Adds two orthogonal columns — practice_area (top-level legal domain:
appeals_committee / national_insurance / labor_law) and appeal_subtype
(building_permit / betterment_levy / compensation_197) — denormalized
into cases, documents, document_chunks, decisions, and style_corpus so
vector searches can filter without JOINs.
Why: the system handles two unrelated sub-domains under the same
appeals committee (1xxx building permits and 8xxx/9xxx betterment/197),
with different rules and writing style. Without a separation axis,
search_similar() and the block-writer's precedent lookup were free to
surface betterment-levy paragraphs while drafting a building-permit
decision — a real risk of cross-domain contamination. The same axis
also lets future domains (national insurance, labor law) coexist
without separate schemas.
Schema (V4 migration in db.py):
- ALTER ... ADD COLUMN IF NOT EXISTS on all five tables + composite
indexes (practice_area first).
- Idempotent backfill: case_number ~ '^1' → building_permit, '^8' →
betterment_levy, '^9' → compensation_197; propagated to documents,
chunks, and decisions via case_id; training-corpus rows (case_id NULL)
default to appeals_committee.
Code:
- New services/practice_area.py with derive_subtype, validate, and
is_override + enum constants.
- db.create_case / create_document / store_chunks / create_decision
inherit practice_area from the parent case (or take an explicit
override for the case_id=None training corpus).
- db.search_similar and search_similar_paragraphs accept practice_area
+ appeal_subtype filters using the denormalized columns.
- tools/search.py auto-resolves the filter from case_number when given.
- block_writer._build_precedents_context now passes the active case's
practice_area to search_similar_paragraphs — closes the contamination
hole for the discussion-block precedent fetch.
- tools/cases.case_create auto-derives subtype from case_number; an
explicit override that disagrees writes a case_subtype_override entry
to audit_log so we can spot bad classifications later.
- tools/documents.document_upload_training tags new training material
with practice_area + subtype end-to-end (corpus, document, chunks).
UI (web/static/index.html + web/app.py):
- New-case wizard gets a practice_area dropdown (others disabled until
national_insurance / labor_law arrive) and an appeal_subtype dropdown
with JS auto-fill from the case-number prefix; manual edits stick.
- Case header shows a blue badge with practice_area · subtype.
- CaseCreateRequest plumbs both fields through to cases_tools.case_create.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
New UploadSheet on the case detail page wraps react-dropzone + a
selector for doc_type. Files post to
POST /api/cases/{n}/documents/upload-tagged as multipart form-data;
the returned task_id is streamed via GET /api/progress/{task_id}
through the new lib/sse.ts EventSource wrapper.
Each upload row shows a per-file progress bar that transitions to
success/error on the terminal SSE payload. Closing the stream inside
the message handler avoids EventSource's auto-reconnect after EOF.
Phase 4 (task 86) is now complete end-to-end: create, upload, edit.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
New /cases/new route with a 3-step wizard (basics / parties / details)
backed by react-hook-form + the caseCreateSchema. Each step validates
only its own fields so the user fixes errors in context. On success
useCreateCase invalidates the case list and the router pushes to the
freshly created case detail page.
PartiesField is a small chip-style editor for the appellants/respondents
arrays. The Home page now has a navy "+ תיק חדש" button that links to
the wizard.
Dropped .default() from the create schema — zod's input/output type
mismatch broke the RHF zodResolver generics; dropping the defaults is
simpler than plumbing z.input vs z.output through the mutation hook.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Add dialog/select/textarea/label/progress/sonner components and wire
a Toaster into Providers. New zod schemas in lib/schemas/case.ts
mirror CaseCreateRequest/CaseUpdateRequest and feed react-hook-form
validation.
CaseEditDialog on the case detail Actions tab posts PUT /api/cases/{n}
with optimistic cache patching via useUpdateCase, showing toast
feedback on success/error.
shadcn's <Form> registry entry skipped at init (missing from the
nova preset); the dialog uses RHF directly against the same Input/
Textarea/Select primitives.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
New /cases/[caseNumber]/compose route ports the research analysis +
chair-position editing flow from the vanilla UI onto the Next.js
stack. Reads /api/cases/{n}/research/analysis, renders background
prose in the side column and threshold claims + issues as collapsible
cards in the main column, each with a blur-autosaved chair editor
wired through a TanStack Query mutation with optimistic cache patching
(so concurrent reads don't steal editor focus).
Handles the common "analysis not yet generated" 404 with a dedicated
empty state rather than an error card.
Phase 3 task 85 is now ready for review end-to-end.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
New dynamic route /cases/[caseNumber] wired to the FastAPI details
endpoint, using Next 16's async params pattern with React's use()
hook. TanStack Query handles 5s refetchInterval so the page
self-updates during long-running processing without manual polling.
New components: CaseHeader (breadcrumb + meta), WorkflowTimeline
(5-phase RTL pipeline view), DocumentsPanel (categorized list).
Tabs split overview/documents/actions.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Initialize shadcn/ui (radix-nova preset) and wire its semantic tokens
to the editorial navy/cream/gold palette so primitives inherit the
judicial voice without per-component overrides.
Replace the Phase 2 live-probe with a real dashboard: KPI tiles,
conic-gradient status donut (ported from the vanilla renderHero),
and a TanStack Table cases list with search + sort. Add useCase(n)
hook with 5s staleTime/refetchInterval to replace the old manual
polling loop when Case Detail ships next.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- create-next-app with TypeScript, Tailwind v4, App Router
- Port design-system.css tokens into Tailwind @theme (navy/gold/parchment, Heebo)
- Install TanStack Query, react-hook-form, zod, lucide-react, react-dropzone
- layout.tsx: RTL Hebrew + Heebo via next/font/google
- AppShell component with navy header + gold rule + nav
- next.config.ts: output:standalone + rewrites to proxy /api/* to production FastAPI
- Dockerfile: multi-stage Node 20 Alpine build for Next.js standalone
(branch-local override of the FastAPI Dockerfile; main is unaffected)
- Switch .taskmaster to claude-code provider (no API key required)
- Add 7 phase tasks (83-89) tracking the full rewrite plan
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The home page already has a prominent '+ תיק חדש' button in the hero.
Cases are always opened by clicking a case card on the home list, so
the top-nav link is noise. Keyboard shortcut 'n' still opens the
wizard directly for power users.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Closes the loop so דפנה's positions (written inline in the UI and
saved to analysis-and-research.md) automatically become binding
direction for the legal-writer agent — no manual copy-paste,
no bypass.
Backend:
- research_md.extract_chair_directions(path) returns a compact dict
with status (missing/empty/partial/complete), filled_count,
empty_count, and a reduced list of threshold_claims + issues each
with {id, number, title, direction}. Designed to be directly usable
as direction_doc by the writer.
- New MCP tool: drafting.get_chair_directions(case_number) wraps the
helper, resolves the case research file path via config.find_case_dir,
returns formatted JSON.
- Registered in server.py as mcp__legal-ai__get_chair_directions.
legal-writer agent update:
- Adds get_chair_directions to the tools list.
- New mandatory "שלב 1ב" before any block writing: call
get_chair_directions, branch on status.
- missing → halt, report "legal-analyst לא רץ עדיין"
- empty → halt, instruct Dafna to fill positions via the UI URL
- partial → halt unless user confirms; write only filled sections
- complete → proceed
- New "שלב 1ג" constructs an internal direction_doc from the
received chair rulings before writing block י.
- Block י section expanded with 5 binding rules:
1. Open each discussion with Dafna's ruling as the thesis
2. Frame the reasoning in her style (use get_style_guide phrases)
3. Match her tone (decisive vs nuanced)
4. Must NOT contradict her position — if she disagreed with your
own inclination, her position rules
5. Use legal_questions from the analysis file as the analytical
structure (principle question first, concrete application second)
- New bullet section for block יא: summarize each chair ruling
briefly, state final outcome, close with the signed date formula.
Verified all four status paths (missing/empty/partial/complete) via
local test. Now Dafna's workflow is fully end-to-end: she reads the
analyst report in the UI, fills "עמדת ועדת הערר" in each card, hits
blur to auto-save, then triggers legal-writer — which picks up her
positions as direction without any file shuffle.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
New feature on case view: the analysis-and-research.md produced by the
legal-analyst agent is now rendered as structured cards in the UI,
with inline editing of "עמדת ועדת הערר" that writes directly back to
the markdown file (atomic rename).
Backend (research_md.py):
- parse(Path) → dict with header, prose sections, threshold_claims[],
issues[], conclusions, other_sections
- Tolerant field extractor handles both block ("**LABEL:**\ncontent")
and inline ("**LABEL:** content") variants
- Detects [ימולא ע"י יו"ר הוועדה] placeholder → empty chair_position
- update_chair_position(path, section_id, text) locates the exact
subsection by ordinal, replaces or appends the chair field, writes
atomically via temp file + os.replace
- Section IDs: threshold_N / issue_N (1-based)
Endpoints:
- GET /api/cases/{n}/research/analysis — returns parsed JSON or 404
- PATCH /api/cases/{n}/research/analysis/chair-position — {section_id, position}
Frontend (#page-case):
- New card "ניתוח משפטי ומחקר" below local-files card
- Prose sections as justified text panels (background + gold border)
- Threshold claims and issues as collapsible <details> items with
gold right-border on open, numbered pills
- Each item shows all extracted fields with label above content
- Chair position editor: gold-wash background, 📝 icon label, textarea
with placeholder prompt
- onblur → PATCH with save indicator: ⏳ שומר → ✓ נשמר HH:MM → fade
- Status pill next to each item title: "ממתין לעמדה" / "✓ עמדה נקבעה"
- First threshold claim opens by default, rest closed
- Card hidden entirely when no analysis file exists (404)
Tested against real file: case 1033-25 with 3 threshold claims and
6 issues, all chair positions correctly empty, update writes only the
targeted section, atomic rewrite preserves all other content.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Document titles are '[קורפוס] ARAR-23-1188 - ...' but decision_number
is '1188/23' — previous LIKE %1188/23% wouldn't match. Now extracts
the first numeric segment and matches against title.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Dark mode:
- body.dark overrides CSS variables (navy→cream reverse)
- Persisted in localStorage, applied before paint to avoid flash
- Toggle button in nav (moon/sun icon), Shift+D shortcut
Keyboard shortcuts:
- g h/n/u/t/s/c/w/d/k for page navigation
- n for new case, ? for help (Shift+/)
- Esc closes any open dialog, blurs focused input
- Help modal via showShortcutsHelp() with styled kbd elements
SSE tasks stream:
- /api/system/tasks/stream pushes snapshots whenever _progress changes
- Client uses EventSource instead of 3s polling
- Auto-reconnect after 5s on error
- 15s heartbeat keeps proxies alive
Compare decisions (new #/compare page):
- /api/training/compare?a=id&b=id serializes both decisions' metadata,
section breakdown from document_chunks, and three buckets of patterns
(only in A, only in B, shared) using variant matching
- Two-column header with section-length breakdown + patterns count
- Three-column diff row (only_a / shared / only_b)
Compose with suggestions (new #/compose page):
- Large RTL justified textarea with Hebrew display font title input
- Sidebar lists all 47 style_patterns grouped by type with filter chips
- Click a pattern → inserts at cursor, replacing [placeholders] with ___
- Live section guess (פתיחה / רקע / טענות / דיון / סוף דבר) based on
most-recent 400 chars
- Auto-save draft to localStorage every second; restore on page load
- "העתק טקסט" copies title+body to clipboard
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Case view:
- Header card gets gold right-border, serif display title, pill-style
action links with gold hover
- Document groups: gold-underlined section headers, hover rows with
parchment background
Wizard (new case):
- Step tabs in display font with separators; active/done states use
navy/success colors with proper background contrast
- Nav buttons separated by hairline divider
Skills page:
- Pill badges for ok/warn, gold icon, hover elevation
Upload zone:
- Larger dashed border, serif header, gold-wash hover state
Loading skeletons:
- .skeleton / .skeleton-line classes with shimmer animation
- Case list shows 3 skeleton cards while loading
- Style report shows skeleton hero while loading
Empty states:
- Case list gets ornamental ❦ + emotional copy in display font
- Error messages include underlying error detail
Print stylesheet:
- Hides header/nav/sidebar/buttons
- Forces card borders and page-break-inside for portrait printing
- Expands details elements so content prints
Responsive:
- Mobile: simplified hero, narrower process panel, wrapping header
- Tablet: home grid collapses to single column
Fixes:
- DONUT_COLORS reverts to hex literals (was var(--color-gold) string
which doesn't interpolate in conic-gradient reliably across browsers)
- Sig-phrase headline now prefers clean phrases over template-heavy ones
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- DELETE /api/training/corpus/{id} + delete button on training page,
with confirmation dialog and recompute hint
- /api/system/tasks + floating process panel (bottom-left) showing
active background tasks with live 3s polling
- /api/system/recent-activity derives a feed from cases, style_corpus,
and last style_patterns run; sidebar on home page renders with
relative timestamps
- /api/system/diagnostics + /#/diagnostics page showing DB health,
row counts per table, active tasks, stuck documents (>10 min),
failed extractions
- Cosmetic: signature phrase headline now prefers clean phrases over
bracket-heavy templates for display
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Replaces Frank Ruhl Libre + Assistant with single-family Heebo for both
display and body. Weight contrast (900/700 for headings, 400 for body,
300 for light captions) provides the hierarchy. Single font family reduces
network requests and renders consistently.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- New design-system.css: CSS variables for Navy/Cream/Gold palette,
Frank Ruhl Libre (display) + Assistant (body) typography via Google Fonts,
spacing/shadow/motion tokens, RTL-safe utilities
- All body paragraphs justify to both sides (text-align: justify, inter-word)
- Existing inline <style> migrated from hardcoded #e94560/#1a1a2e/#27ae60 to
CSS variables
- Header: deep navy with gold accent rule under, display-font brand mark,
active nav link marked with gold underline
- Buttons: navy primary, gold-wash focus rings, elevation on hover
- Case cards: gold right-border, hairline top glow on hover, display font
on case number
- Home dashboard: new hero with eyebrow/title/subtitle, 4 KPI cards with
gold-rule side marker, loadKPIs() fetches case count, corpus size,
pattern count, processing queue
- Style report: larger hero h1, ornamental pull-quote headline with
drop-cap open quote, gold divider under section titles
- Toast, status bar, form inputs: navy/gold palette, serif italics for
subtitles and empty states
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Visual dashboard at #/style-report with 4 sections:
- Hero: 24 decisions, char counts, subject donut, timeline
- Anatomy: average section-length breakdown (intro → ruling → conclusion)
- Signature Phrases Wall: pattern cards with real corpus frequencies, filter
chips by type, click → modal with examples
- Contribution: per-decision "new vs confirmed" patterns, growth curve SVG
Backend:
- /api/training/style-report endpoint computes all 4 sections in one call
- Headlines in Hebrew are computed server-side from real data
- Backfill script for style_patterns.frequency using _strip_nikud +
pattern-variant extraction (templates with [placeholders], / alternatives,
ellipsis all handled)
Real findings from the 24-decision corpus:
- דיון משפטי = 49% of avg decision (the focus)
- 23/24 use "לפנינו ערר" opening formula
- 21/24 use "ניתנה פה אחד" closing
- After 7 decisions we already learned 85% of her style patterns
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- New proofreader service strips Nevo editorial additions (front matter,
postamble, page headers, watermarks, inline codes) from DOCX/PDF/MD
- PDF pages use Google Vision OCR for clean Hebrew RTL extraction
- New training page at #/training with drag-and-drop upload, automatic
metadata extraction (decision number, date, categories), reviewable
preview, and style pattern report grouped by type
- API endpoints: /api/training/{analyze,upload,corpus,patterns,
analyze-style,analyze-style/status}
- Fix claude_session.query to pipe prompt via stdin, avoiding ARG_MAX
overflow when analyzing 900K+ char corpus
- CLI scripts for batch proofreading and corpus upload
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Add "עמדת ועדת הערר" placeholder to legal-analyst agent template
for each legal issue, to be filled by the chair as guidance for the
writing agent
- Fix green checkmark not showing for proofread documents (treat
'proofread' status same as 'completed')
- Show time alongside date in local files listing
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Add cases symlink, Google Vision extraction and benchmark
embedding data, and Paperclip bug report.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Add delete_document_chunks for reprocessing, save extracted text to disk
- Expand case directory structure (original/extracted/proofread/backup)
- Update classifier patterns (תגובה, הודעת עמדה)
- Fix proofreader agent paths for new directory layout
- Update HEARTBEAT to notify on every task completion
- Improve bidi_table with LRE/PDF directional embedding
- Add Paperclip project verification and auto-close setup issue
- Add auto-sync-cases.sh for Gitea synchronization
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Documents with extraction_status='proofread' were incorrectly shown
as "in processing" on the case list page.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- New API endpoint /api/cases/{num}/local-files lists files from disk
- New API endpoint /api/cases/{num}/local-files/{folder}/{file} serves file content
- Case view now shows research/analysis files, proofread texts, and draft decisions
- Files are clickable and open in new tab
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Remove cases/new|in-progress|completed subdivision (status managed in DB)
- Rename documents/original → documents/originals (consistent plural)
- Move exports from global data/exports/ into cases/{num}/exports/
- Add documents/research/ for case law and analysis files
- Update all agents, scripts, config, web API endpoints, and DB paths
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Benchmark on case 1130-25 (4 Hebrew legal docs, 8 queries) showed:
- voyage-law-2: avg top-1 score 0.5839 (+27% over voyage-3-large)
- voyage-4-large: avg top-1 score 0.4119 (worse than current)
- voyage-3-large: avg top-1 score 0.4589 (baseline)
voyage-law-2 costs ~4.6x more per run but delivers significantly
better retrieval quality for Hebrew legal text. Model is now
configurable via VOYAGE_MODEL env var.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- POST /api/admin/skills/{slug}/sync — read SKILL.md from disk, insert/update DB
- DELETE /api/admin/skills/{slug} — remove skill from DB (keeps disk files)
- UI: Sync/Re-sync and Delete buttons per skill in the skills list
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- POST /api/admin/skills/install — upload ZIP, extract to skills dir, update DB
- GET /api/admin/skills — list installed skills with DB/disk sync status
- POST /api/admin/paperclip/restart — restart Paperclip (pm2 or flag file)
- New Skills page in web UI with drag-and-drop ZIP upload
- Coolify volume mount for /paperclip-skills
- Host-side crontab watcher for restart flag file
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Export DOCX now saves to data/exports/{case_number}/ with auto-versioning
(טיוטה-v1, v2...). The case view UI shows all drafts with download buttons,
allows uploading revised versions (עריכה-v1...), and marking a version as
final (copies to training corpus for style learning).
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
legal-ai MCP server now configured globally for all Claude Code sessions,
including Paperclip agents.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
New: scripts/notify.py — sends via SMTP (notify@marcus-law.co.il → paperclip+chaim@marcus-law.co.il)
Updated: HEARTBEAT.md — agents must send email when waiting for human decision
Triggers: outcome choice, direction approval, QA failures, review ready.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
All agent output — comments, status, errors, summaries, thinking — must be in Hebrew.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Two issues that caused QA agent to fail:
1. save_block_content saved to DB only — now also rebuilds drafts/decision.md
2. legal-writer.md now has explicit mandatory step: case_update(status="drafted")
Without these, workflow_status reports has_draft=false and QA can't run.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Paperclip moved back from Docker to pm2 on host.
Reverts c83dcd6 (Docker migration URL change).
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Paperclip moved from embedded PG (localhost:54329) to Coolify-managed
PostgreSQL container (10.0.2.13:5432).
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
brainstorm_directions tool uses claude -p subprocess which times out
when called from inside a claude session (agent). CEO should think
about directions directly — it already has all the context.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
CEO now follows a step-by-step interactive flow:
A. Check status and what's been done
B. Summarize case + ask Chaim for outcome (1/2/3)
C. Read response, run brainstorm, present directions
D. Read direction choice, approve, launch writer agent
E. Monitor writing progress
F. QA and export
All interaction happens through Paperclip comments.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Manages the decision writing pipeline:
- Creates issues and assigns to specialist agents
- Tracks status across all active cases
- Reports to human (Chaim) when approvals needed
- Never writes or analyzes directly — delegates
All 4 specialist agents now report to CEO.
Hierarchy: עוזר משפטי → מנתח/חוקר/כותב/בודק
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Symlinked to Paperclip instructions directory for each agent.
Single source of truth: .claude/agents/ files → symlinked to Paperclip.
Cleaned duplicate soul_md from DB metadata.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Complete agent pipeline for decision writing:
1. legal-analyst (existing) — extract claims/responses/replies
2. legal-researcher (new) — analyze precedents, plans, protocols
3. legal-writer (new) — write decision blocks in Dafna's style
4. legal-qa (new) — validate before export (6 checks)
All agents use claude_local adapter (Claude Code session, zero API cost).
Each has YAML frontmatter with specific tools and detailed Hebrew instructions.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Defines the agent's role, tools, document type rules, and workflow.
Linked to Paperclip agent via --agent legal-analyst extraArg.
Key rules:
- Claims only from appeal docs, responses from response docs, replies from supplementary
- Never extract from precedents, plans, or protocols
- Must report results to Paperclip before finishing
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
New module claude_session.py provides query() and query_json() that
run prompts via `claude -p` CLI — uses the claude.ai session, zero API cost.
Converted 6 services:
- claims_extractor.py: extract_claims_with_ai
- brainstorm.py: brainstorm_directions
- block_writer.py: write_block (was streaming+thinking, now simple)
- qa_validator.py: claims_coverage check
- style_analyzer.py: 3 API calls (single pass, multi pass, synthesis)
- learning_loop.py: extract_lessons
Only extractor.py still uses Anthropic API (for PDF OCR with Vision).
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
