When a derived wellness score (readiness or recovery) crosses a notability gate
— outside the green band AND confidence at least medium — the insights
generator now appends a SYSTEM CONTEXT block so the briefing can narrate the
shift observationally. Mirrors the GLP-1 plateau detector's append mechanism:
reads the one derived contract, returns null (the common case) at zero token
cost, and instructs the model to frame the signal as an observed pattern, never
a diagnosis or a dose recommendation. Add the readiness/recovery sourceMetric
enum values plus their briefing href + icon + trend-chart mappings.
Add a "derived" block to the Coach snapshot: one tiny object per high-signal
derived metric (readiness, recovery, sleep, stress, strain, HRV balance,
cardio-fitness band, vascular-age delta) carrying value + band + confidence +
historyDays — never the raw series. A fully-populated block is ~250 tokens,
comfortably inside the snapshot budget. Insufficient metrics are omitted so the
model never sees no-data noise; each metric's compute is fault-isolated so a
transient failure on one never sinks the turn. Gated on the underlying signals
staying in scope. The system prompt now documents the block and frames the
bands as descriptive composites, not clinical findings.
The standalone /targets (Zielwerte) page is retired. Target editing
moved inline onto the Insights metric pages in v1.8.6 — each metric's
reference panel mounts the editor and writes the same
PUT /api/user/thresholds, reading the same /api/insights/targets
payload. The page carried a deprecation notice and had already dropped
out of the navigation, so removing it is a UI-only change: no data
model, API route, or inline editor moves.
Remove the page and its tests, the components reachable only from it
(target card, per-card coach button, summary header, target prompt /
scope helpers, coach-handoff hook), the now-dead /zielwerte→/targets
proxy redirect, and the orphaned targets.* i18n keys across all six
locales. Repoint the handful of code comments that pointed readers at
the page to the inline Insights panel, and prune the two coach
gate-inventory allowlists plus the queryKey factory guard root that
named the removed files.
The reference panel keeps the range bar, consistency strip, status
pill, edit sheet, and source-link helpers — those are the live editing
surface now.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
(cherry picked from commit 7f842c5620087127e980fe22a56133135b7c0531)
The ChatGPT Codex backend rotated its ChatGPT-auth model slugs off the
`-codex` specialist line onto the plain `gpt-5.x` line, so the in-code
default ladder (`gpt-5.3-codex`, `gpt-5-codex`, `gpt-5`, `gpt-4o`) is
now rejected and insight generation fails with a 503 on a fresh deploy
that has no `CODEX_MODEL_FALLBACK_CHAIN` override.
Replace the default ladder with the current accepted set, in order:
`gpt-5.5` (current default across paid tiers), `gpt-5.4` and
`gpt-5.4-mini` (documented fallbacks), `gpt-5.3-codex` (late rung, still
accepted intermittently), `gpt-5.2` (legacy floor). The
fall-through-on-rejection walk, the working-slug cache, and the env
override path are unchanged.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
(cherry picked from commit bced19de2d4f0788bfd6fa56a78e719347776a1f)
Extend the assessment-card system beyond the seven specialised scopes to
the ~30 HealthKit metric pages, without hand-writing a prompt per metric.
- Add a metric-metadata registry keyed by HealthKit id (display name,
unit, direction, optional normal range, archetype, scope), covering the
data-bearing HealthKit metrics. The seven specialised metrics keep
their own scopes and are excluded from the generic set; an unregistered
id gets no card.
- Add a generic data-driven generator that reuses the existing graded
snapshot, provider runner, stale-while-revalidate cache, and persist
path. One prompt template per archetype (physiological-vital,
activity-fitness, body-composition, mobility-gait,
environmental-exposure) plus a dedicated sleep template, parameterised
by metric metadata. Empty-data metrics return an insufficient marker
with no provider call. Normal ranges use age + sex where the profile
stores them; no ancestry/region ranges.
- Add GET /api/insights/metric-status?metric=<id>: apiHandler-wrapped,
Zod-validated against the closed registry id set (422 on unknown),
read-only with stale-while-revalidate. First insights route with
OpenAPI coverage; regenerate docs/api/openapi.yaml.
- Route the generic metric:<id> scope through the on-demand status queue
worker dispatch.
- Extend the nightly warm pass to the generic metric caches for a user's
data-bearing metrics only (one distinct read gates the set), keeping
de+en warm and never calling a provider for an empty metric.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
(cherry picked from commit 41453fbdfee60793c16269b9a9e5f04b6c3ea450)
The hard '~5 measurement points' floor did not fit mood (counted in
entries) or medication adherence (counted in scheduled doses). Re-word
the gate as 'a few measurement points/entries/events' and note that the
unit depends on the metric. Also fix the gating-field path: the recency
field lives at dataCoverage.newestMeasurementDaysAgo, not on summary.
The mood card noted persistent low phases but offered no gentle path to
support. When mood stays clearly low for several days, the model now
offers an autonomy-preserving pointer toward talking it through with a
trusted person or a professional — never alarming, never a diagnosis, no
emergency tone. The safety-contract matrix does not cover this pathway
and does not reach the per-metric assessment prompts, so it lives here.
For an infrequent schedule such as a weekly injection, the 7-day
compliance figure is dominated by a single dose: one miss swings the
percentage sharply and reads as a collapse it is not. Tell the model to
lean on compliance30 as the load-bearing value when schedulesPerDay is
low and treat compliance7 as a rough pointer only. Output stays {summary}.
The overall-status card summarises up to six metrics, but it inherited
the single-metric 30-60 word budget, which forced the model to either go
generic or overrun. Grant the section an explicit 3-5 sentence / 50-80
word budget and cap it at naming two metrics by name, with the rest
mentioned only when they deviate notably from their own mean.
The bmi and weight cards produced near-identical trend text for a user
with both metrics, since bmi is weight scaled by a constant. Re-aim each
card so they carry distinct information: bmi now centres on WHO-band
placement (call out a band crossing or a near-boundary value against the
person's own baseline), and weight stays on the continuous trend and
pace (kg/week, plateau, milestone). Each defers the other concern to its
sibling card.
Drop the dead-field guidance (avg90/allTime, historicalComparison,
ratePressureProduct, bodyCompositionDivergence, seasonalVariation) and
the chart-token instruction. Describe the per-type measurementSeries map
and the adherence/mood/target context, pull them into one coherent
picture against the person's own baseline, and close with the single
most important doable step.
Replace the historicalComparison and moodAdherenceRisk guidance with the
actual per-medication snapshot fields (compliance7/30, streak,
taken/skipped/missed, dailySeries). Read the recent direction as
compliance7 vs compliance30 against the person's own baseline, frame
positively, and close with one blame-free doable step.
Describe the graded mood series, target band and tag list, lead on the
weekly pattern against the person's own baseline, name persistent low or
high phases calmly as an observation rather than a diagnosis, and close
with one kind doable step.
Describe the graded BMI series and target band, lead on the trend over
the single value, keep the WHO bands as placement anchors rather than a
label for the person, and name BMI's body-composition limits plainly.
Drop the chart-token instruction the status path strips out.
Replace the dead-field guidance (historicalComparison.weight,
allTimeMax, slope30, bodyCompositionDivergence, sleep.avg7) with the
graded weight series. Lead on the weekly/monthly trend rather than the
single value, define plateau and sustainable pace against the person's
own baseline, anchor milestones to their own maximum, and gate BMI
context on a known profile height.
Drop the stale snapshot vocabulary (avg7/30/90, historicalComparison,
slope30, rate-pressure product) and the chart-token instruction the
status path strips out. Describe the graded pulse series and target
band, compare the recent days to the person's own weekly/monthly
baseline at a ~5 bpm significance threshold, and frame a rising or
falling resting pulse as a possible explanation rather than a diagnosis.
The status cards render only the model's summary field, yet the prompt
described a snapshot vocabulary (avg7/30/90, historicalComparison,
ratePressureProduct, seasonalVariation) that the graded snapshot no
longer carries, and demanded a full findings/correlations JSON schema
that this path never reads.
Rebuild the shared base prompt around the actual graded shape (summary +
recent/weekly/monthly/yearly with min/max/mean/slope), the own-baseline
comparison, a name -> place -> one-step structure, a warm
autonomy-supporting tone, a 2-4 sentence length, honest data-gating, and
a { summary } output. The blood-pressure section judges systolic and
diastolic together against the person's own baseline with ESH 2023 as
the placement anchor.
Pure-history medication detail page, legacy step consolidation, and the
finish of the outbound-fetch migration.
- /medications/[id] becomes a read-only history surface; every setting
moves into a new advanced-settings sheet, and the edit trigger becomes
a two-option picker. The list page is unchanged.
- A pg-boss job folds pre-v1.5.0 granular step rows into one canonical
daily total per user per day and soft-deletes the originals; migration
0087 adds a partial index for the converging discovery scan.
- Every remaining server-side fetch routes through safeFetch (Withings,
Codex OAuth + SSE, bug-report, Umami, GlitchTip, Loki); a new
healthlog/safe-fetch-required ESLint rule guards the boundary.
- Fixes: intake-edit dialog seeded from real values, consolidation skips
a unique-constraint day instead of stranding it, avatar upload reads
the body once under a bounded cap, egress lint rejects absolute URLs.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Closes issue 218. Flips the convention from "remember to opt in to
redirect: manual" to "remember to opt out". Every outbound fetch that
doesn't pin a hard-coded host now routes through safeFetch and inherits
AbortSignal.timeout(15_000) so a tar-pit upstream can no longer pin a
worker indefinitely. The local AI client also gates on
requirePublicHost: true since its host is user-supplied; operators
running self-hosted Ollama / LM Studio on an RFC1918 address keep their
escape hatch via ALLOW_LOCAL_AI_PRIVATE_HOSTS=true (also enforced at
write-time in /api/user/ai-provider).
14 outbound call sites migrated. The four that already pinned manual
redirect (the historic templates) keep their semantics; the wrapper
preserves an explicit init.redirect. Adds undici as an explicit
dependency so the connect-time pin landing alongside this can rely on
the documented API rather than a transitive hop.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Adds an optional Coach-backed overlay that extracts a structured
medication payload from a free-text description so the wizard can
pre-fill its steps. The route is rate-limited and budget-gated; the
prompt carries a citation-coverage guard so the extraction cannot
hallucinate a name + dose pair the user did not write.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The OpenAI, Anthropic, and local OpenAI-compatible clients all used a
bare `fetch()` with no `signal`. A tar-pit upstream (a misconfigured
local Ollama on a stalled GPU, a flaky proxy in front of a hosted
provider, or a deliberately malicious user-configured LOCAL endpoint)
could accept the POST and then hang indefinitely, pinning the request
handler until the connection died on the socket level.
A 60 s ceiling lands well outside any legitimate completion budget
(production timings live in `getEvent()?.addExternalCall` traces) while
capping the worst case.
The Codex client uses an SSE stream with its own loop and stays as-is
for now; a follow-up can thread the same ceiling through the streaming
read once the contract there is settled.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Six touch-disjoint waves landed on develop before this release:
- W1-KNIP — exports/types tiers flipped to enforcing-mode on main;
35 unused exports + 52 unused types triaged to 0/0; shadcn surface
+ zod-infer contract types scoped via knip.json ignore-block.
- W2-ZOD-MULTI-ISSUE — `returnAllZodIssues` shared helper +
`/api/dashboard/widgets` 422 now returns every Zod issue + worker
audit-ledger breadcrumb. 41 sibling routes documented for v1.4.43.
- W3-QUERYKEY-LONGTAIL — 40 settings/medications/admin/hooks files
migrated to the queryKeys factory; 9 new factory entries; ESLint
rule + test-guard scope extended in lockstep.
- W4-ARCH-HYGIENE — BERLIN_DAY_FORMATTER consolidated across nine
sites (seven status helpers + bucket-series + bp-in-target);
Suspense double-comment consolidated; doctor-report sanitiser regex
rewritten to escape-form so diffs are reviewable; pr-detection-
worker soft-delete filter; offhost-backup DR-intent comment.
- W5-IOS-WORKOUTS — `dedupeWorkoutBatch` write-time cross-source
dedup helper for the v1.5 iOS HealthKit observer ingest; dashboard
tile-strip placeholder parity with the live TrendCard chrome.
- W6-WITHINGS-OFF + ENV-CHECK — Withings off-response classifier
(transient/reauth/persistent) + WithingsApiError typed throw + the
`pnpm check-env` CLI. APNs `allOrNone: true` closes the AP-2
silent-disable gap the wave was conceived to close.
No migration, no env-var change, no API contract break for iOS v0.5.4.
The new `/api/dashboard/widgets` 422 envelope is additively extended.
pnpm test --run green at 4815 passing / 1 skipped.
pnpm typecheck, pnpm lint, pnpm knip (no --include flag) green.
Eight touch-disjoint waves landed on develop before this release:
- W-INSIGHTS-HOT + W-RECONCILE-INSIGHTS — extract the timeout-stub
persist helper and wire all seven *-status routes through it, closing
the recurring ~14 s warm response the iOS client sees on dashboard
open once the AI provider has stalled once that day.
- W-DELETED-2 — close the remaining three soft-delete reader-tier gaps
(export bundle, gamification achievements, doctor-report aggregator)
with a five-route integration-test pin.
- W-ORG — types consolidation into src/types/analytics.ts and
src/types/backups.ts; prompt directory unification.
- W-FRONTEND-FACTORY — queryKey factory expansion + ESLint rule lift.
- W-IOS-COORD — POST /api/auth/check-user four-branch onboarding
discovery, identifier matched verbatim, per-IP rate-limited.
- W-SIMPLIFIER — today-intake projection helper extract; unused tx?
params dropped; 13 knip-flagged dead exports trimmed.
- W-PERF-OPS — v1.4.39 W-SUM legacy-NULL UNION discovery arm retired.
- W-PROCESS-DOCS — pg.Pool sizing operator doc; ESLint rule
formalisation; knip CI gate staged for v1.4.42 flip.
No migration, no env-var change, no API contract break for iOS v0.5.4.
The new check-user endpoint is an additive surface. AP-2 .p8 key is
installed; SB-5 time-sensitive APNs is live as of this deploy.
pnpm test --run green at 4732 passing / 1 skipped.
pnpm typecheck, pnpm lint, pnpm knip green.
Eleven touch-disjoint waves landed on develop plus a six-axis QA
reconcile round before tagging. See CHANGELOG.md for the user-facing
prose; this commit message documents the wave + report inventory for
release-management traceability.
Waves shipped (each with a phase report under .planning/):
- phase-W-POOL-v1440-report.md — p-limit(4) wrapper around the
analytics 15-way fan-out + pg.Pool max raised 10 -> 20. Closes the
v1.4.39 empirical-trace finding #1 (Prisma pool starvation).
- phase-W-DELETED-v1440-report.md — 11 reader-tier helpers + 3
integration contracts close audit Critical Finding #3 (soft-delete
invisibility) across dashboard, analytics, summaries, rollup tiers,
and the Coach snapshot path.
- phase-W-INSIGHTS-v1440-report.md — mood-rollup swap on the three
/api/insights/{features,targets,cards} routes plus the
compliance-rollup hook gap closure for bulk-projection mints; the
post-QA reconcile patch closes the six remaining measurement.findMany
sites in the cluster that still leaked tombstoned rows.
- phase-W-INFRA-v1440-report.md — rollup helper umbrella consolidation
under src/lib/rollups/* with zero orphan re-exports; lint, typecheck,
knip, and 93/93 rollup tests green post-restructure.
- phase-W-RSC-v1440-report.md — per-tile Suspense boundaries plus the
queryKey factory-bypass walker test (extended to comparison/ in the
reconcile pass).
- phase-W-PRIVACY-v1440-report.md — bilingual /privacy page with 17
paired-section tests pinning the 9 SB-3 disclosure requirements.
- phase-W-AASA-v1440-report.md — /.well-known/apple-app-site-association
endpoint pinned to S8WDX4W5KX.dev.healthlog.app with app-ID parity
assertions guarding against split rotation.
- phase-W-APNS-NOTIFY-v1440-report.md — MEDICATION_REMINDER
time-sensitive APNs payload (priority 10 + interruption-level)
scoped via a parameterised test that pins all 6 other event-types
do not bypass Focus. AP-2 .p8 install gates real delivery.
- phase-W-CONSENT-v1440-report.md — AI consent receipts CRUD with
append-only invariant pinned in test; revoke-then-regrant leaves
both rows; idempotent DELETE returns 200 + receipt: null.
- phase-W-WMY-WIRE-v1440-report.md — three previously-dead WMY readers
(week/month/year) wired through summaries-slice and
health-score-fast-path with a linear-composability parity test
pinning the cross-consumer routing contract.
- phase-W-GHOSTS-v1440-report.md — ~1 177 lines of dead code removed
across 9 atomic commits; startOfUtcDay + wallClockInTz consolidation
eliminates a sibling-drift risk; knip whitelist trimmed to three
files pending follow-up.
QA reconcile patches applied per the v1.4.40 QA round (six reports
under .planning/round-v1440-QA-*-findings.md):
- senior C1 — dashboard-suspense-boundaries regex aligned with the
post-W-INFRA Thread 2 userTimezone-local lift.
- senior H1 — soft-delete filter added to the six remaining
insights measurement.findMany sites.
- specialist H1 — Promise.allSettled around bulk-projection
compliance recompute on both /api/medications/intake and
/api/dashboard/summary.
- ux H1 — compare-toggle migrated to queryKeys.dashboardWidgets
factory; walker test extended to src/components/comparison/.
- security M1 — consent artefact 64 KB cap enforced via
Buffer.byteLength (UTF-8 bytes, not UTF-16 code units).
Quality gates green at tag: pnpm typecheck, pnpm lint, pnpm knip
--include files,dependencies,binaries,unlisted, pnpm test --run
(4726 passing / 1 skipped). Tests 4525 -> 4726 unit + 1 skipped over
the v1.4.39 -> v1.4.40 span.
User-facing prose: see CHANGELOG.md.
Heavy-aggregate skip on the rollup-fresh + fully-covered path,
daily chart fetches opt into rollup buckets via source=rollup,
Insights extractFeatures swap drops the prompt payload from
double-digit MB to the low hundreds of kB on power-user accounts,
page-level isLoading gate replaced with per-section early-skeleton
paint, trends-row chart slot pinned for CLS, IntakeHistoryListV2
restored on the medication detail page, About card folded into the
Admin Console with an auto-checking update badge, cumulative metric
tiles read the day's running sum, IP-whois fallback surfaces city
+ country when the ASN lookup misses. Migration 0068 adds an
additive users.insights_exclude_metrics column. Unit suite 4354
passing; typecheck + lint clean.
Quality-leap release between two HealthKit milestones. The headline is a P0 hotfix for the `/api/analytics` 500 that broke the Insights mother page for any account with more than a few thousand measurements: the six per-metric status helpers were spreading the entire numeric history into `Math.min` / `Math.max`, which trips a stack overflow once a single argument list exceeds the V8 spread cap. Both the surfaced symptom and the latent risk in five sibling helpers were folded onto a reduce-based min/max path.
Around that hotfix landed a deep polish pass: the Insights mother page now defers three below-the-fold blocks behind `next/dynamic` to trim the cold mount cost, the analytics endpoint gained a `?slice=summaries` slim slice that the per-metric sub-pages now ride, the Coach snapshot builder picked up a 60 s LRU keyed on `(userId, scope)`, the Settings shell consolidated three duplicate copies of the about / notifications / about-dropdown surfaces, the navigation strip dropped a redundant "Home" group label and a colliding "Notifications" sibling, every icon-only button on the medications and admin surfaces gained an accessible name, every Progress bar gained one too, three pages had their heading hierarchy repaired to a sequential h1 → h2 → h3, the mobile Coach FAB now hides while a chart tooltip is open so it cannot occlude the read-out, and the auth shell normalised every authenticated route to a single `max-w-screen-xl` container.
Also lands the Apple App Site Association handler at `/.well-known/apple-app-site-association` on every host that fronts the app, advertising the iOS bundle's App ID prefix (S8WDX4W5KX.dev.healthlog.app) under `webcredentials.apps` so the passkey ceremony shares cleanly between the web origin and the iOS app.
The release closes nineteen issues from a five-surface audit + a runtime bug-hunt pass, plus six follow-up tracks of polish across the affected surfaces.
Bug-fix and consistency follow-through after the v1.4.27 mobile sweep.
The headline is a tighter dashboard and insights surface: six widgets
retire from code entirely (GLP-1 tile, dashboard `<DrugLevelChart>`
mount, GLP-1 detail-page intake history + inventory, the
`<InsightAdvisorCard>` block and its regeneration affordance, the
weekly-report route), four broken edges close (workout-edit duplicate-
timestamp 409, BD-Zielbereich tile rebuilt on the shared
`<TrendCard>` primitive, `/insights/puls` chart timeout fallback,
sticky tab-strip scroll lock), and one consistency contract lands per
maintainer directive: every medication-list row, every medication-
detail section header, every trend tile, every Coach launch glyph,
every chart-height contract reads on one shape. The HealthScore card
grows to fill its column, gains an accessible `?` tooltip explaining
the delta, and drops the placeholder "Wochenbericht erstellen"
button. iOS contracts are intact; the only `/api/*` evolution is
additive (the `aggregate=monthly` grain on `/api/measurements` and an
internal-only `/api/internal/web-vitals` beacon route).
Largest feature delta in the v1.4.x line. Insights expands into seven dedicated metric sub-pages; GLP-1 medication tracking lands end-to-end (drug-level chart with Research Mode acknowledgment, EMA titration ladder, cadence + compliance, side-effect taxonomy, pen/vial inventory); cross-source priority becomes a two-axis resolver; per-user timezone threads through ten analytics surfaces; Withings activity + sleep v2 sync; onboarding rebuilt as a nested-route wizard; Personal Records ship end-to-end; Health Score provenance accordion; Coach runs native first-party prompts across six locales with a 1800-assertion refusal-probe matrix; OpenAPI drift gate hard-fails; multi-arch GHCR image. Migrations 0043 through 0060 are additive and forward-only. PROMPT_VERSION 4.24.0 → 4.25.0 with GROUND RULE 9 (refuses dose recommendations) and GROUND RULE 15 (refuses drug-level estimates with MDR + MDCG 2021-24 cites).
See CHANGELOG.md for the full per-section delta.
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>
Three small reuse wins from the W6 simplify review:
- openapi/registry.ts swaps the lazy require() for a static import.
The ESLint disable + as-cast carried no real benefit; the only
callers always loaded the route table anyway.
- Extract useCoachPrefs() into a shared hook so the settings sheet
and message thread share one queryKey + one fallback shape. Removes
the drift between the two existing inline blocks.
- Replace the 9-deep wantsX boolean ladder in coach snapshot with a
single CoachScopeSource -> MeasurementType[] map. Drives both the
WHERE type IN (...) build and the appleHealthBlocks gate, so adding
a new metric is one entry instead of three parallel edits.
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 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>
Extends the strict insight schema, Coach snapshot pipeline, and
provenance envelope with the seven Apple Health categories that landed
in Wave 2 (HRV, sleep, resting HR, steps, active energy, flights,
distance, VO2 max, body temperature). All fields are additive and
optional — web-only accounts pay zero extra SQL and the prompt's new
GROUND RULE 12 instructs the model to stay silent when the snapshot
doesn't carry the HealthKit blocks.
Ratchets PROMPT_VERSION 4.22.0 → 4.23.0 and refreshes the
sourceMetric / trendAnnotations enums in both EN + DE. Two new test
files pin the prompt body and the snapshot fan-out.
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>
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>
Replace the v1.4.20 "conversational summariser" persona with a partner
who sits alongside the user — warm, curious, conservative, with seven
numbered ground rules that prefer invitation over refusal when data is
missing and reserve specific numbers for a structured evidence block
at the end of each reply. The day-level timeline section from v1.4.21
stays verbatim so weekday questions still resolve cleanly. Bumps the
shared PROMPT_VERSION from 4.20.2 to 4.22.0 and broadens existing
schema tests off the 4.20.x pin onto the 4.x train.
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>
Previously the Sources rail listed BP / Weight / Pulse / Mood /
Compliance as a static legend. Marc asked for a real "what I can
see" surface — per-source checkboxes (include/exclude) plus a
window selector (last 7d / 30d / 90d / all-time) that flow through
the Coach request body.
Wire the controls all the way down:
- <SourcesRail> grows scope + onScopeChange props. Each row
becomes a 36px tall flex row with a real checkbox; the row
fades to 60% opacity when its source is excluded.
- A Select trigger above the list drives the window. Both control
surfaces share the existing insights.coach.window.* i18n keys;
add a new windowLabel key so the dropdown has an EN+DE label.
- <CoachDrawer> owns the scope state (resets on each mount per
the v1.4.20.1 plan — no conversation-level persistence yet) and
forwards the picked scope through useSendCoachMessage to the
chat request body. The payload only ships when the user has
narrowed away from the all-source last30days default so the
server can tell "no opinion" from "intentionally narrow".
- buildCoachSnapshot already accepts the optional CoachScope from
the previous commit; it now flows end-to-end.
No new dependencies — checkboxes are plain inputs styled with
Tailwind + Dracula tokens.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The previous Coach prompt only said "ground every number in the
SNAPSHOT" without telling the model that the snapshot now carries a
timeline.recent block of day-level rows with weekday labels.
Without that pointer the model kept defaulting to aggregate-only
phrasing on day-specific questions.
Add a DAY-LEVEL READINGS section to both EN and DE prompts:
- explain the timeline.recent / timeline.weekly shape
- tell the model to answer day-specific or weekday-specific
questions out of timeline.recent and to cite the actual reading
with date + weekday
- when no row exists for the day named, say so plainly and offer
the closest available day rather than the aggregate
- older weekday questions fall back to timeline.weekly
- the scope.sources field is the conversation's source-allowlist;
a question about a non-listed metric should be acknowledged as
out-of-scope rather than answered from the aggregate
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>
- weekly-report eyebrow chip drops uppercase + tracking-wide for the
sentence-case rule the rest of the app follows; print stylesheet
now neutralises bg + colour so monochrome output reads clean
(Design-M4, Design-L3).
- correlation-card "Try a 7-day experiment" CTA flips from default to
outline while disabled. Disabled-primary read as "the system is
broken right now"; outline reads as "this is on the roadmap"
(Design-M7).
- coach-drawer settings cog aria-label switches to the coming-soon
tooltip copy so SR users hear the same "arrives in v1.4.21" message
sighted users see (Design-M9).
- sources-rail static "fresh" dot becomes aria-hidden — v1.4.20 has
no real freshness state behind it; SR users no longer hear "Fresh"
five times in a row (Design-L4).
- summariseTitle slices on Unicode code points rather than UTF-16
code units so a user message ending mid-emoji ("🩺") no longer
produces a half-character on disk (Code-LOW-04).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
