v1.8.0 — add plan2code-metrics recursive self-improvement toolchain

New package for contributors to collect, aggregate, analyze, and improve workflow prompts based on real project data. Includes unit tests (vitest), installer integration, and loop/finalize hints.
2026-07-21 18:33:22 -07:00 · 2026-02-22 19:57:40 -08:00
parent de46275b51
commit 5c2f70a37c
27 changed files with 3333 additions and 6 deletions
@@ -0,0 +1,98 @@
+/**
+ * invoke-llm.ts
+ * Unified LLM invocation for plan2code-metrics.
+ * Supports Claude Code (temp file → stdin) and Copilot CLI (stdin string).
+ * Mirrors the agent pattern from plan2code-loop.
+ */
+
+import { execa } from 'execa';
+import { writeFileSync, unlinkSync } from 'fs';
+import { join } from 'path';
+import { tmpdir } from 'os';
+
+// ── Agent definitions ────────────────────────────────────────────────────────
+
+export type AgentType = 'claude-code' | 'copilot-cli';
+
+export interface AgentDef {
+  name: AgentType;
+  displayName: string;
+  command: string;
+  models: Array<{ value: string; label: string }>;
+}
+
+export const AGENTS: Record<AgentType, AgentDef> = {
+  'claude-code': {
+    name: 'claude-code',
+    displayName: 'Claude Code',
+    command: 'claude',
+    models: [
+      { value: 'claude-opus-4-6', label: 'Claude Opus 4.6 (Recommended)' },
+      { value: 'claude-sonnet-4-6', label: 'Claude Sonnet 4.6 (faster)' },
+    ],
+  },
+  'copilot-cli': {
+    name: 'copilot-cli',
+    displayName: 'GitHub Copilot CLI',
+    command: 'copilot',
+    models: [
+      { value: 'claude-sonnet-4', label: 'Claude Sonnet 4 (Default)' },
+      { value: 'claude-sonnet-4.5', label: 'Claude Sonnet 4.5' },
+      { value: 'claude-opus-4.5', label: 'Claude Opus 4.5' },
+      { value: 'gpt-5', label: 'GPT-5' },
+      { value: 'gpt-5-mini', label: 'GPT-5 Mini' },
+      { value: 'gemini-3-pro-preview', label: 'Gemini 3 Pro' },
+    ],
+  },
+};
+
+// ── Invocation ───────────────────────────────────────────────────────────────
+
+export interface InvokeLLMOptions {
+  prompt: string;
+  model: string;
+  agent: AgentType;
+  timeout?: number;
+}
+
+export async function invokeLLM(opts: InvokeLLMOptions): Promise<string> {
+  const { prompt, model, agent, timeout = 300_000 } = opts;
+  const def = AGENTS[agent];
+
+  if (agent === 'claude-code') {
+    // Write prompt to temp file — more reliable than stdin on Windows
+    const tempFile = join(tmpdir(), `plan2code-metrics-prompt-${Date.now()}.txt`);
+    writeFileSync(tempFile, prompt, 'utf-8');
+
+    try {
+      const args: string[] = [
+        '--print',
+        '--dangerously-skip-permissions',
+      ];
+      if (model) {
+        args.push('--model', model);
+      }
+
+      const result = await execa(def.command, args, {
+        inputFile: tempFile,
+        timeout,
+      });
+      return result.stdout;
+    } finally {
+      try { unlinkSync(tempFile); } catch { /* ignore cleanup errors */ }
+    }
+  } else {
+    // Copilot CLI: pipe prompt via stdin string
+    const args: string[] = [];
+    if (model) {
+      args.push('--model', model);
+    }
+    args.push('--allow-all-tools', '-s');
+
+    const result = await execa(def.command, args, {
+      input: prompt,
+      timeout,
+    });
+    return result.stdout;
+  }
+}