Initial commit: Ten31 Signal Engine (ingest, scoring brain, corpus seeds)

signal_engine/signals/ledger_writer.py

@@ -0,0 +1,49 @@
+"""Ledger + candidate_scores writers. Log EVERY bar-clearer from day one (§6.6 denominator).
+
+date_logged = as_of (backtest rows carry historical dates so lead-time math is correct). The
+discourse_metric JSON is FROZEN here at log time — the resolver (separate forward pass) never edits it.
+Grant's rating lives in human_evaluations; the model never reads it pre-log (§6.7).
+"""
+from __future__ import annotations
+
+import hashlib
+import json
+
+
+def _sig_id(scorer: str, key: str, as_of: str) -> str:
+    return "sig_" + hashlib.sha1(f"{scorer}|{key}|{as_of}".encode()).hexdigest()[:16]
+
+
+def _score_id(scorer: str, key: str, as_of: str) -> str:
+    return hashlib.sha1(f"cs|{scorer}|{key}|{as_of}".encode()).hexdigest()
+
+
+def record_candidate_score(conn, result: dict, as_of: str, evidence: bool, promotion: bool) -> None:
+    key = result.get("node_id") or result.get("conviction_id") or result.get("topic_canonical") or ""
+    conn.execute(
+        """INSERT OR REPLACE INTO candidate_scores
+             (score_id, scorer, as_of, topic_canonical, node_id, conviction_id, score,
+              cleared_evidence_bar, cleared_promotion_bar, inputs_json)
+           VALUES (?,?,?,?,?,?,?,?,?,?)""",
+        (_score_id(result["scorer"], key, as_of), result["scorer"], as_of,
+         result.get("topic_canonical"), result.get("node_id"), result.get("conviction_id"),
+         result["score"], int(evidence), int(promotion), json.dumps(result["inputs"])[:8000]),
+    )
+    conn.commit()
+
+
+def log_candidate(conn, *, scorer: str, as_of: str, ledger_type: str, proposition: str,
+                  discourse_metric: dict, origin_conviction_id=None, origin_node_id=None) -> str:
+    key = origin_node_id or origin_conviction_id or proposition
+    signal_id = _sig_id(scorer, key, as_of)
+    dm = {**discourse_metric, "scorer": scorer}
+    conn.execute(
+        """INSERT OR IGNORE INTO ledger
+             (signal_id, type, proposition, date_logged, discourse_metric, model_confidence,
+              origin_conviction_id, origin_node_id)
+           VALUES (?,?,?,?,?,?,?,?)""",
+        (signal_id, ledger_type, proposition[:1000], as_of, json.dumps(dm)[:8000], None,
+         origin_conviction_id, origin_node_id),
+    )
+    conn.commit()
+    return signal_id