Commit graph

23 commits

Author SHA1 Message Date
nickviljoen
bcd318a7b1 docs: update CLAUDE.md after Phases 1+2 (Dow Jones removed, demos added)
Updates the intro count (9 → 12 clients), adds Google/HP/Ferrero to
the client name list, and adds three table rows for the new demo
clients (Doc column marked _scope pending_ until per-client docs land).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-14 21:39:40 +02:00
nickviljoen
5860abf0f9 docs(dow-jones): update CLAUDE.md after offboarding
Removes the Dow Jones row from the client/profile table and the four
Dow Jones profile names from the pre-session profile-load checklist.
Also updates the intro paragraph counts (9 clients, 15 profiles, 60+
checks) and drops Dow Jones from the client name list, so the intro
no longer contradicts the table.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-14 21:14:30 +02:00
nickviljoen
a46ba9fc71 Split AXA accessibility check into its own profile
Removed axa_pdf_accessibility from axa_policy_document (was 8 checks, now 7)
and created a new axa_accessibility profile that contains only that check.
Marked the new profile strict_grade: true so a single PDF/UA-1 rule failure
forces an unmistakable Fail badge on the report — mirrors how axes4 PAC is
used in practice (single-purpose, binary verdict).

Lets users run accessibility-only QC without sitting through the rest of
the policy-document checks, and removes weight from the policy-document
score that the accessibility check wasn't really earning (its 0/10 verdict
was dragging the overall grade in a way that obscured the content checks).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-10 11:15:46 +02:00
nickviljoen
59a0b2408c Restructure CLAUDE.md docs: slim project-wide root, complete per-client coverage
Splits the monolithic CLAUDE.md (962 lines) into a slim project-wide root (211 lines)
plus per-client files. Auto-loaded context drops ~88% per session.

Changes:
- CLAUDE.md slimmed to project-wide essentials (architecture, auth, deployment, branch
  strategy, deploy scripts, prod troubleshooting, pre-session checklist). Adds explicit
  session-start convention pointing to CLAUDE_<CLIENT>.md for client-specific work.
  Updates client roster table to all 10 clients with profile counts.
- New CLAUDE_AXA.md: document-mode pipeline + axa_policy_document profiles
- New CLAUDE_DIAGEO.md: key_visual + packaging profiles, check inventories
- New CLAUDE_UNILEVER.md: profiles + zero-score logic for face/new visibility
- New CLAUDE_HONDA.md, CLAUDE_RANK.md, CLAUDE_GENERAL.md: stubs (clients use generic
  profiles only — kept for completeness and future expansion)
- backend/CLAUDE.md: stale 932-line duplicate replaced with 18-line redirect to root
  + backend-specific quick pointers

Per-client files (CLAUDE_LOREAL.md, CLAUDE_AMAZON.md, CLAUDE_BOOTS.md,
CLAUDE_DOW_JONES.md) unchanged — already had the right content.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-06 12:29:16 +02:00
nickviljoen
d8062aaa07 Refresh CLAUDE.md docs for v1.1.0
- Bump headline client count from 8 to 10 (added AXA + Rank).
- Refresh the Client Configuration tables to match client_config.py (10 rows, video_general listed across all entries).
- Flip the Prod row in the Deployment Environments table from "Not yet stood up" to "Live (currently v1.1.0)" and drop the matching "prod-to-come" wording.
- Bump the Pre-Session Completion Checklist from "all 8 clients" to "all 10 clients".
- Add a "Self-service Client Access Requests" section under Recent System Enhancements covering the new client-picker tile, /api/access_request + /api/all_clients endpoints, the email_service module, and a "Settings Modal UX (Apr 2026)" section covering the simplified Reference Assets / Media Plan tabs and the context-aware modal footer.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-27 14:43:30 +02:00
nickviljoen
d7d83cf90a Update CLAUDE.md with access control, environments, deploy scripts
- Bump stale counts to 14 profiles / 8 clients / 75 checks across
  overview, file structure, profile system, pre-session checklist.
- New section: User Access Control System (storage schema,
  user_access.py module surface, enforcement points, audit trail,
  frontend hooks).
- New section: Deployment Environments table (local/dev/prod/
  sandbox) with URLs, branches, servers, services, status.
- New section: Branch Strategy (develop→dev, main tags→prod,
  feature branches).
- New section: Deploy Scripts (deploy.sh, rollback.sh, health-check.sh).

Applied to both root CLAUDE.md and backend/CLAUDE.md.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-22 18:50:10 +02:00
nickviljoen
6f3528b54f Add Boots client QC profile with 5 compliance checks and split CLAUDE.md client docs
New boots_static profile (5 checks, 2.0 weight each) for retail promotional
artwork compliance: caveat rules, brand name accuracy (~170 names), offer
mechanics, T&C wording, and currency/locale. Strict grading override (any
check <6 = Fail). Guidelines embedded from 7 thematic guidance documents.

Also splits client-specific documentation out of CLAUDE.md into separate
CLAUDE_LOREAL.md, CLAUDE_AMAZON.md, CLAUDE_BOOTS.md, and CLAUDE_DOW_JONES.md
files to reduce main file size.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-13 09:25:58 +02:00
nickviljoen
fd5661f452 Update docs with L'Oreal text_product_overlap check and tuning round 3 results
L'Oreal Static profile: 3 checks → 4 checks (added text_product_overlap).
Total QC checks: 65 → 66. Documents prompt tuning decisions, detection
accuracy across both test sets, and known gaps.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-09 11:43:47 +02:00
nickviljoen
ff112c830e Update docs with L'Oreal prompt tuning round 2 results (2026-04-07)
Document text_readability neutral scoring for product-only shots,
background_contrast visibility-focused tuning, and test results
for 5 new L'Oreal Absolut Repair Molecular assets.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-07 19:25:48 +02:00
nickviljoen
5a57a8a064 Add Dow Jones client with 3 sub-brand QC profiles (17 new checks)
New client with embedded brand guidelines for Dow Jones Corporate,
MarketWatch, and Wall Street Journal sub-brands. Guidelines sourced
from live.standards.site scrapes and baked into check prompts.

- dow_jones_static: 5 checks (logo, color, typography, square motif, photography)
- marketwatch_static: 6 checks (logo, color, typography, image treatment, layout, art direction)
- wsj_static: 6 checks (logo, color tiers, typography, imagery, capitalization, layout)
- System now has 7 clients, 12 profiles, 65 QC checks

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-07 18:33:14 +02:00
nickviljoen
08b17508ba Add periodic auth session check and rename Amazon Box Placement to Element Placement
- Add silent auth check every 5 minutes to detect expired sessions proactively,
  showing a "Session Expired" prompt instead of failing silently on next action
- Rename amazon_box_placement to amazon_element_placement across module directory,
  profile config, class name, and documentation

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-02 10:01:27 +02:00
nickviljoen
53a8083b03 Update CLAUDE.md with L'Oreal prompt tuning session notes
Documents the L'Oreal Static profile revert to 3 checks, prompt
refinements for hidden/invisible text detection, test results from
both Gemini and OpenAI, and known gaps for future tuning.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-30 14:00:13 +02:00
nickviljoen
a1150268d6 Update CLAUDE.md with Amazon prompt tuning session notes
Documents the full Amazon QC prompt refinement process: test file
pairs and their specific defects, all prompt changes made, current
detection accuracy per LLM, and known gaps for future work.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-30 12:07:10 +02:00
nickviljoen
6333cdeb3e Update docs with PDF processing, media plans, and production notes
Document pdf_processor.py and media_plan_processor.py in main
components. Add detailed sections for PDF reference asset processing
and media plan system. Add production permissions fix to common
issues table.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-26 23:11:34 +02:00
nickviljoen
57b6c28848 Update documentation for new clients, profiles, and features
Update CLAUDE.md and README.md to reflect current system state:
- 48 QC checks (was 33), 9 profiles (was 6), 6 clients
- Document Amazon ASD 2025 tools, Boots client, L'Oreal static profile
- Document client-scoped reporting dashboard, admin panel, user tracking
- Update pre-session checklist with all 9 profiles and 6 clients
- Add client configuration table

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-26 13:30:10 +02:00
nickviljoen
8bc1256e82 Add usage tracking reports, profile versioning, and token tracking
Implements three major feature enhancements:

1. Usage Tracking Reports
   - Command-line tool (generate_usage_report.py) for comprehensive usage reports
   - Supports text, JSON, and CSV output formats
   - Filters by date range, client, and user
   - Aggregates statistics by client, user, profile, and date
   - Automated report generation via cron jobs

2. Profile Auto-Versioning & Visibility Control
   - Automatic version control: edits create new versions (v2, v3, etc.)
   - Original profiles preserved for rollback capability
   - Profile visibility control (all clients vs client-specific)
   - Client-profile relationship management with dynamic updates
   - Audit trail with timestamps and user tracking

3. Actual Token Usage Tracking
   - Captures real token counts from OpenAI and Gemini APIs
   - Precise cost calculations instead of estimates (99% accuracy)
   - Per-check and per-provider token breakdowns
   - Pricing validation tool (validate_pricing.py)
   - Token usage optimization recommendations

Key Files Added:
- backend/generate_usage_report.py - Usage report generator
- backend/validate_pricing.py - Pricing validation tool
- backend/USAGE_REPORTS.md - Usage reports documentation
- backend/PROFILE_MANAGEMENT.md - Profile versioning guide
- backend/TOKEN_TRACKING_ENHANCEMENT.md - Token tracking guide
- backend/PRICING_GUIDE.md - Pricing validation guide
- backend/NEW_FEATURES_QUICKSTART.md - Quick start guide
- IMPLEMENTATION_SUMMARY.md - Complete implementation overview

Key Files Modified:
- backend/api_server.py - Profile versioning, token passthrough
- backend/client_config.py - Visibility-aware profile filtering
- backend/llm_config.py - Token usage extraction from APIs
- backend/usage_tracker.py - Actual token tracking and cost calculation
- CLAUDE.md - Updated documentation with new features

Benefits:
- Accurate cost tracking with real token usage
- Safe profile editing with version history
- Flexible profile visibility for multi-tenant setup
- Comprehensive usage analytics for optimization
- Better budget forecasting and client billing

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
2026-02-02 13:22:33 +02:00
nickviljoen
e46c1d1435 Add comprehensive production deployment documentation
Added detailed troubleshooting guide covering critical production issues
encountered during deployment:

1. Web UI 404 Error Fix
   - Document absolute path requirement for serve_web_ui()
   - Explain why relative paths fail in production environments
   - Provide code examples for both root and backend api_server.py

2. Apache ProxyPass Configuration
   - Document static directory conflict with ProxyPass rules
   - Explain Apache's file-first, proxy-second behavior
   - Provide solution: remove conflicting static directories
   - Include proper ProxyPass ordering (specific paths before general)

3. MSAL Authentication Error Fix
   - Document interaction_in_progress error and root causes
   - Explain concurrent sign-in prevention implementation
   - Include storage cleanup and proper flag reset patterns

4. Production Deployment Checklist
   - Step-by-step deployment verification process
   - Backend testing commands
   - Apache proxy testing commands
   - Browser testing best practices

5. Common Production Issues Table
   - Quick reference for troubleshooting
   - Check commands for each issue
   - Solutions for common problems

This documentation ensures future deployments avoid the same pitfalls
and provides clear guidance for troubleshooting production issues.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-11-06 23:23:02 +02:00
nickviljoen
3c97267d68 Updated README File 2025-09-12 16:45:31 +02:00
nickviljoen
355be50b23 Bug fixes, profile updates, report updates 2025-08-23 14:44:17 +02:00
nickviljoen
e5d36cac82 Updated SSO error, Updated Unilever Profile scoring weighting, updated output file list order 2025-08-21 17:27:11 +02:00
nickviljoen
5243ad4ae3 SSO Added 2025-08-20 15:30:29 +02:00
michael
ea7bcf5747 modified claude.md to test python and excluded venv from .gitignore 2025-08-14 08:45:29 -05:00
michael
c3b0c37ed4 initial commit 2025-08-12 14:52:49 -05:00