Staging at 4ef4c406 produced a standard five-theme document with nine
charts, five chapter bodies, and an empty blocked disclosure.
Co-authored-by: Cursor <cursoragent@cursor.com>
Five-theme assemble cleared the chart and actionNotes caps, then failed
three anonymous guards. Log field path plus kind only, and strip
deterministic phrases from sections the producer already marked blocked.
Co-authored-by: Cursor <cursoragent@cursor.com>
Five-theme personal_full still failed final parse after the charts cap
fix because writer output exceeded actionNotes.max(24). Truncate at
assemble; do not raise the schema cap.
Co-authored-by: Cursor <cursoragent@cursor.com>
Adopted reverse-verify repeated already-asked collect stems, treated 「这题跳过」 as stopping the case, and promised holdout/OOS checks that never ran. Collect spoken stems no longer prefix a year.
Co-authored-by: Cursor <cursoragent@cursor.com>
Five-theme personal_full assembled nine charts after health vargas landed, but the document schema still capped at six. Bind the count to the enum, align JSON/Python contracts, and log final-parse paths without values.
Co-authored-by: Cursor <cursoragent@cursor.com>
Heartbeat and GET were parsing progress_phase with a pattern that rejects the colon prefix the writer already persists, which aborted generation after the first chapter.
Co-authored-by: Cursor <cursoragent@cursor.com>
set-focus only attaches the question stem. Retracting live Chinese before
it wiped the opening hello with an empty replace. Other public tools still
retract planning prose.
BUG-533.
Co-authored-by: Cursor <cursoragent@cursor.com>
Accepted profiles were selecting a revoked rectification table and failing the report before the engine ran. Degrade to a null window when that optional read fails.
Co-authored-by: Cursor <cursoragent@cursor.com>
Move nextDatedCollectFollowup after family coverage so a new case still
asks D9 then D10. Dated third-event collect stays education → finance →
relocation → health. Admin input padding contract follows --space-3.
BUG-531 and BUG-532.
Co-authored-by: Cursor <cursoragent@cursor.com>
Holdout stays closed until the training gate opens and skips declined domains.
Dated collect order is shared with exhaustion; spoken prompts must name the domain; progress copy uses collection_progress only.
BUG-527 through BUG-530.
Co-authored-by: Cursor <cursoragent@cursor.com>
Saying no to a spoken collect left the next stem only on current_question, so the preparing spinner never cleared. Persist the ack, link asked_turn_id, and emit run.completed with turnId (BUG-525).
Co-authored-by: Cursor <cursoragent@cursor.com>
API birth payloads store hour/minute as floats, and datetime() rejected them
after sensitivity was wired into every consultation_workflow call.
Co-authored-by: Cursor <cursoragent@cursor.com>
AbortSignal.timeout() is unref'd, so a hanging generateText drained the test event loop and cancelled the rest of the file. Clear the timer after the model returns.
Co-authored-by: Cursor <cursoragent@cursor.com>
The early-exit reused the pre-click dossier, so the agent never ran on the common path. Use this-turn decision, log agent vs template outcome, and time out after 8s.
Co-authored-by: Cursor <cursoragent@cursor.com>
When leftover probes cannot split adjacent minutes, skip frameless follow-ups and let a no-tool agent explain the stop. Distinguish-card "no" no longer closes a whole evidence domain.
Co-authored-by: Cursor <cursoragent@cursor.com>
A completed tool left only checkmarks under 正在分析, so the run looked stuck. The composer and scoring-card 先这样 buttons were unused early exits.
Co-authored-by: Cursor <cursoragent@cursor.com>
Product default stays Raman. Public-case revalidation and fixture dashas now pass --ayanamsa lahiri; profiles store the four selectable values.
Co-authored-by: Cursor <cursoragent@cursor.com>
GET was dropping choice_card when the recast had no choice_frame, so the
embedded options rendered disabled. Replay the persisted reverse-verify /
out-of-sample schema instead of silencing the live question.
Co-authored-by: Cursor <cursoragent@cursor.com>
The other-domain fallback copy was being used as the first question.
Opening now uses GENERIC_COLLECT_QUESTION; after-evidence other copy stays.
Co-authored-by: Cursor <cursoragent@cursor.com>
One "一时说不好" no longer ends the interview. Plateau streaks use the
same sample floor. Delivery copy states why the range stopped.
Co-authored-by: Cursor <cursoragent@cursor.com>
Public can_adopt no longer starves the collect fallback, 改选 scrolls to
the offer, opening collect uses other, and probe_year stays on the
schema. The status bar no longer starts an empty consultation chat.
Co-authored-by: Cursor <cursoragent@cursor.com>
The 09:31 staging card had four ready sections but showed only structural
validation failure. Derive the list copy from section status so a written
pipeline stop is not described as an empty schema miss.
Co-authored-by: Cursor <cursoragent@cursor.com>
Staging wrote four ready chapters then marked the job schema-invalid 34ms
later with no summary telemetry. Keep chapter persistence and assemble
going if onProgress or a non-lease heartbeat error fails.
Co-authored-by: Cursor <cursoragent@cursor.com>
Public can_adopt follows session_outcome; reverse_verify reuses the persisted question id; offer cards settle on the owning message with a status-bar handoff.
Co-authored-by: Cursor <cursoragent@cursor.com>
Staging lost the job lease mid-chapter because the unref'd interval never
fired outside an HTTP request. Refresh the lease on section progress and
leave the heartbeat timer ref'd so a long model await cannot starve it.
Co-authored-by: Cursor <cursoragent@cursor.com>
Staging verification wrote four ready sections then lost the 120s job lease
mid-chapter. Lengthen the worker lease and cap summary tokens with the same
3072 ceiling the section budget already uses.
Co-authored-by: Cursor <cursoragent@cursor.com>
Staging personal_full died as report_schema_invalid after the first
chapter blocked. Keep assertWriterOutput, stop treating refs mismatch as
missing evidence, and surface section error codes on the report APIs.
Co-authored-by: Cursor <cursoragent@cursor.com>
The outer focus ring overflowed the message bubble and stacked on the existing selected border. Draw keyboard focus inset and skip auto-focusing the first option.
Co-authored-by: Cursor <cursoragent@cursor.com>
Agent set-focus was writing or dropping choice schema, so probes never scored. Force server-owned options, fail closed when focus list RPC errors, and require the probe year in spokenPrompt.
Co-authored-by: Cursor <cursoragent@cursor.com>
Focuses now carry asked_turn_id so GET rebuilds stem and options on the
same turn. Agent writes spokenPrompt; the live question slot is gone.
Co-authored-by: Cursor <cursoragent@cursor.com>
Task 4 evidence: local gates, Gitea 2308/2309, health gitCommit 7faf8555. Live personal_full and writer/token still need a logged-in 委托方.
Co-authored-by: Cursor <cursoragent@cursor.com>
The extractor only read an obsolete varga object shape, never issued Transit receipts, and the consultation response omitted Chara Karakas, so career/marriage/timing/wealth all blocked. Supply the live engine shape, fail-closed receipts, and jaimini.chara_karakas without relaxing the evidence plan.
Co-authored-by: Cursor <cursoragent@cursor.com>
Move the current-question ref off render and persist the collect stem from snapshot/send callbacks so ESLint no longer fails the staging gate.
Co-authored-by: Cursor <cursoragent@cursor.com>
Keep collect text on bubbleMessage but pass displayedMessage.state so the entry contract matches again.
Co-authored-by: Cursor <cursoragent@cursor.com>
The live question slot still rendered the collect prompt below the action icons when the streamed body was only a greeting. Join the GET prompt into that bubble and stop drawing a sibling collect slot.
Co-authored-by: Cursor <cursoragent@cursor.com>
The live question slot disappeared on refresh because it was never written to assistant_message. Attach the current collect_spoken prompt to that turn before finalize so chat history keeps it.
Co-authored-by: Cursor <cursoragent@cursor.com>
BUG-486 demotion dropped wealth and education cards when the snapshot only had machine receipts, which failed Gitea validate. Keep write-theme cards only when varga_full is present.
Co-authored-by: Cursor <cursoragent@cursor.com>
Engine keys like D2_Hora never became structured charts, so wealth write
themes failed the document contract. Canonicalize document vargas, demote
missing charts to blocked, and classify the parse failure.
Co-authored-by: Cursor <cursoragent@cursor.com>
Persist the interview slot before the opening turn, keep the stem in the question slot, and hide that slot while a run is busy so the same ask does not appear twice.
Co-authored-by: Cursor <cursoragent@cursor.com>
Walkthrough polish: fail-closed empty D9 prompts, stop asserting the next question is on screen, vary same-domain collect copy, switch to reverse-verify after adopt, and let coverage route interview without blocking can_adopt.
Co-authored-by: Cursor <cursoragent@cursor.com>
The loading screen now owns every wait: starter questions, today's
starlanguage and the rectification entry summary are fetched in a prepare
phase before reveal (4s budget, static fallbacks), the rectification chunk is
warmed, recent sessions are prefetched, and no component spinner remains
after the page appears. BUG-479.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_0193vBv6w5MV2cifdTUu9H5P
Jesse_Chen