Initial commit: Future-Entropy Sampler prototype

llama.cpp-based implementation of the countbayesie Future-Entropy Sampler,
built via a direct ctypes binding to libllama.so. Includes a one-shot CLI
(entropy_cli.py), an OpenAI-compatible server (entropy_server.py), and the
tuning/benchmark scripts used to derive the alpha/confidence-threshold
defaults documented in the README.

Model path and llama.cpp library path are now read from environment
variables (ENTROPY_SAMPLER_MODEL, LLAMA_CPP_LIB) instead of being hardcoded,
and gguf-py is pulled from PyPI instead of a local llama.cpp checkout, so
this runs on any machine with a compatible llama.cpp build and model.

tune_alpha.py

@@ -0,0 +1,61 @@
+"""Sweep alpha (and a couple of tamed sine schedules) to find the sweet spot
+between the pure-probability baseline (generic but coherent) and the
+pure-entropy extreme (degenerates into blank-template exploitation).
+"""
+from entropy_sampler import EntropySampler, sine_alpha_schedule
+
+PROMPT = "The old lighthouse keeper had seen many storms, but none like"
+MAX_NEW_TOKENS = 60
+
+FIXED_ALPHAS = [-1.0, -0.5, 0.0, 0.3, 0.5, 0.7, 1.0]
+SINE_CONFIGS = [
+    {"period_tokens": 10, "amplitude": 0.4},
+    {"period_tokens": 16, "amplitude": 0.6},
+]
+
+
+def summarize(text, diagnostics_log):
+    ps = [d["candidates"][d["chosen"]]["p"] for d in diagnostics_log]
+    hs = [d["candidates"][d["chosen"]]["h_hat"] for d in diagnostics_log]
+    degenerate = sum(1 for d in diagnostics_log if "_" in d["candidates"][d["chosen"]]["token"])
+    return {
+        "mean_p": sum(ps) / len(ps),
+        "mean_h": sum(hs) / len(hs),
+        "degenerate_tokens": degenerate,
+    }
+
+
+def run_labeled(sampler, label, alpha):
+    log = []
+    orig_step = sampler.step
+
+    def step_and_log(base_logits, a, confidence_threshold=None):
+        token, next_logits, diag = orig_step(base_logits, a, confidence_threshold)
+        log.append(diag)
+        return token, next_logits, diag
+
+    sampler.step = step_and_log
+    text = sampler.generate(PROMPT, max_new_tokens=MAX_NEW_TOKENS, alpha=alpha, verbose=False)
+    sampler.step = orig_step
+
+    stats = summarize(text, log)
+    print(f"=== {label} ===")
+    print(text)
+    print(
+        f"[mean p={stats['mean_p']:.3f}  mean H_hat={stats['mean_h']:.3f}  "
+        f"degenerate(_)={stats['degenerate_tokens']}/{MAX_NEW_TOKENS}]\n"
+    )
+
+
+if __name__ == "__main__":
+    sampler = EntropySampler(top_k=12, top_n_future=20, n_ctx=4096)
+    try:
+        for a in FIXED_ALPHAS:
+            run_labeled(sampler, f"alpha = {a:+.1f}", a)
+
+        for cfg in SINE_CONFIGS:
+            schedule = sine_alpha_schedule(**cfg)
+            label = f"sine period={cfg['period_tokens']} amp={cfg['amplitude']}"
+            run_labeled(sampler, label, schedule)
+    finally:
+        sampler.close()