Conversation
d5a23c4 to
791a320
Compare
This was
linked to
issues
Mar 30, 2026
c7f7e15 to
05c8820
Compare
…l-conditioned write gate Closes #2419, #2444, #2408. - #2419: Add .local/testing/bench-memory.py — seeds N facts, runs M recall queries, reports hit_rate/latency/compression/interference as JSON with CSV append for longitudinal tracking. - #2444: Add cost-sensitive store routing to zeph-memory. New StoreRouter trait with HeuristicRouter, LlmRouter, and HybridRouter. HybridRouter uses heuristic confidence signal and escalates to LLM only when ambiguous. New [memory.store_routing] config section with routing_classifier_provider field. Follow-up wiring: #2484. - #2408: Add CraniMem goal-conditioned write gate to admission control. goal_utility added as 6th AdmissionFactor. Gate is disabled by default (goal_conditioned_write = false). Degenerate goal text guard (<10 chars) prevents arbitrary admission on trivial inputs. New goal_utility_provider config field. Follow-up wiring: #2483.
05c8820 to
e0fcecb
Compare
bug-ops
added a commit
that referenced
this pull request
Mar 30, 2026
Adds .local/testing/bench-memory.py: stdlib-only Python benchmarking harness that seeds N facts into SQLite (FTS5), runs M recall queries, and reports hit_rate, avg_recall_latency_ms, p50_ms, p99_ms, compression_ratio, and interference_rate as JSON with CSV append for longitudinal tracking. Closes #2492
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
.local/testing/bench-memory.py— stdlib-only Python benchmarking harness that seeds N facts into memory, runs M recall queries, and reportshit_rate,avg_recall_latency_ms,p50_ms,p99_ms,compression_ratio,interference_rateas JSON with CSV append for longitudinal tracking.zeph-memory. NewStoreRoutertrait withHeuristicRouter,LlmRouter, andHybridRouter. Hybrid uses heuristic confidence and escalates to LLM only when ambiguous. New[memory.store_routing]config withrouting_classifier_providerfield. Deferred wiring tracked in feat(memory): wire StoreRoutingConfig into build_router() for cost-sensitive routing #2484.goal_utilityadded as 6thAdmissionFactor. Disabled by default (goal_conditioned_write = false). Degenerate goal text guard (<10 chars) prevents arbitrary decisions on trivial input. Newgoal_utility_providerconfig field. Deferred wiring tracked in feat(memory): wire goal_text from agent context into remember() calls for CraniMem write gate #2483.Closes #2419, #2444, #2408.
Test plan
cargo nextest run --config-file .github/nextest.toml --workspace --features full --lib --bins— 7455 passedcargo +nightly fmt --check— cleancargo clippy --features full --workspace -- -D warnings— clean