Add memory system session context API

skills/memory-system-api/SKILL.md

@@ -59,6 +59,7 @@ Base path: `/memory-system`
 | `POST` | `/messages` | Write user/assistant messages to backends | Yes |
 | `POST` | `/sessions/{session_id}/commit` | Commit OpenViking session and flush EverOS | Yes |
 | `POST` | `/sessions/{session_id}/extract` | Trigger OpenViking extract only | Yes |
+| `GET/POST` | `/sessions/{session_id}/context` | Read OpenViking session context plus EverOS recall | Yes |
 | `GET` | `/openviking/tasks/{task_id}` | Poll OpenViking task status | Yes |
 | `POST` | `/search` | Search OpenViking and EverOS | Yes |
 | `GET` | `/users/{user_id}/profile` | Read EverOS profile | Yes |
@@ -127,6 +128,25 @@ curl -sS -X POST "$BASE/memory-system/search" \
   }'
 ```
 
+Session context:
+
+```bash
+curl -sS -X POST "$BASE/memory-system/sessions/sessionA1/context" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "user_id": "userA",
+    "user_key": "'"$USER_KEY"'",
+    "query": "我喜欢喝什么？",
+    "limit": 10
+  }'
+```
+
+GET with query parameters is also supported:
+
+```bash
+curl -sS "$BASE/memory-system/sessions/sessionA1/context?user_id=userA&user_key=$USER_KEY&query=我喜欢喝什么？&limit=10"
+```
+
 ## Response Handling
 
 Top-level `status` is one of:
@@ -137,6 +157,8 @@ Top-level `status` is one of:
 
 Search responses include merged `items` and compact backend diagnostics under `backends`. Keep `source_backend` when using results. Fields named `vector` are stripped from returned payloads, and the raw EverOS `original_data` blob is not returned by search anymore.
 
+Session context responses include OpenViking context under `context`, EverOS recall under `items`, and compact backend diagnostics under `backends`.
+
 ## Common Mistakes
 
 - Calling `/messages` before `/users`.

skills/memory-system-api/references/api.md

@@ -72,6 +72,68 @@ curl -s -X POST <MEMORY_SYSTEM_BASE_URL>/memory-system/sessions/<SESSION_ID>/ext
   -d '{"user_id": "<USER_ID>", "user_key": "<USER_KEY>"}'
 ```
 
+## Session Context
+
+Use this when the caller needs the OpenViking working-memory context for one session plus related EverOS recall for the same user/session.
+
+```bash
+curl -s -X POST <MEMORY_SYSTEM_BASE_URL>/memory-system/sessions/<SESSION_ID>/context \
+  -H "Content-Type: application/json" \
+  -d '{
+    "user_id": "<USER_ID>",
+    "user_key": "<USER_KEY>",
+    "query": "我喜欢喝什么？",
+    "limit": 10
+  }'
+```
+
+Equivalent GET form:
+
+```bash
+curl -s "<MEMORY_SYSTEM_BASE_URL>/memory-system/sessions/<SESSION_ID>/context?user_id=<USER_ID>&user_key=<USER_KEY>&query=我喜欢喝什么？&limit=10"
+```
+
+Response shape:
+
+```json
+{
+  "status": "success",
+  "context": {
+    "latest_archive_overview": "# Working Memory\n...",
+    "pre_archive_abstracts": [],
+    "messages": [],
+    "estimatedTokens": 342,
+    "stats": {"totalArchives": 3}
+  },
+  "items": [
+    {
+      "source_backend": "everos",
+      "memory_type": "episode",
+      "id": "episode-1",
+      "summary": "userB 在对话中表示自己喜欢拿铁。",
+      "score": 0.72
+    }
+  ],
+  "backends": {
+    "openviking": {
+      "status": "success",
+      "result": {
+        "status": "ok",
+        "estimatedTokens": 342,
+        "has_latest_archive_overview": true,
+        "message_count": 0
+      }
+    },
+    "everos": {
+      "status": "success",
+      "result": {
+        "counts": {"episodes": 1, "profiles": 0, "raw_messages": 0}
+      }
+    }
+  }
+}
+```
+
 ## Search
 
 Without LLM planning: