You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: docs/config.md
+26Lines changed: 26 additions & 0 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -5,6 +5,28 @@
5
5
6
6
# 📋 Configuration schema
7
7
8
+
## A2AStateConfiguration
9
+
10
+
11
+
A2A protocol persistent state configuration.
12
+
13
+
Configures how A2A task state and context-to-conversation mappings are
14
+
stored. For multi-worker deployments, use SQLite or PostgreSQL to ensure
15
+
state is shared across all workers.
16
+
17
+
If no configuration is provided, in-memory storage is used (default).
18
+
This is suitable for single-worker deployments but state will be lost
19
+
on restarts and not shared across workers.
20
+
21
+
Attributes:
22
+
sqlite: SQLite database configuration for A2A state storage.
23
+
postgres: PostgreSQL database configuration for A2A state storage.
24
+
25
+
26
+
| Field | Type | Description |
27
+
|-------|------|-------------|
28
+
| sqlite || SQLite database configuration for A2A state storage. |
29
+
| postgres || PostgreSQL database configuration for A2A state storage. |
8
30
9
31
10
32
## APIKeyTokenConfiguration
@@ -128,6 +150,7 @@ Global service configuration.
128
150
| inference || One LLM provider and one its model might be selected as default ones. When no provider+model pair is specified in REST API calls (query endpoints), the default provider and model are used. |
129
151
| conversation_cache |||
130
152
| byok_rag | array | BYOK RAG configuration. This configuration can be used to reconfigure Llama Stack through its run.yaml configuration file |
153
+
| a2a_state || Configuration for A2A protocol persistent state storage. |
0 commit comments