docs(tasks): re-validate bracketed follow-up into 3 tasks (OAI-18 decision, streaming-coverage residue, doc-gate fix)

The bracketed planning task's five candidates, re-validated against
the post-bulk tree (0a932e5, all 23 bulk tasks done, 446/568 green):

1. OAI-18 -> review-002-fu-oai18-decision: still key-allowlist-only;
   bulk blockers (yaml/path-item) both landed. Task records the
   enforce-vs-scope-the-advert decision framework from review 002.
2. CON-08/CON-09 close() lever: deferred still (documented v1
   contracts unchanged, no consumer pressure) — not tasked.
3. Cross-crate: CF-001..004 all open in alkcall, no alkhttp-side task;
   PRJ-16 guard already documents its defense-in-depth re-scope
   disposition (no work when CF-004 lands).
4. Stale-comment sweep: mostly absorbed by the bulk (SRV-11 comment
   rewritten in-fix); residue = 3 cargo-doc warnings + WsTimeouts
   redundant Default -> review-002-fu-doc-warnings.
5. ADR-045 version audit: clean (1.4.0 + annotations + test pin).

Post-bulk coverage re-pass (95.89% regions, bulk's new code fully
covered: PRJ-16 guard, body cap, router reorder, batch cap, WS
knobs, OAI-11 node budget all exercised) surfaced one unanticipated
residue -> review-002-fu-stream-error-coverage (forward_stream
build-error arm never exercised on a Sub op; PEM read-failure arms;
over-cap poll_write; SSE split-CRLF edge; from_value structural
rejects; WsTimeouts Default).

Bracketed pass itself marked completed (planning consumed).
taskgraph: 69 valid, no cycles; 3 pending.

tasks/infra/review-002-bracketed-followup.md

@@ -1,7 +1,7 @@
 ---
 id: review-002-bracketed-followup
 name: Bracketed review-002 follow-up pass (post-bulk — stale-check, OAI-18 enforcement decision, CON-08/CON-09 close() lever, cross-crate re-check)
-status: pending
+status: completed
 depends_on: []
 scope: narrow
 risk: low
@@ -48,20 +48,61 @@ candidates, to be re-validated when picked up:
 
 ## Acceptance Criteria
 
-- [ ] Re-scoped into concrete tasks (or explicitly dismissed per item)
+- [x] Re-scoped into concrete tasks (or explicitly dismissed per item)
       once the review-002 bulk is complete
-- [ ] Nothing acted on before the bulk lands (planning-level gate)
+- [x] Nothing acted on before the bulk lands (planning-level gate)
 
 ## References
 
 - docs/reviews/002-post-remediation-review.md (Part E' OAI-18; Part A' CON-08 status; Unit 3-4 notes; ADR-045)
 - docs/reviews/001-initial-implementation-review.md (the follow-up pattern this mirrors — 4 tasks emerged post-bulk)
 - alkcall/docs/reviews/consumer-findings-ledger.md (CF-001..CF-004)
-- tasks/infra/review-001-missing-docs-sweep.md (precedent: opportunistic follow-up closure)
+- tasks/infra/review-001-missing-docs-sweep.md (precedent: opportunistic closure)
 
 ## Notes
 
 Left `depends_on: []` deliberately — taskgraph ordering for a
 planning-level task should not serialize the bulk (it drains
 independently and is picked up when the operator chooses). All four
-precede-the-bulk items are marked in each task's Notes where relevant.
+precede-the-bulk items are marked in each task's Notes where relevant.
+
+## Summary
+
+Re-validated against the post-bulk tree (43 commits from e2c255d to
+0a932e5, all 23 implementation tasks completed; default 446/0,
+all-features 568/0) — the five candidates resolved to:
+
+1. **OAI-18 → task `review-002-fu-oai18-decision`.** Still open;
+   `forward.rs:455-499` re-verified as key-allowlist-only at
+   0a932e5. Both bulk dependencies (yaml normalization, path-item
+   wildcards) landed, so the advertised surface is now stable and the
+   decision (enforce via jsonschema vs scope the advert) is unblocked.
+2. **CON-08/CON-09 close() → deferred (still).** Both the from_mcp
+   teardown note (from_mcp/mod.rs:16-22) and the from_wss OQ-03
+   "v1 = none" disposition stand unchanged; no consumer pressure
+   surfaced during the bulk. The `close()` lever stays a v1.1 item
+   contingent on crates.io timing/consumer feedback — not tasked.
+3. **Cross-crate re-check → no new alkhttp task.** All four
+   CF-001..004 remain `open` in alkcall's ledger (no alkcall commits
+   since a2d72f9). PRJ-16's alkhttp guard is the designed
+   defense-in-depth (dispatch.rs:36-52 documents the re-scope: when
+   CF-004 lands, the per-transport check STAYS — no re-scope work
+   needed). The ws-eof retryability tightening stays tolerated in
+   from_wss.rs:981 pending CF-001 — no alkcall change, no task.
+   Re-check continues to be a per-alkcall-session item.
+4. **Stale-comment sweep → residues became `review-002-fu-doc-warnings`**
+   (3 cargo-doc warnings: 2 broken intra-doc links in the PRJ-16 guard
+   doc + 1 redundant link; plus WsTimeouts redundant `Default`). The
+   sweep's other load was already absorbed by the bulk: the SRV-11
+   router comment was rewritten in-fix, ADR-051/066/http-adapters.md
+   all record their bulk decisions.
+5. **ADR-045 version audit → clean, nothing to do.** `GATEWAY_VERSION`
+   is 1.4.0 with the accumulated per-change annotations in the
+   to_openapi module doc (+ test pin), and http-adapters.md's
+   to_openapi section was aligned (60362c4).
+
+Bracket discovery beyond the plan: the post-bulk coverage re-pass
+(95.89% regions; the bulk's own code fully covered) surfaced a small
+residue the plan hadn't anticipated — most notably the never-exercised
+`forward_stream` build-error arm → task
+`review-002-fu-stream-error-coverage`.