Add LLM server integration for connecting agents (claude, codex) to Ollama, vLLM, and other providers

docs/configuration.md

@@ -85,6 +85,13 @@ agents:
     volumes: []
     init: []
 
+# Connect agents to a local or remote LLM server (Ollama, vLLM, etc.)
+llm:
+  enabled: false
+  base_url: ""       # Server endpoint URL
+  api_key: ""        # Auth token (set to "ollama" for Ollama)
+  model: ""          # Model name passed to the agent
+
 logging:
   enabled: true
   image: vibepod/datasette:latest
@@ -111,6 +118,10 @@ These variables override the corresponding config keys without editing any file:
 | `VP_NO_COLOR` | `no_color` | `VP_NO_COLOR=true` |
 | `VP_DATASETTE_PORT` | `logging.ui_port` | `VP_DATASETTE_PORT=9001` |
 | `VP_PROXY_ENABLED` | `proxy.enabled` | `VP_PROXY_ENABLED=false` |
+| `VP_LLM_ENABLED` | `llm.enabled` | `VP_LLM_ENABLED=true` |
+| `VP_LLM_BASE_URL` | `llm.base_url` | `VP_LLM_BASE_URL=http://localhost:11434` |
+| `VP_LLM_API_KEY` | `llm.api_key` | `VP_LLM_API_KEY=ollama` |
+| `VP_LLM_MODEL` | `llm.model` | `VP_LLM_MODEL=qwen3:14b` |
 | `VP_CONFIG_DIR` | *(config root)* | `VP_CONFIG_DIR=/custom/path` |
 
 ### Image overrides

docs/llm.md

@@ -0,0 +1,122 @@
+# Using OSS Models via Ollama, vLLM, and other LLM servers
+
+VibePod can connect agents to external LLM servers that expose OpenAI- or Anthropic-compatible APIs. This lets you run agents like Claude Code and Codex against open-source models served by [Ollama](https://ollama.com), [vLLM](https://docs.vllm.ai), or any compatible endpoint.
+
+## Supported agents
+
+| Agent | Env vars injected | CLI flags appended |
+|-------|------------------|--------------------|
+| claude | `ANTHROPIC_BASE_URL`, `ANTHROPIC_API_KEY` | `--model <model>` |
+| codex | `CODEX_OSS_BASE_URL` | `--oss -m <model>` |
+
+Other agents do not yet have LLM mapping and will not receive any LLM configuration.
+
+## Quick start with Ollama
+
+### 1. Start Ollama and pull a model
+
+```bash
+ollama pull qwen3:14b
+```
+
+### 2. Configure VibePod
+
+Add the following to your global or project config:
+
+```yaml
+# ~/.config/vibepod/config.yaml
+llm:
+  enabled: true
+  base_url: "http://host.docker.internal:11434"
+  api_key: "ollama"
+  model: "qwen3:14b"
+```
+
+!!! note
+    Use `host.docker.internal` (not `localhost`) so the Docker container can reach Ollama on the host machine.
+
+### 3. Run an agent
+
+```bash
+vp run claude
+# Starts Claude Code with:
+#   ANTHROPIC_BASE_URL=http://host.docker.internal:11434
+#   ANTHROPIC_API_KEY=ollama
+#   claude --model qwen3:14b
+
+vp run codex
+# Starts Codex with:
+#   CODEX_OSS_BASE_URL=http://host.docker.internal:11434
+#   codex --oss -m qwen3:14b
+```
+
+## Using environment variables
+
+You can also configure LLM settings at runtime without editing config files.
+
+**Claude Code with a remote Ollama server:**
+
+```bash
+VP_LLM_ENABLED=true VP_LLM_MODEL=qwen3.5:9b VP_LLM_BASE_URL=https://ollama.example.com vp run claude
+```
+
+**Codex with a remote Ollama server (note the `/v1` suffix):**
+
+```bash
+VP_LLM_ENABLED=true VP_LLM_MODEL=qwen3.5:9b VP_LLM_BASE_URL=https://ollama.example.com/v1 vp run codex
+```
+
+**Local Ollama with an API key:**
+
+```bash
+VP_LLM_ENABLED=true VP_LLM_BASE_URL=http://host.docker.internal:11434 VP_LLM_API_KEY=ollama VP_LLM_MODEL=qwen3:14b vp run claude
+```
+
+!!! note
+    Claude Code uses the Anthropic-compatible endpoint (no `/v1` suffix), while Codex uses the OpenAI-compatible endpoint (with `/v1` suffix). Adjust `VP_LLM_BASE_URL` accordingly, or use per-agent overrides if you need both agents to work from the same config.
+
+See [Configuration > Environment variables](configuration.md#environment-variables) for the full list.
+
+## Using vLLM or other OpenAI-compatible servers
+
+Point `base_url` at any server that speaks the OpenAI or Anthropic API:
+
+```yaml
+llm:
+  enabled: true
+  base_url: "http://my-vllm-server:8000/v1"
+  api_key: "my-api-key"
+  model: "meta-llama/Llama-3-8B-Instruct"
+```
+
+## Per-agent overrides
+
+If you need different LLM settings for a specific agent, use the per-agent `env` config. Per-agent env vars take precedence over the `llm` section:
+
+```yaml
+llm:
+  enabled: true
+  base_url: "http://host.docker.internal:11434"
+  api_key: "ollama"
+  model: "qwen3:14b"
+
+agents:
+  claude:
+    env:
+      ANTHROPIC_BASE_URL: "http://different-server:11434"
+```
+
+## Disabling
+
+To turn off LLM injection without removing the config:
+
+```yaml
+llm:
+  enabled: false
+```
+
+Or at runtime:
+
+```bash
+VP_LLM_ENABLED=false vp run claude
+```

mkdocs.yml

@@ -53,4 +53,5 @@ nav:
   - Development: development.md
   - Agents: agents/index.md
   - Configuration: configuration.md
+  - LLM Integration: llm.md
   - CLI Reference: cli-reference.md

src/vibepod/commands/run.py

@@ -265,6 +265,22 @@ def run(
         **_parse_env_pairs(env or []),
     }
 
+    llm_cfg = config.get("llm", {})
+    llm_command_extra: list[str] = []
+    if llm_cfg.get("enabled") and spec.llm_env_map:
+        llm_values = {
+            "base_url": str(llm_cfg.get("base_url", "")).strip(),
+            "api_key": str(llm_cfg.get("api_key", "")).strip(),
+            "model": str(llm_cfg.get("model", "")).strip(),
+        }
+        for key, env_var in spec.llm_env_map.items():
+            value = llm_values.get(key, "")
+            if value:
+                merged_env.setdefault(env_var, value)
+        llm_model = llm_values["model"]
+        if llm_model and spec.llm_model_args:
+            llm_command_extra = [*spec.llm_model_args, llm_model]
+
     image = effective_agent_image(selected_agent, config)
 
     try:
@@ -304,6 +320,9 @@ def run(
         else:
             warning(f"IKWID mode not supported for agent '{selected_agent}', ignoring")
 
+    if llm_command_extra:
+        command = list(command or []) + llm_command_extra
+
     config_dir = agent_config_dir(selected_agent)
     config_dir.mkdir(parents=True, exist_ok=True)
 

src/vibepod/core/agents.py

@@ -22,6 +22,8 @@ class AgentSpec:
     platform: str | None = None
     run_as_host_user: bool = False
     ikwid_args: list[str] | None = None
+    llm_env_map: dict[str, str] | None = None
+    llm_model_args: list[str] | None = None
 
 
 AGENT_SPECS: dict[str, AgentSpec] = {
@@ -34,6 +36,8 @@ class AgentSpec:
         "/claude",
         {"CLAUDE_CONFIG_DIR": "/claude"},
         ikwid_args=["--dangerously-skip-permissions"],
+        llm_env_map={"base_url": "ANTHROPIC_BASE_URL", "api_key": "ANTHROPIC_API_KEY"},
+        llm_model_args=["--model"],
     ),
     "gemini": AgentSpec(
         "gemini",
@@ -91,6 +95,10 @@ class AgentSpec:
         "/config",
         {"HOME": "/config"},
         ikwid_args=["--full-auto"],
+        llm_env_map={
+            "base_url": "CODEX_OSS_BASE_URL",
+        },
+        llm_model_args=["--oss", "-m"],
     ),
 }
 

src/vibepod/core/config.py

@@ -105,6 +105,12 @@ def _default_config() -> dict[str, Any]:
             "ca_dir": str(config_root / "proxy" / "mitmproxy"),
             "ca_path": str(config_root / "proxy" / "mitmproxy" / "mitmproxy-ca-cert.pem"),
         },
+        "llm": {
+            "enabled": False,
+            "base_url": "",
+            "api_key": "",
+            "model": "",
+        },
         "aliases": DEFAULT_ALIASES.copy(),
     }
 
@@ -146,6 +152,10 @@ def _apply_env(config: dict[str, Any]) -> dict[str, Any]:
         "VP_NO_COLOR": ("no_color", lambda x: x.lower() == "true"),
         "VP_DATASETTE_PORT": ("logging.ui_port", int),
         "VP_PROXY_ENABLED": ("proxy.enabled", lambda x: x.lower() == "true"),
+        "VP_LLM_ENABLED": ("llm.enabled", lambda x: x.lower() == "true"),
+        "VP_LLM_BASE_URL": ("llm.base_url", str),
+        "VP_LLM_API_KEY": ("llm.api_key", str),
+        "VP_LLM_MODEL": ("llm.model", str),
     }
 
     for env_key, (config_path, converter) in mappings.items():

tests/test_agents.py

@@ -77,3 +77,26 @@ def test_get_agent_shortcut_known_agent() -> None:
         assert get_agent_shortcut(agent) == expected_by_agent[agent]
         assert get_agent_shortcut(f" {agent.upper()} ") == expected_by_agent[agent]
     assert get_agent_shortcut("unknown") is None
+
+
+def test_claude_spec_has_llm_env_map() -> None:
+    spec = get_agent_spec("claude")
+    assert spec.llm_env_map == {
+        "base_url": "ANTHROPIC_BASE_URL",
+        "api_key": "ANTHROPIC_API_KEY",
+    }
+    assert spec.llm_model_args == ["--model"]
+
+
+def test_codex_spec_has_llm_env_map() -> None:
+    spec = get_agent_spec("codex")
+    assert spec.llm_env_map == {
+        "base_url": "CODEX_OSS_BASE_URL",
+    }
+    assert spec.llm_model_args == ["--oss", "-m"]
+
+
+def test_agents_without_llm_env_map() -> None:
+    for agent in ("gemini", "opencode", "devstral", "auggie", "copilot"):
+        spec = get_agent_spec(agent)
+        assert spec.llm_env_map is None, f"{agent} should not have llm_env_map"

tests/test_config.py

@@ -138,3 +138,28 @@ def test_per_agent_auto_pull_override(monkeypatch, tmp_path: Path) -> None:
     assert config["agents"]["claude"]["auto_pull"] is True
     # Other agents should still have None (unset)
     assert config["agents"]["gemini"]["auto_pull"] is None
+
+
+def test_default_config_includes_llm_section(monkeypatch, tmp_path: Path) -> None:
+    monkeypatch.setenv("VP_CONFIG_DIR", str(tmp_path))
+    config = get_config()
+    llm = config.get("llm")
+    assert isinstance(llm, dict)
+    assert llm["enabled"] is False
+    assert llm["base_url"] == ""
+    assert llm["api_key"] == ""
+    assert llm["model"] == ""
+
+
+def test_llm_env_overrides(monkeypatch, tmp_path: Path) -> None:
+    monkeypatch.setenv("VP_CONFIG_DIR", str(tmp_path))
+    monkeypatch.setenv("VP_LLM_ENABLED", "true")
+    monkeypatch.setenv("VP_LLM_BASE_URL", "http://localhost:11434/v1")
+    monkeypatch.setenv("VP_LLM_API_KEY", "sk-test")
+    monkeypatch.setenv("VP_LLM_MODEL", "llama3")
+    config = get_config()
+    llm = config["llm"]
+    assert llm["enabled"] is True
+    assert llm["base_url"] == "http://localhost:11434/v1"
+    assert llm["api_key"] == "sk-test"
+    assert llm["model"] == "llama3"