Skip to content

RELEASE_NOTES.md

Latest commit

 

History

History
302 lines (258 loc) · 23.6 KB

RELEASE_NOTES.md

File metadata and controls

302 lines (258 loc) · 23.6 KB
Raw

Release Notes

All notable changes to this project will be documented in this file.

[1.8.0] - 2026-09-30

  • New flag foragents-cli scaffold upgrade: --force. A fallback for when the 3-way merge cannot run or leaves too many conflicts, similar to the existing flag for agents-cli scaffold enhance. It generates only the new template and overwrites the scaffolding files:
    • Agent code, config files and files you own are kept: your tests, custom eval metrics, eval datasets, READMEs, agent guidance files, .gitignore, deployment_metadata.json and Terraform env.tfvars files.
    • Dependencies are merged as a union. For a dependency in both files the template's version wins, and dependencies only your project has are kept.
  • agents-cli scaffold upgrade keeps your Terraform env.tfvars files instead of treating them as template files.
  • agents-cli scaffold upgrade and agents-cli scaffold enhance stop with an error when writing the merged dependencies fails. Previously they reported success and stamped the new version, so a rerun said "already at version" and could not retry.
  • agents-cli run --mode a2a sends messages and your bearer token only to the --url host, not to the endpoint declared in the agent card.
  • Two concurrent agents-cli deploy deploys no longer overwrite each other's deployment state.
  • Clarified the documentation on when to use agents-cli infra single-project --apply for deployments.
  • Generated CI/CD Terraform for Cloud Build now waits for the CI/CD service account's IAM grants to propagate before creating build triggers, so the first push after agents-cli infra cicd no longer fails on missing permissions.
  • Generated CI/CD Terraform grants Artifact Registry read access on the app's own repository instead of the whole CI/CD project. Destroying one project's infrastructure no longer breaks image pulls for other projects sharing the CI/CD project. A deploy project that relied on the project-wide grant to read another repository loses that access.
  • agents-cli deploy prints pod state, pod descriptions and namespace events when a GKE rollout does not finish.
  • Changed the formatting of some error messages so that they stand out more.
  • Updated the ADK version in scaffolded projects to google-adk>=2.9.2,<3.0.0.
  • Added experimental usage telemetry, off by default. Enable it with AGENTS_CLI_EXPERIMENTS='{"cli_telemetry": true}'. It writes one log entry per command to your own Cloud project, with the command, exit code, error class, duration, and CLI, Python and OS versions (but not arguments). Opt out with AGENTS_CLI_TELEMETRY=0 or DO_NOT_TRACK=1.

[1.7.0] - 2026-09-22

  • Live (voice) agents now work in run and eval. Pass --mode adk_live wherever you already pass --mode adk:
    • agents-cli run --mode adk_live sends a prompt over ADK's /run_live WebSocket, against a local server or any deployment target. A turn that answers only in audio says so instead of printing nothing.
    • agents-cli eval generate and agents-cli eval run play each case over one persistent Live socket, with the same dataset format, trace output and grading as the SSE path.
    • The gemini-3.8-live models answer one prompt with several model turns. The CLI reads the end of a turn from interactionStatus instead of stopping at the first turnComplete.
    • The bundled skills cover Live: an ADK Live reference, which models support it, and how to deploy a voice agent.
  • agents-cli run --mode a2a talks A2A to the local server. A local run used to ignore --mode and always use ADK SSE.
  • agents-cli deploy --ingress sets Cloud Run ingress to all, internal or internal-and-cloud-load-balancing, so a deploy works in a project where constraints/run.allowedIngress rejects a public service.
  • agents-cli deploy updates the Agent Runtime engine whose resource id is recorded in deployment_metadata.json, and scans display names only when no id is recorded. A deleted engine, a display name that no longer matches, or a scan that finds duplicates stops the deploy instead of mutating the wrong engine.
  • agents-cli deploy and scaffolded Terraform both set identity_type = SERVICE_ACCOUNT on the Agent Runtime engine, so an agent keeps its service account when Agent Runtime changes that default to Agent Identity.
  • agents-cli scaffold create --agent <remote URL> handles symlinks again. Since 1.4.1 every symlink in a remote template was dropped, so a template that shared a library across variants scaffolded a project that failed at import. Links inside the cloned repo are copied as real file contents, and a link pointing outside it stops the scaffold with an error.
  • agents-cli deploy gets a new flag --framework, which sets the agent_framework property on the deployed agents.
  • The generated Cloud SQL password no longer lands in Terraform state. State lives in gs://{cicd_project}-terraform-state, whose default IAM let anyone with Viewer on the CI/CD project read the prod database password. Generated Terraform now needs Terraform 1.11.0 or later.
  • Scaffolded projects need google-adk>=2.8.0. 2.7.x does not emit interactionStatus, so a Live turn boundary falls back to a heuristic there. The <2.9.0 cap from 1.6.1 is unchanged.
  • The deprecated --trace-to-cloud alias is gone from agents-cli playground and agents-cli run. Use --otel-to-cloud.

[1.6.1] - 2026-09-16

  • ADK Go is now available to everyone (Preview). The adk_go template ("Go agent with A2A") now appears in agents-cli scaffold create with no experiment override, and Go projects get the toolchain Python already has:
    • Deploy to Agent Runtime, Cloud Run and GKE, with session methods exposed to agent_engines.get() clients.
    • CloudSQL, Agent Platform and in-memory session services.
    • Prompts and responses in BigQuery Agent Analytics, and telemetry through OTLP.
    • CI/CD templates at parity with Python.
    • The bundled skills cover Go and Python.
  • Scaffolds now default to gemini-3.8-flash.
  • agents-cli scaffold create no longer asks for a region when the deployment target is none.
  • The one-off agents-cli run no longer prints stop and resume hints for a server it did not leave running.
  • agents-cli deploy prints how to talk to a Cloud Run agent once the deploy finishes.
  • agents-cli deploy can change the identity type on an existing agent.
  • agents-cli deploy now reports the correct identity after a deploy, instead of the wrong principal for agents using Agent Identity.
  • Exclude vendored extensions from the deploy payload, where they could add megabytes to every deploy.
  • agents-cli infra single-project now correctly enables the Service Usage API, so a new project bootstraps without enabling it by hand.
  • Fix remote ADK samples generating two agent directories and an unbuildable project.
  • Scaffolded Dockerfiles install uv from a pinned image instead of pip install.
  • agents-cli run and agents-cli eval no longer stop a background server they only borrowed.
  • Startup and version notices now go to stderr, so --json output stays machine-readable.
  • agents-cli eval generate no longer silently drops per-case session state.
  • agents-cli run --mode a2a now shows status updates, errors and empty turns instead of staying silent.
  • The run resume hint includes --url and the other routing flags.
  • agents-cli info --json reports root_agent_name.
  • agents-cli extension add no longer copies ignored files from a local@ source.
  • Pin google-adk below 2.9.0. On 2.9.0 a Cloud Run agent's prompts and responses stopped reaching BigQuery Agent Analytics.
  • Fix the macOS-only sed in the Starter Pack migration guide and spell out the dry-run and apply steps.

[1.5.0] - 2026-09-01

  • Extension system with a LangChain template. agents-cli can now be extended with custom commands and add-on agent templates, shipped with a LangChain extension and authoring guides. Extensions install from GitHub, other git hosts (including self-hosted and enterprise servers), or a local path for development.
  • Add agents-cli infra show to inspect the Terraform configuration provisioned by agents-cli infra single-project.
  • Add --update-only to agents-cli deploy, so a deploy updates an existing Agent Runtime engine instead of creating a duplicate.
  • Add a --labels flag to agents-cli deploy to tag Agent Runtime and Cloud Run deployments.
  • Add --qps to agents-cli eval that controls the request rate instead of being throttled to the default value.
  • Name the scaffolded root agent after its project instead of a generic default.
  • agents-cli deploy now retries throttled Agent Platform calls.
  • agents-cli create now reports precondition failures as clear errors instead of exiting successfully or printing a traceback.
  • Fix background server reuse ignoring the requested session mode.
  • Fix reasoning_engine_adapter streaming returning an empty response.
  • Prevent multi-region deployments in scaffold and deploy.
  • Give a clear error for malformed project manifests instead of silently defaulting or printing a traceback.
  • Fix stale command references in docs and CLI hints.
  • Scaffolded A2A agents now forward tool calls and responses to clients, not just text.
  • agents-cli setup now works without network or git access, with skills bundled into the package.
  • Fix a Windows failure loading a scaffolded project whose config points at a local path.

[1.4.2] - 2026-08-28

  • Adds upper-bound for google-cloud-aiplatform dependency.

[1.4.1] - 2026-08-24

  • Scaffolds now default to gemini-3.7-flash.
  • agents-cli eval generate no longer fails to generate traces for some agents.
  • agents-cli deploy now defaults to --min-instances 0 (was 1) on Agent Runtime and Cloud Run, so that idle dev and demo agents don't take up resources.
  • agents-cli scaffold upgrade now creates a project backup before applying changes, just like agents-cli scaffold enhance.
  • Fixed npx skills find to use the pinned skills version.
  • Fixed an arbitrary file write vulnerability in agents-cli scaffold create.

[1.4.0] - 2026-08-17

  • Add Agent Gateway support to agents-cli deploy
  • Improve A2A-on-Agent-Runtime and MCP Agent Registry guidance in skills
  • Use token-based context compaction in ADK cheatsheet
  • Add held-out case guidance during iteration to the eval skill
  • Remove built-in feedback endpoint, add guidance on building a feedback mechanism to the observability skill instead
  • Display project language in agents-cli info
  • Use $GH_TOKEN and $GITHUB_TOKEN environment variables as fallbacks for --github-pat
  • Populate class_methods contract on agent_runtime deploy

[1.3.1] - 2026-08-04

  • Add agent-plugins.org plugin manifest
  • Smarter backoff handling for CICD command
  • Rollback to npx skills 1.5.9 to avoid a spurious error message during setup

[1.3.0] - 2026-07-31

  • Update to use A2A 1.0 throughout, with a compatibility layer for A2A 0.3 clients
  • Improve retry for Cloud Run deploy
  • Streamline retry handing for infra cicd command
  • Fix npx skills output formatting during setup and update
  • Print Cloud Logging URL at Agent Runtime deploy start
  • Add --concurrency and --header flags to eval generate/run
  • Tweak messages around --session-type when used with agent_runtime

[1.2.1] - 2026-07-23

  • Fix an import problem on uv sync caused by a yanked opentelemetry-resourcedetector-gcp version
  • Add optional HTTP-based path for eval generate using --url (in-progress feature, stay tuned)

[1.2.0] - 2026-07-21

  • Cloud telemetry moved to ADK's otel_to_cloud, across the CLI and deploys. playground and run gain an --otel-to-cloud flag that forwards ADK's current --otel_to_cloud; the old --trace-to-cloud stays as a hidden, still-functional alias that warns when used. On the deployment side, Agent Runtime now exports through otel_to_cloud (gated on GOOGLE_CLOUD_AGENT_ENGINE_ENABLE_TELEMETRY) and generated projects configure Cloud telemetry declaratively in Terraform instead of at runtime. Bundled google-adk moves to >=2.2.0 with the otel-gcp extra, and the observability skill was updated to match.
  • Scaffolds now default to gemini-3.6-flash.
  • Agent Analytics now captures GenAI completions on Agent Runtime. The BigQuery telemetry log sink is configured per deployment target, so Agent Runtime deployments route their GenAI request/response logs into BigQuery instead of leaving the completions view empty.
  • Managed Agents guidance in the ADK code skill. The bundled ADK cheatsheet gained a Managed Agents section covering when to use ManagedAgent, Gemini API vs Agent Platform (GEAP) setup, and a runnable create-and-use example.

[1.1.0] - 2026-07-10

  • Guided brainstorming for new agents. The workflow skill's Phase 0 is now an interactive brainstorming dialogue that helps you shape an agent's spec before any code is written, and surfaces its assumptions for review when it can't ask.
  • eval generate and eval grade no longer clutter output with benign third-party warnings and progress bars that never affected results. This output is still shown on failure and can be re-enabled for debugging.
  • Generated projects now name the default scaffolded eval metric module tests/eval/response_quality.py (was metrics.py) to match the metric it implements.
  • Broad Windows compatibility fixes across the CLI.
  • Fixed a command-name typo in user-facing hints so they point to the correct agents-cli command.
  • Refreshed the bundled skills, including pointing the RAG samples at core/python/ in google/adk-samples.

[1.0.0] - 2026-06-30

Agents CLI is now 1.0 — Generally Available. This is our first GA release: a stable, production-ready CLI for scaffolding, evaluating, and deploying ADK agents on Google Cloud.

  • Redeploys now preserve the existing deployment spec on Agent Runtime and Cloud Run instead of resetting unspecified settings.
  • Agent Runtime deploys now honor .gcloudignore and .gitignore when packaging source, so uploads no longer include ignored files.
  • RAG is now a clone-and-study recipe: start from the rag-vector-search / rag-agent-search samples in google/adk-samples (surfaced via the workflow skill). The agentic_rag template, the --datastore flag, and the infra datastore / data-ingestion commands were removed and now print a redirect.
  • Generated projects now consolidate Python environment configuration into a single templated .env file.
  • Eval commands now tolerate ADK toolsets when introspecting eval metadata, so agents that use toolsets no longer fail metadata collection.
  • GKE Cloud Build deploys are now resilient to log-streaming limits and no longer fail when the build log stream is truncated.
  • Refreshed the bundled skills: RAG samples point to core/ on adk-samples main, the always-active workflow skill was generalized and trimmed, and the ADK code guidance notes streaming_agent_run_with_events for debugging on Agent Runtime.

[0.6.1] - 2026-06-28

  • publish gemini-enterprise now registers Agent Runtime deployments via ADK by default, which Gemini Enterprise invokes natively and reliably. A2A registration remains the default for Cloud Run and GKE; requesting A2A on Agent Runtime now warns and recommends ADK. Re-publishing an A2A agent no longer creates duplicate registrations, and A2A agent cards now carry the correct public URL on the first deploy.
  • agents-cli update now exits non-zero and clearly reports when a skill fails to update, instead of always printing a misleading green "Skills updated." banner. Also fixes failure messages rendering in the wrong color on Windows PowerShell.
  • Refreshed the generated project uv.lock files for all templated agents, updating bundled google-adk from 2.2.0 to 2.3.0.

[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
    • #34
    • #35
    • Thanks to @Abdullah-k0de for discovering and reporting these!
  • Fixed stale GCS bucket in failure-investigation guide
  • Added Agent Registry fleet management to publish skill

[0.5.0] - 2026-06-15

  • deploy now surfaces machine-shape parameters as flags for Agent Runtime and Cloud Run.
  • deploy adds a --service-name override.
  • run prints a copy-pasteable resume command in the session footer.
  • run no longer tears down a reused local server on a plain run.
  • scaffold upgrade now builds the prior-version template via uvx.
  • Skills setup/update no longer hangs on large npx output (a pipe-buffer deadlock).
  • The project-root notice now only prints when the command actually changes directory.
  • Fixed pre-existing inaccuracies in the bundled skills and generated project READMEs.
  • Source code is now published to the public GitHub repo: https://github.com/google/agents-cli

[0.4.0] - 2026-06-10

  • Scaffolded Python templates now use ADK 2.0 GA. New adk, adk_a2a, and agentic_rag projects pin google-adk[gcp]>=2.0.0,<3.0.0; the [gcp] extra restores the OpenTelemetry GCP exporters and bundles the BigQuery client, so the separate [bigquery-analytics] extra is no longer needed. Cloud SQL sessions on Cloud Run and GKE keep working under 2.0. The bundled ADK coding skill and its reference docs were refreshed for 2.0.
  • Agent Runtime deploys no longer overwrite a user-supplied AGENT_VERSION (or NUM_WORKERS) passed via --update-env-vars, matching Cloud Run behavior. The "version not found" warning now names the pyproject.toml field to set.
  • Fixed a stale deployment/terraform/dev/ path in the Cloud Trace observability guide so it matches the current single-project terraform layout.

[0.3.1] - 2026-06-04

  • eval generate now works on ADK 2.x projects that use built-in tools such as VertexAiSearchTool. Raised the google-cloud-aiplatform floor to 1.156.0, which carries the SDK fix.
  • Skills installed via agents-cli setup are now visible to Antigravity. Global skills are mirrored into the Antigravity skill directories.
  • update now surfaces errors clearly instead of failing silently.
  • Agent deploys tolerate a corrupt or malformed deployment_metadata.json instead of crashing.
  • Deployment timestamps are now timezone-aware.
  • A malformed AGENTS_CLI_EXPERIMENTS value no longer crashes the CLI.
  • agents-cli install now runs with --locked, so a drifted uv.lock fails fast instead of silently resolving new dependency versions.

[0.3.0] - 2026-05-29

Breaking

  • The eval data format changed from ADK EvalSet to Vertex AI EvaluationDataset. Existing tests/eval/evalsets/*.evalset.json files are no longer read by agents-cli eval generate and friends. See Migrating Eval Datasets for the conversion. scaffold upgrade now prints a notice when legacy files are detected.

Eval - Quality Flywheel (preview)

  • Added eval dataset synthesize for LLM-driven user-simulation dataset generation.
  • Added eval generate to run agent inference over an EvaluationDataset and emit traces.
  • Added eval grade to score agent traces against built-in or custom metrics.
  • Added eval submit to submit an end-to-end cloud-side evaluation run on Vertex AI Eval Service.
  • Added eval results to fetch results from a completed cloud evaluation run.
  • Added eval analyze for failure-mode analysis over graded results.
  • Added eval metric list to discover built-in evaluation metrics.
  • Rewrote the eval skill end-to-end to cover the Quality Flywheel workflow (dataset, generate, grade, analyze, optimize).

Other

  • Minor skills consistency fixes

[0.2.1] - 2026-05-28

  • Add --dryrun as an alias for --dry-run
  • Smarter skills installation
  • Cache credentials for better performance
  • Fix is_authenticated to work without gcloud
  • Fix agent runtime deploy error to be clearer
  • Remove 'beta' from gcloud commands that no longer need them
  • Fix broken doc links
  • Auto gen lockfile if it is missing before trying to export it in deploy

[0.2.0] - 2026-05-15

  • Moved agent-cli project config into a language-independent agents-cli-manifest.yaml file
    • Old config embedded in pyproject.toml can be automatically migrated with agents-cli scaffold upgrade
  • Added eval optimize command
  • add --network-attachment and --dns-peering-* flags to deploy
  • Misc startup performance improvements
  • Avoid crashes related to terminal encodings
  • Smarter tool path resolution, especially for Windows
  • Updated dependency version locks
  • Added manifest support for Claude and Gemini CLI plugin support
  • Fix some bugs around preserving the right config metadata when scaffolding and enhancing and/or upgrading
  • Misc doc and skill fixes
  • Visual Explainer page for Agents CLI lifecycle at https://google.github.io/agents-cli/
  • Cleaned up some dead template code

[0.1.3] - 2026-05-06

  • Default infra commands to terraform plan instead of apply
  • Fix playground to work for Cloud Shell and other similar envs and be more transparent about the underlying command
  • Update skills to cover need for cloud sql role
  • Make agents-cli info print OS info for easier bug reporting
  • Make run only start a background server when requested with --start-server
  • Clearer display string for ADC auth
  • Fix broken doc links
  • Fix missing target description for agent_runtime

[0.1.2] - 2026-04-29

  • Document & image fixes
  • Project metadata fixes
  • Preserve multi-hop traces in completions_view BigQuery SQL
  • Detect legacy ADK skills during setup
  • Save inline artifacts to .google-agents-cli/artifacts/
  • Fix some Windows shell interaction issues
  • Remove unprocessed pass-through args for deploy, updated skills and --help text
  • Fix agents-cli considering the user as authenticated when auth got stale
  • Auto stop local run server on error

[0.1.1] - 2026-04-22

  • Performance improvements, particularly for CLI startup time
  • Doc cleanups

[0.1.0] - 2026-04-21

  • Initial public release