docs: update Learning Hub for Copilot CLI v1.0.66-68 (Jul 2026)

- Add kimi-k2.7-code model (v1.0.68+) to model selection table in
  building-custom-agents.md as a code generation option alongside GPT-4.1
- Document subagent tool filter inheritance (v1.0.67+, v1.0.68) in
  agents-and-subagents.md: parent agent tool restrictions are inherited
  by subagents throughout the entire delegation chain
- Add plan budget visibility note to copilot-configuration-basics.md:
  /usage and the status line now show remaining credit allowances for
  supported plans (v1.0.68+)

Sources:
- https://github.com/github/copilot-cli/releases/tag/v1.0.68
- https://github.com/github/copilot-cli/releases/tag/v1.0.67
- https://github.com/github/copilot-cli/releases/tag/v1.0.66

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

website/src/content/docs/learning-hub/agents-and-subagents.md

@@ -3,7 +3,7 @@ title: 'Agents and Subagents'
 description: 'Learn how delegated subagents differ from primary agents, when to use them, and how to launch them in VS Code and Copilot CLI.'
 authors:
   - GitHub Copilot Learning Hub Team
-lastUpdated: 2026-07-01
+lastUpdated: 2026-07-03
 estimatedReadingTime: '9 minutes'
 tags:
   - agents
@@ -45,6 +45,7 @@ Subagents are useful because they are not just "the same agent in another tab."
 - **Parallelism**: multiple subagents can work at the same time when tasks do not conflict.
 - **Controlled synthesis**: the parent agent decides what gets brought back into the main conversation.
 - **Alternative model selection**: the subagent can use a different AI model to perform a task, so while our main agent might be using a generalist model, a subagent could be configured to use a more specialized one for code review or research.
+- **Inherited tool restrictions** *(v1.0.67+)*: when a custom agent with limited tool access (e.g., read-only tools) spawns subagents, those subagents **inherit** the parent's tool restrictions. This means a security-scoped agent stays security-scoped throughout its entire delegation chain — subagents cannot silently gain access to tools the parent doesn't have.
 
 That isolation is one of the main reasons subagents can outperform a single monolithic agent on larger tasks.
 
@@ -212,6 +213,10 @@ No. They can run sequentially when one step depends on another, or in parallel w
 
 Yes. In v1.0.66+, usage-based billing users can configure **subagent concurrency and depth limits** directly from `/settings`. The concurrency limit controls how many subagents run in parallel; the depth limit controls how many levels deep delegation can chain (preventing runaway recursive subagent trees). These settings give you predictable control over resource consumption during complex orchestrated tasks.
 
+**Do custom agents' tool restrictions apply to their subagents?**
+
+Yes, since v1.0.67+. When a custom agent with a restricted tool set (for example, only `read` and `search`) spawns a subagent, the subagent inherits those same restrictions. In v1.0.68+, this inheritance is also preserved when the subagent itself launches further nested subagents. This is an important security guarantee: a read-only reviewer agent cannot accidentally or intentionally gain write access just by delegating to a subagent. Design your agents' tool lists with this in mind — the restrictions you set on a parent agent act as a security boundary for the entire delegation tree it controls.
+
 ## Next steps
 
 - Read [Building Custom Agents](../building-custom-agents/) to design coordinator and worker agents.

website/src/content/docs/learning-hub/building-custom-agents.md

@@ -3,7 +3,7 @@ title: 'Building Custom Agents'
 description: 'Learn how to create specialized GitHub Copilot agents with custom personas, tool integrations, and domain expertise.'
 authors:
   - GitHub Copilot Learning Hub Team
-lastUpdated: 2026-07-01
+lastUpdated: 2026-07-03
 estimatedReadingTime: '10 minutes'
 tags:
   - agents
@@ -256,7 +256,7 @@ The agent can then query your database, analyze query plans, and suggest optimiz
 |----------|-------------------|
 | Most demanding reasoning, security review | Claude Sonnet 5 *(v1.0.67+)* |
 | Complex reasoning, analysis | Claude Sonnet 4 |
-| Code generation, refactoring | GPT-4.1 |
+| Code generation, refactoring | GPT-4.1 or kimi-k2.7-code *(v1.0.68+)* |
 | Quick analysis, simple tasks | Claude Haiku or GPT-4.1-mini |
 | Large codebase understanding | Models with larger context windows |
 

website/src/content/docs/learning-hub/copilot-configuration-basics.md

@@ -3,7 +3,7 @@ title: 'Copilot Configuration Basics'
 description: 'Learn how to configure GitHub Copilot at user, workspace, and repository levels to optimize your AI-assisted development experience.'
 authors:
   - GitHub Copilot Learning Hub Team
-lastUpdated: 2026-06-30
+lastUpdated: 2026-07-03
 estimatedReadingTime: '10 minutes'
 tags:
   - configuration
@@ -603,7 +603,7 @@ The `/context` command shows a visualization of the current conversation's conte
 /context
 ```
 
-The `/usage` command displays session metrics such as the number of tokens consumed, API calls made, and any quota information for the current session. In v1.0.64+, `/usage` also shows per-model token totals when you have used multiple models in a session:
+The `/usage` command displays session metrics such as the number of tokens consumed, API calls made, and any quota information for the current session. In v1.0.64+, `/usage` also shows per-model token totals when you have used multiple models in a session. In v1.0.68+, `/usage` also shows **plan budget details** (remaining credit allowances) for supported plans, and these budget figures also appear in the status line so you can monitor consumption at a glance without opening `/usage`:
 
 ```
 /usage