Table refs, step ids, chip ids, a chip's anchor ref, clarification choice
ids and a reused table's source are now validated against their exact
server-minted patterns when a stored reply is read back. Some of them are
written into the model's context on a later turn (the earlier-tables list,
the "keep looking" fetched list), so a stored row edited by hand can no
longer carry text into a prompt through them.
show_result now passes the same scope gate a fresh read does before it
decrypts a stored table: a metric the person has since excluded from the
Coach, or one outside the conversation's scope, answers
unavailable_in_scope and nothing is sent. The list of earlier tables in
the context drops those metrics too, so the model is not told they exist.
The exclusion (the person's own list plus switched-off modules, and no
adherence when medications are excluded) is the snapshot builder's, now
one exported helper both paths use.
"Keep looking" no longer copies the unfinished question into the
server-written context lines. The question stays in the transcript as the
person's own turn; the line only points at it. Lifted into the system
role, whatever the question said would have carried the system's
authority.
A turn now reads its conversation's newest messages once and shares the
rows between the chip, clarification, "keep looking" and repeat-question
checks, instead of three identical reads.
Earlier tables keep their m<k> names once a conversation outgrows the
window a turn loads: the index counts the assistant messages before the
window too, so a name the model read on an earlier turn still points at
the same table.
The backup validation now reads the per-message table ceiling from
results/refs, which imports nothing but types. Reading it from
results/project pulled the tool executor and the message store into the
snapshot builder's import graph, and the free-text sanitiser guard then
walked files that never build a prompt.
A restore is refused before it deletes anything when its transaction limit
would run past three quarters of the job's expiry. At two hours that refused
a same-size replacement of about four million readings. The expiry is now six
hours, which admits ten million over ten million; a dead worker still frees
the account within minutes through the heartbeat, so the longer expiry does
not hold an account longer.
The refusal now names both counts, the readings in the backup and the ones the
account holds now (removed readings included until the nightly clean-up),
since clearing the latter costs time too.
A turn never stores more than 128 KB of table JSON, but a restore accepted
any size in resultsJson or resultsEncrypted and sealed it into the database.
Both are now bounded: the readable form by its UTF-8 size, the sealed form at
twice that, above the ciphertext's measured expansion. A file this release
writes always fits; a larger value is refused like any other malformed field.
The grounding ledger derives differences only between figures of one
payload, so a correct "up 4 mmHg on last week" drawn from two separate
table reads was withheld as unverified. A table of the period before or of
a year ago now reads the current window too, and its summary carries the
current figures and the change (delta and percent change) beside the
earlier ones. A wrong delta is still flagged.
The encryption backfill now also removes the two copies of a practitioner's
contact details that outlived the sealing. An appointment reminder's copy of
the address is cleared, since the reminder resolves it from the practitioner
when it fires. An address-book edit's audit row written before the sealing
kept the old phone number and address in its previous values; those values
leave the row and the changed fields stay named. Rows of a deleted account,
which no per-account job reaches, are scrubbed by the discovery pass itself.
A route whose readable geometry is a JSON null rather than SQL NULL had
nothing to seal but matched discovery every night. The pass now sets it to
SQL NULL so it drops out.
Sealing the practitioner's address left the appointment arm reading the old
readable column, which is now empty, so a booked visit's push lost the address
on booking, rescheduling and restoring a deleted visit.
The reminder no longer keeps its own copy of the address. The reminder tick
resolves it from the owning visit's practitioner when it builds the push and
decrypts it there, so an edit of the address also reaches a nudge that is
already booked. MeasurementReminder.location stays NULL on appointment rows:
booking writes none, a re-anchor clears one an earlier release wrote, and a
backup neither carries nor restores one. A checkup's own free-text location is
unchanged.
A withheld table now leaves a line saying why (module off, or the stored
tables could not be read) and a failed read shows an error row with a
retry, so the Data used count matches what is listed. A table copied from
an earlier answer names that answer's date under its title. The preview
shows the latest twelve periods of a time series, and the truncation note
says the latest rows are kept, which is what the server keeps. The title,
copy and view controls sit above the scrolling table with the title kept
as a hidden caption, and a reply with tables takes the full column width.
The step headers and the related-metric chip read as label: value in all
seven locales, so a metric name no longer sits capitalised mid-sentence.
The "compare with the period before" chip now needs a first reading
before the window's start, the same history check the other history chips
use, and is never offered on an all-time table, which has no period
before it: the table tool reads all time as the current period whatever
it is asked.
Tables are now projected outside the provider's failure path: a
projection defect costs the turn its tables and is annotated, instead of
refunding tokens already billed and dropping the reply.
The at-rest ceiling for a message's tables is applied once, when the
dialog is assembled, before anything streams. A table trimmed only at
write time used to show live and read back as withheld after a reload.
A total's weeks and months are now the sum of its days, labelled as a
total, and a level's stay a mean. All time is read as UTC calendar months
from the rollup tier's MONTH fold, or the same fold of the live table when
the tier has no rows, so a month no longer reads as a mean of daily totals
for a short history and a monthly total for a long one. Months are keyed
by their UTC start instead of being re-read in the user's zone, which
named every month one early west of UTC.
The chart's long ranges had the same shift: tier rows are now stamped at
noon UTC of the bucket's first day, which falls inside the bucket's own
week and month in every zone.
Step length and walking speed keep two decimals, loud-sound events count
as a total in whole events, and HRV counts a night measured by both
estimators once and charts the estimator the person mostly has. The model
summary names what a period's value is and gives a total's range total.
A damaged or foreign-key route ciphertext threw out of readRouteGeometry, so
one bad track answered the workout detail with a 500 and failed the activity
insight job. It now reads as no track with a warning on the request event, and
still never falls back to the readable column.
When the tool loop forces an answer at its round cap, the reply leads
its chips with "Keep looking". Tapping it runs a normal turn, under the
budget gate as ever, with two server-written context lines: the question
that was left unfinished (at most 1000 characters) and what the forced
turn already read, each table by the name show_result takes, so the
continued turn shows those again instead of fetching them twice.
An answer is continued at most once. The continued reply records the
message it continues in metricSource.continuationOf and offers no
further "Keep looking", even when it is forced again; a chip on a reply
that is itself a continuation is refused.
Up to three chips, derived on the server from what the turn read: the
other view of a table with a chart, the period before, a year earlier,
a wider window, and a metric a discovered pattern links to. A chip is
offered only when its read was done this turn and the record holds the
metric; the year-ago and wider-window chips also need the record's
first reading to reach back that far. The model may name chips in a
FOLLOWUPS block, but only to reorder ones the rules already allow; every
label is rendered from the catalog.
A tapped chip resolves against the chips stored on the conversation's
latest reply. "As a chart" and "as a table" are answered from the
stored table without a model call or a budget reservation: the rows are
copied unchanged and the message is tagged providerType "reuse". Other
chips run a normal turn with a server-written context line. A chip that
is no longer current falls back to a plain message.
A setting turns the chips off (absent means on).
A table over time is drawn as a line for a level metric and as bars
for a total, with at most two series in one unit. Category counts get
bars, horizontal above six categories, the top eight and one other.
Fewer than two or more than 400 rows, or no numeric column, stay table
only. show_result's view now counts: table drops the chart, chart turns
an earlier day table into counts per range with a histogram (fixed
widths for the common metrics, Freedman-Diaconis otherwise, none below
ten values).
The method line merged a repeated read by keeping the larger count. With
show_result that could let an earlier answer's count stand over the read
this turn just made. A fresh read of the same source, window and period
now always wins, whichever order the steps ran in, and the two are never
added. An entry that rests only on an earlier table says so ("from an
earlier answer"), including a reused table no step accounts for.
The new catalog string is in all seven locales.
get_metric_table now gets a step like every other read: the domain is
its validated metric, and once the table is in, the window, period and
granularity are the ones the table was built with (after the executor's
defaults). The count is the readings the table folds, taken from the
summary the server computed, so a read past the sixth table still counts.
A step whose call produced a table now names it (resultRef), for the
projected tables of the older tools as well.
show_result gets its own step. It reads nothing new: while it runs it
names no domain, and once the stored table is found it takes the source
of the read that built it and the name the copy carries in this turn. A
table that could not be shown is a failed step with the reason, never an
empty read.
The property test now drives show_result too and checks resultRef; the
coverage test gives each tool the smallest arguments it accepts instead
of passing empty arguments to a tool that requires a metric.
The table shows its caption, scoped headers, right-aligned tabular
numbers and a dash for a missing reading, twelve rows before Show all.
Copy writes TSV and an HTML table together, falling back to TSV, with
formula starts neutralised and separators flattened inside cells.
get_metric_table reads one metric as days, weeks or months through the
chart reader, cut in the user's zone and collapsed to one source per day,
with null for a period without a reading. The model reads a bounded
summary; the full table rides the turn, encrypted at rest. show_result
shows a table an earlier reply of the same conversation fetched, resolved
only against that conversation's own messages. Workouts, labs, sleep and
adherence results project into tables, earlier tables are named in the
context by metadata alone, and result:rN marks are stripped from the reply.
The evidence disclosure under a Coach answer now carries one muted
line: which sources and windows the turn read, how many readings, and
how they were aggregated ("Blood pressure, last 90 days: 142 readings,
weekly averages · Sleep, last 30 days: no readings in this window").
The server builds it from the recorded steps and tables in the request
locale; it holds catalog strings and counts only, never a reading, and
a source that turned up nothing says so.
The tool-mode prompt gains a recheck rule: when the person questions a
figure, name the source and window, read it again (or reuse the stored
table), and correct the answer if the two differ.
Each tool call now emits a running step as it starts and its final
status as it settles: found with a server-counted number of readings,
empty with the reason, or failed. The no-tools path shows one step for
the record summary. Steps carry catalog labels rendered in the request
language, closed-enum domains and windows, and integers only; a lab
analyte, a value or a model-written argument never reaches one. At most
twelve per turn. They persist on the provenance, so a reload shows the
same list.
The conversation window reaches the step so a call without a window
names the one it actually read. The no-tools transcripts gain the
summary step; a new transcript pins found, empty and failed steps ahead
of the first token.
A reply may end with a ---CLARIFY--- block (kind metric, window or
context, 512-byte cap). The server keeps only metric choices the record
holds, drops the question when fewer than two remain, takes window
choices from the presets, screens the question text like any reply, and
never offers a second question right after one. Choice labels come from
the catalog, never from the model.
An answer arrives as clarification { messageId, choiceId? }; it resolves
against the stored question on the conversation's latest message and
adds one server-written line to the next turn's context. The card sits
above the composer, announces politely and takes no focus.
A reply that is only the block, with no question before it, is now an
empty reply instead of falling back to the unstripped text.
A restore of an account with 1.9 million readings, most of them deleted
by the nightly consolidation and still awaiting the purge, was cancelled
in its clearing step: `DELETE FROM measurements` ran past the 60 s
statement timeout every pooled connection carries, and the whole restore
rolled back with a message that named no cause (#1031).
Most of that statement was not the delete. Two columns point into
`measurements` with ON DELETE SET NULL and had no index, so Postgres
scanned `personal_records` and `ecg_recordings` once per deleted reading:
38 of 40 s on a seeded account with 300 personal records. Migration 0362
indexes both, which also speeds up the tombstone purge and account
deletion.
The restore transaction now sets its own statement and idle-in-transaction
limits to the transaction budget with SET LOCAL, and the budget counts
the rows the account holds as well as the rows the file carries. A
rolled-back restore names what the database refused it over (timeout,
lock, constraint, storage, connection, other) on the job row, the
console, the audit row and the wide event.
The streaming hook handles the step, result, followUps and clarification
frames and sends followUp and clarification on the tool route only. The
bubble gains slots for the step list, the tables and the method line; the
thread offers chips under the latest assistant turn only; the conversation
shows the clarification card above the composer and marks a typed answer
as answering it. The tables of a persisted message load lazily when it
scrolls into view, seeded from the stream for the turn that produced them.
The new components render nothing yet.
Adds every string the dialog needs up front: step labels, table titles,
columns and controls, the method line, the follow-up chips and their
setting, the clarification card, and the caption of an answer reused from
a stored table. A key catalog shared by server and client names each one;
a test holds the catalog and the bundles equal in both directions.
GET /api/insights/chat/{id}/messages/{messageId}/results returns the
tables one assistant message read, narrowed to the conversation's owner
like the conversation read, with a table withheld as module_disabled when
its domain's module is off and as unavailable when it cannot be read. A
data read: no AI capability.
The published document now describes every stream frame as the
CoachStreamEvent union, including the suggestedAction frame it never
named, the new step, result, followUps and clarification frames, their
components, the provenance fields, the followUp and clarification request
fields, and the reuse provider type.
Each later piece of the dialog gets its own module, answering nothing for
now: the step builder, the table projection and chart choice, the result
ref marks, the follow-up derivation, sentinel, resolution and continue
chip, the reuse turn, the clarification parse and answer, the method line,
and the four prompt addenda. The turn pipeline calls them where they
belong, so the frames go out in the documented order (step, token,
provenance, result, cards, clarification, followUps, done) and a blocked
turn drops its tables, chips and clarification. With every piece empty
the stream and the prompt stay byte for byte as before.
The retrieval loop takes onCallStart and onCallSettled callbacks, fired
for every call with a turn-wide index; a throwing callback is swallowed.
The trace carries each call's schema-validated arguments (never the raw
string, never persisted), the result says whether the answer was forced
at the round cap, and a seedCalls parameter is accepted but not read yet.
The home location of the environment module was rounded to 2 decimals,
about 1 km, which places a home in a neighbourhood rather than the town the
schema comment promised. The weather archive it feeds is gridded at 9 to
25 km, so the extra precision bought nothing.
Every stored coordinate of the module now goes through the same 1-decimal
rounding (about 11 km north-south, 7 km east-west at 50° N): the home, the
travel periods, the geocoder's results, the per-day weather rows, and a
restore of a file written with finer values. Migration 0361 rounds the
existing users, travel periods and per-day rows; running it twice changes
nothing more. The answers keep their shape, plain numbers. The API
descriptions and the schema comment say 1 decimal now.
A new nullable column, coach_messages.results_encrypted, holds the tables
of values a turn read as AES-GCM ciphertext; only their metadata rides the
plaintext provenance. readMessageResults serves them to the owner, each
table whole or withheld with a reason. The provenance restore learns the
steps, method, table metadata, chips, clarification and the forced-answer
marker, entry by entry against the wire schema.
The column is registered for key rotation, carried through both backup
formats (ciphertext in a disaster-recovery file, readable JSON in a
portable one) and goes with its row on conversation delete and wipe.
Adds the TypeScript types for the four additive stream frames and their
provenance fields, a Zod mirror for the published document held equal to
the types by a type test, and a guard that no newer frame reuses a key the
shipped native client decodes. The chat request accepts followUp and
clarification, inert for now.
The route keeps the front door: auth, the coach capability, the body
read and schema, the rate limit, the locale and the inbound refusal
screen. Everything after it moves into one module per step:
conversation, context, chain, budget, model, reply-guards, cards,
provenance, persist, sse, errors and pipeline. The capability re-check
at the egress site stays owned by the route and is handed to the
pipeline, so the capability inventory still reads both calls there.
The stream producer now writes through a TurnEmitter created inside
createSseStream and passed to the model step, which is where live
progress frames will come from. Nothing writes to it early yet.
No behaviour change: the golden transcripts pass byte-identical, the
existing route tests pass unmodified, and every annotate, audit and
error-code name appears as often as before.
Guards follow the code. The fence call-site check reads turn/context.ts,
the German-default locale ban covers every file in turn/, and the
fenced module-graph test now asserts that turn/sse.ts and turn/errors.ts
reach neither the tool registry nor the snapshot builder. That test
named lib/ai/coach/tools.ts, which stopped existing when the registry
became a directory, so its negative check could not fail; it points at
tools/index.ts now, and a new sanity check fails if the tool route can
no longer reach the path it names.
The GPS track of an outdoor workout was stored readable, and its first and
last points are usually the person's front door. The phone number and address
in the address book of doctors and practices were readable too, while the
note beside them was already encrypted.
Migration 0361 adds workout_routes.geometry_encrypted (the geometry loses
its NOT NULL) and practitioners.phone_encrypted / location_encrypted, plus
partial indexes on the backfill's discovery predicates. A track is sealed as
one binary AES-256-GCM value bound to its purpose; the contact fields use the
same Bytes codec as the note. The practitioner's name, practice and specialty
stay readable, because the picker searches and sorts on them.
Every writer stores ciphertext only: workout batch ingest, practitioner
create and edit, and both restore formats. Readers prefer the ciphertext and
fall back to the old column for rows not yet migrated: the workout detail
(map, splits, GPX), the activity insight's climb figure, the practitioner
DTO behind the address book, visits and vaccinations. The wire shape does not
change. An edit's audit row now names a changed phone number or address
without recording either value.
free-text-encryption-backfill covers the three columns in the same pass,
finding a route through its workout. All three are registered for key
rotation (registry, CLI script, and the in-app rotation). A disaster-recovery
backup carries the contact fields as ciphertext only; a portable export
carries them readable. Workout routes are still not part of a backup, as
before. The old columns are marked for removal in a later release.
Marc-André Bombeck