Dark-Alex-17/coyote
1
0
Fork 0
Code Issues Pull Requests Actions 9 Packages Projects Releases Wiki Activity

Compare commits

base: Dark-Alex-17/coyote:v0.5.0
Branches Tags
Dark-Alex-17/coyote:main Dark-Alex-17/coyote:skills Dark-Alex-17/coyote:develop Dark-Alex-17/coyote:graph-agents Dark-Alex-17/coyote:config-refactor Dark-Alex-17/coyote:restful-api-docs Dark-Alex-17/coyote:langchain
Dark-Alex-17/coyote:v0.7.3 Dark-Alex-17/coyote:v0.7.2 Dark-Alex-17/coyote:v0.7.1 Dark-Alex-17/coyote:v0.7.0 Dark-Alex-17/coyote:v0.6.0 Dark-Alex-17/coyote:v0.5.0 Dark-Alex-17/coyote:v0.4.0 Dark-Alex-17/coyote:v0.3.0 Dark-Alex-17/coyote:v0.2.0 Dark-Alex-17/coyote:v0.1.3 Dark-Alex-17/coyote:v0.1.2 Dark-Alex-17/coyote:v0.1.1
..
compare: Dark-Alex-17/coyote:langchain
Branches Tags
Dark-Alex-17/coyote:main Dark-Alex-17/coyote:skills Dark-Alex-17/coyote:develop Dark-Alex-17/coyote:graph-agents Dark-Alex-17/coyote:config-refactor Dark-Alex-17/coyote:restful-api-docs Dark-Alex-17/coyote:langchain
Dark-Alex-17/coyote:v0.7.3 Dark-Alex-17/coyote:v0.7.2 Dark-Alex-17/coyote:v0.7.1 Dark-Alex-17/coyote:v0.7.0 Dark-Alex-17/coyote:v0.6.0 Dark-Alex-17/coyote:v0.5.0 Dark-Alex-17/coyote:v0.4.0 Dark-Alex-17/coyote:v0.3.0 Dark-Alex-17/coyote:v0.2.0 Dark-Alex-17/coyote:v0.1.3 Dark-Alex-17/coyote:v0.1.2 Dark-Alex-17/coyote:v0.1.1

1 Commits
v0.5.0 .. langchain

Author SHA1 Message Date
Dark-Alex-17 139b5cc57e Sisyphus agent recreated in LangChain to figure out how it works and how to use it 2026-04-15 12:47:38 -06:00
219 changed files with 15277 additions and 26604 deletions
Expand all files Collapse all files
.github/ISSUE_TEMPLATE/bug_report.yaml
+13 -13
View File
@@ -21,25 +21,25 @@ body:
value: |
I tried this:
1. `coyote`
1. `loki`
I expected this to happen:
Instead, this happened:
- type: textarea
id: coyote-log
id: loki-log
attributes:
label: Coyote log
description: Include the Coyote log file to help diagnose the issue. (`coyote --info` to see the log_path)
label: Loki log
description: Include the Loki log file to help diagnose the issue. (`loki --info` to see the log_path)
value: |
| OS | Log file location |
| ------- | ----------------------------------------------------- |
| Linux | `~/.cache/coyote/coyote.log` |
| Mac | `~/Library/Logs/coyote/coyote.log` |
| Windows | `C:\Users\<User>\AppData\Local\coyote\coyote.log` |
| Linux | `~/.cache/loki/loki.log` |
| Mac | `~/Library/Logs/loki/loki.log` |
| Windows | `C:\Users\<User>\AppData\Local\loki\loki.log` |
```
please provide a copy of your coyote log file here if possible; you may need to redact some of the lines
please provide a copy of your loki log file here if possible; you may need to redact some of the lines
```
- type: input
@@ -57,13 +57,13 @@ body:
validations:
required: true
- type: input
id: coyote-version
id: loki-version
attributes:
label: Coyote Version
label: Loki Version
description: >
Coyote version (`coyote --version` if using a release, `git describe` if building
Loki version (`loki --version` if using a release, `git describe` if building
from main).
**Make sure that you are using the [latest coyote release](https://github.com/Dark-Alex-17/coyote/releases) or a newer main build**
placeholder: "coyote 0.1.0"
**Make sure that you are using the [latest loki release](https://github.com/Dark-Alex-17/loki/releases) or a newer main build**
placeholder: "loki 0.1.0"
validations:
required: true
.github/workflows/release.yaml
+14 -14
View File
@@ -98,9 +98,9 @@ jobs:
# Ignore Act's local artifact dir noise
echo artifacts/ >> .git/info/exclude || true
# Edit the version line right after name="coyote"
# Edit the version line right after name="loki"
sed -E -i '
/^[[:space:]]*name[[:space:]]*=[[:space:]]*"coyote"[[:space:]]*$/ {
/^[[:space:]]*name[[:space:]]*=[[:space:]]*"loki"[[:space:]]*$/ {
n
s|^[[:space:]]*version[[:space:]]*=[[:space:]]*"[^"]*"|version = "'"$VERSION"'"|
}
@@ -278,7 +278,7 @@ jobs:
- name: Verify file
shell: bash
run: |
file target/${{ matrix.target }}/release/coyote
file target/${{ matrix.target }}/release/loki
- name: Test
if: matrix.target != 'aarch64-apple-darwin' && matrix.target != 'aarch64-pc-windows-msvc'
@@ -382,11 +382,11 @@ jobs:
shell: bash
run: |
# Set environment variables
macos_sha="$(cat ./artifacts/coyote-x86_64-apple-darwin.sha256 | awk '{print $1}')"
macos_sha="$(cat ./artifacts/loki-x86_64-apple-darwin.sha256 | awk '{print $1}')"
echo "MACOS_SHA=$macos_sha" >> $GITHUB_ENV
macos_sha_arm="$(cat ./artifacts/coyote-aarch64-apple-darwin.sha256 | awk '{print $1}')"
macos_sha_arm="$(cat ./artifacts/loki-aarch64-apple-darwin.sha256 | awk '{print $1}')"
echo "MACOS_SHA_ARM=$macos_sha_arm" >> $GITHUB_ENV
linux_sha="$(cat ./artifacts/coyote-x86_64-unknown-linux-musl.sha256 | awk '{print $1}')"
linux_sha="$(cat ./artifacts/loki-x86_64-unknown-linux-musl.sha256 | awk '{print $1}')"
echo "LINUX_SHA=$linux_sha" >> $GITHUB_ENV
release_version="$(cat ./artifacts/release-version)"
echo "RELEASE_VERSION=$release_version" >> $GITHUB_ENV
@@ -402,23 +402,23 @@ jobs:
if: env.ACT != 'true'
run: |
# run packaging script
python "./deployment/homebrew/packager.py" ${{ env.RELEASE_VERSION }} "./deployment/homebrew/coyote.rb.template" "./coyote.rb" ${{ env.MACOS_SHA }} ${{ env.MACOS_SHA_ARM }} ${{ env.LINUX_SHA }}
python "./deployment/homebrew/packager.py" ${{ env.RELEASE_VERSION }} "./deployment/homebrew/loki.rb.template" "./loki.rb" ${{ env.MACOS_SHA }} ${{ env.MACOS_SHA_ARM }} ${{ env.LINUX_SHA }}
- name: Push changes to Homebrew tap
if: env.ACT != 'true'
env:
TOKEN: ${{ secrets.COYOTE_GITHUB_TOKEN }}
TOKEN: ${{ secrets.LOKI_GITHUB_TOKEN }}
run: |
# push to Git
git config --global user.name "Dark-Alex-17"
git config --global user.email "alex.j.tusa@gmail.com"
git clone https://Dark-Alex-17:${{ secrets.COYOTE_GITHUB_TOKEN }}@github.com/Dark-Alex-17/homebrew-coyote.git
rm homebrew-coyote/Formula/coyote.rb
cp coyote.rb homebrew-coyote/Formula
cd homebrew-coyote
git clone https://Dark-Alex-17:${{ secrets.LOKI_GITHUB_TOKEN }}@github.com/Dark-Alex-17/homebrew-loki.git
rm homebrew-loki/Formula/loki.rb
cp loki.rb homebrew-loki/Formula
cd homebrew-loki
git add .
git diff-index --quiet HEAD || git commit -am "Update formula for Coyote release ${{ env.RELEASE_VERSION }}"
git push https://$TOKEN@github.com/Dark-Alex-17/homebrew-coyote.git
git diff-index --quiet HEAD || git commit -am "Update formula for Loki release ${{ env.RELEASE_VERSION }}"
git push https://$TOKEN@github.com/Dark-Alex-17/homebrew-loki.git
publish-crate:
needs: publish-github-release
.gitignore
+1 -1
View File
@@ -3,5 +3,5 @@
/.env
!cli/**
.idea/
/coyote.iml
/loki.iml
/.idea/
CHANGELOG.md
+4 -115
View File
@@ -1,114 +1,3 @@
## v0.5.0 (2026-05-27)
### Feat
- rename Loki to Coyote
### Fix
- bash-based user interactions in agents accidentally regressed in graph implementation
- Claude function calling in agent contexts
- Claude code rate limit error per new Claude changes
## v0.4.0 (2026-05-23)
### Feat
- LLM node failures propgate up
- Added .install remote tab completions to the REPL
- feature complete install remote with category selection
- Support to interactively add secrets to Coyote that are missing from MCP configs when merging
- Added MCP config merging support for remote asset installations
- install remote now writes files to disk
- Created basic install_remote functions
- Created a more comprehensive and immediately useful default config for first runs
- Created an example graph-based agent called deep-research
- Improved coder agent that is now a graph-based agent
- Removed indicatif spinners. The UX just won't stop clobbering for parallel graph nodes
- Added agent variables support for graph agents and improved script executor to use the same environment variables as normal agent tool calling for further flexibility
- Improved UX with colored spinners for parallel graph agents and no clobbering outputs for sub-agents
- created new graph-based deep-research agent
- improved UX for parallel graph execution
- added branch progress tracker for better visualization of parallel graph super-steps
- Removed the jira-helper agent and replaced it with the atlassian role
- created the RenderMode enum to suppress stdout streaming during parallel graph super-steps
- Full support for map node types
- implemented the frontier-based scheduling for the graph executor with simplified state management (gotta love .clone)
- validation support for parallel graph execution; restricted map nodes to only run for nodes without next targets and not supporting chained map nodes
- created the staging area for state merges per super-step and created the built-in reducers (and their application) for the state merge phase of a super step
- scaffolding work for fan-out nodes for parallel branch execution support and stubbed out Map node types
- Coyote can now update itself via .update and --update commands
- added a .edit command for editing the MCP configuration file
- Created a new .install command to install bundled assets on-demand
- migrated llm node validation to graph loading time instead of graph runtime
- ripped out user input timeout scaffolding for approval and input node types; implementation can't be done cleanly
- added additional support for all RAG-configuration fields in RAG nodes
- initial support for RAG nodes in the graph execution system
- implemented structured logging for graph execution
- merged normal agent config and graph agent configs into one file (either/or)
- added structured-output extraction for llm and agent nodes
- created full llm node runtime implementation
- scaffolded together the initial llm node type and its executor
- wired together graph execution and agent graph dispatch
- implemented support for the graph executor
- created the approval node executor and the input node executor for user interaction
- Added initial support for native Coyote agent nodes in the graph-based agent system
- Added direct script invocation support for graph-based agents
- Added graph validation
- Implemented state management for agent graphs
- initial agent graph scaffolding
- add auto-continue support to all contexts
- dynamic tab completions now show the sessions for a given agent instead of only listing global sessions
- legacy SSE support for MCP server configurations
- support http/sse transport types for MCP server configurations so it fully supports claude desktop-style MCP configs
- 99% complete migration to new state structs to get away from God-Config struct; i.e. AppConfig, AppState, and RequestContext
- Automatic runtime customization using shebangs
- Created a demo TypeScript tool and a get_current_weather function in TypeScript
- Updated the Python demo tool to show all possible parameter types and variations
- Added TypeScript tool support using the refactored common ScriptedLanguage trait
### Fix
- Generified the functions usage of script detection for an executable bit on unix systems
- merge required claude code system prompt into instructions
- updated argc argument passing in run-tool and run-agent scripts
- Added additional graph validation for parallel reads and writes with dependencies between nodes states
- bug in next_single method and improved outcome handling for LLM node execution
- inline RAG bug when globbing files by extension without subdirectory globbing
- update the estimate_token_length function to use the standard word count method
- removed unnecessary regenerate logic for sessions and use the same logic for all contexts; prevents a panic on empty message list
- error when users try to start a session on a graph agent
- added on_other field for approval nodes so users can specify an alternative free-text target when none of the options match what they want
- accidentally added back in full agent tools on LLM nodes
- Improve the coder agent's usage of tools
- make the agent__collect escalation-aware so it doesn't freeze on sub-agent escalations
- check for an existing session before starting up MCP servers when switching to a role
- do not switch to agent if a session is active.
- Do not append todo instructions when function calling is disabled
- a bug in the dynamic completions because the crate name is coyote-ai but the binary is named coyote
- bug found by copilot that would create a lock on the PollSender for sse-based MCP servers
- Accidental shadow of temp_file function for Windows function calling
- upgraded to newer rmcp version to get native-tls support
- RagCache was not being used for agent and sub-agent instantiation
- TypeScript function args were being passed as objects rather than direct parameters
- Added in forgotten wrapper scripts for TypeScript tools
- don't shadow variables in binary path handling for Windows
- Tool call improvements for Windows systems
### Refactor
- migrated llm nodes to use Roles to simplify instructions handling and to function like inline roles
- migrated the next_node and apply_state_updates logic for LLM nodes into the LlmExecutor
- fully complete state re-architecting
- Fully ripped out the god Config struct
- Deprecated old Config struct initialization logic
- migrate functions and MCP servers to AppConfig
- Migrate the vault/bare_init logic
- created a single install_builtins free function to remove from Config::init
- partial migration to init in AppConfig
- Extracted common Python parser logic into a common.rs module
- python tools now use tree-sitter queries instead of AST
## v0.3.0 (2026-04-02)
### Feat
@@ -132,7 +21,7 @@
- Created a CodeRabbit-style code-reviewer agent
- Added configuration option in agents to indicate the timeout for user input before proceeding (defaults to 5 minutes)
- Added support for sub-agents to escalate user interaction requests from any depth to the parent agents for user interactions
- built-in user interaction tools to remove the need for the list/confirm/etc prompts in prompt tools and to enhance user interactions in Coyote
- built-in user interaction tools to remove the need for the list/confirm/etc prompts in prompt tools and to enhance user interactions in Loki
- Experimental update to sisyphus to use the new parallel agent spawning system
- Added an agent configuration property that allows auto-injecting sub-agent spawning instructions (when using the built-in sub-agent spawning system)
- Auto-dispatch support of sub-agents and support for the teammate pattern between subagents
@@ -186,7 +75,7 @@
- Simplified sisyphus prompt to improve functionality
- Supported the injection of RAG sources into the prompt, not just via the `.sources rag` command in the REPL so models can directly reference the documents that supported their responses
- Created the Sisyphus agent to make Coyote function like Claude Code, Gemini, Codex, etc.
- Created the Sisyphus agent to make Loki function like Claude Code, Gemini, Codex, etc.
- Created the Oracle agent to handle high-level architectural decisions and design questions about a given codebase
- Updated the coder agent to be much more task-focused and to be delegated to by Sisyphus
- Created the explore agent for exploring codebases to help answer questions
@@ -246,8 +135,8 @@
- Support for secret injection into the global config file (API keys, for example)
- Improved MCP handling toggle handling
- Secret injection into the MCP configuration
- added REPL support for interacting with the Coyote vault
- Integrated gman with Coyote to create a vault and added flags to configure the Coyote vault
- added REPL support for interacting with the Loki vault
- Integrated gman with Loki to create a vault and added flags to configure the Loki vault
- Added a default session to the jira helper to make interaction more natural
- Created the repo-analyzer role
- Created the coder and sql agents
CONTRIBUTING.md
+2 -2
View File
@@ -2,7 +2,7 @@
Contributors are very welcome! **No contribution is too small and all contributions are valued.**
## Rust
You'll need to have the stable Rust toolchain installed in order to develop Coyote.
You'll need to have the stable Rust toolchain installed in order to develop Loki.
The Rust toolchain (stable) can be installed via rustup using the following command:
@@ -84,5 +84,5 @@ Claude, etc.) is not permitted unless explicitly disclosed and approved.
Submissions must certify that the contributor understands and can maintain the code they submit.
## Questions? Reach out to me!
If you encounter any questions while developing Coyote, please don't hesitate to reach out to me at
If you encounter any questions while developing Loki, please don't hesitate to reach out to me at
alex.j.tusa@gmail.com. I'm happy to help contributors in any way I can, regardless of if they're new or experienced!
CREDITS.md
+6 -6
View File
@@ -1,19 +1,19 @@
# Credits
## AIChat
Coyote originally started as a fork of the fantastic
Loki originally started as a fork of the fantastic
[AIChat CLI](https://github.com/sigoden/aichat). The initial goal was simply
to fix a bug in how MCP servers worked with AIChat, allowing different MCP
servers to be specified per agent. Since then, Coyote has evolved far beyond
servers to be specified per agent. Since then, Loki has evolved far beyond
its original scope and grown into a passion project with a life of its own.
Today, Coyote includes first-class MCP server support (for both local and remote
Today, Loki includes first-class MCP server support (for both local and remote
servers), a built-in vault for interpolating secrets in configuration files,
built-in agents and macros, dynamic tab completions, integrated custom
functions (no external `argc` dependency), improved documentation, and much
more with many more ideas planned for the future.
Coyote is now developed and maintained as an independent project. Full credit
Loki is now developed and maintained as an independent project. Full credit
for the original foundation goes to the developers of the wonderful
AIChat project.
@@ -21,10 +21,10 @@ This project is not affiliated with or endorsed by the AIChat maintainers.
## AIChat
Coyote originally began as a fork of [AIChat CLI](https://github.com/sigoden/aichat),
Loki originally began as a fork of [AIChat CLI](https://github.com/sigoden/aichat),
created and maintained by the AIChat contributors.
While Coyote has since diverged significantly and is now developed as an
While Loki has since diverged significantly and is now developed as an
independent project, its early foundation and inspiration came from the
AIChat project.
Cargo.lock
Generated
+600 -1109
View File
File diff suppressed because it is too large Load Diff
Cargo.toml
+24 -28
View File
@@ -1,16 +1,16 @@
[package]
name = "coyote-ai"
version = "0.5.0"
name = "loki-ai"
version = "0.3.0"
edition = "2024"
authors = ["Alex Clarke <alex.j.tusa@gmail.com>"]
description = "An all-in-one, batteries included LLM CLI Tool"
keywords = ["chatgpt", "llm", "cli", "ai", "repl"]
homepage = "https://github.com/Dark-Alex-17/coyote"
repository = "https://github.com/Dark-Alex-17/coyote"
homepage = "https://github.com/Dark-Alex-17/loki"
repository = "https://github.com/Dark-Alex-17/loki"
categories = ["command-line-utilities"]
readme = "README.md"
license = "MIT"
rust-version = "1.95.0"
rust-version = "1.89.0"
exclude = [".github", "CONTRIBUTING.md"]
[dependencies]
@@ -22,7 +22,7 @@ dunce = "1.0.5"
futures-util = "0.3.29"
inquire = "0.9.4"
is-terminal = "0.4.9"
reedline = "0.47.0"
reedline = "0.46.0"
serde = { version = "1.0.152", features = ["derive"] }
serde_json = { version = "1.0.93", features = ["preserve_order"] }
serde_yaml = "0.9.17"
@@ -34,6 +34,10 @@ tokio = { version = "1.34.0", features = [
"rt-multi-thread",
"full",
] }
tokio-graceful = "0.2.2"
tokio-stream = { version = "0.1.15", default-features = false, features = [
"sync",
] }
crossterm = "0.29.0"
chrono = "0.4.23"
bincode = { version = "2.0.0", features = [
@@ -47,7 +51,7 @@ nu-ansi-term = "0.50.0"
async-trait = "0.1.74"
textwrap = "0.16.0"
ansi_colours = "1.2.2"
eventsource-stream = "0.2.3"
reqwest-eventsource = "0.6.0"
log = "0.4.28"
log4rs = { version = "1.4.0", features = ["file_appender"] }
shell-words = "1.1.0"
@@ -55,14 +59,20 @@ sha2 = "0.10.8"
unicode-width = "0.2.0"
async-recursion = "1.1.1"
http = "1.1.0"
http-body-util = "0.1"
hyper = { version = "1.0", features = ["full"] }
hyper-util = { version = "0.1", features = ["server-auto", "client-legacy"] }
time = { version = "0.3.36", features = ["macros"] }
indexmap = { version = "2.2.6", features = ["serde"] }
hmac = "0.12.1"
aws-smithy-eventstream = "0.60.4"
urlencoding = "2.1.3"
unicode-segmentation = "1.11.0"
json-patch = { version = "4.0.0", default-features = false }
bitflags = "2.5.0"
path-absolutize = "3.1.1"
hnsw_rs = "0.3.0"
rayon = "1.10.0"
uuid = { version = "1.9.1", features = ["v4"] }
scraper = { version = "0.23.1", default-features = false, features = [
"deterministic",
@@ -79,14 +89,10 @@ duct = "1.0.0"
argc = "1.23.0"
strum_macros = "0.27.2"
indoc = "2.0.6"
rmcp = { version = "1.5.0", features = [
"client",
"transport-child-process",
"transport-streamable-http-client-reqwest",
"reqwest-native-tls",
] }
rmcp = { version = "0.16.0", features = ["client", "transport-child-process"] }
num_cpus = "1.17.0"
tree-sitter = "0.26.8"
tree-sitter-language = "0.1"
tree-sitter-python = "0.25.0"
tree-sitter-typescript = "0.23"
colored = "3.0.0"
@@ -96,24 +102,15 @@ clap_complete_nushell = "4.5.9"
open = "5"
rand = { version = "0.10.0", features = ["default"] }
url = "2.5.8"
self_update = { version = "0.44", default-features = false, features = [
"reqwest",
"rustls",
"archive-tar",
"compression-flate2",
"archive-zip",
"compression-zip-deflate",
] }
[dependencies.reqwest]
version = "0.13.3"
version = "0.12.0"
features = [
"json",
"multipart",
"stream",
"form",
"socks",
"rustls",
"rustls-tls",
"rustls-tls-native-roots",
]
default-features = false
@@ -123,7 +120,7 @@ default-features = false
features = ["parsing", "regex-onig", "plist-load"]
[target.'cfg(target_os = "macos")'.dependencies]
crossterm = { version = "0.29.0", features = ["use-dev-tty"] }
crossterm = { version = "0.28.1", features = ["use-dev-tty"] }
[target.'cfg(target_os = "linux")'.dependencies]
arboard = { version = "3.3.0", default-features = false, features = [
@@ -135,10 +132,9 @@ arboard = { version = "3.3.0", default-features = false }
[dev-dependencies]
pretty_assertions = "1.4.0"
serial_test = "3"
[[bin]]
name = "coyote"
name = "loki"
path = "src/main.rs"
[profile.release]
README.md
+95 -110
View File
@@ -1,113 +1,121 @@
# Coyote: All-in-one, batteries-included LLM CLI Tool
# Loki: All-in-one, batteries-included LLM CLI Tool
![Test](https://github.com/Dark-Alex-17/coyote/actions/workflows/ci.yaml/badge.svg)
[![crates.io link](https://img.shields.io/crates/v/coyote-ai.svg)](https://crates.io/crates/coyote-ai)
![Release](https://img.shields.io/github/v/release/Dark-Alex-17/coyote?color=%23c694ff)
![Crate.io downloads](https://img.shields.io/crates/d/coyote-ai?label=Crate%20downloads)
[![GitHub Downloads](https://img.shields.io/github/downloads/Dark-Alex-17/coyote/total.svg?label=GitHub%20downloads)](https://github.com/Dark-Alex-17/coyote/releases)
![Test](https://github.com/Dark-Alex-17/loki/actions/workflows/ci.yaml/badge.svg)
![LOC](https://tokei.rs/b1/github/Dark-Alex-17/loki?category=code)
[![crates.io link](https://img.shields.io/crates/v/loki-ai.svg)](https://crates.io/crates/loki-ai)
![Release](https://img.shields.io/github/v/release/Dark-Alex-17/loki?color=%23c694ff)
![Crate.io downloads](https://img.shields.io/crates/d/loki-ai?label=Crate%20downloads)
[![GitHub Downloads](https://img.shields.io/github/downloads/Dark-Alex-17/loki/total.svg?label=GitHub%20downloads)](https://github.com/Dark-Alex-17/loki/releases)
Coyote is an all-in-one, batteries-included, LLM CLI tool featuring Shell Assistant, CLI & REPL Mode, RAG, AI Tools &
Loki is an all-in-one, batteries-included, LLM CLI tool featuring Shell Assistant, CLI & REPL Mode, RAG, AI Tools &
Agents, and More.
It is designed to include a number of useful agents, roles, macros, and more so users can get up and running with Coyote
in as little time as possible. You can also install entire bundles of agents, roles, macros, tools, and MCP servers from
any git repository. See [Sharing Configurations](https://github.com/Dark-Alex-17/coyote/wiki/Sharing-Configurations) for more information.
It is designed to include a number of useful agents, roles, macros, and more so users can get up and running with Loki
in as little time as possible.
![Agent example](https://raw.githubusercontent.com/wiki/Dark-Alex-17/coyote/images/agents/sql.gif)
![Agent example](./docs/images/agents/sql.gif)
Coming from [AIChat](https://github.com/sigoden/aichat)? Follow the [migration guide](https://github.com/Dark-Alex-17/coyote/wiki/AIChat-Migration) to get started.
Coming from [AIChat](https://github.com/sigoden/aichat)? Follow the [migration guide](./docs/AICHAT-MIGRATION.md) to get started.
## Quick Links
* [AIChat Migration Guide](https://github.com/Dark-Alex-17/coyote/wiki/AIChat-Migration): Coming from AIChat? Follow the migration guide to get started.
* [Installation](#install): Install Coyote
* [Getting Started](#getting-started): Get started with Coyote by doing first-run setup steps.
* [Sharing Configurations](https://github.com/Dark-Alex-17/coyote/wiki/Sharing-Configurations): Install bundles of agents, roles, macros, tools, and MCP servers from any git repo, and share your own.
* [REPL](https://github.com/Dark-Alex-17/coyote/wiki/REPL): Interactive Read-Eval-Print Loop for conversational interactions with LLMs and Coyote.
* [Custom REPL Prompt](https://github.com/Dark-Alex-17/coyote/wiki/REPL-Prompt): Customize the REPL prompt to provide useful contextual information.
* [Vault](https://github.com/Dark-Alex-17/coyote/wiki/Vault): Securely store and manage sensitive information such as API keys and credentials.
* [Shell Integrations](https://github.com/Dark-Alex-17/coyote/wiki/Shell-Integrations): Seamlessly integrate Coyote with your shell environment for enhanced command-line assistance.
* [Function Calling](https://github.com/Dark-Alex-17/coyote/wiki/Tools): Leverage function calling capabilities to extend Coyote's functionality with custom tools
* [Creating Custom Tools](https://github.com/Dark-Alex-17/coyote/wiki/Custom-Tools): You can create your own custom tools to enhance Coyote's capabilities.
* [Create Custom Python Tools](https://github.com/Dark-Alex-17/coyote/wiki/Custom-Tools#custom-python-based-tools)
* [Create Custom TypeScript Tools](https://github.com/Dark-Alex-17/coyote/wiki/Custom-Tools#custom-typescript-based-tools)
* [Create Custom Bash Tools](https://github.com/Dark-Alex-17/coyote/wiki/Custom-Bash-Tools)
* [Bash Prompt Utilities](https://github.com/Dark-Alex-17/coyote/wiki/Bash-Prompt-Helpers)
* [First-Class MCP Server Support](https://github.com/Dark-Alex-17/coyote/wiki/MCP-Servers): Easily connect and interact with MCP servers for advanced functionality.
* [Macros](https://github.com/Dark-Alex-17/coyote/wiki/Macros): Automate repetitive tasks and workflows with Coyote "scripts" (macros).
* [RAG](https://github.com/Dark-Alex-17/coyote/wiki/RAG): Retrieval-Augmented Generation for enhanced information retrieval and generation.
* [Sessions](https://github.com/Dark-Alex-17/coyote/wiki/Sessions): Manage and persist conversational contexts and settings across multiple interactions.
* [Roles](https://github.com/Dark-Alex-17/coyote/wiki/Roles): Customize model behavior for specific tasks or domains.
* [Agents](https://github.com/Dark-Alex-17/coyote/wiki/Agents): Leverage AI agents to perform complex tasks and workflows, including sub-agent spawning, teammate messaging, and user interaction tools.
* [Graph Agents](https://github.com/Dark-Alex-17/coyote/wiki/Graph-Agents): Define an agent as a declarative, YAML-driven workflow. A directed graph of typed nodes (LLM calls, scripts, approvals, user input, RAG retrieval, sub-agent spawns).
* [Todo System](https://github.com/Dark-Alex-17/coyote/wiki/TODO-System): Built-in task tracking for improved LLM reliability with smaller models.
* [Environment Variables](https://github.com/Dark-Alex-17/coyote/wiki/Environment-Variables): Override and customize your Coyote configuration at runtime with environment variables.
* [Client Configurations](https://github.com/Dark-Alex-17/coyote/wiki/Clients): Configuration instructions for various LLM providers.
* [Authentication (API Key & OAuth)](https://github.com/Dark-Alex-17/coyote/wiki/Clients#authentication): Authenticate with API keys or OAuth for subscription-based access.
* [Patching API Requests](https://github.com/Dark-Alex-17/coyote/wiki/Patches): Learn how to patch API requests for advanced customization.
* [Custom Themes](https://github.com/Dark-Alex-17/coyote/wiki/Themes): Change the look and feel of Coyote to your preferences with custom themes.
* [History](#history): A history of how Coyote came to be.
* [AIChat Migration Guide](./docs/AICHAT-MIGRATION.md): Coming from AIChat? Follow the migration guide to get started.
* [Installation](#install): Install Loki
* [Getting Started](#getting-started): Get started with Loki by doing first-run setup steps.
* [REPL](./docs/REPL.md): Interactive Read-Eval-Print Loop for conversational interactions with LLMs and Loki.
* [Custom REPL Prompt](./docs/REPL-PROMPT.md): Customize the REPL prompt to provide useful contextual information.
* [Vault](./docs/VAULT.md): Securely store and manage sensitive information such as API keys and credentials.
* [Shell Integrations](./docs/SHELL-INTEGRATIONS.md): Seamlessly integrate Loki with your shell environment for enhanced command-line assistance.
* [Function Calling](./docs/function-calling/TOOLS.md#Tools): Leverage function calling capabilities to extend Loki's functionality with custom tools
* [Creating Custom Tools](./docs/function-calling/CUSTOM-TOOLS.md): You can create your own custom tools to enhance Loki's capabilities.
* [Create Custom Python Tools](./docs/function-calling/CUSTOM-TOOLS.md#custom-python-based-tools)
* [Create Custom TypeScript Tools](./docs/function-calling/CUSTOM-TOOLS.md#custom-typescript-based-tools)
* [Create Custom Bash Tools](./docs/function-calling/CUSTOM-BASH-TOOLS.md)
* [Bash Prompt Utilities](./docs/function-calling/BASH-PROMPT-HELPERS.md)
* [First-Class MCP Server Support](./docs/function-calling/MCP-SERVERS.md): Easily connect and interact with MCP servers for advanced functionality.
* [Macros](./docs/MACROS.md): Automate repetitive tasks and workflows with Loki "scripts" (macros).
* [RAG](./docs/RAG.md): Retrieval-Augmented Generation for enhanced information retrieval and generation.
* [Sessions](/docs/SESSIONS.md): Manage and persist conversational contexts and settings across multiple interactions.
* [Roles](./docs/ROLES.md): Customize model behavior for specific tasks or domains.
* [Agents](/docs/AGENTS.md): Leverage AI agents to perform complex tasks and workflows, including sub-agent spawning, teammate messaging, and user interaction tools.
* [Todo System](./docs/TODO-SYSTEM.md): Built-in task tracking for improved agent reliability with smaller models.
* [Environment Variables](./docs/ENVIRONMENT-VARIABLES.md): Override and customize your Loki configuration at runtime with environment variables.
* [Client Configurations](./docs/clients/CLIENTS.md): Configuration instructions for various LLM providers.
* [Authentication (API Key & OAuth)](./docs/clients/CLIENTS.md#authentication): Authenticate with API keys or OAuth for subscription-based access.
* [Patching API Requests](./docs/clients/PATCHES.md): Learn how to patch API requests for advanced customization.
* [Custom Themes](./docs/THEMES.md): Change the look and feel of Loki to your preferences with custom themes.
* [History](#history): A history of how Loki came to be.
## Prerequisites
Coyote requires the following tools to be installed on your system:
Loki requires the following tools to be installed on your system:
* [jq](https://github.com/jqlang/jq)
* `brew install jq`
* [jira (optional)](https://github.com/ankitpokhrel/jira-cli/wiki/Installation) (For the `query_jira_issues` tool)
* `brew tap ankitpokhrel/jira-cli && brew install jira-cli`
* You'll need to [create a JIRA API token](https://id.atlassian.com/manage-profile/security/api-tokens) for authentication
* Then, save it as an environment variable to your shell profile:
```sh
# ~/.bashrc or ~/.zshrc
export JIRA_API_TOKEN="your_jira_api_token_here"
```
* Then run `jira init`, select installation type as `cloud`, and provide the required details to generate a config
file for the Jira CLI.
* [usql](https://github.com/xo/usql) (For the `sql` agent)
* `brew install xo/xo/usql`
* [docker](https://docs.docker.com/engine/install/)
* [uv](https://docs.astral.sh/uv/getting-started/installation/)
* `curl -LsSf https://astral.sh/uv/install.sh | sh`
These tools are used to provide various functionalities within Coyote, such as document processing, JSON manipulation,
etc., and they are used within agents and tools.
These tools are used to provide various functionalities within Loki, such as document processing, JSON manipulation,
interaction with Jira, and they are used within agents and tools.
## Install
### Cargo
If you have Cargo installed, then you can install `coyote` from Crates.io:
If you have Cargo installed, then you can install `loki` from Crates.io:
```shell
cargo install coyote-ai # Binary name is `coyote`
cargo install loki-ai # Binary name is `loki`
# If you encounter issues installing, try installing with '--locked'
cargo install --locked coyote-ai
cargo install --locked loki-ai
```
### Homebrew (Mac/Linux)
To install Coyote from Homebrew, install the `coyote` tap. Then you'll be able to install `coyote`:
To install Loki from Homebrew, install the `loki` tap. Then you'll be able to install `loki`:
```shell
brew tap Dark-Alex-17/coyote
brew install coyote
brew tap Dark-Alex-17/loki
brew install loki
# If you need to be more specific, use:
brew install Dark-Alex-17/coyote/coyote
brew install Dark-Alex-17/loki/loki
```
To upgrade `coyote` using Homebrew:
To upgrade `loki` using Homebrew:
```shell
brew upgrade coyote
brew upgrade loki
```
### Scripts
#### Linux/MacOS (`bash`)
You can use the following command to run a bash script that downloads and installs the latest version of `coyote` for your
You can use the following command to run a bash script that downloads and installs the latest version of `loki` for your
OS (Linux/MacOS) and architecture (x86_64/arm64):
```shell
curl -fsSL https://raw.githubusercontent.com/Dark-Alex-17/coyote/main/install_coyote.sh | bash
curl -fsSL https://raw.githubusercontent.com/Dark-Alex-17/loki/main/install_loki.sh | bash
```
#### Windows/Linux/MacOS (`PowerShell`)
You can use the following command to run a PowerShell script that downloads and installs the latest version of `coyote`
You can use the following command to run a PowerShell script that downloads and installs the latest version of `loki`
for your OS (Windows/Linux/MacOS) and architecture (x86_64/arm64):
```powershell
powershell -NoProfile -ExecutionPolicy Bypass -Command "iwr -useb https://raw.githubusercontent.com/Dark-Alex-17/coyote/main/scripts/install_coyote.ps1 | iex"
powershell -NoProfile -ExecutionPolicy Bypass -Command "iwr -useb https://raw.githubusercontent.com/Dark-Alex-17/loki/main/scripts/install_loki.ps1 | iex"
```
### Manual
Binaries are available on the [releases](https://github.com/Dark-Alex-17/coyote/releases) page for the following platforms:
Binaries are available on the [releases](https://github.com/Dark-Alex-17/loki/releases) page for the following platforms:
| Platform | Architecture(s) |
|----------------|-----------------|
@@ -118,58 +126,35 @@ Binaries are available on the [releases](https://github.com/Dark-Alex-17/coyote/
#### Windows Instructions
To use a binary from the releases page on Windows, do the following:
1. Download the latest [binary](https://github.com/Dark-Alex-17/coyote/releases) for your OS.
1. Download the latest [binary](https://github.com/Dark-Alex-17/loki/releases) for your OS.
2. Use 7-Zip or TarTool to unpack the Tar file.
3. Run the executable `coyote.exe`!
3. Run the executable `loki.exe`!
#### Linux/MacOS Instructions
To use a binary from the releases page on Linux/MacOS, do the following:
1. Download the latest [binary](https://github.com/Dark-Alex-17/coyote/releases) for your OS.
1. Download the latest [binary](https://github.com/Dark-Alex-17/loki/releases) for your OS.
2. `cd` to the directory where you downloaded the binary.
3. Extract the binary with `tar -C /usr/local/bin -xzf coyote-<arch>.tar.gz` (Note: This may require `sudo`)
4. Now you can run `coyote`!
## Updating
Coyote can update itself in place to the latest GitHub release. Run `coyote --update`
for the newest release, or `coyote --update v0.4.0` for a specific version:
```shell
coyote --update
coyote --update v0.4.0
```
The same is available from within the REPL via `.update` and `.update v0.4.0`.
If Coyote was installed with a package manager, prefer that package manager so its
records stay in sync with the binary on disk; i.e. `brew upgrade coyote` for Homebrew,
or `cargo install --locked coyote-ai` for Cargo.
When Coyote detects a package-manager install it prints a warning and asks for
confirmation. In a non-interactive shell (no TTY), pass `--force` to update
anyway:
```shell
coyote --update --force
```
3. Extract the binary with `tar -C /usr/local/bin -xzf loki-<arch>.tar.gz` (Note: This may require `sudo`)
4. Now you can run `loki`!
## Getting Started
After installation, you can generate the configuration files and directories by simply running:
```sh
coyote --info
loki --info
```
Then, you need to set up the Coyote vault by creating a vault password file. Coyote will do this for you automatically and
Then, you need to set up the Loki vault by creating a vault password file. Loki will do this for you automatically and
guide you through the process when you first attempt to access the vault. So, to get started, you can run:
```sh
coyote --list-secrets
loki --list-secrets
```
### Authentication
Each client in your configuration needs authentication (with a few exceptions; e.g. ollama). Most clients use an API key
(set via `api_key` in the config or through the [vault](https://github.com/Dark-Alex-17/coyote/wiki/Vault)). For providers that support OAuth (e.g. Claude Pro/Max
(set via `api_key` in the config or through the [vault](./docs/VAULT.md)). For providers that support OAuth (e.g. Claude Pro/Max
subscribers, Google Gemini), you can authenticate with your existing subscription instead:
```yaml
@@ -181,40 +166,40 @@ clients:
```
```sh
coyote --authenticate my-claude-oauth
loki --authenticate my-claude-oauth
# Or via the REPL: .authenticate
```
For full details, see the [authentication documentation](https://github.com/Dark-Alex-17/coyote/wiki/Clients#authentication).
For full details, see the [authentication documentation](./docs/clients/CLIENTS.md#authentication).
### Tab-Completions
You can also enable tab completions to make using Coyote easier. To do so, add the following to your shell profile:
You can also enable tab completions to make using Loki easier. To do so, add the following to your shell profile:
```shell
# Bash
# (add to: `~/.bashrc`)
source <(COMPLETE=bash coyote)
source <(COMPLETE=bash loki)
# Zsh
# (add to: `~/.zshrc`)
source <(COMPLETE=zsh coyote)
source <(COMPLETE=zsh loki)
# Fish
# (add to: `~/.config/fish/config.fish`)
source <(COMPLETE=fish coyote | psub)
source <(COMPLETE=fish loki | psub)
# Elvish
# (add to: `~/.elvish/rc.elv`)
eval (E:COMPLETE=elvish coyote | slurp)
eval (E:COMPLETE=elvish loki | slurp)
# PowerShell
# (add to: `$PROFILE`)
$env:COMPLETE = "powershell"
coyote | Out-String | Invoke-Expression
loki | Out-String | Invoke-Expression
```
### Shell Integration
You can integrate Coyote's Shell Assistant into your shell for enhanced command-line assistance. Add the code in the
corresponding [shell integration script](./scripts/shell-integration) to your shell. Then, you can invoke Coyote to convert natural language to
You can integrate Loki's Shell Assistant into your shell for enhanced command-line assistance. Add the code in the
corresponding [shell integration script](./scripts/shell-integration) to your shell. Then, you can invoke Loki to convert natural language to
shell commands by pressing `Alt-e`. For example:
```shell
@@ -224,18 +209,18 @@ find . -name "*.md"
```
## Configuration
The location of the global Coyote configuration varies between systems, so you can use the following command to find your
The location of the global Loki configuration varies between systems, so you can use the following command to find your
`config.yaml` file:
```shell
coyote --info | grep 'config_file' | awk '{print $2}'
loki --info | grep 'config_file' | awk '{print $2}'
```
The configuration file consists of a number of settings. To see a full example configuration file with every setting
defined, refer to the [example configuration file](./config.example.yaml).
### Default LLM
The following settings are available to configure the default LLM that is used when you start Coyote, and its
The following settings are available to configure the default LLM that is used when you start Loki, and its
hyperparameters:
| Setting | Description |
@@ -245,34 +230,34 @@ hyperparameters:
| `top_p` | The default `top_p` hyperparameter value to use for all models, with a range of (0,1) (or (0,2) for some models); <br>Used unless explicitly overridden |
### CLI Behavior
You can use the following settings to modify the behavior of Coyote:
You can use the following settings to modify the behavior of Loki:
| Setting | Default Value | Description |
|---------------|---------------|-------------------------------------------------------------------------------------------------------------------------------------|
| `stream` | `true` | Controls whether to use stream-style APIs when querying for completions from LLM providers |
| `save` | `true` | Controls whether to save each query/response to every model to `messages.md` for posterity; Useful for debugging |
| `keybindings` | `emacs` | Specifies which keybinding schema to use; can either be `emacs` or `vi` |
| `editor` | `null` | What text editor Coyote should use to edit the input buffer or session (e.g. `vim`, `emacs`, `nano`, `hx`); <br>Defaults to `$EDITOR` |
| `editor` | `null` | What text editor Loki should use to edit the input buffer or session (e.g. `vim`, `emacs`, `nano`, `hx`); <br>Defaults to `$EDITOR` |
| `wrap` | `no` | Controls whether text is wrapped (can be `no`, `auto`, or some `<max_width>` |
| `wrap_code` | `false` | Enables or disables the wrapping of code blocks |
### Preludes
Preludes let you define the default behavior for the different operating modes of Coyote. The available settings are
Preludes let you define the default behavior for the different operating modes of Loki. The available settings are
shown below:
| Setting | Description |
|-----------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| `repl_prelude` | This setting lets you specify a default `session` or `role` to use when starting Coyote in [REPL](https://github.com/Dark-Alex-17/coyote/wiki/REPL) mode. <br>Values can be <ul><li>`role:<name>` to define a role</li><li>`session:<name>` to define a session</li><li>`<session>:<role>` to define both a session and a role to use</li></ul> |
| `cmd_prelude` | This setting lets you specify a default `session` or `role` to use when running one-off queries in Coyote via the CLI. <br>Values can be <ul><li>`role:<name>` to define a role</li><li>`session:<name>` to define a session</li><li>`<session>:<role>` to define both a session and a role to use</li></ul> |
| `repl_prelude` | This setting lets you specify a default `session` or `role` to use when starting Loki in [REPL](./docs/REPL.md) mode. <br>Values can be <ul><li>`role:<name>` to define a role</li><li>`session:<name>` to define a session</li><li>`<session>:<role>` to define both a session and a role to use</li></ul> |
| `cmd_prelude` | This setting lets you specify a default `session` or `role` to use when running one-off queries in Loki via the CLI. <br>Values can be <ul><li>`role:<name>` to define a role</li><li>`session:<name>` to define a session</li><li>`<session>:<role>` to define both a session and a role to use</li></ul> |
| `agent_session` | This setting is used to specify a default session that all agents should start into, unless otherwise specified in the agent configuration. (e.g. `temp`, `default`) |
### Appearance
The appearance of Coyote can be modified using the following settings:
The appearance of Loki can be modified using the following settings:
| Setting | Default Value | Description |
|---------------|---------------|------------------------------------------------------|
| `highlight` | `true` | This setting enables or disables syntax highlighting |
| `light_theme` | `false` | This setting toggles light mode in Coyote |
| `light_theme` | `false` | This setting toggles light mode in Loki |
### Miscellaneous Settings
| Setting | Default Value | Description |
@@ -284,7 +269,7 @@ The appearance of Coyote can be modified using the following settings:
## History
Coyote began as a fork of [AIChat CLI](https://github.com/sigoden/aichat) and has since evolved into an independent project.
Loki began as a fork of [AIChat CLI](https://github.com/sigoden/aichat) and has since evolved into an independent project.
See [CREDITS.md](./CREDITS.md) for full attribution and background.
assets/agents/.shared/utils.sh
+4 -4
View File
@@ -7,14 +7,14 @@ set -euo pipefail
#######################
# Cache file name for detected project info
_COYOTE_PROJECT_CACHE=".coyote-project.json"
_LOKI_PROJECT_CACHE=".loki-project.json"
# Read cached project detection if valid
# Usage: _read_project_cache "/path/to/project"
# Returns: cached JSON on stdout (exit 0) or nothing (exit 1)
_read_project_cache() {
local dir="$1"
local cache_file="${dir}/${_COYOTE_PROJECT_CACHE}"
local cache_file="${dir}/${_LOKI_PROJECT_CACHE}"
if [[ -f "${cache_file}" ]]; then
local cached
@@ -32,7 +32,7 @@ _read_project_cache() {
_write_project_cache() {
local dir="$1"
local json="$2"
local cache_file="${dir}/${_COYOTE_PROJECT_CACHE}"
local cache_file="${dir}/${_LOKI_PROJECT_CACHE}"
echo "${json}" > "${cache_file}" 2>/dev/null || true
}
@@ -238,7 +238,7 @@ _detect_with_llm() {
)
local llm_response
llm_response=$(coyote --no-stream "${prompt}" 2>/dev/null) || return 1
llm_response=$(loki --no-stream "${prompt}" 2>/dev/null) || return 1
llm_response=$(echo "${llm_response}" | sed 's/^```json//;s/^```//;s/```$//' | tr -d '\n' | sed 's/^[[:space:]]*//')
llm_response=$(echo "${llm_response}" | grep -o '{[^}]*}' | head -1)
assets/agents/coder/README.md
+21 -63
View File
@@ -1,82 +1,40 @@
# Coder
A graph-based implementation agent. Plans, implements, and runs build +
tests in a bounded fix-loop until verified. Designed to be delegated to by
the **[Sisyphus](../sisyphus/README.md)** agent.
An AI agent that assists you with your coding tasks.
Coder is a [graph agent](https://github.com/Dark-Alex-17/coyote/wiki/Graph-Agents): its workflow is
defined declaratively in `graph.yaml`, with verification and the
implement-fix loop enforced as graph edges rather than prose.
This agent is designed to be delegated to by the **[Sisyphus](../sisyphus/README.md)** agent to implement code specifications. Sisyphus
acts as the coordinator/architect, while Coder handles the implementation details.
## Workflow
## Features
```
analyze_request (llm + output_schema) plan + complexity extraction
↓
route_complexity (script) opt-out approval gate (complexity ≥ 7)
↓
gate_approval (approval, optional)
↓
implement (llm + fs tools) actual file edits
↓
verify_build (script)
↓
verify_tests (script)
↓
fix_loop_gate (script) back-edge to implement (bounded)
↓
end_success / end_rejected / end_failure
```
- 🏗️ Intelligent project structure creation and management
- 🖼️ Convert screenshots into clean, functional code
- 📁 Comprehensive file system operations (create folders, files, read/write files)
- 🧐 Advanced code analysis and improvement suggestions
- 📊 Precise diff-based file editing for controlled code modifications
End nodes emit one of three sentinel outcomes for the caller:
It can also be used as a standalone tool for direct coding assistance.
- `CODER_COMPLETE` — build and tests passed.
- `CODER_REJECTED` — user rejected the plan at the approval gate.
- `CODER_FAILED` — fix-loop exhausted; build/tests still failing.
## Tuning
The agent's `project_dir` is exposed via the standard `variables:` block,
so it accepts the runtime override flag:
```sh
# Invoke from inside the project (project_dir defaults to ".")
cd /path/to/your/project
coyote -a coder "Add a foo() function..."
# Or invoke from anywhere with an explicit override
coyote -a coder --agent-variable project_dir /path/to/your/project "Add..."
```
`graph.yaml` `initial_state` exposes:
- `max_fix_attempts` (default `3`) — fix-loop budget before `end_failure`.
Environment overrides honored by the script nodes:
- `BUILD_CMD` — skip project-type detection for the build/check command.
- `TEST_CMD` — skip detection for tests.
- `CODER_AUTOAPPROVE=1` — bypass the approval gate (for non-interactive runs
where complexity might trip the gate).
## Pro-Tip: IDE MCP Server
Modern IDEs (JetBrains, VS Code, Cursor, Zed, etc.) expose MCP servers
that let LLMs use IDE tools directly. To wire one in, edit `graph.yaml`:
## Pro-Tip: Use an IDE MCP Server for Improved Performance
Many modern IDEs now include MCP servers that let LLMs perform operations within the IDE itself and use IDE tools. Using
an IDE's MCP server dramatically improves the performance of coding agents. So if you have an IDE, try adding that MCP
server to your config (see the [MCP Server docs](../../../docs/function-calling/MCP-SERVERS.md) to see how to configure
them), and modify the agent definition to look like this:
```yaml
# ...
mcp_servers:
- your-ide-mcp-server
- jetbrains # The name of your configured IDE MCP server
global_tools:
# Keep read-only fs tools for files outside the IDE project
# Keep useful read-only tools for reading files in other non-project directories
- fs_read.sh
- fs_grep.sh
- fs_glob.sh
# - fs_write.sh
# - fs_patch.sh
- execute_command.sh
```
Then add the MCP server's write/patch tools to the `implement` node's
`tools:` whitelist.
# ...
```
assets/agents/coder/config.yaml
+129
View File
@@ -0,0 +1,129 @@
name: coder
description: Implementation agent - writes code, follows patterns, verifies with builds
version: 1.0.0
temperature: 0.1
auto_continue: true
max_auto_continues: 15
inject_todo_instructions: true
variables:
- name: project_dir
description: Project directory to work in
default: '.'
- name: auto_confirm
description: Auto-confirm command execution
default: '1'
global_tools:
- fs_read.sh
- fs_grep.sh
- fs_glob.sh
- fs_write.sh
- fs_patch.sh
- execute_command.sh
instructions: |
You are a senior engineer. You write code that works on the first try.
## Your Mission
Given an implementation task:
1. Check for orchestrator context first (see below)
2. Fill gaps only. Read files NOT already covered in context
3. Write the code (using tools, NOT chat output)
4. Verify it compiles/builds
5. Signal completion with a summary
## Using Orchestrator Context (IMPORTANT)
When spawned by sisyphus, your prompt will often contain a `<context>` block
with prior findings: file paths, code patterns, and conventions discovered by
explore agents.
**If context is provided:**
1. Use it as your primary reference. Don't re-read files already summarized
2. Follow the code patterns shown. Snippets in context ARE the style guide
3. Read the referenced files ONLY IF you need more detail (e.g. full function
signature, import list, or adjacent code not included in the snippet)
4. If context includes a "Conventions" section, follow it exactly
**If context is NOT provided or is too vague to act on:**
Fall back to self-exploration: grep for similar files, read 1-2 examples,
match their style.
**Never ignore provided context.** It represents work already done upstream.
## Todo System
For multi-file changes:
1. `todo__init` with the implementation goal
2. `todo__add` for each file to create/modify
3. Implement each, calling `todo__done` immediately after
## Writing Code
**CRITICAL**: Write code using `write_file` tool, NEVER paste code in chat.
Correct:
```
write_file --path "src/user.rs" --content "pub struct User { ... }"
```
Wrong:
```
Here's the implementation:
\`\`\`rust
pub struct User { ... }
\`\`\`
```
## File Reading Strategy (IMPORTANT - minimize token usage)
1. **Use grep to find relevant code** - `fs_grep --pattern "fn handle_request" --include "*.rs"` finds where things are
2. **Read only what you need** - `fs_read --path "src/main.rs" --offset 50 --limit 30` reads lines 50-79
3. **Never cat entire large files** - If 500+ lines, read the relevant section after grepping for it
4. **Use glob to find files** - `fs_glob --pattern "*.rs" --path src/` discovers files by name
## Pattern Matching
Before writing ANY file:
1. Find a similar existing file (use `fs_grep` to locate, then `fs_read` to examine)
2. Match its style: imports, naming, structure
3. Follow the same patterns exactly
## Verification
After writing files:
1. Run `verify_build` to check compilation
2. If it fails, fix the error (minimal change)
3. Don't move on until build passes
## Completion Signal
When done, end your response with a summary so the parent agent knows what happened:
```
CODER_COMPLETE: [summary of what was implemented, which files were created/modified, and build status]
```
Or if something went wrong:
```
CODER_FAILED: [what went wrong]
```
## Rules
1. **Write code via tools** - Never output code to chat
2. **Follow patterns** - Read existing files first
3. **Verify builds** - Don't finish without checking
4. **Minimal fixes** - If build fails, fix precisely
5. **No refactoring** - Only implement what's asked
## Context
- Project: {{project_dir}}
- CWD: {{__cwd__}}
- Shell: {{__shell__}}
## Available tools:
{{__tools__}}
assets/agents/coder/graph.yaml
-278
View File
@@ -1,278 +0,0 @@
name: coder
description: |
Implementation agent. Plans, implements, and runs build + tests in a
bounded fix-loop until verified. Designed to be delegated to by sisyphus.
version: "1.0"
temperature: 0.1
global_tools:
- fs_cat.sh
- fs_ls.sh
- fs_write.sh
- fs_patch.sh
- execute_command.sh
variables:
- name: project_dir
description: |
Absolute path to the project directory. Defaults to "." which is the
directory you invoked `coyote` from. Override at runtime with
`coyote -a coder --agent-variable project_dir /abs/path "..."`.
default: "."
settings:
max_loop_iterations: 20
log_state_snapshots: true
validate_before_run: true
timeout: 1800
initial_state:
project_dir: ""
fix_attempts: 0
max_fix_attempts: 3
fix_instructions: ""
build_output: ""
tests_output: ""
last_node_output: ""
plan_summary: ""
files_to_modify: []
files_to_create: []
risks: []
complexity_score: 0
start: resolve_paths
nodes:
resolve_paths:
id: resolve_paths
type: script
description: Resolve project_dir to an absolute path from the agent variable
script: scripts/resolve_paths.sh
timeout: 5
fallback: end_failure
analyze_request:
id: analyze_request
type: llm
description: Extract a structured plan and complexity score from the orchestrator's prompt
instructions: |
You are a senior engineer's planning assistant. Read the orchestrator's
request and emit a structured plan. You only plan. You never edit files.
Score complexity from 1 to 10:
1-3: trivial - single file, <=20 lines changed, obvious approach
4-6: moderate - 2-5 files, clear approach, some pattern matching
7-10: complex - multi-component, ambiguous tradeoffs, refactoring,
or wide blast radius
Be specific in `files_to_modify` and `files_to_create`. All paths
MUST be absolute. The project root is {{project_dir}}. Prefer paths
like "{{project_dir}}/src/foo.rs" over "src/foo.rs". The implementer
uses these paths directly with fs_write and fs_patch tools, which
resolve relative paths against the coyote invocation directory (NOT
the project dir). Empty arrays are fine if no files in that category.
`risks` is a list of short strings. Anything that could derail the
implementation: unknown dependencies, brittle tests, blast radius,
etc. Empty list is fine.
Project directory: {{project_dir}}
prompt: "{{initial_prompt}}"
tools: []
output_schema:
type: object
properties:
plan_summary:
type: string
description: 1-3 sentences summarizing what will be done
files_to_modify:
type: array
items: {type: string}
files_to_create:
type: array
items: {type: string}
complexity_score:
type: integer
minimum: 1
maximum: 10
risks:
type: array
items: {type: string}
required: [plan_summary, files_to_modify, files_to_create, complexity_score, risks]
state_updates:
last_node_output: "{{output}}"
fallback: end_failure
next: route_complexity
route_complexity:
id: route_complexity
type: script
description: Route to approval gate for complex plans; skip otherwise
script: scripts/route_complexity.sh
timeout: 5
fallback: implement
gate_approval:
id: gate_approval
type: approval
description: Optional human checkpoint for high-complexity plans
question: |
## Plan
{{plan_summary}}
## Files to modify
{{files_to_modify}}
## Files to create
{{files_to_create}}
## Risks
{{risks}}
Complexity: {{complexity_score}}/10
Approve this plan?
options:
- "yes"
- "no"
routes:
"yes": implement
"no": end_rejected
on_other: end_rejected
implement:
id: implement
type: llm
description: Write code via fs tools. Bounded tool-call loop.
instructions: |
You are a senior engineer. Implement the plan by writing code via
tools. Follow existing patterns in the codebase.
## Writing code
1. Use `fs_patch` for surgical edits to existing files.
2. Use `fs_write` for new files or full rewrites.
3. NEVER output code to chat. Always use tools.
4. ALWAYS pass ABSOLUTE paths to fs_write and fs_patch. Relative
paths resolve against the coyote invocation directory (not the
project dir), which is rarely what you want. The project root
is {{project_dir}}.
## File reading
1. Use `execute_command` to grep/find:
`execute_command --command "grep -rn 'fn handle_request' --include='*.rs' ."`
`execute_command --command "find . -name '*.rs' -not -path '*/target/*'"`
2. Read only what you need:
`fs_cat --path "src/main.rs" --offset 50 --limit 30`
3. Never read entire large files. Use offset/limit.
4. Use `fs_ls` to list directory contents.
## Pattern matching
Before writing ANY file:
1. Find a similar existing file (grep, then read).
2. Match its style: imports, naming, structure, error handling.
3. Follow the same patterns exactly. Do not invent new ones.
## Fix loop
If the "Fix loop status" section in your user prompt is non-empty,
the previous attempt failed verification. Read the error, identify
the minimal fix, apply it. Do not refactor while fixing.
## Rules
1. Match existing patterns - read examples first.
2. Minimal changes - implement only what's asked.
3. Never suppress errors (`as any`, `@ts-ignore`, `#[allow(...)]`
on unfamiliar lints, etc.).
4. No dead code, no commented-out blocks, no premature abstractions.
5. End your turn when editing is done. The graph runs verification next.
Project directory: {{project_dir}}
prompt: |
## Plan summary
{{plan_summary}}
## Files involved
- Modify: {{files_to_modify}}
- Create: {{files_to_create}}
## Original request from the orchestrator
{{initial_prompt}}
## Fix loop status
{{fix_instructions}}
tools:
- fs_cat
- fs_ls
- fs_write
- fs_patch
- execute_command
max_iterations: 30
state_updates:
last_node_output: "{{output}}"
fallback: end_failure
next: verify_build
verify_build:
id: verify_build
type: script
description: Run the project's check/build command. Routes to verify_tests on success, fix_loop_gate on failure.
script: scripts/verify_build.sh
timeout: 300
fallback: fix_loop_gate
verify_tests:
id: verify_tests
type: script
description: Run the project's test command. Routes to end_success on pass, fix_loop_gate on failure.
script: scripts/verify_tests.sh
timeout: 600
fallback: fix_loop_gate
fix_loop_gate:
id: fix_loop_gate
type: script
description: Budget gate. Loops back to implement with fix_instructions populated, or terminates as end_failure.
script: scripts/fix_loop_gate.sh
timeout: 5
fallback: end_failure
end_success:
id: end_success
type: end
output: |
CODER_COMPLETE
Plan: {{plan_summary}}
Files modified: {{files_to_modify}}
Files created: {{files_to_create}}
Build: passed
Tests: passed
end_rejected:
id: end_rejected
type: end
output: |
CODER_REJECTED
Plan was rejected at the approval gate.
Plan: {{plan_summary}}
end_failure:
id: end_failure
type: end
output: |
CODER_FAILED
Plan: {{plan_summary}}
Attempts: {{fix_attempts}}/{{max_fix_attempts}}
Last node output:
{{last_node_output}}
Last build output:
{{build_output}}
Last tests output:
{{tests_output}}
assets/agents/coder/scripts/fix_loop_gate.sh
-49
View File
@@ -1,49 +0,0 @@
#!/usr/bin/env bash
set -euo pipefail
if [[ -n "${GRAPH_STATE_FILE:-}" ]]; then
state=$(cat "$GRAPH_STATE_FILE")
elif [[ -n "${GRAPH_STATE:-}" ]]; then
state="$GRAPH_STATE"
else
state='{}'
fi
fix_attempts=$(echo "$state" | jq -r '.fix_attempts // 0')
max_fix_attempts=$(echo "$state" | jq -r '.max_fix_attempts // 3')
build_ok=$(echo "$state" | jq -r '.build_ok | if . == null then "true" else (. | tostring) end')
tests_ok=$(echo "$state" | jq -r '.tests_ok | if . == null then "true" else (. | tostring) end')
build_output=$(echo "$state" | jq -r '.build_output // ""')
tests_output=$(echo "$state" | jq -r '.tests_output // ""')
if (( fix_attempts >= max_fix_attempts )); then
jq -nc \
--argjson n "$fix_attempts" \
'{
"fix_attempts": $n,
"_next": "end_failure"
}'
exit 0
fi
next_attempts=$((fix_attempts + 1))
if [[ "$build_ok" != "true" ]]; then
fix_instructions=$(printf '## Fix loop status (attempt %d of %d)\n\nThe previous attempt failed the build.\n\nBuild output:\n```\n%s\n```\n\nIdentify the minimal fix and apply it. Do not refactor.' \
"$next_attempts" "$max_fix_attempts" "$build_output")
elif [[ "$tests_ok" != "true" ]]; then
fix_instructions=$(printf '## Fix loop status (attempt %d of %d)\n\nBuild passed but tests failed.\n\nTest output:\n```\n%s\n```\n\nIdentify the minimal fix and apply it. Do not refactor.' \
"$next_attempts" "$max_fix_attempts" "$tests_output")
else
fix_instructions=$(printf '## Fix loop status (attempt %d of %d)\n\nfix_loop_gate was reached but no failure was detected in state. Re-run the verification step.' \
"$next_attempts" "$max_fix_attempts")
fi
jq -nc \
--argjson n "$next_attempts" \
--arg fi "$fix_instructions" \
'{
"fix_attempts": $n,
"fix_instructions": $fi,
"_next": "implement"
}'
assets/agents/coder/scripts/resolve_paths.sh
-12
View File
@@ -1,12 +0,0 @@
#!/usr/bin/env bash
set -euo pipefail
project_dir="${LLM_AGENT_VAR_PROJECT_DIR:-.}"
resolved=$(cd "$project_dir" 2>/dev/null && pwd) || resolved="$project_dir"
jq -nc \
--arg pd "$resolved" \
'{
"project_dir": $pd,
"_next": "analyze_request"
}'
assets/agents/coder/scripts/route_complexity.sh
-23
View File
@@ -1,23 +0,0 @@
#!/usr/bin/env bash
set -euo pipefail
if [[ -n "${GRAPH_STATE_FILE:-}" ]]; then
state=$(cat "$GRAPH_STATE_FILE")
elif [[ -n "${GRAPH_STATE:-}" ]]; then
state="$GRAPH_STATE"
else
state='{}'
fi
complexity=$(echo "$state" | jq -r '.complexity_score // 0')
if [[ "${CODER_AUTOAPPROVE:-0}" == "1" ]]; then
jq -nc '{"_next": "implement"}'
exit 0
fi
if (( complexity >= 7 )); then
jq -nc '{"_next": "gate_approval"}'
else
jq -nc '{"_next": "implement"}'
fi
assets/agents/coder/scripts/verify_build.sh
-55
View File
@@ -1,55 +0,0 @@
#!/usr/bin/env bash
set -uo pipefail
# shellcheck disable=SC1091
source "$(dirname "$0")/../../.shared/utils.sh"
if [[ -n "${GRAPH_STATE_FILE:-}" ]]; then
state=$(cat "$GRAPH_STATE_FILE")
elif [[ -n "${GRAPH_STATE:-}" ]]; then
state="$GRAPH_STATE"
else
state='{}'
fi
project_dir=$(echo "$state" | jq -r '.project_dir // "."')
if [[ -n "${BUILD_CMD:-}" ]]; then
cmd="$BUILD_CMD"
else
project_info=$(detect_project "$project_dir")
cmd=$(echo "$project_info" | jq -r '.check // .build // ""')
fi
if [[ -z "$cmd" || "$cmd" == "null" ]]; then
jq -nc '{
"build_ok": true,
"build_output": "(no build/check command available for this project type)",
"_next": "verify_tests"
}'
exit 0
fi
exit_code=0
output=$(cd "$project_dir" && eval "$cmd" 2>&1) || exit_code=$?
if (( exit_code == 0 )); then
jq -nc \
--arg out "$output" \
--arg cmd "$cmd" \
'{
"build_ok": true,
"build_output": ("Ran: " + $cmd + "\n\n" + $out),
"_next": "verify_tests"
}'
else
jq -nc \
--arg out "$output" \
--arg cmd "$cmd" \
--argjson rc "$exit_code" \
'{
"build_ok": false,
"build_output": ("Ran: " + $cmd + "\nExit code: " + ($rc | tostring) + "\n\n" + $out),
"_next": "fix_loop_gate"
}'
fi
assets/agents/coder/scripts/verify_tests.sh
-55
View File
@@ -1,55 +0,0 @@
#!/usr/bin/env bash
set -uo pipefail
# shellcheck disable=SC1091
source "$(dirname "$0")/../../.shared/utils.sh"
if [[ -n "${GRAPH_STATE_FILE:-}" ]]; then
state=$(cat "$GRAPH_STATE_FILE")
elif [[ -n "${GRAPH_STATE:-}" ]]; then
state="$GRAPH_STATE"
else
state='{}'
fi
project_dir=$(echo "$state" | jq -r '.project_dir // "."')
if [[ -n "${TEST_CMD:-}" ]]; then
cmd="$TEST_CMD"
else
project_info=$(detect_project "$project_dir")
cmd=$(echo "$project_info" | jq -r '.test // ""')
fi
if [[ -z "$cmd" || "$cmd" == "null" ]]; then
jq -nc '{
"tests_ok": true,
"tests_output": "(no test command available for this project type)",
"_next": "end_success"
}'
exit 0
fi
exit_code=0
output=$(cd "$project_dir" && eval "$cmd" 2>&1) || exit_code=$?
if (( exit_code == 0 )); then
jq -nc \
--arg out "$output" \
--arg cmd "$cmd" \
'{
"tests_ok": true,
"tests_output": ("Ran: " + $cmd + "\n\n" + $out),
"_next": "end_success"
}'
else
jq -nc \
--arg out "$output" \
--arg cmd "$cmd" \
--argjson rc "$exit_code" \
'{
"tests_ok": false,
"tests_output": ("Ran: " + $cmd + "\nExit code: " + ($rc | tostring) + "\n\n" + $out),
"_next": "fix_loop_gate"
}'
fi
assets/agents/coder/tools.sh
+118
View File
@@ -14,6 +14,99 @@ _project_dir() {
(cd "${dir}" 2>/dev/null && pwd) || echo "${dir}"
}
# Normalize a path to be relative to project root.
# Strips the project_dir prefix if the LLM passes an absolute path.
# Usage: local rel_path; rel_path=$(_normalize_path "/abs/or/rel/path")
_normalize_path() {
local input_path="$1"
local project_dir
project_dir=$(_project_dir)
if [[ "${input_path}" == /* ]]; then
input_path="${input_path#"${project_dir}"/}"
fi
input_path="${input_path#./}"
echo "${input_path}"
}
# @cmd Read a file's contents before modifying
# @option --path! Path to the file (relative to project root)
read_file() {
local file_path
# shellcheck disable=SC2154
file_path=$(_normalize_path "${argc_path}")
local project_dir
project_dir=$(_project_dir)
local full_path="${project_dir}/${file_path}"
if [[ ! -f "${full_path}" ]]; then
warn "File not found: ${file_path}" >> "$LLM_OUTPUT"
return 0
fi
{
info "Reading: ${file_path}"
echo ""
cat "${full_path}"
} >> "$LLM_OUTPUT"
}
# @cmd Write complete file contents
# @option --path! Path for the file (relative to project root)
# @option --content! Complete file contents to write
write_file() {
local file_path
file_path=$(_normalize_path "${argc_path}")
# shellcheck disable=SC2154
local content="${argc_content}"
local project_dir
project_dir=$(_project_dir)
local full_path="${project_dir}/${file_path}"
mkdir -p "$(dirname "${full_path}")"
printf '%s' "${content}" > "${full_path}"
green "Wrote: ${file_path}" >> "$LLM_OUTPUT"
}
# @cmd Find files similar to a given path (for pattern matching)
# @option --path! Path to find similar files for
find_similar_files() {
local file_path
file_path=$(_normalize_path "${argc_path}")
local project_dir
project_dir=$(_project_dir)
local ext="${file_path##*.}"
local dir
dir=$(dirname "${file_path}")
info "Similar files to: ${file_path}" >> "$LLM_OUTPUT"
echo "" >> "$LLM_OUTPUT"
local results
results=$(find "${project_dir}/${dir}" -maxdepth 1 -type f -name "*.${ext}" \
! -name "$(basename "${file_path}")" \
! -name "*test*" \
! -name "*spec*" \
2>/dev/null | sed "s|^${project_dir}/||" | head -3)
if [[ -z "${results}" ]]; then
results=$(find "${project_dir}/src" -type f -name "*.${ext}" \
! -name "*test*" \
! -name "*spec*" \
-not -path '*/target/*' \
2>/dev/null | sed "s|^${project_dir}/||" | head -3)
fi
if [[ -n "${results}" ]]; then
echo "${results}" >> "$LLM_OUTPUT"
else
warn "No similar files found" >> "$LLM_OUTPUT"
fi
}
# @cmd Verify the project builds successfully
verify_build() {
local project_dir
@@ -96,3 +189,28 @@ get_project_structure() {
} >> "$LLM_OUTPUT"
}
# @cmd Search for content in the codebase
# @option --pattern! Pattern to search for
search_code() {
# shellcheck disable=SC2154
local pattern="${argc_pattern}"
local project_dir
project_dir=$(_project_dir)
info "Searching: ${pattern}" >> "$LLM_OUTPUT"
echo "" >> "$LLM_OUTPUT"
local results
results=$(grep -rn "${pattern}" "${project_dir}" 2>/dev/null | \
grep -v '/target/' | \
grep -v '/node_modules/' | \
grep -v '/.git/' | \
sed "s|^${project_dir}/||" | \
head -20) || true
if [[ -n "${results}" ]]; then
echo "${results}" >> "$LLM_OUTPUT"
else
warn "No matches" >> "$LLM_OUTPUT"
fi
}
assets/agents/deep-research/README.md
-274
View File
@@ -1,274 +0,0 @@
# deep-research
A deep web research agent, built as a Coyote graph agent. It plans an
investigation, decomposes it into sub-questions researched in
parallel, grounds the work in a local knowledge corpus, vets the
credibility of cited sources, runs a reflexion self-critique loop to
revise weak findings, delegates the final write-up to a focused
sub-agent, checks that the cited sources are reachable, and gates the
result behind human approval.
Unlike a regular agent (which takes a goal and improvises the steps),
this agent runs a fixed graph: every request goes through the same
`plan -> parallel research -> vet -> critique -> synthesize -> verify -> approve`
pipeline.
This agent is also the **canonical reference for the Coyote graph
system**: it exercises every node type (`script`, `llm`, `rag`, `map`,
`agent`, `input`, `approval`, `end`) and both static fan-out and
dynamic `map` fan-out. If you are learning how to build a graph
agent, this is the file to read alongside the
[Graph-Agents wiki](https://github.com/Dark-Alex-17/coyote/wiki/Graph-Agents).
## Workflow
17 nodes. `->` is the static route; a script node can also route
dynamically via `_next`. The `▶▶` line is a parallel super-step —
those branches run concurrently:
```
parse_request (script) -> bootstrap_research (or -> ask_topic if no topic)
ask_topic (input) -> bootstrap_research
bootstrap_research (script) -> [plan, knowledge_lookup] ▶▶ parallel
plan (llm + output_schema) -> research_each_question
knowledge_lookup (rag) -> research_each_question
research_each_question (map) -> combine_findings (spawns one branch per question)
└─ research_one_question (llm) (atomic; runs N×, joins at map)
combine_findings (script) -> vet_sources
vet_sources (llm + custom tool) -> critique
critique (llm) -> reflexion_gate
reflexion_gate (script) -> synthesize (or -> research_each_question: reflexion loop)
synthesize (agent: report-writer) -> verify_sources
verify_sources (script) -> approve
approve (approval) -> end_accepted ("accept")
-> end_rejected ("reject")
-> incorporate_feedback (any free-form answer)
incorporate_feedback (script) -> research_each_question (the human-feedback loop)
```
### Node-type breakdown
| Type | Nodes |
|-----------------------------|-----------------------------------------------------------------------------------------------------------------------|
| `script` (Python) | `parse_request`, `bootstrap_research`, `combine_findings`, `reflexion_gate`, `verify_sources`, `incorporate_feedback` |
| `llm` (tools: `[]`) | `plan`, `critique` |
| `llm` (with tool whitelist) | `research_one_question`, `vet_sources` |
| `rag` | `knowledge_lookup` — local corpus retrieval |
| `map` | `research_each_question` — dynamic fan-out per sub-question |
| `agent` | `synthesize` — spawns the `report-writer` sub-agent |
| `input` | `ask_topic` |
| `approval` | `approve` |
| `end` | `end_accepted`, `end_rejected` |
## Parallel execution
The graph has two parallel super-steps where Coyote's BSP scheduler runs
branches concurrently.
**1. Context loading (`plan` ‖ `knowledge_lookup`)** — after
`bootstrap_research`, the LLM planner (which decomposes the topic into
sub-questions) and the RAG retrieval over the local `knowledge/`
corpus run side by side. They write disjoint state keys (`plan` writes
`research_plan` and `questions`; `knowledge_lookup` writes
`local_context` and `local_sources`) so no reducer is needed.
**2. Per-question research (`research_each_question` map)** — the
plan emits a `questions` array (3-5 entries, enforced by its
`output_schema`). The `map` node spawns one parallel branch per
question (`max_concurrency: 3`). Each branch is an isolated
`research_one_question` LLM invocation with web tools, instructed to
investigate exactly its assigned question. Outputs collect into
`question_findings` in input order, then `combine_findings` joins
them into a single `findings` Markdown document for downstream nodes.
`settings.max_concurrency: 4` is the graph-wide cap; the per-`map`
override (`max_concurrency: 3` on `research_each_question`) is
deliberately lower to leave headroom for the planner's tool calls
running alongside RAG.
## Local knowledge corpus
`knowledge_lookup` is a `rag` node — it runs hybrid (vector + keyword)
retrieval over every file in `knowledge/`. The directory ships with a
small `research-style-notes.md` so the RAG node has something to
retrieve against on a clean install; drop your own Markdown notes,
PDFs, or text files into `knowledge/` to bias the research toward
your local context.
The knowledge base is built once, at agent-load time, into
`~/.config/coyote/agents/deep-research/knowledge_lookup.yaml`. Because
the node fully specifies its build config (`embedding_model`,
`chunk_size`, `chunk_overlap`), the build is non-interactive. Delete
that cached file after adding or changing knowledge to force a
rebuild.
## Sub-agent: report-writer
The `synthesize` node is an `agent` node that spawns the
`report-writer` sub-agent (`assets/agents/report-writer/`). This is
the agent-as-tool pattern: the orchestrating graph delegates the
writing phase to a focused sub-agent dedicated to coherent prose,
while the research phase uses different (typically cheaper) LLM nodes
for fast-and-many-question investigation.
The `report-writer` sub-agent has no tools — it cannot access the
web, cannot search, and cannot invent facts. It reads only the
findings it is given and produces a final Markdown report preserving
every inline citation. See `assets/agents/report-writer/README.md`
for details.
## Tools and tool scoping
This agent demonstrates Coyote's three tool sources and how an `llm`
node's `tools:` whitelist scopes them per node.
The agent's full tool universe, declared in `graph.yaml`:
- **Global tools** (`global_tools`): `web_search_coyote`,
`fetch_url_via_curl`, `search_arxiv` - Coyote's built-in tool scripts.
- **MCP server** (`mcp_servers`): `ddg-search` - a DuckDuckGo web
search MCP server. Referenced in a whitelist as `mcp:ddg-search`.
- **Custom agent tool** (`tools.sh`): `classify_source` - a
deterministic source-credibility classifier shipped with this agent.
No node receives all of these. Each `llm` node's `tools:` whitelist
narrows the universe to exactly what that step needs:
| Node | `tools:` whitelist | Draws from |
|-------------------------|-----------------------------------------------------------------------------|--------------------------|
| `plan`, `critique` | `[]` | nothing - pure reasoning |
| `research_one_question` | `web_search_coyote`, `fetch_url_via_curl`, `search_arxiv`, `mcp:ddg-search` | global tools + MCP |
| `vet_sources` | `classify_source` | the custom tool only |
`research_one_question` (each parallel branch of the map) can search
and fetch but cannot classify sources; `vet_sources` can classify
sources but cannot touch the web. That separation is the point of the
`tools:` whitelist: a node gets only the tools its job calls for,
never the agent's full set.
The `classify_source` custom tool (`tools.sh`) takes a URL and returns
a credibility tier (government, academic, preprint, organization,
unverified) derived from the host and top-level domain. It is
deterministic - exactly the kind of logic a tool should own rather than
the LLM guessing.
Web search may require API-key configuration; see the
[Tools](https://github.com/Dark-Alex-17/coyote/wiki/Tools) docs.
`fetch_url_via_curl`, `search_arxiv`, and `classify_source` work
without a key.
## Setup
`research_one_question` (each parallel branch of the `map`) uses the
`ddg-search` MCP server via `mcp:ddg-search`. It is one of Coyote's
default MCP servers; make sure it is registered in
`~/.config/coyote/mcp.json` (run `coyote --install mcp_config` to restore
the default template if it is missing). If `ddg-search` is unavailable,
the branches still have their global web-search tools to fall back on.
The `synthesize` node spawns the `report-writer` sub-agent. Both
agents ship with `coyote agents install`; if you install one manually,
install both so the agent reference resolves.
## Reflexion
The agent has two loops, both built with script nodes that route via
`_next`. The engine allows back-edges at runtime; the validator only
rejects cycles built from static `next` / `routes` edges, so script
`_next` loops are always allowed.
**Automated reflexion loop.** After the parallel research map and
`vet_sources`, the `critique` node reviews the merged findings
against the research plan and the source credibility assessment, and
emits `VERDICT: PASS` or `VERDICT: REVISE` with specific feedback.
`reflexion_gate.py` then:
- `PASS` -> continue to `synthesize`.
- `REVISE`, budget remaining -> loop back to `research_each_question`,
with the critique injected as `research_feedback` so every parallel
branch sees it on the retry.
- `REVISE`, budget spent -> continue to `synthesize` anyway (the human
approval step is the final backstop).
The budget is `MAX_REFLEXION_REVISIONS` in `reflexion_gate.py`
(default 2, so the research map runs at most 3 times per pass).
**Human-feedback loop.** At `approve` the user answers `accept`,
`reject`, or types their own feedback. A free-form answer routes via
the approval node's `on_other` to `incorporate_feedback.py`, which
folds that text into `research_feedback` and loops back to
`research_each_question` for another parallel pass.
`settings.max_loop_iterations` (40) is the engine's infinite-loop
backstop: it caps the total visits to any single node.
## Running
```sh
coyote agents install # ships deep-research
coyote -a deep-research "How does HTTP/3 differ from HTTP/2?"
coyote -a deep-research "Recent advances in solid-state batteries"
coyote -a deep-research # no prompt -> triggers ask_topic
```
## Anti-hallucination
- `research_one_question` (each map branch) is instructed to back
every claim with a real retrieved source and never to fabricate
URLs, titles, or DOIs.
- `vet_sources` classifies every cited source so weak sources are
visible to the critique step.
- `critique` independently reviews the merged findings and sends weak
or uncited work back for another parallel research pass.
- `synthesize` (the `report-writer` sub-agent) is grounded: it may use
only the gathered findings and must keep each claim's inline source.
It has no tools and cannot browse the web.
- `verify_sources` probes every cited URL / DOI with an HTTP HEAD
request and reports which are unreachable, so the human reviewer
sees broken citations before approving.
## Customizing
- **Loop budget.** `MAX_REFLEXION_REVISIONS` in `reflexion_gate.py`.
- **Map concurrency.** The `research_each_question` node's
`max_concurrency: 3` caps simultaneous web-research branches.
Raise to investigate more questions in parallel; lower to be gentle
on rate-limited providers.
- **Per-node model.** Add `model: anthropic:...` to any `llm` node.
Cheap models work well for `plan` / `critique` / `vet_sources`; the
heavy intelligence is needed in `research_one_question` and the
`report-writer` sub-agent.
- **Tool scope.** Narrow the `research_one_question` node's `tools:`
list to constrain where each branch looks (for example, drop
`web_search_coyote` and `mcp:ddg-search` to force arXiv-only
research).
- **Local knowledge.** Drop files into `knowledge/` to bias every
research branch toward your local context (see the *Local
knowledge corpus* section above).
- **Different writer.** Replace `agent: report-writer` on the
`synthesize` node with the name of any other agent. The
orchestrator does not care what kind of agent the writer is.
- **Skip approval.** Point both `approve` routes at `end_accepted`,
or wire `verify_sources` straight to an `end` node.
## Files
```
assets/agents/deep-research/
graph.yaml - agent config + 17-node workflow
tools.sh - classify_source custom tool
README.md - this file
knowledge/
README.md - corpus-format notes
research-style-notes.md - starter knowledge file (replace with your notes)
scripts/
parse_request.py - _next: bootstrap_research, or ask_topic if no topic
bootstrap_research.py - fan-out source: next [plan, knowledge_lookup]
combine_findings.py - joins map output (question_findings) into findings
reflexion_gate.py - _next: research_each_question (revise) or synthesize
verify_sources.py - HTTP HEAD on cited URLs / DOIs
incorporate_feedback.py - _next: research_each_question, with user feedback
```
See also `assets/agents/report-writer/` — the sub-agent the
`synthesize` node spawns.
assets/agents/deep-research/graph.yaml
-293
View File
@@ -1,293 +0,0 @@
name: deep-research
description: |
Deep web research workflow. Plans an investigation, decomposes it
into sub-questions researched in parallel, grounds the work in a
local knowledge corpus, vets the credibility of cited sources, runs
a reflexion self-critique loop to revise weak or incomplete findings,
delegates the final write-up to a focused sub-agent, checks that the
cited sources are reachable, and gates the result behind human
approval. A reviewer's free-form feedback at the approval step feeds
back into another research pass.
This is the canonical Coyote graph-agent reference: it exercises every
node type (script, llm, rag, map, agent, input, approval, end) and
both static fan-out and dynamic map fan-out.
version: "1.0"
temperature: 0.0
global_tools:
- web_search_coyote.sh
- fetch_url_via_curl.sh
- search_arxiv.sh
mcp_servers:
- ddg-search
conversation_starters:
- "How does HTTP/3 differ from HTTP/2?"
- "Summarize recent advances in solid-state battery chemistry"
settings:
max_loop_iterations: 40
log_state_snapshots: false
validate_before_run: true
max_concurrency: 4
initial_state:
research_feedback: ""
research_attempts: 0
local_context: ""
local_sources: ""
start: parse_request
nodes:
parse_request:
id: parse_request
type: script
script: scripts/parse_request.py
next: bootstrap_research
ask_topic:
id: ask_topic
type: input
question: "What would you like me to research?"
validation: "len(input) > 0"
state_updates:
topic: "{{input}}"
next: bootstrap_research
bootstrap_research:
id: bootstrap_research
type: script
script: scripts/bootstrap_research.py
next: [plan, knowledge_lookup]
plan:
id: plan
type: llm
instructions: |
You are a research planner. Given a topic, produce a focused
research plan and decompose it into 3-5 specific sub-questions
that can each be researched independently in parallel.
The plan is a short narrative naming the key questions and the
kinds of sources that would be authoritative. The sub-questions
are precise, self-contained queries (each one is sent on its own
to a separate research worker, so they must be answerable
without each other's context).
prompt: "Research topic: {{topic}}"
tools: []
output_schema:
type: object
properties:
research_plan:
type: string
description: A short plan narrative.
questions:
type: array
items: { type: string }
minItems: 1
maxItems: 6
description: 3-5 specific, self-contained sub-questions.
required: [research_plan, questions]
next: research_each_question
knowledge_lookup:
id: knowledge_lookup
type: rag
documents:
- ./knowledge/
query: "{{topic}}"
top_k: 6
chunk_size: 1000
chunk_overlap: 100
state_updates:
local_context: "{{output.context}}"
local_sources: "{{output.sources}}"
next: research_each_question
research_each_question:
id: research_each_question
type: map
over: "{{questions}}"
as: question
branch: research_one_question
collect_into: question_findings
max_concurrency: 3
next: combine_findings
research_one_question:
id: research_one_question
type: llm
instructions: |
You are a web research assistant. Investigate the SINGLE question
given to you using your tools: search the web, fetch and read
pages, and search arXiv for academic sources.
Rules:
- Every factual claim must be backed by a real source you
actually retrieved. Never fabricate URLs, page titles,
authors, or DOIs.
- Prefer primary and authoritative sources over aggregators.
- Where sources disagree, report the disagreement rather than
papering over it.
- Put the URL (or DOI) inline next to each claim it supports.
Return organized findings in plain text. Do not include
meta-commentary about the process.
prompt: |
Research question: {{question}}
Local context that may help:
{{local_context}}
{{research_feedback}}
tools:
- web_search_coyote
- fetch_url_via_curl
- search_arxiv
- mcp:ddg-search
max_iterations: 10
max_attempts: 2
temperature: 0.1
combine_findings:
id: combine_findings
type: script
script: scripts/combine_findings.py
next: vet_sources
vet_sources:
id: vet_sources
type: llm
instructions: |
You assess the credibility of the sources cited in a set of
research findings. For every distinct source URL in the findings,
call the `classify_source` tool to get its credibility tier. Then
summarize: which claims rest on HIGH-credibility sources, and
which rest on PREPRINT or UNVERIFIED sources and so need
corroboration. Do NOT do any new research -- assess only what is
already cited.
prompt: |
Findings to assess:
{{findings}}
tools:
- classify_source
max_iterations: 15
state_updates:
source_assessment: "{{output}}"
next: critique
critique:
id: critique
type: llm
instructions: |
You are a meticulous research reviewer. Judge whether the
findings below are good enough to synthesize a complete,
well-supported report that answers the research plan.
Mark the findings REVISE if ANY of these hold:
- A research-plan question is unanswered or only weakly
addressed.
- A factual claim has no source, or cites a source that looks
fabricated.
- The findings lean on a single source where corroboration is
needed.
- A key claim rests only on a PREPRINT or UNVERIFIED source,
per the source credibility assessment below.
- An obvious counter-perspective or recent development is
missing.
Otherwise mark them PASS.
Respond in EXACTLY this format, nothing else:
VERDICT: <PASS or REVISE>
FEEDBACK: <if REVISE, be specific and actionable -- name the gaps
and what kind of source would close them; if PASS, write "none">
prompt: |
Research plan:
{{research_plan}}
Findings under review:
{{findings}}
Source credibility assessment:
{{source_assessment}}
tools: []
state_updates:
critique: "{{output}}"
next: reflexion_gate
reflexion_gate:
id: reflexion_gate
type: script
script: scripts/reflexion_gate.py
next: synthesize
synthesize:
id: synthesize
type: agent
agent: report-writer
prompt: |
Research topic: {{topic}}
Findings (organized by sub-question, with inline citations):
{{findings}}
Source credibility assessment:
{{source_assessment}}
Produce the final report following your instructions.
timeout: 300
state_updates:
report: "{{output}}"
next: verify_sources
verify_sources:
id: verify_sources
type: script
script: scripts/verify_sources.py
next: approve
approve:
id: approve
type: approval
question: |
Research report on: {{topic}}
{{report}}
----
{{source_check}}
----
Accept this report? Pick "accept" or "reject", or type specific
feedback to send the research back for another pass.
options:
- "accept"
- "reject"
routes:
"accept": end_accepted
"reject": end_rejected
on_other: incorporate_feedback
state_updates:
decision: "{{choice}}"
incorporate_feedback:
id: incorporate_feedback
type: script
script: scripts/incorporate_feedback.py
end_accepted:
id: end_accepted
type: end
output: "{{report}}"
end_rejected:
id: end_rejected
type: end
output: "Research on '{{topic}}' was rejected and discarded."
assets/agents/deep-research/knowledge/README.md
-23
View File
@@ -1,23 +0,0 @@
# Local knowledge corpus for deep-research
The `knowledge_lookup` node in `graph.yaml` is a `rag` node that runs
hybrid (vector + keyword) retrieval over every file in this directory.
Drop your own notes, papers (PDFs), Markdown docs, or text files here
and they will be indexed into a per-agent knowledge base on first run.
Coyote supports common file types out of the box: `.md`, `.txt`, `.pdf`,
`.html`, and others. Subdirectories are walked recursively.
A small starter file (`research-style-notes.md`) ships so the RAG
node has something non-empty to retrieve against on a clean install.
Replace or extend it with your own materials to bias the research
phase toward your local context.
To force the knowledge base to rebuild after you add or change files,
delete the cached index:
```sh
rm ~/.config/coyote/agents/deep-research/knowledge_lookup.yaml
```
The next run will rebuild from the current contents of this directory.
assets/agents/deep-research/knowledge/research-style-notes.md
-49
View File
@@ -1,49 +0,0 @@
# Research style notes
These are general principles the `deep-research` agent should keep in
mind regardless of topic. Replace this file with your own notes if you
want to bias retrieval toward your local context.
## What "good research" means here
- **Every factual claim cites a source you actually retrieved.** Never
fabricate URLs, page titles, authors, or DOIs.
- **Primary sources beat aggregators.** Prefer the original paper, the
RFC, the standards body, or the manufacturer over a blog summarizing
them.
- **Corroboration matters where stakes are high.** If a single source
makes a strong claim, look for a second independent source before
taking it as established.
- **Disagreement is information, not noise.** If two credible sources
disagree, report the disagreement and the reasoning on each side.
- **Old does not mean wrong.** A 2014 RFC is still authoritative if no
newer one has obsoleted it; check before assuming a source is stale.
## Source-tier heuristics
The `vet_sources` node uses these rough tiers to weigh credibility.
The custom tool `classify_source` (see `tools.sh`) implements this
deterministically by hostname / TLD.
- **HIGH:** government domains (`.gov`, `.mil`), academic institutions
(`.edu`, university subdomains), peer-reviewed journals, standards
bodies (IETF/RFCs, W3C, ISO, IEEE, NIST), and primary documents from
the entities being researched (e.g. a vendor's official spec page).
- **PREPRINT:** arXiv, bioRxiv, medRxiv, SSRN. Useful but not yet
peer-reviewed; treat numeric claims with extra caution.
- **ORGANIZATION:** established nonprofits, standards-adjacent groups,
industry consortia. Reliable for their stated mission but may have a
perspective.
- **UNVERIFIED:** general web pages, blogs, news aggregators, social
media. Useful for leads but should not be the only source for a
factual claim.
## Common pitfalls to flag in critique
- A claim cited only to a PREPRINT or UNVERIFIED source on a numeric
or contested point.
- A research-plan question that the findings address only obliquely.
- "Findings" that paraphrase a single source three times rather than
triangulating.
- Citation collisions where two sources are listed but turn out to
be the same study reported via different aggregators.
assets/agents/deep-research/scripts/bootstrap_research.py
-18
View File
@@ -1,18 +0,0 @@
#!/usr/bin/env python3
"""Fan-out source for context loading.
Has no logic of its own. Exists so the static `next: [plan, knowledge_lookup]`
list on this node fans out into two parallel branches (the LLM planner and
the RAG knowledge lookup) as a single super-step. The validator requires
declared parallel-branch script outputs, so we emit an empty JSON object
explicitly here.
"""
import json
def main():
print(json.dumps({}))
if __name__ == "__main__":
main()
assets/agents/deep-research/scripts/combine_findings.py
-39
View File
@@ -1,39 +0,0 @@
#!/usr/bin/env python3
"""Join the per-question map outputs into a single `findings` string.
The `research_each_question` map writes `question_findings` (an array,
one entry per sub-question, in input order). Downstream nodes
(`vet_sources`, `critique`, `synthesize`) read `{{findings}}` as a
single block, so this script renders the array as a Markdown document
with one section per question.
"""
import json
import os
def load_state():
path = os.environ.get("GRAPH_STATE_FILE")
if path:
with open(path) as f:
return json.load(f)
return json.loads(os.environ.get("GRAPH_STATE", "{}"))
def main():
state = load_state()
questions = state.get("questions") or []
per_question = state.get("question_findings") or []
sections = []
for idx, q in enumerate(questions):
body = per_question[idx] if idx < len(per_question) else ""
if isinstance(body, dict) or isinstance(body, list):
body = json.dumps(body, indent=2)
sections.append(f"## {q}\n\n{body}")
findings = "\n\n".join(sections) if sections else "No findings gathered."
print(json.dumps({"findings": findings}))
if __name__ == "__main__":
main()
assets/agents/deep-research/scripts/incorporate_feedback.py
-41
View File
@@ -1,41 +0,0 @@
#!/usr/bin/env python3
"""Fold a reviewer's free-form feedback back into the research loop.
Runs when the user answers the approval step with their own text
instead of "accept" or "reject". That text (saved by the approval node
as `decision`) becomes `research_feedback`, and the graph loops back to
`research_each_question` for another informed pass (each sub-question is
re-researched in parallel with the new feedback in context). The
reflexion counter is reset so the user-driven pass gets a fresh revision
budget.
Routing (`_next`): always research_each_question.
"""
import json
import os
def load_state():
path = os.environ.get("GRAPH_STATE_FILE")
if path:
with open(path) as f:
return json.load(f)
return json.loads(os.environ.get("GRAPH_STATE", "{}"))
def main():
state = load_state()
feedback = (state.get("decision") or "").strip()
output = {
"_next": "research_each_question",
"research_attempts": 0,
"research_feedback": (
"The user reviewed the report and asked for changes. Treat "
"this as the top priority for the next pass:\n\n" + feedback
),
}
print(json.dumps(output))
if __name__ == "__main__":
main()
assets/agents/deep-research/scripts/parse_request.py
-35
View File
@@ -1,35 +0,0 @@
#!/usr/bin/env python3
"""Entry router for deep-research.
Reads the caller's prompt from state. If it contains a usable research
topic, stores it as `topic` and falls through to the static `next`
(plan). If the prompt is empty, routes to `ask_topic` so the user can
supply one interactively.
Routing (`_next`):
- prompt present -> (no _next; static next: plan)
- prompt empty -> ask_topic
"""
import json
import os
def load_state():
path = os.environ.get("GRAPH_STATE_FILE")
if path:
with open(path) as f:
return json.load(f)
return json.loads(os.environ.get("GRAPH_STATE", "{}"))
def main():
state = load_state()
prompt = (state.get("initial_prompt") or "").strip()
if prompt:
print(json.dumps({"topic": prompt}))
else:
print(json.dumps({"_next": "ask_topic"}))
if __name__ == "__main__":
main()
assets/agents/deep-research/scripts/reflexion_gate.py
-76
View File
@@ -1,76 +0,0 @@
#!/usr/bin/env python3
"""Reflexion gate for deep-research.
Runs after `critique` has reviewed the current research findings. If the
critique's verdict is REVISE and the reflexion budget is not spent,
loops back to `research` with the critique attached as
`research_feedback`, so the retry is informed rather than a blind
re-run. Otherwise it proceeds to `synthesize`.
Routing (`_next`):
- verdict PASS -> synthesize
- verdict REVISE, budget remaining -> research_each_question (+ research_feedback)
- verdict REVISE, budget spent -> synthesize
Reflexion is a best-effort quality booster, not a hard gate: once the
budget is spent the workflow proceeds anyway, and the human approval
step is the final backstop.
"""
import json
import os
import re
# Automated revision passes allowed. `research` runs at most
# MAX_REFLEXION_REVISIONS + 1 times per user pass. Bump to allow more.
MAX_REFLEXION_REVISIONS = 2
def load_state():
path = os.environ.get("GRAPH_STATE_FILE")
if path:
with open(path) as f:
return json.load(f)
return json.loads(os.environ.get("GRAPH_STATE", "{}"))
def as_int(value, default=0):
try:
return int(value)
except (TypeError, ValueError):
return default
def parse_verdict(critique):
"""Pull PASS/REVISE from the critique's `VERDICT:` line. Defaults to
PASS when no verdict line is found, so a malformed critique lets the
workflow proceed instead of burning the whole revision budget."""
match = re.search(r"VERDICT:\s*([A-Za-z]+)", critique, re.IGNORECASE)
if not match:
return "PASS"
return match.group(1).upper()
def main():
state = load_state()
critique = state.get("critique") or ""
verdict = parse_verdict(critique)
attempts = as_int(state.get("research_attempts"))
if verdict == "REVISE" and attempts < MAX_REFLEXION_REVISIONS:
feedback = (
"A reviewer judged the previous research pass incomplete. "
"Address every point in the critique below:\n\n" + critique
)
output = {
"_next": "research_each_question",
"research_attempts": attempts + 1,
"research_feedback": feedback,
}
else:
output = {"_next": "synthesize"}
print(json.dumps(output))
if __name__ == "__main__":
main()
assets/agents/deep-research/scripts/verify_sources.py
-69
View File
@@ -1,69 +0,0 @@
#!/usr/bin/env python3
"""Check that the sources cited in the research report are reachable.
Scans the final report for URLs and DOIs, probes each with a HEAD
request, and writes a `source_check` summary into state so the human
reviewer sees broken citations at the approval step.
Times out per request so a slow source cannot stall the graph.
"""
import json
import os
import re
import urllib.error
import urllib.request
DOI_RE = re.compile(r"\b(10\.\d{4,9}/[-._;()/:A-Z0-9]+)", re.IGNORECASE)
URL_RE = re.compile(r"https?://[^\s)\]\}\"'>]+")
def load_state():
path = os.environ.get("GRAPH_STATE_FILE")
if path:
with open(path) as f:
return json.load(f)
return json.loads(os.environ.get("GRAPH_STATE", "{}"))
def reachable(url, timeout=5.0):
req = urllib.request.Request(url, method="HEAD")
try:
with urllib.request.urlopen(req, timeout=timeout) as resp:
return 200 <= resp.status < 400
except urllib.error.HTTPError as e:
return 200 <= e.code < 400
except Exception:
return False
def main():
state = load_state()
report = state.get("report") or ""
urls = sorted({u.rstrip(".,;)") for u in URL_RE.findall(report)})
dois = sorted(set(DOI_RE.findall(report)))
results = []
for url in urls:
ok = reachable(url)
results.append(f" {'OK' if ok else 'UNREACHABLE'} {url}")
for doi in dois:
url = f"https://doi.org/{doi}"
if url in urls:
continue
ok = reachable(url)
results.append(f" {'OK' if ok else 'UNREACHABLE'} DOI {doi} ({url})")
if not results:
summary = "No web sources were cited in the report."
else:
summary = (
f"Source reachability ({len(results)} checked):\n"
+ "\n".join(results)
)
print(json.dumps({"source_check": summary}))
if __name__ == "__main__":
main()
assets/agents/deep-research/tools.sh
-39
View File
@@ -1,39 +0,0 @@
#!/usr/bin/env bash
set -e
# @env LLM_OUTPUT=/dev/stdout The output path
# @cmd Classify the credibility tier of a web source from its URL.
# A deterministic check based on the host and top-level domain. Use it
# to weigh how much trust to place in a source before relying on it.
# @option --url! The full source URL to classify
classify_source() {
# shellcheck disable=SC2154
local url="$argc_url"
local host="${url#*://}"
host="${host%%/*}"
host="${host##*@}"
host="${host%%:*}"
host="$(printf '%s' "$host" | tr '[:upper:]' '[:lower:]')"
local tier
case "$host" in
'')
tier="UNKNOWN - no host could be parsed from the URL" ;;
*.gov | *.gov.* | *.mil)
tier="HIGH - government source" ;;
*.edu | *.edu.* | *.ac.*)
tier="HIGH - academic institution" ;;
arxiv.org | *.arxiv.org | biorxiv.org | *.biorxiv.org | medrxiv.org | *.medrxiv.org | ssrn.com | *.ssrn.com)
tier="PREPRINT - not yet peer reviewed, corroborate before citing" ;;
wikipedia.org | *.wikipedia.org)
tier="TERTIARY - encyclopedia, good for orientation not citation" ;;
*.org | *.org.*)
tier="MEDIUM - organization site, check for institutional bias" ;;
*)
tier="UNVERIFIED - general web source, corroborate before citing" ;;
esac
printf '%s: %s\n' "${host:-<none>}" "$tier" >> "$LLM_OUTPUT"
}
assets/agents/demo/README.md
+1 -1
View File
@@ -2,6 +2,6 @@
This agent serves as a demo to guide agent development and showcase various agent capabilities.
To enable tools, Coyote will look for the first `tools.py` or `tools.sh` file it finds in this directory.
To enable tools, Loki will look for the first `tools.py` or `tools.sh` file it finds in this directory.
The base configuration using `tools.py`. To switch to using `tools.sh`, rename or remove `tools.py`.
assets/agents/explore/README.md
+2 -2
View File
@@ -17,7 +17,7 @@ It can also be used as a standalone tool for understanding codebases and finding
## Pro-Tip: Use an IDE MCP Server for Improved Performance
Many modern IDEs now include MCP servers that let LLMs perform operations within the IDE itself and use IDE tools. Using
an IDE's MCP server dramatically improves the performance of coding agents. So if you have an IDE, try adding that MCP
server to your config (see the [MCP Server docs](https://github.com/Dark-Alex-17/loki/wiki/MCP-Servers) to see how to configure
server to your config (see the [MCP Server docs](../../../docs/function-calling/MCP-SERVERS.md) to see how to configure
them), and modify the agent definition to look like this:
```yaml
@@ -31,7 +31,7 @@ global_tools:
- fs_grep.sh
- fs_glob.sh
- fs_ls.sh
- web_search_coyote.sh
- web_search_loki.sh
# ...
```
assets/agents/jira-helper/README.md
+14
View File
@@ -0,0 +1,14 @@
# Jira AI Agent
## Overview
The Jira AI Agent is designed to assist with managing tasks within Jira projects, providing capabilities such as
creating, searching, updating, assigning, linking, and commenting on issues. Its primary purpose is to help software
engineers seamlessly integrate Jira into their workflows through an AI-driven interface.
## Configuration
This agent uses the official [Atlassian MCP Server](https://github.com/atlassian/atlassian-mcp-server). To use it,
ensure you have Node.js v18+ installed to run the local MCP proxy (`mcp-remote`).
The server uses OAuth 2.0 so it will automatically open your browser for you to sign in to your account. No manual
configuration is necessary!
assets/agents/jira-helper/config.yaml
+37
View File
@@ -0,0 +1,37 @@
name: Jira Agent
description: An AI agent that can assist with Jira tasks such as creating issues, searching for issues, and updating issues.
version: 0.1.0
agent_session: temp
mcp_servers:
- atlassian
instructions: |
You are a AI agent designed to assist with managing Jira tasks and helping software engineers utilize and integrate
Jira into their workflows. You can create, search, update, assign, link, and comment on issues in Jira.
## Create Issue (MANDATORY when creating a issue)
When a user prompts you to create a Jira issue:
1. Prompt the user for what Jira project they want the ticket created in
2. If the ticket type requires a parent issue:
a. Query Jira for potentially relevant parents
b. Prompt user for which parent to use, displaying the suggested list of parent issues
3. Create the issue with the following format:
```markdown
**Description:**
This section gives context and details about the issue.
**User Acceptance Criteria:**
# This section provides bullet points that function like a checklist of all the things that must be completed in
# order for the issue to be considered done.
* Example criteria one
* Example criteria two
```
4. Ask the user if the issue should be assigned to them
a. If yes, then assign the user to the newly created issue
Available tools:
{{__tools__}}
conversation_starters:
- What are the latest issues in my Jira project?
- Can you create a new Jira issue for me?
- What are my open Jira issues?
- Can you search for issues with the label "bug" in my Jira project?
assets/agents/oracle/README.md
+2 -2
View File
@@ -19,7 +19,7 @@ It can also be used as a standalone tool for design reviews and solving difficul
## Pro-Tip: Use an IDE MCP Server for Improved Performance
Many modern IDEs now include MCP servers that let LLMs perform operations within the IDE itself and use IDE tools. Using
an IDE's MCP server dramatically improves the performance of coding agents. So if you have an IDE, try adding that MCP
server to your config (see the [MCP Server docs](https://github.com/Dark-Alex-17/loki/wiki/MCP-Servers) to see how to configure
server to your config (see the [MCP Server docs](../../../docs/function-calling/MCP-SERVERS.md) to see how to configure
them), and modify the agent definition to look like this:
```yaml
@@ -33,7 +33,7 @@ global_tools:
- fs_grep.sh
- fs_glob.sh
- fs_ls.sh
- web_search_coyote.sh
- web_search_loki.sh
# ...
```
assets/agents/report-writer/README.md
-46
View File
@@ -1,46 +0,0 @@
# report-writer
A tiny, focused sub-agent that turns a set of research findings into a
single coherent final report. Reads only what it is given — does not
do independent research, does not access the web, does not invent
facts. It exists as a focused tool for orchestrating agents to
delegate the writing phase to.
## Why a separate agent?
This is an example of the **agent-as-tool** pattern in graph agents.
The `deep-research` graph agent's `synthesize` node is an `agent` node
that spawns this one (see `assets/agents/deep-research/graph.yaml`).
Separating the role has two practical benefits:
- The orchestrating agent can use a cheap model (or a high-temperature
exploratory one) for the research phase, while letting the writing
phase use a different (typically lower-temperature, possibly larger)
model dedicated to coherent prose.
- The writing prompt is owned by this agent's `config.yaml` rather
than buried inside another agent's graph. You can polish it
independently without touching the research flow.
## Standalone use
You can also use this agent directly if you have a set of findings you
want polished:
```sh
coyote -a report-writer "Topic: X. Findings: <paste findings here>"
```
It will produce a single Markdown report following the rules in its
system prompt: executive summary at the top, grouped sections by
related sub-questions, every inline citation preserved verbatim, and a
final "Open questions / disagreements" section.
## What it will NOT do
- Search the web, fetch URLs, query an MCP server, or use any tool.
It has no tools configured.
- Invent facts beyond what is in the findings you give it.
- Strip or rewrite citations.
These constraints are the point of the agent existing: a writer that
the orchestrator can trust to stay in its lane.
assets/agents/report-writer/config.yaml
-34
View File
@@ -1,34 +0,0 @@
name: report-writer
description: Polishes research findings into a clear, citation-preserving final report
version: 1.0.0
temperature: 0.2
instructions: |
You are a technical writer. You will be given:
- a research topic
- a set of findings, organized per sub-question, with inline
citations next to each claim
- a source-credibility assessment of the cited sources
Your job is to produce a single, well-organized final report:
Rules:
- Use ONLY the findings provided. Do not introduce facts from
your own memory. Do not speculate beyond what the findings
support.
- Preserve every inline citation. If a sentence in the findings
had a URL or DOI, the equivalent sentence in your report must
keep the same citation.
- Lead with a 2-3 sentence executive summary at the top.
- Organize the body so that related sub-questions are grouped,
not strictly one section per question. The findings are raw
material; the report should read as a single coherent answer
to the original topic.
- End with a short "Open questions / disagreements" section
naming anything the findings flagged as unresolved or
contested.
Output plain Markdown. No metadata, no JSON wrapper.
conversation_starters:
- "Polish these findings into a cited report"
assets/agents/sisyphus/README.md
+7 -6
View File
@@ -1,6 +1,6 @@
# Sisyphus
The main coordinator agent for the Coyote coding ecosystem, providing a powerful CLI interface for code generation and
The main coordinator agent for the Loki coding ecosystem, providing a powerful CLI interface for code generation and
project management similar to OpenCode, ClaudeCode, Codex, or Gemini CLI.
_Inspired by the Sisyphus and Oracle agents of OpenCode._
@@ -18,22 +18,23 @@ Sisyphus acts as the primary entry point, capable of handling complex tasks by c
- 🛠️ **Tool Integration**: Seamlessly uses system tools for building, testing, and file manipulation.
## Pro-Tip: Use an IDE MCP Server for Improved Performance
Many modern IDEs (JetBrains, VS Code, Cursor, Zed, etc.) expose MCP servers that let LLMs use IDE tools directly. Using
one dramatically improves the performance of coding agents. If you have one, add it to your coyote config (see the
[MCP Server docs](https://github.com/Dark-Alex-17/loki/wiki/MCP-Servers)) and reference it in this agent's `mcp_servers:` list:
Many modern IDEs now include MCP servers that let LLMs perform operations within the IDE itself and use IDE tools. Using
an IDE's MCP server dramatically improves the performance of coding agents. So if you have an IDE, try adding that MCP
server to your config (see the [MCP Server docs](../../../docs/function-calling/MCP-SERVERS.md) to see how to configure
them), and modify the agent definition to look like this:
```yaml
# ...
mcp_servers:
- your-ide-mcp-server
- jetbrains
global_tools:
- fs_read.sh
- fs_grep.sh
- fs_glob.sh
- fs_ls.sh
- web_search_coyote.sh
- web_search_loki.sh
- execute_command.sh
# ...
assets/agents/sisyphus/config.yaml
+12 -29
View File
@@ -119,21 +119,20 @@ instructions: |
1. todo__init --goal "Add user profiles API endpoint"
2. todo__add --task "Explore existing API patterns"
3. todo__add --task "Implement profile endpoint"
4. agent__spawn --agent explore --prompt "Find existing API endpoint patterns, route structures, and controller conventions. Include code snippets."
5. agent__spawn --agent explore --prompt "Find existing data models and database query patterns. Include code snippets."
6. agent__collect --id <id1>
7. agent__collect --id <id2>
8. todo__done --id 1
9. agent__spawn --agent coder --prompt "<structured prompt using Coder Delegation Format above, including code snippets from explore results>"
10. agent__collect --id <coder_id>
11. todo__done --id 2
4. todo__add --task "Verify with build/test"
5. agent__spawn --agent explore --prompt "Find existing API endpoint patterns, route structures, and controller conventions. Include code snippets."
6. agent__spawn --agent explore --prompt "Find existing data models and database query patterns. Include code snippets."
7. agent__collect --id <id1>
8. agent__collect --id <id2>
9. todo__done --id 1
10. agent__spawn --agent coder --prompt "<structured prompt using Coder Delegation Format above, including code snippets from explore results>"
11. agent__collect --id <coder_id>
12. todo__done --id 2
13. run_build
14. run_tests
15. todo__done --id 3
```
Note: the `coder` agent is a graph agent that runs verification (build +
tests) and a bounded fix-loop internally. You do NOT need to spawn a
separate build/test step. A `CODER_COMPLETE` outcome means build and
tests already passed.
### Example 2: Architecture/design question (explore + oracle in parallel)
User: "How should I structure the authentication for this app?"
@@ -173,22 +172,6 @@ instructions: |
10. **Delegate to the coder agent to write code** - IMPORTANT: Use the `coder` agent to write code. Do not try to write code yourself except for trivial changes
11. **Always output a summary of changes when finished** - Make it clear to user's that you've completed your tasks
## Coder Outcomes
The `coder` agent is a graph agent that runs the implement -> verify_build
-> verify_tests -> fix_loop pipeline internally. It always returns one of
three sentinel outcomes:
- `CODER_COMPLETE` - implementation succeeded with build + tests green.
Continue with any follow-up todos.
- `CODER_REJECTED` - user rejected the plan at the approval gate (only
triggered for high-complexity plans). Do NOT re-spawn coder blindly;
ask the user what to change first.
- `CODER_FAILED` - the fix-loop exhausted its budget without producing
green build/tests. The failure output includes the last build and tests
output. Surface this to the user; consider spawning `oracle` for
diagnosis if the failure is unclear.
## When to Do It Yourself
- Simple command execution
assets/arena.html
+1106
View File
File diff suppressed because it is too large Load Diff
assets/functions/mcp.json
-4
View File
@@ -1,7 +1,6 @@
{
"mcpServers": {
"github": {
"type": "stdio",
"command": "docker",
"args": [
"run",
@@ -16,17 +15,14 @@
}
},
"atlassian": {
"type": "stdio",
"command": "npx",
"args": ["-y", "mcp-remote@0.1.13", "https://mcp.atlassian.com/v1/mcp"]
},
"docker": {
"type": "stdio",
"command": "uvx",
"args": ["mcp-server-docker"]
},
"ddg-search": {
"type": "stdio",
"command": "uvx",
"args": ["duckduckgo-mcp-server"]
}
assets/functions/scripts/run-agent.sh
+2 -2
View File
@@ -73,11 +73,11 @@ def to_args:
to_entries | .[] |
(.key | split("_") | join("-")) as $key |
if .value | type == "array" then
.value | .[] | "--\($key)=\(. | escape_shell_word)"
.value | .[] | "--\($key) \(. | escape_shell_word)"
elif .value | type == "boolean" then
if .value then "--\($key)" else "" end
else
"--\($key)=\(.value | escape_shell_word)"
"--\($key) \(.value | escape_shell_word)"
end;
[ to_args ] | join(" ")
EOF
assets/functions/scripts/run-tool.sh
+2 -2
View File
@@ -70,11 +70,11 @@ def to_args:
to_entries | .[] |
(.key | split("_") | join("-")) as $key |
if .value | type == "array" then
.value | .[] | "--\($key)=\(. | escape_shell_word)"
.value | .[] | "--\($key) \(. | escape_shell_word)"
elif .value | type == "boolean" then
if .value then "--\($key)" else "" end
else
"--\($key)=\(.value | escape_shell_word)"
"--\($key) \(.value | escape_shell_word)"
end;
[ to_args ] | join(" ")
EOF
assets/functions/tools/query_jira_issues.sh
Executable
+11
View File
@@ -0,0 +1,11 @@
#!/usr/bin/env bash
set -e
# @meta require-tools jira
# @describe Query for jira issues using a Jira Query Language (JQL) query
# @option --jql-query! The Jira Query Language query to execute
# @env LLM_OUTPUT=/dev/stdout The output path
main() {
jira issue ls -q "$argc_jql_query" --plain >> "$LLM_OUTPUT"
}
assets/functions/tools/web_search_coyote.sh → assets/functions/tools/web_search_loki.sh
+6 -6
View File
@@ -6,11 +6,11 @@ set -e
# @option --query! The search query.
# @meta require-tools coyote
# @meta require-tools loki
# @env WEB_SEARCH_MODEL=gemini:gemini-2.5-flash The model for web-searching.
#
# supported coyote models:
# supported loki models:
# - gemini:gemini-2.0-*
# - vertexai:gemini-*
# - perplexity:*
@@ -22,15 +22,15 @@ main() {
client="${WEB_SEARCH_MODEL%%:*}"
if [[ "$client" == "gemini" ]]; then
export COYOTE_PATCH_GEMINI_CHAT_COMPLETIONS='{".*":{"body":{"tools":[{"google_search":{}}]}}}'
export LOKI_PATCH_GEMINI_CHAT_COMPLETIONS='{".*":{"body":{"tools":[{"google_search":{}}]}}}'
elif [[ "$client" == "vertexai" ]]; then
export COYOTE_PATCH_VERTEXAI_CHAT_COMPLETIONS='{
export LOKI_PATCH_VERTEXAI_CHAT_COMPLETIONS='{
"gemini-1.5-.*":{"body":{"tools":[{"googleSearchRetrieval":{}}]}},
"gemini-2.0-.*":{"body":{"tools":[{"google_search":{}}]}}
}'
elif [[ "$client" == "ernie" ]]; then
export COYOTE_PATCH_ERNIE_CHAT_COMPLETIONS='{".*":{"body":{"web_search":{"enable":true}}}}'
export LOKI_PATCH_ERNIE_CHAT_COMPLETIONS='{".*":{"body":{"web_search":{"enable":true}}}}'
fi
coyote -m "$WEB_SEARCH_MODEL" "$argc_query" >> "$LLM_OUTPUT"
loki -m "$WEB_SEARCH_MODEL" "$argc_query" >> "$LLM_OUTPUT"
}
assets/functions/utils/prompt-utils.sh
+19 -15
View File
@@ -506,14 +506,16 @@ open_link() {
}
guard_operation() {
if [[ -z "$AUTO_CONFIRM" && -z "$LLM_AGENT_VAR_AUTO_CONFIRM" ]]; then
ans="$(confirm "${1:-Are you sure you want to continue?}")"
if [[ -t 1 ]]; then
if [[ -z "$AUTO_CONFIRM" && -z "$LLM_AGENT_VAR_AUTO_CONFIRM" ]]; then
ans="$(confirm "${1:-Are you sure you want to continue?}")"
if [[ "$ans" == 0 ]]; then
error "Operation aborted!" 2>&1
exit 1
if [[ "$ans" == 0 ]]; then
error "Operation aborted!" 2>&1
exit 1
fi
fi
fi
fi
}
# Here is an example of a patch block that can be applied to modify the file to request the user's name:
@@ -653,17 +655,19 @@ guard_path() {
exit 1
fi
path="$(_to_real_path "$1")"
confirmation_prompt="$2"
if [[ -t 1 ]]; then
path="$(_to_real_path "$1")"
confirmation_prompt="$2"
if [[ ! "$path" == "$(pwd)"* && -z "$AUTO_CONFIRM" && -z "$LLM_AGENT_VAR_AUTO_CONFIRM" ]]; then
ans="$(confirm "$confirmation_prompt")"
if [[ ! "$path" == "$(pwd)"* && -z "$AUTO_CONFIRM" && -z "$LLM_AGENT_VAR_AUTO_CONFIRM" ]]; then
ans="$(confirm "$confirmation_prompt")"
if [[ "$ans" == 0 ]]; then
error "Operation aborted!" >&2
exit 1
fi
fi
if [[ "$ans" == 0 ]]; then
error "Operation aborted!" >&2
exit 1
fi
fi
fi
}
_to_real_path() {
assets/playground.html
+1589
View File
File diff suppressed because it is too large Load Diff
assets/roles/atlassian.md
-8
View File
@@ -1,8 +0,0 @@
---
enabled_mcp_servers: atlassian
---
You are the librarian for the company's Confluence and Jira knowledge bases. Your job is to help users find and retrieve
information from these platforms. Use all tools at your disposal to answer user queries.
Available Tools:
{{__tools__}}
assets/roles/repo-analyzer.md
+1 -1
View File
@@ -9,7 +9,7 @@ security/configuration settings. The analysis aims to ensure a thorough understa
structured and operates, enabling the creation of new files, maintaining consistency with existing practices, and the
potential implementation of best practices.
Should the root directory contain a `COYOTE.md` file, this was generated by Coyote and should be used as a reference
Should the root directory contain a `LOKI.md` file, this was generated by Loki and should be used as a reference
point for all analysis, style questions, etc.
**Objective:** Enable the AI to thoroughly analyze a software repository, providing detailed insights and guidelines on
config.agent.example.yaml
+9 -11
View File
@@ -1,5 +1,5 @@
# Agent-specific configuration
# Location `<coyote-config-dir>/agents/<agent-name>/config.yaml`
# Location `<loki-config-dir>/agents/<agent-name>/config.yaml`
#
# Available Environment Variables:
# - <agent-name>_MODEL
@@ -17,18 +17,16 @@ agent_session: null # Set a session to use when starting the agent.
name: <agent-name> # Name of the agent, used in the UI and logs
description: <description> # Description of the agent, used in the UI
version: 1 # Version of the agent
# Auto-Continue (Todo System)
# The auto-continue system provides built-in task tracking for improved reliability.
# When enabled, the model can create todo lists and the system will automatically
# prompt it to continue when incomplete tasks remain.
# See the [Todo System documentation](https://github.com/Dark-Alex-17/coyote/wiki/TODO-System) for more information
# Todo System & Auto-Continuation
# These settings help smaller models handle multi-step tasks more reliably.
# See docs/TODO-SYSTEM.md for detailed documentation.
auto_continue: false # Enable automatic continuation when incomplete todos remain
max_auto_continues: 10 # Maximum number of automatic continuations before stopping
inject_todo_instructions: true # Inject the default todo tool usage instructions into the agent's system prompt
continuation_prompt: null # Custom prompt used when auto-continuing (optional; uses default if null)
# Sub-Agent Spawning System
# Enable this agent to spawn and manage child agents in parallel.
# See https://github.com/Dark-Alex-17/coyote/wiki/Agents for detailed documentation.
# See docs/AGENTS.md for detailed documentation.
can_spawn_agents: false # Enable the agent to spawn child agents
max_concurrent_agents: 4 # Maximum number of agents that can run simultaneously
max_agent_depth: 3 # Maximum nesting depth for sub-agents (prevents runaway spawning)
@@ -37,7 +35,7 @@ summarization_model: null # Model to use for summarizing sub-agent output
summarization_threshold: 4000 # Character threshold above which sub-agent output is summarized before returning to parent
escalation_timeout: 300 # Seconds a sub-agent waits for a user interaction response before timing out (default: 5 minutes)
mcp_servers: # Optional list of MCP servers that the agent utilizes
- github # Corresponds to the name of an MCP server in the `<coyote-config-dir>/functions/mcp.json` file
- github # Corresponds to the name of an MCP server in the `<loki-config-dir>/functions/mcp.json` file
global_tools: # Optional list of additional global tools to enable for the agent; i.e. not tools specific to the agent
- web_search
- fs
@@ -80,10 +78,10 @@ conversation_starters: # Optional conversation starters for the agent
- What is the best way to exercise?
- How do I manage my time effectively?
documents: # Optional documents to load for the agent
- git:/some/repo # Explicitly tell Coyote to use the 'git' document loader using an absolute path
- pdf:some-pdf-file.pdf # Explicitly tell Coyote to use the 'pdf' document loader using a relative path
- git:/some/repo # Explicitly tell Loki to use the 'git' document loader using an absolute path
- pdf:some-pdf-file.pdf # Explicitly tell Loki to use the 'pdf' document loader using a relative path
- https://some-website.com/some-page
- some-file.pdf # File with relative path to the <coyote-config-dir>/agents/<agent-name> directory; i.e. file in the same directory as this config file
- some-file.pdf # File with relative path to the <loki-config-dir>/agents/<agent-name> directory; i.e. file in the same directory as this config file
- ~/some-file.txt # File in the user's home directory
- /absolute/path/to/some-file.md # File with absolute path
- /absolute/path/**/NAME.txt # Find all NAME.txt files in the specified directory and all its subdirectories
config.example.yaml
+46 -55
View File
@@ -18,31 +18,31 @@ agent_session: null # Set a session to use when starting an agent (
# ---- Appearance ----
highlight: true # Controls syntax highlighting
light_theme: false # Activates a light color theme when true. env: COYOTE_LIGHT_THEME
light_theme: false # Activates a light color theme when true. env: LOKI_LIGHT_THEME
# ---- Miscellaneous ----
user_agent: null # Set User-Agent HTTP header, use `auto` for coyote/<current-version>
user_agent: null # Set User-Agent HTTP header, use `auto` for loki/<current-version>
save_shell_history: true # Whether to save shell execution command to the history file
sync_models_url: > # URL to sync model changes from
https://raw.githubusercontent.com/Dark-Alex-17/coyote/refs/heads/main/models.yaml
https://raw.githubusercontent.com/Dark-Alex-17/loki/refs/heads/main/models.yaml
# ---- REPL Prompt ----
# Custom REPL left/right prompts; see the [REPL Prompt Documentation](https://github.com/Dark-Alex-17/coyote/wiki/REPL-Prompt) for more information
# Custom REPL left/right prompts; see the [REPL Prompt Documentation](./docs/REPL-PROMPT.md) for more information
left_prompt:
'{color.red}{model}){color.green}{?session {?agent {agent}>}{session}{?role /}}{!session {?agent {agent}>}}{role}{?rag @{rag}}{color.cyan}{?session )}{!session >}{color.reset} '
right_prompt:
'{color.purple}{?session {?consume_tokens {consume_tokens}({consume_percent}%)}{!consume_tokens {consume_tokens}}}{color.reset}'
# ---- Vault ----
# See the [Vault documentation](https://github.com/Dark-Alex-17/coyote/wiki/Vault) for more information on the Coyote vault
vault_password_file: null # Path to a file containing the password for the Coyote vault (cannot be a secret template)
# See the [Vault documentation](./docs/VAULT.md) for more information on the Loki vault
vault_password_file: null # Path to a file containing the password for the Loki vault (cannot be a secret template)
# ---- Function Calling ----
# See the [Tools documentation](https://github.com/Dark-Alex-17/coyote/wiki/Tools) for more details
# See the [Tools documentation](./docs/function-calling/TOOLS.md) for more details
function_calling: true # Enables or disables function calling (Globally).
mapping_tools: # Alias for a tool or toolset
fs: 'fs_cat,fs_ls,fs_mkdir,fs_rm,fs_write,fs_read,fs_glob,fs_grep'
enabled_tools: null # Which tools to enable by default. (e.g. 'fs,web_search_coyote')
enabled_tools: null # Which tools to enable by default. (e.g. 'fs,web_search_loki')
visible_tools: # Which tools are visible to be compiled (and are thus able to be defined in 'enabled_tools')
# - demo_py.py
# - demo_sh.sh
@@ -64,34 +64,25 @@ visible_tools: # Which tools are visible to be compiled (and a
# - get_current_weather.py
# - get_current_weather.ts
- get_current_weather.sh
- query_jira_issues.sh
# - search_arxiv.sh
# - search_wikipedia.sh
# - search_wolframalpha.sh
# - send_mail.sh
# - send_twilio.sh
# - web_search_coyote.sh
# - web_search_loki.sh
# - web_search_perplexity.sh
# - web_search_tavily.sh
# ---- MCP Servers ----
# See the [MCP Servers documentation](https://github.com/Dark-Alex-17/coyote/wiki/MCP-Servers) for more details
# See the [MCP Servers documentation](./docs/MCP-SERVERS.md) for more details
mcp_server_support: true # Enables or disables MCP servers (globally).
mapping_mcp_servers: # Alias for an MCP server or set of servers
git: github,gitmcp
enabled_mcp_servers: null # Which MCP servers to enable by default (e.g. 'github,slack,ddg-search')
# ---- Auto-Continue (Todo System) ----
# The auto-continue system provides built-in task tracking for improved reliability.
# When enabled, the model can create todo lists and the system will automatically
# prompt it to continue when incomplete tasks remain.
# See the [Todo System documentation](https://github.com/Dark-Alex-17/coyote/wiki/TODO-System) for more information
auto_continue: false # Enable automatic continuation when incomplete todos remain (default: false)
max_auto_continues: 10 # Maximum number of automatic continuations before stopping (default: 10)
inject_todo_instructions: true # Inject default todo usage instructions into the system prompt (default: true)
continuation_prompt: null # Custom prompt used when auto-continuing. If null, uses built-in default
# ---- Session ----
# See the [Session documentation](https://github.com/Dark-Alex-17/coyote/wiki/Sessions) for more information
# See the [Session documentation](./docs/SESSIONS.md) for more information
save_session: null # Controls the persistence of the session. If true, auto save; if false, don't auto-save save; if null, ask the user what to do
compression_threshold: 4000 # Compress the session when the token count reaches or exceeds this threshold
summarization_prompt: > # The text prompt used for creating a concise summary of session message
@@ -100,9 +91,9 @@ summary_context_prompt: > # The text prompt used for including the summar
'This is a summary of the chat history as a recap: '
# ---- RAG ----
# See the [RAG Docs](https://github.com/Dark-Alex-17/coyote/wiki/RAG) for more details.
# See the [RAG Docs](./docs/RAG.md) for more details.
rag_embedding_model: null # Specifies the embedding model used for context retrieval
rag_reranker_model: null # Specifies the reranker model used for sorting retrieved documents; Coyote uses Reciprocal Rank Fusion by default
rag_reranker_model: null # Specifies the reranker model used for sorting retrieved documents; Loki uses Reciprocal Rank Fusion by default
rag_top_k: 5 # Specifies the number of documents to retrieve for answering queries
rag_chunk_size: null # Defines the size of chunks for document processing in characters
rag_chunk_overlap: null # Defines the overlap between chunks
@@ -141,12 +132,12 @@ document_loaders:
docx: 'pandoc --to plain $1' # Use pandoc to convert a .docx file to text
# (see https://pandoc.org for details on how to install pandoc)
jina: 'curl -fsSL https://r.jina.ai/$1 -H "Authorization: Bearer {{JINA_API_KEY}}' # Use Jina to translate a website into text;
# Requires a Jina API key to be added to the Coyote vault
# Requires a Jina API key to be added to the Loki vault
git: > # Use yek to load a git repository into the knowledgebase (https://github.com/bodo-run/yek)
sh -c "yek $1 --json | jq 'map({ path: .filename, contents: .content })'"
# ---- Clients ----
# See the [Clients documentation](https://github.com/Dark-Alex-17/coyote/wiki/Clients) for more details
# See the [Clients documentation](./docs/clients/CLIENTS.md) for more details
clients:
# All clients have the following configuration:
# - type: xxxx
@@ -177,14 +168,14 @@ clients:
# See https://platform.openai.com/docs/quickstart
- type: openai
api_base: https://api.openai.com/v1 # Optional
api_key: '{{OPENAI_API_KEY}}' # You can either hard-code or inject secrets from the Coyote vault
api_key: '{{OPENAI_API_KEY}}' # You can either hard-code or inject secrets from the Loki vault
organization_id: org-xxx # Optional
# For any platform compatible with OpenAI's API
- type: openai-compatible
name: ollama
api_base: http://localhost:11434/v1
api_key: '{{OLLAMA_API_KEY}}' # Optional; You can either hard-code or inject secrets from the Coyote vault
api_key: '{{OLLAMA_API_KEY}}' # Optional; You can either hard-code or inject secrets from the Loki vault
models:
- name: deepseek-r1
max_input_tokens: 131072
@@ -202,9 +193,9 @@ clients:
# See https://ai.google.dev/docs
- type: gemini
api_base: https://generativelanguage.googleapis.com/v1beta
api_key: '{{GEMINI_API_KEY}}' # You can either hard-code or inject secrets from the Coyote vault
auth: null # When set to 'oauth', Coyote will use OAuth instead of an API key
# Authenticate with `coyote --authenticate` or `.authenticate` in the REPL
api_key: '{{GEMINI_API_KEY}}' # You can either hard-code or inject secrets from the Loki vault
auth: null # When set to 'oauth', Loki will use OAuth instead of an API key
# Authenticate with `loki --authenticate` or `.authenticate` in the REPL
patch:
chat_completions:
'.*':
@@ -222,49 +213,49 @@ clients:
# See https://docs.anthropic.com/claude/reference/getting-started-with-the-api
- type: claude
api_base: https://api.anthropic.com/v1 # Optional
api_key: '{{ANTHROPIC_API_KEY}}' # You can either hard-code or inject secrets from the Coyote vault
auth: null # When set to 'oauth', Coyote will use OAuth instead of an API key
# Authenticate with `coyote --authenticate` or `.authenticate` in the REPL
api_key: '{{ANTHROPIC_API_KEY}}' # You can either hard-code or inject secrets from the Loki vault
auth: null # When set to 'oauth', Loki will use OAuth instead of an API key
# Authenticate with `loki --authenticate` or `.authenticate` in the REPL
# See https://docs.mistral.ai/
- type: openai-compatible
name: mistral
api_base: https://api.mistral.ai/v1
api_key: '{{MISTRAL_API_KEY}}' # You can either hard-code or inject secrets from the Coyote vault
api_key: '{{MISTRAL_API_KEY}}' # You can either hard-code or inject secrets from the Loki vault
# See https://docs.x.ai/docs
- type: openai-compatible
name: xai
api_base: https://api.x.ai/v1
api_key: '{{XAI_API_KEY}}' # You can either hard-code or inject secrets from the Coyote vault
api_key: '{{XAI_API_KEY}}' # You can either hard-code or inject secrets from the Loki vault
# See https://docs.ai21.com/docs/overview
- type: openai-compatible
name: ai12
api_base: https://api.ai21.com/studio/v1
api_key: '{{AI21_API_KEY}}' # You can either hard-code or inject secrets from the Coyote vault
api_key: '{{AI21_API_KEY}}' # You can either hard-code or inject secrets from the Loki vault
# See https://docs.cohere.com/docs/the-cohere-platform
- type: cohere
api_base: https://api.cohere.ai/v2 # Optional
api_key: '{{COHERE_API_KEY}}' # You can either hard-code or inject secrets from the Coyote vault
api_key: '{{COHERE_API_KEY}}' # You can either hard-code or inject secrets from the Loki vault
# See https://docs.perplexity.ai/getting-started/overview
- type: openai-compatible
name: perplexity
api_base: https://api.perplexity.ai
api_key: '{{PERPLEXITY_API_KEY}}' # You can either hard-code or inject secrets from the Coyote vault
api_key: '{{PERPLEXITY_API_KEY}}' # You can either hard-code or inject secrets from the Loki vault
# See https://console.groq.com/docs/quickstart
- type: openai-compatible
name: groq
api_base: https://api.groq.com/openai/v1
api_key: '{{GROQ_API_KEY}}' # You can either hard-code or inject secrets from the Coyote vault
api_key: '{{GROQ_API_KEY}}' # You can either hard-code or inject secrets from the Loki vault
# See https://learn.microsoft.com/en-us/azure/ai-services/openai/chatgpt-quickstart
- type: azure-openai
api_base: https://{RESOURCE}.openai.azure.com
api_key: '{{AZURE_OPENAI_API_KEY}}' # You can either hard-code or inject secrets from the Coyote vault
api_key: '{{AZURE_OPENAI_API_KEY}}' # You can either hard-code or inject secrets from the Loki vault
models:
- name: gpt-4o # Model deployment name
max_input_tokens: 128000
@@ -295,8 +286,8 @@ clients:
# See https://docs.aws.amazon.com/bedrock/latest/userguide/
- type: bedrock
access_key_id: '{{AWS_ACCESS_KEY_ID}}' # You can either hard-code or inject secrets from the Coyote vault
secret_access_key: '{{AWS_SECRET_ACCESS_KEY}}' # You can either hard-code or inject secrets from the Coyote vault
access_key_id: '{{AWS_ACCESS_KEY_ID}}' # You can either hard-code or inject secrets from the Loki vault
secret_access_key: '{{AWS_SECRET_ACCESS_KEY}}' # You can either hard-code or inject secrets from the Loki vault
region: xxx
session_token: xxx # Optional, only needed for temporary credentials
@@ -304,67 +295,67 @@ clients:
- type: openai-compatible
name: cloudflare
api_base: https://api.cloudflare.com/client/v4/accounts/{ACCOUNT_ID}/ai/v1
api_key: '{{CLOUDFLARE_API_KEY}}' # You can either hard-code or inject secrets from the Coyote vault
api_key: '{{CLOUDFLARE_API_KEY}}' # You can either hard-code or inject secrets from the Loki vault
# See https://cloud.baidu.com/doc/WENXINWORKSHOP/index.html
- type: openai-compatible
name: ernie
api_base: https://qianfan.baidubce.com/v2
api_key: '{{BAIDU_API_KEY}}' # You can either hard-code or inject secrets from the Coyote vault
api_key: '{{BAIDU_API_KEY}}' # You can either hard-code or inject secrets from the Loki vault
# See https://dashscope.aliyun.com/
- type: openai-compatible
name: qianwen
api_base: https://dashscope.aliyuncs.com/compatible-mode/v1
api_key: '{{ALIYUN_API_KEY}}' # You can either hard-code or inject secrets from the Coyote vault
api_key: '{{ALIYUN_API_KEY}}' # You can either hard-code or inject secrets from the Loki vault
# See https://cloud.tencent.com/product/hunyuan
- type: openai-compatible
name: hunyuan
api_base: https://api.hunyuan.cloud.tencent.com/v1
api_key: '{{TENCENT_API_KEY}}' # You can either hard-code or inject secrets from the Coyote vault
api_key: '{{TENCENT_API_KEY}}' # You can either hard-code or inject secrets from the Loki vault
# See https://platform.moonshot.cn/docs/intro
- type: openai-compatible
name: moonshot
api_base: https://api.moonshot.cn/v1
api_key: '{{MOONSHOT_API_KEY}}' # You can either hard-code or inject secrets from the Coyote vault
api_key: '{{MOONSHOT_API_KEY}}' # You can either hard-code or inject secrets from the Loki vault
# See https://platform.deepseek.com/api-docs/
- type: openai-compatible
name: deepseek
api_base: https://api.deepseek.com
api_key: '{{DEEPSEEK_API_KEY}}' # You can either hard-code or inject secrets from the Coyote vault
api_key: '{{DEEPSEEK_API_KEY}}' # You can either hard-code or inject secrets from the Loki vault
# See https://open.bigmodel.cn/dev/howuse/introduction
- type: openai-compatible
name: zhipuai
api_base: https://open.bigmodel.cn/api/paas/v4
api_key: '{{ZHIPUAI_API_KEY}}' # You can either hard-code or inject secrets from the Coyote vault
api_key: '{{ZHIPUAI_API_KEY}}' # You can either hard-code or inject secrets from the Loki vault
# See https://platform.minimaxi.com/document/Fast%20access
- type: openai-compatible
name: minimax
api_base: https://api.minimax.chat/v1
api_key: '{{MINIMAX_API_KEY}}' # You can either hard-code or inject secrets from the Coyote vault
api_key: '{{MINIMAX_API_KEY}}' # You can either hard-code or inject secrets from the Loki vault
# See https://openrouter.ai/docs#quick-start
- type: openai-compatible
name: openrouter
api_base: https://openrouter.ai/api/v1
api_key: '{{OPENROUTER_API_KEY}}' # You can either hard-code or inject secrets from the Coyote vault
api_key: '{{OPENROUTER_API_KEY}}' # You can either hard-code or inject secrets from the Loki vault
# See https://github.com/marketplace/models
- type: openai-compatible
name: github
api_base: https://models.inference.ai.azure.com
api_key: '{{GITHUB_API_KEY}}' # You can either hard-code or inject secrets from the Coyote vault
api_key: '{{GITHUB_API_KEY}}' # You can either hard-code or inject secrets from the Loki vault
# See https://deepinfra.com/docs
- type: openai-compatible
name: deepinfra
api_base: https://api.deepinfra.com/v1/openai
api_key: '{{DEEPINFRA_API_KEY}}' # You can either hard-code or inject secrets from the Coyote vault
api_key: '{{DEEPINFRA_API_KEY}}' # You can either hard-code or inject secrets from the Loki vault
# ----- RAG dedicated -----
@@ -373,10 +364,10 @@ clients:
- type: openai-compatible
name: jina
api_base: https://api.jina.ai/v1
api_key: '{{JINA_API_KEY}}' # You can either hard-code or inject secrets from the Coyote vault
api_key: '{{JINA_API_KEY}}' # You can either hard-code or inject secrets from the Loki vault
# See https://docs.voyageai.com/docs/introduction
- type: openai-compatible
name: voyageai
api_base: https://api.voyageai.com/v1
api_key: '{{VOYAGEAI_API_KEY}}' # You can either hard-code or inject secrets from the Coyote vault
api_key: '{{VOYAGEAI_API_KEY}}' # You can either hard-code or inject secrets from the Loki vault
config.role.example.md
+1 -14
View File
@@ -1,9 +1,5 @@
---
############################################
## Everything in this section is optional ##
############################################
# Role Configuration
# Everything in this section is optional
name: <role-name> # The name of the role
model: openai:gpt-4o # The model to use for this role
temperature: 0.2 # The temperature to use for this role when querying the model
@@ -12,14 +8,5 @@ enabled_tools: fs_ls,fs_cat # A comma-separated list of tools to enabl
enabled_mcp_servers: github,gitmcp # A comma-separated list of MCP servers to enable for this role
prompt: null # A custom prompt to use for this role that will immediately query
# the model for output instead of using the instructions below
# Auto-Continue (Todo System)
# The auto-continue system provides built-in task tracking for improved reliability.
# When enabled, the model can create todo lists and the system will automatically
# prompt it to continue when incomplete tasks remain.
# See the [Todo System documentation](https://github.com/Dark-Alex-17/coyote/wiki/TODO-System) for more information
auto_continue: false # Enable automatic continuation when incomplete todos remain (default: false)
max_auto_continues: 10 # Maximum number of automatic continuations before stopping (default: 10)
inject_todo_instructions: true # Inject default todo tool usage instructions into the system prompt (default: true)
continuation_prompt: null # Custom prompt used when auto-continuing. If null, uses built-in default
---
You are an expert at doing things. This is where you write the instructions for the role.
deployment/homebrew/coyote.rb.template
-23
View File
@@ -1,23 +0,0 @@
# Documentation: https://docs.brew.sh/Formula-Cookbook
# https://rubydoc.brew.sh/Formula
class Coyote < Formula
desc "All-in-one, batteries included LLM CLI tool"
homepage "https://github.com/Dark-Alex-17/coyote"
if OS.mac? and Hardware::CPU.arm?
url "https://github.com/Dark-Alex-17/coyote/releases/download/v$version/coyote-aarch64-apple-darwin.tar.gz"
sha256 "$hash_mac_arm"
elsif OS.mac? and Hardware::CPU.intel?
url "https://github.com/Dark-Alex-17/coyote/releases/download/v$version/coyote-x86_64-apple-darwin.tar.gz"
sha256 "$hash_mac"
else
url "https://github.com/Dark-Alex-17/coyote/releases/download/v$version/coyote-x86_64-unknown-linux-musl.tar.gz"
sha256 "$hash_linux"
end
version "$version"
license "MIT"
def install
bin.install "coyote"
ohai "You're done! Get started with \"coyote --help\""
end
end
deployment/homebrew/loki.rb.template
+23
View File
@@ -0,0 +1,23 @@
# Documentation: https://docs.brew.sh/Formula-Cookbook
# https://rubydoc.brew.sh/Formula
class Loki < Formula
desc "All-in-one, batteries included LLM CLI tool"
homepage "https://github.com/Dark-Alex-17/loki"
if OS.mac? and Hardware::CPU.arm?
url "https://github.com/Dark-Alex-17/loki/releases/download/v$version/loki-aarch64-apple-darwin.tar.gz"
sha256 "$hash_mac_arm"
elsif OS.mac? and Hardware::CPU.intel?
url "https://github.com/Dark-Alex-17/loki/releases/download/v$version/loki-x86_64-apple-darwin.tar.gz"
sha256 "$hash_mac"
else
url "https://github.com/Dark-Alex-17/loki/releases/download/v$version/loki-x86_64-unknown-linux-musl.tar.gz"
sha256 "$hash_linux"
end
version "$version"
license "MIT"
def install
bin.install "loki"
ohai "You're done! Get started with \"loki --help\""
end
end
docs/AGENTS.md
+775
View File
@@ -0,0 +1,775 @@
# Agents
Agents in Loki follow the same style as OpenAI's GPTs. They consist of 3 parts:
* [Role](./ROLES.md) - Tell the LLM how to behave
* [RAG](./RAG.md) - Pre-built knowledge bases specifically for the agent
* [Function Calling](./function-calling/TOOLS.md#tools) ([#2](./function-calling/MCP-SERVERS.md)) - Extends the functionality of the LLM through custom functions it can call
![Agent example](./images/agents/sql.gif)
Agent configuration files are stored in the `agents` subdirectory of your Loki configuration directory. The location of
this directory varies between systems so you can use the following command to locate yours:
```shell
loki --info | grep 'agents_dir' | awk '{print $2}'
```
If you're looking for more example agents, refer to the [built-in agents](../assets/agents).
## Quick Links
<!--toc:start-->
- [Directory Structure](#directory-structure)
- [Metadata](#1-metadata)
- [2. Define the Instructions](#2-define-the-instructions)
- [Static Instructions](#static-instructions)
- [Special Variables](#special-variables)
- [User-Defined Variables](#user-defined-variables)
- [Dynamic Instructions](#dynamic-instructions)
- [Variables](#variables)
- [3. Initializing RAG](#3-initializing-rag)
- [4. Building Tools for Agents](#4-building-tools-for-agents)
- [Limitations](#limitations)
- [.env File Support](#env-file-support)
- [Python-Based Agent Tools](#python-based-agent-tools)
- [Bash-Based Agent Tools](#bash-based-agent-tools)
- [TypeScript-Based Agent Tools](#typescript-based-agent-tools)
- [5. Conversation Starters](#5-conversation-starters)
- [6. Todo System & Auto-Continuation](#6-todo-system--auto-continuation)
- [7. Sub-Agent Spawning System](#7-sub-agent-spawning-system)
- [Configuration](#spawning-configuration)
- [Spawning & Collecting Agents](#spawning--collecting-agents)
- [Task Queue with Dependencies](#task-queue-with-dependencies)
- [Active Task Dispatch](#active-task-dispatch)
- [Output Summarization](#output-summarization)
- [Teammate Messaging](#teammate-messaging)
- [Runaway Safeguards](#runaway-safeguards)
- [8. User Interaction Tools](#8-user-interaction-tools)
- [Available Tools](#user-interaction-available-tools)
- [Escalation (Sub-Agent to User)](#escalation-sub-agent-to-user)
- [9. Auto-Injected Prompts](#9-auto-injected-prompts)
- [Built-In Agents](#built-in-agents)
<!--toc:end-->
---
## Directory Structure
Agent configurations often have the following directory structure:
```
<loki-config-dir>/agents
└── my-agent
├── config.yaml
├── tools.sh
or
├── tools.py
or
├── tools.ts
```
This means that agent configurations often are only two files: the agent configuration file (`config.yaml`), and the
tool definitions (`agents/my-agent/tools.sh`, `tools.py`, or `tools.ts`).
To see a full example configuration file, refer to the [example agent config file](../config.agent.example.yaml).
The best way to understand how an agent is built is to go step by step in the following manner:
---
## 1. Metadata
Agent configurations have the following settings available to customize each agent:
```yaml
# Model Configuration
model: openai:gpt-4o # Specify the LLM to use
temperature: null # Set default temperature parameter, range (0, 1)
top_p: null # Set default top-p parameter, with a range of (0, 1) or (0, 2), depending on the model
# Agent Metadata Configuration
agent_session: null # Set a session to use when starting the agent. (e.g. temp, default); defaults to globally set agent_session
# Agent Configuration
name: <agent-name> # Name of the agent, used in the UI and logs
description: <description> # Description of the agent, used in the UI
version: 1 # Version of the agent
# Function Calling Configuration
mcp_servers: # Optional list of MCP servers that the agent utilizes
- github # Corresponds to the name of an MCP server in the `<loki-config-dir>/functions/mcp.json` file
global_tools: # Optional list of additional global tools to enable for the agent; i.e. not tools specific to the agent
- web_search
- fs
- python
# Todo System & Auto-Continuation (see "Todo System & Auto-Continuation" section below)
auto_continue: false # Enable automatic continuation when incomplete todos remain
max_auto_continues: 10 # Maximum continuation attempts before stopping
inject_todo_instructions: true # Inject todo tool instructions into system prompt
continuation_prompt: null # Custom prompt for continuations (optional)
# Sub-Agent Spawning (see "Sub-Agent Spawning System" section below)
can_spawn_agents: false # Enable spawning child agents
max_concurrent_agents: 4 # Max simultaneous child agents
max_agent_depth: 3 # Max nesting depth (prevents runaway)
inject_spawn_instructions: true # Inject spawning instructions into system prompt
summarization_model: null # Model for summarizing sub-agent output (e.g. 'openai:gpt-4o-mini')
summarization_threshold: 4000 # Char count above which sub-agent output is summarized
escalation_timeout: 300 # Seconds sub-agents wait for escalated user input (default: 5 min)
```
As mentioned previously: Agents utilize function calling to extend a model's capabilities. However, agents operate in
isolated environment, so in order for an agent to use a tool or MCP server that you have defined globally, you must
explicitly state which tools and/or MCP servers the agent uses. Otherwise, it is assumed that the agent doesn't use any
tools outside its own custom defined tools.
And if you don't define a `agents/my-agent/tools.sh`, `agents/my-agent/tools.py`, or `agents/my-agent/tools.ts`, then the agent is really just a
`role`.
You'll notice there are no settings for agent-specific tooling. This is because they are handled separately and
automatically. See the [Building Tools for Agents](#4-building-tools-for-agents) section below for more information.
To see a full example configuration file, refer to the [example agent config file](../config.agent.example.yaml).
## 2. Define the Instructions
At their heart, agents function similarly to roles in that they tell the model how to behave. Agent configuration files
have the following settings for the instruction definitions:
```yaml
dynamic_instructions: # Whether to use dynamically generated instructions for the agent; if false, static instructions are used. False by default.
instructions: # Static instructions for the LLM; These are ignored if dynamic instructions are used
variables: # An array of optional variables that the agent expects and uses
```
### Static Instructions
By default, Loki agents use statically defined instructions. Think of them as being identical to the instructions for a
[role](./ROLES.md#instructions), because they virtually are.
**Example:**
```yaml
instructions: |
You are an AI agent designed to demonstrate agentic capabilities
```
Just like roles, agents support variable interpolation at runtime. There's two types of variables that can be
interpolated into the instructions at runtime: special variables (like roles have), and user-defined variables. Just
like roles, variables are interpolated into your instructions anywhere Loki sees the `{{variable}}` syntax.
#### Special Variables
The following special variables are provided by Loki at runtime and can be injected into your agent's instructions:
| Name | Description | Example |
|-----------------|---------------------------------------------------------------------|----------------------------|
| `__os__` | Operating system name | `linux` |
| `__os_family__` | Operating system family | `unix` |
| `__arch__` | System architecture | `x86_64` |
| `__shell__` | The current user's default shell | `bash` |
| `__locale__` | The current user's preferred language and region settings | `en-US` |
| `__now__` | Current timestamp in ISO 8601 format | `2025-11-07T10:15:44.268Z` |
| `__cwd__` | The current working directory | `/tmp` |
| `__tools__` | A list of the enabled tools (global + mcp servers + agent-specific) | |
#### User-Defined Variables
Agents also support user-defined variables that can be interpolated into the instructions, and are made available to any
agent-specific tools you define (see [Building Tools for Agents](#4-building-tools-for-agents) for more details on how to
create agent-specific tooling).
The `variables` setting in an agent's config has the following fields:
| Field | Required | Description |
|---------------|----------|----------------------------------------------------------------------------------------------------|
| `name` | * | The name of the variable |
| `description` | * | The description of the field |
| `default` | | A default value for the field. If left undefined, the user will be prompted for a value at runtime |
These variables can be referenced in both the agent's instructions, and in the tool definitions via `LLM_AGENT_VAR_<name>`.
**Example:**
```yaml
instructions: |
You are an agent who answers questions about a user's system.
<tools>
{{__tools__}}
</tools>
<system>
os: {{__os__}}
os_family: {{__os_family__}}
arch: {{__arch__}}
shell: {{__shell__}}
locale: {{__locale__}}
now: {{__now__}}
cwd: {{__cwd__}}
</system>
<user>
username: {{username}}
</user>
variables:
- name: username # Accessible from the tool definitions via the `LLM_AGENT_VAR_USERNAME` environment variable
description: Your user name
```
### Dynamic Instructions
Sometimes you may find it useful to dynamically generate instructions on startup. Whether that be via a call to Loki
itself to generate them, or by some other means. Loki supports this type of behavior using a special function defined
in your `agents/my-agent/tools.py`, `agents/my-agent/tools.sh`, or `agents/my-agent/tools.ts`.
**Example: Instructions for a JSON-reader agent that specializes on each JSON input it receives**
`agents/json-reader/tools.py`:
```python
import json
from pathlib import Path
from genson import SchemaBuilder
def _instructions():
"""Generates instructions for the agent dynamically"""
value = input("Enter a JSON file path OR paste raw JSON: ").strip()
if not value:
raise SystemExit("A file path or JSON string is required.")
p = Path(value)
if p.exists() and p.is_file():
json_file_path = str(p.resolve())
json_text = p.read_text(encoding="utf-8")
else:
try:
json.loads(value)
except json.JSONDecodeError as e:
raise SystemExit(f"Input is neither a file nor valid JSON.\n{e}")
json_file_path = "<provided-inline-json>"
json_text = value
try:
data = json.loads(json_text)
except json.JSONDecodeError as e:
raise SystemExit(f"Provided content is not valid JSON.\n{e}")
builder = SchemaBuilder()
builder.add_object(data)
json_schema = builder.to_schema()
return f"""
You are an AI agent that can view and filter JSON data with jq.
## Context
json_file_path: {json_file_path}
json_schema: {json.dumps(json_schema, indent=2)}
"""
```
or
`agents/json-reader/tools.sh`:
```bash
#!/usr/bin/env bash
set -e
# @meta require-tools jq,genson
# @env LLM_OUTPUT=/dev/stdout The output path
# @cmd Generates instructions for the agent dynamically
_instructions() {
read -r -p "Enter a JSON file path OR paste raw JSON: " value
if [[ -z "${value}" ]]; then
echo "A file path or JSON string is required" >&2
exit 1
fi
json_file_path=""
inline_temp=""
cleanup() {
[[ -n "${inline_temp:-}" && -f "${inline_temp}" ]] && rm -f "${inline_temp}"
}
trap cleanup EXIT
if [[ -f "${value}" ]]; then
json_file_path="$(realpath "${value}")"
if ! jq empty "${json_file_path}" >/dev/null 2>&1; then
echo "Error: File does not contain valid JSON: ${json_file_path}" >&2
exit 1
fi
else
inline_temp="$(mktemp)"
printf "%s" "${value}" > "${inline_temp}"
if ! jq empty "${inline_temp}" >/dev/null 2>&1; then
echo "Error: Input is neither a file nor valid JSON." >&2
exit 1
fi
json_file_path="<provided-inline-json>"
fi
source_file="${json_file_path}"
if [[ "${json_file_path}" == "<provided-inline-json>" ]]; then
source_file="${inline_temp}"
fi
json_schema="$(genson < "${source_file}" | jq -c '.')"
cat <<EOF >> "$LLM_OUTPUT"
You are an AI agent that can view and filter JSON data with jq.
## Context
json_file_path: ${json_file_path}
json_schema: ${json_schema}
EOF
}
```
For more information on how to create custom tools for your agent and the structure of the `agent/my-agent/tools.sh`,
`agent/my-agent/tools.py`, or `agent/my-agent/tools.ts` files, refer to the [Building Tools for Agents](#4-building-tools-for-agents) section below.
#### Variables
All the same variable interpolations supported by static instructions is also supported by dynamic instructions. For
more information on what variables are available and how to use them, refer to the [Special Variables](#special-variables)
and [User-Defined Variables](#user-defined-variables) sections above.
## 3. Initializing RAG
Each agent you create also has a dedicated knowledge base that adds additional context to your queries and helps the LLM
answer queries effectively. The documents to load into RAG are defined in the `documents` array of your agent
configuration file:
```yaml
documents:
- https://www.ohdsi.org/data-standardization/
- https://github.com/OHDSI/Vocabulary-v5.0/wiki/**
- OMOPCDM_ddl.sql # Relative path to agent (i.e. file lives at '<loki-config-dir>/agents/my-agent/OMOPCDM_ddl.sql')
```
These documents use the same syntax as those you'd define when constructing RAG normally. To see all the available types
of documents that Loki supports and how to use custom document loaders, refer to the [RAG documentation](./RAG.md#supported-document-sources).
Anytime your agent starts up, it will automatically be using the RAG you've defined here.
## 4. Building Tools for Agents
Building tools for agents is virtually identical to building custom tools, with one slight difference: instead of
defining a single function that gets executed at runtime (e.g. `main` for bash tools and `run` for Python tools), agent
tools define a number of *subcommands*.
### Limitations
You can only utilize one of: a bash-based `<loki-config-dir>/agents/my-agent/tools.sh`, a Python-based
`<loki-config-dir>/agents/my-agent/tools.py`, or a TypeScript-based `<loki-config-dir>/agents/my-agent/tools.ts`.
However, if it's easier to achieve a task in one language vs the other,
you're free to define other scripts in your agent's configuration directory and reference them from the main
tools file. **Any scripts *not* named `tools.{py,sh,ts}` will not be picked up by Loki's compiler**, meaning they
can be used like any other set of scripts.
It's important to keep in mind the following:
* **Do not give agents the same name as an executable**. Loki compiles the tools for each agent into a binary that it
temporarily places on your path during execution. If you have a binary with the same name as your agent, then your
shell may execute the existing binary instead of your agent's tools
* **`LLM_ROOT_DIR` points to the agent's configuration directory**. This is where agents differ slightly from normal
tools: The `LLM_ROOT_DIR` environment variable does *not* point to the `functions/tools` directory like it does in
global tools. Instead, it points to the agent's configuration directory, making it easier to source scripts and other
miscellaneous files
### .env File Support
When Loki loads an agent, it will also search the agent's configuration directory for a `.env` file. If found, all
environment variables defined in the file will be made available to the agent's tools.
### Python-Based Agent Tools
Python-based tools are defined exactly the same as they are for custom tool definitions. The only difference is that
instead of a single `run` function, you define as many as you like with whatever arguments you like.
**Example:**
`agents/my-agent/tools.py`
```python
import urllib.request
def get_ip_info():
"""
Get your IP information
"""
with urllib.request.urlopen("https://httpbin.org/ip") as response:
data = response.read()
return data.decode('utf-8')
def get_ip_address_from_aws():
"""
Find your public IP address using AWS
"""
with urllib.request.urlopen("https://checkip.amazonaws.com") as response:
data = response.read()
return data.decode('utf-8')
```
Loki automatically compiles these as separate functions for the LLM to call. No extra work is needed. Just make sure you
follow all the same steps to define each function as you would when creating custom Python tools.
For more information on how to build tools in Python, refer to the [custom Python tools documentation](./function-calling/CUSTOM-TOOLS.md#custom-python-based-tools)
### Bash-Based Agent Tools
Bash-based agent tools are virtually identical to custom bash tools, with only one difference. Instead of defining a
single entrypoint via the `main` function, you actually define as many subcommands as you like.
**Example:**
`agents/my-agent/tools.sh`
```bash
#!/usr/bin/env bash
# @env LLM_OUTPUT=/dev/stdout The output path
# @describe Discover network information about your computer and its place in the internet
# Use the `@cmd` annotation to define subcommands for your script.
# @cmd Get your IP information
get_ip_info() {
curl -fsSL https://httpbin.org/ip >> "$LLM_OUTPUT"
}
# @cmd Find your public IP address using AWS
get_ip_address_from_aws() {
curl -fsSL https://checkip.amazonaws.com >> "$LLM_OUTPUT"
}
```
To compile the script so it's executable and testable:
```bash
$ loki --build-tools
```
Then you can execute your script (assuming your current working directory is `agents/my-agent`):
```bash
$ ./tools.sh get_ip_info
$ ./tools.sh get_ip_address_from_aws
```
All other special annotations (`@env`, `@arg`, `@option` `@flags`) apply to subcommands as well, so be sure to follow
the same syntax ad formatting as is used to create custom bash tools globally.
For more information on how to write, [build and test](function-calling/CUSTOM-BASH-TOOLS.md#execute-and-test-your-bash-tools) tools in bash, refer to the
[custom bash tools documentation](function-calling/CUSTOM-BASH-TOOLS.md).
### TypeScript-Based Agent Tools
TypeScript-based agent tools work exactly the same as TypeScript global tools. Instead of a single `run` function,
you define as many exported functions as you like. Non-exported functions are private helpers and are invisible to the
LLM.
**Example:**
`agents/my-agent/tools.ts`
```typescript
/**
* Get your IP information
*/
export async function get_ip_info(): Promise<string> {
const resp = await fetch("https://httpbin.org/ip");
return await resp.text();
}
/**
* Find your public IP address using AWS
*/
export async function get_ip_address_from_aws(): Promise<string> {
const resp = await fetch("https://checkip.amazonaws.com");
return await resp.text();
}
// Non-exported helper — invisible to the LLM
function formatResponse(data: string): string {
return data.trim();
}
```
Loki automatically compiles each exported function as a separate tool for the LLM to call. Just make sure you
follow the same JSDoc and parameter conventions as you would when creating custom TypeScript tools.
TypeScript agent tools also support dynamic instructions via an exported `_instructions()` function:
```typescript
import { readFileSync } from "fs";
/**
* Generates instructions for the agent dynamically
*/
export function _instructions(): string {
const schema = readFileSync("schema.json", "utf-8");
return `You are an AI agent that works with the following schema:\n${schema}`;
}
```
For more information on how to build tools in TypeScript, refer to the [custom TypeScript tools documentation](function-calling/CUSTOM-TOOLS.md#custom-typescript-based-tools).
## 5. Conversation Starters
It's often helpful to also have some conversation starters so users know what kinds of things the agent is capable of
doing. These are available in the REPL via the `.starter` command and are selectable.
They are defined using the `conversation_starters` setting in your agent's configuration file:
**Example:**
`agents/my-agent/config.yaml`:
```yaml
conversation_starters:
- What is my username?
- What is my current shell?
- What is my ip?
- How much disk space is left on my PC??
- How to create an agent?
```
![Example Conversation Starters](./images/agents/conversation-starters.gif)
## 6. Todo System & Auto-Continuation
Loki includes a built-in task tracking system designed to improve the reliability of agents, especially when using
smaller language models. The Todo System helps models:
- Break complex tasks into manageable steps
- Track progress through multi-step workflows
- Automatically continue work until all tasks are complete
### Quick Configuration
```yaml
# agents/my-agent/config.yaml
auto_continue: true # Enable auto-continuation
max_auto_continues: 10 # Max continuation attempts
inject_todo_instructions: true # Include the default todo instructions into prompt
```
### How It Works
1. When `inject_todo_instructions` is enabled, agents receive instructions on using five built-in tools:
- `todo__init`: Initialize a todo list with a goal
- `todo__add`: Add a task to the list
- `todo__done`: Mark a task complete
- `todo__list`: View current todo state
- `todo__clear`: Clear the entire todo list and reset the goal
These instructions are a reasonable default that detail how to use Loki's To-Do System. If you wish,
you can disable the injection of the default instructions and specify your own instructions for how
to use the To-Do System into your main `instructions` for the agent.
2. When `auto_continue` is enabled and the model stops with incomplete tasks, Loki automatically sends a
continuation prompt with the current todo state, nudging the model to continue working.
3. This continues until all tasks are done or `max_auto_continues` is reached.
### When to Use
- Multistep tasks where the model might lose track
- Smaller models that need more structure
- Workflows requiring guaranteed completion of all steps
For complete documentation including all configuration options, tool details, and best practices, see the
[Todo System Guide](./TODO-SYSTEM.md).
## 7. Sub-Agent Spawning System
Loki agents can spawn and manage child agents that run **in parallel** as background tasks inside the same process.
This enables orchestrator-style agents that delegate specialized work to other agents, similar to how tools like
Claude Code or OpenCode handle complex multi-step tasks.
For a working example of an orchestrator agent that uses sub-agent spawning, see the built-in
[sisyphus](../assets/agents/sisyphus) agent. For an example of the teammate messaging pattern with parallel sub-agents,
see the [code-reviewer](../assets/agents/code-reviewer) agent.
### Spawning Configuration
| Setting | Type | Default | Description |
|-----------------------------|---------|---------------|--------------------------------------------------------------------------------|
| `can_spawn_agents` | boolean | `false` | Enable this agent to spawn child agents |
| `max_concurrent_agents` | integer | `4` | Maximum number of child agents that can run simultaneously |
| `max_agent_depth` | integer | `3` | Maximum nesting depth for sub-agents (prevents runaway spawning chains) |
| `inject_spawn_instructions` | boolean | `true` | Inject the default spawning instructions into the agent's system prompt |
| `summarization_model` | string | current model | Model to use for summarizing long sub-agent output (e.g. `openai:gpt-4o-mini`) |
| `summarization_threshold` | integer | `4000` | Character count above which sub-agent output is summarized before returning |
| `escalation_timeout` | integer | `300` | Seconds a sub-agent waits for an escalated user interaction response |
**Example configuration:**
```yaml
# agents/my-orchestrator/config.yaml
can_spawn_agents: true
max_concurrent_agents: 6
max_agent_depth: 2
inject_spawn_instructions: true
summarization_model: openai:gpt-4o-mini
summarization_threshold: 3000
escalation_timeout: 600
```
### Spawning & Collecting Agents
When `can_spawn_agents` is enabled, the agent receives tools for spawning and managing child agents:
| Tool | Description |
|------------------|-------------------------------------------------------------------------|
| `agent__spawn` | Spawn a child agent in the background. Returns an agent ID immediately. |
| `agent__check` | Non-blocking check: is the agent done? Returns `PENDING` or the result. |
| `agent__collect` | Blocking wait: wait for an agent to finish, return its output. |
| `agent__list` | List all spawned agents and their status. |
| `agent__cancel` | Cancel a running agent by ID. |
The core pattern is **Spawn -> Continue -> Collect**:
```
# 1. Spawn agents in parallel (returns IDs immediately)
agent__spawn --agent explore --prompt "Find auth middleware patterns in src/"
agent__spawn --agent explore --prompt "Find error handling patterns in src/"
# 2. Continue your own work while they run
# 3. Check if done (non-blocking)
agent__check --id agent_explore_a1b2c3d4
# 4. Collect results when ready (blocking)
agent__collect --id agent_explore_a1b2c3d4
agent__collect --id agent_explore_e5f6g7h8
```
Any agent defined in your `<loki-config-dir>/agents/` directory can be spawned as a child. Child agents:
- Run in a fully isolated environment (separate session, config, and tools)
- Have their output suppressed from the terminal (no spinner, no tool call logging)
- Return their accumulated output to the parent when collected
### Task Queue with Dependencies
For complex workflows where tasks have ordering requirements, the spawning system includes a dependency-aware
task queue:
| Tool | Description |
|------------------------|-----------------------------------------------------------------------------|
| `agent__task_create` | Create a task with optional dependencies and auto-dispatch agent. |
| `agent__task_list` | List all tasks with their status, dependencies, and assignments. |
| `agent__task_complete` | Mark a task done. Returns newly unblocked tasks and auto-dispatches agents. |
| `agent__task_fail` | Mark a task as failed. Dependents remain blocked. |
```
# Create tasks with dependency ordering
agent__task_create --subject "Explore existing patterns"
agent__task_create --subject "Implement feature" --blocked_by ["task_1"]
agent__task_create --subject "Write tests" --blocked_by ["task_2"]
# Mark tasks complete to unblock dependents
agent__task_complete --task_id task_1
```
### Active Task Dispatch
Tasks can optionally specify an agent to auto-spawn when the task becomes runnable:
```
agent__task_create \
--subject "Implement the auth module" \
--blocked_by ["task_1"] \
--agent coder \
--prompt "Implement auth module based on patterns found in task_1"
```
When `task_1` completes and the dependent task becomes unblocked, an agent is automatically spawned with the
specified prompt. No manual intervention needed. This enables fully automated multi-step pipelines.
### Output Summarization
When a child agent produces long output, it can be automatically summarized before returning to the parent.
This keeps parent context windows manageable.
- If the output exceeds `summarization_threshold` characters (default: 4000), it is sent through an LLM
summarization pass
- The `summarization_model` setting lets you use a cheaper/faster model for summarization (e.g. `gpt-4o-mini`)
- If `summarization_model` is not set, the parent's current model is used
- The summarization preserves all actionable information: code snippets, file paths, error messages, and
concrete recommendations
### Teammate Messaging
All agents (including children) automatically receive tools for **direct sibling-to-sibling messaging**:
| Tool | Description |
|-----------------------|-----------------------------------------------------|
| `agent__send_message` | Send a text message to another agent's inbox by ID. |
| `agent__check_inbox` | Drain all pending messages from your inbox. |
This enables coordination patterns where child agents share cross-cutting findings:
```
# Agent A discovers something relevant to Agent B
agent__send_message --id agent_reviewer_b1c2d3e4 --message "Found a security issue in auth.rs line 42"
# Agent B checks inbox before finalizing
agent__check_inbox
```
Messages are routed through the parent's supervisor. A parent can message its children, and children can message
their siblings. For a working example of the teammate pattern, see the built-in
[code-reviewer](../assets/agents/code-reviewer) agent, which spawns file-specific reviewers that share
cross-cutting findings with each other.
### Runaway Safeguards
The spawning system includes built-in safeguards to prevent runaway agent chains:
- **`max_concurrent_agents`:** Caps how many agents can run at once (default: 4). Spawn attempts beyond this
limit return an error asking the agent to wait or cancel existing agents.
- **`max_agent_depth`:** Caps nesting depth (default: 3). A child agent spawning its own child increments the
depth counter. Attempts beyond the limit are rejected.
- **`can_spawn_agents`:** Only agents with this flag set to `true` can spawn children. By default, spawning is
disabled. This means child agents cannot spawn their own children unless you explicitly create them with
`can_spawn_agents: true` in their config.
## 8. User Interaction Tools
Loki includes built-in tools for agents (and the REPL) to interactively prompt the user for input. These tools
are **always available**. No configuration needed. They are automatically injected into every agent and into
REPL mode when function calling is enabled.
### User Interaction Available Tools
| Tool | Description | Returns |
|------------------|-----------------------------------------|----------------------------------|
| `user__ask` | Present a single-select list of options | The selected option string |
| `user__confirm` | Ask a yes/no question | `"yes"` or `"no"` |
| `user__input` | Request free-form text input | The text entered by the user |
| `user__checkbox` | Present a multi-select checkbox list | Array of selected option strings |
**Parameters:**
- `user__ask`: `--question "..." --options ["Option A", "Option B", "Option C"]`
- `user__confirm`: `--question "..."`
- `user__input`: `--question "..."`
- `user__checkbox`: `--question "..." --options ["Option A", "Option B", "Option C"]`
At the top level (depth 0), these tools render interactive terminal prompts directly using arrow-key navigation,
checkboxes, and text input fields.
### Escalation (Sub-Agent to User)
When a **child agent** (depth > 0) calls a `user__*` tool, it cannot prompt the terminal directly. Instead,
the request is **automatically escalated** to the root agent:
1. The child agent calls `user__ask(...)` and **blocks**, waiting for a reply
2. The root agent sees a `pending_escalations` notification in its next tool results
3. The root agent either answers from context or prompts the user itself, then calls
`agent__reply_escalation` to unblock the child
4. The child receives the reply and continues
The escalation timeout is configurable via `escalation_timeout` in the agent's `config.yaml` (default: 300
seconds / 5 minutes). If the timeout expires, the child receives a fallback message asking it to use its
best judgment.
| Tool | Description |
|---------------------------|--------------------------------------------------------------------------|
| `agent__reply_escalation` | Reply to a pending child escalation, unblocking the waiting child agent. |
This tool is automatically available to any agent with `can_spawn_agents: true`.
## 9. Auto-Injected Prompts
Loki automatically appends usage instructions to your agent's system prompt for each enabled built-in system.
These instructions are injected into both **static and dynamic instructions** after your own instructions,
ensuring agents always know how to use their available tools.
| System | Injected When | Toggle |
|--------------------|----------------------------------------------------------------|-----------------------------|
| Todo tools | `auto_continue: true` AND `inject_todo_instructions: true` | `inject_todo_instructions` |
| Spawning tools | `can_spawn_agents: true` AND `inject_spawn_instructions: true` | `inject_spawn_instructions` |
| Teammate messaging | Always (all agents) | None (always injected) |
| User interaction | Always (all agents) | None (always injected) |
If you prefer to write your own instructions for a system, set the corresponding `inject_*` flag to `false`
and include your custom instructions in the agent's `instructions` field. The built-in tools will still be
available; only the auto-injected prompt text is suppressed.
## Built-In Agents
Loki comes packaged with some useful built-in agents:
* `coder`: An agent to assist you with all your coding tasks
* `code-reviewer`: A [CodeRabbit](https://coderabbit.ai)-style code reviewer that spawns per-file reviewers using the teammate messaging pattern
* `demo`: An example agent to use for reference when learning to create your own agents
* `explore`: An agent designed to help you explore and understand your codebase
* `file-reviewer`: An agent designed to perform code-review on a single file (used by the `code-reviewer` agent)
* `jira-helper`: An agent that assists you with all your Jira-related tasks
* `oracle`: An agent for high-level architecture, design decisions, and complex debugging
* `sisyphus`: A powerhouse orchestrator agent for writing complex code and acting as a natural language interface for your codebase (similar to ClaudeCode, Gemini CLI, Codex, or OpenCode). Uses sub-agent spawning to delegate to `explore`, `coder`, and `oracle`.
* `sql`: A universal SQL agent that enables you to talk to any relational database in natural language
docs/AICHAT-MIGRATION.md
+211
View File
@@ -0,0 +1,211 @@
# AIChat to Loki Migration Guide
Loki originally started as a fork of AIChat but has since evolved into its own separate project with separate goals.
As a result, there's some changes you'll need to make to your AIChat configuration to be able to use Loki.
Be sure you've run `loki` at least once so that the Loki configuration directory and subdirectories exist and is
populated with the built-in defaults.
## Global Configuration File
You should be able to copy/paste your AIChat configuration file into your Loki configuration directory. Since the
location of the Loki configuration directory varies between systems, you can use the following command to locate your
config directory:
```shell
loki --info | grep 'config_dir' | awk '{print $2}'
```
Then, you'll need to make the following changes:
* `function_calling` -> `function_calling_support`
* `use_tools` -> `enabled_tools`
* `agent_prelude` -> `agent_session`
* `compress_threshold` -> `compression_threshold`
* `summarize_prompt` -> `summarization_prompt`
* `summary_prompt` -> `summary_context_prompt`
## Roles
Locate your `roles` directory using the following command:
```shell
loki --info | grep 'roles_dir' | awk '{print $2}'
```
Update any roles that have `use_tools` to `enabled_tools`.
## Sessions
Locate your `sessions` directory using the following command:
```shell
loki --info | grep 'sessions_dir' | awk '{print $2}'
```
Update the following settings:
* `use_tools` -> `enabled_tools`
* `compress_threshold` -> `compression_threshold`
* `summarize_prompt` -> `summarization_prompt`
* `summary_prompt` -> `summary_context_prompt`
---
# LLM Functions Changes
Probably the most significant difference between AIChat and Loki is how tools are handled. So if you cloned the
[llm-functions](https://github.com/sigoden/llm-functions) repo, you'll need to make the following changes.
**Note: JavaScript functions are not supported in Loki.**
The following guide assumes you're using the `llm-functions` repository as your base for custom functions, and thus
follows that directory structure.
## Agents
Agents are now all handled in one place: the `agents` directory (`<loki-config-dir>/agents`):
```shell
loki --info | grep 'agents_dir' | awk '{print $2}'
```
And instead of separate `index.yaml` and `config.yaml` files, they're now both in a single `config.yaml` file.
So now for all of your agents, copy all the contents of those directories to the corresponding directory in the Loki
`agents` directory. Then make the following changes:
* Copy the contents of your `<aichat-config-dir>/functions/agents` directory into `<loki-config-dir/agents`
* Merge `index.yaml` into `config.yaml`
* If you never created a custom `config.yaml` file, then simply rename `index.yaml` to `config.yaml`
* If you've defined an `agent_prelude`, rename that field to `agent_session`
* Convert all JavaScript tools to either Python or Bash
* For Bash `tools.sh`: Remove the following line:
```bash
eval "$(argc --argc-eval "$0" "$@")"
```
* Any `tools.txt` files you have that define what global functions the agent uses is now replaced by the `global_tools`
field in the agent's `config.yaml`. So for example: If your `tools.txt` looks like this:
```text
fs_mkdir.sh
fs_ls.sh
fs_patch.sh
fs_cat.sh
```
then you need to add the following to your agent's `config.yaml`:
```yaml
global_tools:
- fs_mkdir.sh
- fs_ls.sh
- fs_patch.sh
- fs_cat.sh
```
* If you have any bash `tools.sh` that depend on the utility scripts in the `llm-functions` repository, they've been
replaced by built-in utility scripts. So use the following to replace any matching lines in your `tools.sh` files:
```bash
##################
## Scripts file ##
##################
ROOT_DIR="${LLM_ROOT_DIR:-$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)}"
# replace with
source "$LLM_PROMPT_UTILS_FILE"
#######################
## guard_path script ##
#######################
"$ROOT_DIR/utils/guard_path.sh"
# replace with
guard_path
############################
## guard_operation script ##
############################
"$ROOT_DIR/utils/guard_operation.sh"
# replace with
guard_operation
######################
## patch.awk script ##
######################
awk -f "$ROOT_DIR/utils/patch.awk"
# replace with
patch_file
```
When you're done with this migration, you should have the following:
* No more `functions/agents` directory
* No `functions/agents.txt` file (Loki assumes that if the agent directory exists, it is loadable)
* No `<loki-config-dir>/agents/<agent-name>/tools.txt`
* No `<loki-config-dir>/agents/<agent-name>/index.yaml`
## Functions
Loki consolidates much of the `llm-functions` repo functionality into one binary. So this means
* There's no need to have `argc` installed anymore
* No separate repository to manage
* No `tools.txt`
* No `functions.json`
* No `functions/mcp` directory at all
* No `functions/scripts`
Here's how to migrate your functions over to Loki from the `llm-functions` repository.
* Copy your AIChat `<aichat-config-dir>/functions` directory into your Loki config directory
* Delete the following files and directories from your `<loki-config-dir>/functions` directory:
* `scripts/`
* `agents.txt`
* `functions.json`
* `Argcfile.sh`
* `README.md` (irrelevant now)
* `LICENSE` (irrelevant now)
* `utils/guard_operation.sh`
* `utils/guard_path.sh`
* `utils/patch.awk`
* Everything in `tools.txt` now lives in the global config file under the `visible_tools` setting:
```text
get_current_weather.sh
execute_command.sh
web_search.sh
#execute_py_code.py
query_jira_issues.sh
```
becomes the following in your `<loki-config-dir>/config.yaml`
```yaml
visible_tools:
- get_current_weather.sh
- execute_command.sh
- web_search.sh
# - web_search.sh
- query_jira_issues.sh
```
* If you've defined a `functions/mcp.json` file, you can leave it alone.
* Similarly to agents, if you have any bash `tools.sh` that depend on the utility scripts in the `llm-functions`
repository, they've been replaced by built-in utility scripts. So use the following to replace any matching lines in
your `tools.sh` files:
```bash
##################
## Scripts file ##
##################
ROOT_DIR="${LLM_ROOT_DIR:-$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)}"
# replace with
source "$LLM_PROMPT_UTILS_FILE"
#######################
## guard_path script ##
#######################
"$ROOT_DIR/utils/guard_path.sh"
# replace with
guard_path
############################
## guard_operation script ##
############################
"$ROOT_DIR/utils/guard_operation.sh"
# replace with
guard_operation
######################
## patch.awk script ##
######################
awk -f "$ROOT_DIR/utils/patch.awk"
# replace with
patch_file
```
Refer to the [custom bash tools docs](./function-calling/CUSTOM-BASH-TOOLS.md) to learn how to compile and test bash
tools in Loki without needing to use `argc`.
docs/ENVIRONMENT-VARIABLES.md
+113
View File
@@ -0,0 +1,113 @@
# Environment Variables
Loki is designed to be highly dynamic and customizable. As a result, Loki utilizes a number of environment variables
that can be used to modify its behavior at runtime without needing to modify the existing configuration files.
Loki also supports defining environment variables via a `.env` file in the Loki configuration directory. This directory
varies between systems, so you can find the location of your configuration directory using the following command:
```shell
loki --info | grep 'config_dir' | awk '{print $2}'
```
## Quick Links
<!--toc:start-->
- [Global Configuration Related Variables](#global-configuration-related-variables)
- [Client Related Variables](#client-related-variables)
- [Files and Directory Related Variables](#files-and-directory-related-variables)
- [Agent Related Variables](#agent-related-variables)
- [Logging Related Variables](#logging-related-variables)
- [Miscellaneous Variables](#miscellaneous-variables)
<!--toc:end-->
---
## Global Configuration Related Variables
All configuration items in the global config file have environment variables that can be overridden at runtime. To see
all configuration options and more thorough descriptions, refer to the [example config file](../config.example.yaml).
Below are the most commonly used configuration settings and their corresponding environment variables:
| Setting | Environment Variable |
|----------------------------|---------------------------------|
| `model` | `LOKI_MODEL` |
| `temperature` | `LOKI_TEMPERATURE` |
| `top_p` | `LOKI_TOP_P` |
| `stream` | `LOKI_STREAM` |
| `save` | `LOKI_SAVE` |
| `editor` | `LOKI_EDITOR` |
| `wrap` | `LOKI_WRAP` |
| `wrap_code` | `LOKI_WRAP_CODE` |
| `save_session` | `LOKI_SAVE_SESSION` |
| `compression_threshold` | `LOKI_COMPRESSION_THRESHOLD` |
| `function_calling_support` | `LOKI_FUNCTION_CALLING_SUPPORT` |
| `enabled_tools` | `LOKI_ENABLED_TOOLS` |
| `mcp_server_support` | `LOKI_MCP_SERVER_SUPPORT` |
| `enabled_mcp_servers` | `LOKI_ENABLED_MCP_SERVERS` |
| `rag_embedding_model` | `LOKI_RAG_EMBEDDING_MODEL` |
| `rag_reranker_model` | `LOKI_RAG_RERANKER_MODEL` |
| `rag_top_k` | `LOKI_RAG_TOP_K` |
| `rag_chunk_size` | `LOKI_RAG_CHUNK_SIZE` |
| `rag_chunk_overlap` | `LOKI_RAG_CHUNK_OVERLAP` |
| `highlight` | `LOKI_HIGHLIGHT` |
| `theme` | `LOKI_THEME` |
| `serve_addr` | `LOKI_SERVE_ADDR` |
| `user_agent` | `LOKI_USER_AGENT` |
| `save_shell_history` | `LOKI_SAVE_SHELL_HISTORY` |
| `sync_models_url` | `LOKI_SYNC_MODELS_URL` |
## Client Related Variables
The following environment variables are available for clients in Loki:
| Environment Variable | Description |
|----------------------------------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| `{client}_API_KEY` | For clients that require an API key, you can define the keys either through environment variables or <br>using the [vault](./VAULT.md). The variables are named after the client to which they apply; <br>e.g. `OPENAI_API_KEY`, `GEMINI_API_KEY`, etc. |
| `LOKI_PLATFORM` | Combine with `{client}_API_KEY` to run Loki without a configuration file. <br>This variable is ignored if a configuration file exists. |
| `LOKI_PATCH_{client}_CHAT_COMPLETIONS` | Patch chat completion requests to models on the corresponding client; Can modify the URL, body, <br>or headers. |
| `LOKI_SHELL` | Specify the shell that Loki should be using when executing commands |
## Files and Directory Related Variables
You can also customize the files and directories that Loki loads its configuration files from:
| Environment Variable | Description | Default Value |
|----------------------|------------------------------------------------------------------------|---------------------------------|
| `LOKI_CONFIG_DIR` | Customize the location of the Loki configuration directory. | `<user-config-dir>/loki` |
| `LOKI_ENV_FILE` | Customize the location of the `.env` file to load at startup. | `<loki-config-dir>/.env` |
| `LOKI_CONFIG_FILE` | Customize the location of the global `config.yaml` configuration file. | `<loki-config-dir>/config.yaml` |
| `LOKI_ROLES_DIR` | Customize the location of the `roles` directory. | `<loki-config-dir>/roles` |
| `LOKI_SESSIONS_DIR` | Customize the location of the `sessions` directory. | `<loki-config-dir>/sessions` |
| `LOKI_RAGS_DIR` | Customize the location of the `rags` directory. | `<loki-config-dir>/rags` |
| `LOKI_FUNCTIONS_DIR` | Customize the location of the `functions` directory. | `<loki-config-dir>/functions` |
## Agent Related Variables
You can also customize the location of full agent configurations using the following environment variables:
| Environment Variable | Description |
|------------------------------|-------------------------------------------------------------------------------------------------------------------------------------|
| `<AGENT_NAME>_CONFIG_FILE` | Customize the location of the agent's configuration file; e.g. `SQL_CONFIG_FILE` |
| `<AGENT_NAME>_MODEL` | Customize the `model` used for the agent; e.g `SQL_MODEL` |
| `<AGENT_NAME>_TEMPERATURE` | Customize the `temperature` used for the agent; e.g. `SQL_TEMPERATURE` |
| `<AGENT_NAME>_TOP_P` | Customize the `top_p` used for the agent; e.g. `SQL_TOP_P` |
| `<AGENT_NAME>_GLOBAL_TOOLS` | Customize the `global_tools` that are enabled for the agent (a JSON string array); e.g. `SQL_GLOBAL_TOOLS` |
| `<AGENT_NAME>_MCP_SERVERS` | Customize the `mcp_servers` that are enabled for the agent (a JSON string array); e.g. `SQL_MCP_SERVERS` |
| `<AGENT_NAME>_AGENT_SESSION` | Customize the `agent_session` used with the agent; e.g. `SQL_SESSION` |
| `<AGENT_NAME>_INSTRUCTIONS` | Customize the `instructions` for the agent; e.g. `SQL_INSTRUCTIONS` |
| `<AGENT_NAME>_VARIABLES` | Customize the `variables` used for the agent (in JSON format of `[{"key1": "value1", "key2": "value2"}]`); <br>e.g. `SQL_VARIABLES` |
## Logging Related Variables
The following variables can be used to change the log level of Loki or the location of the log file:
| Environment Variable | Description | Default Value |
|----------------------|---------------------------------------------|----------------------------------|
| `LOKI_LOG_LEVEL` | Customize the log level of Loki | `INFO` |
| `LOKI_LOG_FILE` | Customize the location of the Loki log file | `<user-cache-dir>/loki/loki.log` |
**Pro-Tip:** You can always tail the Loki logs using the `--tail-logs` flag. If you need to disable color output, you
can also pass the `--disable-log-colors` flag as well.
## Miscellaneous Variables
| Environment Variable | Description | Default Value |
|----------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|---------------|
| `AUTO_CONFIRM` | Bypass all `guard_*` checks in the bash prompt helpers; useful for agent composition and routing | |
| `LLM_TOOL_DATA_FILE` | Set automatically by Loki on Windows. Points to a temporary file containing the JSON tool call data. <br>Tool scripts (`run-tool.sh`, `run-agent.sh`, etc.) read from this file instead of command-line args <br>to avoid JSON escaping issues when data passes through `cmd.exe` → bash. **Not intended to be set by users.** | |
docs/MACROS.md
+103
View File
@@ -0,0 +1,103 @@
# Macros
Macros are essentially Loki "scripts"; that is, a predefined sequence of REPL commands that automate repetitive tasks or
workflows. Macros run in isolated environments, ensuring that the macros don't inherit any pre-existing role, session,
RAG, or agent state, and they will not affect your current context.
This isolation ensures that your workspace remains clean and unaffected by macro operations.
![Macro Example](./images/macros/macros-example.gif)
For more information on Loki's REPL, refer to the [REPL](./REPL.md) documentation.
## Quick Links
<!--toc:start-->
- [Macro Definition](#macro-definition)
- [Step Definitions](#step-definitions)
- [Macro Variables](#macro-variables)
- [Built-In Macros](#built-in-macros)
<!--toc:end-->
---
## Macro Definition
Macros are defined as YAML files in the `macros` subdirectory of your Loki configuration directory. The Loki configuration
directory can vary between systems, so to find the location of your macros config directory, you can use the following
command:
```shell
loki --info | grep 'macros_dir' | awk '{print $2}'
```
Macro definitions are broken into two parts: the `steps` of the macro, and an optional `variables` section that lets
users pass in variables to alter the behavior of the macro at runtime.
### Step Definitions
The step definitions for a macro are straightforward: They are simply the exact commands you would otherwise type in the
REPL.
**Example: Macro to generate a git commit message**
`macros/generate-commit-message.yaml`
```yaml
steps:
- .file `git diff` -- generate git commit message
```
Usage:
```shell
$ loki --macro generate-commit-message
>> .file `git diff` -- generate a git commit message
Add documentation on macros
```
For a full example configuration, refer to the [example macro configuration file](../config.macro.example.yaml) in the root of this project.
### Macro Variables
Sometimes it's useful to be able to modify the behavior of a macro at runtime. This is achieved with the `variables`
array of the macro definition.
To pass variables to a macro, since they are just Loki scripts, the syntax is the same as it is for any other scripting
language: You just pass them alongside your invocation.
**Example:**
```shell
$ loki --macro example-variable-macro first_argument second_argument
```
Each variable in the `variables` array has the following properties:
* `name` (Required): the name of the variable, which can be referenced in the actual steps of the macro using the
`{{name}}` syntax.
* `default` (Optional): A default value for the variable if no value is specified. If no default value is defined, and
no value is provided for the variable at runtime, Loki will error out.
* `rest` (Optional, Boolean): When set to `true`, this variable will collect all remaining arguments passed to the
macro. This behavior is only applicable when the variable is the last variable in the list. By default, this is
`false`.
The `variables` array is order-dependent; that is to say that all arguments passed to the macro are positional. So be
careful about the ordering if that is important to your macro's invocation.
**Example: Simple variable example to invoke an agent**
`macros/invoke-agent.yaml`
```yaml
variables:
- name: agent # No default value means this must be defined at runtime
- name: args
rest: true # All remaining arguments to the macro are collected into this variable
default: What can you do? # This is used if no value is passed at runtime
steps:
- .agent {{agent}}
- '{{args}}'
```
Usage:
```shell
$ loki --macro invoke-agent sql
# or
$ loki --macro invoke-agent sql What tables are available?
```
For a full example configuration, refer to the [example macro configuration file](../config.macro.example.yaml) in the root of this project.
## Built-In Macros
Loki comes packaged with some useful built-in macros. These are also good examples if you're looking for more examples
on how to make your own macros, so be sure to check out the [built-in macro definitions](../assets/macros) if you're
looking for more examples.
* `generate-commit-message` - Generate a Git commit message based on the staged changes in the current directory
docs/RAG.md
+307
View File
@@ -0,0 +1,307 @@
# RAG
Retrieval Augmented Generation (RAG) is a method of minimizing LLM hallucinations and extending the model's context
without consuming a significant portion of the context length. It uses documents and other additional resources that you
provide to give the model more context for all of your prompts.
Loki has a built-in vector database and full-text search engine to support RAG knowledge bases for your queries.
The generated knowledge bases are stored in the `rag` subdirectory of your Loki configuration directory. The location of
this directory varies by system, so you can use the following command to find your RAG directory:
```shell
loki --info | grep 'rags_dir' | awk '{print $2}'
```
## Quick Links
<!--toc:start-->
- [Usage](#usage)
- [Persistent RAG](#persistent-rag)
- [Ephemeral RAG](#ephemeral-rag)
- [How It Works](#how-it-works)
- [1. Build](#1-build)
- [2. Lookup](#2-lookup)
- [2a. Reranking (Optional)](#2a-reranking-optional)
- [3. Prompt](#3-prompt)
- [Supported Document Sources](#supported-document-sources)
- [Document Loaders](#document-loaders)
- [Document Loader Usage](#document-loader-usage)
- [Advanced Customizations](#advanced-customizations)
- [Embedding Model](#embedding-model)
- [Reranker](#reranker)
- [Chunk Size](#chunk-size)
- [Trade-Offs](#chunk-size-trade-offs)
- [Chunk Overlap](#chunk-overlap)
- [Top K](#top-k)
- [Trade-Offs](#top-k-trade-offs)
- [RAG Template](#rag-template)
<!--toc:end-->
---
## Usage
There's two ways to use RAG in Loki: A persistent RAG that can be loaded on-demand for queries, and an ephemeral one for
adding RAG to a single specific query.
### Persistent RAG
In the REPL, persistent RAG is initialized via the `.rag` command:
![Persistent RAG example](./images/rag/persistent-rag.gif)
The generated RAG is then saved to the `rag` subdirectory of the Loki configuration, and can then be loaded whenever you
want that knowledge base via either `.rag <name>` or `loki --rag <RAG>`.
### Ephemeral RAG
Short-lived RAG that is only used for a single session or query is loaded using `.file`/`--file`.
You can use it to either execute a prompt from a file, or for temporary RAG. The difference is the usage of the `--`
separator. If you only specify a filename and no `--` separator, Loki will know to read the file contents and pass them
as a query to the model. Otherwise, the `--` separator is read to indicate that this is the end of the list of documents
to load into the ephemeral RAG, and what follows is the query to pass to the model.
```shell
.file prompt.md # Read the file as a prompt
.file %% -- translate the last reply to italian
.file `git diff` -- generate a commit message
```
![Ephemeral RAG Example](./images/rag/ephemeral-rag.gif)
Once the session ends, this RAG will no longer be accessible and is only visible to the current session.
#### The `%%` Document Type
In addition to the usual documents that can be specified for persistent RAG, ephemeral RAG has a special `%%` value.
This value references the content of the last reply. So you can use it like this:
```shell
.file %% -- translate the last reply to italian
```
The `--` indicates that this is the end of your documents and the beginning of your prompt.
#### The `cmd` Document Type
Loki also lets you use command outputs for ephemeral RAG input. Simply enclose the command in backticks:
```shell
.file `git diff` -- generate a commit message
```
The `--` indicates that this is the end of your documents and the beginning of your prompt.
## How It Works
#### 1. Build
When you define RAG, Loki will first "build" the RAG. This means that Loki will consume the documents you specified and
generate [embeddings](https://huggingface.co/spaces/hesamation/primer-llm-embedding) for that text. This essentially just means that Loki translates the document into a language
the LLM can understand.
These embeddings are then stored in an in-memory vector database.
#### 2. Lookup
Loki sits between you and the model. So when you submit a prompt to the model, before Loki ever sends it, it will first
convert your prompt into embeddings (LLM language), and look for relevant snippets of text in the vector database.
Loki then passes the top `n`-snippets of text that it finds in the vector database as additional context to the model
before your prompt.
#### 2a. Reranking (Optional)
The lookup for relevant snippets of texts uses embeddings to find text that is semantically similar to your prompt, and
returns the top `n`-results. This often works fairly well, however these top results aren't always the most relevant for
answering the specific query.
Reranking improves these initial results (say, the top 20-100 text snippets) and re-scores them using a more
sophisticated model. The reranker model will rank documents by their actual usefulness for answering the query to ensure
the most relevant context is passed to the model alongside your query.
This reranking model can be customized for each RAG you build in Loki. See the [Custom Reranker](#reranker) section
below for more details on how to customize this.
#### 3. Prompt
Finally, the text snippets that were looked up in RAG are passed to the model as additional context to your prompt,
giving the model query-specific context to answer your question.
## Supported Document Sources
Loki supports a number of document sources that can be used for RAG:
| Source | Example | Comments |
|--------------------------|-----------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------------------------------------------------------|
| Files | `/tmp/dir1/file1;/tmp/dir1/file2` | |
| Directory | `/tmp/dir` | Picks up all files in a directory and all its subdirectories |
| Directory (extensions} | `/tmp/dir2/**/*.{md,txt}` | Finds all files in all subdirectories with the specified extensions |
| Recursive Filename | `/tmp/*/LOKI.md` | The following files will be picked up: <br><ul><li>`/tmp/dir1/LOKI.md`</li><li>`/tmp/dir2/subdir1/LOKI.md`</li><li>`/tmp/dir2/subdir2/LOKI.md`</li></ul> |
| URL | `https://www.ohdsi.org/data-standardization/` | Downloads and loads the specified webpage into the <br>knowledge base |
| Recursive URL (Websites) | `https://github.com/OHDSI/Vocabulary-v5.0/wiki/**` | Crawls all pages under the given URL and loads them <br>into the knowledge base |
| Document Loader (custom) | `jina:https://cloud.google.com/bigquery/docs/reference/standard-sql/` | Use a custom document loader to parse the given document |
## Document Loaders
Loki only has built-in support for loading text files. But that functionality can be extended to read all kinds of files
into your knowledge bases. These custom loaders are used by both RAG and for documents specified using the
`.file`/`--file` flags.
In the global configuration file, you can specify loaders for specific document types using the `document_loaders`
setting. Each loader is defined by specifying a name and then a command that Loki will execute to load the document.
The following variables are interpolated at runtime by Loki and can be used as placeholders in your command definitions:
* `$1` (Required) - The input file
* `$2` (Optional) - The output file. If omitted, `stdout` is used as the output destination
**Note:** It is your responsibility to ensure that any tools used to parse documents into text that Loki can read are
installed on your system and are available on your `$PATH`. Loki does not have any built-in way of installing
dependencies for document loaders for you.
The following are some example loaders:
```yaml
document_loaders:
pdf: 'pdftotext $1 -' # Use pdftotext to convert a PDF file to text
# (see https://poppler.freedesktop.org for details on how to install pdftotext)
docx: 'pandoc --to plain $1' # Use pandoc to convert a .docx file to text
# (see https://pandoc.org for details on how to install pandoc)
jina: 'curl -fsSL https://r.jina.ai/$1 -H "Authorization: Bearer {{JINA_API_KEY}}' # Use Jina to translate a website into text;
# Requires a Jina API key to be added to the Loki vault
git: > # Use yek to load a git repository into the knowledgebase (https://github.com/bodo-run/yek)
sh -c "yek $1 --json | jq 'map({ path: .filename, contents: .content })'"
```
### Document Loader Usage
Once you have your loaders defined, you can specify when Loki should use them by prefixing any RAG file/directory/URI
with the name of the loader.
**Example: Load a git repo into RAG**
![Git Repo Loader Example](./images/rag/git-loader.png)
**Example: Use pdf loader for ephemeral RAG**
```shell
$ loki --file pdf:some-file.pdf
```
## Advanced Customizations
For those familiar with RAG, Loki exposes a handful of advanced global settings that can be used to tweak your default
RAG configurations.
### Embedding Model
When Loki queries your RAG knowledge bases, it needs to first convert your query into embeddings. By default, Loki uses
the same embedding model that was used to create the knowledge base in the first place.
This can be customized to any other embedding model available in your configured clients by setting the
`rag_embedding_model` setting in your global Loki configuration file:
```yaml
rag_embedding_model: null # Specifies the embedding model used for context retrieval
```
### Reranker
By default, Loki uses [Reciprocal Rank Fusion (RRF)](https://www.elastic.co/docs/reference/elasticsearch/rest-apis/reciprocal-rank-fusion) to merge vector and keyword search results.
You can change the default reranker model to any other reranking model in your configured clients. To change the default
reranker model, simply change the value of the `rag_reranker_model` setting in your global configuration file:
```yaml
rag_reranker_model: null # By default,
```
### Chunk Size
In the context of RAG, the chunk size is the maximum length of each text chunk (measured in characters) that is created
when splitting documents. In Loki, this defaults to `2000` characters.
You can specify a different global default by setting the `rag_chunk_size` property in your global configuration file:
```yaml
rag_chunk_size: null # Defines the size of chunks for document processing in characters
```
#### Chunk Size Trade-Offs
Keep in mind the following trade-offs when changing the chunk size:
* **Smaller chunks (e.g. 256 characters):** More precise retrieval, better semantic focus, but may lack context or split
important information
* **Larger chunks (e.g. 1024 characters):** More context preserved, fewer chunks to manage, but less precise matching
and more noise in retrieved document
### Chunk Overlap
Chunk overlap in RAG is the number of characters that overlap between consecutive chunks to maintain continuity.
---
**Example:** If the following sentence is cut off at the end of one chunk
`I was doing fine until someone brought up`
You'll ideally want that full sentence to be picked up at the beginning of the next chunk to make sure the full meaning
is captured. So in this example, if your chunk overlap is 42 characters, then the start of the next chunk would look
like this:
`I was doing fine until someone brought up the game. <next sentence>`
---
Often, this value is 10%-20% of the chunk size.
By default, in Loki, this value is 5% the chunk size. You can override this and specify the default chunk overlap (in
characters) that Loki should use as a global default by setting the `rag_chunk_overlap` property in the global Loki
configuration file:
```yaml
rag_chunk_overlap: null # Defines the overlap between chunks
```
### Top K
In RAG, `top_k` represents the top `k`-chunks to return from the vector database query. Think of it like if you search
something on Google and only care about the top 10 results, that's what you'll use for your context.
In Loki, the default value for this is `5`. You can customize this global default by setting the `rag_top_k` property in
your global configuration file:
```yaml
rag_top_k: 5 # Specifies the number of documents to retrieve for answering queries
```
#### Top K Trade-Offs
When customizing this value, keep in mind the following trade-offs so you get the best performance:
* **Lower top_k (e.g. 3):** Faster, more focused context, lower cost, but risks missing relevant information
* **Higher top_k (e.g. 10):** More comprehensive coverage, but more noise, higher latency, increased token costs, and
potential context window constraints
### RAG Template
When you use RAG in Loki, after Loki performs the lookup for relevant chunks of text to add as context to your query, it
will add the retrieved text chunks as context to your query before sending it to the model. The format of this context
is determined by the `rag_template` setting in your global Loki configuration file.
This template utilizes three placeholders:
* `__INPUT__`: The user's actual query
* `__CONTEXT__`: The context retrieved from RAG
* `__SOURCES__`: A numbered list of the source file paths or URLs that the retrieved context came from
These placeholders are replaced with the corresponding values into the template and make up what's actually passed to
the model at query-time. The `__SOURCES__` placeholder enables the model to cite which documents its answer is based on,
which is especially useful when building knowledge-base assistants that need to provide verifiable references.
The default template that Loki uses is the following:
```text
Answer the query based on the context while respecting the rules. (user query, some textual context and rules, all inside xml tags)
<context>
__CONTEXT__
</context>
<sources>
__SOURCES__
</sources>
<rules>
- If you don't know, just say so.
- If you are not sure, ask for clarification.
- Answer in the same language as the user query.
- If the context appears unreadable or of poor quality, tell the user then answer as best as you can.
- If the answer is not in the context but you think you know the answer, explain that to the user then answer with your own knowledge.
- Answer directly and without using xml tags.
- When using information from the context, cite the relevant source from the <sources> section.
</rules>
<user_query>
__INPUT__
</user_query>
```
You can customize this template by specifying the `rag_template` setting in your global Loki configuration file. Your
template *must* include both the `__INPUT__` and `__CONTEXT__` placeholders in order for it to be valid. The
`__SOURCES__` placeholder is optional. If it is omitted, source references will not be included in the prompt.
docs/REPL-PROMPT.md
+117
View File
@@ -0,0 +1,117 @@
# Customize REPL Prompt
The prompt you see when you start the Loki REPL can be customized to your liking. This is achieved via the `left_prompt`
and `right_prompt` settings in the global Loki configuration file:
```yaml
left_prompt: '{color.red}{model}){color.green}{?session {?agent {agent}>}{session}{?role /}}{!session {?agent {agent}>}}{role}{?rag @{rag}}{color.cyan}{?session )}{!session >}{color.reset} '
right_prompt: '{color.purple}{?session {?consume_tokens {consume_tokens}({consume_percent}%)}{!consume_tokens {consume_tokens}}}{color.reset}'
```
The location of the global configuration file differs between systems, so you can use the following command to find your
global configuration file's location:
```shell
loki --info | grep 'config_file' | awk '{print $2}'
```
## Quick Links
<!--toc:start-->
- [Syntax](#syntax)
- [Variables](#variables)
<!--toc:end-->
## Syntax
The syntax for the prompts consists of plain text and templates contained in `{...}`. The plain text is
printed exactly as given.
The syntax for the templates `{...}` is as follows:
* `{variable}` - Replaced with the value of `variable`
* `{?variable <template>}` - Evaluate the `<template>` when `variable` is evaluated to `true`
* `{!variable <template>}` - Evaluate the `<template>` when `variable` is evaluated to `false`
Where a `<template>` is another expression consisting of plain text and/or more special computations inside `{...}`.
Variables are evaluated to also be "truthy"; that is, if a variable is undefined, it is considered to be the exact same
as if that variable's value was `false`.
**Example 1: Simple Boolean Usage**
For the prompt `{?variable yay}{!variable boo}`, if `variable=true`, then the output will be
```
yay
```
And if `variable=false`:
```
boo
```
**Example 2: Nested Expressions**
For the prompt `{?variable {!variable2 yay}>}`, and assuming
* `variable=true`
* `variable2=false`
the output will be
```
yay>
```
If `variable2=true`, the output will be empty.
If `variable=false`, the output will be empty.
## Variables
The following variables and output modifiers are available to you when you're creating your prompts:
```yaml
# Model Variables
model: openai:gpt-4 # The active model's full name
client_name: openai # The name of the client serving the active model
model_name: gpt-4 # The aliased name of the active model
max_input_tokens: 4096 # The maximum number of input tokens for the active model
# Configuration Variables
temperature: 1.0 # The temperature for the active model
top_p: 0.9 # The top_p for the active model
dry_run: true # Whether the given command is flagged to be a dry run
stream: false # Whether streaming responses are enabled
save: true # Whether shell history is saved
wrap: 120 # The number of characters to allow before wrapping around output to the next line
# Role Variables
role: code # The active role
# Session Variables
session: temp # The name of the active session
dirty: false # Whether the session settings have been updated but not persisted
consume_tokens: 200 # The number of tokens consumed
consume_percent: 1% # The percentage of tokens consumed to the maximum input tokens
user_messages_len: 0 # The total number of sent user messages
# RAG Variables
rag: temp # The name of the active RAG
# Agent Variables
agent: todo-sh # The name of the active agent
# ANSI COLORS
color.reset:
color.black:
color.dark_gray:
color.red:
color.light_red:
color.green:
color.light_green:
color.yellow:
color.light_yellow:
color.blue:
color.light_blue:
color.purple:
color.light_purple:
color.magenta:
color.light_magenta:
color.cyan:
color.light_cyan:
color.white:
color.light_gray:
```
docs/REPL.md
+260
View File
@@ -0,0 +1,260 @@
# Loki REPL Guide
In addition to being a CLI, Loki also has a built-in REPL (Read-Execute-Print-Loop). This enables users to quickly try
out prompts, commands, configurations, and everything in between without having to modify the same command every time.
You can enter the REPL by simply typing `loki` without any follow-up flags or arguments.
## Quick Links
<!--toc:start-->
- [Features](#features)
- [REPL Commands](#repl-commands)
- [`.model` - Change the current LLM](#model---change-the-current-llm)
- [`.role` - Role management](#role---role-management)
- [`.prompt` - Set a temporary role using a prompt](#prompt---set-a-temporary-role-using-a-prompt)
- [`.session` - Session management](#session---session-management)
- [`.agent` - Chat with an AI agent](#agent---chat-with-an-ai-agent)
- [`.rag` - Chat with documents](#rag---chat-with-documents)
- [`.macro` - Execute a macro](#macro---execute-a-macro)
- [`.file` - Read files and use them as input](#file---read-files-and-use-them-as-input)
- [`.vault` - Manage the Loki vault](#vault---manage-the-loki-vault)
- [`.continue` - Continue the previous response](#continue---continue-the-previous-response)
- [`.regenerate` - Regenerate the last response](#regenerate---regenerate-the-last-response)
- [`.copy` - Copy the last response to your clipboard](#copy---copy-the-last-response-to-your-clipboard)
- [`.set` - Adjust runtime settings](#set---adjust-runtime-settings)
- [`.edit` - Modify configuration files](#edit---modify-configuration-files)
- [`.delete` - Delete configurations from Loki](#delete---delete-configurations-from-loki)
- [`.info` - Display information about the current mode](#info---display-information-about-the-current-mode)
- [`.authenticate` - Authenticate the current model client via OAuth](#authenticate---authenticate-the-current-model-client-via-oauth)
- [`.exit` - Exit an agent/role/session/rag or the Loki REPL itself](#exit---exit-an-agentrolesessionrag-or-the-loki-repl-itself)
- [`.help` - Show the help guide](#help---show-the-help-guide)
<!--toc:end-->
---
## Features
The REPL has features that are intended to make your Loki experience as easy and as enjoyable as possible! This includes
things like
* **Tab Autocompletion:** Every command in the REPL (i.e. everything that starts with a `.`) has fuzzy search auto
completions.
* `.<tab>` to complete REPL commands
* `.model <tab>` to complete chat models
* `.set <tab>` to complete configuration keys
* `.set key <tab>` to complete configuration values
* **Multi-Line Prompts:** You can also type prompts that span more than one line to help organize your thoughts. This
can be done in the following ways:
* `Ctrl-o` to open the current input buffer in your preferred editor (either the value of `editor` or `$EDITOR`)
* You can paste multi-line text
* You can type `:::` to start multi-line editing, and use `:::` to finish it.
* And finally, you can use hotkeys like `{ctrl/shift/alt}+enter` or `ctrl-j` to insert a new line directly in the
REPL.
* **History Search** Press `ctrl+r` to search the REPL history, and navigate it with `↑↓`
* **Configurable Keybindings:** You can switch between `emacs` style keybindings or `vi` style keybindings
* [**Custom REPL Prompt:**](./REPL-PROMPT.md) You can even customize the REPL prompt to display information about the
current context in the prompt
* **Built-in user interaction tools:** When function calling is enabled in the REPL, the `user__ask`, `user__confirm`,
`user__input`, and `user__checkbox` tools are always available for interactive prompts. These are not injected in the
one-shot CLI mode.
---
## REPL Commands
All REPL commands begin with a `.` to indicate that they're not part of a prompt. The following list details the
commands available in Loki:
### `.model` - Change the current LLM
When browsing models in the REPL, use the following legend to understand the purpose of each column in the model table:
```
openai:gpt-4o 128000 / 4096 | 5 / 15 👁 ⚒
| | | | | | └─ supports function calling
| | | | | └─ support vision (multi-modal)
| | | | └─ output price ($/1M)
| | | └─ input price ($/1M)
| | |
| | └─ max output tokens
| └─ max input tokens
└─ model id
```
![model](./images/repl/model.gif)
For more information about how to add models to Loki, refer to the [clients documentation](./clients/CLIENTS.md).
### `.role` - Role management
Loki offers the following commands to manage your roles:
| Command | Description |
|--------------|-------------------------------------------------------------------------|
| `.role` | Create or switch to a role |
| `.info role` | Show information about the active role |
| `.edit role` | Open the active role's configuration file in your preferred text editor |
| `.save role` | Save the active role and its configurations to a configuration file |
| `.exit role` | Exit the active role |
![role](./images/roles/code.gif)
For more information about roles in Loki and how to build them, refer to the [roles documentation](./ROLES.md).
### `.prompt` - Set a temporary role using a prompt
If you need to create a temporary role that you want to discard after use, you use `.prompt`. `.prompt`-based roles
cannot be persisted to a file and saved.
![prompt-role](./images/roles/prompt-role.gif)
### `.session` - Session management
Use the following commands to manage sessions in Loki:
| Command | Description |
|---------------------|---------------------------------------------------------------------------------------------|
| `.session` | Start or switch to a session |
| `.empty session` | Clear all messages for the active session |
| `.compress session` | Compress the session messages using the `summarization_prompt` setting in the global config |
| `.info session` | Display information about the active session |
| `.edit session` | Open the active session's configuration in your preferred text editor |
| `.save session` | Save the active session to a `session` configuration file |
| `.exit session` | Exit the active session |
![sessions](./images/sessions/sessions-example.gif)
For more information on sessions and how to use them in Loki, refer to the [sessions documentation](./SESSIONS.md).
### `.agent` - Chat with an AI agent
Loki lets you build OpenAI GPT-style agents. The following commands let you interact with and manage your agents in
Loki:
| Command | Description |
|----------------------|-----------------------------------------------------------------------------------------------|
| `.agent` | Use an agent |
| `.starter` | Display and use conversation starters for the active agent |
| `.clear todo` | Clear the todo list and stop auto-continuation (requires `auto_continue: true` on the agent) |
| `.edit agent-config` | Open the agent configuration in your preferred text editor |
| `.info agent` | Display information about the active agent |
| `.exit agent` | Leave the active agent |
![agent](./images/agents/sql.gif)
For more information on agents in Loki and how to create them, refer to the [agents documentation](./AGENTS.md).
### `.rag` - Chat with documents
RAG (Retrieval Augmented Generation) enables you to load documents into the LLM so you can ask questions about it or
complete tasks using the documents as additional context.
| Command | Description |
|------------------|------------------------------------------------------------------------------|
| `.rag` | Initialize or access a RAG |
| `.edit rag-docs` | Add or remove documents from the active RAG using your preferred text editor |
| `.rebuild rag` | Rebuild the active RAG to accommodate document changes |
| `.sources rag` | Show a works-cited of the sources used in the last query |
| `.info rag` | Display information about the active RAG |
| `.exit rag` | Exit the active RAG |
![rag](./images/rag/persistent-rag.gif)
For more information about RAG in Loki and how to utilize it, refer to the [rag documentation](./RAG.md).
### `.macro` - Execute a macro
Macros in Loki are like "scripts" of commands that can be run in isolated environments; that means they do not use any
active settings and use the same settings they had when written. They are created/executed using the `.macro <name>`
command.
![macro](./images/macros/macros-example.gif)
For more information on macros in Loki and how to create them, refer to the [macros documentation](./MACROS.md).
### `.file` - Read files and use them as input
Loki lets you specify any number of documents that you can load and use as ephemeral RAG to chat with the LLM. To see
what files or values you can pass to it, simply run the command `.file` with no arguments:
```shell
openai:gpt-4o)> .file
Usage: .file <file|dir|url|%%|cmd>... [-- <text>...]
```
![ephemeral-rag](./images/rag/ephemeral-rag.gif)
For more information about ephemeral RAG, refer to the [ephemeral RAG documentation](./RAG.md#ephemeral-rag).
### `.vault` - Manage the Loki vault
The Loki vault lets users store sensitive secrets and credentials securely so that there's no plaintext secrets
anywhere in your configurations.
![vault](./images/vault/vault-demo.gif)
For more information about the Loki vault, refer to the [vault documentation](./VAULT.md).
### `.continue` - Continue the previous response
When you have a response that exceeds the context length, you can use the `.continue` command to continue the generation
of the last response.
![continue](./images/repl/continue.gif)
### `.regenerate` - Regenerate the last response
If ever your response is interrupted, or you want to try generating it again, you can use the `.regenerate` command to do
this without having to retype your query:
![regenerate](./images/repl/regenerate.gif)
### `.copy` - Copy the last response to your clipboard
If you're trying to copy the last response (like copying some code), you can use the `.copy` command to copy the entire
last response to your system clipboard:
![copy](./images/repl/copy.gif)
### `.set` - Adjust runtime settings
You can use `.set` to adjust select settings at runtime. This is useful when you're experimenting with settings and want
to know how they'll affect Loki. To persist the changes you make, be sure to update them in the global configuration
file.
![set](./images/repl/set.gif)
### `.edit` - Modify configuration files
The `.edit` command lets you modify configuration files for the current mode of the REPL. It will open the selected
configuration in your preferred text editor. It lets you modify the following configurations:
* `.edit config` - Modify the global configuration
* `.edit role` - Modify the active role's configuration
* `.edit session` - Modify the active session's configuration
* `.edit agent-config` - Modify the active agent's configuration
* `.edit rag-docs` - Add or remove documents from the active RAG
### `.delete` - Delete configurations from Loki
The `.delete` command allows you to delete entities in Loki without having to directly run `rm -rf` on the configuration
directory or file corresponding to the target entity. You can use it to delete the following entities:
* `.delete role` - Delete select roles
* `.delete session` - Delete select sessions
* `.delete macro` - Delete select macros
* `.delete rag` - Delete select RAGs
* `.delete agent-data` - Delete select agent's configurations and all tools
### `.info` - Display information about the current mode
The `.info` command provides useful information about different modes that Loki may be operating in. It's helpful if you
want a quick understanding of the system info, a role's configuration, an agent's configuration, etc.
The following entities are supported:
| Command | Description |
|-----------------|-------------------------------------------------------------|
| `.info` | Display system information (identical to the `--info` flag) |
| `.info role` | Display information about the active role |
| `.info session` | Display information about the active session |
| `.info agent` | Display information about the active agent |
| `.info rag` | Display information about the active RAG |
### `.authenticate` - Authenticate the current model client via OAuth
The `.authenticate` command will start the OAuth flow for the current model client if
* The client supports OAuth (See the [clients documentation](./clients/CLIENTS.md#providers-that-support-oauth) for supported clients)
* The client is configured in your Loki configuration to use OAuth via the `auth: oauth` property
### `.exit` - Exit an agent/role/session/rag or the Loki REPL itself
The `.exit` command is used to move between modes in the Loki REPL.
| Command | Description |
|-----------------|-------------------------|
| `.exit role` | Exit the active role |
| `.exit session` | Exit the active session |
| `.exit agent` | Exit the active agent |
| `.exit rag` | Exit the active RAG |
| `.exit` | Exit the Loki REPL |
### `.help` - Show the help guide
Just like with any shell or REPL, you sometimes need a little help and want to know what commands are available to you.
That's when you use the `.help` command.
docs/ROLES.md
+266
View File
@@ -0,0 +1,266 @@
# Roles
When customizing the behavior or LLMs, we use roles to "constrain" the responses or behavior of the LLM to whatever
purpose we desire.
Think of them kind of like a baby: That baby can grow up to do anything! Be a resume builder, teacher, engineer, etc.
The only difference is that with roles, we're explicitly telling the LLM what we want it to be. Also: the LLM is already
grown up so we don't have to wait!
![Role demo](./images/roles/code.gif)
## Quick Links
<!--toc:start-->
- [Role Definition](#role-definition)
- [Metadata Header](#metadata-header)
- [Instructions](#instructions)
- [Special Case: Metadata Header Only](#special-case-metadata-header-only)
- [Prompt Types](#prompt-types)
- [Embedded Prompts](#embedded-prompts)
- [System Prompts](#system-prompts)
- [Few-Shot Prompt](#few-shot-prompt)
- [Built-In Roles](#built-in-roles)
<!--toc:end-->
---
## Role Definition
Roles in Loki are Markdown files that live in the `roles` directory of your Loki configuration. Loki configuration
locations vary between systems, so you can use the following command to find the location of your roles configuration
directory:
```shell
loki --info | grep 'roles_dir' | awk '{print $2}'
```
All role configuration files have two parts: The metadata header, and the instructions.
**Example:** An expert resume builder role that specializes in helping users build and refine their resumes.
```markdown
---
# This is the metadata header
name: resume-builder
model: openai:gpt-4o
temperature: 0.2
top_p: 0
enabled_tools: fs_ls,fs_cat
enabled_mcp_servers: github
---
<!-- This is the instructions -->
You are an expert resume builder.
```
To see a full example configuration for a role, refer to the [example role configuration](../config.role.example.md)
file in the root of the repo.
### Metadata Header
The metadata header in all role configuration files is completely optional. It lets you define role-specific settings
for each role that make the model work the way you want for your role. This includes things like forcing your role to
always use a specific model, set of tools, and tailoring the hyperparameters of the model for your role.
The header consists of a YAML-formatted list of settings that let you customize the model behavior for your role. These
settings sit between `---` separators in your role configuration so Loki knows they're not part of the instructions you
want to feed the model.
The following table lists the available configuration settings and their default values (if undefined):
| Setting | Default | Description |
|-----------------------|----------------------------------------------------------------|---------------------------------------------------------------------------------------------------------------|
| `name` | The name of the role markdown file | The name of the role |
| `model` | Default configured model or currently in-use model (REPL mode) | The preferred model to use with this role |
| `temperature` | Default `temperature` for the preferred model | Controls the creativity and randomness of the model's responses |
| `top_p` | Default `top_p` for the preferred model | Alternative way to control the model's output diversity, affecting the <br>probability distribution of tokens |
| `enabled_tools` | Global setting for `enabled_tools` | The tools that this role utilizes |
| `enabled_mcp_servers` | Global setting for `enabled_mcp_servers` | The MCP servers that this role utilizes |
| `prompt` | `null` | See [Prompt Types](#prompt-types) for detailed usage |
### Instructions
The instructions for a role is what you use to tell the model how you want it to behave. This typically consists of one
or two sentences, but can be more. To see some examples, look at the [built-in roles](../assets/roles) to see how they are defined.
**Pro-Tip:** The struggle to create good instructions for a role (or any other kind of instructions for your model) is
so common, that Loki comes with a role to help you write instructions for roles! Simply invoke the role to start
creating a role with the `create-prompt` role:
```shell
loki -r create-prompt
```
### Special Case: Metadata Header Only
When instructions are defined, the metadata header is optional. However sometimes we want a way to enable specific
functions or MCP servers when prompting different models. In this situation, you need only specify the metadata header
to just enable these settings as you like.
**Example: Role that enables all filesystem tools**
`roles/filesystem-functions.md`
```markdown
---
enabled_tools: fs_ls,fs_cat,fs_mkdir,fs_patch,fs_write
---
```
**Example: Role that enables the GitHub MCP server with the ollama:deepseek-r1 model**
`roles/github.md`
```markdown
---
model: ollama:deepseek-r1
enabled_mcp_servers: github
---
```
For more examples of this special use case of roles, you can look at the role configuration files for the following
built-in roles:
* [explain-shell](../assets/roles/explain-shell.md) - Explains cryptic shell commands in natural language
* [functions](../assets/roles/functions.md) - Enables all available functions (i.e. all globally `visible_functions`)
* [mcp-servers](../assets/roles/mcp-servers.md) - Enables all available MCP servers
## Special Variables
Loki has a set of built-in special variables that it will inject into your role's instructions if it finds them in the
`{{variable_name}}` syntax. The available special variables are listed below:
| Name | Description | Example |
|-----------------|-----------------------------------------------------------|----------------------------|
| `__os__` | Operating system name | `linux` |
| `__os_family__` | Operating system family | `unix` |
| `__arch__` | System architecture | `x86_64` |
| `__shell__` | The current user's default shell | `bash` |
| `__locale__` | The current user's preferred language and region settings | `en-US` |
| `__now__` | Current timestamp in ISO 8601 format | `2025-11-07T10:15:44.268Z` |
| `__cwd__` | The current working directory | `/tmp` |
## Prompt Types
In Loki, you can also create roles with pre-configured prompts so you can template prompts for your use cases. This is
the purpose of the `prompt` field in the role's metadata header.
There's three types of prompts you can create:
### Embedded Prompts
Embedded prompts let you create templated prompts for any input given to it. They are ideal for concise, input-driven
replies from the model. The input that users pass to Loki are injected into your prompt via a `__INPUT__` placeholder in
your prompt.
**Example: Role to convert the given input to TOML**
`roles/convert-to-toml.md`
```markdown
---
prompt: convert __INPUT__ to TOML
---
Convert the given input to TOML format. Exclude any markdown formatting or code blocks and only output code.
```
Usage:
```shell
$ loki -r json-to-toml '{"test":"hi me"}'
test = "hi me"
```
Without the instructions (i.e. the prompt after the metadata header), this role would simply generate the following
message for the model:
```json
[
{"role": "user", "content": "convert {\"test\":\"hi me\"} to TOML"}
]
```
### System Prompts
System prompts let you set the general context of the LLMs behavior. This is no different than other system prompts you
define in ChatGPT, Claude, Open WebUI, etc.
They are essentially Embedded Prompts without an `__INPUT__` placeholder.
**Example: Role to convert all input words to emoji**
`roles/emoji.md`
```markdown
---
prompt: convert my words to emojis
---
Convert all given input words into emojis
```
Usage:
```shell
$ loki -r emoji music joy
🎵 😊
```
Without the instructions (i.e. the prompt after the metadata header), this role would simply generate the following
messages for the model:
```json
[
{"role": "system", "content": "convert my words to emojis"},
{"role": "user", "content": "music joy"}
]
```
### Few-Shot Prompt
[Few-Shot prompting](https://www.promptingguide.ai/techniques/fewshot) is a technique to enable in-context learning for LLMs by providing examples in the prompt to steer
the model to better performance. In Loki, this is done as an extension of System Prompts.
**Example: Role to output code only**
`roles/code-generator.md`
~~~markdown
---
prompt: |-
Output code only without comments or explanations.
### INPUT:
async sleep in js
### OUTPUT:
```javascript
async function timeout(ms) {
return new Promise(resolve => setTimeout(resolve, ms));
}
```
---
Output code only in response to the user's request
~~~
Usage:
~~~shell
$ loki -r code-generator python add two numbers
```python
# Function to add two numbers
def add_numbers(num1, num2):
return num1 + num2
# Example usage
number1 = 5
number2 = 7
result = add_numbers(number1, number2)
print(f"The sum of {number1} and {number2} is {result}.")
```
~~~
Without the instructions (i.e. the prompt after the metadata header), this role would simply generate the following
messages for the model:
```json
[
{"role": "system", "content": "Output code only without comments or explanations."},
{"role": "user", "content": "async sleep in js"},
{"role": "assistant", "content": "```javascript\nasync function timeout(ms) {\n return new Promise(resolve => setTimeout(resolve, ms));\n}\n```"},
{"role": "user", "content": "python add two numbers"}
]
```
## Built-In Roles
Loki comes packaged with some useful built-in roles. These are also good examples if you're looking for more examples on
how to make your own roles, so be sure to check out the [built-in role definitions](../assets/roles) if you're looking
for more examples.
* `code`: Generates code (used by `loki -c`)
* `create-prompt`: Creates a prompt based on the user's input
* `create-title`: Creates 3-6 word titles based on the user's input
* `explain-shell`: Explains shell commands
* `functions`: Enable all globally-visible functions
* `github`: Interact with GitHub using natural language
* `mcp-servers`: Enables all MCP servers
* `repo-analyzer`: Ask questions about the code repository in the current working directory
* `shell`: Convert natural language into shell commands (used by `loki -e`)
* `slack`: Interact with Slack using natural language
## Temporary Roles
Loki also enables you to create temporary roles that will be discarded once you're finished with them. This is done via
the `.prompt/--prompt` command:
![prompt role](./images/roles/prompt-role.gif)
docs/SESSIONS.md
+44
View File
@@ -0,0 +1,44 @@
# Sessions
By default, Loki does not send back all previous messages in a conversation to the model. This means that each time you
query a model, it's essentially a one-off. However, Loki does support chat-like conversations with LLMs via its
`sessions` mechanism.
Sessions in Loki enable the familiar conversational interactions with LLMs. This means you can reference previous
answers and ask follow-up questions and the model will know what you're referring to.
Sessions can be temporary, or can be saved so you can continue conversations at a later time.
Saved sessions are stored in the `sessions` subdirectory of the Loki configuration directory. The location of the
`sessions` directory varies by system, so you can use the following command to find the `sessions` directory if you need
it:
```shell
loki --info | grep 'sessions_dir' | awk '{print $2}'
```
## Usage
When you use a session in Loki, you can either persist it or discard it once you're done. Sessions you discard are then
just considered 'temporary' sessions.
![Persistent Session Example](./images/sessions/sessions-example.gif)
Sessions you persist and then load again later will inherit the same configuration as was used during the last usage of
that session. That is to say, if you had certain tools or MCP servers enabled when you were last in that session, they
will be available again when you continue that session.
## Configuration
Session behavior can be configured from the global Loki configuration file. The location of this file varies between
systems so you can use the following command to locate it on your system:
```shell
loki --info | grep 'config_file' | awk '{print $2}'
```
The following settings are available to customize the default behavior of sessions globally:
| Setting | Description |
|--------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| `save_session` | Controls the persistence of the session. <br><ul><li>If `true`, then any time you're in a session, changes will auto-save unless explicitly defined otherwise.</li> <li>If `false`, then any time you're in a session, changes will not auto-save unless explicitly specified otherwise.</li><li>If `null`, Loki will always prompt the user for what to do.</li></ul> |
| `compression_threshold` | Defines the token count threshold at which Loki will compress the session to save on the context length |
| `summarization_prompt` | This is the prompt that is used to compress the session up to a given point when compression is triggered |
| `summary_context_prompt` | This is the prompt that's used to add the summarized conversation generated by the `summarization_prompt` as context to the model |
docs/SHELL-INTEGRATIONS.md
+104
View File
@@ -0,0 +1,104 @@
# Loki Shell Integrations
Loki supports the following integrations with a handful of shell environments to enhance user experience and streamline workflows.
## Tab Completions
### Dynamic
Dynamic tab completions are supported by Loki to assist users in quickly completing commands, options, and arguments.
You can enable it by using the corresponding command for your shell. To enable dynamic tab completions for every
shell session (i.e. persistently), add the corresponding command to your shell's configuration file as indicated:
```shell
# Bash
# (add to: `~/.bashrc`)
source <(COMPLETE=bash loki)
# Zsh
# (add to: `~/.zshrc`)
source <(COMPLETE=zsh loki)
# Fish
# (add to: `~/.config/fish/config.fish`)
source <(COMPLETE=fish loki | psub)
# Elvish
# (add to: `~/.elvish/rc.elv`)
eval (E:COMPLETE=elvish loki | slurp)
# PowerShell
# (add to: `$PROFILE`)
$env:COMPLETE = "powershell"
loki | Out-String | Invoke-Expression
```
At the time of writing, `nushell` is not yet fully supported for dynamic tab completions due to limitations
in the [`clap`](https://crates.io/crates/clap) crate. However, `nushell` support is being actively developed, and will
be added in a future release.
Progress on this feature can be tracked in the following issue: [Clap Issue #5840](https://github.com/clap-rs/clap/issues/5840).
### Static
Static tab completions (i.e. pre-generated completion scripts that are not context aware) can also be generated using the
`--completions` flag. You can enable static tab completions by using the corresponding commands for your shell. These commands
will enable them for every shell session (i.e. persistently):
```shell
# Bash
echo 'source <(loki --completions bash)' >> ~/.bashrc
# Zsh
echo 'source <(loki --completions zsh)' >> ~/.zshrc
# Fish
echo 'loki --completions fish | source' >> ~/.config/fish/config.fish
# Elvish
echo 'eval (loki --completions elvish | slurp)' >> ~/.elvish/rc.elv
# Nushell
[[ -d ~/.config/nushell/completions ]] || mkdir -p ~/.config/nushell/completions
loki --completions nushell | save -f ~/.config/nushell/completions/loki.nu
echo 'use ~/.config/nushell/completions/cli.nu *' >> ~/.config/nushell/config.nu
# PowerShell
Add-content $PROFILE "loki --completions powershell | Out-String | Invoke-Expression"
```
## Shell Assistant
Loki has an `-e,--execute` flag that allows users to run natural language commands directly from the CLI. It accepts
natural language input and translates it into executable shell commands.
![Shell Assistant Demo](./images/shell_integrations/assistant.gif)
## Intelligent Command Completions
Loki also provides shell scripts that bind `Alt-e` to `loki -e "<current command line>"`, allowing users to generate
commands from natural text directly without invoking the CLI.
For example:
```shell
$ find all typescript files with more than 100 lines<Alt-e>
# Gets replaced with
$ find . -name '*.ts' -type f -exec awk 'NR>100{exit 1}' {} \; -print
```
To use the CLI helper, add the content of the appropriate integration script for your shell to your shell configuration file:
* [Bash Integration](../scripts/shell-integration/integration.bash) (add to: `~/.bashrc`)
* [Zsh Integration](../scripts/shell-integration/integration.zsh) (add to: `~/.zshrc`)
* [Elvish Integration](../scripts/shell-integration/integration.elv) (add to: `~/.elvish/rc.elv`)
* [Fish Integration](../scripts/shell-integration/integration.fish) (add to: `~/.config/fish/config.fish`)
* [Nushell Integration](../scripts/shell-integration/integration.nu) (add to: `~/.config/nushell/config.nu`)
* [PowerShell Integration](../scripts/shell-integration/integration.ps1) (add to: `$PROFILE`)
## Explain Commands
In addition to the Shell Assistant, Loki has a built-in role that explains shell commands to you to decipher their
language. So if Loki generates a command that you're unsure of what it does, simply pass it to the `explain-shell` role:
![Explain Shell Role](./images/shell_integrations/explain-shell.png)
## Code Generation
Users can also directly generate code snippets from natural language prompts using the `-c,--code` flag.
![Code Generation Demo](./images/shell_integrations/code-generation.gif)
**Pro Tip:** Pipe the output of the code generation directly into `tee` to ensure the generated code is properly extracted
from any generated Markdown (i.e. remove any triple backticks).
docs/THEMES.md
+71
View File
@@ -0,0 +1,71 @@
# Theming Loki
Loki supports customizing the theme via a `.tmTheme` file.
## Setup
To install a custom theme, download the `.tmTheme` file to the Loki configuration directory and name it `dark.tmTheme`
or `light.tmTheme`. The location of the Loki configuration directory varies between systems, so you can use the
following command to locate it on your system:
```shell
loki --info | grep 'config_dir' | awk '{print $2}'
```
## Themes
### 1337-Scheme
https://raw.githubusercontent.com/MarkMichos/1337-Scheme/ca6a329cfda8307449d405b70f8fab34b8fd23b5/1337.tmTheme
![1337-scheme](./images/themes/1337-scheme.png)
### Coldark
https://raw.githubusercontent.com/ArmandPhilippot/coldark-bat/e44750b2a9629dd12d8ed3ad9fd50c77232170b9/Coldark-Dark.tmTheme
![coldark](./images/themes/coldark.png)
### Dracula
https://raw.githubusercontent.com/dracula/sublime/c2de0acf5af67042393cf70de68013153c043656/Dracula.tmTheme
![dracula](./images/themes/dracula.png)
### GitHub
https://raw.githubusercontent.com/AlexanderEkdahl/github-sublime-theme/508740b2430c3c3a9e785fc93ee1d7c6f233af53/GitHub.tmTheme
![github](./images/themes/github.png)
### gruvbox
#### Dark
https://raw.githubusercontent.com/subnut/gruvbox-tmTheme/64c47250e54298b91e2cf8d401320009aba9f991/gruvbox-dark.tmTheme
![gruvbox-dark](./images/themes/gruvbox-dark.png)
#### Light
https://raw.githubusercontent.com/subnut/gruvbox-tmTheme/64c47250e54298b91e2cf8d401320009aba9f991/gruvbox-light.tmTheme
![gruvbox-light](./images/themes/gruvbox-light.png)
### OneHalf
#### Dark
https://raw.githubusercontent.com/sonph/onehalf/141c775ace6b71992305f144a8ab68e9a8ca4a25/sublimetext/OneHalfDark.tmTheme
![onehalf-dark](./images/themes/onehalf-dark.png)
#### Light
https://raw.githubusercontent.com/sonph/onehalf/141c775ace6b71992305f144a8ab68e9a8ca4a25/sublimetext/OneHalfLight.tmTheme
![onehalf-light](./images/themes/onehalf-light.png)
### Solarized
#### Dark
https://raw.githubusercontent.com/braver/Solarized/87e01090cggjf5fb821a234265b3138426ae84900e7/Solarized%20(dark).tmTheme
![solarized-dark](./images/themes/solarized-dark.png)
#### Light
https://raw.githubusercontent.com/braver/Solarized/87e01090cf5fb821a234265b3138426ae84900e7/Solarized%20(light).tmTheme
![solarized-light](./images/themes/solarized-light.png)
### Sublime Snazzy
https://raw.githubusercontent.com/greggb/sublime-snazzy/70343201f1d7539adbba3c79e2fe81c2559a0431/Sublime%20Snazzy.tmTheme
![sublime-snazzy](./images/themes/sublime-snazzy.png)
### TwoDark
https://raw.githubusercontent.com/erremauro/TwoDark/8e0f6fa5b59d196658a22288f519fd8320de4c87/TwoDark.tmTheme
![twodark](./images/themes/twodark.png)
### Visual Studio Dark+
https://raw.githubusercontent.com/vidann1/visual-studio-dark-plus/01ee1e8e0dc578f3b4e8c0dbb6aa0279b4a26a40/Visual%20Studio%20Dark%2B.tmTheme
![visual-studio-dark-plus](./images/themes/visual-studio-dark-plus.png)
### Zenburn
https://raw.githubusercontent.com/colinta/zenburn/86d4ee7a1f884851a1d21d66249687f527fced32/zenburn.tmTheme
![zenburn](./images/themes/zenburn.png)
docs/TODO-SYSTEM.md
+250
View File
@@ -0,0 +1,250 @@
# Todo System
Loki's Todo System is a built-in task tracking feature designed to improve the reliability and effectiveness of LLM agents,
especially smaller models. It provides structured task management that helps models:
- Break complex tasks into manageable steps
- Track progress through multistep workflows
- Automatically continue work until all tasks are complete
- Avoid forgetting steps or losing context
![Todo System Example](./images/agents/todo-system.png)
## Quick Links
<!--toc:start-->
- [Why Use the Todo System?](#why-use-the-todo-system)
- [How It Works](#how-it-works)
- [Configuration Options](#configuration-options)
- [Available Tools](#available-tools)
- [Auto-Continuation](#auto-continuation)
- [Best Practices](#best-practices)
- [Example Workflow](#example-workflow)
- [Troubleshooting](#troubleshooting)
<!--toc:end-->
## Why Use the Todo System?
Smaller language models often struggle with:
- **Context drift**: Forgetting earlier steps in a multi-step task
- **Incomplete execution**: Stopping before all work is done
- **Lack of structure**: Jumping between tasks without clear organization
The Loki Todo System addresses these issues by giving the model explicit tools to plan, track, and verify task completion.
The system automatically prompts the model to continue when incomplete tasks remain, ensuring work gets finished.
## How It Works
1. **Planning Phase**: The model initializes a todo list with a goal and adds individual tasks
2. **Execution Phase**: The model works through tasks, marking each done immediately after completion
3. **Continuation Phase**: If incomplete tasks remain, the system automatically prompts the model to continue
4. **Completion**: When all tasks are marked done, the workflow ends naturally
The todo state is preserved across the conversation (and any compressions), and injected into continuation prompts,
keeping the model focused on remaining work.
## Configuration Options
The Todo System is configured per-agent in `<loki-config-dir>/agents/<agent-name>/config.yaml`:
| Setting | Type | Default | Description |
|----------------------------|---------|-------------|---------------------------------------------------------------------------------|
| `auto_continue` | boolean | `false` | Enable the To-Do system for automatic continuation when incomplete todos remain |
| `max_auto_continues` | integer | `10` | Maximum number of automatic continuations before stopping |
| `inject_todo_instructions` | boolean | `true` | Inject the default todo tool usage instructions into the agent's system prompt |
| `continuation_prompt` | string | (see below) | Custom prompt used when auto-continuing |
### Example Configuration
```yaml
# agents/my-agent/config.yaml
model: openai:gpt-4o
auto_continue: true # Enable auto-continuation
max_auto_continues: 15 # Allow up to 15 automatic continuations
inject_todo_instructions: true # Include todo instructions in system prompt
continuation_prompt: | # Optional: customize the continuation prompt
[CONTINUE]
You have unfinished tasks. Proceed with the next pending item.
Do not explain; just execute.
```
### Default Continuation Prompt
If `continuation_prompt` is not specified, the following default is used:
```
[SYSTEM REMINDER - TODO CONTINUATION]
You have incomplete tasks in your todo list. Continue with the next pending item.
Call tools immediately. Do not explain what you will do.
```
## Available Tools
When `inject_todo_instructions` is enabled (the default), agents have access to four built-in todo management tools:
### `todo__init`
Initialize a new todo list with a goal. Clears any existing todos.
**Parameters:**
- `goal` (string, required): The overall goal to achieve when all todos are completed
**Example:**
```json
{"goal": "Refactor the authentication module"}
```
### `todo__add`
Add a new todo item to the list.
**Parameters:**
- `task` (string, required): Description of the todo task
**Example:**
```json
{"task": "Extract password validation into separate function"}
```
**Returns:** The assigned task ID
### `todo__done`
Mark a todo item as done by its ID.
**Parameters:**
- `id` (integer, required): The ID of the todo item to mark as done
**Example:**
```json
{"id": 1}
```
### `todo__list`
Display the current todo list with status of each item.
**Parameters:** None
**Returns:** The full todo list with goal, progress, and item statuses
### `todo__clear`
Clear the entire todo list and reset the goal. Use when the current task has been canceled or invalidated.
**Parameters:** None
**Returns:** Confirmation that the todo list was cleared
### REPL Command: `.clear todo`
You can also clear the todo list manually from the REPL by typing `.clear todo`. This is useful when:
- You gave a custom response that changes or cancels the current task
- The agent is stuck in auto-continuation with stale todos
- You want to start fresh without leaving and re-entering the agent
**Note:** This command is only available when an agent with `auto_continue: true` is active. If the todo
system isn't enabled for the current agent, the command will display an error message.
## Auto-Continuation
When `auto_continue` is enabled, Loki automatically sends a continuation prompt if:
1. The agent's response completes (model stops generating)
2. There are incomplete tasks in the todo list
3. The continuation count hasn't exceeded `max_auto_continues`
4. The response isn't identical to the previous continuation (prevents loops)
### What Gets Injected
Each continuation prompt includes:
- The continuation prompt text (default or custom)
- The current todo list state showing:
- The goal
- Progress (e.g., "3/5 completed")
- Each task with status (✓ done, ○ pending)
**Example continuation context:**
```
[SYSTEM REMINDER - TODO CONTINUATION]
You have incomplete tasks in your todo list. Continue with the next pending item.
Call tools immediately. Do not explain what you will do.
Goal: Refactor the authentication module
Progress: 2/4 completed
✓ 1. Extract password validation into separate function
✓ 2. Add unit tests for password validation
○ 3. Update login handler to use new validation
○ 4. Update registration handler to use new validation
```
### Visual Feedback
During auto-continuation, you'll see a message in your terminal:
```
📋 Auto-continuing (3/10): 2 incomplete todo(s) remain
```
## Best Practices
### For Agent Developers
1. **Enable for complex workflows**: Use `auto_continue: true` for agents that handle multistep tasks
2. **Set reasonable limits**: Adjust `max_auto_continues` based on typical task complexity
3. **Customize the prompt**: If your agent needs specific continuation behavior, set a custom `continuation_prompt`
### For Model Behavior
The injected instructions tell models to:
1. **Always create a todo list before starting work**: This ensures planning happens upfront
2. **Mark each task done immediately after finishing**: Don't batch completions
3. **Add all planned steps before starting**: Complete planning before execution
### When to Use vs. Skip
**Use the Todo System when:**
- Tasks have 3+ distinct steps
- The model might lose track of progress
- You want guaranteed completion of all steps
- Working with smaller/less capable models
**Skip the Todo System when:**
- Single-step, simple tasks
- Interactive Q&A sessions
- The overhead of task tracking isn't worth it
## Example Workflow
Here's how a typical todo-driven workflow looks:
**User prompt:** "Add input validation to the user registration form"
**Model actions:**
```
1. todo__init(goal="Add input validation to user registration form")
2. todo__add(task="Analyze current registration form fields")
3. todo__add(task="Create validation rules for email field")
4. todo__add(task="Create validation rules for password field")
5. todo__add(task="Implement client-side validation")
6. todo__add(task="Add server-side validation")
7. todo__add(task="Write tests for validation logic")
```
**Model executes first task, then:**
```
8. todo__done(id=1)
9. [Proceeds with task 2...]
10. todo__done(id=2)
...
```
**If model stops with incomplete tasks:**
- System automatically sends continuation prompt
- Model sees remaining tasks and continues
- Repeats until all tasks are done or max continuations reached
## Troubleshooting
### Model Not Using Todo Tools
- Verify `inject_todo_instructions: true` in your agent config
- Check that the agent is properly loaded (not just a role)
- Some models may need explicit prompting to use the tools
### Too Many Continuations
- Lower `max_auto_continues` to a reasonable limit
- Check if the model is creating new tasks without completing old ones
- Ensure tasks are appropriately scoped (not too granular)
### Continuation Loop
The system detects when a model's response is identical to its previous continuation response and stops
automatically. If you're seeing loops:
- The model may be stuck; check if a task is impossible to complete
- Consider adjusting the `continuation_prompt` to be more directive
---
## Additional Docs
- [Agents](./AGENTS.md) - Full agent configuration guide
- [Function Calling](./function-calling/TOOLS.md) - How tools work in Loki
- [Sessions](./SESSIONS.md) - How conversation state is managed
docs/VAULT.md
+161
View File
@@ -0,0 +1,161 @@
# The Loki Vault
The Loki vault lets users store sensitive secrets and credentials securely so that there's no plaintext secrets
anywhere in your configurations.
It's based on the [G-Man library](https://github.com/Dark-Alex-17/gman) (which also comes in a binary format) which
functions as a universal secret management tool.
![Vault Demo](./images/vault/vault-demo.gif)
## Quick Links
<!--toc:start-->
- [Usage](#usage)
- [CLI Usage](#cli-usage)
- [REPL Usage](#repl-usage)
- [Motivation](#motivation)
- [How it works](#how-it-works)
- [Supported Files](#supported-files)
- [Environment Variable Secret Injection in Agents](#environment-variable-secret-injection-in-agents)
<!--toc:end-->
---
## Usage
The Loki vault can be used in one of two ways: via the CLI or via the REPL for interactive usage.
### CLI Usage
The vault is utilized from the CLI with the following flags:
```bash
--add-secret <SECRET_NAME> Add a secret to the Loki vault
--get-secret <SECRET_NAME> Decrypt a secret from the Loki vault and print the plaintext
--update-secret <SECRET_NAME> Update an existing secret in the Loki vault
--delete-secret <SECRET_NAME> Delete a secret from the Loki vault
--list-secrets List all secrets stored in the Loki vault
```
(The above is also documented in `loki --help`)
Loki will guide you through manipulating your secrets to make usage easier.
### REPL Usage
The vault can be access from within the Loki REPL using the `.vault` commands:
![Loki Vault REPL](./images/vault/vault-repl.png)
![Loki Vault REPL Commands](./images/vault/vault-repl-commands.png)
The manipulation of your vault is guided in the same way as the CLI usage, ensuring ease of use.
## Motivation
Loki is intended to be highly configurable and adaptable to many different use cases. This means that users of Loki
should be able to share configurations for agents, tools, roles, etc. with other users or even entire teams.
My objective is to encourage this, and to make it so that users can easily version their configurations using version
control. Good VCS hygiene dictates that one *never* commits secrets or sensitive information to a repository.
Since a number of files and configurations in Loki may contain sensitive information, the vault exists to solve this problem.
Users can either share the vault password with a team, making it so a single configuration can be pulled from VCS and used
by said team. Alternatively, each user can maintain their own vault password and expect other users to replace secret values
with their user-specific secrets.
## How it works
When you first start Loki, if you don't already have a vault password file, it will prompt you to create one. This file
houses the password that is used to encrypt and decrypt secrets within Loki. This file exists so that you are not prompted
for a password every time Loki attempts to decrypt a secret.
When you encrypt a secret, it uses the local provider for `gman` to securely store those secrets in the Loki vault file.
This file is typically located at your Loki configuration directory under `vault.yml`. If you open this file, you'll see a
bunch of gibberish. This is because all secrets are encrypted using the password you provided, meaning only you can decrypt them.
Secrets are specified in Loki configurations using the same variable templating as the [Jinja templating engine](https://jinja.palletsprojects.com/en/stable/):
```
{{some_variable}}
```
So whenever you want Loki to use a secret from the vault, you simply specify the secret name in this format in the applicable
file.
**Example:**
Suppose my vault has a secret called `GITHUB_TOKEN` in it, and I want to use that in the MCP configuration. Then, I simply replace
the expected value in my `mcp.json` with the templated secret:
```json
{
"mcpServers": {
"atlassian": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://mcp.atlassian.com/v1/sse"]
},
"github": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"GITHUB_PERSONAL_ACCESS_TOKEN",
"ghcr.io/github/github-mcp-server"
],
"env": {
"GITHUB_PERSONAL_ACCESS_TOKEN": "{{GITHUB_TOKEN}}"
}
}
}
}
```
At runtime, Loki will detect the templated secret and replace it with the decrypted value from the vault before executing.
## Supported Files
At the time of writing, the following files support Loki secret injection:
| File Type | Description | Limitations |
|-------------------------|-----------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------|
| `config.yaml` | The main Loki configuration file | Cannot use secret injection on the `vault_password_file` field |
| `functions/mcp.json` | The MCP server configuration file | |
| `<agent>/tools.<py/sh>` | Tool files for agents | Specific configuration and only supported for Agents, not all global tools ([see below](#environment-variable-secret-injection-in-agents)) |
Note that all paths are relative to the Loki configuration directory. The directory varies by system, so you can find yours by
running
```shell
loki --info | grep config_dir | awk '{print $2}'
```
## Environment Variable Secret Injection in Agents
Secrets from the Loki vault can be injected into agent `tools.sh/tools.py` as environment variables. This is done as
follows:
1. Ensure a secret named `MY_USERNAME` is in your Loki vault.
2. Set the name of the secret as the default value for a variable
`<agent>/config.yaml`
```yaml
name: Username
description: An AI agent that demonstrates agent capabilities
instructions: |
You are a AI agent designed to demonstrate agent capabilities.
variables:
- name: username
description: Your user name
# Configure the secret you want to inject using the same templating mentioned above; i.e. wrap the
# case-sensitive name in '{{}}'
default: '{{MY_USERNAME}}'
```
3. Reference the variable in your `<agent>/tools.<py/sh>` file using the familiar variable injection name; that is,
since the name of the variable is `username`, the environment variable that will be provided to the tool call will
be named `LLM_AGENT_VAR_USERNAME`
`tools.sh`
```bash
#!/usr/bin/env bash
# @env LLM_OUTPUT=/dev/stdout The output path
# @cmd Get my username
get_my_username() {
echo "$LLM_AGENT_VAR_USERNAME" >> "$LLM_OUTPUT"
}
```
For more information about variable usage within agents, refer to the [Variables section](./AGENTS.md#user-defined-variables) of the [Agents README](./AGENTS.md)
docs/clients/CLIENTS.md
+185
View File
@@ -0,0 +1,185 @@
# Model Clients
Loki supports a large number of model providers (referred to as `clients` since Loki is a client of these providers). In
order to use them, you must configure each one in the `clients` array in the global Loki configuration file.
The location of the global Loki configuration file varies between systems, so you can use the following command to
locate your configuration file:
```shell
loki --info | grep 'config_file' | awk '{print $2}'
```
## Quick Links
<!--toc:start-->
- [Supported Clients](#supported-clients)
- [Client Configuration](#client-configuration)
- [Authentication](#authentication)
- [Extra Settings](#extra-settings)
<!--toc:end-->
---
## Supported Clients
Loki supports the following model client types:
* Azure AI Foundry
* AWS Bedrock
* Anthropic Claude
* Cohere
* Google Gemini
* OpenAI
* OpenAI-Compatible
* GCP Vertex AI
In addition to the settings detailed below, each client may have additional settings specific to the provider. Check the
[example global configuration file](../../config.example.yaml) to verify that your client has all the necessary fields
defined.
## Client Configuration
Each client in Loki has the same configuration settings available to them, with only special authentication fields added
for specific clients as necessary. They are each placed under the `clients` array in your global configuration file:
```yaml
clients:
- name: client1
# ... client configuration ...
- name: client2
# ... client configuration ...
```
### Metadata
The client metadata uniquely identifies the client in Loki so you can reference it across your configurations. The
available settings are listed below:
| Setting | Description |
|----------|------------------------------------------------------------------------------------------------------------|
| `name` | The name of the client (e.g. `openai`, `gemini`, etc.) |
| `auth` | Authentication method: `oauth` for OAuth, or omit to use `api_key` (see [Authentication](#authentication)) |
| `models` | See the [model settings](#model-settings) documentation below |
| `patch` | See the [client patch configuration](./PATCHES.md#client-configuration-patches) documentation |
| `extra` | See the [extra settings](#extra-settings) documentation below |
Be sure to also check provider-specific configurations for any extra fields that are added for authentication purposes.
### Model Settings
The `models` array lists the available models from the model client. Each one has the following settings:
| Setting | Required | Model Type | Description |
|-----------------------------|----------|-------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| `name` | * | `all` | The name of the model |
| `real_name` | | `all` | You can define model aliases via the `name` field. However, Loki still needs to know the real name <br>of the model so it can query it. For example: If you have `name: gpt-alias`, then you must <br>also define `real_name: gpt-oss:latest` |
| `type` | * | `all` | The type of model. Loki supports only 3 types of models: <ul><li>`chat`</li><li>`embedding`</li><li>`reranker`</li></ul> |
| `input_price` | | `all` | The cost in USD per 1M tokens for each input sequence; Loki will keep track of usage costs if this is defined |
| `output_price` | | `all` | The cost in USD per 1M tokens of the model output; Loki will keep track of usage costs if this is defined |
| `patch` | | `all` | See the [model-specific patch configuration](./PATCHES.md#model-specific-patches) documentation |
| `max_input_tokens` | | `all` | The maximum number of input tokens for the model |
| `max_output_tokens` | | `chat` | The maximum number of output tokens for the model |
| `require_max_tokens` | | `chat` | Whether to enforce the `max_output_tokens` constraint. |
| `supports_vision` | | `chat` | Indicates if the model supports multimodal queries that would require vision (i.e. image recognition) |
| `supports_function_calling` | | `chat` | Indicates if the model supports function calling |
| `no_stream` | | `chat` | Enable or disable streaming API responses |
| `no_system_message` | | `chat` | Controls whether the model supports system messages |
| `system_prompt_prefix` | | `chat` | An additional prefix prompt to add to all system prompts to ensure consistent behavior across all interactions |
| `max_tokens_per_chunk` | | `embedding` | The maximum chunk size supported by the embedding model |
| `default_chunk_size` | | `embedding` | The default chunk size to use with the given model |
| `max_batch_size` | | `embedding` | The maximum batch size that the given embedding model supports |
## Authentication
Loki clients support two authentication methods: **API keys** and **OAuth**. Each client entry in your configuration
must use one or the other.
### API Key Authentication
Most clients authenticate using an API key. Simply set the `api_key` field directly or inject it from the
[Loki vault](../VAULT.md):
```yaml
clients:
- type: claude
api_key: '{{ANTHROPIC_API_KEY}}'
```
API keys can also be provided via environment variables named `{CLIENT_NAME}_API_KEY` (e.g. `OPENAI_API_KEY`,
`GEMINI_API_KEY`). See the [environment variables documentation](../ENVIRONMENT-VARIABLES.md#client-related-variables)
for details.
### OAuth Authentication
For [providers that support OAuth](#providers-that-support-oauth), you can authenticate using your existing subscription instead of an API key. This uses
the OAuth 2.0 PKCE flow.
**Step 1: Configure the client**
Add a client entry with `auth: oauth` and no `api_key`:
```yaml
clients:
- type: claude
name: my-claude-oauth
auth: oauth
```
**Step 2: Authenticate**
Run the `--authenticate` flag with the client name:
```sh
loki --authenticate my-claude-oauth
```
Or if you have only one OAuth-configured client, you can omit the name:
```sh
loki --authenticate
```
Alternatively, you can use the REPL command `.authenticate`.
This opens your browser for the OAuth authorization flow. Depending on the provider, Loki will either start a
temporary localhost server to capture the callback automatically (e.g. Gemini) or ask you to paste the authorization
code back into the terminal (e.g. Claude). Loki stores the tokens in `~/.cache/loki/oauth` and automatically refreshes
them when they expire.
#### Gemini OAuth Note
Loki uses the following scopes for OAuth with Gemini:
* https://www.googleapis.com/auth/generative-language.peruserquota
* https://www.googleapis.com/auth/userinfo.email
* https://www.googleapis.com/auth/generative-language.retriever (Sensitive)
Since the `generative-language.retriever` scope is a sensitive scope, Google needs to verify Loki, which requires full
branding (logo, official website, privacy policy, terms of service, etc.). The Loki app is open-source and is designed
to be used as a simple CLI. As such, there's no terms of service or privacy policy associated with it, and thus Google
cannot verify Loki.
So, when you kick off OAuth with Gemini, you may see a page similar to the following:
![](../images/clients/gemini-oauth-page.png)
Simply click the `Advanced` link and click `Go to Loki (unsafe)` to continue the OAuth flow.
![](../images/clients/gemini-oauth-unverified.png)
![](../images/clients/gemini-oauth-unverified-allow.png)
**Step 3: Use normally**
Once authenticated, the client works like any other. Loki uses the stored OAuth tokens automatically:
```sh
loki -m my-claude-oauth:claude-sonnet-4-20250514 "Hello!"
```
> **Note:** You can have multiple clients for the same provider. For example: you can have one with an API key and
> another with OAuth. Use the `name` field to distinguish them.
### Providers That Support OAuth
* Claude
* Gemini
## Extra Settings
Loki also lets you customize some extra settings for interacting with APIs:
| Setting | Description |
|-------------------|-------------------------------------------------------|
| `proxy` | Set a proxy to use |
| `connect_timeout` | Set the timeout in seconds for connections to the API |
docs/clients/PATCHES.md
+368
View File
@@ -0,0 +1,368 @@
# Request Patching in Loki
Loki provides two mechanisms for modifying API requests sent to LLM providers: **Model-Specific Patches** and
**Client Configuration Patches**. These allow you to customize request parameters, headers, and URLs to work around
provider quirks or add custom behavior.
## Quick Links
- [Model-Specific Patches](#model-specific-patches)
- [Client Configuration Patches](#client-configuration-patches)
- [Comparison](#comparison)
- [Common Use Cases](#common-use-cases)
- [Environment Variable Patches](#environment-variable-patches)
- [Tips](#tips)
- [Debugging Patches](#debugging-patches)
---
## Model-Specific Patches
### Overview
Model-specific patches are applied **unconditionally** to a single model. They are useful for handling model-specific
quirks or requirements.
### When to Use
- A specific model requires certain parameters to be set or removed
- A model needs different default values than other models from the same provider
- You need to add special configuration for one model only
### Structure
```yaml
models:
- name: model-name
type: chat
# ... other model properties ...
patch:
url: "https://custom-endpoint.com" # Optional: override the API endpoint
body: # Optional: modify request body
<parameter>: <value> # Add or modify parameters
<parameter>: null # Remove parameters (set to null)
headers: # Optional: modify request headers
<header-name>: <value> # Add or modify headers
<header-name>: null # Remove headers (set to null)
```
### Examples
#### Example 1: Removing Parameters
OpenAI's o1 models don't support `temperature`, `top_p`, or `max_tokens` parameters. The `patch` removes them:
```yaml
- name: o4-mini
type: chat
max_input_tokens: 200000
max_output_tokens: 100000
supports_function_calling: true
patch:
body:
max_tokens: null # Remove max_tokens from request
temperature: null # Remove temperature from request
top_p: null # Remove top_p from request
```
#### Example 2: Setting Required Parameters
Some models require specific parameters to be set:
```yaml
- name: o4-mini-high
type: chat
patch:
body:
reasoning_effort: high # Always set reasoning_effort to "high"
max_tokens: null
temperature: null
```
#### Example 3: Custom Endpoint
If a model needs a different API endpoint:
```yaml
- name: custom-model
type: chat
patch:
url: "https://special-endpoint.example.com/v1/chat"
```
#### Example 4: Adding Headers
Add authentication or custom headers:
```yaml
- name: special-model
type: chat
patch:
headers:
X-Custom-Header: "special-value"
X-API-Version: "2024-01"
```
### How It Works
1. When you use a model, Loki loads its configuration
2. If the model has a `patch` field, it's **always applied** to every request
3. The patch modifies the request URL, body, or headers before sending to the API
4. Parameters set to `null` are **removed** from the request
---
## Client Configuration Patches
### Overview
Client configuration patches allow you to apply customizations to **multiple models** based on
**regex pattern matching**. They're defined in your `config.yaml` file and can target specific API types (`chat`,
`embeddings`, or `rerank`).
### When to Use
- You want to apply the same settings to multiple models from a provider
- You need different configurations for different groups of models
- You want to override the default client model settings
- You need environment-specific customizations
### Structure
```yaml
clients:
- type: <client> # e.g., gemini, openai, claude
# ... client configuration ...
patch:
chat_completions: # For chat models
'<regex-pattern>': # Regex to match model names
url: "..." # Optional: override endpoint
body: # Optional: modify request body
<parameter>: <value>
headers: # Optional: modify headers
<header>: <value>
embeddings: # For embedding models
'<regex-pattern>':
# ... same structure ...
rerank: # For reranker models
'<regex-pattern>':
# ... same structure ...
```
### Pattern Matching
- Patterns are **regular expressions** that match against the model name
- Use `.*` to match all models
- Use specific patterns like `gpt-4.*` to match model families
- Use `model1|model2` to match multiple specific models
### Examples
#### Example 1: Disable Safety Filters for Gemini Models
Apply to all Gemini chat models:
```yaml
clients:
- type: gemini
api_key: "{{GEMINI_API_KEY}}"
patch:
chat_completions:
'.*': # Matches all Gemini models
body:
safetySettings:
- category: HARM_CATEGORY_HARASSMENT
threshold: BLOCK_NONE
- category: HARM_CATEGORY_HATE_SPEECH
threshold: BLOCK_NONE
- category: HARM_CATEGORY_SEXUALLY_EXPLICIT
threshold: BLOCK_NONE
- category: HARM_CATEGORY_DANGEROUS_CONTENT
threshold: BLOCK_NONE
```
#### Example 2: Apply Settings to Specific Model Family
Only apply to GPT-4 models (not GPT-3.5):
```yaml
clients:
- type: openai
api_key: "{{OPENAI_API_KEY}}"
patch:
chat_completions:
'gpt-4.*': # Matches gpt-4, gpt-4-turbo, gpt-4o, etc.
body:
frequency_penalty: 0.2
presence_penalty: 0.1
```
#### Example 3: Different Settings for Different Models
Apply different patches based on model name:
```yaml
clients:
- type: openai
api_key: "{{OPENAI_API_KEY}}"
patch:
chat_completions:
'gpt-4o': # Specific model
body:
temperature: 0.7
'gpt-3.5.*': # Model family
body:
temperature: 0.9
max_tokens: 2000
```
#### Example 4: Modify Embedding Requests
Apply to embedding models:
```yaml
clients:
- type: openai
api_key: "{{OPENAI_API_KEY}}"
patch:
embeddings:
'text-embedding-.*': # All text-embedding models
body:
dimensions: 1536
encoding_format: "float"
```
#### Example 5: Custom Headers for Specific Models
Add headers only for certain models:
```yaml
clients:
- type: openai-compatible
api_base: "https://api.example.com/v1"
patch:
chat_completions:
'custom-model-.*':
headers:
X-Custom-Auth: "bearer-token"
X-Model-Version: "latest"
```
#### Example 6: Override Endpoint for Specific Models
Use different endpoints for different model groups:
```yaml
clients:
- type: openai-compatible
api_base: "https://default-endpoint.com/v1"
patch:
chat_completions:
'premium-.*': # Premium models use different endpoint
url: "https://premium-endpoint.com/v1/chat/completions"
```
### How It Works
1. When making a request, Loki checks if the client has a `patch` configuration
2. It looks at the appropriate API type (`chat_completions`, `embeddings`, or `rerank`)
3. For each pattern in that section, it checks if the regex matches the model name
4. If a match is found, that patch is applied to the request
5. Only the **first matching pattern** is applied (patterns are processed in order)
---
## Comparison
| Feature | Model-Specific Patch | Client Configuration Patch |
|-----------------------|-----------------------|-------------------------------------|
| **Scope** | Single model only | Multiple models via regex |
| **Matching** | Exact model name | Regular expression pattern |
| **Application** | Always applied | Only if pattern matches |
| **API Type** | All APIs | Separate for chat/embeddings/rerank |
| **Override** | Cannot be overridden | Can override model patch |
| **Use Case** | Model-specific quirks | User preferences & customization |
| **Application Order** | Applied first | Applied second (can override) |
### Patch Application Order
When both patches are present, they're applied in this order:
1. **Model-Specific Patch**
2. **Client Configuration Patch**
This means client configuration patches can override model-specific patches if they modify the same parameters.
## Common Use Cases
### Removing Unsupported Parameters
Some models don't support standard parameters like `temperature` or `max_tokens`:
**Model Patch**:
```yaml
patch:
body:
temperature: null
max_tokens: null
```
### Adding Provider-Specific Parameters
Providers often have unique parameters:
**Client Patch**:
```yaml
patch:
chat_completions:
'.*':
body:
safetySettings: [...] # Gemini
thinking_budget: 10000 # DeepSeek
response_format: # OpenAI
type: json_object
```
### Changing Endpoints
Use custom or regional endpoints:
**Client Patch**:
```yaml
patch:
chat_completions:
'.*':
url: "https://eu-endpoint.example.com/v1/chat"
```
### Setting Default Values
Provide defaults for specific models or model families:
**Client Patch**:
```yaml
patch:
chat_completions:
'claude-3-.*':
body:
max_tokens: 4096
temperature: 0.7
```
### Custom Authentication
Add special authentication headers:
**Client Patch**:
```yaml
patch:
chat_completions:
'.*':
headers:
Authorization: "Bearer {{custom_token}}"
X-Organization-ID: "org-123"
```
## Environment Variable Patches
You can also apply patches via environment variables for temporary overrides:
```bash
export LLM_PATCH_OPENAI_CHAT_COMPLETIONS='{"gpt-4.*":{"body":{"temperature":0.5}}}'
```
This takes precedence over client configuration patches but not model-specific patches.
## Tips
1. **Use model patches** for permanent, model-specific requirements
2. **Use client patches** for personal preferences or environment-specific settings
3. **Test regex patterns** carefully
4. **Set to `null`** to remove parameters, don't just omit them
5. **Check each model provider's docs** for available parameters and their formats
6. **Be specific** with patterns to avoid unintended matches
7. **Remember order matters** - first matching pattern wins for client patches
8. **Patches merge** - both types can be applied, with client patches overriding model patches
## Debugging Patches
To see what request is actually being sent, enable debug logging:
```bash
export RUST_LOG=loki=debug
loki "your prompt here"
```
This will show the final request body after all patches are applied.
docs/function-calling/BASH-PROMPT-HELPERS.md
+279
View File
@@ -0,0 +1,279 @@
# Bash Prompt Helpers
When creating bash based tools, it's often helpful to prompt the user for input or confirmation.
Loki comes pre-packaged with a handful of prompt helpers for your bash-based tools. These helpers
can be used to prompt the user for various types of input, such as yes/no confirmations,
text input, and selections from a list.
The utility script is located at `functions/utils/prompt-utils.sh` within your Loki `functions` directory.
The Loki `functions` directory varies between machines, so you can find its location on your system by running the following command in your terminal:
```shell
loki --info | grep functions_dir | awk '{print $2}'
```
## Quick Links
<!--toc:start-->
- [Import The Prompt Utils Into Your Tools Script](#import-the-prompt-utils-into-your-tools-script)
- [Included Utility Functions](#included-utility-functions)
- [input](#input)
- [confirm](#confirm)
- [list](#list)
- [checkbox](#checkbox)
- [password](#password)
- [editor](#editor)
- [with_validate](#with_validate)
- [validate_present](#validate_present)
- [detect_os](#detect_os)
- [get_opener](#get_opener)
- [open_link](#open_link)
- [guard_operation](#guard_operation)
- [guard_path](#guard_path)
- [patch_file](#patch_file)
- [error](#error)
- [warn](#warn)
- [info](#info)
- [debug](#debug)
- [trace](#trace)
- [Colored Output](#colored-output)
<!--toc:end-->
---
## Import The Prompt Utils Into Your Tools Script
In order to use the bash prompt helpers in your bash scripts, you need to source the provided `prompt-utils.sh` script.
This script is pre-packaged with Loki and is located [here](../../assets/functions/utils/prompt-utils.sh).
When sourcing the file in your bash script, you use the `LLM_PROMPT_UTILS_FILE` environment variable that automatically
populates the `functions/utils/prompt-utils.sh` path for you.
Thus, to properly source and enable all the bash prompt helpers in your Bash tools, add the following prelude to your
scripts:
```bash
source "$LLM_PROMPT_UTILS_FILE"
```
## Included Utility Functions
Below are the built-in bash prompt helpers that can be used to enhance user interaction with your tool scripts.
### input
Prompt for text input
![Prompt Utils Input](../images/tools/prompt-utils-input.png)
**Example With Validation:**
```bash
text=$(with_validation 'input "Please enter something:"' validate_present 2>/dev/tty)
```
**Example Without Validation:**
```bash
text=$(input "Please enter something:" 2>/dev/tty)
```
### confirm
Show a confirm dialog with options for yes/no
![Prompt Utils Confirm](../images/tools/prompt-utils-confirm.png)
**Example:**
```bash
confirmed=$(confirm "Do the thing?" 2>/dev/tty)
if [[ $confirmed == "0" ]]; then echo "No"; else echo "Yes"; fi
```
### list
Renders a text based list of options that can be selected by the user using up, down, and enter
keys that then returns the chosen option.
![Prompt Utils List](../images/tools/prompt-utils-list.png)
**Example:**
```bash
options=("one" "two" "three" "four")
choice=$(list "Select an item" "${options[@]}" 2>/dev/tty)
echo "Your choice: ${options[$choice]}"
```
### checkbox
Render a text based list of options, where multiple options can be selected by the user using down, up,
and enter keys that then returns the chosen options.
![Prompt Utils Checkbox](../images/tools/prompt-utils-checkbox.png)
**Example:**
```bash
options=("one" "two" "three" "four")
checked=$(checkbox "Select one or more items" "${options[@]}" 2>/dev/tty)
echo "Your choices: ${checked}"
```
### password
Show a password prompt displaying stars for each character typed.
![Prompt Utils Password](../images/tools/prompt-utils-password.png)
**Example With Validation:**
```bash
validate_password() {
if [[ ${#1} -lt 10 ]]; then
echo "Password must be at least 10 characters"
exit 1
fi
}
pass=$(with_validate 'password "Enter your password"' validate_password 2>/dev/tty)
```
**Example Without Validation:**
```bash
pass="$(password "Enter your password:" 2>/dev/tty)"
```
### editor
Open the default editor (`$EDITOR`); if none is set, default back to `vi`
**Example:**
```bash
text=$(editor "Please enter something in the editor" 2>/dev/tty)
echo -e "You wrote:\n${text}"
```
### with_validate
Evaluate the given prompt command with validation. This prompts the user for input until the
validation functions returns 0.
![Prompt Utils With-validate](../images/tools/prompt-utils-with-validate.png)
**Example:**
```bash
# Using the built-in 'validate_present' validator
text=$(with_validate 'input "Please enter something and confirm with enter"' validate_present 2>/dev/tty)
# Using a custom validator; e.g. for password
validate_password() {
if [[ ${#1} -lt 10 ]]; then
echo "Password needs to be at least 10 characters"
exit 1
fi
}
pass=$(with_validate 'password "Enter random password"' validate_password 2>/dev/tty)
```
### validate_present
Validate that the prompt returned a value.
![Prompt Utils Validate-Present](../images/tools/prompt-utils-validate-present.png)
**Example:**
```bash
text=$(with_validate 'input "Please enter something and confirm with enter"' validate_present 2>/dev/tty)
```
### detect_os
Detect the current OS.
Returns one of the following:
* `solaris`
* `macos`
* `linux`
* `bsd`
* `windows`
* `unknown`
**Example:**
```bash
detect_os
```
### get_opener
Determines the Os-specific file opening command (i.e. the command to open anything)
**Example:**
```bash
# Returns 'xdg-open'
get_opener
```
### open_link
Opens the given link in the default browser
**Example:**
```bash
open_link https://www.google.com
```
### guard_operation
Prompt for permission to run an operation.
Can be disabled by setting the environment variable `AUTO_CONFIRM`.
**Example:**
```bash
guard_operation "Execute SQL?"
_run_sql
```
### guard_path
Prompt for permission to perform path operations.
Can be disabled by setting the environment variable `AUTO_CONFIRM`.
**Example:***
```bash
guard_path "$target_path" "Remove '$target_path'?"
rm -rf "$target_path"
```
### patch_file
Patch a file and show a diff using the default diff viewer. Uses git diff syntax.
**Example:**
```bash
new_contents="$(patch_file "$path" file.patch)"
```
### error
Log an error
![Prompt Utils Error](../images/tools/prompt-utils-error.png)
### warn
Log a warning
![Prompt Utils Warning](../images/tools/prompt-utils-warning.png)
### info
Log info
![Prompt Utils Info](../images/tools/prompt-utils-info.png)
### debug
Log a debug message
![Prompt Utils Debug](../images/tools/prompt-utils-debug.png)
### trace
Log a trace message
![Prompt Utils Trace](../images/tools/prompt-utils-trace.png)
### Colored Output
The following commands allow users to output text in specific colors.
* `red`
* `green`
* `gold`
* `blue`
* `magenta`
* `cyan`
* `white`
**Example:**
```bash
red "This will be red"
yellow "This will be yellow"
```
docs/function-calling/CUSTOM-BASH-TOOLS.md
+309
View File
@@ -0,0 +1,309 @@
# Custom Bash-Based Tools
Loki supports tools written in Bash. However, they must be written in a special format with special annotations in order
for Loki to be able to properly parse and utilize them. This formatting ensures that each Bash script is
self-describing, and formatted in such a way that Loki can anticipate how to execute it and what parameters to pass to
it. This standardization also lets Loki compile the script into a JSON schema that can be used to inform the LLM about
how to use the tool.
Each Bash-based tool must follow a specific structure in order for Loki to be able to properly compile and execute it:
* The tool must be a Bash script with a `.sh` file extension.
* The script must have the following comments:
* `# @describe ...` comment at the top that describes the tool.
* `# @env LLM_OUTPUT=/dev/stdout The output path` comment to describe the `LLM_OUTPUT` environment variable. This
syntax in particular assigns `/dev/stdout` as the default value for `LLM_OUTPUT`, so that if it's not set by Loki,
the script will still function properly.
* `# @option --option <value> An example option` comments to define each option that the tool accepts.
* Use `--flag` syntax for boolean flags.
* Use `--option <value>` syntax for options that accept a value.
* Use `--option <value1,value2>` syntax for options that accept multiple values (i.e. arrays).
* The script must have a `main` function
* The `main` function must redirect the return value to the `>> "$LLM_OUTPUT"` environment variable.
* This is necessary because Loki relies on the `$LLM_OUTPUT` environment variable to capture the output of the tool.
Essentially, you can think of the Bash-based tool script as just a normal Bash script that uses special comments to
define a CLI.
* The `# @env LLM_OUTPUT=/dev/stdout` comment to define the `$LLM_OUTPUT` environment variable (good practice)
* A `# @describe`
* And a `main` function that writes to `$LLM_OUTPUT`
The following section explains how you can add parameters to your bash functions and how to test out your scripts.
## Quick Links:
<!--toc:start-->
- [Loki Bash Tools Syntax](#loki-bash-tools-syntax)
- [Metadata](#metadata)
- [Environment Variables](#environment-variables)
- [Arguments](#arguments)
- [Flags](#flags)
- [Options](#options)
- [Subcommands (Agents only)](#subcommands-agents-only)
- [Execute and Test Your Bash Tools](#execute-and-test-your-bash-tools)
- [Example](#example)
- [Prompt Helpers](#prompt-helpers)
<!--toc:end-->
---
## Loki Bash Tools Syntax
Loki Bash tools work via `@___` annotations that describe specific functionality of a script. The following reference
explains the general syntax of these annotations and how to use them to create a CLI that Loki can recognize.
Refer to the [Execute and Test Your Bash Tools](#execute-and-test-your-bash-tools) section to learn how to test out your Bash tools
without needing to go through Loki itself.
It's important to note that any functions prefixed with `_` are not sent to the LLM, so they will be invisible to the
LLM at runtime.
### Metadata:
You can define different metadata about your script to help Loki understand its dependencies and purpose.
```bash
# Use the `@meta require-tools` annotation to specify any external tools that your script depends on.
# @meta require-tools jq,yq
# Use the `@describe` annotation to describe the purpose of the script.
# @describe A tool to interact with things
```
### Environment Variables:
```bash
###########################
## Environment Variables ##
###########################
# Use `@env` to define environment variables that the script uses.
# @env LLM_OUTPUT=/dev/stdout The output path, with a default value of '/dev/stdout' if not set.
# @env OPTIONAL An optional environment variable
# @env REQUIRED! A required environment variable
# @env DEFAULT_VALUE=default An environment variable with a default value if unset.
# @env DEFAULT_FROM_FN=`_default_env_fn` An environment variable with a default value calculated from a function if unset.
# @env CHOICE[even|odd] An environment variable that, if set, must be set to either `even` or `odd`
# @env CHOICE_WITH_DEFAULT[=even|odd] An environment variable that, if set, must be set to either `even` or `odd`, and defaults to `even` when unset
# @env CHOICE_FROM_FN[`_choice_env_fn`] An environment variable that, if set, must be set to one of the values returned by the `_choice_fn` function.
# Example variable usage:
export CHOICE=even
# ./script.sh
main() {
[[ $CHOICE == "even" ]] || { echo "The value of the 'CHOICE' env var is not 'even'" >> "$LLM_OUTPUT" && exit 1 }
}
# Loki does not pass functions prefixed with `_` to the LLM, so these are essentially `private` functions
_default_env_fn() {
echo "calculated default env value"
}
# Loki does not pass functions prefixed with `_` to the LLM, so these are essentially `private` functions
_choice_env_fn() {
echo even
echo odd
}
```
### Arguments:
When referencing an argument defined via the `@arg` annotation, you can access its value using the `argc_<argument_name>` variable that
is created at runtime.
```bash
###############
## Arguments ##
###############
# Use `@arg` To define positional arguments for your script.
# To reference an argument within your script, use the `argc_<argument_name>` variable.
# @arg optional Optional argument
# @arg required! Required argument
# @arg multi_value* An argument that accepts multiple values (e.g. './script.sh one two three')
# @arg multi_value_required+ An argument that is required and accepts multiple values
# @arg value_notated <VALUE> An argument that explicitly specifies the name for documentation (e.g. Usage: ./script.sh [VALUE])
# @arg default=default An argument with a default value if unset
# @arg default_from_fn=`_default_arg_fn` An argument with a default value calculated from a function if unset
# @arg choice[even|odd] An argument that, if set, must be set to either `even` or `odd`
# @arg required_choice+[even|odd] An required argument that must be set to either `even` or `odd`
# @arg default_choice[=even|odd] An argument that if unset defaults to 'even', but if set must be either `even` or `odd`
# @arg multi_value_choice*[even|odd] An argument that, if set, must be set to either `even` or `odd`, and accepts multiple values
# @arg choice_fn[`_choice_arg_fn`] An argument that, if set, must be set to one of the values returned by the `_choice_arg_fn` function.
# @arg choice_fn_no_valid[?`_choice_arg_fn`] An argument that, if set, can be set to one of the values returned by the `_choice_arg_fn` function,
# but does not validate the value.
# @arg multi_choice_fn*[`_choice_arg_fn`] An argument that, if set, must be set to one of the values returned by the `_choice_arg_fn` function,
# and accepts multiple values.
# @arg multi_choice_comma_fn*,[`_choice_arg_fn`] An argument that, if set, must be set to one of the values returned by the `_choice_arg_fn` function,
# and accepts multiple values in the form of a comma-separated list
# @arg capture_arg~ An argument that captures all remaining args passed to the script
# Example usage 1: ./script.sh something_required
main() {
[[ $argc_required == "something_required" ]] || { echo "The value of the 'required' arg is not 'something_required'" >> "$LLM_OUTPUT" && exit 1 }
}
# Example usage 2: ./script.sh this is a test
main() {
[[ "${argc_multi_value[*]}" == "this is a test" ]] || { echo "The value of the 'multi_value' arg is not 'this is a test'" >> "$LLM_OUTPUT" && exit 1 }
}
# Loki does not pass functions prefixed with `_` to the LLM, so these are essentially `private` functions
_default_arg_fn() {
echo "default arg value"
}
# Loki does not pass functions prefixed with `_` to the LLM, so these are essentially `private` functions
_choice_arg_fn() {
echo even
echo odd
}
```
### Flags:
To access the value of a flag defined via the `@flag` annotation, you can check the value of the `argc_<flag_name>` variable.
```bash
###########
## Flags ##
###########
# Use `@flag` to define boolean flags for your script
# To reference a flag within your script, use the `argc_<argument_name>` variable.
# @flag --bool A boolean flag with only a long option
# @flag -b --bool A boolean flag with a short and long option
# @flag -b A boolean flag with only a short option
# @flag --multi* A boolean flag that can be used multiple times (e.g. '--multi --multi' will return '2')
# Example usage 1: ./script.sh --bool
main() {
[[ $argc_bool == "1" ]] || { echo "The value of the 'bool' flag is not '1'" >> "$LLM_OUTPUT" && exit 1 }
}
# Example usage 2: ./script.sh --multi --multi
main() {
[[ $argc_multi == "2" ]] || { echo "The value of the 'multi' flag is not 2" >> "$LLM_OUTPUT" && exit 1 }
}
```
### Options:
To access the value of an option defined via the `@option` annotation, you can check the value of the `argc_<option_name>` variable.
```bash
#############
## Options ##
#############
# Use `@option` to define flags that accept values
# To reference an option within your script, use the `argc_<argument_name>` variable.
# @option --option An option that accepts a value with only a long flag
# @option -o --option An option that accepts a value with both a short and long flag
# @option -o An option that accepts a value with only a short flag
# @option --required A required option that accepts a value
# @option --multi* An option that accepts multiple values
# @option --required-multi+ An option that accepts multiple values and is required
# @option --multi-comma*, An option that accepts multiple values in the form of a comma-separated list
# @option --value <VALUE> An option that explicitly specifies the name for documentation (e.g. Usage: ./script.sh --value [VALUE])
# @option --two-args <SRC> <DEST> An option that accepts two arguments and explicitly names them for documentation
# (e.g. Usage: ./script.sh --two-args [SRC] [DEST])
# @option --unlimited-args <SRC> <DEST+> An option that accepts an unlimited number of arguments and explicitly names them for documentation
# (e.g. Usage: ./script.sh --unlimited-args [SRC] [DEST ...])
# @option --default=default An option that has a default value if unset
# @option --default-from-fn=`_default_opt_fn` An option that has a default value calculated from a function if unset
# @option --choice[even|odd] An option that, if set, must be set to either `even` or `odd`
# @option --choice-default[=even|odd] An option that, if unset, defaults to `even`, but if set must be either `even` or `odd`
# @option --choice-multi*[even|odd] An option that, if set, must be set to either `even` or `odd`, and can be specified multiple times
# (e.g. ./script.sh --choice-multi even --choice-multi odd)
# @option --required-choice-multi+[even|odd] A required option that, must be set to either `even` or `odd`, and can be specified multiple times
# @option --choice-fn[`_choice_opt_fn`] An option that, if set, must be set to one of the values returned by the `_choice_opt_fn` function.`
# @option --choice-fn-no-valid[?`_choice_opt_fn`] An option that, if set, can be set to one of the values returned by the `_choice_opt_fn` function, with no validation
# @option --choice-multi-fn*[`_choice_opt_fn`] An option that, if set, must be set to one of the values returned by the `_choice_opt_fn` function,
# and can be specified multiple times
# @option --choice-multi-comma*,[`_choice_opt_fn`] An option that, if set, must be set to one of the values returned by the `_choice_opt_fn` function,
# and is specified as a comma-separated list
# @option --capture~ An option that captures all remaining arguments passed to the script
# Example usage 1: ./script.sh --option some_value
main() {
[[ $argc_option == "some_value" ]] || { echo "The value of the 'option' option is not 'some_value'" >> "$LLM_OUTPUT" && exit 1 }
}
# Example usage 2: ./script.sh --multi value1 --multi value2
main() {
[[ "${argc_multi[*]}" == "value1 value2" ]] || { echo "The value of the 'multi' option is not 'value1 value2'" >> "$LLM_OUTPUT" && exit 1 }
}
# Loki does not pass functions prefixed with `_` to the LLM, so these are essentially `private` functions
_default_opt_fn() {
echo "calculated default option value"
}
# Loki does not pass functions prefixed with `_` to the LLM, so these are essentially `private` functions
_choice_opt_fn() {
echo even
echo odd
}
```
### Subcommands (Agents only):
By default, if no `@cmd` annotations are defined, the script's `main` function is treated as the default command.
However, for agents, there can be many functions defined in one file, and thus it is useful to create subcommands
to organize your agent's tools.
```bash
#################
## Subcommands ##
#################
# Use the `@cmd` annotation to define subcommands for your script.
# @cmd List all files
list() {
ls -la >> "$LLM_OUTPUT"
}
# @cmd Output the contents of the specified file
# @arg file! The file to output
cat() {
cat "$argc_file" >> "$LLM_OUTPUT"
}
# Example usage 1: ./script.sh cat myfile.txt
```
## Execute and Test Your Bash Tools
Your bash tools are just normal bash scripts stored in the `functions/tools` directory. So you can execute and test them
directly by first having Loki compile them so all this syntactic sugar means something.
This is achieved via the `loki --build-tools` command.
### Example
Suppose we want to execute the `functions/tools/get_current_time.sh` script for testing.
We'd first make sure the script is visible in all contexts by ensuring it's in the `visible_tools` array in your global
`config.yaml` file. This ensures Loki builds the tool so it's ready to use in any context.
You can find the location of your global `config.yaml` file with the following command:
```shell
loki --info | grep 'config_file' | awk '{print $2}'
```
Then, we can instruct Loki to build the script so we can test it out:
```shell
loki --build-tools
```
This will add additional boilerplate to the top of the script so that it can be executed directly.
Finally, we can now execute the script:
```bash
$ ./get_current_time.sh
Fri Oct 24 05:55:04 PM MDT 2025
```
## Prompt Helpers
It's often useful to create interactive prompts for our bash tools so that our tools can get input from
users.
To accommodate this, Loki provides a set of prompt helper functions that can be referenced and used within your Bash
tools.
For more information, refer to the [Bash Prompt Helpers documentation](BASH-PROMPT-HELPERS.md).
docs/function-calling/CUSTOM-TOOLS.md
+282
View File
@@ -0,0 +1,282 @@
# Custom Tools
Loki is designed to be as flexible and as customizable as possible. One of the key
features that enables this flexibility is the ability to create and integrate custom tools
into your Loki setup. This document provides a guide on how to create and use custom tools within Loki.
## Quick Links
<!--toc:start-->
- [Supported Languages](#supported-languages)
- [Creating a Custom Tool](#creating-a-custom-tool)
- [Environment Variables](#environment-variables)
- [Custom Bash-Based Tools](#custom-bash-based-tools)
- [Custom Python-Based Tools](#custom-python-based-tools)
- [Custom TypeScript-Based Tools](#custom-typescript-based-tools)
- [Custom Runtime](#custom-runtime)
<!--toc:end-->
---
## Supported Languages
Loki supports custom tools written in the following programming languages:
* Python
* Bash
* TypeScript
## Creating a Custom Tool
All tools are created as scripts in either Python, Bash, or TypeScript. They should be placed in the `functions/tools` directory.
The location of the `functions` directory varies between systems, so you can use the following command to locate
your `functions` directory:
```shell
loki --info | grep functions_dir | awk '{print $2}'
```
Once you've created your custom tool, remember to add it to the `visible_tools` array in your global `config.yaml` file
to enable it globally. See the [Tools](TOOLS.md#enablingdisabling-global-tools) documentation for more information on how Loki utilizes the
`visible_tools` array.
### Environment Variables
All tools have access to the following environment variables that provide context about the current execution environment:
| Variable | Description |
|----------------------|--------------------------------------------------------------------------------------------------------------------------------------------|
| `LLM_OUTPUT` | Indicates where the output of the tool should go. <br>In certain situations, this may be set to a temporary file instead of `/dev/stdout`. |
| `LLM_ROOT_DIR` | The root `config_dir` directory for Loki <br>(i.e. `dirname $(loki --info \| grep config_file \| awk '{print $2}')`) |
| `LLM_TOOL_NAME` | The name of the tool being executed |
| `LLM_TOOL_CACHE_DIR` | A directory specific to the tool for storing cache or temporary files |
Loki also searches the tools directory on startup for a `.env` file. If found, all tools in `functions/tools/` will have
the environment variables defined in the `.env` file available to them.
### Custom Bash-Based Tools
To create a Bash-based tool, refer to the [custom bash tools documentation](CUSTOM-BASH-TOOLS.md).
### Custom Python-Based Tools
Loki supports tools written in Python.
Each Python-based tool must follow a specific structure in order for Loki to be able to properly compile and
execute it:
* The tool must be a Python script with a `.py` file extension.
* The tool must have a `def run` function that serves as the entry point for the tool.
* The `run` function must accept parameters that define the inputs for the tool.
* Always use type hints to specify the data type of each parameter.
* Use `Optional[...]` to indicate optional parameters
* The `run` function must return a `str`.
* For Python, this is automatically written to the `LLM_OUTPUT` environment variable, so there's no need to explicitly
write to the environment variable within the function.
* The function must also have a docstring that describes the tool and its parameters.
* Each parameter in the `run` function should be documented in the docstring using the `Args:` section. They should use the following format:
* `<parameter_name>: <description>` Where
* `<parameter_name>`: The name of the parameter
* `<description>`: The description of the parameter
* These are *very* important because these descriptions are what's passed to the LLM as the description of the tool,
letting the LLM know what the tool does and how to use it.
It's important to note that any functions prefixed with `_` are not sent to the LLM, so they will be invisible to the LLM
at runtime.
Below is the [`demo_py.py`](../../assets/functions/tools/demo_py.py) tool definition that comes pre-packaged with
Loki and demonstrates how to create a Python-based tool:
```python
import os
from typing import List, Literal, Optional
def run(
string: str,
string_enum: Literal["foo", "bar"],
boolean: bool,
integer: int,
number: float,
array: List[str],
string_optional: Optional[str] = None,
integer_with_default: int = 42,
boolean_with_default: bool = True,
number_with_default: float = 3.14,
string_with_default: str = "hello",
array_optional: Optional[List[str]] = None,
):
"""Demonstrates all supported Python parameter types and variations.
Args:
string: A required string property
string_enum: A required string property constrained to specific values
boolean: A required boolean property
integer: A required integer property
number: A required number (float) property
array: A required string array property
string_optional: An optional string property (Optional[str] with None default)
integer_with_default: An optional integer with a non-None default value
boolean_with_default: An optional boolean with a default value
number_with_default: An optional number with a default value
string_with_default: An optional string with a default value
array_optional: An optional string array property
"""
output = f"""string: {string}
string_enum: {string_enum}
boolean: {boolean}
integer: {integer}
number: {number}
array: {array}
string_optional: {string_optional}
integer_with_default: {integer_with_default}
boolean_with_default: {boolean_with_default}
number_with_default: {number_with_default}
string_with_default: {string_with_default}
array_optional: {array_optional}"""
for key, value in os.environ.items():
if key.startswith("LLM_"):
output = f"{output}\n{key}: {value}"
return output
```
### Custom TypeScript-Based Tools
Loki supports tools written in TypeScript. TypeScript tools require [Node.js](https://nodejs.org/) and
[tsx](https://tsx.is/) (`npx tsx` is used as the default runtime).
Each TypeScript-based tool must follow a specific structure in order for Loki to properly compile and execute it:
* The tool must be a TypeScript file with a `.ts` file extension.
* The tool must have an `export function run(...)` that serves as the entry point for the tool.
* Non-exported functions are ignored by the compiler and can be used as private helpers.
* The `run` function must accept flat parameters that define the inputs for the tool.
* Always use type annotations to specify the data type of each parameter.
* Use `param?: type` or `type | null` to indicate optional parameters.
* Use `param: type = value` for parameters with default values.
* The `run` function must return a `string` (or `Promise<string>` for async functions).
* For TypeScript, the return value is automatically written to the `LLM_OUTPUT` environment variable, so there's
no need to explicitly write to the environment variable within the function.
* The function must have a JSDoc comment that describes the tool and its parameters.
* Each parameter should be documented using `@param name - description` tags.
* These descriptions are passed to the LLM as the tool description, letting the LLM know what the tool does and
how to use it.
* Async functions (`export async function run(...)`) are fully supported and handled transparently.
**Supported Parameter Types:**
| TypeScript Type | JSON Schema | Notes |
|-------------------|--------------------------------------------------|-----------------------------|
| `string` | `{"type": "string"}` | Required string |
| `number` | `{"type": "number"}` | Required number |
| `boolean` | `{"type": "boolean"}` | Required boolean |
| `string[]` | `{"type": "array", "items": {"type": "string"}}` | Array (bracket syntax) |
| `Array<string>` | `{"type": "array", "items": {"type": "string"}}` | Array (generic syntax) |
| `"foo" \| "bar"` | `{"type": "string", "enum": ["foo", "bar"]}` | String enum (literal union) |
| `param?: string` | `{"type": "string"}` (not required) | Optional via question mark |
| `string \| null` | `{"type": "string"}` (not required) | Optional via null union |
| `param = "value"` | `{"type": "string"}` (not required) | Optional via default value |
**Unsupported Patterns (will produce a compile error):**
* Rest parameters (`...args: string[]`)
* Destructured object parameters (`{ a, b }: { a: string, b: string }`)
* Arrow functions (`const run = (x: string) => ...`)
* Function expressions (`const run = function(x: string) { ... }`)
Only `export function` declarations are recognized. Non-exported functions are invisible to the compiler.
Below is the [`demo_ts.ts`](../../assets/functions/tools/demo_ts.ts) tool definition that comes pre-packaged with
Loki and demonstrates how to create a TypeScript-based tool:
```typescript
/**
* Demonstrates all supported TypeScript parameter types and variations.
*
* @param string - A required string property
* @param string_enum - A required string property constrained to specific values
* @param boolean - A required boolean property
* @param number - A required number property
* @param array_bracket - A required string array using bracket syntax
* @param array_generic - A required string array using generic syntax
* @param string_optional - An optional string using the question mark syntax
* @param string_nullable - An optional string using the union-with-null syntax
* @param number_with_default - An optional number with a default value
* @param boolean_with_default - An optional boolean with a default value
* @param string_with_default - An optional string with a default value
* @param array_optional - An optional string array using the question mark syntax
*/
export function run(
string: string,
string_enum: "foo" | "bar",
boolean: boolean,
number: number,
array_bracket: string[],
array_generic: Array<string>,
string_optional?: string,
string_nullable: string | null = null,
number_with_default: number = 42,
boolean_with_default: boolean = true,
string_with_default: string = "hello",
array_optional?: string[],
): string {
const parts = [
`string: ${string}`,
`string_enum: ${string_enum}`,
`boolean: ${boolean}`,
`number: ${number}`,
`array_bracket: ${JSON.stringify(array_bracket)}`,
`array_generic: ${JSON.stringify(array_generic)}`,
`string_optional: ${string_optional}`,
`string_nullable: ${string_nullable}`,
`number_with_default: ${number_with_default}`,
`boolean_with_default: ${boolean_with_default}`,
`string_with_default: ${string_with_default}`,
`array_optional: ${JSON.stringify(array_optional)}`,
];
for (const [key, value] of Object.entries(process.env)) {
if (key.startsWith("LLM_")) {
parts.push(`${key}: ${value}`);
}
}
return parts.join("\n");
}
```
## Custom Runtime
By default, Loki uses the following runtimes to execute tools:
| Language | Default Runtime | Requirement |
|------------|-----------------|--------------------------------|
| Python | `python` | Python 3 on `$PATH` |
| TypeScript | `npx tsx` | Node.js + tsx (`npm i -g tsx`) |
| Bash | `bash` | Bash on `$PATH` |
You can override the runtime for Python and TypeScript tools using a **shebang line** (`#!`) at the top of your
script. Loki reads the first line of each tool file; if it starts with `#!`, the specified interpreter is used instead
of the default.
**Examples:**
```python
#!/usr/bin/env python3.11
# This Python tool will be executed with python3.11 instead of the default `python`
def run(name: str):
"""Greet someone.
Args:
name: The name to greet
"""
return f"Hello, {name}!"
```
```typescript
#!/usr/bin/env bun
// This TypeScript tool will be executed with Bun instead of the default `npx tsx`
/**
* Greet someone.
* @param name - The name to greet
*/
export function run(name: string): string {
return `Hello, ${name}!`;
}
```
This is useful for pinning a specific Python version, using an alternative TypeScript runtime like
[Bun](https://bun.sh/) or [Deno](https://deno.com/), or working with virtual environments.
docs/function-calling/MCP-SERVERS.md
+120
View File
@@ -0,0 +1,120 @@
# MCP Servers
[MCP servers](https://modelcontextprotocol.io/docs/getting-started/intro) are essentially APIs designed specifically for LLMs that work like a remote repository of
tools for the model to access and extend its capabilities.
So think of it like this: Instead of having to write all your own custom tools to interact with different
services, those services can expose their functionality through an MCP server.
Loki has first-class support for MCP servers.
As mentioned in the [Loki Vault documentation](../VAULT.md), Loki can inject sensitive
configuration data into your MCP configuration file to ensure that secrets are not hard-coded.
## Quick Links
<!--toc:start-->
- [Important Note](#important-note)
- [MCP Server Configuration](#mcp-server-configuration)
- [Secret Injection](#secret-injection)
- [Default MCP Servers](#default-mcp-servers)
- [Loki Configuration](#loki-configuration)
- [Global Configuration](#global-configuration)
- [Role Configuration](#role-configuration)
- [Agent Configuration](#agent-configuration)
<!--toc:end-->
---
## Important Note
Be careful how many MCP servers you enable at one time, regardless of the context. When there is a significant
number of configured MCP servers, enabling too many MCP servers may overwhelm the context length of a model,
and quickly exceed token limits.
## MCP Server Configuration
Loki stores the MCP server configuration file, `functions/mcp.json`, in the `functions` directory. You can find
this directory using the following command:
```shell
loki --info | grep functions_dir | awk '{print $2}'
```
The syntax for the `functions/mcp.json` file is identical to the syntax for MCP server configurations for Claude Desktop.
So any time you're looking to add a new server, look at the docs for it and find the configuration example for
Claude desktop. You should be able to use the exact same configuration in your `functions/mcp.json` file.
### Secret Injection
As mentioned in the [Loki Vault documentation](../VAULT.md), you can use Loki Vault to inject secrets into your MCP configuration file.
In fact, this is why you need to set up your vault before using Loki at all: the built-in MCP configuration
requires you set up some secrets to use it.
For more information about how to set up your vault and inject secrets, please refer to the [Loki Vault documentation](../VAULT.md).
## Default MCP Servers
Loki ships with a `functions/mcp.json` file that includes some useful MCP servers:
* [github](https://github.com/github/github-mcp-server) - Interact with GitHub repositories, issues, pull requests, and more.
* [docker](https://github.com/ckreiling/mcp-server-docker) - Manage your local Docker containers with natural language
* [slack](https://github.com/korotovsky/slack-mcp-server) - Interact with Slack
* [ddg-search](https://github.com/nickclyde/duckduckgo-mcp-server) - Perform web searches with the DuckDuckGo search engine
## Loki Configuration
MCP servers, like tools, can be used in a handful of contexts:
* Inside a session
* Inside a role
* Inside an agent
* Globally (i.e. outside a session, role, or agent)
Each of these has a different configuration and interaction with the global configuration.
***Note:** The names of each MCP server referenced in the below configuration properties directly corresponds
to the names given in the `functions/mcp.json` configuration file. So if you change the name of an MCP server
from `slack` to `lucem-slack`, then you need to also update your Loki configuration accordingly.
### Global Configuration
The global configuration is essentially what settings you want to have on by default when
you just invoke `loki`. (Don't worry about agents, roles, or sessions yet. We'll get to them in a bit).
The following settings are available in the global configuration for MCP servers:
```yaml
mcp_server_support: true # Enables or disables MCP server support (globally).
mapping_mcp_servers: # Alias for an MCP server or set of servers
git: github,gitmcp
enabled_mcp_servers: null # Which MCP servers to enable by default (e.g. 'github,slack')
```
A special note about `enabled_mcp_servers`: a user can set this to `all` to enable all configured MCP servers in the
`functions/mcp.json` configuration.
(See the [Configuration Example](../../config.example.yaml) file for an example global configuration with all options.)
When running in REPL-mode, the `mcp_server_support` and `enabled_mcp_servers` settings can be overridden using the
`.set` command:
![REPL set MCP servers](../images/mcp/global-settings-overrides-repl.png)
### Role Configuration
When you create a role, you have the following MCP-related configuration options available to you:
```yaml
enabled_mcp_servers: github # Which MCP servers the role uses.
```
The values for `mapping_mcp_servers` are inherited from the `[global configuration](#global-configuration)`.
For more information about roles, refer to the [Roles](../ROLES.md) documentation.
### Agent Configuration
When you create an agent, you have the following MCP-related configuration options available to you:
```yaml
mcp_servers: # Which MCP servers the agent uses
- github
- docker
```
The values for `mapping_mcp_servers` are inherited from the [global configuration](#global-configuration).
For more information about agents, refer to the [Agents](../AGENTS.md) documentation.
For a full example configuration for an agent, see the [Agent Configuration Example](../../config.agent.example.yaml) file.
docs/function-calling/TOOLS.md
+192
View File
@@ -0,0 +1,192 @@
# Tools
Loki supports function calling with various tools built-in to enhance LLM capabilities. All built-in tools for Loki
are located in the [`functions/tools`](../../assets/functions/tools) directory. These tools are also stored in your Loki `functions`
directory, which is also where you'd go to add more tools.
**Pro Tip:** The Loki functions directory can be found by running the following command:
```bash
loki --info | grep functions_dir | awk '{print $2}'
```
# Quick Links
<!--toc:start-->
- [Built-In Tools](#built-in-tools)
- [Configuration](#configuration)
- [Global Configuration](#global-configuration)
- [Enabling/Disabling Global Tools](#enablingdisabling-global-tools)
- [Role Configuration](#role-configuration)
- [Agent Configuration](#agent-configuration)
- [Tool Error Handling](#tool-error-handling)
- [Native/Shell Tool Errors](#nativeshell-tool-errors)
- [MCP Errors](#mcp-tool-errors)
- [Why Tool Error Handling Is Important](#why-this-matters)
<!--toc:end-->
---
## Built-In Tools
The following tools are built-in to Loki by default, and their default enabled/disabled status is indicated. More about how tools can
be enabled/disabled can be found in the [Configuration](#configuration) section below.
| Tool | Description | Enabled/Disabled |
|-------------------------------------------------------------------------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|------------------|
| [`demo_py.py`](../../assets/functions/tools/demo_py.py) | Demonstrates how to create a tool using Python and how to use comments. | 🔴 |
| [`demo_sh.sh`](../../assets/functions/tools/demo_sh.sh) | Demonstrate how to create a tool using Bash and how to use comment tags. | 🔴 |
| [`demo_ts.ts`](../../assets/functions/tools/demo_ts.ts) | Demonstrates how to create a tool using TypeScript and how to use JSDoc comments. | 🔴 |
| [`execute_command.sh`](../../assets/functions/tools/execute_command.sh) | Execute the shell command. | 🟢 |
| [`execute_py_code.py`](../../assets/functions/tools/execute_py_code.py) | Execute the given Python code. | 🔴 |
| [`execute_sql_code.sh`](../../assets/functions/tools/execute_sql_code.sh) | Execute SQL code. | 🔴 |
| [`fetch_url_via_curl.sh`](../../assets/functions/tools/fetch_url_via_curl.sh) | Extract the content from a given URL using cURL. | 🔴 |
| [`fetch_url_via_jina.sh`](../../assets/functions/tools/fetch_url_via_jina.sh) | Extract the content from a given URL using Jina. | 🔴 |
| [`fs_cat.sh`](../../assets/functions/tools/fs_cat.sh) | Read the contents of a file at the specified path. | 🟢 |
| [`fs_read.sh`](../../assets/functions/tools/fs_read.sh) | Controlled reading of the contents of a file at the specified path with line numbers, offset, and limit to read specific sections. | 🟢 |
| [`fs_glob.sh`](../../assets/functions/tools/fs_glob.sh) | Find files by glob pattern. Returns matching file paths sorted by modification time. | 🟢 |
| [`fs_grep.sh`](../../assets/functions/tools/fs_grep.sh) | Search file contents using regular expressions. Returns matching file paths and lines. | 🟢 |
| [`fs_ls.sh`](../../assets/functions/tools/fs_ls.sh) | List all files and directories at the specified path. | 🟢 |
| [`fs_mkdir.sh`](../../assets/functions/tools/fs_mkdir.sh) | Create a new directory at the specified path. | 🔴 |
| [`fs_patch.sh`](../../assets/functions/tools/fs_patch.sh) | Apply a patch to a file at the specified path. <br>This can be used to edit a file without having to rewrite the whole file. | 🔴 |
| [`fs_rm.sh`](../../assets/functions/tools/fs_rm.sh) | Remove a file or directory at the specified path. | 🔴 |
| [`fs_write.sh`](../../assets/functions/tools/fs_write.sh) | Write the full file contents to a file at the specified path. | 🟢 |
| [`get_current_time.sh`](../../assets/functions/tools/get_current_time.sh) | Get the current time. | 🟢 |
| [`get_current_weather.py`](../../assets/functions/tools/get_current_weather.py) | Get the current weather in a given location (Python implementation) | 🔴 |
| [`get_current_weather.sh`](../../assets/functions/tools/get_current_weather.sh) | Get the current weather in a given location. | 🟢 |
| [`get_current_weather.ts`](../../assets/functions/tools/get_current_weather.ts) | Get the current weather in a given location (TypeScript implementation) | 🔴 |
| [`query_jira_issues.sh`](../../assets/functions/tools/query_jira_issues.sh) | Query for jira issues using a Jira Query Language (JQL) query. | 🟢 |
| [`search_arxiv.sh`](../../assets/functions/tools/search_arxiv.sh) | Search arXiv using the given search query and return the top papers. | 🔴 |
| [`search_wikipedia.sh`](../../assets/functions/tools/search_wikipedia.sh) | Search Wikipedia using the given search query. <br>Use it to get detailed information about a public figure, interpretation of a <br>complex scientific concept or in-depth connectivity of a significant historical <br>event, etc. | 🔴 |
| [`search_wolframalpha.sh`](../../assets/functions/tools/search_wolframalpha.sh) | Get an answer to a question using Wolfram Alpha. The input query should be <br>in English. Use it to answer user questions that require computation, detailed <br>facts, data analysis, or complex queries. | 🔴 |
| [`send_mail.sh`](../../assets/functions/tools/send_mail.sh) | Send an email. | 🔴 |
| [`send_twilio.sh`](../../assets/functions/tools/send_twilio.sh) | Send SMS or Twilio Messaging Channels messages using the Twilio API. | 🔴 |
| [`web_search_loki.sh`](../../assets/functions/tools/web_search_loki.sh) | Perform a web search to get up-to-date information or additional context. <br>Use this when you need current information or feel a search could provide <br>a better answer. | 🔴 |
| [`web_search_perplexity.sh`](../../assets/functions/tools/web_search_perplexity.sh) | Perform a web search using the Perplexity API to get up-to-date <br>information or additional context. Use this when you need current <br>information or feel a search could provide a better answer. | 🔴 |
| [`web_search_tavily.sh`](../../assets/functions/tools/web_search_tavily.sh) | Perform a web search using the Tavily API to get up-to-date <br>information or additional context. Use this when you need current <br>information or feel a search could provide a better answer. | 🔴 |
Details on what configuration, if any, is necessary for each tool can be found inside the tool file definition itself.
## Configuration
Tools can be used in a handful of contexts:
* Inside a session
* Inside a role
* Inside an agent
* Globally (i.e. outside a session, role, or agent)
Each of these has a different configuration and interaction with the global configuration.
**Note:** For each configuration property listed below, the functions that are mentioned *only*
correspond to the tool scripts located in your Loki `functions/tools` directory.
### Global Configuration
The global configuration is essentially what settings you want to have on by default when
you just invoke `loki`. (Don't worry about agents, roles, or sessions yet. We'll get to them in a bit).
The following settings are available in the global configuration for tools:
```yaml
function_calling_support: true # Enables or disables function calling in any context
mapping_tools: # Alias for a tool or toolset
fs: 'fs_cat,fs_ls,fs_mkdir,fs_rm,fs_write'
enabled_tools: null # Which tools to use by default. (e.g. 'fs,web_search_loki')
visible_tools: # Which tools are visible to be compiled (and are thus able to be defined in 'enabled_tools')
# - demo_py.py
- execute_command.sh
```
A special not about `enabled_tools`: a user can set this to `all` to enable all available tools listed in the
`visible_tools` section of your Loki `config.yaml` file.
See the [Enabling/Disabling Global Tools](#enablingdisabling-global-tools) section below for more information on how tools
are globally enabled/disabled globally.
(See the [Configuration Example](../../config.example.yaml) file for an example global configuration with all options.)
When running in REPL-mode, the `function_calling_support` and `enabled_tools` settings can be overridden using the
`.set` command:
![REPL set function calling](../images/tools/global-settings-overrides-repl.png)
You'll notice that mentioned above, some tools are disabled while others are enabled. How is that determined?
### Enabling/Disabling Global Tools
The configured tools are enabled/disabled by looking at the values in the `visible_tools` array in your `config.yaml`
file. This file is located in the root of the Loki `config` directory. The location of the Loki config varies by system,
so your config file can be found using the following command:
```bash
loki --info | grep 'config_file' | awk '{print $2}'
```
Each line in the `visible_tools` array lists a tool.
If that line is commented out, then that tool is not included in the global tool set, and cannot be used in any context;
This means it will not be built, and even if enabled under `enabled_tools`, it still will not be available in any
context.
### Role Configuration
When you create a role, you have the following global tool-related configuration options available to you:
```yaml
enabled_tools: query_jira_issues # Which tools the role uses.
```
The values for `mapping_tools` are inherited from the [global configuration](#global-configuration).
For more information about roles, refer to the [Roles](../ROLES.md) documentation.
### Agent Configuration
When you create an agent, you have the following global tool-related configuration options available to you:
```yaml
global_tools: # Which global tools the agent uses
- query_jira_issues.sh
- fs_cat.sh
- fs_ls.sh
```
The values for `mapping_tools` are inherited from the [global configuration](#global-configuration).
For more information about agents, refer to the [Agents](../AGENTS.md) documentation.
For a full example configuration for an agent, see the [Agent Configuration Example](../../config.agent.example.yaml) file.
---
## Tool Error Handling
When tools fail, Loki captures error information and passes it back to the model so it can diagnose issues and
potentially retry or adjust its approach.
### Native/Shell Tool Errors
When a shell-based tool exits with a non-zero exit code, the model receives:
```json
{
"tool_call_error": "Tool call 'my_tool' exited with code 1",
"stderr": "Error: file not found: config.json"
}
```
The `stderr` field contains the actual error output from the tool, giving the model context about what went wrong.
If the tool produces no stderr output, only the `tool_call_error` field is included.
**Note:** Tool stdout streams to your terminal in real-time so you can see progress. Only stderr is captured for
error reporting.
### MCP Tool Errors
When an MCP (Model Context Protocol) tool invocation fails due to connection issues, timeouts, or server errors,
the model receives:
```json
{
"tool_call_error": "MCP tool invocation failed: connection refused"
}
```
This allows the model to understand that an external service failed and take appropriate action (retry, use an
alternative approach, or inform the user).
### Why This Matters
Without proper error propagation, models would only know that "something went wrong" without understanding *what*
went wrong. By including stderr output and detailed error messages, models can:
- Diagnose the root cause of failures
- Suggest fixes (e.g., "the file doesn't exist, should I create it?")
- Retry with corrected parameters
- Fall back to alternative approaches when appropriate
docs/images/agents/conversation-starters.gif
BIN
View File
Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 370 KiB

docs/images/agents/sql.gif
BIN
View File
Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 587 KiB

docs/images/agents/todo-system.png
BIN
View File
Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 55 KiB

docs/images/macros/macros-example.gif
BIN
View File
Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 446 KiB

docs/images/mcp/global-settings-overrides-repl.png
BIN
View File
Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 8.1 KiB

docs/images/rag/ephemeral-rag.gif
BIN
View File
Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 1.0 MiB

docs/images/rag/git-loader.png
BIN
View File
Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 21 KiB

docs/images/rag/persistent-rag.gif
BIN
View File
Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 878 KiB

docs/images/repl/continue.gif
BIN
View File
Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 170 KiB

docs/images/repl/copy.gif
BIN
View File
Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 225 KiB

docs/images/repl/model.gif
BIN
View File
Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 189 KiB

docs/images/repl/regenerate.gif
BIN
View File
Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 67 KiB

docs/images/repl/set.gif
BIN
View File
Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 46 KiB

docs/images/roles/code.gif
BIN
View File
Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 303 KiB

docs/images/roles/prompt-role.gif
BIN
View File
Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 63 KiB

docs/images/sessions/sessions-example.gif
BIN
View File
Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 151 KiB

docs/images/shell_integrations/assistant.gif
BIN
View File
Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 30 KiB

docs/images/shell_integrations/code-generation.gif
BIN
View File
Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 78 KiB

docs/images/shell_integrations/explain-shell.png
BIN
View File
Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 43 KiB

docs/images/themes/1337-scheme.png
BIN
View File
Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 58 KiB

docs/images/themes/coldark.png
BIN
View File
Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 60 KiB

docs/images/themes/dracula.png
BIN
View File
Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 60 KiB

docs/images/themes/github.png
BIN
View File
Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 58 KiB

docs/images/themes/gruvbox-dark.png
BIN
View File
Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 70 KiB

docs/images/themes/gruvbox-light.png
BIN
View File
Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 68 KiB

docs/images/themes/onehalf-dark.png
BIN
View File
Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 67 KiB

Some files were not shown because too many files have changed in this diff Show More