fix(tools): reject mixed-root freeform patches

internal/acp/agent.go

@@ -14,7 +14,6 @@ import (
 	"github.com/Gitlawb/zero/internal/providercatalog"
 	"github.com/Gitlawb/zero/internal/providermodelcatalog"
 	"github.com/Gitlawb/zero/internal/providermodeldiscovery"
-	"github.com/Gitlawb/zero/internal/redaction"
 	"github.com/Gitlawb/zero/internal/sandbox"
 	"github.com/Gitlawb/zero/internal/sessions"
 	"github.com/Gitlawb/zero/internal/tools"
@@ -31,12 +30,10 @@ type Deps struct {
 	DiscoverModels func(context.Context, config.ProviderProfile) ([]providermodeldiscovery.Model, error)
 	NewProvider    func(profile config.ProviderProfile) (zeroruntime.Provider, error)
 	RunAgent       func(ctx context.Context, prompt string, provider zeroruntime.Provider, opts agent.Options) (agent.Result, error)
-	// BuildWorkspace creates the per-turn scoped tool workspace for a validated
-	// workspace root. Its Close method releases any resources the registry owns
-	// (notably MCP server connections) after the turn completes or is cancelled.
-	// Shell tools remain confined exactly like the exec surface — never unconfined
-	// on the host.
-	BuildWorkspace func(ctx context.Context, workspaceRoot string, resolved config.ResolvedConfig, mode agent.PermissionMode) (*Workspace, error)
+	// BuildWorkspace builds the SCOPED tool registry and the sandbox engine for a
+	// validated workspace root, so ACP shell tools (bash/exec_command) are confined
+	// exactly like the exec surface — never run unconfined on the host.
+	BuildWorkspace func(workspaceRoot string, resolved config.ResolvedConfig) (*tools.Registry, *sandbox.Engine, error)
 	// ResolveWorkspaceRoot validates + normalizes a client-supplied cwd (must be an
 	// existing directory; never the bare root). It is the file-tool confinement root.
 	ResolveWorkspaceRoot func(cwd string) (string, error)
@@ -44,27 +41,6 @@ type Deps struct {
 	AgentInfo            Implementation
 }
 
-// Workspace is the per-turn execution environment passed to the agent. ACP does
-// not retain it across turns because MCP connections belong to the registry that
-// advertised their tools; keeping a stale registry after a cancelled turn would
-// leak its server process and its permission state into the next turn.
-type Workspace struct {
-	Registry       *tools.Registry
-	Sandbox        *sandbox.Engine
-	DeferThreshold int
-	Notices        []string
-	Cleanup        func() error
-}
-
-// Close releases resources created with the workspace. A nil cleanup is valid
-// for core-only workspaces.
-func (w *Workspace) Close() error {
-	if w == nil || w.Cleanup == nil {
-		return nil
-	}
-	return w.Cleanup()
-}
-
 // Agent is the ACP agent server bound to one JSON-RPC connection (one editor).
 type Agent struct {
 	conn *Conn
@@ -265,34 +241,13 @@ func (a *Agent) runTurn(ctx context.Context, sess *acpSession, userText string,
 	if err != nil {
 		return "", RPCError(codeInternalError, "provider: "+err.Error())
 	}
-	mode := sess.currentMode()
 	// Build the SCOPED registry + sandbox engine for this session's workspace so
 	// shell/file tools are confined to the workspace exactly like the exec surface.
-	// The workspace can also own MCP connections, which must be closed after every
-	// turn even if the agent run returns an error or the client cancels it.
-	workspace, err := a.deps.BuildWorkspace(ctx, sess.cwd, resolved, mode)
+	registry, sandboxEngine, err := a.deps.BuildWorkspace(sess.cwd, resolved)
 	if err != nil {
 		return "", RPCError(codeInternalError, "workspace: "+err.Error())
 	}
-	if workspace == nil || workspace.Registry == nil {
-		if workspace != nil {
-			_ = workspace.Close()
-		}
-		return "", RPCError(codeInternalError, "workspace: missing tool registry")
-	}
-	defer func() {
-		if err := workspace.Close(); err != nil {
-			log.Printf("acp: close workspace: %v", err)
-		}
-	}()
-	registry := workspace.Registry
-	sandboxEngine := workspace.Sandbox
 	note := &notifier{conn: a.conn, sessionID: sess.id}
-	for _, notice := range workspace.Notices {
-		if text := strings.TrimSpace(redaction.RedactString(notice, redaction.Options{})); text != "" {
-			note.text("\n\n[zero warning] " + text + "\n")
-		}
-	}
 
 	opts := agent.Options{
 		Cwd:            sess.cwd,
@@ -301,8 +256,7 @@ func (a *Agent) runTurn(ctx context.Context, sess *acpSession, userText string,
 		Model:          resolved.Provider.Model,
 		Registry:       registry,
 		Sandbox:        sandboxEngine,
-		PermissionMode: mode,
-		DeferThreshold: workspace.DeferThreshold,
+		PermissionMode: sess.currentMode(),
 		MaxTurns:       resolved.MaxTurns,
 		Images:         images,
 		OnText:         note.text,

internal/acp/agent_test.go

@@ -8,7 +8,6 @@ import (
 	"io"
 	"os"
 	"path/filepath"
-	"slices"
 	"strings"
 	"testing"
 	"time"
@@ -36,35 +35,6 @@ func (f fakeProvider) StreamCompletion(_ context.Context, _ zeroruntime.Completi
 	return ch, nil
 }
 
-type acpDeferredPromptTool struct{ name string }
-
-func (t acpDeferredPromptTool) Name() string           { return t.name }
-func (acpDeferredPromptTool) Description() string      { return "deferred MCP test tool" }
-func (acpDeferredPromptTool) Parameters() tools.Schema { return tools.Schema{Type: "object"} }
-func (acpDeferredPromptTool) Deferred() bool           { return true }
-func (acpDeferredPromptTool) Run(context.Context, map[string]any) tools.Result {
-	return tools.Result{Status: tools.StatusOK, Output: "ok"}
-}
-func (acpDeferredPromptTool) Safety() tools.Safety {
-	return tools.Safety{
-		SideEffect: tools.SideEffectNetwork, Permission: tools.PermissionPrompt,
-		AdvertiseInAuto: true,
-	}
-}
-
-type captureToolsProvider struct {
-	requests chan zeroruntime.CompletionRequest
-}
-
-func (p captureToolsProvider) StreamCompletion(_ context.Context, request zeroruntime.CompletionRequest) (<-chan zeroruntime.StreamEvent, error) {
-	p.requests <- request
-	ch := make(chan zeroruntime.StreamEvent, 2)
-	ch <- zeroruntime.StreamEvent{Type: zeroruntime.StreamEventText, Content: "done"}
-	ch <- zeroruntime.StreamEvent{Type: zeroruntime.StreamEventDone}
-	close(ch)
-	return ch, nil
-}
-
 func testDeps(t *testing.T) Deps {
 	t.Helper()
 	store := sessions.NewStore(sessions.StoreOptions{RootDir: t.TempDir()})
@@ -83,10 +53,10 @@ func testDeps(t *testing.T) Deps {
 			return fakeProvider{text: "Hello from ZERO"}, nil
 		},
 		RunAgent: agent.Run,
-		BuildWorkspace: func(context.Context, string, config.ResolvedConfig, agent.PermissionMode) (*Workspace, error) {
+		BuildWorkspace: func(string, config.ResolvedConfig) (*tools.Registry, *sandbox.Engine, error) {
 			r := tools.NewRegistry()
 			r.Register(tools.NewUpdatePlanTool())
-			return &Workspace{Registry: r}, nil
+			return r, nil, nil
 		},
 		ResolveWorkspaceRoot: func(cwd string) (string, error) { return cwd, nil },
 		Store:                store,
@@ -498,8 +468,8 @@ func TestACPRunTurnWiresSandboxAndScopedRegistry(t *testing.T) {
 	reg := tools.NewRegistry()
 	reg.Register(tools.NewUpdatePlanTool())
 	engine := sandbox.NewEngine(sandbox.EngineOptions{WorkspaceRoot: t.TempDir()})
-	deps.BuildWorkspace = func(context.Context, string, config.ResolvedConfig, agent.PermissionMode) (*Workspace, error) {
-		return &Workspace{Registry: reg, Sandbox: engine}, nil
+	deps.BuildWorkspace = func(string, config.ResolvedConfig) (*tools.Registry, *sandbox.Engine, error) {
+		return reg, engine, nil
 	}
 	var captured agent.Options
 	deps.RunAgent = func(_ context.Context, _ string, _ zeroruntime.Provider, opts agent.Options) (agent.Result, error) {
@@ -527,124 +497,6 @@ func TestACPRunTurnWiresSandboxAndScopedRegistry(t *testing.T) {
 	}
 }
 
-func TestACPRunTurnUsesWorkspaceDeferThresholdAtProviderBoundary(t *testing.T) {
-	for _, tc := range []struct {
-		name      string
-		threshold int
-		want      []string
-	}{
-		{name: "explicit zero disables", threshold: 0, want: []string{"mcp_docs_alpha", "mcp_docs_beta"}},
-		{name: "below threshold stays eager", threshold: 3, want: []string{"mcp_docs_alpha", "mcp_docs_beta"}},
-		{name: "at threshold defers", threshold: 2, want: []string{tools.ToolSearchToolName}},
-	} {
-		t.Run(tc.name, func(t *testing.T) {
-			requests := make(chan zeroruntime.CompletionRequest, 4)
-			deps := testDeps(t)
-			deps.NewProvider = func(config.ProviderProfile) (zeroruntime.Provider, error) {
-				return captureToolsProvider{requests: requests}, nil
-			}
-			deps.BuildWorkspace = func(context.Context, string, config.ResolvedConfig, agent.PermissionMode) (*Workspace, error) {
-				registry := tools.NewRegistry()
-				registry.Register(acpDeferredPromptTool{name: "mcp_docs_alpha"})
-				registry.Register(acpDeferredPromptTool{name: "mcp_docs_beta"})
-				registry.Register(tools.NewToolSearchTool(registry))
-				return &Workspace{Registry: registry, DeferThreshold: tc.threshold}, nil
-			}
-
-			h := newHarness(t, deps)
-			defer h.stop()
-			ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
-			defer cancel()
-			var created NewSessionResult
-			if err := h.client.Call(ctx, MethodSessionNew, NewSessionParams{Cwd: t.TempDir()}, &created); err != nil {
-				t.Fatal(err)
-			}
-			if err := h.client.Call(ctx, MethodSessionPrompt, PromptParams{SessionID: created.SessionID, Prompt: []ContentBlock{TextBlock("hi")}}, &PromptResult{}); err != nil {
-				t.Fatal(err)
-			}
-			request := <-requests
-			got := make([]string, 0, len(request.Tools))
-			for _, definition := range request.Tools {
-				got = append(got, definition.Name)
-			}
-			if !slices.Equal(got, tc.want) {
-				t.Fatalf("provider tools = %#v, want %#v", got, tc.want)
-			}
-		})
-	}
-}
-
-func TestACPRunTurnEmitsWorkspaceSetupNotices(t *testing.T) {
-	deps := testDeps(t)
-	deps.BuildWorkspace = func(context.Context, string, config.ResolvedConfig, agent.PermissionMode) (*Workspace, error) {
-		registry := tools.NewRegistry()
-		registry.Register(tools.NewUpdatePlanTool())
-		return &Workspace{Registry: registry, Notices: []string{"MCP server docs unavailable, skipped: timeout"}}, nil
-	}
-	h := newHarness(t, deps)
-	defer h.stop()
-	ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
-	defer cancel()
-	var created NewSessionResult
-	if err := h.client.Call(ctx, MethodSessionNew, NewSessionParams{Cwd: t.TempDir()}, &created); err != nil {
-		t.Fatal(err)
-	}
-	if err := h.client.Call(ctx, MethodSessionPrompt, PromptParams{SessionID: created.SessionID, Prompt: []ContentBlock{TextBlock("hi")}}, &PromptResult{}); err != nil {
-		t.Fatal(err)
-	}
-	got := drainText(t, h.updates)
-	if !strings.Contains(got, "[zero warning] MCP server docs unavailable, skipped: timeout") || !strings.Contains(got, "Hello from ZERO") {
-		t.Fatalf("streamed text = %q", got)
-	}
-}
-
-// TestACPRunTurnClosesWorkspace proves a per-turn workspace never outlives the
-// agent run. This is particularly important for MCP: its registry owns live
-// client connections and, for stdio servers, child processes.
-func TestACPRunTurnClosesWorkspaceAfterSuccessAndFailure(t *testing.T) {
-	for _, tc := range []struct {
-		name   string
-		runErr error
-	}{
-		{name: "success"},
-		{name: "agent failure", runErr: errors.New("provider interrupted")},
-	} {
-		t.Run(tc.name, func(t *testing.T) {
-			deps := testDeps(t)
-			closed := 0
-			deps.BuildWorkspace = func(context.Context, string, config.ResolvedConfig, agent.PermissionMode) (*Workspace, error) {
-				registry := tools.NewRegistry()
-				registry.Register(tools.NewUpdatePlanTool())
-				return &Workspace{Registry: registry, Cleanup: func() error {
-					closed++
-					return nil
-				}}, nil
-			}
-			deps.RunAgent = func(context.Context, string, zeroruntime.Provider, agent.Options) (agent.Result, error) {
-				return agent.Result{FinalAnswer: "ok"}, tc.runErr
-			}
-			h := newHarness(t, deps)
-			defer h.stop()
-			ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
-			defer cancel()
-			var created NewSessionResult
-			if err := h.client.Call(ctx, MethodSessionNew, NewSessionParams{Cwd: t.TempDir()}, &created); err != nil {
-				t.Fatalf("session/new: %v", err)
-			}
-			err := h.client.Call(ctx, MethodSessionPrompt, PromptParams{SessionID: created.SessionID, Prompt: []ContentBlock{TextBlock("hello")}}, &PromptResult{})
-			if tc.runErr == nil && err != nil {
-				t.Fatalf("session/prompt: %v", err)
-			}
-			if tc.runErr != nil && err == nil {
-				t.Fatal("session/prompt succeeded after agent failure")
-			}
-			if closed != 1 {
-				t.Fatalf("workspace cleanup calls = %d, want 1", closed)
-			}
-		})
-	}
-}
-
 // TestACPRejectsInvalidCwd confirms session/new fails when the workspace root
 // resolver rejects the client cwd (e.g. filesystem root).
 func TestACPRejectsInvalidCwd(t *testing.T) {

internal/agent/compaction.go

@@ -4,9 +4,7 @@ import (
 	"context"
 	"encoding/json"
 	"errors"
-	"strconv"
 	"strings"
-	"unicode/utf8"
 
 	"github.com/Gitlawb/zero/internal/trace"
 	"github.com/Gitlawb/zero/internal/zeroruntime"
@@ -398,27 +396,6 @@ type compactionState struct {
 	// starts at 1.0 and converges via an EMA as each turn reports actual usage, so
 	// later turns compact nearer to real capacity. Zero is treated as 1.0.
 	calibrationRatio float64
-
-	// summarizerFactory lazily builds the dedicated (cheap) summarizer provider
-	// (Options.Summarizer) for the current main model. summarizerProvider
-	// memoizes the built provider and summarizerResolved records that the
-	// factory ran (it may legitimately return no provider: the main model is
-	// already the cheap one). summarizerBroken is the sticky fallback: once a
-	// build or call fails, the run stays on the main provider until the next
-	// model switch — a misconfigured cheap model must never break (or
-	// repeatedly delay) compaction.
-	summarizerFactory  func(ctx context.Context, mainModelID string) (Provider, error)
-	summarizerProvider Provider
-	summarizerResolved bool
-	summarizerBroken   bool
-	// window is the context window the threshold was derived from. The
-	// reactive free-prune stage compares against it (the limit the provider
-	// enforces), not against the 70% proactive threshold — a pruned history
-	// between the two would still succeed on retry.
-	window int
-	// mainModel is the model the run currently streams on; the summarizer
-	// choice is made against it and remade after a mid-run switch.
-	mainModel string
 }
 
 // calibrate folds one turn's (rawEstimate, actualPromptTokens) sample into the
@@ -453,88 +430,17 @@ func (state *compactionState) calibratedTokens(raw int) int {
 
 func newCompactionState(options Options, task *taskState) *compactionState {
 	state := &compactionState{
-		enabled:           options.ContextWindow > 0,
-		threshold:         compactionThreshold(options.ContextWindow),
-		window:            options.ContextWindow,
-		mainModel:         options.Model,
-		preserveLast:      options.CompactionPreserveLast,
-		onUsage:           options.OnUsage,
-		task:              task,
-		planner:           newContextPlanner(contextPlannerConfig{contextWindow: options.ContextWindow, serviceTier: options.ServiceTier}),
-		trace:             options.Trace,
-		summarizerFactory: options.Summarizer,
+		enabled:      options.ContextWindow > 0,
+		threshold:    compactionThreshold(options.ContextWindow),
+		preserveLast: options.CompactionPreserveLast,
+		onUsage:      options.OnUsage,
+		task:         task,
+		planner:      newContextPlanner(contextPlannerConfig{contextWindow: options.ContextWindow, serviceTier: options.ServiceTier}),
+		trace:        options.Trace,
 	}
 	return state
 }
 
-// updateWindow re-derives the compaction threshold after a mid-run model
-// switch. The low-water mark is reset: it was measured against the old
-// threshold, and keeping it could suppress a compaction the smaller window
-// now requires. <= 0 (unknown model) leaves everything unchanged.
-func (state *compactionState) updateWindow(window int) {
-	if window <= 0 {
-		return
-	}
-	state.enabled = true
-	state.window = window
-	state.threshold = compactionThreshold(window)
-	state.lowWaterMark = 0
-	if state.planner != nil {
-		state.planner.config.contextWindow = window
-	}
-}
-
-// switchModel records a mid-run model switch: the window is re-derived
-// (window <= 0 keeps the old one) and the summarizer choice is forgotten so
-// the next compaction re-resolves it against the new main model. A run that
-// started on the cheap model (no dedicated summarizer) and escalated to an
-// expensive one therefore regains cheap summaries — the exact workflow a
-// dedicated summarizer exists for.
-func (state *compactionState) switchModel(modelID string, window int) {
-	state.mainModel = modelID
-	state.updateWindow(window)
-	state.summarizerProvider = nil
-	state.summarizerResolved = false
-	state.summarizerBroken = false
-}
-
-// summarizeProvider returns the provider summarization calls should use and
-// whether it is the dedicated summarizer: that one when it applies to the
-// current main model and is healthy, else the main provider. The factory runs
-// at most once per main model; a build error marks the summarizer broken for
-// that model. Callers branch on the boolean rather than comparing Provider
-// values — interface comparison panics on a non-comparable dynamic type.
-func (state *compactionState) summarizeProvider(ctx context.Context, main Provider) (Provider, bool) {
-	if state.summarizerFactory == nil || state.summarizerBroken {
-		return main, false
-	}
-	if !state.summarizerResolved {
-		state.summarizerResolved = true
-		built, err := state.summarizerFactory(ctx, state.mainModel)
-		if err != nil {
-			state.summarizerBroken = true
-			return main, false
-		}
-		state.summarizerProvider = built
-	}
-	if state.summarizerProvider == nil {
-		return main, false
-	}
-	return state.summarizerProvider, true
-}
-
-// fitsWindow reports whether a calibrated size is safely under the limit the
-// provider enforces. The proactive threshold (70% of the window) is a trigger
-// for the paid summarizer, not the hard limit; the reactive path compares
-// against the window itself, with a small margin for estimate error, so a
-// history pruned to, say, 85% of the window takes the free retry.
-func (state *compactionState) fitsWindow(size int) bool {
-	if state.window <= 0 {
-		return size <= state.threshold
-	}
-	return size <= state.window-state.window/20
-}
-
 // maybeCompact runs proactive compaction at the top of a turn. It returns the
 // (possibly compacted) message slice. It is a no-op when compaction is disabled,
 // when the history is under threshold, or when the history has not grown past
@@ -628,34 +534,10 @@ func (state *compactionState) recover(
 		// context-limit error never triggers an unexpected summarization call.
 		return messages, false, nil
 	}
-	if !isContextLimitError(errorMessage) {
+	if state.reactiveAttempted {
 		return messages, false, nil
 	}
-
-	// CHEAP FIRST STAGE (mirrors maybeCompact): a context-limit failure can
-	// often be fixed for free by dropping superseded reads and pruning old
-	// tool-result bodies. It runs regardless of the one-shot reactive budget
-	// (it costs nothing and cannot loop: a second pass finds nothing left to
-	// prune). The free retry is taken only when the pruned history fits the
-	// window the provider enforces — otherwise a retry would fail the same
-	// way, so fall through to the paid summarizer in this same call.
-	toolTokens := estimateToolDefTokens(tools)
-	prunedAny := false
-	if pruned, reclaimed := pruneSupersededReadResults(messages); reclaimed > 0 {
-		messages, prunedAny = pruned, true
-	}
-	if pruned, reclaimed := pruneStaleToolOutput(messages, state.preserveLast); reclaimed > 0 {
-		messages, prunedAny = pruned, true
-	}
-	if prunedAny {
-		size := state.calibratedTokens(estimateTokens(messages) + toolTokens)
-		if state.fitsWindow(size) {
-			state.lowWaterMark = size
-			return messages, true, nil
-		}
-	}
-
-	if state.reactiveAttempted {
+	if !isContextLimitError(errorMessage) {
 		return messages, false, nil
 	}
 
@@ -695,21 +577,11 @@ 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.
-// The call goes to the dedicated (cheap) summarizer when one applies; if that
-// call fails the summarizer is marked broken for the current model and the
-// same slice is retried once on the main provider, so the caller sees at most
-// one (main-provider-quality) error.
 func (state *compactionState) summarizeClosure(ctx context.Context, provider Provider) func([]zeroruntime.Message) (string, error) {
 	if state.planner == nil {
 		state.planner = newContextPlanner(contextPlannerConfig{})
 	}
 	return func(toSummarize []zeroruntime.Message) (string, error) {
-		chosen, dedicated := state.summarizeProvider(ctx, provider)
-		summary, err := summarizeWithPlanner(ctx, chosen, toSummarize, state.onUsage, state.planner, state.trace)
-		if err == nil || !dedicated {
-			return summary, err
-		}
-		state.summarizerBroken = true
 		return summarizeWithPlanner(ctx, provider, toSummarize, state.onUsage, state.planner, state.trace)
 	}
 }
@@ -793,41 +665,8 @@ func summarizeMessagesOnce(ctx context.Context, provider Provider, messages []ze
 	return summary, nil
 }
 
-// summaryToolResultClamp bounds each tool-result body in the summarizer input.
-// Tool outputs dominate the elided middle's bulk (build logs, file reads,
-// search results), yet the summary instructions only need their gist — the
-// model that ACTED on the full output already turned it into decisions the
-// surrounding messages record. 2,000 chars (~500 tokens) keeps the useful
-// head+tail of a result while cutting the summarizer input by 5-10x on
-// tool-heavy sessions; the summarizer's own cost is the price being cut.
-const summaryToolResultClamp = 2000
-
-// summaryToolArgsClamp bounds each tool-call argument blob in the transcript:
-// a write_file call carries the whole file body in its arguments.
-const summaryToolArgsClamp = 500
-
-// clampForSummary head+tail-truncates text for the summarizer transcript,
-// snapping to rune boundaries so the clamp never splits a UTF-8 sequence.
-func clampForSummary(text string, max int) string {
-	if max <= 0 || len(text) <= max {
-		return text
-	}
-	head := max * 3 / 4
-	tail := max - head
-	for head > 0 && !utf8.RuneStart(text[head]) {
-		head--
-	}
-	start := len(text) - tail
-	for start < len(text) && !utf8.RuneStart(text[start]) {
-		start++
-	}
-	return text[:head] + "\n…[" + strconv.Itoa(len(text)-head-(len(text)-start)) + " chars omitted for summarization]…\n" + text[start:]
-}
-
 // renderTranscript flattens messages into a plain-text transcript for the
 // summarizer. Secret scrubbing already happened upstream at the tool boundary.
-// Tool-result bodies and tool-call arguments are clamped (see the constants
-// above): the summary needs what was done and decided, not the raw payloads.
 func renderTranscript(messages []zeroruntime.Message) string {
 	lines := make([]string, 0, len(messages))
 	for _, message := range messages {
@@ -837,13 +676,13 @@ func renderTranscript(messages []zeroruntime.Message) string {
 			if len(message.ToolCalls) > 0 {
 				calls := make([]string, 0, len(message.ToolCalls))
 				for _, call := range message.ToolCalls {
-					calls = append(calls, call.Name+"("+clampForSummary(call.Arguments, summaryToolArgsClamp)+")")
+					calls = append(calls, call.Name+"("+call.Arguments+")")
 				}
 				line += "\n[tool calls: " + strings.Join(calls, "; ") + "]"
 			}
 			lines = append(lines, line)
 		case zeroruntime.MessageRoleTool:
-			lines = append(lines, "tool result: "+clampForSummary(message.Content, summaryToolResultClamp))
+			lines = append(lines, "tool result: "+message.Content)
 		default:
 			lines = append(lines, string(message.Role)+": "+message.Content)
 		}

internal/agent/compaction_cheap_test.go

@@ -1,469 +0,0 @@
-package agent
-
-import (
-	"context"
-	"errors"
-	"strings"
-	"testing"
-
-	"github.com/Gitlawb/zero/internal/tools"
-	"github.com/Gitlawb/zero/internal/zeroruntime"
-)
-
-// compactableHistory returns a history whose middle is large enough to trip
-// the proactive threshold for a 1000-token window.
-func compactableHistory() []zeroruntime.Message {
-	return []zeroruntime.Message{
-		{Role: zeroruntime.MessageRoleSystem, Content: "sys"},
-		{Role: zeroruntime.MessageRoleUser, Content: strings.Repeat("u", 4000)},
-		{Role: zeroruntime.MessageRoleAssistant, Content: strings.Repeat("a", 4000)},
-		{Role: zeroruntime.MessageRoleUser, Content: "u2"},
-		{Role: zeroruntime.MessageRoleAssistant, Content: "a2"},
-		{Role: zeroruntime.MessageRoleUser, Content: "u3"},
-	}
-}
-
-// Summarization must run on the dedicated (cheap) summarizer when one is
-// configured — the main provider sees no summarize traffic at all.
-func TestMaybeCompactUsesDedicatedSummarizer(t *testing.T) {
-	cheap := &mockProvider{turns: [][]zeroruntime.StreamEvent{{
-		{Type: zeroruntime.StreamEventText, Content: "CHEAP SUMMARY"},
-		{Type: zeroruntime.StreamEventDone},
-	}}}
-	main := &mockProvider{}
-	factoryCalls := 0
-	state := newCompactionState(Options{
-		ContextWindow:          1000,
-		CompactionPreserveLast: 2,
-		Summarizer: func(context.Context, string) (Provider, error) {
-			factoryCalls++
-			return cheap, nil
-		},
-	}, nil)
-
-	compacted := state.maybeCompact(context.Background(), main, compactableHistory(), nil)
-
-	if len(cheap.requests) == 0 {
-		t.Fatal("dedicated summarizer never received the summarize call")
-	}
-	if len(main.requests) != 0 {
-		t.Fatalf("main provider must see no summarize traffic, got %d requests", len(main.requests))
-	}
-	if factoryCalls != 1 {
-		t.Fatalf("summarizer factory calls = %d, want 1 (lazy, memoized)", factoryCalls)
-	}
-	if estimateTokens(compacted) >= estimateTokens(compactableHistory()) {
-		t.Fatal("compaction did not shrink the history")
-	}
-	found := false
-	for _, message := range compacted {
-		if strings.Contains(message.Content, "CHEAP SUMMARY") {
-			found = true
-		}
-	}
-	if !found {
-		t.Fatal("cheap summarizer's summary missing from the compacted history")
-	}
-}
-
-// A failing summarizer falls back to the main provider for the SAME slice and
-// stays broken for the rest of the run — no repeated failed cheap calls.
-func TestSummarizerFailureFallsBackToMainAndSticks(t *testing.T) {
-	broken := &mockProvider{turns: [][]zeroruntime.StreamEvent{{
-		{Type: zeroruntime.StreamEventError, Error: "boom: model not found"},
-	}}}
-	main := &mockProvider{turns: [][]zeroruntime.StreamEvent{
-		{{Type: zeroruntime.StreamEventText, Content: "MAIN SUMMARY"}, {Type: zeroruntime.StreamEventDone}},
-		{{Type: zeroruntime.StreamEventText, Content: "MAIN SUMMARY 2"}, {Type: zeroruntime.StreamEventDone}},
-	}}
-	state := newCompactionState(Options{
-		ContextWindow:          1000,
-		CompactionPreserveLast: 2,
-		Summarizer:             func(context.Context, string) (Provider, error) { return broken, nil },
-	}, nil)
-	summarize := state.summarizeClosure(context.Background(), main)
-	input := []zeroruntime.Message{{Role: zeroruntime.MessageRoleUser, Content: "history"}}
-
-	summary, err := summarize(input)
-	if err != nil {
-		t.Fatalf("fallback must succeed via the main provider: %v", err)
-	}
-	if summary != "MAIN SUMMARY" {
-		t.Fatalf("summary = %q, want the main provider's", summary)
-	}
-	if len(broken.requests) != 1 {
-		t.Fatalf("broken summarizer requests = %d, want exactly 1", len(broken.requests))
-	}
-	if !state.summarizerBroken {
-		t.Fatal("a failed summarizer must be marked broken for the run")
-	}
-
-	// Second summarization: straight to main, no cheap retry.
-	if _, err := summarize(input); err != nil {
-		t.Fatal(err)
-	}
-	if len(broken.requests) != 1 {
-		t.Fatalf("broken summarizer was retried (%d requests)", len(broken.requests))
-	}
-	if len(main.requests) != 2 {
-		t.Fatalf("main provider requests = %d, want 2", len(main.requests))
-	}
-}
-
-// A factory that errors (misconfigured model) is equivalent to no summarizer:
-// main provider used, factory not retried.
-func TestSummarizerFactoryErrorFallsBack(t *testing.T) {
-	main := &mockProvider{turns: [][]zeroruntime.StreamEvent{{
-		{Type: zeroruntime.StreamEventText, Content: "MAIN SUMMARY"},
-		{Type: zeroruntime.StreamEventDone},
-	}}}
-	factoryCalls := 0
-	state := newCompactionState(Options{
-		ContextWindow:          1000,
-		CompactionPreserveLast: 2,
-		Summarizer: func(context.Context, string) (Provider, error) {
-			factoryCalls++
-			return nil, errors.New("unknown model")
-		},
-	}, nil)
-	summarize := state.summarizeClosure(context.Background(), main)
-
-	summary, err := summarize([]zeroruntime.Message{{Role: zeroruntime.MessageRoleUser, Content: "history"}})
-	if err != nil || summary != "MAIN SUMMARY" {
-		t.Fatalf("summary = %q, err = %v; want main provider fallback", summary, err)
-	}
-	if factoryCalls != 1 {
-		t.Fatalf("factory calls = %d, want 1 (sticky failure)", factoryCalls)
-	}
-	if _, dedicated := state.summarizeProvider(context.Background(), main); dedicated {
-		t.Fatal("after a factory failure the run must stay on the main provider")
-	}
-	if factoryCalls != 1 {
-		t.Fatalf("factory retried after failure (%d calls)", factoryCalls)
-	}
-}
-
-// Tool payloads are clamped in the summarizer transcript: results to
-// summaryToolResultClamp, call arguments to summaryToolArgsClamp.
-func TestRenderTranscriptClampsToolPayloads(t *testing.T) {
-	bigResult := strings.Repeat("r", 50_000)
-	bigArgs := strings.Repeat("w", 20_000)
-	transcript := renderTranscript([]zeroruntime.Message{
-		{Role: zeroruntime.MessageRoleAssistant, Content: "editing", ToolCalls: []zeroruntime.ToolCall{
-			{ID: "c1", Name: "write_file", Arguments: bigArgs},
-		}},
-		{Role: zeroruntime.MessageRoleTool, ToolCallID: "c1", Content: bigResult},
-		{Role: zeroruntime.MessageRoleUser, Content: "keep going"},
-	})
-
-	if len(transcript) > summaryToolResultClamp+summaryToolArgsClamp+1024 {
-		t.Fatalf("transcript is %d bytes; clamps did not apply", len(transcript))
-	}
-	if !strings.Contains(transcript, "chars omitted for summarization") {
-		t.Fatal("clamped transcript must carry the omission marker")
-	}
-	if !strings.Contains(transcript, "keep going") {
-		t.Fatal("non-tool content must survive unclamped")
-	}
-	// Head AND tail of the clamped payloads survive.
-	if !strings.HasPrefix(transcript[strings.Index(transcript, "tool result: ")+len("tool result: "):], "r") ||
-		!strings.Contains(transcript, "rrr\n\nuser: keep going") {
-		t.Fatalf("head/tail of the tool result lost:\n%s", transcript[:200])
-	}
-}
-
-// bigToolHistory returns a history with n large tool results (~40k estimated
-// tokens each): the trailing protection window keeps the newest verbatim,
-// the older ones are prunable.
-func bigToolHistory(n int) []zeroruntime.Message {
-	bigBody := strings.Repeat("x", 160_000)
-	messages := []zeroruntime.Message{{Role: zeroruntime.MessageRoleSystem, Content: "sys"}}
-	for i := 0; i < n; i++ {
-		id := string(rune('a' + i))
-		messages = append(messages,
-			zeroruntime.Message{Role: zeroruntime.MessageRoleAssistant, ToolCalls: []zeroruntime.ToolCall{{ID: id, Name: "read_file", Arguments: "{\"path\":\"" + id + "\"}"}}},
-			zeroruntime.Message{Role: zeroruntime.MessageRoleTool, ToolCallID: id, Content: bigBody},
-		)
-	}
-	return append(messages, zeroruntime.Message{Role: zeroruntime.MessageRoleUser, Content: "go"})
-}
-
-func summaryProvider(text string) *mockProvider {
-	return &mockProvider{turns: [][]zeroruntime.StreamEvent{
-		{{Type: zeroruntime.StreamEventText, Content: text}, {Type: zeroruntime.StreamEventDone}},
-		{{Type: zeroruntime.StreamEventText, Content: text}, {Type: zeroruntime.StreamEventDone}},
-	}}
-}
-
-// A context-limit error is first answered with the free prune stage; when the
-// pruned history fits the window the retry is free (no summarizer call) and
-// the one-shot reactive budget is untouched. The paid summarizer only runs
-// when a later error finds nothing left to prune.
-func TestRecoverPrunesBeforeSummarizing(t *testing.T) {
-	provider := summaryProvider("SUMMARY")
-	// The protected trailing tool output (~40k tokens) must fit the window.
-	state := newCompactionState(Options{ContextWindow: 200_000, CompactionPreserveLast: 2}, nil)
-	messages := bigToolHistory(5)
-
-	pruned, retried, err := state.recover(context.Background(), provider, messages, nil, "maximum context length exceeded")
-	if err != nil {
-		t.Fatal(err)
-	}
-	if !retried {
-		t.Fatal("prunable history that fits must produce a free retry")
-	}
-	if len(provider.requests) != 0 {
-		t.Fatalf("free prune stage must not call the summarizer (%d requests)", len(provider.requests))
-	}
-	if state.reactiveAttempted {
-		t.Fatal("a free prune retry must not consume the reactive budget")
-	}
-	if estimateTokens(pruned) >= estimateTokens(messages) {
-		t.Fatal("prune did not shrink the history")
-	}
-
-	// Second context-limit error on the pruned history: nothing meaningfully
-	// prunable remains, so the paid summarizer fires and consumes the budget.
-	_, retried, err = state.recover(context.Background(), provider, pruned, nil, "maximum context length exceeded")
-	if err != nil {
-		t.Fatal(err)
-	}
-	if !retried {
-		t.Fatal("second recover must compact and retry")
-	}
-	if len(provider.requests) == 0 {
-		t.Fatal("second recover must reach the summarizer")
-	}
-	if !state.reactiveAttempted {
-		t.Fatal("a paid recover must consume the reactive budget")
-	}
-}
-
-// When pruning reclaims something but the pruned history still exceeds the
-// window, recover falls through to the paid summarizer in the SAME call
-// instead of spending a retry that would fail the same way.
-func TestRecoverFallsThroughToSummarizerWhenPruneIsInsufficient(t *testing.T) {
-	provider := summaryProvider("SUMMARY")
-	// A 1,000-token window: even the protected trailing output overflows it.
-	state := newCompactionState(Options{ContextWindow: 1000, CompactionPreserveLast: 2}, nil)
-	messages := bigToolHistory(5)
-
-	compacted, retried, err := state.recover(context.Background(), provider, messages, nil, "maximum context length exceeded")
-	if err != nil {
-		t.Fatal(err)
-	}
-	if !retried {
-		t.Fatal("insufficient prune must still end in a retry via summarization")
-	}
-	if len(provider.requests) == 0 {
-		t.Fatal("insufficient prune must reach the summarizer in the same recover call")
-	}
-	if !state.reactiveAttempted {
-		t.Fatal("the paid summarizer consumes the reactive budget")
-	}
-	if estimateTokens(compacted) >= estimateTokens(messages) {
-		t.Fatal("recover did not shrink the history")
-	}
-}
-
-// The free prune stage is not gated behind the one-shot budget: after a paid
-// reactive compaction, a later context-limit error still gets a free retry
-// when pruning makes the history fit.
-func TestRecoverFreePruneRunsAfterBudgetIsSpent(t *testing.T) {
-	provider := summaryProvider("SUMMARY")
-	state := newCompactionState(Options{ContextWindow: 200_000, CompactionPreserveLast: 2}, nil)
-	state.reactiveAttempted = true
-	messages := bigToolHistory(5)
-
-	pruned, retried, err := state.recover(context.Background(), provider, messages, nil, "maximum context length exceeded")
-	if err != nil {
-		t.Fatal(err)
-	}
-	if !retried || len(provider.requests) != 0 {
-		t.Fatalf("free prune must retry without the summarizer even when the budget is spent (retried=%v, requests=%d)", retried, len(provider.requests))
-	}
-	if estimateTokens(pruned) >= estimateTokens(messages) {
-		t.Fatal("prune did not shrink the history")
-	}
-	// With nothing left to prune and the budget spent, the caller keeps its
-	// original error — recover neither loops nor summarizes.
-	_, retried, err = state.recover(context.Background(), provider, pruned, nil, "maximum context length exceeded")
-	if err != nil || retried || len(provider.requests) != 0 {
-		t.Fatalf("spent budget must not summarize again (retried=%v, requests=%d, err=%v)", retried, len(provider.requests), err)
-	}
-}
-
-// The free-retry gate compares against the window the provider enforces, not
-// the 70% proactive threshold: a history pruned to ~80% of the window still
-// takes the free retry.
-func TestRecoverFreeRetryGateUsesWindowNotThreshold(t *testing.T) {
-	provider := summaryProvider("SUMMARY")
-	messages := bigToolHistory(5)
-	pruned, _ := pruneStaleToolOutput(messages, 2)
-	prunedTokens := estimateTokens(pruned)
-	// Choose a window so the pruned size sits between 70% and 95% of it.
-	window := prunedTokens * 100 / 80
-	state := newCompactionState(Options{ContextWindow: window, CompactionPreserveLast: 2}, nil)
-	if prunedTokens <= state.threshold {
-		t.Fatalf("test setup: pruned size %d must exceed the proactive threshold %d", prunedTokens, state.threshold)
-	}
-
-	_, retried, err := state.recover(context.Background(), provider, messages, nil, "maximum context length exceeded")
-	if err != nil {
-		t.Fatal(err)
-	}
-	if !retried || len(provider.requests) != 0 {
-		t.Fatalf("a history that fits the window must take the free retry (retried=%v, requests=%d)", retried, len(provider.requests))
-	}
-}
-
-// After a mid-run model switch the summarizer is re-resolved against the new
-// main model: a run that started on the cheap model (no dedicated summarizer)
-// and escalated gets a cheap summarizer, and a previously broken one is
-// retried for the new model.
-func TestSwitchModelReresolvesSummarizer(t *testing.T) {
-	cheap := summaryProvider("CHEAP SUMMARY")
-	main := summaryProvider("MAIN SUMMARY")
-	var factoryModels []string
-	state := newCompactionState(Options{
-		ContextWindow:          1000,
-		CompactionPreserveLast: 2,
-		Model:                  "cheap-model",
-		Summarizer: func(_ context.Context, mainModelID string) (Provider, error) {
-			factoryModels = append(factoryModels, mainModelID)
-			if mainModelID == "cheap-model" {
-				return nil, nil // main already is the cheap model
-			}
-			return cheap, nil
-		},
-	}, nil)
-
-	if _, dedicated := state.summarizeProvider(context.Background(), main); dedicated {
-		t.Fatal("on the cheap model the main provider must summarize")
-	}
-	if _, dedicated := state.summarizeProvider(context.Background(), main); dedicated || len(factoryModels) != 1 {
-		t.Fatalf("factory must run once per main model, calls=%v", factoryModels)
-	}
-
-	state.switchModel("big-model", 400_000)
-	if state.threshold != compactionThreshold(400_000) || state.window != 400_000 {
-		t.Fatalf("switchModel must re-derive the window, got threshold=%d window=%d", state.threshold, state.window)
-	}
-	if got, dedicated := state.summarizeProvider(context.Background(), main); !dedicated || got != Provider(cheap) {
-		t.Fatal("after escalating to an expensive model the dedicated cheap summarizer must be used")
-	}
-	if len(factoryModels) != 2 || factoryModels[1] != "big-model" {
-		t.Fatalf("factory must be re-invoked with the new main model, calls=%v", factoryModels)
-	}
-
-	// A broken summarizer is retried after the next switch.
-	state.summarizerBroken = true
-	if _, dedicated := state.summarizeProvider(context.Background(), main); dedicated {
-		t.Fatal("a broken summarizer must fall back to main")
-	}
-	state.switchModel("other-model", 0)
-	if got, dedicated := state.summarizeProvider(context.Background(), main); !dedicated || got != Provider(cheap) {
-		t.Fatal("a model switch must clear the broken flag and rebuild the summarizer")
-	}
-}
-
-func TestCompactionUpdateWindow(t *testing.T) {
-	state := newCompactionState(Options{ContextWindow: 100_000, CompactionPreserveLast: 2}, nil)
-	state.lowWaterMark = 50_000
-	before := state.threshold
-
-	state.updateWindow(0) // unknown model: unchanged
-	if state.threshold != before || state.lowWaterMark != 50_000 {
-		t.Fatal("updateWindow(0) must be a no-op")
-	}
-
-	state.updateWindow(10_000)
-	if state.threshold >= before {
-		t.Fatalf("threshold = %d, want re-derived below %d", state.threshold, before)
-	}
-	if state.lowWaterMark != 0 {
-		t.Fatal("low-water mark must reset on a window change")
-	}
-	if !state.enabled {
-		t.Fatal("a positive window must keep compaction enabled")
-	}
-}
-
-// End-to-end: after escalate_model switches providers, the loop re-derives the
-// context window via ContextWindowFor, visible in the OnContext report.
-func TestRunEscalationRederivesContextWindow(t *testing.T) {
-	registry := tools.NewRegistry()
-	registry.Register(escalatingTool{target: "big-model"})
-	switched := &mockProvider{turns: [][]zeroruntime.StreamEvent{{
-		{Type: zeroruntime.StreamEventText, Content: "done"},
-		{Type: zeroruntime.StreamEventDone},
-	}}}
-	provider := &mockProvider{turns: [][]zeroruntime.StreamEvent{{
-		{Type: zeroruntime.StreamEventToolCallStart, ToolCallID: "call-1", ToolName: "escalate"},
-		{Type: zeroruntime.StreamEventToolCallDelta, ToolCallID: "call-1", ArgumentsFragment: `{}`},
-		{Type: zeroruntime.StreamEventToolCallEnd, ToolCallID: "call-1"},
-		{Type: zeroruntime.StreamEventDone},
-	}}}
-
-	var windows []int
-	result, err := Run(context.Background(), "go", provider, Options{
-		Registry:      registry,
-		ContextWindow: 100_000,
-		Model:         "small-model",
-		ModelSwitcher: func(context.Context, string) (Provider, error) { return switched, nil },
-		ContextWindowFor: func(modelID string) int {
-			if modelID == "big-model" {
-				return 400_000
-			}
-			return 0
-		},
-		OnContext: func(breakdown ContextBreakdown) { windows = append(windows, breakdown.ContextWindow) },
-	})
-	if err != nil {
-		t.Fatal(err)
-	}
-	if result.FinalAnswer != "done" {
-		t.Fatalf("final answer = %q", result.FinalAnswer)
-	}
-	if len(windows) < 2 {
-		t.Fatalf("expected at least 2 OnContext reports, got %d", len(windows))
-	}
-	if windows[0] != 100_000 {
-		t.Fatalf("turn 1 window = %d, want the original 100000", windows[0])
-	}
-	if windows[len(windows)-1] != 400_000 {
-		t.Fatalf("post-escalation window = %d, want 400000", windows[len(windows)-1])
-	}
-}
-
-// nonComparableProvider has a slice field, so comparing two Provider interface
-// values holding it would panic; the summarizer path must never compare them.
-type nonComparableProvider struct {
-	inner *mockProvider
-	tags  []string
-}
-
-func (p nonComparableProvider) StreamCompletion(ctx context.Context, request zeroruntime.CompletionRequest) (<-chan zeroruntime.StreamEvent, error) {
-	return p.inner.StreamCompletion(ctx, request)
-}
-
-func TestSummarizeClosureNeverComparesProviderValues(t *testing.T) {
-	broken := &mockProvider{turns: [][]zeroruntime.StreamEvent{{
-		{Type: zeroruntime.StreamEventError, Error: "boom: model not found"},
-	}}}
-	main := nonComparableProvider{inner: summaryProvider("MAIN SUMMARY"), tags: []string{"x"}}
-	state := newCompactionState(Options{
-		ContextWindow:          1000,
-		CompactionPreserveLast: 2,
-		Summarizer:             func(context.Context, string) (Provider, error) { return nonComparableProvider{inner: broken}, nil },
-	}, nil)
-	summary, err := state.summarizeClosure(context.Background(), main)([]zeroruntime.Message{{Role: zeroruntime.MessageRoleUser, Content: "history"}})
-	if err != nil || summary != "MAIN SUMMARY" {
-		t.Fatalf("fallback with non-comparable providers must not panic and must use main, got %q err=%v", summary, err)
-	}
-	// And with no dedicated summarizer at all the closure still works.
-	state = newCompactionState(Options{ContextWindow: 1000, CompactionPreserveLast: 2}, nil)
-	if _, err := state.summarizeClosure(context.Background(), main)([]zeroruntime.Message{{Role: zeroruntime.MessageRoleUser, Content: "history"}}); err != nil {
-		t.Fatal(err)
-	}
-}

internal/agent/loop.go

@@ -846,21 +846,11 @@ func Run(ctx context.Context, prompt string, provider Provider, options Options)
 					options.ServiceTier = ""
 					planner.config.serviceTier = ""
 					options.Trace.Counter(trace.CounterModelSwitches, 1)
-					// Re-derive the context window for the new model so compaction and
-					// the OnContext budget report track the model actually in force —
-					// without this a switch to a smaller-window model can overflow the
-					// target, and a switch to a larger one over-compacts. An unknown
-					// model (<= 0) keeps the original window. The compactor also
-					// re-resolves its dedicated summarizer against the new model.
-					window := 0
-					if options.ContextWindowFor != nil {
-						window = options.ContextWindowFor(turnRequestedModel)
-					}
-					if window > 0 {
-						options.ContextWindow = window
-						planner.config.contextWindow = window
-					}
-					compactor.switchModel(turnRequestedModel, window)
+					// KNOWN LIMITATION (deferred): the compactor's context-window budget
+					// is fixed at run start from options.ContextWindow and is NOT updated
+					// here, so a switch to a model with a different window keeps compacting
+					// against the original budget. Fixing it needs the switcher to also
+					// report the new window — out of scope for this change.
 				}
 			}
 		}

internal/agent/types.go

@@ -348,26 +348,10 @@ type Options struct {
 	// CompactionPreserveLast is how many trailing messages compaction keeps
 	// verbatim. <= 0 falls back to defaultCompactionPreserveLast.
 	CompactionPreserveLast int
-	// Summarizer, when set, lazily builds the provider used for compaction
-	// summarization calls — typically a cheap/fast model, since summaries at
-	// main-model prices are the single most expensive recurring event in a
-	// long run. It receives the main model currently in force and may return
-	// (nil, nil) when no dedicated summarizer applies to it (the main model is
-	// already the cheap one). Built on the first paid compaction and again
-	// after a mid-run model switch. Any failure (build or call) falls back to
-	// the run's main provider until the next switch, so a misconfigured
-	// summarizer can never break compaction. nil keeps today's behavior.
-	Summarizer func(ctx context.Context, mainModelID string) (Provider, error)
-	// ContextWindowFor, when set, resolves a model ID to its context window so
-	// the compactor can re-derive its threshold after a mid-run model switch
-	// (escalate_model). Without it a switch keeps compacting against the
-	// original model's window — overflowing a smaller target or over-compacting
-	// a larger one. Return <= 0 when the model is unknown (window unchanged).
-	ContextWindowFor func(modelID string) int
-	Registry         *tools.Registry
-	PermissionMode   PermissionMode
-	Autonomy         string
-	Sandbox          *sandbox.Engine
+	Registry               *tools.Registry
+	PermissionMode         PermissionMode
+	Autonomy               string
+	Sandbox                *sandbox.Engine
 	// FileTracker records per-session file read/write versions so the write tools
 	// can detect a file changed on disk outside Zero since it was last read. nil
 	// disables the check. Created once per session and threaded into every tool run.

internal/cli/acp.go

@@ -10,11 +10,9 @@ import (
 	"github.com/Gitlawb/zero/internal/acp"
 	"github.com/Gitlawb/zero/internal/agent"
 	"github.com/Gitlawb/zero/internal/config"
-	"github.com/Gitlawb/zero/internal/execution"
-	"github.com/Gitlawb/zero/internal/mcp"
 	"github.com/Gitlawb/zero/internal/providermodeldiscovery"
-	"github.com/Gitlawb/zero/internal/redaction"
 	"github.com/Gitlawb/zero/internal/sandbox"
+	"github.com/Gitlawb/zero/internal/tools"
 )
 
 const acpUsage = `zero acp — serve the Agent Client Protocol (ACP) over stdio
@@ -59,8 +57,20 @@ func runACP(args []string, stdout io.Writer, stderr io.Writer, deps appDeps) int
 		// surface — no ACP-specific credential handling needed.
 		NewProvider: deps.newProvider,
 		RunAgent:    agent.Run,
-		BuildWorkspace: func(ctx context.Context, workspaceRoot string, resolved config.ResolvedConfig, mode agent.PermissionMode) (*acp.Workspace, error) {
-			return buildACPWorkspace(ctx, workspaceRoot, resolved, mode, deps)
+		// Build the SCOPED registry + sandbox engine per workspace, exactly like the
+		// exec surface, so ACP shell/file tools are confined — never run unconfined.
+		BuildWorkspace: func(workspaceRoot string, resolved config.ResolvedConfig) (*tools.Registry, *sandbox.Engine, error) {
+			scope, err := sandbox.NewScope(workspaceRoot, resolved.Sandbox.AdditionalWriteRoots)
+			if err != nil {
+				return nil, nil, err
+			}
+			engine, err := buildExecSandboxEngine(workspaceRoot, resolved, deps, scope)
+			if err != nil {
+				return nil, nil, err
+			}
+			registry := newCoreRegistryScoped(workspaceRoot, scope)
+			registerLocalControlTools(registry, workspaceRoot, resolved.LocalControl)
+			return registry, engine, nil
 		},
 		ResolveWorkspaceRoot: acpWorkspaceRootResolver(deps),
 		Store:                deps.newSessionStore(),
@@ -75,76 +85,6 @@ func runACP(args []string, stdout io.Writer, stderr io.Writer, deps appDeps) int
 	return exitSuccess
 }
 
-// buildACPWorkspace matches exec's registry construction for one ACP turn. MCP
-// servers use the same sandbox-prepared execution runner, project configuration is
-// gated by the validated workspace's trust state, and their runtime is released
-// when acp.Agent completes the turn. ACP deliberately stays at low autonomy: an
-// editor connection never upgrades MCP permissions beyond an interactive prompt.
-func buildACPWorkspace(ctx context.Context, workspaceRoot string, resolved config.ResolvedConfig, mode agent.PermissionMode, deps appDeps) (*acp.Workspace, error) {
-	scope, err := sandbox.NewScope(workspaceRoot, resolved.Sandbox.AdditionalWriteRoots)
-	if err != nil {
-		return nil, err
-	}
-	engine, err := buildExecSandboxEngine(workspaceRoot, resolved, deps, scope)
-	if err != nil {
-		return nil, err
-	}
-	registry := newCoreRegistryScoped(workspaceRoot, scope)
-
-	workspace := &acp.Workspace{
-		Registry: registry, Sandbox: engine,
-		DeferThreshold: resolved.Tools.DeferThreshold,
-	}
-	if mode != agent.PermissionModePlan {
-		// MCP stdio servers are subprocesses. Passing the engine to their runner
-		// keeps them inside the exact sandbox / lifecycle path used by zero exec.
-		runtime, trustSkip, err := registerMCPToolsForWorkspaceWithOptions(
-			ctx, workspaceRoot, registry, deps, mcp.AutonomyLow, workspaceRoot,
-			mcp.RegisterOptions{Execution: execution.NewRunner(engine), AdvertiseInAuto: true},
-		)
-		if err != nil {
-			// RegisterTools may have connected an earlier server before reporting a
-			// later failure, so do not orphan a partial runtime on this error path.
-			if runtime != nil {
-				_ = runtime.Close()
-			}
-			return nil, err
-		}
-		workspace.Cleanup = runtime.Close
-		workspace.Notices = acpMCPSetupNotices(trustSkip, runtime)
-	}
-	registerLocalControlTools(registry, workspaceRoot, resolved.LocalControl)
-	// MCP tools are deferred-eligible. Register their loader only after every
-	// ACP-visible tool is present, using the same mode the agent receives.
-	registerToolSearchIfEligible(registry, resolved.Tools.DeferThreshold, mode, nil, nil)
-	return workspace, nil
-}
-
-func acpMCPSetupNotices(skip trustSkip, runtime mcpToolRuntime) []string {
-	var notices []string
-	if skip.excludedProjectConfig {
-		if skip.trustCheckErrored {
-			notices = append(notices, "The workspace-trust store could not be read; project MCP servers were ignored (fail-closed). Run 'zero trust' to enable them.")
-		} else {
-			notices = append(notices, "Project MCP servers were ignored in this untrusted workspace. Run 'zero trust' to enable them.")
-		}
-	}
-	if runtime == nil {
-		return notices
-	}
-	for _, skipped := range runtime.Skipped() {
-		if skipped.UnconfiguredDefault {
-			continue
-		}
-		message := fmt.Sprintf("MCP server %s unavailable, skipped", skipped.Name)
-		if skipped.Err != nil {
-			message += ": " + redaction.ErrorMessage(skipped.Err, redaction.Options{})
-		}
-		notices = append(notices, redaction.RedactString(message, redaction.Options{}))
-	}
-	return notices
-}
-
 // acpWorkspaceRootResolver validates a client-supplied cwd into a confinement
 // root. It reuses exec's resolveWorkspaceRoot (abs+clean, must be an existing
 // dir) and additionally rejects the filesystem root and the home directory — an

internal/cli/acp_test.go

@@ -5,19 +5,10 @@ import (
 	"context"
 	"errors"
 	"io"
-	"os"
-	"path/filepath"
 	"strings"
 	"sync"
 	"testing"
 	"time"
-
-	"github.com/Gitlawb/zero/internal/agent"
-	"github.com/Gitlawb/zero/internal/config"
-	"github.com/Gitlawb/zero/internal/mcp"
-	"github.com/Gitlawb/zero/internal/sandbox"
-	"github.com/Gitlawb/zero/internal/tools"
-	"github.com/Gitlawb/zero/internal/workspacetrust"
 )
 
 type acpTestReader func([]byte) (int, error)
@@ -117,198 +108,6 @@ func TestRunACPIdleCancellationExitsCleanly(t *testing.T) {
 	}
 }
 
-func TestBuildACPWorkspaceRegistersSandboxedMCPToolsAndClosesThem(t *testing.T) {
-	setTrustConfigRoot(t)
-	workspaceRoot := t.TempDir()
-	if err := workspacetrust.Trust(workspaceRoot); err != nil {
-		t.Fatalf("trust workspace: %v", err)
-	}
-	grantStore, err := sandbox.NewGrantStore(sandbox.StoreOptions{FilePath: t.TempDir() + "/grants.json"})
-	if err != nil {
-		t.Fatalf("new grant store: %v", err)
-	}
-
-	var gotExclude, registered, closed bool
-	deps := fillAppDeps(appDeps{
-		resolveMCPConfig: func(root string, excludeProject bool) (config.MCPConfig, error) {
-			if root != workspaceRoot {
-				t.Fatalf("MCP workspace root = %q, want %q", root, workspaceRoot)
-			}
-			gotExclude = excludeProject
-			return config.MCPConfig{Servers: map[string]config.MCPServerConfig{
-				"docs": {Type: "stdio", Command: "fake-docs"},
-			}}, nil
-		},
-		newMCPStore:     func() (*mcp.PermissionStore, error) { return nil, nil },
-		newSandboxStore: func() (*sandbox.GrantStore, error) { return grantStore, nil },
-		registerMCPTools: func(ctx context.Context, registry *tools.Registry, cfg config.MCPConfig, options mcp.RegisterOptions) (mcpToolRuntime, error) {
-			if ctx == nil {
-				t.Fatal("MCP registration received nil context")
-			}
-			if len(cfg.Servers) != 1 || cfg.Servers["docs"].Command != "fake-docs" {
-				t.Fatalf("MCP config = %+v", cfg)
-			}
-			if options.Autonomy != mcp.AutonomyLow {
-				t.Fatalf("MCP autonomy = %q, want low", options.Autonomy)
-			}
-			if options.Execution == nil {
-				t.Fatal("MCP stdio server was not given the sandbox execution runner")
-			}
-			if options.WorkspaceRoot != workspaceRoot {
-				t.Fatalf("MCP execution workspace = %q, want %q", options.WorkspaceRoot, workspaceRoot)
-			}
-			if !options.AdvertiseInAuto {
-				t.Fatal("ACP MCP tools must be advertised in auto mode without being pre-approved")
-			}
-			registered = true
-			registry.Register(cliFakeDeferredTool{
-				name: "mcp_docs_search", permission: tools.PermissionPrompt,
-				advertiseInAuto: options.AdvertiseInAuto,
-			})
-			return closeFunc(func() error {
-				closed = true
-				return nil
-			}), nil
-		},
-	})
-
-	workspace, err := buildACPWorkspace(context.Background(), workspaceRoot, config.ResolvedConfig{
-		Tools: config.ToolsConfig{DeferThreshold: 1},
-	}, agent.PermissionModeAuto, deps)
-	if err != nil {
-		t.Fatalf("buildACPWorkspace: %v", err)
-	}
-	if gotExclude {
-		t.Fatal("trusted ACP workspace excluded project MCP configuration")
-	}
-	if !registered {
-		t.Fatal("ACP workspace did not register configured MCP tools")
-	}
-	if _, ok := workspace.Registry.Get("mcp_docs_search"); !ok {
-		t.Fatal("MCP tool is absent from ACP agent registry")
-	}
-	if _, ok := workspace.Registry.Get(tools.ToolSearchToolName); !ok {
-		t.Fatal("ACP registry is missing tool_search for deferred MCP tools")
-	}
-	if workspace.DeferThreshold != 1 {
-		t.Fatalf("workspace defer threshold = %d, want 1", workspace.DeferThreshold)
-	}
-	if err := workspace.Close(); err != nil {
-		t.Fatalf("close ACP workspace: %v", err)
-	}
-	if !closed {
-		t.Fatal("ACP workspace did not close its MCP runtime")
-	}
-}
-
-func TestBuildACPWorkspacePreservesRedactedMCPSetupNotices(t *testing.T) {
-	setTrustConfigRoot(t)
-	workspaceRoot := t.TempDir()
-	if err := os.MkdirAll(filepath.Join(workspaceRoot, ".zero"), 0o755); err != nil {
-		t.Fatal(err)
-	}
-	projectConfig := `{"mcp":{"servers":{"project-docs":{"type":"stdio","command":"project-docs"}}}}`
-	if err := os.WriteFile(filepath.Join(workspaceRoot, ".zero", "config.json"), []byte(projectConfig), 0o600); err != nil {
-		t.Fatal(err)
-	}
-	secret := "ghp_ABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789"
-	grantStore, err := sandbox.NewGrantStore(sandbox.StoreOptions{FilePath: filepath.Join(t.TempDir(), "grants.json")})
-	if err != nil {
-		t.Fatal(err)
-	}
-	deps := fillAppDeps(appDeps{
-		resolveMCPConfig: func(string, bool) (config.MCPConfig, error) {
-			return config.MCPConfig{Servers: map[string]config.MCPServerConfig{
-				"docs": {Type: "stdio", Command: "fake-docs"},
-			}}, nil
-		},
-		newMCPStore:     func() (*mcp.PermissionStore, error) { return nil, nil },
-		newSandboxStore: func() (*sandbox.GrantStore, error) { return grantStore, nil },
-		registerMCPTools: func(context.Context, *tools.Registry, config.MCPConfig, mcp.RegisterOptions) (mcpToolRuntime, error) {
-			return fakeMCPRuntimeWithSkips{skipped: []mcp.SkippedServer{{
-				Name: "docs", Err: errors.New("token=" + secret),
-			}}}, nil
-		},
-	})
-
-	workspace, err := buildACPWorkspace(context.Background(), workspaceRoot, config.ResolvedConfig{}, agent.PermissionModeAuto, deps)
-	if err != nil {
-		t.Fatal(err)
-	}
-	defer workspace.Close()
-	joined := strings.Join(workspace.Notices, "\n")
-	if !strings.Contains(joined, "untrusted workspace") || !strings.Contains(joined, "MCP server docs unavailable") {
-		t.Fatalf("workspace notices = %#v", workspace.Notices)
-	}
-	if strings.Contains(joined, secret) || !strings.Contains(joined, "[REDACTED]") {
-		t.Fatalf("workspace notices leaked secret: %q", joined)
-	}
-}
-
-func TestBuildACPWorkspaceSkipsMCPInPlanMode(t *testing.T) {
-	grantStore, err := sandbox.NewGrantStore(sandbox.StoreOptions{FilePath: t.TempDir() + "/grants.json"})
-	if err != nil {
-		t.Fatalf("new grant store: %v", err)
-	}
-	called := false
-	deps := fillAppDeps(appDeps{
-		resolveMCPConfig: func(string, bool) (config.MCPConfig, error) {
-			called = true
-			return config.MCPConfig{}, nil
-		},
-		newSandboxStore: func() (*sandbox.GrantStore, error) { return grantStore, nil },
-		registerMCPTools: func(context.Context, *tools.Registry, config.MCPConfig, mcp.RegisterOptions) (mcpToolRuntime, error) {
-			called = true
-			return nil, nil
-		},
-	})
-
-	workspace, err := buildACPWorkspace(context.Background(), t.TempDir(), config.ResolvedConfig{}, agent.PermissionModePlan, deps)
-	if err != nil {
-		t.Fatalf("buildACPWorkspace: %v", err)
-	}
-	if called {
-		t.Fatal("plan-mode ACP workspace must not resolve or start MCP servers")
-	}
-	if err := workspace.Close(); err != nil {
-		t.Fatalf("close plan workspace: %v", err)
-	}
-}
-
-func TestBuildACPWorkspaceClosesPartialMCPRuntimeOnRegistrationError(t *testing.T) {
-	grantStore, err := sandbox.NewGrantStore(sandbox.StoreOptions{FilePath: t.TempDir() + "/grants.json"})
-	if err != nil {
-		t.Fatalf("new grant store: %v", err)
-	}
-	closed := false
-	deps := fillAppDeps(appDeps{
-		resolveMCPConfig: func(string, bool) (config.MCPConfig, error) {
-			return config.MCPConfig{Servers: map[string]config.MCPServerConfig{
-				"partial": {Type: "stdio", Command: "fake-partial"},
-			}}, nil
-		},
-		newMCPStore:     func() (*mcp.PermissionStore, error) { return nil, nil },
-		newSandboxStore: func() (*sandbox.GrantStore, error) { return grantStore, nil },
-		registerMCPTools: func(context.Context, *tools.Registry, config.MCPConfig, mcp.RegisterOptions) (mcpToolRuntime, error) {
-			return closeFunc(func() error {
-				closed = true
-				return nil
-			}), errors.New("second MCP server failed")
-		},
-	})
-
-	workspace, err := buildACPWorkspace(context.Background(), t.TempDir(), config.ResolvedConfig{}, agent.PermissionModeAuto, deps)
-	if err == nil {
-		t.Fatal("buildACPWorkspace succeeded after MCP registration error")
-	}
-	if workspace != nil {
-		t.Fatal("buildACPWorkspace returned a workspace after MCP registration error")
-	}
-	if !closed {
-		t.Fatal("partial MCP runtime was not closed after registration error")
-	}
-}
-
 type acpNotifyingReadCloser struct {
 	io.ReadCloser
 	readStarted chan<- struct{}

internal/cli/app.go

@@ -974,7 +974,6 @@ func runInteractiveTUIWithSetup(stderr io.Writer, deps appDeps, permissionMode a
 		FavoriteModels:       resolved.Preferences.FavoriteModels,
 		RecentModels:         resolved.Preferences.RecentModels,
 		RecapsEnabled:        resolved.Preferences.RecapsEnabled(),
-		CompactionModel:      resolved.Preferences.CompactionModel,
 		Provider:             provider,
 		NewProvider:          deps.newProvider,
 		NewTurnSessionProvider: func(profile config.ProviderProfile, provider zeroruntime.Provider) zeroruntime.TurnSessionProvider {

internal/cli/deferred_wiring_test.go

@@ -18,20 +18,14 @@ import (
 // cliFakeDeferredTool is deferred-eligible (implements Deferred() bool), mirroring
 // an MCP registry tool, so it counts toward the deferral threshold.
 type cliFakeDeferredTool struct {
-	name            string
-	permission      tools.Permission
-	advertiseInAuto bool
+	name string
 }
 
 func (t cliFakeDeferredTool) Name() string             { return t.name }
 func (t cliFakeDeferredTool) Description() string      { return "fake deferred tool" }
 func (t cliFakeDeferredTool) Parameters() tools.Schema { return tools.Schema{Type: "object"} }
 func (t cliFakeDeferredTool) Safety() tools.Safety {
-	permission := t.permission
-	if permission == "" {
-		permission = tools.PermissionAllow
-	}
-	return tools.Safety{SideEffect: tools.SideEffectNetwork, Permission: permission, AdvertiseInAuto: t.advertiseInAuto}
+	return tools.Safety{SideEffect: tools.SideEffectNetwork, Permission: tools.PermissionAllow}
 }
 func (t cliFakeDeferredTool) Run(context.Context, map[string]any) tools.Result {
 	return tools.Result{Status: tools.StatusOK, Output: "ok"}

internal/cli/exec.go

@@ -682,20 +682,16 @@ func runExec(args []string, stdout io.Writer, stderr io.Writer, deps appDeps) in
 		ModelSwitcher:        modelSwitcher,
 		TurnSessionProvider:  turnSessions,
 		ModelSessionSwitcher: modelSessionSwitcher,
-		Summarizer:           summarizerFactory(resolved, deps.newProvider),
-		ContextWindowFor: func(modelID string) int {
-			return modelregistry.AgentContextWindow(modelContextWindow(modelRegistry, modelID))
-		},
-		ReasoningEffort: forwardEffort,
-		Trace:           traceRecorder,
-		Cwd:             workspaceRoot,
-		Images:          images,
-		Registry:        registry,
-		PermissionMode:  permissionMode,
-		Autonomy:        options.autonomy,
-		SelfCorrect:     selfCorrector,
-		FileDiagnostics: fileDiagnostics,
-		Profile:         execProfile.Policy(displacedMaxTurns, execProfileFilledEffort),
+		ReasoningEffort:      forwardEffort,
+		Trace:                traceRecorder,
+		Cwd:                  workspaceRoot,
+		Images:               images,
+		Registry:             registry,
+		PermissionMode:       permissionMode,
+		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

internal/cli/mcp_tools.go

@@ -31,14 +31,6 @@ type mcpToolListItem struct {
 // into the one-line trust notice (mirroring the hooks and plugins chokepoints);
 // otherwise a workspace whose only project config is MCP would be gated silently.
 func registerMCPToolsForWorkspace(ctx context.Context, workspaceRoot string, registry *tools.Registry, deps appDeps, autonomy mcp.PermissionAutonomy, trustRoot string, runners ...*execution.Runner) (mcpToolRuntime, trustSkip, error) {
-	options := mcp.RegisterOptions{}
-	if len(runners) > 0 {
-		options.Execution = runners[0]
-	}
-	return registerMCPToolsForWorkspaceWithOptions(ctx, workspaceRoot, registry, deps, autonomy, trustRoot, options)
-}
-
-func registerMCPToolsForWorkspaceWithOptions(ctx context.Context, workspaceRoot string, registry *tools.Registry, deps appDeps, autonomy mcp.PermissionAutonomy, trustRoot string, options mcp.RegisterOptions) (mcpToolRuntime, trustSkip, error) {
 	excludeProject, trustCheckErrored := resolveTrust(trustRoot)
 	skip := trustSkip{
 		excludedProjectConfig: excludeProject && projectMCPConfigExists(workspaceRoot),
@@ -55,10 +47,16 @@ func registerMCPToolsForWorkspaceWithOptions(ctx context.Context, workspaceRoot
 	if err != nil {
 		return nil, skip, err
 	}
-	options.PermissionStore = store
-	options.Autonomy = autonomy
-	options.WorkspaceRoot = workspaceRoot
-	runtime, err := deps.registerMCPTools(ctx, registry, cfg, options)
+	var runner *execution.Runner
+	if len(runners) > 0 {
+		runner = runners[0]
+	}
+	runtime, err := deps.registerMCPTools(ctx, registry, cfg, mcp.RegisterOptions{
+		PermissionStore: store,
+		Autonomy:        autonomy,
+		Execution:       runner,
+		WorkspaceRoot:   workspaceRoot,
+	})
 	return runtime, skip, err
 }
 

internal/cli/summarizer.go

@@ -1,17 +0,0 @@
-package cli
-
-import (
-	"context"
-
-	"github.com/Gitlawb/zero/internal/agent"
-	"github.com/Gitlawb/zero/internal/config"
-	"github.com/Gitlawb/zero/internal/providers"
-	"github.com/Gitlawb/zero/internal/zeroruntime"
-)
-
-// summarizerFactory adapts the resolved profile and the authenticated provider
-// builder into agent.Options.Summarizer; the selection rules live in
-// providers.CompactionSummarizerFactory, shared with the TUI.
-func summarizerFactory(resolved config.ResolvedConfig, newProvider func(config.ProviderProfile) (zeroruntime.Provider, error)) func(context.Context, string) (agent.Provider, error) {
-	return providers.CompactionSummarizerFactory(resolved.Provider, resolved.Preferences.CompactionModel, newProvider)
-}

internal/config/types.go

@@ -119,12 +119,6 @@ type PreferencesConfig struct {
 	// the user turned idle recaps off. A *bool is its own tri-state, so no
 	// custom unmarshal is needed (unlike ToolsConfig.DeferThreshold's int).
 	Recaps *bool `json:"recaps,omitempty"`
-	// CompactionModel routes compaction summarization calls to this model
-	// instead of the session's main model (summaries at main-model prices are
-	// the most expensive recurring event in long runs). Empty = automatic: a
-	// curated cheap model on official endpoints, the main model elsewhere.
-	// "main" forces the main model. ZERO_COMPACTION_MODEL overrides.
-	CompactionModel string `json:"compactionModel,omitempty"`
 }
 
 // RecentModelEntry is one provider-qualified model selection recorded in

internal/cron/lock.go

@@ -5,23 +5,31 @@ import (
 	"fmt"
 	"os"
 	"path/filepath"
+	"sync/atomic"
 	"time"
 
 	"github.com/Gitlawb/zero/internal/lockutil"
 )
 
 // Cross-process lock tuning. The lock is held only for a single metadata
-// read-modify-write (milliseconds), never across a job's exec, so the timeout
-// is generous relative to any real hold.
+// read-modify-write (milliseconds), never across a job's exec, so the timeout is
+// generous and the stale threshold sits far above any real hold.
 const (
 	cronLockTimeout    = 10 * time.Second
+	cronLockStaleAfter = 60 * time.Second
 	cronLockRetryDelay = 20 * time.Millisecond
 )
 
-// lockJob takes a cross-process advisory lock for one job on a stable sibling
-// "<id>.lock" file next to the job directory. It serializes the read-modify-write
-// of a job's metadata across concurrent schedulers and commands. The kernel
-// releases the lock when a holder exits; the file is never renamed or removed.
+var cronLockSeq atomic.Uint64
+
+// lockJob takes a cross-process exclusive lock for one job by O_EXCL-creating a
+// sibling "<id>.lock" file next to the job directory (so Remove's RemoveAll of
+// the job dir never deletes a live lock). It serializes the read-modify-write of
+// a job's metadata across concurrent schedulers and commands. The lock file is
+// removed on release; a stale lock from a crashed holder (older than
+// cronLockStaleAfter) is reclaimed. Wall-clock time.Now is used deliberately
+// (not the injectable Store.now) so lock timing never depends on a frozen test
+// clock and the stale check compares against real file mtimes.
 func (s *Store) lockJob(id string) (func(), error) {
 	if !validID(id) {
 		return nil, fmt.Errorf("invalid cron job id %q", id)
@@ -30,15 +38,64 @@ func (s *Store) lockJob(id string) (func(), error) {
 	if err := os.MkdirAll(filepath.Dir(lockPath), 0o700); err != nil {
 		return nil, err
 	}
+	token := fmt.Sprintf("%d-%d-%d", os.Getpid(), time.Now().UnixNano(), cronLockSeq.Add(1))
 	deadline := time.Now().Add(cronLockTimeout)
 	for {
-		lock, err := lockutil.TryAcquireFileLock(lockPath)
+		f, err := os.OpenFile(lockPath, os.O_CREATE|os.O_EXCL|os.O_WRONLY, 0o600)
 		if err == nil {
-			return func() { _ = lock.Release() }, nil
+			// A partial write would leave a lock file without our token, so the
+			// releaser could never delete it — stranding the lock. Fail closed.
+			if _, werr := f.WriteString(token); werr != nil {
+				_ = f.Close()
+				_ = lockutil.RemoveLockFile(lockPath)
+				return nil, fmt.Errorf("cron: write job lock: %w", werr)
+			}
+			if cerr := f.Close(); cerr != nil {
+				_ = lockutil.RemoveLockFile(lockPath)
+				return nil, fmt.Errorf("cron: close job lock: %w", cerr)
+			}
+			var released bool
+			return func() {
+				if released {
+					return
+				}
+				released = true
+				if data, rerr := os.ReadFile(lockPath); rerr == nil && string(data) == token {
+					_ = lockutil.RemoveLockFile(lockPath)
+				}
+			}, nil
 		}
-		if !errors.Is(err, lockutil.ErrLockHeld) {
+		// On Windows a concurrent holder's os.Remove leaves the lock file in a
+		// "delete pending" state, so an O_EXCL create races it with
+		// ERROR_ACCESS_DENIED (os.ErrPermission) rather than ErrExist. Treat that
+		// as contention and retry, exactly like ErrExist — otherwise the lock
+		// spuriously fails under concurrency on Windows.
+		if !errors.Is(err, os.ErrExist) && !errors.Is(err, os.ErrPermission) {
 			return nil, fmt.Errorf("cron: acquire job lock: %w", err)
 		}
+		// Reclaim a stale lock left by a crashed holder — atomically (H3). A blind
+		// Remove lets two racers both "reclaim" and recreate, so both hold the lock;
+		// reclaimStaleLock renames the file aside (only one rename of a given file
+		// wins) and restores it if it turns out fresh, so a live lock is never deleted
+		// out from under its holder.
+		if info, statErr := os.Stat(lockPath); statErr == nil && time.Since(info.ModTime()) > cronLockStaleAfter {
+			cleared, rerr := lockutil.ReclaimStaleLock(lockPath, token, func(reclaimedPath string) bool {
+				info, err := os.Stat(reclaimedPath)
+				return err == nil && time.Since(info.ModTime()) <= cronLockStaleAfter
+			})
+			if rerr != nil {
+				// Reclaim hit a hard failure: the rename aside failed outright, or a
+				// live holder's lock could not be put back (the lock path may be
+				// missing, so re-acquiring would break mutual exclusion). Fail closed
+				// instead of spinning to the deadline.
+				return nil, fmt.Errorf("cron: reclaim stale job lock: %w", rerr)
+			}
+			if cleared {
+				continue // cleared a genuinely stale lock; retry the O_EXCL create now
+			}
+			// Lost the reclaim race (or it was actually fresh) — fall through to the
+			// bounded wait instead of hot-spinning on a reclaim that never wins (L13).
+		}
 		if !time.Now().Before(deadline) {
 			return nil, fmt.Errorf("cron: timed out acquiring job lock for %q", id)
 		}

internal/cron/mutate_test.go

@@ -64,7 +64,7 @@ func TestMutateRemovedJobReturnsNotFound(t *testing.T) {
 	if !errors.Is(err, ErrJobNotFound) {
 		t.Fatalf("Mutate on removed job = %v, want ErrJobNotFound", err)
 	}
-	// The stable advisory-lock file does not resurrect the removed job dir.
+	// And the lock file left no litter / did not resurrect the job dir.
 	if _, gerr := store.Get(job.ID); !errors.Is(gerr, ErrJobNotFound) {
 		t.Fatalf("job should remain removed, Get = %v", gerr)
 	}

internal/daemon/lock.go

@@ -3,60 +3,107 @@ package daemon
 import (
 	"errors"
 	"fmt"
+	"io/fs"
 	"os"
 	"strconv"
 	"strings"
+	"sync/atomic"
 
 	"github.com/Gitlawb/zero/internal/lockutil"
 )
 
-// Single-instance lock. The stable PID file carries a kernel advisory lock for
-// the daemon's full lifetime. Process exit releases the lock automatically, so
-// stale metadata needs no rename/remove recovery protocol.
+// Single-instance lock. Mirrors reference-daemon-code-agent-js/supervisor.js's
+// lock file: a PID file created with O_EXCL. A second start fails; a STALE lock
+// left by a dead daemon (the recorded PID is no longer alive) is reclaimed so the
+// daemon recovers from an unclean shutdown without manual cleanup.
 
 // ErrAlreadyRunning is returned when a live daemon already holds the lock.
 var ErrAlreadyRunning = errors.New("daemon: another instance is already running")
 
 // fileLock is an acquired single-instance lock.
 type fileLock struct {
-	lock *lockutil.FileLock
+	path string
 }
 
 // processAlive reports whether pid is a live process. Implemented per-platform
 // (lock_posix.go / lock_windows.go). It is a package var so tests can stub it.
 var processAlive = osProcessAlive
 
-// acquireLock takes the single-instance advisory lock at path. isAlive is used
-// only to enrich a contention error with the current holder's PID; the kernel
-// lock, not PID metadata, is authoritative.
+// acquireLock takes the single-instance lock at path, reclaiming a stale lock
+// whose recorded PID is dead. isAlive overrides the liveness check (tests pass a
+// stub); nil uses the real processAlive.
 func acquireLock(path string, isAlive func(pid int) bool) (*fileLock, error) {
 	if isAlive == nil {
 		isAlive = processAlive
 	}
-	lock, err := lockutil.TryAcquireFileLock(path)
-	if err != nil {
-		if !errors.Is(err, lockutil.ErrLockHeld) {
+	// At most two passes: create, or detect-stale-then-retry once.
+	for attempt := 0; attempt < 2; attempt++ {
+		f, err := os.OpenFile(path, os.O_CREATE|os.O_EXCL|os.O_WRONLY, 0o600)
+		if err == nil {
+			// A failed PID write would leave a malformed lock file that another
+			// process reads as stale (unparsable PID) and wrongly reclaims, breaking
+			// the single-instance guarantee — so on write failure, remove it and fail.
+			if _, werr := fmt.Fprintf(f, "%d\n", os.Getpid()); werr != nil {
+				_ = f.Close()
+				_ = lockutil.RemoveLockFile(path)
+				return nil, werr
+			}
+			if cerr := f.Close(); cerr != nil {
+				_ = lockutil.RemoveLockFile(path)
+				return nil, cerr
+			}
+			return &fileLock{path: path}, nil
+		}
+		if !errors.Is(err, fs.ErrExist) && !errors.Is(err, os.ErrPermission) {
 			return nil, err
 		}
 		pid, perr := readPidFile(path)
 		if perr == nil && pid > 0 && isAlive(pid) {
 			return nil, fmt.Errorf("%w (pid %d)", ErrAlreadyRunning, pid)
 		}
-		return nil, ErrAlreadyRunning
+		// Stale lock (dead PID or unreadable) — reclaim it atomically, then retry the
+		// O_EXCL create. A blind Remove here races: two daemons starting at once could
+		// both read the stale PID, both Remove, and then one Removes the OTHER's
+		// freshly-created lock — leaving both "holding" the single-instance lock.
+		// reclaimStaleLock renames the file aside so only one racer wins the rename,
+		// and restores it if a live holder reacquired in the gap (D6).
+		if _, rerr := reclaimStaleLock(path, isAlive); rerr != nil {
+			// Reclaim hit a hard failure: the rename aside failed outright, or a
+			// live holder's lock could not be put back (the lock path may be
+			// missing, so re-acquiring would break the single-instance guarantee).
+			// Fail closed instead of spinning to the deadline.
+			return nil, fmt.Errorf("daemon: reclaim stale lock: %w", rerr)
+		}
 	}
-	if err := lock.WriteMetadata([]byte(fmt.Sprintf("%d\n", os.Getpid()))); err != nil {
-		return nil, errors.Join(err, lock.Release())
-	}
-	return &fileLock{lock: lock}, nil
+	return nil, ErrAlreadyRunning
 }
 
-// release drops the kernel lock and closes its handle. The stable PID file is
-// deliberately retained so contenders always address the same inode.
+// daemonLockSeq makes each reclaim attempt's sidelined filename unique per process.
+var daemonLockSeq atomic.Uint64
+
+// reclaimStaleLock atomically reclaims a single-instance lock whose recorded
+// PID is dead, via lockutil.ReclaimStaleLock: the lock file is renamed aside
+// (only one racer can win the rename) and stolen only if the moved file's PID
+// is still dead; a holder that reacquired the lock in the gap between the
+// stale check and the rename carries a LIVE pid and is restored rather than
+// stolen. Returns true only when a genuinely stale lock was removed. A
+// non-nil error means the caller must fail closed instead of re-acquiring
+// (see lockutil.ReclaimStaleLock).
+func reclaimStaleLock(path string, isAlive func(pid int) bool) (bool, error) {
+	suffix := fmt.Sprintf("%d-%d", os.Getpid(), daemonLockSeq.Add(1))
+	return lockutil.ReclaimStaleLock(path, suffix, func(reclaimedPath string) bool {
+		pid, err := readPidFile(reclaimedPath)
+		return err == nil && pid > 0 && isAlive(pid)
+	})
+}
+
+// release removes the lock file. Safe to call once. An already-missing lock
+// file is not an error (lockutil.RemoveLockFile swallows it on every platform).
 func (l *fileLock) release() error {
-	if l == nil || l.lock == nil {
+	if l == nil || l.path == "" {
 		return nil
 	}
-	return l.lock.Release()
+	return lockutil.RemoveLockFile(l.path)
 }
 
 // readPidFile reads and parses the PID recorded in a lock file.
@@ -65,20 +112,5 @@ func readPidFile(path string) (int, error) {
 	if err != nil {
 		return 0, err
 	}
-	metadata := strings.TrimSpace(string(data))
-	if pid, err := strconv.Atoi(metadata); err == nil {
-		return pid, nil
-	}
-	pidText, sequenceText, ok := strings.Cut(metadata, "-")
-	if !ok || pidText == "" || sequenceText == "" || strings.Contains(sequenceText, "-") {
-		return 0, fmt.Errorf("daemon: parse lock PID metadata %q", metadata)
-	}
-	if _, err := strconv.ParseUint(sequenceText, 10, 64); err != nil {
-		return 0, fmt.Errorf("daemon: parse lock holder sequence: %w", err)
-	}
-	pid, err := strconv.Atoi(pidText)
-	if err != nil {
-		return 0, fmt.Errorf("daemon: parse lock PID: %w", err)
-	}
-	return pid, nil
+	return strconv.Atoi(strings.TrimSpace(string(data)))
 }

internal/daemon/lock_test.go

@@ -32,48 +32,27 @@ func TestLockSingleInstance(t *testing.T) {
 	_ = l2.release()
 }
 
-// A PID liveness probe is diagnostic only. Even if it reports the recorded PID
-// dead, a contended kernel lock proves that the holder is active and must win.
-// The old rename-aside protocol trusted this stale observation and admitted a
-// second daemon while the first one was still inside its critical section.
-func TestLockDoesNotOverrideKernelHolderWithStalePIDProbe(t *testing.T) {
+func TestLockStaleRecovery(t *testing.T) {
 	path := filepath.Join(t.TempDir(), "daemon.lock")
-	first, err := acquireLock(path, func(int) bool { return true })
-	if err != nil {
-		t.Fatalf("first acquireLock: %v", err)
-	}
-	defer first.release()
-
-	second, err := acquireLock(path, func(int) bool { return false })
-	if second != nil {
-		_ = second.release()
-	}
-	if !errors.Is(err, ErrAlreadyRunning) {
-		t.Fatalf("contended acquire with stale PID probe = %v, want ErrAlreadyRunning", err)
-	}
-}
-
-func TestLockIgnoresStaleMetadataWhenKernelLockIsFree(t *testing.T) {
-	path := filepath.Join(t.TempDir(), "daemon.lock")
-	// A crashed daemon may leave PID metadata behind, but its kernel lock is
-	// released automatically, so the next daemon can acquire without moving it.
+	// Simulate a stale lock from a crashed daemon: a PID file whose process is
+	// dead.
 	if err := os.WriteFile(path, []byte("4242\n"), 0o600); err != nil {
 		t.Fatalf("write stale lock: %v", err)
 	}
 	dead := func(int) bool { return false }
 	l, err := acquireLock(path, dead)
 	if err != nil {
-		t.Fatalf("acquire over stale metadata: %v", err)
+		t.Fatalf("stale-lock recovery failed: %v", err)
 	}
 	// The lock now records OUR pid, not the stale one.
 	data, _ := os.ReadFile(path)
 	if strings.TrimSpace(string(data)) != strconv.Itoa(os.Getpid()) {
-		t.Fatalf("lock pid = %q, want %d", strings.TrimSpace(string(data)), os.Getpid())
+		t.Fatalf("reclaimed lock pid = %q, want %d", strings.TrimSpace(string(data)), os.Getpid())
 	}
 	_ = l.release()
 }
 
-func TestLockReleaseKeepsStableFile(t *testing.T) {
+func TestLockReleaseRemovesFile(t *testing.T) {
 	path := filepath.Join(t.TempDir(), "daemon.lock")
 	l, err := acquireLock(path, func(int) bool { return true })
 	if err != nil {
@@ -82,37 +61,46 @@ func TestLockReleaseKeepsStableFile(t *testing.T) {
 	if err := l.release(); err != nil {
 		t.Fatalf("release: %v", err)
 	}
-	if _, err := os.Stat(path); err != nil {
-		t.Fatalf("release removed stable lock file: %v", err)
+	if _, err := os.Stat(path); !errors.Is(err, os.ErrNotExist) {
+		t.Fatalf("lock file still present after release: %v", err)
 	}
 }
 
-func TestReadPidFileMetadataFormats(t *testing.T) {
+func TestReclaimStaleLockRemovesDeadHolder(t *testing.T) {
 	path := filepath.Join(t.TempDir(), "daemon.lock")
-	for _, test := range []struct {
-		name     string
-		metadata string
-		wantPID  int
-		wantErr  bool
-	}{
-		{name: "legacy PID", metadata: "4242\n", wantPID: 4242},
-		{name: "PID and holder sequence", metadata: "4242-7\n", wantPID: 4242},
-		{name: "missing sequence", metadata: "4242-", wantErr: true},
-		{name: "non-numeric sequence", metadata: "4242-next", wantErr: true},
-		{name: "extra component", metadata: "4242-7-8", wantErr: true},
-	} {
-		t.Run(test.name, func(t *testing.T) {
-			if err := os.WriteFile(path, []byte(test.metadata), 0o600); err != nil {
-				t.Fatal(err)
-			}
-			got, err := readPidFile(path)
-			if (err != nil) != test.wantErr {
-				t.Fatalf("readPidFile() error = %v, wantErr %v", err, test.wantErr)
-			}
-			if !test.wantErr && got != test.wantPID {
-				t.Fatalf("readPidFile() = %d, want %d", got, test.wantPID)
-			}
-		})
+	if err := os.WriteFile(path, []byte("4242\n"), 0o600); err != nil {
+		t.Fatalf("write stale lock: %v", err)
+	}
+	if ok, err := reclaimStaleLock(path, func(int) bool { return false }); err != nil || !ok {
+		t.Fatalf("reclaimStaleLock must report a genuinely stale (dead-PID) lock reclaimed (ok=%v err=%v)", ok, err)
+	}
+	if _, err := os.Stat(path); !errors.Is(err, os.ErrNotExist) {
+		t.Fatalf("a reclaimed stale lock must be removed, stat = %v", err)
+	}
+}
+
+func TestReclaimStaleLockRestoresLiveHolder(t *testing.T) {
+	// If a holder reacquires the lock in the gap between the stale check and the
+	// rename, the moved file carries a LIVE pid; reclaim must restore it untouched
+	// rather than steal it — otherwise two daemons both "hold" the lock (D6).
+	path := filepath.Join(t.TempDir(), "daemon.lock")
+	if err := os.WriteFile(path, []byte("4242\n"), 0o600); err != nil {
+		t.Fatalf("write lock: %v", err)
+	}
+	if ok, err := reclaimStaleLock(path, func(int) bool { return true }); err != nil || ok {
+		t.Fatalf("reclaimStaleLock must NOT report a live-PID lock reclaimed (ok=%v err=%v)", ok, err)
+	}
+	data, err := os.ReadFile(path)
+	if err != nil {
+		t.Fatalf("live lock must be restored in place, read = %v", err)
+	}
+	if strings.TrimSpace(string(data)) != "4242" {
+		t.Fatalf("restored lock content = %q, want %q (unchanged)", strings.TrimSpace(string(data)), "4242")
+	}
+	// No sidelined ".stale" leftovers.
+	matches, _ := filepath.Glob(path + ".stale.*")
+	if len(matches) != 0 {
+		t.Fatalf("reclaim left sidelined files: %v", matches)
 	}
 }
 

internal/daemon/server_test.go

@@ -124,16 +124,12 @@ func TestServerEndToEnd(t *testing.T) {
 	case <-time.After(3 * time.Second):
 		t.Fatal("Serve did not return after shutdown")
 	}
-	// Runtime endpoints are removed on exit. The advisory lock file remains as
-	// a stable inode, but the kernel lock on it has been released.
-	for _, p := range []string{paths.Socket, paths.Status} {
+	// Socket, status, and lock files are removed on exit.
+	for _, p := range []string{paths.Socket, paths.Status, paths.Lock} {
 		if _, err := os.Stat(p); !errors.Is(err, os.ErrNotExist) {
 			t.Fatalf("file %s not cleaned up after shutdown: %v", p, err)
 		}
 	}
-	if _, err := os.Stat(paths.Lock); err != nil {
-		t.Fatalf("stable lock file missing after shutdown: %v", err)
-	}
 }
 
 func TestServerSecondInstanceFails(t *testing.T) {

internal/execution/process_unix_test.go

@@ -3,93 +3,13 @@
 package execution
 
 import (
-	"errors"
-	"os"
 	"os/exec"
 	"strconv"
-	"strings"
 	"syscall"
 	"testing"
 	"time"
 )
 
-// requireProcessState refuses to let a broken ps pipeline masquerade as passing
-// coverage. Every test in this file proves something about zombie detection,
-// and every one of those proofs is read out of ps — so if ps cannot report
-// state, the tests verify nothing whatever they do next.
-//
-// The old code answered that with t.Skip, which is indistinguishable from
-// success in CI output. This probes BOTH ps pipelines against this test
-// process, which is by definition alive and not a zombie, so a working ps must
-// report a live state for it. Failing that:
-//
-//   - In CI (or with ZERO_REQUIRE_PS=1) it is a hard failure. ps is present on
-//     every image used today, so its absence means the pipeline regressed and
-//     that has to surface immediately rather than as skipped-green.
-//   - Elsewhere it stays a skip, so a contributor on an exotic box is not
-//     blocked by an environment the project does not claim to support.
-//
-// This only covers "ps cannot report state at all". Once it passes, a later
-// failure to observe an EXPECTED state is a real defect, and the tests below
-// treat it as one.
-func requireProcessState(t *testing.T) {
-	t.Helper()
-	self := os.Getpid()
-	var reasons []string
-	// The production path: ps -A -o pid=,pgid=,stat=, parsed by
-	// processTableStateMatches. This is what signalTargetRunning consults.
-	if running, ok := processIsRunning(self); !ok || !running {
-		reasons = append(reasons, "the process table read used by signalTargetRunning reported no live state for this test process")
-	}
-	// This file's independent oracle: ps -o stat= -p <pid>. It is deliberately
-	// NOT the production parser, so a regression in that parser cannot hide by
-	// breaking the test's own precondition check in the same way.
-	if zombie, ok := processIsZombie(self); !ok || zombie {
-		reasons = append(reasons, "the per-PID state read used by this test file reported no live state for this test process")
-	}
-	if len(reasons) == 0 {
-		return
-	}
-	reason := "cannot read process state, so ps-based zombie detection is unverifiable here: " + strings.Join(reasons, "; ")
-	if requireWorkingPS() {
-		t.Fatal(reason + " — failing rather than skipping because CI (or ZERO_REQUIRE_PS) is set, where ps is expected to work")
-	}
-	t.Skip(reason)
-}
-
-// requireWorkingPS reports whether an unusable ps must fail the run instead of
-// skipping it. ZERO_REQUIRE_PS lets a developer opt into the strict behavior
-// locally to reproduce what CI does.
-func requireWorkingPS() bool {
-	if strings.TrimSpace(os.Getenv("ZERO_REQUIRE_PS")) != "" {
-		return true
-	}
-	return strings.TrimSpace(os.Getenv("CI")) != ""
-}
-
-// awaitZombie blocks until pid is an unreaped zombie. The caller must not have
-// waited on the child, so the zombie is a stable state rather than a race: it
-// persists until something reaps it. Failing to reach it therefore means the
-// child never exited or ps stopped reporting its state, and both are defects
-// rather than reasons to skip.
-func awaitZombie(t *testing.T, pid int) {
-	t.Helper()
-	deadline := time.Now().Add(5 * time.Second)
-	for {
-		zombie, ok := processIsZombie(pid)
-		if ok && zombie {
-			return
-		}
-		if time.Now().After(deadline) {
-			if !ok {
-				t.Fatalf("pid %d left the process table without being reaped; this test never waited on it, so its zombie row must persist", pid)
-			}
-			t.Fatalf("pid %d did not reach the zombie state within 5s", pid)
-		}
-		time.Sleep(10 * time.Millisecond)
-	}
-}
-
 // TestTerminateProcessTreeTreatsZombieGroupAsExited is the regression test for
 // counting unreaped processes as alive: kill(2) with signal 0 succeeds for a
 // zombie, so a group whose only remaining member is waiting to be reaped used to
@@ -97,8 +17,6 @@ func awaitZombie(t *testing.T, pid int) {
 // as "did not exit after SIGKILL" — a spurious cleanup failure whose timing
 // depended on when the reaper ran.
 func TestTerminateProcessTreeTreatsZombieGroupAsExited(t *testing.T) {
-	requireProcessState(t)
-
 	cmd := exec.Command("sh", "-c", "exit 0")
 	ConfigureProcessGroup(cmd)
 	if err := cmd.Start(); err != nil {
@@ -109,59 +27,23 @@ func TestTerminateProcessTreeTreatsZombieGroupAsExited(t *testing.T) {
 	// is exactly the state a terminated tree passes through.
 	t.Cleanup(func() { _ = cmd.Wait() })
 
-	awaitZombie(t, pid)
-
-	// Whether a zombie-only group can be signalled is a KERNEL difference, not a
-	// ps one. On Linux the zombie still occupies the process table and
-	// kill(-pid, 0) succeeds, so signalTargetRunning goes on to consult ps —
-	// which is the branch this test was written for. Darwin returns EPERM for
-	// the same call, so signalTargetRunning short-circuits on the kill and never
-	// reaches the ps check.
-	//
-	// The OUTCOME is identical and is asserted on every platform below. Only the
-	// branch that produces it differs, so record that instead of skipping the
-	// whole test (which would drop Darwin's coverage of the outcome) or failing
-	// it (which would report a supported platform as broken). Any errno other
-	// than EPERM means the group is not in the state this test needs.
-	psPathReachable := true
-	if err := syscall.Kill(-pid, syscall.Signal(0)); err != nil {
-		if !errors.Is(err, syscall.EPERM) {
-			t.Fatalf("zombie group %d is unsignalable with an unexpected error (%v); the zombie case is not present, so nothing below would be meaningful", pid, err)
+	deadline := time.Now().Add(5 * time.Second)
+	for {
+		if zombie, ok := processIsZombie(pid); ok && zombie {
+			break
 		}
-		psPathReachable = false
-		t.Logf("kernel refuses to signal zombie-only group %d (EPERM); signalTargetRunning answers from kill(2) rather than ps here, so the ps-based zombie check is asserted directly on platforms that allow the signal", pid)
+		if time.Now().After(deadline) {
+			t.Skip("child did not reach the zombie state; ps output is unavailable in this environment")
+		}
+		time.Sleep(10 * time.Millisecond)
+	}
+	if syscall.Kill(-pid, syscall.Signal(0)) != nil {
+		t.Skip("the zombie group is no longer signalable; cannot exercise the case")
 	}
 
-	// Where the signal IS permitted, pin the ps-based check itself. This is the
-	// regression #774 was about, and asserting only signalTargetRunning would
-	// let a ps-side regression hide behind the kill result.
-	if psPathReachable {
-		running, ok := processGroupHasRunningMember(pid)
-		if !ok {
-			t.Fatalf("process group %d has no rows while its zombie is unreaped; ps stopped reporting the group rather than the group being gone", pid)
-		}
-		if running {
-			t.Fatal("the ps-based group check must not report a zombie-only group as running")
-		}
-	}
-
-	// Valid on every platform: whichever branch answers, a zombie-only group is
-	// not running. On a kernel that refuses the signal this is the whole of the
-	// coverage, and it is more than the previous skip provided.
 	if signalTargetRunning(-pid) {
 		t.Fatal("a group holding only a zombie must not count as running")
 	}
-
-	if !psPathReachable {
-		// terminateTarget's own kill(2) would hit the same EPERM and be returned
-		// as a cleanup error, so this assertion cannot be made where the kernel
-		// refuses the signal. That may be a real gap in TerminateProcessTree on
-		// such a platform rather than a test limitation — a zombie-only tree is
-		// already exited and should terminate cleanly — but confirming and
-		// changing that is a production fix, not this test's business.
-		t.Log("skipping the TerminateProcessTree assertion: its kill(2) would hit the same EPERM as the probe above")
-		return
-	}
 	if err := TerminateProcessTree(pid, 50*time.Millisecond, 10*time.Millisecond); err != nil {
 		t.Fatalf("TerminateProcessTree on an already-exited tree: %v", err)
 	}
@@ -171,8 +53,6 @@ func TestTerminateProcessTreeTreatsZombieGroupAsExited(t *testing.T) {
 // a live member must still be seen as running and then actually stopped, so the
 // zombie tolerance above cannot degrade into ignoring real processes.
 func TestTerminateProcessTreeStopsRunningGroup(t *testing.T) {
-	requireProcessState(t)
-
 	cmd := exec.Command("sh", "-c", "sleep 30")
 	ConfigureProcessGroup(cmd)
 	if err := cmd.Start(); err != nil {
@@ -187,15 +67,7 @@ func TestTerminateProcessTreeStopsRunningGroup(t *testing.T) {
 	if err := TerminateProcessTree(pid, time.Second, 10*time.Millisecond); err != nil {
 		t.Fatalf("TerminateProcessTree: %v", err)
 	}
-	// ok reports whether ANY row for this group was found. This test never waits
-	// on the child, so its zombie row must still be there — an unknown state
-	// means ps stopped answering, not that the group is gone. Treating that as a
-	// pass is what let this assertion succeed without checking anything.
-	running, ok := processGroupHasRunningMember(pid)
-	if !ok {
-		t.Fatalf("process group %d has no rows after termination; the unreaped child's zombie row must persist, so the group's state is undeterminable rather than clean", pid)
-	}
-	if running {
+	if running, ok := processGroupHasRunningMember(pid); ok && running {
 		t.Fatal("the group still has a running member after termination")
 	}
 }
@@ -210,8 +82,6 @@ func TestTerminateProcessTreeStopsRunningGroup(t *testing.T) {
 // "unknown" resulted every time, and signalTargetRunning conservatively (and
 // incorrectly) treated a zombie individual-PID target as still running.
 func TestSignalTargetRunningTreatsZombieIndividualPIDAsExited(t *testing.T) {
-	requireProcessState(t)
-
 	cmd := exec.Command("sh", "-c", "exit 0")
 	// Deliberately do NOT call ConfigureProcessGroup: the child inherits this
 	// test process's group, so it is not its own leader and processSignalTarget
@@ -222,38 +92,40 @@ func TestSignalTargetRunningTreatsZombieIndividualPIDAsExited(t *testing.T) {
 	pid := cmd.Process.Pid
 	t.Cleanup(func() { _ = cmd.Wait() })
 
-	awaitZombie(t, pid)
+	deadline := time.Now().Add(5 * time.Second)
+	for {
+		if zombie, ok := processIsZombie(pid); ok && zombie {
+			break
+		}
+		if time.Now().After(deadline) {
+			t.Skip("child did not reach the zombie state; ps output is unavailable in this environment")
+		}
+		time.Sleep(10 * time.Millisecond)
+	}
 
 	target, err := processSignalTarget(pid)
 	if err != nil {
 		t.Fatalf("processSignalTarget: %v", err)
 	}
-	// The child inherited this process's group, so its PGID is this process's
-	// PID and can never equal its own PID. A negative target here would mean
-	// processSignalTarget misread the group, which is the very thing the
-	// individual-PID fallback exists to handle.
 	if target != pid {
-		t.Fatalf("processSignalTarget(%d) = %d, want the individual PID: the child inherited this process's group, so it is not its own leader", pid, target)
+		t.Skip("child unexpectedly became its own group leader; cannot exercise the individual-PID fallback")
 	}
 	if signalTargetRunning(target) {
 		t.Fatal("a zombie individual-PID target must not count as running")
 	}
 }
 
-// processIsZombie reports a process's zombie state via ps. It is deliberately a
-// separate, per-PID ps invocation rather than a reuse of the production
-// process-table parser: these tests assert what that parser concludes, so
-// borrowing it to establish their own preconditions would let one regression
-// silence both sides at once.
-//
-// ok is false when no state could be read, which after requireProcessState has
-// passed means the process left the table rather than that ps is broken.
+// processIsZombie reports a process's zombie state via ps. ok is false when the
+// state could not be read.
 func processIsZombie(pid int) (zombie bool, ok bool) {
 	output, err := exec.Command("ps", "-o", "stat=", "-p", strconv.Itoa(pid)).Output()
 	if err != nil {
 		return false, false
 	}
-	state := strings.TrimLeft(string(output), " \n\t")
+	state := string(output)
+	for len(state) > 0 && (state[0] == ' ' || state[0] == '\n' || state[0] == '\t') {
+		state = state[1:]
+	}
 	if state == "" {
 		return false, false
 	}

internal/hooks/lock.go

@@ -5,39 +5,93 @@ import (
 	"fmt"
 	"os"
 	"path/filepath"
+	"sync/atomic"
 	"time"
 
 	"github.com/Gitlawb/zero/internal/lockutil"
 )
 
 // Cross-process lock tuning for the audit log. The lock is held only across a
-// single read-then-append (milliseconds), so the timeout is generous relative
-// to any real hold.
+// single read-then-append (milliseconds), so the timeout is generous and the
+// stale threshold sits far above any real hold.
 const (
 	auditLockTimeout    = 10 * time.Second
+	auditLockStaleAfter = 60 * time.Second
 	auditLockRetryDelay = 20 * time.Millisecond
 )
 
-// lockAudit takes a cross-process advisory lock on the audit log through a
-// stable sibling "<auditPath>.lock" file. It makes
+var auditLockSeq atomic.Uint64
+
+// lockAudit takes a cross-process exclusive lock on the audit log by
+// O_EXCL-creating a sibling "<auditPath>.lock" file (removed on release). It makes
 // the lastSequence()+append in append() atomic across processes; the audit log is
 // a shared global file, so without it two processes can read the same last
-// sequence and write duplicate numbers. Kernel lock lifetime provides crash
-// recovery without moving or deleting the lock path.
+// sequence and write duplicate numbers. A stale lock from a crashed holder (older
+// than auditLockStaleAfter) is reclaimed. Wall-clock time is used deliberately so
+// lock timing never depends on the store's injectable clock and the stale check
+// compares against real file mtimes. This mirrors internal/cron/lock.go and
+// internal/oauth/lock.go. Uses internal/lockutil for lock restore and reclaim.
 func (store *AuditStore) lockAudit() (func(), error) {
 	lockPath := store.auditPath + ".lock"
 	if err := os.MkdirAll(filepath.Dir(lockPath), 0o700); err != nil {
 		return nil, err
 	}
+	token := fmt.Sprintf("%d-%d-%d", os.Getpid(), time.Now().UnixNano(), auditLockSeq.Add(1))
 	deadline := time.Now().Add(auditLockTimeout)
 	for {
-		lock, err := lockutil.TryAcquireFileLock(lockPath)
+		f, err := os.OpenFile(lockPath, os.O_CREATE|os.O_EXCL|os.O_WRONLY, 0o600)
 		if err == nil {
-			return func() { _ = lock.Release() }, nil
+			// A partial write would leave a lock file without our token, so the
+			// releaser could never delete it — stranding the lock. Fail closed.
+			if _, werr := f.WriteString(token); werr != nil {
+				_ = f.Close()
+				_ = lockutil.RemoveLockFile(lockPath)
+				return nil, fmt.Errorf("hooks: write audit lock: %w", werr)
+			}
+			if cerr := f.Close(); cerr != nil {
+				_ = lockutil.RemoveLockFile(lockPath)
+				return nil, fmt.Errorf("hooks: close audit lock: %w", cerr)
+			}
+			var released bool
+			return func() {
+				if released {
+					return
+				}
+				released = true
+				if data, rerr := os.ReadFile(lockPath); rerr == nil && string(data) == token {
+					_ = lockutil.RemoveLockFile(lockPath)
+				}
+			}, nil
 		}
-		if !errors.Is(err, lockutil.ErrLockHeld) {
+		// On Windows a concurrent holder's os.Remove leaves the lock file in a
+		// "delete pending" state, so an O_EXCL create races it with
+		// ERROR_ACCESS_DENIED (os.ErrPermission) rather than ErrExist. Treat both
+		// as contention and retry.
+		if !errors.Is(err, os.ErrExist) && !errors.Is(err, os.ErrPermission) {
 			return nil, fmt.Errorf("hooks: acquire audit lock: %w", err)
 		}
+		// Reclaim a stale lock left by a crashed holder — atomically (H3). A blind
+		// Remove lets two racers both reclaim + recreate and so both hold the lock;
+		// reclaimStaleLock renames the file aside (only one rename wins) and restores
+		// it if it turns out fresh, so a live lock is never deleted out from under it.
+		if info, statErr := os.Stat(lockPath); statErr == nil && time.Since(info.ModTime()) > auditLockStaleAfter {
+			cleared, rerr := lockutil.ReclaimStaleLock(lockPath, token, func(reclaimedPath string) bool {
+				info, err := os.Stat(reclaimedPath)
+				return err == nil && time.Since(info.ModTime()) <= auditLockStaleAfter
+			})
+			if rerr != nil {
+				// Reclaim hit a hard failure: the rename aside failed outright, or a
+				// live holder's lock could not be put back (the lock path may be
+				// missing, so re-acquiring would break mutual exclusion). Fail closed
+				// instead of spinning to the deadline.
+				return nil, fmt.Errorf("hooks: reclaim stale audit lock: %w", rerr)
+			}
+			if cleared {
+				continue
+			}
+			// Lost the reclaim race (or it was actually fresh) — fall through to the
+			// bounded wait rather than hot-spinning on a reclaim that never wins.
+		}
 		if !time.Now().Before(deadline) {
 			return nil, fmt.Errorf("hooks: timed out acquiring audit lock")
 		}

internal/lockutil/lockutil.go

@@ -1,127 +1,64 @@
-// Package lockutil provides cross-process advisory file locks used by cron,
-// daemon, hooks, oauth, and swarm. Locks are held by the kernel for the lifetime
-// of an open file handle, so process exit releases them without a stale-file
-// reclaim protocol. The lock file itself is stable: holders never rename or
-// remove it while another process may still have its inode locked.
+// Package lockutil provides the platform-specific file primitives behind the
+// O_EXCL lock files in cron, daemon, hooks, oauth, and swarm: a no-overwrite
+// restore for locks that were sidelined during a stale-reclaim attempt, and a
+// lock file remover with one cross-platform contract (missing files are a
+// no-op; Windows retries transient sharing violations).
 package lockutil
 
 import (
-	"errors"
-	"fmt"
+	"io"
 	"os"
-	"path/filepath"
-	"strings"
-	"sync"
-	"sync/atomic"
 )
 
-var (
-	// ErrLockHeld reports that another process or goroutine currently holds the
-	// advisory lock. Callers may wait and retry until their own deadline.
-	ErrLockHeld = errors.New("lockutil: lock is held")
-	// ErrLockReleased reports an attempt to update metadata after Release.
-	ErrLockReleased = errors.New("lockutil: lock is released")
-)
-
-var holderSequence atomic.Uint64
-
-// FileLock is an exclusive advisory lock held through an open file handle.
-// Release is idempotent. The lock path remains on disk after release; deleting
-// or replacing it would let different processes lock different inodes.
-type FileLock struct {
-	mu         sync.Mutex
-	file       *os.File
-	state      platformLockState
-	released   bool
-	releaseErr error
-}
-
-// TryAcquireFileLock attempts to take an exclusive advisory lock without
-// waiting. A contended lock returns ErrLockHeld. The kernel releases a lock if
-// its process exits, so an old unlocked file never needs stale reclamation.
-func TryAcquireFileLock(path string) (*FileLock, error) {
-	return TryAcquireFileLockAt(filepath.Dir(path), path)
-}
-
-// TryAcquireFileLockAt attempts to lock path while confining every component
-// below root to a handle-relative traversal. root is the caller's trusted
-// boundary and may itself be reached through a legitimate link; links and
-// reparse points below it are rejected before metadata can be written.
-func TryAcquireFileLockAt(root, path string) (*FileLock, error) {
-	if root == "" {
-		return nil, errors.New("lockutil: lock root is empty")
-	}
-	relative, err := filepath.Rel(root, path)
+// restoreByCopy restores reclaimed to path without overwriting an existing
+// path, as a fallback for when the platform's primary no-replace primitive
+// (hard link on POSIX, MoveFileEx on Windows) fails for a reason other than
+// the destination existing. It stages a full copy under a private name next
+// to reclaimed and publishes it to path with publish (the same no-replace
+// primitive the caller's platform uses for the primary restore), so path
+// never appears in a partially-copied state: a crash between staging and
+// publish leaves path exactly as it was (missing or, if a competing holder
+// created it, untouched), never a truncated file that a PID/content-based
+// liveness check could mistake for dead. Leaving path missing here would let
+// the next O_EXCL create succeed while the sidelined holder is still live,
+// breaking mutual exclusion. publish keeps the no-overwrite guarantee: a new
+// holder that appeared in the meantime wins and this returns os.ErrExist. The
+// copy resets the lock's mtime to now, which only makes the restored lock
+// look fresher; that is safe, since it is being handed back to a live holder.
+func restoreByCopy(reclaimed, path string, publish func(from, to string) error) error {
+	staged := reclaimed + ".copy"
+	src, err := os.Open(reclaimed)
 	if err != nil {
-		return nil, fmt.Errorf("lockutil: resolve lock path relative to root: %w", err)
+		return err
 	}
-	relative = filepath.Clean(relative)
-	if relative == "." || relative == ".." || filepath.IsAbs(relative) || strings.HasPrefix(relative, ".."+string(filepath.Separator)) {
-		return nil, fmt.Errorf("lockutil: lock path %q escapes root %q", path, root)
-	}
-
-	file, err := openLockFileAt(root, relative, path)
+	dst, err := os.OpenFile(staged, os.O_CREATE|os.O_EXCL|os.O_WRONLY, 0o600)
 	if err != nil {
-		return nil, fmt.Errorf("lockutil: open lock file: %w", err)
+		_ = src.Close()
+		return err
 	}
-	state, contended, err := tryLockFile(file)
+	_, err = io.Copy(dst, src)
+	// Close the source before removing anything below: Go opens files without
+	// FILE_SHARE_DELETE on Windows, so deleting reclaimed or staged while src
+	// is open would fail with a sharing violation.
+	_ = src.Close()
 	if err != nil {
-		_ = file.Close()
-		return nil, fmt.Errorf("lockutil: acquire advisory lock: %w", err)
+		_ = dst.Close()
+		_ = os.Remove(staged)
+		return err
 	}
-	if contended {
-		_ = file.Close()
-		return nil, ErrLockHeld
+	if err := dst.Close(); err != nil {
+		_ = os.Remove(staged)
+		return err
 	}
-
-	lock := &FileLock{file: file, state: state}
-	metadata := []byte(fmt.Sprintf("%d-%d\n", os.Getpid(), holderSequence.Add(1)))
-	if err := lock.WriteMetadata(metadata); err != nil {
-		return nil, errors.Join(err, lock.Release())
-	}
-	return lock, nil
-}
-
-// WriteMetadata replaces the diagnostic contents of the lock file while the
-// caller holds it. Metadata does not establish ownership; the kernel lock does.
-func (lock *FileLock) WriteMetadata(data []byte) error {
-	if lock == nil {
-		return ErrLockReleased
-	}
-	lock.mu.Lock()
-	defer lock.mu.Unlock()
-	if lock.released || lock.file == nil {
-		return ErrLockReleased
-	}
-	if err := lock.file.Truncate(0); err != nil {
-		return fmt.Errorf("lockutil: truncate lock metadata: %w", err)
-	}
-	if _, err := lock.file.Seek(0, 0); err != nil {
-		return fmt.Errorf("lockutil: seek lock metadata: %w", err)
-	}
-	if _, err := lock.file.Write(data); err != nil {
-		return fmt.Errorf("lockutil: write lock metadata: %w", err)
+	if err := publish(staged, path); err != nil {
+		_ = os.Remove(staged)
+		return err
 	}
+	// publish may leave staged behind (a hard-link publish keeps both names),
+	// so remove it explicitly; a move-based publish already made this a no-op.
+	_ = os.Remove(staged)
+	// The lock is back at path, so the restore has succeeded; failing to clean
+	// up the sidelined name must not be reported as a failed restore.
+	_ = RemoveLockFile(reclaimed)
 	return nil
 }
-
-// Release unlocks and closes the held file handle. It deliberately leaves the
-// stable lock file in place. Repeated calls return the first release result.
-func (lock *FileLock) Release() error {
-	if lock == nil {
-		return nil
-	}
-	lock.mu.Lock()
-	defer lock.mu.Unlock()
-	if lock.released {
-		return lock.releaseErr
-	}
-	lock.released = true
-	unlockErr := unlockFile(lock.file, &lock.state)
-	closeErr := lock.file.Close()
-	lock.file = nil
-	if err := errors.Join(unlockErr, closeErr); err != nil {
-		lock.releaseErr = fmt.Errorf("lockutil: release advisory lock: %w", err)
-	}
-	return lock.releaseErr
-}

internal/lockutil/lockutil_other.go

@@ -4,92 +4,43 @@ package lockutil
 
 import (
 	"errors"
-	"fmt"
+	"io/fs"
 	"os"
-	"path/filepath"
-	"strings"
-
-	"golang.org/x/sys/unix"
 )
 
-type platformLockState struct{}
-
-func openLockFileAt(root, relative, displayPath string) (_ *os.File, resultErr error) {
-	parentFD, err := unix.Open(root, unix.O_RDONLY|unix.O_DIRECTORY|unix.O_CLOEXEC, 0)
-	if err != nil {
-		return nil, fmt.Errorf("open lock root: %w", err)
-	}
-	defer func() {
-		if parentFD >= 0 {
-			resultErr = errors.Join(resultErr, unix.Close(parentFD))
-		}
-	}()
-
-	components := strings.Split(filepath.Clean(relative), string(filepath.Separator))
-	for _, component := range components[:len(components)-1] {
-		nextFD, openErr := unix.Openat(parentFD, component, unix.O_RDONLY|unix.O_DIRECTORY|unix.O_CLOEXEC|unix.O_NOFOLLOW, 0)
-		if openErr != nil {
-			return nil, fmt.Errorf("open lock path component %q: %w", component, openErr)
-		}
-		if closeErr := unix.Close(parentFD); closeErr != nil {
-			_ = unix.Close(nextFD)
-			parentFD = -1
-			return nil, fmt.Errorf("close lock path component: %w", closeErr)
-		}
-		parentFD = nextFD
-	}
-
-	name := components[len(components)-1]
-	fd := -1
-	// Darwin can transiently return ENOENT when many callers race to create the
-	// same O_NOFOLLOW entry. The bound parent handle cannot be redirected, so a
-	// bounded retry preserves first-use contention without weakening no-follow.
-	for attempt := 0; attempt < 10; attempt++ {
-		fd, err = unix.Openat(parentFD, name, unix.O_CREAT|unix.O_RDWR|unix.O_CLOEXEC|unix.O_NOFOLLOW, 0o600)
-		if !errors.Is(err, unix.ENOENT) {
-			break
-		}
-	}
-	if err != nil {
-		return nil, err
-	}
-	file := os.NewFile(uintptr(fd), displayPath)
-	if file == nil {
-		_ = unix.Close(fd)
-		return nil, errors.New("convert lock handle to file")
-	}
-	var stat unix.Stat_t
-	if err := unix.Fstat(fd, &stat); err != nil {
-		return nil, errors.Join(fmt.Errorf("inspect lock file: %w", err), file.Close())
-	}
-	if stat.Mode&unix.S_IFMT != unix.S_IFREG {
-		return nil, errors.Join(errors.New("refusing non-regular lock file"), file.Close())
-	}
-	if stat.Nlink != 1 {
-		return nil, errors.Join(errors.New("refusing multiply-linked lock file"), file.Close())
-	}
-	if err := unix.Close(parentFD); err != nil {
-		parentFD = -1
-		return nil, errors.Join(fmt.Errorf("close lock parent: %w", err), file.Close())
-	}
-	parentFD = -1
-	return file, nil
-}
-
-func tryLockFile(file *os.File) (platformLockState, bool, error) {
-	err := unix.Flock(int(file.Fd()), unix.LOCK_EX|unix.LOCK_NB)
+// RestoreLockFile restores a sidelined lock file on non-Windows platforms. It
+// uses os.Link so a competing lock created at path in the meantime wins: the
+// link fails with os.ErrExist instead of overwriting it. If the link fails for
+// any other reason (hardlink-incapable filesystems such as FAT or some
+// FUSE/network mounts, ENOSPC, EPERM), it falls back to an O_EXCL copy rather
+// than leaving path missing and the live holder's lock stranded in reclaimed.
+// Once the lock is back at path the restore has succeeded, so a failed cleanup
+// of the sidelined name is not reported as an error; the leftover file is
+// invisible to the lock protocol.
+func RestoreLockFile(reclaimed, path string) error {
+	err := os.Link(reclaimed, path)
 	if err == nil {
-		return platformLockState{}, false, nil
-	}
-	if errors.Is(err, unix.EWOULDBLOCK) || errors.Is(err, unix.EAGAIN) {
-		return platformLockState{}, true, nil
-	}
-	return platformLockState{}, false, err
-}
-
-func unlockFile(file *os.File, _ *platformLockState) error {
-	if file == nil {
+		_ = RemoveLockFile(reclaimed)
 		return nil
 	}
-	return unix.Flock(int(file.Fd()), unix.LOCK_UN)
+	if errors.Is(err, os.ErrExist) {
+		return err
+	}
+	return restoreByCopy(reclaimed, path, os.Link)
+}
+
+// isReclaimContended reports whether a failed rename-aside of a suspected
+// stale lock means it was lost to a racer rather than a hard failure. POSIX
+// rename has no contention errno (a lost race surfaces only as ENOENT, which
+// ReclaimStaleLock already treats as benign), so nothing extra is benign here.
+func isReclaimContended(error) bool { return false }
+
+// RemoveLockFile removes a lock file on non-Windows platforms. Removing an
+// already-missing file reports nil, matching the Windows implementation, so
+// callers see one cross-platform contract.
+func RemoveLockFile(path string) error {
+	if err := os.Remove(path); err != nil && !errors.Is(err, fs.ErrNotExist) {
+		return err
+	}
+	return nil
 }

internal/lockutil/lockutil_test.go

@@ -1,220 +1,116 @@
 package lockutil
 
 import (
-	"bufio"
 	"errors"
-	"fmt"
-	"io"
 	"os"
-	"os/exec"
 	"path/filepath"
-	"runtime"
-	"strings"
-	"sync"
 	"testing"
 )
 
-func TestFileLockSerializesAndKeepsStablePath(t *testing.T) {
+func TestRestoreLockFile(t *testing.T) {
+	tempDir := t.TempDir()
+	path := filepath.Join(tempDir, "lock")
+	reclaimed := filepath.Join(tempDir, "lock.stale.token")
+
+	// 1. Successful restore when target does not exist
+	if err := os.WriteFile(reclaimed, []byte("token"), 0o600); err != nil {
+		t.Fatal(err)
+	}
+	if err := RestoreLockFile(reclaimed, path); err != nil {
+		t.Fatalf("RestoreLockFile failed: %v", err)
+	}
+	if data, err := os.ReadFile(path); err != nil || string(data) != "token" {
+		t.Fatalf("restored lock content = %q, err %v; want %q intact", data, err, "token")
+	}
+	if _, err := os.Stat(reclaimed); !os.IsNotExist(err) {
+		t.Fatalf("expected sidelined lock to be cleaned up/removed: %v", err)
+	}
+
+	// 2. Fail when target already exists (prevent overwrite)
+	if err := os.WriteFile(reclaimed, []byte("token"), 0o600); err != nil {
+		t.Fatal(err)
+	}
+	if err := os.WriteFile(path, []byte("competing"), 0o600); err != nil {
+		t.Fatal(err)
+	}
+
+	err := RestoreLockFile(reclaimed, path)
+	if err == nil {
+		t.Fatal("expected RestoreLockFile to fail when target exists")
+	}
+	if !errors.Is(err, os.ErrExist) {
+		t.Fatalf("expected os.ErrExist, got: %v", err)
+	}
+
+	// The sidelined lock must still exist on failure, and the competing lock
+	// must be untouched.
+	if _, err := os.Stat(reclaimed); err != nil {
+		t.Fatalf("expected sidelined lock to still exist: %v", err)
+	}
+	if data, _ := os.ReadFile(path); string(data) != "competing" {
+		t.Fatalf("competing lock was clobbered: %q", data)
+	}
+}
+
+func TestRestoreByCopy(t *testing.T) {
+	tempDir := t.TempDir()
+	path := filepath.Join(tempDir, "lock")
+	reclaimed := filepath.Join(tempDir, "lock.stale.token")
+
+	// 1. Restores content and cleans up the sidelined file when the target is
+	// free (the fallback taken when the platform's no-replace primitive fails
+	// for a reason other than the destination existing).
+	if err := os.WriteFile(reclaimed, []byte("token"), 0o600); err != nil {
+		t.Fatal(err)
+	}
+	if err := restoreByCopy(reclaimed, path, os.Link); err != nil {
+		t.Fatalf("restoreByCopy failed: %v", err)
+	}
+	if data, err := os.ReadFile(path); err != nil || string(data) != "token" {
+		t.Fatalf("restored lock content = %q, err %v; want %q intact", data, err, "token")
+	}
+	if _, err := os.Stat(reclaimed); !errors.Is(err, os.ErrNotExist) {
+		t.Fatalf("expected sidelined lock to be cleaned up after copy: %v", err)
+	}
+	if _, err := os.Stat(reclaimed + ".copy"); !errors.Is(err, os.ErrNotExist) {
+		t.Fatalf("expected staged copy to be cleaned up: %v", err)
+	}
+
+	// 2. Keeps the no-overwrite guarantee: a competing lock at the target wins
+	// and the sidelined lock survives for the caller's ErrExist cleanup.
+	if err := os.WriteFile(reclaimed, []byte("token"), 0o600); err != nil {
+		t.Fatal(err)
+	}
+	if err := os.WriteFile(path, []byte("competing"), 0o600); err != nil {
+		t.Fatal(err)
+	}
+	if err := restoreByCopy(reclaimed, path, os.Link); !errors.Is(err, os.ErrExist) {
+		t.Fatalf("expected os.ErrExist when target exists, got: %v", err)
+	}
+	if data, _ := os.ReadFile(path); string(data) != "competing" {
+		t.Fatalf("competing lock was clobbered: %q", data)
+	}
+	if _, err := os.Stat(reclaimed); err != nil {
+		t.Fatalf("expected sidelined lock to still exist: %v", err)
+	}
+	if _, err := os.Stat(reclaimed + ".copy"); !errors.Is(err, os.ErrNotExist) {
+		t.Fatalf("expected staged copy to be cleaned up after a failed publish: %v", err)
+	}
+}
+
+func TestRemoveLockFile(t *testing.T) {
 	path := filepath.Join(t.TempDir(), "lock")
-	first, err := TryAcquireFileLock(path)
-	if err != nil {
-		t.Fatalf("first acquire: %v", err)
+	if err := os.WriteFile(path, []byte("token"), 0o600); err != nil {
+		t.Fatal(err)
 	}
-	firstInfo, err := os.Stat(path)
-	if err != nil {
-		t.Fatalf("stat first lock path: %v", err)
+	if err := RemoveLockFile(path); err != nil {
+		t.Fatalf("RemoveLockFile failed: %v", err)
 	}
-	if _, err := TryAcquireFileLock(path); !errors.Is(err, ErrLockHeld) {
-		t.Fatalf("contended acquire = %v, want ErrLockHeld", err)
+	if _, err := os.Stat(path); !errors.Is(err, os.ErrNotExist) {
+		t.Fatalf("expected lock file to be removed: %v", err)
 	}
-	if err := first.Release(); err != nil {
-		t.Fatalf("release first: %v", err)
-	}
-	releasedInfo, err := os.Stat(path)
-	if err != nil {
-		t.Fatalf("release removed stable lock path: %v", err)
-	}
-	if !os.SameFile(firstInfo, releasedInfo) {
-		t.Fatal("release replaced the stable lock file")
-	}
-
-	second, err := TryAcquireFileLock(path)
-	if err != nil {
-		t.Fatalf("acquire after release: %v", err)
-	}
-	secondInfo, err := os.Stat(path)
-	if err != nil {
-		t.Fatalf("stat second lock path: %v", err)
-	}
-	if !os.SameFile(firstInfo, secondInfo) {
-		t.Fatal("reacquire used a different lock file")
-	}
-	if err := second.Release(); err != nil {
-		t.Fatalf("release second: %v", err)
-	}
-	if err := second.Release(); err != nil {
-		t.Fatalf("idempotent release: %v", err)
+	// Removing an already-missing lock file is a no-op on every platform.
+	if err := RemoveLockFile(path); err != nil {
+		t.Fatalf("RemoveLockFile on a missing file = %v, want nil", err)
 	}
 }
-
-func TestFileLockMetadata(t *testing.T) {
-	path := filepath.Join(t.TempDir(), "lock")
-	lock, err := TryAcquireFileLock(path)
-	if err != nil {
-		t.Fatal(err)
-	}
-	if err := lock.WriteMetadata([]byte("holder\n")); err != nil {
-		t.Fatalf("write metadata: %v", err)
-	}
-	data, err := os.ReadFile(path)
-	if err != nil || string(data) != "holder\n" {
-		t.Fatalf("metadata = %q, err %v", data, err)
-	}
-	if err := lock.Release(); err != nil {
-		t.Fatal(err)
-	}
-	if err := lock.WriteMetadata(nil); !errors.Is(err, ErrLockReleased) {
-		t.Fatalf("write after release = %v, want ErrLockReleased", err)
-	}
-}
-
-func TestFileLockConcurrentFirstAcquisition(t *testing.T) {
-	path := filepath.Join(t.TempDir(), "lock")
-	const contenders = 200
-	start := make(chan struct{})
-	results := make(chan error, contenders)
-	locks := make(chan *FileLock, contenders)
-	var ready sync.WaitGroup
-	ready.Add(contenders)
-	for range contenders {
-		go func() {
-			ready.Done()
-			<-start
-			lock, err := TryAcquireFileLock(path)
-			if lock != nil {
-				locks <- lock
-			}
-			results <- err
-		}()
-	}
-	ready.Wait()
-	close(start)
-	acquired := 0
-	for range contenders {
-		err := <-results
-		switch {
-		case err == nil:
-			acquired++
-		case !errors.Is(err, ErrLockHeld):
-			t.Errorf("concurrent first acquire: %v", err)
-		}
-	}
-	close(locks)
-	for lock := range locks {
-		if err := lock.Release(); err != nil {
-			t.Error(err)
-		}
-	}
-	if acquired != 1 {
-		t.Fatalf("concurrent first acquire: got %d holders, want 1", acquired)
-	}
-}
-
-func TestFileLockRefusesMultiplyLinkedEntry(t *testing.T) {
-	dir := t.TempDir()
-	target := filepath.Join(dir, "target")
-	lockPath := filepath.Join(dir, "lock")
-	const sentinel = "do not overwrite"
-	if err := os.WriteFile(target, []byte(sentinel), 0o600); err != nil {
-		t.Fatal(err)
-	}
-	if err := os.Link(target, lockPath); err != nil {
-		t.Fatalf("create redirected hard link: %v", err)
-	}
-	if lock, err := TryAcquireFileLock(lockPath); err == nil {
-		_ = lock.Release()
-		t.Fatal("TryAcquireFileLock accepted a multiply-linked entry")
-	}
-	data, err := os.ReadFile(target)
-	if err != nil {
-		t.Fatal(err)
-	}
-	if string(data) != sentinel {
-		t.Fatalf("redirected target was modified: %q", data)
-	}
-}
-
-func TestFileLockAtRejectsEscapingPath(t *testing.T) {
-	base := t.TempDir()
-	outside := filepath.Join(filepath.Dir(base), "outside.lock")
-	if lock, err := TryAcquireFileLockAt(base, outside); err == nil {
-		_ = lock.Release()
-		t.Fatal("TryAcquireFileLockAt accepted a path outside its root")
-	}
-	if _, err := os.Stat(outside); !errors.Is(err, os.ErrNotExist) {
-		t.Fatalf("escaping path was created: %v", err)
-	}
-}
-
-// TestFileLockReleasedByProcessExit proves crash recovery is provided by the
-// kernel lock lifetime. The child exits without calling Release; the next
-// process can then lock the same persistent file without moving or deleting it.
-func TestFileLockReleasedByProcessExit(t *testing.T) {
-	path := filepath.Join(t.TempDir(), "lock")
-	cmd := exec.Command(os.Args[0], "-test.run=^TestFileLockHelperProcess$")
-	cmd.Env = append(os.Environ(), "ZERO_LOCKUTIL_HELPER=1", "ZERO_LOCKUTIL_PATH="+path)
-	stdout, err := cmd.StdoutPipe()
-	if err != nil {
-		t.Fatal(err)
-	}
-	stdin, err := cmd.StdinPipe()
-	if err != nil {
-		t.Fatal(err)
-	}
-	cmd.Stderr = os.Stderr
-	if err := cmd.Start(); err != nil {
-		t.Fatal(err)
-	}
-
-	ready, err := bufio.NewReader(stdout).ReadString('\n')
-	if err != nil || strings.TrimSpace(ready) != "ready" {
-		_ = cmd.Process.Kill()
-		_ = cmd.Wait()
-		t.Fatalf("helper readiness = %q, err %v", ready, err)
-	}
-	if _, err := TryAcquireFileLock(path); !errors.Is(err, ErrLockHeld) {
-		_ = cmd.Process.Kill()
-		_ = cmd.Wait()
-		t.Fatalf("acquire while helper holds lock = %v, want ErrLockHeld", err)
-	}
-	if err := stdin.Close(); err != nil {
-		t.Fatal(err)
-	}
-	if err := cmd.Wait(); err != nil {
-		t.Fatalf("helper exit: %v", err)
-	}
-
-	lock, err := TryAcquireFileLock(path)
-	if err != nil {
-		t.Fatalf("acquire after helper exit: %v", err)
-	}
-	if err := lock.Release(); err != nil {
-		t.Fatal(err)
-	}
-}
-
-func TestFileLockHelperProcess(t *testing.T) {
-	if os.Getenv("ZERO_LOCKUTIL_HELPER") != "1" {
-		return
-	}
-	lock, err := TryAcquireFileLock(os.Getenv("ZERO_LOCKUTIL_PATH"))
-	if err != nil {
-		fmt.Fprintln(os.Stderr, err)
-		os.Exit(2)
-	}
-	if _, err := fmt.Fprintln(os.Stdout, "ready"); err != nil {
-		os.Exit(3)
-	}
-	_, _ = io.Copy(io.Discard, os.Stdin)
-	runtime.KeepAlive(lock) // deliberately exit without Release
-}

internal/lockutil/lockutil_windows.go

@@ -4,202 +4,77 @@ package lockutil
 
 import (
 	"errors"
-	"fmt"
 	"os"
-	"path/filepath"
-	"strings"
-	"unsafe"
+	"syscall"
+	"time"
 
 	"golang.org/x/sys/windows"
 )
 
-type platformLockState struct {
-	overlapped windows.Overlapped
+// RestoreLockFile restores a sidelined lock file on Windows. It moves the file
+// with a no-replace MoveFileEx so a competing lock created at path in the
+// meantime wins: the move fails with os.ErrExist instead of overwriting it. If
+// the move fails for any other reason (ERROR_SHARING_VIOLATION or
+// ERROR_ACCESS_DENIED under concurrent access to the file), it falls back to
+// an O_EXCL copy rather than leaving path missing and the live holder's lock
+// stranded in reclaimed.
+func RestoreLockFile(reclaimed, path string) error {
+	err := moveFileNoReplace(reclaimed, path)
+	if err == nil || errors.Is(err, os.ErrExist) {
+		return err
+	}
+	return restoreByCopy(reclaimed, path, moveFileNoReplace)
 }
 
-const lockByteOffsetHigh = 1
-
-func openLockFileAt(root, relative, displayPath string) (_ *os.File, resultErr error) {
-	rootPtr, err := windows.UTF16PtrFromString(root)
+// moveFileNoReplace renames from to to, failing if to already exists. It calls
+// MoveFileExW directly via golang.org/x/sys/windows (the standard library's
+// syscall package does not export MoveFileEx on this platform) with no flags,
+// so an existing destination fails with ERROR_ALREADY_EXISTS, which satisfies
+// errors.Is(err, os.ErrExist) (pinned by
+// TestMoveFileNoReplaceMapsAlreadyExistsToErrExist), instead of overwriting it
+// the way os.Rename does on Windows (it passes MOVEFILE_REPLACE_EXISTING to
+// match POSIX rename semantics cross-platform).
+func moveFileNoReplace(from, to string) error {
+	fromPtr, err := windows.UTF16PtrFromString(from)
 	if err != nil {
-		return nil, err
+		return err
 	}
-	parent, err := windows.CreateFile(
-		rootPtr,
-		windows.FILE_READ_ATTRIBUTES|windows.FILE_TRAVERSE|windows.SYNCHRONIZE,
-		windows.FILE_SHARE_READ|windows.FILE_SHARE_WRITE|windows.FILE_SHARE_DELETE,
-		nil,
-		windows.OPEN_EXISTING,
-		windows.FILE_FLAG_BACKUP_SEMANTICS,
-		0,
-	)
+	toPtr, err := windows.UTF16PtrFromString(to)
 	if err != nil {
-		return nil, fmt.Errorf("open lock root: %w", err)
+		return err
 	}
-	defer func() {
-		if parent != 0 {
-			resultErr = errors.Join(resultErr, windows.CloseHandle(parent))
-		}
-	}()
-
-	components := strings.Split(filepath.Clean(relative), string(filepath.Separator))
-	for _, component := range components[:len(components)-1] {
-		next, openErr := openLockDirectoryAt(parent, component)
-		if openErr != nil {
-			return nil, fmt.Errorf("open lock path component %q: %w", component, openErr)
-		}
-		if closeErr := windows.CloseHandle(parent); closeErr != nil {
-			_ = windows.CloseHandle(next)
-			parent = 0
-			return nil, fmt.Errorf("close lock path component: %w", closeErr)
-		}
-		parent = next
-	}
-
-	handle, err := openLockFileHandleAt(parent, components[len(components)-1])
-	if err != nil {
-		return nil, err
-	}
-	file := os.NewFile(uintptr(handle), displayPath)
-	if file == nil {
-		_ = windows.CloseHandle(handle)
-		return nil, errors.New("convert lock handle to file")
-	}
-	if err := windows.CloseHandle(parent); err != nil {
-		parent = 0
-		return nil, errors.Join(fmt.Errorf("close lock parent: %w", err), file.Close())
-	}
-	parent = 0
-	return file, nil
+	return windows.MoveFileEx(fromPtr, toPtr, 0)
 }
 
-func openLockDirectoryAt(parent windows.Handle, name string) (windows.Handle, error) {
-	handle, err := openLockPathAt(
-		parent,
-		name,
-		windows.FILE_READ_ATTRIBUTES|windows.FILE_TRAVERSE|windows.SYNCHRONIZE,
-		windows.FILE_OPEN,
-		windows.FILE_ATTRIBUTE_DIRECTORY,
-		windows.FILE_DIRECTORY_FILE|windows.FILE_SYNCHRONOUS_IO_NONALERT|windows.FILE_OPEN_REPARSE_POINT,
-	)
-	if err != nil {
-		return 0, err
-	}
-	if err := validateWindowsLockHandle(handle, true); err != nil {
-		return 0, errors.Join(err, windows.CloseHandle(handle))
-	}
-	return handle, nil
+// isReclaimContended reports whether a failed rename-aside of a suspected
+// stale lock means the file was concurrently open or pending deletion (which
+// surfaces as ERROR_SHARING_VIOLATION or ERROR_ACCESS_DENIED on Windows)
+// rather than a hard failure, so ReclaimStaleLock reports a lost race instead
+// of an error. Neither errno satisfies errors.Is(err, os.ErrExist), and
+// ERROR_SHARING_VIOLATION does not satisfy errors.Is(err, os.ErrPermission)
+// either, so the classification compares raw errnos like RemoveLockFile below.
+func isReclaimContended(err error) bool {
+	var errno syscall.Errno
+	return errors.As(err, &errno) && (errno == windows.ERROR_SHARING_VIOLATION || errno == windows.ERROR_ACCESS_DENIED)
 }
 
-func openLockFileHandleAt(parent windows.Handle, name string) (windows.Handle, error) {
-	for attempt := 0; attempt < 10; attempt++ {
-		handle, err := openLockPathAt(
-			parent,
-			name,
-			windows.GENERIC_READ|windows.GENERIC_WRITE|windows.SYNCHRONIZE,
-			windows.FILE_OPEN,
-			windows.FILE_ATTRIBUTE_NORMAL,
-			windows.FILE_NON_DIRECTORY_FILE|windows.FILE_SYNCHRONOUS_IO_NONALERT|windows.FILE_OPEN_REPARSE_POINT,
-		)
-		if err == nil {
-			if err := validateWindowsLockHandle(handle, false); err != nil {
-				return 0, errors.Join(err, windows.CloseHandle(handle))
-			}
-			return handle, nil
+// RemoveLockFile removes a lock file on Windows, retrying on the sharing
+// violation or access denied errors that are common under heavy concurrent
+// contention. Removing an already-missing file reports nil, matching the
+// non-Windows implementation, so callers see one cross-platform contract.
+func RemoveLockFile(path string) error {
+	var err error
+	for i := 0; i < 15; i++ {
+		err = os.Remove(path)
+		if err == nil || os.IsNotExist(err) {
+			return nil
 		}
-		if !windowsLockPathMissing(err) {
-			return 0, err
-		}
-
-		handle, err = openLockPathAt(
-			parent,
-			name,
-			windows.GENERIC_READ|windows.GENERIC_WRITE|windows.SYNCHRONIZE,
-			windows.FILE_CREATE,
-			windows.FILE_ATTRIBUTE_NORMAL,
-			windows.FILE_NON_DIRECTORY_FILE|windows.FILE_SYNCHRONOUS_IO_NONALERT|windows.FILE_OPEN_REPARSE_POINT,
-		)
-		if err == windows.STATUS_OBJECT_NAME_COLLISION || errors.Is(err, windows.ERROR_ALREADY_EXISTS) {
+		var errno syscall.Errno
+		if errors.As(err, &errno) && (errno == windows.ERROR_SHARING_VIOLATION || errno == windows.ERROR_ACCESS_DENIED) {
+			time.Sleep(5 * time.Millisecond)
 			continue
 		}
-		if err != nil {
-			return 0, err
-		}
-		if err := validateWindowsLockHandle(handle, false); err != nil {
-			return 0, errors.Join(err, windows.CloseHandle(handle))
-		}
-		return handle, nil
+		return err
 	}
-	return 0, errors.New("lock file creation did not stabilize")
-}
-
-func windowsLockPathMissing(err error) bool {
-	return err == windows.STATUS_NO_SUCH_FILE ||
-		err == windows.STATUS_OBJECT_NAME_NOT_FOUND ||
-		err == windows.STATUS_OBJECT_PATH_NOT_FOUND ||
-		errors.Is(err, windows.ERROR_FILE_NOT_FOUND) ||
-		errors.Is(err, windows.ERROR_PATH_NOT_FOUND)
-}
-
-func openLockPathAt(parent windows.Handle, name string, access, disposition, attributes, options uint32) (windows.Handle, error) {
-	objectName, err := windows.NewNTUnicodeString(name)
-	if err != nil {
-		return 0, err
-	}
-	objectAttributes := &windows.OBJECT_ATTRIBUTES{
-		Length:        uint32(unsafe.Sizeof(windows.OBJECT_ATTRIBUTES{})),
-		RootDirectory: parent,
-		ObjectName:    objectName,
-		Attributes:    windows.OBJ_CASE_INSENSITIVE | windows.OBJ_DONT_REPARSE,
-	}
-	var handle windows.Handle
-	err = windows.NtCreateFile(
-		&handle,
-		access,
-		objectAttributes,
-		&windows.IO_STATUS_BLOCK{},
-		nil,
-		attributes,
-		windows.FILE_SHARE_READ|windows.FILE_SHARE_WRITE|windows.FILE_SHARE_DELETE,
-		disposition,
-		options,
-		0,
-		0,
-	)
-	return handle, err
-}
-
-func validateWindowsLockHandle(handle windows.Handle, wantDirectory bool) error {
-	var info windows.ByHandleFileInformation
-	if err := windows.GetFileInformationByHandle(handle, &info); err != nil {
-		return fmt.Errorf("inspect lock path handle: %w", err)
-	}
-	isDirectory := info.FileAttributes&windows.FILE_ATTRIBUTE_DIRECTORY != 0
-	if info.FileAttributes&windows.FILE_ATTRIBUTE_REPARSE_POINT != 0 || isDirectory != wantDirectory {
-		return errors.New("refusing non-file or reparse-point lock path")
-	}
-	if !wantDirectory && info.NumberOfLinks != 1 {
-		return errors.New("refusing multiply-linked lock file")
-	}
-	return nil
-}
-
-func tryLockFile(file *os.File) (platformLockState, bool, error) {
-	state := platformLockState{overlapped: windows.Overlapped{OffsetHigh: lockByteOffsetHigh}}
-	flags := uint32(windows.LOCKFILE_EXCLUSIVE_LOCK | windows.LOCKFILE_FAIL_IMMEDIATELY)
-	err := windows.LockFileEx(windows.Handle(file.Fd()), flags, 0, 1, 0, &state.overlapped)
-	if err == nil {
-		return state, false, nil
-	}
-	if errors.Is(err, windows.ERROR_LOCK_VIOLATION) || errors.Is(err, windows.ERROR_SHARING_VIOLATION) {
-		return platformLockState{}, true, nil
-	}
-	return platformLockState{}, false, err
-}
-
-func unlockFile(file *os.File, state *platformLockState) error {
-	if file == nil {
-		return nil
-	}
-	return windows.UnlockFileEx(windows.Handle(file.Fd()), 0, 1, 0, &state.overlapped)
+	return err
 }

internal/lockutil/lockutil_windows_test.go

@@ -0,0 +1,83 @@
+//go:build windows
+
+package lockutil
+
+import (
+	"errors"
+	"os"
+	"path/filepath"
+	"testing"
+	"time"
+
+	"golang.org/x/sys/windows"
+)
+
+// TestMoveFileNoReplaceMapsAlreadyExistsToErrExist pins the errno coupling
+// every caller keys its cleanup on: with no flags, MoveFileEx fails with
+// ERROR_ALREADY_EXISTS when the destination exists, and that errno must
+// satisfy errors.Is(err, os.ErrExist).
+func TestMoveFileNoReplaceMapsAlreadyExistsToErrExist(t *testing.T) {
+	dir := t.TempDir()
+	from := filepath.Join(dir, "from")
+	to := filepath.Join(dir, "to")
+	if err := os.WriteFile(from, []byte("sidelined"), 0o600); err != nil {
+		t.Fatal(err)
+	}
+	if err := os.WriteFile(to, []byte("competing"), 0o600); err != nil {
+		t.Fatal(err)
+	}
+	err := moveFileNoReplace(from, to)
+	if !errors.Is(err, windows.ERROR_ALREADY_EXISTS) {
+		t.Fatalf("MoveFileEx with an existing destination = %v, want ERROR_ALREADY_EXISTS", err)
+	}
+	if !errors.Is(err, os.ErrExist) {
+		t.Fatalf("ERROR_ALREADY_EXISTS must satisfy errors.Is(err, os.ErrExist), got: %v", err)
+	}
+	if data, _ := os.ReadFile(to); string(data) != "competing" {
+		t.Fatalf("destination was overwritten: %q", data)
+	}
+}
+
+// TestRemoveLockFileRetriesSharingViolation holds the file open briefly (Go
+// opens files without FILE_SHARE_DELETE on Windows, so a concurrent DeleteFile
+// fails with ERROR_SHARING_VIOLATION while the handle is open); RemoveLockFile
+// must ride its retry loop (15 x 5ms) past the window and succeed once the
+// handle closes.
+func TestRemoveLockFileRetriesSharingViolation(t *testing.T) {
+	path := filepath.Join(t.TempDir(), "lock")
+	if err := os.WriteFile(path, []byte("token"), 0o600); err != nil {
+		t.Fatal(err)
+	}
+	f, err := os.Open(path)
+	if err != nil {
+		t.Fatal(err)
+	}
+	go func() {
+		time.Sleep(10 * time.Millisecond)
+		_ = f.Close()
+	}()
+	if err := RemoveLockFile(path); err != nil {
+		t.Fatalf("RemoveLockFile should succeed once the contending handle closes: %v", err)
+	}
+	if _, err := os.Stat(path); !errors.Is(err, os.ErrNotExist) {
+		t.Fatalf("expected lock file to be removed: %v", err)
+	}
+}
+
+// TestRemoveLockFileSharingViolationExhausts verifies the retry loop is
+// bounded: with the contending handle held for the whole call, RemoveLockFile
+// surfaces the sharing violation instead of retrying forever.
+func TestRemoveLockFileSharingViolationExhausts(t *testing.T) {
+	path := filepath.Join(t.TempDir(), "lock")
+	if err := os.WriteFile(path, []byte("token"), 0o600); err != nil {
+		t.Fatal(err)
+	}
+	f, err := os.Open(path)
+	if err != nil {
+		t.Fatal(err)
+	}
+	defer f.Close()
+	if err := RemoveLockFile(path); !errors.Is(err, windows.ERROR_SHARING_VIOLATION) {
+		t.Fatalf("RemoveLockFile with a held handle = %v, want ERROR_SHARING_VIOLATION", err)
+	}
+}

internal/lockutil/reclaim.go

@@ -0,0 +1,82 @@
+package lockutil
+
+import (
+	"errors"
+	"os"
+)
+
+// restoreLockFile is swappable so tests can force the fail-closed path of
+// ReclaimStaleLock, which requires both the fast restore and its no-replace
+// fallback (with its own copy fallback) to fail; that cannot be provoked
+// portably on a healthy filesystem.
+var restoreLockFile = restoreLiveLock
+
+// restoreLiveLock puts a lock that turned out to be live back at path after
+// ReclaimStaleLock moved it aside to inspect it. It first tries a fast,
+// replacing rename straight from reclaimed to path: a single syscall, which
+// keeps the window during which path does not exist (and so is open to a
+// fourth process's unrelated O_EXCL create landing on it) as short as
+// possible. RestoreLockFile's no-replace restore (with its slower copy
+// fallback on some failures) is a correctness-preserving fallback for when
+// the fast path itself fails (e.g. a cross-device sidelined name): it is a
+// much longer version of the identical race, but still detects rather than
+// silently clobbers a competing lock, which the fast path's replacing rename
+// cannot do. Neither path makes the race impossible, only unlikely; see
+// ReclaimStaleLock's doc comment.
+func restoreLiveLock(reclaimed, path string) error {
+	if err := os.Rename(reclaimed, path); err == nil {
+		return nil
+	}
+	return RestoreLockFile(reclaimed, path)
+}
+
+// ReclaimStaleLock atomically reclaims a suspected-stale lock file. It renames
+// lockPath aside to "<lockPath>.stale.<suffix>" (only one racer can win the
+// rename of a given file, so two racers can never both reclaim the same lock),
+// then consults isLive on the moved file; if the lock turns out to be live (a
+// holder reacquired it in the gap between the caller's stale check and the
+// rename) it is restored rather than stolen. The suffix must be unique per
+// acquirer attempt. Returns true only when a genuinely stale lock was removed,
+// so the caller knows it is safe to retry its exclusive create immediately; on
+// a lost race it returns false. A non-nil error means either the rename aside
+// failed for a reason that is not contention (so retrying cannot help and the
+// caller should fail fast instead of spinning to its deadline), or a live
+// holder's lock could not be restored (both restoreLiveLock's fast path and
+// its no-replace fallback failed), so lockPath may be missing; callers must
+// fail closed instead of re-acquiring. The sidelined file is removed on every
+// restore failure: once the restore has failed it has no protocol function
+// (release only consults the lock path), so keeping it would only leak files.
+//
+// The live-restore path has an inherent, unclosed race: between the rename
+// aside above and restoreLiveLock putting the lock back, lockPath does not
+// exist, so an unrelated caller's O_EXCL create can legitimately succeed
+// there. restoreLiveLock's fast path then silently overwrites that new
+// claimant's lock file, which does not corrupt release (it is
+// ownership-aware, so the new claimant's later release safely no-ops against
+// content it no longer owns) but does mean the new claimant can still run
+// its critical section concurrently with the original live holder. Making
+// this race actually impossible would need an OS-level advisory lock (flock
+// / LockFileEx) held for a holder's whole critical section, checked
+// non-destructively instead of by moving the file; restoreLiveLock only
+// shrinks the window to roughly one syscall, it does not close it.
+func ReclaimStaleLock(lockPath, suffix string, isLive func(reclaimedPath string) bool) (bool, error) {
+	reclaimed := lockPath + ".stale." + suffix
+	if err := os.Rename(lockPath, reclaimed); err != nil {
+		if errors.Is(err, os.ErrNotExist) || isReclaimContended(err) {
+			return false, nil // another racer already moved/removed it, or it vanished
+		}
+		return false, err
+	}
+	if isLive(reclaimed) {
+		// Put the live lock back instead of stealing it, and let the caller wait.
+		if rerr := restoreLockFile(reclaimed, lockPath); rerr != nil {
+			_ = RemoveLockFile(reclaimed)
+			if !errors.Is(rerr, os.ErrExist) {
+				return false, rerr
+			}
+		}
+		return false, nil
+	}
+	_ = RemoveLockFile(reclaimed)
+	return true, nil
+}

internal/lockutil/reclaim_other_test.go

@@ -0,0 +1,31 @@
+//go:build !windows
+
+package lockutil
+
+import (
+	"os"
+	"path/filepath"
+	"testing"
+)
+
+// TestReclaimStaleLockPropagatesRenameFailure pins the fail-fast contract of
+// the rename aside: a failure that is not a lost race must reach the caller.
+// Mapping it to the benign lost-race result would leave acquirers spinning
+// until their deadline and reporting a timeout instead of the real cause. A
+// directory squatting on the sidelined name makes os.Rename fail with EISDIR,
+// which matches neither os.ErrNotExist nor a contention errno.
+func TestReclaimStaleLockPropagatesRenameFailure(t *testing.T) {
+	lockPath := filepath.Join(t.TempDir(), "lock")
+	if err := os.WriteFile(lockPath, []byte("stale-holder"), 0o600); err != nil {
+		t.Fatal(err)
+	}
+	if err := os.Mkdir(lockPath+".stale.tok", 0o755); err != nil {
+		t.Fatal(err)
+	}
+	if ok, err := ReclaimStaleLock(lockPath, "tok", func(string) bool { return false }); err == nil || ok {
+		t.Fatalf("a hard rename failure must surface an error (ok=%v err=%v)", ok, err)
+	}
+	if _, err := os.Stat(lockPath); err != nil {
+		t.Fatalf("the lock file must be left in place on a failed rename: %v", err)
+	}
+}

internal/lockutil/reclaim_test.go

@@ -0,0 +1,112 @@
+package lockutil
+
+import (
+	"errors"
+	"os"
+	"path/filepath"
+	"testing"
+)
+
+func TestReclaimStaleLock(t *testing.T) {
+	lockPath := filepath.Join(t.TempDir(), "lock")
+	dead := func(string) bool { return false }
+	live := func(string) bool { return true }
+
+	// A lock the predicate reports dead is reclaimed and removed.
+	if err := os.WriteFile(lockPath, []byte("crashed-holder"), 0o600); err != nil {
+		t.Fatal(err)
+	}
+	if ok, err := ReclaimStaleLock(lockPath, "tok-a", dead); err != nil || !ok {
+		t.Fatalf("a dead lock should be reclaimed (ok=%v err=%v)", ok, err)
+	}
+	if _, err := os.Stat(lockPath); !errors.Is(err, os.ErrNotExist) {
+		t.Fatalf("reclaimed dead lock should be gone, stat err=%v", err)
+	}
+
+	// A LIVE lock (a holder reacquired in the gap) must be RESTORED intact.
+	if err := os.WriteFile(lockPath, []byte("live-holder"), 0o600); err != nil {
+		t.Fatal(err)
+	}
+	if ok, err := ReclaimStaleLock(lockPath, "tok-b", live); err != nil || ok {
+		t.Fatalf("a live lock must not be reclaimed (ok=%v err=%v)", ok, err)
+	}
+	if data, err := os.ReadFile(lockPath); err != nil || string(data) != "live-holder" {
+		t.Fatalf("live lock must be left intact, got %q err %v", data, err)
+	}
+
+	// A missing lock reports no reclaim (nothing to steal).
+	_ = os.Remove(lockPath)
+	if ok, err := ReclaimStaleLock(lockPath, "tok-c", live); err != nil || ok {
+		t.Fatalf("a missing lock should not report a reclaim (ok=%v err=%v)", ok, err)
+	}
+}
+
+// restoreLiveLock's fast path is a single replacing rename, chosen to
+// minimize (not eliminate) the window during which lockPath is absent and
+// open to an unrelated O_EXCL create; see ReclaimStaleLock's doc comment for
+// why that residual race exists. This test pins the resulting behavior: the
+// fast path overwrites a competing file at path rather than detecting it,
+// unlike RestoreLockFile's own no-replace contract.
+func TestRestoreLiveLockFastPathOverwritesCompetingFile(t *testing.T) {
+	dir := t.TempDir()
+	reclaimed := filepath.Join(dir, "lock.stale.tok")
+	path := filepath.Join(dir, "lock")
+
+	if err := os.WriteFile(reclaimed, []byte("original-holder"), 0o600); err != nil {
+		t.Fatal(err)
+	}
+	if err := os.WriteFile(path, []byte("new-claimant"), 0o600); err != nil {
+		t.Fatal(err)
+	}
+	if err := restoreLiveLock(reclaimed, path); err != nil {
+		t.Fatalf("restoreLiveLock failed: %v", err)
+	}
+	data, err := os.ReadFile(path)
+	if err != nil || string(data) != "original-holder" {
+		t.Fatalf("path = %q, err %v; want the original holder's content restored", data, err)
+	}
+	if _, err := os.Stat(reclaimed); !errors.Is(err, os.ErrNotExist) {
+		t.Fatalf("expected reclaimed to be consumed by the rename: %v", err)
+	}
+}
+
+func TestReclaimStaleLockFailsClosedOnRestoreError(t *testing.T) {
+	// When both the no-replace restore and its copy fallback fail (only
+	// provokable via the seam; a healthy filesystem cannot produce it), the
+	// caller must receive an error so it fails closed instead of re-acquiring a
+	// missing lock path, and the sidelined file must not leak.
+	restoreLockFile = func(reclaimed, path string) error { return errors.New("restore failed") }
+	defer func() { restoreLockFile = restoreLiveLock }()
+
+	lockPath := filepath.Join(t.TempDir(), "lock")
+	if err := os.WriteFile(lockPath, []byte("live-holder"), 0o600); err != nil {
+		t.Fatal(err)
+	}
+	ok, err := ReclaimStaleLock(lockPath, "tok", func(string) bool { return true })
+	if err == nil || ok {
+		t.Fatalf("a failed restore must surface an error (ok=%v err=%v)", ok, err)
+	}
+	if matches, _ := filepath.Glob(lockPath + ".stale.*"); len(matches) != 0 {
+		t.Fatalf("a failed restore must not leak sidelined files: %v", matches)
+	}
+}
+
+func TestReclaimStaleLockDropsSidelinedWhenNewHolderWins(t *testing.T) {
+	// An os.ErrExist restore failure means a new holder recreated the lock
+	// path; that is not an error for the caller, and the sidelined file is
+	// dropped rather than leaked.
+	restoreLockFile = func(reclaimed, path string) error { return os.ErrExist }
+	defer func() { restoreLockFile = restoreLiveLock }()
+
+	lockPath := filepath.Join(t.TempDir(), "lock")
+	if err := os.WriteFile(lockPath, []byte("live-holder"), 0o600); err != nil {
+		t.Fatal(err)
+	}
+	ok, err := ReclaimStaleLock(lockPath, "tok", func(string) bool { return true })
+	if err != nil || ok {
+		t.Fatalf("losing to a new holder is not an error (ok=%v err=%v)", ok, err)
+	}
+	if matches, _ := filepath.Glob(lockPath + ".stale.*"); len(matches) != 0 {
+		t.Fatalf("the sidelined file must be dropped when a new holder wins: %v", matches)
+	}
+}

internal/lockutil/reclaim_windows_test.go

@@ -0,0 +1,50 @@
+//go:build windows
+
+package lockutil
+
+import (
+	"os"
+	"path/filepath"
+	"testing"
+)
+
+// TestReclaimStaleLockTreatsSharingViolationAsLostRace pins the errno
+// classification the Windows acquire loops depend on: a rename aside that
+// fails because the lock file is concurrently open (Go opens files without
+// FILE_SHARE_DELETE, so the rename fails with ERROR_SHARING_VIOLATION or
+// ERROR_ACCESS_DENIED) is contention, not a hard failure, and must report a
+// benign lost race so the caller keeps waiting.
+func TestReclaimStaleLockTreatsSharingViolationAsLostRace(t *testing.T) {
+	lockPath := filepath.Join(t.TempDir(), "lock")
+	if err := os.WriteFile(lockPath, []byte("held"), 0o600); err != nil {
+		t.Fatal(err)
+	}
+	f, err := os.Open(lockPath)
+	if err != nil {
+		t.Fatal(err)
+	}
+	defer f.Close()
+	if ok, rerr := ReclaimStaleLock(lockPath, "tok", func(string) bool { return true }); rerr != nil || ok {
+		t.Fatalf("a sharing-violation rename must report a benign lost race (ok=%v err=%v)", ok, rerr)
+	}
+	if _, err := os.Stat(lockPath); err != nil {
+		t.Fatalf("the lock file must be left in place: %v", err)
+	}
+}
+
+// TestReclaimStaleLockPropagatesRenameFailure pins the fail-fast contract of
+// the rename aside on Windows: a failure that is not contention must reach
+// the caller instead of masquerading as a lost race. A quote is an invalid
+// filename character, so the sidelined name fails with ERROR_INVALID_NAME.
+func TestReclaimStaleLockPropagatesRenameFailure(t *testing.T) {
+	lockPath := filepath.Join(t.TempDir(), "lock")
+	if err := os.WriteFile(lockPath, []byte("stale-holder"), 0o600); err != nil {
+		t.Fatal(err)
+	}
+	if ok, err := ReclaimStaleLock(lockPath, `bad"name`, func(string) bool { return false }); err == nil || ok {
+		t.Fatalf("a hard rename failure must surface an error (ok=%v err=%v)", ok, err)
+	}
+	if _, err := os.Stat(lockPath); err != nil {
+		t.Fatalf("the lock file must be left in place on a failed rename: %v", err)
+	}
+}

internal/mcp/oauth.go

@@ -63,9 +63,8 @@ func tokenToStored(t oauth.Token) StoredToken {
 }
 
 // OAuthConfig describes how to authenticate to a remote MCP server using OAuth.
-// Endpoints may be discovered through RFC 9728 protected-resource metadata and
-// RFC 8414 authorization-server metadata; explicit values override or fill in
-// anything discovery cannot provide.
+// Endpoints may be discovered from the server's metadata document; explicit
+// values here override or fill in anything discovery cannot provide.
 type OAuthConfig struct {
 	ClientID              string
 	ClientSecret          string
@@ -86,11 +85,6 @@ type authServerMetadata struct {
 	TokenEndpoint         string   `json:"token_endpoint"`
 	RegistrationEndpoint  string   `json:"registration_endpoint"`
 	ScopesSupported       []string `json:"scopes_supported"`
-
-	protectedResourceURL         string
-	protectAuthorizationEndpoint bool
-	protectTokenEndpoint         bool
-	protectRegistrationEndpoint  bool
 }
 
 // pkceParams holds a PKCE verifier/challenge pair.
@@ -126,7 +120,7 @@ type authorizationFlow struct {
 // discoverAuthorizationServer fetches the RFC 8414 authorization server metadata
 // at the well-known path under baseURL, via the shared engine.
 func discoverAuthorizationServer(ctx context.Context, client *http.Client, baseURL string) (authServerMetadata, error) {
-	meta, err := oauth.DiscoverAuthorizationServer(ctx, withoutDiscoveryRedirects(client), baseURL)
+	meta, err := oauth.DiscoverAuthorizationServer(ctx, client, baseURL)
 	if err != nil {
 		return authServerMetadata{}, err
 	}
@@ -139,9 +133,10 @@ func discoverAuthorizationServer(ctx context.Context, client *http.Client, baseU
 	}, nil
 }
 
-// validateResolvedEndpoints applies the shared https/loopback scheme rule to
-// every non-empty endpoint in the resolved metadata. Protected-resource
-// discovery adds its stricter provenance-aware network rule below.
+// validateResolvedEndpoints applies the shared https/loopback endpoint rule to
+// every non-empty endpoint in the resolved metadata — configured or discovered
+// alike — so discovery metadata can never downgrade an MCP login to an insecure
+// or attacker-controlled authorization, token, or registration endpoint.
 func validateResolvedEndpoints(metadata authServerMetadata) error {
 	for _, ep := range []struct{ kind, url string }{
 		{"authorization", metadata.AuthorizationEndpoint},
@@ -158,43 +153,9 @@ func validateResolvedEndpoints(metadata authServerMetadata) error {
 	return nil
 }
 
-func validateProtectedDiscoveredEndpoints(ctx context.Context, metadata authServerMetadata) error {
-	if metadata.protectedResourceURL == "" {
-		return nil
-	}
-	policy, err := newOAuthDiscoveryNetworkPolicy(metadata.protectedResourceURL)
-	if err != nil {
-		return err
-	}
-	for _, endpoint := range []struct {
-		kind      string
-		url       string
-		protected bool
-	}{
-		{kind: "authorization", url: metadata.AuthorizationEndpoint, protected: metadata.protectAuthorizationEndpoint},
-		{kind: "token", url: metadata.TokenEndpoint, protected: metadata.protectTokenEndpoint},
-		{kind: "registration", url: metadata.RegistrationEndpoint, protected: metadata.protectRegistrationEndpoint},
-	} {
-		if !endpoint.protected || strings.TrimSpace(endpoint.url) == "" {
-			continue
-		}
-		parsed, parseErr := url.Parse(endpoint.url)
-		if parseErr != nil || parsed.Hostname() == "" {
-			return fmt.Errorf("mcp oauth: %s endpoint: %w", endpoint.kind, errUnsafeOAuthDiscoveryTarget)
-		}
-		if err := policy.validateLiteralHost(parsed.Hostname()); err != nil {
-			return fmt.Errorf("mcp oauth: %s endpoint: %w", endpoint.kind, err)
-		}
-		if _, err := policy.resolve(ctx, parsed.Hostname()); err != nil {
-			return fmt.Errorf("mcp oauth: %s endpoint: %w", endpoint.kind, err)
-		}
-	}
-	return nil
-}
-
-// resolveAuthorizationServer follows protected-resource metadata when the MCP
-// endpoint advertises it, falls back to direct authorization-server discovery
-// for legacy providers, then applies explicit config overrides.
+// resolveAuthorizationServer discovers metadata and applies explicit config
+// overrides. Configured endpoints take precedence over discovered ones, and act
+// as a fallback when discovery fails or omits a value.
 func resolveAuthorizationServer(ctx context.Context, client *http.Client, baseURL string, cfg OAuthConfig) (authServerMetadata, error) {
 	// When the config supplies both the authorization and token endpoints
 	// directly, skip network discovery entirely: there is nothing to discover,
@@ -213,40 +174,17 @@ func resolveAuthorizationServer(ctx context.Context, client *http.Client, baseUR
 		return metadata, nil
 	}
 
-	discoveryClient := withoutDiscoveryRedirects(client)
 	discoveryBase := strings.TrimSpace(cfg.IssuerURL)
-	protectedResourceDiscovery := false
 	if discoveryBase == "" {
-		issuer, found, protectedErr := discoverProtectedResourceAuthorizationServer(ctx, discoveryClient, baseURL)
-		if protectedErr != nil {
-			return authServerMetadata{}, protectedErr
-		}
-		if found {
-			discoveryBase = issuer
-			protectedResourceDiscovery = true
-			discoveryClient, protectedErr = newAdvertisedOAuthDiscoveryClient(discoveryClient, baseURL)
-			if protectedErr != nil {
-				return authServerMetadata{}, protectedErr
-			}
-		} else {
-			discoveryBase = baseURL
-		}
+		discoveryBase = baseURL
 	}
 
-	metadata, err := discoverAuthorizationServer(ctx, discoveryClient, discoveryBase)
+	metadata, err := discoverAuthorizationServer(ctx, client, discoveryBase)
 	if err != nil {
 		// Discovery failures are non-fatal when the config supplies the endpoints
 		// directly; otherwise surface the discovery error.
 		metadata = authServerMetadata{}
 	}
-	if protectedResourceDiscovery {
-		if strings.TrimSpace(metadata.Issuer) == "" {
-			return authServerMetadata{}, errors.New("mcp oauth: authorization server metadata is missing its required issuer")
-		}
-		if metadata.Issuer != discoveryBase {
-			return authServerMetadata{}, errors.New("mcp oauth: authorization server metadata issuer does not match protected resource metadata")
-		}
-	}
 
 	if endpoint := strings.TrimSpace(cfg.AuthorizationEndpoint); endpoint != "" {
 		metadata.AuthorizationEndpoint = endpoint
@@ -257,12 +195,6 @@ func resolveAuthorizationServer(ctx context.Context, client *http.Client, baseUR
 	if endpoint := strings.TrimSpace(cfg.RegistrationEndpoint); endpoint != "" {
 		metadata.RegistrationEndpoint = endpoint
 	}
-	if protectedResourceDiscovery {
-		metadata.protectedResourceURL = strings.TrimSpace(baseURL)
-		metadata.protectAuthorizationEndpoint = strings.TrimSpace(cfg.AuthorizationEndpoint) == ""
-		metadata.protectTokenEndpoint = strings.TrimSpace(cfg.TokenEndpoint) == ""
-		metadata.protectRegistrationEndpoint = strings.TrimSpace(cfg.RegistrationEndpoint) == ""
-	}
 
 	if strings.TrimSpace(metadata.AuthorizationEndpoint) == "" {
 		return authServerMetadata{}, errors.New("no authorization endpoint discovered or configured")
@@ -273,9 +205,6 @@ func resolveAuthorizationServer(ctx context.Context, client *http.Client, baseUR
 	if err := validateResolvedEndpoints(metadata); err != nil {
 		return authServerMetadata{}, err
 	}
-	if err := validateProtectedDiscoveredEndpoints(ctx, metadata); err != nil {
-		return authServerMetadata{}, err
-	}
 	return metadata, nil
 }
 
@@ -434,25 +363,10 @@ func Login(ctx context.Context, options LoginOptions) (StoredToken, error) {
 	}
 	defer listener.Close()
 	redirectURI := fmt.Sprintf("http://%s/callback", listener.Addr().String())
-	protectedEndpointClient := httpClient
-	if metadata.protectRegistrationEndpoint || metadata.protectTokenEndpoint {
-		protectedEndpointClient, err = newAdvertisedOAuthDiscoveryClient(httpClient, metadata.protectedResourceURL)
-		if err != nil {
-			return StoredToken{}, err
-		}
-	}
-	tokenClient := httpClient
-	if metadata.protectTokenEndpoint {
-		tokenClient = protectedEndpointClient
-	}
 
 	if strings.TrimSpace(cfg.ClientID) == "" {
 		if registration := strings.TrimSpace(metadata.RegistrationEndpoint); registration != "" {
-			registrationClient := httpClient
-			if metadata.protectRegistrationEndpoint {
-				registrationClient = protectedEndpointClient
-			}
-			clientID, clientSecret, regErr := registerClient(loginCtx, registrationClient, registration, redirectURI, cfg.Scopes)
+			clientID, clientSecret, regErr := registerClient(loginCtx, httpClient, registration, redirectURI, cfg.Scopes)
 			if regErr != nil {
 				return StoredToken{}, regErr
 			}
@@ -476,7 +390,7 @@ func Login(ctx context.Context, options LoginOptions) (StoredToken, error) {
 	}
 
 	flow := &authorizationFlow{
-		httpClient: tokenClient,
+		httpClient: httpClient,
 		metadata:   metadata,
 		config:     cfg,
 		pkce:       pkce,

internal/mcp/oauth_discovery_network.go

@@ -1,290 +0,0 @@
-package mcp
-
-import (
-	"context"
-	"crypto/tls"
-	"errors"
-	"fmt"
-	"net"
-	"net/http"
-	"net/netip"
-	"net/url"
-	"strings"
-)
-
-var errUnsafeOAuthDiscoveryTarget = errors.New("mcp oauth: refused non-public server-advertised discovery target")
-
-var nonPublicOAuthDiscoveryPrefixes = []netip.Prefix{
-	netip.MustParsePrefix("0.0.0.0/8"),
-	netip.MustParsePrefix("10.0.0.0/8"),
-	netip.MustParsePrefix("100.64.0.0/10"),
-	netip.MustParsePrefix("127.0.0.0/8"),
-	netip.MustParsePrefix("169.254.0.0/16"),
-	netip.MustParsePrefix("172.16.0.0/12"),
-	netip.MustParsePrefix("192.0.0.0/24"),
-	netip.MustParsePrefix("192.0.2.0/24"),
-	netip.MustParsePrefix("192.88.99.0/24"),
-	netip.MustParsePrefix("192.168.0.0/16"),
-	netip.MustParsePrefix("198.18.0.0/15"),
-	netip.MustParsePrefix("198.51.100.0/24"),
-	netip.MustParsePrefix("203.0.113.0/24"),
-	netip.MustParsePrefix("224.0.0.0/4"),
-	netip.MustParsePrefix("240.0.0.0/4"),
-	netip.MustParsePrefix("::/128"),
-	netip.MustParsePrefix("::1/128"),
-	netip.MustParsePrefix("100::/64"),
-	netip.MustParsePrefix("2001:2::/48"),
-	netip.MustParsePrefix("2001:db8::/32"),
-	netip.MustParsePrefix("fc00::/7"),
-	netip.MustParsePrefix("fe80::/10"),
-	netip.MustParsePrefix("ff00::/8"),
-}
-
-type oauthDiscoveryNetworkPolicy struct {
-	allowLoopback bool
-	lookupNetIP   func(context.Context, string, string) ([]netip.Addr, error)
-}
-
-type advertisedOAuthDiscoveryTransport struct {
-	base   http.RoundTripper
-	policy oauthDiscoveryNetworkPolicy
-}
-
-// newAdvertisedOAuthDiscoveryClient binds server-advertised discovery to the
-// public network. Loopback targets remain available only when the operator
-// explicitly configured a loopback MCP resource.
-func newAdvertisedOAuthDiscoveryClient(client *http.Client, resourceURL string) (*http.Client, error) {
-	policy, err := newOAuthDiscoveryNetworkPolicy(resourceURL)
-	if err != nil {
-		return nil, err
-	}
-	copied := withoutDiscoveryRedirects(client)
-	transport := copied.Transport
-	if transport == nil {
-		transport = http.DefaultTransport
-	}
-	copied.Transport = advertisedOAuthDiscoveryTransport{base: transport, policy: policy}
-	return copied, nil
-}
-
-func newOAuthDiscoveryNetworkPolicy(resourceURL string) (oauthDiscoveryNetworkPolicy, error) {
-	parsed, err := url.Parse(strings.TrimSpace(resourceURL))
-	if err != nil || parsed.Hostname() == "" {
-		return oauthDiscoveryNetworkPolicy{}, errors.New("mcp oauth: invalid MCP resource URL for discovery policy")
-	}
-	return oauthDiscoveryNetworkPolicy{allowLoopback: isExplicitOAuthLoopbackHost(parsed.Hostname())}, nil
-}
-
-func validateAdvertisedOAuthDiscoveryURL(resourceURL string, targetURL string) error {
-	policy, err := newOAuthDiscoveryNetworkPolicy(resourceURL)
-	if err != nil {
-		return err
-	}
-	parsed, err := url.Parse(targetURL)
-	if err != nil || parsed.Hostname() == "" {
-		return errUnsafeOAuthDiscoveryTarget
-	}
-	return policy.validateLiteralHost(parsed.Hostname())
-}
-
-func (transport advertisedOAuthDiscoveryTransport) RoundTrip(request *http.Request) (*http.Response, error) {
-	if request == nil || request.URL == nil {
-		return nil, errors.New("mcp oauth: discovery request has no URL")
-	}
-	if err := transport.policy.validateLiteralHost(request.URL.Hostname()); err != nil {
-		return nil, err
-	}
-
-	baseTransport, ok := transport.base.(*http.Transport)
-	if !ok {
-		return nil, errors.New("mcp oauth: cannot enforce discovery network policy with a custom HTTP transport")
-	}
-	addresses, err := transport.policy.resolve(request.Context(), request.URL.Hostname())
-	if err != nil {
-		return nil, err
-	}
-	var lastErr error
-	for index, address := range addresses {
-		attempt := request
-		if index > 0 && request.Body != nil {
-			if request.GetBody == nil {
-				break
-			}
-			body, bodyErr := request.GetBody()
-			if bodyErr != nil {
-				return nil, bodyErr
-			}
-			attempt = request.Clone(request.Context())
-			attempt.Body = body
-		}
-		response, roundTripErr := roundTripPinnedOAuthDiscovery(attempt, baseTransport, address)
-		if roundTripErr == nil {
-			return response, nil
-		}
-		lastErr = roundTripErr
-	}
-	if lastErr == nil {
-		lastErr = errUnsafeOAuthDiscoveryTarget
-	}
-	return nil, lastErr
-}
-
-func roundTripPinnedOAuthDiscovery(request *http.Request, base *http.Transport, address netip.Addr) (*http.Response, error) {
-	pinnedRequest := request.Clone(request.Context())
-	pinnedURL := *request.URL
-	originalHost := request.URL.Hostname()
-	port := request.URL.Port()
-	if port == "" {
-		switch strings.ToLower(request.URL.Scheme) {
-		case "http":
-			port = "80"
-		case "https":
-			port = "443"
-		default:
-			return nil, errUnsafeOAuthDiscoveryTarget
-		}
-	}
-	pinnedURL.Host = net.JoinHostPort(address.String(), port)
-	pinnedRequest.URL = &pinnedURL
-	if pinnedRequest.Host == "" {
-		pinnedRequest.Host = request.URL.Host
-	}
-
-	pinnedTransport := base.Clone()
-	pinnedTransport.DisableKeepAlives = true
-	var proxyURL *url.URL
-	if base.Proxy != nil {
-		var err error
-		proxyURL, err = base.Proxy(request)
-		if err != nil {
-			return nil, fmt.Errorf("mcp oauth: resolve discovery proxy: %w", err)
-		}
-		if proxyURL == nil {
-			pinnedTransport.Proxy = nil
-		} else {
-			pinnedTransport.Proxy = http.ProxyURL(proxyURL)
-		}
-	}
-	if pinnedTransport.TLSClientConfig == nil {
-		pinnedTransport.TLSClientConfig = &tls.Config{ServerName: originalHost} //nolint:gosec // standard verification remains enabled
-	} else {
-		pinnedTransport.TLSClientConfig = pinnedTransport.TLSClientConfig.Clone()
-		pinnedTransport.TLSClientConfig.ServerName = originalHost
-	}
-	// A custom TLS dialer must not resolve the advertised hostname again after
-	// the policy has pinned it. For an HTTPS proxy, however, that proxy remains
-	// the TLS first hop and the transport sends CONNECT to the pinned target.
-	dialContext := pinnedTransport.DialContext
-	if dialContext == nil {
-		dialContext = (&net.Dialer{}).DialContext
-	}
-	pinnedAddress := net.JoinHostPort(address.String(), port)
-	targetTLSConfig := pinnedTransport.TLSClientConfig
-	pinnedTransport.DialTLSContext = func(ctx context.Context, network string, address string) (net.Conn, error) {
-		if proxyURL != nil && strings.EqualFold(proxyURL.Scheme, "https") {
-			proxyTLSConfig := targetTLSConfig.Clone()
-			proxyTLSConfig.ServerName = proxyURL.Hostname()
-			return dialOAuthDiscoveryTLS(ctx, dialContext, network, address, proxyTLSConfig)
-		}
-		return dialOAuthDiscoveryTLS(ctx, dialContext, network, pinnedAddress, targetTLSConfig)
-	}
-	return pinnedTransport.RoundTrip(pinnedRequest)
-}
-
-func dialOAuthDiscoveryTLS(ctx context.Context, dialContext func(context.Context, string, string) (net.Conn, error), network string, address string, config *tls.Config) (net.Conn, error) {
-	connection, err := dialContext(ctx, network, address)
-	if err != nil {
-		return nil, err
-	}
-	tlsConnection := tls.Client(connection, config)
-	if err := tlsConnection.HandshakeContext(ctx); err != nil {
-		connection.Close()
-		return nil, err
-	}
-	return tlsConnection, nil
-}
-
-func (policy oauthDiscoveryNetworkPolicy) resolve(ctx context.Context, host string) ([]netip.Addr, error) {
-	if address, err := netip.ParseAddr(strings.Trim(host, "[]")); err == nil {
-		address = address.Unmap()
-		if err := policy.validateAddress(address); err != nil {
-			return nil, err
-		}
-		return []netip.Addr{address}, nil
-	}
-
-	lookupNetIP := policy.lookupNetIP
-	if lookupNetIP == nil {
-		lookupNetIP = net.DefaultResolver.LookupNetIP
-	}
-	addresses, err := lookupNetIP(ctx, "ip", host)
-	if err != nil {
-		return nil, errors.New("mcp oauth: resolve server-advertised discovery target failed")
-	}
-	if len(addresses) == 0 {
-		return nil, errors.New("mcp oauth: server-advertised discovery target resolved to no addresses")
-	}
-	explicitLoopback := isExplicitOAuthLoopbackHost(host)
-	resolved := make([]netip.Addr, 0, len(addresses))
-	for _, address := range addresses {
-		address = address.Unmap()
-		if explicitLoopback && !address.IsLoopback() {
-			return nil, errUnsafeOAuthDiscoveryTarget
-		}
-		if err := policy.validateAddress(address); err != nil {
-			return nil, err
-		}
-		resolved = append(resolved, address)
-	}
-	return resolved, nil
-}
-
-func (policy oauthDiscoveryNetworkPolicy) validateLiteralHost(host string) error {
-	normalized := strings.ToLower(strings.TrimSuffix(strings.Trim(host, "[]"), "."))
-	if normalized == "" {
-		return errUnsafeOAuthDiscoveryTarget
-	}
-	if isCloudMetadataHostname(normalized) {
-		return errUnsafeOAuthDiscoveryTarget
-	}
-	if isExplicitOAuthLoopbackHost(normalized) && !policy.allowLoopback {
-		return errUnsafeOAuthDiscoveryTarget
-	}
-	if address, err := netip.ParseAddr(normalized); err == nil {
-		return policy.validateAddress(address.Unmap())
-	}
-	return nil
-}
-
-func (policy oauthDiscoveryNetworkPolicy) validateAddress(address netip.Addr) error {
-	if policy.allowLoopback && address.IsLoopback() {
-		return nil
-	}
-	if !address.IsValid() || !address.IsGlobalUnicast() || address.IsPrivate() {
-		return errUnsafeOAuthDiscoveryTarget
-	}
-	for _, prefix := range nonPublicOAuthDiscoveryPrefixes {
-		if prefix.Contains(address) {
-			return errUnsafeOAuthDiscoveryTarget
-		}
-	}
-	return nil
-}
-
-func isExplicitOAuthLoopbackHost(host string) bool {
-	normalized := strings.ToLower(strings.TrimSuffix(strings.Trim(host, "[]"), "."))
-	if normalized == "localhost" || strings.HasSuffix(normalized, ".localhost") {
-		return true
-	}
-	address, err := netip.ParseAddr(normalized)
-	return err == nil && address.Unmap().IsLoopback()
-}
-
-func isCloudMetadataHostname(host string) bool {
-	switch strings.ToLower(strings.TrimSuffix(host, ".")) {
-	case "metadata", "metadata.google.internal", "metadata.azure.internal":
-		return true
-	default:
-		return false
-	}
-}

internal/mcp/oauth_discovery_network_test.go

@@ -1,180 +0,0 @@
-package mcp
-
-import (
-	"bufio"
-	"context"
-	"errors"
-	"io"
-	"net"
-	"net/http"
-	"net/netip"
-	"net/url"
-	"strings"
-	"sync/atomic"
-	"testing"
-)
-
-func TestOAuthDiscoveryNetworkPolicyRejectsNonPublicAddresses(t *testing.T) {
-	policy := oauthDiscoveryNetworkPolicy{}
-	for _, value := range []string{
-		"127.0.0.1",
-		"10.0.0.1",
-		"169.254.169.254",
-		"192.0.2.10",
-		"224.0.0.1",
-		"::1",
-		"fc00::1",
-		"fe80::1",
-		"2001:db8::1",
-	} {
-		t.Run(value, func(t *testing.T) {
-			if err := policy.validateAddress(netip.MustParseAddr(value)); err == nil {
-				t.Fatalf("address %s should be rejected", value)
-			}
-		})
-	}
-	for _, value := range []string{"8.8.8.8", "2606:4700:4700::1111"} {
-		if err := policy.validateAddress(netip.MustParseAddr(value)); err != nil {
-			t.Fatalf("public address %s rejected: %v", value, err)
-		}
-	}
-	loopbackPolicy := oauthDiscoveryNetworkPolicy{allowLoopback: true}
-	if err := loopbackPolicy.validateAddress(netip.MustParseAddr("127.0.0.1")); err != nil {
-		t.Fatalf("explicit loopback resource should allow loopback discovery: %v", err)
-	}
-	if err := loopbackPolicy.validateAddress(netip.MustParseAddr("10.0.0.1")); err == nil {
-		t.Fatal("loopback development must not permit arbitrary private targets")
-	}
-}
-
-func TestProtectedDiscoveryRejectsNonPublicOAuthEndpoints(t *testing.T) {
-	for _, endpoint := range []struct {
-		name     string
-		metadata authServerMetadata
-	}{
-		{
-			name: "authorization",
-			metadata: authServerMetadata{
-				AuthorizationEndpoint:        "http://127.0.0.1/authorize",
-				protectAuthorizationEndpoint: true,
-			},
-		},
-		{
-			name: "token",
-			metadata: authServerMetadata{
-				TokenEndpoint:        "https://10.0.0.1/token",
-				protectTokenEndpoint: true,
-			},
-		},
-		{
-			name: "registration",
-			metadata: authServerMetadata{
-				RegistrationEndpoint:        "https://169.254.169.254/register",
-				protectRegistrationEndpoint: true,
-			},
-		},
-	} {
-		t.Run(endpoint.name, func(t *testing.T) {
-			endpoint.metadata.protectedResourceURL = "https://mcp.example/mcp"
-			if err := validateProtectedDiscoveredEndpoints(context.Background(), endpoint.metadata); err == nil {
-				t.Fatalf("protected %s endpoint should be rejected", endpoint.name)
-			}
-		})
-	}
-}
-
-func TestAdvertisedOAuthDiscoveryRejectsHostnameResolvingPrivateAtUseTime(t *testing.T) {
-	var dialed atomic.Bool
-	policy := oauthDiscoveryNetworkPolicy{
-		lookupNetIP: func(context.Context, string, string) ([]netip.Addr, error) {
-			return []netip.Addr{netip.MustParseAddr("10.0.0.12")}, nil
-		},
-	}
-	client := &http.Client{Transport: advertisedOAuthDiscoveryTransport{
-		base: &http.Transport{DialContext: func(context.Context, string, string) (net.Conn, error) {
-			dialed.Store(true)
-			return nil, io.EOF
-		}},
-		policy: policy,
-	}}
-
-	_, err := client.Get("https://auth.example/.well-known/oauth-authorization-server")
-	if err == nil || !strings.Contains(err.Error(), errUnsafeOAuthDiscoveryTarget.Error()) {
-		t.Fatalf("error = %v, want private-resolution rejection", err)
-	}
-	if dialed.Load() {
-		t.Fatal("private resolved address reached the dialer")
-	}
-}
-
-func TestAdvertisedOAuthDiscoveryPinsResolvedAddress(t *testing.T) {
-	const publicAddress = "93.184.216.34"
-	var dialedAddress string
-	policy := oauthDiscoveryNetworkPolicy{
-		lookupNetIP: func(context.Context, string, string) ([]netip.Addr, error) {
-			return []netip.Addr{netip.MustParseAddr(publicAddress)}, nil
-		},
-	}
-	baseTransport := &http.Transport{DialContext: func(_ context.Context, _, address string) (net.Conn, error) {
-		dialedAddress = address
-		clientConn, serverConn := net.Pipe()
-		go func() {
-			defer serverConn.Close()
-			reader := bufio.NewReader(serverConn)
-			for {
-				line, err := reader.ReadString('\n')
-				if err != nil || line == "\r\n" {
-					break
-				}
-			}
-			_, _ = io.WriteString(serverConn, "HTTP/1.1 200 OK\r\nContent-Length: 2\r\nConnection: close\r\n\r\n{}")
-		}()
-		return clientConn, nil
-	}}
-	client := &http.Client{Transport: advertisedOAuthDiscoveryTransport{base: baseTransport, policy: policy}}
-
-	response, err := client.Get("http://auth.example/metadata")
-	if err != nil {
-		t.Fatalf("GET pinned discovery target: %v", err)
-	}
-	response.Body.Close()
-	if dialedAddress != net.JoinHostPort(publicAddress, "80") {
-		t.Fatalf("dialed %q, want resolved address", dialedAddress)
-	}
-}
-
-func TestPinnedOAuthDiscoveryPreservesHTTPSProxyFirstHop(t *testing.T) {
-	for _, test := range []struct {
-		name     string
-		proxy    string
-		firstHop string
-	}{
-		{name: "HTTP", proxy: "http://proxy.example:8080", firstHop: "proxy.example:8080"},
-		{name: "HTTPS", proxy: "https://proxy.example:8443", firstHop: "proxy.example:8443"},
-		{name: "SOCKS", proxy: "socks5://proxy.example:1080", firstHop: "proxy.example:1080"},
-	} {
-		t.Run(test.name, func(t *testing.T) {
-			proxyURL, err := url.Parse(test.proxy)
-			if err != nil {
-				t.Fatalf("parse proxy URL: %v", err)
-			}
-			var dialedAddress string
-			baseTransport := &http.Transport{
-				Proxy: http.ProxyURL(proxyURL),
-				DialContext: func(_ context.Context, _, address string) (net.Conn, error) {
-					dialedAddress = address
-					return nil, errors.New("stop after observing first hop")
-				},
-			}
-			request, err := http.NewRequestWithContext(context.Background(), http.MethodGet, "https://auth.example/metadata", nil)
-			if err != nil {
-				t.Fatalf("create request: %v", err)
-			}
-
-			_, _ = roundTripPinnedOAuthDiscovery(request, baseTransport, netip.MustParseAddr("93.184.216.34"))
-			if dialedAddress != test.firstHop {
-				t.Fatalf("dialed %q, want %s proxy first hop", dialedAddress, test.name)
-			}
-		})
-	}
-}

internal/mcp/oauth_protected_resource.go

@@ -1,233 +0,0 @@
-package mcp
-
-import (
-	"context"
-	"encoding/json"
-	"errors"
-	"fmt"
-	"io"
-	"net/http"
-	"net/url"
-	"strings"
-
-	"github.com/Gitlawb/zero/internal/oauth"
-)
-
-const protectedResourceMetadataLimit = 1 << 20
-
-type protectedResourceMetadata struct {
-	Resource             string   `json:"resource"`
-	AuthorizationServers []string `json:"authorization_servers"`
-}
-
-// withoutDiscoveryRedirects returns a shallow client copy that exposes 3xx
-// responses to the caller. Every discovered URL is validated before use, so a
-// redirect must never replace that validated target with an unchecked one.
-func withoutDiscoveryRedirects(client *http.Client) *http.Client {
-	if client == nil {
-		client = http.DefaultClient
-	}
-	copied := *client
-	// Discovery requests are deliberately unauthenticated. A caller-supplied
-	// jar must not turn a plain metadata GET into a credential-bearing request.
-	copied.Jar = nil
-	copied.CheckRedirect = func(*http.Request, []*http.Request) error {
-		return http.ErrUseLastResponse
-	}
-	return &copied
-}
-
-// discoverProtectedResourceAuthorizationServer follows the RFC 9728 URL
-// advertised by a protected MCP resource. found is false when the endpoint does
-// not advertise protected-resource metadata, allowing legacy direct discovery.
-func discoverProtectedResourceAuthorizationServer(ctx context.Context, client *http.Client, resourceURL string) (issuer string, found bool, err error) {
-	resourceURL = strings.TrimSpace(resourceURL)
-	client = withoutDiscoveryRedirects(client)
-	metadataURL, found, err := probeProtectedResourceMetadataURL(ctx, client, resourceURL)
-	if err != nil || !found {
-		return "", found, err
-	}
-	if err := validateResourceMetadataOrigin(resourceURL, metadataURL); err != nil {
-		return "", true, err
-	}
-	client, err = newAdvertisedOAuthDiscoveryClient(client, resourceURL)
-	if err != nil {
-		return "", true, err
-	}
-	metadata, err := fetchProtectedResourceMetadata(ctx, client, metadataURL)
-	if err != nil {
-		return "", true, err
-	}
-	if metadata.Resource != resourceURL {
-		return "", true, errors.New("mcp oauth: protected resource metadata resource does not match the MCP server URL")
-	}
-	if len(metadata.AuthorizationServers) == 0 {
-		return "", true, errors.New("mcp oauth: protected resource metadata has no authorization_servers")
-	}
-	issuer = metadata.AuthorizationServers[0]
-	if strings.TrimSpace(issuer) == "" {
-		return "", true, errors.New("mcp oauth: protected resource metadata has an empty authorization server")
-	}
-	if issuer != strings.TrimSpace(issuer) {
-		return "", true, errors.New("mcp oauth: protected resource authorization server must not contain surrounding whitespace")
-	}
-	if err := oauth.ValidateEndpointURL(issuer); err != nil {
-		return "", true, fmt.Errorf("mcp oauth: protected resource authorization server: %w", err)
-	}
-	if err := validateAdvertisedOAuthDiscoveryURL(resourceURL, issuer); err != nil {
-		return "", true, err
-	}
-	return issuer, true, nil
-}
-
-func validateResourceMetadataOrigin(resourceURL string, metadataURL string) error {
-	resource, resourceErr := url.Parse(resourceURL)
-	metadata, metadataErr := url.Parse(metadataURL)
-	if resourceErr != nil || metadataErr != nil || !sameMCPOrigin(resource, metadata) {
-		return errors.New("mcp oauth: protected resource metadata URL must be same-origin with the MCP server URL")
-	}
-	return nil
-}
-
-func probeProtectedResourceMetadataURL(ctx context.Context, client *http.Client, resourceURL string) (string, bool, error) {
-	if client == nil {
-		client = http.DefaultClient
-	}
-	request, err := http.NewRequestWithContext(ctx, http.MethodGet, strings.TrimSpace(resourceURL), nil)
-	if err != nil {
-		return "", false, errors.New("mcp oauth: invalid MCP resource URL")
-	}
-	request.Header.Set("Accept", "application/json, text/event-stream")
-	request.Header.Set("MCP-Protocol-Version", defaultProtocolVersion)
-	response, err := client.Do(request)
-	if err != nil {
-		// A resource that cannot be probed may still support the legacy direct
-		// authorization-server discovery flow.
-		return "", false, nil
-	}
-	defer response.Body.Close()
-	if response.StatusCode != http.StatusUnauthorized {
-		return "", false, nil
-	}
-	metadataURL, found, err := parseResourceMetadataURL(response.Header.Values("WWW-Authenticate"))
-	if err != nil {
-		return "", false, fmt.Errorf("mcp oauth: invalid WWW-Authenticate resource_metadata parameter: %w", err)
-	}
-	if !found {
-		return "", false, nil
-	}
-	if err := oauth.ValidateEndpointURL(metadataURL); err != nil {
-		return "", false, fmt.Errorf("mcp oauth: protected resource metadata URL: %w", err)
-	}
-	return metadataURL, true, nil
-}
-
-func fetchProtectedResourceMetadata(ctx context.Context, client *http.Client, metadataURL string) (protectedResourceMetadata, error) {
-	if client == nil {
-		client = http.DefaultClient
-	}
-	request, err := http.NewRequestWithContext(ctx, http.MethodGet, metadataURL, nil)
-	if err != nil {
-		return protectedResourceMetadata{}, errors.New("mcp oauth: invalid protected resource metadata URL")
-	}
-	request.Header.Set("Accept", "application/json")
-	response, err := client.Do(request)
-	if err != nil {
-		return protectedResourceMetadata{}, errors.New("mcp oauth: fetch protected resource metadata failed")
-	}
-	defer response.Body.Close()
-	if response.StatusCode < http.StatusOK || response.StatusCode >= http.StatusMultipleChoices {
-		return protectedResourceMetadata{}, fmt.Errorf("mcp oauth: protected resource metadata returned HTTP %d", response.StatusCode)
-	}
-	var metadata protectedResourceMetadata
-	if err := json.NewDecoder(io.LimitReader(response.Body, protectedResourceMetadataLimit)).Decode(&metadata); err != nil {
-		return protectedResourceMetadata{}, errors.New("mcp oauth: decode protected resource metadata failed")
-	}
-	return metadata, nil
-}
-
-func parseResourceMetadataURL(headerValues []string) (string, bool, error) {
-	var selected string
-	for _, headerValue := range headerValues {
-		for index := 0; index < len(headerValue); {
-			if headerValue[index] == '"' {
-				_, next, err := readAuthQuotedString(headerValue, index)
-				if err != nil {
-					// Malformed parameters for another authentication scheme do
-					// not suppress a valid challenge in a separate header value.
-					break
-				}
-				index = next
-				continue
-			}
-			if !isAuthTokenByte(headerValue[index]) {
-				index++
-				continue
-			}
-			start := index
-			for index < len(headerValue) && isAuthTokenByte(headerValue[index]) {
-				index++
-			}
-			name := headerValue[start:index]
-			for index < len(headerValue) && (headerValue[index] == ' ' || headerValue[index] == '\t') {
-				index++
-			}
-			if index >= len(headerValue) || headerValue[index] != '=' {
-				continue
-			}
-			index++
-			for index < len(headerValue) && (headerValue[index] == ' ' || headerValue[index] == '\t') {
-				index++
-			}
-			if !strings.EqualFold(name, "resource_metadata") {
-				continue
-			}
-			if index >= len(headerValue) || headerValue[index] != '"' {
-				return "", false, errors.New("resource_metadata must be a quoted URL")
-			}
-			value, next, err := readAuthQuotedString(headerValue, index)
-			if err != nil {
-				return "", false, err
-			}
-			value = strings.TrimSpace(value)
-			if value == "" {
-				return "", false, errors.New("resource_metadata URL is empty")
-			}
-			if selected != "" && selected != value {
-				return "", false, errors.New("conflicting resource_metadata URLs")
-			}
-			selected = value
-			index = next
-		}
-	}
-	return selected, selected != "", nil
-}
-
-func readAuthQuotedString(value string, quote int) (string, int, error) {
-	var decoded strings.Builder
-	for index := quote + 1; index < len(value); index++ {
-		switch value[index] {
-		case '"':
-			return decoded.String(), index + 1, nil
-		case '\\':
-			index++
-			if index >= len(value) {
-				return "", 0, errors.New("unterminated quoted resource_metadata URL")
-			}
-			decoded.WriteByte(value[index])
-		default:
-			if value[index] < 0x20 || value[index] == 0x7f {
-				return "", 0, errors.New("resource_metadata URL contains a control character")
-			}
-			decoded.WriteByte(value[index])
-		}
-	}
-	return "", 0, errors.New("unterminated quoted resource_metadata URL")
-}
-
-func isAuthTokenByte(value byte) bool {
-	if value >= 'a' && value <= 'z' || value >= 'A' && value <= 'Z' || value >= '0' && value <= '9' {
-		return true
-	}
-	return strings.ContainsRune("!#$%&'*+-.^_`|~", rune(value))
-}

internal/mcp/oauth_protected_resource_test.go

@@ -1,742 +0,0 @@
-package mcp
-
-import (
-	"context"
-	"encoding/json"
-	"errors"
-	"fmt"
-	"io"
-	"net"
-	"net/http"
-	"net/http/cookiejar"
-	"net/http/httptest"
-	"net/url"
-	"strings"
-	"sync/atomic"
-	"testing"
-	"time"
-)
-
-func TestParseResourceMetadataURL(t *testing.T) {
-	got, found, err := parseResourceMetadataURL([]string{
-		`Basic realm="resource_metadata=not-a-parameter"`,
-		`Bearer realm="OAuth", scope="read", Resource_Metadata="https://mcp.example/resource-metadata"`,
-	})
-	if err != nil || !found {
-		t.Fatalf("parseResourceMetadataURL() found=%v err=%v", found, err)
-	}
-	if got != "https://mcp.example/resource-metadata" {
-		t.Fatalf("resource metadata URL = %q", got)
-	}
-
-	got, found, err = parseResourceMetadataURL([]string{
-		`Basic realm="unterminated`,
-		`Bearer resource_metadata="https://mcp.example/fallback-metadata"`,
-	})
-	if err != nil || !found || got != "https://mcp.example/fallback-metadata" {
-		t.Fatalf("unrelated malformed challenge blocked discovery: got=%q found=%v err=%v", got, found, err)
-	}
-
-	for name, headers := range map[string][]string{
-		"unquoted":     {`Bearer resource_metadata=https://mcp.example/metadata`},
-		"unterminated": {`Bearer resource_metadata="https://mcp.example/metadata`},
-		"conflicting": {
-			`Bearer resource_metadata="https://mcp.example/one"`,
-			`DPoP resource_metadata="https://mcp.example/two"`,
-		},
-	} {
-		t.Run(name, func(t *testing.T) {
-			if _, _, err := parseResourceMetadataURL(headers); err == nil {
-				t.Fatal("expected malformed resource_metadata rejection")
-			}
-		})
-	}
-}
-
-func TestProtectedResourceDiscoveryRejectsInvalidMetadata(t *testing.T) {
-	for _, test := range []struct {
-		name      string
-		challenge func(base string) string
-		metadata  func(base string) string
-		wantError string
-	}{
-		{
-			name:      "malformed challenge",
-			challenge: func(string) string { return `Bearer resource_metadata="unterminated` },
-			wantError: "WWW-Authenticate",
-		},
-		{
-			name:      "insecure metadata URL",
-			challenge: func(string) string { return `Bearer resource_metadata="http://metadata.example/resource"` },
-			wantError: "metadata URL",
-		},
-		{
-			name:      "invalid JSON",
-			challenge: func(base string) string { return `Bearer resource_metadata="` + base + `/metadata"` },
-			metadata:  func(string) string { return `{` },
-			wantError: "decode protected resource metadata",
-		},
-		{
-			name:      "resource mismatch",
-			challenge: func(base string) string { return `Bearer resource_metadata="` + base + `/metadata"` },
-			metadata: func(base string) string {
-				return `{"resource":"` + base + `/other","authorization_servers":["https://auth.example"]}`
-			},
-			wantError: "does not match",
-		},
-		{
-			name:      "resource leading whitespace mismatch",
-			challenge: func(base string) string { return `Bearer resource_metadata="` + base + `/metadata"` },
-			metadata: func(base string) string {
-				return `{"resource":" ` + base + `/mcp","authorization_servers":["https://auth.example"]}`
-			},
-			wantError: "does not match",
-		},
-		{
-			name:      "resource trailing whitespace mismatch",
-			challenge: func(base string) string { return `Bearer resource_metadata="` + base + `/metadata"` },
-			metadata: func(base string) string {
-				return `{"resource":"` + base + `/mcp ","authorization_servers":["https://auth.example"]}`
-			},
-			wantError: "does not match",
-		},
-		{
-			name:      "authorization servers missing",
-			challenge: func(base string) string { return `Bearer resource_metadata="` + base + `/metadata"` },
-			metadata: func(base string) string {
-				return `{"resource":"` + base + `/mcp"}`
-			},
-			wantError: "authorization_servers",
-		},
-		{
-			name:      "insecure authorization server",
-			challenge: func(base string) string { return `Bearer resource_metadata="` + base + `/metadata"` },
-			metadata: func(base string) string {
-				return `{"resource":"` + base + `/mcp","authorization_servers":["http://auth.example"]}`
-			},
-			wantError: "authorization server",
-		},
-	} {
-		t.Run(test.name, func(t *testing.T) {
-			server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
-				base := "http://" + r.Host
-				switch r.URL.Path {
-				case "/mcp":
-					w.Header().Set("WWW-Authenticate", test.challenge(base))
-					w.WriteHeader(http.StatusUnauthorized)
-				case "/metadata":
-					if test.metadata == nil {
-						http.NotFound(w, r)
-						return
-					}
-					_, _ = w.Write([]byte(test.metadata(base)))
-				default:
-					http.NotFound(w, r)
-				}
-			}))
-			defer server.Close()
-
-			_, _, err := discoverProtectedResourceAuthorizationServer(context.Background(), server.Client(), server.URL+"/mcp")
-			if err == nil || !strings.Contains(err.Error(), test.wantError) {
-				t.Fatalf("error = %v, want %q", err, test.wantError)
-			}
-		})
-	}
-}
-
-func TestProtectedResourceProbeSendsNoCredentials(t *testing.T) {
-	var authorization, cookie string
-	server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
-		authorization = r.Header.Get("Authorization")
-		cookie = r.Header.Get("Cookie")
-		w.WriteHeader(http.StatusNotFound)
-	}))
-	defer server.Close()
-	jar, err := cookiejar.New(nil)
-	if err != nil {
-		t.Fatalf("create cookie jar: %v", err)
-	}
-	serverURL, err := url.Parse(server.URL)
-	if err != nil {
-		t.Fatalf("parse server URL: %v", err)
-	}
-	jar.SetCookies(serverURL, []*http.Cookie{{Name: "session", Value: "secret"}})
-	client := server.Client()
-	client.Jar = jar
-
-	_, found, err := discoverProtectedResourceAuthorizationServer(context.Background(), client, server.URL+"/mcp")
-	if err != nil || found {
-		t.Fatalf("discovery found=%v err=%v", found, err)
-	}
-	if authorization != "" || cookie != "" {
-		t.Fatalf("probe sent credentials: authorization=%q cookie=%q", authorization, cookie)
-	}
-}
-
-func TestDirectAuthorizationServerDiscoverySendsNoCookies(t *testing.T) {
-	var cookie string
-	server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
-		cookie = r.Header.Get("Cookie")
-		base := "http://" + r.Host
-		_ = json.NewEncoder(w).Encode(map[string]any{
-			"issuer":                 base,
-			"authorization_endpoint": base + "/authorize",
-			"token_endpoint":         base + "/token",
-		})
-	}))
-	defer server.Close()
-	jar, err := cookiejar.New(nil)
-	if err != nil {
-		t.Fatalf("create cookie jar: %v", err)
-	}
-	serverURL, err := url.Parse(server.URL)
-	if err != nil {
-		t.Fatalf("parse server URL: %v", err)
-	}
-	jar.SetCookies(serverURL, []*http.Cookie{{Name: "session", Value: "secret"}})
-	client := server.Client()
-	client.Jar = jar
-
-	if _, err := resolveAuthorizationServer(context.Background(), client, server.URL, OAuthConfig{}); err != nil {
-		t.Fatalf("resolveAuthorizationServer() error = %v", err)
-	}
-	if cookie != "" {
-		t.Fatalf("direct discovery sent cookie %q", cookie)
-	}
-}
-
-func TestProtectedResourceDiscoveryRejectsAdvertisedLoopbackMetadata(t *testing.T) {
-	var metadataHits atomic.Int64
-	client := &http.Client{Transport: roundTripperFunc(func(request *http.Request) (*http.Response, error) {
-		response := &http.Response{
-			StatusCode: http.StatusOK,
-			Header:     make(http.Header),
-			Body:       io.NopCloser(strings.NewReader("")),
-			Request:    request,
-		}
-		switch request.URL.String() {
-		case "https://mcp.example/mcp":
-			response.StatusCode = http.StatusUnauthorized
-			response.Header.Set("WWW-Authenticate", `Bearer resource_metadata="http://127.0.0.1/metadata"`)
-		case "http://127.0.0.1/metadata":
-			metadataHits.Add(1)
-			response.Body = io.NopCloser(strings.NewReader(`{"resource":"https://mcp.example/mcp","authorization_servers":["https://auth.example"]}`))
-		default:
-			response.StatusCode = http.StatusNotFound
-		}
-		return response, nil
-	})}
-
-	_, _, err := discoverProtectedResourceAuthorizationServer(context.Background(), client, "https://mcp.example/mcp")
-	if err == nil {
-		t.Fatal("advertised loopback metadata URL should be rejected")
-	}
-	if metadataHits.Load() != 0 {
-		t.Fatalf("loopback metadata target was fetched %d time(s)", metadataHits.Load())
-	}
-}
-
-func TestProtectedResourceDiscoveryRejectsAdvertisedLoopbackIssuer(t *testing.T) {
-	var issuerHits atomic.Int64
-	client := &http.Client{Transport: roundTripperFunc(func(request *http.Request) (*http.Response, error) {
-		response := &http.Response{
-			StatusCode: http.StatusOK,
-			Header:     make(http.Header),
-			Body:       io.NopCloser(strings.NewReader("")),
-			Request:    request,
-		}
-		switch request.URL.String() {
-		case "https://mcp.example/mcp":
-			response.StatusCode = http.StatusUnauthorized
-			response.Header.Set("WWW-Authenticate", `Bearer resource_metadata="https://mcp.example/metadata"`)
-		case "https://mcp.example/metadata":
-			response.Body = io.NopCloser(strings.NewReader(`{"resource":"https://mcp.example/mcp","authorization_servers":["http://127.0.0.1"]}`))
-		case "http://127.0.0.1/.well-known/oauth-authorization-server":
-			issuerHits.Add(1)
-			response.Body = io.NopCloser(strings.NewReader(`{"issuer":"http://127.0.0.1","authorization_endpoint":"http://127.0.0.1/authorize","token_endpoint":"http://127.0.0.1/token"}`))
-		default:
-			response.StatusCode = http.StatusNotFound
-		}
-		return response, nil
-	})}
-
-	_, err := resolveAuthorizationServer(context.Background(), client, "https://mcp.example/mcp", OAuthConfig{})
-	if err == nil {
-		t.Fatal("advertised loopback issuer should be rejected")
-	}
-	if issuerHits.Load() != 0 {
-		t.Fatalf("loopback issuer target was fetched %d time(s)", issuerHits.Load())
-	}
-}
-
-func TestProtectedResourceDiscoveryRejectsAdvertisedPrivateTargets(t *testing.T) {
-	for _, target := range []string{
-		"http://10.0.0.8/metadata",
-		"https://169.254.169.254/metadata",
-		"https://metadata.google.internal/metadata",
-	} {
-		t.Run(target, func(t *testing.T) {
-			if err := validateAdvertisedOAuthDiscoveryURL("https://mcp.example/mcp", target); err == nil {
-				t.Fatalf("advertised target %q should be rejected", target)
-			}
-		})
-	}
-}
-
-func TestProtectedDiscoveryPathsSendNoCookies(t *testing.T) {
-	var probeCookie, resourceCookie, issuerCookie string
-	server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
-		base := "http://" + r.Host
-		switch r.URL.Path {
-		case "/mcp":
-			probeCookie = r.Header.Get("Cookie")
-			w.Header().Set("WWW-Authenticate", `Bearer resource_metadata="`+base+`/metadata"`)
-			w.WriteHeader(http.StatusUnauthorized)
-		case "/metadata":
-			resourceCookie = r.Header.Get("Cookie")
-			_ = json.NewEncoder(w).Encode(map[string]any{
-				"resource":              base + "/mcp",
-				"authorization_servers": []string{base},
-			})
-		case "/.well-known/oauth-authorization-server":
-			issuerCookie = r.Header.Get("Cookie")
-			_ = json.NewEncoder(w).Encode(map[string]any{
-				"issuer":                 base,
-				"authorization_endpoint": base + "/authorize",
-				"token_endpoint":         base + "/token",
-			})
-		default:
-			http.NotFound(w, r)
-		}
-	}))
-	defer server.Close()
-	jar, err := cookiejar.New(nil)
-	if err != nil {
-		t.Fatalf("create cookie jar: %v", err)
-	}
-	serverURL, err := url.Parse(server.URL)
-	if err != nil {
-		t.Fatalf("parse server URL: %v", err)
-	}
-	jar.SetCookies(serverURL, []*http.Cookie{{Name: "session", Value: "secret"}})
-	client := server.Client()
-	client.Jar = jar
-
-	if _, err := resolveAuthorizationServer(context.Background(), client, server.URL+"/mcp", OAuthConfig{}); err != nil {
-		t.Fatalf("resolveAuthorizationServer() error = %v", err)
-	}
-	if probeCookie != "" || resourceCookie != "" || issuerCookie != "" {
-		t.Fatalf("discovery sent cookies: probe=%q resource=%q issuer=%q", probeCookie, resourceCookie, issuerCookie)
-	}
-}
-
-func TestProtectedDiscoveryPreservesExplicitEndpointOverride(t *testing.T) {
-	fixture := newPublicProtectedOAuthFixture(t, "", "https://93.184.216.35/token", "", "")
-	explicitToken := "http://127.0.0.1:19432/token"
-	metadata, err := resolveAuthorizationServer(context.Background(), fixture.client, fixture.resourceURL, OAuthConfig{TokenEndpoint: explicitToken})
-	if err != nil {
-		t.Fatalf("resolve with explicit endpoint override: %v", err)
-	}
-	if metadata.TokenEndpoint != explicitToken || metadata.protectTokenEndpoint {
-		t.Fatalf("explicit token override lost provenance: endpoint=%q protected=%v", metadata.TokenEndpoint, metadata.protectTokenEndpoint)
-	}
-}
-
-func TestProtectedDiscoveryRejectsLoopbackRegistrationEndpointBeforeUse(t *testing.T) {
-	var registrationHits atomic.Int64
-	registration := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, _ *http.Request) {
-		registrationHits.Add(1)
-		_ = json.NewEncoder(w).Encode(map[string]any{"client_id": "registered-client"})
-	}))
-	defer registration.Close()
-	fixture := newPublicProtectedOAuthFixture(t, registration.URL+"/register", "https://93.184.216.35/token", "", "")
-
-	_, err := Login(context.Background(), LoginOptions{
-		ServerName: "registration-ssrf",
-		ServerURL:  fixture.resourceURL,
-		HTTPClient: fixture.client,
-		OpenBrowser: func(string) error {
-			return errors.New("authorization browser should not open")
-		},
-		Timeout: 5 * time.Second,
-	})
-	if err == nil {
-		t.Fatal("protected discovery should reject a loopback registration endpoint")
-	}
-	if registrationHits.Load() != 0 {
-		t.Fatalf("loopback registration endpoint received %d request(s)", registrationHits.Load())
-	}
-}
-
-func TestProtectedDiscoveryRejectsLoopbackTokenEndpointBeforeUse(t *testing.T) {
-	var tokenHits atomic.Int64
-	tokenServer := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, _ *http.Request) {
-		tokenHits.Add(1)
-		_ = json.NewEncoder(w).Encode(map[string]any{
-			"access_token": "unexpected",
-			"token_type":   "Bearer",
-		})
-	}))
-	defer tokenServer.Close()
-	fixture := newPublicProtectedOAuthFixture(t, "", tokenServer.URL+"/token", "", "")
-
-	_, err := Login(context.Background(), LoginOptions{
-		ServerName: "token-ssrf",
-		ServerURL:  fixture.resourceURL,
-		Config:     OAuthConfig{ClientID: "configured-client"},
-		HTTPClient: fixture.client,
-		OpenBrowser: func(authURL string) error {
-			parsed, parseErr := url.Parse(authURL)
-			if parseErr != nil {
-				return parseErr
-			}
-			callbackURL := parsed.Query().Get("redirect_uri") + "?code=code&state=" + url.QueryEscape(parsed.Query().Get("state"))
-			go func() {
-				for attempt := 0; attempt < 20; attempt++ {
-					response, requestErr := http.Get(callbackURL)
-					if requestErr == nil {
-						response.Body.Close()
-						return
-					}
-					time.Sleep(25 * time.Millisecond)
-				}
-			}()
-			return nil
-		},
-		Timeout: 5 * time.Second,
-	})
-	if err == nil {
-		t.Fatal("protected discovery should reject a loopback token endpoint")
-	}
-	if tokenHits.Load() != 0 {
-		t.Fatalf("loopback token endpoint received %d request(s)", tokenHits.Load())
-	}
-}
-
-func TestProtectedDiscoveryRegistrationRefusesPublicToPrivateRedirect(t *testing.T) {
-	var victimHits atomic.Int64
-	victim := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, _ *http.Request) {
-		victimHits.Add(1)
-		_ = json.NewEncoder(w).Encode(map[string]any{"client_id": "redirected-client"})
-	}))
-	defer victim.Close()
-	fixture := newPublicProtectedOAuthFixture(t, "", "https://93.184.216.35/token", victim.URL+"/register", "")
-
-	_, err := Login(context.Background(), LoginOptions{
-		ServerName: "registration-redirect",
-		ServerURL:  fixture.resourceURL,
-		HTTPClient: fixture.client,
-		OpenBrowser: func(string) error {
-			return errors.New("authorization browser should not open")
-		},
-		Timeout: 5 * time.Second,
-	})
-	if err == nil {
-		t.Fatal("protected registration redirect should be refused")
-	}
-	if victimHits.Load() != 0 {
-		t.Fatalf("registration redirect reached private victim %d time(s)", victimHits.Load())
-	}
-}
-
-func TestProtectedDiscoveryTokenRefusesPublicToPrivateRedirect(t *testing.T) {
-	var victimHits atomic.Int64
-	victim := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, _ *http.Request) {
-		victimHits.Add(1)
-		_ = json.NewEncoder(w).Encode(map[string]any{"access_token": "redirected-token", "token_type": "Bearer"})
-	}))
-	defer victim.Close()
-	fixture := newPublicProtectedOAuthFixture(t, "", "", "", victim.URL+"/token")
-
-	_, err := Login(context.Background(), LoginOptions{
-		ServerName: "token-redirect",
-		ServerURL:  fixture.resourceURL,
-		Config:     OAuthConfig{ClientID: "configured-client"},
-		HTTPClient: fixture.client,
-		OpenBrowser: func(authURL string) error {
-			parsed, parseErr := url.Parse(authURL)
-			if parseErr != nil {
-				return parseErr
-			}
-			callbackURL := parsed.Query().Get("redirect_uri") + "?code=code&state=" + url.QueryEscape(parsed.Query().Get("state"))
-			go func() {
-				for attempt := 0; attempt < 20; attempt++ {
-					response, requestErr := http.Get(callbackURL)
-					if requestErr == nil {
-						response.Body.Close()
-						return
-					}
-					time.Sleep(25 * time.Millisecond)
-				}
-			}()
-			return nil
-		},
-		Timeout: 5 * time.Second,
-	})
-	if err == nil {
-		t.Fatal("protected token redirect should be refused")
-	}
-	if victimHits.Load() != 0 {
-		t.Fatalf("token redirect reached private victim %d time(s)", victimHits.Load())
-	}
-}
-
-type publicProtectedOAuthFixture struct {
-	client      *http.Client
-	resourceURL string
-}
-
-func newPublicProtectedOAuthFixture(t *testing.T, registrationEndpoint string, tokenEndpoint string, registrationRedirect string, tokenRedirect string) publicProtectedOAuthFixture {
-	t.Helper()
-	var resourceOrigin, issuerOrigin string
-	gateway := httptest.NewTLSServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
-		resourceHost := strings.TrimPrefix(resourceOrigin, "https://")
-		issuerHost := strings.TrimPrefix(issuerOrigin, "https://")
-		switch {
-		case r.Host == resourceHost && r.URL.Path == "/mcp":
-			w.Header().Set("WWW-Authenticate", `Bearer resource_metadata="`+resourceOrigin+`/metadata"`)
-			w.WriteHeader(http.StatusUnauthorized)
-		case r.Host == resourceHost && r.URL.Path == "/metadata":
-			_ = json.NewEncoder(w).Encode(map[string]any{
-				"resource":              resourceOrigin + "/mcp",
-				"authorization_servers": []string{issuerOrigin},
-			})
-		case r.Host == issuerHost && r.URL.Path == "/.well-known/oauth-authorization-server":
-			metadataRegistration := registrationEndpoint
-			metadataToken := tokenEndpoint
-			if registrationRedirect != "" {
-				metadataRegistration = issuerOrigin + "/register"
-			}
-			if tokenRedirect != "" {
-				metadataToken = issuerOrigin + "/token"
-			}
-			_ = json.NewEncoder(w).Encode(map[string]any{
-				"issuer":                 issuerOrigin,
-				"authorization_endpoint": issuerOrigin + "/authorize",
-				"token_endpoint":         metadataToken,
-				"registration_endpoint":  metadataRegistration,
-			})
-		case r.Host == issuerHost && r.URL.Path == "/register" && registrationRedirect != "":
-			http.Redirect(w, r, registrationRedirect, http.StatusTemporaryRedirect)
-		case r.Host == issuerHost && r.URL.Path == "/token" && tokenRedirect != "":
-			http.Redirect(w, r, tokenRedirect, http.StatusTemporaryRedirect)
-		default:
-			http.NotFound(w, r)
-		}
-	}))
-	t.Cleanup(gateway.Close)
-	port := gateway.Listener.Addr().(*net.TCPAddr).Port
-	resourceOrigin = fmt.Sprintf("https://93.184.216.34:%d", port)
-	issuerOrigin = fmt.Sprintf("https://93.184.216.35:%d", port)
-
-	transport := gateway.Client().Transport.(*http.Transport).Clone()
-	transport.TLSClientConfig = transport.TLSClientConfig.Clone()
-	transport.TLSClientConfig.InsecureSkipVerify = true //nolint:gosec // hermetic public-address routing fixture
-	dialer := &net.Dialer{}
-	gatewayAddress := gateway.Listener.Addr().String()
-	transport.DialContext = func(ctx context.Context, network string, address string) (net.Conn, error) {
-		host, _, err := net.SplitHostPort(address)
-		if err == nil && (host == "93.184.216.34" || host == "93.184.216.35") {
-			return dialer.DialContext(ctx, network, gatewayAddress)
-		}
-		return dialer.DialContext(ctx, network, address)
-	}
-	return publicProtectedOAuthFixture{
-		client:      &http.Client{Transport: transport},
-		resourceURL: resourceOrigin + "/mcp",
-	}
-}
-
-func TestProtectedResourceProbeDoesNotFollowRedirects(t *testing.T) {
-	var redirectedHits atomic.Int64
-	redirected := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, _ *http.Request) {
-		redirectedHits.Add(1)
-		w.WriteHeader(http.StatusUnauthorized)
-	}))
-	defer redirected.Close()
-	source := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
-		http.Redirect(w, r, redirected.URL+"/mcp", http.StatusFound)
-	}))
-	defer source.Close()
-
-	_, found, err := discoverProtectedResourceAuthorizationServer(context.Background(), source.Client(), source.URL+"/mcp")
-	if err != nil || found {
-		t.Fatalf("redirected probe found=%v err=%v", found, err)
-	}
-	if redirectedHits.Load() != 0 {
-		t.Fatalf("probe followed redirect %d time(s)", redirectedHits.Load())
-	}
-}
-
-func TestProtectedResourceMetadataDoesNotFollowRedirects(t *testing.T) {
-	var redirectedHits atomic.Int64
-	redirected := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, _ *http.Request) {
-		redirectedHits.Add(1)
-		_ = json.NewEncoder(w).Encode(map[string]any{
-			"resource":              "https://attacker.example/mcp",
-			"authorization_servers": []string{"https://attacker.example"},
-		})
-	}))
-	defer redirected.Close()
-	source := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
-		base := "http://" + r.Host
-		switch r.URL.Path {
-		case "/mcp":
-			w.Header().Set("WWW-Authenticate", `Bearer resource_metadata="`+base+`/metadata"`)
-			w.WriteHeader(http.StatusUnauthorized)
-		case "/metadata":
-			http.Redirect(w, r, redirected.URL+"/metadata", http.StatusFound)
-		}
-	}))
-	defer source.Close()
-
-	_, _, err := discoverProtectedResourceAuthorizationServer(context.Background(), source.Client(), source.URL+"/mcp")
-	if err == nil || !strings.Contains(err.Error(), "HTTP 302") {
-		t.Fatalf("error = %v, want redirect refusal", err)
-	}
-	if redirectedHits.Load() != 0 {
-		t.Fatalf("metadata fetch followed redirect %d time(s)", redirectedHits.Load())
-	}
-}
-
-func TestResolveAuthorizationServerRejectsProtectedIssuerMismatch(t *testing.T) {
-	authorizationServer := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
-		base := "http://" + r.Host
-		_ = json.NewEncoder(w).Encode(map[string]any{
-			"issuer":                 "https://unexpected.example",
-			"authorization_endpoint": base + "/authorize",
-			"token_endpoint":         base + "/token",
-		})
-	}))
-	defer authorizationServer.Close()
-	resourceServer := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
-		base := "http://" + r.Host
-		switch r.URL.Path {
-		case "/mcp":
-			w.Header().Set("WWW-Authenticate", `Bearer resource_metadata="`+base+`/metadata"`)
-			w.WriteHeader(http.StatusUnauthorized)
-		case "/metadata":
-			_ = json.NewEncoder(w).Encode(map[string]any{
-				"resource":              base + "/mcp",
-				"authorization_servers": []string{authorizationServer.URL},
-			})
-		}
-	}))
-	defer resourceServer.Close()
-
-	_, err := resolveAuthorizationServer(context.Background(), resourceServer.Client(), resourceServer.URL+"/mcp", OAuthConfig{})
-	if err == nil || !strings.Contains(err.Error(), "issuer does not match") {
-		t.Fatalf("error = %v, want issuer mismatch", err)
-	}
-}
-
-func TestResolveAuthorizationServerRejectsMissingProtectedIssuer(t *testing.T) {
-	authorizationServer := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
-		base := "http://" + r.Host
-		_ = json.NewEncoder(w).Encode(map[string]any{
-			"authorization_endpoint": base + "/authorize",
-			"token_endpoint":         base + "/token",
-		})
-	}))
-	defer authorizationServer.Close()
-	resourceServer := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
-		base := "http://" + r.Host
-		switch r.URL.Path {
-		case "/mcp":
-			w.Header().Set("WWW-Authenticate", `Bearer resource_metadata="`+base+`/metadata"`)
-			w.WriteHeader(http.StatusUnauthorized)
-		case "/metadata":
-			_ = json.NewEncoder(w).Encode(map[string]any{
-				"resource":              base + "/mcp",
-				"authorization_servers": []string{authorizationServer.URL},
-			})
-		}
-	}))
-	defer resourceServer.Close()
-
-	_, err := resolveAuthorizationServer(context.Background(), resourceServer.Client(), resourceServer.URL+"/mcp", OAuthConfig{})
-	if err == nil || !strings.Contains(err.Error(), "issuer") {
-		t.Fatalf("error = %v, want missing issuer rejection", err)
-	}
-}
-
-func TestResolveAuthorizationServerRejectsWhitespaceAlteredProtectedIssuer(t *testing.T) {
-	for _, alter := range []struct {
-		name  string
-		apply func(string) string
-	}{
-		{name: "leading", apply: func(value string) string { return " " + value }},
-		{name: "trailing", apply: func(value string) string { return value + " " }},
-	} {
-		t.Run(alter.name, func(t *testing.T) {
-			authorizationServer := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
-				base := "http://" + r.Host
-				_ = json.NewEncoder(w).Encode(map[string]any{
-					"issuer":                 alter.apply(base),
-					"authorization_endpoint": base + "/authorize",
-					"token_endpoint":         base + "/token",
-				})
-			}))
-			defer authorizationServer.Close()
-			resourceServer := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
-				base := "http://" + r.Host
-				switch r.URL.Path {
-				case "/mcp":
-					w.Header().Set("WWW-Authenticate", `Bearer resource_metadata="`+base+`/metadata"`)
-					w.WriteHeader(http.StatusUnauthorized)
-				case "/metadata":
-					_ = json.NewEncoder(w).Encode(map[string]any{
-						"resource":              base + "/mcp",
-						"authorization_servers": []string{authorizationServer.URL},
-					})
-				}
-			}))
-			defer resourceServer.Close()
-
-			_, err := resolveAuthorizationServer(context.Background(), resourceServer.Client(), resourceServer.URL+"/mcp", OAuthConfig{})
-			if err == nil || !strings.Contains(err.Error(), "issuer does not match") {
-				t.Fatalf("error = %v, want whitespace issuer mismatch", err)
-			}
-		})
-	}
-}
-
-func TestAuthorizationServerMetadataDoesNotFollowRedirects(t *testing.T) {
-	var redirectedHits atomic.Int64
-	redirected := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
-		redirectedHits.Add(1)
-		base := "http://" + r.Host
-		_ = json.NewEncoder(w).Encode(map[string]any{
-			"issuer":                 base,
-			"authorization_endpoint": base + "/authorize",
-			"token_endpoint":         base + "/token",
-		})
-	}))
-	defer redirected.Close()
-	authorizationServer := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
-		http.Redirect(w, r, redirected.URL+"/.well-known/oauth-authorization-server", http.StatusFound)
-	}))
-	defer authorizationServer.Close()
-	resourceServer := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
-		base := "http://" + r.Host
-		switch r.URL.Path {
-		case "/mcp":
-			w.Header().Set("WWW-Authenticate", `Bearer resource_metadata="`+base+`/metadata"`)
-			w.WriteHeader(http.StatusUnauthorized)
-		case "/metadata":
-			_ = json.NewEncoder(w).Encode(map[string]any{
-				"resource":              base + "/mcp",
-				"authorization_servers": []string{authorizationServer.URL},
-			})
-		}
-	}))
-	defer resourceServer.Close()
-
-	_, err := resolveAuthorizationServer(context.Background(), resourceServer.Client(), resourceServer.URL+"/mcp", OAuthConfig{})
-	if err == nil {
-		t.Fatal("authorization metadata redirect should fail")
-	}
-	if redirectedHits.Load() != 0 {
-		t.Fatalf("authorization metadata fetch followed redirect %d time(s)", redirectedHits.Load())
-	}
-}

internal/mcp/oauth_test.go

@@ -10,7 +10,6 @@ import (
 	"net/http/httptest"
 	"net/url"
 	"strings"
-	"sync/atomic"
 	"testing"
 	"time"
 
@@ -146,130 +145,6 @@ func TestResolveEndpointsConfigOverridesDiscovery(t *testing.T) {
 	}
 }
 
-func TestResolveAuthorizationServerUsesProtectedResourceMetadata(t *testing.T) {
-	var authorizationMetadataHits atomic.Int64
-	authorizationServer := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
-		if r.URL.Path != "/.well-known/oauth-authorization-server" {
-			http.NotFound(w, r)
-			return
-		}
-		authorizationMetadataHits.Add(1)
-		base := "http://" + r.Host
-		_ = json.NewEncoder(w).Encode(map[string]any{
-			"issuer":                 base,
-			"authorization_endpoint": base + "/authorize",
-			"token_endpoint":         base + "/token",
-			"registration_endpoint":  base + "/register",
-		})
-	}))
-	defer authorizationServer.Close()
-
-	var resourceProbeHits, resourceMetadataHits atomic.Int64
-	resourceServer := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
-		switch r.URL.Path {
-		case "/mcp":
-			resourceProbeHits.Add(1)
-			metadataURL := "http://" + r.Host + "/resource-metadata"
-			w.Header().Set("WWW-Authenticate", `Bearer realm="OAuth", resource_metadata="`+metadataURL+`"`)
-			w.WriteHeader(http.StatusUnauthorized)
-		case "/resource-metadata":
-			resourceMetadataHits.Add(1)
-			_ = json.NewEncoder(w).Encode(map[string]any{
-				"resource":              "http://" + r.Host + "/mcp",
-				"authorization_servers": []string{authorizationServer.URL},
-			})
-		default:
-			http.NotFound(w, r)
-		}
-	}))
-	defer resourceServer.Close()
-
-	metadata, err := resolveAuthorizationServer(context.Background(), resourceServer.Client(), resourceServer.URL+"/mcp", OAuthConfig{})
-	if err != nil {
-		t.Fatalf("resolveAuthorizationServer() error = %v", err)
-	}
-	if metadata.Issuer != authorizationServer.URL {
-		t.Fatalf("issuer = %q, want %q", metadata.Issuer, authorizationServer.URL)
-	}
-	if metadata.AuthorizationEndpoint != authorizationServer.URL+"/authorize" || metadata.TokenEndpoint != authorizationServer.URL+"/token" {
-		t.Fatalf("resolved metadata = %#v", metadata)
-	}
-	if resourceProbeHits.Load() != 1 || resourceMetadataHits.Load() != 1 || authorizationMetadataHits.Load() != 1 {
-		t.Fatalf("discovery hits = probe:%d resource:%d authorization:%d", resourceProbeHits.Load(), resourceMetadataHits.Load(), authorizationMetadataHits.Load())
-	}
-}
-
-func TestResolveAuthorizationServerFallsBackToDirectDiscovery(t *testing.T) {
-	var resourceProbeHits, directDiscoveryHits atomic.Int64
-	server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
-		switch r.URL.Path {
-		case "/mcp":
-			resourceProbeHits.Add(1)
-			w.Header().Set("Content-Type", "text/event-stream")
-			w.WriteHeader(http.StatusOK)
-			if flusher, ok := w.(http.Flusher); ok {
-				flusher.Flush()
-			}
-			<-r.Context().Done()
-		case "/.well-known/oauth-authorization-server/mcp":
-			directDiscoveryHits.Add(1)
-			base := "http://" + r.Host
-			_ = json.NewEncoder(w).Encode(map[string]any{
-				"issuer":                 base + "/mcp",
-				"authorization_endpoint": base + "/authorize",
-				"token_endpoint":         base + "/token",
-			})
-		default:
-			http.NotFound(w, r)
-		}
-	}))
-	defer server.Close()
-
-	metadata, err := resolveAuthorizationServer(context.Background(), server.Client(), server.URL+"/mcp", OAuthConfig{})
-	if err != nil {
-		t.Fatalf("resolveAuthorizationServer() error = %v", err)
-	}
-	if metadata.AuthorizationEndpoint != server.URL+"/authorize" || metadata.TokenEndpoint != server.URL+"/token" {
-		t.Fatalf("resolved metadata = %#v", metadata)
-	}
-	if resourceProbeHits.Load() != 1 || directDiscoveryHits.Load() != 1 {
-		t.Fatalf("discovery hits = probe:%d direct:%d", resourceProbeHits.Load(), directDiscoveryHits.Load())
-	}
-}
-
-func TestResolveAuthorizationServerIssuerOverrideSkipsResourceProbe(t *testing.T) {
-	var resourceProbeHits, issuerDiscoveryHits atomic.Int64
-	server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
-		base := "http://" + r.Host
-		switch r.URL.Path {
-		case "/mcp":
-			resourceProbeHits.Add(1)
-			w.WriteHeader(http.StatusUnauthorized)
-		case "/.well-known/oauth-authorization-server/issuer":
-			issuerDiscoveryHits.Add(1)
-			_ = json.NewEncoder(w).Encode(map[string]any{
-				"issuer":                 base + "/issuer",
-				"authorization_endpoint": base + "/authorize",
-				"token_endpoint":         base + "/token",
-			})
-		default:
-			http.NotFound(w, r)
-		}
-	}))
-	defer server.Close()
-
-	metadata, err := resolveAuthorizationServer(context.Background(), server.Client(), server.URL+"/mcp", OAuthConfig{IssuerURL: server.URL + "/issuer"})
-	if err != nil {
-		t.Fatalf("resolveAuthorizationServer() error = %v", err)
-	}
-	if metadata.AuthorizationEndpoint != server.URL+"/authorize" || metadata.TokenEndpoint != server.URL+"/token" {
-		t.Fatalf("resolved metadata = %#v", metadata)
-	}
-	if resourceProbeHits.Load() != 0 || issuerDiscoveryHits.Load() != 1 {
-		t.Fatalf("discovery hits = resource:%d issuer:%d", resourceProbeHits.Load(), issuerDiscoveryHits.Load())
-	}
-}
-
 func TestPKCEChallengeIsS256OfVerifier(t *testing.T) {
 	pkce, err := newPKCE()
 	if err != nil {
@@ -573,98 +448,3 @@ func TestFullFlowStoresTokens(t *testing.T) {
 		t.Fatalf("login token = %#v", result)
 	}
 }
-
-func TestFullFlowUsesProtectedResourceDiscovery(t *testing.T) {
-	var resourceProbeHits, resourceMetadataHits, authorizationMetadataHits, tokenHits atomic.Int64
-	server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
-		base := "http://" + r.Host
-		switch r.URL.Path {
-		case "/mcp":
-			resourceProbeHits.Add(1)
-			if r.Header.Get("Authorization") != "" || r.Header.Get("Cookie") != "" {
-				t.Error("resource probe sent credentials")
-			}
-			w.Header().Set("WWW-Authenticate", `Bearer resource_metadata="`+base+`/resource-metadata"`)
-			w.WriteHeader(http.StatusUnauthorized)
-		case "/resource-metadata":
-			resourceMetadataHits.Add(1)
-			_ = json.NewEncoder(w).Encode(map[string]any{
-				"resource":              base + "/mcp",
-				"authorization_servers": []string{base},
-			})
-		case "/.well-known/oauth-authorization-server":
-			authorizationMetadataHits.Add(1)
-			_ = json.NewEncoder(w).Encode(map[string]any{
-				"issuer":                 base,
-				"authorization_endpoint": base + "/authorize",
-				"token_endpoint":         base + "/token",
-			})
-		case "/token":
-			tokenHits.Add(1)
-			if err := r.ParseForm(); err != nil {
-				t.Errorf("parse token form: %v", err)
-			}
-			if r.Form.Get("code") != "authorization-code-secret" || r.Form.Get("code_verifier") == "" {
-				t.Error("token exchange omitted the authorization code or PKCE verifier")
-			}
-			_ = json.NewEncoder(w).Encode(map[string]any{
-				"access_token":  "access-token-secret",
-				"refresh_token": "refresh-token-secret",
-				"token_type":    "Bearer",
-				"expires_in":    3600,
-			})
-		default:
-			http.NotFound(w, r)
-		}
-	}))
-	defer server.Close()
-
-	opener := func(authURL string) error {
-		parsed, err := url.Parse(authURL)
-		if err != nil {
-			return err
-		}
-		if parsed.Path != "/authorize" || parsed.Query().Get("code_challenge_method") != "S256" || parsed.Query().Get("code_challenge") == "" {
-			return errors.New("authorization request omitted the discovered endpoint or PKCE challenge")
-		}
-		if parsed.Query().Get("code") != "" || parsed.Query().Get("code_verifier") != "" {
-			return errors.New("authorization request exposed an authorization code or PKCE verifier")
-		}
-		state := parsed.Query().Get("state")
-		redirect := parsed.Query().Get("redirect_uri")
-		go func() {
-			callbackURL := redirect + "?code=authorization-code-secret&state=" + url.QueryEscape(state)
-			for attempt := 0; attempt < 20; attempt++ {
-				response, requestErr := http.Get(callbackURL)
-				if requestErr == nil {
-					response.Body.Close()
-					return
-				}
-				time.Sleep(50 * time.Millisecond)
-			}
-		}()
-		return nil
-	}
-
-	token, err := Login(context.Background(), LoginOptions{
-		ServerName: "notion-style",
-		ServerURL:  server.URL + "/mcp",
-		Config: OAuthConfig{
-			ClientID: "client-123",
-			Scopes:   []string{"read"},
-		},
-		HTTPClient:  server.Client(),
-		OpenBrowser: opener,
-		Timeout:     5 * time.Second,
-		Now:         time.Now,
-	})
-	if err != nil {
-		t.Fatalf("Login() error = %v", err)
-	}
-	if token.AccessToken != "access-token-secret" || token.RefreshToken != "refresh-token-secret" {
-		t.Fatal("login did not return the issued tokens")
-	}
-	if resourceProbeHits.Load() != 1 || resourceMetadataHits.Load() != 1 || authorizationMetadataHits.Load() != 1 || tokenHits.Load() != 1 {
-		t.Fatalf("flow hits = probe:%d resource:%d authorization:%d token:%d", resourceProbeHits.Load(), resourceMetadataHits.Load(), authorizationMetadataHits.Load(), tokenHits.Load())
-	}
-}

internal/mcp/registry.go

@@ -23,9 +23,6 @@ const defaultConnectTimeout = 8 * time.Second
 type RegisterOptions struct {
 	PermissionStore *PermissionStore
 	Autonomy        PermissionAutonomy
-	// AdvertiseInAuto exposes prompt-gated MCP tools to model surfaces whose
-	// default mode is auto while preserving the execution-time prompt.
-	AdvertiseInAuto bool
 	ClientFactory   func(context.Context, Server) (ToolClient, error)
 	// ConnectTimeout bounds the per-server connect+list at startup. Zero uses
 	// defaultConnectTimeout.
@@ -274,10 +271,9 @@ func newRegistryTool(server Server, remote RemoteTool, client ToolClient, option
 		client:     client,
 		parameters: SchemaFromMCP(remote.InputSchema),
 		safety: tools.Safety{
-			SideEffect:      tools.SideEffectNetwork,
-			Permission:      permission,
-			Reason:          fmt.Sprintf("MCP tool %s/%s runs through the configured %s server.", server.Name, remote.Name, server.Type),
-			AdvertiseInAuto: options.AdvertiseInAuto,
+			SideEffect: tools.SideEffectNetwork,
+			Permission: permission,
+			Reason:     fmt.Sprintf("MCP tool %s/%s runs through the configured %s server.", server.Name, remote.Name, server.Type),
 		},
 	}
 }

internal/mcp/registry_test.go

@@ -342,19 +342,6 @@ func TestRegistryToolIsDeferredEligible(t *testing.T) {
 	}
 }
 
-func TestRegistryToolCanAdvertiseInAutoWithoutPreapproval(t *testing.T) {
-	tool := newRegistryTool(
-		Server{Name: "docs", Type: "stdio"},
-		RemoteTool{Name: "search"},
-		&fakeToolClient{},
-		RegisterOptions{Autonomy: AutonomyLow, AdvertiseInAuto: true},
-	)
-	safety := tool.Safety()
-	if safety.Permission != tools.PermissionPrompt || !safety.AdvertiseInAuto {
-		t.Fatalf("MCP safety = %#v", safety)
-	}
-}
-
 // TestRegistryToolReportsMCPServerName verifies the registryTool reports its true
 // configured server name (not the sanitized tool-name token) so the deferred-tools
 // discovery label names a multi-token server correctly via tools.DeferredSource.

internal/oauth/lock.go

@@ -5,16 +5,24 @@ import (
 	"fmt"
 	"os"
 	"path/filepath"
+	"sync/atomic"
 	"time"
 
 	"github.com/Gitlawb/zero/internal/lockutil"
 )
 
-const fileLockTimeout = 5 * time.Second
+const (
+	fileLockTimeout    = 5 * time.Second
+	fileLockStaleAfter = 30 * time.Second
+)
 
-// acquireFileLock takes a cross-process advisory lock through a stable lock
-// file. It retries with a short backoff until a timeout. Kernel lock lifetime
-// provides crash recovery, so the path is never renamed or removed.
+var lockSeq atomic.Uint64
+
+// acquireFileLock takes a cross-process exclusive lock by creating lockPath with
+// O_EXCL. It retries with a short backoff until a timeout, breaking a lock whose
+// file is older than fileLockStaleAfter (so a crashed holder cannot deadlock the
+// store). Release is ownership-aware: it removes the lock only if it still holds
+// our token, so a stale-broken holder cannot delete a newer holder's lock.
 func acquireFileLock(lockPath string, now func() time.Time) (func(), error) {
 	if now == nil {
 		now = time.Now
@@ -22,15 +30,64 @@ func acquireFileLock(lockPath string, now func() time.Time) (func(), error) {
 	if err := os.MkdirAll(filepath.Dir(lockPath), 0o700); err != nil {
 		return nil, err
 	}
+	token := fmt.Sprintf("%d-%d-%d", os.Getpid(), now().UnixNano(), lockSeq.Add(1))
 	deadline := now().Add(fileLockTimeout)
 	for {
-		lock, err := lockutil.TryAcquireFileLock(lockPath)
+		f, err := os.OpenFile(lockPath, os.O_CREATE|os.O_EXCL|os.O_WRONLY, 0o600)
 		if err == nil {
-			return func() { _ = lock.Release() }, nil
+			// A partial/failed write would leave a lock file without our token, so
+			// the releaser below could never delete it — stranding the lock for
+			// other processes. Fail closed: remove the file and surface the error.
+			if _, werr := f.WriteString(token); werr != nil {
+				_ = f.Close()
+				_ = lockutil.RemoveLockFile(lockPath)
+				return nil, fmt.Errorf("oauth: write token lock: %w", werr)
+			}
+			if cerr := f.Close(); cerr != nil {
+				_ = lockutil.RemoveLockFile(lockPath)
+				return nil, fmt.Errorf("oauth: close token lock: %w", cerr)
+			}
+			var released bool
+			return func() {
+				if released {
+					return
+				}
+				released = true
+				if data, rerr := os.ReadFile(lockPath); rerr == nil && string(data) == token {
+					_ = lockutil.RemoveLockFile(lockPath)
+				}
+			}, nil
 		}
-		if !errors.Is(err, lockutil.ErrLockHeld) {
+		// On Windows a concurrent holder's os.Remove leaves the lock file in a
+		// "delete pending" state, so an O_EXCL create races it with
+		// ERROR_ACCESS_DENIED (os.ErrPermission) rather than ErrExist. Treat that
+		// as contention and retry, exactly like ErrExist — otherwise the lock
+		// spuriously fails under concurrency on Windows.
+		if !errors.Is(err, os.ErrExist) && !errors.Is(err, os.ErrPermission) {
 			return nil, fmt.Errorf("oauth: acquire token lock: %w", err)
 		}
+		// Reclaim a stale lock left by a crashed holder — atomically (H3). A blind
+		// Remove lets two racers both reclaim + recreate and so both hold the lock;
+		// reclaimStaleLock renames the file aside (only one rename wins) and restores
+		// it if it turns out fresh, so a live lock is never deleted out from under it.
+		if info, statErr := os.Stat(lockPath); statErr == nil && time.Since(info.ModTime()) > fileLockStaleAfter {
+			cleared, rerr := lockutil.ReclaimStaleLock(lockPath, token, func(reclaimedPath string) bool {
+				info, err := os.Stat(reclaimedPath)
+				return err == nil && time.Since(info.ModTime()) <= fileLockStaleAfter
+			})
+			if rerr != nil {
+				// Reclaim hit a hard failure: the rename aside failed outright, or a
+				// live holder's lock could not be put back (the lock path may be
+				// missing, so re-acquiring would break mutual exclusion). Fail closed
+				// instead of spinning to the deadline.
+				return nil, fmt.Errorf("oauth: reclaim stale token lock: %w", rerr)
+			}
+			if cleared {
+				continue
+			}
+			// Lost the reclaim race (or it was actually fresh) — fall through to the
+			// bounded wait rather than hot-spinning on a reclaim that never wins.
+		}
 		if now().After(deadline) {
 			return nil, fmt.Errorf("oauth: timed out acquiring token lock %s", filepath.Base(lockPath))
 		}

internal/providers/compaction_model.go

@@ -1,108 +0,0 @@
-package providers
-
-import (
-	"context"
-	"os"
-	"strings"
-
-	"github.com/Gitlawb/zero/internal/config"
-	"github.com/Gitlawb/zero/internal/zeroruntime"
-)
-
-// Compaction summarization model selection.
-//
-// Compaction summaries used to run on the session's main model — near a 200k
-// window one summarization is a ~100k-token input call at full price, the
-// single most expensive recurring event in a long run. A cheap model handles
-// the "dense factual summary" task fine, so summarization is routed to one
-// whenever the target is knowable.
-//
-// Resolution order: ZERO_COMPACTION_MODEL env > preferences.compactionModel
-// config > a curated per-kind default (OFFICIAL endpoints only) > "" (use the
-// main model). The literal value "main" at any level forces the main model.
-// A wrong choice is never fatal: the agent falls back to the main provider on
-// the first summarizer failure for the rest of the run.
-
-// CompactionModelEnv overrides the compaction summarization model.
-const CompactionModelEnv = "ZERO_COMPACTION_MODEL"
-
-// compactionMainSentinel disables the dedicated summarizer explicitly.
-const compactionMainSentinel = "main"
-
-// Curated cheap summarizer defaults, applied only for provider kinds whose
-// model catalog is guaranteed (official endpoints). Custom / *-compatible
-// endpoints get NO default — their catalogs are unknowable, and a guaranteed
-// failed call per run is worse than main-model prices.
-const (
-	defaultAnthropicCompactionModel = "claude-haiku-4-5-20251001"
-	defaultGoogleCompactionModel    = "gemini-2.5-flash-lite"
-	defaultOpenAICompactionModel    = "gpt-4.1-mini"
-)
-
-// CompactionModelID returns the model that compaction summarization calls
-// should use for the given profile, or "" to use the session's main model.
-// preference is the resolved config value (preferences.compactionModel).
-func CompactionModelID(profile config.ProviderProfile, preference string) string {
-	value := strings.TrimSpace(os.Getenv(CompactionModelEnv))
-	if value == "" {
-		value = strings.TrimSpace(preference)
-	}
-	if value != "" {
-		if strings.EqualFold(value, compactionMainSentinel) {
-			return ""
-		}
-		return value
-	}
-	return defaultCompactionModel(profile)
-}
-
-func defaultCompactionModel(profile config.ProviderProfile) string {
-	metadata, err := ResolveRuntimeMetadata(profile, Options{})
-	if err != nil {
-		return ""
-	}
-	var candidate string
-	switch metadata.ProviderKind {
-	case config.ProviderKindAnthropic:
-		candidate = defaultAnthropicCompactionModel
-	case config.ProviderKindGoogle:
-		candidate = defaultGoogleCompactionModel
-	case config.ProviderKindOpenAI:
-		candidate = defaultOpenAICompactionModel
-	default:
-		return ""
-	}
-	// Session already runs on the cheap model: a dedicated summarizer buys
-	// nothing and would only add a second provider instance.
-	if strings.EqualFold(strings.TrimSpace(metadata.APIModel), candidate) {
-		return ""
-	}
-	return candidate
-}
-
-// CompactionSummarizerFactory returns the lazy constructor the agent loop
-// calls for its dedicated compaction summarizer (agent.Options.Summarizer).
-// The compactor passes the main model in force at that moment — on the first
-// paid compaction and again after a mid-run model switch — so the choice
-// tracks escalations: a run that starts on the cheap model gets no dedicated
-// summarizer, and gains one once it escalates to a pricier main model.
-// Returning (nil, nil) means "summarize on the main provider". The factory
-// itself is nil only when no provider builder exists. Shared by the exec and
-// TUI front ends so the selection rules cannot drift between them.
-func CompactionSummarizerFactory(base config.ProviderProfile, preference string, newProvider func(config.ProviderProfile) (zeroruntime.Provider, error)) func(context.Context, string) (zeroruntime.Provider, error) {
-	if newProvider == nil {
-		return nil
-	}
-	return func(_ context.Context, mainModelID string) (zeroruntime.Provider, error) {
-		profile := base
-		if strings.TrimSpace(mainModelID) != "" {
-			profile.Model = mainModelID
-		}
-		modelID := CompactionModelID(profile, preference)
-		if modelID == "" {
-			return nil, nil
-		}
-		profile.Model = modelID
-		return newProvider(profile)
-	}
-}

internal/providers/compaction_model_test.go

@@ -1,113 +0,0 @@
-package providers
-
-import (
-	"context"
-	"errors"
-	"testing"
-
-	"github.com/Gitlawb/zero/internal/config"
-	"github.com/Gitlawb/zero/internal/zeroruntime"
-)
-
-func TestCompactionModelIDResolutionOrder(t *testing.T) {
-	anthropic := config.ProviderProfile{
-		Name:         "anthropic",
-		ProviderKind: config.ProviderKindAnthropic,
-		Model:        "claude-sonnet-4.5",
-	}
-
-	t.Setenv(CompactionModelEnv, "my-env-model")
-	if got := CompactionModelID(anthropic, "my-config-model"); got != "my-env-model" {
-		t.Fatalf("env must win, got %q", got)
-	}
-
-	t.Setenv(CompactionModelEnv, "main")
-	if got := CompactionModelID(anthropic, "my-config-model"); got != "" {
-		t.Fatalf("env 'main' must force the main model, got %q", got)
-	}
-
-	t.Setenv(CompactionModelEnv, "")
-	if got := CompactionModelID(anthropic, "my-config-model"); got != "my-config-model" {
-		t.Fatalf("config preference must apply when env unset, got %q", got)
-	}
-	if got := CompactionModelID(anthropic, "main"); got != "" {
-		t.Fatalf("config 'main' must force the main model, got %q", got)
-	}
-}
-
-func TestCompactionModelIDCuratedDefaults(t *testing.T) {
-	t.Setenv(CompactionModelEnv, "")
-
-	anthropic := config.ProviderProfile{Name: "anthropic", ProviderKind: config.ProviderKindAnthropic, Model: "claude-sonnet-4.5"}
-	if got := CompactionModelID(anthropic, ""); got != defaultAnthropicCompactionModel {
-		t.Fatalf("anthropic default = %q, want %q", got, defaultAnthropicCompactionModel)
-	}
-
-	google := config.ProviderProfile{Name: "google", ProviderKind: config.ProviderKindGoogle, Model: "gemini-2.5-pro"}
-	if got := CompactionModelID(google, ""); got != defaultGoogleCompactionModel {
-		t.Fatalf("google default = %q, want %q", got, defaultGoogleCompactionModel)
-	}
-
-	openai := config.ProviderProfile{Name: "openai", ProviderKind: config.ProviderKindOpenAI, Model: "gpt-4.1"}
-	if got := CompactionModelID(openai, ""); got != defaultOpenAICompactionModel {
-		t.Fatalf("openai default = %q, want %q", got, defaultOpenAICompactionModel)
-	}
-
-	// Custom/compatible endpoints: catalog unknowable, no default.
-	compatible := config.ProviderProfile{
-		Name:         "opengateway",
-		ProviderKind: config.ProviderKindOpenAICompatible,
-		BaseURL:      "https://opengateway.gitlawb.com/v1",
-		Model:        "some-model",
-	}
-	if got := CompactionModelID(compatible, ""); got != "" {
-		t.Fatalf("openai-compatible must have no default, got %q", got)
-	}
-}
-
-func TestCompactionModelIDSkipsWhenMainIsAlreadyCheap(t *testing.T) {
-	t.Setenv(CompactionModelEnv, "")
-	haiku := config.ProviderProfile{
-		Name:         "anthropic",
-		ProviderKind: config.ProviderKindAnthropic,
-		Model:        defaultAnthropicCompactionModel,
-	}
-	if got := CompactionModelID(haiku, ""); got != "" {
-		t.Fatalf("already-cheap session must not get a dedicated summarizer, got %q", got)
-	}
-}
-
-func TestCompactionSummarizerFactoryTracksMainModel(t *testing.T) {
-	t.Setenv(CompactionModelEnv, "")
-	base := config.ProviderProfile{Name: "anthropic", ProviderKind: config.ProviderKindAnthropic, Model: defaultAnthropicCompactionModel}
-	var built []string
-	newProvider := func(profile config.ProviderProfile) (zeroruntime.Provider, error) {
-		built = append(built, profile.Model)
-		return nil, errors.New("not needed")
-	}
-	factory := CompactionSummarizerFactory(base, "", newProvider)
-	if factory == nil {
-		t.Fatal("factory must exist when a provider builder exists")
-	}
-	// Main model is the cheap default: no dedicated summarizer, nothing built.
-	if provider, err := factory(context.Background(), defaultAnthropicCompactionModel); provider != nil || err != nil || len(built) != 0 {
-		t.Fatalf("cheap main model must yield (nil, nil) without building, got %v %v built=%v", provider, err, built)
-	}
-	// After escalating to an expensive model the cheap default is built.
-	if _, err := factory(context.Background(), "claude-sonnet-4-5"); err == nil || len(built) != 1 || built[0] != defaultAnthropicCompactionModel {
-		t.Fatalf("escalated main model must build the cheap summarizer, built=%v err=%v", built, err)
-	}
-	// An empty main model falls back to the base profile's model — the cheap
-	// default here, so again nothing is built.
-	built = nil
-	if provider, err := factory(context.Background(), ""); provider != nil || err != nil || len(built) != 0 {
-		t.Fatalf("empty main model must use the base profile, got %v %v built=%v", provider, err, built)
-	}
-	// The explicit "main" preference disables the dedicated summarizer.
-	if provider, err := CompactionSummarizerFactory(base, "main", newProvider)(context.Background(), "claude-sonnet-4-5"); provider != nil || err != nil {
-		t.Fatalf("preference main must disable the summarizer, got %v %v", provider, err)
-	}
-	if CompactionSummarizerFactory(base, "", nil) != nil {
-		t.Fatal("no provider builder means no factory")
-	}
-}

internal/sandbox/adapters.go

@@ -7,7 +7,6 @@ import (
 type BackendOptions struct {
 	GOOS             string
 	LookupExecutable func(string) (string, error)
-	DetectWSL        func() WSLInfo
 }
 
 type Backend struct {
@@ -54,7 +53,6 @@ func SelectBackend(options BackendOptions) Backend {
 	return NewSandboxManager(SandboxManagerOptions{
 		GOOS:             options.GOOS,
 		LookupExecutable: options.LookupExecutable,
-		DetectWSL:        options.DetectWSL,
 	}).Backend()
 }
 

internal/sandbox/adapters_test.go

@@ -45,7 +45,6 @@ func TestSelectBackendChoosesPlatformAdapterWithFallback(t *testing.T) {
 				}
 				return "", errors.New("missing")
 			},
-			DetectWSL: func() WSLInfo { return WSLInfo{} },
 		})
 		if backend.Name != BackendUnavailable || backend.Available {
 			t.Fatalf("linux backend = %#v, want native sandbox unavailable without Linux helper", backend)
@@ -55,20 +54,6 @@ func TestSelectBackendChoosesPlatformAdapterWithFallback(t *testing.T) {
 		}
 	})
 
-	t.Run("linux helper missing under WSL reports WSL fallback", func(t *testing.T) {
-		backend := SelectBackend(BackendOptions{
-			GOOS:             "linux",
-			LookupExecutable: func(string) (string, error) { return "", errors.New("missing") },
-			DetectWSL:        func() WSLInfo { return WSLInfo{IsWSL: true, IsWSL2: true} },
-		})
-		if backend.Name != BackendWSL || backend.Available || !backend.Fallback {
-			t.Fatalf("linux backend = %#v, want explicit WSL fallback", backend)
-		}
-		if !strings.Contains(backend.Message, "WSL2") {
-			t.Fatalf("linux fallback message = %q, want WSL2 diagnostic", backend.Message)
-		}
-	})
-
 	t.Run("darwin sandbox exec available", func(t *testing.T) {
 		backend := SelectBackend(BackendOptions{
 			GOOS: "darwin",

internal/sandbox/manager.go

@@ -51,7 +51,6 @@ const (
 type SandboxManagerOptions struct {
 	GOOS             string
 	LookupExecutable func(string) (string, error)
-	DetectWSL        func() WSLInfo
 	Backend          Backend
 }
 
@@ -97,7 +96,7 @@ func NewSandboxManager(options SandboxManagerOptions) SandboxManager {
 		goos = runtime.GOOS
 	}
 	if backend.Name == "" {
-		backend = selectPlatformBackend(goos, options.LookupExecutable, options.DetectWSL)
+		backend = selectPlatformBackend(goos, options.LookupExecutable)
 	}
 	if backend.Platform == "" {
 		backend.Platform = goos
@@ -169,13 +168,10 @@ func lookupExecutable(name string) (string, error) {
 	return "", errors.New("executable file not found")
 }
 
-func selectPlatformBackend(goos string, lookup func(string) (string, error), detect func() WSLInfo) Backend {
+func selectPlatformBackend(goos string, lookup func(string) (string, error)) Backend {
 	if lookup == nil {
 		lookup = lookupExecutable
 	}
-	if detect == nil {
-		detect = detectWSL
-	}
 	switch goos {
 	case "linux":
 		if helper, err := lookup(LinuxSandboxHelperName); err == nil && helper != "" {
@@ -184,7 +180,7 @@ func selectPlatformBackend(goos string, lookup func(string) (string, error), det
 			}
 			return nativeBackend(goos, BackendLinuxBwrap, helper, "Linux sandbox helper available")
 		}
-		if info := detect(); info.IsWSL {
+		if info := detectWSL(); info.IsWSL {
 			return wslBackend(goos, info)
 		}
 		return unavailableBackend(goos, "Linux sandbox helper is not available")

internal/sandbox/scope.go

@@ -19,17 +19,6 @@ type Scope struct {
 	workspaceRoot string
 	readRoots     []string
 	extraRoots    []string
-	// tempReads / tempWrites count how many LIVE temporary grants depend on a
-	// root, so one holder's cleanup cannot revoke another's access.
-	//
-	// Without them a temporary grant was add-then-remove with no notion of who
-	// still needed it: the second caller to ask for a root already present got a
-	// NO-OP undo, and the first caller's cleanup removed the root out from under
-	// it. Two read-only tools in the same parallel batch, both blocked on the
-	// same directory, is exactly that shape — and read-only tools are precisely
-	// the ones the batch runs concurrently.
-	tempReads  map[string]int
-	tempWrites map[string]int
 }
 
 // NewScope builds a scope for workspaceRoot plus the given extra roots. The
@@ -92,88 +81,15 @@ func (s *Scope) Add(path string) (string, error) {
 	}
 	s.mu.Lock()
 	defer s.mu.Unlock()
-	// COVERED BY WHAT. extraRoots holds temporary write roots alongside
-	// permanent ones, so "something already covers this" was not the question
-	// worth asking: a permanent grant made over a path a temporary holder
-	// happened to cover recorded nothing, and vanished the moment that holder
-	// released. A session-scoped grant outliving the request that prompted it is
-	// the entire difference between Add and AddTemporaryWrite.
-	//
-	// Permanent coverage is looked for FIRST and across every root, because a
-	// path can be covered twice and the temporary cover must not decide the
-	// answer when a permanent one is also present.
-	if s.permanentWriteRootCoversLocked(root) {
-		return root, nil
-	}
-	for _, existing := range s.extraRoots {
-		// The same root, held temporarily: promote it in place. Its holders'
-		// releases become no-ops, which is what permanence means here.
-		if existing == root && s.temporaryWriteLocked(existing) {
-			delete(s.tempWrites, root)
+	for _, existing := range append([]string{s.workspaceRoot}, s.extraRoots...) {
+		if pathWithinRoot(existing, root) {
 			return root, nil
 		}
 	}
-	// Either uncovered, or covered only by a BROADER temporary root that is
-	// going to be released. Recording the narrower root in its own right is what
-	// survives that release.
 	s.extraRoots = append(s.extraRoots, root)
 	return root, nil
 }
 
-// temporaryWriteLocked reports whether root is held by a temporary write grant
-// rather than a session-scoped one. Callers must hold the lock.
-func (s *Scope) temporaryWriteLocked(root string) bool {
-	_, temporary := s.tempWrites[root]
-	return temporary
-}
-
-// permanentWriteRootCoversLocked reports whether root sits under write authority
-// that outlives every temporary holder: the workspace root, or a session-scoped
-// grant. Coverage by a TEMPORARY write root deliberately does not count —
-// it is going to be released, so nothing recorded on the strength of it
-// survives. Callers must hold the lock.
-//
-// One helper rather than a copy per caller because Add, AddRead and
-// AddTemporaryRead all turn on the same question, and three copies of "covered,
-// but by what" is how one of them ends up answering it differently.
-// permanentReadRootCoversLocked reports whether root is already readable by a
-// grant that outlives every temporary holder.
-//
-// SLICE ORDER MUST NOT DECIDE THIS. The old check walked readRoots and stopped at
-// the first entry covering the path, so a BROAD TEMPORARY root sitting earlier in
-// the slice shadowed a narrower PERMANENT one later — and the caller was handed a
-// reference on somebody else's grant when it needed no reference at all. Asking
-// the whole question first, over both lists, makes the answer independent of
-// insertion order.
-//
-// Write roots count: a grant that permits writing permits reading the same tree.
-func (s *Scope) permanentReadRootCoversLocked(root string) bool {
-	if s.permanentWriteRootCoversLocked(root) {
-		return true
-	}
-	for _, existing := range s.readRoots {
-		if pathWithinRoot(existing, root) && !s.temporaryReadLocked(existing) {
-			return true
-		}
-	}
-	return false
-}
-
-func (s *Scope) permanentWriteRootCoversLocked(root string) bool {
-	for _, existing := range append([]string{s.workspaceRoot}, s.extraRoots...) {
-		if pathWithinRoot(existing, root) && !s.temporaryWriteLocked(existing) {
-			return true
-		}
-	}
-	return false
-}
-
-// temporaryReadLocked is temporaryWriteLocked for read roots.
-func (s *Scope) temporaryReadLocked(root string) bool {
-	_, temporary := s.tempReads[root]
-	return temporary
-}
-
 // AddRead grants read-only access under path. If the path is already covered by
 // a writable root, no separate read root is stored.
 func (s *Scope) AddRead(path string) (string, error) {
@@ -183,19 +99,11 @@ func (s *Scope) AddRead(path string) (string, error) {
 	}
 	s.mu.Lock()
 	defer s.mu.Unlock()
-	// Same rule as Add: coverage that is going to be released is not coverage a
-	// permanent grant can rely on, whichever side of the read/write boundary it
-	// sits on. A permanent read covered only by a temporary WRITE root died with
-	// that root just as surely.
-	if s.permanentWriteRootCoversLocked(root) {
-		return root, nil
-	}
-	if s.permanentReadRootCoversLocked(root) {
+	if s.writeRootCoversLocked(root) {
 		return root, nil
 	}
 	for _, existing := range s.readRoots {
-		if existing == root && s.temporaryReadLocked(existing) {
-			delete(s.tempReads, root)
+		if pathWithinRoot(existing, root) {
 			return root, nil
 		}
 	}
@@ -210,63 +118,16 @@ func (s *Scope) AddTemporaryRead(path string) (string, func(), error) {
 	}
 	s.mu.Lock()
 	defer s.mu.Unlock()
-	// Genuinely permanent — the workspace root, or a session-scoped grant. It
-	// outlives this reader, so there is nothing to release.
-	if s.permanentWriteRootCoversLocked(root) {
+	if s.writeRootCoversLocked(root) {
 		return root, func() {}, nil
 	}
-	// A TEMPORARY write root covering this path is NOT borrowed, and this is the
-	// one place the distinction bites hardest.
-	//
-	// The dependency on that root is real — the write holder's cleanup must not
-	// revoke this reader, which is the defect the refcount exists to close,
-	// reached across the read/write boundary. But taking a reference on the
-	// WRITE root pays for the lifetime with the authority: the reference keeps
-	// the root in extraRoots, extraRoots is what Roots() feeds validate(), and
-	// validate() is WRITE authorization. So a reader outliving its writer went on
-	// writing anywhere under a write grant that had already ended — not merely
-	// under the path it asked to read.
-	//
-	// One reference cannot be both the lifetime and the capability. The lifetime
-	// is kept below, as a temporary READ root for the path this caller actually
-	// asked for. readRoots feeds ReadRoots(), which confers no write authority —
-	// validate() authorises writes from workspaceRoot plus extraRoots, and this
-	// path never enters that list. So the reader survives its writer with read
-	// authority and only read authority.
-	//
-	// That claim is the written justification for the whole design, so it has to
-	// stay exhaustive as the accessors change. It has already been wrong once, in
-	// both directions: an earlier draft said readRoots fed ReadRoots() and nothing
-	// else while ExtraReadRoots() also read it, and that accessor has since been
-	// removed as belonging to a different change.
-	if s.permanentReadRootCoversLocked(root) {
-		return root, func() {}, nil
+	for _, existing := range s.readRoots {
+		if pathWithinRoot(existing, root) {
+			return root, func() {}, nil
+		}
 	}
-	if s.tempReads == nil {
-		s.tempReads = map[string]int{}
-	}
-	// THE SAME ROOT, ANOTHER HOLDER: one entry, two references. Only an EXACT
-	// match shares — a narrower request must not, which is the whole point below.
-	if _, held := s.tempReads[root]; held {
-		s.tempReads[root]++
-		return root, oncePerHolder(func() { s.releaseTemporaryRead(root) }), nil
-	}
-	// A NARROWER REQUEST RECORDS ITS OWN ROOT, even under a broader temporary
-	// read that currently covers it.
-	//
-	// Borrowing the covering root's reference kept this reader alive by keeping
-	// the BROAD ROOT alive, and readRoots feeds validateRead and the native
-	// sandbox profile. So once the broad reader released, a caller that had asked
-	// to read one subdirectory was left able to read the whole tree its neighbour
-	// had asked for, siblings included. Reported by @jatmn, and it is the read
-	// twin of the write escalation fixed above: the refcount key decides not only
-	// WHEN an entry disappears but WHICH path stays authorised while it lives.
 	s.readRoots = append(s.readRoots, root)
-	if s.tempReads == nil {
-		s.tempReads = map[string]int{}
-	}
-	s.tempReads[root] = 1
-	return root, oncePerHolder(func() { s.releaseTemporaryRead(root) }), nil
+	return root, func() { s.removeReadRoot(root) }, nil
 }
 
 func (s *Scope) AddTemporaryWrite(path string) (string, func(), error) {
@@ -276,107 +137,32 @@ func (s *Scope) AddTemporaryWrite(path string) (string, func(), error) {
 	}
 	s.mu.Lock()
 	defer s.mu.Unlock()
-	// A PERMANENT grant is the only cover that needs no bookkeeping: it outlives
-	// every temporary holder, so there is nothing to keep alive and nothing to
-	// release.
-	if s.permanentWriteRootCoversLocked(root) {
+	if s.writeRootCoversLocked(root) {
 		return root, func() {}, nil
 	}
-	if s.tempWrites == nil {
-		s.tempWrites = map[string]int{}
-	}
-	// THE SAME ROOT, ANOTHER HOLDER: one entry, two references. Only an exact
-	// match shares an entry — a NARROWER request must not, which is the whole
-	// point below.
-	if _, held := s.tempWrites[root]; held {
-		s.tempWrites[root]++
-		return root, oncePerHolder(func() { s.releaseTemporaryWrite(root) }), nil
-	}
-	// A NARROWER REQUEST RECORDS ITS OWN ROOT, even when a broader temporary
-	// grant currently covers it.
-	//
-	// Borrowing a reference on the covering root kept this holder alive, which
-	// was the point, but it kept the COVERING ROOT alive to do it — and
-	// extraRoots is what validate() authorises writes from. So once the broad
-	// holder released, a caller that had asked to write one subdirectory was
-	// left holding write authority over the whole tree its neighbour had asked
-	// for, including siblings it never named. Reported by CodeRabbit, and it is
-	// the write-side twin of the read-side escalation @jatmn found: one
-	// reference cannot be both a lifetime and a capability, whichever side of
-	// the read/write boundary it sits on.
-	//
-	// Recording the requested root separately gives each holder exactly the
-	// authority it asked for and a lifetime of its own. The nesting costs an
-	// extra entry in extraRoots while both are live, which is redundant but not
-	// wrong — the broader root already permits everything the narrower one does.
 	s.extraRoots = append(s.extraRoots, root)
-	s.tempWrites[root] = 1
-	return root, oncePerHolder(func() { s.releaseTemporaryWrite(root) }), nil
+	return root, func() { s.removeWriteRoot(root) }, nil
 }
 
-// releaseTemporaryRead drops ONE holder's reference and removes the root only
-// when the last one is gone.
-//
-// The count alone cannot make this safe, and an earlier comment here claimed it
-// could — that each undo is called exactly once, and flooring at zero handled
-// the rest. Flooring stops the count going negative; it does not stop one
-// holder's second call consuming a DIFFERENT holder's reference. With two
-// readers, calling the first's undo twice took the count 2 -> 1 -> 0 and removed
-// a root the second was still using. Idempotency belongs to the closure, which
-// is the thing that knows whose reference it is, so every undo handed out is
-// wrapped in oncePerHolder.
-func (s *Scope) releaseTemporaryRead(root string) {
+func (s *Scope) writeRootCoversLocked(root string) bool {
+	for _, existing := range append([]string{s.workspaceRoot}, s.extraRoots...) {
+		if pathWithinRoot(existing, root) {
+			return true
+		}
+	}
+	return false
+}
+
+func (s *Scope) removeReadRoot(root string) {
 	s.mu.Lock()
-	remaining, tracked := s.tempReads[root]
-	if !tracked {
-		s.mu.Unlock()
-		return
-	}
-	remaining--
-	if remaining > 0 {
-		s.tempReads[root] = remaining
-		s.mu.Unlock()
-		return
-	}
-	// Both mutations under ONE hold. Dropping the lock between them opened a
-	// window where the root was still in readRoots but no longer in tempReads:
-	// a concurrent AddTemporaryRead landing there reads it as a PERMANENT root,
-	// hands its caller a no-op undo, and then this call strips the root — so
-	// that caller believes it holds access it has already silently lost.
-	delete(s.tempReads, root)
+	defer s.mu.Unlock()
 	s.readRoots = removeScopeRoot(s.readRoots, root)
-	s.mu.Unlock()
 }
 
-// releaseTemporaryWrite is releaseTemporaryRead for write roots. Two functions
-// rather than one generic helper because they guard different slices and the
-// generic version would take the slice by name — which is how the wrong one
-// gets passed.
-func (s *Scope) releaseTemporaryWrite(root string) {
+func (s *Scope) removeWriteRoot(root string) {
 	s.mu.Lock()
-	remaining, tracked := s.tempWrites[root]
-	if !tracked {
-		s.mu.Unlock()
-		return
-	}
-	remaining--
-	if remaining > 0 {
-		s.tempWrites[root] = remaining
-		s.mu.Unlock()
-		return
-	}
-	// Same single-hold rule as releaseTemporaryRead above.
-	delete(s.tempWrites, root)
+	defer s.mu.Unlock()
 	s.extraRoots = removeScopeRoot(s.extraRoots, root)
-	s.mu.Unlock()
-}
-
-// oncePerHolder makes one holder's undo safe to call more than once. The
-// reference it drops is that holder's own, so a second call must do nothing
-// rather than reach into the shared count and take somebody else's.
-func oncePerHolder(release func()) func() {
-	var once sync.Once
-	return func() { once.Do(release) }
 }
 
 func removeScopeRoot(roots []string, root string) []string {

internal/sandbox/scope_extra_read_test.go

@@ -1,56 +0,0 @@
-package sandbox
-
-import (
-	"path/filepath"
-	"testing"
-)
-
-// THE ANTI-ESCALATION PROPERTY. A read grant (AddRead, where --add-read-dir lands)
-// is READABLE but NOT WRITABLE. This is what makes propagating a parent's
-// request_permissions read grant to a child safe: the child can audit the granted
-// path but cannot modify it. Emitting the grant as a WRITE root (--add-dir) would
-// break exactly this.
-func TestAReadGrantIsReadableButNotWritable(t *testing.T) {
-	scope, granted := grantOutsideDefaults(t)
-	root, err := scope.AddRead(granted)
-	if err != nil {
-		t.Fatalf("AddRead: %v", err)
-	}
-	target := filepath.Join(root, "audit-me.go")
-
-	if block := scope.validateRead(target); block != nil {
-		t.Fatalf("a read grant did not allow READING %q: %v — the audit would fail 'outside the workspace'", target, block)
-	}
-	if block := scope.validate(target); block == nil {
-		t.Fatalf("a read grant ALLOWED WRITING %q — a read grant escalated to write", target)
-	}
-}
-
-// grantOutsideDefaults returns a scope and a directory that scope does not
-// already cover, both under test-owned storage.
-//
-// THE CAUSE, NOT THE SYMPTOM. NewScope seeds the system temporary directory as a
-// permanent write root, so a plain t.TempDir() grant is writable before any
-// grant exists and the anti-escalation assertions below prove nothing. The first
-// fix placed the fixture under os.UserHomeDir() to find ground the defaults do
-// not own. That worked and bought two problems: a hermetic runner may expose
-// HOME read-only, so these tests failed at MkdirTemp before asserting anything,
-// and on an ordinary machine they wrote into the developer's real home and left
-// zero-scope-* debris whenever a run was interrupted. Reported by @jatmn.
-//
-// Building the Scope directly removes the seeded defaults, which is what made
-// HOME necessary in the first place. t.TempDir() is then outside by
-// construction, the fixture is hermetic, and nothing touches HOME.
-func grantOutsideDefaults(t *testing.T) (*Scope, string) {
-	t.Helper()
-	workspace := resolvedFixturePath(t, t.TempDir())
-	granted := resolvedFixturePath(t, t.TempDir())
-	scope := &Scope{workspaceRoot: workspace}
-	// PROVED AGAINST THIS SCOPE. The point of the helper is that the grant is
-	// what changes access, so the target has to begin unauthorised — asserted
-	// here once rather than trusted in every caller.
-	if scope.validate(filepath.Join(granted, "probe.txt")) == nil {
-		t.Fatalf("%s is writable before any grant exists; the assertions below would prove nothing", granted)
-	}
-	return scope, granted
-}

internal/sandbox/scope_temp_refcount_test.go

@@ -1,595 +0,0 @@
-package sandbox
-
-import (
-	"os"
-	"path/filepath"
-	"slices"
-	"sync"
-	"testing"
-)
-
-// scopeOutsideDefaults builds a Scope directly instead of through NewScope.
-//
-// NewScope adds the system temp directory as a write root, so a target under
-// t.TempDir() is already covered and AddTemporaryRead returns before it ever
-// touches the refcount. A test built that way exercises none of this and passes
-// against the bug — which is how the first version of this test passed.
-func scopeOutsideDefaults(t *testing.T) (*Scope, string) {
-	t.Helper()
-	workspace := t.TempDir()
-	target := filepath.Join(t.TempDir(), "shared")
-	if err := os.MkdirAll(target, 0o700); err != nil {
-		t.Fatalf("mkdir target: %v", err)
-	}
-	// Built directly, NOT via NewScope: real directories are needed because
-	// normalizeScopeRoot requires them to exist, but NewScope's default temp
-	// write root would then cover the target and short-circuit the path.
-	return &Scope{workspaceRoot: workspace}, target
-}
-
-// The refcount and the root list have to move together.
-//
-// Release used to delete the refcount, drop the lock, then strip the root in a
-// second acquisition. In that window the root was still in readRoots but no
-// longer in tempReads, so a concurrent AddTemporaryRead read it as a PERMANENT
-// root and handed its caller a no-op undo — then the release stripped it and
-// that caller silently lost access it believed it held.
-func TestReleasingATemporaryReadCannotStripALiveGrant(t *testing.T) {
-	scope, target := scopeOutsideDefaults(t)
-
-	// First holder establishes the root.
-	first, releaseFirst, err := scope.AddTemporaryRead(target)
-	if err != nil {
-		t.Fatalf("AddTemporaryRead: %v", err)
-	}
-	if len(scope.tempReads) == 0 {
-		t.Fatal("precondition: the grant should be refcounted, not covered by a default root")
-	}
-
-	// Second holder takes a reference on the same root.
-	second, releaseSecond, err := scope.AddTemporaryRead(target)
-	if err != nil {
-		t.Fatalf("AddTemporaryRead (second): %v", err)
-	}
-
-	// The first holder leaving must not revoke the second's access.
-	releaseFirst()
-	if block := scope.validateRead(second); block != nil {
-		t.Fatalf("the second holder lost its grant when the first released: %v", block)
-	}
-
-	// Only the last release retires the root.
-	releaseSecond()
-	if block := scope.validateRead(first); block == nil {
-		t.Error("the root outlived its last holder")
-	}
-}
-
-// Under contention the same invariant has to hold: while a grant is live, its
-// root is readable.
-func TestTemporaryReadGrantsSurviveConcurrentReleases(t *testing.T) {
-	scope, target := scopeOutsideDefaults(t)
-
-	var wg sync.WaitGroup
-	var mu sync.Mutex
-	var failures []string
-
-	for i := 0; i < 24; i++ {
-		wg.Add(1)
-		go func() {
-			defer wg.Done()
-			for j := 0; j < 200; j++ {
-				granted, undo, err := scope.AddTemporaryRead(target)
-				if err != nil {
-					mu.Lock()
-					failures = append(failures, "AddTemporaryRead: "+err.Error())
-					mu.Unlock()
-					return
-				}
-				if block := scope.validateRead(granted); block != nil {
-					mu.Lock()
-					failures = append(failures, "root not readable while a grant was live")
-					mu.Unlock()
-				}
-				undo()
-			}
-		}()
-	}
-	wg.Wait()
-
-	if len(failures) > 0 {
-		t.Fatalf("%d failures, first: %s", len(failures), failures[0])
-	}
-}
-
-// A read covered by a TEMPORARY WRITE root must take a reference too.
-//
-// permanentWriteRootCoversLocked scans extraRoots, and AddTemporaryWrite appends
-// temporary write roots there — so "covered by a write root" does not mean
-// "covered permanently". Without a reference the write holder's cleanup silently
-// revoked the reader's access: the same defect the refcount closes, reached
-// across the read/write boundary instead of within one side of it.
-func TestAReadCoveredByATemporaryWriteSurvivesItsRelease(t *testing.T) {
-	workspace := t.TempDir()
-	outer := filepath.Join(t.TempDir(), "outer")
-	inner := filepath.Join(outer, "inner")
-	if err := os.MkdirAll(inner, 0o700); err != nil {
-		t.Fatal(err)
-	}
-	// Built directly for the same reason scopeOutsideDefaults is: NewScope's
-	// default temp write root would cover the fixture and short-circuit this.
-	scope := &Scope{workspaceRoot: workspace}
-
-	_, releaseWrite, err := scope.AddTemporaryWrite(outer)
-	if err != nil {
-		t.Fatalf("temporary write: %v", err)
-	}
-	readRoot, releaseRead, err := scope.AddTemporaryRead(inner)
-	if err != nil {
-		t.Fatalf("temporary read: %v", err)
-	}
-
-	covered := func() bool {
-		for _, root := range scope.ReadRoots() {
-			if pathWithinRoot(root, readRoot) {
-				return true
-			}
-		}
-		return false
-	}
-	if !covered() {
-		t.Fatal("the reader did not hold access before any release")
-	}
-
-	// The WRITE holder finishes first; the reader has not released.
-	releaseWrite()
-	if !covered() {
-		t.Errorf("the write holder's cleanup revoked a live read grant on %s", readRoot)
-	}
-
-	// And once the reader releases too, the root is genuinely gone.
-	releaseRead()
-	if covered() {
-		t.Errorf("the root outlived its last holder: %v", scope.ReadRoots())
-	}
-}
-
-func hasExtraRoot(scope *Scope, root string) bool {
-	for _, existing := range writeRootsBeyondWorkspace(scope) {
-		if existing == root {
-			return true
-		}
-	}
-	return false
-}
-
-// A PERMANENT GRANT MUST OUTLIVE THE TEMPORARY ONE IT LANDED ON TOP OF.
-//
-// extraRoots holds temporary write roots alongside permanent ones, so Add asked
-// only "is this already covered" — and a session-scoped grant made while a
-// temporary holder happened to cover the path recorded nothing, then vanished
-// when that holder released. Outliving the request that prompted it is the
-// entire difference between Add and AddTemporaryWrite.
-func TestAPermanentGrantSurvivesTheTemporaryOneItCovered(t *testing.T) {
-	t.Run("write, same root", func(t *testing.T) {
-		scope, _, outside := scopeOutsideRoots(t)
-		_, releaseTemp, err := scope.AddTemporaryWrite(outside)
-		if err != nil {
-			t.Fatal(err)
-		}
-		if _, err := scope.Add(outside); err != nil {
-			t.Fatal(err)
-		}
-		releaseTemp()
-		if !hasExtraRoot(scope, outside) {
-			t.Error("the temporary holder's release revoked a permanent write grant")
-		}
-	})
-
-	t.Run("read, same root", func(t *testing.T) {
-		scope, _, outside := scopeOutsideRoots(t)
-		_, releaseTemp, err := scope.AddTemporaryRead(outside)
-		if err != nil {
-			t.Fatal(err)
-		}
-		if _, err := scope.AddRead(outside); err != nil {
-			t.Fatal(err)
-		}
-		releaseTemp()
-		if !hasReadRoot(scope, outside) {
-			t.Error("the temporary holder's release revoked a permanent read grant")
-		}
-	})
-
-	// The nested shape: a BROAD temporary root covering a NARROW permanent one.
-	// Promoting in place cannot help here — the narrow root has to be recorded
-	// in its own right, or it goes when the broad one does.
-	t.Run("broad temporary over narrow permanent", func(t *testing.T) {
-		scope, _, outside := scopeOutsideRoots(t)
-		inner := filepath.Join(outside, "inner")
-		if err := os.MkdirAll(inner, 0o700); err != nil {
-			t.Fatal(err)
-		}
-		_, releaseBroad, err := scope.AddTemporaryWrite(outside)
-		if err != nil {
-			t.Fatal(err)
-		}
-		if _, err := scope.Add(inner); err != nil {
-			t.Fatal(err)
-		}
-		releaseBroad()
-		covered := false
-		for _, existing := range writeRootsBeyondWorkspace(scope) {
-			if pathWithinRoot(existing, inner) {
-				covered = true
-			}
-		}
-		if !covered {
-			t.Error("a narrower permanent grant died with the broader temporary root it sat under")
-		}
-	})
-
-	// THE READ MIRROR OF BOTH SHAPES ABOVE. AddRead makes two claims that the
-	// subtests so far only made for Add: the loop over extraRoots skips coverage
-	// that is a temporary WRITE, and the loop over readRoots skips coverage that
-	// is a temporary READ. Each claim is a separate branch, and neither was
-	// exercised from the read side.
-	t.Run("permanent read under a temporary write", func(t *testing.T) {
-		scope, _, outside := scopeOutsideRoots(t)
-		_, releaseWrite, err := scope.AddTemporaryWrite(outside)
-		if err != nil {
-			t.Fatal(err)
-		}
-		if _, err := scope.AddRead(outside); err != nil {
-			t.Fatal(err)
-		}
-		releaseWrite()
-		if !hasReadRoot(scope, outside) {
-			t.Error("a temporary write holder's release revoked a permanent read grant")
-		}
-	})
-
-	t.Run("broad temporary read over narrow permanent read", func(t *testing.T) {
-		scope, _, outside := scopeOutsideRoots(t)
-		inner := filepath.Join(outside, "inner")
-		if err := os.MkdirAll(inner, 0o700); err != nil {
-			t.Fatal(err)
-		}
-		_, releaseBroad, err := scope.AddTemporaryRead(outside)
-		if err != nil {
-			t.Fatal(err)
-		}
-		if _, err := scope.AddRead(inner); err != nil {
-			t.Fatal(err)
-		}
-		releaseBroad()
-		if block := scope.validateRead(filepath.Join(inner, "audit-me.go")); block != nil {
-			t.Errorf("a narrower permanent read died with the broader temporary read it sat under: %v", block)
-		}
-	})
-}
-
-// ONE HOLDER'S UNDO DROPS ONE HOLDER'S REFERENCE, HOWEVER OFTEN IT IS CALLED.
-//
-// The count flooring at zero stops it going negative; it does not stop a
-// holder's second call consuming somebody else's reference. With two readers,
-// calling the first's undo twice took the count 2 -> 1 -> 0 and removed a root
-// the second was still using — the exact revocation this refcount exists to
-// prevent, reached through a duplicate call rather than a sibling's cleanup.
-// Deferred cleanups in a retry path are how a real caller does this by accident.
-func TestOneHoldersUndoIsIdempotent(t *testing.T) {
-	scope, workspace, outside := scopeOutsideRoots(t)
-	_, undoFirst, err := scope.AddTemporaryRead(outside)
-	if err != nil {
-		t.Fatal(err)
-	}
-	_, undoSecond, err := scope.AddTemporaryRead(outside)
-	if err != nil {
-		t.Fatal(err)
-	}
-	undoFirst()
-	undoFirst()
-	undoFirst()
-	if !hasReadRoot(scope, outside) {
-		t.Fatal("repeated calls to one holder's undo revoked a live holder's access")
-	}
-	undoSecond()
-	if hasReadRoot(scope, outside) {
-		t.Error("the root outlived its last holder")
-	}
-
-	// The write side takes the same rule. Built directly for the same reason the
-	// helper is: NewScope would seed the system temp directory as a permanent
-	// write root, which already covers this fixture and makes the grant vacuous.
-	writeScope := &Scope{workspaceRoot: workspace}
-	_, undoWriteFirst, err := writeScope.AddTemporaryWrite(outside)
-	if err != nil {
-		t.Fatal(err)
-	}
-	_, undoWriteSecond, err := writeScope.AddTemporaryWrite(outside)
-	if err != nil {
-		t.Fatal(err)
-	}
-	undoWriteFirst()
-	undoWriteFirst()
-	if !hasExtraRoot(writeScope, outside) {
-		t.Fatal("repeated calls to one write holder's undo revoked a live holder's access")
-	}
-	undoWriteSecond()
-	if hasExtraRoot(writeScope, outside) {
-		t.Error("the write root outlived its last holder")
-	}
-}
-
-// temporaryWriteFixture builds a nested pair of real directories and a scope
-// that covers neither: an OUTER directory a temporary write grant will take,
-// and an INNER one below it that a temporary read grant will ask for.
-//
-// Built directly rather than through NewScope, for the reason
-// scopeOutsideDefaults documents: NewScope seeds the system temp directory as a
-// PERMANENT write root, which would cover the whole fixture and send every
-// branch under test down the "genuinely permanent" path instead. Both paths are
-// returned symlink-resolved because normalizeScopeRoot resolves what it stores,
-// and on macOS the fixture's /var spelling is a symlink to /private/var.
-func temporaryWriteFixture(t *testing.T) (scope *Scope, workspace, outer, inner string) {
-	t.Helper()
-	outer = filepath.Join(t.TempDir(), "outer")
-	inner = filepath.Join(outer, "inner")
-	if err := os.MkdirAll(inner, 0o700); err != nil {
-		t.Fatal(err)
-	}
-	workspace = resolvedFixturePath(t, t.TempDir())
-	return &Scope{workspaceRoot: workspace}, workspace, resolvedFixturePath(t, outer), resolvedFixturePath(t, inner)
-}
-
-func resolvedFixturePath(t *testing.T, path string) string {
-	t.Helper()
-	resolved, err := filepath.EvalSymlinks(path)
-	if err != nil {
-		t.Fatalf("resolve fixture %s: %v", path, err)
-	}
-	return resolved
-}
-
-// A READER MUST NOT INHERIT ITS WRITER'S AUTHORITY.
-//
-// The reader's dependency on a covering TEMPORARY WRITE root was recorded as a
-// reference on that root — one reference standing for both the lifetime and the
-// capability. Release the WRITER first and the reference kept the path in
-// extraRoots, which is the list Roots() feeds validate(), so the surviving
-// read-only holder could WRITE anywhere below a write grant that had already
-// ended — including paths it never asked to read.
-//
-// This is TestAReadGrantIsReadableButNotWritable's property for temporary
-// grants: read authority stays read authority, whichever holder leaves first.
-func TestAReaderOutlivingItsWriterKeepsReadAuthorityOnly(t *testing.T) {
-	t.Run("the writer releases first", func(t *testing.T) {
-		scope, workspace, outer, inner := temporaryWriteFixture(t)
-
-		writeRoot, releaseWrite, err := scope.AddTemporaryWrite(outer)
-		if err != nil {
-			t.Fatalf("temporary write: %v", err)
-		}
-		if writeRoot != outer {
-			t.Fatalf("temporary write granted %q, want %q", writeRoot, outer)
-		}
-		readRoot, releaseRead, err := scope.AddTemporaryRead(inner)
-		if err != nil {
-			t.Fatalf("temporary read: %v", err)
-		}
-		if readRoot != inner {
-			t.Fatalf("temporary read granted %q, want %q", readRoot, inner)
-		}
-		// The reader holds a read root of its own and NO reference on the write
-		// root. Both halves matter: the first is what survives the writer, the
-		// second is what stops the write root surviving with it.
-		//
-		// Errorf, not Fatalf: these say WHY the behavior below breaks, and a
-		// bookkeeping check that aborts the run hides the behavior it explains.
-		scope.mu.RLock()
-		writeHolders := scope.tempWrites[outer]
-		readHolders := scope.tempReads[inner]
-		scope.mu.RUnlock()
-		if writeHolders != 1 {
-			t.Errorf("tempWrites[%s] = %d, want 1: the reader took a reference on the WRITE root", outer, writeHolders)
-		}
-		if readHolders != 1 {
-			t.Errorf("tempReads[%s] = %d, want 1: the reader kept no read root of its own", inner, readHolders)
-		}
-
-		// The WRITE holder finishes; only the read-only holder is left.
-		releaseWrite()
-
-		if got := writeRootsBeyondWorkspace(scope); len(got) != 0 {
-			t.Errorf("ExtraRoots() = %v, want none: the reader held the write root open", got)
-		}
-		if got, want := scope.ReadRoots(), []string{workspace, inner}; !slices.Equal(got, want) {
-			t.Errorf("ReadRoots() = %v, want %v", got, want)
-		}
-
-		target := filepath.Join(inner, "audit-me.go")
-		if block := scope.validateRead(target); block != nil {
-			t.Errorf("the writer's cleanup revoked a live read grant on %q: %v", target, block)
-		}
-		block := scope.validate(target)
-		if block == nil {
-			t.Fatalf("a read-only holder may still WRITE %q after the write grant ended", target)
-		}
-		if block.Code != BlockOutsideWorkspace {
-			t.Errorf("write block code = %q, want %q", block.Code, BlockOutsideWorkspace)
-		}
-		if block.Path != target {
-			t.Errorf("write block path = %q, want %q", block.Path, target)
-		}
-		// The escalation was never confined to the path the reader asked for —
-		// a borrowed reference carries the whole covering root — so a sibling
-		// the reader never named has to be denied too.
-		sibling := filepath.Join(outer, "sibling.txt")
-		if block := scope.validate(sibling); block == nil {
-			t.Errorf("a read-only holder of %q may still WRITE %q, which it never asked to read", inner, sibling)
-		}
-
-		releaseRead()
-		if got, want := scope.ReadRoots(), []string{workspace}; !slices.Equal(got, want) {
-			t.Errorf("ReadRoots() = %v, want %v: the read root outlived its last holder", got, want)
-		}
-	})
-
-	// A CONTROL, NOT COVERAGE FOR THE FINDING. This subtest passes on the
-	// unfixed tree too — the escalation needs the WRITER to go first, which the
-	// subtest above exercises. It earns its place by pinning that the opposite
-	// release order was not broken while fixing the dangerous one, and it is
-	// labelled so nobody counts it as evidence the finding is closed.
-	t.Run("the reader releases first (control: passes unfixed)", func(t *testing.T) {
-		scope, _, outer, inner := temporaryWriteFixture(t)
-
-		_, releaseWrite, err := scope.AddTemporaryWrite(outer)
-		if err != nil {
-			t.Fatalf("temporary write: %v", err)
-		}
-		_, releaseRead, err := scope.AddTemporaryRead(inner)
-		if err != nil {
-			t.Fatalf("temporary read: %v", err)
-		}
-
-		// The other order, which the fix must not break: the writer keeps FULL
-		// authority for as long as it holds the grant.
-		releaseRead()
-		buildLog := filepath.Join(outer, "build.log")
-		if block := scope.validate(buildLog); block != nil {
-			t.Fatalf("the reader's cleanup revoked the live write grant on %q: %v", buildLog, block)
-		}
-		if got, want := writeRootsBeyondWorkspace(scope), []string{outer}; !slices.Equal(got, want) {
-			t.Errorf("ExtraRoots() = %v, want %v", got, want)
-		}
-
-		releaseWrite()
-		if block := scope.validate(buildLog); block == nil {
-			t.Errorf("the write root %q outlived its only holder", outer)
-		}
-		if block := scope.validateRead(filepath.Join(inner, "audit-me.go")); block == nil {
-			t.Errorf("the read root %q outlived its only holder", inner)
-		}
-	})
-}
-
-// A NARROWER WRITE HOLDER MUST NOT INHERIT ITS NEIGHBOUR'S TREE.
-//
-// The write-side twin of the read-side escalation above, and the same root
-// cause: a nested holder used to take a reference on the BROADER temporary root
-// that happened to cover it. That kept the nested holder alive, which was the
-// point, but it kept the covering root alive to do it — and extraRoots is what
-// validate() authorises writes from. Once the broad holder released, a caller
-// that had asked for one subdirectory held write authority over the whole tree,
-// siblings included. Reported by CodeRabbit.
-func TestANestedWriteHolderKeepsOnlyItsOwnSubtree(t *testing.T) {
-	scope, _, outsideBase := scopeOutsideRoots(t)
-	outer := filepath.Join(outsideBase, "outer")
-	inner := filepath.Join(outer, "inner")
-	sibling := filepath.Join(outer, "sibling")
-	for _, dir := range []string{outer, inner, sibling} {
-		if err := os.MkdirAll(dir, 0o700); err != nil {
-			t.Fatal(err)
-		}
-	}
-	_, releaseOuter, err := scope.AddTemporaryWrite(outer)
-	if err != nil {
-		t.Fatalf("temporary write on the broad root: %v", err)
-	}
-	_, releaseInner, err := scope.AddTemporaryWrite(inner)
-	if err != nil {
-		t.Fatalf("temporary write on the nested root: %v", err)
-	}
-
-	// THE BROAD HOLDER GOES FIRST — the nested holder outliving it is what
-	// exposes whose authority it is actually holding.
-	releaseOuter()
-
-	if block := scope.validate(filepath.Join(inner, "mine.txt")); block != nil {
-		t.Errorf("the nested holder lost the subtree it asked for: %v", block.Reason)
-	}
-	if block := scope.validate(filepath.Join(sibling, "not-mine.txt")); block == nil {
-		t.Error("the nested holder can write a SIBLING it never asked for: the broad holder's authority outlived the broad holder")
-	}
-	if block := scope.validate(filepath.Join(outer, "not-mine.txt")); block == nil {
-		t.Error("the nested holder can write the covering root itself after its holder released")
-	}
-
-	releaseInner()
-	if block := scope.validate(filepath.Join(inner, "mine.txt")); block == nil {
-		t.Error("the nested root outlived its only holder")
-	}
-}
-
-// The opposite order, as a control: the nested holder releasing first must not
-// disturb the broad holder that is still live.
-func TestANestedWriteHolderReleasingFirstLeavesTheBroadGrant(t *testing.T) {
-	scope, _, outsideBase := scopeOutsideRoots(t)
-	outer := filepath.Join(outsideBase, "outer")
-	inner := filepath.Join(outer, "inner")
-	for _, dir := range []string{outer, inner} {
-		if err := os.MkdirAll(dir, 0o700); err != nil {
-			t.Fatal(err)
-		}
-	}
-	_, releaseOuter, err := scope.AddTemporaryWrite(outer)
-	if err != nil {
-		t.Fatal(err)
-	}
-	_, releaseInner, err := scope.AddTemporaryWrite(inner)
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	releaseInner()
-	if block := scope.validate(filepath.Join(inner, "still-ok.txt")); block != nil {
-		t.Errorf("the nested holder's release revoked the broad holder's coverage: %v", block.Reason)
-	}
-	releaseOuter()
-	if block := scope.validate(filepath.Join(inner, "gone.txt")); block == nil {
-		t.Error("the tree outlived every holder")
-	}
-}
-
-// TWO HOLDERS OF THE SAME ROOT SHARE ONE ENTRY. Only an exact match shares —
-// a narrower request must not, which is what the escalation test above pins.
-func TestTwoHoldersOfTheSameWriteRootShareOneEntry(t *testing.T) {
-	scope, _, outsideBase := scopeOutsideRoots(t)
-	target := filepath.Join(outsideBase, "shared")
-	if err := os.MkdirAll(target, 0o700); err != nil {
-		t.Fatal(err)
-	}
-	_, releaseFirst, err := scope.AddTemporaryWrite(target)
-	if err != nil {
-		t.Fatal(err)
-	}
-	_, releaseSecond, err := scope.AddTemporaryWrite(target)
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	releaseFirst()
-	if block := scope.validate(filepath.Join(target, "still-held.txt")); block != nil {
-		t.Errorf("one holder's release revoked the other's grant on the same root: %v", block.Reason)
-	}
-	releaseSecond()
-	if block := scope.validate(filepath.Join(target, "gone.txt")); block == nil {
-		t.Error("the shared root outlived both holders")
-	}
-}
-
-// writeRootsBeyondWorkspace is Roots() without the workspace entry.
-//
-// These tests need to see which BEYOND-WORKSPACE write roots a scope currently
-// holds. There was an ExtraRoots() accessor that answered exactly this, but it
-// had no production caller — it belongs to #829's child-grant propagation, whose
-// consumer side is not on this branch, and @jatmn was right that carrying it here
-// leaves unrelated production surface in a PR scoped to refcounting. The
-// inspection is a test concern, so it lives in the tests.
-func writeRootsBeyondWorkspace(scope *Scope) []string {
-	all := scope.Roots()
-	if len(all) == 0 {
-		return nil
-	}
-	return append([]string(nil), all[1:]...)
-}

internal/sandbox/scope_temporary_test.go

@@ -1,366 +0,0 @@
-package sandbox
-
-import (
-	"os"
-	"path/filepath"
-	"sync"
-	"testing"
-)
-
-// scopeOutsideRoots builds a workspace and an unrelated directory that no
-// default write root already covers.
-//
-// NOT t.TempDir(). /tmp and $TMPDIR are default write roots, so a temporary
-// grant for a path under one is a no-op — every assertion here would pass
-// against code that grants nothing at all. That is RULES §2.3 in its exact
-// form, and it caught the first version of this test.
-// scopeOutsideRoots builds a workspace and a directory outside it, both under
-// test-owned storage, and returns a Scope that treats the second as genuinely
-// outside.
-//
-// THE FIXTURE PROBLEM AND ITS ACTUAL CAUSE. NewScope seeds the system temporary
-// directory as a permanent write root, so an ordinary t.TempDir() grant is
-// covered before any temporary grant exists and every assertion built on it is
-// vacuous. The first fix for that reached into os.UserHomeDir() to find ground
-// the defaults do not already own — which worked, and bought two new problems:
-// a hermetic runner may expose HOME read-only, so the tests failed at MkdirTemp
-// before asserting anything; and on an ordinary machine they wrote fixtures into
-// the developer's real home and left zeromax-scope-* debris behind whenever a
-// run was interrupted. Reported by @jatmn.
-//
-// The cause is the seeded defaults, not the location, so the Scope is built
-// DIRECTLY here — the same pattern scopeOutsideDefaults and temporaryWriteFixture
-// already use. With no defaults seeded, t.TempDir() is outside by construction,
-// the fixture is hermetic, and nothing touches HOME.
-//
-// Paths are symlink-resolved because the scope stores resolved roots and macOS
-// hands out /var/... temp directories that resolve to /private/var/...; an
-// unresolved fixture path compares unequal to the root the scope just recorded.
-func scopeOutsideRoots(t *testing.T) (scope *Scope, workspace string, outside string) {
-	t.Helper()
-	workspace = resolvedFixturePath(t, t.TempDir())
-	outside = filepath.Join(resolvedFixturePath(t, t.TempDir()), "outside")
-	// FATAL, NOT SKIP. Every caller of this helper asserts an AUTHORIZATION
-	// boundary, so a skipped fixture means that assertion never ran and the build
-	// reported green anyway. t.TempDir() already failed the test if it could not
-	// provide storage, so a subdirectory failing under it is a broken machine.
-	if err := os.MkdirAll(outside, 0o700); err != nil {
-		t.Fatalf("cannot prepare %s: %v", outside, err)
-	}
-	scope = &Scope{workspaceRoot: workspace}
-	// PROVED AGAINST THIS SCOPE, not against production's default list. The point
-	// of the helper is that a grant here changes something, and the only thing
-	// that can answer that is the scope the test will actually use. Checking
-	// defaultTempWriteRoots() instead asks about a scope nobody builds here — and
-	// says "prove nothing" for a t.TempDir() path that this scope, seeded with no
-	// defaults, genuinely does not cover.
-	//
-	// Asserting the NEGATIVE up front is also what keeps every caller honest: it
-	// establishes that the target begins unauthorised, so a later success is the
-	// grant's doing and not the fixture's placement.
-	if scope.validate(filepath.Join(outside, "probe.txt")) == nil {
-		t.Fatalf("%s is writable before any grant exists, so a temporary grant here would prove nothing", outside)
-	}
-	if scope.validateRead(filepath.Join(outside, "probe.txt")) == nil {
-		t.Fatalf("%s is readable before any grant exists, so a temporary read grant here would prove nothing", outside)
-	}
-	return scope, workspace, outside
-}
-
-func hasReadRoot(scope *Scope, root string) bool {
-	for _, existing := range scope.ReadRoots() {
-		if existing == root {
-			return true
-		}
-	}
-	return false
-}
-
-// THE DEFECT: one holder's cleanup revoked another's access. Two read-only
-// tools in the same parallel batch, both blocked on the same directory, is
-// exactly this — and read-only tools are the ones the batch runs concurrently.
-func TestATemporaryReadSurvivesASiblingsCleanup(t *testing.T) {
-	scope, _, outside := scopeOutsideRoots(t)
-	// The probe that the fix must make unnecessary: without it this reads
-	// true -> false.
-	if hasReadRoot(scope, outside) {
-		t.Fatal("the outside root is already covered; this test proves nothing")
-	}
-
-	_, undoA, err := scope.AddTemporaryRead(outside)
-	if err != nil {
-		t.Fatal(err)
-	}
-	_, undoB, err := scope.AddTemporaryRead(outside)
-	if err != nil {
-		t.Fatal(err)
-	}
-	if !hasReadRoot(scope, outside) {
-		t.Fatal("the grant did not take effect")
-	}
-
-	undoA()
-	if !hasReadRoot(scope, outside) {
-		t.Fatal("A's cleanup revoked the root while B still held a grant")
-	}
-	undoB()
-	if hasReadRoot(scope, outside) {
-		t.Fatal("the root outlived its last holder")
-	}
-}
-
-// A NARROWER REQUEST KEEPS ITS OWN SUBTREE AND NOTHING WIDER.
-//
-// THIS TEST USED TO ASSERT THE OPPOSITE, and the earlier version is worth
-// recording because it is how the escalation survived a review round. It was
-// written to prove a LIFETIME property — the broad holder's cleanup must not
-// revoke a live narrow holder — and it proved that by asserting the BROAD root
-// was still present afterwards. That is the defect stated as a requirement: the
-// narrow holder was keeping its neighbour's whole tree alive in order to keep
-// itself alive, so the surviving reader could read siblings it never asked for.
-//
-// Lifetime and capability are two properties and one reference cannot carry
-// both. The assertions below name them separately: the requested path stays
-// readable while its holder lives, AND a sibling under the released broad root
-// is denied as soon as the holder that authorised it exits. Reported by @jatmn.
-func TestANarrowerReaderKeepsOnlyItsOwnSubtree(t *testing.T) {
-	scope, _, outside := scopeOutsideRoots(t)
-	nested := filepath.Join(outside, "nested")
-	sibling := filepath.Join(outside, "sibling")
-	for _, dir := range []string{nested, sibling} {
-		// FATAL, NOT SKIP. These directories are the fixture, not a precondition
-		// the environment might reasonably withhold — skipping on them reports a
-		// broken setup as a passing run.
-		if err := os.MkdirAll(dir, 0o700); err != nil {
-			t.Fatal(err)
-		}
-	}
-
-	_, undoBroad, err := scope.AddTemporaryRead(outside)
-	if err != nil {
-		t.Fatal(err)
-	}
-	_, undoNarrow, err := scope.AddTemporaryRead(nested)
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	// THE BROAD HOLDER GOES FIRST. The narrow holder outliving it is what exposes
-	// whose authority it is actually holding.
-	undoBroad()
-	if block := scope.validateRead(filepath.Join(nested, "mine.txt")); block != nil {
-		t.Errorf("the broad holder's cleanup revoked the subtree the narrow holder asked for: %v", block.Reason)
-	}
-	if block := scope.validateRead(filepath.Join(sibling, "not-mine.txt")); block == nil {
-		t.Error("the narrow reader can read a SIBLING it never asked for: the broad holder's authority outlived the broad holder")
-	}
-	if block := scope.validateRead(filepath.Join(outside, "not-mine.txt")); block == nil {
-		t.Error("the narrow reader can read the covering root itself after its holder released")
-	}
-
-	undoNarrow()
-	if block := scope.validateRead(filepath.Join(nested, "mine.txt")); block == nil {
-		t.Error("the nested root outlived its only holder")
-	}
-}
-
-// The opposite order, as a control: the narrow reader releasing first must not
-// disturb the broad reader that is still live.
-func TestANarrowerReaderReleasingFirstLeavesTheBroadGrant(t *testing.T) {
-	scope, _, outside := scopeOutsideRoots(t)
-	nested := filepath.Join(outside, "nested")
-	if err := os.MkdirAll(nested, 0o700); err != nil {
-		t.Fatal(err)
-	}
-	_, undoBroad, err := scope.AddTemporaryRead(outside)
-	if err != nil {
-		t.Fatal(err)
-	}
-	_, undoNarrow, err := scope.AddTemporaryRead(nested)
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	undoNarrow()
-	if block := scope.validateRead(filepath.Join(nested, "still-ok.txt")); block != nil {
-		t.Errorf("the narrow holder's release revoked the broad holder's coverage: %v", block.Reason)
-	}
-	undoBroad()
-	if block := scope.validateRead(filepath.Join(nested, "gone.txt")); block == nil {
-		t.Error("the tree outlived every holder")
-	}
-}
-
-// TWO READERS OF THE SAME ROOT SHARE ONE ENTRY. Only an exact match shares; a
-// narrower one never does, which is what the escalation test above pins.
-func TestTwoReadersOfTheSameRootShareOneEntry(t *testing.T) {
-	scope, _, outside := scopeOutsideRoots(t)
-	_, undoFirst, err := scope.AddTemporaryRead(outside)
-	if err != nil {
-		t.Fatal(err)
-	}
-	_, undoSecond, err := scope.AddTemporaryRead(outside)
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	undoFirst()
-	if block := scope.validateRead(filepath.Join(outside, "still-held.txt")); block != nil {
-		t.Errorf("one reader's release revoked the other's grant on the same root: %v", block.Reason)
-	}
-	undoSecond()
-	if block := scope.validateRead(filepath.Join(outside, "gone.txt")); block == nil {
-		t.Error("the shared root outlived both holders")
-	}
-}
-
-// A NARROW PERMANENT READ IS NOT BORROWED FROM A BROAD TEMPORARY ONE. The old
-// scan walked readRoots in order and stopped at the first entry covering the
-// path, so a broad TEMPORARY root earlier in the slice shadowed a narrower
-// PERMANENT one later — and the caller took a reference it did not need on a
-// grant that was about to end.
-func TestAPermanentReadIsNotShadowedByABroadTemporaryOne(t *testing.T) {
-	scope, _, outside := scopeOutsideRoots(t)
-	nested := filepath.Join(outside, "nested")
-	if err := os.MkdirAll(nested, 0o700); err != nil {
-		t.Fatal(err)
-	}
-	// The broad TEMPORARY grant is taken first, so it sits earlier in readRoots.
-	_, undoBroad, err := scope.AddTemporaryRead(outside)
-	if err != nil {
-		t.Fatal(err)
-	}
-	if _, err := scope.AddRead(nested); err != nil {
-		t.Fatal(err)
-	}
-
-	undoBroad()
-	if block := scope.validateRead(filepath.Join(nested, "mine.txt")); block != nil {
-		t.Errorf("a PERMANENT read grant died with a broad temporary one that merely preceded it: %v", block.Reason)
-	}
-}
-
-// A PERMANENT root is not refcounted and must never be removed by a temporary
-// holder's cleanup — the undo for a request it already covers is genuinely
-// nothing.
-func TestATemporaryGrantNeverRevokesAPermanentRoot(t *testing.T) {
-	scope, _, outside := scopeOutsideRoots(t)
-	if _, err := scope.AddRead(outside); err != nil {
-		t.Fatal(err)
-	}
-	_, undo, err := scope.AddTemporaryRead(outside)
-	if err != nil {
-		t.Fatal(err)
-	}
-	undo()
-	if !hasReadRoot(scope, outside) {
-		t.Fatal("a temporary holder's cleanup removed a permanent read root")
-	}
-}
-
-// The same rule for WRITE roots, or a write grant keeps the bug reads no longer
-// have.
-func TestATemporaryWriteSurvivesASiblingsCleanup(t *testing.T) {
-	scope, _, outside := scopeOutsideRoots(t)
-	covered := func() bool {
-		for _, existing := range scope.Roots() {
-			if existing == outside {
-				return true
-			}
-		}
-		return false
-	}
-	_, undoA, err := scope.AddTemporaryWrite(outside)
-	if err != nil {
-		t.Fatal(err)
-	}
-	_, undoB, err := scope.AddTemporaryWrite(outside)
-	if err != nil {
-		t.Fatal(err)
-	}
-	if !covered() {
-		t.Fatal("the write grant did not take effect")
-	}
-	undoA()
-	if !covered() {
-		t.Fatal("A's cleanup revoked the write root while B still held a grant")
-	}
-	undoB()
-	if covered() {
-		t.Fatal("the write root outlived its last holder")
-	}
-}
-
-// UNDER REAL CONCURRENCY, which is the shape the parallel tool batch produces:
-// eight holders taking and releasing the same root in overlapping windows. The
-// root must be present the whole time at least one holder has it, and gone once
-// the last releases.
-func TestConcurrentHoldersOfOneRoot(t *testing.T) {
-	scope, _, outside := scopeOutsideRoots(t)
-
-	const holders = 8
-	var wg sync.WaitGroup
-	start := make(chan struct{})
-	release := make(chan struct{})
-	// TWO PER HOLDER, because each one can report at both hasReadRoot checks. At
-	// one slot per holder the channel fills after eight reports, the ninth send
-	// blocks forever, wg.Done() is never reached and wg.Wait() hangs — so the
-	// test would DEADLOCK rather than fail in exactly the case it exists to
-	// catch, since nothing drains failures until after the wait.
-	failures := make(chan string, 2*holders)
-	// Signalled by EVERY holder once its own AddTemporaryRead has returned,
-	// failure included: the gate below waits for all of them, so a holder that
-	// returned early without signalling would hang this test rather than fail it.
-	acquired := make(chan struct{}, holders)
-	for i := 0; i < holders; i++ {
-		wg.Add(1)
-		go func() {
-			defer wg.Done()
-			<-start
-			_, undo, err := scope.AddTemporaryRead(outside)
-			acquired <- struct{}{}
-			if err != nil {
-				failures <- err.Error()
-				return
-			}
-			// Every holder must SEE its own grant for as long as it holds it.
-			if !hasReadRoot(scope, outside) {
-				failures <- "a holder could not see the root it had just been granted"
-			}
-			<-release
-			if !hasReadRoot(scope, outside) {
-				failures <- "a holder lost the root while still holding it"
-			}
-			undo()
-		}()
-	}
-	close(start)
-	// EVERY holder, not the first one. Spinning on hasReadRoot only waited for
-	// somebody to hold the root, and the spin is tight enough to win that race
-	// against the goroutines still being scheduled: measured over 200 runs, 194
-	// of them peaked at a single simultaneous holder and none ever reached
-	// eight. A test named for concurrent holders was testing one holder at a
-	// time, and would have passed against an implementation with no refcount at
-	// all. Counting the acquisitions makes the overlap real instead of hoped for.
-	for i := 0; i < holders; i++ {
-		<-acquired
-	}
-	close(release)
-	wg.Wait()
-	close(failures)
-	for failure := range failures {
-		t.Fatal(failure)
-	}
-	if hasReadRoot(scope, outside) {
-		t.Fatal("the root outlived every holder")
-	}
-	// AND THE BOOKKEEPING IS EMPTY, not merely invisible. hasReadRoot answers
-	// what a caller can see; a refcount entry left behind at zero is not visible
-	// that way and would still leak, one map entry per acquire/release cycle.
-	scope.mu.Lock()
-	leftover, stillCounted := scope.tempReads[outside]
-	scope.mu.Unlock()
-	if stillCounted {
-		t.Fatalf("the refcount table kept an entry for %q after every holder released: %v", outside, leftover)
-	}
-}

internal/swarm/lock_other.go

@@ -0,0 +1,15 @@
+//go:build !windows
+
+package swarm
+
+import (
+	"errors"
+	"os"
+)
+
+// isLockContended reports whether an O_EXCL lock-create error means the lock is
+// currently held (so the caller should retry/wait) rather than a hard failure.
+// On POSIX an existing lock surfaces only as os.ErrExist.
+func isLockContended(err error) bool {
+	return errors.Is(err, os.ErrExist)
+}

internal/swarm/lock_redirect_other_test.go

@@ -1,18 +0,0 @@
-//go:build !windows
-
-package swarm
-
-import (
-	"os"
-	"path/filepath"
-	"testing"
-)
-
-func makeRedirectedLockPath(t *testing.T, root, target string) string {
-	t.Helper()
-	lockPath := filepath.Join(root, "redirected.lock")
-	if err := os.Symlink(target, lockPath); err != nil {
-		t.Fatalf("create redirected lock path: %v", err)
-	}
-	return lockPath
-}

internal/swarm/lock_redirect_windows_test.go

@@ -1,20 +0,0 @@
-//go:build windows
-
-package swarm
-
-import (
-	"os/exec"
-	"path/filepath"
-	"strings"
-	"testing"
-)
-
-func makeRedirectedLockPath(t *testing.T, root, target string) string {
-	t.Helper()
-	linkDir := filepath.Join(root, "redirected")
-	out, err := exec.Command("cmd", "/c", "mklink", "/J", linkDir, filepath.Dir(target)).CombinedOutput()
-	if err != nil {
-		t.Fatalf("create redirected lock junction: %v %s", err, strings.TrimSpace(string(out)))
-	}
-	return filepath.Join(linkDir, filepath.Base(target))
-}

internal/swarm/lock_windows.go

@@ -0,0 +1,30 @@
+//go:build windows
+
+package swarm
+
+import (
+	"errors"
+	"os"
+	"syscall"
+)
+
+// Windows error codes that an O_EXCL create (or a racing delete) can surface
+// when another writer holds the lock file open, instead of ERROR_FILE_EXISTS.
+// Treating them as "contended" makes the lock retry/wait rather than fail the
+// whole send/read spuriously under contention.
+const (
+	errorAccessDenied     = syscall.Errno(5)  // ERROR_ACCESS_DENIED
+	errorSharingViolation = syscall.Errno(32) // ERROR_SHARING_VIOLATION
+)
+
+// isLockContended reports whether an O_EXCL lock-create error means the lock is
+// currently held (so the caller should retry/wait) rather than a hard failure.
+// On Windows a held lock can appear as ERROR_FILE_EXISTS (mapped to os.ErrExist)
+// but also as ERROR_ACCESS_DENIED / ERROR_SHARING_VIOLATION when the file is
+// concurrently open or pending deletion.
+func isLockContended(err error) bool {
+	if errors.Is(err, os.ErrExist) {
+		return true
+	}
+	return errors.Is(err, errorAccessDenied) || errors.Is(err, errorSharingViolation)
+}

internal/swarm/mailbox.go

@@ -8,6 +8,7 @@ import (
 	"path/filepath"
 	"regexp"
 	"strings"
+	"sync/atomic"
 	"time"
 
 	"github.com/Gitlawb/zero/internal/fsutil"
@@ -16,10 +17,10 @@ import (
 
 // Mailbox is a per-agent, per-team message inbox persisted as a JSON array on
 // disk at <baseDir>/<team>/inboxes/<agent>.json, written atomically under a
-// advisory lock. It is hardened for untrusted input:
+// lock file. It is hardened for untrusted input:
 //
 //   - inbox files and their parent dirs are owner-only (0600/0700);
-//   - every write takes an exclusive advisory lock (bounded retry);
+//   - every write takes an exclusive lock file (bounded retry, stale-break);
 //   - message bodies and whole inboxes are size-capped (fail closed on oversize);
 //   - team/agent names are sanitized so a name can never escape the base dir;
 //   - malformed inbox JSON is rejected rather than silently reset (fail closed).
@@ -43,6 +44,7 @@ const (
 	defaultMaxMessageBytes = 64 * 1024 // 64 KiB per message
 	defaultMaxMessages     = 1000      // per inbox
 	defaultLockTimeout     = 5 * time.Second
+	lockStaleAfter         = 30 * time.Second
 	inboxFileMode          = 0o600
 	inboxDirMode           = 0o700
 )
@@ -204,7 +206,7 @@ func (m *Mailbox) Send(team, recipient string, msg Message) error {
 	if err := m.ensureInboxDir(path); err != nil {
 		return err
 	}
-	release, err := acquireLock(m.BaseDir, path+".lock", m.lockTimeout())
+	release, err := acquireLock(path+".lock", m.lockTimeout())
 	if err != nil {
 		return err
 	}
@@ -231,12 +233,12 @@ func (m *Mailbox) ReadAndConsume(team, recipient string) ([]Message, error) {
 	if err != nil {
 		return nil, err
 	}
-	// The stable lock file lives beside the inbox; create the dir so it can be taken
+	// The lock file lives beside the inbox; create the dir so it can be taken
 	// even on first read of a not-yet-existing inbox.
 	if err := m.ensureInboxDir(path); err != nil {
 		return nil, err
 	}
-	release, err := acquireLock(m.BaseDir, path+".lock", m.lockTimeout())
+	release, err := acquireLock(path+".lock", m.lockTimeout())
 	if err != nil {
 		return nil, err
 	}
@@ -332,19 +334,63 @@ func (m *Mailbox) atomicWriteJSON(path string, data any) error {
 	return nil
 }
 
-// acquireLock takes an exclusive advisory lock through a stable lock file. It
-// retries with a short backoff until timeout. The kernel releases the lock when
-// a holder exits, so crash recovery never moves or deletes the canonical path.
-func acquireLock(root, lockPath string, timeout time.Duration) (func(), error) {
+// lockSeq makes each lock token unique within the process even when two
+// goroutines acquire in the same nanosecond.
+var lockSeq atomic.Uint64
+
+// acquireLock takes an exclusive lock by creating lockPath with O_EXCL. It
+// retries with a short backoff until timeout, breaking a lock whose file is
+// older than lockStaleAfter (so a crashed holder cannot deadlock the swarm).
+//
+// Each holder writes a unique token into the lock file and release is
+// OWNERSHIP-AWARE: it removes the lock only if it still holds our token. After a
+// stale-break another writer may legitimately own the lock; unconditionally
+// removing it would let a third writer in and create split-brain writers that
+// can corrupt or drop mailbox updates.
+func acquireLock(lockPath string, timeout time.Duration) (func(), error) {
+	token := fmt.Sprintf("%d-%d-%d", os.Getpid(), time.Now().UnixNano(), lockSeq.Add(1))
 	deadline := time.Now().Add(timeout)
 	for {
-		lock, err := lockutil.TryAcquireFileLockAt(root, lockPath)
+		f, err := os.OpenFile(lockPath, os.O_CREATE|os.O_EXCL|os.O_WRONLY, inboxFileMode)
 		if err == nil {
-			return func() { _ = lock.Release() }, nil
+			// Record our ownership token; the exclusive create already holds the
+			// lock, so a write error only weakens diagnostics, not safety.
+			_, _ = f.WriteString(token)
+			f.Close()
+			var released bool
+			return func() {
+				if released {
+					return
+				}
+				released = true
+				if data, rerr := os.ReadFile(lockPath); rerr == nil && string(data) == token {
+					_ = lockutil.RemoveLockFile(lockPath)
+				}
+			}, nil
 		}
-		if !errors.Is(err, lockutil.ErrLockHeld) {
+		if !isLockContended(err) {
 			return nil, fmt.Errorf("swarm: acquire lock: %w", err)
 		}
+		// Lock held: break it if stale via the atomic rename-with-verify in
+		// lockutil.ReclaimStaleLock (AUDIT-M13), otherwise wait.
+		if info, statErr := os.Stat(lockPath); statErr == nil && time.Since(info.ModTime()) > lockStaleAfter {
+			cleared, rerr := lockutil.ReclaimStaleLock(lockPath, token, func(reclaimedPath string) bool {
+				info, err := os.Stat(reclaimedPath)
+				return err == nil && time.Since(info.ModTime()) <= lockStaleAfter
+			})
+			if rerr != nil {
+				// Reclaim hit a hard failure: the rename aside failed outright, or a
+				// live holder's lock could not be put back (the lock path may be
+				// missing, so re-acquiring would break mutual exclusion). Fail closed
+				// instead of spinning to the deadline.
+				return nil, fmt.Errorf("swarm: reclaim stale lock: %w", rerr)
+			}
+			if cleared {
+				continue // cleared a genuinely stale lock; retry the O_EXCL create now
+			}
+			// Lost the reclaim race (or it was actually fresh) — fall through to the
+			// bounded wait instead of hot-spinning on a reclaim that never wins.
+		}
 		if time.Now().After(deadline) {
 			return nil, fmt.Errorf("swarm: timed out acquiring lock %s", filepath.Base(lockPath))
 		}

internal/swarm/mailbox_test.go

@@ -219,75 +219,64 @@ func TestMailboxRejectsSymlinkedInboxDir(t *testing.T) {
 	}
 }
 
-func TestMailboxLockReleaseKeepsStablePath(t *testing.T) {
+func TestMailboxLockReleaseIsOwnershipAware(t *testing.T) {
 	mb := newTestMailbox(t)
 	path, _ := mb.inboxPath("team", "bob")
 	if err := mb.ensureInboxDir(path); err != nil {
 		t.Fatalf("ensureInboxDir: %v", err)
 	}
 	lockPath := path + ".lock"
-	releaseA, err := acquireLock(mb.BaseDir, lockPath, time.Second)
+	// Writer A acquires the lock.
+	releaseA, err := acquireLock(lockPath, time.Second)
 	if err != nil {
 		t.Fatalf("acquire A: %v", err)
 	}
+	// Simulate a stale-break + takeover by writer B: overwrite the lock content
+	// with B's token (as a fresh acquire after a break would).
+	if err := os.WriteFile(lockPath, []byte("writer-B-token"), 0o600); err != nil {
+		t.Fatalf("simulate B takeover: %v", err)
+	}
+	// A's release must NOT delete B's lock (ownership-aware).
 	releaseA()
 	if _, err := os.Stat(lockPath); err != nil {
-		t.Fatalf("release removed stable advisory-lock path: %v", err)
+		t.Fatalf("A's release deleted B's lock (split-brain): %v", err)
 	}
+	// B's own release removes it.
+	os.Remove(lockPath)
 }
 
-func TestAcquireLockIgnoresOldUnlockedFile(t *testing.T) {
-	// A crashed holder can leave an old file behind, but the kernel releases its
-	// advisory lock. Acquisition must succeed without renaming the stable path.
+func TestAcquireLockReclaimsStaleLock(t *testing.T) {
+	// A crashed holder's stale lock (old mtime) must be reclaimed via the atomic
+	// rename-with-verify path, leaving no sidelined .stale.* file (AUDIT-M13).
 	lockPath := filepath.Join(t.TempDir(), "x.lock")
 	if err := os.WriteFile(lockPath, []byte("dead-holder"), 0o600); err != nil {
-		t.Fatalf("seed old lock metadata: %v", err)
+		t.Fatalf("seed stale lock: %v", err)
 	}
-	old := time.Now().Add(-time.Hour)
+	old := time.Now().Add(-2 * lockStaleAfter)
 	if err := os.Chtimes(lockPath, old, old); err != nil {
 		t.Fatalf("chtimes: %v", err)
 	}
-	release, err := acquireLock(filepath.Dir(lockPath), lockPath, time.Second)
+	release, err := acquireLock(lockPath, time.Second)
 	if err != nil {
-		t.Fatalf("acquire over old unlocked file: %v", err)
+		t.Fatalf("acquireLock should reclaim a genuinely stale lock, got %v", err)
 	}
 	release()
-	if _, err := os.Stat(lockPath); err != nil {
-		t.Fatalf("stable lock path missing after release: %v", err)
+	if matches, _ := filepath.Glob(lockPath + ".stale.*"); len(matches) != 0 {
+		t.Fatalf("reclaim left sidelined files: %v", matches)
 	}
 }
 
-func TestAcquireLockDoesNotBreakHeldLock(t *testing.T) {
-	// File age is irrelevant while the kernel reports an active holder.
+func TestAcquireLockDoesNotBreakFreshLock(t *testing.T) {
+	// A fresh, held lock (recent mtime) must never be broken — the stale-break must
+	// not steal a live lock (AUDIT-M13).
 	lockPath := filepath.Join(t.TempDir(), "x.lock")
-	release, err := acquireLock(filepath.Dir(lockPath), lockPath, time.Second)
+	release, err := acquireLock(lockPath, time.Second)
 	if err != nil {
 		t.Fatalf("first acquire: %v", err)
 	}
 	defer release()
-	if _, err := acquireLock(filepath.Dir(lockPath), lockPath, 50*time.Millisecond); err == nil {
-		t.Fatal("acquireLock admitted a second holder")
-	}
-}
-
-func TestAcquireLockRefusesRedirectedPath(t *testing.T) {
-	root := t.TempDir()
-	target := filepath.Join(t.TempDir(), "target")
-	const sentinel = "do not overwrite"
-	if err := os.WriteFile(target, []byte(sentinel), 0o600); err != nil {
-		t.Fatal(err)
-	}
-	lockPath := makeRedirectedLockPath(t, root, target)
-	if release, err := acquireLock(root, lockPath, time.Second); err == nil {
-		release()
-		t.Fatal("acquireLock followed a redirected lock path")
-	}
-	data, err := os.ReadFile(target)
-	if err != nil {
-		t.Fatal(err)
-	}
-	if string(data) != sentinel {
-		t.Fatalf("redirected target was modified: %q", data)
+	if _, err := acquireLock(lockPath, 50*time.Millisecond); err == nil {
+		t.Fatal("acquireLock broke a fresh, held lock (split-brain risk)")
 	}
 }
 

internal/tools/edit_file.go

@@ -140,6 +140,7 @@ func (tool editFileTool) RunWithOptions(ctx context.Context, args map[string]any
 		return errorResult(fileUnseenMessage(relativePath))
 	}
 
+	previouslySeenWhole := options.FileTracker.SeenWhole(absolutePath)
 	updated := strings.Replace(content, oldString, newString, 1)
 	replacedCount := 1
 	if replaceAll {
@@ -164,28 +165,15 @@ func (tool editFileTool) RunWithOptions(ctx context.Context, args map[string]any
 	// Re-baseline to the content we just wrote so subsequent edits in this session
 	// compare against the current on-disk state, not the pre-edit version.
 	newInfo, _ := os.Stat(absolutePath)
+	options.FileTracker.Record(absolutePath, []byte(updated), newInfo)
 	if updated == modelKnownContent {
-		// OUR edit, so we know precisely which lines moved: RecordEdit carries
-		// across the reads this edit did not disturb instead of dropping them.
-		//
-		// Record would drop all of them, and did — a file read in three pieces
-		// lost every piece to a single two-line edit, and the next six edits into
-		// regions that had been read were refused as unseen. See RecordEdit.
-		//
-		// This SUBSUMES the previouslySeenWhole special-case #956 added here.
-		// That branch re-recorded 1..total when the file had been read whole;
-		// RecordEdit does the same thing one level down (its seenWhole arm
-		// re-baselines as a single covering observation) and additionally keeps
-		// the partial reads the old else-branch discarded. Two copies of the
-		// rule would drift, and only one of them sees the pre-edit observation.
-		options.FileTracker.RecordEdit(absolutePath, []byte(content), []byte(updated), newInfo)
-		for _, span := range editedSpans {
-			options.FileTracker.RecordSeenBytes(absolutePath, span.start, span.end, len(updated))
+		if previouslySeenWhole {
+			options.FileTracker.RecordSeenRange(absolutePath, 1, trackedLineTotal(updated), trackedLineTotal(updated))
+		} else {
+			for _, span := range editedSpans {
+				options.FileTracker.RecordSeenBytes(absolutePath, span.start, span.end, len(updated))
+			}
 		}
-	} else {
-		// A formatter rewrote the file after us. We no longer know which line
-		// holds what was read, so the conservative drop is the right answer here.
-		options.FileTracker.Record(absolutePath, []byte(updated), newInfo)
 	}
 
 	suffix := ""

internal/tools/edit_preserves_reads_test.go

@@ -1,296 +0,0 @@
-package tools
-
-import (
-	"context"
-	"os"
-	"path/filepath"
-	"strings"
-	"testing"
-)
-
-// editTrackerFixture writes a numbered file and returns its real path plus a
-// tracker that has already recorded the whole content as the current version.
-//
-// EvalSymlinks matters: on macOS t.TempDir() hands back /var/..., the tools
-// resolve it to /private/var/..., and a tracker keyed on the unresolved path
-// silently misses every lookup — which makes an edit fail for the very reason
-// this file is about, and for entirely the wrong cause.
-func editTrackerFixture(t *testing.T, lines []string) (string, *FileTracker, Tool) {
-	t.Helper()
-	root, err := filepath.EvalSymlinks(t.TempDir())
-	if err != nil {
-		t.Fatal(err)
-	}
-	path := filepath.Join(root, "index.go")
-	if err := os.WriteFile(path, []byte(strings.Join(lines, "\n")), 0o644); err != nil {
-		t.Fatal(err)
-	}
-	tracker := NewFileTracker()
-	content, _ := os.ReadFile(path)
-	info, _ := os.Stat(path)
-	tracker.Record(path, content, info)
-	return path, tracker, NewScopedEditFileTool(root, nil)
-}
-
-func numberedLines(total int, special map[int]string) []string {
-	lines := make([]string, 0, total)
-	for i := 1; i <= total; i++ {
-		if text, ok := special[i]; ok {
-			lines = append(lines, text)
-			continue
-		}
-		lines = append(lines, "filler")
-	}
-	return lines
-}
-
-func runTrackedEdit(t *testing.T, tool Tool, tracker *FileTracker, path, oldString, newString string) Result {
-	t.Helper()
-	return tool.(optionsAwareTool).RunWithOptions(context.Background(), map[string]any{
-		"path": path, "old_string": oldString, "new_string": newString,
-	}, RunOptions{FileTracker: tracker})
-}
-
-// ONE EDIT MUST NOT ERASE EVERY OTHER READ, and this is the run that made the
-// point: a 371-line file read in three pieces (40-45, 85-260, 260-371), one
-// two-line edit at line 92, and then six consecutive refusals to edit regions
-// that HAD been read and that the edit never touched — until the
-// repeated-failure guard halted the run. The error told the model to re-read,
-// which its next successful edit would have undone again.
-func TestASuccessfulEditKeepsTheReadsItDidNotDisturb(t *testing.T) {
-	path, tracker, tool := editTrackerFixture(t, numberedLines(371, map[int]string{
-		92:  "cmp := keyCmp(k, n.split)",
-		200: "prio: l.prio, split: l.split,",
-	}))
-	tracker.RecordSeenRange(path, 40, 45, 371)
-	tracker.RecordSeenRange(path, 85, 260, 371)
-	tracker.RecordSeenRange(path, 260, 371, 371)
-
-	if !tracker.SeenRange(path, 200, 200) {
-		t.Fatal("setup: line 200 sits inside the 85-260 read and must start out seen")
-	}
-
-	first := runTrackedEdit(t, tool, tracker, path, "cmp := keyCmp(k, n.split)", "cmp := keyCmp(k, n.pivot)")
-	if strings.Contains(first.Output, "Error") {
-		t.Fatalf("the first edit failed, so the test never reaches its subject: %s", first.Output)
-	}
-
-	if !tracker.SeenRange(path, 200, 200) {
-		t.Error("line 200 was read, the edit at line 92 did not touch it, and the file still has 371 lines — but it is no longer considered seen")
-	}
-	// The assertion that matters: the SECOND edit is what the run could never do.
-	second := runTrackedEdit(t, tool, tracker, path, "prio: l.prio, split: l.split,", "prio: l.prio, pivot: l.pivot,")
-	if strings.Contains(second.Output, "not been read exactly in this session") {
-		t.Fatalf("a second edit into an already-read region was refused as unseen: %s", second.Output)
-	}
-	if strings.Contains(second.Output, "Error") {
-		t.Fatalf("the second edit failed: %s", second.Output)
-	}
-}
-
-// LINE NUMBERS MOVE WHEN AN EDIT CHANGES THE LINE COUNT, so a range after the
-// edit has to be carried across SHIFTED, not left where it was.
-func TestReadsAfterAnEditAreShiftedByTheLineDelta(t *testing.T) {
-	path, tracker, tool := editTrackerFixture(t, numberedLines(100, map[int]string{
-		10: "short",
-		80: "target line",
-	}))
-	tracker.RecordSeenRange(path, 5, 20, 100)
-	tracker.RecordSeenRange(path, 70, 90, 100)
-
-	// Replace one line with three: everything after line 10 moves down by two.
-	res := runTrackedEdit(t, tool, tracker, path, "short", "one\ntwo\nthree")
-	if strings.Contains(res.Output, "Error") {
-		t.Fatalf("setup edit failed: %s", res.Output)
-	}
-
-	// "target line" was line 80 and is now line 82. It was read either way.
-	content, _ := os.ReadFile(path)
-	moved := strings.Count(strings.SplitN(string(content), "target line", 2)[0], "\n") + 1
-	if moved != 82 {
-		t.Fatalf("fixture moved the target to line %d, expected 82", moved)
-	}
-	if !tracker.SeenRange(path, moved, moved) {
-		t.Errorf("the read at lines 70-90 was not shifted with the content: line %d reads as unseen", moved)
-	}
-	second := runTrackedEdit(t, tool, tracker, path, "target line", "target changed")
-	if strings.Contains(second.Output, "Error") {
-		t.Fatalf("editing a line that was read and merely moved was refused: %s", second.Output)
-	}
-}
-
-// THE GUARD STILL GUARDS. Carrying reads across must not credit the model with
-// content it never saw — that is the whole reason the check exists.
-func TestAnUnreadRegionIsStillRefusedAfterAnEdit(t *testing.T) {
-	path, tracker, tool := editTrackerFixture(t, numberedLines(300, map[int]string{
-		50:  "seen line",
-		250: "never read line",
-	}))
-	// Only 40-60 is read. Line 250 is not.
-	tracker.RecordSeenRange(path, 40, 60, 300)
-
-	if res := runTrackedEdit(t, tool, tracker, path, "seen line", "seen line edited"); strings.Contains(res.Output, "Error") {
-		t.Fatalf("setup edit failed: %s", res.Output)
-	}
-	res := runTrackedEdit(t, tool, tracker, path, "never read line", "sneaky")
-	if !strings.Contains(res.Output, "not been read exactly in this session") {
-		t.Fatalf("an edit into a region that was NEVER read was allowed: %s", res.Output)
-	}
-}
-
-// A RANGE THE EDIT SPANS IS SPLIT, NOT DROPPED — and getting this wrong is not
-// hypothetical: dropping on overlap was my first attempt, and it left the
-// original defect exactly in place. A read almost always CONTAINS the line it
-// is about to edit, because containing it is why it was read.
-//
-// So the flanks survive and only the rewritten lines stop being known.
-func TestARangeTheEditSpansIsSplitAroundIt(t *testing.T) {
-	path, tracker, tool := editTrackerFixture(t, numberedLines(100, map[int]string{
-		20: "alpha",
-		21: "beta",
-		22: "gamma",
-	}))
-	tracker.RecordSeenRange(path, 15, 30, 100)
-
-	// Replace a three-line span with one line, entirely inside the read range.
-	if res := runTrackedEdit(t, tool, tracker, path, "alpha\nbeta\ngamma", "merged"); strings.Contains(res.Output, "Error") {
-		t.Fatalf("setup edit failed: %s", res.Output)
-	}
-
-	// Before the edit: still known, still at the same line numbers.
-	if !tracker.SeenRange(path, 15, 19) {
-		t.Error("lines 15-19 sit before the edit and did not move, but were forgotten")
-	}
-	// After it: still known, shifted up by the two lines the edit removed.
-	if !tracker.SeenRange(path, 21, 28) {
-		t.Error("lines 23-30 were read and merely moved to 21-28, but were forgotten")
-	}
-	// The rewritten span itself is no longer described by that read.
-	if tracker.SeenRange(path, 15, 30) {
-		t.Error("the whole original range still reads as seen, so the model is credited with content the edit replaced")
-	}
-}
-
-// AN EXTERNAL CHANGE STILL INVALIDATES EVERYTHING. RecordEdit is only for edits
-// we made; a file changed behind our back is exactly the case the blanket drop
-// is right for, and it must keep working.
-func TestAnExternalChangeStillDropsEveryRead(t *testing.T) {
-	path, tracker, _ := editTrackerFixture(t, numberedLines(100, map[int]string{50: "hello"}))
-	tracker.RecordSeenRange(path, 40, 60, 100)
-	if !tracker.SeenRange(path, 50, 50) {
-		t.Fatal("setup: line 50 should be seen")
-	}
-
-	// Something outside Zero rewrites the file.
-	changed := strings.Repeat("different\n", 100)
-	if err := os.WriteFile(path, []byte(changed), 0o644); err != nil {
-		t.Fatal(err)
-	}
-	info, _ := os.Stat(path)
-	tracker.Record(path, []byte(changed), info)
-
-	if tracker.SeenRange(path, 50, 50) {
-		t.Error("an external rewrite left the old read ranges in place")
-	}
-}
-
-// A file read in FULL stays read in full: an edit of ours does not make that
-// untrue, and re-reading a whole file after every edit is the cost this avoids.
-func TestAWhollyReadFileStaysWhollyRead(t *testing.T) {
-	path, tracker, tool := editTrackerFixture(t, numberedLines(40, map[int]string{5: "one"}))
-	tracker.RecordSeenRange(path, 1, 40, 40)
-	if !tracker.SeenWhole(path) {
-		t.Fatal("setup: the file should read as wholly seen")
-	}
-
-	if res := runTrackedEdit(t, tool, tracker, path, "one", "one\ntwo"); strings.Contains(res.Output, "Error") {
-		t.Fatalf("edit failed: %s", res.Output)
-	}
-	if !tracker.SeenWhole(path) {
-		t.Error("a wholly-read file stopped being wholly read after an edit")
-	}
-}
-
-// The span helpers, directly: these decide what survives, so their edges are
-// worth pinning independently of the tool.
-func TestChangedSpanHelpers(t *testing.T) {
-	t.Run("a single line replaced in place", func(t *testing.T) {
-		first, last, delta := changedLineSpan("a\nb\nc", "a\nB\nc")
-		if first != 2 || last != 2 || delta != 0 {
-			t.Fatalf("got (%d,%d,%d), want (2,2,0)", first, last, delta)
-		}
-	})
-	t.Run("one line becomes three", func(t *testing.T) {
-		first, last, delta := changedLineSpan("a\nb\nc", "a\nx\ny\nz\nc")
-		if first != 2 || last != 2 || delta != 2 {
-			t.Fatalf("got (%d,%d,%d), want (2,2,2)", first, last, delta)
-		}
-	})
-	t.Run("lines removed", func(t *testing.T) {
-		first, last, delta := changedLineSpan("a\nb\nc\nd", "a\nd")
-		if first != 2 || last != 3 || delta != -2 {
-			t.Fatalf("got (%d,%d,%d), want (2,3,-2)", first, last, delta)
-		}
-	})
-	t.Run("bytes", func(t *testing.T) {
-		first, last, delta := changedByteSpan([]byte("abcdef"), []byte("abXYef"))
-		if first != 2 || last != 4 || delta != 0 {
-			t.Fatalf("got (%d,%d,%d), want (2,4,0)", first, last, delta)
-		}
-	})
-}
-
-// A file read whole IN PIECES must stay seen-whole after an edit. SeenWhole
-// derives its answer from the ranges precisely because the raw flag is only set
-// by a single covering read; RecordEdit branching on the flag instead sent this
-// case down the split path, and the write_file refusal the derived answer exists
-// to prevent came back within one edit.
-func TestAFileReadWholeInPiecesStaysWholeAfterAnEdit(t *testing.T) {
-	dir := t.TempDir()
-	path := filepath.Join(dir, "chunked.go")
-	content := "l1\nl2\nl3\nl4\n"
-	if err := os.WriteFile(path, []byte(content), 0o600); err != nil {
-		t.Fatal(err)
-	}
-	tracker := NewFileTracker()
-	info, _ := os.Stat(path)
-	tracker.Record(path, []byte(content), info)
-	// Two reads that together cover the file, neither covering it alone.
-	tracker.RecordSeenRange(path, 1, 2, 4)
-	tracker.RecordSeenRange(path, 3, 4, 4)
-	if !tracker.SeenWhole(path) {
-		t.Fatal("two chunked reads did not add up to seen-whole")
-	}
-
-	updated := "l1\nl2X\nl3\nl4\n"
-	if err := os.WriteFile(path, []byte(updated), 0o600); err != nil {
-		t.Fatal(err)
-	}
-	newInfo, _ := os.Stat(path)
-	tracker.RecordEdit(path, []byte(content), []byte(updated), newInfo)
-
-	if !tracker.SeenWhole(path) {
-		t.Error("a file read whole in two chunks stopped being seen whole after one edit")
-	}
-}
-
-// observation.total is compared against read ranges, so it has to be the line
-// count a READER would give. strings.Split leaves an empty final element for
-// content ending in a newline, which counted one line too many — and since
-// SeenWhole asks whether the ranges cover 1..total, that made full coverage
-// unreachable for a file that had just been read in full.
-func TestCountLinesMatchesWhatAReaderWouldSay(t *testing.T) {
-	for _, testCase := range []struct {
-		content string
-		want    int
-	}{
-		{"a\nb\nc\n", 3}, // the common case: trailing newline opens no line
-		{"a\nb\nc", 3},
-		{"\n", 1},
-		{"", 0},
-	} {
-		if got := countLines([]byte(testCase.content)); got != testCase.want {
-			t.Errorf("countLines(%q) = %d, want %d", testCase.content, got, testCase.want)
-		}
-	}
-}

internal/tools/file_tracker.go

@@ -1,13 +1,11 @@
 package tools
 
 import (
-	"bytes"
 	"crypto/sha256"
 	"encoding/hex"
 	"errors"
 	"os"
 	"sort"
-	"strings"
 	"sync"
 	"time"
 )
@@ -167,241 +165,6 @@ func (tracker *FileTracker) RecordSeenBytes(absPath string, start, end, total in
 	tracker.seen[absPath] = observation
 }
 
-// RecordEdit re-baselines absPath after an edit THIS SESSION made, keeping the
-// reads the edit did not disturb.
-//
-// WHY THIS EXISTS RATHER THAN Record. RecordHash drops every recorded range when
-// the content hash moves, which is right for a change we did not make: we cannot
-// say which lines still hold what was read. After our own edit we can say
-// exactly. The content before the first changed line is byte-identical and sits
-// at the same line numbers; the content after the last changed line is
-// byte-identical and has moved by a known delta. Only the lines the edit
-// actually spans stop describing the file.
-//
-// Dropping the lot instead cost a real run. A 371-line file was read in three
-// pieces (40-45, 85-260, 260-371) and one two-line edit at line 92 erased the
-// credit for all three: the next six edits — into regions that had been read,
-// that the edit did not touch, in a file whose line count had not changed — were
-// each refused as content "not read in this session", and the repeated-failure
-// guard halted the run. The error even told the model to re-read, which would
-// have been undone by its next successful edit. The guard is right that a model
-// must not edit what it has not seen; it was wrong about what it had seen.
-func (tracker *FileTracker) RecordEdit(absPath string, before, after []byte, info os.FileInfo) {
-	if tracker == nil {
-		return
-	}
-	firstLine, lastLineBefore, lineDelta := changedLineSpan(string(before), string(after))
-	firstByte, lastByteBefore, byteDelta := changedByteSpan(before, after)
-
-	tracker.mu.Lock()
-	defer tracker.mu.Unlock()
-
-	version := FileVersion{Hash: HashContent(after)}
-	if info != nil {
-		version.Size = info.Size()
-		version.MTime = info.ModTime()
-	}
-	tracker.versions[absPath] = version
-
-	observation, tracked := tracker.seen[absPath]
-	if !tracked {
-		return
-	}
-	// The DERIVED answer, not the raw flag. Branching on observation.whole here
-	// sent a file read whole in two chunks — seenWhole true, flag false — into
-	// the split path below, where it stopped being seen whole after one edit.
-	if seenWhole(observation) {
-		// Still whole: every line was read, and an edit of ours does not make
-		// that untrue. Re-baseline as a single covering observation so the
-		// answer survives regardless of how the ranges shifted.
-		observation.whole = true
-		observation.ranges = nil
-		observation.byteRanges = nil
-		observation.total = countLines(after)
-		observation.totalBytes = len(after)
-		tracker.seen[absPath] = observation
-		return
-	}
-
-	// SPLIT AROUND THE EDIT, never drop the whole range. A read almost always
-	// SPANS the line it is about to edit — that is why it was read — so dropping
-	// on overlap would have thrown away 85-260 to change line 92 and left the
-	// original defect in place under a longer implementation.
-	kept := make([]lineRange, 0, len(observation.ranges)+1)
-	for _, seen := range observation.ranges {
-		if end := min(seen.end, firstLine-1); seen.start <= end {
-			kept = append(kept, lineRange{start: seen.start, end: end})
-		}
-		if start := max(seen.start, lastLineBefore+1); start <= seen.end {
-			kept = append(kept, lineRange{start: start + lineDelta, end: seen.end + lineDelta})
-		}
-	}
-	observation.ranges = kept
-	if observation.total != 0 {
-		observation.total = countLines(after)
-	}
-
-	// Same split, on half-open byte intervals.
-	keptBytes := make([]lineRange, 0, len(observation.byteRanges)+1)
-	for _, seen := range observation.byteRanges {
-		if end := min(seen.end, firstByte); seen.start < end {
-			keptBytes = append(keptBytes, lineRange{start: seen.start, end: end})
-		}
-		if start := max(seen.start, lastByteBefore); start < seen.end {
-			keptBytes = append(keptBytes, lineRange{start: start + byteDelta, end: seen.end + byteDelta})
-		}
-	}
-	observation.byteRanges = keptBytes
-	if observation.totalBytes != 0 {
-		observation.totalBytes = len(after)
-	}
-	tracker.seen[absPath] = observation
-}
-
-// changedLineSpan reports the 1-based first line that differs between before and
-// after, the 1-based last line of BEFORE that differs, and the line-count delta.
-//
-// Computed from a common prefix and suffix rather than from the caller's
-// replacement spans: one edit_file call with replace_all can rewrite many
-// scattered occurrences, and the span between the outermost two is the only
-// region that is honestly unknown afterwards.
-// The span is derived by scanning BYTES, not by materialising lines.
-//
-// The first version split both versions into []string. That allocates one string
-// header per line for each version — work that scales with the SIZE OF THE FILE
-// rather than the size of the edit, and it ran before RecordEdit had even checked
-// whether there was a tracked observation to update. @jatmn measured 32,036,640
-// bytes for two 2 MB versions of a million short lines, and extrapolated roughly
-// 1.6 GB of headers for a 100 MB file before counting the content and hashes
-// already live alongside them.
-//
-// That mattered beyond memory pressure: edit_file writes the updated bytes BEFORE
-// calling RecordEdit, so an out-of-memory kill lands after the user's file has
-// changed and before the tracker baseline catches up — the file and the record of
-// it disagree, and nothing says so.
-//
-// Bytes give the same answer in bounded memory. Two identical byte prefixes share
-// every line that ends inside them, so counting newlines in the common prefix
-// counts the unchanged leading lines directly.
-func changedLineSpan(before, after string) (firstChanged, lastChangedBefore, delta int) {
-	beforeCount := countTrackedLines(before)
-	afterCount := countTrackedLines(after)
-
-	prefix := commonLinePrefix(before, after)
-	// Never more leading lines than the shorter version has. The byte scan can
-	// otherwise claim a line that only one side possesses — two empty versions
-	// share a whole "line" that neither actually contains.
-	prefix = min(prefix, min(beforeCount, afterCount))
-	// The suffix may not reach back past the lines the prefix already claimed,
-	// exactly as the line-array loop bounded itself.
-	suffix := commonLineSuffix(before, after, min(beforeCount-prefix, afterCount-prefix))
-	return prefix + 1, beforeCount - suffix, afterCount - beforeCount
-}
-
-// commonLinePrefix counts the leading lines that are byte-identical in both.
-func commonLinePrefix(before, after string) int {
-	limit := min(len(before), len(after))
-	at := 0
-	for at < limit && before[at] == after[at] {
-		at++
-	}
-	lines := strings.Count(before[:at], "\n")
-	// A LINE THAT ENDS EXACTLY WHERE THE SCAN STOPPED IS STILL SHARED. Scanning
-	// halts where the bytes diverge OR where the shorter version runs out, and in
-	// the second case the line containing that point can be complete and equal on
-	// both sides — "a\nb" against "a\nb\nc" diverges only because the first ended,
-	// and "b" is a whole matching line in each.
-	if lineBoundary(before, at) && lineBoundary(after, at) {
-		lines++
-	}
-	return lines
-}
-
-// commonLineSuffix counts the trailing lines that are byte-identical in both, up
-// to the ceiling the prefix leaves.
-func commonLineSuffix(before, after string, ceiling int) int {
-	if ceiling <= 0 {
-		return 0
-	}
-	limit := min(len(before), len(after))
-	back := 0
-	for back < limit && before[len(before)-1-back] == after[len(after)-1-back] {
-		back++
-	}
-	beforeAt, afterAt := len(before)-back, len(after)-back
-	// Each newline inside the shared tail closes a line that lies wholly within
-	// it. The line the tail STARTS in is shared only when the tail begins on a
-	// line boundary in both versions — otherwise its opening bytes differ and it
-	// is a changed line that merely ends the same way.
-	lines := strings.Count(before[beforeAt:], "\n")
-	if lineStart(before, beforeAt) && lineStart(after, afterAt) {
-		lines++
-	}
-	return min(lines, ceiling)
-}
-
-// lineBoundary reports whether at is the end of a line: the end of the text, or
-// the position of the newline that closes it.
-func lineBoundary(text string, at int) bool { return at == len(text) || text[at] == '\n' }
-
-// lineStart reports whether at begins a line.
-func lineStart(text string, at int) bool { return at == 0 || text[at-1] == '\n' }
-
-// changedByteSpan is changedLineSpan in bytes: the first differing offset, the
-// end offset of the changed region in BEFORE, and the size delta.
-func changedByteSpan(before, after []byte) (firstChanged, lastChangedBefore, delta int) {
-	prefix := 0
-	for prefix < len(before) && prefix < len(after) && before[prefix] == after[prefix] {
-		prefix++
-	}
-	suffix := 0
-	for suffix < len(before)-prefix && suffix < len(after)-prefix &&
-		before[len(before)-1-suffix] == after[len(after)-1-suffix] {
-		suffix++
-	}
-	return prefix, len(before) - suffix, len(after) - len(before)
-}
-
-// countLines reports the line count a READER would give the content, which is
-// what observation.total is compared against.
-//
-// The trailing newline does not open a line. strings.Split leaves an empty final
-// element for "a\nb\nc\n" and so counted 4 where a read reports 3 — and because
-// SeenWhole asks whether the ranges cover 1..total, an inflated total made full
-// coverage unreachable for the very file that had just been read in full. Almost
-// every text file ends in a newline, so this was the common case rather than an
-// edge one.
-//
-// countTrackedLines keeps the OTHER rule deliberately: the span arithmetic has to
-// match the indices strings.Split produced, so it counts the empty element after
-// a trailing newline where this one does not. Two rules, two names, both stated —
-// they were one function with an if, and that is how they were confused.
-func countLines(content []byte) int {
-	// Counted, not split. This only ever needed a number, and building a slice of
-	// every line to take its length was the third full per-line allocation in the
-	// same call path.
-	if len(content) == 0 {
-		return 0
-	}
-	lines := bytes.Count(content, []byte{'\n'})
-	if content[len(content)-1] != '\n' {
-		lines++
-	}
-	return lines
-}
-
-// countTrackedLines is countLines' rule for the string form: the number of
-// elements strings.Split would produce, which counts the empty element after a
-// trailing newline. The two differ deliberately — observation.total compares
-// against what a READER reports, while the span arithmetic has to match the
-// indices the split produced.
-func countTrackedLines(text string) int {
-	if text == "" {
-		return 0
-	}
-	return strings.Count(text, "\n") + 1
-}
-
 // coversFully reports whether ranges together cover every line in [start, end].
 //
 // Ranges are merged rather than scanned line by line: a caller asking about a
@@ -511,27 +274,14 @@ func (tracker *FileTracker) SeenWhole(absPath string) bool {
 	if !ok {
 		return false
 	}
-	return seenWhole(observation)
-}
-
-// seenWhole is the DERIVED answer to "has every line been seen", and the single
-// place that decides it. Callers must hold the lock.
-//
-// Derived from the ranges rather than read off the flag, because the flag is
-// only ever set by a SINGLE read covering the file: a file read in two halves
-// stayed "not seen whole" forever even though SeenRange agreed every line had
-// been seen, and write_file, which gates on this, refused the overwrite with
-// advice to read the file that could not change the answer.
-//
-// IT HAS TO BE ONE FUNCTION. RecordEdit branched on the raw flag while this
-// derived the answer, so the very case the derivation exists to rescue fell into
-// the wrong arm and lost: a file read whole in two chunks reported SeenWhole
-// true, then reported false after a single edit, putting the write_file refusal
-// back within one edit of where it was fixed.
-func seenWhole(observation fileObservation) bool {
 	if observation.whole {
 		return true
 	}
+	// Derived from the ranges rather than tracked as its own flag. The flag was
+	// only ever set by a SINGLE read covering the file, so a file read in two
+	// halves stayed "not seen whole" forever even though SeenRange agreed every
+	// line had been seen — and write_file, which gates on this, then refused the
+	// overwrite with advice to read the file that could not change the answer.
 	if observation.total > 0 && coversFully(observation.ranges, 1, observation.total) {
 		return true
 	}

internal/tools/file_tracker_test.go

@@ -3,7 +3,6 @@ package tools
 import (
 	"os"
 	"path/filepath"
-	"strings"
 	"testing"
 )
 
@@ -154,85 +153,3 @@ func TestNilFileTrackerCreatedFilesIsANoop(t *testing.T) {
 		t.Fatalf("CreatedFiles() on nil tracker = %v, want nil", got)
 	}
 }
-
-// THE SPAN IS DERIVED IN BOUNDED MEMORY, whatever the file size.
-//
-// changedLineSpan used to split both versions into []string, so it allocated one
-// string header per line for each — work scaling with the SIZE OF THE FILE rather
-// than the size of the edit, and it ran before RecordEdit had even checked whether
-// there was an observation to update. @jatmn measured 32,036,640 bytes for two
-// 2 MB versions of a million short lines.
-//
-// The cost was not only memory. edit_file writes the updated bytes BEFORE calling
-// RecordEdit, so an out-of-memory kill lands after the user's file has changed and
-// before the tracker baseline catches up — file and record disagree, silently.
-//
-// This asserts an absolute ceiling rather than a ratio, so a future rewrite that
-// reintroduces per-line slices fails here rather than merely getting slower.
-func TestTheChangedSpanDoesNotAllocatePerLine(t *testing.T) {
-	before := strings.Repeat("x\n", 200_000)
-	after := before[:len(before)-2] + "y\n"
-
-	spanBytes := testing.Benchmark(func(b *testing.B) {
-		b.ReportAllocs()
-		for i := 0; i < b.N; i++ {
-			changedLineSpan(before, after)
-		}
-	}).AllocedBytesPerOp()
-	if spanBytes > 4096 {
-		t.Errorf("changedLineSpan allocated %d bytes for a %d-line pair; per-line slices are back", spanBytes, 200_000)
-	}
-
-	content := []byte(before)
-	countBytes := testing.Benchmark(func(b *testing.B) {
-		b.ReportAllocs()
-		for i := 0; i < b.N; i++ {
-			countLines(content)
-		}
-	}).AllocedBytesPerOp()
-	if countBytes > 4096 {
-		t.Errorf("countLines allocated %d bytes to return a number", countBytes)
-	}
-}
-
-// AND IT GIVES THE SAME ANSWERS THE LINE-ARRAY VERSION DID. The rewrite is only
-// safe if it is behaviour-preserving, so the replaced implementation is kept here
-// as an oracle and both are asked the same questions. This caught 206 mismatches
-// in the first attempt at the byte scan — empty versions and partially shared
-// trailing lines, neither of which the hand-written cases below would have found.
-func TestTheByteScanAgreesWithTheLineSplit(t *testing.T) {
-	oracle := func(before, after string) (int, int, int) {
-		split := func(text string) []string {
-			if text == "" {
-				return nil
-			}
-			return strings.Split(text, "\n")
-		}
-		beforeLines, afterLines := split(before), split(after)
-		prefix := 0
-		for prefix < len(beforeLines) && prefix < len(afterLines) && beforeLines[prefix] == afterLines[prefix] {
-			prefix++
-		}
-		suffix := 0
-		for suffix < len(beforeLines)-prefix && suffix < len(afterLines)-prefix &&
-			beforeLines[len(beforeLines)-1-suffix] == afterLines[len(afterLines)-1-suffix] {
-			suffix++
-		}
-		return prefix + 1, len(beforeLines) - suffix, len(afterLines) - len(beforeLines)
-	}
-
-	versions := []string{
-		"", "a", "\n", "a\n", "a\nb", "a\nb\n", "a\nb\nc", "a\nb\nc\n",
-		"\n\n", "x\n\ny", "a\nb\nc\nd\ne", "same\nsame\nsame\n", "ab\nc", "b\nc",
-	}
-	for _, before := range versions {
-		for _, after := range versions {
-			wantFirst, wantLast, wantDelta := oracle(before, after)
-			gotFirst, gotLast, gotDelta := changedLineSpan(before, after)
-			if wantFirst != gotFirst || wantLast != gotLast || wantDelta != gotDelta {
-				t.Errorf("changedLineSpan(%q, %q) = (%d, %d, %d), want (%d, %d, %d)",
-					before, after, gotFirst, gotLast, gotDelta, wantFirst, wantLast, wantDelta)
-			}
-		}
-	}
-}

internal/tui/commands.go

@@ -109,7 +109,7 @@ var commandDefinitions = []commandDefinition{
 		name:        "/voice",
 		usage:       "/voice",
 		group:       commandGroupRuntime,
-		description: "Toggle voice mode (" + voiceCaptureUsage + ").",
+		description: "Toggle voice mode (hold Space to dictate).",
 		kind:        commandVoice,
 	},
 	{

internal/tui/dictation.go

@@ -88,7 +88,7 @@ type dictationController struct {
 	waveBars []int
 	waveTick int
 
-	// voiceModeEnabled repurposes Ctrl+Space into hold-to-record (§13.9).
+	// voiceModeEnabled repurposes Space into hold-to-record (§13.9).
 	voiceModeEnabled bool
 	// eventTypesSupported records whether the terminal confirmed key-release
 	// reporting (Kitty protocol); eventTypesKnown gates it until the terminal has
@@ -173,7 +173,7 @@ func firstNonEmptyStr(a, b string) string {
 func (d dictationController) active() bool { return d.phase != dictIdle }
 
 // toggleDictation starts a recording when idle and stops-and-transcribes when
-// recording. Invoked by the voice-mode Ctrl+Space gesture; a call during
+// recording. Invoked by the voice-mode Space gesture; a call during
 // startup/transcription is ignored (the machine is mid-transition).
 func (m model) toggleDictation() (model, tea.Cmd) {
 	if !m.dictation.available() {
@@ -193,15 +193,15 @@ func (m model) toggleDictation() (model, tea.Cmd) {
 	}
 }
 
-// toggleVoiceMode flips the /voice hold-to-record gesture. While on,
-// Ctrl+Space records and ordinary Space continues to type normally.
+// toggleVoiceMode flips the /voice hold-to-record gesture — the dictation
+// trigger. While on, Space records; run /voice again to type spaces normally.
 func (m model) toggleVoiceMode() (model, tea.Cmd) {
 	if !m.dictation.available() {
 		return m.appendSystemNotice("Dictation is not configured. See docs/dictation.md to set up a local engine or a Groq/OpenAI key."), nil
 	}
 	m.dictation.voiceModeEnabled = !m.dictation.voiceModeEnabled
 	if m.dictation.voiceModeEnabled {
-		return m.showTransientNoticeInline("Voice mode on — "+voiceCaptureUsage+". Run /voice again to turn it off.", transientNoticeSuccess), nil
+		return m.showTransientNoticeInline("Voice mode on — hold Space to dictate; run /voice again to turn it off.", transientNoticeSuccess), nil
 	}
 	// Turning voice off is the "done dictating" signal, so release the warm sherpa
 	// streaming server — otherwise a loaded model keeps idling in RAM (and holding
@@ -374,7 +374,7 @@ func (m model) handleDictationStarted(msg dictationStartedMsg) (model, tea.Cmd)
 	if m.dictation.phase == dictStarting {
 		m.dictation.phase = dictRecording
 	}
-	// A voice-mode Ctrl+Space release that arrived mid-startup asked us to stop as soon
+	// A voice-mode Space release that arrived mid-startup asked us to stop as soon
 	// as recording began.
 	if m.dictation.voiceStopPending && m.dictation.phase == dictRecording {
 		m.dictation.voiceStopPending = false
@@ -480,8 +480,12 @@ func needsLeadingSpace(state composerState) bool {
 func (m model) dictationStatusChip() string {
 	switch m.dictation.phase {
 	case dictStarting, dictRecording:
+		stop := "release Space to stop"
+		if !m.dictation.eventTypesSupported {
+			stop = "press Space to stop" // press-to-toggle fallback
+		}
 		wave := zeroTheme.amber.Render("● " + renderWaveBars(m.dictation.waveBars) + " REC")
-		return wave + zeroTheme.muted.Render(" · "+m.voiceCaptureStatus()+", Esc to cancel")
+		return wave + zeroTheme.muted.Render(" · "+stop+", Esc to cancel")
 	case dictTranscribing:
 		return zeroTheme.accent.Render("●") + " " + zeroTheme.muted.Render("transcribing…")
 	}
@@ -597,12 +601,13 @@ func (m model) handleRecTick() (model, tea.Cmd) {
 	return m, nil
 }
 
-// voiceModeIndicator renders the current voice gesture or transcription state.
+// voiceModeIndicator renders the persistent "voice mode on" hint shown while
+// idle so the user knows Space is repurposed to hold-to-record (§10).
 func (m model) voiceModeIndicator() string {
 	if !m.dictation.voiceModeEnabled {
 		return ""
 	}
-	return zeroTheme.accent.Render("🎙 voice") + zeroTheme.muted.Render(" · "+m.voiceCaptureStatus()+" · "+m.dictation.currentModelLabel())
+	return zeroTheme.accent.Render("🎙 voice") + zeroTheme.muted.Render(" · "+m.dictation.currentModelLabel())
 }
 
 // dictationErrorText renders a dictation error for the transcript: a missing-

internal/tui/dictation_voice.go

@@ -4,19 +4,17 @@ import (
 	tea "charm.land/bubbletea/v2"
 )
 
-const voiceCaptureUsage = "hold Ctrl+Space to record; press it to toggle where key releases are unavailable"
-
-// Voice mode's Ctrl+Space gesture — the (only) dictation trigger. Two terminal
+// Voice mode's Space-hold gesture — the (only) dictation trigger. Two terminal
 // tiers:
 //
 //  1. The terminal confirms key-release reporting (Ghostty/Kitty/WezTerm, …):
-//     Ctrl+Space press starts recording and release stops it — true
-//     hold-to-record, with ordinary Space left available for typing.
-//  2. The terminal does not confirm release events: Ctrl+Space falls back to
+//     Space press starts recording, Space release stops it — true hold-to-record,
+//     no ambiguity.
+//  2. The terminal does not confirm release events: Space falls back to
 //     press-to-toggle (press to start, press again to stop) — a deliberately
 //     simpler, robust fallback than inferring release from key-repeat timing
-//     (racy in a terminal). Legacy NUL input is decoded as Ctrl+Space by the
-//     terminal input layer, so the same matcher covers both tiers.
+//     (racy in a terminal). This works on ANY terminal, so voice mode is always
+//     usable once enabled.
 //
 // Only active while voice mode is on; the rest of dispatch is built on
 // KeyPressMsg and is untouched.
@@ -29,37 +27,8 @@ func (m model) handleKeyboardEnhancements(msg tea.KeyboardEnhancementsMsg) model
 	return m
 }
 
-func voiceCaptureKey(msg tea.KeyMsg) bool {
-	mod := msg.Key().Mod &^ (tea.ModCapsLock | tea.ModNumLock)
-	return keyIs(msg, tea.KeySpace) && mod == tea.ModCtrl
-}
-
-// voiceCaptureReleaseKey matches either half of the held Ctrl+Space chord. A
-// terminal may report Ctrl releasing first, or report the later Space release
-// without ModCtrl because Ctrl is no longer down.
-func voiceCaptureReleaseKey(msg tea.KeyMsg) bool {
-	return keyIs(msg, tea.KeySpace) || keyIs(msg, tea.KeyLeftCtrl) || keyIs(msg, tea.KeyRightCtrl)
-}
-
-func (m model) voiceCaptureStatus() string {
-	switch m.dictation.phase {
-	case dictStarting, dictRecording:
-		if m.dictation.eventTypesSupported {
-			return "release Ctrl+Space to stop"
-		}
-		return "press Ctrl+Space to stop"
-	case dictTranscribing:
-		return "transcribing…"
-	default:
-		if m.dictation.eventTypesSupported {
-			return "hold Ctrl+Space to record"
-		}
-		return "press Ctrl+Space to record"
-	}
-}
-
-// handleVoiceCapturePress handles Ctrl+Space while voice mode is on.
-func (m model) handleVoiceCapturePress(msg tea.KeyMsg) (model, tea.Cmd) {
+// handleVoiceSpacePress handles a Space press while voice mode is on.
+func (m model) handleVoiceSpacePress(msg tea.KeyMsg) (model, tea.Cmd) {
 	if !m.dictation.eventTypesSupported {
 		// Tier 2: no release events — press-to-toggle.
 		return m.toggleDictation()
@@ -76,8 +45,8 @@ func (m model) handleVoiceCapturePress(msg tea.KeyMsg) (model, tea.Cmd) {
 	return m, nil // already recording; the release will stop it
 }
 
-// handleVoiceCaptureRelease stops a hold-to-record session when Ctrl+Space is released.
-func (m model) handleVoiceCaptureRelease() (model, tea.Cmd) {
+// handleVoiceSpaceRelease stops a hold-to-record session when Space is released.
+func (m model) handleVoiceSpaceRelease() (model, tea.Cmd) {
 	if !m.dictation.spaceHeld {
 		return m, nil
 	}

internal/tui/dictation_voice_test.go

@@ -2,7 +2,6 @@ package tui
 
 import (
 	"context"
-	"strings"
 	"testing"
 
 	tea "charm.land/bubbletea/v2"
@@ -37,7 +36,7 @@ func TestToggleVoiceModeFlips(t *testing.T) {
 	if !next.dictation.voiceModeEnabled {
 		t.Fatal("first /voice should enable voice mode")
 	}
-	if next.transientNotice.text != "Voice mode on — hold Ctrl+Space to record; press it to toggle where key releases are unavailable. Run /voice again to turn it off." {
+	if next.transientNotice.text != "Voice mode on — hold Space to dictate; run /voice again to turn it off." {
 		t.Errorf("voice-mode-on notice = %q", next.transientNotice.text)
 	}
 	if transcriptHasText(next, "Voice mode on") {
@@ -69,27 +68,15 @@ func TestKeyboardEnhancementsRecorded(t *testing.T) {
 	}
 }
 
-func TestVoiceCaptureKeyIgnoresLockModifiers(t *testing.T) {
-	for _, mod := range []tea.KeyMod{
-		tea.ModCtrl | tea.ModCapsLock,
-		tea.ModCtrl | tea.ModNumLock,
-		tea.ModCtrl | tea.ModCapsLock | tea.ModNumLock,
-	} {
-		if !voiceCaptureKey(tea.KeyPressMsg(tea.Key{Code: tea.KeySpace, Mod: mod})) {
-			t.Fatalf("Ctrl+Space with lock modifiers %v was not recognized", mod)
-		}
-	}
-}
-
-func TestVoiceCaptureHoldStartsRecording(t *testing.T) {
+func TestVoiceSpaceHoldStartsRecording(t *testing.T) {
 	m := model{dictation: batchOnlyController()}
 	m.dictation.voiceModeEnabled = true
 	m.dictation.eventTypesSupported = true
 
-	press := tea.KeyPressMsg(tea.Key{Code: tea.KeySpace, Mod: tea.ModCtrl})
-	next, cmd := m.handleVoiceCapturePress(press)
+	press := tea.KeyPressMsg(tea.Key{Code: tea.KeySpace})
+	next, cmd := m.handleVoiceSpacePress(press)
 	if next.dictation.phase != dictStarting {
-		t.Fatalf("Ctrl+Space press should start recording (phase=%d)", next.dictation.phase)
+		t.Fatalf("Space press should start recording (phase=%d)", next.dictation.phase)
 	}
 	if !next.dictation.spaceHeld {
 		t.Error("spaceHeld should be set in hold mode")
@@ -99,28 +86,28 @@ func TestVoiceCaptureHoldStartsRecording(t *testing.T) {
 	}
 }
 
-func TestVoiceCaptureHoldIgnoresRepeat(t *testing.T) {
+func TestVoiceSpaceHoldIgnoresRepeat(t *testing.T) {
 	m := model{dictation: batchOnlyController()}
 	m.dictation.voiceModeEnabled = true
 	m.dictation.eventTypesSupported = true
 	m.dictation.phase = dictRecording
 	m.dictation.spaceHeld = true
 
-	repeat := tea.KeyPressMsg(tea.Key{Code: tea.KeySpace, Mod: tea.ModCtrl, IsRepeat: true})
-	next, _ := m.handleVoiceCapturePress(repeat)
+	repeat := tea.KeyPressMsg(tea.Key{Code: tea.KeySpace, IsRepeat: true})
+	next, _ := m.handleVoiceSpacePress(repeat)
 	if next.dictation.phase != dictRecording {
 		t.Error("auto-repeat while held must not restart or change phase")
 	}
 }
 
-func TestVoiceCaptureReleaseStops(t *testing.T) {
+func TestVoiceSpaceReleaseStops(t *testing.T) {
 	m := model{dictation: batchOnlyController()}
 	m.dictation.voiceModeEnabled = true
 	m.dictation.eventTypesSupported = true
 	m.dictation.phase = dictRecording
 	m.dictation.spaceHeld = true
 
-	next, _ := m.handleVoiceCaptureRelease()
+	next, _ := m.handleVoiceSpaceRelease()
 	if next.dictation.phase != dictTranscribing {
 		t.Errorf("release should stop recording → transcribing (phase=%d)", next.dictation.phase)
 	}
@@ -136,7 +123,7 @@ func TestVoiceReleaseDuringStartupDefersStop(t *testing.T) {
 	m.dictation.phase = dictStarting
 	m.dictation.spaceHeld = true
 
-	next, _ := m.handleVoiceCaptureRelease()
+	next, _ := m.handleVoiceSpaceRelease()
 	if !next.dictation.voiceStopPending {
 		t.Error("a release during startup should defer the stop")
 	}
@@ -147,186 +134,14 @@ func TestVoiceReleaseDuringStartupDefersStop(t *testing.T) {
 	}
 }
 
-func TestVoiceCaptureToggleFallback(t *testing.T) {
+func TestVoiceSpaceToggleFallback(t *testing.T) {
 	m := model{dictation: batchOnlyController()}
 	m.dictation.voiceModeEnabled = true
 	m.dictation.eventTypesSupported = false // no release events → toggle fallback
 
-	press := tea.KeyPressMsg(tea.Key{Code: tea.KeySpace, Mod: tea.ModCtrl})
-	next, _ := m.handleVoiceCapturePress(press)
+	press := tea.KeyPressMsg(tea.Key{Code: tea.KeySpace})
+	next, _ := m.handleVoiceSpacePress(press)
 	if next.dictation.phase != dictStarting {
-		t.Errorf("toggle-mode Ctrl+Space should start recording (phase=%d)", next.dictation.phase)
-	}
-}
-
-func TestVoiceModeCtrlSpaceReleaseStopsHoldRecording(t *testing.T) {
-	m := newModel(t.Context(), Options{})
-	m.dictation = batchOnlyController()
-	m.dictation.voiceModeEnabled = true
-	m.dictation.eventTypesSupported = true
-	m.dictation.phase = dictRecording
-	m.dictation.spaceHeld = true
-
-	updated, _ := m.Update(tea.KeyReleaseMsg(tea.Key{Code: tea.KeySpace, Mod: tea.ModCtrl}))
-	next := updated.(model)
-	if next.dictation.phase != dictTranscribing || next.dictation.spaceHeld {
-		t.Fatalf("Ctrl+Space release did not stop hold recording: phase=%d held=%v", next.dictation.phase, next.dictation.spaceHeld)
-	}
-}
-
-func TestVoiceModeCaptureStopsWhenEitherChordKeyIsReleased(t *testing.T) {
-	for _, test := range []struct {
-		name string
-		key  tea.Key
-	}{
-		{name: "left Ctrl first", key: tea.Key{Code: tea.KeyLeftCtrl}},
-		{name: "right Ctrl first", key: tea.Key{Code: tea.KeyRightCtrl}},
-		{name: "Space after Ctrl", key: tea.Key{Code: tea.KeySpace}},
-	} {
-		t.Run(test.name, func(t *testing.T) {
-			m := newModel(t.Context(), Options{})
-			m.dictation = batchOnlyController()
-			m.dictation.voiceModeEnabled = true
-			m.dictation.eventTypesSupported = true
-			m.dictation.phase = dictRecording
-			m.dictation.spaceHeld = true
-
-			updated, _ := m.Update(tea.KeyReleaseMsg(test.key))
-			next := updated.(model)
-			if next.dictation.phase != dictTranscribing || next.dictation.spaceHeld {
-				t.Fatalf("release did not stop hold recording: phase=%d held=%v", next.dictation.phase, next.dictation.spaceHeld)
-			}
-		})
-	}
-}
-
-func TestVoiceModeIndicatorDescribesTierAndPhase(t *testing.T) {
-	for _, test := range []struct {
-		name          string
-		releaseEvents bool
-		phase         dictationPhase
-		spaceHeld     bool
-		want          string
-	}{
-		{name: "toggle idle", want: "press Ctrl+Space to record"},
-		{name: "hold idle", releaseEvents: true, want: "hold Ctrl+Space to record"},
-		{name: "toggle recording", phase: dictRecording, want: "press Ctrl+Space to stop"},
-		{name: "hold recording", releaseEvents: true, phase: dictRecording, spaceHeld: true, want: "release Ctrl+Space to stop"},
-		{name: "transcribing", phase: dictTranscribing, want: "transcribing"},
-	} {
-		t.Run(test.name, func(t *testing.T) {
-			m := model{dictation: batchOnlyController()}
-			m.dictation.voiceModeEnabled = true
-			m.dictation.eventTypesSupported = test.releaseEvents
-			m.dictation.phase = test.phase
-			m.dictation.spaceHeld = test.spaceHeld
-			if got := m.voiceModeIndicator(); !strings.Contains(strings.ToLower(got), strings.ToLower(test.want)) {
-				t.Fatalf("voice indicator = %q, want %q", got, test.want)
-			}
-		})
-	}
-}
-
-func TestDictationStatusChipUsesVoiceCaptureShortcut(t *testing.T) {
-	for _, test := range []struct {
-		name          string
-		releaseEvents bool
-		want          string
-	}{
-		{name: "toggle", want: "press Ctrl+Space to stop"},
-		{name: "hold", releaseEvents: true, want: "release Ctrl+Space to stop"},
-	} {
-		t.Run(test.name, func(t *testing.T) {
-			m := model{dictation: batchOnlyController()}
-			m.dictation.voiceModeEnabled = true
-			m.dictation.eventTypesSupported = test.releaseEvents
-			m.dictation.phase = dictRecording
-			if got := m.dictationStatusChip(); !strings.Contains(got, test.want) {
-				t.Fatalf("dictation status = %q, want %q", got, test.want)
-			}
-		})
-	}
-}
-
-func TestVoiceCommandDescriptionExplainsBothTerminalTiers(t *testing.T) {
-	for _, command := range commandDefinitions {
-		if command.kind == commandVoice {
-			for _, want := range []string{"hold Ctrl+Space", "press it to toggle", "key releases"} {
-				if !strings.Contains(command.description, want) {
-					t.Fatalf("voice command description = %q, want %q", command.description, want)
-				}
-			}
-			return
-		}
-	}
-	t.Fatal("voice command definition not found")
-}
-
-func TestVoiceModePlainSpaceTypesNormally(t *testing.T) {
-	for _, releaseEvents := range []bool{false, true} {
-		t.Run(map[bool]string{false: "toggle", true: "hold"}[releaseEvents], func(t *testing.T) {
-			m := newModel(t.Context(), Options{})
-			m.dictation = batchOnlyController()
-			m.dictation.voiceModeEnabled = true
-			m.dictation.eventTypesSupported = releaseEvents
-
-			updated, cmd := m.Update(tea.KeyPressMsg(tea.Key{Code: tea.KeySpace}))
-			next := updated.(model)
-			if got := next.composerValue(); got != " " {
-				t.Fatalf("plain Space composer = %q, want one space", got)
-			}
-			if next.dictation.phase != dictIdle || cmd != nil {
-				t.Fatalf("plain Space started dictation: phase=%d cmd=%v", next.dictation.phase, cmd != nil)
-			}
-		})
-	}
-}
-
-func TestVoiceModeCtrlSpaceStartsAcrossTerminalTiers(t *testing.T) {
-	for _, releaseEvents := range []bool{false, true} {
-		t.Run(map[bool]string{false: "toggle", true: "hold"}[releaseEvents], func(t *testing.T) {
-			m := newModel(t.Context(), Options{})
-			m.dictation = batchOnlyController()
-			m.dictation.voiceModeEnabled = true
-			m.dictation.eventTypesSupported = releaseEvents
-
-			updated, cmd := m.Update(tea.KeyPressMsg(tea.Key{Code: tea.KeySpace, Mod: tea.ModCtrl}))
-			next := updated.(model)
-			if next.dictation.phase != dictStarting || cmd == nil {
-				t.Fatalf("Ctrl+Space did not start dictation: phase=%d cmd=%v", next.dictation.phase, cmd != nil)
-			}
-			if got := next.composerValue(); got != "" {
-				t.Fatalf("Ctrl+Space typed into composer: %q", got)
-			}
-		})
-	}
-}
-
-func TestVoiceModeTypingPreservesSpacesAcrossTerminalTiers(t *testing.T) {
-	for _, releaseEvents := range []bool{false, true} {
-		t.Run(map[bool]string{false: "toggle", true: "hold"}[releaseEvents], func(t *testing.T) {
-			m := newModel(t.Context(), Options{})
-			m.dictation = batchOnlyController()
-			m.dictation.voiceModeEnabled = true
-			m.dictation.eventTypesSupported = releaseEvents
-			for _, key := range []tea.Key{
-				{Code: 'f', Text: "f"},
-				{Code: 'i', Text: "i"},
-				{Code: 'x', Text: "x"},
-				{Code: tea.KeySpace},
-				{Code: 't', Text: "t"},
-				{Code: 'h', Text: "h"},
-				{Code: 'e', Text: "e"},
-			} {
-				updated, _ := m.Update(tea.KeyPressMsg(key))
-				m = updated.(model)
-			}
-			if got := m.composerValue(); got != "fix the" {
-				t.Fatalf("composer = %q, want %q", got, "fix the")
-			}
-			if m.dictation.phase != dictIdle {
-				t.Fatalf("typing started dictation: phase=%d", m.dictation.phase)
-			}
-		})
+		t.Errorf("toggle-mode Space should start recording (phase=%d)", next.dictation.phase)
 	}
 }

internal/tui/model.go

@@ -30,7 +30,6 @@ import (
 	"github.com/Gitlawb/zero/internal/peermsg"
 	"github.com/Gitlawb/zero/internal/providerhealth"
 	"github.com/Gitlawb/zero/internal/providermodeldiscovery"
-	"github.com/Gitlawb/zero/internal/providers"
 	"github.com/Gitlawb/zero/internal/providers/providerio"
 	"github.com/Gitlawb/zero/internal/sandbox"
 	"github.com/Gitlawb/zero/internal/sessions"
@@ -548,7 +547,6 @@ type model struct {
 	recapIdleArmed               bool
 	recapIdleRunID               int
 	idleRecap                    string
-	compactionModel              string // preferences.compactionModel (see providers.CompactionModelID)
 	modelPickerLoading           bool
 	modelPickerLoadingProviderID string
 	modelPickerLoadError         string
@@ -980,7 +978,6 @@ func newModel(ctx context.Context, options Options) model {
 		providerProfile:             options.ProviderProfile,
 		favoriteModels:              favoriteModelSet(options.FavoriteModels),
 		recentModels:                normalizeRecentModelEntries(options.RecentModels),
-		compactionModel:             options.CompactionModel,
 		recapsEnabled:               options.RecapsEnabled,
 		provider:                    options.Provider,
 		newProvider:                 options.NewProvider,
@@ -1539,10 +1536,10 @@ func (m model) updateModel(msg tea.Msg) (tea.Model, tea.Cmd) {
 	case tea.KeyboardEnhancementsMsg:
 		return m.handleKeyboardEnhancements(msg), nil
 	case tea.KeyReleaseMsg:
-		// Voice mode's hold-to-record ends on Ctrl+Space release; every other
-		// release event is ignored (dispatch elsewhere is press-based).
-		if m.dictation.voiceModeEnabled && voiceCaptureReleaseKey(msg) {
-			return m.handleVoiceCaptureRelease()
+		// Voice mode's hold-to-record ends on Space release; every other release
+		// event is ignored (dispatch elsewhere is press-based).
+		if m.dictation.voiceModeEnabled && keyIs(msg, tea.KeySpace) {
+			return m.handleVoiceSpaceRelease()
 		}
 		return m, nil
 	case tea.KeyPressMsg:
@@ -1676,10 +1673,11 @@ func (m model) updateModel(msg tea.Msg) (tea.Model, tea.Cmd) {
 				return m.appendSystemNotice(fmt.Sprintf("Mouse released — drag to select and copy text. Press %s again to re-enable mouse interaction (clicks, right-click paste).", mouseKey)), nil
 			}
 			return m.showTransientNoticeInline("Mouse interaction re-enabled.", transientNoticeSuccess), nil
-		case m.dictation.voiceModeEnabled && !m.transcriptDetailed && voiceCaptureKey(msg) && m.noBlockingModal():
-			// Voice mode reserves Ctrl+Space for recording; ordinary Space continues
-			// through the composer path below.
-			return m.handleVoiceCapturePress(msg)
+		case m.dictation.voiceModeEnabled && !m.transcriptDetailed && keyIs(msg, tea.KeySpace) && !keyHasMod(msg, tea.ModCtrl) && !keyAlt(msg) && m.noBlockingModal():
+			// Voice mode (/voice) repurposes Space into the record gesture — the only
+			// dictation trigger — so it must not also type a space. Turn voice mode
+			// off (/voice) to type normally.
+			return m.handleVoiceSpacePress(msg)
 		case keyIs(msg, tea.KeyEsc):
 			// Esc is heavily overloaded below (subchat exit, MCP cancel, ask-user,
 			// permission deny, wizard/picker/suggestions dismiss, ...) before ever
@@ -5484,18 +5482,6 @@ func (m model) runAgentWithOptions(runID int, runCtx context.Context, prompt str
 		// compaction (proactive + reactive) is enabled for every model, not just
 		// catalogued ones.
 		options.ContextWindow = modelregistry.AgentContextWindow(m.modelContextWindow(m.modelName))
-		// Route compaction summarization to a cheap model when one applies
-		// (env > config > curated default). The factory is lazy, re-evaluated
-		// against the model in force when the compactor asks (so an escalation
-		// away from the cheap model gains a summarizer), and the agent falls
-		// back to the main provider on any summarizer failure. Resolved against
-		// the ACTIVE profile so it tracks mid-session model switches.
-		options.Summarizer = providers.CompactionSummarizerFactory(m.providerProfile, m.compactionModel, m.newProvider)
-		// Let compaction re-derive its threshold after a mid-run escalate_model
-		// switch instead of keeping the original model's window.
-		options.ContextWindowFor = func(modelID string) int {
-			return modelregistry.AgentContextWindow(m.modelContextWindow(modelID))
-		}
 
 		// Post-edit self-correction is on by default in the TUI but kept FAST: it
 		// runs LSP diagnostics over the changed files only — cheap, change-scoped,

internal/tui/options.go

@@ -22,22 +22,18 @@ import (
 
 // Options configures the reusable Zero terminal UI shell.
 type Options struct {
-	Cwd                  string
-	Version              string // CLI build version, shown on the home screen; empty hides it
-	UserConfigPath       string
-	DoctorUserConfigPath string
-	ProjectConfigPath    string
-	ProviderName         string
-	ModelName            string
-	ProviderProfile      config.ProviderProfile
-	SavedProviders       []config.ProviderProfile // all configured providers, for the /model multi-provider list
-	FavoriteModels       []string
-	RecentModels         []config.RecentModelEntry
-	RecapsEnabled        bool
-	// CompactionModel is the resolved preferences.compactionModel value; see
-	// providers.CompactionModelID for how it combines with the env override
-	// and the curated cheap defaults.
-	CompactionModel             string
+	Cwd                         string
+	Version                     string // CLI build version, shown on the home screen; empty hides it
+	UserConfigPath              string
+	DoctorUserConfigPath        string
+	ProjectConfigPath           string
+	ProviderName                string
+	ModelName                   string
+	ProviderProfile             config.ProviderProfile
+	SavedProviders              []config.ProviderProfile // all configured providers, for the /model multi-provider list
+	FavoriteModels              []string
+	RecentModels                []config.RecentModelEntry
+	RecapsEnabled               bool
 	Provider                    zeroruntime.Provider
 	NewProvider                 func(config.ProviderProfile) (zeroruntime.Provider, error)
 	NewTurnSessionProvider      func(config.ProviderProfile, zeroruntime.Provider) zeroruntime.TurnSessionProvider

internal/tui/stt_key_prompt.go

@@ -123,7 +123,7 @@ func (m model) finalizeSTTModelFromKey(p *sttKeyPromptState, prefix string) (tea
 	if modelID != "" {
 		label += " " + modelID
 	}
-	return m.showTransientNoticeInline(prefix+"Dictation model: "+label+". Run /voice; "+voiceCaptureUsage+".", transientNoticeSuccess), nil
+	return m.showTransientNoticeInline(prefix+"Dictation model: "+label+". Run /voice, then hold Space to dictate.", transientNoticeSuccess), nil
 }
 
 // sttKeyPromptOverlay renders the API-key prompt as a centered modal, matching

internal/tui/stt_model_picker.go

@@ -226,7 +226,7 @@ func (m model) handleSTTModelSelection(value string) (model, string) {
 			// instead); this is the manual-setup path (e.g. Termux).
 			hint += " Set stt.localModelPath to a model directory (see docs/dictation.md)."
 		} else {
-			hint += " Run /voice; " + voiceCaptureUsage + "."
+			hint += " Run /voice, then hold Space to dictate."
 		}
 		return m, hint
 	}