Skip to content

Latest commit

 

History

History
474 lines (416 loc) · 49.2 KB

RELEASE_NOTES.md

File metadata and controls

474 lines (416 loc) · 49.2 KB

Release Notes

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

[1.15.0] - 2026-11-17

  • First-party extensions and templates move to google/agents-cli-extensions. Installing one from google/agents-cli shows a deprecation warning that points to the new location.
    • The google-agents-cli-extensions package installs from PyPI without a trust prompt.
  • A git extension pinned to a commit SHA must be on a branch or tag of the repo it names.
  • The LangChain extension template supports --session-type cloud_sql, which stores conversation checkpoints and long-term memory in Cloud SQL for PostgreSQL.
  • agents-cli create no longer reports success when the Google Cloud credential or API check fails.
  • When agents-cli can't get a Google Cloud access token, it explains why and suggests agents-cli login.
  • Generated projects ignore the artifacts/ and .google-agents-cli/ directories that agents-cli eval and agents-cli run write.
  • Go projects serve /apps/{app_name}/app-info from ADK Go's exp/appinfo package, and new projects no longer contain an appinfo/ folder.
    • Action needed: if you kept a customized main.go during agents-cli scaffold upgrade, change the import "<project>/appinfo" to "google.golang.org/adk/v2/exp/appinfo".

[1.14.0] - 2026-11-12

  • agents-cli deploy runs pre-flight checks before source builds.
    • Before uploading, it checks for issues that would break the remote build and explains each one: a uv.lock pointing at a package index the builder can't reach, a missing or stale lock, build inputs excluded by .gcloudignore or .gitignore, path dependencies outside the upload, or a base image Python that doesn't match requires-python.
    • --skip-preflight skips the checks.
    • deploy --dry-run exits 1 on pre-flight errors. Scripts and CI jobs that run it may need an update.
    • #95
  • agents-cli deploy adds --remove-env-vars KEY,..., --clear-env-vars, --remove-secrets KEY,... and --clear-secrets for Cloud Run and Agent Runtime.
    • A key that is in the project .env can't be removed (delete it from .env instead), and env vars agents-cli sets itself (such as AGENT_VERSION) are set again on every deploy.
    • --clear-secrets also removes secrets set outside agents-cli (such as by Terraform) and secrets mounted as volumes.
    • #60
  • agents-cli deploy shows the error reason and help links when an Agent Runtime request fails.
  • agents-cli extension add pypi@<package>[==<version>][#<folder>] installs an extension from a wheel on PyPI, or on the index set in UV_DEFAULT_INDEX, UV_INDEX_URL or PIP_INDEX_URL, pinned to the wheel's sha256. agents-cli extension update <name> --to <version> or --to :latest moves the pin.
  • agents-cli scaffold enhance --from-adk-project writes a minimal agents-cli-manifest.yaml for an existing ADK project without rendering a template, so eval, info and playground can find it. Use --dry-run to preview and --force to replace an existing manifest.
  • agents-cli scaffold create -a claude --memory-bank scaffolds a Claude agent with long-term memory in Vertex AI Memory Bank, which works the way ADK's does. The agent recalls the user's memories at the start of each turn, learns from each finished turn, and can call a search_memory tool. Other agents reject the flag; ADK agents can follow the cross-session-memory recipe.
    • Memory is per user. For A2A callers without authentication, it lasts one conversation, as in ADK.
    • With OTEL_INSTRUMENTATION_GENAI_CAPTURE_MESSAGE_CONTENT on, Claude agents record the system prompt the model got, recalled memories included, as gen_ai.system_instructions on the turn span.
  • Claude Agent SDK projects send x-goog-api-client: agents-cli-app/<version>+claude-agent-sdk on model calls, so Google can count usage from agents-cli projects. Set DO_NOT_TRACK=1 or AGENTS_CLI_TELEMETRY=0 to turn it off; your own ANTHROPIC_CUSTOM_HEADERS are always sent. Existing projects are unchanged until they adopt the new template code.
  • agents-cli login --status, login -i and setup warn when Google Cloud credentials work but agents can't call Gemini yet, and say how to fix it.
  • agents-cli login with the Gemini API key option prints the .env changes a generated project needs to use the key, instead of reporting "Continuing without authentication".
  • agents-cli create explains which Google Cloud setup step failed.
  • agents-cli run and agents-cli playground check the agent's Google Cloud credentials before starting it.
    • Model errors from agents-cli run, such as permission denied, disabled API, billing disabled, quota, or an invalid API key, include a one-line fix.
  • agents-cli run prints the local-server banner and a failed run's error once, and shows auth errors as plain text instead of Python object reprs.
  • agents-cli infra single-project stops with terraform import instructions when an existing Agent Runtime engine is missing from Terraform state, instead of creating a duplicate. On a new project the first run may log "Skipping the Agent Runtime import check" until Terraform enables the Vertex AI API.
  • google-agents-cli no longer installs scikit-learn, scipy, litellm, jsonschema or ruamel.yaml, which roughly halves its install size. Eval commands work as before.
  • New ADK Python projects pin FastAPI below 0.142.0, so traces from agents on Agent Runtime and Cloud Run are no longer dropped for requests the platform forwards as unsampled.
  • New Go projects use ADK Go v2.7.1.
    • For Go projects on ADK Go v2.5.0 or later, agents-cli playground honors --host and binds 127.0.0.1 by default, the same as Python projects. Pass --host 0.0.0.0 to reach it from another machine. Older projects keep binding all interfaces.
    • Action needed: when you run agents-cli scaffold upgrade on a Go project and keep your own Dockerfile, add "--host", "0.0.0.0" after "web" in its ENTRYPOINT. ADK Go v2.5.0 and later listen only on localhost by default, so the container would otherwise get no traffic.
  • The setup.md prompt no longer stops after install to ask for a new session. The coding agent reads the installed workflow skill and continues.

[1.13.0] - 2026-11-04

  • Cloud Run deployments support Agent Identity.
    • agents-cli deploy --agent-identity deploys a Cloud Run service with Agent Identity.
    • New projects default using Agent Identity for Cloud Run deployments. To migrate an old project so that it uses Agent Identity, run agents-cli scaffold enhance with --cloud-run-identity-type agent_identity.
    • To create a new project that uses a service account instead, run agents-cli scaffold create with --cloud-run-identity-type service_account.
  • agents-cli eval run and agents-cli eval grade end with a RESULT: PASS or RESULT: FAIL (...) line, preceded on failure by the metrics and cases that failed and a next step.
    • Set a minimum mean score per metric with a thresholds: map in the eval config, or for one run with --fail-under METRIC=SCORE (repeatable, one metric each). A missed threshold exits 1. pass_rate in the results is filled from the threshold when the eval service doesn't report one.
    • Breaking: a run where any case errored now exits 1, even without thresholds. If the errors are rate limits, lower --qps.
  • agents-cli login signs in both the gcloud CLI and Application Default Credentials (gcloud auth login --update-adc), so commands that run gcloud work right after login.
    • When only Application Default Credentials are available and gcloud has no credentials of its own, agents-cli passes an ADC access token to the gcloud commands it runs. GKE deploys in that setup are not covered yet.
    • Note: the account you sign in with also becomes gcloud's active account.
  • New projects record create_params.app_name in agents-cli-manifest.yaml: the name the server serves the agent under (/apps/{app_name}/...). run, eval, playground, deploy and publish use it; projects without it keep using the basename of agent_directory.
    • eval generate --app-name and eval run --app-name default to the project's app name instead of app.
  • agents-cli deploy --image <artifact-registry-uri> works for Agent Runtime. The Agent Runtime service agent needs roles/artifactregistry.reader on the repository. --build-args can't be combined with --image, and an existing agent can't switch between a source build and --image.
  • Agent Runtime deploys of A2A agents register the agent card in Agent Registry, so the agent shows up as A2A-capable in Gemini Enterprise.
  • agents-cli deploy --dry-run also validates a GKE deployment against Google Cloud.
  • agents-cli extension add <name> pins a first-party extension to the latest release compatible with your agents-cli instead of main. Pass --ref main to track main.
    • agents-cli extension update --to <ref|:latest> moves a pin. First-party extensions installed from main move to the latest release on their next update.
  • agents-cli extension add langchain and agents-cli extension add claude install instead of failing with "has no agents-cli-extension.yaml".
  • agents-cli extension add installs extensions from agents-cli pre-approved repositories without a trust prompt, whether given as a shorthand, an org/repo reference or a URL.
  • Usage telemetry names an extension when it serves a command if the extension comes from Google.
  • Extensions can share files through symlinks that stay inside their repository. These links are copied as regular files when the extension is vendored and when its skills are installed.
  • A project, template, or deployment metadata that declares a language this version of agents-cli doesn't support fails with an error listing the supported languages and suggesting uv tool upgrade google-agents-cli, instead of being treated as Python.
  • agents-cli scaffold enhance . in a project without a manifest records the base template it rendered (adk_python, adk_go), so later enhance and upgrade runs work. Before, they failed with "Base template 'local_' not found". In projects already affected, set base_template in agents-cli-manifest.yaml to adk_python (or adk_go) by hand.
  • agents-cli scaffold enhance --region <region> writes the region to agents-cli-manifest.yaml and to the files it renders, such as the Terraform variables. Enhancing a project without --region keeps the region recorded in its manifest.
  • agents-cli publish gemini rejects a response that isn't a valid A2A agent card.
  • Local A2A agent cards advertise the server's real port instead of http://localhost:8000.
  • Claude Agent SDK projects: a turn fails when its transcript can't be saved to the session store (Cloud SQL, or the agent's own session_store), instead of succeeding while the conversation can't be fully resumed on another instance.
  • agents-cli setup tells a coding agent running it mid-session to read the workflow skill directly, since newly installed skills only load in the next session.
  • The bundled ADK code skill no longer points coding agents straight at scaffold create for a new project. It has them load the workflow skill and agree the agent's spec with you before scaffolding.
  • The bundled deploy skill now points to GoogleCloudPlatform/genai-factory and its agents-cli extension for enterprise agent infrastructure.
  • The docs site has a new homepage and layout, a "Debug a failing agent" guide, a "Control cost" page, and guides updated to match the bundled skills.

[1.12.0] - 2026-10-27

  • ADK Go is now Generally Available. The adk_go template is out of Preview: it is stable, production-ready and supported on the same terms as adk_python. This release also brings:
    • agents-cli create --agent <template> supports ADK Go v2 templates whose manifest.yaml declares language: go. Templates built for other ADK Go versions are rejected. A declared language that contradicts the base template (or --base-template) fails with an error explaining how to fix it.
    • The server e2e tests in new ADK Go projects time out after 120s instead of 60s, so multi-step agents no longer time out.
  • The Python agent template is now adk_python, selected with --agent adk_python (or -a adk_python). adk still works as an alias. New projects record adk_python in agents-cli-manifest.yaml, and upgrading a project recorded as adk records adk_python too. Enhancing or upgrading these projects requires this CLI version or newer.
  • New experimental Claude Agent SDK extension. Create a project with agents-cli scaffold create --agent google/agents-cli/extensions/claude/template@<version>, or migrate an existing agent with scaffold enhance and that template. It deploys to Agent Runtime or Cloud Run over A2A, calls Claude on Gemini platform only, and comes with Cloud Trace, Cloud Logging, Cloud Monitoring, optional BigQuery Agent Analytics and Cloud SQL sessions. playground, eval dataset synthesize and eval optimize aren't supported, and publish gemini is refused on Agent Runtime.
    • On Agent Runtime, these agents also serve :query (async_create_session) and :streamQuery (async_stream_query), so an ingress Agent Gateway can govern them (for example with Model Armor) and agents-cli run --mode adk works.
  • The agent template directory can be a nested folder, such as src/my_agent, both in remote templates and with --agent-directory.
  • agents-cli scaffold enhance <template> on a project agents-cli didn't create writes the template's files as create would, and moves each of your files it replaces (such as pyproject.toml, README.md, Dockerfile, .env) to .agents-cli-original/, keeping its path. Your other files stay where they are. Port what you need from the folder, then delete it; enhance won't run again while it exists. New projects' .gitignore and .gcloudignore exclude the folder.
  • Extension templates can set settings.session_types, so create offers and accepts only those session types, with the first as the default. A template whose list is empty or names an unknown session type is rejected.
  • agents-cli scaffold enhance --dry-run exits with code 2 (was 0) when combined with --force, when run with -y and no override flags, or when run without a saved agents-cli-manifest.yaml.
  • Cloud Run projects run their Cloud Run service on the hashicorp/google-beta provider, pinned to ~> 8.7. Other resources keep hashicorp/google ~> 7.28. Existing projects pick it up through agents-cli scaffold upgrade; if terraform init then reports a locked google-beta older than 8.7, run terraform init -upgrade once.
  • The server e2e tests in new Python projects time out after 120s instead of 60s, so multi-step agents no longer time out.
  • agents-cli deploy --dry-run for Agent Runtime prints the plan even when a check fails. It still exits with code 1.
  • agents-cli deploy --dry-run for Agent Runtime warns that it could not verify the secrets when the Secret Manager API is disabled, instead of skipping the check silently.
  • agents-cli deploy --dry-run also validates a Cloud Run deployment against Google Cloud.
  • A malformed --env-vars, --secrets or --labels value fails before the project prompt.
  • A failed agents-cli publish gemini reports the API's reason (for example a SERVICE_DISABLED message with the enable link) instead of a bare HTTP error.
  • A failed terraform step in agents-cli infra exits with a short error naming the step and how to rerun it, instead of a Python traceback.
  • agents-cli info lists globally installed skills.
  • agents-cli run --mode a2a no longer prints a streamed reply twice when the agent ends with the full reply as its last chunk.
  • The bundled skills point to google/adk-recipes and call its agents "recipes". The ADK catalog is now references/recipes.md.

[1.11.0] - 2026-10-20

  • Breaking: The adk@<name> shortcut has been removed. Pass the recipe's GitHub URL to agents-cli create instead, and browse recipes at https://github.com/google/adk-recipes.
    • The scaffold's "Browse ADK recipes" option lists recipes from both core/python/ and contrib/python/ in google/adk-recipes.
    • Projects created with adk@ still upgrade. Their base_template is rewritten to the recipe URL on the first applied change.
  • New projects use google-adk>=2.12.0 and google-cloud-aiplatform>=2.2,<3. Agent Runtime projects also depend on google-cloud-agentplatform, and the LangChain extension template moves to google-cloud-aiplatform>=2.2,<3.
  • agents-cli deploy to Agent Runtime registers the ADK artifact methods (async_save_artifact, async_load_artifact, and others).
  • agents-cli deploy to Agent Runtime shows the last 40 lines of the build log when a build fails, instead of only "Build failed". deploy --status shows it too.
  • agents-cli's uv commands use public PyPI even when a machine-wide uv config points at a mirror, so deploy no longer breaks. agents-cli install warns when uv.lock uses a mirror and shows the command to re-lock. install --locked now fails on such a lock. Scripts and CI jobs that run install --locked may need an update.
  • agents-cli create finds the agent code in any remote template, not only adk-recipes ones. When both app/ and a folder-named package exist, app/ wins; use --agent-directory to pick the other. A top-level agent_directory in a template's agents-cli-manifest.yaml is now respected.
  • LangChain agents are now named after your project, or the name you pass with --root-agent-name, like ADK agents.
    • Template authors can list files under render_files in .template/templateconfig.yaml. Placeholders such as the agent name are then filled in in those files when a project is created.
  • Traces from LangChain agents now record which conversation each request belongs to (gen_ai.conversation.id), so you can follow a conversation across requests, as you already can for ADK agents.
  • agents-cli run --mode a2a shows why an agent's task failed, was rejected or was canceled ([error]: <reason>) instead of "(no response content)".
  • ADK Go agents no longer lose replies for turns that take longer than 15 seconds on /run or A2A.
  • The Cloud Build pipelines and Dockerfile in generated ADK Go projects retry Go module downloads, so a dropped connection to the Go module proxy no longer fails the build.
  • ADK Go projects include only the session backend chosen at creation time.
  • agents-cli scaffold upgrade stops instead of reporting success when it cannot build the template of the project's original version. It shows why, and suggests --force when that can help.
  • agents-cli scaffold upgrade no longer warns about a legacy eval file that an earlier, stopped upgrade already migrated.
  • agents-cli setup --workspace lists each installed skill's folder once.
  • Extensions can no longer override agents-cli info, login, setup or update.
  • agents-cli --help, the docs and error hints show create commands that work as written: -i to choose options in prompts, -y to accept the defaults (adk template, agent_runtime target).
  • Warnings print as ⚠️ Warning: <message> with a yellow prefix on stderr. Some warnings that used to go to stdout now go to stderr. Scripts that read warnings from stdout may need an update.
  • Errors that agents-cli logs print with the same red ❌ Error: prefix as other errors, and --debug output prints as dim Debug: … lines.
  • agents-cli no longer prints the google-auth quota-project warning or google-genai's automatic function calling advice. eval run no longer prints "Could not obtain credentials" when it talks to the local agent server.

[1.10.0] - 2026-10-12

  • New projects use Agent Identity by default. agents-cli scaffold create records agent_runtime_identity_default: agent_identity. Then agents-cli deploy creates the Agent Runtime agent under its own Agent Identity principal, and the generated Terraform (infra single-project, infra cicd) does the same. To keep a service account, pass --agent-runtime-identity-default service_account to scaffold create or scaffold enhance. Existing projects are not changed: if the setting is missing, it reads as service_account, and scaffold upgrade does not migrate it.
    • deploy uses this default only when it creates a new agent. A redeploy without --agent-identity or --no-agent-identity does not change the identity of an existing agent.
  • Extensions can ship skills. An extension declares skills in the skills: field of agents-cli-extension.yaml:
    • agents-cli extension add copies them to <project>/.agents/skills/, or to ~/.agents/skills/ with --global.
    • agents-cli extension update replaces them with the new version's skills and lists the skills it removed.
    • agents-cli extension remove deletes them. The new --global flag removes the user-scope install.
    • agents-cli install restores the skills of every recorded extension.
    • A skill folder copied by an extension is managed by that extension, and manual modifications to it might be overwritten.
  • agents-cli extension update keeps the old local copy when it refuses a new version or a copy fails.
  • New agents-cli deploy flags for Agent Runtime and Cloud Run: --remove-labels KEY,... and --clear-labels. New aliases that match gcloud run deploy: --update-labels, --update-secrets and --env-vars.
  • agents-cli deploy now rejects --iap, --port, --service-account and --cluster-name on targets that ignored them. Before, they were silently ignored. Scripts that pass them may need an update.
  • agents-cli run fails with Agent run failed: <reason> and a non-zero exit code when the ADK stream sends an error. Before, the run looked successful.
  • agents-cli scaffold create shows the dependency changes, like enhance and upgrade do.
  • agents-cli scaffold create keeps the detected project in .env when credential checks fail, instead of writing the your-gcp-project-id placeholder. It also warns when --session-type is ignored for --deployment-target none.
  • agents-cli scaffold enhance creates missing config and dependency files instead of skipping them.
  • Values in agents-cli-manifest.yaml are now escaped, so a quote or newline in a value no longer breaks the file. Project names are limited to a-z, 0-9 and -.
  • Terminology has been adjusted in various places to use appropriate names for the Gemini ecosystem. No functional change, as old variants are kept as aliases where applicable.
  • The CLI now uses google-cloud-aiplatform 2.x, and gcsfs is pinned to >=2026.10.0. The template lock files are updated.
  • The bundled skills list the Ambient Quality Agent (AQuA) recipe.

[1.9.0] - 2026-10-06

  • Usage telemetry is now on by default. Each command writes one log entry to your own Google Cloud project with the command name, exit code, error class, duration, and CLI, Python and OS versions, never arguments or file contents. Its purpose is to provide users with analytics regarding their tool use, process efficiency, and help diagnose potential issues. The request also sends Google the CLI, Python and OS versions, CPU architecture and command name for usage analytics; no sensitive data is sent. Opt out with AGENTS_CLI_TELEMETRY=0 or DO_NOT_TRACK=1. agents-cli info now always shows whether telemetry is on.
  • agents-cli deploy --key encrypts an Agent Runtime agent with a customer-managed Cloud KMS key (CMEK), so deploys work in projects that enforce constraints/gcp.restrictNonCmekServices. The key can only be set when the agent is created, and deploy --list shows it in a new Encryption column.
  • agents-cli deploy --dry-run checks an Agent Runtime deployment against Google Cloud: enabled APIs, the target engine, IAM permissions, actAs on the service account, and secrets. A definite problem exits with code 1, and a check that cannot run only warns. A dry run now makes read-only network calls. A real deploy is unchanged.
  • agents-cli deploy reports unsupported flags in one format, <flag> is only supported for <targets> deployments (current target: <target>), and names only the flags you passed. An empty value for such a flag, such as --key "" on Cloud Run, is now rejected instead of ignored. Scripts that match the old error text may need updating.
  • New ADK Python projects set GOOGLE_GENAI_USE_ENTERPRISE=true instead of the deprecated GOOGLE_GENAI_USE_VERTEXAI. Existing projects keep working: agents-cli deploy to Agent Runtime respects whichever name your .env sets. Go projects keep the old name.
  • New ADK Go projects enable the gofmt and goimports formatters, so agents-cli lint reports formatting issues and lint --fix fixes them.
  • Re-applying the Terraform generated by this release, for example with agents-cli infra single-project or infra cicd, no longer replaces the BigQuery log sink tables once logs have arrived. The replacement deleted every exported log. completions_view also gains a service_version column with the deployment revision. Run agents-cli scaffold upgrade to get this in an existing project.
  • Scaffolded ADK projects no longer append a duplicate JSONRPC 0.3 interface to the agent card on every request to .well-known/agent-card.json.
  • A tool that exists but cannot run, such as uv.exe blocked by AppLocker on Windows, now fails with a clear error naming the tool and the OS reason instead of a PermissionError traceback.
  • Installed extensions no longer print a warning on every command. A notice appears only when a command overridden by an extension runs.

[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