devsper 2.5.0__tar.gz → 2.7.0__tar.gz

{devsper-2.5.0 → devsper-2.7.0}/CHANGELOG.md

@@ -7,6 +7,46 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [2.7.0] — 2026-04-07
+
+### Added
+
+- **MemoryProvider abstraction** — Introduced `MemoryBackend` ABC (`devsper/memory/providers/base.py`) mirroring the `LLMBackend` pattern. All memory backends implement a unified async interface: `store`, `retrieve`, `delete`, `list_memory`, `list_all_ids`, `query_similar`, `health`.
+- **MemoryProvider factory** — `get_memory_provider()` singleton factory resolves the active backend from config (`[memory] provider`), `DEVSPER_MEMORY_PROVIDER` env var, or legacy `backend` field. Defaults to Vektori (pgvector) with automatic SQLite fallback when `DATABASE_URL` is not set.
+- **Snowflake memory backend** — New `SnowflakeBackend` using `VECTOR(FLOAT, 1536)` columns and `VECTOR_COSINE_SIMILARITY` for native semantic search. Credentials resolved exclusively via the devsper credential store or `SNOWFLAKE_*` env vars — never from config files.
+- **SQLite, Redis, Vektori, Platform backends** — Existing stores wrapped as `MemoryBackend` implementations with `get_sync_store()` escape hatch for legacy sync callers.
+- **Credential store: Snowflake + Redis** — Added `snowflake` and `redis_memory` providers to keyring mappings. `devsper credentials set snowflake password` stores the Snowflake password securely; `inject_into_env()` propagates all `SNOWFLAKE_*` vars automatically.
+- **Config schema** — Added `RedisMemoryConfig` and `SnowflakeMemoryConfig` sub-models under `[memory]`. `SnowflakeMemoryConfig` has no `password` field — credentials are credential-store-only.
+- **`devsper doctor` memory provider health check** — `run_doctor()` now calls `provider.health()` and reports the active backend name and status.
+- **`devsper[snowflake]` and `devsper[redis-memory]` extras** — `snowflake-connector-python>=3.6.0` and `redis>=5.0.0` optional dependency groups.
+- **`deregister(name)` in tool registry** — Public function to remove a single tool by name without clearing the whole registry.
+- **`MemoryIndex` native search delegation** — When the active backend has `supports_native_vector_search=True`, `query_memory()` and `query_across_runs()` delegate directly to `backend.query_similar()`, bypassing in-process cosine ranking.
+
+### Changed
+
+- **`MemoryRouter` and `MemoryIndex`** accept an optional `backend: MemoryBackend` parameter. The `_build_memory_store()` fallback now calls the factory instead of constructing `MemoryStore()` directly.
+- **`get_effective_memory_store()`** preserved as a backwards-compatible alias; new `get_effective_memory_backend()` returns the full `MemoryBackend`. Async-only backends (Vektori, Snowflake) are bridged via `_AsyncBridgeStore` for sync callers.
+- **Legacy `backend` values** (`local`, `supermemory`, `hybrid`) now map to `"vektori"` as the default production store.
+
+### Fixed
+
+- **`test_pipelines.py`** — Replaced `registry._tools.pop()` (broken module-level access) with new `deregister()` function.
+- **`test_e2e_redis_loop.py`** — Import guard prevents `ModuleNotFoundError` when `redis` is not installed; test now correctly skips instead of failing.
+
+## [2.6.0] — 2026-04-06
+
+### Added
+
+- **TruLens observability integration** — Added first-class TruLens instrumentation for swarm runs and agent calls, with configurable runtime toggles in `[telemetry]` (`trulens_enabled`, `trulens_database_url`) and recorder/session exports in `devsper.telemetry`.
+- **CLI observability dashboard command** — Added `devsper observe` to launch the TruLens dashboard locally with optional `--port` and `--db` overrides.
+- **Optional `trulens` extra** — Added `devsper[trulens]` dependency group for straightforward TruLens installation.
+
+### Changed
+
+- **Swarm execution path** — `Swarm.run` now records via a TruLens custom app wrapper when enabled, with safe fallback to the standard runtime path if TruLens initialization or recorder setup fails.
+- **Agent call capture** — `Agent.run` is instrumented for per-call telemetry capture when TruLens is installed.
+- **Telemetry defaults and examples** — Updated default config template to include TruLens options and local database guidance.
+
 ## [2.5.0] — 2026-04-06
 
 ### Added
@@ -68,7 +108,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 - **Supermemory ranking backend** — `[memory] backend = "supermemory"` (default) uses the Rust `supermemory-core` ranker for hybrid lexical (+ optional embedding) memory retrieval, deduplication, and recency-aware context formatting.
 - **Platform memory backends** — `[memory] backend` can be `platform` or `hybrid` with `platform_api_url` and `platform_org_slug`; config resolver honors `DEVSPER_PLATFORM_API_URL` and `DEVSPER_PLATFORM_ORG` when set.
-- **Remote platform workflows** — `load_workflow("org/pkg@N")` fetches workflow specs from the Devsper Platform API when `DEVSPER_PLATFORM_API_URL`, `DEVSPER_PLATFORM_ORG`, and (when required) `DEVSPER_PLATFORM_TOKEN` are configured.
+- **Remote platform workflows** — `load_workflow("org/pkg@N")` fetches workflow specs from the Devsper Cloud API when `DEVSPER_PLATFORM_API_URL`, `DEVSPER_PLATFORM_ORG`, and (when required) `DEVSPER_PLATFORM_TOKEN` are configured.
 - **Local worker pool** — `devsper pool` subcommands to run the local worker pool manager (foreground spawner) alongside improved swarm execution when using pool-backed paths.
 - **Devsper Cloud CLI** — `devsper cloud login`, `logout`, `run`, `status`, and `logs` for JWT authentication (OS keychain) and runs against the platform API.
 

{devsper-2.5.0 → devsper-2.7.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: devsper
-Version: 2.5.0
+Version: 2.7.0
 Summary: Orchestrate distributed swarms of AI agents that collaboratively solve complex tasks.
 Project-URL: Homepage, https://github.com/devsper-com/runtime
 Project-URL: Documentation, https://docs.devsper.com
@@ -68,6 +68,9 @@ Provides-Extra: mcp
 Requires-Dist: anyio>=4.0; extra == 'mcp'
 Requires-Dist: httpx>=0.27; extra == 'mcp'
 Provides-Extra: ollama
+Provides-Extra: redis-memory
+Requires-Dist: hiredis>=2.3.0; extra == 'redis-memory'
+Requires-Dist: redis>=5.0.0; extra == 'redis-memory'
 Provides-Extra: research
 Requires-Dist: duckduckgo-search>=6.0.0; extra == 'research'
 Provides-Extra: server
@@ -75,6 +78,10 @@ Requires-Dist: fastapi>=0.110; extra == 'server'
 Requires-Dist: sse-starlette>=2.0; extra == 'server'
 Requires-Dist: uvicorn>=0.29; extra == 'server'
 Requires-Dist: vektori>=0.1.1; extra == 'server'
+Provides-Extra: snowflake
+Requires-Dist: snowflake-connector-python>=3.6.0; extra == 'snowflake'
+Provides-Extra: trulens
+Requires-Dist: trulens-core>=1.0; extra == 'trulens'
 Provides-Extra: worker
 Description-Content-Type: text/markdown
 

{devsper-2.5.0 → devsper-2.7.0}/devsper/agents/agent.py

@@ -15,6 +15,7 @@ from devsper.events import (
     ClarificationField,
     ClarificationRequest,
 )
+from devsper.telemetry.trulens import instrument as _tru_instrument
 
 log = logging.getLogger(__name__)
 
@@ -765,6 +766,7 @@ class Agent:
             answers[f.question] = self._default_answer_for_field(f)
         return answers
 
+    @_tru_instrument
     def run(self, request: AgentRequest) -> AgentResponse:
         """Stateless run: all context in AgentRequest, all output in AgentResponse."""
         import time

{devsper-2.5.0 → devsper-2.7.0}/devsper/cli/init.py

@@ -534,6 +534,31 @@ def run_doctor() -> int:
     except Exception as e:
         warnings.append(f"Memory store: {e}")
 
+    # Memory provider health check
+    try:
+        import asyncio
+        from devsper.memory.providers.factory import get_memory_provider
+        provider = get_memory_provider()
+        try:
+            loop = asyncio.get_event_loop()
+            if loop.is_running():
+                import concurrent.futures
+                with concurrent.futures.ThreadPoolExecutor(max_workers=1) as pool:
+                    healthy = pool.submit(asyncio.run, provider.health()).result()
+            else:
+                healthy = loop.run_until_complete(provider.health())
+        except Exception:
+            healthy = False
+        if healthy:
+            ok.append(f"Memory provider: {provider.name} — healthy")
+        else:
+            warnings.append(
+                f"Memory provider: {provider.name} — health check failed. "
+                "Check credentials and connectivity."
+            )
+    except Exception as e:
+        warnings.append(f"Memory provider health check failed: {e}")
+
     try:
         from devsper.knowledge.knowledge_graph import KnowledgeGraph
         kg = KnowledgeGraph(store=get_default_store())

{devsper-2.5.0 → devsper-2.7.0}/devsper/cli/main.py

@@ -2068,6 +2068,33 @@ def _run_analytics() -> int:
     return 0
 
 
+def _run_observe(port: int = 8501, db: str = "") -> int:
+    """Launch the TruLens observability dashboard."""
+    try:
+        from devsper.telemetry.trulens import init_trulens, get_session
+    except ImportError:
+        print("TruLens is not installed. Run: uv pip install 'devsper[trulens]'")
+        return 1
+
+    session = get_session() or init_trulens(database_url=db)
+    if session is None:
+        print(
+            "TruLens is not installed or failed to initialize.\n"
+            "Run: uv pip install 'devsper[trulens]'"
+        )
+        return 1
+
+    db_url = getattr(session, "connector", None)
+    db_label = str(db or ".devsper/trulens.sqlite")
+    print(f"Opening TruLens dashboard — db: {db_label}  port: {port}")
+    print("Press Ctrl-C to stop.")
+    try:
+        session.run_dashboard(port=port)
+    except KeyboardInterrupt:
+        pass
+    return 0
+
+
 def _run_tools(args: object) -> int:
     """List tools with reliability scores, or reset score history."""
     from rich.console import Console
@@ -4032,6 +4059,29 @@ Examples:
     )
     version_parser.set_defaults(func=_run_version)
 
+    observe_parser = subparsers.add_parser(
+        "observe",
+        help="Launch TruLens observability dashboard",
+        description="Open the TruLens dashboard for browsing run records, traces, and feedback.",
+        epilog="""
+Examples:
+  devsper observe
+  devsper observe --port 8502
+  devsper observe --db sqlite:///custom.sqlite
+""",
+        formatter_class=argparse.RawDescriptionHelpFormatter,
+    )
+    observe_parser.add_argument(
+        "--port", type=int, default=8501, help="Dashboard port (default: 8501)"
+    )
+    observe_parser.add_argument(
+        "--db",
+        default="",
+        metavar="URL",
+        help="TruLens database URL (default: sqlite:///.devsper/trulens.sqlite)",
+    )
+    observe_parser.set_defaults(func=lambda a: _run_observe(a.port, a.db))
+
     health_parser = subparsers.add_parser(
         "health",
         help="Health and readiness check",

{devsper-2.5.0 → devsper-2.7.0}/devsper/config/schema.py

@@ -74,13 +74,46 @@ class ModelsConfig(BaseModel):
     quality: str | None = None  # v1.6: complex tier (defaults to planner)
 
 
+class RedisMemoryConfig(BaseModel):
+    """Connection config for Redis memory backend."""
+
+    redis_url: str = "redis://localhost:6379"
+    run_id: str = ""  # empty = auto-generated from os.getpid()
+
+
+class SnowflakeMemoryConfig(BaseModel):
+    """Connection config for Snowflake memory backend.
+
+    Credentials (account, user, password, etc.) are resolved from:
+      1. devsper credential store (devsper credentials set snowflake <key>)
+      2. SNOWFLAKE_* environment variables
+      3. These TOML fields as a last fallback (non-secret fields only)
+
+    NEVER put passwords in config files — use the credential store.
+    """
+
+    account: str = ""       # or SNOWFLAKE_ACCOUNT env var
+    user: str = ""          # or SNOWFLAKE_USER env var
+    database: str = ""      # or SNOWFLAKE_DATABASE env var
+    schema_name: str = ""   # "schema" is reserved by Pydantic; or SNOWFLAKE_SCHEMA
+    warehouse: str = ""     # or SNOWFLAKE_WAREHOUSE env var
+    role: str = ""          # or SNOWFLAKE_ROLE env var
+    table: str = "devsper_memory"
+
+
 class MemoryConfig(BaseModel):
     enabled: bool = True
     store_results: bool = True
     top_k: int = 5
+    # New explicit provider field. Takes precedence over legacy `backend`.
+    # Values: "sqlite" | "redis" | "snowflake" | "vektori"
+    # Empty string = auto-detect (vektori if DATABASE_URL set, else sqlite).
+    provider: str = ""
     backend: Literal["local", "platform", "hybrid", "supermemory"] = "supermemory"
     platform_api_url: str = ""
     platform_org_slug: str = ""
+    redis: RedisMemoryConfig = Field(default_factory=RedisMemoryConfig)
+    snowflake: SnowflakeMemoryConfig = Field(default_factory=SnowflakeMemoryConfig)
 
 
 class KnowledgeConfig(BaseModel):
@@ -109,6 +142,8 @@ class TelemetryConfig(BaseModel):
     otel_endpoint: str = ""
     otel_headers: dict[str, str] = Field(default_factory=dict)
     cost_tracking: bool = True
+    trulens_enabled: bool = True
+    trulens_database_url: str = ""  # empty = SQLite default (~/.trulens/)
 
 
 class BudgetConfig(BaseModel):

{devsper-2.5.0 → devsper-2.7.0}/devsper/credentials/cli.py

@@ -22,10 +22,12 @@ KNOWN_CREDENTIALS = {
     "gemini": ["api_key"],
     "azure": ["endpoint", "api_key", "deployment", "api_version"],
     "azure_anthropic": ["endpoint", "api_key", "deployment"],
+    "snowflake": ["account", "user", "password", "database", "schema", "warehouse", "role"],
+    "redis_memory": ["url"],
 }
 
 # Keys that must never be shown in list (only "(stored)"); all others can show value
-SENSITIVE_KEYS = {"api_key", "token"}
+SENSITIVE_KEYS = {"api_key", "token", "password"}
 
 # (provider, key) -> env var name for export
 PROVIDER_KEY_TO_ENV: dict[tuple[str, str], str] = {
@@ -40,6 +42,14 @@ PROVIDER_KEY_TO_ENV: dict[tuple[str, str], str] = {
     ("azure_anthropic", "endpoint"): "AZURE_ANTHROPIC_ENDPOINT",
     ("azure_anthropic", "api_key"): "AZURE_ANTHROPIC_API_KEY",
     ("azure_anthropic", "deployment"): "AZURE_ANTHROPIC_DEPLOYMENT_NAME",
+    ("snowflake", "account"): "SNOWFLAKE_ACCOUNT",
+    ("snowflake", "user"): "SNOWFLAKE_USER",
+    ("snowflake", "password"): "SNOWFLAKE_PASSWORD",
+    ("snowflake", "database"): "SNOWFLAKE_DATABASE",
+    ("snowflake", "schema"): "SNOWFLAKE_SCHEMA",
+    ("snowflake", "warehouse"): "SNOWFLAKE_WAREHOUSE",
+    ("snowflake", "role"): "SNOWFLAKE_ROLE",
+    ("redis_memory", "url"): "REDIS_URL",
 }
 
 

{devsper-2.5.0 → devsper-2.7.0}/devsper/credentials/store.py

@@ -19,6 +19,15 @@ _PROVIDER_KEY_TO_ENV: list[tuple[str, str, str]] = [
     ("azure_anthropic", "api_key", "AZURE_ANTHROPIC_API_KEY"),
     ("azure_anthropic", "endpoint", "AZURE_ANTHROPIC_ENDPOINT"),
     ("azure_anthropic", "deployment", "AZURE_ANTHROPIC_DEPLOYMENT_NAME"),
+    # Memory backends
+    ("snowflake", "account", "SNOWFLAKE_ACCOUNT"),
+    ("snowflake", "user", "SNOWFLAKE_USER"),
+    ("snowflake", "password", "SNOWFLAKE_PASSWORD"),
+    ("snowflake", "database", "SNOWFLAKE_DATABASE"),
+    ("snowflake", "schema", "SNOWFLAKE_SCHEMA"),
+    ("snowflake", "warehouse", "SNOWFLAKE_WAREHOUSE"),
+    ("snowflake", "role", "SNOWFLAKE_ROLE"),
+    ("redis_memory", "url", "REDIS_URL"),
 ]
 
 SERVICE_NAME = "devsper"
@@ -31,6 +40,8 @@ KNOWN_CREDENTIALS = {
     "gemini": ["api_key"],
     "azure": ["endpoint", "api_key", "deployment", "api_version"],
     "azure_anthropic": ["endpoint", "api_key", "deployment"],
+    "snowflake": ["account", "user", "password", "database", "schema", "warehouse", "role"],
+    "redis_memory": ["url"],
 }
 
 

devsper-2.7.0/devsper/memory/context.py

@@ -0,0 +1,134 @@
+"""Process/async context for memory store + namespace (tools + agent execution)."""
+
+from __future__ import annotations
+
+from contextvars import ContextVar, Token
+from typing import TYPE_CHECKING
+
+if TYPE_CHECKING:
+    pass
+
+_current_store: ContextVar[object | None] = ContextVar("devsper_memory_store", default=None)
+_current_namespace: ContextVar[str | None] = ContextVar("devsper_memory_namespace", default=None)
+_current_run_id: ContextVar[str | None] = ContextVar("devsper_memory_run_id", default=None)
+
+
+def attach_memory_context(
+    store: object | None,
+    namespace: str | None,
+    run_id: str | None = None,
+) -> tuple[Token[object | None], Token[str | None], Token[str | None]]:
+    return (
+        _current_store.set(store),
+        _current_namespace.set(namespace),
+        _current_run_id.set(run_id),
+    )
+
+
+def detach_memory_context(
+    tokens: tuple[Token[object | None], Token[str | None], Token[str | None]]
+) -> None:
+    _current_store.reset(tokens[0])
+    _current_namespace.reset(tokens[1])
+    _current_run_id.reset(tokens[2])
+
+
+def get_effective_memory_backend():
+    """
+    Return the active MemoryBackend for the current context.
+    Prefers the context-var store (set by attach_memory_context) if it is a MemoryBackend,
+    otherwise returns the process-level singleton from the factory.
+    """
+    s = _current_store.get()
+    if s is not None and hasattr(s, "health"):
+        return s  # it is already a MemoryBackend
+    from devsper.memory.providers.factory import get_memory_provider
+
+    return get_memory_provider()
+
+
+def get_effective_memory_store():
+    """
+    Legacy: return a synchronous MemoryStore compatible object.
+    Backends that wrap a sync store (sqlite, redis, platform) expose get_sync_store().
+    Async-only backends (vektori, snowflake) return an _AsyncBridgeStore shim.
+    """
+    s = _current_store.get()
+    if s is not None and not hasattr(s, "health"):
+        # Legacy MemoryStore object set directly via attach_memory_context
+        return s
+    backend = get_effective_memory_backend()
+    if hasattr(backend, "get_sync_store"):
+        return backend.get_sync_store()
+    # Async-only backend: return a sync bridge so legacy callers still work
+    return _AsyncBridgeStore(backend)
+
+
+class _AsyncBridgeStore:
+    """
+    Sync shim for async-only backends (VektoriBackend, SnowflakeBackend).
+    Runs coroutines via asyncio in a thread so sync callers don't need to be async.
+    This mirrors the _run_async() pattern already used in server/memory_utils.py.
+    """
+
+    def __init__(self, backend) -> None:
+        self._backend = backend
+
+    def _run(self, coro):
+        import asyncio
+
+        try:
+            loop = asyncio.get_running_loop()
+        except RuntimeError:
+            loop = None
+        if loop and loop.is_running():
+            import concurrent.futures
+
+            with concurrent.futures.ThreadPoolExecutor(max_workers=1) as pool:
+                return pool.submit(asyncio.run, coro).result()
+        return asyncio.run(coro)
+
+    def store(self, record, namespace=None):
+        return self._run(self._backend.store(record, namespace))
+
+    def retrieve(self, memory_id, namespace=None):
+        try:
+            return self._run(self._backend.retrieve(memory_id, namespace))
+        except NotImplementedError:
+            return None
+
+    def delete(self, memory_id, namespace=None):
+        try:
+            return self._run(self._backend.delete(memory_id, namespace))
+        except NotImplementedError:
+            return False
+
+    def list_memory(
+        self,
+        memory_type=None,
+        limit=100,
+        offset=0,
+        tag_contains=None,
+        include_archived=False,
+        run_id_filter=None,
+        namespace=None,
+    ):
+        return self._run(
+            self._backend.list_memory(
+                memory_type, limit, offset, tag_contains,
+                include_archived, run_id_filter, namespace,
+            )
+        )
+
+    def list_all_ids(self, memory_type=None, namespace=None):
+        return self._run(self._backend.list_all_ids(memory_type, namespace))
+
+
+def get_effective_memory_namespace() -> str | None:
+    """Active namespace for tool memory ops (None = legacy global/run default)."""
+    return _current_namespace.get()
+
+
+def get_effective_run_id() -> str | None:
+    """Active run id for shared memory scope."""
+    return _current_run_id.get()

{devsper-2.5.0 → devsper-2.7.0}/devsper/memory/memory_index.py

@@ -2,11 +2,18 @@
 Semantic search across stored memory via embeddings and top_k retrieval.
 """
 
+from __future__ import annotations
+
+from typing import TYPE_CHECKING
+
 from devsper.memory.embeddings import embed_text
 from devsper.memory.memory_store import MemoryStore
 from devsper.memory.memory_types import MemoryRecord
 from devsper.memory.supermemory_rust_ranker import rank_memories
 
+if TYPE_CHECKING:
+    from devsper.memory.providers.base import MemoryBackend
+
 
 def _cosine_sim(a: list[float], b: list[float]) -> float:
     if not a or not b or len(a) != len(b):
@@ -19,14 +26,45 @@ def _cosine_sim(a: list[float], b: list[float]) -> float:
     return dot / (na * nb)
 
 
+def _run_async_in_thread(coro):
+    """Run a coroutine synchronously, safely bridging from sync context."""
+    import asyncio
+    import concurrent.futures
+
+    try:
+        loop = asyncio.get_running_loop()
+    except RuntimeError:
+        loop = None
+    if loop and loop.is_running():
+        with concurrent.futures.ThreadPoolExecutor(max_workers=1) as pool:
+            return pool.submit(asyncio.run, coro).result()
+    return asyncio.run(coro)
+
+
 class MemoryIndex:
     """
     Vector search over memory. Uses store for persistence and optional
     embeddings on records for query_memory(text, top_k).
+
+    When a MemoryBackend with supports_native_vector_search=True is provided,
+    query_memory() and query_across_runs() delegate to the backend's native
+    vector search (e.g. Snowflake VECTOR_COSINE_SIMILARITY, pgvector <=>),
+    bypassing in-process cosine ranking.
     """
 
-    def __init__(self, store: MemoryStore | None = None, ranking_backend: str = "local") -> None:
-        self.store = store or MemoryStore()
+    def __init__(
+        self,
+        store: MemoryStore | None = None,
+        ranking_backend: str = "local",
+        backend: "MemoryBackend | None" = None,
+    ) -> None:
+        self._backend = backend
+        if store is not None:
+            self.store = store
+        elif backend is not None and hasattr(backend, "get_sync_store"):
+            self.store = backend.get_sync_store()
+        else:
+            self.store = store or MemoryStore()
         self.ranking_backend = ranking_backend
 
     def query_memory(
@@ -39,6 +77,7 @@ class MemoryIndex:
     ) -> list[MemoryRecord]:
         """
         Semantic search via ranking strategy:
+        - native (vektori/snowflake): delegates to backend.query_similar() directly.
         - local (default): embed query, cosine-rank records that have embeddings.
         - supermemory: hybrid local ranking (lexical token overlap + optional embedding
           cosine similarity) using `rank_memories()`; records without embeddings can
@@ -48,6 +87,22 @@ class MemoryIndex:
         Use min_similarity > 0 (e.g. 0.45) to avoid injecting barely-related memory.
         By default excludes archived records (consolidation).
         """
+        # Fast path: delegate to native vector search when supported
+        if self._backend is not None and self._backend.supports_native_vector_search:
+            try:
+                from devsper.memory.providers.base import MemoryQuery
+
+                query = MemoryQuery(
+                    text=text,
+                    top_k=top_k,
+                    min_similarity=min_similarity,
+                    namespace=namespace,
+                    include_archived=include_archived,
+                )
+                return _run_async_in_thread(self._backend.query_similar(query))
+            except Exception:
+                pass  # fall through to in-process ranking
+
         records = self.store.list_memory(
             limit=500, include_archived=include_archived, namespace=namespace
         )
@@ -112,6 +167,22 @@ class MemoryIndex:
         v1.8: Same as query_memory but over more records (all runs), optional run_id filter.
         Used by CrossRunSynthesizer. Excludes archived by default.
         """
+        # Fast path: delegate to native vector search when supported
+        if self._backend is not None and self._backend.supports_native_vector_search:
+            try:
+                from devsper.memory.providers.base import MemoryQuery
+
+                query = MemoryQuery(
+                    text=text,
+                    top_k=top_k,
+                    min_similarity=min_similarity,
+                    namespace=namespace,
+                    include_archived=include_archived,
+                )
+                return _run_async_in_thread(self._backend.query_similar(query))
+            except Exception:
+                pass  # fall through to in-process ranking
+
         records = self.store.list_memory(
             limit=2000,
             include_archived=include_archived,

{devsper-2.5.0 → devsper-2.7.0}/devsper/memory/memory_router.py

@@ -2,10 +2,17 @@
 Memory router: determine which memories are relevant to a task and return context for the agent.
 """
 
+from __future__ import annotations
+
+from typing import TYPE_CHECKING
+
 from devsper.memory.memory_index import MemoryIndex
 from devsper.memory.memory_store import MemoryStore
 from devsper.memory.memory_types import MemoryRecord
 
+if TYPE_CHECKING:
+    from devsper.memory.providers.base import MemoryBackend
+
 
 class MemoryRouter:
     """
@@ -22,8 +29,16 @@ class MemoryRouter:
         min_similarity: float = 0.55,
         default_namespace: str | None = None,
         ranking_backend: str | None = None,
+        backend: "MemoryBackend | None" = None,
     ) -> None:
-        self.store = store or _build_memory_store()
+        # Resolve the sync store from whichever source is provided
+        if backend is not None:
+            self.store = _sync_store_from_backend(backend)
+        elif store is not None:
+            self.store = store
+        else:
+            self.store = _build_memory_store()
+
         # Ranking backend only affects retrieval/ranking; persistence remains store-backed.
         try:
             from devsper.config import get_config
@@ -101,20 +116,27 @@ class MemoryRouter:
         return "\n".join(lines) if lines else ""
 
 
-def _build_memory_store() -> MemoryStore:
-    try:
-        from devsper.config import get_config
+def _sync_store_from_backend(backend: "MemoryBackend"):
+    """
+    Return a sync-compatible store from a MemoryBackend.
+    Backends with get_sync_store() (sqlite, redis, platform) return their underlying store.
+    Async-only backends (vektori, snowflake) return an _AsyncBridgeStore shim.
+    """
+    if hasattr(backend, "get_sync_store"):
+        return backend.get_sync_store()
+    from devsper.memory.context import _AsyncBridgeStore
 
-        cfg = get_config()
-        backend = getattr(cfg.memory, "backend", "local")
-        if backend == "platform":
-            # Lazy import so local-only memory backends don't require optional HTTP deps.
-            from devsper.memory.platform_memory import PlatformMemoryStore
+    return _AsyncBridgeStore(backend)
 
-            return PlatformMemoryStore(
-                base_url=getattr(cfg.memory, "platform_api_url", ""),
-                org_slug=getattr(cfg.memory, "platform_org_slug", ""),
-            )
+
+def _build_memory_store():
+    """Build the default memory store via the provider factory."""
+    try:
+        from devsper.memory.providers.factory import get_memory_provider
+
+        backend = get_memory_provider()
+        return _sync_store_from_backend(backend)
     except Exception:
         pass
+    # Hard fallback: bare SQLite
     return MemoryStore()

devsper-2.7.0/devsper/memory/providers/__init__.py

@@ -0,0 +1,5 @@
+"""Memory provider abstraction — analogous to devsper/providers/router/."""
+
+from devsper.memory.providers.base import MemoryBackend, MemoryQuery
+
+__all__ = ["MemoryBackend", "MemoryQuery"]

devsper-2.7.0/devsper/memory/providers/backends/__init__.py

@@ -0,0 +1 @@
+"""Concrete MemoryBackend implementations."""