@ory/amp 0.13.8 → 0.14.0

package/README.md

@@ -21,12 +21,14 @@ Run one command. It installs the plugin and walks you through connecting:
 npx -y -p @ory/amp ory-amp install
 ```
 
-You'll be asked how you want to connect — **press Enter for the default**:
+It opens a guided setup **in your browser** where you pick how to connect — the default takes just a click:
 
 - **Ory Network** *(default)* — sign in, or create a free account, in your browser. The project, keys, permissions, and login are all set up for you. Nothing to configure by hand.
 - **Local** — run a complete Ory on your laptop with Docker. No account, no signup, no keys. Great for trying it out.
 - **Audit-only** — skip Ory entirely and just log what Amp does.
 
+> No browser available (CI, SSH, headless)? The same walkthrough runs right in your terminal instead — or force it with `--no-web`.
+
 That's it. Confirm everything landed with:
 
 ```bash
@@ -52,6 +54,7 @@ If Ory is ever slow or unreachable, the plugin gets out of the way and lets Amp
 Everything the plugin does is observable out of the box — no configuration required:
 
 - **Status at a glance.** `npx -y -p @ory/amp ory-amp status` shows what's configured, who's signed in, how many built-in tools your permissions cover, and the most recent tool-call activity.
+- **Live dashboard.** `npx -y -p @ory/amp ory-amp dashboard` opens the same picture in your browser — configuration, identities, permission coverage, Ory service health, and the latest tool-call activity, all refreshing live. From there you can flip **enforcement** on or off, toggle **user login**, and use **Change stack** to reconnect to a different Ory — no CLI required.
 - **Live traces.** Every tool call is recorded as an OpenTelemetry-style span. Watch them stream as the agent works:
 
   ```bash
@@ -69,7 +72,7 @@ When the watch-mode logs look right, turn on blocking with one command (setup al
 npx -y -p @ory/amp ory-amp permissions enforce
 ```
 
-Now a denied tool is actually blocked and Amp shows why. Go back to watch mode anytime with `permissions observe`. Use `permissions status` to see what's covered and `permissions bootstrap` to (re-)grant the built-in tools.
+Now a denied tool is actually blocked and Amp shows why. Go back to watch mode anytime with `permissions observe`. Prefer clicking? The dashboard has the same **Enforce** switch — flip it on, or back to watch mode, without touching the CLI. Use `permissions status` to see what's covered and `permissions bootstrap` to (re-)grant the built-in tools.
 
 <details>
 <summary>How the plugin plugs into Amp</summary>
@@ -100,22 +103,22 @@ The guided setup covers most people. For scripted or CI setups, or to point at a
 ```bash
 npx -y -p @ory/amp ory-amp configure \
   --project-url https://<slug>.projects.oryapis.com \
-  --oauth2-client-id <sign-in client id> \
-  --user-login
+  --oauth2-client-id <sign-in client id>
 ```
 
-Amp's own identity registers itself automatically on first run — nothing to create. The `--oauth2-client-id` is the one piece browser sign-in needs (the public client registered with the four loopback callback URLs `http://127.0.0.1:47823..47826/callback`); the guided setup makes it for you. Pass `--api-key ory_pat_...` only to override Amp's auto-created identity with a static token. For logging-only with no checks, use `--audit-only`. The matching env vars are `ORY_PROJECT_URL`, `ORY_OAUTH2_CLIENT_ID`, `ORY_USER_LOGIN`, and `ORY_AGENT_API_KEY`.
+Amp's own identity registers itself automatically on first run — nothing to create. The `--oauth2-client-id` is the one piece browser sign-in needs (the public client registered with the four loopback callback URLs `http://127.0.0.1:47823..47826/callback`); the guided setup makes it for you. Pass `--api-key ory_pat_...` only to override Amp's auto-created identity with a static token. For logging-only with no checks, use `--audit-only`. The interactive user login runs every session (always on, non-blocking) and only needs `ORY_OAUTH2_CLIENT_ID` to complete the browser flow. The matching env vars are `ORY_PROJECT_URL`, `ORY_OAUTH2_CLIENT_ID`, and `ORY_AGENT_API_KEY`.
 
 With nothing configured, the plugin still loads and runs in **pass-through mode**: skills and logging work, but no checks run and nothing is blocked. Perfectly fine if you only want the app-building features.
 
 ## Commands
 
 ```
-ory-amp install | uninstall        Install/remove; --reconfigure re-runs setup, --no-configure skips it
+ory-amp install | uninstall        Install/remove; --reconfigure re-runs setup, --no-web forces the terminal wizard, --no-configure skips it
 ory-amp status                     Show configuration, identities, permission coverage, and recent activity
+ory-amp dashboard                  Open the live browser dashboard (status + service health + Change stack)
 ory-amp watch                      Tail the live trace stream (OTel spans)
 ory-amp permissions <cmd>          status | bootstrap | observe (watch) | enforce (block)
-ory-amp configure <flags>          Point at a project by hand (--project-url, --oauth2-client-id, --user-login, --audit-only)
+ory-amp configure <flags>          Point at a project by hand (--project-url, --oauth2-client-id, --audit-only)
 ory-amp agent <status|unregister>  Manage Amp's own auto-created identity
 ```
 

package/dist/cli/main.js

@@ -100,6 +100,12 @@ function main() {
         case "watch":
             (0, argus_1.runWatchCommand)("amp", args);
             break;
+        case "dashboard":
+            (0, argus_1.runDashboardCommand)("ory-amp", "amp", args).then((code) => process.exit(code), (err) => {
+                console.error(err.message ?? err);
+                process.exit(1);
+            });
+            break;
         case "version":
         case "--version":
         case "-v":
@@ -183,6 +189,7 @@ Commands:
                                    (status, bootstrap, observe, enforce)
   setup [--project-dir <path>]     Write config directly (fallback)
   status [--project-dir <path>]    Show plugin configuration and status
+  dashboard            Open the Ory Agent dashboard (system health + configuration)
   watch [trace-file]               Tail the trace stream (OTel spans) live
   version                          Show version and the ory-agent-plugins build commit
   local <cmd>                      Manage local Ory dev environment

package/dist/plugin.d.ts

@@ -6,8 +6,8 @@
  * Each handler receives the event payload and a `PluginEventContext`. We
  * subscribe to:
  *
- *   session.start → run the user gate (advisory, allowBlock:false), the
- *                   agent gate, and write the user→agent delegation tuple.
+ *   session.start → run the user gate, the agent gate, and write the
+ *                   user→agent delegation tuple.
  *   tool.result   → record a `tool.complete` audit span.
  *
  * The BLOCKING permission decision deliberately does NOT live here. Amp's
@@ -18,9 +18,9 @@
  * observational. The delegate runs as its own process and decides by exit
  * code; this module only authenticates and traces.
  *
- * Because Amp's `session.start` handler has no return-value channel for
- * blocking, the user login runs in advisory mode (allowBlock:false), like
- * the OpenCode / OpenClaw factory plugins.
+ * The user login runs every session and never blocks — it emits the
+ * user.auth audit span, refreshes tokens, and may prompt when interactive.
+ * Enforcement is governed solely by permissionMode at tool-call time.
  */
 import { OryAgentClient, ensureUserAuthenticated, ensureAgentIdentity } from "@ory/argus";
 import type { AmpPlugin } from "./types.js";

package/dist/plugin.js

@@ -7,8 +7,8 @@
  * Each handler receives the event payload and a `PluginEventContext`. We
  * subscribe to:
  *
- *   session.start → run the user gate (advisory, allowBlock:false), the
- *                   agent gate, and write the user→agent delegation tuple.
+ *   session.start → run the user gate, the agent gate, and write the
+ *                   user→agent delegation tuple.
  *   tool.result   → record a `tool.complete` audit span.
  *
  * The BLOCKING permission decision deliberately does NOT live here. Amp's
@@ -19,9 +19,9 @@
  * observational. The delegate runs as its own process and decides by exit
  * code; this module only authenticates and traces.
  *
- * Because Amp's `session.start` handler has no return-value channel for
- * blocking, the user login runs in advisory mode (allowBlock:false), like
- * the OpenCode / OpenClaw factory plugins.
+ * The user login runs every session and never blocks — it emits the
+ * user.auth audit span, refreshes tokens, and may prompt when interactive.
+ * Enforcement is governed solely by permissionMode at tool-call time.
  */
 Object.defineProperty(exports, "__esModule", { value: true });
 exports.createOryPlugin = createOryPlugin;
@@ -55,95 +55,26 @@ function createSessionStartHandler(client, deps) {
         client.tracer.record("session.start", "ok", {
             attributes: sessionId ? { sessionId } : {},
         });
-        // Run the user login. Amp's session.start has no block primitive, so
-        // allowBlock is false — the flow emits the user.auth audit span,
-        // refreshes tokens, and may prompt when interactive, but never
-        // prevents the session from starting. When ORY_USER_LOGIN is unset it
-        // is a no-op (mode === "disabled") and we fall through to legacy
-        // logging.
+        // Run the user login. It runs every session and never blocks — the
+        // flow emits the user.auth audit span, refreshes tokens, and may
+        // prompt when interactive, but never prevents the session from
+        // starting. Enforcement is governed solely by permissionMode at
+        // tool-call time.
         const userGate = deps.userLogin ?? argus_1.ensureUserAuthenticated;
-        const decision = await userGate(client, {
+        await userGate(client, {
             binName: "ory-amp",
             harness: "amp",
-            allowBlock: false,
         });
         // Resolve the agent identity (machine credentials). Never blocks;
         // attaches the agent's bearer token to outgoing Ory API calls.
         const agentGate = deps.agentGate ?? argus_1.ensureAgentIdentity;
         await agentGate(client, { projectUrl: (0, argus_1.resolveConfig)().projectUrl, harness: "amp" });
         // Once both principals are populated, write the user→agent delegation
-        // tuple. Idempotent + fail-open: audit-trail data only.
-        await recordUserDelegatesAgent(client);
-        if (decision.mode !== "disabled") {
-            return;
-        }
-        const resolved = (0, argus_1.resolveConfig)();
-        if (resolved.auditOnly) {
-            client.logger.info("config.audit_only", {
-                message: "Audit-only mode enabled. Auth and permission checks are disabled.",
-            });
-            return;
-        }
-        if (!resolved.projectUrl) {
-            client.logger.warn("config.not_configured", {
-                message: "Ory plugin is not configured. Auth and permission checks are disabled. " +
-                    "Run 'npx ory-amp configure' to connect to an Ory project.",
-            });
-            return;
-        }
-        const sessionToken = process.env.ORY_SESSION_TOKEN;
-        const oauth2Token = process.env.ORY_OAUTH2_TOKEN;
-        if (sessionToken) {
-            await verifySessionToken(client, sessionToken);
-            return;
-        }
-        if (oauth2Token) {
-            await verifyOAuth2Token(client, oauth2Token);
-            return;
-        }
-        client.logger.warn("session.no_credentials", {
-            message: "Neither ORY_SESSION_TOKEN nor ORY_OAUTH2_TOKEN is set. " +
-                "Skipping authentication.",
-        });
+        // tuple. Written at most once per install + fail-open: audit-trail data
+        // only.
+        await (0, argus_1.writeUserDelegatesAgent)(client);
     };
 }
-async function verifySessionToken(client, token) {
-    try {
-        const session = await client.verifySession(token);
-        if (!session.active) {
-            client.logger.warn("session.inactive", {
-                message: "Ory session is not active. Re-authenticate to enable auth checks.",
-            });
-        }
-    }
-    catch (err) {
-        client.logger.warn("session.verify_failed", {
-            code: isOryError(err) ? err.code : "unknown",
-            message: err instanceof Error ? err.message : String(err),
-        });
-    }
-}
-async function verifyOAuth2Token(client, token) {
-    try {
-        const tokenInfo = await client.introspectToken(token);
-        if (!tokenInfo.active) {
-            client.logger.warn("oauth2.token_inactive", {
-                message: "Ory OAuth2 token is not active. Obtain a new token to enable auth checks.",
-            });
-            return;
-        }
-        client.logger.info("oauth2.session_authenticated", {
-            clientId: tokenInfo.clientId,
-            subject: tokenInfo.subject,
-        });
-    }
-    catch (err) {
-        client.logger.warn("oauth2.introspect_failed", {
-            code: isOryError(err) ? err.code : "unknown",
-            message: err instanceof Error ? err.message : String(err),
-        });
-    }
-}
 // ─── tool.result ───────────────────────────────────────────────────
 function createToolResultHandler(client) {
     return async (event, _ctx) => {
@@ -171,47 +102,3 @@ function createToolResultHandler(client) {
         });
     };
 }
-// ─── Helpers ───────────────────────────────────────────────────────
-function resolveNamespace() {
-    return process.env.ORY_PERMISSION_NAMESPACE ?? "AgentTools";
-}
-function isOryError(err) {
-    return (typeof err === "object" &&
-        err !== null &&
-        "code" in err &&
-        "message" in err);
-}
-/**
- * Write the user→agent delegation tuple. Idempotent and fail-open:
- * requires both principal subjects to be populated; any error (including
- * an unconfigured projectUrl, which manifests as a network_error) is
- * logged and swallowed. Purely audit-trail data — does not affect
- * enforcement.
- */
-async function recordUserDelegatesAgent(client) {
-    const user = client.userPrincipal.subject;
-    const agent = client.agentPrincipal.subject;
-    if (!user || !agent) {
-        client.logger.debug("delegation.skip", {
-            reason: "missing principal",
-            hasUser: !!user,
-            hasAgent: !!agent,
-        });
-        return;
-    }
-    try {
-        await client.createRelationship({
-            namespace: resolveNamespace(),
-            object: `agent:${agent}`,
-            relation: "delegate",
-            subjectId: `user:${user}`,
-        }, { spanAttributes: { delegation: "user-to-agent" } });
-    }
-    catch (err) {
-        const oryErr = err;
-        client.logger.warn("delegation.user_to_agent.failed", {
-            code: oryErr.code,
-            message: oryErr.message,
-        });
-    }
-}

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@ory/amp",
-  "version": "0.13.8",
+  "version": "0.14.0",
   "description": "Ory plugin for Amp (Sourcegraph's coding agent): a permission delegate that authorizes every tool call plus an in-process plugin for session auth and audit tracing",
   "license": "Apache-2.0",
   "homepage": "https://ory.com",
@@ -68,7 +68,7 @@
   ],
   "dependencies": {
     "reo-census": "^1.2.8",
-    "@ory/argus": "0.13.8"
+    "@ory/argus": "0.14.0"
   },
   "devDependencies": {
     "typescript": "^6.0.2",