Release Notes:

- N/A

Release Notes:

- agent: Improve MCP tools compatibility with Gemini models

cc @notpeter

Before this change we used our own copy of `cx.key_context()` when
matching.
This led to races where the context queried could be either before (or
after) the
context used in dispatching.

To avoid the race, gpui now passes out the context stack actually used
instead.

Release Notes:

- Fixed a bug where the Key Context View could show the incorrect
context,
  causing confusing results.

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.

Add deepseek-v3 max token length for ollama

Release Notes:

- N/A

These were nearly always used when using `format!` / `write!` etc, so it
makes sense to not have an intermediate `String`.

Release Notes:

- N/A

When using the agent with a project shared by a collaborator, rules file
loading didn't work as it was trying to read from the client's
filesystem

Release Notes:

- Fixed rules file loading when using the agent with a project shared by
a collaborator.

This PR puts the displaying of the plan in the user menu behind the
`new-billing` feature flag instead of the old `zed-pro` feature flag.

Release Notes:

- N/A

This PR adds the `FeatureFlag` suffix to the feature flag types that
were missing them.

This makes the names easier to search in the codebase.

Release Notes:

- N/A

This PR removes the `remoting` feature flag.

The feature is shipped, and we aren't referencing the flag anywhere
anymore.

Release Notes:

- N/A

This PR addresses the behavior of the agent's terminal tool when the
executed command is interrupted or fails after producing some output.
Currently, if the command doesn't finish successfully, any partial
output captured before the interruption/failure is discarded, and only
an error message (or a generic cancellation message) is returned to the
LLM.

This change modifies the `run_command_limited` function in the terminal
tool to catch errors when awaiting the command's status (which includes
interruptions). In the case of such an error, it now includes any
partial stdout/stderr captured up to that point within the error message
returned to the `ToolUseState`. This ensures the LLM receives the
partial context even when the command doesn't complete cleanly, framed
appropriately as part of an error/interruption message.

Closes #29101

Release Notes:

- N/A

This PR wires the counting of Google AI tokens back up.

It now goes through the LLM service instead of collab's RPC.

Still only available for Zed staff.

Release Notes:

- N/A

This PR makes it so we pass up the `mode` for completion requests
through the Zed provider.

Release Notes:

- N/A

This PR removes the `CountLanguageModelTokens` RPC message from collab.

We were only using this for Google AI models through the Zed provider
(which is only available to Zed staff).

For now we're returning `0`, but will bring back soon.

Release Notes:

- N/A

This PR removes the embeddings-related code from collab and the
protocol, as we weren't using it anywhere.

Release Notes:

- N/A

This change updates the system prompt to conditionally include
`grep`-related instructions based on whether the `grep` tool is enabled.

Implementation details:
1. Add a `has_tool` handlebars helper.
2. Pass the `model` to all locations where the prompt is built.
3. Use `{{#if has_tool "grep"}}` in the system prompt to gate
`grep`-specific instructions.

Testing:
- Unit tests for the `hasTool` helper.
- Unit tests to verify that `grep`-related instructions are included /
omitted from the prompt as appropriate.
- Manual agent evaluation:
- Setup: Asked the Agent "List all impls of MyTrait in the project"
using a custom "No tools" profile (all tools disabled).
- Before the change: The Agent attempted to call `grep`, encountered an
error, then realized the tool was unavailable.
- After the change: The Agent immediately asked to enable a search tool.

Note: in principle, `grep`/`read_file` tool descriptions alone might be
enough, but to confirm this we need more evaluation. If it turns out to
be true, we'll be able to remove grep-specific instructions from the
system prompt and undo this change.

Release Notes:

- N/A

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

* Brings back hover popover of selection context.

* Adds hover popover for symbol, rules, and thread context.

* Makes context attached to messages display the names / content at
attachment time.

* Adds the file name as the displayed parent of symbol context.

* Brings back `impl Component for AddedContext`

Release Notes:

- N/A

---------

Co-authored-by: Bennet Bo Fenner <bennet@zed.dev>

Truncation to a 32 bit `usize` could cause two distinct IDs to be
considered the same element.

Release Notes:

- N/A

Cherry-picked askpass: Shell escape Zed path in askpass script (#29447)

Closes #29439

Add shell escaping as well as additional sanity check for Zed path when
used in askpass. This caused issues on preview and nightly as the
standard paths for those releases contain spaces which were not escaped
appropriately leading to erroneous "Permission denied" errors from SSH
when the askpass script failed

Release Notes:

- Fixed a missing shell-escape in askpass resulting in erroneous
"Permission denied" errors when trying to connect to a remote server
over ssh (effecting preview release v0.184.1 and nightly only)

Co-authored-by: Ben Kunkle <ben@zed.dev>

Namely, this PR removes the layout shift when you click on a user
message to edit it and displays the feedback disclaimer only upon
hovering the thumbs up/down button container.

Release Notes:

- N/A

This also fixes a little UI bug where the text thread title would push
the buttons away from the UI when there was still space.

Release Notes:

- agent: Made text thread titles editable again.

---------

Co-authored-by: Michael Sloan <mgsloan@gmail.com>

One motivation is that the outlines returned by `read_file` for large
files list line numbers assuming an inclusive `end_line`. As a result,
when the agent uses these outlines for `read_line` calls, it would
otherwise miss the last line.

Release Notes:

- N/A

Sometimes Gemini would report `Content` without a `parts` field.

Release Notes:

- Fixed a bug that would sometimes cause Gemini models to fail streaming
their response.

Add new test and improve fuzzy match bucket logic which results into far
better balance between LSP and fuzzy search.

Before:
<img width="500" alt="before"
src="https://github.com/user-attachments/assets/3e8900a6-c0ff-4f37-b88e-b0e3783b7e9a"
/>

After:
<img width="500" alt="after"
src="https://github.com/user-attachments/assets/738c074c-d446-4697-aac6-9814362e88db"
/>

Release Notes:

- N/A

Added `snippet_sort_order`, which determines how snippets are sorted
relative to other completion items. It can have the values `top`,
`bottom`, or `inline`, with `inline` being the default.

This mimics VS Code’s setting:
https://code.visualstudio.com/docs/editing/intellisense#_snippets-in-suggestions

Release Notes:

- Added support for `snippet_sort_order` to control snippet sorting
behavior in code completion menus.

This makes it easy to have a label that looks like Markdown inline code
via the `inline_code(cx)` method.

Release Notes:

- N/A

Accidentally omitted this in #29233

Release Notes:

- N/A

Implementing the `ToolCard` for the path_search tool. It also adds the
"jump to file" functionality if you expand the results.

Release Notes:

- N/A

---------

Co-authored-by: Richard Feldman <oss@rtfeldman.com>
Co-authored-by: Agus Zubiaga <hi@aguz.me>

Seeing the markdown code stream in is actually more helpful than hiding
parts of it; parts that you may be interested in.

Release Notes:

- N/A

Previously, all MCP tools would be completed regardless if they were
disabled/enabled for the profile. This meant that the "Write" profile
was always using all MCP tools, even if you disabled them in the
settings.

Now, when `enable_all_context_servers` is set to `true`, we will enable
all tools from all MCP servers by default but disable the ones that are
explicitly disabled for the profile.

Also fixes an issue where the tools would not show up as enabled when
using `enable_all_context_servers: true`

Release Notes:

- agent: Fix an issue where MCP tools could not be enabled/disabled

Cherry-picked assistant: Fix issue when using inline assistant with
Gemini models (#29407)

Closes #29020

Release Notes:

- assistant: Fix issue when using inline assistant with Gemini models

Co-authored-by: Bennet Bo Fenner <bennet@zed.dev>

This PR updates the Zed provider to use the `POST /completions`
endpoint.

There is no functional difference from `POST /completion`, but the
pluralized version reads better.

Release Notes:

- N/A

Realized after merging #29233 that this behavior is desired

Release Notes:

- N/A

This PR removes two fields from JSON schemas (`$schema` and `title`),
which are not expected by any model provider, but were spuriously
included by our JSON schema library, `schemars`.

These added noise to requests and cost wasted input tokens.

### Old

```json
{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "title": "FetchToolInput",
  "type": "object",
  "required": [
    "url"
  ],
  "properties": {
    "url": {
      "description": "The URL to fetch.",
      "type": "string"
    }
  }
}
```

### New:

```json
{
  "properties": {
    "url": {
      "description": "The URL to fetch.",
      "type": "string"
    }
  },
  "required": [
    "url"
  ],
  "type": "object"
}
```

- N/A

Simplifies the data structures involved in agent context by removing
caching and limiting the use of ContextId:

* `AssistantContext` enum is now like an ID / handle to context that
does not need to be updated. `ContextId` still exists but is only used
for generating unique `ElementId`.
* `ContextStore` has a `IndexMap<ContextSetEntry>`. Only need to keep a
`HashSet<ThreadId>` consistent with it. `ContextSetEntry` is a newtype
wrapper around `AssistantContext` which implements eq / hash on a subset
of fields.
* Thread `Message` directly stores its context.

Fixes the following bugs:

* If a context entry is removed from the strip and added again, it was
reincluded in the next message.
* Clicking file context in the thread that has been removed from the
context strip didn't jump to the file.
* Refresh of directory context didn't reflect added / removed files.
* Deleted directories would remain in the message editor context strip.
* Token counting requests didn't include image context.
* File, directory, and symbol context deduplication relied on
`ProjectPath` for identity, and so didn't handle renames.
* Symbol context line numbers didn't update when shifted

Known bugs (not fixed):

* Deleting a directory causes it to disappear from messages in threads.
Fixing this in a nice way is tricky. One easy fix is to store the
original path and show that on deletion. It's weird that deletion would
cause the name to "revert", though. Another possibility would be to
snapshot context metadata on add (ala `AddedContext`), and keep that
around despite deletion.

Release Notes:

- N/A

Release Notes:

- N/A

---------

Co-authored-by: Max <max@zed.dev>
Co-authored-by: Max Brunsfeld <maxbrunsfeld@gmail.com>

There's probably more to do to fully make the transition, and we'll
still debate a bit internally whether this is the name, but just opening
this PR up now for visibility.

Release Notes:

- N/A

Fixes a regression introduced in #29322

Release Notes:

- N/A

Co-authored-by: Agus Zubiaga <hi@aguz.me>

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

#29354 introduced a bug where we would append tool uses to the last
assistant message even if it was from a previous request.

Release Notes:

- N/A

Co-authored-by: Bennet Bo Fenner <bennetbo@gmx.de>

We used to insert empty user messages into the `Thread::messages` `Vec`
when tools finished running and then we would attach the results when
creating the request. This approach was very easy to mess up during
state handling, leading to empty user messages displayed in the
conversation and API failures.

Instead, we will no longer insert actual user messages for tool results
to the `Thread`, and will only do this on the fly when creating the
model request. This simplifies a lot of code and show fix the mentioned
errors.

Release Notes:

- agent: Improve reliability of LLM requests when including tool results

---------

Co-authored-by: Bennet Bo Fenner <bennetbo@gmx.de>
Co-authored-by: Oleksiy Syvokon <oleksiy.syvokon@gmail.com>

Follow-up to https://github.com/zed-industries/zed/pull/29165 where the
user message design is simplified even more. The edit button is not
visible anymore, and you can click on the whole message block to edit a
message.

Release Notes:

- N/A

Closes: https://github.com/zed-industries/zed/issues/24501

This has been broken for a while on linux (at least since Feb 8th!) for Assistant1.
It is also broken for Text Threads in Assitant2 (on macos and linux).

This should fix both.

Potentially related:
- https://github.com/zed-industries/zed/pull/29107

Release Notes:

- Fix for `ctrl-enter` shortcut in Assistant text threads incorrectly
opening inline assist instead of triggering Send.

Co-authored-by: Conrad Irwin <conrad@zed.dev>

This PR significantly improves the quality of the initial file search
that occurs when the model doesn't yet know the full path to a file it
needs to read/edit.

Previously, the assertions in file_search often failed on main as the
model attempted to guess full file paths. On this branch, it reliably
calls `find_path` (previously `path_search`) before reading files.

After getting the model to find paths first, I noticed it would try
using `grep` instead of `path_search`. This motivated renaming
`path_search` to `find_path` (continuing the analogy to unix commands)
and adding system prompt instructions about proper tool selection.

Note: I know the command is just called `find`, but that seemed too
general.

In my eval runs, the `file_search` example improved from 40% ± 10% to
98% ± 2%. The only assertion I'm seeing occasionally fail is "glob
starts with `**` or project". We can probably add some instructions in
that regard.

Release Notes:

- N/A