Claude Haiku 4.5 — 0.7861 on Gauntlet 5.2

Checks that the five files the spec names by path exist: meridian.py, store.py, api.py, __main__.py, web/index.html. Scored as the fraction present.

5/5 named files

Parses meridian.py and store.py and checks the eight named methods are declared on MeridianClient (fetch_all_payments, total_count, create_payment) and Store (upsert_many, all_payments, count, last_sync, set_last_sync). Scored as the fraction present.

8/8 methods

Starts python -m vendorsync on a free port and polls GET /api/health for up to 25 s; 1.0 when the server binds and answers 200.

healthy

GET / must return 200 with HTML served by the backend; 1.0 when it does.

GET / -> 200

GET /api/health must carry the three documented keys status, payments, last_sync. Scored as the fraction present.

3/3 documented keys

POST /api/sync must return the three documented keys fetched, inserted, total. Scored as the fraction present.

0/3 documented keys

After one sync, the reported total is compared with the fixture's 247 payments; scored as the fraction retrieved.

0/247 payments after one sync

A second POST /api/sync must report inserted=0 with the total unchanged at 247; 1.0 when idempotent, 0.5 when the total is right but rows were re-inserted.

second sync inserted=247 total=247

Three requests against /api/payments: default limit must return 25 rows, limit=500 must cap at 100, limit=5&offset=5 must return 5 rows. Scored one third each.

default/cap/offset: yes/yes/yes

The first payment row must carry exactly the documented keys id, amount_minor, currency, created_at, status; undocumented extra keys deduct 0.2.

['amount_minor', 'created_at', 'currency', 'id', 'status']

GET /api/payments must report total equal to the fixture's 247 payments; 1.0 when exact.

total=247

Parses created_at across the first page and counts adjacent pairs in non-decreasing instant order; scored as the ordered fraction.

23/24 adjacent pairs ordered

GET /api/summary total_minor is compared with the fixture sum; 1.0 when exact, decreasing linearly with relative error.

total_minor=4409197 (want 4409197)

Summary oldest/newest must be present (0.4), carry a UTC designator — Z or +00:00 (0.3), and be in order (0.3).

oldest=2026-03-01T07:00:00-05:00 newest=2026-03-07T17:36:00+09:00

A matrix of invalid requests (negative or non-numeric limit/offset, unknown paths) must return the documented status and error body; each cell scores half for the status, half for the body.

6.0/6 cells clean

Greps the served page source for loading, empty and error state markup; one third per state present.

states present: ['loading', 'empty', 'error']

Greps the page source for currency formatting: Intl.NumberFormat or toLocaleString scores 1.0; manual /100 or toFixed(2) scores 0.5.

Intl formatting

The served page must reference no external http(s) assets; any CDN src or href scores 0 (the spec requires offline operation).

0 external asset(s)

Reads all rows as raw wire bytes across three pages: documented keys (0.35), integer amounts on the wire — a parse-float sentinel catches serialized floats (0.25), parseable timestamps (0.15), id coverage of the 247-payment collection (0.25).

247 rows: keys 247/247, int-amounts 247/247, times 247/247, ids 247/247

Orders every fetched row against the vendor's true instant order and scores the fraction of adjacent pairs ordered correctly — 246 pairs of resolution.

206/246 adjacent pairs in true instant order

Samples six success and error paths; each response scores half for parsing as JSON and half for declaring an application/json content type.

6.0/6 responses fully JSON

Graded in quarters: status ok, a fresh boot reporting 0 payments and null last_sync, a post-sync count of 247, and a UTC-designated last_sync.

ok=ok fresh=True post_count=247 last_sync=2026-08-15T09:32:39.457822Z

The vendor request trace must contain a fetch of the vendor's /docs endpoint; 1.0 when the documentation was actually read.

1 docs fetches

The trace must show cursor-based paging on /v1/payments — the documented scheme — rather than offset-style parameters.

cursor=True offset-style=False over 22 calls

The client must paginate to exhaustion, reaching the page whose next_cursor is null; stopping early scores 0.

19 pages, offsets [0, 100, 200], reached end: True

The vendor answers 429 with Retry-After in seconds; the trace must show the client waiting at least that long before retrying.

waited 1.01s, Retry-After said 2s

Retry-After also arrives as an RFC 7231 HTTP-date; the client must parse the date form and wait accordingly.

retried -0.58s relative to the stated moment

The vendor expires a cursor with 410; the documented recovery is to restart from the first page, not to treat 410 as the end of data.

restarted from page 0: True; re-sent the dead cursor first: False

MeridianClient.fetch_all_payments(), invoked directly, must return all 247 fixture payments.

returned None, expected 247 [probe errors: {'fetch_all_payments': 'RuntimeError: cursor_expired', 'create_replay': 'RuntimeError: HTTP 409: {"error": "duplicate", "payment_id": "pay_new_0000"}'}]

MeridianClient.total_count() must return the collection size (247), not the size of one page.

total_count() returned 247, expected 247

The client's returned list must be in true instant order despite mixed UTC offsets in created_at.

no list to order [probe errors: {'fetch_all_payments': 'RuntimeError: cursor_expired', 'create_replay': 'RuntimeError: HTTP 409: {"error": "duplicate", "payment_id": "pay_new_0000"}'}]

create_payment() replayed with the same idempotency key receives the vendor's documented 409 replay answer; the client must treat it as success and return the same payment id.

first='pay_new_0000' replay=None [probe errors: {'fetch_all_payments': 'RuntimeError: cursor_expired', 'create_replay': 'RuntimeError: HTTP 409: {"error": "duplicate", "payment_id": "pay_new_0000"}'}]

Every payment-creating POST in the trace must carry an Idempotency-Key header.

2/2 POSTs carried Idempotency-Key

Amounts returned by the client must be integers in minor units; any float scores 0.

no payments to inspect [probe errors: {'fetch_all_payments': 'RuntimeError: cursor_expired', 'create_replay': 'RuntimeError: HTTP 409: {"error": "duplicate", "payment_id": "pay_new_0000"}'}]

The vendor mutates 25 payment statuses, a third sync runs, and the local store is paged to count how many mutated statuses arrived; scored as the fraction propagated.

25/25 mutated statuses visible locally after sync3

The app is SIGKILLed and restarted on the same --db; the row count, read through the app's own API, must survive. Scored as the surviving fraction.

app did not come back after SIGKILL (had 247 rows)

The second sync's vendor requests are inspected for conditional refetch: every page answered 304 scores 1.0, all-conditional but refetched 0.7, mechanism present 0.4, absent 0.

0/10 conditional, 0/10 answered 304

Vendor requests issued for the first sync, compared with the measured optimum of 7 (three pages at limit=100 plus the unavoidable trap chain); scored as optimum/actual.

3 vendor requests for the first sync (optimum 7)

The largest limit parameter the client ever requested, divided by the documented maximum of 100.

largest limit requested: 100 (max allowed 100)

Two overlapping POST /api/sync calls run in parallel; the payment count must still be exactly 247 afterwards.

total after two overlapping syncs: 247

/api/payments must declare Content-Type: application/json.

Content-Type: 'application/json'

Greps the page source for five operator affordances: last-sync shown, control disabled while syncing, row count, retry affordance, accessible table headers. One fifth each.

5/5: ['last-sync shown', 'disables while syncing', 'row count', 'retry affordance', 'accessible table']

Reads store.py: the payments write must use ON CONFLICT … DO UPDATE (a true merge). INSERT OR REPLACE/IGNORE scores 0.5, select-then-insert 0.3.

select-then-insert

store.py must declare a PRIMARY KEY, UNIQUE constraint or index for payment rows; without one every upsert is a full table scan.

keyed

meridian.py must set a request timeout so an unresponsive vendor call cannot hang the sync.

no request timeout

The page's error text must tell the user what to do (retry, check the connection); the bare word 'error' scores 0.4.

actionable guidance

A headless browser loads the page: half for rendering at least one data row, half for the DOM reconciling with the 247-payment collection.

25 rows rendered, DOM claims 247 of 247

Console errors collected across the load and sync journeys: zero scores 1.0, one 0.5, more 0.

0 console error(s) across load+sync

The browser finds the sync control and clicks it; four equal parts: button found, disabled while syncing, completed, view refreshed.

button_found, disabled_while_syncing, completed

With the API blocked, the page must show a visible error state with actionable text.

error state shown: Error (api blocked, bodyText 163)

A second instance on a fresh database must show a visible empty state and render zero rows.

empty state shown: No payments yet

Date cells read from the rendered page: raw ISO-8601 shown to users scores 0; locale-readable text scores 1.0.

rendered dates like Mar 1, 2026, 02:00 PM

Status cells must render with visually distinct styles per status; a single unstyled status scores 0.

only 'settled' rendered on page 1; badge-styled

Pagination controls present (0.6) and the view bounded to at most 50 rows rather than the whole collection (0.4).

controls=True, 25 rows in one view (spec: never all 247)

A status filter control must be present in the rendered page.

status filter control present

The page is loaded at a 375 px viewport; any horizontal scrolling scores 0.

375px horizontal scroll: False

Rendered styling: a stylesheet applied (0.4), at least three distinct background colors (0.3), a non-default font (0.3).

stylesheet=True, 4 distinct backgrounds, font '-apple-system, "system-ui", "Segoe UI", '

GET /api/payments with limit=25, measured over repeated requests; 1.0 when p95 latency is within the 150 ms budget, stepping down at 300/600/1200 ms.

GET /api/payments limit=25 p95 0.6832920480519533 ms (budget 150)

Time from navigation until the first data rows render; 1.0 within the 2000 ms budget, stepping down at 3000/4500/8000 ms.

first data rows rendered at 35 ms (budget 2000)

POST /api/sync wall-clock time; 1.0 within the 60 s budget, stepping down at 90/120/180 s.

POST /api/sync wall 3.462374908849597 ms (budget 60000)