diff --git a/CHANGELOG.md b/CHANGELOG.md index 76825c76d..30148c7ce 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -5,6 +5,16 @@ of current runtime behavior, see [`docs/CURRENT-STATE.md`](docs/CURRENT-STATE.md ## [Unreleased] +### Fixed + +- The Overpass proxy now rotates to the next mirror on any non-2xx upstream + response, not only on 5xx. `overpass-api.de` and its `lz4` alias answer 406 to + the proxy's User-Agent while two of the configured mirrors answer 200 to the + identical request, so the fan-out stopped at the first refusal with healthy + mirrors untried. The refusal was also cached to memory and disk and served as + data — boundary-class queries hold a month-long TTL — which affected every + Overpass-backed feature: road geometry, annotation outlines and place lookup. + ## [0.1.1] — 2026-09-01 — Installation and live-data fixes ### Changed diff --git a/docs/CURRENT-STATE.md b/docs/CURRENT-STATE.md index f86f627aa..b07da999a 100644 --- a/docs/CURRENT-STATE.md +++ b/docs/CURRENT-STATE.md @@ -2006,6 +2006,12 @@ silently demoting every later lookup for the session. - **Track trails**: server accumulates per-MMSI ring buffers (`/api/ais-live/track?mmsi=`, Float32+Uint32, 64 samples, 30s/25m thinning); aircraft backfill proxies `/api/opensky-track` (OAuth, own credit bucket) and `/api/adsblol/trace` (tar1090 readsb, ~24h history, ODbL — credit adsb.lol). - Shared `src/data/pickRegistry.js` stops the two flight layers' click handlers from fighting over the camera. +### Overpass proxy mirror rotation (September 2026) + +- `/api/overpass` fans out across four public mirrors. `overpassPayloadIsData()` is the single predicate deciding what counts as an answer, and it governs BOTH what enters the cache and when a stale entry may stand in, so the two cannot drift apart. Only a 2xx that is neither rate-limited nor a body-level runtime error is data. +- The rotation used to trigger on 5xx alone, so a 4xx ended the fan-out and was returned, cached to memory AND disk, and served to the client as data. Measured against the live mirrors: `overpass-api.de` and `lz4.overpass-api.de` answer **406** to the proxy's `User-Agent` while `overpass.kumi.systems` and `overpass.private.coffee` answer **200** to the byte-identical request — so every Overpass-backed feature failed on an Apache error page with two healthy mirrors untried, and four of twenty-three cached entries on the machine this was found on held that error page. Boundary-class queries carry a month-long TTL, so one refusal outlived its outage by weeks. +- A refusal every mirror agrees on is still reported with the first mirror's status and body, so a genuinely malformed query says what upstream said — but only after every mirror has had the chance to answer it. `fetchOverpassPayload` takes injectable endpoints and fetch so the rotation is tested without a live mirror (`src/overpassProxy.test.mjs`). + ### Share-link v2 layer state (August 2026) - Generated share links use a deterministic v2 hash. Existing camera, visual, diff --git a/src/overpassProxy.test.mjs b/src/overpassProxy.test.mjs new file mode 100644 index 000000000..e4357d4b0 --- /dev/null +++ b/src/overpassProxy.test.mjs @@ -0,0 +1,123 @@ +// OVERPASS PROXY — which upstream answers count as an answer. +// +// The proxy fans out across four public mirrors. What decides whether a mirror +// has answered is one predicate, and it is used TWICE: once to decide what +// enters the cache, and once to decide when a stale entry may stand in. When +// those two drifted, a refusal was written to memory and disk AND served as +// data — and boundary-class queries hold a month-long TTL, so a single refusal +// outlived the outage that caused it by weeks. +// +// The refusal was real and measured: overpass-api.de and its lz4 alias answer +// 406 to this proxy's User-Agent, while kumi.systems and private.coffee answer +// 200 to the identical request. Only 5xx rotated mirrors, so the fan-out +// stopped at the first refusal with two healthy mirrors untried, and four of +// twenty-three cached entries on this machine held an Apache error page. +// +// Run with: npm test +import { test } from 'node:test'; +import assert from 'node:assert/strict'; +import { fetchOverpassPayload, overpassPayloadIsData } from '../vite.config.js'; + +const ENDPOINTS = ['https://a.example/api', 'https://b.example/api', 'https://c.example/api']; + +/** Answer each endpoint from a map of url → {status, body}; record the order. */ +function mirrors(byUrl) { + const tried = []; + const fetchImpl = async (url) => { + tried.push(url); + const answer = byUrl[url]; + if (answer instanceof Error) throw answer; + return { status: answer.status, headers: { get: () => answer.contentType || 'application/json' } }; + }; + return { fetchImpl, tried, readBody: async (_, __) => byUrl[tried[tried.length - 1]]?.body ?? '' }; +} + +const run = (byUrl) => { + const m = mirrors(byUrl); + return fetchOverpassPayload('data=x', 1e6, { + endpoints: ENDPOINTS, + fetchImpl: m.fetchImpl, + readBody: m.readBody, + simplify: (body) => body, + }).then((payload) => ({ payload, tried: m.tried }), (error) => ({ error, tried: m.tried })); +}; + +const DATA = { status: 200, body: '{"elements":[]}' }; + +// ── The predicate ──────────────────────────────────────────────────────────── + +test('only a 2xx that is neither rate-limited nor a runtime error is data', () => { + assert.equal(overpassPayloadIsData({ status: 200 }), true); + assert.equal(overpassPayloadIsData({ status: 204 }), true); + + // The measured refusal, and its neighbours. `< 500` admitted every one. + for (const status of [400, 403, 406, 410, 429]) { + assert.equal(overpassPayloadIsData({ status }), false, `${status} is not data`); + } + assert.equal(overpassPayloadIsData({ status: 502 }), false); + // A 200 can still not be data: Overpass reports runtime failures in the body. + assert.equal(overpassPayloadIsData({ status: 200, runtimeError: true }), false); + assert.equal(overpassPayloadIsData({ status: 200, rateLimited: true }), false); + assert.equal(overpassPayloadIsData({}), false); + assert.equal(overpassPayloadIsData(null), false); +}); + +// ── The fan-out ────────────────────────────────────────────────────────────── + +test('a refusal moves to the next mirror instead of ending the fan-out', async () => { + // The exact shape measured against the live mirrors. + const { payload, tried } = await run({ + [ENDPOINTS[0]]: { status: 406, contentType: 'text/html', body: '406' }, + [ENDPOINTS[1]]: DATA, + [ENDPOINTS[2]]: DATA, + }); + + assert.equal(payload.status, 200); + assert.equal(payload.endpoint, ENDPOINTS[1]); + assert.deepEqual(tried, ENDPOINTS.slice(0, 2), 'the healthy mirror must be reached, and no further'); +}); + +test('the first mirror to answer wins, and the rest are left alone', async () => { + const { payload, tried } = await run({ + [ENDPOINTS[0]]: DATA, [ENDPOINTS[1]]: DATA, [ENDPOINTS[2]]: DATA, + }); + + assert.equal(payload.endpoint, ENDPOINTS[0]); + assert.deepEqual(tried, [ENDPOINTS[0]]); +}); + +test('a refusal every mirror agrees on is reported, not swallowed', async () => { + // A genuinely bad query must still say what upstream said — but only after + // every mirror has had its chance to answer it. + const refusal = { status: 400, body: 'line 1: parse error' }; + const { payload, tried } = await run({ + [ENDPOINTS[0]]: refusal, [ENDPOINTS[1]]: refusal, [ENDPOINTS[2]]: refusal, + }); + + assert.equal(payload.status, 400); + assert.equal(payload.endpoint, ENDPOINTS[0], 'the FIRST refusal is the one reported'); + assert.deepEqual(tried, ENDPOINTS); + assert.equal(overpassPayloadIsData(payload), false, 'so it is neither cached nor served as data'); +}); + +test('a mirror that throws is no different from one that refuses', async () => { + const { payload, tried } = await run({ + [ENDPOINTS[0]]: new Error('ECONNRESET'), + [ENDPOINTS[1]]: { status: 503, body: 'busy' }, + [ENDPOINTS[2]]: DATA, + }); + + assert.equal(payload.endpoint, ENDPOINTS[2]); + assert.deepEqual(tried, ENDPOINTS); +}); + +test('when every mirror is unreachable the caller gets a throw, not a payload', async () => { + const { error, payload } = await run({ + [ENDPOINTS[0]]: new Error('ECONNRESET'), + [ENDPOINTS[1]]: new Error('ETIMEDOUT'), + [ENDPOINTS[2]]: new Error('ENOTFOUND'), + }); + + assert.equal(payload, undefined); + assert.match(error.message, /ENOTFOUND/); +}); diff --git a/vite.config.js b/vite.config.js index 6edefe8e7..fbe27782b 100644 --- a/vite.config.js +++ b/vite.config.js @@ -2558,16 +2558,39 @@ function sendOverpassResponse(res, payload, cacheStatus = 'MISS') { * @param {number} [maxResponseBytes] Endpoint-specific response cap. * @returns {Promise<{status:number,body:string,contentType:string,endpoint:string,rateLimited:boolean}>} */ -async function fetchOverpassPayload(body, maxResponseBytes = OVERPASS_MAX_RESPONSE_BYTES) { +/** + * True only for an upstream response that is actually Overpass data. + * + * The proxy caches on this and serves stale on its negation, so the two + * decisions cannot drift apart: a payload that is not data must never be + * written to the cache and must always be eligible for a stale replacement. + * @param {{status: number, rateLimited?: boolean, runtimeError?: boolean}} payload + * @returns {boolean} + */ +export function overpassPayloadIsData(payload) { + const status = Number(payload?.status); + return Number.isFinite(status) + && status >= 200 && status < 300 + && !payload.rateLimited + && !payload.runtimeError; +} + +export async function fetchOverpassPayload(body, maxResponseBytes = OVERPASS_MAX_RESPONSE_BYTES, { + endpoints = OVERPASS_UPSTREAMS, + fetchImpl = fetch, + readBody = readResponseTextCapped, + simplify = simplifyOverpassPayloadBody, +} = {}) { let lastError = null; let lastRateLimitPayload = null; + let lastRefusalPayload = null; - for (const endpoint of OVERPASS_UPSTREAMS) { + for (const endpoint of endpoints) { const controller = new AbortController(); const timeoutId = setTimeout(() => controller.abort(), OVERPASS_TIMEOUT_MS); try { - const upstream = await fetch(endpoint, { + const upstream = await fetchImpl(endpoint, { method: 'POST', headers: { 'Content-Type': 'application/x-www-form-urlencoded', @@ -2577,7 +2600,7 @@ async function fetchOverpassPayload(body, maxResponseBytes = OVERPASS_MAX_RESPON signal: controller.signal, }); - const responseBody = await readResponseTextCapped(upstream, maxResponseBytes); + const responseBody = await readBody(upstream, maxResponseBytes); const contentType = upstream.headers.get('content-type') || 'application/json'; const status = upstream.status; const rateLimited = status === 429 || overpassLooksRateLimited(responseBody); @@ -2601,14 +2624,23 @@ async function fetchOverpassPayload(body, maxResponseBytes = OVERPASS_MAX_RESPON lastError = new Error(`Overpass runtime error (${endpoint})`); continue; } - if (status >= 500) { + // Anything but 2xx is this mirror declining, not an answer. Only 5xx used + // to rotate, so a 4xx ended the fan-out and was returned — and cached — + // as data: overpass-api.de and its lz4 alias answer 406 to this proxy's + // User-Agent while kumi.systems and private.coffee answer 200 to the very + // same request, so every Overpass-backed layer failed on an Apache error + // page with two healthy mirrors untried. The first refusal is kept so a + // genuinely bad query still reports what upstream said, but only after + // every mirror has had the chance to answer it. + if (status < 200 || status >= 300) { + if (!lastRefusalPayload) lastRefusalPayload = payload; lastError = new Error(`Overpass upstream returned ${status} (${endpoint})`); continue; } // Success: decimate giant boundary geometry before it reaches the cache, // the disk, or the client (what makes the 32 MB read cap safe to hold). - payload.body = simplifyOverpassPayloadBody(payload.body); + payload.body = simplify(payload.body); return payload; } catch (error) { lastError = error; @@ -2618,6 +2650,7 @@ async function fetchOverpassPayload(body, maxResponseBytes = OVERPASS_MAX_RESPON } if (lastRateLimitPayload) return lastRateLimitPayload; + if (lastRefusalPayload) return lastRefusalPayload; throw lastError || new Error('All Overpass upstreams failed'); } @@ -2710,7 +2743,11 @@ function overpassProxy() { _overpassConcurrent += 1; const requestPromise = fetchOverpassPayload(safeBody) .then((payload) => { - if (payload.status < 500 && !payload.rateLimited && !payload.runtimeError) { + // Only a 2xx is data. `< 500` cached every 4xx, so one mirror's + // refusal was written to memory AND disk — and boundary-class + // queries hold a month-long TTL, so a single 406 outlived the + // outage that caused it. + if (overpassPayloadIsData(payload)) { const entry = { ...payload, cachedAt: Date.now() }; _overpassCache.set(cacheKey, entry); trimOverpassCache(); @@ -2728,7 +2765,7 @@ function overpassProxy() { // Degraded upstream (rate-limited on every mirror / 5xx / runtime // error): last-good roads beat an empty layer — serve stale from // memory or disk at ANY age before surfacing the failure. - if (payload.rateLimited || payload.runtimeError || payload.status >= 500) { + if (!overpassPayloadIsData(payload)) { const stale = _overpassCache.get(cacheKey) || await readOverpassDisk(cacheKey, Infinity); if (stale) { sendOverpassResponse(res, stale, 'STALE');