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/meta_plugin/mod.rs

@@ -16,8 +16,9 @@ pub mod read_time;
 pub mod shell;
 pub mod shell_pid;
 pub mod text;
+#[cfg(feature = "tokens")]
+pub mod tokens;
 pub mod user;
-// pub mod text; // Removed duplicate
 
 pub use digest::DigestMetaPlugin;
 pub use exec::MetaPluginExec;
@@ -232,6 +233,7 @@ pub enum MetaPluginType {
     Hostname,
     Exec,
     Env,
+    Tokens,
 }
 
 /// Central function to handle metadata output with name mapping.