fix: v0.1.1 — MCP identity, timeouts, exit codes, URL validation

Critical:
- MCP server identifies as "webclaw-mcp" instead of "rmcp"
- Research tool poll loop capped at 200 iterations (~10 min)

CLI:
- Non-zero exit codes on errors
- Text format strips markdown table syntax

MCP server:
- URL validation on all tools
- 60s cloud API timeout, 30s local fetch timeout
- Diff cloud fallback computes actual diff
- Batch capped at 100 URLs, crawl at 500 pages
- Graceful startup failure instead of panic

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Cargo.lock

@@ -2854,7 +2854,7 @@ dependencies = [
 
 [[package]]
 name = "webclaw-cli"
-version = "0.1.0"
+version = "0.1.1"
 dependencies = [
  "clap",
  "dotenvy",
@@ -2874,7 +2874,7 @@ dependencies = [
 
 [[package]]
 name = "webclaw-core"
-version = "0.1.0"
+version = "0.1.1"
 dependencies = [
  "ego-tree",
  "once_cell",
@@ -2891,7 +2891,7 @@ dependencies = [
 
 [[package]]
 name = "webclaw-fetch"
-version = "0.1.0"
+version = "0.1.1"
 dependencies = [
  "primp",
  "quick-xml",
@@ -2909,7 +2909,7 @@ dependencies = [
 
 [[package]]
 name = "webclaw-llm"
-version = "0.1.0"
+version = "0.1.1"
 dependencies = [
  "async-trait",
  "reqwest",
@@ -2922,7 +2922,7 @@ dependencies = [
 
 [[package]]
 name = "webclaw-mcp"
-version = "0.1.0"
+version = "0.1.1"
 dependencies = [
  "dotenvy",
  "reqwest",
@@ -2933,6 +2933,7 @@ dependencies = [
  "tokio",
  "tracing",
  "tracing-subscriber",
+ "url",
  "webclaw-core",
  "webclaw-fetch",
  "webclaw-llm",
@@ -2941,7 +2942,7 @@ dependencies = [
 
 [[package]]
 name = "webclaw-pdf"
-version = "0.1.0"
+version = "0.1.1"
 dependencies = [
  "pdf-extract",
  "thiserror",