4 Commits

Include renames

Author	SHA1	Message	Date
osobhandClaude Opus 5.5	00b0cb0035	perf(agent): cheaper novelty scoring; complete the consolidation benchmark ... consolidation_efficiency never finished: stopped after 19 minutes on one core while building its 100K case. Not the consolidation cycle (linear: 17 us at 100 records, 2.16 ms at 10K) but the setup — every add_memory scores the new record's novelty against the whole working tier, the benchmark lets that tier reach 50K, and each comparison recomputed both norms: ~5e9 comparisons of three passes each. ImportanceScorer::score_surprise now computes the new record's norm once, takes each comparison in one fused, 8-lane pass (dot product and the other norm together), and splits a working tier of 4096+ records across threads with the `parallel` feature. Same results: tested against the old cosine formula, including shorter, empty and zero vectors and the parallel path. The work stays quadratic in the working-tier size by design; with regular consolidation the tier stays near working_capacity (100) and inserts are cheap. The complete run takes 8 min 10 s on tank and fills in the 100K cycle row (46.66 ms) and the memory-reduction table, which had never been published. The binary no longer prints a record-count ratio as a "BM25 Speedup" (never measured; Part 1 measures search latency) or claims sub-linear cycle scaling (its own numbers grow slightly faster than linearly). Co-Authored-By: Claude Opus 5.5 (1M context) <[email protected]>	2026-09-25 08:51:08 -05:00
osobhandClaude Fable 5.1	a3f7c6fe89	style: cargo fmt --all ... Formatting only. cargo fmt --check was already failing on main (accel SIMD kernels, agent, format, migrate, bench); CI now enforces it. Co-Authored-By: Claude Fable 5.1 <[email protected]>	2026-09-19 05:36:23 -07:00
ClawHDF5 Coding Agent	3c7c229e20	security(agent): gate elevated MemorySource construction behind a distinct API ... Two related trust-boundary gaps, both closed: 1. ConsolidationEngine::add_memory took a plain `source: MemorySource` parameter, so any caller could claim MemorySource::System/Correction — which get elevated importance weighting in score_correction — for content whose actual origin the caller doesn't control or hasn't verified. Split into add_memory(UntrustedSource) for ordinary caller-supplied content (User/Tool/Retrieval only, no elevated variant exists to claim) and add_trusted_memory(TrustedSource) for content whose elevated trust the caller has independently verified (System/ Correction). Updated the one production consumer outside this crate (clawhdf5-bench's consolidation_efficiency benchmark) and all tests. 2. The provenance/anomaly wiring added in the previous commit introduced the same pattern: infer_memory_source mapped source_channel == "system" or "correction" straight to the elevated MemorySource variants. Since MemoryEntry.source_channel is unvalidated caller-supplied text, this let a write dodge check_source_anomaly's User-flood detection by simply self-labeling source_channel = "system". infer_memory_source now never returns System/Correction — only Tool/Retrieval (recognized channel names) or User (everything else, the conservative default). INT-05	2026-08-17 00:49:34 +00:00
redclawsystems	3f222f6956	Merge pull request 'docs(clawhdf5): document DType variants, fix unresolved doc links' (#17) from sdlc-docs/clawhdf5-types-20260514-165210 into main	2026-05-14 23:54:48 +00:00