Jyotisha

2,942 Commits 76 Branches 0 Tags

3 Commits

Include renames

Author	SHA1	Message	Date
Jesse_ChenandClaude Opus 5.5	758fee954b	feat(rectification): range delivery needs 4 dated events across 3 domains (R1, BUG-1193) Product decision 2026-10-02 (TASK-upstream-sync5 R1): a time range is offered only with at least 4 dated, primary-scoreable events covering 3 domains, counted on all of them (training + reserved holdout). Was 3 training events / 2 domains in three TS copies and the Python acceptance gate while the policy file already said 4/3. - One definition: references/rectification_policy.v1.json (minConfirmationEvents / minConfirmationDomains). TS core/types MIN_DATED_, rectification-decision MIN_STANDALONE_, evidence-model MIN_ACCEPTANCE_, the convergence evaluator and the post-inference trainingGateOpen all read it; Python decision_policy MIN_ACCEPTANCE_ alias MIN_CONFIRMATION_*. - Python receipt counts all scoreable events / domains for event_quality and domain_diversity; decision policy identity v3 -> v4 (candidate UUIDs carry it). Candidate scores unchanged (77 v5 cases A/B identical), so the algorithm stays rectification-v5-matrix-scoring-10. - Memoization golden v3 written by write_golden; v2 frozen by sha256 with a test that its scores equal v3 and only the receipt policy moved. - Collect gap copy names the exact gap ("再来两件……其中至少一件不是……") instead of always "再来一件"; VOICE.md updated. Legacy life-events form copy 4/3 as well. - 30 frontend test files, 4 Python tests: fixtures extended to the same scenario at 4/3, or assertions changed with 原值/新值/原因 notes. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01N4f2nya58RoRu4yEmJgRGE	2026-10-03 00:08:00 +08:00
Jesse_ChenandClaude Opus 5.5	ea21743b09	fix(rectification): stop spoken collect once the training gate opens (BUG-1084..1087) 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	2026-09-29 10:06:57 +08:00
jesse-ux	69ffa07d6b	fix(rectification): stop speaking unstampable distinguish stems (BUG-674/675) Independent Staging Quality Gate / validate (push) Failing after 20s Details Independent Staging Quality Gate / publish (push) Skipped Details Distinguish followups that cannot stamp a probe now go to persistExhaustionCollect instead of repeating the card stem in the assistant body. Choice focuses without asked_turn_id hang on the last assistant turn, and persisted_question with a live choice_card renders the existing card. Representative-time inconsistency is warn-only (BUG-676 investigating).	2026-09-14 03:42:48 +08:00

Author

SHA1

Message

Date

Jesse_ChenandClaude Opus 5.5

758fee954b

feat(rectification): range delivery needs 4 dated events across 3 domains (R1, BUG-1193)

Product decision 2026-10-02 (TASK-upstream-sync5 R1): a time range is offered
only with at least 4 dated, primary-scoreable events covering 3 domains,
counted on all of them (training + reserved holdout). Was 3 training events /
2 domains in three TS copies and the Python acceptance gate while the policy
file already said 4/3.

- One definition: references/rectification_policy.v1.json
(minConfirmationEvents / minConfirmationDomains). TS core/types MIN_DATED_*,
rectification-decision MIN_STANDALONE_*, evidence-model MIN_ACCEPTANCE_*,
the convergence evaluator and the post-inference trainingGateOpen all read
it; Python decision_policy MIN_ACCEPTANCE_* alias MIN_CONFIRMATION_*.
- Python receipt counts all scoreable events / domains for event_quality and
domain_diversity; decision policy identity v3 -> v4 (candidate UUIDs carry
it). Candidate scores unchanged (77 v5 cases A/B identical), so the
algorithm stays rectification-v5-matrix-scoring-10.
- Memoization golden v3 written by write_golden; v2 frozen by sha256 with a
test that its scores equal v3 and only the receipt policy moved.
- Collect gap copy names the exact gap ("再来两件……其中至少一件不是……")
instead of always "再来一件"; VOICE.md updated. Legacy life-events form copy
4/3 as well.
- 30 frontend test files, 4 Python tests: fixtures extended to the same
scenario at 4/3, or assertions changed with 原值/新值/原因 notes.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01N4f2nya58RoRu4yEmJgRGE

2026-10-03 00:08:00 +08:00

Jesse_ChenandClaude Opus 5.5

ea21743b09

fix(rectification): stop spoken collect once the training gate opens (BUG-1084..1087)

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

2026-09-29 10:06:57 +08:00

jesse-ux

69ffa07d6b

fix(rectification): stop speaking unstampable distinguish stems (BUG-674/675)

Independent Staging Quality Gate / validate (push) Failing after 20s

Details

Independent Staging Quality Gate / publish (push) Skipped

Details

Distinguish followups that cannot stamp a probe now go to persistExhaustionCollect instead of repeating the card stem in the assistant body. Choice focuses without asked_turn_id hang on the last assistant turn, and persisted_question with a live choice_card renders the existing card. Representative-time inconsistency is warn-only (BUG-676 investigating).

2026-09-14 03:42:48 +08:00