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
{{ message }}
Repository navigation
Commit f8bc87a
Browse filesBrowse the repository at this point in the historyBrowse files
| Prompt | System or user prompt sent to a model |
@@ -201,6 +199,14 @@ Translatable companions (do NOT belong in DNT — translate to Chinese):
201
199
| English | Chinese |
202
200
|---------|---------|
203
201
| Artifact / Artifacts | 产物 |
202
+
| Knowledge | 知识库 — the DUTY.md-rooted file tree an account or team maintains for AI SRE. Formerly "Knowledge Pack"; do not use that name in copy. Running text uses lowercase "knowledge" (e.g., "team knowledge"); API identifiers such as `pack_id` and `knowledge-pack-*` CLI commands stay unchanged |
203
+
| Memory | 记忆 |
204
+
| Context | 上下文 — the Customize group holding Knowledge and Memory |
205
+
| Customize | 自定义 — the AI SRE sidebar entry that opens Context, Plugins, and Environments |
Copy file name to clipboardExpand all lines: en/ai-sre/agents.mdx
+4-4Lines changed: 4 additions & 4 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -30,7 +30,7 @@ Delegation does not make you wait: after AI SRE hands a task to a remote agent,
30
30
**Instructions have two levels and act as the agent-selection signal.** Before delegating, AI SRE sees a list of available agents where each entry is just `name: summary` — the summary comes from a `summary:` line at the top of the instructions (if omitted, the beginning of the body is excerpted automatically). AI SRE uses it to decide **whether and when** to delegate to this agent, so state clearly when to prefer it, what it excels at, and what it is not suited for. The body that follows the summary is not kept in the list — it is delivered to AI SRE in full only the **first time it delegates to this agent**, so you can write it as long and detailed as needed (procedures, hard rules, examples) without slowing down everyday conversations. See "[Writing Instructions](#writing-instructions)" below for the format.
31
31
</Tip>
32
32
33
-
The A2A agent list and management entry point are on the **Plugins → Agents** page (menu tab labeled **Agents**).
33
+
The A2A agent list and management entry point are on the **Customize → Plugins → Agents** page (menu tab labeled **Agents**).
34
34
35
35
<Note>
36
36
**Agents covers two distinct concepts.** This page (Agents) currently manages **A2A Agents** (external agent-to-agent calls). The other concept is the **Subagent** — a platform-built-in task executor that AI SRE dispatches on demand within a session. Subagents have no create / edit entry point; you only observe their behavior in sessions. See "[Subagent](#subagent)" below.
@@ -279,7 +279,7 @@ When a session **enters via an incident route** (e.g., AI SRE is triggered from
279
279
280
280
---
281
281
282
-
The full lifecycle of A2A agents is managed on the **Plugins → Agents** page.
282
+
The full lifecycle of A2A agents is managed on the **Customize → Plugins → Agents** page.
283
283
284
284
<AccordionGroup>
285
285
<Accordion title="Create" icon="plus">
@@ -303,7 +303,7 @@ The full lifecycle of A2A agents is managed on the **Plugins → Agents** page.
303
303
304
304
---
305
305
306
-
A2A agents share the same **two-level scope** model as other resources (skills, Knowledge Packs, MCP, environments), divided into account level and team level. In the console UI, the account-level option is labeled "**Shared**" / "**Shared scope**" — synonymous with account level (visible account-wide):
306
+
A2A agents share the same **two-level scope** model as other resources (skills, Knowledge, MCP, environments), divided into account level and team level. In the console UI, the account-level option is labeled "**Shared**" / "**Shared scope**" — synonymous with account level (visible account-wide):
307
307
308
308
| Scope | Visibility |
309
309
| --- | --- |
@@ -328,7 +328,7 @@ A2A agents share the same **two-level scope** model as other resources (skills,
328
328
Connect external tools to agents to expand their capability boundary during tasks.
Copy file name to clipboardExpand all lines: en/ai-sre/apps.mdx
+6-6Lines changed: 6 additions & 6 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -31,10 +31,10 @@ AI SRE sessions run in a **Flashduty cloud sandbox** by default. The sandbox is
31
31
32
32
---
33
33
34
-
Go to **Plugins → Apps**. Opening the Plugins area lands on the **Overview** tab by default; Apps is one of its tabs (the tab order is Overview / Apps / Skill / MCP / Agents).
34
+
Go to **AI SRE → Customize → Plugins → Apps**. The Plugins group in the Customize sidebar lists Overview / Apps / Skill / MCP / Agents in that order, and clicking **Customize** opens **Overview** by default.
35
35
36
36
<Note>
37
-
Viewing the Apps tab requires the appropriate permission; without it, the tab is hidden. Authorizing, disconnecting / revoking, and enabling / disabling each require their own action permission — when you lack one, the corresponding button is shown disabled.
37
+
Viewing the Apps page requires the appropriate permission; without it, the entry is hidden from the sidebar. Authorizing, disconnecting / revoking, and enabling / disabling each require their own action permission — when you lack one, the corresponding button is shown disabled.
38
38
</Note>
39
39
40
40
## Kubernetes Apps
@@ -47,7 +47,7 @@ A Kubernetes App connects an in-cluster agent to AI SRE. After installation, AI
47
47
48
48
<Steps>
49
49
<Steptitle="Create a Kubernetes App">
50
-
Go to **Plugins → Apps → Kubernetes Apps** and click **Create Kubernetes App**. Enter a cluster name and choose its scope: **Shared** is available to all sessions in the account; **Team** is available to that team's sessions and to personal sessions of its members. Cluster names must be unique within a scope.
50
+
Go to **Customize → Plugins → Apps → Kubernetes Apps** and click **Create Kubernetes App**. Enter a cluster name and choose its scope: **Shared** is available to all sessions in the account; **Team** is available to that team's sessions and to personal sessions of its members. Cluster names must be unique within a scope.
51
51
</Step>
52
52
<Steptitle="Set namespace access">
53
53
Choose **All namespaces** or **Specific namespaces**. All namespaces applies one permission level to current and future namespaces. With specific namespaces, set **Read-only**, **Read + limited modifications**, or **Full access** for each namespace. Leaving the specific-namespace list empty allows the agent to read only basic cluster metadata. **Full access** is the highest level within the namespace: on a specific namespace it applies only inside that namespace (cluster metadata stays read-only), while **All namespaces + Full access** grants `cluster-admin` via a `ClusterRoleBinding`, including cluster-scoped resources and cluster RBAC (available only with All namespaces). See [Permission details](#permission-details) below for what each level can do; open **View Kubernetes RBAC details** in the form for the complete RBAC rules.
@@ -142,10 +142,10 @@ Each authorized organization adds one installation row under the GitHub card. Ea
142
142
143
143
### Adding or Adjusting Repository Access
144
144
145
-
The organization is already connected, but you want AI SRE to reach more of its repositories — you don't need to revoke and reconnect. In **Plugins → Apps**, click **More repositories** again for that organization (or open the App's **Configure** page on GitHub directly). GitHub shows the **Repository access** screen; select the additional repositories and save, and AI SRE **re-syncs** the granted repository list automatically — the new repositories become available without re-creating the connection.
145
+
The organization is already connected, but you want AI SRE to reach more of its repositories — you don't need to revoke and reconnect. In **Customize → Plugins → Apps**, click **More repositories** again for that organization (or open the App's **Configure** page on GitHub directly). GitHub shows the **Repository access** screen; select the additional repositories and save, and AI SRE **re-syncs** the granted repository list automatically — the new repositories become available without re-creating the connection.
146
146
147
147
<Note>
148
-
**Fallback**: if a newly added repository still reports "cannot access / 404 / 403" in a session, open the App's page on GitHub (e.g. `github.com/apps/flashduty`) → **Configure** → select the organization → scroll to the **Danger zone** → **Uninstall**. Then return to **Plugins → Apps** in Flashduty and authorize the organization again, granting **all** the repositories you need in one pass.
148
+
**Fallback**: if a newly added repository still reports "cannot access / 404 / 403" in a session, open the App's page on GitHub (e.g. `github.com/apps/flashduty`) → **Configure** → select the organization → scroll to the **Danger zone** → **Uninstall**. Then return to **Customize → Plugins → Apps** in Flashduty and authorize the organization again, granting **all** the repositories you need in one pass.
149
149
</Note>
150
150
151
151
## The GitLab App
@@ -226,7 +226,7 @@ After authorization, you need no extra configuration. When you ask AI SRE to wor
226
226
- Never delete branches, close others' issues / PRs / MRs, or change repository settings; never commit secrets, credentials, or build artifacts.
227
227
228
228
<Note>
229
-
If the agent reports it cannot access a repository in a cloud session, it usually means the account has not authorized the relevant App (GitHub or GitLab), or the target repository / group was not granted — just authorize and grant it under **Plugins → Apps**. The agent does **not** ask you for any token.
229
+
If the agent reports it cannot access a repository in a cloud session, it usually means the account has not authorized the relevant App (GitHub or GitLab), or the target repository / group was not granted — just authorize and grant it under **Customize → Plugins → Apps**. The agent does **not** ask you for any token.
description: Context is the long-lived material AI SRE carries into troubleshooting. People maintain the knowledge base. The system organizes memory. The Context page shows both, by scope.
3
+
description: Context is the long-lived material AI SRE carries into troubleshooting. People maintain knowledge. The system organizes memory. The console gives each its own page under Customize → Context.
@@ -13,34 +13,36 @@ sidebarTitle: Learn about Context
13
13
14
14
---
15
15
16
-
Context is the material AI SRE can reuse across troubleshooting sessions. It has two parts, shown together on the **Context**page.
16
+
Context is the material AI SRE can reuse across troubleshooting sessions. It has two parts, each with its own page under the **Context**group of the **AI SRE → Customize** sidebar.
17
17
18
-
-**Memory** is organized by the system. After a session, it keeps preferences, procedures, facts, and lessons that will still matter later. You can also ask, in the conversation, to remember or forget something.
19
-
- The **knowledge base** is maintained by people. It describes how this environment runs: a guide named `DUTY.md`, plus runbooks, service lists, and similar files. A session reads the guide first and opens the other files when it needs them.
18
+
-**[Knowledge](/en/ai-sre/knowledge)** is maintained by people. It describes how this environment runs: a guide named `DUTY.md`, plus runbooks, service lists, and similar files. A session reads the guide first and opens the other files when it needs them. Entry: **AI SRE → Customize → Context → Knowledge**.
19
+
-**[Memory](/en/ai-sre/memory)** is organized by the system. After a session, it keeps preferences, procedures, facts, and lessons that will still matter later. You can also ask, in the conversation, to remember or forget something. Entry: **AI SRE → Customize → Context → Memory**.
20
+
21
+
Both pages have an input box at the bottom: write what to change, and the console opens a new chat where the AI first explains the change and saves it after you agree.
20
22
21
23
## Three scopes
22
24
23
25
---
24
26
25
-
You pick a scope first. That scope is what you can see here, and what the assistant is allowed to change.
27
+
Both kinds of material are organized by scope, but they support different scopes.
26
28
27
-
| Scope | Memory | Knowledge base |
29
+
| Scope | Memory | Knowledge |
28
30
| --- | --- | --- |
29
31
| Personal | Yours | None |
30
-
| Team | That team's |The pack that team already has|
32
+
| Team | That team's |That team's (at most one per team)|
31
33
| Shared | None | The whole account's |
32
34
33
-
Personal scope has no knowledge base. Shared scope has no memory.
35
+
Personal scope has no knowledge. Shared scope has no memory.
34
36
35
37
## Read next
36
38
37
39
---
38
40
39
41
<CardGroupcols={2}>
40
-
<Cardtitle="Learn about the knowledge base"icon="book"href="/en/ai-sre/knowledge">
42
+
<Cardtitle="Learn about Knowledge"icon="book"href="/en/ai-sre/knowledge">
41
43
How the guide, runbooks, and files are organized, and how the assistant reads them in a session.
42
44
</Card>
43
-
<Cardtitle="Learn about memory"icon="brain"href="/en/ai-sre/memory">
45
+
<Cardtitle="Learn about Memory"icon="brain"href="/en/ai-sre/memory">
44
46
How memory is gathered from conversations, what personal and team scopes each show, and how to edit or delete a file on the page.
0 commit comments