ce6e82c
collab: Treat staff as having usage-based pricing enabled (#30020)
Click to expand commit body
This PR makes it so staff are treated as having opted-in to usage-based
pricing.
Release Notes:
- N/A
Marshall Bowers
created
009963f
Improve token counting for OpenAI models (#30242)
Click to expand commit body
tiktoken_rs is a bit behind (and even upstream tiktoken doesn't have all
of these models)
We were incorrectly using the cl100k tokenizer for some models that
actually use the o200k tokenizers. So that is updated.
I also made the match arms specific so that we do a better job of
catching whether or not tiktoken-rs accurately supports new models we
add in.
I will also do a PR upstream to see if we can move some of this logic
back out if tiktoken better supports the newer models.
Release Notes:
- Improved tokenizer support for openai models.
Ben Brandt
created
5d49675
Reuse conversation cache when streaming edits (#30245)
Click to expand commit body
Release Notes:
- Improved latency when the agent applies edits.
Antonio Scandurra
created
5c22af3
agent: Rename a number of constructs from Assistant to Agent (#30196)
Click to expand commit body
This PR renames a number of constructs in the `agent` crate from the
"Assistant" terminology to "Agent".
Not comprehensive, but it's a start.
Release Notes:
- N/A
Closes #30056
Apparently the API supports the "default" field now, so we can remove
that transformation.
However, optional is not supported
See https://ai.google.dev/api/caching#Schema
Release Notes:
- agent: Improve tool schema compatibility for Gemini models
Bennet Bo Fenner
created
cb22acc
mistral: Add new Mistral medium model (#30171)
Click to expand commit body
Release Notes:
- Added `mistral-medium` to the Mistral provider.
versecafe
created
552382f
Load Profile state from Thread and tie visibility to the thread's model (#30090)
Click to expand commit body
When deciding if a model supports tools or not, we weren't reading from
the configured model in a given thread.
This also stores the profile on the thread, which matches the behavior
of the Model and Max Mode, which we also already store per thread.
Hopefully this helps alleviate some confusion.
Release Notes:
- agent: Save profile selection per-Agent thread
59cab2a
Allow opening the FS root dir as a remote project (#30190)
Click to expand commit body
### Todo
* [x] Allow opening `ssh://username@host:/` from the CLI
* [x] Allow selecting `/` in the `open path` picker
* [x] Allow selecting the home directory in the `open path` picker
Release Notes:
- Changed the initial state of the SSH project picker to show the full
path to your home directory on the remote machine, instead of `~`.
- Added the ability to open `/` as a project folder over SSH
---------
Co-authored-by: Agus Zubiaga <hi@aguz.me>
Max Brunsfeld
and
Agus Zubiaga
created
cd4024a
Use agent panel font size for all content in thread / history views and fix text thread font size adjust (#30041)
Click to expand commit body
Release Notes:
- N/A
Michael Sloan
created
7a37a02
Avoid empty schema in copilot dummy tool (#30178)
Click to expand commit body
Copilot chat still returns a 400 if the dummy tool uses the `{}` schema.
This is a follow-up to https://github.com/zed-industries/zed/pull/30007.
Release Notes:
- Fixed a bug where agent edits would fail when using GitHub Copilot
Chat.
Co-authored-by: Agus Zubiaga <hi@aguz.me>
cfaf16a
agent: Fix profile menu hover flicker after settings update (#30109)
Click to expand commit body
Closes #30091
Follow-up to #29958
This PR fixes the profile menu flickering due to the documentation aside
after updating the agent dock position over the settings file.
The problem arose because the `documentation_side` could get out of sync
with the actual agent panel dock position. The `documentation_side` was
only updated whenever the user changed the agent panel position using
the UI, but not when updating the position in the settings file.
You can reproduce this easily by changing the `agent.dock` position to
the opposite site in your settings, which will make the profile menu
flicker again in some scenarios due to the de-sync.
This PR fixes this behavior by computing the position during render,
thus the actual set panel position and the documentation position can
never get out of sync
Release Notes:
- Fixed the agent profile menu flickering after updating the assistant
panel dock position in the settings.
Finn Evers
created
cf30cc7
language_models: Update copy for Zed Pro subscription (#30152)
Click to expand commit body
This PR updates the copy around the Zed Pro description to be more
accurate.
Release Notes:
- agent: Updated some copy about Zed Pro in the configuration view.
Updated terms for Agent panel launch.
Release Notes:
- N/A
Peter Tripp
created
3c9d39b
Send up Zed version with edit prediction and completion requests (#30136)
Click to expand commit body
This PR makes it so we send up an `x-zed-version` header with the
client's version when making a request to llm.zed.dev for edit
predictions and completions.
Release Notes:
- N/A
Marshall Bowers
created
85f63c9
agent: Use correct timezone for thread history separators (#30059)
Click to expand commit body
Turns out `naive_local` doesn't actually offset a `DateTime<Utc>` to the
local timezone before creating a `NaiveDate`.
Release Notes:
- agent: Use correct timezone for thread history separators
Agus Zubiaga
created
3cabcd7
Fix agent reading and editing files over SSH (#30144)
Click to expand commit body
Release Notes:
- Fixed a bug that would prevent the agent from working over SSH.
---------
Co-authored-by: Nathan Sobo <nathan@zed.dev>
Co-authored-by: Richard Feldman <oss@rtfeldman.com>
Co-authored-by: Max Brunsfeld <maxbrunsfeld@gmail.com>
Co-authored-by: Cole Miller <m@cole-miller.net>
Antonio Scandurra
,
Nathan Sobo
,
Richard Feldman
,
Max Brunsfeld
, and
Cole Miller
created
c833618
Restore tool cards on thread deserialization (#30053)
Click to expand commit body
Release Notes:
- N/A
---------
Co-authored-by: Julia Ryan <juliaryan3.14@gmail.com>
Mikayla Maki
and
Julia Ryan
created
1d6a5b2
agent: Make feedback buttons more minimal (#30133)
Click to expand commit body
Also swapped out the svgs for `ThumbsDown` and `ThumbsUp`, and added
`DocumentText`.
Release Notes:
- N/A
792bae2
Fix zero-sized message editors when context strip is empty (cherry-pick #30079) (#30085)
Click to expand commit body
Cherry-picked Fix zero-sized message editors when context strip is empty
(#30079)
Release Notes:
- Fixed a bug that would cause the message composer in the agent panel
to not render when the context strip was empty.
Co-authored-by: Ben Brandt <benjamin.j.brandt@gmail.com>
Co-authored-by: Nathan Sobo <nathan@zed.dev>
Co-authored-by: Antonio Scandurra <me@as-cii.com>
Co-authored-by: Ben Brandt <benjamin.j.brandt@gmail.com>
Co-authored-by: Nathan Sobo <nathan@zed.dev>
gcp-cherry-pick-bot[bot]
,
Antonio Scandurra
,
Ben Brandt
, and
Nathan Sobo
created
012f4c2
Avoid panic when opening thread as markdown in non-local project (cherry-pick #30061) (#30062)
Click to expand commit body
Cherry-picked Avoid panic when opening thread as markdown in non-local
project (#30061)
Right now `agent: open active thread as markdown` will always panic when
you try to use it over collab or when SSH remoting. This PR makes it log
an error instead (we should follow up by restoring full remote support).
Release Notes:
- Prevented `agent: open active thread as markdown` from panicking when
used in a non-local project.
Co-authored-by: Cole Miller <cole@zed.dev>
f4c6b2f
agent: Remove feature flag checks (#30055)
Click to expand commit body
This PR removes all of the feature flag checks related to the Agent.
Tried to do this in the least invasive way possible; we can follow up
with a full removal.
Release Notes:
- N/A
8512ba4
lmstudio: Fix streaming not working in v0.3.15 (#30013)
Click to expand commit body
Closes #29781
Tested this with llama3, gemma3 and qwen3.
This is a breaking change, which means after adding this code changes in
future version zed we will require atleast lmstudio >= 0.3.15. For
context why it's breaking changes check out the issue: #29781.
What this doesn't try to solve is:
* Tool calling, thinking text rendering. Will raise a seperate PR for
these as those are not required in this PR to make it work.
https://github.com/user-attachments/assets/945f9c73-6323-4a88-92e2-2219b760a249
Release Notes:
- lmstudio: Fixed Zed support for LMStudio >= v0.3.15 (breaking change -- older versions are no longer supported).
---------
Co-authored-by: Peter Tripp <peter@zed.dev>
This PR enables the Agent-related feature flags on the client.
Release Notes:
- N/A
Marshall Bowers
created
41fe53b
Add an onboarding banner for the Agent panel (#30050)
Click to expand commit body
This PR adds an onboarding banner for the Agent panel:
<img width="262" alt="Screenshot 2025-05-06 at 6 54 58 PM"
src="https://github.com/user-attachments/assets/52849e64-7d5d-488c-8456-4d7bd97f8ebd"
/>
Release Notes:
- N/A
Marshall Bowers
created
6c29cbe
git_ui: Fix resetting of onboarding banner (#30051)
Click to expand commit body
This PR fixes an issue where the Git onboarding banner wasn't able to be
reset.
Release Notes:
- N/A
Marshall Bowers
created
520bbd2
agent: Add date separators to Thread History (#29961)
Click to expand commit body
Adds time-bucket separators to the thread history list:
https://github.com/user-attachments/assets/c9ac3ec4-b632-4ea5-8234-382b48de2bd6
Note: I'm simulating that Today is next Thursday so that I can show the
"This Week" bucket.
Release Notes:
- agent: Add date separators to Thread History
Agus Zubiaga
created
42894f6
agent: Allow customizing temperature by provider/model (#30033)
Click to expand commit body
Adds a new `agent.model_parameters` setting that allows the user to
specify a custom temperature for a provider AND/OR model:
```json5
"model_parameters": [
// To set parameters for all requests to OpenAI models:
{
"provider": "openai",
"temperature": 0.5
},
// To set parameters for all requests in general:
{
"temperature": 0
},
// To set parameters for a specific provider and model:
{
"provider": "zed.dev",
"model": "claude-3-7-sonnet-latest",
"temperature": 1.0
}
],
```
Release Notes:
- agent: Allow customizing temperature by provider/model
---------
Co-authored-by: Max Brunsfeld <maxbrunsfeld@gmail.com>
Co-authored-by: Marshall Bowers <git@maxdeviant.com>
Agus Zubiaga
,
Max Brunsfeld
, and
Marshall Bowers
created
44ef5bd
Remember max mode setting per-thread and add a user setting (#30042)
Click to expand commit body
Supersedes: https://github.com/zed-industries/zed/pull/29936
Thanks for your contribution @imumesh18, but we had a slightly different
take on it :)
Release Notes:
- N/A
Co-authored-by: Ben Brandt <benjamin.j.brandt@gmail.com>
Mikayla Maki
and
Ben Brandt
created
0670484
agent: Only show the trial upsell in the thread view (#30040)
Click to expand commit body
This PR makes it so we only show the trial upsell in the thread view.
Fixes https://github.com/zed-industries/zed/issues/30037.
Release Notes:
- Agent Beta: Changed the trial upsell to only be visible in the thread
view.
Marshall Bowers
created
ac70f22
Clean up some styling issues in the editing tool card and render the animated lines a bit smaller (#30038)
Click to expand commit body
Release Notes:
- N/A
---------
Co-authored-by: Michael Sloan <mgsloan@gmail.com>
Nathan Sobo
and
Michael Sloan
created
400a4fa
agent: Add missing Linux keybindings (#30032)
Click to expand commit body
This PR updates the default Linux keybindings to align with changes made
to the macOS bindings in #29943.
Release Notes:
- N/A
6ae2417
Fix token count not appearing for the first message (#30035)
Click to expand commit body
Release Notes:
- N/A
Co-authored-by: Ben Brandt <benjamin.j.brandt@gmail.com>
Mikayla Maki
and
Ben Brandt
created
6cc6acc
Avoid panicking when edit agent emits an empty old_text tag (#30030)
Click to expand commit body
Release Notes:
- Fixed a panic that could sometimes occur when the agent applies edits.
Co-authored-by: Nathan <nathan@zed.dev>
Antonio Scandurra
and
Nathan
created
ca51c0c
agent: Don't render trial upsell when not using the Zed provider (#30029)
Click to expand commit body
This PR makes it so we don't render the trial upsell when not using the
Zed provider.
Release Notes:
- Agent Beta: Changed Zed Pro trial upsell to only be displayed when
using a model through the Zed provider.
Marshall Bowers
created
4da8f4a
agent: Fix "tool cancelled" status being overapplied to failed tool calls (#30021)
Click to expand commit body
Release Notes:
- Agent Beta: Fixed a bug that caused past failed tool calls to
incorrectly display as cancelled by the user.
Cole Miller
created
764c529
agent: Don't render usage callouts when not using the Zed provider (#30025)
Click to expand commit body
This PR makes it so we don't render the usage callouts when not using
the Zed provider.
Release Notes:
- Agent Beta: Changed usage callouts to only be displayed when using a
model through the Zed provider.
Marshall Bowers
created
121e3b5
agent: Handle context servers that do not provide a configuration in MCP setup dialog (#30023)
80a85a3
Fix checkpoints not being rendered (#30019)
Click to expand commit body
Closes #ISSUE
Release Notes:
- Agent Beta: Fixed a bug causing "Restore Checkpoint" buttons in the
agent panel not to be rendered.
Co-authored-by: Antonio Scandurra <me@as-cii.com>