When the agent panel's thread is empty, the toolbar no longer shows the
labeled agent dropdown on the far left. Instead, it uses the same layout
as an active thread: a stable plus icon button on the far right, and the
left slot displays a muted "New {agent} Thread" placeholder title —
matching the sidebar's draft thread item. As soon as you type into the
message editor, the title shows your prompt text instead, reusing the
sidebar's draft label truncation logic.
Release Notes:
- Improved the agent panel's empty-state toolbar to show a "New {agent}
Thread" placeholder title (or your draft prompt as you type), with a
stable new-thread button on the right.
We recently changed this given some new models (e.g., Fable) don't allow
turning thinking off. In those cases, we are not rendering the split
button anymore, but we should still display the thinking icon, so they
look a bit more consistent.
Release Notes:
- N/A
Sometimes, landing in the archive view at first, particularly after
importing ACP threads, can be confusing as there's not an immediately
available "create new thread" button users can click on.
Release Notes:
- N/A
On transparent or blurred window backgrounds, several agent panel
surfaces and
the multibuffer header rendered drop shadows and fade gradients that
have no
opaque surface to blend into, so they showed up as dark halos or colored
patches:
- agent message boxes and the activity bar (drop shadows)
- diff-hunk Reject/Keep controls (drop shadow)
- the diff review pane (double-painted `editor_background`)
- agent thread-list rows, the conversation title edit affordance, and
sidebar
project headers (fade gradient)
- the multibuffer buffer header (`editor_subheader_background` + sticky
shadow)
These are skipped when `window_background_appearance` isn't `Opaque`.
Opaque
windows are unchanged; on transparent windows the elements stay
delineated by
their borders and truncate text with an ellipsis instead of fading.
## Screenshots
Before:
<img width="1920" height="1200" alt="Screenshot 2026-06-09 at 3 26 26
PM"
src="https://github.com/user-attachments/assets/7dc9c76c-7de9-4c50-8719-05957d091706"
/>
After:
<img width="1728" height="1117" alt="Screenshot 2026-06-09 at 3 26 29
PM"
src="https://github.com/user-attachments/assets/889a53ad-9f11-41b9-9f51-ffcbd5c37821"
/>
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 adheres to Zed's UI standards
([UX/UI](https://github.com/zed-industries/zed/blob/main/CONTRIBUTING.md#uiux-checklist)
and
[icon](https://github.com/zed-industries/zed/blob/main/crates/icons/README.md)
guidelines)
- [x] Tests cover the new/changed behavior
- [x] Performance impact has been considered and is acceptable
Release Notes:
- Fixed dark shadow and gradient artifacts in the agent panel and
multibuffer headers when using a transparent or blurred window
background
Fixes the agent panel silently reverting all pending subagent file
changes when an earlier message is edited and regenerated.
`ThreadView::regenerate` decides whether to auto-keep pending edits from
earlier prompts (behavior introduced in #43347) by scanning the parent
thread's entries for diffs. Subagent edits never appear there — they are
only forwarded to the parent's action log via the linked-log mechanism —
so the auto-keep step was skipped and `rewind`'s unscoped
`reject_all_edits` reverted all of them on disk, without confirmation.
The fix treats any earlier subagent tool call as potentially having
edits, so they get auto-kept just like direct edits from earlier
prompts. Keeping all edits is a no-op when the subagent made none. Edits
produced by the prompt being regenerated are still auto-rejected,
consistent with existing behavior.
Also adds a regression test
(`test_regenerate_keeps_pending_subagent_edits`) that reproduces the
full flow — subagent edit forwarded through a linked action log,
follow-up prompt, regenerate — and fails with the exact reported data
loss without the fix.
Closes AI-386
Closes https://github.com/zed-industries/zed/issues/58932
Release Notes:
- Fixed pending subagent file changes being discarded when editing an
earlier message in the agent panel.
Claude Fable 5 always thinks and cannot honor a request with thinking
disabled, but the cloud models listing gives clients no way to tell it
apart from models where thinking is optional (e.g. Claude Opus 4.6):
both report `supports_thinking: true` plus the same adaptive effort
levels. As a result, the agent panel shows a thinking toggle for Fable
even though turning it off isn't actually supported.
zed-industries/cloud#2789 adds a `supports_disabling_thinking` field to
the models listing. This PR mirrors it through
`cloud_llm_client::LanguageModel` (serde-defaulted to `false`, so a
server without the field is treated as "don't claim thinking can be
turned off") and exposes it as
`LanguageModel::supports_disabling_thinking()`, forwarded from the
listing by `CloudLanguageModel`. The agent panel now hides the thinking
toggle for models that report `false`, showing only the effort selector.
The trait default is `true`: every non-cloud provider in the tree treats
thinking as toggleable today, and only the cloud listing knows about
always-thinking models.
Draft until zed-industries/cloud#2789 lands and deploys.
Release Notes:
- Fixed the agent panel offering a thinking toggle for models that
cannot run with thinking disabled.
Stop the Zed cloud LLM provider from funneling completion failures
through anyhow::Error and collapsing them into
LanguageModelCompletionError::Other (which surfaced as a generic
"Request failed.").
- perform_llm_completion now returns a typed
LanguageModelCompletionError, mapping each failure to its real variant
(SerializeRequest, HttpSend, ApiReadResponseError, and ApiError-derived
status variants).
- response_lines yields a typed ResponseStreamError so mid-stream read/
deserialize failures become ApiReadResponseError/DeserializeResponse
without a runtime downcast.
- Add a first-class PaymentRequired variant for HTTP 402 and remove the
now-dead PaymentRequiredError struct and its anyhow downcast checks.
Self-Review Checklist:
- [ ] I've reviewed my own diff for quality, security, and reliability
- [ ] Unsafe blocks (if any) have justifying comments
- [ ] The content adheres to Zed's UI standards
([UX/UI](https://github.com/zed-industries/zed/blob/main/CONTRIBUTING.md#uiux-checklist)
and
[icon](https://github.com/zed-industries/zed/blob/main/crates/icons/README.md)
guidelines)
- [ ] Tests cover the new/changed behavior
- [ ] Performance impact has been considered and is acceptable
Closes #ISSUE
Release Notes:
- N/A
---------
Co-authored-by: Piotr Osiewicz <24362066+osiewicz@users.noreply.github.com>
Co-authored-by: zed-zippy[bot] <234243425+zed-zippy[bot]@users.noreply.github.com>
Running `/compact` rendered a `/compact` user-message bubble during the
live session, but that text is never sent to the model as an ordinary
user turn — it triggers a built-in compaction that produces its own
"Context compacted" entry. Showing the bubble was misleading (it implied
the model received `/compact`), and it was also inconsistent: after a
reload the bubble vanished, since the persisted thread only carries an
empty marker. This changes the direction so native slash commands are
never echoed as user messages at all, live or after reload.
`AcpThread` gains a `send_command` path that runs the turn (so the agent
still receives and handles `/compact`) without pushing a user-message
entry or capturing a git checkpoint. In the UI, `leading_native_command`
now matches a native command whether or not it has trailing text, so
both `/compact` and `/compact do X` route through the command path; the
queued-message path detects native commands too, so a `/compact` typed
while a turn is generating behaves the same. MCP/ACP commands are
unaffected and still render as normal user messages, since their text is
a real argument the agent consumes.
Release Notes:
- N/A
---------
Co-authored-by: Bennet Bo Fenner <bennetbo@gmx.de>
Removes the `handoff` feature flag entirely and un-gates context
compaction so auto-compaction and the `/compact` command are available
to everyone. The `HandoffFeatureFlag` definition is deleted, and every
flag check is removed: auto-compaction always runs in the agent turn
loop (still governed by the `agent.auto_compact` setting and the model's
context window size), the `/compact` slash command is always registered
and routed to manual compaction, the token-limit callout always defers
to auto-compaction when the window is large enough, and the Auto Compact
settings always appear in the settings UI.
Merging this is the switch that ships the feature; until then it stays
stacked behind the telemetry and retry-fix PRs.
Release Notes:
- Added auto-compaction and /compact to Zed Agent
---------
Co-authored-by: Bennet Bo Fenner <bennetbo@gmx.de>
This PR changes how base texts are managed by the `buffer_diff` crate,
to enable keeping two diff entities alive that share the same base text
buffer entity. Previously, each diff owned its own base text buffer and
edited it when calling `BufferDiff::set_snapshot`, so the only way to
reuse the same base text between two diffs was to have two independent
buffers for it, which is pretty inefficient.
After this PR, each diff still has a base text buffer, but
`set_snapshot` doesn't edit it. Instead, that responsibility moves into
the caller. For updating the base text buffer, this PR also introduces a
new pair of APIs, `Buffer::snapshot_with_edits` and
`Buffer::fast_forward`, which allow us to move the parsing of the new
base text into the background and then install the new syntax tree
synchronously on the foreground.
The git store uses the low-level APIs `set_snapshot` and `fast_forward`
directly, and manages the head text and index text buffers itself
(garbage-collecting them when they're no longer needed); this enables
adding an `open_staged_diff` API which returns a diff between the
managed index buffer and the managed head buffer (the latter is also
used for the uncommitted diff's base text). Other downstreams don't need
to reuse a base text buffer, and those have been migrated to use the
high-level `set_base_text` API, which now calls `set_snapshot` and
`fast_forward` internally, with a guard to prevent concurrent updates.
Another change worthy of note is that we now always diff the old base
text with the new base text to create `snapshot_with_edits`.
There are also some incidental bug fixes:
- Fixed an issue where a dangling weak unstaged diff could stick around
in the git store forever
- Restored the `IndexMatchesHead` optimization that had become
inoperative in the remote case
- Fixed a crash in the multibuffer due to the handling of
`BufferDiffEvent::LanguageChanged`, which could cause the multibuffer to
have transforms that were inconsistent with the diff base text.
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
Closes ZED-81P
Release Notes:
- Fixed a rare crash that could occur while using the uncommitted diff.
---------
Co-authored-by: Ben Kunkle <ben@zed.dev>
Co-authored-by: Anthony Eid <hello@anthonyeid.me>
Resolves a leftover TODO from the Claude Fable 5 data-retention work:
the "Learn More" button in the data-retention consent callout pointed at
a `#link-tbd` placeholder, so it did nothing. It now opens Anthropic's
data retention practices support article.
Release Notes:
- N/A
<img width="325" height="201" alt="Screenshot 2026-06-09 at 1 38 32 PM"
src="https://github.com/user-attachments/assets/a6518073-1e17-41ff-a8fc-cb279fcd4436"
/>
Adds support for Anthropic's Claude Fable 5 model when using your own
Anthropic API key. Because Fable 5 cannot be offered under Zero Data
Retention (Anthropic retains inference logs for 30 days), this gates the
model behind an explicit data-retention consent: a new
telemetry.anthropic_retention setting (default off, surfaced in the
Privacy section of the settings UI), and a hard, non-retryable check in
the cloud completion path that raises a typed error when consent is
missing.
When Fable 5 declines a request, it transparently falls back to Claude
Opus 4.8 (matching Anthropic's server-side behavior), and the agent
panel shows a callout for the consent error with "Switch to Opus 4.8" /
"Accept" actions that resume the failed turn so the user's message
continues without retyping.
Closes AI-382
Release Notes:
- Add Claude Fable 5 to Anthropic BYOK
---------
Co-authored-by: Mikayla Maki <mikayla@zed.dev>
Here are the things I tried to tackle on this PR:
- Make the compaction call stand out a bit more from other regular tool
calls
- Make text size of the compaction's markdown output be consistent with
the thread body text
- Don't show regular thread loading spinner while compaction is in
progress, given that has its own spinner
- Add a different icon than scissors for compaction and add it to the
autocomplete menu so its consistent w/ skills items
<img width="600" alt="Screenshot 2026-06-09 at 10 57@2x"
src="https://github.com/user-attachments/assets/5c3d25af-aa49-42e1-b6b6-c3f95c664456"
/>
Release Notes:
- N/A
Makes it so that we show "Compaction cancelled" when the user interrupts
generation.
Also fixes another small issue where the chevron of the expanded state
would not reflect if it is expanded/collapsed while there is no summary
yet.
Release Notes:
- N/A
Adds two new agent settings nested under `auto_compact`, `enabled` and
`threshold`, which control automatic compaction of the agent's context
window as part of the handoff feature. Both surface in the settings UI
under Agent Configuration, gated behind the `handoff` feature flag so
they only appear for users on that flag.
The `threshold` accepts three forms: a percentage string ending in `%`
(e.g. `"80%"` or `"95.5%"`) measured against the model's context window,
a positive integer to compact after that many tokens have been used, or
a negative integer to compact once that many tokens remain in the
window. `0` and bare non-integer numbers are rejected. It deserializes
from either a JSON string or integer and resolves to a typed enum,
falling back to the `"80%"` default (with a logged warning) when the
configured value is invalid. In the settings UI the threshold is a
free-form text field so all three forms can be entered.
Release Notes:
- N/A
---------
Co-authored-by: Bennet Bo Fenner <bennetbo@gmx.de>
<img width="851" height="315" alt="Screenshot 2026-06-09 at 2 15 51 AM"
src="https://github.com/user-attachments/assets/958f2d2f-db7d-4afb-b4b3-ed11f36b00e7"
/>
<img width="644" height="260" alt="Screenshot 2026-06-09 at 2 16 04 AM"
src="https://github.com/user-attachments/assets/e6a74c6b-aba5-4fbb-991c-25842ced5832"
/>
<img width="619" height="128" alt="Screenshot 2026-06-09 at 2 18 08 AM"
src="https://github.com/user-attachments/assets/ba7fa303-852b-4a17-b8df-ea5bd4df7c11"
/>
Adds an always-available `/compact` slash command to Zed's native agent
that forces a summary-based context compaction of the current
conversation, regardless of token usage. This reuses the agent's
existing compaction logic (always the summary strategy, never
provider-native), bypassing the automatic-compaction token threshold and
minimum-context-window guard since the user explicitly asked to compact.
The command lives entirely in `NativeAgent`/`NativeAgentConnection`, so
external (ACP) agents are untouched and keep their own `/compact`
implementations.
The command is gated behind the `handoff` feature flag, matching the
gate on automatic compaction, so it's only advertised and dispatched
when that flag is enabled. When the flag is off, typing `/compact` is
treated as an ordinary prompt.
Because the agent panel always renders the typed `/compact` as a user
message, the manual compaction records a matching zero-content user
message in the model thread (skipped when building model requests) so
that rewinding/truncating that message works instead of erroring, while
keeping the command itself out of the model's context.
The slash-command popup now groups commands into separate sections by
source — "Commands" (built-in, e.g. `/compact`), "MCP Server Commands",
and "ACP Agent Commands" — so same-named commands from different sources
show up as distinguishable duplicates. The source category travels on
each command's ACP `_meta`.
Release Notes:
- N/A
---------
Co-authored-by: Bennet Bo Fenner <bennetbo@gmx.de>
This PR tackles how we communicate errors/warnings relative to skills.
It touches three major surfaces: callouts in the thread view, menu items
in the completion menu, and settings UI. These are all the places where
we display something to tell the user a skill might have a problem.
In the settings UI, we now clamp the skill description to five lines.
And if there's a warning, we show the warning icon and the description
in a tooltip when hovering it:
<img width="600" alt="Screenshot 2026-06-08 at 10 51@2x"
src="https://github.com/user-attachments/assets/1a1233b0-c24a-4082-9fe6-2ab1d00ba9fd"
/>
In the thread view, we display callouts with the warnings. I simplified
the long-description one specifically given we can click on each skill
item right there, so no need for a "manage global skills" button or
descriptions in each item:
<img width="600" alt="Screenshot 2026-06-08 at 10 52@2x"
src="https://github.com/user-attachments/assets/4b9aad23-7362-40cd-8ab5-6dfceb46badd"
/>
In the code completion menu, I removed the icon that appeared at the far
right and instead added the ability for it to render a colored warning
icon instead of the icon it'd already display in the left; I think this
simplifies it nicely:
<img width="350" alt="Screenshot 2026-06-08 at 10 53@2x"
src="https://github.com/user-attachments/assets/8d0c731a-31a0-4d30-abab-1eb40f61031e"
/>
Release Notes:
- Agent: Improved how we communicate problems relative to skills, in
both the agent panel and the settings UI.
---------
Co-authored-by: Martin Ye <martin@zed.dev>
Closes AI-344
Closes AI-342
Moves agent skills management out of the agent panel and into the
settings UI. The skill creator (previously its own crate) now lives in
`settings_ui` as a settings page, alongside the skills setup page. The
agent panel's ellipsis menu now links to the settings page instead of
hosting skill management directly.
Release Notes:
- Improved agent skills management by moving it into the settings UI
---------
Co-authored-by: Danilo Leal <daniloleal09@gmail.com>
Closes#56778
## Problem
The agent-profile tool configuration lists every built-in tool from
`agent::ALL_TOOL_NAMES`, filtering only by provider support
(`crates/agent_ui/src/agent_configuration/manage_profiles_modal.rs`).
But `Thread::enabled_tools` additionally drops feature-flag-gated tools
before they reach the model — the LSP tools (`go_to_definition`,
`find_references`, `get_code_actions`, `apply_code_action`) behind
`LspToolFeatureFlag`, `rename_symbol` behind `RenameToolFeatureFlag`,
and `create_thread` / `list_agents_and_models` / `update_plan` /
`update_title` behind their own flags.
The result: when a flag is off, a user can enable the tool in a profile,
but the agent never receives it. The picker and the runtime gate
disagreed.
## Fix
Extract the feature-flag gating into a single shared predicate,
`agent::tool_feature_flag_enabled`, and route **both**
`Thread::enabled_tools` and the profile tool picker through it. The
configuration UI can no longer offer a tool the agent would silently
drop, and the two call sites can't drift apart. Also updated the "silent
drop gates" comment in `tools.rs` to document this third gate.
This matches the behavior requested in the issue (don't list tools that
can't be used). The alternative — showing them disabled with an
explanation — is also possible; happy to switch if preferred.
## Testing
- Added `lsp_tools_are_gated_by_their_feature_flag` in
`crates/agent/src/tools.rs`.
- `cargo test -p agent`, `cargo clippy -p agent`, and `cargo fmt` are
clean.
- (`agent_ui` doesn't build in my local environment due to an unrelated
`webrtc-sys` C++ toolchain issue; the `agent_ui` change is a one-line
filter addition mirroring the adjacent provider-support check — relying
on CI to confirm.)
Release Notes:
- Fixed feature-flag-gated tools (such as the LSP tools) being listed in
agent profile configuration when they could not actually be used by the
agent.
---------
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This migrates the `Workspace::show_error` method to take a generic type
that implements `WorkspaceError` instead. That trait containts methods
to show a proper error message but most importantly means to help with
providing actions given certain errors.
The intention for this is rather easy: Whenever we show an error to the
user on the workspace level, that error should be
- actionable to a degree, even if that is only opening logs or whatnot
- show a message that is understandable to the user
- for not-too-critical errors, should hide after a certain delay and not
force the user to dismiss it using their mouse.
For now, there exist trait implementations for string error types and
anyhow errors. The long term goal here is to get rid of these altogether
and migrate everything to be strongly typed and especially actionable
instead.
Self-Review Checklist:
- [ ] I've reviewed my own diff for quality, security, and reliability
- [ ] 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:
- N/A
---------
Co-authored-by: Kirill Bulatov <kirill@zed.dev>
Co-authored-by: Ben Brandt <benjamin.j.brandt@gmail.com>
When a pending tool call awaiting permission contains tall content (e.g.
a full plan in Claude Code plan mode) and the inline prompt is scrolled
out of view, the floating awaiting-permission row embeds that content
and can grow to consume the entire panel, squeezing the conversation
list to zero height. `ListState::item_is_above_viewport` /
`item_is_below_viewport` returned `None` for a zero-height viewport, so
the row's visibility decision oscillated from frame to frame, flickering
between the conversation and the permission prompt and making the thread
unusable.
This PR fixes the root cause and hardens the UI:
- `gpui`: `item_is_above_viewport` / `item_is_below_viewport` now answer
definitively from the last layout bounds even when the viewport is
zero-height, so callers that size sibling UI based on these queries
can't oscillate. Adds a regression test.
- `agent_ui`: adds a `Floating` tool call layout used by the
awaiting-permission row that caps the embedded tool call content with a
scrollable max height, so the row can never crowd the conversation list
out of view while keeping the permission buttons visible. Adds an
integration test that drives real window draws and asserts the row's
visibility is stable across frames.
Closes AI-372
Closes https://github.com/zed-industries/zed/issues/58564
Release Notes:
- Fixed the agent panel flickering and becoming unusable when a
permission prompt with tall content (such as a plan awaiting approval)
was scrolled out of view.
Stabilizes context windows + persistent session/delete for acp agents
that support them
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
Release Notes:
- acp: Show context window usage and cost metrics for external agents
that support it.
- acp: Persist session deletion from history for external agents that
support it.
Noticed that when you had an empty draft and created a worktree we
weren't respecting agent selection. It was because of an early ? return
on an option, and should be fixed now.
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
Release Notes:
- agent: Fix for current agent not being selected when creating a new
git worktree
Closes https://github.com/zed-industries/zed/issues/54840
There are likely more places we can use this new workspace function in,
but these are the known ones to me right now
Release Notes:
- Fixed file hyperlinks in the agent panel not opening files when
clicked
Co-authored-by: saberoueslati <saberoueslati12@gmail.com>
Removing the `Rule` variant from `MentionUri` in #58080 broke
deserialization of any thread saved before the rules-to-skills
migration. Loading one failed with `unknown variant `Rule``, making
those threads inaccessible.
This restores access without bringing back the rules feature:
- Reintroduce a backward-compatible `Rule` mention variant so legacy
threads deserialize again.
- Preserve the original rule `id` through save/load so a thread re-saved
by a newer build still loads on older Zed versions (and synthesize a
valid placeholder when the id is missing).
- Clicking a legacy rule mention now opens the skill the rule was
migrated into, and shows a notification linking the Skills docs. On
remote/collab projects the migrated file lives on the local machine, so
it opens as a read-only buffer. If no matching skill exists, it does
nothing.
Closes https://github.com/zed-industries/zed/issues/58498
Closes AI-371
Release Notes:
- Fixed old threads that mention Rules being inaccessible after Rules
were migrated to Skills
Closes FR-61
To reproduce:
- you should be on a remote project
- terminal’s working directory is set to home
Release Notes:
- Fixed a crash that could occur when restoring an agent terminal in a
remote project.
Summary:
- Allow agent tool-call locations outside visible worktrees to resolve
as local buffers.
- Fall back to opening absolute paths from the tool-call click handler.
Tests:
- cargo test -p acp_thread
test_tool_call_location_resolves_external_file
- cargo check -p agent_ui
Closes AI-362
Release Notes:
- Fixed opening agent-created files outside the current project, such as
global skill files.
Closes AI-286
This PR adds a right-click menu to thread items in the sidebar. A big
motivation for this addition was surfacing the "regenerate thread title"
action. And because this action and the "open thread as markdown" action
previously only worked on the already-loaded agent panel, there was a
load of plumbing needed to make that work even for threads in workspaces
that haven't been loaded, mostly using the thread metadata store. At the
end of the day, the title regeneration feature is only possible for the
Zed agent, so this is gated from external agents. But I believe it's now
in a slightly nicer spot due to some refactors to better expose the
state in which the title regeneration can fall into.
Release Notes:
- Agent: Added a right-click menu to thread items in the sidebar,
allowing to regenerate a thread title, rename a thread title, open the
thread as markdown, and archive it.
---------
Co-authored-by: zed-zippy[bot] <234243425+zed-zippy[bot]@users.noreply.github.com>
Co-authored-by: Bennet Bo Fenner <bennetbo@gmx.de>
channels_with_threads opened a fresh SQLite connection per
release-channel database on every call, and the sidebar called it twice
per frame from its render path, blocking the render loop on disk I/O.
Run the per-channel checks on a background thread and cache the
resulting channel names once at sidebar construction, since the
per-channel databases cannot change while this process runs.
Release Notes:
- Fixed a cause of stutters in the agent panel sidebar rendering
This crash occurred because metion crease were using raw text ranges
that were precomputed before calling editor.edit(), and didn't take into
account that editor normalizes text inserted
The fix is normalizing the text first, then using the normalize text
range for the crease
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
Release Notes:
- Fix a crash that could occur when adding a crease to the agent panel
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
Closes https://github.com/zed-industries/zed/issues/58153
Release Notes:
- Agent: Fixed image previews not being displayed after submitting a
prompt and then hovering the mentioned image.
## **NOTE:**
I'm new both to Rust and Zed, so it's mostly vibecoded alleged fix for
#57295, just as a PoC of expected behavior that works on macOS. So
please be critical and skeptical of the code, as it may not account for
many nuances and behavior on other platforms.
## Summary
- Fixes#57295: the `Add to Agent Thread` action (or `cmd->`) was a
silent
no-op when a terminal thread was the active conversation in the agent
panel.
- The action's deferred handler only routed through
`active_conversation_view()`,
which returns `None` for `BaseView::Terminal`, so the selection was
dropped.
- Extends the handler with an `else if` branch that, when a terminal
thread is
active, formats the selection as `@<rel-path>:<start>-<end>` (matching
the
mention syntax CLI agents already understand) and pastes it into the
terminal, then focuses the terminal so the user can edit/submit.
## Test plan
- [x] Select a range of lines in a buffer, open a terminal thread in the
agent
panel, invoke `Add to Agent Thread` from the context menu → the
formatted
mention is pasted into the terminal.
- [x] Same flow via the `cmd->` keybinding on macOS.
- [x] Multiple selections in one buffer produce space-separated
mentions.
- [x] `cargo check -p agent_ui` and `./script/clippy -p agent_ui` pass.
## Demo
<img width="2928" height="1920" alt="ScreenShot 2026-05-20 at 21 03 27"
src="https://github.com/user-attachments/assets/dc29f380-a864-4c12-b454-bdb4201f5b8d"
/>
https://github.com/user-attachments/assets/9d3914d8-8ba2-4bcb-be43-78efb342d8a8
## Release Notes:
- Fixed `Add to Agent Thread` being a no-op when a terminal thread is
the active conversation in the agent panel
---------
Co-authored-by: Martin Ye <martin@zed.dev>
Updates the sandbox authorization prompt for terminal write-path
requests to show a compact, collapsible list of the requested paths. The
list now matches the edited-files disclosure style, sorts paths for
stable scanning, and uses existing file icons plus muted parent
directories so users can quickly see which locations the command wants
to write to.
This is a UI-only change; sandbox permission behavior remains unchanged.
Release Notes:
- Improved agent sandbox permission prompts by showing requested write
paths in a clearer file list
---------
Co-authored-by: Martin Ye <martin@zed.dev>
Follow-up hardening on top of #57972 (granular sandbox write
permissions), based on a review of that branch. The most important fix
is that model-requested `fs_write_paths` were joined but never
normalized, so a path containing `..` could pass the lexical
subtree-containment checks while seatbelt canonicalized it to somewhere
else entirely — causing skipped approval prompts and silent runtime
write denials. Write paths are now lexically normalized (via
`util::paths::normalize_lexically`) at the point they enter the system,
both for model requests and for hand-edited persistent grants, so the
containment check, the approval prompt, and the enforced sandbox policy
all operate on the same path.
The subtree insert/prune and containment logic had drifted into roughly
five near-identical copies across `agent`, `agent_settings`, and
`settings_content`; these now share `util::paths::insert_subtree` and
`path_within_subtree`. The dead `SandboxPermissions::covers` (only ever
exercised by its own tests, duplicating the production
`covers_with_persistent`) is removed, and its tests rewritten to cover
the real settings-compilation path including `..` normalization.
The remaining changes reduce brittleness: the sandbox permission option
ids (`allow`, `allow_thread`, `allow_always`, `deny`) are now shared
constants in `acp_thread` instead of bare string literals scattered
across the agent and UI, `persist_sandbox_always_permission` logs
instead of silently doing nothing when no filesystem is available, and a
comment documents why replay always resolves the terminal tool to the
non-sandboxed variant.
Release Notes:
- N/A
---------
Co-authored-by: Martin Ye <martin@zed.dev>
Co-authored-by: MartinYe1234 <52641447+MartinYe1234@users.noreply.github.com>
Brings stable logout and additional directories support as well as
removing dep on rmcp + tokio
This also removed the unstable model selector (replaced awhile ago by
session config options) so it removes all of that code.
Native agent still uses it because we have a special model selector that
would need more work to rip out
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
Release Notes:
- N/A
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>
Closes ZED-8SQ
This PR uses the same pattern for `can_select` as other delegates and
also guards `can_select` call in `Picker::render_element` which was
regressed in #50705.
Release Notes:
- Fixed a crash that could occur when searching or configuring tools in
agent profile settings.
Adds granular, per-path write permissions to the agent's sandboxed
`terminal` tool.
Previously a command could only request unrestricted filesystem writes
(`allow_fs_write: true`) as an all-or-nothing escape hatch. Now the
model can request write access to specific paths via `fs_write_paths`,
and each granted directory covers its whole subtree. The broad escape
hatch is still available as `allow_fs_write_all: true` for cases where
the paths can't be enumerated up front.
Approval prompts now let the user grant a write request either just for
that command or for the rest of the conversation. Conversation grants
are tracked in memory (never persisted) using pure subtree containment,
so later commands writing under an already-granted path run without
prompting again.
Closes AI-335
Release Notes:
- Improved the agent's terminal sandbox so commands can request write
access to specific paths instead of all-or-nothing filesystem access,
with the option to grant access for a single command or the rest of the
conversation.
---------
Co-authored-by: Anant Goel <anantdgoel@gmail.com>
Co-authored-by: Richard Feldman <oss@rtfeldman.com>
Adds two built-in agent tools, behind the staff-only
`create-thread-tool` feature flag, that let the agent spawn independent
sibling threads:
- **`create_thread`** creates a new thread with a title and initial
prompt. It runs on the user's behalf and shows up in the agent sidebar
like a thread the user started themselves, but it runs in the background
— the active thread is never interrupted — and it does **not** report
results back to the caller. (Use `spawn_agent` when you want the
results.)
- **`list_agents_and_models`** enumerates the configured agents and, for
the native agent, the available models, so the agent can pick a
cheaper/faster model for bulk work. The motivating stress test was
"spawn 100 threads that each write a haiku, using Haiku instead of
Opus."
By default the sibling shares the parent's project and worktree. If
`use_new_worktree` is set, `create_thread` instead opens a new
background workspace backed by fresh linked git worktrees of the
project's repos — the same flow you get from the worktree picker's
"Create worktree" — and starts the thread there. The new workspace opens
as a background tab so it doesn't pull you away from what you're doing.
A few notes on the design:
- The `agent` crate can't depend on the UI, so there's a
`SiblingThreadHost` trait that `agent_ui::AgentPanel` implements and
installs on the `NativeAgent`. Tool calls in a native-agent thread route
through it.
- Sibling threads go through the same `create_agent_thread` →
`ConversationView` path as the user-facing "new thread" action, so
eviction, persistence, and sidebar rendering match user-created threads.
- An explicit `agent`/`model` override doesn't clobber the panel's
selected agent or the last-used-agent preference — those are snapshotted
and restored around the call.
- The worktree path reuses the existing "Create worktree" machinery
rather than reimplementing it; the agent flow just opens the new
workspace in the background instead of activating it.
A couple of things I left out or want to call out:
- There's no tool to operate on an already-created sibling by session
id. The success payload deliberately omits it, since the session is
populated asynchronously and nothing consumes it yet.
- When a project has multiple worktrees that are linked worktrees of the
*same* underlying repo, they collapse into a single new worktree (they
resolve to the same target path). The tool returns a warning in that
case rather than failing — and this also fixes a latent collision the
manual "Create worktree" flow would hit in the same situation.
Release Notes:
- N/A
Closes https://github.com/zed-industries/zed/issues/57992
Closes AI-349
## Summary
- Run rules-to-skills migration during agent UI init instead of waiting
for feature flags in production.
- Add a command palette action to rerun the migration manually.
- Make AGENTS.md migration appends idempotent to avoid duplicated
default-rule prompts.
Release Notes:
- Added a manual way to trigger the Rules to Skills migration
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
Release Notes:
- N/A
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
Release Notes:
- N/A
Makes sure that the reasoning effort levels picker can be controlled
with the same shortcuts that are used in the native agent.
Also adds the keyboard shortcuts to the tooltips for all pickers that
support them
Closes#56074
Release Notes:
- Fixed an issue where reasoning effort selector could not be controlled
via keyboard shortcuts for ACP agents
Refactor to isolate alacritty types into the terminal crate and offers
comparable apis where needed for similar functionality. However, these
are Zed-owned types instead of the dependency leaking across multiple
crates, making alacritty an implementation detail of the terminal crate.
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
Release Notes:
- N/A
Danilo Leal