@clawos-dev/clawd 0.2.50 → 0.2.51-beta.78.2024c11

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

@@ -1,195 +0,0 @@
-#!/usr/bin/env python3
-"""Smoke tests for citation_manager.py CLI."""
-
-import json
-import os
-import subprocess
-import sys
-import tempfile
-import unittest
-
-SCRIPT = os.path.join(os.path.dirname(__file__), '..', 'scripts', 'citation_manager.py')
-
-
-def run_cm(*args: str) -> dict:
-    """Run citation_manager.py with args, return parsed JSON from stdout."""
-    result = subprocess.run(
-        [sys.executable, SCRIPT, *args],
-        capture_output=True, text=True,
-    )
-    if result.returncode != 0:
-        raise RuntimeError(f'Exit {result.returncode}: {result.stderr}')
-    return json.loads(result.stdout) if result.stdout.strip().startswith(('{', '[')) else result.stdout
-
-
-class TestInitRun(unittest.TestCase):
-    def test_creates_manifest_and_artifacts(self):
-        with tempfile.TemporaryDirectory() as d:
-            out = run_cm('init-run', '--out-dir', d, '--query', 'test question', '--mode', 'deep')
-            self.assertEqual(out['status'], 'ok')
-
-            # Manifest exists and has correct fields
-            manifest = json.load(open(os.path.join(d, 'run_manifest.json')))
-            self.assertEqual(manifest['version'], '3.0.0')
-            self.assertEqual(manifest['query'], 'test question')
-            self.assertEqual(manifest['mode'], 'deep')
-            self.assertIsNotNone(manifest['started_at'])
-            self.assertIsNone(manifest['finished_at'])
-            self.assertEqual(manifest['artifact_paths']['sources'], 'sources.jsonl')
-
-            # Empty JSONL files exist
-            for name in ('sources.jsonl', 'evidence.jsonl', 'claims.jsonl'):
-                path = os.path.join(d, name)
-                self.assertTrue(os.path.exists(path), f'{name} missing')
-                self.assertEqual(os.path.getsize(path), 0)
-
-
-class TestRegisterSource(unittest.TestCase):
-    def setUp(self):
-        self.tmpdir = tempfile.mkdtemp()
-        run_cm('init-run', '--out-dir', self.tmpdir, '--query', 'test')
-
-    def tearDown(self):
-        import shutil
-        shutil.rmtree(self.tmpdir, ignore_errors=True)
-
-    def test_register_and_dedup(self):
-        src = json.dumps({
-            'raw_url': 'https://arxiv.org/abs/2305.14251',
-            'title': 'FActScore',
-            'source_type': 'academic',
-            'year': '2023',
-        })
-        out1 = run_cm('register-source', '--json', src, '--dir', self.tmpdir)
-        self.assertEqual(out1['status'], 'registered')
-        self.assertEqual(len(out1['source_id']), 16)
-        self.assertTrue(out1['canonical_locator'].startswith('arxiv:'))
-
-        # Same URL -> duplicate
-        out2 = run_cm('register-source', '--json', src, '--dir', self.tmpdir)
-        self.assertEqual(out2['status'], 'duplicate')
-        self.assertEqual(out2['source_id'], out1['source_id'])
-
-    def test_doi_canonicalization(self):
-        src = json.dumps({
-            'raw_url': 'https://doi.org/10.1038/s41586-023-06745-9',
-            'title': 'Some Nature paper',
-        })
-        out = run_cm('register-source', '--json', src, '--dir', self.tmpdir)
-        self.assertTrue(out['canonical_locator'].startswith('doi:10.1038/'))
-
-    def test_url_normalization(self):
-        src1 = json.dumps({
-            'raw_url': 'https://Example.Com/article?utm_source=google&id=42',
-            'title': 'Test',
-        })
-        src2 = json.dumps({
-            'raw_url': 'https://example.com/article?id=42&utm_medium=email',
-            'title': 'Test duplicate',
-        })
-        out1 = run_cm('register-source', '--json', src1, '--dir', self.tmpdir)
-        out2 = run_cm('register-source', '--json', src2, '--dir', self.tmpdir)
-        # Both should resolve to same canonical locator -> same source_id
-        self.assertEqual(out1['source_id'], out2['source_id'])
-        self.assertEqual(out2['status'], 'duplicate')
-
-
-class TestAssignDisplayNumbers(unittest.TestCase):
-    def test_assigns_in_order(self):
-        with tempfile.TemporaryDirectory() as d:
-            run_cm('init-run', '--out-dir', d, '--query', 'test')
-
-            for i, url in enumerate(['https://a.com/1', 'https://b.com/2', 'https://c.com/3']):
-                run_cm('register-source', '--json', json.dumps({
-                    'raw_url': url, 'title': f'Source {i+1}',
-                }), '--dir', d)
-
-            mapping = run_cm('assign-display-numbers', '--dir', d)
-            self.assertEqual(len(mapping), 3)
-            # Values should be 1, 2, 3
-            self.assertEqual(sorted(mapping.values()), [1, 2, 3])
-
-
-class TestExportBibliography(unittest.TestCase):
-    def test_markdown_export(self):
-        with tempfile.TemporaryDirectory() as d:
-            run_cm('init-run', '--out-dir', d, '--query', 'test')
-            run_cm('register-source', '--json', json.dumps({
-                'raw_url': 'https://arxiv.org/abs/2305.14251',
-                'title': 'FActScore',
-                'authors': ['Min, S.', 'Krishna, K.'],
-                'year': '2023',
-                'source_type': 'academic',
-            }), '--dir', d)
-
-            out = run_cm('export-bibliography', '--dir', d, '--style', 'markdown')
-            self.assertIn('[1]', out)
-            self.assertIn('FActScore', out)
-            self.assertIn('Min, S. & Krishna, K.', out)
-
-    def test_json_export(self):
-        with tempfile.TemporaryDirectory() as d:
-            run_cm('init-run', '--out-dir', d, '--query', 'test')
-            run_cm('register-source', '--json', json.dumps({
-                'raw_url': 'https://example.com/paper',
-                'title': 'Test Paper',
-            }), '--dir', d)
-
-            out = run_cm('export-bibliography', '--dir', d, '--style', 'json')
-            self.assertEqual(len(out), 1)
-            self.assertEqual(out[0]['display_number'], 1)
-            self.assertEqual(out[0]['title'], 'Test Paper')
-
-
-class TestCanonicalization(unittest.TestCase):
-    """Unit tests for canonicalize_locator without running the CLI."""
-
-    @classmethod
-    def setUpClass(cls):
-        sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..', 'scripts'))
-        from citation_manager import canonicalize_locator, compute_source_id
-        cls.canonicalize = staticmethod(canonicalize_locator)
-        cls.compute_id = staticmethod(compute_source_id)
-
-    def test_doi_from_url(self):
-        canonicalize_locator = self.canonicalize
-        self.assertEqual(
-            canonicalize_locator('https://doi.org/10.1038/s41586-023-06745-9'),
-            'doi:10.1038/s41586-023-06745-9',
-        )
-        self.assertEqual(
-            canonicalize_locator('https://dx.doi.org/10.1234/test.'),
-            'doi:10.1234/test',
-        )
-
-    def test_arxiv_from_url(self):
-        canonicalize_locator = self.canonicalize
-        self.assertEqual(
-            canonicalize_locator('https://arxiv.org/abs/2305.14251v2'),
-            'arxiv:2305.14251v2',
-        )
-        self.assertEqual(
-            canonicalize_locator('arxiv:2401.15884'),
-            'arxiv:2401.15884',
-        )
-
-    def test_url_strips_tracking(self):
-        canonicalize_locator = self.canonicalize
-        result = canonicalize_locator('https://Example.Com/page?utm_source=x&key=val')
-        self.assertNotIn('utm_source', result)
-        self.assertIn('key=val', result)
-        self.assertTrue(result.startswith('https://example.com'))
-
-    def test_url_strips_fragment(self):
-        canonicalize_locator = self.canonicalize
-        result = canonicalize_locator('https://example.com/page#section')
-        self.assertNotIn('#section', result)
-
-    def test_url_strips_trailing_slash(self):
-        canonicalize_locator = self.canonicalize
-        result = canonicalize_locator('https://example.com/page/')
-        self.assertFalse(result.endswith('/'))
-
-
-if __name__ == '__main__':
-    unittest.main()

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

@@ -1,166 +0,0 @@
-#!/usr/bin/env python3
-"""Smoke tests for evidence_store.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', 'evidence_store.py')
-
-
-def run_es(*args: str) -> dict | list:
-    """Run evidence_store.py with args, return parsed JSON from stdout."""
-    result = subprocess.run(
-        [sys.executable, SCRIPT, *args],
-        capture_output=True, text=True,
-    )
-    if result.returncode != 0:
-        raise RuntimeError(f'Exit {result.returncode}: {result.stderr}')
-    return json.loads(result.stdout)
-
-
-class TestInit(unittest.TestCase):
-    def test_creates_empty_file(self):
-        with tempfile.TemporaryDirectory() as d:
-            out = run_es('init', '--dir', d)
-            self.assertEqual(out['status'], 'ok')
-            path = os.path.join(d, 'evidence.jsonl')
-            self.assertTrue(os.path.exists(path))
-            self.assertEqual(os.path.getsize(path), 0)
-
-
-class TestAddEvidence(unittest.TestCase):
-    def setUp(self):
-        self.tmpdir = tempfile.mkdtemp()
-        run_es('init', '--dir', self.tmpdir)
-
-    def tearDown(self):
-        shutil.rmtree(self.tmpdir, ignore_errors=True)
-
-    def test_add_and_dedup(self):
-        ev = json.dumps({
-            'source_id': 'abcdef0123456789',
-            'quote': 'FActScore decomposes generation into atomic facts.',
-            'evidence_type': 'direct_quote',
-            'locator': 'page 3',
-            'retrieval_query': 'factuality evaluation methods',
-        })
-        out1 = run_es('add', '--json', ev, '--dir', self.tmpdir)
-        self.assertEqual(out1['status'], 'added')
-        self.assertEqual(len(out1['evidence_id']), 16)
-
-        # Same quote -> duplicate
-        out2 = run_es('add', '--json', ev, '--dir', self.tmpdir)
-        self.assertEqual(out2['status'], 'duplicate')
-        self.assertEqual(out2['evidence_id'], out1['evidence_id'])
-
-    def test_whitespace_normalization(self):
-        ev1 = json.dumps({
-            'source_id': 'abcdef0123456789',
-            'quote': '  FActScore   decomposes   generation  into atomic facts.  ',
-            'evidence_type': 'direct_quote',
-        })
-        ev2 = json.dumps({
-            'source_id': 'abcdef0123456789',
-            'quote': 'FActScore decomposes generation into atomic facts.',
-            'evidence_type': 'direct_quote',
-        })
-        out1 = run_es('add', '--json', ev1, '--dir', self.tmpdir)
-        out2 = run_es('add', '--json', ev2, '--dir', self.tmpdir)
-        # Should be same ID due to normalization
-        self.assertEqual(out1['evidence_id'], out2['evidence_id'])
-        self.assertEqual(out2['status'], 'duplicate')
-
-    def test_different_sources_different_ids(self):
-        ev1 = json.dumps({
-            'source_id': 'aaaaaaaaaaaaaaaa',
-            'quote': 'Same quote text.',
-            'evidence_type': 'paraphrase',
-        })
-        ev2 = json.dumps({
-            'source_id': 'bbbbbbbbbbbbbbbb',
-            'quote': 'Same quote text.',
-            'evidence_type': 'paraphrase',
-        })
-        out1 = run_es('add', '--json', ev1, '--dir', self.tmpdir)
-        out2 = run_es('add', '--json', ev2, '--dir', self.tmpdir)
-        self.assertNotEqual(out1['evidence_id'], out2['evidence_id'])
-        self.assertEqual(out2['status'], 'added')
-
-
-class TestListAndExport(unittest.TestCase):
-    def setUp(self):
-        self.tmpdir = tempfile.mkdtemp()
-        run_es('init', '--dir', self.tmpdir)
-        # Add 3 evidence items from 2 sources
-        for src, quote in [
-            ('src_aaa', 'First quote from source A.'),
-            ('src_aaa', 'Second quote from source A.'),
-            ('src_bbb', 'Quote from source B.'),
-        ]:
-            run_es('add', '--json', json.dumps({
-                'source_id': src,
-                'quote': quote,
-                'evidence_type': 'direct_quote',
-            }), '--dir', self.tmpdir)
-
-    def tearDown(self):
-        shutil.rmtree(self.tmpdir, ignore_errors=True)
-
-    def test_list_all(self):
-        out = run_es('list', '--dir', self.tmpdir)
-        self.assertEqual(out['count'], 3)
-
-    def test_list_filtered(self):
-        out = run_es('list', '--dir', self.tmpdir, '--source-id', 'src_aaa')
-        self.assertEqual(out['count'], 2)
-
-        out = run_es('list', '--dir', self.tmpdir, '--source-id', 'src_bbb')
-        self.assertEqual(out['count'], 1)
-
-    def test_export(self):
-        out = run_es('export', '--dir', self.tmpdir)
-        self.assertIsInstance(out, list)
-        self.assertEqual(len(out), 3)
-        # Each has required fields
-        for row in out:
-            self.assertIn('evidence_id', row)
-            self.assertIn('source_id', row)
-            self.assertIn('quote', row)
-            self.assertIn('evidence_type', row)
-            self.assertIn('captured_at', row)
-
-
-class TestEvidenceID(unittest.TestCase):
-    """Unit tests for compute_evidence_id."""
-
-    @classmethod
-    def setUpClass(cls):
-        sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..', 'scripts'))
-        from evidence_store import compute_evidence_id, normalize_quote
-        cls.compute_id = staticmethod(compute_evidence_id)
-        cls.normalize = staticmethod(normalize_quote)
-
-    def test_deterministic(self):
-        id1 = self.compute_id('src_a', 'test quote', 'page 1')
-        id2 = self.compute_id('src_a', 'test quote', 'page 1')
-        self.assertEqual(id1, id2)
-
-    def test_locator_matters(self):
-        id1 = self.compute_id('src_a', 'test quote', 'page 1')
-        id2 = self.compute_id('src_a', 'test quote', 'page 2')
-        self.assertNotEqual(id1, id2)
-
-    def test_normalize_whitespace(self):
-        self.assertEqual(
-            self.normalize('  hello   world  '),
-            'hello world',
-        )
-
-
-if __name__ == '__main__':
-    unittest.main()

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

@@ -1,213 +0,0 @@
-#!/usr/bin/env python3
-"""Tests for extract_claims.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', 'extract_claims.py')
-FIXTURES = os.path.join(os.path.dirname(__file__), 'fixtures')
-
-
-def run_ec(*args: str) -> dict | list:
-    """Run extract_claims.py with args."""
-    result = subprocess.run(
-        [sys.executable, SCRIPT, *args],
-        capture_output=True, text=True,
-    )
-    if result.returncode != 0:
-        raise RuntimeError(f'Exit {result.returncode}: {result.stderr}')
-    return json.loads(result.stdout)
-
-
-SAMPLE_REPORT = """\
----
-title: Test Research Report
----
-
-## Executive Summary
-
-This report examines the impact of quantum computing on cryptography [1, 2]. The field has advanced significantly since 2020, with major breakthroughs in error correction.
-
-## Introduction
-
-Quantum computing represents a paradigm shift in computational capability. Researchers at Google demonstrated quantum supremacy in 2019 using a 53-qubit processor [3]. This milestone confirmed theoretical predictions made decades earlier.
-
-## Finding 1
-
-The Shor algorithm can factor large numbers exponentially faster than classical methods [4]. Current RSA-2048 encryption could be broken by a sufficiently large quantum computer. However, such machines are estimated to require millions of physical qubits [5, 6].
-
-## Finding 2
-
-Post-quantum cryptography standards should be adopted within the next 5 years. Organizations should consider hybrid classical-quantum approaches during the transition period. NIST has already standardized several lattice-based algorithms [7].
-
-## Synthesis
-
-Taken together, the evidence suggests that quantum computing poses a real but manageable threat to current cryptographic systems. The timeline for practical quantum attacks remains uncertain, but proactive migration reduces risk substantially.
-
-## Recommendations
-
-Organizations should begin evaluating post-quantum cryptography solutions immediately. Security teams should conduct a cryptographic inventory to identify vulnerable systems. Companies should consider implementing crypto-agility frameworks to enable rapid algorithm switching.
-
-## Bibliography
-
-[1] Smith et al. (2023). Quantum Computing Advances.
-[2] Johnson (2024). Cryptographic Implications.
-"""
-
-
-class TestExtract(unittest.TestCase):
-    def setUp(self):
-        self.tmpdir = tempfile.mkdtemp()
-        # Create empty claims.jsonl
-        open(os.path.join(self.tmpdir, 'claims.jsonl'), 'w').close()
-        # Write sample report
-        self.report_path = os.path.join(self.tmpdir, 'report.md')
-        with open(self.report_path, 'w') as f:
-            f.write(SAMPLE_REPORT)
-
-    def tearDown(self):
-        shutil.rmtree(self.tmpdir, ignore_errors=True)
-
-    def test_extract_finds_claims(self):
-        out = run_ec('extract', '--report', self.report_path, '--dir', self.tmpdir)
-        self.assertEqual(out['status'], 'ok')
-        self.assertGreater(out['claims_added'], 5)
-
-    def test_extract_idempotent(self):
-        out1 = run_ec('extract', '--report', self.report_path, '--dir', self.tmpdir)
-        out2 = run_ec('extract', '--report', self.report_path, '--dir', self.tmpdir)
-        self.assertEqual(out2['claims_added'], 0)
-        self.assertEqual(out2['claims_skipped'], out1['claims_added'])
-
-    def test_claim_types_assigned(self):
-        run_ec('extract', '--report', self.report_path, '--dir', self.tmpdir)
-        out = run_ec('stats', '--dir', self.tmpdir)
-        # Should have at least factual and recommendation types
-        self.assertIn('factual', out['by_type'])
-        self.assertIn('recommendation', out['by_type'])
-
-    def test_sections_detected(self):
-        run_ec('extract', '--report', self.report_path, '--dir', self.tmpdir)
-        out = run_ec('stats', '--dir', self.tmpdir)
-        self.assertIn('finding_1', out['by_section'])
-        self.assertIn('finding_2', out['by_section'])
-        self.assertIn('recommendations', out['by_section'])
-
-
-class TestAdd(unittest.TestCase):
-    def setUp(self):
-        self.tmpdir = tempfile.mkdtemp()
-        open(os.path.join(self.tmpdir, 'claims.jsonl'), 'w').close()
-
-    def tearDown(self):
-        shutil.rmtree(self.tmpdir, ignore_errors=True)
-
-    def test_add_and_dedup(self):
-        claim = json.dumps({
-            'section_id': 'finding_1',
-            'text': 'Quantum computers can break RSA encryption.',
-            'claim_type': 'factual',
-        })
-        out1 = run_ec('add', '--json', claim, '--dir', self.tmpdir)
-        self.assertEqual(out1['status'], 'added')
-        self.assertEqual(len(out1['claim_id']), 16)
-
-        out2 = run_ec('add', '--json', claim, '--dir', self.tmpdir)
-        self.assertEqual(out2['status'], 'duplicate')
-
-    def test_add_with_sources(self):
-        claim = json.dumps({
-            'section_id': 'finding_1',
-            'text': 'NIST standardized CRYSTALS-Kyber in 2024.',
-            'claim_type': 'factual',
-            'cited_source_ids': ['abcdef0123456789'],
-            'evidence_ids': ['1234567890abcdef'],
-        })
-        out = run_ec('add', '--json', claim, '--dir', self.tmpdir)
-        self.assertEqual(out['status'], 'added')
-
-
-class TestListAndStats(unittest.TestCase):
-    def setUp(self):
-        self.tmpdir = tempfile.mkdtemp()
-        open(os.path.join(self.tmpdir, 'claims.jsonl'), 'w').close()
-        # Add mixed claims
-        for sec, text, ctype in [
-            ('finding_1', 'The sky appears blue due to Rayleigh scattering.', 'factual'),
-            ('finding_1', 'Light wavelengths scatter differently in the atmosphere.', 'factual'),
-            ('synthesis', 'Overall, atmospheric optics explains most visual phenomena.', 'synthesis'),
-            ('recommendations', 'Researchers should investigate polarization effects further.', 'recommendation'),
-        ]:
-            run_ec('add', '--json', json.dumps({
-                'section_id': sec, 'text': text, 'claim_type': ctype,
-            }), '--dir', self.tmpdir)
-
-    def tearDown(self):
-        shutil.rmtree(self.tmpdir, ignore_errors=True)
-
-    def test_list_all(self):
-        out = run_ec('list', '--dir', self.tmpdir)
-        self.assertEqual(out['count'], 4)
-
-    def test_list_by_section(self):
-        out = run_ec('list', '--dir', self.tmpdir, '--section', 'finding_1')
-        self.assertEqual(out['count'], 2)
-
-    def test_list_by_type(self):
-        out = run_ec('list', '--dir', self.tmpdir, '--type', 'recommendation')
-        self.assertEqual(out['count'], 1)
-
-    def test_stats(self):
-        out = run_ec('stats', '--dir', self.tmpdir)
-        self.assertEqual(out['total'], 4)
-        self.assertEqual(out['by_type']['factual'], 2)
-        self.assertEqual(out['by_type']['synthesis'], 1)
-        self.assertEqual(out['by_type']['recommendation'], 1)
-
-
-class TestClaimID(unittest.TestCase):
-    """Unit tests for compute_claim_id."""
-
-    @classmethod
-    def setUpClass(cls):
-        sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..', 'scripts'))
-        from extract_claims import compute_claim_id, classify_claim
-        cls.compute_id = staticmethod(compute_claim_id)
-        cls.classify = staticmethod(classify_claim)
-
-    def test_deterministic(self):
-        id1 = self.compute_id('finding_1', 'Test claim.')
-        id2 = self.compute_id('finding_1', 'Test claim.')
-        self.assertEqual(id1, id2)
-
-    def test_section_matters(self):
-        id1 = self.compute_id('finding_1', 'Same text.')
-        id2 = self.compute_id('finding_2', 'Same text.')
-        self.assertNotEqual(id1, id2)
-
-    def test_classify_recommendation(self):
-        self.assertEqual(
-            self.classify('Organizations should adopt PQC immediately.', 'recommendations'),
-            'recommendation',
-        )
-
-    def test_classify_factual(self):
-        self.assertEqual(
-            self.classify('RSA-2048 uses 2048-bit keys.', 'finding_1'),
-            'factual',
-        )
-
-    def test_classify_synthesis(self):
-        self.assertEqual(
-            self.classify('Taken together, the results indicate a clear trend.', 'synthesis'),
-            'synthesis',
-        )
-
-
-if __name__ == '__main__':
-    unittest.main()