refactor(schema): make runs.task_id nullable, delete heartbeat workaround

The NOT NULL constraint forced heartbeat runs to synthesize a fake task
row (`[Heartbeat] X — Check for work`) so the FK could resolve. Three
layers of code — acquireHeartbeatTask, findReusableHeartbeatTask,
cleanupDuplicateHeartbeatTasks, plus the is_heartbeat flag column + UI
filter — existed to paper over one bad constraint. Remove the
constraint and the whole workaround vanishes.

SQLite table rebuild with data preservation. Live production DB, no
backup — migration is atomic, idempotent, and verified before DROP.

## Migration v35 (rebuild runs with nullable task_id)

Uses `fn:` form so it can:
- Snapshot `COUNT(*) FROM runs` before copy
- Walk `PRAGMA table_info(runs)` to detect drift columns (v34 declared
  a column set; any additive ALTER since v14 shows up here)
- Assert `COUNT(*) FROM runs_new == beforeCount` before `DROP TABLE runs`
- `PRAGMA defer_foreign_keys = ON` so run_events(run_id) FK defers to
  commit time, by which runs has the same id set under the new name
- Recreate all 6 indexes on the new table

If the assertion fails, the migration throws inside the existing
`transaction()` wrapper. SQLite rolls back the whole migration, old
`runs` table is untouched, `schema_migrations` never records v35. Next
app start retries cleanly.

## Migration v36 (drop tasks.is_heartbeat + synthetic rows)

Runs now carry `task_id = NULL` for heartbeat dispatches. The
`is_heartbeat` flag is dead data going forward.

1. `UPDATE runs SET task_id = NULL WHERE task_id IN (SELECT id FROM tasks WHERE is_heartbeat = 1)`
2. `DELETE FROM tasks WHERE is_heartbeat = 1` (synthetic rows, not real work)
3. Rebuild `tasks` without the `is_heartbeat` column (same defer-FK +
   row-count-assert pattern as v35)

## Code cleanup

- `RunRecord.taskId: string | null`; `createRun` / `cancelRunForDeletion`
  / `finishRun` guard every `UPDATE tasks` path with a null-check.
- `TaskRecord.isHeartbeat` removed; every SELECT / filter / UI reference
  dropped.
- Delete `acquireHeartbeatTask` / `findReusableHeartbeatTask` /
  `cleanupDuplicateHeartbeatTasks` — dead after the constraint lifts.
- Delete `src/main/orchestration/heartbeat-task.ts` (pure workaround
  constant file).
- `heartbeat.ts` creates runs with `taskId: null` when the agent has no
  assigned work. Turn context already supports nullable task
  (heartbeatFallbackSection); prompt surface unchanged.
- `validateTaskCreation` drops the `isHeartbeat` parameter — user-
  authored + automation-authored tasks are never heartbeat.
- Renderer: `run.taskId ? taskMap.get(...) : undefined` in Dashboard /
  RunCenter / RunDetail / RunQueue.
- Delete `tests/unit/heartbeat-coalescing.test.ts` (12 tests that
  exercised the deleted DB methods).
- Drop 1 isHeartbeat-bypass test from `task-quality-gates.test.ts`.

## Grep verification

- `isHeartbeatTaskTitle src/` → 0
- `acquireHeartbeatTask src/` → migration comment only
- `is_heartbeat src/` → schema.ts migration history only
- `isHeartbeat src/` → 0

Tests: 578/578 (was 591 — delta is 13 tests that tested deleted code).
This commit is contained in:
ZacharyZhang-NY committed 2026-04-17 16:16:08 -04:00
1 parent 92795f7bfb
commit 7e1d4199ee
44 files changed
+385 -674

No files matched your search

+23 -15
View File
@@ -60,7 +60,7 @@ export function buildRunMethods(
createRun(input: {
id?: string;
companyId: string;
taskId: string;
taskId: string | null;
agentId: string;
workspaceId: string | null;
connectorId: ConnectorId;
@@ -74,7 +74,9 @@ export function buildRunMethods(
"insert into runs (id, company_id, task_id, agent_id, workspace_id, connector_id, status, summary, unattributed_cost, log_path, created_at, updated_at) values (?, ?, ?, ?, ?, ?, 'queued', '', 0, ?, ?, ?)",
)
.run(id, input.companyId, input.taskId, input.agentId, input.workspaceId, input.connectorId, logPath, ts, ts);
getDb().prepare("update tasks set active_run_id = ?, updated_at = ? where id = ?").run(id, ts, input.taskId);
if (input.taskId !== null) {
getDb().prepare("update tasks set active_run_id = ?, updated_at = ? where id = ?").run(id, ts, input.taskId);
}
});
writeFileSync(logPath, "", "utf8");
return { id, logPath };
@@ -163,7 +165,7 @@ export function buildRunMethods(
unattributedCost: boolean;
}) {
const run = getDb().prepare("select task_id as taskId, agent_id as agentId, company_id as companyId, connector_id as connectorId from runs where id = ?").get(input.runId) as
| { taskId: string; agentId: string; companyId: string; connectorId: ConnectorId }
| { taskId: string | null; agentId: string; companyId: string; connectorId: ConnectorId }
| undefined;
if (!run) return { budgetHardStopped: false };
const ts = nowIso();
@@ -198,14 +200,18 @@ export function buildRunMethods(
input.signal, input.model, input.sessionDisplayId, runCostUsd,
input.unattributedCost ? 1 : 0, ts, ts, input.runId,
);
getDb().prepare("update tasks set active_run_id = null, updated_at = ? where id = ?").run(ts, run.taskId);
getDb()
.prepare("UPDATE tasks SET checkout_run_id = NULL, execution_locked_at = NULL, updated_at = ? WHERE id = ? AND checkout_run_id = ?")
.run(ts, run.taskId, input.runId);
if (runCostUsd > 0) {
if (run.taskId !== null) {
getDb().prepare("update tasks set active_run_id = null, updated_at = ? where id = ?").run(ts, run.taskId);
getDb()
.prepare("update tasks set cost_usd = cost_usd + ?, updated_at = ? where id = ?")
.run(runCostUsd, ts, run.taskId);
.prepare("UPDATE tasks SET checkout_run_id = NULL, execution_locked_at = NULL, updated_at = ? WHERE id = ? AND checkout_run_id = ?")
.run(ts, run.taskId, input.runId);
}
if (runCostUsd > 0) {
if (run.taskId !== null) {
getDb()
.prepare("update tasks set cost_usd = cost_usd + ?, updated_at = ? where id = ?")
.run(runCostUsd, ts, run.taskId);
}
getDb()
.prepare("update agents set spent_monthly_usd = spent_monthly_usd + ?, updated_at = ? where id = ?")
.run(runCostUsd, ts, run.agentId);
@@ -223,17 +229,19 @@ export function buildRunMethods(
return { budgetHardStopped };
},
cancelRunForDeletion(runId: string, taskId: string, workspaceId: string | null, summary: string) {
cancelRunForDeletion(runId: string, taskId: string | null, workspaceId: string | null, summary: string) {
const ts = nowIso();
getDb()
.prepare(
"update runs set status = 'cancelled', summary = ?, error_message = null, exit_code = null, signal = null, model = null, session_display_id = null, cost_usd = null, unattributed_cost = 1, finished_at = ?, updated_at = ? where id = ?",
)
.run(summary, ts, ts, runId);
getDb().prepare("update tasks set active_run_id = null, updated_at = ? where id = ?").run(ts, taskId);
getDb()
.prepare("UPDATE tasks SET checkout_run_id = NULL, execution_locked_at = NULL, updated_at = ? WHERE id = ? AND checkout_run_id = ?")
.run(ts, taskId, runId);
if (taskId !== null) {
getDb().prepare("update tasks set active_run_id = null, updated_at = ? where id = ?").run(ts, taskId);
getDb()
.prepare("UPDATE tasks SET checkout_run_id = NULL, execution_locked_at = NULL, updated_at = ? WHERE id = ? AND checkout_run_id = ?")
.run(ts, taskId, runId);
}
if (workspaceId) {
getDb()
.prepare(