#!/usr/bin/env python3
"""
Optimize AGENTS.md by condensing verbose rules into summaries with .opencode references.

This script:
1. Preserves header (lines 1-23)
2. Condenses rules 0-34 (lines 24-2775) into enhanced summaries with .opencode references
3. Preserves all unique reference content (lines 2776-5332) in full
"""

import re
from pathlib import Path

# Enhanced rule mappings with more detail for key rules
RULE_CONTENT = {
    0: """### Rule 0: LinkML Schemas Are the Single Source of Truth

🚨 **CRITICAL**: LinkML schema files in `schemas/20251121/linkml/` are the authoritative definition of the Heritage Custodian Ontology.

**Key Points**:
- ALL derived files (RDF, TypeDB, UML) are GENERATED - never edit them directly
- Always use full timestamps (`YYYYMMDD_HHMMSS`) in generated filenames
- Primary schema: `schemas/20251121/linkml/01_custodian_name.yaml`

**Workflow**:
```
1. EDIT LinkML schema
2. REGENERATE: gen-owl → rdfpipe → all 8 RDF formats
3. REGENERATE: gen-yuml → UML diagrams
4. UPDATE: TypeDB schema (manual)
5. VALIDATE: linkml-validate
```

**See**: `.opencode/SCHEMA_GENERATION_RULES.md` for complete generation rules

---
""",

    1: """### Rule 1: Ontology Files Are Your Primary Reference

🚨 **CRITICAL**: Before designing any schema, class, or property, consult base ontologies.

**Required Steps**:
1. READ base ontology files in `/data/ontology/`
2. SEARCH for existing classes and properties
3. DOCUMENT your ontology alignment with rationale
4. NEVER invent custom properties when ontology equivalents exist

**Available Ontologies**:
- `tooiont.ttl` - TOOI (Dutch government)
- `core-public-organisation-ap.ttl` - CPOV (EU public sector)
- `schemaorg.owl` - Schema.org (web semantics)
- `CIDOC_CRM_v7.1.3.rdf` - CIDOC-CRM (cultural heritage)
- `RiC-O_1-1.rdf` - Records in Contexts (archival)
- `pico.ttl` - PiCo (person observations)

**See**: `.opencode/HYPER_MODULAR_STRUCTURE.md` for complete documentation

---
""",

    2: """### Rule 2: Wikidata Entities Are NOT Ontology Classes

🚨 **CRITICAL**: Files in `data/wikidata/GLAMORCUBEPSXHFN/` contain Wikidata Q-numbers for institution TYPES, NOT formal ontology class definitions.

**Workflow**: `Wikidata Q-number → Analyze semantics → Search ontologies → Map to ontology class → Document rationale`

**Note**: Full rule content preserved in Appendix below (no .opencode equivalent).

---
""",

    3: """### Rule 3: Multi-Aspect Modeling is Mandatory

🚨 **CRITICAL**: Every heritage entity has MULTIPLE ontological aspects with INDEPENDENT temporal lifecycles.

**Required Aspects**:
| Aspect | Ontology Class | Temporal Example |
|--------|---------------|------------------|
| Place | `crm:E27_Site` | Building: 1880-present |
| Custodian | `cpov:PublicOrganisation` | Foundation: 1994-present |
| Legal Form | `org:FormalOrganization` | Registration: 1994-present |
| Collections | `rico:RecordSet` | Accession dates vary |
| People | `pico:PersonObservation` | Employment: 2020-present |
| Events | `crm:E10_Transfer_of_Custody` | Discrete timestamps |

**Note**: Full rule content preserved in Appendix below (no .opencode equivalent).

---
""",

    4: """### Rule 4: Technical Classes Are Excluded from Visualizations

🚨 **CRITICAL**: Some LinkML classes exist solely for validation (e.g., `Container` with `tree_root: true`). These have NO semantic significance and MUST be excluded from UML diagrams.

**Excluded Classes**: `Container` (tree_root for validation only)

**See**: `.opencode/LINKML_TECHNICAL_CLASSES.md` for complete documentation

---
""",

    5: """### Rule 5: NEVER Delete Enriched Data - Additive Only

🚨 **CRITICAL**: Data enrichment is ADDITIVE ONLY. Never delete or overwrite existing enriched content.

**Protected Data Types**:
| Source | Protected Fields |
|--------|------------------|
| Google Maps | `reviews`, `rating`, `photo_count`, `popular_times`, `place_id` |
| OpenStreetMap | `osm_id`, `osm_type`, `osm_tags`, `amenity`, `heritage` |
| Wikidata | `wikidata_id`, `claims`, `sitelinks`, `aliases` |
| Website Scrape | `organization_details`, `collections`, `contact`, `social_media` |
| ISIL Registry | `isil_code`, `assigned_date`, `remarks` |

**See**: `.opencode/DATA_PRESERVATION_RULES.md` for complete documentation

---
""",

    6: """### Rule 6: WebObservation Claims MUST Have XPath Provenance

🚨 **CRITICAL**: Every claim extracted from a webpage MUST have an XPath pointer to the exact location in archived HTML. Claims without XPath provenance are FABRICATED.

**Required Fields**:
```yaml
claim_type: full_name
claim_value: "Institution Name"
source_url: https://example.org/about
retrieved_on: "2025-11-29T12:28:00Z"
xpath: /html/body/div[1]/h1
html_file: web/GHCID/example.org/rendered.html
xpath_match_score: 1.0
```

**Scope**: Applies to `WebClaim` and `WebObservation` classes. Other classes (LinkupTimelineEvent, GoogleMapsEnrichment) have different provenance models.

**See**: `.opencode/WEB_OBSERVATION_PROVENANCE_RULES.md` for complete documentation

---
""",

    7: """### Rule 7: Deployment is LOCAL via SSH/rsync (NO CI/CD)

🚨 **CRITICAL**: NO GitHub Actions. ALL deployments executed locally via SSH and rsync.

**Server**: `91.98.224.44` (Hetzner Cloud)

**Two Frontend Apps** (MONOREPO):
| Domain | Local Directory | Server Path |
|--------|-----------------|-------------|
| bronhouder.nl | `/frontend/` | `/var/www/glam-frontend/` |
| archief.support | `/apps/archief-assistent/` | `/var/www/archief-assistent/` |

**Deployment Commands**:
```bash
./infrastructure/deploy.sh --frontend  # bronhouder.nl
./infrastructure/deploy.sh --data      # Data files only
./infrastructure/deploy.sh --status    # Check server
```

**See**: `.opencode/DEPLOYMENT_RULES.md` and `.opencode/MONOREPO_FRONTEND_APPS.md`

---
""",

    8: """### Rule 8: Legal Form Terms MUST Be Filtered from CustodianName

🚨 **CRITICAL**: Exception to emic principle - Legal forms are ALWAYS filtered from CustodianName.

**Examples**: `Stichting Rijksmuseum` → CustodianName: `Rijksmuseum`, Legal Form: `Stichting`

**Terms to Filter** (by language):
- Dutch: Stichting, B.V., N.V., Coöperatie
- English: Foundation, Inc., Ltd., LLC, Corp.
- German: Stiftung, e.V., GmbH, AG
- French: Fondation, S.A., S.A.R.L.

**NOT Filtered** (part of identity): Vereniging, Association, Society, Verein

**See**: `.opencode/LEGAL_FORM_FILTERING_RULE.md` for complete documentation

---
""",

    9: """### Rule 9: Enum-to-Class Promotion - Single Source of Truth

🚨 **CRITICAL**: When an enum is promoted to a class hierarchy, the original enum MUST be deleted. Never maintain parallel enum/class definitions.

**Archive Location**: `schemas/20251121/linkml/archive/enums/`

**See**: `.opencode/ENUM_TO_CLASS_PRINCIPLE.md` for complete documentation

---
""",

    10: """### Rule 10: CH-Annotator is the Entity Annotation Convention

🚨 **CRITICAL**: All entity annotation follows `ch_annotator-v1_7_0` convention.

**9 Hypernym Types**: AGT (Agent), GRP (Group), TOP (Toponym), GEO (Geometry), TMP (Temporal), APP (Appellation), ROL (Role), WRK (Work), QTY (Quantity)

**Heritage Institutions**: `GRP.HER` with GLAMORCUBESFIXPHDNT subtypes (GRP.HER.MUS, GRP.HER.LIB, GRP.HER.ARC, etc.)

**See**: `.opencode/CH_ANNOTATOR_CONVENTION.md` for complete documentation

---
""",

    11: """### Rule 11: Z.AI GLM API for LLM Tasks (NOT BigModel)

🚨 **CRITICAL**: Use Z.AI Coding Plan endpoint, NOT regular BigModel API.

**Configuration**:
- API URL: `https://api.z.ai/api/coding/paas/v4/chat/completions`
- Environment Variable: `ZAI_API_TOKEN`
- Models: `glm-4.5`, `glm-4.5-air`, `glm-4.5-flash`, `glm-4.6`
- Cost: Free (0 per token)

**See**: `.opencode/ZAI_GLM_API_RULES.md` for complete documentation

---
""",

    12: """### Rule 12: Person Data Reference Pattern - Avoid Inline Duplication

🚨 **CRITICAL**: Person profiles stored in `data/custodian/person/entity/`. Custodian files reference via `person_profile_path` - NEVER duplicate 50+ lines of profile data inline.

**File Naming**: `{linkedin-slug}_{ISO-timestamp}.json`

**See**: `.opencode/PERSON_DATA_REFERENCE_PATTERN.md` for complete documentation

---
""",

    13: """### Rule 13: Custodian Type Annotations on LinkML Schema Elements

🚨 **CRITICAL**: All schema elements MUST have `custodian_types` annotation with GLAMORCUBESFIXPHDNT single-letter codes.

**Annotation Keys**: `custodian_types` (list), `custodian_types_rationale` (string), `custodian_types_primary` (string)

**Universal**: Use `["*"]` for elements applying to all types.

**See**: `.opencode/CUSTODIAN_TYPE_ANNOTATION_CONVENTION.md` for complete documentation

---
""",

    14: """### Rule 14: Exa MCP LinkedIn Profile Extraction

🚨 **CRITICAL**: Use `exa_crawling_exa` with direct URL for comprehensive LinkedIn profile extraction.

**Tool Priority**:
1. `exa_crawling_exa` - Profile URL known (preferred)
2. `exa_linkedin_search_exa` - Profile URL unknown
3. `exa_web_search_exa` - Fallback search

**Output**: `data/custodian/person/entity/{linkedin-slug}_{timestamp}.json`

**See**: `.opencode/EXA_LINKEDIN_EXTRACTION_RULES.md` for complete documentation

---
""",

    15: """### Rule 15: Connection Data Registration - Full Network Preservation

🚨 **CRITICAL**: ALL LinkedIn connections must be fully registered in dedicated connections files.

**File Location**: `data/custodian/person/{slug}_connections_{timestamp}.json`

**Required**: `source_metadata`, `connections[]` array, `network_analysis` with heritage type breakdown

**See**: `.opencode/CONNECTION_DATA_REGISTRATION_RULE.md` for complete documentation

---
""",

    16: """### Rule 16: LinkedIn Photo URLs - Store CDN URLs, Not Overlay Pages

🚨 **CRITICAL**: Store actual CDN URL, NOT overlay page URL.

- ❌ WRONG: `linkedin.com/in/{slug}/overlay/photo/` (derivable, useless)
- ✅ CORRECT: `media.licdn.com/dms/image/v2/{ID}/profile-displayphoto-shrink_800_800/...`

**See**: `.opencode/LINKEDIN_PHOTO_CDN_RULE.md` for complete documentation

---
""",

    17: """### Rule 17: LinkedIn Connection Unique Identifiers

🚨 **CRITICAL**: Every connection gets unique ID including abbreviated and anonymous names.

**Format**: `{target_slug}_conn_{index:04d}_{name_slug}`

**Name Types**: `full`, `abbreviated` (Amy B.), `anonymous` (LinkedIn Member)

**See**: `.opencode/LINKEDIN_CONNECTION_ID_RULE.md` for complete documentation

---
""",

    18: """### Rule 18: Custodian Staff Parsing from LinkedIn Company Pages

🚨 **CRITICAL**: Use `scripts/parse_custodian_staff.py` for staff registration parsing.

**Staff ID Format**: `{custodian_slug}_staff_{index:04d}_{name_slug}`

**See**: `.opencode/CUSTODIAN_STAFF_PARSING_RULE.md` for complete documentation

---
""",

    19: """### Rule 19: HTML-Only LinkedIn Extraction (Preferred Method)

🚨 **CRITICAL**: Use ONLY manually saved HTML files for LinkedIn data extraction.

**Data Completeness**: HTML = 100% (including profile URLs), MD copy-paste = ~90%

**Script**: `scripts/parse_linkedin_html.py`

**How to Save**: Navigate → Scroll to load all → File > Save Page As > "Webpage, Complete"

**See**: `.opencode/HTML_ONLY_LINKEDIN_EXTRACTION_RULE.md` for complete documentation

---
""",

    20: """### Rule 20: Person Entity Profiles - Individual File Storage

🚨 **CRITICAL**: Person profiles stored as individual files in `data/custodian/person/entity/`.

**File Naming**: `{linkedin-slug}_{ISO-timestamp}.json`

**Required**: ALL profiles MUST use structured JSON with `extraction_agent: "claude-opus-4.5"`. Raw content dumps are NOT acceptable.

**See**: `.opencode/PERSON_ENTITY_PROFILE_FORMAT_RULE.md` for complete documentation

---
""",

    21: """### Rule 21: Data Fabrication is Strictly Prohibited

🚨 **CRITICAL**: ALL DATA MUST BE REAL AND VERIFIABLE. Fabricating any data is strictly prohibited.

**❌ FORBIDDEN**:
- Creating fake names, job titles, companies
- Inventing education history or skills
- Generating placeholder data when extraction fails
- Creating fictional LinkedIn URLs

**✅ ALLOWED**:
- Skip profiles that cannot be extracted
- Return `null` or empty fields for missing data
- Mark profiles with `extraction_error: true`
- Log why extraction failed

**See**: `.opencode/DATA_FABRICATION_PROHIBITION.md` for complete documentation

---
""",

    22: """### Rule 22: Custodian YAML Files Are the Single Source of Truth

🚨 **CRITICAL**: `data/custodian/*.yaml` is the SINGLE SOURCE OF TRUTH for all enrichment data.

**Data Hierarchy**:
```
data/custodian/*.yaml  ← SINGLE SOURCE OF TRUTH
       ↓
Ducklake → PostgreSQL → TypeDB → Oxigraph → Qdrant
(All databases are DERIVED - never add data independently)
       ↓
REST API → Frontend (both DERIVED)
```

**Workflow**: FETCH → VALIDATE → WRITE TO YAML → Import to database → Verify

**See**: `.opencode/CUSTODIAN_DATA_SOURCE_OF_TRUTH.md` for complete documentation

---
""",

    23: """### Rule 23: Social Media Link Validation - No Generic Links

🚨 **CRITICAL**: Social media links MUST be institution-specific, NOT generic platform homepages.

**Invalid**: `facebook.com/`, `facebook.com/facebook`, `twitter.com/twitter`

**Valid**: `facebook.com/rijksmuseum/`, `twitter.com/rijksmuseum`

**See**: `.opencode/SOCIAL_MEDIA_LINK_VALIDATION.md` for complete documentation

---
""",

    24: """### Rule 24: Unused Import Investigation - Check Before Removing

🚨 **CRITICAL**: Before removing unused imports, INVESTIGATE whether they indicate incomplete implementations.

**Checklist**:
1. Was it recently used? (`git log -p --all -S 'ImportName'`)
2. Is there a TODO/FIXME?
3. Pattern mismatch (old vs new syntax)?
4. Incomplete feature?
5. Conditional usage (`TYPE_CHECKING` blocks)?

**See**: `.opencode/UNUSED_IMPORT_INVESTIGATION_RULE.md` for complete documentation

---
""",

    25: """### Rule 25: Digital Platform Discovery Enrichment

🚨 **CRITICAL**: Every heritage custodian MUST be enriched with digital platform discovery data.

**Discover**: Collection management systems, discovery portals, external integrations, APIs

**Required Provenance**: `retrieval_agent`, `retrieval_timestamp`, `source_url`, `xpath_base`, `html_file`

**See**: `.opencode/DIGITAL_PLATFORM_DISCOVERY_RULE.md` for complete documentation

---
""",

    26: """### Rule 26: Person Data Provenance - Web Claims for Staff Information

🚨 **CRITICAL**: All person/staff data MUST have web claim provenance with verifiable sources.

**Required Fields**: `claim_type`, `claim_value`, `source_url`, `retrieved_on`, `retrieval_agent`

**Recommended**: `xpath`, `xpath_match_score`

**See**: `.opencode/PERSON_DATA_PROVENANCE_RULE.md` for complete documentation

---
""",

    27: """### Rule 27: Person-Custodian Data Architecture

🚨 **CRITICAL**: Person entity files are the SINGLE SOURCE OF TRUTH for all person data.

**In Person Entity File**: `extraction_metadata`, `profile_data`, `web_claims`, `affiliations`

**In Custodian YAML**: `person_id`, `person_name`, `role_title`, `affiliation_provenance`, `linkedin_profile_path` (reference only)

**NEVER**: Put `web_claims` in custodian YAML files

**See**: `.opencode/PERSON_CUSTODIAN_DATA_ARCHITECTURE.md` for complete documentation

---
""",

    28: """### Rule 28: Web Claims Deduplication - No Redundant Claims

🚨 **CRITICAL**: Do not duplicate claims unless genuine variation exists with uncertainty.

**Eliminate**: Favicon variants, same value from different extractions, dynamic content

**Document**: Removed claims in `removed_claims` section for audit trail

**See**: `.opencode/WEB_CLAIMS_DEDUPLICATION_RULE.md` for complete documentation

---
""",

    29: """### Rule 29: Anonymous Profile Name Derivation from LinkedIn Slugs

🚨 **CRITICAL**: Names CAN be derived from hyphenated LinkedIn slugs - this is data transformation, NOT fabrication.

**Dutch Particles**: Keep lowercase when not first word (van, de, den, der)

**Known Compound Slugs**: Use mapping for `jponjee` → "J. Ponjee", etc.

**See**: `.opencode/ANONYMOUS_PROFILE_NAME_RULE.md` for complete documentation

---
""",

    30: """### Rule 30: Person Profile Extraction Confidence Scoring

🚨 **CRITICAL**: Every enriched profile MUST have confidence score (0.50-0.95) for data extraction quality.

**Distinct from**: Heritage sector relevance score (different purpose)

**Scoring Factors**:
- Clear job title: +0.10 to +0.15
- Named institution: +0.05 to +0.10
- Privacy-abbreviated name: -0.15 to -0.20
- Intern/trainee: -0.10

**See**: `.opencode/PERSON_PROFILE_CONFIDENCE_SCORING.md` for complete documentation

---
""",

    31: """### Rule 31: Organizational Subdivision Extraction

🚨 **CRITICAL**: ALWAYS capture organizational subdivisions as structured data.

**Types**: department, team, unit, division, section, lab_or_center, office

**Store in**: `affiliations[].subdivision` with `type`, `name`, `parent_subdivision`, `extraction_source`

**See**: `.opencode/ORGANIZATIONAL_SUBDIVISION_EXTRACTION.md` for complete documentation

---
""",

    32: """### Rule 32: Government Ministries Are Heritage Custodians (Type O)

🚨 **CRITICAL**: Government ministries ARE heritage custodians due to statutory record-keeping obligations.

**Heritage Relevance Scores**:
| Role Category | Score Range |
|---------------|-------------|
| Records Management | 0.40-0.50 |
| IT/Systems (records) | 0.30-0.40 |
| Policy/Advisory | 0.25-0.35 |
| Administrative | 0.15-0.25 |

**See**: `.opencode/GOVERNMENT_MINISTRY_HERITAGE_RULE.md` for complete documentation

---
""",

    33: """### Rule 33: GHCID Collision Duplicate Detection

🚨 **CRITICAL**: Duplicate detection is MANDATORY in GHCID collision resolution.

**Decision Matrix**:
- ALL details match → DUPLICATE (keep earliest, archive later)
- Same name, different city → NOT DUPLICATE (keep both, add suffix)
- Same name, same city, different Wikidata IDs → NOT DUPLICATE
- When in doubt → Keep both files (can merge later)

**See**: `.opencode/GHCID_COLLISION_DUPLICATE_DETECTION.md` for complete documentation

---
""",

    34: """### Rule 34: Linkup is the Preferred Web Scraper

🚨 **CRITICAL**: Use Linkup as primary web scraper. Firecrawl credits are limited.

**Tool Priority**:
| Priority | Tool | When to Use |
|----------|------|-------------|
| 1st | `linkup_linkup-search` | General research, finding pages |
| 2nd | `linkup_linkup-fetch` | Fetching known URL |
| 3rd | `firecrawl_*` | Only when Linkup fails |
| 4th | `playwright_*` | Interactive pages, HTML archival |

**Two-Phase for XPath Provenance** (Rule 6 compliance):
1. Linkup for discovery
2. Playwright for archival with XPath extraction

**See**: `.opencode/LINKUP_PREFERRED_WEB_SCRAPER_RULE.md` for complete documentation

---
""",
}


def main():
    agents_path = Path("/Users/kempersc/apps/glam/AGENTS.md")
    output_path = Path("/Users/kempersc/apps/glam/AGENTS_OPTIMIZED.md")
    
    # Read original file
    with open(agents_path, "r", encoding="utf-8") as f:
        original_lines = f.readlines()
    
    print(f"Original file: {len(original_lines)} lines")
    
    # Extract sections
    header = original_lines[:22]  # Lines 1-22 (0-indexed: 0-21)
    unique_content = original_lines[2775:]  # Lines 2776+ (0-indexed: 2775+)
    
    print(f"Header: {len(header)} lines")
    print(f"Unique content: {len(unique_content)} lines")
    
    # Extract Rules 2-3 full content for appendix
    rule2_start = None
    rule4_start = None
    
    for i, line in enumerate(original_lines):
        if "### Rule 2: Wikidata Entities Are NOT Ontology Classes" in line:
            rule2_start = i
        elif "### Rule 4:" in line:
            rule4_start = i
            break
    
    if rule2_start and rule4_start:
        rules_2_3_content = original_lines[rule2_start:rule4_start]
        print(f"Rules 2-3 full content: {len(rules_2_3_content)} lines")
    else:
        rules_2_3_content = []
        print("Warning: Could not extract Rules 2-3 boundaries")
    
    # Build output
    output_lines = []
    
    # Header
    output_lines.extend(header)
    output_lines.append("\n")
    
    # Enhanced rules section
    output_lines.append("## 🚨 CRITICAL RULES FOR ALL AGENTS\n\n")
    output_lines.append("This section summarizes 35 critical rules. Each rule has complete documentation in `.opencode/` files.\n\n")
    
    for rule_num in range(35):
        output_lines.append(RULE_CONTENT[rule_num])
        output_lines.append("\n")
    
    # Add appendix for rules without .opencode files
    if rules_2_3_content:
        output_lines.append("## Appendix: Full Rule Content (No .opencode Equivalent)\n\n")
        output_lines.append("The following rules have no separate .opencode file and are preserved in full:\n\n")
        output_lines.extend([line if line.endswith("\n") else line + "\n" for line in rules_2_3_content])
        output_lines.append("\n")
    
    # Unique content (Project Overview onward)
    output_lines.extend(unique_content)
    
    # Write output
    with open(output_path, "w", encoding="utf-8") as f:
        f.writelines(output_lines)
    
    final_lines = len(output_lines)
    print(f"\nOutput file: {final_lines} lines")
    print(f"Reduction: {len(original_lines)} → {final_lines} ({len(original_lines) - final_lines} lines removed)")
    print(f"Saved to: {output_path}")
    
    return output_path


if __name__ == "__main__":
    main()