The retry suffix still described the strict insight wrapper that was removed
long ago: it demanded citations[] and warnings[] — fields insightResultSchema
does not have — required metricSource, rationale, id and severity on every
recommendation when all four are optional, and named none of the five fields
the live schema actually requires (classification, findings, correlations,
dataQuality, disclaimer).
So the one corrective pass steered the model away from the contract it was
being corrected towards. A reply that obeyed the correction could not
validate, fell through parseComprehensiveResult's raw-object escape hatch,
and the downstream surfaces read an unvalidated payload.
Describe insightResultSchema and nothing else, and carry the contract as data
in RETRY_CONTRACT_EXAMPLE so a test can assert prompt and validator agree.
With the error notice hoisted to the page, the three cards fell through
to their skeleton on a failed read — a spinner that can never resolve.
Return null instead, so a card rendered outside the page's gate is still
honest about having nothing to show.
The rhythm, average-sleep and chronotype cards on /insights/sleep share
a single ["sleep-rhythm"] read, and each rendered its own copy of the
same failure sentence — so one failed read painted the identical notice
three times, none of them offering a way to try again.
The page owns the shared state now: one notice with a retry in place of
the card row. The cards keep their loading and empty handling and drop
the duplicated error branch.
Importing the plural helper directly from the dashboard trend tile cost
~78 KB gz across the route chunks: the module is tiny, but a new edge
from a widely-instantiated component gets duplicated into every chunk
that contains it rather than hoisted. The provider is already in every
chunk, so expose a plural-aware tCount() there and let components call
that instead. Total client JS goes back under budget.
Also fix the two tests the honest-loading-state change invalidated: the
mental-wellbeing landing tests seeded a never-resolving read and so now
render skeletons rather than instrument cards, and the achievements page
needs a router in scope for its module-gate redirect.
The reminder, coach and plural fixes were pinned; the three formatter
fixes were not. Add the duration abbreviations across all six locales
and a structural check that the cycle calendar, device-score tile and
sleep-stage axis pass a resolved app locale to Intl rather than
undefined, which silently resolves to the browser locale.
"No data yet" is a claim about the user's record. Making it when the
read failed states something false about their health history.
The mental-wellbeing surface was the one that mattered: the assessment
history read dropped isError entirely, so a failure left both
instrument cards showing "not taken yet" and the detail sheet showing
an empty trend. Someone with months of screening results was told, on
a mental-health surface, that the results did not exist. It now tells
loading, failed and genuinely empty apart, with a retry on the failure.
Also swept:
- the workouts insights page read isEmpty but not isError, so a failed
list read fell through every branch to null and painted a titled
shell with nothing in it;
- the micronutrients card (not in the original list) rendered its "no
nutrient data" empty state on a failed read, while its sibling
hydration card already used the shared error card;
- the medication detail page and the custom-metric values list showed
an honest error with no way out. Both keep retry: false — right for
a deleted row, wrong for a transient failure — and gain a
user-initiated retry instead, which cannot storm;
- /achievements rendered a blank page on a direct hit with the module
disabled. It now bounces to /insights like every other gated page.
The achievements query error branch, the custom-metric error branch and
the chronotype notice were already correct and are left alone.
Four locales received English on surfaces whose translations were
already complete, because the resolving code was a de/en binary.
- Medication reminder push and the Telegram inline-keyboard labels
admitted only de/en, so es/fr/it/pl got the English template on every
channel. Route the resolver through a shared coerceLocale().
- The Coach's trailing "reply now in X" clause said English for any
non-German locale, overriding the correct system-prompt directive.
Read the language name from a shared map instead.
- Coach refusal copy was a de/en constant pair, answering four locales
in English at the one turn the Coach is declining to help. Move the
copy into the bundles; the EN/DE constants now derive from them.
- The sleep-stage chart formatted axis ticks as en-US for four locales;
the cycle calendar and the device-score tile followed the *browser*
locale rather than the app locale.
- Three components carried a byte-identical duration formatter that
branched on German. Lift it to one key-driven helper.
Polish needs a third plural tier: 2-4 takes a "few" form a two-form
scheme cannot express, so "2 godzin temu" read as "2 of-hours ago".
Add a pluralKey() helper driven by Intl.PluralRules and a Few tier to
the relative-time and stale-hint keys. The five locales whose rules
have no "few" category resolve exactly as before by construction, and
their Few values mirror Other. Teach the reverse-coverage guard to
expand a pluralKey() base into its three tiers.
generateInsight() parsed against the strict aiInsightResponseSchema,
cross-checked that every recommendation's metricSource appeared in
citations[], and threw InsightSchemaError on a second failure. Its only
caller was runWithFallback(), which had no production caller — every
live surface runs runRawCompletionWithFallback. So none of it executed.
Wiring it into the live path was the alternative and it is not viable:
the live insightResultSchema has no citations[] field at all and treats
metricSource as optional, so the cross-check would have rejected
essentially every generation rather than tightening anything.
Removed: runWithFallback and its param/result types, generateInsight
and its private helpers, findUncitedRecommendations,
findRecommendationsMissingRationale, the never-thrown InsightSchemaError
and the isHardProviderFailure branch that excluded it, and
computeConfidence — a deterministic override that only ran inside the
dead wrapper.
Kept: buildRetryCorrectionMessage, which comprehensive-generate sends on
its own retry leg; the file it lived in is renamed to match what it now
holds. aiInsightResponseSchema stays as the shape that message
describes. Note the retry prompt asks for a stricter payload than the
live validator requires — that mismatch predates this and is left alone.
computeCitationCoverage is untouched and still live: it is a metric, not
a gate, and v1.30.24 wired it into the comprehensive post-parse step.
Chain-runner coverage the deleted tests carried (last-working cache,
empty-input guard) is ported onto runRawCompletionWithFallback, which
shares the machinery.
Three things the write surface claimed but did not hold.
Scope: the run bodies never re-checked ctx.canWrite. Enforcement was
real but lived entirely in the registration decision, and the test
asserted registration only — so a refactor that registered the write
tools unconditionally and meant to refuse at call time would open the
surface with the suite still green. Wrap every run body in a scope
guard at the registry level, so a new write tool inherits it, and drive
the run bodies directly from a read-only context in the test.
Free text: medication names, doses, treatment classes and lab analyte
names were interpolated into tool prose with no delimiter. A lab
analyte name is transcribed out of an uploaded document, so a hostile
document chooses it, and the write tools ride the same wire. Fence the
assembled prose with the shared data-fence markers and scrub short
result titles, which would leak markers into a host's result list.
Confirm: the header called the confirm flag a PROTOCOL-LEVEL CONFIRM
GATE. It is a client-asserted boolean with nothing binding it to a
prior preview. Binding it to a server-issued preview token would prove
only that a preview call happened, which any client can do, so it buys
no human-in-the-loop for a round trip and server state the stateless
transport does not want. Describe it as the convention it is and name
what actually bounds the blast radius.
The changelog merge left conflict markers inside the CACHE_VERSION
assignment. The version generator only rewrites the version string, so
it could not repair the broken structure, and every service-worker test
failed while both branches were green on their own.
enforceBudget and recordSpend have no callers left. Both defects they
carried recurred every time a surface copied them: a TOCTOU window
between the read and the bump, and a cap parameter defaulting to the
operator ceiling so an omitted argument rationed a self-hoster paying
for their own key. Deleting them means a future surface cannot reach
for the older, simpler-looking helper and reintroduce either.
getDailyTokenSpend goes with them — it existed to feed the read half.
The ledger-poisoning clamps recordSpend carried (NaN, negative,
fractional token counts) move to reserveBudget, where the property now
lives. Refresh the doc comments that still narrated the old flow.
The route used the enforceBudget + recordSpend read-then-write pair and
passed no cap, so every call measured against the operator ceiling — a
self-hoster on their own key was rationed by the operator's bill while
paying for their own usage. It also left the TOCTOU window the rest of
the codebase closed: concurrent calls could each read a sub-cap total
and all proceed.
Move the gate after the chain resolves and reserve atomically against
resolveDailyCap(chain), matching runStatusCompletion and the document
paths. Reconcile on every exit: the provider's reported count on a
completed call, a full refund when nothing was generated.
Pin the four guarantees at the new chokepoint and at both call sites: spend
lands on the ledger, over-cap is refused before any egress, a BYOK chain is
measured against the user-plan ceiling rather than the operator's, and a
failed call refunds in full. Also pin the ordering the consent gate depends
on — a consent-blocked user is never charged.
The fixture described a clean resting series but supplied rows for only
twenty of the thirty days it fed PULSE for. Now that the resolver merges
per day, the ten resting-free days are estimated from their own readings
— and on a day whose only readings are a 150 bpm workout the honest
estimate falls outside the band. Match the spans so the case tests what
its name claims; gap-day behaviour is pinned in resting-pulse.test.ts.
The status tier funnels every generation through runStatusCompletion, which
reserves against the day's ledger before egress and reconciles after. The
comprehensive briefing did not: the shared generator and the on-demand
POST /api/insights/generate route both called the provider chain directly, so
none of that spend reached coach_usage and no daily ceiling applied to it.
Route every briefing provider call — first pass, JSON-shape retry,
grounding-correction retry, and the daily paragraph re-roll — through one
chokepoint that reuses reserveBudget / reconcileSpend and resolveDailyCap. The
reservation lands after the consent gate, so a consent-blocked user is never
charged, and a failed or timed-out call is refunded in full.
Over-cap is a typed skipped outcome for the off-request generator (no upstream
fault to retry against, so no failure marker and no retry enqueue) and a 429
for the on-demand route.
Each case fails on the pre-fix code: the rollup tests on an unaligned
recompute window, the batch tests on the older stats: snapshot winning,
and the resting test on a series that stops at the fold horizon.
resolveRestingPulseSeries returned the resting branch as soon as a
single RESTING_HEART_RATE row existed and never consulted the PULSE
proxy again. Since the retention fold began minting derived resting
rows for the days it folds, a proxy account carries derived rows for
old folded days and nothing but raw PULSE for the recent ones — so the
visible series stopped dead at the fold horizon.
Merge per day instead: a day with a resting row uses it, a day without
falls back to the proxy. which stays a three-value labelling signal and
reports proxy as soon as one point is estimated, so a partly-estimated
series is never labelled resting heart rate.
Widen the intraday baseline read to pull PULSE history when the newest
resting row is stale, not only when the rows are few — the count gate
alone pinned the baseline to the fold horizon.
Two entries carrying the same stats: key in one batch both miss the
existing-row probe, so the overwrite branch never runs, both land in the
bulk insert, and skipDuplicates keeps whichever the unique index saw
first. The older snapshot of a per-day cumulative total or of a filling
ten-minute heart-rate bucket therefore won and the newer, larger figure
was dropped silently — both entries reported inserted, the counters
still summed, and the client checkpointed past both.
stats: rows carry overwrite semantics by contract, so within one batch
the last entry for a key is the authoritative one. Resolve it up front
and report the superseded earlier entries as duplicate with a
superseded_in_batch reason, a status the client already checkpoints
past.
recomputeUserRollups filtered measurements by a caller-supplied from/to
but grouped them by date_trunc, and persistRollupRows then deletes every
rollup row in the bucket range it is about to write. A from that landed
mid-bucket therefore replaced a complete bucket with an aggregate
computed only from the readings after that instant.
Every caller passes a moving instant — now minus ninety days on the
read-path refresh, an arbitrary instant on the coverage fallback, now
minus five years on the boot backfill and the restore path — so a
different oldest bucket was corrupted on each invocation and nothing
repaired it. Snap both edges out to whole buckets via bucketSpan, whose
own contract note already required exactly this of every recompute.
The red-team corpus probed only user messages and model replies. Neither is
the channel that reaches the prompt unguarded: a lab analyte, panel or unit
name, or a medication label, none of which the account holder authors when
the row was committed from an uploaded document.
The free-text guard's file list was hardcoded and had rotted — three of its
four entries were no longer reachable from the snapshot, and it covered one
of the dozen files that actually emit free text, which is why the lab fields
went unnoticed. Derive it from the import graph instead; it now covers 75
files, with a floor assertion so a resolver break cannot silently empty it.
Deriving the list immediately surfaced a second leak: features.ts shipped a
raw medication name and dose into the snapshot medications block.
Also fix sanitizeForPrompt itself. It deleted control characters, which
welded neighbouring tokens together and destroyed the word boundary its own
injection patterns anchor on, so a payload preceded by a newline survived
because of the newline. Replace with a space and collapse before matching.
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.
The status-provider suite drives the real budget module against an
in-memory stand-in for the day's usage row, so it exercises the atomic
reserve/reconcile path rather than asserting a mock was called: spend
lands on the ledger, an exhausted day is refused before any egress, a
failed generation is refunded, and a chain on the user's own key is
measured against the user-plan ceiling rather than the operator's.
The snapshot suite walks a 60-turn conversation and pins the full
snapshot to exactly two turns — the first and the elision crossing —
including the case where a lost reply shifts the turn parity.
The provider chokepoint every status and reference generator funnels
through ran with no budget accounting at all. Nine generator families
egressed behind it — the specialised status cards, the generic metric
cards, biomarker cards, the batched assessment, the derived scores, the
period narrative, and the off-request Coach memory workers (rolling
summary, fact extraction, plan proposals) — and none of that spend landed
on the daily ledger or met any ceiling. On an operator-key account it was
unmetered operator spend.
Reserve and reconcile around the provider call, using the same atomic
upsert the Coach and document paths use. The ceiling follows the cost
owner: a chain whose primary is the operator's own credential draws the
operator ceiling, everything else draws the user-plan ceiling, so a
self-hoster on their own key is never rationed by the operator's bill.
The status enqueue keyed its de-dupe singleton on (user, metric, locale).
The locale on a status read is client-chosen, so each of the six
supported locales opened its own slot and one legitimate generation pass
could be multiplied into six. Key on (user, metric) and carry the locale
in the payload instead.
The Coach re-shipped the full snapshot on every turn past the history
cap, not just the turn that crosses it, so a long conversation paid the
per-turn snapshot cost the snapshot-once model exists to remove. Re-ground
on the crossing only, tested as a narrow window rather than an equality
because a turn advances the count by one or two depending on whether the
reply persisted.
Give /api/ai/test a daily ceiling and a ledger entry. Its burst bucket
bounded rate but nothing cumulative, and with an empty body it resolves
the same chain generation uses — which can be the operator's credential.
Correct the memory-refresh worker comment, which asserted a budget check
inside the chokepoint that did not exist.
The coverage check hung off generateInsight, whose only caller runWithFallback
has no production caller left -- every live surface routes through
runRawCompletionWithFallback instead. The admin quality dashboard was reading a
metric nothing emitted. Widen the input to the structural shape both payloads
share and call it from the comprehensive post-parse step, so the annotation
reflects real generations.
Writing the locale tests found three gaps the English-only banks hid: Polish
verb suffixes fell outside the ASCII word class, a trailing word boundary after
an accented character never closed, and German subordinate clauses put the verb
last so the natural phrasing of a dose instruction never matched. The payload
collector also skipped legacy bare-string recommendations entirely.
Marc-André Bombeck