root/Jyotisha

Fork 0

Files

T

Jesse_Chen 30ef6afea7

Independent Staging Quality Gate / validate (push) Has been cancelled

Details

Independent Staging Quality Gate / publish (push) Has been cancelled

Details

docs(rectification): archive upstream playbook and add stop-rule task

The upstream interview playbook and evidence thresholds resolve task 0.
Upstream stops and reports when evidence is thin — fewer than three dated
events, fewer than two domains, or a tie — while this repo treats the same
kind of thresholds as a confirmation gate and keeps asking when they are
not met. Its label ladder has no confirmed rung at all, and every contract
test asserts candidate_range_not_birth_time_truth.

Task 1 capped the interview by round count, which is half of it. Task 6
adds the evidence-state stop rules, reframes exhausted as a normal
delivery, adopts the upstream label ladder and closing wording, and keeps
the 4/3 confirmation gate separate from the 3/2 delivery floor.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_0155nFCgCHtoA7jhSDGmZmMu

2026-08-31 02:27:32 +00:00

2.2 KiB

Raw Blame History

Interview Playbook

Intake

Collect birth date, birthplace, timezone, known time/range, source of the time, confidence in that source, and the user's priority domain. Ask permission before collecting dated life events.

Routes

`range`

For a remembered time or bounded interval:

Restate the interval in clock time.
Split it into early / middle / late.
Ask 3-5 A/B/C/D questions across education, relocation, relationship, career, and recent learning/expression.
Request dated events only in the strongest 2-3 domains.

`block`

For morning, afternoon, evening, family recollections, or zodiac-hour style descriptions:

Convert the label into a stated coarse interval.
Split that interval into early / middle / late.
Ask the same domain questions.
Request events from the leading domains only.

`unknown`

For no usable time memory:

State that the first valid result can only be a broad block.
Compare morning / afternoon / evening / night through high-signal domains.
Do not refine the winning block until enough dated evidence exists.
If one broad block leads, begin the next round by splitting only that block.

Event Ledger

Use one row per event with:

id
domain
date
precision (day, month, year)
reliability (high, medium, low)
user wording
supports (candidate labels helped by this event)
conflicts (candidate labels weakened by this event)

Confirm date precision instead of inventing a day.

Question Rhythm

First round: 3-5 high-information A/B/C/D questions.
Second round: ask only for dated events in the strongest domains.
Third round: ask only the next 1-3 events that could separate the top candidates.
Never collect a long autobiography before the first route decision.

Stop Rules

Stop and report the current interval when any is true:

fewer than three dated events
fewer than two domains
tied first-place candidates
user uncertainty is too high to map support/conflict reliably
an optional adapter was promised but cannot be executed and the user wants an audited result

Final Wording

State: "当前最优结果是候选时间段，而不是已经确认的唯一出生分钟。临时代表时间仅用于下一轮验证与比较。"

2.2 KiB Raw Blame History