Step35
|
86eb1c9a50
|
feat: training data pipeline — knowledge entries → JSONL training pairs
Test / pytest (pull_request) Failing after 7s
Add scripts/knowledge_to_training_pairs.py which reads quality-gated
knowledge entries from knowledge/index.json and emits terse→rich
training pairs in JSONL format.
Features:
- Derives terse queries from facts via category-aware heuristics
- Configurable quality filters: min-confidence, model-filter, date range
- Output includes domain, source_confidence, source_model
- Smoke tests added in tests/test_knowledge_to_training_pairs.py
Deliverables for #199:
1. Pipeline script: scripts/knowledge_to_training_pairs.py
2. End-to-end: knowledge/index.json → training_pairs.jsonl (or custom JSONL)
3. Config: min-confidence, model-filter, after/before date filters
4. Test: 9 smoke tests covering conversion, filtering, and end-to-end run
Closes #199
|
2026-04-26 13:03:06 -04:00 |
|
|
|
345d2451d0
|
Merge pull request 'feat: knowledge deduplication — content hash + token similarity (#196)' (#228) from burn/196-1776306000 into main
Test / pytest (push) Failing after 33s
|
2026-04-21 15:28:50 +00:00 |
|
|
|
277f9e3a2b
|
Merge pull request 'feat: Knowledge freshness cron — detect stale entries from code changes (#200)' (#227) from feat/200-knowledge-freshness-cron into main
Test / pytest (push) Has been cancelled
|
2026-04-21 15:21:28 +00:00 |
|
|
|
cc215e3ed7
|
feat: knowledge deduplication — content hash + token similarity (#196)
Test / pytest (pull_request) Failing after 21s
Dedup module for knowledge entries with:
- SHA256 content hashing for exact duplicates
- Token Jaccard similarity for near-duplicates (default 0.95)
- Quality-based merge: keeps higher confidence/source_count
- Metadata merging: tags, related, source_count
- Dry-run mode
- 30 tests passing
- Built-in --test mode with generated duplicates
Usage:
python scripts/dedup.py --input knowledge/index.json
python scripts/dedup.py --input knowledge/index.json --dry-run
python scripts/dedup.py --test
Closes #196.
|
2026-04-21 07:58:09 -04:00 |
|
|
|
baa2c84c3f
|
feat: Add test_freshness.py (#200)
Test / pytest (pull_request) Failing after 26s
|
2026-04-21 11:57:54 +00:00 |
|
Alexander Whitestone
|
e1e42c3f8e
|
feat: quality gate — score and filter knowledge entries (#198)
Test / pytest (pull_request) Failing after 34s
quality_gate.py:
4-dimension scoring (0.0-1.0):
specificity (0.3): concrete examples vs vague
actionability (0.3): can this be used?
freshness (0.2): exponential decay over time
source_quality (0.2): model reliability score
filter_entries(entries, threshold=0.5)
quality_report() — distribution + pass rate
CLI: --threshold, --json, --filter
tests/test_quality_gate.py: 14 tests
specificity: specific high, vague low, empty baseline
actionability: actionable high, abstract low
freshness: recent high, old low, none baseline
source: claude high, ollama low, unknown default
entry: good high, poor low
filter: removes low quality
|
2026-04-20 20:31:04 -04:00 |
|
Alexander Whitestone
|
5e8a201a26
|
Merge remote-tracking branch 'origin/burn/172-1776263893'
|
2026-04-15 22:11:26 -04:00 |
|
Alexander Whitestone
|
c7b7b38510
|
Merge remote-tracking branch 'origin/burn/171-1776263896'
|
2026-04-15 22:11:23 -04:00 |
|
Alexander Whitestone
|
4bd0a5d7ac
|
test: define CI configuration acceptance for #190
|
2026-04-15 11:26:08 -04:00 |
|
|
|
b3592e14ad
|
test: add tests for Performance Bottleneck Finder
Refs #171
|
2026-04-15 14:48:59 +00:00 |
|
|
|
5eab5e4aac
|
test: knowledge gap identifier tests (#172)
|
2026-04-15 14:42:30 +00:00 |
|
