* docs: add Markifact MCP integration
Adds the Markifact MCP server (https://api.markifact.com/mcp) as an ADK integration with both Local (mcp-remote OAuth) and Remote (Streamable HTTP + bearer) connection patterns for Python and TypeScript.
* Formatting and edits
* Markifact site is returning an error with our link checker CI
Rejected status code: 429 Too Many Requests (configurable with "accept" option)
* Remove unneeded URL that is also failing link checker
---------
Co-authored-by: Kristopher Overholt <koverholt@google.com>
* Update documentation for setting logging in ADK
* Added OTEL_INSTRUMENTATION_GENAI_CAPTURE_MESSAGE_CONTENT to Python and ADK web
* Small formatting issue
* Fix logging docs: bugs, heading structure, and copy-paste errors
- Fix os.environ assignment crash: bool True to string "true"
- Fix two errors: "traces"/"metrics" changed to "logs"
- Fix heading hierarchy: Python and Go setup as sibling h3 sections
- Add intro text under Python and Go programmatic setup headings
- Restore Go launcher CLI example that was removed in restructure
- Remove TypeScript and Java from language tags
- Remove redundant sentences in intro and Python setup sections
* Improve logging docs formatting and trim debugging example
- Convert blockquote notes to MkDocs admonitions
- Remove horizontal rules between sections
- Trim debugging example: trim redundant steps and log output
- Clean up section headings
---------
Co-authored-by: Kristopher Overholt <koverholt@google.com>
* docs(memory): refresh against current adk-python APIs
The memory page has drifted from the implementation. The MultiMemoryAgent
example raises ValueError on construction (assigning to a Pydantic model
with extra="forbid"), the auto-save callback reaches into the private
_invocation_context attribute when public Context.add_session_to_memory()
exists, and the API surface description is missing add_events_to_memory,
add_memory, and the third memory service (VertexAiRagMemoryService).
* Update product names
---------
Co-authored-by: Kristopher Overholt <koverholt@google.com>
* fix: working code for the new version
* fix: typos
* fix: lint
* Fix import paths, remove trailing underscore from prefix, and replace Runner with InMemoryRunner/run_debug for a self-contained runnable example.
---------
Co-authored-by: Kristopher Overholt <koverholt@google.com>
* docs(integrations): add Cisco AI Defense integration page
Add documentation for the Cisco AI Defense plugin for Google ADK,
providing runtime LLM and MCP tool inspection with monitor and enforce
modes. Includes logo asset and code examples for both plugin and
callback approaches.
Resolves#1665
Made-with: Cursor
* Formatting and copy edits
---------
Co-authored-by: Kristopher Overholt <koverholt@google.com>
* fix: correct agents-cli skill names and deployment targets in Coding with AI tutorial
- Fix skill names to match actual agents-cli implementation:
- google-agents-cli-adk-deploy → google-agents-cli-deploy
- google-agents-cli-adk-dev → google-agents-cli-workflow
- google-agents-cli-adk-eval → google-agents-cli-eval
- google-agents-cli-adk-observe → google-agents-cli-observability
- google-agents-cli-adk-scaffold → google-agents-cli-scaffold
- Add missing google-agents-cli-publish skill
- Add GKE as deployment target (was missing from deploy command description)
- Fix publish destination: 'Agent Store' → 'Gemini Enterprise'
- Reorder skills to match canonical order from agents-cli
* docs: use full branding 'Agents CLI in Agent Platform' in intro paragraphs
Use the full product name 'Agents CLI in Agent Platform' in introductory
paragraphs and first mentions, then shorten to 'Agents CLI' in subsequent
prose references. Command names and code blocks remain as 'agents-cli'.
Changes:
- coding-with-ai.md: First mention uses full branding
- agents-cli.md: Title and intro paragraph use full branding
- index.md: Deployment path description uses full branding
- All subsequent prose references use 'Agents CLI' instead of 'agents-cli'
- Command references and code blocks unchanged (still 'agents-cli')
The 'run' is marked as @final in BaseNode class's implementation and hence can not be be overridden in the child class. Moreover, there is a method _run_impl() specifically for overriding.
Overriding run directly bypasses the logic that converts raw return values into Event objects. This causes downstream failures in _track_event_in_context, which expects a valid Event type Object.
The _run_impl is called inside the run method.
The _run_impl can return any value and this value is appropriately converted to Event Object by run method.
This change moves the custom logic for GetInput into _run_impl, allowing the base class to correctly wrap the yielded request in an Event object before it is tracked by the workflow loop.
* Rename asp.md to agents-cli.md and update redirects
- Renamed docs/deploy/agent-runtime/asp.md to agents-cli.md
- Updated navigation reference in mkdocs.yml
- Added redirect rule: agent-runtime/asp.md → agents-cli.md
- Updated existing redirect: agent-engine/asp.md → agents-cli.md
The 'asp' name no longer makes sense as a page name now that we're
referencing Agent Starter Pack / agents-cli directly.
Note: This applies on top of PR #1673 which renamed:
- 'agent-engine' directory → 'agent-runtime'
- 'Agent Engine' product → 'Agent Runtime'
* Complete migration from Agent Starter Pack to agents-cli
This commit completes the migration from "Agent Starter Pack (ASP)"
terminology to "agents-cli" across documentation and updates references
to align with the new Agent Platform tooling.
Changes:
- Updated docs/deploy/agent-runtime/agents-cli.md: Replaced all "Agent
Starter Pack" and "ASP" references with "agents-cli", updated commands
from 'uvx agent-starter-pack enhance --adk -d agent_engine' to
'agents-cli scaffold enhance --deployment-target agent_engine', and
updated all documentation links to point to google.github.io/agents-cli/
- Updated docs/tutorials/coding-with-ai.md: Replaced "ADK Dev Skills"
section with "agents-cli" section, changed installation from
'npx skills add google/adk-docs/skills -y -g' to
'uvx google-agents-cli setup', updated skill names table to new
agents-cli skill names, and added CLI commands table
- Updated docs/deploy/agent-runtime/index.md: Changed "Agent Starter Pack
deployment" to "agents-cli deployment" and updated reference from
"The Agent Starter Pack (ASP)" to "agents-cli in Agent Platform"
- Deleted docs/skills/ directory: Skills have been migrated to the
agents-cli repository
* Fix agents-cli deployment instructions to use correct CLI commands
Replace incorrect make command references with agents-cli deploy and agents-cli infra single-project. Update deployment workflow to reflect actual agents-cli usage.
* Update navigation to use agents-cli instead of Agent Starter Pack
Replace "Agent Starter Pack" with "agents-cli" in the navigation menu. Redirects from old ASP URLs are already in place.
* Restore docs/skills/index.md - Agent Skills documentation
This file documents the Agent Skills feature (agentskills.io specification),
not ADK Dev Skills. It was mistakenly deleted in the ASP → agents-cli migration.
Agent Skills are a general ADK feature where agents can use modular,
self-contained units of functionality based on the Agent Skill specification.
* Fix terminology: Agent Engine runtime → Agent Runtime runtime
Update deployment path description to use consistent "Agent Runtime runtime"
terminology instead of "Agent Engine runtime".
* Fix broken agents-cli documentation links
Replace broken links to /guide/ (which 404s) with correct links to main
documentation page. The /guide/ URL is a directory listing that doesn't
exist in the agents-cli docs structure.
Changes:
- Line 31: "Development guide" link → "Guide" pointing to main docs
- Line 221: "Development guide" link → "agents-cli documentation" pointing to main docs
Both now correctly point to https://google.github.io/agents-cli/
* Delete ADK Dev Skills directory - migrated to agents-cli
Remove the entire skills/ directory containing ADK Dev Skills. These
skills have been migrated to the agents-cli repository and are now
distributed as part of the agents-cli package.
Users should now install skills via:
uvx google-agents-cli setup
Instead of the old method:
npx skills add google/adk-docs/skills -y -g
Deleted skills (now available in agents-cli):
- adk-dev-guide → google-agents-cli-workflow
- adk-cheatsheet → google-agents-cli-adk-code
- adk-eval-guide → google-agents-cli-eval
- adk-deploy-guide → google-agents-cli-deploy
- adk-observability-guide → google-agents-cli-observability
- adk-scaffold → google-agents-cli-scaffold
Total: 19 files removed across 6 skill directories
* Remove skills CI checks
---------
Co-authored-by: Kristopher Overholt <koverholt@google.com>
* Adding initial confirmation js snippets
* updating confirmation tools examples to output text response to user to improve test flow
* fixing boolean_confirmation failure to deny excessive requests
---------
Co-authored-by: Kristopher Overholt <koverholt@google.com>
* docs(integrations): add Database Memory Service
Add a new integration entry for adk-database-memory, a drop-in durable
BaseMemoryService for the Python ADK backed by any async SQLAlchemy
dialect (SQLite, PostgreSQL, MySQL/MariaDB).
Repo: https://github.com/anmolg1997/adk-database-memory
Package: adk-database-memory on PyPI (Apache 2.0)
This fills the gap between InMemoryMemoryService (ephemeral, for dev)
and VertexAiMemoryBankService (managed GCP) for self-hosted durable
memory on the database the user already runs.
* Update formatting and wording
---------
Co-authored-by: Kristopher Overholt <koverholt@google.com>
* docs: add MLflow AI Gateway model provider page
Adds a model provider page showing how to connect ADK agents to
MLflow AI Gateway via the LiteLlm wrapper with a custom api_base.
* docs: add Create Endpoint screenshot
* docs: move MLflow AI Gateway to integrations section
Per reviewer feedback: move the gateway page from agents/models/ to
integrations/ as a standalone integration page. Rename the existing
MLflow tracing page catalog_title to "MLflow Tracing" to distinguish
the two entries.
* Remove nav entry for integrations
* Additional cleanup / redirects / renames
* Additional edits
---------
Co-authored-by: Kristopher Overholt <koverholt@google.com>
Updated the section on consuming logged data to clarify the use of the BigQuery Agent Analytics SDK and its example notebook for visualizing performance data.
Updated documentation for the BigQuery Agent Analytics plugin, removing outdated preview release information and adding links to the SDK and dashboard notebook.
Co-authored-by: Kristopher Overholt <koverholt@google.com>
* Add ambient agents documentation
Document how to build event-driven ambient agents using ADK trigger
endpoints and the /run endpoint. Covers Pub/Sub, Eventarc (Standard
and Advanced), Cloud Scheduler, concurrency control, retry logic,
session lifecycle, and deployment to Cloud Run.
* Address reviewer feedback: clarify event processing flow
- Move "How events are processed" higher, right after trigger endpoints
intro, so the mental model comes before setup instructions
- Reword step 5: explicitly describe status code behavior (200 = ack,
500 = retry) instead of vague "determines whether to retry"
- Clarify that trigger endpoints auto-create sessions without needing
the --auto_create_session flag
- Restructure heading hierarchy under "Using trigger endpoints"
* Address reviewer feedback from koverholt
- Use named sections (--8<-- [start/end]) in code snippets to hide
license headers in doc embeds
- Change model to gemini-flash-latest alias
- Restructure: show example agent first, then enable instructions,
then "Try it locally" with step-by-step commands and curl test
- Fix port consistency (curl uses 8000 matching adk api_server default)
- Add curl example for /run endpoint
---------
Co-authored-by: Kristopher Overholt <koverholt@google.com>
Kristopher Overholt