ai-openrouter: reasoning is not sent back to the model between tool-call iterations #2191
Send to my agentSummary#
@tanstack/ai-openrouter (1.1.2, and main at packages/ai-openrouter/src/adapters/text.ts, convertMessage) builds previous assistant messages with only content and toolCalls. The thinking blocks that @tanstack/ai stores on the assistant ModelMessage (thinking?: Array<{ content, signature?, redacted? }>) are dropped, so reasoning is never sent back to the provider in later iterations of the agent loop.
The OpenRouter SDK already accepts it on ChatAssistantMessage (reasoning, reasoningDetails).
Why it matters#
- OpenRouter recommends preserving reasoning during tool use: "Preserving reasoning blocks is useful specifically for tool calling" — https://openrouter.ai/docs/guides/best-practices/reasoning-tokens#preserving-reasoning-blocks
- DeepSeek V4's thinking mode requires it when
toolsare present ("thereasoning_contentmust be fully passed back to the API in all subsequent requests"); their first-party API returns 400 without it — https://api-docs.deepseek.com/guides/thinking_mode - Anthropic models need their signed thinking (
reasoning_detailswith signatures) passed back unmodified when using tools. - The TanStack AI docs (
chat/thinking-content) list the Anthropic, Gemini, Mistral and Bedrock adapters as sending reasoning back; OpenRouter isn't mentioned.
Repro#
chat({ adapter: openRouterText('deepseek/deepseek-v4.1-flash'), tools: [someTool], messages })with a prompt that triggers a tool call.- Inspect the second request of the loop (e.g. via a gateway log): the assistant message with
tool_callshas noreasoning/reasoning_details.
Expected#
convertMessage forwards reasoning for assistant messages, e.g. the plaintext reasoning field (OpenRouter accepts reasoning / reasoning_content as plaintext), or the original reasoning_details array (unmodified, including signatures) so that Anthropic/encrypted reasoning can round-trip too. The latter probably needs the adapter to keep reasoning_details from the stream, since thinking only keeps text + signature.
Data point (honest caveat)#
We tried a minimal override that adds reasoning: thinking.map(t => t.content).join('') for DeepSeek and measured ~1 900 full tool-call turns (streaming), A/B paired. We saw no measurable change in answer quality for our case (≈2.2 % vs 2.3 % of answers with a visible self-correction, p ≈ 0.88). So this is reported as a protocol-compliance gap rather than a confirmed quality bug — but it does mean DeepSeek receives a conversation shape it doesn't expect, and it will hard-fail on providers that enforce it.
Happy to open a PR if a direction is agreed (plaintext reasoning vs. preserving reasoning_details).
github-actions[bot](GitHub profile, opens in a new tab) assignedAlemTuzlak
github-actions[bot](GitHub profile, opens in a new tab) added labelswaiting-on: maintainer
Sign in to join this conversation.