Improve --format llm output quality (#37)

Improve LLM-format output for modern news and documentation pages.

- Filter noisy hydration and low-value page chrome structured data while preserving content-bearing Schema.org records
- Fix element/text spacing without detaching punctuation on docs, forums, and reference pages
- Remove common accessibility link chrome from LLM text and link labels
- Bump workspace version to 0.6.0 and update the changelog

Thanks to Nenad Oric (@devnen) for the original PR and contribution.

Cargo.lock

@@ -3219,7 +3219,7 @@ dependencies = [
 
 [[package]]
 name = "webclaw-cli"
-version = "0.5.9"
+version = "0.6.0"
 dependencies = [
  "clap",
  "dotenvy",
@@ -3240,7 +3240,7 @@ dependencies = [
 
 [[package]]
 name = "webclaw-core"
-version = "0.5.9"
+version = "0.6.0"
 dependencies = [
  "ego-tree",
  "once_cell",
@@ -3258,7 +3258,7 @@ dependencies = [
 
 [[package]]
 name = "webclaw-fetch"
-version = "0.5.9"
+version = "0.6.0"
 dependencies = [
  "async-trait",
  "bytes",
@@ -3284,7 +3284,7 @@ dependencies = [
 
 [[package]]
 name = "webclaw-llm"
-version = "0.5.9"
+version = "0.6.0"
 dependencies = [
  "async-trait",
  "reqwest",
@@ -3297,7 +3297,7 @@ dependencies = [
 
 [[package]]
 name = "webclaw-mcp"
-version = "0.5.9"
+version = "0.6.0"
 dependencies = [
  "dirs",
  "dotenvy",
@@ -3317,7 +3317,7 @@ dependencies = [
 
 [[package]]
 name = "webclaw-pdf"
-version = "0.5.9"
+version = "0.6.0"
 dependencies = [
  "pdf-extract",
  "thiserror",
@@ -3326,7 +3326,7 @@ dependencies = [
 
 [[package]]
 name = "webclaw-server"
-version = "0.5.9"
+version = "0.6.0"
 dependencies = [
  "anyhow",
  "axum",