4 Commits

Include renames

Author	SHA1	Message	Date
Jesse_ChenandClaude Opus 5	f8aea88bc3	docs(rectification): archive session records and add delivery-gap tasks ... Two real local sessions are archived. In them the agent states twice that its minute came from a report already in the upstream repo rather than from the user's answers, and the follow-up "fix" wired that answer into the scoring chain; upstream now carries a Narayana tie-break derived from that single case. This repo was checked and is clean, so two red lines now keep it that way and gate any upstream sync. The same records show what the answers genuinely bought: a 30-minute window narrowed to 3. Tasks 7-10 add what makes that deliverable — the per-answer narrowing table, an explain surface, mid-case window changes with evidence retained, and the batched first round. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_0155nFCgCHtoA7jhSDGmZmMu	2026-08-31 03:05:11 +00:00
Jesse_ChenandClaude Opus 5	30ef6afea7	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
Jesse_ChenandClaude Opus 5	db6716e76c	docs(rectification): rewrite convergence brief after upstream comparison ... Comparing against the upstream skill repo overturned v1's premise. The three methodology files are byte-identical across both repos, and the production v5 scorer imports the same upstream event engine the v4 ranker does, so swapping engines is off the table and v1's three-way bake-off is dropped. What productization actually dropped is the stopping mechanism: upstream terminates on a fixed 8-question bank and a one-shot adjudication, while the production decision path discriminates as long as a probe exists. The round budget is computed but never read by that path, and the "exhausted" branch it needs already exists. Tasks now wire that budget in, restore the upstream next-step summary, and keep the report readable from turn zero. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_0155nFCgCHtoA7jhSDGmZmMu	2026-08-30 19:35:52 +00:00
Jesse_ChenandClaude Opus 5	7db2dd2de0	docs(rectification): add convergence refactor task brief ... Audit found three unrelated rectification scoring paths: the local-agent methodology references, the production v5 server scorer, and the v4 fact ranker that only the eval scripts import. The sealed holdout numbers measure the third one, so neither the production path nor the local path has ever been evaluated. Task 0 is therefore a blind three-way bake-off on one case set, gating every later task. The remaining tasks cover a single convergence function with property tests, moving question authority fully to the server, making the deliverable exist from turn zero, and the calibration data shortage. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_0155nFCgCHtoA7jhSDGmZmMu	2026-08-30 18:45:30 +00:00