merge: T93 cross-chat search service

chat/services/cross_chat_search.py

@@ -0,0 +1,75 @@
+"""Cross-chat search service (T93, Phase 4).
+
+FTS5-based search across ALL owners and ALL chats. Used by the
+top-bar search UX (T100) for "where did I last see this character
+mention X?" queries. NO witness filter -- this is intentionally a
+power-user surface that surfaces memories across POVs.
+
+Mirrors the FTS5 access pattern of ``chat.state.memory.search_memories``
+but drops both the ``owner_id = ?`` and the per-witness predicates so a
+single query can sweep every chat in the database. The composite
+re-rank is also dropped: callers want raw BM25 ordering for the
+"highest match strength wins" semantics expected of a global search box.
+"""
+
+from __future__ import annotations
+
+from sqlite3 import Connection
+
+
+def search_all_memories(
+    conn: Connection,
+    *,
+    query: str,
+    k: int = 20,
+) -> list[dict]:
+    """Search FTS5 across all owners and chats.
+
+    Returns rows with ``{memory_id, owner_id, chat_id, scene_id,
+    pov_summary, significance, ts, fts_rank}``, sorted by FTS5 BM25
+    rank ascending (lower rank = stronger match, surfaced first).
+
+    The ``memories`` table has no ``ts`` column; we expose ``created_at``
+    (the projector-side row insertion timestamp) under that key so the
+    UI does not have to know the storage name.
+
+    An empty / whitespace-only ``query`` short-circuits to ``[]`` to
+    avoid an FTS5 ``MATCH ''`` syntax error and to keep the top-bar
+    "no input yet" state from triggering a full-table scan.
+    """
+    if not query or not query.strip():
+        return []
+
+    # FTS5 MATCH against the same ``memories_fts`` virtual table that
+    # backs ``state.memory.search_memories``; the JOIN pulls metadata
+    # from the content table because the FTS index only stores
+    # ``pov_summary``. ORDER BY rank ASC because BM25 in FTS5 returns
+    # negative scores where lower is better.
+    rows = conn.execute(
+        "SELECT m.id, m.owner_id, m.chat_id, m.scene_id, "
+        "       m.pov_summary, m.significance, m.created_at, "
+        "       memories_fts.rank "
+        "FROM memories_fts "
+        "JOIN memories m ON m.id = memories_fts.rowid "
+        "WHERE memories_fts MATCH ? "
+        "ORDER BY memories_fts.rank ASC "
+        "LIMIT ?",
+        (query.strip(), k),
+    ).fetchall()
+
+    return [
+        {
+            "memory_id": r[0],
+            "owner_id": r[1],
+            "chat_id": r[2],
+            "scene_id": r[3],
+            "pov_summary": r[4],
+            "significance": r[5],
+            "ts": r[6],
+            "fts_rank": r[7],
+        }
+        for r in rows
+    ]
+
+
+__all__ = ["search_all_memories"]

chat/services/embeddings.py

@@ -0,0 +1,108 @@
+"""Embedding generation service (T91, Phase 4).
+
+Wraps the embedding API call. For Phase 4's first cut we ship a
+deterministic local pseudo-embedding (hash-derived) so the vector
+retrieval pipeline can land without an external embedding endpoint
+or heavy local dependency. Phase 4.5+ swaps to a real model — the
+EmbeddingResult shape stays the same, only the generator changes.
+"""
+
+from __future__ import annotations
+
+import hashlib
+import math
+import struct
+
+from pydantic import BaseModel
+
+from chat.llm.client import LLMClient
+
+
+DEFAULT_EMBEDDING_DIM = 384
+DEFAULT_EMBEDDING_MODEL = "pseudo-sha256-384"
+FALLBACK_EMBEDDING_MODEL = "fallback"
+
+
+class EmbeddingResult(BaseModel):
+    vector: list[float]
+    model: str
+    dim: int
+
+
+def _pseudo_embed(text: str, dim: int = DEFAULT_EMBEDDING_DIM) -> list[float]:
+    """Deterministic pseudo-embedding for Phase 4 first cut.
+
+    Hashes the text with SHA-256, then expands by re-hashing each
+    successive block with the previous block + a counter — this gives
+    ``dim * 4`` bytes of fresh entropy per input rather than naively
+    repeating the 32-byte digest (which would collapse the vector onto
+    only 8 unique floats and make distinct inputs cosine-similar).
+
+    Bytes are unpacked as little-endian int32s and rescaled to [-1, 1]
+    so we sidestep the float32 NaN/denormal values that ``struct.unpack
+    'f'`` would otherwise produce on raw hash bytes. The result is
+    unit-normalized so cosine similarity reduces to a dot product.
+
+    NOT semantically meaningful — just consistent for testing the
+    pipeline. Phase 4.5 should swap to a real embedding model.
+    """
+    needed = dim * 4  # 4 bytes per int32
+    seed = text.encode("utf-8")
+    chunks: list[bytes] = []
+    counter = 0
+    while sum(len(c) for c in chunks) < needed:
+        block = hashlib.sha256(seed + counter.to_bytes(4, "big")).digest()
+        chunks.append(block)
+        counter += 1
+    full = b"".join(chunks)[:needed]
+    ints = struct.unpack(f"<{dim}i", full)
+    # Map int32 to roughly [-1, 1] — exact bound doesn't matter since we
+    # normalize, but keeps values numerically tame.
+    raw = [x / 2147483648.0 for x in ints]
+    norm = math.sqrt(sum(x * x for x in raw)) or 1.0
+    return [x / norm for x in raw]
+
+
+async def generate_embedding(
+    client: LLMClient,
+    *,
+    text: str,
+    model: str = DEFAULT_EMBEDDING_MODEL,
+    dim: int = DEFAULT_EMBEDDING_DIM,
+    timeout_s: float = 30.0,
+) -> EmbeddingResult:
+    """Generate an embedding for the given text.
+
+    Phase 4 default uses a deterministic local pseudo-embedding. If
+    the LLMClient grows an ``embed(...)`` method in Phase 4.5, this
+    wrapper will route to it when ``model != "pseudo-sha256-384"``.
+
+    Falls back to a zero vector with ``model="fallback"`` on any
+    failure (callers detect the sentinel and skip indexing). For the
+    pseudo path, failure is structurally impossible — it's pure local
+    computation.
+    """
+    if not text or not text.strip():
+        # Empty input — return fallback so caller doesn't index empty rows.
+        return EmbeddingResult(
+            vector=[0.0] * dim, model=FALLBACK_EMBEDDING_MODEL, dim=dim
+        )
+
+    if model == DEFAULT_EMBEDDING_MODEL:
+        # Pure-local pseudo path — no LLMClient call.
+        return EmbeddingResult(vector=_pseudo_embed(text, dim), model=model, dim=dim)
+
+    # Future: real embedding via client.embed(...). Phase 4.5 work.
+    # For Phase 4, any non-default model falls through to fallback.
+    return EmbeddingResult(
+        vector=[0.0] * dim, model=FALLBACK_EMBEDDING_MODEL, dim=dim
+    )
+
+
+__all__ = [
+    "DEFAULT_EMBEDDING_DIM",
+    "DEFAULT_EMBEDDING_MODEL",
+    "FALLBACK_EMBEDDING_MODEL",
+    "EmbeddingResult",
+    "generate_embedding",
+]

chat/services/vector_search.py

@@ -0,0 +1,79 @@
+"""Vector search service (T92, Phase 4).
+
+Pure-Python cosine similarity over the embeddings table. Phase 4 ships
+this without sqlite-vec because the host Python build doesn't support
+loadable extensions. For single-user scale (< few thousand memories
+per owner), iterating in Python is sub-millisecond.
+
+Phase 4.5+ may swap to sqlite-vec when the host Python supports
+enable_load_extension; the public API stays stable.
+"""
+
+from __future__ import annotations
+import math
+from sqlite3 import Connection
+
+from chat.state.embeddings import list_embeddings_for_owner
+
+
+_VALID_WITNESS_ROLES = {"you", "host", "guest"}
+
+
+def _cosine_similarity(a: list[float], b: list[float]) -> float:
+    """Cosine similarity. Assumes both vectors are non-zero."""
+    if len(a) != len(b):
+        return 0.0
+    dot = sum(x * y for x, y in zip(a, b))
+    norm_a = math.sqrt(sum(x * x for x in a)) or 1.0
+    norm_b = math.sqrt(sum(x * x for x in b)) or 1.0
+    return dot / (norm_a * norm_b)
+
+
+def vector_search(
+    conn: Connection,
+    *,
+    owner_id: str,
+    witness_role: str,    # "you" | "host" | "guest"
+    query_vector: list[float],
+    k: int = 4,
+) -> list[dict]:
+    """Return top-K memories by cosine similarity to query_vector,
+    witness-filtered for the viewer's POV. Returns rows with
+    {memory_id, pov_summary, significance, score} sorted by score
+    DESC. Empty list if no embeddings indexed for this owner.
+    """
+    if witness_role not in _VALID_WITNESS_ROLES:
+        raise ValueError(
+            f"witness_role must be one of {_VALID_WITNESS_ROLES}, got {witness_role!r}"
+        )
+
+    rows = list_embeddings_for_owner(conn, owner_id)
+    if not rows:
+        return []
+
+    # Witness-filter by the requesting role.
+    witness_key = f"witness_{witness_role}"
+    filtered = [r for r in rows if r.get(witness_key) == 1]
+    if not filtered:
+        return []
+
+    scored: list[tuple[float, dict]] = []
+    for row in filtered:
+        score = _cosine_similarity(query_vector, row["vector"])
+        scored.append(
+            (
+                score,
+                {
+                    "memory_id": row["memory_id"],
+                    "pov_summary": row["pov_summary"],
+                    "significance": row["significance"],
+                    "score": score,
+                },
+            )
+        )
+
+    scored.sort(key=lambda t: t[0], reverse=True)
+    return [item for _, item in scored[:k]]
+
+
+__all__ = ["vector_search"]

tests/test_cross_chat_search.py

@@ -0,0 +1,155 @@
+"""T93 (Phase 4): cross-chat FTS5 search across all owners and chats.
+
+Verifies that ``chat.services.cross_chat_search.search_all_memories``:
+* surfaces matches across multiple owner_ids (the per-owner restriction
+  used by ``state.memory.search_memories`` is intentionally absent),
+* applies no witness filter (admin/power-user surface),
+* orders results by FTS5 BM25 rank (lower = stronger match, surfaced
+  first), and
+* honours the ``k`` LIMIT and the empty-query fast-path.
+"""
+
+from __future__ import annotations
+
+from chat.db.connection import open_db
+from chat.db.migrate import apply_migrations
+from chat.eventlog.log import append_event
+from chat.eventlog.projector import project
+from chat.services.cross_chat_search import search_all_memories
+import chat.state.memory  # noqa: F401  (registers memory_written handler)
+
+
+def _seed(db, *, memory_specs):
+    """Apply migrations + project a list of memory_written events."""
+    apply_migrations(db)
+    with open_db(db) as conn:
+        for spec in memory_specs:
+            payload = {
+                "owner_id": spec.get("owner_id", "bot_a"),
+                "chat_id": spec.get("chat_id", "chat_bot_a"),
+                "pov_summary": spec["pov_summary"],
+                "witness_you": spec.get("witness_you", 1),
+                "witness_host": spec.get("witness_host", 1),
+                "witness_guest": spec.get("witness_guest", 0),
+                "source": "direct",
+                "reliability": 1.0,
+                "significance": spec.get("significance", 1),
+                "pinned": 0,
+                "auto_pinned": 0,
+            }
+            append_event(conn, kind="memory_written", payload=payload)
+        project(conn)
+
+
+def test_search_all_memories_returns_matches_across_owners(tmp_path):
+    """Cross-owner: a single query must surface memories from every owner.
+
+    The per-owner ``owner_id = ?`` predicate that ``search_memories`` uses
+    is intentionally absent here, so a "rabbit" memory under ``bot_a`` and
+    one under ``bot_b`` should both come back from a single call.
+    """
+    db = tmp_path / "t.db"
+    _seed(
+        db,
+        memory_specs=[
+            {
+                "owner_id": "bot_a",
+                "chat_id": "chat_bot_a",
+                "pov_summary": "the rabbit darted into the brambles",
+            },
+            {
+                "owner_id": "bot_b",
+                "chat_id": "chat_bot_b",
+                "pov_summary": "a white rabbit watched from the hedge",
+            },
+            # Distractor: must not appear for "rabbit".
+            {
+                "owner_id": "bot_a",
+                "chat_id": "chat_bot_a",
+                "pov_summary": "the kettle whistled",
+            },
+        ],
+    )
+    with open_db(db) as conn:
+        out = search_all_memories(conn, query="rabbit")
+        owners = {row["owner_id"] for row in out}
+        assert owners == {"bot_a", "bot_b"}
+        assert len(out) == 2
+        # Returned shape contract.
+        for row in out:
+            assert set(row.keys()) >= {
+                "memory_id",
+                "owner_id",
+                "chat_id",
+                "scene_id",
+                "pov_summary",
+                "significance",
+                "ts",
+                "fts_rank",
+            }
+
+
+def test_search_all_memories_orders_by_fts_rank(tmp_path):
+    """Stronger BM25 match must come first (rank ASC = lower is better)."""
+    db = tmp_path / "t.db"
+    _seed(
+        db,
+        memory_specs=[
+            # Single occurrence -> weaker BM25 score.
+            {
+                "owner_id": "bot_a",
+                "chat_id": "chat_bot_a",
+                "pov_summary": "a rabbit appeared",
+            },
+            # Triple occurrence in a short row -> stronger BM25 score.
+            {
+                "owner_id": "bot_b",
+                "chat_id": "chat_bot_b",
+                "pov_summary": "rabbit rabbit rabbit",
+            },
+        ],
+    )
+    with open_db(db) as conn:
+        out = search_all_memories(conn, query="rabbit", k=5)
+        assert len(out) == 2
+        # Stronger match first; fts_rank monotonically non-decreasing
+        # (lower-is-better, so ASC).
+        assert out[0]["pov_summary"] == "rabbit rabbit rabbit"
+        assert out[0]["fts_rank"] <= out[1]["fts_rank"]
+
+
+def test_search_all_memories_respects_k_limit(tmp_path):
+    """LIMIT ? must cap result count even when more matches exist."""
+    db = tmp_path / "t.db"
+    _seed(
+        db,
+        memory_specs=[
+            {
+                "owner_id": f"bot_{i}",
+                "chat_id": f"chat_{i}",
+                "pov_summary": f"rabbit sighting number {i}",
+            }
+            for i in range(10)
+        ],
+    )
+    with open_db(db) as conn:
+        out = search_all_memories(conn, query="rabbit", k=3)
+        assert len(out) == 3
+
+
+def test_search_all_memories_empty_query_returns_empty(tmp_path):
+    """Empty / whitespace-only query must short-circuit to []."""
+    db = tmp_path / "t.db"
+    _seed(
+        db,
+        memory_specs=[
+            {
+                "owner_id": "bot_a",
+                "chat_id": "chat_bot_a",
+                "pov_summary": "the rabbit darted into the brambles",
+            },
+        ],
+    )
+    with open_db(db) as conn:
+        assert search_all_memories(conn, query="") == []
+        assert search_all_memories(conn, query="   ") == []

tests/test_embeddings.py

@@ -0,0 +1,91 @@
+"""Tests for the embedding generation service (T91, Phase 4).
+
+Phase 4's first cut ships a deterministic local pseudo-embedding so the
+vector retrieval pipeline can land without an external embeddings API
+or a heavy local model dependency. These tests pin the contract:
+
+* the result has the right shape (vector length, ``dim`` metadata),
+* the default ``model`` string is reported back unchanged,
+* output is byte-identical for the same input (deterministic),
+* distinct inputs produce distinct vectors (so cosine actually
+  discriminates),
+* empty / whitespace-only input collapses to the ``"fallback"`` sentinel
+  with a zero vector — callers detect this and skip indexing,
+* the vector is unit-normalized so cosine similarity behaves.
+
+The pseudo path doesn't touch the LLMClient, so we pass an empty
+``MockLLMClient`` — any accidental call into it would raise
+``IndexError`` and surface as a regression.
+"""
+
+from __future__ import annotations
+
+import math
+
+import pytest
+
+from chat.llm.mock import MockLLMClient
+from chat.services.embeddings import (
+    DEFAULT_EMBEDDING_DIM,
+    DEFAULT_EMBEDDING_MODEL,
+    FALLBACK_EMBEDDING_MODEL,
+    EmbeddingResult,
+    generate_embedding,
+)
+
+
+def _client() -> MockLLMClient:
+    # Pseudo path never calls the client — empty canned list ensures any
+    # accidental call raises and surfaces the regression loudly.
+    return MockLLMClient(canned=[])
+
+
+@pytest.mark.asyncio
+async def test_generate_embedding_returns_vector_of_correct_dim():
+    result = await generate_embedding(_client(), text="hello")
+    assert isinstance(result, EmbeddingResult)
+    assert isinstance(result.vector, list)
+    assert len(result.vector) == DEFAULT_EMBEDDING_DIM == 384
+    assert result.dim == 384
+    assert all(isinstance(x, float) for x in result.vector)
+
+
+@pytest.mark.asyncio
+async def test_generate_embedding_returns_correct_model_metadata():
+    result = await generate_embedding(_client(), text="hello")
+    assert result.model == DEFAULT_EMBEDDING_MODEL == "pseudo-sha256-384"
+
+
+@pytest.mark.asyncio
+async def test_generate_embedding_is_deterministic():
+    a = await generate_embedding(_client(), text="hello world")
+    b = await generate_embedding(_client(), text="hello world")
+    assert a.vector == b.vector
+
+
+@pytest.mark.asyncio
+async def test_generate_embedding_distinct_text_produces_distinct_vectors():
+    a = await generate_embedding(_client(), text="hello world")
+    b = await generate_embedding(_client(), text="totally different content")
+    assert a.vector != b.vector
+    # Sanity-check cosine similarity — both vectors are unit-normalized,
+    # so this reduces to a plain dot product.
+    cosine = sum(x * y for x, y in zip(a.vector, b.vector))
+    assert cosine < 0.99
+
+
+@pytest.mark.asyncio
+async def test_generate_embedding_empty_text_returns_fallback():
+    for empty in ("", "   ", "\n\t"):
+        result = await generate_embedding(_client(), text=empty)
+        assert result.model == FALLBACK_EMBEDDING_MODEL == "fallback"
+        assert result.dim == DEFAULT_EMBEDDING_DIM
+        assert len(result.vector) == DEFAULT_EMBEDDING_DIM
+        assert all(x == 0.0 for x in result.vector)
+
+
+@pytest.mark.asyncio
+async def test_generate_embedding_unit_normalized():
+    result = await generate_embedding(_client(), text="some non-empty text")
+    norm_sq = sum(x * x for x in result.vector)
+    assert math.isclose(norm_sq, 1.0, abs_tol=1e-6)

tests/test_vector_search.py

@@ -0,0 +1,242 @@
+from __future__ import annotations
+
+import pytest
+
+from chat.db.connection import open_db
+from chat.db.migrate import apply_migrations
+from chat.eventlog.log import append_event
+from chat.eventlog.projector import project
+import chat.state.memory  # registers memory_written handler
+import chat.state.embeddings  # registers embedding handlers
+from chat.services.vector_search import vector_search
+
+
+def _base_memory(**overrides):
+    payload = {
+        "owner_id": "bot_a",
+        "chat_id": "chat_bot_a",
+        "scene_id": 1,
+        "pov_summary": "She laughed at his joke about owls.",
+        "witness_you": 1,
+        "witness_host": 1,
+        "witness_guest": 0,
+        "chat_clock_at": "2026-04-26T10:00:00",
+        "source": "direct",
+        "reliability": 1.0,
+        "significance": 1,
+        "pinned": 0,
+        "auto_pinned": 0,
+    }
+    payload.update(overrides)
+    return payload
+
+
+def _one_hot(dim: int, idx: int) -> list[float]:
+    """Return a one-hot vector of length ``dim`` with 1.0 at ``idx``."""
+    v = [0.0] * dim
+    v[idx] = 1.0
+    return v
+
+
+def _seed_memory_with_embedding(
+    conn,
+    *,
+    owner_id: str,
+    pov_summary: str,
+    vector: list[float],
+    significance: int = 1,
+    witness_you: int = 1,
+    witness_host: int = 1,
+    witness_guest: int = 0,
+    model: str = "test-model",
+) -> int:
+    append_event(
+        conn,
+        kind="memory_written",
+        payload=_base_memory(
+            owner_id=owner_id,
+            pov_summary=pov_summary,
+            significance=significance,
+            witness_you=witness_you,
+            witness_host=witness_host,
+            witness_guest=witness_guest,
+        ),
+    )
+    project(conn)
+    memory_id = conn.execute(
+        "SELECT id FROM memories WHERE pov_summary = ?", (pov_summary,)
+    ).fetchone()[0]
+    append_event(
+        conn,
+        kind="embedding_indexed",
+        payload={
+            "memory_id": memory_id,
+            "vector": vector,
+            "model": model,
+            "dim": len(vector),
+        },
+    )
+    project(conn)
+    return memory_id
+
+
+def test_vector_search_returns_nearest_neighbors(tmp_path):
+    db = tmp_path / "t.db"
+    apply_migrations(db)
+    with open_db(db) as conn:
+        dim = 8
+        ids = []
+        for i in range(5):
+            mid = _seed_memory_with_embedding(
+                conn,
+                owner_id="bot_a",
+                pov_summary=f"Memory {i}.",
+                vector=_one_hot(dim, i),
+            )
+            ids.append(mid)
+
+        # Query close to memory index 3 (one-hot at position 3, plus tiny noise).
+        query = _one_hot(dim, 3)
+        query[2] = 0.01
+
+        results = vector_search(
+            conn,
+            owner_id="bot_a",
+            witness_role="you",
+            query_vector=query,
+            k=3,
+        )
+        assert len(results) == 3
+        # Top-1 must be memory at index 3.
+        assert results[0]["memory_id"] == ids[3]
+        assert results[0]["pov_summary"] == "Memory 3."
+        # Score for the near-perfect match should be very close to 1.0.
+        assert results[0]["score"] > 0.99
+        # Results sorted by score DESC.
+        scores = [r["score"] for r in results]
+        assert scores == sorted(scores, reverse=True)
+        # Second place should be memory index 2 (the small noise component).
+        assert results[1]["memory_id"] == ids[2]
+
+
+def test_vector_search_respects_witness_filter(tmp_path):
+    db = tmp_path / "t.db"
+    apply_migrations(db)
+    with open_db(db) as conn:
+        dim = 4
+        # Memory visible to you=1, host=1, guest=0.
+        _seed_memory_with_embedding(
+            conn,
+            owner_id="bot_a",
+            pov_summary="Restricted.",
+            vector=_one_hot(dim, 0),
+            witness_you=1,
+            witness_host=1,
+            witness_guest=0,
+        )
+
+        # Guest sees nothing.
+        guest_results = vector_search(
+            conn,
+            owner_id="bot_a",
+            witness_role="guest",
+            query_vector=_one_hot(dim, 0),
+            k=4,
+        )
+        assert guest_results == []
+
+        # Host sees the memory.
+        host_results = vector_search(
+            conn,
+            owner_id="bot_a",
+            witness_role="host",
+            query_vector=_one_hot(dim, 0),
+            k=4,
+        )
+        assert len(host_results) == 1
+        assert host_results[0]["pov_summary"] == "Restricted."
+
+        # You also see it.
+        you_results = vector_search(
+            conn,
+            owner_id="bot_a",
+            witness_role="you",
+            query_vector=_one_hot(dim, 0),
+            k=4,
+        )
+        assert len(you_results) == 1
+
+
+def test_vector_search_respects_owner_filter(tmp_path):
+    db = tmp_path / "t.db"
+    apply_migrations(db)
+    with open_db(db) as conn:
+        dim = 4
+        _seed_memory_with_embedding(
+            conn,
+            owner_id="bot_a",
+            pov_summary="Owner A memory.",
+            vector=_one_hot(dim, 0),
+        )
+        _seed_memory_with_embedding(
+            conn,
+            owner_id="bot_b",
+            pov_summary="Owner B memory.",
+            vector=_one_hot(dim, 0),
+        )
+
+        a_results = vector_search(
+            conn,
+            owner_id="bot_a",
+            witness_role="you",
+            query_vector=_one_hot(dim, 0),
+            k=10,
+        )
+        assert len(a_results) == 1
+        assert a_results[0]["pov_summary"] == "Owner A memory."
+
+        b_results = vector_search(
+            conn,
+            owner_id="bot_b",
+            witness_role="you",
+            query_vector=_one_hot(dim, 0),
+            k=10,
+        )
+        assert len(b_results) == 1
+        assert b_results[0]["pov_summary"] == "Owner B memory."
+
+
+def test_vector_search_invalid_witness_role_raises(tmp_path):
+    db = tmp_path / "t.db"
+    apply_migrations(db)
+    with open_db(db) as conn:
+        with pytest.raises(ValueError, match="witness_role"):
+            vector_search(
+                conn,
+                owner_id="bot_a",
+                witness_role="invalid",
+                query_vector=[1.0, 0.0, 0.0],
+                k=4,
+            )
+
+
+def test_vector_search_empty_when_no_embeddings_indexed(tmp_path):
+    db = tmp_path / "t.db"
+    apply_migrations(db)
+    with open_db(db) as conn:
+        # Seed a memory but don't index an embedding for it.
+        append_event(
+            conn,
+            kind="memory_written",
+            payload=_base_memory(owner_id="bot_a", pov_summary="No embedding here."),
+        )
+        project(conn)
+
+        results = vector_search(
+            conn,
+            owner_id="bot_a",
+            witness_role="you",
+            query_vector=[1.0, 0.0, 0.0, 0.0],
+            k=4,
+        )
+        assert results == []