v0.20.6 rebuild platform environments from templates

This commit is contained in:
Deep Research System
2026-05-07 21:00:21 +08:00
parent bb2c91754b
commit b3050260b2
93 changed files with 6027 additions and 89 deletions
+11 -13
View File
@@ -14,30 +14,28 @@ This repository is not an application codebase. Its code supports the research p
- Cross-tool baseline: `AGENTS.md`
- Gemini / Antigravity override: `GEMINI.md`
- Antigravity roles: `.agent/agents.md`
- Antigravity strong rules: `.agent/rules/`
- Antigravity reusable skills: `.agent/skills/`
- Antigravity workflows: `.agent/workflows/`
- Legacy/full-repo adapter files: `.agents/`, `.codex/`, `.opencode/`, `.claude/`, `.gemini/`
- Platform adapter source templates: `platform_adapters/`
- Rebuilt local platform environments: `platform_envs/` (ignored; generated)
- Implementation plan and changelog: `PLAN.md`
If instructions conflict, use the more specific layer. For Antigravity, `GEMINI.md` and `.agent/rules/` override this file.
If instructions conflict, use the more specific layer. For Antigravity, `GEMINI.md` and the generated `platform_envs/antigravity/.agent/rules/` override this file.
## Operating Modes
Python-core mode:
- Use `scripts/dr.py`, `scripts/runtime/**`, `configs/models.yaml`, and `.agent/skills`.
- Use `scripts/dr.py`, `scripts/runtime/**`, `configs/models.yaml`, and `platform_adapters/antigravity/agent/skills`.
- Platform agents should call the Python CLI rather than reimplement worker orchestration.
- Model routing is resolved by the Python runtime.
Antigravity native mode:
- Use `.agent/agents.md`, `.agent/rules/`, `.agent/skills/`, and `.agent/workflows/`.
- Use a rebuilt `platform_envs/antigravity` workspace.
- Inside that workspace, Antigravity loads `.agent/agents.md`, `.agent/rules/`, `.agent/skills/`, and `.agent/workflows/`.
- Antigravity uses its own model quota for research execution.
- Python scripts are auxiliary for scaffolding, local material processing, deterministic checks, citation/report rendering, and status.
- Do not run Python model-worker commands such as `dr.py run`, `research --execute-packets`, or `research --assemble-chapters` unless the user explicitly approves external API/ZenMux usage.
- Do not inspect or follow `.codex/`, `.opencode/`, `.claude/`, `.gemini/`, or legacy `.agents/` when operating in Antigravity native mode unless the user explicitly asks. Those directories are for other platforms and may contain incompatible prompts.
- Do not open the full multi-platform repository in Antigravity for production research. Rebuild and open `platform_envs/antigravity`.
## Core Commands
@@ -65,11 +63,11 @@ uv run python scripts/deploy_adapters.py antigravity --target /path/to/workspace
Do not default to McKinsey/MECE for every topic.
Choose the research method and tools based on the user's scenario. Use `.agent/skills/method-selection/SKILL.md` for Antigravity native work and `configs/research_methods.yaml` for Python-core mode.
Choose the research method and tools based on the user's scenario. Use `platform_adapters/antigravity/agent/skills/method-selection/SKILL.md` as source, or `.agent/skills/method-selection/SKILL.md` inside the generated Antigravity env.
## Source Quality
Detailed scoring belongs in `.agent/skills/source-quality/SKILL.md`.
Detailed scoring belongs in `platform_adapters/antigravity/agent/skills/source-quality/SKILL.md`.
Baseline tiers:
@@ -88,6 +86,6 @@ Baseline tiers:
## Change Management
- Treat `AGENTS.md`, `GEMINI.md`, `.agent/**`, `.agents/**`, and `PLAN.md` as production configuration.
- Keep root rules short. Move Antigravity roles to `.agent/agents.md`, constraints to `.agent/rules`, capabilities to `.agent/skills`, and phase sequencing to `.agent/workflows`.
- Treat `AGENTS.md`, `GEMINI.md`, `platform_adapters/**`, `scripts/update_platform_envs.py`, and `PLAN.md` as production configuration.
- Keep root rules short. Move platform-specific roles, constraints, skills, and workflows to `platform_adapters/<platform>/`, then rebuild `platform_envs/<platform>/`.
- When changing runtime rules or adapter behavior, update `PLAN.md` changelog.