* Add Aerospike integration to ADK catalog
Document adk-aerospike session, memory, and artifact services with tabbed
Python examples, URI configuration, storage layout, and catalog assets.
* Fix adk web CLI flags and minor formatting edits
---------
Co-authored-by: Kristopher Overholt <koverholt@google.com>
* UpdateContext.md
* Update index.md
* Update index.md
noticed that the hierarchy of bullet points was not correct
* Update context and callbackcontext.md
* Enhance BigQuery Agent Analytics with reliability fixes
Added reliability and observability fixes for BigQuery Agent Analytics, including cross-region storage write routing, dropped-event tracking, and improved span management in Cloud Trace.
* Fix markdown formatting in BQAA doc
Resolve the code-fence/content-tab indentation issues flagged in review:
- Full example: restore the === "Python" content tab and indent the whole
Python code block uniformly to 8 spaces so it is a proper sibling of the
=== "Java" tab (previously the block was half-de-indented with an orphaned
opening fence next to a lone Java tab).
- Public methods: move the Python list inside the === "Python" tab (it had
been pasted at column 0, outside the tab) and remove the duplicated list
that ended up wrongly nested under the "Async context manager" bullet.
* Revise BigQuery Agent Analytics documentation
Updated version requirements and added details about ADK 2.0 multi-agent workflow features and event types. Enhanced descriptions for internal span tracking and storage behavior.
* docs: Document GCS first party toolset
* Update gcs.md for clarity and style considerations
* Update gcs.md
---------
Co-authored-by: Joe Fernandez <931947+joefernandez@users.noreply.github.com>
* Update index.md
1. Updated the evaluation page, added the 4th evaluation "adk conformance", 2. removed numbering in headers as suggested, 3. improved the "notes" and "warnings" that had an incorrect formatting.
* Update index.md
* Update index.md
worked on all your comments
* Update index.md
* Add context graph section to BigQuery Agent Analytics docs
Added a section on the context graph, detailing its purpose, structure, and operational references for materialization and deployment.
* Add files via upload
---------
Co-authored-by: Joe Fernandez <931947+joefernandez@users.noreply.github.com>
* docs(gke): add Workload Identity IAM binding for adk deploy gke
The automated deployment path (`adk deploy gke`) generates a manifest
that uses the `default` Kubernetes service account in the `default`
namespace, but the docs only documented the Workload Identity IAM
binding for the manual path (which uses a custom `adk-agent-sa`).
Without binding `roles/aiplatform.user` to the `default` service
account, agent pods start but model requests fail with
`403 PERMISSION_DENIED`.
Add a "Configure Workload Identity for Agent Platform" step under
Option 2 with the correct binding for the `default` service account,
and cross-reference it from the 403 troubleshooting entry.
Fixes#1254
* Update gke.md
---------
Co-authored-by: Joe Fernandez <931947+joefernandez@users.noreply.github.com>
* Update compaction.md
Added the explanation for token compaction, and a header section for sliding window section, added the section: What is compaction?
* Update compaction.md
Worked on changes
* Update compaction.md
* Update compaction.md
worked on other 2 comments
* Update compaction.md
* docs: Document concurrency and locking in DatabaseSessionService
* Concurrencyandlocking.md
instead of a note, created a subsection
* Concurrencyandlocking.md
---------
Co-authored-by: Zyan <zyanya@google.com>
* Update version for ADK Kotlin to 0.2.0
* Update version for ADK Kotlin examples to 0.2.0
* Update install steps on multi-tool-agent page
* Update ADK Kotlin API reference docs to 0.2.0
* Remove runner parameter from AdkWebServer constructor
* docs(integrations): refresh e2a — hosted endpoint + 7 missing tools
The e2a integration page has drifted from what the e2a MCP server
actually ships. Two gaps this PR closes:
1. **Hosted endpoint not documented.** e2a runs a hosted Streamable
HTTP MCP at https://mcp.e2a.dev/mcp that accepts an API key in
the Authorization header. The page currently only shows the
stdio path (npx -y @e2a/mcp-server), which doesn't work for ADK
agents deployed to Cloud Run since Cloud Run can't host stdio
MCP child processes. Adds a "Hosted MCP Server" tab to both the
Python and TypeScript code examples using
StreamableHTTPConnectionParams.
2. **7 tools missing from the table.** The MCP server now registers
18 tools but the page lists 11. Adds:
Identity: update_agent, delete_agent
Messages: get_attachment_data
Domains: list_domains, register_domain, verify_domain,
delete_domain (new section)
Also clarifies a few descriptions:
- `whoami` notes E2A_AGENT_EMAIL is only required for multi-agent
accounts (the hosted endpoint auto-resolves the sole agent at
session init).
- `delete_agent` and `delete_domain` flag the `confirm: true`
required arg.
- `get_attachment_data` uses 0-based `attachment_index`, not an
attachment ID.
- `E2A_BASE_URL` clarifies the var has no effect when connecting
to the public hosted endpoint.
Cross-linked the cloud-mode webhook example (already shipped in
the e2a repo, not previously referenced from this page) and the
hosted endpoint URL under Additional resources.
No frontmatter / catalog metadata changes — title, description,
icon, and tags (`["mcp"]`) all unchanged.
* fix: import McpToolset from deep path (google-adk 2.0 compat)
google-adk 2.0 stopped re-exporting McpToolset from
`google.adk.tools.mcp_tool`'s package __init__ — only the deep path
`google.adk.tools.mcp_tool.mcp_toolset.McpToolset` still works.
Caught when I actually ran the example against a fresh
google-adk 2.0 install:
ImportError: cannot import name 'McpToolset' from
'google.adk.tools.mcp_tool'
($VENV/site-packages/google/adk/tools/mcp_tool/__init__.py)
Applies to both the stdio code block and the new hosted code block.
StdioConnectionParams and StreamableHTTPConnectionParams already use
deep paths and continue to work — only McpToolset was broken.
* Revert McpToolset import to standard path
The claim that google-adk 2.0 stopped re-exporting McpToolset from
google.adk.tools.mcp_tool is incorrect. The __init__.py at
src/google/adk/tools/mcp_tool/__init__.py explicitly re-exports
McpToolset (and MCPToolset) via `from .mcp_toolset import McpToolset`.
It has done so in every release, including v2.0.0.
* Rename tab to Remote MCP server for consistency with all other integration pages
* Remove link to raw MCP endpoint
* Match API key variable / format with all other integration pages
* Formatting and consistency edits
---------
Co-authored-by: Kristopher Overholt <koverholt@google.com>
* Updated the python code sample for routing.
* Simplified the routing sample
* Update routes.md
add more indent to "if" statement return for readability
---------
Co-authored-by: Joe Fernandez <joefernandez@users.noreply.github.com>
* Add GA tag injection to Kotlin API docs generation script
- Inject Google Analytics tag into all generated HTML files using awk
- Remove unnecessary gradle prerequisite check (script uses ./gradlew)
- Update prerequisites comment to clarify Android SDK requirement
* Regenerate ADK Kotlin 0.1.0 API docs with Google Analytics tag
* Add Redis integration entry
Adds an integration catalog entry for `adk-redis`
(https://github.com/redis-developer/adk-redis), the Python package
that provides Redis-backed ADK integrations:
- RedisVL-backed search tools (vector, hybrid, range, text, SQL),
including native FT.HYBRID on Redis 8.4+
- Session and long-term memory services that implement
BaseSessionService and BaseMemoryService against
Redis Agent Memory Server
- An McpToolset helper for RedisVL's own MCP server (`rvl mcp`),
alongside the existing Agent Memory Server MCP helper
- Self-hosted and managed (Redis LangCache) semantic cache providers
Built and previewed with `mkdocs build --strict`; the page renders at
/integrations/redis/ and appears on the catalog grid.
* Minor fixes to Redis integration page
* Use ADK's native McpToolset for the RedisVL MCP integration
Per maintainer guidance on the PR review thread:
- Replace `create_redisvl_mcp_toolset(...)` (a third-party Python
wrapper that adk-redis shipped briefly but does not ship in the
released 0.0.5) with ADK's native `McpToolset` plus
`StdioConnectionParams` + `StdioServerParameters(command="rvl", ...)`.
Matches the pattern used by every other MCP catalog page
(cartesia, chroma, mongodb, pinecone, qdrant).
- Add a `!!! note` admonition pointing readers to
`/tools-custom/mcp-tools/` if they want to connect to the `rvl mcp`
server from other ADK language SDKs.
- Rename the tab from "MCP toolset" to "RedisVL MCP server" and
prepend a one-paragraph explanation.
- Update the surface table at the top: split the single "MCP toolsets"
row into "RedisVL MCP" (native McpToolset against `rvl mcp`) and
"AMS MCP toolset" (`create_memory_mcp_toolset`).
- Update the "Available tools" table: replace the
`create_redisvl_mcp_toolset(...)` helper row with a description of
the `rvl mcp` server's exposed tools and how to wire `McpToolset`
to them.
Other clean-ups:
- Drop the `pip install 'adk-redis[mcp-search]'` line; the extra was
retired from adk-redis 0.0.5 along with the wrapper. Add a
`pip install 'redisvl[mcp]>=0.18.2'` line for the MCP CLI.
- Switch sample vectorizer to `redis/langcache-embed-v2`, matching
the repo's runnable examples and the rest of the adk-redis docs.
Verified with `mkdocs build --strict` locally. The admonition renders;
the link to `/tools-custom/mcp-tools/` resolves.
* Switch Redis catalog icon to the official Red wordmark SVG
The page previously used the Redis org GitHub avatar PNG (460x460,
cube mark). Swap to `Redis_Logo_Red_RGB.svg` from the official Redis
brand kit (sourced via redis/redis-vl-python), matching the logo used
in the adk-redis README hero. SVG is acceptable for catalog assets
(see goodmem.svg precedent).
Note: this asset is a wordmark (viewBox ~500x156), wider than peer
catalog cards which are mostly square. If it renders awkwardly on the
catalog grid, swap back to a square cube-mark variant.
- Add `docs/integrations/assets/redis.svg`.
- Update `catalog_icon` in `redis.md` frontmatter.
- Drop `docs/integrations/assets/redis.png`.
Verified with `mkdocs build --strict`.
* Formatting and minor edits
* fix: remove AMS MCP toolset mentions per reviewer feedback
Remove create_memory_mcp_toolset() references from the overview table
and MCP tools table. This wrapper was removed from adk-redis in v0.0.6
(redis-developer/adk-redis#13). Users should use ADK's native McpToolset
with SseConnectionParams for Agent Memory Server MCP access.
Resolves comments from @koverholt on lines 29 and 239.
* fix: reorder tabs and table to lead with MCP, fix count to four ways
* feat: add AMS MCP server tab and MCP table entry
Add a separate code tab showing how to connect ADK's native McpToolset
to Agent Memory Server's MCP endpoint over SSE, based on the
fitness_coach_mcp example. Also add a corresponding row to the MCP
reference table. Update overview count to five ways.
* fix: rename AMS MCP to Sessions + Memory MCP server
* feat: split Semantic cache tab into self-hosted and LangCache
Add a separate LangCache tab with accurate code snippet using
LangCacheProvider and LangCacheProviderConfig (cache_id, api_key,
server_url). No local vectorizer needed for the managed service.
* refactor: move semantic caching into its own section
Semantic caching is a cross-cutting optimization rather than a core
integration approach. Move the self-hosted (RedisVL) and managed
(LangCache) cache tabs out of 'Use with agent' into a dedicated
'## Semantic caching' section. Drop the cache row from the overview
table, leaving four core approaches.
* fix: add descriptions to Sessions + Memory and Search tools tabs
* fix: semantic search -> hybrid search in Sessions + Memory description
* docs: link to adk-redis mkdocs site in additional resources
Primary docs link now points to redis-developer.github.io/adk-redis/.
The redis.io integration page is kept as a secondary reference.
* Remove redundant MCP table - does not show tools; make approaches wording future proof
* Readd MCP table with tools and options as before
---------
Co-authored-by: Kristopher Overholt <koverholt@google.com>
* Add Python API docs generation script and Sphinx config
* Add Python API reference docs for ADK Python 2.0.0
* Include version and release number in config for built API docs
* Move adk web Visual Builder page content into Runtime > adk web page
* Clarify Visual Builder in intro
* Fix casing for consistency
* More casing fixes
* Move Visual Builder page under Web Interface
* Fix link from runtime index page
* Keep Visual Builder file at original path, nest under Web Interface in nav
---------
Co-authored-by: Joe Fernandez <joefernandez@users.noreply.github.com>
Juan Carlos Gonzalez Resendiz