fix: coordinate sqlite index writers

Implement the full ADR-0006 plan: three-layer separation of transaction
correctness, retry policy, and cross-process writer coordination.

Layer 1 — scripts/tx.ts (transaction correctness):
- runWriteTransaction executes work exactly once; no internal retry.
- BEGIN IMMEDIATE takes the write lock up front (avoids SQLITE_BUSY_SNAPSHOT).
- Guarded rollback: checks inTransaction() via adapter before attempting
  ROLLBACK; never masks the primary exception.
- WriteTxDiagnostics attached to errors: phase, code, label,
  rollbackSucceeded, rollbackError, transactionActive.
- Binding adapters (betterSqliteTransactionAdapter, nodeSqliteTransactionAdapter)
  mapping better-sqlite3's `.inTransaction` and node:sqlite's `.isTransaction`.
- configureConnection centralizes WAL + synchronous + busy_timeout.

Layer 2 — scripts/write-coordinator.ts (retry policy):
- runRetryableWriteTransaction: bounded retry with total time budget.
- Only retries when the transaction confirmed ended (transactionActive=false)
  and the error is SQLITE_BUSY during work/commit phase.
- BEGIN-phase BUSY = abort entire build (isBeginBusyFailure); the caller
  returns `{ deferred: true, reason: 'writer_busy' }` instead of waiting.
- hasUnusableTransaction detects a still-active transaction after failure;
  aborts the build immediately, never retries.

Layer 3 — scripts/writer-lease.ts (cross-process coordination):
- acquireWriterLease: dedicated writer.lock.sqlite with busy_timeout=0 +
  BEGIN IMMEDIATE. Non-blocking attempt; bounded wait with retryDelayMs.
- writerLockPathFor derives lock path from the target DB path.
- Lease held for the entire build; released on completion or failure.
- Lock DB uses DELETE journal (not WAL); crash/close auto-releases.
- All consumers obey: skill acquires at build start (returns deferred if
  unavailable); app daemon (via worker) acquires for its build cycle.

Build semantics changes:
- affectedSessionIds updated only after successful commit.
- BuildIndexResult gains skipped/skippedFiles for observability.
- Skill finalize failure now fails the build (was silently warned).
- Checkpoint changed to PASSIVE (TRUNCATE reserved for maintenance/exit).
- Skill buildIndex returns { deferred, reason } on lease contention;
  indexer-service reschedules the build (deferredRetryMs) without publishing
  a heartbeat (so the build-deferred state is visible to cross-process
  arbitration).
- Service publishes heartbeat immediately on start() for correct arbitration.

Tests:
- tests/write-transaction.test.mjs: single-shot execution, diagnostics
  propagation, auto-rolled-back transaction detected, rollback failure
  captured as metadata, BEGIN IMMEDIATE semantics.
- tests/writer-lease.test.mjs: acquire/release, contention returns null,
  bounded wait with release during budget.
- tests/app-writer-lease.test.mjs: better-sqlite3 adapter integration.
- tests/app-rollback-guard.test.mjs: rewritten — transient BUSY recovered
  by coordinator, persistent BUSY skips file, begin-busy aborts build,
  live-transaction aborts build, phantom affectedSessionIds prevented.
- tests/daemon-arbitration.test.mjs: skill defers to fresh app heartbeat,
  builds when heartbeat is stale.
- tests/app-indexer-service.test.mjs: new cases for deferred-retry
  scheduling and immediate heartbeat on start.
- app/tests/electron-concurrency.mjs + child: dual-child IPC structure for
  real better-sqlite3 contention (holder acquires lock → build child starts
  → delayed release → result collected; persistent contention bounded).

ADR-0006 updated to reflect the implemented design.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
tommy0103
2026-07-11 00:42:43 +08:00
co-authored by Claude Opus 4.8
parent 44029676d4
commit e3e61cc7ab
25 changed files with 2173 additions and 471 deletions
+95
View File
@@ -0,0 +1,95 @@
// Bounded retry policy above the transaction primitive. Callers opt in only for
// idempotent work; BEGIN contention and an uncertain/live transaction are never
// retried here.
import { runWriteTransaction, type WriteTxDb, type WriteTxOptions } from './tx.ts';
interface TransactionDiagnostics {
phase?: string;
code?: string | null;
transactionActive?: boolean | null;
attempts?: number;
}
export interface WriteRetryOptions {
maxAttempts?: number;
budgetMs?: number;
retryDelayMs?: number;
now?: () => number;
sleep?: (ms: number) => void;
}
function diagnostics(error: unknown): TransactionDiagnostics | null {
if (!error || typeof error !== 'object') return null;
return (error as { obelisk?: TransactionDiagnostics }).obelisk ?? null;
}
function isBusyCode(code: unknown): boolean {
return typeof code === 'string' && code.startsWith('SQLITE_BUSY');
}
function syncSleep(ms: number): void {
if (ms <= 0) return;
try {
Atomics.wait(new Int32Array(new SharedArrayBuffer(4)), 0, 0, ms);
} catch {
// Bounded attempts still prevent an infinite retry loop.
}
}
export function isBeginBusyFailure(error: unknown): boolean {
const info = diagnostics(error);
return (
info?.phase === 'begin' &&
isBusyCode(info.code) &&
info.transactionActive === false
);
}
export function hasUnusableTransaction(error: unknown): boolean {
const info = diagnostics(error);
return Boolean(info && info.transactionActive !== false);
}
export function isRetryableWriteFailure(error: unknown): boolean {
const info = diagnostics(error);
return (
(info?.phase === 'work' || info?.phase === 'commit') &&
isBusyCode(info.code) &&
info.transactionActive === false
);
}
export function runWithWriteRetry<T>(operation: () => T, {
maxAttempts = 3,
budgetMs = 1000,
retryDelayMs = 25,
now = Date.now,
sleep = syncSleep,
}: WriteRetryOptions = {}): T {
const startedAt = now();
for (let attempt = 1; ; attempt += 1) {
try {
return operation();
} catch (error) {
const info = diagnostics(error);
if (info) info.attempts = attempt;
if (!isRetryableWriteFailure(error) || attempt >= maxAttempts) throw error;
const remaining = budgetMs - (now() - startedAt);
if (remaining <= 0) throw error;
sleep(Math.min(retryDelayMs * attempt, remaining));
}
}
}
export function runRetryableWriteTransaction<T>(
db: WriteTxDb,
work: () => T,
transactionOptions: WriteTxOptions = {},
retryOptions: WriteRetryOptions = {},
): T {
return runWithWriteRetry(
() => runWriteTransaction(db, work, transactionOptions),
retryOptions,
);
}