ezer-mishpati/legal-ai
1
0
Fork 0
Code Issues Pull Requests 1 Actions Packages Projects Releases Wiki Activity

Merge pull request 'feat(learning): ניתוח-§A של האוצֵר רץ על mark-final — לכידת source='curator' על כל סופי (#159)' (#342) from worktree-curator-autofire into main
All checks were successful
Build & Deploy / build-and-deploy (push) Successful in 8s
Details
G12 Leak-Guard / leak-guard (push) Successful in 4s
Details
Lint — undefined names / undefined-names (push) Successful in 10s
Details

Browse Source
This commit was merged in pull request #342.
This commit is contained in:
chaim
2026-06-28 22:03:15 +00:00
parent b0a6c2fe01 4d6268820c
commit b8eb0ee123
3 changed files with 34 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
scripts/final_learning_pipeline.py
View File

@@ -91,15 +91,22 @@ async def main(args: argparse.Namespace) -> int:
# The 3 steps as durable nodes (X16 / INV-DUR1) — shared runtime with
# final_halacha (scripts/_pipeline_runtime.py). A crash/OOM in the long style
# panel [3] resumes from [3] instead of re-paying the Opus distillation [1].
# panel [3] resumes from [3] instead of re-paying the Opus distillation [2].
#
# Order (#159): enroll FIRST. enroll creates the style_corpus row (fast, no LLM)
# that decision_lessons attach to. Running it before the up-to-30-min distillation
# means the corpus exists within seconds — so the curator agent's §A (which fires
# in parallel on a final_learning_* wake) can record source='curator' findings
# without racing the 30-min step. enroll/ingest are mutually independent; panel
# needs both, so it stays last.
async def step_ingest(results: dict) -> dict:
# [1] distillation (Opus) — skip if already analyzed (idempotent; --force to redo).
# [2] distillation (Opus) — skip if already analyzed (idempotent; --force to redo).
status = await _latest_pair_status(case["id"])
if status == "analyzed" and not args.force:
print("[1/3] ingest_final_version — דולג (הזוג כבר analyzed; --force לחידוש)")
print("[2/3] ingest_final_version — דולג (הזוג כבר analyzed; --force לחידוש)")
return {"ingest": "skipped:analyzed"}
print("[1/3] ingest_final_version — דיסטילציית טיוטה↔סופי…", flush=True)
print("[2/3] ingest_final_version — דיסטילציית טיוטה↔סופי…", flush=True)
raw = await ingest_final_version(case_number, file_path=final_path)
try:
env = json.loads(raw)
@@ -120,8 +127,9 @@ async def main(args: argparse.Namespace) -> int:
return {"ingest": "done"}
async def step_enroll(results: dict) -> dict:
# [2] enroll into style_corpus (idempotent) — lessons need a corpus_id.
print("[2/3] רישום לקורפוס-הסגנון (idempotent)…", flush=True)
# [1] enroll into style_corpus (idempotent) — lessons need a corpus_id, and
# it must exist early (before the long distillation) so curator §A can attach.
print("[1/3] רישום לקורפוס-הסגנון (idempotent)…", flush=True)
if await _has_style_corpus(case_number):
print(" ✓ כבר רשום בקורפוס-הסגנון")
return {"enroll": "exists"}
@@ -150,8 +158,8 @@ async def main(args: argparse.Namespace) -> int:
return {"panel_rc": rc or 0}
steps = [
_pipeline_runtime.Step("ingest_final_version", step_ingest),
_pipeline_runtime.Step("enroll_style_corpus", step_enroll),
_pipeline_runtime.Step("ingest_final_version", step_ingest),
_pipeline_runtime.Step("style_panel", step_panel),
]
checkpoint_db = config.DATA_DIR / "checkpoints" / "learning.sqlite"