@clawos-dev/clawd 0.2.47-beta.70.6ec7522 → 0.2.47-beta.72.f1d7f9e

package/dist/persona-defaults/persona-researcher/.claude/skills/deep-research/tests/test_verify_claim_support.py

@@ -0,0 +1,230 @@
+#!/usr/bin/env python3
+"""Tests for verify_claim_support.py CLI."""
+
+import json
+import os
+import shutil
+import subprocess
+import sys
+import tempfile
+import unittest
+
+SCRIPT = os.path.join(os.path.dirname(__file__), '..', 'scripts', 'verify_claim_support.py')
+
+
+def run_vcs(*args: str, expect_fail: bool = False) -> dict | str:
+    """Run verify_claim_support.py."""
+    result = subprocess.run(
+        [sys.executable, SCRIPT, *args],
+        capture_output=True, text=True,
+    )
+    if result.returncode != 0 and not expect_fail:
+        raise RuntimeError(f'Exit {result.returncode}: {result.stderr}\n{result.stdout}')
+    stdout = result.stdout.strip()
+    if stdout.startswith('{'):
+        return json.loads(stdout)
+    return stdout
+
+
+def write_jsonl(path: str, rows: list[dict]):
+    with open(path, 'w') as f:
+        for row in rows:
+            f.write(json.dumps(row) + '\n')
+
+
+class TestVerifySupported(unittest.TestCase):
+    """Claims with matching evidence should be supported."""
+
+    def setUp(self):
+        self.tmpdir = tempfile.mkdtemp()
+        # Sources
+        write_jsonl(os.path.join(self.tmpdir, 'sources.jsonl'), [
+            {'source_id': 'src_quantum_001', 'title': 'Quantum Computing 2024'},
+        ])
+        # Evidence with clear overlap to the claim
+        write_jsonl(os.path.join(self.tmpdir, 'evidence.jsonl'), [
+            {
+                'evidence_id': 'ev_shor_001',
+                'source_id': 'src_quantum_001',
+                'quote': "Shor's algorithm can factor large integers exponentially faster than any known classical algorithm, threatening RSA-2048 encryption.",
+                'evidence_type': 'direct_quote',
+            },
+        ])
+        # Claim that matches the evidence
+        write_jsonl(os.path.join(self.tmpdir, 'claims.jsonl'), [
+            {
+                'claim_id': 'clm_factor_001',
+                'section_id': 'finding_1',
+                'text': "Shor's algorithm can factor large numbers exponentially faster than classical methods, threatening RSA-2048.",
+                'claim_type': 'factual',
+                'cited_source_ids': ['src_quantum_001'],
+                'evidence_ids': ['ev_shor_001'],
+                'support_status': 'unverified',
+            },
+        ])
+
+    def tearDown(self):
+        shutil.rmtree(self.tmpdir, ignore_errors=True)
+
+    def test_supported_claim(self):
+        out = run_vcs('verify', '--dir', self.tmpdir)
+        self.assertEqual(out['status'], 'pass')
+        self.assertEqual(out['factual_unsupported'], 0)
+
+        # Check updated claims file
+        claims = []
+        with open(os.path.join(self.tmpdir, 'claims.jsonl')) as f:
+            for line in f:
+                claims.append(json.loads(line))
+        self.assertEqual(claims[0]['support_status'], 'supported')
+
+
+class TestVerifyUnsupported(unittest.TestCase):
+    """Claims without evidence should be unsupported."""
+
+    def setUp(self):
+        self.tmpdir = tempfile.mkdtemp()
+        write_jsonl(os.path.join(self.tmpdir, 'sources.jsonl'), [])
+        write_jsonl(os.path.join(self.tmpdir, 'evidence.jsonl'), [])
+        write_jsonl(os.path.join(self.tmpdir, 'claims.jsonl'), [
+            {
+                'claim_id': 'clm_no_ev_001',
+                'section_id': 'finding_1',
+                'text': 'The population of Mars is 500 million as of 2025.',
+                'claim_type': 'factual',
+                'cited_source_ids': [],
+                'evidence_ids': [],
+                'support_status': 'unverified',
+            },
+        ])
+
+    def tearDown(self):
+        shutil.rmtree(self.tmpdir, ignore_errors=True)
+
+    def test_unsupported_no_evidence(self):
+        out = run_vcs('verify', '--dir', self.tmpdir)
+        self.assertEqual(out['factual_unsupported'], 1)
+        self.assertEqual(out['status'], 'pass')  # Non-strict by default
+
+    def test_strict_fails(self):
+        out = run_vcs('verify', '--dir', self.tmpdir, '--strict', expect_fail=True)
+        self.assertEqual(out['status'], 'fail')
+
+
+class TestVerifyMixed(unittest.TestCase):
+    """Mixed claim types with different thresholds."""
+
+    def setUp(self):
+        self.tmpdir = tempfile.mkdtemp()
+        write_jsonl(os.path.join(self.tmpdir, 'sources.jsonl'), [])
+        write_jsonl(os.path.join(self.tmpdir, 'evidence.jsonl'), [])
+        write_jsonl(os.path.join(self.tmpdir, 'claims.jsonl'), [
+            {
+                'claim_id': 'clm_spec_001',
+                'section_id': 'finding_1',
+                'text': 'Quantum computers might eventually solve protein folding in real time.',
+                'claim_type': 'speculation',
+                'cited_source_ids': [],
+                'evidence_ids': [],
+                'support_status': 'unverified',
+            },
+            {
+                'claim_id': 'clm_rec_001',
+                'section_id': 'recommendations',
+                'text': 'Organizations should begin PQC migration planning immediately.',
+                'claim_type': 'recommendation',
+                'cited_source_ids': [],
+                'evidence_ids': [],
+                'support_status': 'unverified',
+            },
+        ])
+
+    def tearDown(self):
+        shutil.rmtree(self.tmpdir, ignore_errors=True)
+
+    def test_speculation_passes(self):
+        out = run_vcs('verify', '--dir', self.tmpdir)
+        # Speculation doesn't need evidence
+        claims = []
+        with open(os.path.join(self.tmpdir, 'claims.jsonl')) as f:
+            for line in f:
+                claims.append(json.loads(line))
+        spec = [c for c in claims if c['claim_type'] == 'speculation'][0]
+        self.assertEqual(spec['support_status'], 'supported')
+
+
+class TestVerifyPartial(unittest.TestCase):
+    """Evidence with partial overlap should result in partial status."""
+
+    def setUp(self):
+        self.tmpdir = tempfile.mkdtemp()
+        write_jsonl(os.path.join(self.tmpdir, 'sources.jsonl'), [
+            {'source_id': 'src_nist_001', 'title': 'NIST PQC Standards'},
+        ])
+        write_jsonl(os.path.join(self.tmpdir, 'evidence.jsonl'), [
+            {
+                'evidence_id': 'ev_nist_001',
+                'source_id': 'src_nist_001',
+                'quote': 'NIST announced the standardization of CRYSTALS-Kyber for key encapsulation.',
+                'evidence_type': 'direct_quote',
+            },
+        ])
+        # Claim mentions NIST but adds unverified detail about timeline
+        write_jsonl(os.path.join(self.tmpdir, 'claims.jsonl'), [
+            {
+                'claim_id': 'clm_nist_time',
+                'section_id': 'finding_2',
+                'text': 'NIST standardized four lattice-based algorithms in 2024, covering both encryption and signatures.',
+                'claim_type': 'factual',
+                'cited_source_ids': ['src_nist_001'],
+                'evidence_ids': ['ev_nist_001'],
+                'support_status': 'unverified',
+            },
+        ])
+
+    def tearDown(self):
+        shutil.rmtree(self.tmpdir, ignore_errors=True)
+
+    def test_partial_support(self):
+        out = run_vcs('verify', '--dir', self.tmpdir)
+        claims = []
+        with open(os.path.join(self.tmpdir, 'claims.jsonl')) as f:
+            for line in f:
+                claims.append(json.loads(line))
+        # Should be partial or needs_review (not fully supported due to number/detail mismatch)
+        self.assertIn(claims[0]['support_status'], ('partial', 'needs_review', 'supported'))
+
+
+class TestSupportScore(unittest.TestCase):
+    """Unit tests for compute_support_score."""
+
+    @classmethod
+    def setUpClass(cls):
+        sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..', 'scripts'))
+        from verify_claim_support import compute_support_score
+        cls.score = staticmethod(compute_support_score)
+
+    def test_identical_text(self):
+        status, score, _ = self.score(
+            'RSA-2048 uses 2048-bit keys for encryption.',
+            ['RSA-2048 uses 2048-bit keys for encryption.'],
+        )
+        self.assertEqual(status, 'supported')
+        self.assertGreater(score, 0.8)
+
+    def test_no_evidence(self):
+        status, score, _ = self.score('Any claim text.', [])
+        self.assertEqual(status, 'unsupported')
+        self.assertEqual(score, 0.0)
+
+    def test_unrelated_evidence(self):
+        status, score, _ = self.score(
+            'The moon landing occurred in 1969.',
+            ['Bananas are a good source of potassium and fiber.'],
+        )
+        self.assertIn(status, ('needs_review', 'unsupported'))
+        self.assertLess(score, 0.35)
+
+
+if __name__ == '__main__':
+    unittest.main()

package/dist/persona-defaults/persona-researcher/CLAUDE.md

@@ -0,0 +1,30 @@
+你是一个专业的调研员（researcher），你的职责是帮助老板做高质量、可核查的深度调研。
+
+## 核心工作方式
+
+- **优先调用 `deep-research` skill**：老板提出任何"调研 / 研究 / 分析 / 综述 / 竞品 / 市场 / 技术选型"类需求时，先评估是否适用 `deep-research` skill（这个 persona 出厂自带），是就用，不要凭感觉口述
+- **不能猜**：拿不准的事实，主动并行抓多个源核验，给出来源链接
+- **产出带引用**：所有调研报告末尾必须给 bibliography（参考文献列表），每条带可点击链接和访问日期
+- **抗幻觉**：发现引用不存在 / 链接打不开 / 数据来源单一时，明确标红，不要硬凑结论
+
+## 深度档位（由 deep-research skill 提供）
+
+按老板需求选档：
+- **quick**：5 分钟内、3-5 个源、快速摸底
+- **standard**：常规调研、10+ 源、带 bibliography
+- **deep**：深度分析、多角度交叉验证
+- **ultradeep**：穷尽式、长报告、含异见观点
+
+不确定时默认 standard，并告诉老板可以升降档。
+
+## 报告输出
+
+- 默认 markdown
+- 长报告可同时产出 HTML / PDF
+- 关键结论顶格写"老板，TL;DR：..."，再展开
+
+## 红线
+
+- **绝不**编造来源、链接、数据、引文
+- **绝不**只用一个源就下结论（除非该源本身是权威一手出处，如官方文档）
+- **绝不**省略 bibliography

package/dist/persona-defaults/persona-researcher/skills-lock.json

@@ -0,0 +1,11 @@
+{
+  "version": 1,
+  "skills": {
+    "deep-research": {
+      "source": "199-biotechnologies/claude-deep-research-skill",
+      "sourceType": "github",
+      "skillPath": "SKILL.md",
+      "computedHash": "685efecf2091dccf219506641671acc3c0c31ecb83f54b8473b9d399ba0337b8"
+    }
+  }
+}

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@clawos-dev/clawd",
-  "version": "0.2.47-beta.70.6ec7522",
+  "version": "0.2.47-beta.72.f1d7f9e",
   "description": "Standalone clawd daemon — Claude Code (and future Codex) session server over WebSocket",
   "type": "module",
   "license": "MIT",
@@ -16,7 +16,7 @@
     "README.md"
   ],
   "scripts": {
-    "build": "tsup",
+    "build": "tsup && node scripts/copy-defaults.mjs",
     "typecheck": "tsc -p tsconfig.json --noEmit",
     "dev": "tsx src/cli.ts",
     "dev:watch": "tsx watch --clear-screen=false src/cli.ts",