fix(anthropic): deep scan fixes — auth, retries, edge cases

Fixes from comprehensive code review and cross-referencing with
clawdbot/OpenCode implementations:

CRITICAL:
- Add one-shot guard (anthropic_auth_retry_attempted) to prevent
  infinite 401 retry loops when credentials keep changing
- Fix _is_oauth_token(): managed keys from ~/.claude.json are NOT
  regular API keys (don't start with sk-ant-api). Inverted the logic:
  only sk-ant-api* is treated as API key auth, everything else uses
  Bearer auth + oauth beta headers

HIGH:
- Wrap json.loads(args) in try/except in message conversion — malformed
  tool_call arguments no longer crash the entire conversation
- Raise AuthError in runtime_provider when no Anthropic token found
  (was silently passing empty string, causing confusing API errors)
- Remove broken _try_anthropic() from auxiliary vision chain — the
  centralized router creates an OpenAI client for api_key providers
  which doesn't work with Anthropic's Messages API

MEDIUM:
- Handle empty assistant message content — Anthropic rejects empty
  content blocks, now inserts '(empty)' placeholder
- Fix setup.py existing_key logic — set to 'KEEP' sentinel instead
  of None to prevent falling through to the auth choice prompt
- Add debug logging to _fetch_anthropic_models on failure

Tests: 43 adapter tests (2 new for token detection), 3197 total passed

run_agent.py

@@ -3553,6 +3553,7 @@ class AIAgent:
             compression_attempts = 0
             max_compression_attempts = 3
             codex_auth_retry_attempted = False
+            anthropic_auth_retry_attempted = False
             nous_auth_retry_attempted = False
             restart_with_compressed_messages = False
             restart_with_length_continuation = False
@@ -3892,7 +3893,9 @@ class AIAgent:
                         self.api_mode == "anthropic_messages"
                         and status_code == 401
                         and hasattr(self, '_anthropic_api_key')
+                        and not anthropic_auth_retry_attempted
                     ):
+                        anthropic_auth_retry_attempted = True
                         # Try re-reading Claude Code credentials (they may have been refreshed)
                         from agent.anthropic_adapter import resolve_anthropic_token, build_anthropic_client
                         new_token = resolve_anthropic_token()