File size: 13,763 Bytes
420bcec
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
"""Tests for app.py functionality - Upload Meeting and Create Project."""
import pytest
import os
from pathlib import Path
import tempfile
import shutil

# Import app functions
import sys
sys.path.insert(0, str(Path(__file__).parent.parent))

from src.rag import ProjectRAG
from src.parsers import MeetingParser


# Sample raw meeting notes for testing
SAMPLE_RAW_NOTES_QUANTUM = """
We had a sync meeting about the quantum error correction project.
Dr. Chen presented the new surface code implementation results.
The decoder is showing 15ms latency which is too slow for real-time correction.

Sarah mentioned we got access to IBM's 127-qubit Eagle processor next month.
Marcus is still blocked on the FPGA development - waiting for the new boards.

We decided to switch from Union-Find to MWPM decoder for better accuracy.
Also agreed to target 1ms latency for the final system.

Tasks:
- Dr. Chen will optimize the decoder by end of week
- Sarah needs to prepare the calibration scripts for IBM hardware
- Marcus to follow up with vendor about FPGA delivery
"""

SAMPLE_RAW_NOTES_NEW_PROJECT = """
Kickoff meeting for the new recommendation engine project.
Team: Alice, Bob, Carol, David

Discussed architecture options - decided on collaborative filtering approach.
Bob raised concern about cold start problem for new users.

Alice will research embedding models this week.
Carol to set up the data pipeline by Friday.
David blocked on getting production database access.

Next meeting scheduled for Monday.
"""


class TestMeetingParser:
    """Test meeting parsing functionality."""

    def test_parse_action_items_from_raw_notes(self):
        """Test that action items can be extracted from structured notes."""
        # Create a structured meeting file
        structured_content = """# Meeting: Test Meeting
Date: 2025-01-30
Participants: Alice, Bob

## Discussion
Test discussion.

## Action Items
- [ ] Alice: Complete task by 2025-02-05
- [ ] Bob: Review code
- [x] Carol: Setup done (completed)

## Blockers
- Waiting for API access
"""
        with tempfile.NamedTemporaryFile(mode='w', suffix='.md', delete=False) as f:
            f.write(structured_content)
            temp_path = Path(f.name)

        try:
            meeting = MeetingParser.parse(temp_path, "test_project")
            assert meeting is not None
            assert len(meeting.action_items) == 3

            # Check open items
            open_items = [a for a in meeting.action_items if not a.completed]
            assert len(open_items) == 2

            # Check assignees
            assignees = [a.assignee for a in meeting.action_items if a.assignee]
            assert "Alice" in assignees
            assert "Bob" in assignees
        finally:
            os.unlink(temp_path)

    def test_parse_blockers(self):
        """Test blocker extraction."""
        structured_content = """# Meeting: Blocker Test
Date: 2025-01-30
Participants: Team

## Discussion
Discussed blockers.

## Blockers
- Waiting for hardware delivery
- Need security clearance for data access
- Vendor has not responded to queries
"""
        with tempfile.NamedTemporaryFile(mode='w', suffix='.md', delete=False) as f:
            f.write(structured_content)
            temp_path = Path(f.name)

        try:
            meeting = MeetingParser.parse(temp_path, "test_project")
            assert meeting is not None
            assert len(meeting.blockers) == 3
            # blockers is a List[str], not objects
            assert any("hardware" in b.lower() for b in meeting.blockers)
        finally:
            os.unlink(temp_path)


class TestProjectCreation:
    """Test creating new projects."""

    def test_create_new_project_directory(self):
        """Test that new project directories are created correctly."""
        with tempfile.TemporaryDirectory() as temp_dir:
            project_name = "test_new_project"
            project_dir = Path(temp_dir) / project_name / "meetings"

            # Simulate what app.py does
            project_dir.mkdir(parents=True, exist_ok=True)

            assert project_dir.exists()
            assert project_dir.is_dir()
            assert (Path(temp_dir) / project_name).exists()

    def test_save_meeting_to_new_project(self):
        """Test saving a meeting file to a new project."""
        with tempfile.TemporaryDirectory() as temp_dir:
            project_name = "recommendation_engine"
            meeting_date = "2025-01-30"
            meeting_title = "kickoff"

            project_dir = Path(temp_dir) / project_name / "meetings"
            project_dir.mkdir(parents=True, exist_ok=True)

            filename = f"{meeting_date}-{meeting_title}.md"
            file_path = project_dir / filename

            content = """# Meeting: Kickoff
Date: 2025-01-30
Participants: Alice, Bob

## Discussion
Initial project discussion.

## Action Items
- [ ] Alice: Research models by 2025-02-05

## Blockers
- Need database access
"""
            with open(file_path, 'w') as f:
                f.write(content)

            assert file_path.exists()

            # Verify RAG can load it
            rag = ProjectRAG(Path(temp_dir))
            rag.load_and_index()

            projects = rag.get_all_projects()
            assert project_name in projects

            # Verify action items are indexed
            action_items = rag.get_open_action_items(project=project_name)
            assert len(action_items) >= 1

    def test_create_project_with_special_characters(self):
        """Test project creation handles names properly."""
        with tempfile.TemporaryDirectory() as temp_dir:
            # Test with underscores and numbers
            project_name = "project_v2_2025"
            project_dir = Path(temp_dir) / project_name / "meetings"
            project_dir.mkdir(parents=True, exist_ok=True)

            assert project_dir.exists()


class TestUploadMeeting:
    """Test the upload meeting functionality."""

    def test_meeting_file_naming(self):
        """Test that meeting files are named correctly."""
        meeting_date = "2025-01-30"
        meeting_title = "Sprint Planning"

        # Simulate the naming logic from app.py
        filename = f"{meeting_date}-{meeting_title.lower().replace(' ', '-')}.md"

        assert filename == "2025-01-30-sprint-planning.md"

    def test_meeting_file_naming_no_title(self):
        """Test meeting file naming when no title provided."""
        meeting_date = "2025-01-30"
        meeting_title = None

        filename = f"{meeting_date}-{meeting_title.lower().replace(' ', '-') if meeting_title else 'meeting'}.md"

        assert filename == "2025-01-30-meeting.md"

    def test_quantum_project_upload(self):
        """Test uploading a meeting to quantum_computing project."""
        with tempfile.TemporaryDirectory() as temp_dir:
            # Create existing quantum_computing project
            quantum_dir = Path(temp_dir) / "quantum_computing" / "meetings"
            quantum_dir.mkdir(parents=True)

            # Add an existing meeting
            existing_meeting = """# Meeting: Previous Sync
Date: 2025-01-25
Participants: Dr. Chen, Sarah

## Discussion
Previous work discussion.
"""
            (quantum_dir / "2025-01-25-previous-sync.md").write_text(existing_meeting)

            # Now simulate uploading a new meeting
            new_meeting_content = """# Meeting: Decoder Optimization Review
Date: 2025-01-30
Participants: Dr. Chen, Sarah, Marcus

## Discussion
Reviewed decoder performance. Current latency is 15ms, target is 1ms.
Discussed MWPM vs Union-Find approaches.

## Decisions
- Switch to MWPM decoder for better accuracy
- Target 1ms latency for production

## Action Items
- [ ] Dr. Chen: Implement MWPM decoder by 2025-02-07
- [ ] Sarah: Benchmark on IBM simulator by 2025-02-10
- [ ] Marcus: Order additional FPGA boards

## Blockers
- FPGA delivery delayed by 2 weeks
- Need IBM quantum credits approval
"""
            new_file = quantum_dir / "2025-01-30-decoder-optimization-review.md"
            new_file.write_text(new_meeting_content)

            # Verify both meetings exist
            meetings = list(quantum_dir.glob("*.md"))
            assert len(meetings) == 2

            # Verify RAG indexes both
            rag = ProjectRAG(Path(temp_dir))
            rag.load_and_index()

            assert "quantum_computing" in rag.get_all_projects()
            assert len(rag.meetings) == 2

            # Verify action items
            action_items = rag.get_open_action_items(project="quantum_computing")
            assert len(action_items) >= 3

            # Verify blockers
            blockers = rag.get_blockers(project="quantum_computing")
            assert len(blockers) >= 2


class TestRAGWithMultipleProjects:
    """Test RAG functionality with multiple projects."""

    def test_multiple_projects_isolation(self):
        """Test that queries can be isolated to specific projects."""
        with tempfile.TemporaryDirectory() as temp_dir:
            # Create two projects
            project1_dir = Path(temp_dir) / "quantum_computing" / "meetings"
            project2_dir = Path(temp_dir) / "covid_prediction" / "meetings"
            project1_dir.mkdir(parents=True)
            project2_dir.mkdir(parents=True)

            # Add meeting to project 1
            (project1_dir / "2025-01-30-quantum.md").write_text("""# Meeting: Quantum Sync
Date: 2025-01-30
Participants: Dr. Chen

## Action Items
- [ ] Dr. Chen: Optimize decoder

## Blockers
- FPGA delivery delayed
""")

            # Add meeting to project 2
            (project2_dir / "2025-01-30-covid.md").write_text("""# Meeting: COVID Analysis
Date: 2025-01-30
Participants: Dr. Foster

## Action Items
- [ ] Dr. Foster: Review model accuracy

## Blockers
- Data quality issues with GISAID
""")

            rag = ProjectRAG(Path(temp_dir))
            rag.load_and_index()

            # Test project filtering
            quantum_items = rag.get_open_action_items(project="quantum_computing")
            covid_items = rag.get_open_action_items(project="covid_prediction")

            assert any("decoder" in item['task'].lower() for item in quantum_items)
            assert any("model" in item['task'].lower() for item in covid_items)

            # Test blocker filtering
            quantum_blockers = rag.get_blockers(project="quantum_computing")
            covid_blockers = rag.get_blockers(project="covid_prediction")

            assert any("fpga" in b['blocker'].lower() for b in quantum_blockers)
            assert any("gisaid" in b['blocker'].lower() for b in covid_blockers)

    def test_all_projects_query(self):
        """Test querying across all projects."""
        with tempfile.TemporaryDirectory() as temp_dir:
            # Create two projects with meetings
            for project in ["project_a", "project_b"]:
                project_dir = Path(temp_dir) / project / "meetings"
                project_dir.mkdir(parents=True)
                (project_dir / "2025-01-30-meeting.md").write_text(f"""# Meeting: {project} Sync
Date: 2025-01-30
Participants: Team

## Action Items
- [ ] Someone: Task for {project}
""")

            rag = ProjectRAG(Path(temp_dir))
            rag.load_and_index()

            # Get all action items without filter
            all_items = rag.get_open_action_items()
            assert len(all_items) >= 2


class TestIntegrationUploadMeeting:
    """Integration tests for upload meeting with LLM (requires tokens)."""

    def test_structure_meeting_hf(self):
        """Test meeting structuring with HuggingFace."""
        hf_token = os.getenv("HF_TOKEN")
        if not hf_token:
            pytest.skip("HF_TOKEN not set")

        from langchain_huggingface import ChatHuggingFace, HuggingFaceEndpoint
        from langchain_core.messages import SystemMessage, HumanMessage

        endpoint = HuggingFaceEndpoint(
            repo_id="meta-llama/Llama-3.2-3B-Instruct",
            temperature=0.3,
            max_new_tokens=1024,
            huggingfacehub_api_token=hf_token,
            timeout=60
        )
        llm = ChatHuggingFace(llm=endpoint)

        system_prompt = """Structure these meeting notes into markdown with sections:
# Meeting: [title], Date:, Participants:, ## Discussion, ## Action Items, ## Blockers"""

        messages = [
            SystemMessage(content=system_prompt),
            HumanMessage(content=f"Raw notes: {SAMPLE_RAW_NOTES_QUANTUM}")
        ]

        response = llm.invoke(messages)
        assert response.content is not None
        assert len(response.content) > 100
        # Should have some structure
        assert "action" in response.content.lower() or "task" in response.content.lower()

    def test_structure_meeting_google(self):
        """Test meeting structuring with Google."""
        api_key = os.getenv("GOOGLE_API_KEY")
        if not api_key:
            pytest.skip("GOOGLE_API_KEY not set")

        from langchain_google_genai import ChatGoogleGenerativeAI
        from langchain_core.messages import SystemMessage, HumanMessage

        llm = ChatGoogleGenerativeAI(
            model="gemini-2.0-flash",
            temperature=0.3,
            google_api_key=api_key,
            timeout=60
        )

        system_prompt = """Structure these meeting notes into markdown with sections:
# Meeting: [title], Date:, Participants:, ## Discussion, ## Action Items, ## Blockers"""

        messages = [
            SystemMessage(content=system_prompt),
            HumanMessage(content=f"Raw notes: {SAMPLE_RAW_NOTES_NEW_PROJECT}")
        ]

        response = llm.invoke(messages)
        assert response.content is not None
        assert len(response.content) > 100