chore(repo): add LICENSE, CI workflow, and untrack local config

Public-repo hygiene now that the project is hosted on Forgejo:

- LICENSE: add the MIT text that pyproject.toml already declares.
- .forgejo/workflows/ci.yml: run the pytest suite on push/PR against
  Python 3.10 and 3.12, so regressions (e.g. the healthcheck port bug)
  get caught automatically.
- Untrack llama.cpp.config and gitignore it: it is a machine-specific
  runtime config that may later hold an api_key. The tracked template
  remains llama.cpp.config.example (copy it to get started).

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

.forgejo/workflows/ci.yml

@@ -0,0 +1,27 @@
+name: CI
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        # requires-python = ">=3.10"; test the floor and a recent version.
+        python-version: ["3.10", "3.12"]
+    steps:
+      - uses: actions/checkout@v4
+
+      - uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+
+      - name: Install package with dev extras
+        run: pip install -e ".[dev]"
+
+      - name: Run test suite
+        run: pytest -q

.gitignore

@@ -19,3 +19,7 @@ venv/
 
 # Runtime lock files
 *.lock
+
+# Local runtime config (machine-specific; may hold an api_key).
+# The tracked template is llama.cpp.config.example — copy it to get started.
+llama.cpp.config

LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Dieter Schlueter
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

llama.cpp.config

@@ -1,79 +0,0 @@
-# llama.cpp.config.example
-#
-# Copy this file to llama.cpp.config and adjust it for your host before
-# running llamacppctl. See docs/SECURITY_AND_OPERATIONS.md for details on
-# every field and on the security model for --system-url/--prompt-url.
-#
-# Section types:
-#   [default]       global defaults, merged over the built-in fallbacks
-#   [model.<name>]  a model profile, selected via --profile <name>
-#   [prompt.<name>] a system-prompt profile, selected via --system-prompt-profile <name>
-#
-# container_name is MANDATORY and must be unique per profile you intend to
-# run concurrently: it is the single identity anchor for Docker naming,
-# locking (--change), and --stop/--check targeting.
-
-[default]
-image = ghcr.io/ggml-org/llama.cpp:server-cuda
-hf_home = ${HF_HOME}
-model_path = models/qwen3/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-Q4_K_M.gguf
-container_name = llama_cpp_server
-host_port = 8001
-container_port = 8000
-model_alias = default_llm
-gpu_device = 1
-restart_policy = unless-stopped
-# Groß-Profil für literarische Texte / durchdachte Reden: volles
-# 256k-Kontextfenster (= n_ctx_train des Modells) und sehr lange Antworten.
-# Empirisch gemessen passt der q4_0-KV-Cache dafür knapp auf EINE 24-GB-3090
-# (~22,6 GB inkl. 21-GB-Modell). Bei Bedarf auf 131072/65536 senken.
-ctx_size = 262144
-n_predict = 32768
-temp = 0.65
-top_p = 0.80
-top_k = 20
-min_p = 0.01
-repeat_penalty = 1.05
-main_gpu = 0
-ngl = 999
-fa = true
-kv_unified = true
-jinja = true
-reasoning = on
-no_context_shift = true
-cache_type_k = q4_0
-cache_type_v = q4_0
-batch_size = 1024
-ubatch_size = 512
-parallel = 1
-cont_batching = true
-health_endpoint = /health
-models_endpoint = /v1/models
-chat_endpoint = /v1/chat/completions
-timeout = 300
-poll_interval = 2
-# Chat-Antwortbudget (Reasoning-Modell braucht viel; für lange Texte hoch):
-max_tokens = 32768
-# chat_temperature leer lassen -> Server-Temp (temp oben) gilt.
-chat_temperature =
-
-# Modell-Profile: erben ALLES aus [default] (Port 8001, Container
-# llama_cpp_server, Alias default_llm, gpu_device 1, ctx_size 262144) und
-# überschreiben NUR das Modell. Es läuft also immer ein Modell auf dem
-# Standard-Port; --start/--change tauscht es aus. Wer Modelle GLEICHZEITIG
-# betreiben will, gibt dem Profil zusätzlich einen eigenen container_name +
-# host_port (Muster siehe llama.cpp.config.example).
-[model.carnice]
-model_path = models/qwen3/Carnice-Qwen3.6-MoE-35B-A3B-Q4_K_M.gguf
-
-[model.qwen27b]
-model_path = models/qwen3/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive-IQ4_XS.gguf
-
-[model.qwopus]
-model_path = models/qwen3/Qwopus3.6-35B-A3B-v1-Q4_K_M.gguf
-
-[prompt.concise]
-system_prompt = Du antwortest kurz, präzise und technisch.
-
-[prompt.coding]
-system_prompt = Du bist ein erfahrener Linux-, Python- und LLM-Infrastruktur-Engineer.