literature-searchlisted

# literature-search Goal: - Run the canonical literature search bridge for one evidence query and persist traceable evidence artifacts. Inputs: - active run directory - a `SearchRequestContract` payload or enough context to build one - optional existing `literature/queries/<query_id>/REQUEST.json` Outputs: - `literature/queries/<query_id>/REQUEST.json` - `literature/queries/<query_id>/PROVIDER_RECEIPTS.json` - `literature/queries/<query_id>/CANDIDATE_PAPERS.json` - `literature/queries/<query_id>/VERIFIED_PAPERS.json` - `literature/queries/<query_id>/EVIDENCE_BUNDLE.json` - `literature/queries/<query_id>/EVIDENCE_BUNDLE.md` - `literature/queries/<query_id>/SEARCH_TRACE.jsonl` - `literature/bundles/<bundle_id>.json` Context Loading: - Open `skills/shared-references/schema-index.md`. - Open `skills/shared-references/literature-search-contract.md`. - Read `packages/agent_contracts/literature.py` before building or editing a search request or evidence bundle. - Read `tools/literature_search_client.py` before invoking the bridge. Execution Contract: - Import and call `from tools import search_literature`. - When the host exposes the configured `co_scientist_search_bridge` MCP server, its tools are an allowed transport for the same canonical bridge. - If the MCP server is unavailable, fall back to the Python tools surface instead of performing informal web search. - Do not perform informal web search as a substitute for `tools.search_literature(...)`. - Do not invent paper