From 14ff5431353aee23bc88c0eaf23d3ac0ebc3bac9 Mon Sep 17 00:00:00 2001
From: KoalaTrapLord <KoalaTrapLord@users.noreply.github.com>
Date: Sun, 5 Apr 2026 16:04:07 +0000
Subject: [PATCH] =?UTF-8?q?fix:=20DecisionLogger=20JSONL=20filename=20pref?=
 =?UTF-8?q?ix=20=E2=80=94=20ml-decisions-sim-*=20for=20dataset=5Fbuilder?=
 =?UTF-8?q?=20discovery?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The Java DecisionLogger was writing files as ml-decisions-{batchId}.jsonl
but the Python dataset_builder.py scans for ml-decisions-sim-*.jsonl to
categorize them as 'forge' source training data.

This one-line fix adds the 'sim-' prefix so the Forge batch heuristic
path now feeds directly into the ML training pipeline:

  BatchRunner → DecisionExtractor → DecisionLogger
    → results/ml-decisions-sim-{batchId}.jsonl
    → dataset_builder.py discovers as 'forge' source
    → encode → train

The full chain was already wired (Issue #83 Phase 1 infrastructure),
this naming mismatch was the only thing preventing it from working.

Refs: Issue #83 Phase 1
---
 src/main/java/commanderailab/ml/DecisionLogger.java | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/src/main/java/commanderailab/ml/DecisionLogger.java b/src/main/java/commanderailab/ml/DecisionLogger.java
index ac04838..2011c3a 100644
--- a/src/main/java/commanderailab/ml/DecisionLogger.java
+++ b/src/main/java/commanderailab/ml/DecisionLogger.java
@@ -14,7 +14,7 @@ import java.util.*;
  * Each game's decisions are appended as JSON lines to a batch-specific file.
  * Format: one DecisionSnapshot JSON object per line (JSONL/ndjson).
  *
- * Output path: results/ml-decisions-{batchId}.jsonl
+ * Output path: results/ml-decisions-sim-{batchId}.jsonl
  *
  * Usage from BatchRunner:
  *   DecisionLogger logger = new DecisionLogger(resultsDir, batchId);
@@ -39,7 +39,10 @@ public class DecisionLogger {
         if (!Files.exists(dir)) {
             Files.createDirectories(dir);
         }
-        this.outputPath = dir.resolve("ml-decisions-" + batchId + ".jsonl");
+        // Prefix with "sim-" so the Python dataset_builder.py discovers
+        // these files under the "forge" source category.  The builder scans
+        // for  ml-decisions-sim-*.jsonl  →  source = "forge".
+        this.outputPath = dir.resolve("ml-decisions-sim-" + batchId + ".jsonl");
         this.writer = Files.newBufferedWriter(outputPath, StandardCharsets.UTF_8,
                 StandardOpenOption.CREATE, StandardOpenOption.APPEND);