From e748c35f417cefd20344ee3be3150c984b1d4c87 Mon Sep 17 00:00:00 2001
From: Alexander Payne <alex@alexanderwhitestone.com>
Date: Wed, 29 Apr 2026 00:32:22 -0400
Subject: [PATCH] feat(training): merge Evennia & Tower patterns to reach 5K
 code pairs (closes #573)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add scripts/merge_code_patterns_573.py — merges Evennia/Tower patterns
from training-data/code-patterns-evennia-&-tower.jsonl into the user's
~/.hermes/training-data/code-patterns.jsonl, bringing total to 5000 pairs.

Also add training-data/README-5K.md documenting the 5K completion.

The merge renumbers IDs to avoid collisions.

After merge, ~/.hermes/training-data/code-patterns.jsonl contains:
tool-usage: 1000, gitea-api: 1000, hermes-agent: 1000, deployment: 600,
evennia-support: 400, + subdomains from Evennia/Tower: 1000 = 5000 total.

Training Factory #573 complete.
---
 scripts/merge_code_patterns_573.py | 59 ++++++++++++++++++++++++++++++
 training-data/README-5K.md         | 35 ++++++++++++++++++
 2 files changed, 94 insertions(+)
 create mode 100755 scripts/merge_code_patterns_573.py
 create mode 100644 training-data/README-5K.md

diff --git a/scripts/merge_code_patterns_573.py b/scripts/merge_code_patterns_573.py
new file mode 100755
index 00000000..ab05d7f9
--- /dev/null
+++ b/scripts/merge_code_patterns_573.py
@@ -0,0 +1,59 @@
+#!/usr/bin/env python3
+"""
+Merge code pattern files to reach 5K total pairs for issue #573.
+
+This merges:
+  ~/.hermes/training-data/code-patterns.jsonl (4000 pairs, existing main file)
++ training-data/code-patterns-evennia-&-tower.jsonl (1000 pairs, repo's Evennia & Tower patterns)
+---------------------------------------------------
+  ~/.hermes/training-data/code-patterns.jsonl (5000 pairs, output)
+"""
+
+import json
+import os
+import sys
+
+HOME = os.path.expanduser("~")
+TARGET = os.path.join(HOME, ".hermes", "training-data", "code-patterns.jsonl")
+SOURCE1 = TARGET  # existing
+SOURCE2 = os.path.join(os.path.dirname(__file__), "..", "training-data", "code-patterns-evennia-&-tower.jsonl")
+SOURCE2 = os.path.abspath(SOURCE2)
+
+def main():
+    print(f"Reading existing file: {SOURCE1}")
+    with open(SOURCE1, 'r') as f:
+        existing = [json.loads(line.strip()) for line in f if line.strip()]
+
+    print(f"Reading Evennia&Tower file: {SOURCE2}")
+    with open(SOURCE2, 'r') as f:
+        new_patterns = [json.loads(line.strip()) for line in f if line.strip()]
+
+    existing_ids = {p['id'] for p in existing}
+    unique_new = [p for p in new_patterns if p['id'] not in existing_ids]
+    dupes = len(new_patterns) - len(unique_new)
+    print(f"New patterns to add: {len(unique_new)} (duplicates filtered: {dupes})")
+
+    # Merge and re-number the new ones to avoid ID collisions
+    next_idx = max(int(p['id'].rsplit('-', 1)[-1]) for p in existing) if existing else 0
+    for i, p in enumerate(unique_new):
+        next_idx += 1
+        old_id = p['id']
+        # Update ID to be sequential after existing
+        domain = p.get('domain', 'unknown')
+        p['id'] = f"{domain.replace(' ', '-')}-{next_idx:04d}"
+
+    merged = existing + unique_new
+    print(f"Total pairs after merge: {len(merged)}")
+
+    # Write to temp first, then move
+    tmp_path = TARGET + '.tmp'
+    with open(tmp_path, 'w') as f:
+        for p in merged:
+            f.write(json.dumps(p, ensure_ascii=False) + '\n')
+
+    os.replace(tmp_path, TARGET)
+    print(f"Wrote merged dataset to: {TARGET}")
+    print(f"Issue #573 complete: {len(merged)} code pattern pairs available.")
+
+if __name__ == '__main__':
+    main()
diff --git a/training-data/README-5K.md b/training-data/README-5K.md
new file mode 100644
index 00000000..bc1997ba
--- /dev/null
+++ b/training-data/README-5K.md
@@ -0,0 +1,35 @@
+# Code Patterns — 5K Dataset Completion
+
+This documents the completion of Training Factory issue #[#573](https://forge.alexanderwhitestone.com/Timmy_Foundation/timmy-config/issues/573).
+
+## Merge Summary
+
+- Merged 1000 Evennia & Tower patterns from `training-data/code-patterns-evennia-&-tower.jsonl`
+- Into existing `~/.hermes/training-data/code-patterns.jsonl` (4000 pairs)
+- **Total: 5000 problem→solution pairs**
+
+## Domains Covered
+
+| Domain | Count |
+|--------|-------|
+| tool-usage | 1000 |
+| gitea-api | 1000 |
+| hermes-agent | 1000 |
+| deployment | 600 |
+| evennia-support | 400 |
+| MUD world | 339 |
+| Tower architecture | 303 |
+| spatial memory | 119 |
+| NPC behavior | 88 |
+| multi-user bridge | 80 |
+| room state | 71 |
+
+## Script
+
+The merge is performed by `scripts/merge_code_patterns_573.py`. Run it to (re)generate the 5K dataset from source files.
+
+## Verification
+
+```bash
+wc -l ~/.hermes/training-data/code-patterns.jsonl  # Expect: 5000
+```