xevol 0.12.10 → 0.14.0

package/README.md

@@ -47,6 +47,8 @@ xevol workspace switch <workspace-id>
 
 ### Auth
 - `xevol login` — device auth flow (or `--token` for headless/CI)
+- `xevol connect <codex|claude|pi|other> [--workspace <id>]` — connect an AI app to Xevol's MCP server in one step. You approve with a code in any browser, so it works over SSH; the app gets limited agent access (read and draft in one Workspace) and is listed under Settings → Connected AI agents. `other` prints the URL and header for any other MCP client.
+- `xevol login --agent --workspace <id>` — limited access for an AI agent (Claude Code, Codex): one Workspace, read and draft, never approve, send, publish or delete. Give agents this token, never the full one. Disconnect it in Settings.
 - `xevol logout` — revoke token + clear local config
 - `xevol whoami` — current authenticated account
 
@@ -180,8 +182,9 @@ Add, upload, status, and retry use the selected Work Workspace's Creator gateway
 - `xevol resume <transcriptionId>` — resume interrupted stream session
 - `xevol prompts ...` — prompt CRUD/list/get
 
-### Usage, exports, locations
+### Usage, billing, exports, locations
 - `xevol usage` — plan + usage snapshot
+- `xevol billing [--workspace-id <id>] [--json]` — read the Workspace credit balance, monthly use, enforcement policy, and waiting-work count
 - `xevol export <id> --format json|markdown|text` — export content locally
 - `xevol coordinates current` — latest Xevol Coordinates context, with coordinates hidden unless `--exact`
 - `xevol coordinates current --json` — stable machine-readable current context for scripts/agents
@@ -199,7 +202,7 @@ Use `--agent-id` and `--agent-revision` together only when reading a legitimatel
 These commands require a Work API release that provides `agentSkills.discover` and `agentSkills.readRevision`. An older server returns `UNSUPPORTED_SERVER`; the CLI never falls back to the administrative skill-history surface.
 
 ### Interface
-- `xevol agent-help` — machine-oriented guide for agents/scripts using xevol-cli
+- `xevol agent-help` — guide for AI agents with agent access: what they can read and draft, and what only people decide
 - `xevol agent-help --json` — structured command/workflow guide for agents
 - `xevol tui` — interactive terminal UI