Andrew Phillips
914190e119
Add tiktoken-based token counting via new 'tokens' feature flag. New components: - Shared tokenizer module wrapping tiktoken CoreBPE (cl100k_base, o200k_base) - TokensMetaPlugin: streaming token counter, tokenizes each chunk independently - head_tokens(N): stream first N tokens, split at exact boundary when mid-chunk - skip_tokens(N): skip first N tokens, stream the rest - tail_tokens(N): bounded ring buffer (~16KB), outputs last N tokens at finalize All filters are fully streaming — no full-stream buffering. Meta plugin accuracy: exact for normal text, ±1-2 tokens if long whitespace sequence spans a chunk boundary. Also: add 'client' and 'tokens' to default features, add curl to Dockerfile builder stage.
123 lines
3.5 KiB
TOML
123 lines
3.5 KiB
TOML
[package]
|
|
name = "keep"
|
|
version = "0.1.0"
|
|
edition = "2024"
|
|
description = "Keep and manage temporary files with automatic compression and metadata generation"
|
|
readme = "README.md"
|
|
categories = ["command-line-utilities"]
|
|
|
|
|
|
# See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
|
|
|
|
[dependencies]
|
|
anyhow = "1.0.72"
|
|
axum = { version = "0.8.4", optional = true }
|
|
derive_more = { version = "2.0", features = ["full"] }
|
|
smart-default = "0.7"
|
|
thiserror = "1.0"
|
|
base64 = "0.22.1"
|
|
chrono = { version = "0.4.26", features = ["serde"] }
|
|
clap = { version = "4.3.10", features = ["derive", "env"] }
|
|
config = "0.14.0"
|
|
ctor = "0.2"
|
|
directories = "6.0.0"
|
|
dns-lookup = "2.0.2"
|
|
enum-map = "2.6.1"
|
|
flate2 = { version = "1.0.27", features = ["zlib-ng-compat"], optional = true }
|
|
futures = "0.3"
|
|
gethostname = "1.0.2"
|
|
humansize = "2.1.3"
|
|
async-stream = "0.3"
|
|
hyper = { version = "1.0", features = ["full"] }
|
|
http-body-util = "0.1"
|
|
inventory = "0.3"
|
|
is-terminal = "0.4.9"
|
|
lazy_static = "1.4.0"
|
|
libc = "0.2.147"
|
|
local-ip-address = "0.6.5"
|
|
log = "0.4.19"
|
|
lz4_flex = { version = "0.11.1", optional = true }
|
|
magic = { version = "0.13.0", optional = true }
|
|
nix = "0.30.1"
|
|
once_cell = "1.19.0"
|
|
comfy-table = "7.2.0"
|
|
pwhash = "1.0.0"
|
|
regex = "1.9.5"
|
|
ringbuf = "0.3"
|
|
rmcp = { version = "0.2.0", features = ["server"], optional = true }
|
|
rusqlite = { version = "0.37.0", features = ["bundled", "array", "chrono"] }
|
|
rusqlite_migration = "2.3.0"
|
|
serde = { version = "1.0.219", features = ["derive"] }
|
|
serde_json = "1.0.142"
|
|
serde_yaml = "0.9.34"
|
|
sha2 = "0.10.0"
|
|
md5 = "0.7.0"
|
|
subtle = "2.6"
|
|
stderrlog = "0.6.0"
|
|
strum = { version = "0.27.2", features = ["derive"] }
|
|
term = "1.1.0"
|
|
tokio = { version = "1.0", features = ["full"] }
|
|
tokio-stream = "0.1"
|
|
tokio-util = "0.7.16"
|
|
tower = { version = "0.5.2", optional = true }
|
|
tower-http = { version = "0.6.6", features = ["cors", "fs", "trace"], optional = true }
|
|
utoipa = { version = "5.4.0", features = ["axum_extras"], optional = true }
|
|
utoipa-swagger-ui = { version = "9.0.2", features = ["axum"], optional = true }
|
|
uzers = "0.12.1"
|
|
which = "8.0.0"
|
|
xdg = "2.5.2"
|
|
strip-ansi-escapes = "0.2.1"
|
|
pest = "2.8.1"
|
|
pest_derive = "2.8.1"
|
|
dirs = "6.0.0"
|
|
similar = { version = "2.7.0", default-features = false, features = ["text"] }
|
|
ureq = { version = "3", features = ["json"], optional = true }
|
|
os_pipe = { version = "1", optional = true }
|
|
axum-server = { version = "0.8", features = ["tls-rustls"], optional = true }
|
|
jsonwebtoken = { version = "10", optional = true, features = ["aws_lc_rs"] }
|
|
tiktoken-rs = { version = "0.9", optional = true }
|
|
|
|
[features]
|
|
# Default features include core compression engines and swagger UI
|
|
default = ["magic", "lz4", "gzip", "client", "tokens"]
|
|
|
|
# Full
|
|
#default = ["server", "magic", "lz4", "swagger"]
|
|
|
|
|
|
# Server feature (includes axum and related dependencies)
|
|
server = ["dep:axum", "dep:tower", "dep:tower-http", "dep:utoipa", "dep:jsonwebtoken"]
|
|
|
|
# Compression features
|
|
gzip = ["flate2"]
|
|
lz4 = ["lz4_flex"]
|
|
bzip2 = []
|
|
xz = []
|
|
zstd = []
|
|
|
|
# Plugin features (meta and filter)
|
|
all-meta-plugins = ["dep:magic"]
|
|
all-filter-plugins = []
|
|
|
|
# Individual plugin features
|
|
magic = ["dep:magic"]
|
|
|
|
# MCP feature (Model Context Protocol support)
|
|
mcp = ["dep:rmcp"]
|
|
|
|
# Swagger UI feature
|
|
swagger = ["dep:utoipa-swagger-ui"]
|
|
|
|
# Client feature (HTTP client for remote server)
|
|
client = ["dep:ureq", "dep:os_pipe"]
|
|
|
|
# TLS feature (HTTPS server support)
|
|
tls = ["dep:axum-server"]
|
|
|
|
# Token counting feature (LLM token support via tiktoken)
|
|
tokens = ["dep:tiktoken-rs"]
|
|
|
|
[dev-dependencies]
|
|
tempfile = "3.3.0"
|
|
rand = "0.8.5"
|