Commit graph

3 commits

Author SHA1 Message Date
Till JS
1f35206433 docs: update Cloudflare domains guide and tech independence roadmap
CLOUDFLARE_DOMAINS.md: Complete rewrite for self-hosted landing architecture
- Document DNS migration from CF Pages to Tunnel (step-by-step)
- List all 30+ domains with their routing (Apps, Landings, Services)
- Tunnel CNAME for 10 new landing domains to create
- Process for adding new landing pages

TECH_STACK_INDEPENDENCE.md: Mark Prio 4, 6, 8 as completed
- Prio 4: PostgreSQL backup (hourly dumps + daily base backups)
- Prio 6: Landing pages self-hosted (Nginx on port 4400)
- Prio 8: Cloudflare fallback documented (WireGuard + Caddy)
- Update self-hosted percentage: 80% → ~85%
- Remaining: Prio 5 (email), 7 (vision models), 9 (redundancy)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-24 12:42:55 +01:00
Till JS
62c5dddab0 feat(project-doc-bot): migrate to shared-llm, remove OpenAI dependency
Migrate matrix-project-doc-bot from raw fetch to @manacore/shared-llm
and remove the unused openai npm package. The bot was already using
mana-llm and mana-stt (not OpenAI directly), but the code still had
raw fetch calls and the openai package installed.

Changes:
- generation.service.ts: raw fetch → llm.chat() via LlmClientService
- app.module.ts: add LlmModule.forRootAsync()
- Remove openai dependency (was unused in code)
- Update CLAUDE.md: document actual AI stack (mana-llm + mana-stt)
- Update TECH_STACK_INDEPENDENCE.md: mark Prio 1-3 as completed
  - Prio 1: Picture App → mana-image-gen 
  - Prio 2: Project Doc Bot → Ollama + mana-stt 
  - Prio 3: All LLM calls via mana-llm 
  - Self-hosted percentage: 75% → ~80%

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-24 10:44:56 +01:00
Till JS
376cfe881b docs: add tech stack independence analysis and improvement roadmap
Comprehensive analysis of self-hosted vs cloud dependencies with
prioritized roadmap to reach ~90% self-hosting. Key findings: mana-image-gen
can replace Replicate, all LLM calls should route through mana-llm,
and backup strategy needs strengthening.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-23 10:01:14 +01:00