# Overview
The previous installation instructions for the Toolbox binary only
provided a curl command for Linux AMD64 systems. This was confusing for
users on other platforms like macOS and Windows, who had to manually
figure out the correct download URL from the releases page.
This PR overhauls the installation process in both the `README.md` and
the official documentation site. It provides dedicated, copy-pasteable
commands for all major platforms and makes the download commands more
reliable.
# Changes
* Replaced the single, Linux-only installation command with a
multi-level tabbed/collapsible interface in both the `README.md` and the
official documentation.
* Added dedicated installation commands for multiple platforms,
including Windows (AMD64) that now using the native `Invoke-WebRequest`
in PowerShell.
* Updated all `curl` commands to include the `-L` flag.
* This makes the download more robust by automatically following any
HTTP redirects.
# Before
## `README.md`
<img width="1870" height="868" alt="image"
src="https://github.com/user-attachments/assets/28b714b5-1938-42cb-904b-3a4d61f1c56a"
/>
## Docsite
<img width="1728" height="788" alt="image"
src="https://github.com/user-attachments/assets/b63d579d-ce8f-4974-9860-1fee5a8d0dc7"
/>
# After
## `README.md`
<img width="1814" height="1082" alt="image"
src="https://github.com/user-attachments/assets/54985eaf-c721-4f11-86d2-cc027aeea0ad"
/>
## Docsite
<img width="2066" height="1112" alt="image"
src="https://github.com/user-attachments/assets/a07380b7-3b38-4b99-a95e-f942356f2200"
/>
Add `_meta` for `tools/list` method in MCP Toolbox.
If there are authorized invocation, the following will be return in
`_meta`:
```
{
"name":"my-tool-name",
"description":"my tool description",
"inputSchema":{
"type":"object",
"properties":{
"user_id":{"type":"string","description":"user's name from google login"}
},
"required":["user_id"]
},
"_meta":{
"toolbox/authParam":{"user_id":["my_auth"]}
}
}
```
If there are authenticated parameter, the following will be return in
`_meta`:
```
{
"name":"my-tool-name",
"description":"my tool description",
"inputSchema":{
"type":"object",
"properties":{
"sql":{"type":"string","description":"The sql to execute."}
},
"required":["sql"]
},
"_meta":{
"toolbox/authInvoke":["my_auth"]
}
}
```
If there are no authorized invocation or authenticated prameter, the
`_meta` field will be omitted.
With this feature, the following were updated in the source code:
* In each `func(p CommonParameter) McpManifest()`, we will return a
`[]string` for the list of authenticated parameters. This is similar to
how Manifest() return the list of authNames in non-MCP Toolbox's
manifest.
* The `func(ps Parameters) McpManifest()` will return a
`map[string][]string` that with key as param's name, and value as the
param's auth.
* Added a new function `GetMcpManifest()` in `tools.go`. This function
will consctruct the McpManifest, and add the `Metadata` field.
* Associated tests were added or updated.
Inline queries are directed to an undocumented endpoint so that they can
be tracked in Looker System Activity separately. The logic is to try the
undocumented endpoint first, and if there is any error, fall back to the
documented endpoint.
This was done in multiple places. This PR combines that logic into one
helper function, reducing the duplication of code.
This PR contains the following updates:
| Package | Change | Age | Confidence |
|---|---|---|---|
| [google-adk](https://redirect.github.com/google/adk-python)
([changelog](https://redirect.github.com/google/adk-python/blob/main/CHANGELOG.md))
| `==1.14.1` -> `==1.15.0` |
[](https://docs.renovatebot.com/merge-confidence/)
|
[](https://docs.renovatebot.com/merge-confidence/)
|
---
### Release Notes
<details>
<summary>google/adk-python (google-adk)</summary>
###
[`v1.15.0`](https://redirect.github.com/google/adk-python/blob/HEAD/CHANGELOG.md#1150-2025-09-24)
[Compare
Source](https://redirect.github.com/google/adk-python/compare/v1.14.1...v1.15.0)
##### Features
- \[Core]
- Adding the ContextFilterPlugin
([a06bf27](a06bf278cb))
- Adds plugin to save artifacts for issue
[#​2176](https://redirect.github.com/google/adk-python/issues/2176)
([657369c](657369cffe))
- Expose log probs of candidates in LlmResponse
([f7bd3c1](f7bd3c111c))
- \[Context Caching]
- Support context caching
([c66245a](c66245a3b8))
- Support explicit context caching auto creation and lifecycle
management.
Usage: `App(root_agent=..., plugins=..., context_cache_config=...)`
- Support non-text content in static instruction
([61213ce](61213ce4d4))
- Support static instructions
([9be9cc2](9be9cc2fee))
- Support static instruction that won't change, put at the beginning of
the instruction.
Static instruction support inline\_data and file\_data as contents.
Dynamic instruction moved to the end of LlmRequest, increasing prefix
caching matching size.
Usage:
`LlmAgent(model=...,static_instruction =types.Content(parts=...), ... )`
- \[Telemetry]
- Add --otel\_to\_cloud experimental support
([1ae0b82](1ae0b82f56),
[b131268](b1312680f4),
[7870480](7870480c63))
- Add GenAI Instrumentation if --otel\_to\_cloud is enabled
([cee365a](cee365a13d))
- Support standard OTel env variables for exporter endpoints
([f157b2e](f157b2ee4c))
- Temporarily disable Cloud Monitoring integration in --otel\_to\_cloud
([3b80337](3b80337faf))
- \[Services]
- Add endpoint to generate memory from session
([2595824](25958242db))
- \[Tools]
- Add Google Maps Grounding Tool to ADK
([6b49391](6b49391546))
- **MCP:** Initialize tool\_name\_prefix in MCPToolse
([86dea5b](86dea5b53a))
- \[Evals]
- Data model for storing App Details and data model for steps
([01923a9](01923a9227))
- Adds Rubric based final response evaluator
([5a485b0](5a485b01cd))
- Populate AppDetails to each Invocation
([d486795](d48679582d))
- \[Samples]
- Make the bigquery sample agent run with ADC out-of-the-box
([10cf377](10cf377494))
##### Bug Fixes
- Close runners after running eval
([86ee6e3](86ee6e3fa3))
- Filter out thought parts when saving agent output to state
([632bf8b](632bf8b0bc))
- Ignore empty function chunk in LiteLlm streaming response
([8a92fd1](8a92fd18b6))
- Introduces a `raw_mcp_tool` method in `McpTool` to provide direct
access to the underlying MCP tool
([6158075](6158075a65))
- Make a copy of the `columns` instead of modifying it in place
([aef1ee9](aef1ee97a5))
- Prevent escaping of Latin characters in LLM response
([c9ea80a](c9ea80af28))
- Retain the consumers and transport registry when recreating the
ClientFactory in remote\_a2a\_agent.py
([6bd33e1](6bd33e1be3))
- Remove unsupported 'type': 'unknown' in test\_common.py for fastapi
0.117.1
([3745221](374522197f))
##### Documentation
- Correct the documentation of `after_agent_callback`
([b9735b2](b9735b2193))
</details>
---
### Configuration
📅 **Schedule**: Branch creation - At any time (no schedule defined),
Automerge - At any time (no schedule defined).
🚦 **Automerge**: Disabled by config. Please merge this manually once you
are satisfied.
♻ **Rebasing**: Whenever PR becomes conflicted, or you tick the
rebase/retry checkbox.
🔕 **Ignore**: Close this PR and you won't be reminded about this update
again.
---
- [ ] <!-- rebase-check -->If you want to rebase/retry this PR, check
this box
---
This PR was generated by [Mend Renovate](https://mend.io/renovate/).
View the [repository job
log](https://developer.mend.io/github/googleapis/genai-toolbox).
<!--renovate-debug:eyJjcmVhdGVkSW5WZXIiOiI0MS4xMzAuMSIsInVwZGF0ZWRJblZlciI6IjQxLjEzMC4xIiwidGFyZ2V0QnJhbmNoIjoibWFpbiIsImxhYmVscyI6W119-->
## Description
---
Add mssql's prebuilt tools tests to cloud-sql-mssql integration tests.
Cloud sql mssql's integration test coverage check against the mssql
package since those tools are compatible. Hence, when we add new tools
to mssql, we will have to add those integration tests against cloud sql
mssql as well.
## Description
---
> Should include a concise description of the changes (bug or feature),
it's
> impact, along with a summary of the solution
## PR Checklist
---
> Thank you for opening a Pull Request! Before submitting your PR, there
are a
> few things you can do to make sure it goes smoothly:
- [ ] Make sure you reviewed
[CONTRIBUTING.md](https://github.com/googleapis/genai-toolbox/blob/main/CONTRIBUTING.md)
- [ ] Make sure to open an issue as a
[bug/issue](https://github.com/googleapis/genai-toolbox/issues/new/choose)
before writing your code! That way we can discuss the change, evaluate
designs, and agree on the general idea
- [ ] Ensure the tests and linter pass
- [ ] Code coverage does not decrease (if any source code was changed)
- [ ] Appropriate docs were updated (if necessary)
- [ ] Make sure to add `!` if this involve a breaking change
🛠️ Fixes #<issue_number_goes_here>
## Description
This introduces a breaking change. The bigquery-execute-sql tool will
now enforce the allowed datasets setting from its BigQuery source
configuration. Previously, this setting had no effect on the tool.
---
> Should include a concise description of the changes (bug or feature),
it's
> impact, along with a summary of the solution
## PR Checklist
---
> Thank you for opening a Pull Request! Before submitting your PR, there
are a
> few things you can do to make sure it goes smoothly:
- [ ] Make sure you reviewed
[CONTRIBUTING.md](https://github.com/googleapis/genai-toolbox/blob/main/CONTRIBUTING.md)
- [ ] Make sure to open an issue as a
[bug/issue](https://github.com/googleapis/genai-toolbox/issues/new/choose)
before writing your code! That way we can discuss the change, evaluate
designs, and agree on the general idea
- [ ] Ensure the tests and linter pass
- [ ] Code coverage does not decrease (if any source code was changed)
- [ ] Appropriate docs were updated (if necessary)
- [ ] Make sure to add `!` if this involve a breaking change
🛠️ Fixes https://github.com/googleapis/genai-toolbox/issues/873
---------
Co-authored-by: Yuan Teoh <45984206+Yuan325@users.noreply.github.com>
This PR contains the following updates:
| Package | Type | Update | Change |
|---|---|---|---|
|
[google.golang.org/genproto](https://redirect.github.com/googleapis/go-genproto)
| require | digest | `ef028d9` -> `9219d12` |
---
### Configuration
📅 **Schedule**: Branch creation - At any time (no schedule defined),
Automerge - At any time (no schedule defined).
🚦 **Automerge**: Disabled by config. Please merge this manually once you
are satisfied.
♻ **Rebasing**: Whenever PR becomes conflicted, or you tick the
rebase/retry checkbox.
🔕 **Ignore**: Close this PR and you won't be reminded about this update
again.
---
- [ ] <!-- rebase-check -->If you want to rebase/retry this PR, check
this box
---
This PR was generated by [Mend Renovate](https://mend.io/renovate/).
View the [repository job
log](https://developer.mend.io/github/googleapis/genai-toolbox).
<!--renovate-debug:eyJjcmVhdGVkSW5WZXIiOiI0MS45Ny4xMCIsInVwZGF0ZWRJblZlciI6IjQxLjk3LjEwIiwidGFyZ2V0QnJhbmNoIjoibWFpbiIsImxhYmVscyI6W119-->
Co-authored-by: Averi Kitsch <akitsch@google.com>
## Description
---
### What
Fixed a bug where `FilterParams` was being concatenated twice in the
parameter list for MongoDB update operations.
### Why
The duplicate concatenation would cause parameter validation to fail
during tool initialization, preventing the MongoDB update tools from
working.
### Changes
- `mongodbupdateone.go`: Fixed `slices.Concat()` to properly combine
FilterParams and UpdateParams
- `mongodbupdatemany.go`: Fixed `slices.Concat()` to properly combine
FilterParams and UpdateParams
## PR Checklist
---
> Thank you for opening a Pull Request! Before submitting your PR, there
are a
> few things you can do to make sure it goes smoothly:
- [x] Make sure you reviewed
[CONTRIBUTING.md](https://github.com/googleapis/genai-toolbox/blob/main/CONTRIBUTING.md)
- [x] Make sure to open an issue as a
[bug/issue](https://github.com/googleapis/genai-toolbox/issues/new/choose)
before writing your code! That way we can discuss the change, evaluate
designs, and agree on the general idea
- [x] Ensure the tests and linter pass
- [x] Code coverage does not decrease (if any source code was changed)
- [x] Appropriate docs were updated (if necessary)
- [x] Make sure to add `!` if this involve a breaking change
## Description
---
This introduces a breaking change. The bigquery-forecast tool will now
enforce the allowed datasets setting from its BigQuery source
configuration. Previously, this setting had no effect on the tool.
## PR Checklist
---
> Thank you for opening a Pull Request! Before submitting your PR, there
are a
> few things you can do to make sure it goes smoothly:
- [ ] Make sure you reviewed
[CONTRIBUTING.md](https://github.com/googleapis/genai-toolbox/blob/main/CONTRIBUTING.md)
- [ ] Make sure to open an issue as a
[bug/issue](https://github.com/googleapis/genai-toolbox/issues/new/choose)
before writing your code! That way we can discuss the change, evaluate
designs, and agree on the general idea
- [ ] Ensure the tests and linter pass
- [ ] Code coverage does not decrease (if any source code was changed)
- [ ] Appropriate docs were updated (if necessary)
- [ ] Make sure to add `!` if this involve a breaking change
🛠️ Fixes #<issue_number_goes_here>
---------
Co-authored-by: Yuan Teoh <45984206+Yuan325@users.noreply.github.com>
[Cassandra](https://cassandra.apache.org/_/cassandra-basics.html) is a
NoSQL distributed database. By design, NoSQL databases are lightweight,
open-source, non-relational, and largely distributed. Counted among
their strengths are horizontal scalability, distributed architectures,
and a flexible approach to schema definition.
Cassandra go driver link -
https://pkg.go.dev/github.com/apache/cassandra-gocql-driver/v2
This PR
- adds a new source for cassandra
- adds a new tool _cassandra-cql_ with support for executing predefined
parameterized CQL queries on cassandra
- adds unit and integration tests for the tool and the source
- adds documentation for the cassandra source and cassandra-cql tool
---------
Co-authored-by: Wenxin Du <117315983+duwenxin99@users.noreply.github.com>
Co-authored-by: duwenxin <duwenxin@google.com>
## Description
Follows up https://github.com/googleapis/genai-toolbox/pull/1274/ with a
list tables tool for ClickHouse
## PR Checklist
---
> Thank you for opening a Pull Request! Before submitting your PR, there
are a
> few things you can do to make sure it goes smoothly:
- [x] Make sure you reviewed
[CONTRIBUTING.md](https://github.com/googleapis/genai-toolbox/blob/main/CONTRIBUTING.md)
- [ ] Make sure to open an issue as a
[bug/issue](https://github.com/googleapis/genai-toolbox/issues/new/choose)
before writing your code! That way we can discuss the change, evaluate
designs, and agree on the general idea
- [x] Ensure the tests and linter pass
- [x] Code coverage does not decrease (if any source code was changed)
- [x] Appropriate docs were updated (if necessary)
- [ ] Make sure to add `!` if this involve a breaking change
🛠️ Fixes #<issue_number_goes_here>
---------
Co-authored-by: Pete Hampton <pjhampton@users.noreply.github.com>
Co-authored-by: Averi Kitsch <akitsch@google.com>
## Description
---
Added `DatabaseId` to the Firestore Source and Firestore-Get-Rules tool
for fetching the granular per-database rules instead of rules for the
default database.
## PR Checklist
---
> Thank you for opening a Pull Request! Before submitting your PR, there
are a
> few things you can do to make sure it goes smoothly:
- [x] Make sure you reviewed
[CONTRIBUTING.md](https://github.com/googleapis/genai-toolbox/blob/main/CONTRIBUTING.md)
- [x] Make sure to open an issue as a
[bug/issue](https://github.com/googleapis/genai-toolbox/issues/new/choose)
before writing your code! That way we can discuss the change, evaluate
designs, and agree on the general idea
- [x] Ensure the tests and linter pass
- [x] Code coverage does not decrease (if any source code was changed)
- [x] Appropriate docs were updated (if necessary)
- [x] Make sure to add `!` if this involve a breaking change
---------
Co-authored-by: Averi Kitsch <akitsch@google.com>
## Description
---
> Should include a concise description of the changes (bug or feature),
it's
> impact, along with a summary of the solution
## PR Checklist
---
> Thank you for opening a Pull Request! Before submitting your PR, there
are a
> few things you can do to make sure it goes smoothly:
- [ ] Make sure you reviewed
[CONTRIBUTING.md](https://github.com/googleapis/genai-toolbox/blob/main/CONTRIBUTING.md)
- [ ] Make sure to open an issue as a
[bug/issue](https://github.com/googleapis/genai-toolbox/issues/new/choose)
before writing your code! That way we can discuss the change, evaluate
designs, and agree on the general idea
- [ ] Ensure the tests and linter pass
- [ ] Code coverage does not decrease (if any source code was changed)
- [ ] Appropriate docs were updated (if necessary)
- [ ] Make sure to add `!` if this involve a breaking change
🛠️ Fixes #<issue_number_goes_here>
## Description
---
A `mysql-list-tables-missing-index` tool searches tables that do not
have primary or unique indices in a MySQL database. It's compatible
with:
- cloud-sql-mysql
- mysql
`mysql-list-tables-missing-index` outputs table names, including
`table_schema` and `table_name` in JSON format. It takes 2 optional
input parameters:
- `table_schema` (optional): Only check tables in this specific
schema/database. Search all visible tables in all visible databases if
not specified.
- `limit` (optional): max number of queries to return, default `50`.
## Example
```yaml
tools:
list_tables_missing_index:
kind: mysql-list-tables-missing-index
source: my-mysql-instance
description: Find tables that do not have primary or unique key constraint. A primary key or unique key is the only mechanism that guaranttes a row is unique. Without them, the database-level protection against data integrity issues will be missing.
```
The response is a json array with the following fields:
```json
{
"table_schema": "the schema/database this table belongs to",
"table_name": "name of the table",
}
```
## Reference
| **field** | **type** | **required** | **description** |
|-------------|:------------------------------------------:|:------------:|--------------------------------------------------------------------------------------------------|
| kind | string | true | Must be "mysql-list-active-queries". |
| source | string | true | Name of the source the SQL should execute on.
|
| description | string | true | Description of the tool that is passed
to the LLM. |
## PR Checklist
---
> Thank you for opening a Pull Request! Before submitting your PR, there
are a
> few things you can do to make sure it goes smoothly:
- [x] Make sure you reviewed
[CONTRIBUTING.md](https://github.com/googleapis/genai-toolbox/blob/main/CONTRIBUTING.md)
- [x] Make sure to open an issue as a
[bug/issue](https://github.com/googleapis/genai-toolbox/issues/new/choose)
before writing your code! That way we can discuss the change, evaluate
designs, and agree on the general idea
- [x] Ensure the tests and linter pass
- [x] Code coverage does not decrease (if any source code was changed)
- [x] Appropriate docs were updated (if necessary)
- [x] Make sure to add `!` if this involve a breaking change
---------
Co-authored-by: Averi Kitsch <akitsch@google.com>
## Description
---
Update prebuilt reference documentation with cloud sql admin tools,
correct tool names for alloydb and firestore.
## PR Checklist
---
> Thank you for opening a Pull Request! Before submitting your PR, there
are a
> few things you can do to make sure it goes smoothly:
- [x] Make sure you reviewed
[CONTRIBUTING.md](https://github.com/googleapis/genai-toolbox/blob/main/CONTRIBUTING.md)
- [x] Make sure to open an issue as a
[bug/issue](https://github.com/googleapis/genai-toolbox/issues/new/choose)
before writing your code! That way we can discuss the change, evaluate
designs, and agree on the general idea
- [x] Ensure the tests and linter pass
- [x] Code coverage does not decrease (if any source code was changed)
- [x] Appropriate docs were updated (if necessary)
- [ ] Make sure to add `!` if this involve a breaking change
🛠️ Fixes #<issue_number_goes_here>
Co-authored-by: Averi Kitsch <akitsch@google.com>
## Description
A `mysql-list-table-fragmentation` tool checks table fragmentation of
MySQL tables by calculating the size of the data and index files in
bytes and comparing with free space allocated to each table. This tool
calculates `fragmentation_percentage` which represents the proportion of
free space relative to the total data and index size. It's compatible
with
- cloud-sql-mysql
- mysql
`mysql-list-table-fragmentation` outputs detailed information as JSON ,
ordered by the fragmentation percentage in descending order.
This tool takes 4 optional input parameters:
- `table_schema` (optional): The database where fragmentation check is
to be executed. Check all tables visible to the current user if not
specified.
- `table_name` (optional): Name of the table to be checked. Check all
tables visible to the current user if not specified.
- `data_free_threshold_bytes` (optional): Only show tables with at least
this much free space in bytes. Default 1.
- `limit` (optional): Max rows to return, default 10.
## Example
```yaml
tools:
list_table_fragmentation:
kind: mysql-list-table-fragmentation
source: my-mysql-instance
description: List table fragmentation in MySQL, by calculating the size of the data and index files and free space allocated to each table. The query calculates fragmentation percentage which represents the proportion of free space relative to the total data and index size. Storage can be reclaimed for tables with high fragmentation using OPTIMIZE TABLE.
```
The response is a json array with the following fields:
```json
{
"table_schema": "The schema/database this table belongs to",
"table_name": "Name of this table",
"data_size": "Size of the table data in bytes",
"index_size": "Size of the table's indexes in bytes",
"data_free": "Free space (bytes) available in the table's data file",
"fragmentation_percentage": "How much fragementation this table has",
}
```
## PR Checklist
---
> Thank you for opening a Pull Request! Before submitting your PR, there
are a
> few things you can do to make sure it goes smoothly:
- [x] Make sure you reviewed
[CONTRIBUTING.md](https://github.com/googleapis/genai-toolbox/blob/main/CONTRIBUTING.md)
- [x] Make sure to open an issue as a
[bug/issue](https://github.com/googleapis/genai-toolbox/issues/new/choose)
before writing your code! That way we can discuss the change, evaluate
designs, and agree on the general idea
- [x] Ensure the tests and linter pass
- [x] Code coverage does not decrease (if any source code was changed)
- [x] Appropriate docs were updated (if necessary)
- [x] Make sure to add `!` if this involve a breaking change
---------
Co-authored-by: Yuan Teoh <45984206+Yuan325@users.noreply.github.com>
Co-authored-by: Averi Kitsch <akitsch@google.com>
## Description
---
> Should include a concise description of the changes (bug or feature),
it's
> impact, along with a summary of the solution
## PR Checklist
---
> Thank you for opening a Pull Request! Before submitting your PR, there
are a
> few things you can do to make sure it goes smoothly:
- [ ] Make sure you reviewed
[CONTRIBUTING.md](https://github.com/googleapis/genai-toolbox/blob/main/CONTRIBUTING.md)
- [ ] Make sure to open an issue as a
[bug/issue](https://github.com/googleapis/genai-toolbox/issues/new/choose)
before writing your code! That way we can discuss the change, evaluate
designs, and agree on the general idea
- [ ] Ensure the tests and linter pass
- [ ] Code coverage does not decrease (if any source code was changed)
- [ ] Appropriate docs were updated (if necessary)
- [ ] Make sure to add `!` if this involve a breaking change
🛠️ Fixes #<issue_number_goes_here>
This PR contains the following updates:
| Package | Change | Age | Confidence |
|---|---|---|---|
| [google-adk](https://redirect.github.com/google/adk-python)
([changelog](https://redirect.github.com/google/adk-python/blob/main/CHANGELOG.md))
| `==1.13.0` -> `==1.14.1` |
[](https://docs.renovatebot.com/merge-confidence/)
|
[](https://docs.renovatebot.com/merge-confidence/)
|
---
### Release Notes
<details>
<summary>google/adk-python (google-adk)</summary>
###
[`v1.14.1`](https://redirect.github.com/google/adk-python/blob/HEAD/CHANGELOG.md#1141-2025-09-12)
[Compare
Source](https://redirect.github.com/google/adk-python/compare/v1.14.0...v1.14.1)
##### Bug Fixes
- Fix logging issues with RemoteA2aAgent
[0c1f1fa](0c1f1fadeb)
###
[`v1.14.0`](https://redirect.github.com/google/adk-python/blob/HEAD/CHANGELOG.md#1140-2025-09-10)
[Compare
Source](https://redirect.github.com/google/adk-python/compare/v1.13.0...v1.14.0)
##### Features
- \[A2A]
- Allow users to pass their own agent card to to\_a2a method
[a1679da](a1679dae3f)
- Allow custom part converters in A2A classes
[b05fef9](b05fef9ba7)
- \[Tools]
- Allow setting agent/application name and compute project for BigQuery
tools
[11a2ffe](11a2ffe35a)
- Add BigQuery forecast tool
[0935a40](0935a40011)
- Add GkeCodeExecutor for sandboxed code execution on GKE
[72ff9c6](72ff9c64a2)
- Add a tool confirmation flow that can guard tool execution with
explicit confirmation and custom input
[a17bcbb](a17bcbb2aa)
- Add audience and prompt as configurable for OAuth flows
[edda922](edda922791)
- Allow user specify embedding model for file retrieval
[67f23df](67f23df25a)
- \[Core]
- Allow all possible values for `agent_class` field in all Agent Configs
[3bc2d77](3bc2d77b4d)
- Allow agent loader to load built-in agents from special directories in
adk folder
[578fad7](578fad7034)
- Upgrade ADK runner to use App in addition to root\_agent
[4df79dd](4df79dd5c9)
- Allow inject artifact into instructions
[bb4cfde](bb4cfdec12)
- \[Misc] Create an initial ADK release analyzer agent to find the doc
updates needed between releases
[e3422c6](e3422c616d)
##### Bug Fixes
- Add a NOTE to agent transfer instructions listing available agents
[43eec82](43eec82f84)
- Fix pagination of list\_sessions in VertexAiSessionService
[e63fe0c](e63fe0c0eb)
- Fix AttributeError and indentation in parameter processing of LiteLlm
[1e23652](1e23652968)
- Allow AgentTool to inherit/use plugins from its invocation context
when running
[1979dcf](1979dcf496)
- Enforce foreign key constraint for SQLite DB
[0c87907](0c87907bcb)
- Add back installing requirements.txt to Dockerfile template for cloud
run
[8e43f0d](8e43f0dd83)
- Only process the auth responses in the last event with content (if
applicable i.e. it's authored by user)
[3b922a2](3b922a2f6d)
- Extract a utility for aggregating partial streaming responses and
emitting LlmResponses for them as needed
[7975e8e](7975e8e196)
- Support saving text artifacts in GCS artifact service
[cecf7e8](cecf7e805d)
- Fixes `thought` handling in contents.py and refactors its unit tests
[a30851e](a30851ee16)
- Fixes the `thought` field handling in \_planning.py
[fe8b37b](fe8b37b0d3)
- Pass state\_delta to runner in /run endpoint
[a3410fa](a3410fab7b)
- Fix discussion answering github action workflow to escape the quote in
the discussion content JSON
[43c9681](43c96811da)
- Send full MIME types for image/video/pdf in get\_content
[e45c3be](e45c3be238)
- Fix flaky unit tests:
tests/unittests/flows/llm\_flows/test\_functions\_simple.py
[b92b288](b92b288c97)
- Make UT of a2a consistent about how tests should be skipped when
python verison < 3.10
[98b0426](98b0426cd2)
##### Improvements
- Update contribution guide
[8174a29](8174a29c6d)
- Skip PR triage for already triaged or Google-contributor PRs
[78eea1a](78eea1aa55)
- Avoid mutable default arguments in `local_eval_service` and `runners`
[64f11a6](64f11a6a67)
- Avoid mutable default arguments in `local_eval_service` and `runners`
[5b465fd](5b465fd71b)
- Reorder dependencies in `pyproject.toml`
[ca5f7f1](ca5f7f1ff0)
- Follow pydantic convention to make field\_validator a public method
[1448406](14484065c6)
- Update comment to clarify `after_run` callbacks
[7720616](7720616c5f)
- Tune instructions to not ask root directory if it's already provided
in the context
[25df6c2](25df6c22d5)
- Load discussion data from event content to avoid additional GraphQL
API call
[a503a0c](a503a0c807)
- Refactor discussion answering agent to merge answer\_discussions.py
into main.py
[408d3df](408d3dfeb1)
- Add community repo dependency group to pyproject toml
[7b077ac](7b077ac351)
- Add warning for using Gemini models via LiteLLM
[9291daa](9291daaa8e)
##### Documentation
- Update root\_agent description for clarity
[467df1a](467df1a36f)
- Update the ask\_data\_insights docstring
[aad1533](aad153322e)
- Add contributing Spanner tools RAG agent sample
[fcd748e](fcd748e17f)
##### Tests
- Add functional telemetry tests
[bc6b546](bc6b5462a7)
- Add unit tests for the `App` class and improve `Runner` initialization
tests
[fc90ce9](fc90ce968f)
##### Chores
- Use lazy % formatting in logging functions to fix pylint warnings
[b431072](b4310727d9)
- Update release cadence in README
[decc19b](decc19b188)
- Add `custom_metadata` to DatabaseSessionService
[fb009d8](fb009d8ea6)
- Update create\_session endpoint to use Request message as post body
[219815d](219815d2d7)
</details>
---
### Configuration
📅 **Schedule**: Branch creation - At any time (no schedule defined),
Automerge - At any time (no schedule defined).
🚦 **Automerge**: Disabled by config. Please merge this manually once you
are satisfied.
♻ **Rebasing**: Whenever PR becomes conflicted, or you tick the
rebase/retry checkbox.
🔕 **Ignore**: Close this PR and you won't be reminded about this update
again.
---
- [ ] <!-- rebase-check -->If you want to rebase/retry this PR, check
this box
---
This PR was generated by [Mend Renovate](https://mend.io/renovate/).
View the [repository job
log](https://developer.mend.io/github/googleapis/genai-toolbox).
<!--renovate-debug:eyJjcmVhdGVkSW5WZXIiOiI0MS45Ny4xMCIsInVwZGF0ZWRJblZlciI6IjQxLjk3LjEwIiwidGFyZ2V0QnJhbmNoIjoibWFpbiIsImxhYmVscyI6W119-->
Co-authored-by: Twisha Bansal <58483338+twishabansal@users.noreply.github.com>
Anubhav Dhawan