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>
Both DELETE /api/devices/[id] and DELETE /api/auth/me/devices/[id]
performed the same four-write cascade (refresh-token lookup, refresh
revoke, access-token revoke, device delete) as separate Prisma calls.
A partial failure between the third and fourth write left the device
row alive with all its tokens revoked - the user's iPad showed in the
device list as "still registered" but every request returned 401.
Extract the cascade into a shared revokeDeviceCascade() helper and
wrap the writes in prisma.$transaction so they commit atomically.
Both routes now call the helper; the audit-log via tag and the wide
event action name stay route-local.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The Apple Health pink chip rendered only inside the desktop `<Table>`
cell. iOS users — the audience that actually consumes Apple Health
data — land on the mobile card branch and saw no source indicator at
all, risking duplicate hand-entries on top of synced rows. Add a
compact badge inline with the timestamp on the mobile card so the
distinction lands at every viewport. Component test asserts the
`measurement-source-badge` testid appears twice (desktop + mobile)
so the next layout refactor can't silently drop one branch.
Also extends the `POST /api/devices` unit test mocks for the
NotificationChannel auto-upsert added in the previous commit, plus a
new test that pins the same-user apnsToken collision path returning
201 idempotently (the cross-user path keeps its 409).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Two collision paths let the same APNs token attach to multiple Device
rows for one user, fanning a single push out to two rows and double-
charging the APNs quota:
1. The cross-user-hijack guard filtered `NOT: { userId }` so it
skipped same-user collisions entirely.
2. The `apns_token` index was non-unique.
Drop the `NOT: { userId }` clause so the lookup catches both cases —
cross-user collisions still 409, same-user collisions fall through to
the existing legacy-token upsert path. Pair with migration 0041
introducing a partial UNIQUE index over `apns_token IS NOT NULL` and
dropping the redundant non-unique sibling. Apple's APNs contract
guarantees one token per (device, app), so global uniqueness matches
the upstream invariant.
Migration is strictly additive at the rolling-upgrade boundary; the
NULL-allowed partial-index shape preserves legacy iOS rows without an
APNs handshake. Schema-side comment documents why the partial index is
introduced via raw SQL (Prisma can't express it natively) and warns
against re-adding the non-unique sibling.
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 Pearson p-value derives from the Fisher's-Z normal approximation.
At low df (df < 18, n < 20) the normal approx is generous in the
wrong direction — at df=12 a true p≈0.04 reports as p≈0.025, sneaking
past the p<0.05 surfacing gate. The v1.4.22 product-lead memo flagged
this as Code-MED-03 with a deadline of "before v1.5/v1.6 auto-
discovery ships" because the false-positive cost compounds when
correlations get auto-generated.
Two paths considered:
- Rigorous: drop in a 30-LOC incomplete-beta implementation so the
p-value is accurate at every df. Cleanest fix, no test churn.
- Conservative: raise `MIN_PAIRED_N` from 14 to 20 so the borderline
band is excluded entirely. Smaller patch, no maths-library
dependency.
v1.4.23 ships the conservative fix. The rigorous incomplete-beta
swap is queued as a v1.4.24 candidate; if usage data from the
v1.4.16 B5e feedback aggregator later shows users miss the
borderline cards, the rigorous path lands then.
Trade-off: a small set of borderline-significance correlation cards
stop rendering. Acceptable for v1.5 — the prompt-injection guards +
warm Coach prose make it more important to under-report than over-
report patterns.
Tests +1 (`pearson` n=15 → insufficient pin) plus an existing
`correlateBpCompliance` n=13 test renamed to n=15 + the noise-fixture
extended from 15 to 20 entries to clear the new gate.
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>
The W3-of-v1.4.22 sentinel parser silently dropped malformed rows and
fired `coach.keyvalues.parse_failed` only when the entire block was
unusable. Mixed-format drift (one row breaks, the other six parse)
landed without any signal. Surface it.
- `SentinelParseResult.malformedEntries[]` records each skipped row
with a typed reason (`missing_colon` / `value_overflow` /
`label_overflow` / `no_END_marker` / `byte_overflow` /
`schema_invalid`). Block-level failures (truncation, missing close
marker) land here as synthetic entries so the wide-event always
carries a typed cause.
- Per-row label and value caps moved out of the Zod schema into the
parser so the row-level reason can be `label_overflow` /
`value_overflow` rather than the catch-all `schema_invalid`.
- Chat route splits the annotation: `coach.keyvalues.parse_partial`
when at least one row parsed AND at least one row failed, the
existing `coach.keyvalues.parse_failed` stays for full-block
failures. Both annotations carry the per-line reason array.
- Backwards-compatible `parseKeyValueLine` wrapper preserved.
Tests +5: label_overflow, value_overflow, byte_overflow,
mixed-malformed entry assertions, and a tryParseKeyValueLine
direct-API surface check.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Adds GET /api/auth/me/devices to list a user's paired devices
(label, lastSeen, channels, isCurrent marker) plus matching DELETE
routes at /api/auth/me/devices/[id] and /api/devices/[id]. Revoke
cascades: every refresh token bound to the device is killed alongside
its paired access tokens, then the device row is deleted.
Cross-user attempts return 404 (no enumeration leak). The duplicated
/api/devices/[id] endpoint is the native-friendly URL the iOS client
calls on APNs token rotation, mirroring the W3 open question.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Extends the device-registration body schema with the paired APNs
identity fields the iOS client populates once it has an APNs token from
`application:didRegisterForRemoteNotificationsWithDeviceToken:`.
Validation rejects half-supplied requests (`apnsToken` without
`apnsEnvironment` or vice versa) with 422 and enforces hex format on
the token — catching the common iOS implementation bug where the token
gets serialised through Swift's `Data.description` (which renders
`<deadbeef cafebabe>` with spaces and angle brackets) instead of the
hex-join shape Apple's docs spec.
The cross-user-hijack guard from CLAUDE.md is duplicated at the
APNs-token layer: a registration whose `apnsToken` is already owned by
another user returns 409 with reason `apns_token_owned_by_other_user`.
APNs tokens aren't secrets, so trusting wire input would let any
client who learns one redirect another user's pushes — same threat
model as the existing `token` guard, applied to the new field.
Audit-log details for `devices.register` now carry `hasApnsToken` and
`apnsEnvironment` so admin trails surface APNs pairing events without
leaking the raw token. Five new route tests cover the validation +
hijack paths (paired-or-omitted, hex regex, create-with-pair,
cross-user-409, the original 401/422/409/201 contracts stay green).
Ticks STATE.md F4 and lands `.planning/phase-W3-v1423-report.md`
covering the six W3 commits.
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>
The measurements list now paints `APPLE_HEALTH` rows with a Dracula-
pink chip whose accent matches the iOS app's brand. The localised
label ships in both English and German via the new
`measurements.sourceAppleHealth` key; the helper falls back to the
SCREAMING_SNAKE value for unknown sources so a missing key would
surface immediately instead of silently rendering blank.
Admin backup restore guards (`MEASUREMENT_TYPES`,
`MEASUREMENT_SOURCES`) gain the seven new HealthKit-shaped types and
the new source value so a restore from a backup that contains Apple
Health rows doesn't get rejected as malformed.
A new badge regression test mirrors the existing BP-badge guard:
asserts the localised label paints, the Dracula-pink utility classes
land, and the bilingual locale still renders the same brand spelling.
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>
Six MEDs grouped per the W5 reconcile brief:
- Sec-MED-1: `hl_onboarding` cookie now `SameSite=Strict` (no
cross-site flow depends on it; sibling `healthlog_session` stays
`Lax` for the Withings OAuth callback).
- Sec-MED-2: `/onboarding` PUBLIC_PATHS match tightened from loose
`startsWith("/onboarding")` to exact path + subroute guard
(`pathname === "/onboarding" || pathname.startsWith("/onboarding/")`).
A future `/onboarding-export` route can no longer inherit the
silent-pass-through. Same guard mirrored on the redirect short-
circuit. Two new proxy tests pin the contract.
- Code-MED-3: lift `berlinDayKey()` from
`src/app/api/analytics/route.ts` to a shared
`src/lib/analytics/berlin-day.ts` and route the targets
sparkline-bucketing through it. The targets route used to bucket
by UTC `YYYY-MM-DD` so a 23:30-Berlin reading on Tuesday landed
in Wednesday's bucket. Four new unit tests pin DST + UTC-midnight
edge cases.
- Code-MED (streaming race): on slow connections SSE `done` fires
before the invalidate-refetch resolves, producing a 200-500ms
duplicate-bubble render. Add a 150ms grace window on the
message-thread that suppresses the persisted twin while the
streaming bubble is still in flight.
- Code-MED-2: drop dead i18n keys `insights.coach.settings` and
`insights.coach.settingsTooltip` (W3 removed the cog; the keys
had zero call sites and would carry confusing legacy if v1.4.23's
prompt-tuning panel picks a different key shape).
- Code-LOW-5: centralise `["user", "dashboardWidgets"]` query key
in `queryKeys.dashboardWidgets()` and migrate the three call
sites (dashboard, insights, settings/dashboard-layout-section).
Same query-key-collision discipline as `queryKeys.analytics()`.
Closes Sec-MED-1, Sec-MED-2, Code-MED-2, Code-MED-3, Code-MED-3
(streaming race), Code-LOW-5.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The Coach chat route had three identical `new ReadableStream({
start(controller) { try { ... } finally { controller.close(); } } })`
blocks (refusal / provider-error / happy path), differing only in
which frames they enqueued. Extract the boilerplate into
`src/lib/sse/create-stream.ts` so the v1.5 iOS streaming endpoints
inherit the same try/finally close semantics without copy-paste.
The helper accepts sync or async emit callbacks; the controller is
always closed in `finally` so a thrown emit never hangs the response.
Three unit tests pin the sync, async, and throw paths.
Closes Sr-H2.
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>
The tile computed `bp30 - bpAll` regardless of which baseline the
user picked under Settings → Dashboard, while rendering a caption
keyed on `comparisonBaseline` ("vs. last month" / "vs. last year").
The math therefore lied to the user. Every other trend tile uses
`tileCompareDelta()` against period-aligned `avg30LastMonth` /
`avg30LastYear` baselines.
Add `priorMonth` (now-60d…now-30d) and `priorYear` (now-395d…
now-365d) windows to `computeBpInTargetWindows()`. Ship the pcts on
the analytics envelope as `bpInTargetPctPriorMonth` /
`bpInTargetPctPriorYear`. Route the dashboard's `bpCompareDelta` to
subtract the prior window matching the user's baseline; fall back
to null for `none`.
Three new bp-in-target unit tests (priorMonth, priorYear, null
windows) and two insights-polish guards (envelope contains the
fields, page no longer subtracts `bpAll`).
Closes Code-H2.
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>
Maintainer-voice sweep across `src/`. ~190 references to the
maintainer by first name in code comments and JSDoc neutralised to
"the maintainer", "the live tenant", "users", or "the user" depending
on context. Three sed passes covering ~50 distinct patterns
(`Marc reported`, `Marc wants`, `Marc kept`, `Marc rolled back`, etc.).
Test fixtures (`displayName: "Marc B."`, `username: "marc"`,
`<HeroStrip userName="Marc">`) kept as opaque test data per the brief.
CHANGELOG normalisation. The v1.4.14 + v1.4.15 entries paired a
German bullet with its English translation by historical design — the
in-app copy is English-default and the user docs are English, so the
mixed-language style was a holdover from the early-marathon notes.
A one-off node script extracted the `_..._` English paragraph from
each bilingual bullet and rewrote the entry as that text. ~44 bullets
reduced; one Docs bullet that lost a leading word in the regex
fixed by hand.
CLAUDE.md → CONTRIBUTING-AI.md rename so the filename is no longer
AI-vendor-specific. `CONTRIBUTING.md` reference updated. `AGENTS.md`
stays in place for multi-agent compatibility (the conventions doc is
shared with Codex / Cursor / etc.).
Wave-4 state wrap. STATE.md now records C1–C5 + D + D2 as complete;
v1421-backlog.md grew a "Closed in v1.4.22" header listing the 20
items the marathon landed; `.planning/phase-W4-report.md` documents
the per-commit decisions, test deltas, and the 23 items deferred to
v1.4.23 with reasoning.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The post-hydration redirect for users with `onboardingCompletedAt ===
null` caused a brief dashboard flash before the client-side effect
could fire. The redirect now lives in `src/proxy.ts` so it lands on the
first server response.
The proxy runs in the Edge runtime and can't reach Prisma, so the auth
routes (login / passkey-verify / register / password / /api/auth/me)
mirror the DB `onboardingCompletedAt` column into a non-httpOnly
`hl_onboarding` cookie. The cookie is a UX hint, not a security
signal — a user editing it locally only skips the dashboard flash;
they still can't bypass any server check. `/api/onboarding/complete`
clears the cookie so the next navigation drops the redirect
immediately, and `destroySession` + expired-session purge wipe it
alongside the session cookie.
The e2e onboarding-flicker spec can return to testing the actual
incomplete-onboarding case: the proxy reads the cookie (absent for
the fully-onboarded storage-state user), not the mocked `/api/auth/me`
response, so the test now sets `onboardingCompletedAt: null` honestly
instead of pinning it to a non-null value as a workaround.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The Zielwerte page read as a static reference cheat-sheet — every card
surfaced a current value + range bar but no recent trajectory. Each
target now grows a dependency-free 30-day sparkline beneath the range
bar plus a localised "Δ −2.3 kg vs. last month" caption so the page
reads as a living health log rather than a guideline lookup.
The API computes both fields from a single 60-day query (one round-trip,
not two): `points30d` is the daily-mean series for the last 30 days,
`deltaVsLastMonth` is the signed difference between the current and
prior 30-day averages. Both are null when either window has fewer than
3 readings so cold-start accounts don't see a misleading flat trace
or a "± 0" comparison that's really "no comparison".
BMI piggybacks on the weight series (divided by height²) so the BMI
card's sparkline matches its range bar's y-axis. Derived metrics
(BP-in-target rate, mood stability, medication compliance,
blood-glucose-by-context) keep their previous chrome — the rich
status surface they already render is the right answer there.
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>
New `.planning/phase-v1421-hotfix-report.md` summarises the six
fixes (Daily Briefing regenerate · Coach day-level snapshot · Coach
prompt update · streaming-bubble dedup · drawer header · sources rail
scope picker), the test-count delta (2026 → 2036 unit), the
token-budget impact of the day-level snapshot (~190 → ~3000 tokens
per full-scope turn), and a recommendation to ship as a v1.4.20.1
hotfix.
STATE.md grows a Phase F section + status block tracking the six
commits on develop. Includes prettier polish across the touched
coach surfaces (sources-rail, drawer, message-thread, snapshot,
chat route).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The Coach snapshot used to ship only aggregated statistics (mean,
slope, SD, range, count) per metric. A turn that asked
"why was BP higher on Monday?" had no day-level rows to ground in
and the model fell back to apologetic aggregate-only phrasing
("from the snapshot I cannot isolate the specific Monday").
Extend buildCoachSnapshot to fold in:
- timeline.recent: one row per UTC day for the last 14 days, each
tagged with its weekday so the model can answer day or weekday
questions directly. BP rows pair systolic + diastolic; days with
only one side measured are dropped to avoid fabricating a
complement.
- timeline.weekly: ISO-week buckets covering days 15..N where N is
the configured window. Keeps the prompt budget tight on 30/90-day
windows while still letting the Coach cite older weeks.
- per-day medication adherence rows from MedicationIntakeEvent so
the Coach can answer "did I miss my dose Tuesday?" without
inventing the schedule.
Also add the optional `scope` field to coachChatRequestSchema (sources
+ window) so the upcoming sources-rail picker can narrow the snapshot
without breaking older clients — missing fields fall through to
all-source last30days.
A typical 30-day, 5-source snapshot lands around 2.4-2.8 KB JSON
(≈700-900 prompt tokens) — comfortably inside the 25k/day Coach token
budget.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The /api/insights/generate route was still calling the legacy
getInsightsSystemPrompt that returns the v1.4.5 {changed, stable,
drivers, …} shape and never asks the model for a dailyBriefing block.
GROUND RULE 8 (emit dailyBriefing when the snapshot has signal) lives
on getStrictInsightsSystemPrompt in src/lib/ai/prompts/insight-
generator.ts; the route never adopted it. Re-runs from the hero strip
therefore stored a payload with no briefing, the use-insights-advisor
lift saw null, and the briefing card painted its empty state forever.
Switch the route to getStrictInsightsSystemPrompt(locale). Existing
strict-shape tolerance is unchanged: insightResultSchema.safeParse
falls through to the raw parsed body on shape mismatch, and
aiInsightResponseSchema's passthrough() keeps any custom keys for
forward compat.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The Phase D security review flagged a "Marc's data (572 paired
readings, …)" comment in the analytics route. It predates v1.4.20
but the file received new commits in this release, so neutralise the
example to a generic "busy account" wording that conveys the same
shape without leaking a maintainer name.
Fixes Security-LOW-4.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- Drop the withIdempotency wrap on POST /api/insights/chat. The wrapper
caches response bodies via cloned.text() then replays through
NextResponse.json(JSON.parse(...)) — turning the SSE wire format into
a null body on retry. The PWA never sends Idempotency-Key so the bug
is hidden today; the iOS client would walk straight into it. Dedup
still holds via the conversationId existence check + 20-turn cap.
- Read the SSE response body even on !response.ok when the content type
is text/event-stream so the structured error frame the route emits
surfaces its errorCode to the bubble. Without this the stream was
read only on 2xx and the rich error channel was dead code.
- Stabilise the useSendCoachMessage opts reference via useRef so an
inline-literal { onDone } from the drawer no longer re-memoises send
on every render.
- Drop the unused snapshot parameter from streamProviderError (the
ReturnType<typeof Object.assign> alias widened to any). Switch the
error response to status 200 so the streaming client reads the SSE
body and parses the error frame instead of branching on HTTP status.
Fixes Code-HIGH-1, Code-HIGH-2, Code-HIGH-3, Code-HIGH-4, Security-M-1,
Senior-HIGH-1, Simplify-S-01.
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>
Compute the three pre-defined correlation hypotheses
(BP × compliance, mood × pulse, weight × weekday) on the trailing
30-day window in `/api/analytics` and surface the typed result
shapes on the response payload. Each runner is gated on n >= 14
+ p < 0.05; below the bar the result.status === "insufficient"
and the per-card EmptyState paints in place of a misleading
near-zero scatter.
The insights page now mounts:
- `<CorrelationRow>` between the Daily Briefing and the Advisor
card — the layout slot the artboard reserves for the patterns
surface.
- `<TrendsRow>` immediately below it, fed from
`advisor.payload.trendAnnotations` (lifted client-side via
`trendAnnotationsSchema.safeParse`). Legacy cached payloads
predating PROMPT_VERSION 4.20.1 surface the per-metric
empty-state hint instead of a half-rendered annotation.
The wide-event annotation captures per-hypothesis status so admin
observability can attribute coverage gaps without re-querying
the DB.
10 source-scan tests pin the load-bearing imports, the JSX mounts,
the analytics-route surfacing, and the malformed-payload null
fallback in the advisor hook.
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>
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 concurrent toggles on different charts (user opens two tabs,
flips BP "Target range" in one and Weight "Trend" in the other
within ~50ms) could drop one of the updates. Both reads landed on
the same dashboard-layout snapshot, then each wrote its merged blob
back, with the second write clobbering the first chart's change.
Wrap the read-modify-write in a $transaction with Serializable
isolation so the second writer either sees the first writer's
result or aborts. Same pattern any future widget-prefs route should
follow until we move the JSON to a jsonb_set-based atomic merge.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Seven mechanical cleanups, no behaviour changes:
- Drop the duplicate ChartOverlayPrefs type + DEFAULT in
chart-overlay-controls; re-export the canonical pair from
dashboard-layout so a future fourth toggle can't drift between
the UI and persistence layers.
- useChartOverlayPrefs accepts null/undefined chartKey and short-
circuits the dashboard-layout fetch when none is supplied. Drops
the chartKey ?? "bp" fallback and the three discard-the-result
ternaries in health-chart; mini-mode renders no longer subscribe
to the BP chart's persisted prefs.
- /api/analytics no longer pair-and-counts BP twice — the windowed
helper already produces last30Days, so the headline reads it back
instead of running computeBpInTargetPct on the same input.
- Drop the redundant moodEntries.map shape in the achievements
route; the prisma select already returns the matching shape.
- Merge the five hidden-metric cases into the no-precondition block
of isEarnable; the defensive comment admitted they couldn't fire.
- Remove the deprecated getAchievementCategory wrapper (zero callers).
- Strip six "v1.4.18 gradient removed" what-comments scattered
across the chart wrappers; the polish tests pin the absence.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Hidden Easter-eggs leaked their trigger semantics through the JSON
response: a curious user with DevTools open could read metric names
(nightOwlCount, leapDayCount, etc.), i18n keys (hiddenNightOwl,
hiddenLeapDay, etc.), icon names, and target values without unlocking
anything. The opaque-card UI was already correct, but the wire shape
spoiled the surprise.
Project hidden+locked entries to a sentinel shape before serialising
(achievements.hiddenCard.title key, HelpCircle icon, target 0,
metric totalTakenIntakes), and drop hidden-only metric counters from
the metrics block unless the matching achievement is unlocked. The
iOS branch reuses the same redacted view so native clients can't
short-circuit the surprise via the resolved-strings shape.
Once an Easter-egg unlocks the real fields ship — the unlock IS the
reveal moment.
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>
Wires the v1.4.18 expansion metrics into the gamification route.
- Fetches `MoodEntry` rows alongside the existing measurement /
intake / passkey / audit fetches so the mood badges have data.
- Extends the audit-log query with `doctor-report.export` and
`settings.locale.update` (the new hidden Easter-egg triggers).
- Pushes the raw rows through `buildExpansionMetricValues` —
mood streak / improvement, weight/BP/pulse counts, consistent-month,
entry day-streak, weekend warrior, and the hidden trigger counts.
- Computes `EarnabilityFlags` from the same numbers and applies
`applyDiscoveryFilter` to the evaluated achievement list. Locked
public badges that the user has *no path* to earn yet are filtered
out; hidden Easter-eggs and already-unlocked badges always pass.
- Recomputes the headline summary (`unlockedCount`, `totalCount`,
`earnedPoints`, `totalPoints`, `nextAchievement`) from the visible
set so the dashboard counters match the rendered list. The
`nextAchievement` selector skips hidden cards so we never tease
the user with a "next goal: ?" suggestion.
The iOS format mock had to grow a `moodEntry.findMany` mock; that's
a one-line pure-test change.
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>
The GET response used to surface the resolveProviderChain()-filtered
list, which DROPS disabled entries upstream. The Settings UI then
seeded `enabled: true` for every returned row, so disabling an entry
made it disappear on next refetch and lose its toggle position —
the toggle was functionally a "remove from chain" button.
Changed GET to read the *persisted* chain via parseProviderChain() so
disabled rows still round-trip with their flag. The active-provider
summary still uses resolveProviderChain so the displayed "Active: …"
line continues to reflect the actual runner ordering (enabled-only).
The Settings UI seeds entries with the wire-supplied `enabled` value
instead of always-true, so re-enabling becomes possible without a
page reload.
4 unit tests pin the GET shape (persisted-chain ordering, disabled
entries surfaced, cached-active overlay, default-chain fallback).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
H5 — `POST /api/insights/feedback` had no rate limit. The unique
index `(userId, recommendationId, recommendationText)` blocks exact
replays but a malicious client could distort the daily aggregator's
bucket slice by varying recommendationId/text per request. Added
`checkRateLimit("insights-feedback:<user.id>", 60, 60 * 60 * 1000)`.
60/h is generous given a comprehensive insight rarely has >10 recs.
H6 — `<RecommendationFeedback>` invalidated the entire `["insights"]`
prefix on every thumbs click, which matches all 8 insights queries
(comprehensive + 7 per-status). None of them depend on the feedback
row. The 24h server cache absorbs the actual LLM round-trip but the
network thrash + stale-cache refetch was waste. Dropped the
invalidation; user-visible verdict state lives in localStorage +
local React state. v1.4.17's prompt-version ratchet will scope its
own invalidation when feedback feeds the next generation.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
`redactEventForEgress()` only redacted `error.message`, `error.stack`,
`warnings`, `http.user_agent` and `external_calls[*].error`. The
free-shape `meta` field and `action.details` blob carry annotated
key=value pairs from `annotate()` calls — including the
provider-runner's `ai_chain_hop_<n>_reason` which captures the upstream
error body capped at 240 chars. If an upstream provider ever echoes a
Bearer token in its error body, the raw token would land in `meta`
without any scrub. Added a recursive `redactDeep()` walker that runs
`redactSecrets()` over every string-shaped value inside both blobs.
Same gap on `/api/admin/audit-log`: the `details` JSON column was
returned verbatim. A user-supplied identifier in a failed-login row
(e.g. a typo'd "Bearer hlk_..." in a username field) flowed through
the deepened B4 admin viewer + CSV export. Run `redactSecrets()` over
each row's `details` at egress so already-persisted rows are scrubbed
on read without a backfill migration.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Extend `buildUserPrompt()` to accept an optional `ComparisonSnapshot`
that, when supplied, appends a SYSTEM CONTEXT block listing each
metric's current 30d average, baseline 30d average (from 30 / 365
days back), absolute delta, and percentage delta. The strict system
prompt gains a sixth ground rule that instructs the model to narrate
the most clinically-significant non-null delta in the summary's first
sentence and forbids inventing comparison numbers.
The route reads the user's persisted `dashboardWidgetsJson.compari-
sonBaseline` and builds the snapshot from a per-metric `summarize()`
sweep so the numbers the LLM sees match what the dashboard tile
renders — single source of truth for the comparison delta. Comparison
is default-on whenever the toggle is on per research §7 Q4: there's
no secondary "include in AI" preference, the pulldown is the single
affordance.
PROMPT_VERSION bumped 4.16.0 → 4.16.1 so the Wide-Event annotations
attribute responses to the new prompt revision.
Eight new unit tests pin: empty-comparison block render, EN/DE
locale switch, lastMonth vs lastYear language, the
"summary first sentence" instruction, and the anti-hallucination
"do NOT invent" guard.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
