Skip to content

docs: clarify Antigravity hook support#126

Open
ebbsanchez wants to merge 2 commits into
griddynamics:mainfrom
ebbsanchez:codex/clarify-antigravity-hook-support
Open

docs: clarify Antigravity hook support#126
ebbsanchez wants to merge 2 commits into
griddynamics:mainfrom
ebbsanchez:codex/clarify-antigravity-hook-support

Conversation

@ebbsanchez

Copy link
Copy Markdown

Summary

  • Clarify that Antigravity/OpenCode are covered by the MCP integration path in the architecture diagram.
  • Add an explicit note that native hook support is IDE-specific and needs separate validation.
  • Update docs/CONTEXT.md so Antigravity hooks are not implied to be supported while src/hooks/tests/MANUAL-TEST-CASES.md still says they are not tested/supported.

Fixes #94.

Validation

  • git diff --check
  • rg -n "Antigravity|native hooks|Native hook support|hooks are not supported" docs/ARCHITECTURE.md docs/CONTEXT.md src/hooks/tests/MANUAL-TEST-CASES.md

Signed-off-by: clancy <imclancypro@gmail.com>
@isolomatov-gd

Copy link
Copy Markdown
Contributor

/rosetta Review and triage

@github-actions github-actions Bot added the documentation Improvements or additions to documentation label Jul 6, 2026
@github-actions

github-actions Bot commented Jul 6, 2026

Copy link
Copy Markdown
Contributor

Rosetta Triage Review

Summary: This PR clarifies that Antigravity and OpenCode integrate with Rosetta via MCP only, and that native hook support is IDE-specific and unverified for Antigravity — addressing an inconsistency between docs/CONTEXT.md, docs/ARCHITECTURE.md, and src/hooks/tests/MANUAL-TEST-CASES.md.

Findings:

  • Scope: Focused and minimal — 2 doc files, +3/-2 lines, single concern. Good.
  • Consistency: The changes correctly align CONTEXT.md and ARCHITECTURE.md with the existing honest statement in MANUAL-TEST-CASES.md that Antigravity hooks are not tested/supported. No code changes required.
  • Diagram note (docs/ARCHITECTURE.md): The added line (MCP integration; native hooks vary by IDE) inside the ASCII art box is accurate and visible. Verify the box alignment is preserved (exact character count for the fixed-width box).
  • CONTEXT.md wording: "Antigravity hooks remain unverified and should not be treated as supported until validated" is accurate but slightly verbose. Functional — no blocking issue.
  • PR description: Clear. Explains what, why, and how to validate. References hooks: Antigravity support status contradicts docs — ARCHITECTURE.md vs MANUAL-TEST-CASES.md #94. Validation commands are practical.
  • Test coverage: N/A — documentation-only change.
  • Breaking changes: None.

Suggestions (non-blocking):

  • Consider trimming docs/CONTEXT.md wording to "Antigravity hooks are not yet validated" for conciseness — the current sentence is functionally correct but a bit long for a bullet point.
  • If src/hooks/tests/MANUAL-TEST-CASES.md has any wording that could be misread as implied support for Antigravity, it may be worth a one-liner fix in the same PR for completeness.

Labels added: documentation

Automated triage by Rosetta agent

@isolomatov-gd

Copy link
Copy Markdown
Contributor

I have a follow-up patch for this PR but can't push to the fork. This tightens the MCP vs native-hooks wording and updates the mirrored web docs so the public site stays aligned.

Why:

  • keep the "works through MCP" claim explicit
  • state that native hooks are IDE-specific and require validation
  • clarify that Antigravity and OpenCode hooks are not currently supported/tested
  • update the mirrored docs under docs/web/docs/* so the public site does not drift

Patch:

diff --git a/OVERVIEW.md b/OVERVIEW.md
index 4496bdb3..a4dcbb97 100644
--- a/OVERVIEW.md
+++ b/OVERVIEW.md
@@ -17,7 +17,7 @@ Rosetta is a **meta-prompting, context engineering, and centralized instructions
 
 Design principles:
 
-**Agent-agnostic.** Works across Cursor, Claude Code, VS Code, Windsurf, JetBrains (Copilot, Junie), GitHub Copilot, Codex, Antigravity, OpenCode, and any MCP-compatible IDE. Adopts agent-specific features where available, simulates them where not.
+**Agent-agnostic.** Works through MCP across Cursor, Claude Code, VS Code, Windsurf, JetBrains (Copilot, Junie), GitHub Copilot, Codex, Antigravity, OpenCode, and any MCP-compatible IDE. Adopts agent-specific features where available; native hooks remain IDE-specific and require per-IDE validation.
 
 **Progressive disclosure.** Instructions load in stages (bootstrap, classification, workflow-specific, sub-instructions) to [prevent context overflow](docs/ARCHITECTURE.md#context-overflow-prevention). The agent gets only what it needs for the current task.
 
diff --git a/docs/CONTEXT.md b/docs/CONTEXT.md
index 62c79a58..43e9aa08 100644
--- a/docs/CONTEXT.md
+++ b/docs/CONTEXT.md
@@ -104,7 +104,7 @@ Not reactive like gateways. Not static like prompt libraries. Verified, project-
 ## Domain and Operating Context
 
 - Rosetta operates across the full Software Development Lifecycle: planning, requirements, implementation, QA, release, and operations
-- Agent-agnostic: works through MCP with Cursor, Claude Code, VS Code, Windsurf, JetBrains (Copilot, Junie), GitHub Copilot, Codex, Antigravity, OpenCode, and any MCP-compatible IDE. Native hook support is IDE-specific; Antigravity hooks remain unverified and should not be treated as supported until validated.
+- Agent-agnostic: works through MCP with Cursor, Claude Code, VS Code, Windsurf, JetBrains (Copilot, Junie), GitHub Copilot, Codex, Antigravity, OpenCode, and any MCP-compatible IDE. Native hook support is IDE-specific; Antigravity and OpenCode hooks are not currently supported or tested.
 - Integrates via [Model Context Protocol (MCP)](ARCHITECTURE.md#rosetta-mcp), the standard transport for AI agent instructions
 - Security model: Rosetta is designed to only serve knowledge and instructions to agents — it does not see or process source code. No code leaves the organization's perimeter by design. Rosetta itself does not store any project data. Opt-in features (project datasets, plan_manager, submit_feedback, usage analytics) can be enabled in your deployment for cross-project intelligence, execution tracking, and adoption visibility; when enabled, your infrastructure stores the data and you are responsible for it. plan_manager receives execution plans created by AI, which may contain project-specific information. Usage analytics (PostHog) collects basic operational metadata — IP address, user email, coding agent with version, tool called, and tool parameters — when you deploy and configure a PostHog instance on your infrastructure.
 - Grounded in production experience, not theory. Active feedback loop from real projects.
diff --git a/docs/web/docs/architecture.md b/docs/web/docs/architecture.md
index 253af7e5..c739abd3 100644
--- a/docs/web/docs/architecture.md
+++ b/docs/web/docs/architecture.md
@@ -33,6 +33,7 @@ The instructions repo defines *how agents should behave*. The target repo is *wh
 │              Target Repository + IDE                    │
 │  Cursor · Claude Code · VS Code · JetBrains · Codex     │
 │  Windsurf · Antigravity · OpenCode                      │
+│  (MCP integration; native hooks vary by IDE)            │
 │                         │                               │
 │                    MCP Protocol                         │
 │             (Streamable HTTP + OAuth)                   │
@@ -167,7 +168,7 @@ Command aliases are used exclusively for Rosetta MCP resources (instructions, kn
 
 Instructions never call MCP tools directly. Rosetta defines command aliases that work across all IDEs and coding agents. This serves three purposes:
 
-- **Portability.** Same instructions work in Cursor, Claude Code, VS Code, JetBrains, Codex, and any MCP-compatible tool.
+- **Portability.** Same instructions work in Cursor, Claude Code, VS Code, JetBrains, Codex, and any MCP-compatible tool. Native hook support is IDE-specific and must be validated separately.
 - **Decoupling.** Instruction content is independent of MCP API changes.
 - **Authoring.** Workflows, skills, and rules reference each other through aliases, not tool calls.
 
diff --git a/docs/web/docs/context.md b/docs/web/docs/context.md
index eaacdd07..9b72f9b4 100644
--- a/docs/web/docs/context.md
+++ b/docs/web/docs/context.md
@@ -112,7 +112,7 @@ Not reactive like gateways. Not static like prompt libraries. Verified, project-
 ## Domain and Operating Context
 
 - Rosetta operates across the full Software Development Lifecycle: planning, requirements, implementation, QA, release, and operations
-- Agent-agnostic: works with Cursor, Claude Code, VS Code, Windsurf, JetBrains (Copilot, Junie), GitHub Copilot, Codex, Antigravity, OpenCode, and any MCP-compatible IDE
+- Agent-agnostic: works through MCP with Cursor, Claude Code, VS Code, Windsurf, JetBrains (Copilot, Junie), GitHub Copilot, Codex, Antigravity, OpenCode, and any MCP-compatible IDE. Native hook support is IDE-specific; Antigravity and OpenCode hooks are not currently supported or tested.
 - Integrates via [Model Context Protocol (MCP)](/rosetta/docs/architecture/#rosetta-mcp), the standard transport for AI agent instructions
 - Security model: Rosetta is designed to only serve knowledge and instructions to agents — it does not see or process source code. No code leaves the organization's perimeter by design. Rosetta itself does not store any project data. Opt-in features (project datasets, plan_manager, usage analytics) can be enabled in your deployment for cross-project intelligence, execution tracking, and adoption visibility; when enabled, your infrastructure stores the data and you are responsible for it. plan_manager receives execution plans created by AI, which may contain project-specific information. Usage analytics (PostHog) collects basic operational metadata — IP address, user email, coding agent with version, tool called, and tool parameters — when you deploy and configure a PostHog instance on your infrastructure.
 - Grounded in production experience, not theory. Active feedback loop from real projects.
diff --git a/docs/web/docs/overview.md b/docs/web/docs/overview.md
index d316844d..93e877f4 100644
--- a/docs/web/docs/overview.md
+++ b/docs/web/docs/overview.md
@@ -25,7 +25,7 @@ Rosetta is an **open-source governance and context layer** for AI coding agents.
 
 Design principles:
 
-**Agent-agnostic.** Works across Cursor, Claude Code, VS Code, Windsurf, JetBrains (Copilot, Junie), GitHub Copilot, Codex, Antigravity, OpenCode, and any MCP-compatible IDE. Adopts agent-specific features where available, simulates them where not.
+**Agent-agnostic.** Works through MCP across Cursor, Claude Code, VS Code, Windsurf, JetBrains (Copilot, Junie), GitHub Copilot, Codex, Antigravity, OpenCode, and any MCP-compatible IDE. Adopts agent-specific features where available; native hooks remain IDE-specific and require per-IDE validation.
 
 **Progressive disclosure.** Instructions load in stages (bootstrap, classification, workflow-specific, sub-instructions) to [prevent context overflow](/rosetta/docs/architecture/#context-overflow-prevention). The agent gets only what it needs for the current task.

@isolomatov-gd isolomatov-gd left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

See above for diff of changes required to be applied

@github-actions

github-actions Bot commented Jul 6, 2026

Copy link
Copy Markdown
Contributor

Rosetta Triage Review — Follow-up Patch Analysis

Thanks @isolomatov-gd. The proposed patch is valid and addresses a real gap in PR #126. Here's the analysis:

What PR #126 already covers:

  • docs/ARCHITECTURE.md: adds (MCP integration; native hooks vary by IDE) to the diagram + updates the Portability bullet
  • docs/CONTEXT.md: adds "works through MCP" + "Antigravity hooks remain unverified..."

What the follow-up patch adds (all valid):

File Status Notes
OVERVIEW.md ✅ Needed PR #126 skips OVERVIEW.md; it has the same "Agent-agnostic" design-principle statement that needs the same update
docs/CONTEXT.md ✅ Improvement Extends "Antigravity hooks" to also cover OpenCode; drops the awkward "should not be treated as supported until validated" for cleaner "not currently supported or tested"
docs/web/docs/architecture.md ✅ Needed Direct mirror of the ARCHITECTURE.md changes PR #126 makes; public site would drift without it
docs/web/docs/context.md ✅ Needed Same for the CONTEXT.md web mirror
docs/web/docs/overview.md ✅ Needed Same for the OVERVIEW.md web mirror

Concerns: None. All changes are factually accurate — the hook verification work (cross-IDE output-format verification series) confirmed that Antigravity and OpenCode hooks are not validated. The wording "not currently supported or tested" is more direct and less ambiguous.

Suggestion for the PR author: Please apply this patch to your branch. The web mirror updates are the most important missing piece — without them the public site (docs/web) will diverge from the source docs after merge.

Automated triage by Rosetta agent

@ebbsanchez

Copy link
Copy Markdown
Author

Thanks for the follow-up patch. I applied the requested docs and web mirror updates in commit 4fb80762a7e6086da08b31b1b4a8e4cf9cad9c6a.

Local checks after the update:

  • git diff --check
  • rg "works through MCP|native hooks|Antigravity and OpenCode hooks" OVERVIEW.md docs/CONTEXT.md docs/ARCHITECTURE.md docs/web/docs/overview.md docs/web/docs/context.md docs/web/docs/architecture.md

Please re-review when you have time.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

documentation Improvements or additions to documentation

Projects

None yet

Development

Successfully merging this pull request may close these issues.

hooks: Antigravity support status contradicts docs — ARCHITECTURE.md vs MANUAL-TEST-CASES.md

3 participants