Enumerate evidence kinds so education cannot be proposed as a kind, and stream Chinese thinking on a separate channel that collapses when the reply arrives.
Co-authored-by: Cursor <cursoragent@cursor.com>
eslint-config-next failed staging lint because the case snapshot helper and choice-card reset called setState from useEffect. Load the snapshot in the fetch callback and remount the card by question id instead.
Co-authored-by: Cursor <cursoragent@cursor.com>
Conflict nodes stay server-owned; the Agent writes the question and option copy so users can tap instead of typing through an interrogation.
Co-authored-by: Cursor <cursoragent@cursor.com>
Rectification dropped tool.activity started events and treated length finishes as completed. Share generation settings with consultation, keep the activity line through streaming, and name multi-domain chart calculation.
Co-authored-by: Cursor <cursoragent@cursor.com>
Quality gate lint failed on setHeaderSlot inside useLayoutEffect, so staging never published. Pass the header mount node from a callback ref instead.
Co-authored-by: Cursor <cursoragent@cursor.com>
Put the compact board trigger in the chat header, keep the sheet above the composer on iOS, and align onboarding messages with the intake card on the session column.
Co-authored-by: Cursor <cursoragent@cursor.com>
The quality gate still expected the old board-only varga sentence ban, and public dasha ledger copy leaked raw scores.
Co-authored-by: Cursor <cursoragent@cursor.com>
BUG-330: the compact board sat in the same layer as the composer, so peek copy overlapped the sheet title. Overlay only below 768px; desktop stays a side column.
Co-authored-by: Cursor <cursoragent@cursor.com>
Use the quiet overlay scrollbar on chat and the house board, replace the blocking mobile dialog with a bottom sheet, and emit agent deltas before billing so users can read progress and stop a run.
Co-authored-by: Cursor <cursoragent@cursor.com>
eslint-plugin-react-hooks forbids updating ref.current in render, which failed staging lint after the compact rectification board landed.
Co-authored-by: Cursor <cursoragent@cursor.com>
The board was live data sitting under chat, so each new event looked like nothing changed. Keep candidate cards in the transcript and group 换升 by minute for the side panel.
Co-authored-by: Cursor <cursoragent@cursor.com>
Surface D9/D10 change minutes, event-dasha match copy, dual-dasha conflict, and a post-adopt consult handoff so users can keep narrowing or start a reading from a representative time.
Co-authored-by: Cursor <cursoragent@cursor.com>
Keep collecting while a method follow-up can still distinguish candidates, and show adoption cards only after offer-candidates. Align the natal house snapshot with the agent text column.
Co-authored-by: Cursor <cursoragent@cursor.com>
Keep the natal house table as a live snapshot outside chat, and show candidate times only after selection is allowed, attached to the latest settled reply.
Co-authored-by: Cursor <cursoragent@cursor.com>
The house table sat on the avatar edge because it is a sibling of the message row. Inset it with the avatar width plus assistant gap.
Co-authored-by: Cursor <cursoragent@cursor.com>
BUG-304 rewrote the natural-end instruction; keep the source-level lock
aligned so staging quality gate still passes.
Co-authored-by: Cursor <cursoragent@cursor.com>
Incomplete Flash generations were billed as completed consultations. Fail
those runs, keep the partial text, and reuse the rectification like/copy/rerun
bar on ordinary chat replies.
Co-authored-by: Cursor <cursoragent@cursor.com>
Adjacent minutes still cannot confirm a unique birth minute. A scored
representative time can now be accepted, and the copy must say the minute
is not unique.
Co-authored-by: Cursor <cursoragent@cursor.com>
SQL kinds now match the TypeScript ledger so batch ingest can confirm dated events. Confirm no longer burns the opening focus, recap uses server date labels, and the Agent sees indistinguishable width instead of a fake unique minute.
Co-authored-by: Cursor <cursoragent@cursor.com>
Measured use of the three chips above the composer was negligible. They
were also not what they appeared to be: the server looked up a fixed
triplet by session theme and passed it as metadata that overrode
anything the model produced, so the same ten hardcoded sets served every
user regardless of question or chart. That is a plausible reason nobody
pressed them.
Both copies of the per-theme table are gone, reply metadata narrows to
the session title, and the two parse entry points collapse into one now
that they return the same shape. The write schema still tolerates a
suggestions field so a client on the previous bundle does not lose its
message mid-deploy, and stored answers containing the legacy hidden
block are still stripped rather than shown raw.
Co-authored-by: Cursor <cursoragent@cursor.com>
- New suites: entry routing (13), evidence (11), skill/agent (13), stream (9),
status/security (11) plus shared fake-accounting support.
- Migration static contract tests extended for the v9 agent api migration
(run_phases, dossier/finalize/persist/accept/confirm RPCs, consent gate,
needs_rebaseline guard, runtime flag, identity-foundation boundary).
- database-local-business.test.ts ledger + exact public table set updated
(agentic_rectification_run_phases; BUG-127/BUG-144 boundary).
- rectification-v9-database.test.ts adds the agent-api migration test
(flag seed, turn finalize, run phase receipt, consent rejection).
- rectification-agentic-entry.test.ts rewritten: the old tests locked in the
hasRectificationSession + sessions.find guessing, textStream consumption and
client-side session creation; they now assert the server-owned Case open
flow, fullStream NDJSON, durable turns and exact-session routing.
- consultation-entrypoint / application-billing-contract rectification sections
updated to the caseId-bound billing and open API contracts.
- docs/BUG_HISTORY.md: BUG-162 follow-up with regression record explaining why
the old tests missed the broken entry guessing.
Jesse_Chen