update

Co-authored-by: Copilot <copilot@github.com>

ROADMAP.md

@@ -2,13 +2,14 @@
 
 This document outlines the major decisions, milestones, and development phases required to bring `tai` from concept to a working tool.
 
----
+______________________________________________________________________
 
 ## Phase 0 — Decisions & Prerequisites
 
 These must be resolved before meaningful development can begin.
 
 ### Language Selection
+
 - [x] **Decision: Python**
 - Key factors: native vLLM integration, mature SSH libraries (`paramiko` / `asyncssh`), strong text/log parsing, rapid development
 - Single binary distribution will be achieved via **Nuitka** (preferred for true compilation) or **PyInstaller** as a fallback
@@ -16,12 +17,14 @@ These must be resolved before meaningful development can begin.
 - [ ] Add binary build step to CI pipeline
 
 ### AI Backend & Model
+
 - [ ] Confirm use of [vLLM](https://github.com/vllm-project/vllm) as the inference backend
 - [ ] Confirm `gemma4:a4b` as the default model (or select an alternative)
 - [ ] Define minimum hardware requirements for running the model locally
 - [ ] Decide whether the AI backend is bundled, self-hosted externally, or user-supplied
 
 ### SSH Strategy
+
 - [x] **Decision: keypair authentication only** — no password auth; eliminates credential storage risk
   - Default key resolution: `~/.ssh/id_ed25519`, `~/.ssh/id_rsa` (in order of preference)
   - CLI override via `--identity-file <path>`
@@ -33,6 +36,7 @@ These must be resolved before meaningful development can begin.
   - Override switch: `--ignore-ssh-config` to bypass local SSH config when required
 
 ### Scope & Constraints
+
 - [ ] Define the supported scope of issues (services, network, disk, kernel, etc.)
 - [ ] Confirm read-only guarantee — document exactly what "read-only" means in practice
 - [x] **Decision: interactive REPL mode for v0.1, full TUI for v0.2+**
@@ -40,7 +44,7 @@ These must be resolved before meaningful development can begin.
   - v0.2+: `textual`-based TUI with split panes (collected data | AI output | input bar)
   - Built-in slash commands: `/collect`, `/show logs`, `/clear`, `/host <hostname>`, `/help`, `/quit`
 
----
+______________________________________________________________________
 
 ## Phase 1 — Project Foundation
 
@@ -58,7 +62,7 @@ Basic project scaffolding and connectivity.
   - [x] Input parser and CLI tests added
   - [x] SSH module tests added for command policy and SSH argv behavior
 
----
+______________________________________________________________________
 
 ## Phase 2 — Data Collection Layer
 
@@ -74,7 +78,7 @@ Define what information the agent gathers and how.
 - [ ] Add support for per-distro variations (Ubuntu vs RHEL path differences, etc.)
 - [ ] Write tests with mocked SSH output
 
----
+______________________________________________________________________
 
 ## Phase 3 — AI Integration
 
@@ -87,7 +91,7 @@ Wire collected data into the local AI model.
 - [ ] Add streaming support for long AI responses
 - [ ] Evaluate and test model output quality on common issue types
 
----
+______________________________________________________________________
 
 ## Phase 4 — CLI & User Experience
 
@@ -99,7 +103,7 @@ Polish the interface for real-world use.
 - [ ] Support output to file or clipboard
 - [ ] Write man page / `--help` documentation
 
----
+______________________________________________________________________
 
 ## Phase 5 — Hardening & Distribution
 
@@ -111,7 +115,7 @@ Prepare for broader use.
 - [ ] Write installation and quickstart documentation
 - [ ] End-to-end integration tests against a test VM
 
----
+______________________________________________________________________
 
 ## Decisions Log