Jyotisha

2,582 Commits 64 Branches 0 Tags

3 Commits

Include renames

Author	SHA1	Message	Date
Jesse_ChenandClaude Opus 5.5	ab0f01a9cf	fix(rectification): stream-first typed turns, 10 s classifier cap, stage progress, run timings (BUG-1047) - D2: each intent-classifier attempt is capped at 10 s (same session model, thinking untouched); a hang takes the existing retry -> classifier_unavailable path. Success is timed too (RectificationClassifierDiagnostic). - D3: a typed message builds the NDJSON stream first; the first line is turn.progress "received", then the classifier and deterministic replies run inside the stream. Preflight rejections become turn.rejected (old status, code, message) and the client handles them like the old HTTP rejection. Stage lines 收到，正在对照你的档案… / 正在记下这件事… / 正在重新对照盘面… / 正在准备下一个问题… are driven by existing tool events and engine calls, are transient (live row only) and never persisted. VOICE / DESIGN updated. - D4: RectificationRunDiagnostic records per-step start/end, provider token usage incl. reasoning tokens, classifier timing and per-engine-call durations (AsyncLocalStorage scope per turn); RectificationTurnDiagnostic for deterministic turns. No user text, birth data or model text. - D5: /v5/versions memo (30 s, complete identities only, per transport); the exit gate skips its second persistNextInterviewIfIdle when the run's own call found the next focus already active (provably identical). Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_017eEAG8HD3mm8gsKXgk8uU8	2026-09-26 11:45:47 +08:00
Jesse_ChenandCursor	cfa824994e	fix(rectification): keep a live analyzing step and drop the range-stop exits Independent Staging Quality Gate / validate (push) Successful in 9m26s Details Independent Staging Quality Gate / publish (push) Successful in 1m57s Details 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>	2026-09-04 12:46:10 +08:00
Jesse_ChenandClaude Fable 5.1	6356d7b549	refactor(chat): render rectification activity through the shared step timeline The rectification surface had its own activity pipeline: a trace panel with a 20px canvas orb clipped inside a 14px marker, a list that never collapsed, a second receipt disclosure under every reply, an inline failure banner and a staged label while regenerating. Its trace and receipt are now projected onto ConsultationTimelineRow so both surfaces render one ConsultationRunTimeline with one live marker and one settled summary; receipt methods become source chips on the last completed row. The unreachable sections-report/step-tree path, the trace panel, the receipt component and the thinking-orbs dependency are removed. The server-side drop of rectification thinking deltas is untouched. BUG-476 Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01JUei7K13cYxLHE3Axe4A45	2026-09-02 04:29:01 +00:00

Author

SHA1

Message

Date

Jesse_ChenandClaude Opus 5.5

ab0f01a9cf

fix(rectification): stream-first typed turns, 10 s classifier cap, stage progress, run timings (BUG-1047)

- D2: each intent-classifier attempt is capped at 10 s (same session model,
  thinking untouched); a hang takes the existing retry -> classifier_unavailable
  path. Success is timed too (RectificationClassifierDiagnostic).
- D3: a typed message builds the NDJSON stream first; the first line is
  turn.progress "received", then the classifier and deterministic replies run
  inside the stream. Preflight rejections become turn.rejected (old status,
  code, message) and the client handles them like the old HTTP rejection.
  Stage lines 收到，正在对照你的档案… / 正在记下这件事… / 正在重新对照盘面… /
  正在准备下一个问题… are driven by existing tool events and engine calls, are
  transient (live row only) and never persisted. VOICE / DESIGN updated.
- D4: RectificationRunDiagnostic records per-step start/end, provider token
  usage incl. reasoning tokens, classifier timing and per-engine-call
  durations (AsyncLocalStorage scope per turn); RectificationTurnDiagnostic
  for deterministic turns. No user text, birth data or model text.
- D5: /v5/versions memo (30 s, complete identities only, per transport); the
  exit gate skips its second persistNextInterviewIfIdle when the run's own
  call found the next focus already active (provably identical).

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_017eEAG8HD3mm8gsKXgk8uU8

2026-09-26 11:45:47 +08:00

Jesse_ChenandCursor

cfa824994e

fix(rectification): keep a live analyzing step and drop the range-stop exits

Independent Staging Quality Gate / validate (push) Successful in 9m26s

Details

Independent Staging Quality Gate / publish (push) Successful in 1m57s

Details

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>

2026-09-04 12:46:10 +08:00

Jesse_ChenandClaude Fable 5.1

6356d7b549

refactor(chat): render rectification activity through the shared step timeline

The rectification surface had its own activity pipeline: a trace panel
with a 20px canvas orb clipped inside a 14px marker, a list that never
collapsed, a second receipt disclosure under every reply, an inline
failure banner and a staged label while regenerating. Its trace and
receipt are now projected onto ConsultationTimelineRow so both surfaces
render one ConsultationRunTimeline with one live marker and one settled
summary; receipt methods become source chips on the last completed row.
The unreachable sections-report/step-tree path, the trace panel, the
receipt component and the thinking-orbs dependency are removed. The
server-side drop of rectification thinking deltas is untouched.

BUG-476

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01JUei7K13cYxLHE3Axe4A45

2026-09-02 04:29:01 +00:00