SDK 1.3.0-rc1

.openapi-generator/FILES

@@ -14,6 +14,7 @@ docs/CategoryPatchBody.md
 docs/Content.md
 docs/Content1.md
 docs/ContentItem.md
+docs/ContextInput.md
 docs/Data.md
 docs/Data1.md
 docs/DeleteByIdsData.md
@@ -169,6 +170,7 @@ everos_cloud/models/category_patch_body.py
 everos_cloud/models/content.py
 everos_cloud/models/content1.py
 everos_cloud/models/content_item.py
+everos_cloud/models/context_input.py
 everos_cloud/models/data.py
 everos_cloud/models/data1.py
 everos_cloud/models/delete_by_ids_data.py
@@ -317,6 +319,7 @@ test/test_category_patch_body.py
 test/test_content.py
 test/test_content1.py
 test/test_content_item.py
+test/test_context_input.py
 test/test_data.py
 test/test_data1.py
 test/test_delete_by_ids_data.py

docs/ContextInput.md

@@ -0,0 +1,39 @@
+# ContextInput
+
+Request body of `POST /api/v2/memory/context`.  The same fields as the `/search` request, except that `method` is fixed to `\"context\"`, `min_score` is not supported, and `radius`, `enable_llm_rerank` and `with_readable_episode` are not accepted.
+
+## Properties
+
+Name | Type | Description | Notes
+------------ | ------------- | ------------- | -------------
+**app_id** | **str** | Scope to search in, defaulting to \"default\". Must match the pair used on write. | [optional] [default to 'default']
+**project_id** | **str** | Second half of the scope, defaulting to \"default\". | [optional] [default to 'default']
+**user_id** | **str** |  | [optional] 
+**agent_id** | **str** |  | [optional] 
+**query** | **str** | The question to retrieve for. The loop keeps searching until it judges the evidence sufficient to answer it, so pass the whole question, not keywords. | 
+**method** | **str** | Fixed to `\"context\"`; may be omitted. Any other value is a 422. | [optional] [default to 'context']
+**top_k** | **int** | Maximum number of episodes returned. Either -1 (the default, letting the engine decide) or a value from 1 to 100; anything else is rejected with 422. | [optional] [default to -1]
+**min_score** | **float** |  | [optional] 
+**include_profile** | **bool** | Also return the user's profile alongside the episodes, as on /search. | [optional] [default to False]
+**filters** | [**FilterNode**](FilterNode.md) |  | [optional] 
+
+## Example
+
+```python
+from everos_cloud.models.context_input import ContextInput
+
+# TODO update the JSON string below
+json = "{}"
+# create an instance of ContextInput from a JSON string
+context_input_instance = ContextInput.from_json(json)
+# print the JSON string representation of the object
+print(ContextInput.to_json())
+
+# convert the object into a dict
+context_input_dict = context_input_instance.to_dict()
+# create an instance of ContextInput from a dict
+context_input_from_dict = ContextInput.from_dict(context_input_dict)
+```
+[[Back to Model list]](../README.md#documentation-for-models) [[Back to API list]](../README.md#documentation-for-api-endpoints) [[Back to README]](../README.md)
+
+

docs/EpisodeItem.md

@@ -15,12 +15,12 @@ Name | Type | Description | Notes
 **summary** | **str** | Short summary of the episode — what a result list should show. | 
 **subject** | **str** | What the episode is about, in a few words. | 
 **episode** | **str** | The episode's stored narrative body. This is the indexed, searchable text. | 
-**readable_episode** | **str** |  | [optional] 
 **type** | **str** | How the episode was produced — \"Conversation\" or \"AgentConversation\". | 
 **atomic_facts** | [**List[AtomicFactItem]**](AtomicFactItem.md) | The individual facts extracted from this episode, nested rather than returned separately. | [optional] 
 **tags** | **List[str]** | Tags attached through /api/v2/memory/tag/*. | [optional] 
 **edited_at** | **datetime** |  | [optional] 
 **reflect_state** | **str** |  | [optional] 
+**readable_episode** | **str** |  | [optional] 
 
 ## Example
 

docs/GetInput.md

@@ -14,7 +14,7 @@ Name | Type | Description | Notes
 **page_size** | **int** | Items per page, 1 to 100 (default 20). | [optional] [default to 20]
 **sort_by** | **str** | Order by \"timestamp\" (when the memory happened, default) or \"updated_at\" (when it was last written). Profiles and agent skills have no temporal column and always sort by \"updated_at\". | [optional] [default to 'timestamp']
 **sort_order** | **str** | \"desc\" (default, newest first) or \"asc\". | [optional] [default to 'desc']
-**with_readable_episode** | **bool** | Attach a human-readable rendering to each returned episode, for display only. Ignored for every non-episode `memory_type` rather than rejected. | [optional] [default to False]
+**with_readable_episode** | **bool** | Deprecated and has no effect. Still accepted so existing clients that send it keep working; new code should leave it out. | [optional] [default to False]
 **filters** | [**FilterNode**](FilterNode.md) |  | [optional] 
 
 ## Example

docs/MemoryApi.md

@@ -12,6 +12,7 @@ Method | HTTP request | Description
 [**flush_memory**](MemoryApi.md#flush_memory) | **POST** /api/v2/memory/flush | Force memory extraction [OSS + Cloud]
 [**get_memory**](MemoryApi.md#get_memory) | **POST** /api/v2/memory/get | Get memories [OSS + Cloud]
 [**replace_tags**](MemoryApi.md#replace_tags) | **POST** /api/v2/memory/tag/replace | Replace tags on memories [Cloud]
+[**retrieve_context**](MemoryApi.md#retrieve_context) | **POST** /api/v2/memory/context | Context Retrieval [Cloud-only]
 [**search_memory**](MemoryApi.md#search_memory) | **POST** /api/v2/memory/search | Search memories [OSS + Cloud]
 [**submit_feedback**](MemoryApi.md#submit_feedback) | **POST** /api/v2/memory/feedback | Submit feedback about one memory [Cloud-only]
 [**unbind_tags**](MemoryApi.md#unbind_tags) | **POST** /api/v2/memory/tag/unbind | Unbind tags from memories [Cloud]
@@ -691,6 +692,90 @@ Name | Type | Description  | Notes
 
 [[Back to top]](#) [[Back to API list]](../README.md#documentation-for-api-endpoints) [[Back to Model list]](../README.md#documentation-for-models) [[Back to README]](../README.md)
 
+# **retrieve_context**
+> SuccessEnvelopeSearchData retrieve_context(context_input)
+
+Context Retrieval [Cloud-only]
+
+Retrieve memories with a multi-round, LLM-driven search loop.  An LLM plans and runs several searches over the owner's memories — keyword, semantic, hybrid, topic-cluster, and reading the surrounding conversation or a whole session — and keeps searching until it judges the evidence sufficient to answer `query`. The memories it found are returned. **The response contains memories, not an answer**: the model's own answer is discarded.  Use it for questions a single search answers poorly: multi-hop, temporal, or spread across several conversations. For simple lookups, `/search` is faster and cheaper.  **Request** — the same body as `/search`, except: - `method` is fixed to `\"context\"`. It can be omitted; any other value is a 422. - `min_score` is not supported (422): results are ranked by rank fusion, not by a similarity score. - `radius`, `enable_llm_rerank` and `with_readable_episode` are not accepted (422): the loop does not use them.  **Response** — the same `SearchData` shape as `/search`: - The loop returns its memories in `episodes`, for a `user_id` owner only; for an `agent_id` owner `episodes`, `agent_cases` and `agent_skills` are empty. `profiles` (`include_profile`) and `unprocessed_messages` (a top-level `session_id` filter) are filled exactly as on `/search`. - `episodes[].cited` is `true` for memories the model named as the ones its answer rested on. - `episodes[].score` is a rank-fusion score, not a similarity: roughly 0.01–0.05, plus 1.0 for a cited memory, so cited memories come first. It is not comparable with `/search` scores.  **Limits** — by default at most 5 LLM rounds and 45 seconds per request. Reaching a limit is not an error: the memories found so far are returned.  **Latency** — several LLM calls per request, so noticeably slower than `/search`.
+
+### Example
+
+* Bearer Authentication (BearerAuth):
+
+```python
+import everos_cloud
+from everos_cloud.models.context_input import ContextInput
+from everos_cloud.models.success_envelope_search_data import SuccessEnvelopeSearchData
+from everos_cloud.rest import ApiException
+from pprint import pprint
+
+# Defining the host is optional and defaults to https://api.evermind.ai
+# See configuration.py for a list of all supported configuration parameters.
+configuration = everos_cloud.Configuration(
+    host = "https://api.evermind.ai"
+)
+
+# The client must configure the authentication and authorization parameters
+# in accordance with the API server security policy.
+# Examples for each auth method are provided below, use the example that
+# satisfies your auth use case.
+
+# Configure Bearer authorization: BearerAuth
+configuration = everos_cloud.Configuration(
+    access_token = os.environ["BEARER_TOKEN"]
+)
+
+# Enter a context with an instance of the API client
+with everos_cloud.ApiClient(configuration) as api_client:
+    # Create an instance of the API class
+    api_instance = everos_cloud.MemoryApi(api_client)
+    context_input = everos_cloud.ContextInput() # ContextInput | 
+
+    try:
+        # Context Retrieval [Cloud-only]
+        api_response = api_instance.retrieve_context(context_input)
+        print("The response of MemoryApi->retrieve_context:\n")
+        pprint(api_response)
+    except Exception as e:
+        print("Exception when calling MemoryApi->retrieve_context: %s\n" % e)
+```
+
+
+
+### Parameters
+
+
+Name | Type | Description  | Notes
+------------- | ------------- | ------------- | -------------
+ **context_input** | [**ContextInput**](ContextInput.md)|  | 
+
+### Return type
+
+[**SuccessEnvelopeSearchData**](SuccessEnvelopeSearchData.md)
+
+### Authorization
+
+[BearerAuth](../README.md#BearerAuth)
+
+### HTTP request headers
+
+ - **Content-Type**: application/json
+ - **Accept**: application/json
+
+### HTTP response details
+
+| Status code | Description | Response headers |
+|-------------|-------------|------------------|
+**200** | The memories the loop found, in `episodes`, using the same `SearchData` shape as `/search`. |  -  |
+**422** | Validation Error |  -  |
+**401** | Missing or invalid bearer token. |  -  |
+**403** | Authenticated but not permitted — either rejected by the auth service, or the account's memory API version does not match the interface version implied by the path (a v1 account calling an /api/v2 route). |  -  |
+**429** | Rate limit or quota exceeded. |  -  |
+**503** | The gateway could not reach the authentication service. Transient — retry with backoff. |  -  |
+
+[[Back to top]](#) [[Back to API list]](../README.md#documentation-for-api-endpoints) [[Back to Model list]](../README.md#documentation-for-models) [[Back to README]](../README.md)
+
 # **search_memory**
 > SuccessEnvelopeSearchData search_memory(search_input)
 

docs/Reason.md

@@ -6,7 +6,7 @@ Why the operator made the change. OPTIONAL on both ops: it is recorded on the au
 
 Name | Type | Description | Notes
 ------------ | ------------- | ------------- | -------------
-**code** | **str** | What was wrong, from the fixed list — hallucination, wrong_subject, wrong_time, redundant, missing, privacy, style, other. Required whenever a reason is given. Same base list as `FeedbackInput.reason` plus `missing`, which only an edit can express (an operator fixes a record that left something out; a rating always names a memory that exists). On the contract this SDK is generated from (engine release-20260901_v15) `outdated` is not yet accepted here — the engine adds it in its next release; until then record an outdated-type fix as `wrong_time` or `other`. | 
+**code** | **str** | What was wrong, from the fixed list — hallucination, outdated, wrong_subject, wrong_time, redundant, missing, privacy, style, other. Required whenever a reason is given. Same base list as `FeedbackInput.reason` plus `missing`, which only an edit can express (an operator fixes a record that left something out; a rating always names a memory that exists). | 
 **note** | **str** |  | [optional] 
 
 ## Example

docs/SearchEpisodeItem.md

@@ -15,13 +15,14 @@ Name | Type | Description | Notes
 **summary** | **str** | Short summary of the episode — what a result list should show. | 
 **subject** | **str** | What the episode is about, in a few words. | 
 **episode** | **str** | The episode's stored narrative body. This is the indexed, searchable text. | 
-**readable_episode** | **str** |  | [optional] 
 **type** | **str** | How the episode was produced — \"Conversation\" or \"AgentConversation\". | 
 **atomic_facts** | [**List[SearchAtomicFactItem]**](SearchAtomicFactItem.md) | The facts extracted from this episode, each with its own relevance score. | [optional] 
 **tags** | **List[str]** | Tags attached through /api/v2/memory/tag/*. | [optional] 
 **edited_at** | **datetime** |  | [optional] 
 **reflect_state** | **str** |  | [optional] 
-**score** | **float** | Relevance of this episode to the query. What the number means depends on `method`: the hybrid path fuses its two routes into a probability in 0.0–1.0 (which is what `min_score` filters on), while keyword and vector pass the underlying engine's own score through — BM25 has no upper bound and vector similarity depends on the metric. So compare scores within one method, not across methods. | 
+**score** | **float** | Relevance of this episode to the query. What the number means depends on `method`: the hybrid path fuses its two routes into a probability in 0.0–1.0 (which is what `min_score` filters on), while keyword and vector pass the underlying engine's own score through — BM25 has no upper bound and vector similarity depends on the metric. On /api/v2/memory/context it is a rank-fusion score instead, roughly 0.01–0.05, plus 1.0 for a `cited` episode. So compare scores within one method, not across methods. | 
+**cited** | **bool** | `/context` only: the retrieval model named this memory as one its answer rested on. Always `false` on `/search`. | [optional] [default to False]
+**readable_episode** | **str** |  | [optional] 
 
 ## Example
 

docs/SearchInput.md

@@ -15,7 +15,7 @@ Name | Type | Description | Notes
 **radius** | **float** |  | [optional] 
 **min_score** | **float** |  | [optional] 
 **include_profile** | **bool** | Also return the user's profile alongside the hits, saving a second call. Ignored for an agent owner, whose results carry no profiles. | [optional] [default to False]
-**with_readable_episode** | **bool** | Attach a human-readable rendering of each episode to the returned items, for display only — it is not indexed, filterable or scored, and callers fall back to `episode` when it is null. Ignored for an agent owner. | [optional] [default to False]
+**with_readable_episode** | **bool** | Deprecated and has no effect. Still accepted so existing clients that send it keep working; new code should leave it out. | [optional] [default to False]
 **enable_llm_rerank** | **bool** | Opt-in LLM rerank, and only for hybrid agent_case / agent_skill retrieval. The episode hybrid path has its own fact eviction and ignores this, as do keyword, vector and agentic. | [optional] [default to False]
 **filters** | [**FilterNode**](FilterNode.md) |  | [optional] 
 

docs/UpdateData.md

@@ -16,13 +16,13 @@ Name | Type | Description | Notes
 **summary** | **str** | Short summary of the episode — what a result list should show. | 
 **subject** | **str** | What the episode is about, in a few words. | 
 **episode** | **str** | The episode's stored narrative body. This is the indexed, searchable text. | 
-**readable_episode** | **str** |  | [optional] 
 **type** | **str** | How the episode was produced — \"Conversation\" or \"AgentConversation\". | 
 **atomic_facts** | [**List[AtomicFactItem]**](AtomicFactItem.md) | The individual facts extracted from this episode, nested rather than returned separately. | [optional] 
 **tags** | **List[str]** | Tags attached through /api/v2/memory/tag/*. | [optional] 
 **edited_at** | **datetime** |  | [optional] 
 **reflect_state** | **str** |  | [optional] 
 **unchanged** | **bool** | True when the patch equalled what was already stored — nothing was written and nothing downstream was triggered. | [optional] [default to False]
+**readable_episode** | **str** |  | [optional] 
 
 ## Example
 

everos_cloud/__init__.py

@@ -15,7 +15,7 @@
 """  # noqa: E501
 
 
-__version__ = "1.2.0"
+__version__ = "1.3.0-rc1"
 
 # import apis into sdk package
 from everos_cloud.api.knowledge_api import KnowledgeApi
@@ -49,6 +49,7 @@
 from everos_cloud.models.content import Content
 from everos_cloud.models.content1 import Content1
 from everos_cloud.models.content_item import ContentItem
+from everos_cloud.models.context_input import ContextInput
 from everos_cloud.models.data import Data
 from everos_cloud.models.data1 import Data1
 from everos_cloud.models.delete_by_ids_data import DeleteByIdsData