fix(api): change list_company_skills to return flat List[CompanySkillResponse] to fix frontend crash

feat: redesign UI to premium shadcn/ui with Canifa warm red/orange accents and translate company terms to Vietnamese departments (Phòng ban)

chore: Integrate Paperclip with FastAPI and resolve API case discrepancies, custom endpoints, and route issues

feat: migrate python backend, fix relative imports, fix adapter capabilities crash, and update README.md

- Add jsdiff v7.0.0 via CDN for Myers diff algorithm
- Side-by-Side view: dual pane with synced scrolling, line numbers
- Unified view: single pane with dual line number columns
- Color coded: green=added, red=removed, white=same, striped=empty
- Summary stats bar: identical/added/removed counts + char counts
- View mode toggle: switch between side-by-side and unified
- Replace old raw text dump with real diff computation

- Rewrite manage_prompt.css: larger fonts (14-16px), premium card layout, better spacing
- Cookbook sidebar: replace emoji with color-coded SVG Lucide icons per group
- Cookbook CSS: add proper pre/code/blockquote/heading styling for markdown content
- Support separator groups (no recipes) in sidebar navigation
- Add mermaid diagram container styles
- Light theme support for code blocks

feat(report-agent): complete hermes bridge integration, curator loop, multi-job cron, and e2e testing

- Reduce role_max_items from 20 to 2-3 to avoid duplicate items
- Simplify deduplicate logic to take top N by score
- Add outfit_pairing_data.json with 59 products and 250 pairings
- Add outfit-logic UI visualizer for fashion rules
- Fix main_router.py indentation for pairing_router

Includes:
- OPENAI_API_KEY for zunef gateway (OpenAI-compatible)
- DEFAULT_MODEL=claude-sonnet-4-6
- Optional ANTHROPIC_API_KEY for direct Anthropic API
- Other services (Redis, StarRocks, Langfuse)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

Inject English reminder message right before LLM call to force:
- All SKUs in response MUST be in product_ids
- Combo/set queries MUST return 5+ products
- Pick from suggest_items/ai_matches if tool returns <5
- Final self-check for (XXXXX) patterns
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

Add strict rules before JSON output:
- Any SKU in ai_response MUST be in product_ids
- For outfits: MUST include both Top + Bottom SKUs
- If tool returns <5 SP, MUST pick from suggest_items/ai_matches
- Self-check: scan ai_response for (XXXXX) before returning
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

Update discovery section to:
- Require 5-8 products (up from 3-5)
- Force TOP + BOTTOM for combo/set queries
- Encourage picking from suggest_items/ai_matches if tool returns <5
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

Move VD1 (combo di bien) to first example so Classifier
sees it before Early Exit section. Helps LLM trigger tool
for combo/set do queries.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

Force tool_name=lead_search_tool for:
- combo/set do/phoi do queries
- sale/giam gia/discount queries (set discount_min=1)
- moi nhat/new arrivals (set discovery_mode=new)
- best seller queries (set discovery_mode=best_seller)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

Prompt contains JSON examples with { } that confused .format().
Escape all braces first, then substitute only stage_injection.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

Cherry-pick commit 88341cc with conflict resolution in graph.py.
Replace with_structured_output with manual JSON parsing for Claude API.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

- Added hard_patterns.py: detect patterns (cheaper_than, more_expensive_than, similar_to) and extract reference product
- product_search_engine.py: integrate pattern detection, auto-set price_max/min based on reference price
- lead_search_tool.py: added user_insight parameter
- graph.py: pass user_insight to tool, removed product_ids filter (always return full tool result)
- prompts.py: added family/group intent examples, emphasize product_ids must include all items
- stylist_engine.py: added occasion and rule_id to matches, save to DB properly
- Added scripts: regenerate_matches.py and test_insert_one.py

Impact:
- Query 'rẻ hơn' auto sets price_max = ref_price * 0.95
- Query 'đắt hơn' auto sets price_min = ref_price * 1.05
- UI receives complete product list from tool (not truncated by AI)