feat: add #bm:links_to directive for ambiguous relations

.claude-plugin/marketplace.json

@@ -6,14 +6,14 @@
   },
   "metadata": {
     "description": "Official Basic Memory plugins from the canonical basic-memory repository",
-    "version": "0.22.1"
+    "version": "0.23.0"
   },
   "plugins": [
     {
       "name": "basic-memory",
       "source": "./plugins/claude-code",
       "description": "The bridge between Claude's working memory and Basic Memory's durable knowledge graph \u2014 session briefings, pre-compaction checkpoints, and capture reflexes",
-      "version": "0.22.1",
+      "version": "0.23.0",
       "author": {
         "name": "Basic Machines"
       },

CHANGELOG.md

@@ -2,7 +2,7 @@
 
 ## Unreleased
 
-## v0.23.0 (2026-08-XX)
+## v0.23.0 (2026-08-23)
 
 Semantic search grows up and concurrent writes stop deadlocking. Search gains
 opt-in cross-encoder reranking, pluggable vector indexes with a first-party
@@ -229,6 +229,11 @@ search entries.
 - **#1073**: `edit_note` with a `memory://` URL routes to the target
   project instead of creating phantom notes (**#1066**), and scoped
   `memory://` URL paths are preserved (**#1092**).
+- **#1299**: `build_context` bounds its traversal requests — primary pages
+  cap at 50 results, related context at 100 per page, and negative
+  `max_related` is rejected instead of acting as an unbounded SQL limit —
+  so a traversal call can no longer become a multi-megabyte vault export
+  (**#1296**). Callers paginate or follow returned `memory://` links.
 - **#1285**: Glob-filtered directory listings traverse subdirectories
   again: `file_name_glob` filters results instead of accidentally pruning
   recursion, so `*.md` with depth 2 finds files inside subdirectories.
@@ -261,6 +266,15 @@ search entries.
   `create_time` — timestamps fall back to `update_time`, then the earliest
   message time, so the whole archive imports (**#1276**); undecodable
   import uploads return a 400 with the parse error instead of a 500.
+- **#1298**: The update check no longer reports "up to date" when the
+  Homebrew probe fails, no longer auto-runs `brew upgrade` for an update
+  inferred from PyPI metadata, and names the actual Homebrew target
+  version it will install.
+- **#1300 / #1302**: The multilingual-E5 prefix contract is documented —
+  asymmetric FastEmbed models need `semantic_embedding_query_prefix` /
+  `semantic_embedding_document_prefix`, which already drive reindex through
+  the embedding identity — along with custom-model selection, the installed
+  FastEmbed catalog, and dimensions (**#1264**).
 - **#1058 / #1094**: `bm doctor` never prints a blank failure message, and
   migrations adapt to existing event loops (**#1027**).
 - **#1080**: Loading config no longer recreates an empty `~/basic-memory`
@@ -279,7 +293,9 @@ search entries.
   registration APIs instead of private PluginManager writes, preserving the
   lifecycle ownership that cleans them up on provider unload (**#1257**);
   the slash-command monkeypatch docs are split by Hermes version so modern
-  installs skip the legacy collector workaround (**#1278**).
+  installs skip the legacy collector workaround (**#1278**), and the install
+  docs require a Hermes release with managed manifest-v2 installation
+  instead of the nonexistent `--path` option (**#1280**, **#1303**).
 
 ### Maintenance
 
@@ -292,6 +308,12 @@ search entries.
 - Kept Milvus as a first-party optional vector backend while removing the
   unused Python entry-point registry for separately packaged vector
   adapters.
+- **#1292 / #1293**: The dev-release pipeline publishes again via PyPI
+  trusted publishing — its version gate imported a hardcoded module version
+  and had silently skipped every dev publish since the 0.22.1 bump.
+- **#1304 / #1307**: The concurrent-write convergence benchmark is ported
+  into the canonical `/benchmarks` package, and the read-load benchmark
+  runs against the current MCP SDK's typed result fields.
 
 ## v0.22.1 (2026-06-12)
 

benchmarks/AGENTS.md

@@ -7,7 +7,7 @@ directory for comparing Basic Memory against other memory systems.
 
 Primary goals:
 - Deterministic retrieval benchmarks
-- Optional LLM-as-a-judge benchmarks
+- End-to-end QA scoring with fixed answerer and judge models
 - Public, reproducible artifact publication (including provenance metadata)
 
 The benchmark package keeps its own `pyproject.toml` and lockfile so benchmark
@@ -16,7 +16,6 @@ dependencies do not pollute the Core product environment.
 ## Build / Test Commands
 
 - Install: `uv sync --group dev`
-- Install judge extras: `uv sync --group dev --extra judge`
 - Run tests: `uv run pytest -q`
 - Lint: `uv run ruff check .`
 - Type check: `uv run pyright`
@@ -37,8 +36,8 @@ Dataset and conversion:
 Run retrieval:
 - `uv run bm-bench run retrieval --providers bm-local,mem0-local --dataset-id locomo --dataset-path benchmarks/datasets/locomo/locomo10.json --corpus-dir benchmarks/generated/locomo/docs --queries-path benchmarks/generated/locomo/queries.json --output-root benchmarks/runs --allow-provider-skip`
 
-Run judge (optional):
-- `uv run bm-bench run judge --run-dir benchmarks/runs/<run-id>`
+Run end-to-end QA scoring:
+- `uv run bm-bench run qa --run-dir benchmarks/runs/<run-id> --answerer claude:claude-haiku-4-5 --judge claude:claude-sonnet-4-6`
 
 Validate and publish:
 - `uv run bm-bench validate-artifacts --run-dir benchmarks/runs/<run-id>`
@@ -53,15 +52,15 @@ Validate and publish:
 - `just bench-run-bm-local`
 - `just bench-run-mem0-local`
 - `just bench-run-full`
-- `just bench-judge RUN_DIR=benchmarks/runs/<run-id>`
-- `just bench-publish RUN_DIR=benchmarks/runs/<run-id>`
+- `just bench-qa benchmarks/runs/<run-id>`
+- `just bench-publish benchmarks/runs/<run-id>`
 
 ## Repository Layout
 
 - `src/basic_memory_benchmarks/cli.py` - CLI surface
 - `src/basic_memory_benchmarks/runner.py` - run orchestration
 - `src/basic_memory_benchmarks/providers/` - provider adapters (`bm-local`, `bm-cloud`, `mem0-local`, `zep-reference`)
-- `src/basic_memory_benchmarks/scoring/` - retrieval + judge scoring
+- `src/basic_memory_benchmarks/scoring/` - retrieval + end-to-end QA scoring
 - `src/basic_memory_benchmarks/reporting/` - artifact writers / comparison helpers
 - `src/basic_memory_benchmarks/converters/` - dataset conversion logic
 - `src/basic_memory_benchmarks/datasets/` - dataset fetch/load helpers

benchmarks/README.md

@@ -7,7 +7,7 @@ dependencies remain isolated from the product environment.
 ## Goals
 
 - Deterministic retrieval benchmarks (Recall@5/10, MRR, Precision@5, content-hit, latency)
-- Optional LLM-as-judge scoring (Pydantic Evals)
+- End-to-end QA scoring with fixed answerer and judge models
 - Public artifacts with provenance and reproducibility metadata
 - Clean dependency isolation from the core Basic Memory package
 
@@ -29,12 +29,6 @@ dependencies remain isolated from the product environment.
 uv sync --group dev
 ```
 
-Optional judge dependencies:
-
-```bash
-uv sync --group dev --extra judge
-```
-
 ## Quickstart
 
 ### 1) Fetch LoCoMo dataset
@@ -85,16 +79,7 @@ know") when the retrieved memories don't contain the answer, and abstention is
 graded correct only when the gold answer marks the question unanswerable
 (LoCoMo adversarial cases).
 
-### 5) Optional retrieval-context judge (legacy)
-
-Scores whether the *retrieved context* contains the expected answer, without
-answer generation:
-
-```bash
-uv run bm-bench run judge --run-dir benchmarks/runs/<run-id>
-```
-
-### 6) Publish run artifacts
+### 5) Publish run artifacts
 
 ```bash
 uv run bm-bench publish --run-dir benchmarks/runs/<run-id>
@@ -290,8 +275,6 @@ Per run (`benchmarks/runs/<run-id>/`):
 - `retrieval-summary.json`
 - `per-query-qa.jsonl` (optional)
 - `qa-summary.json` (optional)
-- `per-query-judge.jsonl` (optional)
-- `judge-summary.json` (optional)
 - `summary.md`
 
 ## Just commands
@@ -303,8 +286,8 @@ just bench-convert-locomo
 just bench-run-bm-local
 just bench-run-mem0-local
 just bench-run-full
-just bench-judge
-just bench-publish RUN_DIR=benchmarks/runs/<run-id>
+just bench-qa benchmarks/runs/<run-id>
+just bench-publish benchmarks/runs/<run-id>
 ```
 
 ## Notes on dataset publication

benchmarks/docs/benchmarks.md

@@ -12,9 +12,9 @@ It covers:
 
 | Area | Status |
 | --- | --- |
-| Single run execution (`run retrieval`, `run full`, `run judge`) | Implemented |
+| Single run execution (`run retrieval`, `run full`, `run qa`) | Implemented |
 | Concurrent write convergence (`run concurrent-write`) | Implemented |
-| `just` one-command pipelines (`bench-full`, `bench-full-judge`) | Implemented |
+| `just` retrieval and QA workflows (`bench-full`, `bench-qa`) | Implemented |
 | Artifact generation and publish/compare commands | Implemented |
 | Manual BM revision comparison via worktrees + `--bm-local-path` | Implemented workflow, manual orchestration |
 | `bm-bench run revision-matrix` | Planned, not implemented yet |
@@ -58,12 +58,6 @@ cd /path/to/basic-memory/benchmarks
 just sync
 ```
 
-If you plan to run judge metrics:
-
-```bash
-just sync-judge
-```
-
 ### Dataset assumptions
 
 LoCoMo source and converted outputs are created by:
@@ -78,15 +72,14 @@ just bench-prepare-long
 ### `just` commands (current)
 
 - `bench-full`
-- `bench-full-judge`
+- `bench-qa`
 - `bench-concurrent-write-smoke`
 - `bench-concurrent-write-load`
 - `bench-prepare-short`
 - `bench-prepare-long`
 - `bench-run-short`
 - `bench-run-long`
 - `bench-run-full`
-- `bench-judge`
 - `bench-validate`
 - `bench-publish`
 - `bench-compare`
@@ -101,7 +94,9 @@ Top-level commands:
 - `run retrieval`
 - `run concurrent-write`
 - `run full`
-- `run judge`
+- `run qa`
+- `run rejudge`
+- `run review`
 - `compare`
 - `validate-artifacts`
 - `publish`
@@ -120,17 +115,15 @@ This runs:
 2. `just bench-prepare-long`
 3. `just bench-run-full`
 
-### One-command full retrieval + judge
+### End-to-end QA scoring
 
 ```bash
 cd /path/to/basic-memory/benchmarks
-just bench-full-judge
+just bench-qa benchmarks/runs/<run_id>
 ```
 
-This runs:
-1. `just sync-judge`
-2. `just bench-prepare-long`
-3. `just bench-run-full-judge`
+This generates answers from each provider's retrieved context, applies the
+same judge to every provider, and writes QA artifacts into the retrieval run.
 
 ### Short vs long workflows
 
@@ -196,10 +189,15 @@ Required files:
 - `retrieval-summary.json`
 - `summary.md`
 
-Optional judge files:
+Optional QA files:
 
-- `per-query-judge.jsonl`
-- `judge-summary.json`
+- `per-query-qa.jsonl`
+- `qa-summary.json`
+- `per-query-qa-rejudge.jsonl`
+- `qa-rejudge-summary.json`
+- `qa-rejudge-flips.json`
+- `review.html`
+- `qa-diagnosis.json`
 
 ### Key provenance fields
 
@@ -483,7 +481,7 @@ Dry-run checks:
 just --dry-run bench-run-short
 just --dry-run bench-run-long
 just --dry-run bench-full
-just --dry-run bench-full-judge
+just --dry-run bench-qa benchmarks/runs/<run_id>
 ```
 
 Artifact field checks:

benchmarks/justfile

@@ -18,9 +18,6 @@ longmemeval_dev_output_dir := "benchmarks/generated/longmemeval-s-dev"
 sync:
     uv sync --group dev
 
-sync-judge:
-    uv sync --group dev --extra judge
-
 test:
     uv run pytest -q
 
@@ -110,13 +107,6 @@ bench-full:
     just bench-prepare-long
     just bench-run-full
 
-# Full retrieval + judge pipeline:
-# 1) sync deps (+judge extras), 2) fetch+convert long dataset, 3) run full with judge
-bench-full-judge model="gpt-4o-mini":
-    just sync-judge
-    just bench-prepare-long
-    just bench-run-full-judge model="{{model}}"
-
 # --- Benchmark execution ---
 
 bench-smoke:
@@ -198,18 +188,6 @@ bench-run-full:
       {{bm_local_path_flag}} \
       --allow-provider-skip
 
-bench-run-full-judge model="gpt-4o-mini":
-    uv run bm-bench run full \
-      --dataset-id locomo \
-      --dataset-path {{locomo_dataset_path}} \
-      --corpus-dir benchmarks/generated/locomo/docs \
-      --queries-path benchmarks/generated/locomo/queries.json \
-      --providers bm-local,mem0-local \
-      {{bm_local_path_flag}} \
-      --allow-provider-skip \
-      --judge \
-      --judge-model "{{model}}"
-
 # --- Concurrency benchmark (basic-memory#1248) ---
 
 # Small-scale smoke: 4 writers x 25 notes; strict so divergence fails the command
@@ -244,8 +222,11 @@ bench-latest-run:
     set -euo pipefail
     ls -1dt benchmarks/runs/* | head -n 1
 
-bench-judge run_dir model="gpt-4o-mini":
-    uv run bm-bench run judge --run-dir "{{run_dir}}" --model "{{model}}"
+bench-qa run_dir answerer="claude:claude-haiku-4-5" judge="claude:claude-sonnet-4-6":
+    uv run bm-bench run qa \
+      --run-dir "{{run_dir}}" \
+      --answerer "{{answerer}}" \
+      --judge "{{judge}}"
 
 bench-validate run_dir:
     uv run bm-bench validate-artifacts --run-dir "{{run_dir}}"

benchmarks/pyproject.toml

@@ -18,11 +18,6 @@ dependencies = [
     "typer>=0.16.1",
 ]
 
-[project.optional-dependencies]
-judge = [
-    "pydantic-evals>=0.4.0",
-]
-
 [project.scripts]
 bm-bench = "basic_memory_benchmarks.cli:main"
 basic-memory-benchmarks = "basic_memory_benchmarks.cli:main"