fix(mcp): forward image tool results on the existing image channel

internal/acp/agent.go

@@ -11,6 +11,7 @@ import (
 
 	"github.com/Gitlawb/zero/internal/agent"
 	"github.com/Gitlawb/zero/internal/config"
+	"github.com/Gitlawb/zero/internal/modelregistry"
 	"github.com/Gitlawb/zero/internal/providercatalog"
 	"github.com/Gitlawb/zero/internal/providermodelcatalog"
 	"github.com/Gitlawb/zero/internal/providermodeldiscovery"
@@ -249,6 +250,13 @@ func (a *Agent) runTurn(ctx context.Context, sess *acpSession, userText string,
 	}
 	note := &notifier{conn: a.conn, sessionID: sess.id}
 
+	supportsVision := func(modelID string) bool {
+		return a.modelSupportsVision(ctx, resolved.Provider, modelID)
+	}
+	if len(images) > 0 && !supportsVision(resolved.Provider.Model) {
+		images = nil
+	}
+
 	opts := agent.Options{
 		Cwd:            sess.cwd,
 		SessionID:      sess.id,
@@ -259,6 +267,7 @@ func (a *Agent) runTurn(ctx context.Context, sess *acpSession, userText string,
 		PermissionMode: sess.currentMode(),
 		MaxTurns:       resolved.MaxTurns,
 		Images:         images,
+		SupportsVision: supportsVision,
 		OnText:         note.text,
 		OnReasoning:    note.thought,
 		OnToolCall:     note.toolCall,
@@ -767,3 +776,32 @@ func (s *acpSession) snapshotHistory() []turnRecord {
 	defer s.mu.Unlock()
 	return append([]turnRecord(nil), s.history...)
 }
+
+func (a *Agent) modelSupportsVision(ctx context.Context, profile config.ProviderProfile, modelID string) bool {
+	trimmed := strings.TrimSpace(modelID)
+	if trimmed == "" {
+		return false
+	}
+	reg, _ := modelregistry.DefaultRegistry()
+	if entry, known := reg.Resolve(trimmed); known {
+		return entry.Supports(modelregistry.ModelCapabilityVision)
+	}
+	if a.deps.DiscoverModels != nil {
+		if discovered, err := a.deps.DiscoverModels(ctx, profile); err == nil {
+			for _, dm := range discovered {
+				if strings.EqualFold(strings.TrimSpace(dm.ID), trimmed) {
+					if len(dm.InputModalities) > 0 {
+						for _, mod := range dm.InputModalities {
+							if strings.EqualFold(strings.TrimSpace(mod), "image") {
+								return true
+							}
+						}
+						return false
+					}
+					break
+				}
+			}
+		}
+	}
+	return modelregistry.SupportsVision(reg, trimmed)
+}

internal/acp/agent_test.go

@@ -497,6 +497,48 @@ func TestACPRunTurnWiresSandboxAndScopedRegistry(t *testing.T) {
 	}
 }
 
+func TestACPWiresSupportsVision(t *testing.T) {
+	deps := testDeps(t)
+	var captured agent.Options
+	deps.RunAgent = func(_ context.Context, _ string, _ zeroruntime.Provider, opts agent.Options) (agent.Result, error) {
+		captured = opts
+		return agent.Result{FinalAnswer: "done"}, nil
+	}
+	deps.DiscoverModels = func(_ context.Context, _ config.ProviderProfile) ([]providermodeldiscovery.Model, error) {
+		return []providermodeldiscovery.Model{
+			{ID: "custom-vision", InputModalities: []string{"text", "image"}},
+			{ID: "custom-text", InputModalities: []string{"text"}},
+		}, nil
+	}
+	h := newHarness(t, deps)
+	defer h.stop()
+	ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
+	defer cancel()
+
+	var newRes NewSessionResult
+	if err := h.client.Call(ctx, MethodSessionNew, NewSessionParams{Cwd: t.TempDir(), McpServers: []McpServer{}}, &newRes); err != nil {
+		t.Fatalf("session/new: %v", err)
+	}
+	var promptRes PromptResult
+	if err := h.client.Call(ctx, MethodSessionPrompt, PromptParams{
+		SessionID: newRes.SessionID,
+		Prompt: []ContentBlock{
+			{Type: "text", Text: "hello"},
+		},
+	}, &promptRes); err != nil {
+		t.Fatalf("session/prompt: %v", err)
+	}
+	if captured.SupportsVision == nil {
+		t.Fatal("SupportsVision was not wired into agent.Options")
+	}
+	if !captured.SupportsVision("custom-vision") {
+		t.Fatal("SupportsVision(custom-vision) = false, want true")
+	}
+	if captured.SupportsVision("custom-text") {
+		t.Fatal("SupportsVision(custom-text) = true, want false")
+	}
+}
+
 // TestACPRejectsInvalidCwd confirms session/new fails when the workspace root
 // resolver rejects the client cwd (e.g. filesystem root).
 func TestACPRejectsInvalidCwd(t *testing.T) {

internal/agent/loop.go

@@ -13,6 +13,7 @@ import (
 
 	"github.com/Gitlawb/zero/internal/execution"
 	"github.com/Gitlawb/zero/internal/hooks"
+	"github.com/Gitlawb/zero/internal/modelregistry"
 	"github.com/Gitlawb/zero/internal/redaction"
 	"github.com/Gitlawb/zero/internal/sandbox"
 	"github.com/Gitlawb/zero/internal/streamjson"
@@ -646,9 +647,25 @@ func Run(ctx context.Context, prompt string, provider Provider, options Options)
 		// recorded. They travel as user messages, and a user message between two
 		// tool_results breaks strict provider replay — Anthropic coalesces them
 		// into one user block list and requires the tool_result blocks first, so
-		// interleaving yields [tool_result, text, image, tool_result] and a 400.
-		// Same reason the self-correction feedback below is deferred.
-		var toolImageMessages []zeroruntime.Message
+		// Images ride a following USER message rather than the tool result
+		// above. Every provider drops images on a tool-role message —
+		// Anthropic's tool_result content is a string, Gemini's is a
+		// functionResponse, and OpenAI guards its image parts to the user role
+		// — so attaching them there would silently deliver nothing. A separate
+		// message also keeps the one-tool-result-per-tool-call pairing intact,
+		// which the providers validate. Vision-gate evaluation is deferred until
+		// after any model switch this turn resolves, so images can reach an
+		// escalated vision-capable model.
+		var toolResultsWithImages []ToolResult
+		buildToolImageMessages := func() []zeroruntime.Message {
+			var out []zeroruntime.Message
+			for _, tr := range toolResultsWithImages {
+				if imageMessage, ok := toolResultImageMessage(tr, options); ok {
+					out = append(out, imageMessage)
+				}
+			}
+			return out
+		}
 		// Parallel read-ahead state: results for calls[precomputedStart:precomputedEnd]
 		// executed concurrently, consumed strictly in order below.
 		var precomputed []precomputedToolResult
@@ -705,15 +722,8 @@ func Run(ctx context.Context, prompt string, provider Provider, options Options)
 				IsError:            toolResult.Status == tools.StatusError,
 				ChangedFiles:       append([]string(nil), toolResult.ChangedFiles...),
 			})
-			// Images ride a following USER message rather than the tool result
-			// above. Every provider drops images on a tool-role message —
-			// Anthropic's tool_result content is a string, Gemini's is a
-			// functionResponse, and OpenAI guards its image parts to the user role
-			// — so attaching them there would silently deliver nothing. A separate
-			// message also keeps the one-tool-result-per-tool-call pairing intact,
-			// which the providers validate.
-			if imageMessage, ok := toolResultImageMessage(toolResult); ok {
-				toolImageMessages = append(toolImageMessages, imageMessage)
+			if len(toolResult.Images) > 0 {
+				toolResultsWithImages = append(toolResultsWithImages, toolResult)
 			}
 
 			// A tool may demand the run ABORT — a canceled/timed-out ask_user prompt
@@ -725,13 +735,13 @@ func Run(ctx context.Context, prompt string, provider Provider, options Options)
 			}
 			if abortErr != nil {
 				messages = appendAbortedToolResults(messages, collected.ToolCalls[index+1:])
-				messages = append(messages, toolImageMessages...)
+				messages = append(messages, buildToolImageMessages()...)
 				result.Messages = copyMessages(messages)
 				return result, abortErr
 			}
 			if stopReason := stopReasonFromToolResult(toolResult); stopReason != "" {
 				messages = appendAbortedToolResults(messages, collected.ToolCalls[index+1:])
-				messages = append(messages, toolImageMessages...)
+				messages = append(messages, buildToolImageMessages()...)
 				result.FinalAnswer = toolResult.ModelOutput()
 				result.StopReason = stopReason
 				result.Messages = copyMessages(messages)
@@ -755,7 +765,7 @@ func Run(ctx context.Context, prompt string, provider Provider, options Options)
 				// messages stay valid for a strict provider replay (Anthropic
 				// rejects a tool_use with no answering tool_result).
 				messages = appendAbortedToolResults(messages, collected.ToolCalls[index+1:])
-				messages = append(messages, toolImageMessages...)
+				messages = append(messages, buildToolImageMessages()...)
 				result.FinalAnswer = toolFailureStopAnswer(call.Name, outcome.Count)
 				result.Messages = copyMessages(messages)
 				return result, nil
@@ -774,10 +784,6 @@ func Run(ctx context.Context, prompt string, provider Provider, options Options)
 				postEditDiagnostics.enqueue(ctx, toolResult.ChangedFiles)
 			}
 		}
-		// Every tool_result for this turn is now recorded, including aborted
-		// placeholders, so the images can follow without splitting them.
-		messages = append(messages, toolImageMessages...)
-		toolImageMessages = nil
 
 		// Run post-edit self-correction once over the union of files this turn
 		// changed, then append any feedback after every tool_result is recorded so
@@ -865,6 +871,12 @@ func Run(ctx context.Context, prompt string, provider Provider, options Options)
 			}
 		}
 
+		// Every tool_result, self-correct notice, and model-switch update for this
+		// turn is now in place; evaluate and append image messages against the
+		// effective (potentially escalated) model.
+		messages = append(messages, buildToolImageMessages()...)
+		toolResultsWithImages = nil
+
 		// A turn can mix valid tool calls with a dropped (nameless) one. The valid
 		// calls executed above; surface the dropped call too so it is never
 		// silently ignored just because the turn also did real work. This is
@@ -3457,8 +3469,10 @@ func copyMessages(messages []Message) []Message {
 //
 // The text names the tool so the model can tell which call an image came from
 // when several ran in one turn — the images arrive detached from their tool
-// result, so nothing else associates them.
-func toolResultImageMessage(result ToolResult) (zeroruntime.Message, bool) {
+// result, so nothing else associates them. If the effective model cannot
+// accept images, the tool's text result is left unchanged and this follow-up
+// is a notice with no image parts, matching the CLI/TUI vision gate.
+func toolResultImageMessage(result ToolResult, options Options) (zeroruntime.Message, bool) {
 	images := make([]zeroruntime.ImageBlock, 0, len(result.Images))
 	for _, image := range result.Images {
 		if len(image.Data) == 0 {
@@ -3479,9 +3493,26 @@ func toolResultImageMessage(result ToolResult) (zeroruntime.Message, bool) {
 	if label == "" {
 		label = "tool"
 	}
+	if !modelAcceptsToolImages(options) {
+		return zeroruntime.Message{
+			Role:    zeroruntime.MessageRoleUser,
+			Content: "Image output from " + label + " was not sent because the current model does not support image input.",
+		}, true
+	}
 	return zeroruntime.Message{
 		Role:    zeroruntime.MessageRoleUser,
 		Content: "Image output from " + label + ":",
 		Images:  images,
 	}, true
 }
+
+func modelAcceptsToolImages(options Options) bool {
+	if options.SupportsVision != nil {
+		return options.SupportsVision(options.Model)
+	}
+	registry, err := modelregistry.DefaultRegistry()
+	if err != nil {
+		return modelregistry.VisionCapableByName(options.Model)
+	}
+	return modelregistry.SupportsVision(registry, options.Model)
+}