andrewbelcher → created an issue.
Tested, and it's working great!
andrewbelcher → made their first commit to this issue’s fork.
Also tested and looks good! Am merging now!
andrewbelcher → made their first commit to this issue’s fork.
PR on top of 📌 Add function calls for epics & tasks Active - https://git.drupalcode.org/project/minikanban_agent/-/merge_requests/9/d... are the changes for this issue.
andrewbelcher → created an issue.
PR on top of 📌 Refactor hooks into OO classes Active - https://git.drupalcode.org/project/minikanban_agent/-/merge_requests/8/d... is just the changes for this issue
andrewbelcher → created an issue.
andrewbelcher → created an issue.
andrewbelcher → created an issue.
andrewbelcher → created an issue.
andrewbelcher → created an issue.
andrewbelcher → created an issue.
Looks good!
Looks good!
andrewbelcher → created an issue.
andrewbelcher → created an issue.
andrewbelcher → created an issue.
andrewbelcher → created an issue.
marcus_johansson → credited andrewbelcher → .
andrewbelcher → created an issue.
andrewbelcher → made their first commit to this issue’s fork.
Add token replacement on property restrictions and expose tokens on explorer. Well tested locally and working really nicely!
andrewbelcher → made their first commit to this issue’s fork.
andrewbelcher → created an issue.
Oh, and I also added the ability to apply restrictions via the tool explorer, in line with what can be configured on agents in AI Agents. That makes it a lot easier to test!
I believe that's all tests fixed - failure was a runner issue.
I've slightly tweaked it to not automatically modify the required property. That can still be done by things that modify the definition though.
I would actually describe this as a bug, and a have upped it to major as there is no reasonable workaround that I can see.
So to get the LLM to respect this, I had to put reiterate that it's a constant multiple times by:
- Setting
const - Setting
enumwith a single value - Adding a note to the description.
But it was consistently behaving after that!
I also adjusted the way required constraints are managed so it's computed at the point of render rather than adding the property, so it respects and changes. I've also made isRequired always FALSE if it's a constant.
andrewbelcher → created an issue.
Original issue in AI was a duplicate of 📌 Add module dependencies to tools Active which has been done!
Ah, just realised this is a duplicate of a ticket Marcus has already fixed - 📌 Add module dependencies to tools Active .
Steps given in the initial report.
The isAvailable method only appears to be called in ai_agents_extra's MCP plugin, and the ai_content_suggestions settings form.
That probably should be checked in other places, but is more suitable for "run time" checks, rather than dependency checks. For example, if a function call tried to inject a dependency from a module not enabled, you wouldn't be able to instantiate the plugin to call isAvailable.
marcus_johansson → credited andrewbelcher → .
andrewbelcher → created an issue.
PR also includes some fixes to type hints/usage etc.
andrewbelcher → created an issue.
andrewbelcher → created an issue.
andrewbelcher → created an issue.
andrewbelcher → created an issue.
andrewbelcher → created an issue.
andrewbelcher → created an issue.
andrewbelcher → created an issue.
andrewbelcher → created an issue.
andrewbelcher → created an issue.
andrewbelcher → created an issue.
andrewbelcher → made their first commit to this issue’s fork.
andrewbelcher → made their first commit to this issue’s fork.
I think this should actually be against the AI module. OpenAI provider (along with most other providers) do make use of key.
However AI, which is where the explicit dependency is, doesn't directly use it. In the case of the AWS Bedrock provider, key is never used as it makes use of the AWS module's profiles to manage the credentials.
marcus_johansson → credited andrewbelcher → .