perf: validate secondary formatting, chart and frame-scratch hotspots

[subinium]

Priority: P2
Evidence: Investigation; costs identified in source, aggregate impact unmeasured
Baseline: v0.23.0 source 37933f9, audited 2026-09-05. Native execution/compile probes used Rust 1.98.0 on aarch64 macOS unless explicitly stated otherwise.

Problem and Reproduction

Potential costs include histogram full sorting for min/max/counting, repeated Sequence duration sums, selection cells scanning the content map, owned WASM events copied through frame's slice API, and newly allocated named-focus/consumed scratch. These are not established top bottlenecks.

src/chart/bar.rs:67 · src/anim.rs:561 · src/terminal/selection.rs:119 · crates/slt-wasm/src/lib.rs:990 · src/context/runtime.rs:243

Scope

• Measure each candidate separately and only land independently justified changes.
• Compare one-pass min/max, immutable duration caching, interval-based selection lookup, frame_owned and scratch reuse.
• For ANSI integer formatting, prefer MSRV-compatible buffer writes before considering newer standard-library APIs.

Expected Effect

Capture low-risk savings after larger correctness and scaling issues, without speculative refactoring or an unnecessary MSRV bump.

Acceptance Criteria

• Provide per-candidate release timings/allocation deltas and output/interaction parity tests.
• Public mutation, event ordering/consumption and selection boundaries remain correct.
• Do not aggregate unrelated changes into one unreviewable implementation commit.
• Record rejected candidates as measured no-change decisions.
• Follow the repository quality gates and the evidence rules in tracking: post-v0.23 correctness, resource efficiency and WASM completion #366; record actual results rather than treating a proposed test as passed.

Boundaries and Dependencies

Local1.98.0 was the audit baseline; patched stable should be used for future validation. New1.98 formatting APIs are optional tradeoffs, not a requirement to raise MSRV1.88.

• perf: establish release-mode workload, allocation and idle-resource baselines #414
• wasm: replace unsupported time sources on the browser frame path #403

Related closed work: #81, #269. This is a scoped follow-up at the audit baseline, not a claim that every prior fix is absent.

Tracking: #366. This issue records unresolved work, not an implemented fix.

[subinium]

v0.24.0 Disposition

Histogram work uses finite-value linear passes; Sequence duration is cached; event/focus scratch is reclaimed. Unit/output parity and scoped diagnostics pass. These microbenchmarks do not establish a general full-frame or end-to-end latency gain. Keep the remaining secondary-hotspot validation bounded and measurement-driven.

Implementation and evidence mapping: PR #433. Release v0.24.0 and its 20/20 release workflow are verified. This issue stays open only for the remaining acceptance/investigation described above; publication alone does not establish it.