feat: Add get summaries endpoints & Custom Timestamps (#185)

* feat: add support for custom message timestamps in API - Introduced `created_at` parameter for message creation, allowing users to specify custom timestamps. - **Single source of truth for timestamp string format** - Updated SDK documentation to reflect this new feature and its use cases. - Enhanced validation schemas to include the optional `created_at` field. - Added tests to verify functionality for messages with and without custom timestamps, ensuring correct behavior and default timestamp usage. * feat: add timestamp option to sdks * feat: Add get summaries endpoints * feat: WIP basic SDK implementation blocked until stainless release * feat: Implement SDKs with honcho-core methods * fix (sdk): Used release 1.4.0 core sdks * fix: Code Rabbit * chore: Pytest errors --------- Co-authored-by: Benjamin McCormick <docterformer@protonmail.com>
2025-08-12 17:19:53 -04:00 · 2025-08-12 17:19:53 -04:00 · e914dbe334
parent 0838a281c1
commit e914dbe334
57 changed files with 2237 additions and 524 deletions
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@ -5,7 +5,23 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](http://keepachangelog.com/)
 and this project adheres to [Semantic Versioning](http://semver.org/).

-## [2.2.0] - 2025-08-07
+## [2.3.0] — 2025-08-14
+
+### Added
+
+- `getSummaries` endpoint to get all available summaries for a session directly
+
+### Changed
+
+- Session Peer limit to be based on observers instead, renamed config value to
+  `SESSION_OBSERVERS_LIMIT`
+- Deriver uses `get_context` internally to prevent context window limit errors
+- `Messages` can take a custom timestamp for the `created_at` field, defaulting
+  to the current time
+- `get_context` endpoint returns detailed `Summary` object rather than just
+  summary content
+
+## [2.2.0] — 2025-08-07

 ### Added

@ -28,14 +44,14 @@ and this project adheres to [Semantic Versioning](http://semver.org/).
 - Re-introduced Sentry tracing to deriver
 - Better integrity logic in get_or_create API methods

-## [2.1.2] - 2025-07-30
+## [2.1.2] — 2025-07-30

 ### Fixed

 - Summarizer module to ignore empty summaries and pass appropriate one to get_context
 - Structured Outputs calls with OpenAI provider to pass strict=True to Pydantic Schema

-## [2.1.1] - 2025-07-23
+## [2.1.1] — 2025-07-23

 ### Added

@ -58,7 +74,7 @@ and this project adheres to [Semantic Versioning](http://semver.org/).
 - Refactor summarization for performance and code clarity
 - Refactor queue payloads for clarity

-## [2.1.0] - 2025-07-17
+## [2.1.0] — 2025-07-17

 ### Added

--- a/README.md
+++ b/README.md
@ -1,6 +1,6 @@
 # 🫡 Honcho

-![Static Badge](https://img.shields.io/badge/Version-2.2.0-blue)
+![Static Badge](https://img.shields.io/badge/Version-2.3.0-blue)
 [![Discord](https://img.shields.io/discord/1016845111637839922?style=flat&logo=discord&logoColor=23ffffff&label=Plastic%20Labs&labelColor=235865F2)](https://discord.gg/plasticlabs)
 [![arXiv](https://img.shields.io/badge/arXiv-2310.06983-b31b1b.svg)](https://arxiv.org/abs/2310.06983)
 ![GitHub License](https://img.shields.io/github/license/plastic-labs/honcho)
--- a/docs/changelog/compatibility-guide.mdx
+++ b/docs/changelog/compatibility-guide.mdx
@ -8,23 +8,23 @@ This guide helps you understand which versions of Honcho's API are compatible wi

 ## Version Compatibility

-### Honcho API v2.2.0 (Current)
+### Honcho API v2.3.0 (Current)

 <CardGroup cols={2}>
  <Card title="TypeScript SDK" icon="js">
-    **Compatible Version:** v1.3.0
+    **Compatible Version:** v1.4.0

    Install with:
    ```bash
-    npm install @honcho-ai/sdk@1.3.0
+    npm install @honcho-ai/sdk@1.4.0
    ```
  </Card>
  <Card title="Python SDK" icon="python">
-    **Compatible Version:** v1.3.0
+    **Compatible Version:** v1.4.0

    Install with:
    ```bash
-    pip install honcho-ai==1.3.0
+    pip install honcho-ai==1.4.0
    ```
  </Card>
 </CardGroup>
@ -33,20 +33,20 @@ This guide helps you understand which versions of Honcho's API are compatible wi

 <CardGroup cols={2}>
  <Card title="TypeScript SDK" icon="js">
-    **Compatible Version:** v1.2.1
+    **Compatible Version:** v1.4.0

    Install with:
    ```bash
-    npm install @honcho-ai/sdk@1.2.1
+    npm install @honcho-ai/sdk@1.4.0
    ```
  </Card>

  <Card title="Python SDK" icon="python">
-    **Compatible Version:** v1.2.2
+    **Compatible Version:** v1.4.0

    Install with:
    ```bash
-    pip install honcho-ai==1.2.2
+    pip install honcho-ai==1.4.0
    ```
  </Card>

@ -56,7 +56,8 @@ This guide helps you understand which versions of Honcho's API are compatible wi

 | Honcho API Version | TypeScript SDK | Python SDK |
 |-------------------|---------------|------------|
-| v2.2.0 (Current) | v1.3.0 | v1.3.0 |
+| v2.3.0 (Current) | v1.4.0 | v1.4.0 |
+| v2.2.0 | v1.3.0 | v1.3.0 |
 | v2.1.2 | v1.2.1 | v1.2.2 |
 | v2.1.1 | v1.2.1 | v1.2.2 |
 | v2.1.0 | v1.2.1 | v1.2.2 |
--- a/docs/changelog/introduction.mdx
+++ b/docs/changelog/introduction.mdx
@ -27,7 +27,23 @@ Welcome to the Honcho changelog! This section documents all notable changes to t
 ### Honcho API and SDK Changelogs
 <Tabs>
    <Tab title="Honcho API">
-        <Update label="v2.2.0 (Current)">
+        <Update label="v2.3.0 (Current)">
+        ### Added
+
+        - `getSummaries` endpoint to get all available summaries for a session directly
+
+        ### Changed
+
+        - Session Peer limit to be based on observers instead, renamed config value to
+          `SESSION_OBSERVERS_LIMIT`
+        - Deriver uses `get_context` internally to prevent context window limit errors
+        - `Messages` can take a custom timestamp for the `created_at` field, defaulting
+          to the current time
+        - `get_context` endpoint returns detailed `Summary` object rather than just
+          summary content
+        </Update>
+
+        <Update label="v2.2.0">
        ### Added

        - Arbitrary filters now available on all search endpoints
@ -239,6 +255,16 @@ Welcome to the Honcho changelog! This section documents all notable changes to t

    <Tab title="Python SDK">
        [Python SDK](https://pypi.org/project/honcho-ai/)
+        <Update label="v1.4.0 (Current)">
+        ### Added
+
+        - getSummaries API returning structured summaries
+
+        ### Changed
+
+        - Messages can take an optional `created_at` value, defaulting to the current
+          time (UTC ISO 8601)
+        </Update>
        <Update label="v1.2.2">
            ### Added

@ -275,6 +301,16 @@ Welcome to the Honcho changelog! This section documents all notable changes to t

    <Tab title="TypeScript SDK">
        [TypeScript SDK](https://www.npmjs.com/package/@honcho-ai/sdk)
+        <Update label="v1.4.0 (Current)">
+        ### Added
+
+        - getSummaries API returning structured summaries
+
+        ### Changed
+
+        - Messages can take an optional `created_at` value, defaulting to the current
+          time (UTC ISO 8601)
+        </Update>
        <Update label="v1.2.1">
            ### Added

--- a/docs/docs.json
+++ b/docs/docs.json
@ -14,7 +14,7 @@
  "navigation": {
    "versions": [
      {
-        "version": "v2.2.0",
+        "version": "v2.3.0",
        "api": {
          "openapi": ["openapi.documented.yml"]
        },
@ -131,6 +131,7 @@
                  "v2/api-reference/endpoint/sessions/get-peer-config",
                  "v2/api-reference/endpoint/sessions/set-peer-config",
                  "v2/api-reference/endpoint/sessions/get-session-context",
+                  "v2/api-reference/endpoint/sessions/get-session-summaries",
                  "v2/api-reference/endpoint/sessions/search-session"
                ]
              },
@ -141,12 +142,21 @@
                  "v2/api-reference/endpoint/messages/get-messages",
                  "v2/api-reference/endpoint/messages/get-message",
                  "v2/api-reference/endpoint/messages/update-message",
-                  "v2/api-reference/endpoint/messages/upload-file"
+                  "v2/api-reference/endpoint/messages/create-messages-with-file"
                ]
              },
              {
                "group": "keys",
                "pages": ["v2/api-reference/endpoint/keys/create-key"]
+              },
+              {
+                "group": "webhooks",
+                "pages": [
+                  "v2/api-reference/endpoint/webhooks/list-webhook-endpoints",
+                  "v2/api-reference/endpoint/webhooks/get-or-create-webhook-endpoint",
+                  "v2/api-reference/endpoint/webhooks/delete-webhook-endpoint",
+                  "v2/api-reference/endpoint/webhooks/test-emit"
+                ]
              }
            ]
          },
--- a/docs/package.json
+++ b/docs/package.json
@ -5,7 +5,7 @@
  "main": ".pnp.js",
  "scripts": {
    "dev": "mint dev",
-    "openapi": "npx @mintlify/scraping openapi-file openapi.json -o api-reference/endpoint",
+    "openapi": "npx @mintlify/scraping openapi-file openapi.documented.yml -o api-reference/endpoint",
    "test": "echo \"Error: no test specified\" && exit 1"
  },
  "author": "",
--- a/docs/v2/api-reference/endpoint/messages/create-messages-with-file.mdx
+++ b/docs/v2/api-reference/endpoint/messages/create-messages-with-file.mdx
--- a/docs/v2/api-reference/endpoint/sessions/get-session-summaries.mdx
+++ b/docs/v2/api-reference/endpoint/sessions/get-session-summaries.mdx
@ -0,0 +1,3 @@
+---
+openapi: get /v2/workspaces/{workspace_id}/sessions/{session_id}/summaries
+---
--- a/docs/v2/api-reference/endpoint/webhooks/delete-webhook-endpoint.mdx
+++ b/docs/v2/api-reference/endpoint/webhooks/delete-webhook-endpoint.mdx
@ -0,0 +1,3 @@
+---
+openapi: delete /v2/workspaces/{workspace_id}/webhooks/{endpoint_id}
+---
--- a/docs/v2/api-reference/endpoint/webhooks/get-or-create-webhook-endpoint.mdx
+++ b/docs/v2/api-reference/endpoint/webhooks/get-or-create-webhook-endpoint.mdx
@ -0,0 +1,3 @@
+---
+openapi: post /v2/workspaces/{workspace_id}/webhooks
+---
--- a/docs/v2/api-reference/endpoint/webhooks/list-webhook-endpoints.mdx
+++ b/docs/v2/api-reference/endpoint/webhooks/list-webhook-endpoints.mdx
@ -0,0 +1,3 @@
+---
+openapi: get /v2/workspaces/{workspace_id}/webhooks
+---
--- a/docs/v2/api-reference/endpoint/webhooks/test-emit.mdx
+++ b/docs/v2/api-reference/endpoint/webhooks/test-emit.mdx
@ -0,0 +1,3 @@
+---
+openapi: get /v2/workspaces/{workspace_id}/webhooks/test
+---
--- a/docs/v2/documentation/reference/sdk.mdx
+++ b/docs/v2/documentation/reference/sdk.mdx
@ -555,6 +555,33 @@ const response = await openai.chat.completions.create({
 ```
 </CodeGroup>

+### Custom Message Timestamps
+
+When creating messages, you can optionally specify a custom `created_at` timestamp instead of using the server's current time:
+
+```bash
+curl -X POST "https://api.honcho.dev/v2/workspaces/{workspace_id}/sessions/{session_id}/messages" \
+  -H "Authorization: Bearer $API_KEY" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "messages": [
+      {
+        "peer_id": "user123",
+        "content": "This message happened yesterday",
+        "created_at": "2024-01-01T12:00:00Z",
+        "metadata": {"source": "historical_data"}
+      }
+    ]
+  }'
+```
+
+This is useful for:
+- Importing historical conversation data
+- Backfilling messages from other systems
+- Maintaining accurate timeline ordering when processing batch data
+
+If `created_at` is not provided, messages will use the server's current timestamp.
+
 ### Metadata and Filtering

 See [Using Filters](/v2/guides/using-filters) for more examples on how to use filters.
--- a/docs/v2/openapi.documented.yml
+++ b/docs/v2/openapi.documented.yml
@ -7,7 +7,7 @@ info:
    name: Plastic Labs
    url: https://honcho.dev/
    email: hello@plasticlabs.ai
-  version: 2.1.1
+  version: 2.3.0
 servers:
  - url: http://localhost:8000
    description: Local Development Server
@ -231,42 +231,23 @@ paths:
            description: ID of the workspace to search
            title: Workspace Id
          description: ID of the workspace to search
-        - name: page
-          in: query
-          required: false
-          schema:
-            type: integer
-            minimum: 1
-            description: Page number
-            default: 1
-            title: Page
-          description: Page number
-        - name: size
-          in: query
-          required: false
-          schema:
-            type: integer
-            maximum: 100
-            minimum: 1
-            description: Page size
-            default: 50
-            title: Size
-          description: Page size
      requestBody:
        required: true
        content:
          application/json:
            schema:
-              type: string
-              description: Search query
-              title: Query
+              $ref: '#/components/schemas/MessageSearchOptions'
+              description: 'Message search parameters '
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
-                $ref: '#/components/schemas/Page_Message_'
+                type: array
+                items:
+                  $ref: '#/components/schemas/Message'
+                title: Response Search Workspace V2 Workspaces  Workspace Id  Search Post
        '422':
          description: Validation Error
          content:
@ -282,10 +263,9 @@ paths:
              apiKey: 'My API Key',
            });

-            // Automatically fetches more pages as needed.
-            for await (const message of client.workspaces.search('workspace_id', { body: 'body' })) {
-              console.log(message.id);
-            }
+            const messages = await client.workspaces.search('workspace_id', { query: 'query' });
+
+            console.log(messages);
        - lang: Python
          source: |-
            from honcho_core import Honcho
@ -293,12 +273,11 @@ paths:
            client = Honcho(
                api_key="My API Key",
            )
-            page = client.workspaces.search(
+            messages = client.workspaces.search(
                workspace_id="workspace_id",
-                body="body",
+                query="query",
            )
-            page = page.items[0]
-            print(page.id)
+            print(messages)
  /v2/workspaces/{workspace_id}/deriver/status:
    get:
      tags:
@ -891,27 +870,6 @@ paths:
            description: ID of the peer
            title: Peer Id
          description: ID of the peer
-        - name: page
-          in: query
-          required: false
-          schema:
-            type: integer
-            minimum: 1
-            description: Page number
-            default: 1
-            title: Page
-          description: Page number
-        - name: size
-          in: query
-          required: false
-          schema:
-            type: integer
-            maximum: 100
-            minimum: 1
-            description: Page size
-            default: 50
-            title: Size
-          description: Page size
      requestBody:
        required: true
        content:
@ -925,7 +883,10 @@ paths:
          content:
            application/json:
              schema:
-                $ref: '#/components/schemas/Page_Message_'
+                type: array
+                items:
+                  $ref: '#/components/schemas/Message'
+                title: Response Search Peer V2 Workspaces  Workspace Id  Peers  Peer Id  Search Post
        '422':
          description: Validation Error
          content:
@ -943,12 +904,11 @@ paths:
            });


-            // Automatically fetches more pages as needed.
+            const messages = await client.workspaces.peers.search('workspace_id', 'peer_id', { query: 'query'
+            });

-            for await (const message of client.workspaces.peers.search('workspace_id', 'peer_id', { query:
-            'query' })) {
-              console.log(message.id);
-            }
+
+            console.log(messages);
        - lang: Python
          source: |-
            from honcho_core import Honcho
@ -956,13 +916,12 @@ paths:
            client = Honcho(
                api_key="My API Key",
            )
-            page = client.workspaces.peers.search(
+            messages = client.workspaces.peers.search(
                peer_id="peer_id",
                workspace_id="workspace_id",
                query="query",
            )
-            page = page.items[0]
-            print(page.id)
+            print(messages)
  /v2/workspaces/{workspace_id}/sessions:
    post:
      tags:
@ -1699,20 +1658,20 @@ paths:
                $ref: '#/components/schemas/HTTPValidationError'
      x-codeSamples:
        - lang: JavaScript
-          source: >-
+          source: |-
            import Honcho from '@honcho-ai/core';

-
            const client = new Honcho({
              apiKey: 'My API Key',
            });

+            const sessionPeerConfig = await client.workspaces.sessions.peers.getConfig(
+              'workspace_id',
+              'session_id',
+              'peer_id',
+            );

-            const response = await client.workspaces.sessions.peers.getConfig('workspace_id', 'session_id',
-            'peer_id');
-
-
-            console.log(response.observe_me);
+            console.log(sessionPeerConfig.observe_me);
        - lang: Python
          source: |-
            from honcho_core import Honcho
@ -1720,12 +1679,12 @@ paths:
            client = Honcho(
                api_key="My API Key",
            )
-            response = client.workspaces.sessions.peers.get_config(
+            session_peer_config = client.workspaces.sessions.peers.get_config(
                peer_id="peer_id",
                workspace_id="workspace_id",
                session_id="session_id",
            )
-            print(response.observe_me)
+            print(session_peer_config.observe_me)
    post:
      tags:
        - sessions
@ -1814,15 +1773,16 @@ paths:
        - sessions
      summary: Get Session Context
      description: >-
-        Produce a context object from the session. The caller provides a token limit which the entire context
-        must fit into.
+        Produce a context object from the session. The caller provides an optional token limit which the
+        entire context must fit into.

-        To do this, we allocate 40% of the token limit to the summary, and 60% to recent messages -- as many
-        as can fit.
+        If not provided, the context will be exhaustive (within configured max tokens). To do this, we
+        allocate 40% of the token limit

-        If the caller does not want a summary, we allocate all the tokens to recent messages.
+        to the summary, and 60% to recent messages -- as many as can fit. Note that the summary will usually
+        take up less space than

-        The default token limit if not provided is 2048. (TODO: make this configurable)
+        this. If the caller does not want a summary, we allocate all the tokens to recent messages.
      operationId: get_session_context_v2_workspaces__workspace_id__sessions__session_id__context_get
      security:
        - HTTPBearer: []
@ -1850,19 +1810,24 @@ paths:
          schema:
            anyOf:
              - type: integer
+                maximum: 100000
              - type: 'null'
-            description: Number of tokens to use for the context. Includes summary if set to true
+            description: >-
+              Number of tokens to use for the context. Includes summary if set to true. If not provided, the
+              context will be exhaustive (within 100000 tokens)
            title: Tokens
-          description: Number of tokens to use for the context. Includes summary if set to true
+          description: >-
+            Number of tokens to use for the context. Includes summary if set to true. If not provided, the
+            context will be exhaustive (within 100000 tokens)
        - name: summary
          in: query
          required: false
          schema:
            type: boolean
-            description: Whether to summarize the session history prior to the cutoff message
-            default: false
+            description: Whether or not to include a summary *if* one is available for the session
+            default: true
            title: Summary
-          description: Whether to summarize the session history prior to the cutoff message
+          description: Whether or not to include a summary *if* one is available for the session
      responses:
        '200':
          description: Successful Response
@ -1900,6 +1865,74 @@ paths:
                workspace_id="workspace_id",
            )
            print(response.id)
+  /v2/workspaces/{workspace_id}/sessions/{session_id}/summaries:
+    get:
+      tags:
+        - sessions
+      summary: Get Session Summaries
+      description: |-
+        Get available summaries for a session.
+
+        Returns both short and long summaries if available, including metadata like
+        the message ID they cover up to, creation timestamp, and token count.
+      operationId: get_session_summaries_v2_workspaces__workspace_id__sessions__session_id__summaries_get
+      security:
+        - HTTPBearer: []
+        - {}
+      parameters:
+        - name: workspace_id
+          in: path
+          required: true
+          schema:
+            type: string
+            description: ID of the workspace
+            title: Workspace Id
+          description: ID of the workspace
+        - name: session_id
+          in: path
+          required: true
+          schema:
+            type: string
+            description: ID of the session
+            title: Session Id
+          description: ID of the session
+      responses:
+        '200':
+          description: Successful Response
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/SessionSummaries'
+        '422':
+          description: Validation Error
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/HTTPValidationError'
+      x-codeSamples:
+        - lang: JavaScript
+          source: |-
+            import Honcho from '@honcho-ai/core';
+
+            const client = new Honcho({
+              apiKey: 'My API Key',
+            });
+
+            const response = await client.workspaces.sessions.summaries('workspace_id', 'session_id');
+
+            console.log(response.id);
+        - lang: Python
+          source: |-
+            from honcho_core import Honcho
+
+            client = Honcho(
+                api_key="My API Key",
+            )
+            response = client.workspaces.sessions.summaries(
+                session_id="session_id",
+                workspace_id="workspace_id",
+            )
+            print(response.id)
  /v2/workspaces/{workspace_id}/sessions/{session_id}/search:
    post:
      tags:
@ -1927,41 +1960,23 @@ paths:
            description: ID of the session
            title: Session Id
          description: ID of the session
-        - name: page
-          in: query
-          required: false
-          schema:
-            type: integer
-            minimum: 1
-            description: Page number
-            default: 1
-            title: Page
-          description: Page number
-        - name: size
-          in: query
-          required: false
-          schema:
-            type: integer
-            maximum: 100
-            minimum: 1
-            description: Page size
-            default: 50
-            title: Size
-          description: Page size
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/MessageSearchOptions'
-              description: 'Message search parameters '
+              description: Message search parameters
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
-                $ref: '#/components/schemas/Page_Message_'
+                type: array
+                items:
+                  $ref: '#/components/schemas/Message'
+                title: Response Search Session V2 Workspaces  Workspace Id  Sessions  Session Id  Search Post
        '422':
          description: Validation Error
          content:
@ -1970,19 +1985,20 @@ paths:
                $ref: '#/components/schemas/HTTPValidationError'
      x-codeSamples:
        - lang: JavaScript
-          source: |-
+          source: >-
            import Honcho from '@honcho-ai/core';

+
            const client = new Honcho({
              apiKey: 'My API Key',
            });

-            // Automatically fetches more pages as needed.
-            for await (const message of client.workspaces.sessions.search('workspace_id', 'session_id', {
-              query: 'query',
-            })) {
-              console.log(message.id);
-            }
+
+            const messages = await client.workspaces.sessions.search('workspace_id', 'session_id', { query:
+            'query' });
+
+
+            console.log(messages);
        - lang: Python
          source: |-
            from honcho_core import Honcho
@ -1990,13 +2006,12 @@ paths:
            client = Honcho(
                api_key="My API Key",
            )
-            page = client.workspaces.sessions.search(
+            messages = client.workspaces.sessions.search(
                session_id="session_id",
                workspace_id="workspace_id",
                query="query",
            )
-            page = page.items[0]
-            print(page.id)
+            print(messages)
  /v2/workspaces/{workspace_id}/sessions/{session_id}/messages/:
    post:
      tags:
@ -2505,6 +2520,267 @@ paths:
            )
            key = client.keys.create()
            print(key)
+  /v2/workspaces/{workspace_id}/webhooks:
+    post:
+      tags:
+        - webhooks
+      summary: Get Or Create Webhook Endpoint
+      description: Get or create a webhook endpoint URL.
+      operationId: get_or_create_webhook_endpoint_v2_workspaces__workspace_id__webhooks_post
+      security:
+        - HTTPBearer: []
+        - {}
+      parameters:
+        - name: workspace_id
+          in: path
+          required: true
+          schema:
+            type: string
+            description: Workspace ID
+            title: Workspace Id
+          description: Workspace ID
+      requestBody:
+        required: true
+        content:
+          application/json:
+            schema:
+              $ref: '#/components/schemas/WebhookEndpointCreate'
+              description: Webhook endpoint parameters
+      responses:
+        '200':
+          description: Successful Response
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/WebhookEndpoint'
+        '422':
+          description: Validation Error
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/HTTPValidationError'
+      x-codeSamples:
+        - lang: JavaScript
+          source: >-
+            import Honcho from '@honcho-ai/core';
+
+
+            const client = new Honcho({
+              apiKey: 'My API Key',
+            });
+
+
+            const webhookEndpoint = await client.workspaces.webhooks.getOrCreate('workspace_id', { url: 'url'
+            });
+
+
+            console.log(webhookEndpoint.id);
+        - lang: Python
+          source: |-
+            from honcho_core import Honcho
+
+            client = Honcho(
+                api_key="My API Key",
+            )
+            webhook_endpoint = client.workspaces.webhooks.get_or_create(
+                workspace_id="workspace_id",
+                url="url",
+            )
+            print(webhook_endpoint.id)
+    get:
+      tags:
+        - webhooks
+      summary: List Webhook Endpoints
+      description: List all webhook endpoints, optionally filtered by workspace.
+      operationId: list_webhook_endpoints_v2_workspaces__workspace_id__webhooks_get
+      security:
+        - HTTPBearer: []
+        - {}
+      parameters:
+        - name: workspace_id
+          in: path
+          required: true
+          schema:
+            type: string
+            description: Workspace ID
+            title: Workspace Id
+          description: Workspace ID
+        - name: page
+          in: query
+          required: false
+          schema:
+            type: integer
+            minimum: 1
+            description: Page number
+            default: 1
+            title: Page
+          description: Page number
+        - name: size
+          in: query
+          required: false
+          schema:
+            type: integer
+            maximum: 100
+            minimum: 1
+            description: Page size
+            default: 50
+            title: Size
+          description: Page size
+      responses:
+        '200':
+          description: Successful Response
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/Page_WebhookEndpoint_'
+        '422':
+          description: Validation Error
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/HTTPValidationError'
+      x-codeSamples:
+        - lang: JavaScript
+          source: |-
+            import Honcho from '@honcho-ai/core';
+
+            const client = new Honcho({
+              apiKey: 'My API Key',
+            });
+
+            // Automatically fetches more pages as needed.
+            for await (const webhookEndpoint of client.workspaces.webhooks.list('workspace_id')) {
+              console.log(webhookEndpoint.id);
+            }
+        - lang: Python
+          source: |-
+            from honcho_core import Honcho
+
+            client = Honcho(
+                api_key="My API Key",
+            )
+            page = client.workspaces.webhooks.list(
+                workspace_id="workspace_id",
+            )
+            page = page.items[0]
+            print(page.id)
+  /v2/workspaces/{workspace_id}/webhooks/{endpoint_id}:
+    delete:
+      tags:
+        - webhooks
+      summary: Delete Webhook Endpoint
+      description: Delete a specific webhook endpoint.
+      operationId: delete_webhook_endpoint_v2_workspaces__workspace_id__webhooks__endpoint_id__delete
+      security:
+        - HTTPBearer: []
+        - {}
+      parameters:
+        - name: workspace_id
+          in: path
+          required: true
+          schema:
+            type: string
+            description: Workspace ID
+            title: Workspace Id
+          description: Workspace ID
+        - name: endpoint_id
+          in: path
+          required: true
+          schema:
+            type: string
+            description: Webhook endpoint ID
+            title: Endpoint Id
+          description: Webhook endpoint ID
+      responses:
+        '200':
+          description: Successful Response
+          content:
+            application/json:
+              schema: {}
+        '422':
+          description: Validation Error
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/HTTPValidationError'
+      x-codeSamples:
+        - lang: JavaScript
+          source: |-
+            import Honcho from '@honcho-ai/core';
+
+            const client = new Honcho({
+              apiKey: 'My API Key',
+            });
+
+            const webhook = await client.workspaces.webhooks.delete('workspace_id', 'endpoint_id');
+
+            console.log(webhook);
+        - lang: Python
+          source: |-
+            from honcho_core import Honcho
+
+            client = Honcho(
+                api_key="My API Key",
+            )
+            webhook = client.workspaces.webhooks.delete(
+                endpoint_id="endpoint_id",
+                workspace_id="workspace_id",
+            )
+            print(webhook)
+  /v2/workspaces/{workspace_id}/webhooks/test:
+    get:
+      tags:
+        - webhooks
+      summary: Test Emit
+      description: Test publishing a webhook event.
+      operationId: test_emit_v2_workspaces__workspace_id__webhooks_test_get
+      security:
+        - HTTPBearer: []
+        - {}
+      parameters:
+        - name: workspace_id
+          in: path
+          required: true
+          schema:
+            type: string
+            description: Workspace ID
+            title: Workspace Id
+          description: Workspace ID
+      responses:
+        '200':
+          description: Successful Response
+          content:
+            application/json:
+              schema: {}
+        '422':
+          description: Validation Error
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/HTTPValidationError'
+      x-codeSamples:
+        - lang: JavaScript
+          source: |-
+            import Honcho from '@honcho-ai/core';
+
+            const client = new Honcho({
+              apiKey: 'My API Key',
+            });
+
+            const response = await client.workspaces.webhooks.testEmit('workspace_id');
+
+            console.log(response);
+        - lang: Python
+          source: |-
+            from honcho_core import Honcho
+
+            client = Honcho(
+                api_key="My API Key",
+            )
+            response = client.workspaces.webhooks.test_emit(
+                "workspace_id",
+            )
+            print(response)
 components:
  schemas:
    Body_create_messages_with_file_v2_workspaces__workspace_id__sessions__session_id__messages_upload_post:
@ -2612,9 +2888,7 @@ components:
          type: string
          title: Peer Id
        session_id:
-          anyOf:
-            - type: string
-            - type: 'null'
+          type: string
          title: Session Id
        metadata:
          additionalProperties: true
@ -2670,6 +2944,12 @@ components:
              type: object
            - type: 'null'
          title: Metadata
+        created_at:
+          anyOf:
+            - type: string
+              format: date-time
+            - type: 'null'
+          title: Created At
      type: object
      required:
        - content
@ -2682,7 +2962,7 @@ components:
            - additionalProperties: true
              type: object
            - type: 'null'
-          title: Filter
+          title: Filters
      type: object
      title: MessageGet
    MessageSearchOptions:
@ -2691,12 +2971,20 @@ components:
          type: string
          title: Query
          description: Search query
-        semantic:
+        filters:
          anyOf:
-            - type: boolean
+            - additionalProperties: true
+              type: object
            - type: 'null'
-          title: Semantic
-          description: Whether to explicitly use semantic search to filter the results
+          title: Filters
+          description: Filters to scope the search
+        limit:
+          type: integer
+          maximum: 100
+          minimum: 1
+          title: Limit
+          description: Number of results to return
+          default: 10
      type: object
      required:
        - query
@ -2798,6 +3086,35 @@ components:
        - page
        - size
      title: Page[Session]
+    Page_WebhookEndpoint_:
+      properties:
+        items:
+          items:
+            $ref: '#/components/schemas/WebhookEndpoint'
+          type: array
+          title: Items
+        total:
+          type: integer
+          minimum: 0
+          title: Total
+        page:
+          type: integer
+          minimum: 1
+          title: Page
+        size:
+          type: integer
+          minimum: 1
+          title: Size
+        pages:
+          type: integer
+          minimum: 0
+          title: Pages
+      type: object
+      required:
+        - items
+        - page
+        - size
+      title: Page[WebhookEndpoint]
    Page_Workspace_:
      properties:
        items:
@ -2884,7 +3201,7 @@ components:
            - additionalProperties: true
              type: object
            - type: 'null'
-          title: Filter
+          title: Filters
      type: object
      title: PeerGet
    PeerRepresentationGet:
@ -2960,13 +3277,14 @@ components:
          type: array
          title: Messages
        summary:
-          type: string
-          title: Summary
+          anyOf:
+            - $ref: '#/components/schemas/Summary'
+            - type: 'null'
+          description: The summary if available
      type: object
      required:
        - id
        - messages
-        - summary
      title: SessionContext
    SessionCreate:
      properties:
@ -3037,7 +3355,7 @@ components:
            - additionalProperties: true
              type: object
            - type: 'null'
-          title: Filter
+          title: Filters
      type: object
      title: SessionGet
    SessionPeerConfig:
@ -3059,6 +3377,25 @@ components:
            representation of this peer
      type: object
      title: SessionPeerConfig
+    SessionSummaries:
+      properties:
+        id:
+          type: string
+          title: Id
+        short_summary:
+          anyOf:
+            - $ref: '#/components/schemas/Summary'
+            - type: 'null'
+          description: The short summary if available
+        long_summary:
+          anyOf:
+            - $ref: '#/components/schemas/Summary'
+            - type: 'null'
+          description: The long summary if available
+      type: object
+      required:
+        - id
+      title: SessionSummaries
    SessionUpdate:
      properties:
        metadata:
@ -3075,6 +3412,36 @@ components:
          title: Configuration
      type: object
      title: SessionUpdate
+    Summary:
+      properties:
+        content:
+          type: string
+          title: Content
+          description: The summary text
+        message_id:
+          type: integer
+          title: Message Id
+          description: The ID of the message that this summary covers up to
+        summary_type:
+          type: string
+          title: Summary Type
+          description: The type of summary (short or long)
+        created_at:
+          type: string
+          title: Created At
+          description: The timestamp of when the summary was created (ISO format)
+        token_count:
+          type: integer
+          title: Token Count
+          description: The number of tokens in the summary text
+      type: object
+      required:
+        - content
+        - message_id
+        - summary_type
+        - created_at
+        - token_count
+      title: Summary
    ValidationError:
      properties:
        loc:
@ -3096,6 +3463,39 @@ components:
        - msg
        - type
      title: ValidationError
+    WebhookEndpoint:
+      properties:
+        id:
+          type: string
+          title: Id
+        workspace_id:
+          anyOf:
+            - type: string
+            - type: 'null'
+          title: Workspace Id
+        url:
+          type: string
+          title: Url
+        created_at:
+          type: string
+          format: date-time
+          title: Created At
+      type: object
+      required:
+        - id
+        - workspace_id
+        - url
+        - created_at
+      title: WebhookEndpoint
+    WebhookEndpointCreate:
+      properties:
+        url:
+          type: string
+          title: Url
+      type: object
+      required:
+        - url
+      title: WebhookEndpointCreate
    Workspace:
      properties:
        id:
@ -3147,7 +3547,7 @@ components:
            - additionalProperties: true
              type: object
            - type: 'null'
-          title: Filter
+          title: Filters
      type: object
      title: WorkspaceGet
    WorkspaceUpdate:
--- a/pyproject.toml
+++ b/pyproject.toml
@ -1,6 +1,6 @@
 [project]
 name = "honcho"
-version = "2.2.0"
+version = "2.3.0"
 description = "Honcho Server"
 authors = [
  {name = "Plastic Labs", email = "hello@plasticlabs.ai"},
@ -32,8 +32,6 @@ dependencies = [
 ]
 [tool.uv]
 dev-dependencies = [
-    "honcho-core==1.3.0",
-    "honcho-ai==1.3.0",
    "pytest>=8.2.2",
    "sqlalchemy-utils>=0.41.2",
    "pytest-asyncio>=0.23.7",
@ -44,8 +42,17 @@ dev-dependencies = [
    "basedpyright>=1.29.4",
    "pre-commit>=4.2.0",
    "pytest-cov>=6.2.1",
+    "honcho-ai",
 ]

+[tool.uv.workspace]
+members = [
+    "sdks/python",
+]
+
+[tool.uv.sources]
+honcho-ai = { workspace = true }
+
 [tool.ruff.lint]
 # from https://docs.astral.sh/ruff/linter/#rule-selection example
 select = [
--- a/scripts/update_version.py
+++ b/scripts/update_version.py
@ -608,7 +608,7 @@ TYPESCRIPT_VERSION=
            )

            # Add new row at the top
-            new_row = f"| v{api_version} (Current) | v{typescript_version} | v{python_version} | Latest release |"
+            new_row = f"| v{api_version} (Current) | v{typescript_version} | v{python_version} |"

            # Reconstruct table
            new_table = header + new_row + "\n" + rows + after_table
--- a/sdks/python/CHANGELOG.md
+++ b/sdks/python/CHANGELOG.md
@ -5,6 +5,17 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](http://keepachangelog.com/)
 and this project adheres to [Semantic Versioning](http://semver.org/).

+## [1.4.0] - 2025-08-12
+
+### Added
+
+- getSummaries API returning structured summaries
+
+### Changed
+
+- Messages can take an optional `created_at` value, defaulting to the current
+  time (UTC ISO 8601)
+
 ## [1.3.0] - 2025-08-04

 ### Added
--- a/sdks/python/examples/get_summaries.py
+++ b/sdks/python/examples/get_summaries.py
@ -0,0 +1,82 @@
+"""
+Example of getting session summaries using the Honcho Python SDK.
+
+This example demonstrates how to retrieve both short and long summaries
+for a session, including their metadata like message ID, creation timestamp,
+and token count.
+"""
+
+from honcho import AsyncHoncho, Honcho, SessionSummaries
+import asyncio
+import os
+
+# Initialize the Honcho client
+api_key = os.getenv("HONCHO_API_KEY")
+if not api_key:
+    raise ValueError("Please set HONCHO_API_KEY environment variable")
+
+client = Honcho(api_key=api_key)
+
+# Get a session (replace with your actual session ID)
+session = client.session("my-conversation-session")
+
+# Get summaries for the session
+summaries: SessionSummaries = session.get_summaries()
+
+print(f"Session ID: {summaries.id}")
+print("-" * 50)
+
+# Check and display short summary
+if summaries.short_summary:
+    print("SHORT SUMMARY:")
+    print(f"  Content: {summaries.short_summary.content[:200]}...")  # First 200 chars
+    print(f"  Covers up to message ID: {summaries.short_summary.message_id}")
+    print(f"  Created at: {summaries.short_summary.created_at}")
+    print(f"  Token count: {summaries.short_summary.token_count}")
+    print(f"  Type: {summaries.short_summary.summary_type}")
+else:
+    print("No short summary available yet")
+
+print("-" * 50)
+
+# Check and display long summary
+if summaries.long_summary:
+    print("LONG SUMMARY:")
+    print(f"  Content: {summaries.long_summary.content[:200]}...")  # First 200 chars
+    print(f"  Covers up to message ID: {summaries.long_summary.message_id}")
+    print(f"  Created at: {summaries.long_summary.created_at}")
+    print(f"  Token count: {summaries.long_summary.token_count}")
+    print(f"  Type: {summaries.long_summary.summary_type}")
+else:
+    print("No long summary available yet")
+
+# Example with async client
+print("\n" + "=" * 50)
+print("ASYNC EXAMPLE:")
+print("=" * 50)
+
+
+async def get_summaries_async():
+    async_client = AsyncHoncho(api_key=api_key)
+
+    # Get a session
+    async_session = async_client.session("my-conversation-session")
+
+    # Get summaries asynchronously
+    summaries = await async_session.get_summaries()
+
+    print(f"Session ID (async): {summaries.id}")
+
+    if summaries.short_summary:
+        print(
+            f"Short summary available with {summaries.short_summary.token_count} tokens"
+        )
+
+    if summaries.long_summary:
+        print(
+            f"Long summary available with {summaries.long_summary.token_count} tokens"
+        )
+
+
+# Run the async example
+asyncio.run(get_summaries_async())
--- a/sdks/python/examples/pydantic_validation_example.py
+++ b/sdks/python/examples/pydantic_validation_example.py
@ -5,11 +5,13 @@ This example shows how the SDK now uses Pydantic to validate inputs at runtime,
 providing better error messages and type safety.
 """

+import datetime
 import logging

-from honcho import Honcho
 from pydantic import ValidationError

+from honcho import Honcho
+
 logging.basicConfig(level=logging.INFO)


@ -119,6 +121,24 @@ def demonstrate_validation():
    except ValidationError as e:
        print(f"❌ Validation error: {e}")

+    # Example 10: Custom created_at timestamps
+    print("10. Custom created_at timestamps:")
+    try:
+        honcho = Honcho(environment="local", workspace_id="test")
+        peer = honcho.peer("alice")
+        message = peer.message("Hello, world!", created_at=datetime.datetime.now())
+        print(f"✅ Created message: {message}")
+        message = peer.message(
+            "Hello, world!",
+            created_at=datetime.datetime(1999, 1, 1, tzinfo=datetime.timezone.utc),
+        )
+        print(f"✅ Created message: {message}")
+        session = honcho.session("conversation_1")
+        session.add_messages([message])
+        print(f"✅ Added message to session: {session}")
+    except ValidationError as e:
+        print(f"❌ Validation error: {e}")
+
    print("\n" + "=" * 50 + "\n")
    print("🎉 Pydantic validation examples completed!")

--- a/sdks/python/pyproject.toml
+++ b/sdks/python/pyproject.toml
@ -1,6 +1,6 @@
 [project]
 name = "honcho-ai"
-version = "1.3.0"
+version = "1.4.0"
 description = "Official DX Optimized Python SDK for Honcho"
 dynamic = ["readme"]
 license = "Apache-2.0"
@ -8,7 +8,7 @@ authors = [
 { name = "Plastic Labs", email = "hello@plasticlabs.ai" },
 ]
 dependencies = [
-    "honcho-core==1.3.0",
+    "honcho-core>=1.4.0",
    "httpx>=0.28.0, <1",
    "pydantic>=2.0.0, <3",
 ]
--- a/sdks/python/src/honcho/init.py
+++ b/sdks/python/src/honcho/init.py
@ -44,9 +44,9 @@ from .client import Honcho
 from .pagination import SyncPage
 from .peer import Peer
 from .session import Session
-from .session_context import SessionContext
+from .session_context import SessionContext, SessionSummaries, Summary

-__version__ = "1.0.0"
+__version__ = "1.4.0"
 __author__ = "Plastic Labs"
 __email__ = "hello@plasticlabs.ai"

@ -59,5 +59,7 @@ __all__ = [
    "Peer",
    "Session",
    "SessionContext",
+    "SessionSummaries",
+    "Summary",
    "SyncPage",
 ]
--- a/sdks/python/src/honcho/async_client/peer.py
+++ b/sdks/python/src/honcho/async_client/peer.py
@ -1,5 +1,6 @@
 from __future__ import annotations

+import datetime
 from typing import TYPE_CHECKING

 from honcho_core import AsyncHoncho as AsyncHonchoCore
@ -175,6 +176,10 @@ class AsyncPeer(BaseModel):
        metadata: dict[str, object] | None = Field(
            None, description="Optional metadata dictionary"
        ),
+        created_at: datetime.datetime | str | None = Field(
+            None,
+            description="Optional created-at timestamp for the message. Accepts a datetime which will be converted to an ISO 8601 string, or a preformatted string.",
+        ),
    ) -> MessageCreateParam:
        """
        Create a MessageCreateParam object attributed to this peer.
@ -189,7 +194,18 @@ class AsyncPeer(BaseModel):
        Returns:
            A new MessageCreateParam object with this peer's ID and the provided content
        """
-        return MessageCreateParam(peer_id=self.id, content=content, metadata=metadata)
+        created_at_str: str | None
+        if isinstance(created_at, datetime.datetime):
+            created_at_str = created_at.isoformat()
+        else:
+            created_at_str = created_at
+
+        return MessageCreateParam(
+            peer_id=self.id,
+            content=content,
+            metadata=metadata,
+            created_at=created_at_str,
+        )

    async def get_metadata(self) -> dict[str, object]:
        """
--- a/sdks/python/src/honcho/async_client/session.py
+++ b/sdks/python/src/honcho/async_client/session.py
@ -8,7 +8,7 @@ from honcho_core.types.workspaces.sessions import MessageCreateParam
 from honcho_core.types.workspaces.sessions.message import Message
 from pydantic import BaseModel, ConfigDict, Field, PrivateAttr, validate_call

-from ..session_context import SessionContext
+from ..session_context import SessionContext, SessionSummaries, Summary
 from ..utils import prepare_file_for_upload
 from .pagination import AsyncPage

@ -440,8 +440,72 @@ class AsyncSession(BaseModel):
            summary=summary,
        )

+        # Convert the honcho_core summary to our Summary if it exists
+        session_summary = None
+        if context.summary:
+            session_summary = Summary(
+                content=context.summary.content,
+                message_id=context.summary.message_id,
+                summary_type=context.summary.summary_type,
+                created_at=context.summary.created_at,
+                token_count=context.summary.token_count,
+            )
+
        return SessionContext(
-            session_id=self.id, messages=context.messages, summary=context.summary
+            session_id=self.id, messages=context.messages, summary=session_summary
+        )
+
+    async def get_summaries(self) -> SessionSummaries:
+        """
+        Get available summaries for this session.
+
+        Makes an async API call to retrieve both short and long summaries for this session,
+        if they are available. Summaries are created asynchronously by the backend
+        as messages are added to the session.
+
+        Returns:
+            A SessionSummaries object containing:
+            - id: The session ID
+            - short_summary: The short summary if available, including metadata
+            - long_summary: The long summary if available, including metadata
+
+        Note:
+            Summaries may be None if:
+            - Not enough messages have been added to trigger summary generation
+            - The summary generation is still in progress
+            - Summary generation is disabled for this session
+        """
+        # Use the honcho_core client to get summaries
+        response = await self._client.workspaces.sessions.summaries(
+            session_id=self.id,
+            workspace_id=self.workspace_id,
+        )
+
+        # Create Summary objects from the response data
+        short_summary = None
+        if response.short_summary:
+            short_summary = Summary(
+                content=response.short_summary.content,
+                message_id=response.short_summary.message_id,
+                summary_type=response.short_summary.summary_type,
+                created_at=response.short_summary.created_at,
+                token_count=response.short_summary.token_count,
+            )
+
+        long_summary = None
+        if response.long_summary:
+            long_summary = Summary(
+                content=response.long_summary.content,
+                message_id=response.long_summary.message_id,
+                summary_type=response.long_summary.summary_type,
+                created_at=response.long_summary.created_at,
+                token_count=response.long_summary.token_count,
+            )
+
+        return SessionSummaries(
+            id=response.id or self.id,
+            short_summary=short_summary,
+            long_summary=long_summary,
        )

    @validate_call
--- a/sdks/python/src/honcho/peer.py
+++ b/sdks/python/src/honcho/peer.py
@ -1,5 +1,6 @@
 from __future__ import annotations

+import datetime
 from typing import TYPE_CHECKING

 from honcho_core import Honcho as HonchoCore
@ -158,6 +159,10 @@ class Peer(BaseModel):
        metadata: dict[str, object] | None = Field(
            None, description="Optional metadata dictionary"
        ),
+        created_at: datetime.datetime | str | None = Field(
+            None,
+            description="Optional created-at timestamp for the message. Accepts a datetime which will be converted to an ISO 8601 string, or a preformatted string.",
+        ),
    ) -> MessageCreateParam:
        """
        Create a MessageCreateParam object attributed to this peer.
@ -172,7 +177,18 @@ class Peer(BaseModel):
        Returns:
            A new MessageCreateParam object with this peer's ID and the provided content
        """
-        return MessageCreateParam(peer_id=self.id, content=content, metadata=metadata)
+        created_at_str: str | None
+        if isinstance(created_at, datetime.datetime):
+            created_at_str = created_at.isoformat()
+        else:
+            created_at_str = created_at
+
+        return MessageCreateParam(
+            peer_id=self.id,
+            content=content,
+            metadata=metadata,
+            created_at=created_at_str,
+        )

    def get_metadata(self) -> dict[str, object]:
        """
--- a/sdks/python/src/honcho/session.py
+++ b/sdks/python/src/honcho/session.py
@ -9,7 +9,7 @@ from honcho_core.types.workspaces.sessions.message import Message
 from pydantic import BaseModel, ConfigDict, Field, PrivateAttr, validate_call

 from .pagination import SyncPage
-from .session_context import SessionContext
+from .session_context import SessionContext, SessionSummaries, Summary
 from .utils import prepare_file_for_upload

 if TYPE_CHECKING:
@ -421,8 +421,72 @@ class Session(BaseModel):
            summary=summary,
        )

+        # Convert the honcho_core summary to our Summary if it exists
+        session_summary = None
+        if context.summary:
+            session_summary = Summary(
+                content=context.summary.content,
+                message_id=context.summary.message_id,
+                summary_type=context.summary.summary_type,
+                created_at=context.summary.created_at,
+                token_count=context.summary.token_count,
+            )
+
        return SessionContext(
-            session_id=self.id, messages=context.messages, summary=context.summary
+            session_id=self.id, messages=context.messages, summary=session_summary
+        )
+
+    def get_summaries(self) -> SessionSummaries:
+        """
+        Get available summaries for this session.
+
+        Makes an API call to retrieve both short and long summaries for this session,
+        if they are available. Summaries are created asynchronously by the backend
+        as messages are added to the session.
+
+        Returns:
+            A SessionSummaries object containing:
+            - id: The session ID
+            - short_summary: The short summary if available, including metadata
+            - long_summary: The long summary if available, including metadata
+
+        Note:
+            Summaries may be None if:
+            - Not enough messages have been added to trigger summary generation
+            - The summary generation is still in progress
+            - Summary generation is disabled for this session
+        """
+        # Use the honcho_core client to get summaries
+        response = self._client.workspaces.sessions.summaries(
+            session_id=self.id,
+            workspace_id=self.workspace_id,
+        )
+
+        # Create Summary objects from the response data
+        short_summary = None
+        if response.short_summary:
+            short_summary = Summary(
+                content=response.short_summary.content,
+                message_id=response.short_summary.message_id,
+                summary_type=response.short_summary.summary_type,
+                created_at=response.short_summary.created_at,
+                token_count=response.short_summary.token_count,
+            )
+
+        long_summary = None
+        if response.long_summary:
+            long_summary = Summary(
+                content=response.long_summary.content,
+                message_id=response.long_summary.message_id,
+                summary_type=response.long_summary.summary_type,
+                created_at=response.long_summary.created_at,
+                token_count=response.long_summary.token_count,
+            )
+
+        return SessionSummaries(
+            id=response.id or self.id,
+            short_summary=short_summary,
+            long_summary=long_summary,
        )

    @validate_call
--- a/sdks/python/src/honcho/session_context.py
+++ b/sdks/python/src/honcho/session_context.py
@ -9,6 +9,34 @@ if TYPE_CHECKING:
    from .peer import Peer


+class Summary(BaseModel):
+    """Represents a summary of a session's conversation."""
+
+    content: str = Field(..., description="The summary text")
+    message_id: int = Field(
+        ..., description="The ID of the message that this summary covers up to"
+    )
+    summary_type: str = Field(..., description="The type of summary (short or long)")
+    created_at: str = Field(
+        ..., description="The timestamp of when the summary was created (ISO format)"
+    )
+    token_count: int = Field(
+        ..., description="The number of tokens in the summary text"
+    )
+
+
+class SessionSummaries(BaseModel):
+    """Contains both short and long summaries for a session."""
+
+    id: str = Field(..., description="The session ID")
+    short_summary: Summary | None = Field(
+        None, description="The short summary if available"
+    )
+    long_summary: Summary | None = Field(
+        None, description="The long summary if available"
+    )
+
+
 class SessionContext(BaseModel):
    """
    Represents the context of a session containing a curated list of messages.
@ -27,8 +55,8 @@ class SessionContext(BaseModel):
    messages: list[Message] = Field(
        ..., description="List of Message objects to include in the context"
    )
-    summary: str = Field(
-        ..., description="Summary of the session history prior to the message cutoff"
+    summary: Summary | None = Field(
+        None, description="Summary of the session history prior to the message cutoff"
    )

    @validate_call
@ -40,8 +68,8 @@ class SessionContext(BaseModel):
        messages: list[Message] = Field(
            ..., description="List of Message objects to include in the context"
        ),
-        summary: str = Field(
-            ...,
+        summary: Summary | None = Field(
+            None,
            description="Summary of the session history prior to the message cutoff",
        ),
    ) -> None:
@ -50,6 +78,7 @@ class SessionContext(BaseModel):

        Args:
            messages: List of Message objects to include in the context
+            summary: Optional Summary object containing summary information
        """
        super().__init__(
            session_id=session_id,
@ -80,10 +109,6 @@ class SessionContext(BaseModel):
        """

        assistant_id = assistant if isinstance(assistant, str) else assistant.id
-        summary_message = {
-            "role": "system",
-            "content": f"<summary>{self.summary}</summary>",
-        }
        messages = [
            {
                "role": "assistant" if message.peer_id == assistant_id else "user",
@ -92,7 +117,14 @@ class SessionContext(BaseModel):
            }
            for message in self.messages
        ]
-        return [summary_message, *messages] if self.summary else messages
+
+        if self.summary:
+            summary_message = {
+                "role": "system",
+                "content": f"<summary>{self.summary.content}</summary>",
+            }
+            return [summary_message, *messages]
+        return messages

    def to_anthropic(
        self,
@ -120,10 +152,6 @@ class SessionContext(BaseModel):
        """

        assistant_id = assistant if isinstance(assistant, str) else assistant.id
-        summary_message = {
-            "role": "user",
-            "content": f"<summary>{self.summary}</summary>",
-        }
        messages = [
            {
                "role": "assistant",
@ -136,7 +164,14 @@ class SessionContext(BaseModel):
            }
            for message in self.messages
        ]
-        return [summary_message, *messages] if self.summary else messages
+
+        if self.summary:
+            summary_message = {
+                "role": "user",
+                "content": f"<summary>{self.summary.content}</summary>",
+            }
+            return [summary_message, *messages]
+        return messages

    def __len__(self) -> int:
        """
@ -154,4 +189,4 @@ class SessionContext(BaseModel):
        Returns:
            A string representation suitable for debugging
        """
-        return f"SessionContext(messages={len(self.messages)}, summary={self.summary})"
+        return f"SessionContext(messages={len(self.messages)}, summary={'present' if self.summary else 'None'})"
--- a/sdks/python/uv.lock
+++ b/sdks/python/uv.lock
@ -1,5 +1,5 @@
 version = 1
-revision = 2
+revision = 3
 requires-python = ">=3.8"
 resolution-markers = [
    "python_full_version >= '3.9'",
@ -38,7 +38,7 @@ wheels = [

 [[package]]
 name = "anyio"
-version = "4.9.0"
+version = "4.10.0"
 source = { registry = "https://pypi.org/simple" }
 resolution-markers = [
    "python_full_version >= '3.9'",
@ -47,20 +47,20 @@ dependencies = [
    { name = "exceptiongroup", marker = "python_full_version >= '3.9' and python_full_version < '3.11'" },
    { name = "idna", marker = "python_full_version >= '3.9'" },
    { name = "sniffio", marker = "python_full_version >= '3.9'" },
-    { name = "typing-extensions", version = "4.14.0", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version >= '3.9' and python_full_version < '3.13'" },
+    { name = "typing-extensions", version = "4.14.1", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version >= '3.9' and python_full_version < '3.13'" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/95/7d/4c1bd541d4dffa1b52bd83fb8527089e097a106fc90b467a7313b105f840/anyio-4.9.0.tar.gz", hash = "sha256:673c0c244e15788651a4ff38710fea9675823028a6f08a5eda409e0c9840a028", size = 190949, upload-time = "2025-03-17T00:02:54.77Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/f1/b4/636b3b65173d3ce9a38ef5f0522789614e590dab6a8d505340a4efe4c567/anyio-4.10.0.tar.gz", hash = "sha256:3f3fae35c96039744587aa5b8371e7e8e603c0702999535961dd336026973ba6", size = 213252, upload-time = "2025-08-04T08:54:26.451Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/a1/ee/48ca1a7c89ffec8b6a0c5d02b89c305671d5ffd8d3c94acf8b8c408575bb/anyio-4.9.0-py3-none-any.whl", hash = "sha256:9f76d541cad6e36af7beb62e978876f3b41e3e04f2c1fbf0884604c0a9c4d93c", size = 100916, upload-time = "2025-03-17T00:02:52.713Z" },
+    { url = "https://files.pythonhosted.org/packages/6f/12/e5e0282d673bb9746bacfb6e2dba8719989d3660cdb2ea79aee9a9651afb/anyio-4.10.0-py3-none-any.whl", hash = "sha256:60e474ac86736bbfd6f210f7a61218939c318f43f9972497381f1c5e930ed3d1", size = 107213, upload-time = "2025-08-04T08:54:24.882Z" },
 ]

 [[package]]
 name = "certifi"
-version = "2025.4.26"
+version = "2025.8.3"
 source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/e8/9e/c05b3920a3b7d20d3d3310465f50348e5b3694f4f88c6daf736eef3024c4/certifi-2025.4.26.tar.gz", hash = "sha256:0a816057ea3cdefcef70270d2c515e4506bbc954f417fa5ade2021213bb8f0c6", size = 160705, upload-time = "2025-04-26T02:12:29.51Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/dc/67/960ebe6bf230a96cda2e0abcf73af550ec4f090005363542f0765df162e0/certifi-2025.8.3.tar.gz", hash = "sha256:e564105f78ded564e3ae7c923924435e1daa7463faeab5bb932bc53ffae63407", size = 162386, upload-time = "2025-08-03T03:07:47.08Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/4a/7e/3db2bd1b1f9e95f7cddca6d6e75e2f2bd9f51b1246e546d88addca0106bd/certifi-2025.4.26-py3-none-any.whl", hash = "sha256:30350364dfe371162649852c63336a15c70c6510c2ad5015b21c2345311805f3", size = 159618, upload-time = "2025-04-26T02:12:27.662Z" },
+    { url = "https://files.pythonhosted.org/packages/e5/48/1549795ba7742c948d2ad169c1c8cdbae65bc450d6cd753d124b17c8cd32/certifi-2025.8.3-py3-none-any.whl", hash = "sha256:f6c12493cfb1b06ba2ff328595af9350c65d6644968e5d3a2ffd78699af217a5", size = 161216, upload-time = "2025-08-03T03:07:45.777Z" },
 ]

 [[package]]
@ -78,7 +78,7 @@ version = "1.3.0"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
    { name = "typing-extensions", version = "4.13.2", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version < '3.9'" },
-    { name = "typing-extensions", version = "4.14.0", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version >= '3.9' and python_full_version < '3.13'" },
+    { name = "typing-extensions", version = "4.14.1", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version >= '3.9' and python_full_version < '3.13'" },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/0b/9f/a65090624ecf468cdca03533906e7c69ed7588582240cfe7cc9e770b50eb/exceptiongroup-1.3.0.tar.gz", hash = "sha256:b241f5885f560bc56a59ee63ca4c6a8bfa46ae4ad651af316d4e81817bb9fd88", size = 29749, upload-time = "2025-05-10T17:42:51.123Z" }
 wheels = [
@ -96,13 +96,13 @@ wheels = [

 [[package]]
 name = "honcho-ai"
-version = "1.3.0"
+version = "1.4.0"
 source = { editable = "." }
 dependencies = [
    { name = "honcho-core" },
    { name = "httpx" },
    { name = "pydantic", version = "2.10.6", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version < '3.9'" },
-    { name = "pydantic", version = "2.11.5", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version >= '3.9'" },
+    { name = "pydantic", version = "2.11.7", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version >= '3.9'" },
 ]

 [package.dev-dependencies]
@ -112,7 +112,7 @@ dev = [

 [package.metadata]
 requires-dist = [
-    { name = "honcho-core", specifier = "==1.3.0" },
+    { name = "honcho-core", specifier = ">=1.4.0" },
    { name = "httpx", specifier = ">=0.28.0,<1" },
    { name = "pydantic", specifier = ">=2.0.0,<3" },
 ]
@ -122,22 +122,22 @@ dev = [{ name = "ruff", specifier = ">=0.11.13" }]

 [[package]]
 name = "honcho-core"
-version = "1.3.0"
+version = "1.4.0"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
    { name = "anyio", version = "4.5.2", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version < '3.9'" },
-    { name = "anyio", version = "4.9.0", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version >= '3.9'" },
+    { name = "anyio", version = "4.10.0", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version >= '3.9'" },
    { name = "distro" },
    { name = "httpx" },
    { name = "pydantic", version = "2.10.6", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version < '3.9'" },
-    { name = "pydantic", version = "2.11.5", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version >= '3.9'" },
+    { name = "pydantic", version = "2.11.7", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version >= '3.9'" },
    { name = "sniffio" },
    { name = "typing-extensions", version = "4.13.2", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version < '3.9'" },
-    { name = "typing-extensions", version = "4.14.0", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version >= '3.9'" },
+    { name = "typing-extensions", version = "4.14.1", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version >= '3.9'" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/ee/49/1810de2351be1fdff330ffadcc5eef709889b2f698b0340966cae2c1eef9/honcho_core-1.3.0.tar.gz", hash = "sha256:276a73e8d523f7d22f06746922fda97e4a11fbbef4a51a0b43573bc817089cec", size = 123333, upload-time = "2025-08-06T16:42:10.941Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/71/c2/4d3737d5c0a75e2f59f324bed7428a9593c8edfcb7500cf402c46ad7378a/honcho_core-1.4.0.tar.gz", hash = "sha256:b30de9247763c01c3c37ed22b5d04d3c611440dd1983168f3d7d93f2cc0ecf7d", size = 126164, upload-time = "2025-08-12T19:06:54.828Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/6e/3f/3beb750ed65bb1b604c585ae1c51a54f8b34ea3002f4525f93fe86549531/honcho_core-1.3.0-py3-none-any.whl", hash = "sha256:c7c0bf77b61162e6c65a580327fc054785aef794923abc35acd3dbd8287245db", size = 112895, upload-time = "2025-08-06T16:42:08.967Z" },
+    { url = "https://files.pythonhosted.org/packages/c1/ac/6eb2e38376736bb1dfd26bbdfd96490bfbb6f0ddcb00b39913e93799e7d8/honcho_core-1.4.0-py3-none-any.whl", hash = "sha256:a84397fd9daf546a04f5458d7233ebd5eeafcb97af75ec60a9327db89abdaf03", size = 117602, upload-time = "2025-08-12T19:06:53.667Z" },
 ]

 [[package]]
@ -159,7 +159,7 @@ version = "0.28.1"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
    { name = "anyio", version = "4.5.2", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version < '3.9'" },
-    { name = "anyio", version = "4.9.0", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version >= '3.9'" },
+    { name = "anyio", version = "4.10.0", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version >= '3.9'" },
    { name = "certifi" },
    { name = "httpcore" },
    { name = "idna" },
@ -197,7 +197,7 @@ wheels = [

 [[package]]
 name = "pydantic"
-version = "2.11.5"
+version = "2.11.7"
 source = { registry = "https://pypi.org/simple" }
 resolution-markers = [
    "python_full_version >= '3.9'",
@ -205,12 +205,12 @@ resolution-markers = [
 dependencies = [
    { name = "annotated-types", marker = "python_full_version >= '3.9'" },
    { name = "pydantic-core", version = "2.33.2", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version >= '3.9'" },
-    { name = "typing-extensions", version = "4.14.0", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version >= '3.9'" },
+    { name = "typing-extensions", version = "4.14.1", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version >= '3.9'" },
    { name = "typing-inspection", marker = "python_full_version >= '3.9'" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/f0/86/8ce9040065e8f924d642c58e4a344e33163a07f6b57f836d0d734e0ad3fb/pydantic-2.11.5.tar.gz", hash = "sha256:7f853db3d0ce78ce8bbb148c401c2cdd6431b3473c0cdff2755c7690952a7b7a", size = 787102, upload-time = "2025-05-22T21:18:08.761Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/00/dd/4325abf92c39ba8623b5af936ddb36ffcfe0beae70405d456ab1fb2f5b8c/pydantic-2.11.7.tar.gz", hash = "sha256:d989c3c6cb79469287b1569f7447a17848c998458d49ebe294e975b9baf0f0db", size = 788350, upload-time = "2025-06-14T08:33:17.137Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/b5/69/831ed22b38ff9b4b64b66569f0e5b7b97cf3638346eb95a2147fdb49ad5f/pydantic-2.11.5-py3-none-any.whl", hash = "sha256:f9c26ba06f9747749ca1e5c94d6a85cb84254577553c8785576fd38fa64dc0f7", size = 444229, upload-time = "2025-05-22T21:18:06.329Z" },
+    { url = "https://files.pythonhosted.org/packages/6a/c0/ec2b1c8712ca690e5d61979dee872603e92b8a32f94cc1b72d53beab008a/pydantic-2.11.7-py3-none-any.whl", hash = "sha256:dde5df002701f6de26248661f6835bbe296a47bf73990135c7d07ce741b9623b", size = 444782, upload-time = "2025-06-14T08:33:14.905Z" },
 ]

 [[package]]
@ -334,7 +334,7 @@ resolution-markers = [
    "python_full_version >= '3.9'",
 ]
 dependencies = [
-    { name = "typing-extensions", version = "4.14.0", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version >= '3.9'" },
+    { name = "typing-extensions", version = "4.14.1", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version >= '3.9'" },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/ad/88/5f2260bdfae97aabf98f1778d43f69574390ad787afb646292a638c923d4/pydantic_core-2.33.2.tar.gz", hash = "sha256:7cb8bc3605c29176e1b105350d2e6474142d7c1bd1d9327c4a9bdb46bf827acc", size = 435195, upload-time = "2025-04-23T18:33:52.104Z" }
 wheels = [
@ -440,27 +440,27 @@ wheels = [

 [[package]]
 name = "ruff"
-version = "0.11.13"
+version = "0.12.8"
 source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/ed/da/9c6f995903b4d9474b39da91d2d626659af3ff1eeb43e9ae7c119349dba6/ruff-0.11.13.tar.gz", hash = "sha256:26fa247dc68d1d4e72c179e08889a25ac0c7ba4d78aecfc835d49cbfd60bf514", size = 4282054, upload-time = "2025-06-05T21:00:15.721Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/4b/da/5bd7565be729e86e1442dad2c9a364ceeff82227c2dece7c29697a9795eb/ruff-0.12.8.tar.gz", hash = "sha256:4cb3a45525176e1009b2b64126acf5f9444ea59066262791febf55e40493a033", size = 5242373, upload-time = "2025-08-07T19:05:47.268Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/7d/ce/a11d381192966e0b4290842cc8d4fac7dc9214ddf627c11c1afff87da29b/ruff-0.11.13-py3-none-linux_armv6l.whl", hash = "sha256:4bdfbf1240533f40042ec00c9e09a3aade6f8c10b6414cf11b519488d2635d46", size = 10292516, upload-time = "2025-06-05T20:59:32.944Z" },
-    { url = "https://files.pythonhosted.org/packages/78/db/87c3b59b0d4e753e40b6a3b4a2642dfd1dcaefbff121ddc64d6c8b47ba00/ruff-0.11.13-py3-none-macosx_10_12_x86_64.whl", hash = "sha256:aef9c9ed1b5ca28bb15c7eac83b8670cf3b20b478195bd49c8d756ba0a36cf48", size = 11106083, upload-time = "2025-06-05T20:59:37.03Z" },
-    { url = "https://files.pythonhosted.org/packages/77/79/d8cec175856ff810a19825d09ce700265f905c643c69f45d2b737e4a470a/ruff-0.11.13-py3-none-macosx_11_0_arm64.whl", hash = "sha256:53b15a9dfdce029c842e9a5aebc3855e9ab7771395979ff85b7c1dedb53ddc2b", size = 10436024, upload-time = "2025-06-05T20:59:39.741Z" },
-    { url = "https://files.pythonhosted.org/packages/8b/5b/f6d94f2980fa1ee854b41568368a2e1252681b9238ab2895e133d303538f/ruff-0.11.13-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ab153241400789138d13f362c43f7edecc0edfffce2afa6a68434000ecd8f69a", size = 10646324, upload-time = "2025-06-05T20:59:42.185Z" },
-    { url = "https://files.pythonhosted.org/packages/6c/9c/b4c2acf24ea4426016d511dfdc787f4ce1ceb835f3c5fbdbcb32b1c63bda/ruff-0.11.13-py3-none-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:6c51f93029d54a910d3d24f7dd0bb909e31b6cd989a5e4ac513f4eb41629f0dc", size = 10174416, upload-time = "2025-06-05T20:59:44.319Z" },
-    { url = "https://files.pythonhosted.org/packages/f3/10/e2e62f77c65ede8cd032c2ca39c41f48feabedb6e282bfd6073d81bb671d/ruff-0.11.13-py3-none-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:1808b3ed53e1a777c2ef733aca9051dc9bf7c99b26ece15cb59a0320fbdbd629", size = 11724197, upload-time = "2025-06-05T20:59:46.935Z" },
-    { url = "https://files.pythonhosted.org/packages/bb/f0/466fe8469b85c561e081d798c45f8a1d21e0b4a5ef795a1d7f1a9a9ec182/ruff-0.11.13-py3-none-manylinux_2_17_ppc64.manylinux2014_ppc64.whl", hash = "sha256:d28ce58b5ecf0f43c1b71edffabe6ed7f245d5336b17805803312ec9bc665933", size = 12511615, upload-time = "2025-06-05T20:59:49.534Z" },
-    { url = "https://files.pythonhosted.org/packages/17/0e/cefe778b46dbd0cbcb03a839946c8f80a06f7968eb298aa4d1a4293f3448/ruff-0.11.13-py3-none-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:55e4bc3a77842da33c16d55b32c6cac1ec5fb0fbec9c8c513bdce76c4f922165", size = 12117080, upload-time = "2025-06-05T20:59:51.654Z" },
-    { url = "https://files.pythonhosted.org/packages/5d/2c/caaeda564cbe103bed145ea557cb86795b18651b0f6b3ff6a10e84e5a33f/ruff-0.11.13-py3-none-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:633bf2c6f35678c56ec73189ba6fa19ff1c5e4807a78bf60ef487b9dd272cc71", size = 11326315, upload-time = "2025-06-05T20:59:54.469Z" },
-    { url = "https://files.pythonhosted.org/packages/75/f0/782e7d681d660eda8c536962920c41309e6dd4ebcea9a2714ed5127d44bd/ruff-0.11.13-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:4ffbc82d70424b275b089166310448051afdc6e914fdab90e08df66c43bb5ca9", size = 11555640, upload-time = "2025-06-05T20:59:56.986Z" },
-    { url = "https://files.pythonhosted.org/packages/5d/d4/3d580c616316c7f07fb3c99dbecfe01fbaea7b6fd9a82b801e72e5de742a/ruff-0.11.13-py3-none-musllinux_1_2_aarch64.whl", hash = "sha256:4a9ddd3ec62a9a89578c85842b836e4ac832d4a2e0bfaad3b02243f930ceafcc", size = 10507364, upload-time = "2025-06-05T20:59:59.154Z" },
-    { url = "https://files.pythonhosted.org/packages/5a/dc/195e6f17d7b3ea6b12dc4f3e9de575db7983db187c378d44606e5d503319/ruff-0.11.13-py3-none-musllinux_1_2_armv7l.whl", hash = "sha256:d237a496e0778d719efb05058c64d28b757c77824e04ffe8796c7436e26712b7", size = 10141462, upload-time = "2025-06-05T21:00:01.481Z" },
-    { url = "https://files.pythonhosted.org/packages/f4/8e/39a094af6967faa57ecdeacb91bedfb232474ff8c3d20f16a5514e6b3534/ruff-0.11.13-py3-none-musllinux_1_2_i686.whl", hash = "sha256:26816a218ca6ef02142343fd24c70f7cd8c5aa6c203bca284407adf675984432", size = 11121028, upload-time = "2025-06-05T21:00:04.06Z" },
-    { url = "https://files.pythonhosted.org/packages/5a/c0/b0b508193b0e8a1654ec683ebab18d309861f8bd64e3a2f9648b80d392cb/ruff-0.11.13-py3-none-musllinux_1_2_x86_64.whl", hash = "sha256:51c3f95abd9331dc5b87c47ac7f376db5616041173826dfd556cfe3d4977f492", size = 11602992, upload-time = "2025-06-05T21:00:06.249Z" },
-    { url = "https://files.pythonhosted.org/packages/7c/91/263e33ab93ab09ca06ce4f8f8547a858cc198072f873ebc9be7466790bae/ruff-0.11.13-py3-none-win32.whl", hash = "sha256:96c27935418e4e8e77a26bb05962817f28b8ef3843a6c6cc49d8783b5507f250", size = 10474944, upload-time = "2025-06-05T21:00:08.459Z" },
-    { url = "https://files.pythonhosted.org/packages/46/f4/7c27734ac2073aae8efb0119cae6931b6fb48017adf048fdf85c19337afc/ruff-0.11.13-py3-none-win_amd64.whl", hash = "sha256:29c3189895a8a6a657b7af4e97d330c8a3afd2c9c8f46c81e2fc5a31866517e3", size = 11548669, upload-time = "2025-06-05T21:00:11.147Z" },
-    { url = "https://files.pythonhosted.org/packages/ec/bf/b273dd11673fed8a6bd46032c0ea2a04b2ac9bfa9c628756a5856ba113b0/ruff-0.11.13-py3-none-win_arm64.whl", hash = "sha256:b4385285e9179d608ff1d2fb9922062663c658605819a6876d8beef0c30b7f3b", size = 10683928, upload-time = "2025-06-05T21:00:13.758Z" },
+    { url = "https://files.pythonhosted.org/packages/c9/1e/c843bfa8ad1114fab3eb2b78235dda76acd66384c663a4e0415ecc13aa1e/ruff-0.12.8-py3-none-linux_armv6l.whl", hash = "sha256:63cb5a5e933fc913e5823a0dfdc3c99add73f52d139d6cd5cc8639d0e0465513", size = 11675315, upload-time = "2025-08-07T19:05:06.15Z" },
+    { url = "https://files.pythonhosted.org/packages/24/ee/af6e5c2a8ca3a81676d5480a1025494fd104b8896266502bb4de2a0e8388/ruff-0.12.8-py3-none-macosx_10_12_x86_64.whl", hash = "sha256:9a9bbe28f9f551accf84a24c366c1aa8774d6748438b47174f8e8565ab9dedbc", size = 12456653, upload-time = "2025-08-07T19:05:09.759Z" },
+    { url = "https://files.pythonhosted.org/packages/99/9d/e91f84dfe3866fa648c10512904991ecc326fd0b66578b324ee6ecb8f725/ruff-0.12.8-py3-none-macosx_11_0_arm64.whl", hash = "sha256:2fae54e752a3150f7ee0e09bce2e133caf10ce9d971510a9b925392dc98d2fec", size = 11659690, upload-time = "2025-08-07T19:05:12.551Z" },
+    { url = "https://files.pythonhosted.org/packages/fe/ac/a363d25ec53040408ebdd4efcee929d48547665858ede0505d1d8041b2e5/ruff-0.12.8-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c0acbcf01206df963d9331b5838fb31f3b44fa979ee7fa368b9b9057d89f4a53", size = 11896923, upload-time = "2025-08-07T19:05:14.821Z" },
+    { url = "https://files.pythonhosted.org/packages/58/9f/ea356cd87c395f6ade9bb81365bd909ff60860975ca1bc39f0e59de3da37/ruff-0.12.8-py3-none-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:ae3e7504666ad4c62f9ac8eedb52a93f9ebdeb34742b8b71cd3cccd24912719f", size = 11477612, upload-time = "2025-08-07T19:05:16.712Z" },
+    { url = "https://files.pythonhosted.org/packages/1a/46/92e8fa3c9dcfd49175225c09053916cb97bb7204f9f899c2f2baca69e450/ruff-0.12.8-py3-none-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:cb82efb5d35d07497813a1c5647867390a7d83304562607f3579602fa3d7d46f", size = 13182745, upload-time = "2025-08-07T19:05:18.709Z" },
+    { url = "https://files.pythonhosted.org/packages/5e/c4/f2176a310f26e6160deaf661ef60db6c3bb62b7a35e57ae28f27a09a7d63/ruff-0.12.8-py3-none-manylinux_2_17_ppc64.manylinux2014_ppc64.whl", hash = "sha256:dbea798fc0065ad0b84a2947b0aff4233f0cb30f226f00a2c5850ca4393de609", size = 14206885, upload-time = "2025-08-07T19:05:21.025Z" },
+    { url = "https://files.pythonhosted.org/packages/87/9d/98e162f3eeeb6689acbedbae5050b4b3220754554526c50c292b611d3a63/ruff-0.12.8-py3-none-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:49ebcaccc2bdad86fd51b7864e3d808aad404aab8df33d469b6e65584656263a", size = 13639381, upload-time = "2025-08-07T19:05:23.423Z" },
+    { url = "https://files.pythonhosted.org/packages/81/4e/1b7478b072fcde5161b48f64774d6edd59d6d198e4ba8918d9f4702b8043/ruff-0.12.8-py3-none-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:0ac9c570634b98c71c88cb17badd90f13fc076a472ba6ef1d113d8ed3df109fb", size = 12613271, upload-time = "2025-08-07T19:05:25.507Z" },
+    { url = "https://files.pythonhosted.org/packages/e8/67/0c3c9179a3ad19791ef1b8f7138aa27d4578c78700551c60d9260b2c660d/ruff-0.12.8-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:560e0cd641e45591a3e42cb50ef61ce07162b9c233786663fdce2d8557d99818", size = 12847783, upload-time = "2025-08-07T19:05:28.14Z" },
+    { url = "https://files.pythonhosted.org/packages/4e/2a/0b6ac3dd045acf8aa229b12c9c17bb35508191b71a14904baf99573a21bd/ruff-0.12.8-py3-none-musllinux_1_2_aarch64.whl", hash = "sha256:71c83121512e7743fba5a8848c261dcc454cafb3ef2934a43f1b7a4eb5a447ea", size = 11702672, upload-time = "2025-08-07T19:05:30.413Z" },
+    { url = "https://files.pythonhosted.org/packages/9d/ee/f9fdc9f341b0430110de8b39a6ee5fa68c5706dc7c0aa940817947d6937e/ruff-0.12.8-py3-none-musllinux_1_2_armv7l.whl", hash = "sha256:de4429ef2ba091ecddedd300f4c3f24bca875d3d8b23340728c3cb0da81072c3", size = 11440626, upload-time = "2025-08-07T19:05:32.492Z" },
+    { url = "https://files.pythonhosted.org/packages/89/fb/b3aa2d482d05f44e4d197d1de5e3863feb13067b22c571b9561085c999dc/ruff-0.12.8-py3-none-musllinux_1_2_i686.whl", hash = "sha256:a2cab5f60d5b65b50fba39a8950c8746df1627d54ba1197f970763917184b161", size = 12462162, upload-time = "2025-08-07T19:05:34.449Z" },
+    { url = "https://files.pythonhosted.org/packages/18/9f/5c5d93e1d00d854d5013c96e1a92c33b703a0332707a7cdbd0a4880a84fb/ruff-0.12.8-py3-none-musllinux_1_2_x86_64.whl", hash = "sha256:45c32487e14f60b88aad6be9fd5da5093dbefb0e3e1224131cb1d441d7cb7d46", size = 12913212, upload-time = "2025-08-07T19:05:36.541Z" },
+    { url = "https://files.pythonhosted.org/packages/71/13/ab9120add1c0e4604c71bfc2e4ef7d63bebece0cfe617013da289539cef8/ruff-0.12.8-py3-none-win32.whl", hash = "sha256:daf3475060a617fd5bc80638aeaf2f5937f10af3ec44464e280a9d2218e720d3", size = 11694382, upload-time = "2025-08-07T19:05:38.468Z" },
+    { url = "https://files.pythonhosted.org/packages/f6/dc/a2873b7c5001c62f46266685863bee2888caf469d1edac84bf3242074be2/ruff-0.12.8-py3-none-win_amd64.whl", hash = "sha256:7209531f1a1fcfbe8e46bcd7ab30e2f43604d8ba1c49029bb420b103d0b5f76e", size = 12740482, upload-time = "2025-08-07T19:05:40.391Z" },
+    { url = "https://files.pythonhosted.org/packages/cb/5c/799a1efb8b5abab56e8a9f2a0b72d12bd64bb55815e9476c7d0a2887d2f7/ruff-0.12.8-py3-none-win_arm64.whl", hash = "sha256:c90e1a334683ce41b0e7a04f41790c429bf5073b62c1ae701c9dc5b3d14f0749", size = 11884718, upload-time = "2025-08-07T19:05:42.866Z" },
 ]

 [[package]]
@ -486,14 +486,14 @@ wheels = [

 [[package]]
 name = "typing-extensions"
-version = "4.14.0"
+version = "4.14.1"
 source = { registry = "https://pypi.org/simple" }
 resolution-markers = [
    "python_full_version >= '3.9'",
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/d1/bc/51647cd02527e87d05cb083ccc402f93e441606ff1f01739a62c8ad09ba5/typing_extensions-4.14.0.tar.gz", hash = "sha256:8676b788e32f02ab42d9e7c61324048ae4c6d844a399eebace3d4979d75ceef4", size = 107423, upload-time = "2025-06-02T14:52:11.399Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/98/5a/da40306b885cc8c09109dc2e1abd358d5684b1425678151cdaed4731c822/typing_extensions-4.14.1.tar.gz", hash = "sha256:38b39f4aeeab64884ce9f74c94263ef78f3c22467c8724005483154c26648d36", size = 107673, upload-time = "2025-07-04T13:28:34.16Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/69/e0/552843e0d356fbb5256d21449fa957fa4eff3bbc135a74a691ee70c7c5da/typing_extensions-4.14.0-py3-none-any.whl", hash = "sha256:a1514509136dd0b477638fc68d6a91497af5076466ad0fa6c338e44e359944af", size = 43839, upload-time = "2025-06-02T14:52:10.026Z" },
+    { url = "https://files.pythonhosted.org/packages/b5/00/d631e67a838026495268c2f6884f3711a15a9a2a96cd244fdaea53b823fb/typing_extensions-4.14.1-py3-none-any.whl", hash = "sha256:d1e1e3b58374dc93031d6eda2420a48ea44a36c2b4766a4fdeb3710755731d76", size = 43906, upload-time = "2025-07-04T13:28:32.743Z" },
 ]

 [[package]]
@ -501,7 +501,7 @@ name = "typing-inspection"
 version = "0.4.1"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "typing-extensions", version = "4.14.0", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version >= '3.9'" },
+    { name = "typing-extensions", version = "4.14.1", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version >= '3.9'" },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/f8/b1/0c11f5058406b3af7609f121aaa6b609744687f1d158b3c3a5bf4cc94238/typing_inspection-0.4.1.tar.gz", hash = "sha256:6ae134cc0203c33377d43188d4064e9b357dba58cff3185f22924610e70a9d28", size = 75726, upload-time = "2025-05-21T18:55:23.885Z" }
 wheels = [
--- a/sdks/typescript/CHANGELOG.md
+++ b/sdks/typescript/CHANGELOG.md
@ -5,6 +5,17 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](http://keepachangelog.com/)
 and this project adheres to [Semantic Versioning](http://semver.org/).

+## [1.4.0] - 2025-08-12
+
+### Added
+
+- getSummaries API returning structured summaries
+
+### Changed
+
+- Messages can take an optional `created_at` value, defaulting to the current
+  time (UTC ISO 8601)
+
 ## [1.3.0] - 2025-08-04

 ### Added
--- a/sdks/typescript/tests/integration.test.ts
+++ b/sdks/typescript/tests/integration.test.ts
@ -1,18 +1,18 @@
-import { Honcho } from '../src/client';
-import { Peer } from '../src/peer';
-import { Session } from '../src/session';
-import { SessionContext } from '../src/session_context';
-import { Page } from '../src/pagination';
+import { Honcho } from '../src/client'
+import { Peer } from '../src/peer'
+import { Session } from '../src/session'
+import { SessionContext } from '../src/session_context'
+import { Page } from '../src/pagination'

 // Mock the @honcho-ai/core module
-let mockWorkspacesApi: any;
+let mockWorkspacesApi: any

 jest.mock('@honcho-ai/core', () => {
-  return jest.fn().mockImplementation(() => mockWorkspacesApi);
-});
+  return jest.fn().mockImplementation(() => mockWorkspacesApi)
+})

 describe('Honcho SDK Integration Tests', () => {
-  let honcho: Honcho;
+  let honcho: Honcho

  beforeEach(() => {
    mockWorkspacesApi = {
@ -29,7 +29,12 @@ describe('Honcho SDK Integration Tests', () => {
        },
        sessions: {
          list: jest.fn(),
-          peers: { add: jest.fn(), set: jest.fn(), remove: jest.fn(), list: jest.fn() },
+          peers: {
+            add: jest.fn(),
+            set: jest.fn(),
+            remove: jest.fn(),
+            list: jest.fn(),
+          },
          messages: { create: jest.fn(), list: jest.fn() },
          getOrCreate: jest.fn(),
          update: jest.fn(),
@ -41,112 +46,135 @@ describe('Honcho SDK Integration Tests', () => {
        list: jest.fn(),
        search: jest.fn(),
      },
-    };
+    }

-    jest.clearAllMocks();
+    jest.clearAllMocks()

    honcho = new Honcho({
      workspaceId: 'integration-test-workspace',
      apiKey: 'test-api-key',
      environment: 'local',
-    });
-  });
+    })
+  })

  describe('Complete Workflow Integration', () => {
    it('should handle complete chat session workflow', async () => {
      // Setup mock responses
-      const mockPeerData = { id: 'assistant', metadata: { role: 'ai' } };
-      const mockSessionData = { id: 'chat-session', metadata: { topic: 'general' } };
+      const mockPeerData = { id: 'assistant', metadata: { role: 'ai' } }
+      const mockSessionData = {
+        id: 'chat-session',
+        metadata: { topic: 'general' },
+      }
      const mockMessages = [
        { id: 'msg1', content: 'Hello', peer_id: 'user' },
        { id: 'msg2', content: 'Hi there!', peer_id: 'assistant' },
-      ];
-      const mockContextData = { messages: mockMessages, summary: 'Friendly greeting' };
+      ]
+      const mockContextData = {
+        messages: mockMessages,
+        summary: {
+          content: 'Friendly greeting',
+          message_id: 5,
+          summary_type: 'short',
+          created_at: '2024-01-01T00:00:00Z',
+          token_count: 50,
+        },
+      }

-      mockWorkspacesApi.workspaces.peers.getOrCreate.mockResolvedValue(mockPeerData);
-      mockWorkspacesApi.workspaces.sessions.getOrCreate.mockResolvedValue(mockSessionData);
-      mockWorkspacesApi.workspaces.sessions.peers.add.mockResolvedValue({});
-      mockWorkspacesApi.workspaces.sessions.messages.create.mockResolvedValue({});
-      mockWorkspacesApi.workspaces.sessions.getContext.mockResolvedValue(mockContextData);
-      mockWorkspacesApi.workspaces.peers.chat.mockResolvedValue({ content: 'AI response' });
+      mockWorkspacesApi.workspaces.peers.getOrCreate.mockResolvedValue(
+        mockPeerData
+      )
+      mockWorkspacesApi.workspaces.sessions.getOrCreate.mockResolvedValue(
+        mockSessionData
+      )
+      mockWorkspacesApi.workspaces.sessions.peers.add.mockResolvedValue({})
+      mockWorkspacesApi.workspaces.sessions.messages.create.mockResolvedValue(
+        {}
+      )
+      mockWorkspacesApi.workspaces.sessions.getContext.mockResolvedValue(
+        mockContextData
+      )
+      mockWorkspacesApi.workspaces.peers.chat.mockResolvedValue({
+        content: 'AI response',
+      })

      // Step 1: Create peers
-      const user = await honcho.peer('user');
-      const assistant = await honcho.peer('assistant');
+      const user = await honcho.peer('user')
+      const assistant = await honcho.peer('assistant')

-      expect(user).toBeInstanceOf(Peer);
-      expect(assistant).toBeInstanceOf(Peer);
-      expect(user.id).toBe('user');
-      expect(assistant.id).toBe('assistant');
+      expect(user).toBeInstanceOf(Peer)
+      expect(assistant).toBeInstanceOf(Peer)
+      expect(user.id).toBe('user')
+      expect(assistant.id).toBe('assistant')

      // Step 2: Create session
-      const session = await honcho.session('chat-session');
-      expect(session).toBeInstanceOf(Session);
-      expect(session.id).toBe('chat-session');
+      const session = await honcho.session('chat-session')
+      expect(session).toBeInstanceOf(Session)
+      expect(session.id).toBe('chat-session')

      // Step 3: Add peers to session
-      await session.addPeers([user, assistant]);
-      expect(mockWorkspacesApi.workspaces.sessions.peers.add).toHaveBeenCalledWith(
-        'integration-test-workspace',
-        'chat-session',
-        {
-          'user': {},
-          'assistant': {}
-        }
-      );
+      await session.addPeers([user, assistant])
+      expect(
+        mockWorkspacesApi.workspaces.sessions.peers.add
+      ).toHaveBeenCalledWith('integration-test-workspace', 'chat-session', {
+        user: {},
+        assistant: {},
+      })

      // Step 4: Add messages to session
-      const userMessage = user.message('Hello');
-      const assistantMessage = assistant.message('Hi there!');
+      const userMessage = user.message('Hello')
+      const assistantMessage = assistant.message('Hi there!')

-      await session.addMessages([userMessage, assistantMessage]);
-      expect(mockWorkspacesApi.workspaces.sessions.messages.create).toHaveBeenCalledWith(
-        'integration-test-workspace',
-        'chat-session',
-        {
-          messages: [
-            { peer_id: 'user', content: 'Hello', metadata: undefined },
-            { peer_id: 'assistant', content: 'Hi there!', metadata: undefined },
-          ]
-        }
-      );
+      await session.addMessages([userMessage, assistantMessage])
+      expect(
+        mockWorkspacesApi.workspaces.sessions.messages.create
+      ).toHaveBeenCalledWith('integration-test-workspace', 'chat-session', {
+        messages: [
+          { peer_id: 'user', content: 'Hello', metadata: undefined },
+          { peer_id: 'assistant', content: 'Hi there!', metadata: undefined },
+        ],
+      })

      // Step 5: Get session context
-      const context = await session.getContext();
-      expect(context).toBeInstanceOf(SessionContext);
-      expect(context.sessionId).toBe('chat-session');
-      expect(context.messages).toEqual(mockMessages);
-      expect(context.summary).toBe('Friendly greeting');
+      const context = await session.getContext()
+      expect(context).toBeInstanceOf(SessionContext)
+      expect(context.sessionId).toBe('chat-session')
+      expect(context.messages).toEqual(mockMessages)
+      expect(context.summary?.content).toBe('Friendly greeting')

      // Step 6: Convert context to different formats
-      const openAIFormat = context.toOpenAI('assistant');
-      const anthropicFormat = context.toAnthropic('assistant');
+      const openAIFormat = context.toOpenAI('assistant')
+      const anthropicFormat = context.toAnthropic('assistant')

      expect(openAIFormat).toEqual([
        { role: 'system', content: '<summary>Friendly greeting</summary>' },
        { role: 'user', content: 'Hello', name: 'user' },
        { role: 'assistant', content: 'Hi there!', name: 'assistant' },
-      ]);
+      ])

      expect(anthropicFormat).toEqual([
        { role: 'user', content: '<summary>Friendly greeting</summary>' },
        { role: 'user', content: 'user: Hello' },
        { role: 'assistant', content: 'Hi there!' },
-      ]);
+      ])

      // Step 7: Query assistant
-      const response = await assistant.chat('How are you?');
-      expect(response).toBe('AI response');
+      const response = await assistant.chat('How are you?')
+      expect(response).toBe('AI response')
      expect(mockWorkspacesApi.workspaces.peers.chat).toHaveBeenCalledWith(
        'integration-test-workspace',
        'assistant',
-        { query: 'How are you?', stream: undefined, target: undefined, session_id: undefined }
-      );
-    });
+        {
+          query: 'How are you?',
+          stream: undefined,
+          target: undefined,
+          session_id: undefined,
+        }
+      )
+    })

    it('should handle workspace and peer management workflow', async () => {
      // Setup mock responses
-      const mockWorkspaceMetadata = { name: 'Test Workspace', version: '1.0' };
+      const mockWorkspaceMetadata = { name: 'Test Workspace', version: '1.0' }
      const mockPeersList = {
        items: [
          { id: 'peer1', metadata: { role: 'user' } },
@ -155,105 +183,115 @@ describe('Honcho SDK Integration Tests', () => {
        total: 2,
        size: 2,
        hasNextPage: false,
-      };
+      }

      mockWorkspacesApi.workspaces.getOrCreate.mockResolvedValue({
        id: 'integration-test-workspace',
        metadata: mockWorkspaceMetadata,
-      });
-      mockWorkspacesApi.workspaces.update.mockResolvedValue({});
-      mockWorkspacesApi.workspaces.peers.list.mockResolvedValue(mockPeersList);
+      })
+      mockWorkspacesApi.workspaces.update.mockResolvedValue({})
+      mockWorkspacesApi.workspaces.peers.list.mockResolvedValue(mockPeersList)

      // Step 1: Get workspace metadata
-      const metadata = await honcho.getMetadata();
-      expect(metadata).toEqual(mockWorkspaceMetadata);
+      const metadata = await honcho.getMetadata()
+      expect(metadata).toEqual(mockWorkspaceMetadata)

      // Step 2: Update workspace metadata
-      const newMetadata = { ...mockWorkspaceMetadata, updated: true };
-      await honcho.setMetadata(newMetadata);
+      const newMetadata = { ...mockWorkspaceMetadata, updated: true }
+      await honcho.setMetadata(newMetadata)
      expect(mockWorkspacesApi.workspaces.update).toHaveBeenCalledWith(
        'integration-test-workspace',
        { metadata: newMetadata }
-      );
+      )

      // Step 3: Get all peers
-      const peersPage = await honcho.getPeers();
-      expect(peersPage).toBeInstanceOf(Page);
+      const peersPage = await honcho.getPeers()
+      expect(peersPage).toBeInstanceOf(Page)

      // Step 4: Iterate through peers
-      const peersList: Peer[] = [];
+      const peersList: Peer[] = []
      for await (const peer of peersPage) {
-        peersList.push(peer);
+        peersList.push(peer)
      }

-      expect(peersList).toHaveLength(2);
-      expect(peersList[0]).toBeInstanceOf(Peer);
-      expect(peersList[1]).toBeInstanceOf(Peer);
-      expect(peersList[0].id).toBe('peer1');
-      expect(peersList[1].id).toBe('peer2');
-    });
+      expect(peersList).toHaveLength(2)
+      expect(peersList[0]).toBeInstanceOf(Peer)
+      expect(peersList[1]).toBeInstanceOf(Peer)
+      expect(peersList[0].id).toBe('peer1')
+      expect(peersList[1].id).toBe('peer2')
+    })

    it('should handle search functionality across different scopes', async () => {
      // Setup mock responses
      const mockWorkspaceSearchResults = [
        { id: 'msg1', content: 'workspace message', peer_id: 'peer1' },
-      ];
+      ]

      const mockPeerSearchResults = [
        { id: 'msg2', content: 'peer message', peer_id: 'peer1' },
-      ];
+      ]

      const mockSessionSearchResults = [
        { id: 'msg3', content: 'session message', peer_id: 'peer1' },
-      ];
+      ]

-      mockWorkspacesApi.workspaces.search.mockResolvedValue(mockWorkspaceSearchResults);
-      mockWorkspacesApi.workspaces.peers.search.mockResolvedValue(mockPeerSearchResults);
-      mockWorkspacesApi.workspaces.sessions.search.mockResolvedValue(mockSessionSearchResults);
+      mockWorkspacesApi.workspaces.search.mockResolvedValue(
+        mockWorkspaceSearchResults
+      )
+      mockWorkspacesApi.workspaces.peers.search.mockResolvedValue(
+        mockPeerSearchResults
+      )
+      mockWorkspacesApi.workspaces.sessions.search.mockResolvedValue(
+        mockSessionSearchResults
+      )

      // Step 1: Search workspace
-      const workspaceResults = await honcho.search('test query');
-      expect(Array.isArray(workspaceResults)).toBe(true);
+      const workspaceResults = await honcho.search('test query')
+      expect(Array.isArray(workspaceResults)).toBe(true)
      expect(mockWorkspacesApi.workspaces.search).toHaveBeenCalledWith(
        'integration-test-workspace',
        { query: 'test query', limit: undefined }
-      );
+      )

      // Step 2: Search peer
-      const peer = await honcho.peer('test-peer');
-      const peerResults = await peer.search('peer query');
-      expect(Array.isArray(peerResults)).toBe(true);
+      const peer = await honcho.peer('test-peer')
+      const peerResults = await peer.search('peer query')
+      expect(Array.isArray(peerResults)).toBe(true)
      expect(mockWorkspacesApi.workspaces.peers.search).toHaveBeenCalledWith(
        'integration-test-workspace',
        'test-peer',
        { query: 'peer query', limit: undefined }
-      );
+      )

      // Step 3: Search session
-      const session = await honcho.session('test-session');
-      const sessionResults = await session.search('session query');
-      expect(Array.isArray(sessionResults)).toBe(true);
+      const session = await honcho.session('test-session')
+      const sessionResults = await session.search('session query')
+      expect(Array.isArray(sessionResults)).toBe(true)
      expect(mockWorkspacesApi.workspaces.sessions.search).toHaveBeenCalledWith(
        'integration-test-workspace',
        'test-session',
        { query: 'session query', limit: undefined }
-      );
-    });
+      )
+    })

    it('should handle error scenarios gracefully', async () => {
      // Setup error scenarios
-      mockWorkspacesApi.workspaces.peers.chat.mockRejectedValue(new Error('Chat API failed'));
-      mockWorkspacesApi.workspaces.sessions.getContext.mockRejectedValue(new Error('Context API failed'));
+      mockWorkspacesApi.workspaces.peers.chat.mockRejectedValue(
+        new Error('Chat API failed')
+      )
+      mockWorkspacesApi.workspaces.sessions.getContext.mockRejectedValue(
+        new Error('Context API failed')
+      )

-      const assistant = await honcho.peer('assistant');
-      const session = await honcho.session('error-session');
+      const assistant = await honcho.peer('assistant')
+      const session = await honcho.session('error-session')

      // Test error handling in chat
-      await expect(assistant.chat('Hello')).rejects.toThrow();
+      await expect(assistant.chat('Hello')).rejects.toThrow()

      // Test error handling in context
-      await expect(session.getContext()).rejects.toThrow();
-    });
+      await expect(session.getContext()).rejects.toThrow()
+    })

    it('should handle pagination correctly', async () => {
      // Setup paginated response
@ -266,7 +304,7 @@ describe('Honcho SDK Integration Tests', () => {
        size: 2,
        hasNextPage: true,
        nextPage: jest.fn(),
-      };
+      }

      const secondPageData = {
        items: [
@ -277,34 +315,34 @@ describe('Honcho SDK Integration Tests', () => {
        size: 2,
        hasNextPage: false,
        nextPage: jest.fn().mockResolvedValue(null),
-      };
+      }

-      firstPageData.nextPage.mockResolvedValue(secondPageData);
-      mockWorkspacesApi.workspaces.peers.list.mockResolvedValue(firstPageData);
+      firstPageData.nextPage.mockResolvedValue(secondPageData)
+      mockWorkspacesApi.workspaces.peers.list.mockResolvedValue(firstPageData)

      // Step 1: Get first page
-      const firstPage = await honcho.getPeers();
-      expect(firstPage.total).toBe(4);
-      expect(firstPage.size).toBe(2);
-      expect(firstPage.hasNextPage).toBe(true);
+      const firstPage = await honcho.getPeers()
+      expect(firstPage.total).toBe(4)
+      expect(firstPage.size).toBe(2)
+      expect(firstPage.hasNextPage).toBe(true)

      // Step 2: Get data from first page
-      const firstPageData_ = await firstPage.data();
-      expect(firstPageData_).toHaveLength(2);
+      const firstPageData_ = await firstPage.data()
+      expect(firstPageData_).toHaveLength(2)

      // Step 3: Get next page
-      const secondPage = await firstPage.nextPage();
-      expect(secondPage).not.toBeNull();
-      expect(secondPage!.hasNextPage).toBe(false);
+      const secondPage = await firstPage.nextPage()
+      expect(secondPage).not.toBeNull()
+      expect(secondPage!.hasNextPage).toBe(false)

      // Step 4: Get data from second page
-      const secondPageData_ = await secondPage!.data();
-      expect(secondPageData_).toHaveLength(2);
+      const secondPageData_ = await secondPage!.data()
+      expect(secondPageData_).toHaveLength(2)

      // Step 5: Verify no more pages
-      const thirdPage = await secondPage!.nextPage();
-      expect(thirdPage).toBeNull();
-    });
+      const thirdPage = await secondPage!.nextPage()
+      expect(thirdPage).toBeNull()
+    })

    it('should handle working representation queries', async () => {
      const mockWorkingRep = {
@ -312,94 +350,115 @@ describe('Honcho SDK Integration Tests', () => {
        knowledge: 'Alice likes coffee and works as a developer',
        relationships: ['bob', 'charlie'],
        context: 'session-specific context',
-      };
+      }

-      mockWorkspacesApi.workspaces.peers.workingRepresentation.mockResolvedValue(mockWorkingRep);
+      mockWorkspacesApi.workspaces.peers.workingRepresentation.mockResolvedValue(
+        mockWorkingRep
+      )

-      const session = await honcho.session('working-rep-session');
-      const alice = await honcho.peer('alice');
-      const bob = await honcho.peer('bob');
+      const session = await honcho.session('working-rep-session')
+      const alice = await honcho.peer('alice')
+      const bob = await honcho.peer('bob')

      // Test working representation without target
-      const globalRep = await session.workingRep('alice');
-      expect(globalRep).toEqual(mockWorkingRep);
-      expect(mockWorkspacesApi.workspaces.peers.workingRepresentation).toHaveBeenCalledWith(
-        'integration-test-workspace',
-        'alice',
-        { session_id: 'working-rep-session', target: undefined }
-      );
+      const globalRep = await session.workingRep('alice')
+      expect(globalRep).toEqual(mockWorkingRep)
+      expect(
+        mockWorkspacesApi.workspaces.peers.workingRepresentation
+      ).toHaveBeenCalledWith('integration-test-workspace', 'alice', {
+        session_id: 'working-rep-session',
+        target: undefined,
+      })

      // Test working representation with target
-      await session.workingRep(alice, bob);
-      expect(mockWorkspacesApi.workspaces.peers.workingRepresentation).toHaveBeenCalledWith(
-        'integration-test-workspace',
-        'alice',
-        { session_id: 'working-rep-session', target: 'bob' }
-      );
-    });
-  });
+      await session.workingRep(alice, bob)
+      expect(
+        mockWorkspacesApi.workspaces.peers.workingRepresentation
+      ).toHaveBeenCalledWith('integration-test-workspace', 'alice', {
+        session_id: 'working-rep-session',
+        target: 'bob',
+      })
+    })
+  })

  describe('Edge Cases and Error Handling Integration', () => {
    it('should handle empty and null responses gracefully', async () => {
      // Setup empty/null responses
-      mockWorkspacesApi.workspaces.peers.chat.mockResolvedValue({ content: null });
-      mockWorkspacesApi.workspaces.peers.list.mockResolvedValue({ items: [], total: 0, hasNextPage: false });
-      mockWorkspacesApi.workspaces.sessions.getContext.mockResolvedValue({ messages: [] });
+      mockWorkspacesApi.workspaces.peers.chat.mockResolvedValue({
+        content: null,
+      })
+      mockWorkspacesApi.workspaces.peers.list.mockResolvedValue({
+        items: [],
+        total: 0,
+        hasNextPage: false,
+      })
+      mockWorkspacesApi.workspaces.sessions.getContext.mockResolvedValue({
+        messages: [],
+      })

-      const peer = await honcho.peer('empty-peer');
-      const session = await honcho.session('empty-session');
+      const peer = await honcho.peer('empty-peer')
+      const session = await honcho.session('empty-session')

      // Test null chat response
-      const chatResult = await peer.chat('Hello');
-      expect(chatResult).toBeNull();
+      const chatResult = await peer.chat('Hello')
+      expect(chatResult).toBeNull()

      // Test empty peers list
-      const peersPage = await honcho.getPeers();
-      const peersList = await peersPage.data();
-      expect(peersList).toEqual([]);
+      const peersPage = await honcho.getPeers()
+      const peersList = await peersPage.data()
+      expect(peersList).toEqual([])

      // Test empty context
-      const context = await session.getContext();
-      expect(context.messages).toEqual([]);
-      expect(context.length).toBe(0);
-    });
+      const context = await session.getContext()
+      expect(context.messages).toEqual([])
+      expect(context.length).toBe(0)
+    })

    it('should maintain type safety throughout the workflow', async () => {
      // This test verifies TypeScript types are maintained correctly
-      const peer: Peer = await honcho.peer('typed-peer');
-      const session: Session = await honcho.session('typed-session');
+      const peer: Peer = await honcho.peer('typed-peer')
+      const session: Session = await honcho.session('typed-session')

-      expect(typeof peer.id).toBe('string');
-      expect(typeof session.id).toBe('string');
+      expect(typeof peer.id).toBe('string')
+      expect(typeof session.id).toBe('string')

-      const message = peer.message('typed message', { metadata: { type: 'test' } });
-      expect(typeof message.peer_id).toBe('string');
-      expect(typeof message.content).toBe('string');
-      expect(typeof message.metadata).toBe('object');
+      const message = peer.message('typed message', {
+        metadata: { type: 'test' },
+      })
+      expect(typeof message.peer_id).toBe('string')
+      expect(typeof message.content).toBe('string')
+      expect(typeof message.metadata).toBe('object')

      // Mock successful operations
      mockWorkspacesApi.workspaces.sessions.getContext.mockResolvedValue({
        messages: [{ id: 'msg1', content: 'Hello', peer_id: 'typed-peer' }],
-        summary: 'Test summary',
-      });
+        summary: {
+          content: 'Test summary',
+          message_id: 1,
+          summary_type: 'short',
+          created_at: '2024-01-01T00:00:00Z',
+          token_count: 20,
+        },
+      })

-      const context: SessionContext = await session.getContext();
-      expect(typeof context.sessionId).toBe('string');
-      expect(Array.isArray(context.messages)).toBe(true);
-      expect(typeof context.summary).toBe('string');
-      expect(typeof context.length).toBe('number');
-      expect(typeof context.toString()).toBe('string');
+      const context: SessionContext = await session.getContext()
+      expect(typeof context.sessionId).toBe('string')
+      expect(Array.isArray(context.messages)).toBe(true)
+      expect(context.summary).not.toBeNull()
+      expect(typeof context.summary?.content).toBe('string')
+      expect(typeof context.length).toBe('number')
+      expect(typeof context.toString()).toBe('string')

-      const openAI = context.toOpenAI(peer);
-      const anthropic = context.toAnthropic('assistant');
+      const openAI = context.toOpenAI(peer)
+      const anthropic = context.toAnthropic('assistant')

-      expect(Array.isArray(openAI)).toBe(true);
-      expect(Array.isArray(anthropic)).toBe(true);
+      expect(Array.isArray(openAI)).toBe(true)
+      expect(Array.isArray(anthropic)).toBe(true)

      if (openAI.length > 0) {
-        expect(typeof openAI[0].role).toBe('string');
-        expect(typeof openAI[0].content).toBe('string');
+        expect(typeof openAI[0].role).toBe('string')
+        expect(typeof openAI[0].content).toBe('string')
      }
-    });
-  });
-});
+    })
+  })
+})
--- a/sdks/typescript/tests/session.test.ts
+++ b/sdks/typescript/tests/session.test.ts
@ -455,6 +455,107 @@ describe('Session', () => {

      await expect(session.addMessages({ peer_id: 'peer1', content: 'test' })).rejects.toThrow();
    });
+
+    it('should add message with custom timestamp', async () => {
+      const message = {
+        peer_id: 'peer1',
+        content: 'Message with timestamp',
+        created_at: '2023-01-01T12:00:00Z',
+        metadata: { test: 'timestamp' },
+      };
+      mockClient.workspaces.sessions.messages.create.mockResolvedValue({});
+
+      await session.addMessages(message);
+
+      expect(mockClient.workspaces.sessions.messages.create).toHaveBeenCalledWith(
+        'test-workspace',
+        'test-session',
+        {
+          messages: [{
+            peer_id: 'peer1',
+            content: 'Message with timestamp',
+            created_at: '2023-01-01T12:00:00Z',
+            metadata: { test: 'timestamp' }
+          }]
+        }
+      );
+    });
+
+    it('should add message with null timestamp', async () => {
+      const message = {
+        peer_id: 'peer1',
+        content: 'Message without timestamp',
+        created_at: null,
+        metadata: { test: 'no_timestamp' },
+      };
+      mockClient.workspaces.sessions.messages.create.mockResolvedValue({});
+
+      await session.addMessages(message);
+
+      expect(mockClient.workspaces.sessions.messages.create).toHaveBeenCalledWith(
+        'test-workspace',
+        'test-session',
+        {
+          messages: [{
+            peer_id: 'peer1',
+            content: 'Message without timestamp',
+            created_at: null,
+            metadata: { test: 'no_timestamp' }
+          }]
+        }
+      );
+    });
+
+    it('should add mixed messages with and without timestamps', async () => {
+      const messages = [
+        {
+          peer_id: 'peer1',
+          content: 'Message with timestamp',
+          created_at: '2023-01-01T12:00:00Z',
+          metadata: { type: 'historical' }
+        },
+        {
+          peer_id: 'peer2',
+          content: 'Message without timestamp',
+          metadata: { type: 'current' }
+        },
+        {
+          peer_id: 'peer3',
+          content: 'Message with null timestamp',
+          created_at: null,
+          metadata: { type: 'default' }
+        }
+      ];
+      mockClient.workspaces.sessions.messages.create.mockResolvedValue({});
+
+      await session.addMessages(messages);
+
+      expect(mockClient.workspaces.sessions.messages.create).toHaveBeenCalledWith(
+        'test-workspace',
+        'test-session',
+        {
+          messages: [
+            {
+              peer_id: 'peer1',
+              content: 'Message with timestamp',
+              created_at: '2023-01-01T12:00:00Z',
+              metadata: { type: 'historical' }
+            },
+            {
+              peer_id: 'peer2',
+              content: 'Message without timestamp',
+              metadata: { type: 'current' }
+            },
+            {
+              peer_id: 'peer3',
+              content: 'Message with null timestamp',
+              created_at: null,
+              metadata: { type: 'default' }
+            }
+          ]
+        }
+      );
+    });
  });

  describe('getMessages', () => {
@ -582,7 +683,13 @@ describe('Session', () => {
          { id: 'msg1', content: 'Hello', peer_id: 'peer1' },
          { id: 'msg2', content: 'Hi there', peer_id: 'peer2' },
        ],
-        summary: 'Conversation summary',
+        summary: {
+          content: 'Conversation summary',
+          message_id: 10,
+          summary_type: 'short',
+          created_at: '2024-01-01T00:00:00Z',
+          token_count: 100
+        },
      };
      mockClient.workspaces.sessions.getContext.mockResolvedValue(mockContext);

@ -591,7 +698,7 @@ describe('Session', () => {
      expect(context).toBeInstanceOf(SessionContext);
      expect(context.sessionId).toBe('test-session');
      expect(context.messages).toEqual(mockContext.messages);
-      expect(context.summary).toBe('Conversation summary');
+      expect(context.summary?.content).toBe('Conversation summary');
      expect(mockClient.workspaces.sessions.getContext).toHaveBeenCalledWith(
        'test-workspace',
        'test-session',
@ -602,7 +709,13 @@ describe('Session', () => {
    it('should get session context with options', async () => {
      const mockContext = {
        messages: [{ id: 'msg1', content: 'Hello', peer_id: 'peer1' }],
-        summary: 'Brief summary',
+        summary: {
+          content: 'Brief summary',
+          message_id: 5,
+          summary_type: 'short',
+          created_at: '2024-01-01T00:00:00Z',
+          token_count: 50
+        },
      };
      mockClient.workspaces.sessions.getContext.mockResolvedValue(mockContext);

@ -624,7 +737,7 @@ describe('Session', () => {

      const context = await session.getContext();

-      expect(context.summary).toBe('');
+      expect(context.summary).toBeNull();
    });

    it('should handle API errors', async () => {
--- a/sdks/typescript/tests/session_context.test.ts
+++ b/sdks/typescript/tests/session_context.test.ts
@ -1,4 +1,4 @@
-import { SessionContext } from '../src/session_context';
+import { SessionContext, Summary } from '../src/session_context';
 import { Peer } from '../src/peer';

 /**
@ -17,6 +17,19 @@ function createTestMessage(id: string, content: string, peer_id: string, additio
  };
 }

+/**
+ * Helper function to create a test Summary object
+ */
+function createTestSummary(content: string): Summary {
+  return new Summary({
+    content,
+    message_id: 1,
+    summary_type: 'short',
+    created_at: new Date().toISOString(),
+    token_count: content.length
+  });
+}
+
 describe('SessionContext', () => {
  let sessionContext: SessionContext;
  let mockMessages: any[];
@ -29,38 +42,39 @@ describe('SessionContext', () => {
      createTestMessage('msg4', 'I am doing well, thank you!', 'assistant'),
    ];

-    sessionContext = new SessionContext('test-session', mockMessages, '');
+    sessionContext = new SessionContext('test-session', mockMessages, null);
  });

  describe('constructor', () => {
    it('should initialize with all properties', () => {
      expect(sessionContext.sessionId).toBe('test-session');
      expect(sessionContext.messages).toEqual(mockMessages);
-      expect(sessionContext.summary).toBe('');
+      expect(sessionContext.summary).toBe(null);
    });

-    it('should initialize with empty summary when not provided', () => {
+    it('should initialize with null summary when not provided', () => {
      const context = new SessionContext('session-id', mockMessages);

      expect(context.sessionId).toBe('session-id');
      expect(context.messages).toEqual(mockMessages);
-      expect(context.summary).toBe('');
+      expect(context.summary).toBe(null);
    });

    it('should handle empty messages array', () => {
-      const context = new SessionContext('session-id', [], 'No messages');
+      const summary = createTestSummary('No messages');
+      const context = new SessionContext('session-id', [], summary);

      expect(context.sessionId).toBe('session-id');
      expect(context.messages).toEqual([]);
-      expect(context.summary).toBe('No messages');
+      expect(context.summary).toBe(summary);
    });

    it('should handle null/undefined summary', () => {
      const context1 = new SessionContext('session-id', mockMessages, undefined as any);
-      const context2 = new SessionContext('session-id', mockMessages, null as any);
+      const context2 = new SessionContext('session-id', mockMessages, null);

-      expect(context1.summary).toBe('');
-      expect(context2.summary).toBe('');
+      expect(context1.summary).toBe(null);
+      expect(context2.summary).toBe(null);
    });
  });

@ -109,7 +123,8 @@ describe('SessionContext', () => {
    });

    it('should include summary message when summary exists', () => {
-      const contextWithSummary = new SessionContext('test-session', mockMessages, 'This is a summary');
+      const summary = createTestSummary('This is a summary');
+      const contextWithSummary = new SessionContext('test-session', mockMessages, summary);
      const openAIMessages = contextWithSummary.toOpenAI('assistant');

      expect(openAIMessages).toEqual([
@ -201,7 +216,8 @@ describe('SessionContext', () => {
    });

    it('should include summary message when summary exists', () => {
-      const contextWithSummary = new SessionContext('test-session', mockMessages, 'This is a summary');
+      const summary = createTestSummary('This is a summary');
+      const contextWithSummary = new SessionContext('test-session', mockMessages, summary);
      const anthropicMessages = contextWithSummary.toAnthropic('assistant');

      expect(anthropicMessages).toEqual([
@ -250,13 +266,13 @@ describe('SessionContext', () => {
  describe('toString', () => {
    it('should return correct string representation', () => {
      const result = sessionContext.toString();
-      expect(result).toBe('SessionContext(messages=4, summary=)');
+      expect(result).toBe('SessionContext(messages=4, summary=none)');
    });

    it('should handle empty messages', () => {
      const emptyContext = new SessionContext('session-id', []);
      const result = emptyContext.toString();
-      expect(result).toBe('SessionContext(messages=0, summary=)');
+      expect(result).toBe('SessionContext(messages=0, summary=none)');
    });

    it('should handle large number of messages', () => {
@ -266,7 +282,7 @@ describe('SessionContext', () => {
      const context = new SessionContext('session-id', manyMessages);

      const result = context.toString();
-      expect(result).toBe('SessionContext(messages=1000, summary=)');
+      expect(result).toBe('SessionContext(messages=1000, summary=none)');
    });
  });

@ -305,11 +321,13 @@ describe('SessionContext', () => {

    it('should handle very long session IDs and summaries', () => {
      const longSessionId = 'x'.repeat(1000);
-      const longSummary = 'Very long summary that goes on and on...'.repeat(100);
+      const longSummaryText = 'Very long summary that goes on and on...'.repeat(100);
+      const longSummary = createTestSummary(longSummaryText);
      const context = new SessionContext(longSessionId, mockMessages, longSummary);

      expect(context.sessionId).toBe(longSessionId);
      expect(context.summary).toBe(longSummary);
+      expect(context.summary?.content).toBe(longSummaryText);
      expect(context.length).toBe(5); // 4 messages + 1 summary
    });

--- a/sdks/typescript/bun.lock
+++ b/sdks/typescript/bun.lock
@ -4,7 +4,7 @@
    "": {
      "name": "@honcho-ai/sdk",
      "dependencies": {
-        "@honcho-ai/core": "1.3.0",
+        "@honcho-ai/core": "^1.4.0",
        "@types/node": "^24.0.1",
        "zod": "4.0.0",
      },
@ -108,7 +108,7 @@

    "@biomejs/cli-win32-x64": ["@biomejs/cli-win32-x64@2.1.3", "", { "os": "win32", "cpu": "x64" }, "sha512-dxy599q6lgp8ANPpR8sDMscwdp9oOumEsVXuVCVT9N2vAho8uYXlCz53JhxX6LtJOXaE73qzgkGQ7QqvFlMC0g=="],

-    "@honcho-ai/core": ["@honcho-ai/core@1.3.0", "", { "dependencies": { "@types/node": "^18.11.18", "@types/node-fetch": "^2.6.4", "abort-controller": "^3.0.0", "agentkeepalive": "^4.2.1", "form-data-encoder": "1.7.2", "formdata-node": "^4.3.2", "node-fetch": "^2.6.7" } }, "sha512-yhxpZ00sQhO24PrHoTlj1cwR1q7/8FKSFZoCImqsFFmdERiXtE74YXhhfqzseyuShu1WfM7IwD8T2oCOB3hu7A=="],
+    "@honcho-ai/core": ["@honcho-ai/core@1.4.0", "", { "dependencies": { "@types/node": "^18.11.18", "@types/node-fetch": "^2.6.4", "abort-controller": "^3.0.0", "agentkeepalive": "^4.2.1", "form-data-encoder": "1.7.2", "formdata-node": "^4.3.2", "node-fetch": "^2.6.7" } }, "sha512-pHyUgkiIlf+pMfZJx7NmJ1UH8yOKWZ+vmPRummg3olgstMXApcBrW0bhJTPjHWoGGA+OFYcOPxJBoZKY6VCtMw=="],

    "@istanbuljs/load-nyc-config": ["@istanbuljs/load-nyc-config@1.1.0", "", { "dependencies": { "camelcase": "^5.3.1", "find-up": "^4.1.0", "get-package-type": "^0.1.0", "js-yaml": "^3.13.1", "resolve-from": "^5.0.0" } }, "sha512-VjeHSlIzpv/NyD3N0YuHfXOPDIixcA1q2ZV98wsMqcYlPmv2n3Yb2lYP9XMElnaFVXg5A7YLTeLu6V84uQDjmQ=="],

@ -644,7 +644,7 @@

    "@babel/helper-compilation-targets/semver": ["semver@6.3.1", "", { "bin": { "semver": "bin/semver.js" } }, "sha512-BR7VvDCVHO+q2xBEWskxS6DJE1qRnb7DxzUrogb71CWoSficBxYsiAGd+Kl0mmq/MprG9yArRkyrQxTO6XjMzA=="],

-    "@honcho-ai/core/@types/node": ["@types/node@18.19.121", "", { "dependencies": { "undici-types": "~5.26.4" } }, "sha512-bHOrbyztmyYIi4f1R0s17QsPs1uyyYnGcXeZoGEd227oZjry0q6XQBQxd82X1I57zEfwO8h9Xo+Kl5gX1d9MwQ=="],
+    "@honcho-ai/core/@types/node": ["@types/node@18.19.122", "", { "dependencies": { "undici-types": "~5.26.4" } }, "sha512-yzegtT82dwTNEe/9y+CM8cgb42WrUfMMCg2QqSddzO1J6uPmBD7qKCZ7dOHZP2Yrpm/kb0eqdNMn2MUyEiqBmA=="],

    "@istanbuljs/load-nyc-config/camelcase": ["camelcase@5.3.1", "", {}, "sha512-L28STB170nwWS63UjtlEOE3dldQApaJXZkOI1uMFfzf3rRuPegHaHesyee+YxQ+W6SvRDQV6UrdOdRiR153wJg=="],

--- a/sdks/typescript/examples/get_summaries.ts
+++ b/sdks/typescript/examples/get_summaries.ts
@ -0,0 +1,104 @@
+/**
+ * Example of getting session summaries using the Honcho TypeScript SDK.
+ *
+ * This example demonstrates how to retrieve both short and long summaries
+ * for a session, including their metadata like message ID, creation timestamp,
+ * and token count.
+ */
+
+import { Honcho, type SessionSummaries, type Summary } from "../src";
+
+async function main() {
+	// Initialize the Honcho client
+	const apiKey = process.env.HONCHO_API_KEY;
+	if (!apiKey) {
+		throw new Error("Please set HONCHO_API_KEY environment variable");
+	}
+
+	const client = new Honcho({ apiKey });
+
+	// Get a session (replace with your actual session ID)
+	const session = await client.session("my-conversation-session");
+
+	// Get summaries for the session
+	const summaries: SessionSummaries = await session.getSummaries();
+
+	console.log(`Session ID: ${summaries.id}`);
+	console.log("-".repeat(50));
+
+	// Check and display short summary
+	if (summaries.shortSummary) {
+		console.log("SHORT SUMMARY:");
+		console.log(
+			`  Content: ${summaries.shortSummary.content.slice(0, 200)}...`,
+		); // First 200 chars
+		console.log(
+			`  Covers up to message ID: ${summaries.shortSummary.messageId}`,
+		);
+		console.log(`  Created at: ${summaries.shortSummary.createdAt}`);
+		console.log(`  Token count: ${summaries.shortSummary.tokenCount}`);
+		console.log(`  Type: ${summaries.shortSummary.summaryType}`);
+	} else {
+		console.log("No short summary available yet");
+	}
+
+	console.log("-".repeat(50));
+
+	// Check and display long summary
+	if (summaries.longSummary) {
+		console.log("LONG SUMMARY:");
+		console.log(`  Content: ${summaries.longSummary.content.slice(0, 200)}...`); // First 200 chars
+		console.log(
+			`  Covers up to message ID: ${summaries.longSummary.messageId}`,
+		);
+		console.log(`  Created at: ${summaries.longSummary.createdAt}`);
+		console.log(`  Token count: ${summaries.longSummary.tokenCount}`);
+		console.log(`  Type: ${summaries.longSummary.summaryType}`);
+	} else {
+		console.log("No long summary available yet");
+	}
+
+	// Example showing how to use summaries in application logic
+	console.log("\n" + "=".repeat(50));
+	console.log("USAGE EXAMPLE:");
+	console.log("=".repeat(50));
+
+	// Check if we have any summaries
+	if (summaries.shortSummary || summaries.longSummary) {
+		// Prefer long summary if available and under token limit
+		const MAX_TOKENS = 2000;
+		let selectedSummary: Summary | null = null;
+
+		if (
+			summaries.longSummary &&
+			summaries.longSummary.tokenCount <= MAX_TOKENS
+		) {
+			selectedSummary = summaries.longSummary;
+			console.log("Using long summary (within token limit)");
+		} else if (summaries.shortSummary) {
+			selectedSummary = summaries.shortSummary;
+			console.log("Using short summary");
+		}
+
+		if (selectedSummary) {
+			console.log(
+				`Selected summary covers up to message ${selectedSummary.messageId}`,
+			);
+			console.log(`Token count: ${selectedSummary.tokenCount}`);
+
+			// You could use this summary as context for an LLM call
+			// For example, with OpenAI:
+			// const systemPrompt = `Previous conversation summary: ${selectedSummary.content}`
+		}
+	} else {
+		console.log(
+			"No summaries available - would need to use full message history",
+		);
+	}
+}
+
+// Run the example
+main().catch((err) => {
+	console.error(err);
+	process.exit(1);
+});
--- a/sdks/typescript/package.json
+++ b/sdks/typescript/package.json
@ -1,6 +1,6 @@
 {
  "name": "@honcho-ai/sdk",
-  "version": "1.3.0",
+  "version": "1.4.0",
  "description": "Official DX Optimized TypeScript SDK for Honcho",
  "author": "Plastic Labs <hello@plasticlabs.ai>",
  "license": "Apache-2.0",
@ -20,7 +20,7 @@
    "test:coverage": "jest --coverage"
  },
  "dependencies": {
-    "@honcho-ai/core": "1.3.0",
+    "@honcho-ai/core": "^1.4.0",
    "@types/node": "^24.0.1",
    "zod": "4.0.0"
  },
--- a/sdks/typescript/src/index.ts
+++ b/sdks/typescript/src/index.ts
@ -6,7 +6,12 @@ export { Honcho } from './client'
 export { Page } from './pagination'
 export { Peer } from './peer'
 export { Session, SessionPeerConfig } from './session'
-export { SessionContext } from './session_context'
+export {
+  SessionContext,
+  SessionSummaries,
+  Summary,
+  SummaryData,
+} from './session_context'

 // Export validation types for advanced usage
 export type {
--- a/sdks/typescript/src/peer.ts
+++ b/sdks/typescript/src/peer.ts
@ -131,21 +131,31 @@ export class Peer {
   *
   * @param content - The text content for the message
   * @param metadata - Optional metadata to associate with the message
+   * @param created_at - Optional ISO 8601 timestamp for the message
   * @returns A new message object with this peer's ID and the provided content
   */
  message(
    content: string,
-    options?: { metadata?: Record<string, unknown> }
+    options?: {
+      metadata?: Record<string, unknown>
+      created_at?: string | Date
+    }
  ): ValidatedMessageCreate {
    const validatedContent = MessageContentSchema.parse(content)
    const validatedMetadata = options?.metadata
      ? MessageMetadataSchema.parse(options.metadata)
      : undefined

+    const createdAt =
+      options?.created_at instanceof Date
+        ? options.created_at.toISOString()
+        : options?.created_at
+
    return {
      peer_id: this.id,
      content: validatedContent,
      metadata: validatedMetadata,
+      created_at: createdAt,
    }
  }

--- a/sdks/typescript/src/session.ts
+++ b/sdks/typescript/src/session.ts
@ -3,7 +3,7 @@ import type { Message } from '@honcho-ai/core/src/resources/workspaces/sessions/
 import type { Uploadable } from '@honcho-ai/core/src/uploads'
 import { Page } from './pagination'
 import { Peer } from './peer'
-import { SessionContext } from './session_context'
+import { SessionContext, SessionSummaries, Summary } from './session_context'
 import {
  ContextParamsSchema,
  FileUploadSchema,
@ -350,6 +350,12 @@ export class Session {
   *   { peer_id: 'user1', content: 'Hello!' },
   *   { peer_id: 'assistant', content: 'Hi there!' }
   * ])
+   * // Add message with custom ISO 8601 timestamp
+   * await session.addMessages({
+   *   peer_id: 'user123',
+   *   content: 'Hello world!',
+   *   created_at: '2021-01-01T00:00:00.000Z'
+   * })
   * ```
   */
  async addMessages(messages: MessageAddition): Promise<void> {
@ -457,7 +463,37 @@ export class Session {
        summary: contextParams.summary,
      }
    )
-    return new SessionContext(this.id, context.messages, context.summary)
+    // Convert the summary response to Summary object if present
+    const summary = context.summary ? new Summary(context.summary) : null
+    return new SessionContext(this.id, context.messages, summary)
+  }
+
+  /**
+   * Get available summaries for this session.
+   *
+   * Makes an API call to retrieve both short and long summaries for this session,
+   * if they are available. Summaries are created asynchronously by the backend
+   * as messages are added to the session.
+   *
+   * @returns Promise resolving to a SessionSummaries object containing:
+   *          - id: The session ID
+   *          - shortSummary: The short summary if available, including metadata
+   *          - longSummary: The long summary if available, including metadata
+   *
+   * @note Summaries may be null if:
+   *       - Not enough messages have been added to trigger summary generation
+   *       - The summary generation is still in progress
+   *       - Summary generation is disabled for this session
+   */
+  async getSummaries(): Promise<SessionSummaries> {
+    // Use the core SDK's summaries method
+    const data = await this._client.workspaces.sessions.summaries(
+      this.workspaceId,
+      this.id
+    )
+
+    // Return a SessionSummaries instance
+    return new SessionSummaries(data)
  }

  /**
--- a/sdks/typescript/src/session_context.ts
+++ b/sdks/typescript/src/session_context.ts
@ -1,6 +1,84 @@
 import type { Message } from '@honcho-ai/core/src/resources/workspaces/sessions/messages'
 import type { Peer } from './peer'

+export interface SummaryData {
+  content: string
+  message_id: number
+  summary_type: string
+  created_at: string
+  token_count: number
+}
+
+/**
+ * Represents a summary of a session's conversation.
+ */
+export class Summary {
+  /**
+   * The summary text.
+   */
+  readonly content: string
+
+  /**
+   * The ID of the message that this summary covers up to.
+   */
+  readonly messageId: number
+
+  /**
+   * The type of summary (short or long).
+   */
+  readonly summaryType: string
+
+  /**
+   * The timestamp of when the summary was created (ISO format).
+   */
+  readonly createdAt: string
+
+  /**
+   * The number of tokens in the summary text.
+   */
+  readonly tokenCount: number
+
+  constructor(data: SummaryData) {
+    this.content = data.content
+    this.messageId = data.message_id
+    this.summaryType = data.summary_type
+    this.createdAt = data.created_at
+    this.tokenCount = data.token_count
+  }
+}
+
+/**
+ * Contains both short and long summaries for a session.
+ */
+export class SessionSummaries {
+  /**
+   * The session ID.
+   */
+  readonly id: string
+
+  /**
+   * The short summary if available.
+   */
+  readonly shortSummary: Summary | null
+
+  /**
+   * The long summary if available.
+   */
+  readonly longSummary: Summary | null
+
+  constructor(data: {
+    id: string
+    short_summary?: SummaryData | null
+    long_summary?: SummaryData | null
+  }) {
+    this.id = data.id
+    this.shortSummary = data.short_summary
+      ? new Summary(data.short_summary)
+      : null
+    this.longSummary = data.long_summary ? new Summary(data.long_summary) : null
+  }
+}
+
 /**
 * Represents the context of a session containing a curated list of messages.
 *
@ -22,7 +100,7 @@ export class SessionContext {
  /**
   * Summary of the session history prior to the message cutoff.
   */
-  readonly summary: string
+  readonly summary: Summary | null

  /**
   * Initialize a new SessionContext.
@ -31,10 +109,14 @@ export class SessionContext {
   * @param messages List of Message objects to include in the context
   * @param summary Summary of the session history prior to the message cutoff
   */
-  constructor(sessionId: string, messages: Message[], summary: string = '') {
+  constructor(
+    sessionId: string,
+    messages: Message[],
+    summary: Summary | null = null
+  ) {
    this.sessionId = sessionId
    this.messages = messages
-    this.summary = summary || ''
+    this.summary = summary
  }

  /**
@ -54,16 +136,18 @@ export class SessionContext {
    assistant: string | Peer
  ): Array<{ role: string; content: string; name?: string }> {
    const assistantId = typeof assistant === 'string' ? assistant : assistant.id
-    const summaryMessage = {
-      role: 'system',
-      content: `<summary>${this.summary}</summary>`,
-    }
+    const summaryMessage = this.summary
+      ? {
+          role: 'system',
+          content: `<summary>${this.summary.content}</summary>`,
+        }
+      : null
    const messages = this.messages.map((message) => ({
      role: message.peer_id === assistantId ? 'assistant' : 'user',
      name: message.peer_id,
      content: message.content,
    }))
-    return this.summary ? [summaryMessage, ...messages] : messages
+    return summaryMessage ? [summaryMessage, ...messages] : messages
  }

  /**
@ -86,10 +170,12 @@ export class SessionContext {
    assistant: string | Peer
  ): Array<{ role: string; content: string }> {
    const assistantId = typeof assistant === 'string' ? assistant : assistant.id
-    const summaryMessage = {
-      role: 'user',
-      content: `<summary>${this.summary}</summary>`,
-    }
+    const summaryMessage = this.summary
+      ? {
+          role: 'user',
+          content: `<summary>${this.summary.content}</summary>`,
+        }
+      : null
    const messages = this.messages.map((message) =>
      message.peer_id === assistantId
        ? {
@ -101,20 +187,20 @@ export class SessionContext {
            content: `${message.peer_id}: ${message.content}`,
          }
    )
-    return this.summary ? [summaryMessage, ...messages] : messages
+    return summaryMessage ? [summaryMessage, ...messages] : messages
  }

  /**
   * Return the number of messages in the context.
   */
  get length(): number {
-    return this.messages.length + (this.summary.length > 0 ? 1 : 0)
+    return this.messages.length + (this.summary ? 1 : 0)
  }

  /**
   * Return a string representation of the SessionContext.
   */
  toString(): string {
-    return `SessionContext(messages=${this.messages.length}, summary=${this.summary})`
+    return `SessionContext(messages=${this.messages.length}, summary=${this.summary ? 'present' : 'none'})`
  }
 }
--- a/sdks/typescript/src/validation.ts
+++ b/sdks/typescript/src/validation.ts
@ -94,6 +94,7 @@ export const MessageCreateSchema = z.object({
  peer_id: PeerIdSchema,
  content: MessageContentSchema,
  metadata: MessageMetadataSchema,
+  created_at: z.string().nullable().optional(),
 })

 /**
--- a/src/crud/message.py
+++ b/src/crud/message.py
@ -89,6 +89,7 @@ async def create_messages(
            workspace_name=workspace_name,
            public_id=generate_nanoid(),
            token_count=len(message.encoded_message),
+            created_at=message.created_at,  # Use provided created_at if available
        )
        message_objects.append(message_obj)

--- a/src/deriver/deriver.py
+++ b/src/deriver/deriver.py
@ -19,6 +19,7 @@ from src.utils.formatting import (
    find_new_observations,
    format_context_for_prompt,
    format_new_turn_with_timestamp,
+    utc_now_iso,
 )
 from src.utils.logging import (
    accumulate_metric,
@ -630,7 +631,7 @@ async def save_working_representation_to_peer(
    working_rep_data = {
        "final_observations": final_obs_dict,
        "message_id": message_id,
-        "created_at": datetime.datetime.now().isoformat(),
+        "created_at": utc_now_iso(),
    }

    # if session_name is supplied, save working representation to session peer
--- a/src/dialectic/chat.py
+++ b/src/dialectic/chat.py
@ -18,7 +18,7 @@ from mirascope.llm import Stream
 from src import crud
 from src.config import settings
 from src.dependencies import tracked_db
-from src.routers.sessions import get_session_context
+from src.utils import summarizer
 from src.utils.clients import honcho_llm_call
 from src.utils.embedding_store import EmbeddingStore
 from src.utils.logging import (
@ -262,25 +262,16 @@ async def chat(
    # If query is session-scoped, get recent conversation history from that session
    if session_name:
        async with tracked_db("chat.get_session_context") as db:
-            session_context = await get_session_context(
-                workspace_id=workspace_name,
-                session_id=session_name,
-                tokens=context_window_size,
-                summary=True,
-                db=db,
+            recent_conversation_history = (
+                await summarizer.get_session_context_formatted(
+                    db,
+                    workspace_name=workspace_name,
+                    session_name=session_name,
+                    token_limit=context_window_size,
+                    include_summary=True,
+                )
            )
-        logger.info(
-            "Retrieved recent conversation history with %s messages",
-            len(session_context.messages),
-        )
-        recent_conversation_history = f"""
-        <summary>
-        {session_context.summary}
-        </summary>
-        <recent_messages>
-        {session_context.messages}
-        </recent_messages>
-        """
+        logger.info("Retrieved recent conversation history")
    else:
        recent_conversation_history = None
        logger.info("Query is not session-scoped, skipping recent conversation history")
--- a/src/dialectic/utils.py
+++ b/src/dialectic/utils.py
@ -11,6 +11,7 @@ from src.utils.clients import honcho_llm_call
 from src.utils.embedding_store import EmbeddingStore
 from src.utils.formatting import (
    format_premises_for_display,
+    parse_datetime_iso,
 )
 from src.utils.logging import conditional_observe
 from src.utils.shared_models import SemanticQueries
@ -190,11 +191,9 @@ def _format_observations(
        if last_accessed:
            # Format the last_accessed datetime for display
            try:
-                from datetime import datetime
-
                if isinstance(last_accessed, str):
                    # Parse ISO format datetime string
-                    dt = datetime.fromisoformat(last_accessed.replace("Z", "+00:00"))
+                    dt = parse_datetime_iso(last_accessed)
                    formatted_last_accessed: str = dt.strftime("%Y-%m-%d %H:%M")
                    access_parts.append(f"last accessed {formatted_last_accessed}")
            except (ValueError, AttributeError):
--- a/src/main.py
+++ b/src/main.py
@ -117,7 +117,7 @@ app = FastAPI(
    title="Honcho API",
    summary="The Identity Layer for the Agentic World",
    description="""Honcho is a platform for giving agents user-centric memory and social cognition""",
-    version="2.2.0",
+    version="2.3.0",
    contact={
        "name": "Plastic Labs",
        "url": "https://honcho.dev",
--- a/src/routers/keys.py
+++ b/src/routers/keys.py
@ -10,6 +10,7 @@ from src.security import (
    create_jwt,
    require_auth,
 )
+from src.utils.formatting import format_datetime_utc

 logger = logging.getLogger(__name__)

@ -43,7 +44,7 @@ async def create_key(

    key_str = create_jwt(
        JWTParams(
-            exp=expires_at.isoformat() if expires_at else None,
+            exp=format_datetime_utc(expires_at) if expires_at else None,
            w=workspace_id,
            p=peer_id,
            s=session_id,
--- a/src/routers/sessions.py
+++ b/src/routers/sessions.py
@ -374,9 +374,11 @@ async def get_session_context(
        le=config.settings.GET_CONTEXT_MAX_TOKENS,
        description=f"Number of tokens to use for the context. Includes summary if set to true. If not provided, the context will be exhaustive (within {config.settings.GET_CONTEXT_MAX_TOKENS} tokens)",
    ),
-    summary: bool = Query(
-        True,
+    *,
+    include_summary: bool = Query(
+        default=True,
        description="Whether or not to include a summary *if* one is available for the session",
+        alias="summary",
    ),
    db: AsyncSession = db,
 ):
@ -389,18 +391,59 @@ async def get_session_context(
    token_limit = tokens or config.settings.GET_CONTEXT_MAX_TOKENS

    # Use the shared get_session_context function from summarizer
-    summary_content, messages = await summarizer.get_session_context(
+    summary_obj, messages = await summarizer.get_session_context(
        db,
        workspace_name=workspace_id,
        session_name=session_id,
        token_limit=token_limit,
-        include_summary=summary,
+        include_summary=include_summary,
    )

    return schemas.SessionContext(
        name=session_id,
        messages=messages,  # pyright: ignore -- db message type and schema message type are different, but excess gets removed by schema
-        summary=summary_content,
+        summary=summary_obj,
+    )
+
+
+@router.get(
+    "/{session_id}/summaries",
+    response_model=schemas.SessionSummaries,
+    dependencies=[
+        Depends(require_auth(workspace_name="workspace_id", session_name="session_id"))
+    ],
+)
+async def get_session_summaries(
+    workspace_id: str = Path(..., description="ID of the workspace"),
+    session_id: str = Path(..., description="ID of the session"),
+    db: AsyncSession = db,
+) -> schemas.SessionSummaries:
+    """
+    Get available summaries for a session.
+
+    Returns both short and long summaries if available, including metadata like
+    the message ID they cover up to, creation timestamp, and token count.
+    """
+    # Reuse the logic from get_context to get both summaries
+    short_summary, long_summary = await summarizer.get_both_summaries(
+        db,
+        workspace_name=workspace_id,
+        session_name=session_id,
+    )
+
+    # Convert the internal Summary TypedDict to our Pydantic schema
+    short_summary_schema = None
+    if short_summary:
+        short_summary_schema = summarizer.to_schema_summary(short_summary)
+
+    long_summary_schema = None
+    if long_summary:
+        long_summary_schema = summarizer.to_schema_summary(long_summary)
+
+    return schemas.SessionSummaries(
+        name=session_id,
+        short_summary=short_summary_schema,
+        long_summary=long_summary_schema,
    )


--- a/src/schemas.py
+++ b/src/schemas.py
@ -117,6 +117,7 @@ class MessageCreate(MessageBase):
    content: Annotated[str, Field(min_length=0, max_length=50000)]
    peer_name: str = Field(alias="peer_id")
    metadata: dict[str, Any] | None = None
+    created_at: datetime.datetime | None = None

    _encoded_message: list[int] = PrivateAttr(default=[])

@ -223,10 +224,38 @@ class Session(SessionBase):
    )


+class Summary(BaseModel):
+    content: str = Field(description="The summary text")
+    message_id: int = Field(
+        description="The ID of the message that this summary covers up to"
+    )
+    summary_type: str = Field(description="The type of summary (short or long)")
+    created_at: str = Field(
+        description="The timestamp of when the summary was created (ISO format)"
+    )
+    token_count: int = Field(description="The number of tokens in the summary text")
+
+
 class SessionContext(SessionBase):
    name: str = Field(serialization_alias="id")
    messages: list[Message]
-    summary: str
+    summary: Summary | None = Field(
+        default=None, description="The summary if available"
+    )
+
+    model_config = ConfigDict(  # pyright: ignore
+        from_attributes=True, populate_by_name=True
+    )
+
+
+class SessionSummaries(SessionBase):
+    name: str = Field(serialization_alias="id")
+    short_summary: Summary | None = Field(
+        default=None, description="The short summary if available"
+    )
+    long_summary: Summary | None = Field(
+        default=None, description="The long summary if available"
+    )

    model_config = ConfigDict(  # pyright: ignore
        from_attributes=True, populate_by_name=True
--- a/src/security.py
+++ b/src/security.py
@ -8,6 +8,7 @@ from fastapi.security import HTTPAuthorizationCredentials, HTTPBearer
 from pydantic import BaseModel

 from src.config import settings
+from src.utils.formatting import utc_now_iso

 from .exceptions import AuthenticationException

@ -54,7 +55,7 @@ class JWTParams(BaseModel):
    `s`: (string) session name
    """

-    t: str = datetime.datetime.now().isoformat()
+    t: str = utc_now_iso()
    exp: str | None = None
    ad: bool | None = None
    w: str | None = None
--- a/src/utils/embedding_store.py
+++ b/src/utils/embedding_store.py
@ -12,6 +12,7 @@ from src import crud, models
 from src.config import settings
 from src.dependencies import tracked_db
 from src.embedding_client import embedding_client
+from src.utils.formatting import format_datetime_utc
 from src.utils.logging import conditional_observe
 from src.utils.shared_models import (
    Observation,
@ -115,7 +116,7 @@ class EmbeddingStore:
                    "message_id": message_id,
                    "session_name": session_name,
                    "premises": obs.premises,  # Store premises in metadata
-                    "created_at": message_created_at.isoformat()
+                    "created_at": format_datetime_utc(message_created_at)
                    if message_created_at
                    else None,
                }
--- a/src/utils/filter.py
+++ b/src/utils/filter.py
@ -7,6 +7,7 @@ from sqlalchemy import ColumnElement, Select, and_, case, cast, literal, not_, o
 from sqlalchemy.types import Numeric

 from ..exceptions import FilterError
+from .formatting import parse_datetime_iso

 logger = getLogger(__name__)

@ -561,9 +562,9 @@ def _validate_datetime_string(value: str) -> datetime.datetime | None:
        except ValueError:
            continue

-    # Try fromisoformat as a fallback (Python 3.7+)
+    # Try fromisoformat as a fallback (Python 3.7+) with Z format support
    try:
-        return datetime.datetime.fromisoformat(value.replace("Z", "+00:00"))
+        return parse_datetime_iso(value)
    except ValueError:
        pass

--- a/src/utils/formatting.py
+++ b/src/utils/formatting.py
@ -5,13 +5,83 @@ This module contains helper functions for processing observations, formatting co
 and handling temporal metadata for the reasoning system.
 """

-from datetime import datetime
+from datetime import datetime, timezone
 from typing import Any, Protocol, cast, runtime_checkable

 from src.utils.logging import conditional_observe
 from src.utils.shared_models import ReasoningResponse


+def format_datetime_utc(dt: datetime) -> str:
+    """
+    Format datetime to ISO 8601 string with Z suffix for UTC timezone.
+
+    This ensures consistent datetime formatting across the entire backend,
+    using the Z format which is the ISO 8601 standard for UTC and matches
+    Pydantic's JSON serialization behavior.
+
+    Args:
+        dt: datetime object (should be timezone-aware)
+
+    Returns:
+        ISO 8601 formatted string with Z suffix for UTC
+
+    Example:
+        >>> dt = datetime(2023, 1, 1, 12, 0, 0, tzinfo=timezone.utc)
+        >>> format_datetime_utc(dt)
+        '2023-01-01T12:00:00Z'
+    """
+    if dt.tzinfo is None:
+        # If no timezone info, assume UTC
+        dt = dt.replace(tzinfo=timezone.utc)
+
+    # Convert to UTC if not already
+    if dt.tzinfo != timezone.utc:
+        dt = dt.astimezone(timezone.utc)
+
+    # Format and replace +00:00 with Z
+    return dt.isoformat().replace("+00:00", "Z")
+
+
+def utc_now_iso() -> str:
+    """
+    Get current UTC time as ISO 8601 string with Z suffix.
+
+    Returns:
+        Current UTC time in ISO 8601 format with Z suffix
+
+    Example:
+        >>> utc_now_iso()
+        '2023-01-01T12:34:56.789123Z'
+    """
+    return format_datetime_utc(datetime.now(timezone.utc))
+
+
+def parse_datetime_iso(iso_string: str) -> datetime:
+    """
+    Parse ISO 8601 datetime string, handling both Z and +00:00 UTC formats.
+
+    This function handles the fact that Python's fromisoformat() doesn't
+    directly support the 'Z' suffix, which is the standard ISO 8601 way
+    to represent UTC timezone.
+
+    Args:
+        iso_string: ISO 8601 formatted datetime string
+
+    Returns:
+        datetime object with timezone information
+
+    Example:
+        >>> parse_datetime_iso('2023-01-01T12:00:00Z')
+        datetime.datetime(2023, 1, 1, 12, 0, tzinfo=datetime.timezone.utc)
+        >>> parse_datetime_iso('2023-01-01T12:00:00+00:00')
+        datetime.datetime(2023, 1, 1, 12, 0, tzinfo=datetime.timezone.utc)
+    """
+    # Convert Z format to +00:00 format for Python's fromisoformat
+    normalized_string = iso_string.replace("Z", "+00:00")
+    return datetime.fromisoformat(normalized_string)
+
+
@runtime_checkable
 class StructuredObservation(Protocol):
    """Protocol for observations that have conclusion and premises attributes."""
--- a/src/utils/summarizer.py
+++ b/src/utils/summarizer.py
@ -1,5 +1,4 @@
 import asyncio
-import datetime
 import logging
 import time
 from enum import Enum
@ -9,10 +8,12 @@ from sqlalchemy import update
 from sqlalchemy.ext.asyncio import AsyncSession
 from typing_extensions import TypedDict

+from src import schemas
 from src.config import settings
 from src.dependencies import tracked_db
 from src.exceptions import ResourceNotFoundException
 from src.utils.clients import honcho_llm_call
+from src.utils.formatting import utc_now_iso
 from src.utils.logging import accumulate_metric

 from .. import crud, models
@ -40,6 +41,16 @@ class Summary(TypedDict):
    token_count: int


+def to_schema_summary(s: Summary) -> schemas.Summary:
+    return schemas.Summary(
+        content=s["content"],
+        message_id=s["message_id"],
+        summary_type=s["summary_type"],
+        created_at=s["created_at"],
+        token_count=s["token_count"],
+    )
+
+
 # Export the public functions
 __all__ = [
    "get_summary",
@ -49,6 +60,7 @@ __all__ = [
    "get_session_context_formatted",
    "SummaryType",
    "Summary",
+    "to_schema_summary",
 ]


@ -388,7 +400,7 @@ async def _create_summary(
        content=summary_text,
        message_id=messages[-1].id if messages else 0,
        summary_type=summary_type.value,
-        created_at=datetime.datetime.now(datetime.timezone.utc).isoformat(),
+        created_at=utc_now_iso(),
        token_count=summary_tokens,
    )

@ -564,7 +576,7 @@ async def get_session_context(
    *,
    cutoff: int | None = None,
    include_summary: bool = True,
-) -> tuple[str, list[models.Message]]:
+) -> tuple[schemas.Summary | None, list[models.Message]]:
    """
    Get session context similar to the API endpoint but for internal use.

@ -577,10 +589,10 @@ async def get_session_context(
        include_summary: Whether to include summary if available

    Returns:
-        Tuple of (summary_content, messages) where summary_content is the summary text (or empty string)
+        Tuple of (summary, messages) where summary is a Summary pydantic model (or None)
        and messages is the list of message objects
    """
-    summary_content = ""
+    summary = None
    messages_tokens = token_limit
    messages_start_id = 0

@ -601,13 +613,25 @@ async def get_session_context(
            and long_len <= summary_tokens_limit
            and long_len > short_len
        ):
-            summary_content = latest_long_summary["content"]
+            summary = schemas.Summary(
+                content=latest_long_summary["content"],
+                message_id=latest_long_summary["message_id"],
+                summary_type=latest_long_summary["summary_type"],
+                created_at=latest_long_summary["created_at"],
+                token_count=latest_long_summary["token_count"],
+            )
            messages_tokens = token_limit - latest_long_summary["token_count"]
            messages_start_id = latest_long_summary["message_id"]
        elif (
            latest_short_summary and short_len <= summary_tokens_limit and short_len > 0
        ):
-            summary_content = latest_short_summary["content"]
+            summary = schemas.Summary(
+                content=latest_short_summary["content"],
+                message_id=latest_short_summary["message_id"],
+                summary_type=latest_short_summary["summary_type"],
+                created_at=latest_short_summary["created_at"],
+                token_count=latest_short_summary["token_count"],
+            )
            messages_tokens = token_limit - latest_short_summary["token_count"]
            messages_start_id = latest_short_summary["message_id"]
        else:
@ -628,7 +652,7 @@ async def get_session_context(
        token_limit=messages_tokens,
    )

-    return summary_content, messages
+    return summary, messages


 async def get_session_context_formatted(
@ -646,7 +670,7 @@ async def get_session_context_formatted(
    This is a convenience wrapper around get_session_context that formats
    the output as a string.
    """
-    summary_content, messages = await get_session_context(
+    summary, messages = await get_session_context(
        db,
        workspace_name,
        session_name,
@ -657,6 +681,7 @@ async def get_session_context_formatted(

    # Format the messages
    messages_text = _format_messages(messages)
+    summary_content = summary.content if summary else ""

    if summary_content and messages_text:
        return f"""<summary>
--- a/src/webhooks/webhook_delivery.py
+++ b/src/webhooks/webhook_delivery.py
@ -3,7 +3,6 @@ import hashlib
 import hmac
 import json
 import logging
-from datetime import datetime, timezone

 import httpx
 from sqlalchemy.ext.asyncio import AsyncSession
@ -11,6 +10,7 @@ from sqlalchemy.ext.asyncio import AsyncSession
 from src.config import settings
 from src.crud.webhook import list_webhook_endpoints
 from src.deriver.queue_payload import WebhookPayload
+from src.utils.formatting import utc_now_iso

 logger = logging.getLogger(__name__)

@ -31,7 +31,7 @@ async def deliver_webhook(db: AsyncSession, payload: WebhookPayload) -> None:
            event_payload = {
                "type": payload.event_type,
                "data": payload.data,
-                "timestamp": datetime.now(timezone.utc).isoformat(),
+                "timestamp": utc_now_iso(),
            }
            event_json = json.dumps(
                event_payload, separators=(",", ":"), sort_keys=True
--- a/tests/bench/run_tests.py
+++ b/tests/bench/run_tests.py
@ -509,8 +509,12 @@ Evaluate whether the actual response contains the core correct information from
                    summary=summary, tokens=max_tokens
                )

+                summary_content = ""
+                if session_context.summary:
+                    summary_content = session_context.summary.content
+
                tokenizer = tiktoken.get_encoding("cl100k_base")
-                summary_tokens = len(tokenizer.encode(session_context.summary))
+                summary_tokens = len(tokenizer.encode(summary_content))
                print(f"    summary: {session_context.summary}")

                got_tokens = summary_tokens
--- a/tests/routes/test_messages.py
+++ b/tests/routes/test_messages.py
@ -1,3 +1,4 @@
+import datetime
 from unittest.mock import patch

 import pytest
@ -921,3 +922,219 @@ async def test_create_messages_with_file_too_large(

        # Should raise FileTooLargeError which gets converted to 413
        assert response.status_code == 413
+
+
+@pytest.mark.asyncio
+async def test_create_message_with_timestamp(
+    client: TestClient, db_session: AsyncSession, sample_data: tuple[Workspace, Peer]
+):
+    """Test creating a message with custom timestamp"""
+    test_workspace, test_peer = sample_data
+
+    # Create a test session
+    test_session = models.Session(
+        workspace_name=test_workspace.name, name=str(generate_nanoid())
+    )
+    db_session.add(test_session)
+    await db_session.commit()
+
+    # Use a specific timestamp for testing
+    custom_timestamp = datetime.datetime(
+        2023, 1, 1, 12, 0, 0, tzinfo=datetime.timezone.utc
+    )
+
+    response = client.post(
+        f"/v2/workspaces/{test_workspace.name}/sessions/{test_session.name}/messages",
+        json={
+            "messages": [
+                {
+                    "content": "Test message with timestamp",
+                    "peer_id": test_peer.name,
+                    "created_at": custom_timestamp.isoformat(),
+                    "metadata": {"test": "with_timestamp"},
+                }
+            ]
+        },
+    )
+    assert response.status_code == 200
+    data = response.json()
+    assert len(data) == 1
+    message = data[0]
+    assert message["content"] == "Test message with timestamp"
+    assert message["peer_id"] == test_peer.name
+    assert message["metadata"] == {"test": "with_timestamp"}
+
+    # Verify the created_at field matches our custom timestamp
+    # Pydantic serializes UTC timezone as 'Z' format (ISO 8601 standard)
+    expected_timestamp = "2023-01-01T12:00:00Z"
+    assert message["created_at"] == expected_timestamp
+
+
+@pytest.mark.asyncio
+async def test_create_message_without_timestamp_uses_default(
+    client: TestClient, db_session: AsyncSession, sample_data: tuple[Workspace, Peer]
+):
+    """Test creating a message without timestamp uses default timestamp"""
+    test_workspace, test_peer = sample_data
+
+    # Create a test session
+    test_session = models.Session(
+        workspace_name=test_workspace.name, name=str(generate_nanoid())
+    )
+    db_session.add(test_session)
+    await db_session.commit()
+
+    # Record time before request
+    before_request = datetime.datetime.now(datetime.timezone.utc)
+
+    response = client.post(
+        f"/v2/workspaces/{test_workspace.name}/sessions/{test_session.name}/messages",
+        json={
+            "messages": [
+                {
+                    "content": "Test message without timestamp",
+                    "peer_id": test_peer.name,
+                    "metadata": {"test": "no_timestamp"},
+                }
+            ]
+        },
+    )
+
+    # Record time after request
+    after_request = datetime.datetime.now(datetime.timezone.utc)
+
+    assert response.status_code == 200
+    data = response.json()
+    assert len(data) == 1
+    message = data[0]
+    assert message["content"] == "Test message without timestamp"
+    assert message["peer_id"] == test_peer.name
+    assert message["metadata"] == {"test": "no_timestamp"}
+
+    # Verify the created_at field is between our before/after times
+    message_created_at = datetime.datetime.fromisoformat(
+        message["created_at"].replace("Z", "+00:00")
+    )
+    assert before_request <= message_created_at <= after_request
+
+
+@pytest.mark.asyncio
+async def test_create_batch_messages_with_mixed_timestamps(
+    client: TestClient, db_session: AsyncSession, sample_data: tuple[Workspace, Peer]
+):
+    """Test creating batch messages with some having custom timestamps and others using default"""
+    test_workspace, test_peer = sample_data
+
+    # Create a test session
+    test_session = models.Session(
+        workspace_name=test_workspace.name, name=str(generate_nanoid())
+    )
+    db_session.add(test_session)
+    await db_session.commit()
+
+    # Use specific timestamps for testing
+    timestamp1 = datetime.datetime(2023, 1, 1, 12, 0, 0, tzinfo=datetime.timezone.utc)
+    timestamp2 = datetime.datetime(2023, 1, 2, 12, 0, 0, tzinfo=datetime.timezone.utc)
+
+    # Record time before request for default timestamp
+    before_request = datetime.datetime.now(datetime.timezone.utc)
+
+    response = client.post(
+        f"/v2/workspaces/{test_workspace.name}/sessions/{test_session.name}/messages",
+        json={
+            "messages": [
+                {
+                    "content": "Message 1 with timestamp",
+                    "peer_id": test_peer.name,
+                    "created_at": timestamp1.isoformat(),
+                    "metadata": {"type": "custom_timestamp"},
+                },
+                {
+                    "content": "Message 2 without timestamp",
+                    "peer_id": test_peer.name,
+                    "metadata": {"type": "default_timestamp"},
+                },
+                {
+                    "content": "Message 3 with timestamp",
+                    "peer_id": test_peer.name,
+                    "created_at": timestamp2.isoformat(),
+                    "metadata": {"type": "custom_timestamp"},
+                },
+            ]
+        },
+    )
+
+    after_request = datetime.datetime.now(datetime.timezone.utc)
+
+    assert response.status_code == 200
+    data = response.json()
+    assert len(data) == 3
+
+    # Check first message with custom timestamp
+    assert data[0]["content"] == "Message 1 with timestamp"
+    assert (
+        data[0]["created_at"] == "2023-01-01T12:00:00Z"
+    )  # Pydantic converts to Z format
+    assert data[0]["metadata"] == {"type": "custom_timestamp"}
+
+    # Check second message with default timestamp
+    assert data[1]["content"] == "Message 2 without timestamp"
+    message2_created_at = datetime.datetime.fromisoformat(
+        data[1]["created_at"].replace("Z", "+00:00")
+    )
+    assert before_request <= message2_created_at <= after_request
+    assert data[1]["metadata"] == {"type": "default_timestamp"}
+
+    # Check third message with custom timestamp
+    assert data[2]["content"] == "Message 3 with timestamp"
+    assert (
+        data[2]["created_at"] == "2023-01-02T12:00:00Z"
+    )  # Pydantic converts to Z format
+    assert data[2]["metadata"] == {"type": "custom_timestamp"}
+
+
+@pytest.mark.asyncio
+async def test_create_message_with_null_timestamp(
+    client: TestClient, db_session: AsyncSession, sample_data: tuple[Workspace, Peer]
+):
+    """Test creating a message with null timestamp uses default"""
+    test_workspace, test_peer = sample_data
+
+    # Create a test session
+    test_session = models.Session(
+        workspace_name=test_workspace.name, name=str(generate_nanoid())
+    )
+    db_session.add(test_session)
+    await db_session.commit()
+
+    # Record time before request
+    before_request = datetime.datetime.now(datetime.timezone.utc)
+
+    response = client.post(
+        f"/v2/workspaces/{test_workspace.name}/sessions/{test_session.name}/messages",
+        json={
+            "messages": [
+                {
+                    "content": "Test message with null timestamp",
+                    "peer_id": test_peer.name,
+                    "created_at": None,
+                    "metadata": {"test": "null_timestamp"},
+                }
+            ]
+        },
+    )
+
+    after_request = datetime.datetime.now(datetime.timezone.utc)
+
+    assert response.status_code == 200
+    data = response.json()
+    assert len(data) == 1
+    message = data[0]
+    assert message["content"] == "Test message with null timestamp"
+    assert message["metadata"] == {"test": "null_timestamp"}
+
+    # Verify the created_at field uses default (current time)
+    message_created_at = datetime.datetime.fromisoformat(
+        message["created_at"].replace("Z", "+00:00")
+    )
+    assert before_request <= message_created_at <= after_request
--- a/tests/routes/test_sessions.py
+++ b/tests/routes/test_sessions.py
@ -784,7 +784,7 @@ def test_get_session_context(client: TestClient, sample_data: tuple[Workspace, P
    assert "summary" in data
    assert data["id"] == session_id
    assert isinstance(data["messages"], list)
-    assert data["summary"] == ""  # Default is empty when summary=False
+    assert data["summary"] is None  # No summary available


 def test_get_session_context_with_summary(
@ -855,6 +855,55 @@ def test_get_session_context_with_all_params(
    assert "summary" in data


+def test_get_session_summaries(
+    client: TestClient, sample_data: tuple[Workspace, Peer]
+) -> None:
+    """Test getting summaries for a valid session"""
+    test_workspace, test_peer = sample_data
+    session_id = str(generate_nanoid())
+
+    # Create session
+    client.post(
+        f"/v2/workspaces/{test_workspace.name}/sessions",
+        json={"id": session_id, "peers": {test_peer.name: {}}},
+    )
+
+    # Get summaries
+    response = client.get(
+        f"/v2/workspaces/{test_workspace.name}/sessions/{session_id}/summaries",
+    )
+    assert response.status_code == 200
+    data = response.json()
+
+    # Validate response structure
+    assert "id" in data
+    assert data["id"] == session_id
+    assert "short_summary" in data
+    assert "long_summary" in data
+    # Summaries will be None since they're created asynchronously
+    assert data["short_summary"] is None
+    assert data["long_summary"] is None
+
+
+def test_get_session_summaries_nonexistent_session(
+    client: TestClient, sample_data: tuple[Workspace, Peer]
+) -> None:
+    """Test getting summaries for a non-existent session"""
+    test_workspace, _ = sample_data
+    nonexistent_session_id = str(generate_nanoid())
+
+    # Try to get summaries for non-existent session
+    # Should still return 200 with null summaries
+    response = client.get(
+        f"/v2/workspaces/{test_workspace.name}/sessions/{nonexistent_session_id}/summaries",
+    )
+    assert response.status_code == 200
+    data = response.json()
+    assert data["id"] == nonexistent_session_id
+    assert data["short_summary"] is None
+    assert data["long_summary"] is None
+
+
 def test_search_session(client: TestClient, sample_data: tuple[Workspace, Peer]):
    """Test the session search functionality"""
    test_workspace, test_peer = sample_data
--- a/uv.lock
+++ b/uv.lock
@ -1,5 +1,5 @@
 version = 1
-revision = 2
+revision = 3
 requires-python = ">=3.10"
 resolution-markers = [
    "python_full_version >= '3.13'",
@ -7,6 +7,12 @@ resolution-markers = [
    "python_full_version < '3.11'",
 ]

+[manifest]
+members = [
+    "honcho",
+    "honcho-ai",
+]
+
 [[package]]
 name = "alembic"
 version = "1.16.4"
@ -822,7 +828,7 @@ wheels = [

 [[package]]
 name = "honcho"
-version = "2.2.0"
+version = "2.3.0"
 source = { virtual = "." }
 dependencies = [
    { name = "alembic" },
@ -853,7 +859,6 @@ dev = [
    { name = "basedpyright" },
    { name = "coverage" },
    { name = "honcho-ai" },
-    { name = "honcho-core" },
    { name = "interrogate" },
    { name = "pre-commit" },
    { name = "py-spy" },
@ -893,8 +898,7 @@ requires-dist = [
 dev = [
    { name = "basedpyright", specifier = ">=1.29.4" },
    { name = "coverage", specifier = ">=7.6.0" },
-    { name = "honcho-ai", specifier = "==1.3.0" },
-    { name = "honcho-core", specifier = "==1.3.0" },
+    { name = "honcho-ai", editable = "sdks/python" },
    { name = "interrogate", specifier = ">=1.7.0" },
    { name = "pre-commit", specifier = ">=4.2.0" },
    { name = "py-spy", specifier = ">=0.3.14" },
@ -907,21 +911,32 @@ dev = [

 [[package]]
 name = "honcho-ai"
-version = "1.3.0"
-source = { registry = "https://pypi.org/simple" }
+version = "1.4.0"
+source = { editable = "sdks/python" }
 dependencies = [
    { name = "honcho-core" },
    { name = "httpx" },
    { name = "pydantic" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/a3/d3/c882f95637e30124c57a3496ac8221865c2449323f5bd6823009658ce8f7/honcho_ai-1.3.0.tar.gz", hash = "sha256:674440071ae66f3382c7a2355e1c9e8a2c9f0f9482ca0633151d30d42b20ea2c", size = 25042, upload-time = "2025-08-06T21:49:15.655Z" }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/dc/f9/0d3c71f4a400da433119eabfb03837a00f1badd31994d578e4fdc9f95c1f/honcho_ai-1.3.0-py3-none-any.whl", hash = "sha256:cb610384956752a8a33f7dee1a01f10b7732c76417b72c87f0d91dea2acd1174", size = 32599, upload-time = "2025-08-06T21:49:14.418Z" },
+
+[package.dev-dependencies]
+dev = [
+    { name = "ruff" },
 ]

+[package.metadata]
+requires-dist = [
+    { name = "honcho-core", specifier = ">=1.4.0" },
+    { name = "httpx", specifier = ">=0.28.0,<1" },
+    { name = "pydantic", specifier = ">=2.0.0,<3" },
+]
+
+[package.metadata.requires-dev]
+dev = [{ name = "ruff", specifier = ">=0.11.13" }]
+
 [[package]]
 name = "honcho-core"
-version = "1.3.0"
+version = "1.4.0"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
    { name = "anyio" },
@ -931,9 +946,9 @@ dependencies = [
    { name = "sniffio" },
    { name = "typing-extensions" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/ee/49/1810de2351be1fdff330ffadcc5eef709889b2f698b0340966cae2c1eef9/honcho_core-1.3.0.tar.gz", hash = "sha256:276a73e8d523f7d22f06746922fda97e4a11fbbef4a51a0b43573bc817089cec", size = 123333, upload-time = "2025-08-06T16:42:10.941Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/71/c2/4d3737d5c0a75e2f59f324bed7428a9593c8edfcb7500cf402c46ad7378a/honcho_core-1.4.0.tar.gz", hash = "sha256:b30de9247763c01c3c37ed22b5d04d3c611440dd1983168f3d7d93f2cc0ecf7d", size = 126164, upload-time = "2025-08-12T19:06:54.828Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/6e/3f/3beb750ed65bb1b604c585ae1c51a54f8b34ea3002f4525f93fe86549531/honcho_core-1.3.0-py3-none-any.whl", hash = "sha256:c7c0bf77b61162e6c65a580327fc054785aef794923abc35acd3dbd8287245db", size = 112895, upload-time = "2025-08-06T16:42:08.967Z" },
+    { url = "https://files.pythonhosted.org/packages/c1/ac/6eb2e38376736bb1dfd26bbdfd96490bfbb6f0ddcb00b39913e93799e7d8/honcho_core-1.4.0-py3-none-any.whl", hash = "sha256:a84397fd9daf546a04f5458d7233ebd5eeafcb97af75ec60a9327db89abdaf03", size = 117602, upload-time = "2025-08-12T19:06:53.667Z" },
 ]

 [[package]]