hypothesis-generate-literaturelisted

# hypothesis-generate-literature Goal: - Generate exactly one literature-grounded hypothesis candidate for the active round. Inputs: - `research_plan/RESEARCH_PLAN.json` - `state/STRATEGY_PLAN.json` - `literature/queries/<query_id>/EVIDENCE_BUNDLE.json` produced by `tools.search_literature(...)` - optional parent hypothesis and review artifacts when the round is part of an evolution continuation Outputs: - `hypotheses/<id>/HYPOTHESIS.json` - `hypotheses/<id>/HYPOTHESIS.md` - `hypotheses/<id>/ORIGIN.json` - `literature/queries/<query_id>/*` search bridge artifacts for the evidence query used by this generation 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 consuming any search bridge request or evidence bundle. - Read `research_plan/RESEARCH_PLAN.json`. - Treat `research_goal` as the task anchor. - Treat `preferences` as the quality axes that the hypothesis should optimize for. - Treat `constraints` as hard boundaries that the hypothesis and experiment design must satisfy. - Read `state/STRATEGY_PLAN.json` and confirm that the current round allows `literature_exploration_generation`. - If the round is parented, read the selected parent hypothesis and its latest review summary before generating a child. Improve the known weaknesses instead of paraphrasing the parent. Execution Prompt Contract: - System Intent: - You