perf(agent): execution profiles with one-shot posture escalation (PR10b+PR10c)

cmd/zero-perf-bench/turn.go

@@ -9,6 +9,7 @@ import (
 	"path/filepath"
 	"strings"
 
+	"github.com/Gitlawb/zero/internal/execprofile"
 	"github.com/Gitlawb/zero/internal/perfbench"
 )
 
@@ -20,6 +21,7 @@ type turnOptions struct {
 	SuitePath   string
 	Model       string
 	Mode        string
+	ExecProfile string
 	SelfCorrect bool
 	Binary      string
 	Iterations  int
@@ -64,6 +66,7 @@ func runTurnCommand(args []string, getenv func(string) string, stdout io.Writer,
 	result, err := perfbench.RunTurnBench(context.Background(), set, perfbench.TurnBenchConfig{
 		Model:       options.Model,
 		Mode:        options.Mode,
+		ExecProfile: options.ExecProfile,
 		SelfCorrect: options.SelfCorrect,
 		Version:     options.Version,
 		Commit:      options.Commit,
@@ -137,6 +140,13 @@ func parseTurnArgs(args []string, getenv func(string) string) (turnOptions, erro
 			}
 			options.Mode = value
 			index = next
+		case "--exec-profile":
+			value, next, err := readOptionValue(args, inlineValue, index, flag)
+			if err != nil {
+				return options, err
+			}
+			options.ExecProfile = value
+			index = next
 		case "--binary":
 			value, next, err := readOptionValue(args, inlineValue, index, flag)
 			if err != nil {
@@ -209,6 +219,20 @@ func parseTurnArgs(args []string, getenv func(string) string) (turnOptions, erro
 	if strings.TrimSpace(options.Model) == "" && !options.DryRun {
 		return options, fmt.Errorf("--model is required (or pass --dry-run)")
 	}
+	// Validate the profile here, before anything spawns: an unknown name would
+	// otherwise make every child exit with a usage error in milliseconds, and
+	// those near-zero walls would be recorded as valid latency samples in an
+	// exit-0 report — exactly the misread-as-improvement trap the harness
+	// closed for spawn failures. Normalizing to the catalog name also keeps
+	// the stamped execProfile canonical (Lookup is case-insensitive), so two
+	// captures of the same posture always compare equal.
+	if raw := strings.TrimSpace(options.ExecProfile); raw != "" {
+		profile, ok := execprofile.Lookup(raw)
+		if !ok {
+			return options, fmt.Errorf("unknown execution profile %q for --exec-profile. Valid profiles: %s", raw, strings.Join(execprofile.Names(), ", "))
+		}
+		options.ExecProfile = profile.Name
+	}
 	return options, nil
 }
 
@@ -239,6 +263,9 @@ func turnHelpText() string {
 		"  --suite <path>      Task set JSON file (required)",
 		"  --model <model>     Model to run (required unless --dry-run)",
 		"  --mode <name>       Exec mode preset to apply",
+		"  --exec-profile <name>",
+		"                      Execution profile for every task (fast|balanced|thorough);",
+		"                      forwarded to zero exec and stamped into the result",
 		"  --self-correct      Enable the post-edit verify-and-correct loop",
 		"  --binary <path>     Path to the `zero` binary (default: zero on PATH / repo root)",
 		"  --iterations <n>    Times to run each task (default: 1)",

cmd/zero-perf-bench/turn_test.go

@@ -0,0 +1,65 @@
+package main
+
+import (
+	"strings"
+	"testing"
+)
+
+func TestParseTurnArgsExecProfile(t *testing.T) {
+	getenv := func(string) string { return "" }
+	options, err := parseTurnArgs([]string{
+		"--suite", "suite.json",
+		"--model", "m",
+		"--exec-profile", "fast",
+	}, getenv)
+	if err != nil {
+		t.Fatalf("parseTurnArgs: %v", err)
+	}
+	if options.ExecProfile != "fast" {
+		t.Fatalf("ExecProfile = %q, want fast", options.ExecProfile)
+	}
+
+	// Inline form.
+	options, err = parseTurnArgs([]string{
+		"--suite=suite.json",
+		"--model=m",
+		"--exec-profile=thorough",
+	}, getenv)
+	if err != nil {
+		t.Fatalf("parseTurnArgs inline: %v", err)
+	}
+	if options.ExecProfile != "thorough" {
+		t.Fatalf("ExecProfile = %q, want thorough", options.ExecProfile)
+	}
+}
+
+// The bench validates the profile BEFORE spawning anything: an unknown name
+// would otherwise make every child exit with a usage error in milliseconds
+// and record those near-zero walls as valid latency samples in an exit-0
+// report. Lookup normalization also keeps the stamped name canonical so two
+// captures of the same posture compare equal.
+func TestParseTurnArgsExecProfileValidatesAndNormalizes(t *testing.T) {
+	getenv := func(string) string { return "" }
+
+	options, err := parseTurnArgs([]string{
+		"--suite", "suite.json", "--model", "m", "--exec-profile", "FAST",
+	}, getenv)
+	if err != nil {
+		t.Fatalf("parseTurnArgs: %v", err)
+	}
+	if options.ExecProfile != "fast" {
+		t.Fatalf("ExecProfile = %q, want the canonical fast", options.ExecProfile)
+	}
+
+	_, err = parseTurnArgs([]string{
+		"--suite", "suite.json", "--model", "m", "--exec-profile", "blanced",
+	}, getenv)
+	if err == nil {
+		t.Fatal("an unknown profile must fail parse, before anything spawns")
+	}
+	for _, name := range []string{"balanced", "fast", "thorough"} {
+		if !strings.Contains(err.Error(), name) {
+			t.Fatalf("error must list %q, got %q", name, err.Error())
+		}
+	}
+}

internal/agent/loop.go

@@ -202,6 +202,8 @@ func Run(ctx context.Context, prompt string, provider Provider, options Options)
 			}
 			if target.ReasoningEffort != "" {
 				options.ReasoningEffort = target.ReasoningEffort
+			} else if target.RestoreDefaultEffort {
+				options.ReasoningEffort = ""
 			}
 			if target.RestoreCompletionGate {
 				options.RequireCompletionSignal = true

internal/agent/profile_controller_test.go

@@ -153,6 +153,51 @@ func TestPostureEscalationOnUncertainCompletion(t *testing.T) {
 	}
 }
 
+// A profile that filled the run's effort displaced the provider default ("");
+// RestoreDefaultEffort lets escalation restore that default, which a plain ""
+// ReasoningEffort target cannot express (it means "leave untouched").
+func TestPostureEscalationRestoresDefaultEffort(t *testing.T) {
+	provider := &mockProvider{turns: [][]zeroruntime.StreamEvent{
+		{
+			{Type: zeroruntime.StreamEventText, Content: "Let me read the file:"},
+			{Type: zeroruntime.StreamEventDone},
+		},
+		{
+			{Type: zeroruntime.StreamEventText, Content: "Done. All set."},
+			{Type: zeroruntime.StreamEventDone},
+		},
+	}}
+
+	result, err := Run(context.Background(), "go", provider, Options{
+		Registry:                tools.NewRegistry(),
+		MaxTurns:                10,
+		ReasoningEffort:         "low",
+		RequireCompletionSignal: true,
+		Profile: &ProfilePolicy{
+			Name: "fast",
+			Escalate: &PostureEscalation{
+				RestoreDefaultEffort:  true,
+				OnCompletionUncertain: 1,
+			},
+		},
+	})
+	if err != nil {
+		t.Fatal(err)
+	}
+	if result.FinalAnswer != "Done. All set." {
+		t.Fatalf("expected the completed answer, got %q", result.FinalAnswer)
+	}
+	if len(provider.requests) != 2 {
+		t.Fatalf("expected 2 requests, got %d", len(provider.requests))
+	}
+	if provider.requests[0].ReasoningEffort != "low" {
+		t.Fatalf("pre-escalation request effort = %q, want the profile's low", provider.requests[0].ReasoningEffort)
+	}
+	if provider.requests[1].ReasoningEffort != "" {
+		t.Fatalf("post-escalation request effort = %q, want the restored provider default (empty)", provider.requests[1].ReasoningEffort)
+	}
+}
+
 // failingProfileTool always errors with the same signature so the repeated-
 // failure guard builds a streak.
 type failingProfileTool struct{}

internal/agent/types.go

@@ -126,6 +126,12 @@ type PostureEscalation struct {
 	MaxTurns int
 	// ReasoningEffort replaces the run's effort when non-empty.
 	ReasoningEffort string
+	// RestoreDefaultEffort clears the run's effort override (back to the
+	// provider/model default) when true. It exists because the displaced value
+	// of a profile-filled effort is "" — which as a ReasoningEffort target
+	// means "leave untouched" — so restoring the default needs its own signal.
+	// Ignored when ReasoningEffort is non-empty.
+	RestoreDefaultEffort bool
 	// RestoreCompletionGate re-enables RequireCompletionSignal (headless
 	// completion semantics) when true.
 	RestoreCompletionGate bool

internal/cli/app.go

@@ -1341,6 +1341,9 @@ Flags:
       --spec-reasoning-effort <effort>
                                     Override draft reasoning effort when --use-spec is set
       --max-turns <number>           Override the maximum agent loop turns
+      --exec-profile <name>          Apply an execution profile (balanced, fast, thorough): loop
+                                    posture only (turn budget, effort, self-correction, escalation);
+                                    composes with --mode (which picks the model) and explicit flags win
       --auto <low|medium|high>       Set exec autonomy; high enables unsafe tools
       --enabled-tools <tools>        Only expose these comma or space separated tools
       --disabled-tools <tools>       Hide these comma or space separated tools

internal/cli/exec.go

@@ -13,6 +13,7 @@ import (
 	"github.com/Gitlawb/zero/internal/agent"
 	"github.com/Gitlawb/zero/internal/config"
 	"github.com/Gitlawb/zero/internal/errhint"
+	"github.com/Gitlawb/zero/internal/execprofile"
 	"github.com/Gitlawb/zero/internal/imageinput"
 	"github.com/Gitlawb/zero/internal/lsp"
 	"github.com/Gitlawb/zero/internal/modelregistry"
@@ -69,7 +70,14 @@ type execOptions struct {
 	// intentionally inert: nothing consumes it. Model selection is driven by
 	// --model / --mode instead. See writeExecHelp ("Accept legacy model profile
 	// selection") and TestRunExecAcceptsLegacyModelProfileFlags.
-	modelProfile          string
+	modelProfile string
+	// execProfile selects a named execution profile (balanced, fast, thorough):
+	// a loop-posture bundle (turn budget, reasoning effort, self-correction,
+	// escalation triggers) applied AFTER --mode with the same
+	// fill-only-if-unset rule, so precedence is explicit flag > mode > profile.
+	// Distinct from the mode preset also named "fast" (which picks a model) and
+	// from the legacy inert --profile above. See internal/execprofile.
+	execProfile           string
 	reasoningEffort       string
 	useSpec               bool
 	specModel             string
@@ -167,6 +175,14 @@ func runExec(args []string, stdout io.Writer, stderr io.Writer, deps appDeps) in
 	if err := applyExecMode(&options); err != nil {
 		return writeExecFormatUsageError(stdout, stderr, options.outputFormat, err.Error())
 	}
+	// A profile tunes loop posture the way a mode tunes model selection, and
+	// runs after it so the mode's fills count as "set" and win. MaxTurns is
+	// deferred to config resolution below, where the displaced resolved budget
+	// is known and becomes the escalation restore target.
+	execProfile, execProfileFilledEffort, err := applyExecProfile(&options)
+	if err != nil {
+		return writeExecFormatUsageError(stdout, stderr, options.outputFormat, err.Error())
+	}
 
 	workspaceRoot, err := resolveWorkspaceRoot(options.cwd, deps)
 	if err != nil {
@@ -272,6 +288,8 @@ func runExec(args []string, stdout io.Writer, stderr io.Writer, deps appDeps) in
 		}
 		return writeExecProviderError(stdout, stderr, options.outputFormat, "provider_error", err.Error())
 	}
+	var displacedMaxTurns int
+	resolved.MaxTurns, displacedMaxTurns = applyProfileTurnBudget(execProfile, options.maxTurns, resolved.MaxTurns)
 	registerLocalControlTools(registry, workspaceRoot, resolved.LocalControl)
 	if err := validateExecToolFilters(options, registry); err != nil {
 		return writeExecFormatUsageError(stdout, stderr, options.outputFormat, err.Error())
@@ -486,6 +504,13 @@ func runExec(args []string, stdout io.Writer, stderr io.Writer, deps appDeps) in
 			reasoningEffort:    forwardEffort,
 			specPermissionMode: permissionMode,
 			notifier:           notifier,
+			// The profile displaced resolved.MaxTurns above, so the spec-draft
+			// run arms the same escalation policy as the main run (in practice
+			// only the failure-streak and risky-mutation triggers can fire
+			// here: the draft runs without the completion gate or a
+			// self-corrector).
+			profilePolicy: execProfile.Policy(displacedMaxTurns,
+				specProfileEffortFilled(execProfileFilledEffort, options.specReasoningEffort)),
 		})
 	}
 
@@ -528,7 +553,7 @@ func runExec(args []string, stdout io.Writer, stderr io.Writer, deps appDeps) in
 	var traceRecorder *trace.Recorder
 	var traceSnapshot *trace.TurnTrace
 	if tracePath != "" {
-		traceRecorder = trace.NewRecorder(preparedSession.Session.SessionID, runID, "")
+		traceRecorder = trace.NewRecorder(preparedSession.Session.SessionID, runID, execProfile.Name)
 		defer func() {
 			if err := writeTraceSnapshot(traceSnapshot, tracePath, stderr); err != nil {
 				fmt.Fprintf(stderr, "[zero] failed to write trace: %s\n", err)
@@ -627,6 +652,7 @@ func runExec(args []string, stdout io.Writer, stderr io.Writer, deps appDeps) in
 		Autonomy:             options.autonomy,
 		SelfCorrect:          selfCorrector,
 		FileDiagnostics:      fileDiagnostics,
+		Profile:              execProfile.Policy(displacedMaxTurns, execProfileFilledEffort),
 		// Headless exec: don't accept a no-tool-call turn as "done" while work
 		// clearly remains (pending plan items / a mid-step continuation cue) —
 		// nudge to continue, and finalize as INCOMPLETE rather than false success
@@ -1133,6 +1159,67 @@ func applyExecMode(options *execOptions) error {
 	return nil
 }
 
+// applyExecProfile expands an --exec-profile selection onto the exec options.
+// Like applyExecMode it only fills fields the caller left unset, and it runs
+// AFTER the mode so a mode-filled field counts as set: precedence is explicit
+// flag > --mode > --exec-profile. Only the options-level knobs are applied here
+// (reasoning effort still flows through the model-supported gating downstream;
+// self-correct is presence-only so a profile can only turn it on). MaxTurns is
+// intentionally NOT applied here — the profile displaces the resolved budget
+// after config resolution, where the displaced value is known and becomes the
+// escalation restore target. An unknown profile is a usage error listing the
+// valid names. Not to be confused with the legacy inert --profile flag.
+// The second return reports whether the profile actually filled the reasoning
+// effort (false when the user set one explicitly), so the escalation policy
+// knows the displaced effort was the provider default and can restore it.
+func applyExecProfile(options *execOptions) (execprofile.Profile, bool, error) {
+	name := strings.TrimSpace(options.execProfile)
+	if name == "" {
+		return execprofile.Profile{}, false, nil
+	}
+	profile, ok := execprofile.Lookup(name)
+	if !ok {
+		return execprofile.Profile{}, false, execUsageError{fmt.Sprintf("unknown execution profile %q. Valid profiles: %s.", options.execProfile, strings.Join(execprofile.Names(), ", "))}
+	}
+	effortFilled := false
+	if options.reasoningEffort == "" && profile.ReasoningEffort != "" {
+		options.reasoningEffort = profile.ReasoningEffort
+		effortFilled = true
+	}
+	// Spec-safe projection: the spec-draft path wires no self-corrector (an
+	// explicit --self-correct --use-spec is rejected at parse time, before
+	// profiles apply), so a profile's self-correct knob is meaningless there.
+	// Project it away rather than erroring: the user asked for a thorough
+	// DRAFT, and the profile's other knobs (budget, effort) apply to it fine.
+	if profile.SelfCorrect && !options.useSpec {
+		options.selfCorrect = true
+	}
+	return profile, effortFilled, nil
+}
+
+// specProfileEffortFilled reports whether the profile's effort fill actually
+// governs the spec-draft run. An explicit --spec-reasoning-effort replaces the
+// filled effort for the draft, so the escalation's effort restore must not arm
+// there: escalation must never clear an effort the user pinned by hand.
+func specProfileEffortFilled(effortFilled bool, specReasoningEffort string) bool {
+	return effortFilled && strings.TrimSpace(specReasoningEffort) == ""
+}
+
+// applyProfileTurnBudget decides the run's turn budget once config is resolved.
+// The profile displaces the RESOLVED value, not the flag: a pinned budget
+// always wins and the profile backs off entirely, while an env/config budget
+// is the "balanced posture" a mid-run escalation can restore. pinnedMaxTurns
+// is any caller-pinned budget — an explicit --max-turns flag OR a mode
+// preset's fill (both land in options.maxTurns, and a mode outranks a profile
+// just like the flag does). displaced is 0 when nothing was displaced, so an
+// escalation leaves the ceiling untouched.
+func applyProfileTurnBudget(profile execprofile.Profile, pinnedMaxTurns int, resolvedMaxTurns int) (effective int, displaced int) {
+	if profile.MaxTurns > 0 && pinnedMaxTurns == 0 {
+		return profile.MaxTurns, resolvedMaxTurns
+	}
+	return resolvedMaxTurns, 0
+}
+
 // resolveSelectedModel routes a user-supplied --model value through the model
 // registry so that fuzzy aliases (e.g. "sonnet 4.5") resolve to canonical ids
 // and deprecated models auto-redirect to their fallback. It returns the model id

internal/cli/exec_parse.go

@@ -147,6 +147,19 @@ func parseExecArgs(args []string) (execOptions, bool, error) {
 			index = next
 		case strings.HasPrefix(arg, "--profile="):
 			options.modelProfile = strings.TrimSpace(strings.TrimPrefix(arg, "--profile="))
+		case arg == "--exec-profile":
+			value, next, err := nextFlagValue(args, index, arg)
+			if err != nil {
+				return options, false, err
+			}
+			options.execProfile = strings.TrimSpace(value)
+			index = next
+		case strings.HasPrefix(arg, "--exec-profile="):
+			value, err := requiredInlineFlagValue(arg, "--exec-profile")
+			if err != nil {
+				return options, false, err
+			}
+			options.execProfile = value
 		case arg == "-r" || arg == "--reasoning-effort":
 			value, next, err := nextFlagValue(args, index, arg)
 			if err != nil {