pan-wizard 2.9.1 → 3.5.0

package/agents/pan-reviewer.md

@@ -3,6 +3,8 @@ name: pan-reviewer
 description: Read-only code review agent. Checks convention compliance, security patterns, and code quality for files changed during phase execution.
 tools: Read, Grep, Glob, Bash
 color: yellow
+thinking: enabled
+thinking_budget: 4000
 ---
 
 <role>

package/agents/pan-verifier.md

@@ -3,6 +3,8 @@ name: pan-verifier
 description: Verifies phase goal achievement through goal-backward analysis. Checks codebase delivers what phase promised, not just that tasks completed. Creates verification.md report.
 tools: Read, Write, Bash, Grep, Glob
 color: green
+thinking: enabled
+thinking_budget: 6000
 ---
 
 <role>

package/bin/install-lib.cjs

@@ -570,6 +570,198 @@ function buildHookCommand(configDir, hookName) {
   return `node "${hooksPath}"`;
 }
 
+// ─── Opus 4.7 Skills & Thinking ────────────────────────────────────────────
+
+/**
+ * Build a Claude Code native skill shim for a PAN command.
+ *
+ * Claude Code 1.x discovers skills in `.claude/skills/` by frontmatter.
+ * PAN's commands live in `.claude/commands/pan/`, so we write a small shim
+ * that registers the command as a skill pointing back at the command file.
+ *
+ * @param {Object} opts
+ * @param {string} opts.commandName - e.g. "focus-scan"
+ * @param {string} opts.description - Human-readable one-liner (≤120 chars preferred)
+ * @param {string} [opts.trigger] - Optional trigger guidance for auto-invocation
+ * @returns {string} Skill markdown content
+ */
+function buildClaudeSkillShim(opts) {
+  if (!opts || typeof opts.commandName !== 'string' || !opts.commandName.trim()) {
+    throw new Error('buildClaudeSkillShim: commandName is required');
+  }
+  const name = opts.commandName.trim();
+  const description = (opts.description || '').replace(/\s+/g, ' ').trim();
+  const trigger = (opts.trigger || '').replace(/\s+/g, ' ').trim();
+
+  const frontmatter = [
+    '---',
+    `name: pan-${name}`,
+    `description: ${yamlQuote(description)}`,
+    trigger ? `trigger: ${yamlQuote(trigger)}` : null,
+    'source: pan-wizard',
+    '---',
+  ].filter(Boolean).join('\n');
+
+  const body = [
+    '',
+    `# /pan:${name}`,
+    '',
+    description || `PAN command: ${name}`,
+    '',
+    `Invokes the command defined at \`.claude/commands/pan/${name}.md\`.`,
+    '',
+    `To use, run: \`/pan:${name}\``,
+    '',
+  ].join('\n');
+
+  return frontmatter + body;
+}
+
+/**
+ * Translate a thinking directive from the generic PAN frontmatter shape
+ * into the runtime-specific syntax (or prose fallback).
+ *
+ * PAN agents declare: `thinking: enabled` and `thinking_budget: 8000` in
+ * frontmatter. Runtimes that support native extended thinking consume those
+ * fields directly. Runtimes without native support get a prose preamble
+ * that coaches the model to think step-by-step before tool calls.
+ *
+ * @param {string} runtime - 'claude'|'codex'|'gemini'|'opencode'|'copilot'
+ * @param {Object} directive - {enabled: boolean, budget: number}
+ * @returns {{frontmatter: Object, preamble: string}} Translated directive.
+ *   `frontmatter` = fields to add to the agent's YAML header.
+ *   `preamble` = prose to inject at top of agent prompt.
+ */
+function translateThinkingDirective(runtime, directive) {
+  const result = { frontmatter: {}, preamble: '' };
+  if (!directive || !directive.enabled) return result;
+  const budget = Number(directive.budget) > 0 ? Number(directive.budget) : 2000;
+
+  switch (runtime) {
+    case 'claude':
+      // Claude Code consumes these natively.
+      result.frontmatter = { thinking: 'enabled', thinking_budget: budget };
+      return result;
+    case 'codex':
+    case 'opencode':
+    case 'gemini':
+    case 'copilot':
+    default:
+      // Prose fallback — host runtime has no native thinking support.
+      result.preamble = `Think through the problem step-by-step before taking any action. Reason about edge cases, hidden dependencies, and likely failure modes. Use up to ~${budget} tokens of internal reasoning. Only after that, call tools or write output.`;
+      return result;
+  }
+}
+
+/**
+ * Strip Opus 4.7 `thinking` / `thinking_budget` frontmatter fields from an
+ * agent markdown file for runtimes that don't support native extended
+ * thinking. When thinking was enabled, inject a prose preamble at the top
+ * of the body instructing the model to think step-by-step.
+ *
+ * Claude runtime is a no-op — those fields stay in frontmatter so the
+ * host runtime consumes them.
+ *
+ * @param {string} content - Full agent .md content
+ * @param {string} runtime - 'claude'|'codex'|'gemini'|'opencode'|'copilot'
+ * @returns {string} Possibly-rewritten content
+ */
+function stripThinkingFrontmatter(content, runtime) {
+  if (runtime === 'claude') return content;
+  if (typeof content !== 'string' || !content) return content;
+
+  const { frontmatter, body } = extractFrontmatterAndBody(content);
+  if (!frontmatter) return content;
+
+  const thinkingValue = extractFrontmatterField(frontmatter, 'thinking');
+  const budgetValue = extractFrontmatterField(frontmatter, 'thinking_budget');
+  if (!thinkingValue && !budgetValue) return content;
+
+  // Remove the two fields (match on their own lines only).
+  let fmBody = frontmatter
+    .replace(/^thinking:\s*[^\n]*\n?/gm, '')
+    .replace(/^thinking_budget:\s*[^\n]*\n?/gm, '');
+
+  const rebuilt = `---\n${fmBody.replace(/^---\n|\n---$/g, '')}\n---`;
+  let out = rebuilt.replace(/\n\n+/g, '\n\n') + '\n\n';
+
+  // If thinking was enabled, prepend a prose preamble.
+  const enabled = String(thinkingValue || '').toLowerCase().trim() === 'enabled'
+    || String(thinkingValue || '').toLowerCase().trim() === 'true';
+  if (enabled) {
+    const directive = { enabled: true, budget: Number(budgetValue) || 2000 };
+    const { preamble } = translateThinkingDirective(runtime, directive);
+    if (preamble) {
+      out += `<!-- pan:thinking -->\n${preamble}\n<!-- /pan:thinking -->\n\n`;
+    }
+  }
+
+  out += body.replace(/^\n+/, '');
+  return out;
+}
+
+// ─── Opus 4.7 Capability Detection ──────────────────────────────────────────
+
+/**
+ * Detect model capabilities from a model name string.
+ * Used by installer to warn users when their default model lacks features
+ * PAN 2.10+ relies on (1M context, extended thinking, prompt caching).
+ *
+ * @param {string} modelName - e.g. "claude-opus-4-7", "claude-sonnet-4-6", "gpt-5"
+ * @returns {{has_1m_ctx: boolean, has_thinking: boolean, has_cache: boolean, tier: string}}
+ */
+function detectModelCapabilities(modelName) {
+  const result = { has_1m_ctx: false, has_thinking: false, has_cache: false, tier: 'unknown' };
+  if (typeof modelName !== 'string' || !modelName) return result;
+  const n = modelName.toLowerCase();
+
+  // Anthropic Claude family
+  if (n.includes('opus-4-7') || n.includes('opus-4.7')) {
+    return { has_1m_ctx: true, has_thinking: true, has_cache: true, tier: 'reasoning' };
+  }
+  if (n.includes('opus-4-6') || n.includes('opus-4.6') || n.includes('opus-4')) {
+    return { has_1m_ctx: false, has_thinking: true, has_cache: true, tier: 'reasoning' };
+  }
+  if (n.includes('sonnet-4-6') || n.includes('sonnet-4.6') || n.includes('sonnet-4')) {
+    return { has_1m_ctx: false, has_thinking: true, has_cache: true, tier: 'mid' };
+  }
+  if (n.includes('haiku-4-5') || n.includes('haiku-4.5') || n.includes('haiku-4')) {
+    return { has_1m_ctx: false, has_thinking: false, has_cache: true, tier: 'fast' };
+  }
+  // Older Claude 3.x — no thinking, no 1M context.
+  if (n.includes('claude-3')) {
+    return { has_1m_ctx: false, has_thinking: false, has_cache: true, tier: n.includes('opus') ? 'reasoning' : (n.includes('haiku') ? 'fast' : 'mid') };
+  }
+
+  // OpenAI GPT-5 family — assume caching + thinking but not 1M ctx.
+  if (n.startsWith('gpt-5') || n.includes('o3') || n.includes('o4')) {
+    return { has_1m_ctx: false, has_thinking: true, has_cache: true, tier: 'reasoning' };
+  }
+  if (n.startsWith('gpt-4')) {
+    return { has_1m_ctx: false, has_thinking: false, has_cache: true, tier: 'mid' };
+  }
+
+  // Gemini family. Distinguishes Pro / Flash / Flash-Lite and 2.5/3.x.
+  //   - Pro variants  → reasoning tier (thinking available on 2.5+)
+  //   - Flash         → mid tier (thinking on 2.5+)
+  //   - Flash-Lite    → fast tier (no thinking)
+  //   - 1M context is native on 2.x / 3.x Pro + Flash; Flash-Lite is 1M too on 2.5+.
+  if (n.includes('gemini-3') || n.includes('gemini-2') || n.includes('gemini-1.5')) {
+    const isFlashLite = n.includes('flash-lite');
+    const isFlash = !isFlashLite && n.includes('flash');
+    const isPro = !isFlash && !isFlashLite; // default to Pro when neither flash nor flash-lite in name
+    const is25orNewer = n.includes('gemini-2.5') || n.includes('gemini-3') || n.includes('-2-5');
+    const hasThinking = (is25orNewer || n.includes('thinking')) && !isFlashLite;
+    // 1M context: Pro + Flash on 2.x/3.x, Flash-Lite on 2.5+, Gemini 1.5 Pro (but not 1.5 Flash typically).
+    const has1m = isPro || isFlash || (isFlashLite && is25orNewer)
+      || (n.includes('gemini-1.5-pro') && !isFlash);
+    const tier = isFlashLite ? 'fast' : (isFlash ? 'mid' : 'reasoning');
+    return { has_1m_ctx: has1m, has_thinking: hasThinking, has_cache: true, tier };
+  }
+
+  return result;
+}
+
 // ─── Exports ────────────────────────────────────────────────────────────────
 
 module.exports = {
@@ -613,4 +805,9 @@ module.exports = {
   processAttribution,
   // JSONC
   parseJsonc,
+  // Opus 4.7 capabilities
+  detectModelCapabilities,
+  buildClaudeSkillShim,
+  translateThinkingDirective,
+  stripThinkingFrontmatter,
 };