Commit graph

13 commits

Author SHA1 Message Date
SkywardSyntax
955248fee0
copilot_chat: Rename o1-preview model to o1 (#23038)
https://github.blog/news-insights/openais-o1-model-available-in-copilot-chat-and-github-models/

Release Notes:

- Renamed Github Copilot Chat "o1-preview" model to "o1".

---------

Co-authored-by: Marshall Bowers <elliott.codes@gmail.com>
2025-01-13 15:32:26 +00:00
Marcel Kersten
787466383e
copilot: Update Copilot Chat to o1 GA model version (#22376)
Closes #22375

Release Notes:

- Fixed model version of o1 in GitHub Copilot Chat

---------

Co-authored-by: Peter Tripp <peter@zed.dev>
2024-12-27 18:09:50 +00:00
Marshall Bowers
937186da12
gpui: Don't export named Context from prelude (#21869)
This PR updates the `gpui::prelude` to not export the `Context` trait
named.

This prevents some naming clashes in downstream consumers.

Release Notes:

- N/A
2024-12-11 13:21:40 -05:00
fred-sch
380679fcc2
Fix: Copilot Chat is logged out (#21360)
Closes #21255

Release Notes:

- Fixed Copilot Chat OAuth Token parsing

---------

Co-authored-by: Bennet Bo Fenner <bennet@zed.dev>
2024-12-02 10:35:29 +01:00
Thorsten Ball
aee01f2c50
assistant: Remove low_speed_timeout (#20681)
This removes the `low_speed_timeout` setting from all providers as a
response to issue #19509.

Reason being that the original `low_speed_timeout` was only as part of
#9913 because users wanted to _get rid of timeouts_. They wanted to bump
the default timeout from 5sec to a lot more.

Then, in the meantime, the meaning of `low_speed_timeout` changed in
#19055 and was changed to a normal `timeout`, which is a different thing
and breaks slower LLMs that don't reply with a complete response in the
configured timeout.

So we figured: let's remove the whole thing and replace it with a
default _connect_ timeout to make sure that we can connect to a server
in 10s, but then give the server as long as it wants to complete its
response.

Closes #19509

Release Notes:

- Removed the `low_speed_timeout` setting from LLM provider settings,
since it was only used to _increase_ the timeout to give LLMs more time,
but since we don't have any other use for it, we simply remove the
setting to give LLMs as long as they need.

---------

Co-authored-by: Antonio <antonio@zed.dev>
Co-authored-by: Peter Tripp <peter@zed.dev>
2024-11-15 07:37:31 +01:00
dhaus67
c350321318
Update Copilot Chat max_tokens soft limits (#20363)
Closes #20362 

Co-authored-by: Peter Tripp <peter@zed.dev>
2024-11-07 16:03:12 -05:00
Jonathan Toledo
67be6ec3b5
copilot: Add support for new models (#19968)
Closes #19963

This PR implements integration with the newly announced GitHub Copilot
LLM models, including:
- Claude 3.5 Sonnet
- o1-mini
- o1-preview

Release Notes:

- N/A

---------

Co-authored-by: Bennet Bo Fenner <bennet@zed.dev>
2024-11-04 10:55:20 +01:00
Conrad Irwin
e28496d4e2
Stop leaking isahc assumption (#18408)
Users of our http_client crate knew they were interacting with isahc as
they set its extensions on the request. This change adds our own
equivalents for their APIs in preparation for changing the default http
client.

Release Notes:

- N/A
2024-09-26 14:01:05 -06:00
Piotr Osiewicz
e6c1c51b37
chore: Fix several style lints (#17488)
It's not comprehensive enough to start linting on `style` group, but
hey, it's a start.

Release Notes:

- N/A
2024-09-06 11:58:39 +02:00
Ryan Hawkins
8a320668ed
Add support for GPT-4o in Copilot Chat (#16446)
Release Notes:
- Added support for GPT-4o for Copilot Chat.
2024-08-19 09:03:06 +02:00
Marshall Bowers
d6e558e3c9
copilot: Colocate copilot_chat_config_path with the rest of the Copilot code (#15703)
This PR moves the `copilot_chat_config_path` out of `paths` and into
`copilot` with the rest of the Copilot code.

Since this doesn't actually return a Zed path, it doesn't belong in
`paths`.

Release Notes:

- N/A
2024-08-02 15:46:06 -04:00
Antonio Scandurra
99bc90a372
Allow customization of the model used for tool calling (#15479)
We also eliminate the `completion` crate and moved its logic into
`LanguageModelRegistry`.

Release Notes:

- N/A

---------

Co-authored-by: Nathan <nathan@zed.dev>
2024-07-30 16:18:53 +02:00
Ryan Hawkins
6f0655810e
Add GitHub Copilot Chat Support (#14842)
# Summary

This commit implements Github Copilot Chat support within the existing
Assistant panel/framework. It required a little bit of trickery and
internal API modification, as Copilot doesn't use the same
authentication-style as all of the existing providers, opting to use
OAuth and a short lived API key instead of a straight API key. All
existing Assistant features should work.

Release Notes:
- Added Github Copilot Chat support
([#4673](https://github.com/zed-industries/zed/issues/4673)).

## Screenshots
<img width="1552" alt="A screenshot showing a conversation between a
user and Github Copilot Chat within the Zed editor."
src="https://github.com/user-attachments/assets/73eaf6a2-792b-4c40-a7fe-f763bd6417d7">

---------

Co-authored-by: Bennet Bo Fenner <bennet@zed.dev>
2024-07-30 09:32:58 +02:00