Skip to content

Solution for long term memory for agent coding CLIs and to facilitate handoff between different agent vendors

Rust

docs(benchmarks): record the 3.2.4 release gate

AkitaOnRailsc12094f952ff
diff --git a/docs/benchmarks/README.md b/docs/benchmarks/README.md
index 69438f5e..6786ed5a 100644
--- a/docs/benchmarks/README.md
+++ b/docs/benchmarks/README.md
@@ -13,6 +13,8 @@ cargo run --release -p ai-memory-eval -- retrieval --fetch
| date | dataset | mode | overall hit@5 | file |
|---|---|---|---|---|
+| **2026-10-25** | LongMemEval-S (v1) | **zero-llm FTS + observation stream (3.2.4 release)** | **0.951** | [longmemeval-s-3.2.4-release.md](longmemeval-s-3.2.4-release.md) |
+| **2026-10-25** | LongMemEval-S (v1) | **local embeddings + observation stream (3.2.4 release)** | **0.945** | [longmemeval-s-3.2.4-release.md](longmemeval-s-3.2.4-release.md) |
| **2026-10-22** | LongMemEval-S (v1) | **zero-llm FTS + observation stream (3.2.2 release)** | **0.951** | [longmemeval-s-3.2.2-release.md](longmemeval-s-3.2.2-release.md) |
| **2026-10-22** | LongMemEval-S (v1) | **local embeddings + observation stream (3.2.2 release)** | **0.945** | [longmemeval-s-3.2.2-release.md](longmemeval-s-3.2.2-release.md) |
| **2026-10-22** | LongMemEval-S (v1) | **zero-llm FTS + observation stream (3.2.1 release)** | **0.951** | [longmemeval-s-3.2.1-release.md](longmemeval-s-3.2.1-release.md) |
@@ -33,6 +35,12 @@ cargo run --release -p ai-memory-eval -- retrieval --fetch
| 2026-09-01 | LongMemEval-S (v1) | zero-llm, stopword-filtered FTS (prior) | 0.668 | [longmemeval-s-2026-09-01-fts.md](longmemeval-s-2026-09-01-fts.md) |
| 2026-09-01 | LongMemEval-S (v1) | zero-llm (pre-2.0 FTS) | 0.617 | [longmemeval-s-2026-09-01.md](longmemeval-s-2026-09-01.md) |
+The 3.2.4 patch-release run found FTS identical to 3.2.2 at every accuracy
+cutoff and local embeddings unchanged at `hit@5` overall and on every slice.
+Local `hit@1` and `hit@10` improved. See the
+[3.2.4 release report](longmemeval-s-3.2.4-release.md) for provenance and the
+load-sensitive latency and ingest comparison.
+
The 3.2.2 patch-release run found FTS identical to 3.2.1 on every question.
Local embeddings moved from 0.949 to 0.945 `hit@5`, inside the pre-registered
overall noise band; the two changed questions remain within the top ten, and
diff --git a/docs/benchmarks/longmemeval-s-3.2.4-release.md b/docs/benchmarks/longmemeval-s-3.2.4-release.md
new file mode 100644
index 00000000..b1eb9e76
--- /dev/null
+++ b/docs/benchmarks/longmemeval-s-3.2.4-release.md
@@ -0,0 +1,77 @@
+# LongMemEval-S release benchmark: 3.2.4
+
+The 3.2.4 release benchmark runs all 470 answerable LongMemEval-S questions
+through the shipped hook capture pipeline. It measures the default zero-LLM
+FTS path and the in-process local embedder, both with the production-default
+observation stream enabled.
+
+## Provenance
+
+- code: both modes used `f4b283de04f470f807e493e7f0779f0494188198`,
+ the frozen 3.2.4 code candidate before the documentation and version commits.
+- dataset: `longmemeval_s`, sha256
+ `08d8dad4be43ee2049a22ff5674eb86725d0ce5ff434cde2627e5e8e7e117894`.
+- hardware: AMD Ryzen 9 7950X3D (32 threads), with no other deliberate
+ workload during the run.
+- commands, after building `ai-memory` and `ai-memory-eval` in release mode:
+
+ ```bash
+ ai-memory-eval retrieval \
+ --server-bin target/release/ai-memory \
+ --concurrency 6 --http-timeout-secs 900 \
+ --server-env AI_MEMORY_RETRIEVAL__OBSERVATION_STREAM=true \
+ --server-env AI_MEMORY_EVAL_SKIP_WIKI_CHECKPOINTS=1
+
+ ai-memory-eval retrieval \
+ --server-bin target/release/ai-memory \
+ --concurrency 6 --http-timeout-secs 900 \
+ --embeddings local \
+ --server-env AI_MEMORY_RETRIEVAL__OBSERVATION_STREAM=true \
+ --server-env AI_MEMORY_EVAL_SKIP_WIKI_CHECKPOINTS=1
+ ```
+
+- run dirs: `evals/runs/2026-10-25T15-37-36-037419279Z-retrieval` (FTS)
+ and `evals/runs/2026-10-25T15-38-37-620897357Z-retrieval` (local).
+
+## Results
+
+FTS matches 3.2.2 exactly at every accuracy cutoff and in its returned-context
+estimate. Local embeddings keep the same `hit@5`, `recall@5`, and context
+estimate. Local `hit@1` improves by four questions and `hit@10` improves by one.
+
+| mode | hit@1 | hit@3 | hit@5 | hit@10 | recall@5 | recall@10 | p50 | p95 | mean context tokens |
+|---|---:|---:|---:|---:|---:|---:|---:|---:|---:|
+| FTS 3.2.2 | 0.857 | 0.930 | 0.951 | 0.972 | 0.893 | 0.937 | 12 ms | 73 ms | 534.8 |
+| **FTS 3.2.4** | **0.857** | **0.930** | **0.951** | **0.972** | **0.893** | **0.937** | **12 ms** | **79 ms** | **534.8** |
+| local 3.2.2 | 0.755 | 0.900 | 0.945 | 0.974 | 0.880 | 0.940 | 188 ms | 468 ms | 535.2 |
+| **local 3.2.4** | **0.764** | **0.906** | **0.945** | **0.977** | **0.880** | **0.943** | **149 ms** | **350 ms** | **535.2** |
+
+Every local-embedding slice has the same `hit@5` as 3.2.2:
+
+| slice | n | 3.2.2 | 3.2.4 | delta |
+|---|---:|---:|---:|---:|
+| knowledge-update | 72 | 1.000 | 1.000 | 0.000 |
+| multi-session | 121 | 0.975 | 0.975 | 0.000 |
+| single-session-assistant | 56 | 0.893 | 0.893 | 0.000 |
+| single-session-preference | 30 | 0.867 | 0.867 | 0.000 |
+| single-session-user | 64 | 0.953 | 0.953 | 0.000 |
+| temporal-reasoning | 127 | 0.921 | 0.921 | 0.000 |
+
+## Latency and ingest
+
+FTS query latency moved from 12/73 ms to 12/79 ms p50/p95. Local query
+latency moved from 188/468 ms to 149/350 ms. These runs shared the same
+hardware but not a controlled load, so the changes are not attributed to the
+patch.
+
+FTS ingested 278,946 items in 60.8 seconds, against 61.9 seconds in 3.2.2.
+Local embeddings ingested the same items in 1,430.6 seconds, 7.2% slower than
+3.2.2's 1,335.1 seconds. Ingest wall time is load-sensitive; the unchanged
+accuracy, context size, item count, and zero raw-observation fallback hits do
+not indicate a retrieval regression.
+
+## Verdict
+
+There is no material retrieval regression. FTS is exact on accuracy, local
+`hit@5` is exact overall and on every slice, and local top-ten accuracy and
+recall improve. The 3.2.4 release gate passes.