merge: sync upstream/main, wire WebSearch through factory

Merge upstream/main into refactor/provider-protocol-122. Resolve http_provider.go conflict (keep thin delegate). Wire OpenAIProviderConfig.WebSearch through providerSelection and into CodexProvider for codex-auth and codex-cli-token paths.
2026-06-12 18:08:54 +00:00 · 2026-02-18 11:09:18 -03:00
parent c4cbb5fb35 eda6e37332
commit 2276bd149e
23 changed files with 1465 additions and 94 deletions
@@ -18,9 +18,10 @@ const codexDefaultModel = "gpt-5.2"
 const codexDefaultInstructions = "You are Codex, a coding assistant."

 type CodexProvider struct {
-	client      *openai.Client
-	accountID   string
-	tokenSource func() (string, string, error)
+	client          *openai.Client
+	accountID       string
+	tokenSource     func() (string, string, error)
+	enableWebSearch bool
 }

 const defaultCodexInstructions = "You are Codex, a coding assistant."
@@ -37,8 +38,9 @@ func NewCodexProvider(token, accountID string) *CodexProvider {
 	}
 	client := openai.NewClient(opts...)
 	return &CodexProvider{
-		client:    &client,
-		accountID: accountID,
+		client:          &client,
+		accountID:       accountID,
+		enableWebSearch: true,
 	}
 }

@@ -78,7 +80,7 @@ func (p *CodexProvider) Chat(ctx context.Context, messages []Message, tools []To
 		})
 	}

-	params := buildCodexParams(messages, tools, resolvedModel, options)
+	params := buildCodexParams(messages, tools, resolvedModel, options, p.enableWebSearch)

 	stream := p.client.Responses.NewStreaming(ctx, params, opts...)
 	defer stream.Close()
@@ -182,7 +184,7 @@ func resolveCodexModel(model string) (string, string) {
 	return codexDefaultModel, "unsupported model family"
 }

-func buildCodexParams(messages []Message, tools []ToolDefinition, model string, options map[string]interface{}) responses.ResponseNewParams {
+func buildCodexParams(messages []Message, tools []ToolDefinition, model string, options map[string]interface{}, enableWebSearch bool) responses.ResponseNewParams {
 	var inputItems responses.ResponseInputParam
 	var instructions string

@@ -217,12 +219,18 @@ func buildCodexParams(messages []Message, tools []ToolDefinition, model string,
 					})
 				}
 				for _, tc := range msg.ToolCalls {
-					argsJSON, _ := json.Marshal(tc.Arguments)
+					name, args, ok := resolveCodexToolCall(tc)
+					if !ok {
+						logger.WarnCF("provider.codex", "Skipping invalid tool call in history", map[string]interface{}{
+							"call_id": tc.ID,
+						})
+						continue
+					}
 					inputItems = append(inputItems, responses.ResponseInputItemUnionParam{
 						OfFunctionCall: &responses.ResponseFunctionToolCallParam{
 							CallID:    tc.ID,
-							Name:      tc.Name,
-							Arguments: string(argsJSON),
+							Name:      name,
+							Arguments: args,
 						},
 					})
 				}
@@ -260,20 +268,50 @@ func buildCodexParams(messages []Message, tools []ToolDefinition, model string,
 		params.Instructions = openai.Opt(defaultCodexInstructions)
 	}

-	if maxTokens, ok := options["max_tokens"].(int); ok {
-		params.MaxOutputTokens = openai.Opt(int64(maxTokens))
-	}
-
-	if len(tools) > 0 {
-		params.Tools = translateToolsForCodex(tools)
+	if len(tools) > 0 || enableWebSearch {
+		params.Tools = translateToolsForCodex(tools, enableWebSearch)
 	}

 	return params
 }

-func translateToolsForCodex(tools []ToolDefinition) []responses.ToolUnionParam {
-	result := make([]responses.ToolUnionParam, 0, len(tools))
+func resolveCodexToolCall(tc ToolCall) (name string, arguments string, ok bool) {
+	name = tc.Name
+	if name == "" && tc.Function != nil {
+		name = tc.Function.Name
+	}
+	if name == "" {
+		return "", "", false
+	}
+
+	if len(tc.Arguments) > 0 {
+		argsJSON, err := json.Marshal(tc.Arguments)
+		if err != nil {
+			return "", "", false
+		}
+		return name, string(argsJSON), true
+	}
+
+	if tc.Function != nil && tc.Function.Arguments != "" {
+		return name, tc.Function.Arguments, true
+	}
+
+	return name, "{}", true
+}
+
+func translateToolsForCodex(tools []ToolDefinition, enableWebSearch bool) []responses.ToolUnionParam {
+	capHint := len(tools)
+	if enableWebSearch {
+		capHint++
+	}
+	result := make([]responses.ToolUnionParam, 0, capHint)
 	for _, t := range tools {
+		if t.Type != "function" {
+			continue
+		}
+		if enableWebSearch && strings.EqualFold(t.Function.Name, "web_search") {
+			continue
+		}
 		ft := responses.FunctionToolParam{
 			Name:       t.Function.Name,
 			Parameters: t.Function.Parameters,
@@ -284,6 +322,9 @@ func translateToolsForCodex(tools []ToolDefinition) []responses.ToolUnionParam {
 		}
 		result = append(result, responses.ToolUnionParam{OfFunction: &ft})
 	}
+	if enableWebSearch {
+		result = append(result, responses.ToolParamOfWebSearch(responses.WebSearchToolTypeWebSearch))
+	}
 	return result
 }

@@ -19,7 +19,7 @@ func TestBuildCodexParams_BasicMessage(t *testing.T) {
 	params := buildCodexParams(messages, nil, "gpt-4o", map[string]interface{}{
 		"max_tokens":  2048,
 		"temperature": 0.7,
-	})
+	}, true)
 	if params.Model != "gpt-4o" {
 		t.Errorf("Model = %q, want %q", params.Model, "gpt-4o")
 	}
@@ -29,6 +29,9 @@ func TestBuildCodexParams_BasicMessage(t *testing.T) {
 	if params.Instructions.Or("") != defaultCodexInstructions {
 		t.Errorf("Instructions = %q, want %q", params.Instructions.Or(""), defaultCodexInstructions)
 	}
+	if params.MaxOutputTokens.Valid() {
+		t.Fatalf("MaxOutputTokens should not be set for Codex backend")
+	}
 }

 func TestBuildCodexParams_SystemAsInstructions(t *testing.T) {
@@ -36,7 +39,7 @@ func TestBuildCodexParams_SystemAsInstructions(t *testing.T) {
 		{Role: "system", Content: "You are helpful"},
 		{Role: "user", Content: "Hi"},
 	}
-	params := buildCodexParams(messages, nil, "gpt-4o", map[string]interface{}{})
+	params := buildCodexParams(messages, nil, "gpt-4o", map[string]interface{}{}, true)
 	if !params.Instructions.Valid() {
 		t.Fatal("Instructions should be set")
 	}
@@ -56,7 +59,7 @@ func TestBuildCodexParams_ToolCallConversation(t *testing.T) {
 		},
 		{Role: "tool", Content: `{"temp": 72}`, ToolCallID: "call_1"},
 	}
-	params := buildCodexParams(messages, nil, "gpt-4o", map[string]interface{}{})
+	params := buildCodexParams(messages, nil, "gpt-4o", map[string]interface{}{}, false)
 	if params.Input.OfInputItemList == nil {
 		t.Fatal("Input.OfInputItemList should not be nil")
 	}
@@ -65,6 +68,45 @@ func TestBuildCodexParams_ToolCallConversation(t *testing.T) {
 	}
 }

+func TestBuildCodexParams_ToolCallFunctionFallback(t *testing.T) {
+	messages := []Message{
+		{Role: "user", Content: "Read a file"},
+		{
+			Role: "assistant",
+			ToolCalls: []ToolCall{
+				{
+					ID:   "call_1",
+					Type: "function",
+					Function: &FunctionCall{
+						Name:      "read_file",
+						Arguments: `{"path":"README.md"}`,
+					},
+				},
+			},
+		},
+		{Role: "tool", Content: "ok", ToolCallID: "call_1"},
+	}
+
+	params := buildCodexParams(messages, nil, "gpt-4o", map[string]interface{}{}, false)
+	if params.Input.OfInputItemList == nil {
+		t.Fatal("Input.OfInputItemList should not be nil")
+	}
+	if len(params.Input.OfInputItemList) != 3 {
+		t.Fatalf("len(Input items) = %d, want 3", len(params.Input.OfInputItemList))
+	}
+
+	fc := params.Input.OfInputItemList[1].OfFunctionCall
+	if fc == nil {
+		t.Fatal("assistant tool call should be converted to function_call input item")
+	}
+	if fc.Name != "read_file" {
+		t.Errorf("Function call name = %q, want %q", fc.Name, "read_file")
+	}
+	if fc.Arguments != `{"path":"README.md"}` {
+		t.Errorf("Function call arguments = %q, want %q", fc.Arguments, `{"path":"README.md"}`)
+	}
+}
+
 func TestBuildCodexParams_WithTools(t *testing.T) {
 	tools := []ToolDefinition{
 		{
@@ -81,7 +123,7 @@ func TestBuildCodexParams_WithTools(t *testing.T) {
 			},
 		},
 	}
-	params := buildCodexParams([]Message{{Role: "user", Content: "Hi"}}, tools, "gpt-4o", map[string]interface{}{})
+	params := buildCodexParams([]Message{{Role: "user", Content: "Hi"}}, tools, "gpt-4o", map[string]interface{}{}, false)
 	if len(params.Tools) != 1 {
 		t.Fatalf("len(Tools) = %d, want 1", len(params.Tools))
 	}
@@ -94,12 +136,61 @@ func TestBuildCodexParams_WithTools(t *testing.T) {
 }

 func TestBuildCodexParams_StoreIsFalse(t *testing.T) {
-	params := buildCodexParams([]Message{{Role: "user", Content: "Hi"}}, nil, "gpt-4o", map[string]interface{}{})
+	params := buildCodexParams([]Message{{Role: "user", Content: "Hi"}}, nil, "gpt-4o", map[string]interface{}{}, false)
 	if !params.Store.Valid() || params.Store.Or(true) != false {
 		t.Error("Store should be explicitly set to false")
 	}
 }

+func TestBuildCodexParams_DefaultWebSearchEnabled(t *testing.T) {
+	params := buildCodexParams([]Message{{Role: "user", Content: "Hi"}}, nil, "gpt-4o", map[string]interface{}{}, true)
+	if len(params.Tools) != 1 {
+		t.Fatalf("len(Tools) = %d, want 1", len(params.Tools))
+	}
+	if params.Tools[0].OfWebSearch == nil {
+		t.Fatal("Tool should include built-in web_search")
+	}
+	if params.Tools[0].OfWebSearch.Type != responses.WebSearchToolTypeWebSearch {
+		t.Errorf("Web search tool type = %q, want %q", params.Tools[0].OfWebSearch.Type, responses.WebSearchToolTypeWebSearch)
+	}
+}
+
+func TestBuildCodexParams_WebSearchFunctionReplacedWithBuiltin(t *testing.T) {
+	tools := []ToolDefinition{
+		{
+			Type: "function",
+			Function: ToolFunctionDefinition{
+				Name:        "web_search",
+				Description: "local web search",
+				Parameters: map[string]interface{}{
+					"type": "object",
+				},
+			},
+		},
+		{
+			Type: "function",
+			Function: ToolFunctionDefinition{
+				Name:        "read_file",
+				Description: "read file",
+				Parameters: map[string]interface{}{
+					"type": "object",
+				},
+			},
+		},
+	}
+
+	params := buildCodexParams([]Message{{Role: "user", Content: "Hi"}}, tools, "gpt-4o", map[string]interface{}{}, true)
+	if len(params.Tools) != 2 {
+		t.Fatalf("len(Tools) = %d, want 2", len(params.Tools))
+	}
+	if params.Tools[0].OfFunction == nil || params.Tools[0].OfFunction.Name != "read_file" {
+		t.Fatalf("first tool should be function read_file, got %#v", params.Tools[0])
+	}
+	if params.Tools[1].OfWebSearch == nil {
+		t.Fatalf("second tool should be built-in web_search, got %#v", params.Tools[1])
+	}
+}
+
 func TestParseCodexResponse_TextOutput(t *testing.T) {
 	respJSON := `{
 		"id": "resp_test",
@@ -214,6 +305,20 @@ func TestCodexProvider_ChatRoundTrip(t *testing.T) {
 			http.Error(w, "stream must be true", http.StatusBadRequest)
 			return
 		}
+		if _, ok := reqBody["max_output_tokens"]; ok {
+			http.Error(w, "max_output_tokens is not supported", http.StatusBadRequest)
+			return
+		}
+		toolsAny, ok := reqBody["tools"].([]interface{})
+		if !ok || len(toolsAny) != 1 {
+			http.Error(w, "missing default web search tool", http.StatusBadRequest)
+			return
+		}
+		toolObj, ok := toolsAny[0].(map[string]interface{})
+		if !ok || toolObj["type"] != "web_search" {
+			http.Error(w, "expected web_search tool", http.StatusBadRequest)
+			return
+		}

 		resp := map[string]interface{}{
 			"id":     "resp_test",
@@ -261,6 +366,64 @@ func TestCodexProvider_ChatRoundTrip(t *testing.T) {
 	}
 }

+func TestCodexProvider_ChatRoundTrip_WebSearchDisabled(t *testing.T) {
+	server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		if r.URL.Path != "/responses" {
+			http.Error(w, "not found: "+r.URL.Path, http.StatusNotFound)
+			return
+		}
+
+		var reqBody map[string]interface{}
+		if err := json.NewDecoder(r.Body).Decode(&reqBody); err != nil {
+			http.Error(w, "invalid json", http.StatusBadRequest)
+			return
+		}
+		if _, ok := reqBody["tools"]; ok {
+			http.Error(w, "tools should be absent when web search disabled", http.StatusBadRequest)
+			return
+		}
+
+		resp := map[string]interface{}{
+			"id":     "resp_test",
+			"object": "response",
+			"status": "completed",
+			"output": []map[string]interface{}{
+				{
+					"id":     "msg_1",
+					"type":   "message",
+					"role":   "assistant",
+					"status": "completed",
+					"content": []map[string]interface{}{
+						{"type": "output_text", "text": "Hi from Codex!"},
+					},
+				},
+			},
+			"usage": map[string]interface{}{
+				"input_tokens":          4,
+				"output_tokens":         3,
+				"total_tokens":          7,
+				"input_tokens_details":  map[string]interface{}{"cached_tokens": 0},
+				"output_tokens_details": map[string]interface{}{"reasoning_tokens": 0},
+			},
+		}
+		writeCompletedSSE(w, resp)
+	}))
+	defer server.Close()
+
+	provider := NewCodexProvider("test-token", "acc-123")
+	provider.enableWebSearch = false
+	provider.client = createOpenAITestClient(server.URL, "test-token", "acc-123")
+
+	messages := []Message{{Role: "user", Content: "Hello"}}
+	resp, err := provider.Chat(t.Context(), messages, nil, "gpt-4o", map[string]interface{}{})
+	if err != nil {
+		t.Fatalf("Chat() error: %v", err)
+	}
+	if resp.Content != "Hi from Codex!" {
+		t.Errorf("Content = %q, want %q", resp.Content, "Hi from Codex!")
+	}
+}
+
 func TestCodexProvider_ChatRoundTrip_TokenSourceFallbackAccountID(t *testing.T) {
 	server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
 		if r.URL.Path != "/responses" {
@@ -293,6 +456,10 @@ func TestCodexProvider_ChatRoundTrip_TokenSourceFallbackAccountID(t *testing.T)
 			http.Error(w, "temperature is not supported", http.StatusBadRequest)
 			return
 		}
+		if _, ok := reqBody["max_output_tokens"]; ok {
+			http.Error(w, "max_output_tokens is not supported", http.StatusBadRequest)
+			return
+		}
 		if reqBody["stream"] != true {
 			http.Error(w, "stream must be true", http.StatusBadRequest)
 			return
@@ -25,13 +25,14 @@ const (
 )

 type providerSelection struct {
-	providerType providerType
-	apiKey       string
-	apiBase      string
-	proxy        string
-	model        string
-	workspace    string
-	connectMode  string
+	providerType    providerType
+	apiKey          string
+	apiBase         string
+	proxy           string
+	model           string
+	workspace       string
+	connectMode     string
+	enableWebSearch bool
 }

 func createClaudeAuthProvider(apiBase string) (LLMProvider, error) {
@@ -48,7 +49,7 @@ func createClaudeAuthProvider(apiBase string) (LLMProvider, error) {
 	return NewClaudeProviderWithTokenSourceAndBaseURL(cred.AccessToken, createClaudeTokenSource(), apiBase), nil
 }

-func createCodexAuthProvider() (LLMProvider, error) {
+func createCodexAuthProvider(enableWebSearch bool) (LLMProvider, error) {
 	cred, err := getCredential("openai")
 	if err != nil {
 		return nil, fmt.Errorf("loading auth credentials: %w", err)
@@ -56,7 +57,9 @@ func createCodexAuthProvider() (LLMProvider, error) {
 	if cred == nil {
 		return nil, fmt.Errorf("no credentials for openai. Run: picoclaw auth login --provider openai")
 	}
-	return NewCodexProviderWithTokenSource(cred.AccessToken, cred.AccountID, createCodexTokenSource()), nil
+	p := NewCodexProviderWithTokenSource(cred.AccessToken, cred.AccountID, createCodexTokenSource())
+	p.enableWebSearch = enableWebSearch
+	return p, nil
 }

 func resolveProviderSelection(cfg *config.Config) (providerSelection, error) {
@@ -83,6 +86,7 @@ func resolveProviderSelection(cfg *config.Config) (providerSelection, error) {
 			}
 		case "openai", "gpt":
 			if cfg.Providers.OpenAI.APIKey != "" || cfg.Providers.OpenAI.AuthMethod != "" {
+				sel.enableWebSearch = cfg.Providers.OpenAI.WebSearch
 				if cfg.Providers.OpenAI.AuthMethod == "codex-cli" {
 					sel.providerType = providerTypeCodexCLIToken
 					return sel, nil
@@ -248,6 +252,7 @@ func resolveProviderSelection(cfg *config.Config) (providerSelection, error) {
 			}
 		case (strings.Contains(lowerModel, "gpt") || strings.HasPrefix(model, "openai/")) &&
 			(cfg.Providers.OpenAI.APIKey != "" || cfg.Providers.OpenAI.AuthMethod != ""):
+			sel.enableWebSearch = cfg.Providers.OpenAI.WebSearch
 			if cfg.Providers.OpenAI.AuthMethod == "codex-cli" {
 				sel.providerType = providerTypeCodexCLIToken
 				return sel, nil
@@ -338,9 +343,11 @@ func CreateProvider(cfg *config.Config) (LLMProvider, error) {
 	case providerTypeClaudeAuth:
 		return createClaudeAuthProvider(sel.apiBase)
 	case providerTypeCodexAuth:
-		return createCodexAuthProvider()
+		return createCodexAuthProvider(sel.enableWebSearch)
 	case providerTypeCodexCLIToken:
-		return NewCodexProviderWithTokenSource("", "", CreateCodexCliTokenSource()), nil
+		c := NewCodexProviderWithTokenSource("", "", CreateCodexCliTokenSource())
+		c.enableWebSearch = sel.enableWebSearch
+		return c, nil
 	case providerTypeClaudeCLI:
 		return NewClaudeCliProvider(sel.workspace), nil
 	case providerTypeCodexCLI: