Hide engine branding, gate supported divisional columns, align house cells, and add accessible symbol help. Reduce desktop chart width and stabilize the waiting slot.
Validated with 78 browser checks and 87 focused frontend tests. Full suite retains 29 identical baseline loader failures; no new failures.
Co-Authored-By: Claude Code <noreply@anthropic.com>
Once the discriminator training gate is open, only choice cards are asked
and the range card goes out when they are exhausted; targeted lines, their
re-ask and guided windows no longer hold the card or invite more events.
Delivery body says how many choice questions were used instead of the event
fit percent; narration names an excluded cluster instead of "range
unchanged"; a delivered turn no longer carries a collect question.
Offline replay (v4, 3 radii x 2 directions): truth in range 20/20 in every
cell; guided-window injections give the same width in truth and opposite
directions, so red line 1 was revised by product to truth-in-range only.
Skill 10.0.31 -> 10.0.32 (10.0.31 kept as deprecated for pinned cases).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_017eEAG8HD3mm8gsKXgk8uU8
v4 open holdout, ±10/±30/±60, raw and percent priors: only 4/9/14 of 57
day-precision training events split candidates; widths unchanged, top-1
drops. Narrowed year blocking (R3) mixed. All arms no_benefit; no
implementation brief recommended. Two runs byte-identical.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_017eEAG8HD3mm8gsKXgk8uU8
Wording only: _quality_user_meaning names start/change/interruption as
升学/学业变动/学业中断; _display_date_label drops the stored month for
year-precision events. Split hash and month field unchanged; same-machine
A/B (PYTHONHASHSEED=0) differs only in user_meaning/display_date_label.
Re-frozen per ERR-110 under new quality_wording_2026_09_29 records;
sealed rerun (20) and reported-offset sweep (900) identical to 09-21.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_017eEAG8HD3mm8gsKXgk8uU8
Measure the model-visible consultation payload on three public charts, draft per-domain cards, and record the Narayana/pratyantar projection gap as BUG-1054. No runtime behavior change.
- R1: flipping 1 answer keeps truth in range 98-100% but cuts head hit by
a third or more; 2 flips squeeze truth out in 7-10% of ±30/±60 replays
(two flips = 8 points = SEPARATION_LEAD).
- R2: weights do apply (research scorer == production at V0); V1/V2 are
identity at ±30/±60 by construction and leave six-question metrics
unchanged at ±10 -> no_benefit (measured). Supplementary V1n does not
pass the gate.
- R3: boundary shift is ~3.8 days/minute (1.3-5.9), not 1.1; the 45-day
gate is ~8-34 minutes. The _representative_pairs hypothesis is refuted
(all-pairs adds no dated probes); the bottleneck is monthly evaluation.
New finding recorded as BUG-1048 (investigating): _boundary_windows
year-straddle exemption and positional zip misalignment bypass the gate.
- Dated errata appended (no deletions) to the 09-14/09-16 briefs and
research docs; README board row -> 待验收. No production code, scoring,
thresholds, gates or Skill changed.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_017eEAG8HD3mm8gsKXgk8uU8
Validate on Linux Node 22 and PostgreSQL 17: 3894 frontend tests and 64 database tests pass, with no removed test names or new failures. Preserve static Home, bounded gzip, assertion-change records and manual acceptance gaps.
Co-Authored-By: Claude Code <noreply@anthropic.com>
New reports request reader_main from upstream origin/main 23b9609e.
KP and transit no longer copy an empty vars() dict, solar returns keep
birth_asc_sign_idx, and ordinary projection deletes internal lines whole.
Add bounded chart loading, per-layer retry states, and shared SVG skeletons. Add report block downloads with SVG, localized metadata, and inline deletion.
Record verification and retain CRLF export, full-build, and controlled-device acceptance blockers. User authorized staging delivery with these gaps documented.
Co-Authored-By: Claude Code <noreply@anthropic.com>
Create a fresh local consultation for explicit new-chat navigation and keep reserved recovery from taking over its landing. Add regression tests and record validation gaps for remote review.
Co-Authored-By: Claude Code <noreply@anthropic.com>
Record Gitea run 2857 evidence: H1-H3 pass, BUG-1011 remains the sole E2BIG failure, publish skipped, and staging is not deployed. Mark BUG-1012 through BUG-1014 resolved at the code-contract level while retaining the deployment blocker.
Co-Authored-By: Claude Code <noreply@anthropic.com>
Carry explicit local date intervals instead of inferring the day from clock
order. Cluster width, delivery, adoption, and reports keep the actual civil
date; adopted date is stored separately from the reported birth_date.
Algorithm identity is scoring-9 / spec-v5. Scoring weights, confirmation
thresholds, and Skill version are unchanged. Isolated Linux final-3 gates
passed; four pre-existing Python failures remain. This is not a production
release.
Unify minute and block cache identity, keep unverifiable historical results read-only across server tools and write entrypoints, and aggregate completed receipt sources chronologically through a compatible function migration.
Co-Authored-By: Claude Code <noreply@anthropic.com>
Implement BUG-984 F2 option A and reproduce mixed completed identities through real tools. Stop at the required SQL authorization boundary; F1/F3/F4 remain pending.
Co-Authored-By: Claude Code <noreply@anthropic.com>
Replace machine-specific float hashes with strict score and matrix byte comparisons. Keep quick bridge coverage and document duplicate collection. Verify Windows/Linux float behavior and in-memory candidate-date reversal; record the separate-machine acceptance gap and BUG-984 end-to-end blocker.
Co-Authored-By: Claude Code <noreply@anthropic.com>
Preserve both the reviewed implementation and latest staging records. No production scoring changes beyond aa46da10.
Co-Authored-By: Claude Code <noreply@anthropic.com>
Add date-isolated caches and regression coverage, align scoring identity, and freeze full research reruns while preserving historical artifacts. Record unresolved cache/receipt identity and end-to-end acceptance gaps for branch review only.
Co-Authored-By: Claude Code <noreply@anthropic.com>
Keep full consultation tool contracts unchanged. Persist short replies and refund the original reservation atomically while recording actual model usage. Verify Linux frontend 3566/3566, database 40/40, Static home and gzip +0.0493%.
Co-Authored-By: Claude Code <noreply@anthropic.com>
20 public AA cases, raman/mean. Lowering MIN_BOUNDARY_DAYS narrows ±10 from
15 to 11 minutes but drops top-1 0.80→0.75; wider radii get wider ranges.
Varga sensitivity weights (V1/V2) match production; D60 (V3) hurts ±10.
Day-precision events offset ±7 never squeeze the true minute out. Production
45/30 gate and equal varga weights stay unchanged.
Offline v4 holdout probe. Last round's width=window result was the
no-elimination metric; production still-valid ranges after six answers
are 15/33/56 minutes. Adjacent merge never fires under step-2 radii.
W1/W2 match baseline; W3 is uncertain after one coverage squeeze.
No production clustering or scoring defaults changed.
Build holdout v4 from the public AA set, correct the two v3 dates, and sweep
R1–R5 plus pairs offline. No production scoring defaults change. No
implementation brief: delivered width stays the full window on every radius.
Block-layer unique top-1 0.20 sits at or below the 0.35 random expectation for
2.95 candidate ascendants, so H1-H4 had no signal to amplify. Not significant at
n=20; recorded as "no positive signal", not "worse than chance".
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_0193vBv6w5MV2cifdTUu9H5P
Offline H1-H4 measurement on 20 public AA holdout cases.
Block unique top-1 did not rise; H4 made it worse; minute layer unchanged.
Leave production scoring untouched. Transits must not drive minute conclusions.
Session history was silently clipped to the first 4000 characters of the last 12 messages, so follow-ups could not see timing or audit tables. Keep an append-only tail plus a checkpoint summary, retry overflow in the same request, and expose cache hit rate in admin usage.
Co-authored-by: Cursor <cursoragent@cursor.com>
