Description
DeepSeek V4 Flash and Pro models support reasoning_effort (documented on DeepSeek's Thinking Mode page — search for "Thinking Effort Control"), but Kilo v7.2.23 explicitly excludes all DeepSeek models from the reasoning effort variant and option system.
From DeepSeek's Thinking Mode docs, the Thinking Effort Control table shows:
| Control Parameter (OpenAI Format) |
Values |
| Thinking Effort Control |
{"reasoning_effort": "high/max"} |
Their footnote also explicitly mentions: "for some complex agent requests (such as Claude Code, OpenCode), effort is automatically set to max" — so this is a known integration point where OpenCode should already be recognized.
DeepSeek API docs reference: https://api-docs.deepseek.com/guides/thinking_mode
Location in source (v7.2.23)
packages/opencode/src/provider/transform.ts — the variants() function:
if (
id.includes("deepseek") ||
id.includes("minimax") ||
id.includes("mistral") ||
id.includes("qwen") ||
// ...
)
return {}
When variants() returns {}, no reasoning effort variants are offered or applied. The options() function also does not inject any default reasoningEffort for DeepSeek models.
As a result:
- Users must manually set
options.reasoningEffort per agent in their config
- No UI dropdown or variant selection is available for DeepSeek models
- No model-level defaults exist (unlike GPT-5 which gets
reasoningEffort: "medium" by default)
Expected behavior
DeepSeek V4 Flash and Pro models should be included in the reasoning effort system:
- Remove
deepseek from the exclusion list in variants(), or make the exclusion version-aware so V4+ models are included
- Add default
reasoningEffort injection in options() for DeepSeek V4 models (e.g., "medium" default, "low" for small-model tasks)
- Allow variant presets for DeepSeek V4 similar to what exists for OpenAI models
Workaround
Users can add "options": { "reasoningEffort": "max" } to each agent definition in their config, but this bypasses the proper variant system and requires manual per-agent configuration.
Environment
- Kilo version: v7.2.23
- Models affected: deepseek-v4-flash, deepseek-v4-pro (and future V4+ variants)
Note
If this exclusion is intentional rather than an oversight, feel free to close this issue — just wanted to raise it since V4 models are new and the docs explicitly mention OpenCode as a recognized integration.
Description
DeepSeek V4 Flash and Pro models support
reasoning_effort(documented on DeepSeek's Thinking Mode page — search for "Thinking Effort Control"), but Kilo v7.2.23 explicitly excludes all DeepSeek models from the reasoning effort variant and option system.From DeepSeek's Thinking Mode docs, the Thinking Effort Control table shows:
{"reasoning_effort": "high/max"}Their footnote also explicitly mentions: "for some complex agent requests (such as Claude Code, OpenCode), effort is automatically set to
max" — so this is a known integration point where OpenCode should already be recognized.DeepSeek API docs reference: https://api-docs.deepseek.com/guides/thinking_mode
Location in source (v7.2.23)
packages/opencode/src/provider/transform.ts— thevariants()function:When
variants()returns{}, no reasoning effort variants are offered or applied. Theoptions()function also does not inject any defaultreasoningEffortfor DeepSeek models.As a result:
options.reasoningEffortper agent in their configreasoningEffort: "medium"by default)Expected behavior
DeepSeek V4 Flash and Pro models should be included in the reasoning effort system:
deepseekfrom the exclusion list invariants(), or make the exclusion version-aware so V4+ models are includedreasoningEffortinjection inoptions()for DeepSeek V4 models (e.g.,"medium"default,"low"for small-model tasks)Workaround
Users can add
"options": { "reasoningEffort": "max" }to each agent definition in their config, but this bypasses the proper variant system and requires manual per-agent configuration.Environment
Note
If this exclusion is intentional rather than an oversight, feel free to close this issue — just wanted to raise it since V4 models are new and the docs explicitly mention OpenCode as a recognized integration.