Regresja po zamknieciu Etapu B fazy mailowej dala FAIL wylacznie na kryterium 3: kontrolka N2 "piaskownica plastikowa" spadla do 0.4924 (flat/hybrid) na mail przedszkolny "Materialy plastyczne" -- kolizja leksykalna ponizej progu 0.50. Rownoczesnie odrzucone w Etapie A zapytanie "piaskownica plac zabaw wspolnota" ma dzis realne odpowiedzi (maile administracji wspolnoty holc.waw.pl, 2023). To nie regresja retrievalu -- korpus urosl o tresc, ktorej w Etapie A nie bylo, wiec kontrolka negatywna stracila waznosc. - N2 wycofana; pelna historia decyzji (pilot, 2026-07-23, 2026-08-06) zachowana jako komentarz w queries.yaml, nie skasowana. - M5: "wymiana piasku w piaskownicy na placu zabaw wspolnoty", expected_envelope 6ab218df-...@holc.waw.pl, d1=0.2858, hit3=y. Wariant z "wymiana piasku" zamiast doslownego sformulowania operatora, bo tamto daje 0.4562/0.4597 -- oba nad HIT_THRESHOLD 0.45. - N3: "sterylizacja kota cennik kliniki weterynaryjnej", bar 0.50 bez zmian, 0.5257/0.5799/0.5257. Dwaj odrzuceni kandydaci i lista tematow majacych realna odpowiedz w korpusie udokumentowane w komentarzu. - retrieval_eval.py: tylko komentarz -- mail_hit nadal ocenia sie source-matchem, expected_envelope M5 jest dokumentacyjne. Weryfikacja: retrieval_eval.py --transport http --base-url http://192.168.31.5:8230 --gate-n 10 -> OVERALL PASS (exit 0), kryteria 1/2/3 PASS, kryterium 4 = 5/5 (wymagane >= 4). Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> |
||
|---|---|---|
| .claude/skills | ||
| backups/zigbee | ||
| docs/sessions | ||
| dotfiles | ||
| hardware/esp/ir-ac-ha-integration | ||
| hosts | ||
| inventory | ||
| jobs | ||
| kb | ||
| packages | ||
| scripts | ||
| services | ||
| .codex | ||
| .gitignore | ||
| .mcp.json | ||
| CLAUDE.md | ||
| codex_context | ||
| codex_context.yaml | ||
| deploy_agent.py | ||
| ollama_client.py | ||
| README.md | ||
| start-aider.sh | ||
| start-codex.sh | ||
| sync-context.sh | ||
| update-context.md | ||
Homelab Codex
GitOps-lite orchestration for a distributed homelab environment.
Architecture
The homelab consists of several nodes connected via a Tailscale internal mesh.
| Host | Role | Description |
|---|---|---|
| SATURN | Primary Node | Development, orchestration, and git source of truth (commit node). |
| SOLARIA | Compute Node | GPU, inference, and heavy compute workloads. |
| PIHA | Infra Node | Core infrastructure services, automation, and monitoring. |
| VPS | Edge Node | Public ingress, reverse proxy, and edge services. |
Agent System
The homelab uses a multi-agent orchestration model with human-in-the-loop for destructive actions:
| Agent | Node | Role |
|---|---|---|
| stability-agent | all nodes | Per-node watchdog — monitors Docker, disk, Tailscale, MQTT; emits events |
| node-agent | all nodes | Publishes container health events to Redis pub/sub |
| observer | VPS | Synthesizes world state from events into /opt/homelab/world/*.json |
| supervisor | VPS | Detects drift between desired and actual state; writes pending actions |
| planner-agent | SOLARIA | LLM-powered diagnosis — listens to Redis, proposes remediation actions |
| executor | VPS | Executes actions only after operator approval |
| operator-ui + telegram-bot | VPS / PIHA | Operator reviews and approves/rejects pending actions |
Action approval flow: pending/ → operator approves → approved/ → executor runs.
Repository Structure
docs/: Infrastructure Standards and Deployment Conventions.kb/phases/subsystem-a-naprawa.md: Current Maintenance Plan (Control Plane).hosts/: Host-specific configurations and service assignments.services/: Reusable Docker Compose service definitions.scripts/: Deployment and management scripts.
Getting Started
- Standardization: Follow the Infrastructure Standards.
- Deployment: See Deployment Conventions for how to roll out changes.
- SATURN: Remember that SATURN is the only node where commits should be made.
Documentation Index
- Current Maintenance Plan (Control Plane)
- Infrastructure Standards
- Agent Operating Procedures (For AI/Non-Human Agents)
- Deployment Conventions
- Hardware
- Networking
- Services
- Node Capabilities
- Action Model
Note: This repository documents the state of the homelab. Runtime state lives outside the repository in /opt/homelab.