Turns the graph into a gap-finder: the 247 unresolved internal citations
(a corpus precedent cites a ruling NOT in the corpus) collapse to 230 distinct
"gap" nodes — each sized by how many corpus precedents cite it, i.e. the
most-wanted missing precedent.
Backend (web/graph_api.py — read-only, G2):
- "gap" added to VALID_NODE_TYPES (NOT default → off unless requested).
- New _gap_nodes_and_edges(): gap:<normalized citation> nodes from
precedent_internal_citations WHERE cited_case_law_id IS NULL, sized by global
in-degree; cites edges only from precedents present in the view (dangling-edge
invariant holds). Best-effort enrichment from missing_precedents via exact
normalized-citation match → gap_status + missing_precedent_id. Validated:
230 gaps, top ע"א 3213/97 (cited 5×), 230/230 matched to missing_precedents.
- GraphNode += gap_status, missing_precedent_id. Metrics correctly exclude gap
edges (target not a precedent). No app.py change (gated via node_types).
Frontend:
- graph.ts: GraphNodeType += "gap"; node fields.
- graph-filter-panel: toggle "חוסרי מחקר (פסיקה חסרה)" (off by default).
- graph-canvas: gaps render as faint hollow dashed circles, never recoloured
by color-by; sized by citation count.
- graph-node-panel: gap branch — "מצוטטת ע״י N פסיקות" + status badge + link
to /missing-precedents.
web-ui build + lint pass. Invariants: G2 (SELECT-only), UI2 (model grows on
explicit Pydantic). api:types post-deploy.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The chair cannot review every pending halacha. Three independent-lineage judges
(Opus via claude_session · DeepSeek · Gemini-2.5-flash — #1 on LegalBench) vote
on the COARSE axis we proved reliable across models (92%): "is this a genuine,
keepable rule?". Only an agreed verdict acts; every split escalates to the chair
(INV-G10). Buckets: clean→KEEP?; nli_unsupported→entailment re-adjudication;
extraction-defects→re-extraction.
halacha_panel_calibrate.py calibrates the voting policy on the gold-set's
is_holding (the coarse label) per Trust-or-Escalate (ICLR 2025): unanimous →
94.9% precision / 78% coverage; majority → 92.9% / 99%; ZERO false-drops in
both (the panel never rejects a good rule). Chosen policy (chair-approved):
clean→majority-2/3, nli→asymmetric (majority-reject, unanimous-approve),
defects→re-extraction. Reversible (--apply backs up review_status+flags first).
Sources: Panel-of-LLM-Evaluators (PoLL) · Trust-or-Escalate (ICLR 2025,
arXiv:2407.18370) · selective-prediction / learning-to-defer.
Invariants: upholds G10 (human gate — splits escalate, panel only collapses the
queue) and G9 (provenance — reviewer records the panel + policy). Read paths only
in calibrate; --apply writes review_status/quality_flags reversibly with backup.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
COURT_FETCH_SHARED_SECRET + LEGAL_CHAT_SHARED_SECRET migrated to Infisical
nautilus:/legal-ai (2026-06-07). Updated the pm2 config comments: the stale
"migrate to Infisical once the MCP server is back" TODO is now done; local
env files remain the runtime source, Infisical is the SoT/record.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
ה-cron של drain_digests הוא מנגנון ה-resume (pending-based, idempotent, host-side,
לא תלוי בסשן). חיזוק: אם enrich נכשל באמצע (מכסת claude נגמרה) השורה נשארה
'completed' עם שדות ריקים → לא היתה מטופלת שוב. עכשיו drain מאפס בתחילתו כל
digest 'completed' עם concept_tag ריק *וגם* underlying_citation ריק (= חילוץ
שמעולם לא נחת; שורה תקינה תמיד מכילה לפחות מראה-מקום) → pending לריצה חוזרת.
כך כל קטיעה/מכסה מתאוששת אוטומטית בריצת ה-cron הבאה.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Adds legal-metadata filtering and the payload to color by it (foundation for
the color-by selector in the analytics PR).
Backend (web/graph_api.py, web/app.py) — read-only, G2:
- GraphNode += court, date (ISO) — precedents carry them for filter/color-by.
- build_corpus_graph += server-side WHERE filters (G5): court, precedent_level,
chair, district, year_from, year_to (EXTRACT(YEAR FROM date)). Neighborhood
query also selects court/date.
- New GET /api/graph/facets (response_model GraphFacets, UI2) → distinct
courts/levels/chairs/districts so the UI doesn't hardcode Hebrew strings.
Frontend:
- graph.ts: GraphNode += court/date; GraphFilters += the six params;
buildParams; useGraphFacets() hook.
- graph-filter-panel: an "advanced" Accordion with court/precedent_level/chair/
district Selects (from facets) + year-from/year-to Selects.
- graph-view: new controls wired into filters; facets fetched and passed down.
Verified read-only against the live DB (precedent_level=עליון&year_from=2015
filters correctly; facets populated: 36 courts / 3 levels / 19 chairs / 4
districts). web-ui build + lint pass.
Invariants: G2 (SELECT-only via db.get_pool), G5 (filters server-side),
UI2 (explicit response_models). api:types to be regenerated post-deploy.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The spec said "supreme → Tier-0"; reality (PR #124) routes by נט-format
availability — נט המשפט (Tier-1) serves all courts incl. Supreme-with-נט-format,
and only serial-only Supreme falls to the (still-unbuilt) Tier-0 → manual.
Updated §0 source-distinction, §1 routing diagram, §5 risks (Tier-0 limitation
+ scheduled drain). Docs-only.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Live drain surfaced three issues:
1. Tier-0 needed `h2` (httpx http2) — added to the court-fetch extra.
2. Supreme cases that carry a נט-format number (e.g. בר"מ 72182-06-25) were
routed to the unvalidated Tier-0 and failed, even though נט המשפט serves
Supreme cases too. classify() now parses the file-month-year triple for
Supreme prefixes; the orchestrator routes by triple-availability:
נט-format present → Tier-1 (validated, all courts)
serial-only Supreme (עע"מ 5886/24) → Tier-0
neither → clear "no public route" failure
Validated live: בר"מ 72182-06-25 fetched via Tier-1 (5-page PDF).
3. A non-`RuntimeError` fetch exception (the h2 import error) left jobs stuck
in 'running'. The fetch block now catches any Exception → _record_failure
(INV-CF2/CF3), so a job always reaches a terminal state.
+ test_supreme_with_net_format_triple. Suite 11/11.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
- scripts/drain_court_fetch.py: drives orchestrator.drain_pending (host-only;
no-op when queue empty). Mirrors drain_halacha_queue.py.
- scripts/legal-court-fetch-drain.config.cjs: pm2 cron (hourly :17, one-shot),
COURT_FETCH_DRAIN_CRON override.
- fix: orchestrator default service URL 127.0.0.1 → 10.0.1.1 (the service binds
the docker0 gateway; the host can't reach it on loopback). Found live — the
first drain failed "connection refused" until corrected.
- SCRIPTS.md entries.
Validated end-to-end in PRODUCTION on a real digest: עת"מ 43830-12-24
(החברה להגנת הטבע) fetched from נט המשפט → case_law (79 chunks, source_url),
digest relinked (INV-DIG3 closed), halacha queued pending_review. job=done.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
חילוץ-המטא-דאטה של יומון הוא טקסט→JSON טהור, אבל ה-claude CLI רץ עם tools
זמינים, ו-Sonnet לפעמים פולט stop_reason=tool_use → פוגע ב---max-turns 1 →
error_max_turns → retry (איטי). מבזבז זמן רב בגיבוי-המוני.
- claude_session.query/query_json: פרמטר חדש `tools` → מועבר כ---tools.
"" = ביטוי כל ה-tools (אין tool_use → אין max-turns trip). None = ברירת-CLI.
- digest_metadata_extractor.extract: מעביר tools="".
אומת: extract על יומון 5160 ב-Sonnet+tools="" → num_turns=1, JSON תקין, ללא
error_max_turns. claude_session נשאר local-only.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The gold-set's human role tags were made while seeing a claude AI recommendation,
so human↔AI agreement (~100%) is anchoring, not an independent accuracy signal.
This adds a third, genuinely independent judge — a DIFFERENT model (DeepSeek,
direct OpenAI-compatible API) classifies rule_role BLIND (never sees the human
tag nor the first AI's answer) — and reports an inter-rater agreement matrix.
Finding (100 tagged items): ai↔human 100% (anchored) vs deepseek↔human 50%
fine-grained — BUT 92% on the coarse axis (generalizable-rule vs application/
obiter). Conclusion: the fine sub-type (holding/interpretive/procedural) is an
inherently fuzzy boundary two capable models split differently; the coarse
"is this a real rule" axis is robust across models. Use the coarse axis as
ground truth; treat the sub-type as advisory, never as a gate.
Zero chair tagging, read-only on the gold-set. Key from ~/.hermes deepseek env.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Labels piled on top of each other (esp. in the neighborhood view) for two
reasons, both fixed in graph-canvas.tsx:
1. Font grew as you zoomed OUT (size was divided by sqrt(globalScale) and had
a +6 floor), so at overview zoom labels became huge and collided. Now the
label font is a ~constant SCREEN size (fontPx / globalScale).
2. Every node drew its label at once. Now labels are zoom-gated: at overview
zoom only the active node, the 3 practice-area hubs, and the most-cited
precedents (size>=4) are labeled; topic hubs appear at >=1.05 and the rest
at >=1.5 — by which point there is pixel room between nodes.
Also: a white halo (strokeText) behind each label for legibility over edges
and nearby nodes, and stronger d3 forces (charge -220, link distance 60) so
nodes spread out and labels have more room.
web-ui build passes; /graph in the route table.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
סוגר את הלולאה — יומון שמצביע על פס"ד בית-משפט שלא בקורפוס מזניק אחזור
אוטומטי, וקושר את היומון חזרה אחרי הקליטה (INV-DIG3 + INV-CF2).
- digest_library.try_autolink: בכשל-קישור, אם הציטוט מסווג כפס"ד-בימ"ש
(supreme/admin) → _enqueue_court_fetch יוצר court_fetch_jobs(pending);
ועדת-ערר (skip) לא מוזנק. never-raises (לא שובר קליטת-יומון).
- orchestrator.drain_pending(limit): מנקז pending/failed סדרתי (cooldown,
INV-CF4), fetch+ingest לכל אחד; בהצלחה מקשר את היומון ל-case_law שנקלט.
- כלי-MCP court_fetch_drain + רישום ב-server.py.
- X13 spec: עודכן (הפער ב-INV-CF2 סומן כמתוקן).
נבדק מול ה-DB: עת"מ 46111-12-22 → job tier=admin pending digest-linked;
ערר 1110/20 → לא מוזנק. כלי מקומי בלבד (ingest = claude CLI).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
חילוץ-המטא-דאטה של יומון (תג-מושג, כותרת-הלכה, מראה-מקום, תגיות מסיכום
עמוד-אחד) הוא משימה פשוטה בנפח גבוה — Sonnet הוא נקודת-האיזון מהירות/עלות,
בניגוד לחילוץ-הלכות שמצמיד Opus.
- config.DIGEST_EXTRACT_MODEL (env-tunable, ברירת-מחדל claude-sonnet-4-6).
- digest_metadata_extractor.extract(model=None) → ברירת-מחדל מה-config; קודם
לא צוין model → רץ על ברירת-המחדל של ה-CLI (Opus 4.8).
אומת: extract על יומון 5163 עם Sonnet החזיר תג-מושג/כותרת/מראה-מקום/תחום/
תגיות תקינים (~36s). claude_session נשאר local-only.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
שלוש שכבות-הגנה נגד דליפת-זיכרון מדפדפנים יתומים, + טיפול בדליפה הגדולה
בפועל בשרת (task-master-mcp).
- camofox_client.py:
- asyncio.wait_for קשיח סביב כל ה-fetch (COURT_FETCH_HARD_TIMEOUT_S=180ש')
— hang → ביטול → async-with tear-down → reap.
- _reap_orphan_browsers(): הורג camoufox-bin יתומים (ppid=1) לפני ואחרי כל
fetch. סדרתיות (INV-CF4) → כל ppid=1 הוא שארית בטוחה.
- scripts/reap_orphan_procs.py: reaper כללי ל-task-master-mcp (~3GB יתומים)
+ camoufox-bin. רק ppid=1; /proc טהור. --dry-run / --loop N.
- scripts/legal-reaper.config.cjs: דמון pm2 (loop 180s, max_memory_restart 100M).
- X13 spec + SCRIPTS.md: תיעוד שכבות-ההגנה.
max_memory_restart בשירות (1.5G) כבר נותן רשת-ביטחון ברמת-התהליך.
Invariants: מקיים INV-CF4 (politeness/serial) — ללא שינוי חוזה.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Native, Obsidian-graph-view-like network of the precedent corpus, rendered
in web-ui from a read-only projection of the live DB. Replaces the idea of
exporting to an external Obsidian vault (which would be a parallel, drifting
copy of the corpus — the exact root cause G2 forbids).
The graph edges already existed in the data model; this only surfaces them:
nodes = precedents (case_law) + synthesized topic/practice-area hubs;
edges = cites (precedent_internal_citations) + same_chain (case_law_relations)
+ tagged/in_area (subject_tags / practice_area membership). Node size =
incoming-citation count (index-backed GROUP BY on idx_pic_target). Click a
node → local-graph neighborhood focus; panel deep-links to /precedents/[id].
Backend (read-only, SELECT only — G2):
- web/graph_api.py — Pydantic models (CorpusGraph/GraphNode/GraphEdge, so
OpenAPI emits real types — UI2) + SQL assembly over the shared db.get_pool().
- web/app.py — GET /api/graph/corpus, GET /api/graph/node/{id}/neighborhood,
both with explicit response_model. practice_area validated against the
closed enum (G5); both endpoints write nothing.
Frontend:
- react-force-graph-2d (canvas/d3-force), loaded via next/dynamic ssr:false.
- /graph page + nav entry; graph.ts TanStack hooks; filter panel (practice_area
/ source / min-citations / search / node-type toggles), node detail panel,
hover+selection neighborhood highlight. Explicit error handling (UI4).
Not a retrieval path (03-retrieval): returns graph topology, never ranked
search results. Halacha nodes + corroboration/equivalence edges are Phase 2,
already gated behind the node_types param (no contract change needed).
SQL validated read-only against the live DB (142 precedents, 85 resolved
citations, JSONB tag expansion, ANY(uuid[]) edge + BFS queries). web-ui lint
+ build pass; /graph in the route table.
Invariants: keeps G2 (single source of truth — live projection, no parallel
store), G5 (corpus separation filtered server-side), UI2 (response models),
UI4 (no swallowed UI errors).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The extractor classified rule_type by SOURCE bindingness (higher-court→binding,
committee→persuasive) instead of by rule KIND. The gold-set proved it: 'binding'
appeared on 19/19 external rulings & 0 committees; 'persuasive' on 13/13
committees & 0 external — only 58% agreement with the human role tags. The two
axes (authority vs rule role) were crammed into one enum.
This splits them per INV-DM7:
- authority (binding/persuasive) — DERIVED from case_law.precedent_level
(עליון/מנהלי→binding, ועדת_ערר_מחוזית→persuasive), never stored, never
LLM-guessed. New helper halacha_quality.derive_authority; surfaced read-only
in list_halachot / goldset_list / search results.
- rule_type — now the rule ROLE only: holding/interpretive/procedural/
application/obiter. Both extractor prompts unified to this vocabulary;
_coerce_halacha no longer defaults rule_type from the source; legacy
binding→holding / persuasive→interpretive fold for safety.
UI: authority shown as a separate read-only badge (gold=מחייב / muted=משכנע)
across the review queue, precedent detail, and gold-set; the gold-set role
selector drops binding/persuasive and adds מהותי (holding).
Migration: scripts/halacha_rule_role_backfill.py re-classifies the 276 pre-split
binding/persuasive rows into a genuine role via local claude_session (run after
deploy). Gold-set correct_type/ai_correct_type 'binding'→'holding' via SQL.
Sources (≥3, per research-decision policy): OASIS LegalRuleML v1.0
(appliesAuthority/Strength as metadata orthogonal to rule logic) · SemEval-2023
Task 6 LegalEval (rhetorical roles by function, authority kept separate) ·
Bluebook signals (weight-of-authority is a separate dimension).
Invariants: ESTABLISHES INV-DM7. Upholds G1 (normalize at source — extractor
classifies role, system derives authority) and G2 (single source of truth —
authority derived, not a parallel stored field). Tests: 211 pass + new
derive_authority/coerce coverage. web-ui build + tsc clean.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The old independent toggles had a trap: clicking "אי-הסכמות AI" set a filter,
and once all disagreements were resolved the toggle button disappeared
(rendered only when count>0) while the filter stayed ON — so the list showed
zero items and the untagged ones were unreachable.
Replaced hideTagged + disagreeOnly with one mutually-exclusive segmented
control: הכל / לא תויגו / תויגו / ⚠ אי-הסכמות, each with a live count and always
visible. No stuck state; "לא תויגו" makes the remaining work obvious.
Verified: tsc --noEmit 0.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The chair wanted an independent recommendation beside each tag, to reconsider
his own judgments. Adds a NON-ground-truth AI second-opinion:
- schema: halacha_goldset.ai_is_holding / ai_correct_type / ai_rationale /
ai_generated_at (additive).
- db.goldset_set_ai_recommendation + goldset_list now returns the ai_* fields.
- scripts/goldset_ai_recommend.py — local claude_session judges is_holding +
type + a one-line rationale per item, INDEPENDENTLY (own legal rubric).
Independent of the rule-based validators #81.8 measures → no circularity.
Never auto-applied; QA aid only.
- web-ui: each card shows "🤖 המלצת AI: הלכה/לא · type" + rationale and an
agreement/disagreement chip vs the human tag (amber on disagree); a
"⚠ אי-הסכמות AI (N)" filter to review only the conflicts.
Methodology note kept explicit: the human stays the ground truth; the AI is a
prompt to reconsider, not to copy.
Verified: tsc --noEmit 0; generator stores recs and flags disagreements with
existing human tags.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
