Refresh performance ledger and close small append audit

[tomsanbear]

Refreshes the full single-file performance ledger and records the completed four-element append investigation.

Ledger corrections:

• Makes the top active roadmap the only actionable checkbox set
• Updates merged repository, compact-header, allocator, and corrected Linux state
• Resolves stale tagging, safety, post-append, builder, platform, and baseline entries
• Adds the July 11 decision history

Append result:

• Pre-change assembly showed an out-of-line reserve call on the forced wrapper
• Candidate removed 27.6% of fixed-driver instructions and 18.2% of branches
• Seven exact-parent system-allocator rounds found no wall-time improvement: +0.51% at four elements, interval -0.05%..+0.87%
• 1,024 elements and unchanged Vec controls were neutral
• Candidate was reverted; net library code diff is zero
• The focused JackVec/Vec gap was ~3.45%, showing the five-library 33.4% point is code/link-layout sensitive rather than a clear implementation target

Validation: Rust 1.97 all-target tests, Rust 1.86 all-target and no-std feature checks, comparison tests, reporting tests, warning-denied Clippy/docs, formatting, and diff hygiene.

[codspeed-hq]

Merging this PR will not alter performance

⚡ 2 improved benchmarks
❌ 2 regressed benchmarks
✅ 106 untouched benchmarks

Warning

Please fix the performance issues or acknowledge them on CodSpeed.

Performance Changes

	Benchmark	BASE	HEAD	Efficiency
❌	ThinVec[4]	132.5 ns	161.7 ns	-18.04%
❌	JackVec[4]	192.5 ns	221.7 ns	-13.16%
⚡	SmallVec4[4]	174.4 ns	145.3 ns	+20.08%
⚡	SmallVec8[8]	277.5 ns	248.3 ns	+11.74%

Tip

Investigate this regression by commenting @codspeedbot fix this regression on this PR, or directly use the CodSpeed MCP with your agent.

---

_{Comparing perf/append-small-audit (2d516da) with main (55ea7c3)}