Add support for scaling the Markdown preview's body text and headings
with `cmd-=` / `cmd--` / `cmd-0`. Previously these shortcuts only
resized code blocks because the preview's body used `ui_font_size` and
headings used a rem-based scale anchored to it, while the keybindings
only mutated `BufferFontSize`.
The preview's scroll subtree is now wrapped in
`WithRemSize(buffer_font_size)`, so `1rem` resolves to the buffer font
size inside the preview. Body text, headings
(`text_3xl`/`text_2xl`/...), and rem-based spacing all scale together.
The outer focus root and scrollbar remain at the UI font size.
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#55374
Release Notes:
- Added `markdown_preview_font_size` setting and actions to scale
Markdown preview font size separately from the editor.
---------
Co-authored-by: Smit Barmase <heysmitbarmase@gmail.com>
# Objective
Fix OpenAI-compatible reasoning/thinking support. Previously,
`OpenAiCompatibleLanguageModel` never reported thinking support, so
configured `reasoning_effort` values did not reliably reach the wire and
Responses API reasoning state could miss `include:
["reasoning.encrypted_content"]`.
Fixes#58289
Addresses #59207 for OpenAI-compatible Responses models configured with
`reasoning_effort`.
## Solution
- Treat a non-`none` configured `reasoning_effort` as OpenAI-compatible
thinking support.
- Expose common OpenAI-style effort levels in the agent UI, using the
configured effort as the default.
- Honor selected reasoning effort for OpenAI-compatible chat-completions
requests.
- Send `reasoning_effort: "none"` when thinking is disabled for a
configured reasoning model.
- Preserve native OpenAI behavior by continuing to use native
model-specific supported efforts and `max_completion_tokens`.
- Add an OpenAI-compatible `max_tokens_parameter` capability for
endpoints that expect output limits as `max_tokens`.
- Parse common streamed thinking fields (`reasoning` and
`reasoning_content`).
- Add provider setup UI and docs for configuring OpenAI-compatible
reasoning models.
## Testing
- `cargo fmt -p language_model_core -p agent_ui -p language_models`
- `cargo test -p language_models provider::open_ai_compatible::tests
--lib`
- `cargo test -p language_models provider::open_ai::tests --lib`
- `cargo test -p open_ai completion::tests --lib`
- `cargo test -p agent_ui
agent_configuration::add_llm_provider_modal::tests --lib`
- `git --no-pager diff --check`
## 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:
- Improved OpenAI-compatible provider setup for reasoning models.
---------
Co-authored-by: Anant Goel <anant@zed.dev>
Agent terminal sandboxing now protects `.git` metadata by default and
exposes an explicit `allow_git_access` approval. Without it, file
contents of the `.git` directories for opened worktrees and discovered
repositories (including a linked worktree's common `.git`) cannot be
read or written, though their metadata stays visible; when approved,
those Git directories become writable so commands like fetch/commit
work. SSH commit signing keeps working because the inherited
`SSH_AUTH_SOCK` is allowed as local Unix-socket IPC, which does not let
sandboxed commands send network packets to other machines. The Seatbelt
profile also allows PTY terminal-control ioctls so signing/passphrase
prompts can manage terminal state.
This intentionally restricts only `.git` itself (whose location we know
exactly, including the worktree case) rather than
`.gitignore`/`.gitattributes`/`.gitmodules`, since those can be nested
arbitrarily and the goal is to keep the policy expressible as a plain
deny-by-default allowlist that will port to Linux and Windows sandboxes
later.
Closes AI-334
Release Notes:
- Improved agent terminal sandboxing for Git metadata, Git worktrees,
and SSH commit signing.
Follow-ups to the recently-landed agent terminal sandboxing work.
- Make the persistent "Allow Unsandboxed Terminal Commands" setting
(`allow_unsandboxed`) the single off-switch for the agent terminal
sandbox: when enabled, the sandboxed terminal tool isn't exposed and the
system prompt omits the sandbox section, so the model uses the plain
`terminal` tool (and on Windows, WSL sandbox setup is skipped). This
removes the dead, unwired `disabled` setting that was meant to do the
same thing but had no UI, writer, or docs. Per-command and per-thread
`unsandboxed: true` grants are unchanged.
- Expand the blocklist of Windows-specific environment variables that
aren't forwarded into the WSL sandbox (system locations, `HOME`/profile
paths, host/session identity, CPU descriptors, etc.) so they can't
shadow or break Linux commands. It stays a blocklist, so portable
variables like `LANG` still reach the command.
Release Notes:
- N/A
# Objective
The current behavior of the git panel is that when you click a file it
will open the multi-buffer view that shows all files with changes. If
you use CMD+Click or CTRL+Click, it will open the solo-file experience
where you only see the diff of the file you have selected. But, there is
no way to customize this behavior.
Related to:
https://github.com/zed-industries/zed/pull/56152#issuecomment-4641971669
## Solution
This MR adds a setting that allows you to customize the default click
behavior. The alternate behavior will always be accessible via CMD+Click
or CTRL+Click.
## 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:
- Added a setting to control default click behavior for git panel files
---------
Co-authored-by: Christopher Biscardi <chris@christopherbiscardi.com>
Self-Review Checklist:
- [x] I have reviewed my own diff for quality, security, and reliability
- [x] Unsafe blocks (if any) have justifying comments
- [x] The content adheres to Zed 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
## Summary
This updates the Git Panel view controls so the panel can independently
model:
- whether entries are shown as a list or tree
- whether flat entries are sorted by path or name
- whether entries are grouped by status or shown as one combined set
It also keeps the Project Diff order consistent with the Git Panel,
including tree ordering, status grouping, and flat name/path sorting.
## Why This Is Useful
The previous sort_by_path boolean overloaded two separate ideas: sorting
and grouping. That made it hard to represent the view users actually
wanted, especially a single tree where tracked and untracked files are
not split into separate sections.
This change replaces that boolean with explicit enum settings:
- git_panel.sort_by: path or name
- git_panel.group_by: none or status
That keeps the settings mutually exclusive, easier to extend, and closer
to the UI model.
## Implementation Notes
- Adds a dedicated Git Panel View Options menu using the sliders icon.
- Moves view, sort, and group controls out of the overflow actions menu.
- Disables sort options in tree view because tree order is folder-first
rather than pure path/name sorting.
- Removes the Tracked heading when grouping is disabled.
- Keeps Git Panel tree expansion state when switching view options.
- Recomputes Project Diff sort prefixes from tree_view, sort_by, and
group_by so diff cards follow the same top-to-bottom order as the Git
Panel.
- Preserves Project Diff open/closed file state across view option
changes by carrying fold state by repo path instead of by synthetic sort
key.
- Updates settings UI renderers and docs for the new enum settings.
## Testing
- [x] cargo fmt --package git_ui --package settings_ui
- [x] cargo check -p git_ui
- [x] Verified settings UI enum dropdown rendering for Git Panel
sort/group settings
Closes https://github.com/zed-industries/zed/issues/53555
Closes https://github.com/zed-industries/zed/issues/56039
Closes https://github.com/zed-industries/zed/issues/45438
Release Notes:
- Improved Git Panel view options and Project Diff ordering.
---------
Co-authored-by: Christopher Biscardi <chris@christopherbiscardi.com>
# Objective
- Fixes#59614.
- A stdio `context_servers` entry defined with only a `command` (the
minimal form most MCP hosts accept, e.g. `{ "command": "echo" }`) fails
to deserialize. `ContextServerCommand.args` is a required field, so the
entry matches no variant of the untagged `ContextServerSettingsContent`;
the server silently never loads, and the only log line is the opaque
`data did not match any variant of untagged enum
ContextServerSettingsContent`. Other fields (`env`, `timeout`) are
already optional, and the docs only ever show `args` with a value
without stating it is required, so users reasonably assume it is
optional.
## Solution
- Add `#[serde(default)]` to `ContextServerCommand.args` in
`crates/settings_content/src/project.rs`, so it defaults to an empty
list when omitted, the same way `env` and `timeout` are already
optional. `{ "command": "echo" }` now defines a valid stdio server with
no arguments.
## Testing
- Added `test_stdio_context_server_without_args` in
`crates/settings_content/src/project.rs`, which deserializes `{
"command": "echo" }` (asserts empty `args`) and `{ "command": "echo",
"args": ["hello"] }` (regression guard).
- Fail-before/pass-after confirmed: without the change the new test
fails with the exact error from the issue; with it, `cargo test -p
settings_content` passes (24 passed, 0 failed).
- `cargo clippy -p settings_content --tests` and `cargo fmt -p
settings_content -- --check` are clean.
- serde-only change; platform-independent.
## 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 stdio MCP servers configured with only a `command` (no `args`)
failing to load.
This PR introduces a markdown preview max-width setting in which we
allow to limit by a given pixel number how wide the content within the
preview tab should go. Before this, content would render edge-to-edge
and if you're reading long markdown docs with no split panes, having it
be full width like that was a horrible reading experience.
So, right now, you can control that through the
`zed://settings/markdown_preview.max_width` setting.
<img width="600" alt="Screenshot 2026-06-18 at 1 24@2x"
src="https://github.com/user-attachments/assets/7f0216e1-e4ac-47f7-975b-5de7a0dd4c6d"
/>
Release Notes:
- Added setting to control max-width of content within the markdown
preview.
Summary
- Adds Windows agent terminal sandboxing by routing commands through WSL
and Bubblewrap.
- Supports native Windows and WSL project paths, including elevated
write grants for WSL paths.
- Shows a confirmation prompt to turn off sandboxing when WSL sandbox
setup is unavailable.
This builds on the work in the sandbox-linux branch.
Closes AI-376
Release Notes:
- Added Windows terminal sandboxing for agent commands when sandboxing
is enabled.
---------
Co-authored-by: cameron <cameron.studdstreet@gmail.com>
Co-authored-by: Richard Feldman <oss@rtfeldman.com>
Co-authored-by: zed-zippy[bot] <234243425+zed-zippy[bot]@users.noreply.github.com>
## Summary
- Adds an `agent.terminal_init_command` setting for Terminal Threads.
- Runs the configured command automatically when creating a new Terminal
Thread, while skipping restored terminal threads.
- Documents the setting and exposes it in the AI settings page.
Closes https://github.com/zed-industries/zed/issues/58697
Closes AI-337
Release Notes:
- Added a setting to automatically run a command when opening a new
terminal thread in the agent panel.
---------
Co-authored-by: Anant Goel <anant@zed.dev>
Third of a four-PR stack adding hostname-allowlisted network access to
agent terminal sandboxing. Stacked on #59218 — review/merge #59217 and
#59218 first.
Replaces the boolean `allow_network` terminal-sandbox escalation with a
hostname allowlist. The `terminal` tool now takes `allow_hosts` (exact
hostnames or leading-`*.` subdomain wildcards, validated up front) and
`allow_all_hosts` as a broad escape hatch. Approval prompts name the
requested hosts, thread grants and persistent "allow always" settings
cover requests via host-pattern subsumption the same way write paths use
subtree containment, and the authorization card in the agent panel lists
the requested hosts.
Host allowlists aren't enforced yet in this PR: `SandboxWrap` carries
the allowlist, but any network request still maps to unrestricted egress
at the Seatbelt layer, matching previous behavior. Enforcement via the
in-process proxy lands in the final PR of the stack. All of this is
behind the existing sandboxing feature flag. For non-local projects
(where the loopback proxy won't apply), host requests are widened to
"arbitrary network access" before prompting so approvals match
enforcement. Old persisted `network: bool` authorization details still
deserialize via a serde alias.
Release Notes:
- N/A
---------
Co-authored-by: MartinYe1234 <52641447+MartinYe1234@users.noreply.github.com>
Co-authored-by: Martin Ye <martin@zed.dev>
The work introduced in https://github.com/zed-industries/zed/pull/54496
updated the `command_aliases` schema, adding support for auto-completion
action names when editing the settings file. However, it didn't take
into consideration the case where the user is simply creating an alias
to an arbitrary string.
These changes introduce a new `CommandAliasTarget` newtype for which the
json schema is either a registered action name, from `ActionName` or any
arbitrary string, as those are supported by the `command_aliases`
setting.
Updating the `ActionName` schema to accept any arbitrary string would
break the guarantees we have on the keymap binding schema, so that's why
a new schema was introduced.
Lastly, trying to set `CommandAliasTarget::json_schema` to a simply
`anyOf` with either the registered action name or a string that is not a
registered action name, like shown below, broke deprecation warnings,
hence why we're still doing the approach of only building
`CommandAliasTarget` at runtime.
```json
{
"anyOf": [
{ "$ref": "#/$defs/ActionName" },
{ "type": "string", "not": {
"$ref": "#/$defs/ActionName"
}},
]
}
```
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:
- Fixed validation of `command_aliases` setting to avoid showing
warnings when aliasing to an arbitrary string
Dev container image builds default to BuildKit (`docker buildx`).
Docker-compatible engines that lack an integrated BuildKit — notably
[Apple Container](https://github.com/apple/container) accessed through a
Docker-API bridge — cannot resolve a locally-built image in a `FROM`,
which breaks the dev container build: Zed builds the features image,
then a second `FROM <features-image>` build (the UID remap), and
BuildKit's docker-container/remote drivers can't see the daemon's local
image, failing with `pull access denied`.
The daemon's *classic* builder resolves locally-built images, and Zed
already generates a BuildKit-free Dockerfile for the non-BuildKit path
(multi-stage `FROM` + `COPY --from`, no `RUN --mount`). This wires that
path to a setting and makes the remaining build invocations actually use
the classic builder.
## Changes
- Add a `dev_container_use_buildkit` setting (tri-state):
- unset → auto-detect via the `docker buildx` plugin (current behavior)
- `false` → force the classic builder
- `true` → force BuildKit
- When the classic builder is selected, pass `DOCKER_BUILDKIT=0` (and
`COMPOSE_DOCKER_CLI_BUILD=0` for compose) to the feature-content build,
the compose build, and the UID-remap build, so multi-stage `FROM` of a
locally-built image resolves through the daemon's classic builder.
- Document the setting in `docs/src/dev-containers.md`.
With this setting plus a Docker-API bridge, a real Rails dev container
(compose: app + mysql + valkey, with features) builds and starts on
Apple Container.
## How to Review
- `settings_content.rs` / `dev_container/src/lib.rs` — the new setting
and its plumbing into `DevContainerContext`.
- `docker.rs` — `Docker::new` honors the setting
(`supports_compose_buildkit`), `docker_compose_build` selects the
classic builder; unit test
`use_buildkit_setting_overrides_buildx_detection`.
- `devcontainer_manifest.rs` — `DOCKER_BUILDKIT=0` for the
feature-content and UID-remap builds.
## Self-Review Checklist
- [x] I've reviewed my own diff for quality, security, and reliability
- [ ] Unsafe blocks (if any) have justifying comments
- [ ] 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:
- Added a `dev_container_use_buildkit` setting to build dev containers
with the classic Docker builder for engines without an integrated
BuildKit (e.g. Apple Container)
This is a bit too opinionated to be turning on for everyone by default.
We could consider bringing back a default-enabled setting with a less
intrusive UI.
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:
- Warnings about the lengths of commit message titles are now disabled
by default.
Adds `default_open_behavior` which let's users control which action
should be the default (add to existing window/open a new window)
TODO:
- [x] Use sensible icon (not `IconName::Screen`) when
`default_open_behavior` is set to `new_window`
- [x] Tweak wording for actions in recent projects menu
<img width="420" height="59" alt="image"
src="https://github.com/user-attachments/assets/69ef112e-bf20-4dd1-9994-e4442266ef87"
/>
Release Notes:
- Added `default_open_behavior` which controls which action (add to
sidebar/open in new window) should be the default when selecting a
project from the recent projects menu
---------
Co-authored-by: Danilo Leal <daniloleal09@gmail.com>
<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>
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>
Self-Review Checklist:
- [x] I've reviewed my own diff for quality, security, and reliability
- [ ] Unsafe blocks (if any) have justifying comments
- [ ] 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
- [ ] Performance impact has been considered and is acceptable
Please check
https://github.com/zed-industries/zed/issues/56277#issuecomment-4417185748
for more context.
Release Notes:
- N/A or Added/Fixed/Improved ...
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>
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 option to always search/scan symlinks for more thorough coverage of
#41887 issue
This is a significant rewrite and more thoroughly reviewed and tested
version of the old PR here:
https://github.com/zed-industries/zed/pull/46344
The "never" option was removed from the old PR, since "expanded" is now
the default. Perhaps "never" can be added as an option later if there's
demand for it. Adding that option may resolve#48890 for instance.
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
(significant impact with "always" option, but "expanded" is default)
Release Notes:
- Add option choose between including expanded symlinks or include all
symlinks in project search (#41887)
---------
Co-authored-by: Eric Holk <eric@zed.dev>
There's currently no way to customize AI-generated commit messages on a
per-commit basis. You can put instructions in AGENTS.md or a project
rules file, but those get fed into every agent interaction, not just
commit generation. The built-in "Commit message" prompt used to be
editable in the Rules Library, but that was replaced by Skills, which
aren't used when generating commit messages.
This PR adds an `agent.commit_message_instructions` setting. Its
contents are added to the commit message prompt in their own section,
alongside any project rules, so you can ask for a specific format
(Conventional Commits, a ticket prefix, etc.) without changing how the
agent behaves elsewhere:
```json
{
"agent": {
"commit_message_instructions": "Use the Conventional Commits format: <type>(<scope>): <description>."
}
}
```
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
Addresses #26503
Release Notes:
- Added an `agent.commit_message_instructions` setting to customize
AI-generated git commit messages.
---------
Co-authored-by: Christopher Biscardi <chris@christopherbiscardi.com>
- Add a separate `git_commit_buffer_font_size` setting, defaulting to
`12px` (the previous default before it was changed to use the buffer
font size)
- Add in-memory buffer font size overrides for zooming the commit modal
and in-panel editor
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 a `git_commit_buffer_font_size` setting and made the in-panel
and modal commit message editors zoomable.
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 #ISSUE
Release Notes:
- N/A or Added/Fixed/Improved ...
Self-Review Checklist:
- [X] I've reviewed my own diff for quality, security, and reliability
- [N/A] 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:
- Removed support for ACP extensions. Installed ACP extensions will be
migrated to use the ACP servers as provided by the ACP registry instead.
---------
Co-authored-by: Ben Brandt <benjamin.j.brandt@gmail.com>
Co-authored-by: Marshall Bowers <git@maxdeviant.com>
In the interactive MCP OAuth flow, the MCP client registers itself with
the authorization in one of three ways:
- Client ID Metadata Document aka CIMD (recommended default). This is
already implemented: https://zed.dev/oauth/client-metadata.json.
- Dynamic Client Registration (DCR). This is the traditional method.
Also already implemented in Zed.
- Pre-registration: the client is registered out of band, typically in
the IdP or SaaS provider's UI. You get a client id and maybe a client
secret, that have to be provided by the MCP client when it wants to
exchange an access token. This is what this pull request is about.
This PR has two main parts:
- Allow users to configure a client id and optional client secret for an
MCP server in their configuration, under a new `oauth` key, and take it
into account
- Make the MCP server state and the configuration modal aware of the
intermediate states (client secret missing) and error cases stemming
from client pre-registration.
The client secret can be stored either in the system keychain or in
plain text in the MCP server configuration. The UI tries to steer user
towards the more secure option: the keychain.
<img width="715" height="201" alt="Screenshot 2026-04-10 at 16 48 06"
src="https://github.com/user-attachments/assets/5e64103e-6746-4ef0-8bd9-533d492b6912"
/>
<img width="884" height="544" alt="Screenshot 2026-04-10 at 16 47 07"
src="https://github.com/user-attachments/assets/0e35bb3c-cbc4-4e8c-a713-66323597b2e2"
/>
<img width="785" height="558" alt="Screenshot 2026-04-10 at 16 47 23"
src="https://github.com/user-attachments/assets/03339187-1508-461a-87ae-a7c2647df9a5"
/>
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/issues/assigned?issue=zed-industries%7Czed%7C52198
**Note for the reviewer: I know how busy the AI team is at the moment so
please treat this as low priority, we don't have signal that this is a
highly desired feature. It's a rather large PR, so I'm happy to pair
review / walk through it.**
Release Notes:
- Added support for OAuth client pre-registration (client id, client
secret) to the built-in MCP client.
Adds a `markdown_preview_code_font_family` setting that overrides the
font used in the markdown preview for code — inline `code` spans and
fenced code blocks.
This is the counterpart to `markdown_preview_font_family` (#54003),
which already does this for body text. Together they let you choose a
typographically matched body + code font pair for the preview without
forcing the code font onto editor buffers, where it may not be a good
coding font:
```json
{
"markdown_preview_font_family": "Noto Serif",
"markdown_preview_code_font_family": "Noto Sans Mono"
}
```
Behavior mirrors `markdown_preview_font_family`:
- Scoped to the markdown preview only (`MarkdownFont::Preview`). The
agent panel, notifications, hover popovers, and REPL output are
unaffected — they keep using the buffer font for code.
- Falls back to the buffer font family when unset, so existing previews
are unchanged.
- Overrides the font family only; fallbacks and features still come from
the buffer font.
Before (uses buffer font, here Iosevka):
<img width="509" height="368" alt="Screenshot 2026-05-14 at 1 39 51 PM"
src="https://github.com/user-attachments/assets/6b7e49b2-fc6e-4db1-9679-392b3447f411"
/>
After (uses specified font, here Noto Sans Mono):
<img width="508" height="368" alt="Screenshot 2026-05-14 at 1 40 51 PM"
src="https://github.com/user-attachments/assets/f911c99b-08f8-4336-83eb-54b555f11c54"
/>
Release Notes:
- Added `markdown_preview_code_font_family` to override the code font in
the markdown preview
With long lines or a small viewport, the stage/restore buttons often
cover code.
Adds a setting to hide the buttons altogether. Defaults to showing them.
Release Notes:
- Added: Setting to hide Git Stage/Restore buttons
## Background: Amazon Bedrock Guardrails
AWS Bedrock Guardrails enables configurable safety and compliance
controls for generative AI applications:
- Evaluates both user inputs and model responses against policies.
:contentReference[oaicite:8]{index=8}
- Can block or filter content based on harmful categories, denied
topics, PII, or hallucination criteria.
:contentReference[oaicite:9]{index=9}
- Guardrails are applied during inference API calls by specifying
`guardrailIdentifier` and `guardrailVersion` in the request.
:contentReference[oaicite:10]{index=10}
Relevant AWS documentation:
- User Guide:
https://docs.aws.amazon.com/bedrock/latest/userguide/guardrails.html
- How Guardrails Works:
https://docs.aws.amazon.com/bedrock/latest/userguide/guardrails-how.html
- API Reference (GuardrailConfiguration):
https://docs.aws.amazon.com/bedrock/latest/APIReference/API_GuardrailConfiguration.html
Some AWS environments enforce IAM policies that require a guardrail to
be specified on every Bedrock API call (via a `StringEquals` condition
on `bedrock:GuardrailIdentifier`). Without this, Zed returns
`AccessDenied` and Bedrock models are completely unusable in those
environments.
This adds two optional settings, `guardrail_identifier` and
`guardrail_version`, to the Bedrock provider config. When set, a
`GuardrailStreamConfiguration` is attached to every `converse_stream`
request. When unset, behaviour is identical to before.
```json
{
"language_models": {
"bedrock": {
"guardrail_identifier": "arn:aws:bedrock:us-east-1:123456789012:guardrail/abc123",
"guardrail_version": "DRAFT"
}
}
}
```
`guardrail_version` defaults to `"DRAFT"` if omitted.
Release Notes:
- agent: Added `guardrail_identifier` and `guardrail_version` settings
for AWS Bedrock, enabling use in environments where IAM policies require
a guardrail on all model requests
---------
Co-authored-by: Bennet Bo Fenner <bennetbo@gmx.de>
Closes#52042
Release Notes:
- agent: Added setting `subagent_model` to specify which model is used
when subagent is spawned
---------
Co-authored-by: Ben Brandt <benjamin.j.brandt@gmail.com>
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
Closes https://github.com/zed-industries/zed/issues/52585
Release Notes:
- Fixed local zeta2 edit predictions using the wrong prompt format.
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 #ISSUE
Release Notes:
- Added a setting
[vim.show_edit_predictions_in_normal_mode](zed://settings/vim.show_edit_predictions_in_normal_mode)
to control whether edit predictions are shown in normal mode.
This PR makes editor diff hunk colors configurable from themes, instead
of hardcoded values.
It introduces 6 new optional theme keys:
- `editor.diff_hunk.added.background`
- `editor.diff_hunk.added.hollow_background`
- `editor.diff_hunk.added.hollow_border`
- `editor.diff_hunk.deleted.background`
- `editor.diff_hunk.deleted.hollow_background`
- `editor.diff_hunk.deleted.hollow_border`
When a theme omits these keys, each color falls back to the existing
version-control color with the previous hardcoded opacity values:
- Light defaults:
- background_opacity = 0.16
- hollow_background_opacity = 0.08
- hollow_border_opacity = 0.48
- Dark defaults:
- background_opacity = 0.12
- hollow_background_opacity = 0.06
- hollow_border_opacity = 0.36
There is an existing feature request
https://github.com/zed-industries/zed/discussions/51667
## Screenshots
I used `Modus Themes` (Modus Vivendi) since these themes provide highly
accessible themes.
Original version:
<img width="3248" height="2120" alt="CleanShot 2026-03-17 at 20 26
41@2x"
src="https://github.com/user-attachments/assets/730be802-835d-436e-a1fc-4c60dcb5fce8"
/>
This version:
<img width="3248" height="2120" alt="CleanShot 2026-03-17 at 20 23
09@2x"
src="https://github.com/user-attachments/assets/785c86d3-147e-437f-9624-9576bc201551"
/>
Before you mark this PR as ready for review, make sure that you have:
- [x] Added a solid test coverage and/or screenshots from doing manual
testing
- [x] Done a self-review taking into account security and performance
aspects
- [x] Aligned any UI changes with the [UI
checklist](https://github.com/zed-industries/zed/blob/main/CONTRIBUTING.md#uiux-checklist)
Release Notes:
- Added theme keys for configuring editor diff hunk colors.
---------
Co-authored-by: MrSubidubi <finn@zed.dev>
The `opencode` built-in provider is registered in the language model
registry
but missing from the JSON schema enum in `LanguageModelProviderSetting`.
<img width="724" height="399" alt="image"
src="https://github.com/user-attachments/assets/33da4626-eb44-443e-b656-65533b3a85f1"
/>
<br>
OpenCode is one of the "first class" providers, so I was surprised it
was missing from the auto-complete for the provider fields in the
settings file.
## 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
OpenCode API endpoints for DeepSeek were [moved from
Anthropic-compatible to
OpenAI-compatible](https://github.com/anomalyco/opencode/pull/24500) and
DeepSeek requires interleaved reasoning enabled to work. I ran a
_"rename this variable to potato"_ test and I can confirm DeepSeek V4
Flash and Pro both work now 🎉
Some other OpenCode Go models were marked [on
models.dev](https://github.com/anomalyco/models.dev/tree/dev/providers/opencode-go/models)
as supporting `interleaved_reasoning` so they too got that enabled. Kimi
K2.5 and Kimi K2.6 continue to fail with
https://github.com/zed-industries/zed/issues/51743
(https://github.com/zed-industries/zed/pull/55085 seems to hint at this
being [an OpenCode
issue](https://github.com/zed-industries/zed/issues/51743#issuecomment-4336785765)?),
but all other models seem to work fine both with `interleaved_reasoning`
and without it 🤷 I assume it's better to have that turned on? Again, the
intersection of OpenAI Chat Completions API, different models, different
inference providers, how they all work together is something I know
nothing about!
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:
- OpenCode Go: use correct DeepSeek endpoints
- OpenCode: add support for interleaved_reasoning
The [Parallel Agents release](https://zed.dev/blog/parallel-agents)
introduced a new default layout: the agent panel now docks on the left,
while the project, git, outline, and collaboration panels now dock on
the right. The rustdoc comments in `crates/settings_content` were not
updated to reflect this change.
This PR corrects the `Default:` values in the following structs:
- `ProjectPanelSettingsContent.dock`: `left` → `right`
- `GitPanelSettingsContent.dock`: `left` → `right`
- `PanelSettingsContent.dock` (collaboration panel): `left` → `right`
- `OutlinePanelSettingsContent.dock`: `left` → `right`
- `AgentSettingsContent.dock`: `right` → `left`
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
Instead of manually handing hiding the cursor on keyboard input at the
editor level, GPUI will now take care of it.
This makes it significantly easier to handle the edge cases, and allows
delegating the cursor restoration to the platform itself in the macOS
case. On Linux and Windows, we still have to restore the cursor on
movement ourselves, but this now happens at the platform-specific level.
Bugs fixed by this change:
- No cursor when "Unsaved edits" prompt appears
- Cursor disappears when clicking a panel button if it contains a search
bar (e.g. collab panel)
### Setting rename
The `hide_mouse` setting value `"on_typing_and_movement"` has been
renamed to `"on_typing_and_action"` to better reflect what it actually
does — it hides the cursor when a keystroke resolves to an action (e.g.
cursor movement, deletion). Existing settings are migrated
automatically.
### Tested platforms
- [x] macOS
- [x] Wayland
- [x] X11
- [x] Windows
- [x] Web
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:
- Renamed the `hide_mouse` setting value `on_typing_and_movement` to
`on_typing_and_action` to better describe its behavior (existing
settings are auto-migrated)
- Fixed a few situations where the mouse cursor would be incorrectly
hidden
cc: @danilo-leal
This setting is from when we had the git worktree picker in the agent
panel, now that it is in the menu bar it doesn't make sense to keep it.
We plan to add a similar feature in the future to handle the "new thread
== new git worktree" workflow
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 #ISSUE
Release Notes:
- N/A
Removes the Vercel v0 Provider, as the v0 API has been
depredated/removed (https://api.v0.dev/v1)
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:
- agent: Removed Vercel v0 provider as it has been deprecated by Vercel
These changes attempt to expand on the work introduced by
https://github.com/zed-industries/zed/pull/54778 by introducing a new
`GoToDefinitionScrollStrategy::Preserve` variant that attempts to keep
the cursor at the same vertical offset within the viewport when
navigating to a definition.
Most of the machinery for this was already in place. To support cases
where the user's scroll position isn't snapped to an exact display row,
for example, after scrolling with the mmouse, `Autoscroll::TopRelative`
and `Autoscroll::BottomRelative` were updated from `usize` to
`ScrollOffset`, allowing fractional offsets.
When the cursor is offscreen at the moment the `editor: go to
definition` action is invoked, `Preserve` falls back to
`Autoscroll::center`, matching the existing default for
`go_to_definition_scroll_strategy`. This avoids attempting to preserve
an offset where the cursor isn't visible which would lead to the cursor
being offscreen when jumping to the definition.
Documentation has also been updated to reflect this new strategy value.
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
Relates to #52173
Release Notes:
- Added a new `preserve` option to `go_to_definition_scroll_strategy`
that keeps the cursor at the same vertical position within the viewport
when navigating to a definition
Leftovers after https://github.com/zed-industries/zed/pull/53651
Updated models:
- **Zen**: GPT 5.5 and GPT 5.5 Pro - not tested because I don't have a
Zen subscription and I stubbornly refuse to get one
- **Go**: DeepSeek V4 Pro and DeepSeek V4 Flash - failing due to
https://github.com/anomalyco/opencode/issues/24224
- **Go**: MiMo V2.5 and MiMo V2.5 Pro - tested, confirmed working
- **Free**: Ling 2.6 Flash, [available for "a limited
time"](https://x.com/opencode/status/2046717718028513694) - tested,
confirmed working
- **Free**: Hy3 Preview, [available until May
8](https://x.com/opencode/status/2047328981435756824) - tested,
confirmed working
When testing the new models and comparing with OpenCode CLI, I realized
the
[variants](https://opencode.ai/docs/models/#built-in-variants)/thinking
effort configuration was not supported by the Zed Agent implementation.
I added that for OpenCode Go models, after manually checking what each
model supports in OpenCode. Reasoning levels and everything seems to
work (UI looks good, model works) but I have no idea how to specifically
test reasoning levels without doing a full benchmark 🤷
I did not add the same thing for OpenCode Zen models because I could not
figure out a way to get the supported variants.
@benbrandt let me know if you want me to take this out of this PR and to
keep just the model updates!
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:
- OpenCode: add new models (GPT 5.5, DeepSeek V4, MiMo V2.5, Ling 2.6,
Hy3)
- OpenCode Go: add support for configurable reasoning effort levels
---------
Co-authored-by: Ben Brandt <benjamin.j.brandt@gmail.com>
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 #ISSUE
Release Notes:
- N/A or Added/Fixed/Improved ...
