Chaim
9a19db1ec1
The voice-fingerprint (docs/daphna-voice-fingerprint.md) is the PRIMARY abstract style channel the writer consumes (07-learning §0.2 channel A), but it was hand-authored and never regenerated from the growing corpus — the "voice" the writer adapts stayed frozen while finals accumulated. PR #345 unfroze the structural half (corpus-measured ratios → writer); this is the prose half. scripts/regenerate_voice_fingerprint.py reads the corpus (style_corpus stats + a bounded block-level style_exemplars sample + measured section ratios) and asks Opus (local) to PROPOSE refinements/additions to the fingerprint — STYLE / METHOD / VOICE / LEXICON only, grounded in corpus evidence, never case substance (INV-LRN5), preserving curated insights rather than replacing them. CHAIR-GATED, HARD (INV-LRN1): the prose profile is voice-knowledge, not a low-risk style rule, so it does NOT auto-flow. The script writes a PROPOSAL to data/curator-proposals/ (the existing curator-proposal surface) and NEVER overwrites the live fingerprint; the chair reviews and hand-commits accepted parts — the same manual gate the fingerprint already uses. Runs on the host (claude CLI). Reuses claude_session + measure_corpus_ratios + the curator-proposals dir (G2 — no parallel synthesis or gate). SCRIPTS.md + spec §0.2 updated. Invariants: INV-LRN1 (hard chair gate for voice-knowledge prose), INV-LRN5 (style-only synthesis), G2 (reuses existing synthesis inputs + proposal surface). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
114 lines
6.5 KiB
Python
Executable File
114 lines
6.5 KiB
Python
Executable File
#!/usr/bin/env python3
|
||
"""Propose a corpus-refreshed update to Dafna's voice-fingerprint (TaskMaster #161).
|
||
|
||
The voice-fingerprint (docs/daphna-voice-fingerprint.md) is the PRIMARY abstract
|
||
style channel the writer consumes (07-learning §0.2, channel A). It was hand-authored
|
||
and never regenerated from the growing corpus — so the "voice" the writer adapts has
|
||
been frozen while the corpus grew. This script reads the corpus (style_corpus stats +
|
||
block-level style_exemplars sample + measured section ratios) and asks Opus (local)
|
||
to PROPOSE refinements/additions to the fingerprint — STYLE / METHOD / VOICE / LEXICON
|
||
ONLY, never case substance (INV-LRN5).
|
||
|
||
CHAIR-GATED (INV-LRN1, HARD gate — the prose profile is voice-knowledge, not a
|
||
low-risk style rule, so it does NOT auto-flow): the proposal is written to
|
||
data/curator-proposals/ and NEVER overwrites the live fingerprint. The chair reviews
|
||
it (in /training, with the other curator proposals) and hand-commits the parts she
|
||
accepts to docs/daphna-voice-fingerprint.md — the same manual gate the fingerprint
|
||
already uses. This is the prose half of the voice-profile refresh; the structural
|
||
half (corpus-measured ratios → writer) shipped in PR #345.
|
||
|
||
Runs on the HOST (claude_session needs the local claude CLI). Usage:
|
||
DOTENV_PATH=/home/chaim/.env DATA_DIR=/home/chaim/legal-ai/data \\
|
||
/home/chaim/legal-ai/mcp-server/.venv/bin/python scripts/regenerate_voice_fingerprint.py
|
||
"""
|
||
from __future__ import annotations
|
||
|
||
import asyncio
|
||
import logging
|
||
from datetime import datetime, timezone
|
||
|
||
from legal_mcp import config
|
||
from legal_mcp.services import claude_session, db
|
||
from legal_mcp.services.style_distance import measure_corpus_ratios
|
||
|
||
logging.basicConfig(level=logging.INFO, format="%(message)s")
|
||
log = logging.getLogger("voice_fingerprint_refresh")
|
||
|
||
FINGERPRINT = config.DATA_DIR.parent / "docs" / "daphna-voice-fingerprint.md"
|
||
PROPOSALS = config.DATA_DIR / "curator-proposals"
|
||
_PER_SECTION = 5 # exemplars per section in the evidence pack
|
||
_MAX_PARA_CHARS = 700 # cap each exemplar so the prompt stays bounded
|
||
|
||
_SYSTEM = """אתה מזקק את טביעת-אצבע-הקול של עו"ד דפנה תמיר — פרופיל-סגנון מופשט (איך היא כותבת: קול, שיטה, מבנה, לקסיקון, אנטי-דפוסים), לא תוכן.
|
||
חוקים מחייבים:
|
||
- **סגנון/שיטה בלבד (INV-LRN5):** אסור לכלול מהות משפטית ספציפית — הלכה, עובדה, תקדים, או ניסוח מתיק קונקרטי. רק הכללות-סגנון.
|
||
- **לחדד ולהרחיב, לא לזרוק:** שמר את התובנות האצורות בפרופיל הנוכחי; הצע תוספות/חידודים מעוגנים בראיות-הקורפוס שלהלן.
|
||
- **לעגן:** כל קביעה חדשה נשענת על דפוס שחוזר בראיות. אם אין עיגון — אל תמציא ואל תוסיף.
|
||
- שמר על מבנה-המסמך והסעיפים הקיימים.
|
||
הפלט: גרסת-fingerprint מוצעת מלאה (Markdown), מוכנה לסקירת-יו"ר — בלי הקדמות או הסברים מסביב."""
|
||
|
||
|
||
async def _gather_evidence() -> tuple[str, str]:
|
||
pool = await db.get_pool()
|
||
async with pool.acquire() as conn:
|
||
n_corpus = await conn.fetchval("SELECT count(*) FROM style_corpus WHERE coalesce(full_text,'') <> ''")
|
||
n_ex = await conn.fetchval("SELECT count(*) FROM style_exemplars")
|
||
rows = await conn.fetch(
|
||
"""SELECT section, decision_number, outcome, paragraph_text FROM (
|
||
SELECT section, decision_number, outcome, paragraph_text,
|
||
row_number() OVER (PARTITION BY section
|
||
ORDER BY decision_number DESC, word_count DESC) AS rn
|
||
FROM style_exemplars
|
||
) t WHERE rn <= $1 ORDER BY section, rn""",
|
||
_PER_SECTION,
|
||
)
|
||
ratios = await measure_corpus_ratios()
|
||
parts = [f"קורפוס: {n_corpus} החלטות, {n_ex} דוגמאות-בלוק.", "", "יחסי-מבנה מדודים מהקורפוס (אחוז-מהסך, לפי תוצאה):"]
|
||
for outcome, entry in (ratios or {}).items():
|
||
secs = ", ".join(f"{s} {round(p)}%" for s, p in (entry.get("sections") or {}).items())
|
||
parts.append(f" - {outcome} (n={entry.get('n', 0)}): {secs}")
|
||
parts += ["", "דוגמאות-סגנון מייצגות (פסקאות אמיתיות של דפנה — מקור ללמידת-קול, לא להעתקת-מהות):"]
|
||
for r in rows:
|
||
para = (r["paragraph_text"] or "").strip()[:_MAX_PARA_CHARS]
|
||
parts.append(f"\n[{r['section']} · {r['decision_number']} · {r['outcome'] or '—'}]\n{para}")
|
||
return "\n".join(parts), f"{n_corpus} החלטות / {n_ex} דוגמאות"
|
||
|
||
|
||
async def main() -> int:
|
||
if not FINGERPRINT.exists():
|
||
log.error("fingerprint not found: %s", FINGERPRINT)
|
||
return 1
|
||
current = FINGERPRINT.read_text(encoding="utf-8")
|
||
evidence, summary = await _gather_evidence()
|
||
|
||
user = (
|
||
f"## הפרופיל הנוכחי (לחדד ולהרחיב, לא להחליף):\n{current}\n\n"
|
||
f"## ראיות-קורפוס:\n{evidence}\n\n"
|
||
"## המשימה:\nהצע גרסת-fingerprint מעודכנת המשלבת חידודים/תוספות-סגנון מעוגנים בראיות לעיל, "
|
||
"תוך שימור כל התובנות האצורות. סגנון/שיטה בלבד — בלי מהות."
|
||
)
|
||
log.info("synthesizing voice-fingerprint proposal from %s (Opus, local)…", summary)
|
||
proposed = await claude_session.query(
|
||
user, timeout=claude_session.LONG_TIMEOUT, system=_SYSTEM,
|
||
model="claude-opus-4-8", tools="",
|
||
)
|
||
if not proposed or not proposed.strip():
|
||
log.error("empty proposal from model — aborting (nothing written)")
|
||
return 1
|
||
|
||
PROPOSALS.mkdir(parents=True, exist_ok=True)
|
||
ts = datetime.now(timezone.utc).strftime("%Y%m%dT%H%M%SZ")
|
||
out = PROPOSALS / f"voice-fingerprint-{ts}.md"
|
||
header = (
|
||
f"<!-- הצעת-חידוש לטביעת-אצבע-הקול · {ts} · מקור: {summary} -->\n"
|
||
"<!-- שער-יו\"ר (INV-LRN1): הצעה בלבד. לסקור ולקבע ידנית ל-docs/daphna-voice-fingerprint.md. -->\n\n"
|
||
)
|
||
out.write_text(header + proposed, encoding="utf-8")
|
||
log.info("✓ proposal written (chair-gated, NOT applied): %s", out)
|
||
log.info(" review in /training → commit accepted parts to %s", FINGERPRINT)
|
||
return 0
|
||
|
||
|
||
if __name__ == "__main__":
|
||
raise SystemExit(asyncio.run(main()))
|