From 76cd972bdeea9ef07b4b38e9d8b5b5ed3312ca5b Mon Sep 17 00:00:00 2001 From: victorsteele428 Date: Sun, 22 Nov 2026 15:33:14 +0600 Subject: [PATCH] fix(p02): guard Redis ACK and dedupe CSV crash-window replays [skip ci] --- core/data/buffer.ts | 78 +++++++++++++++++++++-- notes/001-PRODUCTION-FORENSIC-AUDIT.md | 11 ++++ notes/002-PRODUCTION-UPDATE-ROADMAP.md | 9 +++ notes/003-PHASE-STATUS-LOG.md | 16 +++++ notes/004-ERROR-HANDLING-REGISTER.md | 12 ++++ notes/005-ACTUAL-FEATURE-REGISTER.md | 8 +++ notes/006-BASELINE-AND-PATCH-EVIDENCE.md | 22 +++++++ server/index.js | 80 ++++++++++++++++++++++-- server/socket/handlers.js | 63 ++++++++++++++++--- tests/phase02-sync.test.ts | 59 ++++++++++++++++- tests/phase03-storage-buffer.test.ts | 52 ++++++++++++++- 11 files changed, 388 insertions(+), 22 deletions(-) diff --git a/core/data/buffer.ts b/core/data/buffer.ts index 661f9e0..9e37623 100644 --- a/core/data/buffer.ts +++ b/core/data/buffer.ts @@ -650,6 +650,66 @@ export class DataBufferEngine { } const executeFlush = async (): Promise => { + + // P02 R-02: examine CSV partitions before replay of an untrimmed Redis + // batch. Streaming parsing limits memory and handles escaped/newline CSV. + const excludeAlreadyPersisted = async (events: DataEvent[]): Promise => { + if (!events.length) return events; + const fs = await import('node:fs'); + const path = await import('node:path'); + const zlib = await import('node:zlib'); + const { pipeline } = await import('node:stream/promises'); + const { Writable } = await import('node:stream'); + const { parse } = await import('csv-parse'); + const groups = new Map; + }>(); + for (const event of events) { + const clientId = String(event.clientId || 'unknown'); + const date = CSVStorageManager.extractSafePartitionDate(event.timestamp); + const key = JSON.stringify([clientId, date]); + if (!groups.has(key)) groups.set(key, { clientId, date, ids: new Set() }); + groups.get(key)!.ids.add(String(event.eventId)); + } + const persisted = new Set(); + for (const [groupKey, group] of groups) { + const dir = CSVStorageManager.ensureClientDir(group.clientId); + const entries = await fs.promises.readdir(dir, { withFileTypes: true }); + for (const entry of entries) { + if (!entry.isFile() || + !/\.csv(?:\.gz)?$/.test(entry.name) || + CSVStorageManager.extractSafePartitionDate( + entry.name.replace(/\.csv(?:\.gz)?$/, '').replace(/(?:-(?:part|gz)\d+)+$/, ''), + ) !== group.date) continue; + const reader = fs.createReadStream(path.join(dir, entry.name)); + const parser = parse({ columns: true, bom: true, skip_empty_lines: true }); + const sink = new Writable({ + objectMode: true, + write(row: { clientId?: string; eventId?: string }, _enc, done) { + if (row.clientId === group.clientId && group.ids.has(String(row.eventId))) { + persisted.add(JSON.stringify([groupKey, String(row.eventId)])); + } + done(); + }, + }); + if (entry.name.endsWith('.gz')) { + await pipeline(reader, zlib.createGunzip(), parser, sink); + } else { + await pipeline(reader, parser, sink); + } + } + } + const batchSeen = new Set(); + return events.filter((event) => { + const key = JSON.stringify([String(event.clientId || 'unknown'), + CSVStorageManager.extractSafePartitionDate(event.timestamp)]); + const rowKey = JSON.stringify([key, String(event.eventId)]); + if (persisted.has(rowKey) || batchSeen.has(rowKey)) return false; + batchSeen.add(rowKey); + return true; + }); + }; + state.isFlushing = true; let totalWritten = 0; let lockTimedOut = false; @@ -793,9 +853,12 @@ export class DataBufferEngine { if (lockLost) break; if (parsedBatch.length > 0) { - const res = await CSVStorageManager.appendBatch(parsedBatch); - totalWritten += res.written; - for (const f of res.filesUpdated) filesSet.add(f); + const unwritten = await excludeAlreadyPersisted(parsedBatch); + if (unwritten.length > 0) { + const res = await CSVStorageManager.appendBatch(unwritten); + totalWritten += res.written; + for (const f of res.filesUpdated) filesSet.add(f); + } } if (Date.now() - lastRenewAt >= renewIntervalMs) { @@ -845,9 +908,12 @@ export class DataBufferEngine { if (validRamBatch.length > 0) { try { - const res = await CSVStorageManager.appendBatch(validRamBatch); - totalWritten += res.written; - for (const f of res.filesUpdated) filesSet.add(f); + const unwritten = await excludeAlreadyPersisted(validRamBatch); + if (unwritten.length > 0) { + const res = await CSVStorageManager.appendBatch(unwritten); + totalWritten += res.written; + for (const f of res.filesUpdated) filesSet.add(f); + } } catch (err) { state.buffer.unshift(...validRamBatch); throw err; diff --git a/notes/001-PRODUCTION-FORENSIC-AUDIT.md b/notes/001-PRODUCTION-FORENSIC-AUDIT.md index 52b75d1..7e2cf40 100644 --- a/notes/001-PRODUCTION-FORENSIC-AUDIT.md +++ b/notes/001-PRODUCTION-FORENSIC-AUDIT.md @@ -89,3 +89,14 @@ Source freeze for P02: Gitea/GitHub main `667a140c4e9e75382bfdcdbe1d3e9eb96f6e80 - **R-03 health:** `server/index.js:1926-1957` returns HTTP 200 `status:online` when Redis LLEN fails, while surfacing `redisConnected:false`; the historical route is **liveness**, not dependency readiness. `app/api/health/route.ts:95-111` likewise reports web liveness/buffer and does not prove database/Redis write readiness. A new readiness endpoint or altered public response requires separate approval. Do not auto-fix source based solely on tests. Runtime code is READ-ONLY under the current approval. Any proven R-01/R-02 risk requiring behavior change needs a new exact method/file approval before application changes. P03 remains independent and unstarted. + + +## P02 Runtime Remediation Candidate — 2026-11-22 (NOT YET VERIFIED) + +Authorized follow-up baseline: Gitea/GitHub `fd57a3518d14bcb8367ce9ab9c3ec306bcfc9898` (GitLab same tree). Local isolated branch `p02-runtime-remediation-20261122`, implementation commit `44eee8877e40d1683f44502c2a0ba3d437a03b88`. Scope: **server/index.js** (`pushEventsToRedisOrFallback`, `flushBuffer`), **server/socket/handlers.js** (sync_data/batch_sync ACK and claim rollback), **core/data/buffer.ts** (`flush`), **tests/phase02-sync.test.ts** and **tests/phase03-storage-buffer.test.ts** only, plus notes/001–006. All other source is unchanged. + +**Candidate R-01 behavior:** when a configured Redis client returns an RPUSH error, `pushEventsToRedisOrFallback` retains RAM fallback but throws a sanitized `BUFFER_PERSIST_FAILED` instead of returning a durable-looking buffer count. Socket single/batch ACK returns `success:false`; best-effort Redis idempotency-key removal and bounded in-process negative-ACK marker handle ordinary retries. This is a **candidate** pending tests. When Redis is intentionally absent, historical RAM fallback is deliberately unchanged; it is not a universal durable-ACK guarantee. If Redis claim deletion fails and the server restarts, stale Redis idempotency claims could still misclassify a retry; a full crash-atomic claim/queue protocol is **not established** by this patch. + +**Candidate R-02 behavior:** Port 4000 `flushBuffer` and Port 3000 `DataBufferEngine.flush` stream-parse existing CSV/CSV.gz partitions for same-client/date/event IDs before replaying any buffered Redis or RAM batch, dropping already-persisted IDs while retaining Redis queue until the write/check completes. Scan/read/parse exceptions fail closed before LTRIM. In-scope test adds a direct Port 4000 writer + Redis LTRIM-failure/recovery test and updates the existing web-buffer replay fixture. **Not proven globally exactly-once:** cross-process CSV writers outside the Redis flush lock and unknown archival/partial-corruption cases remain; scanning partitions on each flush also has real disk-I/O cost, requiring throughput evaluation before production promotion. + +**Candidate acceptance:** one disposable Gitea CI with 24/24 suites, strict TS, lint, Linux/Windows clean npm CI and production build; direct Port4000 replay tests; exact allowlist/diff audit and three-remote tree parity. The Gitea MCP/host was unavailable on the implementation attempt, so this is **NOT PASSED** and the P02 phase remains **BLOCKED / NOT CLOSED**. No live deployment or runtime production mutation. diff --git a/notes/002-PRODUCTION-UPDATE-ROADMAP.md b/notes/002-PRODUCTION-UPDATE-ROADMAP.md index 7b6df8d..c4e1799 100644 --- a/notes/002-PRODUCTION-UPDATE-ROADMAP.md +++ b/notes/002-PRODUCTION-UPDATE-ROADMAP.md @@ -81,3 +81,12 @@ P02 approved as **diagnostic-only**. Published P01 baseline: `667a140c4e9e75382b `APPROVED — DataStack P02-RUNTIME-REMEDIATION. Baseline: use the verified P02 diagnostic commit/remote tree. Fix reproduced R-01 and R-02 only, following exact notes/001–006 proof and scoped server/index.js pushEventsToRedisOrFallback/onBufferPush and flushBuffer, server/socket/handlers.js sync_data/batch_sync ACK, and their three existing P02 test files. First document safe ACK/retry semantics, exactly-once versus at-least-once CSV contract and crash recovery. Add disposable fault tests proving no positive ACK for non-durable data and no unbounded duplicate replay. Runtime sources core/data/buffer.ts and server/workers/csvWriter.js remain READ-ONLY unless a separately justified exact file/line amendment is approved. Preserve all UI/auth/SDK/public health behavior and existing error codes, production data, security, other features and Docker. One focused CI, diff/security audit, notes update, commit and 3-remote parity. No deployment, migrations, tags/releases or scope expansion. If a safe fix cannot be achieved within these exact methods, stop and report the required additional Scope Lock rather than broadening automatically.` After separate approved remediation and verified P02 closure, **P03 plan** remains CI-06 Linux Python runner provisioning, CI-07 isolated Docker/BuildKit failure remediation and 3-image build, CI-08 supply-chain advisory triage, and non-mutating readiness evidence. P03 should not modify unrelated UI/runtime/API code by default. + + +## P02 Runtime Remediation Execution Handoff — 2026-11-22 + +The user explicitly approved **only** R-01 Redis failure ACK and R-02 Redis-to-CSV replay corrections in these methods: `server/index.js` `pushEventsToRedisOrFallback` / `flushBuffer` / existing `onBufferPush` integration; `server/socket/handlers.js` `sync_data` / `batch_sync` ACK handling; `core/data/buffer.ts` `flush` if needed; the three earlier P02 test files; `notes/001–006`. No other application method/UI/API/auth/SDK/Docker/CI-workflow edit. Public R-03 `/health` semantics remain unchanged. + +Local candidate `44eee8877e40d1683f44502c2a0ba3d437a03b88` is **not release-ready** until Gitea acceptance. Before closure, prove: negative ACK on Redis failure with no sensitive error leakage; ordinary successful Redis ACK preserved; both single and batch retries don't convert volatile failures to success; Redis queued event replays after crash without writing duplicate CSV rows in the Port 4000 worker and Port 3000 web buffer; CSV read/parse failure never causes premature Redis trim; validate bounded scan overhead and edge cases for rotated/gzipped partitions; all historical 401/403/429/507/503 tests unchanged. + +**Stop rule:** if required fixes need touching `validateSingleEventAsync`, `csvWriter.js` or separate journal/storage scheme, do not broaden the implementation scope; record the residual and request new explicit approval. Existing unrelated files including `MEMORY.md` remain unchanged due exact Scope Lock; this note is the cross-IDE handoff. P03 must wait for P02 CLOSED, not merely implementation committed. diff --git a/notes/003-PHASE-STATUS-LOG.md b/notes/003-PHASE-STATUS-LOG.md index 32a61ca..d71ce12 100644 --- a/notes/003-PHASE-STATUS-LOG.md +++ b/notes/003-PHASE-STATUS-LOG.md @@ -91,3 +91,19 @@ Historical baseline code stayed frozen through these CI workflow changes. Curren - **BLOCKING RELEASE FINDINGS:** R-01 success ACK issued for non-durable RAM fallback when Redis RPUSH fails; R-02 identical eventId can append twice on post-CSV Redis-trim failure (web-side representative test). R-03 health remains online on Redis loss; liveness-only behavior is backward-compatible, protected dependency-readiness verification remains missing. - **P02 PHASE = BLOCKED**, diagnostic implementation done, release reliability acceptance NOT satisfied. Runtime remediation requires separate exact approval. 1/3 phases still CLOSED (P01 only); P02 and P03 remain unclosed. No P03 start authorization from this diagnostic completion. - Next approval must explicitly authorize exact narrow server/core patch for ACK durability and CSV replay deduplication, plus concrete no-loss/no-duplicate tests. Any readiness endpoint change needs separate explicit approval. User's initial P02 approval is insufficient for runtime mutation. + + +## P02-RUNTIME-REMEDIATION — Candidate implementation checkpoint (2026-11-22) + +- **Current P02: BLOCKED / NOT CLOSED.** One previous diagnostic Gitea CI #63 reproduced R-01/R-02/R-03; runtime remediation was separately approved after that. Verified completed implementation phases remain **1/3** (P01 only). Do not approve P03 yet. +- Published P02 diagnosis baseline `fd57a3518d14bcb8367ce9ab9c3ec306bcfc9898`; isolated local candidate commit `44eee8877e40d1683f44502c2a0ba3d437a03b88` on `p02-runtime-remediation-20261122`. +- Exactly five code/test files changed in this candidate: `server/index.js`, `server/socket/handlers.js`, `core/data/buffer.ts`, `tests/phase02-sync.test.ts`, `tests/phase03-storage-buffer.test.ts`. No `server/workers/csvWriter.js`, `app/**`, `components/**`, SDK, public R-03 health, CI workflow, database, migration, production data, secrets or deployment touched. +- JS `node --check` on two changed JS files PASS; `git diff --check` PASS and allowlist audit PASS. Targeted TS/Node regression and Gitea CI **NOT YET RUN TO TERMINAL PASS**. The Gitea connector/host was unavailable when dispatch/push was attempted. Local temporary dependency installation also not yet complete. +- The original user PC root `D:\VibTools_Workspace\01_Products\14_DataStack` still has 16 pre-existing staged P01 paths on older `d8ac96e`; deliberately preserved without reset/stash/discard. All P02 implementation is in a separate temporary worktree. Do not assume the old local root is up to date. +- R-01 and R-02 implementations are candidates; practical reliability limitations and I/O cost recorded in `notes/001` and `notes/004`. No false claim of globally exactly-once CSV or universally durable ACK. +- **Next gates:** restore Gitea access; run one focused disposable acceptance; fix any in-scope test/TS defects; record exact CI terminal results; only after required acceptance and security audit, squash single phase main commit and verify GitHub/GitLab/Gitea tree parity; then, and only then, decide P02 CLOSED versus residual-risk blocker. + + +### Verification environment blocker — local dependency install + +The authorized Windows PC attempted a **local disposable** `npm.cmd ci --ignore-scripts --no-audit --no-fund --prefer-offline` in the isolated P02 worktree only; it failed with `npm ERR! ETARGET No matching version found for yaml@2.9.1` plus cleanup EPERM warnings in the temp worktree's `node_modules`. Exact output captured in `%TEMP%\DataStack-P02-npm-ci.log` on the authorized PC. This is **not a passed code test nor proof of a repository package defect**, and `package-lock.json` / `package.json` cannot be edited under P02 scope. Gitea MCP remained UNAVAILABLE and the Git remote/HTTP service was not responding when CI was attempted, so the mandatory P02 focused CI was **not dispatched**. Phase remains BLOCKED pending actual CI evidence; no runtime change was pushed to production/main. diff --git a/notes/004-ERROR-HANDLING-REGISTER.md b/notes/004-ERROR-HANDLING-REGISTER.md index 6ea9755..017e53c 100644 --- a/notes/004-ERROR-HANDLING-REGISTER.md +++ b/notes/004-ERROR-HANDLING-REGISTER.md @@ -64,3 +64,15 @@ The previous #58 package-lock error was resolved by adding the exact nested opti | R-03 availability | Redis `llen` rejection leaves Express `/health` online with `redisConnected:false`. Recovery flips the flag while HTTP 200 remains unchanged. | Public 200 is liveness by existing contract; a protected dependency readiness probe/503 is **not implemented** and needs explicit approval. | Security invariants: do not expose secrets in ACK/errors, keep JWT/auth and 401/403/429/503/507 contracts unchanged, and never run failure-injection against actual Redis, Postgres, production API, live events, or user CSV. Disposable fake Redis and temporary files only. CI #63: https://dev.ivib.cc/vibtools/DataStack/actions/runs/63; results tracked in notes/003. + + +## P02 Runtime Candidate — Error-path change inventory (pending CI) + +| Path | Candidate result | Explicit limitation | +|---|---|---| +| Redis `RPUSH` rejects with configured Redis client | Retains event in volatile RAM as preexisting fallback but returns `BUFFER_PERSIST_FAILED` to Socket.IO via thrown error; **no successful ACK** for that failure; error text does not expose connection details | No-Redis intentional legacy RAM mode unchanged, still not a durable guarantee | +| `sync_data` and `batch_sync` failures | `success:false`, `code:BUFFER_PERSIST_FAILED` and best-effort rollback of previously claimed idempotency keys, negative failure marker for in-process retries | If claim rollback cannot reach Redis and process crashes, durable claim/queue atomicity remains unsolved | +| Redis buffer `LTRIM` rejects after successful CSV append | Subsequent flush checks physically stored CSV IDs and avoids appending matching rows again; Redis is trimmed only after successful check/write | Concurrent independent CSV appenders, compressed archived CSV, corrupt partial rows, and per-flush CSV scan cost require separate proof | +| Legacy public health | **UNCHANGED** HTTP 200 liveness contract and Redis-connected diagnostic field; R-03 readiness is not introduced in this approval | Does not prove full DB/Redis transactional readiness | + +Security/API invariants: leave token/JWT/auth/rate limits/quotas/webhooks/MCP/sandbox/UI/SDK unchanged. No production Redis/Postgres/API/CSV mutation. No lockfile/dependency versions or CI workflow changes. CI acceptance remains pending; these are code-level observations, not release certification. diff --git a/notes/005-ACTUAL-FEATURE-REGISTER.md b/notes/005-ACTUAL-FEATURE-REGISTER.md index c04fb43..bc2fa87 100644 --- a/notes/005-ACTUAL-FEATURE-REGISTER.md +++ b/notes/005-ACTUAL-FEATURE-REGISTER.md @@ -52,3 +52,11 @@ Do not mark "actual working" simply because a patch compiled. Distinguish source - R-02: existing CSV-before-Redis-trim order audited, *not corrected*. Exactly-once replay safety is **NOT VERIFIED**. - R-03: current public Express health 200 plus `redisConnected:false` is liveness, not dependency readiness. Separate readiness remains **NOT IMPLEMENTED**. - Gitea disposable CI #63: https://dev.ivib.cc/vibtools/DataStack/actions/runs/63. The previous P01 working results remain valid; no live read/write test or production deploy is included in P02. + + +## P02 Runtime Candidate Feature Delta — 2026-11-22 (NOT RELEASED) + +- **Intended change:** failure cases on socket ingestion report `BUFFER_PERSIST_FAILED` instead of positive ACK when Redis RPUSH rejects; single and batch code paths tested by new disposable assertions. Ordinary success ACK, auth, limits and SDK public interfaces intended unchanged. +- **Intended change:** Redis replay flush on both ingestion/Next paths inspects existing client CSV partitions and filters already-stored event IDs before reappend; safe failure leaves Redis queue untrimmed. This prevents the tested post-append/LTRIM replay duplication but does **not** prove transactionally exactly-once delivery or zero performance impact. +- **No changes:** application UI/UX, auth, SDK, database schema, Docker, environment, public R-03 health, other features and production runtime. No deployment or live verification. +- **Status:** P02 code candidate locally committed, acceptance CI blocked by Gitea unavailability; **NOT CLOSED**, not production-ready. P01 remains only completed phase. diff --git a/notes/006-BASELINE-AND-PATCH-EVIDENCE.md b/notes/006-BASELINE-AND-PATCH-EVIDENCE.md index f8470de..2812376 100644 --- a/notes/006-BASELINE-AND-PATCH-EVIDENCE.md +++ b/notes/006-BASELINE-AND-PATCH-EVIDENCE.md @@ -237,3 +237,25 @@ return bufferQueue.length; - `P02 R-03 diagnostic: Redis query failure leaves public ingestion health 200/online` — **ok 16**, same suite exit 0, Redis flag false while liveness stays online. - `P02 R-02 diagnostic: post-CSV Redis trim failure replays identical event on retry` — **ok 18**, `phase03-storage-buffer` suite exit 0; duplicate append after retry reproduced on representative web buffer path. **Direct ingestion Port 4000 CSV worker crash coverage remains outstanding** and should be requested in remediation approval before guarantee changes. - These three diagnostic tests **prove findings, do not close production-readiness**. See Gitea https://dev.ivib.cc/vibtools/DataStack/actions/runs/63; never call run successful until terminal conclusion is confirmed. No server-side source fix applied. + + +## F. P02 Remediation Candidate Patch Proof — 2026-11-22 + +Base: Gitea/GitHub published P02 diagnostic tree `fd57a3518d14bcb8367ce9ab9c3ec306bcfc9898`; GitLab distinct commit, same previous tree. Local candidate commit `44eee8877e40d1683f44502c2a0ba3d437a03b88` on isolated worktree. Initial exact delta: 5 approved source/test paths, 310 insertions and 22 deletions, no application UI, Python SDK, auth, public health route, CI or deployment edit. `git diff --check` and `node --check` on JS files PASS. + +- `server/index.js:pushEventsToRedisOrFallback`: catch RPUSH failure, keep previous RAM buffering, throw sanitized `BUFFER_PERSIST_FAILED`; no positive ACK for that branch. +- `server/socket/handlers.js:sync_data/batch_sync`: negative ACK and best-effort claimed idempotency-key rollback with negative retry guard, no change to legitimate duplicate success path or existing auth/limits/error codes. +- `server/index.js:flushBuffer` and `core/data/buffer.ts:flush`: scoped streaming CSV/CSV.gz read-before-reappend (parsing quoted/multiline rows), exact client/date/event ID match; failures abort before Redis LTRIM. No changes to `server/workers/csvWriter.js`. +- `tests/phase02-sync.test.ts`: R-01 single/batch outage and duplicate claim ACK negative, successful recovery ACK, and unchanged R-03 liveness. +- `tests/phase03-storage-buffer.test.ts`: web-side replay verifies exactly one physically stored row; new direct Port 4000 writer Redis-trim failure/recovery proof. All tests on fake Redis and disposable temp CSV paths. + +**Unverified:** Gitea P02 implementation acceptance was unavailable due inaccessible host/connector. Local `npm ci` not confirmed successful. Do not invent a CI run ID or claim full PASS. Full cross-process transactional exactly-once and all Redis claim crash windows are out of proof scope and may require exact additional approval. The streaming dedupe scan changes I/O cost per flush; performance validation before production is required. + + +### Blocked acceptance evidence — actual tool outcomes + +- JS syntax: local `node --check server/index.js` and `node --check server/socket/handlers.js` PASS. +- Source scope: local `git diff --check` PASS; only the five allowed P02 runtime/test paths changed before notes updates. +- Gitea: connection returned `UNAVAILABLE: McpServerError: Connection failed`; Git remote `dev.ivib.cc` unresponsive. No Gitea CI run ID exists for candidate `44eee8877e40d1683f44502c2a0ba3d437a03b88`. +- Local Windows npm: `npm ci` failed `ETARGET yaml@2.9.1` and cleanup `EPERM` in the isolated worktree, **not** a TypeScript/test result. Dependency changes are out of P02 scope. +- Therefore neither TS typecheck nor regression-suite remediation acceptance is established; keep P02 BLOCKED and do not advance P03 or alter any protected runtime/source beyond this approval. diff --git a/server/index.js b/server/index.js index f0c60f4..a605320 100644 --- a/server/index.js +++ b/server/index.js @@ -165,6 +165,7 @@ function setRedisClientForTests(client) { async function pushEventsToRedisOrFallback(events) { if (!events || events.length === 0) return bufferQueue.length; const redis = getRedisClient(); + let persistFailed = false; if (redis) { const serialized = events.map((e) => JSON.stringify(e)); let bufferLen = null; @@ -173,6 +174,7 @@ async function pushEventsToRedisOrFallback(events) { redisConnected = true; } catch { redisConnected = false; + persistFailed = true; } if (bufferLen !== null) { @@ -189,6 +191,11 @@ async function pushEventsToRedisOrFallback(events) { } bufferQueue.push(...events); + if (persistFailed) { + // Keep the volatile fallback for later recovery, but never ACK it as durable. + // Suppress sensitive Redis transport details in the client-facing error. + throw new Error('BUFFER_PERSIST_FAILED: Redis unavailable; event not durably queued'); + } return bufferQueue.length; } @@ -834,6 +841,61 @@ async function isClientDeletedForFlush(clientId, redis, cache) { } async function flushBuffer(options = {}) { + + // P02 R-02: Redis and CSV cannot be committed atomically. Before replaying an + // untrimmed Redis batch, check actual CSV partitions for previously written IDs. + // Streaming parsing bounds memory and preserves multiline/quoted CSV fields. + const excludeAlreadyPersisted = async (events) => { + if (!events.length) return events; + const fs = require('node:fs'); + const path = require('node:path'); + const zlib = require('node:zlib'); + const { pipeline } = require('node:stream/promises'); + const { Writable } = require('node:stream'); + const { parse } = require('csv-parse'); + const groups = new Map(); + for (const event of events) { + const clientId = String(event.clientId || 'unknown'); + const date = writer.extractSafePartitionDate(event.timestamp); + const key = JSON.stringify([clientId, date]); + if (!groups.has(key)) groups.set(key, { clientId, date, ids: new Set() }); + groups.get(key).ids.add(String(event.eventId)); + } + const persisted = new Set(); + for (const [groupKey, group] of groups) { + const dir = writer.ensureClientDir(group.clientId); + const entries = await fs.promises.readdir(dir, { withFileTypes: true }); + for (const entry of entries) { + if (!entry.isFile() || !writer.isPartitionFilename(entry.name) || + writer.extractDateFromFilename(entry.name) !== group.date) continue; + const reader = fs.createReadStream(path.join(dir, entry.name)); + const streams = [reader]; + if (entry.name.endsWith('.gz')) streams.push(zlib.createGunzip()); + streams.push(parse({ columns: true, bom: true, skip_empty_lines: true })); + streams.push(new Writable({ + objectMode: true, + write(row, _enc, done) { + if (row.clientId === group.clientId && group.ids.has(String(row.eventId))) { + persisted.add(JSON.stringify([groupKey, String(row.eventId)])); + } + done(); + }, + })); + // On read/parse failure, abort without LTRIM: never discard uncertain rows. + await pipeline(...streams); + } + } + const batchSeen = new Set(); + return events.filter((event) => { + const key = JSON.stringify([String(event.clientId || 'unknown'), + writer.extractSafePartitionDate(event.timestamp)]); + const rowKey = JSON.stringify([key, String(event.eventId)]); + if (persisted.has(rowKey) || batchSeen.has(rowKey)) return false; + batchSeen.add(rowKey); + return true; + }); + }; + if (pendingRedisWrites.size > 0) { await Promise.allSettled([...pendingRedisWrites]); } @@ -979,9 +1041,12 @@ async function flushBuffer(options = {}) { if (lockLost) break; if (parsedBatch.length > 0) { - const res = await writer.writeBatch(parsedBatch); - totalWritten += res.written; - for (const f of res.files) filesSet.add(f); + const unwritten = await excludeAlreadyPersisted(parsedBatch); + if (unwritten.length > 0) { + const res = await writer.writeBatch(unwritten); + totalWritten += res.written; + for (const f of res.files) filesSet.add(f); + } } if (Date.now() - lastRenewAt >= renewIntervalMs) { @@ -1022,9 +1087,12 @@ async function flushBuffer(options = {}) { if (validBatch.length > 0) { try { - const res = await writer.writeBatch(validBatch); - totalWritten += res.written; - for (const f of res.files) filesSet.add(f); + const unwritten = await excludeAlreadyPersisted(validBatch); + if (unwritten.length > 0) { + const res = await writer.writeBatch(unwritten); + totalWritten += res.written; + for (const f of res.files) filesSet.add(f); + } } catch (err) { bufferQueue.unshift(...validBatch); throw err; diff --git a/server/socket/handlers.js b/server/socket/handlers.js index 917088c..fa406d3 100644 --- a/server/socket/handlers.js +++ b/server/socket/handlers.js @@ -549,6 +549,9 @@ function setupSocketHandlers(io, bufferQueue, worker, options = {}) { : new Date().toISOString(); const eventData = extractSingleEventData(payload); + // A previous Redis write failure can leave an uncommitted idempotency + // claim. Never report that claim as a successful durable duplicate. + const failedAt = idempotencyMap.get(`${clientId}:${eventId}`); const check = await validateSingleEventAsync( clientId, eventId, @@ -557,7 +560,13 @@ function setupSocketHandlers(io, bufferQueue, worker, options = {}) { ); if (!check.allowed) { if (check.duplicate) { - if (callback) { + if (typeof failedAt === "number" && failedAt < 0 && + Date.now() + failedAt < IDEMPOTENCY_TTL_MS) { + if (callback) callback({ + success: false, eventId, code: "BUFFER_PERSIST_FAILED", + error: "BUFFER_PERSIST_FAILED: Event not durably queued", + }); + } else if (callback) { callback({ success: true, eventId, note: "DUPLICATE_DROPPED" }); } return; @@ -585,6 +594,19 @@ function setupSocketHandlers(io, bufferQueue, worker, options = {}) { try { await onBufferPush(); } catch (persistErr) { + // Invalidate the pre-persistence idempotency claim so SDK retry can + // resubmit after Redis recovers. Keep the volatile RAM event pending. + const claimKey = `${clientId}:${eventId}`; + idempotencyMap.set(claimKey, -Date.now()); + const claimRedis = getRedisClient(); + if (claimRedis && typeof claimRedis.del === "function") { + try { + await claimRedis.del(`${REDIS_IDEMPOTENCY_PREFIX}${claimKey}`); + idempotencyMap.delete(claimKey); + } catch { + // Claim may remain: negative ACK must be retained for retries. + } + } if (callback) { callback({ success: false, @@ -689,6 +711,8 @@ function setupSocketHandlers(io, bufferQueue, worker, options = {}) { const rateLimitedEventIds = []; const oversizedEventIds = []; const errors = []; + const acceptedEventIds = []; + let volatileDuplicate = false; for (const item of batch) { const safeItem = item && typeof item === "object" ? item : {}; @@ -702,6 +726,7 @@ function setupSocketHandlers(io, bufferQueue, worker, options = {}) { : new Date().toISOString(); const rawData = extractBatchItemData(safeItem); + const failedAt = idempotencyMap.get(`${clientId}:${eventId}`); const check = await validateSingleEventAsync( clientId, eventId, @@ -710,7 +735,15 @@ function setupSocketHandlers(io, bufferQueue, worker, options = {}) { ); if (!check.allowed) { if (check.duplicate) { - duplicates += 1; + if (typeof failedAt === "number" && failedAt < 0 && + Date.now() + failedAt < IDEMPOTENCY_TTL_MS) { + rejected += 1; + volatileDuplicate = true; + if (errors.length < 5) errors.push( + `${eventId}: BUFFER_PERSIST_FAILED: Event not durably queued`); + } else { + duplicates += 1; + } continue; } rejected += 1; @@ -735,6 +768,7 @@ function setupSocketHandlers(io, bufferQueue, worker, options = {}) { payload: check.payloadStr, }); processed += 1; + acceptedEventIds.push(eventId); } if (processed > 0) { @@ -742,6 +776,19 @@ function setupSocketHandlers(io, bufferQueue, worker, options = {}) { try { await onBufferPush(); } catch (persistErr) { + const claimRedis = getRedisClient(); + for (const eventId of acceptedEventIds) { + const claimKey = `${clientId}:${eventId}`; + idempotencyMap.set(claimKey, -Date.now()); + if (claimRedis && typeof claimRedis.del === "function") { + try { + await claimRedis.del(`${REDIS_IDEMPOTENCY_PREFIX}${claimKey}`); + idempotencyMap.delete(claimKey); + } catch { + // Preserve negative-ACK retry guard if claim removal fails. + } + } + } if (callback) { callback({ success: false, @@ -760,11 +807,13 @@ function setupSocketHandlers(io, bufferQueue, worker, options = {}) { } if (processed === 0 && duplicates === 0 && rejected > 0) { - const code = hitPayloadLimit - ? "PAYLOAD_TOO_LARGE" - : hitRateLimit - ? "RATE_LIMIT_EXCEEDED" - : "BATCH_REJECTED"; + const code = volatileDuplicate + ? "BUFFER_PERSIST_FAILED" + : hitPayloadLimit + ? "PAYLOAD_TOO_LARGE" + : hitRateLimit + ? "RATE_LIMIT_EXCEEDED" + : "BATCH_REJECTED"; if (callback) { callback({ success: false, diff --git a/tests/phase02-sync.test.ts b/tests/phase02-sync.test.ts index 8d65f9d..6067ab5 100644 --- a/tests/phase02-sync.test.ts +++ b/tests/phase02-sync.test.ts @@ -1246,12 +1246,29 @@ test("P02 R-01 diagnostic: Redis RPUSH failure yields positive WS ACK for volati ); const committedRows = await failingRedis.lrange("datastack:buffer:events", 0, -1); const volatileRows = serverMod.bufferQueue.filter((e) => e.eventId === "p02-ack-before-crash-001"); - assert.equal(ack.success, true, "Existing handler currently sends a positive ACK after Redis failure"); + assert.equal(ack.success, false, "P02 remediation must reject non-durable ACK"); + assert.equal(ack.code, "BUFFER_PERSIST_FAILED"); + const sameIdRetry = await emitWithAck<{ success: boolean; code?: string }>( + socket, "sync_data", + { eventId: "p02-ack-before-crash-001", data: { value: 42 } }, + ); + assert.equal(sameIdRetry.success, false, + "Pending idempotency claims must not return false positive duplicate ACK"); + assert.equal(sameIdRetry.code, "BUFFER_PERSIST_FAILED"); assert.equal(committedRows.length, 0, "Fake Redis has no durable event"); assert.equal(volatileRows.length, 1, "Acknowledged event is RAM-only"); // Crash model: restart loses RAM but fake Redis survives. No actual process is killed. serverMod.bufferQueue.length = 0; assert.equal((await failingRedis.lrange("datastack:buffer:events", 0, -1)).length, 0); + // A new event may ACK only after Redis actually resumes persistence. + const healthyRedis = createSharedMockRedis(); + serverMod.setRedisClientForTests(healthyRedis); + const recovered = await emitWithAck<{ success: boolean; eventId?: string }>( + socket, "sync_data", + { eventId: "p02-ack-recovered-002", data: { value: 43 } }, + ); + assert.equal(recovered.success, true); + assert.equal((await healthyRedis.lrange("datastack:buffer:events", 0, -1)).length, 1); } finally { socket?.disconnect(); serverMod.setRedisClientForTests(undefined); @@ -1281,3 +1298,43 @@ test("P02 R-03 diagnostic: Redis query failure leaves public ingestion health 20 serverMod.setRedisClientForTests(undefined); } }); + +test("P02 R-01: batch_sync rejects non-durable Redis writes and pending duplicate claims", async () => { + const previousThreshold = serverMod.runtimeConfig.batchFlushThreshold; + const previousQueue = serverMod.bufferQueue.slice(); + const failingRedis = createSharedMockRedis(); + failingRedis.rpush = async () => { throw new Error("P02 injected batch Redis outage"); }; + serverMod.setRedisClientForTests(failingRedis); + serverMod.runtimeConfig.batchFlushThreshold = 100_000; + serverMod.bufferQueue.length = 0; + let socket: Socket | undefined; + const payload = [ + { eventId: "p02-batch-volatile-1", data: { value: 1 } }, + { eventId: "p02-batch-volatile-2", data: { value: 2 } }, + ]; + try { + const client = await SDKManager.registerClientAsync({ + clientId: "p02_redis_batch_failure", + name: "P02 Redis Batch Failure", + rateLimit: 100, + }); + socket = await connectSocket(client.token); + const ack = await emitWithAck<{ success: boolean; code?: string; processed?: number }>( + socket, "batch_sync", payload, + ); + assert.equal(ack.success, false); + assert.equal(ack.code, "BUFFER_PERSIST_FAILED"); + assert.equal(ack.processed, 0); + assert.equal((await failingRedis.lrange("datastack:buffer:events", 0, -1)).length, 0); + const retry = await emitWithAck<{ success: boolean; code?: string }>( + socket, "batch_sync", payload, + ); + assert.equal(retry.success, false); + assert.equal(retry.code, "BUFFER_PERSIST_FAILED"); + } finally { + socket?.disconnect(); + serverMod.setRedisClientForTests(undefined); + serverMod.runtimeConfig.batchFlushThreshold = previousThreshold; + serverMod.bufferQueue.splice(0, serverMod.bufferQueue.length, ...previousQueue); + } +}); diff --git a/tests/phase03-storage-buffer.test.ts b/tests/phase03-storage-buffer.test.ts index 6e971cd..a75652f 100644 --- a/tests/phase03-storage-buffer.test.ts +++ b/tests/phase03-storage-buffer.test.ts @@ -1584,10 +1584,58 @@ test("P02 R-02 diagnostic: post-CSV Redis trim failure replays identical event o assert.equal(await redis.llen(REDIS_BUFFER_KEY), 1, "Redis still queues previously appended CSV event"); await DataBufferEngine.flush(); assert.equal(await redis.llen(REDIS_BUFFER_KEY), 0); - assert.equal(writtenIds.filter((id) => id === event.eventId).length, 2, - "A second flush appends the same eventId again after failed trim: at-least-once, not exactly-once"); + assert.equal(writtenIds.filter((id) => id === event.eventId).length, 1, + "Replay must detect the persisted CSV eventId before attempting another append"); + const csvPath = path.join(tmpStorageDir, event.clientId, "2026-11-22.csv"); + const csvContents = fs.readFileSync(csvPath, "utf8"); + assert.equal(csvContents.split(event.eventId).length - 1, 1, + "Exactly one physical CSV row must exist after a failed LTRIM and retry"); } finally { CSVStorageManager.appendBatch = originalAppend; DataBufferEngine.setRedisClientForTests(undefined); } }); + +test("P02 R-02: Port 4000 CSV worker suppresses a crash-window replay after Redis LTRIM error", async () => { + const mockRedis = new FakeRedisClient(); + const originalTrim = mockRedis.ltrim.bind(mockRedis); + let failedOnce = false; + mockRedis.ltrim = async (key: string, start: number, stop: number): Promise<"OK"> => { + if (key === REDIS_BUFFER_KEY && !failedOnce) { + failedOnce = true; + throw new Error("P02 Port4000 injected post-CSV trim failure"); + } + return originalTrim(key, start, stop); + }; + const ingestion = require("../server/index.js") as IngestionServerModule; + const previousDir = ingestion.writer.baseDir; + const previousQueue = ingestion.bufferQueue.slice(); + ingestion.writer.baseDir = tmpStorageDir; + ingestion.bufferQueue.length = 0; + ingestion.setRedisClientForTests(mockRedis); + const evt: DataEvent = { + clientId: "p02_ingestion_replay", + eventId: "p02-port4000-001", + timestamp: "2026-11-22T13:00:00.000Z", + payload: JSON.stringify({ stage: "before-ltrim" }), + }; + try { + await mockRedis.rpush(REDIS_BUFFER_KEY, JSON.stringify(evt)); + await assert.rejects( + () => ingestion.flushBuffer(), + /P02 Port4000 injected post-CSV trim failure/, + ); + assert.equal(failedOnce, true); + assert.equal(await mockRedis.llen(REDIS_BUFFER_KEY), 1); + const csvPath = path.join(tmpStorageDir, evt.clientId, "2026-11-22.csv"); + assert.equal(fs.readFileSync(csvPath, "utf8").split(evt.eventId).length - 1, 1); + const recovered = await ingestion.flushBuffer(); + assert.equal(recovered.written, 0, "Recovered replay should not append the event again"); + assert.equal(await mockRedis.llen(REDIS_BUFFER_KEY), 0); + assert.equal(fs.readFileSync(csvPath, "utf8").split(evt.eventId).length - 1, 1); + } finally { + ingestion.writer.baseDir = previousDir; + ingestion.bufferQueue.splice(0, ingestion.bufferQueue.length, ...previousQueue); + ingestion.setRedisClientForTests(undefined); + } +});