feat(anthropic): support extended thinking round trips

[dailingtao]

Summary

Fixes #2219.

• map GenerateOptions.thinkingBudget to Anthropic budget_tokens
• preserve Anthropic thinking signatures and redacted thinking blocks in ThinkingBlock metadata
• restore those native blocks, in their original order, when conversation history is sent back to Anthropic
• preserve provider metadata while streaming thinking chunks are accumulated by ReasoningContext
• keep the existing text fallback for unsigned or malformed provider-specific ThinkingBlock metadata
• document Anthropic extended-thinking configuration in English and Chinese

Validation

• mvn -pl agentscope-extensions/agentscope-extensions-model/agentscope-extensions-model-anthropic -am clean verify
• AgentScope Core: 2214 tests, 0 failures, 0 errors, 9 skipped
• Anthropic model extension: 151 tests, 0 failures, 0 errors, 1 skipped

[codecov]

Codecov Report

❌ Patch coverage is 86.15385% with 18 lines in your changes missing coverage. Please review.

Files with missing lines	Patch %	Lines
...anthropic/formatter/AnthropicThinkingMetadata.java	77.27%	4 Missing and 6 partials ⚠️
...pe/core/agent/accumulator/ThinkingAccumulator.java	58.33%	2 Missing and 3 partials ⚠️
...l/anthropic/formatter/AnthropicResponseParser.java	95.31%	0 Missing and 3 partials ⚠️

📢 Thoughts on this report? Let us know!

[AgentScopeJavaBot]

🤖 AI Review

Aspect	Count
🟢 Nitpick (信息性建议，不阻塞合并)	3
🟡 Recommended (建议修复，但不阻塞合并)	2

Overall Assessment: COMMENT — Well-designed extended thinking round-trip support; two defensive-programming improvements recommended before merge.

[AgentScopeJavaBot]

🤖 AI Review

Aspect	Count
🟢 Nitpick (信息性建议，不阻塞合并)	3
🟡 Recommended (建议修复，但不阻塞合并)	2

Overall Assessment: COMMENT — Well-designed extended thinking round-trip support; two defensive-programming improvements recommended before merge.

[dailingtao]

Hi @jujn, it looks like AgentScopeJavaBot may be stuck on this PR.

The bot submitted the same review summary twice for commit d7f6dea4,
reporting 3 nitpicks and 2 recommendations, but no inline comments or
review threads were created, so I couldn't see the specific findings.

The latest head is now 1bcd3d7c, and the new review request is still
pending. I also don't have permission to re-request reviewers.

Could you please help re-trigger the AI review or check whether the bot
service is working correctly?

All current CI checks are passing. Thanks!

[jujn]

Thanks for your contribution. I'll review it later when I have time.