2f2becd4f2
Some checks failed
Auto Tag / auto-tag (push) Has been cancelled
Test / rust-fmt-check (push) Has been cancelled
Test / rust-clippy (push) Has been cancelled
Test / rust-tests (push) Has been cancelled
Test / frontend-typecheck (push) Has been cancelled
Test / frontend-tests (push) Has been cancelled
Add comprehensive documentation for integrating AWS Bedrock Claude models via LiteLLM proxy. Enables enterprise users to leverage existing AWS contracts while maintaining OpenAI-compatible API interface. Changes: - README.md: Add quickstart section for LiteLLM + Bedrock setup - docs/wiki/LiteLLM-Bedrock-Setup.md: New comprehensive guide covering single/multi-account setup, Claude Code integration, troubleshooting, and auto-start configuration - docs/wiki/AI-Providers.md: Update OpenAI-compatible section to reference LiteLLM - docs/wiki/Home.md: Add LiteLLM guide to navigation and feature list Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
3.3 KiB
3.3 KiB
TFTSR — IT Triage & RCA Desktop Application
TFTSR is a secure desktop application for guided IT incident triage, root cause analysis (RCA), and post-mortem documentation. Built with Tauri 2.x (Rust + WebView) and React 18.
CI: 
— rustfmt · clippy · 64 Rust tests · tsc · vitest — all green
Quick Navigation
| Topic | Description |
|---|---|
| Architecture | Backend, frontend, and data flow |
| Development Setup | Prerequisites, commands, environment |
| Database | Schema, migrations, encryption |
| AI Providers | Supported providers and configuration |
| LiteLLM + Bedrock Setup | AWS Bedrock integration via LiteLLM proxy |
| PII Detection | Patterns, redaction flow, security |
| IPC Commands | Full list of Tauri backend commands |
| CI/CD Pipeline | Gitea Actions setup, multi-platform builds, act_runner config |
| Security Model | Encryption, audit trail, capabilities |
| Integrations | Confluence, ServiceNow, Azure DevOps (v0.2) |
| Troubleshooting | Known issues and fixes |
Key Features
- 5-Whys AI Triage — Interactive guided root cause analysis via multi-turn AI chat
- PII Auto-Redaction — Detects and redacts sensitive data before any AI send
- Multi-Provider AI — OpenAI, Anthropic Claude, Google Gemini, Mistral, AWS Bedrock (via LiteLLM), local Ollama (fully offline)
- SQLCipher AES-256 — All issue history encrypted at rest
- RCA + Post-Mortem Generation — Auto-populated Markdown templates, exportable as MD/PDF
- Ollama Management — Hardware detection, model recommendations, in-app model management
- Audit Trail — Every external data send logged with SHA-256 hash
- Domain-Specific Prompts — 8 IT domains: Linux, Windows, Network, Kubernetes, Databases, Virtualization, Hardware, Observability
Releases
| Version | Status | Platforms |
|---|---|---|
| v0.1.1 | 🚀 Released | linux/amd64 · linux/arm64 · windows/amd64 (.deb, .rpm, .AppImage, .exe, .msi) |
Download from Releases. All builds are produced natively (no QEMU emulation).
Project Status
| Phase | Status |
|---|---|
| Phases 1–8 (Core application) | ✅ Complete |
| Phase 9 (History/Search) | 🔲 Pending |
| Phase 10 (Integrations) | 🕐 v0.2 stubs only |
| Phase 11 (CI/CD) | ✅ Complete — Gitea Actions fully operational |
| Phase 12 (Release packaging) | ✅ linux/amd64 · linux/arm64 (native) · windows/amd64 |
Tech Stack
| Layer | Technology |
|---|---|
| Desktop framework | Tauri 2.x |
| Backend | Rust (async/await, tokio) |
| Frontend | React 18 + TypeScript + Vite |
| Styling | Tailwind CSS + custom components |
| Database | rusqlite + SQLCipher (AES-256) |
| Secret storage | tauri-plugin-stronghold |
| State | Zustand |
| Testing | Vitest (13 frontend) + #[cfg(test)] (64 Rust tests) |
| CI/CD | Gitea Actions (act_runner v0.3.1) + Gitea |