The schemas stay: the insight result still parses recommendations
through them. Only the exported aliases went unused once the card that
consumed them was removed, and the dead-code gate says so.
The knip blind spot (ignoreExportsUsedInFile) left eight symbols carrying
an export nothing outside their file consumes — the modifier goes, the
symbols stay. The score series module goes whole: its only importer was
its own guard test, whose composite- and config-guarding suites survive
in place.
DocumentContentIndex.tokenizerVersion gains the consumer that was the
point of storing it: the content-index job now re-tokenises rows whose
version trails CONTENT_TOKENIZER_VERSION, from the decrypted index text
along the same path the rotation script uses, keyset-paginated and
fault-isolated per row — a future tokenizer bump migrates the index
instead of silently splitting it. ImportJob.uploadSha256 turned out to
already have its dedupe consumer (both kick-off routes short-circuit on
same-bytes non-failed jobs); its comment now names that instead of
pretending to be write-only. The remaining write-only columns carry
their honest annotations in the shape the audit sweep parses.
- The record-settings contract, slug-list, and section-frame tests
follow the slugs that left the registry (layout children resolve
their headings from the layout namespace, like production).
- The orphaned settings.sections.<module>.title/description keys leave
all six locales; the reverse-coverage guard flagged them the moment
their nav entries stopped existing.
- The operator-cap ledger read fails open on a read error — the
reservation layer still meters against the same ledger, and a
transient blip must not take the fallback chain down.
- The reaper queue joins the subsystem surface; its healed count and
the sweep's nag_dismissed join the job-fact vocabulary.
- The intake-event contract fixture carries the full row the resource
now declares; the workouts empty-state test asserts the
source-neutral cue; the persister poll gates on rendered content
first.
- The provider-chain walker now checks the day's recorded spend against
OPERATOR_COST_CAP before invoking an operator-funded admin-* entry. A
request whose primary provider runs on the user's own key reserves
under the generous user-plan ceiling; a fallback hop (or health-ledger
reorder) onto the operator's key could then spend past the operator's
cap unchecked. An exhausted cap skips the candidate like a failed hop.
- summaryState PENDING gets a giver-upper: the detail serialiser
degrades a PENDING older than an hour to UNAVAILABLE (which offers the
manual generate action), and an hourly reaper persists the same heal
following the orphan-ImportJob reconcile precedent — a job dead past
its retry budget no longer leaves the sheet saying "generating"
forever.
tsc rejects spreading unknown[] into a zero-parameter vi.fn; give the
context-evaluator stubs a variadic signature and cast the recorded call
tuples where the tests read them back.
A Coach reminder captured with NEXT_BP_LOGGED, NEXT_WEIGHT_LOGGED,
NEXT_SLEEP_LOGGED or NEXT_APP_OPEN confirmed to the user and then never
fired: the daily sweep skipped context triggers and no other evaluator
existed.
Build the evaluator. The three logging cues resolve on evidence — a
live matching-type measurement logged after capture — and ride the same
eventful reminder-satisfy hook every ingest path already fires, with the
daily sweep re-running them as the idempotent backstop. NEXT_APP_OPEN
resolves on the nudge-status read (the poll that mounts with the app
chrome), owner-only so a delegate's visit never satisfies it, with a
capture grace so the session that created the reminder does not count as
the next open. Every trigger delivers through the surfacing transaction
extracted from the sweep: conversation + assistant message + status
flip, all-or-nothing.
The facts fold already skips the empty assistant row a cancelled turn
leaves behind; the plan fold read it as a blank turn and spent one of
its recent-turn slots on nothing. Same skip, same reason. Also state
the accepted one-slot slack a late rate-limit refund can leave in a
freshly opened window. Refs #781.
The rolling-summary and fact-extraction workers read message bodies
directly, so an empty cancelled marker would ride their prompts as a
blank assistant line. Skip empty bodies in both folds. Refs #781
The Coach can now see that a visit is coming and what the last one was
about, without being handed a visit archive. The block is deliberately
small: the appointments booked within the next 14 days plus the single
most recent visit that happened. A full history is a get_visits
question, not a prompt-budget one.
Built as a peer of the illness and labs blocks and registered for
degradation EXPLICITLY against the lowest-priority cluster, so it is
among the first blocks shed when the character cap binds, before any
clinical cluster. Encrypted reason and outcome decrypt fail-soft and
every free-text string routes through the prompt sanitiser first.
A lab runs its own method on its own device, so the window a physician
evaluates a value against is the one printed next to it on that report,
not a catalog band averaged over every lab. Reading a report pulled the
value and dropped that range: the extraction asked for it, the commit
handed it to the biomarker resolver, and the resolver only uses it when
it mints a NEW marker. For every analyte the user already had — the
normal case after a first panel — the printed range was read and then
thrown away.
Add `sourceReferenceLow` / `sourceReferenceHigh` / `sourceReferenceText`
to `LabResult` and carry the range from the report to the reading. The
text is stored whether or not numbers can be read out of it, because
"bis 5,0" and "negativ" state a window too; a range that could not be
parsed is kept verbatim, never replaced with invented bounds.
`resolveEffectiveReferenceRange` is the one place the precedence lives:
the source window wins for that single reading, and the catalog stays
the net for readings without one. A printed string with no derivable
bound does not displace the catalog. Every surface that judges a
reading routes through it — the API verdict, the doctor report, the
insights blocks and per-marker assessment, the coach snapshot, the MCP
read and the FHIR `referenceRange` — so a value cannot read in range on
one surface and out on another.
The API keeps `referenceLow` / `referenceHigh` as the window in force,
so a client that reads only those two renders the right range and the
right verdict with no change of its own; the catalog band, the source
window, its origin and a divergence flag ride alongside for clients
that want to show both.
Read side: the chart draws the source window as a second, visually
distinct band with the reading it came from named beneath it, the
reading rows name the printed range and the catalog band where the two
disagree, and the doctor-report PDF prints the report's own string with
a footnote naming the saved range. Entry side: one optional field on
the lab form, folded away until asked for, and the printed range is
editable on the scan review screen.
The range parser covers the notations German and English reports
actually print — two-sided, one-sided, comma or dot decimals, thousands
separators, trailing units — reads units without ever converting them,
and refuses to guess on anything ambiguous.
The engine ended the open cycle's phase window at the predicted next
start, so the day after a missed forecast carried no phase at all and
the verdict resolver read that as today falling outside every known
cycle window. An ordinary three-days-late period therefore reported
INSUFFICIENT_DATA: no cycle day, no phase, an empty ring and the words
insufficient data, while the reminder cron was pushing a period-confirm
prompt for the same day. OVERDUE was only reachable when the engine
itself forecast a cycle longer than the grace window.
The open cycle now runs to the predicted start or through today,
whichever is later, and stops the moment the next start is logged. The
count is bounded on the far side where it already was: past the typical
length plus its grace window the verdict degrades to OVERDUE and says
how late the period is.
The extension pins the open cycle's ovulation anchor to the predicted
length. Left to the span, an unconfirmed ovulation is back-calculated
from the window's own length, so a window that grows with the delay
would walk the estimate and every phase boundary drawn from it.
- buildPhaseCycles, phaseForDate and buildPhaseDayMap take the user's
today; the insights route and the coach snapshot pass it
- verdict round-trip covers the predicted start day, three days past it,
past the grace window, and the case where a new start closes the run
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.
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.
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.
`binaryReferenceSex` was already the declared owner of the shrink from the
three stored values to the two a sex-split reference table has rows for, but
eight sites still narrowed inline — including a byte-for-byte private copy in
the effective-range resolver and a ternary 37 lines above a `toProfileSex`
call in the same file. Each of those is a place the fallback can drift.
Delete the copy, replace the ternaries, and name the pair once as
`BinaryReferenceSex` so a signature that needs it stops re-listing the two
literals. No behaviour changes: every site already resolved OTHER and "no
answer" to the same neutral or absent value, and the existing suites pass
untouched.
The properties this provider has to keep: it resolves against the base
URL that was saved for it, the pinned OpenAI arm cannot see that URL and
still posts to api.openai.com, and the OpenAI key never travels to the
gateway. Each is asserted at the wire, not on internals.
The SSRF floor is checked through the same alt-notation classes the
Local provider is checked against, and the pinned tags are shown to keep
requiring a public host even when the operator opened every private one.
The AI settings connect-src is pinned to what it already allowed: the
gateway is called server-side, so no CSP change is needed, and a future
change that needs one will turn this red.
The chain gains a seventh entry. It builds the OpenAI client against the
base URL the user saved, with the bearer they saved for it and the model
they named, and it reads none of the OpenAI columns — the pinned
api.openai.com arm stays pinned.
Host policy is the Local provider's, unchanged: a public host always, a
private one only where the operator allowlisted it, which is what a LAN
LiteLLM or vLLM needs. Egress keeps riding safeFetch.
The JSON-mode dialect the Local client learns per endpoint moves into a
shared module and now serves both clients, so a gateway that rejects
response_format is detected once and retried without it.
The entry stays out of the default chain: it can only resolve against a
base URL somebody configured.
The preamble already says once what the two states mean and that neither is
absence; repeating it per row would have doubled a manifest that rides every
turn.
The unit suite mocks Prisma, so it proves the discriminant and nothing about the
query underneath it — a wrong column would have left every test green and every
account answering no_data_unconfirmed in production. Seeds the reported case and
the four other shapes: an empty record, another account's rows, tombstoned rows,
and a history that mixes units.
Rounds the out-of-window mean to one decimal, like every other mean the snapshot
surfaces, and annotates a failed manifest probe rather than letting it degrade in
silence.
The mutation check found both holes: an addendum test that only looked for the
new reason codes passed with the old declare-absence-and-move-on sentence still
in place, and a block-failure check whose window was wide enough to see the
neighbouring block's annotation.
The fixture is the report: a fortnight of glucose readings from April 2024 on an
account that displays them everywhere else. The clock is pinned so it cannot age
out of the window it was written to sit outside of.
Covers the four states an empty window read can resolve to, that a never-recorded
metric and a historical one differ in the SAME run, that a mean is withheld
across mixed units rather than fabricated, that the manifest advertises the range
instead of "absent", that both instructions branch on the reason code, and that a
miss carrying figures reaches the prose verifier's authoritative set. Adds the
medication-compliance page to the failed-read sweep and pins the narration
blocks' failure annotation.
A Coach retrieval tool that read the window and found nothing returned
`reason: "no_data"` — the same code for two situations that have nothing in
common: the record holds nothing for that metric, and the record holds a
substantial history for it, all of it older than the window that was searched.
Nothing downstream could tell them apart, so the Coach said the honest-sounding
sentence for the wrong case, and then, having been told there was nothing there,
changed the subject. Someone with a year of imported glucose readings was told
the readings did not exist, on the same account whose glucose page was showing
them.
The window cap stays. It exists because a multi-year history does not fit a
prompt budget, and widening it would only move the same failure. What was
missing is the ability to say a different true sentence.
- `tools/availability.ts` — one grouped aggregate per miss, no rows
materialised, resolving four states: `no_data` (probe confirmed empty),
`outside_window` (rows exist, older than the searched window; carries the
count, the date range in the user's own timezone, and a bounded per-series
mean/min/max), `unavailable_in_scope` (rows exist inside the window and the
domain still produced none — a module is off), and `no_data_unconfirmed` (the
probe itself failed; absence was never established, so it is not asserted).
- Every empty read in the executor routes through it. A bare `no_data` can no
longer be returned without the record having been checked.
- The DATA INVENTORY carries the same distinction, so a domain the window
cannot reach is advertised with what it holds instead of as absent — the model
no longer skips the fetch, and a vague follow-up keeps the subject.
- Both instructions that told the model to report absence and move on now
branch on the reason code, and forbid answering about one metric by reporting
another.
- The out-of-window aggregate joins the authoritative set for the prose
verifier, so the sentence the fix exists to make sayable is not elided.
- A cross-cutting narration block that throws is now counted rather than
vanishing into a `null` that looks like honest absence.
- The medication-compliance page tells a failed read apart from an account with
no medications, instead of inviting someone to re-enter what it already holds.
Refs #648
Adds the cases that were missing everywhere except the FHIR conformance
suite: an empty string clears without taking its siblings down, OTHER
round-trips through the profile and onboarding writes, an unsupported
value is still refused and says which field it is about, the Strain
model scores an unanswered account on neither side, the dashboard bands
give OTHER the neutral fallback, the snapshot payload carries the value
instead of flattening it, and the doctor-report cover omits the row
rather than claiming a value the account never chose.
Refs #645
Mood has been a first-class module here for a long time, with entries,
structured tags, rated factors and notes. The bridge to the external moodLog
service had nothing left to add, and its Settings card was withdrawn in
a56e6fe61 on the promise of a dedicated removal. This delivers it.
Removed: the hourly `moodlog-sync` queue, cron and handler binding; the
inbound webhook and its shared-secret handling; the reverse push and its four
call sites; the pull-sync module; the per-user credential routes and the
instance-wide toggle; the entry on the `/api/integrations/status` envelope,
the `IntegrationKey` union, the cadence map and the display-name table; the
boot-time secret rotation pass; 22 message keys per locale.
Migration 0271 drops the five `users` credential columns and
`app_settings.mood_log_global`, clears the ledger row for the provider, and
deletes the retired pg-boss schedule so no cron keeps enqueuing work no
handler drains.
Mood data is untouched. `mood_entries` is not named anywhere in the migration
and cannot be reached from it: the dropped columns carry no index, constraint
or foreign key, and `mood_entries.user_id` references `users(id)`, not any of
them. Rows the bridge imported keep `source = 'MOODLOG'`, and every read path
- list filter, source badge, exports, backups - still resolves that value.
`src/lib/validations/moodlog.ts` held the native mood-entry schemas alongside
the bridge's own; it is now `validations/mood.ts` and carries only the former.
Route the medication-compliance status card through finalizeStatusSummary so
it enforces the same dose / risk / causal outbound contracts its seven sibling
status cards do, not only the unparseable-envelope withhold it already had. A
dose-change imperative or a fabricated figure is now withheld to the controlled
fallback on this surface too.
Add the status cards' structured-envelope detection to the two background hero
lines (arrival reaction, coach nudge): a brace-led or fenced JSON reply, or a
truncated envelope under the char cap, now resolves to the deterministic lead
rather than rendering raw.
Fold in the residuals from the same sweep: strip a truncated SUGGEST-ACTION
marker from the Coach prose tail, drop an unreachable zero-rate branch in the
adherence fold, and document why the internal conversation summary stays off
the render-boundary screen.
Replace the internal "[unverified]" token the grounding guard left in a Coach
reply with the editorial elision mark […], and add a quiet muted caption
under the bubble explaining that some figures could not be checked against the
user's data. The mark holds the slot grammar-safely mid-sentence, before a
surviving unit, and inside a range; the notice carries the meaning. The withheld
count rides the existing provenance envelope (unverifiedFigures) through the
stream, persistence, and reload, and the fenced document-chat path carries a
minimal envelope so its notice survives too. New i18n key across all six locales.
Also fix an adjacent reload gap: provenanceFromJson restored only a subset of the
serialised envelope, so a persisted suggestion card, confirm action card, and the
tool trace were dropped on conversation reload despite the render layer expecting
them to survive. Restore them defensively alongside the new field.
Promote the per-turn magnitude bag to a per-conversation typed Grounding
Ledger built from every source the model was actually shown: this turn's
tool payloads, prior-turn tool figures, coach-memory goals, the medication
schedule, the reference-grounding block, and guided blocks. Assistant prose
is never a registration source, so a figure that slipped a rung cannot
launder into an authoritative value on the next turn.
Complete the action ladder: a reconciled number passes, a reference or
education sentence is exempt across all six locales, a positively-typed
benign number (date, time, year, ordinal, list marker) passes while an
untyped unreconciled one stays on the strip path, and an unreconciled
health figure is soft-stripped.
Gate the dose continuation exemption on the user's actual schedule: a
"keep taking your N mg" is trusted only when N is a dose the user is on;
an off-schedule maintenance dose is caught. Extend the risk and percent
classifiers to fr/es/it/pl to match the EN/DE depth.
No schema migration: the ledger is rebuilt per turn from persisted tool
traces and re-rendered prompt blocks.
Replace the untyped magnitude bag in the Coach numeric verifier with a typed
tokenizer and a normal-form reconciler, and narrow the outbound risk and dose
banks so correct figures and correct refusals stop being blocked while every
fabrication shape still blocks.
Grounding verifier (coach-prose-grounding.ts):
- Classify each prose number before grading — ISO/written dates, clock times,
bare years, ordinals, list markers, hyphenated time spans, ranges, percents,
thousands-separated integers, unit-suffixed measurements. Benign types are
never graded or stripped; ranges decompose into per-endpoint magnitudes.
- Grade against typed authoritative entries (value + kind + aggregation).
Sign-insensitive, canonical rounding, ratio to percent in percent space, and
minutes to hours widen the match only for an aggregate, kinded entry; kind
scoping stops a weight value grounding a blood-pressure claim.
- Thousands/decimal separators follow the reply language.
- Boundary-safe strip so a flagged token never clips a larger grounded number.
Outbound screen (outbound-screen.ts):
- Risk bank requires an asserted figure or a categorical engine result; a bare
engine or horizon mention (education/refusal) passes. Spelled-out percents
count as figures. No refusal-context exemption. EN + DE.
- Dose bank keeps a maintenance-continuation restatement, voided by any change
stem. Taper suffix fixed.
Route + fenced-chat thread the reply locale into the verifier.
Merge the eight reviewed audit fixes that were cut a week ago and never
landed. Main has moved on since, so each fix was re-checked against the
current tree and each of the five conflicts resolved by understanding
both sides.
Kept, still open on main:
- Proxy early exits now carry the transport security header subset via a
shared helper. Reconciled with main's /api/health worker-only carve-out.
- Batch measurement ingest bounds the entry instant so a future-dated row
can no longer win "latest reading" or poison the rollup buckets.
- Web Push dials through the pinned safeFetch dispatcher with
requirePublicHost, closing the last user-controlled-host egress.
- Mood bulk upsert and its tag/factor links run in one transaction, so a
rejected rating rolls the mood row back instead of leaving a tagless row.
- Full backup carries NutrientIntakeDay with its unit and source. Folded
into main's portable-export / disaster-recovery split.
- Live daily-series fallback restores the min/max spread band the tiered
read already emitted.
- Coach stream aborts its in-flight reader on unmount and resets send state
on a conversation switch.
- Manual water writes share the day-bound helper, nutrient add clamps after
the increment, and the thiamin cap drops to a real supplement ceiling.
- Compliance point window widens symmetrically instead of wrapping overnight.
- Oura, Polar and Fitbit token helpers classify an empty or non-JSON 2xx
body as a handled transient error.
- WebAuthn relying-party fallback to localhost is gated to development.
- Chart-token strip list is derived from the allowlist and pinned by a test.
- Regression tests pin the snapshot-cache tenant key, the GlitchTip
path-secret redaction and the Withings credentials delete.
Superseded by main, tests re-pointed at the current shape:
- The intake CSV import was rewritten on main to run through a background
job with a single-active-job admission gate. The future-date bound is
re-applied at request validation and the per-user limiter is kept for
parity with the bulk twin; the old synchronous-write test is replaced.
The previous commit spliced the DATA INVENTORY manifest into the tool-mode
authoritative payload set unconditionally. That made the payload set
non-empty on a turn where the model answered WITHOUT calling any tool
(empty tool results), which flipped the verifier from dormant to active —
grading the reply against an inventory that carries per-domain sample counts
only, never the snapshot's pre-computed averages. A figure the model
correctly narrated from the snapshot (a 30-day systolic average) was then
stripped to "[unverified]" — the exact false positive this work exists to
prevent, and a regression from main's "no tool figures this turn → skip,
prompt-level grounding is the backstop" contract.
The inventory must only WIDEN an already-active authoritative set, never
ACTIVATE it on its own. Gate activation on a real present figure block
(a pinned workout-evidence block or a present tool result) exactly as main
did; when active, the inventory counts still join the set so a plain count
restatement stays grounded.
Adds a route-level regression test (fast suite) proving the verifier stays
dormant when no tool returned figures, plus companion unit tests documenting
that a real tool section grounds the average while a counts-only inventory
does not.
Three confirmed false-positive shapes in findUnverifiedCoachNumbers/
stripUnverifiedNumbers were replacing legitimate prose with the literal
"[unverified]" placeholder even though the underlying data was grounded:
- A correctly-computed delta, midpoint average, or percent change between
two of a payload's own headline aggregate figures (e.g. "down 3.5 kg from
your 7-day average") was never itself a raw leaf in any tool result, so it
was flagged as invented. The authoritative set now also carries the
pairwise delta/average/percent-change between a SINGLE payload's own
named aggregate fields (latest, avg7, avg30, avgSys30, allTimeAvg, ...),
scoped per payload so a weight delta cannot ground itself against an
unrelated metric's figure.
- The always-sent DATA INVENTORY manifest (tool-mode base context) carries a
sample count per domain, but that count was never added to the
authoritative set the way the pinned workout-evidence block already is —
so a plain restatement of a domain's count ("you've logged 42 BP
readings") was flagged whenever the model didn't also call that domain's
retrieval tool in the same turn. The inventory entries now splice into
toolResultPayloads exactly like workoutEvidence.
- A calendar-date ordinal ("July 21st") or a numbered-list marker ("1. Cut
back on sodium") tokenised as a bare number and, when ungrounded, got
soft-stripped mid-word into visibly broken text ("July [unverified]st").
Prose is now masked for these two narrow, high-precision shapes before
numeric extraction; the original text used for stripping is untouched.
A genuinely fabricated figure (unrelated to any grounded point, inventory
count, date, or list marker) is still caught and stripped — covered by new
adversarial cases alongside each fix.
Investigated and ruled out: multi-round tool-loop result accumulation (all
present results across every round already reach the verifier); unit
conversion (the app resolves and serves one consistent unit, so there is no
independent conversion step for the model to get wrong). The Daily
Briefing's separate withhold-a-whole-section grounding gate is unrelated to
the reported symptom (a different failure mode, whole-line omission vs.
inline replacement) and was not touched.
The named-risk-engine pattern in the outbound safety screen used
score2? (the 2 optional), so it matched bare "score" too — any mention
of one of this app's own computed, documented scores (Sleep Score,
Readiness Score, Health Score, Recovery Score, Stress Score, Strain
Score) tripped the bank meant only to catch a fabricated named
clinical-risk calculator (SCORE2, Framingham, ASCVD, QRISK).
Require the literal "SCORE2" instead. The other risk patterns —
percentage-shaped risk claims and the other three named engines — are
untouched, so a genuinely fabricated risk figure or a named
risk-calculator claim still blocks.
Closes#587.
The harness landed in v1.30.35, after the slices that built this
release were already cut — so the reaction line's prompt module was
never registered, and its own docblock's warning against the
two-locale collapse was untested. Registering it surfaced a real gap:
the meaning-first instruction lived only in the system prompt's own
words, never in the user prompt in the family's shared phrasing, which
is where the rest of the surfaces carry it and where the tone contract
checks for it. The German body carried no such instruction at all.
Threads locale through the user-prompt builder so the fixed
instruction line matches the reader's own reply language, and wires
the per-user per-day opener-archetype rotation the milestone spec
called for and the first implementation had not connected.
Marc-André Bombeck