feat: implement message continuation and error handling improvements

[chenyme]

Summary

修复对话流式生成在中途失败或上游协议异常时的回复保留问题。现在如果错误发生前已经生成了部分 assistant 内容、工具调用记录或原生工具用量，会保留为本轮中断消息，并返回给前端展示，同时统一 run、消息用量和账单记录口径，避免“内容已展示但未计费/日志不一致”。

同时优化上游成功状态码但响应格式不兼容时的错误摘要，避免把原始 SSE data: 内容直接暴露在错误正文中，原始响应仍保留在调试信息里。

Change type

• Bug fix
• Feature
• Documentation
• Refactor
• Configuration / deployment
• Security hardening
• Other

Affected areas

• Frontend / UI
• Backend / API
• Authentication / authorization
• Conversations / streaming
• Files / RAG / extraction
• Model routing / providers
• MCP / tools
• Billing / payments
• Admin console
• Deployment / Docker / configuration
• Documentation

Verification

• cd backend && go test ./internal/application/conversation
• cd backend && go test ./internal/transport/http/conversation
• cd backend && go test ./...
• cd frontend && pnpm lint
• cd frontend && pnpm build
• git diff --check

Screenshots, API examples, or logs

No screenshots added.

Relevant behavior:

• Interrupted stream responses now include retained message data in the final error event when partial content was persisted.
• Raw upstream SSE bodies are no longer shown in the user-facing error summary for HTTP 2xx protocol-incompatible responses.

Configuration, migration, and compatibility notes

Configuration changes: None.

Database migrations: None.

Deployment changes: None.

API compatibility: Existing send/stream endpoints remain unchanged. Stream error events may now include retained message data when an interrupted assistant message was successfully persisted.

Swagger: Not regenerated; no new route or request/response DTO schema was introduced.

Documentation

• Documentation is not needed for this change.
• Documentation was updated.
• Documentation still needs to be updated.

Security and privacy

• No secrets, tokens, credentials, local config, or personal data are included.
• User data access remains scoped by authenticated user context unless an admin-only path explicitly requires broader access.
• Security-sensitive behavior was reviewed, including authentication, authorization, provider routing, file processing, billing, and admin APIs where relevant.

Checklist

• I searched existing issues and pull requests.
• Changes are focused and do not include unrelated refactors.
• Tests or static verification were run where practical.
• User-facing behavior, deployment steps, API contracts, or configuration changes are documented.
• Generated artifacts are included only when this project explicitly requires them.
• Caches, build output, .pyc files, .env files, and local storage data are not committed.