Fixes the case where the H1 chip, the pipeline stepper and the manual-changer
dropdown disagreed (e.g. 1043-02-26 on analyst_verified): the status sat between
the canonical 10 and a legacy bucket, so each surface read a different list.
Root fix — ONE authoritative status model + canonicalize the real intermediate
states (chair-approved):
- New mcp-server/.../case_status_model.py — the single registry: ordered
StatusDef list (key/label/description/phase/selectable/terminal/on_enter),
the 5 phases, STATUS_ORDER, phase_of/label_of, and a drift assertion that the
CaseStatus enum matches it. `on_enter` is the seam for a status to *do*
something on entry, declared next to its definition (no dispatcher wired yet).
- models.CaseStatus enum: analyst_verified + research_complete promoted to
first-class canonical statuses (the agents set them — they belong in the
model, not a legacy fallback).
- tools/cases.py: the forward-only STATUS_ORDER guard now derives from the
registry instead of an inline list.
- GET /api/status-model exposes the model so the frontend mirror can be
generated against it.
- web-ui case-status.ts mirrors it: the two intermediates moved from the
legacy map into CASE_STATUSES / PHASES(thinking) / STATUS_LABELS /
STATUS_DESCRIPTIONS; status-badge icons+tones extended. So the chip (status),
stepper (its phase) and dropdown (now includes it) all agree.
Invariants: G2 — collapses the scattered status definitions (enum, inline
STATUS_ORDER, two frontend label maps) onto one backend authority + a documented
frontend mirror; no parallel status list remains. Agent-prompt alignment +
backfill follow in a separate change. py_compile + tsc + eslint clean.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The summarize_party_claims tool (#202) generated a distilled executive
summary of party claims but was orphaned: not granted to any agent and
no CEO trigger. Wire it parallel to the interim-draft (שלב H).
- Grant mcp__legal-ai__summarize_party_claims in legal-ceo.md frontmatter.
- Add שלב H2 (סיכום מנהלים) mirroring שלב H: side-quest (no cases.status
change, no sub-agent issues), in_progress → run tool → in_review + notify.
Two triggers: chair comment ("סיכום מנהלים"/"סיכום טענות"/"סיכום לקראת
דיון"/"executive summary") OR structured action
$PAPERCLIP_WAKE_PAYLOAD_JSON action == "party_claims_summary".
- Add structured-action trigger to שלב H (interim draft):
action == "interim_draft" — same deterministic UI-button path.
- שלב 0 + HEARTBEAT.md: route structured actions deterministically.
- Spec note in docs/spec/04-analysis-writing.md §1.4.
Invariants: G2 (reuse existing summarize_party_claims tool/path, no parallel
route), G10 (chair-requested side-quest). Agent-prompt/docs only — no app code.
Note: CEO prompt is shared across CMP+CMPA via instructionsFilePath; after
merge the host tree needs `git pull` (agents run host-side reading
.claude/agents/*.md).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Groups the drafts/comments tab into distinct cards instead of one long scroll:
- "פסיקה שצוטטה" (CitationsSection) moved inside the chair's signed-final card
as its sub-section (was floating between final and the files table).
- "קבצי טיוטה" and "הערות יו״ר" sections each wrapped in a bordered surface card.
Result: draft-ready banner + active-draft badge at top, then three cards —
final-decision+learning (gold), draft files, chair feedback. All logic,
mutations, dialogs and the feedback list preserved verbatim.
tsc --noEmit + eslint clean. Design-gate: mockup 18h approved in Claude Design X17.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
- Agents tab: render the AgentStatusWidget roster at the top of the activity
feed ("who's doing what right now") and surface pending agent interactions in
an amber "ממתין לתשובתך" banner above the timeline (mockup 18i key wins).
- Drafts tab: Hebraize the drafts-table headers File/Size/Date → קובץ/גודל/תאריך
(mockup 18h).
All existing feed logic, mutations and interaction forms preserved.
tsc --noEmit + eslint clean.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Chair-requested refinements to the case banner:
- Tabs now span the full band width via justify-between — wide gaps with the
current 6 tabs, tightening as more are added (gap-2 no-overlap floor).
- Parties moved out of the always-on header line into a "צדדים" Popover, so the
band is shorter and the tab content sits higher on the page.
- Case subject (title) moved up onto the case-number line in a smaller font,
instead of its own line below.
tsc --noEmit + eslint clean.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Make the effort-calibration recommendation style-clean (style acquisition is
the goal — write like chair Dafna Tamir):
- recommend_effort ranks by anti_pattern_total (PRIMARY, the clean style-rule
violation count) → golden_ratio_deviation_pp (SECONDARY, structural-style,
None=worst) → distance (faint final tiebreak). change_percent is EXCLUDED from
the ranking (it mixes style with content-completeness per 07-learning §0.7 —
noise for STYLE) and kept in the report as context only.
- Add a confidence flag ("clear"/"weak"): a pick whose anti-pattern lead over the
runner-up is within noise (margin < epsilon = max(0.5, 0.20·spread)) is flagged
⚠️ weak, so an over-claimed pick (the old confident block-zayin "low") is never
shown as confident. Rendered as a confidence column in the report.
- Add --rerank <report.json>: re-apply the new key to a saved calibration JSON
offline (NO LLM, NO DB), print + write *-reranked.md. Re-ranks today's 8-final
run without regenerating.
- recommend_effort stays a single shared pure function reused by
scripts/calibrate_block_yod.py (G2); both --self-test suites pass.
- Spec note added (07-learning §0.7) + SCRIPTS.md updated.
Invariants: G8 (style-clean empirical ranking), G2 (single shared recommend_effort,
reused by the block-yod harness — no parallel metric path), INV-LRN5 (style-only
signal; change% reported-not-ranked).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Summary with a verification progress bar, status filter chips + only-unverified
toggle, per-argument collapsible accordion with a v/t verify-progress chip, and
compact precedent rows (clamped/expandable quote, collapsible chair note). All
verify/saveNote mutations + types preserved verbatim.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Folds the standalone /compose decision-editor route into the main case page so
there is no more "sub-page" (mockup 18f), with the final 6-tab workflow order:
סקירה · טיעונים ועמדות · אימות פסיקה · ההחלטה · טיוטות והערות · סוכנים.
- New PositionsPanel — the chair's editing surface (threshold claims + issues
SubsectionCards + ChairEditor + background prose + case precedents + finish
rail), extracted verbatim from the former /compose "עמדות וטענות" tab. Drops
only the doc-strip (the overview DocumentsPanel is the sole owner — no dup).
- "טיעונים ועמדות" tab = PositionsPanel above + the aggregated by-party
LegalArgumentsPanel in a collapsible below.
- "אימות פסיקה" promoted to its own top-level tab (CitationVerificationPanel,
was /compose tab 3); placed BEFORE "ההחלטה" — verify citations, then write
(INV-AH: the writer cites only verified precedents).
- "ההחלטה" stays the single 12-block editor (DecisionBlocksPanel) — no longer
duplicated between /compose and the case page.
- Tabs are now controlled; the "פתח עורך החלטה" CTA switches to the ההחלטה tab
instead of navigating to the deleted route.
- /compose route deleted; header-context /compose special-case removed.
No duplication remains (G2): blocks editor single, docs single (overview),
citation-verify single. Design-gate: mockup 18f approved in Claude Design X17.
tsc --noEmit + eslint clean.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Implements the approved X17 case-detail redesign foundation (mockups 18c "A" +
18e "V2"):
- New StatusRail component — the integrated status strip (current-phase chip,
expected-outcome semantic tag, hearing/updated/sync meta inline, agents
Popover, manual-changer Popover) over the 5-phase pipeline stepper. Lives
INSIDE the parchment band (CaseHeader), so status is now visible on EVERY tab
(supersedes the overview-only StatusHero / reverses the prior INV-IA1
overview-only decision, deliberately).
- CaseHeader absorbs the rail and drops its separate hearing/updated/sync dl
(those moved into the rail — no duplication).
- Tabs restyled to the V2 "segmented" look (each tab a pill, active = raised
white card) with per-tab icons.
- Overview tab body is now just documents + agent-activity preview (status left
the body).
- StatusHero deleted — its content moved wholesale into StatusRail, so no
parallel status surface remains (G2).
Reuses the shared StatusChanger / StatusGuide / AgentStatusWidget verbatim
(G2). Design-gate: mockups 18c + 18e approved in Claude Design X17.
tsc --noEmit + eslint clean.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Set block-vav (בלוק ו', רקע/background) generation effort from medium to
low in BLOCK_CONFIG. The #208 empirical effort calibration
(scripts/calibrate_effort.py, report
data/eval/effort-calibration-20260630T155054Z.md, n=7 finals) found that
for block-vav, low effort lands closest to chair Dafna Tamir's finalized
text — winning on BOTH the composite distance metric (low 0.4454 vs
medium 0.4749 vs high 0.5381 vs xhigh 0.5413) AND the cleaner style
signal anti_pattern_total (low 1.57 vs medium 2.29 vs high 4.14). Chair
(chaim) approved adopting low for block-vav.
This is the only block with a clean/confident calibration signal —
block-zayin and block-yod-alef signals were ambiguous/tied and are left
unchanged. No other block effort is touched.
Invariants: G8 (effort empirically calibrated, not by-feel);
claude_session-local-only (block_writer runs via the local MCP/claude_local
generation path). Host-side generation parameter — after merge the host
tree needs `git pull` to take effect.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
A case parked on a status the trimmed PHASES list dropped — but the agents
still set, e.g. `analyst_verified` (HEARTBEAT.md), `research_complete`
(legal-researcher) — rendered with NO active phase: phaseIndexOf returned -1,
so the pipeline stepper went fully blank and the chair couldn't see where the
case stood (reported on 1043-02-26, currently at analyst_verified).
Add LEGACY_STATUS_PHASE in case-status.ts mapping each legacy/intermediate
status to its display phase (analyst_verified/research_complete → "ניתוח וכיוון"),
and a single phaseIndexOf() exported from the SSoT. status-hero.tsx and
workflow-timeline.tsx both dropped their identical local phaseIndexOf (which had
the bug) and import the shared one — no parallel path (G2).
Display-only data-mapping fix; the stepper design is unchanged. Does NOT address
the root drift (agents still set analyst_verified) — that prompt-alignment is a
separate, carefully-sequenced follow-up needing cross-company agent sync.
Invariants: G2 (single phase-resolution path, legacy handled in the SSoT, no
new parallel logic). No backend / status-model change.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The "אימות פסיקה" tab reloaded its data on every tab revisit and the first
load took 1.5–3s. Two independent causes, two fixes:
Frontend (web-ui/src/lib/api/citation-verification.ts):
- staleTime 10s → 5min and refetchOnMount: false. Radix Tabs unmounts inactive
TabsContent, so switching back used to trigger a full rebuild once the 10s
window elapsed. Verify mutations still invalidate the query, so edits pull
fresh data.
Backend (mcp-server/.../case_citation_verification.py):
- The per-argument loop ran a Voyage embed + vector search + batched authority
query sequentially (N args × ~300ms waterfall). Extracted to _fetch() and
fanned out with asyncio.gather — order preserved, n_verified counter and
per-argument seen-sets unchanged. First load ~5× faster on multi-argument cases.
Pure read/assembly — no new parallel path (G2), no silent error swallowing
(search/radar still log warnings). Invariants: INV-DIG1/INV-AH unaffected
(still read-only, never cites).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Backend follow-up to INV-UI9 (X6 §"אודיט-נלווה"): make server-side
datetimes explicit so flipping the container to TZ=Asia/Jerusalem cannot
silently skew stored or displayed timestamps. Storage stays UTC; human
display is Israel time.
- audit.py: naive datetime.utcnow() → datetime.now(timezone.utc) for the
TIMESTAMPTZ audit_log.created_at. Under TZ=Asia/Jerusalem the naive UTC
wall-clock would be read as Israel-local and stored ~3h off. (§6: no
silent skew.)
- calibrate_effort.py: _ts() report stamp now Israel-time via
ZoneInfo("Asia/Jerusalem") with a filename-safe "-IL" suffix (script runs
on the UTC host); added a labeled "שעון ישראל" line to the report header
so the chair-facing timestamp is unambiguous. --self-test still ALL PASS.
- research_md.py: display fields made deterministic Israel-tz —
update_chair_position timestamp (datetime.now(IL_TZ)) and parse() mtime
(datetime.fromtimestamp(..., tz=IL_TZ)) — correct regardless of process TZ.
Left intentionally Israel-local-day date.today()/year-cutoff call sites
untouched (drafting/party_claims_summary/block_writer/court_fetch_supreme)
— a Jerusalem committee wants the Israel calendar day; they resolve
correctly once TZ flips.
Invariants: INV-UI9 (store-UTC / display-Israel, server side); §6
(timezone-aware datetimes, no silent ~3h skew).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Storage stays UTC (DB TIMESTAMPTZ, API ISO-UTC) — only the display layer is
localized, and now deterministically: every timestamp renders pinned to
Asia/Jerusalem via a single Intl-based formatter, so SSR (UTC container) and
the browser agree on any runtime. No layout/visible-format change — only the tz.
- New single date formatter web-ui/src/lib/format-date.ts (G2): formatDate /
formatDateShort / formatDateLong / formatDateTime / formatDateTimeFull /
formatTime / formatIsoDate + Israel helpers getIsraelYear / israelDayKey /
israelMidnightMs / israelParts + formatRelative (long/short/tight wording).
- Routed all ad-hoc toLocaleDateString/toLocaleTimeString/toLocaleString +
hand-rolled new Date(...).get*() / toISOString().slice(0,10) timestamp call
sites (30 files) through it. Number toLocaleString left untouched.
- Spec: added INV-UI9 to docs/spec/X6 (UTC storage, Asia/Jerusalem display).
Display-only; no layout/design/IA change → Claude Design gate N/A.
Invariants: G2 (single date formatter, no parallel ad-hoc formatting), INV-UI9.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
A live calibration run crashed with no error handling and lost ~2h of work:
the per-cell loop in _run() reached block-yod (discussion), block_writer.write_block
raised ValueError("לא ניתן לכתוב בלוק דיון ללא כיוון מאושר…") because the discussion
block needs an approved direction calibration cases don't have, and since the report
was only written at the very end of main(), every completed generation was lost.
Three robustness fixes (no metric/scoring change — G2):
1. Drop block-yod from default CALIBRATABLE_BLOCKS — out of WS5 interim-draft scope
AND structurally non-calibratable standalone (needs brainstorm→approve_direction).
Kept in new VALID_BLOCKS so a user can still force it via --blocks block-yod.
2. Per-cell try/except in _run(): any single (case, block, effort) cell failure is
logged as a warning (case/block/effort/error) and skipped, never fatal —
defense-in-depth for a forced block-yod and for transient rate-limits mid-run.
3. Incremental persistence: _write_report flushes after each completed block (ts
threaded into _run), so a crash later in the grid never loses finished blocks.
JSON/MD shape unchanged — partial results omit not-yet-done blocks from by_block.
--self-test: ALL PASS (14/14). block-yod gone from --dry-run defaults.
Invariants — נוגע / מקיים:
- G8 (eval-harness robustness) — partial results persist; a single-cell failure is
non-fatal; the harness survives block-yod's missing-direction raise and rate-limits.
- G2 (מקור-מדידה יחיד) — no metric-path change; _score_cell / block_distance_to_final
/ recommend_effort / aggregate_cell untouched.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Regenerate src/lib/api/types.ts from the live production OpenAPI schema
after PR #358 (#202) added the read-only summarize_party_claims endpoints:
- GET /api/cases/{case_number}/research/party-claims-summary (read)
- GET /api/cases/{case_number}/research/party-claims-summary/download
- GET /api/cases/{case_number}/research/party-claims-summary/export-docx
The regen also picks up other endpoints that had drifted out of sync
(citation-verification, agents/reset, digest-radar, plans/fetch,
style-distance-history, scripts/{name}/run, canonical-halachot instances),
bringing the single generated client back in line with production.
Invariants: X6 (UI<->API contract kept in sync via the generated client),
G2 (single auto-generated client, no hand-edited parallel types).
tsc --noEmit passes clean.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
WS2b של עיצוב-מחדש זרימת-העבודה. מאפשר ניתוח כתב-הערר לבד ואז איחוד
מסמך-עיקרי שנוסף מאוחר, בלי force-delete גורף, עם diff ליו"ר.
- SCHEMA_V49: documents.claims_extracted_at + claims_extraction_status
(אירוע-חילוץ per-מסמך, לא נגזר מ-doc_type), + אינדקס חלקי
idx_documents_claims_pending. idempotent (ADD COLUMN IF NOT EXISTS).
V48 שמור ל-#357.
- claims_extractor חותם את המסמך אחרי שמירת/אי-מציאת טענות.
- db.primary_docs_not_analyzed (is_primary V47 + claims_extracted_at IS NULL)
+ mark_document_claims_extracted; _row_to_doc חושף claims_analyzed.
- reanalyze_claims (כלי-MCP): snapshot→חילוץ-מאחד רק למסמכים חדשים/לא-נותחו
(store_claims מחליף per-source ⇒ טענות אחרות נשמרות)→aggregate force=True
(מסלול קנוני, מוחק רק legal_arguments)→_impact_diff before↔after ליו"ר.
- workflow_status חושף primary_docs_not_analyzed + next-step.
- ספ: 02-data-model §2ג (דגל לא-נותח), 04-analysis-writing §1.3.
- 5 בדיקות-יחידה ל-_impact_diff/_snapshot (פונקציות טהורות).
Invariants:
- G1 (נרמול-במקור): claims_extracted_at נחתם בנקודת-החילוץ, claims_analyzed
נגזר ממנו — לא תיקון-בקריאה.
- G2 (מסלול קנוני יחיד / merge-not-fork): reanalyze מרחיב את מסלול
claims_extractor+argument_aggregator הקיים, לא forks; האיחוד דרך
store_claims per-source; aggregate force=True מוחק רק נגזר (legal_arguments).
- INV-DM (מודל-נתונים): דגל-אירוע per-מסמך, אינדקס חלקי, מקור-אמת יחיד.
- G10 (שער-אנושי): בדיקת-ההשפעה מוצגת ליו"ר, לא מוחלת אוטומטית.
- INV-TOOL idempotency: SCHEMA_V49 idempotent; ניתוח-מחדש חוזר על מסמך
כבר-נותח הוא refresh נקי (store_methods replace per-source).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Root cause (proven 2026-06-30, legal-ai #164): the comment-sweep wakes the CEO
via ctx.agents.invoke, which does NOT populate $PAPERCLIP_WAKE_REASON or
payload.issueId. The run transcript showed "generic heartbeat with no scoped
wake" — the CEO's `user_commented` branch never fired, it ran a generic
heartbeat that scans only CEO-assigned issues, and chair comments on
chaim/sub-agent-owned issues (e.g. CMPA-116) were invisible → no-op. Two real
6-day-stale chair requests sat undelivered.
Fix: on any wake without a scoped reason, the CEO must DISCOVER pending chair
comments itself. Adds "סריקת הערות-יו"ר תלויות (company-wide)":
- enumerate all active company issues (/api/companies/{id}/issues)
- pending = newest user comment newer than newest agent comment (ignore
system); order-independent sort_by(createdAt) since the API is newest-first
- MANDATORY case binding from the STRUCTURED project.name ("ערר <case> — …"),
never from the title (CMPA-116 has none) nor the comment content (which may
name a different case, e.g. "ניסיתי ב-CMPA-89"). No confident case → do NOT
act; escalate to chair.
- handle each pending comment scoped to its own $ISSUE_ID/$CASE_NUMBER
Verified end-to-end against live data: 13 active issues → exactly 2 pending
(CMPA-116, CMPA-89), both resolved to case 8125-09-24 via project.name, zero
false positives. Step 0 + Step A wired to run the scan on blind wakes.
Refs #164. Pairs with the plugin sweep (delivery) — this is discovery+action.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
