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>
This commit is contained in:
LinYushen 2026-03-31 13:48:39 +08:00 committed by GitHub
parent 5517136d73
commit 961de18c97
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
15 changed files with 150 additions and 80 deletions

View file

@ -32,7 +32,7 @@ WHERE id = (
LIMIT 1
FOR UPDATE SKIP LOCKED
)
RETURNING id, agent_id, issue_id, status, priority, dispatched_at, started_at, completed_at, result, error, created_at, context, runtime_id, session_id, work_dir
RETURNING id, agent_id, issue_id, status, priority, dispatched_at, started_at, completed_at, result, error, created_at, context, runtime_id, session_id, work_dir, trigger_comment_id
`
func (q *Queries) ClaimAgentTask(ctx context.Context, agentID pgtype.UUID) (AgentTaskQueue, error) {
@ -54,6 +54,7 @@ func (q *Queries) ClaimAgentTask(ctx context.Context, agentID pgtype.UUID) (Agen
&i.RuntimeID,
&i.SessionID,
&i.WorkDir,
&i.TriggerCommentID,
)
return i, err
}
@ -62,7 +63,7 @@ const completeAgentTask = `-- name: CompleteAgentTask :one
UPDATE agent_task_queue
SET status = 'completed', completed_at = now(), result = $2, session_id = $3, work_dir = $4
WHERE id = $1 AND status = 'running'
RETURNING id, agent_id, issue_id, status, priority, dispatched_at, started_at, completed_at, result, error, created_at, context, runtime_id, session_id, work_dir
RETURNING id, agent_id, issue_id, status, priority, dispatched_at, started_at, completed_at, result, error, created_at, context, runtime_id, session_id, work_dir, trigger_comment_id
`
type CompleteAgentTaskParams struct {
@ -96,6 +97,7 @@ func (q *Queries) CompleteAgentTask(ctx context.Context, arg CompleteAgentTaskPa
&i.RuntimeID,
&i.SessionID,
&i.WorkDir,
&i.TriggerCommentID,
)
return i, err
}
@ -177,16 +179,17 @@ func (q *Queries) CreateAgent(ctx context.Context, arg CreateAgentParams) (Agent
}
const createAgentTask = `-- name: CreateAgentTask :one
INSERT INTO agent_task_queue (agent_id, runtime_id, issue_id, status, priority)
VALUES ($1, $2, $3, 'queued', $4)
RETURNING id, agent_id, issue_id, status, priority, dispatched_at, started_at, completed_at, result, error, created_at, context, runtime_id, session_id, work_dir
INSERT INTO agent_task_queue (agent_id, runtime_id, issue_id, status, priority, trigger_comment_id)
VALUES ($1, $2, $3, 'queued', $4, $5)
RETURNING id, agent_id, issue_id, status, priority, dispatched_at, started_at, completed_at, result, error, created_at, context, runtime_id, session_id, work_dir, trigger_comment_id
`
type CreateAgentTaskParams struct {
AgentID pgtype.UUID `json:"agent_id"`
RuntimeID pgtype.UUID `json:"runtime_id"`
IssueID pgtype.UUID `json:"issue_id"`
Priority int32 `json:"priority"`
AgentID pgtype.UUID `json:"agent_id"`
RuntimeID pgtype.UUID `json:"runtime_id"`
IssueID pgtype.UUID `json:"issue_id"`
Priority int32 `json:"priority"`
TriggerCommentID pgtype.UUID `json:"trigger_comment_id"`
}
func (q *Queries) CreateAgentTask(ctx context.Context, arg CreateAgentTaskParams) (AgentTaskQueue, error) {
@ -195,6 +198,7 @@ func (q *Queries) CreateAgentTask(ctx context.Context, arg CreateAgentTaskParams
arg.RuntimeID,
arg.IssueID,
arg.Priority,
arg.TriggerCommentID,
)
var i AgentTaskQueue
err := row.Scan(
@ -213,6 +217,7 @@ func (q *Queries) CreateAgentTask(ctx context.Context, arg CreateAgentTaskParams
&i.RuntimeID,
&i.SessionID,
&i.WorkDir,
&i.TriggerCommentID,
)
return i, err
}
@ -230,7 +235,7 @@ const failAgentTask = `-- name: FailAgentTask :one
UPDATE agent_task_queue
SET status = 'failed', completed_at = now(), error = $2
WHERE id = $1 AND status IN ('dispatched', 'running')
RETURNING id, agent_id, issue_id, status, priority, dispatched_at, started_at, completed_at, result, error, created_at, context, runtime_id, session_id, work_dir
RETURNING id, agent_id, issue_id, status, priority, dispatched_at, started_at, completed_at, result, error, created_at, context, runtime_id, session_id, work_dir, trigger_comment_id
`
type FailAgentTaskParams struct {
@ -257,6 +262,7 @@ func (q *Queries) FailAgentTask(ctx context.Context, arg FailAgentTaskParams) (A
&i.RuntimeID,
&i.SessionID,
&i.WorkDir,
&i.TriggerCommentID,
)
return i, err
}
@ -369,7 +375,7 @@ func (q *Queries) GetAgentInWorkspace(ctx context.Context, arg GetAgentInWorkspa
}
const getAgentTask = `-- name: GetAgentTask :one
SELECT id, agent_id, issue_id, status, priority, dispatched_at, started_at, completed_at, result, error, created_at, context, runtime_id, session_id, work_dir FROM agent_task_queue
SELECT id, agent_id, issue_id, status, priority, dispatched_at, started_at, completed_at, result, error, created_at, context, runtime_id, session_id, work_dir, trigger_comment_id FROM agent_task_queue
WHERE id = $1
`
@ -392,6 +398,7 @@ func (q *Queries) GetAgentTask(ctx context.Context, id pgtype.UUID) (AgentTaskQu
&i.RuntimeID,
&i.SessionID,
&i.WorkDir,
&i.TriggerCommentID,
)
return i, err
}
@ -452,7 +459,7 @@ func (q *Queries) HasPendingTaskForIssue(ctx context.Context, issueID pgtype.UUI
}
const listActiveTasksByIssue = `-- name: ListActiveTasksByIssue :many
SELECT id, agent_id, issue_id, status, priority, dispatched_at, started_at, completed_at, result, error, created_at, context, runtime_id, session_id, work_dir FROM agent_task_queue
SELECT id, agent_id, issue_id, status, priority, dispatched_at, started_at, completed_at, result, error, created_at, context, runtime_id, session_id, work_dir, trigger_comment_id FROM agent_task_queue
WHERE issue_id = $1 AND status IN ('dispatched', 'running')
ORDER BY created_at DESC
`
@ -482,6 +489,7 @@ func (q *Queries) ListActiveTasksByIssue(ctx context.Context, issueID pgtype.UUI
&i.RuntimeID,
&i.SessionID,
&i.WorkDir,
&i.TriggerCommentID,
); err != nil {
return nil, err
}
@ -494,7 +502,7 @@ func (q *Queries) ListActiveTasksByIssue(ctx context.Context, issueID pgtype.UUI
}
const listAgentTasks = `-- name: ListAgentTasks :many
SELECT id, agent_id, issue_id, status, priority, dispatched_at, started_at, completed_at, result, error, created_at, context, runtime_id, session_id, work_dir FROM agent_task_queue
SELECT id, agent_id, issue_id, status, priority, dispatched_at, started_at, completed_at, result, error, created_at, context, runtime_id, session_id, work_dir, trigger_comment_id FROM agent_task_queue
WHERE agent_id = $1
ORDER BY created_at DESC
`
@ -524,6 +532,7 @@ func (q *Queries) ListAgentTasks(ctx context.Context, agentID pgtype.UUID) ([]Ag
&i.RuntimeID,
&i.SessionID,
&i.WorkDir,
&i.TriggerCommentID,
); err != nil {
return nil, err
}
@ -580,7 +589,7 @@ func (q *Queries) ListAgents(ctx context.Context, workspaceID pgtype.UUID) ([]Ag
}
const listPendingTasksByRuntime = `-- name: ListPendingTasksByRuntime :many
SELECT id, agent_id, issue_id, status, priority, dispatched_at, started_at, completed_at, result, error, created_at, context, runtime_id, session_id, work_dir FROM agent_task_queue
SELECT id, agent_id, issue_id, status, priority, dispatched_at, started_at, completed_at, result, error, created_at, context, runtime_id, session_id, work_dir, trigger_comment_id FROM agent_task_queue
WHERE runtime_id = $1 AND status IN ('queued', 'dispatched')
ORDER BY priority DESC, created_at ASC
`
@ -610,6 +619,7 @@ func (q *Queries) ListPendingTasksByRuntime(ctx context.Context, runtimeID pgtyp
&i.RuntimeID,
&i.SessionID,
&i.WorkDir,
&i.TriggerCommentID,
); err != nil {
return nil, err
}
@ -622,7 +632,7 @@ func (q *Queries) ListPendingTasksByRuntime(ctx context.Context, runtimeID pgtyp
}
const listTasksByIssue = `-- name: ListTasksByIssue :many
SELECT id, agent_id, issue_id, status, priority, dispatched_at, started_at, completed_at, result, error, created_at, context, runtime_id, session_id, work_dir FROM agent_task_queue
SELECT id, agent_id, issue_id, status, priority, dispatched_at, started_at, completed_at, result, error, created_at, context, runtime_id, session_id, work_dir, trigger_comment_id FROM agent_task_queue
WHERE issue_id = $1
ORDER BY created_at DESC
`
@ -652,6 +662,7 @@ func (q *Queries) ListTasksByIssue(ctx context.Context, issueID pgtype.UUID) ([]
&i.RuntimeID,
&i.SessionID,
&i.WorkDir,
&i.TriggerCommentID,
); err != nil {
return nil, err
}
@ -667,7 +678,7 @@ const startAgentTask = `-- name: StartAgentTask :one
UPDATE agent_task_queue
SET status = 'running', started_at = now()
WHERE id = $1 AND status = 'dispatched'
RETURNING id, agent_id, issue_id, status, priority, dispatched_at, started_at, completed_at, result, error, created_at, context, runtime_id, session_id, work_dir
RETURNING id, agent_id, issue_id, status, priority, dispatched_at, started_at, completed_at, result, error, created_at, context, runtime_id, session_id, work_dir, trigger_comment_id
`
func (q *Queries) StartAgentTask(ctx context.Context, id pgtype.UUID) (AgentTaskQueue, error) {
@ -689,6 +700,7 @@ func (q *Queries) StartAgentTask(ctx context.Context, id pgtype.UUID) (AgentTask
&i.RuntimeID,
&i.SessionID,
&i.WorkDir,
&i.TriggerCommentID,
)
return i, err
}