Previously we were guessing the context window size here:
8c3f09e31e/crates/ollama/src/ollama.rs (L22)
This is inaccurate and must be updated manually. This PR ensures that we
extract the context window size from the request in the same way that
the Ollama CLI does when running `ollama show <model-name>` (Relevant
code is
[here](3d32249c74/cmd/cmd.go (L860)))
The format looks like this:
```json
{
"model_info": {
"general.architecture": "llama",
"llama.context_length": 132000
}
}
```
Once this PR is merged we could technically remove the old code
8c3f09e31e/crates/ollama/src/ollama.rs (L22)
I decided to keep it for now, as it is unclear if the necessary fields
are available via the API on older Ollama versions.
Release Notes:
- Fixed an issue where Ollama models would use the wrong context window
size
Release Notes:
- Added Codestral edit predictions provider which can be enabled by adding an API key in the Mistral section of agent settings.
## Config
Get API key from https://console.mistral.ai/codestral and add it in the Mistral section of the agent settings.
```
"features": {
"edit_prediction_provider": "codestral"
},
"edit_predictions": {
"codestral": {
"model": "codestral-latest",
"max_tokens": 150
}
},
```
---------
Co-authored-by: Michael Sloan <michael@zed.dev>
Before this change the active theme and icon theme were retrofitted onto
the ThemeSettings.
Now they're in their own new global (GlobalTheme::theme(cx) and
GlobalTheme::icon_theme(cx))
This lets us remove cx from the settings traits, and tidy up a few other
things along the way.
Release Notes:
- N/A
After the change, we can add "supports_images", "supports_tools" and
"parallel_tool_calls" properties to set up new models. Our
`settings.json` will be as follows:
```json
"language_models": {
"x_ai": {
"api_url": "https://api.x.ai/v1",
"available_models": [
{
"name": "grok-4-fast-reasoning",
"display_name": "Grok 4 Fast Reasoning",
"max_tokens": 2000000,
"max_output_tokens": 64000,
"supports_tools": true,
"parallel_tool_calls": true,
},
{
"name": "grok-4-fast-non-reasoning",
"display_name": "Grok 4 Fast Non-Reasoning",
"max_tokens": 2000000,
"max_output_tokens": 64000,
"supports_images": true,
}
]
}
}
```
Closes https://github.com/zed-industries/zed/issues/38752
Release Notes:
- xAI: Added support for for configuring tool and image support for
custom model configurations
This PR adds an `x-zed-client-supports-x-ai` header to the `GET /models`
request sent to Cloud to indicate that the client supports xAI models.
Release Notes:
- N/A
The `Duration` argument in `get_models` has been unused for over a year.
The `complete` function is also unused and it has fallen behind in new
feature additions such as Authorization support. This used to exist
because ollama didn't support tools in streaming mode, `with_tools` also
existed because of that. Now however there is no reason to keep this
around.
`ChatResponseDelta ` had unnecessary `#[allow(unused)]` macros since the
fields are marked `pub`. Using `#[expect(unused)]` would've caught this.
Release Notes:
- N/A
The current problem is that if I specify model parameters, like
`max_tokens`, in `settings.json` for an Ollama model, they do not
override the values coming from the Ollama API. Instead, the parameters
from the API are used. For example, in the settings below, even though I
have overridden `max_tokens`, Zed will still use the API's default
`context_length` of 4k.
```
"language_models": {
"ollama": {
"available_models": [
{
"name": "qwen3-coder:latest",
"display_name": "Qwen 3 Coder",
"max_tokens": 64000,
"supports_tools": true,
"keep_alive": "15m",
"supports_thinking": false,
"supports_images": false
}
]
}
},
```
Release Notes:
- Fixed an issue where Ollama model parameters were not being correctly
overridden by user settings.
This PR updates the Gemini provider to treat a
`prompt_feedback.block_reason` as a refusal, as Gemini does not seem to
return a `stop_reason` to use in this case.
<img width="639" height="162" alt="Screenshot 2025-09-22 at 4 23 15 PM"
src="https://github.com/user-attachments/assets/7a86d67e-06c1-49ea-b58f-fa80666f0f8c"
/>
Previously this would just result in no feedback to the user.
Release Notes:
- Added an error message when a Gemini response contains a
`block_reason`.
`HttpClient`: Relaxes the lifetime bound to `&self` in `get`/`post`
by returning the `self.send` future directly. This makes both
methods return `'static` futures without extra boxing.
`HttpRequestExt`: Added fluent builder methods to `HttpRequestExt`
inspired by the `gpui::FluentBuilder` trait.
Release Notes:
- N/A
When we refactored settings to not pass JSON blobs around, we ended up
needing
to write *a lot* of code that just merged things (like json merge used
to do).
Use a derive macro to prevent typos in this logic.
Release Notes:
- N/A
Co-Authored-By: Ben K <ben@zed.dev>
Co-Authored-By: Anthony <anthony@zed.dev>
Co-Authored-By: Mikayla <mikayla@zed.dev>
Release Notes:
- settings: Major internal changes to settings. The primary user-facing
effect is that some settings which did not make sense in project
settings files are no-longer read from there. (For example the inline
blame settings)
---------
Co-authored-by: Ben Kunkle <ben@zed.dev>
Co-authored-by: Mikayla Maki <mikayla.c.maki@gmail.com>
Co-authored-by: Anthony <anthony@zed.dev>
This PR updates the Cloud language model provider to use the `message`
field from the Cloud error response, if it is present.
Previously we would always show the entire JSON payload in the error
message, but with this change we can show just the user-facing `message`
the error response is in a shape that we recognize.
Release Notes:
- N/A
Three motivations for this:
* Changing provider URL could cause credentials for the prior URL to be
sent to the new URL.
* The UI is in a misleading state after URL change - it shows a
configured API key, but on restart it will show no API key.
* #34110 will add support for both URL and key configuration for Ollama.
This is the first provider to have UI for setting the URL, and this
makes these issues show up more directly as odd UI interactions.
#37610 implemented something similar for the OpenAI and OpenAI
compatible providers. This extracts out some shared code, uses it in all
relevant providers, and adds more safety around key use.
I haven't tested all providers, but the per-provider changes were pretty
mechanical, so hopefully work properly.
Release Notes:
- Fixed handling of changes to LLM provider URL in settings to also load
the associated API key.
In zed logs you can see these logs of lmstudio connection refused.
Currently zed connects to lmstudio by default as there is no credential
mechanism to check if the user has enabled lmstudio previously or not
like we do with other providers using api keys.
This pr removes the below annoying log and makes the zed logs less
polluted.
```
2025-09-01T02:11:33+05:30 ERROR [language_models] Other(error sending request for url (http://localhost:1234/api/v0/models)
Caused by:
0: client error (Connect)
1: tcp connect error: Connection refused (os error 61)
2: Connection refused (os error 61))
```
Release Notes:
- N/A
---------
Signed-off-by: Umesh Yadav <git@umesh.dev>
Supersedes: #34500
Also this will allow to fix this: #35386 without the UX changes but
providers can now be control through settings as well within zed.
Just rebased the latest main and docs added. Added @AurelienTollard as
co-author as it was started by him everything else remains the same from
original PR.
Release Notes:
- Added ability to control Provider Routing for OpenRouter models from
settings.
Co-authored-by: Aurelien Tollard <tollard.aurelien1999@gmail.com>
This PR fixes the backwards compatibility of the new `Plan` variants.
We can't add new variants to the wire representation, as old clients
won't be able to understand them.
Release Notes:
- N/A
While working on fixing this: #37116. I reliased the current
implementation of github copilot is not truly resilient to upstream
changes.
This PR enhances GitHub Copilot Chat to be forward-compatible with new
AI model vendors and improves token counting accuracy by using
vendor-specific tokenizers from the GitHub Copilot API. The system
previously failed when GitHub added new model vendors like xAI with
deserialization errors, and token counting wasn't utilizing the
vendor-specific tokenizer information provided by the API. The solution
adds an Unknown variant to the ModelVendor enum with serde other
attribute to gracefully handle any new vendors GitHub introduces,
implements tokenizer-aware token counting that uses the model's
specified tokenizer mapping o200k_base to gpt-4o with fallback, adds
explicit support for xAI models with proper tool input format handling,
and includes comprehensive test coverage for unknown vendor scenarios.
Key changes include adding the tokenizer field to model capabilities,
implementing the tokenizer method on models, updating tool input format
logic to handle unknown vendors, and simplifying token counting to use
the vendor's specified tokenizer or fall back to gpt-4o. This ensures
Zed's Copilot Chat integration remains robust and accurate as GitHub
continues expanding their AI model provider ecosystem.
Release Notes:
- Enhanced model vendor compatibility to automatically support future AI
providers and improved token counting accuracy using vendor-specific
tokenizers from the GitHub Copilot
---------
Signed-off-by: Umesh Yadav <git@umesh.dev>
Closes#37093
Also check this: #37099.
So currently in zed for both OpenAI and OpenAI Compatible provider when
the url is changed from settings the api_key stored in the provider
state is not cleared and it is still used. But if you restart zed the
api_key is cleared. Currently zed uses the api_url to store and fetch
the api key from credential provider. The behaviour is not changed
overall, it's just that we have made it consistent it with the zed
restart logic where it re-authenticates and fetches the api_key again. I
have attached the video below to show case before and after of this.
So all in all the problem was we were not re-authenticating the in case
api_url change while zed is still running. Now we trigger a
re-authentication and clear the state in case authentication fails.
OpenAI Compatible Provider:
| Before | After |
|--------|--------|
| <video
src="https://github.com/user-attachments/assets/324d2707-ea72-4119-8981-6b596a9f40a3"
/> | <video
src="https://github.com/user-attachments/assets/cc7fdb73-8975-4aaf-a642-809bb03ce319"
/> |
OpenAI Provider:
| Before | After |
|--------|--------|
| <video
src="https://github.com/user-attachments/assets/a1c07d1b-1909-4b49-b33c-fc05123e92e7"
/> | <video
src="https://github.com/user-attachments/assets/d78aeccd-5cd3-4d0c-8b9f-6f98e499d7c8"
/> |
Release Notes:
- Fixed OpenAI and OpenAI Compatible provide API keys being persisted
when changing the API URL setting. Authentication is now properly
revalidated when settings change.
---------
Signed-off-by: Umesh Yadav <git@umesh.dev>
Fix an issue that resulted in Ollama models not being able to not being
able to access the input of the commands they executed (only being able
to access the result).
This properly return the function history as shown in
https://github.com/ollama/ollama/blob/main/docs/api.md#chat-request-with-history-with-tools
Previously, function input where not returned and result where returned
as a "user" role.
Release Notes:
- ollama: Improved format when returning tool results to the models
This PR switches the OpenRouter integration from fetching all models to
fetching only the models specified in the user's account preferences.
This will help improve the experience
**The Problem**
The previous implementation used the `/models` endpoint, which returned
an exhaustive list of all models supported by OpenRouter. This resulted
in a long and cluttered model selection dropdown in Zed, making it
difficult for users to find the models they actually use.
**The Solution**
We now use the `/models/user` endpoint. This API call returns a curated
list based on the models and providers the user has selected in their
[OpenRouter dashboard](https://openrouter.ai/models).
Ref: [OpenRouter API Docs for User-Filtered
Models](https://openrouter.ai/docs/api-reference/list-models-filtered-by-user-provider-preferences)
Release Notes:
- language_models: Support OpenRouter user preferences for available
models
Closes#37302
Related: #37614
In case of open_ai_compatible providers like Zhipu AI and z.ai they
return empty content along with usage data. below is the example json
captured from z.ai. We now ignore empty content returned by providers
now to avoid this issue where we would return the same empty content
back to provider which would error out.
```
OpenAI Stream Response JSON:
{
"id": "2025090518465610d80dc21e66426d",
"created": 1757069216,
"model": "glm-4.5",
"choices": [
{
"index": 0,
"finish_reason": "tool_calls",
"delta": {
"role": "assistant",
"content": ""
}
}
],
"usage": {
"prompt_tokens": 7882,
"completion_tokens": 150,
"total_tokens": 8032,
"prompt_tokens_details": {
"cached_tokens": 7881
}
}
}
```
Release Notes:
- Skip empty delta text content in OpenAI and OpenAI compatible provider
Signed-off-by: Umesh Yadav <git@umesh.dev>
This PR separates out the associated constant `KEY` from the `Settings`
trait into a new trait `SettingsKey`. This allows for the key trait to
be derived using attributes to specify the path so that the new
`SettingsUi` derive macro can use the same attributes to determine top
level settings paths thereby removing the need to duplicate the path in
both `Settings::KEY` and `#[settings_ui(path = "...")]`
Co-authored-by: Ben Kunkle <ben@zed.dev>
Release Notes:
- N/A
---------
Co-authored-by: Ben Kunkle <ben@zed.dev>
Closes#37289
The current implementation has a problem. The **`from_id` method** in
the Anthropic crate works well for predefined models, but not for custom
models that are defined in the settings. This is because it fallbacks to
using default beta headers, which are incorrect for custom models.
The issue is that the model instance for custom models lives within the
`language_models` provider, so I've updated the **`stream_completion`**
method to explicitly accept beta headers from its caller. Now, the beta
headers are passed from the `language_models` provider all the way to
`anthropic.stream_completion`, which resolves the issue.
Release Notes:
- Fixed a bug where extra_beta_headers defined in settings for Anthropic
custom models were being ignored.
---------
Signed-off-by: Umesh Yadav <git@umesh.dev>
Closes#32758
Release Notes:
- Resolved an issue with the Ollama provider that caused requests to
fail with a 400 error for models that don't support tools. The tools
object is now only sent to compatible models to ensure successful
requests.
Improves the error handling for openrouter and adds automatic retry like
anthropic for few of the status codes.
Release Notes:
- Improves error messages for Openrouter provider
- Automatic retry when rate limited or Server error from Openrouter
Closes#30188Closes#34911Closes#34906
Many OpenAI-compatible providers do not automatically filter the tool
schema to comply with the underlying model's requirements; they simply
proxy the request. This creates issues, as models like **Gemini**,
**Grok**, and **Claude** (when accessed via LiteLLM on Bedrock) are
incompatible with Zed's default tool schema.
This PR addresses this by defaulting to a more compatible schema subset
instead of the full schema.
### Why this approach?
* **Avoids Poor User Experience:** One alternative was to add an option
for users to manually set the JSON schema for models that return a `400
Bad Request` due to an invalid tool schema. This was discarded as it
provides a poor user experience.
* **Simplifies Complex Logic:** Another option was to filter the schema
based on the model ID. However, as demonstrated in the attached issues,
this is unreliable. For instance, `claude-4-sonnet` fails when proxied
through LiteLLM on Bedrock. Reliably determining behavior would require
a non-trivial implementation to manage provider-and-model combinations.
* **Better Default Behavior:** The current approach ensures that tool
usage works out-of-the-box for the majority of cases by default,
providing the most robust and user-friendly solution.
Release Notes:
- Improved tool compatibility with OpenAI API-compatible providers
Signed-off-by: Umesh Yadav <git@umesh.dev>
Co-authored-by: Peter Tripp <peter@zed.dev>
This PR fixes an issue where extension operations would never show in
the activity indicator despite this being implemented for ages. This
happened because we were always returning `None` whenever the app has a
global auto updater, which is always the case, so the code path for
showing extension updates in the indicator could never be hit despite
existing prior. Also slightly improves the messages shown for ongoing
extension operations, as these were previously context unaware.
While I was at this, I also quickly took a stab at cleaning up some
remotely related stuff, namely:
- The `AnimationExt` trait is now by default only implemented for
anything that also implements `IntoElement`. This prevents
`with_animation` from showing up for e.g. `u32` within the suggestions
(finally).
- Commonly used animations are now implemented in the
`CommonAnimationExt` trait within the `ui` crate so the needed code does
not always need to be copied and element IDs for the animations are
truly unique.
Relevant change here regarding the original issue is the change from the
`return match` to just a `match` within the activitiy indicator, which
solved the issue at hand.
If we find this to be too noisy at some point, we can easily revisit,
but I think this holds important enough information to be shown in the
activity indicator, especially whilst developing extensions.
Release Notes:
- Extension installation and updates will now be shown in the activity
indicator.
Closes #ISSUE
Initially, the `SettingsUi` trait was tied to `Settings`, however, given
that the `Settings::FileContent` type (which may be the same as the type
that implements `Settings`) will be the type that more directly maps to
the JSON structure (and therefore have the documentation, correct field
names (or `serde` rename attributes), etc) it makes more sense to have
the deriving of `SettingsUi` occur on the `FileContent` type rather than
the `Settings` type.
In order for this to work a relatively important change had to be made
to the derive macro, that being that it now "unwraps" options into their
inner type, so a field with type `Option<Foo>` where `Foo: SettingsUi`
will treat the field as if it were just `Foo`, expecting there to be a
default set in `default.json`. This imposes some restrictions on what
`Settings::FileContent` can be as seen in 1e19398 where `FileContent`
itself can't be optional without manually implementing `SettingsUi`, as
well as introducing some risk that if the `FileContent` type has
`serde(default)`, the default value will override the default value from
`default.json` in the UI even though it may differ (but it should!).
A future PR should probably replace the other settings with `FileContent
= Option<T>` (all of which currently have `T == bool`) with wrapper
structs and have `KEY = None` so the further niceties
`derive(SettingsUi)` will provide such as path renaming, custom UI, auto
naming and doc comment extraction can be used.
Release Notes:
- N/A *or* Added/Fixed/Improved ...
This PR fixes a deserialization issue in GitHub Copilot Chat that was
causing warnings when encountering xAI models from the GitHub Copilot
API and skipping the Grok model from model selector.
Release Notes:
- Fixed support for xAI models that are now available through GitHub
Copilot Chat.
Removes excess log which got through on each start of Zed
```
ERROR [agent_ui::language_model_selector] Failed to authenticate provider: Anthropic: credentials not found
```
The `AnthropicLanguageModelProvider::api_key` method returned a
`anyhow::Result` which would convert
`AuthenticateError::CredentialsNotFound` into a generic error because of
the implicit `Into` when using the `?` operator. This would then get
converted into a `AuthenticateError::Other` later.
By specifying the error type as `AuthenticateError`, we remove this
implicit conversion and the log gets removed.
Release Notes:
- N/A
Closes#37025
This PR fixes GitHub Copilot thread summary failures by removing the
unnecessary `noop` tool insertion logic. The code was originally added
as a workaround in https://github.com/zed-industries/zed/pull/30007 for
supposed GitHub Copilot API issues when tools were used previously in a
conversation but no tools are provided in the current request. However,
testing revealed that this scenario works fine without the workaround,
and the `noop` tool insertion was actually causing "Invalid schema for
function 'noop'" errors that prevented thread summarization from
working. Removing this logic eliminates the errors and allows thread
summarization to function correctly with GitHub Copilot models.
The best way to see if removing that part of code works is just
triggering thread summarisation.
Error Log:
```
2025-08-27T13:47:50-04:00 ERROR [workspace::notifications] "Failed to connect to API: 400 Bad Request {"error":{"message":"Invalid schema for function 'noop': In context=(), object schema missing properties.","code":"invalid_function_parameters"}}\n"
```
Release Notes:
- Fixed GitHub Copilot thread summary failures by removing unnecessary
noop tool insertion logic.
## Goal
This PR creates the initial settings ui structure with the primary goal
of making a settings UI that is
- Comprehensive: All settings are available through the UI
- Correct: Easy to understand the underlying JSON file from the UI
- Intuitive
- Easy to implement per setting so that UI is not a hindrance to future
settings changes
### Structure
The overall structure is settings layer -> data layer -> ui layer.
The settings layer is the pre-existing settings definitions, that
implement the `Settings` trait. The data layer is constructed from
settings primarily through the `SettingsUi` trait, and it's associated
derive macro. The data layer tracks the grouping of the settings, the
json path of the settings, and a data representation of how to render
the controls for the setting in the UI, that is either a marker value
for the component to use (avoiding a dependency on the `ui` crate) or a
custom render function.
Abstracting the data layer from the ui layer allows crates depending on
`settings` to implement their own UI without having to add additional UI
dependencies, thus avoiding circular dependencies. In cases where custom
UI is desired, and a creating a custom render function in the same crate
is infeasible due to circular dependencies, the current solution is to
implement a marker for the component in the `settings` crate, and then
handle the rendering of that component in `settings_ui`.
### Foundation
This PR creates a macro and a trait both called `SettingsUi`. The
`SettingsUi` trait is added as a new trait bound on the `Settings`
trait, this allows the type system to guarantee that all settings
implement UI functionality. The macro is used to derived the trait for
most types, and can be modified through attributes for unique cases as
well.
A derive-macro is used to generate the settings UI trait impl, allowing
it the UI generation to be generated from the static information in our
code base (`default.json`, Struct/Enum names, field names, `serde`
attributes, etc). This allows the UI to be auto-generated for the most
part, and ensures consistency across the UI.
#### Immediate Follow ups
- Add a new `SettingsPath` trait that will be a trait bound on
`SettingsUi` and `Settings`
- This trait will replace the `Settings::key` value to enable
`SettingsUi` to infer the json path of it's derived type
- Figure out how to render `Option<T> where T: SettingsUi` correctly
- Handle `serde` attributes in the `SettingsUi` proc macro to correctly
get json path from a type's field and identity
Release Notes:
- N/A
---------
Co-authored-by: Ben Kunkle <ben@zed.dev>
Closes#37022Closes#36994
This update ensures all Grok models use the JsonSchemaSubset format for
tool schemas.
A previous fix for this issue was too specific, only targeting grok-4
models. This caused other variants, like grok-code-fast-1, to be missed.
We've now broadened the logic to correctly apply the setting to the
entire Grok model family.
Release Notes:
- Fix tool calling for `x-ai/grok-code-fast-1` model via OpenRouter.
Users now accept ToS from Zed's website when they sign in to Zed the
first time. So it's no longer possible that a signed in account could
not have accepted the ToS.
Release Notes:
- N/A
---------
Co-authored-by: Mikayla Maki <mikayla.c.maki@gmail.com>
This PR identifies automatic configuration options that users can select
from the agent panel. If no default provider is set in their settings,
the PR defaults to the first recommended option. Additionally, it
updates the selected provider for a thread when a user changes the
default provider through the settings file, if the thread hasn't had any
queries yet.
Release Notes:
- agent: automatically select a language model provider if there's no
user set provider.
---------
Co-authored-by: Michael Sloan <michael@zed.dev>
