ticlawk 0.1.17-dev.14 → 0.1.17-dev.16

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "ticlawk",
-  "version": "0.1.17-dev.14",
+  "version": "0.1.17-dev.16",
   "description": "Local connector that links agent harnesses (Claude Code, Codex, OpenClaw, opencode, Pi) to the Ticlawk mobile app.",
   "type": "module",
   "main": "ticlawk.mjs",

package/src/cli/agent-commands.mjs

@@ -241,7 +241,9 @@ export async function runMessageReadCommand(args) {
 export async function runTaskCreateCommand(args) {
   const env = requireAgentEnv();
   const target = getArg(args, 'target');
-  const conversationId = getArg(args, 'conversation-id');
+  // Default to the conversation this turn is running for (the daemon sets it).
+  // Lets a goal-lane step just `task create --title ...` without addressing.
+  const conversationId = getArg(args, 'conversation') || getArg(args, 'conversation-id') || env.currentConversationId;
   if (!target && !conversationId) {
     console.error('--target or --conversation-id is required');
     return 2;
@@ -276,7 +278,7 @@ export async function runTaskClaimCommand(args) {
   const messageId = getArg(args, 'message-id');
   const number = getNumberArg(args, 'number');
   const target = getArg(args, 'target');
-  const conversationId = getArg(args, 'conversation-id');
+  const conversationId = getArg(args, 'conversation') || getArg(args, 'conversation-id') || env.currentConversationId;
   if (!messageId && number == null) {
     console.error('--message-id or --number is required');
     return 2;
@@ -465,7 +467,10 @@ export async function runTaskListCommand(args) {
   const env = requireAgentEnv();
   const params = new URLSearchParams();
   const target = getArg(args, 'target');
-  const conversationId = getArg(args, 'conversation-id');
+  // No filter given → scope to the conversation this turn runs for, instead
+  // of dumping tasks from every conversation the owner can see.
+  const conversationId = getArg(args, 'conversation') || getArg(args, 'conversation-id')
+    || (target ? null : env.currentConversationId);
   if (target) params.set('target', target);
   if (conversationId) params.set('conversation_id', conversationId);
   const res = await daemonRequest({
@@ -1416,9 +1421,11 @@ export const AGENT_COMMAND_HELP = {
       --in-minutes 1 --recur-at 18:30 --recur-weekday 1,2,3,4,5
 `,
   task: `ticlawk task <create|claim|unclaim|update|list>
-  ticlawk task create --target "<target>" [--title <t>] [--assign-agent <agent-id>]
+  ticlawk task create [--conversation <id>|--target "<target>"] [--title <t>] [--assign-agent <agent-id>]
     Body is read from stdin. Creates a brand-new group task. Group admins
     may assign it immediately to an agent member with --assign-agent.
+    Conversation defaults to the one this turn is running for; pass
+    --conversation <id> (or --target) only to address a different one.
   ticlawk task claim --message-id <id> [--lease-seconds N]
   ticlawk task claim --number <N> --target "<target>" [--lease-seconds N]
   ticlawk task unclaim --task-id <id>
@@ -1426,11 +1433,11 @@ export const AGENT_COMMAND_HELP = {
     Only a group admin can set status=done. Other agents should set
     in_review and let the group's admin finalize. A group admin can also
     reopen another agent's in_review task to in_progress for redo.
-  ticlawk task list [--target <target>|--conversation-id <id>]
-    Default view is open tasks plus tasks owned by the caller. When the
-    caller is a group admin and --target/--conversation-id scopes the
-    request to that group, the list shows the full task board, including
-    other agents' in_progress, in_review, and done tasks.
+  ticlawk task list [--conversation <id>|--target <target>]
+    Scopes to the conversation this turn runs for by default; pass
+    --conversation <id> (or --target) to look at a different one. When the
+    caller is a group admin and the scope is that group, the list shows the
+    full task board, including other agents' in_progress/in_review/done tasks.
 `,
   workstream: `ticlawk workstream <create|delete|list|charter>
     Compatibility alias for group admin commands. Prefer \`ticlawk group ...\`

package/src/core/agent-cli-handlers.mjs

@@ -50,6 +50,13 @@ export function invalidateServerInfoCache(actingAgentId = null) {
 export async function resolveTarget(actingAgentId, target) {
   if (!target) return { conversationId: null, replyToMessageId: null, error: 'target is required' };
 
+  // `conv:<uuid>` — an explicit conversation by id (the intuitive first guess).
+  // Handled before the generic colon-split so the uuid isn't mistaken for a
+  // reply-message suffix.
+  if (/^conv:[0-9a-f-]{36}$/i.test(target)) {
+    return { conversationId: target.slice(5), replyToMessageId: null, error: null };
+  }
+
   // Strip optional message-reply suffix.
   let base = target;
   let replyToMessageId = null;

package/src/runtimes/_shared/goal-step-prompt.mjs

@@ -111,7 +111,7 @@ export function buildGoalStepPrompt(msg) {
       `  ${reportCmd}`,
       ``,
       `Reporting the outcome continues the loop: a running next state comes back as a fresh step; with no gap or a wait, the loop parks itself. Report exactly once — do not loop inside this turn.`,
-      `Reach the owner only through two surfaces: \`ticlawk dashboard set\` (the goal report — routine progress, the owner pulls it) and \`ticlawk briefing publish\` (a scarce push, per the rule above). The goal lane never uses \`ticlawk message send\` — chat is the chat lane's. Write owner-facing text for someone reading cold who has never seen your plan or task board: what changed, why it matters, and what (if anything) they must do — naming things by what they are, never by a private code, run name, or task number.`,
+      `Reach the owner only through two surfaces: \`ticlawk dashboard set\` (the goal report — routine progress, the owner pulls it) and \`ticlawk briefing publish\` (a scarce push, per the rule above). The goal lane never uses \`ticlawk message send\` — chat is the chat lane's. Write owner-facing text for someone reading cold who has never seen your plan or task board: what changed, why it matters, and what (if anything) they must do — naming things by what they are, never exposing how the system works inside or how your work is organized behind the scenes (tracks, loops, internal states, codes, run names, task numbers).`,
       `[/goal_step]`,
     ].join('\n'));
   } else {

package/src/runtimes/_shared/standing-prompt.mjs

@@ -97,6 +97,12 @@ Schedule a reminder for time-based follow-up. For a fixed cadence, use ONE recur
 - \`ticlawk reminder schedule --title <t> (--fire-at <iso>|--in-seconds N|--in-minutes N) (--target <target>|--anchor-conversation-id <id>) [--recur-at HH:MM] [--recur-weekday 1,2,3]\` — schedule a reminder. \`--recur-at\` is the owner's local wall-clock; the system fills the timezone. On each fire, a recurring reminder auto-advances.`;
 }
 
+// The lane breakdown above is how YOU operate — your own model. It is never
+// something to explain to a person. When someone asks what you do or what your
+// role is, answer by what you help them accomplish, not by how the system is
+// built.
+const INTERNAL_MODEL_NOTE = `This split is your own operating model — never something to explain to a person. When the owner asks what you do or what your role is, answer by what you help them accomplish, not by how the system is built.`;
+
 // ---------------------------------------------------------------------------
 // Chat-authority (DM or group admin/owner)
 // ---------------------------------------------------------------------------
@@ -124,7 +130,9 @@ function chatAuthorityOverviewBlock(ctx) {
   return `${whereLine} The conversation is part of an agent system that drives itself to achieve a goal. It has two components:
 
 ${goalLaneBullet}
-${chatLaneBullet}`;
+${chatLaneBullet}
+
+${INTERNAL_MODEL_NOTE}`;
 }
 
 function chatAuthorityMessagingSubsection(ctx) {
@@ -135,7 +143,7 @@ function chatAuthorityMessagingSubsection(ctx) {
     : '';
   return `### Messaging
 
-You reply to incoming messages with \`ticlawk message send\`. Pass body via stdin or heredoc so quotes and code blocks survive. The body is plain natural language — never include an internal code, run name, or task number the recipient has no context for.
+You reply to incoming messages with \`ticlawk message send\`. Pass body via stdin or heredoc so quotes and code blocks survive. The body is plain natural language. Never expose how the system works inside or how your work is organized behind the scenes (tracks, loops, internal states, codes, run names, task numbers) — none of it means anything to them.
 
 - \`ticlawk message send --target <target> --phase progress|final [--attach <path>]\` — send a reply. Copy \`<target>\` from the incoming message verbatim. Body via stdin. Use \`--phase progress\` for any intermediate update and \`--phase final\` for the last message of the turn; after the final send succeeds, output exactly \`<turn_end>\` and stop.
 - \`ticlawk message read --target <target> [--around <message-id>]\` — recent chat context, or context around one specific message.
@@ -201,13 +209,15 @@ function chatWorkerOverviewBlock(ctx) {
   return `You are in a group chat named ${groupLabel} as a member, not the admin. The group is part of an agent system that drives itself to achieve a goal. It has two components:
 
 - Goal lane — backend state machine that pursues the goal, owned by the group admin. It runs on its own; you don't drive it.
-- Chat lane — where you are right now. Your job is to take tasks the admin or owner assigns to you and execute them. You don't set goals or touch the admin-owned surfaces (charter, dashboard, briefings, membership). You send messages to external recipients with \`ticlawk message send\`, and you execute work through \`ticlawk task claim\` / \`ticlawk task update\`.`;
+- Chat lane — where you are right now. Your job is to take tasks the admin or owner assigns to you and execute them. You don't set goals or touch the admin-owned surfaces (charter, dashboard, briefings, membership). You send messages to external recipients with \`ticlawk message send\`, and you execute work through \`ticlawk task claim\` / \`ticlawk task update\`.
+
+${INTERNAL_MODEL_NOTE}`;
 }
 
 function chatWorkerMessagingSubsection() {
   return `### Messaging
 
-You reply to incoming messages with \`ticlawk message send\`. Pass body via stdin or heredoc so quotes and code blocks survive. The body is plain natural language — never include an internal code, run name, or task number the recipient has no context for.
+You reply to incoming messages with \`ticlawk message send\`. Pass body via stdin or heredoc so quotes and code blocks survive. The body is plain natural language. Never expose how the system works inside or how your work is organized behind the scenes (tracks, loops, internal states, codes, run names, task numbers) — none of it means anything to them.
 
 - \`ticlawk message send --target <target> --phase progress|final [--attach <path>]\` — send a reply. Copy \`<target>\` from the incoming message verbatim. Body via stdin. Use \`--phase progress\` for any intermediate update and \`--phase final\` for the last message of the turn; after the final send succeeds, output exactly \`<turn_end>\` and stop.
 - \`ticlawk message read --target <target> [--around <message-id>]\` — recent chat context, or context around one specific message.
@@ -261,7 +271,7 @@ Do only what this step requires; leave work for other steps to those steps. The
 function goalLaneOwnerSurfacesSubsection() {
   return `### Owner surfaces (dashboard + briefing)
 
-You reach the owner only through dashboard (pull) and briefing (push). You do NOT use \`ticlawk message send\` — chat is the chat lane's. Write what changed and why it matters in plain language; refer to things by what they are and do, never by an internal code, run name, or task number.
+You reach the owner only through dashboard (pull) and briefing (push). You do NOT use \`ticlawk message send\` — chat is the chat lane's. Write what changed and why it matters in plain language; refer to things by what they are and do, never exposing how the system works inside or how your work is organized behind the scenes (tracks, loops, internal states, codes, run names, task numbers).
 
 Dashboard is the owner's at-a-glance progress report. Design it during goal setup (or when first needed), keep the design stable, update content as progress moves; redesign only when the goal, metrics, or main focus changes materially. Briefings are scarce pushes that interrupt the owner: send only when the owner must act or decide (\`--mode approval\`), asked to be told (\`--mode info\`), or would be wrong not to know now — goal done, blocked, materially off-track, or a result they are waiting on (\`--mode info\`).