feat: real LLM call via wasi-http (Ollama adapter) — v0.2.0

The orchestrator now calls a configured Ollama-compatible LLM
endpoint over wasi-http and emits the LLM-generated plan back
to the hub. When llm_endpoint is empty, the v0.1.0 deterministic
stub is preserved as fallback (useful for tests and air-gapped
environments).

- module.yaml: bump to 0.2.0; new inputs llm_endpoint,
  llm_model, llm_api_key; net: permissions for OpenAI,
  Anthropic, localhost, 127.0.0.1 (Ollama defaults)
- src/llm.rs: LlmClient trait, OllamaParams, build_user_prompt,
  build_ollama_body, extract_ollama_content, generate_plan;
  9 unit tests for prompt-building and response-parsing
- src/plan.rs: tagged enum with Explain/SaveFlow/RunFlow/
  InstallModule variants; parse_and_validate; build_stub_plan
  (renamed from build_plan); validate(); 6 unit tests
- src/lib.rs: WakiClient implementing LlmClient over the waki
  WASI-0.2 HTTP crate (wasm32-only); empty endpoint → stub
- Cargo.toml: 0.2.0; thiserror dep; waki dep gated on wasm32

17 host-side tests pass. WASM bundle is 386KB (was 74KB; the
delta is wasi-http via waki, expected). The deny path is
exercised by the platform-side integration test in
fai_platform/crates/fai_hub/tests/orchestrator_llm_path.rs.

Signed-off-by: flemming-it <sf@flemming.it>

module.yaml

@@ -1,15 +1,24 @@
 schema_version: 1
 name: orchestrator-llm
-version: 0.1.0
+version: 0.2.0
 
 # Capability provided by this module.
 provides:
   - capability: orchestrator.plan
-    version: 0.1.0
+    version: 0.2.0
 
 # Inputs the invoke function accepts.
 inputs:
   goal: text
+  # LLM HTTP endpoint, e.g. "http://localhost:11434/api/chat"
+  # for Ollama, "https://api.openai.com/v1/chat/completions",
+  # or "https://api.anthropic.com/v1/messages".
+  llm_endpoint: text
+  # Model identifier, e.g. "qwen2.5:14b" for Ollama or "gpt-4o-mini".
+  llm_model: text
+  # Optional bearer token for cloud providers. Empty string means
+  # no Authorization header is sent.
+  llm_api_key: text
   # Optional JSON-encoded list of installed capabilities. If
   # omitted or empty, the module plans without capability context.
   available_capabilities: text
@@ -25,7 +34,13 @@ outputs:
 
 # Permissions required.
 #
-# v0.1.0 is a deterministic stub — no network, no fs, no env.
-# v0.2.0 will add `net: <llm-endpoint>` once the platform exposes
-# wasi-http to permitted modules.
-permissions: []
+# The module makes outbound HTTP to the configured LLM endpoint.
+# Default declarations cover the common providers (cloud OpenAI,
+# Anthropic, local Ollama on loopback). Operators with different
+# LLM endpoints add a host-level entry via operator config
+# (Phase 1+) — for Phase 0.5 they fork module.yaml.
+permissions:
+  - "net: api.openai.com"
+  - "net: api.anthropic.com"
+  - "net: localhost"
+  - "net: 127.0.0.1"