Files
multica/server/pkg/db/generated/runtime.sql.go
Bohan Jiang a73336dcf8 feat(daemon): persistent UUID identity + legacy-id merge at register-time (#1220)
* feat(daemon): persistent UUID identity + legacy-id merge at register-time

daemon_id is now a stable UUID persisted to `<profile-dir>/daemon.id` on
first start, replacing the hostname-derived id that drifted whenever
`.local` appeared/disappeared, a system was renamed, or a profile
switched — each of which used to mint a fresh `agent_runtime` row and
strand agents on the old one.

To migrate existing installs without operator intervention, the daemon
reports every legacy id it may have registered under previously
(`host`, `host` with `.local` stripped, and `host[-profile]` variants
for both). At register-time the server looks up each candidate row
scoped to (workspace, provider), re-points its agents and tasks onto
the new UUID-keyed row, records which legacy id was subsumed in the
new `legacy_daemon_id` column for audit, and deletes the stale row.
Result: users running `xxx.local`-keyed runtimes today transparently
land on the new UUID row on next daemon restart.

The hostname-prefix `MigrateAgentsToRuntime` / `daemon_id LIKE '...-%'`
compatibility shim is no longer needed and has been removed along with
the handler call that invoked it.

* fix(daemon): handle bidirectional .local drift and case drift in legacy merge

Review on #1220 flagged two gaps in the legacy-id migration candidate set:

1. Reverse .local: LegacyDaemonIDs only added the stripped variant when the
   current hostname ended in `.local`. The opposite direction — DB has
   `foo.local`, current host is `foo` — was missed, so runtimes registered
   under the `.local` variant stayed orphaned after upgrade. Now both
   variants (`foo` and `foo.local`) are always emitted, regardless of what
   `os.Hostname()` currently returns, plus their `-<profile>` suffix forms.

2. Case drift: os.Hostname() has been observed returning different casings
   on the same machine across mDNS/reboot state. A case-sensitive `=`
   comparison stranded rows like `Jiayuans-MacBook-Pro.local` when the
   daemon later reported `jiayuans-macbook-pro.local`. FindLegacyRuntimeByDaemonID
   now uses `LOWER(daemon_id) = LOWER(@daemon_id)` on both sides, so casing
   differences merge rather than orphan. The (workspace_id, provider) prefix
   still bounds the scan to a tiny set of rows so the non-indexed LOWER()
   comparison has negligible cost.

Tests: TestLegacyDaemonIDs gets the mixed-case + reverse-direction cases;
daemon_test.go adds TestDaemonRegister_MergesLegacyDaemonIDRuntime_ReverseDotLocal
and TestDaemonRegister_MergesLegacyDaemonIDRuntime_CaseDrift.

* fix(daemon): consolidate every case-duplicate legacy runtime, not just the first

Follow-up review on #1220: after switching to `LOWER(daemon_id) =
LOWER(@daemon_id)`, the single-row lookup still only merged one legacy
row per candidate. If a machine already had two rows in the DB that
differed only in casing (e.g. `Jiayuans-MacBook-Pro.local` AND
`jiayuans-macbook-pro.local` coexisting because earlier hostname drift
already minted a duplicate), only one of them got consolidated and the
other stayed orphaned — violating the "no duplicate runtime per machine
after backfill" acceptance.

- FindLegacyRuntimeByDaemonID → FindLegacyRuntimesByDaemonID (:many)
- mergeLegacyRuntimes iterates every returned row and dedupes across
  overlapping legacy candidates so `foo` and `foo.local` both resolving
  to the same stored row don't double-process

Test: TestDaemonRegister_MergesAllCaseDuplicateLegacyRuntimes seeds two
case-duplicate rows with one agent each and confirms both rows are
deleted and both agents end up on the new UUID-keyed row.
2026-04-17 15:10:38 +08:00

530 lines
15 KiB
Go

// Code generated by sqlc. DO NOT EDIT.
// versions:
// sqlc v1.30.0
// source: runtime.sql
package db
import (
"context"
"github.com/jackc/pgx/v5/pgtype"
)
const countActiveAgentsByRuntime = `-- name: CountActiveAgentsByRuntime :one
SELECT count(*) FROM agent WHERE runtime_id = $1 AND archived_at IS NULL
`
func (q *Queries) CountActiveAgentsByRuntime(ctx context.Context, runtimeID pgtype.UUID) (int64, error) {
row := q.db.QueryRow(ctx, countActiveAgentsByRuntime, runtimeID)
var count int64
err := row.Scan(&count)
return count, err
}
const deleteAgentRuntime = `-- name: DeleteAgentRuntime :exec
DELETE FROM agent_runtime WHERE id = $1
`
func (q *Queries) DeleteAgentRuntime(ctx context.Context, id pgtype.UUID) error {
_, err := q.db.Exec(ctx, deleteAgentRuntime, id)
return err
}
const deleteArchivedAgentsByRuntime = `-- name: DeleteArchivedAgentsByRuntime :exec
DELETE FROM agent WHERE runtime_id = $1 AND archived_at IS NOT NULL
`
func (q *Queries) DeleteArchivedAgentsByRuntime(ctx context.Context, runtimeID pgtype.UUID) error {
_, err := q.db.Exec(ctx, deleteArchivedAgentsByRuntime, runtimeID)
return err
}
const deleteStaleOfflineRuntimes = `-- name: DeleteStaleOfflineRuntimes :many
DELETE FROM agent_runtime
WHERE status = 'offline'
AND last_seen_at < now() - make_interval(secs => $1::double precision)
AND id NOT IN (SELECT DISTINCT runtime_id FROM agent)
RETURNING id, workspace_id
`
type DeleteStaleOfflineRuntimesRow struct {
ID pgtype.UUID `json:"id"`
WorkspaceID pgtype.UUID `json:"workspace_id"`
}
// Deletes runtimes that have been offline for longer than the TTL and have
// no agents bound (active or archived). The FK constraint on agent.runtime_id
// is ON DELETE RESTRICT, so we must exclude all agent references.
func (q *Queries) DeleteStaleOfflineRuntimes(ctx context.Context, staleSeconds float64) ([]DeleteStaleOfflineRuntimesRow, error) {
rows, err := q.db.Query(ctx, deleteStaleOfflineRuntimes, staleSeconds)
if err != nil {
return nil, err
}
defer rows.Close()
items := []DeleteStaleOfflineRuntimesRow{}
for rows.Next() {
var i DeleteStaleOfflineRuntimesRow
if err := rows.Scan(&i.ID, &i.WorkspaceID); err != nil {
return nil, err
}
items = append(items, i)
}
if err := rows.Err(); err != nil {
return nil, err
}
return items, nil
}
const failTasksForOfflineRuntimes = `-- name: FailTasksForOfflineRuntimes :many
UPDATE agent_task_queue
SET status = 'failed', completed_at = now(), error = 'runtime went offline'
WHERE status IN ('dispatched', 'running')
AND runtime_id IN (
SELECT id FROM agent_runtime WHERE status = 'offline'
)
RETURNING id, agent_id, issue_id
`
type FailTasksForOfflineRuntimesRow struct {
ID pgtype.UUID `json:"id"`
AgentID pgtype.UUID `json:"agent_id"`
IssueID pgtype.UUID `json:"issue_id"`
}
// Marks dispatched/running tasks as failed when their runtime is offline.
// This cleans up orphaned tasks after a daemon crash or network partition.
func (q *Queries) FailTasksForOfflineRuntimes(ctx context.Context) ([]FailTasksForOfflineRuntimesRow, error) {
rows, err := q.db.Query(ctx, failTasksForOfflineRuntimes)
if err != nil {
return nil, err
}
defer rows.Close()
items := []FailTasksForOfflineRuntimesRow{}
for rows.Next() {
var i FailTasksForOfflineRuntimesRow
if err := rows.Scan(&i.ID, &i.AgentID, &i.IssueID); err != nil {
return nil, err
}
items = append(items, i)
}
if err := rows.Err(); err != nil {
return nil, err
}
return items, nil
}
const findLegacyRuntimesByDaemonID = `-- name: FindLegacyRuntimesByDaemonID :many
SELECT id, workspace_id, daemon_id, name, runtime_mode, provider, status, device_info, metadata, last_seen_at, created_at, updated_at, owner_id, legacy_daemon_id FROM agent_runtime
WHERE workspace_id = $1
AND provider = $2
AND LOWER(daemon_id) = LOWER($3)
`
type FindLegacyRuntimesByDaemonIDParams struct {
WorkspaceID pgtype.UUID `json:"workspace_id"`
Provider string `json:"provider"`
DaemonID string `json:"daemon_id"`
}
// Looks up runtime rows keyed on a prior (hostname-derived) daemon_id. Used
// at register-time to find rows owned by the same machine under its old
// identity so agents/tasks can be re-pointed at the new UUID-keyed row.
//
// Comparison is case-insensitive because os.Hostname() has been observed to
// return different casings on the same machine (e.g. `Jiayuans-MacBook-Pro`
// vs `jiayuans-macbook-pro`) across reboots/mDNS state changes. A case-
// sensitive `=` would strand the old row; LOWER() on both sides handles drift
// without forcing the daemon to enumerate cased permutations.
//
// Returns many rather than one because case drift may have already minted
// duplicate rows historically (e.g. `Foo.local` AND `foo.local` under the
// same workspace+provider). A single-row lookup would consolidate only one
// of them and leave the rest orphaned. Callers must merge every returned
// row into the new UUID-keyed runtime.
func (q *Queries) FindLegacyRuntimesByDaemonID(ctx context.Context, arg FindLegacyRuntimesByDaemonIDParams) ([]AgentRuntime, error) {
rows, err := q.db.Query(ctx, findLegacyRuntimesByDaemonID, arg.WorkspaceID, arg.Provider, arg.DaemonID)
if err != nil {
return nil, err
}
defer rows.Close()
items := []AgentRuntime{}
for rows.Next() {
var i AgentRuntime
if err := rows.Scan(
&i.ID,
&i.WorkspaceID,
&i.DaemonID,
&i.Name,
&i.RuntimeMode,
&i.Provider,
&i.Status,
&i.DeviceInfo,
&i.Metadata,
&i.LastSeenAt,
&i.CreatedAt,
&i.UpdatedAt,
&i.OwnerID,
&i.LegacyDaemonID,
); err != nil {
return nil, err
}
items = append(items, i)
}
if err := rows.Err(); err != nil {
return nil, err
}
return items, nil
}
const getAgentRuntime = `-- name: GetAgentRuntime :one
SELECT id, workspace_id, daemon_id, name, runtime_mode, provider, status, device_info, metadata, last_seen_at, created_at, updated_at, owner_id, legacy_daemon_id FROM agent_runtime
WHERE id = $1
`
func (q *Queries) GetAgentRuntime(ctx context.Context, id pgtype.UUID) (AgentRuntime, error) {
row := q.db.QueryRow(ctx, getAgentRuntime, id)
var i AgentRuntime
err := row.Scan(
&i.ID,
&i.WorkspaceID,
&i.DaemonID,
&i.Name,
&i.RuntimeMode,
&i.Provider,
&i.Status,
&i.DeviceInfo,
&i.Metadata,
&i.LastSeenAt,
&i.CreatedAt,
&i.UpdatedAt,
&i.OwnerID,
&i.LegacyDaemonID,
)
return i, err
}
const getAgentRuntimeForWorkspace = `-- name: GetAgentRuntimeForWorkspace :one
SELECT id, workspace_id, daemon_id, name, runtime_mode, provider, status, device_info, metadata, last_seen_at, created_at, updated_at, owner_id, legacy_daemon_id FROM agent_runtime
WHERE id = $1 AND workspace_id = $2
`
type GetAgentRuntimeForWorkspaceParams struct {
ID pgtype.UUID `json:"id"`
WorkspaceID pgtype.UUID `json:"workspace_id"`
}
func (q *Queries) GetAgentRuntimeForWorkspace(ctx context.Context, arg GetAgentRuntimeForWorkspaceParams) (AgentRuntime, error) {
row := q.db.QueryRow(ctx, getAgentRuntimeForWorkspace, arg.ID, arg.WorkspaceID)
var i AgentRuntime
err := row.Scan(
&i.ID,
&i.WorkspaceID,
&i.DaemonID,
&i.Name,
&i.RuntimeMode,
&i.Provider,
&i.Status,
&i.DeviceInfo,
&i.Metadata,
&i.LastSeenAt,
&i.CreatedAt,
&i.UpdatedAt,
&i.OwnerID,
&i.LegacyDaemonID,
)
return i, err
}
const listAgentRuntimes = `-- name: ListAgentRuntimes :many
SELECT id, workspace_id, daemon_id, name, runtime_mode, provider, status, device_info, metadata, last_seen_at, created_at, updated_at, owner_id, legacy_daemon_id FROM agent_runtime
WHERE workspace_id = $1
ORDER BY created_at ASC
`
func (q *Queries) ListAgentRuntimes(ctx context.Context, workspaceID pgtype.UUID) ([]AgentRuntime, error) {
rows, err := q.db.Query(ctx, listAgentRuntimes, workspaceID)
if err != nil {
return nil, err
}
defer rows.Close()
items := []AgentRuntime{}
for rows.Next() {
var i AgentRuntime
if err := rows.Scan(
&i.ID,
&i.WorkspaceID,
&i.DaemonID,
&i.Name,
&i.RuntimeMode,
&i.Provider,
&i.Status,
&i.DeviceInfo,
&i.Metadata,
&i.LastSeenAt,
&i.CreatedAt,
&i.UpdatedAt,
&i.OwnerID,
&i.LegacyDaemonID,
); err != nil {
return nil, err
}
items = append(items, i)
}
if err := rows.Err(); err != nil {
return nil, err
}
return items, nil
}
const listAgentRuntimesByOwner = `-- name: ListAgentRuntimesByOwner :many
SELECT id, workspace_id, daemon_id, name, runtime_mode, provider, status, device_info, metadata, last_seen_at, created_at, updated_at, owner_id, legacy_daemon_id FROM agent_runtime
WHERE workspace_id = $1 AND owner_id = $2
ORDER BY created_at ASC
`
type ListAgentRuntimesByOwnerParams struct {
WorkspaceID pgtype.UUID `json:"workspace_id"`
OwnerID pgtype.UUID `json:"owner_id"`
}
func (q *Queries) ListAgentRuntimesByOwner(ctx context.Context, arg ListAgentRuntimesByOwnerParams) ([]AgentRuntime, error) {
rows, err := q.db.Query(ctx, listAgentRuntimesByOwner, arg.WorkspaceID, arg.OwnerID)
if err != nil {
return nil, err
}
defer rows.Close()
items := []AgentRuntime{}
for rows.Next() {
var i AgentRuntime
if err := rows.Scan(
&i.ID,
&i.WorkspaceID,
&i.DaemonID,
&i.Name,
&i.RuntimeMode,
&i.Provider,
&i.Status,
&i.DeviceInfo,
&i.Metadata,
&i.LastSeenAt,
&i.CreatedAt,
&i.UpdatedAt,
&i.OwnerID,
&i.LegacyDaemonID,
); err != nil {
return nil, err
}
items = append(items, i)
}
if err := rows.Err(); err != nil {
return nil, err
}
return items, nil
}
const markStaleRuntimesOffline = `-- name: MarkStaleRuntimesOffline :many
UPDATE agent_runtime
SET status = 'offline', updated_at = now()
WHERE status = 'online'
AND last_seen_at < now() - make_interval(secs => $1::double precision)
RETURNING id, workspace_id
`
type MarkStaleRuntimesOfflineRow struct {
ID pgtype.UUID `json:"id"`
WorkspaceID pgtype.UUID `json:"workspace_id"`
}
func (q *Queries) MarkStaleRuntimesOffline(ctx context.Context, staleSeconds float64) ([]MarkStaleRuntimesOfflineRow, error) {
rows, err := q.db.Query(ctx, markStaleRuntimesOffline, staleSeconds)
if err != nil {
return nil, err
}
defer rows.Close()
items := []MarkStaleRuntimesOfflineRow{}
for rows.Next() {
var i MarkStaleRuntimesOfflineRow
if err := rows.Scan(&i.ID, &i.WorkspaceID); err != nil {
return nil, err
}
items = append(items, i)
}
if err := rows.Err(); err != nil {
return nil, err
}
return items, nil
}
const reassignAgentsToRuntime = `-- name: ReassignAgentsToRuntime :execrows
UPDATE agent
SET runtime_id = $1
WHERE runtime_id = $2
`
type ReassignAgentsToRuntimeParams struct {
NewRuntimeID pgtype.UUID `json:"new_runtime_id"`
OldRuntimeID pgtype.UUID `json:"old_runtime_id"`
}
// Re-points every agent referencing old_runtime_id at new_runtime_id.
func (q *Queries) ReassignAgentsToRuntime(ctx context.Context, arg ReassignAgentsToRuntimeParams) (int64, error) {
result, err := q.db.Exec(ctx, reassignAgentsToRuntime, arg.NewRuntimeID, arg.OldRuntimeID)
if err != nil {
return 0, err
}
return result.RowsAffected(), nil
}
const reassignTasksToRuntime = `-- name: ReassignTasksToRuntime :execrows
UPDATE agent_task_queue
SET runtime_id = $1
WHERE runtime_id = $2
`
type ReassignTasksToRuntimeParams struct {
NewRuntimeID pgtype.UUID `json:"new_runtime_id"`
OldRuntimeID pgtype.UUID `json:"old_runtime_id"`
}
// Re-points every queued/running/completed task referencing old_runtime_id.
// Required before deleting the old runtime row because agent_task_queue has
// an ON DELETE CASCADE FK that would otherwise drop historical tasks.
func (q *Queries) ReassignTasksToRuntime(ctx context.Context, arg ReassignTasksToRuntimeParams) (int64, error) {
result, err := q.db.Exec(ctx, reassignTasksToRuntime, arg.NewRuntimeID, arg.OldRuntimeID)
if err != nil {
return 0, err
}
return result.RowsAffected(), nil
}
const recordRuntimeLegacyDaemonID = `-- name: RecordRuntimeLegacyDaemonID :exec
UPDATE agent_runtime
SET legacy_daemon_id = COALESCE(legacy_daemon_id, $2)
WHERE id = $1
`
type RecordRuntimeLegacyDaemonIDParams struct {
ID pgtype.UUID `json:"id"`
LegacyDaemonID pgtype.Text `json:"legacy_daemon_id"`
}
// Remembers the most recent hostname-derived daemon_id that was merged into
// this row. Useful for debugging when tracing back why a given runtime row
// subsumed an old one, and only overwrites NULL so the earliest merge is
// preserved.
func (q *Queries) RecordRuntimeLegacyDaemonID(ctx context.Context, arg RecordRuntimeLegacyDaemonIDParams) error {
_, err := q.db.Exec(ctx, recordRuntimeLegacyDaemonID, arg.ID, arg.LegacyDaemonID)
return err
}
const setAgentRuntimeOffline = `-- name: SetAgentRuntimeOffline :exec
UPDATE agent_runtime
SET status = 'offline', updated_at = now()
WHERE id = $1
`
func (q *Queries) SetAgentRuntimeOffline(ctx context.Context, id pgtype.UUID) error {
_, err := q.db.Exec(ctx, setAgentRuntimeOffline, id)
return err
}
const updateAgentRuntimeHeartbeat = `-- name: UpdateAgentRuntimeHeartbeat :one
UPDATE agent_runtime
SET status = 'online', last_seen_at = now(), updated_at = now()
WHERE id = $1
RETURNING id, workspace_id, daemon_id, name, runtime_mode, provider, status, device_info, metadata, last_seen_at, created_at, updated_at, owner_id, legacy_daemon_id
`
func (q *Queries) UpdateAgentRuntimeHeartbeat(ctx context.Context, id pgtype.UUID) (AgentRuntime, error) {
row := q.db.QueryRow(ctx, updateAgentRuntimeHeartbeat, id)
var i AgentRuntime
err := row.Scan(
&i.ID,
&i.WorkspaceID,
&i.DaemonID,
&i.Name,
&i.RuntimeMode,
&i.Provider,
&i.Status,
&i.DeviceInfo,
&i.Metadata,
&i.LastSeenAt,
&i.CreatedAt,
&i.UpdatedAt,
&i.OwnerID,
&i.LegacyDaemonID,
)
return i, err
}
const upsertAgentRuntime = `-- name: UpsertAgentRuntime :one
INSERT INTO agent_runtime (
workspace_id,
daemon_id,
name,
runtime_mode,
provider,
status,
device_info,
metadata,
owner_id,
last_seen_at
) VALUES ($1, $2, $3, $4, $5, $6, $7, $8, $9, now())
ON CONFLICT (workspace_id, daemon_id, provider)
DO UPDATE SET
name = EXCLUDED.name,
runtime_mode = EXCLUDED.runtime_mode,
status = EXCLUDED.status,
device_info = EXCLUDED.device_info,
metadata = EXCLUDED.metadata,
owner_id = COALESCE(EXCLUDED.owner_id, agent_runtime.owner_id),
last_seen_at = now(),
updated_at = now()
RETURNING id, workspace_id, daemon_id, name, runtime_mode, provider, status, device_info, metadata, last_seen_at, created_at, updated_at, owner_id, legacy_daemon_id
`
type UpsertAgentRuntimeParams struct {
WorkspaceID pgtype.UUID `json:"workspace_id"`
DaemonID pgtype.Text `json:"daemon_id"`
Name string `json:"name"`
RuntimeMode string `json:"runtime_mode"`
Provider string `json:"provider"`
Status string `json:"status"`
DeviceInfo string `json:"device_info"`
Metadata []byte `json:"metadata"`
OwnerID pgtype.UUID `json:"owner_id"`
}
func (q *Queries) UpsertAgentRuntime(ctx context.Context, arg UpsertAgentRuntimeParams) (AgentRuntime, error) {
row := q.db.QueryRow(ctx, upsertAgentRuntime,
arg.WorkspaceID,
arg.DaemonID,
arg.Name,
arg.RuntimeMode,
arg.Provider,
arg.Status,
arg.DeviceInfo,
arg.Metadata,
arg.OwnerID,
)
var i AgentRuntime
err := row.Scan(
&i.ID,
&i.WorkspaceID,
&i.DaemonID,
&i.Name,
&i.RuntimeMode,
&i.Provider,
&i.Status,
&i.DeviceInfo,
&i.Metadata,
&i.LastSeenAt,
&i.CreatedAt,
&i.UpdatedAt,
&i.OwnerID,
&i.LegacyDaemonID,
)
return i, err
}