Closes #1143. Completes the Anthropic purge across the-nexus repo to match timmy-config PR #440. Removes Claude as an active provider, replaces with Gemini/Kimi in all operational config. Golden state: Kimi K2.5 (primary) > Gemini 2.5 Pro (fallback) > Ollama (terminal) Changes across 16 files: CONFIG (provider references removed): - config/deepdive.env.example: model → google/gemini-2.5-pro, Anthropic block purged - scaffold/deep-dive/.env.example: ANTHROPIC_API_KEY removed - scaffold/deep-dive/synthesis/synthesis_prompt.txt: Claude → Kimi/Gemini - scaffold/deep-dive/aggregator/blog_fetcher.py: annotated as research source - intelligence/deepdive/docker-compose.yml: cleaned comment FLEET (Claude references deprecated): - fleet/fleet-routing.json: ezra model → google/gemini-2.5-pro - fleet/hermes-trismegistus/: full lane deprecated with header - docs/FLEET_VOCABULARY.md: fallback chain → Kimi > Gemini > Ollama - intelligence/deepdive/OPERATIONAL_READINESS.md: Anthropic → Gemini FRONTEND (Claude → Gemini in Three.js world): - app.js: agent station, simulation, chat prefix, status panels → Gemini - style.css: .tag-claude → .tag-gemini, .chat-msg-claude → .chat-msg-gemini - portals.json: claude → gemini - world_state.json: Claude → Gemini - nexus/components/agent-presence-panel.html: Claude → Gemini - nexus/components/heartbeat-briefing-panel.html: Claude status → Gemini standby PRESERVED (intentionally not changed): - CLAUDE.md (canonical doc name) - Historical audits, changelogs, reviews - Git hooks (stale-pr-closer pattern matching) - Secret detection hooks (catches leaked Anthropic keys) - Research/competitor monitoring configs (annotated) - Test files (test_repo_truth.py)
Deep Dive: Automated Intelligence Briefing System
Sovereign, automated daily intelligence pipeline for the Timmy Foundation fleet.
Vision
Zero-manual-input daily AI-generated podcast briefing covering:
- arXiv (cs.AI, cs.CL, cs.LG)
- OpenAI, Anthropic, DeepMind research blogs
- AI newsletters (Import AI, TLDR AI)
Architecture
┌─────────────────┐ ┌─────────────────┐ ┌─────────────────┐
│ Phase 1 │───▶│ Phase 2 │───▶│ Phase 3 │
│ Aggregation │ │ Relevance │ │ Synthesis │
│ (RSS/Feeds) │ │ (Embeddings) │ │ (LLM Briefing) │
└─────────────────┘ └─────────────────┘ └────────┬────────┘
│
┌────────────────────────┘
▼
┌─────────────────┐ ┌─────────────────┐
│ Phase 4 │───▶│ Phase 5 │
│ Audio (TTS) │ │ Delivery │
│ (Piper) │ │ (Telegram) │
└─────────────────┘ └─────────────────┘
Status: IMPLEMENTATION COMPLETE
This is no longer a reference scaffold — it is a production-ready executable pipeline.
| Component | Status | File |
|---|---|---|
| Phase 1: Aggregation | ✅ Complete | pipeline.py — RSS fetcher with caching |
| Phase 2: Relevance | ✅ Complete | pipeline.py — sentence-transformers ranking |
| Phase 3: Synthesis | ✅ Complete | pipeline.py — LLM briefing generation |
| Phase 4: Audio | ✅ Complete | tts_engine.py — Piper + ElevenLabs hybrid |
| Phase 5: Delivery | ✅ Complete | pipeline.py — Telegram text + voice |
| Orchestrator | ✅ Complete | pipeline.py — asyncio CLI + Python API |
| Tests | ✅ Complete | tests/test_e2e.py — dry-run validation |
| Systemd Timer | ✅ Complete | systemd/deepdive.timer — 06:00 daily |
Quick Start
See QUICKSTART.md for exact commands to run the pipeline.
Sovereignty Compliance
| Component | Implementation | Non-Negotiable |
|---|---|---|
| Aggregation | Local RSS polling | No third-party APIs |
| Relevance | sentence-transformers local | No cloud embeddings |
| Synthesis | Gemma 4 via Hermes llama-server | No OpenAI/Anthropic API |
| TTS | Piper TTS local | No ElevenLabs |
| Delivery | Hermes Telegram gateway | Existing infra |
Files
pipeline.py— Main orchestrator (production implementation)tts_engine.py— Phase 4 TTS engine (Piper + ElevenLabs fallback)config.yaml— Configuration templateMakefile— Build automation (make test-e2e,make install-systemd)tests/— pytest suite including end-to-end dry-run testsystemd/— Daily timer for 06:00 executionQUICKSTART.md— Step-by-step execution guidearchitecture.md— Full technical specificationtelegram_command.py— Hermes/deepdivecommand handler
Issue
#830 — Deep Dive: Sovereign NotebookLM + Daily AI Intelligence Briefing