If the agent server supports it, we pass along the multiple directories.
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#54480
Release Notes:
- acp: External agents that support it now have access to all working
directories in a project.
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: Add Logout flow for agents that support it.
When the agent mentions a file path inside `backticks` (e.g. ``
`src/main.rs` `` or `` `src/main.rs:42` ``), the rendered code span now
becomes a clickable link in the agent panel. Clicking opens the
referenced file in the workspace, jumping to the right line and column
when present.
## How it works
- **Shared path resolution.** Extracted `OpenTarget` and the
workspace/worktree resolution logic out of
`terminal_view::terminal_path_like_target` into a new
`workspace::path_link` module so both the terminal and the agent panel
can use the same code. Includes a `sanitize_path_text` helper ported
from the terminal's URL/punctuation handling. Pure refactor — terminal
behavior is unchanged.
- **`markdown` crate hook.** Added
`MarkdownElement::on_code_span_link(callback)`. When the callback
returns `Some(url)` for a given code span's contents, the existing
`push_link` machinery wires up cmd-hover, hit testing, and the existing
`on_url_click` callback. When it returns `None`, the code span renders
as before. The hook is opt-in, so `markdown` stays workspace-agnostic.
- **Agent panel wiring.** `render_agent_markdown` constructs an
`AgentCodeSpanResolver` that snapshots the project's visible worktree
entries plus their file extensions. `try_resolve` does a cheap
synchronous heuristic check (path must contain `/`/`\` or end in an
extension present in the workspace, can't be a URL, can't be all digits,
etc.) and then looks the candidate up in the per-worktree
`HashSet<Arc<RelPath>>`. On a hit it returns a `MentionUri::File` or
`MentionUri::Selection` URI, which the existing `thread_view::open_link`
already knows how to open at the right line.
## Edge cases handled
- Code spans inside fenced code blocks stay plain (gated on
`builder.code_block_stack.is_empty()`, matching how regular markdown
links behave).
- Trailing prose punctuation (`` `src/main.rs.` ``) is stripped before
lookup.
- Identifiers like `` `String` ``, `` `await` ``, `` `npm run dev` ``
stay plain — they don't pass the path-like heuristic.
- Cross-platform path separators handled via the per-worktree
`PathStyle`.
## Tests
- `crates/markdown` — unit test asserting code spans become links when
the callback returns `Some`, and stay plain when it doesn't.
- `crates/agent_ui` — unit test for `AgentCodeSpanResolver::try_resolve`
covering hits with and without a `:line` suffix, misses, identifiers,
and trailing punctuation.
- Existing `terminal_view` tests cover the moved resolution code
(unchanged behavior).
## Notes
- There's currently a temporary `log::info!` in
`AgentCodeSpanResolver::try_resolve` that reports per-call worktree-walk
timing and a cumulative total. Kept in for now to verify the feature
isn't being called excessively during streaming renders. Can be removed
before merge.
- Resolution is sync-only against worktree entries; absolute paths
outside the workspace are not resolved (would require an async re-render
path).
Closes AI-277
Release Notes:
- Made file paths in `backticks` clickable in the agent panel; clicking
opens the referenced file at the given line when present.
Turns out we were creating an ImageDecoder on every frame (added in
#46167) when a tool returned an image as output, because we were trying
to get its dimensions. That is now cached on `ContentBlock::Image`.
Release Notes:
- N/A
Closes AI-266
This PR adds a built-in skill called `create-skill`, which allows the
Zed agent to have access to a skill that teaches it how to properly
create skills for Zed. You can manually invoke it as well as just
letting the model auto-invoke it in case your prompt suggests creating a
new skill.
Release Notes:
- Agent: Added a built-in skill called `create-skill` to make the Zed
agent informed about how to do that.
---------
Co-authored-by: Richard Feldman <richard@zed.dev>
Still behind a feature flag for now for testing with various agents.
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
Closes AI-261
This PR adds mention disambiguation in the agent panel, which works both
for regular @-mentions as well as for skills. Effectively, when you
mention files with the same name, the mention crease displays the next
path parent name, following a similar approach to common tabs in the
editor. For skills, the skill source is displayed (either global or from
some project).
<img width="500" alt="Screenshot 2026-05-15 at 6 32@2x"
src="https://github.com/user-attachments/assets/72c99480-cf32-42ac-9304-3f65167a1d94"
/>
Release Notes:
- Agent: Improved file and skill mention disambiguation in the agent
panel.
---------
Co-authored-by: Richard Feldman <richard@zed.dev>
Behind feature flag until we move RFD forward, but already working great
on codex
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
---------
Co-authored-by: zed-zippy[bot] <234243425+zed-zippy[bot]@users.noreply.github.com>
Still behind a flag until RFD progresses. But also fixes one area where
we would have called delete even if we didn't have support.
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
Closes AI-230
This PR makes skills, added as /-mentions, be rendered in the agent
panel as creases, like anything you'd @-mention. Naturally, clicking on
the crease button opens the corresponding skill file in a buffer.
It turned out to be quite a bit of plumbing to make this work,
particularly as I am also introducing an interface to display dividers
and headers in the completion menu. This was relevant to me to add
because it sets a good foundation to convert many agent panel-related
actions as slash commands.
Release Notes:
- N/A
---------
Co-authored-by: MartinYe1234 <52641447+MartinYe1234@users.noreply.github.com>
Makes it so that "Restore checkpoint" shows up as soon as the model
performs an edit, instead of waiting until the turn ends
Release Notes:
- Fixed the agent panel to show "Restore checkpoint" as soon as the
agent starts editing instead of waiting until the turn ends
Treat `.agents/skills/` (project-local) and `~/.agents/skills/` (global)
as **sensitive paths**, on par with `.zed/` and the global config
directory. The agent's built-in editing tools (`edit_file`,
`write_file`, `create_directory`, `delete_path`, `move_path`,
`copy_path`) now require explicit user authorization before modifying
anything inside those paths, because the contents of skill files control
agent behavior.
This protection is worth landing on its own, ahead of Zed adding its own
skills support: other agents (e.g. Claude Code) already write skill
files into these locations, so a Zed installation may already have
skills on disk that should not be silently editable by the agent.
Also tightens the **pre-existing `.zed/` check** to compare path
components case-insensitively. macOS and Windows use case-insensitive
filesystems by default, so without this fix a malicious settings author
could bypass the local-settings classifier with `.ZED/settings.json`
(the canonicalized inode would match, but the path-component comparison
would miss it). The new `.agents/skills/` check has the same hazard and
now shares a single `component_matches_ignore_ascii_case` helper with
the `.zed/` check.
Introduces the `agent_skills` crate, scoped for now to just the path
constants and helpers (`global_skills_dir`,
`project_skills_relative_path`, `SKILL_FILE_NAME`) so the
tool-permission machinery can recognize the agent skills tree without
depending on a skill discovery / parsing / loading layer. Those will
land in follow-up PRs.
Closes AI-217
Release Notes:
- Agent: Require user confirmation before letting tools modify files
inside `.agents/skills/` (per-project) or `~/.agents/skills/` (global),
so skills installed by any agent are protected from unsolicited edits
---------
Co-authored-by: MartinYe1234 <52641447+MartinYe1234@users.noreply.github.com>
Co-authored-by: Martin Ye <martinye022@gmail.com>
Co-authored-by: Danilo Leal <daniloleal09@gmail.com>
Before:
1. Agent tries to edit unsaved file
2. Tool call fails with error telling the agent to ask the user to save
or discard edits
3. User types save/restore
4. Agent uses save/restore tool
https://github.com/user-attachments/assets/c94dd361-e8e0-48ee-be31-da8afe594419
After:
1. Agent tries to edit unsaved file
2. User is prompted to save/restore file
3. User accepts/rejects or saves/discards file manually
https://github.com/user-attachments/assets/1d98a0c4-4420-4426-94f2-42355de230be
Release Notes:
- agent: Improved UX when agent tries to edit unsaved buffer
---------
Co-authored-by: Ben Brandt <benjamin.j.brandt@gmail.com>
`AcpThread::status` is purely `running_turn.is_some()`. The cleanup that
takes `running_turn` sat below the early-return guard that fires when
the prompt response oneshot resolves to `Err(Cancelled)` (the inner
`send_task` was dropped before `tx.send`). Any code path that drops the
in-flight `send_task` therefore left the panel stuck in `Generating`.
Reordered so cleanup runs before the dropped-tx guard; the same-turn
invariant is preserved.
Related to #47928 (partial — that issue also has an upstream
`claude-agent-acp` component this PR does not address).
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 agent panel staying in a generating state when the underlying
prompt task was cancelled before completing
Store the ACP agent version from agent_info and expose it
through AgentConnection so the configuration UI can display it
for connected agents.
Helpful when debugging to know which version is currently running.
<img width="214" height="67" alt="image"
src="https://github.com/user-attachments/assets/4f4c0e3c-a621-48fb-98d4-67329db1e62a"
/>
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:
- acp: Show running agent version in the External Agent settings
We had a regression where the labels were being rendered as markdown,
which is usually not what you want on a command
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:
- N/A
Previously, we weren't waiting on the status future early enough so we
would just hang if we weren't able to start the agent process.
I also added the recent stderr logs in there to help the user debug the
issue, since it is likely relevant in these cases.
<img width="902" height="226" alt="image"
src="https://github.com/user-attachments/assets/204e42ff-4c9b-49e7-8a6d-ecf7b022fbd0"
/>
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: Improve error messages if the ACP agent fails to start.
Sometimes the contents in the agent's thread are direct file links.
Codex ACP almost every time uses absolute file paths instead of
file://path/to/file. This is resulting in an error described in the
#49978 .
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#49978
Release Notes:
- Fixed absolute path mentions in `acp_thread` so direct file references
(including `:line` and `#Lline` formats) now open correctly instead of
resolving to invalid/empty files.
---------
Co-authored-by: Eric Holk <eric@zed.dev>
When the agent issued several parallel tool calls that all required
confirmation, clicking "Always for en.wikipedia.org" (or similar) on the
first prompt would persist the new rule to settings but leave the
sibling prompts stuck waiting on their own oneshot channels. The same
happened across subagents, and whenever the user edited settings.json by
hand while prompts were on screen.
`ToolCallEventStream::authorize()` now takes full ownership of the
permission decision. It evaluates the tool-permission settings up front,
and on Confirm it spawns a task that races the user's response against a
`SettingsStore` observer. When settings change, it re-runs the decision;
a new Allow or Deny drops the response receiver, flips the tool call
status to dismiss the prompt UI, and resolves the task without user
input. Subagents fall out of this for free since each thread observes
`SettingsStore` independently.
A few tools (`copy_path`, `move_path`, `delete_path`,
`create_directory`, `save_file`, `restore_file_from_disk`, and the
`edit-file` helper) sometimes need to prompt even when settings say
Allow — for example, edits that target `.zed/settings.json`. For those,
a new `authorize_always_prompt()` method skips the settings check and
always waits for user input; tools pick between the two at the call site
based on whether the path is sensitive.
Closes#54101.
Release Notes:
- In the agent panel, when you click "Always allow" for a tool, this
decision now gets propagated to other pending calls to the same tool.
Co-authored-by: Ben Brandt <benjamin.j.brandt@gmail.com>
Co-authored-by: Bennet Bo Fenner <bennetbo@gmx.de>
No, sadly, the title is not a typo. See
https://www.githubstatus.com/incidents/zsg1lk7w13cf for the context.
I'll read with joy and popcorn through that root cause analysis.
It makes literally zero sense what happened here, but for some completly
bonkers reason GitHub completely messed up the merge queue with
https://github.com/zed-industries/zed/pull/54632.
I have no idea how it happened. It makes literally zero sense. A PR
going into the merge queue should have the same LoC when getting out of
it. GitHub obviously does not check this. GitHub causes extra work with
a feature that is supposed to save time.
Thanks, I guess.
Release Notes:
- N/A
---------
Co-authored-by: Danilo Leal <daniloleal09@gmail.com>
This PR brings back the button to filter remote branches when accessing
the title bar's branch picker with the mouse. It was unintentionally
removed when we introduced the new worktree picker.
Release Notes:
- N/A
Fixes#53981
Selection mentions inserted from the agent panel are stored as folded
placeholder text in the message editor. That meant a normal copy would
put the literal `selection` token on the clipboard, and pasting into a
new thread would lose the original mention context.
This teaches `MessageEditor` to serialize selected folded mentions as
their mention links before writing to the clipboard. The surrounding
text stays intact, and the existing paste path can rebuild the mentions
in a fresh thread.
Release Notes:
- Fixed copied agent prompts replacing selection mentions with the
literal word `selection`.
---------
Co-authored-by: Neel <neel@zed.dev>
Testing out Niko's new SDK design
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
---------
Co-authored-by: Max Brunsfeld <maxbrunsfeld@gmail.com>
Adds initial beta test of ACP usage stats. Behind a flag for now while
we work on standardizing the usage values.
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
Follow up to #53850. #53850 fixed the panic, but had the side effect
that we would allow editing messages in the UI, even if the agent did
not support it.
Related #53735
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
The `user_message_id` parameter on `AgentConnection::prompt` was
`Option<UserMessageId>`, but `NativeAgentConnection::prompt` immediately
called `.expect()` on it, crashing when the value was `None`.
Because the `expect` message said `UserMessageId` was required, this PR
makes the parameter not optional which makes the panic impossible.
This means we also need to unconditionally generate an ID in `send`,
where before we gated this on whether `truncate` returned `Some`.
Generating IDs unconditionally should be find, especially because the
prompt requires them.
Release Notes:
- N/A
> **Foundation PRs:** #53732, #53733, #53734 — These three draft PRs
contain the base refactors (retained workspaces, agent panel overlay
split, ThreadId introduction) that this PR builds on.
## Goal
Remove `DraftId` and merge `draft_threads` + `background_threads` into a
single `retained_threads: HashMap<ThreadId, Entity<ConversationView>>`
in `AgentPanel`. A draft is just a thread that hasn't sent its first
message — no separate identity or storage needed.
## Changes
### agent_panel.rs
- Remove `DraftId` / `DraftIdCounter` / the `Global` impl
- Merge the two maps into `retained_threads`
- Add `thread_id: ThreadId` field to `BaseView::AgentThread`
- Rename methods: `create_draft` → `create_thread`, `activate_draft` →
`activate_retained_thread`, `remove_draft` → `remove_thread`, etc.
- Replace `clear_active_thread` with `show_or_create_empty_draft`
- Update `update_thread_work_dirs` to sync `ThreadMetadataStore` paths
when worktrees change
- Keep `load_agent_thread(...)` cleanup so activating a real thread
removes empty retained drafts
### sidebar.rs
- Remove `active_entry` derivation from `rebuild_contents` (was racing
with deferred effects)
- Add `sync_active_entry_from_panel` called from event handlers instead
- Simplify `ActiveEntry` — remove `ThreadActivation` struct, make
`session_id` optional
- Move `seen_thread_ids` to global scope (was per-group, causing
duplicate thread entries)
- Remove dead code: `clear_draft`, `render_draft_thread`
- Generalize `pending_remote_thread_activation` into
`pending_thread_activation` so all persisted-thread activations suppress
fallback draft reconciliation
- Set the activation guard before local persisted-thread activation
switches workspaces
- Make `reconcile_groups(...)` bail while a persisted-thread activation
is in flight
- On `ActiveViewChanged`, clear empty group drafts as soon as a pending
persisted-thread activation resolves
### thread_metadata_store.rs
- Make `ThreadMetadata.title` an `Option<SharedString>` with
`display_title()` fallback
- Add `update_worktree_paths` for batched path updates when project
worktrees change
### Other crates
- Update all `ThreadMetadata` construction sites and title display sites
across `agent_ui` and `sidebar`
## Fallback draft invariant
This PR now tightens the retained-thread invariant around fallback
drafts vs real thread activation/restoration:
- Fallback drafts are always empty
- User-created drafts worth preserving are non-empty
- While a persisted thread is being activated/restored/loaded, sidebar
reconciliation must not create an empty fallback draft for that target
group/workspace
- Once the real thread becomes active, empty fallback drafts in that
target group are removed
This is enforced by the sidebar-side activation guard plus existing
`AgentPanel` empty-draft cleanup after real-thread load.
## Tests
Added and/or kept focused sidebar regression coverage for:
-
`test_confirm_on_historical_thread_in_new_project_group_opens_real_thread`
-
`test_unarchive_into_inactive_existing_workspace_does_not_leave_active_draft`
-
`test_unarchive_after_removing_parent_project_group_restores_real_thread`
- `test_pending_thread_activation_suppresses_reconcile_draft_creation`
Focused test runs:
- `cargo test -p sidebar activate_archived_thread -- --nocapture`
- `cargo test -p sidebar unarchive -- --nocapture`
- `cargo test -p sidebar archive_last_thread_on_linked_worktree --
--nocapture`
- `cargo test -p sidebar
test_confirm_on_historical_thread_in_new_project_group_opens_real_thread
-- --nocapture`
- `cargo test -p sidebar
test_unarchive_into_inactive_existing_workspace_does_not_leave_active_draft
-- --nocapture`
- `cargo test -p sidebar
test_unarchive_after_removing_parent_project_group_restores_real_thread
-- --nocapture`
- `cargo test -p sidebar
test_pending_thread_activation_suppresses_reconcile_draft_creation --
--nocapture`
## Test fix
Fixed flaky `test_backfill_sets_kvp_flag` — added per-App `AppDatabase`
isolation in `setup_backfill_test` so backfill tests no longer share a
static in-memory DB.
Release Notes:
- N/A
---------
Co-authored-by: Mikayla Maki <mikayla.c.maki@gmail.com>
Co-authored-by: Mikayla Maki <mikayla@zed.dev>
Replaces raw provider error strings in the agent panel with specific,
user-friendly error callouts. Each error now has a clear title,
actionable copy, and appropriate buttons instead of the generic "An
Error Happened" fallback.
Error variants added:
Variant | Title | Body | Trigger |
|---|---|---|---|
| `RateLimitExceeded` | Rate Limit Reached | {Provider}'s rate limit was
reached. Zed will retry automatically. You can also wait a moment and
try again. | Provider rate limit exhausted after retries |
| `ServerOverloaded` | Provider Unavailable | {Provider}'s servers are
temporarily unavailable. Zed will retry automatically. If the problem
persists, check the provider's status page. | Provider server overloaded
or internal server error |
| `PromptTooLarge` | Context Too Large | This conversation is too long
for the model's context window. Start a new thread or remove some
attached files to continue. | Conversation exceeds model's context
window |
| `NoApiKey` | API Key Missing | No API key is configured for
{Provider}. Add your key via the Agent Panel settings to continue. | No
API key configured for a direct provider |
| `StreamError` | Connection Interrupted | The connection to
{Provider}'s API was interrupted. Zed will retry automatically. If the
problem persists, check your network connection. | Stream dropped or I/O
error during generation |
| `InvalidApiKey` | Invalid API Key | The API key for {Provider} is
invalid or has expired. Update your key via the Agent Panel settings to
continue. | API key present but invalid or expired |
| `PermissionDenied` | Permission Denied | {Provider}'s API rejected the
request due to insufficient permissions. Check that your API key has
access to this model. | API key lacks access to the requested model |
| `RequestFailed` | Request Failed | The request could not be completed
after multiple attempts. Try again in a moment. | Upstream provider
unreachable after retries |
| `MaxOutputTokens` | Output Limit Reached | The model stopped because
it reached its maximum output length. You can ask it to continue where
it left off. | Model hit its maximum output token budget |
| `NoModelSelected` | No Model Selected | Select a model from the model
picker below to get started. | No model configured when a message is
sent |
| `ApiError` | API Error | {Provider}'s API returned an unexpected
error. If the problem persists, try switching models or restarting Zed.
## Approach
- Added typed errors (`NoModelConfiguredError`, `MaxOutputTokensError`)
where previously raw strings were used, so they can be reliably downcast
- Extended `From<anyhow::Error> for ThreadError` to downcast
`LanguageModelCompletionError` variants before falling through to the
generic `Other` case
- Each variant has a dedicated `render_*` function with appropriate
buttons (retry icon, New Thread, or none)
- Telemetry events updated with specific `kind` labels for each new
variant
Release Notes:
- Improved error messages in the agent panel to show specific,
actionable copy instead of raw provider error strings
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)
- [n/a ] Tests cover the new/changed behavior
- [x] Performance impact has been considered and is acceptable
Release Notes:
Improved error messages in the agent panel to show specific, actionable
copy instead of raw provider error strings
### Summary
Fixes duplicated Prompts/context in ACP threads after sending a message,
as reported in #53201.
### Root Cause
The thread already inserts the user prompt optimistically at send time.
If an ACP server also echoes UserMessageChunk updates for the same
prompt, the same content is appended again, which can duplicate rendered
context sections.
### Fix
Ignore echoed UserMessageChunk updates while a turn is actively running,
so user prompt content is not appended twice.
### Validation
- Reproduced with OpenCode ACP flow from the issue.
- Confirmed duplication appears after send (not in the input box).
- Confirmed duplicate Prompts/context no longer appears with the fix.
### Video
[Screencast from 2026-04-06
08-21-32.webm](https://github.com/user-attachments/assets/33075312-9af7-4dd5-a2a3-5e1169b80243)
### 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#53201
## Release Notes
- Fixed duplicated Prompts/context in ACP conversations when servers
echo user message chunks after send.
We were incorrectly wrapping new terminal auth methods in double ssh
calls.
Only affected ACP beta users, but important for testing and stabilizing
the feature.
We moved the ssh wrapping to be only added in the acp process creation
where it was needed.
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
---------
Co-authored-by: Bennet Bo Fenner <bennetbo@gmx.de>
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
- [x] Tests cover the new/changed behavior
- [x] Performance impact has been considered and is acceptable
Closes#52239
## Summary
Note - The code in this fix is AI generated.
OpenCode ACP chats lost slash-command support after Zed restarted and a
thread was reopened. The UI no longer showed `/ for commands`, and slash
commands like `/help` were treated as unsupported.
## Root Cause
ACP available commands were treated as transient UI state instead of
durable thread state.
- `AcpThread` handled `AvailableCommandsUpdate` but did not retain the
commands on the thread
- restored thread views rebuilt `SessionCapabilities` with an empty
`available_commands` list
- the message-editor placeholder started in the wrong state for restored
threads
- live command updates could be applied to the wrong thread view
## Fix
- persisted `available_commands` on `AcpThread`
- restored `SessionCapabilities` from thread state
- reused the same command augmentation logic for restore and live update
paths
- updated live command handling to target the correct thread view
- initialized the message-editor placeholder from current command
availability
- added a regression test for the restore path
## Verification
- `cargo test -p agent_ui
conversation_view::tests::test_restored_threads_keep_available_commands
-- --exact --nocapture`
- `./script/clippy -p agent_ui --tests`
Release Notes:
- Fixed ACP slash commands disappearing after reopening restored
threads.
---------
Co-authored-by: Ben Brandt <benjamin.j.brandt@gmail.com>
This PR fixes an issue where an image mention would have its label reset
to just "Image", instead of persisting the original label, when the
prompt got submitted.
Closes#48564
Release Notes:
- agent: Fixed image mention labels by persisting the file name after
submitting the prompt
- agent: Fixed directory mentions being incorrectly parsed as files when
pasting into prompt editor
---------
Co-authored-by: Bennet Bo Fenner <bennetbo@gmx.de>
TODO:
- [x] merge main
- [x] nonshrinking `set_excerpts_for_path`
- [x] Test-drive potential problem areas in the app
- [x] prepare cloud side
- [x] test collaboration
- [ ] docstrings
- [ ] ???
## Context
### Background
Currently, a multibuffer consists of an arbitrary list of
anchor-delimited excerpts from individual buffers. Excerpt ranges for a
fixed buffer are permitted to overlap, and can appear in any order in
the multibuffer, possibly separated by excerpts from other buffers.
However, in practice all code that constructs multibuffers does so using
the APIs defined in the `path_key` submodule of the `multi_buffer` crate
(`set_excerpts_for_path` etc.) If you only use these APIs, the resulting
multibuffer will maintain the following invariants:
- All excerpts for the same buffer appear contiguously in the
multibuffer
- Excerpts for the same buffer cannot overlap
- Excerpts for the same buffer appear in order
- The placement of the excerpts for a specific buffer in the multibuffer
are determined by the `PathKey` passed to `set_excerpts_for_path`. There
is exactly one `PathKey` per buffer in the multibuffer
### Purpose of this PR
This PR changes the multibuffer so that the invariants maintained by the
`path_key` APIs *always* hold. It's no longer possible to construct a
multibuffer with overlapping excerpts, etc. The APIs that permitted
this, like `insert_excerpts_with_ids_after`, have been removed in favor
of the `path_key` suite.
The main upshot of this is that given a `text::Anchor` and a
multibuffer, it's possible to efficiently figure out the unique excerpt
that includes that anchor, if any:
```
impl MultiBufferSnapshot {
fn buffer_anchor_to_anchor(&self, anchor: text::Anchor) -> Option<multi_buffer::Anchor>;
}
```
And in the other direction, given a `multi_buffer::Anchor`, we can look
at its `text::Anchor` to locate the excerpt that contains it. That means
we don't need an `ExcerptId` to create or resolve
`multi_buffer::Anchor`, and in fact we can delete `ExcerptId` entirely,
so that excerpts no longer have any identity outside their
`Range<text::Anchor>`.
There are a large number of changes to `editor` and other downstream
crates as a result of removing `ExcerptId` and multibuffer APIs that
assumed it.
### Other changes
There are some other improvements that are not immediate consequences of
that big change, but helped make it smoother. Notably:
- The `buffer_id` field of `text::Anchor` is no longer optional.
`text::Anchor::{MIN, MAX}` have been removed in favor of
`min_for_buffer`, etc.
- `multi_buffer::Anchor` is now a three-variant enum (inlined slightly):
```
enum Anchor {
Min,
Excerpt {
text_anchor: text::Anchor,
path_key_index: PathKeyIndex,
diff_base_anchor: Option<text::Anchor>,
},
Max,
}
```
That means it's no longer possible to unconditionally access the
`text_anchor` field, which is good because most of the places that were
doing that were buggy for min/max! Instead, we have a new API that
correctly resolves min/max to the start of the first excerpt or the end
of the last excerpt:
```
impl MultiBufferSnapshot {
fn anchor_to_buffer_anchor(&self, anchor: multi_buffer::Anchor) -> Option<text::Anchor>;
}
```
- `MultiBufferExcerpt` has been removed in favor of a new
`map_excerpt_ranges` API directly on `MultiBufferSnapshot`.
## Self-Review Checklist
<!-- Check before requesting review: -->
- [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
---------
Co-authored-by: Conrad Irwin <conrad.irwin@gmail.com>
Co-authored-by: Piotr Osiewicz <24362066+osiewicz@users.noreply.github.com>
Co-authored-by: Jakub Konka <kubkon@jakubkonka.com>
Co-authored-by: Conrad <conrad@zed.dev>
🫡
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:
- Removed legacy Text Threads feature to help streamline the new agentic
workflows in Zed. Thanks to all of you who were enthusiastic Text Thread
users over the years ❤️!
---------
Co-authored-by: Bennet Bo Fenner <bennetbo@gmx.de>
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
---------
Co-authored-by: Gaauwe Rombouts <mail@grombouts.nl>
This PR changes things so that when the user mutates their current
project (e.g. adding a folder), the thread entries now update the
currently running threads to be pointing at this new set of folders.
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
TODO:
- [x] Manually test this case
Release Notes:
- N/A
When generation stops due to the per-response output limit, Zed was
surfacing "Max tokens reached", which implies the full context window
was exhausted. In reality, `max_output_tokens` (the per-response cap)
may have been hit a different condition.
This change distinguishes between the two cases: if `output_tokens >=
max_output_tokens`, it surfaces "Maximum output tokens reached";
otherwise it falls back to "Maximum tokens reached".
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
- [ ] Tests cover the new/changed behavior
- [x] Performance impact has been considered and is acceptable
Closes#50254
Note : Reopens#50372 suggested by @bennetbo
Release Notes:
- Fixed misleading "Max tokens reached" error by distinguishing between
per-response output token limit and total context window limit.
---------
Co-authored-by: Bennet Bo Fenner <bennetbo@gmx.de>
When a plan generate by the plan tool fully completes, there's no need
for that to be in the activity bar anymore. It's complete and in the
next turn, the agent may come up with another plan and the cycle
restarts. So, this PR moves a fully complete plan to the thread view, so
that it stays as part of a given turn:
<img width="600" height="1858" alt="image"
src="https://github.com/user-attachments/assets/43ad4eb0-49d0-488c-bbbf-ab7956c1dd5a"
/>
The way this PR does this is by adding a new entry to `AgentThreadEntry`
and snapshotting the completed plan so we can display it properly in the
thread.
Release Notes:
- N/A
## Context
This PR adds a button to remove the plan UI, if the user wants.
## Self-Review Checklist
<!-- Check before requesting review: -->
- [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
## Context
This test was bugging me, so I had claude take a look at it.
## Self-Review Checklist
<!-- Check before requesting review: -->
- [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
Many editors such as vim and emacs support "modelines", a comment at the
beginning of the file that allows the file type to be explicitly
specified along with per-file specific settings
- The amount of configurations, style and settings mapping cannot be
handled in one go, so this opens up a lot of potential improvements.
- I left out the possiblity to have "zed" specific modelines for now,
but this could be potentially interesting.
- Mapping the mode or filetype to zed language names isn't obvious
either. We may want to make it configurable.
This is my first contribution to zed, be kind. I struggled a bit to find
the right place to add those settings. I use a similar approach as done
with editorconfig (merge_with_editorconfig). There might be better ways.
Closes#4762
Release Notes:
- Add basic emacs/vim modeline support.
Supersedes #41899, changes:
- limit reading to the first and last 1kb
- add documentation
- more variables handled
- add Arc around ModelineSettings to avoid extra cloning
- changed the way mode -> language mapping is done, thanks to
`modeline_aliases` language config
- drop vim ex: support
- made "Local Variables:" handling a separate commit, so we can drop it
easily
- various code style improvements
---------
Signed-off-by: Marc-André Lureau <marcandre.lureau@redhat.com>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Conrad Irwin <conrad.irwin@gmail.com>
Follow-up to the terminal permission params refactor, addressing
@benbrandt's [review
feedback](https://github.com/zed-industries/zed/pull/51782#pullrequestreview-2926899804)
about string formatting leaking into the UI layer.
## Changes
### Outcome construction moved to acp_thread
- Added `PermissionOptionChoice::build_outcome(is_allow)` — builds a
`SelectedPermissionOutcome` from a choice, attaching
`SelectedPermissionParams::Terminal` when the choice carries
`sub_patterns`.
- Added
`PermissionOptions::build_outcome_for_checked_patterns(checked_indices,
is_allow)` — handles the `DropdownWithPatterns` per-command checklist
flow, returning `None` when zero patterns are checked (degrading to
once).
The UI's `authorize_with_granularity` no longer does any
`format!("always_allow:{}",...)` string formatting or
`SelectedPermissionParams` construction.
### `option_kind` folded into `SelectedPermissionOutcome`
`SelectedPermissionOutcome` now carries `option_kind:
acp::PermissionOptionKind`, eliminating the separate parameter that was
threaded through the entire `authorize_tool_call` chain:
```
ThreadView::authorize_tool_call
→ Conversation::authorize_tool_call
→ AcpThread::authorize_tool_call
```
Every signature in this chain dropped one parameter.
### `SelectedPermissionParams` removed from UI imports
The type is now only referenced by `acp_thread` (construction) and
`agent` (consumption). The UI passes `SelectedPermissionOutcome`
opaquely.
Release Notes:
- N/A
## Context
We were seeing some off by one errors because we weren't counting in
progress as either pending or completed.
Release Notes:
- acp: Fix plan stats showing all tasks as done when items were still in
progress.
## Context
If you went back and edited the first message, we were resetting the
provisional title, even though the title had previously already been set
from a summarization pass.
In order to achieve this, we moved the default thread title logic up the
UI layer, and allowed AcpThreads to have an optional title.
## Self-Review Checklist
<!-- Check before requesting review: -->
- [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
---------
Co-authored-by: Bennet Bo Fenner <bennetbo@gmx.de>
## Summary
Adds a new permission UI for terminal pipeline commands (e.g. `cargo
test | tail`) that lets users selectively always-allow individual
commands in the pipeline, rather than only offering a blanket
always-allow for the first command.
## Screenshot
<img width="464" height="293" alt="Screenshot 2026-03-18 at 3 27 48 PM"
src="https://github.com/user-attachments/assets/e027eeec-c2b3-4f73-a596-95f42a9adad2"
/>
Release notes:
- The terminal permissions UI now allows you to select individual
subcommands independently.
---------
Co-authored-by: Danilo Leal <daniloleal09@gmail.com>
Co-authored-by: Ben Brandt <benjamin.j.brandt@gmail.com>
## Context
Previously we were very eagerly dropping threads from memory. However,
reloading threads has a cost:
- For our agent, we have to replay events, which is lossy
- It's slower for external agents
- Some agents don't support reloading
So we keep the most recent 5 idle threads (or all threads who can't be
reloaded) and clean up our list after every insertion.
## Self-Review Checklist
<!-- Check before requesting review: -->
- [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:
- N/A
---------
Co-authored-by: Bennet Bo Fenner <bennetbo@gmx.de>
