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.

Dockerfile

@@ -3,6 +3,7 @@ FROM rust:1.88-slim AS builder
 
 RUN apt-get update && apt-get install -y --no-install-recommends \
     cmake \
+    curl \
     make \
     gcc \
     musl-tools \
@@ -16,7 +17,6 @@ WORKDIR /app
 # Copy manifests and fetch dependencies (cached layer)
 COPY Cargo.toml Cargo.lock ./
 RUN mkdir src && echo 'fn main() {}' > src/main.rs && echo '' > src/lib.rs
-
 RUN cargo fetch --target x86_64-unknown-linux-musl
 
 # Copy real source and build static binary