ticlawk 0.1.17-dev.2 → 0.1.17-dev.20

package/README.md

@@ -13,57 +13,42 @@ from your phone.
 
 ## Quickstart — 2 minutes
 
-You need a project directory on this machine where Claude Code (or another
-supported runtime) can run, and the Ticlawk app installed on your phone.
+You need a machine with at least one supported runtime installed and the
+Ticlawk app installed on your phone.
 
 ```bash
 # 1. install
 curl -fsSL https://raw.githubusercontent.com/darthjaja6/ticlawk/main/install.sh | bash
 
 # 2. connect this machine to your Ticlawk account by scanning the QR code
-cd /path/to/project
 ticlawk connect
 ```
 
-`ticlawk connect` auto-detects every supported runtime in that project
-directory (Codex, Claude Code, opencode, pi) and lets you pick one inside the
-app once pairing completes. Run `ticlawk connect` again from a different
-directory when you want to bind a new project.
+`ticlawk connect` authorizes the current machine as a Ticlawk host. After the
+host is connected, create agents in the app by choosing that host and one of
+the runtimes the daemon reports as available.
 
 > ⚠️ **Single user, by design.** The connector binds to your Ticlawk account;
 > agents run with your local user's permissions and can edit files / run
-> commands inside the bound `--workdir`. Don't share your connector API key
-> and don't connect a workdir you wouldn't trust a shell to touch.
+> commands on that host. Don't share your connector API key and don't connect
+> a host you wouldn't trust a shell to touch.
 
 ---
 
-## Resuming an existing runtime session
+## Creating Agents
 
-By default each new chat creates a fresh runtime session. To resume an
-existing Claude Code or Codex transcript, point at it explicitly:
-
-| Runtime     | Required       | Optional resume handle | Where to find it                                              |
-|-------------|----------------|------------------------|---------------------------------------------------------------|
-| Claude Code | `--workdir`    | `--session-id`         | filename of `~/.claude/projects/**/*.jsonl` (without `.jsonl`)|
-| Codex       | `--workdir`    | `--session-id`         | `payload.id` in the first `session_meta` record of `~/.codex/sessions/**/*.jsonl` |
-| OpenClaw    | `--agent-id`   | none                   | logical agent name (`main` by default)                        |
-| opencode    | `--workdir`    | `--session-id` (with `--workdir`) | `.id` from `opencode session list --format json` (run inside the project dir) |
+`ticlawk connect` does not create an agent. It connects a host. The daemon
+then reports runtime health for Codex, Claude Code, opencode, OpenClaw, and pi.
+In the mobile app, tap `+`, choose a connected host, choose an available
+runtime, and create the agent there.
 
 [OpenClaw](https://github.com/openclaw/openclaw) is an open-source local-first
-agent runtime; skip this row if you don't use it.
-
-[opencode](https://opencode.ai) is provider-agnostic — it doesn't carry its own
-account system. Before connecting through `ticlawk`, install the CLI
-(`npm i -g opencode-ai`) and authenticate it once against the LLM provider
-you want it to use (`opencode auth login`, then pick Anthropic / OpenAI /
-Google / OpenRouter / etc. and paste the corresponding API key). Model
-selection lives in opencode's own config (`opencode.json` in the project
-root, or user-level config) — `ticlawk` does not pass `--model`.
+agent runtime; skip it if you don't use it.
 
-`ticlawk` spawns opencode and codex with `--dangerously-skip-permissions`-style
-flags so chat messages can drive shell commands and file edits in the bound
-workdir without further confirmation prompts. Only connect a workdir you
-trust to a chat you control.
+[opencode](https://opencode.ai) is provider-agnostic. Before creating an
+opencode-backed agent through Ticlawk, install the CLI (`npm i -g opencode-ai`)
+and authenticate it once against the LLM provider you want it to use
+(`opencode auth login`).
 
 ---
 
@@ -74,11 +59,10 @@ After setup:
 - Keep `ticlawk` running as a user service. If Linux prints an
   `Action required` message during install or connect, run the command it
   shows so the daemon keeps running after logout and reboot.
-- Bind to a new project: run `ticlawk connect` from the new directory.
-- Resume an existing transcript: add `--session-id` (Claude Code / Codex /
-  opencode) or `--agent-id` (OpenClaw) to the `connect` call.
-- If replies stop because the local runtime session ended, run `connect`
-  again or reset the session from the app.
+- Connect another host: run `ticlawk connect` on that machine.
+- Create a new agent from the app by choosing a connected host and runtime.
+- If replies stop because the local runtime session ended, reset the agent
+  session from the app.
 - `ticlawk health` is the first thing to check when something feels off.
 
 ---
@@ -201,7 +185,6 @@ Usage:
   ticlawk config
   ticlawk config get <streaming...|runtimes.claude_code.path|runtimes.codex.path|runtimes.opencode.path|runtimes.pi.path|ticlawk.connector-api-key|ticlawk.api-url|ticlawk.connector-ws-url>
   ticlawk config set <streaming...|runtimes.claude_code.path|runtimes.codex.path|runtimes.opencode.path|runtimes.pi.path|ticlawk.connector-api-key|ticlawk.api-url|ticlawk.connector-ws-url> <value>
-  ticlawk auth --code <6-digit-code> [--api-url <url>]
   ticlawk connect
   ticlawk profile list
   ticlawk profile current
@@ -212,35 +195,20 @@ Usage:
   ticlawk version
 
 Agent CLI (run inside an agent runtime; requires TICLAWK_RUNTIME_AGENT_ID):
-  ticlawk message send --target <t> --phase progress|final  # body on stdin
+  ticlawk message send --target <t>           # body on stdin
   ticlawk message read --target <t> [opts]
   ticlawk task claim --message-id <id>
   ticlawk task update --task-id <id> --status <s>
-  ticlawk task list [--target <t>]       # group admins see the full task board
-  ticlawk charter get --target <t>
+  ticlawk task list [--target <t>]
   ticlawk group members --target <t>
-  ticlawk group list
-  ticlawk agent list
-  ticlawk dashboard get --conversation-id <id>
   ticlawk server info [--refresh]
 
 Commands:
-  auth     store the ticlawk app pairing code locally
-  connect  connect ticlawk to a local runtime
+  connect  connect this host to Ticlawk
   profile  list or switch saved local identities
   message  send/read chat messages (agent CLI surface)
   task     claim/update/list tasks (agent CLI surface)
-  goal     report FSM transitions / signal goal changes (agent CLI surface)
-  approval canonical goal-loop approval request/resolve (agent CLI surface)
-  charter  get/set conversation goal and role spec (agent CLI surface)
-  group    create/list/delete groups, manage charters/members (agent CLI surface)
-  dashboard   set/get conversation dashboards (agent CLI surface)
-  briefing    publish/get owner briefings (agent CLI surface)
-  agent       list/create/delete owned agent slots (agent CLI surface)
-  service     publish/list/call shared services (agent CLI surface)
-  credential  request owner-filled credentials (agent CLI surface)
-  reminder    schedule/list/snooze/cancel reminders (agent CLI surface)
-  attachment  view private chat assets (agent CLI surface)
+  group    list members of a group conversation (agent CLI surface)
   server   server-info introspection (agent CLI surface)
   install-daemon  install or refresh the background daemon
   update   update the npm package and refresh the daemon
@@ -259,7 +227,6 @@ Config examples:
 
 Examples:
   ticlawk connect
-  ticlawk auth --code <6-digit-code>
 ```
 <!-- usage:end -->
 
@@ -268,7 +235,7 @@ Examples:
 ## Security model
 
 - **Agents can run code on your machine.** Whatever Claude Code / Codex /
-  OpenClaw / opencode / pi can do in the bound workdir, the Ticlawk app can
+  OpenClaw / opencode / pi can do on the connected host, the Ticlawk app can
   ask it to do. Treat the chat as you'd treat a shell.
 - **Single user.** The connector binds to one Ticlawk account. Don't share
   your connector API key.

package/bin/ticlawk.mjs

@@ -18,7 +18,6 @@ import {
   getActiveProfile,
   listProfiles,
 } from '../src/core/profiles.mjs';
-import { runAdapterAuth } from '../src/core/adapter-registry.mjs';
 import { runTiclawkConnect } from '../src/core/ticlawk-control.mjs';
 import {
   RUNTIME_DEFINITIONS,
@@ -32,36 +31,12 @@ import {
   AGENT_COMMAND_HELP,
   runAttachmentViewCommand,
   runGroupCreateCommand,
-  runWorkstreamCharterGetCommand,
-  runWorkstreamCharterSetCommand,
-  runWorkstreamCreateCommand,
-  runWorkstreamDeleteCommand,
-  runWorkstreamListCommand,
-  runAgentListCommand,
-  runAgentCreateCommand,
-  runAgentDeleteCommand,
-  runDashboardSetCommand,
-  runDashboardGetCommand,
-  runCredentialRequestCommand,
-  runBriefingPublishCommand,
-  runBriefingGetCommand,
-  runServiceCreateCommand,
-  runServiceUpdateCommand,
-  runServiceDeleteCommand,
-  runServiceListCommand,
-  runServiceInfoCommand,
-  runServiceCallCommand,
   runGroupMembersAddCommand,
   runGroupMembersCommand,
   runGroupMembersRemoveCommand,
   runMessageCheckCommand,
   runMessageReactCommand,
   runMessageReadCommand,
-  runGoalChangedCommand,
-  runGoalReportCommand,
-  runApprovalRequestCommand,
-  runApprovalResolveCommand,
-  runApprovalListCommand,
   runMessageSearchCommand,
   runMessageSendCommand,
   runProfileShowCommand,
@@ -105,7 +80,6 @@ Usage:
   ticlawk config
   ticlawk config get <${configKeys}>
   ticlawk config set <${configKeys}> <value>
-  ticlawk auth --code <6-digit-code> [--api-url <url>]
   ticlawk connect
   ticlawk profile list
   ticlawk profile current
@@ -116,35 +90,20 @@ Usage:
   ticlawk version
 
 Agent CLI (run inside an agent runtime; requires TICLAWK_RUNTIME_AGENT_ID):
-  ticlawk message send --target <t> --phase progress|final  # body on stdin
+  ticlawk message send --target <t>           # body on stdin
   ticlawk message read --target <t> [opts]
   ticlawk task claim --message-id <id>
   ticlawk task update --task-id <id> --status <s>
-  ticlawk task list [--target <t>]       # group admins see the full task board
-  ticlawk charter get --target <t>
+  ticlawk task list [--target <t>]
   ticlawk group members --target <t>
-  ticlawk group list
-  ticlawk agent list
-  ticlawk dashboard get --conversation-id <id>
   ticlawk server info [--refresh]
 
 Commands:
-  auth     store the ticlawk app pairing code locally
-  connect  connect ticlawk to a local runtime
+  connect  connect this host to Ticlawk
   profile  list or switch saved local identities
   message  send/read chat messages (agent CLI surface)
   task     claim/update/list tasks (agent CLI surface)
-  goal     report FSM transitions / signal goal changes (agent CLI surface)
-  approval canonical goal-loop approval request/resolve (agent CLI surface)
-  charter  get/set conversation goal and role spec (agent CLI surface)
-  group    create/list/delete groups, manage charters/members (agent CLI surface)
-  dashboard   set/get conversation dashboards (agent CLI surface)
-  briefing    publish/get owner briefings (agent CLI surface)
-  agent       list/create/delete owned agent slots (agent CLI surface)
-  service     publish/list/call shared services (agent CLI surface)
-  credential  request owner-filled credentials (agent CLI surface)
-  reminder    schedule/list/snooze/cancel reminders (agent CLI surface)
-  attachment  view private chat assets (agent CLI surface)
+  group    list members of a group conversation (agent CLI surface)
   server   server-info introspection (agent CLI surface)
   install-daemon  install or refresh the background daemon
   update   update the npm package and refresh the daemon
@@ -160,30 +119,15 @@ ${getRuntimeConfigExamples()}
 
 Examples:
   ticlawk connect
-  ticlawk auth --code <6-digit-code>
-`;
-}
-
-function getAuthHelp() {
-  return `ticlawk auth --code <6-digit-code> [--api-url <url>]
-
-Store the ticlawk app pairing code locally. The daemon picks it up on the
-next start and exchanges it for an API key.
-
-Options:
-  --code <code>       6-digit setup code from the ticlawk app
-  --api-url <url>     optional ticlawk API base URL override
 `;
 }
 
 function getConnectHelp() {
   return `ticlawk connect
 
-Use \`connect\` to connect the selected adapter to a local runtime.
-For ticlawk, connect starts the QR pairing flow when no local credential exists.
-Run \`ticlawk connect\` from a project directory to auto-detect
-Codex, Claude Code, opencode, and pi, then choose the runtime in ticlawk.
-No pairing QR code is shown when no local agent harness is detected.
+Use \`connect\` to authorize this machine as a Ticlawk host.
+After the host is connected, create agents from the app by choosing this host
+and one of the detected local runtimes.
 
 Examples:
   ticlawk connect
@@ -200,10 +144,6 @@ function printHelp(helpPath, args = {}) {
     printUsage();
     return;
   }
-  if (head === 'auth') {
-    console.log(getAuthHelp());
-    return;
-  }
   if (head === 'connect') {
     console.log(getConnectHelp());
     return;
@@ -216,10 +156,6 @@ function printHelp(helpPath, args = {}) {
     console.log(getInstallDaemonHelp());
     return;
   }
-  if (AGENT_COMMAND_HELP[head]) {
-    console.log(AGENT_COMMAND_HELP[head]);
-    return;
-  }
   printUsage();
 }
 
@@ -284,7 +220,7 @@ function formatSecretConfigValue(configKey, value) {
 }
 
 function buildConnectPayload(args) {
-  const legacyArgs = [
+  const rejectedArgs = [
     'adapter',
     'type',
     'session-id',
@@ -294,21 +230,19 @@ function buildConnectPayload(args) {
     'agent-id',
     'runtime-path',
     'code',
+    'name',
+    'switch-user',
   ].filter((key) => args[key] !== undefined);
   const positionalRuntime = args._?.[1];
-  if (positionalRuntime || legacyArgs.length > 0) {
+  if (positionalRuntime || rejectedArgs.length > 0) {
     const suffix = positionalRuntime ? ` ${positionalRuntime}` : '';
     console.error(`ticlawk connect${suffix} no longer accepts explicit runtime, adapter, session, or workdir arguments.`);
-    console.error('Run `ticlawk connect` from the directory you want to offer to local agent harnesses.');
-    console.error('Ticlawk will detect Codex, Claude Code, opencode, and pi locally, then let you choose in the app.');
+    console.error('Run `ticlawk connect` with no runtime arguments to authorize this host.');
+    console.error('Create agents from the app after the host is connected.');
     process.exit(1);
   }
   return {
     adapter: 'ticlawk',
-    autoRuntime: true,
-    switchUser: Boolean(args['switch-user']),
-    workdir: process.cwd(),
-    ...(args.name ? { name: args.name } : {}),
   };
 }
 
@@ -399,6 +333,24 @@ async function main() {
     process.exit(1);
   }
 
+  if (command === 'profile') {
+    const sub = args._[1];
+    if (args.help || args.h || !sub) {
+      console.log(AGENT_COMMAND_HELP.profile);
+      return;
+    }
+    if (sub === 'show') {
+      process.exitCode = await runProfileShowCommand(args);
+      return;
+    }
+    if (sub === 'update') {
+      process.exitCode = await runProfileUpdateCommand(args);
+      return;
+    }
+    console.error(`unknown profile subcommand: ${sub}`);
+    process.exit(1);
+  }
+
   if (command === 'reminder') {
     const sub = args._[1];
     if (args.help || args.h || !sub) {
@@ -477,187 +429,6 @@ async function main() {
     process.exit(1);
   }
 
-  if (command === 'goal') {
-    const sub = args._[1];
-    if (args.help || args.h || !sub) {
-      console.log(AGENT_COMMAND_HELP.goal);
-      return;
-    }
-    if (sub === 'report') {
-      process.exitCode = await runGoalReportCommand(args);
-      return;
-    }
-    if (sub === 'changed') {
-      process.exitCode = await runGoalChangedCommand(args);
-      return;
-    }
-    console.error(`unknown goal subcommand: ${sub}`);
-    process.exit(1);
-  }
-
-  if (command === 'approval') {
-    const sub = args._[1];
-    if (args.help || args.h || !sub) {
-      console.log(AGENT_COMMAND_HELP.approval);
-      return;
-    }
-    if (sub === 'request') {
-      process.exitCode = await runApprovalRequestCommand(args);
-      return;
-    }
-    if (sub === 'resolve') {
-      process.exitCode = await runApprovalResolveCommand(args);
-      return;
-    }
-    if (sub === 'list') {
-      process.exitCode = await runApprovalListCommand(args);
-      return;
-    }
-    console.error(`unknown approval subcommand: ${sub}`);
-    process.exit(1);
-  }
-
-  if (command === 'workstream') {
-    const sub = args._[1];
-    if (args.help || args.h || !sub) {
-      console.log(AGENT_COMMAND_HELP.workstream);
-      return;
-    }
-    if (sub === 'create') {
-      process.exitCode = await runWorkstreamCreateCommand(args);
-      return;
-    }
-    if (sub === 'delete') {
-      process.exitCode = await runWorkstreamDeleteCommand(args);
-      return;
-    }
-    if (sub === 'list') {
-      process.exitCode = await runWorkstreamListCommand(args);
-      return;
-    }
-    if (sub === 'charter') {
-      const op = args._[2];
-      if (op === 'get') {
-        process.exitCode = await runWorkstreamCharterGetCommand(args);
-        return;
-      }
-      if (op === 'set') {
-        process.exitCode = await runWorkstreamCharterSetCommand(args);
-        return;
-      }
-      console.error(`unknown workstream charter op: ${op}`);
-      process.exit(1);
-    }
-    console.error(`unknown workstream subcommand: ${sub}`);
-    process.exit(1);
-  }
-
-  if (command === 'agent') {
-    const sub = args._[1];
-    if (args.help || args.h || !sub) {
-      console.log(AGENT_COMMAND_HELP.agent);
-      return;
-    }
-    if (sub === 'list') {
-      process.exitCode = await runAgentListCommand(args);
-      return;
-    }
-    if (sub === 'create') {
-      process.exitCode = await runAgentCreateCommand(args);
-      return;
-    }
-    if (sub === 'delete') {
-      process.exitCode = await runAgentDeleteCommand(args);
-      return;
-    }
-    console.error(`unknown agent subcommand: ${sub}`);
-    process.exit(1);
-  }
-
-  if (command === 'service') {
-    const sub = args._[1];
-    if (args.help || args.h || !sub) {
-      console.log(AGENT_COMMAND_HELP.service);
-      return;
-    }
-    if (sub === 'create') { process.exitCode = await runServiceCreateCommand(args); return; }
-    if (sub === 'update') { process.exitCode = await runServiceUpdateCommand(args); return; }
-    if (sub === 'delete') { process.exitCode = await runServiceDeleteCommand(args); return; }
-    if (sub === 'list')   { process.exitCode = await runServiceListCommand(args); return; }
-    if (sub === 'info')   { process.exitCode = await runServiceInfoCommand(args); return; }
-    if (sub === 'call')   { process.exitCode = await runServiceCallCommand(args); return; }
-    console.error(`unknown service subcommand: ${sub}`);
-    process.exit(1);
-  }
-
-  if (command === 'briefing') {
-    const sub = args._[1];
-    if (args.help || args.h || !sub) {
-      console.log(AGENT_COMMAND_HELP.briefing);
-      return;
-    }
-    if (sub === 'publish') {
-      process.exitCode = await runBriefingPublishCommand(args);
-      return;
-    }
-    if (sub === 'get') {
-      process.exitCode = await runBriefingGetCommand(args);
-      return;
-    }
-    console.error(`unknown briefing subcommand: ${sub}`);
-    process.exit(1);
-  }
-
-  if (command === 'credential') {
-    const sub = args._[1];
-    if (args.help || args.h || !sub) {
-      console.log(AGENT_COMMAND_HELP.credential);
-      return;
-    }
-    if (sub === 'request') {
-      process.exitCode = await runCredentialRequestCommand(args);
-      return;
-    }
-    console.error(`unknown credential subcommand: ${sub}`);
-    process.exit(1);
-  }
-
-  if (command === 'dashboard') {
-    const sub = args._[1];
-    if (args.help || args.h || !sub) {
-      console.log(AGENT_COMMAND_HELP.dashboard);
-      return;
-    }
-    if (sub === 'set') {
-      process.exitCode = await runDashboardSetCommand(args);
-      return;
-    }
-    if (sub === 'get') {
-      process.exitCode = await runDashboardGetCommand(args);
-      return;
-    }
-    console.error(`unknown dashboard subcommand: ${sub}`);
-    process.exit(1);
-  }
-
-  if (command === 'charter') {
-    const sub = args._[1];
-    if (args.help || args.h || !sub) {
-      console.log(AGENT_COMMAND_HELP.charter);
-      return;
-    }
-    if (sub === 'get') {
-      process.exitCode = await runWorkstreamCharterGetCommand(args);
-      return;
-    }
-    if (sub === 'set') {
-      process.exitCode = await runWorkstreamCharterSetCommand(args);
-      return;
-    }
-    console.error(`unknown charter subcommand: ${sub}`);
-    process.exit(1);
-  }
-
   if (command === 'group') {
     const sub = args._[1];
     if (args.help || args.h || !sub) {
@@ -668,27 +439,6 @@ async function main() {
       process.exitCode = await runGroupCreateCommand(args);
       return;
     }
-    if (sub === 'list') {
-      process.exitCode = await runWorkstreamListCommand(args);
-      return;
-    }
-    if (sub === 'delete') {
-      process.exitCode = await runWorkstreamDeleteCommand(args);
-      return;
-    }
-    if (sub === 'charter') {
-      const op = args._[2];
-      if (op === 'get') {
-        process.exitCode = await runWorkstreamCharterGetCommand(args);
-        return;
-      }
-      if (op === 'set') {
-        process.exitCode = await runWorkstreamCharterSetCommand(args);
-        return;
-      }
-      console.error(`unknown group charter op: ${op}`);
-      process.exit(1);
-    }
     if (sub === 'members') {
       // Same subcommand handles list / add / remove based on flags.
       if (args.add) {
@@ -831,14 +581,6 @@ async function main() {
       console.log('Restart ticlawk for the daemon to use the selected profile.');
       return;
     }
-    if (subcommand === 'show') {
-      process.exitCode = await runProfileShowCommand(args);
-      return;
-    }
-    if (subcommand === 'update') {
-      process.exitCode = await runProfileUpdateCommand(args);
-      return;
-    }
     console.error(`unknown profile subcommand: ${subcommand}`);
     process.exit(1);
   }
@@ -871,18 +613,6 @@ async function main() {
     return;
   }
 
-  if (command === 'auth') {
-    if (args.help || args.h) {
-      printHelp(['auth'], args);
-      return;
-    }
-    const adapterArgv = rawArgv.slice(1);
-    const res = await runAdapterAuth('ticlawk', adapterArgv);
-    printCommandResult(res);
-    process.exitCode = res.statusCode >= 400 ? 1 : 0;
-    return;
-  }
-
   if (command === 'connect') {
     if (args.help || args.h) {
       console.log(getConnectHelp());

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "ticlawk",
-  "version": "0.1.17-dev.2",
+  "version": "0.1.17-dev.20",
   "description": "Local connector that links agent harnesses (Claude Code, Codex, OpenClaw, opencode, Pi) to the Ticlawk mobile app.",
   "type": "module",
   "main": "ticlawk.mjs",
@@ -15,6 +15,7 @@
     "assets/",
     "bin/",
     "scripts/postinstall.mjs",
+    "scripts/publish-dev.sh",
     "src/",
     "cc-watcher.mjs",
     "ticlawk.mjs",
@@ -33,7 +34,8 @@
     "health": "node ./bin/ticlawk.mjs health",
     "dev": "echo 'Configure ~/.ticlawk/.config, then: npm run start'",
     "generate:usage-docs": "node scripts/generate-usage-docs.mjs",
-    "verify:public-package": "bash scripts/verify-ticlawk-public.sh"
+    "verify:public-package": "bash scripts/verify-ticlawk-public.sh",
+    "publish:dev": "bash scripts/publish-dev.sh"
   },
   "repository": {
     "type": "git",