fix: address all review findings (context timeout, docs, early exit)

- Overall context timeout now derived from LLM timeout + 1 minute
  (no longer hardcoded 3min that could conflict with longer LLM timeouts)
- Clarify concurrency docs: With* methods are setup-only, not concurrent
- Add ctx.Err() checks in fetchFileContext and fetchPatterns loops
  (break early on cancellation instead of making unnecessary requests)

llm/client.go

@@ -13,6 +13,7 @@ import (
 
 // Client calls an OpenAI-compatible chat completion API.
 // A Client is safe for concurrent use by multiple goroutines after construction.
+// WithTimeout and WithTemperature must be called during setup, before concurrent use.
 type Client struct {
 	baseURL     string
 	apiKey      string