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>
The quality gate binds the hashed rectification skill; the engine-month
wording changed those bytes without updating the registry.
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>
The four-option probe contract adds a non-scoring unsure row; keep the D24 discriminator assertion aligned with that packet shape.
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>
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>
Coverage-complete ties stayed in discrimination because whole-window D9/D24 follow-ups were treated as probes, and restated dates inserted duplicate evidence. Skip encoded remaining layers, ask leftover D4 or offer a provisional range, and dedupe dated rows by kind and date.
Co-authored-by: Cursor <cursoragent@cursor.com>
The staging quality gate scanned the old settled.spoken streaming state after the live path started rendering answer.delta as raw.
Co-authored-by: Cursor <cursoragent@cursor.com>
Give the interview a hidden reasoning channel so planning leaves the spoken reply, publish terminal text-delta as-is, and stop regex or Case templates from replacing the model.
Co-authored-by: Cursor <cursoragent@cursor.com>
Coverage-complete ties never persisted A/B/C/D because contrast probes were stamped with an answered education quality probe, remaining minutes were asked as window D10 signs, and 「没有了」 missed the stop pattern.
Co-authored-by: Cursor <cursoragent@cursor.com>
Thinking is disabled, so Chinese process talk after tools arrives as
text-delta. Widen the leak-net so tool-label echoes and internal field
names stay out of answer.delta, and keep the user-facing follow-up.
Co-authored-by: Cursor <cursoragent@cursor.com>
Aborting the turn on a second identical public tool-call failed staging
after evidence and compare had already succeeded. Skip the duplicate
receipt instead and let maxSteps bound real loops.
Co-authored-by: Cursor <cursoragent@cursor.com>
BUG-368 dropped createServerSupabaseClient while keeping the call, so staging publish failed at next build after validate skipped the production build.
Co-authored-by: Cursor <cursoragent@cursor.com>
The staging quality gate already passed 2006 frontend tests, then ESLint failed on prefer-const in the BUG-367 test helper.
Co-authored-by: Cursor <cursoragent@cursor.com>
BUG-367/368 expanded the agent action enum, dropped public thinking traces, and added two business tables, but the quality-gate source scans and exact public table list were still on the old snapshots.
Co-authored-by: Cursor <cursoragent@cursor.com>
Mastra intermediate text-delta was published as answer.delta, then set-focus domain errors reset the attempt and replayed evidence. Publish only the terminal no-tool step, persist the next probe on the server, and ground batch quotes in the source turn.
Co-authored-by: Cursor <cursoragent@cursor.com>
Clicking A/B/C/D or stop must persist the answer, close the probe, and
update posteriors in one idempotent transaction instead of sending the
option text as a chat message.
Co-authored-by: Cursor <cursoragent@cursor.com>
Coverage complete only unlocks discrimination. A 34/33/33 window plus an
occupation note must ask a D9/D10 contrast probe instead of offering a
stale winner card.
Co-authored-by: Cursor <cursoragent@cursor.com>
Engine result rows stay immutable. Choice answers append transitions, and reads overlay the latest revision instead of patching the cached receipt.
Co-authored-by: Cursor <cursoragent@cursor.com>
Choice C/D without new evidence never changed the candidate posterior until the next dated-event rescore, and persist-v2 would cache-hit on the same evidence fingerprint. Patch the latest decision_receipt.inference_state in place so the next follow-up sees the asked split immediately.
Co-authored-by: Cursor <cursoragent@cursor.com>
Dateless occupation_note stayed draft, so classic coverage never finished
and offer-candidates stayed blocked. Confirm those notes, stop crowding
dasha probes with encoded exam quality, and adopt once blocking methods
are covered.
Co-authored-by: Cursor <cursoragent@cursor.com>
BUG-360: stream thinking and tool activity as an ordered trace so later CoT opens under 正在整理 instead of filling the first 思考 block.
Co-authored-by: Cursor <cursoragent@cursor.com>
Jesse_Chen