devopsiq 0.1.0__tar.gz → 0.1.1__tar.gz

{devopsiq-0.1.0/devopsiq.egg-info → devopsiq-0.1.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: devopsiq
-Version: 0.1.0
+Version: 0.1.1
 Summary: A from-scratch, read-only AI agent that investigates real DevOps problems — Kubernetes, Docker, Helm, Argo CD, Istio, Terraform, GitHub Actions, cloud, New Relic and more.
 Author: DevOpsAbhii
 License-Expression: MIT
@@ -400,6 +400,30 @@ Swapping to another OpenRouter model later is a one-line change (an env var
 today); moving to any other OpenAI-compatible provider changes only
 `agent/agent.py` configuration.
 
+**Your model, your choice.** The default is baked in as a fallback, never a
+restriction — set `OPENROUTER_MODEL` (shell or `.env`) to any model on
+OpenRouter:
+
+```bash
+export OPENROUTER_MODEL=anthropic/claude-sonnet-5   # or openai/gpt-5.2, google/gemini-2.5-pro, ...
+```
+
+Two things to weigh when picking: the agent is a tool-use loop, so choose a
+model with solid function-calling (a chat-only model will answer from
+imagination instead of gathering evidence); and an investigation makes
+several model calls per run, so price-per-call multiplies — that is why the
+default is a cheap, reliable tool-caller rather than the biggest model.
+
+**No OpenRouter at all?** `OPENROUTER_BASE_URL` points the same client at
+any OpenAI-compatible endpoint — including a local one. Ollama, free and
+offline:
+
+```bash
+export OPENROUTER_BASE_URL=http://localhost:11434/v1
+export OPENROUTER_MODEL=llama3.2          # any Ollama model that does tools
+devopsiq "docker container checkout keeps exiting, investigate"
+```
+
 ## 5. Installation
 
 Three ways — pick one. Whatever you choose, the agent also needs the CLIs of
@@ -463,6 +487,27 @@ Recommended CLIs, by domain:
 | New Relic    | `curl` + `NEW_RELIC_API_KEY` / `NEW_RELIC_ACCOUNT_ID` env vars |
 | Ansible      | `ansible-inventory`, `ansible-playbook`          |
 
+### No API key? You still have the tools
+
+The model is the only part that needs a key — the agent builds without one
+(model-less mode), and two things keep working:
+
+- **Record commands**: `devopsiq /report`, `devopsiq /investigations`, and
+  the same commands inside the REPL, all work with no key configured. Only
+  actual questions exit 1 with the setup message naming `OPENROUTER_API_KEY`.
+- **The whole 58-tool layer** via the Python library, with no model and no
+  key (see INTEGRATION.md):
+
+```python
+import agent.agent                            # registers every tool
+from tools.registry import execute_tool
+
+print(execute_tool("k8s_pods", '{"namespace": "prod"}'))
+```
+
+And the fully key-free *agent* path is a local model (Ollama example in
+section 4 above) — no cloud account needed at all.
+
 ## 6. Environment setup
 
 ```bash
@@ -490,7 +535,9 @@ NEW_RELIC_ACCOUNT_ID=1234567                        # (Phase 9) numeric account
 
 `.env` is gitignored; the API key is never hard-coded in Python, printed, or
 logged. If `OPENROUTER_API_KEY` is already set in your shell, the shell value
-wins and `.env` is not consulted. Kubernetes tools use kubectl's own config
+wins and `.env` is not consulted. Without any key the agent still starts in
+model-less mode (record commands + the tool layer — see "No API key?" in
+section 5). Kubernetes tools use kubectl's own config
 (`~/.kube/config` or `KUBECONFIG`); no agent-side config is needed.
 
 ## 7. How to run the agent

{devopsiq-0.1.0 → devopsiq-0.1.1}/README.md

@@ -371,6 +371,30 @@ Swapping to another OpenRouter model later is a one-line change (an env var
 today); moving to any other OpenAI-compatible provider changes only
 `agent/agent.py` configuration.
 
+**Your model, your choice.** The default is baked in as a fallback, never a
+restriction — set `OPENROUTER_MODEL` (shell or `.env`) to any model on
+OpenRouter:
+
+```bash
+export OPENROUTER_MODEL=anthropic/claude-sonnet-5   # or openai/gpt-5.2, google/gemini-2.5-pro, ...
+```
+
+Two things to weigh when picking: the agent is a tool-use loop, so choose a
+model with solid function-calling (a chat-only model will answer from
+imagination instead of gathering evidence); and an investigation makes
+several model calls per run, so price-per-call multiplies — that is why the
+default is a cheap, reliable tool-caller rather than the biggest model.
+
+**No OpenRouter at all?** `OPENROUTER_BASE_URL` points the same client at
+any OpenAI-compatible endpoint — including a local one. Ollama, free and
+offline:
+
+```bash
+export OPENROUTER_BASE_URL=http://localhost:11434/v1
+export OPENROUTER_MODEL=llama3.2          # any Ollama model that does tools
+devopsiq "docker container checkout keeps exiting, investigate"
+```
+
 ## 5. Installation
 
 Three ways — pick one. Whatever you choose, the agent also needs the CLIs of
@@ -434,6 +458,27 @@ Recommended CLIs, by domain:
 | New Relic    | `curl` + `NEW_RELIC_API_KEY` / `NEW_RELIC_ACCOUNT_ID` env vars |
 | Ansible      | `ansible-inventory`, `ansible-playbook`          |
 
+### No API key? You still have the tools
+
+The model is the only part that needs a key — the agent builds without one
+(model-less mode), and two things keep working:
+
+- **Record commands**: `devopsiq /report`, `devopsiq /investigations`, and
+  the same commands inside the REPL, all work with no key configured. Only
+  actual questions exit 1 with the setup message naming `OPENROUTER_API_KEY`.
+- **The whole 58-tool layer** via the Python library, with no model and no
+  key (see INTEGRATION.md):
+
+```python
+import agent.agent                            # registers every tool
+from tools.registry import execute_tool
+
+print(execute_tool("k8s_pods", '{"namespace": "prod"}'))
+```
+
+And the fully key-free *agent* path is a local model (Ollama example in
+section 4 above) — no cloud account needed at all.
+
 ## 6. Environment setup
 
 ```bash
@@ -461,7 +506,9 @@ NEW_RELIC_ACCOUNT_ID=1234567                        # (Phase 9) numeric account
 
 `.env` is gitignored; the API key is never hard-coded in Python, printed, or
 logged. If `OPENROUTER_API_KEY` is already set in your shell, the shell value
-wins and `.env` is not consulted. Kubernetes tools use kubectl's own config
+wins and `.env` is not consulted. Without any key the agent still starts in
+model-less mode (record commands + the tool layer — see "No API key?" in
+section 5). Kubernetes tools use kubectl's own config
 (`~/.kube/config` or `KUBECONFIG`); no agent-side config is needed.
 
 ## 7. How to run the agent

{devopsiq-0.1.0 → devopsiq-0.1.1}/agent/agent.py

@@ -80,23 +80,30 @@ class DevOpsAgent:
     ) -> None:
         # Configuration resolution order: explicit argument > environment > default.
         self.api_key = api_key or os.getenv("OPENROUTER_API_KEY")
+
+        self.model = model or os.getenv("OPENROUTER_MODEL", DEFAULT_MODEL)
+        self.base_url = base_url or os.getenv("OPENROUTER_BASE_URL", DEFAULT_BASE_URL)
+
+        # Model-less mode: a missing (or placeholder) key no longer blocks
+        # construction. Record operations (the slash commands) and the tool
+        # layer never call the model, so the agent builds with client=None
+        # and only the chat path (_complete) demands a working key.
+        self.client = None
+        self.model_error: str | None = None
         if not self.api_key:
-            raise ValueError(
+            self.model_error = (
                 "OPENROUTER_API_KEY is not set. Copy .env.example to .env and "
                 "fill in your key, or export OPENROUTER_API_KEY in your shell."
             )
-        if self.api_key.strip().lower() == PLACEHOLDER_KEY:
-            raise ValueError(
+        elif self.api_key.strip().lower() == PLACEHOLDER_KEY:
+            self.model_error = (
                 "OPENROUTER_API_KEY still has the placeholder value. Edit .env "
                 "and replace `your_key_here` with your real key."
             )
-
-        self.model = model or os.getenv("OPENROUTER_MODEL", DEFAULT_MODEL)
-        self.base_url = base_url or os.getenv("OPENROUTER_BASE_URL", DEFAULT_BASE_URL)
-
-        # OpenRouter exposes an OpenAI-compatible API, so the official OpenAI
-        # SDK is a drop-in client — just pointed at OpenRouter's base URL.
-        self.client = OpenAI(api_key=self.api_key, base_url=self.base_url)
+        else:
+            # OpenRouter exposes an OpenAI-compatible API, so the official
+            # OpenAI SDK is a drop-in client — just pointed at the base URL.
+            self.client = OpenAI(api_key=self.api_key, base_url=self.base_url)
 
         # Short-term conversation history. Starts with the system prompt;
         # grows as user, model, and tool results exchange turns.
@@ -110,7 +117,8 @@ class DevOpsAgent:
 
         The message, any tool exchanges, and the final assistant reply are all
         kept in this session's history so the model retains context across
-        turns. Raises ValueError on empty input.
+        turns. Raises ValueError on empty input, or when no API key is
+        configured (model-less mode).
         """
         message = user_message.strip()
         if not message:
@@ -180,6 +188,10 @@ class DevOpsAgent:
         model again. Stops when the model answers in plain text, or when the
         iteration cap is reached.
         """
+        if self.client is None:
+            # Model-less construction: the first chat attempt is where the
+            # missing key finally surfaces, as a normal caught ValueError.
+            raise ValueError(self.model_error)
         for _ in range(MAX_TOOL_ITERATIONS):
             request: dict = {"model": self.model, "messages": self.messages}
             if self.tools:

{devopsiq-0.1.0 → devopsiq-0.1.1/devopsiq.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: devopsiq
-Version: 0.1.0
+Version: 0.1.1
 Summary: A from-scratch, read-only AI agent that investigates real DevOps problems — Kubernetes, Docker, Helm, Argo CD, Istio, Terraform, GitHub Actions, cloud, New Relic and more.
 Author: DevOpsAbhii
 License-Expression: MIT
@@ -400,6 +400,30 @@ Swapping to another OpenRouter model later is a one-line change (an env var
 today); moving to any other OpenAI-compatible provider changes only
 `agent/agent.py` configuration.
 
+**Your model, your choice.** The default is baked in as a fallback, never a
+restriction — set `OPENROUTER_MODEL` (shell or `.env`) to any model on
+OpenRouter:
+
+```bash
+export OPENROUTER_MODEL=anthropic/claude-sonnet-5   # or openai/gpt-5.2, google/gemini-2.5-pro, ...
+```
+
+Two things to weigh when picking: the agent is a tool-use loop, so choose a
+model with solid function-calling (a chat-only model will answer from
+imagination instead of gathering evidence); and an investigation makes
+several model calls per run, so price-per-call multiplies — that is why the
+default is a cheap, reliable tool-caller rather than the biggest model.
+
+**No OpenRouter at all?** `OPENROUTER_BASE_URL` points the same client at
+any OpenAI-compatible endpoint — including a local one. Ollama, free and
+offline:
+
+```bash
+export OPENROUTER_BASE_URL=http://localhost:11434/v1
+export OPENROUTER_MODEL=llama3.2          # any Ollama model that does tools
+devopsiq "docker container checkout keeps exiting, investigate"
+```
+
 ## 5. Installation
 
 Three ways — pick one. Whatever you choose, the agent also needs the CLIs of
@@ -463,6 +487,27 @@ Recommended CLIs, by domain:
 | New Relic    | `curl` + `NEW_RELIC_API_KEY` / `NEW_RELIC_ACCOUNT_ID` env vars |
 | Ansible      | `ansible-inventory`, `ansible-playbook`          |
 
+### No API key? You still have the tools
+
+The model is the only part that needs a key — the agent builds without one
+(model-less mode), and two things keep working:
+
+- **Record commands**: `devopsiq /report`, `devopsiq /investigations`, and
+  the same commands inside the REPL, all work with no key configured. Only
+  actual questions exit 1 with the setup message naming `OPENROUTER_API_KEY`.
+- **The whole 58-tool layer** via the Python library, with no model and no
+  key (see INTEGRATION.md):
+
+```python
+import agent.agent                            # registers every tool
+from tools.registry import execute_tool
+
+print(execute_tool("k8s_pods", '{"namespace": "prod"}'))
+```
+
+And the fully key-free *agent* path is a local model (Ollama example in
+section 4 above) — no cloud account needed at all.
+
 ## 6. Environment setup
 
 ```bash
@@ -490,7 +535,9 @@ NEW_RELIC_ACCOUNT_ID=1234567                        # (Phase 9) numeric account
 
 `.env` is gitignored; the API key is never hard-coded in Python, printed, or
 logged. If `OPENROUTER_API_KEY` is already set in your shell, the shell value
-wins and `.env` is not consulted. Kubernetes tools use kubectl's own config
+wins and `.env` is not consulted. Without any key the agent still starts in
+model-less mode (record commands + the tool layer — see "No API key?" in
+section 5). Kubernetes tools use kubectl's own config
 (`~/.kube/config` or `KUBECONFIG`); no agent-side config is needed.
 
 ## 7. How to run the agent

{devopsiq-0.1.0 → devopsiq-0.1.1}/main.py

@@ -253,6 +253,13 @@ def main() -> int:
         print(f"[setup] {exc}", file=sys.stderr)
         return 1
 
+    if agent.client is None:
+        # Model-less mode: the REPL still starts — record commands (slash
+        # commands) work, only questions to the model are unavailable.
+        print(f"[setup] {agent.model_error}", file=sys.stderr)
+        print("[setup] Starting without a model — slash commands still work; "
+              "questions need OPENROUTER_API_KEY.", file=sys.stderr)
+
     tool_names = ", ".join(sorted(tool.name for tool in agent.tools)) or "none"
 
     print("DevOps AI Agent (Phase 9 — 58 read-only tools, persistent investigations)")

{devopsiq-0.1.0 → devopsiq-0.1.1}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "devopsiq"
-version = "0.1.0"
+version = "0.1.1"
 description = "A from-scratch, read-only AI agent that investigates real DevOps problems — Kubernetes, Docker, Helm, Argo CD, Istio, Terraform, GitHub Actions, cloud, New Relic and more."
 readme = "README.md"
 license = "MIT"

{devopsiq-0.1.0 → devopsiq-0.1.1}/tests/test_automation.py

@@ -247,5 +247,58 @@ class OneShotCliTests(unittest.TestCase):
         json.loads(out)  # the entire stdout must be one valid JSON document
 
 
+class KeylessTests(unittest.TestCase):
+    """Model-less mode: no API key configured.
+
+    The agent must still construct (record commands + tool layer never call
+    the model); only the chat path raises, and the CLI reports it loudly.
+    """
+
+    def setUp(self):
+        self._old_key = os.environ.get("OPENROUTER_API_KEY")
+        os.environ.pop("OPENROUTER_API_KEY", None)
+        self.addCleanup(self._restore_key)
+        inv_tools.set_store(None)
+
+    def _restore_key(self):
+        os.environ.pop("OPENROUTER_API_KEY", None)
+        if self._old_key is not None:
+            os.environ["OPENROUTER_API_KEY"] = self._old_key
+        inv_tools.finish_investigation()
+        inv_tools.set_store(None)
+
+    def test_agent_constructs_without_a_key(self):
+        agent = DevOpsAgent()
+        self.assertIsNone(agent.client)
+        self.assertIn("OPENROUTER_API_KEY", agent.model_error)
+        self.assertTrue(agent.tools)  # the tool layer is fully usable
+
+    def test_placeholder_key_is_also_model_less(self):
+        os.environ["OPENROUTER_API_KEY"] = "your_key_here"
+        agent = DevOpsAgent()
+        self.assertIsNone(agent.client)
+        self.assertIn("placeholder", agent.model_error)
+
+    def test_ask_without_key_raises_loud(self):
+        agent = DevOpsAgent()
+        with self.assertRaises(ValueError) as ctx:
+            agent.ask("why is it down?")
+        self.assertIn("OPENROUTER_API_KEY", str(ctx.exception))
+
+    def test_oneshot_slash_command_works_without_key(self):
+        out = io.StringIO()
+        with contextlib.redirect_stdout(out):
+            code = main_module.run_one_shot("/report")
+        self.assertEqual(code, 0)
+        self.assertIn("(no investigation recorded)", out.getvalue())
+
+    def test_oneshot_question_without_key_exits_1(self):
+        err = io.StringIO()
+        with contextlib.redirect_stdout(err), contextlib.redirect_stderr(err):
+            code = main_module.run_one_shot("why is api-5d6f crash-looping?")
+        self.assertEqual(code, 1)
+        self.assertIn("OPENROUTER_API_KEY", err.getvalue())
+
+
 if __name__ == "__main__":
     unittest.main()