loki-mode 7.0.2 → 7.2.0

package/docs/INSTALLATION.md

@@ -2,7 +2,7 @@
 
 The flagship product of [Autonomi](https://www.autonomi.dev/). Complete installation instructions for all platforms and use cases.
 
-**Version:** v7.0.2
+**Version:** v7.2.0
 
 ---
 
@@ -34,7 +34,7 @@ The flagship product of [Autonomi](https://www.autonomi.dev/). Complete installa
 - [Quick Start](#quick-start)
 - [Verify Installation](#verify-installation)
 - [Other Methods](#other-methods)
-- [VS Code Extension](#vs-code-extension)
+- [VS Code Extension (Deprecated)](#vs-code-extension-deprecated)
 - [Sandbox Mode](#sandbox-mode)
 - [Multi-Provider Support](#multi-provider-support)
 - [Claude Code (CLI)](#claude-code-cli)
@@ -117,79 +117,33 @@ loki doctor       # Check skill symlinks, providers, and system prerequisites
 
 ## Other Methods
 
-Git clone, Docker, GitHub Action, and VS Code Extension are also available. See [alternative-installations.md](alternative-installations.md) for details and trade-offs.
+Git clone and Docker installation methods are also available. See
+[alternative-installations.md](alternative-installations.md) for details and
+trade-offs.
 
 ---
 
-## VS Code Extension
+## VS Code Extension (Deprecated)
 
-The easiest way to use Loki Mode with a visual interface.
+> **DEPRECATED as of v7.2.0.** The Loki Mode VS Code extension is no longer
+> maintained. Use the dashboard at `loki dashboard start` instead.
+>
+> The marketplace listing remains for users on v7.2.0 and earlier but will
+> not receive further updates. The `vscode-extension/` source remains in the
+> repository for contributors who want to build the extension locally; it is
+> no longer published to the VS Code Marketplace and is not included in npm
+> tarballs.
 
-### Installation
+### Recommended replacement: the dashboard
 
-**From VS Code:**
-1. Open Extensions (`Cmd+Shift+X` / `Ctrl+Shift+X`)
-2. Search for "loki-mode"
-3. Click **Install**
-
-**From Command Line:**
 ```bash
-code --install-extension asklokesh.loki-mode
+loki dashboard start
+# Then open http://localhost:57374 in your browser.
 ```
 
-**From Marketplace:**
-Visit [marketplace.visualstudio.com/items?itemName=asklokesh.loki-mode](https://marketplace.visualstudio.com/items?itemName=asklokesh.loki-mode)
-
-### Features
-
-- **Activity Bar Icon**: Dedicated Loki Mode panel in the sidebar
-- **Session View**: Real-time session status, provider, phase, and duration
-- **Task View**: Tasks grouped by status (In Progress, Pending, Completed)
-- **Status Bar**: Current state and progress at a glance
-- **Quick Actions**: Start/Stop/Pause/Resume from command palette
-- **Keyboard Shortcut**: `Cmd+Shift+L` (Mac) / `Ctrl+Shift+L` (Windows/Linux)
-
-### Usage
-
-1. Open a project folder in VS Code
-2. Click the Loki Mode icon in the activity bar (or press `Cmd+Shift+L`)
-3. Click "Start Session" and select your PRD file
-4. Choose your AI provider (Claude, Codex, or Gemini)
-5. Watch progress in the sidebar and status bar
-
-### Configuration
-
-Open VS Code Settings and search for "loki":
-
-| Setting | Default | Description |
-|---------|---------|-------------|
-| `loki.provider` | `claude` | Default AI provider |
-| `loki.apiPort` | `57374` | API server port |
-| `loki.apiHost` | `localhost` | API server host |
-| `loki.autoConnect` | `true` | Auto-connect on activation |
-| `loki.showStatusBar` | `true` | Show status bar item |
-| `loki.pollingInterval` | `2000` | Status polling interval (ms) |
-
-### Requirements
-
-**The VS Code extension requires the Loki Mode API server to be running.**
-
-Before using the extension, start the server:
-
-```bash
-# Option A: Using Loki CLI (if installed via npm or Homebrew)
-loki start
-
-# Option B: Using the autonomous runner (from source)
-./autonomy/run.sh
-
-# Option C: Direct API server start
-loki serve
-```
-
-The extension will automatically connect when it detects the server is running at `localhost:57374`.
-
-**Troubleshooting:** If you see "API server is not running" errors, make sure you started the server first using one of the commands above.
+The dashboard provides session monitoring, task views, the completion
+council, log streaming, and the managed-memory panel -- the same surface
+the extension exposed, plus everything added since v7.2.0.
 
 ---
 
@@ -507,13 +461,13 @@ Loki Mode uses two network ports for different services:
 
 | Port | Service | Description |
 |------|---------|-------------|
-| **57374** | Dashboard + API (FastAPI) | Unified server serving both the web dashboard UI (real-time monitoring, task board, Completion Council, memory browser, log streaming) and the REST API (used by VS Code extension, CLI tools, programmatic access). Served by `dashboard/server.py`. |
+| **57374** | Dashboard + API (FastAPI) | Unified server serving both the web dashboard UI (real-time monitoring, task board, Completion Council, memory browser, log streaming) and the REST API (used by CLI tools, programmatic access, and the deprecated VS Code extension). Served by `dashboard/server.py`. |
 
 ### When to Use Which Port
 
 - **Browser access** (dashboard, monitoring): Use port **57374** -- `http://localhost:57374`
 - **API calls** (REST, programmatic): Use port **57374** -- `http://localhost:57374`
-- **VS Code extension**: Connects to API on port **57374** automatically (configurable via `loki.apiPort` setting)
+- **VS Code extension** (deprecated as of v7.2.0): Connects to API on port **57374** automatically (configurable via `loki.apiPort` setting). No new releases will be published; see the deprecation notice above.
 - The server is started automatically when you run `loki start` or `./autonomy/run.sh`. No manual configuration is needed.
 
 ### Port Configuration

package/mcp/__init__.py

@@ -57,4 +57,4 @@ try:
 except ImportError:
     __all__ = ['mcp']
 
-__version__ = '7.0.2'
+__version__ = '7.2.0'

package/memory/managed_memory/client.py

@@ -101,7 +101,12 @@ class ManagedClient:
         stores = getattr(beta, "memory_stores", None) or getattr(beta, "stores", None)
         if stores is None or not hasattr(stores, "list"):
             raise ManagedDisabled("memory_stores API not available in SDK")
-        result = stores.list()
+        try:
+            result = stores.list()
+        except ManagedDisabled:
+            raise
+        except Exception as e:
+            raise ManagedDisabled(f"stores_list failed: {e!s}") from e
         # SDK returns a pydantic model; normalize to list of dicts.
         data = getattr(result, "data", result)
         return [self._to_dict(x) for x in (data or [])]
@@ -117,7 +122,12 @@ class ManagedClient:
         stores = getattr(beta, "memory_stores", None) or getattr(beta, "stores", None)
         if stores is None or not hasattr(stores, "create"):
             raise ManagedDisabled("memory_stores.create not available in SDK")
-        created = stores.create(name=name, description=description, scope=scope)
+        try:
+            created = stores.create(name=name, description=description, scope=scope)
+        except ManagedDisabled:
+            raise
+        except Exception as e:
+            raise ManagedDisabled(f"stores_get_or_create failed: {e!s}") from e
         return self._to_dict(created)
 
     # ---------- memories ------------------------------------------------
@@ -148,7 +158,12 @@ class ManagedClient:
         }
         if sha256_precondition:
             kwargs["if_match_sha256"] = sha256_precondition
-        created = memories.create(**kwargs)
+        try:
+            created = memories.create(**kwargs)
+        except ManagedDisabled:
+            raise
+        except Exception as e:
+            raise ManagedDisabled(f"memory_create failed: {e!s}") from e
         return self._to_dict(created)
 
     def memory_read(self, store_id: str, memory_id: str) -> Dict[str, Any]:
@@ -156,7 +171,12 @@ class ManagedClient:
         memories = getattr(beta, "memories", None)
         if memories is None or not hasattr(memories, "retrieve"):
             raise ManagedDisabled("memories.retrieve not available in SDK")
-        got = memories.retrieve(store_id=store_id, memory_id=memory_id)
+        try:
+            got = memories.retrieve(store_id=store_id, memory_id=memory_id)
+        except ManagedDisabled:
+            raise
+        except Exception as e:
+            raise ManagedDisabled(f"memory_read failed: {e!s}") from e
         return self._to_dict(got)
 
     def memories_list(
@@ -169,7 +189,12 @@ class ManagedClient:
         kwargs: Dict[str, Any] = {"store_id": store_id}
         if path_prefix:
             kwargs["path_prefix"] = path_prefix
-        result = memories.list(**kwargs)
+        try:
+            result = memories.list(**kwargs)
+        except ManagedDisabled:
+            raise
+        except Exception as e:
+            raise ManagedDisabled(f"memories_list failed: {e!s}") from e
         data = getattr(result, "data", result)
         return [self._to_dict(x) for x in (data or [])]
 

package/memory/managed_memory/events.py

@@ -21,6 +21,45 @@ from typing import Any, Dict, Optional
 _ROTATE_BYTES = 10 * 1024 * 1024
 
 
+def _load_loki_version() -> str:
+    """
+    Read the repo VERSION file once at module import.
+
+    Resolves to <repo_root>/VERSION assuming this file lives at
+    <repo_root>/memory/managed_memory/events.py. If the file is missing
+    or unreadable for any reason, returns the literal string "unknown"
+    so the correlation field is ALWAYS present on emitted events.
+    """
+    try:
+        version_path = Path(__file__).resolve().parents[2] / "VERSION"
+        return version_path.read_text(encoding="utf-8").strip() or "unknown"
+    except Exception:
+        return "unknown"
+
+
+# Cached at module load: never re-read per-event. The repo version does not
+# change during a single Python process lifetime.
+_LOKI_VERSION: str = _load_loki_version()
+
+
+def _correlation_stamp() -> Dict[str, Any]:
+    """
+    Build the correlation fields to merge into every payload.
+
+    Reads LOKI_ITERATION_COUNT and LOKI_SESSION_ID from the environment.
+    Missing env vars are OMITTED (not set to None) so callers can tell
+    "unset" apart from "explicitly null". loki_version is always present.
+    """
+    stamp: Dict[str, Any] = {"loki_version": _LOKI_VERSION}
+    iteration = os.environ.get("LOKI_ITERATION_COUNT")
+    if iteration is not None and iteration != "":
+        stamp["iteration_id"] = iteration
+    session = os.environ.get("LOKI_SESSION_ID")
+    if session is not None and session != "":
+        stamp["session_id"] = session
+    return stamp
+
+
 def _events_dir(target_dir: Optional[str] = None) -> Path:
     base = target_dir or os.environ.get("LOKI_TARGET_DIR") or os.getcwd()
     return Path(base) / ".loki" / "managed"
@@ -66,10 +105,18 @@ def emit_managed_event(
         path = dir_path / "events.ndjson"
         _maybe_rotate(path)
 
+        # Stamp correlation fields (loki_version always; iteration_id and
+        # session_id when env vars are set). Caller-supplied keys win: if
+        # the payload already carries iteration_id / session_id / loki_version
+        # the explicit caller value is preserved. Single-writer invariant
+        # is preserved because we only mutate the in-memory dict here; the
+        # write path (file handle, lock-free append) is unchanged.
+        merged_payload = {**_correlation_stamp(), **(payload or {})}
+
         record = {
             "ts": datetime.now(timezone.utc).isoformat().replace("+00:00", "Z"),
             "type": event_type,
-            "payload": payload,
+            "payload": merged_payload,
         }
         # Line-buffered append; JSONL.
         with open(path, "a", encoding="utf-8") as f:

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "loki-mode",
-  "version": "7.0.2",
+  "version": "7.2.0",
   "description": "Loki Mode by Autonomi - Multi-agent autonomous startup system for Claude Code, Codex CLI, and Gemini CLI",
   "keywords": [
     "agent",

package/skills/memory.md

@@ -1,4 +1,4 @@
-# Memory Integration (v7.0.2+)
+# Memory Integration (v7.2.0+)
 
 Loki Mode ships two memory layers:
 
@@ -184,4 +184,4 @@ Dashboard endpoints (read-only, view-layer merge):
 
 ---
 
-**v7.0.2** | Opt-in, additive, rollback-safe. Default behavior unchanged.
+**v7.2.0** | Opt-in, additive, rollback-safe. Default behavior unchanged.