memgineering 0.7.0 → 0.7.1

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/CHANGELOG.md CHANGED
@@ -11,6 +11,30 @@ language the reader wants. The bilingual rule the monorepo applies to
11
11
 
12
12
  ## [Unreleased]
13
13
 
14
+ ## [0.7.1] — 2026-08-17
15
+
16
+ ### Changed
17
+
18
+ - **The semantic-search figures 0.7.0 quoted were measured on the set it was
19
+ tuned against.** An independent set of 70 questions — written by someone
20
+ reading only the notes and never a search result, with the expected note fixed
21
+ from what they had just read — scores lower on the same brain and the same
22
+ server: the right note is in the top five for **72.9%** of them and ranked
23
+ first for **45.7%**, and for a question asked across a language, **61.1%** and
24
+ **33.3%**. Text search alone scores 47.1% / 35.7% overall and 5.6% / 0% across
25
+ a language on that set, so meaning still moves every category it touches, and
26
+ cross-language remains the largest move either set shows. Both sets are real
27
+ measurements; only the tuned one had been reported. Expect the lower pair from
28
+ a question nobody tuned for.
29
+
30
+ ### Fixed
31
+
32
+ - `recall --help` no longer offers `--detail summary`, `chunks`, and `full` as
33
+ though a hosted brain could answer them. It now says which two levels a hosted
34
+ brain does answer, and points at a brain in a folder or `open <handle>` for the
35
+ deeper ones. The refusal was already correct; the help text described a
36
+ different product.
37
+
14
38
  ## [0.7.0] — 2026-08-16
15
39
 
16
40
  Recall reads what a note says, not only what it is called. And the pile of
@@ -181,6 +205,7 @@ that goes one approved change at a time.
181
205
  the shape of its answers without changing its name.
182
206
 
183
207
  ### Fixed
208
+
184
209
  - **`push` now reports the notes it never sent.** A note held back by the name
185
210
  deny list or by an ignore rule was dropped before the upload and appeared in
186
211
  no summary — a 277-note brain reported `276 note(s) uploaded` and said nothing
@@ -205,7 +230,6 @@ that goes one approved change at a time.
205
230
  held each note, instead of pointing at `memgineering reindex` — which reports
206
231
  the name and content screens and says nothing about an ignore rule.
207
232
 
208
-
209
233
  - **A `supersedes:` written as a single value is no longer ignored.**
210
234
  `supersedes: mem-abc` is what somebody writes when one memory replaces one
211
235
  other, and it parsed to nothing at all — no relation, no complaint, no way to
@@ -2,7 +2,7 @@
2
2
  name: memgineering
3
3
  description: Use whenever the user refers to something they told you before, asks what was decided, tells you something worth keeping, or settles something that should hold next time. The memory lives in their own folder and outlives this session; check it before answering from guesswork, and write to it when you learn something durable.
4
4
  type: skill
5
- version: 0.7.0
5
+ version: 0.7.1
6
6
  ---
7
7
 
8
8
  # memgineering
package/dist/index.js CHANGED
@@ -12424,7 +12424,10 @@ init_errors();
12424
12424
  init_vault();
12425
12425
  init_ui();
12426
12426
  function recallCommand() {
12427
- return new Command18("recall").description("recall memory cards for a question").argument("<query>", "what you want to remember").option("--vault <path>", "which brain to search").option("--local", "search the brain on this machine, even when signed in to a hosted one").option("--scope <scope>", "restrict to one scope").option("--limit <n>", "max cards", (v) => parseInt(v, 10), 8).option("--detail <level>", "title | card | summary | chunks | full (default: card)").option("--depth <depth>", "exact | standard (default: standard, which also searches bodies)").option("--budget <tokens>", "max estimated size of the answer", (v) => parseInt(v, 10)).action(
12427
+ return new Command18("recall").description("recall memory cards for a question").argument("<query>", "what you want to remember").option("--vault <path>", "which brain to search").option("--local", "search the brain on this machine, even when signed in to a hosted one").option("--scope <scope>", "restrict to one scope").option("--limit <n>", "max cards", (v) => parseInt(v, 10), 8).option(
12428
+ "--detail <level>",
12429
+ "title | card | summary | chunks | full (default: card) \u2014 a hosted brain answers title and card only; deeper needs a brain in a folder, or `open <handle>`"
12430
+ ).option("--depth <depth>", "exact | standard (default: standard, which also searches bodies)").option("--budget <tokens>", "max estimated size of the answer", (v) => parseInt(v, 10)).action(
12428
12431
  async (query, opts) => {
12429
12432
  const detail = parseDetail(opts.detail, "card");
12430
12433
  const depth = parseDepth(opts.depth);
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "memgineering",
3
- "version": "0.7.0",
3
+ "version": "0.7.1",
4
4
  "private": false,
5
5
  "description": "One memory for the AI you connect. Recall, remember, and revise a brain your agents share \u2014 stored in your own folder.",
6
6
  "license": "Apache-2.0",