This is an automated email from the ASF dual-hosted git repository. luigidemasi pushed a commit to branch main in repository https://gitbox.apache.org/repos/asf/camel-kit.git
commit c1a53c3c5d3d35133f36d1218b3bd44d47ac14e1 Author: Jinal Sarvaiya <[email protected]> AuthorDate: Thu Oct 29 22:44:49 2026 +0000 fix #95: add docs and changelog for Antigravity native Ship --- CHANGELOG.md | 5 +++++ docs/modules/ROOT/pages/agents.adoc | 4 ++-- docs/modules/ROOT/pages/ship.adoc | 20 +++++++++++++------- 3 files changed, 20 insertions(+), 9 deletions(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index 9848fc0c..2051ead7 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -22,6 +22,11 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0 ### Added +- **Google Antigravity native Ship (#95)** — eligible sessions relay controller-issued stages through a dedicated + `camel-ship-worker` agent with `commandExecutionPolicy: "off"` and read-only tools. + `--backend antigravity-native` reuses the native task/result, recovery, oversight and deterministic publication + contract while preserving Antigravity's permission prompts, sandbox settings and existing session permissions. + Fresh and regenerated workspaces receive the native skill and worker; runs retain their recorded host. - **OpenAI Codex CLI native Ship (#225)** — eligible sessions relay controller-issued stages through the dedicated `camel_ship_worker` custom agent with `sandbox_mode = "read-only"` and instruction-level restrictions. `--backend codex-native` reuses the native task/result, recovery, oversight and deterministic publication contract diff --git a/docs/modules/ROOT/pages/agents.adoc b/docs/modules/ROOT/pages/agents.adoc index 4302dc9f..d6115e44 100644 --- a/docs/modules/ROOT/pages/agents.adoc +++ b/docs/modules/ROOT/pages/agents.adoc @@ -69,9 +69,9 @@ Install Antigravity following https://antigravity.google/docs/getting-started[Go camel-kit init my-integration --ai antigravity ---- -`init` writes `AGENTS.md`, the skills under `.agents/skills/`, two custom agents under `.agents/agents/` +`init` writes `AGENTS.md`, the skills under `.agents/skills/`, three custom agents under `.agents/agents/` (`camel-worker` with file and sandboxed command tools, `camel-reviewer` with read and search tools plus the -inherited MCP access), the role +inherited MCP access, `camel-ship-worker` with read and search tools for Ship stages), the role personas under `.agents/camel-kit-personas/` and the MCP servers in `.agents/mcp_config.json` (two by default; three with `--with-citrus-mcp`). Open the project root in Antigravity and invoke `/camel-start` in the CLI, or ask it to use the `camel-start` skill by name; `/skills` lists the native skills and `/mcp` the connections. diff --git a/docs/modules/ROOT/pages/ship.adoc b/docs/modules/ROOT/pages/ship.adoc index 187617a3..057d1124 100644 --- a/docs/modules/ROOT/pages/ship.adoc +++ b/docs/modules/ROOT/pages/ship.adoc @@ -60,8 +60,8 @@ the discovery input before any question, and open points come back as grouped un | `--status RUN_ID` | | Read the latest durable state without starting the workflow runtime | `--abort RUN_ID` | | Abort a run that has not completed; aborted runs cannot be resumed | `--start-from STAGE` | | Start a new run at `discovery`, `design` or `plan` -| `--backend MODE` | `pi` | `pi`, `bob2-native`, `copilot-native`, `claude-native` or, in the development snapshot, - `codex-native`; a run keeps its mode for its lifetime +| `--backend MODE` | `pi` | `pi`, `bob2-native`, `copilot-native`, `claude-native`, `antigravity-native` or, in the + development snapshot, `codex-native`; a run keeps its mode for its lifetime | `--json` | off | Structured run state and any pending native task | `--submit RUN_ID --result PATH` | | Relay one native child result | `--pi PATH`, `--node PATH` | found on `PATH` | Executables for the Pi backend; rejected for native runs @@ -147,16 +147,16 @@ is trusted. [[native]] == Native subagents -With the Pi backend, Ship runs an external Pi worker. Eligible IBM Bob 2, GitHub Copilot CLI and Claude Code -sessions can instead relay the controller's stage tasks to their own read-only native subagents; OpenAI Codex CLI -joins them in the development snapshot. The contract is the same for every host: +With the Pi backend, Ship runs an external Pi worker. Eligible IBM Bob 2, GitHub Copilot CLI, Claude Code and +Google Antigravity sessions can instead relay the controller's stage tasks to their own read-only native subagents; +OpenAI Codex CLI joins them in the development snapshot. The contract is the same for every host: . The controller creates one pending task with its run, stage, attempt, input digest, deadline and a unique task ID, and returns to the parent session. . The parent dispatches a fresh `camel-ship-worker` child with the controller's complete prompt, copied verbatim, and submits the observed result through `ship --submit RUN_ID --result PATH --json`. . The worker never edits project files, writes to the candidate or the state directory, calls MCP servers, delegates - or publishes. On Bob 2, Copilot CLI and Claude Code it has read and search tools only; on Codex CLI it may use + or publishes. On Bob 2, Copilot CLI, Claude Code and Antigravity it has read and search tools only; on Codex CLI it may use the host's file-reading means, shell commands included, for the named inputs and sources, under the host's permissions. For execute it returns complete text proposals for the approved route and test paths, `pom.xml` and `.camel-kit/config.properties`; arbitrary extra resources, binary files and deletions are outside the contract. @@ -195,6 +195,11 @@ certification. `sandbox_mode = "read-only"` and no MCP servers. Where the host does not enforce the sandbox, the worker's instructions are the operative restriction. If `--backend codex-native` is requested and dispatch is unavailable the skill stops without starting a run. + +| Google Antigravity +| `/camel-ship` from the generated skill in a session that exposes `invoke_subagent` and the `camel-ship-worker` + custom agent, which declares `commandExecutionPolicy: "off"`, `inheritMcp: true` and only read and search tools. + The skill respects Antigravity's permission prompts and sandbox settings. |=== A fresh context is not an OS sandbox: read access follows the parent's permitted paths. Do not broaden permissions, @@ -215,7 +220,8 @@ error, including `stale-stage-input` or a permission denial, and wait for a new to their read-only worker; Claude Code's compatibility command stub only points at the skill. * *IBM Bob 2* exposes the native skill as `$camel-ship` in Bob Shell and `/camel-ship` in Bob IDE. * *OpenAI Codex CLI* exposes `$camel-ship` with no generated command file. -* *Google Antigravity* invokes the native `camel-ship` skill, which forwards the options once. +* *Google Antigravity* exposes `/camel-ship` through its skills directory and relays eligible runs to its read-only + worker via `invoke_subagent`. * *Qwen Code* and *OpenCode* generate a `/camel-ship` command stub that forwards the options once. * *Pi* exposes Ship only as `/skill:camel-ship`; there is deliberately no `/camel-ship` prompt, because Pi's prompt expansion flattens quoted option values.
