### Adds one new tool to the Notion toolkit
* **AppendContentToEndOfPage**: Append markdown content to the end of a
Notion page by its ID or title
### Fixes a bug
* The **CreatePage** would previously fail if the content provided was
broken into more than 100 blocks. I added 'chunking' logic to support >
100 blocks.
This solves an edge case where the `"url"` entity does not have an
`"expanded_url"` case when expanding. The behavior for now is simply
don't replace the URL as it seems the display_url is NOT what we want to
keep as it's normally abbreviated
---------
Co-authored-by: Eric Gustin <34000337+EricGustin@users.noreply.github.com>
This PR adds a simplified Linear toolkit focused on core functionality:
## What's Included
**Tools:**
- `get_issue` - Get detailed information about Linear issues
- `get_teams` - Get team information and details
**Models:**
- `DateRange` enum with comprehensive date range support (TODAY,
YESTERDAY, THIS_WEEK, LAST_WEEK, THIS_MONTH, LAST_MONTH, THIS_YEAR,
LAST_YEAR, LAST_7_DAYS, LAST_30_DAYS)
- Timezone-aware datetime handling following Google toolkit patterns
## What's Simplified
This toolkit has been streamlined by removing:
- Cycles management tools
- Projects management tools
- Users management tools
- Workflows management tools
- Corresponding tests and evaluations for removed features
## Quality Assurance
- All linting and formatting checks pass
- Comprehensive test coverage for included functionality
- Follows established patterns from Google toolkit
---------
Co-authored-by: Eric Gustin <34000337+EricGustin@users.noreply.github.com>
This PR adds a new toolkit for integrating with Zendesk Help Center and
ticketing system.
Features
- Search Articles: Search Help Center knowledge base with filters for
text, categories, labels, and dates
- List Tickets: Retrieve all open support tickets
- Get Comments: Retrieve all comments for a specific ticket to
understand the context
- Add Comments: Add public or internal comments to existing tickets
- Solve Tickets: Mark tickets as solved with optional internal
resolution comments
Testing & Quality
- Comprehensive test suite
- Evaluation scripts for real-world testing
- All tests passing (make test)
- Code quality checks passing (make check)
- All evals passing
---------
Co-authored-by: “lgesuellip” <“lgesuellipinto@uade.edu.ar”>
Co-authored-by: lgesuellip <102637283+lgesuellip@users.noreply.github.com>
Co-authored-by: “lgesuellip” <lgesuellipinto@uade.edu.ar>
We know that forks won't have our secrets, so we separate those toolkits
out to new a new test group and skip them if you aren't in this main
repo. We know if a test suite has a secret via a magic comment
---------
Co-authored-by: Eric Gustin <34000337+EricGustin@users.noreply.github.com>
## Summary
This PR removes the requirement that all toolkits must have the arcade_
prefix and introduces a more flexible toolkit discovery system using
Python entry points.
### 🏷️ Flexible Toolkit Naming
* Community toolkits: Only add arcade_ prefix when the user is in
arcade-ai/toolkits/ directory and explicitly chooses to create a
community contribution.
* External toolkits: No prefix requirement - developers can name their
toolkits however they want
* Toolkit names are now determined by user choice rather than enforced
automatically
### 🔍 Entry Point Discovery
* Added find_arcade_toolkits_from_entrypoints() method to discover
toolkits via entry points
* Entry point group: arcade_toolkits with name: toolkit_name
* Updated pyproject.toml template to include entry point configuration
* Entry point discovery takes precedence over prefix-based discovery for
deduplication
### 📦 Backward Compatibility
* Existing arcade_* prefixed toolkits continue to work via
find_arcade_toolkits_from_prefix()
find_all_arcade_toolkits() now combines both discovery methods
* Deduplication logic prefers entry point toolkits over prefix-based
ones when package names match
### 🛠️ `arcade new` Template Updates
* pyproject.toml template for `arcade new` now includes entry point
configuration: [project.entry-points.arcade_toolkits]
### 🔧 Minor Improvements
* Refactored _strip_arcade_prefix() into a separate method for
reusability
* Updated variable naming for clarity (community_toolkit →
is_community_toolkit)
### Benefits
* Developer Freedom: Toolkit developers are no longer forced to use the
arcade_ prefix. They are also no longer forced to use the package name
as the toolkit name.
* Cleaner Naming: External toolkits can use more natural names (e.g.,
my_company_toolkit instead of arcade_my_company_toolkit)
* Better Discovery: Entry points provide a more standard Python
mechanism for plugin discovery
* Flexible Distribution: Toolkits can be distributed with any package
name while still being discoverable
### Testing
* Added comprehensive tests for the new entry point functionality
* Tests cover edge cases like deduplication, error handling, and
backward compatibility
### Version Bumps
arcade-core: 2.0.0 → 2.1.0
arcade-ai: 2.0.5 → 2.1.0
This change makes the Arcade toolkit ecosystem more flexible and
developer-friendly while maintaining full backward compatibility with
existing toolkits.
---------
Co-authored-by: Mateo Torres <mateo@arcade.dev>
Say you are @shubcodes and running arcade on replit or vs codespaces.
Today, `arcade login` assumes that the browser you've opened for the
auth flow's "localhost" is the same that is running the `arcade login`
command. If you are running on one of these remote code execution
environments, that won't be true.
Usage:
```
arcade login --callback-host "https://replit.com:9999/path/to/my/codespace"
```
Adds an example of a good "general case" SQL tool:
* enforces read-only mode
* hints to the LLM to discover the tables and schemas for the tables it
needs before any query
* uses RetryableToolErrors to hint to the LLM about what to do next
Docs: https://github.com/ArcadeAI/docs/pull/345
For testing, `TEST_POSTGRES_DATABASE_CONNECTION_STRING` has been set in
the repo (from Neon). details in 1 password.
<img width="1178" height="1091"
alt="464977013-49aff5e5-e301-4ca0-83b5-3ea742db2283"
src="https://github.com/user-attachments/assets/9344c27b-015d-4b91-907e-84f2e4193e16"
/>
New toolkit versions are release candidates now.
Also fixed a test for e2b toolkit.
Also, I am explicitly not running test for toolkits for the post merge
workflow because they are run on every PR commit (i.e., they must pass
before we even merge)
# Backwards-compatible refactoring of the Slack toolkit
Several performance improvements, streamlined tool set, and easier to
understand tool interfaces.
All "old" tools were kept for backwards compatibility, with the same
interfaces and response structure (but using the new and more performant
tools under the hood).
Full revision of unit-tests and evals.
## Streamlined tool set
Multiple groups of tools were streamlined into a single one:
* "get conversation metadata" from 5 tools to one;
* "send message" from 2 tools to one;
* "get users in conversation" from 3 tools to one;
* "get messages" from 4 tools to one
## New capabilities
* Messages retrieved are now populated with the users' names, apart from
ID: makes it easier for LLMs to reference who sent a message, were
mentioned, or reacted to a message
* Retrieve users by username, email, and/or ID (before we only supported
ID)
* Retrieve multiple users in a single tool call
## Concurrency controls
All operations issuing multiple requests concurrently now have a
`Semaphore` to limit the concurrency level. The limit can be controlled
through the `SLACK_MAX_CONCURRENT_REQUESTS` env var (defaults to 3).
## Networking performance improvement
Various operations that used to make multiple API calls are now executed
more efficiently:
### Find users by username
* Before: a full scan of `users_list` was required (potentially multiple
pages for large workspaces);
* Now it stops as soon as we have all users needed (yes, it was dumb
before)
### Get multiple users by their IDs
* Before: for each user ID, we made one API call to the `users_info`
endpoint
* Now: we call `list_users` and scan the results to match the user IDs
(an estimate of 99.5% of Slack workspaces have < 200 users; for large
workspaces, we may need to paginate `list_users`)
### Get a conversation by its users
* Before:
* Call to `list_conversations` (potentially paginating)
* For each conversation, one call to `conversations_members`
(potentially paginating)
* Then loop and find which conversation matches the users' IDs
* Now:
* A single call to `conversations_open`
# PR Description
## Split toolkits
This PR splits the `Microsoft`, `Google`, and `Search` toolkits into
multiple toolkits each.
* `Microsoft` --> `OutlookCalendar`, `OutlookMail`.
* `Google` -----> `GoogleCalendar`, `GoogleContacts`, `GoogleDocs`,
`GoogleDrive`, `Gmail`, `GoogleSheets`
* `Search` -----> `GoogleFinance`, `GoogleFlights`, `GoogleHotels`,
`GoogleJobs`, `GoogleMaps`, `GoogleNews`, `GoogleSearch`,
`GoogleShopping`, `Walmart`, `Youtube`
> The original monolithic toolkits (`Microsoft`, `Google`, `Search`) are
not removed in this PR. The plan is to keep those toolkits around while
we
> 1. Stop documenting the toolkits,
> 2. Stop displaying the toolkits in the dashboard, and
> 3. Help customers migrate over to the new split toolkits.
## Rename toolkits
This PR renames the following toolkits
* `Web` ------------> `Firecrawl`
* `CodeSandbox` ---> `E2B`
> The `Web` and `CodeSandbox` toolkits are not removed in this PR. The
plan is to keep them around while we
> 1. Stop documenting the toolkits,
> 2. Stop displaying the toolkits in the dashboard, and
> 3. Help customers migrate over to the new renamed toolkits.
## Rename tools
Since toolkit names were changed, this called for some tools to be
renamed as well.
* `GoogleSearch.SearchGoogle` ----------------> `GoogleSearch.Search`
* `GoogleShopping.SearchShoppingProducts` --->
`GoogleShopping.SearchProducts`
* `Walmart.SearchWalmartProducts` ------------> `Walmart.SearchProducts`
* `Walmart.GetWalmartProductDetails` --------->
`Walmart.GetProductDetails`
* `Youtube.SearchYoutubeVideos` -------------->
`Youtube.SearchForVideos`
## Google File Picker
Improvements to the Google File Picker experience were also added in
this PR.
The following tools will ALWAYS provide llm_instructions in their
response to "let the end-user know that they have the option to select
more files via the file picker url if they want to":
* `GoogleDocs.SearchDocuments`
* `GoogleDocs.SearchAndRetrieveDocuments`
* `GoogleDrive.GetFileTreeStructure`
The following tools will only provide the file picker URL if a 404 or
403 from the Google API:
* `GoogleDocs.InsertTextAtEndOfDocument`
* `GoogleDocs.GetDocumentById`
* `GoogleSheets.GetSpreadsheet`
* `GoogleSheets.WriteToCell`
Also, a standalone `GoogleDrive.GenerateGoogleFilePickerUrl` tool
exists.
## Other
* The `SearchDocuments` and `SearchAndRetrieveDocuments` tools used to
be organized within the Drive portion of the Google toolkit, but I moved
these into the new GoogleDocs toolkit because they are specific to Docs.
# Progress
- [x] `OutlookCalendar`
- [x] `OutlookMail`
- [x] `GoogleFinance`
- [x] `GoogleFlights`
- [x] `GoogleHotels`
- [x] `GoogleJobs`
- [x] `GoogleMaps`
- [x] `GoogleNews`
- [x] `GoogleSearch`
- [x] `GoogleShopping`
- [x] `Walmart`
- [x] `Youtube`
- [x] `GoogleCalendar`
- [x] `GoogleContacts`
- [x] `GoogleDocs`
- [x] `GoogleDrive`
- [x] `Gmail`
- [x] `GoogleSheets`
- [x] `Firecrawl`
- [x] `E2B`
- [x] File picker
# Discussion
* Repeated code is a consequence of splitting toolkits that use the same
provider. I am open to any ideas that would allow multiple toolkits to
reference common code. Comment your ideas in this PR.
This reintroduces a question into `arcade new`, which adds the ruff and
pre-commit files into new toolkits that are aimed to be contributed back
to Arcade AI.
I use it in the toolkit building tutorial
---------
Co-authored-by: Evan Tahler <evantahler@gmail.com>
`arcade deploy` is failing for local packages that have large unneeded
files such as `uv.lock`. It is failing because it is taking too long for
the CLI to compress and PUT to the cloud.
Update the Slack notification to use the "package" notification instead
of the "toolkit" notification since this workflow runs for not only
toolkits but also our libs.
The current `arcade new` command fails to `make install` and `make
check` if it's not manually patched with pre-commit files. It also fails
due to local dependencies if it's not run inside `arcade-ai/toolkits`
This PR patches the toolkit template to only include the local
dependencies if it detects is `arcade new` being run inside
`arcade-ai/toolkits`, it also makes pre-commit commands optional.
1. Patch, Minor, or Major is selected during workflow dispatch (defaults
to patch)
2. Get most recent release version
3. Calculate new version based on findings from step 2
4. Build wheels
5. Build worker and base-worker
6. Push to GHCR
7. Create new release with release notes
Also, I removed everything related to ECR
This is the first of a few PRs. Deploy to staging will fail until we
have `arcade-core`, `arcade-serve`, and `arcade-ai` released to PyPI.
This PR will release `arcade-core` to PyPI.
### PR Description
* Adds workflow that checks for changes in any pyproject.toml, and if
its version has changed, then tests, builds wheel, then publishes to
PyPI
* Updates the Dockerfile for our new structure
* Updates porter yamls
* Updates `make full-dist`
* Removes a couple unused workflows
Check out https://github.com/ArcadeAI/arcade-ai/actions/runs/15622059209
to see how the new workflow works (note that it failed publishing to
PyPI on purpose)
