release v0.6.0 at 2026-06-26 17:30:36 UTC

Author: CallumHYoung

.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "google-agents-cli",
-  "version": "0.5.1",
+  "version": "0.6.0",
   "description": "Scaffold, develop, evaluate, and deploy AI agents with Google ADK. Bundles 7 skills for the agent development lifecycle.",
   "author": { "name": "Google LLC" },
   "homepage": "https://github.com/google/agents-cli",

RELEASE_NOTES.md

@@ -2,6 +2,11 @@
 
 All notable changes to this project will be documented in this file.
 
+## [0.6.0] - 2026-06-23
+- Agent Runtime deploys now serve ADK web, A2A, and the reasoning engine from a single unified container app.
+- Cloud Trace spans no longer capture LLM prompts and responses, keeping sensitive content out of traces.
+- Refreshed the bundled skills: correctness fixes, de-duplication, and a leaner always-active workflow guide, plus a2ui documented in the ADK code cheatsheet.
+
 ## [0.5.1] - 2026-06-18
 - Fixed run and playground commands on Windows
   - https://github.com/google/agents-cli/issues/34

docs/src/guide/deployment.md

@@ -32,7 +32,7 @@ gcloud config set project YOUR_DEV_PROJECT_ID
 agents-cli deploy
 ```
 
-The command reads your `deployment_target` from `pyproject.toml` and dispatches to the right flow:
+The command reads your `deployment_target` from `agents-cli-manifest.yaml` (under `create_params`) and dispatches to the right flow:
 
 | `deployment_target`  | What happens                                  |
 |----------------------|-----------------------------------------------|
@@ -70,14 +70,20 @@ agents-cli deploy --status  # Check deployment status
 
 ### Agent Runtime
 
-*Selected with `agents-cli create my-agent -d agent_runtime` or `deployment_target = "agent_runtime"` in `pyproject.toml`.*
+*Selected with `agents-cli create my-agent -d agent_runtime`, or `create_params.deployment_target: agent_runtime` in `agents-cli-manifest.yaml`.*
 
-Fully managed — no containers or infrastructure to manage:
+Fully managed runtime: you provide a `Dockerfile` (scaffolded for you) and Agent Engine builds and runs the container — no cluster or service to operate:
 
 ```bash
 agents-cli deploy --project my-gcp-project --region us-east1
 ```
 
+Pass Docker build args or a container port; a prebuilt `--image` is not supported (Agent Runtime always builds from the Dockerfile):
+
+```bash
+agents-cli deploy --build-args KEY=VALUE --port 8080
+```
+
 Check on an async deployment:
 
 ```bash
@@ -87,7 +93,7 @@ agents-cli deploy --status      # Check progress later
 
 ### Cloud Run
 
-*Selected with `agents-cli create my-agent -d cloud_run` or `deployment_target = "cloud_run"` in `pyproject.toml`.*
+*Selected with `agents-cli create my-agent -d cloud_run`, or `create_params.deployment_target: cloud_run` in `agents-cli-manifest.yaml`.*
 
 Builds a container from source and deploys as a Cloud Run service:
 
@@ -112,7 +118,7 @@ agents-cli deploy --image gcr.io/my-project/my-agent:v1
 
 ### GKE
 
-*Selected with `agents-cli create my-agent -d gke` or `deployment_target = "gke"` in `pyproject.toml`.*
+*Selected with `agents-cli create my-agent -d gke`, or `create_params.deployment_target: gke` in `agents-cli-manifest.yaml`.*
 
 Deploys to a GKE cluster using Terraform and kubectl:
 

docs/src/guide/development.md

@@ -27,7 +27,7 @@ Create a new project from a template:
 agents-cli create my-agent
 ```
 
-Choose your agent template (`adk`, `adk_a2a`, `agentic_rag`) and deployment target during creation. For fast prototyping without infrastructure decisions:
+Choose your agent template (`adk`, `agentic_rag`) and deployment target during creation. For fast prototyping without infrastructure decisions:
 
 ```bash
 agents-cli create my-agent --prototype --yes

docs/src/guide/getting-started.md

@@ -208,7 +208,7 @@ For a full walkthrough, see the [Manual Workflow Tutorial](hands-on-tutorial.md)
 - [Tutorial: Manual Workflow](hands-on-tutorial.md) — type every command yourself
 - [Use Cases](use-cases.md) — get inspired by real agent patterns people build
 - [Project Structure](project-structure.md) — understand what each generated file does
-- [Agent Templates](templates.md) — choose the right template (`adk`, `adk_a2a`, `agentic_rag`)
+- [Agent Templates](templates.md) — choose the right template (`adk`, `agentic_rag`)
 - [Development Guide](development.md) — full development workflow
 - [CLI Reference](../cli/index.md) — all commands and flags
 

docs/src/guide/lifecycle.md

@@ -126,7 +126,7 @@ The single-agent body works while the problem is small. Real production agents g
 
 Splitting helps for three reasons that show up in eval, deploy, and observe: smaller prompts make each agent more reliable, separate tool surfaces let you apply per-agent guardrails, and the trace tells you exactly which sub-agent took the bad turn.
 
-When the team needs to span processes — or call agents your team doesn't own — use the **[A2A protocol](https://a2a-protocol.org/)** as the wire format. Scaffold with `--agent adk_a2a` and any A2A-compatible agent (built with Agents CLI or not) can call yours, and yours can call theirs.
+When the team needs to span processes — or call agents your team doesn't own — use the **[A2A protocol](https://a2a-protocol.org/)** as the wire format. A2A is built into every ADK agent, so just scaffold normally (`--agent adk`): any A2A-compatible agent (built with Agents CLI or not) can call yours, and yours can call theirs.
 
 ### 4 · Evaluate
 
@@ -245,7 +245,7 @@ See [Observability](observability/index.md) for the full setup.
 
 ## Where to dig deeper
 
-- [Templates](templates.md) — full list of scaffold templates (`adk`, `adk_a2a`, `agentic_rag`, …)
+- [Templates](templates.md) — full list of scaffold templates (`adk`, `agentic_rag`, …)
 - [Project Structure](project-structure.md) — what each generated file does
 - [Development Guide](development.md) — day-to-day workflow
 - [Evaluation Guide](evaluation.md) — dataset schema, the eval-fix loop

docs/src/guide/observability/bq-agent-analytics.md

@@ -25,7 +25,8 @@ Compared to the always-on [Cloud Trace telemetry](cloud-trace.md), this plugin p
 
 ## Prerequisites
 
-*   Agent project generated with an **ADK-based** template (e.g., `adk`, `adk_a2a`, `agentic_rag`).
+*   Agent project generated with an **ADK-based** template (e.g., `adk`, `agentic_rag`).
+*   `google-adk` version `>=1.21.0` (added automatically when you enable the plugin).
 *   A Google Cloud project with BigQuery API and BigQuery Storage API enabled (typically handled by Terraform).
 
 ---

docs/src/guide/quickstart-tutorial.md

@@ -164,7 +164,7 @@ The skills gave your coding agent the context to make the right decisions at eac
 Try building something more complex:
 
 - Add tools — *"Add a Google Search tool so the caveman can grunt about current events"*
-- Multi-agent — *"Create an A2A agent that other agents can talk to"* (use `adk_a2a` template)
+- Multi-agent — *"Create an A2A agent that other agents can talk to"* (use the `adk` template — A2A is built in)
 - RAG — *"Build an agent that answers questions from our docs"* (use `agentic_rag` template)
 
 See [Agent Templates](templates.md) for all options, or jump to the [Development Guide](development.md) for the full workflow.

docs/src/guide/templates.md

@@ -9,7 +9,6 @@
 | Template | Description | Use Case |
 |----------|-------------|----------|
 | `adk` | ReAct agent using ADK | General-purpose conversational agent with tool use |
-| `adk_a2a` | ADK agent with A2A protocol | Distributed multi-agent systems that communicate across frameworks |
 | `agentic_rag` | ADK agent with RAG pipeline | Document Q&A with automated data ingestion |
 
 ### adk
@@ -20,13 +19,7 @@ The default template. Creates a ReAct agent using the [Agent Development Kit](ht
 agents-cli create my-agent --agent adk
 ```
 
-### adk_a2a
-
-Extends the base `adk` template with [Agent-to-Agent (A2A) protocol](https://a2a-protocol.org) support. Use this when your agent needs to interoperate with agents built on other frameworks (LangGraph, CrewAI, etc.) or when building a distributed multi-agent system.
-
-```bash
-agents-cli create my-agent --agent adk_a2a
-```
+Every Python ADK agent serves the [Agent-to-Agent (A2A) protocol](https://a2a-protocol.org) out of the box — the A2A routes (agent card + JSON-RPC) are mounted automatically. Use this when your agent needs to interoperate with agents built on other frameworks (LangGraph, CrewAI, etc.) or when building a distributed multi-agent system; no separate template or hand-written A2A code is required.
 
 ### agentic_rag
 

docs/src/guide/use-cases.md

@@ -170,19 +170,19 @@ Build a RAG agent that drafts RFP responses by pulling from past proposals, curr
 
 ### Incident Response Coordination
 
-*Advanced (A2A) · `adk_a2a`*
+*Advanced (A2A) · `adk`*
 
 Run specialist agents in parallel during an outage: one bisects recent changes, one correlates errors across services, one searches past incidents, and one drafts customer communications. Parallel investigation reduces time-to-cause compared to sequential troubleshooting.
 
 ```
 Build an A2A multi-agent system for incident response. Specialists for bisection, error correlation, past-incident lookup, and customer comms — coordinated in parallel.
 ```
 
-The [`adk_a2a` template](templates.md) wires up the A2A protocol. Each specialist runs as a service, and the coordinator orchestrates execution.
+The [`adk` template](templates.md) (A2A built in) exposes the A2A protocol. Each specialist runs as a service, and the coordinator orchestrates execution.
 
 ### Distributed Code Migration
 
-*Advanced (A2A) · `adk_a2a`*
+*Advanced (A2A) · `adk`*
 
 Run specialist agents for a large framework migration: one handles data models, one handles API contracts, one handles tests, and one handles validation. Specialists coordinate over A2A to share findings about breaking changes. GKE is the recommended runtime when running many concurrent specialist instances.
 
@@ -196,6 +196,6 @@ Build A2A specialist agents for a large framework migration: data models, API co
 
 - [Tutorial: Build Your First Agent](quickstart-tutorial.md) — build, evaluate, and deploy with your coding agent
 - [Project Structure](project-structure.md) — understand what each generated file does
-- [Agent Templates](templates.md) — choose the right template (`adk`, `adk_a2a`, `agentic_rag`)
+- [Agent Templates](templates.md) — choose the right template (`adk`, `agentic_rag`)
 - [Development Guide](development.md) — full development workflow
 - [CLI Reference](../cli/index.md) — all commands and flags