wontopos-mcp 1.0.20 → 1.0.22

package/README.md

@@ -1,8 +1,8 @@
 # wontopos-mcp — one memory across every AI tool
 
-> **Stable.** The tool names, their arguments and the shape of their results are a
-> contract now: a change that would break a working install waits for a major version.
-> The [API and SDKs](https://wontopos.com/en/why) underneath are versioned separately.
+> **Beta.** The tools work today and are tested, but the surface may still
+> change as we finish it. The [API and SDKs](https://wontopos.com/en/why)
+> underneath are versioned separately.
 
 [Wontopos (WOS)](https://wontopos.com) long-term memory as an [MCP](https://modelcontextprotocol.io) server.
 
@@ -40,11 +40,11 @@ claude mcp add wontopos --env WONTOPOS_API_KEY=wos-live-... -- npx -y wontopos-m
 `WONTOPOS_USER_ID` picks the store this tool remembers into (optional, default
 `"default"`) - one per project, per person, or per agent.
 
-Store ids are folded: lowercased, and anything outside `[a-z0-9_]` becomes `_`, so
-`My-Project`, `my_project` and `MY.PROJECT` all name **one store**. The boot line
-prints the folded id, which is the one that actually holds the memories. Creating a
-second id that folds onto an existing one is refused with `409 conflict_error`
-rather than silently sharing it, so pick ids that stay distinct after the fold.
+Store ids compare without regard to case, so `My-Project` and `my-project` name one
+store. An id that differs from an existing store's only by punctuation (`my_project`,
+`My.Project`) cannot be created beside it: creating it answers `409 conflict_error`,
+and using it answers 404. The boot line prints the id as configured. Pick ids that
+stay distinct once punctuation is ignored.
 
 The id must also match `[A-Za-z0-9][A-Za-z0-9._-]{0,63}`. An id outside that (anything
 in a non-Latin script, an email address) cannot be used at all: creating it answers 400 and every
@@ -119,7 +119,7 @@ quietly ignored, and that refusal would otherwise land on every search.
 | `recall` | One-call context: the **last 20 turns** (oldest first, one entry per utterance, so ten exchanges) plus relevant long-term memories and surroundings. First call when past context matters. `limit` (5-20) widens the sweep; `context_limit` (0-20) sets how much surrounding conversation rides along, `0` for the memories alone. Both need a limit-aware engine — an older one refuses the whole call, and the tool says which argument to drop. |
 | `remember` | Store what the user said that is worth keeping. `speaker: "me"` = the agent's own spoken commitments. Fetched content (search results, files) is not a memory. |
 | `store_turn` | Record one exchange as short-term history - what the user said and what the agent replied. This is what fills `recall`'s 20-turn window — one call appends two entries — and nothing else writes it, so the agent is told to call it after **each** exchange. A turn is billed like any write and is kept long-term as well, searchable afterwards. |
-| `search` | Search stored memories. `filters` narrows by TIME or topic (`event_from`/`event_to` = when the content happened, `categories`) — for "what did we decide in June?", which a query alone will not pin down. `verify` (0-3) spends extra passes to reach further back; `max_images` (0-5) asks for photos. Answers with `memories`, plus `images` and `verify_used` when those applied. |
+| `search` | Search stored memories. `filters` narrows by TIME or topic (`event_from`/`event_to` = when the content happened, `categories`) — for "what did we decide in June?", which a query alone will not pin down. `verify` (0-3) spends extra passes to reach further back; `max_images` (0-5) asks for photos. Answers with `memories`, plus `self_memories` (the assistant's own words, which `filters` do not narrow), `images` and `verify_used` when those applied. |
 | `update` | Rewrite a memory the user's own words contradicted - keeps what is still true, adds what changed. |
 | `forget` | Delete one memory by id. |
 | `list_memories` | Browse everything stored (original text + metadata, paged) - "what do you know about me?", housekeeping. |
@@ -224,6 +224,28 @@ advertise different limits.
 
 ## Changelog
 
+- **1.0.22** - back to beta, and less for the model to read. 1.0.19 to 1.0.21 said this
+  server was stable, but it is not ready yet, and this release changes the shape of
+  results. We are sorry for the change. The server instructions and tool descriptions go
+  from about 11.4k characters to 5.2k in the default setup: explanations, examples and
+  repeated notes are cut. With the argument schemas, what a model reads each session
+  goes from about 16.3k characters to 10.1k. Replies leave out empty and default fields
+  and the service's own notes, cut the times on memories to the second, and are not
+  indented. The fields left out no longer arrive, `revisions`' `counts` and `excludes`
+  among them. `search` returns the assistant's own words apart, in `self_memories`. They
+  used to be added to `memories`, so a filtered search mixed them, unfiltered, with what
+  matched. `view_image` says why it cannot show a picture rather than "Not found".
+  Underneath, the `wontopos` SDK pin moves to **2.2.42**.
+
+- **1.0.21** - in HTTP mode every client gets its own session. A second host, a
+  reconnecting host and one that ended its session with DELETE each start a fresh
+  session, and a session id the server no longer holds answers 404, so a host starts
+  again after a restart. At most 32 sessions are kept, and an idle one closes after
+  30 minutes. A request body over 256 KiB or a batch of more than 16 messages is
+  refused. `--help` and `--version` print and exit without reading the environment,
+  and the boot lines name the store id as you configured it. Node 20 or later is now
+  required (it was 18). Underneath, the `wontopos` SDK pin moves to **2.2.41**.
+
 - **1.0.20** - a trimmed reply no longer misreports its own size. When a result is
   larger than the 128KB cap the server cuts the arrays inside it, and the sibling
   `count` field kept the number from before the cut: a model was handed 100 memories
@@ -388,8 +410,7 @@ advertise different limits.
   collision (`alice-smith` vs `alice.smith`, two people, one collection) from the same id
   typed again. Sending the pre-folded form destroyed the signal, so a store created as
   `My-Project` answered a later `create_store` for `my_project` with **409
-  conflict_error** - the store reported colliding with itself. Reads and writes were
-  never affected (the API folds those on lookup either way). Now the raw id travels and
+  conflict_error** - the store reported colliding with itself. Now the raw id travels and
   only the messages speak in folded terms. Also corrected: 1.0.10 warned that an id with
   no latin alphanumerics makes every such id share one store. Measured
   against the live rule, that is not what happens - store ids must match
@@ -401,10 +422,10 @@ advertise different limits.
   1.0.8 fixed this for whitespace and stopped there: the API also lowercases an id and
   turns anything outside `[a-z0-9_]` into `_`, so `WONTOPOS_USER_ID=My-Project` read and
   wrote `my_project` while the ready line, the boot check and `create_store` all repeated
-  the operator's own spelling back as confirmation. The fold matters because it collides:
-  ids differing only by case or punctuation are ONE store, and an id with no latin
-  alphanumerics folds to underscores that every such id shares - two different people,
-  one set of memories. Both are now stated at boot. Underneath, the `wontopos` SDK floor
+  the operator's own spelling back as confirmation. The fold mattered because it collided:
+  ids differing only by case or punctuation reached ONE store then (case still does), and
+  1.0.10 also warned that an id with no latin alphanumerics folds to underscores that every
+  such id shares, which 1.0.11 above corrects. Both were stated at boot. Underneath, the `wontopos` SDK floor
   moved to **2.2.27**: the declared range said `^2.2.24` while the lockfile still pinned
   **2.2.22**, so this package was built and tested against an SDK five releases old,
   including the one where store ids collapsed silently. A test now compares the LOCKED