Now we only auto-retry if burn mode is enabled. We also show a "Retry"
button (so you don't have to type "continue") if you think that's the
right remedy, and additionally we show a "Retry and Enable Burn Mode"
button if you don't have it enabled.
<img width="484" height="260" alt="Screenshot 2025-07-17 at 6 25 27 PM"
src="https://github.com/user-attachments/assets/dc5bf1f6-8b11-4041-87aa-4f37c95ea9f0"
/>
<img width="478" height="307" alt="Screenshot 2025-07-17 at 6 22 36 PM"
src="https://github.com/user-attachments/assets/1ed6578a-1696-449d-96d1-e447d11959fa"
/>
Release Notes:
- Only auto-retry Agent requests when Burn Mode is enabled
This tool needs more polishing before being generally available.
Release Notes:
- agent: Disabled `project_notifications` tool by default for the time
being
This change improves user/agent collaborative editing.
When the user edits files that are used by the agent, the
`project_notification` tool now pushes *diffs* of the changes, not just
file names. This helps the agent to stay up to date without needing to
re-read files.
Release Notes:
- Improved user/agent collaborative editing: agent now receives diffs of
user edits
In #33275 I was very conservative about when to retry when there are
errors in language completions in the Agent panel.
Now we retry in more scenarios (e.g. HTTP 5xx and 4xx errors that aren't
in the specific list of ones that we handle differently, such as 429s),
and also we show a notification if the thread halts for any reason.
<img width="441" height="68" alt="Screenshot 2025-07-15 at 12 51 30 PM"
src="https://github.com/user-attachments/assets/433775d0-a8b2-403d-9427-1e296d164980"
/>
<img width="482" height="322" alt="Screenshot 2025-07-15 at 12 44 15 PM"
src="https://github.com/user-attachments/assets/5a508224-0fe0-4d34-9768-25d95873eab8"
/>
Release Notes:
- Automatic retry for more Agent errors
- Whenever the Agent stops, play a sound (if configured) and show a
notification (if configured) if the Zed window was in the background.
This introduces a new field `thinking_allowed` on `LanguageModelRequest`
which lets us control whether thinking should be enabled if the model
supports it.
We permit thinking in the Inline Assistant, Edit File tool and the Git
Commit message generator, this should make generation faster when using
a thinking model, e.g. `claude-sonnet-4-thinking`
Release Notes:
- N/A
Previously, we sent notifications repeatedly until the agent read a
file, which was often inefficient. With this change, we now send a
notification only once (unless the files are modified again, in which
case we'll send another notification).
Release Notes:
- N/A
This commit introduces the `project_notifications` tool, which
proactively pushes notifications to the agent.
Unlike other tools, `Thread` automatically invokes this tool on every
turn, even when the LLM doesn't ask for it. When notifications are
available, the tool use and results are inserted into the thread,
simulating an LLM tool call.
As with other tools, users can disable `project_notifications` in
Profiles if they do not want them.
Currently, the tool only notifies users about stale files: that is,
files that have been edited by the user while the agent is also working
on them. In the future, notifications may be expanded to include
compiler diagnostics, long-running processes, and more.
Release Notes:
- Added `project_notifications` tool
Closes#33792
Follow up to #33237 - Turns out my fix for this was not correct
Release Notes:
- agent: Fixed an issue where tools would not work when two MCP servers
provided a tool with the same name
* Updates to `zed_llm_client-0.8.5` which adds support for `retry_after`
when anthropic provides it.
* Distinguishes upstream provider errors and rate limits from errors
that originate from zed's servers
* Moves `LanguageModelCompletionError::BadInputJson` to
`LanguageModelCompletionEvent::ToolUseJsonParseError`. While arguably
this is an error case, the logic in thread is cleaner with this move.
There is also precedent for inclusion of errors in the event type -
`CompletionRequestStatus::Failed` is how cloud errors arrive.
* Updates `PROVIDER_ID` / `PROVIDER_NAME` constants to use proper types
instead of `&str`, since they can be constructed in a const fashion.
* Removes use of `CLIENT_SUPPORTS_EXA_WEB_SEARCH_PROVIDER_HEADER_NAME`
as the server no longer reads this header and just defaults to that
behavior.
Release notes for this is covered by #33275
Release Notes:
- N/A
---------
Co-authored-by: Richard Feldman <oss@rtfeldman.com>
Co-authored-by: Richard <richard@zed.dev>
Closes https://github.com/zed-industries/zed/issues/33519
Release Notes:
- agent: Improved support for explicitly disabling individual tools when
`enable_all_context_servers` is true. (e.g. enable all tools except
XYZ).
Seeing this come up in our server logs when sending requests to
Anthropic: `final assistant content cannot end with trailing
whitespace`.
Release Notes:
- agent: Fixed an issue where Anthropic requests would sometimes fail
because of malformed assistant messages
<img width="484" alt="Screenshot 2025-06-25 at 2 26 16 PM"
src="https://github.com/user-attachments/assets/340f15d7-b115-4895-bae8-b12a915bfda1"
/>
<img width="460" alt="Screenshot 2025-06-25 at 2 26 08 PM"
src="https://github.com/user-attachments/assets/6e587a38-d542-405f-809f-402e87520538"
/>
Now we:
* Automatically retry up to 3 times on upstream Overloaded or 500 errors
(currently for Anthropic only; will add others in future PRs)
* Also automatically retry on rate limit errors (using the provided
duration to wait, if we were given one)
* Give you a notification if you don't have Zed open and we stopped the
thread because of an error
Still todo in future PRs:
* Update collab to report Overloaded and 500 errors differently if
collab itself is passing through an upstream error vs not (currently we
report these as "Zed's API is overloaded" when actually it's the
upstream one!)
* Updating providers other than Anthropic to categorize their errors so
that they benefit from this
* Expanding graceful error handling/retry to other things besides
Overloaded and 500 errors (e.g. connection reset)
Release Notes:
- Automatically retry in Agent Panel instead of erroring out when an
upstream AI API is overloaded or 500s
- Show a notification when an Agent thread errors out and Zed is not the
active window
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>
