Some APIs fail when they get this parameter
Closes#36215
Release Notes:
- Fixed OpenAI-compatible providers that don't support prompt caching
and/or reasoning
Release Notes:
- Added `reasoning_effort` support to custom models
Tested using the following config:
```json5
"language_models": {
"openai": {
"available_models": [
{
"name": "gpt-5-mini",
"display_name": "GPT 5 Mini (custom reasoning)",
"max_output_tokens": 128000,
"max_tokens": 272000,
"reasoning_effort": "high" // Can be minimal, low, medium (default), and high
}
],
"version": "1"
}
}
```
Docs:
https://platform.openai.com/docs/api-reference/chat/create#chat_create-reasoning_effort
This work could be used to split the GPT 5/5-mini/5-nano into each of
it's reasoning effort variant. E.g. `gpt-5`, `gpt-5 low`, `gpt-5
minimal`, `gpt-5 high`, and same for mini/nano.
Release Notes:
* Added a setting to control `reasoning_effort` in OpenAI models
Context: In this PR: https://github.com/zed-industries/zed/pull/33362,
we started to use underlying open_ai crate for making api calls for
vercel as well. Now whenever we get the error we get something like the
below. Where on part of the error mentions OpenAI but the rest of the
error returns the actual error from provider. This PR tries to make the
error generic for now so that people don't get confused seeing OpenAI in
their v0 integration.
```
Error interacting with language model
Failed to connect to OpenAI API: 403 Forbidden {"success":false,"error":"Premium or Team plan required to access the v0 API: https://v0.dev/chat/settings/billing"}
```
Release Notes:
- N/A
Ran into this while adding support for Vercel v0s models:
- The timestamp seems to be returned in Milliseconds instead of seconds
so it breaks the bounds of `created: u32`. We did not use this field
anywhere so just decided to remove it
- Sometimes the `choices` field can be empty when the last chunk comes
in because it only contains `usage`
Release Notes:
- N/A
Previously we were using a mix of `u32` and `usize`, e.g. `max_tokens:
usize, max_output_tokens: Option<u32>` in the same `struct`.
Although [tiktoken](https://github.com/openai/tiktoken) uses `usize`,
token counts should be consistent across targets (e.g. the same model
doesn't suddenly get a smaller context window if you're compiling for
wasm32), and these token counts could end up getting serialized using a
binary protocol, so `usize` is not the right choice for token counts.
I chose to standardize on `u64` over `u32` because we don't store many
of them (so the extra size should be insignificant) and future models
may exceed `u32::MAX` tokens.
Release Notes:
- N/A
Remove unnecessary alias attributes from Model enum variants and add
max_output_tokens limits for all OpenAI models. Also fix
supports_system_messages to explicitly handle all model variants.
Release Notes:
- N/A
There is no ISSUE opened on this topic
Release Notes:
- N/A
---------
Co-authored-by: Peter Tripp <peter@zed.dev>
Co-authored-by: Ben Brandt <benjamin.j.brandt@gmail.com>
Fixes regression caused by:
https://github.com/zed-industries/zed/pull/30639
Assistant messages can come back with no content, and we no longer
allowed that in the deserialization.
Release Notes:
- open_ai: fixed deserialization issue if assistant content was empty
https://github.com/zed-industries/zed/issues/30972 brought up another
case where our context is not enough to track the actual source of the
issue: we get a general top-level error without inner error.
The reason for this was `.ok_or_else(|| anyhow!("failed to read HEAD
SHA"))?; ` on the top level.
The PR finally reworks the way we use anyhow to reduce such issues (or
at least make it simpler to bubble them up later in a fix).
On top of that, uses a few more anyhow methods for better readability.
* `.ok_or_else(|| anyhow!("..."))`, `map_err` and other similar error
conversion/option reporting cases are replaced with `context` and
`with_context` calls
* in addition to that, various `anyhow!("failed to do ...")` are
stripped with `.context("Doing ...")` messages instead to remove the
parasitic `failed to` text
* `anyhow::ensure!` is used instead of `if ... { return Err(...); }`
calls
* `anyhow::bail!` is used instead of `return Err(anyhow!(...));`
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
Release Notes:
- Add support for OpenAI o3 and o4-mini models via OpenAI API and
Copilot Chat providers.
---------
Co-authored-by: Peter Tripp <peter@zed.dev>
Release Notes:
- Add support for OpenAI GPT-4.1 via Copilot Chat and OpenAI API
---------
Co-authored-by: Danilo Leal <daniloleal09@gmail.com>
Co-authored-by: Bennet Bo Fenner <bennetbo@gmx.de>
This PR disables `parallel_tool_calls` for the models that support it,
as the Agent currently expects at most one tool use per turn.
It was a bit of trial and error to figure this out. OpenAI's API
annoyingly will return an error if passing `parallel_tool_calls` to a
model that doesn't support it.
Release Notes:
- N/A
This adds a "workspace-hack" crate, see
[mozilla's](https://hg.mozilla.org/mozilla-central/file/3a265fdc9f33e5946f0ca0a04af73acd7e6d1a39/build/workspace-hack/Cargo.toml#l7)
for a concise explanation of why this is useful. For us in practice this
means that if I were to run all the tests (`cargo nextest r
--workspace`) and then `cargo r`, all the deps from the previous cargo
command will be reused. Before this PR it would rebuild many deps due to
resolving different sets of features for them. For me this frequently
caused long rebuilds when things "should" already be cached.
To avoid manually maintaining our workspace-hack crate, we will use
[cargo hakari](https://docs.rs/cargo-hakari) to update the build files
when there's a necessary change. I've added a step to CI that checks
whether the workspace-hack crate is up to date, and instructs you to
re-run `script/update-workspace-hack` when it fails.
Finally, to make sure that people can still depend on crates in our
workspace without pulling in all the workspace deps, we use a `[patch]`
section following [hakari's
instructions](https://docs.rs/cargo-hakari/0.9.36/cargo_hakari/patch_directive/index.html)
One possible followup task would be making guppy use our
`rust-toolchain.toml` instead of having to duplicate that list in its
config, I opened an issue for that upstream: guppy-rs/guppy#481.
TODO:
- [x] Fix the extension test failure
- [x] Ensure the dev dependencies aren't being unified by Hakari into
the main dependencies
- [x] Ensure that the remote-server binary continues to not depend on
LibSSL
Release Notes:
- N/A
---------
Co-authored-by: Mikayla <mikayla@zed.dev>
Co-authored-by: Mikayla Maki <mikayla.c.maki@gmail.com>
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>
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>
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
Release Notes:
- Added support for OpenAI o1-mini and o1-preview models.
---------
Co-authored-by: Jason Mancuso <7891333+jvmncs@users.noreply.github.com>
Co-authored-by: Bennet <bennet@zed.dev>
This is a barebones modification of the OpenAI provider code to
accommodate non-streaming completions. This is specifically for the o1
models, which do not support streaming. Tested that this is working by
running a `/workflow` with the following (arbitrarily chosen) settings:
```json
{
"language_models": {
"openai": {
"version": "1",
"available_models": [
{
"name": "o1-preview",
"display_name": "o1-preview",
"max_tokens": 128000,
"max_completion_tokens": 30000
},
{
"name": "o1-mini",
"display_name": "o1-mini",
"max_tokens": 128000,
"max_completion_tokens": 20000
}
]
}
},
}
```
Release Notes:
- Changed `low_speed_timeout_in_seconds` option to `600` for OpenAI
provider to accommodate recent o1 model release.
---------
Co-authored-by: Peter <peter@zed.dev>
Co-authored-by: Bennet <bennet@zed.dev>
Co-authored-by: Marshall Bowers <elliott.codes@gmail.com>
- Cloudflare provides ISO-3166-1 country code for protectorates. Expand our allowlist to include the territories of countries on the allowlist (US, UK, France, Australia, New Zealand).
- Also include the country_code in the error message when we block.
Co-authored-by: Marshall Bowers <elliott.codes@gmail.com>
### Pull Request Title
Introduce `max_output_tokens` Field for OpenAI Models
https://platform.deepseek.com/api-docs/news/news0725/#4-8k-max_tokens-betarelease-longer-possibilities
### Description
This commit introduces a new field `max_output_tokens` to the OpenAI
models, which allows specifying the maximum number of tokens that can be
generated in the output. This field is now integrated into the request
handling across multiple crates, ensuring that the output token limit is
respected during language model completions.
Changes include:
- Adding `max_output_tokens` to the `Custom` variant of the
`open_ai::Model` enum.
- Updating the `into_open_ai` method in `LanguageModelRequest` to accept
and use `max_output_tokens`.
- Modifying the `OpenAiLanguageModel` and `CloudLanguageModel`
implementations to pass `max_output_tokens` when converting requests.
- Ensuring that the `max_output_tokens` field is correctly serialized
and deserialized in relevant structures.
This enhancement provides more control over the output length of OpenAI
model responses, improving the flexibility and accuracy of language
model interactions.
### Changes
- Added `max_output_tokens` to the `Custom` variant of the
`open_ai::Model` enum.
- Updated the `into_open_ai` method in `LanguageModelRequest` to accept
and use `max_output_tokens`.
- Modified the `OpenAiLanguageModel` and `CloudLanguageModel`
implementations to pass `max_output_tokens` when converting requests.
- Ensured that the `max_output_tokens` field is correctly serialized and
deserialized in relevant structures.
### Related Issue
https://github.com/zed-industries/zed/pull/16358
### Screenshots / Media
N/A
### Checklist
- [x] Code compiles correctly.
- [x] All tests pass.
- [ ] Documentation has been updated accordingly.
- [ ] Additional tests have been added to cover new functionality.
- [ ] Relevant documentation has been updated or added.
### Release Notes
- Added `max_output_tokens` field to OpenAI models for controlling
output token length.
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
This PR updates the LLM service to authorize access to language model
providers based on the requester's country.
We detect the country using Cloudflare's
[`CF-IPCountry`](https://developers.cloudflare.com/fundamentals/reference/http-request-headers/#cf-ipcountry)
header.
The country code is then checked against the list of supported countries
for the given LLM provider. Countries that are not supported will
receive an `HTTP 451: Unavailable For Legal Reasons` response.
Release Notes:
- N/A
- [x] OpenAI
- [ ] ~Google~ Moved into a separate branch at:
https://github.com/zed-industries/zed/tree/tool-calls-in-google-ai I've
ran into issues with having the API digest our schema without tripping
over itself - the function call parameters are malformed and whatnot. We
can resume from that branch if needed.
- [x] Ollama
- [x] Cloud
- [ ] ~Copilot Chat (?)~
Release Notes:
- Added tool calling capabilities to OpenAI and Ollama models.
In this pull request, we change the zed.dev protocol so that we pass the
raw JSON for the specified provider directly to our server. This avoids
the need to define a protobuf message that's a superset of all these
formats.
@bennetbo: We also changed the settings for available_models under
zed.dev to be a flat format, because the nesting seemed too confusing.
Can you help us upgrade the local provider configuration to be
consistent with this? We do whatever we need to do when parsing the
settings to make this simple for users, even if it's a bit more complex
on our end. We want to use versioning to avoid breaking existing users,
but need to keep making progress.
```json
"zed.dev": {
"available_models": [
{
"provider": "anthropic",
"name": "some-newly-released-model-we-havent-added",
"max_tokens": 200000
}
]
}
```
Release Notes:
- N/A
---------
Co-authored-by: Nathan <nathan@zed.dev>
