Files
2aad9842a9 MUL-6891, MUL-7048: fix(agents): preserve presence for hidden private runtimes (#7830)
* fix(agents): preserve presence for hidden private runtimes

Co-authored-by: multica-agent <[email protected]>

* test: trim hidden-runtime regression fixtures

Co-authored-by: multica-agent <[email protected]>

* fix(agents): use coarse hidden runtime availability

Co-authored-by: multica-agent <[email protected]>

* fix(agents): refresh unstable availability

Co-authored-by: multica-agent <[email protected]>

* fix(agents): omit visible runtime availability

Co-authored-by: multica-agent <[email protected]>

* fix(agents): poll projected availability on all clients

Co-authored-by: multica-agent <[email protected]>

* fix(runtimes): stop availability polling once every projection is offline

Polling now runs at 30s only while at least one agent's projected
runtime_availability is online or unstable. A stable offline projection
stops polling; recovery is already covered by daemon:register and
reconnect invalidating the agents query.

Co-authored-by: multica-agent <[email protected]>

* fix(agents): publish heartbeat recovery refreshes

* fix(agents): keep projected availability polling

Co-authored-by: multica-agent <[email protected]>

* fix(agents): bound recovery and projection polling

Co-authored-by: multica-agent <[email protected]>

* fix(agents): stop polling stable offline projections

Co-authored-by: multica-agent <[email protected]>

* fix(agents): align projected presence signals

Co-authored-by: multica-agent <[email protected]>

---------

Co-authored-by: multica-agent <[email protected]>
Co-authored-by: worker-opencode <[email protected]>
Co-authored-by: Sol-Boy <[email protected]>
2026-09-04 15:39:38 +08:00

1244 lines
44 KiB
Go

package handler
import (
"context"
"encoding/json"
"log/slog"
"net/http"
"strconv"
"time"
"github.com/go-chi/chi/v5"
"github.com/jackc/pgx/v5/pgtype"
"github.com/multica-ai/multica/server/internal/analytics"
"github.com/multica-ai/multica/server/internal/logger"
obsmetrics "github.com/multica-ai/multica/server/internal/metrics"
"github.com/multica-ai/multica/server/internal/util"
db "github.com/multica-ai/multica/server/pkg/db/generated"
"github.com/multica-ai/multica/server/pkg/dbid"
"github.com/multica-ai/multica/server/pkg/protocol"
)
// ── Response types ──────────────────────────────────────────────────────────
type SquadResponse struct {
ID string `json:"id"`
WorkspaceID string `json:"workspace_id"`
Name string `json:"name"`
Description string `json:"description"`
Instructions string `json:"instructions"`
AvatarURL *string `json:"avatar_url"`
LeaderID string `json:"leader_id"`
CreatorID string `json:"creator_id"`
CreatedAt string `json:"created_at"`
UpdatedAt string `json:"updated_at"`
ArchivedAt *string `json:"archived_at"`
ArchivedBy *string `json:"archived_by"`
MemberCount int `json:"member_count"`
MemberPreview []SquadMemberPreviewResponse `json:"member_preview"`
}
type SquadMemberPreviewResponse struct {
MemberType string `json:"member_type"`
MemberID string `json:"member_id"`
Role string `json:"role"`
}
type squadMemberSummary struct {
count int
preview []SquadMemberPreviewResponse
}
type SquadMemberResponse struct {
ID string `json:"id"`
SquadID string `json:"squad_id"`
MemberType string `json:"member_type"`
MemberID string `json:"member_id"`
Role string `json:"role"`
CreatedAt string `json:"created_at"`
}
// ── Converters ──────────────────────────────────────────────────────────────
func (h *Handler) squadToResponse(s db.Squad) SquadResponse {
return SquadResponse{
ID: uuidToString(s.ID),
WorkspaceID: uuidToString(s.WorkspaceID),
Name: s.Name,
Description: s.Description,
Instructions: s.Instructions,
AvatarURL: h.resolveAvatarURLPtr(textToPtr(s.AvatarUrl)),
LeaderID: uuidToString(s.LeaderID),
CreatorID: uuidToString(s.CreatorID),
CreatedAt: timestampToString(s.CreatedAt),
UpdatedAt: timestampToString(s.UpdatedAt),
ArchivedAt: timestampToPtr(s.ArchivedAt),
ArchivedBy: uuidToPtr(s.ArchivedBy),
MemberPreview: []SquadMemberPreviewResponse{},
}
}
func squadMemberToResponse(m db.SquadMember) SquadMemberResponse {
return SquadMemberResponse{
ID: uuidToString(m.ID),
SquadID: uuidToString(m.SquadID),
MemberType: m.MemberType,
MemberID: uuidToString(m.MemberID),
Role: m.Role,
CreatedAt: timestampToString(m.CreatedAt),
}
}
func addSquadMemberPreview(summary *squadMemberSummary, memberType string, memberID pgtype.UUID, role string) {
summary.count++
if len(summary.preview) >= 3 {
return
}
summary.preview = append(summary.preview, SquadMemberPreviewResponse{
MemberType: memberType,
MemberID: uuidToString(memberID),
Role: role,
})
}
func applySquadMemberSummary(resp *SquadResponse, summary *squadMemberSummary) {
if summary == nil {
return
}
resp.MemberCount = summary.count
resp.MemberPreview = summary.preview
}
// ── Helpers ─────────────────────────────────────────────────────────────────
// canManageSquad reports whether the member may mutate the squad. Workspace
// owner/admin manage every squad; a regular member manages only the squads
// they created. Squads stay creator-scoped for management while remaining
// visible workspace-wide (ListSquads is unfiltered). Mirrors the front-end
// per-squad `canManage` gate so the UI and API agree on who can rename / add
// members / archive (MUL-4223).
func canManageSquad(member db.Member, squad db.Squad) bool {
if roleAllowed(member.Role, "owner", "admin") {
return true
}
return uuidToString(squad.CreatorID) == uuidToString(member.UserID)
}
// memberCanWireAgent reports whether the acting member may attach the given
// agent to a squad (as leader or worker). Workspace owner/admin may wire any
// workspace agent — their management surface is unchanged. A regular member
// (a creator managing their own squad) may only wire agents they can
// @-trigger: canInvokeAgent judged as the member themselves, so public_to
// agents on their allow-list and their own private agents pass, while other
// members' private / non-allow-listed agents are rejected. This stops a
// creator from smuggling an agent they cannot invoke into a squad and reaching
// it through squad routing (MUL-4223).
func (h *Handler) memberCanWireAgent(ctx context.Context, member db.Member, agent db.Agent, workspaceID string) bool {
if roleAllowed(member.Role, "owner", "admin") {
return true
}
uid := uuidToString(member.UserID)
return h.canInvokeAgent(ctx, agent, "member", uid, uid, workspaceID)
}
// loadSquadInWorkspace loads a squad scoped to the current workspace.
func (h *Handler) loadSquadInWorkspace(w http.ResponseWriter, r *http.Request) (db.Squad, string, bool) {
workspaceID := workspaceIDFromURL(r, "workspaceId")
squadID := chi.URLParam(r, "id")
squadUUID, ok := parseUUIDOrBadRequest(w, squadID, "squad id")
if !ok {
return db.Squad{}, "", false
}
wsUUID, ok := parseUUIDOrBadRequest(w, workspaceID, "workspace_id")
if !ok {
return db.Squad{}, "", false
}
squad, err := h.Queries.GetSquadInWorkspace(r.Context(), db.GetSquadInWorkspaceParams{
ID: squadUUID,
WorkspaceID: wsUUID,
})
if err != nil {
writeError(w, http.StatusNotFound, "squad not found")
return db.Squad{}, "", false
}
return squad, workspaceID, true
}
func (h *Handler) loadSquadMemberSummary(ctx context.Context, squadID pgtype.UUID) (*squadMemberSummary, error) {
rows, err := h.Queries.ListSquadMemberPreviewRowsBySquad(ctx, squadID)
if err != nil {
return nil, err
}
summary := &squadMemberSummary{}
for _, row := range rows {
addSquadMemberPreview(summary, row.MemberType, row.MemberID, row.Role)
}
return summary, nil
}
func (h *Handler) squadToResponseWithPreview(ctx context.Context, squad db.Squad) (SquadResponse, error) {
resp := h.squadToResponse(squad)
summary, err := h.loadSquadMemberSummary(ctx, squad.ID)
if err != nil {
return resp, err
}
applySquadMemberSummary(&resp, summary)
return resp, nil
}
// ── Handlers ────────────────────────────────────────────────────────────────
func (h *Handler) ListSquads(w http.ResponseWriter, r *http.Request) {
workspaceID := workspaceIDFromURL(r, "workspaceId")
wsUUID, ok := parseUUIDOrBadRequest(w, workspaceID, "workspace_id")
if !ok {
return
}
squads, err := h.Queries.ListSquads(r.Context(), wsUUID)
if err != nil {
writeError(w, http.StatusInternalServerError, "failed to list squads")
return
}
previewRows, err := h.Queries.ListSquadMemberPreviewRows(r.Context(), wsUUID)
if err != nil {
writeError(w, http.StatusInternalServerError, "failed to list squad member preview")
return
}
summaries := make(map[string]*squadMemberSummary, len(squads))
for _, row := range previewRows {
squadID := uuidToString(row.SquadID)
summary := summaries[squadID]
if summary == nil {
summary = &squadMemberSummary{}
summaries[squadID] = summary
}
addSquadMemberPreview(summary, row.MemberType, row.MemberID, row.Role)
}
resp := make([]SquadResponse, len(squads))
for i, s := range squads {
resp[i] = h.squadToResponse(s)
applySquadMemberSummary(&resp[i], summaries[uuidToString(s.ID)])
}
writeJSON(w, http.StatusOK, resp)
}
func (h *Handler) CreateSquad(w http.ResponseWriter, r *http.Request) {
workspaceID := workspaceIDFromURL(r, "workspaceId")
// Any workspace member can create a squad and becomes its creator
// (CreatorID below). This aligns squads with agents/projects, which are
// also member-creatable; management stays creator-scoped (MUL-4223).
member, ok := h.requireWorkspaceMember(w, r, workspaceID, "workspace not found")
if !ok {
return
}
var req struct {
Name string `json:"name"`
Description string `json:"description"`
LeaderID string `json:"leader_id"`
AvatarURL *string `json:"avatar_url"`
}
if err := json.NewDecoder(r.Body).Decode(&req); err != nil {
writeError(w, http.StatusBadRequest, "invalid request body")
return
}
if req.Name == "" {
writeError(w, http.StatusBadRequest, "name is required")
return
}
if req.LeaderID == "" {
writeError(w, http.StatusBadRequest, "leader_id is required")
return
}
leaderUUID, ok := parseUUIDOrBadRequest(w, req.LeaderID, "leader_id")
if !ok {
return
}
wsUUID, ok := parseUUIDOrBadRequest(w, workspaceID, "workspace_id")
if !ok {
return
}
// Validate leader is an agent in this workspace.
leaderAgent, err := h.Queries.GetAgentInWorkspace(r.Context(), db.GetAgentInWorkspaceParams{
ID: leaderUUID,
WorkspaceID: wsUUID,
})
if err != nil {
writeError(w, http.StatusBadRequest, "leader must be a valid agent in this workspace")
return
}
// A non-admin creator may only lead their squad with an agent they can
// @-trigger; admins may wire any workspace agent (MUL-4223).
if !h.memberCanWireAgent(r.Context(), member, leaderAgent, workspaceID) {
writeError(w, http.StatusForbidden, "you can only use an agent you have access to as leader")
return
}
avatarURL := pgtype.Text{}
if req.AvatarURL != nil {
accepted, ok := h.acceptAvatarURL(w, r, *req.AvatarURL, "")
if !ok {
return
}
avatarURL = pgtype.Text{String: accepted, Valid: true}
}
squad, err := h.Queries.CreateSquad(r.Context(), db.CreateSquadParams{
WorkspaceID: wsUUID,
Name: req.Name,
Description: req.Description,
LeaderID: leaderUUID,
CreatorID: member.UserID,
AvatarUrl: avatarURL,
})
if err != nil {
writeError(w, http.StatusInternalServerError, "failed to create squad")
return
}
// Auto-add leader as a member with role "leader".
h.Queries.AddSquadMember(r.Context(), db.AddSquadMemberParams{
SquadID: squad.ID,
MemberType: "agent",
MemberID: leaderUUID,
Role: "leader",
})
resp, err := h.squadToResponseWithPreview(r.Context(), squad)
if err != nil {
writeError(w, http.StatusInternalServerError, "failed to load squad member preview")
return
}
h.publish(protocol.EventSquadCreated, workspaceID, "member", uuidToString(member.UserID), map[string]any{"squad": resp})
obsmetrics.RecordEvent(h.Analytics, h.Metrics, analytics.SquadCreated(
uuidToString(member.UserID),
workspaceID,
uuidToString(squad.ID),
1,
))
writeJSON(w, http.StatusCreated, resp)
}
func (h *Handler) GetSquad(w http.ResponseWriter, r *http.Request) {
squad, _, ok := h.loadSquadInWorkspace(w, r)
if !ok {
return
}
resp, err := h.squadToResponseWithPreview(r.Context(), squad)
if err != nil {
writeError(w, http.StatusInternalServerError, "failed to load squad member preview")
return
}
writeJSON(w, http.StatusOK, resp)
}
func (h *Handler) UpdateSquad(w http.ResponseWriter, r *http.Request) {
workspaceID := workspaceIDFromURL(r, "workspaceId")
member, ok := h.requireWorkspaceMember(w, r, workspaceID, "workspace not found")
if !ok {
return
}
squad, _, ok := h.loadSquadInWorkspace(w, r)
if !ok {
return
}
if !canManageSquad(member, squad) {
writeError(w, http.StatusForbidden, "insufficient permissions")
return
}
wsUUID, ok := parseUUIDOrBadRequest(w, workspaceID, "workspace_id")
if !ok {
return
}
var req struct {
Name *string `json:"name"`
Description *string `json:"description"`
Instructions *string `json:"instructions"`
LeaderID *string `json:"leader_id"`
AvatarURL *string `json:"avatar_url"`
}
if err := json.NewDecoder(r.Body).Decode(&req); err != nil {
writeError(w, http.StatusBadRequest, "invalid request body")
return
}
params := db.UpdateSquadParams{ID: squad.ID}
if req.Name != nil {
params.Name = pgtype.Text{String: *req.Name, Valid: true}
}
if req.Description != nil {
params.Description = pgtype.Text{String: *req.Description, Valid: true}
}
if req.Instructions != nil {
params.Instructions = pgtype.Text{String: *req.Instructions, Valid: true}
}
if req.AvatarURL != nil {
accepted, ok := h.acceptAvatarURL(w, r, *req.AvatarURL, squad.AvatarUrl.String)
if !ok {
return
}
params.AvatarUrl = pgtype.Text{String: accepted, Valid: true}
}
tx, err := h.TxStarter.Begin(r.Context())
if err != nil {
writeError(w, http.StatusInternalServerError, "failed to update squad")
return
}
defer tx.Rollback(r.Context())
qtx := h.Queries.WithTx(tx)
// Autopilot assignment takes FOR SHARE on the squad before locking its
// leader Agent. Take the exclusive side in the same order so leader
// rotation and active Autopilot saves cannot leave an automation pointing
// at an unbound effective Agent.
if _, err := qtx.LockSquadForUpdate(r.Context(), db.LockSquadForUpdateParams{
ID: squad.ID,
WorkspaceID: wsUUID,
}); err != nil {
writeError(w, http.StatusInternalServerError, "failed to update squad")
return
}
newLeaderRuntimeBound := true
if req.LeaderID != nil {
lid, ok := parseUUIDOrBadRequest(w, *req.LeaderID, "leader_id")
if !ok {
return
}
// Stabilize runtime_id through commit. Runtime teardown takes FOR UPDATE
// on this row and follows the same Agent→Autopilot lock order, so
// whichever operation starts first produces a complete result.
newLeader, err := qtx.LockAgentForAutopilotAssignment(r.Context(), db.LockAgentForAutopilotAssignmentParams{
ID: lid,
WorkspaceID: wsUUID,
})
if err != nil {
writeError(w, http.StatusBadRequest, "leader must be a valid agent in this workspace")
return
}
// A non-admin creator may only promote an agent they can @-trigger.
if !h.memberCanWireAgent(r.Context(), member, newLeader, workspaceID) {
writeError(w, http.StatusForbidden, "you can only use an agent you have access to as leader")
return
}
// Ensure new leader is a squad member; auto-add if not.
isMember, err := qtx.IsSquadMember(r.Context(), db.IsSquadMemberParams{
SquadID: squad.ID, MemberType: "agent", MemberID: lid,
})
if err != nil {
writeError(w, http.StatusInternalServerError, "failed to update squad")
return
}
if !isMember {
if _, err := qtx.AddSquadMember(r.Context(), db.AddSquadMemberParams{
SquadID: squad.ID, MemberType: "agent", MemberID: lid, Role: "leader",
}); err != nil {
writeError(w, http.StatusInternalServerError, "failed to update squad")
return
}
}
params.LeaderID = lid
newLeaderRuntimeBound = newLeader.RuntimeID.Valid
}
updated, err := qtx.UpdateSquad(r.Context(), params)
if err != nil {
writeError(w, http.StatusInternalServerError, "failed to update squad")
return
}
var pausedAutopilots []db.Autopilot
if req.LeaderID != nil && !newLeaderRuntimeBound {
pausedAutopilots, err = qtx.PauseAutopilotsByUnrunnableSquad(r.Context(), squad.ID)
if err != nil {
writeError(w, http.StatusInternalServerError, "failed to update squad")
return
}
}
if err := tx.Commit(r.Context()); err != nil {
writeError(w, http.StatusInternalServerError, "failed to update squad")
return
}
resp, err := h.squadToResponseWithPreview(r.Context(), updated)
if err != nil {
writeError(w, http.StatusInternalServerError, "failed to load squad member preview")
return
}
h.publish(protocol.EventSquadUpdated, workspaceID, "member", requestUserID(r), map[string]any{"squad": resp})
for _, autopilot := range pausedAutopilots {
h.publish(protocol.EventAutopilotUpdated, workspaceID, "member", requestUserID(r), map[string]any{
"autopilot": autopilotToResponse(autopilot, nil),
})
}
writeJSON(w, http.StatusOK, resp)
}
func (h *Handler) DeleteSquad(w http.ResponseWriter, r *http.Request) {
workspaceID := workspaceIDFromURL(r, "workspaceId")
member, ok := h.requireWorkspaceMember(w, r, workspaceID, "workspace not found")
if !ok {
return
}
squad, _, ok := h.loadSquadInWorkspace(w, r)
if !ok {
return
}
if !canManageSquad(member, squad) {
writeError(w, http.StatusForbidden, "insufficient permissions")
return
}
if squad.ArchivedAt.Valid {
writeError(w, http.StatusBadRequest, "squad is already archived")
return
}
// Transfer issues assigned to this squad to the leader agent.
if err := h.Queries.TransferSquadAssignees(r.Context(), db.TransferSquadAssigneesParams{
AssigneeID: squad.ID,
AssigneeID_2: squad.LeaderID,
}); err != nil {
slog.Warn("transfer squad assignees failed", "squad_id", uuidToString(squad.ID), "error", err)
}
// Mirror the issue-assignee transfer for autopilots that target this
// squad. Without this, autopilot.assignee_id would still point at the
// archived squad row and every subsequent dispatch would skip with
// "assignee squad is archived" — visible to ops but useless to the
// owner. Rewriting to the leader keeps the autopilot semantics
// unchanged (Path A from MUL-2429 is leader-only execution anyway).
if err := h.Queries.TransferSquadAutopilotsToLeader(r.Context(), db.TransferSquadAutopilotsToLeaderParams{
AssigneeID: squad.ID,
AssigneeID_2: squad.LeaderID,
}); err != nil {
slog.Warn("transfer squad autopilots failed", "squad_id", uuidToString(squad.ID), "error", err)
}
userID := requestUserID(r)
userUUID, _ := parseUUIDOrBadRequest(w, userID, "user_id")
if _, err := h.Queries.ArchiveSquad(r.Context(), db.ArchiveSquadParams{
ID: squad.ID,
ArchivedBy: userUUID,
}); err != nil {
writeError(w, http.StatusInternalServerError, "failed to archive squad")
return
}
h.publish(protocol.EventSquadDeleted, workspaceID, "member", userID, map[string]any{
"squad_id": uuidToString(squad.ID),
"leader_id": uuidToString(squad.LeaderID),
})
w.WriteHeader(http.StatusNoContent)
}
// ── Squad Members ───────────────────────────────────────────────────────────
func (h *Handler) ListSquadMembers(w http.ResponseWriter, r *http.Request) {
squad, _, ok := h.loadSquadInWorkspace(w, r)
if !ok {
return
}
members, err := h.Queries.ListSquadMembers(r.Context(), squad.ID)
if err != nil {
writeError(w, http.StatusInternalServerError, "failed to list squad members")
return
}
resp := make([]SquadMemberResponse, len(members))
for i, m := range members {
resp[i] = squadMemberToResponse(m)
}
writeJSON(w, http.StatusOK, resp)
}
// ── Squad Member Status ────────────────────────────────────────────────────
// SquadMemberStatus is the per-member entry in the squad member status
// response. Agent members carry a derived working/idle/offline/unstable
// status plus any active issues; human members are returned with member_type
// only so the front-end can render them in the same list without
// reordering.
type SquadMemberStatusResponse struct {
MemberType string `json:"member_type"`
MemberID string `json:"member_id"`
Status *string `json:"status"`
ActiveIssues []SquadActiveIssueBrief `json:"active_issues"`
LastActiveAt *string `json:"last_active_at"`
}
type SquadActiveIssueBrief struct {
IssueID string `json:"issue_id"`
Identifier string `json:"identifier"`
Title string `json:"title"`
IssueStatus string `json:"issue_status"`
}
type SquadMemberStatusListResponse struct {
Members []SquadMemberStatusResponse `json:"members"`
}
// deriveRuntimeAvailability owns the shared three-state runtime reachability
// policy. Agent projections use these values directly; squad presence maps an
// online runtime to its user-facing "idle" bucket after workload precedence.
func deriveRuntimeAvailability(
runtimeStatus pgtype.Text,
lastSeen pgtype.Timestamptz,
now time.Time,
) string {
if !runtimeStatus.Valid {
return "offline"
}
if runtimeStatus.String == "online" {
return "online"
}
if !lastSeen.Valid {
return "offline"
}
if now.Sub(lastSeen.Time) < 5*time.Minute {
return "unstable"
}
return "offline"
}
// deriveSquadMemberStatus collapses runtime + task signals into the five
// status buckets used by the squad UI. Mirrors the workload+availability
// split in packages/core/agents/derive-presence.ts: working wins over
// runtime health (an agent that is in the middle of dispatched/running
// work counts as working even if the runtime briefly drops), then
// availability buckets decide between idle / unstable / offline.
//
// Thresholds match deriveRuntimeHealth: any offline runtime whose
// last_seen_at is within the last 5 minutes is reported as "unstable" so
// the squad UI surfaces transient drops the same way the agent dot does.
//
// Archived agents always report `archived` regardless of any leftover
// runtime row or task — they should appear in the list but never look
// like they're still working or merely offline (a leftover online
// runtime row would otherwise read as "offline" and hide the fact that
// the agent has been archived). Per the RFC decision (see MUL-2319), we
// surface archived agents in this endpoint rather than filtering them
// out in the SQL.
func deriveSquadMemberStatus(
archived bool,
runtimeStatus pgtype.Text,
lastSeen pgtype.Timestamptz,
hasWorkingTask bool,
now time.Time,
) string {
if archived {
return "archived"
}
if hasWorkingTask {
return "working"
}
availability := deriveRuntimeAvailability(runtimeStatus, lastSeen, now)
if availability == "online" {
return "idle"
}
return availability
}
// ListSquadMemberStatus returns one entry per squad member with derived
// status, the issues each agent member is currently running or waiting to run,
// and the last observed runtime activity. The endpoint is read-only and
// inherits the workspace-membership guard from the route middleware — any
// member of the workspace can read it.
func (h *Handler) ListSquadMemberStatus(w http.ResponseWriter, r *http.Request) {
squad, _, ok := h.loadSquadInWorkspace(w, r)
if !ok {
return
}
rows, err := h.Queries.ListSquadMemberStatusRows(r.Context(), squad.ID)
if err != nil {
writeError(w, http.StatusInternalServerError, "failed to list squad member status")
return
}
prefix := h.getIssuePrefix(r.Context(), squad.WorkspaceID)
now := time.Now()
// Group rows by member_id while preserving the SQL ORDER BY (squad_member
// insertion order). One member may appear in multiple rows when they have
// more than one active task.
type memberAcc struct {
response SquadMemberStatusResponse
archived bool
hasWorkingTask bool
runtimeStatus pgtype.Text
runtimeSeenAt pgtype.Timestamptz
latestActiveAt pgtype.Timestamptz
}
order := make([]string, 0, len(rows))
acc := make(map[string]*memberAcc, len(rows))
for _, row := range rows {
memberID := uuidToString(row.MemberID)
entry, exists := acc[memberID]
if !exists {
entry = &memberAcc{
response: SquadMemberStatusResponse{
MemberType: row.MemberType,
MemberID: memberID,
ActiveIssues: []SquadActiveIssueBrief{},
},
archived: row.AgentArchivedAt.Valid,
runtimeStatus: row.RuntimeStatus,
runtimeSeenAt: row.RuntimeLastSeenAt,
}
acc[memberID] = entry
order = append(order, memberID)
}
if row.MemberType != "agent" {
continue
}
// Keep waiting_local_directory rows available for issue visibility,
// but only dispatched/running work drives the `working` bucket. A
// working task may have no issue (chat / quick-create), so decide the
// bucket independently from whether an issue link can be rendered.
if row.TaskID.Valid {
if row.TaskStatus.Valid &&
(row.TaskStatus.String == "dispatched" || row.TaskStatus.String == "running") {
entry.hasWorkingTask = true
}
if row.TaskIssueID.Valid {
brief := SquadActiveIssueBrief{
IssueID: uuidToString(row.TaskIssueID),
Identifier: prefix + "-" + strconv.Itoa(int(row.IssueNumber.Int32)),
Title: row.IssueTitle.String,
IssueStatus: func() string {
if row.IssueStatus.Valid {
return row.IssueStatus.String
}
return ""
}(),
}
entry.response.ActiveIssues = append(entry.response.ActiveIssues, brief)
}
if row.TaskDispatchedAt.Valid && (!entry.latestActiveAt.Valid ||
row.TaskDispatchedAt.Time.After(entry.latestActiveAt.Time)) {
entry.latestActiveAt = row.TaskDispatchedAt
}
}
}
resp := SquadMemberStatusListResponse{
Members: make([]SquadMemberStatusResponse, 0, len(order)),
}
for _, id := range order {
entry := acc[id]
if entry.response.MemberType == "agent" {
status := deriveSquadMemberStatus(
entry.archived,
entry.runtimeStatus,
entry.runtimeSeenAt,
entry.hasWorkingTask,
now,
)
entry.response.Status = &status
// last_active_at prefers the freshest active-task dispatch
// over the runtime heartbeat: a working agent should not
// look stale because the runtime heartbeat is a few seconds
// behind. Falls back to runtime last_seen_at otherwise.
if entry.latestActiveAt.Valid {
entry.response.LastActiveAt = timestampToPtr(entry.latestActiveAt)
} else if entry.runtimeSeenAt.Valid {
entry.response.LastActiveAt = timestampToPtr(entry.runtimeSeenAt)
}
}
resp.Members = append(resp.Members, entry.response)
}
writeJSON(w, http.StatusOK, resp)
}
func (h *Handler) AddSquadMember(w http.ResponseWriter, r *http.Request) {
workspaceID := workspaceIDFromURL(r, "workspaceId")
member, ok := h.requireWorkspaceMember(w, r, workspaceID, "workspace not found")
if !ok {
return
}
squad, _, ok := h.loadSquadInWorkspace(w, r)
if !ok {
return
}
if !canManageSquad(member, squad) {
writeError(w, http.StatusForbidden, "insufficient permissions")
return
}
wsUUID, ok := parseUUIDOrBadRequest(w, workspaceID, "workspace_id")
if !ok {
return
}
var req struct {
MemberType string `json:"member_type"`
MemberID string `json:"member_id"`
Role string `json:"role"`
}
if err := json.NewDecoder(r.Body).Decode(&req); err != nil {
writeError(w, http.StatusBadRequest, "invalid request body")
return
}
if req.MemberType != "agent" && req.MemberType != "member" {
writeError(w, http.StatusBadRequest, "member_type must be 'agent' or 'member'")
return
}
if req.MemberID == "" {
writeError(w, http.StatusBadRequest, "member_id is required")
return
}
memberUUID, ok := parseUUIDOrBadRequest(w, req.MemberID, "member_id")
if !ok {
return
}
// Validate the member belongs to this workspace.
if req.MemberType == "agent" {
agent, err := h.Queries.GetAgentInWorkspace(r.Context(), db.GetAgentInWorkspaceParams{
ID: memberUUID, WorkspaceID: wsUUID,
})
if err != nil {
writeError(w, http.StatusBadRequest, "agent not found in this workspace")
return
}
// A non-admin creator may only add agents they can @-trigger (public
// or their own / allow-listed agents); admins may add any workspace
// agent (MUL-4223).
if !h.memberCanWireAgent(r.Context(), member, agent, workspaceID) {
writeError(w, http.StatusForbidden, "you can only add an agent you have access to")
return
}
} else {
if _, err := h.Queries.GetMemberByUserAndWorkspace(r.Context(), db.GetMemberByUserAndWorkspaceParams{
UserID: memberUUID, WorkspaceID: wsUUID,
}); err != nil {
writeError(w, http.StatusBadRequest, "member not found in this workspace")
return
}
}
sm, err := h.Queries.AddSquadMember(r.Context(), db.AddSquadMemberParams{
SquadID: squad.ID,
MemberType: req.MemberType,
MemberID: memberUUID,
Role: req.Role,
})
if err != nil {
if isUniqueViolation(err) {
writeError(w, http.StatusConflict, "member already in squad")
return
}
writeError(w, http.StatusInternalServerError, "failed to add squad member")
return
}
writeJSON(w, http.StatusCreated, squadMemberToResponse(sm))
h.publish(protocol.EventSquadUpdated, workspaceID, "member", requestUserID(r), map[string]any{
"squad_id": uuidToString(squad.ID),
})
}
func (h *Handler) RemoveSquadMember(w http.ResponseWriter, r *http.Request) {
workspaceID := workspaceIDFromURL(r, "workspaceId")
member, ok := h.requireWorkspaceMember(w, r, workspaceID, "workspace not found")
if !ok {
return
}
squad, _, ok := h.loadSquadInWorkspace(w, r)
if !ok {
return
}
if !canManageSquad(member, squad) {
writeError(w, http.StatusForbidden, "insufficient permissions")
return
}
var req struct {
MemberType string `json:"member_type"`
MemberID string `json:"member_id"`
}
if err := json.NewDecoder(r.Body).Decode(&req); err != nil {
writeError(w, http.StatusBadRequest, "invalid request body")
return
}
memberUUID, ok := parseUUIDOrBadRequest(w, req.MemberID, "member_id")
if !ok {
return
}
// Prevent removing the leader.
if req.MemberType == "agent" && uuidToString(squad.LeaderID) == req.MemberID {
writeError(w, http.StatusBadRequest, "cannot remove the squad leader; change leader first")
return
}
rows, err := h.Queries.RemoveSquadMember(r.Context(), db.RemoveSquadMemberParams{
SquadID: squad.ID,
MemberType: req.MemberType,
MemberID: memberUUID,
})
if err != nil {
writeError(w, http.StatusInternalServerError, "failed to remove squad member")
return
}
if rows == 0 {
writeError(w, http.StatusNotFound, "squad member not found")
return
}
h.publish(protocol.EventSquadUpdated, workspaceID, "member", requestUserID(r), map[string]any{
"squad_id": uuidToString(squad.ID),
})
w.WriteHeader(http.StatusNoContent)
}
func (h *Handler) UpdateSquadMemberRole(w http.ResponseWriter, r *http.Request) {
workspaceID := workspaceIDFromURL(r, "workspaceId")
member, ok := h.requireWorkspaceMember(w, r, workspaceID, "workspace not found")
if !ok {
return
}
squad, _, ok := h.loadSquadInWorkspace(w, r)
if !ok {
return
}
if !canManageSquad(member, squad) {
writeError(w, http.StatusForbidden, "insufficient permissions")
return
}
var req struct {
MemberType string `json:"member_type"`
MemberID string `json:"member_id"`
Role string `json:"role"`
}
if err := json.NewDecoder(r.Body).Decode(&req); err != nil {
writeError(w, http.StatusBadRequest, "invalid request body")
return
}
memberUUID, ok := parseUUIDOrBadRequest(w, req.MemberID, "member_id")
if !ok {
return
}
sm, err := h.Queries.UpdateSquadMemberRole(r.Context(), db.UpdateSquadMemberRoleParams{
SquadID: squad.ID,
MemberType: req.MemberType,
MemberID: memberUUID,
Role: req.Role,
})
if err != nil {
writeError(w, http.StatusNotFound, "squad member not found")
return
}
h.publish(protocol.EventSquadUpdated, workspaceID, "member", requestUserID(r), map[string]any{
"squad_id": uuidToString(squad.ID),
})
writeJSON(w, http.StatusOK, squadMemberToResponse(sm))
}
// ── Squad Leader Evaluation ──────────────────────────────────────────────────
// RecordSquadLeaderEvaluation records a squad leader's evaluation decision
// into the unified activity_log. Called by the leader agent via CLI after
// each trigger to record whether it took action, stayed silent, or failed.
//
// The leader-turn check is task-provenance based (is_leader_task + squad_id on
// the X-Task-ID row), the SAME source the claim path uses to inject the squad
// briefing and the mandatory-recording instruction. The target issue's own
// assignee is deliberately NOT consulted: leaders legitimately run on issues
// that are not squad-assigned. See MUL-6622 / GH #7487.
//
// Two authorization gates, in this order: the caller must own the task, and must
// still be the squad's leader. The first is what makes it safe to quote the
// task's issue id in an error; the second is what keeps a claim-downgraded run
// (see the comment at gate 2) from writing a leader verdict.
func (h *Handler) RecordSquadLeaderEvaluation(w http.ResponseWriter, r *http.Request) {
issue, ok := h.loadIssueForUser(w, r, chi.URLParam(r, "id"))
if !ok {
return
}
var req struct {
Outcome string `json:"outcome"` // action | no_action | failed
Reason string `json:"reason"` // short explanation from leader
}
if err := json.NewDecoder(r.Body).Decode(&req); err != nil {
writeError(w, http.StatusBadRequest, "invalid request body")
return
}
if req.Outcome != "action" && req.Outcome != "no_action" && req.Outcome != "failed" {
writeError(w, http.StatusBadRequest, "outcome must be 'action', 'no_action', or 'failed'")
return
}
// Authority for "is this run a squad leader turn" is the TASK ROW, not the
// target issue's assignee (MUL-6622 / GH #7487). is_leader_task + squad_id
// are stamped at enqueue time and are exactly what the claim path keys the
// squad briefing and the mandatory-`squad activity` instruction off
// (handler/daemon.go, daemon/prompt.go taskIsSquadLeader). Gating this
// endpoint on issue.assignee_type == "squad" instead made the recording
// call unsatisfiable on the paths where a leader legitimately runs on a
// non-squad-assigned issue — a `@squad` mention on an issue owned by a
// plain agent, or a leader task bound to a child issue — and because the
// no_action instruction forbids substituting a comment, the decision left
// no trace at all.
//
// Check ORDER is load-bearing. Every rejection below the ownership gate may
// quote task-derived ids; every rejection above it must not. `GetAgentTask`
// is a global lookup by id, so tenant scoping (GetAgentTaskInWorkspace,
// which joins the owning agent's workspace) and the "caller owns this task"
// gate both come first — otherwise an unrelated task id, probed through an
// issue the caller can legitimately read, would echo back a foreign
// workspace's issue id.
taskID := r.Header.Get("X-Task-ID")
taskUUID, ok := parseUUIDOrBadRequest(w, taskID, "task id")
if !ok {
return
}
task, err := h.Queries.GetAgentTaskInWorkspace(r.Context(), db.GetAgentTaskInWorkspaceParams{
ID: taskUUID,
WorkspaceID: issue.WorkspaceID,
})
if err != nil || !task.IssueID.Valid {
writeError(w, http.StatusBadRequest, "task does not belong to issue")
return
}
// Security gate 1: the caller must be the agent this task was enqueued for.
workspaceID := uuidToString(issue.WorkspaceID)
userID := requestUserID(r)
actorType, actorID := h.resolveActor(r, userID, workspaceID)
if actorType != "agent" || !task.AgentID.Valid || actorID != uuidToString(task.AgentID) {
writeError(w, http.StatusForbidden, "only the squad leader agent can record evaluations")
return
}
// Past the ownership gate, naming the task's own issue is safe — and useful:
// a leader woken by a stage barrier / child-done callback runs on the PARENT
// issue, so recording against the child it just read is the common mistake.
if uuidToString(task.IssueID) != uuidToString(issue.ID) {
writeError(w, http.StatusBadRequest,
"task does not belong to issue; record the evaluation on issue "+uuidToString(task.IssueID)+" (the issue this task is running on)")
return
}
// Narrowing vs. the old behavior: a leader agent running a NON-leader task
// on a squad-assigned issue (for example a same-squad worker task) used to
// be accepted here. It is rejected now — it is not running as the leader,
// and the runtime only mandates this call when taskIsSquadLeader(task).
if !task.IsLeaderTask {
writeError(w, http.StatusBadRequest, "task is not a squad leader task")
return
}
if !task.SquadID.Valid {
// Pre-MUL-3730 rows can be leader tasks without a stamped squad. Log it
// rather than failing silently from the operator's point of view.
slog.Warn("squad leader evaluation: leader task has no squad_id",
append(logger.RequestAttrs(r),
"task_id", uuidToString(task.ID),
"issue_id", uuidToString(issue.ID),
)...)
writeError(w, http.StatusBadRequest, "leader task has no squad_id")
return
}
squad, err := h.Queries.GetSquadInWorkspace(r.Context(), db.GetSquadInWorkspaceParams{
ID: task.SquadID,
WorkspaceID: issue.WorkspaceID,
})
if err != nil {
writeError(w, http.StatusNotFound, "squad not found")
return
}
// Security gate 2: the caller must still be this squad's leader.
//
// `is_leader_task` on the row records the enqueue-time INTENT, which is not
// always the role the claim actually delivered: when the leader was swapped
// between enqueue and claim, the claim path clears resp.IsLeaderTask and the
// run proceeds as an ordinary agent turn, while the row keeps
// is_leader_task = true (handler/daemon.go, "claim delivered as a non-leader
// task"). Trusting the row alone would let such a downgraded run write a
// leader verdict — and, on no_action, suppress its own comment. Until the
// delivered role is persisted, the live leader check is the only thing that
// distinguishes the two, so it stays.
//
// Cost of the conservative choice: a leader rotated away MID-run is refused
// here. That no longer means silence — the injected rules now tell a leader
// whose recording call failed to leave a short comment instead.
if actorID != uuidToString(squad.LeaderID) {
writeError(w, http.StatusForbidden, "only the squad leader agent can record evaluations")
return
}
details, _ := json.Marshal(map[string]string{
"squad_id": uuidToString(squad.ID),
"task_id": util.UUIDToString(taskUUID),
"outcome": req.Outcome,
"reason": req.Reason,
})
activity, err := h.Queries.CreateActivity(r.Context(), db.CreateActivityParams{
ID: dbid.NewV7(),
WorkspaceID: issue.WorkspaceID,
IssueID: issue.ID,
ActorType: pgtype.Text{String: "agent", Valid: true},
// task.AgentID, not squad.LeaderID: the no_action comment suppression
// lookup matches actor_id against task.agent_id
// (service.HasSquadLeaderNoActionEvaluationForTask), so this column has
// to carry the task's agent for suppression to find the row at all.
ActorID: task.AgentID,
Action: "squad_leader_evaluated",
Details: details,
})
if err != nil {
writeError(w, http.StatusInternalServerError, "failed to record evaluation")
return
}
h.publish(protocol.EventActivityCreated, uuidToString(issue.WorkspaceID), "agent", actorID, map[string]any{
"issue_id": uuidToString(issue.ID),
"entry": map[string]any{
"type": "activity",
"id": uuidToString(activity.ID),
"actor_type": "agent",
"actor_id": actorID,
"action": activity.Action,
"details": json.RawMessage(details),
"created_at": timestampToString(activity.CreatedAt),
},
})
writeJSON(w, http.StatusCreated, map[string]string{
"id": uuidToString(activity.ID),
"action": activity.Action,
"created_at": timestampToString(activity.CreatedAt),
})
}
// ── Squad Trigger Logic ─────────────────────────────────────────────────────
// shouldSuppressSquadLeaderSelfTrigger reports whether a squad leader's own
// comment should be blocked from re-enqueuing that same leader. The only
// leader-authored non-leader task allowed to wake the assigned leader is a
// same-squad worker task; generic agent tasks such as direct mentions and
// thread-parent replies are not worker-role proof and must not self-trigger.
func (h *Handler) shouldSuppressSquadLeaderSelfTrigger(ctx context.Context, issueID, leaderID, squadID pgtype.UUID) bool {
latest, err := h.Queries.GetLatestTaskRoleForIssueAndAgent(ctx, db.GetLatestTaskRoleForIssueAndAgentParams{
IssueID: issueID,
AgentID: leaderID,
})
if err != nil {
return false
}
if latest.IsLeaderTask {
return true
}
return !latest.SquadID.Valid || uuidToString(latest.SquadID) != uuidToString(squadID)
}
// commentMentionsAnyone returns true when the comment body contains at least
// one routing-style mention — [@Name](mention://agent|member|squad|all/<id>).
// Issue cross-references (mention://issue/...) are ignored because they are
// not directed at a participant. Only the current comment is inspected —
// parent (thread root) mentions are NOT inherited here.
func commentMentionsAnyone(content string) bool {
for _, m := range util.ParseMentions(content) {
switch m.Type {
case "agent", "member", "squad", "all":
return true
}
}
return false
}
// The squad-leader assign/promotion readiness decision now lives in the single
// service.IssueService.WillEnqueueRun predicate (MUL-3375), shared by the issue
// write paths and the preview endpoint. The former handler-local mirrors
// (shouldEnqueueSquadLeaderOnAssign / isSquadLeaderReady) were removed to stop
// the four-entry-point drift. The squad enqueue side effect still flows through
// enqueueSquadLeaderTask below, which keeps the leader access gate and pending
// dedup in one place.
// enqueueSquadLeaderTask triggers the squad leader agent for an issue assigned
// to a squad. Assign and backlog-promotion paths use this directly; comment
// paths go through computeCommentAgentTriggers so preview and create share the
// same trigger set.
// It returns true only when a leader task was actually enqueued.
func (h *Handler) enqueueSquadLeaderTask(ctx context.Context, issue db.Issue, triggerCommentID pgtype.UUID, authorType, authorID, handoffNote string) bool {
squad, err := h.Queries.GetSquadInWorkspace(ctx, db.GetSquadInWorkspaceParams{
ID: issue.AssigneeID,
WorkspaceID: issue.WorkspaceID,
})
if err != nil {
return false
}
// The gate must judge the SAME top-of-chain human the enqueue path will
// persist on the leader task row, or it drifts: an agent-created issue that
// correctly inherits its originator (MUL-4305) would still be denied here
// if the gate used an empty originator. Member authors are their own
// originator; for agent/system-triggered assigns we resolve the originator
// exactly like EnqueueTaskForSquadLeader* does (via the issue's origin
// link). triggerCommentID is always empty on the assign/promote path, so we
// pass an invalid UUID to match. A still-unresolved originator leaves
// leaderOriginator empty, which correctly fails closed for member/team
// targets while a workspace target still admits the agent principal.
leaderOriginator := ""
if authorType == "member" {
leaderOriginator = authorID
} else {
leaderOriginator = uuidToString(h.TaskService.OriginatorForIssueTask(ctx, issue, pgtype.UUID{}))
}
if !h.canEnqueueSquadLeader(ctx, squad.LeaderID, authorType, authorID, leaderOriginator, uuidToString(issue.WorkspaceID)) {
return false
}
hasPending, err := h.Queries.HasPendingTaskForIssueAndAgent(ctx, db.HasPendingTaskForIssueAndAgentParams{
IssueID: issue.ID,
AgentID: squad.LeaderID,
// Key dedup on the reviewed head (TEN-356).
HeadSha: h.TaskService.ResolveIssueReviewSHAParam(ctx, issue.ID),
})
if err != nil || hasPending {
return false
}
// triggerCommentID is always empty on the assign/promote path; legacy
// handoff text rides its dedicated task column instead.
_ = triggerCommentID
// The member who performed the assign/promote is the accountable human for the
// leader run (MUL-4302 §4) — the same principal the gate above judged. An agent
// author is not a human, so only a member actor is threaded.
if _, err := h.TaskService.EnqueueTaskForSquadLeaderWithHandoff(ctx, issue, squad.LeaderID, squad.ID, handoffNote, memberActorUserID(authorType, authorID)); err != nil {
slog.Warn("enqueue squad leader task failed",
"issue_id", uuidToString(issue.ID),
"squad_id", uuidToString(squad.ID),
"leader_id", uuidToString(squad.LeaderID),
"error", err)
return false
}
return true
}