linkedin-studio/docs/hardening
Kjell Tore Guttormsen 69f37ba2b3 docs(linkedin-studio): cold-review R3 (Engage surfaces) — independent kald-review of 4 surfaces
Reproduces the S1/R2a/R2b non-fabricating method: 2 blind cold Opus lenses for
the round (intent + correctness), each covering all 4 surfaces, no cross-feed,
every mechanical claim tool-grounded. Surfaces: firsthour, calendar,
headless-review, pivot.

Verdict REWORK — 1 of 4 surfaces, 1 MAJOR; 0 BLOCKER:
- calendar: the queue load (queueFormatSummary) surfaces none of the
  id/draft_path/character_count that publish/reschedule/cancel require, and the
  reschedule step's "carry from the entry shown in Step 2" is a direct
  contradiction (those fields are never shown) -> MAJOR
- firsthour: ALLOW (1 MINOR bare ref paths; clipboard printf pointer)
- headless-review: ALLOW (2 MINOR: SendUserFile absent from allowed-tools on the
  primary surfacing path; dead v3.1.0 reload anchor post version-reset)
- pivot: ALLOW (clean — heuristic, worked example, off-by-one phase map all
  reconcile)

Independence axis earned its keep again: convergence on headless SendUserFile
(both lenses) + one divergence resolved by main grounding (calendar -
intent-lens flagged the data-gap MAJOR, correctness-lens passed it on structural
arithmetic; main grounded queueFormatSummary's output and confirmed the MAJOR,
same shape as R2b's newsletter resumption table).

Connects to existing systemic findings (no new cross-cutting): clipboard printf
(firsthour confirmed, folds into R2a's 10-file finding) and bare reference paths
(firsthour adds 3 sites to R2b's pattern). New SUGGESTION-class pattern:
allowed-tools over-declaration on 3 of 4 surfaces.

Counts: 0 BLOCKER, 1 MAJOR, 3 MINOR, 5 SUGGESTION. Cumulative cold-review
coverage 17/29. Review finds; changes no code. test-runner 138/0 unchanged.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_012GqEHp4uDiivfrAUjw4BdE
2026-06-30 09:29:47 +02:00
..
brief.md docs(linkedin-studio): hardening-phase foundation (brief + adversarially-reviewed plan) 2026-05-31 05:31:52 +02:00
log.md docs(linkedin-studio): S31c hardening log entry + STATE session-end — S31 complete (a+b+c) 2026-06-20 09:54:55 +02:00
plan.md fix(linkedin-studio): S28 ref-consistency B — format magnitudes → SSOT 2026-06-19 22:17:54 +02:00
review-R2a.md docs(linkedin-studio): cold-review R2a (Create emitters) — independent kald-review of 5 surfaces 2026-06-30 07:18:43 +02:00
review-R2b.md docs(linkedin-studio): cold-review R2b (Create orchestrators) — independent kald-review of 4 surfaces 2026-06-30 08:58:44 +02:00
review-R3.md docs(linkedin-studio): cold-review R3 (Engage surfaces) — independent kald-review of 4 surfaces 2026-06-30 09:29:47 +02:00
review.md fix(linkedin-studio): S1 hardening — method calibration (quick) + Start journey 2026-05-31 06:46:11 +02:00