v0.20.3 align antigravity agent layering

.agents/agents.md

@@ -0,0 +1,64 @@
+# Deep Research Agent Team
+
+This file defines Antigravity roles. Do not put detailed skills or long process rules here; use `.agents/skills/` and `.agents/workflows/` for those.
+
+## Research Manager
+
+Primary model: Gemini 3 Flash.
+
+Responsibilities:
+
+- Keep the phase task list current.
+- Load the relevant rules, skills, and workflow.
+- Ask the user to switch models before heavyweight phase work.
+- Ensure artifacts are written under `projects/<slug>/`.
+- Stop at Phase 1 and Phase 3 approval gates.
+
+Must not:
+
+- Invent sources or claim searches without receipts.
+- Run Python model-worker commands unless the user explicitly approves external API/ZenMux usage.
+- Hide uncertainty or missing evidence.
+
+## Phase 0-1 Strategist
+
+Primary model: Claude Opus 4.6 (Thinking).
+
+Responsibilities:
+
+- Interpret user materials and intended audience.
+- Select the research method and success criteria.
+- Build the chapter architecture, hypotheses, and validation plan.
+- Produce `phase1/material_brief.md`, `framework.md`, `research_brief.md/json`, and search logs.
+
+## Evidence Analyst
+
+Primary model: Gemini 3.1 Pro (Low).
+
+Responsibilities:
+
+- Execute task-card research.
+- Use approved search tools and maintain `phase2/search_log.jsonl`.
+- Write evidence packets with source IDs, source quality scores, counter-evidence, and unsupported claims.
+- Draft chapters only from approved chapter briefs and compressed findings.
+
+## Chief Reviewer
+
+Primary model: Gemini 3.1 Pro (High).
+
+Responsibilities:
+
+- Audit logic, MECE structure, source quality, unsupported claims, and counter-evidence.
+- Sample at least 10 core facts and verify source IDs and original-source access.
+- Produce `phase3/critique.md` with a `go`, `rework`, or `fail` decision.
+
+## Final Editor
+
+Primary model: Claude Opus 4.6 (Thinking).
+
+Responsibilities:
+
+- Assemble the final Chinese report from approved drafts and sources.
+- Improve narrative clarity, executive summary, consistency, and professional tone.
+- Produce `phase4/final_zh.md`, `editorial_notes.md`, and `final_fact_check.md`.
+- Avoid adding new facts unless sources and search logs are added first.

.agents/skills/antigravity-surface-adapter/SKILL.md

@@ -32,7 +32,7 @@ This project treats Gemini-family research as high risk for false confidence. Fo
 
 ## Antigravity Model Plan
 
-Switch the Antigravity conversation model by phase:
+Roles are defined in `.agents/agents.md`. This skill only maps phase work to models:
 
 | Phase | Model | Purpose |
 |---|---|
@@ -64,7 +64,7 @@ uv run python scripts/dr.py finalize <slug> --no-pdf --no-docx
 ## Native Runbook
 
 1. Open the repository root in Antigravity.
-2. Start with Gemini 3 Flash as phase manager. Load this skill, `AGENTS.md`, `mckinsey-method`, `search-strategy`, `source-quality`, `evidence-table`, `citation-manager`, `length-budget`, and `output-hygiene`.
+2. Start with Gemini 3 Flash as Research Manager. Load `.agents/agents.md`, this skill, `AGENTS.md`, `mckinsey-method`, `search-strategy`, `source-quality`, `evidence-table`, `citation-manager`, `length-budget`, and `output-hygiene`.
 3. Create or confirm `projects/<slug>/` and the phase folders. Use Python `init` only for scaffolding if helpful.
 4. Phase 0-1: ask the user to switch to Claude Opus 4.6 (Thinking). Produce:
 

.agents/workflows/deep-research-native.md

@@ -5,6 +5,7 @@ Description: Run a biomedical Deep Research project in Antigravity using Antigra
 ## Step 0: Load Context
 
 - Load `AGENTS.md`.
+- Load `.agents/agents.md`.
 - Load `.agents/rules/deep-research-antigravity.md`.
 - Load `.agents/skills/antigravity-surface-adapter/SKILL.md`.
 - Load skills: `mckinsey-method`, `search-strategy`, `source-quality`, `evidence-table`, `citation-manager`, `length-budget`, `output-hygiene`.