From 52a2967f61e340b600e367718c437bac454e28c7 Mon Sep 17 00:00:00 2001
From: curo1305 <curo1305@proton.me>
Date: Tue, 14 Apr 2026 11:48:15 +0200
Subject: [PATCH] Dev AI config: env var overrides in config_reader, LM Studio
 via .env

config_reader.py now merges environment variables (AI_PROVIDER,
LMSTUDIO_BASE_URL, LMSTUDIO_API_KEY, LMSTUDIO_MODEL, OLLAMA_*,
ANTHROPIC_*) on top of the JSON config file, so the dev .env file
can pin the AI connection without writing to the shared config volume.

docker-compose.dev.yml loads features/doc-service/.env (gitignored)
into the doc-service container so the token is never committed.

.env.example updated with all supported override variables and comments.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---
 docker-compose.dev.yml                        |  1 +
 features/doc-service/.env.example             | 18 ++++++
 .../doc-service/app/services/config_reader.py | 62 ++++++++++++++++++-
 3 files changed, 78 insertions(+), 3 deletions(-)

diff --git a/docker-compose.dev.yml b/docker-compose.dev.yml
index e058e68..ad7dc16 100644
--- a/docker-compose.dev.yml
+++ b/docker-compose.dev.yml
@@ -25,5 +25,6 @@ services:
 
   doc-service:
     command: sh scripts/start_dev.sh
+    env_file: ./features/doc-service/.env   # gitignored — holds local AI credentials
     volumes:
       - ./features/doc-service:/app
diff --git a/features/doc-service/.env.example b/features/doc-service/.env.example
index 129e4ce..c3565d6 100644
--- a/features/doc-service/.env.example
+++ b/features/doc-service/.env.example
@@ -1,3 +1,21 @@
 DATABASE_URL=postgresql+asyncpg://postgres:password@db:5432/destroying_sap
 DATA_DIR=/data/documents
 CONFIG_PATH=/config/doc_service_config.json
+
+# Optional AI provider overrides — if set, these take precedence over
+# whatever is stored in doc_service_config.json.
+# Useful for pinning a dev environment to a specific local AI instance
+# without touching the shared config volume.
+#
+# AI_PROVIDER=lmstudio
+# LMSTUDIO_BASE_URL=http://host.docker.internal:1234/v1
+# LMSTUDIO_API_KEY=your-lm-studio-token
+# LMSTUDIO_MODEL=local-model
+#
+# AI_PROVIDER=ollama
+# OLLAMA_BASE_URL=http://host.docker.internal:11434/v1
+# OLLAMA_MODEL=llama3.2
+#
+# AI_PROVIDER=anthropic
+# ANTHROPIC_API_KEY=sk-ant-...
+# ANTHROPIC_MODEL=claude-haiku-4-5-20251001
diff --git a/features/doc-service/app/services/config_reader.py b/features/doc-service/app/services/config_reader.py
index 5c37aa2..9f4992d 100644
--- a/features/doc-service/app/services/config_reader.py
+++ b/features/doc-service/app/services/config_reader.py
@@ -2,10 +2,23 @@
 Reads doc_service_config.json from the shared config volume.
 Caches the result for 30 seconds to avoid hitting the filesystem on every request.
 Uses asyncio.to_thread so the synchronous file read doesn't block the event loop.
+
+Env var overrides (take precedence over the JSON config file, never committed):
+  AI_PROVIDER          — "lmstudio" | "ollama" | "anthropic"
+  LMSTUDIO_BASE_URL    — e.g. http://host.docker.internal:1234/v1
+  LMSTUDIO_API_KEY
+  LMSTUDIO_MODEL
+  OLLAMA_BASE_URL
+  OLLAMA_MODEL
+  OLLAMA_API_KEY
+  ANTHROPIC_API_KEY
+  ANTHROPIC_MODEL
 """
 import asyncio
 import json
+import os
 import time
+from copy import deepcopy
 from pathlib import Path
 
 from app.core.config import settings
@@ -31,9 +44,52 @@ _CACHE_TTL = 30.0
 def _read_config_sync() -> dict:
     path = Path(settings.CONFIG_PATH)
     if not path.exists():
-        return _DEFAULT_CONFIG.copy()
-    with open(path) as f:
-        return json.load(f)
+        base = deepcopy(_DEFAULT_CONFIG)
+    else:
+        with open(path) as f:
+            base = json.load(f)
+    return _apply_env_overrides(base)
+
+
+def _apply_env_overrides(config: dict) -> dict:
+    """
+    Merge environment variable overrides into the config dict.
+    Env vars win over whatever is stored in the JSON file.
+    This lets the dev .env file pin the AI connection without writing to the
+    shared volume (which would affect all users).
+    """
+    cfg = deepcopy(config)
+    ai = cfg.setdefault("ai", {})
+
+    if provider := os.environ.get("AI_PROVIDER"):
+        ai["provider"] = provider
+
+    # LM Studio
+    lms = ai.setdefault("lmstudio", {})
+    if v := os.environ.get("LMSTUDIO_BASE_URL"):
+        lms["base_url"] = v
+    if v := os.environ.get("LMSTUDIO_API_KEY"):
+        lms["api_key"] = v
+    if v := os.environ.get("LMSTUDIO_MODEL"):
+        lms["model"] = v
+
+    # Ollama
+    oll = ai.setdefault("ollama", {})
+    if v := os.environ.get("OLLAMA_BASE_URL"):
+        oll["base_url"] = v
+    if v := os.environ.get("OLLAMA_MODEL"):
+        oll["model"] = v
+    if v := os.environ.get("OLLAMA_API_KEY"):
+        oll["api_key"] = v
+
+    # Anthropic
+    ant = ai.setdefault("anthropic", {})
+    if v := os.environ.get("ANTHROPIC_API_KEY"):
+        ant["api_key"] = v
+    if v := os.environ.get("ANTHROPIC_MODEL"):
+        ant["model"] = v
+
+    return cfg
 
 
 async def load_doc_config() -> dict: