The W7 per-user-tz sweep threaded `userTz` through every aggregator on
the analytics route except `berlinIsoWeekday()` — the module-level
`Intl.DateTimeFormat` stayed pinned to `Europe/Berlin`. A user in
`Pacific/Auckland` whose 23:30 weight reading lands at 12:30 the same
day in Berlin had their Monday-local reading bucketed under Sunday's
weekday column. Pearson/ANOVA on the wrong weekday.
Replace the pinned formatter with a per-tz memoised lookup, rename the
helper to `isoWeekdayInTz()`, and feed `userTz` through the call site.
Also rename the misleading `dateFromBerlinKey()` → `dateFromDayKey()`
since the keys it consumes are already anchored to the user's tz
upstream.
Integration test covers the non-Berlin path: 28 weight readings at a
UTC instant where the Berlin and Auckland weekdays disagree; the
correlator reaches the gate with every seeded row counted, confirming
the helper used the user's tz to bucket.
Lock the GET /api/analytics wire-up to the new two-axis picker with a
fixture-driven test that drives a real Postgres testcontainer + the
production handler. Four scenarios on the same Berlin day:
1. Plain default user (single source, no override) — picker passes
through; v1.4.25-today behaviour stays a regression sentinel.
2. Per-metric override (sleep: [WITHINGS, APPLE_HEALTH]) — flips
the default APPLE_HEALTH-first ladder; Withings row wins.
3. Per-device default (no user override) — Apple Watch row beats
iPhone row under same source on default ladder (watch first).
4. User flips device ladder to [phone, watch] — iPhone row wins.
Wire-up: analytics' fetchMeasurementSeriesChunked now selects
deviceType + type on every chunk so the picker can read both axes.
ChunkedRow gains two fields; all existing aggregation paths continue
to compile and the integration suite stays green (6/6 passing across
analytics-sleep-stages.test.ts + source-priority-two-axis.test.ts).
Unit tests already cover the picker's internal edge cases (45 unit
across helper + algorithm); this file is the end-to-end guard.
7 conflict files resolved by taking the upstream/HEAD side (which carries
the W4d/W5/W6c/W3f feature additions). Stashed-side changes that were
genuine new features re-land in subsequent commits if any were lost.
This sweeps up the loose state the W4e+W5e+W5d combined agent left
mid-stash. Resolves develop's working tree for clean push.
The Settings → Dashboard sub-section's Save button silently 422'd once
the user had touched any per-chart overlay popover. Root cause was a
Zod v4 semantics change: `z.record(z.enum(KEYS), ...)` now requires
every enum key to be present in the input, where Zod v3 treated the
same shape as a partial record. Real-world Save payloads only carry
the chart keys the user actually toggled, so every Settings → Dashboard
Save attempt with one or two `chartOverlayPrefs` entries failed with
`expected: object, path: ["chartOverlayPrefs", "<missing-key>"]` and
the toast surfaced "Layout konnte nicht gespeichert werden".
Fix uses `z.partialRecord(z.enum(KEYS), ...)` which preserves the
original v1.4.18 intent — per-chart opt-in overlay prefs, missing keys
filled by the resolver. The inner object now also accepts the
`comparisonBaseline` field so a Settings save preserves the per-chart
comparison toggle the user set via the chart-card popover (otherwise
Zod's default strip behaviour wiped it on every save).
New integration suite pins:
- partial chartOverlayPrefs round-trips
- per-chart comparisonBaseline survives a Settings save
- empty chartOverlayPrefs still persists (fresh accounts)
- widget toggle changes land in the DB
Up to v1.4.24 the snapshot's day-key and weekday labels ran through
utcDayKey() / utcWeekday() / isoWeekKey(), so a 23:50 Pacific/Auckland
reading was filed under the next UTC day and the Coach replied with
the wrong calendar. The pipeline now reads User.timezone (alongside
the existing coachPrefsJson read so the read budget is unchanged) and
threads it through every bucketing helper (dailyMeans, bucketWeekly,
buildDailyValueRows, buildDailyBpRows) plus the medication-compliance
day-roll-up and the Apple Health additive blocks.
The prompt-budget calculator (src/lib/ai/coach/budget.ts) is unaffected.
The ledger still uses UTC midnight for spend roll-over because the
operator's LLM bill cycles on UTC; only the SNAPSHOT itself shifts to
the user's calendar. The provenance counts are row counts, not day
counts, so no provenance drift either.
Integration test pins the boundary: a 13:00 UTC May 14 reading (=
01:00 NZST May 15) appears under "2026-05-15" in the Coach snapshot
for a Pacific/Auckland user. The same instant in Berlin would land on
May 14; the test asserts the snapshot does NOT bucket there.
Existing 88-test coach unit suite stays green (the mocked user row
returns no timezone, so the snapshot falls back to Europe/Berlin and
the v1.4.24 byte-shape holds).
HealthKit's API does not surface a stream of deleted UUIDs, so the iOS
HealthLog client performs a periodic 30-day reconciliation: it diffs
HealthKit's current UUID set against the server's externalIds and
posts the surplus here. This endpoint deletes the user's matching
rows and never touches another user's data (Prisma's deleteMany with
the userId predicate is the cross-user 404 guard).
Contract:
- Body: { externalIds: string[] } with min 0, max 500 entries.
- Auth: requireAuth() — session cookie or bearer.
- Empty array: returns { deletedCount: 0 } with 200 (no-op, not a
failure — matches the ingest path's symmetric tolerance).
- Over-cap: 422 with errorCode "measurement.delete.too_large" so
the iOS client can surface a specific diagnostic.
Integration coverage: happy path, cross-user 404 guard, empty array,
and batch-cap rejection. The cap (500) mirrors POST /measurements/batch
so the two surfaces share one operational ceiling.
OpenAPI: registered as DELETE on /api/measurements/by-external-ids
with the Measurements tag; req/res schemas reuse the same z.array cap
the runtime validator enforces. openapi.yaml regenerated.
Four chart components (HealthChart, MoodChart, MedicationComplianceChart,
ComplianceLineChart) now accept a userTimezone prop, default
"Europe/Berlin" for backwards compat. Inside each chart, the X-axis
tick formatter, tooltip date label, and per-day bucketing all run
through a tz-aware makeFormatters(locale, userTz) instance instead of
the legacy formatDateShort() which pinned to Europe/Berlin.
Mount sites that already pull useAuth() pass user?.timezone:
dashboard /page.tsx, trends-row, recommendation-card,
insight-advisor-card. Ad-hoc usages without a user (storybook-style
or test harnesses) keep the default Europe/Berlin rendering
bit-for-bit.
The HealthChart's daily-aggregation key (toDayKey) was also rewritten
to depend on the userTimezone prop so a 23:50 Pacific/Auckland reading
buckets to the Auckland day instead of the Berlin day for chart data
display. The TanStack Query cache key gains userTimezone so a tz
change inside a session re-fetches and re-buckets correctly.
Tests: 109 chart-component tests stay green.
The four routes that bucket by Berlin calendar day (dashboard summary,
medication intake, analytics correlations and sleep, insights targets)
now read userTz from the authenticated User and pass it through
userDayKey(). Streaks and consistency strips for a Pacific/Auckland user
land on their Auckland-day, not the legacy Berlin-day.
The aggregation logic is unchanged — only the bucket key function
swaps from berlinDayKey(date) to userDayKey(date, userTz). Existing
Berlin users see no behaviour change (Europe/Berlin is the schema
default).
Integration test extended with a two-case assertion: the userDayKey()
boundary case (13:00 UTC May 14 → 2026-05-15 Auckland vs 2026-05-14
Berlin) and the dashboard summary route returning a non-zero streak for
an Auckland account with three consecutive Auckland-day measurements.
v1.4.25 W7 phase 7 — proposal §6.4 test strategy applied.
Seven cases cover the full per-user-tz pipeline against the
integration testcontainer:
1. CSV export for an Auckland user emits '+12:00' on measuredAt,
never the bare 'Z'. This is the issue #167 fix from the user's
end-to-end perspective: an Auckland user's exported spreadsheet
carries unambiguous local time.
2. CSV export for an Asia/Tokyo user emits '+09:00' (no DST in
Japan, deterministic offset year-round).
3. CSV export with no userTz (legacy library callers — admin tools,
canonical backup-on-disk) keeps the 'Z' suffix. Protects the
backward-compatibility path.
4. PUT /api/auth/me/timezone writes the new zone, the user row
reflects it, AND the in-process resolver cache returns the new
value immediately (the route invalidates on write — proves the
evict path works without waiting 60s for the TTL to roll).
5. PUT /api/auth/me/timezone rejects an invalid IANA zone with
422 and does not touch the column.
6. POST /api/auth/register captures a browser-detected zone from
the signup payload onto User.timezone.
7. POST /api/auth/register falls back to Europe/Berlin when the
payload's zone is invalid. The 'admin server default'
intermediate fallback layer is exercised by the unit suite —
the integration test runs against a testcontainer whose
migration history doesn't carry every AppSettings column,
so setting a non-NULL default would error before the route
runs. Documented inline.
The Coach snapshot's UTC bucketing (proposal §3 symptom 9) is
intentionally NOT asserted — that surface is deferred to a
follow-up wave because the snapshot's day/week bucketing pipeline
is a separate refactor that touches the prompt budget calculator.
The two failing cases in tests/integration/coach-prefs.test.ts were invoking
the route's GET handler with zero arguments — `(GET as () => Promise<Response>)()`.
The apiHandler wrapper at src/lib/api-handler.ts:46-47 reads args[0].url to
build the Wide Event `http.path`, so the call threw
`TypeError: Cannot read properties of undefined (reading 'url')` before the
route body ever ran. Other integration tests already pass a real Request to
GET (see analytics-health-score, chart-overlay-prefs); aligning this test to
the same pattern restores parity with production where Next.js always
invokes route handlers with a Request.
The api-handler wrapper itself was left untouched — defending against a
caller passing undefined would mask the same bug in any future test.
Mostly table column normalisation under docs/audit/ + planning, object-
literal expansion in src/lib/ai/coach/snapshot.ts after the W4 F6 Apple
Health metric block landed, and small wrap/unwrap line adjustments in
the device + APNs routes / tests touched across W3/W4/W5 sessions.
No behavioural change.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Reviewer note: W5 H7 wrote Coach assistant prose plaintext into
recommendation_feedback.recommendation_text. Same prose lives
encrypted in coach_messages — backups captured the leak.
Migration 0042_coach_feedback_message_ref adds nullable coachMessageId
(FK + cascade) and drops recommendation_text. Aggregator joins +
decrypts on read; admin view reads through the same path.
Fixes: Sr-H3 (Wave-6 v1.4.23 senior-dev review)
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Reviewer note: src/app/api/analytics/route.ts fanned out 17+
unbounded prisma.measurement.findMany per request — growth linear
in HealthKit-days. Replace with prisma.groupBy where possible;
chunked-paged with take=5000 where running-window slope or paired
correlations require row-level access. Wide-event annotation
analytics.bp_aggregate.row_count for slow-query attribution.
Fixes: Sr-H1 (Wave-6 v1.4.23 senior-dev review)
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The dispatcher's APNS branch only fires when a NotificationChannel of
type APNS exists for the user, but no production code path created one.
Every iOS install needed a manual settings toggle that doesn't exist,
making the v1.4.23 W3 APNs cascade unreachable in real traffic.
When `POST /api/devices` accepts an apnsToken, eagerly upsert the
channel row with an encrypted empty config — the per-device token and
environment live on the Device row by design, so the channel only
exists to flip the dispatcher's gate. Mirrors the legacy Telegram
on-first-dispatch auto-migration but eager so the very first reminder
after registration routes through APNs.
Adds an integration test that registers a device with apnsToken and
asserts the channel row exists, registers without one and asserts
absence, and re-registers the same apnsToken and asserts idempotency
(channel count stays at one).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The v1.4.22 prose rewrite shipped without a way for users to signal
whether the new tone is landing. v1.4.23 H7 closes that loop with a
light-touch thumbs row + an admin first-week dashboard.
Schema: extend `RecommendationFeedback` with a polymorphic
`target_type` column (default "recommendation" so legacy rows stay
representative) plus a nullable `reason` field. New index on
(target_type, created_at) so the aggregator can scan per-surface
buckets without a full sweep. Migration `0040_recommendation_feedback_target_type`.
Route: POST /api/insights/chat/messages/:id/feedback. Body
{ rating: "helpful" | "unhelpful", reason?: string }. Verifies
ownership (404 on cross-account messages — no existence leak),
decrypts the message body for the dedup key, and writes the row with
target_type="coach" + a metric-source string encoding the user's
active prefs (`coach:tone=warm:verbosity=default`). Per-user 60/h rate
limit. 409 on a P2002 (already_rated) so a double-click is a no-op.
Aggregator: new `buildCoachFeedbackBuckets()` slices Coach rows by
(promptVersion, tone, verbosity). The summary blob the worker writes
to AppSettings.adminAiInsightsFeedbackSummary now carries both
`buckets` (pre-existing) and `coachBuckets` (H7 addition). Targets
the same singleton row so no second worker handler is needed.
Admin view: `/admin/coach-feedback` (new section slug) renders the
Coach buckets as a small DataTable (prompt version × tone × verbosity
× helpful × not-helpful × n × helpful-rate). Helpful-rate column
tinted via Dracula tokens (green ≥80%, yellow ≥50%, orange below).
First useful question this answers: "Is the v1.4.22 prose rewrite
landing well, or did the warm tone overshoot?" If the helpful-rate
for PROMPT_VERSION 4.23.x drops below 50% within the first 100
ratings, v1.4.24 walks the persona back.
UI: `<ThumbsUp>` / `<ThumbsDown>` buttons (lucide icons, no emoji)
under each persisted assistant bubble. Streaming bubbles + refusals
+ error bubbles skip the row so users can't rate before the message
lands on disk. Localised "Thanks for the signal." after submit.
OpenAPI: spec carries the new POST route + the request schema.
Coverage now includes the H4 + H7 routes — three additions over
v1.4.22 baseline.
Tests +9 unit (aggregator Coach-bucket slicing, admin section
render-paths) plus an integration round-trip for the route.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The v1.4.22 B5 audit removed the placeholder cog from the Coach
drawer header because it had no real wiring. v1.4.23 H4 returns
the cog with an actual settings surface backed by a per-user
preferences row.
Schema: nullable JSONB column `users.coach_prefs_json` (migration
0038_coach_prefs). Null = legacy v1.4.22 defaults; non-null carries
`{ tone, verbosity, excludeMetrics, showEvidenceByDefault }` validated
by the Zod schema in `src/lib/validations/coach-prefs.ts`.
Routes: GET + PUT `/api/auth/me/coach-prefs`. PUT validates the body,
persists the canonical defaulted form, and emits an
`auth.me.coach-prefs.put` annotation with the four-knob meta. OpenAPI
registry covers both verbs; the spec regenerates without drift.
Coach prompt builder: `getCoachSystemPrompt(locale, prefs)` prepends a
per-user OVERRIDE paragraph for non-default tone (neutral / concise)
and verbosity (brief / detailed). Concise tone forces brief verbosity
regardless of the explicit selection — concise == short. Default
prefs leave the prompt unchanged so the v1.4.22 train stays in place.
Snapshot builder: reads the prefs row BEFORE any measurement query
and intersects `excludeMetrics` with the resolved scope. The model
never sees data the user opted out of — that's the load-bearing
order: filter first, query second.
UI: settings cog in the drawer header opens a right-edge `<Sheet>`
with three Select pickers (tone, verbosity) and one Switch column
(per-metric exclusions + showEvidenceByDefault). Save calls the PUT
route and invalidates the `["coach-prefs"]` query so the next reply
honours the new defaults without a reload. EN + DE i18n keys for
every label and hint.
Message-thread reads the same `["coach-prefs"]` cache and toggles the
`open` attribute on the evidence `<details>` element when
`showEvidenceByDefault` is true.
Tests +24 unit (coach-prefs schema, system-prompt prefix, snapshot
mock for new prefs row). Integration round-trip seeds a session,
PUTs a non-default prefs shape, asserts the GET reflects the saved
values + the DB row carries the canonical defaulted form.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The W2-of-v1.4.20 BD-Zielbereich fix needed the complete sys + dia
series to compute the all-time + prior-month + prior-year windows,
so it pulled both tables via single-shot `findMany`. For a 5-year
power user (~9 000 rows per side) that's a 50-100 ms Prisma round-
trip and a ~2 MB working-set allocation per /api/analytics request.
Switch to a cursor-paged 5 000-row chunked read via the new
`fetchBpSeriesChunked()` helper. The accumulated `BpReading[]` is the
same shape `computeBpInTargetWindows()` already consumed; the
working-set ceiling is now `BP_CHUNK_SIZE` instead of unbounded. Safety
bound at 1 000 pages = 5 M rows so a cursor-staleness bug can't loop
forever.
Wide-event annotation `analytics.bp_in_target.row_count` (+ per-side
`sys_rows` / `dia_rows`) lets ops attribute slow requests to outlier
users without rerunning the DB queries.
Integration test seeds a 6 000-row dataset (3 000 sys + 3 000 dia)
spanning a chunk boundary and asserts the response shape stays the
same — last30Days, last7Days, allTime windows all carry the
hand-derivable percentages.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
23 unit tests under `senders/__tests__/apns.test.ts` exercise:
* env-var loader — all-or-none guard, inline-PEM `\n` unescape, file
fallback path, cache, APNS_PRODUCTION override
* Provider lazy-init + per-gateway cache (sandbox vs production stay
isolated; APNS_PRODUCTION funnels every send through production)
* permanent-failure detection (`Unregistered`, `BadDeviceToken`,
`DeviceTokenNotForTopic` flip `shouldDisable: true`; transient
reasons stay false)
* `sendViaApns()` dispatcher entry — fan-out, dead-row cleanup,
hard-vs-soft channel-reject classification, HTML stripping
3 integration tests under `tests/integration/apns-dispatch.test.ts`
drive the real dispatcher against a Postgres testcontainer with a
stubbed `@parse/node-apn` Provider:
* Round-trip: notification fans out via APNs and the channel-state
machine records `lastSuccessAt` + clears any cooldown
* Failure path: `Unregistered` deletes the dead Device row,
auto-disables the channel with the captured reason, and writes the
`notification.channel.auto_disabled` audit-log entry
* Cascade: a disabled APNS channel falls through to Telegram on the
next dispatch — the apns send-mock stays untouched
Adds `senders/__mocks__/apns.ts` — a deterministic mock with queued
per-token responses + recorded calls so future test files can swap the
real sender for a fixture-driven double without touching `@parse/node-apn`.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The W2 commit shipped with `as never` casts on the request + params
arguments, which let the runtime test pass but failed strict tsc
because `apiHandler<() => Promise<Response>>` narrows the wrapper's
signature down to its inner handler's. Cast through `unknown` so the
wrapper-side `request.url` read works and tsc is satisfied.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Apple Health stores sleep as one Measurement row per stage per night,
so the existing single-value SLEEP_DURATION summary would treat each
stage as its own datapoint and grossly understate the per-night total.
The route now sums per Berlin day before summarising — one summary
datapoint per night, value equal to total minutes asleep.
A new optional `sleepStages` block surfaces the per-stage breakdown
over the trailing 30 days when stage-tagged rows exist (and `null`
otherwise so the existing UI keeps painting the totals-only path).
The block reports total minutes, the night count covered, and the
per-stage minute sums so the upcoming insights surface can render
"averaged across N nights" captions truthfully.
Two integration tests cover both shapes — a four-stage night
aggregating to 880 minutes with a populated stages map, and a
manual-source no-stage row keeping `sleepStages` at null.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
`POST /api/measurements/batch` accepts up to 500 HealthKit-shaped
entries per call, runs each through the new mapping helper, and writes
them under `source = APPLE_HEALTH` with the inbound sample UUID as the
external id. The composite unique index on
`(user_id, type, source, external_id)` does the per-entry dedup;
`Idempotency-Key` covers the batch-level retry case so the iOS observer
queue can replay in flight without double-writing.
Per-entry status (`inserted` / `duplicate` / `skipped`) lets the
client advance its sync cursor accurately even when individual rows
land on different paths. Skip reasons cover unknown HealthKit
identifiers and out-of-plausible-range values so a single bogus sensor
reading never rejects an otherwise clean batch.
Insertion uses chunked `createMany` with `skipDuplicates: true` so a
race between two concurrent retries reconciles cleanly via the unique
index instead of failing the transaction. Wide Event annotation logs
`processed / inserted / duplicates / skipped` for ops visibility.
Six integration tests against a real Postgres testcontainer cover the
happy path, the per-entry duplicate path, the over-cap 422, mixed
unmappable + out-of-range entries, per-stage sleep rows, and
`Idempotency-Key` replay.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The `setOnboardingPendingCookie` helper was called from six different
auth routes (login, passkey-verify, register, password, /me,
/onboarding/complete) by convention. A future auth surface (SSO,
magic link, social login) added without remembering the helper would
silently re-introduce the dashboard flash that v1.4.22 C4 was
designed to fix.
Make `onboardingPending` a required parameter on `createSession`
(not optional) so issuing a session without anchoring the cookie is
type-impossible. The five primary auth surfaces now thread the
user's `onboardingCompletedAt == null` value through; the
`/api/auth/me` mirror remains as a fall-back for legacy sessions
that predate the cookie. The `/api/onboarding/complete` clear stays
where it is — it is a value flip after a DB write, not a session
issuance.
Three new integration tests pin: createSession sets the cookie when
pending, clears it when completed, and destroySession clears it
alongside the session cookie.
Closes Sr-H1.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
When the model emits only a `---KEYVALUES---` block with no leading
prose (or a malformed block missing the closing marker), the
post-strip prose is empty. The previous fallback chained back to
`rawReply`, surfacing raw sentinel markers to the user. Replace with
a structured `coach.provider.empty` error frame so the UI renders
the localised provider-error copy instead of leaking the markers.
Add a regression integration test pinning that the streamed body
never contains `---KEYVALUES---` for a sentinel-only reply, and that
no assistant message is persisted in this branch.
Closes Code-H1.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Add a text-marker sentinel parser (`---KEYVALUES---` … `---END---`)
that strips the Coach's evidence block out of the prose before it
streams to the client, validates each line against a Zod schema, and
attaches the parsed entries to `provenance.keyValues`. The persisted
envelope round-trips so the disclosure renders on conversation
reload. Hard-capped at 8 lines and 1 KB to guard against
prompt-injection padding; malformed blocks log a wide-event and pass
the prose through unchanged.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Up to v1.4.19 the BD-Zielbereich tile pinned 50/50/50 because the
route routed the headline through `windows.last30Days?.pct` — making
the headline a literal copy of the `30T` sub-value. v1.4.19 A1
re-anchored the headline to all-time so the three windows could
diverge. That fixed the algorithmic pin but introduced an emotional
problem: the headline became the slowest-moving aggregate possible,
punishing users who had recently dragged their compliance up. A user
seeing 7d 50 % / 30d 50 % alongside a stubborn 11 % all-time read it
as "your work doesn't count yet."
Re-anchor the headline to `windows.last30Days?.pct` and surface
all-time as a third sub-value (`bpInTargetPctAllTime`) so power users
still see the long-arc number without it dominating. The integration
test pins the new contract: with three legitimately divergent windows
the route's `bpInTargetPct` equals `last30Days.pct`, and the new
all-time field carries the historical figure.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The route now builds the four-component Health Score input from the
already-fetched BP figure plus a fresh weight + mood + medication
intake fetch (last 30 days, plus a 7-day-shifted snapshot for the
delta). The response gains a `healthScore: { score, band,
components, delta } | null` field; null when no component is
computable so the UI hero panel can hide cleanly.
The wide-event annotation carries `healthScore.score` + `band` +
`delta` so admin-app-logs can attribute coverage without DB queries.
The previous-week BP rate reuses the all-time figure (it's a slow-
moving aggregate; rewinding it cheaply isn't possible without a
full historical re-pair). Delta therefore primarily reflects week-
over-week movement in weight / mood / compliance — the components
that actually move on a weekly cadence.
Integration coverage seeds three synthetic-data shapes against the
postgres testcontainer:
- strong-positive → green band (>= 75)
- empty user → null healthScore
- compliance-only → bp/weight/mood null, compliance weight 1.0
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
GET /api/insights/chat returns the caller's conversations newest-first
with cursor pagination (default limit 20, hard cap 50). Each row
carries id, title, timestamps, and a message count so the rail can
render without paying the per-message decrypt cost.
GET /api/insights/chat/[id] fetches one conversation with every
message decrypted in memory before serialisation. Provenance metadata
round-trips alongside the assistant turns.
DELETE /api/insights/chat/[id] hard-deletes the thread; the FK chain
cascades the message rows.
Cross-user lookups map to 404, never 403, so the existence channel
never leaks across accounts.
6 integration tests cover the list ordering, owner-only filter,
decryption round-trip, and the 404 boundary on both verbs.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The route gates on requireAuth (cookie or bearer), enforces the daily
token budget, runs the prompt-injection / off-topic refusal scanner,
and only then walks the user's provider chain.
The conversation is created via withIdempotency() when no
conversationId is supplied, so a retry under the same Idempotency-Key
replays the original assistant reply rather than spinning up a second
thread. Existing-thread turns skip the wrap.
Replies stream as SSE: one "token" frame per word-sized chunk, then a
"provenance" frame describing the windows + metrics the assistant
could see, then a "done" frame carrying the persisted message id.
Provider failure cascades to a single "error" frame and the assistant
message is never persisted. Conversation history is capped at 20 turns
in the prompt window via a synthetic summary placeholder so cost stays
bounded.
`buildCoachSnapshot()` reuses the analytics features pipeline so the
Coach narrates the same numbers the dashboard tiles render.
`getCoachSystemPrompt()` extends the strict-insight ground rules with
conversational framing while keeping the zero-hallucination rule.
5 integration tests pin the round-trip, refusal short-circuit, budget
429, foreign-conversation 404, and validation 422 paths against the
postgres testcontainer.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Persist Coach chat threads with AES-256-GCM-encrypted message bodies
and a per-user, per-day token-spend ledger. Encryption reuses the
active ENCRYPTION_KEYS entry so rotation continues to work without a
backfill. metric_source_json carries provenance labels only (window +
metric names, never raw values), keeping it queryable for analytics.
Cascade-on-user-delete is wired through the FK chain so GDPR delete
removes Coach data with the rest of the account. The integration-suite
truncation list picks up the new tables.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Marc reported the BD-Zielbereich tile pinned at exactly 50/50/50 for
7T, 30T, and the headline ("total") on his real production data — the
fourth attempt at this surface (v1.4.15 → v1.4.16 → v1.4.18 → v1.4.19).
Root cause: the analytics route routed `bpInTargetPct` (the headline)
through `windows.last30Days?.pct` — a literal copy of the `30T`
sub-value. Since `computeBpInTargetWindows` only returned 7d + 30d
windows, the headline could never legitimately differ from `30T`. For
Marc's real data (572 paired readings since 2022, recent 30d = 50 %,
all-time ≈ 11 %) the tile read 50 % / 50 % / 50 % and looked
algorithmically pinned — exactly the symptom he reported.
The previous three passes treated this as either a predicate bug
(v1.4.16 ceiling-vs-narrow-band, real and merged) or a missing
`avg7`/`avg30` wiring (v1.4.18, also real and merged). Both fixes
landed correctly, but neither addressed the headline duplication.
Fix:
- `computeBpInTargetWindows` now returns a third `allTime` window
that aggregates EVERY paired reading in the input series.
- The analytics route fetches all paired BP rows (no 30-day cutoff)
and routes the headline through `windows.allTime?.pct`. The route
only re-pairs once internally so the cost is paid once per request.
- The 7T / 30T sub-values are unchanged (still windowed slices of
the same input).
Failing test reproduces the bug with Marc's data shape (`allTime` MUST
not equal `last30Days` once older history is present); fix turns it
green. Integration test seeds 40 paired readings against real Postgres
and asserts all three windows compute independently.
Hand-counted against Marc's prod data:
- 7T: 50 % (1/2) — matches what he sees, real coincidence
- 30T: 50 % (5/10) — matches what he sees, real coincidence
- Headline: ~11 % (62/572) — was 50 %, now correct
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Pre-existing format drift accumulated across v1.4.x; running
prettier brings the whole tree back to baseline so future diffs
read clean. No behaviour change.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Two trigger fixes so the new achievements actually fire end-to-end.
The doctor-PDF hidden Easter-egg used to watch a non-existent
`doctor-report.export` audit action. The real route emits two:
`doctor-report.generate` (the JSON helper) and
`doctor-report.pdf.generate` (the PDF route). Either now counts.
The locale-flip hidden Easter-egg used to watch
`settings.locale.update`, which no endpoint emits — the locale
field shares the catch-all `profile.update` audit row with every
other profile field. Profile-update now emits a separate
`settings.locale.update` row when (and only when) the locale value
actually changes (compares the new value to the prior persisted
locale, suppresses the row when they match), with the from/to
values in the details payload for traceability.
Already-existing TanStack Query invalidation map covers the new
metrics: `measurementDependentKeys`, `moodDependentKeys`, and
`medicationDependentKeys` already include
`queryKeys.gamificationAchievements()`, so any measurement / mood /
intake mutation triggers a refetch and the route persists the new
unlock to `UserAchievement` (existing v1.4.15 mechanism).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Three new layers of coverage for the v1.4.18 expansion set:
- Unit (expansion-metrics.test.ts) — drives synthetic data through
every new evaluator (count by type, mood mean improvement, weekend
warrior, hidden Easter-egg triggers including the Berlin TZ
classifier for night-owl / early-bird) and the earnability flag
builder. 13 new assertions.
- Integration (achievements-expansion.test.ts) — round-trips real
prisma rows (MoodEntry's YYYY-MM-DD `date` string, Measurement
type discrimination, audit log row) through
`buildExpansionMetricValues` so a schema drift in any of the row
shapes surfaces here rather than at runtime. We don't drive the
full HTTP route in this spec because of pre-existing
medication_schedules.days_of_week migration drift.
- E2E (achievements.spec.ts) — the existing sidebar smoke gets a
sibling describe-block exercising all four card states (unlocked /
locked-earnable / hidden-locked / hidden-unlocked) and asserting
hidden-locked cards never leak their real strings to the rendered
HTML, which is the entire point of the "hidden" state.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Hook the overlay-controls dropdown into a TanStack Query mutation so
each chart's three toggle states (7-day trend / Trend arrow / Target
range) save per user and survive reloads. The prefs piggy-back on the
existing User.dashboardWidgetsJson blob with a `chartOverlayPrefs`
keyed by chart id, mirroring the v1.4.16 phase B8 comparison-baseline
pattern — no Prisma migration needed.
Wires up:
- GET /api/dashboard/widgets surfaces the resolved prefs in its
response so a fresh dashboard load knows which overlays to paint.
- PUT /api/dashboard/chart-overlay-prefs replaces a single chart's
prefs without round-tripping the whole layout.
- Existing PUT /api/dashboard/widgets preserves any chartOverlayPrefs
the client doesn't send, so saving widget visibility doesn't wipe
chart prefs.
- useChartOverlayPrefs hook reads + optimistically updates the cache.
- HealthChart, MoodChart, MedicationComplianceChart all consume the
hook, render the controls dropdown next to the range tabs, and gate
their three overlays behind the persisted toggles.
Default state for every chart, every flag: false. The clean line is
the new default; users opt into overlays they care about per chart.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The tile rendered the 30-day headline correctly but the `7T:` and
`30T:` sub-values fell back to "—" even when the user had paired BP
readings in both windows. Root cause was that `/api/analytics` only
returned a single `bpInTargetPct`; the tile received `avg7={null}`
and `avg30={null}` and the TrendCard rendered the dash placeholder.
Add `computeBpInTargetWindows()` next to the existing `computeBpInTargetPct()`
helper. It filters the input series by `measuredAt` against the supplied
clock and runs the same pair-and-count logic over the trailing 7-day and
30-day windows. The route fetches the last 30 days of data once, derives
both shares from the result, and surfaces them as `bpInTargetPct7d` and
`bpInTargetPct30d` on the response. The dashboard tile maps them to
`avg7` and `avg30` so the sub-values now show the actual percentages.
Coverage:
- 6 unit tests for the windowed helper (empty input, mixed window data,
null-7d-with-real-30d, default-clock, Marc's production fixture).
- 2 integration tests against testcontainers seeding 30 days of paired
BP measurements; both windows produce the expected hand-counted shares.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
v1.4.16 phase B5e: ship the POST endpoint that backs the per-rec
thumbs-up / thumbs-down UI. Body is the four rec-attributes the
client just rendered (id, text-snapshot, severity, metric-source +
time-range) plus the boolean verdict; server-fills providerType +
promptVersion via `resolveFeedbackAttribution()` so the client cannot
poison the daily aggregator's slice by claiming a thumbs-down was
attributed to a rival provider.
Idempotent via the existing `withIdempotency()` wrapper — a retry
with the same Idempotency-Key replays the cached response with
`X-Idempotent-Replay: true`. The dedup unique key on the model
(userId, recommendationId, recommendationText) returns 409 when the
same rec-text is re-rated — that's by design, the aggregator wants
per-text signal not per-id signal so a regeneration that rewrites
the same id with new text re-rates cleanly.
The attribution helper prefers `chainProviderType` over `providerType`
in the latest insights.generate audit row so when the B5b multi-
provider chain falls through to a secondary, the feedback row
reflects the working provider not the configured one. Falls back to
"unknown" + the current PROMPT_VERSION constant when no audit row
exists yet — the aggregator buckets that separately.
Audit row: action `insights.recommendation.feedback`, details carry
the feedback id, severity, helpful, providerType, promptVersion.
Tests:
- 7 unit tests for the Zod request schema (valid path, severity
poisoning, time-range poisoning, empty fields, stringified bool,
extra-field stripping)
- 5 unit tests for `pickProviderType()` priority + fallback
- 4 integration tests: 201 happy path with provider attribution,
409 dedup, 422 validation, fallback to unknown when no audit row
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
v1.4.16 phase B5e: ship the table that backs per-recommendation
thumbs-up / thumbs-down feedback. Each row captures (userId, recId,
recText) with snapshotted severity + metric-source attributes plus the
provider + prompt-version that produced the rec — server-fills the
attribution from the user's most recent cached payload so the client
can't tamper.
Dedup key (userId, recommendationId, recommendationText) lets a
regeneration that rewrites the same id with new text re-rate cleanly
while blocking accidental double-submission of the same (id + text).
Indexes: (userId, createdAt) for the per-user timeline and
(severity, helpful, createdAt) for the daily aggregator's slice. Both
are needed by the v1.4.16 admin AI quality preview.
GDPR: ON DELETE CASCADE through users; cascade-delete integration
test now seeds and asserts a feedback row.
Same migration adds AppSettings.adminAiInsightsFeedbackSummary — the
JSON blob the daily aggregator (next commit) writes a per-(severity x
provider x prompt) helpful-rate to. Null until the aggregator runs
or until there is feedback in the 30-day window.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Two scenarios pinned end-to-end against the postgres testcontainer:
saving a valid reordered chain persists the JSON column with priority
normalised to 1-indexed insertion order, and saving an empty chain
rejects with 422 + leaves the column untouched. No fetch mocks; the
route runs against the real Prisma client so a future schema drift on
User.aiProviderChain trips the suite immediately.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
End-to-end integration test for the multi-provider redundancy runner.
Boots the postgres testcontainer, seeds a user with both an OpenAI key
and an Anthropic key plus an explicit chain (openai -> anthropic),
intercepts upstream HTTP calls via fetch-spy, and exercises three
scenarios:
1. Hard-fail-then-success cascade. OpenAI primary returns 401, the
runner walks to Anthropic, the route surfaces a 200 with
`chainProviderType: "anthropic"` and `fallbackHopCount: 1` recorded
in the audit log.
2. All-fail cascade. Every chain entry returns 503, the route surfaces
a 503 with the "temporarily unavailable" envelope.
3. Last-working cache. After scenario 1 the runner remembers Anthropic
was the working provider; the next call (cache bypass forced via
nulled `insightsCachedAt`) reorders the chain so Anthropic is tried
first and only ONE upstream fetch fires (not two — the doomed
OpenAI 401 round-trip is skipped).
Test routing on URL substring (`/chat/completions` for OpenAI,
`/messages` for Anthropic) instead of headers so the assertion is
robust against any future header-shape drift in the clients.
Constrained to user-level providers because the testcontainer
migration history pre-dates several `app_settings` columns added
through schema-only edits — touching admin-openai resolution would
blow up before the chain runner even sees the request.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The integration suite that landed in commit 226cac4 still imported
the dotted-segment routes (`@/app/api/export/measurements.csv/route`)
that vitest can't resolve. Realign the import paths and request URLs
to the actually-shipped `/api/export/{kind}` segments. 9 tests pass.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Host-load chart above /admin/system-status renders the last 2h of
load1, memory %, and disk-IO % from a per-minute pg-boss sampler.
Schema migration 0032_host_metric, /api/admin/host-metrics endpoint,
HostMetricsChart component (Recharts wrapper, next/dynamic from the
consumer), system-status section wired with the chart on top, EN+DE
i18n keys, 13 unit + 6 integration tests.
Three commits landed cleanly under their own titles (db, jobs, api);
the chart + wiring + i18n got absorbed into another agent's commit
due to a parallel-agent staging race during the verification gate's
stash/restore loop. Functionally everything is on origin/main.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Backs the new chart above /admin/system-status. Reads HostMetric rows
captured by the per-minute sampler and returns the window the chart
asks for via `?since=` (30m / 1h / 2h / 6h / 12h / 24h, default 2h).
Per-row response shape is what Recharts can plot directly:
- capturedAt ISO-8601
- loadAvg1 number
- memUsedPercent 0..100, rounded to 2 decimals
- diskReadBps / diskWriteBps number | null
Disk fields are derived server-side from the cumulative byte counters
the sampler captured. Computing the per-second delta in the route
keeps the chart component stateless and means a hypothetical CLI / iOS
admin view gets the same units. The first row in any window has no
predecessor, so disk fields are null. A negative delta — counter reset
on host reboot — also surfaces as null instead of a misleading negative
BPS spike.
`meta.memTotalBytes` carries the most recent total so the tooltip can
render an absolute "4.2 GiB / 8 GiB" without a second round-trip.
requireAdmin()-gated: host telemetry is admin-only, never exposed via
Bearer tokens. apiHandler wrapper handles the wide-event annotation
("admin.host-metrics.list") and request-id propagation for free.
6 integration tests against the testcontainer Postgres pin auth
gating, the 2h default window, the diskBps derivation across a
counter-reset, the `?since=30m` filter, and the empty-DB happy path.
Adds the per-minute snapshot table that backs the new admin host-load
chart above /admin/system-status. One row per minute, captured by the
pg-boss sampler in the next commit, with 7-day retention enforced
inside the worker so the table stays under a few thousand rows.
Schema mirrors what the chart needs:
- load_avg_1/5/15 (DOUBLE PRECISION) — os.loadavg() output
- mem_used_bytes / mem_total_bytes — derived from os.totalmem() and
os.freemem(), kept as raw bytes so the API can compute either a
percent or a MiB delta downstream
- disk_read_bytes / disk_write_bytes — nullable cumulative byte
counters from /proc/diskstats. NULL on macOS/Windows dev hosts;
Linux production picks them up automatically. The API endpoint
converts deltas to bytes-per-second between samples
Indexed by captured_at so the "last 2 hours" query stays index-only.
Migration 0032_host_metric. integration setup.ts adds host_metrics to
the truncate list so testcontainers stays clean across runs.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The BD-Zielbereich tile rendered 0% for users whose readings sat below
the ESH 2023 narrow goal band (Sys 120-129 / Dia 70-79 for under-65).
Marc's actual production data has many readings like 117/79 — textbook
normotensive, well-controlled — that v1.4.15 A4 still counted as OUT
of target because sys < sysLow (120). 5 of 10 of his last-30-day pairs
should be in-target by clinical interpretation; v1.4.15 reported 0.
Root cause: "in target" was defined as the narrow goal band, which is
the ESH treatment goal for hypertensive patients ON therapy — NOT the
desirable range for a normotensive HealthLog user. Users (and the
dashboard label) intuitively mean "BP is well-controlled = at or below
the ceiling, not implausibly hypotensive".
Fix: change semantics from `sysLow <= sys <= sysHigh && diaLow <= dia <=
diaHigh` to `90 <= sys <= sysHigh && 50 <= dia <= diaHigh`. The 90/50
floors guard against counting symptomatic hypotension as "good control".
Centralised the check in `isBpReadingInTarget()` so the 6 historical
call sites (analytics route, blood-pressure-status, features,
general-status, insights/cards, insights/comprehensive, insights/targets)
share one definition — pre-fix they had 5 independent inline copies of
the narrow-band formula, easy to drift on a future refactor.
Tests:
- 6 new unit tests pin the new ceiling+floor semantics including Marc's
exact production fixture (10 paired readings -> 50% under v1.4.16,
was 0% under v1.4.15).
- New `tests/integration/bp-in-target.test.ts` seeds Postgres
testcontainer with Marc's reading shape + null-tolerance + hypotension
edge cases.
Cache invalidation already correct: `measurementDependentKeys` includes
`analytics()` so adding a BP measurement invalidates the tile's
TanStack Query cache.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
v1.4.15 Phase B2, criterion 4. Every IntegrationStatus failure path
now writes a single AuditLog row with a documented schema, and this
commit lights up the real-Postgres regression guard for it:
action : "integrations.sync.failed"
userId : <subject>
details : {
integration: "withings" | "moodlog",
kind: "transient" | "reauth_required",
errorCode: string | null,
message: string, // plaintext (not encrypted —
// audit table is admin-only)
attemptNumber: number, // 1..N consecutive
state: "error_transient" | "error_reauth"
}
Successes are NOT audited — that path would be far too noisy
(every webhook-triggered sync is a row, ~ten times a day per active
user) and the integration_statuses.lastSuccessAt column already
tracks the same signal at one row per integration per user.
The integration test in tests/integration/integration-status.test.ts
provides 8 cases against a real Postgres testcontainer:
- failure writes both the integration_statuses row AND a matching
AuditLog entry, with the structured meta validated field-by-field
- lastError is encrypted at rest (column never matches plaintext)
- getIntegrationStatus() decrypts cleanly on read
- success clears the streak AND does NOT write an audit row
- admin Telegram alert fires once per burst (24h re-alert window)
- reauth_required parks the integration so isReauthRequired() is true
- markReconnected() clears the parked state without writing a fresh
success — that's the next sync's job
- markDisconnected() preserves the row as a tombstone but wipes
error state
- CASCADE delete on User removes the IntegrationStatus row
Setup file additions: integration_statuses added to the truncate-list
in tests/integration/setup.ts (already shipped under commit 4db72a8;
this commit only adds the test file that consumes it).
Tests: 11 / 39 integration pass. The dispatcher is module-mocked so
the test doesn't actually hit Telegram — we only assert that the
helper INVOKED the dispatcher with the right payload.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
v1.4.15 Phase B2, criterion 1. Until this release the Settings →
Integrations card showed "Connected / Last sync 23 min ago" and
nothing else. A user whose Withings refresh token had revoked saw a
green badge; a user whose moodLog instance was down saw the same
green badge with a slightly older timestamp. The signal was useless.
This commit adds:
- New `IntegrationStatus` table (`integration_statuses` migration
`0029`). One row per (user, integration) capturing `state`
(`connected | error_transient | error_reauth | disconnected`),
`lastSuccessAt`, `lastAttemptAt`, encrypted `lastError`,
`consecutiveFailures` counter, `alertedAt` window-guard.
- `src/lib/integrations/status.ts` — the only writers
(`recordSyncSuccess`, `recordSyncFailure`, `markReauthRequired`,
`markReconnected`, `markDisconnected`) plus a read-only
`getIntegrationStatus()` for the API. The error column is
AES-256-GCM encrypted at rest because Withings/moodLog 401s can
echo URL/apiKey fragments — we can't ship that into a future
backup tarball.
- `GET /api/integrations/status` — single roundtrip returns both
Withings and moodLog snapshots plus the global threshold (so the
UI's "{n}/{threshold}" string is server-sourced and rotates with
the env var).
- Settings → Integrations cards both gain an
`IntegrationStatusBanner` row above the credentials form: state
badge ("Connected" / "Reconnect required" / "Error" /
"Disconnected"), `{n}/{threshold} consecutive failures` chip,
last-success / last-attempt times, and a destructive-toned
last-error line. The banner is suppressed entirely when the
integration is fresh-connected with no history (no false alarms).
Tests: +20 unit (status helper threshold + alert-window state machine,
banner rendering across all four states) + 8 integration
(`tests/integration/integration-status.test.ts`) confirming
encrypted-at-rest, audit-log row shape, alert idempotency window,
and CASCADE-delete on User. 116 files / 883 unit pass, 11 integration
files / 39 pass.
Encryption uses the existing `src/lib/crypto.ts` AES-256-GCM helper —
no new key material. The `consecutive_failures` counter and
`alerted_at` window are wired to the dispatcher in the next commit
(`feat(integrations): admin Telegram alert on persistent sync
failure`).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
