The chat stays bound to that section's saved calculation, checks each chart fact before answering, and bills like an ordinary turn.
Co-authored-by: Cursor <cursoragent@cursor.com>
The list query had been split into four reads, so older pages no longer followed one cursor. A7 was read from the wrong module, and the shell asked for the product switch on every mount.
Co-Authored-By: Grok (agent loop)
Co-authored-by: Cursor <cursoragent@cursor.com>
The second review still failed on missing database and route coverage, an unmarked relationship structure, a stuck English lease, and a sidebar that fetched the product switch itself.
Co-Authored-By: Grok (agent loop)
Co-authored-by: Cursor <cursoragent@cursor.com>
The review found empty sections and an English job that stayed running. Take evidence from reader briefs, retry one section, and settle before marking the report ready.
Co-Authored-By: Grok (agent loop)
Co-authored-by: Cursor <cursoragent@cursor.com>
The pair page and reader replace the leftover chat draft, and the same pair is not charged again.
Co-Authored-By: Grok (agent loop)
Co-authored-by: Cursor <cursoragent@cursor.com>
The saved row was the whole dossier twice. Keep the default and Raman match results, drop a concurrent duplicate insert back to the first row, and hide the new rows from the old history list.
Checked service tests 9/9, tsc 0, lint 0 errors, and test:db 73 pass / 13 fail matching the Windows known list.
Co-Authored-By: Grok (agent loop)
Co-authored-by: Cursor <cursoragent@cursor.com>
Keep both changelog entries and the archive-limit board row. The marriage-match row stays on this branch for the storage fix.
Co-Authored-By: Grok (agent loop)
Co-authored-by: Cursor <cursoragent@cursor.com>
Upstream e628118d, 7d545039, f75a6e77, and ac565836. Dignity follows the sign, Deeptadi keeps every condition that applies, and Shayanadi hours come from the previous Hindu sunrise. BUG-1389.
Co-Authored-By: Grok (agent loop)
Co-authored-by: Cursor <cursoragent@cursor.com>
Move the bde5d615 engine and full-synastry skill in unchanged, save both profiles without billing or a page, and retire the old synastry module.
Checked targeted pytest, tsc 0, lint 0 errors, service tests 6/6, and test:db 73 pass / 13 fail matching the Windows known list.
Co-Authored-By: Grok (agent loop)
Co-authored-by: Cursor <cursoragent@cursor.com>
The trigger, the shared constants, and the limit sentence now agree, and the archive and person menus scroll instead of growing past the screen.
Co-authored-by: Cursor <cursoragent@cursor.com>
Consult, rectification turns, and report generation stop before a credit reservation when the product caps are hit. A full heavy-compute gate waits up to 8 seconds, and one consultation retries that 429 inside the same request.
Co-Authored-By: Grok (agent loop)
The self-hosted client was typed as a full Supabase client, so an old scoring poll called .single() on a plain promise and failed. The new DataClient only lists methods the adapter implements.
Co-Authored-By: Grok (agent loop)
The switch is off unless CONSULT_ANSWER_REASONING_EFFORT is set, so today's request body stays the same. A set value is sent as top-level reasoning_effort only on the answer step. The real A/B did not run: there is no model key.
Request-body probe, the named frontend tests (114 pass, 0 fail), tsc, and lint (0 errors) were run.
Co-Authored-By: Grok (agent loop)
Co-authored-by: Cursor <cursoragent@cursor.com>
Cache work that depends only on the candidate minute, drop unread response fields, and reject windows above 241 candidates before any chart is built. Eleven canonical scenario hashes match 77057a819. Sealed and reported-offset replays match the 2026-10-08 records (changed_trial_count 8 and 581) and are stored as scoring_perf_2026_10_13.
Co-Authored-By: Grok (agent loop)
Career significator and house-lord rows now carry one presentation sentence. Values stay the same. A second three-repeat biography run still has one field conflict, so this is not accepted.
Not pushed.
The career checklist now says the direction section only covers strength, resistance, timing, and three events. Warm builds one packet per cache key and skips when its own cap is full.
A three-repeat biography run still has one career answer that names a direction from a planet nature, so this is not accepted. Not pushed.
The career checklist now says significators are only for strength and affliction. Chart-save warm no longer takes a heavy-compute slot.
Biography severe conflicts fell from 3 to 1. One career answer still names a direction from a planet nature, so this is not accepted for merge. Not pushed.
The cache key now includes the request date, and files older than two days are removed. The model card keeps values only. Parashari aspects are copied from the engine. Saving a chart warms the packet without blocking the response.
Biography severe conflicts rose from 1 to 3, so this is not accepted for merge. Not pushed.
Dialogue cards now take numbers from the same packet as the full-data report. Each of the twelve domains gets one table the card builder assembles. Lookups allow three calls a turn. further_reading is a per-domain technique index. BUG-1293, BUG-1294, BUG-1295.
Generate the full-data edition (pl9_personal_long_report.v4) and remove the reader edition. English still contains Han, so the API withholds it (BUG-1272, investigating). This commit is not pushed to staging.
