Introduce an operator-level ChatGPT-subscription (Codex) credential that the
operator connects once and shares server-wide, plus a per-user switch to route
AI egress through it.
- Schema (migration 0235): three encrypted columns on AppSettings for the
operator's central Codex access/refresh tokens and the ChatGPT-Account-ID
claim, plus expiry/connected-at/status; a per-user useCentralCodex flag
(default false). Register the new encrypted columns in the rotation registry
and script.
- Resolution: add the admin-codex chain type; append it to a user's resolved
chain only when they opted in AND the operator connected it. Tokens refresh
server-side against the singleton row (CAS-style), same primitives as the
per-user Codex path.
- Budget: bill an admin-codex primary against the operator cost cap, not the
user plan — it drains the operator's account.
- Consent: admin-codex is server-managed external egress, gated by the existing
consent machinery (self-snapshot and document surfaces alike). No existing
consent path is weakened.
- Document order: rank admin-codex with the subscription tier (last), so the
document class stays local-first.
- UI: admin device-code connect/disconnect card (cookie-only admin routes) with
honest copy on account pooling, shared rate limits, and training-by-default;
a per-user opt-in switch shown only once the operator has connected it, off by
default, behind a one-time honesty confirm.
- i18n across all six locales; unit tests for the chain type, budget cap,
consent gate, vision capability, and document order; a mocked e2e for both
the admin connect surface and the per-user switch.
The central credential's tokens are encrypted at rest and never returned to a
non-admin API; the opt-in only takes effect once the operator has connected the
shared account.
The comprehensive briefing warm/cron path wrapped generation in a fixed
130 s outer abort, but the per-user response-timeout setting accepts
10-600 s and the AI settings tell users to raise it for slow local
models. Any account whose response timeout was >= ~130 s had every
comprehensive warm clipped by the warm bound, not the provider, so the
generation never landed: no cached briefing row was written and the
dashboard fell to the hard empty state.
Size the warm outer abort from the resolved effective timeout
(`aiResponseTimeoutSeconds * 1000`, falling back to the comprehensive
surface budget) plus a fixed headroom for feature extraction, prompt
assembly, and the cache write. A raised setting now extends the warm and
nightly budgets instead of being silently capped. An absolute ceiling
(the 600 s write-time maximum plus the headroom) keeps a wedged call from
pinning the worker while staying above the largest value a user can set.
Both the nightly loop and the forced on-visit warm read the per-user
setting and use the derived budget.
Make the empty state more useful: record the upstream HTTP status on a
failure marker and classify it (timeout / auth / rate-limit / provider /
format), so the "couldn't generate" state points at the right lever —
raise the response timeout for a timeout, re-check the provider for an
auth rejection — instead of one generic line. Keep-last-good behaviour is
unchanged.
Align the response-timeout field copy with the actual default budget
(~120 s, not ~180 s) across the placeholder, the OpenAPI description, and
the inline note.
The insights alert cards computed medication compliance with the naive
`schedules.length × days` denominator, so a fully-adherent weekly
injectable read ~14% and fired a false low-compliance alert (and a paused
medication mis-fired the same way). Route the alert path through the
canonical `calculateCompliance` engine like every other compliance
surface — pause eras, schedule revisions and dose windows honoured.
Document confirm: committing a numeric observation against an existing
biomarker silently replaced the stated unit with the catalog's, with no
conversion — a stated "6.1 mmol/L" against a mg/dL marker committed
"6.1 mg/dL". Reject on a unit mismatch (fail closed) so the user
reconciles on the review screen, the same posture as the unit-required
guard.
Wire grip strength, waist (with waist-to-height) and pain into the
briefing feature set and the grounding allow-set so the clinical-depth
signals reach the daily narrative; the mental-health screeners stay
excluded by construction.
Biomarker detail: fall back to a generic description for catalog-less
markers, and keep the heading + description with a retry on the error
state. Collapse the medication External-API and Lifecycle groups by
default. Re-enable the insights scroll-to-top regression and assert the
shipped main-content reset.
Align the EN haemoglobin/haematocrit display names to British spelling.
Drop the redundant `(userId, deletedAt)` index on inbound documents — a
strict prefix of the new three-column index. Trim the dead
MedicalDisclaimer variants to the one live `dataPosture`. Move the
crisis-resources card off the retired amber tint to a calm
destructive-subtle border. Add a registry invariant asserting every
biomarker signal key resolves to a real catalog slug.
- Reword two LOINC verification comments in the signals registry so they
no longer trip the forbidden-marker grep, keeping the meaning intact.
- Resolve the dead-code gate: gate the seeded-question opener on the
per-user ambient-suggestions opt-out (wiring the previously orphaned
resolveCoachAmbientSuggestionsEnabled, server-authoritative), drop the
unread decryptDocumentFromBytes helper and its now-unused import, and
remove the unused SignalKind type alias.
- Delegate undici's fetch to the global stub in the provider-chain
integration test so the egress-pinned client HTTP is mocked again.
- Defer the JSON example-download cleanup a tick so revoking the blob URL
no longer races the browser download start (stabilises the e2e).
- Sync the service-worker version fallback to v1.25.0.
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.
Register the seven environmental-exposure signals through the signal registry
as a new "environment" kind (correlation-eligible; off Coach/MCP/FHIR in v1),
and fold their daily series into the correlation engine as lagged behaviour
channels. Weather/daylight now pair against mood, sleep, and vitals through
the existing FDR / effect-size / shrinkage gates, so a thin series degrades to
absent rather than a spurious link. All env channels share one ENVIRONMENT
family so two same-day fields never lag-correlate against each other.
Add coverage for the new biomarker-assessment seam and the marker detail
surface:
- the generator serves today's cache, re-stamps unchanged readings without an
LLM call, and regenerates only when the latest-reading fingerprint changes
- the read-only endpoint returns the envelope, 422s a missing id, and honours
the auth + insightStatus gates
- the detail page paints the stat strip, the chart placeholder, and the
assessment card
- the biomarker resource route drops the marker with its readings in one
userId-narrowed transaction and rejects an inverted target range
Hold the input gate independent of the worker's forced run so an idle marker
re-stamps cached text instead of regenerating, and list the new route on the
non-Coach gate allowlist.
Give each biomarker a detail page that matches the metric sub-pages: a
numbers-first Min/Max/Median/Mean strip over the numeric readings and a
data-grounded AI assessment card.
The assessment is served by a new read-only endpoint
GET /api/insights/biomarker-assessment?biomarkerId=&locale=, returning the
same envelope as /api/insights/metric-status so InsightStatusCard consumes
it unchanged. A new generator reads the marker's LabResult history and
reuses the shared provider runner, the stale-while-revalidate read-only
path, and the persist helper. Regeneration is gated on a fingerprint of the
latest reading, so the assessment is rebuilt only when a new reading lands;
an idle marker re-stamps the cached text without an LLM call. The
biomarker: scope rides the existing on-demand status queue.
The stat strip and the assessment card both self-gate on numeric data, so a
qualitative-only or brand-new marker paints neither.
The daily briefing and the per-metric status assessments ignored the
per-user response-timeout setting: they hardcoded their per-surface
AI_BUDGETS default, so raising the timeout for a slow self-hosted or
local backend had no effect and the surfaces still aborted early. Only
the coach threaded the setting through.
Resolve the effective timeout from User.aiResponseTimeoutSeconds in one
shared helper and thread it onto every non-coach generation call:
- runStatusCompletion is the single chokepoint every status / reference
surface funnels through (per-metric cards, the batched assessment, the
derived assessments, the period narratives), so resolving it there
applies the setting to all of them at once — on both the upstream
call's own timeout and the outer wall-clock cap that previously clipped
a raised value at 60 s.
- The comprehensive briefing generator and the user-initiated regenerate
route thread it onto the main generation, the JSON retry, the grounding
retry, and the paragraph re-roll.
On a failed generation the briefing keeps its last good text — no cache
row is written, so the previous payload stays intact — and records a
dated, append-only failure marker (no migration; reuses the audit-log
JSON pattern). The read path compares the marker against the last
successful generation so it can tell a held briefing from a current one.
A cluster of related correctness gaps in the compliance denominator and the
insight surfaces that read it:
- Paused medications. A doctor-ordered pause flipped `active` off and stamped
`pausedAt`, but resume nulled `pausedAt`, so the interval was irrecoverable
and every paused day became a missed dose after resume — collapsing
adherence across the Health Score, the BP gate, the Coach snapshot and the
report. Persist pause intervals as durable eras (new `MedicationPauseEra`,
migration 0211), close the open era on resume, thread the eras through the
compliance context and drop slots inside a paused interval from the
denominator. Every compliance call site now fetches and passes the eras.
- Health Score eras. The Health-Score fast path was the only compliance
caller that skipped the shared schedule select and schedule revisions, so
after a schedule edit it scored past days against the current schedule
while every other surface used the historical era. Switch it to the shared
select and thread revisions (and pause eras) like the canonical path.
- Insight bucketing timezone. The per-metric status series bucketed every
user in Europe/Berlin, so a near-midnight reading landed in the wrong day
and the relative-day phrasing was off for non-Berlin self-hosters. Thread
the resolved user timezone and key off `userDayKey`.
- Correlation significance. User-facing correlations surfaced from five
paired points with strength read straight off the coefficient. Route them
through the rigorous engine (at least twenty pairs, Student-t p below 0.05)
so small-N coincidences no longer render as confident findings.
- Resting-pulse input. The mood-versus-"resting pulse" correlation fed the
raw PULSE day-mean, which folds in workout HR, under a "Resting pulse"
label. Feed `resolveRestingPulseSeries` (clean RESTING_HEART_RATE, else a
daily low-percentile proxy) so the label matches the input.
Add three read-only awareness cards to the Insights overview, each drawn
off an existing engine and each honest about empty state — the section
un-mounts rather than surfacing a husk.
- Health status: surfaces what is drifting from the user's own normal by
folding the personal-band deviations (coincident-deviation engine) with
the dated, sustained level shifts (changepoint detector) at
GET /api/insights/health-status. Awareness only, never a diagnosis.
- Breathing screening: summarises the last 30 nights of the per-night
sleep-breathing-disturbance index plus device-flagged events at
GET /api/insights/breathing-screening. Mirrors the device's own
classification and states plainly that it is a screening signal, not a
diagnosis — discuss with a clinician.
- Lab changes: pairs the two most-recent numeric lab panels and reports
each shared analyte's signed delta and reference-band standing at
GET /api/insights/labs-changes. Neutral framing only.
Each reshaping helper is pure and unit-tested for its present/absent
states. Register the three sections in the insights-layout universe so
they merge in as default-visible, wire them into the overview and the
edit-mode title map, add the query-factory keys, document the routes in
the OpenAPI contract, and translate every new string across all six
locales.
Encrypt MedicationSideEffect.notes, MedicationDoseChange.note and
MedicationInventoryItem.notes with AES-256-GCM, closing the last plaintext
PHI columns left after the v1.23 note-encryption rollout. Add the three
*Encrypted Bytes columns (migration 0208), register them in the encrypted-
column rotation set, route every read/write through the note cipher, and add
a transactional fail-closed boot-time backfill for legacy rows. Plaintext
columns drop in a later release once the backfill reports zero remaining rows.
Require a fresh second factor on password change for MFA-enrolled accounts,
matching the existing step-up on MFA-disable and recovery-code regen. Redact
free-text note values from the Zod validation excerpt that can reach a wide
event.
Code-review and design follow-ups before the v1.22 cut. No behaviour change
beyond the items below.
Coach / insights:
- Coach SSE route: a non-provider error raised inside the open producer (e.g. a
DB failure persisting the reply) now records on the wide event and forwards to
GlitchTip instead of masquerading as a provider outage; it still surfaces an
error frame since the stream is open.
- Lab ↔ outcome correlations: hedge faint-tier pairs ("a faint hint, if
anything … too small to lean on") so the narrated confidence never outruns the
effect, matching the daily engine.
- Reminder sweep: mint the plan-review reminder and clear the plan's reviewDate
in one transaction so a half-applied write can't duplicate the reminder.
- Fold the two raw provider-fallback runners onto one shared chain walker.
Design / accessibility:
- Lift sub-44px tap targets to the 44px mobile floor (suggested-action card,
Coach bubble affordances), brighten the resting timestamp clock for non-text
contrast, and route the lab chart height through the shared constant.
- Replace ad-hoc arbitrary type sizes with the scale token and static size-11
icon buttons with the named icon-lg variant.
- Settings: add the missing About card-header descriptions, normalise the
low-stock numeric widths, and relax the notification-status rows from nested
cards to a divided list.
Housekeeping:
- Drop three unused exported types (and the now-orphaned source const), re-stamp
v1.21.5 comments to v1.22, and register the live-judge eval harness as a knip
entry so the script-only module resolves.
Add three per-user AI settings, all configured in the app (no new env vars),
behind one migration (0198):
- Response timeout (seconds). A per-user upstream timeout threaded onto the
provider call. A local/self-hosted backend can take more than the legacy
60 s default to load a model on the first request, which timed the Coach
out before the first token. Defaults to a generous ~180 s when unset;
validated to 10–600 s.
- True token streaming for the local OpenAI-compatible client. The client now
POSTs with stream:true and parses the SSE delta chunks, emitting tokens as
they arrive, with a per-idle-gap timeout instead of a whole-call ceiling and
a graceful fallback to the buffered path when a server cannot stream. The
Coach route runs the provider call inside the response stream behind a
keepalive heartbeat so a reverse proxy no longer idle-drops the connection
during model load or generation. Grounding, refusal, and sentinel-stripping
still run on the complete reply before any token reaches the client.
- Dedicated document-scan (Lab-OCR) provider. Off by default — the OCR path
uses the main provider chain. When enabled, lab-report processing resolves a
separate provider/model/key, with a hint when the chosen model is not
vision-capable. The new key column is AES-256-GCM at rest and registered in
the encrypted-columns registry and the rotation script.
i18n: EN + DE translations for the new Settings → AI strings (other locales
carry interim copies to keep locale parity green).
Feed the user's own usual blood-pressure range — the median plus or minus
MAD band, computed from the readings already in the snapshot — into the Coach
context with a clause to quote those bounds verbatim, so a band is never
invented from window means. Thread the stored first name into the prompt and
surface it sparingly on roughly one turn in three, never as a rote greeting.
Add the context-layer rule that names the relevant context before a
suggestion, a single-chart-token allowance that works on every provider, and
a per-turn opener hint.
Wire the already-shipped suggested-action SSE frame to render: the streaming
hook collects it and the message thread shows the action card, mirroring the
reminder-suggestion path. Extend the eval golden set with band-verbatim,
chart-token, and no-overclaim cases, and pin a red-team case proving the
chart-token syntax cannot smuggle a dose past the outbound screen.
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.
Capture the casual "remember this / remind me about X" utterance the Coach
used to drop. The model emits a provider-neutral `---REMEMBER---` sentinel
that the chat route strips inline on EVERY turn — so a short conversation,
where the request usually happens, no longer waits for the long-chat memory
worker. The note is the user's own explicit request, so it is stored
silently as active; a validated closed grammar (ISO date, relative +Nd/+Nw,
or a context cue) sets the trigger, and a malformed block is dropped.
Surface the stored reminders two ways. A snapshot recall sub-block injects
near, overdue, and already-surfaced reminders so the Coach references them
unprompted next turn. A daily sweep flips overdue reminders to due and
mints a one-off review reminder from a plan whose review date has passed,
finally activating the plan review-date column. In-app surfacing only here;
push delivery follows later.
Also generalise the propose-then-confirm action card: a closed
`---SUGGEST-ACTION---` allowlist (a preventive-care item or a reminder note)
rides an additive SSE frame. Nothing is created until the user confirms.
Thread the rolling early-detection pass and the labs -> outcome pass through the
correlations route and the coach correlations reader, both of which already
build the same daily series. The route response gains an optional `emerging`
block (recent-window pairs not yet established, flagged provisional) and a
`labCorrelations` block; the coach reader gains matching `emerging` and
`labDrivers` fields. Regenerate the OpenAPI contract for the new response shape.
The bottom-right launcher opened a blank new chat on an unread proactive
message instead of the thread the Coach wrote. Return the owning
conversation id from the nudge-status endpoint, have the launcher open
/coach?c=<id> on the unread path, and stamp the same deep link on the push
metadata so the notification lands in the exact conversation rather than
relying on a most-recent heuristic.
The comprehensive insight that feeds both the daily briefing and the
insights trend narrative is a single reasoning-heavy generation over the
full feature snapshot. On a large account it runs past the provider
client's fixed 60 s timeout and is aborted mid-stream, so the chain
reports an all-failed outcome, no cached block is written, and the
surface falls back to its static placeholder on every visit. The warm
paths bounded the same generation tighter still (45 s) and counted the
failure with no observable signal, so the blank state was permanent and
silent.
Make the per-request upstream timeout configurable
(CompletionParams.timeoutMs, default 60 s for every existing caller) and
raise it to 120 s for the comprehensive surface only, across all three
generation paths: the on-demand regenerate, the on-demand warm, and the
nightly pre-generation. Raise the warm-pass budget to 130 s so the
provider's own timeout governs a genuine completion rather than clipping
it early. Annotate the comprehensive failure in both the generator and
the nightly loop so a generation that keeps failing is queryable instead
of leaving the surface empty without a trace.
Hotfix: the Coach and daily briefing failed for ChatGPT-provider accounts —
a provider tool-call rejection surfaced as a 500. Provider failures now
degrade gracefully, the Codex tool-call wire format is corrected, and the
provider error body is captured for diagnosis. Also: the thinking bubble
shows only the animated dots.
A Codex backend 400 on the richer Coach tool-call request (and the daily
briefing) propagated out of the provider chain runner unwrapped: a 4xx other
than 401/403/429 was not classified as a hard provider failure, so it bypassed
AllProvidersFailedError and rethrew from the chat route as an HTTP 500. Plain
status-card completions, which never send a tools array, were unaffected.
Harden the failure path so a provider error can never surface as a 500:
- Treat any 4xx a provider wire returns as a hard failure so it cascades and is
wrapped in AllProvidersFailedError. InsightSchemaError (the strict-JSON 422
surface) stays the only non-hard class, so that diagnostic is preserved.
- The chat route now also classifies a tagged provider error that reaches its
catch unwrapped and emits the graceful coach.provider.* SSE frame instead of
rethrowing. Only an untagged error keeps the 500 + error-reporter path.
Make the Codex 400 diagnosable: fold the redacted upstream response body into
the thrown error message and the chain wide-event, so the field the backend
rejects is visible in logs (it was previously dropped).
Fix the Codex request shape behind the tool-call 400:
- Send the required strict flag on each Responses-API function tool.
- Replay prior assistant turns as output_text, not input_text, per the
Responses API multi-turn contract — the violation only surfaced on round two
of the tool loop, which is the path that broke.
Codex-only; the OpenAI, Anthropic, local and mock providers are untouched.
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 metric-page "Coach read" strip and the unscoped-hero seeded opener are
Coach surfaces, so both routes now call requireAssistantSurface("coach")
alongside the insights module gate. With the Coach turned off they return
the same refusal every other Coach route does, instead of lingering as a
"Coach read" line while the assistant is disabled. Restores the coach
route-gate inventory invariant.
Replace the hidden composer prefill with a visible scope affordance: when
the Coach is launched narrowed to a metric, the hero shows a scope pill
naming that metric plus a tappable seed question, and the drawer sources
rail surfaces the same scope line. When the Coach opens unscoped, resolve
today's most notable derived signal server-side and offer it as a tappable
opener; fall back to the neutral greeting when no signal crosses the gate,
so the blank box is never cold and never fabricated.
Add an internal GET /api/insights/coach/seeded-question that reuses the
briefing's derived-signal detector to select the opener server-side; the
client renders the resolved DTO.
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 post-hoc numeric verifier only graded the tool path, so local /
no-tools providers got no grounding net. Grade the no-tools prose
against the snapshot the model was shown — its structured sections,
which already carry the correlations-snapshot block — and flag any
cited number that traces to no snapshot leaf. Non-blocking: the count
is annotated under coach.prose.number_unverified and the unverified
token soft-stripped, never a stream-killer. Only runs when the full
figures were delivered this turn; a cheap follow-up has no fresh set
to grade and no-ops. Tool-path behaviour and tolerance unchanged.
The correlation discovery matrix gained two non-MeasurementType channels
(medication compliance, symptom severity), but the Coach get_correlations
reader still filtered its measurement query by hand and never built the new
channels. The channel keys leaked into the Postgres enum cast and threw for any
user with medication or illness data.
Extract the route's two channel-series fetchers into a shared module
(correlation-channel-series.ts) so both consumers build the channels identically,
then wire the reader to derive its type filter from discoveryMeasurementTypes and
fold the fetched compliance + symptom series into the discovery input. The reader
now humanises the channel keys to "medication adherence" / "symptom severity".
Render daily medication-compliance rate and illness symptom-severity as
first-class series in the FDR discovery engine, so the adherence-dip →
symptom-flare link (and compliance → vital drift) can finally surface.
Compliance pools every active medication's dose-history ledger into a per-day
taken/(taken+missed) rate, re-keyed to the user's display timezone. Symptom
severity reads the illness day-log functional impact, zero-filling healthy days
only across real episode spans so a user with no episodes yields an empty
series rather than a constant. Both flow through the existing n >= 20, BH-FDR,
effect-size, and shrinkage gates unchanged; a sparse series degrades to absent.
Each channel forms its own metric family (no self-lag tautology) and keeps the
association-not-causation framing. Add discoveryMeasurementTypes() so every
caller drops the non-measurement channels before a Prisma type filter.
The Coach may point at a published /learn guide, but only a slug in the
catalog. That was a prompt instruction with no enforcement — a model could
hallucinate /learn/lower-your-cortisol and ship a dead link. Add a deterministic
post-filter on the assembled reply that keeps a published slug verbatim and
strips any reference whose slug is not in the catalog, tidying the prose around
the removed link. Makes the catalog's impossible-by-construction claim an
enforced guarantee.
Each retrieval tool re-scoped the snapshot to a single source, so its cache key
never matched the inventory's full-source build — a four-tool turn paid four
extra full snapshot builds on top of the inventory's. Thread the inventory's
probe scope to every tool so a per-tool read lands the one cache entry the
inventory already primed, collapsing the turn to a single build (a window
override still gets its own correct build). Raise the loop's round cap from two
to three so a sequential cross-metric why-chain isn't starved; the per-round
token budget is unchanged and the absolute ceiling tracks one above so the
final round still forces prose.
The tool-mode path dropped the launch scope's sources: the inventory probes the
full source set, so a Coach opened from a metric page saw the whole inventory
and could roam, while only the no-tools path honoured the narrowing. Inject a
one-line FOCUS hint naming the launched domain(s) into the tool-mode user turn
so the model prioritises that metric and fetches its figures first, with every
other domain still reachable if the question leads there. Empty on a generic
open, so the prompt prefix is unchanged on that path.
The daily AI-token gate was a flat 25,000/day for every provider. That cap
exists to bound the OPERATOR's API bill, but a ChatGPT-OAuth (Codex) or BYOK
chain egresses on the USER's own plan/key and costs the operator nothing, so
gating it on the operator-cost ceiling is wrong. A single gpt-5.x reasoning
turn legitimately reports 20k-40k gross total_tokens (re-sent system prompt +
inventory + tool defs per round + hidden reasoning, summed across rounds), so
one or two turns exhausted the flat cap and locked the user out of a plan they
pay for.
Classify the chain's cost owner by its primary provider via resolveDailyCap:
an admin-openai primary (operator pays) keeps the operator-cost cap; every
user-egress primary (codex/openai/anthropic/local) gets a generous
abuse-only ceiling. Threaded into the Coach chat gate and both OCR-extract
modes.
Raise the operator-cost cap 25,000 -> 200,000 so the operator-key path also
survives a normal day of reasoning turns, keeping gross-token accounting
rather than reworking the reconcile math.
Subtract cached input tokens at reconcile: the Responses-API gross total still
includes prompt-cached input the user did not re-pay for. The codex client
already parsed cached_tokens; sum it through the tool loop and bill
total_tokens minus cached.
The Daily Briefing strips any number absent from its server-computed
figures; the Coach's tool path had no equivalent, so a transcription or
paraphrase drift (a tool returns systolic 128, the reply says ~138) could
ship. Collect the numeric leaves from every present tool result this turn,
extract the numbers the reply asserts, and soft-correct any that match no
fetched figure to a neutral placeholder — annotated, non-blocking, and a
no-op on a qualitative turn or the no-tools path where there is nothing to
grade against. The bounded retrieval loop now returns the present results'
payloads so the check has an authoritative figure set.
Thread the request abort signal through runCoachToolLoop into each
per-round completion so a mid-generation client disconnect tears down
the upstream call instead of paying the full token cost. Completes the
no-tools-path wiring to cover the tool-retrieval path as well.
Regenerate the OpenAPI spec for the trimmed OCR-capability reason enum.
The Coach SSE turn ran the provider call to completion before the stream
existed and never wired it to the request's abort signal, so a mid-generation
client disconnect still paid the full upstream token cost. Thread an optional
`signal` through CompletionParams and singleUserTurn into each client's
safeFetch (composed with the per-call timeout via AbortSignal.any), and pass
`request.signal` from the chat route's no-tools path. An early disconnect now
tears the upstream request down instead of generating into a closed
connection. Omitting the signal leaves behaviour unchanged (timeout-only).
buildComparisonSnapshotForUser read a user's entire measurement history
per type with no date floor, then fed each series to summarize(). The
snapshot only consumes avg30 / avg30LastMonth / avg30LastYear, and the
widest of those reaches into the [365, 395)-day window (ageMs < 395 days
in meanOfWindow), so nothing older than 395 days can change a result.
Add a 400-day measuredAt.gte lower bound to every per-type read in both
copies of the builder — the page-blocking POST /api/insights/generate
handler and the shared comprehensive-generate path the nightly
pregenerate cron drives. The fan-out runs all seven snapshot types via
Promise.all, so on multi-year accounts the unbounded scan was tens of
thousands of rows per type. 400 days keeps a 5-day floor over the
strict-less-than 395-day reach.
The OpenAI client pinned `response_format: { type: "json_object" }` on every
call. The Coach tool loop's forced-final round runs with `tool_choice: "none"`
and expects plain prose, but JSON mode coerced the reply into a JSON object —
the user saw a JSON blob or an empty reply instead of the coach's answer.
Send `response_format` only when the caller opts in with `responseFormat: "json"`
and no tools are present, mirroring the Anthropic client's prefill gate. The
JSON-consuming callers that relied on the implicit mode (insight generate +
briefing retry, medication extraction, the connection-test probe) now pass the
flag explicitly; the prose Coach path and every tool round stay out of JSON
mode. Codex already omitted the flag and is unaffected.
Marc-André Bombeck