superlocalmemory 3.8.14 → 4.0.0

package/plugin-src/skills/slm-profile/SKILL.md

@@ -0,0 +1,148 @@
+---
+name: slm-profile
+description: Workspace isolation and runtime profile switching for SuperLocalMemory. Each profile is a fully independent memory namespace — separate facts, code graphs, and tool sets. Use switch_profile (MCP, requires code/full/power profile) to change the active workspace without restarting. Check the active profile with slm status. Required when working across multiple projects, clients, or tenants.
+when_to_use: |
+  - "Switch to my work profile"
+  - "Use the code profile for this session"
+  - "What profile am I currently in?"
+  - "I need mesh tools — switch to full profile"
+  - "Load the devops workspace"
+  - Multi-project workflows needing memory isolation
+  - Switching between personal and team workspaces
+  - Enabling additional MCP tools by activating a richer profile
+allowed-tools: switch_profile, Bash
+---
+
+# slm-profile — Workspace Isolation and Profile Switching
+
+A profile is a fully isolated memory workspace. Each profile has its own:
+- Memory facts (nothing bleeds across profiles by default)
+- Code graph index (separate per repo/project)
+- Active MCP tool set (determined by profile tier)
+- Retention policy and decay settings
+
+Profiles are the right tool when you have genuinely separate contexts: a personal
+project, a client engagement, a production vs staging environment.
+
+---
+
+## Available profiles and their tool sets
+
+| Profile | Tools | When to use |
+|---------|-------|-------------|
+| `core` | 14 tools — remember, recall, search, session, optimize | Minimal footprint, no code tools |
+| `code` | 24 tools — core + 6 code-graph tools + switch_profile + 3 bounded-loop tools | Default for IDE/coding agents |
+| `full` | 42 tools — code + all memory ops + mesh + bounded loops | Multi-session, team workflows |
+| `power` | 54 tools — full + governance + behavioral tools | Enterprise, admin, audit use cases |
+| `mesh` | 8 tools — mesh coordination only | Lightweight cross-session signalling |
+
+The profile is set at MCP server startup via `SLM_MCP_PROFILE` in the MCP config.
+`switch_profile` lets you change it at runtime without a restart.
+
+---
+
+## Checking the active profile
+
+```bash
+slm status --json
+```
+
+The `profile` field in the output is the currently active profile name.
+
+Or via MCP (works in any profile):
+
+```bash
+slm status
+```
+
+---
+
+## Switching profiles at runtime (v3.8.0+)
+
+`switch_profile` is available in `code`, `full`, and `power` profiles.
+
+```
+switch_profile(
+  profile: str,   # one of: "core", "code", "full", "power", "mesh"
+)
+```
+
+### Example: activate full profile to access mesh tools
+
+```
+# You started in code profile but need mesh coordination
+switch_profile(profile="full")
+
+# Now mesh_peers, mesh_send, mesh_inbox, etc. are available
+mesh_peers()
+```
+
+### Example: switch workspaces
+
+```
+# Switch from personal to work workspace
+switch_profile(profile="work-project")
+```
+
+Wait — profile names and workspace names are distinct concepts:
+- **Profile tier** (`core`, `code`, `full`, `power`, `mesh`) controls which MCP
+  tools are registered.
+- **Workspace / data directory** (`SLM_DATA_DIR`) controls which memory database
+  is used.
+
+`switch_profile` changes the **tool tier** within the current workspace. To
+switch to a completely different memory database (workspace), you need to change
+`SLM_DATA_DIR` — this requires restarting the MCP server or using a separately
+configured MCP server instance.
+
+---
+
+## Configuring the initial profile
+
+In your `.mcp.json` (Claude Code) or `.codex/config.toml` (Codex):
+
+```json
+"env": {
+  "SLM_MCP_PROFILE": "code",
+  "SLM_DATA_DIR": "~/.superlocalmemory"
+}
+```
+
+Profile aliases from older versions still resolve: `code20` → `code`,
+`full38` → `full`, `power50` → `power`. Stale configs get a startup warning
+but continue to work.
+
+---
+
+## Profile isolation guarantees
+
+- `recall` returns only memories in the active profile (plus opt-in shared/global
+  facts — see `slm-scope`).
+- `remember` writes to the active profile only unless `scope="shared"/"global"`.
+- Code graph tools (`build_code_graph`, `get_blast_radius`, etc.) index into the
+  active profile's graph store.
+- KV cache entries are namespaced per profile — switching profiles gives you a
+  clean cache.
+
+---
+
+## Multiple concurrent profiles
+
+You can run multiple SLM MCP server instances simultaneously, each pointed at a
+different `SLM_DATA_DIR`, to serve different workspaces in the same IDE session.
+Name them differently in your MCP config (e.g. `superlocalmemory-personal` and
+`superlocalmemory-work`) and route tool calls to the appropriate server.
+
+---
+
+## Related skills
+
+- `slm-scope` — opt-in fact sharing across profiles (personal/shared/global)
+- `slm-graph` — code-graph tools available in code/full/power profiles
+- `slm-mesh` — mesh tools available in full/power/mesh profiles
+- `slm-status` — check active profile name and tool inventory
+- `slm-governance` — enterprise role-based access to profiles
+
+---
+
+*SuperLocalMemory v4.0.0 · Qualixar · AGPL-3.0-or-later*

package/plugin-src/skills/slm-recall/SKILL.md

@@ -236,4 +236,4 @@ before recalling, then switch back. See `slm-profile` for workspace switching.
 
 ---
 
-*SuperLocalMemory v3.8.14 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v4.0.0 · Qualixar · AGPL-3.0-or-later*

package/plugin-src/skills/slm-remember/SKILL.md

@@ -238,4 +238,4 @@ different workspace, use `switch_profile` first. See `slm-profile`.
 
 ---
 
-*SuperLocalMemory v3.8.14 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v4.0.0 · Qualixar · AGPL-3.0-or-later*

package/plugin-src/skills/slm-scope/SKILL.md

@@ -0,0 +1,176 @@
+---
+name: slm-scope
+description: Controls memory visibility across profiles — personal (private, default), shared (selected profiles), or global (all profiles on this machine). Default is always personal. Only change scope when the user explicitly asks to share a memory across workspaces. Works with both remember (write scope) and recall (read scope flags).
+when_to_use: |
+  - "Share this memory with the team profile"
+  - "Store this globally so all my agents can see it"
+  - "Recall anything shared from the work profile"
+  - "Can other agents on this machine see my memories?"
+  - User explicitly asks to cross-profile share a fact or see shared facts
+  - Enterprise setup where multiple profiles collaborate
+allowed-tools: remember, recall, search, list_recent, Bash
+---
+
+# slm-scope — Memory Scope and Sharing Model
+
+SuperLocalMemory is profile-isolated by default. Every profile is a fully
+independent memory namespace. The scope model adds controlled, opt-in sharing
+between profiles on the same machine — it is never active unless you explicitly
+set it.
+
+---
+
+## The Three Scopes
+
+| Scope | Visibility | When to use |
+|-------|-----------|-------------|
+| `personal` | Active profile only | Default — all facts. Never set explicitly. |
+| `shared` | Active profile + `shared_with` profiles | Team handoffs, shared project context |
+| `global` | Every profile on this machine | Machine-wide conventions, org-wide rules |
+
+**The default is always `personal`.** A fact stored without a `scope` argument
+is private to the profile that stored it. Recall without scope flags returns only
+personal facts. This is identical to single-profile SLM.
+
+---
+
+## Opt-in is mandatory
+
+Never set `scope="shared"` or `scope="global"` (or the recall equivalents
+`include_shared`, `include_global`) unless the user explicitly asks you to share
+or read across profiles. This is a hard rule — scope expansion is an action with
+team-wide or machine-wide impact, and it must always be user-initiated.
+
+---
+
+## Writing a shared or global fact
+
+### share with specific profiles
+
+```
+remember(
+  content="API gateway rate limit is 1000 req/min per client",
+  tags="api,limits,ops",
+  project="platform",
+  importance=8,
+  session_id="<sid>",
+  scope="shared",
+  shared_with="devops-profile,backend-profile",
+)
+```
+
+`shared_with` is a comma-separated list of profile IDs that should be able to
+recall this fact. Use `slm status` to see the current profile name — that is the
+`profile_id` to supply.
+
+### share with all profiles on the machine
+
+```
+remember(
+  content="All services must enforce TLS 1.3 minimum",
+  tags="security,tls,global",
+  project="infra",
+  importance=9,
+  session_id="<sid>",
+  scope="global",
+)
+```
+
+`scope="global"` makes the fact visible to every profile on this machine. Use
+this only for machine-wide conventions (security rules, org-wide constraints).
+
+---
+
+## Reading shared or global facts
+
+By default, `recall` returns only the active profile's personal facts. To surface
+shared and global facts, pass the opt-in flags:
+
+```
+recall(
+  query="rate limiting rules",
+  limit=20,
+  include_global=True,   # include global-scope facts
+  include_shared=True,   # include facts shared with this profile
+  session_id="<sid>",
+)
+```
+
+You can opt in to either or both flags independently. Only the active profile's
+permitted shared facts are returned — you cannot read another profile's personal
+facts.
+
+### CLI equivalents
+
+```bash
+# Recall with global facts included
+slm recall "rate limiting rules" --include-global
+
+# Recall with shared facts included
+slm recall "rate limiting rules" --include-shared
+
+# Both
+slm recall "rate limiting rules" --include-global --include-shared
+
+# Store a global fact
+slm remember "TLS 1.3 minimum" --scope global
+
+# Store a shared fact (shared-with is a comma-separated list of profile IDs)
+slm remember "API rate limit 1000/min" --scope shared --shared-with devops,backend
+```
+
+CLI flags verified in source: `--include-global` / `--no-global`, `--include-shared` / `--no-shared`,
+`--scope personal|shared|global`, `--shared-with <profile-ids>`.
+
+---
+
+## Configuring scope defaults
+
+Per-profile defaults live in `mode_a/b/c.json` configuration. To make a profile
+always include global facts without passing flags each time:
+
+```json
+{
+  "recall": {
+    "include_global": true,
+    "include_shared": false
+  }
+}
+```
+
+Changing the default requires editing the profile config directly — this is an
+admin-level operation.
+
+---
+
+## Enterprise governance
+
+In a governed workspace (admin/member/viewer roles), scope expansion may be
+restricted:
+- **Viewers** cannot write `scope="global"` facts — their writes are always `personal`.
+- **Members** can write `scope="shared"` with profiles in their access list.
+- **Admins** can write `scope="global"` unrestricted.
+
+See `slm-governance` for the full enterprise behavior model.
+
+---
+
+## Scope deletion and retention
+
+A `scope="global"` fact deleted by one profile is deleted for all profiles. A
+`scope="shared"` fact is deleted from all profiles that had access to it.
+Use `slm forget "<query>" --dry-run` before any deletion involving shared facts
+to review the impact. See `slm-remember` for the full deletion discipline.
+
+---
+
+## Related skills
+
+- `slm-remember` — full fact storage reference including scope parameters
+- `slm-recall` — full retrieval reference including include_global/include_shared
+- `slm-profile` — what a profile is and how to switch between them
+- `slm-governance` — enterprise role restrictions on scope
+
+---
+
+*SuperLocalMemory v4.0.0 · Qualixar · AGPL-3.0-or-later*

package/plugin-src/skills/slm-session/SKILL.md

@@ -227,4 +227,4 @@ explicitly and call `recall` with `include_global`/`include_shared` after
 
 ---
 
-*SuperLocalMemory v3.8.14 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v4.0.0 · Qualixar · AGPL-3.0-or-later*

package/plugin-src/skills/slm-status/SKILL.md

@@ -163,4 +163,4 @@ multi-profile setup. To switch the active profile, see `slm-profile`.
 
 ---
 
-SuperLocalMemory v3.8.14 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v4.0.0 · Qualixar · AGPL-3.0-or-later

package/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "superlocalmemory"
-version = "3.8.14"
+version = "4.0.0"
 description = "Local-first agent memory with auditable hybrid retrieval"
 readme = "README.md"
 license = "AGPL-3.0-or-later"
@@ -16,7 +16,6 @@ keywords = [
 classifiers = [
     "Development Status :: 4 - Beta",
     "Intended Audience :: Developers",
-    "Operating System :: OS Independent",
     "Operating System :: MacOS",
     "Operating System :: Microsoft :: Windows",
     "Operating System :: POSIX :: Linux",
@@ -37,7 +36,7 @@ dependencies = [
     "numpy==2.4.4",
     "scipy==1.17.1",
     "networkx==3.6.1",
-    "mcp==1.28.1",
+    "mcp==2.0.0",
     "python-dateutil==2.9.0.post0",
     "rank-bm25==0.2.2",
     "vadersentiment==3.3.2",
@@ -63,7 +62,7 @@ dependencies = [
     # Keep this direct: portalocker also needs pywin32 today, but capture must
     # not depend on that transitive implementation detail.
     "pywin32==311; sys_platform == 'win32'",
-    "cryptography==48.0.1",
+    "cryptography==50.0.0",
     # Semantic search + cross-encoder reranker. Do NOT use
     # sentence-transformers[onnx] — its extras pull optimum which
     # overrides the sentence-transformers pin via transitive deps.
@@ -91,6 +90,9 @@ dependencies = [
     # the ~560MB model downloads on first setup/warmup (fail-open). Verified the
     # pin does NOT disturb the transformers/torch/numpy pins above.
     "llmlingua==0.2.2",
+    # LLMLingua pulls NLTK transitively. Pin the patched release so clean
+    # installs cannot resolve to the vulnerable 3.9.x line.
+    "nltk==3.10.0",
 ]
 
 [project.optional-dependencies]
@@ -173,9 +175,14 @@ superlocalmemory = ["ui/**/*", "optimize/NOTICE"]
 [tool.setuptools.data-files]
 "share/superlocalmemory/codex/skills/slm-cache" = ["plugin-src/skills/slm-cache/SKILL.md"]
 "share/superlocalmemory/codex/skills/slm-compress" = ["plugin-src/skills/slm-compress/SKILL.md"]
+"share/superlocalmemory/codex/skills/slm-governance" = ["plugin-src/skills/slm-governance/SKILL.md"]
 "share/superlocalmemory/codex/skills/slm-graph" = ["plugin-src/skills/slm-graph/SKILL.md"]
+"share/superlocalmemory/codex/skills/slm-loop" = ["plugin-src/skills/slm-loop/SKILL.md"]
+"share/superlocalmemory/codex/skills/slm-mesh" = ["plugin-src/skills/slm-mesh/SKILL.md"]
+"share/superlocalmemory/codex/skills/slm-profile" = ["plugin-src/skills/slm-profile/SKILL.md"]
 "share/superlocalmemory/codex/skills/slm-recall" = ["plugin-src/skills/slm-recall/SKILL.md"]
 "share/superlocalmemory/codex/skills/slm-remember" = ["plugin-src/skills/slm-remember/SKILL.md"]
+"share/superlocalmemory/codex/skills/slm-scope" = ["plugin-src/skills/slm-scope/SKILL.md"]
 "share/superlocalmemory/codex/skills/slm-session" = ["plugin-src/skills/slm-session/SKILL.md"]
 "share/superlocalmemory/codex/skills/slm-status" = ["plugin-src/skills/slm-status/SKILL.md"]
 "share/superlocalmemory/portable-kit/rules" = ["plugin-src/rules/AGENTS.md"]

package/src/superlocalmemory/__init__.py

@@ -32,7 +32,7 @@ if "OMP_NUM_THREADS" not in os.environ:
     os.environ["OMP_NUM_THREADS"] = "2"
 # ---------------------------------------------------------------------------
 
-__version__ = "3.8.14"
+__version__ = "4.0.0"
 
 _REQUIRED_VERSIONS = {
     "sentence_transformers": "5.3.0",