Commit Graph
50 Commits
Author SHA1 Message Date
Marc-André Bombeck cf68055cb2 feat(coach): run the turn on a budget with a live trail, questions and comparisons
Replace the fixed three tool rounds with a budget fixed by who pays:
120k tokens, 150 s and 12 rounds on the person's own plan, key or local
model, 40k, 90 s and 6 rounds when the operator pays. Cached input counts
at a tenth. The final answer is reserved from the start, so a turn whose
budget, clock or round cap runs out answers from what it read. A
no-progress brake stops a turn that repeats calls or reads nothing new,
and a repeated call is never run again.

The day's ledger is booked round by round: round one and the final
reserve when the turn starts, each further round right before it runs,
every round settled as it returns, the unused reserve given back at the
end. A round the daily ceiling refuses ends the turn with an answer.

Every phase goes out live as an activity frame (thinking, fetching,
summarising, asking, remembering, planning, the stop, the answer), with
screened reasoning titles and summaries; the structure rides the
provenance and the text is sealed in trail_encrypted, served by
GET /api/insights/chat/{id}/messages/{messageId}/trail. Tables go out as
interim results as soon as they are read.

Add ask_clarification with a server brake, remember_fact and
propose_plan over the memory contract, model-free decision turns,
compare_series with the compare chart, eight tables per message,
assumptions with change-assumption chips, a reasoning level per turn and
at most two concurrent turns per person.
2026-10-06 19:09:15 +02:00
Marc-André Bombeck 143a39e369 fix(coach): take a condensed series summary from its daily values
The summary of a condensed block was taken over the block's mix of daily
values and weekly means: over a year the newest fourteen days weighed as
much as fourteen weeks, min and max were extremes of means, and change was
one day minus a weekly mean.

Each series block now hands the budget pass its daily values over the
whole read, computed only when the block is condensed. The summary states
the first and last day, the lowest and highest day, the mean of the days,
and the change from the first calendar week to the latest one. A block
without daily values gets no summary rather than one of what is left. The
coverage note says how the summary is taken.
2026-10-05 22:03:59 +02:00
Marc-André Bombeck 73ce721ff2 fix(mcp): keep the metric series read as it was
The Coach's figure check ran before the MCP branch, so an MCP client was
told retrieval_failed for a block it used to receive, and the plain-text
renderer then said no data was on file. Any single-source build also
condensed its own block, which reached MCP through the source snapshot's
fallback to the full builder.

The figure check now runs after the MCP branch, and condensing is an
explicit option of the snapshot build that only the Coach tools set (it is
part of the cache key). MCP output is what it was before.
2026-10-05 21:52:48 +02:00
Marc-André Bombeck af79f4fb5c fix(coach): do not count the freshness stamp as a figure in a series block
A block trimmed to its unit and freshness stamp passed the figure check,
because asOf.daysAgo is a number. The check now skips the asOf and scope
fields, so that shape answers retrieval_failed like any other block
without a reading.
2026-10-05 21:50:48 +02:00
Marc-André Bombeck ac48e0d0ed fix(coach): give a series read its numbers when the shared build cut its block
Inside a chat turn every tool read lands on the turn's shared full-source
snapshot when its window matches. On an account with many synced series
that build passes the prompt budget, and the budget pass collapses blocks
to a bare unit and then to an `{ omitted }` marker. get_metric_series
sliced the marker out and answered `present: true` with it, so the model
was told the readings exist and was given no figure. The same held for
sleep, glucose, compliance and workouts.

- The snapshot result names the blocks the budget pass cut. A tool whose
  block was cut in the shared build reads it again from its own source at
  the same window.
- A read scoped to one source condenses its own blocks last and never
  swaps them for the marker: it keeps a summary (first, last, min, max,
  mean, change) taken before anything is cut, the newest daily values,
  weekly means folded into monthly means, and names each cut.
- get_metric_series never answers present with a block holding no figure;
  that read reports retrieval_failed instead.
- A chat series read carries the readings it counted, so the step shows
  them, and on a long or condensed window a note on what it covers. The
  tool description and a new tool-mode rule tell the model to call
  get_metric_table itself for longer history instead of asking.
- The screen-reader comma between step parts is unselectable, so a copied
  row no longer reads "Weight · ,all time".

MCP output is unchanged: the source-snapshot equality suite stays green.
2026-10-05 21:29:04 +02:00
Marc-André Bombeck 1158ae9ffd fix(coach): keep earlier tables beyond the lookback limit out of the context
The earlier-tables block names each stored table with its window and row
count. The list was filtered by module and exclusion only, so a table
stored before the limit was set or narrowed still told the model how much
history it covered. It now answers to the same range test show_result
uses, and the history-reach guard checks both the filter and that the
call site passes the limit.
2026-10-05 07:47:31 +02:00
Marc-André Bombeck 929c0ebaa4 Merge remote-tracking branch 'origin/main' into feat/coach-lookback-limit
# Conflicts:
#	src/lib/ai/coach/snapshot.ts
#	src/lib/ai/coach/tools/executor.ts
#	src/lib/insights/features.ts
2026-10-05 07:31:03 +02:00
Marc-André Bombeck 393ac955f6 Make the Coach lookback a limit on every read
The saved Coach window only seeded the snapshot and each tool's default.
A tool could still read back to all time, the availability probe reported
counts and means for history outside the window, and several blocks read
fixed windows of their own (labs 12 months, correlations 180 days, the
coarse tail, the all-time extremes) whatever the setting said.

coachPrefs.defaultWindow is now enforced as a limit through one module,
history-reach.ts: the turn context clamps the client window, the snapshot
clamps its window and gives every fixed-window block either the shorter
window or, when the block's own window cannot fit, leaves it out. Every
retrieval tool clamps its window, an earlier period or a stored table that
reaches past the limit answers outside_reach, and the probe reads only
inside the limit and names older history as outside_reach without any
figure. Follow-up chips that would read past the limit are not offered.
The default (allTime) is no limit and reads as before. MCP clients pass no
limit and keep their own window arguments.

Adds the twelve-month option, rewrites the picker text to state what is
read with the numbers the readers use, shows the same options in the
managed-profile settings, counts cluster members with a singular, and
drops the opacity on switched-off rows that put their text below WCAG AA.
2026-10-04 20:45:21 +02:00
Marc-André Bombeck 546e67475f perf(mcp): build single-metric reads from the metric's own rows
get_metric_series (and get_metrics, the metric resources and the review
prompts, which fan out over it) answered with one section of a Coach
snapshot, but built the whole snapshot to get it: the all-type feature
extraction, the derived wellness layer, trajectory, correlations, memory,
GLP-1, cycle, illness, labs and visits. On a seeded account with about
215k measurements a resting heart rate read ran 208 SQL statements and
blocked the event loop for 175 ms to return under 2 KB.

The MCP surface now asks the executor for a source snapshot. It runs the
same prelude (prefs, module gates, admitted sources, cutoffs, now shared in
snapshot-prelude.ts) and the same block builders over the requested
source's reads only. The core clinical aggregates come from extractFeatures
scoped to the one block, whose bulk read keeps its all-type cap so the rows
a block sees do not change. A section large enough for the full builder's
prompt-budget pass to trim, and the environment cluster, go to the full
builder, so their results are the old ones by construction.

The integration test compares the tool's serialised result with the full
builder's section and grounding for nine sources over four windows, the
get_metrics batch and the metric resource, on a seeded account dense enough
to put the feature row cap into play.
2026-10-04 18:17:24 +02:00
Marc-André Bombeck 8f730484e0 Average pulse by day in the comparison snapshot and Coach inventory
The insights comparison snapshot took its current and baseline pulse figures
from a reading AVG, and the Coach's data inventory told the model a reading
mean of the whole pulse history. Both now read the mean of the user's local
days, each the mean of its hours' means, through the day-mean helper. Every
other type keeps its aggregate.
2026-10-04 11:37:57 +02:00
Marc-André Bombeck d11c165675 fix(coach): read the cycle contrast and the metric table in the reader's units
The cycle block's headline contrast labelled weight in kg and the
temperatures in °C, and left a glucose contrast without any unit. The
metric table, which the person sees and whose summary the model reads,
listed weight in kilograms, temperatures in degrees Celsius, walking
speed in metres per second and distance in metres.

The cycle contrast now converts both means and the gap into the
reader's units (the gap by the factor alone) and names the unit in its
sentence. The table resolves each column's unit and decimals from the
reader's preferences and converts every folded period value once; the
snapshot carries the preferences it was written in, so the table and
the snapshot of a turn always agree.

Refs #1067
2026-10-01 13:23:17 +02:00
Marc-André Bombeck 21a2e2fcef fix(coach): keep the chart on "as a table" so the chart is offered back
"As a table" used to drop the table's chart, so the reply offered no way
back to it. The copied table now keeps its chart and carries view: table,
which the panel opens on the table (the chart one tap away on the toggle)
and the chips read to offer "as a chart". show_result with view table
does the same. The field is optional on the result metadata; a client
that ignores it shows the chart first as before.
2026-09-27 13:36:48 +02:00
Marc-André Bombeck b1629e2ad3 refactor(coach): keep the exclusion gate in its own module beside the snapshot builder 2026-09-27 13:32:58 +02:00
Marc-André Bombeck 7e91596f02 perf(coach): send the table rules only when there is a table
The recheck and follow-up rules now ride the tool-mode prompt only once
the conversation holds a table, or from the round after the turn produced
its first one. The clarifying-question rules are shorter and English for
every locale, like the other instructions to the model; the German copy
of them and of the recheck rule is gone. A turn without tables sends
about 1 300 characters less on every round.

The golden transcripts change only in the system prompt's hash and
length (4 509 to 3 187 characters; 4 728 to 3 280 for the German turn).
2026-09-27 13:26:16 +02:00
Marc-André Bombeck 4e47670f25 refactor(coach): import the prior-table gate from the executor, not the tools barrel 2026-09-27 13:22:09 +02:00
Marc-André Bombeck bd3aa3ddb1 fix(coach): hold an excluded metric's earlier tables back from the model
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.
2026-09-27 13:18:26 +02:00
Marc-André Bombeck 4558271b3e fix(coach): let a correct comparison with an earlier period stand
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.
2026-09-27 13:08:36 +02:00
Marc-André Bombeck c4bf5a916d feat(coach): choose a chart for each result table on the server
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).
2026-09-27 12:34:06 +02:00
Marc-André Bombeck a967ccac44 feat(coach): metric tables and show_result for the chat tools
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.
2026-09-27 11:54:30 +02:00
Marc-André Bombeck 8fcd204172 feat(coach): seams for steps, tables, charts, method, chips and clarification
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.
2026-09-27 10:43:15 +02:00
Marc-André Bombeck 742ef2c9b0 feat(coach): report tool calls as they start and settle
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.
2026-09-27 10:37:40 +02:00
Marc-André Bombeck 9d2fd1db14 fix(tz): one default zone, and the user's own calendar where Berlin was hard-coded
The status assessments folded their recent days, weeks, months and years on
Berlin days whatever the user's zone, the mood and cycle crosstabs keyed
their metric days in Berlin, the resting-pulse proxy defaulted to Berlin
days, the briefing's opener rotated at Berlin midnight, and every
assessment prompt labelled today's date as Berlin's. They now use the
user's zone. Rollup months and years are labelled by their UTC start,
which is how they are cut; read in a zone west of UTC the label named the
month before.

"Europe/Berlin" was written out in some eighty places. DEFAULT_TIMEZONE in
lib/tz/format is now the one definition: the second copy in mood/date-key,
DISPLAY_TIMEZONE, the Berlin-only day key helpers and the per-route copies
are gone. An in-repo lint rule rejects the literal outside lib/tz and
tests; four areas another change owns are listed as pending.
2026-09-26 16:23:14 +02:00
Marc-André Bombeck 5bd19573ea fix(insights): pass the record's module map to every correlation scan
The Coach correlations tool, the per-metric card and the period
narrative scanned every channel, so a switched-off module still fed
their statistics and the text a model was grounded on. The matrix's
modules option is now required, each caller resolves the record's map,
and the Coach skips the lab pass with labs off. A registry guard holds
every caller to resolving the map itself.

The mask's doc comment now states what it does to the false discovery
correction: fewer channels is a smaller family, so q-values of the
remaining pairs move and a borderline pair can cross the threshold.
2026-09-24 10:17:14 +02:00
Marc-André Bombeck 18ed57b867 fix(ai): every surface keeps a ceiling on the day's mixed total
The owner split left an operator-funded chain with no ceiling at all. Its arm
compared operator_tokens, and that counter returns to roughly zero on every
reconcile the user's own plan settled: on the 2026-09-11 evidence the shared
key answered 500 and codex served, so the counter never grew, every job
reservation was admitted forever, and a runaway client loop could write an
unbounded row. A pre-existing concurrency contract caught it from the other
side, two reservations that must not both pass one cap both passing.

reserveBudget now refuses when the owner's counter is over its cap OR the day's
mixed total is over the abuse ceiling, and a background surface gets its share
of that ceiling too, so background spend is bounded on the total and not only
under a counter the operator's key never fills. The surface is a required
argument, so the type checker enumerated every reservation site.

The hop guard learns the same lesson: an operator-funded fallback hop is now
rationed at the calling surface's ceiling rather than the full operator cap. A
job admitted under the job share could previously spend the whole 200 000 once
its chain fell back onto the shared key, which is the original defect reached
by the fallback path.

The job share applies only where the operator pays for the chain. Multiplying
whichever ceiling the chain resolved halved background generation for a
self-hoster on a local model, who costs the operator nothing.

Refusals now name the ceiling they hit and whose it was. A refusal used to emit
the day's mixed total and nothing else, which on an operator refusal is not the
counter that tripped.
2026-09-11 11:11:01 +02:00
Marc-André Bombeck 31991924f0 Merge branch 'chore/knip-dead-exports' into release/v1.37.27 2026-08-23 19:38:45 +02:00
Marc-André Bombeck 244a939d05 Drop unimported re-exports from the remaining barrels
Same shape as the derived and MCP barrels: the line in the barrel had no
importer because the consumer imports the concrete module. Affected:
cycle (15), coach tools (9), record-settings (8), links (4), data-list,
workout-detail and analytics/score (1 each).

analytics/score also carried CompositeValue on an explicit export line
above an export * of the same module, so the name stays exported either
way.

Definitions are untouched.
2026-08-23 19:11:12 +02:00
Marc-André Bombeck 8ffa9cd87a fix(insights): scan one discovery matrix from every correlation surface
Four surfaces assembled the correlation-discovery matrix and three carried a
different channel set. The Coach `get_correlations` tool had neither the
environmental-exposure channels nor the custom-metric ones, so asking it
whether air pressure relates to your sleep met a matrix the pair had never
been in. Its own file header said the opposite - "the SAME full-matrix scan
the route runs" - and had said it since the weather channels arrived in
v1.25. The period narrative was missing those two families and the
compliance / symptom pair on top.

`src/lib/insights/discovery-matrix.ts` is now the one place a matrix is
built. v1.30.3 hoisted the fetch discipline into a shared module for exactly
this reason and left the assembly duplicated behind; this finishes it. The
route, the per-metric card, the Coach tool and the period narrative all call
`assembleDiscoveryMatrix` and get the same families. What still differs is
declared as an option with its reason at the declaration: the measurement
read mode (a read-cost choice, left per surface), the extra metric types the
narrative's delta beat needs, and the RATED mood factors.

Mood factors stay on the narrative alone. That capture kind is frozen, the
two surfaces that persist a discovered pair write its channel key into a
plaintext column, and a custom factor's key is an opaque id - so admitting
them elsewhere is a decision about what to ask, not a parity fix.

Restore the per-metric filter on the assessment card's relations. It was
written in place of the pattern-dismissal filter rather than chained with it,
so a weight card's prompt had been receiving every surviving pair in the
record while the function name, the docstring and the early-return guard all
still said one metric.

`discovery-matrix-guard.test.ts` freezes who may fetch a channel, who may
construct one, and who may scan. Each matcher asserts a non-zero match count,
so a matcher that has stopped matching fails rather than agreeing with the
allowlist.

The statistics are untouched - same Pearson, same exact p-value, same
Benjamini-Hochberg, same floors. The Coach's family is larger now, which is
the point: it is corrected over the same family the insights page is.
2026-08-23 17:38:14 +02:00
Marc-André Bombeck 4ed6f7d1ce Write the Coach read strip's second line in the reader's language
On a German metric page the strip printed its own summary in German and
the pattern line under it in English. The pattern line is a finished
sentence the server writes, and the route never told the server who was
reading, so it wrote English.

The route now resolves the reader's language the same way the
correlations and analytics routes do and passes it down. The language is
a required argument the whole way through — it used to be optional with
an English fallback, which is why a caller could stay silent and still
get a sentence back. The cycle page's lagged rows had the same gap and
are fixed with it.

The strip's browser cache is keyed by language too, so switching
language no longer re-uses the sentence written for the previous one.
2026-07-31 08:52:23 +02:00
Marc-André Bombeck 5a71f376d4 refactor(coach): keep the manifest's out-of-window rows terse
The preamble already says once what the two states mean and that neither is
absence; repeating it per row would have doubled a manifest that rides every
turn.
2026-07-26 18:34:42 +02:00
Marc-André Bombeck 2a9b5ba59d test(coach): prove the availability probe's SQL against Postgres
The unit suite mocks Prisma, so it proves the discriminant and nothing about the
query underneath it — a wrong column would have left every test green and every
account answering no_data_unconfirmed in production. Seeds the reported case and
the four other shapes: an empty record, another account's rows, tombstoned rows,
and a history that mixes units.

Rounds the out-of-window mean to one decimal, like every other mean the snapshot
surfaces, and annotates a failed manifest probe rather than letting it degrade in
silence.
2026-07-26 18:34:42 +02:00
Marc-André Bombeck 59a435d5ac test(coach): pin the window/absence discriminant to the reported case
The fixture is the report: a fortnight of glucose readings from April 2024 on an
account that displays them everywhere else. The clock is pinned so it cannot age
out of the window it was written to sit outside of.

Covers the four states an empty window read can resolve to, that a never-recorded
metric and a historical one differ in the SAME run, that a mean is withheld
across mixed units rather than fabricated, that the manifest advertises the range
instead of "absent", that both instructions branch on the reason code, and that a
miss carrying figures reaches the prose verifier's authoritative set. Adds the
medication-compliance page to the failed-read sweep and pins the narration
blocks' failure annotation.
2026-07-26 18:34:42 +02:00
Marc-André Bombeck a402eaaf15 fix(coach): tell a history outside the window apart from a metric never recorded
A Coach retrieval tool that read the window and found nothing returned
`reason: "no_data"` — the same code for two situations that have nothing in
common: the record holds nothing for that metric, and the record holds a
substantial history for it, all of it older than the window that was searched.
Nothing downstream could tell them apart, so the Coach said the honest-sounding
sentence for the wrong case, and then, having been told there was nothing there,
changed the subject. Someone with a year of imported glucose readings was told
the readings did not exist, on the same account whose glucose page was showing
them.

The window cap stays. It exists because a multi-year history does not fit a
prompt budget, and widening it would only move the same failure. What was
missing is the ability to say a different true sentence.

- `tools/availability.ts` — one grouped aggregate per miss, no rows
  materialised, resolving four states: `no_data` (probe confirmed empty),
  `outside_window` (rows exist, older than the searched window; carries the
  count, the date range in the user's own timezone, and a bounded per-series
  mean/min/max), `unavailable_in_scope` (rows exist inside the window and the
  domain still produced none — a module is off), and `no_data_unconfirmed` (the
  probe itself failed; absence was never established, so it is not asserted).
- Every empty read in the executor routes through it. A bare `no_data` can no
  longer be returned without the record having been checked.
- The DATA INVENTORY carries the same distinction, so a domain the window
  cannot reach is advertised with what it holds instead of as absent — the model
  no longer skips the fetch, and a vague follow-up keeps the subject.
- Both instructions that told the model to report absence and move on now
  branch on the reason code, and forbid answering about one metric by reporting
  another.
- The out-of-window aggregate joins the authoritative set for the prose
  verifier, so the sentence the fix exists to make sayable is not elided.
- A cross-cutting narration block that throws is now counted rather than
  vanishing into a `null` that looks like honest absence.
- The medication-compliance page tells a failed read apart from an account with
  no medications, instead of inviting someone to re-enter what it already holds.

Refs #648
2026-07-26 18:34:42 +02:00
Marc-André Bombeck fa2b9531f7 Gate the MCP export reads on the module map
The MCP surface reached three data families that deliberately bypass the
Coach snapshot and so inherited none of its module narrowing: the
doctor-report aggregate behind healthlog://report/doctor-visit and the
doctor_visit_summary prompt, the rollup-backed rich reads (compare_metric,
get_metric_baseline, detect_changepoints), and the correlations reader.
A disabled module — or one an operator switched off server-wide — still
egressed to a third-party assistant.

Gate at the read rather than per call site. The module-to-data ownership
table moves out of the Coach snapshot builder into
lib/modules/measurement-scope so every read gates off one map; the rich
reads resolve metrics through a module-aware resolver; the correlations
reader gates on insights itself, which also closes the same gap on the
Coach chat tool and the metric-page read strip.

Per-domain reads omit with an honest module_disabled reason; the
whole-record aggregate refuses, mirroring /api/export/health-record.
collectDoctorReportData gains a fail-closed backstop on its own module
key. The clinician share link, found while tracing the aggregate's
callers, had the same gap and now collapses to its documents-only state.
2026-07-19 03:09:29 +02:00
Marc-André Bombeck 6c2eb15f05 fix(insights): hoist the correlation window fetch so every reader shares one grain
The asc+take(20000) window-cap bug (fixed on the correlations route
alone) and the mixed-grain toDailyMeans bug (fixed on three of four
readers) both survived on the Coach get_correlations tool, the
per-metric assessment card, and the period narrative. Dense accounts
saw the cap drop the newest rows on the coach/card readers and drop
the CURRENT period on the narrative — backwards for a recent-window
and a current-vs-prior surface respectively; the narrative's own local
toDailyMeans twin also averaged sleep stage-segments and blended
per-sample step chunks with drained daily totals instead of summing.

Hoists the fetch + grain resolution into
fetchMeasurementWindowSeries/fetchMoodWindowSeries
(correlation-channel-series.ts) — desc+cap+resort, full column select
for buildMeasurementDailySeries's per-type grain — and routes the
route, the coach tool, the per-metric card, and the period narrative
through it, deleting every local copy.
2026-07-18 06:47:32 +02:00
Marc-André Bombeck 8902d3985c fix(measurements,insights): source-collapse + timezone parity across multi-source surfaces
Four data-correctness fixes in the same class as the workouts-list
ordering bug (05f80ad37):

- GET /api/measurements groupBy=day: the raw-row scan ordered oldest
  first and sliced to `limit` before bucketing, so a long history never
  surfaced its recent days. Reads newest-first now. The per-day sum
  also ran over every source unfiltered — an Apple Health + Withings
  write for the same day doubled the total. Routes through
  pickCanonicalSourceRows first, matching the rollup tile's collapse.

- PR detection's cumulative-day picker summed every row on a calendar
  day regardless of source (false "record" days) and bucketed on the
  UTC calendar day instead of the user's timezone. Rewritten to
  source-collapse before summing and bucket on the user's IANA zone,
  reading through the worker's injected Prisma client so the existing
  dependency-injection contract for tests stays intact.

- The correlation-discovery matrix (the insights route, the per-metric
  assessment card, and the Coach's get_correlations tool — three
  independent copies of the same fetch) averaged cumulative types
  (steps, daylight) and sleep across mismatched grains: per-sample
  chunk means blended with drained daily totals, and sleep averaged
  per-stage segment durations instead of summing a night's total.
  Hoisted the grain resolution into one shared
  buildMeasurementDailySeries helper (source-collapsed day-sum for
  cumulative types, per-night reconstruction for sleep, mean
  unchanged for spot vitals) so all three surfaces agree.

Regression tests cover newest-first ordering, cross-source collapse
matching the rollup, PR no-double-count, and the shared grain helper.
2026-07-17 23:12:12 +02:00
Marc-André Bombeck 0f2b548138 style: apply prettier 3.9.1 formatting
Mechanical reflow from the prettier 3.9.1 bump; no behaviour change.
2026-06-28 19:26:16 +02:00
Marc-André Bombeck b91649d6de feat(ai): UI-configurable response timeout, local streaming, dedicated OCR provider
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).
2026-06-27 15:21:40 +02:00
Marc-André Bombeck 0aaaaac081 feat(insights): surface early-detection and lab correlations to the correlations route and coach
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.
2026-06-27 13:34:43 +02:00
Marc-André Bombeck 57682f8df1 fix(coach): build compliance + symptom channels in get_correlations
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".
2026-06-26 13:50:17 +02:00
Marc-André Bombeck 976ecf8a75 Surface the computed illness retrospective to the Coach
The illness-recovery tool and the illness context block carried only labels,
lifecycle, and dates plus the recovery composite — never the recovery-gap, the
metric that drove it, the nadir, the pre-onset deviations, or the red flags the
illness card renders. So a recovery question got the composite, not the gap the
user sees, and a sustained-fever or low-SpO2 escalation was invisible
in-conversation.

Run the existing episode-correlation read-layer (the same engine the card and
the red-flag notifier use) for the most relevant episode — active first, else
the most-recently-resolved — and attach the computed scores to get_illness_recovery,
coverage-gated so a thin signal yields nothing rather than a fabricated number.
Document the illnessScores shape in the Coach prompt so it restates those
numbers verbatim and escalates a red flag rather than reassuring.
2026-06-26 13:36:59 +02:00
Marc-André Bombeck abceff04c7 Build the Coach snapshot once per turn and widen the round budget to three
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.
2026-06-26 13:32:42 +02:00
Marc-André Bombeck d45d60627f Narrow the tool-mode Coach to the metric it was launched from
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.
2026-06-26 13:25:35 +02:00
Marc-André Bombeck f493ff58cb merge(RECON1): clinical-floors, coincident-tz, correlation quality, local drivers 2026-06-26 13:15:03 +02:00
Marc-André Bombeck b75cef9190 fix(insights): key coincident-deviation 'today' in the user's timezone
The coincident-deviation read grouped the latest day with a UTC date
slice while the sibling readiness read already used the tz-aware day key.
For a user east or west of UTC, a late-evening or early-morning reading
landed on the wrong calendar day, so a fired flag could compare a vital
from the wrong day against its band and narrate '2 or more vitals out of
band today' on the wrong day.

Thread the user's timezone into the latest-day read and mint the day key
with userDayKey, matching readiness. The Coach derived-snapshot and the
correlations reader pass the real account timezone through. Adds a
regression covering a UTC+2 user whose late-night reading rolls to the
next local day.
2026-06-26 13:01:39 +02:00
Marc-André Bombeck 3783348506 fix(coach): make the daily token budget provider-aware
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.
2026-06-26 12:53:04 +02:00
Marc-André Bombeck 58376a0705 feat(coach): verify Coach prose numbers against fetched figures
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.
2026-06-26 12:36:07 +02:00
Marc-André Bombeck 6de1f34efb feat(coach): widen tool-mode data reach to every stored domain
The retrieval-tool DATA INVENTORY was built against the user's default
narration cluster (cardio/body/mood/medication), so sleep, glucose,
activity, body composition, vascular, SpO2, gait and environment series
reported absent even when the data existed — and the grounding rule then
told the model not to fetch them. Probe presence against the full source
set instead, and generate the metric-series inventory rows from the
complete source-to-section map so every series the user has rows for is
advertised. Per-tool reads still re-scope to their own domain, so the
wider probe never widens a figure read.

Add three retrieval tools whose snapshot blocks already existed but were
unreachable in tool mode:
  - get_workouts: recent sessions + per-sport rollup
  - get_cycle: phase / prediction / correlation (gated by cycle access)
  - get_correlations: the FDR-controlled lagged cross-metric drivers plus
    the coincident-deviation flag, surfaced descriptively

Also honour the caller's window in get_labs and get_illness_recovery so a
cross-metric answer no longer silently mixes horizons.
2026-06-26 12:35:57 +02:00
Marc-André Bombeck bf29ab1e0e fix(insights): cancel the Coach tool-loop provider calls on disconnect
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.
2026-06-26 09:30:08 +02:00
Marc-André Bombeck e023571a08 chore(labs): tidy OCR capability enum, Fitbit key delimiter, Coach docblock
Drop the unreachable text-only-model reason from the OCR capability
enum and its DTO type. Replace the literal NUL delimiter in the Fitbit
dedup map keys with a named constant so text tooling stops treating the
file as binary (behaviour unchanged). Correct the Coach tool-executor
docblock, which overstated cross-tool snapshot-cache sharing.
2026-06-26 09:27:05 +02:00
Marc-André Bombeck 7a9e326e85 feat(coach): retrieve health data on demand via tools
Replace snapshot-stuffing in the Coach turn with a small base context plus
on-demand retrieval. The model receives the full system prompt, a tool-mode
grounding addendum, and a tiny DATA INVENTORY manifest listing which domains the
user has logged and which tool fetches each; the figures themselves are pulled
only when a question needs them.

Six read-only tools wrap the existing server-authoritative snapshot builder:
get_metric_series (blood pressure / weight / pulse + the additive series),
get_glucose_panel, get_sleep, get_medication_compliance, get_labs, and
get_illness_recovery. Each returns a structured { present: false } for an absent
or opted-out domain rather than throwing or returning an ambiguous empty list,
so the model can always tell missing data from real data. Module and cycle gates
are enforced at the builder, so opted-out domains are unfetchable.

A bounded loop runs the call -> tool-result -> answer cycle: at most two rounds
with a hard cap of three that forces a final answer, parallel tool execution,
and only the final round streamed. The day's budget reserves the per-call
ceiling times the round count and reconciles the summed tokens; the atomic
reserve and reconcile primitives are unchanged. All inbound gates (rate limit,
refusal, replay scan, consent, budget) stay before the loop.

The legacy snapshot path stays alive as the no-tools fallback: tool mode is on
only when every provider in the chain supports tool-calling, so a chain that
includes a local model falls back to the prior behaviour verbatim. The tool
trace is persisted onto the assistant message provenance.
2026-06-22 07:37:29 +02:00