The eleven per-metric/derived-score status helpers (pulse, weight,
bmi, mood, blood-pressure, medication-compliance, general, the generic
metric card, biomarker, the shared feature cache, the derived-score AI
warm layer) computed todayKey from toBerlinDayKey(new Date()) before
resolving the user's own timezone — several fetched the profile only
for downstream day-bucketing, after the cache read had already run on
the Berlin key. A non-Berlin user's card regenerated at their local
evening (Berlin midnight) and, for biomarker series and the
derived-score prompt label, mis-keyed data or displayed a hardcoded
"(Europe/Berlin)" regardless of their actual zone.
Threads resolveUserTimezone()/userDayKey() ahead of every cache read
so the day-key and the data bucketing agree, and reuses the one
resolved value everywhere downstream instead of re-deriving it.
The asc+take(20000) window-cap bug (fixed on the correlations route
alone) and the mixed-grain toDailyMeans bug (fixed on three of four
readers) both survived on the Coach get_correlations tool, the
per-metric assessment card, and the period narrative. Dense accounts
saw the cap drop the newest rows on the coach/card readers and drop
the CURRENT period on the narrative — backwards for a recent-window
and a current-vs-prior surface respectively; the narrative's own local
toDailyMeans twin also averaged sleep stage-segments and blended
per-sample step chunks with drained daily totals instead of summing.
Hoists the fetch + grain resolution into
fetchMeasurementWindowSeries/fetchMoodWindowSeries
(correlation-channel-series.ts) — desc+cap+resort, full column select
for buildMeasurementDailySeries's per-type grain — and routes the
route, the coach tool, the per-metric card, and the period narrative
through it, deleting every local copy.
Four data-correctness fixes in the same class as the workouts-list
ordering bug (05f80ad37):
- GET /api/measurements groupBy=day: the raw-row scan ordered oldest
first and sliced to `limit` before bucketing, so a long history never
surfaced its recent days. Reads newest-first now. The per-day sum
also ran over every source unfiltered — an Apple Health + Withings
write for the same day doubled the total. Routes through
pickCanonicalSourceRows first, matching the rollup tile's collapse.
- PR detection's cumulative-day picker summed every row on a calendar
day regardless of source (false "record" days) and bucketed on the
UTC calendar day instead of the user's timezone. Rewritten to
source-collapse before summing and bucket on the user's IANA zone,
reading through the worker's injected Prisma client so the existing
dependency-injection contract for tests stays intact.
- The correlation-discovery matrix (the insights route, the per-metric
assessment card, and the Coach's get_correlations tool — three
independent copies of the same fetch) averaged cumulative types
(steps, daylight) and sleep across mismatched grains: per-sample
chunk means blended with drained daily totals, and sleep averaged
per-stage segment durations instead of summing a night's total.
Hoisted the grain resolution into one shared
buildMeasurementDailySeries helper (source-collapsed day-sum for
cumulative types, per-night reconstruction for sleep, mean
unchanged for spot vitals) so all three surfaces agree.
Regression tests cover newest-first ordering, cross-source collapse
matching the rollup, PR no-double-count, and the shared grain helper.
Fold the ECG silo into the insights narrative without crossing the
non-diagnostic line — the app reports the recording device's own verdict
and the existence/count of recordings, never an interpretation of the trace.
- Feature snapshot: a bounded, device-verdict-only ECG descriptor (recording
count, device-verdict distribution, latest recorded-days-ago + average HR)
flows into the nightly briefing prompt. The waveform never enters the
payload; the grounding gate admits the pre-computed counts so a
device-attributed sentence stays grounded. A prompt rule (EN + DE)
constrains any mention to the device's attribution and forbids reading
morphology, measuring intervals, or emitting a verdict of the app's own.
- Pulse cross-link: a device-attributed pointer from the resting-HR / pulse
page into the ECG viewer, un-mounting when no recordings exist.
- Daily rail: an ecg_new_recording item surfaces once when a recording landed
within the last day — calm, info-level, deep-linking the viewer. Gated on
the insights module; the DTO carries no waveform.
- i18n across all six locales; non-diagnostic disclaimer copy per language.
"Ask the Coach" on a document used to navigate to /coach?doc=<id> — a full-page
jump away from the vault. It now opens the real, doc-scoped conversation in the
shared side drawer, and the drawer's maximize control expands it to the full
/coach page while preserving scope.
- Thread an optional documentId through the launch context: askCoach gains a
fourth argument, the provider tracks it alongside prefill/scope and clears it
on close, and LayoutCoachMount forwards it to the drawer as initialDocumentId.
The open-state precedence moves into a pure resolveLaunchState helper.
- The vault detail sheet closes itself and calls askCoach(..., doc.id) instead
of routing away, so the drawer owns the surface.
- Maximize preserves continuity: the drawer reads the live conversation id via
a new imperative getter out of the conversation surface (parallel to the
reset registration) and hands off to /coach?c=<id> once a thread exists,
falling back to /coach?doc=<id> for a chat maximized before its first turn.
The send path is untouched: every document turn still routes through the
hardened fenced endpoint keyed on documentId — only where the conversation
renders (drawer vs page) changed. The documents-chat e2e now asserts the
drawer opens in place, doc-scoped, rather than a URL change.
ECG recordings synced from a compatible watch were stored encrypted but
shown nowhere. They now have a surface in Insights: a list of recordings,
each opening the full single-lead waveform on a familiar ECG grid, with the
date, duration, average heart rate, and the result the device recorded.
The read routes narrow ownership in the query and decrypt the waveform
through the existing fail-closed codec; the overview is min/max-decimated so
the R-wave peaks survive the reduction, with a raw path for a calibrated
view. The result shown is the recording device's own classification,
attributed to the device — HealthLog does not read or interpret the trace
and produces no verdict of its own. A permanent note states this, and a
non-normal result carries a line to discuss the recording with a clinician.
Deferred perf fixes from the campaign's verified perf-correctness audit,
correctness-first (each with an output-equivalence test):
- comprehensive-generate fan-out: replaced per-type 400d findMany+JS-average
with DB prisma.aggregate(_avg) over the exact half-open windows the JS
reducer used (current 30d, lastMonth (60d,30d], lastYear (395d,365d]), same
rounding + null-on-empty, pLimit(4). SLEEP_DURATION stays on the raw path
(per-night reconstruction dedup). Byte-equality test vs the old algorithm.
- boot-discovery: replaced Prisma in-memory distinct with DB SELECT DISTINCT
in the 4 backfill discovery scans + migration 0243 (7 additive
partial indexes matching each predicate). Integration test asserts identical
discovered set against real Postgres.
- ChatBubble wrapped in React.memo with a comparator (onRegenerate compared by
presence — the thread rebuilds it each render), so only the streaming bubble
re-renders per token.
- doctor-report mood read narrowed to {score, tags} (the only fields the
collector uses); the 730d main measurement read left as-is — a blind bound
would corrupt clinical stats (documented deferred follow-up).
Migration 0243 additive-only.
The per-metric insight assessments opened on the current value and read as
a data readout, while the overview texts lead with the day's verdict and
land the warm, motivating tone. Diagnosis (campaign insights-copy audit +
verification): identical warm persona/contract fragments, but the
per-metric USER prompt instructed number-first while the overview
instructed verdict-first, and the opener-hint rotation was wired into
briefing/scores/Coach but never the per-metric path (so the base prompt's
'do not open with the number' clause stayed dormant there).
Rewrote the seven per-metric assessment user prompts (generic archetype +
six bespoke: BP/weight/pulse/BMI/mood/compliance + overall) verdict-first
in EN+DE — meaning first, the number right after as support; grounding,
non-diagnostic framing, no-vendor and no-markdown all preserved (only
clause order changed). Wired openerArchetypeHint into metric-status and
the bespoke generators. Factored a shared openingShape contract into
shared-contracts so overview/per-metric/scores can't drift again, with a
coverage test. Lifted the three deterministic first-paint fallbacks to
verdict-led. Prompt-contract regression tests added. No new model calls,
token budget flat.
The recurring no-briefing day had a chain of causes, closed end to end:
Every failure path in the nightly pregenerate + the comprehensive generator
now annotates a queryable cause (several classes — features-error,
payload-too-large, aborted, generator-failed — previously bumped a counter
with zero trace). A failed nightly warm enqueues one bounded retry ~45
minutes later (singleton per user, existing budgets apply), so a transient
provider hiccup heals before morning. A cached payload that carries NO
briefing no longer satisfies the 24h POST short-circuit nor the
unchanged-content hash gate — a once-stripped briefing could previously
block its own regeneration indefinitely. The card surfaces the omission
reason persistently (grounding strip, generation failure, not attempted)
with a forcing retry.
Documentation corrected against code truth: Withings credentials are
per-user (the documented env path never existed; the dead example entries
and manifest rows are gone, and WITHINGS_WEBHOOK_SECRET is now actually
whitelisted in compose — stock deploys could never deliver it); the classic
Fitbit portal no longer accepts new registrations; the backup-restore
example no longer mints a fresh encryption key and uses pnpm dlx tsx; the
TLS guide describes the real client model (two CA-level SPKI pins,
any-match, leaf renewals need no build); scaling/admin references fixed;
the operator-shared subscription provider is documented.
Platform-wide hardening: the failure classes found live this week hunted down
across every integration.
Fitbit carried the same tombstone wedge fixed for Google — probe now matches
soft-deleted rows and the update resurrects them; the comment describing a
partial unique index that never existed is corrected. Sleep segment ids are
stable across re-scoring for Withings (session+segment-start), WHOOP/Polar
(one segment per stage, no positional index) and Oura (run-start keyed), each
with a session-scoped sweep that soft-deletes rows a re-score orphaned — so
legacy and affected nights heal as they are re-read.
One platform rule for deleted rows: source-owned readings resurrect on
re-import (Withings, WHOOP, Oura, Polar, Nightscout, mood webhook, CSV
re-imports, Apple stats day-totals); Apple sample-grain deletions stick per
the paired-client contract, and the mood bulk route's tombstone match is now
a true no-op reported as duplicate. Import counts reconcile against actual
createMany counts.
Google lifecycle: a dead token registers on the cycle's hard-fail ledger, so
an expired connection parks instead of stamping success hourly; backfill and
sleep-repair markers stamp only after a clean pass (pg-boss retries are now
real); failed measurement writes hold the watermark; no-op updates are
skipped; mapping.md tells the current truth.
Scale: doctor-report reads only consumed columns and enabled sections;
exports and backups keyset-paginate; achievements tally via SQL buckets;
series charts day-bucket dense kinds beyond 90 days; BP pairing is a linear
two-pointer; distinct-type scans run server-side; the graded-series cold
fallback is bounded; the fitbit defer tracker loops instead of spreading.
The comprehensive briefing warm/cron path wrapped generation in a fixed
130 s outer abort, but the per-user response-timeout setting accepts
10-600 s and the AI settings tell users to raise it for slow local
models. Any account whose response timeout was >= ~130 s had every
comprehensive warm clipped by the warm bound, not the provider, so the
generation never landed: no cached briefing row was written and the
dashboard fell to the hard empty state.
Size the warm outer abort from the resolved effective timeout
(`aiResponseTimeoutSeconds * 1000`, falling back to the comprehensive
surface budget) plus a fixed headroom for feature extraction, prompt
assembly, and the cache write. A raised setting now extends the warm and
nightly budgets instead of being silently capped. An absolute ceiling
(the 600 s write-time maximum plus the headroom) keeps a wedged call from
pinning the worker while staying above the largest value a user can set.
Both the nightly loop and the forced on-visit warm read the per-user
setting and use the derived budget.
Make the empty state more useful: record the upstream HTTP status on a
failure marker and classify it (timeout / auth / rate-limit / provider /
format), so the "couldn't generate" state points at the right lever —
raise the response timeout for a timeout, re-check the provider for an
auth rejection — instead of one generic line. Keep-last-good behaviour is
unchanged.
Align the response-timeout field copy with the actual default budget
(~120 s, not ~180 s) across the placeholder, the OpenAPI description, and
the inline note.
The insights alert cards computed medication compliance with the naive
`schedules.length × days` denominator, so a fully-adherent weekly
injectable read ~14% and fired a false low-compliance alert (and a paused
medication mis-fired the same way). Route the alert path through the
canonical `calculateCompliance` engine like every other compliance
surface — pause eras, schedule revisions and dose windows honoured.
Document confirm: committing a numeric observation against an existing
biomarker silently replaced the stated unit with the catalog's, with no
conversion — a stated "6.1 mmol/L" against a mg/dL marker committed
"6.1 mg/dL". Reject on a unit mismatch (fail closed) so the user
reconciles on the review screen, the same posture as the unit-required
guard.
Wire grip strength, waist (with waist-to-height) and pain into the
briefing feature set and the grounding allow-set so the clinical-depth
signals reach the daily narrative; the mental-health screeners stay
excluded by construction.
Biomarker detail: fall back to a generic description for catalog-less
markers, and keep the heading + description with a retry on the error
state. Collapse the medication External-API and Lifecycle groups by
default. Re-enable the insights scroll-to-top regression and assert the
shipped main-content reset.
Align the EN haemoglobin/haematocrit display names to British spelling.
Drop the redundant `(userId, deletedAt)` index on inbound documents — a
strict prefix of the new three-column index. Trim the dead
MedicalDisclaimer variants to the one live `dataPosture`. Move the
crisis-resources card off the retired amber tint to a calm
destructive-subtle border. Add a registry invariant asserting every
biomarker signal key resolves to a real catalog slug.
Add coverage for the new biomarker-assessment seam and the marker detail
surface:
- the generator serves today's cache, re-stamps unchanged readings without an
LLM call, and regenerates only when the latest-reading fingerprint changes
- the read-only endpoint returns the envelope, 422s a missing id, and honours
the auth + insightStatus gates
- the detail page paints the stat strip, the chart placeholder, and the
assessment card
- the biomarker resource route drops the marker with its readings in one
userId-narrowed transaction and rejects an inverted target range
Hold the input gate independent of the worker's forced run so an idle marker
re-stamps cached text instead of regenerating, and list the new route on the
non-Coach gate allowlist.
The daily briefing and the per-metric status assessments ignored the
per-user response-timeout setting: they hardcoded their per-surface
AI_BUDGETS default, so raising the timeout for a slow self-hosted or
local backend had no effect and the surfaces still aborted early. Only
the coach threaded the setting through.
Resolve the effective timeout from User.aiResponseTimeoutSeconds in one
shared helper and thread it onto every non-coach generation call:
- runStatusCompletion is the single chokepoint every status / reference
surface funnels through (per-metric cards, the batched assessment, the
derived assessments, the period narratives), so resolving it there
applies the setting to all of them at once — on both the upstream
call's own timeout and the outer wall-clock cap that previously clipped
a raised value at 60 s.
- The comprehensive briefing generator and the user-initiated regenerate
route thread it onto the main generation, the JSON retry, the grounding
retry, and the paragraph re-roll.
On a failed generation the briefing keeps its last good text — no cache
row is written, so the previous payload stays intact — and records a
dated, append-only failure marker (no migration; reuses the audit-log
JSON pattern). The read path compares the marker against the last
successful generation so it can tell a held briefing from a current one.
A cluster of related correctness gaps in the compliance denominator and the
insight surfaces that read it:
- Paused medications. A doctor-ordered pause flipped `active` off and stamped
`pausedAt`, but resume nulled `pausedAt`, so the interval was irrecoverable
and every paused day became a missed dose after resume — collapsing
adherence across the Health Score, the BP gate, the Coach snapshot and the
report. Persist pause intervals as durable eras (new `MedicationPauseEra`,
migration 0211), close the open era on resume, thread the eras through the
compliance context and drop slots inside a paused interval from the
denominator. Every compliance call site now fetches and passes the eras.
- Health Score eras. The Health-Score fast path was the only compliance
caller that skipped the shared schedule select and schedule revisions, so
after a schedule edit it scored past days against the current schedule
while every other surface used the historical era. Switch it to the shared
select and thread revisions (and pause eras) like the canonical path.
- Insight bucketing timezone. The per-metric status series bucketed every
user in Europe/Berlin, so a near-midnight reading landed in the wrong day
and the relative-day phrasing was off for non-Berlin self-hosters. Thread
the resolved user timezone and key off `userDayKey`.
- Correlation significance. User-facing correlations surfaced from five
paired points with strength read straight off the coefficient. Route them
through the rigorous engine (at least twenty pairs, Student-t p below 0.05)
so small-N coincidences no longer render as confident findings.
- Resting-pulse input. The mood-versus-"resting pulse" correlation fed the
raw PULSE day-mean, which folds in workout HR, under a "Resting pulse"
label. Feed `resolveRestingPulseSeries` (clean RESTING_HEART_RATE, else a
daily low-percentile proxy) so the label matches the input.
Add three read-only awareness cards to the Insights overview, each drawn
off an existing engine and each honest about empty state — the section
un-mounts rather than surfacing a husk.
- Health status: surfaces what is drifting from the user's own normal by
folding the personal-band deviations (coincident-deviation engine) with
the dated, sustained level shifts (changepoint detector) at
GET /api/insights/health-status. Awareness only, never a diagnosis.
- Breathing screening: summarises the last 30 nights of the per-night
sleep-breathing-disturbance index plus device-flagged events at
GET /api/insights/breathing-screening. Mirrors the device's own
classification and states plainly that it is a screening signal, not a
diagnosis — discuss with a clinician.
- Lab changes: pairs the two most-recent numeric lab panels and reports
each shared analyte's signed delta and reference-band standing at
GET /api/insights/labs-changes. Neutral framing only.
Each reshaping helper is pure and unit-tested for its present/absent
states. Register the three sections in the insights-layout universe so
they merge in as default-visible, wire them into the overview and the
edit-mode title map, add the query-factory keys, document the routes in
the OpenAPI contract, and translate every new string across all six
locales.
The daily briefing's always-on feature payload carried only the core vitals,
mood, sleep, steps and medication compliance, leaving four captured domains
invisible to it. Add four blocks to the aggregated features:
- Labs: recent flagged biomarkers (out-of-range or trending vs the prior
reading). Retired markers are excluded; qualitative results stay neutral with
no fabricated verdict.
- Preventive care: due and overdue items off the server-authoritative next-due
date, so an overdue screening can prompt an early nudge.
- Workouts: a provider-agnostic count, duration and distance aggregate over the
trailing windows (the briefing previously saw activity only as step counts).
- Glucose: the present-and-trend block the other vitals carry, where glucose
previously reached the briefing only as a single signal-of-the-day row.
The three extra reads are scoped to the wide briefing window; the tight
snapshot window that already carries its own context skips them. Every block is
omitted when its domain is empty rather than emitting zeros, and user-entered
labels are sanitised before they reach the prompt.
Add a rolling 14-21 day early-detection pass to the FDR correlation engine
so an emerging shift (illness pulling HRV and sleep down together) surfaces
before the 180-day retrospective scan accrues the n>=20 it needs. The recent
pass re-runs the same engine over the trailing window with a lower paired-day
floor, a tighter Benjamini-Hochberg target, and a no-faint effect bar, then
drops any pair the retrospective scan already established so a pattern is never
reported as both established and emerging.
Extend the curated behaviour x outcome matrix with three clinically meaningful
links: medication adherence -> next-day blood pressure (systolic and diastolic,
the latter previously never a candidate channel), sleep as a behaviour
(poor sleep -> next-day mood / HRV), and a separate point-vs-window labs ->
outcome pass (each draw against the contemporaneous outcome mean) since sparse
lab draws cannot meet a daily-lag floor. Every pass keeps FDR control, the
effect-size floor, and shrinkage; thin data degrades to absent, never a
fabricated link. All associations stay descriptive, never causal.
Clicking a type on the measurements list now drills into that metric's
insights sub-page when one exists, falling back to the existing
?type= filtered list when it does not. A reverse type-to-slug map backs
the navigation, preferring the dedicated single-metric page so an
ambiguous type resolves correctly (PULSE to pulse, not blood-pressure;
WEIGHT to weight, not bmi). No API change.
The comprehensive insight that feeds both the daily briefing and the
insights trend narrative is a single reasoning-heavy generation over the
full feature snapshot. On a large account it runs past the provider
client's fixed 60 s timeout and is aborted mid-stream, so the chain
reports an all-failed outcome, no cached block is written, and the
surface falls back to its static placeholder on every visit. The warm
paths bounded the same generation tighter still (45 s) and counted the
failure with no observable signal, so the blank state was permanent and
silent.
Make the per-request upstream timeout configurable
(CompletionParams.timeoutMs, default 60 s for every existing caller) and
raise it to 120 s for the comprehensive surface only, across all three
generation paths: the on-demand regenerate, the on-demand warm, and the
nightly pre-generation. Raise the warm-pass budget to 130 s so the
provider's own timeout governs a genuine completion rather than clipping
it early. Annotate the comprehensive failure in both the generator and
the nightly loop so a generation that keeps failing is queryable instead
of leaving the surface empty without a trace.
Add a deterministic narrative layer the Coach narrates rather than invents:
- Briefing callbacks + forward-looks: the daily briefing recalls the prior
period and points ahead, anchored to a figure, one callback per surface.
- Tension Verdict: when the readiness composite's contributors disagree
(good sleep but a rising resting pulse), surface a brief honest internal
read on the health-score card. A real clinical red-flag is never reconciled
away into a calm verdict.
- Streaks + return-to-baseline: a pure detector over a DAY-bucket series
closes a worry once a metric returns inside the personal MAD band after a
genuine out-of-band run; a gap day breaks a streak.
- Coach prompt: add develop-discrepancy, roll-with-resistance, and an
anti-persuasion clause; ratchet PROMPT_VERSION.
The tension flag and streak event are computed server-side; the card lines
render resolved fields and the model narrates them.
Render daily medication-compliance rate and illness symptom-severity as
first-class series in the FDR discovery engine, so the adherence-dip →
symptom-flare link (and compliance → vital drift) can finally surface.
Compliance pools every active medication's dose-history ledger into a per-day
taken/(taken+missed) rate, re-keyed to the user's display timezone. Symptom
severity reads the illness day-log functional impact, zero-filling healthy days
only across real episode spans so a user with no episodes yields an empty
series rather than a constant. Both flow through the existing n >= 20, BH-FDR,
effect-size, and shrinkage gates unchanged; a sparse series degrades to absent.
Each channel forms its own metric family (no self-lag tautology) and keeps the
association-not-causation framing. Add discoveryMeasurementTypes() so every
caller drops the non-measurement channels before a Prisma type filter.
Significance alone surfaced trivial drivers: a large-n pair with r=0.16
narrated as a confident "tends to go with" link while explaining ~2.5%
of variance. Add three gates before a pair is ranked as a driver:
- exclude same-metric-family lagged pairs (mood->mood, BP component
self-lag) as serial-autocorrelation tautologies, widening the existing
exact self-pair skip to the whole family.
- shrink each Pearson estimate toward null by n/(n+10) so a thin-data
correlation cannot out-rank a deep one on an inflated point estimate.
- floor the shrunk effect at 0.2 (drop below) and bind 0.2-0.3 to a
hedged "faint hint" phrasing tier, 0.3+ to confident phrasing scaled
by sample depth. The reported r and p stay the honest raw statistics.
Rank by shrunk effect magnitude, q as tie-break.
The no-key and timeout fallback text carried zero reference to the user's
own readings and, on a provider timeout, rendered as hasProvider:true —
indistinguishable from a fresh assessment. Compose each fallback from the
per-metric signal the card already builds: name the current value, place it
against the user's own baseline, and close with one plain-language pointer,
in the same warm voice as the model surfaces. Degrade to the prior generic
tip only when a metric has no usable history. The timeout envelope now
reports hasProvider:false so the UI surfaces it as the computed summary it
is rather than mislabelling it as provider prose.
The floor reads Date.now() inside buildComparisonSnapshotForUser, so it
lands in [before - 400d, after - 400d] relative to the test's brackets.
The prior upper bound used before - 400d, which fails when a millisecond
ticks between the bracket read and the snapshot's clock read.
buildComparisonSnapshotForUser read a user's entire measurement history
per type with no date floor, then fed each series to summarize(). The
snapshot only consumes avg30 / avg30LastMonth / avg30LastYear, and the
widest of those reaches into the [365, 395)-day window (ageMs < 395 days
in meanOfWindow), so nothing older than 395 days can change a result.
Add a 400-day measuredAt.gte lower bound to every per-type read in both
copies of the builder — the page-blocking POST /api/insights/generate
handler and the shared comprehensive-generate path the nightly
pregenerate cron drives. The fan-out runs all seven snapshot types via
Promise.all, so on multi-year accounts the unbounded scan was tens of
thousands of rows per type. 400 days keeps a 5-day floor over the
strict-less-than 395-day reach.
Store additive per-bucket regression accumulators (sum_x, sum_xy, sum_xx,
sum_yy) so windowed slope, r2 and standard deviation compose from the
rollup tier instead of a live raw-table scan on every warm request
(migration 0190, backfilled by the boot queue). Median and the exact
anomaly count stay on a minimal live query. Parity with the live REGR_*
path within float tolerance, well below the read rounding.
Replace the CompletionParams { systemPrompt, userPrompt } string pair with a
structured { system, messages[] } request across all five AI clients. One
refactor unlocks three things: provider prompt-caching (Anthropic cache_control
on the stable system prefix, OpenAI/Codex automatic prefix cache, with
cachedInputTokens surfaced for observability), the tool-calling wire surface,
and clean multi-turn.
Each client maps the new shape to its own wire and degrades unsupported
features silently: the local OpenAI-compatible server never receives a tools
field (most reject unknown keys), and prompt-caching is best-effort everywhere.
CompletionResult gains toolCalls, finishReason and cachedInputTokens; the tool
types and per-provider mapping ship now, the tool-use loop does not.
Vision inputs fold into the user turn's content parts via singleUserTurn, with
each provider's pre-existing block ordering preserved. The corrective-retry
paths append to the last user message rather than a flat string. The Coach
keeps assembling one user turn so its snapshot-once and grounding behaviour is
unchanged. No wire schema visible to API consumers changed.
Behaviour is unchanged across every surface; the full suite stays green.
The summaries slice (computeFromRollups) and the comprehensive aggregator
(buildFromRollups) each ran a narrow live $queryRaw over the raw
measurements partition on EVERY warm-rollup request to fold slope7/30/90
and r2_7/30/90 via REGR_SLOPE / REGR_R2 - the un-eliminated live scan on
the happy path.
Drop the six REGR_* columns from both narrow queries and compose the
windowed slope / r2 (and the population sd via composeRegression) from
the per-bucket accumulators stored in measurement_rollups. The 90-day
DAY buckets are loaded once (already loaded in comprehensive; one bounded
findMany added in the slim slice), source-collapsed to the canonical
source, then summed over the day-aligned 7/30/90-day sub-windows. A
window whose buckets lack accumulators (pre-backfill) composes to null,
the same shape the empty REGR_* FILTER returned, so a transitional read
never returns a wrong partial regression.
median (PERCENTILE_CONT) and the exact |z|>2 anomaly count stay on the
minimal live query - both are non-composable across buckets. The cold
coverage-miss path keeps the live REGR_* regression. Annotate
slope_source:"rollup" + median_source/anomaly_source:"live" so a
regression to the heavy path stays observable (no-silent-cap rule).
The comprehensive briefing's bounded feature read (extractFeatures) was
paid more than once where it should not be: the on-demand route and the
shared generator each run a downgrade ladder that re-reads with identical
arguments, and a nightly warm has no shared object across consumers in a
single tick.
Add a request/run-scoped feature cache: withFeatureCacheScope opens an
AsyncLocalStorage store, getCachedFeatures memoises the first compute per
(userId, day, includeRaw, sinceDays), gated on a cheap salient-input
fingerprint so a mid-scope ingest recomputes and a probe failure fails
safe. Outside a scope it is a pure passthrough. Wired into the
comprehensive generator, the on-demand POST handler, and the nightly
per-candidate loop + forceWarmUser. Coach keeps its own snapshot.
The slow-moving status input fingerprint covered the card's own metric
rows plus mood and height, but not the FDR discovery channels that also
feed the prompt via getRelevantCorrelationsForMetric. A correlation
newly surfacing off a behaviour channel (e.g. daylight -> next-day
weight) left the card's own rows untouched, so the input gate re-stamped
the stale assessment and the discovery never reached the prose.
computeStatusInputFingerprint gains includeCorrelationChannels: it widens
the same grouped probe by the discovery behaviour + outcome channels
(deduped, mood excluded as it is mood-entry backed), so a channel change
flips the hash. Wired into weight-status, the one caller that folds a
relations block.
Weight and BMI move on a weekly cadence, but the per-metric generators
rebuilt the full snapshot (bounded findMany + per-series rollup reads +
correlation math) every day and relied on the post-build content-hash gate
to skip only the model call. Add an input gate that runs first: a single
grouped probe over the salient inputs (per-type count + newest reading, plus
mood for weight and the profile height for BMI) fingerprints what the
snapshot would read. On a non-forced run whose fingerprint matches the cached
row, the cached assessment is re-stamped under today's key and the whole
build is skipped. A miss falls through to the normal build and the existing
post-build gate.
Consent is checked before any re-date so a revoked-consent user never has
stale text presented as current. Forced runs never gate but still record a
fresh fingerprint for the next day.
The warm narrow query and the cold heavy query each referenced the
canonical-source subquery twice — once in the window_stats CTE and once in
the outer body — so the DISTINCT-ON pick over the live 90-day rows ran twice
per rebuild. Extract canonicalMeasurementsCte (the SELECT body without the
alias wrapper), bind it once as WITH cm AS (...), and select FROM cm m from
both window_stats and the outer aggregate. Output is identical; the dominant
self-join runs once.
canonicalMeasurementsFrom now wraps the same body, byte-stable for the
single-reference call sites (pinned by a new parity test).
Bound the comprehensive briefing's feature read to a 400-day window instead of
walking the full measurement history on every generation. All-time min/max/avg
are sourced from one grouped aggregation over the whole history, so the
allTime* fields stay honest while the unbounded row materialisation is gone;
the oversize downgrade ladder remains as the safety net.
Fold illness-episode and cycle state into the briefing prompt, reusing the
server-authoritative builders the Coach already assembles. Both are
module-gated and cost nothing for users without them, so a mid-illness or
mid-cycle user finally gets context-aware prose.
Ground daily-briefing numbers against the signal features, guard Coach replies
against fabricated doses and risk scores, gate the period narrative, feed the six
status cards a precomputed signal block, add SSE cancellation, and cap the Coach
snapshot read.
BP, pulse, weight, BMI, mood and medication-compliance still asked the
model to derive the recent-vs-baseline comparison from raw buckets — the
exact arithmetic small models do unreliably, and the pattern the
base-system prompt already advertises as precomputed.
Build the SIGNAL block (current / baseline / signed delta / normal-swing
verdict) with buildMetricSignal from each card's graded series and inject
it into the snapshot; BP carries two signals, compliance one per
medication. Each card's prompt section now leads from the signal block
and is told to state, not recompute. The server-computed compliance %
is unchanged.
The raw BP pulls in the comprehensive aggregator and the bp-in-target live
fallback read every source's row for BLOOD_PRESSURE_SYS/DIA. BP is a
multi-source metric — a Withings reading mirrored into Apple Health is two
rows for one event — so each shared reading was counted twice in the
in-target denominator and twice in the recency-weighted grade. The rollup
branch of the same fast-path reads source-collapsed measurement_rollups, so a
rollup-warm account and a rollup-cold account returned different BP
percentages and grades for identical data — a web/iOS and cold/warm parity
break.
Route both raw pulls through canonicalMeasurementsFrom so the cold/live path
picks the ladder-winning source per (type, day), matching the warm/rollup
path. Per-event rows of the winning source survive the collapse, so the
downstream 5-minute pairing still sees individual readings.
One-shot prettier pass so the new format:check gate starts from a clean
baseline. Formatting only — no behaviour change. Generator-owned and
vendored artifacts stay untouched via .prettierignore.
Prove one provider call covers every present metric, absent metrics are
omitted from the prompt and never fabricated, an all-served cycle makes no
call (the per-metric hash gate still short-circuits), and the batch degrades
gracefully: an omitted metric or a provider error falls each affected card
back to its single-card path, invalid JSON retries once, and a no-provider
cycle serves each card's precomputed no-key result.
The comprehensive generator did an ad-hoc JSON.parse with no corrective
retry and failed cold to `invalid-json` on a first-pass miss, while the
strict insight wrapper's `buildRetryCorrectionMessage` sat right next
door. Export that helper and reuse it: on a parse miss, append the
correction to the user prompt and re-run the chain once before declaring
failure. Unifies the JSON-robustness story across the two paths.
The content-hash gate re-stamps the prior text whenever the snapshot is
unchanged, so the "daily" briefing read byte-stable day-over-day. Decouple
phrasing freshness from data freshness for the dailyBriefing.paragraph
alone: on a hash-unchanged hit, re-roll just the paragraph once per
calendar day at a higher, seedless temperature, keeping every structured
finding verbatim from the cached payload.
A new `insightsBriefingRerollDate` column gates it to at most one extra
call per day, and a re-roll miss still stamps the day so a failing
provider cannot be re-driven on every page-open. The hash gate stays
fully intact for the status cards (reference assessments — monotony is
fine).
The overview charted each trend but never offered a way into the metric's
detail page — the steps page in particular exists and is used, yet Insights
never linked to it. Give every Trends-row chart a routed detail target and a
discreet "view details" link below the caption, so a metric the row surfaces
(steps included, when the briefing flags it) drills into /insights/<slug>.
An active illness/condition episode annotates, it never penalises: the
measured number is untouched, only the narrative changes.
- rest-mode.ts: one server-authoritative resolver (module-gated, fail-soft)
for "is the account in Rest Mode + which episodes back it". iOS mirrors the
resolved context, never recomputes the suppression.
- health-score: /api/analytics attaches a value-free Rest Mode annotation;
computeHealthScore stays pure (score never adjusted).
- recovery-score: computeRecoveryScore carries the Rest Mode context as of the
scored day; the persisted blend is unchanged.
- coach-nudge: pause cadence-nudges during an active episode (new
skippedDuringIllness counter, gate sits before the trigger search).
- achievements: bridgeFrozenStreakGaps freezes (does not break) every
day-streak across illness days; never invents a streak, a non-illness gap
still breaks.
- coincident-deviation: reframe a fired flag as illness-explained; vital
numbers untouched. Surfaced as a neutral line on the insights card.
- coach snapshot: illness history + active illness as load-bearing context so
the coach knows about Rest Mode (no decrypted note reaches the prompt).
- FHIR: illness episodes map to Condition (generic disease root, label on
code.text, patient-reported/unconfirmed) + a bounding Encounter.
- doctor-report: module-gated illness section in the aggregator + PDF table
(retrospective, neutral palette); FHIR Condition section in the bundle.
i18n x6 for the report + reframe copy. Tests: score-annotation-not-
penalisation, streak-freeze, coach-nudge pause, FHIR Condition/Encounter
mapping, doctor-report inclusion, Rest Mode resolver. typecheck/lint/test
green, openapi in sync, knip clean.