Brings in the jobs, stored-text and consent package and the extraction
routes. Conflicts resolved:
- The digest keeps its capability-driven reaction line and check-in,
now through the shared `aiCapabilityForRecord`; the local copy of it
is removed.
- The route inventories classify the extraction routes (documents,
labs OCR, medication text, fenced chat and attachments) as actions;
a capability call counts as the gate for the module inventory.
- With every caller moved, `requireAssistantSurface` and
`AssistantDisabledError` are deleted. The `assistant.disabled.*`
codes stay on the capability refusal, and the guard now asserts the
retired gate is gone.
- `aiCapabilityToServe` answers whether stored model text may be shown
from the record's own state, apart from who is reading.
Refs #975
Data never depends on AI. The Insights data reads no longer ask an AI
switch or the `insights` module (now only the AI analysis opt-out): ECG
list, detail and upload, rhythm events, derived scores, rule cards,
correlations and patterns, the baseline strip, health status, intraday
pulse, and the Today digest with its dismiss. Breathing screening moves
to the sleep module and lab changes to the labs module. Stored Coach
facts, conversations, message ratings and the seen stamp stay readable
and erasable while the Coach is unavailable. Cards now say
`provider: "rules"`.
Reads that mix data with model text answer 200, null the model text
and publish an `ai` state from the capability resolver, without warming
anything: comprehensive (`ai.briefing`, `ai.statusText`, `hasProvider`
from the presence probe), the derived assessment override, the period
narrative, nudge status, the seeded opener, about-me questions, the
workout paragraph, the pregenerate warm (`queued: false`), the Today
digest (lead, reaction line, check-in) and the dashboard briefing,
which is now applied per read after the snapshot cache. Hiding the
Coach no longer hides the briefing.
`insights/generate` GET and POST ask the `briefing` capability and
`insights/chat` POST the `coach` capability, with the typed refusal
envelope; a missing provider keeps the chat's `coach.provider.none`
frame and adds `reason`. The /coach page, the MCP ECG and intraday
tools and `aiAvailable` on the provider route follow the same answer.
An inventory of AI and data routes replaces the Coach gate inventory:
every route that asks a capability names it, and no data route asks.
Refs #975
Every status note reader and writer moves to InsightStatusCache: the
generators, the unchanged-data gates, the stale-while-revalidate read,
the ingest debounce, the previous-note prompt block and the
medication-compliance card with its per-medication lines. A stall now
opens a negative-cache window next to the note instead of a stub row
that shadowed it.
Stored model text is never served while its capability is unavailable,
whatever the reason: the status readers and gates check statusText, the
period narrative hides a model-written row while periodNarrative is
unavailable (the deterministic narrative is data and always shown), and
the daily digest drops reaction lines while reactionLines is
unavailable. A read-only miss now reports why (`unavailable` with the
capability's reason) and keeps hasProvider meaning provider presence, so
a withdrawn consent no longer reads as "no provider".
runStatusCompletion takes the capability as a required argument and
re-checks it before the provider chain is resolved, so a job queued
before a switch flipped still stops at the wire. The comprehensive
briefing re-checks briefing the same way. hasUsableStatusProvider is the
one presence probe.
Refs #975
A single account syncing heart rate from a watch took the worker down
within half an hour. The status cards' graded series read the last 91
days of raw rows, bounded in time but not in rows, so a stream sampled
every minute or faster materialised six or seven figures of objects on
every refresh and the read ran into the statement timeout.
Add readDayAggregates, which folds one type into per-day sum, count, min
and max in Postgres (optionally split into age segments and filtered to
the metric's plausibility domain), and move the readers that folded raw
rows into days in memory onto it: the graded series (recent, weekly and
the cold-tier fallback, for every type), the vitals day-mean fallback
behind the personal band, the tiered context's recent days and the plan
review. Recent, weekly and monthly buckets are identical to the raw
fold; the cold-tier yearly slope now runs over day means.
On 91 days of per-minute pulse the graded series now allocates 1.6 MB
where it allocated 62 MB, while the raw read alone holds 22 MB.
A structural guard freezes the remaining untaken measurement reads in
the worker and insight directories: each must name a sparse literal
type or carry a listed reason.
Refs #1023
Six suites pinned the old rule as the rule. Each inversion, and why it is
one:
`breadth.test.ts` — the case table asserted a refusal reason per set; it
asserts a tier and a `physiological` flag now. Every row in it except the
empty set used to be a refusal, and each is a number somebody gets to see.
Adds the tier boundaries (one pillar, two areas, physiological-absent), a
case proving the same pillars produce the same number at `partial` and at
`full`, and a block whose only job is the counter-case: the empty verdict
still carries a reason and no tier, and a composite whose selected pillars
all came back short still refuses with `no_usable_data`. A rule that has
stopped refusing anything is a deleted rule, not a graded one.
`composite.test.ts` — "requires three domains and one measured
physiological domain" asserted the refusal that no longer happens; it now
asserts the score and the basis block on the same fixture. The coverage
case keeps its fixture and its arithmetic and flips its outcome: two of
three used to be a refusal and is a scored account with a real coverage
fraction. Adds the one-area case and the zero-pillar counter-case, and the
`SCORE_VERSION` floor moves 2 -> 3 because widening who gets a score is
exactly the kind of change that must not ship without a version bump.
`record.test.ts` — "records nothing when the composite did not resolve"
used a two-pillar fixture to prove a below-the-floor day stored nothing.
That day has a number now and the table has to keep it, or an account that
starts narrow and widens later has a hole where its early days were. The
assertion is now that a one-pillar day builds a draft AND reaches the
database; the absence case survives on the fixture that genuinely produces
no score.
`composition-source.test.ts` — three recipes asserted as refused at read
time. Two of them score. What the block proves is unchanged — the reader
publishes the shared rule's verdict on the reader's own resolved set, so a
second copy of the rule would still surface here — but the agreement is
over a tier rather than over a refusal.
`route.test.ts` (score config) — the two too-narrow refusals become
acceptances, because a write that refuses what the read is willing to serve
is the two layers disagreeing. The empty selection keeps its 422 and gains
the assertions the old cases carried: errorCode, reason, and the sentence.
The errorCode driver loses the two selections that no longer 422.
`score-refusal-consumer-guard.test.ts` — its non-zero control anchored on
`three_domains_required`; it anchors on `no_pillars_selected`.
New: `health-score-basis-additive-contract.test.ts` pins that `scoreBasis`
is published, is optional on all three carriers, and points at the one
shared component — a required field on a cached surface would invalidate
every cached payload with nothing failing anywhere. It also pins that the
walk does not confuse the composite's basis with the older per-pillar
`scoreBasis` that blood pressure uses for its axis, since they share a key.
Fixtures: the notice-key assertions derive the method half from
`SCORE_VERSION` rather than restating 3. Three fixtures that named
`three_domains_required` now name `no_usable_data`, a reason the server can
still emit. The settings e2e drove its refusal through a two-pillar
selection that now succeeds; it deselects every pillar instead.
`GET /api/insights/derived` accepts `windowDays`, bounded to 1..90, and
threads it to the dispatcher. Omitting it changes nothing: every engine
keeps its own default, so a caller that asks for nothing reads exactly
what it read before.
Ninety is where the tier this route promises runs out. The rollup router
opens its WEEK floor at 91 days, and the baseline engines cannot compose
a spread from WEEK buckets, so a 91-day request falls through to a raw
`measurement.findMany` with no row cap — for a densely sampled type that
is a full history scan, and the analytics-read budget allows 120 of them
a minute per account. The trailing `series` is capped at 30 points
regardless, so past the ceiling a wider window would only broaden the
mean behind the value. Out of range is a 422 rather than a clamp.
An unhonoured window is visible rather than silent. `provenance.windowDays`
is the window the engine actually used and `coverage.historyDays` the days
that actually backed it, so a three-week record answering a thirty-day
request reports both numbers instead of implying coverage it does not
have. `HEALTH_SCORE` composes fixed per-pillar windows and reports the
widest; a new suite freezes that it is the only metric that does, so an
arm added later cannot quietly drop the parameter.
Recovery keeps its canonical resolution under the wider window. A worn
band stamps the wake morning and the computed proxy the night before, and
only `resolveCanonicalRecovery` pairs them; a test seeds forty such
nights, asks for sixty days, and holds the answer to forty nights with a
flat trend — a bypass leaves eighty rows and a false climb.
Contract: model `WellnessScoreValue` field for field and publish it. The
envelope's `value` has to stay an open record because one route serves
eighteen differently-shaped metrics, so nothing can `$ref` the shape and
it went out undocumented — `series`, `daysInWindow` and `asOf` were on
the wire with no way to find them short of inspecting a live response. It
is registered in the forced-components slot instead, held against the
runtime interface by a test, and the fields it does not cover are named
in the schema comment so the remaining gap is known rather than invisible.
Eighteen modules carried a convenience re-export of a symbol defined
elsewhere. In each case the callers the comment describes now import the
concrete module directly, so the line had no importer left. Where the
whole re-export block went, the comment explaining it went with it —
doctor-report-pdf-core, trend-card and medication-extract-prompt each
claimed to be a single import surface that nothing was using.
Definitions are untouched; imports that existed only to feed a removed
re-export go too.
The barrel mirrored every export under src/lib/insights/derived. Of the
124 lines, 101 had no importer: consumers and per-metric tests reach for
the concrete module (./sleep-score, ./trajectory, …) directly. Keep the
cross-cutting surface — registry, dispatcher, baseline loader, and the
value shapes outside consumers read — and say in the header that the
barrel is not a mirror, so the next addition needs a consumer first.
Definitions are untouched; only the re-export lines go.
Four surfaces assembled the correlation-discovery matrix and three carried a
different channel set. The Coach `get_correlations` tool had neither the
environmental-exposure channels nor the custom-metric ones, so asking it
whether air pressure relates to your sleep met a matrix the pair had never
been in. Its own file header said the opposite - "the SAME full-matrix scan
the route runs" - and had said it since the weather channels arrived in
v1.25. The period narrative was missing those two families and the
compliance / symptom pair on top.
`src/lib/insights/discovery-matrix.ts` is now the one place a matrix is
built. v1.30.3 hoisted the fetch discipline into a shared module for exactly
this reason and left the assembly duplicated behind; this finishes it. The
route, the per-metric card, the Coach tool and the period narrative all call
`assembleDiscoveryMatrix` and get the same families. What still differs is
declared as an option with its reason at the declaration: the measurement
read mode (a read-cost choice, left per surface), the extra metric types the
narrative's delta beat needs, and the RATED mood factors.
Mood factors stay on the narrative alone. That capture kind is frozen, the
two surfaces that persist a discovered pair write its channel key into a
plaintext column, and a custom factor's key is an opaque id - so admitting
them elsewhere is a decision about what to ask, not a parity fix.
Restore the per-metric filter on the assessment card's relations. It was
written in place of the pattern-dismissal filter rather than chained with it,
so a weight card's prompt had been receiving every surviving pair in the
record while the function name, the docstring and the early-return guard all
still said one metric.
`discovery-matrix-guard.test.ts` freezes who may fetch a channel, who may
construct one, and who may scan. Each matcher asserts a non-zero match count,
so a matcher that has stopped matching fails rather than agreeing with the
allowlist.
The statistics are untouched - same Pearson, same exact p-value, same
Benjamini-Hochberg, same floors. The Coach's family is larger now, which is
the point: it is corrected over the same family the insights page is.
The hero line said a pulse was well above its 30-day average today. Nothing
had measured a pulse for five days. The day-signals card flagged the same
reading, and the baseline-drift card said the value was above the usual range,
present tense, on a day that held no reading at all.
One class, and it sits in the data preparation rather than in any of the
sentences. Each surface was handed "the freshest stored value" with no notion
of when it was taken, so each of them assumed now. The age was reachable — the
aggregates carry `newestDaysAgo` inside their coverage object — but it read as
a statistics footnote rather than as the fact that governs the tense of every
sentence about the metric, and none of the three consulted it.
A reading is material for a claim about today when it comes from today or from
yesterday. One day rather than zero: a vital taken at 23:40 and read at 00:10
is the same reading it was half an hour earlier. Two is not, because by then a
whole day has passed with nothing in it and the sentence would be describing a
gap.
The rule now lives beside the data. The vital deviations carry the age of the
reading they were computed from, and the two deterministic consumers apply it:
the day-signals flag counts only current vitals toward its count, and the
baseline-drift card surfaces only current deviations. Stale vitals stay in the
list with their age, so the anatomy view still shows them and nothing silently
disappears; the dated level shifts were never today claims and are untouched.
For the narrated surfaces the same fact is stamped onto every metric block of
the Coach snapshot before anything reads it, so the age travels with the
numbers into the hero, the briefing, the Coach reply and the retrieval tools
instead of each of them guessing. A block narrated off a stale series also
lands in the wide event, which is where it should have been visible all along.
The baseline-drift card reported a pulse in the hundreds of millions against a
usual range in the tens of thousands. Neither figure is a heart rate, and both
came from the same place.
The application declares a plausibility domain per metric, and every
interactive, import, MCP and Telegram write validates against it. The
derivation layer did not ask. So a single stored value outside that domain — a
provider unit-decode slip, or a row from a writer that never had the gate — was
folded into the day mean, carried by the median into the band, and then held
against itself as "currently". The two numbers in the sentence were wrong by
different amounts, which is why the line read as nonsense rather than as an
exaggeration.
Both readers now refuse a value the application has already declared
impossible: the per-day means behind the band, and the latest-day mean the
deviation reads. A day left with no plausible reading contributes nothing
rather than a fabricated point, and the vital drops out of the comparison — the
coverage floor already knows how to report an absent day. The rollup branch
applies the same rule to a bucket mean, since the rollup writer averages
whatever is stored. Everything downstream of `readDayMeanSeries` inherits it,
which is every consumer of the usual range: the band strip, the drift card, the
changepoint detector, readiness, trajectory, the coach read.
The card also printed raw doubles. Each figure now renders at the metric's own
decimal precision through the shared formatter, so a mean reads as a number
rather than as a float and follows the reader's number convention.
Left open, and recorded for a separate pass: the provider sync writers do not
enforce the domain on the way in, so the impossible rows keep landing.
It could never score. The schema records VO2max but cannot tell a
measured test apart from a device estimate, so every fitness row reached
the scorer unproven and was refused - the pillar has never produced a
value on any account. Listing it on the score settings page as a thing
you can choose, with a line admitting it does nothing, was chrome over a
switch that changed no number.
So it leaves the catalogue: no pillar id, no domain, no scorer, no row,
no wire field. A stored selection that still names it reads back fine -
the resolver has always filtered stored ids against the catalogue and
drops what it no longer knows, so nobody's saved recipe throws or is
discarded over it.
That also fixes the page claiming unsaved changes forever. The save
stripped the fitness pillar out of the selection on its way to the
server, so the answer that came back could never match the form that
sent it, and 'All pillars' left the save button lit no matter how often
you pressed it.
Two branches met here. One made `configured` a required field so a caller
cannot stay silent and publish "not authored" for an account that chose its
own composition. The other wrote these cases before that existed, so they
compiled against the old shape and stopped compiling against the new one.
Filling the field in to satisfy the compiler would have thrown away the point
of making it required, so each case now states what it actually is: the two
with a hand-picked selection are authored, and the one whose own comment says
the account counts all eight is the default.
Two sentences about the Health Score stopped being true the moment
someone could choose which pillars count toward it.
The one people read said the score averaged "every pillar that has
enough recent data". For an account that took a pillar out, that
describes ground the number does not cover, and it reads as a
reassurance rather than a description. It now says the average is over
the pillars that count, that a pillar without recent data is still left
out rather than zeroed, and that which pillars count is the reader's own
choice, so the combined number is not itself a clinical standard. All
six locales.
The one nobody reads named the WHO HEARTS technical package flat, as
though a standards body had signed off on whatever selection the account
holds. HEARTS names the risk factors the pillars are drawn from; it
prescribes no average over them. The entry now says what it is cited
for. While checking where that citation surfaces it turned out it
surfaces nowhere: ProvenanceExplainer takes the prop and renders only
the method caption, which v1.22 did on purpose when the info popover
went away. That is written down in the file now, because the map's own
header implies otherwise and the next person would trust it.
The registry entry for HEALTH_SCORE lists all eight pillars with a
minimum of three, which reads like the recipe and like a threshold. It
is neither. The published coverage and confidence are built in
computeComposite over the resolved composition, so a person counting
four pillars is not measured against a denominator of eight, and the
real floor is the breadth rule, which counts distinct domains rather
than inputs. Both facts are now stated at the entry instead of being
inferable only by following the call chain.
Tests: the published denominator is never the eight-pillar catalogue; a
pillar somebody took out of their score is never listed back as missing
coverage; a pillar they kept and have no data for still is; the registry
list stays equal to the score catalogue; the choice sentence is present
in all six locales.
Three things are held down here. The route hands the reader's language to
the strip builder, for a cookie and for a stored preference. The pattern
sentence comes back in German for a German reader, asserted word for
word, through the real chain rather than the engine on its own — the
engine could always write German, it was simply never asked, so an
engine-only test would have stayed green the whole time it was broken.
And a cached strip stays with the language it was written in.
The guard reads the declarations rather than grepping them, so renaming
the argument or moving the fallback into a variable does not slip past
it. Its counterpart runs the same detector against those disguises and
insists each one is caught, because a check that cannot fail reads like
proof and is not.
On a German metric page the strip printed its own summary in German and
the pattern line under it in English. The pattern line is a finished
sentence the server writes, and the route never told the server who was
reading, so it wrote English.
The route now resolves the reader's language the same way the
correlations and analytics routes do and passes it down. The language is
a required argument the whole way through — it used to be optional with
an English fallback, which is why a caller could stay silent and still
get a sentence back. The cycle page's lagged rows had the same gap and
are fixed with it.
The strip's browser cache is keyed by language too, so switching
language no longer re-uses the sentence written for the previous one.
Two parallel lines of work reached the same conclusion independently: a
baseline band over a quantity that cannot go negative must not report a lower
edge below zero. One of them answered it locally with a `Math.max(0, …)` at the
call site; the other gave every metric's numeric domain a single home and made
`buildBaselineBand` take the metric so the floor comes from the declaration.
Keep the second and drop the first. The required parameter is what surfaced
this at all: the new call site could not compile without naming its metric,
which is the whole reason it was made required rather than defaulted.
The rail gains a same_time_baseline kind and a server builder, which is the
growth path that type documents for itself. It speaks only when today is
actually outside the typical band: a card that reports doing exactly what you
usually do teaches people to stop reading the rail. Dismissing it is keyed by
day and metric, not by the hour, so it stays dismissed instead of coming back
every sixty minutes.
The Insights grid gains a section of four tiles, one per cumulative metric,
each honestly quiet until the history accrues.
The two-trajectory chart it needs did not exist, so DeltaSparkline gains a
second mode rather than a second chart family: the comparison curve rides the
same container, the same fixed height and the same shared y-domain as a dashed
muted line behind the live one, which is the only way the two can be read
against each other.
Six locales. The wipe and backup plans learn about the new table: the profile
cannot be rebuilt once the samples are gone, so it is carried, not derived.
Compare today's running total at the last completed local hour against this
person's own typical total at that same hour, over a trailing four weeks of
stored intraday profiles. Same estimator as the vitals baseline — median for
the centre, median plus or minus k times MAD for the band — so a reader who
understands one understands the other.
It refuses to speak below fourteen usable days and says so through the
existing insufficient arm rather than a band built on three days. It ships no
projected day total: extrapolating a partial day is a guess, and this exists
to replace guesses.
Steps first; active energy, distance and flights ride the same engine.
Three defects on one card of the step sub-page, all of them a surface
answering a question that belongs to the metric.
"Your usual range is -5,595.6-13,387.6 steps", under a chart whose own
y-axis refuses to draw a negative step. Same app, same question, two
answers: the axis clamped and the sentence beneath it did not. Both now
read the same fact. `VALUE_RANGES` already declares every metric's
plausibility floor for ingest; `value-domain.ts` reads it and answers
"can this metric be negative" for the padded y-domain and for the median
+/- k.MAD band alike. The band's lower edge floors at zero for a
non-negative metric; `spread` stays the unclamped dispersion so a
deviation-in-sigma calculation is unaffected. `buildBaselineBand` now
takes the metric it is describing as a required argument, so a new caller
cannot quietly reintroduce a negative edge. Two types carried no
plausibility range at all, which let any number through ingest and read
as "unknown" on the negativity question: walking steadiness gets the same
0-100 percent band as its two gait siblings, the loud-listening event a
floor of 1 with a generous ceiling.
"13,387.6 steps" also said steps to a reader of German. Five sub-page
units are English words, not symbols - steps, flights, falls, years, and
a "count" that was a poor label in any language. They now travel as i18n
keys through a new `unitKey` on the metric-page scaffold and resolve in
all six locales. The thirteen real symbols (bpm, mmHg, %, m/s, kg/m2,
...) stay literals; translating a symbol would be the opposite mistake.
And the Min read "104.0 steps". Precision was a per-page prop defaulting
to one decimal, so every page had to remember that its metric is a count
- and the step page did not. It follows the metric now: a discrete metric
(tallies, category events, closed integer instrument scores, ordinal
levels) resolves zero decimals wherever it is rendered, and a page only
passes the prop to override that.
The profile validator has accepted MALE, FEMALE and OTHER for a long
time, but the published contract documented two, and a client written
against that contract had no way to know the third existed. The profile
PATCH is one write, so a rejected gender took every sibling field with
it - a time-format change lost to a field the person never touched.
Gender now clears on an empty string, the same contract every other
profile field documents, and an unsupported value is refused with a
message that names the field and its accepted values instead of the
validator's own prose. Onboarding validated against a narrower enum
than the profile schema and 422'd the whole submission; its form could
not record the third value at all.
The rest is the same defect in other clothes. The Strain model scored
an unanswered or OTHER account on the male Banister coefficients; it
now uses the midpoint of both published models, matching every other
sex-split formula here. The dashboard snapshot emitted null for an
account that answered OTHER, which is indistinguishable from no answer.
Three casts asserted a two-value type over a three-value column. All of
them now carry the stored value and narrow once, at the boundary of a
reference table that genuinely has no third row, through one named
helper in src/lib/profile/sex.ts.
Refs #645
A truncated or malformed { "summary": "..." } envelope fell through the
status-card parser and rendered raw — braces, the summary property name,
quotes, and literal \n — in the Assessment card (resting pulse and the
other per-metric cards). parseSummaryFromContent returned the raw content
on any JSON parse failure, and a truncated envelope with no closing brace
also fell into that path, so partial structured output reached the reader.
Split the read into extractAssessmentSummary, which classifies a completion
as a parsed summary, genuine prose, or an unparseable structured envelope.
A payload that opened like a JSON object but failed to parse (or parsed
without a usable summary) resolves to the controlled fallback rather than
raw text; plain prose that merely contains a brace is still preserved.
finalizeStatusSummary withholds an unparseable envelope so every status
card serves its deterministic stub, and the two direct callers
(medication compliance, derived-score assessment) get the same guard.
Refs #608
Three surfaces where the words no longer matched the code, plus the missing
web control for a preference the server already honours.
Delete confirmations. Four dialogs promised permanence on surfaces that
render an Undo: the measurements and mood bulk bodies, the lab-result body,
and the illness-episode body (which said "cannot be undone" sixty lines
below the code that fires the Undo toast). All four now use the same
sentence the single-row measurement and mood dialogs already used. A sweep
of every other confirmation in the tree found the rest accurate — the
biomarker cascade, the mood-tag purge, and the account purge keep their
warning because those deletes really are unrecoverable.
Sleep debt. v1.19.0 replaced the summed shortfall with a running balance
that credits catch-up sleep; the labels still described the old sum, so the
word contradicted the number for anyone who slept in after a short night.
Corrected in all six locales, plus the places the old semantics had
propagated: the Coach system prompt, the OpenAPI field descriptions the
native client reads, and four module docblocks.
Glucose reference band. `hasDiabetes` selects the tighter reference band and
grounds the Coach, but no web surface set it — a web-only account was pinned
to the non-diabetic scale with no way out. The control goes on Targets,
above the per-metric editor, because it answers the same question that page
answers and the two are ordered: it picks the default band, an override
below beats it. The copy says what it is — a reference band, not a
diagnosis, never inferred from a reading, no clinical action taken on it.
The passkey list was reported as always reading "never used". It does not
reproduce: the column is selected by the list route and stamped on every
verified assertion, both since v1.23.0. Pinned with tests on both halves so
the contract cannot quietly regress.
The Coach SNAPSHOT was spliced into the prompt bare. Its JSON leaves are not
all server-computed: lab analyte, panel and unit names are transcribed by a
model out of an uploaded PDF and stored verbatim as the biomarker name, so a
hostile document chooses those strings. The about-me block has been fenced
since v1.16.1; extend the same pattern rather than adding per-field escapes.
- Move the fence markers and the wrapping primitive into a shared data-fence
module. Content is scrubbed against every known marker, not just its own
pair, so text in one block cannot forge another block's boundary.
- Fence the SNAPSHOT with an explicit data/instruction frame.
- Fence the OCR text handed to the document extractor; the previous
'OCR TEXT:' label was a label, not a boundary.
- Sanitise analyte, panel and unit at the labs source, which feeds both the
snapshot prompt and the labs_read tool result, and the medication label in
the adherence storyline.
- Capture a ---REMEMBER--- sentinel as proposed rather than active. It was
the only model-driven write with no confirm step, and the reminder recall
block fed it back into every later turn. Proposed reminders are already
excluded from that block and already carry a confirm control.
getBaseSystemPrompt appended the directive, then each metric module
appended its own section after it, so the directive was no longer the
last instruction the model reads - the one property that makes it
authoritative. The base now exposes its body, and every composing module
wraps the finished prompt so the directive ends it.
Also drops a duplicate import that survived the merge of the two prompt
branches.
Holds every sibling prompt module to one invariant: strip the directive
and the interpolated language name out of a French, Spanish, Italian or
Polish prompt and what remains is the English prompt, byte for byte. A
German instruction body leaking back into a non-German prompt, an
English body drifting away from what the four locales receive, and a
module appending a second directive on top of the one the base prompt
already carries all fail here.
Also drops the now-unused narrow locale alias from the two modules whose
prompt builders take the full locale.
The per-metric assessment pipeline typed every locale as `de | en` and
narrowed on the way in, so a French, Spanish, Italian or Polish account
never reached a prompt with its own locale — the output-language directive
could not fire and the reader got English, or German where the binary
defaulted that way.
Widen `SupportedLocale` to the six locales the UI ships and replace the
narrowing binaries with one validating `normalizeLocale` that passes a
recognised locale through unchanged and defaults an unknown value to
English. The status-generate payload, status batch, status cache,
comprehensive generation, the pre-generate warm passes and the forced-warm
handlers all carry the full locale now.
Fix the collapse sites that discarded it: the warm enqueue on the
comprehensive route and the pregenerate route, the nightly batch cron, and
the forced-warm job handler — the last two defaulted to German outright.
The deterministic derived-score templates and the previous-context block
ship de/en bodies only, so they route through `instructionLocale` (German
for German readers, English otherwise) while the prompt names the reader's
own language.
The derived-score archetype and the Coach preference overrides branched
on the raw locale, so fr/es/it/pl composed German instruction text. Both
now route through `instructionLocale`. The score archetype rides on
`getBaseSystemPrompt` and therefore appends no directive of its own —
the base prompt already carries it.
The biomarker assessment is the one prompt in the family that does not
compose the base scaffold, so it appends the reader's directive itself;
the append collapses into the shared path once that prompt moves onto
the base scaffold.
The two prompt builders in each of those modules now take the full
`Locale` rather than the narrowed de/en alias, so the routing is right
the moment the pipeline stops collapsing the four locales on the way in.
Also targets the output-language contract test's regex at the compile
target instead of the dotAll flag, which does not compile.
German and English prompts are unchanged, byte for byte.
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 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 recovery detail page rendered only the ring — the one wellness
score without a composition view, although the COMPUTED score IS the
readiness blend persisted nightly. The wellness-score read now attaches
the blend's per-factor sub-scores (RHR, HRV, sleep, respiratory rate,
mood stability — same engine, same weights, resolved server-side on the
same request) when the canonical latest row is the COMPUTED proxy, and
the anatomy view renders them through the identical ranked contributor
rows the readiness and sleep-score composites use, reusing their
labels. A WHOOP-native percentage is not our blend, so it keeps the
row-less presentation; a gated blend simply omits the breakdown. The
new value field is optional and additive — existing clients decode
unchanged.
The Coach adherence storyline derived its rate from the raw coverage
rollup, whose denominator counts logged slots rather than scheduled
doses, so a user who logged only taken doses read ~100% and the dip gate
suppressed a real decline. Extract the dashboard tile's schedule-anchored,
cadence-aware compliance into one shared engine and route both surfaces
through it, so Coach and the dashboard report the same number.
Grip strength and waist circumference resolved against a single sex-aware
bracket for every adult age. Replace each with age x sex norm bands:
- Grip strength: age x sex bands from Dodds et al. 2014 (PLOS ONE
9(12):e113637) British normative data — band low is the 10th centile
floored at the EWGSOP2 probable-sarcopenia cut-off (men 27 kg, women
16 kg), band high is the 50th-centile median. Strength peaks in the 30s
and declines from midlife, so the bands step down with age.
- Waist circumference: WHO increased-risk threshold (men 94 cm, women
80 cm) held flat through midlife and raised for older adults toward the
WHO substantially-increased-risk line, since the WHO cut-points derive
from cohorts aged 20-74. The standard threshold is never lowered.
The norms resolver gains an age-independent clinical cut-off row per sex,
used only as the no-age fallback so a profile with a known sex but no date
of birth keeps the sex cut-off rather than the coarse registry anchor. The
signal registry structure is unchanged — only the resolver tables move.
Grip strength, pain (0–10 NRS), waist circumference, and waist-to-height
existed in the measurement enum, signal registry, and FHIR export but had
no web entry, no detail page, single non-sex-aware bands, and a split-brain
MCP exposure. This closes those gaps.
Web capture: the four signals join the manual measurement form, so a
web-only self-hoster can log them (the iOS client and the measurements API
already could).
Detail pages: flip detailPage on for the four signals and mount each on the
shared HealthKit metric template (chart, stat strip, Coach-read strip,
assessment card) via routed sub-pages and tab-strip pills, the same detail
spine every other metric carries.
Sex-aware bands: grip strength (EWGSOP2 men 27 / women 16 kg) and waist
(WHO men 94 / women 80 cm) now classify by the profile sex through the
age/sex norm resolver the assessment already threads; the resolver also
returns a sex-specific, age-independent band when no date of birth is set.
Fix the waist-to-height boundary so the NICE >= 0.5 rule is correct (the
last in-range value is 0.49).
MCP single source of truth: decouple the registry mcp facet from the Coach
snapshot — a signal can be MCP-readable without being on the Coach surface.
Mark the four physical signals mcp:true, derive the MCP rich-reads clinical
set from the registry flag instead of a duplicate allowlist, and relax the
invariant to coachSnapshot implies mcp (not the reverse). PHQ-9 / GAD-7 and
the environmental signals stay mcp:false and unreachable. compare_metric and
detect_changepoints now advertise clinical-signal support to match
get_metric_baseline.
Generalise sleep debt onto the existing per-metric source-priority picker
(a new sleepDebt ladder, native-above-computed, default WHOOP > Oura > Polar >
computed) instead of assuming one provider. The rhythm read resolves the active
source off the ladder and carries it on the DTO; when the active source is our
own COMPUTED engine — every user today, since no provider ships a native
sleep-debt balance — the Sleep page explains what the figure means and that it
differs from a wearable's native number. The computed model itself is unchanged
and correct (a short rolling balance of need minus sleep, surplus-credited);
only stale comments that still referenced the old 14-night window are corrected.
Add the medication-class to target-vital map and the adherence-to-vital
storyline so the Coach can surface, association-only, when an adherence dip
lines up with a drift in the vital that medication targets. Never causal,
never a dose-change suggestion; dose questions defer to the prescriber.
Add an in-repo CUSUM / binary-segmentation changepoint detector over DAY
rollups with a high firing bar (persistence plus within-segment-spread
magnitude) so the Coach can name a dated, sustained level shift instead of a
vague "lately", and stays silent when no break clears the bar.
Surface which source recovery is read from when two sources materially
diverge, with the honest reason, instead of silently averaging.
Lay the n-of-1 experiment substrate: a nullable encrypted outcome column on
coach_plans (migration 0197), the review_due / reviewed lifecycle statuses
wired into the encrypted-column registry and rotation script, and a daily
worker that reads the experiment result back in the user's own before/after
numbers — association-only, honest-null, no cheerlead on an adverse trend,
and routing a worsened vital to the clinician. The user-visible read-back
stays behind COACH_EXPERIMENT_VERDICT until its review cases clear.
Extend the outbound dose screen to catch experiment-shaped dose changes
(halve / skip / stop a medication to test it). Add evaluation cases and unit
tests for each new surface.
Replace the fixed three-beat assessment skeleton with a menu of moves the
model orders freely, and reframe the daily briefing from per-signal
enumeration to a verdict-first read that weaves the few salient signals into
one associative story. Score cards now name both the helped and the hurt
contributors, translate the band into a forward read for the day, and close
on one grounded nudge; the deterministic fallback gains the same band-meaning
sentence so provider-less and demo accounts read as well.
Add a hash-seeded opener-archetype rotation (deterministic, testable) so
consecutive cards and days no longer open the same way, a day-rotated sampling
seed for the period narrative in place of the fixed reference seed, and a
shared paragraph formatting contract. Add a score-number grounding gate and
extend the briefing grounding allow-set to the glucose, labs, preventive-care
and workout aggregate blocks so real figures can be cited without opening the
gate. Gate the daily score warm on an input fingerprint so a quiet day skips
the model call.
The A1–A3 source files carried v1.22.0 docstrings from before the work was
re-cut as the v1.21.2 point release. Comment-only sweep so blame and the
in-file version tags read consistently with the shipped version.
The builder is server-only by construction — only the metric-page route
imports it and it reads Prisma — and no other module in the tree depends on
the `server-only` package, so the import was both redundant and an undeclared
dependency. Removing it keeps the dead-code gate clean without weakening the
boundary.
Render a compact two-line "Coach read" above each metric sub-page chart:
an own-baseline line ("Your usual range is X–Y; today's Z sits within /
above / below") and one top lagged-association line from discovered
correlations, framed descriptively. It makes a metric read seen-in-context
rather than isolated.
The strip is server-authoritative: a new GET /api/insights/coach-read
resolves the band via the median ± k·MAD baseline engine (with its 7-day
history floor — below it the strip says "still learning your range" rather
than inventing a range) and the strongest on-metric driver from the
existing FDR-controlled, effect-size-floored correlation discovery (no
lowered floor; the line is omitted when nothing clears it). The client
component only renders the resolved DTO, so web and iOS read identical
numbers. DTO shapes and the pure selection logic live in a client-safe
sibling shared by the component and the unit test.
Wired through the HealthKit metric scaffold (every generic metric page) and
the bespoke weight, blood-pressure, and pulse pages.
The coincident-deviation read grouped the latest day with a UTC date
slice while the sibling readiness read already used the tz-aware day key.
For a user east or west of UTC, a late-evening or early-morning reading
landed on the wrong calendar day, so a fired flag could compare a vital
from the wrong day against its band and narrate '2 or more vitals out of
band today' on the wrong day.
Thread the user's timezone into the latest-day read and mint the day key
with userDayKey, matching readiness. The Coach derived-snapshot and the
correlations reader pass the real account timezone through. Adds a
regression covering a UTC+2 user whose late-night reading rolls to the
next local day.
The per-score deterministic text named the score, its standing, and the
weakest contributor, then stopped at the diagnosis. When the band is not
green and the weakest driver is behaviourally addressable (sleep, mood,
consistency, timing), append a single grounded pointer drawn from that same
contributor. Physiology-only drivers add nothing, so the text affirms and
watches rather than manufacturing a step.
The comment claimed the average-per-night, sleep-debt, and chronotype
cards share one window and cannot disagree. They each read their own
sub-window — the average over the full scorable span, sleep-debt over
its trailing 14 nights, chronotype over CHRONOTYPE_WINDOW_NIGHTS — so
the figures are each internally honest rather than identical, and every
card's caption discloses its own nightsCounted. State that plainly; no
computation changes.
Marc-André Bombeck