feat(v2): add Parse() function and extensible Registry for model string resolution

Introduces llm.Parse(spec) backed by an extensible Registry that resolves
model strings like "openai/gpt-4o", aliases like "fast", and named targets
like "m5/qwen3:30b" (via LLM_M5 env var DSNs) into ready-to-use *Model
objects. Extension points: RegisterProvider, RegisterAlias, RegisterResolver.
Adds Foreman constructor and sentinel errors ErrAliasLoop, ErrUnknownProvider,
ErrInvalidDSN.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

v2/CLAUDE.md

@@ -32,3 +32,15 @@
 6. Streaming via pull-based `StreamReader.Next()`
 7. Middleware for logging, retry, timeout, usage tracking
 8. Ollama uses the native `/api/chat` API rather than the OpenAI-compat `/v1` endpoint. Native API supports `think: false` for thinking-capable models, has more reliable tool calling, and is approximately 15-20% lower latency. Both local and cloud share the same provider; only the apiKey/baseURL differ. `llm.Ollama()` targets `http://localhost:11434` with no Authorization header; `llm.OllamaCloud(key)` targets `https://ollama.com` with `Authorization: Bearer <key>`.
+
+### DD#9 — Parse() function and extensible Registry (2026-05-23)
+**Context:** mort's ParseModelRequest resolves "provider/model" strings but is
+mort-specific. Multi-instance providers (foreman) need named targets.
+**Decision:** Add `llm.Parse(spec)` backed by an extensible `Registry`. Supports
+aliases, dynamic resolvers, and `LLM_X` env var DSNs for named targets.
+Provider/model syntax: `"openai/gpt-4o"`, aliases: `"fast"`, named targets:
+`"m5/qwen3:30b"` (reads `LLM_M5` env var). Registry is extensible via
+`RegisterProvider`, `RegisterAlias`, `RegisterResolver`.
+**Consequence:** Any go-llm consumer gets model-string parsing. mort migrates by
+registering its tier aliases as resolvers. Foreman instances are addressed via
+`LLM_X` DSN env vars without code changes.