版本： Discourse v2026.7.2 — Commits · discourse/discourse · GitHub — Ember v6.10.1 报错详情： DiscourseAi::Completions::Endpoints::OpenAi: status: 400 - body: {"error":{"code":400,"upstream_code":"invalid_request_error","message":"The `reasoning_content` in the thinking mode must be passed bac activesupport-8.0.5/lib/active_support/broadcast_logger.rb:218:in 'block in ActiveSupport::BroadcastLogger#dispatch' activesupport-8.0.5/lib/active_support/broadcast_logger.rb:217:in 'Array#map' activesupport-8.0.5/lib/active_support/broadcast_logger.rb:217:in 'ActiveSupport::BroadcastLogger#dispatch' activesupport-8.0.5/lib/active_support/broadcast_logger.rb:129:in 'ActiveSupport::BroadcastLogger#error' /var/www/discourse/plugins/discourse-ai/lib/completions/endpoints/base.rb:685:in 'Kernel#public_send' /var/www/discourse/plugins/discourse-ai/lib/completions/endpoints/base.rb:685:in 'DiscourseAi::Completions::Endpoints::Base#failed_response_retry_status_and_delay' /var/www/discourse/plugins/discourse-ai/lib/completions/endpoints/base.rb:330:in 'block (3 levels) in DiscourseAi::Completions::Endpoints::Base#perform_completion_request_with_retries' net-http-0.9.1/lib/net/http.rb:2461:in 'block in Net::HTTP#transport_request' net-http-0.9.1/lib/net/http/response.rb:321:in 'Net::HTTPResponse#reading_body' net-http-0.9.1/lib/net/http.rb:2458:in 'Net::HTTP#transport_request' net-http-0.9.1/lib/net/http.rb:2410:in 'Net::HTTP#request' rack-mini-profiler-4.0.1/lib/patches/net_patches.rb:19:in 'block in Net::HTTP#request_with_mini_profiler' rack-mini-profiler-4.0.1/lib/mini_profiler/profiling_methods.rb:51:in 'Rack::MiniProfiler::ProfilingMethods#step' rack-mini-profiler-4.0.1/lib/patches/net_patches.rb:18:in 'Net::HTTP#request_with_mini_profiler' /var/www/discourse/plugins/discourse-ai/lib/completions/endpoints/base.rb:325:in 'block (2 levels) in DiscourseAi::Completions::Endpoints::Base#perform_completion_request_with_retries' net-http-0.9.1/lib/net/http.rb:1630:in 'Net::HTTP#start' net-http-0.9.1/lib/net/http.rb:1064:in 'Net::HTTP.start' /var/www/discourse/plugins/discourse-ai/lib/completions/endpoints/base.rb:306:in 'block in DiscourseAi::Completions::Endpoints::Base#perform_completion_request_with_retries' :168:in 'Kernel#loop' /var/www/discourse/plugins/discourse-ai/lib/completions/endpoints/base.rb:282:in 'DiscourseAi::Completions::Endpoints::Base#perform_completion_request_with_retries' /var/www/discourse/plugins/discourse-ai/lib/completions/endpoints/base.rb:191:in 'DiscourseAi::Completions::Endpoints::Base#perform_completion!' /var/www/discourse/plugins/discourse-ai/lib/completions/endpoints/open_ai_shared.rb:50:in 'DiscourseAi::Completions::Endpoints::OpenAiShared#perform_completion!' /var/www/discourse/plugins/discourse-ai/lib/completions/endpoints/base.rb:218:in 'DiscourseAi::Completions::Endpoints::Base#replay_non_streaming_as_streaming!' /var/www/discourse/plugins/discourse-ai/lib/completions/endpoints/base.rb:172:in 'DiscourseAi::Completions::Endpoints::Base#perform_completion!' /var/www/discourse/plugins/discourse-ai/lib/completions/endpoints/open_ai_shared.rb:50:in 'DiscourseAi::Completions::Endpoints::OpenAiShared#perform_completion!' /var/www/discourse/plugins/discourse-ai/lib/completions/llm.rb:245:in 'DiscourseAi::Completions::Llm#generate' /var/www/discourse/plugins/discourse-ai/lib/agents/bot.rb:176:in 'DiscourseAi::Agents::Bot#reply' /var/www/discourse/plugins/discourse-ai/lib/ai_bot/playground.rb:378:in 'DiscourseAi::AiBot::Playground#reply_to_chat_message' /var/www/discourse/plugins/discourse-ai/app/jobs/regular/create_ai_chat_reply.rb:20:in 'Jobs::CreateAiChatReply#execute' /var/www/discourse/app/jobs/base.rb:313:in 'block (2 levels) in Jobs::Base#perform' rails_multisite-7.0.0/lib/rails_multisite/connection_management/null_instance.rb:49:in 'RailsMultisite::ConnectionManagement::NullInstance#with_connection' rails_multisite-7.0.0/lib/rails_multisite/connection_management.rb:17:in 'RailsMultisite::ConnectionManagement.with_connection' /var/www/discourse/app/jobs/base.rb:300:in 'block in Jobs::Base#perform' /var/www/discourse/app/jobs/base.rb:297:in 'Array#each' /var/www/discourse/app/jobs/base.rb:297:in 'Jobs::Base#perform' sidekiq-7.3.10/lib/sidekiq/processor.rb:220:in 'Sidekiq::Processor#execute_job' sidekiq-7.3.10/lib/sidekiq/processor.rb:185:in 'block (4 levels) in Sidekiq::Processor#process' sidekiq-7.3.10/lib/sidekiq/middleware/chain.rb:180:in 'Sidekiq::Middleware::Chain#traverse' sidekiq-7.3.10/lib/sidekiq/middleware/chain.rb:183:in 'block in Sidekiq::Middleware::Chain#traverse' /var/www/discourse/lib/sidekiq/suppress_user_email_errors.rb:6:in 'Sidekiq::SuppressUserEmailErrors#call' sidekiq-7.3.10/lib/sidekiq/middleware/chain.rb:182:in 'Sidekiq::Middleware::Chain#traverse' sidekiq-7.3.10/lib/sidekiq/middleware/chain.rb:183:in 'block in Sidekiq::Middleware::Chain#traverse' /var/www/discourse/lib/sidekiq/discourse_event.rb:6:in 'Sidekiq::DiscourseEvent#call' sidekiq-7.3.10/lib/sidekiq/middleware/chain.rb:182:in 'Sidekiq::Middleware::Chain#traverse' sidekiq-7.3.10/lib/sidekiq/middleware/chain.rb:183:in 'block in Sidekiq::Middleware::Chain#traverse' /var/www/discourse/lib/sidekiq/pausable.rb:131:in 'Sidekiq::Pausable#call' sidekiq-7.3.10/lib/sidekiq/middleware/chain.rb:182:in 'Sidekiq::Middleware::Chain#traverse' sidekiq-7.3.10/lib/sidekiq/middleware/chain.rb:183:in 'block in Sidekiq::Middleware::Chain#traverse' sidekiq-7.3.10/lib/sidekiq/job/interrupt_handler.rb:9:in 'Sidekiq::Job::InterruptHandler#call' sidekiq-7.3.10/lib/sidekiq/middleware/chain.rb:182:in 'Sidekiq::Middleware::Chain#traverse' sidekiq-7.3.10/lib/sidekiq/middleware/chain.rb:183:in 'block in Sidekiq::Middleware::Chain#traverse' sidekiq-7.3.10/lib/sidekiq/metrics/tracking.rb:26:in 'Sidekiq::Metrics::ExecutionTracker#track' sidekiq-7.3.10/lib/sidekiq/metrics/tracking.rb:134:in 'Sidekiq::Metrics::Middleware#call' sidekiq-7.3.10/lib/sidekiq/middleware/chain.rb:182:in 'Sidekiq::Middleware::Chain#traverse' sidekiq-7.3.10/lib/sidekiq/middleware/chain.rb:173:in 'Sidekiq::Middleware::Chain#invoke' sidekiq-7.3.10/lib/sidekiq/processor.rb:184:in 'block (3 levels) in Sidekiq::Processor#process' sidekiq-7.3.10/lib/sidekiq/processor.rb:145:in 'block (6 levels) in Sidekiq::Processor#dispatch' sidekiq-7.3.10/lib/sidekiq/job_retry.rb:118:in 'Sidekiq::JobRetry#local' sidekiq-7.3.10/lib/sidekiq/processor.rb:144:in 'block (5 levels) in Sidekiq::Processor#dispatch' sidekiq-7.3.10/lib/sidekiq/config.rb:39:in 'block in ' sidekiq-7.3.10/lib/sidekiq/processor.rb:139:in 'block (4 levels) in Sidekiq::Processor#dispatch' sidekiq-7.3.10/lib/sidekiq/processor.rb:281:in 'Sidekiq::Processor#stats' sidekiq-7.3.10/lib/sidekiq/processor.rb:134:in 'block (3 levels) in Sidekiq::Processor#dispatch' sidekiq-7.3.10/lib/sidekiq/job_logger.rb:15:in 'Sidekiq::JobLogger#call' sidekiq-7.3.10/lib/sidekiq/processor.rb:133:in 'block (2 levels) in Sidekiq::Processor#dispatch' sidekiq-7.3.10/lib/sidekiq/job_retry.rb:85:in 'Sidekiq::JobRetry#global' sidekiq-7.3.10/lib/sidekiq/processor.rb:132:in 'block in Sidekiq::Processor#dispatch' sidekiq-7.3.10/lib/sidekiq/job_logger.rb:40:in 'Sidekiq::JobLogger#prepare' sidekiq-7.3.10/lib/sidekiq/processor.rb:131:in 'Sidekiq::Processor#dispatch' sidekiq-7.3.10/lib/sidekiq/processor.rb:183:in 'block (2 levels) in Sidekiq::Processor#process' sidekiq-7.3.10/lib/sidekiq/processor.rb:182:in 'Thread.handle_interrupt' sidekiq-7.3.10/lib/sidekiq/processor.rb:182:in 'block in Sidekiq::Processor#process' sidekiq-7.3.10/lib/sidekiq/processor.rb:181:in 'Thread.handle_interrupt' sidekiq-7.3.10/lib/sidekiq/processor.rb:181:in 'Sidekiq::Processor#process' sidekiq-7.3.10/lib/sidekiq/processor.rb:86:in 'Sidekiq::Processor#process_one' sidekiq-7.3.10/lib/sidekiq/processor.rb:76:in 'Sidekiq::Processor#run' sidekiq-7.3.10/lib/sidekiq/component.rb:10:in 'Sidekiq::Component#watchdog' sidekiq-7.3.10/lib/sidekiq/component.rb:19:in 'block in Sidekiq::Component#safe_thread' AI配置： [image]

我进行了以下尝试：尝试一：开启禁用流式补全（将流式请求转换为非流式请求），但是运行测试报错：流式传输请求失败：模型返回了空回答。尝试二：关闭禁用流式补全（将流式请求转换为非流式请求）同时推理工作（仅适用于推理模型） (可选)选择none 运行测试正常，但是这样我失去了推理功能，这不是我想要的。疑问：到底是AI插件没有处理好运行测试的逻辑，还是我对接的大模型平台返回格式不匹配。如果需要更多信息，我很愿意提供，来查明具体问题。

Is the DiscourseAi::Completions::Endpoints::OpenAi: ... error message cut off?

I just searched that error message on Bing and it seems to be a DeepSeek provider-specific issue https://blog.csdn.net/weixin_38106322/article/details/161165043 Have you tested another provider (e.g. OpenRouter)?

多谢回复，我使用的是企业内部自己聚合的llmrouter服务。 openrouter没试过，我没开通它的服务。

If the problem is that DeepSeek requires reasoning tokens to be sent back during completion (also known as interleaved thinking[1]) I think it’s a legitimate feature request This might not be accurate, I just searched and interleaved thinking is more about preserving reasoning between tool calls instead of arbitrary content ↩︎

Can you try changing the provider to vLLM and the reasoning parser to deepseek_v4 ?

[image] AI 日志如下： [image] topic@discourse-2026-09-16.dcqresult.json (14.8 KB)

I needed to do some LiteLLM hacky things to get some models working in Discourse AI. Had you tried different reasoning models? Some LLMs only work with it enabled, and others with it on low (not minimal) or always default; that is usually heavy.

试过了，基本上都是一开启推理模式就会报错“模型返回了空的回答”，但是从AI日志中，模型确实是返回了，看上去像是没有能正确接收模型的返回。点一次测试，有两条AI日志，第一条看上去不是流式，而第二条是流式。我不知道为什么会有两条日志。

Erro no modo de raciocínio da IA

Suporte ao Produto

singi2016cn (Singi Qin) 16 Setembro , 2026 01:27 8

O log da IA é o seguinte:

topic@discourse-2026-09-16.dcqresult.json (14,8 KB)

Tópico		Respostas	Vistas
Discourse AI going off the rails Product Support ai	11	370	14 Setembro , 2026
AI translations errors Bug ai	10	500	10 Maio , 2026
Reasoning Models 400 error Product Support ai	7	519	28 Janeiro , 2025
Internal Server Error 500- Manual configuration [ Discourse AI] Product Support ai	7	502	5 Setembro , 2025
Debugging Discourse's AI Features: When OpenAI Responds but Forum Doesn't Product Support ai	5	507	3 Julho , 2024

Erro no modo de raciocínio da IA

Related topics