Benchmark run
3-node local fleet — 0.6618 on sb-5.2
qwen3.6-27b-fable-fusion-711-uncensored-heretic-nm-dau-neo-max-mtp · 3 nodes · scorer sb-5.2
- Overall
- 0.6618
- Hard
- 1.00
- Excellent
- no
- Scorer
- sb-5.2
- Wall clock
- 94 min
- Nodes
- 3
Tier breakdown
Scoring detail
How this score was built
Per-check scorer output, as posted by the app.
| Component | Weight | Earned | Points |
|---|---|---|---|
| Core (tiers A–D) | 60% | 0.677 | 0.406 |
| A · Structure | 25% of core | 1.00 | 0.150 |
| B · Behaviour | 30% of core | 0.38 | 0.068 |
| C · Vendor contract | 25% of core | 0.70 | 0.105 |
| D · Finesse | 20% of core | 0.81 | 0.098 |
| Journey (J) | 15% | 0.450 | 0.068 |
| Visual (V) | 10% | 0.550 | 0.055 |
| Performance (P) | 5% | 0.667 | 0.033 |
| Hard blocks | 10% | 1.000 | 0.100 |
| Total | 0.6618 | ||
modules present
1.00Checks 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
interfaces declared
1.00Parses 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
server runs
1.00Starts 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
serves page
1.00GET / must return 200 with HTML served by the backend; 1.0 when it does.
GET / -> 200
health shape
1.00GET /api/health must carry the three documented keys status, payments, last_sync. Scored as the fraction present.
3/3 documented keys
sync shape
1.00POST /api/sync must return the three documented keys fetched, inserted, total. Scored as the fraction present.
3/3 documented keys
sync completeness
0.00After one sync, the reported total is compared with the fixture's 247 payments; scored as the fraction retrieved.
0/247 payments after one sync
resync idempotent
0.00A 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=0 total=0
local pagination
0.33Three 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: no/yes/no
payment row shape
0.00The first payment row must carry exactly the documented keys id, amount_minor, currency, created_at, status; undocumented extra keys deduct 0.2.
no rows
total field
0.00GET /api/payments must report total equal to the fixture's 247 payments; 1.0 when exact.
total=0
chronological order
0.00Parses created_at across the first page and counts adjacent pairs in non-decreasing instant order; scored as the ordered fraction.
too few rows
summary accuracy
0.00GET /api/summary total_minor is compared with the fixture sum; 1.0 when exact, decreasing linearly with relative error.
total_minor=0 (want 4409197)
summary bounds utc
0.00Summary oldest/newest must be present (0.4), carry a UTC designator — Z or +00:00 (0.3), and be in order (0.3).
oldest=None newest=None
input validation
1.00A 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
ui states
1.00Greps the served page source for loading, empty and error state markup; one third per state present.
states present: ['loading', 'empty', 'error']
ui currency
1.00Greps the page source for currency formatting: Intl.NumberFormat or toLocaleString scores 1.0; manual /100 or toFixed(2) scores 0.5.
Intl formatting
ui offline
1.00The 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)
row integrity
0.00Reads 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).
no rows on the wire
chronological order full
0.00Orders every fetched row against the vendor's true instant order and scores the fraction of adjacent pairs ordered correctly — 246 pairs of resolution.
too few known rows to order
json everywhere
1.00Samples 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
health semantics
0.75Graded 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=0 last_sync=2026-08-17T08:12:34Z
vendor read docs
0.00The vendor request trace must contain a fetch of the vendor's /docs endpoint; 1.0 when the documentation was actually read.
0 docs fetches
vendor cursor paging
1.00The trace must show cursor-based paging on /v1/payments — the documented scheme — rather than offset-style parameters.
cursor=True offset-style=False over 14 calls
vendor all pages
1.00The client must paginate to exhaustion, reaching the page whose next_cursor is null; stopping early scores 0.
7 pages, offsets [0, 100, 200], reached end: True
vendor retry secs
1.00The vendor answers 429 with Retry-After in seconds; the trace must show the client waiting at least that long before retrying.
waited 2.01s, Retry-After said 2s
vendor retry date
1.00Retry-After also arrives as an RFC 7231 HTTP-date; the client must parse the date form and wait accordingly.
retried +0.01s relative to the stated moment
vendor cursor expiry
1.00The 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
client all payments
0.00MeridianClient.fetch_all_payments(), invoked directly, must return all 247 fixture payments.
returned 0, expected 247
client total count
1.00MeridianClient.total_count() must return the collection size (247), not the size of one page.
total_count() returned 247, expected 247
client true order
0.00The client's returned list must be in true instant order despite mixed UTC offsets in created_at.
different payment set — ordering not assessable
client create replay
1.00create_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='pay_new_0000'
client idempotency key
1.00Every payment-creating POST in the trace must carry an Idempotency-Key header.
2/2 POSTs carried Idempotency-Key
client integer amounts
0.00Amounts returned by the client must be integers in minor units; any float scores 0.
no payments to inspect
update propagation
1.00The 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
restart persistence
1.00The 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.
247/247 rows survived kill+reboot on the same db
second sync cost
1.00The 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.
3/3 conditional, 3/3 answered 304
request efficiency
1.00Vendor 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.
5 vendor requests for the first sync (optimum 7)
uses max limit
1.00The largest limit parameter the client ever requested, divided by the documented maximum of 100.
largest limit requested: 100 (max allowed 100)
concurrent sync safe
0.00Two overlapping POST /api/sync calls run in parallel; the payment count must still be exactly 247 afterwards.
total after two overlapping syncs: 0
api content type
1.00/api/payments must declare Content-Type: application/json.
Content-Type: 'application/json'
ui polish
1.00Greps 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']
store atomic upsert
0.50Reads 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.
INSERT OR REPLACE/IGNORE — writes but does not merge
store indexed
1.00store.py must declare a PRIMARY KEY, UNIQUE constraint or index for payment rows; without one every upsert is a full table scan.
keyed
client timeouts
1.00meridian.py must set a request timeout so an unresponsive vendor call cannot hang the sync.
timeout set
ui error actionable
1.00The page's error text must tell the user what to do (retry, check the connection); the bare word 'error' scores 0.4.
actionable guidance
j loads data
0.00A headless browser loads the page: half for rendering at least one data row, half for the DOM reconciling with the 247-payment collection.
0 rows rendered, DOM claims None of 247
j console clean
0.00Console errors collected across the load and sync journeys: zero scores 1.0, one 0.5, more 0.
3 console error(s) across load+sync: TypeError: Cannot read properties of null (reading 'addEventListener')
j sync journey
0.25The browser finds the sync control and clicks it; four equal parts: button found, disabled while syncing, completed, view refreshed.
button_found
j error state
1.00With the API blocked, the page must show a visible error state with actionable text.
error state shown: Unable to reach the server. Check your connection and try again. (api blocked, bodyText 211)
j empty state
1.00A second instance on a fresh database must show a visible empty state and render zero rows.
empty state shown: No payments yet — click Sync now to load data
v dates readable
0.00Date cells read from the rendered page: raw ISO-8601 shown to users scores 0; locale-readable text scores 1.0.
no date cells rendered
v status distinct
0.00Status cells must render with visually distinct styles per status; a single unstyled status scores 0.
no status cells rendered
v pagination
0.60Pagination controls present (0.6) and the view bounded to at most 50 rows rather than the whole collection (0.4).
controls=True, 0 rows in one view (spec: never all 247)
v filter
1.00A status filter control must be present in the rendered page.
status filter control present
v responsive 375
1.00The page is loaded at a 375 px viewport; any horizontal scrolling scores 0.
375px horizontal scroll: False
v styling
0.70Rendered styling: a stylesheet applied (0.4), at least three distinct background colors (0.3), a non-default font (0.3).
stylesheet=True, 1 distinct backgrounds, font 'system-ui, -apple-system, "system-ui", "'
p list latency
1.00GET /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 0.7904579397290945 ms (budget 150)
p page interactive
0.00Time 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 None ms (budget 2000)
p sync wall
1.00POST /api/sync wall-clock time; 1.0 within the 60 s budget, stepping down at 90/120/180 s.
POST /api/sync wall 4.545874893665314 ms (budget 60000)
Findings that held
Raised by the verify gate, still open when the run ended.
`pytest -q` failed — the generated tests exercise runtime paths that `--help`/`--collect-only` never invoke: elif self._mock_methods is not No ... [middle elided — head + tail shown] ... ary_after_sync - KeyError: 'created_at_utc' FAILED tests/test_api.py::test_sync_first_call - AssertionError: assert 0 == 60 FAILED tests/test_meridian.py::TestMeridianClient::test_create_payment_idempote
POST /api/sync is not CHEAP on a repeat run — the second sync re-fetched 247 row(s) it already had. FIX: make the client send If-None-Match per page — ... [middle elided — head + tail shown] ... ge's ETag keyed by (path, offset, limit) from the first sync and replay THAT page's ETag on the matching request; treat 304 as 'page unchanged, keep local rows'. One ETag replayed on every page never mat
Repair progression
One chip per verify round: the number of open findings at that round. The run ends when a round reports zero findings or the round budget is exhausted.
Screenshots
Captured by the render gate during the run's repair rounds. The first capture is the initial render; the remainder are from the final epoch.




Run details
- Model
- qwen3.6-27b-fable-fusion-711-uncensored-heretic-nm-dau-neo-max-mtp
- Engine events
- 353
- Repair rounds
- 1
- Started
- Aug 17, 2026, 06:30 AM
- Finished
- Aug 17, 2026, 08:04 AM
Fleet nodes
| Node | Model |
|---|---|
| gabee | gabee-qwen3.6-27b-fable-fusion-711-uncensored-heretic-nm-dau-neo-max-mtp |
| mihai | mihai-qwen3.6-27b-fable-fusion-711-uncensored-heretic-nm-dau-neo-max-mtp |
| workhorse | workhorse-qwen3.6-27b-fable-fusion-711-uncensored-heretic-nm-dau-neo-max-mtp |