v0.14.0 — Performance & Benchmarking

Performance & Benchmarking

This release focuses on profiling hot paths across the framework and delivering measurable performance improvements, along with expanded benchmark coverage for recently added components.

Performance Improvements

Area	Metric	Improvement
ToolRegistry spec generation	uncached 50-tool lookup	-33% (10.4 µs → 6.9 µs)
Chain transforms	3-stage pipeline	-30% (287 ns → 210 ns)
HotSwapAgent prompt	simple prompt	-18% (2.5 µs → 1.8 µs)
HotSwapAgent swap	model swap	-26% (140 ns → 112 ns)
DAG fan-out	3-way fan-out + merge	-11% (10.9 µs → 10.5 µs)

What Changed

• ToolRegistry: generation-based cache invalidation — tool_specs() uses a generation counter to detect stale caches, avoiding redundant recomputation.
• Memory contiguous slice clone — SlidingWindowMemory and TokenWindowMemory now use make_contiguous().to_vec() instead of iter().cloned().collect(), producing a single memcpy.
• SlidingWindowMemory: single-pop eviction — replaced while loop with single if check since only one message is added at a time.
• ReAct loop: reduced cloning — tool calls moved with std::mem::take instead of .to_vec(); middleware short-circuit paths move messages instead of cloning.
• MiddlewareStack: early return when empty — all three middleware pipeline methods return Continue immediately when no middleware is registered.

New Benchmarks

• HotSwapAgent (prompt, swap_model)
• InProcessBroker (submit/receive/complete roundtrip)
• InProcessEventBus (publish/receive)
• InMemoryCheckpoint (save/load)
• SerializableStreamEvent (serialize/deserialize)

Full Changelog: v0.13.0...v0.14.0