## Summary
Fixes#37815.
`State::fetch_models()` calls `/api/tags` to list models, then calls
`/api/show` for **every** model in that list to get its capabilities,
collecting the results with `collect::<Result<Vec<_>>>()?`. If
`/api/show` errors for even one model, the whole batch fails and
`fetched_models` is never populated. Since `is_authenticated()` is
defined as `!self.fetched_models.is_empty()`, this means a single bad
model permanently breaks both authentication state and the model picker
for the entire Ollama provider - with no error surfaced anywhere (not
the UI, not the logs), which matches the reports in #37815 of "Connect
does nothing" / "no logs, no nothing".
I hit this myself: I had a stale local reference to an Ollama Cloud
model that had been retired server-side. `/api/show` for that one model
returned `410 Gone`, which silently broke Connect and the model picker
for every other model too. Removing the retired model with `ollama rm`
fixed it immediately, which confirmed the root cause.
## Fix
Instead of aborting the whole fetch on the first error, skip individual
models that fail `/api/show` and log a warning, keeping the rest.
Extracted this into a small `skip_failed_models` helper so it's
unit-testable without mocking HTTP.
## Disclosure
I used Claude (Anthropic's Claude Code) to help track down this root
cause (tracing through `fetch_models`/`is_authenticated` in this file)
and draft the fix + tests below. I reviewed and understand the change -
it's a small, targeted fix to a single function plus two unit tests for
the new helper.
## Test plan
- [x] `cargo check -p language_models` passes
- [x] `cargo test -p language_models --lib ollama::` - all 3 tests pass
(the 2 new ones plus the existing
`test_merge_settings_preserves_display_names_for_similar_models`,
unaffected by this change)
- [x] `cargo fmt -p language_models -- --check` - no diff
## Release Notes
Release Notes:
- Fixed Ollama models silently failing to show up in the model picker
(and "Connect" appearing to do nothing) when a single model's details
couldn't be fetched, e.g. a retired Ollama Cloud model
---------
Co-authored-by: MrSubidubi <finn@zed.dev>
Co-authored-by: Ben Brandt <benjamin.j.brandt@gmail.com>
Add a `custom_headers` setting to each HTTP-based language model
provider
(Anthropic, Bedrock, DeepSeek, Google, LM Studio, Mistral, Ollama,
OpenAI,
OpenAI-compatible, OpenCode, OpenRouter, Vercel AI Gateway, and xAI) so
users
can attach extra headers to every outgoing request. Headers managed by
Zed
(authentication, content-type, etc.) cannot be overridden and are
skipped with
a warning.
Self-Review Checklist:
- [x] I've reviewed my own diff for quality, security, and reliability
- [x] Unsafe blocks (if any) have justifying comments
- [x] The content is consistent with the [UI/UX
checklist](https://github.com/zed-industries/zed/blob/main/CONTRIBUTING.md#uiux-checklist)
- [] Tests cover the new/changed behavior
- [x] Performance impact has been considered and is acceptable
Release Notes:
- Added support for configuring custom HTTP headers on language model
providers via `language_models.<provider>.custom_headers`.
Signed-off-by: Aurabindo Pillai <mail@aurabindo.in>
Self-Review Checklist:
- [x] I've reviewed my own diff for quality, security, and reliability
- [x] Unsafe blocks (if any) have justifying comments
- [x] The content is consistent with the [UI/UX
checklist](https://github.com/zed-industries/zed/blob/main/CONTRIBUTING.md#uiux-checklist)
- [x] Tests cover the new/changed behavior
- [x] Performance impact has been considered and is acceptable
Fixes calculation of Ollama model context length. Now prefers num_ctx
model configuration over model architecture context length the same way
Ollama does.
Closes#42340
Release Notes:
- Fix calculation of Ollama model context length
## Summary
When no stop tokens are provided, Zed was sending an empty array
(`"stop": []`) to Ollama. This caused Ollama to override the model's
default stop tokens (defined in its Modelfile) with nothing, resulting
in models like rnj-1:8b generating infinitely with literal stop tokens
appearing in the output.
## Problem
Models with custom stop tokens in their Modelfile (like `<|eot_id|>` for
rnj-1:8b) would generate forever because:
1. Agent thread creates request with `stop: Vec::new()` (empty)
2. Ollama provider converts this to `stop: Some(vec![])`
3. Serializes as `"stop": []` in JSON
4. Ollama interprets this as "override default stop tokens with nothing"
5. Model generates forever, outputting stop tokens as literal text
## Solution
1. In `crates/language_models/src/provider/ollama.rs`:
- Only send `stop` when explicitly provided
- When empty, use `None` so the field is omitted from JSON
2. In `crates/ollama/src/ollama.rs`:
- Add `#[serde(skip_serializing_if = "Option::is_none")]` to all
`ChatOptions` fields
- Ensures `None` values are omitted, not serialized as `null`
## Testing
Added 4 new tests in `crates/ollama/src/ollama.rs`:
- `test_chat_options_serialization`: Verifies None fields are omitted
- `test_chat_request_with_stop_tokens`: Verifies stop tokens are
serialized when provided
- `test_chat_request_without_stop_tokens_omits_field`: Verifies empty
stop is omitted
All 11 ollama tests pass, plus 1 language_models ollama test.
Fixes#47798
Release Notes:
- Fixed Ollama models with custom stop tokens generating infinitely by
not overriding model defaults when no stop tokens are specified.
Release Notes:
- Changed the way context window is set for ollama at the provider level
instead of per model.
---------
Co-authored-by: Conrad Irwin <conrad.irwin@gmail.com>
Closes#42303
Ollama added tool call identifiers
(https://github.com/ollama/ollama/pull/12956) in its latest version
[v0.12.10](https://github.com/ollama/ollama/releases/tag/v0.12.10). This
broke our json schema and made all tool calls fail.
This PR fixes the schema and uses the Ollama provided tool call
identifier when available. We remain backwards compatible and still use
our own identifier with older versions of Ollama. I added a `TODO` to
remove the `Option` around the new field when most users have updated
their installations to v0.12.10 or above.
Note to reviewer: The fix to this issue should likely get cherry-picked
into the next release, since Ollama becomes unusable as an agent without
it.
Release Notes:
- Fixed tool calling when using the latest version of Ollama
We've been considering removing workspace-hack for a couple reasons:
- Lukas ran into a situation where its build script seemed to be causing
spurious rebuilds. This seems more likely to be a cargo bug than an
issue with workspace-hack itself (given that it has an empty build
script), but we don't necessarily want to take the time to hunt that
down right now.
- Marshall mentioned hakari interacts poorly with automated crate
updates (in our case provided by rennovate) because you'd need to have
`cargo hakari generate && cargo hakari manage-deps` after their changes
and we prefer to not have actions that make commits.
Currently removing workspace-hack causes our workspace to grow from
~1700 to ~2000 crates being built (depending on platform), which is
mainly a problem when you're building the whole workspace or running
tests across the the normal and remote binaries (which is where
feature-unification nets us the most sharing). It doesn't impact
incremental times noticeably when you're just iterating on `-p zed`, and
we'll hopefully get these savings back in the future when
rust-lang/cargo#14774 (which re-implements the functionality of hakari)
is finished.
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
`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
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>
Adding mistral nemo, sorting by name and adding comment about clamp
sizing
Release Notes:
- Added support for mistral-nemo
---------
Co-authored-by: Conrad Irwin <conrad.irwin@gmail.com>
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
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
We push the usage data whenever we receive it from the provider to make
sure the counting is correct after the turn has ended.
- [x] Ollama
- [x] Copilot
- [x] Mistral
- [x] OpenRouter
- [x] LMStudio
Put all the changes into a single PR open to move these to separate PR
if that makes the review and testing easier.
Release Notes:
- N/A
Removes the load_model trait method and its implementations in Ollama
and LM Studio providers, along with associated preload_model functions
and unused imports.
Release Notes:
- N/A
This PR updates how we handle Ollama responses, leveraging the new
[v0.9.0](https://github.com/ollama/ollama/releases/tag/v0.9.0) release.
Previously, thinking text was embedded within the model's main content,
leading to it appearing directly in the agent's response. Now, thinking
content is provided as a separate parameter, allowing us to display it
correctly within the agent panel, similar to other providers. I have
tested this with qwen3:8b and works nicely. ~~We can release this once
the ollama is release is stable.~~ It's released now as stable.
<img width="433" alt="image"
src="https://github.com/user-attachments/assets/2983ef06-6679-4033-82c2-231ea9cd6434"
/>
Release Notes:
- Add thinking support for ollama
---------
Co-authored-by: Bennet Bo Fenner <bennetbo@gmx.de>
Ollama increased their default context size from 2048 to 4096 tokens in
version v0.6.7, which released over a month ago.
https://github.com/ollama/ollama/releases/tag/v0.6.7
Release Notes:
- ollama: Update default model context to 4096 (matching upstream)
Mistral just released a sota coding model:
https://mistral.ai/news/devstral
This PR adds support for it in both ollama and mistral
Release Notes:
- Add DevstralSmallLatest model to Mistral and Ollama
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
The goal of this PR is to support tool calls using ollama. A lot of the
serialization work was done in
https://github.com/zed-industries/zed/pull/15803 however the abstraction
over language models always disables tools.
## Changelog:
- Use `serde_json::Value` inside `OllamaFunctionCall` just as it's used
in `OllamaFunctionCall`. This fixes deserialization of ollama tool
calls.
- Added deserialization tests using json from official ollama api docs.
- Fetch model capabilities during model enumeration from ollama provider
- Added `supports_tools` setting to manually configure if a model
supports tools
## TODO:
- [x] Fix tool call serialization/deserialization
- [x] Fetch model capabilities from ollama api
- [x] Add tests for parsing model capabilities
- [ ] Documentation for `supports_tools` field for ollama language model
config
- [ ] Convert between generic language model types
- [x] Pass tools to ollama
Release Notes:
- N/A
---------
Co-authored-by: Antonio Scandurra <me@as-cii.com>
Co-authored-by: Nathan Sobo <nathan@zed.dev>
If you have the VRAM you can increase the context by adding this to your
settings.json:
```json
"language_models": {
"ollama": {
"available_models": [
{ "max_tokens": 65536, "name": "qwen3", "display_name": "Qwen3-64k" }
]
}
},
```
Release Notes:
- ollama: Add support for Qwen3. Defaults to 16K token context. See:
[Assistant Configuration
Docs](https://zed.dev/docs/assistant/configuration#ollama-context) to
increase.
The `ollama` crate has a `use schemars::JsonSchema` statement even when
building with default features, which doesn't include the `schemars`
crate.
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>
Add `phi4` maximum context length (128K).
By default this clamps to `16384` but if you have enough video memory
you can set it higher or connect to a non-local machine via settings:
```json
"language_models": {
"ollama": {
"api_url": "http://localhost:11434",
"available_models": [
{
"name": "phi4",
"display_name": "Phi4 64K",
"max_tokens": 65536
}
]
}
}
```
Release Notes:
- Improve support for Phi4 with ollama.
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>
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
