Files
kebab/Cargo.toml
altair823 ed03e71a1c chore: bump version 0.30.1 → 0.31.0 + v0.31.0 release notes
척추 단순화(#214) + 임베딩 캐시 전면화(#216) + OCR/caption 캐시(#217) 누적 릴리스.
minor 트리거 = 척추의 V015 drop chat_sessions + config v4→v5 breaking 마이그레이션.
도그푸딩 evidence(HOTFIXES 2026-06-25): OCR 캐시 17 jira PNG 재인덱싱 7× + 캐시 히트
created_at 17/17 고정 / 실 v3 KB 마이그레이션(config v5 + V14/V15 자동, chat_sessions 드롭).
2026-06-25 02:07:23 +00:00

221 lines
11 KiB
TOML
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
[workspace]
resolver = "3"
members = [
"crates/kebab-core",
"crates/kebab-config",
"crates/kebab-source-fs",
"crates/kebab-parse-md",
"crates/kebab-chunk",
"crates/kebab-store-sqlite",
"crates/kebab-store-vector",
"crates/kebab-search",
"crates/kebab-embed",
"crates/kebab-embed-local",
"crates/kebab-embed-ollama",
"crates/kebab-llm",
"crates/kebab-llm-local",
"crates/kebab-rag",
"crates/kebab-app",
"crates/kebab-cli",
"crates/kebab-eval",
"crates/kebab-parse-image",
"crates/kebab-parse-pdf",
"crates/kebab-mcp",
"crates/kebab-parse-code",
"crates/kebab-nli",
]
[workspace.package]
edition = "2024"
rust-version = "1.85"
license = "MIT OR Apache-2.0"
repository = "https://github.com/altair823/kebab"
version = "0.31.0" # v0.31.0 — 척추 단순화 + 캐시 전면화. (1) 척추 재작성(#214, breaking): tui·multi-turn 세션·rag-v1/v2·search캐시·candle 제거(crate 24→22), config v4→v5 무손실 마이그레이션, V015 drop chat_sessions. (2) 임베딩 캐시 전면화(#216, patch): image/pdf/code 핸들러를 markdown 과 동일한 embed_with_cache 경유로 — 출력 byte-identical. (3) OCR/caption derivation 캐시(#217, patch): ocr/caption 네임스페이스로 비전 산출물을 소스 바이트로 캐싱 → 버전-캐스케이드에서 분리, 출력 불변. minor 트리거 = 척추의 V015 + config v5 breaking. 도그푸딩 evidence: HOTFIXES 2026-06-25(OCR 캐시 17 jira PNG 7× + v3 KB 마이그레이션). 상세 docs/release-notes/v0.31.0-draft.md — CLAUDE.md §Release
# pre-v0.18 workspace-wide cleanup: enable clippy::pedantic group with
# intentional allow-list. The allowed lints are either cosmetic (doc style),
# informational (function size), or carry intentional truncation we accept
# (numeric casts in tokenizer/ONNX inputs, hash modular reduction, etc).
[workspace.lints.clippy]
pedantic = { level = "warn", priority = -1 }
# Intentional u32 ↔ i64 casts in kebab-nli (ONNX i64 inputs from tokenizer u32 ids).
# u64 ↔ usize across kebab-store-sqlite row counts. Wide truncation is auditable
# at use site, not lint-wide.
cast_possible_truncation = "allow"
cast_possible_wrap = "allow"
cast_sign_loss = "allow"
cast_precision_loss = "allow"
# Doc markdown style is cosmetic; we run rustdoc on demand.
doc_markdown = "allow"
missing_errors_doc = "allow"
missing_panics_doc = "allow"
# Informational only — splitting a long pipeline function isn't always cleaner.
too_many_lines = "allow"
# `Foo::default()` is concise and idiomatic here; `<Foo as Default>::default()`
# adds noise without surfacing intent.
default_trait_access = "allow"
# Module name prefix on public items keeps the wire/log surface readable
# (`refusal_reason::no_chunks` etc).
module_name_repetitions = "allow"
# We use `#[must_use]` deliberately on public results, not blanket.
must_use_candidate = "allow"
# `String` arg sometimes signals "I'll consume this" — let signature decide.
needless_pass_by_value = "allow"
# Idiomatic single-line bindings stay; let-else expansion isn't always clearer.
manual_let_else = "allow"
# `use` after `let` is a common kebab pattern (scoped imports next to use site).
items_after_statements = "allow"
# Naming pairs like `chunk_id` / `chunks_id` are intentional domain terms.
similar_names = "allow"
# `iter.map(format!).collect::<String>()` is idiomatic when the per-element
# string is genuinely independent — `fold` only wins on accumulation patterns.
format_collect = "allow"
# Exhaustive `match` with explicit variant arms (vs `_`) catches future
# variant additions at compile time (kebab core's `RefusalReason` pattern).
match_wildcard_for_single_variants = "allow"
# Copy types under `&self` keep call-site discipline; auto-deref noise > tiny perf gain.
trivially_copy_pass_by_ref = "allow"
# `unnecessary_wraps` flags helpers that could drop `Result`, but keeping the
# Result allows future error variants without churning callers.
unnecessary_wraps = "allow"
# NLI score / RRF fusion / similarity threshold comparisons are intentional —
# floats live in the `[0, 1]` band and are compared with explicit thresholds.
float_cmp = "allow"
# File-extension dispatch is keyed on ASCII conventions; case sensitivity
# is part of the spec for `.md`, `.pdf`, etc.
case_sensitive_file_extension_comparisons = "allow"
# Config / opts structs intentionally bundle boolean flags (ingest options,
# search modes, etc) — splitting them into enums would obscure the wire shape.
struct_excessive_bools = "allow"
# `bytecount` crate would be a new dep just for one-off ASCII counts.
naive_bytecount = "allow"
# `#[ignore]` annotations on tests document via the test name + nearby comment.
ignore_without_reason = "allow"
# `format!` push patterns are common in CLI output paths;
# `write!` rewrite needs a verified-equal benchmark before swapping.
format_push_string = "allow"
# Builder-style `with_*` methods return `Self`; the existing `#[must_use]`
# discipline lives on aggregate constructors, not every chainable setter.
return_self_not_must_use = "allow"
# Match arms grouped by side-effect over body equality (e.g. snake_case wire
# label tables) — fanning them out keeps adding a new variant trivial.
match_same_arms = "allow"
# Remaining style-only warnings: trailing `continue` is sometimes clearer than
# rewriting, `_x` underscored bindings document intent at the use site, and
# `!(a == b)` reads better than `a != b` when paired with a complementary check.
needless_continue = "allow"
used_underscore_binding = "allow"
nonminimal_bool = "allow"
# Other one-off cosmetic items: large literal formatting, doc link quoting,
# `Clone::clone_from` swap, `str::replace` chaining, `Iterator::any` ergonomics.
unreadable_literal = "allow"
many_single_char_names = "allow"
doc_link_with_quotes = "allow"
assigning_clones = "allow"
collapsible_str_replace = "allow"
trivial_regex = "allow"
elidable_lifetime_names = "allow"
range_plus_one = "allow"
explicit_iter_loop = "allow"
implicit_hasher = "allow"
ref_option = "allow"
[workspace.dependencies]
anyhow = "1"
thiserror = "2"
serde = { version = "1", features = ["derive"] }
serde_json = "1"
# Golden-fixture loader (P5-1, kebab-eval) parses YAML; pinned in the
# workspace so future eval-adjacent crates share the same major.
serde_yaml = "0.9"
time = { version = "0.3", features = ["serde", "macros", "formatting", "parsing"] }
uuid = { version = "1", features = ["v7", "serde"] }
blake3 = "1"
tracing = "0.1"
# `bundled` ships SQLite source so the workspace doesn't depend on a
# system libsqlite3 (matches the kebab-store-sqlite feature set).
rusqlite = { version = "0.32", features = ["bundled"] }
globset = "0.4"
tempfile = "3"
proptest = "1"
lopdf = "0.32"
# fastembed-rs ships ONNX runtime via the `ort-download-binaries` feature
# in its default set (which also pulls `hf-hub` for first-run model
# downloads). Pinned to the 4.x line per task p3-2 (current 5.x release
# remains untested for this workspace).
fastembed = "4.9"
# LanceDB embedded vector store (P3-3). 0.23.x pulls arrow / arrow-array /
# arrow-schema 56.x transitively (via lance 1.0); the kebab-store-vector
# crate matches that major to share the same Arrow types without a
# re-export adapter.
lancedb = { version = "0.23", default-features = false }
arrow = "56"
arrow-array = "56"
arrow-schema = "56"
tokio = { version = "1", features = ["rt", "macros"] }
futures = "0.3"
# Strict citation-marker extraction in kebab-rag (P4-3) needs a single regex
# pass; pulled into the workspace deps so future crates can share the
# same major.
regex = "1"
# MCP (Model Context Protocol) SDK. server + macros + transport-io provide
# stdio JSON-RPC transport for `kebab-mcp` (p9-fb-30). schemars feature
# exposes the derive macro used by tool input schemas.
rmcp = { version = "1.6", default-features = false, features = ["server", "macros", "transport-io", "schemars"] }
# Dev-only HTTP mock server for kebab-llm-local Ollama adapter tests. Requires
# a tokio runtime to host its mock server (the runtime adapter crate stays
# sync via reqwest::blocking — wiremock is dev-only there).
wiremock = "0.6"
base64 = "0.22"
# Pure-Rust git library for repo metadata detection (kebab-parse-code).
# No `git` binary required. Default features include thread-safety + most
# object-reading capabilities needed for HEAD name + commit SHA queries.
gix = { version = "0.70", default-features = false, features = ["revision"] }
# Rust source parsing for code ingest (kebab-parse-code, p10-1A-2). The
# chunker stays tree-sitter-free — AST work is parser-side per design §6.3.
tree-sitter = "0.26"
tree-sitter-rust = "0.24"
# Python / TS / JS grammars for code ingest (kebab-parse-code, p10-1B).
tree-sitter-python = "0.25.0"
tree-sitter-typescript = "0.23.2"
tree-sitter-javascript = "0.25.0"
# Go grammar for code ingest (kebab-parse-code, p10-1C-Go).
tree-sitter-go = "0.25.0"
# JVM family grammars for code ingest (kebab-parse-code, p10-1C-JK).
tree-sitter-java = "0.23.5"
tree-sitter-kotlin-ng = "1.1.0" # bare tree-sitter-kotlin requires ts <0.23; -ng uses tree-sitter-language 0.1 (ts 0.26 compat)
# C/C++ family grammars for code ingest (kebab-parse-code, p10-1D).
tree-sitter-c = "0.24.2"
tree-sitter-cpp = "0.23.4"
# fb-41 PR-9 (kebab-nli): mDeBERTa-v3 XNLI verifier deps. Versions match
# the fastembed 4.9 transitive set so the ONNX Runtime + tokenizer stack
# stays single-versioned across the workspace. ort `default-features=false`
# drops the bundled binary downloader (fastembed already provides one);
# tokenizers `default-features=false, onig` swaps the default `esaxx` regex
# backend for `onig` so the build doesn't need libstdc++ headers (verified
# via PR-9a pre-flight: SentencePiece tokenizer.json loads + KR/EN encode).
# hf-hub uses `ureq + rustls-tls` to stay aligned with kebab-embed-local's
# pure-Rust TLS stack.
ort = { version = "=2.0.0-rc.9", default-features = false, features = ["ndarray"] }
tokenizers = { version = "0.21", default-features = false, features = ["onig"] }
hf-hub = { version = "0.4", default-features = false, features = ["ureq", "rustls-tls"] }
ndarray = "0.16"
# Korean morphological tokenizer (FTS v0.20.x, §6.1). lindera-ko-dic bundles
# the KO-DIC dictionary as an embedded blob via the embed-ko-dic feature.
lindera = "3"
lindera-ko-dic = "3"
# Disk-footprint trim for dev / test builds. Codegen, opt-level, and
# behavior are unchanged — only DWARF debug info is reduced (line
# numbers kept, column numbers dropped) and split into separate
# `.dwo` files. backtrace stays useful (function + line). release
# profile is untouched, so CI / `--release` runs are byte-identical
# to upstream defaults.
[profile.dev]
debug = "line-tables-only"
split-debuginfo = "unpacked"
[profile.test]
debug = "line-tables-only"
split-debuginfo = "unpacked"