Add web search capabilities

README.md

@@ -76,9 +76,38 @@ Each bot is one JSON file in `config/` (see `config/default.json` for the templa
 | `max_tokens`       | number | `1000`      | Maximum output tokens per reply. **Thinking tokens count toward this limit** — raise it (e.g. `4000`+) whenever `thinking` is `"adaptive"`, or a turn can spend the whole budget on reasoning and produce no text. |
 | `thinking`         | string | *(omitted)* | Reasoning mode: `"adaptive"` (the model decides when and how much to think) or `"disabled"`. Omit the key entirely to use the model's own API default. If the configured model doesn't support the chosen mode, the API rejects the request with a 400 — owners/admins see the raw error, regular users get the generic fallback. Check [Anthropic's model docs](https://platform.claude.com/docs/en/build-with-claude/adaptive-thinking) for per-model support. |
 | `thinking_display` | string | *(omitted)* | `"summarized"` or `"omitted"`. Only valid together with `"thinking": "adaptive"`. Controls whether the API returns a readable summary of the reasoning (logged, never sent to chat). Thinking is billed the same either way; when omitted, the API's per-model default applies. |
+| `web_search`       | object | *(omitted)* | Enables Anthropic's server-side web search (and, optionally, web fetch), sandboxed to a domain allowlist. Omit the key entirely to leave both tools off — an absent block sends byte-identical requests to before. See [Web search / fetch](#web-search--fetch) below. |
 
 Every reply logs one accounting line — `[usage] model=... in=... out=... thinking=... stop=...` — so thinking spend (billed even when its text is omitted) stays visible in `journalctl`/`docker compose logs`. A `stop=max_tokens` line is accompanied by an error-level warning that the reply was truncated.
 
+### Web search / fetch
+
+The `web_search` block wires in Anthropic's server-side `web_search` (and optionally `web_fetch`) tools, mirroring how `mcp_servers` wires in MCP toolsets: the engine provides the generic mechanism, and the per-bot config carries the policy. **No domains are hardcoded in the engine** — each profile declares its own allowlist. When the model decides a question needs current information, it runs a search server-side; results and any fetch targets are confined to the domains you list.
+
+```json
+"web_search": {
+  "allowed_domains": [
+    "example.com/help",
+    "docs.example.com"
+  ],
+  "max_uses": 3,
+  "fetch": true,
+  "max_content_tokens": 50000
+}
+```
+
+| Field                | Type     | Description |
+| -------------------- | -------- | ----------- |
+| `allowed_domains`    | string[] | Search results and fetch targets are restricted to these. Each entry is a **domain with an optional path prefix and no scheme** — `example.com` or `example.com/help`. Mutually exclusive with `blocked_domains`. |
+| `blocked_domains`    | string[] | Excludes these domains instead of allowlisting. Mutually exclusive with `allowed_domains` (setting both fails validation at boot, since the API 400s). |
+| `max_uses`           | number   | Caps how many searches the model may run per turn. Omit for no cap. |
+| `fetch`              | bool     | Also enable `web_fetch`, which pulls full page content for URLs already surfaced by a search or pasted by the user (it cannot fetch model-invented URLs). Shares the same allow/block list. Citations are always on when fetch is enabled, so fetched passages are sourceable. |
+| `max_content_tokens` | number   | Caps the tokens a single `web_fetch` may pull into context. Only meaningful with `fetch: true`. |
+
+The allowlist is a **hard, server-side sandbox**, not a prompt request — off-list results are dropped and an off-list fetch target returns `url_not_allowed`, which is the exfiltration mitigation Anthropic recommends for bots processing untrusted input. Keep the list tight. Note that `web_fetch` cannot read JavaScript-rendered pages, so for dynamic sites the search snippet (plus citations) is the reliable signal and a full fetch is a bonus, not a dependency.
+
+Web search is **not free** — Anthropic bills per search (plus the tokens the results add) — so scope the allowlist and `max_uses` deliberately, and lean on a prompt that tells the bot to search only when a question actually turns on current or authoritative information. Search activity logs as `[web] ...` lines, and long multi-search turns are handled transparently (the engine follows Anthropic's `pause_turn` continuations up to a small cap, so a slow search doesn't truncate the reply).
+
 > [!TIP]
 > For deep request/response debugging, the Anthropic Go SDK ships `option.WithDebugLog(...)` (dumps full HTTP bodies with auth headers redacted). It is not wired into the bot — dev-only, add it temporarily to the client constructor if you ever need wire-level traces.
 

anthropic.go

@@ -17,6 +17,8 @@ var ErrModelNotFound = errors.New("model not found or deprecated")
 
 const maxFileNotFoundRetries = 3
 
+const maxPauseTurnContinuations = 5
+
 const defaultMaxTokens = 1000
 
 const mcpUnsupportedSentinel = "format not currently supported by the Anthropic API"
@@ -65,9 +67,10 @@ func (b *Bot) getAnthropicResponse(ctx context.Context, chatID int64, messages [
 		params.Thinking = thinking
 	}
 
+	var tools []anthropic.BetaToolUnionParam
+
 	if len(b.config.MCPServers) > 0 {
 		mcpServers := make([]anthropic.BetaRequestMCPServerURLDefinitionParam, 0, len(b.config.MCPServers))
-		tools := make([]anthropic.BetaToolUnionParam, 0, len(b.config.MCPServers))
 		for _, s := range b.config.MCPServers {
 			srv := anthropic.BetaRequestMCPServerURLDefinitionParam{
 				Name: s.Name,
@@ -95,32 +98,99 @@ func (b *Bot) getAnthropicResponse(ctx context.Context, chatID int64, messages [
 			tools = append(tools, anthropic.BetaToolUnionParam{OfMCPToolset: toolset})
 		}
 		params.MCPServers = mcpServers
-		params.Tools = tools
 		params.Betas = append(params.Betas, anthropic.AnthropicBetaMCPClient2025_11_20)
 	}
 
-	for attempt := 0; attempt < maxFileNotFoundRetries; attempt++ {
+	tools = append(tools, webSearchTools(b.config.WebSearch)...)
-		joined, streamErr := b.streamMessages(ctx, params, onSegment)
+
-		if streamErr == nil {
+	if len(tools) > 0 {
-			return joined, nil
+		params.Tools = tools
-		}
-		var apiErr *anthropic.Error
-		if !errors.As(streamErr, &apiErr) || apiErr.StatusCode != http.StatusNotFound {
-			return "", fmt.Errorf("error creating Anthropic message: %w", streamErr)
-		}
-		missingFileID := extractMissingFileID(streamErr)
-		if missingFileID == "" {
-			return "", fmt.Errorf("%w: %s", ErrModelNotFound, b.config.Model)
-		}
-		ErrorLogger.Printf("[%s] self-heal: stripping dead file_id %s from chat %d (attempt %d/%d)",
-			b.config.ID, missingFileID, chatID, attempt+1, maxFileNotFoundRetries)
-		b.stripDeadFileIDFromMemory(chatID, missingFileID)
-		if _, cleanupErr := b.markFilesPendingCleanup(ctx, chatID, []string{missingFileID}); cleanupErr != nil {
-			ErrorLogger.Printf("[%s] mark files pending cleanup: %v", b.config.ID, cleanupErr)
-		}
-		params.Messages = b.prepareContextMessages(b.getOrCreateChatMemory(chatID))
 	}
-	return "", fmt.Errorf("max self-heal retries (%d) exceeded: too many file_ids gone from anthropic", maxFileNotFoundRetries)
+
+	var fullText strings.Builder
+	var lastMsg anthropic.BetaMessage
+	fileRetries, pauseContinuations := 0, 0
+	for {
+		joined, msg, streamErr := b.streamMessages(ctx, params, onSegment)
+		if streamErr != nil {
+			var apiErr *anthropic.Error
+			if !errors.As(streamErr, &apiErr) || apiErr.StatusCode != http.StatusNotFound {
+				return "", fmt.Errorf("error creating Anthropic message: %w", streamErr)
+			}
+			missingFileID := extractMissingFileID(streamErr)
+			if missingFileID == "" {
+				return "", fmt.Errorf("%w: %s", ErrModelNotFound, b.config.Model)
+			}
+			fileRetries++
+			if fileRetries > maxFileNotFoundRetries {
+				return "", fmt.Errorf("max self-heal retries (%d) exceeded: too many file_ids gone from anthropic", maxFileNotFoundRetries)
+			}
+			ErrorLogger.Printf("[%s] self-heal: stripping dead file_id %s from chat %d (attempt %d/%d)",
+				b.config.ID, missingFileID, chatID, fileRetries, maxFileNotFoundRetries)
+			b.stripDeadFileIDFromMemory(chatID, missingFileID)
+			if _, cleanupErr := b.markFilesPendingCleanup(ctx, chatID, []string{missingFileID}); cleanupErr != nil {
+				ErrorLogger.Printf("[%s] mark files pending cleanup: %v", b.config.ID, cleanupErr)
+			}
+			params.Messages = b.prepareContextMessages(b.getOrCreateChatMemory(chatID))
+			continue
+		}
+
+		lastMsg = msg
+		if joined != "" {
+			if fullText.Len() > 0 {
+				fullText.WriteString("\n\n")
+			}
+			fullText.WriteString(joined)
+		}
+
+		if msg.StopReason == anthropic.BetaStopReasonPauseTurn {
+			pauseContinuations++
+			if pauseContinuations > maxPauseTurnContinuations {
+				ErrorLogger.Printf("[%s] pause_turn continuations exceeded (%d); returning partial answer",
+					b.config.ID, maxPauseTurnContinuations)
+				break
+			}
+			params.Messages = append(params.Messages, msg.ToParam())
+			continue
+		}
+		break
+	}
+
+	if fullText.Len() == 0 {
+		return "", emptyStreamError(string(lastMsg.StopReason),
+			lastMsg.Usage.OutputTokensDetails.ThinkingTokens, params.MaxTokens)
+	}
+	return fullText.String(), nil
+}
+
+func webSearchTools(cfg *WebSearchConfig) []anthropic.BetaToolUnionParam {
+	if cfg == nil {
+		return nil
+	}
+	search := &anthropic.BetaWebSearchTool20250305Param{
+		AllowedDomains: cfg.AllowedDomains,
+		BlockedDomains: cfg.BlockedDomains,
+	}
+	if cfg.MaxUses > 0 {
+		search.MaxUses = param.NewOpt(int64(cfg.MaxUses))
+	}
+	tools := []anthropic.BetaToolUnionParam{{OfWebSearchTool20250305: search}}
+
+	if cfg.Fetch {
+		fetch := &anthropic.BetaWebFetchTool20250910Param{
+			AllowedDomains: cfg.AllowedDomains,
+			BlockedDomains: cfg.BlockedDomains,
+			Citations:      anthropic.BetaCitationsConfigParam{Enabled: param.NewOpt(true)},
+		}
+		if cfg.MaxUses > 0 {
+			fetch.MaxUses = param.NewOpt(int64(cfg.MaxUses))
+		}
+		if cfg.MaxContentTokens > 0 {
+			fetch.MaxContentTokens = param.NewOpt(int64(cfg.MaxContentTokens))
+		}
+		tools = append(tools, anthropic.BetaToolUnionParam{OfWebFetchTool20250910: fetch})
+	}
+	return tools
 }
 
 func buildUserContext(username, firstName, lastName string, isPremium bool, languageCode string, messageTime int) string {
@@ -179,7 +249,7 @@ func thinkingParamFromConfig(mode, display string) (anthropic.BetaThinkingConfig
 	}
 }
 
-func (b *Bot) streamMessages(ctx context.Context, params anthropic.BetaMessageNewParams, onSegment func(string) error) (string, error) {
+func (b *Bot) streamMessages(ctx context.Context, params anthropic.BetaMessageNewParams, onSegment func(string) error) (string, anthropic.BetaMessage, error) {
 	stream := b.anthropicClient.Beta.Messages.NewStreaming(ctx, params)
 	defer func() {
 		if err := stream.Close(); err != nil {
@@ -188,6 +258,7 @@ func (b *Bot) streamMessages(ctx context.Context, params anthropic.BetaMessageNe
 	}()
 
 	var (
+		message                                           anthropic.BetaMessage
 		allSegments                                       []string
 		currentKind                                       string
 		currentText                                       strings.Builder
@@ -197,31 +268,24 @@ func (b *Bot) streamMessages(ctx context.Context, params anthropic.BetaMessageNe
 		currentTResultUseID, currentTResultServer         string
 		currentTResultIsError                             bool
 		currentTResultContent                             string
+		currentServerToolName, currentServerToolID        string
+		currentServerResult                               string
 		mcpCalls                                          = map[string]mcpCall{}
-		startInputTokens                                  int64
-		finalUsage                                        anthropic.BetaMessageDeltaUsage
-		stopReason                                        string
 	)
 
 	for stream.Next() {
 		e := stream.Current()
+		if accErr := message.Accumulate(e); accErr != nil {
+			ErrorLogger.Printf("[stream] accumulate failed: %v", accErr)
+		}
 		switch e.Type {
-		case "message_start":
-			startInputTokens = e.AsMessageStart().Message.Usage.InputTokens
-
-		case "message_delta":
-			md := e.AsMessageDelta()
-			finalUsage = md.Usage
-			if md.Delta.StopReason != "" {
-				stopReason = string(md.Delta.StopReason)
-			}
-
 		case "content_block_start":
 			cbs := e.AsContentBlockStart()
 			currentKind = cbs.ContentBlock.Type
 			currentText.Reset()
 			currentThinking.Reset()
 			currentInputJSON.Reset()
+			currentServerResult = ""
 			switch currentKind {
 			case "mcp_tool_use":
 				currentTUseName = cbs.ContentBlock.Name
@@ -232,6 +296,11 @@ func (b *Bot) streamMessages(ctx context.Context, params anthropic.BetaMessageNe
 				currentTResultServer = cbs.ContentBlock.ServerName
 				currentTResultIsError = cbs.ContentBlock.IsError
 				currentTResultContent = cbs.ContentBlock.JSON.Content.Raw()
+			case "server_tool_use":
+				currentServerToolName = cbs.ContentBlock.Name
+				currentServerToolID = cbs.ContentBlock.ID
+			case "web_search_tool_result", "web_fetch_tool_result":
+				currentServerResult = cbs.ContentBlock.JSON.Content.Raw()
 			}
 
 		case "content_block_delta":
@@ -246,7 +315,7 @@ func (b *Bot) streamMessages(ctx context.Context, params anthropic.BetaMessageNe
 					currentThinking.WriteString(cbd.Delta.Thinking)
 				}
 			case "input_json_delta":
-				if currentKind == "mcp_tool_use" {
+				if currentKind == "mcp_tool_use" || currentKind == "server_tool_use" {
 					currentInputJSON.WriteString(cbd.Delta.PartialJSON)
 				}
 			}
@@ -285,6 +354,15 @@ func (b *Bot) streamMessages(ctx context.Context, params anthropic.BetaMessageNe
 						"(total=%d): server=%q tool=%q input=%s tool_use_id=%q",
 						b.config.ID, total, call.server, call.name, call.input, currentTResultUseID)
 				}
+			case "server_tool_use":
+				InfoLogger.Printf("[web] %s id=%q input=%s",
+					currentServerToolName, currentServerToolID, currentInputJSON.String())
+			case "web_search_tool_result", "web_fetch_tool_result":
+				preview := currentServerResult
+				if len(preview) > 500 {
+					preview = preview[:500] + "...(truncated)"
+				}
+				InfoLogger.Printf("[web] %s content=%s", currentKind, preview)
 			case "thinking", "redacted_thinking":
 				if summary := strings.TrimSpace(currentThinking.String()); summary != "" {
 					if len(summary) > 500 {
@@ -296,7 +374,7 @@ func (b *Bot) streamMessages(ctx context.Context, params anthropic.BetaMessageNe
 				}
 			default:
 				if currentKind != "" {
-					InfoLogger.Printf("[mcp] block type=%q (unhandled)", currentKind)
+					InfoLogger.Printf("[stream] block type=%q (unhandled)", currentKind)
 				}
 			}
 			currentKind = ""
@@ -304,27 +382,21 @@ func (b *Bot) streamMessages(ctx context.Context, params anthropic.BetaMessageNe
 	}
 
 	if err := stream.Err(); err != nil {
-		return "", err
+		return "", message, err
 	}
 
-	if stopReason != "" || finalUsage.OutputTokens > 0 {
+	stopReason := string(message.StopReason)
-		inputTokens := finalUsage.InputTokens
+	if stopReason != "" || message.Usage.OutputTokens > 0 {
-		if inputTokens == 0 {
-			inputTokens = startInputTokens
-		}
 		InfoLogger.Printf("[usage] model=%s in=%d out=%d thinking=%d stop=%s",
-			params.Model, inputTokens, finalUsage.OutputTokens,
+			params.Model, message.Usage.InputTokens, message.Usage.OutputTokens,
-			finalUsage.OutputTokensDetails.ThinkingTokens, stopReason)
+			message.Usage.OutputTokensDetails.ThinkingTokens, stopReason)
-		if stopReason == "max_tokens" {
+		if message.StopReason == anthropic.BetaStopReasonMaxTokens {
 			ErrorLogger.Printf("[usage] response truncated at max_tokens=%d - raise max_tokens (thinking counts toward it)",
 				params.MaxTokens)
 		}
 	}
 
-	if len(allSegments) == 0 {
+	return strings.Join(allSegments, "\n\n"), message, nil
-		return "", emptyStreamError(stopReason, finalUsage.OutputTokensDetails.ThinkingTokens, params.MaxTokens)
-	}
-	return strings.Join(allSegments, "\n\n"), nil
 }
 
 func emptyStreamError(stopReason string, thinkingTokens, maxTokens int64) error {

anthropic_test.go

@@ -127,6 +127,90 @@ func TestBackwardCompatibleParams(t *testing.T) {
 	}
 }
 
+func TestWebSearchTools(t *testing.T) {
+	t.Run("nil config yields no tools", func(t *testing.T) {
+		if tools := webSearchTools(nil); tools != nil {
+			t.Errorf("webSearchTools(nil) = %v, want nil", tools)
+		}
+	})
+
+	t.Run("search only when fetch off", func(t *testing.T) {
+		tools := webSearchTools(&WebSearchConfig{
+			AllowedDomains: []string{"example.com/hc"},
+			MaxUses:        3,
+		})
+		if len(tools) != 1 {
+			t.Fatalf("got %d tools, want 1 (search only)", len(tools))
+		}
+		if tools[0].OfWebSearchTool20250305 == nil {
+			t.Fatalf("tools[0] is not a web_search tool")
+		}
+		if tools[0].OfWebFetchTool20250910 != nil {
+			t.Error("web_fetch tool present but fetch is off")
+		}
+	})
+
+	t.Run("search + fetch with allowlist and citations", func(t *testing.T) {
+		tools := webSearchTools(&WebSearchConfig{
+			AllowedDomains:   []string{"example.com/hc", "docs.example.com"},
+			MaxUses:          3,
+			Fetch:            true,
+			MaxContentTokens: 50000,
+		})
+		if len(tools) != 2 {
+			t.Fatalf("got %d tools, want 2 (search + fetch)", len(tools))
+		}
+
+		search := tools[0].OfWebSearchTool20250305
+		if search == nil {
+			t.Fatalf("tools[0] is not a web_search tool")
+		}
+		if len(search.AllowedDomains) != 2 {
+			t.Errorf("search AllowedDomains = %v, want 2 entries", search.AllowedDomains)
+		}
+		if search.MaxUses.Value != 3 {
+			t.Errorf("search MaxUses = %d, want 3", search.MaxUses.Value)
+		}
+
+		fetch := tools[1].OfWebFetchTool20250910
+		if fetch == nil {
+			t.Fatalf("tools[1] is not a web_fetch tool")
+		}
+		if len(fetch.AllowedDomains) != 2 {
+			t.Errorf("fetch AllowedDomains = %v, want 2 entries", fetch.AllowedDomains)
+		}
+		if fetch.MaxContentTokens.Value != 50000 {
+			t.Errorf("fetch MaxContentTokens = %d, want 50000", fetch.MaxContentTokens.Value)
+		}
+		if fetch.Citations.Enabled.Value != true {
+			t.Error("fetch citations not enabled")
+		}
+	})
+
+	t.Run("wire shape carries allowed_domains", func(t *testing.T) {
+		tools := webSearchTools(&WebSearchConfig{
+			AllowedDomains: []string{"thatgamecompany.helpshift.com/hc"},
+			MaxUses:        2,
+			Fetch:          true,
+		})
+		raw, err := json.Marshal(tools)
+		if err != nil {
+			t.Fatalf("marshal: %v", err)
+		}
+		body := string(raw)
+		for _, want := range []string{
+			"web_search_20250305",
+			"web_fetch_20250910",
+			"thatgamecompany.helpshift.com/hc",
+			"allowed_domains",
+		} {
+			if !strings.Contains(body, want) {
+				t.Errorf("wire body missing %q:\n%s", want, body)
+			}
+		}
+	})
+}
+
 func TestEmptyStreamError(t *testing.T) {
 	err := emptyStreamError("max_tokens", 3900, 4000)
 	for _, want := range []string{"output budget exhausted", "3900", "4000"} {

config.go

@@ -15,6 +15,14 @@ type MCPServer struct {
 	AllowedTools       []string `json:"allowed_tools,omitempty"`
 }
 
+type WebSearchConfig struct {
+	AllowedDomains   []string `json:"allowed_domains,omitempty"`
+	BlockedDomains   []string `json:"blocked_domains,omitempty"`
+	MaxUses          int      `json:"max_uses,omitempty"`
+	Fetch            bool     `json:"fetch,omitempty"`
+	MaxContentTokens int      `json:"max_content_tokens,omitempty"`
+}
+
 const (
 	ThinkingModeAdaptive      = "adaptive"
 	ThinkingModeDisabled      = "disabled"
@@ -43,6 +51,7 @@ type BotConfig struct {
 	ElevenLabsModel   string            `json:"elevenlabs_model"`
 	DebugScreening    bool              `json:"debug_screening"`
 	MCPServers        []MCPServer       `json:"mcp_servers,omitempty"`
+	WebSearch         *WebSearchConfig  `json:"web_search,omitempty"`
 	ConfigFilePath    string            `json:"-"`
 }
 
@@ -112,6 +121,11 @@ func loadAllConfigs(dir string) ([]BotConfig, error) {
 					config.ID, config.MaxTokens)
 			}
 
+			if ws := config.WebSearch; ws != nil && len(ws.AllowedDomains) == 0 && len(ws.BlockedDomains) == 0 {
+				InfoLogger.Printf("[%s] web_search enabled with no allowed_domains/blocked_domains: the model may search the open web",
+					config.ID)
+			}
+
 			config.ConfigFilePath = validPath
 			configs = append(configs, config)
 		}
@@ -168,6 +182,18 @@ func validateConfig(config *BotConfig, ids, tokens map[string]bool) error {
 		return fmt.Errorf("'max_tokens' must be greater than 0 when set")
 	}
 
+	if ws := config.WebSearch; ws != nil {
+		if len(ws.AllowedDomains) > 0 && len(ws.BlockedDomains) > 0 {
+			return fmt.Errorf("'web_search' cannot set both allowed_domains and blocked_domains (the API rejects that)")
+		}
+		if ws.MaxUses < 0 {
+			return fmt.Errorf("'web_search.max_uses' must be greater than 0 when set")
+		}
+		if ws.MaxContentTokens < 0 {
+			return fmt.Errorf("'web_search.max_content_tokens' must be greater than 0 when set")
+		}
+	}
+
 	if config.MessagePerHour <= 0 {
 		return fmt.Errorf("'messages_per_hour' must be greater than 0")
 	}

config_test.go

@@ -875,3 +875,84 @@ func TestThinkingConfigLoad(t *testing.T) {
 		t.Errorf("MaxTokens = %d, want 4096", cfg.MaxTokens)
 	}
 }
+
+func TestWebSearchConfig(t *testing.T) {
+	t.Run("absent leaves nil", func(t *testing.T) {
+		var cfg BotConfig
+		if err := json.Unmarshal([]byte(`{}`), &cfg); err != nil {
+			t.Fatalf("unmarshal: %v", err)
+		}
+		if cfg.WebSearch != nil {
+			t.Errorf("WebSearch = %+v, want nil when absent", cfg.WebSearch)
+		}
+	})
+
+	t.Run("loads allowlist", func(t *testing.T) {
+		jsonData := `{
+			"web_search": {
+				"allowed_domains": ["example.com/hc", "docs.example.com"],
+				"max_uses": 3,
+				"fetch": true,
+				"max_content_tokens": 50000
+			}
+		}`
+		var cfg BotConfig
+		if err := json.Unmarshal([]byte(jsonData), &cfg); err != nil {
+			t.Fatalf("unmarshal: %v", err)
+		}
+		if cfg.WebSearch == nil {
+			t.Fatalf("WebSearch = nil, want populated")
+		}
+		if len(cfg.WebSearch.AllowedDomains) != 2 {
+			t.Errorf("AllowedDomains = %v, want 2 entries", cfg.WebSearch.AllowedDomains)
+		}
+		if cfg.WebSearch.MaxUses != 3 {
+			t.Errorf("MaxUses = %d, want 3", cfg.WebSearch.MaxUses)
+		}
+		if !cfg.WebSearch.Fetch {
+			t.Error("Fetch = false, want true")
+		}
+		if cfg.WebSearch.MaxContentTokens != 50000 {
+			t.Errorf("MaxContentTokens = %d, want 50000", cfg.WebSearch.MaxContentTokens)
+		}
+	})
+
+	cases := []struct {
+		name    string
+		ws      *WebSearchConfig
+		wantErr string
+	}{
+		{"nil ok", nil, ""},
+		{"allowlist ok", &WebSearchConfig{AllowedDomains: []string{"example.com"}, MaxUses: 3}, ""},
+		{"blocklist ok", &WebSearchConfig{BlockedDomains: []string{"evil.com"}}, ""},
+		{"empty ok", &WebSearchConfig{}, ""},
+		{"both allow and block rejected",
+			&WebSearchConfig{AllowedDomains: []string{"a.com"}, BlockedDomains: []string{"b.com"}},
+			"cannot set both allowed_domains and blocked_domains"},
+		{"negative max_uses rejected",
+			&WebSearchConfig{AllowedDomains: []string{"a.com"}, MaxUses: -1},
+			"'web_search.max_uses' must be greater than 0"},
+		{"negative max_content_tokens rejected",
+			&WebSearchConfig{AllowedDomains: []string{"a.com"}, MaxContentTokens: -1},
+			"'web_search.max_content_tokens' must be greater than 0"},
+	}
+	for i, tc := range cases {
+		t.Run(tc.name, func(t *testing.T) {
+			cfg := thinkingTestConfig(fmt.Sprintf("bot-web-%d", i))
+			cfg.WebSearch = tc.ws
+			err := validateConfig(&cfg, map[string]bool{}, map[string]bool{})
+			if tc.wantErr == "" {
+				if err != nil {
+					t.Fatalf("validateConfig(web_search=%+v) = %v, want nil", tc.ws, err)
+				}
+				return
+			}
+			if err == nil {
+				t.Fatalf("validateConfig(web_search=%+v) = nil, want error containing %q", tc.ws, tc.wantErr)
+			}
+			if !contains(err.Error(), tc.wantErr) {
+				t.Errorf("error %q does not contain %q", err.Error(), tc.wantErr)
+			}
+		})
+	}
+}