starintel-local-searchlisted

# StarIntel local search ## Goal Search canonical local DB records and Auto-Dig packets before research, document creation, linking, or remote ingest. Requires Python 3.11+, a current StarIntel Auto-Dig checkout, and `starintel-spec-version`. ## Input A query, identifier, dtype, dataset, predicate, source, or confidence requirement. ## Output Matching canonical documents with stable IDs and optional repository locations. ## Command Run from the Auto-Dig repository root: ```bash python3 scripts/starintel.py search '<terms>' \ --dtype <dtype> \ --dataset <dataset-fragment> \ --predicate <predicate-fragment> \ --source <source-fragment> \ --min-confidence 0.8 \ --with-location ``` Use only the filters needed for the question. Results are JSONL. `--with-location` adds path, line, and surface around each document. ## Workflow 1. Read the checkout's `AGENTS.md`, use `starintel-spec-version` to resolve the active release, and run `python3 scripts/schema-release.py check` before interpreting dtype/field semantics. A `v0.9.0` schema filename identifies the immutable base family, not necessarily the active release. 2. Start with exact entity names, StarIntel IDs, external identifiers, source URLs, or predicates. 3. Search without a confidence floor first so contrary or uncertain records remain visible. 4. Narrow with `--dtype`, `--dataset`, `--id`, `--predicate`, or `--source`. 5. Preserve result IDs and locations in downstream notes or document proposals. 6. F