Release Notes:
- Added support for GPT-4o for Copilot Chat.

Release Notes:

- N/A

Release Notes:

- N/A

This commit adds a custom icon for Anthropic hosted models.


![CleanShot 2024-08-18 at 15 40
38@2x](https://github.com/user-attachments/assets/d467ccab-9628-4258-89fc-782e0d4a48d4)
![CleanShot 2024-08-18 at 15 40
34@2x](https://github.com/user-attachments/assets/7efaff9c-6a58-47ba-87ea-e0fe0586fedc)


- 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

I want to showcase Zed's performance via videos, and this seemed like a
good way to demonstrate it.


https://github.com/user-attachments/assets/f4a5fabc-efe7-4b48-9ba5-719882fdc856

Release Notes:

- On macOS, you can now set assign `performance.show_in_status_bar:
true` in your settings to show the time to the first window draw on
startup and then current FPS of the containing window's renderer.

---------

Co-authored-by: Max Brunsfeld <maxbrunsfeld@gmail.com>
Co-authored-by: Kirill Bulatov <kirill@zed.dev>
Co-authored-by: David Soria Parra <167242713+dsp-ant@users.noreply.github.com>
Co-authored-by: Danny Hua <danny.hua@hey.com>

Add language-specific subdirectory in example directory structure, since
that's the requisite structure - see `extensions/languages.md`

Release Notes:

- N/A

Release Notes:

- Fixed an issue where an extra newline was inserted after running a
`/file` command in the assistant.

When launching Zed from the CLI via `cargo run`, we'll always prompt
load templates from the repo.

This restores behavior that I reverted last night in #16403.

Also, I've improved the `script/prompts link/unlink` workflow for
overriding prompts of your production copy of Zed. Zed now detects when
the overrides directory is created or removed, and does the right thing.
You can link and unlink repeatedly without restarting Zed.

Release Notes:

- N/A

The original idea was for the keybinding to be within the description, but given it's already inline with the title, I figure we don't need this anymore—cleaning it up a bit!

--- 

Release Notes:

- N/A

This PR adds an icon button that appears as you hover over the step header, which allows users to visit the step view.

---

Release Notes:

- N/A

This PR reverts #16145 and subsequent changes.

This reverts commit a515442a365229155cde3de946e1b3eb244c0d36.

We still have issues with our approach to indentation in Python
unfortunately, but this feels like a safer equilibrium than where we
were.

Release Notes:

- Returned to our previous prompt for inline assist transformations,
since recent changes were introducing issues.

Release Notes:

- N/A

This PR adds the `is_staff` field to our LLM spans so that we can
distinguish between staff and non-staff traffic.

Release Notes:

- N/A

Release Notes:

- N/A

---------

Co-authored-by: Marshall <marshall@zed.dev>

Release Notes:

- N/A

Logged several of the detached tasks that before would silently fail if
the context server wasn't in compliance.

Release Notes:

- N/A

Also added some docs for our settings.

Release Notes:

- N/A

Just some super small padding and absolute-positioning tweaks. 

---

Release Notes:

- N/A

This PR adds a new `enabled_for_all` column to the `feature_flags` table
to allow enabling a feature flag for all users.

Release Notes:

- N/A

- [x] Put the slash command popover on the footer
- [x] Refine the popover (change it to a picker)
- [x] Add more options dropdown on the assistant's toolbar
- [x] Add quote selection button on the footer

---

Release Notes:

- N/A

---------

Co-authored-by: Piotr Osiewicz <24362066+osiewicz@users.noreply.github.com>
Co-authored-by: Nate Butler <iamnbutler@gmail.com>
Co-authored-by: Kirill Bulatov <mail4score@gmail.com>

This adds a configuration prompt when using the inline assist button in
the editor.

Release Notes:

- N/A

This PR fixes the writing of LLM rate limit events to Clickhouse.

We had a table in the table name: `llm_rate_limits` instead of
`llm_rate_limit_events`.

I also extracted a helper function to write to Clickhouse so we can use
it anywhere we need to.

Release Notes:

- N/A

Updates instances of the `MagicWand` icon to our more recent `Sparkle` /
`ZedAssistant` icon in places where we reference inline assist.

Before:

![CleanShot 2024-08-16 at 13 41
58@2x](https://github.com/user-attachments/assets/67af27a2-a09b-44bb-a8af-2bafcbbd9038)

After:
![CleanShot 2024-08-16 at 13 48
34@2x](https://github.com/user-attachments/assets/229ccc8e-8a93-44c1-abe0-7b6e22ca93e2)


Release Notes:

- Updated inline assist icon in the editor & terminal.

This PR reworks how we do checks for model names in the LLM service.

We now normalize the model names using the models defined in the
database.

Release Notes:

- N/A

Release Notes:

- N/A

Release Notes:

- N/A

Fixes:
- [x] an issue where directories would only match by prefix, causing
both a directory and a file to be matched if in the same directory
- [x] An issue where you could not continue a file completion when
selecting a directory, as `tab` on a file would always run the command.
This effectively disabled directory sub queries.
- [x] Inconsistent rendering of files and directories in the slash
command

Release Notes:

- N/A

---------

Co-authored-by: max <max@zed.dev>

Fixed the output format section of the content_prompt.hbs template
getting rendered away by handlebars. Also fixed a leftover hardcoded
"Rust" in the rewrite section snippet. (follow-up to #16333)

Release Notes:

- N/A

Release Notes:

- Added support for 8192 output tokens from Claude Sonnet 3.5
(https://x.com/alexalbert__/status/1812921642143900036)

Release Notes:

- N/A

Release Notes:

- N/A

Release Notes:

- N/A

Closes #16297

It seems that currently we can't draw custom title bar. I have checked
the `title_bar` crate, it seems to be `zed` only.

Before:

![Screenshot 2024-08-16
004350](https://github.com/user-attachments/assets/e11aa0bb-9d3e-47d5-b488-d3b8220158cc)

After:

![Screenshot 2024-08-16
004235](https://github.com/user-attachments/assets/028b4eb2-c878-4ea7-87e3-22817caefa00)


Release Notes:

- N/A

I focused on cases where we're inserting doc comments or annotations
above symbols.

I added 5 new examples to the content generation prompt, covering
various scenarios:

1. Inserting documentation for a Rust struct
2. Writing docstrings for a Python class
3. Adding comments to a TypeScript method
4. Adding a derive attribute to a Rust struct
5. Adding a decorator to a Python class

These examples demonstrate how to handle different languages and common
tasks like adding documentation, attributes, and decorators.

To improve context integration, I've made the following changes:

1. Added a `transform_context_range` that includes 3 lines before and
after the transform range
2. Introduced `rewrite_section_prefix` and `rewrite_section_suffix` to
provide more context around the section being rewritten
3. Updated the prompt template to include this additional context in a
separate code snippet

Release Notes:

- Reduced instances of over-generation when inserting docs or
annotations above a symbol.

If you submit an image with empty space above it and text below, it will
fail with this error:


![image](https://github.com/user-attachments/assets/a4a2265e-815f-48b5-b09e-e178fce82ef7)

Now instead it fails with an error about needing a message.

<img width="640" alt="image"
src="https://github.com/user-attachments/assets/72b267eb-b288-40a5-a829-750121ff16cc">

It will however work with text above and empty text below the image now.

Release Notes:

- Improved conformance with Anthropic Images in Chat Completions API

Release Notes:

- Adds support for Prompt Caching in Anthropic. For models that support
it this can dramatically lower cost while improving performance.

* Improve the tab title: give it an icon, and indicate the step index.
* Display the line number ranges that the symbols resolve to.
* Don't open duplicate tabs for the same step

Release Notes:

- N/A

This makes it easier to use the outline view to navigate `context.rs`,
and reduces the indentation level of the tests.

Release Notes:

- N/A

Now that there's a dedicated, user-facing view for each workflow step,
we don't need the inspector functionality. This PR also cleans up some
naming around workflow steps and step resolutions.

Release Notes:

- N/A

Replaces #16273.

Release Notes:

- repl: Fixed scaling of stdout/stderr line heights

---------

Co-authored-by: Mikayla <mikayla@zed.dev>
Co-authored-by: Nate Butler <iamnbutler@gmail.com>

Release Notes:

- N/A

This PR improves the empty state of the prompt library.

The right-hand side of the library is now dedicated to an empty state
that guides the user to create their first prompt.

Additionally, the message in the picker now reads "No prompts." when
there are no prompts.

#### No prompts

<img width="1136" alt="Screenshot 2024-08-15 at 6 20 26 PM"
src="https://github.com/user-attachments/assets/f9af2b5d-c4d3-4e2c-9ba2-f17e89f19bb7">

#### No prompts that match the search

<img width="1136" alt="Screenshot 2024-08-15 at 5 55 07 PM"
src="https://github.com/user-attachments/assets/2cd4ff9b-958d-4bd0-90d3-dca62b1a91a0">

Release Notes:

- N/A

This PR restores the ability to toggle the model selector via a keybind
after it was lost in #15693.

Release Notes:

- Restored the ability to toggle the model selector in the Assistant via
a keybinding (Preview only).

You can now click on a step header (the words `Step 3`, etc) to open a
new tab containing a dedicated view for the resolution of that step.
This view looks similar to a context editor, and has sections for the
step input, the streaming tool output, and the interpreted results.

Hitting `cmd-enter` in this view re-resolves the step.


https://github.com/user-attachments/assets/64d82cdb-e70f-4204-8697-b30df5a645d5



Release Notes:

- N/A

---------

Co-authored-by: Nathan <nathan@zed.dev>