Accept first survey batch + add commit-hash post-processing

Spot-check of the three drafts gemini produced in the --max 3
survey smoke test: all cited file paths exist, line numbers and
function names land within 1-2 lines of actual symbols
(game.pyx:217 cdef class GameState, evaluate.py:220 batched-entropy
block, trainer.py:892 _evaluate_parallel, action_distribution at
evaluate.py:238 with cited code at line 250 inside it). Numbers
cross-checked against archives match. Conclusions preserved.

The one systemic weakness was the Last-verified commit field:
gemini left a `<short-hash>` placeholder, a literal `HEAD`, or
omitted the commit entirely depending on the call. Fixed in two
places:

1. Manually patched the three drafts before acceptance and copied
   them into docs/research/.
2. Added _current_commit_sha and _post_process_draft helpers to
   both librarian_survey.py and librarian_promote.py. The drafts
   now go through `**Last verified:**` line normalization that
   substitutes today's date and `git rev-parse --short HEAD`
   before being written to disk. Future runs converge
   deterministically.

Net: docs/research/ gains classic-port-notes.md,
deep-cfr-batched-evaluation.md, and deep-cfr-evaluation-profile.md.
12 archive entries remain unprocessed.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

scripts/librarian_promote.py

@@ -24,7 +24,6 @@ from __future__ import annotations
 import argparse
 import os
 import re
-import shutil
 import subprocess
 import sys
 from datetime import datetime
@@ -37,6 +36,7 @@ LLM_COMMANDS = {
 }
 
 DATE_SUFFIX = re.compile(r"-\d{4}-\d{2}-\d{2}$")
+LAST_VERIFIED = re.compile(r"^\*\*Last verified:\*\*[^\n]*$", re.MULTILINE)
 
 
 def _repo_root() -> Path:
@@ -47,6 +47,34 @@ def _repo_root() -> Path:
     raise RuntimeError("pyproject.toml을 찾을 수 없어 repository root를 판정할 수 없습니다.")
 
 
+def _current_commit_sha(root: Path) -> str:
+    """Resolve HEAD to a short SHA. Returns 'unknown' if git is unavailable."""
+    result = subprocess.run(
+        ["git", "rev-parse", "--short", "HEAD"],
+        capture_output=True,
+        text=True,
+        check=False,
+        cwd=root,
+    )
+    if result.returncode != 0:
+        return "unknown"
+    return result.stdout.strip() or "unknown"
+
+
+def _post_process_draft(content: str, commit_sha: str) -> str:
+    """Normalize a draft before writing to disk.
+
+    The LLM is unreliable about running `git` itself in headless mode; it
+    tends to leave `<short-hash>` placeholders or literal `HEAD` strings.
+    Rewrite the `**Last verified:**` line in place with today's date and
+    the real short SHA. If the line is missing entirely, leave the draft
+    untouched so the omission stays visible during review.
+    """
+    today = datetime.now().strftime("%Y-%m-%d")
+    new_line = f"**Last verified:** {today}, commit `{commit_sha}`"
+    return LAST_VERIFIED.sub(new_line, content, count=1)
+
+
 def _assemble_prompt(
     system_prompt: str,
     rel_archive: Path,
@@ -167,7 +195,9 @@ def main() -> int:
         print(result.stderr, file=sys.stderr)
         return result.returncode
 
-    draft_path.write_text(result.stdout, encoding="utf-8")
+    commit_sha = _current_commit_sha(root)
+    draft_text = _post_process_draft(result.stdout, commit_sha)
+    draft_path.write_text(draft_text, encoding="utf-8")
     print(f"Draft written to: {draft_path.relative_to(root)}")
 
     if args.accept:
@@ -177,7 +207,7 @@ def main() -> int:
                 file=sys.stderr,
             )
             return 1
-        shutil.copyfile(draft_path, target)
+        target.write_text(draft_text, encoding="utf-8")
         print(f"Copied to: {rel_target}")
         print("Next: review the diff and `git add` + commit if you're satisfied.")
     else:

scripts/librarian_survey.py

@@ -40,6 +40,7 @@ LLM_COMMANDS = {
 }
 
 DATE_SUFFIX = re.compile(r"-\d{4}-\d{2}-\d{2}$")
+LAST_VERIFIED = re.compile(r"^\*\*Last verified:\*\*[^\n]*$", re.MULTILINE)
 
 
 def _repo_root() -> Path:
@@ -78,6 +79,34 @@ def _assemble_prompt(
     )
 
 
+def _current_commit_sha(root: Path) -> str:
+    """Resolve HEAD to a short SHA. Returns 'unknown' if git is unavailable."""
+    result = subprocess.run(
+        ["git", "rev-parse", "--short", "HEAD"],
+        capture_output=True,
+        text=True,
+        check=False,
+        cwd=root,
+    )
+    if result.returncode != 0:
+        return "unknown"
+    return result.stdout.strip() or "unknown"
+
+
+def _post_process_draft(content: str, commit_sha: str) -> str:
+    """Normalize a draft before writing to disk.
+
+    The LLM is unreliable about running `git` itself in headless mode; it
+    tends to leave `<short-hash>` placeholders or literal `HEAD` strings.
+    Rewrite the `**Last verified:**` line in place with today's date and
+    the real short SHA. If the line is missing entirely, leave the draft
+    untouched so the omission stays visible during review.
+    """
+    today = datetime.now().strftime("%Y-%m-%d")
+    new_line = f"**Last verified:** {today}, commit `{commit_sha}`"
+    return LAST_VERIFIED.sub(new_line, content, count=1)
+
+
 def _has_counterpart(archive_stem_no_date: str, research_stems: set[str]) -> bool:
     """True if a research note already covers this archive entry.
 
@@ -150,6 +179,7 @@ def main() -> int:
         return 1
 
     system_prompt = (root / "scripts" / "librarian-prompt.md").read_text(encoding="utf-8")
+    commit_sha = _current_commit_sha(root)
 
     timestamp = datetime.now().strftime("%Y-%m-%d_%H%M%S")
     out_dir = root / "runs" / "tmp" / f"librarian-survey-{timestamp}"
@@ -186,9 +216,10 @@ def main() -> int:
             skips += 1
             print(f"    SKIP ({output[:80]})", file=sys.stderr)
         else:
-            (out_dir / f"{stem_out}.md").write_text(output, encoding="utf-8")
+            normalized = _post_process_draft(output, commit_sha)
+            (out_dir / f"{stem_out}.md").write_text(normalized, encoding="utf-8")
             drafts += 1
-            print(f"    draft ({len(output)} chars)", file=sys.stderr)
+            print(f"    draft ({len(normalized)} chars)", file=sys.stderr)
 
     print()
     print(f"Survey complete: {drafts} drafts, {skips} skips, {errors} errors.")