Python
release: hy-memory 2.0.10
alvinfei6cad02bc8225
diff --git a/CHANGELOG.md b/CHANGELOG.mdindex 8ba160e..8a72d7a 100644--- a/CHANGELOG.md+++ b/CHANGELOG.md@@ -4,7 +4,9 @@ Hy Memory and MemHub are versioned and released independently.## Unreleased-- Hy Memory: new `hy_memory.reembed` module for switching the embedding+## Hy Memory 2.0.10 — 2026-11-01++- new `hy_memory.reembed` module for switching the embeddingmodel. Writers must be paused for the whole run. Nothing is derived fromthe provider or endpoint: source and target are named explicitly, and theidentity of a space is the model name plus the width (`space_identity`).@@ -36,14 +38,14 @@ Hy Memory and MemHub are versioned and released independently.graph is opened read-only and kept for rollback. A run that fails or iscancelled leaves no target behind, and a rerun starts over.`verify_graph_reembed` and `drop_graph` complete the graph side.-- Hy Memory: `EmbedService.embed_batch` now splits large batches into+- `EmbedService.embed_batch` now splits large batches intorequests of `embedder.batch_size` texts each (`MEMORY_EMBEDDER_BATCH_SIZE`,default 64); before, it sent them all in one request. On a 429 it waits forthe `Retry-After` time plus jitter, capped at 60 s. It takes a per-call`max_retries`. A returned vector whose width differs from the configured`embedding_dims` now raises `EmbeddingDimensionMismatchError` and is notretried.-- Hy Memory: Raw conversations are stored already trimmed. MemHub now keeps every raw+- Raw conversations are stored already trimmed. MemHub now keeps every rawforever and lite mode stores nothing else, so tool output and long pastedlogs no longer stay in full. One rule (`hy_memory/utils/raw_trim.py`) isapplied to each message when the raw is written:@@ -63,7 +65,7 @@ Hy Memory and MemHub are versioned and released independently.reading the history back no longer rewrites the omitted-count markers. Thetext embedded for `L1_RAW` is the trimmed text. New raws carry`custom.raw_trimmed=true`.-- Hy Memory: extractor history ("last k messages") now joins the stored raws directly+- Extractor history ("last k messages") now joins the stored raws directlyand does not trim them again. Raws written before this change have no`raw_trimmed` flag, so they are still trimmed with the same rule when theyare read. The extractor still receives the current batch in full (tooldiff --git a/pyproject.toml b/pyproject.tomlindex 76ac57d..a9c35dc 100644--- a/pyproject.toml+++ b/pyproject.toml@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"[project]name = "hy-memory"-version = "2.0.9"+version = "2.0.10"description = "HY Memory - Industrial-grade dual-system cognitive memory framework"readme = "README.md"requires-python = ">=3.9"