[Scenario]: Terminal Chat #19539

Open
opened 2026-01-31 06:46:35 +00:00 by claunia · 14 comments
Owner

Originally created by @zadjii-msft on GitHub (Mar 16, 2023).

Originally assigned to: @PankajBhojwani on GitHub.

We'll be using this thread to track the ongoing work for Copilot for the Windows Terminal.

This is not something that's in public preview yet.

More details will follow soon!

Initial PR: #16285

### Tasks
- [ ] #16401 
- [ ] https://github.com/microsoft/terminal/issues/16435
- [ ] https://github.com/microsoft/terminal/issues/16442
- [ ] https://github.com/microsoft/terminal/issues/16485
- [ ] https://github.com/microsoft/terminal/issues/16484
- [ ] https://github.com/microsoft/terminal/issues/18142
- [ ] https://github.com/microsoft/terminal/issues/18270
- [ ] https://github.com/microsoft/terminal/issues/16471
- [ ] https://github.com/microsoft/terminal/issues/18200
Originally created by @zadjii-msft on GitHub (Mar 16, 2023). Originally assigned to: @PankajBhojwani on GitHub. We'll be using this thread to track the ongoing work for Copilot for the Windows Terminal. This is not something that's in public preview yet. More details will follow soon! Initial PR: #16285 ```[tasklist] ### Tasks - [ ] #16401 - [ ] https://github.com/microsoft/terminal/issues/16435 - [ ] https://github.com/microsoft/terminal/issues/16442 - [ ] https://github.com/microsoft/terminal/issues/16485 - [ ] https://github.com/microsoft/terminal/issues/16484 - [ ] https://github.com/microsoft/terminal/issues/18142 - [ ] https://github.com/microsoft/terminal/issues/18270 - [ ] https://github.com/microsoft/terminal/issues/16471 - [ ] https://github.com/microsoft/terminal/issues/18200 ```
claunia added the Needs-Tag-FixProduct-TerminalIssue-ScenarioArea-Chat labels 2026-01-31 06:46:36 +00:00
Author
Owner

@WeihanLi commented on GitHub (Nov 23, 2023):

Seemed not working for me, even the network request success

image

network request && response:

image

@WeihanLi commented on GitHub (Nov 23, 2023): Seemed not working for me, even the network request success ![image](https://github.com/microsoft/terminal/assets/7604648/71b01032-d320-4654-85ae-c494c3e666eb) network request && response: ![image](https://github.com/microsoft/terminal/assets/7604648/dd1ccf12-3572-482b-9b37-278da8ea455f)
Author
Owner

@PankajBhojwani commented on GitHub (Nov 29, 2023):

Seemed not working for me, even the network request success

Thanks for letting us know about this! What is the endpoint you are using?

@PankajBhojwani commented on GitHub (Nov 29, 2023): > Seemed not working for me, even the network request success Thanks for letting us know about this! What is the endpoint you are using?
Author
Owner

@WeihanLi commented on GitHub (Nov 29, 2023):

The endpoint I use is

https://spark-01.openai.azure.com/openai/deployments/gpt-35-turbo/chat/completions?api-version=2023-05-15

@WeihanLi commented on GitHub (Nov 29, 2023): The endpoint I use is > https://spark-01.openai.azure.com/openai/deployments/gpt-35-turbo/chat/completions?api-version=2023-05-15
Author
Owner

@PankajBhojwani commented on GitHub (Dec 5, 2023):

@WeihanLi do you have any content filters on for that endpoint? We expect the endpoint to have content filters on with severity = safe

@PankajBhojwani commented on GitHub (Dec 5, 2023): @WeihanLi do you have any content filters on for that endpoint? We expect the endpoint to have content filters on with `severity` = `safe`
Author
Owner

@WeihanLi commented on GitHub (Dec 5, 2023):

do you have any content filters on for that endpoint?

I think so, it may relate to this. I'm using the default settings, the content filter could exists

@WeihanLi commented on GitHub (Dec 5, 2023): > do you have any content filters on for that endpoint? I think so, it may relate to this. I'm using the default settings, the content filter could exists
Author
Owner

@PankajBhojwani commented on GitHub (Dec 5, 2023):

Could you check that? I think your content filters might be switched off, just based on the screenshot you sent. With the content filters on, the JSON response should contain a prompt_filter_results or prompt_annotations field

@PankajBhojwani commented on GitHub (Dec 5, 2023): Could you check that? I think your content filters might be switched off, just based on the screenshot you sent. With the content filters on, the JSON response should contain a `prompt_filter_results` or `prompt_annotations` field
Author
Owner

@WeihanLi commented on GitHub (Dec 5, 2023):

No item for the content filter page

image
image

Are there more places I need to check?

@WeihanLi commented on GitHub (Dec 5, 2023): No item for the content filter page ![image](https://github.com/microsoft/terminal/assets/7604648/0d84a888-7e8f-475e-a8f8-3f0fc41adac9) ![image](https://github.com/microsoft/terminal/assets/7604648/75d1fc94-e530-4018-a128-843efb5ea093) Are there more places I need to check?
Author
Owner

@mikenelson-io commented on GitHub (Apr 29, 2024):

Same error here now on any deployments. Even my old deployments no longer work and get this error.
image

There does not appear to be any way to set any of the content filtering to "safe" via the Playground UI. You can only set Low-Medium-High.

@mikenelson-io commented on GitHub (Apr 29, 2024): Same error here now on any deployments. Even my old deployments no longer work and get this error. ![image](https://github.com/microsoft/terminal/assets/6254544/73d7ea6c-c445-42c9-bb96-59660e98d60a) There does not appear to be any way to set any of the content filtering to "safe" via the Playground UI. You can only set Low-Medium-High.
Author
Owner

@g0t4 commented on GitHub (Jun 15, 2024):

@mikenelson-io I had that too so I went into content filters and turned everything on and highest level and then I cleared credentials in win term and it worked...

@g0t4 commented on GitHub (Jun 15, 2024): @mikenelson-io I had that too so I went into content filters and turned everything on and highest level and then I cleared credentials in win term and it worked...
Author
Owner

@g0t4 commented on GitHub (Jun 15, 2024):

The troubleshooting experience could really use some ❤️... i.e. logging more info on failures

@g0t4 commented on GitHub (Jun 15, 2024): The troubleshooting experience could really use some ❤️... i.e. logging more info on failures
Author
Owner

@ChrisYin commented on GitHub (Jul 17, 2024):

@PankajBhojwani I see you PR for supporting OpenAI in Terminal Chat: https://github.com/microsoft/terminal/pull/17540
Could you please be considering support self-hosting LLM models?
Since different model may use different request headers.
A similar feature has been supported in an extension of VScode, see: https://docs.continue.dev/setup/configuration, Section: Self-hosting an open-source model
User can specify its own request headers by setting config.json.
Looking for Terminal Chat can support more self-hosting opensource models.

@ChrisYin commented on GitHub (Jul 17, 2024): @PankajBhojwani I see you PR for supporting OpenAI in Terminal Chat: https://github.com/microsoft/terminal/pull/17540 Could you please be considering support self-hosting LLM models? Since different model may use different request headers. A similar feature has been supported in an extension of VScode, see: https://docs.continue.dev/setup/configuration, Section: S**elf-hosting an open-source model** User can specify its own request headers by setting config.json. Looking for Terminal Chat can support more self-hosting opensource models.
Author
Owner

@PankajBhojwani commented on GitHub (Jul 18, 2024):

Could you please be considering support self-hosting LLM models?

@nguyen-dows thoughts on this?

@PankajBhojwani commented on GitHub (Jul 18, 2024): > Could you please be considering support self-hosting LLM models? @nguyen-dows thoughts on this?
Author
Owner

@mikenelson-io commented on GitHub (Aug 5, 2024):

Still no resolution for me on this issue. With or without content filters, I always get the message about the model not being safe. Created a new model, new filters, etc.

@mikenelson-io commented on GitHub (Aug 5, 2024): Still no resolution for me on this issue. With or without content filters, I always get the message about the model not being safe. Created a new model, new filters, etc.
Author
Owner

@Chris-Hammer commented on GitHub (Mar 13, 2025):

Did this issue ever get resolved? I'm using a gpt-35-turbo AI model. I have a content filter turned on for the model to restrict everything as much as possible. And yet it still tells me the following:

The model you have provided is either invalid or does not adhere to our content filter requirements. Please use a gpt-35-turbo AI model and set all content filter categories to "safe".

My Github Copilot license works just fine. But this Azure OpenAI connection just will not work.

@Chris-Hammer commented on GitHub (Mar 13, 2025): Did this issue ever get resolved? I'm using a gpt-35-turbo AI model. I have a content filter turned on for the model to restrict everything as much as possible. And yet it still tells me the following: _The model you have provided is either invalid or does not adhere to our content filter requirements. Please use a gpt-35-turbo AI model and set all content filter categories to "safe"._ My Github Copilot license works just fine. But this Azure OpenAI connection just will not work.
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: starred/terminal#19539