test: clean up the paid eval lane (B1-B4, B6, B7)

- B1: delete paid files that assert nothing or cannot pass meaningfully:
  skill-llm-eval-spec and skill-e2e-spec-execute (test.todo), gemini-e2e
  (+ gemini-session-runner; no gemini CLI in CI), ship-idempotency (red
  since v1.63), the two opus-4-7 *-sonnet overlay wrappers, conductor-prose
  (+ its source-evaluation replay), codex-e2e-plan-format; drop their keys,
  scripts and census rows.
- B2: skill-llm-eval grades browse/sections/command-list.md with one union
  judge that also carries the baseline score pin; regression-vs-baseline
  deleted (paid run: pass, c4/c4/a4).
- B3: memory-pipeline, ios-qa, ios-qa-swift-build and plan-tune-cathedral
  make no model calls; renamed out of the paid glob so they run on every
  PR. Swift builds need GSTACK_TEST_SWIFT=1; device stub deleted.
- B4: codex-e2e*, outside-voice, aside and ios-device cannot run in the CI
  image; excluded from the weekly lane with a tracked re-entry condition.
- B6: fold opus-47's negative routing controls into skill-routing-e2e
  journey-negatives (paid run: 3/3 unrouted) and delete the file.
- B7: delete the never-green brain-privacy-gate eval; a free
  gstack-skill-start test now proves consent precedes artifacts egress.

scripts/paid-test-durations.json

@@ -15,14 +15,12 @@
     "test/skill-e2e-investigate-owned-termination.test.ts": 49000,
     "test/skill-e2e-learnings.test.ts": 32000,
     "test/skill-e2e-office-hours-auto-mode.test.ts": 61000,
-    "test/skill-e2e-opus-47.test.ts": 20000,
     "test/skill-e2e-plan-ceo-finding-floor.test.ts": 233000,
     "test/skill-e2e-plan-ceo-plan-mode.test.ts": 35000,
     "test/skill-e2e-plan-design-with-ui.test.ts": 435000,
     "test/skill-e2e-plan-devex-finding-floor.test.ts": 187000,
     "test/skill-e2e-plan-devex-plan-mode.test.ts": 103000,
     "test/skill-e2e-plan-mode-no-op.test.ts": 206000,
-    "test/skill-e2e-plan-tune-cathedral.test.ts": 1000,
     "test/skill-e2e-plan-tune.test.ts": 58000,
     "test/skill-e2e-plan.test.ts": 312000,
     "test/skill-e2e-qa-workflow.test.ts": 437000,

scripts/test-paid-shards.ts

@@ -393,7 +393,7 @@ export interface DiffSkipOptions {
  *     than literal.
  *
  * FAIL-OPEN by construction: run-all selection, non-skill-e2e paid files
- * (llm-judge / codex-e2e / gemini-e2e / routing, keyed off other maps),
+ * (llm-judge / codex-e2e / routing, keyed off other maps),
  * unreadable sources, and files with zero mapped names all KEEP their shard —
  * the child's self-skip stays authoritative. A parent bug may only run
  * extra work, never drop it.