hebbrix 2.2.0__tar.gz → 2.3.1__tar.gz

hebbrix-2.3.1/CHANGELOG.md

@@ -0,0 +1,23 @@
+# Changelog
+
+## 2.3.1 — 2026-08-26
+
+- Make `wait_for_index=True` poll the authoritative memory or job readiness
+  endpoint instead of returning a non-searchable receipt.
+- Add `memories.wait_until_searchable(...)` to the async and synchronous
+  clients, with explicit timeout and terminal-failure handling.
+- Preserve valid evidence-bound search rows during a degraded or abstaining
+  server response while retaining the safety metadata; malformed and explicit
+  no-match envelopes still fail closed.
+- Keep the synchronous and asynchronous memory create, scope, idempotency, and
+  search-safety behavior aligned.
+- Add `temporal.delete_fact(fact_id)` for tenant-scoped, idempotent cleanup of
+  facts created through the temporal API.
+
+The supported server/SDK release pair is published by the server OpenAPI
+document in `info.x-hebbrix-sdk-compatibility`. Patch releases preserve the
+public API within the same major version.
+
+## 2.3.0
+
+- Added the GA scoped memory, corrections, search proof, and ProofLoop surface.

{hebbrix-2.2.0 → hebbrix-2.3.1}/MANIFEST.in

@@ -1,4 +1,5 @@
 include README.md
+include CHANGELOG.md
 include LICENSE
 include pyproject.toml
 recursive-include hebbrix *.py

{hebbrix-2.2.0/hebbrix.egg-info → hebbrix-2.3.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: hebbrix
-Version: 2.2.0
+Version: 2.3.1
 Summary: Advanced Memory API for AI Agents with Reinforcement Learning - 3-line integration
 Author-email: Hebbrix Team <support@hebbrix.com>
 Maintainer-email: Hebbrix Team <support@hebbrix.com>
@@ -33,8 +33,10 @@ Provides-Extra: dev
 Requires-Dist: pytest>=7.0.0; extra == "dev"
 Requires-Dist: pytest-asyncio>=0.21.0; extra == "dev"
 Requires-Dist: black>=23.0.0; extra == "dev"
-Requires-Dist: flake8>=6.0.0; extra == "dev"
+Requires-Dist: flake8<6.0.0,>=5.0.4; python_full_version < "3.8.1" and extra == "dev"
+Requires-Dist: flake8>=6.0.0; python_full_version >= "3.8.1" and extra == "dev"
 Requires-Dist: mypy>=1.0.0; extra == "dev"
+Requires-Dist: cryptography>=42.0.0; extra == "dev"
 Dynamic: license-file
 
 # Hebbrix Python SDK
@@ -47,14 +49,14 @@ Official Python SDK for the Hebbrix api - **the only memory API with Reinforceme
 
 ## 🚀 Features
 
-- ✅ **Complete API Coverage** - All 50+ endpoints supported
+- ✅ **Core API Coverage** - Typed resources for memories, search, and ProofLoop
 - ✅ **Reinforcement Learning** - Train AI agents to optimize memory operations
 - ✅ **Temporal Knowledge Graphs** - Track facts over time with bi-temporal model
 - ✅ **Procedural Memory** - Store and execute learned skills
 - ✅ **Working Memory** - Short-term context buffer for conversations
 - ✅ **Memory Consolidation** - Automatic compression of episodic memories
 - ✅ **ProofLoop** - Learn from outcomes with automatic, verifiable evidence receipts
-- ✅ **Async/Await** - Full async support with httpx
+- ✅ **Sync + Async** - Equivalent core memory and ProofLoop workflows
 - ✅ **Type Hints** - Complete type annotations
 - ✅ **Clean API** - Pythonic, intuitive interface
 
@@ -83,10 +85,17 @@ async def main():
     # Store a memory
     memory = await client.memories.create(
         collection_id=collection["id"],
+        user_id="customer-7",
+        agent_id="support-agent",
         content="User prefers dark mode and loves Python",
-        importance=0.9
+        importance=0.9,
+        wait_for_index=True,
     )
 
+    # wait_for_index=True polls the returned memory status through the SDK.
+    # It returns only when searchable=true, raises on terminal failure, and
+    # raises TimeoutError if the caller's readiness deadline expires.
+
     # Search memories
     results = await client.search(
         query="What programming language does user like?",
@@ -102,6 +111,26 @@ async def main():
 asyncio.run(main())
 ```
 
+Blocking applications can use the same create/search/ProofLoop fields:
+
+```python
+from hebbrix import SyncMemoryClient
+
+with SyncMemoryClient(api_key="mem_sk_your_api_key") as client:
+    collection = client.collections.create(name="My Agent")
+    client.memories.create(
+        collection_id=collection["id"],
+        user_id="customer-7",
+        content="User prefers concise answers",
+        wait_for_index=True,
+    )
+    results = client.search(
+        "How should answers be formatted?",
+        collection_id=collection["id"],
+        user_id="customer-7",
+    )
+```
+
 ## ProofLoop: search → decision → outcome → proof
 
 ```python

{hebbrix-2.2.0 → hebbrix-2.3.1}/README.md

@@ -8,14 +8,14 @@ Official Python SDK for the Hebbrix api - **the only memory API with Reinforceme
 
 ## 🚀 Features
 
-- ✅ **Complete API Coverage** - All 50+ endpoints supported
+- ✅ **Core API Coverage** - Typed resources for memories, search, and ProofLoop
 - ✅ **Reinforcement Learning** - Train AI agents to optimize memory operations
 - ✅ **Temporal Knowledge Graphs** - Track facts over time with bi-temporal model
 - ✅ **Procedural Memory** - Store and execute learned skills
 - ✅ **Working Memory** - Short-term context buffer for conversations
 - ✅ **Memory Consolidation** - Automatic compression of episodic memories
 - ✅ **ProofLoop** - Learn from outcomes with automatic, verifiable evidence receipts
-- ✅ **Async/Await** - Full async support with httpx
+- ✅ **Sync + Async** - Equivalent core memory and ProofLoop workflows
 - ✅ **Type Hints** - Complete type annotations
 - ✅ **Clean API** - Pythonic, intuitive interface
 
@@ -44,10 +44,17 @@ async def main():
     # Store a memory
     memory = await client.memories.create(
         collection_id=collection["id"],
+        user_id="customer-7",
+        agent_id="support-agent",
         content="User prefers dark mode and loves Python",
-        importance=0.9
+        importance=0.9,
+        wait_for_index=True,
     )
 
+    # wait_for_index=True polls the returned memory status through the SDK.
+    # It returns only when searchable=true, raises on terminal failure, and
+    # raises TimeoutError if the caller's readiness deadline expires.
+
     # Search memories
     results = await client.search(
         query="What programming language does user like?",
@@ -63,6 +70,26 @@ async def main():
 asyncio.run(main())
 ```
 
+Blocking applications can use the same create/search/ProofLoop fields:
+
+```python
+from hebbrix import SyncMemoryClient
+
+with SyncMemoryClient(api_key="mem_sk_your_api_key") as client:
+    collection = client.collections.create(name="My Agent")
+    client.memories.create(
+        collection_id=collection["id"],
+        user_id="customer-7",
+        content="User prefers concise answers",
+        wait_for_index=True,
+    )
+    results = client.search(
+        "How should answers be formatted?",
+        collection_id=collection["id"],
+        user_id="customer-7",
+    )
+```
+
 ## ProofLoop: search → decision → outcome → proof
 
 ```python

{hebbrix-2.2.0 → hebbrix-2.3.1}/hebbrix/__init__.py

@@ -41,24 +41,26 @@ Features:
 - ✅ Type hints throughout
 """
 
-__version__ = "2.2.0"
+__version__ = "2.3.1"
 __author__ = "Hebbrix Team"
 __license__ = "MIT"
 
-from hebbrix.client import MemoryClient
 from hebbrix.chat import MemoryChat
+from hebbrix.client import MemoryClient
 from hebbrix.exceptions import (
-    HebbrixError,
     AuthenticationError,
-    ValidationError,
+    HebbrixError,
     NotFoundError,
     RateLimitError,
     ServerError,
+    ValidationError,
 )
-
+from hebbrix.models import EvidenceClaim, GroundingReceipt, SearchSafetyEnvelope
+from hebbrix.sync_client import SyncMemoryClient
 
 __all__ = [
     "MemoryClient",
+    "SyncMemoryClient",
     "MemoryChat",
     "HebbrixError",
     "AuthenticationError",
@@ -66,4 +68,7 @@ __all__ = [
     "NotFoundError",
     "RateLimitError",
     "ServerError",
+    "GroundingReceipt",
+    "EvidenceClaim",
+    "SearchSafetyEnvelope",
 ]

{hebbrix-2.2.0 → hebbrix-2.3.1}/hebbrix/client.py

@@ -20,7 +20,9 @@ from hebbrix.resources import (
     AuthResource,
     CollectionsResource,
     ConsolidationResource,
+    CorrectionsResource,
     MemoriesResource,
+    MemoryJobsResource,
     MemoryToolsResource,
     ProceduralResource,
     ProofLoopResource,
@@ -73,6 +75,8 @@ class MemoryClient:
         self.auth = AuthResource(self)
         self.collections = CollectionsResource(self)
         self.memories = MemoriesResource(self)
+        self.memory_jobs = MemoryJobsResource(self)
+        self.corrections = CorrectionsResource(self)
         self.search_resource = SearchResource(self)
         self.proofloop = ProofLoopResource(self)
         self.rl = RLResource(self)
@@ -87,7 +91,7 @@ class MemoryClient:
         """Get request headers."""
         headers = {
             "Content-Type": "application/json",
-            "User-Agent": "hebbrix-python/2.2.0",
+            "User-Agent": "hebbrix-python/2.3.1",
         }
 
         if self.api_key:
@@ -175,6 +179,14 @@ class MemoryClient:
         limit: int = 10,
         search_type: str = "hybrid",
         filters: Optional[Dict[str, Any]] = None,
+        user_id: Optional[str] = None,
+        agent_id: Optional[str] = None,
+        run_id: Optional[str] = None,
+        fast: Optional[bool] = None,
+        threshold: Optional[float] = None,
+        include_low_confidence: bool = False,
+        group_by_source: bool = True,
+        debug: bool = False,
     ) -> List[Dict[str, Any]]:
         """
         Search memories.
@@ -195,6 +207,14 @@ class MemoryClient:
             limit=limit,
             search_type=search_type,
             filters=filters or {},
+            user_id=user_id,
+            agent_id=agent_id,
+            run_id=run_id,
+            fast=fast,
+            threshold=threshold,
+            include_low_confidence=include_low_confidence,
+            group_by_source=group_by_source,
+            debug=debug,
         )
 
     async def search_with_proof(
@@ -205,6 +225,13 @@ class MemoryClient:
         search_type: str = "hybrid",
         filters: Optional[Dict[str, Any]] = None,
         user_id: Optional[str] = None,
+        agent_id: Optional[str] = None,
+        run_id: Optional[str] = None,
+        fast: Optional[bool] = None,
+        threshold: Optional[float] = None,
+        include_low_confidence: bool = False,
+        group_by_source: bool = True,
+        debug: bool = False,
     ) -> Dict[str, Any]:
         """Search and return both results and the automatic ProofLoop context."""
 
@@ -215,6 +242,13 @@ class MemoryClient:
             search_type=search_type,
             filters=filters or {},
             user_id=user_id,
+            agent_id=agent_id,
+            run_id=run_id,
+            fast=fast,
+            threshold=threshold,
+            include_low_confidence=include_low_confidence,
+            group_by_source=group_by_source,
+            debug=debug,
         )
 
     async def reason(
@@ -223,6 +257,10 @@ class MemoryClient:
         collection_id: Optional[str] = None,
         provider: Optional[str] = None,
         include_steps: bool = False,
+        user_id: Optional[str] = None,
+        agent_id: Optional[str] = None,
+        run_id: Optional[str] = None,
+        facets: Optional[List[str]] = None,
     ) -> Dict[str, Any]:
         """
         Perform reasoning over memories.
@@ -232,6 +270,10 @@ class MemoryClient:
             collection_id: Optional collection filter
             provider: LLM provider (gemini, openai, anthropic)
             include_steps: Include reasoning steps
+            user_id: End-user isolation scope
+            agent_id: Agent isolation scope
+            run_id: Run isolation scope
+            facets: Optional typed decomposition facets
 
         Returns:
             Reasoning result with answer and sources
@@ -241,6 +283,10 @@ class MemoryClient:
             collection_id=collection_id,
             provider=provider,
             include_steps=include_steps,
+            user_id=user_id,
+            agent_id=agent_id,
+            run_id=run_id,
+            facets=facets,
         )
 
     async def close(self):

hebbrix-2.3.1/hebbrix/models.py

@@ -0,0 +1,40 @@
+"""Public response contracts for evidence-bearing Hebbrix operations."""
+
+from typing import Any, Dict, List, TypedDict
+
+
+class GroundingReceipt(TypedDict, total=False):
+    """Authoritative claim-grounding decision returned by the API."""
+
+    status: str
+    reason: str
+    contract_version: str
+    requested_predicate: str
+    requested_attribute: str
+    subject_anchors: List[str]
+
+
+class EvidenceClaim(TypedDict, total=False):
+    """Claims attributed to one exact memory evidence identifier."""
+
+    memory_id: str
+    claims: Dict[str, Any]
+
+
+class SearchSafetyEnvelope(TypedDict, total=False):
+    """Fail-closed response shared by search and reasoning helpers."""
+
+    query: str
+    results: List[Dict[str, Any]]
+    sources: List[Dict[str, Any]]
+    total: int
+    no_match: bool
+    abstain_recommended: bool
+    query_confidence: float
+    grounding: GroundingReceipt
+    evidence_ids: List[str]
+    evidence_claims: List[EvidenceClaim]
+    safety_contract_version: str
+    degraded: bool
+    sdk_safety_reason: str
+    proof_context: Dict[str, Any]