agentplugged 1.4.0 → 2.0.0

package/README.md

@@ -34,6 +34,7 @@ method once. Run it again to refresh the method; your documents, stories, settin
 | `profile` | Changes what the method does for this product (domains, phases, developer specialties and the ceiling of stories at once) and its validation level (`--validation chat\|auto\|strict`). |
 | `sync` | Generates the AI tools' files from the method and your customisations. |
 | `agent create\|edit\|enable\|disable <id>` | Manages your own agents and skills. |
+| `update [--check on\|off] [--auto on\|off]` | Moves the product to a newer engine when you say yes (in your own terminal), and sets two settings of this machine: `check` (off by default: the engine never looks for a new version on its own) and `auto` (off by default). |
 | `mcp` | Runs the MCP server (stdio only) your agents report their status, progress, costs and results through. `sync` declares it in each AI tool's project configuration, pinned to your engine version. |
 | `review [<G-id>]` | Answers a checkpoint your agents opened, in an interactive terminal only: its card, numbered actions, then your answer signed by your key (`locale`, or `presence` with Windows Hello). It also reopens a checkpoint applied automatically at the `auto` level. It is the way of the `strict` level; at the other levels you answer in the chat. |
 | `key presence [--reset]` | Protects your validations with Windows Hello (Windows only; `init` proposes it). Without it, they keep the `locale` assurance. `--reset` creates the credential again when the stored one no longer works. |
@@ -68,8 +69,9 @@ In Claude Code, `sync` writes a `UserPromptSubmit` hook of type `command`
 digest, time, session) in `~/.agentplugged/chat/`, outside the repository and the journal, for
 24 hours. The engine accepts a quote only when it is one of your messages of that session, sent
 after the checkpoint opened, and not already used for another checkpoint; otherwise nothing is
-written (`CHAT_QUOTE_NOT_FOUND`). In the other AI tools, answers are recorded « unverified »
-(`chat_unverified`) and shown so everywhere. The deny rules `sync` writes keep agents from the
+written (`CHAT_QUOTE_NOT_FOUND`). In the other AI tools the chat proves nothing and an answer given there is refused
+(`REVIEW_REQUIRED`, `no_proof`): you validate on the decision card of the web view or the phone
+(a signed order of a device you linked), or at the terminal. The deny rules `sync` writes keep agents from the
 store and the script; they are best-effort: an agent that deliberately works around its
 permission profile is out of reach of this check, and `strict` is there for that.
 
@@ -228,6 +230,10 @@ By default the tools start it with `npx -y agentplugged@<engine_version> mcp`.
   active agent. The tool's main session, which is not an agent of the method, uses the reserved
   id `main`.
 
+## What the engine contacts
+
+The engine alone contacts none of our servers and has no feature that needs an account. By default it makes no network request of its own: the look at the npm registry is off until `update --check on`, and `update` asks the registry only when you run it. It does talk to **your own Git repository**: the automatic backup of the journal fetches from and sends to its remote (a separate private repository when yours is public), and the forge commands run `gh` or `glab` and Git after your approval. Without a Git remote they make no call.
+
 ## Pinned engine version
 
 `.agentplugged/method.yaml` pins the version of agentplugged the product was installed with