feat(agents): reply as thread instead of top-level comment (#205)

* feat(agents): reply as thread instead of top-level comment

When an agent responds to a user comment, the reply is now nested under
the triggering comment (parent_id) instead of appearing as a separate
top-level comment. Also enables on_comment trigger by default for newly
created agents.

- Add trigger_comment_id column to agent_task_queue (migration 028)
- Pass triggering comment ID through EnqueueTaskForIssue → task → createAgentComment
- Include parent_id in WebSocket broadcast for agent comments
- Default agent creation includes both on_assign and on_comment triggers

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* feat(cli): add --parent flag to comment add for threaded replies

The agent posts comments via the CLI, so the correct fix is giving it a
--parent flag rather than wiring trigger_comment_id through the task
infrastructure. The agent reads the comment list, decides which comment
to reply to, and passes --parent <comment-id>.

- Add --parent flag to `multica issue comment add`
- Update agent runtime instructions to explain --parent usage

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* feat(daemon): pass trigger_comment_id to agent execution context

The agent now knows which comment triggered its task and gets an explicit
instruction to reply to it using --parent. The trigger_comment_id flows
from the DB through the claim response, daemon Task struct, and into
issue_context.md where the agent sees it.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix(comments): agent replies to thread root, matching frontend behavior

When the triggering comment is itself a reply (has parent_id), resolve
to the thread root so the agent's reply stays in the same flat thread.
This matches the frontend where all replies share the top-level parent.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* feat(cli): show parent_id and full IDs in comment list

The table output now includes a PARENT column and shows full comment IDs
(not truncated) so agents can see thread structure and use --parent.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* feat(daemon): instruct agents to always use --output json

Agents now see explicit guidance to use --output json for all read
commands, ensuring they get structured data with full IDs and parent_id
for proper threading.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* feat(daemon): differentiate comment-trigger vs assign-trigger context

When triggered by a comment, the agent now gets clear instructions:
- Primary goal is to read and respond to the comment
- Do NOT change issue status just because you replied
- Only change status if explicitly requested

This prevents the agent from seeing "In Review" and stopping, since
it now understands the task is to reply, not to re-evaluate the issue.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix(daemon): split workflow by trigger type in CLAUDE.md/AGENTS.md

The Workflow section in the agent's runtime config now shows a
comment-reply workflow when triggered by a comment (read comments,
find trigger, reply, don't change status) vs the full assignment
workflow (set in_progress, do work, set in_review).

Previously the agent always saw the assignment workflow, causing it
to check the issue status, see "In Review", and stop without reading
or replying to the triggering comment.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* refactor(daemon): remove duplicate workflow from issue_context.md

Workflow instructions now live only in CLAUDE.md/AGENTS.md (runtime_config.go).
issue_context.md keeps just the task data: issue ID, trigger type, and
triggering comment ID.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix(task): skip duplicate comment on completion for comment-triggered tasks

When triggered by a comment, the agent posts its own reply via CLI
with --parent. The task completion path was also creating a comment
from the agent's stdout output, resulting in duplicates. Now only
assignment-triggered tasks auto-post output as a comment. Error
messages from FailTask are still posted regardless of trigger type.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

server/internal/handler/agent.go

@@ -104,8 +104,9 @@ type AgentTaskResponse struct {
 	Agent          *TaskAgentData `json:"agent,omitempty"`
 	Repos          []RepoData     `json:"repos,omitempty"`
 	CreatedAt      string         `json:"created_at"`
-	PriorSessionID string         `json:"prior_session_id,omitempty"` // session ID from a previous task on same issue
-	PriorWorkDir   string         `json:"prior_work_dir,omitempty"`   // work_dir from a previous task on same issue
+	PriorSessionID   string         `json:"prior_session_id,omitempty"`    // session ID from a previous task on same issue
+	PriorWorkDir     string         `json:"prior_work_dir,omitempty"`     // work_dir from a previous task on same issue
+	TriggerCommentID *string        `json:"trigger_comment_id,omitempty"` // comment that triggered this task
 }
 
 // TaskAgentData holds agent info included in claim responses so the daemon
@@ -133,8 +134,9 @@ func taskToResponse(t db.AgentTaskQueue) AgentTaskResponse {
 		StartedAt:    timestampToPtr(t.StartedAt),
 		CompletedAt:  timestampToPtr(t.CompletedAt),
 		Result:       result,
-		Error:        textToPtr(t.Error),
-		CreatedAt:    timestampToString(t.CreatedAt),
+		Error:            textToPtr(t.Error),
+		CreatedAt:        timestampToString(t.CreatedAt),
+		TriggerCommentID: uuidToPtr(t.TriggerCommentID),
 	}
 }
 

server/internal/handler/comment.go

@@ -146,7 +146,14 @@ func (h *Handler) CreateComment(w http.ResponseWriter, r *http.Request) {
 	// If the issue is assigned to an agent with on_comment trigger, enqueue a new task.
 	// Skip when the comment comes from the assigned agent itself to avoid loops.
 	if authorType == "member" && h.shouldEnqueueOnComment(r.Context(), issue) {
-		if _, err := h.TaskService.EnqueueTaskForIssue(r.Context(), issue); err != nil {
+		// Resolve thread root: if the comment is a reply, agent should reply
+		// to the thread root (matching frontend behavior where all replies
+		// in a thread share the same top-level parent).
+		replyTo := comment.ID
+		if comment.ParentID.Valid {
+			replyTo = comment.ParentID
+		}
+		if _, err := h.TaskService.EnqueueTaskForIssue(r.Context(), issue, replyTo); err != nil {
 			slog.Warn("enqueue agent task on comment failed", "issue_id", issueID, "error", err)
 		}
 	}