jpmschweitzer/library-desk
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 5 Wiki Activity
60 Commits 1 Branch 34 Tags
1e31e74ad6e72a8da6f246bda71e33db1ebf5909
Commit Graph
5 Commits
Author SHA1 Message Date
jpmschweitzerandClaude Opus 4.5 910b289c9e feat: integrate external scheduler for prefetch task registration 
Add SchedulerClient to communicate with external scheduler service for
registering volatile prefetch tasks discovered during HybridRAG searches.

- Add scheduler_client.py with full REST API for task CRUD operations
- Add scheduler_url config setting (default: http://scheduler:8090)
- Update consolidation service to use scheduler for prefetch registration
- Add scheduler health checks to startup/shutdown lifecycle

When HybridRAG classifies web content as prefetch-worthy, it now creates
scheduled tasks that periodically refresh the volatile cache via the
external scheduler service.

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

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2025-12-29 20:42:37 +01:00
jpmschweitzerandClaude Opus 4.5 1f47b052d8 feat: add unified memory routing to consolidation service 
- Add MemoryRouteClassification and MemoryRoutingResult models
- Implement unified classifier (_classify_web_results_unified) that routes
  web results to: wiki, volatile, file (Paperless), prefetch, or skip
- Add routing methods: _route_to_volatile, _route_to_files, _register_prefetch
- Update _process_search to use unified classifier instead of separate analysis
- Add get_volatile_cache_service factory to dependencies
- Wire volatile_service and settings_client into ConsolidationService
- Update ConsolidationResult/Response with new routing counters

Test fixes:
- Fix WikiJSClient fixtures to use api_token instead of username/password
- Fix entity linking test assertions to expect full user-namespaced paths
- Add sample_unified_classification fixture for new classifier format

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

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2025-12-28 17:19:20 +01:00
jpmschweitzerandClaude Opus 4.5 b976da0092 refactor: improve web results analysis prompt 
Apply llm-findings.md recommendations:

Web results analysis (temp 0.0):
- Add ANALYSIS STEPS for chain-of-thought reasoning
- Strict RULES section with negative constraints:
  - "Do NOT suggest pages with insufficient info"
  - "Do NOT invent entities not mentioned"
  - "Do NOT suggest paths outside taxonomy"
- Conservative approach: quality over quantity
- Removed "be INCLUSIVE" guidance (caused over-suggestion)

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

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2025-12-23 17:22:12 +01:00
jpmschweitzerandClaude Opus 4.5 a1832e3245 refactor: consolidate Ollama model configuration
Build and Push / build (release) Successful in 27s
Details 
- Add OLLAMA_EMBEDDING_MODEL for embeddings (nomic-embed-text)
- OLLAMA_MODEL now used for all LLM operations (mistral-nemo-large:latest)
- Remove separate reranker_model setting
- Update WikiPageWriter to use settings instead of hardcoded model
- Improves VRAM efficiency by keeping one model hot

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

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2025-12-22 11:15:27 +01:00
jpmschweitzer 95852190ba Initial commit: library-desk service extraction from portainer-core
Build and Push / build (release) Successful in 36s
Details
2025-12-11 17:28:23 +01:00