Closes https://github.com/zed-industries/zed/issues/57992
Closes AI-349
## Summary
- Run rules-to-skills migration during agent UI init instead of waiting
for feature flags in production.
- Add a command palette action to rerun the migration manually.
- Make AGENTS.md migration appends idempotent to avoid duplicated
default-rule prompts.
Release Notes:
- Added a manual way to trigger the Rules to Skills migration
## Summary
- Track existing skill file contents and instruction bodies before
migrating Rules to Skills
- Skip writing migrated skills when an equivalent skill already exists
- Cover duplicate detection across differently named skills
## Tests
- cargo test -p prompt_store rules_to_skills_migration
Release Notes:
- Fixed duplicate Skills being created when migrating Rules.
Closes AI-244
This PR changes the approach for announcing skills support. It uses the
announcement toast, the same thing used for parallel agents, which
observes a specific version number to be displayed. I ended up
simplifying things a bit by thinking we could rely on documentation for
more detailed information (with more extensive paths and whatnot).
Release Notes:
- N/A
---------
Co-authored-by: Richard Feldman <richard@zed.dev>
Co-authored-by: MartinYe1234 <52641447+MartinYe1234@users.noreply.github.com>
Co-authored-by: Martin Ye <martinye022@gmail.com>
Removes the `skills` feature flag now that Skills are ready to ship to
all users. Cleans up all `cx.has_flag::<SkillsFeatureFlag>()` gates
across the agent, agent_ui, prompt_store, and title_bar crates, drops
the now-unused `feature_flags` dependency from `prompt_store` and
`title_bar`, and removes the dead `update_flags(true, vec!["skills"])`
calls from the agent's skills tests.
Closes AI-269
Release Notes:
- Enabled Skills for all users.
---------
Co-authored-by: MartinYe1234 <52641447+MartinYe1234@users.noreply.github.com>
Co-authored-by: Martin Ye <martinye022@gmail.com>
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>
Adds a one-time, idempotent startup migration that moves every user Rule
out of the `PromptStore` LMDB database into the new Skills + AGENTS.md
world, in a single pass:
- **Non-Default Rules → global Skills.** Each one becomes
`~/.agents/skills/<slug>/SKILL.md` with `disable-model-invocation:
true`, preserving the original behavior that non-Default Rules were only
ever invoked when the user named them. They're now invokable via
`/skill-name` (and still `@`-mentions).
- **Default Rules → global AGENTS.md.** Each one is appended to
`paths::agents_file()` (e.g. `~/.config/zed/AGENTS.md` on macOS/Linux,
`%APPDATA%\Zed\AGENTS.md` on Windows) under an `## H2` heading
containing the rule's title. Default Rules used to be auto-included in
every conversation; the global AGENTS.md is loaded into the system
prompt of every conversation, so the behavior is preserved.
- **Customized built-in prompts → global AGENTS.md** (currently just the
commit-message prompt). If the user has edited a built-in away from
Zed's shipped `default_content()`, the edited body is appended at the
top of the AGENTS.md block. Uncustomized built-ins (still on the shipped
default) are skipped so we don't pollute AGENTS.md with text the user
never wrote.
The migration is gated on the `skills` feature flag — users without the
flag never have their Rules touched in any way. A single global KVP flag
(`rules_to_skills_migration_done`) short-circuits the migration on
subsequent launches, so it runs at most once per machine even across
release channels. A process-lifetime `AtomicBool` guard additionally
prevents racing duplicate spawns when the underlying `cx.on_flags_ready`
callback fires multiple times at startup.
Migration is intentionally non-destructive: rule rows in the LMDB
database stay in place. Users can still see and edit them through the
existing UI, and a downgrade to a Zed build without skills support won't
lose anything.
Slug generation (`agent_skills::slugify_skill_name`) lowercases ASCII
letters, turns spaces into dashes, and drops every other
non-alphanumeric character entirely — so `foo!bar` becomes `foobar`, not
`foo-bar`. `&` is special-cased to become `and` (so `rock&roll` →
`rock-and-roll`). Slug collisions and pre-existing skill directories are
handled by appending `-2`, `-3`, etc.
A title-bar onboarding banner ("Skills have replaced Rules") surfaces
for every user on the `skills` feature flag. Clicking it opens a small
`AlertModal`-based explainer that summarizes the two destinations and
points users at the new `/skill-name` slash command (and notes that
`@`-mentions still work).
Closes AI-227
Closes AI-232
Release Notes:
- N/A
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>
This reduces the size of Sharedstring from 32 bytes to 24 while also
allowing for small-string optimization, meaning strings with length < 23
bytes will not actually allocate.
Release Notes:
- N/A or Added/Fixed/Improved ...
## Context
This makes zed-agent prioritize rules files in the same order as is
described in the docs. My order of experience was
- saw in my zed agent thread `Using project "CLAUDE.md" file.
- went to settings to see if I can make it use `AGENTS.md` instead.
- went to [the docs](https://zed.dev/docs/ai/rules) where it specifies
that AGENTS.md is be picked over CLAUDE.md.
- went to source to see what went wrong
## How to Review
I'm changing the order of filenames in an array - the only two places
where the order matters is when picking which rules file to use. The
last place it's used with an `.iter().any()`.
## 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
- If you want the behavior tested I can, but I think it's equally hard
keeping docs and tests and docs and this codepath in sync.
- [x] Performance impact has been considered and is acceptable
Release Notes:
-Fixed agent rules files are prioritized as described in docs
## Summary
This PR extends the `always_allow` tool permission patterns to work with
Nushell, Elvish, and Rc shells. Previously, these shells were
incorrectly excluded because they don't use `&&`/`||` operators for
command chaining. However, brush-parser can safely parse their command
syntax since they all use `;` for sequential execution.
## Changes
- Add `ShellKind::Nushell`, `ShellKind::Elvish`, and `ShellKind::Rc` to
`supports_posix_chaining()`
- Split `ShellKind::Unknown` into `ShellKind::UnknownWindows` and
`ShellKind::UnknownUnix` to preserve platform-specific fallback behavior
while still denying `always_allow` patterns for unrecognized shells
- Add comprehensive tests for the new shell support
- Clarify documentation about shell compatibility
## Shell Notes
- **Nushell**: Uses `;` for sequential execution. The `and`/`or`
keywords are boolean operators on values, not command chaining.
- **Elvish**: Uses `;` to separate pipelines. Does not have `&&` or `||`
operators. Its `and`/`or` are special commands operating on values.
- **Rc (Plan 9)**: Uses `;` for sequential execution and `|` for piping.
Does not have `&&`/`||` operators.
## Security
Unknown shells still return `false` from `supports_posix_chaining()`, so
`always_allow` patterns are denied for safety when we can't verify the
shell's syntax.
(No release notes because granular tool permissions are still
feature-flagged.)
Release Notes:
- N/A
---------
Co-authored-by: Zed Zippy <234243425+zed-zippy[bot]@users.noreply.github.com>
Closes#40648
When deleting a prompt from the rules library, we now also delete it
from the legacy V1 database tables (if they exist). Previously, the V1
data would persist and get re-migrated on the next startup.
Release Notes:
- Fixed an issue where deleted rules from the rules library were getting
restored after a restart.
Also adjust the code for streaming tool use to always use a
rewrite_section; remove insert_here entirely.
Release Notes:
- N/A
Co-authored-by: Max Brunsfeld <maxbrunsfeld@gmail.com>
Relevant for Nightly Users only, follow up to #45004.
In case you use nightly this will break preview/stable since
deserialisation will fail. Shipping this to Nightly so that staff does
not run into this issue. We can revert this PR in the following days.
I'll make a follow up PR which only stores the prompt in the database in
case you customise it.
Release Notes:
- N/A
Closes#26823
Release Notes:
- Added support for customising the prompt used for generating commit
message in the rules library
---------
Co-authored-by: Danilo Leal <daniloleal09@gmail.com>
We've been considering removing workspace-hack for a couple reasons:
- Lukas ran into a situation where its build script seemed to be causing
spurious rebuilds. This seems more likely to be a cargo bug than an
issue with workspace-hack itself (given that it has an empty build
script), but we don't necessarily want to take the time to hunt that
down right now.
- Marshall mentioned hakari interacts poorly with automated crate
updates (in our case provided by rennovate) because you'd need to have
`cargo hakari generate && cargo hakari manage-deps` after their changes
and we prefer to not have actions that make commits.
Currently removing workspace-hack causes our workspace to grow from
~1700 to ~2000 crates being built (depending on platform), which is
mainly a problem when you're building the whole workspace or running
tests across the the normal and remote binaries (which is where
feature-unification nets us the most sharing). It doesn't impact
incremental times noticeably when you're just iterating on `-p zed`, and
we'll hopefully get these savings back in the future when
rust-lang/cargo#14774 (which re-implements the functionality of hakari)
is finished.
Release Notes:
- N/A
Closes#39614
The `ShellKind` struct is built on Windows' side, meaning that when
connecting to remotes, we fall back to PowerShell construction, even if
the shell program we are spawning is a unix program.
This broke tasks creation since we are using the shell kind to construct
args:
https://github.com/zed-industries/zed/blob/068bf1f7cc3da0eb00d7a4da86d27bb102b5c84b/crates/project/src/terminals.rs#L149
In normal terminals this only affected activation scripts (only place
where shell kind is used)
I don't have a Windows machine to test it, so I would appreciate any
help with testing!
Release Notes:
- Fixed an issue where tasks could not be executed in Windows WSL
---------
Signed-off-by: Marco Mihai Condrache <52580954+marcocondrache@users.noreply.github.com>
In the ACP changes, we changed how terminals are created for the agent,
and so the system prompt was putting in the system shell instead of the
default one, potentially causing confusion for the model.
These are now in sync, so this will hopefully alleviate issues people
were seeing, as well as use a more standard shell to increase the
likelihood of successful model tool calls.
Release Notes:
- agent: Align default shell path in system prompt with the actual path
it is given
Closes https://github.com/zed-industries/zed/issues/38690Closes#37353
### Background
On Windows, paths are normally separated by `\`, unlike mac and linux
where they are separated by `/`. When editing code in a project that
uses a different path style than your local system (e.g. remoting from
Windows to Linux, using WSL, and collaboration between windows and unix
users), the correct separator for a path may differ from the "native"
separator.
Previously, to work around this, Zed converted paths' separators in
numerous places. This was applied to both absolute and relative paths,
leading to incorrect conversions in some cases.
### Solution
Many code paths in Zed use paths that are *relative* to either a
worktree root or a git repository. This PR introduces a dedicated type
for these paths called `RelPath`, which stores the path in the same way
regardless of host platform, and offers `Path`-like manipulation APIs.
RelPath supports *displaying* the path using either separator, so that
we can display paths in a style that is determined at runtime based on
the current project.
The representation of absolute paths is left untouched, for now.
Absolute paths are different from relative paths because (except in
contexts where we know that the path refers to the local filesystem)
they should generally be treated as opaque strings. Currently we use a
mix of types for these paths (std::path::Path, String, SanitizedPath).
Release Notes:
- N/A
---------
Co-authored-by: Cole Miller <cole@zed.dev>
Co-authored-by: Piotr Osiewicz <24362066+osiewicz@users.noreply.github.com>
Co-authored-by: Peter Tripp <petertripp@gmail.com>
Co-authored-by: Smit Barmase <heysmitbarmase@gmail.com>
Co-authored-by: Lukas Wirth <me@lukaswirth.dev>
This removes around 900 unnecessary clones, ranging from cloning a few
ints all the way to large data structures and images.
A lot of these were fixed using `cargo clippy --fix --workspace
--all-targets`, however it often breaks other lints and needs to be run
again. This was then followed up with some manual fixing.
I understand this is a large diff, but all the changes are pretty
trivial. Rust is doing some heavy lifting here for us. Once I get it up
to speed with main, I'd appreciate this getting merged rather sooner
than later.
Release Notes:
- N/A
Some MCP servers expose tools that take absolute paths as arguments. To
interact with these, the agent needs to know the absolute path to the
project directories, not just their names. This PR changes the system
prompt to include the full path to each worktree, and updates some tool
descriptions to reflect this.
Todo:
* [x] Run evals, make sure assistant still understand how to specify
paths for tools, now that we include abs paths in the system prompt.
Release Notes:
- Improved the agent's ability to use MPC tools that require absolute
paths to files and directories in the project.
---------
Co-authored-by: Ben Brandt <benjamin.j.brandt@gmail.com>
https://github.com/zed-industries/zed/issues/30972 brought up another
case where our context is not enough to track the actual source of the
issue: we get a general top-level error without inner error.
The reason for this was `.ok_or_else(|| anyhow!("failed to read HEAD
SHA"))?; ` on the top level.
The PR finally reworks the way we use anyhow to reduce such issues (or
at least make it simpler to bubble them up later in a fix).
On top of that, uses a few more anyhow methods for better readability.
* `.ok_or_else(|| anyhow!("..."))`, `map_err` and other similar error
conversion/option reporting cases are replaced with `context` and
`with_context` calls
* in addition to that, various `anyhow!("failed to do ...")` are
stripped with `.context("Doing ...")` messages instead to remove the
parasitic `failed to` text
* `anyhow::ensure!` is used instead of `if ... { return Err(...); }`
calls
* `anyhow::bail!` is used instead of `return Err(anyhow!(...));`
Release Notes:
- N/A
This PR removes the code for the "Suggest Edits" functionality from
Assistant1.
This feature was already disabled entirely with the launch of the Agent,
we're just cleaning up the unused code.
Release Notes:
- N/A
This change updates the system prompt to conditionally include
`grep`-related instructions based on whether the `grep` tool is enabled.
Implementation details:
1. Add a `has_tool` handlebars helper.
2. Pass the `model` to all locations where the prompt is built.
3. Use `{{#if has_tool "grep"}}` in the system prompt to gate
`grep`-specific instructions.
Testing:
- Unit tests for the `hasTool` helper.
- Unit tests to verify that `grep`-related instructions are included /
omitted from the prompt as appropriate.
- Manual agent evaluation:
- Setup: Asked the Agent "List all impls of MyTrait in the project"
using a custom "No tools" profile (all tools disabled).
- Before the change: The Agent attempted to call `grep`, encountered an
error, then realized the tool was unavailable.
- After the change: The Agent immediately asked to enable a search tool.
Note: in principle, `grep`/`read_file` tool descriptions alone might be
enough, but to confirm this we need more evaluation. If it turns out to
be true, we'll be able to remove grep-specific instructions from the
system prompt and undo this change.
Release Notes:
- N/A
When using the agent with a project shared by a collaborator, rules file
loading didn't work as it was trying to read from the client's
filesystem
Release Notes:
- Fixed rules file loading when using the agent with a project shared by
a collaborator.
Simplifies the data structures involved in agent context by removing
caching and limiting the use of ContextId:
* `AssistantContext` enum is now like an ID / handle to context that
does not need to be updated. `ContextId` still exists but is only used
for generating unique `ElementId`.
* `ContextStore` has a `IndexMap<ContextSetEntry>`. Only need to keep a
`HashSet<ThreadId>` consistent with it. `ContextSetEntry` is a newtype
wrapper around `AssistantContext` which implements eq / hash on a subset
of fields.
* Thread `Message` directly stores its context.
Fixes the following bugs:
* If a context entry is removed from the strip and added again, it was
reincluded in the next message.
* Clicking file context in the thread that has been removed from the
context strip didn't jump to the file.
* Refresh of directory context didn't reflect added / removed files.
* Deleted directories would remain in the message editor context strip.
* Token counting requests didn't include image context.
* File, directory, and symbol context deduplication relied on
`ProjectPath` for identity, and so didn't handle renames.
* Symbol context line numbers didn't update when shifted
Known bugs (not fixed):
* Deleting a directory causes it to disappear from messages in threads.
Fixing this in a nice way is tricky. One easy fix is to store the
original path and show that on deletion. It's weird that deletion would
cause the name to "revert", though. Another possibility would be to
snapshot context metadata on add (ala `AddedContext`), and keep that
around despite deletion.
Release Notes:
- N/A
Now that we've established a proper eval in tree, this PR is reboots of
our agent loop back to a set of minimal tools and simpler prompts. We
should aim to get this branch feeling subjectively competitive with
what's on main and then merge it, and build from there.
Let's invest in our eval and use it to drive better performance of the
agent loop. How you can help: Pick an example, and then make the outcome
faster or better. It's fine to even use your own subjective judgment, as
our evaluation criteria likely need tuning as well at this point. Focus
on making the agent work better in your own subjective experience first.
Let's focus on simple/practical improvements to make this thing work
better, then determine how we can craft our judgment criteria to lock
those improvements in.
Release Notes:
- N/A
---------
Co-authored-by: Max <max@zed.dev>
Co-authored-by: Antonio <antonio@zed.dev>
Co-authored-by: Agus <agus@zed.dev>
Co-authored-by: Richard <richard@zed.dev>
Co-authored-by: Max Brunsfeld <maxbrunsfeld@gmail.com>
Co-authored-by: Antonio Scandurra <me@as-cii.com>
Co-authored-by: Michael Sloan <mgsloan@gmail.com>
Related to #28490.
- Default prompts from the prompt library are now included as "user
rules" in the system prompt.
- Presence of these user rules is shown at the beginning of the thread
in the UI.
_ Now uses an `Entity<PromptStore>` instead of an `Arc<PromptStore>`.
Motivation for this is emitting a `PromptsUpdatedEvent`.
- Now disallows concurrent reloading of the system prompt. Before this
change it was possible for reloads to race.
Release Notes:
- agent: Added support for including default prompts from the Prompt
Library as "user rules" in the system prompt.
---------
Co-authored-by: Danilo Leal <daniloleal09@gmail.com>
Release Notes:
- Fixed a regression that caused the agent to hang sometimes.
---------
Co-authored-by: Thomas Mickley-Doyle <tmickleydoyle@gmail.com>
Co-authored-by: Nathan Sobo <nathan@zed.dev>
Co-authored-by: Michael Sloan <mgsloan@gmail.com>
