feat: add LLM token counting meta plugin and token filters

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.
This commit is contained in:
2026-03-13 16:48:31 -03:00
parent e672ec751e
commit 914190e119
9 changed files with 1128 additions and 3 deletions

59
Cargo.lock generated
View File

@@ -310,6 +310,21 @@ version = "0.22.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "72b3254f16251a8381aa12e40e3c4d2f0199f8c6508fbecb9d91f575e0fbb8c6"
[[package]]
name = "bit-set"
version = "0.5.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "0700ddab506f33b20a03b13996eccd309a48e5ff77d0d95926aa0210fb4e95f1"
dependencies = [
"bit-vec",
]
[[package]]
name = "bit-vec"
version = "0.6.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "349f9b6a179ed607305526ca489b34ad0a41aed5f7980fa90eb03160b69598fb"
[[package]]
name = "bitflags"
version = "1.3.2"
@@ -354,6 +369,17 @@ dependencies = [
"opaque-debug",
]
[[package]]
name = "bstr"
version = "1.12.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "63044e1ae8e69f3b5a92c736ca6269b8d12fa7efe39bf34ddb06d102cf0e2cab"
dependencies = [
"memchr",
"regex-automata",
"serde",
]
[[package]]
name = "bumpalo"
version = "3.19.0"
@@ -929,6 +955,17 @@ version = "0.1.9"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "7360491ce676a36bf9bb3c56c1aa791658183a54d2744120f27285738d90465a"
[[package]]
name = "fancy-regex"
version = "0.13.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "531e46835a22af56d1e3b66f04844bed63158bc094a628bec1d321d9b4c44bf2"
dependencies = [
"bit-set",
"regex-automata",
"regex-syntax",
]
[[package]]
name = "fastrand"
version = "2.3.0"
@@ -1598,6 +1635,7 @@ dependencies = [
"tempfile",
"term",
"thiserror 1.0.69",
"tiktoken-rs",
"tokio",
"tokio-stream",
"tokio-util",
@@ -2354,6 +2392,12 @@ version = "0.1.26"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "56f7d92ca342cea22a06f2121d944b4fd82af56988c270852495420f961d4ace"
[[package]]
name = "rustc-hash"
version = "1.1.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "08d43f7aa6b08d49f382cde6a7982047c3426db949b1424bc4b7ec9ae12c6ce2"
[[package]]
name = "rustix"
version = "1.0.8"
@@ -2851,6 +2895,21 @@ dependencies = [
"cfg-if",
]
[[package]]
name = "tiktoken-rs"
version = "0.9.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "3a19830747d9034cd9da43a60eaa8e552dfda7712424aebf187b7a60126bae0d"
dependencies = [
"anyhow",
"base64 0.22.1",
"bstr",
"fancy-regex",
"lazy_static",
"regex",
"rustc-hash",
]
[[package]]
name = "time"
version = "0.3.47"