chuan/CLIProxyAPI
1
0
Fork 0
mirror of https://github.com/router-for-me/CLIProxyAPI.git synced 2026-02-03 21:10:51 +08:00
Code Issues Packages Projects Releases Wiki Activity

refactor(iflow): simplify thinking config handling for GLM and MiniMax models

Browse Source
This commit is contained in:
hkfires
2026-01-01 19:31:08 +08:00
parent 2d2f4572a7
commit 4fc3d5e935
3 changed files with 31 additions and 45 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
internal/registry/model_definitions.go
View File

@@ -740,7 +740,7 @@ func GetIFlowModels() []*ModelInfo {
{ID: "qwen3-235b-a22b-thinking-2507", DisplayName: "Qwen3-235B-A22B-Thinking", Description: "Qwen3 235B A22B Thinking (2507)", Created: 1753401600}, {ID: "qwen3-235b-a22b-thinking-2507", DisplayName: "Qwen3-235B-A22B-Thinking", Description: "Qwen3 235B A22B Thinking (2507)", Created: 1753401600},
{ID: "qwen3-235b-a22b-instruct", DisplayName: "Qwen3-235B-A22B-Instruct", Description: "Qwen3 235B A22B Instruct", Created: 1753401600}, {ID: "qwen3-235b-a22b-instruct", DisplayName: "Qwen3-235B-A22B-Instruct", Description: "Qwen3 235B A22B Instruct", Created: 1753401600},
{ID: "qwen3-235b", DisplayName: "Qwen3-235B-A22B", Description: "Qwen3 235B A22B", Created: 1753401600}, {ID: "qwen3-235b", DisplayName: "Qwen3-235B-A22B", Description: "Qwen3 235B A22B", Created: 1753401600},
{ID: "minimax-m2", DisplayName: "MiniMax-M2", Description: "MiniMax M2", Created: 1758672000}, {ID: "minimax-m2", DisplayName: "MiniMax-M2", Description: "MiniMax M2", Created: 1758672000, Thinking: iFlowThinkingSupport},
{ID: "minimax-m2.1", DisplayName: "MiniMax-M2.1", Description: "MiniMax M2.1", Created: 1766448000, Thinking: iFlowThinkingSupport}, {ID: "minimax-m2.1", DisplayName: "MiniMax-M2.1", Description: "MiniMax M2.1", Created: 1766448000, Thinking: iFlowThinkingSupport},
} }
models := make([]*ModelInfo, 0, len(entries)) models := make([]*ModelInfo, 0, len(entries))

70
internal/runtime/executor/iflow_executor.go
View File

@@ -441,21 +441,18 @@ func ensureToolsArray(body []byte) []byte {
return updated return updated
} }
// preserveReasoningContentInMessages ensures reasoning_content from assistant messages in the // preserveReasoningContentInMessages checks if reasoning_content from assistant messages
// conversation history is preserved when sending to iFlow models that support thinking. // is preserved in conversation history for iFlow models that support thinking.
// This is critical for multi-turn conversations where the model needs to see its previous // This is helpful for multi-turn conversations where the model may benefit from seeing
// reasoning to maintain coherent thought chains across tool calls and conversation turns. // its previous reasoning to maintain coherent thought chains.
// //
// For GLM-4.7 and MiniMax-M2.1, the full assistant response (including reasoning) must be // For GLM-4.6/4.7 and MiniMax M2/M2.1, it is recommended to include the full assistant
// appended back into message history before the next call. // response (including reasoning_content) in message history for better context continuity.
func preserveReasoningContentInMessages(body []byte) []byte { func preserveReasoningContentInMessages(body []byte) []byte {
model := strings.ToLower(gjson.GetBytes(body, "model").String()) model := strings.ToLower(gjson.GetBytes(body, "model").String())
// Only apply to models that support thinking with history preservation // Only apply to models that support thinking with history preservation
needsPreservation := strings.HasPrefix(model, "glm-4.7") || needsPreservation := strings.HasPrefix(model, "glm-4") || strings.HasPrefix(model, "minimax-m2")
strings.HasPrefix(model, "glm-4-7") ||
strings.HasPrefix(model, "minimax-m2.1") ||
strings.HasPrefix(model, "minimax-m2-1")
if !needsPreservation { if !needsPreservation {
return body return body
@@ -493,45 +490,34 @@ func preserveReasoningContentInMessages(body []byte) []byte {
// This should be called after NormalizeThinkingConfig has processed the payload. // This should be called after NormalizeThinkingConfig has processed the payload.
// //
// Model-specific handling: // Model-specific handling:
// - GLM-4.7: Uses extra_body={"thinking": {"type": "enabled"}, "clear_thinking": false} // - GLM-4.6/4.7: Uses chat_template_kwargs.enable_thinking (boolean) and chat_template_kwargs.clear_thinking=false
// - MiniMax-M2.1: Uses reasoning_split=true for OpenAI-style reasoning separation // - MiniMax M2/M2.1: Uses reasoning_split=true for OpenAI-style reasoning separation
// - Other iFlow models: Uses chat_template_kwargs.enable_thinking (boolean)
func applyIFlowThinkingConfig(body []byte) []byte { func applyIFlowThinkingConfig(body []byte) []byte {
effort := gjson.GetBytes(body, "reasoning_effort") effort := gjson.GetBytes(body, "reasoning_effort")
model := strings.ToLower(gjson.GetBytes(body, "model").String()) if !effort.Exists() {
return body
// Check if thinking should be enabled
val := ""
if effort.Exists() {
val = strings.ToLower(strings.TrimSpace(effort.String()))
} }
enableThinking := effort.Exists() && val != "none" && val != ""
model := strings.ToLower(gjson.GetBytes(body, "model").String())
val := strings.ToLower(strings.TrimSpace(effort.String()))
enableThinking := val != "none" && val != ""
// Remove reasoning_effort as we'll convert to model-specific format // Remove reasoning_effort as we'll convert to model-specific format
if effort.Exists() { body, _ = sjson.DeleteBytes(body, "reasoning_effort")
body, _ = sjson.DeleteBytes(body, "reasoning_effort")
}
// GLM-4.7: Use extra_body with thinking config and clear_thinking: false // GLM-4.6/4.7: Use chat_template_kwargs
if strings.HasPrefix(model, "glm-4.7") || strings.HasPrefix(model, "glm-4-7") { if strings.HasPrefix(model, "glm-4") {
if enableThinking {
body, _ = sjson.SetBytes(body, "extra_body.thinking.type", "enabled")
body, _ = sjson.SetBytes(body, "extra_body.clear_thinking", false)
}
return body
}
// MiniMax-M2.1: Use reasoning_split=true for interleaved thinking
if strings.HasPrefix(model, "minimax-m2.1") || strings.HasPrefix(model, "minimax-m2-1") {
if enableThinking {
body, _ = sjson.SetBytes(body, "reasoning_split", true)
}
return body
}
// Other iFlow models (including GLM-4.6): Use chat_template_kwargs.enable_thinking
if effort.Exists() {
body, _ = sjson.SetBytes(body, "chat_template_kwargs.enable_thinking", enableThinking) body, _ = sjson.SetBytes(body, "chat_template_kwargs.enable_thinking", enableThinking)
if enableThinking {
body, _ = sjson.SetBytes(body, "chat_template_kwargs.clear_thinking", false)
}
return body
}
// MiniMax M2/M2.1: Use reasoning_split
if strings.HasPrefix(model, "minimax-m2") {
body, _ = sjson.SetBytes(body, "reasoning_split", enableThinking)
return body
} }
return body return body