While working on retries, I discovered some opportunities to reduce
cloning of message segments. These segments have full `String`s (not
`SharedString`s), so cloning them means copying cloning all the bytes of
all the strings in the message, which would be nice to avoid!
Release Notes:
- N/A
The agent now checks if a tool is enabled in the current profile before
calling it. Previously, the agent could still call disabled tools, which
commonly happened after switching profiles in the middle of a thread.
Release Notes:
- Fixed a bug where the agent could use disabled tools sometimes
cc @osyvokon
We were seeing a bunch of errors in our backend when people were using
Claude models with thinking enabled.
In the logs we would see
> an error occurred while interacting with the Anthropic API:
invalid_request_error: messages.x.content.0.type: Expected `thinking` or
`redacted_thinking`, but found `text`. When `thinking` is enabled, a
final `assistant` message must start with a thinking block (preceeding
the lastmost set of `tool_use` and `tool_result` blocks). We recommend
you include thinking blocks from previous turns. To avoid this
requirement, disable `thinking`. Please consult our documentation at
https://docs.anthropic.com/en/docs/build-with-claude/extended-thinking
However, this issue did not occur frequently and was not easily
reproducible. Turns out it was triggered by us not correctly handling
[Redacted Thinking
Blocks](https://docs.anthropic.com/en/docs/build-with-claude/extended-thinking#thinking-redaction).
I could constantly reproduce this issue by including this magic string:
`ANTHROPIC_MAGIC_STRING_TRIGGER_REDACTED_THINKING_46C9A13E193C177646C7398A98432ECCCE4C1253D5E2D82641AC0E52CC2876CB
` in the request, which forces `claude-3-7-sonnet` to emit redacted
thinking blocks (confusingly the magic string does not seem to be
working for `claude-sonnet-4`). As soon as we hit a tool call Anthropic
would return an error.
Thanks to @osyvokon for pointing me in the right direction 😄!
Release Notes:
- agent: Fixed an issue where Anthropic models would sometimes return an
error when thinking was enabled
This breaks a transitive dependency of `agent` on UI crates. I've also
found and eliminated some dead code in assistant_context_editor.
Release Notes:
- N/A
This PR moves the UI-dependent logic in the `agent` crate into its own
crate, `agent_ui`. The remaining `agent` crate no longer depends on
`editor`, `picker`, `ui`, `workspace`, etc.
This has compile time benefits, but the main motivation is to isolate
our core agentic logic, so that we can make agents more
pluggable/configurable.
Release Notes:
- N/A
Removed an additional label from the modal empty state as I figured we
don't need it, given we already have a version of the description in
place for when the extension itself doesn't return any. So, ultimately,
having both the label and the description was redundant.
Release Notes:
- N/A
This PR is in preparation for doing automatic retries for certain
errors, e.g. Overloaded. It doesn't change behavior yet (aside from some
granularity of error messages shown to the user), but rather mostly
changes some error handling to be exhaustive enum matches instead of
`anyhow` downcasts, and leaves some comments for where the behavior
change will be in a future PR.
Release Notes:
- N/A
CC: @danilo-leal Do you have thoughts on this? I found myself typing
chat messages after a long thread and then deciding I would be better
served by restarting from a summary -- and then "poof" the contents of
my chat box was lost.
Release Notes:
- agent: "New From Summary" now preserves any unsent content in the chat
box.
Previously, if editing a long previous user message in the thread, you'd
have a double scroll situation because the editor used in that case had
its max number of lines capped. To solve that, I made the `max_lines` in
the editor `AutoHeight` mode optional, allowing me to not pass any
arbitrary number to the previous user message editor, and ultimately,
solving the double scroll problem by not having any scroll at all.
Release Notes:
- agent: Fixed double scroll that happened when editing a long previous
user message.
@ConradIrwin adding you as a reviewer as I'm touching editor code
here... want to be careful. :)
Closes#31903
Release Notes:
- agent: Fix an issue where an error would occur when MCP servers
specified tools with the same name
---------
Co-authored-by: Ben Brandt <benjamin.j.brandt@gmail.com>
- [x] Show disabled MCP servers in the list so you can enable them again
- [x] If MCP is not present in the settings, add it
Closes #ISSUE
Release Notes:
- agent: Allow to enable/disable context servers permanently in the
agent configuration view
---------
Co-authored-by: Danilo Leal <daniloleal09@gmail.com>
Having `Thread::last_usage` as an override of the initially fetched
usage could cause the initial usage to be displayed when the current
thread is empty or in text threads. Fix is to just store last usage info
in `UserStore` and not have these overrides
Release Notes:
- Agent: Fixed request usage display to always include the most recently
known usage - there were some cases where it would show the initially
requested usage.
Removing it for two reasons:
1. We need a better implementation that doesn't hurt caching and doesn't
distracts the agent too much (see
https://github.com/zed-industries/zed/pull/32876 for more context)
2. Current insertion point of notifications doesn't play well with
Claude Thinking models (see
https://github.com/zed-industries/zed/issues/33000#issuecomment-2991709484)
I think we should get this code back in a form of a tool. But for now,
I'm dropping it to resolve recent issues.
Closes#33000
Release Notes:
- N/A
Follow up to https://github.com/zed-industries/zed/pull/32765.
This PR creates a slot for the `message_editor::create_editor` to allow
using different values for min and max lines. In practice, the panel's
main editor now has a minimum of 4 lines, whereas the previous message
editor has just one. This makes the layout shift when clicking on a
previous message to edit it much smaller.
Release Notes:
- agent: Improved layout shift when clicking to edit a previous sent
message.
Just a tiny, one-line change to avoid the "Waiting for Confirmation"
animated label pushing the "allow" buttons to the side.
Release Notes:
- agent: Fixed layout shift in "waiting for confirmation" state in the
terminal card.
Previously, you could only expand the provider item in the agent panel
settings view by clicking on the little chevron icon button. Now, you
can click on the whole title area (minus the button, when present) to do
that. Just that little bit more convenient to interact with it.
Release Notes:
- N/A
Still a work in progress! Todos before merging:
- [x] Allow to delete (not just turn off) an MCP server from the panel's
settings view
- [x] Also uninstall the extension upon deleting the server (check if
the extension just provides MCPs)
- [x] Resolve repository URL again
- [x] Add a button to open the configuration modal from the panel's
settings view
- [x] Improve modal UX to install and configure a non-extension MCP
Release Notes:
- N/A
---------
Co-authored-by: Bennet Bo Fenner <bennetbo@gmx.de>
Co-authored-by: Ben Brandt <benjamin.j.brandt@gmail.com>
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
This is a follow up to my original attempt
https://github.com/zed-industries/zed/pull/30878 and to the PR that
eventually reverted parts of it because it broke stuff
https://github.com/zed-industries/zed/pull/31295. This new approach
attaches the `scroll_to_bottom` feature to the `chat` function, which is
triggered when the `Chat` action is dispatched by the "send" icon
buttons. With that, and from my testing, the thread doesn't forcefully
scroll as new messages are added, which was the regression I had
introduced.
Release Notes:
- agent: The panel nows scrolls to the bottom after submitting a new
message, allowing to see it more easily.
- [x] foreground highlights
- [x] background highlights
- [x] advertise support in DAP capabilities
Closes#31372
Release Notes:
- Debugger Beta: added basic support for highlighting in the console
based on ANSI escape codes.
When the user edits one of the tracked files, we used to notify the
agent by inserting a user message at the end of the thread. This was
causing a few problems:
- The agent would stop doing its work and start reading changed files
- The agent would write something like, "Thank you for letting me know
about these changed files."
This fix contains two parts:
1. Changing the prompt to indicate this is a service message
2. Moving the message higher in the conversation thread
This works, but it slightly hurts caching.
We may consider making these notification messages stick in history,
trading context tokens count for the cache.
This might be related to #30906
Release Notes:
- N/A
---------
Co-authored-by: Marshall Bowers <git@maxdeviant.com>
This changes the way context servers are organised. We now store a
`source` which indicates if the MCP server is configured manually or
managed by an extension.
Release Notes:
- N/A
---------
Co-authored-by: Ben Brandt <benjamin.j.brandt@gmail.com>
Previously, you could only accept and reject all changes from a specific
file by checking that file out on a tab. Now, you can do that via the
message editor changes summary bar. The buttons appear as you hover over
the file item in the accordion.
Here's what it looks like:
<img
src="https://github.com/user-attachments/assets/8c0843d3-9bf1-4588-8b42-4cd8d0798a68"
width="500" />
Release Notes:
- agent: Enable accepting and rejecting individual file changes from
message editor.
* Adds `min_lines` to `EditorMode::AutoHeight` and use `min_lines: 4` in
agent message editor. This makes it so that clicks in the blank space
below the first line of the editor also focus it, instead of needing to
click the very first line.
* Removes the div wrapping the editor, as it was only there to set
`min_h_16()`. This also tightens up the min space given to the editor -
before it was not evenly dividing the number of lines.
* Further tightens up vertical spacing by using `gap_1` instead of
`gap_4` between editor and controls below
At 4 line min height (after on the left, before on the right):
At 5 lines, one more than min height (after on the left, before on the
right):
Release Notes:
- Agent: Fixed clicking to focus the message editor to also work for
clicks below the last line.
Some MCP servers expose tools that take absolute paths as arguments. To
interact with these, the agent needs to know the absolute path to the
project directories, not just their names. This PR changes the system
prompt to include the full path to each worktree, and updates some tool
descriptions to reflect this.
Todo:
* [x] Run evals, make sure assistant still understand how to specify
paths for tools, now that we include abs paths in the system prompt.
Release Notes:
- Improved the agent's ability to use MPC tools that require absolute
paths to files and directories in the project.
---------
Co-authored-by: Ben Brandt <benjamin.j.brandt@gmail.com>
Previously, upon getting close to reaching the context window, we'd just
suggest creating a new thread using the summary of the current one. Now,
we also suggest turning burn mode on as an alternative action to solve
the context window problem.
Release Notes:
- agent: Added a suggestion to turn burn mode on when getting close to
the context window limit.
What motivated me to refactor this component was the fact that I wanted
a new variant to allow having _two CTAs_ instead of just one. This
variant should work with either a single or multiline description. But,
given we were using a `Callout::single_line` and `Callout::multi_line`
API, I'd then need to have both `Callout::single_line_one_button` and
`Callout::single_line_two_buttons` type of variants, which just points
to a combinatorial problem.
With this refactor, the Callout now follows the same structure of the
Banner component, where it's all `Callout::new` and every method is
passed as if they were props in a React component, allowing for a more
flexible design where you can customize button styles. Also made it
slightly more robust for wrapping and removed the top border as that
should be defined by the place it is being used in.
Release Notes:
- N/A
Consolidates configuration error handling by moving the error type and
logic from assistant_context_editor to language_model::registry.
The registry now provides a single method to check for configuration
errors, making the error handling more consistent across the agent panel
and context editor.
This also now checks if the issue is that we don't have any providers,
or if we just can't find the model.
Previously, an incorrect model name showed up as having no providers,
which is very confusing.
Release Notes:
- N/A
I think we mistakenly added an early return for the review multibuffer
button if `has_pending_edit_tool_uses` is true. It is totally fine _to
access_ the review multibuffer while that's happening. It's another
thing to _accept and reject_ changes while they're still ongoing!
Release Notes:
- agent: Fixed access to the review multibuffer from the agent panel.
This is reverting a change from #32071 which caused agent following to
stop after the file was edited.
This will reintroduce the behavior that the keyboard shortcuts don't
work until the model is done generating, but we will revisit that
afterwards.
Co-authored-by: Bennet Bo Fenner <bennetbo@gmx.de>
Release Notes:
- agent: Fix a regression in agent following behavior after file edits
Co-authored-by: Bennet Bo Fenner <bennetbo@gmx.de>
When editing a message, cancel any in-progress completion before
starting a new request to prevent overlapping model responses.
Release Notes:
- agent: Fixed previous completion not cancelling when editing a
previous message
This PR also introduces `Context::processor`, a sibling of
`Context::listener` that takes a strong pointer to entity and allows for
a return result.
Release Notes:
- N/A
Co-authored-by: Mikayla <mikayla@zed.dev>
We were previously displaying this modal in all open Zed windows if
triggered. That was a bit annoying because I had to go to each window
individually to close it, which meant doing it multiple times. 😅
Release Notes:
- agent: Fixed the MCP configuration modal to show only in the active
window.
Previously, upon hitting the "Continue" button to restart an interrupted
thread due to consecutive tool calls reaching its limit, you wouldn't
see the loading dots and the UI would be a weird state. This PR improves
when these loading dots actually show up, including in their conditional
a check for `message.is_hidden`.
Also took advantage of the opportunity to quickly organize some of these
variables. The `render_message` function could potentially be chopped up
in more smaller pieces. Lots of things going on here.
Release Notes:
- N/A
Mostly a small tweak making sure that the indicator tooltip hit area is
bigger and the loading state is clearer (not using an indicator
anymore). Way more little improvement opportunities in this component to
do, though.
Release Notes:
- N/A
- Improved colors
- Blank out diff hunk gutter highlights in conflict regions
- Paint conflict marker highlights all the way to the gutter
Release Notes:
- Improved the highlighting of merge conflict markers in editors.
---------
Co-authored-by: Marshall Bowers <git@maxdeviant.com>
Co-authored-by: Cole Miller <cole@zed.dev>
Richard Feldman