maintenance: CI migration, code hygiene, and test suite

.github/workflows/ci.yml

@@ -0,0 +1,76 @@
+name: CI
+
+on:
+  push:
+  pull_request:
+
+jobs:
+  # ------------------------------------------------------------------
+  # Job 1: run pytest — every branch, every PR
+  # ------------------------------------------------------------------
+  test:
+    name: pytest
+    runs-on: ubuntu-latest
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - uses: actions/setup-python@v5
+        with:
+          python-version: "3.11"
+          cache: pip
+
+      - name: Install dependencies
+        run: pip install -r requirements.txt
+
+      - name: Run tests
+        run: pytest tests/ -v
+
+  # ------------------------------------------------------------------
+  # Job 2: build & push Docker image to GHCR
+  # Runs only on pushes to main or tag pushes; requires tests to pass.
+  # ------------------------------------------------------------------
+  build-and-push:
+    name: Build and push Docker image
+    runs-on: ubuntu-latest
+    needs: test
+    if: |
+      github.event_name == 'push' &&
+      (github.ref == 'refs/heads/main' || startsWith(github.ref, 'refs/tags/'))
+
+    permissions:
+      contents: read
+      packages: write
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Log in to GitHub Container Registry
+        uses: docker/login-action@v3
+        with:
+          registry: ghcr.io
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Derive image tags
+        id: tags
+        run: |
+          REGISTRY="ghcr.io/${{ github.repository }}"
+          REF_SLUG="${GITHUB_REF_NAME//\//-}"   # replace '/' with '-' for branch names
+          SHORT_SHA="${GITHUB_SHA::8}"
+
+          TAGS="${REGISTRY}:${REF_SLUG},${REGISTRY}:${SHORT_SHA}"
+
+          # Add :latest only for pushes to main
+          if [ "${{ github.ref }}" = "refs/heads/main" ]; then
+            TAGS="${TAGS},${REGISTRY}:latest"
+          fi
+
+          echo "tags=${TAGS}" >> "$GITHUB_OUTPUT"
+
+      - name: Build and push
+        uses: docker/build-push-action@v5
+        with:
+          context: .
+          push: true
+          tags: ${{ steps.tags.outputs.tags }}

.pre-commit-config.yaml

@@ -0,0 +1,9 @@
+repos:
+  - repo: local
+    hooks:
+      - id: pytest
+        name: pytest
+        entry: pytest tests/
+        language: system
+        pass_filenames: false
+        always_run: true

agents.py

@@ -1,7 +1,9 @@
+from typing import Callable
+
 from omegaconf import DictConfig
 
 from smolagents import CodeAgent, OpenAIServerModel, WikipediaSearchTool, tool, LogLevel
-from tools import opencti_tools, osint_tools, todays_date
+from tools import opencti_tools, opencti_write_tools, osint_tools, attack_tools, todays_date
 
 
 def create_llm_model(model_id: str, api_key: str, api_base: str = "https://openrouter.ai/api/v1") -> OpenAIServerModel:
@@ -14,68 +16,94 @@ def create_llm_model(model_id: str, api_key: str, api_base: str = "https://openr
         max_tokens=10_000,
     )
 
+
+# Registry: maps a tool-set name to a factory that returns a list of tool instances.
+# Adding a new tool group = one dict entry.
+_TOOL_REGISTRY: dict[str, Callable[[], list]] = {
+    "opencti":       lambda: [tool(t) for t in opencti_tools],
+    "opencti_write": lambda: [tool(t) for t in opencti_write_tools],
+    "osint":         lambda: [tool(t) for t in osint_tools],
+    "attack":        lambda: [tool(t) for t in attack_tools],
+    "wikipedia":     lambda: [WikipediaSearchTool()],
+    "todays_date":   lambda: [tool(todays_date)],
+}
+
+
 def get_agent_tools(tool_names: list[str] | str) -> list:
     """Gets the tool instances from their names."""
     if isinstance(tool_names, str):
         tool_names = [tool_names] if tool_names != "none" else []
 
     tools = []
     for name in tool_names:
-        if name == "opencti":
-            tools.extend([tool(t) for t in opencti_tools])
-        elif name == "osint":
-            tools.extend([tool(t) for t in osint_tools])
-        elif name == "wikipedia":
-            tools.append(WikipediaSearchTool())
-        elif name == "todays_date":
-            tools.append(tool(todays_date))
-        else:
+        factory = _TOOL_REGISTRY.get(name)
+        if factory is None:
             raise ValueError(f"Unknown tool name: {name}")
+        tools.extend(factory())
     return tools
 
-def create_agent(cfg: DictConfig, model: OpenAIServerModel):
-    """Creates an agent instance based on the hydra configuration."""
-    # Look up the agent configuration from the library using the agent_name
-    agent_cfg = cfg.agent_lib[cfg.agent_name]
-    agent_type = agent_cfg.type
 
-    if agent_type == "simple":
-        blueprint = cfg.agent_definitions[agent_cfg.blueprint]
-        return CodeAgent(
+# ---------------------------------------------------------------------------
+# Private builder functions — one per agent type
+# ---------------------------------------------------------------------------
+
+def _build_simple(cfg: DictConfig, agent_cfg, model: OpenAIServerModel) -> CodeAgent:
+    blueprint = cfg.agent_definitions[agent_cfg.blueprint]
+    return CodeAgent(
+        model=model,
+        tools=get_agent_tools(blueprint.tools),
+        verbosity_level=LogLevel.DEBUG,
+        name=blueprint.name,
+        description=blueprint.description,
+    )
+
+
+def _build_all_in_one(cfg: DictConfig, agent_cfg, model: OpenAIServerModel) -> CodeAgent:
+    return CodeAgent(
+        model=model,
+        tools=get_agent_tools(["opencti", "osint", "wikipedia", "todays_date"]),
+        verbosity_level=LogLevel.DEBUG,
+        planning_interval=3,
+        name="all_task_agent",
+    )
+
+
+def _build_managing(cfg: DictConfig, agent_cfg, model: OpenAIServerModel) -> CodeAgent:
+    managed_agents = []
+    for agent_key in agent_cfg.managed_agents:
+        blueprint = cfg.agent_definitions[agent_key]
+        managed_agent = CodeAgent(
             model=model,
             tools=get_agent_tools(blueprint.tools),
             verbosity_level=LogLevel.DEBUG,
             name=blueprint.name,
             description=blueprint.description,
         )
-    elif agent_type == "all_in_one":
-        return CodeAgent(
-            model=model,
-            tools=get_agent_tools(["opencti", "osint", "wikipedia", "todays_date"]),
-            verbosity_level=LogLevel.DEBUG,
-            planning_interval=3,
-            name="all_task_agent",
-        )
-    elif agent_type == "managing":
-        managed_agents = []
-        for agent_key in agent_cfg.managed_agents:
-            blueprint = cfg.agent_definitions[agent_key]
-            managed_agent = CodeAgent(
-                model=model,
-                tools=get_agent_tools(blueprint.tools),
-                verbosity_level=LogLevel.DEBUG,
-                name=blueprint.name,
-                description=blueprint.description,
-            )
-            managed_agents.append(managed_agent)
-
-        return CodeAgent(
-            model=model,
-            tools=[tool(todays_date)],
-            verbosity_level=LogLevel.DEBUG,
-            planning_interval=3,
-            managed_agents=managed_agents,
-            name="managing_agent",
-        )
-    else:
-        raise ValueError(f"Unknown agent type: {agent_type}")
+        managed_agents.append(managed_agent)
+
+    return CodeAgent(
+        model=model,
+        tools=[tool(todays_date)],
+        verbosity_level=LogLevel.DEBUG,
+        planning_interval=3,
+        managed_agents=managed_agents,
+        name="managing_agent",
+    )
+
+
+# Registry: adding a new agent type = one dict entry
+_BUILDERS: dict[str, Callable] = {
+    "simple":      _build_simple,
+    "all_in_one":  _build_all_in_one,
+    "managing":    _build_managing,
+}
+
+
+def create_agent(cfg: DictConfig, model: OpenAIServerModel) -> CodeAgent:
+    """Creates an agent instance based on the hydra configuration."""
+    agent_cfg = cfg.agent_lib[cfg.agent_name]
+    builder = _BUILDERS.get(agent_cfg.type)
+    if builder is None:
+        raise ValueError(f"Unknown agent type: {agent_cfg.type}")
+    return builder(cfg, agent_cfg, model)
+