deep-research

# Deep Research Produce research whose claims can be traced to content actually read or repository artifacts actually observed. ## Quick Reference | Need | Action | |---|---| | Classify `web | codebase | hybrid` and `quick | standard | deep` | Run `plan` before retrieval | | Enforce cumulative query, extraction, and report-source ceilings | Reuse the session artifact created by `plan --output` | | Author findings JSON | Load `references/output-contract-template.md` | | Assess hallucination, confidence, or source quality | Load `references/hallucination-and-verification.md` | | Understand Web trust boundaries and safe egress | Load `references/web-evidence-and-egress.md` | | Apply programmer-specific query/evidence patterns | Load `references/research-patterns.md` | | Claim runtime behavior from tests | Load `references/test-receipt-schema.md` | ## Mandatory Gates Execute gates in strict order. Stop when a gate blocks later work. ``` 1) Scope → 2) Ambiguity → 3) Evidence → 4) Research Mode → 5) Hallucination Awareness → 6) Budget Control → 7) Content Extraction → 8) Execution Integrity ``` ### 1) Scope Classification Gate Select one research kind and one goal. - Research kind: `web | codebase | hybrid` - Category: comparison, trend, claim verification, technical deep-dive, codebase audit - Goal: Know, Compare, Verify, Recommend, or Audit Run the executable classifier: ```bash python3 scripts/deep_research.py plan \ --request "<user request>" \ --output /...