kai/deep_research
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

v0.20.6 rebuild platform environments from templates

Browse Source
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
Download Patch File Download Diff File Expand all files Collapse all files
GEMINI.md
+5 -7
View File
@@ -5,14 +5,12 @@ This file has higher priority than `AGENTS.md` for Gemini CLI and Antigravity.
## Load The Right Layer
- Shared baseline: `AGENTS.md`
- Antigravity roles: `.agent/agents.md`
- Strong research rules: `.agent/rules/`
- Skills: `.agent/skills/`
- Workflows: `.agent/workflows/`
- Antigravity source templates: `platform_adapters/antigravity/agent/`
- Generated Antigravity workspace: `platform_envs/antigravity/.agent/`
For Antigravity native research, load `.agent/agents.md`, `.agent/rules/deep-research-antigravity.md`, `.agent/skills/antigravity-surface-adapter/SKILL.md`, `.agent/skills/method-selection/SKILL.md`, `.agent/skills/research-quality-gates/SKILL.md`, and `.agent/workflows/deep-research-native.md`.
For Antigravity native research, first rebuild the environment with `python scripts/update_platform_envs.py --platform antigravity`, then open `platform_envs/antigravity` in Antigravity. Inside that generated workspace, load `.agent/agents.md`, `.agent/rules/deep-research-antigravity.md`, `.agent/skills/antigravity-surface-adapter/SKILL.md`, `.agent/skills/method-selection/SKILL.md`, `.agent/skills/research-quality-gates/SKILL.md`, and `.agent/workflows/deep-research-native.md`.
Ignore `.codex/`, `.opencode/`, `.claude/`, `.gemini/`, and legacy `.agents/` during Antigravity native research unless the user explicitly asks about those platform adapters.
Do not open the full multi-platform repository in Antigravity for production research.
Use `/memory show` or `/memory refresh` in Gemini CLI when the loaded context may be stale.
@@ -29,7 +27,7 @@ Treat Gemini-family models as high risk for false certainty in research.
## Platform Boundary
Gemini CLI normally uses Python-core mode through `.gemini/commands/dr/*.toml` or `uv run python scripts/dr.py ...`.
Gemini CLI normally uses Python-core mode through the generated `platform_envs/gemini-cli/.gemini/commands/dr/*.toml` or `uv run python scripts/dr.py ...`.
Antigravity is different: use native mode and its model quota for research execution. Python scripts are auxiliary unless the user explicitly approves Python model-worker/API usage.