td>kilo-auto/free</td><td>Gateway with 500+ models. Includes free tier.</td></tr>
-    <tr><td>Ollama (Local)</td><td><code>OLLAMA_API_KEY</code></td><td>llama3.3</td><td>Local models via Ollama server at <code>http://localhost:11434/v1</code>. Offline-capable.</td></tr>
-    <tr><td>Together AI</td><td><code>TOGETHER_API_KEY</code></td><td>—</td><td>Llama 4 models. OpenAI-compatible.</td></tr>
-    <tr><td>Fireworks AI</td><td><code>FIREWORKS_API_KEY</code></td><td>—</td><td>Llama 4 70B. Fast inference.</td></tr>
-    <tr><td>NVIDIA NIM</td><td><code>NVIDIA_API_KEY</code></td><td>—</td><td>NVIDIA AI Foundation Models. DeepSeek, Llama 3.1, Nemotron. Live model list fetched from API on /model list.</td></tr>
-    <tr><td>Cohere</td><td><code>COHERE_API_KEY</code></td><td>command-a-plus-05-2026</td><td>Command A+ model. 128K context. No vision.</td></tr>
-    <tr><td>Deep Infra</td><td><code>DEEPINFRA_API_KEY</code></td><td>—</td><td>OpenAI-compatible gateway. Llama 4 Scout with 327K context.</td></tr>
-    <tr><td>Perplexity</td><td><code>PERPLEXITY_API_KEY</code></td><td>—</td><td>Sonar Huge Online. No tool calling support.</td></tr>
-    <tr><td>Cerebras</td><td><code>CEREBRAS_API_KEY</code></td><td>—</td><td>Wafer-Scale Engine. Extremely fast inference. Qwen 3 235B.</td></tr>
-    <tr><td>SiliconFlow</td><td><code>SILICONFLOW_API_KEY</code></td><td>—</td><td>China-based AI platform. DeepSeek V4 Pro and Flash.</td></tr>
-    <tr><td>Moonshot AI (Kimi)</td><td><code>MOONSHOT_API_KEY</code></td><td>kimi-latest</td><td>Kimi models. 128K context. Vision and tool calling.</td></tr>
-    <tr><td>Zhipu AI (GLM)</td><td><code>ZHIPU_API_KEY</code></td><td>glm-4</td><td>GLM-4 model. 128K context.</td></tr>
-    <tr><td>Hugging Face</td><td><code>HUGGINGFACE_API_KEY</code></td><td>—</td><td>Inference API. Llama 3.1 70B. No tool calling.</td></tr>
-    <tr><td>Poe</td><td><code>POE_API_KEY</code></td><td>—</td><td>OpenAI-compatible gateway. Claude 3.7 Sonnet available.</td></tr>
-    <tr><td>DigitalOcean</td><td><code>DIGITALOCEAN_API_KEY</code></td><td>—</td><td>Serverless Inference. Llama 3.1 70B.</td></tr>
-  </table>
-  <h2>Provider Selection</h2>
-  <p>ProviderManager resolves the active provider by:</p>
-  <ol>
-    <li>Scanning environment variables for configured API keys</li>
-    <li>Loading provider metadata from <code>providers.json</code></li>
-    <li>Resolving model names to provider-specific identifiers</li>
-    <li>Applying the adapter layer for non-Anthropic providers</li>
-    <li>Handling config migration and backward compatibility</li>
-  </ol>
-  <h2>Adapter Layer</h2>
-  <p>Non-Anthropic providers pass through adapters that normalize:</p>
-  <ul>
-    <li><strong>Content blocks</strong> — text, tool_use, tool_result, thinking block conversion (<code>contentBlockUtils.ts</code>)</li>
-    <li><strong>Tool calls</strong> — parsing across provider formats (<code>toolCallParser.ts</code>)</li>
-    <li><strong>Streaming chunks</strong> — per-chunk normalization for real-time display</li>
-    <li><strong>Errors</strong> — normalization with retry/rate-limit handling (<code>errorNormalizer.ts</code>)</li>
-    <li><strong>Usage</strong> — token counting and cost estimation (<code>usageNormalizer.ts</code>)</li>
-  </ul>
-  <h2>Runtime Switching</h2>
-  <pre><code>/model                          # Interactive model picker
-/model list                     # List all available models across providers
-/model claude-sonnet-4-7        # Switch to a specific model
-/provider-select                 # Show or change active provider</code></pre>
-  <h2>Provider Capabilities</h2>
-  <p>Each provider declares capabilities in <code>providers.json</code>:</p>
-  <ul>
-    <li><strong>chat</strong> — Chat completion endpoint</li>
-    <li><strong>streaming</strong> — full, partial, or none</li>
-    <li><strong>toolCalling</strong> — native, adapted, or none</li>
-    <li><strong>vision</strong> — Image input support</li>
-    <li><strong>jsonSchema</strong> — Structured output via JSON schema</li>
-    <li><strong>reasoningEffort</strong> — Configurable reasoning depth</li>
-    <li><strong>contextLength</strong> — Maximum context window size</li>
-  </ul>
-  <h2>Local / Offline Development</h2>
-  <pre><code># Ollama — fully offline
-export OLLAMA_API_KEY=ollama  # (any non-empty value)
-export OLLAMA_HOST=http://localhost:11434
-clew
-> /model ollama/llama4:70b
-# Debug specific provider
-DEBUG=provider:anthropic clew</code></pre>
-  <footer class="footer">
-    <span>Clew Code 0.2.14 — Open Source</span>
-    <div class="footer-links">
-      <a href="https://github.com/ClewCode/ClewCode">GitHub</a>
-      <a href="https://github.com/ClewCode/ClewCode/issues">Issues</a>
-    </div>
-  </footer>
-</main>
-<nav class="toc-sidebar"></nav>
-</div>
-</div>
-<script src="js/main.js"></script>
-</body>
-</html>
-/footer>
-</main>
-<nav class="toc-sidebar"></nav>
-</div>
-</div>
-<script src="js/main.js"></script>
-</body>
-</html>
+<!DOCTYPE html>
+<html lang="en">
+<head>
+<meta charset="UTF-8">
+<meta name="viewport" content="width=device-width, initial-scale=1.0">
+<title>Providers — Clew Code</title>
+<meta name="description" href="All 27 AI providers supported by Clew Code.">
+<link rel="icon" type="image/svg+xml" href="assets/clew.svg">
+<link rel="preconnect" href="https://fonts.googleapis.com">
+<link href="https://fonts.googleapis.com/css2?family=DM+Sans:wght@400;500;600;700&family=JetBrains+Mono:wght@400;500;600;700&display=swap" rel="stylesheet">
+<link rel="stylesheet" href="css/styles.css">
+</head>
+<body>
+<header class="header"></header>
+<div id="sidebarOverlay" class="sidebar-overlay"></div>
+<aside id="sidebar" class="sidebar"></aside>
+<div class="content-wrap">
+<div class="content">
+<div class="breadcrumbs"><a href="index.html">Home</a><span class="sep">/</span><span class="current">Providers</span></div>
+<h1>Providers</h1>
+<p class="sub">Clew Code supports 27 AI providers. Switch between them anytime with <code>/model</code>.</p>
+<h2 id="supported">Supported Providers</h2>
+<table>
+  <thead>
+    <tr><th>Provider</th><th>Env Variable</th><th>Notes</th></tr>
+  </thead>
+  <tbody>
+    <tr><td>Anthropic</td><td><code>ANTHROPIC_API_KEY</code></td><td>Claude models</td></tr>
+    <tr><td>OpenAI</td><td><code>OPENAI_API_KEY</code></td><td>GPT-4, GPT-4o, o-series</td></tr>
+    <tr><td>Google Gemini</td><td><code>GOOGLE_API_KEY</code></td><td>Gemini 1.5/2.0</td></tr>
+    <tr><td>DeepSeek</td><td><code>DEEPSEEK_API_KEY</code></td><td>DeepSeek-V3, R1</td></tr>
+    <tr><td>Groq</td><td><code>GROQ_API_KEY</code></td><td>Fast inference</td></tr>
+    <tr><td>xAI (Grok)</td><td><code>XAI_API_KEY</code></td><td>Grok models</td></tr>
+    <tr><td>Mistral</td><td><code>MISTRAL_API_KEY</code></td><td>Mistral Large, Small</td></tr>
+    <tr><td>Cohere</td><td><code>COHERE_API_KEY</code></td><td>Command R+</td></tr>
+    <tr><td>Perplexity</td><td><code>PERPLEXITY_API_KEY</code></td><td>Sonar models</td></tr>
+    <tr><td>Cerebras</td><td><code>CEREBRAS_API_KEY</code></td><td>Fast ASIC inference</td></tr>
+    <tr><td>Moonshot (Kimi)</td><td><code>MOONSHOT_API_KEY</code></td><td>Chinese market</td></tr>
+    <tr><td>Zhipu (GLM)</td><td><code>ZHIPU_API_KEY</code></td><td>GLM models</td></tr>
+    <tr><td>NVIDIA NIM</td><td><code>NVIDIA_API_KEY</code></td><td>Self-hosted NIM</td></tr>
+    <tr><td>OpenRouter</td><td><code>OPENROUTER_API_KEY</code></td><td>Unified API to many models</td></tr>
+    <tr><td>GitHub Copilot</td><td><code>COPILOT_GITHUB_TOKEN</code></td><td>Copilot models</td></tr>
+    <tr><td>OpenCode</td><td><code>OPENCODE_API_KEY</code></td><td>Open-source provider</td></tr>
+    <tr><td>KiloCode</td><td><code>KILOCODE_API_KEY</code></td><td>Kilo API</td></tr>
+    <tr><td>Ollama</td><td><code>OLLAMA_HOST</code></td><td>Local models (<code>http://localhost:11434</code>)</td></tr>
+    <tr><td>Together AI</td><td><code>TOGETHER_API_KEY</code></td><td>Hosted open models</td></tr>
+    <tr><td>Fireworks AI</td><td><code>FIREWORKS_API_KEY</code></td><td>Fast inference</td></tr>
+    <tr><td>Deep Infra</td><td><code>DEEP_INFRA_API_KEY</code></td><td>Serverless GPU</td></tr>
+    <tr><td>SiliconFlow</td><td><code>SILICONFLOW_API_KEY</code></td><td>Asian cloud</td></tr>
+    <tr><td>Hugging Face</td><td><code>HUGGINGFACE_API_KEY</code></td><td>HF Inference API</td></tr>
+    <tr><td>Poe</td><td><code>POE_API_KEY</code></td><td>Poe by Quora</td></tr>
+    <tr><td>DigitalOcean</td><td><code>DIGITALOCEAN_API_KEY</code></td><td>GPU droplets</td></tr>
+    <tr><td>Cline</td><td><code>CLINE_API_KEY</code></td><td>Cline provider</td></tr>
+    <tr><td>OpenCode Go</td><td><code>OPENCODE_GO_API_KEY</code></td><td>OpenCode Go variant</td></tr>
+  </tbody>
+</table>
+<h2 id="switch">Switching Providers</h2>
+<p>Use the <code>/model</code> command inside the REPL:</p>
+<pre><code class="language-bash">❯ /model openai
+❯ /model gpt-5.5
+❯ /model deepseek-v4-flash
+❯ /model ollama/llama3.3
+</code></pre>
+<h2 id="list">List Available Models</h2>
+<pre><code class="language-bash">❯ /model list
+</code></pre>
+<p>Shows live model lists from provider APIs with capability tags:<br>
+<code>[200K ctx, vision, tools, reason, free]</code></p>
+<h2 id="effort">Reasoning Effort</h2>
+<p>Some providers expose <code>reasoningEffort</code> (NVIDIA, DeepSeek, OpenRouter, etc.). Control it with:</p>
+<pre><code class="language-bash">❯ /effort high
+</code></pre>
+</div>
+</div>
+<script src="js/main.js"></script>
+</body>
+</html>

package/docs/quick-start.html CHANGED Viewed

@@ -1,93 +1,81 @@
-<!DOCTYPE html>
-<html lang="en">
-<head>
-  <meta charset="UTF-8">
-  <meta name="viewport" content="width=device-width, initial-scale=1.0">
-  <title>Quick Start — Clew</title>
-  <meta name="description" content="Get started with Clew in minutes — install, configure a provider, and run your first session.">
-  <link rel="preconnect" href="https://fonts.googleapis.com">
-  <link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
-  <link href="https://fonts.googleapis.com/css2?family=DM+Sans:wght@400;500;600;700&family=JetBrains+Mono:wght@400;500;600;700&display=swap" rel="stylesheet">
-  <link rel="stylesheet" href="css/styles.css">
-  <link rel="icon" type="image/svg+xml" href="./assets/clew.svg">
-</head>
-<body>
-<header class="header"></header>
-<div class="app">
-  <aside class="sidebar" id="sidebar"></aside>
-  <div class="sidebar-overlay" id="sidebarOverlay"></div>
-  <div class="content-wrap">
-    <main class="content">
-      <div class="breadcrumbs"><a href="index.html">Home</a><span class="sep">/</span><span>Quick Start</span></div>
-      <h1>Quick Start</h1>
-      <p class="section-subtitle">From zero to AI-assisted coding in under a minute.</p>
-      <h2>1. Install</h2>
-      <pre><code>npm install -g clew-code
-clew --version</code></pre>
-      <p>Make sure <a href="installation.html">Bun 1.3+</a> is installed first. The npm package does not bundle Bun.</p>
-      <h2>2. Set a Provider Key</h2>
-      <p>Set at least one API key as an environment variable. See <a href="providers.html">Providers</a> for all 29 options.</p>
-      <pre><code># Anthropic (recommended for best tool calling)
-export ANTHROPIC_API_KEY=sk-ant-...
-# Or DeepSeek
-export DEEPSEEK_API_KEY=sk-...
-# Or Google Gemini
-export GOOGLE_API_KEY=...</code></pre>
-      <h2>3. Launch</h2>
-      <pre><code>cd /path/to/your/project
-clew</code></pre>
-      <p>The terminal UI starts with model name, provider, and context usage in the status bar.</p>
-      <h2>4. First Commands</h2>
-      <pre><code>> "explain this project's structure"
-> "find all the test files"
-> /status          # Check model, provider, API status
-> /model sonnet    # Switch model (alias or full ID)
-> /doctor          # Run environment diagnostics</code></pre>
-      <h2>5. Key Commands to Know</h2>
-      <table>
-        <tr><th>Command</th><th>Use</th></tr>
-        <tr><td><code>/clear</code></td><td>Clear conversation and free context</td></tr>
-        <tr><td><code>/compact</code></td><td>Compress context to save tokens (auto multi-pass for large sessions)</td></tr>
-        <tr><td><code>/model &lt;name&gt;</code></td><td>Switch model or provider</td></tr>
-        <tr><td><code>/permissions</code></td><td>Manage tool permission rules</td></tr>
-        <tr><td><code>/plan</code></td><td>Toggle plan mode</td></tr>
-        <tr><td><code>/config</code></td><td>Open config panel</td></tr>
-        <tr><td><code>/help</code></td><td>Show all available commands</td></tr>
-      </table>
-      <h2>6. Sessions</h2>
-      <pre><code># Continue last conversation
-clew -c
-# Resume a specific session
-clew -r
-# Print mode (non-interactive, pipe-friendly)
-clew -p "find all unused exports"
-# With structured output
-clew -p --output-format json "list all dependencies"</code></pre>
-      <div class="callout callout-info">
-        <strong>Tips</strong>
-        Type <code>/</code> to discover all commands. Use <code>/powerup</code> for interactive lessons. Set <code>--model sonnet</code> at startup to skip the default model.
-      </div>
-    </main>
-    <nav class="toc-sidebar"></nav>
-  </div>
-</div>
-<script src="js/main.js"></script>
-</body>
-</html>
+<!DOCTYPE html>
+<html lang="en">
+<head>
+<meta charset="UTF-8">
+<meta name="viewport" content="width=device-width, initial-scale=1.0">
+<title>Quick Start — Clew Code</title>
+<meta name="description" content="Get started with Clew Code in under a minute.">
+<link rel="icon" type="image/svg+xml" href="assets/clew.svg">
+<link rel="preconnect" href="https://fonts.googleapis.com">
+<link href="https://fonts.googleapis.com/css2?family=DM+Sans:wght@400;500;600;700&family=JetBrains+Mono:wght@400;500;600;700&display=swap" rel="stylesheet">
+<link rel="stylesheet" href="css/styles.css">
+</head>
+<body>
+<header class="header"></header>
+<div id="sidebarOverlay" class="sidebar-overlay"></div>
+<aside id="sidebar" class="sidebar"></aside>
+<div class="content-wrap">
+<div class="content">
+<div class="breadcrumbs"><a href="index.html">Home</a><span class="sep">/</span><span class="current">Quick Start</span></div>
+<h1>Quick Start</h1>
+<p class="sub">Get Clew Code running in under a minute.</p>
+<h2 id="install">1. Install</h2>
+<pre><code class="language-bash">npm install -g clew-code
+</code></pre>
+<p>Requires <a href="https://bun.sh">Bun</a> 1.3+, Node.js 18+, Git, and one provider API key.</p>
+<h2 id="run">2. Run</h2>
+<pre><code class="language-bash">cd my-project
+clew
+</code></pre>
+<p>On first launch you'll be prompted to select a provider.</p>
+<h2 id="configure-provider">3. Configure a Provider</h2>
+<p>Inside the REPL, pick your provider and model:</p>
+<pre><code class="language-bash">❯ /model openai
+❯ /model gpt-5.5
+❯ /model deepseek-v4-pro
+❯ /model ollama/llama3.3
+</code></pre>
+<p>Or set environment variables before starting:</p>
+<pre><code class="language-bash">export ANTHROPIC_API_KEY=sk-ant-...
+export OPENAI_API_KEY=sk-...
+export GOOGLE_API_KEY=...
+export DEEPSEEK_API_KEY=...
+</code></pre>
+<h2 id="first-commands">4. Try Commands</h2>
+<pre><code class="language-bash">❯ /help           # list everything
+❯ /status         # current provider, model, context info
+❯ /mesh discover  # find other Clew instances on LAN
+❯ /mcp list       # connected MCP servers
+</code></pre>
+<h2 id="one-shot">One-Shot Mode</h2>
+<p>Pipe-friendly single-use mode:</p>
+<pre><code class="language-bash">clew -p "summarize CHANGELOG.md"
+</code></pre>
+<h2 id="resume">Resume Last Session</h2>
+<pre><code class="language-bash">clew --resume last
+</code></pre>
+<h2 id="next">Next Steps</h2>
+<ul>
+  <li><a href="installation.html">Full installation guide</a></li>
+  <li><a href="configuration.html">Configuration reference</a></li>
+  <li><a href="providers.html">All 27 providers</a></li>
+  <li><a href="commands.html">Slash commands</a></li>
+</ul>
+</div>
+</div>
+<script src="js/main.js"></script>
+</body>
+</html>

package/docs/research-memory.html CHANGED Viewed

@@ -1,102 +1,71 @@
-<!DOCTYPE html>
-<html lang="en">
-<head>
-  <meta charset="UTF-8">
-  <meta name="viewport" content="width=device-width, initial-scale=1.0">
-  <title>Research & Memory — Clew</title>
-  <meta name="description" content="Deep research system and semantic memory — citation extraction, claim verification, dossier generation, cross-lingual memory search.">
-  <link rel="preconnect" href="https://fonts.googleapis.com">
-  <link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
-  <link href="https://fonts.googleapis.com/css2?family=DM+Sans:wght@400;500;600;700&family=JetBrains+Mono:wght@400;500;600;700&display=swap" rel="stylesheet">
-  <link rel="stylesheet" href="css/styles.css">
-  <link rel="icon" type="image/svg+xml" href="./assets/clew.svg">
-</head>
-<body>
-<header class="header"></header>
-<div class="app">
-  <aside class="sidebar" id="sidebar"></aside>
-  <div class="sidebar-overlay" id="sidebarOverlay"></div>
-  <div class="content-wrap">
-    <main class="content">
-      <div class="breadcrumbs"><a href="index.html">Home</a><span class="sep">/</span><span>Research &amp; Memory</span></div>
-      <h1>Research &amp; Memory</h1>
-      <p class="section-subtitle">Clew provides a built-in deep research system and cross-session semantic memory — both designed to work with local files, web sources, and a persistent knowledge store.</p>
-      <h2>Research System</h2>
-      <p>The research system lives in <code>src/research/</code> and supports deep, source-grounded research across local files, wiki content, and memory:</p>
-      <ul>
-        <li><strong>Citation extraction</strong> — Automatic extraction of citations from research sources</li>
-        <li><strong>Claim verification</strong> — Fact-check claims against multiple sources</li>
-        <li><strong>Dossier generation</strong> — Structured reports with source attribution</li>
-        <li><strong>Truth checking</strong> — Cross-reference claims for accuracy</li>
-        <li><strong>Source ranking</strong> — Prioritize authoritative sources</li>
-      </ul>
-      <h3>Research Commands</h3>
-      <table>
-        <tr><th>Command</th><th>Description</th></tr>
-        <tr><td><code>/research</code></td><td>Deep source-grounded research across local files, wiki, and memory</td></tr>
-      </table>
-      <h2>Memory System</h2>
-      <p>Clew has a <strong>two-tier memory system</strong>:</p>
-      <h3>1. FTS5 Semantic Search (<code>src/memory/</code>)</h3>
-      <p>Cross-session persistent knowledge storage with SQLite FTS5 search:</p>
-      <ul>
-        <li><strong>SQLite FTS5 search</strong> — Find relevant memories using FTS5 similarity</li>
-        <li><strong>Cross-lingual</strong> — Search across languages using FTS5 indexing</li>
-        <li><strong>Token-aware chunking</strong> — 3000-token chunks with word-boundary splitting</li>
-        <li><strong>Secret redaction</strong> — Strips API keys and tokens before indexing</li>
-      </ul>
-      <h3>2. Cross-Session Long-Term Memory (<code>src/services/longTermMemory/</code>)</h3>
-      <p>Session persistence with <strong>knowledge graph</strong> and <strong>experience system</strong>:</p>
-      <ul>
-        <li><strong>Knowledge Graph</strong> — Entities (session, decision, file, tag, model) with typed edges; multi-hop traversal via recursive CTE</li>
-        <li><strong>Experience System</strong> — XP, levels, streak bonuses, expertise profile, cold detection, correction learning</li>
-        <li><strong>Human-like consolidation</strong> — Recent=detail, old=weekly/monthly digests, patterns extracted</li>
-        <li><strong>Auto-inject</strong> — Previous session context auto-injected at session start</li>
-        <li><strong>Timeline</strong> — Chronological view with density stats</li>
-      </ul>
-      <h3>Memory Commands</h3>
-      <table>
-        <tr><th>Command</th><th>Description</th></tr>
-        <tr><td><code>/memory save [summary]</code></td><td>Save current session to long-term memory + knowledge graph</td></tr>
-        <tr><td><code>/memory timeline</code></td><td>Show session history chronologically</td></tr>
-        <tr><td><code>/memory stats</code></td><td>Show memory density stats and activity chart</td></tr>
-        <tr><td><code>/memory xp</code></td><td>Show experience report, expertise profile, XP progress</td></tr>
-        <tr><td><code>/memory graph</code></td><td>Show knowledge graph stats and structure</td></tr>
-        <tr><td><code>/memory digest</code></td><td>Show consolidated weekly/monthly digests</td></tr>
-        <tr><td><code>/memory preview</code></td><td>Preview sessions ready for consolidation</td></tr>
-        <tr><td><code>/memory consolidate</code></td><td>Mark old sessions as consolidated</td></tr>
-        <tr><td><code>/memory search &lt;query&gt;</code></td><td>Search indexed memory facts using SQLite FTS5</td></tr>
-        <tr><td><code>/memory-search</code></td><td>Search memories using FTS5 (cross-lingual)</td></tr>
-      </table>
-      <h2>Architecture Files</h2>
-      <table>
-        <tr><th>Path</th><th>Role</th></tr>
-        <tr><td><code>src/research/</code></td><td>Deep research, dossier generation, truth checking, source ranking</td></tr>
-        <tr><td><code>src/memory/</code></td><td>SQLite FTS5 memory search (14 files, no embeddings)</td></tr>
-        <tr><td><code>src/services/longTermMemory/</code></td><td>Knowledge graph, experience system, consolidation, timeline, cross-session, auto-inject</td></tr>
-      </table>
-      <footer class="footer">
-        <span>Clew Code 0.2.14 — Open Source</span>
-        <div class="footer-links">
-          <a href="https://github.com/ClewCode/ClewCode">GitHub</a>
-          <a href="https://github.com/ClewCode/ClewCode/issues">Issues</a>
-        </div>
-      </footer>
-    </main>
-    <nav class="toc-sidebar"></nav>
-  </div>
-</div>
-<script src="js/main.js"></script>
-</body>
-</html>
+<!DOCTYPE html>
+<html lang="en">
+<head>
+<meta charset="UTF-8">
+<meta name="viewport" content="width=device-width, initial-scale=1.0">
+<title>Research &amp; Memory — Clew Code</title>
+<meta name="description" content="Persistent memory and research system in Clew Code.">
+<link rel="icon" type="image/svg+xml" href="assets/clew.svg">
+<link rel="preconnect" href="https://fonts.googleapis.com">
+<link href="https://fonts.googleapis.com/css2?family=DM+Sans:wght@400;500;600;700&family=JetBrains+Mono:wght@400;500;600;700&display=swap" rel="stylesheet">
+<link rel="stylesheet" href="css/styles.css">
+</head>
+<body>
+<header class="header"></header>
+<div id="sidebarOverlay" class="sidebar-overlay"></div>
+<aside id="sidebar" class="sidebar"></aside>
+<div class="content-wrap">
+<div class="content">
+<div class="breadcrumbs"><a href="index.html">Home</a><span class="sep">/</span><span class="current">Research &amp; Memory</span></div>
+<h1>Research &amp; Memory</h1>
+<p class="sub">Clew Code learns from your sessions over time. The memory system persists knowledge, preferences, and project context across sessions.</p>
+<h2 id="auto-memory">Auto-Memory</h2>
+<p>Clew Code automatically captures lessons from edit and exec sessions, storing them in <code>.moocode/memory.md</code>. The system tracks:</p>
+<ul>
+  <li>Project conventions and patterns</li>
+  <li>User preferences and workflow choices</li>
+  <li>Frequently used commands and tools</li>
+  <li>Architectural decisions and their rationale</li>
+</ul>
+<h2 id="ltm">Long-Term Memory</h2>
+<p>The long-term memory system uses SQLite (<code>~/.clew/projects/&lt;project&gt;/session-memory.db</code>) with a human-like consolidation model:</p>
+<table>
+  <thead>
+    <tr><th>Age</th><th>Level</th><th>Detail</th></tr>
+  </thead>
+  <tbody>
+    <tr><td>&lt; 7 days</td><td>Raw</td><td>Full session detail</td></tr>
+    <tr><td>1-4 weeks</td><td>Weekly digest</td><td>Summary + patterns</td></tr>
+    <tr><td>&gt; 1 month</td><td>Monthly digest</td><td>High-level trends</td></tr>
+    <tr><td>Ancient</td><td>Patterns only</td><td>Recurring topics preserved</td></tr>
+  </tbody>
+</table>
+<h2 id="memory-commands">Memory Commands</h2>
+<pre><code class="language-bash">❯ /memory save            # save session summary
+❯ /memory timeline        # show chronological session history
+❯ /memory stats           # activity density chart
+❯ /memory digest          # weekly/monthly digests
+❯ /memory preview         # preview sessions ready for consolidation
+❯ /memory consolidate     # mark old sessions as consolidated
+❯ /memory search &lt;q&gt;     # search stored memory entries
+</code></pre>
+<h2 id="research">Research System</h2>
+<p>The research system enables deep-dive investigations with persistent findings. Research results are indexed and searchable across sessions.</p>
+<pre><code class="language-bash">❯ /research start "topic"    # start a research session
+❯ /research list              # list all research topics
+❯ /research show &lt;id&gt;        # show research findings
+</code></pre>
+</div>
+</div>
+<script src="js/main.js"></script>
+</body>
+</html>