You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@flink.apache.org by we...@apache.org on 2026/10/22 10:59:24 UTC

(flink-agents) branch main updated: [docs] Clarify shared action scope and complete agent documentation (#1319)

This is an automated email from the ASF dual-hosted git repository.

wenjin272 pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/flink-agents.git


The following commit(s) were added to refs/heads/main by this push:
     new efd7b8f3c [docs] Clarify shared action scope and complete agent documentation (#1319)
efd7b8f3c is described below

commit efd7b8f3cdcf2d0efd3a9328b18990ae4b289c05
Author: Yi Zhang <72...@users.noreply.github.com>
AuthorDate: Thu Oct 22 18:59:18 2026 +0800

    [docs] Clarify shared action scope and complete agent documentation (#1319)
    
    Generated-by: Qoder
---
 .../docs/development/create-agent/choose-apis-and-languages.md    | 7 +++++++
 docs/content/docs/development/create-agent/events.md              | 1 +
 docs/content/docs/development/create-agent/yaml.md                | 8 +++++---
 3 files changed, 13 insertions(+), 3 deletions(-)

diff --git a/docs/content/docs/development/create-agent/choose-apis-and-languages.md b/docs/content/docs/development/create-agent/choose-apis-and-languages.md
index 4268595bc..49d1cca38 100644
--- a/docs/content/docs/development/create-agent/choose-apis-and-languages.md
+++ b/docs/content/docs/development/create-agent/choose-apis-and-languages.md
@@ -151,6 +151,13 @@ where supported and install its dependencies.
 | [Mem0]({{< ref "docs/development/vector-search/vector_stores/providers#mem0" >}}) | ✅ | ❌ |
 | [Milvus]({{< ref "docs/development/vector-search/vector_stores/providers#milvus" >}}) | ❌ | ✅ |
 
+**Decision Models**
+
+| Provider | Python | Java |
+|---|---|---|
+| [OpenAI]({{< ref "docs/development/decision_models" >}}) | ✅ | ❌ |
+| [TypeSafe]({{< ref "docs/development/decision_models" >}}) | ✅ | ❌ |
+
 **MCP Server**
 
 | Provider | Python | Java |
diff --git a/docs/content/docs/development/create-agent/events.md b/docs/content/docs/development/create-agent/events.md
index 0fbd094c3..22a58ef79 100644
--- a/docs/content/docs/development/create-agent/events.md
+++ b/docs/content/docs/development/create-agent/events.md
@@ -29,6 +29,7 @@ Events carry data between Actions. Each Event has:
 | `type` | Identifies the Event type used to match Actions. |
 | `attributes` | Holds the Event's payload as named values. |
 | `id` | Identifies the Event. A new ID is generated by default when the Event is created and cannot be changed afterward. |
+| `attachments` | Holds named data passed between Actions through [Sensory Memory]({{< ref "docs/development/memory/sensory_and_short_term_memory" >}}). Not supported by `OutputEvent`. |
 
 One Event can trigger multiple Actions. For matching by type or payload, see
 [Trigger Conditions]({{< ref "docs/development/create-agent/actions#trigger-conditions" >}}).
diff --git a/docs/content/docs/development/create-agent/yaml.md b/docs/content/docs/development/create-agent/yaml.md
index 3a08e2517..ea6988fb8 100644
--- a/docs/content/docs/development/create-agent/yaml.md
+++ b/docs/content/docs/development/create-agent/yaml.md
@@ -56,7 +56,7 @@ This section walks through:
 
 1. Declaring a single agent in one YAML file.
 2. Declaring multiple agents in one YAML file.
-3. Declaring shared Resources and Actions that any agent in the file (or any later-loaded file) can reuse.
+3. Declaring shared Resources and Actions that agents can reuse.
 4. Declaring sub-agents and referencing them from a parent Agent.
 
 ### Declaring a single agent
@@ -376,7 +376,9 @@ agents:
 
 ### Declaring and reusing shared Resources and Actions
 
-Any resource section (`prompts`, `tools`, `chat_model_connections`, ...) or `actions:` declared as a **top-level sibling** of `agents:` is **shared**: it is registered on the `AgentsExecutionEnvironment` itself, and any agent in the file — or in any file later loaded into the same environment — can reference it by name.
+Any resource section (`prompts`, `tools`, `chat_model_connections`, ...) declared as a **top-level sibling** of `agents:` is **shared**: it is registered on the `AgentsExecutionEnvironment` itself, and any agent in the file — or in any file later loaded into the same environment — can reference it by name.
+
+A top-level `actions:` list is shared only within its file: agents in the same file can reference these actions by name, but agents in other files cannot.
 
 **Shared resources** are referenced inside an agent simply by name:
 
@@ -437,7 +439,7 @@ actions:
 ```
 
 {{< hint info >}}
-Composing one agent across multiple YAML files is **not** supported. If two files loaded into the same environment declare the same agent name, or the same shared resource/action name, the second `load_yaml` call raises an error.
+Composing one agent across multiple YAML files is **not** supported. If two files loaded into the same environment declare the same agent name, or the same shared resource name, the second `load_yaml` call raises an error.
 {{< /hint >}}
 
 ### Declaring sub-agents