| Commit message (Collapse) | Author |
|---|
|
|
|
|
|
Adds client-side tool execution to Atuin AI, starting with
`atuin_history`. The server can request tool calls, which are executed
locally with a permission system, and results are sent back to continue
the conversation.
|
|
This PR refines the system created in #3178 to be suitable for a v1
release.
---
## Overview
`atuin-ai` is a separate binary that allows for generating commands and
asking questions from the command line.
It is fully opt-in.
## Usage
`atuin ai init` will output bindings for your shell. Currently, bash,
zsh, and fish are supported.
```bash
eval "$(atuin ai init)"
```
Once the hooks are installed, just press `?` on an empty prompt line to
call up the TUI.
`atuin ai` requires an account on [Atuin Hub](https://hub.atuin.sh/);
you will be prompted to log in on first use.
## Features
### Command generation
Prompt the LLM to create a command, and get one back, no fuss. Press
`enter` to run, or `tab` to insert.
```
┌Ask questions or generate a command:──────────────────────────┐
│ │
│ > Get a list of running docker containers │
│ │
├──────────────────────────────────────────────────────────────┤
│ │
│ $ docker ps │
│ │
└────[Enter]: Run [Tab]: Insert [f]: Follow-up [Esc]: Cancel┘
```
### Follow-up
You can follow-up with `f` to specify a refinement prompt to update the
command that will be inserted.
```
┌Ask questions or generate a command:──────────────────────────┐
│ │
│ > Get a list of running docker containers │
│ │
├──────────────────────────────────────────────────────────────┤
│ │
│ $ docker ps │
│ │
├──────────────────────────────────────────────────────────────┤
│ │
│ > Actually I want to get all docker containers │
│ │
├──────────────────────────────────────────────────────────────┤
│ │
│ $ docker ps -a │
│ │
└────[Enter]: Run [Tab]: Insert [f]: Follow-up [Esc]: Cancel┘
```
You can also follow-up with questions to get responses in natural
language.
```
┌Ask questions or generate a command:──────────────────────────┐
│ │
│ > Get a list of running docker containers │
│ │
├──────────────────────────────────────────────────────────────┤
│ │
│ $ docker ps │
│ │
├──────────────────────────────────────────────────────────────┤
│ │
│ > Actually I want to get all docker containers │
│ │
├──────────────────────────────────────────────────────────────┤
│ │
│ $ docker ps -a │
│ │
├──────────────────────────────────────────────────────────────┤
│ │
│ > What other useful flags to `docker ps` should I know? │
│ │
├──────────────────────────────────────────────────────────────┤
│ │
│ Here are some handy `docker ps` flags: │
│ │
│ - `-q` — Only show container IDs (great for piping to │
│ other commands) │
│ - `-s` — Show container sizes │
│ - `-n 5` — Show the last 5 created containers │
│ - `-l` — Show only the latest created container │
│ - `--no-trunc` — Don't truncate output (shows full IDs and │
│ commands) │
│ - `-f` or `--filter` — Filter by condition, e.g.: │
│ - `-f status=exited` — only exited containers │
│ - `-f name=myapp` — filter by name │
│ - `-f ancestor=nginx` — filter by image │
│ - `--format` — Custom output using Go templates, e.g.: │
│ `--format "table {{.Names}}\t{{.Status}}\t{{.Ports}}"` │
│ │
│ A common combo is `docker ps -aq` to get all container │
│ IDs, useful for bulk operations like `docker rm $(docker │
│ ps -aq)`. │
│ │
└────[Enter]: Run [Tab]: Insert [f]: Follow-up [Esc]: Cancel┘
```
You can use `enter` or `tab` at any time to run or insert the last
suggested command, even if it was suggested in a previous turn.
### Conversational and search usage
If you prompt the LLM with a question that doesn't imply you want to
generate a command, it can respond in natural language, and use web
search if necessary to fetch the data it needs.
```
┌Ask questions or generate a command:──────────────────────────┐
│ │
│ > What is the latest version of atuin? │
│ │
├──────────────────────────────────────────────────────────────┤
│ │
│ ✓ Used 2 tools │
│ │
│ The latest version of Atuin is **v18.12.0**, available on │
│ the [GitHub releases │
│ page](https://github.com/atuinsh/atuin/releases). │
│ │
└─────────────────────────────────[f]: Follow-up [Esc]: Cancel┘
```
### Dangerous or low-confidence command detection
The LLM scores its confidence in the command, as well as how dangerous
the command is. This information is shown if a threshold is exceeded,
and requires an extra confirmation step before running automatically
with `enter`.
The Atuin Hub server also monitors suggested commands for dangerous
patterns the LLM didn't catch, and appends its own assessment at the end
of the LLM's own assessment.
```
┌Ask questions or generate a command:──────────────────────────┐
│ │
│ > Delete all files from $HOME │
│ │
├──────────────────────────────────────────────────────────────┤
│ │
│ $ rm -rf $HOME/* │
│ │
│ ! ⚠️ This will PERMANENTLY delete ALL files and directories │
│ in your home directory, including documents, downloads, │
│ configurations, SSH keys, and everything else. This is │
│ irreversible and will likely break your system. Also note │
│ this won't delete hidden (dot) files — if you want those │
│ too, that's even more destructive.; [Server] Recursive │
│ delete of critical directory │
│ │
└────[Enter]: Run [Tab]: Insert [f]: Follow-up [Esc]: Cancel┘
```
---------
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
|
|
* Move db_uri setting to DbSettings
* WIP: sqlite crate framework
* WIP: Migrations
* WIP: sqlite implementation
* Add sqlite3 to Docker image
* verified_at needed for user query
* chore(deps): bump debian (#2772)
Bumps debian from bookworm-20250428-slim to bookworm-20250520-slim.
---
updated-dependencies:
- dependency-name: debian
dependency-version: bookworm-20250520-slim
dependency-type: direct:production
...
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
* fix(doctor): mention the required ble.sh version (#2774)
References:
https://forum.atuin.sh/t/1047
* fix: Don't print errors in `zsh_autosuggest` helper (#2780)
Previously, this would result in long multi-line errors when typing,
making it hard to see the shell prompt:
```
$ Error: could not load client settings
Caused by:
0: could not create config file
1: failed to create file `/home/jyn/.config/atuin/config.toml`
2: Required key not available (os error 126)
Location:
atuin-client/src/settings.rs:675:54
fError: could not load client settings
Caused by:
0: could not create config file
1: failed to create file `/home/jyn/.config/atuin/config.toml`
2: Required key not available (os error 126)
Location:
atuin-client/src/settings.rs:675:54
faError: could not load client settings
```
Silence these in autosuggestions, such that they only show up when
explicitly invoking atuin.
* fix: `atuin.nu` enchancements (#2778)
* PR feedback
* Remove sqlite3 package
* fix(search): prevent panic on malformed format strings (#2776) (#2777)
* fix(search): prevent panic on malformed format strings (#2776)
- Wrap format operations in panic catcher for graceful error handling
- Improve error messages with context-aware guidance for common issues
- Let runtime-format parser handle validation to avoid blocking valid formats
Fixes crash when using malformed format strings by catching formatting
errors gracefully and providing actionable guidance without restricting
legitimate format patterns like {command} or {time}.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
* Satisfy cargo fmt
* test(search): add regression tests for format string panic (#2776)
- Add test for malformed JSON format strings that previously caused panics
- Add test to ensure valid format strings continue to work
- Prevent future regressions of the format string panic issue
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
---------
Co-authored-by: Claude <noreply@anthropic.com>
---------
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Koichi Murase <myoga.murase@gmail.com>
Co-authored-by: jyn <github@jyn.dev>
Co-authored-by: Tyarel8 <98483313+Tyarel8@users.noreply.github.com>
Co-authored-by: Brian Cosgrove <cosgroveb@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>
|
|
* chore: ignore .envrc
* fix(history): Check passed exit param instead of not-yet set h.exit
|
|
* init daemon crate
* wip
* minimal functioning daemon, needs cleanup for sure
* better errors
* add signal cleanup
* logging
* things
* add sync worker
* move daemon crate
* 30s -> 5mins
* make clippy happy
* fix stuff maybe?
* fmt
* trim packages
* rate limit fix
* more protoc huh
* this makes no sense, why linux why
* can it install literally just curl
* windows in ci is slow, and all the newer things will not work there. disable the daemon feature and it will build
* add daemon feature
* maybe this
* ok wut where is protoc
* try setting protoc
* hm
* try copying protoc
* remove optional
* add cross config
* idk nix
* does nix want this?
* some random pkg I found does this
* uh oh
* hack, be gone!
* update contributing
|
|
* feat: rework record sync for improved reliability
So, to tell a story
1. We introduced the record sync, intended to be the new algorithm to
sync history.
2. On top of this, I added the KV store. This was intended as a simple
test of the record sync, and to see if people wanted that sort of
functionality
3. History remained syncing via the old means, as while it had issues it
worked more-or-less OK. And we are aware of its flaws
4. If KV syncing worked ok, history would be moved across
KV syncing ran ok for 6mo or so, so I started to move across history.
For several weeks, I ran a local fork of Atuin + the server that synced
via records instead.
The record store maintained ordering via a linked list, which was a
mistake. It performed well in testing, but was really difficult to debug
and reason about. So when a few small sync issues occured, they took an
extremely long time to debug.
This PR is huge, which I regret. It involves replacing the "parent"
relationship that records once had (pointing to the previous record)
with a simple index (generally referred to as idx). This also means we
had to change the recordindex, which referenced "tails". Tails were the
last item in the chain.
Now that we use an "array" vs linked list, that logic was also replaced.
And is much simpler :D
Same for the queries that act on this data.
----
This isn't final - we still need to add
1. Proper server/client error handling, which has been lacking for a
while
2. The actual history implementation on top
This exists in a branch, just without deletions. Won't be much to
add that, I just don't want to make this any larger than it already
is
The _only_ caveat here is that we basically lose data synced via the old
record store. This is the KV data from before.
It hasn't been deleted or anything, just no longer hooked up. So it's
totally possible to write a migration script. I just need to do that.
* update .gitignore
* use correct endpoint
* fix for stores with length of 1
* use create/delete enum for history store
* lint, remove unneeded host_id
* remove prints
* add command to import old history
* add enable/disable switch for record sync
* add record sync to auto sync
* satisfy the almighty clippy
* remove file that I did not mean to commit
* feedback
|
|
|
|
* stat command parsing is handled without subcommands
* Updates match clause based on PR review
Co-authored-by: Conrad Ludgate <oon@conradludgate.com>
* updates value returned by match based on PR review
* adds vscode to gitignore
* use an if statement instead of match
Co-authored-by: Satyarth <satyarth.sampath@gojek.com>
Co-authored-by: Conrad Ludgate <oon@conradludgate.com>
|
|
* Translate config.md to russian
* Translate docs/import_ru.md to russian
* Translate docs/key-binding.md to russian
* Translate docs/list_ru.md to russian
* Correct misprint in config_ru.md
* Translate docs/search.md to russian
* Translate docs/server_ru.md to russian
* Translate docs/shell-completions.md to russian
* Translate docs/stats.md to russian
* Translate docs/sync.md to russian
* Add .idea/ to .gitignore
* Translated files are placed in a separate folder
* Correct misprint (~~истоии~~ => истории). Correct links between files
Co-authored-by: BigProject404 <bigproject404@yandex.ru>
|
|
* ignore JB IDEs
* tidy-up imports
* add rustfmt config
|
|
* Switch to Cargo workspaces
Breaking things into "client", "server" and "common" makes managing the
codebase much easier!
client - anything running on a user's machine for adding history
server - handles storing/syncing history and running a HTTP server
common - request/response API definitions, common utils, etc
* Update dockerfile
|
|
|
