From 01e6975d20c7cae035a3b7a6a868b03a0149d9b7 Mon Sep 17 00:00:00 2001
From: Joseph Doherty <dohejw01@gmail.com>
Date: Sun, 26 Apr 2026 11:28:40 -0400
Subject: [PATCH] feat: config loader with toml + env override

---
 chat/config.py           | 40 ++++++++++++++++++++++++++++++++++++++++
 data/config.example.toml |  6 ++++++
 tests/test_config.py     | 26 ++++++++++++++++++++++++++
 3 files changed, 72 insertions(+)
 create mode 100644 chat/config.py
 create mode 100644 data/config.example.toml
 create mode 100644 tests/test_config.py

diff --git a/chat/config.py b/chat/config.py
new file mode 100644
index 0000000..90d6175
--- /dev/null
+++ b/chat/config.py
@@ -0,0 +1,40 @@
+from __future__ import annotations
+import os
+import tomllib
+from pathlib import Path
+from pydantic import BaseModel, Field
+
+REPO_ROOT = Path(__file__).resolve().parent.parent
+DEFAULT_CONFIG = REPO_ROOT / "data" / "config.toml"
+DEFAULT_DB = REPO_ROOT / "data" / "chat.db"
+
+class Settings(BaseModel):
+    featherless_api_key: str
+    featherless_base_url: str = "https://api.featherless.ai/v1"
+    narrative_model: str = "dphn/Dolphin-Mistral-24B-Venice-Edition"
+    classifier_model: str = "NousResearch/Hermes-3-Llama-3.1-8B"
+    classifier_fallbacks: list[str] = Field(
+        default_factory=lambda: [
+            "cognitivecomputations/dolphin-2.9.4-llama3-8b",
+            "mlabonne/Meta-Llama-3.1-8B-Instruct-abliterated",
+        ]
+    )
+    ooc_marker: str = "(("
+    retrieval_k: int = 4
+    narrative_budget_hard: int = 8000
+    narrative_budget_soft: int = 6000
+    classifier_budget_hard: int = 4000
+    classifier_timeout_s: float = 10.0
+    db_path: Path = DEFAULT_DB
+    data_dir: Path = REPO_ROOT / "data"
+    bind_host: str = "127.0.0.1"
+    bind_port: int = 8000
+
+def load_settings() -> Settings:
+    config_path = Path(os.environ.get("CHAT_CONFIG_PATH", DEFAULT_CONFIG))
+    raw: dict = {}
+    if config_path.exists():
+        raw = tomllib.loads(config_path.read_text())
+    if "CHAT_DB_PATH" in os.environ:
+        raw["db_path"] = Path(os.environ["CHAT_DB_PATH"])
+    return Settings(**raw)
diff --git a/data/config.example.toml b/data/config.example.toml
new file mode 100644
index 0000000..1da91f2
--- /dev/null
+++ b/data/config.example.toml
@@ -0,0 +1,6 @@
+# Copy this file to data/config.toml and fill in your API key.
+featherless_api_key = "REPLACE_ME"
+narrative_model = "dphn/Dolphin-Mistral-24B-Venice-Edition"
+classifier_model = "NousResearch/Hermes-3-Llama-3.1-8B"
+ooc_marker = "(("
+retrieval_k = 4
diff --git a/tests/test_config.py b/tests/test_config.py
new file mode 100644
index 0000000..abffd57
--- /dev/null
+++ b/tests/test_config.py
@@ -0,0 +1,26 @@
+import os
+from pathlib import Path
+import pytest
+from chat.config import load_settings
+
+def test_load_settings_reads_toml(tmp_path, monkeypatch):
+    cfg = tmp_path / "config.toml"
+    cfg.write_text("""
+        featherless_api_key = "sk-test"
+        narrative_model = "dphn/Dolphin-Mistral-24B-Venice-Edition"
+        classifier_model = "NousResearch/Hermes-3-Llama-3.1-8B"
+        ooc_marker = "(("
+        retrieval_k = 4
+    """)
+    monkeypatch.setenv("CHAT_CONFIG_PATH", str(cfg))
+    s = load_settings()
+    assert s.featherless_api_key == "sk-test"
+    assert s.narrative_model.startswith("dphn/")
+    assert s.retrieval_k == 4
+
+def test_chat_db_path_env_overrides_default(tmp_path, monkeypatch):
+    monkeypatch.setenv("CHAT_DB_PATH", str(tmp_path / "alt.db"))
+    monkeypatch.setenv("CHAT_CONFIG_PATH", str(tmp_path / "config.toml"))
+    (tmp_path / "config.toml").write_text('featherless_api_key = "x"\n')
+    s = load_settings()
+    assert s.db_path == tmp_path / "alt.db"