The opt-in timeline module gets its page (#613). At 768 px and up the
record's lanes (life, conditions, allergies, medications, vaccinations,
doctor and procedures, labs, documents) are drawn in one SVG on a shared
time axis, with a year, month or week grid, open periods ending in an
arrow, a dashed lead-in where a start is unknown, dose marks and pauses on
the medication they belong to, a Today line and a selection line. Up to
three neutral value lines run below as monthly means, chosen in a menu.
Recharts stays for every value chart; this surface is plain SVG like the
heatmaps.
All geometry is pure (timeline-geometry.ts): window, scale, row packing
and label placement through one occupancy map, so no label overlaps
another label or a bar, none runs past the card edge, and labels that do
not fit are left out rather than squeezed. The width comes from a
ResizeObserver, so a docked day panel re-runs the layout.
The bar under the chart names the selected month's entries as chips, the
month's means and "Open 3 Jan.", which puts ?day= in the URL for the day
layer. The chart is one tab stop: arrows move the selection by a day, a
month or a year with the zoom, Home and End jump to the ends, Enter opens
the day. A visually hidden table lists every entry for screen readers.
The legend says once that stacked means at the same time, not cause and
effect.
Below 768 px the timeline is a chronicle, newest first by month or year,
with an Ongoing block for what has no meaningful start, rails beside the
rows an episode or course spans, and empty stretches named as such.
Switching the module on in Settings opens the readiness inventory: each
lane carries, is thin or is empty, with one link per gap and the verdict
as a count. The same inventory sits as a dismissible card on the timeline
while a gap is open, and under Layers as "Data coverage".
Life events are entered in a sheet (title, kind, a date to the day, month
or year, an optional end, an optional note) from the timeline, the
capture picker and the dashboard's add menu; one surface line maps the
capture kind to the timeline module, and it is offered in one's own
record only. Deleting asks first.
Server routes are built in parallel; the e2e journey answers them with the
contract's shapes. Copy in all seven locales; the timeline and lifeEvents
release-pending prefixes are gone.
Land every file the day view, the timeline and life events share before
any of them is built, so the server, the day view and the timeline can be
built side by side without editing the same file (#613).
Schema and migration 0387: LifeEvent with a short category list, calendar
start and end dates, a day/month/year precision, encrypted title and note,
a soft-delete tombstone and an index for the per-user live list. Every new
column is annotated for the column-reader sweep. Life events travel in both
backup purposes with their two ends in one file, are wiped with the
account, and are registered for key rotation.
src/lib/day/contract.ts carries the constants and wire types for
GET /api/day/{date}, /api/day/index, /api/timeline, /api/timeline/readiness
and the life-event routes, free of Zod so the navigation chrome can import
it; the schemas beside it feed the routes and the published contract. The
Coach and MCP tool name get_day is reserved there, and life events are
listed as the one section no model ever sees.
The opt-in timeline module, its navigation entry, the day-section and
timeline-lane surfaces, the day and timeline query keys (evicted by every
record data bundle), and stub routes that answer 501 behind their
admissions. The four cross-section reads declare the whole record for now;
the life-event list is a profile read, and life events join the profile
sharing domain and its consent copy in all seven locales. The day,
timeline and lifeEvents message namespaces carry their base copy as
release-pending keys.
The aggregate bundle cap moves to 4400: the branch already measured 4365
against 4335, and the new copy adds 10 KB.
A dose can now name a vaccine the catalogue does not list. The person
defines it once (a name, the diseases it protects against from the
catalogue's antigen list, the series length and the booster interval) and
logs doses against it; such a dose counts into each listed antigen's
series, settles a booster reminder keyed to one of them and offers a
booster, the way a catalogue combination does.
One resolver (resolve-vaccine-entry.ts) now answers for every consumer
that asked the catalogue directly: the series, the satisfy matcher, the
booster mint, the dose DTO, the doctor report, document links, the
upload suggestion, MCP search and the client's info sentences and
booster offer. The catalogue wins when a dose carries both.
The custom routes resolve the record through requireRecordAuth (list at
READ, create at WRITE with the actor-keyed write bucket, edit and remove
at MANAGE with the C4 overwrite audit) and join the sharing guard, the
MANAGE matrix and the activity feed. Removing a definition tombstones it
and lets go of its doses, each keeping a name. Definitions travel in the
backup and restore before the doses that name them; the dose form picks
them, adds one without leaving the form, and the page lists them for
editing. With the last contract stub implemented, the 501 helper and the
not_implemented code leave the tree.
The nightly dense-intraday fold scanned Apple Health rows only, so the
per-minute heart rate a Health Connect import writes for the last 90 days
never aged into hourly means and every new export added another quarter
of raw samples.
The fold now walks each fold source in turn, Apple Health first and
unchanged, and folds Health Connect samples into hourly stats: rows under
their own source, deleting the raw rows outright. The folded_window rule
covers both sources for the hour window and looks a covering row up under
the sample's own source; the day window stays Apple Health only. The
Health Connect importer applies the same rule to raw samples, so an
export that still holds folded minutes does not put them back.
- Load each settings section on its own: the section route imported all
twenty-one statically. A preload starts the chunk beside the record
gate's read, and the loading state paints the settings card shell.
/settings/[section] goes from 611 to 403 KB gz.
- Take Zod out of the shell every route shares: the account-access parse
run on each boot is plain TypeScript now, held to the published schema
by an equivalence test over good and broken blocks. The canonical unit
table moves to its own module, so the display transform no longer
pulls Zod in either. Layout entry 199 to 136 KB gz; /insights 369 to
304, /medications 428 to 365, /labs 400 to 337.
- Open a saved Coach conversation at its last answer: an instant jump
instead of the smooth scroll that lost the end, then follow late
layout (charts, tables) for a few seconds until the reader scrolls.
- Show the document archive as a month grid of preview tiles, two
across on a phone and three or four on a desktop, with the month
headings kept.
- Add the admin card for the measurement table maintenance: a status
read on the maintenance route, one calm confirmation, and the run's
state while it is queued, running, finished or stopped.
- Re-base the bundle budget: /insights at 304, /settings/[section]
watched at 403, aggregate cap 4335 with the reason written down.
A guardian with a fresh second factor mints a one-time handover link
(hlp_ token, HMAC hash stored only, 1/7/14 days, at most one open per
profile, withdrawable) with a proposed access level per guardian: end,
view only or manage, view only by default. The link is shown once with a
copy button and a QR code; nothing is mailed. The panel sits at the end
of each managed-profile row and hints when the person is under 16.
The person opens /claim/<token>, sees a minimal preview (name, expiry,
who keeps which access, no health data) and chooses a username, a
required email and a password under the registration policy. The claim
is one transaction under the managed-profile lock: the token is
consumed, the credentials are set, the marker is cleared, every pending
invitation the record offered is withdrawn, each guardian's access is
set to its proposal, the disclaimer, onboarding and AI consent are
reset, and every step is audited on the record and on each guardian's
own account. A failure anywhere leaves the profile managed and the link
unused. Each guardian is notified on their own channels.
The new owner then sees each guardian's access on the first screen after
signing in and decides finally; until then the proposal holds, and the
decision waits at the top of Shared access. A guardian whose access
moved since the claim is left alone. The same screen points the owner
at their own notification channels, since reminders no longer reach the
guardians.
Both anonymous routes refuse a single-sign-on-only instance, refuse a
live session before spending the per-address rate limit, check the link
before probing names, and answer one 404 for every unusable token. The
token travels in request bodies only; hlp_ joins the redaction and
secret-shape rules and /claim/ the path-secret registry. Usernames
starting with managed- are reserved. The session-surface and acting-
account guards list the new surfaces with their reasons.
- Publish timezone, glucoseUnit and a features block on the account
payload; glucoseUnit reads as the closed pair the contract names, and
features.trackIntake tells a separately released client that
medications take the record-only switch.
- Refuse a new dose for a record-only medication with
medication.intake.notTracked on every dose-writing route; the bulk
route reports it per entry as intake_not_tracked, and correcting an
already resolved event stays open.
- Answer passkey sign-in failures by name instead of a 500:
passkey.challenge.expired, passkey.unknown, passkey.response.invalid
and passkey.verification.failed, each with an audit row.
- Carry one account-wide adherence figure in meta.aggregate on the
batched compliance read, weighted by expected doses, and accept
?days=30|60|90|180|365 for a report window.
- Accept ?days=30|90|180|365 on the mood insights read so stability
covers the period shown, and name the window it covers.
- Keep only the reminder that announces a dose off APNs when the phone
owns medication reminders; follow-ups for a dose still open are
pushed again, marked by a followUp flag the reminder cron sets.
- Document which batch validation issues belong to an entry and pin it
with a test that splits and resends a batch; publish rejectedFields
items as ValidationIssue.
Fetch the Open-Meteo air-quality feed (CAMS, domains=auto) with the weather:
17 hourly variables folded into local days by fixed rules (means and maxima
only with 18 of 24 hours, ozone as the highest 8-hour running mean, UV only
with the midday hours), a value the feed did not cover stored as null, never
as zero. Requests are cut into 90-day chunks, newest first, and chunks before
mid 2022 ask for the eight pollutant and index variables only. An air-quality
failure never costs the weather row; the day stays unfetched and the nightly
gap fill (up to 90 days per account, newest first) asks for it again.
Every Open-Meteo request asks an instance-wide budget kept in Postgres first
(500 a minute, 4000 an hour, 8000 a day, weighted by the hosted pricing
rule). A refused request is not sent and the run ends as done with
budget_blocked. OPENMETEO_AIR_QUALITY_URL and ENVIRONMENT_AIR_QUALITY_DISABLED
are honoured; the account switch lives on PATCH /api/environment/preferences.
The home, each dated location period and each stored day keep their coarse
location sealed as one value under healthlog/environment-location/v1. The
writers write the sealed value only, the readers open it and fall back to the
readable columns for rows the free-text encryption backfill has not reached,
and the backfill now seals all three and clears the readable columns. The
backup carries the location readable in a portable file and sealed in a
disaster-recovery file; a restore seals either under the receiving key.
Three correlation channels join the environment family (PM2.5, the ozone
8-hour high, the day's highest pollen count), read through the averaged
same-day window and left empty while air quality is off. The Coach and MCP
gain get_environment: module-gated, clamped to the lookback limit, no
coordinate or place name anywhere, with provenance and the attribution
lines. The settings section gets the switch, the coverage and the newest
day's values; the dashboard shows a quiet chip on a day with high pollen,
a warm night or very poor air. Copernicus and Open-Meteo are credited next
to the values.
Upload the ZIP the Android Health Connect app writes and import its
`health_connect_export.db` in the background, the same way an Apple
Health export is imported: streamed to disk with a SHA-256, capped at
1 GiB, one import per account, a job row of kind `health_connect` that
the shared reconcile cron and staging sweep now look up on its own
queue.
The worker extracts the database (4 GiB ceiling, zip-bomb checks) and
opens it read-only with `immutable=1`, `trusted_schema=OFF` and
`query_only`. A view in place of a record table refuses the file,
columns are found by name, and schema versions below 9 are refused.
Records are read in batches of 500 and aggregated in SQLite: steps,
energy and distance as one total per day from the app the person's
Health Connect priority list ranks first, heart rate per minute for 90
days and as hourly means before that, sleep stages with the unknown
stage counted only in sessions without real stages, workouts, cycle
days, water and micronutrients. Apps whose integration the account has
connected are left out, and a reading already stored under another
source is skipped. Rows carry source HEALTH_CONNECT, `hc:<uuid>` or the
`stats:` ids, so a second import of the same export writes nothing.
Both staged files are removed on every way out; the job result holds
counts per type and per app only. Settings gain a Health Connect card
with the export steps, progress and the outcome, in all seven
languages, and the import is documented in
docs/integrations/health-connect.md.
The HRV page's second chart reported its visible window into the same
stat-strip slot as the first, so the two replaced each other on every
render until React stopped it and the chart failed to load. Only the
primary chart reports the window now; the strip describes that measure.
The workout edit sheet no longer shows the "leave empty if you just
finished" hint, which is about logging and not about a stored start. On
the Apple Health card a type's name reads as the row's content above its
arrival line, with room between rows.
MCP `search` and `fetch` link a metric as `/insights?metric=<id>` and a lab
value as `/labs?analyte=<name>`. Neither page read its query, so every link
opened the overview or the full list.
`/insights` now resolves the id server-side, in whichever spelling the
result carries (a Coach source key such as `hrv` or `bp`, a signal or
metric-status key such as `GRIP_STRENGTH`, a measurement type, or a
sub-page slug), and redirects to the metric's page, or to its value list
when no page focuses it. An id it cannot place renders the overview as
before.
`/labs` asks for the newest reading stored under the exact analyte name
and opens its marker's page; a name with no reading keeps the list and
drops the query.
iOS and watchOS 27 add `HKQuantityTypeIdentifierHeartRateVariabilityRMSSD`
(Apple's symbol `c:@HKQuantityTypeIdentifierHeartRateVariabilityRMSSD`,
available from 27.0). The live batch and the export.zip import now store it
as `HRV_RMSSD`, the type WHOOP, Oura and Polar already write, in
milliseconds, mean-aggregated and flagged privacy-sensitive like SDNN. The
accepted range is 1 to 300 ms.
RMSSD ranks on its own `hrvRmssd` ladder in the SQL source collapse, so a
day holding it from Apple Health and a strap resolves to one source
instead of a name tiebreak.
SDNN and RMSSD are different statistics and are kept apart once one
account holds both. The HRV page charts each on its own, titled with its
measure, instead of hiding RMSSD behind SDNN. The Coach's HRV section
carries one timeline per measure under `byMeasure` (same section key, so
every reader still finds it) rather than one daily series averaging the
two; the budget pass condenses and sheds each measure's timeline like a
glucose context.
A workout logged by hand could only be deleted and logged again. The
detail page now offers an edit control beside delete for a MANUAL workout
carrying the form's `manual:` id, in one's own record. It opens the log
sheet on the stored values and saves by re-posting that id through
`POST /api/workouts/batch`, which already applies such a re-post as an
overwrite of that one row. No new route.
The overwrite nulls every overwritable column a re-post leaves out, and
the form has no fields for heart rate, steps, elevation or pauses. The
edit therefore sends those back as stored. A field left as shown sends the
stored value rather than one re-parsed from its display, so saving an
untouched edit keeps the start's seconds and a distance shown in miles at
its exact metres, and answers `duplicate`.
The detail read's `avgHr` / `maxHr` can come from a same-session twin;
the read now also serves the row's own `storedAvgHr` / `storedMaxHr`,
which is what the edit sends back.
The Apple Health card listed each type's newest sample. A type the phone
only hands over on "Sync all" can carry a reading from this morning and
never have arrived in the background, so the sample time could not answer
whether a type flows on its own.
The batch route's per-type ledger now records, in one upsert per batch,
when each Apple Health type last arrived, the trigger that carried it
(including the new `manual`), and when a batch last brought a new or
updated sample of it. Duplicate-only re-sends move the arrival but keep the
last new value; scoped credentials and MANUAL rows write nothing, the same
rule as the sync checkpoint. A ledger failure leaves a warn line and never
fails the ingest.
`GET /api/integrations/healthkit` lays `lastReceivedAt`, `lastTrigger` and
`lastNewSampleAt` over each `metricFreshness` entry (null for a type no live
sync has carried, absent on the workouts entry and when the ledger read
failed), and the card shows them as a second line per type.
The per-type newest-sample read walks live types through
`listLiveMeasurementTypes` and probes each type's newest row instead of
grouping every live row of the source.
A catch that drops what it caught is where the silent nightly failures
started. Every `catch` and `.catch()` under src/lib/jobs now rethrows,
fails the job, writes to a ledger an operator reads, counts into the run's
failure facts, hands the error back to its caller, or logs at warn under a
stable action. The enqueue helpers that swallowed a failed send (briefing,
status, narrative, morning digest, document index / summary / thumbnail,
workout insight, boot-time sweeps), the Coach nudge's provider fallback,
the workout and reaction-line cleanups, the advisory-lock release, the
backup attempt bookkeeping and the cycle reminder's dedupe reads now leave
a warn line instead of nothing or an info annotation.
`error-level-discipline-guard` holds the rule. The catches that stay
silent are listed with their reason (the pgboss readers' documented null on
a web-only deployment, the key-ring trial, the restore drill's per-account
result, an already-deleted Telegram message); a new silent catch fails, an
entry that no longer matches fails, and each entry is shown to be
load-bearing by removing it.
A Coach turn cut short by its token, time or round budget writes
`coach.turn.budget_stop` at warn.
The nightly briefing warm completed every night and read "all-failed",
because one run event held every account's annotations and the last
account won. Each candidate now runs in its own wide event and the run
reports every outcome through `reportJobRun`, so ok, dead sign-in,
withheld and failed accounts show side by side.
A dead Codex refresh token threw a bare error with no status, so the chain
read it as a network failure: the health ledger recorded hard_failed, no
"reconnect" hint appeared, and every night tried the same token. The
refresh now throws `CodexRefreshError` with a 401 for a dead grant
(invalid_grant / invalid_refresh_token on a 400 included), as do a missing
or undecryptable stored credential. The ledger records auth_failed, the
chain marks the primary credential expired, and the nightly pass reports
the account as auth_failed without queuing a retry.
A briefing the outbound screen withheld (a causal claim) failed outright,
and the 45-minute provider retry then asked the same question eight times
a night. The generator now makes one bounded repair that names the broken
rule and keeps the repaired payload only if it passes the same parse,
grounding and screen; a withheld outcome queues no retry.
A provider that keeps failing is paused: from five consecutive hard
failures the skip window starts at 30 minutes and doubles per further
failure, capped at a day. A paused provider is walked last and tried again
when the window lifts; one success resumes it. The operator card shows how
many accounts it is paused for and until when. After a 5xx from a
non-canonical OpenAI-compatible endpoint the client asks the free model
listing, and a configured model the endpoint no longer offers is named in
the error, on the hop line and on the card.
Also:
- The tiered context's live day band read `measured_at AT TIME ZONE tz`,
which treats the stored UTC as local time; a far-from-UTC reader's
evening readings landed on the next day. It converts from UTC first now.
- Google Health intraday heart rate re-reads two hours per sync instead of
a day; daily summaries and sleep keep the day (#1023).
- The first filtered daily read that answers 400 and triggers the
snake_case retry is recorded as a note, not an error (#1023).
- The single derived-score read goes through the derived cache with
stale-while-revalidate, like the batch beside it.
A wide event carries one action and the last annotation wins, so a hop
that failed before the next provider answered, one failed account among
six, or a caught error the code carried on past was either a meta key on
someone else's info line or nothing at all. `emitSignal` writes one extra
line under a stable action and level, joined to the surrounding event by
request and trace id; `logCaught` / `caughtAs` are its warn-level shape
for a catch that degrades on purpose.
Every failed pg-boss run now writes `job.run.failed` at error with the
queue and how many runs of it in a row have failed, counted from pg-boss's
own rows (`readConsecutiveRunFailures`). `reportJobRun` takes a fan-out
pass's whole candidate list: an all-failed run is `job.run.failed`, a
partial one `job.run.partial` at warn, and the run reports `all_failed` in
its facts so a completed night with nothing done still counts toward the
streak. The repeated-failure alert keys on that one action and number.
Retention is per queue now. `failureReaderRetention` refuses a queue
retention under 96 hours (the 72-hour reader window plus a day), and a
guard refuses any `deleteAfterSeconds` that is neither that helper nor a
literal at or above the floor.
A refusal the request was meant to get (any error carrying a 4xx status)
is recorded at warn instead of error. Expired-token 401s were most of the
error lines and hid the real failures between them.
The nightly folds soft-deleted every raw Apple Health sample they folded
into an hourly or daily stats row and kept it for 75 days. Nothing ever
read those rows as deletions; they only held a re-upload of the sample
off, and they were most of the measurements table and its indexes.
Ingest now refuses such a re-upload directly: a raw sample of a dense or
mean type, old enough to have been folded, whose hour or day a live
stats row covers, is a duplicate with reason folded_window. The batch
route and the Apple Health export import apply the same rule. With that
in place the dense retention and the daily-mean consolidation delete the
raw rows outright, and a new compaction-tombstone-purge job removes the
backlog: 5,000 rows a batch, one account at a time under the restore
lock, a short pause between batches, resumable because the predicate is
idempotent, queued at every boot and continuing itself while it makes
progress. A person's own deletions are never in its predicate. The sync
feed leaves compaction tombstones out and a restore does not write them
back; all three classify through the same function.
The batch route answers an exact re-sent sample without a transaction:
one read over the batch's sample ids, live or deleted, decides what the
reconciler would have decided, at the same point in the loop, so every
status, reason, counter and the cross-source merge stay as they were. A
batch of duplicates only no longer queues PR detection, a reminder sweep
or the detection audit row. Caches are evicted only for a foreground or
manual sync or a batch that wrote a hand-entered reading, and marked
stale otherwise; the targets cache follows the same split.
Also:
- POST /api/admin/maintenance/measurements queues VACUUM (ANALYZE) and a
REINDEX INDEX CONCURRENTLY per index, largest first, on a connection of
its own; it refuses while the purge runs, drops invalid leftover copies
and stops at the first failed rebuild. Runbook in docs/ops.
- The pure volume queues keep their finished jobs for 96 hours instead
of seven days, never less than the failure window plus a day.
- work_mem is set per app connection from DATABASE_WORK_MEM (16MB), also
when the statement timeout is disabled.
- The PR-detection fallback tick re-scans only accounts whose readings
or workouts changed since the previous tick.
- Type discovery for the status refill walks the live-rows index as a
loose index scan instead of grouping every live row.
- The host metrics chart polls every five minutes, like its sampler.
- The batch route records per-type HealthKit arrivals.
Two daily series that both follow the season (temperature and blood
pressure, daylight and sleep) correlated strongly with nothing between
them. In a seeded simulation of such a pair the engine surfaced a
finding in 58 % of 400-day runs and 30 % of 180-day runs, and a real
next-day effect under the season came back with the wrong sign.
Every daily pair now goes through seasonallyAdjustedPearson: a linear
trend and one annual harmonic are removed from both series (trend only
under 120 paired days), the residuals are correlated, and the p-value
uses the Pyper-Peterman effective sample size. Shrinkage and the
phrasing tier read the effective size too. BH-FDR and the effect floor
are unchanged. Pairs too short to fit the basis are not tested.
The weather channels are tested once over the mean of the day before
and the day itself against the same day's outcome (lagDays 0), which
pairs the overnight low with the night it shaped now that sleep is
keyed on the wake day. Discovered pairs carry an additive nEff, the
same-day templates are wired, and the matrix skips the weather read
when the environment module is off.
scripts/compare-correlation-findings.ts counts findings per account
before and after, read-only, for the release-candidate dry run.
Land every file the v1.42 work shares before any of it is built, so the
parts built side by side never edit the same file.
Schema and migrations 0379-0386: the HEALTH_CONNECT measurement source,
ImportJob.kind, the air-quality columns and the per-user switch on the
environment tables, sealed environment locations with nullable plaintext,
managed-profile handover links, the per-type HealthKit arrival ledger, lab
unit-conversion provenance, and user-defined vaccines. Every new column is
annotated for the column-reader sweep.
HEALTH_CONNECT reaches every exhaustive list: the source labels, the
read enum (not the write allowlist), the source-priority ladder cap, now
the number of sources rather than a fixed eight, and the write-path smoke
test. RMSSD gets its own priority class and a 300 ms ceiling. The batch
syncTrigger gains `manual`, with its label on the Apple Health card.
Queues for the Health Connect import, the compaction-tombstone purge and
the measurement-table maintenance are registered with stub handlers;
host-metric sampling moves to every five minutes. Environment and work_mem
variables reach the compose whitelist, the production example and the
manifest. The proxy admits the handover link and redirects it at the edge,
and the Health Connect upload bypasses the proxy body limit.
The new routes answer 501 behind their final authentication and are
published in the contract; backup, wipe and key rotation classify the new
models and columns; the seven message bundles carry the base copy. Guards
that list release-pending keys and columns fail once an entry is wired, so
those lists empty themselves before the tag.
Also re-anchor a login-throttle fixture to the wall clock, where its
expiry is compared, and re-base the aggregate bundle cap on a measured
12 KB of new locale strings.
list_metrics declares availability, the Coach-backed reads declare
searchedWindow and available, and get_intraday_pulse declares min and
max per bucket. An integration test validates every tool's real output
against its advertised schema under a strict 2020-12 validator.
The metric-status discovery rows and the search clinical-signal probe
filter deletedAt, guarded for every measurement read in the MCP and
Coach tool trees.
Own-plan turns get 165k tokens, 200 s and 16 rounds, operator turns 55k,
120 s and 8; the final-answer reserve, the concurrent-turn slot and the
step cap move with them.
Codex requests carry a per-conversation prompt_cache_key and a stable
session id, api.openai.com gets the same key, Anthropic usage counts
cache reads and writes in the gross, and local servers report cached
prompt tokens, so the turn budget discounts cached input on every
provider.
While a turn runs the Coach now shows a single row: a brain icon, the
current step in the answer's text size with a shimmer passing through it
and fading dots, and a chevron once there are steps to open. There is no
running clock any more, and the interim table preview with its sparkline
no longer renders under the row; interim tables stay in state until the
answer's own results show them.
When the answer is done the row reads "Thought process · N steps" with
proper plurals, and "Answer needed" while a clarifying question waits.
It never opens by itself, and a row opened during the run closes when
the turn ends. Opened, the steps form a vertical list with an icon per
kind of work on a thin connector line, and a reasoning round shows its
summary under its title.
The shimmer and the dots are a `text-shimmer` utility and a reusable
WaitingText component, both still under reduced motion.
The demo's write block now carries `meta.errorCode: "demo.readOnly"`,
listed in the error-code catalogue, and the Coach answers it with an
honest line instead of the provider-outage copy.
Removes the interim preview component, the elapsed-seconds and summary
helpers, and their message keys in all seven locales.
The Coach loop's final round sent toolChoice "none" without the tool
definitions. With tool_use/tool_result blocks in the history Anthropic
refuses such a request (400), and OpenAI Chat Completions refuses
tool_choice without tools, so every budget, time, cap and no-progress stop
ended in an error on those wires. The final round now carries the tools
with toolChoice "none", which every wire accepts, thinking included.
Codex kept reasoning items as provider state even when the request asked
for no encrypted reasoning; replaying such an item under store:false is a
400. Items are kept only when the request included
reasoning.encrypted_content and the item carries it.
The reasoning dialect cache learned from any 4xx that mentioned
reasoning or thinking (auth, rate limits, model names such as
deepseek-reasoner) and from replay errors, and kept the downgrade for the
life of the process. Learning now requires an HTTP 400 that refuses a
sent parameter, ignores replay errors and the model name, and a learned
downgrade expires after an hour.
remember_fact and propose_plan wrote their rows during the tool round. An
answer that was then blocked, failed or abandoned left the fact in memory
without its note and Undo, and left the plan listed, activatable and fed
into later turns and the briefing. Both are now staged under an id minted
up front and written in the transaction that stores the assistant message,
only when its provenance carries them. A background proposal counts as
offered only once an answer carrying it is stored.
Plan text is model text: ifCue, thenAction and target pass the outbound
dose and risk screen in the person's locale, with their scheduled doses and
medication names, and the injection screen; a trip declines as "unsafe".
The trail route serves recalled facts and the proposal's fact to the owner
whatever the AI capability (only the model-written entries are gated), and
withholds medication facts while the medications module is off.
Accepting a fact proposal is decided under a per-message advisory lock, so
concurrent taps write one fact. Editing a fact re-reads its wording: text
naming a medication moves to "medication", other health wording moves a
non-health fact to "condition", and a health fact the person edited counts
as confirmed.
Marc-André Bombeck