# `LlmCore.LLM.Native`
[🔗](https://github.com/fosferon/llm_core/blob/v0.3.0/lib/llm_core/llm/native.ex#L1)

In-process agentic provider — runs the agent loop inside the BEAM VM.

  1. Reads the agent .md system prompt
  2. Resolves an LLM API provider (Appliance → Zai → Anthropic)
  3. Calls LlmCore.Agent.Loop.run with LlmToolkit.CodeTools
  4. Returns a standard LlmCore.LLM.Response

Zero CLI cost. Uses whatever API provider is available.

## Provider Resolution Priority

  1. **Appliance** (local, free) — Qwen, etc. on DGX Spark / LM Studio
  2. **Z.ai** (plan-covered) — GLM-5.1, included in coding plan
  3. **Anthropic** (direct API) — Claude models, pay-per-token

## Usage

This provider implements `LlmCore.LLM.Provider` and is selected by
provider routing when `provider: "native"` is specified or when no
CLI providers are available.

    {:ok, response} = LlmCore.LLM.Native.send(task,
      system_prompt_file: "/path/to/agent.md",
      cwd: "/path/to/project",
      model: "qwen3-vl-32b-thinking"
    )

# `try_cascade`

```elixir
@spec try_cascade([{module(), String.t(), keyword()}], (tuple() -> term())) ::
  {:ok, LlmCore.LLM.Response.t(), [map()]} | {:error, term()}
```

Walk a list of `{module, model, opts}` candidates and invoke `run_fn`
on each until one succeeds.

- `{:ok, response, messages}` from `run_fn` → returned immediately.
- `{:error, :max_iterations_reached}` → returned immediately (reasoning
  failure, not a provider outage — retrying elsewhere won't help).
- Any other `{:error, reason}` → logs and advances to the next candidate.
- Empty list → `{:error, :no_provider_succeeded}`.

Exposed for direct testing; production call sites go through `send/2`.

---

*Consult [api-reference.md](api-reference.md) for complete listing*