agent-loop: new crate — LLM loop kernel + Model clients (phase 0)

Extract the LLM agent loop into a standalone workspace crate with zero
deps on skald-core/core-api (blueprint project-loop.md, D13-D15):

- kernel: round loop, model fallback with rebuild, parallel tool fan-out
  (ordered id alloc / bounded concurrent exec / ordered record), streaming
  deltas drained before outcomes, sticky cancellation
- models: OpenAiModel/AnthropicModel/OllamaModel/LmStudioModel ported from
  llm-client onto the Model trait; ModelError carries the HTTP status;
  is_retriable default = the 401/403/404/422 rule
- DTL as crate protocol (ToolRendering Inline/DeferredToolReference/
  SystemToolBlock; Anthropic conversions + Kimi system+tools passthrough),
  host catalog behind ActivationSource/ToolActivator
- HistoryStore durability contract + InMemoryStore; LinearAssembler with
  well-formed projection (incl. DTL injection, summary, crash survivors)
- LoopManager singleton (broadcast bus + live registry), one live loop
  per conversation, orphan-marking on start_turn
- 32 tests green (kernel §13 suite, assembler DTL, SSE/Anthropic ports),
  clippy clean

crates/agent-loop/Cargo.toml

@@ -0,0 +1,21 @@
+[package]
+name        = "agent-loop"
+version     = "0.1.0"
+edition     = "2024"
+description = "Reusable LLM agent loop kernel: round loop, tool calling, fallback, streaming, durability traits — no database, no host types."
+license     = "MIT"
+
+[dependencies]
+tokio        = { version = "1", features = ["sync", "rt", "time", "macros"] }
+tokio-util   = { version = "0.7" }
+async-trait  = "0.1"
+serde        = { version = "1", features = ["derive"] }
+serde_json   = "1"
+tracing      = "0.1"
+anyhow       = "1"
+futures      = "0.3"
+futures-util = "0.3"
+reqwest      = { version = "0.13.4", default-features = false, features = ["rustls-no-provider", "charset", "http2", "system-proxy", "json", "stream"] }
+
+[dev-dependencies]
+tokio = { version = "1", features = ["macros", "rt-multi-thread"] }