fix: Gemini provider compatibility with Gemini 3 models

- Strip additionalProperties and $schema from tool parameter schemas (Gemini API rejects these unsupported JSON Schema fields) - Add thoughtSignature to functionCall parts for multi-turn tool calling (Gemini 3 models require thought signatures on function call history) - Ensure functionResponse.response is always a JSON object, never an array or primitive (wrap non-objects in {"result": ...}) - Resolve tool names from tool_call_id or positional index when the tool message doesn't carry a name field - Add functionCall parsing in streaming responses (emitGeminiChunk) to properly relay tool calls via SSE - Add error logging for Gemini stream failures with request body dump - Add unit tests for schema cleaning and streaming tool call emission
2026-07-17 13:41:41 +00:00
parent a187d8e20e
commit eb90f949a0
3 changed files with 337 additions and 22 deletions
@@ -59,6 +59,7 @@ type GeminiPart struct {
 	InlineData       *GeminiInlineData       `json:"inlineData,omitempty"`
 	FunctionCall     *GeminiFunctionCall     `json:"functionCall,omitempty"`
 	FunctionResponse *GeminiFunctionResponse `json:"functionResponse,omitempty"`
+	ThoughtSignature string                  `json:"thoughtSignature,omitempty"`
 }

 type GeminiInlineData struct {
@@ -231,6 +232,7 @@ func (p *GeminiProvider) ChatCompletion(ctx context.Context, req *models.Unified
 						Name: tc.Function.Name,
 						Args: json.RawMessage(tc.Function.Arguments),
 					},
+					ThoughtSignature: "skip_thought_signature_validator",
 				})
 			}
 			contents = append(contents, GeminiContent{Role: "model", Parts: parts})
@@ -256,16 +258,9 @@ func (p *GeminiProvider) ChatCompletion(ctx context.Context, req *models.Unified
 				if len(m.Content) > 0 {
 					text = m.Content[0].Text
 				}
-				name := "unknown_function"
-				if m.Name != nil {
-					name = *m.Name
-				}
+				name := resolveToolName(m, msg.ToolCalls, j-i-1)

-				var responseObj interface{}
-				if err := json.Unmarshal([]byte(text), &responseObj); err != nil {
-					responseObj = map[string]interface{}{"result": text}
-				}
-				respBytes, _ := json.Marshal(responseObj)
+				respBytes := ensureJSONObject(text)

 				functionParts = append(functionParts, GeminiPart{
 					FunctionResponse: &GeminiFunctionResponse{
@@ -353,7 +348,9 @@ func (p *GeminiProvider) ChatCompletion(ctx context.Context, req *models.Unified
 		geminiTool := GeminiTool{FunctionDeclarations: []models.FunctionDef{}}
 		for _, t := range req.Tools {
 			if t.Type == "function" {
-				geminiTool.FunctionDeclarations = append(geminiTool.FunctionDeclarations, t.Function)
+				funcDef := t.Function
+				funcDef.Parameters = cleanParametersSchema(funcDef.Parameters)
+				geminiTool.FunctionDeclarations = append(geminiTool.FunctionDeclarations, funcDef)
 			}
 		}
 		if len(geminiTool.FunctionDeclarations) > 0 {
@@ -509,6 +506,7 @@ func (p *GeminiProvider) ChatCompletionStream(ctx context.Context, req *models.U
 						Name: tc.Function.Name,
 						Args: json.RawMessage(tc.Function.Arguments),
 					},
+					ThoughtSignature: "skip_thought_signature_validator",
 				})
 			}
 			contents = append(contents, GeminiContent{Role: "model", Parts: parts})
@@ -522,16 +520,9 @@ func (p *GeminiProvider) ChatCompletionStream(ctx context.Context, req *models.U
 				if len(m.Content) > 0 {
 					text = m.Content[0].Text
 				}
-				name := "unknown_function"
-				if m.Name != nil {
-					name = *m.Name
-				}
+				name := resolveToolName(m, msg.ToolCalls, j-i-1)

-				var responseObj interface{}
-				if err := json.Unmarshal([]byte(text), &responseObj); err != nil {
-					responseObj = map[string]interface{}{"result": text}
-				}
-				respBytes, _ := json.Marshal(responseObj)
+				respBytes := ensureJSONObject(text)

 				functionParts = append(functionParts, GeminiPart{
 					FunctionResponse: &GeminiFunctionResponse{
@@ -610,7 +601,9 @@ func (p *GeminiProvider) ChatCompletionStream(ctx context.Context, req *models.U
 		geminiTool := GeminiTool{FunctionDeclarations: []models.FunctionDef{}}
 		for _, t := range req.Tools {
 			if t.Type == "function" {
-				geminiTool.FunctionDeclarations = append(geminiTool.FunctionDeclarations, t.Function)
+				funcDef := t.Function
+				funcDef.Parameters = cleanParametersSchema(funcDef.Parameters)
+				geminiTool.FunctionDeclarations = append(geminiTool.FunctionDeclarations, funcDef)
 			}
 		}
 		if len(geminiTool.FunctionDeclarations) > 0 {
@@ -652,6 +645,9 @@ func (p *GeminiProvider) ChatCompletionStream(ctx context.Context, req *models.U
 				msg = string(body)
 			}
 		}
+		fmt.Printf("[Gemini-Stream] API Error %d: %s\n", resp.StatusCode(), msg)
+		reqJSON, _ := json.Marshal(body)
+		fmt.Printf("[Gemini-Stream] Request Body: %s\n", string(reqJSON))
 		return nil, fmt.Errorf("Gemini API error (%d): %s", resp.StatusCode(), msg)
 	}

@@ -668,3 +664,87 @@ func uint32Ptr(v uint32) *uint32 {
 	}
 	return nil
 }
+
+func cleanGeminiSchema(schema map[string]interface{}) {
+	delete(schema, "additionalProperties")
+	delete(schema, "$schema")
+	for _, v := range schema {
+		if subMap, ok := v.(map[string]interface{}); ok {
+			cleanGeminiSchema(subMap)
+		} else if subList, ok := v.([]interface{}); ok {
+			for _, item := range subList {
+				if itemMap, ok := item.(map[string]interface{}); ok {
+					cleanGeminiSchema(itemMap)
+				}
+			}
+		}
+	}
+}
+
+func cleanParametersSchema(raw json.RawMessage) json.RawMessage {
+	if len(raw) == 0 {
+		return raw
+	}
+	var schema map[string]interface{}
+	if err := json.Unmarshal(raw, &schema); err != nil {
+		return raw
+	}
+	cleanGeminiSchema(schema)
+	cleaned, err := json.Marshal(schema)
+	if err != nil {
+		return raw
+	}
+	return json.RawMessage(cleaned)
+}
+
+// ensureJSONObject ensures that a tool result string is serialized as a JSON object
+// for Gemini's functionResponse.response field, which must always be an object.
+// If the text is a JSON array, primitive, or invalid JSON, it gets wrapped in {"result": ...}.
+func ensureJSONObject(text string) []byte {
+	if text == "" {
+		b, _ := json.Marshal(map[string]interface{}{"result": ""})
+		return b
+	}
+
+	var parsed interface{}
+	if err := json.Unmarshal([]byte(text), &parsed); err != nil {
+		// Not valid JSON — wrap as string
+		b, _ := json.Marshal(map[string]interface{}{"result": text})
+		return b
+	}
+
+	// Only allow map types through; wrap everything else
+	if _, ok := parsed.(map[string]interface{}); ok {
+		return []byte(text)
+	}
+
+	// It's a JSON array, number, string, bool, or null — wrap it
+	b, _ := json.Marshal(map[string]interface{}{"result": parsed})
+	return b
+}
+
+// resolveToolName determines the function name for a tool response message.
+// It tries: 1) the Name field on the tool message, 2) matching by ToolCallID
+// against the preceding assistant's tool calls, 3) positional index match.
+func resolveToolName(toolMsg models.UnifiedMessage, toolCalls []models.ToolCall, posIndex int) string {
+	if toolMsg.Name != nil && *toolMsg.Name != "" {
+		return *toolMsg.Name
+	}
+
+	// Try to match by tool_call_id
+	if toolMsg.ToolCallID != nil && *toolMsg.ToolCallID != "" {
+		for _, tc := range toolCalls {
+			if tc.ID == *toolMsg.ToolCallID {
+				return tc.Function.Name
+			}
+		}
+	}
+
+	// Positional fallback
+	if posIndex >= 0 && posIndex < len(toolCalls) {
+		return toolCalls[posIndex].Function.Name
+	}
+
+	return "unknown_function"
+}
+