Phillip Tarrant adbb442ce5 Add Phase 3: LLM integration with Ollama streaming and preflight checks ...

Wire the REPL to a local Ollama instance via streaming HTTP (SSE).
LLMClient handles async streaming chat, StreamHandler renders live
Markdown via Rich and accumulates tool call fragments. Startup now
runs a preflight check that verifies Ollama is reachable and the
configured model is pulled, exiting with a clear message on failure.
Also adds .gitignore and updates config to use qwen3.5.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

2026-03-11 07:27:56 -05:00

app

Add Phase 3: LLM integration with Ollama streaming and preflight checks

2026-03-11 07:27:56 -05:00

config

init commit

2026-03-11 07:21:21 -05:00

docs

init commit

2026-03-11 07:21:21 -05:00

tests

init commit

2026-03-11 07:21:21 -05:00

.gitignore

init commit

2026-03-11 07:21:21 -05:00

CLAUDE.md

init commit

2026-03-11 07:21:21 -05:00

pyproject.toml

init commit

2026-03-11 07:21:21 -05:00

uv.lock

init commit

2026-03-11 07:21:21 -05:00

Description

No description provided

465 KiB

Languages

Python 100%