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.

src/lib.rs

@@ -43,6 +43,9 @@ pub mod services;
 #[cfg(feature = "client")]
 pub mod client;
 
+#[cfg(feature = "tokens")]
+pub mod tokenizer;
+
 // Re-export Args struct for library usage
 pub use args::Args;
 // Re-export PIPESIZE constant
@@ -52,6 +55,10 @@ pub use common::PIPESIZE;
 #[allow(unused_imports)]
 use filter_plugin::{grep, head, skip, strip_ansi, tail};
 
+#[cfg(feature = "tokens")]
+#[allow(unused_imports)]
+use filter_plugin::tokens as token_filters;
+
 use crate::meta_plugin::{
     cwd, digest, env, exec, hostname, keep_pid, read_rate, read_time, shell, shell_pid, user,
 };
@@ -60,6 +67,10 @@ use crate::meta_plugin::{
 #[allow(unused_imports)]
 use crate::meta_plugin::magic_file;
 
+#[cfg(feature = "tokens")]
+#[allow(unused_imports)]
+use crate::meta_plugin::tokens;
+
 /// Initializes plugins at library load time.
 ///
 /// Plugin registration happens automatically via `#[ctor]` constructors