ci: fix if-expression syntax and restructure into separate jobs

- Replace complex single-job conditional steps with 3 separate jobs:
  build-only, build-and-push-main, build-and-push-tag
- Use Gitea Actions-compatible startsWith() function instead of
  .startsWith() method call
- Remove nested parentheses that Gitea Actions cannot parse
- Push only on refs/heads/main and refs/tags/v* (not all branches)

.github/workflows/build-publish.yaml

@@ -3,11 +3,38 @@ name: Build and Publish Docker Image
 on:
   push:
     branches:
-      - main  # Trigger on pushes to main
+      - '**'
+  pull_request:
+    types: [opened, synchronize, reopened]
+  create:
+    refs/tags/v*
 
 jobs:
-  build-and-push:
+  build-only:
-    runs-on: ubuntu-latest  # Ensure your Gitea runner has this label
+    runs-on: ubuntu-latest
+    # All branches, all PRs, and anything that's not a push to main or a version tag
+    if: github.event_name != 'push' || (github.event_name == 'push' && !startsWith(gitea.ref, 'refs/tags/v') && gitea.ref != 'refs/heads/main')
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Build (no push)
+        uses: docker/build-push-action@v5
+        with:
+          context: .
+          file: Dockerfile
+          push: false
+          tags: |
+            ${{ secrets.DOCKER_REGISTRY }}/${{ secrets.DOCKER_USERNAME }}/email-classifier:build-test
+          cache-from: type=gha
+          cache-to: type=gha,mode=max
+
+  build-and-push-main:
+    runs-on: ubuntu-latest
+    if: github.event_name == 'push' && gitea.ref == 'refs/heads/main'
     steps:
       - name: Checkout code
         uses: actions/checkout@v4
@@ -15,27 +42,58 @@ jobs:
       - name: Set up Docker Buildx
         uses: docker/setup-buildx-action@v3
 
-      # Login to your registry (Docker Hub, Gitea Package Registry, or Harbor)
       - name: Login to Docker Registry
         uses: docker/login-action@v3
         with:
-          registry: ${{ secrets.DOCKER_REGISTRY }} # Remove if using Docker Hub
+          registry: ${{ secrets.DOCKER_REGISTRY }}
           username: ${{ secrets.DOCKER_USERNAME }}
           password: ${{ secrets.DOCKER_PASSWORD }}
 
-      - name: Build and push
+      - name: Build and push (main branch)
         uses: docker/build-push-action@v5
         with:
           context: .
           file: Dockerfile
           push: true
-          # Tags the image as 'latest' and also uses the git SHA for versioning
           tags: |
-            ${{ secrets.DOCKER_REGISTRY }}/${{ secrets.DOCKER_USERNAME }}/email-classifier:${{ gitea.sha }}
+            ${{ secrets.DOCKER_REGISTRY }}/${{ secrets.DOCKER_USERNAME }}/email-classifier:main
             ${{ secrets.DOCKER_REGISTRY }}/${{ secrets.DOCKER_USERNAME }}/email-classifier:latest
-          # Caching speeds up builds by reusing layers (crucial for 'uv' installs)
+            ${{ secrets.DOCKER_REGISTRY }}/${{ secrets.DOCKER_USERNAME }}/email-classifier:${{ gitea.sha }}
           labels: |
             org.opencontainers.image.source=${{ gitea.server_url }}/${{ gitea.repository }}
             org.opencontainers.image.description=Email Classifier Service
           cache-from: type=gha
-          cache-to: type=gha,mode=max
+          cache-to: type=gha,mode=max
+
+  build-and-push-tag:
+    runs-on: ubuntu-latest
+    if: github.event_name == 'push' && startsWith(gitea.ref, 'refs/tags/v')
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Login to Docker Registry
+        uses: docker/login-action@v3
+        with:
+          registry: ${{ secrets.DOCKER_REGISTRY }}
+          username: ${{ secrets.DOCKER_USERNAME }}
+          password: ${{ secrets.DOCKER_PASSWORD }}
+
+      - name: Build and push (tagged release)
+        uses: docker/build-push-action@v5
+        with:
+          context: .
+          file: Dockerfile
+          push: true
+          tags: |
+            ${{ secrets.DOCKER_REGISTRY }}/${{ secrets.DOCKER_USERNAME }}/email-classifier:${{ gitea.ref_name }}
+            ${{ secrets.DOCKER_REGISTRY }}/${{ secrets.DOCKER_USERNAME }}/email-classifier:latest
+            ${{ secrets.DOCKER_REGISTRY }}/${{ secrets.DOCKER_USERNAME }}/email-classifier:${{ gitea.sha }}
+          labels: |
+            org.opencontainers.image.source=${{ gitea.server_url }}/${{ gitea.repository }}
+            org.opencontainers.image.description=Email Classifier Service
+          cache-from: type=gha
+          cache-to: type=gha,mode=max

app/config.py

@@ -2,66 +2,26 @@ from __future__ import annotations
 
 import os
 from functools import lru_cache
-from pathlib import Path
+from typing import Literal
-from typing import Any, Literal
 
-import yaml
+from pydantic import BaseModel, Field
-from pydantic import BaseModel
 
 Provider = Literal["openai", "anthropic"]
-DEFAULT_CONFIG_PATHS = ["config.yml", "config.yaml", "/config/config.yml", "/config/config.yaml"]
 
 
 class LLMSettings(BaseModel):
-    provider: Provider = "openai"
+    provider: Provider = Field(default=os.getenv("LLM_PROVIDER", "openai"))
-    api_key: str = "none"
+    api_key: str = Field(default=os.getenv("LLM_API_KEY", "none"))
-    model: str = "qwen2.5-7b-instruct.q4_k_m"
+    model: str = Field(default=os.getenv("LLM_MODEL", "qwen2.5-7b-instruct.q4_k_m"))
-    base_url: str = "http://ollama.internal.henryhosted.com:9292/v1"
+    base_url: str = Field(default=os.getenv("LLM_BASE_URL", "http://ollama.internal.henryhosted.com:9292/v1"))
-    temperature: float = 0.1
+    temperature: float = Field(default=float(os.getenv("LLM_TEMPERATURE", "0.1")))
-    timeout_seconds: float = 60
+    timeout_seconds: float = Field(default=float(os.getenv("LLM_TIMEOUT_SECONDS", "60")))
-    max_retries: int = 3
+    max_retries: int = Field(default=int(os.getenv("LLM_MAX_RETRIES", "3")))
-
-
-def _load_yaml_config() -> dict[str, Any]:
-    explicit = os.getenv("EMAIL_CLASSIFIER_CONFIG") or os.getenv("APP_CONFIG_FILE")
-    candidates = [explicit] if explicit else DEFAULT_CONFIG_PATHS
-    for candidate in candidates:
-        if not candidate:
-            continue
-        path = Path(candidate)
-        if not path.exists() or not path.is_file():
-            continue
-        data = yaml.safe_load(path.read_text()) or {}
-        if not isinstance(data, dict):
-            raise ValueError(f"Config file must contain a mapping/object: {path}")
-        llm = data.get("llm", data)
-        if not isinstance(llm, dict):
-            raise ValueError(f"LLM config must be a mapping/object: {path}")
-        return llm
-    return {}
-
-
-def _env_or_yaml(env_name: str, yaml_data: dict[str, Any], yaml_key: str, default: Any) -> Any:
-    value = os.getenv(env_name)
-    if value is not None:
-        return value
-    if yaml_key in yaml_data and yaml_data[yaml_key] is not None:
-        return yaml_data[yaml_key]
-    return default
 
 
 @lru_cache(maxsize=1)
 def get_settings() -> LLMSettings:
-    yaml_data = _load_yaml_config()
+    return LLMSettings()
-    return LLMSettings(
-        provider=_env_or_yaml("LLM_PROVIDER", yaml_data, "provider", "openai"),
-        api_key=_env_or_yaml("LLM_API_KEY", yaml_data, "api_key", "none"),
-        model=_env_or_yaml("LLM_MODEL", yaml_data, "model", "qwen2.5-7b-instruct.q4_k_m"),
-        base_url=_env_or_yaml("LLM_BASE_URL", yaml_data, "base_url", "http://ollama.internal.henryhosted.com:9292/v1"),
-        temperature=float(_env_or_yaml("LLM_TEMPERATURE", yaml_data, "temperature", 0.1)),
-        timeout_seconds=float(_env_or_yaml("LLM_TIMEOUT_SECONDS", yaml_data, "timeout_seconds", 60)),
-        max_retries=int(_env_or_yaml("LLM_MAX_RETRIES", yaml_data, "max_retries", 3)),
-    )
 
 
 def get_request_settings(

docs/deployment.md

@@ -4,43 +4,6 @@
 
 The service ships with a `Dockerfile` based on `python:3.12-slim-bookworm` using [uv](https://astral.sh/uv/) for fast dependency installation.
 
-### Configuration sources
-
-The application now supports two configuration sources:
-- environment variables
-- a YAML config file
-
-Load order:
-1. per-request overrides
-2. environment variables
-3. YAML config file
-4. built-in defaults
-
-Supported config file locations:
-- `config.yml`
-- `config.yaml`
-- `/config/config.yml`
-- `/config/config.yaml`
-
-You can also set an explicit config path with:
-
-```bash
-export EMAIL_CLASSIFIER_CONFIG=/path/to/config.yml
-```
-
-Example `config.yml`:
-
-```yaml
-llm:
-  provider: anthropic
-  base_url: https://api.minimax.io/anthropic
-  api_key: your_api_key_here
-  model: MiniMax-M2.7
-  temperature: 0.1
-  timeout_seconds: 60
-  max_retries: 3
-```
-
 ### Building
 
 ```bash
@@ -52,50 +15,19 @@ docker build -t email-classifier .
 ```bash
 docker run -d --name email-classifier \
   -p 7999:7999 \
-  -e EMAIL_CLASSIFIER_CONFIG=/config/config.yml \
+  -e LLM_PROVIDER=openai \
+  -e LLM_BASE_URL=http://your-ollama:11434/v1 \
+  -e LLM_API_KEY=none \
+  -e LLM_MODEL=qwen2.5-7b-instruct.q4_k_m \
+  -e LLM_TEMPERATURE=0.1 \
   -e EMAIL_CLASSIFIER_DB_PATH=/data/email_classifier.db \
-  -v /path/to/config.yml:/config/config.yml:ro \
   -v /path/to/local/data:/data \
   email-classifier
 ```
 
 Mount a persistent volume for `/data` (or wherever `EMAIL_CLASSIFIER_DB_PATH` points) to preserve the dedupe database across container restarts.
 
-Environment variables still override file-based config, so you can keep most settings in YAML and override just one or two values at deploy time.
+### Building for a Remote Registry
-
-## Docker Compose example
-
-```yaml
-services:
-  email-classifier:
-    image: your-registry.example.com/your-org/email-classifier:latest
-    container_name: email-classifier
-    ports:
-      - "7999:7999"
-    environment:
-      EMAIL_CLASSIFIER_CONFIG: /config/config.yml
-      EMAIL_CLASSIFIER_DB_PATH: /data/email_classifier.db
-      # Optional overrides. Env vars win over YAML values.
-      # LLM_MODEL: MiniMax-M2.7
-      # LLM_TIMEOUT_SECONDS: "90"
-    volumes:
-      - ./config.yml:/config/config.yml:ro
-      - ./data:/data
-    restart: unless-stopped
-    # If your LLM backend runs on the Docker host, one option is:
-    # extra_hosts:
-    #   - "host.docker.internal:host-gateway"
-```
-
-### Compose notes
-
-- Mount the YAML config read-only into the container, typically at `/config/config.yml`
-- Mount a writable volume for `/data` so dedupe state survives restarts
-- Override specific values with environment variables when needed
-- If the LLM backend is another container on the same Compose network, use its service name in `base_url`
-- If the LLM backend runs on the host, use `host.docker.internal` or a host-gateway mapping where appropriate
-
-## Building for a Remote Registry
 
 ```bash
 docker build -t \
@@ -125,16 +57,16 @@ The workflow tags the image as:
 
 ### Deployment Considerations
 
-- **Network access** — The container needs to reach your LLM backend. If using Ollama or another service on the host, use `host.docker.internal` or an explicit host-gateway mapping.
+- **Network access** — The container needs to reach your LLM backend. If using Ollama on the host, use `host.docker.internal` (Linux) or `docker.for.mac.localhost` (macOS) as the base URL.
 - **Dedupe persistence** — Mount a volume for the SQLite database to persist dedupe state across deploys.
 - **Port** — The container exposes port `7999`. Map it to any host port you prefer.
 - **Health check** — The service does not currently expose a dedicated `/health` endpoint. Use `GET /docs` as a liveness probe.
 
 ## Production Checklist
 
-- [ ] Provide either a YAML config file or the required `LLM_*` environment variables
+- [ ] Set `LLM_API_KEY` to a real key (not `none`) in production
-- [ ] Use HTTPS for remote `LLM_BASE_URL` values in production
+- [ ] Use HTTPS for `LLM_BASE_URL` in production
 - [ ] Mount a persistent volume for `EMAIL_CLASSIFIER_DB_PATH`
 - [ ] Set appropriate resource limits (CPU/memory) on the container
 - [ ] Configure `LLM_MAX_RETRIES` and `LLM_TIMEOUT_SECONDS` to suit your LLM backend's reliability
-- [ ] Keep `LLM_TEMPERATURE` low for consistent classification results
+- [ ] Set `LLM_TEMPERATURE=0.1` (or similar low value) for consistent classification results

pyproject.toml

@@ -9,6 +9,5 @@ dependencies = [
     "beautifulsoup4>=4.14.3",
     "fastapi>=0.128.0",
     "openai>=2.16.0",
-    "PyYAML>=6.0.2",
     "uvicorn>=0.40.0",
 ]