paseo-room 0.10.0 → 0.12.0

package/README.md

@@ -311,6 +311,7 @@ still required where Paseo launch state outranks the agent's own configuration:
 | `disableAgentView: true` + `CLAUDE_CODE_DISABLE_AGENT_VIEW=1` | Claude | Disables Claude's separate background-agent control plane across settings scopes and at launch. |
 | `disableWorkflows: true` + `CLAUDE_CODE_DISABLE_WORKFLOWS=1` | Claude | Disables dynamic workflows through every entry point, beyond denying the `Workflow` tool. |
 | `crossSessionInbound: "refuse"` | Claude | Prevents another Claude session from injecting a turn into a room seat. |
+| `disableClaudeAiConnectors: true` + `ENABLE_CLAUDEAI_MCP_SERVERS=0` | Claude | Keeps the signed-in account's claude.ai connectors (Canva, Claude Docs, …) out of every seat. They bypass the room's MCP check and reach Peer, and one that needs authorising makes each seat ask you to connect it. Your own Claude Code sessions keep them. |
 | strict argv + `PI_MCP_CONFIG_MODE=exclusive` + additive runtime capsule | Pi | Disables extension discovery and project trust, and restricts adapter config to the role-home `mcp.json`; forbids a second agent control plane without claiming sandboxing. |
 | `paseoTools: {enabled}` | all | Room tools for Supervisor and Lead, never for Peer. |
 
@@ -353,10 +354,11 @@ list is written to both provider `disallowedTools` and every role's `settings.js
 `permissions.deny`. The role file is minimal, deterministic room policy: it does not copy operator
 env, hooks, permissions, or auth helpers. The room does not write `permissions.defaultMode`:
 Paseo passes the profile's mode as a command-line session setting, which outranks that file. The two
-Claude disable environment keys are likewise pinned in both the provider and generated
-`settings.json`, because Claude applies settings-file environment values after launch values.
-The generated top-level `disableAgentView` and `disableWorkflows` settings are also forced to
-`true`; their restrictive value cannot be weakened by another ordinary settings scope.
+Claude disable environment keys, `ENABLE_CLAUDEAI_MCP_SERVERS=0` among them, are likewise pinned in
+both the provider and generated `settings.json`, because Claude applies settings-file environment
+values after launch values. The generated top-level `disableAgentView`, `disableWorkflows` and
+`disableClaudeAiConnectors` settings are also forced to `true`; their restrictive value cannot be
+weakened by another ordinary settings scope.
 
 No default model is pinned. The profile schema supports `model`, but leaving it absent lets
 each provider use its current default and avoids silently choosing a cost/capability tier for
@@ -656,6 +658,10 @@ npx paseo-room verify
     daemon restart, so Claude compacts at that share instead of near the end of a 1M window. An open
     session keeps what it opened with. Codex and Pi seats show their context and keep their own
     compaction.
+  - A mark applies to a seat only where it comes to at least 150k tokens on its window: at 30%, a
+    Lead on a 1M model is reported at 300k, but one on a 272k Codex or Pi model, or a 200k Claude
+    model, is not reported and keeps its agent's own compaction. The hints show what each mark comes
+    to per window.
 - **A runtime-dispatched Peer** is titled `<Disposition> · <outcome gist> · <assignment id>` (for
   example `Reviewer · Review the Docker Compose dev env… · asg_…`), and the runtime's notices to Lead
   name the assignment the same way. It gets exactly two tools, `ask` and `handoff`, for its own
@@ -670,18 +676,28 @@ npx paseo-room verify
   cleans or stashes, and releases a writer only after Paseo proves the Peer archived.
 - **State** lives under `~/.paseo-room/runtime/v1` as append-only event files. Setup never edits it.
 - **The Room runtime panel** (sidebar item, and a workspace panel that opens on its own project)
-  puts what needs you first. Below that come your projects, ordered by status, then your
-  Supervisors.
-  - A project shows its Supervisor, its Lead and Peer seats (each opens its agent in Paseo, and
-    shows the model and thinking option it runs with, and the worktree or main checkout it works in
-    with its branch) and its runtime record: assignments, isolated writers, findings and recovery.
+  puts what needs you first. Below that come your projects, then your Supervisors.
+  - Each project is one line: a status mark whose shape says it (needs a look, working, idle, or
+    asleep — its sessions closed, resumed by opening one or a message), then what it is doing, such
+    as *Lead idle · 1 of 2 Peers working · 3 open · 1 waiting on Lead*, and when it last did
+    something. Projects needing a look come first, then working, idle and asleep ones, the most
+    recently active first. Projects with no live seat fold into one *inactive* line, unless
+    dispatched work there is still undecided or a Lead replacement is in progress.
+  - A project shows who watches it, its Lead and Peer seats (each opens its agent in Paseo, and
+    shows the model and thinking option it runs with, the worktree or main checkout it works in, and
+    its context as a bar with a tick at its mark), recent activity (dispatches, handbacks, gates and
+    decisions, with who did them), and its assignments: open ones first, the most recently updated on
+    top, and finished ones by day with when they settled and how long they took, twenty at a time.
+    An assignment shows its brief, Peer, evidence and history.
   - Starting a Supervisor, adding a repository, starting a Lead for a project that has none, and
-    assigning a Supervisor are guided forms.
+    assigning a Supervisor are guided forms. The bell and people icons open the two settings
+    screens.
   - The design notes are in [docs/design/runtime-panel-ux.md](docs/design/runtime-panel-ux.md).
 - **Settings › Room seats** shows which account each seat is signed in to (email, plan and
   organization for Claude; login method for Codex; for Pi, only whether a credential file exists).
   It runs each seat's own `claude auth status` or `codex login status` when you open it or press
-  Refresh, and never reads a credential file. A seat linked to another home's login is flagged.
+  Refresh, and never reads a credential file. A seat linked to another home's login is flagged, and
+  when seats sign in as more than one account, each gets a letter (*account A*, *account B*).
 
 ### Room attention: what reaches a Supervisor
 
@@ -739,12 +755,15 @@ learn only when you ask it to check.
     Lead is not running, when Paseo would take none.
   - **The Supervisor may do the same**, but only for a Lead of its own project that is past its
     rotation mark, through the runtime's `lead_replace_*` tools. The runtime refuses a Lead below
-    the mark and applies the same quiet-point checks. The Supervisor reviews the handoff against the
-    repository, confirms it, and tells you which Lead now owns the project. The panel shows a
-    replacement the Supervisor started, and you may cancel it until it completes. Any other reason to
-    replace a Lead stays yours.
-- **Settings › Room attention.** Here you turn letters on or off, change their thresholds, and
-  configure the optional **attention sensor**.
+    the mark, or on a window where the mark does not apply, and applies the same quiet-point
+    checks. The Supervisor reviews the handoff against the repository, confirms it, and tells you
+    which Lead now owns the project. The panel shows a replacement the Supervisor started, and you
+    may cancel it until it completes. Any other reason to replace a Lead stays yours.
+- **Settings › Room attention.** Here you turn letters on or off, see what reached Supervisors in
+  the last 24 hours (letters by level, incidents, Lead turns by what was decided, and the ratings you
+  or a Supervisor gave), change when a Supervisor is told and how often, and configure the optional
+  **attention sensor** in the order it is set up: mode and state, connection, privacy, then the
+  shadow evaluation beside the switch that lets it assist.
   - The sensor speaks the System One HTTP shape, with [TypeSafe Jev](https://docs.typesafe.ai/)
     first and any compatible or self-hosted endpoint after it. It is `off` by default.
   - Without a TypeSafe key, use Jev through OpenRouter: endpoint

package/dist/index.js

@@ -15,7 +15,7 @@ var init_package = __esm({
   "package.json"() {
     package_default = {
       name: "paseo-room",
-      version: "0.10.0",
+      version: "0.12.0",
       description: "One CLI that configures Codex, Claude Code, and Pi role homes in $HOME and registers them with your local Paseo daemon.",
       keywords: [
         "paseo",
@@ -1186,7 +1186,7 @@ function renderRoleSettings(role, secureStorageDir) {
   const settings = {
     // Claude applies settings.env after the launch environment, so repeat provider closures here.
     env: {
-      ...CONTROL_PLANE_ENV,
+      ...LAUNCH_ENV,
       PASEO_ROOM_ROLE: role,
       ...secureStorageDir === void 0 ? {} : { [SECURE_STORAGE_ENV]: secureStorageDir }
     },
@@ -1195,6 +1195,7 @@ function renderRoleSettings(role, secureStorageDir) {
     // These restrictive settings cannot be weakened by another settings scope.
     disableAgentView: true,
     disableWorkflows: true,
+    disableClaudeAiConnectors: true,
     crossSessionInbound: "refuse"
   };
   return JSON.stringify(settings, null, 2) + "\n";
@@ -1252,7 +1253,7 @@ function mcpDriftCheck(role, home, path, divergence) {
     `If this role should have the same servers, add them with: CLAUDE_CONFIG_DIR=${home} claude mcp add ... \u2014 or delete ${path} and run setup --apply to reseed it from your current Claude state, which discards that role's other runtime state.`
   );
 }
-var SHARED, EXECUTABLE, RUNTIME_SKILLS, MCP_KEY, AUTH_ENV, CONTROL_PLANE_ENV, DISALLOWED_TOOLS, SECURE_STORAGE_ENV, SEEDED_KEYS, claudeAgent;
+var SHARED, EXECUTABLE, RUNTIME_SKILLS, MCP_KEY, AUTH_ENV, CONTROL_PLANE_ENV, CONNECTOR_ENV, LAUNCH_ENV, DISALLOWED_TOOLS, SECURE_STORAGE_ENV, SEEDED_KEYS, claudeAgent;
 var init_claude = __esm({
   "src/agents/claude.ts"() {
     "use strict";
@@ -1290,6 +1291,8 @@ var init_claude = __esm({
       CLAUDE_CODE_DISABLE_AGENT_VIEW: "1",
       CLAUDE_CODE_DISABLE_WORKFLOWS: "1"
     };
+    CONNECTOR_ENV = { ENABLE_CLAUDEAI_MCP_SERVERS: "0" };
+    LAUNCH_ENV = { ...CONTROL_PLANE_ENV, ...CONNECTOR_ENV };
     DISALLOWED_TOOLS = [
       "Task",
       "Agent",
@@ -1312,8 +1315,9 @@ var init_claude = __esm({
       id: "claude",
       label: "Claude Code",
       homeEnv: "CLAUDE_CONFIG_DIR",
-      // Agent View and dynamic workflows have entry points beyond model tool calls.
-      providerEnv: CONTROL_PLANE_ENV,
+      // Agent View and dynamic workflows have entry points beyond model tool calls, and claude.ai
+      // connectors arrive with the account rather than from any declaration the room inspects.
+      providerEnv: LAUNCH_ENV,
       defaultModeId: "bypassPermissions",
       // Keep the legacy Task name and block current native orchestration,
       // shared task/cron coordination, and cross-session paths. Paseo alone owns
@@ -2527,6 +2531,15 @@ var init_limits = __esm({
   }
 });
 
+// src/runtime-plugin/shared/states.ts
+var SETTLED_STATES;
+var init_states = __esm({
+  "src/runtime-plugin/shared/states.ts"() {
+    "use strict";
+    SETTLED_STATES = ["accepted", "rejected", "abandoned"];
+  }
+});
+
 // src/runtime-plugin/server/domain/scope.ts
 function normalizeScope(raw) {
   return raw.normalize("NFC").replace(/\/{2,}/g, "/").replace(/\/+$/, "");
@@ -3193,8 +3206,9 @@ var init_state = __esm({
   "src/runtime-plugin/server/domain/state.ts"() {
     "use strict";
     init_limits();
+    init_states();
     init_scope();
-    TERMINAL_STATES = ["accepted", "rejected", "abandoned"];
+    TERMINAL_STATES = SETTLED_STATES;
   }
 });