hypothesis-full-reviewlisted

# hypothesis-full-review Goal: - Run the full literature-grounded review for a hypothesis. Inputs: - `research_plan/RESEARCH_PLAN.json` - `hypotheses/<id>/HYPOTHESIS.json` - `literature/queries/<query_id>/EVIDENCE_BUNDLE.json` produced by `tools.search_literature(...)` - optional run-level review guidance from `meta/INSIGHTS_FROM_REVIEWS.json` Outputs: - `hypotheses/<id>/REVIEW/FULL_REVIEW.json` - `literature/queries/<query_id>/*` search bridge artifacts when a new evidence query is required Context Loading: - Open `skills/shared-references/schema-index.md`. - Open `skills/shared-references/literature-search-contract.md`. - Open `skills/shared-references/codex-reviewer-routing.md` before using any optional Codex reviewer subagent route. - Read `packages/agent_contracts/literature.py` before building or consuming search bridge artifacts. - Read `research_plan/RESEARCH_PLAN.json`. - Use `research_goal` as the review anchor. - Use `preferences` as the detailed quality criteria. - Use `constraints` as non-negotiable boundaries. - Read `hypotheses/<id>/HYPOTHESIS.json`. - If meta-review guidance exists, use it to calibrate recurring failure patterns without replacing local evidence. Execution Prompt Contract: - System Intent: - You are performing a thorough literature-grounded review of one hypothesis. - Required Reasoning Focus: - Use `tools.search_literature(run_dir, request)` to gather the minimum external evidence needed to evaluate the hypothesis claims unless a