many fixes

docs/how_to_run.md

@@ -26,8 +26,9 @@ chat and accept that it can slow down the next request.
 bash scripts/duck.sh start
 ```
 
-This starts both processes:
+This starts the local stack:
 
+- Qdrant vector memory on `http://127.0.0.1:6333/`
 - `llama-server` on `http://127.0.0.1:8081/v1`
 - DuckLM API/WebChat on `http://127.0.0.1:8000/`
 
@@ -97,5 +98,4 @@ curl http://127.0.0.1:8000/v1/approvals/pending
 
 ```bash
 bash scripts/duck.sh stop
-docker compose -f docker-compose.memory.yml down
 ```

docs/memory_architecture.md

@@ -1,5 +1,68 @@
 # Memory Architecture
 
-Semantic memory uses Qdrant as the vector store. Embeddings come from `/v1/embeddings` when the model backend supports it.
+DuckLM currently has two memory layers:
 
-If embeddings are unavailable, `VectorMemory` fails explicitly with `EmbeddingsUnavailableError`; it does not invent a local embedding algorithm.
+- SQLite memory in `duck_core.memory.store.MemoryStore` for durable structured records.
+- Vector memory in `duck_core.memory.vector_memory.VectorMemory` for semantic search through Qdrant.
+
+## SQLite Memory
+
+SQLite is the primary durable store. Runtime writes memory records after
+`memory_policy` decides that a completed task contains reusable information.
+Manual memory records can also be added through `/v1/memory` and the WebChat
+memory drawer.
+
+SQLite memory remains available even when Qdrant is down.
+
+## Vector Memory
+
+Vector memory stores the same useful memory summaries in Qdrant when vector
+storage is configured and reachable. Qdrant is managed by the local service
+scripts:
+
+```bash
+bash scripts/duck.sh start
+bash scripts/duck.sh status --probe
+bash scripts/duck.sh stop
+```
+
+The MTP stack uses the same memory lifecycle through `scripts/duck-mtp.sh`.
+
+## Embeddings
+
+The default embedding source is a local `sentence-transformers` model:
+
+```text
+./models/all-MiniLM-L6-v2
+```
+
+`VectorMemory` lazy-loads that model only when it needs to write or search
+vectors. Health checks do not load the embedding model; they only probe Qdrant.
+
+A remote OpenAI-compatible embeddings endpoint can be used by setting
+`embeddings_base_url`, but the normal local stack does not rely on
+`llama-server` embeddings.
+
+If no embedding source is configured, `VectorMemory` raises
+`EmbeddingsUnavailableError`. It does not silently invent fallback embeddings.
+
+## Status And Verification
+
+Runtime status is available through:
+
+```bash
+curl --noproxy '*' 'http://127.0.0.1:8000/v1/status?probe=true'
+```
+
+`scripts/duck.sh status --probe` prints the same backend result plus Docker
+Compose state for Qdrant. WebChat also shows model and vector memory state in
+the Runtime panel.
+
+The live smoke test for Qdrant write/search is:
+
+```bash
+.venv/bin/python -m pytest tests/smoke/test_vector_memory_live.py -q
+```
+
+The test skips when Qdrant is not reachable, and runs a real add/search cycle
+when the local stack is up.