hypothesis-generation-pipelinelisted

# hypothesis-generation-pipeline Goal: - Dispatch one enabled generation strategy for a given `ResearchPlan`. Inputs: - `ResearchPlan` - active `state/STRATEGY_PLAN.json` - one enabled generation `strategy` - optional resume context from `state/PIPELINE_STATE.json` Outputs: - `hypotheses/<id>/HYPOTHESIS.json` - `hypotheses/<id>/HYPOTHESIS.md` - `hypotheses/<id>/ORIGIN.json` - `literature/queries/<query_id>/*` when `hypothesis-generate-literature` is selected - `hypotheses/<id>/REVIEW/*.json` - updated `meta/INSIGHTS_FROM_REVIEWS.json` when the hypothesis is viable - updated proximity receipt/status artifacts, plus `state/PROXIMITY_GRAPH.json` when the embedding bridge succeeds - updated `tournaments/*.json` - updated `islands/ISLANDS.json` - updated `state/PIPELINE_STATE.json` Sub-skills: - `hypothesis-generate-literature` - `literature-search` - `hypothesis-generate-debate` - `hypothesis-generate-assumptions` - `hypothesis-review-pipeline` - `insights-from-reviews` - `hypothesis-proximity-update` - `hypothesis-ranking-pipeline` Context Loading: - Open `skills/shared-references/schema-index.md`. - Read `packages/agent_contracts/research_plan.py` before consuming `research_plan/RESEARCH_PLAN.json` as the canonical generation brief. - Read `packages/agent_contracts/strategy_plan.py` before consuming `state/STRATEGY_PLAN.json` as the active generation-stage routing input. - Read `packages/agent_contracts/hypothesis.py` before dispatching any atomic generation skill tha