memgineering 0.3.0 → 0.4.1

package/CHANGELOG.md

@@ -11,6 +11,105 @@ language the reader wants. The bilingual rule the monorepo applies to
 
 ## [Unreleased]
 
+## [0.4.1] — 2026-08-10
+
+Security fixes in `setup --web`, from the 2026-08-09 audit
+(`docs/security-audit-2026-08-09.md`). Every one was reproduced against
+0.3.0/0.4.0 rather than reasoned about. No command or flag changed.
+
+### Fixed
+
+- **The setup screen no longer stays up for whoever is knocking.** Its idle
+  timer was reset before any request was checked, so anything that could reach
+  the port kept a writable install endpoint alive by pinging it — without ever
+  presenting the key. The timer now moves only for requests that passed the
+  origin and key checks, and there is a one-hour ceiling above it that nothing
+  can push back.
+- **`--web` no longer reads a folder you did not mean.** Pointed at a system
+  directory it walked one and returned the title and first paragraph of every
+  markdown file under it. System folders are refused, the scan stops after
+  5,000 notes rather than running for minutes on a large folder with no way to
+  cancel, and the folder step stops answering once the install is done.
+- **A second submit no longer reports a failed install that succeeded.** Two
+  applies — the ordinary case of opening the setup link in a second tab —
+  both got past the already-applied guard, and the loser was told "Nothing
+  further was written" while everything had been written.
+- **The screen cannot be embedded in another page**, and a request that changes
+  something must say where it came from.
+- **`--web` no longer claims it opened a browser when it did not.** On a machine
+  with no default browser — or a sandbox, or `xdg-open` with nothing to hand it
+  — the opener exits non-zero and this reported success anyway, so an agent told
+  its user the screen was open while the desktop was unchanged and the printed
+  URL was the only way forward.
+
+## [0.4.0] — 2026-08-10
+
+A template is not an answer, a revision that revises nothing is not written,
+and linking a second brain no longer breaks the first one everywhere.
+
+### Added
+
+- **`recall` tells a template apart from an answer.** A card that is one of the
+  five `01_BASE/` files and is still byte-for-byte what `init` wrote is marked
+  `not filled in yet`; when every card in a result carries that mark, one line
+  above them says nothing you have written matched, and points at `onboard`.
+  `--json` carries it as `scaffolding`. Nothing is removed from the result —
+  the label is a fact about the file, so an unfilled base note padding out a
+  weak answer is visible as padding instead of reading like a conclusion. The
+  mark disappears the moment the file is edited, which is also the moment a base
+  note starts being the best answer in the brain.
+
+- **`revise` refuses a revision that revises nothing.** When the claim, summary
+  and title all match what the note already holds, nothing is written and the
+  reason is given — a user repeating an answer they had already given used to
+  become ledger entries recording no change. Saying `--reason` makes it a real
+  record again, which is what `reinforce` is for.
+- **`revise` says when a conclusion landed above `init`'s instructions.** These
+  files take two steps — write the body, then record the claim — and doing only
+  the second leaves a note whose frontmatter concludes something while the prose
+  under it is still the form telling you what to write.
+
+### Changed
+
+- **`revise --help` says which `--action` to pick and what it costs to pick
+  wrong.** Only `supersede` moves `valid_from`, so using it on a fact that was
+  true all along dates it from today. Filling in a blank `01_BASE/` file for the
+  first time is `reinforce`.
+
+### Fixed
+
+- **Linking a second brain no longer breaks the first one everywhere.** With
+  more than one brain linked and no pointer in the current folder, every command
+  refused as ambiguous — so a scratch brain linked for an afternoon stopped
+  `recall` and `remember` working in every other directory, for every tool
+  sharing the config. The first brain linked is now the default and is used when
+  nothing more specific applies; `memgineering use --default <path>` changes it,
+  and `--vault`, a `.memgineering` pointer, and standing inside a brain all
+  still win. The ambiguity refusal remains for the case it was written for —
+  several brains and nothing ever said which — and now names the one-time fix.
+  Upgrading picks the brain you already had, not the next one you happen to
+  link.
+- **The cross-language warning no longer fires over a base file the user wrote.**
+  It decided "did this query reach anything the person wrote" from the path — a
+  match under `01_BASE/` did not count — so somebody who had answered those five
+  questions could ask about their own preferences, get their own note, and be
+  told the query could not reach their brain. It now asks whether the file has
+  been touched, which is what it meant all along.
+
+### Agent guidance
+
+- `memgineering-memory` covers the `not filled in yet` mark and the header above
+  a result made only of templates: what they mean, and that a card carrying one
+  is not evidence of anything.
+- `memgineering-memory` spells out that filling in a base file is two steps —
+  write the body, then record the claim — why it is `--action reinforce` rather
+  than the default, and that re-recording something unchanged is refused.
+- `memgineering-setup` covers the default brain, and says not to abandon a write
+  because the brain was ambiguous: a refused `remember` means the thing the user
+  asked you to keep was not kept.
+
+**Restart your agent session after upgrading** so the updated skills load.
+
 ## [0.3.0] — 2026-08-10
 
 Recall says how old a memory is and why two of them disagree; a screen for

package/assets/memgineering-memory/SKILL.md

@@ -74,6 +74,29 @@ Say so. Only titles, aliases and summaries are searched, so suggest broader
 words — but do not go read their folder yourself to compensate. A brain that
 answers "nothing" is giving you real information.
 
+### Cards that are not answers
+
+A card marked `not filled in yet` is one of the five `01_BASE/` files, still
+byte-for-byte what `init` wrote. Nobody has answered it, so it is evidence of
+nothing — do not quote it back as if it were what they think.
+
+When every card carries that mark, recall says so above them:
+
+```
+⚠ Nothing you have written matched this.
+  Every card below is still the template `init` wrote
+```
+
+That is the moment to offer to fill them in rather than to answer from them —
+`memgineering onboard` prints the questions. The cards are still listed, because
+the label is a claim about the file, not a decision about what you may see;
+`--json` carries the same fact as `scaffolding: true`.
+
+The mark disappears the moment the user writes in the file. A base note they
+have filled in is an ordinary note of theirs and often the best answer in the
+brain — `who am I`, `what am I not allowed to do`, `where does everything live`
+are all answered from `01_BASE/`.
+
 ## Filling in the base files, which only you can do
 
 `init` creates five files in `01_BASE/` and leaves them empty, because what
@@ -114,17 +137,30 @@ answers thin out — three good lines beat a filled-in template. Take what they
 say in passing during ordinary work too; most of `TOOLING.md` gets written by
 noticing, not by asking.
 
-**How to write it.** These files' bodies are prose, and `revise` only touches
-frontmatter — so write the body with your normal file tools, then set the
-summary so recall shows the real thing rather than the prompt:
+**How to write it — both halves.** `revise` only touches frontmatter, so it
+takes two steps, and skipping the first is the common failure: write the body
+with your normal file tools FIRST, replacing `init`'s instructions with what
+they actually said, then record the conclusion.
 
 ```
+# 1. replace the body — their words, not the template's prompt
+# 2. then:
 memgineering revise 01_BASE/USER.md \
   --action reinforce \
   --claim "<one line: who they are>" \
   --summary "<the line recall should show>"
 ```
 
+A claim written above the untouched template leaves the file reading as a form
+somebody half-filled — the conclusion in the frontmatter, the instructions for
+writing one still underneath. `revise` warns when you do this; the warning means
+go back and write the body.
+
+`--action reinforce`, not the default, and the reason is the date. `supersede`
+stamps `valid_from` with now because a replaced conclusion starts now — but
+these facts were always true and you have only just been told them. Dating them
+today is wrong in the one field a memory store exists to get right.
+
 This is the ONE place you edit a brain file directly, and the boundary is
 narrow: `01_BASE/` only, and only while the file is still the template `init`
 wrote. Nothing is lost — there is no history to break and nothing to undo — and
@@ -221,11 +257,24 @@ memgineering revise deploy-manual \
   --summary "manual only, no CD"
 ```
 
-- `--action supersede` (default) replaces the conclusion
-- `--action reinforce` keeps it and adds support
-- `--action conflict` records that two notes disagree without picking a winner
+- `--action supersede` (default) — the conclusion CHANGED. Stamps `valid_from`
+  with now, because a replaced conclusion starts now.
+- `--action reinforce` — the SAME conclusion, new support. Leaves `valid_from`
+  alone. Use it when nothing about the fact changed, only your evidence.
+- `--action conflict` — two notes DISAGREE. Records the edge, leaves both
+  standing, and deliberately does not write the claim you passed.
 - `--dry-run` shows the diff and writes nothing
 
+Pick by what changed, not by habit: `supersede` on a fact that was true all
+along dates it from today, and the date is the field this is all for.
+
+**Re-recording something unchanged is refused.** If the claim, summary and title
+all match what the note already holds, `revise` writes nothing and says so —
+otherwise a user repeating themselves turns into ledger entries that record no
+change. When you do mean "this still holds", say what confirms it:
+`--action reinforce --reason "<what confirms it>"`. Check with `open <ref>`
+before rewriting something you may already have.
+
 This only ever rewrites the memory block in a note's frontmatter. The prose is
 the user's; neither this command nor you should rewrite it uninvited.
 

package/assets/memgineering-setup/SKILL.md

@@ -137,8 +137,9 @@ one answers is decided by where you are, in this order:
 2. a `.memgineering` pointer file, found by walking up from the cwd
 3. the brain the current directory is inside
 4. the only one linked
+5. their default brain — the first one they linked, unless they changed it
 
-If it says the choice is ambiguous, bind the directory once:
+Bind a directory to one brain when that directory belongs to it:
 
 ```
 memgineering use ~/brains/work
@@ -147,6 +148,19 @@ memgineering use ~/brains/work
 Inside a repository this writes a relative path, so it can be committed and
 will resolve for a teammate who links the same brain.
 
+If it still says the choice is ambiguous — several brains, and nothing has ever
+said which is theirs — that is a question for them, not a guess for you. Show
+the list it printed and offer the one-time fix:
+
+```
+memgineering use --default ~/brains/work
+```
+
+**Do not give up on a write because of this.** A refused `remember` means the
+thing they asked you to keep was not kept, and "I could not tell which brain"
+is a solvable problem — ask which one, or use `--vault` for the write and raise
+the default with them afterwards.
+
 ## Checking it worked
 
 ```