alvis 08d08ad7b0 feat(clustering): LLM-enrichment before embedding (port from taskpile #129) ...

Ported from taskpile experiments/clustering_eval (prompt v1, qwen2.5:1.5b).
The experiment showed ARI 0.22→0.77 and AUROC 0.76→0.91 on synthetic tasks
when embedding LLM-expanded descriptions instead of raw titles.

- Expand each task title via LiteLLM tip-generator before embedding
- Prefix with "clustering: " (nomic-embed-text task instruction prefix)
- Cache expansions in-memory by content hash within a compute cycle
- Falls back to raw title if enrichment fails; no change to fallback behaviour

Fixes #129

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

2026-05-12 14:20:48 +00:00

..

__init__.py

feat(ml): multi-agent context framework + v4 orchestrator prompt

2026-05-04 10:20:05 +00:00

test_agents.py

feat(integrations): add Google Health (Fit) integration with full permissions

2026-05-11 11:12:11 +00:00

test_clustering.py

feat(clustering): LLM-enrichment before embedding (port from taskpile #129)

2026-05-12 14:20:48 +00:00

test_inference.py

feat(agents): quiet window + peak hours + tz prefs for time-of-day agent (#112)

2026-05-06 06:05:51 +00:00

test_manifest.py

feat(agents): manifest plumbing + GET /agents/registry (ADR-0014 step 3)

2026-05-05 10:55:54 +00:00

test_per_agent_inference.py

feat(agents): semantic task clustering + focus-area inferred preferred_areas (#97, #113)

2026-05-06 06:54:46 +00:00