corpus-mill/.gitignore at main · cahlen/corpus-mill · GitHub

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
# Python
__pycache__/
*.pyc
*.pyo
*.egg-info/
.python-version
.venv/
build/
dist/

# Test artifacts
.pytest_cache/
tests/fixtures/sample-*.mp4
tests/fixtures/sample-*.wav

# Node (in case any frontend tooling lands later)
node_modules/

# Environment / secrets
.env
.env.*
!.env.example
*.cookies.txt
*.cookies.txt.lastgood
~/.local/state/corpus-mill-*

# Cold-archive of per-stream artifacts. Lives outside the repo at
# $CORPUS_MILL_STREAMS_DIR. Pipeline reads via cfg.streams_dir.
streams/

# Per-stream and corpus runtime state
global/global.db
global/global.db-shm
global/global.db-wal
global/voiceprints/
global/jobs/
global/locks/
global/state/
global/cache/
global/forensics/
global/uploads/
global/watchers/

# Per-user channel watchlist — not source. Track watch_channels.example.json
# as the template; users copy it to watch_channels.json and edit privately.
global/watch_channels.json

# Catalogued runtime data — generated by the pipeline, not source
global/profiles/
global/briefs/
global/training_corpus/
global/market_context.md

# Logs
*.log

# Editor / agent state
.claude/
.codex
.qwen/
.idea/
.vscode/

# Coverage
.coverage
htmlcov/
.playwright-mcp/