Answer: Reasoning models often have specific requirements: use_temperature may need to be set to false, some reasoning models don't support streaming, and some don't support system prompts. These settings (use_temperature, streaming, use_system_prompt) must be set to false for certain reasoning models. Status: Confirmed Entry: tool/aider/troubleshooting/reasoning-model-limitations Revision: 1 Digest: sha256:ee39a608e0bdb7d1 (changes whenever the content changes) Timeline: Created: 2026-11-13T02:56:14Z Last changed: 2026-11-13T02:56:14Z Last verified: 2026-11-20T11:42:21Z Next check: 2026-11-21T11:42:21Z Check interval: Daily Expected change: No fixed schedule Data: Field | Value | Source | As of use_temperature restriction | false | [1] | 2026-11-20 streaming restriction | false | [1] | 2026-11-20 use_system_prompt restriction | false | [1] | 2026-11-20 settings to set false | use_temperature streaming use_system_prompt | [1] | 2026-11-20 Sources: [1] Aider. "aider.chat/docs/config/reasoning.html". https://aider.chat/docs/config/reasoning.html Role: primary. Accessed: 2026-11-20T11:42:21Z Quote: "Many reasoning models require this set to false" (Supports: use_temperature restriction) Quote: "false streaming Whether to stream responses Some reasoning models don’t support streaming" (Supports: streaming restriction) Quote: "Some reasoning models don’t support system prompts It may be helpful to find one of the existing model setting configuration entries for the model you are interested in, say o3-mini: - name : o3-mini edit_format : diff weak_model_name : gpt-4o-mini use_repo_map : true use_temperature : false" (Supports: use_system_prompt restriction) Quote: "which must be set to false for certain reasoning models: use_temperature streaming use_system_prompt" (Supports: settings to set false) Published: 2026-04-25T16:45:23Z Snapshot SHA-256: d13a58b25ea8a5f41e48af01102f03c2c3c5febb3611db6511235e1b64c438fd (captured 2026-11-13T02:56:13Z) Verification: Method: Automated extraction from [1] with deepseek-flash (JSON output, thinking disabled). Every value was checked by code to appear verbatim in a quoted passage of [1]. On this check the text of [1] was unchanged since 2026-11-13T02:56:14Z, so the values verified then were kept. Cross-check: not-available at 2026-11-20T11:42:21Z. No independent second source is configured for this entry Last successful check: 2026-11-20T11:42:21Z Last attempt: 2026-11-20T11:42:21Z Notes and limitations: Extracted automatically from a single official source (section "Temperature, streaming and system prompt"). Related: https://latestn.com/tool/aider/troubleshooting/too-many-files-edit-errors How do I reduce Aider edit errors by adding fewer files? https://latestn.com/tool/aider/troubleshooting/unknown-context-window-warning What does the "Unknown context window size and token costs" warning in Aider mean and how do I fix it? https://latestn.com/tool/aider/troubleshooting/unknown-required-env-vars-warning What does the "Unknown which environment variables are required" warning in Aider mean? https://latestn.com/tool/aider/troubleshooting/lm-studio-dummy-api-key Why does Aider fail with an empty Bearer token when using LM Studio? https://latestn.com/tool/aider/troubleshooting/missing-environment-variables-warning How do I resolve the "Missing environment variables" warning in Aider? https://latestn.com/tool/aider/troubleshooting/other-token-limit-causes What other causes can trigger token limit errors in Aider? https://latestn.com/tool/ All entries in AI tools Change log: Time | Event | Change | Source 2026-11-13T02:56:14Z | added | Entry created | — Changes for this entry as a feed: https://latestn.com/tool/aider/troubleshooting/reasoning-model-limitations/latest Challenge this entry: Open challenges: None How: If a value here is wrong or out of date, send what is wrong and a link to evidence. Challenges are queued and checked against the evidence; they do not change the entry by themselves. If the entry changes as a result, the change log says so. Form: https://latestn.com/dispute/tool/aider/troubleshooting/reasoning-model-limitations POST: https://latestn.com/dispute/tool/aider/troubleshooting/reasoning-model-limitations with claim, evidence_url, and optionally field and contact (form-encoded or JSON) GET: https://latestn.com/dispute/tool/aider/troubleshooting/reasoning-model-limitations?claim={what is wrong}&evidence_url={link} How to cite: LatestN. (2026). What are the limitations of reasoning models in Aider regarding temperature, streaming and system prompts? Revision 1, last verified 2026-11-20T11:42:21Z. https://latestn.com/tool/aider/troubleshooting/reasoning-model-limitations (accessed 2026-11-21T09:58:19Z). @misc{LatestN_tool_aider_troubleshooting_reasoning_model_limitations_r1, title = {What are the limitations of reasoning models in Aider regarding temperature, streaming and system prompts?}, author = {{LatestN}}, year = {2026}, howpublished = {\url{https://latestn.com/tool/aider/troubleshooting/reasoning-model-limitations}}, note = {Revision 1; digest sha256:ee39a608e0bdb7d1; last verified 2026-11-20T11:42:21Z; accessed 2026-11-21T09:58:19Z} } Reuse: License: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/) Attribution: Copying and adapting are allowed, including commercially, if you credit LatestN and link to the entry you used. Each entry ends with a ready-made citation. URL: https://latestn.com/tool/aider/troubleshooting/reasoning-model-limitations