The palette is restated for dark rather than inverted: elevation reads
through lightness on dark and through darkness on light, so the floor is
the darkest surface here and the second-lightest there. The clay hue is
kept and lifted, because #85432f is 2.1:1 on a dark ground. All 37
themeable tokens are covered, in an OS-preference block and a data-theme
block that a contract test keeps identical, and ink, action, danger,
success and warning are asserted at 4.5:1 against the dark canvas.
Four raw colors that would have stayed light-theme values are tokenised
(the avatar hairline, the sheen sweep, a one-off shadow, a literal
warning hex). The QR keeps literal white in both themes, since scanners
need light modules to be light, and print keeps white paper.
The four root boundary pages cannot read a token, so they restate the
handful they need in both themes. forbidden.tsx also stops painting a
bespoke near-black page in four colours that appear nowhere in the
palette, which broke the rule that dark ink is never a page-scale
surface.
Also fixes what the audit found in DESIGN.md itself: two ink values that
had drifted from the code, a motion tier documented at 360ms that was
never implemented, a breakpoint section claiming three tiers where the
stylesheet has eleven, an undocumented report-paper palette, and an admin
section describing a bespoke panel that antd + Refine replaced. Five
zero-reference admin rules go with it.
The sidebar gets the accent, opaque drawer, heading rank and empty-state
guidance settled earlier, and fenced code blocks finally get a container.
BUG-439.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_0155nFCgCHtoA7jhSDGmZmMu
The nav buttons defaulted to centered for the desktop icon rail and were
flipped back by `[data-state="expanded"]`. That attribute tracks the
desktop open state, while the mobile drawer runs off `openMobile`, so on
a phone the labels rendered but the override never matched: 新建对话 and
我的报告 floated mid-drawer while every other row sat flush left.
Left alignment is the base layer now, correct for both the drawer and the
expanded desktop sidebar, and centering moved into the >=768px collapsed
block beside the rest of the rail rules. That was the only top-level
`[data-state=...]` selector left in the stylesheet.
personal-report-entry asserted `justify-content: center` on the report
button, which is the defect itself; the value is updated and the rest of
that assertion stands.
BUG-438.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_0155nFCgCHtoA7jhSDGmZmMu
Scoring scoped the contrast packet to the previous round's candidate set while
minting probes for the new one, so every later read re-prefixed the stored hash
and the persisted focus schema could never match. Mint one prefix per set and
compare splits by probe identity.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01LVapmh2oGNyr6ECHKjPJY8
The onboarding paywall wrote `dialog-header`, a class no stylesheet
defines, so its close button stacked under the title instead of sitting
beside it. The session-delete confirm buttons had the same problem, and a
`message-entry` wrapper added in August had quietly killed the
`.message + .message` spacing rule in the main chat.
Fixes all three against the patterns already in the codebase, then adds a
contract test so the next undefined class fails instead of shipping: it
scopes itself to our own class families so Tailwind utilities stay out,
strips CSS comments before deciding what counts as defined, and carries
an allowlist of the fifteen deliberate no-op modifiers that must shrink
rather than grow.
Also collapses the paywall's duplicate display heading into the intro
sentence, leaving one heading in the dialog.
BUG-434, BUG-435, BUG-436.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_0155nFCgCHtoA7jhSDGmZmMu
The post-choice decision used a looser plan than the followup builder.
Load compute once in persistApplied and feed the same birthDate to both.
Co-authored-by: Cursor <cursoragent@cursor.com>
Collect focus was leaking discriminator probes into the agent prompt and
inheriting choice identity. Mark spoken questions, hide current_probe
unless a real choice card exists, strip fallback identity, log persist
failures, and align the decision probe with the plan including birthDate.
Co-authored-by: Cursor <cursoragent@cursor.com>
Root error/not-found pages lost all CSS after globals left the shared
layout. Inline the same token fallbacks as global-error so admin stays
off the chat stylesheet. Collapse three LoaderCircle spins into one
InlineSpinner, and build greeting fixtures in local time so UTC CI
does not hit the night-time copy.
Co-authored-by: Cursor <cursoragent@cursor.com>
Decision and question ranking now share contrast option completion, so a
missing style card cannot deadlock the interview with a dead-end reply.
Co-authored-by: Cursor <cursoragent@cursor.com>
Self-hosted PostgreSQL is the runtime. A missing APP_DATABASE_URL
must not tell users the retired hosted service is unconfigured.
Co-authored-by: Cursor <cursoragent@cursor.com>
Settled messages no longer rebuild on every token, Inter is actually
requested, and admin routes drop the 33 KB chat stylesheet. Root
force-dynamic is gone so public shells can prerender without changing
the no-store Cache-Control contract.
Co-authored-by: Cursor <cursoragent@cursor.com>
Ask-holdout now requires a renderable choice frame. Scoring uses the same effective contrast kind as rendering, because the engine-varga.d9/d10 fork was live. varga_style weak_yes counts as a strong conflict; existence weak_yes still does not.
Co-authored-by: Cursor <cursoragent@cursor.com>
Keep the four migrated cases in the queue. Record prior score exposures, distinguish migrated review from a fresh biography audit, and reject exposed or auto-attested cases from blind holdout use.
Co-authored-by: Cursor <cursoragent@cursor.com>
The published six keys stay on the 2026-07-21 freeze. Current-tree sidecar numbers remain diagnostic and unlabeled as release metrics. Remove the unused v2 PILOT_REPORT_PATH.
Co-authored-by: Cursor <cursoragent@cursor.com>
Training already counted quarter/range as dated, while the inference ledger mapped them to unknown and left the events unused.
Co-authored-by: Cursor <cursoragent@cursor.com>
Write and read used different range definitions at the same lead of 8, so a real separation always fail-closed the candidate projection.
Co-authored-by: Cursor <cursoragent@cursor.com>
Independent Staging Quality Gate 2141 failed because four tests still matched the old Mastra prompt wall and treated an unrenderable focus as null.
Co-authored-by: Cursor <cursoragent@cursor.com>
Silent unrenderable discriminators, a missing question-contract golden, and a always-on tool table were hiding fail-closed drops behind the prompt wall.
Co-authored-by: Cursor <cursoragent@cursor.com>
Missing evidence fingerprints are stale, not current. Stale snapshots keep asking discriminators when a probe exists, and offer-candidates refuses until the ledger matches.
Co-authored-by: Cursor <cursoragent@cursor.com>
Reserve a month-or-better holdout, degrade unsigned D9/D10 to existence, and treat ledger keywords as mention-only so remaining discriminators stay in the pool.
Co-authored-by: Cursor <cursoragent@cursor.com>
Closing a discriminator used to leave GET without a card after refresh.
Write the next dated question in the same request, skip childhood career
and move probes, and do not continue a read-only turn when that question
is already persisted.
Co-authored-by: Cursor <cursoragent@cursor.com>
Family and occupation method layers were blocking discrimination even when
training events were complete and a discriminator probe existed, so the agent
only acknowledged evidence and stopped.
Co-authored-by: Cursor <cursoragent@cursor.com>
Docker next build failed on ProbeAnswer.id and optional decisionReceipt,
so staging never received the month-lock SHA.
Co-authored-by: Cursor <cursoragent@cursor.com>
Keep Vimshottari/Narayana start dates instead of truncating to year, so
same-year month splits can appear on the choice card.
Co-authored-by: Cursor <cursoragent@cursor.com>
Dated evidence in a domain no longer yields another existence question
in that domain. Remaining varga discriminators all stay in the pool so
the next card is whichever unused split scores highest.
Co-authored-by: Cursor <cursoragent@cursor.com>
Empty snapshot candidates were starving remaining D24 splits, so the
TypeScript follow-up chain asked the low-gain Python career probe.
Read paths now share one inference+engine catalog and yield a stale
low-gain distinguish card to the current winner.
Co-authored-by: Cursor <cursoragent@cursor.com>
BUG-401 hid the legend to avoid duplicating Agent copy. After the
question contract, the Agent only leads in, so the persisted stem
must be visible on the card.
Co-authored-by: Cursor <cursoragent@cursor.com>
Python and TypeScript now share a four-option probe contract, persist Focus before asking, and pick the highest-value renderable probe instead of preferring low-gain career events over D24.
Co-authored-by: Cursor <cursoragent@cursor.com>
Staging web never became healthy because /api/health selected migration.schema_migrations as app_runtime, which is forbidden, so Docker rolled the image back.
Co-authored-by: Cursor <cursoragent@cursor.com>
Three collected events with a reserved holdout were stalling because the discriminator door counted holdout. Public selection_allowed still had snapshot fallbacks, and health only proved the image SHA.
Co-authored-by: Cursor <cursoragent@cursor.com>
Staging publish next build failed after validate skipped production TypeScript, so holdout unions and the decision barrel never reached the image.
Co-authored-by: Cursor <cursoragent@cursor.com>
Showing a choice card is no longer treated as completion. Distinguish probes
require real candidate groups, holdout stays out of scoring, and ordinary
sessions can finish with a credible range instead of an exact-minute gate.
Co-authored-by: Cursor <cursoragent@cursor.com>
Exam-quality cards may still jump ahead of adoption, but career years stay on method rotation. Server stamps only period and family; spoken questions remain model-authored.
Co-authored-by: Cursor <cursoragent@cursor.com>
Recorded-year quality probes were spoken-only, so the interview had no
choice card. Compare also re-scored after batch until the 105s attempt
aborted the turn.
Co-authored-by: Cursor <cursoragent@cursor.com>
Publish next build failed because the spoken-bind helper required result/output
on chunk payload, which the runner stream type does not have.
Co-authored-by: Cursor <cursoragent@cursor.com>
Conflict probes were jumping after one dated event, so the interview asked
another domain before method collection. Spoken replies now follow the
stamped choice prompt instead of a topic denylist.
Co-authored-by: Cursor <cursoragent@cursor.com>
Evidence writes now return the persisted open_question so the model asks that stem instead of a second education probe, and the jump-to-latest chip is centered again.
Co-authored-by: Cursor <cursoragent@cursor.com>
Staging lint failed on react-hooks/refs after the jump overlay fix.
Keep the latest card-open flag in the existing layout effect so ESLint
passes and the overlay still stays off the choice card.
Co-authored-by: Cursor <cursoragent@cursor.com>
Choice cards used a hardcoded domain menu and always asked existence.
Rank scoring layers by remaining-minute entropy, keep finance and health
volunteer-only, and ask D9/D10 style or exam quality so taps match outcomes.
Co-authored-by: Cursor <cursoragent@cursor.com>
Progress and spoken text shared a 24px consultation-report gap, and the jump chip covered option D. Put D-chart names back on the activity strip from evidence rescore methods.
Co-authored-by: Cursor <cursoragent@cursor.com>
Jesse_Chen