This PR adds a notice when reaching consecutive tool use limits when
using normal mode.
Here's an example with the limit artificially lowered to 2 consecutive
tool uses:
https://github.com/user-attachments/assets/32da8d38-67de-4d6b-8f24-754d2518e5d4
Release Notes:
- agent: Added a notice when reaching consecutive tool use limits when
using a model in normal mode.
This sets us up to display queue position information to the user, once
our language model backend is updated to support request queuing.
The JSON returned by the LLM backend will need to look like this:
```json
{"queue": {"status": "queued", "position": 1}}
{"queue": {"status": "started"}}
{"event": {"THE_UPSTREAM_MODEL_PROVIDER_EVENT": "..."}}
```
Release Notes:
- N/A
---------
Co-authored-by: Marshall Bowers <git@maxdeviant.com>
This PR makes it possible to use different LLM models in the agent
panels of two different projects, simultaneously. It also properly
restores a thread's original model when restoring it from the history,
rather than having it use the default model. As before, newly-created
threads will use the current default model.
Release Notes:
- Enabled different project windows to use different models in the agent
panel
- Enhanced the agent panel so that when revisiting old threads, their
original model will be used.
---------
Co-authored-by: Richard Feldman <oss@rtfeldman.com>
This PR adds a "max mode" toggle to the Agent panel, for models that
support it.
Only visible to folks in the `new-billing` feature flag.
Icon is just a placeholder.
Release Notes:
- N/A
This is to enable alternative streaming solutions at the application
layer. I'm not sure we really should have performed parsing of the input
at this layer. Either way I want to experiment with streaming approaches
in a separate crate on a branch, and this will help.
/cc @maxdeviant @bennetbo @rtfeldman
Closes #ISSUE
Release Notes:
- N/A
* Adds a fast / cheaper model to providers and defaults thread
summarization to this model. Initial motivation for this was that
https://github.com/zed-industries/zed/pull/29099 would cause these
requests to fail when used with a thinking model. It doesn't seem
correct to use a thinking model for summarization.
* Skips system prompt, context, and thinking segments.
* If tool use is happening, allows 2 tool uses + one more agent response
before summarizing.
Downside of this is that there was potential for some prefix cache reuse
before, especially for title summarization (thread summarization omitted
tool results and so would not share a prefix for those). This seems fine
as these requests should typically be fairly small. Even for full thread
summarization, skipping all tool use / context should greatly reduce the
token use.
Release Notes:
- N/A
Looks like the required backend component of this was deployed.
https://github.com/zed-industries/monorepo/actions/runs/14541199197
Release Notes:
- N/A
---------
Co-authored-by: Antonio Scandurra <me@as-cii.com>
Co-authored-by: Agus Zubiaga <hi@aguz.me>
Co-authored-by: Richard Feldman <oss@rtfeldman.com>
Co-authored-by: Nathan Sobo <nathan@zed.dev>
This PR makes it so the thread summarization also reports the model
request usage, to prevent the case where the count would appear to jump
by 2 the next time a message was sent after summarization.
Release Notes:
- N/A
This PR updates the Agent to extract the usage information from the
response headers, if they are present.
For now we just log the information, but we'll be using this soon to
populate some UI.
Release Notes:
- N/A
The UI was mistakenly using the cumulative token usage for the token
counter. It will now display the last request token count, plus an
estimation of the tokens in the message editor and context entries that
haven't been sent yet.
https://github.com/user-attachments/assets/0438c501-b850-4397-9135-57214ca3c07a
Additionally, when the user edits a message, we'll display the actual
token count up to it and estimate the tokens in the new message.
Note: We don't currently estimate the delta when switching profiles. In
the future, we want to use the count tokens API to measure every part of
the request and display a breakdown.
Release Notes:
- agent: Made the token count more accurate and added back estimation of
used tokens as you type and add context.
---------
Co-authored-by: Bennet Bo Fenner <bennetbo@gmx.de>
Co-authored-by: Danilo Leal <daniloleal09@gmail.com>
Release Notes:
- agent: Show recommended models in the agent model selector and display
the provider in the model selector's trigger.
---------
Co-authored-by: Danilo Leal <daniloleal09@gmail.com>
Co-authored-by: Danilo Leal <67129314+danilo-leal@users.noreply.github.com>
This PR adds the token count to the active thread view. It doesn't
behaves quite like Assistant 1 where it updates as you type, though; it
updates after you submit the message.
<img
src="https://github.com/user-attachments/assets/82d2a180-554a-43ee-b776-3743359b609b"
width="700" />
---
Release Notes:
- agent: Add token count in the thread view
---------
Co-authored-by: Agus Zubiaga <hi@aguz.me>
This PR removes the `use_any_tool` method from the `LanguageModel`
trait.
It was not being used anywhere, and doesn't really fit in our new tool
use story.
Release Notes:
- N/A
This PR removes the dependency on the `ui` crate from the
`language_model` crate.
We were only depending on it to import `IconName`—which now lives in
`icons`—and some re-exported GPUI items.
Release Notes:
- N/A
Closes#25671
Release Notes:
- Added support for `claude-3-7-sonnet-thinking` in the assistant panel
---------
Co-authored-by: Danilo Leal <daniloleal09@gmail.com>
Co-authored-by: Antonio Scandurra <me@as-cii.com>
Co-authored-by: Agus Zubiaga <hi@aguz.me>
This PR removes the dependents of the `language_models` crate.
The following types have been moved from `language_models` to
`language_model` to facilitate this:
- `LlmApiToken`
- `RefreshLlmTokenListener`
- `MaxMonthlySpendReachedError`
- `PaymentRequiredError`
With this change only `zed` now depends on `language_models`.
Release Notes:
- N/A
This PR moves the `report_assistant_event` function from the
`language_models` crate to the `language_model` crate.
This allows us to drop some dependencies on `language_models`.
Release Notes:
- N/A
While investigating #24896, I noticed two issues:
1. The default configuration for the `zed.dev` provider was using the
wrong string for Claude 3.5 Sonnet. This meant the provider would always
result as not configured until the user selected it from the model
picker, because we couldn't deserialize that string to a valid
`anthropic::Model` enum variant.
2. When clicking on `Open New Chat`/`Start New Thread` in the provider
configuration, we would select `Claude 3.5 Haiku` by default instead of
Claude 3.5 Sonnet.
Release Notes:
- Fixed some issues that caused AI providers to sometimes be
misconfigured.
This PR updates the `LanguageModelProvider::authenticate` method to
return an `AuthenticateError` instead of an `anyhow::Error`.
This allows us to model the "credentials not found" state explicitly as
`AuthenticateError::CredentialsNotFound`, which enables the caller to
check for this state and act accordingly.
Planning to use this in #25123 to silence errors about missing
credentials when authenticating providers in the background.
Release Notes:
- N/A
Fix a bug where a GPUI macro still used `ModelContext`
Rename `AsyncAppContext` -> `AsyncApp`
Rename update_model, read_model, insert_model, and reserve_model to
update_entity, read_entity, insert_entity, and reserve_entity
Release Notes:
- N/A
There's still a bit more work to do on this, but this PR is compiling
(with warnings) after eliminating the key types. When the tasks below
are complete, this will be the new narrative for GPUI:
- `Entity<T>` - This replaces `View<T>`/`Model<T>`. It represents a unit
of state, and if `T` implements `Render`, then `Entity<T>` implements
`Element`.
- `&mut App` This replaces `AppContext` and represents the app.
- `&mut Context<T>` This replaces `ModelContext` and derefs to `App`. It
is provided by the framework when updating an entity.
- `&mut Window` Broken out of `&mut WindowContext` which no longer
exists. Every method that once took `&mut WindowContext` now takes `&mut
Window, &mut App` and every method that took `&mut ViewContext<T>` now
takes `&mut Window, &mut Context<T>`
Not pictured here are the two other failed attempts. It's been quite a
month!
Tasks:
- [x] Remove `View`, `ViewContext`, `WindowContext` and thread through
`Window`
- [x] [@cole-miller @mikayla-maki] Redraw window when entities change
- [x] [@cole-miller @mikayla-maki] Get examples and Zed running
- [x] [@cole-miller @mikayla-maki] Fix Zed rendering
- [x] [@mikayla-maki] Fix todo! macros and comments
- [x] Fix a bug where the editor would not be redrawn because of view
caching
- [x] remove publicness window.notify() and replace with
`AppContext::notify`
- [x] remove `observe_new_window_models`, replace with
`observe_new_models` with an optional window
- [x] Fix a bug where the project panel would not be redrawn because of
the wrong refresh() call being used
- [x] Fix the tests
- [x] Fix warnings by eliminating `Window` params or using `_`
- [x] Fix conflicts
- [x] Simplify generic code where possible
- [x] Rename types
- [ ] Update docs
### issues post merge
- [x] Issues switching between normal and insert mode
- [x] Assistant re-rendering failure
- [x] Vim test failures
- [x] Mac build issue
Release Notes:
- N/A
---------
Co-authored-by: Antonio Scandurra <me@as-cii.com>
Co-authored-by: Cole Miller <cole@zed.dev>
Co-authored-by: Mikayla <mikayla@zed.dev>
Co-authored-by: Joseph <joseph@zed.dev>
Co-authored-by: max <max@zed.dev>
Co-authored-by: Michael Sloan <michael@zed.dev>
Co-authored-by: Mikayla Maki <mikaylamaki@Mikaylas-MacBook-Pro.local>
Co-authored-by: Mikayla <mikayla.c.maki@gmail.com>
Co-authored-by: joão <joao@zed.dev>
`LanguageModel::stream_completion_text` can poll the `stream_completion`
stream (ultimately a `futures::Unfold`) after it's returned
`Ready(None)`, which leads to a panic; avoid this by fusing the stream.
Release Notes:
- Fixed a panic when streaming language model completions
This PR restructures the storage of the tool uses and results in
`assistant2` so that they don't live on the individual messages.
It also introduces a `LanguageModelToolUseId` newtype for better type
safety.
Release Notes:
- N/A
This PR adds a new `language_models` crate to house the various language
model providers.
By extracting the provider definitions out of `language_model`, we're
able to remove `language_model`'s dependency on `editor`, which improves
incremental compilation when changing `editor`.
Release Notes:
- N/A
This PR adds a bit of telemetry for Anthropic models, in order to
understand model health. With this logging, we can monitor and diagnose
dips in performance, for example due to model rollouts.
Release Notes:
- N/A
---------
Co-authored-by: Max Brunsfeld <maxbrunsfeld@gmail.com>
This PR adds a bit more metadata for assistant logging.
Release Notes:
- Assistant: Added `language_name` and `model_provider` fields to
telemetry events.
---------
Co-authored-by: Marshall Bowers <elliott.codes@gmail.com>
Co-authored-by: Max <max@zed.dev>
This PR updates the message content for an LLM request to allow it
contain tool uses.
We need to send the tool uses back to the model in order for it to
recognize the subsequent tool results.
Release Notes:
- N/A
This PR makes it so we propagate the `stop_reason` from Anthropic up to
the Assistant so that we can take action based on it.
The `extract_content_from_events` function was moved from `anthropic` to
the `anthropic` module in `language_model` since it is more useful if it
is able to name the `LanguageModelCompletionEvent` type, as otherwise
we'd need an additional layer of plumbing.
Release Notes:
- N/A
This PR adjusts the approach we use to encoding tool uses in the
completion response to use a structured format rather than simply
injecting it into the response stream as text.
In #17170 we would encode the tool uses as XML and insert them as text.
This would require then re-parsing the tool uses out of the buffer in
order to use them.
The approach taken in this PR is to make `stream_completion` return a
stream of `LanguageModelCompletionEvent`s. Each of these events can be
either text, or a tool use.
A new `stream_completion_text` method has been added to `LanguageModel`
for scenarios where we only care about textual content (currently,
everywhere that isn't the Assistant context editor).
Release Notes:
- N/A
This commit adds a custom icon for Anthropic hosted models.
- Adding a new SVG icon for Anthropic hosted models.
- The new icon is located at: `assets/icons/ai_anthropic_hosted.svg`
- Updating the LanguageModel trait to include an optional icon method
- Implementing the icon method for CloudModel to return the custom icon
for Anthropic hosted models
- Updating the UI components to use the model-specific icon when
available
- Adding a new IconName variant for the Anthropic hosted icon
We should change the non-hosted icon in some small way to distinguish it
from the hosted version. I duplicated the path for now so we can
hopefully add it for the next release.
Release Notes:
- N/A
Release Notes:
- Adds support for Prompt Caching in Anthropic. For models that support
it this can dramatically lower cost while improving performance.
This PR is just a refactor, to pave the way toward adding a view for
workflow step resolution. The entity carries the state of the tool
call's streaming output.
Release Notes:
- N/A
This PR is a refactor to pave the way for allowing the user to view and
edit workflow step resolutions. I've made tool calls work more like
normal streaming completions for all providers. The `use_any_tool`
method returns a stream of strings (which contain chunks of JSON). I've
also done some minor cleanup of language model providers in general,
removing the duplication around handling streaming responses.
Release Notes:
- N/A
