mirror of https://github.com/windmill-labs/windmill.git synced 2026-08-18 16:02:10 +00:00

Files

T

claude[bot] 6be060bea8 feat(ai): add websearch tool for AI agents (#7399 )

* refactor(ai): use responses API for OpenAI/Azure, create 'other' provider for completion endpoint

- Created new 'other.rs' provider using the OpenAI-compatible completion endpoint
- Refactored 'openai.rs' to use the Responses API for both text and image output
- Updated query_builder to route OpenAI/AzureOpenAI to OpenAIQueryBuilder
- All other providers (Mistral, DeepSeek, Groq, etc.) now use OtherQueryBuilder
- Updated OpenRouter to delegate to OtherQueryBuilder instead of OpenAIQueryBuilder

This prepares the codebase for adding websearch tool support using the Responses API.

Co-authored-by: windmill-internal-app[bot] <windmill-internal-app[bot]@users.noreply.github.com>

* feat(ai): add websearch as AI agent tool type

- Added WebsearchToolValue to ToolValue enum in flows.rs
- Updated all pattern matches to handle websearch tool type
- Added has_websearch parameter to run_agent function
- Websearch tools don't require additional configuration

This prepares the backend for provider-specific websearch implementations.

Co-authored-by: windmill-internal-app[bot] <windmill-internal-app[bot]@users.noreply.github.com>

* feat(frontend): add websearch as tool option in AI agent UI

- Added WebsearchTool type and utility functions to agentToolUtils.ts
- Added "Web Search" option in tool insertion menu (InsertModuleInner)
- Updated NewAIToolNode to handle pickWebsearchTool event
- Updated AIToolNode to render websearch tools properly
- Updated FlowModuleSchemaMap to create websearch tools

Users can now add websearch tools to AI agents through the UI.

Co-authored-by: windmill-internal-app[bot] <windmill-internal-app[bot]@users.noreply.github.com>

* feat(ai): implement websearch for OpenAI provider

- Added has_websearch parameter to BuildRequestArgs
- OpenAI provider now adds web_search tool to requests when enabled
- Uses OpenAI Responses API web_search tool type
- Websearch tool is added before other custom tools in the request

Implements websearch functionality for OpenAI and Azure OpenAI providers.

Co-authored-by: windmill-internal-app[bot] <windmill-internal-app[bot]@users.noreply.github.com>

* feat(ai): implement websearch for Anthropic provider

- Created anthropic.rs provider with native Anthropic API format
- Added web_search tool to Anthropic requests when enabled
- Anthropic uses /messages endpoint with x-api-key authentication
- Updated query_builder to route Anthropic to new provider

Implements websearch functionality for Anthropic Claude models.

Co-authored-by: windmill-internal-app[bot] <windmill-internal-app[bot]@users.noreply.github.com>

* feat(ai): implement websearch for Gemini/GoogleAI provider

- GoogleAI now uses completion endpoint (other.rs) for text instead of responses API
- Added Google Search grounding when websearch is enabled
- Uses google_search_retrieval tool in request when has_websearch is true
- Updated parse methods to use OtherQueryBuilder for completion endpoint

Implements websearch functionality for Google Gemini models.

Co-authored-by: windmill-internal-app[bot] <windmill-internal-app[bot]@users.noreply.github.com>

* fix frontend

* fix anthropic and openai

* better for gemini

* structured output

* cleaning

* fix validate tool

* fixes

* cleaning

* cleaning

* fix for openai

* no responses api for azure

* fixes

* fix

* add tests for ai agent

* avoid panic

* better tests

* test user images

* fix tool choice

* always use streaming backend side

* big cleaning

* show annotations plus agent action for open ai websearch use

* show annotations plus agent action for anthropic websearch use

* show annotations plus agent action for google websearch use

* nit forntend

* rm

* fix

* add test for image ouptut

* fix for azure

* add in openflow

* fix

* fix

* nit tests

* fixes

---------

Co-authored-by: claude[bot] <41898282+claude[bot]@users.noreply.github.com>
Co-authored-by: windmill-internal-app[bot] <windmill-internal-app[bot]@users.noreply.github.com>
Co-authored-by: centdix <farhadg110@gmail.com>

2025-12-22 11:41:28 +00:00

ai_agent_tests

feat(ai): add websearch tool for AI agents (#7399 )

2025-12-22 11:41:28 +00:00

test

extra logging for agent_token flake (#5693 )

2025-05-01 19:46:52 +02:00

verdaccio

chore: eetest (#2937 )

2023-12-30 03:29:00 +01:00

.gitignore

feat(ai): add websearch tool for AI agents (#7399 )

2025-12-22 11:41:28 +00:00

build.sh

chore: eetest (#2937 )

2023-12-30 03:29:00 +01:00

common.sh

chore: eetest (#2937 )

2023-12-30 03:29:00 +01:00

docker-compose.yml

chore: eetest (#2937 )

2023-12-30 03:29:00 +01:00

README.md

chore: eetest (#2937 )

2023-12-30 03:29:00 +01:00

requirements.txt

agent integration tests (#5684 )

2025-04-29 23:55:38 +02:00

run.sh

chore: eetest (#2937 )

2023-12-30 03:29:00 +01:00

README.md

Windmill integration tests

Integration that are run on every push to the main branch (excluding tags)

The concept is the following:

It pulls the latest published image with the version from (version.txt)[../version.txt] and deploys a Windmill stack using the (docker-compose.yml)[docker-compose.yml]
It runs the tests using python testing framework (python -m unittest -v test). All test classes exported in (__init__.py)[./test/__init__py] will be run
Then it upgrades the stack to the latest (unpublished) version of Windmill built for this commit. It expects a docker image with the tag dev to be present.
It re-runs the tests with the following env var: WMILL_RUNNING_DEV set to 1

Some tests behaves differently depending on WMILL_RUNNING_DEV. This way we can test that scripts/flows/schedules... deployed on a previous version of Windmill won't break with the upgrade Some tests are skipped unless WMILL_RUNNING_DEV == 1, those are just regular integration tests that just needs to be run on the dev version.

Running locally

Running the tests locally is not easy given that we need to have a Docker image running the latest version of the code. However, the tests simply reaches Windmill API on http://localhost:8000, so it can easily be modified to run alongside a simple cargo run --features enterprise.

Note that Windmill Enterprise version is required, you'll need a license key for all the tests to run. It needs to be set to the environment variable: WM_LICENSE_KEY_CI

For example, to run identity_script_test.py, you can do the following:

In one terminal, run your local version of Windmill:

cargo run --features enterprise

Then in another tab, run the test:

python -m unittest -v test.TestIdentityScript

Some tests requires additional setup. This is the case of the SDK tests, which requires Windmill SDK package to be published to either private NPM registry or PyPI server. Custom setup logic can be found in (build.sh)[./build.sh].

TODOs

Add integration tests for:

Test Python SDK
Test job failures as well
Test dedicated workers
Error handlers and Recovery handlers for schedule
Concurrency limits