sync chart feature code 2026-07-03

workspace/cil/chart_features.py

@@ -0,0 +1,56 @@
+from __future__ import annotations
+
+import hashlib
+from typing import Any
+
+try:
+    import numpy as np
+except ImportError:  # pragma: no cover
+    np = None
+
+
+CONTEXT_HASH_WIDTH = 8
+CHART_FEATURE_MODES = ("base", "base_context")
+
+
+def build_chart_feature(
+    base_action: Any,
+    metadata: dict[str, Any] | None = None,
+    *,
+    mode: str = "base",
+) -> Any:
+    """Build a deployment-visible chart feature vector.
+
+    `base` preserves the original behavior: the chart token is the flattened
+    base action chunk. `base_context` appends stable hashes of task/language
+    metadata that are visible at proposal time. It intentionally does not read
+    outcomes, labels, hidden chart branches, or evaluator-only fields.
+    """
+
+    if np is None:  # pragma: no cover
+        raise ImportError("build_chart_feature requires numpy")
+    if mode not in CHART_FEATURE_MODES:
+        raise ValueError(f"unknown chart feature mode: {mode}")
+    base = np.asarray(base_action, dtype=np.float32).reshape(-1)
+    if mode == "base":
+        return base
+    metadata = metadata or {}
+    context = np.asarray(
+        [
+            *_stable_hash_features(str(metadata.get("task_id", "")), CONTEXT_HASH_WIDTH),
+            *_stable_hash_features(str(metadata.get("instruction", "")).lower(), CONTEXT_HASH_WIDTH),
+            min(len(str(metadata.get("instruction", ""))) / 128.0, 4.0),
+            min(len(str(metadata.get("instruction", "")).split()) / 32.0, 4.0),
+        ],
+        dtype=np.float32,
+    )
+    return np.concatenate([base, context]).astype(np.float32, copy=False)
+
+
+def chart_feature_dim(base_action: Any, *, mode: str = "base") -> int:
+    return int(build_chart_feature(base_action, {}, mode=mode).reshape(-1).shape[0])
+
+
+def _stable_hash_features(text: str, width: int) -> list[float]:
+    digest = hashlib.sha256(text.encode("utf-8")).digest()
+    return [float(digest[index] / 127.5 - 1.0) for index in range(width)]