fix(openai): handle Ollama reasoning stream deltas

docs/STREAM_JSON_PROTOCOL.md

@@ -41,6 +41,7 @@ events when present.
 
 ```json
 { "schemaVersion": 2, "type": "run_start", "runId": "run_20260603_abc123", "sessionId": "zero_20260603100000_abc123", "cwd": "/repo", "provider": "openai", "model": "gpt-4.1", "apiModel": "gpt-4.1" }
+{ "schemaVersion": 2, "type": "reasoning", "runId": "run_20260603_abc123", "delta": "Thinking..." }
 { "schemaVersion": 2, "type": "text", "runId": "run_20260603_abc123", "delta": "..." }
 { "schemaVersion": 2, "type": "tool_call", "runId": "run_20260603_abc123", "id": "call_1", "name": "read_file", "args": { "path": "README.md" }, "sideEffect": "read" }
 { "schemaVersion": 2, "type": "permission_request", "runId": "run_20260603_abc123", "id": "call_2", "name": "write_file", "action": "prompt", "permission": "prompt", "permissionMode": "ask", "sideEffect": "write", "reason": "Creates or overwrites files." }
@@ -51,6 +52,10 @@ events when present.
 { "schemaVersion": 2, "type": "run_end", "runId": "run_20260603_abc123", "status": "success", "exitCode": 0 }
 ```
 
+`reasoning` events carry live model reasoning/status deltas for providers that
+stream them separately from answer text. They are liveness/progress events only:
+they are not folded into `text` or the final answer.
+
 Permission events may include structured sandbox metadata:
 
 ```json

internal/agent/guardrails.go

@@ -414,8 +414,9 @@ func (state *guardState) observeToolResult(name string, failed bool, output stri
 func (state *guardState) observeTurn(collected zeroruntime.CollectedStream) (stop bool) {
 	hasToolCalls := len(collected.ToolCalls) > 0
 	hasVisibleText := strings.TrimSpace(collected.Text) != ""
+	hasReasoning := collected.HasReasoning || len(collected.ReasoningBlocks) > 0
 
-	if hasToolCalls || hasVisibleText {
+	if hasToolCalls || hasVisibleText || hasReasoning {
 		state.emptyTurns = 0
 	} else {
 		state.emptyTurns++

internal/agent/guardrails_test.go

@@ -22,6 +22,14 @@ func textTurn(content string) []zeroruntime.StreamEvent {
 	}
 }
 
+// reasoningTurn produces live reasoning without visible assistant text.
+func reasoningTurn(content string) []zeroruntime.StreamEvent {
+	return []zeroruntime.StreamEvent{
+		{Type: zeroruntime.StreamEventReasoning, Content: content},
+		{Type: zeroruntime.StreamEventDone},
+	}
+}
+
 // toolTurn produces a turn that calls a named tool with the given args JSON.
 func toolTurn(callID string, toolName string, args string) []zeroruntime.StreamEvent {
 	return []zeroruntime.StreamEvent{
@@ -101,6 +109,31 @@ func TestRunResetsEmptyTurnCounterOnVisibleOutput(t *testing.T) {
 	}
 }
 
+func TestRunResetsEmptyTurnCounterOnReasoning(t *testing.T) {
+	provider := &mockProvider{
+		turns: [][]zeroruntime.StreamEvent{
+			reasoningTurn("thinking 1"),
+			reasoningTurn("thinking 2"),
+			reasoningTurn("thinking 3"),
+			textTurn("done"),
+		},
+	}
+
+	result, err := Run(context.Background(), "go", provider, Options{
+		Registry: tools.NewRegistry(),
+		MaxTurns: 12,
+	})
+	if err != nil {
+		t.Fatal(err)
+	}
+	if result.FinalAnswer != "done" {
+		t.Fatalf("expected reasoning-only turns to keep the run live until final answer, got %q", result.FinalAnswer)
+	}
+	if len(provider.requests) != 4 {
+		t.Fatalf("expected 4 turns, got %d", len(provider.requests))
+	}
+}
+
 func TestRunResetsEmptyTurnCounterOnToolCall(t *testing.T) {
 	root := t.TempDir()
 	writeAgentTestFile(t, root+"/notes.txt", "alpha")

internal/cli/exec.go

@@ -535,6 +535,7 @@ func runExec(args []string, stdout io.Writer, stderr io.Writer, deps appDeps) in
 		EnabledTools:            options.enabledTools,
 		DisabledTools:           options.disabledTools,
 		OnText:                  writer.text,
+		OnReasoning:             writer.reasoning,
 		OnToolCall: func(call agent.ToolCall) {
 			writer.toolCall(call, registry)
 			sessionRecorder.append(sessions.EventToolCall, map[string]any{

internal/cli/exec_protocol_test.go

@@ -529,6 +529,45 @@ func TestRunExecStreamJSONRunStartUsesResolvedAPIModel(t *testing.T) {
 	}
 }
 
+func TestRunExecStreamJSONEmitsReasoningEvents(t *testing.T) {
+	t.Setenv("XDG_DATA_HOME", t.TempDir())
+	cwd := t.TempDir()
+	var stdout bytes.Buffer
+	var stderr bytes.Buffer
+
+	exitCode := runWithDeps([]string{"exec", "--output-format", "stream-json", "think then answer"}, &stdout, &stderr, appDeps{
+		getwd: func() (string, error) {
+			return cwd, nil
+		},
+		resolveConfig: func(_ string, _ config.Overrides) (config.ResolvedConfig, error) {
+			return execResolvedConfig(), nil
+		},
+		newProvider: func(config.ProviderProfile) (zeroruntime.Provider, error) {
+			return reasoningExecProvider{}, nil
+		},
+	})
+
+	if exitCode != exitSuccess {
+		t.Fatalf("expected exit code %d, got %d: %s", exitSuccess, exitCode, stderr.String())
+	}
+	events := decodeJSONLines(t, stdout.String())
+	reasoningIdx, reasoning := findJSONEventIndex(t, events, "reasoning")
+	if reasoning["delta"] != "Thinking. " {
+		t.Fatalf("unexpected reasoning event: %#v", reasoning)
+	}
+	textIdx, text := findJSONEventIndex(t, events, "text")
+	if text["delta"] != "done" {
+		t.Fatalf("unexpected text event: %#v", text)
+	}
+	if reasoningIdx >= textIdx {
+		t.Fatalf("expected reasoning event before text event, got indices %d and %d", reasoningIdx, textIdx)
+	}
+	final := findJSONEvent(t, events, "final")
+	if final["text"] != "done" {
+		t.Fatalf("reasoning must not be folded into final answer: %#v", final)
+	}
+}
+
 func TestExecEventWriterTruncatesStreamJSONToolResults(t *testing.T) {
 	var stdout bytes.Buffer
 	writer := execEventWriter{
@@ -751,6 +790,17 @@ type toolCallingExecProvider struct {
 	answer     string
 }
 
+type reasoningExecProvider struct{}
+
+func (reasoningExecProvider) StreamCompletion(context.Context, zeroruntime.CompletionRequest) (<-chan zeroruntime.StreamEvent, error) {
+	ch := make(chan zeroruntime.StreamEvent, 3)
+	ch <- zeroruntime.StreamEvent{Type: zeroruntime.StreamEventReasoning, Content: "Thinking. "}
+	ch <- zeroruntime.StreamEvent{Type: zeroruntime.StreamEventText, Content: "done"}
+	ch <- zeroruntime.StreamEvent{Type: zeroruntime.StreamEventDone}
+	close(ch)
+	return ch, nil
+}
+
 func (provider toolCallingExecProvider) StreamCompletion(ctx context.Context, request zeroruntime.CompletionRequest) (<-chan zeroruntime.StreamEvent, error) {
 	for _, message := range request.Messages {
 		if message.Role == zeroruntime.MessageRoleTool {
@@ -777,13 +827,19 @@ func (provider toolCallingExecProvider) StreamCompletion(ctx context.Context, re
 
 func findJSONEvent(t *testing.T, events []map[string]any, eventType string) map[string]any {
 	t.Helper()
-	for _, event := range events {
+	_, event := findJSONEventIndex(t, events, eventType)
+	return event
+}
+
+func findJSONEventIndex(t *testing.T, events []map[string]any, eventType string) (int, map[string]any) {
+	t.Helper()
+	for idx, event := range events {
 		if event["type"] == eventType {
-			return event
+			return idx, event
 		}
 	}
 	t.Fatalf("event %q not found in %#v", eventType, events)
-	return nil
+	return -1, nil
 }
 
 func findSessionEvent(t *testing.T, events []sessions.Event, eventType sessions.EventType) sessions.Event {

internal/cli/exec_writer.go

@@ -80,6 +80,16 @@ func (writer *execEventWriter) text(delta string) {
 	writer.writeStdout(delta)
 }
 
+func (writer *execEventWriter) reasoning(delta string) {
+	if writer.format == execOutputJSON {
+		writer.writeJSON(map[string]any{"type": "reasoning", "delta": delta})
+		return
+	}
+	if writer.format == execOutputStreamJSON {
+		writer.writeStreamJSON(streamjson.Event{Type: streamjson.EventReasoning, RunID: writer.runID, Delta: delta})
+	}
+}
+
 func (writer *execEventWriter) toolCall(call agent.ToolCall, registry *tools.Registry) {
 	if writer.format == execOutputJSON {
 		writer.writeJSON(map[string]any{

internal/providers/openai/provider.go

@@ -283,10 +283,10 @@ func (provider *Provider) emitChunk(
 	events chan<- zeroruntime.StreamEvent,
 ) {
 	for _, choice := range chunk.Choices {
-		if choice.Delta.ReasoningContent != "" {
+		if reasoning := choice.Delta.reasoningText(); reasoning != "" {
 			sendEvent(ctx, events, zeroruntime.StreamEvent{
 				Type:    zeroruntime.StreamEventReasoning,
-				Content: choice.Delta.ReasoningContent,
+				Content: reasoning,
 			})
 		}
 		if choice.Delta.Content != "" {
@@ -317,6 +317,13 @@ func (provider *Provider) emitChunk(
 	}
 }
 
+func (delta streamDelta) reasoningText() string {
+	if delta.ReasoningContent != "" {
+		return delta.ReasoningContent
+	}
+	return delta.Reasoning
+}
+
 // mapFinishReason maps OpenAI's finish_reason onto the runtime's normalized
 // terminal reasons. A normal finish ("stop"/"tool_calls"/"") returns "".
 func mapFinishReason(reason string) string {

internal/providers/openai/provider_test.go

@@ -227,6 +227,39 @@ func TestStreamCompletionEmitsReasoningContentDeltas(t *testing.T) {
 	}
 }
 
+func TestStreamCompletionEmitsReasoningAliasDeltas(t *testing.T) {
+	provider := newTestProvider(t, func(w http.ResponseWriter, r *http.Request) {
+		writeSSE(w, `{"choices":[{"delta":{"reasoning":"Thinking. "}}]}`)
+		writeSSE(w, `{"choices":[{"delta":{"reasoning":"Answering now."}}]}`)
+		writeSSE(w, `[DONE]`)
+	})
+
+	events := collectProviderEvents(t, provider)
+	reasoning := eventsOfType(events, zeroruntime.StreamEventReasoning)
+	if len(reasoning) != 2 {
+		t.Fatalf("reasoning events = %#v, want two reasoning deltas", reasoning)
+	}
+	if reasoning[0].Content != "Thinking. " || reasoning[1].Content != "Answering now." {
+		t.Fatalf("unexpected reasoning events: %#v", reasoning)
+	}
+	if text := eventsOfType(events, zeroruntime.StreamEventText); len(text) != 0 {
+		t.Fatalf("reasoning must not emit text events, got %#v", text)
+	}
+}
+
+func TestStreamCompletionPrefersReasoningContentOverAlias(t *testing.T) {
+	provider := newTestProvider(t, func(w http.ResponseWriter, r *http.Request) {
+		writeSSE(w, `{"choices":[{"delta":{"reasoning_content":"standard","reasoning":"alias"}}]}`)
+		writeSSE(w, `[DONE]`)
+	})
+
+	events := collectProviderEvents(t, provider)
+	reasoning := eventsOfType(events, zeroruntime.StreamEventReasoning)
+	if len(reasoning) != 1 || reasoning[0].Content != "standard" {
+		t.Fatalf("reasoning events = %#v, want standard reasoning_content", reasoning)
+	}
+}
+
 func TestStreamCompletionEmitsReasoningBeforeRegularContent(t *testing.T) {
 	provider := newTestProvider(t, func(w http.ResponseWriter, r *http.Request) {
 		writeSSE(w, `{"choices":[{"delta":{"reasoning_content":"Thinking. ","content":"Answer."}}]}`)

internal/providers/openai/types.go

@@ -78,6 +78,7 @@ type streamChoice struct {
 type streamDelta struct {
 	Content          string                `json:"content"`
 	ReasoningContent string                `json:"reasoning_content"`
+	Reasoning        string                `json:"reasoning"`
 	ToolCalls        []streamToolCallDelta `json:"tool_calls"`
 }
 

internal/streamjson/streamjson.go

@@ -21,6 +21,7 @@ type EventType string
 const (
 	EventRunStart           EventType = "run_start"
 	EventText               EventType = "text"
+	EventReasoning          EventType = "reasoning"
 	EventToolCall           EventType = "tool_call"
 	EventPermission         EventType = "permission"
 	EventPermissionRequest  EventType = "permission_request"

internal/zeroruntime/helpers.go

@@ -21,6 +21,9 @@ type CollectedStream struct {
 	// thinking blocks) that must be replayed on the next turn. Empty for providers
 	// or runs without extended thinking.
 	ReasoningBlocks []ReasoningBlock
+	// HasReasoning records whether the provider streamed reasoning deltas. The
+	// deltas remain non-answer content, but they still prove the turn was live.
+	HasReasoning bool
 }
 
 // Truncated reports whether the response ended for a non-normal reason (the
@@ -132,6 +135,9 @@ func CollectStreamWithOptions(ctx context.Context, events <-chan StreamEvent, op
 					options.OnText(event.Content)
 				}
 			case StreamEventReasoning:
+				if strings.TrimSpace(event.Content) != "" {
+					collected.HasReasoning = true
+				}
 				if options.OnReasoning != nil {
 					options.OnReasoning(event.Content)
 				}

internal/zeroruntime/provider_test.go

@@ -312,6 +312,9 @@ func TestCollectStreamWithOptionsEmitsTextReasoningAndUsageCallbacks(t *testing.
 	if collected.Text != "Hello zero" {
 		t.Fatalf("text = %q, want Hello zero", collected.Text)
 	}
+	if !collected.HasReasoning {
+		t.Fatal("expected reasoning stream to mark collected turn as reasoning-bearing")
+	}
 	if len(textDeltas) != 2 || textDeltas[0] != "Hello " || textDeltas[1] != "zero" {
 		t.Fatalf("unexpected text callbacks: %#v", textDeltas)
 	}