Add transcript-grounded structured task state

internal/agent/compaction.go

@@ -56,6 +56,10 @@ type CompactionOptions struct {
 	// injected so Compact stays pure and testable; the agent loop wires it to a
 	// real provider call.
 	Summarize func(toSummarize []zeroruntime.Message) (string, error)
+	// taskState is a snapshot supplied by the running agent. Its immutable
+	// objective is always preserved; mutable fields are admitted only when its
+	// plan projection still matches the transcript.
+	taskState *taskStateSnapshot
 }
 
 // CompactionResult is the metadata-bearing result returned by CompactMessages.
@@ -220,7 +224,7 @@ func CompactMessages(messages []zeroruntime.Message, opts CompactionOptions) (Co
 
 	// Preserve structured state (active plan + loaded skills) from the elided
 	// middle verbatim, so it is not lost or paraphrased away by the prose summary.
-	content := appendPreservedState(summaryLabel+"\n"+summary, middle)
+	content := appendPreservedState(summaryLabel+"\n"+summary, middle, opts.taskState)
 
 	compacted := make([]zeroruntime.Message, 0, systemEnd+1+(len(messages)-boundary))
 	compacted = append(compacted, messages[:systemEnd]...)
@@ -326,6 +330,7 @@ type compactionState struct {
 	// OnText is deliberately NOT forwarded (compaction stays invisible to the user),
 	// but its token COST must still be counted so usage reports and budgets include it.
 	onUsage func(Usage)
+	task    *taskState
 
 	// calibrationRatio scales the raw byte/4 token estimate toward the provider's
 	// real prompt-token count. ApproxTextTokens over-counts code-heavy content by
@@ -365,13 +370,15 @@ func (state *compactionState) calibratedTokens(raw int) int {
 	return int(float64(raw) * state.calibrationRatio)
 }
 
-func newCompactionState(options Options) *compactionState {
-	return &compactionState{
+func newCompactionState(options Options, task *taskState) *compactionState {
+	state := &compactionState{
 		enabled:      options.ContextWindow > 0,
 		threshold:    compactionThreshold(options.ContextWindow),
 		preserveLast: options.CompactionPreserveLast,
 		onUsage:      options.OnUsage,
+		task:         task,
 	}
+	return state
 }
 
 // maybeCompact runs proactive compaction at the top of a turn. It returns the
@@ -418,6 +425,7 @@ func (state *compactionState) maybeCompact(
 	compacted, err := Compact(messages, CompactionOptions{
 		PreserveLast: state.preserveLast,
 		Summarize:    summarizeClosure(ctx, provider, state.onUsage),
+		taskState:    state.task.snapshotForCompaction(messages),
 	})
 	if err != nil {
 		// Summarizer failed: keep the original history. The reactive path (or a
@@ -468,6 +476,7 @@ func (state *compactionState) recover(
 	result, compactErr := Compact(messages, CompactionOptions{
 		PreserveLast: state.preserveLast,
 		Summarize:    summarizeClosure(ctx, provider, state.onUsage),
+		taskState:    state.task.snapshotForCompaction(messages),
 	})
 	if compactErr != nil {
 		// A genuine compaction attempt was made (and failed): the budget is spent

internal/agent/compaction_preserve.go

@@ -30,6 +30,10 @@
 const (
 	maxRecentEdits   = 20
 	maxEditNoteBytes = 160
+	// maxTaskObjectiveBytes keeps the original objective recognizable after
+	// compaction without allowing an unusually large prompt to recreate the
+	// context pressure the compaction just removed.
+	maxTaskObjectiveBytes = 512
 )
 
 const (
@@ -76,32 +80,14 @@
 // ({"plan":[{content,status,...}]}) as terse status-tagged bullet lines. Returns
 // "" on malformed arguments or an empty plan.
 func formatPlanArguments(arguments string) string {
-	var parsed struct {
-		Plan []struct {
-			Content string `json:"content"`
-			Step    string `json:"step"`
-			Status  string `json:"status"`
-			Notes   string `json:"notes"`
-		} `json:"plan"`
-	}
-	if err := json.Unmarshal([]byte(strings.TrimSpace(arguments)), &parsed); err != nil {
+	plan, ok := parseTaskPlan(arguments)
+	if !ok {
 		return ""
 	}
-	lines := make([]string, 0, len(parsed.Plan))
-	for _, item := range parsed.Plan {
-		content := strings.TrimSpace(item.Content)
-		if content == "" {
-			content = strings.TrimSpace(item.Step)
-		}
-		if content == "" {
-			continue
-		}
-		status := strings.TrimSpace(item.Status)
-		if status == "" {
-			status = "pending"
-		}
-		line := "- [" + status + "] " + content
-		if notes := strings.TrimSpace(item.Notes); notes != "" {
+	lines := make([]string, 0, len(plan))
+	for _, item := range plan {
+		line := "- [" + item.Status + "] " + item.Content
+		if notes := item.Notes; notes != "" {
 			line += "\n  Notes: " + notes
 		}
 		lines = append(lines, line)
@@ -431,12 +417,25 @@
 // preservedState is the JSON shape of the carried-across-compaction block.
 type preservedState struct {
 	Plan                string                 `json:"plan,omitempty"`
+	Task                *preservedTaskState    `json:"task,omitempty"`
 	RecentEdits         []preservedEdit        `json:"recent_edits,omitempty"`
 	Tools               []preservedTool        `json:"tools,omitempty"`
 	Skills              []preservedSkill       `json:"skills,omitempty"`
 	ProjectInstructions []preservedInstruction `json:"project_instructions,omitempty"`
 }
 
+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"`
+}
+
 type preservedEdit struct {
 	Path string `json:"path"`
 	Note string `json:"note,omitempty"`
@@ -464,8 +463,27 @@
 // may live only inside the injected summary message, which on a later compaction
 // lands in middle with no real tool calls left to extract. Fresh tool calls and
 // instruction blocks override the carried-forward copy by name/source.
-func appendPreservedState(summary string, middle []zeroruntime.Message) string {
+func appendPreservedState(summary string, middle []zeroruntime.Message, taskSnapshot *taskStateSnapshot) string {
 	priorState := parsePreservedStateBlock(latestSummaryContent(middle))
+	task := priorState.Task
+	if taskSnapshot != nil {
+		task = &preservedTaskState{
+			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
+		// even after compaction removes the plan tool call needed for comparison.
+		if taskSnapshot.PlanParity == taskPlanParityMatch {
+			task.Status = taskSnapshot.Status
+			task.Pending = taskSnapshot.Plan.Pending
+			task.InProgress = taskSnapshot.Plan.InProgress
+			task.Completed = taskSnapshot.Plan.Completed
+			task.Failed = taskSnapshot.Plan.Failed
+			task.VerificationPassed = taskSnapshot.Verification.Passed
+			task.VerificationFailed = taskSnapshot.Verification.Failed
+			task.VerificationOutcome = taskSnapshot.Verification.LastOutcome
+		}
+	}
 
 	// Plan: a fresh update_plan in middle is authoritative; otherwise carry the
 	// plan preserved by an earlier compaction.
@@ -493,12 +511,25 @@
 		projectInstructionEntries(middle),
 	)
 
-	if block := formatPreservedState(plan, edits, tools, skills, instructions); block != "" {
+	if block := formatPreservedState(plan, task, edits, tools, skills, instructions); block != "" {
 		summary += "\n\n" + block
 	}
 	return summary
 }
 
+func capTaskObjective(objective string) string {
+	objective = strings.TrimSpace(objective)
+	if len(objective) <= maxTaskObjectiveBytes {
+		return objective
+	}
+	const suffix = "…"
+	limit := maxTaskObjectiveBytes - len(suffix)
+	for limit > 0 && !utf8.RuneStart(objective[limit]) {
+		limit--
+	}
+	return strings.TrimSpace(objective[:limit]) + suffix
+}
+
 // mergeRecentEdits overlays fresh edits onto edits preserved by an earlier
 // compaction. Unlike mergeSkillEntries (which keeps refreshed entries in their
 // original slot), a path touched again by a fresh edit MOVES to the newest
@@ -555,11 +586,11 @@
 
 // formatPreservedState renders state as the labelled, single-line
 // JSON block. Returns "" when there is nothing to preserve.
-func formatPreservedState(plan string, edits, tools, skills, instructions []skillEntry) string {
-	if plan == "" && len(edits) == 0 && len(tools) == 0 && len(skills) == 0 && len(instructions) == 0 {
+func formatPreservedState(plan string, task *preservedTaskState, edits, tools, skills, instructions []skillEntry) string {
+	if plan == "" && task == nil && len(edits) == 0 && len(tools) == 0 && len(skills) == 0 && len(instructions) == 0 {
 		return ""
 	}
-	state := preservedState{Plan: plan}
+	state := preservedState{Plan: plan, Task: task}
 	for _, e := range edits {
 		state.RecentEdits = append(state.RecentEdits, preservedEdit{Path: e.name, Note: e.body})
 	}
@@ -583,7 +614,7 @@
 // block. JSON escaping makes this lossless even when a skill body contains
 // markdown headings, code fences, or quotes. Returns ("", nil) when absent or
 // malformed.
 func parsePreservedState(summaryContent string) (string, []skillEntry) {
 	state := parsePreservedStateBlock(summaryContent)
 	return state.Plan, preservedSkillsToEntries(state.Skills)
 }

internal/agent/compaction_preserve_test.go

@@ -1,6 +1,7 @@
 package agent
 
 import (
+	"encoding/json"
 	"strings"
 	"testing"
 	"unicode/utf8"
@@ -59,6 +60,103 @@ func TestCompactPreservesActivePlan(t *testing.T) {
 	}
 }
 
+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"}]}`})
+	messages := stateConversation()
+	compacted, err := Compact(messages, CompactionOptions{
+		PreserveLast: 2,
+		Summarize:    func([]zeroruntime.Message) (string, error) { return "SUMMARY", nil },
+		taskState:    task.snapshotForCompaction(messages),
+	})
+	if err != nil {
+		t.Fatalf("Compact: %v", err)
+	}
+	state := parsePreservedStateBlock(compacted[1].Content)
+	if state.Task == nil || state.Task.Status != taskStatusActive || state.Task.InProgress != 1 || state.Task.Pending != 1 {
+		t.Fatalf("unexpected compact task state: %#v", state.Task)
+	}
+	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)
+	}
+}
+
+func TestCompactPreservesObjectiveAfterPlanParityMismatch(t *testing.T) {
+	prior := preservedState{Task: &preservedTaskState{Objective: "stale objective", Status: taskStatusActive, Pending: 1}}
+	encoded, err := json.Marshal(prior)
+	if err != nil {
+		t.Fatal(err)
+	}
+	messages := []zeroruntime.Message{
+		{Role: zeroruntime.MessageRoleSystem, Content: "system"},
+		{Role: zeroruntime.MessageRoleUser, Content: summaryLabel + "\nold\n\n" + preservedStateLabel + "\n" + string(encoded)},
+		{Role: zeroruntime.MessageRoleAssistant, Content: "continuing"},
+		{Role: zeroruntime.MessageRoleUser, Content: "more"},
+		{Role: zeroruntime.MessageRoleAssistant, Content: "working"},
+		{Role: zeroruntime.MessageRoleUser, Content: "again"},
+		{Role: zeroruntime.MessageRoleAssistant, Content: "done"},
+	}
+	compacted, err := Compact(messages, CompactionOptions{
+		PreserveLast: 2,
+		Summarize:    func([]zeroruntime.Message) (string, error) { return "SUMMARY", nil },
+		taskState: &taskStateSnapshot{
+			Objective:  "current objective",
+			PlanParity: taskPlanParityMismatch,
+		},
+	})
+	if err != nil {
+		t.Fatalf("Compact: %v", err)
+	}
+	state := parsePreservedStateBlock(compacted[1].Content)
+	if state.Task == nil || state.Task.Objective != "current objective" {
+		t.Fatalf("immutable objective was lost on plan mismatch: %#v", state.Task)
+	}
+	if state.Task.Status != "" || state.Task.Pending != 0 {
+		t.Fatalf("uncorroborated mutable task fields survived plan mismatch: %#v", state.Task)
+	}
+}
+
+func TestTaskObjectiveSurvivesRepeatedCompactionWithoutPlanRefresh(t *testing.T) {
+	task := newTaskState("keep this objective", nil)
+	task.observe(taskStateEvent{kind: taskStateEventPlan, arguments: `{"plan":[{"content":"write code","status":"in_progress"},{"content":"add tests","status":"pending"}]}`})
+	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.Fatalf("first Compact: %v", err)
+	}
+	secondInput := append(append([]zeroruntime.Message{}, first...),
+		zeroruntime.Message{Role: zeroruntime.MessageRoleUser, Content: "more"},
+		zeroruntime.Message{Role: zeroruntime.MessageRoleAssistant, Content: "working"},
+		zeroruntime.Message{Role: zeroruntime.MessageRoleUser, Content: "again"},
+		zeroruntime.Message{Role: zeroruntime.MessageRoleAssistant, Content: "done"},
+	)
+	snapshot := task.snapshotForCompaction(secondInput)
+	if snapshot.PlanParity != taskPlanParityMismatch {
+		t.Fatalf("plan call should be absent after first compaction, parity=%q", snapshot.PlanParity)
+	}
+	second, err := Compact(secondInput, CompactionOptions{
+		PreserveLast: 2,
+		Summarize:    func([]zeroruntime.Message) (string, error) { return "SECOND", nil },
+		taskState:    snapshot,
+	})
+	if err != nil {
+		t.Fatalf("second Compact: %v", err)
+	}
+	state := parsePreservedStateBlock(second[1].Content)
+	if state.Task == nil || state.Task.Objective != "keep this objective" {
+		t.Fatalf("objective lost after second compaction: %#v", state.Task)
+	}
+	if state.Task.Status != "" || state.Task.InProgress != 0 {
+		t.Fatalf("uncorroborated mutable fields survived second compaction: %#v", state.Task)
+	}
+}
+
 func TestCompactPreservesLoadedSkills(t *testing.T) {
 	summary := compactStateConversation(t, stateConversation())
 	if !strings.Contains(summary, preservedStateLabel) {
@@ -283,12 +381,10 @@ func TestExtractLatestPlanReturnsMostRecent(t *testing.T) {
 	}
 }
 
-func TestFormatPlanArgumentsAcceptsStepAlias(t *testing.T) {
+func TestFormatPlanArgumentsRejectsUnsupportedStepAlias(t *testing.T) {
 	got := formatPlanArguments(`{"plan":[{"step":"write failing test","status":"in_progress"},{"content":"keep existing shape","status":"pending"}]}`)
-	for _, want := range []string{"- [in_progress] write failing test", "- [pending] keep existing shape"} {
-		if !strings.Contains(got, want) {
-			t.Fatalf("expected %q in formatted plan, got %q", want, got)
-		}
+	if got != "" {
+		t.Fatalf("unsupported alias should reject the whole plan like update_plan, got %q", got)
 	}
 }
 

internal/agent/compaction_test.go

@@ -581,7 +581,7 @@ func TestCompactNeverProducesConsecutiveUserMessages(t *testing.T) {
 }
 
 func TestRecoverNoopDoesNotConsumeReactiveBudget(t *testing.T) {
-	st := newCompactionState(Options{ContextWindow: 1000, CompactionPreserveLast: 2})
+	st := newCompactionState(Options{ContextWindow: 1000, CompactionPreserveLast: 2}, nil)
 	provider := &mockProvider{turns: [][]zeroruntime.StreamEvent{{
 		{Type: zeroruntime.StreamEventText, Content: "SUMMARY"}, {Type: zeroruntime.StreamEventDone},
 	}}}
@@ -628,7 +628,7 @@ func TestRecoverNoopDoesNotConsumeReactiveBudget(t *testing.T) {
 }
 
 func TestRecoverDisabledIsNoop(t *testing.T) {
-	st := newCompactionState(Options{ContextWindow: 0})
+	st := newCompactionState(Options{ContextWindow: 0}, nil)
 	msgs := []zeroruntime.Message{{Role: zeroruntime.MessageRoleUser, Content: "x"}}
 	called := false
 	// recover must not invoke the provider/summarize when disabled, even on a

internal/agent/completion_policy.go

@@ -39,7 +39,7 @@ func newCompletionPolicy(requireSemanticCheck bool) *completionPolicy {
 	return &completionPolicy{requireSemanticCheck: requireSemanticCheck}
 }
 
-func (policy *completionPolicy) evaluate(text string, planPending bool) completionEvaluation {
+func (policy *completionPolicy) evaluate(text string, context completionContext) completionEvaluation {
 	// A direct admission is strong local evidence and takes precedence over all
 	// weaker signals, avoiding both continuation nudges and semantic checks.
 	if reason := selfReportedIncompletion(text); reason != "" {
@@ -50,7 +50,7 @@ func (policy *completionPolicy) evaluate(text string, planPending bool) completi
 	// weak evidence because bookkeeping can be stale. Both get a bounded chance
 	// to continue, but only a persisted cue is ultimately incomplete.
 	cue := endsWithContinuationCue(text)
-	if cue || planPending {
+	if cue || context.PlanPending {
 		if policy.continueNudges < maxContinueNudges {
 			policy.continueNudges++
 			reason := "your message ended mid-step"