docs: three guidance-extraction defects, found by reading the data back

docs: close both defects in the run record, and correct one classification

data: re-extract 88 periods, guidance from the calls, segments on six tickers

docs: implementation plan for the data foundation (sub-project 1)

docs: correct Workstream C — the two fallback causes, diagnosed

docs: analysis-depth roadmap and the data-foundation spec behind it

docs: design spec for falsification conditions (sub-project D)

chore: rename the project to Readthrough

Merge branch 'sdd/prospection': buy-side prospection sub-system

docs: preserve the prospection execution decision log

docs: fix the real bootstrap block - pass 1 gated on a value it cannot have

docs: rule on the Task 14 findings - the Tier 1 bootstrap circularity

docs: separate enforced refusals from human process rules in the prospection README

docs: rule on the Task 13 CLI findings

docs: rule on the Task 12 demo-builder findings

docs: the RGPD placeholder must appear exactly once (T11)

docs: rule on the Task 11 validator findings

docs: drop a duplicated pytest import in the Task 10 test

docs: rule on the Task 10 compliance findings

docs: word-bound the holdings reject list so TotalEnergies survives (T9)

docs: rule on the Task 9 holdings findings

docs: sync Task 9 with the retrieved_at column and the PDF fixture gitignore rule

docs: close the unclosed-script leak and restore feminine role forms (T8)

docs: rule on the Task 8 signal findings

docs: rule on the Task 7 provider findings

docs: the LinkedIn test must name a vendor to reach the path it checks

docs: rule on the Task 6 waterfall findings

docs: note where the usual-name convention is applied (Task 6)

docs: rule on the Task 5 scoring findings

docs: rule on the Task 4 findings

docs: rule on the Task 3 registry findings

Merge branch 'sdd/attention-brief' into attention-dashboard

docs: rule on the Task 1 provenance gap

docs: pre-flight rulings on the prospection plan

fix: close four review minors on the attention-ordered brief

docs: prospection plan, tasks 12-14 and self-review

docs: use the real agent/llm.py API in the compose task

docs: prospection plan, tasks 10-11

docs: prospection plan, tasks 7-9

docs: prospection implementation plan, tasks 1-6

docs: spec the buy-side prospection sub-system

fix: correct two false claims in the attention-ordered brief spec

docs: add implementation plan for the attention-ordered company view

fix: correct fetch_earnings return shape in the consensus archive plan

docs: add implementation plan for the consensus archive

docs: add attention-ordered dashboard roadmap and first two sub-project specs

docs: add implementation plan for The Brief dashboard redesign

docs: add design spec for The Brief dashboard redesign

fix: restore evidence_snippet threading lost from an earlier uncommitted edit

fix: correct plan's continuity-category test to expect coercion