agentic-dataset-builder 0.2.1 → 0.2.3

package/README.md

@@ -18,7 +18,7 @@ The CLI is native Node.js + TypeScript. It does not require Python.
 If the package is published on npm:
 
 ```bash
-npx --registry=https://registry.npmjs.org/ agentic-dataset-builder@0.2.1 --output-root ./out
+npx --registry=https://registry.npmjs.org/ agentic-dataset-builder@0.2.3 --output-root ./out
 ```
 
 If working from this repo locally:

package/dist/cli.js

@@ -10,10 +10,10 @@ import { Qwen35RecordSchema } from './schemas/qwen35.js';
 import { writeParquet } from './parquet.js';
 function parseArgs(argv) {
     if (argv.includes('--help') || argv.includes('-h')) {
-        console.log(`agentic-dataset-builder@0.2.1
+        console.log(`agentic-dataset-builder@0.2.3
 
 Usage:
-  npx agentic-dataset-builder@0.2.1 --output-root ./out
+  npx agentic-dataset-builder@0.2.3 --output-root ./out
 
 Options:
   --output-root <dir>       Output directory root

package/dist/platform/paths.js

@@ -1,13 +1,36 @@
 import os from 'node:os';
 import path from 'node:path';
 import fs from 'node:fs';
+function currentPlatform() {
+    return process.platform;
+}
+function xdgConfigHome() {
+    return process.env.XDG_CONFIG_HOME;
+}
+function xdgDataHome() {
+    return process.env.XDG_DATA_HOME;
+}
+function macAppSupportHome() {
+    if (currentPlatform() !== 'darwin')
+        return undefined;
+    return path.join(os.homedir(), 'Library', 'Application Support');
+}
 export function candidatePiRoots() {
     const home = os.homedir();
     const appdata = process.env.APPDATA;
     const localappdata = process.env.LOCALAPPDATA;
+    const xdgConfig = xdgConfigHome();
+    const xdgData = xdgDataHome();
+    const macAppSupport = macAppSupportHome();
     return dedupe([
         process.env.PI_SESSION_ROOT,
         path.join(home, '.pi', 'agent', 'sessions'),
+        xdgConfig ? path.join(xdgConfig, 'pi', 'agent', 'sessions') : undefined,
+        xdgConfig ? path.join(xdgConfig, '.pi', 'agent', 'sessions') : undefined,
+        xdgData ? path.join(xdgData, 'pi', 'agent', 'sessions') : undefined,
+        xdgData ? path.join(xdgData, '.pi', 'agent', 'sessions') : undefined,
+        macAppSupport ? path.join(macAppSupport, 'pi', 'agent', 'sessions') : undefined,
+        macAppSupport ? path.join(macAppSupport, '.pi', 'agent', 'sessions') : undefined,
         appdata ? path.join(appdata, 'pi', 'agent', 'sessions') : undefined,
         appdata ? path.join(appdata, '.pi', 'agent', 'sessions') : undefined,
         localappdata ? path.join(localappdata, 'pi', 'agent', 'sessions') : undefined,
@@ -18,9 +41,18 @@ export function candidateCodexRoots() {
     const home = os.homedir();
     const appdata = process.env.APPDATA;
     const localappdata = process.env.LOCALAPPDATA;
+    const xdgConfig = xdgConfigHome();
+    const xdgData = xdgDataHome();
+    const macAppSupport = macAppSupportHome();
     return dedupe([
         process.env.CODEX_SESSION_ROOT,
         path.join(home, '.codex', 'sessions'),
+        xdgConfig ? path.join(xdgConfig, 'codex', 'sessions') : undefined,
+        xdgConfig ? path.join(xdgConfig, '.codex', 'sessions') : undefined,
+        xdgData ? path.join(xdgData, 'codex', 'sessions') : undefined,
+        xdgData ? path.join(xdgData, '.codex', 'sessions') : undefined,
+        macAppSupport ? path.join(macAppSupport, 'Codex', 'sessions') : undefined,
+        macAppSupport ? path.join(macAppSupport, '.codex', 'sessions') : undefined,
         appdata ? path.join(appdata, 'Codex', 'sessions') : undefined,
         appdata ? path.join(appdata, '.codex', 'sessions') : undefined,
         localappdata ? path.join(localappdata, 'Codex', 'sessions') : undefined,
@@ -31,9 +63,18 @@ export function candidateClaudeRoots() {
     const home = os.homedir();
     const appdata = process.env.APPDATA;
     const localappdata = process.env.LOCALAPPDATA;
+    const xdgConfig = xdgConfigHome();
+    const xdgData = xdgDataHome();
+    const macAppSupport = macAppSupportHome();
     return dedupe([
         process.env.CLAUDE_SESSION_ROOT,
         path.join(home, '.claude', 'projects'),
+        xdgConfig ? path.join(xdgConfig, 'claude', 'projects') : undefined,
+        xdgConfig ? path.join(xdgConfig, '.claude', 'projects') : undefined,
+        xdgData ? path.join(xdgData, 'claude', 'projects') : undefined,
+        xdgData ? path.join(xdgData, '.claude', 'projects') : undefined,
+        macAppSupport ? path.join(macAppSupport, 'Claude', 'projects') : undefined,
+        macAppSupport ? path.join(macAppSupport, '.claude', 'projects') : undefined,
         appdata ? path.join(appdata, 'Claude', 'projects') : undefined,
         appdata ? path.join(appdata, '.claude', 'projects') : undefined,
         localappdata ? path.join(localappdata, 'Claude', 'projects') : undefined,

package/dist/platform/paths.test.d.ts

@@ -0,0 +1 @@
+export {};

package/dist/platform/paths.test.js

@@ -0,0 +1,36 @@
+import { describe, expect, it, vi, beforeEach, afterEach } from 'vitest';
+const envBackup = { ...process.env };
+describe('platform path candidates', () => {
+    beforeEach(() => {
+        vi.resetModules();
+        process.env = { ...envBackup };
+    });
+    afterEach(() => {
+        process.env = { ...envBackup };
+        vi.unstubAllGlobals();
+    });
+    it('includes XDG candidates for pi on linux', async () => {
+        process.env.XDG_CONFIG_HOME = '/home/test/.config';
+        process.env.XDG_DATA_HOME = '/home/test/.local/share';
+        vi.stubGlobal('process', { ...process, platform: 'linux', env: process.env });
+        const mod = await import('./paths.js');
+        const candidates = mod.candidatePiRoots();
+        expect(candidates).toContain('/home/test/.config/pi/agent/sessions');
+        expect(candidates).toContain('/home/test/.local/share/pi/agent/sessions');
+    });
+    it('includes Application Support candidates for codex on macOS', async () => {
+        vi.stubGlobal('process', { ...process, platform: 'darwin', env: process.env });
+        const mod = await import('./paths.js');
+        const candidates = mod.candidateCodexRoots();
+        expect(candidates.some((value) => value.includes('Library/Application Support/Codex/sessions'))).toBe(true);
+    });
+    it('includes APPDATA and LOCALAPPDATA candidates for claude on Windows', async () => {
+        process.env.APPDATA = 'C:/Users/test/AppData/Roaming';
+        process.env.LOCALAPPDATA = 'C:/Users/test/AppData/Local';
+        vi.stubGlobal('process', { ...process, platform: 'win32', env: process.env });
+        const mod = await import('./paths.js');
+        const candidates = mod.candidateClaudeRoots();
+        expect(candidates).toContain('C:/Users/test/AppData/Roaming/Claude/projects');
+        expect(candidates).toContain('C:/Users/test/AppData/Local/Claude/projects');
+    });
+});

package/dist/sources/codex.js

@@ -68,8 +68,16 @@ class TurnBuilder {
         this.flushAssistant();
         if (role === 'user')
             this.messages.push({ role: 'user', content: text });
-        else if (role === 'developer' && text)
-            this.messages.push({ role: 'system', content: text });
+        else if (role === 'developer' && text) {
+            const seenNonSystem = this.messages.some((message) => message.role !== 'system');
+            if (seenNonSystem) {
+                this.lossyReasons.add('late_developer_message_demoted');
+                this.messages.push({ role: 'assistant', content: `[developer]\n${text}` });
+            }
+            else {
+                this.messages.push({ role: 'system', content: text });
+            }
+        }
     }
     ingestReasoning(payload) {
         const summary = Array.isArray(payload.summary) ? payload.summary : [];

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "agentic-dataset-builder",
-  "version": "0.2.1",
+  "version": "0.2.3",
   "description": "Pure TypeScript agentic dataset builder for Pi, Codex, and Claude Code history",
   "license": "MIT",
   "type": "module",