fixes

Author: jcodella

README.md

@@ -10,7 +10,7 @@
 
 Agent Memory Toolkit is a Python library and Azure-backed reference implementation for storing, retrieving, and transforming agent memories over time. It combines a simple SDK for local and Cosmos DB operations with Durable Functions pipelines that generate thread summaries, extract facts, and build cross-thread user profiles. The toolkit also supports automatic processing via a Cosmos DB change feed trigger that fires these pipelines in the background when configurable message count thresholds are crossed. The toolkit is designed for agent applications that need both raw conversation history and higher-value derived memory that can be searched semantically later. It provides matching sync (`CosmosMemoryClient`) and async (`AsyncCosmosMemoryClient`) APIs so the same memory model can be used in scripts, services, notebooks, and larger agent systems.
 
-![Agent Memory Toolkit overview](overview.png)
+![Agent Memory Toolkit overview](Overview.png)
 
 ---
 

Samples/Notebooks/Demo_async.ipynb

@@ -2,12 +2,11 @@
 name: dedup
 description: Reconcile a pool of active facts — collapse duplicates and resolve semantic contradictions in one pass.
 model:
-  apiType: chat
-  options:
+  api: chat
+  parameters:
     temperature: 0.0
-    additionalProperties:
-      response_format:
-        type: json_object
+    response_format:
+      type: json_object
 inputs:
   facts_text:
     type: string

agent_memory_toolkit/prompts/dedup.prompty

@@ -2,12 +2,11 @@
 name: extract_memories
 description: Extract facts, procedural rules, and episodic memories from a conversation, reconciled against existing memories.
 model:
-  apiType: chat
-  options:
+  api: chat
+  parameters:
     temperature: 0.0
-    additionalProperties:
-      response_format:
-        type: json_object
+    response_format:
+      type: json_object
 inputs:
   existing_facts:
     type: string

agent_memory_toolkit/prompts/extract_memories.prompty

@@ -2,12 +2,11 @@
 name: summarize
 description: Produce a structured JSON summary of a single conversation thread.
 model:
-  apiType: chat
-  options:
+  api: chat
+  parameters:
     temperature: 0.2
-    additionalProperties:
-      response_format:
-        type: json_object
+    response_format:
+      type: json_object
 inputs:
   transcript:
     type: string

agent_memory_toolkit/prompts/summarize.prompty

@@ -2,12 +2,11 @@
 name: summarize_update
 description: Update an existing JSON thread summary with new messages.
 model:
-  apiType: chat
-  options:
+  api: chat
+  parameters:
     temperature: 0.2
-    additionalProperties:
-      response_format:
-        type: json_object
+    response_format:
+      type: json_object
 inputs:
   prior_summary:
     type: string

agent_memory_toolkit/prompts/summarize_update.prompty

@@ -2,12 +2,11 @@
 name: user_summary
 description: Build a structured JSON user profile from one or more conversation threads.
 model:
-  apiType: chat
-  options:
+  api: chat
+  parameters:
     temperature: 0.2
-    additionalProperties:
-      response_format:
-        type: json_object
+    response_format:
+      type: json_object
 inputs:
   transcript:
     type: string

agent_memory_toolkit/prompts/user_summary.prompty

@@ -2,12 +2,11 @@
 name: user_summary_update
 description: Update an existing JSON user profile with new conversation data.
 model:
-  apiType: chat
-  options:
+  api: chat
+  parameters:
     temperature: 0.2
-    additionalProperties:
-      response_format:
-        type: json_object
+    response_format:
+      type: json_object
 inputs:
   prior_summary:
     type: string