Trim eager read tool schemas

internal/agent/compaction.go

@@ -38,9 +38,8 @@ const compactionTriggerRatio = 0.7
 // transcript (and so tests can assert on it).
 const summaryLabel = "[Summary of earlier conversation]"
 
-// CompactionSummaryInstructions is the system prompt handed to both automatic
-// and manually requested compaction summarizers.
-const CompactionSummaryInstructions = "You are compacting a coding-assistant conversation to save context. " +
+// summaryInstructions is the system prompt handed to the summarizer model.
+const summaryInstructions = "You are compacting a coding-assistant conversation to save context. " +
 	"Write a dense, factual summary of the conversation so far. Preserve: the user's goals and explicit constraints; " +
 	"decisions made and why; files created or modified (with paths) and key code changes; commands run and their important " +
 	"results; and anything still in progress or unresolved. Omit pleasantries. Use terse bullet points. Do not invent details. " +
@@ -76,12 +75,6 @@ type CompactionResult struct {
 	// summary message also includes summaryLabel and any preserved structured
 	// state needed by later compactions.
 	SummaryText string
-	// ProjectedChars is the text content sent to the summarizer after semantic
-	// projection, excluding provider protocol framing.
-	ProjectedChars int
-	// Truncated reports whether projection dropped content to satisfy its
-	// bounded brief or previous-summary limits.
-	Truncated bool
 	// Compacted reports whether Messages contains an injected summary.
 	Compacted bool
 }
@@ -223,11 +216,11 @@ func CompactMessages(messages []zeroruntime.Message, opts CompactionOptions) (Co
 		}, nil
 	}
 
-	summaryResult, err := SummarizeCompactionMessages(middle, opts.Summarize)
+	summary, err := opts.Summarize(middle)
 	if err != nil {
 		return CompactionResult{}, err
 	}
-	summary := summaryResult.SummaryText
+	summary = strings.TrimSpace(summary)
 
 	// Preserve structured state (active plan + loaded skills) from the elided
 	// middle verbatim, so it is not lost or paraphrased away by the prose summary.
@@ -245,53 +238,10 @@ func CompactMessages(messages []zeroruntime.Message, opts CompactionOptions) (Co
 		RemovedCount:   len(middle),
 		PreservedCount: len(messages) - len(middle),
 		SummaryText:    summary,
-		ProjectedChars: summaryResult.ProjectedChars,
-		Truncated:      summaryResult.Truncated,
 		Compacted:      true,
 	}, nil
 }
 
-// CompactionSummaryResult describes the shared summarization input and output.
-type CompactionSummaryResult struct {
-	SummaryText    string
-	ProjectedChars int
-	Truncated      bool
-}
-
-// SummarizeCompactionMessages applies the shared semantic projection before
-// invoking a caller-supplied summarizer. Automatic context-pressure compaction
-// and manual session compaction both use this path.
-func SummarizeCompactionMessages(messages []zeroruntime.Message, summarize func([]zeroruntime.Message) (string, error)) (CompactionSummaryResult, error) {
-	if summarize == nil {
-		return CompactionSummaryResult{}, errors.New("compaction requires a Summarize function")
-	}
-	projection := projectCompactionInput(messages)
-	summaryInput := projection.messages
-	if len(summaryInput) == 0 {
-		summaryInput = messages
-	}
-	summary, err := summarize(summaryInput)
-	if err != nil {
-		return CompactionSummaryResult{}, err
-	}
-	return CompactionSummaryResult{
-		SummaryText:    strings.TrimSpace(summary),
-		ProjectedChars: compactionMessageChars(summaryInput),
-		Truncated:      projection.truncated,
-	}, nil
-}
-
-func compactionMessageChars(messages []zeroruntime.Message) int {
-	total := 0
-	for _, message := range messages {
-		total += len(message.Content)
-		for _, call := range message.ToolCalls {
-			total += len(call.Name) + len(call.Arguments)
-		}
-	}
-	return total
-}
-
 // safeSuffixBoundary walks the preserve boundary backward (toward systemEnd) so
 // the preserved suffix begins on a user or assistant message rather than a
 // tool/tool_result message. A tool result with no preceding assistant tool call
@@ -381,8 +331,6 @@ type compactionState struct {
 	// but its token COST must still be counted so usage reports and budgets include it.
 	onUsage func(Usage)
 	task    *taskState
-	planner *contextPlanner
-	trace   *trace.Recorder
 
 	// calibrationRatio scales the raw byte/4 token estimate toward the provider's
 	// real prompt-token count. ApproxTextTokens over-counts code-heavy content by
@@ -429,8 +377,6 @@ func newCompactionState(options Options, task *taskState) *compactionState {
 		preserveLast: options.CompactionPreserveLast,
 		onUsage:      options.OnUsage,
 		task:         task,
-		planner:      newContextPlanner(contextPlannerConfig{contextWindow: options.ContextWindow}),
-		trace:        options.Trace,
 	}
 	return state
 }
@@ -486,7 +432,7 @@ func (state *compactionState) maybeCompact(
 
 	compacted, err := Compact(messages, CompactionOptions{
 		PreserveLast: state.preserveLast,
-		Summarize:    state.summarizeClosure(ctx, provider),
+		Summarize:    summarizeClosure(ctx, provider, state.onUsage),
 		taskState:    state.task.snapshotForCompaction(messages),
 	})
 	if err != nil {
@@ -537,7 +483,7 @@ func (state *compactionState) recover(
 
 	result, compactErr := Compact(messages, CompactionOptions{
 		PreserveLast: state.preserveLast,
-		Summarize:    state.summarizeClosure(ctx, provider),
+		Summarize:    summarizeClosure(ctx, provider, state.onUsage),
 		taskState:    state.task.snapshotForCompaction(messages),
 	})
 	if compactErr != nil {
@@ -571,12 +517,9 @@ func (state *compactionState) recover(
 // provider call. The summary stream intentionally does NOT forward OnText (so
 // compaction stays invisible on the user-facing surface), but it DOES forward
 // OnUsage so the summarizer's token cost is still counted by usage/budgeting.
-func (state *compactionState) summarizeClosure(ctx context.Context, provider Provider) func([]zeroruntime.Message) (string, error) {
-	if state.planner == nil {
-		state.planner = newContextPlanner(contextPlannerConfig{})
-	}
+func summarizeClosure(ctx context.Context, provider Provider, onUsage func(Usage)) func([]zeroruntime.Message) (string, error) {
 	return func(toSummarize []zeroruntime.Message) (string, error) {
-		return summarizeWithPlanner(ctx, provider, toSummarize, state.onUsage, state.planner, state.trace)
+		return summarizeWithFallback(ctx, provider, toSummarize, onUsage)
 	}
 }
 
@@ -588,11 +531,7 @@ func (state *compactionState) summarizeClosure(ctx context.Context, provider Pro
 // Non-context-limit errors (and a single message that still won't fit) surface
 // to the caller unchanged.
 func summarizeWithFallback(ctx context.Context, provider Provider, messages []zeroruntime.Message, onUsage func(Usage)) (string, error) {
-	return summarizeWithPlanner(ctx, provider, messages, onUsage, newContextPlanner(contextPlannerConfig{}), nil)
-}
-
-func summarizeWithPlanner(ctx context.Context, provider Provider, messages []zeroruntime.Message, onUsage func(Usage), planner *contextPlanner, recorder *trace.Recorder) (string, error) {
-	summary, err := summarizeMessagesOnce(ctx, provider, messages, onUsage, planner, recorder)
+	summary, err := summarizeMessagesOnce(ctx, provider, messages, onUsage)
 	if err == nil {
 		return summary, nil
 	}
@@ -601,11 +540,11 @@ func summarizeWithPlanner(ctx context.Context, provider Provider, messages []zer
 	}
 
 	mid := len(messages) / 2
-	left, leftErr := summarizeWithPlanner(ctx, provider, messages[:mid], onUsage, planner, recorder)
+	left, leftErr := summarizeWithFallback(ctx, provider, messages[:mid], onUsage)
 	if leftErr != nil {
 		return "", leftErr
 	}
-	right, rightErr := summarizeWithPlanner(ctx, provider, messages[mid:], onUsage, planner, recorder)
+	right, rightErr := summarizeWithFallback(ctx, provider, messages[mid:], onUsage)
 	if rightErr != nil {
 		return "", rightErr
 	}
@@ -618,7 +557,7 @@ func summarizeWithPlanner(ctx context.Context, provider Provider, messages []zer
 	combined := strings.TrimSpace(left + "\n\n" + right)
 	reduced, reduceErr := summarizeMessagesOnce(ctx, provider, []zeroruntime.Message{
 		{Role: zeroruntime.MessageRoleUser, Content: combined},
-	}, onUsage, planner, recorder)
+	}, onUsage)
 	if reduceErr != nil {
 		if isContextLimitError(reduceErr.Error()) {
 			// Even the two combined partials don't fit (extreme): fall back to the
@@ -634,15 +573,15 @@ func summarizeWithPlanner(ctx context.Context, provider Provider, messages []zer
 }
 
 // summarizeMessagesOnce performs a single tool-less summarization call.
-func summarizeMessagesOnce(ctx context.Context, provider Provider, messages []zeroruntime.Message, onUsage func(Usage), planner *contextPlanner, recorder *trace.Recorder) (string, error) {
-	requestMessages := []zeroruntime.Message{
-		{Role: zeroruntime.MessageRoleSystem, Content: CompactionSummaryInstructions},
-		{Role: zeroruntime.MessageRoleUser, Content: "Summarize this conversation:\n\n" + renderTranscript(messages)},
+func summarizeMessagesOnce(ctx context.Context, provider Provider, messages []zeroruntime.Message, onUsage func(Usage)) (string, error) {
+	request := zeroruntime.CompletionRequest{
+		Messages: []zeroruntime.Message{
+			{Role: zeroruntime.MessageRoleSystem, Content: summaryInstructions},
+			{Role: zeroruntime.MessageRoleUser, Content: "Summarize this conversation:\n\n" + renderTranscript(messages)},
+		},
+		// No tools: this is a plain text summarization call.
 	}
-	parts := systemPromptParts{prompt: CompactionSummaryInstructions, baseInstructions: CompactionSummaryInstructions}
-	plan := planner.planWithPromptParts(requestMessages, nil, "", parts)
-	recordContextPlanTrace(recorder, plan)
-	stream, err := provider.StreamCompletion(ctx, plan.Request)
+	stream, err := provider.StreamCompletion(ctx, request)
 	if err != nil {
 		return "", err
 	}

internal/agent/compaction_metadata_test.go

@@ -43,14 +43,8 @@ func TestCompactMessagesReturnsMetadataForManualCompaction(t *testing.T) {
 	if result.SummaryText != "manual summary" {
 		t.Fatalf("SummaryText = %q, want trimmed summary", result.SummaryText)
 	}
-	if result.ProjectedChars != compactionMessageChars(captured) || result.ProjectedChars == 0 {
-		t.Fatalf("ProjectedChars = %d, want %d", result.ProjectedChars, compactionMessageChars(captured))
-	}
-	if result.Truncated {
-		t.Fatal("Truncated = true for a projection within its limits")
-	}
-	if len(captured) != 1 || !strings.Contains(captured[0].Content, "first question") || !strings.Contains(captured[0].Content, "second question") {
-		t.Fatalf("summarized projection = %#v, want intent from the non-preserved middle", captured)
+	if len(captured) != 3 || captured[0].Content != "first question" || captured[2].Content != "second question" {
+		t.Fatalf("summarized middle = %#v, want the three non-preserved non-system messages", captured)
 	}
 	if len(result.Messages) != 4 {
 		t.Fatalf("compacted message count = %d, want 4", len(result.Messages))
@@ -102,46 +96,11 @@ func TestCompactMessagesNoopReturnsUncompactedMetadata(t *testing.T) {
 	if result.SummaryText != "" {
 		t.Fatalf("SummaryText = %q, want empty", result.SummaryText)
 	}
-	if result.ProjectedChars != 0 || result.Truncated {
-		t.Fatalf("no-op projection metadata = (%d, %t), want zero values", result.ProjectedChars, result.Truncated)
-	}
 	if !reflect.DeepEqual(result.Messages, messages) {
 		t.Fatalf("Messages changed on no-op: %#v", result.Messages)
 	}
 }
 
-func TestCompactMessagesReturnsTruncatedProjectionMetadata(t *testing.T) {
-	messages := []zeroruntime.Message{{Role: zeroruntime.MessageRoleSystem, Content: "system"}}
-	for index := range 20 {
-		messages = append(messages, zeroruntime.Message{
-			Role:    zeroruntime.MessageRoleUser,
-			Content: strings.Repeat("contextword ", 256) + string(rune('a'+index)),
-		})
-	}
-	messages = append(messages,
-		zeroruntime.Message{Role: zeroruntime.MessageRoleAssistant, Content: "recent answer"},
-		zeroruntime.Message{Role: zeroruntime.MessageRoleUser, Content: "latest question"},
-	)
-
-	var captured []zeroruntime.Message
-	result, err := CompactMessages(messages, CompactionOptions{
-		PreserveLast: 2,
-		Summarize: func(toSummarize []zeroruntime.Message) (string, error) {
-			captured = append([]zeroruntime.Message(nil), toSummarize...)
-			return "bounded summary", nil
-		},
-	})
-	if err != nil {
-		t.Fatal(err)
-	}
-	if !result.Compacted || !result.Truncated {
-		t.Fatalf("compaction metadata = compacted %t, truncated %t; want both true", result.Compacted, result.Truncated)
-	}
-	if result.ProjectedChars != compactionMessageChars(captured) || result.ProjectedChars == 0 {
-		t.Fatalf("ProjectedChars = %d, want %d", result.ProjectedChars, compactionMessageChars(captured))
-	}
-}
-
 func TestCompactMessagesPropagatesSummarizeError(t *testing.T) {
 	messages := []zeroruntime.Message{
 		{Role: zeroruntime.MessageRoleSystem, Content: "system"},

internal/agent/compaction_preserve.go

@@ -102,7 +102,7 @@ type skillEntry struct {
 	body string
 }
 
-// recentEdits returns files mutated by editing calls in messages
+// recentEdits returns the files mutated by write_file/edit_file calls in messages
 // — latest note per path, in last-seen order — as skillEntry{name: path, body:
 // note}. After compaction elides the editing turns, this tells the model WHAT it
 // changed in each file (from the tool's result) so it need not re-read to
@@ -113,7 +113,6 @@ type skillEntry struct {
 // rather than an earlier, now-stale entry.
 func recentEdits(messages []zeroruntime.Message) []skillEntry {
 	pathByID := map[string]string{}
-	noteByPath := map[string]string{}
 	sequence := make([]string, 0)
 	for _, message := range messages {
 		for _, call := range message.ToolCalls {
@@ -130,24 +129,12 @@ func recentEdits(messages []zeroruntime.Message) []skillEntry {
 			sequence = append(sequence, path)
 		}
 	}
-	for _, message := range messages {
-		if message.Role != zeroruntime.MessageRoleTool || len(message.ChangedFiles) == 0 {
-			continue
-		}
-		for _, path := range message.ChangedFiles {
-			path = strings.TrimSpace(path)
-			if path == "" {
-				continue
-			}
-			sequence = append(sequence, path)
-			noteByPath[path] = editNote(message.Content)
-		}
-	}
 	order := lastSeenOrder(sequence)
 	if len(order) == 0 {
 		return nil
 	}
 
+	noteByPath := map[string]string{}
 	for _, message := range messages {
 		if message.Role != zeroruntime.MessageRoleTool || message.ToolCallID == "" {
 			continue
@@ -438,20 +425,15 @@ type preservedState struct {
 }
 
 type preservedTaskState struct {
-	Objective           string              `json:"objective"`
-	Status              taskStatus          `json:"status,omitempty"`
-	Pending             int                 `json:"pending,omitempty"`
-	InProgress          int                 `json:"in_progress,omitempty"`
-	Completed           int                 `json:"completed,omitempty"`
-	Failed              int                 `json:"failed,omitempty"`
-	VerificationPassed  int                 `json:"verification_passed,omitempty"`
-	VerificationFailed  int                 `json:"verification_failed,omitempty"`
-	VerificationOutcome Outcome             `json:"verification_outcome,omitempty"`
-	Constraints         []string            `json:"constraints,omitempty"`
-	ChangedFiles        []string            `json:"changed_files,omitempty"`
-	UnresolvedFailures  []taskFailureState  `json:"unresolved_failures,omitempty"`
-	Approvals           []taskApprovalState `json:"approvals,omitempty"`
-	Artifacts           []taskArtifactState `json:"artifacts,omitempty"`
+	Objective           string     `json:"objective"`
+	Status              taskStatus `json:"status,omitempty"`
+	Pending             int        `json:"pending,omitempty"`
+	InProgress          int        `json:"in_progress,omitempty"`
+	Completed           int        `json:"completed,omitempty"`
+	Failed              int        `json:"failed,omitempty"`
+	VerificationPassed  int        `json:"verification_passed,omitempty"`
+	VerificationFailed  int        `json:"verification_failed,omitempty"`
+	VerificationOutcome Outcome    `json:"verification_outcome,omitempty"`
 }
 
 type preservedEdit struct {
@@ -486,12 +468,7 @@ func appendPreservedState(summary string, middle []zeroruntime.Message, taskSnap
 	task := priorState.Task
 	if taskSnapshot != nil {
 		task = &preservedTaskState{
-			Objective:          capTaskObjective(taskSnapshot.Objective),
-			Constraints:        mergeBoundedComparable(priorTaskConstraints(priorState.Task), taskSnapshot.Constraints, maxTaskConstraints),
-			ChangedFiles:       mergeBoundedComparable(priorTaskChangedFiles(priorState.Task), taskSnapshot.ChangedFiles, maxTaskEvidenceEntries),
-			UnresolvedFailures: mergeTaskFailures(priorTaskFailures(priorState.Task), taskSnapshot.UnresolvedFailures, taskSnapshot.ResolvedFailureKeys),
-			Approvals:          mergeBoundedComparable(priorTaskApprovals(priorState.Task), taskSnapshot.Approvals, maxTaskEvidenceEntries),
-			Artifacts:          mergeBoundedComparable(priorTaskArtifacts(priorState.Task), taskSnapshot.Artifacts, maxTaskEvidenceEntries),
+			Objective: capTaskObjective(taskSnapshot.Objective),
 		}
 		// Plan parity corroborates only the mutable task projection. The objective
 		// comes directly from the run prompt and is immutable, so it must survive
@@ -507,13 +484,6 @@ func appendPreservedState(summary string, middle []zeroruntime.Message, taskSnap
 			task.VerificationOutcome = taskSnapshot.Verification.LastOutcome
 		}
 	}
-	freshConstraints := explicitConstraintsFromMessages(middle)
-	if len(freshConstraints) > 0 {
-		if task == nil {
-			task = &preservedTaskState{}
-		}
-		task.Constraints = mergeBoundedComparable(task.Constraints, freshConstraints, maxTaskConstraints)
-	}
 
 	// Plan: a fresh update_plan in middle is authoritative; otherwise carry the
 	// plan preserved by an earlier compaction.
@@ -547,95 +517,6 @@ func appendPreservedState(summary string, middle []zeroruntime.Message, taskSnap
 	return summary
 }
 
-func explicitConstraintsFromMessages(messages []zeroruntime.Message) []string {
-	var constraints []string
-	for _, message := range messages {
-		if message.Role != zeroruntime.MessageRoleUser || strings.Contains(message.Content, preservedStateLabel) {
-			continue
-		}
-		if _, body := projectInstructionBlock(message.Content); body != "" {
-			continue
-		}
-		constraints = mergeBoundedComparable(constraints, extractExplicitConstraints(message.Content), maxTaskConstraints)
-	}
-	return constraints
-}
-
-func priorTaskConstraints(task *preservedTaskState) []string {
-	if task == nil {
-		return nil
-	}
-	return task.Constraints
-}
-
-func priorTaskChangedFiles(task *preservedTaskState) []string {
-	if task == nil {
-		return nil
-	}
-	return task.ChangedFiles
-}
-
-func priorTaskFailures(task *preservedTaskState) []taskFailureState {
-	if task == nil {
-		return nil
-	}
-	return task.UnresolvedFailures
-}
-
-func priorTaskApprovals(task *preservedTaskState) []taskApprovalState {
-	if task == nil {
-		return nil
-	}
-	return task.Approvals
-}
-
-func priorTaskArtifacts(task *preservedTaskState) []taskArtifactState {
-	if task == nil {
-		return nil
-	}
-	return task.Artifacts
-}
-
-func mergeTaskFailures(older, newer []taskFailureState, resolved []string) []taskFailureState {
-	resolvedSet := make(map[string]struct{}, len(resolved))
-	for _, key := range resolved {
-		resolvedSet[key] = struct{}{}
-	}
-	merged := make([]taskFailureState, 0, len(older)+len(newer))
-	for _, failure := range append(append([]taskFailureState(nil), older...), newer...) {
-		if _, ok := resolvedSet[failure.Key]; ok {
-			continue
-		}
-		withoutSameKey := make([]taskFailureState, 0, len(merged))
-		for _, existing := range merged {
-			if existing.Key != failure.Key {
-				withoutSameKey = append(withoutSameKey, existing)
-			}
-		}
-		merged = append(withoutSameKey, failure)
-	}
-	if len(merged) > maxTaskEvidenceEntries {
-		merged = merged[len(merged)-maxTaskEvidenceEntries:]
-	}
-	return merged
-}
-
-func mergeBoundedComparable[T comparable](older, newer []T, limit int) []T {
-	merged := make([]T, 0, len(older)+len(newer))
-	seen := make(map[T]struct{}, len(older)+len(newer))
-	for _, value := range append(append([]T(nil), older...), newer...) {
-		if _, ok := seen[value]; ok {
-			continue
-		}
-		seen[value] = struct{}{}
-		merged = append(merged, value)
-	}
-	if len(merged) > limit {
-		merged = merged[len(merged)-limit:]
-	}
-	return merged
-}
-
 func capTaskObjective(objective string) string {
 	objective = strings.TrimSpace(objective)
 	if len(objective) <= maxTaskObjectiveBytes {

internal/agent/compaction_preserve_test.go

@@ -6,7 +6,6 @@ import (
 	"testing"
 	"unicode/utf8"
 
-	"github.com/Gitlawb/zero/internal/tools"
 	"github.com/Gitlawb/zero/internal/zeroruntime"
 )
 
@@ -65,9 +64,6 @@ func TestCompactPreservesBoundedTaskContext(t *testing.T) {
 	objective := strings.Repeat("世", maxTaskObjectiveBytes)
 	task := newTaskState(objective, nil)
 	task.observe(taskStateEvent{kind: taskStateEventPlan, arguments: `{"plan":[{"content":"write code","status":"in_progress"},{"content":"add tests","status":"pending"}]}`})
-	task.observe(taskStateEvent{kind: taskStateEventToolResult, arguments: `{"patch":"*** Update File: internal/db.go"}`, toolResult: ToolResult{
-		Name: "apply_patch", Status: tools.StatusOK, Output: "Done!", ChangedFiles: []string{"internal/db.go"},
-	}})
 	messages := stateConversation()
 	compacted, err := Compact(messages, CompactionOptions{
 		PreserveLast: 2,
@@ -84,69 +80,6 @@ func TestCompactPreservesBoundedTaskContext(t *testing.T) {
 	if len(state.Task.Objective) > maxTaskObjectiveBytes || !utf8.ValidString(state.Task.Objective) {
 		t.Fatalf("objective was not safely bounded: %d bytes %q", len(state.Task.Objective), state.Task.Objective)
 	}
-	if len(state.Task.ChangedFiles) != 1 || state.Task.ChangedFiles[0] != "internal/db.go" {
-		t.Fatalf("changed files were not preserved: %#v", state.Task.ChangedFiles)
-	}
-}
-
-func TestCompactPreservesRuntimeEvidenceAcrossRepeatedCompaction(t *testing.T) {
-	task := newTaskState("Please keep the change focused.", nil)
-	task.observe(taskStateEvent{kind: taskStateEventToolResult, arguments: `{"cmd":"go test ./..."}`, toolResult: ToolResult{
-		Name: "exec_command", Status: tools.StatusError, Output: "Error: tests failed",
-		Meta: map[string]string{"spill_path": ".zero/artifacts/tests.txt"},
-	}})
-	task.observe(taskStateEvent{kind: taskStateEventPermission, permission: PermissionEvent{
-		ToolName: "exec_command", DecisionAction: PermissionDecisionAllowForSession, Scope: "/tmp",
-	}})
-	messages := stateConversation()
-
-	first, err := Compact(messages, CompactionOptions{
-		PreserveLast: 2,
-		Summarize:    func([]zeroruntime.Message) (string, error) { return "FIRST", nil },
-		taskState:    task.snapshotForCompaction(messages),
-	})
-	if err != nil {
-		t.Fatal(err)
-	}
-	task.observe(taskStateEvent{kind: taskStateEventToolResult, arguments: `{"cmd":"go test ./..."}`, toolResult: ToolResult{
-		Name: "exec_command", Status: tools.StatusError, Output: "Error: tests still fail with newer evidence",
-		Meta: map[string]string{"spill_path": ".zero/artifacts/tests.txt"},
-	}})
-	secondInput := append(append([]zeroruntime.Message{}, first...),
-		zeroruntime.Message{Role: zeroruntime.MessageRoleUser, Content: "Never add background memory models."},
-		zeroruntime.Message{Role: zeroruntime.MessageRoleAssistant, Content: "understood"},
-		zeroruntime.Message{Role: zeroruntime.MessageRoleUser, Content: "continue"},
-		zeroruntime.Message{Role: zeroruntime.MessageRoleAssistant, Content: "working"},
-	)
-	second, err := Compact(secondInput, CompactionOptions{
-		PreserveLast: 2,
-		Summarize:    func([]zeroruntime.Message) (string, error) { return "SECOND", nil },
-		taskState:    task.snapshotForCompaction(secondInput),
-	})
-	if err != nil {
-		t.Fatal(err)
-	}
-	state := parsePreservedStateBlock(second[1].Content)
-	if state.Task == nil || len(state.Task.UnresolvedFailures) != 1 || len(state.Task.Approvals) != 1 || len(state.Task.Artifacts) != 1 {
-		t.Fatalf("runtime evidence did not survive repeated compaction: %#v", state.Task)
-	}
-	if got := state.Task.UnresolvedFailures[0].Summary; got != "Error: tests still fail with newer evidence" {
-		t.Fatalf("newer failure evidence did not replace the older summary: %#v", state.Task.UnresolvedFailures)
-	}
-	for _, want := range []string{"Please keep the change focused.", "Never add background memory models."} {
-		if !containsString(state.Task.Constraints, want) {
-			t.Fatalf("constraint %q missing after repeated compaction: %#v", want, state.Task.Constraints)
-		}
-	}
-}
-
-func containsString(values []string, want string) bool {
-	for _, value := range values {
-		if value == want {
-			return true
-		}
-	}
-	return false
 }
 
 func TestCompactPreservesObjectiveAfterPlanParityMismatch(t *testing.T) {

internal/agent/compaction_projection.go

@@ -1,315 +0,0 @@
-package agent
-
-import (
-	"encoding/json"
-	"fmt"
-	"regexp"
-	"strings"
-
-	"github.com/Gitlawb/zero/internal/zeroruntime"
-)
-
-const (
-	compactionUserWordBudget       = 256
-	compactionAssistantWordBudget  = 200
-	compactionToolCallsPerTurn     = 8
-	compactionToolArgumentBytes    = 120
-	compactionErrorBytes           = 150
-	compactionResultBytes          = 1200
-	compactionPreviousSummaryBytes = 16 * 1024
-	compactionBriefMaxBytes        = 24 * 1024
-)
-
-var compactionWordPattern = regexp.MustCompile(`[\p{L}\p{N}]+`)
-
-type compactionProjection struct {
-	messages  []zeroruntime.Message
-	truncated bool
-}
-
-// projectCompactionInput removes reconstructible tool output before the model
-// summary call. It retains a bounded transcript of user intent, assistant
-// decisions, tool actions, and concise errors. Exact durable state is appended
-// separately from the original messages after the summary returns.
-func projectCompactionInput(messages []zeroruntime.Message) compactionProjection {
-	sections := make([]string, 0, len(messages))
-	previousSummary := ""
-	truncated := false
-	for index, message := range messages {
-		switch message.Role {
-		case zeroruntime.MessageRoleUser:
-			content := message.Content
-			if marker := strings.Index(content, preservedStateLabel); marker >= 0 {
-				content = content[:marker]
-			}
-			trimmed := strings.TrimSpace(content)
-			if strings.HasPrefix(trimmed, summaryLabel) {
-				fullSummary := strings.TrimSpace(strings.TrimPrefix(trimmed, summaryLabel))
-				previousSummary = clipHeadTailBytes(fullSummary, compactionPreviousSummaryBytes)
-				truncated = truncated || len(fullSummary) > compactionPreviousSummaryBytes
-				continue
-			}
-			if content = clipInformativeWords(content, compactionUserWordBudget); content != "" {
-				sections = append(sections, fmt.Sprintf("[user #%d]\n%s", index, content))
-			}
-		case zeroruntime.MessageRoleAssistant:
-			lines := make([]string, 0, 1+len(message.ToolCalls))
-			if content := clipInformativeWords(message.Content, compactionAssistantWordBudget); content != "" {
-				lines = append(lines, content)
-			}
-			calls := message.ToolCalls
-			omitted := 0
-			if len(calls) > compactionToolCallsPerTurn {
-				omitted = len(calls) - compactionToolCallsPerTurn
-				calls = calls[omitted:]
-			}
-			if omitted > 0 {
-				lines = append(lines, fmt.Sprintf("* (%d earlier tool calls omitted)", omitted))
-			}
-			for _, call := range calls {
-				lines = append(lines, compactionToolCallLine(call))
-			}
-			if len(lines) > 0 {
-				sections = append(sections, fmt.Sprintf("[assistant #%d]\n%s", index, strings.Join(lines, "\n")))
-			}
-		case zeroruntime.MessageRoleTool:
-			// New tool-result messages carry the execution status directly, as the
-			// source ToolResult does. Keep the text check for older session history
-			// created before Message exposed IsError.
-			name := toolNameForResult(messages, index)
-			mustPreserve := name == "ask_user" || len(message.ChangedFiles) > 0
-			if !mustPreserve && !message.IsError && !isLikelyToolError(message.Content) {
-				continue
-			}
-			if name == "" {
-				name = "tool"
-			}
-			switch {
-			case message.IsError || isLikelyToolError(message.Content):
-				sections = append(sections, fmt.Sprintf("[tool_error #%d] %s\n%s", index, name, clipBytes(firstLine(message.Content), compactionErrorBytes)))
-			case name == "ask_user":
-				sections = append(sections, fmt.Sprintf("[user_answer #%d] %s\n%s", index, name, clipBytes(message.Content, compactionResultBytes)))
-			default:
-				sections = append(sections, fmt.Sprintf("[tool_result #%d] %s changed %s\n%s", index, name,
-					clipBytes(strings.Join(message.ChangedFiles, ", "), compactionToolArgumentBytes), clipBytes(firstLine(message.Content), compactionErrorBytes)))
-			}
-		}
-	}
-	if len(sections) == 0 && previousSummary == "" {
-		return compactionProjection{}
-	}
-	brief, briefTruncated := capCompactionBrief(strings.Join(sections, "\n\n"))
-	truncated = truncated || briefTruncated
-	if previousSummary != "" {
-		brief = "[previous summary]\n" + previousSummary + "\n\n" + brief
-	}
-	return compactionProjection{
-		messages:  []zeroruntime.Message{{Role: zeroruntime.MessageRoleUser, Content: strings.TrimSpace(brief)}},
-		truncated: truncated,
-	}
-}
-
-func capCompactionBrief(brief string) (string, bool) {
-	if len(brief) <= compactionBriefMaxBytes {
-		return brief, false
-	}
-	marker := "\n\n...[middle transcript omitted to fit compaction budget]...\n\n"
-	available := compactionBriefMaxBytes - len(marker)
-	// Keep both chronological edges: the oldest material has not necessarily
-	// been summarized before, while the newest material is most actionable.
-	headBytes := available * 2 / 5
-	tailBytes := available - headBytes
-	head := clipPrefixAtBoundary(brief, headBytes)
-	tail := clipSuffixAtBoundary(brief, tailBytes)
-	return strings.TrimSpace(head) + marker + strings.TrimSpace(tail), true
-}
-
-func compactionToolCallLine(call zeroruntime.ToolCall) string {
-	detail := ""
-	var arguments map[string]any
-	if json.Unmarshal([]byte(strings.TrimSpace(call.Arguments)), &arguments) == nil {
-		for _, key := range []string{"file_path", "path", "url", "query", "pattern", "prompt", "description", "question"} {
-			if value, ok := arguments[key].(string); ok && strings.TrimSpace(value) != "" {
-				detail = value
-				break
-			}
-		}
-		if detail == "" && call.Name == "ask_user" {
-			detail = askUserQuestionsDetail(arguments)
-		}
-		if detail == "" && call.Name == "apply_patch" {
-			if patch, ok := arguments["patch"].(string); ok {
-				detail = strings.Join(patchPaths(patch), ", ")
-			}
-		}
-	}
-	if detail == "" {
-		detail = commandFromArguments(call.Arguments)
-	}
-	if detail == "" {
-		return "* " + call.Name
-	}
-	return fmt.Sprintf("* %s %q", call.Name, clipBytes(detail, compactionToolArgumentBytes))
-}
-
-func isLikelyToolError(content string) bool {
-	prefix := strings.TrimSpace(content)
-	if len(prefix) > compactionErrorBytes {
-		prefix = prefix[:compactionErrorBytes]
-	}
-	lower := strings.ToLower(prefix)
-	for _, prefix := range []string{"error:", "tool error:", "failed:", "permission denied", "command failed"} {
-		if strings.HasPrefix(lower, prefix) {
-			return true
-		}
-	}
-	return false
-}
-
-func clipInformativeWords(text string, limit int) string {
-	flat := strings.Join(strings.Fields(text), " ")
-	if flat == "" || limit <= 0 {
-		return ""
-	}
-	count := 0
-	for _, location := range compactionWordPattern.FindAllStringIndex(flat, -1) {
-		word := strings.ToLower(flat[location[0]:location[1]])
-		if compactionStopWords[word] {
-			continue
-		}
-		count++
-		if count > limit {
-			end := location[0]
-			return strings.TrimSpace(flat[:end]) + "...(truncated)"
-		}
-	}
-	return flat
-}
-
-func clipBytes(text string, limit int) string {
-	text = strings.TrimSpace(text)
-	if limit <= 0 {
-		return ""
-	}
-	if len(text) <= limit {
-		return text
-	}
-	if limit <= 3 {
-		end := limit
-		for end > 0 && end < len(text) && text[end]&0xc0 == 0x80 {
-			end--
-		}
-		return text[:end]
-	}
-	end := limit - 3
-	for end > 0 && end < len(text) && text[end]&0xc0 == 0x80 {
-		end--
-	}
-	return strings.TrimSpace(text[:end]) + "..."
-}
-
-func clipHeadTailBytes(text string, limit int) string {
-	text = strings.TrimSpace(text)
-	if len(text) <= limit {
-		return text
-	}
-	if limit <= 0 {
-		return ""
-	}
-	marker := "\n...[middle omitted]...\n"
-	if limit <= len(marker) {
-		return clipBytes(text, limit)
-	}
-	available := limit - len(marker)
-	head := clipPrefixAtBoundary(text, available/2)
-	tail := clipSuffixAtBoundary(text, available-available/2)
-	return strings.TrimSpace(head) + marker + strings.TrimSpace(tail)
-}
-
-func clipPrefixAtBoundary(text string, limit int) string {
-	if limit <= 0 {
-		return ""
-	}
-	if len(text) <= limit {
-		return text
-	}
-	end := limit
-	for end > 0 && text[end]&0xc0 == 0x80 {
-		end--
-	}
-	if boundary := strings.LastIndex(text[:end], "\n\n["); boundary > 0 {
-		end = boundary
-	}
-	return text[:end]
-}
-
-func clipSuffixAtBoundary(text string, limit int) string {
-	if limit <= 0 {
-		return ""
-	}
-	if len(text) <= limit {
-		return text
-	}
-	start := len(text) - limit
-	for start < len(text) && text[start]&0xc0 == 0x80 {
-		start++
-	}
-	if boundary := strings.Index(text[start:], "\n\n["); boundary >= 0 {
-		start += boundary + 2
-	}
-	return text[start:]
-}
-
-func askUserQuestionsDetail(arguments map[string]any) string {
-	raw, ok := arguments["questions"].([]any)
-	if !ok {
-		return ""
-	}
-	questions := make([]string, 0, len(raw))
-	for _, item := range raw {
-		object, ok := item.(map[string]any)
-		if !ok {
-			continue
-		}
-		if question, ok := object["question"].(string); ok && strings.TrimSpace(question) != "" {
-			questions = append(questions, strings.TrimSpace(question))
-		}
-	}
-	return strings.Join(questions, " | ")
-}
-
-func patchPaths(patch string) []string {
-	var paths []string
-	seen := map[string]bool{}
-	for _, line := range strings.Split(patch, "\n") {
-		for _, prefix := range []string{"*** Add File: ", "*** Update File: ", "*** Delete File: ", "*** Move to: "} {
-			if !strings.HasPrefix(line, prefix) {
-				continue
-			}
-			path := strings.TrimSpace(strings.TrimPrefix(line, prefix))
-			if path != "" && !seen[path] {
-				seen[path] = true
-				paths = append(paths, path)
-			}
-		}
-	}
-	return paths
-}
-
-var compactionStopWords = map[string]bool{
-	"a": true, "an": true, "the": true, "is": true, "are": true, "was": true, "were": true,
-	"be": true, "been": true, "being": true, "have": true, "has": true, "had": true,
-	"do": true, "does": true, "did": true, "will": true, "would": true, "could": true,
-	"should": true, "may": true, "might": true, "shall": true, "can": true, "need": true, "must": true,
-	"to": true, "of": true, "in": true, "for": true, "on": true, "with": true, "at": true,
-	"by": true, "from": true, "as": true, "into": true, "through": true, "during": true,
-	"before": true, "after": true, "above": true, "below": true, "between": true, "under": true, "over": true,
-	"and": true, "but": true, "or": true, "nor": true, "not": true, "so": true, "yet": true,
-	"both": true, "either": true, "neither": true, "each": true, "every": true, "all": true,
-	"any": true, "few": true, "more": true, "most": true, "other": true, "some": true, "such": true, "no": true,
-	"that": true, "this": true, "these": true, "those": true, "it": true, "its": true,
-	"i": true, "me": true, "my": true, "we": true, "our": true, "you": true, "your": true,
-	"he": true, "him": true, "his": true, "she": true, "her": true, "they": true, "them": true, "their": true,
-	"who": true, "which": true, "what": true, "if": true, "then": true, "than": true,
-	"when": true, "where": true, "how": true, "just": true, "also": true,
-}

internal/agent/compaction_projection_test.go

@@ -1,130 +0,0 @@
-package agent
-
-import (
-	"strings"
-	"testing"
-	"unicode/utf8"
-
-	"github.com/Gitlawb/zero/internal/zeroruntime"
-)
-
-func TestClipBytesHandlesTinyLimitsOnRuneBoundaries(t *testing.T) {
-	for _, limit := range []int{0, 1, 2, 3} {
-		if clipped := clipBytes("世界", limit); len(clipped) > limit || !utf8.ValidString(clipped) {
-			t.Fatalf("clipBytes limit %d returned invalid result %q", limit, clipped)
-		}
-	}
-}
-
-func TestBoundaryClippersHandleNonPositiveLimits(t *testing.T) {
-	for _, clip := range []func(string, int) string{clipPrefixAtBoundary, clipSuffixAtBoundary} {
-		for _, limit := range []int{-1, 0} {
-			if got := clip("世界", limit); got != "" {
-				t.Fatalf("clipper limit %d = %q, want empty", limit, got)
-			}
-		}
-	}
-}
-
-func TestProjectCompactionInputDropsRecoverableToolBodies(t *testing.T) {
-	largeBody := strings.Repeat("recoverable source line\n", 1000)
-	messages := []zeroruntime.Message{
-		{Role: zeroruntime.MessageRoleUser, Content: "Inspect the parser and preserve its current behavior."},
-		{Role: zeroruntime.MessageRoleAssistant, Content: "I will inspect before editing.", ToolCalls: []zeroruntime.ToolCall{{ID: "read", Name: "read_file", Arguments: `{"path":"internal/parser.go"}`}}},
-		{Role: zeroruntime.MessageRoleTool, ToolCallID: "read", Content: largeBody},
-		{Role: zeroruntime.MessageRoleAssistant, ToolCalls: []zeroruntime.ToolCall{{ID: "test", Name: "exec_command", Arguments: `{"cmd":"go test ./internal/parser"}`}}},
-		{Role: zeroruntime.MessageRoleTool, ToolCallID: "test", Content: "Error: parser regression\nlong diagnostic details"},
-	}
-
-	projection := projectCompactionInput(messages)
-	projected := projection.messages
-	if len(projected) != 1 {
-		t.Fatalf("projection = %#v, want one compact message", projected)
-	}
-	content := projected[0].Content
-	for _, want := range []string{"Inspect the parser", `read_file "internal/parser.go"`, `exec_command "go test ./internal/parser"`, "Error: parser regression"} {
-		if !strings.Contains(content, want) {
-			t.Fatalf("projection missing %q: %q", want, content)
-		}
-	}
-	if strings.Contains(content, "recoverable source line") || strings.Contains(content, "long diagnostic details") {
-		t.Fatalf("projection retained reconstructible or overlong tool output: %q", content)
-	}
-	if estimateTokens(projected)*20 >= estimateTokens(messages) {
-		t.Fatalf("projection did not materially reduce tokens: before=%d after=%d", estimateTokens(messages), estimateTokens(projected))
-	}
-}
-
-func TestProjectCompactionInputRetainsStructurallyMarkedToolErrors(t *testing.T) {
-	messages := []zeroruntime.Message{
-		{Role: zeroruntime.MessageRoleAssistant, ToolCalls: []zeroruntime.ToolCall{{ID: "git", Name: "exec_command", Arguments: `{"cmd":"git status"}`}}},
-		{Role: zeroruntime.MessageRoleTool, ToolCallID: "git", Content: "fatal: not a git repository", IsError: true},
-	}
-
-	projected := projectCompactionInput(messages).messages
-	if len(projected) != 1 || !strings.Contains(projected[0].Content, "fatal: not a git repository") {
-		t.Fatalf("structured tool error was dropped from projection: %#v", projected)
-	}
-}
-
-func TestProjectCompactionInputRetainsAskUserExchangeAndSemanticArguments(t *testing.T) {
-	messages := []zeroruntime.Message{
-		{Role: zeroruntime.MessageRoleAssistant, ToolCalls: []zeroruntime.ToolCall{{ID: "ask", Name: "ask_user", Arguments: `{"questions":[{"question":"Which database should remain?"}]}`}}},
-		{Role: zeroruntime.MessageRoleTool, ToolCallID: "ask", Content: "Which database should remain?: Postgres only; do not touch MySQL."},
-		{Role: zeroruntime.MessageRoleAssistant, ToolCalls: []zeroruntime.ToolCall{
-			{ID: "patch", Name: "apply_patch", Arguments: `{"patch":"*** Begin Patch\n*** Update File: internal/db.go\n*** End Patch"}`},
-			{ID: "fetch", Name: "web_fetch", Arguments: `{"url":"https://example.com/spec"}`},
-			{ID: "task", Name: "task", Arguments: `{"prompt":"Inspect the Windows implementation"}`},
-		}},
-		{Role: zeroruntime.MessageRoleTool, ToolCallID: "patch", Content: "Done!", ChangedFiles: []string{"internal/db.go"}},
-	}
-
-	content := projectCompactionInput(messages).messages[0].Content
-	for _, want := range []string{"Which database should remain?", "Postgres only; do not touch MySQL", "internal/db.go", "https://example.com/spec", "Inspect the Windows implementation"} {
-		if !strings.Contains(content, want) {
-			t.Fatalf("projection missing %q: %q", want, content)
-		}
-	}
-}
-
-func TestProjectCompactionInputCapsToolCallsPerTurn(t *testing.T) {
-	calls := make([]zeroruntime.ToolCall, 12)
-	for index := range calls {
-		calls[index] = zeroruntime.ToolCall{Name: "read_file", Arguments: `{"path":"file.go"}`}
-	}
-	projected := projectCompactionInput([]zeroruntime.Message{{Role: zeroruntime.MessageRoleAssistant, ToolCalls: calls}}).messages
-	content := projected[0].Content
-	if strings.Count(content, "* read_file") != compactionToolCallsPerTurn || !strings.Contains(content, "4 earlier tool calls omitted") {
-		t.Fatalf("tool-call tail was not bounded: %q", content)
-	}
-}
-
-func TestProjectCompactionInputCarriesPreviousSummaryOutsideBriefCap(t *testing.T) {
-	previous := "keep the earlier architecture decision\n" + strings.Repeat("prior detail ", 2000) + "\nkeep the newest prior decision"
-	messages := []zeroruntime.Message{{Role: zeroruntime.MessageRoleUser, Content: summaryLabel + "\n" + previous + "\n\n" + preservedStateLabel + "\n{}"}}
-	for index := range 500 {
-		messages = append(messages, zeroruntime.Message{Role: zeroruntime.MessageRoleAssistant, Content: strings.Repeat("later transcript detail ", 20)})
-		messages = append(messages, zeroruntime.Message{Role: zeroruntime.MessageRoleUser, Content: "later request " + strings.Repeat("context ", 20) + string(rune('a'+index%26))})
-	}
-
-	projection := projectCompactionInput(messages)
-	content := projection.messages[0].Content
-	if !strings.Contains(content, "[previous summary]\nkeep the earlier architecture decision") || !strings.Contains(content, "keep the newest prior decision") {
-		t.Fatalf("previous summary was lost when the brief tail was capped: %q", content)
-	}
-	if !strings.Contains(content, "middle transcript omitted to fit compaction budget") {
-		t.Fatalf("oversized brief was not head/tail capped: %q", content)
-	}
-	if !projection.truncated {
-		t.Fatal("projection did not structurally report truncation")
-	}
-}
-
-func TestProjectCompactionInputDoesNotInferTruncationFromUserText(t *testing.T) {
-	projection := projectCompactionInput([]zeroruntime.Message{{
-		Role: zeroruntime.MessageRoleUser, Content: "Keep this literal marker: [middle omitted]",
-	}})
-	if projection.truncated {
-		t.Fatal("literal user text produced a false truncation signal")
-	}
-}

internal/agent/compaction_recent_edits_test.go

@@ -20,15 +20,11 @@ func TestRecentEditsExtractsPathsAndNotes(t *testing.T) {
 			{ID: "e2", Name: "edit_file", Arguments: `{"path":"internal/bar.go","old_string":"a","new_string":"b"}`},
 		}},
 		{Role: zeroruntime.MessageRoleTool, ToolCallID: "e2", Content: "Applied edit to internal/bar.go"},
-		{Role: zeroruntime.MessageRoleAssistant, ToolCalls: []zeroruntime.ToolCall{
-			{ID: "e3", Name: "apply_patch", Arguments: `{"patch":"*** Update File: internal/baz.go"}`},
-		}},
-		{Role: zeroruntime.MessageRoleTool, ToolCallID: "e3", Content: "Done!", ChangedFiles: []string{"internal/baz.go"}},
 	}
 
 	edits := recentEdits(messages)
-	if len(edits) != 3 {
-		t.Fatalf("expected 3 edited files, got %d: %#v", len(edits), edits)
+	if len(edits) != 2 {
+		t.Fatalf("expected 2 edited files, got %d: %#v", len(edits), edits)
 	}
 	if edits[0].name != "internal/foo.go" || !strings.Contains(edits[0].body, "12 lines") {
 		t.Fatalf("first edit = %#v, want foo.go with its note", edits[0])
@@ -36,9 +32,6 @@ func TestRecentEditsExtractsPathsAndNotes(t *testing.T) {
 	if edits[1].name != "internal/bar.go" || !strings.Contains(edits[1].body, "Applied edit") {
 		t.Fatalf("second edit = %#v, want bar.go with its note", edits[1])
 	}
-	if edits[2].name != "internal/baz.go" || edits[2].body != "Done!" {
-		t.Fatalf("third edit = %#v, want apply_patch changed file with its note", edits[2])
-	}
 }
 
 // After compaction elides the editing turns, the preserved-state block still

internal/agent/compaction_test.go

@@ -7,7 +7,6 @@ import (
 	"testing"
 
 	"github.com/Gitlawb/zero/internal/tools"
-	"github.com/Gitlawb/zero/internal/trace"
 	"github.com/Gitlawb/zero/internal/zeroruntime"
 )
 
@@ -59,15 +58,12 @@ func TestCompactKeepsSystemAndPreservedSuffix(t *testing.T) {
 	if last.Content != "most recent question" {
 		t.Fatalf("expected most recent message preserved, got %q", last.Content)
 	}
-	// The summarizer receives a compact semantic projection of the middle rather
-	// than reconstructible raw tool output.
-	if len(captured) != 1 || captured[0].Role != zeroruntime.MessageRoleUser {
-		t.Fatalf("expected one projected summary input, got %#v", captured)
+	// The summarized middle excludes system and preserved suffix.
+	if len(captured) != 3 {
+		t.Fatalf("expected 3 summarized messages, got %d: %#v", len(captured), captured)
 	}
-	for _, want := range []string{"[user #0]", "first question", "[assistant #1]", "first answer", "second question"} {
-		if !strings.Contains(captured[0].Content, want) {
-			t.Fatalf("projected summary input missing %q: %q", want, captured[0].Content)
-		}
+	if captured[0].Content != "first question" {
+		t.Fatalf("expected oldest non-system message first, got %#v", captured[0])
 	}
 	// Compaction must shrink the conversation.
 	if estimateTokens(result) >= estimateTokens(messages) {
@@ -429,7 +425,6 @@ type reactiveProvider struct {
 	summarizeCalls int
 	turnRequests   int
 	failedOnce     bool
-	connectError   bool
 	bigText        string
 	finalText      string
 }
@@ -451,9 +446,6 @@ func (provider *reactiveProvider) StreamCompletion(ctx context.Context, request
 		return streamEvents(toolTurnWithText(provider.bigText, "1", "read_file", `{"path":"x"}`)), nil
 	case provider.turnRequests == 2 && !provider.failedOnce:
 		provider.failedOnce = true
-		if provider.connectError {
-			return nil, errors.New("context_length_exceeded")
-		}
 		return streamEvents([]zeroruntime.StreamEvent{
 			{Type: zeroruntime.StreamEventError, Error: "This model's maximum context length is 1000 tokens. Please reduce the length of the messages."},
 		}), nil
@@ -462,39 +454,6 @@ func (provider *reactiveProvider) StreamCompletion(ctx context.Context, request
 	}
 }
 
-func TestRunConnectErrorCompactionRecordsReplacementPlan(t *testing.T) {
-	provider := &reactiveProvider{
-		connectError: true,
-		bigText:      strings.Repeat("b", 6000),
-		finalText:    "recovered",
-	}
-	registry := tools.NewRegistry()
-	registry.Register(tools.NewScopedReadFileTool(t.TempDir(), nil))
-	recorder := trace.NewRecorder("connect-compaction", "run-1", "test")
-	var contextPlans []ContextBreakdown
-
-	result, err := Run(context.Background(), strings.Repeat("z", 6000), provider, Options{
-		Registry:               registry,
-		PermissionMode:         PermissionModeUnsafe,
-		ContextWindow:          10_000_000,
-		CompactionPreserveLast: 2,
-		Trace:                  recorder,
-		OnContext: func(breakdown ContextBreakdown) {
-			contextPlans = append(contextPlans, breakdown)
-		},
-	})
-	if err != nil || result.FinalAnswer != "recovered" {
-		t.Fatalf("connect-error compaction failed: result=%#v err=%v", result, err)
-	}
-	if len(contextPlans) != 3 || contextPlans[2].MessageTokens >= contextPlans[1].MessageTokens {
-		t.Fatalf("replacement request context not reported: %#v", contextPlans)
-	}
-	gotTrace := recorder.Finish()
-	if len(gotTrace.PrefixHashes) != 4 || gotTrace.PrefixHashes[3].InvalidationReason != "unchanged" {
-		t.Fatalf("replacement request trace not recorded: %#v", gotTrace.PrefixHashes)
-	}
-}
-
 func TestRunReactiveCompactionRecovers(t *testing.T) {
 	provider := &reactiveProvider{
 		bigText:   strings.Repeat("b", 6000),
@@ -506,8 +465,6 @@ func TestRunReactiveCompactionRecovers(t *testing.T) {
 	// bloats the history.
 	registry := tools.NewRegistry()
 	registry.Register(tools.NewScopedReadFileTool(t.TempDir(), nil))
-	recorder := trace.NewRecorder("reactive-compaction", "run-1", "test")
-	var contextPlans []ContextBreakdown
 
 	// ContextWindow large enough that proactive compaction never triggers, so
 	// only the reactive path can save the run.
@@ -516,10 +473,6 @@ func TestRunReactiveCompactionRecovers(t *testing.T) {
 		PermissionMode:         PermissionModeUnsafe,
 		ContextWindow:          10_000_000,
 		CompactionPreserveLast: 2,
-		Trace:                  recorder,
-		OnContext: func(breakdown ContextBreakdown) {
-			contextPlans = append(contextPlans, breakdown)
-		},
 	})
 	if err != nil {
 		t.Fatalf("expected reactive compaction to recover the run, got error: %v", err)
@@ -530,25 +483,6 @@ func TestRunReactiveCompactionRecovers(t *testing.T) {
 	if provider.summarizeCalls == 0 {
 		t.Fatal("expected reactive compaction to invoke the summarizer")
 	}
-	if len(contextPlans) != 3 {
-		t.Fatalf("main request context callbacks = %d, want initial turns plus compacted retry", len(contextPlans))
-	}
-	if contextPlans[2].MessageTokens >= contextPlans[1].MessageTokens {
-		t.Fatalf("retry context was not updated after compaction: before=%d after=%d", contextPlans[1].MessageTokens, contextPlans[2].MessageTokens)
-	}
-	gotTrace := recorder.Finish()
-	if len(gotTrace.PrefixHashes) != 4 {
-		t.Fatalf("prefix evidence count = %d, want two turns, compaction, and retry: %#v", len(gotTrace.PrefixHashes), gotTrace.PrefixHashes)
-	}
-	if gotTrace.PrefixHashes[0].InvalidationReason != "initial" ||
-		gotTrace.PrefixHashes[1].InvalidationReason != "unchanged" ||
-		gotTrace.PrefixHashes[2].InvalidationReason != "initial" ||
-		gotTrace.PrefixHashes[3].InvalidationReason != "unchanged" {
-		t.Fatalf("unexpected request-specific invalidation evidence: %#v", gotTrace.PrefixHashes)
-	}
-	if gotTrace.PrefixHashes[2].CompletePrefixHash == gotTrace.PrefixHashes[1].CompletePrefixHash {
-		t.Fatalf("compaction fingerprint reused the main request prefix: %#v", gotTrace.PrefixHashes)
-	}
 }
 
 // midStreamReactiveProvider forwards some text BEFORE surfacing a context-limit

internal/agent/context_measurement.go

@@ -23,24 +23,6 @@ type ContextBreakdown struct {
 	TotalTokens   int     // SystemTokens + ToolTokens + MessageTokens
 	ContextWindow int     // model context window; 0 when unknown
 	UsedFraction  float64 // TotalTokens / ContextWindow; 0 when window unknown
-	// Blocks explain why each model-visible category is present without exposing
-	// its content. The planner currently preserves all three categories.
-	Blocks []ContextBlock
-	// CompletePrefixHash identifies the provider-visible system+tool prefix.
-	CompletePrefixHash string
-	// PrefixInvalidationReason is "initial", "unchanged", or a stable comma-
-	// separated list of changed prefix categories.
-	PrefixInvalidationReason string
-}
-
-// ContextBlock is content-free evidence for one model-visible context category.
-type ContextBlock struct {
-	Kind        string
-	Tokens      int
-	CacheClass  string
-	Authority   string
-	Recoverable bool
-	Reason      string
 }
 
 // MeasureContext estimates the per-category token footprint of a request: the
@@ -59,24 +41,6 @@ func MeasureContext(messages []zeroruntime.Message, tools []zeroruntime.ToolDefi
 		ContextWindow: contextWindow,
 	}
 	breakdown.TotalTokens = breakdown.SystemTokens + breakdown.ToolTokens + breakdown.MessageTokens
-	if breakdown.SystemTokens > 0 {
-		breakdown.Blocks = append(breakdown.Blocks, ContextBlock{
-			Kind: "system", Tokens: breakdown.SystemTokens, CacheClass: "stable_prefix",
-			Authority: "required", Reason: "instructions, workspace policy, and safety policy",
-		})
-	}
-	if breakdown.ToolTokens > 0 {
-		breakdown.Blocks = append(breakdown.Blocks, ContextBlock{
-			Kind: "tools", Tokens: breakdown.ToolTokens, CacheClass: "stable_prefix",
-			Authority: "capability", Reason: "currently permitted and selected tool definitions",
-		})
-	}
-	if breakdown.MessageTokens > 0 {
-		breakdown.Blocks = append(breakdown.Blocks, ContextBlock{
-			Kind: "conversation", Tokens: breakdown.MessageTokens, CacheClass: "dynamic_tail",
-			Authority: "transcript", Reason: "valid provider replay history and current task context",
-		})
-	}
 	if contextWindow > 0 {
 		breakdown.UsedFraction = float64(breakdown.TotalTokens) / float64(contextWindow)
 	}

internal/agent/context_measurement_test.go

@@ -32,9 +32,6 @@ func TestMeasureContextSplitsByCategory(t *testing.T) {
 	if breakdown.UsedFraction != wantFraction {
 		t.Fatalf("UsedFraction = %v, want %v", breakdown.UsedFraction, wantFraction)
 	}
-	if len(breakdown.Blocks) != 3 {
-		t.Fatalf("Blocks = %#v, want system/tools/conversation", breakdown.Blocks)
-	}
 }
 
 func TestMeasureContextUnknownWindowHasZeroFraction(t *testing.T) {

internal/agent/context_planner.go

@@ -1,183 +0,0 @@
-package agent
-
-import (
-	"strings"
-
-	"github.com/Gitlawb/zero/internal/zeroruntime"
-)
-
-type contextPlannerConfig struct {
-	contextWindow  int
-	promptCacheKey string
-	promptParts    systemPromptParts
-}
-
-// contextPlanner is the single seam for constructing model-visible requests.
-// Planning is deterministic and does not retrieve content, execute tools, or
-// change permissions. The initial implementation deliberately preserves every
-// message and tool definition while making composition and cache drift
-// inspectable; later selection policies must continue to cross this seam.
-type contextPlanner struct {
-	config          contextPlannerConfig
-	previousPrefix  prefixFingerprint
-	hasPrevious     bool
-	toolSnapshotKey string
-	toolSnapshot    []zeroruntime.ToolDefinition
-}
-
-type contextPlan struct {
-	Request           zeroruntime.CompletionRequest
-	Breakdown         ContextBreakdown
-	PrefixFingerprint prefixFingerprint
-}
-
-func newContextPlanner(config contextPlannerConfig) *contextPlanner {
-	return &contextPlanner{config: config}
-}
-
-// Plan returns a provider request snapshot plus content-free accounting.
-// It intentionally performs no relevance filtering: preserving current model
-// capability is the baseline contract for future planner policies.
-func (planner *contextPlanner) Plan(messages []zeroruntime.Message, toolDefs []zeroruntime.ToolDefinition, reasoningEffort string) contextPlan {
-	return planner.plan(messages, toolDefs, reasoningEffort, planner.config.promptParts)
-}
-
-// planWithPromptParts plans a request whose stable system sections differ from
-// the planner's configured main-run prompt, such as a compaction summary call.
-func (planner *contextPlanner) planWithPromptParts(messages []zeroruntime.Message, toolDefs []zeroruntime.ToolDefinition, reasoningEffort string, parts systemPromptParts) contextPlan {
-	return planner.plan(messages, toolDefs, reasoningEffort, parts)
-}
-
-func (planner *contextPlanner) plan(messages []zeroruntime.Message, toolDefs []zeroruntime.ToolDefinition, reasoningEffort string, parts systemPromptParts) contextPlan {
-	requestMessages := copyMessages(messages)
-	requestSystemPrompt := leadingSystemContent(requestMessages)
-	if parts.prompt != requestSystemPrompt {
-		// Component boundaries from a different request would make the detailed
-		// invalidation reason misleading. Retain the exact request prefix and
-		// classify it conservatively as an unstructured system prompt instead.
-		parts = systemPromptParts{prompt: requestSystemPrompt}
-	}
-	fingerprint := computePrefixFingerprint(buildPromptSubstringsFromParts(parts, toolDefs))
-	request := zeroruntime.CompletionRequest{
-		Messages:        requestMessages,
-		Tools:           planner.snapshotTools(toolDefs, fingerprint),
-		ReasoningEffort: reasoningEffort,
-		PromptCacheKey:  planner.config.promptCacheKey,
-	}
-	breakdown := MeasureContext(request.Messages, request.Tools, planner.config.contextWindow)
-	breakdown.CompletePrefixHash = fingerprint.CompletePrefixHash
-	var previous *prefixFingerprint
-	if planner.hasPrevious {
-		previous = &planner.previousPrefix
-	}
-	breakdown.PrefixInvalidationReason = explainPrefixChange(previous, fingerprint)
-	planner.previousPrefix = fingerprint
-	planner.hasPrevious = true
-	return contextPlan{
-		Request:           request,
-		Breakdown:         breakdown,
-		PrefixFingerprint: fingerprint,
-	}
-}
-
-// snapshotTools freezes provider-visible tool definitions when their semantic
-// fingerprint changes. Stable turns reuse the frozen schemas instead of
-// recursively cloning every map and slice for every request.
-func (planner *contextPlanner) snapshotTools(toolDefs []zeroruntime.ToolDefinition, fingerprint prefixFingerprint) []zeroruntime.ToolDefinition {
-	key := fingerprint.ToolsHash + "\x00" + fingerprint.SchemaHash
-	if planner.toolSnapshotKey != key {
-		planner.toolSnapshot = copyToolDefinitions(toolDefs)
-		planner.toolSnapshotKey = key
-	}
-	return planner.toolSnapshot
-}
-
-func copyToolDefinitions(toolDefs []zeroruntime.ToolDefinition) []zeroruntime.ToolDefinition {
-	if toolDefs == nil {
-		return nil
-	}
-	copied := make([]zeroruntime.ToolDefinition, len(toolDefs))
-	for index, definition := range toolDefs {
-		copied[index] = definition
-		copied[index].Parameters = copySchemaMap(definition.Parameters)
-	}
-	return copied
-}
-
-func copySchemaMap(schema map[string]any) map[string]any {
-	if schema == nil {
-		return nil
-	}
-	copied := make(map[string]any, len(schema))
-	for key, value := range schema {
-		copied[key] = copySchemaValue(value)
-	}
-	return copied
-}
-
-func copySchemaValue(value any) any {
-	switch typed := value.(type) {
-	case map[string]any:
-		return copySchemaMap(typed)
-	case []any:
-		copied := make([]any, len(typed))
-		for index, item := range typed {
-			copied[index] = copySchemaValue(item)
-		}
-		return copied
-	case []string:
-		return append([]string(nil), typed...)
-	default:
-		return value
-	}
-}
-
-func leadingSystemContent(messages []zeroruntime.Message) string {
-	contents := make([]string, 0, 1)
-	for _, message := range messages {
-		if message.Role != zeroruntime.MessageRoleSystem {
-			break
-		}
-		contents = append(contents, message.Content)
-	}
-	return strings.Join(contents, "\n\n")
-}
-
-func explainPrefixChange(previous *prefixFingerprint, current prefixFingerprint) string {
-	if previous == nil {
-		return "initial"
-	}
-	if previous.CompletePrefixHash == current.CompletePrefixHash {
-		return "unchanged"
-	}
-	reasons := make([]string, 0, 3)
-	if previous.SystemPromptHash != current.SystemPromptHash {
-		parts := make([]string, 0, 4)
-		if previous.BaseInstructionsHash != current.BaseInstructionsHash {
-			parts = append(parts, "base_instructions")
-		}
-		if previous.ConfirmationPolicyHash != current.ConfirmationPolicyHash {
-			parts = append(parts, "confirmation_policy")
-		}
-		if previous.ProjectContextHash != current.ProjectContextHash {
-			parts = append(parts, "project_context")
-		}
-		if previous.SkillsHash != current.SkillsHash {
-			parts = append(parts, "skills")
-		}
-		if len(parts) == 0 {
-			parts = append(parts, "system_prompt")
-		}
-		reasons = append(reasons, parts...)
-	}
-	if previous.ToolsHash != current.ToolsHash {
-		reasons = append(reasons, "tools")
-	}
-	if previous.SchemaHash != current.SchemaHash {
-		reasons = append(reasons, "schema")
-	}
-	if len(reasons) == 0 {
-		return "prefix_changed"
-	}
-	return strings.Join(reasons, ",")
-}

internal/agent/context_planner_test.go

@@ -1,185 +0,0 @@
-package agent
-
-import (
-	"reflect"
-	"testing"
-
-	"github.com/Gitlawb/zero/internal/zeroruntime"
-)
-
-func TestContextPlannerPreservesProviderRequest(t *testing.T) {
-	messages := []zeroruntime.Message{
-		{Role: zeroruntime.MessageRoleSystem, Content: "system"},
-		{Role: zeroruntime.MessageRoleUser, Content: "inspect this", Images: []zeroruntime.ImageBlock{{MediaType: "image/png", Data: []byte{1, 2, 3}}}},
-		{Role: zeroruntime.MessageRoleAssistant, Content: "working", ToolCalls: []zeroruntime.ToolCall{{ID: "call-1", Name: "read_file", Arguments: `{"path":"main.go"}`}}, Reasoning: []zeroruntime.ReasoningBlock{{Provider: "test", Type: "thinking", Signature: "sig"}}},
-	}
-	toolDefs := []zeroruntime.ToolDefinition{{
-		Name: "read_file", Description: "Read a file",
-		Parameters: map[string]any{
-			"type":       "object",
-			"required":   []string{"path"},
-			"properties": map[string]any{"path": map[string]any{"type": "string"}},
-			"anyOf":      []any{map[string]any{"type": "object"}},
-		},
-	}}
-	planner := newContextPlanner(contextPlannerConfig{
-		contextWindow:  128_000,
-		promptCacheKey: "session-1",
-		promptParts:    systemPromptParts{prompt: "system", baseInstructions: "system"},
-	})
-
-	plan := planner.Plan(messages, toolDefs, "medium")
-	want := zeroruntime.CompletionRequest{
-		Messages:        copyMessages(messages),
-		Tools:           toolDefs,
-		ReasoningEffort: "medium",
-		PromptCacheKey:  "session-1",
-	}
-	if !reflect.DeepEqual(plan.Request, want) {
-		t.Fatalf("planned request changed provider input:\n got: %#v\nwant: %#v", plan.Request, want)
-	}
-	stable := planner.Plan(messages, toolDefs, "medium")
-	if &stable.Request.Tools[0] != &plan.Request.Tools[0] {
-		t.Fatal("stable tool fingerprint rebuilt the immutable schema snapshot")
-	}
-
-	// A plan owns its request snapshot; later caller mutation cannot change its
-	// messages or its recursively nested tool schema.
-	messages[1].Content = "changed"
-	messages[1].Images[0].Data[0] = 9
-	toolDefs[0].Name = "changed_tool"
-	toolDefs[0].Parameters["required"].([]string)[0] = "other"
-	toolDefs[0].Parameters["properties"].(map[string]any)["path"].(map[string]any)["type"] = "integer"
-	toolDefs[0].Parameters["anyOf"].([]any)[0].(map[string]any)["type"] = "array"
-	if plan.Request.Messages[1].Content != "inspect this" || plan.Request.Messages[1].Images[0].Data[0] != 1 {
-		t.Fatalf("planned messages alias caller state: %#v", plan.Request.Messages[1])
-	}
-	if plan.Request.Tools[0].Name != "read_file" ||
-		plan.Request.Tools[0].Parameters["required"].([]string)[0] != "path" ||
-		plan.Request.Tools[0].Parameters["properties"].(map[string]any)["path"].(map[string]any)["type"] != "string" ||
-		plan.Request.Tools[0].Parameters["anyOf"].([]any)[0].(map[string]any)["type"] != "object" {
-		t.Fatalf("planned tools alias caller state: %#v", plan.Request.Tools[0])
-	}
-
-	next := planner.Plan(messages, toolDefs, "medium")
-	if next.PrefixFingerprint == plan.PrefixFingerprint || next.Request.Tools[0].Name != "changed_tool" {
-		t.Fatalf("changed tool schema did not refresh snapshot: %#v", next)
-	}
-	if plan.Request.Tools[0].Name != "read_file" {
-		t.Fatalf("refresh mutated earlier request: %#v", plan.Request.Tools[0])
-	}
-}
-
-func TestContextPlannerReportsInspectableBlocks(t *testing.T) {
-	planner := newContextPlanner(contextPlannerConfig{contextWindow: 100_000})
-	plan := planner.Plan([]zeroruntime.Message{
-		{Role: zeroruntime.MessageRoleSystem, Content: filler(400)},
-		{Role: zeroruntime.MessageRoleUser, Content: filler(200)},
-	}, []zeroruntime.ToolDefinition{{Name: "read_file", Description: "Read a file"}}, "")
-
-	if plan.Breakdown.PrefixInvalidationReason != "initial" || plan.Breakdown.CompletePrefixHash == "" {
-		t.Fatalf("prefix evidence = %#v", plan.Breakdown)
-	}
-	if len(plan.Breakdown.Blocks) != 3 {
-		t.Fatalf("blocks = %#v, want system/tools/conversation", plan.Breakdown.Blocks)
-	}
-	wantKinds := []string{"system", "tools", "conversation"}
-	total := 0
-	for index, block := range plan.Breakdown.Blocks {
-		if block.Kind != wantKinds[index] || block.Tokens <= 0 || block.Reason == "" || block.Authority == "" || block.CacheClass == "" {
-			t.Fatalf("block %d = %#v", index, block)
-		}
-		total += block.Tokens
-	}
-	if total != plan.Breakdown.TotalTokens {
-		t.Fatalf("block tokens = %d, want total %d", total, plan.Breakdown.TotalTokens)
-	}
-}
-
-func TestContextPlannerFingerprintsActualRequestSystemPrompt(t *testing.T) {
-	planner := newContextPlanner(contextPlannerConfig{promptParts: systemPromptParts{
-		prompt: "configured system", baseInstructions: "configured system",
-	}})
-	messages := []zeroruntime.Message{
-		{Role: zeroruntime.MessageRoleSystem, Content: "request-specific system"},
-		{Role: zeroruntime.MessageRoleUser, Content: "task"},
-	}
-
-	plan := planner.Plan(messages, nil, "")
-	want := computePrefixFingerprint(buildPromptSubstringsFromParts(
-		systemPromptParts{prompt: "request-specific system"}, nil,
-	))
-	if plan.PrefixFingerprint != want {
-		t.Fatalf("fingerprint describes configured prompt instead of request:\n got: %#v\nwant: %#v", plan.PrefixFingerprint, want)
-	}
-}
-
-func TestContextPlannerExplainsPrefixInvalidation(t *testing.T) {
-	planner := newContextPlanner(contextPlannerConfig{promptParts: systemPromptParts{
-		prompt: "system", baseInstructions: "base", projectContext: "project",
-	}})
-	messages := []zeroruntime.Message{{Role: zeroruntime.MessageRoleSystem, Content: "system"}, {Role: zeroruntime.MessageRoleUser, Content: "task"}}
-	tools := []zeroruntime.ToolDefinition{{Name: "read_file", Description: "Read", Parameters: map[string]any{"type": "object"}}}
-
-	if got := planner.Plan(messages, tools, "").Breakdown.PrefixInvalidationReason; got != "initial" {
-		t.Fatalf("first reason = %q, want initial", got)
-	}
-	if got := planner.Plan(messages, tools, "").Breakdown.PrefixInvalidationReason; got != "unchanged" {
-		t.Fatalf("stable reason = %q, want unchanged", got)
-	}
-	tools[0].Description = "Read an exact file"
-	if got := planner.Plan(messages, tools, "").Breakdown.PrefixInvalidationReason; got != "tools" {
-		t.Fatalf("tool reason = %q, want tools", got)
-	}
-	tools[0].Parameters["required"] = []any{"path"}
-	if got := planner.Plan(messages, tools, "").Breakdown.PrefixInvalidationReason; got != "schema" {
-		t.Fatalf("schema reason = %q, want schema", got)
-	}
-	planner.config.promptParts.prompt = "system with changed project"
-	planner.config.promptParts.projectContext = "changed project"
-	messages[0].Content = "system with changed project"
-	if got := planner.Plan(messages, tools, "").Breakdown.PrefixInvalidationReason; got != "project_context" {
-		t.Fatalf("project reason = %q, want project_context", got)
-	}
-}
-
-func TestExplainPrefixChangeNamesEveryChangedComponent(t *testing.T) {
-	baseline := prefixFingerprint{
-		SystemPromptHash:       "system",
-		BaseInstructionsHash:   "base",
-		ConfirmationPolicyHash: "policy",
-		ProjectContextHash:     "project",
-		SkillsHash:             "skills",
-		ToolsHash:              "tools",
-		SchemaHash:             "schema",
-		CompletePrefixHash:     "complete",
-	}
-	tests := []struct {
-		name   string
-		mutate func(*prefixFingerprint)
-		want   string
-	}{
-		{name: "base instructions", mutate: func(value *prefixFingerprint) {
-			value.SystemPromptHash, value.BaseInstructionsHash = "changed", "changed"
-		}, want: "base_instructions"},
-		{name: "confirmation policy", mutate: func(value *prefixFingerprint) {
-			value.SystemPromptHash, value.ConfirmationPolicyHash = "changed", "changed"
-		}, want: "confirmation_policy"},
-		{name: "project context", mutate: func(value *prefixFingerprint) {
-			value.SystemPromptHash, value.ProjectContextHash = "changed", "changed"
-		}, want: "project_context"},
-		{name: "skills", mutate: func(value *prefixFingerprint) { value.SystemPromptHash, value.SkillsHash = "changed", "changed" }, want: "skills"},
-		{name: "unclassified system prompt", mutate: func(value *prefixFingerprint) { value.SystemPromptHash = "changed" }, want: "system_prompt"},
-		{name: "tools and schema", mutate: func(value *prefixFingerprint) { value.ToolsHash, value.SchemaHash = "changed", "changed" }, want: "tools,schema"},
-	}
-	for _, test := range tests {
-		t.Run(test.name, func(t *testing.T) {
-			current := baseline
-			test.mutate(&current)
-			current.CompletePrefixHash = "changed"
-			if got := explainPrefixChange(&baseline, current); got != test.want {
-				t.Fatalf("reason = %q, want %q", got, test.want)
-			}
-		})
-	}
-}

internal/agent/loop.go

@@ -183,22 +183,10 @@ func Run(ctx context.Context, prompt string, provider Provider, options Options)
 	defer runPermissions.cleanup()
 
 	promptParts := buildSystemPromptParts(options)
-	planner := newContextPlanner(contextPlannerConfig{
-		contextWindow:  options.ContextWindow,
-		promptCacheKey: options.SessionID,
-		promptParts:    promptParts,
-	})
 	messages := zeroruntime.SeedMessagesWithImages(promptParts.prompt, prompt, options.Images)
 
 	guards := newGuardState()
 	task := newTaskState(prompt, options.Trace)
-	onPermission := options.OnPermission
-	options.OnPermission = func(event PermissionEvent) {
-		task.observe(taskStateEvent{kind: taskStateEventPermission, permission: event})
-		if onPermission != nil {
-			onPermission(event)
-		}
-	}
 	compactor := newCompactionState(options, task)
 	defer func() {
 		// A final transcript comparison is observational. It records drift but
@@ -287,15 +275,42 @@ func Run(ctx context.Context, prompt string, provider Provider, options Options)
 		exposed, _ := partitionToolsCached(registry, permissionMode, options, loaded, toolDefCache)
 		toolPartitionSpan.End()
 
+		// Fingerprint the exact system prompt built at run start plus this turn's
+		// provider-visible tool definitions in their emitted order. Reusing the
+		// retained prompt parts avoids rebuilding workspace context while ensuring
+		// the trace describes the same bytes carried by the request.
+		if options.Trace != nil {
+			fp := computePrefixFingerprint(buildPromptSubstringsFromParts(promptParts, exposed))
+			options.Trace.EmitPrefixHash(trace.PrefixHash{
+				SystemPromptHash:       fp.SystemPromptHash,
+				BaseInstructionsHash:   fp.BaseInstructionsHash,
+				ConfirmationPolicyHash: fp.ConfirmationPolicyHash,
+				ProjectContextHash:     fp.ProjectContextHash,
+				SkillsHash:             fp.SkillsHash,
+				ToolsHash:              fp.ToolsHash,
+				SchemaHash:             fp.SchemaHash,
+				CompletePrefixHash:     fp.CompletePrefixHash,
+			})
+		}
+
 		// PROACTIVE compaction: if the history is approaching the model's
 		// context window, summarize the oldest middle before building the
 		// request. A no-op when ContextWindow == 0 (compaction disabled).
 		compactionSpan := options.Trace.Span(trace.SpanCompaction)
 		messages = compactor.maybeCompact(ctx, provider, messages, exposed)
 		compactionSpan.End()
-		plan := planner.Plan(messages, exposed, options.ReasoningEffort)
-		request := plan.Request
-		recordContextPlan(options, plan)
+		request := zeroruntime.CompletionRequest{
+			Messages:        copyMessages(messages),
+			Tools:           exposed,
+			ReasoningEffort: options.ReasoningEffort,
+			PromptCacheKey:  options.SessionID,
+		}
+
+		// Report the per-category context budget for this turn so a surface can
+		// show utilization. Opt-in: a no-op when OnContext is unset.
+		if options.OnContext != nil {
+			options.OnContext(MeasureContext(messages, request.Tools, options.ContextWindow))
+		}
 
 		// A transient upstream disconnect on the initial connect is retried with
 		// backoff (before any content is forwarded, so no OnText is duplicated);
@@ -320,9 +335,12 @@ func Run(ctx context.Context, prompt string, provider Provider, options Options)
 				// on registry+loaded, not on the messages, so they stay valid after
 				// compaction. Using the bare toolDefinitions here would route through an
 				// empty-loaded partition, re-hiding every already-loaded deferred tool.
-				retryPlan := planner.Plan(messages, exposed, options.ReasoningEffort)
-				request = retryPlan.Request
-				recordContextPlan(options, retryPlan)
+				request = zeroruntime.CompletionRequest{
+					Messages:        copyMessages(messages),
+					Tools:           exposed,
+					ReasoningEffort: options.ReasoningEffort,
+					PromptCacheKey:  options.SessionID,
+				}
 				// Pre-content connect after a context-limit compaction: route through the
 				// reconnect helper so a transient upstream hiccup here doesn't fail the
 				// whole run and re-burn every token (AUDIT-L1).
@@ -406,9 +424,12 @@ func Run(ctx context.Context, prompt string, provider Provider, options Options)
 				// Reuse the SAME active-mode partition (exposed) from this turn rather
 				// than the bare toolDefinitions: exposed depends on registry+loaded (not
 				// the messages), so it stays valid after compaction.
-				retryPlan := planner.Plan(messages, exposed, options.ReasoningEffort)
-				retryRequest := retryPlan.Request
-				recordContextPlan(options, retryPlan)
+				retryRequest := zeroruntime.CompletionRequest{
+					Messages:        copyMessages(messages),
+					Tools:           exposed,
+					ReasoningEffort: options.ReasoningEffort,
+					PromptCacheKey:  options.SessionID,
+				}
 				retryStream, retryStreamErr := streamWithReconnect(ctx, provider, retryRequest, reconnectNoticeFor(options))
 				if retryStreamErr != nil {
 					return collected, retryStreamErr
@@ -466,9 +487,12 @@ func Run(ctx context.Context, prompt string, provider Provider, options Options)
 				result.Messages = copyMessages(messages)
 				return result, err
 			}
-			retryPlan := planner.Plan(messages, exposed, options.ReasoningEffort)
-			retryRequest := retryPlan.Request
-			recordContextPlan(options, retryPlan)
+			retryRequest := zeroruntime.CompletionRequest{
+				Messages:        copyMessages(messages),
+				Tools:           exposed,
+				ReasoningEffort: options.ReasoningEffort,
+				PromptCacheKey:  options.SessionID,
+			}
 			retryStream, retryErr := streamWithReconnect(ctx, provider, retryRequest, reconnectNoticeFor(options))
 			if retryErr != nil {
 				result.Messages = copyMessages(messages)
@@ -674,7 +698,7 @@ func Run(ctx context.Context, prompt string, provider Provider, options Options)
 			}
 			options.Trace.Counter(trace.CounterToolCalls, 1)
 			recordOutputBudgetTrace(options.Trace, toolResult)
-			task.observe(taskStateEvent{kind: taskStateEventToolResult, arguments: call.Arguments, toolResult: toolResult})
+			task.observe(taskStateEvent{kind: taskStateEventToolResult, toolResult: toolResult})
 			if options.OnToolResult != nil {
 				options.OnToolResult(toolResult)
 			}
@@ -688,11 +712,9 @@ func Run(ctx context.Context, prompt string, provider Provider, options Options)
 				turnRequestedModel = toolResult.RequestedModel
 			}
 			messages = append(messages, zeroruntime.Message{
-				Role:         zeroruntime.MessageRoleTool,
-				Content:      toolResult.ModelOutput(),
-				ToolCallID:   toolResult.ToolCallID,
-				IsError:      toolResult.Status == tools.StatusError,
-				ChangedFiles: append([]string(nil), toolResult.ChangedFiles...),
+				Role:       zeroruntime.MessageRoleTool,
+				Content:    toolResult.Output,
+				ToolCallID: toolResult.ToolCallID,
 			})
 			// Images ride a following USER message rather than the tool result
 			// above. Every provider drops images on a tool-role message —
@@ -721,7 +743,7 @@ func Run(ctx context.Context, prompt string, provider Provider, options Options)
 			if stopReason := stopReasonFromToolResult(toolResult); stopReason != "" {
 				messages = appendAbortedToolResults(messages, collected.ToolCalls[index+1:])
 				messages = append(messages, toolImageMessages...)
-				result.FinalAnswer = toolResult.ModelOutput()
+				result.FinalAnswer = toolResult.Output
 				result.StopReason = stopReason
 				result.Messages = copyMessages(messages)
 				return result, nil
@@ -734,7 +756,7 @@ func Run(ctx context.Context, prompt string, provider Provider, options Options)
 			// aren't fixed by reformatting the call, so a "match this schema" hint
 			// would misdirect the model toward JSON shape or blocked behavior.
 			retriableFailure := isRetriableToolError(toolResult)
-			outcome := guards.observeToolResult(call.Name, retriableFailure, toolResult.ModelOutput())
+			outcome := guards.observeToolResult(call.Name, retriableFailure, toolResult.Output)
 			posture.observeToolOutcome(outcome, toolResult)
 			if outcome.Stop {
 				// The assistant message advertised EVERY collected tool call, but
@@ -750,7 +772,7 @@ func Run(ctx context.Context, prompt string, provider Provider, options Options)
 				return result, nil
 			}
 			if outcome.InjectHint && failureHint == "" {
-				failureHint = toolFailureHint(call.Name, toolSchemaJSON(registry, call.Name), toolResult.ModelOutput())
+				failureHint = toolFailureHint(call.Name, toolSchemaJSON(registry, call.Name), toolResult.Output)
 			}
 
 			// Collect the files this successful mutating tool changed. Self-correct
@@ -898,7 +920,7 @@ func Run(ctx context.Context, prompt string, provider Provider, options Options)
 		})
 	}
 	finalExposed, _ := partitionToolsCached(registry, permissionMode, options, loaded, toolDefCache)
-	if answer, finalMessages, finishReason := finalAnswerAfterMaxTurns(ctx, provider, planner, messages, finalExposed, options); strings.TrimSpace(answer) != "" {
+	if answer, finalMessages, finishReason := finalAnswerAfterMaxTurns(ctx, provider, messages, finalExposed, options); strings.TrimSpace(answer) != "" {
 		result.FinalAnswer = answer
 		result.FinishReason = finishReason
 		result.Messages = copyMessages(finalMessages)
@@ -922,21 +944,6 @@ func recordOutputBudgetTrace(recorder *trace.Recorder, result ToolResult) {
 	if recorder == nil || result.Meta["output_budget_category"] == "" {
 		return
 	}
-	if result.Outcome.Finalized() {
-		diagnostics := result.Outcome.Diagnostics
-		recorder.EmitOutputBudget(trace.OutputBudgetEvent{
-			Tool:                    result.Name,
-			Category:                diagnostics.Category,
-			OriginalBytes:           diagnostics.OriginalBytes,
-			RetainedBytes:           diagnostics.ModelBytes,
-			EstimatedOriginalTokens: diagnostics.EstimatedOriginalTokens,
-			EstimatedRetainedTokens: diagnostics.EstimatedModelTokens,
-			Truncated:               diagnostics.Truncated,
-			Reason:                  diagnostics.Reason,
-			SpillCreated:            result.Outcome.Artifact != nil,
-		})
-		return
-	}
 	parseInt := func(key string) int {
 		value, _ := strconv.Atoi(result.Meta[key])
 		return value
@@ -955,32 +962,7 @@ func recordOutputBudgetTrace(recorder *trace.Recorder, result ToolResult) {
 	})
 }
 
-func recordContextPlan(options Options, plan contextPlan) {
-	recordContextPlanTrace(options.Trace, plan)
-	if options.OnContext != nil {
-		options.OnContext(plan.Breakdown)
-	}
-}
-
-func recordContextPlanTrace(recorder *trace.Recorder, plan contextPlan) {
-	if recorder == nil {
-		return
-	}
-	fingerprint := plan.PrefixFingerprint
-	recorder.EmitPrefixHash(trace.PrefixHash{
-		SystemPromptHash:       fingerprint.SystemPromptHash,
-		BaseInstructionsHash:   fingerprint.BaseInstructionsHash,
-		ConfirmationPolicyHash: fingerprint.ConfirmationPolicyHash,
-		ProjectContextHash:     fingerprint.ProjectContextHash,
-		SkillsHash:             fingerprint.SkillsHash,
-		ToolsHash:              fingerprint.ToolsHash,
-		SchemaHash:             fingerprint.SchemaHash,
-		CompletePrefixHash:     fingerprint.CompletePrefixHash,
-		InvalidationReason:     plan.Breakdown.PrefixInvalidationReason,
-	})
-}
-
-func finalAnswerAfterMaxTurns(ctx context.Context, provider Provider, planner *contextPlanner, messages []zeroruntime.Message, toolDefs []zeroruntime.ToolDefinition, options Options) (string, []zeroruntime.Message, string) {
+func finalAnswerAfterMaxTurns(ctx context.Context, provider Provider, messages []zeroruntime.Message, toolDefs []zeroruntime.ToolDefinition, options Options) (string, []zeroruntime.Message, string) {
 	finalMessages := copyMessages(messages)
 	finalMessages = append(finalMessages, zeroruntime.Message{
 		Role:    zeroruntime.MessageRoleUser,
@@ -989,9 +971,12 @@ func finalAnswerAfterMaxTurns(ctx context.Context, provider Provider, planner *c
 	// The max-turns final-answer call is a pre-content connect, often after a long
 	// autonomous/cron run — route it through the reconnect helper so a single
 	// transient hiccup doesn't drop the final summary (AUDIT-L1).
-	plan := planner.Plan(finalMessages, toolDefs, options.ReasoningEffort)
-	recordContextPlan(options, plan)
-	stream, err := streamWithReconnect(ctx, provider, plan.Request, reconnectNoticeFor(options))
+	stream, err := streamWithReconnect(ctx, provider, zeroruntime.CompletionRequest{
+		Messages:        copyMessages(finalMessages),
+		Tools:           toolDefs,
+		ReasoningEffort: options.ReasoningEffort,
+		PromptCacheKey:  options.SessionID,
+	}, reconnectNoticeFor(options))
 	if err != nil {
 		return "", messages, ""
 	}
@@ -1472,15 +1457,14 @@ func executeToolCall(ctx context.Context, registry *tools.Registry, call ToolCal
 		ToolCallID:      call.ID,
 		Name:            call.Name,
 		Status:          result.Status,
-		Output:          result.ModelOutput(),
+		Output:          result.Output,
 		Truncated:       result.Truncated,
 		Meta:            result.Meta,
 		Images:          result.Images,
 		Redacted:        result.Redacted,
 		ChangedFiles:    result.ChangedFiles,
 		ChangeSummaries: result.ChangeSummaries,
-		Display:         result.HumanDisplay(),
-		Outcome:         result.Outcome,
+		Display:         result.Display,
 		LoadedTools:     loadedToolsFromResult(result.Meta),
 		// A tool may signal a mid-run model escalation by carrying the target id
 		// in Meta["escalate_to_model"]. Lift it into the typed loop-level field;
@@ -2077,14 +2061,13 @@ func askUserFallbackResult(ctx context.Context, registry *tools.Registry, call T
 			ToolCallID:      call.ID,
 			Name:            call.Name,
 			Status:          result.Status,
-			Output:          result.ModelOutput(),
+			Output:          result.Output,
 			Truncated:       result.Truncated,
 			Meta:            result.Meta,
 			Redacted:        result.Redacted,
 			ChangedFiles:    result.ChangedFiles,
 			ChangeSummaries: result.ChangeSummaries,
-			Display:         result.HumanDisplay(),
-			Outcome:         result.Outcome,
+			Display:         result.Display,
 		}
 	}
 	return ToolResult{
@@ -3295,7 +3278,6 @@ func appendAbortedToolResults(messages []Message, remaining []ToolCall) []Messag
 			Role:       zeroruntime.MessageRoleTool,
 			Content:    abortedToolResultNotice,
 			ToolCallID: call.ID,
-			IsError:    true,
 		})
 	}
 	return messages
@@ -3326,9 +3308,6 @@ func copyMessages(messages []Message) []Message {
 		if message.Reasoning != nil {
 			copied[index].Reasoning = append([]zeroruntime.ReasoningBlock{}, message.Reasoning...)
 		}
-		if message.ChangedFiles != nil {
-			copied[index].ChangedFiles = append([]string(nil), message.ChangedFiles...)
-		}
 		// Deep-copy image attachments (slice AND each Data byte slice) so the
 		// raw image bytes are never aliased across history/request/result copies.
 		copied[index].Images = zeroruntime.CloneImageBlocks(message.Images)

internal/agent/loop_test.go

@@ -3592,11 +3592,6 @@ func TestRunAppendsAbortedPlaceholderForUnexecutedToolCallsOnGuardStop(t *testin
 	if !strings.Contains(strings.ToLower(placeholder), "aborted") {
 		t.Fatalf("expected the placeholder result to mark the call as aborted, got %q", placeholder)
 	}
-	for _, message := range result.Messages {
-		if message.ToolCallID == "flaky-2" && !message.IsError {
-			t.Fatalf("aborted placeholder must carry error status: %#v", message)
-		}
-	}
 
 	// Every tool_use in the final assistant message must have a matching result.
 	for _, message := range result.Messages {
@@ -3611,33 +3606,6 @@ func TestRunAppendsAbortedPlaceholderForUnexecutedToolCallsOnGuardStop(t *testin
 	}
 }
 
-func TestRunCarriesToolErrorStatusIntoMessageHistory(t *testing.T) {
-	registry := tools.NewRegistry()
-	registry.Register(alwaysFailingTool{})
-	provider := &mockProvider{turns: [][]zeroruntime.StreamEvent{
-		{
-			{Type: zeroruntime.StreamEventToolCallStart, ToolCallID: "failed-call", ToolName: "flaky"},
-			{Type: zeroruntime.StreamEventToolCallEnd, ToolCallID: "failed-call"},
-			{Type: zeroruntime.StreamEventDone},
-		},
-		{{Type: zeroruntime.StreamEventText, Content: "done"}, {Type: zeroruntime.StreamEventDone}},
-	}}
-
-	result, err := Run(context.Background(), "go", provider, Options{Registry: registry})
-	if err != nil {
-		t.Fatal(err)
-	}
-	for _, message := range result.Messages {
-		if message.ToolCallID == "failed-call" {
-			if !message.IsError {
-				t.Fatalf("failed tool result lost its structured status: %#v", message)
-			}
-			return
-		}
-	}
-	t.Fatalf("failed tool result missing from message history: %#v", result.Messages)
-}
-
 type secretEmittingTool struct{ output string }
 
 func (t secretEmittingTool) Name() string        { return "leak" }
@@ -3729,8 +3697,6 @@ func TestRunTracingWrapperStampsUsage(t *testing.T) {
 		{Type: zeroruntime.StreamEventDone},
 	}}}
 	onUsageCalls := 0
-	onContextCalls := 0
-	var contextPlan ContextBreakdown
 	rec := trace.NewRecorder("tracing-session", "run-1", "test")
 	if _, err := Run(context.Background(), "hi", provider, Options{
 		SessionID:    "tracing-session",
@@ -3739,10 +3705,6 @@ func TestRunTracingWrapperStampsUsage(t *testing.T) {
 		Model:        "test-model",
 		Trace:        rec,
 		OnUsage:      func(Usage) { onUsageCalls++ },
-		OnContext: func(breakdown ContextBreakdown) {
-			onContextCalls++
-			contextPlan = breakdown
-		},
 	}); err != nil {
 		t.Fatalf("Run: %v", err)
 	}
@@ -3769,12 +3731,6 @@ func TestRunTracingWrapperStampsUsage(t *testing.T) {
 	if onUsageCalls == 0 {
 		t.Fatal("wrapped OnUsage did not forward to the caller's callback")
 	}
-	if onContextCalls != 1 || len(contextPlan.Blocks) != 2 || contextPlan.PrefixInvalidationReason != "initial" {
-		t.Fatalf("context plan callback = calls %d, plan %#v", onContextCalls, contextPlan)
-	}
-	if len(tr.PrefixHashes) != 1 || tr.PrefixHashes[0].InvalidationReason != "initial" || tr.PrefixHashes[0].CompletePrefixHash != contextPlan.CompletePrefixHash {
-		t.Fatalf("trace context evidence = %#v, plan %#v", tr.PrefixHashes, contextPlan)
-	}
 }
 
 // TestRunNilTraceForwardsUsage verifies a nil recorder leaves the loop

internal/agent/task_state.go

@@ -1,14 +1,10 @@
 package agent
 
 import (
-	"crypto/sha256"
 	"encoding/json"
-	"fmt"
 	"reflect"
-	"regexp"
 	"sort"
 	"strings"
-	"unicode/utf8"
 
 	"github.com/Gitlawb/zero/internal/tools"
 	"github.com/Gitlawb/zero/internal/trace"
@@ -56,41 +52,17 @@ type taskVerificationState struct {
 	LastOutcome Outcome `json:"last_outcome,omitempty"`
 }
 
-type taskFailureState struct {
-	Key     string `json:"key,omitempty"`
-	Tool    string `json:"tool"`
-	Command string `json:"command,omitempty"`
-	Summary string `json:"summary"`
-}
-
-type taskApprovalState struct {
-	Tool     string                   `json:"tool"`
-	Decision PermissionDecisionAction `json:"decision,omitempty"`
-	Scope    string                   `json:"scope,omitempty"`
-	Reason   string                   `json:"reason,omitempty"`
-}
-
-type taskArtifactState struct {
-	Tool string `json:"tool"`
-	Path string `json:"path"`
-}
-
 type taskStateSnapshot struct {
-	Revision            int                   `json:"revision"`
-	Objective           string                `json:"objective"`
-	Status              taskStatus            `json:"status"`
-	Plan                taskPlanState         `json:"plan"`
-	Tools               taskToolState         `json:"tools"`
-	Verification        taskVerificationState `json:"verification"`
-	ChangedFiles        []string              `json:"changed_files,omitempty"`
-	Constraints         []string              `json:"constraints,omitempty"`
-	UnresolvedFailures  []taskFailureState    `json:"unresolved_failures,omitempty"`
-	Approvals           []taskApprovalState   `json:"approvals,omitempty"`
-	Artifacts           []taskArtifactState   `json:"artifacts,omitempty"`
-	ResolvedFailureKeys []string              `json:"-"`
-	CompletionDecision  CompletionDecision    `json:"completion_decision,omitempty"`
-	CompletionReason    string                `json:"completion_reason,omitempty"`
-	PlanParity          taskPlanParity        `json:"plan_parity"`
+	Revision           int                   `json:"revision"`
+	Objective          string                `json:"objective"`
+	Status             taskStatus            `json:"status"`
+	Plan               taskPlanState         `json:"plan"`
+	Tools              taskToolState         `json:"tools"`
+	Verification       taskVerificationState `json:"verification"`
+	ChangedFiles       []string              `json:"changed_files,omitempty"`
+	CompletionDecision CompletionDecision    `json:"completion_decision,omitempty"`
+	CompletionReason   string                `json:"completion_reason,omitempty"`
+	PlanParity         taskPlanParity        `json:"plan_parity"`
 }
 
 type taskStateEventKind int
@@ -100,7 +72,6 @@ const (
 	taskStateEventToolResult
 	taskStateEventVerification
 	taskStateEventCompletion
-	taskStateEventPermission
 )
 
 type taskStateEvent struct {
@@ -109,7 +80,6 @@ type taskStateEvent struct {
 	toolResult   ToolResult
 	verification Outcome
 	completion   completionEvaluation
-	permission   PermissionEvent
 }
 
 // taskState is a deterministic projection of facts the loop already observes.
@@ -131,7 +101,6 @@ func newTaskState(objective string, recorder *trace.Recorder) *taskState {
 		},
 		changedFiles: map[string]struct{}{},
 	}
-	state.snapshotValue.Constraints = extractExplicitConstraints(objective)
 	state.recorder = recorder
 	return state
 }
@@ -165,7 +134,6 @@ func (state *taskState) observe(event taskStateEvent) bool {
 			}
 		}
 		state.snapshotValue.ChangedFiles = sortedKeys(state.changedFiles)
-		state.observeToolEvidence(event.arguments, event.toolResult)
 		changed = true
 	case taskStateEventVerification:
 		if event.verification == OutcomeDisabled {
@@ -192,10 +160,6 @@ func (state *taskState) observe(event taskStateEvent) bool {
 			state.snapshotValue.Status = taskStatusActive
 		}
 		changed = true
-	case taskStateEventPermission:
-		state.markActive()
-		state.observePermission(event.permission)
-		changed = true
 	}
 	if changed {
 		state.snapshotValue.Revision++
@@ -219,180 +183,9 @@ func (state *taskState) snapshot() taskStateSnapshot {
 	snapshot := state.snapshotValue
 	snapshot.Plan.Items = append([]taskPlanItem(nil), state.snapshotValue.Plan.Items...)
 	snapshot.ChangedFiles = append([]string(nil), state.snapshotValue.ChangedFiles...)
-	snapshot.Constraints = append([]string(nil), state.snapshotValue.Constraints...)
-	snapshot.UnresolvedFailures = append([]taskFailureState(nil), state.snapshotValue.UnresolvedFailures...)
-	snapshot.Approvals = append([]taskApprovalState(nil), state.snapshotValue.Approvals...)
-	snapshot.Artifacts = append([]taskArtifactState(nil), state.snapshotValue.Artifacts...)
-	snapshot.ResolvedFailureKeys = append([]string(nil), state.snapshotValue.ResolvedFailureKeys...)
 	return snapshot
 }
 
-const (
-	maxTaskEvidenceEntries = 8
-	maxTaskEvidenceBytes   = 320
-	maxTaskConstraints     = 10
-)
-
-func (state *taskState) observeToolEvidence(arguments string, result ToolResult) {
-	command := capTaskEvidence(commandFromArguments(arguments))
-	key := taskFailureKey(result.Name, command, arguments)
-	if result.Status == tools.StatusOK {
-		if hasTaskFailure(state.snapshotValue.UnresolvedFailures, key) {
-			state.snapshotValue.UnresolvedFailures = removeTaskFailure(state.snapshotValue.UnresolvedFailures, key)
-			state.snapshotValue.ResolvedFailureKeys = appendBoundedUnique(state.snapshotValue.ResolvedFailureKeys, key, maxTaskEvidenceEntries)
-		}
-	} else {
-		state.snapshotValue.ResolvedFailureKeys = removeString(state.snapshotValue.ResolvedFailureKeys, key)
-		state.snapshotValue.UnresolvedFailures = removeTaskFailure(state.snapshotValue.UnresolvedFailures, key)
-		state.snapshotValue.UnresolvedFailures = appendBounded(state.snapshotValue.UnresolvedFailures, taskFailureState{
-			Key: key, Tool: result.Name, Command: command, Summary: capTaskEvidence(firstLine(result.Output)),
-		}, maxTaskEvidenceEntries)
-	}
-	for _, metaKey := range []string{"spill_path", "artifact_path"} {
-		if path := strings.TrimSpace(result.Meta[metaKey]); path != "" {
-			state.snapshotValue.Artifacts = appendBoundedUnique(state.snapshotValue.Artifacts,
-				taskArtifactState{Tool: result.Name, Path: capTaskEvidence(path)}, maxTaskEvidenceEntries)
-		}
-	}
-}
-
-func taskFailureKey(toolName, command, arguments string) string {
-	identity := command
-	if identity == "" {
-		canonical := []byte(strings.TrimSpace(arguments))
-		var value any
-		if json.Unmarshal(canonical, &value) == nil {
-			if encoded, err := json.Marshal(value); err == nil {
-				canonical = encoded
-			}
-		}
-		digest := sha256.Sum256(canonical)
-		identity = fmt.Sprintf("args:%x", digest[:8])
-	}
-	return strings.TrimSpace(toolName) + "\x00" + identity
-}
-
-func (state *taskState) observePermission(event PermissionEvent) {
-	decision := event.DecisionAction
-	if decision == "" {
-		decision = PermissionDecisionAction(event.Action)
-	}
-	state.snapshotValue.Approvals = appendBoundedUnique(state.snapshotValue.Approvals, taskApprovalState{
-		Tool: event.ToolName, Decision: decision, Scope: capTaskEvidence(event.Scope),
-		Reason: capTaskEvidence(firstNonEmptyString(event.DecisionReason, event.Reason)),
-	}, maxTaskEvidenceEntries)
-}
-
-func commandFromArguments(arguments string) string {
-	var object map[string]json.RawMessage
-	if json.Unmarshal([]byte(strings.TrimSpace(arguments)), &object) != nil {
-		return ""
-	}
-	for _, key := range []string{"cmd", "command", "script", "shell"} {
-		var command string
-		if raw, ok := object[key]; ok && json.Unmarshal(raw, &command) == nil {
-			return strings.TrimSpace(command)
-		}
-	}
-	return ""
-}
-
-func firstLine(value string) string {
-	value = strings.TrimSpace(value)
-	if index := strings.IndexByte(value, '\n'); index >= 0 {
-		value = value[:index]
-	}
-	return value
-}
-
-func capTaskEvidence(value string) string {
-	value = strings.TrimSpace(value)
-	if len(value) <= maxTaskEvidenceBytes {
-		return value
-	}
-	limit := maxTaskEvidenceBytes - 3
-	for limit > 0 && !utf8.RuneStart(value[limit]) {
-		limit--
-	}
-	return strings.TrimSpace(value[:limit]) + "..."
-}
-
-var explicitConstraintPatterns = []*regexp.Regexp{
-	regexp.MustCompile(`(?i)\bprefer(?:s|red|ring)?\s+\w`),
-	regexp.MustCompile(`(?i)\bdon'?t want\b`),
-	regexp.MustCompile(`(?i)\balways (?:use|do|run|prefer|keep|make|format|write|add|set|put|prefix|start|include|append)\b`),
-	regexp.MustCompile(`(?i)\bnever (?:use|do|run|push|commit|write|ignore|add|set|put|remove|delete|include|deploy)\b`),
-	regexp.MustCompile(`(?i)\bplease (?:use|avoid|keep|make|don'?t|do not|format|write)\b`),
-	regexp.MustCompile(`(?i)\b(?:style|format|language|naming)\s*[:=]\s*\S`),
-}
-
-func extractExplicitConstraints(text string) []string {
-	var constraints []string
-	for _, line := range strings.Split(text, "\n") {
-		line = strings.TrimSpace(line)
-		if len(line) < 5 || len(line) > 200 || strings.HasSuffix(line, "?") || strings.Contains(line, "?...") {
-			continue
-		}
-		for _, pattern := range explicitConstraintPatterns {
-			if pattern.MatchString(line) {
-				constraints = appendBoundedUnique(constraints, line, maxTaskConstraints)
-				break
-			}
-		}
-		if len(constraints) == maxTaskConstraints {
-			break
-		}
-	}
-	return constraints
-}
-
-func appendBounded[T any](values []T, value T, limit int) []T {
-	values = append(values, value)
-	if len(values) > limit {
-		values = values[len(values)-limit:]
-	}
-	return values
-}
-
-func appendBoundedUnique[T comparable](values []T, value T, limit int) []T {
-	filtered := values[:0]
-	for _, existing := range values {
-		if existing != value {
-			filtered = append(filtered, existing)
-		}
-	}
-	return appendBounded(filtered, value, limit)
-}
-
-func hasTaskFailure(values []taskFailureState, key string) bool {
-	for _, value := range values {
-		if value.Key == key {
-			return true
-		}
-	}
-	return false
-}
-
-func removeTaskFailure(values []taskFailureState, key string) []taskFailureState {
-	out := values[:0]
-	for _, value := range values {
-		if value.Key != key {
-			out = append(out, value)
-		}
-	}
-	return out
-}
-
-func removeString(values []string, target string) []string {
-	out := make([]string, 0, len(values))
-	for _, value := range values {
-		if value != target {
-			out = append(out, value)
-		}
-	}
-	return out
-}
-
 // observePlanParity compares only the latest plan projection with the plan tool
 // calls still present in messages. It mutates the snapshot and emits when the
 // parity value changes; objective, tool, and verification fields are not part of

internal/agent/task_state_test.go

@@ -115,68 +115,6 @@ func TestTaskStateSnapshotIsImmutable(t *testing.T) {
 	}
 }
 
-func TestTaskStateRecordsDurableRuntimeEvidence(t *testing.T) {
-	state := newTaskState("Please keep the change focused.\nNever commit generated reports.", nil)
-	arguments := `{"cmd":"go test ./internal/agent"}`
-	state.observe(taskStateEvent{kind: taskStateEventToolResult, arguments: arguments, toolResult: ToolResult{
-		ToolCallID: "test-1", Name: "exec_command", Status: tools.StatusError,
-		Output: "Error: TestResumeRetainsState failed\nfull diagnostic",
-		Meta:   map[string]string{"spill_path": ".zero/artifacts/test-1.txt"},
-	}})
-	state.observe(taskStateEvent{kind: taskStateEventPermission, permission: PermissionEvent{
-		ToolName: "exec_command", DecisionAction: PermissionDecisionAllowForSession,
-		Scope: "/tmp", DecisionReason: "write a temporary fixture",
-	}})
-
-	snapshot := state.snapshot()
-	if !reflect.DeepEqual(snapshot.Constraints, []string{"Please keep the change focused.", "Never commit generated reports."}) {
-		t.Fatalf("unexpected explicit constraints: %#v", snapshot.Constraints)
-	}
-	if len(snapshot.UnresolvedFailures) != 1 || snapshot.UnresolvedFailures[0].Command != "go test ./internal/agent" || snapshot.UnresolvedFailures[0].Summary != "Error: TestResumeRetainsState failed" {
-		t.Fatalf("unexpected failure evidence: %#v", snapshot.UnresolvedFailures)
-	}
-	if len(snapshot.Artifacts) != 1 || snapshot.Artifacts[0].Path != ".zero/artifacts/test-1.txt" {
-		t.Fatalf("unexpected artifact evidence: %#v", snapshot.Artifacts)
-	}
-	if len(snapshot.Approvals) != 1 || snapshot.Approvals[0].Decision != PermissionDecisionAllowForSession || snapshot.Approvals[0].Scope != "/tmp" {
-		t.Fatalf("unexpected approval evidence: %#v", snapshot.Approvals)
-	}
-	state.observe(taskStateEvent{kind: taskStateEventToolResult, arguments: `{"path":"a.go"}`, toolResult: ToolResult{
-		ToolCallID: "read-a", Name: "read_file", Status: tools.StatusError, Output: "Error: a.go is unavailable",
-	}})
-	state.observe(taskStateEvent{kind: taskStateEventToolResult, arguments: `{"path":"b.go"}`, toolResult: ToolResult{
-		ToolCallID: "read-b", Name: "read_file", Status: tools.StatusOK, Output: "package b",
-	}})
-	if failures := state.snapshot().UnresolvedFailures; len(failures) != 2 || failures[1].Summary != "Error: a.go is unavailable" {
-		t.Fatalf("success for a different target resolved the wrong failure: %#v", failures)
-	}
-
-	state.observe(taskStateEvent{kind: taskStateEventToolResult, arguments: arguments, toolResult: ToolResult{
-		ToolCallID: "test-2", Name: "exec_command", Status: tools.StatusOK, Output: "ok",
-	}})
-	if failures := state.snapshot().UnresolvedFailures; len(failures) != 1 || failures[0].Summary != "Error: a.go is unavailable" {
-		t.Fatalf("successful retry did not resolve only its matching failure: %#v", failures)
-	}
-	state.observe(taskStateEvent{kind: taskStateEventToolResult, arguments: `{"path":"a.go"}`, toolResult: ToolResult{
-		ToolCallID: "read-a-2", Name: "read_file", Status: tools.StatusOK, Output: "package a",
-	}})
-	if failures := state.snapshot().UnresolvedFailures; len(failures) != 0 {
-		t.Fatalf("successful non-command retry did not resolve its matching failure: %#v", failures)
-	}
-	state.observe(taskStateEvent{kind: taskStateEventToolResult, arguments: `{"path":"a.go"}`, toolResult: ToolResult{
-		ToolCallID: "read-a-3", Name: "read_file", Status: tools.StatusError, Output: "Error: a.go failed again",
-	}})
-	snapshot = state.snapshot()
-	if len(snapshot.UnresolvedFailures) != 1 || snapshot.UnresolvedFailures[0].Summary != "Error: a.go failed again" {
-		t.Fatalf("a failure recurring after success was hidden: %#v", snapshot.UnresolvedFailures)
-	}
-	for _, key := range snapshot.ResolvedFailureKeys {
-		if key == snapshot.UnresolvedFailures[0].Key {
-			t.Fatalf("recurring failure retained a stale resolved key: %#v", snapshot.ResolvedFailureKeys)
-		}
-	}
-}
-
 func TestTaskStatePlanParityUsesLatestPlan(t *testing.T) {
 	state := newTaskState("objective", nil)
 	state.observe(taskStateEvent{kind: taskStateEventPlan, arguments: `{"plan":[{"content":"old","status":"completed"}]}`})

internal/agent/types.go

@@ -79,7 +79,6 @@ type ToolResult struct {
 	// command execution; callers must not schedule per-file work from them.
 	ChangeSummaries []execution.Change
 	Display         tools.Display
-	Outcome         tools.ToolOutcome
 	// DenialReason categorizes why a tool call was blocked (empty when it ran).
 	// It lets a surface distinguish the cause precisely instead of parsing Output.
 	DenialReason DenialCategory
@@ -100,24 +99,6 @@ type ToolResult struct {
 	RequestedModel string
 }
 
-// ModelOutput returns the bounded provider-facing result while preserving
-// compatibility with synthetic and restored results created before outcomes
-// were finalized.
-func (result ToolResult) ModelOutput() string {
-	if result.Outcome.Finalized() {
-		return result.Outcome.ModelView
-	}
-	return result.Output
-}
-
-// HumanDisplay returns the presentation intended for interactive surfaces.
-func (result ToolResult) HumanDisplay() tools.Display {
-	if result.Outcome.Finalized() {
-		return result.Outcome.HumanView
-	}
-	return result.Display
-}
-
 // DenialCategory classifies why a tool call was blocked before it executed.
 type DenialCategory string
 
@@ -352,11 +333,9 @@ type Options struct {
 	// specialist child process emits while running. The toolCallID identifies
 	// which Task tool call the progress belongs to. nil is a no-op.
 	OnToolProgress func(toolCallID string, event streamjson.Event)
-	// OnContext, when set, is called for each main agent request with its
-	// per-category context budget, including a replacement request after
-	// compaction or a stall retry. Internal summarizer requests are excluded so
-	// surfaces keep showing the active conversation budget. Opt-in like the other
-	// callbacks; nil is a no-op.
+	// OnContext, when set, is called once per turn with the per-category context
+	// budget of the request about to be sent, so a surface (TUI/CLI) can show
+	// context utilization. Opt-in like the other callbacks; nil is a no-op.
 	OnContext func(ContextBreakdown)
 	// ModelSwitcher, when set, lets a tool escalate the run to a stronger model
 	// mid-run: the loop calls it with the requested model id and, on success,

internal/cli/exec_writer.go

@@ -142,15 +142,13 @@ func (writer *execEventWriter) checkpoint(event sessions.Event) {
 }
 
 func (writer *execEventWriter) toolResult(result agent.ToolResult) {
-	modelOutput := result.ModelOutput()
-	display := result.HumanDisplay()
 	if writer.format == execOutputJSON {
 		payload := map[string]any{
 			"type":         "tool_result",
 			"tool_call_id": result.ToolCallID,
 			"name":         result.Name,
 			"status":       string(result.Status),
-			"output":       modelOutput,
+			"output":       result.Output,
 		}
 		if len(result.Meta) > 0 {
 			payload["meta"] = result.Meta
@@ -164,14 +162,14 @@ func (writer *execEventWriter) toolResult(result agent.ToolResult) {
 		if len(result.ChangedFiles) > 0 {
 			payload["changed_files"] = result.ChangedFiles
 		}
-		if display.Summary != "" || display.Kind != "" {
-			payload["display"] = map[string]string{"summary": display.Summary, "kind": display.Kind}
+		if result.Display.Summary != "" || result.Display.Kind != "" {
+			payload["display"] = map[string]string{"summary": result.Display.Summary, "kind": result.Display.Kind}
 		}
 		writer.writeJSON(payload)
 		return
 	}
 	if writer.format == execOutputStreamJSON {
-		output, surfaceTruncated := truncateForStreamJSONOutput(modelOutput)
+		output, surfaceTruncated := truncateForStreamJSONOutput(result.Output)
 		truncated := result.Truncated || surfaceTruncated
 		event := streamjson.Event{
 			Type:         streamjson.EventToolResult,
@@ -188,13 +186,13 @@ func (writer *execEventWriter) toolResult(result agent.ToolResult) {
 			redacted := true
 			event.Redacted = &redacted
 		}
-		if display.Summary != "" || display.Kind != "" {
-			event.Display = &streamjson.Display{Summary: display.Summary, Kind: display.Kind}
+		if result.Display.Summary != "" || result.Display.Kind != "" {
+			event.Display = &streamjson.Display{Summary: result.Display.Summary, Kind: result.Display.Kind}
 		}
 		writer.writeStreamJSON(event)
 		return
 	}
-	writer.writeStderr("[result] " + truncateForStatus(modelOutput) + "\n")
+	writer.writeStderr("[result] " + truncateForStatus(result.Output) + "\n")
 }
 
 func (writer *execEventWriter) permission(event agent.PermissionEvent) {

internal/sessions/replay.go

@@ -7,7 +7,6 @@ import (
 	"unicode/utf8"
 
 	"github.com/Gitlawb/zero/internal/redaction"
-	"github.com/Gitlawb/zero/internal/zeroruntime"
 )
 
 type EventRef struct {
@@ -38,7 +37,6 @@ type RewindPlan struct {
 type CompactionOptions struct {
 	PreserveLast   int
 	MaxPromptChars int
-	SkipPrompt     bool
 }
 
 type CompactionPlan struct {
@@ -49,9 +47,8 @@ type CompactionPlan struct {
 	CompactableEvents []EventRef `json:"compactableEvents"`
 	PreservedEvents   []EventRef `json:"preservedEvents"`
 	SummaryPrompt     string     `json:"summaryPrompt"`
-	// PromptChars counts prompt text content and excludes provider protocol framing.
-	PromptChars int  `json:"promptChars"`
-	Truncated   bool `json:"truncated,omitempty"`
+	PromptChars       int        `json:"promptChars"`
+	Truncated         bool       `json:"truncated,omitempty"`
 }
 
 type RecordCompactionInput struct {
@@ -167,11 +164,7 @@ func (store *Store) PlanCompaction(sessionID string, options CompactionOptions)
 	}
 	compactable := events[:split]
 	preserved := events[split:]
-	prompt := ""
-	truncated := false
-	if !options.SkipPrompt {
-		prompt, truncated = buildCompactionPrompt(compactable, maxPromptChars)
-	}
+	prompt, truncated := buildCompactionPrompt(compactable, maxPromptChars)
 	return CompactionPlan{
 		SessionID:         sessionID,
 		PreserveLast:      preserveLast,
@@ -319,88 +312,6 @@ func buildCompactionPrompt(events []Event, maxChars int) (string, bool) {
 	return prompt, false
 }
 
-// CompactionMessages converts durable session events into the same normalized
-// message shape used by the running agent's compaction pipeline. Provider usage
-// and checkpoint blobs are omitted. Message/tool fields rely on the session
-// writer's invariant that tool output is scrubbed before persistence;
-// ask_user answers and generic event previews are redacted here.
-func CompactionMessages(events []Event) []zeroruntime.Message {
-	messages := make([]zeroruntime.Message, 0, len(events))
-	for _, event := range events {
-		var payload map[string]any
-		_ = json.Unmarshal(event.Payload, &payload)
-		stringField := func(key string) string {
-			value, _ := payload[key].(string)
-			return strings.TrimSpace(value)
-		}
-		switch event.Type {
-		case EventMessage:
-			role := strings.ToLower(stringField("role"))
-			content := stringField("content")
-			switch role {
-			case "user":
-				messages = append(messages, zeroruntime.Message{Role: zeroruntime.MessageRoleUser, Content: content})
-			case "assistant":
-				messages = append(messages, zeroruntime.Message{Role: zeroruntime.MessageRoleAssistant, Content: content})
-			case "ask_user_answers":
-				if answers, ok := payload["answers"]; ok {
-					encoded, _ := json.Marshal(answers)
-					messages = append(messages, zeroruntime.Message{Role: zeroruntime.MessageRoleUser, Content: "User answers: " + redaction.RedactString(string(encoded), redaction.Options{})})
-				}
-			default:
-				if content != "" {
-					messages = append(messages, zeroruntime.Message{Role: zeroruntime.MessageRoleUser, Content: content})
-				}
-			}
-		case EventToolCall:
-			messages = append(messages, zeroruntime.Message{Role: zeroruntime.MessageRoleAssistant, ToolCalls: []zeroruntime.ToolCall{{
-				ID: firstSessionString(stringField("toolCallId"), stringField("id")), Name: firstSessionString(stringField("name"), stringField("toolName")), Arguments: stringField("arguments"),
-			}}})
-		case EventToolResult:
-			status := strings.ToLower(stringField("status"))
-			messages = append(messages, zeroruntime.Message{
-				Role: zeroruntime.MessageRoleTool, ToolCallID: firstSessionString(stringField("toolCallId"), stringField("id")),
-				Content: stringField("output"), IsError: status != "" && status != "ok", ChangedFiles: sessionStringSlice(payload["changedFiles"]),
-			})
-		case EventCompaction:
-			if summary := stringField("summary"); summary != "" {
-				messages = append(messages, zeroruntime.Message{Role: zeroruntime.MessageRoleUser, Content: "[Summary of earlier conversation]\n" + summary})
-			}
-		case EventProviderUsage, EventSessionCheckpoint:
-			continue
-		default:
-			preview := shapedPayloadPreview(event)
-			if strings.TrimSpace(preview) != "" && preview != "{}" {
-				messages = append(messages, zeroruntime.Message{Role: zeroruntime.MessageRoleUser, Content: fmt.Sprintf("[%s] %s", event.Type, preview)})
-			}
-		}
-	}
-	return messages
-}
-
-func firstSessionString(values ...string) string {
-	for _, value := range values {
-		if strings.TrimSpace(value) != "" {
-			return strings.TrimSpace(value)
-		}
-	}
-	return ""
-}
-
-func sessionStringSlice(value any) []string {
-	raw, ok := value.([]any)
-	if !ok {
-		return nil
-	}
-	values := make([]string, 0, len(raw))
-	for _, item := range raw {
-		if text, ok := item.(string); ok && strings.TrimSpace(text) != "" {
-			values = append(values, strings.TrimSpace(text))
-		}
-	}
-	return values
-}
-
 func shapedPayloadPreview(event Event) string {
 	switch event.Type {
 	case EventPermission, EventPermissionRequest, EventPermissionDecision:

internal/sessions/replay_test.go

@@ -5,27 +5,8 @@ import (
 	"strings"
 	"testing"
 	"time"
-
-	"github.com/Gitlawb/zero/internal/zeroruntime"
 )
 
-func TestCompactionMessagesPreservesInteractiveAndMutationEvidence(t *testing.T) {
-	events := []Event{
-		{Type: EventToolCall, Payload: json.RawMessage(`{"id":"ask","name":"ask_user","arguments":"{\"questions\":[{\"question\":\"Which database?\"}]}"}`)},
-		{Type: EventToolResult, Payload: json.RawMessage(`{"toolCallId":"ask","name":"ask_user","status":"ok","output":"Postgres only"}`)},
-		{Type: EventToolCall, Payload: json.RawMessage(`{"id":"patch","name":"apply_patch","arguments":"{\"patch\":\"*** Update File: db.go\"}"}`)},
-		{Type: EventToolResult, Payload: json.RawMessage(`{"toolCallId":"patch","name":"apply_patch","status":"ok","output":"Done!","changedFiles":["db.go"]}`)},
-	}
-
-	messages := CompactionMessages(events)
-	if len(messages) != 4 || messages[0].Role != zeroruntime.MessageRoleAssistant || messages[1].Role != zeroruntime.MessageRoleTool {
-		t.Fatalf("unexpected normalized compaction messages: %#v", messages)
-	}
-	if messages[1].Content != "Postgres only" || len(messages[3].ChangedFiles) != 1 || messages[3].ChangedFiles[0] != "db.go" {
-		t.Fatalf("interactive or mutation evidence was lost: %#v", messages)
-	}
-}
-
 func TestStorePlansRewindBySequence(t *testing.T) {
 	store := NewStore(StoreOptions{RootDir: t.TempDir(), Now: sequenceClock([]time.Time{
 		time.Date(2026, 6, 6, 10, 0, 0, 0, time.UTC),
@@ -149,26 +130,6 @@ func TestStorePlansCompactionWindow(t *testing.T) {
 	}
 }
 
-func TestStoreCanPlanCompactionWithoutBuildingLegacyPrompt(t *testing.T) {
-	store := NewStore(StoreOptions{RootDir: t.TempDir()})
-	session, err := store.Create(CreateInput{SessionID: "compactnoprompt"})
-	if err != nil {
-		t.Fatal(err)
-	}
-	for _, content := range []string{"one", "two", "three"} {
-		if _, err := store.AppendEvent(session.SessionID, AppendEventInput{Type: EventMessage, Payload: map[string]string{"content": content}}); err != nil {
-			t.Fatal(err)
-		}
-	}
-	plan, err := store.PlanCompaction(session.SessionID, CompactionOptions{PreserveLast: 1, SkipPrompt: true})
-	if err != nil {
-		t.Fatal(err)
-	}
-	if plan.CompactableCount != 2 || plan.SummaryPrompt != "" || plan.PromptChars != 0 || plan.Truncated {
-		t.Fatalf("unexpected prompt-free plan: %#v", plan)
-	}
-}
-
 func TestStoreCompactionShapesSensitivePermissionEvents(t *testing.T) {
 	secret := "sk-proj-abcdefghijklmnopqrstuvwxyz"
 	store := NewStore(StoreOptions{RootDir: t.TempDir()})

internal/tools/output_boundary.go

@@ -99,18 +99,15 @@ func selfManagedOutputBudget(toolName string, args map[string]any) outputBudget
 // newly combined result so hooks cannot bypass the established safety ceiling.
 func (registry *Registry) RebudgetAfterHook(toolName string, args map[string]any, result Result) Result {
 	result = scrubResultSecrets(result)
-	boundaryOutput := result.Output
 	tool, _ := registry.Get(toolName)
 	if _, ok := tool.(selfBudgeting); ok {
 		// Match the primary registry boundary: self-managed tools keep their
 		// call-specific capture/output budget instead of being tightened or
 		// loosened to the generic registry ceiling after hook feedback.
-		result = applySelfManagedOutputBudget(tool, toolName, args, result)
-		return finalizeToolOutcome(result, boundaryOutput)
+		return applySelfManagedOutputBudget(tool, toolName, args, result)
 	}
 	result = applyRegistryOutputBudget(tool, toolName, args, result)
-	result = enforceOutputCeiling(toolName, result)
-	return finalizeToolOutcome(result, boundaryOutput)
+	return enforceOutputCeiling(toolName, result)
 }
 
 func registryOutputBudget(toolName string) outputBudget {

internal/tools/registry.go

@@ -143,7 +143,6 @@ func (registry *Registry) RunWithOptions(ctx context.Context, name string, args
 	var ok bool
 	defer func() {
 		result = scrubResultSecrets(result)
-		boundaryOutput := result.Output
 		result = reduceCommandOutput(name, args, result)
 		if selfManagedOutput {
 			result = applySelfManagedOutputBudget(tool, name, args, result)
@@ -151,7 +150,6 @@ func (registry *Registry) RunWithOptions(ctx context.Context, name string, args
 			result = applyRegistryOutputBudget(tool, name, args, result)
 			result = enforceOutputCeiling(name, result)
 		}
-		result = finalizeToolOutcome(result, boundaryOutput)
 		if commitFileObservation {
 			result = registry.CommitFileObservation(result, options.FileTracker)
 		}

internal/tools/tool_outcome.go

@@ -1,115 +0,0 @@
-package tools
-
-import (
-	"encoding/json"
-	"strings"
-)
-
-const humanOutcomePreviewBytes = 8 * 1024
-
-type serializedToolOutcome struct {
-	ModelView   string             `json:"modelView,omitempty"`
-	HumanView   Display            `json:"humanView,omitempty"`
-	Artifact    *ToolArtifact      `json:"artifact,omitempty"`
-	Diagnostics OutcomeDiagnostics `json:"diagnostics,omitempty"`
-	Finalized   bool               `json:"finalized,omitempty"`
-}
-
-// MarshalJSON preserves the private finalized marker without making outcome
-// state mutable to callers.
-func (outcome ToolOutcome) MarshalJSON() ([]byte, error) {
-	return json.Marshal(serializedToolOutcome{
-		ModelView:   outcome.ModelView,
-		HumanView:   outcome.HumanView,
-		Artifact:    outcome.Artifact,
-		Diagnostics: outcome.Diagnostics,
-		Finalized:   outcome.finalized,
-	})
-}
-
-// UnmarshalJSON restores the finalized marker used to select canonical views.
-func (outcome *ToolOutcome) UnmarshalJSON(data []byte) error {
-	var serialized serializedToolOutcome
-	if err := json.Unmarshal(data, &serialized); err != nil {
-		return err
-	}
-	outcome.ModelView = serialized.ModelView
-	outcome.HumanView = serialized.HumanView
-	outcome.Artifact = serialized.Artifact
-	outcome.Diagnostics = serialized.Diagnostics
-	outcome.finalized = serialized.Finalized
-	return nil
-}
-
-// finalizeToolOutcome is the single seam between tool execution and its three
-// consumers: provider context, human presentation, and recoverable artifacts.
-// boundaryOutput must already be redacted. It is the text seen immediately
-// before command reduction and semantic budgeting.
-func finalizeToolOutcome(result Result, boundaryOutput string) Result {
-	previous := result.Outcome
-	human := result.Display
-	if human.Preview == "" && result.Meta["command_output_reduced"] == "true" {
-		human.Preview = boundedHumanOutcomePreview(boundaryOutput, result.Meta["spill_path"])
-	}
-	// A tool-provided success preview (for example, a prospective file diff)
-	// must not hide the actual error. Command reduction is different: its
-	// preview is the redacted execution output containing that same failure plus
-	// the evidence omitted from the model view.
-	if result.Status == StatusError && result.Meta["command_output_reduced"] != "true" {
-		human.Preview = ""
-	}
-
-	originalBytes := len(boundaryOutput)
-	originalTokens := estimateOutputTokens(boundaryOutput)
-	if previous.Finalized() {
-		originalBytes = previous.Diagnostics.OriginalBytes
-		originalTokens = previous.Diagnostics.EstimatedOriginalTokens
-	}
-	modelBytes := len(result.Output)
-	modelTokens := estimateOutputTokens(result.Output)
-
-	var artifact *ToolArtifact
-	if previous.Finalized() {
-		artifact = previous.Artifact
-	}
-	if path := strings.TrimSpace(result.Meta["spill_path"]); path != "" {
-		if artifact == nil || artifact.Path != path {
-			artifact = &ToolArtifact{
-				Path:               path,
-				CompleteAtBoundary: result.Meta["command_output_reduced"] == "true" || result.Meta[outputBudgetSpillCreatedMeta] == "true",
-			}
-		}
-	}
-
-	result.Display = human
-	result.Outcome = ToolOutcome{
-		ModelView: result.Output,
-		HumanView: human,
-		Artifact:  artifact,
-		Diagnostics: OutcomeDiagnostics{
-			Category:                result.Meta[outputBudgetCategoryMeta],
-			OriginalBytes:           originalBytes,
-			ModelBytes:              modelBytes,
-			EstimatedOriginalTokens: originalTokens,
-			EstimatedModelTokens:    modelTokens,
-			Truncated:               result.Truncated,
-			Redacted:                result.Redacted,
-			Reason:                  result.Meta["truncation_reason"],
-		},
-		finalized: true,
-	}
-	return result
-}
-
-func boundedHumanOutcomePreview(output string, artifactPath string) string {
-	if len(output) <= humanOutcomePreviewBytes {
-		return output
-	}
-	marker := "\n[zero] human preview shortened"
-	if strings.TrimSpace(artifactPath) != "" {
-		marker += "; exact output: " + artifactPath
-	}
-	marker += "\n"
-	contentBudget := max(0, humanOutcomePreviewBytes-len(marker))
-	return utf8Prefix(output, contentBudget*3/5) + marker + utf8Suffix(output, contentBudget*2/5)
-}

internal/tools/tool_outcome_test.go

@@ -1,187 +0,0 @@
-package tools
-
-import (
-	"context"
-	"os"
-	"strings"
-	"testing"
-)
-
-type outcomeErrorTool struct {
-	ceilingFakeTool
-	display Display
-}
-
-func (tool outcomeErrorTool) Run(context.Context, map[string]any) Result {
-	return Result{Status: StatusError, Output: tool.output, Display: tool.display}
-}
-
-func TestRegistryFinalizesSeparateModelHumanAndArtifactViews(t *testing.T) {
-	setTestTempDir(t)
-	lines := []string{"output:"}
-	for index := 0; index < 24; index++ {
-		lines = append(lines, "ok  \texample.test/package\t0.01s")
-	}
-	lines = append(lines, "exit_code: 0")
-	raw := strings.Join(lines, "\n")
-
-	registry := NewRegistry()
-	registry.Register(newCeilingFakeTool(ExecCommandToolName, raw))
-	result := registry.Run(context.Background(), ExecCommandToolName, map[string]any{"cmd": "go test ./..."})
-
-	if !result.Outcome.Finalized() {
-		t.Fatal("registry result did not finalize a tool outcome")
-	}
-	if result.ModelOutput() != result.Output || result.Outcome.ModelView != result.Output {
-		t.Fatalf("model representations drifted: output=%q outcome=%q", result.Output, result.Outcome.ModelView)
-	}
-	if strings.Count(result.ModelOutput(), "ok  \t") != 0 {
-		t.Fatalf("model view retained repetitive passing-package lines: %q", result.ModelOutput())
-	}
-	if !strings.Contains(result.HumanDisplay().Preview, "ok  \texample.test/package") {
-		t.Fatalf("human preview lost the raw passing-package evidence: %q", result.HumanDisplay().Preview)
-	}
-	if result.Outcome.Artifact == nil || !result.Outcome.Artifact.CompleteAtBoundary {
-		t.Fatalf("missing complete boundary artifact: %#v", result.Outcome.Artifact)
-	}
-	artifact, err := os.ReadFile(result.Outcome.Artifact.Path)
-	if err != nil {
-		t.Fatalf("read outcome artifact: %v", err)
-	}
-	if string(artifact) != raw {
-		t.Fatal("outcome artifact differs from the exact boundary output")
-	}
-	diagnostics := result.Outcome.Diagnostics
-	if diagnostics.OriginalBytes != len(raw) || diagnostics.ModelBytes != len(result.Output) {
-		t.Fatalf("incorrect outcome byte diagnostics: %#v", diagnostics)
-	}
-	if diagnostics.EstimatedModelTokens >= diagnostics.EstimatedOriginalTokens {
-		t.Fatalf("expected reduced model view: %#v", diagnostics)
-	}
-}
-
-func TestRegistryOutcomeRedactsModelHumanAndArtifactViews(t *testing.T) {
-	setTestTempDir(t)
-	secret := "ghp_" + strings.Repeat("s", 36)
-	raw := "output:\n" + secret + "\n" + strings.Repeat("ok  \texample.test/package\t0.01s\n", 24) + "exit_code: 0"
-
-	registry := NewRegistry()
-	registry.Register(newCeilingFakeTool(ExecCommandToolName, raw))
-	result := registry.Run(context.Background(), ExecCommandToolName, map[string]any{"cmd": "go test ./..."})
-
-	if !result.Outcome.Diagnostics.Redacted {
-		t.Fatal("outcome did not record redaction")
-	}
-	for name, value := range map[string]string{
-		"model": result.ModelOutput(),
-		"human": result.HumanDisplay().Preview,
-	} {
-		if strings.Contains(value, secret) {
-			t.Fatalf("%s view leaked secret", name)
-		}
-	}
-	artifact, err := os.ReadFile(result.Outcome.Artifact.Path)
-	if err != nil {
-		t.Fatalf("read outcome artifact: %v", err)
-	}
-	if strings.Contains(string(artifact), secret) {
-		t.Fatal("artifact leaked secret")
-	}
-}
-
-func TestDirectToolResultUsesLegacyViewFallbacks(t *testing.T) {
-	result := Result{
-		Output:  "direct output",
-		Display: Display{Summary: "direct summary"},
-	}
-	if result.Outcome.Finalized() {
-		t.Fatal("direct result unexpectedly finalized")
-	}
-	if result.ModelOutput() != result.Output || result.HumanDisplay() != result.Display {
-		t.Fatalf("direct result fallbacks changed: %#v", result)
-	}
-}
-
-func TestRebudgetAfterHookPreservesExecutionArtifactAndRefreshesModelView(t *testing.T) {
-	setTestTempDir(t)
-	raw := "output:\n" + strings.Repeat("ok  \texample.test/package\t0.01s\n", 24) + "exit_code: 0"
-	registry := NewRegistry()
-	registry.Register(newCeilingFakeTool(ExecCommandToolName, raw))
-	result := registry.Run(context.Background(), ExecCommandToolName, map[string]any{"cmd": "go test ./..."})
-	artifact := result.Outcome.Artifact
-	originalBytes := result.Outcome.Diagnostics.OriginalBytes
-
-	result.Output += "\nafter-hook diagnostic"
-	result = registry.RebudgetAfterHook(ExecCommandToolName, map[string]any{"cmd": "go test ./..."}, result)
-
-	if result.Outcome.Artifact != artifact {
-		t.Fatalf("rebudget replaced the execution artifact: before=%#v after=%#v", artifact, result.Outcome.Artifact)
-	}
-	if result.Outcome.Diagnostics.OriginalBytes != originalBytes {
-		t.Fatalf("rebudget lost original execution size: before=%d after=%d", originalBytes, result.Outcome.Diagnostics.OriginalBytes)
-	}
-	if !strings.Contains(result.ModelOutput(), "after-hook diagnostic") {
-		t.Fatalf("rebudget did not refresh model view: %q", result.ModelOutput())
-	}
-}
-
-func TestToolOutcomeCorpusMetrics(t *testing.T) {
-	setTestTempDir(t)
-	totalOriginalTokens := 0
-	totalModelTokens := 0
-	for _, testCase := range commandReducerCorpus() {
-		t.Run(testCase.name, func(t *testing.T) {
-			registry := NewRegistry()
-			registry.Register(newCeilingFakeTool(ExecCommandToolName, testCase.output))
-			result := registry.Run(context.Background(), ExecCommandToolName, map[string]any{"cmd": testCase.command})
-
-			if !result.Outcome.Finalized() || result.Outcome.Artifact == nil {
-				t.Fatalf("corpus result lacks a finalized recoverable outcome: %#v", result.Outcome)
-			}
-			if result.HumanDisplay().Preview != testCase.output {
-				t.Fatal("bounded corpus output was not preserved exactly for the human view")
-			}
-			diagnostics := result.Outcome.Diagnostics
-			totalOriginalTokens += diagnostics.EstimatedOriginalTokens
-			totalModelTokens += diagnostics.EstimatedModelTokens
-			t.Logf("original_tokens=%d model_tokens=%d human_bytes=%d artifact_complete=%t",
-				diagnostics.EstimatedOriginalTokens,
-				diagnostics.EstimatedModelTokens,
-				len(result.HumanDisplay().Preview),
-				result.Outcome.Artifact.CompleteAtBoundary,
-			)
-		})
-	}
-	if totalModelTokens >= totalOriginalTokens {
-		t.Fatalf("outcome corpus did not reduce model context: original=%d model=%d", totalOriginalTokens, totalModelTokens)
-	}
-	t.Logf("aggregate original_tokens=%d model_tokens=%d reduction_pct=%d",
-		totalOriginalTokens,
-		totalModelTokens,
-		100*(totalOriginalTokens-totalModelTokens)/totalOriginalTokens,
-	)
-}
-
-func TestErrorOutcomeUsesRawCommandEvidenceButDropsUnrelatedPreview(t *testing.T) {
-	setTestTempDir(t)
-	raw := "output:\n" + strings.Repeat("ok  \texample.test/package\t0.01s\n", 24) +
-		"--- FAIL: TestImportant\nexpected 7, got 9\nFAIL\nexit_code: 1"
-
-	registry := NewRegistry()
-	registry.Register(outcomeErrorTool{ceilingFakeTool: newCeilingFakeTool(ExecCommandToolName, raw)})
-	result := registry.Run(context.Background(), ExecCommandToolName, map[string]any{"cmd": "go test ./..."})
-	if !strings.Contains(result.HumanDisplay().Preview, "TestImportant") ||
-		!strings.Contains(result.HumanDisplay().Preview, "ok  \texample.test/package") {
-		t.Fatalf("error outcome lost raw command evidence: %q", result.HumanDisplay().Preview)
-	}
-
-	registry = NewRegistry()
-	registry.Register(outcomeErrorTool{
-		ceilingFakeTool: newCeilingFakeTool("write_failure", "Error: permission denied"),
-		display:         Display{Preview: "prospective diff must not hide error"},
-	})
-	result = registry.Run(context.Background(), "write_failure", map[string]any{})
-	if result.HumanDisplay().Preview != "" {
-		t.Fatalf("ordinary error retained an unrelated preview: %q", result.HumanDisplay().Preview)
-	}
-}

internal/tools/types.go

@@ -126,73 +126,11 @@ type Result struct {
 	ChangeSummaries []execution.Change
 	// Display carries a short, structured summary for the TUI / stream.
 	Display Display
-	// Outcome is the finalized, typed representation produced at the registry
-	// seam. ModelView, HumanView, and Artifact deliberately serve different
-	// consumers; Output, Display, and spill metadata remain synchronized for
-	// compatibility with direct tool callers and persisted sessions.
-	Outcome ToolOutcome
 	// pendingFileObservation is proposed by read_file and committed only after
 	// the final model-visible output boundary confirms the exact content survived.
 	pendingFileObservation *pendingFileObservation
 }
 
-// ToolOutcome is the canonical post-execution representation of one tool
-// result. It separates the bounded provider payload from the human-facing
-// presentation and the recoverable output retained outside model context.
-type ToolOutcome struct {
-	ModelView   string
-	HumanView   Display
-	Artifact    *ToolArtifact
-	Diagnostics OutcomeDiagnostics
-	finalized   bool
-}
-
-// Finalized reports whether the outcome crossed the registry boundary. Direct
-// Tool.Run results deliberately return false and use their legacy fields.
-func (outcome ToolOutcome) Finalized() bool {
-	return outcome.finalized
-}
-
-// ToolArtifact identifies recoverable output saved by the tool boundary.
-// CompleteAtBoundary means the artifact contains every redacted byte received
-// by that boundary; an underlying process may already have applied its own
-// capture limit before producing the result.
-type ToolArtifact struct {
-	Path               string
-	CompleteAtBoundary bool
-}
-
-// OutcomeDiagnostics describes how the model-facing representation differs
-// from the redacted output received by the registry boundary.
-type OutcomeDiagnostics struct {
-	Category                string
-	OriginalBytes           int
-	ModelBytes              int
-	EstimatedOriginalTokens int
-	EstimatedModelTokens    int
-	Truncated               bool
-	Redacted                bool
-	Reason                  string
-}
-
-// ModelOutput returns the finalized provider-facing text, falling back to the
-// legacy field for direct Tool.Run callers that have not crossed the registry.
-func (result Result) ModelOutput() string {
-	if result.Outcome.finalized {
-		return result.Outcome.ModelView
-	}
-	return result.Output
-}
-
-// HumanDisplay returns the finalized presentation, falling back to the legacy
-// display for direct Tool.Run callers.
-func (result Result) HumanDisplay() Display {
-	if result.Outcome.finalized {
-		return result.Outcome.HumanView
-	}
-	return result.Display
-}
-
 // Display carries a short, structured summary of a tool result for the TUI/stream.
 type Display struct {
 	Summary string

internal/trace/emit.go

@@ -86,16 +86,16 @@ func WriteNDJSON(w io.Writer, t *TurnTrace) error {
 		}
 	}
 
-	// Prefix fingerprints are emitted after counters in insertion (request)
+	// Prefix fingerprints are emitted after counters in insertion (turn)
 	// order. The order is the order EmitPrefixHash was called, which is the
-	// order the agent computed each request's fingerprint, which is the
-	// order a downstream consumer needs to reconstruct prefix changes across
-	// main, compaction, and retry requests. Sorting by complete_prefix hash would
-	// destroy that sequence, so we do not
+	// order the agent loop computed each turn's fingerprint, which is the
+	// order a downstream consumer needs to correlate a prefix_hash event
+	// with the cached_input_tokens counter for that turn. Sorting by
+	// complete_prefix hash would destroy that correlation, so we do not
 	// sort. The slice is already a deep copy from Finish (see
 	// Recorder.Finish) so it is safe to range over without copying.
 	for _, p := range t.PrefixHashes {
-		obj := map[string]any{
+		if err := enc.Encode(map[string]any{
 			"type":                "prefix_hash",
 			"system_prompt":       p.SystemPromptHash,
 			"base_instructions":   p.BaseInstructionsHash,
@@ -105,11 +105,7 @@ func WriteNDJSON(w io.Writer, t *TurnTrace) error {
 			"tools":               p.ToolsHash,
 			"schema":              p.SchemaHash,
 			"complete_prefix":     p.CompletePrefixHash,
-		}
-		if p.InvalidationReason != "" {
-			obj["invalidation_reason"] = p.InvalidationReason
-		}
-		if err := enc.Encode(obj); err != nil {
+		}); err != nil {
 			return err
 		}
 	}

internal/trace/parse.go

@@ -116,7 +116,6 @@ func ReadNDJSON(r io.Reader) (*TurnTrace, error) {
 				ToolsHash:              stringField(obj, "tools"),
 				SchemaHash:             stringField(obj, "schema"),
 				CompletePrefixHash:     stringField(obj, "complete_prefix"),
-				InvalidationReason:     stringField(obj, "invalidation_reason"),
 			})
 		case "output_budget":
 			if !sawTraceHeader {

internal/trace/recorder.go

@@ -177,9 +177,9 @@ func (r *Recorder) StampFirstUsefulAction() {
 }
 
 // EmitPrefixHash records one prompt-prefix fingerprint on the trace. Multiple
-// calls are allowed within a run (one per planned provider request) and
-// accumulate in request order. The first call after Finish is a no-op; later
-// calls are also no-ops because the trace has been sealed.
+// calls are allowed within a run (one per turn, typically) and accumulate in
+// order. The first call after Finish is a no-op; later calls are also no-ops
+// because the trace has been sealed.
 func (r *Recorder) EmitPrefixHash(p PrefixHash) {
 	if r == nil {
 		return

internal/trace/trace.go

@@ -159,7 +159,6 @@ type PrefixHash struct {
 	ToolsHash              string `json:"tools"`
 	SchemaHash             string `json:"schema"`
 	CompletePrefixHash     string `json:"complete_prefix"`
-	InvalidationReason     string `json:"invalidation_reason,omitempty"`
 }
 
 // WallDuration is the total traced wall time of the run.

internal/trace/trace_test.go

@@ -382,7 +382,6 @@ func TestReadNDJSONRoundTrip(t *testing.T) {
 		ToolsHash:              "t1",
 		SchemaHash:             "x1",
 		CompletePrefixHash:     "complete1",
-		InvalidationReason:     "initial",
 	})
 	r.EmitPrefixHash(PrefixHash{
 		SystemPromptHash:       "system2",
@@ -393,7 +392,6 @@ func TestReadNDJSONRoundTrip(t *testing.T) {
 		ToolsHash:              "t2",
 		SchemaHash:             "x2",
 		CompletePrefixHash:     "complete2",
-		InvalidationReason:     "tools",
 	})
 	original := r.Finish()
 
@@ -423,8 +421,8 @@ func TestReadNDJSONRoundTrip(t *testing.T) {
 	if parsed.FirstTokenAt.IsZero() {
 		t.Fatal("first_token_at lost in round-trip")
 	}
-	// prefix_hash round-trip: two events, in insertion order, with all hash
-	// fields and the invalidation reason preserved exactly.
+	// prefix_hash round-trip: two events, in insertion order, with all
+	// seven sub-hash fields preserved exactly.
 	if len(parsed.PrefixHashes) != 2 {
 		t.Fatalf("expected 2 prefix_hash events after round-trip, got %d", len(parsed.PrefixHashes))
 	}
@@ -437,38 +435,6 @@ func TestReadNDJSONRoundTrip(t *testing.T) {
 	if parsed.PrefixHashes[1].SystemPromptHash != "system2" || parsed.PrefixHashes[1].BaseInstructionsHash != "b2" || parsed.PrefixHashes[1].SchemaHash != "x2" {
 		t.Fatalf("prefix_hash sub-hashes lost on second event: got %+v", parsed.PrefixHashes[1])
 	}
-	if parsed.PrefixHashes[0].InvalidationReason != "initial" || parsed.PrefixHashes[1].InvalidationReason != "tools" {
-		t.Fatalf("prefix invalidation reasons lost: %+v", parsed.PrefixHashes)
-	}
-}
-
-func TestWriteNDJSONOmitsEmptyPrefixInvalidationReason(t *testing.T) {
-	recorder := NewRecorder("session", "run", "test")
-	recorder.Start()
-	recorder.EmitPrefixHash(PrefixHash{CompletePrefixHash: "stable"})
-	tr := recorder.Finish()
-
-	var output bytes.Buffer
-	if err := WriteNDJSON(&output, tr); err != nil {
-		t.Fatalf("WriteNDJSON: %v", err)
-	}
-	found := false
-	for _, line := range strings.Split(strings.TrimSpace(output.String()), "\n") {
-		var event map[string]any
-		if err := json.Unmarshal([]byte(line), &event); err != nil {
-			t.Fatalf("decode event: %v", err)
-		}
-		if event["type"] != "prefix_hash" {
-			continue
-		}
-		found = true
-		if _, exists := event["invalidation_reason"]; exists {
-			t.Fatalf("empty invalidation reason should be omitted: %s", line)
-		}
-	}
-	if !found {
-		t.Fatal("prefix_hash event not written")
-	}
 }
 
 func TestReadNDJSONRejectsNonTrace(t *testing.T) {

internal/tui/model.go

@@ -5666,11 +5666,10 @@ func (m model) sendAgentUsage(runID int, modelID string, event zeroruntime.Usage
 // (a code/diff preview) when present on a successful result, else the Output that
 // the model also saw. Error results keep their Output so the failure shows.
 func toolResultDetail(result agent.ToolResult) string {
-	display := result.HumanDisplay()
-	if strings.TrimSpace(display.Preview) != "" && (result.Status != tools.StatusError || result.Outcome.Finalized()) {
-		return display.Preview
+	if result.Status != tools.StatusError && strings.TrimSpace(result.Display.Preview) != "" {
+		return result.Display.Preview
 	}
-	return result.ModelOutput()
+	return result.Output
 }
 
 func toolResultRowText(result agent.ToolResult) string {
@@ -5678,5 +5677,5 @@ func toolResultRowText(result agent.ToolResult) string {
 	if status == "" {
 		status = tools.StatusOK
 	}
-	return fmt.Sprintf("tool result: %s %s %s", result.Name, status, truncateTUIOutput(result.ModelOutput(), tuiToolOutputLimit))
+	return fmt.Sprintf("tool result: %s %s %s", result.Name, status, truncateTUIOutput(result.Output, tuiToolOutputLimit))
 }

internal/tui/session_controls.go

@@ -21,6 +21,7 @@ import (
 var responseStyles = []string{"balanced", "concise", "explanatory", "review"}
 
 const tuiCompactionPreserveLast = 8
+const tuiCompactionMaxPromptChars = 8000
 const compactStatusRowID = "compact/status"
 
 var compactFrames = []string{"⠂", "⠒", "⠲", "⠴"}
@@ -841,8 +842,8 @@ func (m model) compactActiveSession() (model, CompactResult, error) {
 	beforeEvents := append([]sessions.Event{}, m.sessionEvents...)
 	beforeTokens := estimateTranscriptTokens(m.transcript)
 	plan, err := m.sessionStore.PlanCompaction(m.activeSession.SessionID, sessions.CompactionOptions{
-		PreserveLast: tuiCompactionPreserveLast,
-		SkipPrompt:   true,
+		PreserveLast:   tuiCompactionPreserveLast,
+		MaxPromptChars: tuiCompactionMaxPromptChars,
 	})
 	if err != nil {
 		return m, CompactResult{}, err
@@ -856,26 +857,13 @@ func (m model) compactActiveSession() (model, CompactResult, error) {
 		}, nil
 	}
 
-	rawEvents, err := m.sessionStore.ReadEvents(m.activeSession.SessionID)
-	if err != nil {
-		return m, CompactResult{}, fmt.Errorf("read session events for compaction: %w", err)
-	}
-	compactableEvents, err := sessionEventsForRefs(rawEvents, plan.CompactableEvents)
+	summary, err := m.summarizeCompactionPlan(plan)
 	if err != nil {
 		return m, CompactResult{}, err
 	}
-	summaryResult, err := m.summarizeCompactionPlan(plan, sessions.CompactionMessages(compactableEvents))
-	if err != nil {
-		return m, CompactResult{}, err
-	}
-	// PromptChars counts the text content sent to the provider: the shared
-	// system instruction plus projected message/tool payloads. Provider protocol
-	// framing is intentionally excluded.
-	plan.PromptChars = len(agent.CompactionSummaryInstructions) + summaryResult.ProjectedChars
-	plan.Truncated = summaryResult.Truncated
 	if _, err := m.sessionStore.RecordCompaction(m.activeSession.SessionID, sessions.RecordCompactionInput{
 		Plan:    plan,
-		Summary: summaryResult.SummaryText,
+		Summary: summary,
 	}); err != nil {
 		return m, CompactResult{}, err
 	}
@@ -897,47 +885,32 @@ func (m model) compactActiveSession() (model, CompactResult, error) {
 		Compacted:    len(events) < len(beforeEvents)+1,
 		BeforeTokens: beforeTokens,
 		AfterTokens:  estimateTranscriptTokens(m.transcript),
-		Summary:      summaryResult.SummaryText,
+		Summary:      summary,
 	}, nil
 }
 
-func sessionEventsForRefs(events []sessions.Event, refs []sessions.EventRef) ([]sessions.Event, error) {
-	byID := make(map[string]sessions.Event, len(events))
-	for _, event := range events {
-		byID[event.ID] = event
+func (m model) summarizeCompactionPlan(plan sessions.CompactionPlan) (string, error) {
+	if m.provider == nil {
+		return deterministicCompactionSummary(plan), nil
 	}
-	selected := make([]sessions.Event, 0, len(refs))
-	for _, ref := range refs {
-		event, ok := byID[ref.ID]
-		if !ok || event.Sequence != ref.Sequence || event.Type != ref.Type {
-			return nil, fmt.Errorf("session changed while compaction was being planned; retry /compact")
-		}
-		selected = append(selected, event)
-	}
-	return selected, nil
-}
-
-func (m model) summarizeCompactionPlan(plan sessions.CompactionPlan, messages []zeroruntime.Message) (agent.CompactionSummaryResult, error) {
-	return agent.SummarizeCompactionMessages(messages, func(projected []zeroruntime.Message) (string, error) {
-		if m.provider == nil {
-			return deterministicCompactionSummary(plan), nil
-		}
-		stream, streamErr := m.provider.StreamCompletion(m.ctx, zeroruntime.CompletionRequest{
-			Messages: append([]zeroruntime.Message{{Role: zeroruntime.MessageRoleSystem, Content: agent.CompactionSummaryInstructions}}, projected...),
-		})
-		if streamErr != nil {
-			return "", fmt.Errorf("summarize compacted session: %w", streamErr)
-		}
-		collected := zeroruntime.CollectStream(m.ctx, stream)
-		if collected.Error != "" {
-			return "", fmt.Errorf("summarize compacted session: %s", collected.Error)
-		}
-		result := strings.TrimSpace(collected.Text)
-		if result == "" {
-			return "", fmt.Errorf("summarize compacted session: empty summary")
-		}
-		return result, nil
+	stream, err := m.provider.StreamCompletion(m.ctx, zeroruntime.CompletionRequest{
+		Messages: []zeroruntime.Message{
+			{Role: zeroruntime.MessageRoleSystem, Content: "Summarize compacted Zero session events for future coding context. Preserve user goals, decisions, files, tool outcomes, blockers, and exact next steps. Omit secrets and do not invent details."},
+			{Role: zeroruntime.MessageRoleUser, Content: plan.SummaryPrompt},
+		},
 	})
+	if err != nil {
+		return "", fmt.Errorf("summarize compacted session: %w", err)
+	}
+	collected := zeroruntime.CollectStream(m.ctx, stream)
+	if collected.Error != "" {
+		return "", fmt.Errorf("summarize compacted session: %s", collected.Error)
+	}
+	summary := strings.TrimSpace(collected.Text)
+	if summary == "" {
+		return "", fmt.Errorf("summarize compacted session: empty summary")
+	}
+	return summary, nil
 }
 
 func deterministicCompactionSummary(plan sessions.CompactionPlan) string {

internal/tui/session_controls_test.go

@@ -481,15 +481,6 @@ func TestCompactCommandUsesProviderSummaryWhenAvailable(t *testing.T) {
 	if err != nil {
 		t.Fatal(err)
 	}
-	for _, input := range []sessions.AppendEventInput{
-		{Type: sessions.EventToolCall, Payload: map[string]any{"id": "ask", "name": "ask_user", "arguments": `{"questions":[{"question":"Which database should remain?"}]}`}},
-		{Type: sessions.EventToolResult, Payload: map[string]any{"toolCallId": "ask", "name": "ask_user", "status": "ok", "output": "Postgres only"}},
-	} {
-		m, err = m.appendSessionEvent(input.Type, input.Payload)
-		if err != nil {
-			t.Fatal(err)
-		}
-	}
 	for _, content := range []string{
 		"old decision A",
 		"old decision B",
@@ -530,15 +521,6 @@ func TestCompactCommandUsesProviderSummaryWhenAvailable(t *testing.T) {
 	if len(provider.requests) != 1 {
 		t.Fatalf("expected one provider summarization request, got %d", len(provider.requests))
 	}
-	request := provider.requests[0]
-	if len(request.Messages) != 2 || request.Messages[0].Content != agent.CompactionSummaryInstructions {
-		t.Fatalf("manual compaction did not use the shared agent compaction prompt: %#v", request.Messages)
-	}
-	for _, want := range []string{"Which database should remain?", "Postgres only"} {
-		if !strings.Contains(request.Messages[1].Content, want) {
-			t.Fatalf("manual compaction projection lost %q: %q", want, request.Messages[1].Content)
-		}
-	}
 	if next.lastCompactResult == nil || next.lastCompactResult.Summary != "Provider summary keeps the actual old decisions." {
 		t.Fatalf("expected provider summary result, got %#v", next.lastCompactResult)
 	}
@@ -551,56 +533,6 @@ func TestCompactCommandUsesProviderSummaryWhenAvailable(t *testing.T) {
 	}
 }
 
-func TestManualCompactionPersistsStructuralTruncationMetadata(t *testing.T) {
-	store := sessions.NewStore(sessions.StoreOptions{RootDir: t.TempDir()})
-	provider := &fakeProvider{events: []zeroruntime.StreamEvent{
-		{Type: zeroruntime.StreamEventText, Content: "Bounded summary."},
-		{Type: zeroruntime.StreamEventDone},
-	}}
-	m := newModel(context.Background(), Options{ModelName: "gpt-4.1", Provider: provider, SessionStore: store})
-	var err error
-	m, err = m.ensureActiveSession("compact a large session")
-	if err != nil {
-		t.Fatal(err)
-	}
-	for index := range 20 {
-		content := strings.Repeat("contextword ", 256) + string(rune('a'+index))
-		m, err = m.appendSessionEvent(sessions.EventMessage, map[string]any{"role": "user", "content": content})
-		if err != nil {
-			t.Fatal(err)
-		}
-		m.transcript = appendTranscriptRow(m.transcript, transcriptRow{kind: rowUser, text: content})
-	}
-
-	next, result, err := m.compactActiveSession()
-	if err != nil || !result.Compacted {
-		t.Fatalf("compactActiveSession() = (%#v, %v)", result, err)
-	}
-	raw, err := store.ReadEvents(next.activeSession.SessionID)
-	if err != nil {
-		t.Fatal(err)
-	}
-	latest := raw[len(raw)-1]
-	if latest.Type != sessions.EventCompaction {
-		t.Fatalf("latest event = %s, want compaction", latest.Type)
-	}
-	payload := sessionPayload(latest)
-	if !payloadBool(payload, "truncated") {
-		t.Fatalf("compaction did not persist structural truncation: %#v", payload)
-	}
-	request := provider.requests[0]
-	wantPromptChars := len(agent.CompactionSummaryInstructions)
-	for _, message := range request.Messages[1:] {
-		wantPromptChars += len(message.Content)
-		for _, call := range message.ToolCalls {
-			wantPromptChars += len(call.Name) + len(call.Arguments)
-		}
-	}
-	if promptChars, ok := payload["promptChars"].(float64); !ok || int(promptChars) != wantPromptChars {
-		t.Fatalf("promptChars = %#v, want %d", payload["promptChars"], wantPromptChars)
-	}
-}
-
 func TestCompactCommandRecordsRequestWhenNoCompactorIsAvailable(t *testing.T) {
 	m := newModel(context.Background(), Options{})
 	m.input.SetValue("/compact")

internal/tui/tool_outcome_test.go

@@ -1,92 +0,0 @@
-package tui
-
-import (
-	"context"
-	"encoding/json"
-	"strings"
-	"testing"
-
-	"github.com/Gitlawb/zero/internal/agent"
-	"github.com/Gitlawb/zero/internal/tools"
-)
-
-type tuiOutcomeErrorTool struct {
-	output string
-}
-
-func (tool tuiOutcomeErrorTool) Name() string             { return tools.ExecCommandToolName }
-func (tool tuiOutcomeErrorTool) Description() string      { return "test tool" }
-func (tool tuiOutcomeErrorTool) Parameters() tools.Schema { return tools.Schema{Type: "object"} }
-func (tool tuiOutcomeErrorTool) Safety() tools.Safety {
-	return tools.Safety{Permission: tools.PermissionAllow}
-}
-func (tool tuiOutcomeErrorTool) Run(context.Context, map[string]any) tools.Result {
-	return tools.Result{Status: tools.StatusError, Output: tool.output}
-}
-
-func setToolOutcomeTempDir(t *testing.T) {
-	t.Helper()
-	tempDir := t.TempDir()
-	t.Setenv("TMPDIR", tempDir)
-	t.Setenv("TMP", tempDir)
-	t.Setenv("TEMP", tempDir)
-}
-
-func TestToolResultDetailUsesFinalizedHumanEvidenceForReducedError(t *testing.T) {
-	setToolOutcomeTempDir(t)
-	raw := "output:\n" + strings.Repeat("ok  \texample.test/package\t0.01s\n", 24) +
-		"--- FAIL: TestImportant\nexpected 7, got 9\nFAIL\nexit_code: 1"
-	registry := tools.NewRegistry()
-	registry.Register(tuiOutcomeErrorTool{output: raw})
-	result := registry.Run(context.Background(), tools.ExecCommandToolName, map[string]any{"cmd": "go test ./..."})
-
-	detail := toolResultDetail(agent.ToolResult{
-		Name:    tools.ExecCommandToolName,
-		Status:  result.Status,
-		Output:  result.Output,
-		Display: result.Display,
-		Outcome: result.Outcome,
-	})
-	for _, want := range []string{"ok  \texample.test/package", "TestImportant", "expected 7, got 9"} {
-		if !strings.Contains(detail, want) {
-			t.Fatalf("human error detail missing %q: %q", want, detail)
-		}
-	}
-	if detail == result.ModelOutput() {
-		t.Fatal("human detail collapsed back to the reduced model view")
-	}
-}
-
-func TestToolResultDetailSurvivesOutcomeJSONRoundTrip(t *testing.T) {
-	setToolOutcomeTempDir(t)
-	raw := "output:\n" + strings.Repeat("ok  \texample.test/package\t0.01s\n", 24) +
-		"--- FAIL: TestImportant\nexpected 7, got 9\nFAIL\nexit_code: 1"
-	registry := tools.NewRegistry()
-	registry.Register(tuiOutcomeErrorTool{output: raw})
-	toolResult := registry.Run(context.Background(), tools.ExecCommandToolName, map[string]any{"cmd": "go test ./..."})
-	original := agent.ToolResult{
-		Name:    tools.ExecCommandToolName,
-		Status:  toolResult.Status,
-		Output:  toolResult.Output,
-		Display: toolResult.Display,
-		Outcome: toolResult.Outcome,
-	}
-
-	data, err := json.Marshal(original)
-	if err != nil {
-		t.Fatalf("marshal tool result: %v", err)
-	}
-	var restored agent.ToolResult
-	if err := json.Unmarshal(data, &restored); err != nil {
-		t.Fatalf("unmarshal tool result: %v", err)
-	}
-	if !restored.Outcome.Finalized() {
-		t.Fatal("restored outcome lost its finalized state")
-	}
-	detail := toolResultDetail(restored)
-	for _, want := range []string{"ok  \texample.test/package", "TestImportant", "expected 7, got 9"} {
-		if !strings.Contains(detail, want) {
-			t.Fatalf("restored human detail missing %q: %q", want, detail)
-		}
-	}
-}

internal/zeroruntime/types.go

@@ -93,14 +93,12 @@ type ReasoningBlock struct {
 
 // Message is a normalized conversation turn passed to providers.
 type Message struct {
-	Role         MessageRole
-	Content      string
-	ToolCalls    []ToolCall
-	ToolCallID   string
-	IsError      bool             // tool-result status; ignored for non-tool messages
-	ChangedFiles []string         // durable tool-result mutation targets; ignored by providers
-	Images       []ImageBlock     // optional; nil for text-only messages
-	Reasoning    []ReasoningBlock // optional; preserved thinking blocks to replay
+	Role       MessageRole
+	Content    string
+	ToolCalls  []ToolCall
+	ToolCallID string
+	Images     []ImageBlock     // optional; nil for text-only messages
+	Reasoning  []ReasoningBlock // optional; preserved thinking blocks to replay
 }
 
 // ToolDefinition describes a model-visible tool and its JSON-schema parameters.