test(lockutil): require one concurrent holder

README.md

@@ -273,19 +273,6 @@ zero sandbox grants list
 Zero includes local file/search/edit/shell tools, `web_fetch` for public URLs,
 and MCP support for additional tools.
 
-`web_fetch` refuses loopback, private and other special-use addresses: it checks
-the URL before asking permission, resolves the host, and dials the address it
-validated so a name cannot resolve to something else in between.
-
-If `HTTP_PROXY`/`HTTPS_PROXY` is set, `web_fetch` and the provider connectivity
-probe use it, and that last step changes: the proxy is dialed and the target
-hostname is sent to it, so the proxy decides which address the request actually
-reaches. The URL is still checked and resolved locally first, but a proxy that
-answers differently can reach a private service. A forward proxy already sees
-and can rewrite every request through it, so this is the trust you accept by
-configuring one. Leave the variables unset for the checks to be enforced end to
-end.
-
 For local dev servers, use shell commands such as `curl` through `exec_command`
 so the normal sandbox and permission policy applies. Long-running commands stay
 attached to a background terminal session and can be listed or stopped from the
@@ -384,13 +371,9 @@ go run ./cmd/zero-perf-bench
 
 Experimental: `ZERO_OPENAI_TURN_SESSION=1` enables the optimized OpenAI turn
 session (background connection prewarm + request-prefix telemetry) for headless
-`zero exec` runs against official OpenAI profiles. Off by default; `0`, `false`,
-or `off` disable it. A/B-benchmark it by running the same `zero-perf-bench` suite
-with the variable unset and set.
-
-Native ChatGPT Responses sessions are enabled by default. Set
-`ZERO_CHATGPT_TURN_SESSION=0`, `false`, or `off` to restore stateless HTTP/SSE
-transport.
+`zero exec` runs against official OpenAI profiles. Off by default; `0`/`false`
+disable. A/B-benchmark it by running the same `zero-perf-bench` suite with the
+variable unset and set.
 
 ### Code Quality and Security Checks
 

docs/HOW_ZERO_WORKS.md

@@ -627,12 +627,7 @@ Core tool groups include:
   skills, `ask_user`, permission requests.
 - **Write tools**: `write_file`, `edit_file`, `apply_patch`, `update_plan`.
 - **Shell tools**: `exec_command`, `write_stdin`, legacy `bash`.
-- **Network tools**: `web_fetch` and optional web search backend. `web_fetch`
-  validates the URL before the permission prompt, refuses loopback/private/
-  special-use addresses, and dials the address it resolved. With
-  `HTTP_PROXY`/`HTTPS_PROXY` set, the proxy is dialed instead and resolves the
-  target itself, so destination enforcement ends at the proxy; see the note in
-  the README.
+- **Network tools**: `web_fetch` and optional web search backend.
 - **Local-control tools**: config-gated wrappers for browser, terminal, desktop,
   and artifact helpers backed by packages such as `internal/localcontrol` and
   `internal/browser`.

go.mod

@@ -4,7 +4,7 @@ go 1.26.6
 
 require (
 	charm.land/bubbles/v2 v2.1.1
-	charm.land/bubbletea/v2 v2.0.9
+	charm.land/bubbletea/v2 v2.0.8
 	charm.land/lipgloss/v2 v2.0.5
 	github.com/Microsoft/go-winio v0.6.2
 	github.com/alecthomas/chroma/v2 v2.27.0

go.sum

@@ -1,7 +1,7 @@
 charm.land/bubbles/v2 v2.1.1 h1:7r55WzBxpo/R3z98hGmY7KKPd3ET6vsf0Fb9sDHOV60=
 charm.land/bubbles/v2 v2.1.1/go.mod h1:GE6M31gaWZVXzGw73OeuTTgy4lX+OtkH0E5ymnNsHxo=
-charm.land/bubbletea/v2 v2.0.9 h1:DpJCMWKgzQK8SJv4zbKKFHAI10ymWy/evClPFk0k0f8=
-charm.land/bubbletea/v2 v2.0.9/go.mod h1:2SkdgoTXluXJHOUwAoRlRXF/28vklb1rFl6GcgV1/ss=
+charm.land/bubbletea/v2 v2.0.8 h1:SxTJMhCAI3lbPmy4SgX5LWZ24AdINr4I6UEqzZvYJuY=
+charm.land/bubbletea/v2 v2.0.8/go.mod h1:2SkdgoTXluXJHOUwAoRlRXF/28vklb1rFl6GcgV1/ss=
 charm.land/lipgloss/v2 v2.0.5 h1:kbNxgeeUOYv5J0YdpxFjfvf3dFvqH8Aci4zB6xqFtrY=
 charm.land/lipgloss/v2 v2.0.5/go.mod h1:9oqhxt4yxIMe6q5A4kHr44DremZk7J9UNh74GlWa5nc=
 github.com/Microsoft/go-winio v0.6.2 h1:F2VQgta7ecxGYO8k3ZZz3RS8fVIXVxONVUPlNERoyfY=
@@ -64,6 +64,8 @@ github.com/xo/terminfo v0.0.0-20220910002029-abceb7e1c41e h1:JVG44RsyaB9T2KIHavM
 github.com/xo/terminfo v0.0.0-20220910002029-abceb7e1c41e/go.mod h1:RbqR21r5mrJuqunuUZ/Dhy/avygyECGrLceyNeo4LiM=
 golang.org/x/exp v0.0.0-20260611194520-c48552f49976 h1:X8Hz2ImujgbmetVuW+w2YkyZChE3cBpZi2P158rTG9M=
 golang.org/x/exp v0.0.0-20260611194520-c48552f49976/go.mod h1:vnf4pv9iKZXY58sQE1L86zmNWJ4159e1RkcWiLCkeEY=
+golang.org/x/image v0.44.0 h1:+tDekMZED9+LrtB3G5xzRggpVh9CARjZqROla3R3R+I=
+golang.org/x/image v0.44.0/go.mod h1:V8K3KE9KKKE+pLpQDOeN18w9oacNSvy1tDOirTu4xtY=
 golang.org/x/image v0.45.0 h1:FMb1nTbH5H9vF55SriQHgFw5GnNL9Jg6L25BwXKzhB0=
 golang.org/x/image v0.45.0/go.mod h1:n62x/7RqlwXDvGsSU4u6IUTUf6KghUZ9Bt7cG/T9Fx4=
 golang.org/x/sync v0.22.0 h1:SZjpbeLmrCk4xhRSZFNZW5gFUeCeFgjekvI/+gfScek=

internal/acp/permission.go

@@ -142,15 +142,13 @@ func actionOffered(optionID string, offered []PermissionOption) bool {
 // session/request_permission request from a ZERO permission request.
 func permissionToolCall(req agent.PermissionRequest) ToolCallUpdate {
 	args := marshalArgs(req.Args)
-	upd := ToolCallUpdate{
+	return ToolCallUpdate{
 		ToolCallID: req.ToolCallID,
 		Title:      toolTitle(req.ToolName, string(args)),
 		Kind:       toolKindFor(req.ToolName),
 		Status:     ToolStatusPending,
 		RawInput:   rawInputBytes(args),
 	}
-	attachBrowserToolDetails(&upd, req.ToolName)
-	return upd
 }
 
 func marshalArgs(args map[string]any) []byte {

internal/acp/permission_test.go

@@ -82,17 +82,3 @@ func TestPermissionToolCall(t *testing.T) {
 		t.Error("expected rawInput from args")
 	}
 }
-
-func TestPermissionToolCallKeepsTheBrowserDescriptor(t *testing.T) {
-	call := permissionToolCall(agent.PermissionRequest{
-		ToolCallID: "browser-1",
-		ToolName:   "browser_connect",
-		Args:       map[string]any{"target": "127.0.0.1:9222"},
-	})
-	if got := browserDescriptor(t, call); got != (BrowserToolDetails{Version: 1, Command: "connect"}) {
-		t.Fatalf("browser descriptor = %#v", got)
-	}
-	if call.Title != "browser connect" {
-		t.Fatalf("title = %q", call.Title)
-	}
-}

internal/acp/translate.go

@@ -2,9 +2,7 @@ package acp
 
 import (
 	"encoding/json"
-	"net/url"
 	"strings"
-	"unicode"
 	"unicode/utf8"
 
 	"github.com/Gitlawb/zero/internal/agent"
@@ -46,125 +44,12 @@ func toolKindFor(name string) string {
 
 // toolTitle builds a concise human title, e.g. "read_file src/main.go".
 func toolTitle(name, rawArgs string) string {
-	if browser, ok := browserToolDetails(name); ok {
-		return browserToolTitle(browser.Command, rawArgs)
-	}
 	if hint := primaryArgHint(rawArgs); hint != "" {
 		return name + " " + hint
 	}
 	return name
 }
 
-// browserToolDetails identifies ZERO's local browser helpers without treating
-// similarly named MCP tools as browser automation. The descriptor intentionally
-// contains no request data: ACP tool input is already protocol-visible, but a
-// durable UI must not need to retain text, local CDP targets, or full URLs just
-// to recognise the browser operation.
-func browserToolDetails(name string) (*BrowserToolDetails, bool) {
-	const prefix = "browser_"
-	command, ok := strings.CutPrefix(name, prefix)
-	if !ok {
-		return nil, false
-	}
-	switch command {
-	case "install", "launch", "connect", "open", "snapshot", "click", "type", "press", "action":
-		return &BrowserToolDetails{Version: 1, Command: command}, true
-	default:
-		return nil, false
-	}
-}
-
-const zeroBrowserMetaKey = "github.com/Gitlawb/zero/browser"
-
-// attachBrowserToolDetails stores ZERO's browser descriptor in ACP's reserved
-// extension channel. Keeping this in one helper prevents start, result, and
-// permission payloads from drifting onto different wire shapes.
-func attachBrowserToolDetails(update *ToolCallUpdate, name string) {
-	browser, ok := browserToolDetails(name)
-	if !ok {
-		return
-	}
-	raw, err := json.Marshal(browser)
-	if err != nil {
-		return
-	}
-	update.Meta = map[string]json.RawMessage{zeroBrowserMetaKey: raw}
-}
-
-// browserToolTitle avoids putting browser_type text, an attached DevTools
-// endpoint, or a URL query/fragment in a tool-card title. Those values can
-// carry credentials or session data; the UI only needs the operation and, for
-// navigation, a human-recognisable origin.
-func browserToolTitle(command, rawArgs string) string {
-	switch command {
-	case "action":
-		action, ok := exactJSONStringArg(rawArgs, "command")
-		if !ok {
-			return "browser action"
-		}
-		if action, ok := tools.NormalizedBrowserActionCommand(action); ok {
-			return "browser action " + action
-		}
-		return "browser action"
-	case "open":
-		rawURL, ok := exactJSONStringArg(rawArgs, "url")
-		if !ok {
-			return "browser open"
-		}
-		normalized, err := tools.NormalizeBrowserOpenURL(rawURL)
-		if err != nil {
-			return "browser open"
-		}
-		u, err := url.Parse(normalized)
-		if err != nil || u.Scheme == "" || u.Host == "" {
-			return "browser open"
-		}
-		origin := u.Scheme + "://" + u.Host
-		if !browserTitleTextSafe(origin) {
-			return "browser open"
-		}
-		return "browser open " + truncateHint(origin)
-	default:
-		return "browser " + command
-	}
-}
-
-// browserTitleTextSafe validates text after URL parsing has decoded escaped
-// UTF-8 in the host. Valid UTF-8 alone is not presentation-safe: control,
-// format/bidi, and line/paragraph separator runes can reorder or split the
-// permission label shown to a user. The execution URL remains unchanged.
-func browserTitleTextSafe(text string) bool {
-	if !utf8.ValidString(text) {
-		return false
-	}
-	for _, r := range text {
-		if unicode.IsControl(r) || unicode.Is(unicode.Cf, r) || unicode.Is(unicode.Zl, r) || unicode.Is(unicode.Zp, r) {
-			return false
-		}
-	}
-	return true
-}
-
-// exactJSONStringArg mirrors ZERO's map-based tool argument decoding: only the
-// exact JSON key is considered, and a non-string value is invalid. In
-// particular, an incidental "URL" key must not change a permission title when
-// browser_open will only read "url".
-func exactJSONStringArg(rawArgs, key string) (string, bool) {
-	var args map[string]json.RawMessage
-	if json.Unmarshal([]byte(rawArgs), &args) != nil {
-		return "", false
-	}
-	raw, ok := args[key]
-	if !ok {
-		return "", false
-	}
-	var value string
-	if json.Unmarshal(raw, &value) != nil {
-		return "", false
-	}
-	return value, true
-}
-
 // primaryArgHint extracts the most relevant argument (path/pattern/command) from
 // raw JSON arguments. Best-effort; returns "" when it can't parse.
 func primaryArgHint(rawArgs string) string {
@@ -204,7 +89,7 @@ func rawInput(args string) json.RawMessage {
 // toolCallStart maps an advertised ZERO tool call to the initial ACP "tool_call"
 // update (status in_progress — ZERO executes immediately after advertising).
 func toolCallStart(call agent.ToolCall) ToolCallUpdate {
-	upd := ToolCallUpdate{
+	return ToolCallUpdate{
 		SessionUpdate: UpdateToolCall,
 		ToolCallID:    call.ID,
 		Title:         toolTitle(call.Name, call.Arguments),
@@ -212,8 +97,6 @@ func toolCallStart(call agent.ToolCall) ToolCallUpdate {
 		Status:        ToolStatusInProgress,
 		RawInput:      rawInput(call.Arguments),
 	}
-	attachBrowserToolDetails(&upd, call.Name)
-	return upd
 }
 
 // toolCallResult maps a finished ZERO tool result to a "tool_call_update".
@@ -233,7 +116,6 @@ func toolCallResult(result agent.ToolResult) ToolCallUpdate {
 	if locs := toolResultLocations(result); len(locs) > 0 {
 		upd.Locations = locs
 	}
-	attachBrowserToolDetails(&upd, result.Name)
 	return upd
 }
 

internal/acp/translate_test.go

@@ -1,29 +1,14 @@
 package acp
 
 import (
-	"encoding/json"
 	"strings"
 	"testing"
-	"unicode"
 	"unicode/utf8"
 
 	"github.com/Gitlawb/zero/internal/agent"
 	"github.com/Gitlawb/zero/internal/tools"
 )
 
-func browserDescriptor(t *testing.T, update ToolCallUpdate) BrowserToolDetails {
-	t.Helper()
-	raw, ok := update.Meta[zeroBrowserMetaKey]
-	if !ok {
-		t.Fatalf("browser metadata = %#v, want %q", update.Meta, zeroBrowserMetaKey)
-	}
-	var details BrowserToolDetails
-	if err := json.Unmarshal(raw, &details); err != nil {
-		t.Fatalf("decode browser metadata: %v", err)
-	}
-	return details
-}
-
 func TestAgentMessageAndThoughtChunks(t *testing.T) {
 	m := agentMessageChunk("hello")
 	if m.SessionUpdate != UpdateAgentMessageChunk || m.Content.Type != "text" || m.Content.Text != "hello" {
@@ -71,217 +56,6 @@ func TestToolTitleAndHint(t *testing.T) {
 	}
 }
 
-func TestBrowserToolUpdatesAreStructuredAndPresentationSafe(t *testing.T) {
-	start := toolCallStart(agent.ToolCall{
-		ID:        "browser-1",
-		Name:      "browser_open",
-		Arguments: `{"url":"https://example.com/settings?token=not-for-a-title#account"}`,
-	})
-	if got := browserDescriptor(t, start); got != (BrowserToolDetails{Version: 1, Command: "open"}) {
-		t.Fatalf("browser descriptor = %#v, want open", got)
-	}
-	if start.Title != "browser open https://example.com" {
-		t.Fatalf("browser title = %q", start.Title)
-	}
-	if strings.Contains(start.Title, "token=") || strings.Contains(start.Title, "#account") {
-		t.Fatalf("browser title leaked URL-sensitive data: %q", start.Title)
-	}
-	encoded, err := json.Marshal(start)
-	if err != nil {
-		t.Fatal(err)
-	}
-	var wire struct {
-		Meta map[string]json.RawMessage `json:"_meta"`
-	}
-	if err := json.Unmarshal(encoded, &wire); err != nil {
-		t.Fatal(err)
-	}
-	if _, ok := wire.Meta[zeroBrowserMetaKey]; !ok {
-		t.Fatalf("browser wire metadata = %#v", wire.Meta)
-	}
-
-	typed := toolCallStart(agent.ToolCall{
-		ID:        "browser-2",
-		Name:      "browser_type",
-		Arguments: `{"ref":"email","text":"[email protected]"}`,
-	})
-	if got := browserDescriptor(t, typed); got.Command != "type" {
-		t.Fatalf("browser type descriptor = %#v", got)
-	}
-	if typed.Title != "browser type" || strings.Contains(typed.Title, "[email protected]") {
-		t.Fatalf("browser type title = %q", typed.Title)
-	}
-
-	action := toolCallStart(agent.ToolCall{
-		ID:        "browser-3",
-		Name:      "browser_action",
-		Arguments: `{"command":"keyboard_insert_text","args":["[email protected]"]}`,
-	})
-	if action.Title != "browser action keyboard_insert_text" {
-		t.Fatalf("browser action title = %q", action.Title)
-	}
-
-	result := toolCallResult(agent.ToolResult{
-		ToolCallID: "browser-2",
-		Name:       "browser_type",
-		Status:     tools.StatusOK,
-	})
-	if got := browserDescriptor(t, result); got.Command != "type" {
-		t.Fatalf("browser result descriptor = %#v", got)
-	}
-}
-
-func TestBrowserDescriptorSurvivesProtocolShapedRoundTrip(t *testing.T) {
-	updates := []ToolCallUpdate{
-		toolCallStart(agent.ToolCall{
-			ID:        "start",
-			Name:      "browser_open",
-			Arguments: `{"url":"https://user:[email protected]/private?token=secret#fragment"}`,
-		}),
-		toolCallResult(agent.ToolResult{
-			ToolCallID: "result",
-			Name:       "browser_type",
-			Status:     tools.StatusOK,
-		}),
-		permissionToolCall(agent.PermissionRequest{
-			ToolCallID: "permission",
-			ToolName:   "browser_connect",
-			Args:       map[string]any{"target": "127.0.0.1:9222"},
-		}),
-	}
-
-	type protocolToolCallUpdate struct {
-		SessionUpdate string                     `json:"sessionUpdate,omitempty"`
-		ToolCallID    string                     `json:"toolCallId"`
-		Title         string                     `json:"title,omitempty"`
-		Kind          string                     `json:"kind,omitempty"`
-		Status        string                     `json:"status,omitempty"`
-		RawInput      json.RawMessage            `json:"rawInput,omitempty"`
-		Content       []ToolCallContent          `json:"content,omitempty"`
-		Locations     []ToolCallLocation         `json:"locations,omitempty"`
-		Meta          map[string]json.RawMessage `json:"_meta,omitempty"`
-	}
-
-	for _, update := range updates {
-		encoded, err := json.Marshal(update)
-		if err != nil {
-			t.Fatal(err)
-		}
-		var root map[string]json.RawMessage
-		if err := json.Unmarshal(encoded, &root); err != nil {
-			t.Fatal(err)
-		}
-		if _, ok := root["browser"]; ok {
-			t.Fatalf("browser descriptor escaped ACP _meta: %s", encoded)
-		}
-
-		var protocol protocolToolCallUpdate
-		if err := json.Unmarshal(encoded, &protocol); err != nil {
-			t.Fatal(err)
-		}
-		forwarded, err := json.Marshal(protocol)
-		if err != nil {
-			t.Fatal(err)
-		}
-		var roundTripped ToolCallUpdate
-		if err := json.Unmarshal(forwarded, &roundTripped); err != nil {
-			t.Fatal(err)
-		}
-		details := browserDescriptor(t, roundTripped)
-		if details.Version != 1 || details.Command == "" {
-			t.Fatalf("round-tripped browser descriptor = %#v", details)
-		}
-		descriptorJSON := string(roundTripped.Meta[zeroBrowserMetaKey])
-		for _, secret := range []string{"password", "private", "token", "fragment", "127.0.0.1", "9222"} {
-			if strings.Contains(descriptorJSON, secret) {
-				t.Fatalf("browser descriptor leaked %q: %s", secret, descriptorJSON)
-			}
-		}
-	}
-}
-
-func TestBrowserPermissionTitlesMirrorSafeToolArguments(t *testing.T) {
-	if got := browserToolTitle("open", `{"url":"evil.example.test/pay?token=hidden#fragment"}`); got != "browser open https://evil.example.test" {
-		t.Fatalf("bare-host title = %q", got)
-	}
-	if got := browserToolTitle("open", `{"URL":"https://different.example.test"}`); got != "browser open" {
-		t.Fatalf("case-variant URL title = %q", got)
-	}
-	if got := browserToolTitle("open", `{"URL":"https://different.example.test","url":"https://actual.example.test/path"}`); got != "browser open https://actual.example.test" {
-		t.Fatalf("exact URL key title = %q", got)
-	}
-	if got := browserToolTitle("action", `{"command":"not an action"}`); got != "browser action" {
-		t.Fatalf("unknown browser action title = %q", got)
-	}
-
-	longHost := "https://" + strings.Repeat("a", 200) + ".example.test/path?token=hidden"
-	title := browserToolTitle("open", `{"url":"`+longHost+`"}`)
-	if !utf8.ValidString(title) || utf8.RuneCountInString(title) > len("browser open ")+61 || strings.Contains(title, "token=") {
-		t.Fatalf("bounded browser origin title = %q", title)
-	}
-}
-
-func TestBrowserOpenTitlesRejectDecodedUnicodePresentationControls(t *testing.T) {
-	for _, rawURL := range []string{
-		"https://safe.example%E2%80%AEevil.test/path",
-		"https://safe.example%E2%81%A6evil.test/path",
-		"https://safe.example%C2%85evil.test/path",
-		"https://safe.example%E2%80%A8evil.test/path",
-		"https://safe.example%E2%80%A9evil.test/path",
-	} {
-		t.Run(rawURL, func(t *testing.T) {
-			normalized, err := tools.NormalizeBrowserOpenURL(rawURL)
-			if err != nil {
-				t.Fatalf("execution URL rejected: %v", err)
-			}
-			if normalized != rawURL {
-				t.Fatalf("execution URL = %q, want unchanged %q", normalized, rawURL)
-			}
-
-			args, err := json.Marshal(map[string]any{"url": rawURL})
-			if err != nil {
-				t.Fatal(err)
-			}
-			updates := []ToolCallUpdate{
-				toolCallStart(agent.ToolCall{ID: "start", Name: "browser_open", Arguments: string(args)}),
-				permissionToolCall(agent.PermissionRequest{ToolCallID: "permission", ToolName: "browser_open", Args: map[string]any{"url": rawURL}}),
-			}
-			for _, update := range updates {
-				encoded, err := json.Marshal(update)
-				if err != nil {
-					t.Fatal(err)
-				}
-				var decoded ToolCallUpdate
-				if err := json.Unmarshal(encoded, &decoded); err != nil {
-					t.Fatal(err)
-				}
-				if decoded.Title != "browser open" {
-					t.Fatalf("unsafe browser title survived wire round trip: %q", decoded.Title)
-				}
-				for _, r := range decoded.Title {
-					if unicode.IsControl(r) || unicode.Is(unicode.Cf, r) || unicode.Is(unicode.Zl, r) || unicode.Is(unicode.Zp, r) {
-						t.Fatalf("browser title contains unsafe presentation rune %U: %q", r, decoded.Title)
-					}
-				}
-			}
-		})
-	}
-}
-
-func TestBrowserDescriptorDoesNotClaimSimilarlyNamedMCPTools(t *testing.T) {
-	start := toolCallStart(agent.ToolCall{ID: "mcp-1", Name: "browser_plugin_open", Arguments: `{}`})
-	if len(start.Meta) != 0 {
-		t.Fatalf("MCP-like tool received built-in browser metadata: %#v", start.Meta)
-	}
-	encoded, err := json.Marshal(start)
-	if err != nil {
-		t.Fatal(err)
-	}
-	if strings.Contains(string(encoded), `"browser"`) {
-		t.Fatalf("non-browser tool encoded browser field: %s", encoded)
-	}
-}
-
 func TestToolCallStart(t *testing.T) {
 	upd := toolCallStart(agent.ToolCall{ID: "tc1", Name: "read_file", Arguments: `{"path":"a.go"}`})
 	if upd.SessionUpdate != UpdateToolCall {

internal/acp/types.go

@@ -210,21 +210,6 @@ type ToolCallUpdate struct {
 	RawInput      json.RawMessage    `json:"rawInput,omitempty"`
 	Content       []ToolCallContent  `json:"content,omitempty"`
 	Locations     []ToolCallLocation `json:"locations,omitempty"`
-	// Meta is ACP's extension channel. ZERO-owned values must remain beneath a
-	// namespaced key so protocol-shaped clients can preserve them while decoding
-	// and re-encoding a tool call.
-	Meta map[string]json.RawMessage `json:"_meta,omitempty"`
-}
-
-// BrowserToolDetails identifies the browser helper operation behind a tool
-// call. Version is the schema version for this optional ZERO extension;
-// Command is one of install, launch, connect, open, snapshot, click, type,
-// press, or action. Future fields must remain display-safe and must not
-// include browser profile data, cookies, typed text, URL paths/queries, or
-// DevTools endpoints.
-type BrowserToolDetails struct {
-	Version int    `json:"version"`
-	Command string `json:"command"`
 }
 
 // ToolCallContent is a tool call's rendered output. ZERO emits "content" (a

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"
@@ -146,17 +144,11 @@ func estimateToolDefTokens(tools []zeroruntime.ToolDefinition) int {
 	for _, tool := range tools {
 		total += ApproxTextTokens(tool.Name)
 		total += ApproxTextTokens(tool.Description)
-		total += ApproxTextTokens(string(tool.Type))
 		if len(tool.Parameters) > 0 {
 			if encoded, err := json.Marshal(tool.Parameters); err == nil {
 				total += ApproxTextTokens(string(encoded))
 			}
 		}
-		if tool.Format != nil {
-			total += ApproxTextTokens(tool.Format.Type)
-			total += ApproxTextTokens(tool.Format.Syntax)
-			total += ApproxTextTokens(tool.Format.Definition)
-		}
 		total += 4 // per-tool overhead
 	}
 	return total
@@ -398,27 +390,6 @@ 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 +424,17 @@ 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 +528,10 @@ 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 +571,11 @@ 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 +659,8 @@ 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 +670,13 @@ 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/compaction_projection.go

@@ -126,11 +126,8 @@ func capCompactionBrief(brief string) (string, bool) {
 
 func compactionToolCallLine(call zeroruntime.ToolCall) string {
 	detail := ""
-	if call.Freeform && call.Name == "apply_patch" {
-		detail = strings.Join(patchPaths(call.Arguments), ", ")
-	}
 	var arguments map[string]any
-	if detail == "" && json.Unmarshal([]byte(strings.TrimSpace(call.Arguments)), &arguments) == nil {
+	if json.Unmarshal([]byte(strings.TrimSpace(call.Arguments)), &arguments) == nil {
 		for _, key := range []string{"file_path", "path", "url", "query", "pattern", "prompt", "description", "question"} {
 			if value, ok := arguments[key].(string); ok && strings.TrimSpace(value) != "" {
 				detail = value

internal/agent/compaction_projection_test.go

@@ -73,7 +73,6 @@ func TestProjectCompactionInputRetainsAskUserExchangeAndSemanticArguments(t *tes
 		{Role: zeroruntime.MessageRoleTool, ToolCallID: "ask", Content: "Which database should remain?: Postgres only; do not touch MySQL."},
 		{Role: zeroruntime.MessageRoleAssistant, ToolCalls: []zeroruntime.ToolCall{
 			{ID: "patch", Name: "apply_patch", Arguments: `{"patch":"*** Begin Patch\n*** Update File: internal/db.go\n*** End Patch"}`},
-			{ID: "raw-patch", Name: "apply_patch", Freeform: true, Arguments: "*** Begin Patch\n*** Update File: internal/api.go\n*** Add File: internal/config.go\n*** End Patch\n"},
 			{ID: "fetch", Name: "web_fetch", Arguments: `{"url":"https://example.com/spec"}`},
 			{ID: "task", Name: "task", Arguments: `{"prompt":"Inspect the Windows implementation"}`},
 		}},
@@ -81,7 +80,7 @@ func TestProjectCompactionInputRetainsAskUserExchangeAndSemanticArguments(t *tes
 	}
 
 	content := projectCompactionInput(messages).messages[0].Content
-	for _, want := range []string{"Which database should remain?", "Postgres only; do not touch MySQL", "internal/db.go", "internal/api.go", "internal/config.go", "https://example.com/spec", "Inspect the Windows implementation"} {
+	for _, want := range []string{"Which database should remain?", "Postgres only; do not touch MySQL", "internal/db.go", "https://example.com/spec", "Inspect the Windows implementation"} {
 		if !strings.Contains(content, want) {
 			t.Fatalf("projection missing %q: %q", want, content)
 		}

internal/agent/compaction_test.go

@@ -275,27 +275,6 @@ func TestEstimateToolDefTokensCountsDefinitions(t *testing.T) {
 	if estimateToolDefTokens(one) <= 0 {
 		t.Fatal("a tool definition (name + description + schema) should estimate > 0 tokens")
 	}
-	typed := append([]zeroruntime.ToolDefinition(nil), one...)
-	typed[0].Type = zeroruntime.ToolDefinitionFreeform
-	if estimateToolDefTokens(typed) <= estimateToolDefTokens(one) {
-		t.Fatal("a non-empty tool type must increase the estimated request cost")
-	}
-	for _, test := range []struct {
-		name   string
-		format zeroruntime.ToolDefinitionFormat
-	}{
-		{name: "type", format: zeroruntime.ToolDefinitionFormat{Type: "grammar"}},
-		{name: "syntax", format: zeroruntime.ToolDefinitionFormat{Syntax: "lark"}},
-		{name: "definition", format: zeroruntime.ToolDefinitionFormat{Definition: "start: WORD"}},
-	} {
-		t.Run("format "+test.name, func(t *testing.T) {
-			formatted := append([]zeroruntime.ToolDefinition(nil), one...)
-			formatted[0].Format = &test.format
-			if estimateToolDefTokens(formatted) <= estimateToolDefTokens(one) {
-				t.Fatalf("a non-empty format %s must increase the estimated request cost", test.name)
-			}
-		})
-	}
 	two := append(append([]zeroruntime.ToolDefinition{}, one...), zeroruntime.ToolDefinition{
 		Name:        "write_file",
 		Description: "Write contents to a file in the workspace.",

internal/agent/context_planner.go

@@ -102,10 +102,6 @@ func copyToolDefinitions(toolDefs []zeroruntime.ToolDefinition) []zeroruntime.To
 	for index, definition := range toolDefs {
 		copied[index] = definition
 		copied[index].Parameters = copySchemaMap(definition.Parameters)
-		if definition.Format != nil {
-			format := *definition.Format
-			copied[index].Format = &format
-		}
 	}
 	return copied
 }

internal/agent/context_planner_test.go

@@ -15,7 +15,6 @@ func TestContextPlannerPreservesProviderRequest(t *testing.T) {
 	}
 	toolDefs := []zeroruntime.ToolDefinition{{
 		Name: "read_file", Description: "Read a file",
-		Format: &zeroruntime.ToolDefinitionFormat{Type: "grammar", Syntax: "lark", Definition: "start: PATH"},
 		Parameters: map[string]any{
 			"type":       "object",
 			"required":   []string{"path"},
@@ -54,12 +53,10 @@ func TestContextPlannerPreservesProviderRequest(t *testing.T) {
 	toolDefs[0].Parameters["required"].([]string)[0] = "other"
 	toolDefs[0].Parameters["properties"].(map[string]any)["path"].(map[string]any)["type"] = "integer"
 	toolDefs[0].Parameters["anyOf"].([]any)[0].(map[string]any)["type"] = "array"
-	toolDefs[0].Format.Definition = "changed"
 	if plan.Request.Messages[1].Content != "inspect this" || plan.Request.Messages[1].Images[0].Data[0] != 1 {
 		t.Fatalf("planned messages alias caller state: %#v", plan.Request.Messages[1])
 	}
 	if plan.Request.Tools[0].Name != "read_file" ||
-		plan.Request.Tools[0].Format == nil || plan.Request.Tools[0].Format.Definition != "start: PATH" ||
 		plan.Request.Tools[0].Parameters["required"].([]string)[0] != "path" ||
 		plan.Request.Tools[0].Parameters["properties"].(map[string]any)["path"].(map[string]any)["type"] != "string" ||
 		plan.Request.Tools[0].Parameters["anyOf"].([]any)[0].(map[string]any)["type"] != "object" {

internal/agent/freeform_tool_test.go

@@ -1,378 +0,0 @@
-package agent
-
-import (
-	"context"
-	"os"
-	"path/filepath"
-	"runtime"
-	"strings"
-	"testing"
-
-	"github.com/Gitlawb/zero/internal/sandbox"
-	"github.com/Gitlawb/zero/internal/tools"
-	"github.com/Gitlawb/zero/internal/zeroruntime"
-)
-
-type customApplyPatchTool struct {
-	calls int
-}
-
-type fixedPathScope struct {
-	roots []string
-}
-
-func (scope fixedPathScope) Roots() []string {
-	return append([]string(nil), scope.roots...)
-}
-
-func newFixedPathScope(t *testing.T, roots ...string) fixedPathScope {
-	t.Helper()
-	resolved := make([]string, 0, len(roots))
-	for _, root := range roots {
-		absolute, err := filepath.Abs(root)
-		if err != nil {
-			t.Fatalf("Abs(%q): %v", root, err)
-		}
-		if physical, err := filepath.EvalSymlinks(absolute); err == nil {
-			absolute = physical
-		}
-		resolved = append(resolved, absolute)
-	}
-	return fixedPathScope{roots: resolved}
-}
-
-func (*customApplyPatchTool) Name() string        { return "apply_patch" }
-func (*customApplyPatchTool) Description() string { return "custom JSON tool" }
-func (*customApplyPatchTool) Parameters() tools.Schema {
-	return tools.Schema{Type: "object", Properties: map[string]tools.PropertySchema{"value": {Type: "string"}}}
-}
-func (*customApplyPatchTool) Safety() tools.Safety {
-	return tools.Safety{Permission: tools.PermissionAllow, SideEffect: tools.SideEffectRead}
-}
-func (tool *customApplyPatchTool) Run(context.Context, map[string]any) tools.Result {
-	tool.calls++
-	return tools.Result{Status: tools.StatusOK}
-}
-
-func TestFreeformApplyPatchUsesExistingToolExecutionPath(t *testing.T) {
-	root := t.TempDir()
-	registry := tools.NewRegistry()
-	registry.Register(tools.NewScopedApplyPatchTool(root, nil))
-	patch := "*** Begin Patch\n*** Add File: hello.txt\n+hello\n*** End Patch\n"
-
-	result, err := executeToolCall(context.Background(), registry, zeroruntime.ToolCall{
-		ID:        "call-1",
-		Name:      "apply_patch",
-		Arguments: patch,
-		Freeform:  true,
-	}, PermissionModeUnsafe, Options{Cwd: root, FileTracker: tools.NewFileTracker()})
-	if err != nil {
-		t.Fatalf("executeToolCall: %v", err)
-	}
-	if result.Status != tools.StatusOK {
-		t.Fatalf("freeform apply_patch status = %s: %s", result.Status, result.Output)
-	}
-	content, err := os.ReadFile(filepath.Join(root, "hello.txt"))
-	if err != nil {
-		t.Fatalf("read patched file: %v", err)
-	}
-	if string(content) != "hello\n" {
-		t.Fatalf("patched content = %q, want hello newline", content)
-	}
-}
-
-func TestFreeformApplyPatchSupportsGrantedExtraRoot(t *testing.T) {
-	root := t.TempDir()
-	extra := t.TempDir()
-	scope, err := sandbox.NewScope(root, []string{extra})
-	if err != nil {
-		t.Fatalf("NewScope: %v", err)
-	}
-	registry := tools.NewRegistry()
-	registry.Register(tools.NewScopedApplyPatchTool(root, scope))
-	target := filepath.Join(extra, "hello.txt")
-	patch := "*** Begin Patch\n*** Add File: " + target + "\n+hello\n*** End Patch\n"
-
-	result, err := executeToolCall(context.Background(), registry, zeroruntime.ToolCall{
-		ID: "call-1", Name: "apply_patch", Arguments: patch, Freeform: true,
-	}, PermissionModeUnsafe, Options{Cwd: root, FileTracker: tools.NewFileTracker()})
-	if err != nil {
-		t.Fatalf("executeToolCall: %v", err)
-	}
-	if result.Status != tools.StatusOK {
-		t.Fatalf("freeform extra-root apply_patch status = %s: %s", result.Status, result.Output)
-	}
-	content, err := os.ReadFile(target)
-	if err != nil {
-		t.Fatalf("read extra-root patched file: %v", err)
-	}
-	if string(content) != "hello\n" {
-		t.Fatalf("patched content = %q, want hello newline", content)
-	}
-}
-
-func TestFreeformApplyPatchRejectsMixedWorkspaceAndExtraRoots(t *testing.T) {
-	for _, extraHasMatchingPath := range []bool{false, true} {
-		name := "extra target missing"
-		if extraHasMatchingPath {
-			name = "extra target exists"
-		}
-		t.Run(name, func(t *testing.T) {
-			workspace := t.TempDir()
-			extra := t.TempDir()
-			if err := os.MkdirAll(filepath.Join(workspace, "src"), 0o755); err != nil {
-				t.Fatal(err)
-			}
-			workspaceTarget := filepath.Join(workspace, "src", "a.go")
-			if err := os.WriteFile(workspaceTarget, []byte("old\n"), 0o644); err != nil {
-				t.Fatal(err)
-			}
-			extraTarget := filepath.Join(extra, "src", "a.go")
-			if extraHasMatchingPath {
-				if err := os.MkdirAll(filepath.Dir(extraTarget), 0o755); err != nil {
-					t.Fatal(err)
-				}
-				if err := os.WriteFile(extraTarget, []byte("old\n"), 0o644); err != nil {
-					t.Fatal(err)
-				}
-			}
-			scope, err := sandbox.NewScope(workspace, []string{extra})
-			if err != nil {
-				t.Fatal(err)
-			}
-			registry := tools.NewRegistry()
-			registry.Register(tools.NewScopedApplyPatchTool(workspace, scope))
-			extraCreated := filepath.Join(extra, "b.go")
-			patch := strings.Join([]string{
-				"*** Begin Patch",
-				"*** Update File: src/a.go",
-				"@@",
-				"-old",
-				"+new",
-				"*** Add File: " + extraCreated,
-				"+extra",
-				"*** End Patch",
-			}, "\n")
-
-			result, err := executeToolCall(context.Background(), registry, zeroruntime.ToolCall{
-				ID: "call-1", Name: "apply_patch", Arguments: patch, Freeform: true,
-			}, PermissionModeUnsafe, Options{Cwd: workspace, FileTracker: tools.NewFileTracker()})
-			if err != nil {
-				t.Fatalf("executeToolCall: %v", err)
-			}
-			if result.Status != tools.StatusError || !strings.Contains(result.Output, "mixes workspace-relative paths with an extra write root") {
-				t.Fatalf("mixed-root patch result = %s: %s", result.Status, result.Output)
-			}
-			if content, err := os.ReadFile(workspaceTarget); err != nil || string(content) != "old\n" {
-				t.Fatalf("workspace target changed: content=%q err=%v", content, err)
-			}
-			if extraHasMatchingPath {
-				if content, err := os.ReadFile(extraTarget); err != nil || string(content) != "old\n" {
-					t.Fatalf("extra-root target changed: content=%q err=%v", content, err)
-				}
-			}
-			if _, err := os.Stat(extraCreated); !os.IsNotExist(err) {
-				t.Fatalf("mixed-root patch created extra file: %v", err)
-			}
-		})
-	}
-}
-
-func TestFreeformApplyPatchAcceptsOneSemanticRoot(t *testing.T) {
-	for _, test := range []struct {
-		name         string
-		useExtraRoot bool
-	}{
-		{name: "workspace"},
-		{name: "extra root", useExtraRoot: true},
-	} {
-		t.Run(test.name, func(t *testing.T) {
-			workspace := t.TempDir()
-			extra := t.TempDir()
-			scope, err := sandbox.NewScope(workspace, []string{extra})
-			if err != nil {
-				t.Fatal(err)
-			}
-			root := workspace
-			if test.useExtraRoot {
-				root = extra
-			}
-			if err := os.MkdirAll(filepath.Join(root, "src"), 0o755); err != nil {
-				t.Fatal(err)
-			}
-			target := filepath.Join(root, "src", "a.go")
-			if err := os.WriteFile(target, []byte("old\n"), 0o644); err != nil {
-				t.Fatal(err)
-			}
-			updatePath := target
-			if !test.useExtraRoot {
-				updatePath = filepath.Join("src", "a.go")
-			}
-			created := filepath.Join(root, "b.go")
-			patch := strings.Join([]string{
-				"*** Begin Patch",
-				"*** Update File: " + updatePath,
-				"@@",
-				"-old",
-				"+new",
-				"*** Add File: " + created,
-				"+created",
-				"*** End Patch",
-			}, "\n")
-			registry := tools.NewRegistry()
-			registry.Register(tools.NewScopedApplyPatchTool(workspace, scope))
-			result, err := executeToolCall(context.Background(), registry, zeroruntime.ToolCall{
-				ID: "call-1", Name: "apply_patch", Arguments: patch, Freeform: true,
-			}, PermissionModeUnsafe, Options{Cwd: workspace, FileTracker: tools.NewFileTracker()})
-			if err != nil {
-				t.Fatalf("executeToolCall: %v", err)
-			}
-			if result.Status != tools.StatusOK {
-				t.Fatalf("single-root patch status = %s: %s", result.Status, result.Output)
-			}
-			if content, err := os.ReadFile(target); err != nil || string(content) != "new\n" {
-				t.Fatalf("updated content=%q err=%v", content, err)
-			}
-			if content, err := os.ReadFile(created); err != nil || string(content) != "created\n" {
-				t.Fatalf("created content=%q err=%v", content, err)
-			}
-		})
-	}
-}
-
-func TestFreeformApplyPatchRejectsAbsolutePathOutsideGrantedRoots(t *testing.T) {
-	root := t.TempDir()
-	granted := t.TempDir()
-	outside := t.TempDir()
-	scope := newFixedPathScope(t, root, granted)
-	registry := tools.NewRegistry()
-	registry.Register(tools.NewScopedApplyPatchTool(root, scope))
-	target := filepath.Join(outside, "blocked.txt")
-	patch := "*** Begin Patch\n*** Add File: " + target + "\n+blocked\n*** End Patch\n"
-
-	result, err := executeToolCall(context.Background(), registry, zeroruntime.ToolCall{
-		ID: "call-1", Name: "apply_patch", Arguments: patch, Freeform: true,
-	}, PermissionModeUnsafe, Options{Cwd: root})
-	if err != nil {
-		t.Fatalf("executeToolCall: %v", err)
-	}
-	if result.Status != tools.StatusError {
-		t.Fatalf("ungranted absolute patch status = %s, want error: %s", result.Status, result.Output)
-	}
-	if _, err := os.Stat(target); !os.IsNotExist(err) {
-		t.Fatalf("ungranted absolute patch created target: %v", err)
-	}
-}
-
-func TestPreparedFreeformPatchRejectsIntermediateSymlinkSwap(t *testing.T) {
-	if runtime.GOOS == "windows" {
-		t.Skip("creating directory symlinks requires privileges on Windows")
-	}
-	root := t.TempDir()
-	extra := t.TempDir()
-	outside := t.TempDir()
-	intermediate := filepath.Join(extra, "nested")
-	if err := os.Mkdir(intermediate, 0o755); err != nil {
-		t.Fatalf("Mkdir: %v", err)
-	}
-	scope := newFixedPathScope(t, root, extra)
-	tool := tools.NewScopedApplyPatchTool(root, scope)
-	target := filepath.Join(intermediate, "blocked.txt")
-	patch := "*** Begin Patch\n*** Add File: " + target + "\n+blocked\n*** End Patch\n"
-	args, err := tools.PrepareFreeformApplyPatchArguments(tool, patch)
-	if err != nil {
-		t.Fatalf("PrepareFreeformApplyPatchArguments: %v", err)
-	}
-
-	if err := os.Remove(intermediate); err != nil {
-		t.Fatalf("Remove intermediate: %v", err)
-	}
-	if err := os.Symlink(outside, intermediate); err != nil {
-		t.Fatalf("Symlink: %v", err)
-	}
-	result := tool.Run(context.Background(), args)
-	if result.Status != tools.StatusError {
-		t.Fatalf("symlink-swapped patch status = %s, want error: %s", result.Status, result.Output)
-	}
-	if _, err := os.Stat(filepath.Join(outside, "blocked.txt")); !os.IsNotExist(err) {
-		t.Fatalf("symlink-swapped patch wrote outside root: %v", err)
-	}
-}
-
-func TestUnknownFreeformToolFailsClosed(t *testing.T) {
-	result, err := executeToolCall(context.Background(), tools.NewRegistry(), zeroruntime.ToolCall{
-		ID: "call-1", Name: "unknown", Arguments: "raw", Freeform: true,
-	}, PermissionModeUnsafe, Options{})
-	if err != nil {
-		t.Fatalf("executeToolCall: %v", err)
-	}
-	if result.Status != tools.StatusError {
-		t.Fatalf("unknown freeform status = %s, want error", result.Status)
-	}
-}
-
-func TestCustomApplyPatchCannotUseFreeformContract(t *testing.T) {
-	custom := &customApplyPatchTool{}
-	registry := tools.NewRegistry()
-	registry.Register(custom)
-
-	result, err := executeToolCall(context.Background(), registry, zeroruntime.ToolCall{
-		ID: "call-1", Name: "apply_patch", Arguments: "raw patch", Freeform: true,
-	}, PermissionModeUnsafe, Options{})
-	if err != nil {
-		t.Fatalf("executeToolCall: %v", err)
-	}
-	if result.Status != tools.StatusError || !strings.Contains(result.Output, "Unsupported freeform tool call") {
-		t.Fatalf("custom freeform apply_patch result = %#v, want unsupported error", result)
-	}
-	if custom.calls != 0 {
-		t.Fatalf("custom apply_patch executed %d times", custom.calls)
-	}
-}
-
-func TestDeniedFreeformApplyPatchDoesNotWrite(t *testing.T) {
-	root := t.TempDir()
-	registry := tools.NewRegistry()
-	registry.Register(tools.NewScopedApplyPatchTool(root, nil))
-	patch := "*** Begin Patch\n*** Add File: denied.txt\n+must not exist\n*** End Patch\n"
-
-	result, err := executeToolCall(context.Background(), registry, zeroruntime.ToolCall{
-		ID:        "call-1",
-		Name:      "apply_patch",
-		Arguments: patch,
-		Freeform:  true,
-	}, PermissionModeAsk, Options{
-		Cwd: root,
-		OnPermissionRequest: func(context.Context, PermissionRequest) (PermissionDecision, error) {
-			return PermissionDecision{Action: PermissionDecisionDeny, Reason: "test denial"}, nil
-		},
-	})
-	if err != nil {
-		t.Fatalf("executeToolCall: %v", err)
-	}
-	if result.Status != tools.StatusError {
-		t.Fatalf("denied freeform status = %s, want error", result.Status)
-	}
-	if _, err := os.Stat(filepath.Join(root, "denied.txt")); !os.IsNotExist(err) {
-		t.Fatalf("denied freeform patch changed the workspace: %v", err)
-	}
-}
-
-func TestHistorySafeToolCallsPreservesRawFreeformArguments(t *testing.T) {
-	raw := "*** Begin Patch\n*** Update File: internal/main.go\n@@\n-old\n+new\n*** End Patch\n"
-	safe := historySafeToolCalls([]ToolCall{{
-		ID: "call-1", ProviderCallID: "provider-1", Name: "apply_patch", Arguments: raw, Freeform: true,
-	}})
-	if len(safe) != 1 || safe[0].Arguments != raw || safe[0].ProviderCallID != "provider-1" || !safe[0].Freeform {
-		t.Fatalf("freeform history changed raw call: %#v", safe)
-	}
-}
-
-func TestAbortedToolResultPreservesProviderCallID(t *testing.T) {
-	messages := appendAbortedToolResults(nil, []ToolCall{{
-		ID: "call-1", ProviderCallID: "provider-1", Name: "read_file",
-	}})
-	if len(messages) != 1 || messages[0].ToolCallID != "call-1" || messages[0].ToolCallProviderID != "provider-1" || !messages[0].IsError {
-		t.Fatalf("aborted tool result lost provider identity: %#v", messages)
-	}
-}

internal/agent/guardrails.go

@@ -33,11 +33,11 @@ const (
 	// knows before spending more tool turns.
 	toolOnlyProgressReminderAt = 6
 
-	// planReminderTurn and planReminderToolThreshold keep bounded implementation
-	// work plan-free while still nudging a genuinely sustained run that has not
-	// established any structured progress. Both thresholds must be met.
-	planReminderTurn          = 7
-	planReminderToolThreshold = 7
+	// planReminderTurn is the turn (1-based) by the end of which a multi-step
+	// task should have called update_plan; if it hasn't, a one-time reminder is
+	// injected. Set to 3 (not 2) so short, legitimate two-step tasks finish
+	// without a spurious planning nag.
+	planReminderTurn = 3
 
 	// planToolName is the planning tool the loop watches for by name.
 	planToolName = "update_plan"
@@ -591,12 +591,13 @@ func (state *guardState) planReminder(turn int) string {
 		return planStaleReminder(state.toolCallsSincePlanUpdate)
 	}
 
-	// NOT-CALLED reminder: once both the turn and tool-call thresholds are met,
-	// sustained work should have called update_plan. One-shot for the whole run.
+	// NOT-CALLED reminder: by the end of planReminderTurn the model should have
+	// called update_plan if it's doing a multi-step task (>=1 other tool call).
+	// One-shot for the whole run.
 	if !state.notCalledReminderSent &&
 		!state.planEverCalled &&
 		turn >= planReminderTurn &&
-		state.totalToolCalls >= planReminderToolThreshold {
+		state.totalToolCalls >= 1 {
 		state.notCalledReminderSent = true
 		return planNotCalledReminder()
 	}

internal/agent/guardrails_test.go

@@ -257,16 +257,19 @@ func TestRunDoesNotCountDroppedToolCallTurnsAsEmpty(t *testing.T) {
 }
 
 func TestRunInjectsPlanNotCalledReminderForMultiStepTask(t *testing.T) {
-	const expectedThreshold = 7
-	if planReminderToolThreshold != expectedThreshold {
-		t.Fatalf("plan reminder tool threshold = %d, want %d", planReminderToolThreshold, expectedThreshold)
-	}
 	root := t.TempDir()
 	writeAgentTestFile(t, root+"/notes.txt", "alpha")
 	registry := tools.NewRegistry()
 	registry.Register(tools.NewScopedReadFileTool(root, nil))
 
-	provider := &mockProvider{turns: append(repeatedReadTurns(expectedThreshold), textTurn("done"))}
+	provider := &mockProvider{
+		turns: [][]zeroruntime.StreamEvent{
+			toolTurn("call-1", "read_file", `{"path":"notes.txt"}`), // turn 1: other tool call
+			toolTurn("call-2", "read_file", `{"path":"notes.txt"}`), // turn 2: still no update_plan
+			toolTurn("call-3", "read_file", `{"path":"notes.txt"}`), // turn 3: reminder fires here
+			textTurn("done"),
+		},
+	}
 
 	result, err := Run(context.Background(), "go", provider, Options{
 		Registry: registry,
@@ -284,44 +287,6 @@ func TestRunInjectsPlanNotCalledReminderForMultiStepTask(t *testing.T) {
 	}
 }
 
-func TestRunDoesNotInjectPlanReminderForBoundedToolSequence(t *testing.T) {
-	const expectedThreshold = 7
-	root := t.TempDir()
-	writeAgentTestFile(t, root+"/notes.txt", "alpha")
-	registry := tools.NewRegistry()
-	registry.Register(tools.NewScopedReadFileTool(root, nil))
-
-	provider := &mockProvider{turns: append(repeatedReadTurns(expectedThreshold-1), textTurn("done"))}
-	result, err := Run(context.Background(), "go", provider, Options{Registry: registry, MaxTurns: 12})
-	if err != nil {
-		t.Fatal(err)
-	}
-	if result.FinalAnswer != "done" {
-		t.Fatalf("expected final answer, got %q", result.FinalAnswer)
-	}
-	if count := countUserMessagesContaining(result.Messages, planNotCalledReminderMarker); count != 0 {
-		t.Fatalf("bounded tool sequence must not draw a plan reminder, got %d", count)
-	}
-}
-
-func TestPlanReminderWaitsForTurnThresholdAfterEnoughToolCalls(t *testing.T) {
-	state := guardState{totalToolCalls: 7}
-	if got := state.planReminder(6); got != "" {
-		t.Fatalf("planReminder(6) = %q, want no reminder before turn threshold", got)
-	}
-	if state.notCalledReminderSent {
-		t.Fatal("early turn marked the not-called reminder as sent")
-	}
-}
-
-func repeatedReadTurns(count int) [][]zeroruntime.StreamEvent {
-	turns := make([][]zeroruntime.StreamEvent, 0, count)
-	for range count {
-		turns = append(turns, toolTurn("call", "read_file", `{"path":"notes.txt"}`))
-	}
-	return turns
-}
-
 func TestRunDoesNotInjectPlanReminderForTrivialTask(t *testing.T) {
 	root := t.TempDir()
 	writeAgentTestFile(t, root+"/notes.txt", "alpha")

internal/agent/loop.go

@@ -141,7 +141,6 @@ func Run(ctx context.Context, prompt string, provider Provider, options Options)
 			}
 			options.Trace.Counter(trace.CounterInputTokens, int64(usage.InputTokens))
 			options.Trace.Counter(trace.CounterCachedInputTokens, int64(usage.CachedInputTokens))
-			options.Trace.Counter(trace.CounterCacheWriteTokens, int64(usage.CacheWriteTokens))
 			options.Trace.Counter(trace.CounterOutputTokens, int64(usage.OutputTokens))
 		}
 	}
@@ -698,12 +697,11 @@ func Run(ctx context.Context, prompt string, provider Provider, options Options)
 				turnRequestedModel = toolResult.RequestedModel
 			}
 			messages = append(messages, zeroruntime.Message{
-				Role:               zeroruntime.MessageRoleTool,
-				Content:            toolResult.ModelOutput(),
-				ToolCallID:         toolResult.ToolCallID,
-				ToolCallProviderID: call.ProviderCallID,
-				IsError:            toolResult.Status == tools.StatusError,
-				ChangedFiles:       append([]string(nil), toolResult.ChangedFiles...),
+				Role:         zeroruntime.MessageRoleTool,
+				Content:      toolResult.ModelOutput(),
+				ToolCallID:   toolResult.ToolCallID,
+				IsError:      toolResult.Status == tools.StatusError,
+				ChangedFiles: append([]string(nil), toolResult.ChangedFiles...),
 			})
 			// Images ride a following USER message rather than the tool result
 			// above. Every provider drops images on a tool-role message —
@@ -846,21 +844,11 @@ 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.
 				}
 			}
 		}
@@ -1047,9 +1035,6 @@ func historySafeToolCalls(calls []ToolCall) []ToolCall {
 	safe := make([]ToolCall, len(calls))
 	for i, call := range calls {
 		safe[i] = call
-		if call.Freeform {
-			continue
-		}
 		args := strings.TrimSpace(call.Arguments)
 		switch {
 		case args == "":
@@ -1133,28 +1118,8 @@ func decodeToolArguments(arguments string, v any) error {
 }
 
 func executeToolCall(ctx context.Context, registry *tools.Registry, call ToolCall, permissionMode PermissionMode, options Options) (ToolResult, error) {
-	tool, toolFound := registry.Get(call.Name)
 	args := map[string]any{}
-	if call.Freeform {
-		if !toolFound || !tools.IsBuiltInApplyPatch(tool) {
-			return ToolResult{
-				ToolCallID: call.ID,
-				Name:       call.Name,
-				Status:     tools.StatusError,
-				Output:     "Error: Unsupported freeform tool call for " + call.Name + ".",
-			}, nil
-		}
-		prepared, err := tools.PrepareFreeformApplyPatchArguments(tool, call.Arguments)
-		if err != nil {
-			return ToolResult{
-				ToolCallID: call.ID,
-				Name:       call.Name,
-				Status:     tools.StatusError,
-				Output:     "Error: Invalid freeform apply_patch input: " + err.Error(),
-			}, nil
-		}
-		args = prepared
-	} else if call.Arguments != "" {
+	if call.Arguments != "" {
 		if err := decodeToolArguments(call.Arguments, &args); err != nil {
 			return ToolResult{
 				ToolCallID: call.ID,
@@ -1182,6 +1147,7 @@ func executeToolCall(ctx context.Context, registry *tools.Registry, call ToolCal
 			DenialReason: DenialFiltered,
 		}, nil
 	}
+	tool, toolFound := registry.Get(call.Name)
 	if (permissionMode == PermissionModeSpecDraft || permissionMode == PermissionModePlan) && toolFound && !ToolAdvertised(tool, permissionMode) {
 		modeName := string(permissionMode)
 		return ToolResult{
@@ -3244,15 +3210,11 @@ func cachedRuntimeToolDefinition(defCache map[string]zeroruntime.ToolDefinition,
 // runtimeToolDefinition renders a tool's advertised definition (name, description,
 // JSON-schema parameters) as sent to the provider.
 func runtimeToolDefinition(tool tools.Tool) zeroruntime.ToolDefinition {
-	definition := zeroruntime.ToolDefinition{
+	return zeroruntime.ToolDefinition{
 		Name:        tool.Name(),
 		Description: tool.Description(),
 		Parameters:  schemaToRuntimeMap(tool.Parameters()),
 	}
-	if tools.IsBuiltInApplyPatch(tool) {
-		definition.Type = zeroruntime.ToolDefinitionFreeform
-	}
-	return definition
 }
 
 func ToolVisible(tool tools.Tool, permissionMode PermissionMode, enabledTools []string, disabledTools []string) bool {
@@ -3407,11 +3369,10 @@ func loadedToolsFromResult(meta map[string]string) []string {
 func appendAbortedToolResults(messages []Message, remaining []ToolCall) []Message {
 	for _, call := range remaining {
 		messages = append(messages, zeroruntime.Message{
-			Role:               zeroruntime.MessageRoleTool,
-			Content:            abortedToolResultNotice,
-			ToolCallID:         call.ID,
-			ToolCallProviderID: call.ProviderCallID,
-			IsError:            true,
+			Role:       zeroruntime.MessageRoleTool,
+			Content:    abortedToolResultNotice,
+			ToolCallID: call.ID,
+			IsError:    true,
 		})
 	}
 	return messages

internal/agent/loop_test.go

@@ -4096,7 +4096,7 @@ func TestRunDoesNotFlagCleanToolOutput(t *testing.T) {
 // caller's callback AND stamps token counters, and the run completes.
 func TestRunTracingWrapperStampsUsage(t *testing.T) {
 	provider := &mockProvider{turns: [][]zeroruntime.StreamEvent{{
-		{Type: zeroruntime.StreamEventUsage, Usage: zeroruntime.Usage{PromptTokens: 100, CachedInputTokens: 20, CacheWriteTokens: 10, CompletionTokens: 40}},
+		{Type: zeroruntime.StreamEventUsage, Usage: zeroruntime.Usage{InputTokens: 100, CachedInputTokens: 20, OutputTokens: 40}},
 		{Type: zeroruntime.StreamEventText, Content: "done"},
 		{Type: zeroruntime.StreamEventDone},
 	}}}
@@ -4135,9 +4135,6 @@ func TestRunTracingWrapperStampsUsage(t *testing.T) {
 	if got := tr.Counter(trace.CounterCachedInputTokens); got != 20 {
 		t.Fatalf("cached input token counter = %d, want 20", got)
 	}
-	if got := tr.Counter(trace.CounterCacheWriteTokens); got != 10 {
-		t.Fatalf("cache-write token counter = %d, want 10", got)
-	}
 	if got := tr.Counter(trace.CounterOutputTokens); got != 40 {
 		t.Fatalf("output token counter = %d, want 40", got)
 	}

internal/agent/partition_cache_test.go

@@ -31,19 +31,6 @@ func (t countingSchemaTool) Run(_ context.Context, _ map[string]any) tools.Resul
 	return tools.Result{Status: tools.StatusOK}
 }
 
-func TestRuntimeToolDefinitionMarksOnlyBuiltInApplyPatchFreeform(t *testing.T) {
-	builtIn := runtimeToolDefinition(tools.NewScopedApplyPatchTool(t.TempDir(), nil))
-	if builtIn.Type != zeroruntime.ToolDefinitionFreeform {
-		t.Fatalf("built-in apply_patch type = %q, want freeform", builtIn.Type)
-	}
-
-	calls := 0
-	custom := runtimeToolDefinition(countingSchemaTool{name: "apply_patch", calls: &calls})
-	if custom.Type != "" {
-		t.Fatalf("custom apply_patch type = %q, want legacy function shape", custom.Type)
-	}
-}
-
 // The cache renders a tool's schema once and reuses it across calls, and its
 // output is identical to the uncached path.
 func TestPartitionToolsCacheRendersOnceAndMatchesUncached(t *testing.T) {

internal/agent/prompt_budget_test.go

@@ -68,7 +68,7 @@ func TestEagerToolSchemaTokenBudget(t *testing.T) {
 	}
 }
 
-func TestAgentAdvertisesBothEditTools(t *testing.T) {
+func TestAgentAdvertisesPatchInsteadOfAmbiguousStringReplacement(t *testing.T) {
 	registry := tools.NewRegistry()
 	for _, tool := range tools.CoreToolsScoped(t.TempDir(), nil) {
 		registry.Register(tool)
@@ -79,9 +79,9 @@ func TestAgentAdvertisesBothEditTools(t *testing.T) {
 		names[definition.Name] = true
 	}
 	if !names["apply_patch"] {
-		t.Fatal("agent must retain apply_patch for multi-hunk changes")
+		t.Fatal("agent must retain apply_patch for existing-file changes")
 	}
-	if !names["edit_file"] {
-		t.Fatal("agent must receive edit_file for targeted exact replacements")
+	if names["edit_file"] {
+		t.Fatal("agent must not receive the ambiguous string-replacement tool")
 	}
 }

internal/agent/prompt_fingerprint.go

@@ -58,18 +58,12 @@ func toolSubstrings(exposed []zeroruntime.ToolDefinition) (toolsSubstr, schemaSu
 	for _, def := range exposed {
 		writeLengthPrefixed(&toolsSB, def.Name)
 		writeLengthPrefixed(&toolsSB, def.Description)
-		writeLengthPrefixed(&toolsSB, string(def.Type))
 		// Parameters is rendered to a canonical JSON string per tool. The
 		// schema-render cache in internal/agent (used by partitionToolsCached)
 		// guarantees the same render is byte-identical across turns for the
 		// same tool, so this substring is a stable hash input.
 		writeLengthPrefixed(&schemaSB, def.Name)
 		writeLengthPrefixed(&schemaSB, canonicalSchemaString(def.Parameters))
-		if def.Format != nil {
-			writeLengthPrefixed(&schemaSB, def.Format.Type)
-			writeLengthPrefixed(&schemaSB, def.Format.Syntax)
-			writeLengthPrefixed(&schemaSB, def.Format.Definition)
-		}
 	}
 	return toolsSB.String(), schemaSB.String()
 }

internal/agent/prompt_fingerprint_test.go

@@ -73,38 +73,6 @@ func TestComputePrefixFingerprintSchemaChangeChangesSchemaHash(t *testing.T) {
 	}
 }
 
-func TestComputePrefixFingerprintIncludesToolTypeAndFormat(t *testing.T) {
-	opts := Options{Cwd: t.TempDir(), SystemPrompt: "core"}
-	base := zeroruntime.ToolDefinition{Name: "apply_patch", Description: "Patch files"}
-	baseFingerprint := ComputePrefixFingerprint(opts, []zeroruntime.ToolDefinition{base})
-
-	typed := base
-	typed.Type = zeroruntime.ToolDefinitionFreeform
-	if got := ComputePrefixFingerprint(opts, []zeroruntime.ToolDefinition{typed}); got.ToolsHash == baseFingerprint.ToolsHash {
-		t.Fatal("ToolsHash must change when tool Type changes")
-	}
-
-	formatCases := []struct {
-		name   string
-		format zeroruntime.ToolDefinitionFormat
-	}{
-		{name: "type", format: zeroruntime.ToolDefinitionFormat{Type: "grammar"}},
-		{name: "syntax", format: zeroruntime.ToolDefinitionFormat{Syntax: "lark"}},
-		{name: "definition", format: zeroruntime.ToolDefinitionFormat{Definition: "start: PATCH"}},
-		{name: "empty", format: zeroruntime.ToolDefinitionFormat{}},
-	}
-	for _, test := range formatCases {
-		t.Run(test.name, func(t *testing.T) {
-			withFormat := base
-			withFormat.Format = &test.format
-			got := ComputePrefixFingerprint(opts, []zeroruntime.ToolDefinition{withFormat})
-			if got.SchemaHash == baseFingerprint.SchemaHash {
-				t.Fatalf("SchemaHash must change for %s format input", test.name)
-			}
-		})
-	}
-}
-
 // TestComputePrefixFingerprintSystemPromptChangeChangesBaseHash asserts the
 // most common drift path: a system-prompt edit (e.g. an agent.md update, a
 // model addendum change) must move the base-instructions hash, which moves

internal/agent/system_prompt.md

@@ -30,10 +30,13 @@ work.
    read-before-edit discipline: inspect the target file and nearby callers,
    tests, or config before you modify behavior. Never edit a file you have not
    read.
-2. **Plan.** Use update_plan for multi-component, sequencing-uncertain, or long
-   work. Skip it for bounded changes in one component. Update only when the
-   overall phase changes, keep at most one item in_progress, and never create a
-   plan after the work is complete.
+2. **Plan.** Use update_plan for implementation or investigation that has at
+   least three meaningful dependent steps, then keep it current at milestones.
+   Mark completed work and the next in-progress step together when practical;
+   do not spend separate turns updating it after every file or command. Keep at
+   most one item in_progress. Skip plans for simple lookups, explanations, code
+   navigation, and other short tasks. Never create a plan after the work is
+   already complete merely to describe what you did.
 3. **Implement.** Make focused changes that match the surrounding code's style,
    naming, and conventions. Prefer the smallest change that fully solves the
    problem. Avoid broad refactors, unrelated rewrites, dependency churn, and
@@ -49,48 +52,38 @@ work.
 
 - Choose the narrowest tool that safely accomplishes the step. Prefer native
   file tools - read_file, read_minified_file, list_directory, glob, grep,
-  edit_file, apply_patch, write_file - over shelling out to
+  write_file, apply_patch - over shelling out to
   cat/sed/awk/python for file operations.
   They are safer, reviewable, and produce clean diffs.
-- Use read_minified_file only to explore large or unfamiliar source. Use
-  read_file for small or likely edit targets and exact text, comments, or line
-  numbers. Do not read both unless a new need for exact content appears.
+- Prefer read_minified_file when initially exploring source code; it preserves
+  code while removing comments and redundant whitespace. Use read_file when
+  exact text, comments, or line numbers are needed.
 - Keep edits focused and reviewable. A single patch may update several related
   files when they form one coherent change; do not hide unrelated edits in a
   bulk shell or script rewrite.
-- For edits to existing files, use edit_file for a targeted change (old_string
-  must match the file exactly and be unique, so include a few surrounding
-  lines) and apply_patch when one coherent change spans several hunks or
-  files. Use write_file only to create a file or when most of it changes; do
-  not rewrite a whole file to change a few lines. Match the existing
-  indentation, imports, and idioms. Match the file's comment density: do not
-  add explanatory comments unless the user asks or the code is already
+- For edits to existing files, prefer apply_patch with minimal, targeted hunks
+  and enough unchanged context to identify the intended location. Match the
+  existing indentation, imports, and idioms. Match the file's comment density:
+  do not add explanatory comments unless the user asks or the code is already
   comment-dense.
-- A successful edit result already confirms the change; do not re-read a file
-  just to verify an edit that succeeded. If an edit fails, read the error, fix
-  the old_string or hunk, and retry the same tool rather than switching to a
-  full rewrite.
 - Solve the problem as posed, not a more general version of it. Add no
   speculative abstraction, configurability, or handling for cases that cannot
   occur, and nothing the user did not ask for. A small diff can still be
-  over-built; if a 200-line solution could be 50, rewrite it. Once the required
-  behavior passes validation, stop instead of adding optional cleanup.
+  over-built; if a 200-line solution could be 50, rewrite it.
 - Preserve behavior you were not asked to change. Do not delete or rewrite code
   you did not author unless the task requires it; if you must, say so.
 
 ## Testing gate (mandatory)
 
-- After code changes, run the project's documented appropriate validators.
-  Scope iteration checks, combine compatible commands when diagnostics stay
-  useful, and run the final set once after the last edit. Rerun only after a
-  change or failure.
-- If unsure which entry points apply, inspect the Makefile, manifests, or CI;
-  do not invent a parallel flow.
+- After any change to code, verify after edits by running the project's
+  validators before you summarize or commit: tests, type-checks, linters, and/or
+  the build, as appropriate. Scope them to the change while iterating; reserve
+  full-suite runs for milestones.
+- If you are unsure which validators apply, search the repo (Makefile, package
+  manifests, CI config) to find them.
 - Never claim a task is done, and never commit, while validators are failing. If
   they fail, fix the cause and rerun; do not paper over it. If you could not run
   a validator, say so explicitly rather than implying success.
-- A successful native patch confirms the edit. Reread only when the next change
-  needs exact content or the result was ambiguous.
 
 ## Tool use
 
@@ -112,7 +105,7 @@ work.
   you need to clean up a running foreground command yourself, use write_stdin.
 - write_stdin's session_id is only ever an id returned by a still-running
   exec_command; never guess or probe ids. If you have no such session, start one
-  with exec_command, or use edit_file/apply_patch/write_file for file changes.
+  with exec_command, or use write_file/apply_patch for file changes.
 - write_stdin with empty input polls an existing exec_command session, and
   `\u0003` interrupts it. Sending other stdin bytes may require approval because
   it can drive the running process beyond the original command. Non-tty sessions
@@ -148,7 +141,6 @@ work.
 - Default to concise, skimmable output. Lead with the answer or the result.
 - Use GitHub-flavored Markdown: headings to structure longer replies, fenced
   code blocks for code, and `inline code` for file paths, commands, symbols, and
-  short snippets. Reference code with file paths and include line numbers when
-  already known; do not look them up solely for the final summary.
+  short snippets. Reference code as `file:line` so it is clickable.
 - Report outcomes faithfully: if tests failed, show it; if a step was skipped,
   say so; when something is done and verified, state it plainly without hedging.

internal/agent/system_prompt_models.go

@@ -60,17 +60,14 @@ const openAIPromptAddendum = `<model_guidance>
   longer answers, fenced code blocks for code, and ` + "`inline code`" + ` for paths,
   commands, and symbols.
 - Strongly prefer the native file tools (read_file, list_directory, grep, glob,
-  edit_file, apply_patch, write_file) over shelling out to cat/sed/awk/python for
-  file work. Use them directly; never run apply_patch through exec_command.
-  read_file, edit_file and write_file take one file per call, while one coherent
-  apply_patch may span several files. Keep independent native calls in the same
-  turn, and do not batch file writes into a script.
+  write_file, apply_patch) over shelling out to cat/sed/awk/python for
+  file work. Make one tool call per file; do not batch file writes into a script.
 - Persist until the task is fully handled this turn: gather context, implement,
   run the validators, and report — do not stop at a partial result.
 </model_guidance>`
 
 const geminiPromptAddendum = `<model_guidance>
-- Prefer the dedicated tools (read_file, grep, glob, edit_file, apply_patch) over
+- Prefer the dedicated tools (read_file, grep, glob, apply_patch) over
   equivalent shell commands; they are safer and produce cleaner diffs.
 - Be concise and concrete. When you run a shell command with side effects, state
   in one short clause why it is needed.

internal/agent/system_prompt_models_test.go

@@ -29,9 +29,6 @@ func TestBuildSystemPromptAppendsModelAddendum(t *testing.T) {
 	if got := buildSystemPrompt(Options{Model: "gpt-5"}); !strings.Contains(got, openAIPromptAddendum) {
 		t.Fatalf("expected the OpenAI addendum in the gpt-5 prompt")
 	}
-	if got := strings.Join(strings.Fields(strings.ToLower(buildSystemPrompt(Options{Model: "gpt-5"}))), " "); !strings.Contains(got, "never run apply_patch through exec_command") {
-		t.Fatalf("OpenAI prompt must route edits through the native patch tool:\n%s", got)
-	}
 	// Claude is aligned with the core prompt and gets no family addendum now that
 	// comment discipline is universal; it must not pick up another family's block.
 	claude := buildSystemPrompt(Options{Model: "claude-opus-4-6"})

internal/agent/system_prompt_test.go

@@ -29,17 +29,14 @@ func TestMain(m *testing.M) {
 }
 
 func TestCoreSystemPromptIncludesCodingQualityRules(t *testing.T) {
-	prompt := strings.Join(strings.Fields(strings.ToLower(buildSystemPrompt(Options{}))), " ")
-	if strings.Contains(prompt, "clickable file paths") {
-		t.Fatalf("system prompt must not claim inline-code file paths are clickable: %s", prompt)
-	}
+	prompt := strings.ToLower(buildSystemPrompt(Options{}))
 
 	for _, want := range []string{
 		"read-before-edit",
 		"inspect the target file",
 		"plan then act",
 		"choose the narrowest tool",
-		"for edits to existing files, use edit_file",
+		"for edits to existing files, prefer apply_patch",
 		"verify after edits",
 		"honor the active permission mode",
 		"avoid broad refactors",
@@ -47,13 +44,6 @@ func TestCoreSystemPromptIncludesCodingQualityRules(t *testing.T) {
 		"do not recognize",
 		"scaled to the work",
 		"comment density",
-		"skip it for bounded changes in one component",
-		"do not read both unless a new need for exact content appears",
-		"combine compatible commands when diagnostics stay useful",
-		"do not invent a parallel flow",
-		"a successful native patch confirms the edit",
-		"once the required behavior passes validation, stop",
-		"do not look them up solely for the final summary",
 	} {
 		if !strings.Contains(prompt, want) {
 			t.Fatalf("expected core system prompt to include %q, got:\n%s", want, buildSystemPrompt(Options{}))

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/app.go

@@ -839,20 +839,18 @@ func runInteractiveTUIWithSetup(stderr io.Writer, deps appDeps, permissionMode a
 		mcpTokenStore = nil
 		err = nil
 	}
-	criticalMCPConfig, optionalMCPConfig := splitMCPStartupConfig(mcpConfig)
 	mcpRuntime := mcpToolRuntime(noopMCPRuntime{})
-	if len(criticalMCPConfig.Servers) > 0 {
-		runtime, registerErr := deps.registerMCPTools(context.Background(), registry, criticalMCPConfig, mcp.RegisterOptions{
+	if len(mcpConfig.Servers) > 0 {
+		mcpRuntime, err = deps.registerMCPTools(context.Background(), registry, mcpConfig, mcp.RegisterOptions{
 			PermissionStore: mcpPermissionStore,
 			Autonomy:        mcp.AutonomyLow,
 			Execution:       executionRunner,
 			WorkspaceRoot:   workspaceRoot,
 		})
-		if registerErr != nil {
-			closeMCPRuntime(stderr, runtime)
-			return writeAppError(stderr, redaction.ErrorMessage(registerErr, redaction.Options{}), 1)
-		}
-		mcpRuntime = runtime
+	}
+	if err != nil {
+		closeMCPRuntime(stderr, mcpRuntime)
+		return writeAppError(stderr, err.Error(), 1)
 	}
 	defer closeMCPRuntime(stderr, mcpRuntime)
 	// A server that could not be reached or validated is skipped, not fatal (one
@@ -911,35 +909,11 @@ func runInteractiveTUIWithSetup(stderr io.Writer, deps appDeps, permissionMode a
 	}
 	// Activate deferred MCP-tool loading for the interactive run only when the
 	// VISIBLE deferred-eligible count meets the resolved threshold, matching exec.
-	// This first pass covers every prompt-critical tool. Optional built-in MCP
-	// defaults re-run the same gate after publishing their atomic batch, so a
-	// later catalog generation cannot miss its loader. The interactive surface
-	// applies no operator tool filters, so enabled/disabled are nil — matching the
-	// AgentOptions below.
+	// The registry is complete (core + specialist + MCP + plugins) here, so the
+	// count is accurate; below threshold this is a no-op and the surface is
+	// unchanged. The interactive surface applies no operator tool filters, so
+	// enabled/disabled are nil — matching the AgentOptions below.
 	registerToolSearchIfEligible(registry, resolved.Tools.DeferThreshold, permissionMode, nil, nil)
-	var optionalMCPRuntime *optionalMCPStartup
-	var awaitToolReadiness func(context.Context)
-	if len(optionalMCPConfig.Servers) > 0 {
-		optionalMCPRuntime = startOptionalMCP(
-			context.Background(),
-			registry,
-			optionalMCPConfig,
-			mcp.RegisterOptions{
-				PermissionStore: mcpPermissionStore,
-				Autonomy:        mcp.AutonomyLow,
-				Execution:       executionRunner,
-				WorkspaceRoot:   workspaceRoot,
-			},
-			deps.registerMCPTools,
-			func() {
-				registerToolSearchIfEligible(registry, resolved.Tools.DeferThreshold, permissionMode, nil, nil)
-			},
-		)
-		defer closeMCPRuntime(stderr, optionalMCPRuntime)
-		awaitToolReadiness = func(ctx context.Context) {
-			optionalMCPRuntime.Await(ctx, optionalMCPPromptGrace)
-		}
-	}
 	lastKnownMCPConfig := mcpConfig
 	fileTracker := tools.NewFileTracker()
 	var scratchBaseline scratchFileBaseline
@@ -974,20 +948,10 @@ 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 {
-			if provider == nil {
-				return nil
-			}
-			if optimized, ok := providers.OptimizedTurnSessions(profile, provider, providers.Options{}); ok {
-				return optimized
-			}
-			return providers.DefaultTurnSessions(profile, provider, providers.Options{})
-		},
-		ProbeProviderHealth: deps.probeProviderHealth,
-		UserAgent:           userAgent(),
+		ProbeProviderHealth:  deps.probeProviderHealth,
+		UserAgent:            userAgent(),
 		PrepareRunCompletionWarning: func() {
 			scratchBaseline = scratchFileSnapshot(workspaceRoot)
 		},
@@ -995,7 +959,6 @@ func runInteractiveTUIWithSetup(stderr io.Writer, deps appDeps, permissionMode a
 			return scratchFileWarning(workspaceRoot, scratchBaseline)
 		},
 		Registry:           registry,
-		AwaitToolReadiness: awaitToolReadiness,
 		SessionStore:       sessionStore,
 		PeerService:        peerService,
 		SandboxStore:       sandboxStore,

internal/cli/app_test.go

@@ -17,7 +17,6 @@ import (
 	"github.com/Gitlawb/zero/internal/agent"
 	"github.com/Gitlawb/zero/internal/config"
 	"github.com/Gitlawb/zero/internal/mcp"
-	"github.com/Gitlawb/zero/internal/redaction"
 	"github.com/Gitlawb/zero/internal/tools"
 	"github.com/Gitlawb/zero/internal/tui"
 	"github.com/Gitlawb/zero/internal/update"
@@ -487,74 +486,6 @@ func TestRunNoArgsLaunchesTUIWithMCPState(t *testing.T) {
 	}
 }
 
-func TestRunNoArgsPaintsBeforeOptionalDefaultMCPIsReady(t *testing.T) {
-	var stdout bytes.Buffer
-	var stderr bytes.Buffer
-	cwd := t.TempDir()
-	userConfigPath := filepath.Join(t.TempDir(), "zero", "config.json")
-	permissionStore, err := mcp.NewPermissionStore(mcp.StoreOptions{FilePath: filepath.Join(t.TempDir(), "mcp-permissions.json")})
-	if err != nil {
-		t.Fatalf("NewPermissionStore() error = %v", err)
-	}
-	tokenStore, err := mcp.NewTokenStore(mcp.TokenStoreOptions{FilePath: filepath.Join(t.TempDir(), "mcp-oauth.json")})
-	if err != nil {
-		t.Fatalf("NewTokenStore() error = %v", err)
-	}
-	started := make(chan struct{})
-	release := make(chan struct{})
-	configResult := make(chan error, 1)
-
-	exitCode := runWithDeps([]string{}, &stdout, &stderr, appDeps{
-		getwd:          func() (string, error) { return cwd, nil },
-		userConfigPath: func() (string, error) { return userConfigPath, nil },
-		resolveConfig: func(string, config.Overrides) (config.ResolvedConfig, error) {
-			return config.ResolvedConfig{MaxTurns: 8}, nil
-		},
-		resolveMCPConfig: func(string, bool) (config.MCPConfig, error) {
-			return config.MCPConfig{Servers: config.DefaultMCPServers()}, nil
-		},
-		newMCPStore:      func() (*mcp.PermissionStore, error) { return permissionStore, nil },
-		newMCPTokenStore: func() (*mcp.TokenStore, error) { return tokenStore, nil },
-		registerMCPTools: func(_ context.Context, registry *tools.Registry, cfg config.MCPConfig, _ mcp.RegisterOptions) (mcpToolRuntime, error) {
-			var configErr error
-			if _, ok := cfg.Servers["exa"]; !ok || len(cfg.Servers) != 1 {
-				configErr = fmt.Errorf("optional MCP config = %#v, want only exa", cfg.Servers)
-			}
-			configResult <- configErr
-			close(started)
-			<-release
-			registry.Register(cliFakeMCPRegistryTool{})
-			return noopMCPRuntime{}, nil
-		},
-		runTUI: func(ctx context.Context, options tui.Options) int {
-			select {
-			case <-started:
-			case <-time.After(time.Second):
-				t.Fatal("optional MCP initialization did not start")
-			}
-			if options.AwaitToolReadiness == nil {
-				t.Fatal("TUI did not receive optional tool readiness barrier")
-			}
-			if _, ok := options.Registry.Get("mcp_docs_lookup"); ok {
-				t.Fatal("optional MCP tool was published before registration completed")
-			}
-			close(release)
-			options.AwaitToolReadiness(ctx)
-			if _, ok := options.Registry.Get("mcp_docs_lookup"); !ok {
-				t.Fatal("optional MCP tool was not visible after readiness completed")
-			}
-			return 0
-		},
-	})
-
-	if exitCode != 0 {
-		t.Fatalf("exitCode = %d stderr=%s", exitCode, stderr.String())
-	}
-	if configErr := <-configResult; configErr != nil {
-		t.Fatal(configErr)
-	}
-}
-
 func TestTUIMCPCommandUsesLastGoodConfigOnRefreshError(t *testing.T) {
 	var stdout bytes.Buffer
 	var stderr bytes.Buffer
@@ -634,7 +565,6 @@ func TestRunNoArgsClosesPartialMCPRuntimeWhenRegistrationFails(t *testing.T) {
 		t.Fatalf("NewTokenStore() error = %v", err)
 	}
 	runtimeClosed := false
-	secret := "sk-proj-" + strings.Repeat("a", 23) + "0"
 
 	exitCode := runWithDeps([]string{}, &stdout, &stderr, appDeps{
 		getwd: func() (string, error) {
@@ -661,7 +591,7 @@ func TestRunNoArgsClosesPartialMCPRuntimeWhenRegistrationFails(t *testing.T) {
 			return closeFunc(func() error {
 				runtimeClosed = true
 				return nil
-			}), fmt.Errorf("register mcp tools failed: %s", secret)
+			}), errors.New("register mcp tools failed")
 		},
 		runTUI: func(ctx context.Context, options tui.Options) int {
 			t.Fatal("TUI should not launch after MCP registration fails")
@@ -675,12 +605,6 @@ func TestRunNoArgsClosesPartialMCPRuntimeWhenRegistrationFails(t *testing.T) {
 	if !strings.Contains(stderr.String(), "register mcp tools failed") {
 		t.Fatalf("stderr missing registration error: %s", stderr.String())
 	}
-	if strings.Contains(stderr.String(), secret) {
-		t.Fatalf("stderr leaked MCP registration secret: %s", stderr.String())
-	}
-	if !strings.Contains(stderr.String(), redaction.RedactedSecret) {
-		t.Fatalf("stderr missing redaction marker: %s", stderr.String())
-	}
 	if !runtimeClosed {
 		t.Fatal("partial MCP runtime was not closed after registration error")
 	}

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
@@ -943,9 +939,6 @@ func registerToolSearchIfEligible(registry *tools.Registry, deferThreshold int,
 	if deferThreshold <= 0 {
 		return
 	}
-	if _, registered := registry.Get(tools.ToolSearchToolName); registered {
-		return
-	}
 	if deferredEligibleCount(registry, permissionMode, enabledTools, disabledTools) < deferThreshold {
 		return
 	}

internal/cli/exec_writer.go

@@ -267,29 +267,23 @@ func streamJSONPermissionEventType(event agent.PermissionEvent) streamjson.Event
 func (writer *execEventWriter) usage(usage agent.Usage) {
 	if writer.format == execOutputJSON {
 		writer.writeJSON(map[string]any{
-			"type":                "usage",
-			"prompt_tokens":       usage.PromptTokens,
-			"completion_tokens":   usage.CompletionTokens,
-			"cached_input_tokens": usage.CachedInputTokens,
-			"cache_write_tokens":  usage.CacheWriteTokens,
-			"total_tokens":        usage.TotalTokens(),
+			"type":              "usage",
+			"prompt_tokens":     usage.PromptTokens,
+			"completion_tokens": usage.CompletionTokens,
+			"total_tokens":      usage.TotalTokens(),
 		})
 		return
 	}
 	if writer.format == execOutputStreamJSON {
 		promptTokens := usage.EffectiveInputTokens()
 		completionTokens := usage.EffectiveOutputTokens()
-		cachedInputTokens := usage.CachedInputTokens
-		cacheWriteTokens := usage.CacheWriteTokens
 		totalTokens := usage.TotalTokens()
 		writer.writeStreamJSON(streamjson.Event{
-			Type:              streamjson.EventUsage,
-			RunID:             writer.runID,
-			PromptTokens:      &promptTokens,
-			CompletionTokens:  &completionTokens,
-			CachedInputTokens: &cachedInputTokens,
-			CacheWriteTokens:  &cacheWriteTokens,
-			TotalTokens:       &totalTokens,
+			Type:             streamjson.EventUsage,
+			RunID:            writer.runID,
+			PromptTokens:     &promptTokens,
+			CompletionTokens: &completionTokens,
+			TotalTokens:      &totalTokens,
 		})
 	}
 }

internal/cli/exec_writer_test.go

@@ -52,39 +52,3 @@ func TestExecWriterPropagatesToolResultTruncation(t *testing.T) {
 		})
 	}
 }
-
-func TestExecWriterPropagatesCacheUsage(t *testing.T) {
-	for _, format := range []execOutputFormat{execOutputJSON, execOutputStreamJSON} {
-		t.Run(string(format), func(t *testing.T) {
-			var stdout bytes.Buffer
-			writer := execEventWriter{
-				stdout:       &stdout,
-				format:       format,
-				runID:        "run_usage",
-				streamedText: &strings.Builder{},
-			}
-			writer.usage(agent.Usage{
-				InputTokens:       100,
-				OutputTokens:      20,
-				PromptTokens:      100,
-				CompletionTokens:  20,
-				CachedInputTokens: 60,
-				CacheWriteTokens:  10,
-			})
-			if writer.err != nil {
-				t.Fatalf("usage: %v", writer.err)
-			}
-			var payload map[string]any
-			if err := json.Unmarshal(bytes.TrimSpace(stdout.Bytes()), &payload); err != nil {
-				t.Fatalf("decode output %q: %v", stdout.String(), err)
-			}
-			cachedKey, writeKey := "cached_input_tokens", "cache_write_tokens"
-			if format == execOutputStreamJSON {
-				cachedKey, writeKey = "cachedInputTokens", "cacheWriteTokens"
-			}
-			if payload[cachedKey] != float64(60) || payload[writeKey] != float64(10) {
-				t.Fatalf("cache usage missing from payload: %#v", payload)
-			}
-		})
-	}
-}

internal/cli/mcp_startup.go

@@ -1,147 +0,0 @@
-package cli
-
-import (
-	"context"
-	"sync"
-	"time"
-
-	"github.com/Gitlawb/zero/internal/config"
-	"github.com/Gitlawb/zero/internal/mcp"
-	"github.com/Gitlawb/zero/internal/tools"
-)
-
-const (
-	optionalMCPPromptGrace = time.Second
-	optionalMCPCloseGrace  = 250 * time.Millisecond
-)
-
-// splitMCPStartupConfig keeps explicitly configured servers on the
-// prompt-critical path. Only unchanged built-in defaults may initialize after
-// first paint; their failure was already intentionally silent.
-func splitMCPStartupConfig(cfg config.MCPConfig) (critical config.MCPConfig, optional config.MCPConfig) {
-	critical.Servers = map[string]config.MCPServerConfig{}
-	optional.Servers = map[string]config.MCPServerConfig{}
-	for name, server := range cfg.Servers {
-		if server.Disabled {
-			continue
-		}
-		if config.IsUnconfiguredDefault(name, server) {
-			optional.Servers[name] = server
-			continue
-		}
-		critical.Servers[name] = server
-	}
-	return critical, optional
-}
-
-type optionalMCPStartup struct {
-	cancel context.CancelFunc
-	done   chan struct{}
-
-	mu      sync.Mutex
-	runtime mcpToolRuntime
-
-	closeOnce        sync.Once
-	runtimeCloseOnce sync.Once
-	closeErr         error
-}
-
-func startOptionalMCP(
-	parent context.Context,
-	registry *tools.Registry,
-	cfg config.MCPConfig,
-	options mcp.RegisterOptions,
-	register func(context.Context, *tools.Registry, config.MCPConfig, mcp.RegisterOptions) (mcpToolRuntime, error),
-	onReady func(),
-) *optionalMCPStartup {
-	ctx, cancel := context.WithCancel(parent)
-	startup := &optionalMCPStartup{cancel: cancel, done: make(chan struct{})}
-	go func() {
-		runtime, err := register(ctx, registry, cfg, options)
-		if err == nil && onReady != nil {
-			onReady()
-		}
-		startup.mu.Lock()
-		startup.runtime = runtime
-		startup.mu.Unlock()
-		close(startup.done)
-	}()
-	return startup
-}
-
-// Await gives optional tools one bounded opportunity to join the next turn's
-// immutable registry snapshot. A timeout leaves this turn on the existing core
-// tool set; a later turn observes the completed generation.
-func (startup *optionalMCPStartup) Await(ctx context.Context, timeout time.Duration) bool {
-	if startup == nil {
-		return true
-	}
-	select {
-	case <-startup.done:
-		return true
-	default:
-	}
-	if timeout <= 0 {
-		select {
-		case <-startup.done:
-			return true
-		case <-ctx.Done():
-			return false
-		}
-	}
-	timer := time.NewTimer(timeout)
-	defer timer.Stop()
-	select {
-	case <-startup.done:
-		return true
-	case <-timer.C:
-		return false
-	case <-ctx.Done():
-		return false
-	}
-}
-
-func (startup *optionalMCPStartup) Close() error {
-	if startup == nil {
-		return nil
-	}
-	startup.closeOnce.Do(func() {
-		startup.cancel()
-		reaped := make(chan struct{})
-		go func() {
-			defer close(reaped)
-			<-startup.done
-			startup.closeRuntime()
-		}()
-		timer := time.NewTimer(optionalMCPCloseGrace)
-		defer timer.Stop()
-		select {
-		case <-reaped:
-		case <-timer.C:
-		}
-	})
-	startup.mu.Lock()
-	defer startup.mu.Unlock()
-	return startup.closeErr
-}
-
-func (startup *optionalMCPStartup) closeRuntime() {
-	startup.runtimeCloseOnce.Do(func() {
-		startup.mu.Lock()
-		runtime := startup.runtime
-		startup.mu.Unlock()
-		if runtime == nil {
-			return
-		}
-		err := runtime.Close()
-		startup.mu.Lock()
-		if err != nil && startup.closeErr == nil {
-			startup.closeErr = err
-		}
-		startup.mu.Unlock()
-	})
-}
-
-func (startup *optionalMCPStartup) Skipped() []mcp.SkippedServer {
-	return nil
-}

internal/cli/mcp_startup_test.go

@@ -1,187 +0,0 @@
-package cli
-
-import (
-	"context"
-	"errors"
-	"testing"
-	"time"
-
-	"github.com/Gitlawb/zero/internal/config"
-	"github.com/Gitlawb/zero/internal/mcp"
-	"github.com/Gitlawb/zero/internal/tools"
-)
-
-type closeTrackingMCPRuntime struct {
-	closed chan struct{}
-	err    error
-}
-
-func (runtime *closeTrackingMCPRuntime) Close() error {
-	close(runtime.closed)
-	return runtime.err
-}
-
-func (*closeTrackingMCPRuntime) Skipped() []mcp.SkippedServer { return nil }
-
-func TestSplitMCPStartupConfigDefersOnlyUnconfiguredDefaults(t *testing.T) {
-	defaults := config.DefaultMCPServers()
-	cfg := config.MCPConfig{Servers: map[string]config.MCPServerConfig{
-		"exa":      defaults["exa"],
-		"docs":     {Type: "http", URL: "https://docs.example.test/mcp"},
-		"disabled": {Type: "http", URL: "https://disabled.example.test/mcp", Disabled: true},
-	}}
-
-	critical, optional := splitMCPStartupConfig(cfg)
-	if _, ok := critical.Servers["docs"]; !ok || len(critical.Servers) != 1 {
-		t.Fatalf("critical servers = %#v, want only docs", critical.Servers)
-	}
-	if _, ok := optional.Servers["exa"]; !ok || len(optional.Servers) != 1 {
-		t.Fatalf("optional servers = %#v, want only exa", optional.Servers)
-	}
-}
-
-func TestOptionalMCPAwaitTimesOutThenObservesPublishedTools(t *testing.T) {
-	registry := tools.NewRegistry()
-	release := make(chan struct{})
-	started := make(chan struct{})
-	startup := startOptionalMCP(
-		context.Background(),
-		registry,
-		config.MCPConfig{Servers: config.DefaultMCPServers()},
-		mcp.RegisterOptions{},
-		func(ctx context.Context, registry *tools.Registry, _ config.MCPConfig, _ mcp.RegisterOptions) (mcpToolRuntime, error) {
-			close(started)
-			select {
-			case <-release:
-				registry.RegisterBatch([]tools.Tool{tools.NewScopedReadFileTool(t.TempDir(), nil)})
-				return noopMCPRuntime{}, nil
-			case <-ctx.Done():
-				return noopMCPRuntime{}, ctx.Err()
-			}
-		},
-		nil,
-	)
-	defer func() { _ = startup.Close() }()
-	<-started
-
-	if startup.Await(t.Context(), time.Millisecond) {
-		t.Fatal("optional startup unexpectedly completed before release")
-	}
-	if got := len(registry.All()); got != 0 {
-		t.Fatalf("registry published tools before readiness: %d", got)
-	}
-	close(release)
-	if !startup.Await(t.Context(), time.Second) {
-		t.Fatal("optional startup did not complete after release")
-	}
-	if _, ok := registry.Get("read_file"); !ok {
-		t.Fatal("completed optional startup did not publish its tool batch")
-	}
-}
-
-func TestOptionalMCPFailedRegistrationSkipsReadinessCallback(t *testing.T) {
-	readyCalls := 0
-	startup := startOptionalMCP(
-		context.Background(),
-		tools.NewRegistry(),
-		config.MCPConfig{Servers: config.DefaultMCPServers()},
-		mcp.RegisterOptions{},
-		func(context.Context, *tools.Registry, config.MCPConfig, mcp.RegisterOptions) (mcpToolRuntime, error) {
-			return noopMCPRuntime{}, errors.New("connect failed")
-		},
-		func() { readyCalls++ },
-	)
-	defer func() { _ = startup.Close() }()
-
-	if !startup.Await(t.Context(), time.Second) {
-		t.Fatal("failed optional startup did not settle")
-	}
-	if readyCalls != 0 {
-		t.Fatalf("readiness callback ran after failed registration: %d", readyCalls)
-	}
-}
-
-func TestOptionalMCPCloseCancelsBlockedStartup(t *testing.T) {
-	started := make(chan struct{})
-	startup := startOptionalMCP(
-		context.Background(),
-		tools.NewRegistry(),
-		config.MCPConfig{Servers: config.DefaultMCPServers()},
-		mcp.RegisterOptions{},
-		func(ctx context.Context, _ *tools.Registry, _ config.MCPConfig, _ mcp.RegisterOptions) (mcpToolRuntime, error) {
-			close(started)
-			<-ctx.Done()
-			return noopMCPRuntime{}, nil
-		},
-		nil,
-	)
-	<-started
-	if err := startup.Close(); err != nil {
-		t.Fatalf("Close() error = %v", err)
-	}
-}
-
-func TestOptionalMCPCloseReturnsRuntimeErrorWithinGrace(t *testing.T) {
-	closeErr := errors.New("close failed")
-	runtime := &closeTrackingMCPRuntime{closed: make(chan struct{}), err: closeErr}
-	startup := startOptionalMCP(
-		context.Background(),
-		tools.NewRegistry(),
-		config.MCPConfig{Servers: config.DefaultMCPServers()},
-		mcp.RegisterOptions{},
-		func(context.Context, *tools.Registry, config.MCPConfig, mcp.RegisterOptions) (mcpToolRuntime, error) {
-			return runtime, nil
-		},
-		nil,
-	)
-	if !startup.Await(t.Context(), time.Second) {
-		t.Fatal("optional startup did not settle")
-	}
-	if err := startup.Close(); !errors.Is(err, closeErr) {
-		t.Fatalf("Close() error = %v, want %v", err, closeErr)
-	}
-}
-
-func TestOptionalMCPCloseBoundsRegistrationThatIgnoresCancellation(t *testing.T) {
-	started := make(chan struct{})
-	release := make(chan struct{})
-	released := false
-	defer func() {
-		if !released {
-			close(release)
-		}
-	}()
-	runtime := &closeTrackingMCPRuntime{closed: make(chan struct{})}
-	startup := startOptionalMCP(
-		context.Background(),
-		tools.NewRegistry(),
-		config.MCPConfig{Servers: config.DefaultMCPServers()},
-		mcp.RegisterOptions{},
-		func(context.Context, *tools.Registry, config.MCPConfig, mcp.RegisterOptions) (mcpToolRuntime, error) {
-			close(started)
-			<-release
-			return runtime, nil
-		},
-		nil,
-	)
-	<-started
-
-	closeResult := make(chan error, 1)
-	go func() { closeResult <- startup.Close() }()
-	select {
-	case err := <-closeResult:
-		if err != nil {
-			t.Fatalf("Close() error = %v", err)
-		}
-	case <-time.After(time.Second):
-		t.Fatal("Close blocked on registration after cancellation")
-	}
-
-	close(release)
-	released = true
-	select {
-	case <-runtime.closed:
-	case <-time.After(time.Second):
-		t.Fatal("late optional MCP runtime was not closed")
-	}
-}

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/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/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

@@ -176,11 +176,9 @@ func RegisterTools(ctx context.Context, registry *tools.Registry, cfg config.MCP
 			staged = append(staged, tool)
 		}
 	}
-	registered := make([]tools.Tool, 0, len(staged))
-	for index := range staged {
-		registered = append(registered, staged[index])
+	for _, tool := range staged {
+		registry.Register(tool)
 	}
-	registry.RegisterBatch(registered)
 	return runtime, nil
 }
 

internal/mcp/registry_test.go

@@ -70,62 +70,6 @@ func TestRegisterToolsAddsPromptGatedMCPTools(t *testing.T) {
 	}
 }
 
-func TestRegisterToolsPublishesServerToolsInOneGeneration(t *testing.T) {
-	registry := tools.NewRegistry()
-	before := registry.Snapshot().Generation
-	client := &fakeToolClient{listed: []RemoteTool{
-		{Name: "lookup", Description: "Lookup documentation"},
-		{Name: "search", Description: "Search documentation"},
-	}}
-	runtime, err := RegisterTools(context.Background(), registry, config.MCPConfig{Servers: map[string]config.MCPServerConfig{
-		"docs": {Type: "stdio", Command: "docs-mcp"},
-	}}, RegisterOptions{ClientFactory: func(context.Context, Server) (ToolClient, error) {
-		return client, nil
-	}})
-	if err != nil {
-		t.Fatalf("RegisterTools() error = %v", err)
-	}
-	defer runtime.Close()
-
-	after := registry.Snapshot()
-	if after.Generation != before+1 {
-		t.Fatalf("registry generation = %d, want %d", after.Generation, before+1)
-	}
-	for _, name := range []string{"mcp_docs_lookup", "mcp_docs_search"} {
-		if _, ok := registry.Get(name); !ok {
-			t.Fatalf("expected %s to be published in the batch", name)
-		}
-	}
-}
-
-func TestRegisterToolsPublishesNoneWhenServerToolValidationFails(t *testing.T) {
-	registry := tools.NewRegistry()
-	before := registry.Snapshot().Generation
-	client := &fakeToolClient{listed: []RemoteTool{
-		{Name: "lookup", Description: "Lookup documentation"},
-		{Name: "", Description: "Invalid nameless tool"},
-	}}
-	runtime, err := RegisterTools(context.Background(), registry, config.MCPConfig{Servers: map[string]config.MCPServerConfig{
-		"docs": {Type: "stdio", Command: "docs-mcp"},
-	}}, RegisterOptions{ClientFactory: func(context.Context, Server) (ToolClient, error) {
-		return client, nil
-	}})
-	if err != nil {
-		t.Fatalf("RegisterTools() error = %v", err)
-	}
-	defer runtime.Close()
-
-	if got := registry.Snapshot().Generation; got != before {
-		t.Fatalf("registry generation = %d, want unchanged %d", got, before)
-	}
-	if _, ok := registry.Get("mcp_docs_lookup"); ok {
-		t.Fatal("valid prefix of rejected server batch was published")
-	}
-	if skipped := runtime.Skipped(); len(skipped) != 1 || skipped[0].Name != "docs" || skipped[0].Err == nil {
-		t.Fatalf("Skipped() = %#v, want one validation failure for docs", skipped)
-	}
-}
-
 func TestRegisterToolsMarksPersistentlyApprovedToolsAllow(t *testing.T) {
 	store, err := NewPermissionStore(StoreOptions{
 		FilePath: filepath.Join(t.TempDir(), "permissions.json"),

internal/perfbench/turn_bench.go

@@ -191,7 +191,6 @@ type TurnBenchResult struct {
 type TurnBenchTotals struct {
 	InputTokens       int64 `json:"inputTokens"`
 	CachedInputTokens int64 `json:"cachedInputTokens"`
-	CacheWriteTokens  int64 `json:"cacheWriteTokens"`
 	OutputTokens      int64 `json:"outputTokens"`
 	ModelRequests     int64 `json:"modelRequests"`
 	ToolCalls         int64 `json:"toolCalls"`
@@ -480,7 +479,6 @@ func topLatencySources(perSpan map[string]SpanStats, top int) []LatencySource {
 func aggregateTotals(totals *TurnBenchTotals, tr *trace.TurnTrace) {
 	totals.InputTokens += tr.Counter(trace.CounterInputTokens)
 	totals.CachedInputTokens += tr.Counter(trace.CounterCachedInputTokens)
-	totals.CacheWriteTokens += tr.Counter(trace.CounterCacheWriteTokens)
 	totals.OutputTokens += tr.Counter(trace.CounterOutputTokens)
 	totals.ModelRequests += tr.Counter(trace.CounterModelRequests)
 	totals.ToolCalls += tr.Counter(trace.CounterToolCalls)
@@ -533,9 +531,8 @@ func FormatTurnBenchSummary(result TurnBenchResult) string {
 			lines = append(lines, fmt.Sprintf("  %-18s %10s  %5.1f%%", src.Span, FormatMetric(src.TotalMs, "ms"), src.Share*100))
 		}
 	}
-	lines = append(lines, fmt.Sprintf("totals: in=%d (cache-read %d, cache-write %d, uncached %d) out=%d | requests=%d tools=%d retries=%d reconnects=%d compactions=%d",
-		result.Totals.InputTokens, result.Totals.CachedInputTokens, result.Totals.CacheWriteTokens,
-		uncachedInputTokens(result.Totals), result.Totals.OutputTokens,
+	lines = append(lines, fmt.Sprintf("totals: in=%d (cached %d) out=%d | requests=%d tools=%d retries=%d reconnects=%d compactions=%d",
+		result.Totals.InputTokens, result.Totals.CachedInputTokens, result.Totals.OutputTokens,
 		result.Totals.ModelRequests, result.Totals.ToolCalls, result.Totals.Retries,
 		result.Totals.Reconnects, result.Totals.Compactions))
 	for _, class := range sortedClasses(result.PerClass) {
@@ -548,23 +545,6 @@ func FormatTurnBenchSummary(result TurnBenchResult) string {
 	return strings.Join(lines, "\n")
 }
 
-func uncachedInputTokens(totals TurnBenchTotals) int64 {
-	remaining := totals.InputTokens
-	if remaining <= 0 {
-		return 0
-	}
-	for _, cached := range []int64{totals.CachedInputTokens, totals.CacheWriteTokens} {
-		if cached <= 0 {
-			continue
-		}
-		if cached >= remaining {
-			return 0
-		}
-		remaining -= cached
-	}
-	return remaining
-}
-
 // classTier returns the oracle tier label a class was classified into, so the
 // per-class roll-up states explicitly which oracle (if any) its "passed" count
 // is measured against.

internal/perfbench/turn_bench_test.go

@@ -74,7 +74,6 @@ func TestRunTurnBenchAggregation(t *testing.T) {
 		"t3": cannedTrace(150, 20, 1500),
 		"t4": cannedTrace(300, 10, 1000),
 	}
-	canned["t1"].Counters = append(canned["t1"].Counters, trace.Counter{Name: trace.CounterCacheWriteTokens, Value: 125})
 	cfg := TurnBenchConfig{
 		Model:      "fake-model",
 		Iterations: 1,
@@ -156,9 +155,6 @@ func TestRunTurnBenchAggregation(t *testing.T) {
 	if result.Totals.InputTokens != 5500 {
 		t.Fatalf("inputTokens = %d, want 5500", result.Totals.InputTokens)
 	}
-	if result.Totals.CacheWriteTokens != 125 {
-		t.Fatalf("cacheWriteTokens = %d, want 125", result.Totals.CacheWriteTokens)
-	}
 	if result.Totals.OutputTokens != 2750 {
 		t.Fatalf("outputTokens = %d, want 2750", result.Totals.OutputTokens)
 	}
@@ -338,35 +334,6 @@ func TestFormatTurnBenchSummaryNamesTopSources(t *testing.T) {
 	}
 }
 
-func TestUncachedInputTokensClampsInconsistentTotals(t *testing.T) {
-	tests := []struct {
-		name   string
-		totals TurnBenchTotals
-		want   int64
-	}{
-		{name: "normal", totals: TurnBenchTotals{InputTokens: 100, CachedInputTokens: 30, CacheWriteTokens: 20}, want: 50},
-		{name: "cached exceeds input", totals: TurnBenchTotals{InputTokens: 100, CachedInputTokens: 120}, want: 0},
-		{name: "write exceeds remainder", totals: TurnBenchTotals{InputTokens: 100, CachedInputTokens: 20, CacheWriteTokens: 90}, want: 0},
-		{name: "overflowing inconsistent counters", totals: TurnBenchTotals{CachedInputTokens: 1<<63 - 1, CacheWriteTokens: 1<<63 - 1}, want: 0},
-		{name: "overflowing counters with input", totals: TurnBenchTotals{InputTokens: 100, CachedInputTokens: 1<<63 - 1, CacheWriteTokens: 1<<63 - 1}, want: 0},
-		{name: "negative cache counters ignored", totals: TurnBenchTotals{InputTokens: 100, CachedInputTokens: -20, CacheWriteTokens: -10}, want: 100},
-	}
-	for _, test := range tests {
-		t.Run(test.name, func(t *testing.T) {
-			if got := uncachedInputTokens(test.totals); got != test.want {
-				t.Fatalf("uncachedInputTokens(%+v) = %d, want %d", test.totals, got, test.want)
-			}
-		})
-	}
-	summary := FormatTurnBenchSummary(TurnBenchResult{Totals: TurnBenchTotals{
-		CachedInputTokens: 1<<63 - 1,
-		CacheWriteTokens:  1<<63 - 1,
-	}})
-	if !strings.Contains(summary, "uncached 0") {
-		t.Fatalf("summary did not clamp inconsistent cache totals:\n%s", summary)
-	}
-}
-
 func TestLoadBaselineManifest(t *testing.T) {
 	path := filepath.Join("manifests", "baseline.json")
 	set, err := LoadTaskSet(path)

internal/providerhealth/providerhealth.go

@@ -19,7 +19,6 @@ import (
 	"github.com/Gitlawb/zero/internal/providercatalog"
 	"github.com/Gitlawb/zero/internal/providers"
 	"github.com/Gitlawb/zero/internal/providers/providerio"
-	"github.com/Gitlawb/zero/internal/proxydial"
 	"github.com/Gitlawb/zero/internal/redaction"
 )
 
@@ -519,15 +518,9 @@ func newConnectivityClient(timeout time.Duration, resolver Resolver, sensitiveHe
 		transport = &http.Transport{}
 	}
 	transport.DialContext = safeDialContext(resolver, allowLoopbackOrPrivate)
-	// WRAPPED, SO THE DIALER LEARNS THE ROUTE THIS TRANSPORT CHOSE. The wrapper
-	// records the proxy selected for each request on that request, and the
-	// dialer reads it back on the dial that request causes; installing the bare
-	// transport instead would leave a proxied dial looking like a loopback
-	// target and fail the probe (#569). The cloned default transport already
-	// reads HTTPS_PROXY and friends; nothing new is enabled.
 	return &http.Client{
 		Timeout:   timeout,
-		Transport: proxydial.Wrap(transport),
+		Transport: transport,
 		CheckRedirect: func(req *http.Request, via []*http.Request) error {
 			if len(via) >= maxConnectivityRedirects {
 				return fmt.Errorf("provider connectivity exceeded %d redirects", maxConnectivityRedirects)
@@ -590,17 +583,6 @@ func sensitiveAuthHeaderNames(profile config.ProviderProfile, kind config.Provid
 func safeDialContext(resolver Resolver, allowLoopbackOrPrivate bool) func(context.Context, string, string) (net.Conn, error) {
 	dialer := &net.Dialer{Timeout: 10 * time.Second, KeepAlive: 30 * time.Second}
 	return func(ctx context.Context, network, address string) (net.Conn, error) {
-		// THE PROXY IS NOT THE TARGET. With HTTPS_PROXY set to a local forward
-		// proxy, the transport dials the proxy first and tunnels the request
-		// through it, and this dialer used to refuse that dial as a loopback
-		// address: "proxyconnect tcp: ... loopback hosts are blocked" for a
-		// request whose real target had already been validated (#569). The
-		// target validation is unchanged; only the dial the transport opens to
-		// the proxy it picked for this very request is let past the guard, and a
-		// direct dial is checked as it always was.
-		if proxydial.IsProxyDial(ctx) {
-			return dialer.DialContext(ctx, network, address)
-		}
 		host, port, err := net.SplitHostPort(address)
 		if err != nil {
 			return nil, err

internal/providerhealth/proxy_dial_test.go

@@ -1,218 +0,0 @@
-package providerhealth
-
-import (
-	"context"
-	"errors"
-	"net"
-	"net/http"
-	"net/netip"
-	"net/url"
-	"strconv"
-	"strings"
-	"testing"
-	"time"
-
-	"github.com/Gitlawb/zero/internal/proxydial"
-)
-
-// connectivityClientWithProxy builds the real connectivity client and swaps in
-// a proxy function, which is how the transport learns its route. The
-// environment is left alone deliberately: http.ProxyFromEnvironment reads it
-// once per process, so an environment-driven test would depend on test order.
-func connectivityClientWithProxy(t *testing.T, resolver Resolver, proxyFor func(*http.Request) (*url.URL, error)) *http.Client {
-	t.Helper()
-	client := newConnectivityClient(3*time.Second, resolver, nil, false)
-	wrapped, ok := client.Transport.(*proxydial.Transport)
-	if !ok {
-		t.Fatalf("transport = %T, want the route-recording wrapper; without it no dial can be recognised as the proxy dial", client.Transport)
-	}
-	wrapped.Proxy = proxyFor
-	return client
-}
-
-// recordingProxy is a listener standing in for a local forward proxy. It
-// records the first line it receives and hangs up.
-func recordingProxy(t *testing.T) (*url.URL, <-chan string) {
-	t.Helper()
-	listener, err := net.Listen("tcp", "127.0.0.1:0")
-	if err != nil {
-		t.Fatal(err)
-	}
-	t.Cleanup(func() { _ = listener.Close() })
-	arrived := make(chan string, 1)
-	go func() {
-		conn, err := listener.Accept()
-		if err != nil {
-			return
-		}
-		defer conn.Close()
-		buffer := make([]byte, 256)
-		n, _ := conn.Read(buffer)
-		arrived <- string(buffer[:n])
-	}()
-	proxyURL, err := url.Parse("http://" + listener.Addr().String())
-	if err != nil {
-		t.Fatal(err)
-	}
-	return proxyURL, arrived
-}
-
-// THE PROXY IS NOT THE TARGET, AND THE GUARD HAS TO KNOW THE DIFFERENCE.
-//
-// With HTTPS_PROXY set to a local forward proxy, the transport dials the proxy
-// first and tunnels the request through it. This dialer refused that dial as a
-// loopback address, so `zero doctor --connectivity` failed with "proxyconnect
-// tcp: ... loopback hosts are blocked" for a target that had already been
-// validated and was public (#569). Driven through the real client, so the route
-// is the transport's own decision.
-func TestConnectivityClientTunnelsThroughTheConfiguredProxy(t *testing.T) {
-	proxyURL, arrived := recordingProxy(t)
-	client := connectivityClientWithProxy(t,
-		staticResolver{err: errors.New("resolver must not be called for a proxied request")},
-		func(*http.Request) (*url.URL, error) { return proxyURL, nil })
-
-	request, err := http.NewRequestWithContext(context.Background(), http.MethodGet, "https://api.example.com/v1/models", nil)
-	if err != nil {
-		t.Fatal(err)
-	}
-	_, err = client.Do(request)
-	select {
-	case first := <-arrived:
-		if line := strings.SplitN(first, "\r\n", 2)[0]; line != "CONNECT api.example.com:443 HTTP/1.1" {
-			t.Fatalf("proxy received %q, want a CONNECT for the validated target", line)
-		}
-	case <-time.After(5 * time.Second):
-		t.Fatalf("the proxy never received a connection; request error: %v", err)
-	}
-}
-
-// AND A DIRECT REQUEST STAYS GUARDED, EVEN WHEN ITS ORIGIN IS THE PROXY'S OWN
-// ADDRESS.
-//
-// This is the NO_PROXY shape: the proxy function sends one host direct. An
-// exemption derived from asking that function about a request of our own
-// invention would answer "proxied" for the excluded host too, and this dial,
-// whose address equals the configured proxy endpoint, would skip the resolver
-// and reach whatever the name resolves to at connect time.
-func TestDirectRequestToTheProxyEndpointIsStillGuarded(t *testing.T) {
-	proxyURL, err := url.Parse("http://rebind.example:80")
-	if err != nil {
-		t.Fatal(err)
-	}
-	lookups := 0
-	resolver := countingResolver{
-		onLookup: func() { lookups++ },
-		addr:     netip.MustParseAddr("10.0.0.5"),
-	}
-	client := connectivityClientWithProxy(t, resolver, func(request *http.Request) (*url.URL, error) {
-		if request.URL.Hostname() == "rebind.example" {
-			return nil, nil
-		}
-		return proxyURL, nil
-	})
-
-	request, err := http.NewRequestWithContext(context.Background(), http.MethodGet, "http://rebind.example/data", nil)
-	if err != nil {
-		t.Fatal(err)
-	}
-	_, err = client.Do(request)
-
-	if lookups == 0 {
-		t.Fatal("the direct dial skipped the safety resolver because its address matched the configured proxy endpoint")
-	}
-	var safety endpointSafetyError
-	if !errors.As(err, &safety) {
-		t.Fatalf("err = %v, want the private answer to be refused", err)
-	}
-}
-
-// A proxy configured with a Unicode hostname is dialed by its IDNA-encoded
-// name, and it is still the proxy: the request must reach it rather than be
-// refused as an ordinary private address.
-func TestUnicodeProxyHostnameIsStillTheProxy(t *testing.T) {
-	dialed := ""
-	client := connectivityClientWithProxy(t,
-		staticResolver{err: errors.New("resolver must not be called for a proxied request")},
-		func(*http.Request) (*url.URL, error) { return url.Parse("http://büro.example:3067") })
-	wrapped := client.Transport.(*proxydial.Transport)
-	guarded := wrapped.DialContext
-	wrapped.DialContext = func(ctx context.Context, network, address string) (net.Conn, error) {
-		dialed = address
-		return guarded(ctx, network, address)
-	}
-
-	request, err := http.NewRequestWithContext(context.Background(), http.MethodGet, "https://api.example.com/v1/models", nil)
-	if err != nil {
-		t.Fatal(err)
-	}
-	_, err = client.Do(request)
-
-	if dialed != "xn--bro-hoa.example:3067" {
-		t.Fatalf("SETUP INVALID: dialed %q, want the IDNA-encoded proxy endpoint", dialed)
-	}
-	var safety endpointSafetyError
-	if errors.As(err, &safety) {
-		t.Fatalf("the configured proxy was refused by the guard: %v", err)
-	}
-}
-
-// Without a proxy the guard is exactly what it was: loopback is refused.
-func TestSafeDialContextStillRefusesLoopbackWithoutAProxy(t *testing.T) {
-	dial := safeDialContext(staticResolver{err: errors.New("resolver must not be called")}, false)
-	conn, err := dial(context.Background(), "tcp", "127.0.0.1:3067")
-	if conn != nil {
-		_ = conn.Close()
-		t.Fatal("loopback was dialed with no proxy configured")
-	}
-	var safety endpointSafetyError
-	if !errors.As(err, &safety) {
-		t.Fatalf("err = %v, want endpointSafetyError", err)
-	}
-}
-
-// A sibling loopback port is not the proxy, and the guard is unchanged for it.
-func TestSafeDialContextRefusesALoopbackPortThatIsNotTheProxy(t *testing.T) {
-	proxyURL, arrived := recordingProxy(t)
-	client := connectivityClientWithProxy(t,
-		staticResolver{err: errors.New("resolver must not be called")},
-		func(request *http.Request) (*url.URL, error) {
-			// Only the https probe is proxied; the http one below is direct and
-			// happens to point at the neighbouring port.
-			if request.URL.Scheme == "https" {
-				return proxyURL, nil
-			}
-			return nil, nil
-		})
-
-	_, port, _ := net.SplitHostPort(proxyURL.Host)
-	number, _ := strconv.Atoi(port)
-	sibling := "http://" + net.JoinHostPort("127.0.0.1", strconv.Itoa(number+1)) + "/"
-	request, err := http.NewRequestWithContext(context.Background(), http.MethodGet, sibling, nil)
-	if err != nil {
-		t.Fatal(err)
-	}
-	_, err = client.Do(request)
-	var safety endpointSafetyError
-	if !errors.As(err, &safety) {
-		t.Fatalf("err = %v, want a loopback port beside the proxy to stay blocked", err)
-	}
-	select {
-	case first := <-arrived:
-		t.Fatalf("the proxy received a connection it should not have: %q", first)
-	default:
-	}
-}
-
-// countingResolver answers with one address and reports each lookup, so a test
-// can tell a skipped guard from a guard that ran and allowed the address.
-type countingResolver struct {
-	onLookup func()
-	addr     netip.Addr
-}
-
-func (resolver countingResolver) LookupNetIP(context.Context, string, string) ([]netip.Addr, error) {
-	if resolver.onLookup != nil {
-		resolver.onLookup()
-	}
-	return []netip.Addr{resolver.addr}, nil
-}

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/providers/openai/codex_responses.go

@@ -62,7 +62,6 @@ const (
 	responsesEventReasoningDelta    = "response.reasoning_summary_text.delta"
 	responsesEventOutputTextDone    = "response.output_text.done"
 	responsesEventFunctionArgsDelta = "response.function_call_arguments.delta"
-	responsesEventCustomInputDelta  = "response.custom_tool_call_input.delta"
 	responsesEventContentPartDone   = "response.content_part.done"
 	responsesEventOutputItemDone    = "response.output_item.done"
 	responsesEventCompleted         = "response.completed"
@@ -71,37 +70,17 @@ const (
 	responsesEventIncomplete        = "response.incomplete"
 )
 
-const applyPatchLarkGrammar = `start: begin_patch hunk+ end_patch
-begin_patch: "*** Begin Patch" LF
-end_patch: "*** End Patch" LF?
-hunk: add_hunk | delete_hunk | update_hunk
-add_hunk: "*** Add File: " filename LF add_line+
-delete_hunk: "*** Delete File: " filename LF
-update_hunk: "*** Update File: " filename LF change_move? change?
-filename: /(.+)/
-add_line: "+" /(.*)/ LF -> line
-change_move: "*** Move to: " filename LF
-change: (change_context | change_line)+ eof_line?
-change_context: ("@@" | "@@ " /(.+)/) LF
-change_line: ("+" | "-" | " ") /(.*)/ LF
-eof_line: "*** End of File" LF
-%import common.LF`
-
 // responsesRequest is the wire shape POSTed to {baseURL}/responses.
 type responsesRequest struct {
-	Type               string              `json:"type,omitempty"`
-	Model              string              `json:"model"`
-	Instructions       string              `json:"instructions"`
-	PreviousResponseID string              `json:"previous_response_id,omitempty"`
-	Input              []inputItem         `json:"input"`
-	Stream             bool                `json:"stream"`
-	Store              bool                `json:"store"`
-	ParallelToolCalls  bool                `json:"parallel_tool_calls"`
-	MaxOutputTokens    int                 `json:"max_output_tokens,omitempty"`
-	Tools              []responsesTool     `json:"tools,omitempty"`
-	Reasoning          *responsesReasoning `json:"reasoning,omitempty"`
-	ServiceTier        string              `json:"service_tier,omitempty"`
-	PromptCacheKey     string              `json:"prompt_cache_key,omitempty"`
+	Model           string              `json:"model"`
+	Instructions    string              `json:"instructions"`
+	Input           []inputItem         `json:"input"`
+	Stream          bool                `json:"stream"`
+	Store           bool                `json:"store"`
+	MaxOutputTokens int                 `json:"max_output_tokens,omitempty"`
+	Tools           []responsesTool     `json:"tools,omitempty"`
+	Reasoning       *responsesReasoning `json:"reasoning,omitempty"`
+	ServiceTier     string              `json:"service_tier,omitempty"`
 }
 
 // responsesReasoning carries the reasoning controls for the Responses API. The
@@ -126,7 +105,6 @@ type inputItem struct {
 	CallID    string `json:"call_id,omitempty"`
 	Name      string `json:"name,omitempty"`
 	Arguments string `json:"arguments,omitempty"`
-	Input     string `json:"input,omitempty"`
 	// function_call_output fields
 	Output any `json:"output,omitempty"`
 }
@@ -140,11 +118,10 @@ type contentItem struct {
 }
 
 type responsesTool struct {
-	Type        string                            `json:"type"`
-	Name        string                            `json:"name"`
-	Description string                            `json:"description,omitempty"`
-	Parameters  map[string]any                    `json:"parameters,omitempty"`
-	Format      *zeroruntime.ToolDefinitionFormat `json:"format,omitempty"`
+	Type        string         `json:"type"`
+	Name        string         `json:"name"`
+	Description string         `json:"description,omitempty"`
+	Parameters  map[string]any `json:"parameters,omitempty"`
 }
 
 // responsesEvent is the decoded form of one Responses SSE data payload.
@@ -155,7 +132,6 @@ type responsesEvent struct {
 	Delta string `json:"delta,omitempty"`
 	// item payloads (response.output_item.added / done)
 	ItemID string `json:"item_id,omitempty"`
-	CallID string `json:"call_id,omitempty"`
 	// OutputIndex is a *int so a real 0 (the first output) is distinguishable from
 	// "absent" — a plain int defaulting to 0 dropped a no-item_id call's args (M1).
 	OutputIndex *int         `json:"output_index,omitempty"`
@@ -174,7 +150,6 @@ type itemPayload struct {
 	CallID    string `json:"call_id,omitempty"`
 	Name      string `json:"name,omitempty"`
 	Arguments string `json:"arguments,omitempty"`
-	Input     string `json:"input,omitempty"`
 	Status    string `json:"status,omitempty"`
 }
 
@@ -198,8 +173,7 @@ type outputDetails struct {
 }
 
 type inputDetails struct {
-	CachedTokens     int `json:"cached_tokens"`
-	CacheWriteTokens int `json:"cache_write_tokens"`
+	CachedTokens int `json:"cached_tokens"`
 }
 
 type errorPayload struct {
@@ -213,10 +187,8 @@ type errorPayload struct {
 // response.output_item.done.
 type toolCallBuilder struct {
 	ID        string
-	CallID    string
 	Name      string
 	Arguments strings.Builder
-	Freeform  bool
 	started   bool
 	ended     bool
 }
@@ -225,57 +197,15 @@ type toolCallBuilder struct {
 // event has been emitted. It is the Responses-API equivalent of the
 // chat-completions toolState in provider.go.
 type responsesState struct {
-	toolCalls  map[string]*toolCallBuilder
-	toolOrder  []string
-	text       strings.Builder
-	responseID string
-	usage      *usagePayload
-	emitted    bool
-	done       bool
+	toolCalls map[string]*toolCallBuilder
+	usage     *usagePayload
+	done      bool
 }
 
 func newResponsesState() *responsesState {
 	return &responsesState{toolCalls: map[string]*toolCallBuilder{}}
 }
 
-func (state *responsesState) outputInputItems() []inputItem {
-	items := make([]inputItem, 0, len(state.toolOrder)+1)
-	if state.text.Len() > 0 {
-		items = append(items, inputItem{
-			Type:    "message",
-			Role:    "assistant",
-			Content: []contentItem{{Type: "output_text", Text: state.text.String()}},
-		})
-	}
-	for _, key := range state.toolOrder {
-		builder := state.toolCalls[key]
-		if builder == nil || builder.ID == "" || builder.Name == "" {
-			continue
-		}
-		callID := builder.CallID
-		if callID == "" {
-			callID = builder.ID
-		}
-		itemType := "function_call"
-		if builder.Freeform {
-			itemType = "custom_tool_call"
-		}
-		item := inputItem{
-			Type:   itemType,
-			ID:     builder.ID,
-			CallID: callID,
-			Name:   builder.Name,
-		}
-		if builder.Freeform {
-			item.Input = builder.Arguments.String()
-		} else {
-			item.Arguments = builder.Arguments.String()
-		}
-		items = append(items, item)
-	}
-	return items
-}
-
 // buildResponsesRequest converts a runtime CompletionRequest into the
 // Responses API wire format. System messages fold into a top-level
 // `instructions` field; everything else (user/assistant turns, tool
@@ -285,14 +215,11 @@ func (p *CodexProvider) buildResponsesRequest(request zeroruntime.CompletionRequ
 		return nil, errors.New("codex provider: model is required")
 	}
 	req := &responsesRequest{
-		Model:             p.inner.model,
-		Stream:            true,
-		ParallelToolCalls: true,
-		MaxOutputTokens:   p.inner.maxTokens,
-		PromptCacheKey:    request.PromptCacheKey,
+		Model:           p.inner.model,
+		Stream:          true,
+		MaxOutputTokens: p.inner.maxTokens,
 	}
 	instructions := []string{}
-	customCallIDs := map[string]string{}
 	for _, msg := range request.Messages {
 		switch msg.Role {
 		case zeroruntime.MessageRoleSystem:
@@ -307,31 +234,13 @@ func (p *CodexProvider) buildResponsesRequest(request zeroruntime.CompletionRequ
 				return nil, err
 			}
 			req.Input = append(req.Input, items...)
-			for _, call := range msg.ToolCalls {
-				if call.Freeform && call.ID != "" {
-					callID := call.ProviderCallID
-					if callID == "" {
-						callID = call.ID
-					}
-					customCallIDs[call.ID] = callID
-				}
-			}
 		case zeroruntime.MessageRoleTool:
 			if msg.ToolCallID == "" {
 				return nil, fmt.Errorf("codex provider: tool message missing tool call id")
 			}
-			outputType := "function_call_output"
-			callID := msg.ToolCallProviderID
-			if callID == "" {
-				callID = msg.ToolCallID
-			}
-			if customID, custom := customCallIDs[msg.ToolCallID]; custom {
-				outputType = "custom_tool_call_output"
-				callID = customID
-			}
 			req.Input = append(req.Input, inputItem{
-				Type:   outputType,
-				CallID: callID,
+				Type:   "function_call_output",
+				CallID: msg.ToolCallID,
 				Output: msg.Content,
 			})
 		default:
@@ -340,25 +249,12 @@ func (p *CodexProvider) buildResponsesRequest(request zeroruntime.CompletionRequ
 	}
 	req.Instructions = strings.Join(instructions, "\n\n")
 	for _, tool := range request.Tools {
-		definition := tool
-		if definition.Name == "apply_patch" && definition.Type == zeroruntime.ToolDefinitionFreeform {
-			definition.Description = "The apply_patch tool edits files from a raw structured patch. Use absolute file paths in patch headers to target a granted extra write root. Do not wrap the patch in JSON."
-			definition.Format = &zeroruntime.ToolDefinitionFormat{Type: "grammar", Syntax: "lark", Definition: applyPatchLarkGrammar}
-		}
-		wireTool := responsesTool{
-			Type:        string(definition.Type),
-			Name:        definition.Name,
-			Description: definition.Description,
-			Parameters:  definition.Parameters,
-			Format:      definition.Format,
-		}
-		if wireTool.Type == "" {
-			wireTool.Type = string(zeroruntime.ToolDefinitionFunction)
-		}
-		if wireTool.Type == string(zeroruntime.ToolDefinitionFreeform) {
-			wireTool.Parameters = nil
-		}
-		req.Tools = append(req.Tools, wireTool)
+		req.Tools = append(req.Tools, responsesTool{
+			Type:        "function",
+			Name:        tool.Name,
+			Description: tool.Description,
+			Parameters:  tool.Parameters,
+		})
 	}
 	// Codex / o-series reasoning models take the effort tier nested under
 	// `reasoning` on the Responses API (the chat-completions `reasoning_effort`
@@ -416,26 +312,13 @@ func (p *CodexProvider) assistantInputItems(msg zeroruntime.Message) ([]inputIte
 		if tc.Name == "" {
 			return nil, errors.New("codex provider: assistant tool call missing name")
 		}
-		callID := tc.ProviderCallID
-		if callID == "" {
-			callID = tc.ID
-		}
-		itemType := "function_call"
-		if tc.Freeform {
-			itemType = "custom_tool_call"
-		}
-		item := inputItem{
-			Type:   itemType,
-			ID:     tc.ID,
-			CallID: callID,
-			Name:   tc.Name,
-		}
-		if tc.Freeform {
-			item.Input = tc.Arguments
-		} else {
-			item.Arguments = tc.Arguments
-		}
-		items = append(items, item)
+		items = append(items, inputItem{
+			Type:      "function_call",
+			ID:        tc.ID,
+			CallID:    tc.ID,
+			Name:      tc.Name,
+			Arguments: tc.Arguments,
+		})
 	}
 	return items, nil
 }
@@ -596,18 +479,6 @@ func (p *CodexProvider) emitResponsesEvent(
 		state.done = true
 		return false
 	}
-	return p.emitParsedResponsesEvent(ctx, &event, state, events)
-}
-
-// emitParsedResponsesEvent converts one already-decoded Responses event into
-// zero or more runtime events. WebSocket sessions use this path to avoid
-// decoding each frame twice; the SSE path retains emitResponsesEvent above.
-func (p *CodexProvider) emitParsedResponsesEvent(
-	ctx context.Context,
-	event *responsesEvent,
-	state *responsesState,
-	events chan<- zeroruntime.StreamEvent,
-) bool {
 	if event.Type == "" {
 		// A payload that parses as JSON but carries no `type` field is a
 		// malformed Responses event — the type is the discriminator that
@@ -629,17 +500,12 @@ func (p *CodexProvider) emitParsedResponsesEvent(
 		// the runtime. response.incomplete is folded into a length finish at
 		// scan-end (state.done stays false so the wrapper emits the
 		// StreamEventDone with FinishReasonLength).
-		if event.Response != nil && event.Response.ID != "" {
-			state.responseID = event.Response.ID
-		}
 		return true
 	case responsesEventOutputItemAdded:
-		p.handleOutputItemAdded(ctx, event, state, events)
+		p.handleOutputItemAdded(ctx, &event, state, events)
 		return true
 	case responsesEventOutputTextDelta:
 		if event.Delta != "" {
-			state.emitted = true
-			state.text.WriteString(event.Delta)
 			providerio.SendEvent(ctx, events, zeroruntime.StreamEvent{
 				Type:    zeroruntime.StreamEventText,
 				Content: event.Delta,
@@ -651,7 +517,6 @@ func (p *CodexProvider) emitParsedResponsesEvent(
 		// phase shows progress (and keeps the activity clock fresh) instead of
 		// looking like a hang. Requested via reasoning.summary="auto".
 		if event.Delta != "" {
-			state.emitted = true
 			providerio.SendEvent(ctx, events, zeroruntime.StreamEvent{
 				Type:    zeroruntime.StreamEventReasoning,
 				Content: event.Delta,
@@ -659,16 +524,13 @@ func (p *CodexProvider) emitParsedResponsesEvent(
 		}
 		return true
 	case responsesEventFunctionArgsDelta:
-		p.handleToolInputDelta(ctx, event, state, events, false)
-		return true
-	case responsesEventCustomInputDelta:
-		p.handleToolInputDelta(ctx, event, state, events, true)
+		p.handleFunctionArgsDelta(ctx, &event, state, events)
 		return true
 	case responsesEventOutputItemDone:
-		p.handleOutputItemDone(ctx, event, state, events)
+		p.handleOutputItemDone(ctx, &event, state, events)
 		return true
 	case responsesEventCompleted, responsesEventFailed:
-		return p.handleTerminalResponse(ctx, event, state, events)
+		return p.handleTerminalResponse(ctx, &event, state, events)
 	case responsesEventError:
 		message := event.Message
 		if event.Code != "" {
@@ -708,38 +570,22 @@ func (p *CodexProvider) handleOutputItemAdded(
 		return
 	}
 	switch event.Item.Type {
-	case "function_call", "custom_tool_call":
+	case "function_call":
 		key := p.toolCallKey(event)
 		if key == "" {
 			return
 		}
-		builder, exists := state.toolCalls[key]
-		if !exists {
-			builder = &toolCallBuilder{ID: key, Freeform: event.Item.Type == "custom_tool_call"}
-			state.toolCalls[key] = builder
-			state.toolOrder = append(state.toolOrder, key)
-		}
-		if event.Item.CallID != "" {
-			builder.CallID = event.Item.CallID
-		}
-		if event.Item.Name != "" {
-			builder.Name = event.Item.Name
-		}
-		builder.Freeform = builder.Freeform || event.Item.Type == "custom_tool_call"
-		if builder.Freeform && event.Item.Input != "" && builder.Arguments.Len() == 0 {
-			builder.Arguments.WriteString(event.Item.Input)
-		}
-		state.emitted = true
-		if !builder.started {
-			providerio.SendEvent(ctx, events, zeroruntime.StreamEvent{
-				Type:               zeroruntime.StreamEventToolCallStart,
-				ToolCallID:         key,
-				ToolCallProviderID: builder.CallID,
-				ToolName:           builder.Name,
-				ToolCallFreeform:   builder.Freeform,
-			})
-			builder.started = true
+		builder := &toolCallBuilder{
+			ID:   key,
+			Name: event.Item.Name,
 		}
+		state.toolCalls[key] = builder
+		providerio.SendEvent(ctx, events, zeroruntime.StreamEvent{
+			Type:       zeroruntime.StreamEventToolCallStart,
+			ToolCallID: key,
+			ToolName:   event.Item.Name,
+		})
+		builder.started = true
 	}
 }
 
@@ -747,12 +593,11 @@ func (p *CodexProvider) handleOutputItemAdded(
 // to the in-flight builder and emits StreamEventToolCallDelta. The
 // Codex backend uses either `item_id` or `output_index` to attribute
 // the delta; we honor both.
-func (p *CodexProvider) handleToolInputDelta(
+func (p *CodexProvider) handleFunctionArgsDelta(
 	ctx context.Context,
 	event *responsesEvent,
 	state *responsesState,
 	events chan<- zeroruntime.StreamEvent,
-	freeform bool,
 ) {
 	key := p.toolCallKey(event)
 	if key == "" {
@@ -765,16 +610,10 @@ func (p *CodexProvider) handleToolInputDelta(
 		// an intermediate proxy). Treat the delta as the start of a new
 		// tool call with no known name yet — the eventual
 		// response.output_item.done carries the final name.
-		builder = &toolCallBuilder{ID: key, Freeform: freeform}
+		builder = &toolCallBuilder{ID: key}
 		state.toolCalls[key] = builder
-		state.toolOrder = append(state.toolOrder, key)
-	}
-	builder.Freeform = builder.Freeform || freeform
-	if event.CallID != "" && builder.CallID == "" {
-		builder.CallID = event.CallID
 	}
 	builder.Arguments.WriteString(event.Delta)
-	state.emitted = true
 	providerio.SendEvent(ctx, events, zeroruntime.StreamEvent{
 		Type:              zeroruntime.StreamEventToolCallDelta,
 		ToolCallID:        key,
@@ -793,7 +632,7 @@ func (p *CodexProvider) handleOutputItemDone(
 	state *responsesState,
 	events chan<- zeroruntime.StreamEvent,
 ) {
-	if event.Item == nil || (event.Item.Type != "function_call" && event.Item.Type != "custom_tool_call") {
+	if event.Item == nil || event.Item.Type != "function_call" {
 		return
 	}
 	key := p.toolCallKey(event)
@@ -802,31 +641,20 @@ func (p *CodexProvider) handleOutputItemDone(
 	}
 	builder, ok := state.toolCalls[key]
 	if !ok {
-		builder = &toolCallBuilder{ID: key, Freeform: event.Item.Type == "custom_tool_call"}
+		builder = &toolCallBuilder{ID: key}
 		state.toolCalls[key] = builder
-		state.toolOrder = append(state.toolOrder, key)
 	}
 	if event.Item.Name != "" {
 		builder.Name = event.Item.Name
 	}
-	if event.Item.CallID != "" {
-		builder.CallID = event.Item.CallID
-	}
-	builder.Freeform = builder.Freeform || event.Item.Type == "custom_tool_call"
-	finalInput := event.Item.Arguments
-	if builder.Freeform {
-		finalInput = event.Item.Input
-	}
-	if finalInput != "" && builder.Arguments.Len() == 0 {
-		builder.Arguments.WriteString(finalInput)
+	if event.Item.Arguments != "" && builder.Arguments.Len() == 0 {
+		builder.Arguments.WriteString(event.Item.Arguments)
 	}
 	if !builder.started {
 		providerio.SendEvent(ctx, events, zeroruntime.StreamEvent{
-			Type:               zeroruntime.StreamEventToolCallStart,
-			ToolCallID:         key,
-			ToolCallProviderID: builder.CallID,
-			ToolName:           builder.Name,
-			ToolCallFreeform:   builder.Freeform,
+			Type:       zeroruntime.StreamEventToolCallStart,
+			ToolCallID: key,
+			ToolName:   builder.Name,
 		})
 		builder.started = true
 	}
@@ -836,7 +664,6 @@ func (p *CodexProvider) handleOutputItemDone(
 		ToolName:   builder.Name,
 	})
 	builder.ended = true
-	state.emitted = true
 }
 
 // handleTerminalResponse emits the final usage + done event for a
@@ -866,7 +693,6 @@ func (p *CodexProvider) handleTerminalResponse(
 		return false
 	}
 	state.usage = event.Response.Usage
-	state.responseID = event.Response.ID
 	if event.Response.Usage != nil {
 		usage := zeroruntime.Usage{
 			InputTokens:  event.Response.Usage.InputTokens,
@@ -874,7 +700,6 @@ func (p *CodexProvider) handleTerminalResponse(
 		}
 		if event.Response.Usage.InputTokensDetails != nil {
 			usage.CachedInputTokens = event.Response.Usage.InputTokensDetails.CachedTokens
-			usage.CacheWriteTokens = event.Response.Usage.InputTokensDetails.CacheWriteTokens
 		}
 		if event.Response.Usage.OutputTokensDetails != nil {
 			usage.ReasoningTokens = event.Response.Usage.OutputTokensDetails.ReasoningTokens
@@ -910,7 +735,7 @@ func (p *CodexProvider) handleTerminalResponse(
 		state.done = true
 		return false
 	}
-	providerio.SendEvent(ctx, events, zeroruntime.StreamEvent{Type: zeroruntime.StreamEventDone, ResponseID: event.Response.ID})
+	providerio.SendEvent(ctx, events, zeroruntime.StreamEvent{Type: zeroruntime.StreamEventDone})
 	state.done = true
 	return false
 }
@@ -929,9 +754,6 @@ func (p *CodexProvider) toolCallKey(event *responsesEvent) string {
 	if event.Item != nil && event.Item.CallID != "" {
 		return event.Item.CallID
 	}
-	if event.CallID != "" {
-		return event.CallID
-	}
 	if event.OutputIndex != nil {
 		// output_index is present (a *int distinguishes a real 0 — the first output
 		// in the response — from "absent"), so key on it even when 0 instead of

internal/providers/openai/codex_session.go

@@ -1,421 +0,0 @@
-package openai
-
-import (
-	"context"
-	"encoding/json"
-	"errors"
-	"fmt"
-	"net/http"
-	"net/url"
-	"reflect"
-	"strings"
-	"sync"
-	"time"
-
-	"github.com/coder/websocket"
-
-	"github.com/Gitlawb/zero/internal/providers/providerio"
-	"github.com/Gitlawb/zero/internal/trace"
-	"github.com/Gitlawb/zero/internal/zeroruntime"
-)
-
-const (
-	responsesWebSocketBetaHeader = "OpenAI-Beta"
-	responsesWebSocketBetaValue  = "responses_websockets=2026-02-06"
-	responsesWebSocketRequest    = "response.create"
-	previousResponseNotFoundCode = "previous_response_not_found"
-	webSocketConnectionLimitCode = "websocket_connection_limit_reached"
-	responsesWebSocketReadLimit  = 16 << 20
-)
-
-var errCodexTurnSessionBusy = errors.New("codex turn session already has an active stream")
-
-// NewCodexTurnSessionProvider enables one Responses WebSocket connection for
-// each agent run. The session falls back to the existing HTTP/SSE provider when
-// the endpoint cannot upgrade or loses its response chain.
-func NewCodexTurnSessionProvider(provider *CodexProvider, caps zeroruntime.ProviderCapabilities) zeroruntime.TurnSessionProvider {
-	return &codexTurnSessionProvider{provider: provider, caps: caps}
-}
-
-type codexTurnSessionProvider struct {
-	provider *CodexProvider
-	caps     zeroruntime.ProviderCapabilities
-}
-
-func (provider *codexTurnSessionProvider) OpenTurnSession(ctx context.Context) (zeroruntime.TurnSession, error) {
-	if provider == nil || provider.provider == nil || provider.provider.inner == nil {
-		return nil, errors.New("codex turn session requires a provider")
-	}
-	sessionCtx, cancel := context.WithCancel(ctx)
-	return &codexTurnSession{
-		ctx:         sessionCtx,
-		cancel:      cancel,
-		provider:    provider.provider,
-		prewarmDone: make(chan struct{}),
-	}, nil
-}
-
-func (provider *codexTurnSessionProvider) Capabilities() zeroruntime.ProviderCapabilities {
-	return provider.caps
-}
-
-type codexTurnSession struct {
-	ctx      context.Context
-	cancel   context.CancelFunc
-	provider *CodexProvider
-
-	mu             sync.Mutex
-	connection     *websocket.Conn
-	webSocketOff   bool
-	lastRequest    *responsesRequest
-	lastResponseID string
-	lastOutput     []inputItem
-	streamActive   bool
-
-	prewarmOnce sync.Once
-	prewarmDone chan struct{}
-	closeOnce   sync.Once
-}
-
-// Prewarm starts the WebSocket handshake without blocking prompt assembly. The
-// first Stream waits for this bounded attempt; failure simply selects HTTP/SSE.
-func (session *codexTurnSession) Prewarm(ctx context.Context) error {
-	session.prewarmOnce.Do(func() {
-		go func() {
-			defer close(session.prewarmDone)
-			prewarmCtx, cancel := context.WithTimeout(session.ctx, prewarmTimeout)
-			defer cancel()
-			recorder := trace.FromContext(ctx)
-			span := recorder.Span(trace.SpanProviderPrewarm)
-			defer span.End()
-			recorder.Counter(trace.CounterPrewarmAttempts, 1)
-			connection, err := session.provider.dialResponsesWebSocket(prewarmCtx)
-			session.mu.Lock()
-			defer session.mu.Unlock()
-			if err != nil {
-				session.webSocketOff = true
-				return
-			}
-			session.connection = connection
-		}()
-	})
-	return nil
-}
-
-func (session *codexTurnSession) Stream(ctx context.Context, request zeroruntime.CompletionRequest) (<-chan zeroruntime.StreamEvent, error) {
-	_ = session.Prewarm(ctx)
-	select {
-	case <-session.prewarmDone:
-	case <-ctx.Done():
-		return nil, ctx.Err()
-	}
-
-	fullRequest, err := session.provider.buildResponsesRequest(request)
-	if err != nil {
-		return nil, err
-	}
-
-	session.mu.Lock()
-	if session.streamActive {
-		session.mu.Unlock()
-		return nil, errCodexTurnSessionBusy
-	}
-	if session.webSocketOff || session.connection == nil {
-		session.mu.Unlock()
-		trace.FromContext(ctx).Counter(trace.CounterResponsesHTTPFallback, 1)
-		return session.provider.StreamCompletion(ctx, request)
-	}
-	session.streamActive = true
-	connection := session.connection
-	wireRequest := *fullRequest
-	wireRequest.Type = responsesWebSocketRequest
-	if delta, ok := responseInputDelta(session.lastRequest, session.lastOutput, fullRequest); ok && session.lastResponseID != "" {
-		wireRequest.PreviousResponseID = session.lastResponseID
-		wireRequest.Input = delta
-		trace.FromContext(ctx).Counter(trace.CounterResponseChainReused, 1)
-	} else if session.lastRequest != nil {
-		trace.FromContext(ctx).Counter(trace.CounterResponseChainReset, 1)
-		session.lastRequest = nil
-		session.lastResponseID = ""
-		session.lastOutput = nil
-	}
-	session.mu.Unlock()
-
-	body, err := json.Marshal(wireRequest)
-	if err != nil {
-		session.releaseStream()
-		return nil, fmt.Errorf("encode codex websocket request: %w", err)
-	}
-	events := make(chan zeroruntime.StreamEvent, 16)
-	go func() {
-		defer close(events)
-		defer session.releaseStream()
-		session.streamWebSocket(ctx, connection, body, fullRequest, request, events)
-	}()
-	return events, nil
-}
-
-func (session *codexTurnSession) releaseStream() {
-	session.mu.Lock()
-	session.streamActive = false
-	session.mu.Unlock()
-}
-
-func (session *codexTurnSession) Compact(context.Context, zeroruntime.CompletionRequest) ([]zeroruntime.Message, error) {
-	return nil, zeroruntime.ErrCompactionUnsupported
-}
-
-func (session *codexTurnSession) Close() error {
-	session.closeOnce.Do(func() {
-		session.cancel()
-		session.prewarmOnce.Do(func() { close(session.prewarmDone) })
-		select {
-		case <-session.prewarmDone:
-		case <-time.After(prewarmTimeout):
-		}
-		session.mu.Lock()
-		connection := session.connection
-		session.connection = nil
-		session.webSocketOff = true
-		session.mu.Unlock()
-		if connection != nil {
-			_ = connection.CloseNow()
-		}
-	})
-	return nil
-}
-
-func responseInputDelta(previous *responsesRequest, output []inputItem, current *responsesRequest) ([]inputItem, bool) {
-	if previous == nil || current == nil || !responsesRequestPropertiesEqual(previous, current) {
-		return nil, false
-	}
-	prefix := make([]inputItem, 0, len(previous.Input)+len(output))
-	prefix = append(prefix, previous.Input...)
-	prefix = append(prefix, output...)
-	if len(current.Input) <= len(prefix) || !reflect.DeepEqual(current.Input[:len(prefix)], prefix) {
-		return nil, false
-	}
-	return append([]inputItem(nil), current.Input[len(prefix):]...), true
-}
-
-func responsesRequestPropertiesEqual(left, right *responsesRequest) bool {
-	return left.Model == right.Model &&
-		left.Instructions == right.Instructions &&
-		left.Stream == right.Stream &&
-		left.Store == right.Store &&
-		left.ParallelToolCalls == right.ParallelToolCalls &&
-		left.MaxOutputTokens == right.MaxOutputTokens &&
-		reflect.DeepEqual(left.Tools, right.Tools) &&
-		reflect.DeepEqual(left.Reasoning, right.Reasoning) &&
-		left.ServiceTier == right.ServiceTier &&
-		left.PromptCacheKey == right.PromptCacheKey
-}
-
-func (session *codexTurnSession) streamWebSocket(
-	ctx context.Context,
-	connection *websocket.Conn,
-	body []byte,
-	fullRequest *responsesRequest,
-	runtimeRequest zeroruntime.CompletionRequest,
-	events chan<- zeroruntime.StreamEvent,
-) {
-	if err := connection.Write(ctx, websocket.MessageText, body); err != nil {
-		session.disableWebSocket(connection)
-		session.forwardHTTP(ctx, runtimeRequest, events)
-		return
-	}
-
-	state := newResponsesState()
-	for {
-		readCtx := ctx
-		cancel := func() {}
-		idleTimeout := session.provider.inner.streamIdleTimeout
-		if idleTimeout > 0 {
-			readCtx, cancel = context.WithTimeout(ctx, idleTimeout)
-		}
-		messageType, data, err := connection.Read(readCtx)
-		readTimedOut := errors.Is(readCtx.Err(), context.DeadlineExceeded) && ctx.Err() == nil
-		cancel()
-		if err != nil {
-			session.disableWebSocket(connection)
-			if ctx.Err() != nil {
-				return
-			}
-			if !state.emitted {
-				session.forwardHTTP(ctx, runtimeRequest, events)
-				return
-			}
-			errorMessage := err.Error()
-			if readTimedOut {
-				errorMessage = providerio.StreamTimeoutMessage(providerio.ErrStreamIdle, idleTimeout)
-			}
-			providerio.SendEvent(ctx, events, zeroruntime.StreamEvent{
-				Type:  zeroruntime.StreamEventError,
-				Error: session.provider.redact("provider stream error: " + errorMessage),
-			})
-			return
-		}
-		if messageType != websocket.MessageText {
-			continue
-		}
-
-		var responseEvent responsesEvent
-		decodeErr := json.Unmarshal(data, &responseEvent)
-		if decodeErr == nil {
-			if (responseEvent.Code == previousResponseNotFoundCode || responseEvent.Code == webSocketConnectionLimitCode) &&
-				!state.emitted {
-				session.disableWebSocket(connection)
-				session.forwardHTTP(ctx, runtimeRequest, events)
-				return
-			}
-			if responseEvent.Type == responsesEventIncomplete {
-				session.resetResponseChain(connection)
-				providerio.SendEvent(ctx, events, zeroruntime.StreamEvent{
-					Type:         zeroruntime.StreamEventDone,
-					FinishReason: zeroruntime.FinishReasonLength,
-				})
-				return
-			}
-		}
-
-		keepReading := false
-		if decodeErr == nil {
-			keepReading = session.provider.emitParsedResponsesEvent(ctx, &responseEvent, state, events)
-		} else {
-			keepReading = session.provider.emitResponsesEvent(ctx, string(data), state, events)
-		}
-		if keepReading {
-			continue
-		}
-		if responseEvent.Type == responsesEventCompleted && responseEvent.Response != nil &&
-			responseEvent.Response.Error == nil && responseEvent.Response.Status != "failed" && state.responseID != "" {
-			session.mu.Lock()
-			if session.connection == connection && !session.webSocketOff {
-				requestCopy := *fullRequest
-				requestCopy.Input = append([]inputItem(nil), fullRequest.Input...)
-				session.lastRequest = &requestCopy
-				session.lastResponseID = state.responseID
-				session.lastOutput = state.outputInputItems()
-			}
-			session.mu.Unlock()
-		}
-		return
-	}
-}
-
-func (session *codexTurnSession) resetResponseChain(connection *websocket.Conn) {
-	session.mu.Lock()
-	defer session.mu.Unlock()
-	if session.connection != connection {
-		return
-	}
-	session.lastRequest = nil
-	session.lastResponseID = ""
-	session.lastOutput = nil
-}
-
-func (session *codexTurnSession) forwardHTTP(ctx context.Context, request zeroruntime.CompletionRequest, events chan<- zeroruntime.StreamEvent) {
-	trace.FromContext(ctx).Counter(trace.CounterResponsesHTTPFallback, 1)
-	stream, err := session.provider.StreamCompletion(ctx, request)
-	if err != nil {
-		providerio.SendEvent(ctx, events, zeroruntime.StreamEvent{
-			Type:  zeroruntime.StreamEventError,
-			Error: session.provider.redact(err.Error()),
-		})
-		return
-	}
-	for event := range stream {
-		providerio.SendEvent(ctx, events, event)
-	}
-}
-
-func (session *codexTurnSession) disableWebSocket(connection *websocket.Conn) {
-	session.mu.Lock()
-	if session.connection == connection {
-		session.connection = nil
-		session.webSocketOff = true
-		session.lastRequest = nil
-		session.lastResponseID = ""
-		session.lastOutput = nil
-	}
-	session.mu.Unlock()
-	_ = connection.CloseNow()
-}
-
-func (provider *CodexProvider) dialResponsesWebSocket(ctx context.Context) (*websocket.Conn, error) {
-	endpoint, err := responsesWebSocketURL(provider.inner.endpoint)
-	if err != nil {
-		return nil, err
-	}
-	for authTry := 0; authTry < 2; authTry++ {
-		headers, err := provider.responsesWebSocketHeaders(ctx, authTry == 1)
-		if err != nil {
-			return nil, err
-		}
-		connection, response, err := websocket.Dial(ctx, endpoint, &websocket.DialOptions{
-			HTTPClient:      provider.inner.httpClient,
-			HTTPHeader:      headers,
-			CompressionMode: websocket.CompressionNoContextTakeover,
-		})
-		if err == nil {
-			connection.SetReadLimit(responsesWebSocketReadLimit)
-			return connection, nil
-		}
-		if response == nil || response.StatusCode != http.StatusUnauthorized || provider.inner.oauthResolver == nil || authTry == 1 {
-			return nil, err
-		}
-	}
-	return nil, errors.New("codex websocket authentication failed")
-}
-
-func (provider *CodexProvider) responsesWebSocketHeaders(ctx context.Context, forceRefresh bool) (http.Header, error) {
-	request, err := http.NewRequestWithContext(ctx, http.MethodGet, provider.inner.endpoint, nil)
-	if err != nil {
-		return nil, err
-	}
-	base := providerio.AuthHeaders{
-		APIKey:            provider.inner.apiKey,
-		DefaultAuthHeader: "Authorization",
-		DefaultAuthScheme: "Bearer",
-		AuthHeader:        provider.inner.authHeader,
-		AuthScheme:        provider.inner.authScheme,
-		AuthHeaderValue:   provider.inner.authHeaderValue,
-		CustomHeaders:     provider.inner.customHeaders,
-	}
-	if resolver := provider.inner.oauthResolver; resolver != nil {
-		header, value, ok, err := resolver(ctx, forceRefresh)
-		if err != nil {
-			return nil, err
-		}
-		if ok {
-			providerio.ApplyAuthHeaders(request, providerio.AuthHeaders{CustomHeaders: provider.inner.customHeaders})
-			if strings.TrimSpace(header) == "" {
-				header = "Authorization"
-			}
-			request.Header.Set(header, value)
-		} else {
-			providerio.ApplyAuthHeaders(request, base)
-		}
-	} else {
-		providerio.ApplyAuthHeaders(request, base)
-	}
-	provider.injectCodexHeaders(request)
-	request.Header.Set(responsesWebSocketBetaHeader, responsesWebSocketBetaValue)
-	return request.Header.Clone(), nil
-}
-
-func responsesWebSocketURL(endpoint string) (string, error) {
-	parsed, err := url.Parse(strings.TrimSpace(endpoint))
-	if err != nil {
-		return "", err
-	}
-	switch parsed.Scheme {
-	case "http":
-		parsed.Scheme = "ws"
-	case "https":
-		parsed.Scheme = "wss"
-	default:
-		return "", fmt.Errorf("unsupported Responses websocket URL scheme %q", parsed.Scheme)
-	}
-	return parsed.String(), nil
-}

internal/providers/openai/codex_session_test.go

@@ -1,590 +0,0 @@
-package openai
-
-import (
-	"context"
-	"encoding/json"
-	"errors"
-	"fmt"
-	"net/http"
-	"net/http/httptest"
-	"strings"
-	"sync"
-	"testing"
-	"time"
-
-	"github.com/coder/websocket"
-
-	"github.com/Gitlawb/zero/internal/trace"
-	"github.com/Gitlawb/zero/internal/zeroruntime"
-)
-
-func TestCodexTurnSessionChainsOnlyAppendOnlyRequests(t *testing.T) {
-	var mu sync.Mutex
-	requests := []map[string]any{}
-	betaHeader := ""
-	server := httptest.NewServer(http.HandlerFunc(func(writer http.ResponseWriter, request *http.Request) {
-		if !strings.EqualFold(request.Header.Get("Upgrade"), "websocket") {
-			http.Error(writer, "websocket required", http.StatusUpgradeRequired)
-			return
-		}
-		mu.Lock()
-		betaHeader = request.Header.Get(responsesWebSocketBetaHeader)
-		mu.Unlock()
-		connection, err := websocket.Accept(writer, request, nil)
-		if err != nil {
-			return
-		}
-		defer connection.CloseNow()
-		for index := 0; index < 3; index++ {
-			_, body, err := connection.Read(request.Context())
-			if err != nil {
-				return
-			}
-			var payload map[string]any
-			if err := json.Unmarshal(body, &payload); err != nil {
-				return
-			}
-			mu.Lock()
-			requests = append(requests, payload)
-			mu.Unlock()
-			switch index {
-			case 0:
-				writeWebSocketEvents(request.Context(), connection,
-					`{"type":"response.created","response":{"id":"resp-1","status":"in_progress"}}`,
-					`{"type":"response.output_item.added","item_id":"call-1","item":{"type":"function_call","id":"call-1","call_id":"call-1","name":"read_file"}}`,
-					`{"type":"response.function_call_arguments.delta","item_id":"call-1","delta":"{}"}`,
-					`{"type":"response.output_item.done","item_id":"call-1","item":{"type":"function_call","id":"call-1","call_id":"call-1","name":"read_file","arguments":"{}"}}`,
-					`{"type":"response.completed","response":{"id":"resp-1","status":"completed"}}`,
-				)
-			case 1:
-				writeWebSocketEvents(request.Context(), connection,
-					`{"type":"response.output_text.delta","delta":"done"}`,
-					`{"type":"response.completed","response":{"id":"resp-2","status":"completed"}}`,
-				)
-			case 2:
-				writeWebSocketEvents(request.Context(), connection,
-					`{"type":"response.completed","response":{"id":"resp-3","status":"completed"}}`,
-				)
-			}
-		}
-	}))
-	defer server.Close()
-
-	provider := newCodexSessionTestProvider(t, server)
-	// A disabled stream watchdog must use the parent context rather than creating
-	// an immediately-expired read deadline.
-	provider.inner.streamIdleTimeout = 0
-	session := openCodexSession(t, provider)
-	defer session.Close()
-	recorder := trace.NewRecorder("session-1", "run-1", "test")
-	recorder.Start()
-	streamContext := trace.WithContext(t.Context(), recorder)
-
-	base := zeroruntime.CompletionRequest{
-		Messages: []zeroruntime.Message{
-			{Role: zeroruntime.MessageRoleSystem, Content: "Use tools carefully."},
-			{Role: zeroruntime.MessageRoleUser, Content: "Read the file."},
-		},
-		Tools:          []zeroruntime.ToolDefinition{{Name: "read_file", Parameters: map[string]any{"type": "object"}}},
-		PromptCacheKey: "session-1",
-	}
-	first := collectCodexSessionEvents(t, session, base)
-	if !hasToolCallEnd(first, "call-1") {
-		t.Fatalf("first stream did not produce the tool call: %#v", first)
-	}
-
-	second := base
-	second.Messages = append(append([]zeroruntime.Message(nil), base.Messages...),
-		zeroruntime.Message{Role: zeroruntime.MessageRoleAssistant, ToolCalls: []zeroruntime.ToolCall{{ID: "call-1", Name: "read_file", Arguments: "{}"}}},
-		zeroruntime.Message{Role: zeroruntime.MessageRoleTool, ToolCallID: "call-1", Content: "contents"},
-	)
-	secondEvents := collectCodexSessionEventsContext(t, streamContext, session, second)
-	if got := joinedText(secondEvents); got != "done" {
-		t.Fatalf("second stream text = %q, want done", got)
-	}
-
-	third := second
-	third.ReasoningEffort = "high"
-	third.Messages = append(append([]zeroruntime.Message(nil), second.Messages...),
-		zeroruntime.Message{Role: zeroruntime.MessageRoleAssistant, Content: "done"},
-		zeroruntime.Message{Role: zeroruntime.MessageRoleUser, Content: "Continue."},
-	)
-	collectCodexSessionEventsContext(t, streamContext, session, third)
-	finishedTrace := recorder.Finish()
-	if got := finishedTrace.Counter(trace.CounterResponseChainReused); got != 1 {
-		t.Fatalf("response-chain reuse count = %d, want 1", got)
-	}
-	if got := finishedTrace.Counter(trace.CounterResponseChainReset); got != 1 {
-		t.Fatalf("response-chain reset count = %d, want 1", got)
-	}
-
-	mu.Lock()
-	defer mu.Unlock()
-	if len(requests) != 3 {
-		t.Fatalf("websocket requests = %d, want 3", len(requests))
-	}
-	if betaHeader != responsesWebSocketBetaValue {
-		t.Fatalf("OpenAI-Beta = %q, want %q", betaHeader, responsesWebSocketBetaValue)
-	}
-	if requests[0]["type"] != responsesWebSocketRequest || requests[0]["previous_response_id"] != nil {
-		t.Fatalf("first request chaining fields = %#v", requests[0])
-	}
-	if requests[0]["parallel_tool_calls"] != true || requests[0]["prompt_cache_key"] != "session-1" {
-		t.Fatalf("first request stable fields = %#v", requests[0])
-	}
-	if requests[1]["previous_response_id"] != "resp-1" {
-		t.Fatalf("second previous_response_id = %#v", requests[1]["previous_response_id"])
-	}
-	secondInput, _ := requests[1]["input"].([]any)
-	if len(secondInput) != 1 || secondInput[0].(map[string]any)["type"] != "function_call_output" {
-		t.Fatalf("second incremental input = %#v", requests[1]["input"])
-	}
-	if requests[2]["previous_response_id"] != nil {
-		t.Fatalf("incompatible request reused response chain: %#v", requests[2])
-	}
-	thirdInput, _ := requests[2]["input"].([]any)
-	if len(thirdInput) <= 1 {
-		t.Fatalf("incompatible request did not send full input: %#v", thirdInput)
-	}
-}
-
-func TestCodexTurnSessionFallsBackWhenPreviousResponseIsMissing(t *testing.T) {
-	var mu sync.Mutex
-	webSocketRequests := 0
-	httpRequests := 0
-	server := httptest.NewServer(http.HandlerFunc(func(writer http.ResponseWriter, request *http.Request) {
-		if strings.EqualFold(request.Header.Get("Upgrade"), "websocket") {
-			connection, err := websocket.Accept(writer, request, nil)
-			if err != nil {
-				return
-			}
-			defer connection.CloseNow()
-			for index := 0; index < 2; index++ {
-				if _, _, err := connection.Read(request.Context()); err != nil {
-					return
-				}
-				mu.Lock()
-				webSocketRequests++
-				mu.Unlock()
-				if index == 0 {
-					writeWebSocketEvents(request.Context(), connection,
-						`{"type":"response.output_item.added","item_id":"call-1","item":{"type":"function_call","id":"call-1","call_id":"call-1","name":"read_file"}}`,
-						`{"type":"response.output_item.done","item_id":"call-1","item":{"type":"function_call","id":"call-1","call_id":"call-1","name":"read_file","arguments":"{}"}}`,
-						`{"type":"response.completed","response":{"id":"resp-1","status":"completed"}}`,
-					)
-					continue
-				}
-				writeWebSocketEvents(request.Context(), connection,
-					`{"type":"response.error","code":"previous_response_not_found","message":"missing"}`,
-				)
-			}
-			return
-		}
-
-		mu.Lock()
-		httpRequests++
-		mu.Unlock()
-		writer.Header().Set("Content-Type", "text/event-stream")
-		_, _ = fmt.Fprint(writer, "data: {\"type\":\"response.output_text.delta\",\"delta\":\"fallback\"}\n\n")
-		_, _ = fmt.Fprint(writer, "data: {\"type\":\"response.completed\",\"response\":{\"id\":\"resp-http\",\"status\":\"completed\"}}\n\n")
-	}))
-	defer server.Close()
-
-	provider := newCodexSessionTestProvider(t, server)
-	session := openCodexSession(t, provider)
-	defer session.Close()
-	base := zeroruntime.CompletionRequest{
-		Messages: []zeroruntime.Message{{Role: zeroruntime.MessageRoleUser, Content: "Read it."}},
-		Tools:    []zeroruntime.ToolDefinition{{Name: "read_file", Parameters: map[string]any{"type": "object"}}},
-	}
-	collectCodexSessionEvents(t, session, base)
-	second := base
-	second.Messages = append(append([]zeroruntime.Message(nil), base.Messages...),
-		zeroruntime.Message{Role: zeroruntime.MessageRoleAssistant, ToolCalls: []zeroruntime.ToolCall{{ID: "call-1", Name: "read_file", Arguments: "{}"}}},
-		zeroruntime.Message{Role: zeroruntime.MessageRoleTool, ToolCallID: "call-1", Content: "contents"},
-	)
-	events := collectCodexSessionEvents(t, session, second)
-	if got := joinedText(events); got != "fallback" {
-		t.Fatalf("fallback stream text = %q, want fallback; events=%#v", got, events)
-	}
-	for _, event := range events {
-		if event.Type == zeroruntime.StreamEventError {
-			t.Fatalf("response-chain recovery leaked an error: %#v", event)
-		}
-	}
-	mu.Lock()
-	defer mu.Unlock()
-	if webSocketRequests != 2 || httpRequests != 1 {
-		t.Fatalf("requests = websocket:%d http:%d, want 2/1", webSocketRequests, httpRequests)
-	}
-}
-
-func TestCodexTurnSessionFallsBackWhenSocketClosesBeforeOutput(t *testing.T) {
-	var mu sync.Mutex
-	httpRequests := 0
-	server := httptest.NewServer(http.HandlerFunc(func(writer http.ResponseWriter, request *http.Request) {
-		if strings.EqualFold(request.Header.Get("Upgrade"), "websocket") {
-			connection, err := websocket.Accept(writer, request, nil)
-			if err != nil {
-				return
-			}
-			if _, _, err := connection.Read(request.Context()); err == nil {
-				_ = connection.CloseNow()
-			}
-			return
-		}
-		mu.Lock()
-		httpRequests++
-		mu.Unlock()
-		writer.Header().Set("Content-Type", "text/event-stream")
-		_, _ = fmt.Fprint(writer, "data: {\"type\":\"response.output_text.delta\",\"delta\":\"recovered\"}\n\n")
-		_, _ = fmt.Fprint(writer, "data: {\"type\":\"response.completed\",\"response\":{\"id\":\"resp-http\",\"status\":\"completed\"}}\n\n")
-	}))
-	defer server.Close()
-
-	provider := newCodexSessionTestProvider(t, server)
-	session := openCodexSession(t, provider)
-	defer session.Close()
-	recorder := trace.NewRecorder("session-fallback", "run-fallback", "test")
-	recorder.Start()
-	events := collectCodexSessionEventsContext(t, trace.WithContext(t.Context(), recorder), session, zeroruntime.CompletionRequest{
-		Messages: []zeroruntime.Message{{Role: zeroruntime.MessageRoleUser, Content: "Hello"}},
-	})
-	if got := joinedText(events); got != "recovered" {
-		t.Fatalf("fallback text = %q, want recovered", got)
-	}
-	mu.Lock()
-	defer mu.Unlock()
-	if httpRequests != 1 {
-		t.Fatalf("HTTP fallback requests = %d, want 1", httpRequests)
-	}
-	if got := recorder.Finish().Counter(trace.CounterResponsesHTTPFallback); got != 1 {
-		t.Fatalf("responses HTTP fallback counter = %d, want 1", got)
-	}
-}
-
-func TestCodexTurnSessionKeepsWebSocketAfterIncompleteResponse(t *testing.T) {
-	var mu sync.Mutex
-	webSocketRequests := 0
-	httpRequests := 0
-	server := httptest.NewServer(http.HandlerFunc(func(writer http.ResponseWriter, request *http.Request) {
-		if strings.EqualFold(request.Header.Get("Upgrade"), "websocket") {
-			connection, err := websocket.Accept(writer, request, nil)
-			if err != nil {
-				return
-			}
-			defer connection.CloseNow()
-			for index := 0; index < 2; index++ {
-				if _, _, err := connection.Read(request.Context()); err != nil {
-					return
-				}
-				mu.Lock()
-				webSocketRequests++
-				mu.Unlock()
-				if index == 0 {
-					writeWebSocketEvents(request.Context(), connection,
-						`{"type":"response.incomplete","response":{"id":"resp-1","status":"incomplete"}}`,
-					)
-					continue
-				}
-				writeWebSocketEvents(request.Context(), connection,
-					`{"type":"response.output_text.delta","delta":"websocket"}`,
-					`{"type":"response.completed","response":{"id":"resp-2","status":"completed"}}`,
-				)
-			}
-			return
-		}
-
-		mu.Lock()
-		httpRequests++
-		mu.Unlock()
-		writer.Header().Set("Content-Type", "text/event-stream")
-		_, _ = fmt.Fprint(writer, "data: {\"type\":\"response.output_text.delta\",\"delta\":\"fallback\"}\n\n")
-		_, _ = fmt.Fprint(writer, "data: {\"type\":\"response.completed\",\"response\":{\"id\":\"resp-http\",\"status\":\"completed\"}}\n\n")
-	}))
-	defer server.Close()
-
-	provider := newCodexSessionTestProvider(t, server)
-	session := openCodexSession(t, provider)
-	defer session.Close()
-	request := zeroruntime.CompletionRequest{
-		Messages: []zeroruntime.Message{{Role: zeroruntime.MessageRoleUser, Content: "Continue."}},
-	}
-	first := collectCodexSessionEvents(t, session, request)
-	if len(first) != 1 || first[0].Type != zeroruntime.StreamEventDone || first[0].FinishReason != zeroruntime.FinishReasonLength {
-		t.Fatalf("incomplete response events = %#v, want length completion", first)
-	}
-	second := collectCodexSessionEvents(t, session, request)
-	if got := joinedText(second); got != "websocket" {
-		t.Fatalf("second turn text = %q, want websocket; events=%#v", got, second)
-	}
-	mu.Lock()
-	defer mu.Unlock()
-	if webSocketRequests != 2 || httpRequests != 0 {
-		t.Fatalf("requests = websocket:%d http:%d, want 2/0", webSocketRequests, httpRequests)
-	}
-}
-
-func TestCodexTurnSessionDoesNotReplayAfterVisibleOutput(t *testing.T) {
-	var mu sync.Mutex
-	httpRequests := 0
-	server := httptest.NewServer(http.HandlerFunc(func(writer http.ResponseWriter, request *http.Request) {
-		if strings.EqualFold(request.Header.Get("Upgrade"), "websocket") {
-			connection, err := websocket.Accept(writer, request, nil)
-			if err != nil {
-				return
-			}
-			if _, _, err := connection.Read(request.Context()); err == nil {
-				writeWebSocketEvents(request.Context(), connection,
-					`{"type":"response.output_text.delta","delta":"visible"}`,
-				)
-			}
-			_ = connection.Close(websocket.StatusInternalError, "interrupted")
-			return
-		}
-		mu.Lock()
-		httpRequests++
-		mu.Unlock()
-	}))
-	defer server.Close()
-
-	provider := newCodexSessionTestProvider(t, server)
-	session := openCodexSession(t, provider)
-	defer session.Close()
-	stream, err := session.Stream(t.Context(), zeroruntime.CompletionRequest{
-		Messages: []zeroruntime.Message{{Role: zeroruntime.MessageRoleUser, Content: "Hello"}},
-	})
-	if err != nil {
-		t.Fatalf("Stream: %v", err)
-	}
-	sawText, sawError := false, false
-	for event := range stream {
-		sawText = sawText || event.Type == zeroruntime.StreamEventText
-		sawError = sawError || event.Type == zeroruntime.StreamEventError
-	}
-	if !sawText || !sawError {
-		t.Fatalf("visible interrupted stream = text:%v error:%v", sawText, sawError)
-	}
-	mu.Lock()
-	defer mu.Unlock()
-	if httpRequests != 0 {
-		t.Fatalf("visible interrupted stream was replayed over HTTP %d time(s)", httpRequests)
-	}
-}
-
-func TestCodexTurnSessionReportsWebSocketIdleTimeout(t *testing.T) {
-	server := httptest.NewServer(http.HandlerFunc(func(writer http.ResponseWriter, request *http.Request) {
-		connection, err := websocket.Accept(writer, request, nil)
-		if err != nil {
-			return
-		}
-		defer connection.CloseNow()
-		if _, _, err := connection.Read(request.Context()); err != nil {
-			return
-		}
-		writeWebSocketEvents(request.Context(), connection,
-			`{"type":"response.output_text.delta","delta":"visible"}`,
-		)
-		<-request.Context().Done()
-	}))
-	defer server.Close()
-
-	provider := newCodexSessionTestProvider(t, server)
-	provider.inner.streamIdleTimeout = 200 * time.Millisecond
-	session := openCodexSession(t, provider)
-	defer session.Close()
-	stream, err := session.Stream(t.Context(), zeroruntime.CompletionRequest{
-		Messages: []zeroruntime.Message{{Role: zeroruntime.MessageRoleUser, Content: "Hello"}},
-	})
-	if err != nil {
-		t.Fatalf("Stream: %v", err)
-	}
-
-	var streamError string
-	for event := range stream {
-		if event.Type == zeroruntime.StreamEventError {
-			streamError = event.Error
-			break
-		}
-	}
-	if !strings.Contains(streamError, "idle timeout after 200ms") {
-		t.Fatalf("stream error = %q, want idle-timeout detail", streamError)
-	}
-}
-
-func TestCodexTurnSessionRejectsOverlappingStreams(t *testing.T) {
-	started := make(chan struct{})
-	release := make(chan struct{})
-	var releaseOnce sync.Once
-	releaseStream := func() { releaseOnce.Do(func() { close(release) }) }
-	t.Cleanup(releaseStream)
-	server := httptest.NewServer(http.HandlerFunc(func(writer http.ResponseWriter, request *http.Request) {
-		connection, err := websocket.Accept(writer, request, nil)
-		if err != nil {
-			return
-		}
-		defer connection.CloseNow()
-		if _, _, err := connection.Read(request.Context()); err != nil {
-			return
-		}
-		close(started)
-		<-release
-		writeWebSocketEvents(request.Context(), connection,
-			`{"type":"response.completed","response":{"id":"resp-1","status":"completed"}}`,
-		)
-	}))
-	defer server.Close()
-
-	provider := newCodexSessionTestProvider(t, server)
-	session := openCodexSession(t, provider)
-	defer session.Close()
-	request := zeroruntime.CompletionRequest{
-		Messages: []zeroruntime.Message{{Role: zeroruntime.MessageRoleUser, Content: "Hello"}},
-	}
-	first, err := session.Stream(t.Context(), request)
-	if err != nil {
-		t.Fatalf("first Stream: %v", err)
-	}
-	select {
-	case <-started:
-	case <-time.After(time.Second):
-		t.Fatal("first WebSocket stream did not start")
-	}
-	if _, err := session.Stream(t.Context(), request); !errors.Is(err, errCodexTurnSessionBusy) {
-		t.Fatalf("overlapping Stream error = %v, want %v", err, errCodexTurnSessionBusy)
-	}
-	releaseStream()
-	for range first {
-	}
-}
-
-func TestCodexTurnSessionHTTPFallbackRedactsSetupError(t *testing.T) {
-	const secret = "sk-secret-fallback"
-	provider, err := NewCodexProvider(CodexOptions{Options: Options{
-		APIKey:  secret,
-		BaseURL: "https://chatgpt.example/backend-api/codex",
-		Model:   "gpt-test",
-	}})
-	if err != nil {
-		t.Fatalf("NewCodexProvider: %v", err)
-	}
-	session := &codexTurnSession{provider: provider}
-	events := make(chan zeroruntime.StreamEvent, 1)
-	session.forwardHTTP(t.Context(), zeroruntime.CompletionRequest{
-		Messages: []zeroruntime.Message{{Role: zeroruntime.MessageRole(secret), Content: "invalid"}},
-	}, events)
-
-	select {
-	case event := <-events:
-		if event.Type != zeroruntime.StreamEventError {
-			t.Fatalf("fallback event type = %s, want error", event.Type)
-		}
-		if strings.Contains(event.Error, secret) {
-			t.Fatalf("fallback error leaked credential: %q", event.Error)
-		}
-	case <-time.After(time.Second):
-		t.Fatal("fallback did not emit setup error")
-	}
-}
-
-func TestCodexTurnSessionCloseDoesNotStartPrewarm(t *testing.T) {
-	provider, err := NewCodexProvider(CodexOptions{Options: Options{
-		APIKey:  "test-token",
-		BaseURL: "https://chatgpt.example/backend-api/codex",
-		Model:   "gpt-test",
-	}})
-	if err != nil {
-		t.Fatalf("NewCodexProvider: %v", err)
-	}
-	session, err := NewCodexTurnSessionProvider(provider, zeroruntime.ProviderCapabilities{}).OpenTurnSession(t.Context())
-	if err != nil {
-		t.Fatalf("OpenTurnSession: %v", err)
-	}
-	done := make(chan error, 1)
-	go func() { done <- session.Close() }()
-	select {
-	case err := <-done:
-		if err != nil {
-			t.Fatalf("Close() error = %v", err)
-		}
-	case <-time.After(200 * time.Millisecond):
-		t.Fatal("Close blocked without a prewarm attempt")
-	}
-}
-
-func newCodexSessionTestProvider(t *testing.T, server *httptest.Server) *CodexProvider {
-	t.Helper()
-	provider, err := NewCodexProvider(CodexOptions{
-		Options: Options{
-			APIKey:     "test-token",
-			BaseURL:    server.URL,
-			Model:      "gpt-test",
-			HTTPClient: server.Client(),
-		},
-		AccountID: "account-test",
-	})
-	if err != nil {
-		t.Fatalf("NewCodexProvider: %v", err)
-	}
-	return provider
-}
-
-func openCodexSession(t *testing.T, provider *CodexProvider) zeroruntime.TurnSession {
-	t.Helper()
-	session, err := NewCodexTurnSessionProvider(provider, zeroruntime.ProviderCapabilities{}).OpenTurnSession(t.Context())
-	if err != nil {
-		t.Fatalf("OpenTurnSession: %v", err)
-	}
-	if err := session.Prewarm(t.Context()); err != nil {
-		t.Fatalf("Prewarm: %v", err)
-	}
-	return session
-}
-
-func collectCodexSessionEvents(t *testing.T, session zeroruntime.TurnSession, request zeroruntime.CompletionRequest) []zeroruntime.StreamEvent {
-	t.Helper()
-	return collectCodexSessionEventsContext(t, t.Context(), session, request)
-}
-
-func collectCodexSessionEventsContext(t *testing.T, ctx context.Context, session zeroruntime.TurnSession, request zeroruntime.CompletionRequest) []zeroruntime.StreamEvent {
-	t.Helper()
-	stream, err := session.Stream(ctx, request)
-	if err != nil {
-		t.Fatalf("Stream: %v", err)
-	}
-	events := []zeroruntime.StreamEvent{}
-	for event := range stream {
-		events = append(events, event)
-		if event.Type == zeroruntime.StreamEventError {
-			t.Fatalf("stream error: %s", event.Error)
-		}
-	}
-	return events
-}
-
-func writeWebSocketEvents(ctx context.Context, connection *websocket.Conn, events ...string) {
-	for _, event := range events {
-		if err := connection.Write(ctx, websocket.MessageText, []byte(event)); err != nil {
-			return
-		}
-	}
-}
-
-func hasToolCallEnd(events []zeroruntime.StreamEvent, id string) bool {
-	for _, event := range events {
-		if event.Type == zeroruntime.StreamEventToolCallEnd && event.ToolCallID == id {
-			return true
-		}
-	}
-	return false
-}
-
-func joinedText(events []zeroruntime.StreamEvent) string {
-	var builder strings.Builder
-	for _, event := range events {
-		if event.Type == zeroruntime.StreamEventText {
-			builder.WriteString(event.Content)
-		}
-	}
-	return builder.String()
-}

internal/providers/openai/codex_terminal_test.go

@@ -2,8 +2,6 @@ package openai
 
 import (
 	"context"
-	"reflect"
-	"strings"
 	"testing"
 
 	"github.com/Gitlawb/zero/internal/zeroruntime"
@@ -27,126 +25,6 @@ func TestToolCallKeyOutputIndexZero(t *testing.T) {
 	}
 }
 
-func TestResponsesStatePreservesDistinctCallID(t *testing.T) {
-	provider := &CodexProvider{}
-	state := newResponsesState()
-	events := make(chan zeroruntime.StreamEvent, 4)
-	provider.handleOutputItemAdded(context.Background(), &responsesEvent{
-		ItemID: "item-1",
-		Item: &itemPayload{
-			Type:   "function_call",
-			ID:     "item-1",
-			CallID: "call-1",
-			Name:   "read_file",
-		},
-	}, state, events)
-	items := state.outputInputItems()
-	if len(items) != 1 || items[0].ID != "item-1" || items[0].CallID != "call-1" {
-		t.Fatalf("captured function call = %#v, want item id item-1 and call id call-1", items)
-	}
-}
-
-func TestCodexCustomApplyPatchStreamProducesFreeformCall(t *testing.T) {
-	provider := &CodexProvider{}
-	state := newResponsesState()
-	events := make(chan zeroruntime.StreamEvent, 16)
-	patch := "*** Begin Patch\n*** Add File: hello.txt\n+hello\n*** End Patch\n"
-	for _, payload := range []string{
-		`{"type":"response.output_item.added","item_id":"item-1","item":{"type":"custom_tool_call","call_id":"call-1","name":"apply_patch"}}`,
-		`{"type":"response.custom_tool_call_input.delta","item_id":"item-1","call_id":"call-1","delta":"*** Begin Patch\n*** Add File: hello.txt\n"}`,
-		`{"type":"response.custom_tool_call_input.delta","item_id":"item-1","call_id":"call-1","delta":"+hello\n*** End Patch\n"}`,
-		`{"type":"response.output_item.done","item_id":"item-1","item":{"type":"custom_tool_call","call_id":"call-1","name":"apply_patch","input":"*** Begin Patch\n*** Add File: hello.txt\n+hello\n*** End Patch\n"}}`,
-		`{"type":"response.completed","response":{"id":"resp-1","status":"completed"}}`,
-	} {
-		if keepReading := provider.emitResponsesEvent(context.Background(), payload, state, events); !keepReading && !state.done {
-			t.Fatalf("stream stopped before terminal event for %s", payload)
-		}
-	}
-	close(events)
-	collected := zeroruntime.CollectStream(context.Background(), events)
-	if len(collected.ToolCalls) != 1 {
-		t.Fatalf("tool calls = %#v, want one", collected.ToolCalls)
-	}
-	call := collected.ToolCalls[0]
-	if call.ID != "item-1" || call.ProviderCallID != "call-1" || call.Name != "apply_patch" || !call.Freeform || call.Arguments != patch {
-		t.Fatalf("custom apply_patch call = %#v", call)
-	}
-}
-
-func TestCodexApplyPatchUsesFreeformWireContract(t *testing.T) {
-	provider, err := NewCodexProvider(CodexOptions{Options: Options{
-		APIKey:  "test-token",
-		BaseURL: "https://chatgpt.example/backend-api/codex",
-		Model:   "gpt-test",
-	}})
-	if err != nil {
-		t.Fatalf("NewCodexProvider: %v", err)
-	}
-	patch := "*** Begin Patch\n*** Add File: hello.txt\n+hello\n*** End Patch\n"
-	request, err := provider.buildResponsesRequest(zeroruntime.CompletionRequest{
-		Messages: []zeroruntime.Message{
-			{Role: zeroruntime.MessageRoleUser, Content: "Add the file."},
-			{Role: zeroruntime.MessageRoleAssistant, ToolCalls: []zeroruntime.ToolCall{{
-				ID: "item-1", ProviderCallID: "call-1", Name: "apply_patch", Arguments: patch, Freeform: true,
-			}}},
-			{Role: zeroruntime.MessageRoleTool, ToolCallID: "item-1", ToolCallProviderID: "call-1", Content: "Done!"},
-		},
-		Tools: []zeroruntime.ToolDefinition{{
-			Name: "apply_patch", Description: "Apply a patch.", Type: zeroruntime.ToolDefinitionFreeform,
-		}},
-	})
-	if err != nil {
-		t.Fatalf("buildResponsesRequest: %v", err)
-	}
-	if len(request.Tools) != 1 || request.Tools[0].Type != string(zeroruntime.ToolDefinitionFreeform) ||
-		request.Tools[0].Format == nil || request.Tools[0].Format.Syntax != "lark" || request.Tools[0].Parameters != nil {
-		t.Fatalf("apply_patch tool wire shape = %#v", request.Tools)
-	}
-	if !strings.Contains(request.Tools[0].Format.Definition, "*** Begin Patch") {
-		t.Fatalf("apply_patch grammar = %q", request.Tools[0].Format.Definition)
-	}
-	if !strings.Contains(request.Tools[0].Description, "absolute file paths") || !strings.Contains(request.Tools[0].Description, "granted extra write root") {
-		t.Fatalf("apply_patch description does not explain extra-root paths: %q", request.Tools[0].Description)
-	}
-	if len(request.Input) != 3 || request.Input[1].Type != "custom_tool_call" || request.Input[1].ID != "item-1" ||
-		request.Input[1].CallID != "call-1" || request.Input[1].Input != patch ||
-		request.Input[2].Type != "custom_tool_call_output" || request.Input[2].CallID != "call-1" {
-		t.Fatalf("custom apply_patch replay input = %#v", request.Input)
-	}
-}
-
-func TestCodexPreservesCustomApplyPatchFunction(t *testing.T) {
-	provider, err := NewCodexProvider(CodexOptions{Options: Options{
-		APIKey:  "test-token",
-		BaseURL: "https://chatgpt.example/backend-api/codex",
-		Model:   "gpt-test",
-	}})
-	if err != nil {
-		t.Fatalf("NewCodexProvider: %v", err)
-	}
-	parameters := map[string]any{
-		"type":       "object",
-		"properties": map[string]any{"value": map[string]any{"type": "string"}},
-	}
-	request, err := provider.buildResponsesRequest(zeroruntime.CompletionRequest{
-		Messages: []zeroruntime.Message{{Role: zeroruntime.MessageRoleUser, Content: "Call the custom tool."}},
-		Tools: []zeroruntime.ToolDefinition{{
-			Name: "apply_patch", Description: "Custom integration tool.", Parameters: parameters,
-		}},
-	})
-	if err != nil {
-		t.Fatalf("buildResponsesRequest: %v", err)
-	}
-	if len(request.Tools) != 1 {
-		t.Fatalf("tools = %#v, want one", request.Tools)
-	}
-	tool := request.Tools[0]
-	if tool.Type != string(zeroruntime.ToolDefinitionFunction) || tool.Format != nil ||
-		tool.Description != "Custom integration tool." || !reflect.DeepEqual(tool.Parameters, parameters) {
-		t.Fatalf("custom apply_patch function was rewritten: %#v", tool)
-	}
-}
-
 func TestHandleTerminalResponseNilPayload(t *testing.T) {
 	p := &CodexProvider{}
 
@@ -212,14 +90,11 @@ func TestHandleTerminalResponseFailedPayloadWithoutError(t *testing.T) {
 	// A response.completed with a payload and no error remains a clean done.
 	ok := make(chan zeroruntime.StreamEvent, 8)
 	p.handleTerminalResponse(context.Background(),
-		&responsesEvent{Type: responsesEventCompleted, Response: &responsePayload{ID: "resp-1", Status: "completed"}}, &responsesState{}, ok)
+		&responsesEvent{Type: responsesEventCompleted, Response: &responsePayload{Status: "completed"}}, &responsesState{}, ok)
 	close(ok)
 	for ev := range ok {
 		if ev.Type == zeroruntime.StreamEventError {
 			t.Error("response.completed with a non-error payload must NOT emit an error")
 		}
-		if ev.Type == zeroruntime.StreamEventDone && ev.ResponseID != "resp-1" {
-			t.Errorf("done response id = %q, want resp-1", ev.ResponseID)
-		}
 	}
 }

internal/providers/openai/codex_test.go

@@ -771,7 +771,7 @@ func TestCodexProviderParsesResponsesTextDeltas(t *testing.T) {
 		`{"type":"response.output_text.delta","delta":"hello "}`,
 		`{"type":"response.output_text.delta","delta":"world"}`,
 		`{"type":"response.output_text.delta","delta":"!"}`,
-		`{"type":"response.completed","response":{"id":"resp-1","status":"completed","usage":{"input_tokens":7,"output_tokens":3,"output_tokens_details":{"reasoning_tokens":1},"input_tokens_details":{"cached_tokens":2,"cache_write_tokens":1}}}}`,
+		`{"type":"response.completed","response":{"id":"resp-1","status":"completed","usage":{"input_tokens":7,"output_tokens":3,"output_tokens_details":{"reasoning_tokens":1},"input_tokens_details":{"cached_tokens":2}}}}`,
 	)
 	defer srv.Close()
 
@@ -809,8 +809,8 @@ func TestCodexProviderParsesResponsesTextDeltas(t *testing.T) {
 	if usage == nil {
 		t.Fatal("expected a usage event, got none")
 	}
-	if usage.InputTokens != 7 || usage.OutputTokens != 3 || usage.CachedInputTokens != 2 || usage.CacheWriteTokens != 1 || usage.ReasoningTokens != 1 {
-		t.Fatalf("usage = %+v, want input=7 output=3 cached=2 cache-write=1 reasoning=1", *usage)
+	if usage.InputTokens != 7 || usage.OutputTokens != 3 || usage.CachedInputTokens != 2 || usage.ReasoningTokens != 1 {
+		t.Fatalf("usage = %+v, want input=7 output=3 cached=2 reasoning=1", *usage)
 	}
 	if !gotDone {
 		t.Fatal("expected a done event, got none")

internal/providers/openai/provider.go

@@ -357,7 +357,6 @@ func (provider *Provider) emitChunk(
 				PromptTokens:      chunk.Usage.PromptTokens,
 				CompletionTokens:  chunk.Usage.CompletionTokens,
 				CachedInputTokens: chunk.Usage.PromptTokensDetails.CachedTokens,
-				CacheWriteTokens:  chunk.Usage.PromptTokensDetails.CacheWriteTokens,
 				ReasoningTokens:   chunk.Usage.CompletionTokensDetails.ReasoningTokens,
 			},
 		})

internal/providers/openai/provider_test.go

@@ -260,14 +260,14 @@ func TestStreamCompletionAppliesCustomAuthAndHeaders(t *testing.T) {
 func TestStreamCompletionEmitsTextUsageAndDone(t *testing.T) {
 	provider := newTestProvider(t, func(w http.ResponseWriter, r *http.Request) {
 		writeSSE(w, `{"choices":[{"delta":{"content":"hello "}}]}`)
-		writeSSE(w, `{"choices":[{"delta":{"content":"zero"}}],"usage":{"prompt_tokens":12,"completion_tokens":5,"prompt_tokens_details":{"cached_tokens":3,"cache_write_tokens":2}}}`)
+		writeSSE(w, `{"choices":[{"delta":{"content":"zero"}}],"usage":{"prompt_tokens":12,"completion_tokens":5,"prompt_tokens_details":{"cached_tokens":3}}}`)
 		writeSSE(w, `[DONE]`)
 	})
 
 	events := collectProviderEvents(t, provider)
 	assertEvent(t, events[0], zeroruntime.StreamEventText, "hello ")
 	assertEvent(t, events[1], zeroruntime.StreamEventText, "zero")
-	if events[2].Type != zeroruntime.StreamEventUsage || events[2].Usage.PromptTokens != 12 || events[2].Usage.CompletionTokens != 5 || events[2].Usage.CachedInputTokens != 3 || events[2].Usage.CacheWriteTokens != 2 {
+	if events[2].Type != zeroruntime.StreamEventUsage || events[2].Usage.PromptTokens != 12 || events[2].Usage.CompletionTokens != 5 || events[2].Usage.CachedInputTokens != 3 {
 		t.Fatalf("unexpected usage event: %#v", events[2])
 	}
 	if events[3].Type != zeroruntime.StreamEventDone {

internal/providers/openai/session.go

@@ -195,12 +195,7 @@ func (s *turnSession) computeFingerprint(request zeroruntime.CompletionRequest)
 func wireToolsDigest(tools []zeroruntime.ToolDefinition) string {
 	rendered := make([]string, 0, len(tools))
 	for _, tool := range tools {
-		wireShape := struct {
-			Type       zeroruntime.ToolDefinitionType    `json:"type,omitempty"`
-			Parameters map[string]any                    `json:"parameters,omitempty"`
-			Format     *zeroruntime.ToolDefinitionFormat `json:"format,omitempty"`
-		}{Type: tool.Type, Parameters: tool.Parameters, Format: tool.Format}
-		schema, err := json.Marshal(wireShape)
+		schema, err := json.Marshal(tool.Parameters)
 		if err != nil {
 			rendered = append(rendered, tool.Name+"\n"+tool.Description+"\n__non_json:"+tool.Name)
 			continue

internal/providers/openai/types.go

@@ -109,8 +109,7 @@ type usage struct {
 }
 
 type promptTokenDetails struct {
-	CachedTokens     int `json:"cached_tokens"`
-	CacheWriteTokens int `json:"cache_write_tokens"`
+	CachedTokens int `json:"cached_tokens"`
 }
 
 type completionTokenDetails struct {

internal/providers/turn_session.go

@@ -15,27 +15,9 @@ import (
 // value (e.g. "1") to enable — the same boolean idiom as ZERO_FORMAT_ON_WRITE.
 const openaiTurnSessionEnv = "ZERO_OPENAI_TURN_SESSION"
 
-// ChatGPT Responses sessions are enabled by default for their native provider.
-// Setting this to 0/false/off restores the stateless HTTP/SSE transport.
-const chatGPTTurnSessionEnv = "ZERO_CHATGPT_TURN_SESSION"
-
 func openaiTurnSessionEnabled() bool {
 	value := strings.TrimSpace(os.Getenv(openaiTurnSessionEnv))
-	return value != "" && !explicitEnvFalse(value)
-}
-
-func chatGPTTurnSessionEnabled() bool {
-	value := strings.TrimSpace(os.Getenv(chatGPTTurnSessionEnv))
-	return value == "" || !explicitEnvFalse(value)
-}
-
-func explicitEnvFalse(value string) bool {
-	switch strings.ToLower(strings.TrimSpace(value)) {
-	case "0", "false", "off":
-		return true
-	default:
-		return false
-	}
+	return value != "" && value != "0" && !strings.EqualFold(value, "false")
 }
 
 // OptimizedTurnSessions returns the gated optimized TurnSessionProvider for an
@@ -43,35 +25,22 @@ func explicitEnvFalse(value string) bool {
 // is ineligible. Callers leave agent Options.TurnSessionProvider nil on false,
 // so the loop's default wrap keeps today's behavior byte-identical.
 //
-// Eligibility is deliberately narrow: native ChatGPT Responses uses its
-// concrete Codex provider and defaults on with a kill switch; official OpenAI
-// chat-completions keeps its existing opt-in prewarm session. Compatible
-// gateways and foreign provider values always retain the default adapter.
+// Eligibility is deliberately narrow: the resolved provider kind must be
+// official OpenAI (NOT openai-compatible gateways — the constructor merges the
+// two, so this branches on the resolved kind explicitly), not the ChatGPT
+// Codex catalog, and the provider value must be the concrete *openai.Provider
+// (a fake, a Codex provider, or nil falls back to the default path safely).
+// No base-URL check on top of the kind: prewarm and fingerprint telemetry are
+// harmless against any host, and kind==openai mirrors the existing
+// official-OpenAI precedent used for prompt_cache_key.
 func OptimizedTurnSessions(profile config.ProviderProfile, provider zeroruntime.Provider, options Options) (zeroruntime.TurnSessionProvider, bool) {
-	resolved, err := resolveProfile(profile, options)
-	if err != nil {
-		return nil, false
-	}
-	if isCodexCatalog(profile, resolved) {
-		if !chatGPTTurnSessionEnabled() {
-			return nil, false
-		}
-		concrete, ok := provider.(*openai.CodexProvider)
-		if !ok {
-			return nil, false
-		}
-		caps, err := resolveCapabilities(profile, options)
-		if err != nil {
-			return nil, false
-		}
-		return openai.NewCodexTurnSessionProvider(concrete, caps), true
-	}
-	if resolved.providerKind != config.ProviderKindOpenAI {
-		return nil, false
-	}
 	if !openaiTurnSessionEnabled() {
 		return nil, false
 	}
+	resolved, err := resolveProfile(profile, options)
+	if err != nil || resolved.providerKind != config.ProviderKindOpenAI || isCodexCatalog(profile, resolved) {
+		return nil, false
+	}
 	concrete, ok := provider.(*openai.Provider)
 	if !ok {
 		return nil, false

internal/providers/turn_session_gate_test.go

@@ -5,7 +5,6 @@ import (
 	"testing"
 
 	"github.com/Gitlawb/zero/internal/config"
-	"github.com/Gitlawb/zero/internal/providers/openai"
 	"github.com/Gitlawb/zero/internal/zeroruntime"
 )
 
@@ -46,7 +45,7 @@ func TestOptimizedTurnSessionsDefaultOff(t *testing.T) {
 func TestOptimizedTurnSessionsFalseyValues(t *testing.T) {
 	profile := openaiEligibleProfile()
 	provider := buildGateProvider(t, profile)
-	for _, value := range []string{"0", "false", "FALSE", "False", "off", "OFF", " ", ""} {
+	for _, value := range []string{"0", "false", "FALSE", "False", " ", ""} {
 		t.Setenv(openaiTurnSessionEnv, value)
 		if _, ok := OptimizedTurnSessions(profile, provider, Options{}); ok {
 			t.Fatalf("gate enabled for falsey value %q", value)
@@ -60,21 +59,6 @@ func TestOptimizedTurnSessionsFalseyValues(t *testing.T) {
 	}
 }
 
-func TestChatGPTTurnSessionGateValues(t *testing.T) {
-	for _, value := range []string{"0", "false", "FALSE", "off", "OFF"} {
-		t.Setenv(chatGPTTurnSessionEnv, value)
-		if chatGPTTurnSessionEnabled() {
-			t.Fatalf("ChatGPT gate enabled for falsey value %q", value)
-		}
-	}
-	for _, value := range []string{"", " ", "1", "true", "on"} {
-		t.Setenv(chatGPTTurnSessionEnv, value)
-		if !chatGPTTurnSessionEnabled() {
-			t.Fatalf("ChatGPT gate disabled for default/truthy value %q", value)
-		}
-	}
-}
-
 func TestOptimizedTurnSessionsOpenAIEligible(t *testing.T) {
 	t.Setenv(openaiTurnSessionEnv, "1")
 	profile := openaiEligibleProfile()
@@ -104,64 +88,13 @@ func TestOptimizedTurnSessionsRejectsCompatible(t *testing.T) {
 }
 
 func TestOptimizedTurnSessionsRejectsCodexCatalog(t *testing.T) {
-	t.Setenv(chatGPTTurnSessionEnv, "0")
-	profile := openaiEligibleProfile()
-	profile.Name = "chatgpt"
-	profile.CatalogID = "chatgpt"
-	if _, ok := OptimizedTurnSessions(profile, buildChatGPTGateProvider(t, profile), Options{}); ok {
-		t.Fatal("the ChatGPT Codex catalog must honor the turn-session kill switch")
-	}
-}
-
-func TestOptimizedTurnSessionsEnablesChatGPTResponsesByDefault(t *testing.T) {
-	t.Setenv(chatGPTTurnSessionEnv, "")
-	profile := openaiEligibleProfile()
-	profile.Name = "chatgpt"
-	profile.CatalogID = "chatgpt"
-	provider := buildChatGPTGateProvider(t, profile)
-
-	turnSessions, ok := OptimizedTurnSessions(profile, provider, Options{})
-	if !ok || turnSessions == nil {
-		t.Fatal("ChatGPT Responses provider did not receive its default turn session")
-	}
-	if got := turnSessions.Capabilities().Model; got != profile.Model {
-		t.Fatalf("Capabilities().Model = %q, want %q", got, profile.Model)
-	}
-}
-
-func TestOptimizedTurnSessionsRecognizesCompatibleLabeledChatGPTProfile(t *testing.T) {
-	t.Setenv(chatGPTTurnSessionEnv, "")
-	profile := openaiEligibleProfile()
-	profile.Name = "chatgpt"
-	profile.CatalogID = "chatgpt"
-	profile.ProviderKind = config.ProviderKindOpenAICompatible
-	if turnSessions, ok := OptimizedTurnSessions(profile, buildChatGPTGateProvider(t, profile), Options{}); !ok || turnSessions == nil {
-		t.Fatal("ChatGPT catalog profile must use its native session regardless of the stored compatibility label")
-	}
-}
-
-func buildChatGPTGateProvider(t *testing.T, profile config.ProviderProfile) *openai.CodexProvider {
-	t.Helper()
-	provider, err := openai.NewCodexProvider(openai.CodexOptions{
-		Options: openai.Options{
-			APIKey:  "test-token",
-			BaseURL: "https://chatgpt.example/backend-api/codex",
-			Model:   profile.Model,
-		},
-		AccountID: "account-test",
-	})
-	if err != nil {
-		t.Fatalf("NewCodexProvider: %v", err)
-	}
-	return provider
-}
-
-func TestOptimizedTurnSessionsRejectsNonCodexProviderForChatGPT(t *testing.T) {
-	t.Setenv(chatGPTTurnSessionEnv, "1")
+	t.Setenv(openaiTurnSessionEnv, "1")
 	profile := openaiEligibleProfile()
 	profile.CatalogID = "chatgpt"
+	// Build the provider from the base profile: the point under test is the
+	// catalog check, not Codex construction (which needs OAuth wiring).
 	if _, ok := OptimizedTurnSessions(profile, buildGateProvider(t, openaiEligibleProfile()), Options{}); ok {
-		t.Fatal("a ChatGPT catalog profile with a non-Codex provider must use the default session")
+		t.Fatal("the ChatGPT Codex catalog must not get the optimized session")
 	}
 }
 

internal/proxydial/proxydial.go

@@ -1,93 +0,0 @@
-// Package proxydial answers one question for an SSRF-guarded dialer: is this
-// dial the connection dial of a request the transport routed through a forward
-// proxy?
-//
-// A guarded transport validates the TARGET of a request before dialing, and its
-// dialer refuses loopback, private and link-local addresses so a redirect or a
-// DNS rebind cannot walk the request onto the local network. When a forward
-// proxy is configured, the transport dials the PROXY first and tunnels the
-// request through it, and a local proxy is by far the common shape:
-// HTTPS_PROXY=http://127.0.0.1:3067. The dialer then sees 127.0.0.1, refuses it,
-// and the user gets "loopback hosts are blocked" for a request whose real target
-// was validated and public (#569).
-//
-// The proxy address is not the request target, and the guard was never about it.
-// It is configuration the user set on purpose, and the transport is going to dial
-// it for every request whether the guard likes it or not. So that dial is let
-// through, and only that dial.
-//
-// THE EXEMPTION FOLLOWS THE TRANSPORT'S OWN ROUTE DECISION, NOT A GUESS AT IT.
-// Asking the Proxy function a question of one's own invention answers for a
-// request the transport never made: with NO_PROXY excluding a host, the real
-// request to that host goes direct while a synthetic probe still comes back
-// proxied, and a direct dial whose address happens to equal the proxy endpoint
-// would then skip the guard entirely. Host-dependent proxy callbacks make the
-// mismatch general, and no amount of care over the probe's spelling closes it,
-// because the two calls are about different requests.
-//
-// So the decision is recorded where it is made, on the request, and read back on
-// the dial that request causes. Transport.RoundTrip asks the wrapped transport's
-// Proxy function about the actual request, stores the answer in that request's
-// context, and hands it on; the transport derives the dial context from the
-// request context, so the dialer reads back the route this very connection is
-// being opened for. Per-request, so concurrent requests cannot overwrite each
-// other, and unforgeable from outside the package: the context key is private.
-package proxydial
-
-import (
-	"context"
-	"net/http"
-	"net/url"
-)
-
-// selectedProxyKey addresses the route decision inside a request context. It is
-// unexported so nothing outside this package can plant one.
-type selectedProxyKey struct{}
-
-// Transport records the proxy its wrapped transport selects for each request in
-// that request's context, so a guarded DialContext installed on the same
-// transport can tell the dial to a proxy from a direct dial.
-//
-// The embedded transport stays reachable: callers configure Proxy, DialContext
-// and the rest on it exactly as before, and tests can read them back.
-type Transport struct {
-	*http.Transport
-}
-
-// Wrap returns a Transport around transport. The result is the http.RoundTripper
-// to install on the client; installing the bare transport instead leaves every
-// dial looking direct, which is safe (the guard applies) but reopens #569.
-func Wrap(transport *http.Transport) *Transport {
-	return &Transport{Transport: transport}
-}
-
-// RoundTrip resolves the route for this request and passes the decision down to
-// the dialer through the request context.
-func (transport *Transport) RoundTrip(request *http.Request) (*http.Response, error) {
-	if transport.Transport.Proxy != nil {
-		// A Proxy error is left for the transport to report: it fails the
-		// request before dialing, so there is no dial to classify. The function
-		// is called once here and once by the transport, which is what a
-		// host-dependent callback already expects from redirects and retries.
-		if proxyURL, err := transport.Transport.Proxy(request); err == nil && proxyURL != nil {
-			request = request.WithContext(context.WithValue(request.Context(), selectedProxyKey{}, proxyURL))
-		}
-	}
-	return transport.Transport.RoundTrip(request)
-}
-
-// IsProxyDial reports whether ctx belongs to a request this package's Transport
-// routed through a proxy, which makes the dial about to happen the dial to that
-// proxy.
-//
-// THE ADDRESS IS NOT COMPARED, AND DOES NOT NEED TO BE. A transport opens
-// exactly one connection dial per connection, and when a proxy is selected that
-// dial goes to the proxy; the target is reached through it, never dialed. So the
-// route decision on the context already identifies the dial, and matching the
-// address against the proxy URL on top of it could only ever disagree with the
-// transport, which is what a punycoded Unicode proxy hostname does: Go dials
-// xn--bro-hoa.example while the URL still spells buero as the user wrote it.
-func IsProxyDial(ctx context.Context) bool {
-	proxyURL, _ := ctx.Value(selectedProxyKey{}).(*url.URL)
-	return proxyURL != nil
-}

internal/proxydial/proxydial_test.go

@@ -1,224 +0,0 @@
-package proxydial
-
-import (
-	"context"
-	"errors"
-	"net"
-	"net/http"
-	"net/url"
-	"sync"
-	"testing"
-)
-
-// errDialed ends the request at the dial, after the route decision has been
-// observed. Nothing here needs a live server.
-var errDialed = errors.New("dial recorded")
-
-type dialRecord struct {
-	address string
-	proxied bool
-}
-
-// driveRequest sends one request through a wrapped transport whose dialer
-// records what it was asked for and whether the context says this dial belongs
-// to a proxied request.
-func driveRequest(t *testing.T, target string, proxyFor func(*http.Request) (*url.URL, error)) dialRecord {
-	t.Helper()
-	var record dialRecord
-	transport := &http.Transport{Proxy: proxyFor}
-	transport.DialContext = func(ctx context.Context, _, address string) (net.Conn, error) {
-		record = dialRecord{address: address, proxied: IsProxyDial(ctx)}
-		return nil, errDialed
-	}
-	client := &http.Client{Transport: Wrap(transport)}
-	request, err := http.NewRequest(http.MethodGet, target, nil)
-	if err != nil {
-		t.Fatal(err)
-	}
-	if _, err := client.Do(request); !errors.Is(err, errDialed) {
-		t.Fatalf("%s: request ended before the dial: %v", target, err)
-	}
-	if record.address == "" {
-		t.Fatalf("%s: the dialer was never called", target)
-	}
-	return record
-}
-
-func fixedProxy(raw string) func(*http.Request) (*url.URL, error) {
-	parsed, err := url.Parse(raw)
-	if err != nil {
-		panic(err)
-	}
-	return func(*http.Request) (*url.URL, error) { return parsed, nil }
-}
-
-// THE DIAL TO A CONFIGURED PROXY IS THE ONE THAT IS EXEMPT. A proxied request
-// dials the proxy, never the target, so the route on the context is what
-// identifies the dial.
-func TestProxiedRequestDialsTheProxyAndSaysSo(t *testing.T) {
-	record := driveRequest(t, "https://api.example.com/v1/models", fixedProxy("http://127.0.0.1:3067"))
-	if !record.proxied {
-		t.Error("a request routed through a proxy did not reach the dialer as proxied")
-	}
-	if record.address != "127.0.0.1:3067" {
-		t.Errorf("dial address = %q, want the proxy endpoint", record.address)
-	}
-}
-
-// AND A DIRECT REQUEST IS NOT, EVEN WHEN ITS ORIGIN IS THE PROXY'S OWN ADDRESS.
-//
-// This is the NO_PROXY shape: the proxy function excludes one host, so a request
-// to that host goes direct. Asking that same function about a request of our own
-// invention would answer "proxied" (the invented host is not excluded) and the
-// direct dial, whose address equals the proxy endpoint, would skip the guard
-// while resolving to whatever the name resolves to at connect time.
-func TestDirectRequestToTheProxyEndpointIsNotAProxyDial(t *testing.T) {
-	proxyURL, err := url.Parse("http://rebind.example:80")
-	if err != nil {
-		t.Fatal(err)
-	}
-	noProxyForRebind := func(request *http.Request) (*url.URL, error) {
-		if request.URL.Hostname() == "rebind.example" {
-			return nil, nil
-		}
-		return proxyURL, nil
-	}
-
-	record := driveRequest(t, "http://rebind.example/data", noProxyForRebind)
-	if record.address != "rebind.example:80" {
-		t.Fatalf("SETUP INVALID: dial address = %q, want the direct origin, which is also the proxy endpoint", record.address)
-	}
-	if record.proxied {
-		t.Error("a direct dial was reported as the proxy dial because its address matched the configured proxy")
-	}
-
-	// The same function still routes another host through that proxy, so the
-	// exclusion above is a route difference and not a disabled proxy.
-	if record := driveRequest(t, "http://elsewhere.example/data", noProxyForRebind); !record.proxied {
-		t.Error("the configured proxy was not used for a host outside the exclusion")
-	}
-}
-
-// The inverse mismatch: a callback that routes by host must not have its answer
-// taken from some other host. A proxy selected only for the real target is
-// honoured.
-func TestHostDependentProxySelectionIsHonoured(t *testing.T) {
-	proxyURL, err := url.Parse("http://127.0.0.1:3067")
-	if err != nil {
-		t.Fatal(err)
-	}
-	onlyForOneHost := func(request *http.Request) (*url.URL, error) {
-		if request.URL.Hostname() == "api.example.com" {
-			return proxyURL, nil
-		}
-		return nil, nil
-	}
-	if record := driveRequest(t, "https://api.example.com/v1", onlyForOneHost); !record.proxied || record.address != "127.0.0.1:3067" {
-		t.Errorf("selected proxy not reached: %+v", record)
-	}
-	if record := driveRequest(t, "https://other.example/v1", onlyForOneHost); record.proxied {
-		t.Error("an unproxied host was reported as proxied")
-	}
-}
-
-// Scheme separation: an https-only proxy leaves an http request direct, and the
-// decision recorded is the one made for that request's own scheme.
-func TestSchemeSeparation(t *testing.T) {
-	proxyURL, err := url.Parse("http://127.0.0.1:3067")
-	if err != nil {
-		t.Fatal(err)
-	}
-	httpsOnly := func(request *http.Request) (*url.URL, error) {
-		if request.URL.Scheme == "https" {
-			return proxyURL, nil
-		}
-		return nil, nil
-	}
-	if record := driveRequest(t, "https://api.example.com/v1", httpsOnly); !record.proxied {
-		t.Error("the https proxy was not applied to an https request")
-	}
-	if record := driveRequest(t, "http://api.example.com/v1", httpsOnly); record.proxied {
-		t.Error("an http request was treated as proxied by an https-only proxy")
-	}
-}
-
-// A UNICODE PROXY HOSTNAME IS STILL THE PROXY. Go dials proxies by their
-// IDNA-encoded name, so a matcher comparing the URL's own spelling would call
-// this dial direct and refuse it as an ordinary private address. Nothing is
-// compared here, so both spellings of one host are one host.
-func TestUnicodeProxyHostnameIsRecognised(t *testing.T) {
-	unicodeRecord := driveRequest(t, "https://api.example.com/v1", fixedProxy("http://büro.example:3067"))
-	if !unicodeRecord.proxied {
-		t.Error("a proxy configured with a Unicode hostname was not recognised as the proxy")
-	}
-	asciiRecord := driveRequest(t, "https://api.example.com/v1", fixedProxy("http://xn--bro-hoa.example:3067"))
-	if !asciiRecord.proxied {
-		t.Error("a proxy configured with the ASCII spelling was not recognised as the proxy")
-	}
-	// The two spellings name one endpoint, and it is the ASCII one that is
-	// dialed. This is the mismatch a string comparison would have had to close.
-	if unicodeRecord.address != asciiRecord.address {
-		t.Errorf("dial addresses differ across spellings of one host: %q vs %q", unicodeRecord.address, asciiRecord.address)
-	}
-}
-
-// A transport with no proxy leaves every dial direct.
-func TestNoProxyMeansNoExemption(t *testing.T) {
-	if record := driveRequest(t, "http://127.0.0.1:3067/", nil); record.proxied {
-		t.Error("a dial was reported as proxied by a transport with no Proxy function")
-	}
-	if IsProxyDial(context.Background()) {
-		t.Error("a context that never went through the wrapper reported a proxy dial")
-	}
-}
-
-// THE DECISION IS PER REQUEST. A shared record of the last selected proxy would
-// let a proxied request hand its exemption to a direct one running beside it.
-func TestConcurrentRequestsKeepTheirOwnRoute(t *testing.T) {
-	proxyURL, err := url.Parse("http://127.0.0.1:3067")
-	if err != nil {
-		t.Fatal(err)
-	}
-	byHost := func(request *http.Request) (*url.URL, error) {
-		if request.URL.Hostname() == "proxied.example" {
-			return proxyURL, nil
-		}
-		return nil, nil
-	}
-
-	var mutex sync.Mutex
-	seen := map[string]bool{}
-	transport := &http.Transport{Proxy: byHost}
-	transport.DialContext = func(ctx context.Context, _, address string) (net.Conn, error) {
-		mutex.Lock()
-		seen[address] = IsProxyDial(ctx)
-		mutex.Unlock()
-		return nil, errDialed
-	}
-	client := &http.Client{Transport: Wrap(transport)}
-
-	var group sync.WaitGroup
-	for range 40 {
-		for _, target := range []string{"http://proxied.example/", "http://direct.example/"} {
-			group.Add(1)
-			go func() {
-				defer group.Done()
-				request, _ := http.NewRequest(http.MethodGet, target, nil)
-				_, _ = client.Do(request)
-			}()
-		}
-	}
-	group.Wait()
-
-	mutex.Lock()
-	defer mutex.Unlock()
-	if !seen["127.0.0.1:3067"] {
-		t.Error("the proxy dial was not recorded as proxied under concurrency")
-	}
-	if seen["direct.example:80"] {
-		t.Error("a direct dial picked up another request's proxy exemption")
-	}
-	if len(seen) != 2 {
-		t.Fatalf("SETUP INVALID: dialed %v, want exactly the proxy and the direct origin", seen)
-	}
-}

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/apply_patch_paths_test.go

@@ -1,96 +0,0 @@
-package sandbox
-
-import (
-	"path/filepath"
-	"strings"
-	"testing"
-)
-
-func TestApplyPatchPathBlockOnlyRejectsRelativeTraversal(t *testing.T) {
-	root := t.TempDir()
-	inside := filepath.Join(root, "main.js")
-	structured := func(path string) string {
-		return strings.Join([]string{"*** Begin Patch", "*** Update File: " + path, "@@", "-a", "+b", "*** End Patch"}, "\n")
-	}
-	for name, patch := range map[string]string{
-		"absolute inside workspace": structured(inside),
-		"relative":                  structured("main.js"),
-		"decorated markers":         "*** Begin Patch ***\n*** Update File: main.js\n@@\n-a\n+b\n*** End Patch ***",
-		"no-space marker":           "***Begin Patch\n*** Update File: main.js\n@@\n-a\n+b\n***End Patch",
-	} {
-		request := Request{ToolName: "apply_patch", WorkspaceRoot: root, SideEffect: SideEffectWrite, Args: map[string]any{"patch": patch}}
-		if block := applyPatchPathBlock(request); block != nil {
-			t.Fatalf("%s: unexpected block %+v", name, block)
-		}
-	}
-	for _, path := range []string{"../escape.js", ".."} {
-		for name, patch := range map[string]string{"canonical": structured(path), "no-space": "***Begin Patch\n*** Update File: " + path + "\n@@\n-a\n+b\n***End Patch"} {
-			request := Request{ToolName: "apply_patch", WorkspaceRoot: root, SideEffect: SideEffectWrite, Args: map[string]any{"patch": patch}}
-			block := applyPatchPathBlock(request)
-			if block == nil || block.Code != BlockOutsideWorkspace {
-				t.Fatalf("%s %q must be blocked as traversal, got %+v", name, path, block)
-			}
-		}
-	}
-}
-
-// Every marker spelling the tool applies must be classified as structured at
-// the sandbox boundary too; otherwise the boundary scans the patch as a unified
-// diff, extracts no targets, and validates nothing (fail-open).
-func TestStructuredPatchClassifierMatchesToolSpellings(t *testing.T) {
-	for _, header := range []string{"*** Begin Patch", "*** Begin Patch ***", "***Begin Patch", "  *** Begin Patch  ", "\ufeff*** Begin Patch"} {
-		patch := header + "\n*** Update File: main.js\n@@\n-a\n+b\n*** End Patch"
-		if !IsStructuredPatch(patch) {
-			t.Fatalf("%q must classify as a structured patch", header)
-		}
-		if paths := applyPatchPaths(patch); len(paths) != 1 || paths[0] != "main.js" {
-			t.Fatalf("%q: sandbox must extract the structured target, got %v", header, paths)
-		}
-	}
-	for _, header := range []string{"--- a/x", "Begin Patch", "*** Begin Patchwork", "*** Update File: x"} {
-		if IsStructuredPatch(header + "\n-a\n+b") {
-			t.Fatalf("%q must not classify as a structured patch", header)
-		}
-	}
-	if StructuredPatchMarker("*** End Patch ***") != "end" || StructuredPatchMarker("***End Patch") != "end" {
-		t.Fatal("decorated end markers must classify as end")
-	}
-}
-
-func TestApplyPatchRequestPathsCarryAbsolutePathsToScopeValidation(t *testing.T) {
-	root := t.TempDir()
-	// NewScope also grants the system temp dir, so a sibling t.TempDir() is
-	// legitimately in scope; pick a path under the filesystem root instead.
-	outside, err := filepath.Abs(filepath.Join(string(filepath.Separator), "zero-outside-workspace-test", "escape.js"))
-	if err != nil {
-		t.Fatal(err)
-	}
-	scope, err := NewScope(root, nil)
-	if err != nil {
-		t.Fatal(err)
-	}
-	inside := filepath.Join(root, "main.js")
-	structured := func(header, footer, path string) string {
-		return strings.Join([]string{header, "*** Update File: " + path, "@@", "-a", "+b", footer}, "\n")
-	}
-	for name, spelling := range map[string][2]string{"canonical": {"*** Begin Patch", "*** End Patch"}, "no-space": {"***Begin Patch", "***End Patch"}} {
-		// Failure path: the exact path the boundary parsed must be denied by the
-		// scope. structuredPatchHeaderPaths normalises separators to "/", so the
-		// parsed form is compared in slash form and then validated as-is.
-		paths := applyPatchRequestPaths(map[string]any{"patch": structured(spelling[0], spelling[1], outside)})
-		if len(paths) != 1 || paths[0] != filepath.ToSlash(outside) {
-			t.Fatalf("%s: absolute patch path must reach scope validation unchanged, got %v", name, paths)
-		}
-		if block := scope.validate(paths[0]); block == nil || block.Code != BlockOutsideWorkspace {
-			t.Fatalf("%s: scope must deny the parsed outside path %q, got %+v", name, paths[0], block)
-		}
-		// Success path: the parsed inside path must be accepted by the scope.
-		paths = applyPatchRequestPaths(map[string]any{"patch": structured(spelling[0], spelling[1], inside)})
-		if len(paths) != 1 || paths[0] != filepath.ToSlash(inside) {
-			t.Fatalf("%s: inside patch path must reach scope validation unchanged, got %v", name, paths)
-		}
-		if block := scope.validate(paths[0]); block != nil {
-			t.Fatalf("%s: scope must accept the parsed inside path %q, got %+v", name, paths[0], block)
-		}
-	}
-}

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/profile.go

@@ -96,28 +96,15 @@ var protectedMetadataNames = []string{".git", ".zero", ".agents"}
 // gitMetadataWriteCarveouts below.
 var sandboxFullyProtectedMetadataNames = []string{".zero", ".agents"}
 
-// gitMetadataWriteCarveouts returns the .git paths that stay write-denied under
-// the OS-level sandbox even though the rest of .git is writable to git
-// subprocesses. Worktrees and submodules store .git as a regular pointer file,
-// so they protect that file itself: constructing .git/hooks below it makes
-// bwrap fail before the command starts. All other entry and error states retain
-// the legacy child paths. The pointer is deliberately not parsed here;
-// repository-controlled metadata must not redirect sandbox rules elsewhere.
+// gitMetadataWriteCarveouts returns the .git subpaths that stay write-denied
+// under the OS-level sandbox even though the rest of .git is writable to git
+// subprocesses. Nonexistent paths are harmless no-ops in every backend's
+// enforcement (seatbelt regex, bwrap ro-bind, Windows ACL deny entry).
 func gitMetadataWriteCarveouts(root string) []string {
-	return gitMetadataWriteCarveoutsWithLstat(root, os.Lstat)
-}
-
-func gitMetadataWriteCarveoutsWithLstat(root string, lstat func(string) (os.FileInfo, error)) []string {
-	gitPath := filepath.Join(root, ".git")
-	children := []string{
-		filepath.Join(gitPath, "hooks"),
-		filepath.Join(gitPath, "config"),
+	return []string{
+		filepath.Join(root, ".git", "hooks"),
+		filepath.Join(root, ".git", "config"),
 	}
-	info, err := lstat(gitPath)
-	if err != nil || !info.Mode().IsRegular() {
-		return children
-	}
-	return []string{gitPath}
 }
 
 func PermissionProfileFromPolicy(workspaceRoot string, policy Policy, scope *Scope) PermissionProfile {

internal/sandbox/profile_worktree_test.go

@@ -1,115 +0,0 @@
-package sandbox
-
-import (
-	"errors"
-	"os"
-	"path/filepath"
-	"testing"
-)
-
-func mustEqualCarveouts(t *testing.T, got, want []string) {
-	t.Helper()
-	if len(got) != len(want) {
-		t.Fatalf("carveouts = %v, want %v", got, want)
-	}
-	for i := range want {
-		if got[i] != want[i] {
-			t.Fatalf("carveout[%d] = %q, want %q", i, got[i], want[i])
-		}
-	}
-}
-
-// Worktree/submodule checkouts store .git as a pointer file. Protect the file
-// itself and never create a bwrap mount target beneath it.
-func TestGitMetadataWriteCarveoutsProtectsWorktreePointer(t *testing.T) {
-	root := t.TempDir()
-	gitPath := filepath.Join(root, ".git")
-	if err := os.WriteFile(gitPath, []byte("gitdir: ../outside\n"), 0o644); err != nil {
-		t.Fatal(err)
-	}
-
-	got := gitMetadataWriteCarveouts(root)
-	mustEqualCarveouts(t, got, []string{gitPath})
-	for _, carveout := range got {
-		if carveout == filepath.Join(gitPath, "hooks") || carveout == filepath.Join(gitPath, "config") {
-			t.Fatalf("carveout points beneath .git file: %q", carveout)
-		}
-	}
-}
-
-func TestLinuxBwrapPlanDoesNotMountBelowWorktreePointer(t *testing.T) {
-	root := t.TempDir()
-	gitPath := filepath.Join(root, ".git")
-	if err := os.WriteFile(gitPath, []byte("gitdir: ../outside\n"), 0o644); err != nil {
-		t.Fatal(err)
-	}
-	profile := PermissionProfile{FileSystem: FileSystemPolicy{
-		Kind: FileSystemRestricted,
-		WriteRoots: []WritableRoot{{
-			Root:             root,
-			ReadOnlySubpaths: gitMetadataWriteCarveouts(root),
-		}},
-	}}
-	args := linuxBwrapFilesystemArgs(profile)
-	assertArgsContainSequence(t, args, "--ro-bind", gitPath, gitPath)
-	for _, child := range []string{"hooks", "config"} {
-		bogus := filepath.Join(gitPath, child)
-		if argsContainSequence(args, "--tmpfs", bogus) || argsContainSequence(args, "--ro-bind", bogus, bogus) {
-			t.Fatalf("bwrap args contain mount below .git file %q: %v", bogus, args)
-		}
-	}
-}
-
-func TestGitMetadataWriteCarveoutsPlainCheckout(t *testing.T) {
-	root := t.TempDir()
-	want := []string{
-		filepath.Join(root, ".git", "hooks"),
-		filepath.Join(root, ".git", "config"),
-	}
-	mustEqualCarveouts(t, gitMetadataWriteCarveouts(root), want)
-
-	if err := os.MkdirAll(filepath.Join(root, ".git"), 0o755); err != nil {
-		t.Fatal(err)
-	}
-	mustEqualCarveouts(t, gitMetadataWriteCarveouts(root), want)
-}
-
-func TestGitMetadataWriteCarveoutsPreservesSymlinkBehavior(t *testing.T) {
-	for _, targetKind := range []string{"directory", "file", "dangling"} {
-		t.Run(targetKind, func(t *testing.T) {
-			root := t.TempDir()
-			target := filepath.Join(root, "real.git")
-			switch targetKind {
-			case "directory":
-				if err := os.MkdirAll(target, 0o755); err != nil {
-					t.Fatal(err)
-				}
-			case "file":
-				if err := os.WriteFile(target, []byte("gitdir: ../outside\n"), 0o644); err != nil {
-					t.Fatal(err)
-				}
-			}
-			if err := os.Symlink(target, filepath.Join(root, ".git")); err != nil {
-				t.Skipf("symlink unavailable: %v", err)
-			}
-			want := []string{
-				filepath.Join(root, ".git", "hooks"),
-				filepath.Join(root, ".git", "config"),
-			}
-			mustEqualCarveouts(t, gitMetadataWriteCarveouts(root), want)
-		})
-	}
-}
-
-func TestGitMetadataWriteCarveoutsPreservesInspectionErrorBehavior(t *testing.T) {
-	root := t.TempDir()
-	gitPath := filepath.Join(root, ".git")
-	want := []string{
-		filepath.Join(gitPath, "hooks"),
-		filepath.Join(gitPath, "config"),
-	}
-	got := gitMetadataWriteCarveoutsWithLstat(root, func(string) (os.FileInfo, error) {
-		return nil, errors.New("inspection failed")
-	})
-	mustEqualCarveouts(t, got, want)
-}

internal/sandbox/profile_worktree_unix_test.go

@@ -1,21 +0,0 @@
-//go:build unix
-
-package sandbox
-
-import (
-	"path/filepath"
-	"syscall"
-	"testing"
-)
-
-func TestGitMetadataWriteCarveoutsPreservesSpecialGitEntryBehavior(t *testing.T) {
-	root := t.TempDir()
-	gitPath := filepath.Join(root, ".git")
-	if err := syscall.Mkfifo(gitPath, 0o644); err != nil {
-		t.Skip(err)
-	}
-	mustEqualCarveouts(t, gitMetadataWriteCarveouts(root), []string{
-		filepath.Join(gitPath, "hooks"),
-		filepath.Join(gitPath, "config"),
-	})
-}

internal/sandbox/risk.go

@@ -281,15 +281,11 @@ func applyPatchPathBlock(request Request) *pathBlock {
 	if patch == "" {
 		return nil
 	}
-	// Only relative traversal is rejected up front. Absolute paths flow through
-	// the regular workspace-scope validation below (requestPaths), which accepts
-	// one inside the workspace and denies one outside — a model that echoes the
-	// absolute path read_file showed it must not be blocked for that alone.
 	for _, path := range applyPatchPaths(patch) {
 		if path == "" || path == "/dev/null" {
 			continue
 		}
-		if path == ".." || strings.HasPrefix(path, "../") {
+		if filepath.IsAbs(path) || path == ".." || strings.HasPrefix(path, "../") {
 			return &pathBlock{
 				Code:   BlockOutsideWorkspace,
 				Path:   path,
@@ -300,35 +296,8 @@ func applyPatchPathBlock(request Request) *pathBlock {
 	return nil
 }
 
-// structuredPatchMarkerPattern is the single classifier for structured-patch
-// markers, shared by the sandbox boundary and the apply_patch tool (which
-// imports this package). It accepts the canonical "*** Begin Patch" /
-// "*** End Patch" and the decorated spellings models emit ("*** Begin Patch ***",
-// "***Begin Patch", trailing whitespace). Both sides must agree: a spelling the
-// tool would apply but the sandbox did not recognise would make the sandbox
-// scan the patch as a unified diff, extract no targets, and validate nothing.
-var structuredPatchMarkerPattern = regexp.MustCompile(`^\*{3}\s*(Begin|End) Patch\s*\**\s*$`)
-
-// StructuredPatchMarker classifies a line as the "begin" or "end" marker of a
-// structured patch, or "" when it is neither.
-func StructuredPatchMarker(line string) string {
-	match := structuredPatchMarkerPattern.FindStringSubmatch(strings.TrimSpace(line))
-	if match == nil {
-		return ""
-	}
-	return strings.ToLower(match[1])
-}
-
-// IsStructuredPatch reports whether patch opens with a structured begin marker.
-// The tool applies exactly the patches this returns true for, so the sandbox
-// extracts structured header paths for exactly the same set.
-func IsStructuredPatch(patch string) bool {
-	first, _, _ := strings.Cut(strings.TrimSpace(strings.TrimPrefix(patch, "\ufeff")), "\n")
-	return StructuredPatchMarker(first) == "begin"
-}
-
 func applyPatchPaths(patch string) []string {
-	if IsStructuredPatch(patch) {
+	if strings.HasPrefix(strings.TrimSpace(strings.TrimPrefix(patch, "\ufeff")), "*** Begin Patch") {
 		return structuredPatchHeaderPaths(patch)
 	}
 	return patchHeaderPaths(patch)

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/specialist/exec.go

@@ -76,17 +76,12 @@ type BuildArgsInput struct {
 }
 
 type BuildResumeArgsInput struct {
-	SessionID    string
-	Prompt       string
-	CurrentDepth int
-	Manifest     Manifest
-	Cwd          string
-	// ParentModel and ParentReasoningEffort are the same fallbacks the fresh
-	// path takes, and they are here for the same reason: appendModelArgs uses
-	// them only when the manifest pins nothing of its own.
-	ParentModel           string
-	ParentReasoningEffort string
-	PermissionMode        string
+	SessionID      string
+	Prompt         string
+	CurrentDepth   int
+	Manifest       Manifest
+	Cwd            string
+	PermissionMode string
 }
 
 type BuildArgsResult struct {
@@ -349,18 +344,6 @@ func (executor Executor) BuildResumeArgs(input BuildResumeArgsInput) (BuildArgsR
 	}
 	args := []string{"exec", "--resume", sessionID}
 	args = append(args, promptArgs...)
-	// A RESUMED SPECIALIST KEEPS THE MODEL ITS MANIFEST PINNED.
-	//
-	// The fresh path appends this and the resume path did not, so a specialist
-	// pinned to a cheap model ran on that model once and then silently reverted
-	// to the parent's configured model on every resume. Nothing reports it: the
-	// child starts normally and the only symptom is the bill.
-	//
-	// Resuming does not restore the recorded model on its own. sessions.PrepareExec
-	// records the model it ran under but never feeds it back into provider
-	// construction, so without this the child takes whatever the config default
-	// resolves to now.
-	args = appendModelArgs(args, input.Manifest, input.ParentModel, input.ParentReasoningEffort)
 	args = append(args, "--auto", specialistAutonomy(input.PermissionMode), "--output-format", "stream-json")
 	// See BuildArgs: only plan/spec-draft propagate --permission-mode so --auto
 	// remains the authority for member/auto/ask/unsafe child resolution.
@@ -441,14 +424,12 @@ func (executor Executor) runResume(ctx context.Context, params TaskParameters, o
 		return ExecResult{}, err
 	}
 	built, err := executor.BuildResumeArgs(BuildResumeArgsInput{
-		SessionID:             params.Resume,
-		Prompt:                params.Prompt,
-		CurrentDepth:          options.CurrentDepth,
-		Manifest:              manifest,
-		Cwd:                   options.Cwd,
-		ParentModel:           options.ParentModel,
-		ParentReasoningEffort: options.ParentReasoningEffort,
-		PermissionMode:        options.PermissionMode,
+		SessionID:      params.Resume,
+		Prompt:         params.Prompt,
+		CurrentDepth:   options.CurrentDepth,
+		Manifest:       manifest,
+		Cwd:            options.Cwd,
+		PermissionMode: options.PermissionMode,
 	})
 	if err != nil {
 		return ExecResult{}, err

internal/specialist/resume_model_test.go

@@ -1,303 +0,0 @@
-package specialist
-
-import (
-	"context"
-	"strings"
-	"testing"
-
-	"github.com/Gitlawb/zero/internal/sessions"
-	"github.com/Gitlawb/zero/internal/streamjson"
-)
-
-// argValue returns the value following flag in argv, and whether it was present.
-func argValue(args []string, flag string) (string, bool) {
-	for index, arg := range args {
-		if arg == flag && index+1 < len(args) {
-			return args[index+1], true
-		}
-	}
-	return "", false
-}
-
-func pinnedManifest(model string, effort string) Manifest {
-	return Manifest{
-		Metadata: Metadata{
-			Name:            "skim",
-			Description:     "Bounded read-only lookups.",
-			Model:           model,
-			ReasoningEffort: effort,
-			Tools:           []string{"read_file"},
-		},
-		SystemPrompt:  "Find the thing and stop.",
-		ResolvedTools: []string{"read_file"},
-	}
-}
-
-// A RESUMED SPECIALIST KEEPS THE MODEL ITS MANIFEST PINNED.
-//
-// Metadata.Model exists so a bounded, delegated task can run on a cheaper model
-// than its parent. BuildArgs appended it; BuildResumeArgs did not. So the
-// specialist ran on the cheap model once, and the moment the orchestrator
-// resumed it the child fell back to whatever the parent's configured model
-// resolved to. Nothing surfaced it: the resumed child starts normally, does the
-// work, and the only symptom is the bill.
-//
-// Resuming does not restore the recorded model on its own, which is why the flag
-// has to be passed again rather than relied upon.
-func TestAResumedSpecialistKeepsItsPinnedModel(t *testing.T) {
-	manifest := pinnedManifest("claude-haiku-4.5", "")
-
-	fresh, err := (Executor{}).BuildArgs(BuildArgsInput{
-		Manifest:     manifest,
-		Prompt:       "find the thing",
-		CurrentDepth: 0,
-		ParentModel:  "claude-opus-4.1",
-	})
-	if err != nil {
-		t.Fatalf("BuildArgs: %v", err)
-	}
-	// SETUP: the fresh path really does pin it, or the comparison below is
-	// asserting against a path that never worked either.
-	freshModel, ok := argValue(fresh.Args, "--model")
-	if !ok || freshModel != "claude-haiku-4.5" {
-		t.Fatalf("SETUP INVALID: the fresh path passed --model %q (present=%t), want the manifest's model", freshModel, ok)
-	}
-
-	resumed, err := (Executor{}).BuildResumeArgs(BuildResumeArgsInput{
-		SessionID:    "01HZZZZZZZZZZZZZZZZZZZZZZZ",
-		Prompt:       "keep going",
-		CurrentDepth: 0,
-		Manifest:     manifest,
-		ParentModel:  "claude-opus-4.1",
-	})
-	if err != nil {
-		t.Fatalf("BuildResumeArgs: %v", err)
-	}
-	resumedModel, ok := argValue(resumed.Args, "--model")
-	if !ok {
-		t.Fatalf("a resumed specialist carries no --model at all, so it reverts to the parent's configured model: %v", resumed.Args)
-	}
-	if resumedModel != "claude-haiku-4.5" {
-		t.Fatalf("a resumed specialist runs on %q, want the manifest's pinned %q", resumedModel, "claude-haiku-4.5")
-	}
-}
-
-// And a manifest that pins nothing still inherits the parent's model, which is
-// what makes the fallback in appendModelArgs meaningful rather than the pinned
-// case being special-cased.
-func TestAResumedSpecialistWithNoPinInheritsTheParentModel(t *testing.T) {
-	resumed, err := (Executor{}).BuildResumeArgs(BuildResumeArgsInput{
-		SessionID:    "01HZZZZZZZZZZZZZZZZZZZZZZZ",
-		Prompt:       "keep going",
-		CurrentDepth: 0,
-		Manifest:     pinnedManifest("", ""),
-		ParentModel:  "claude-opus-4.1",
-	})
-	if err != nil {
-		t.Fatalf("BuildResumeArgs: %v", err)
-	}
-	model, ok := argValue(resumed.Args, "--model")
-	if !ok || model != "claude-opus-4.1" {
-		t.Fatalf("a resumed specialist with no pinned model passed --model %q (present=%t), want the parent's", model, ok)
-	}
-}
-
-// The reasoning-effort rule travels with the model, or the two paths disagree
-// about what a pinned model implies. appendModelArgs inherits the parent's
-// effort ONLY when the manifest pins no model of its own: a manifest that chose
-// a different model has not agreed to the parent's effort for it.
-func TestAResumedSpecialistFollowsTheSameReasoningEffortRule(t *testing.T) {
-	t.Run("pinned model does not inherit parent effort", func(t *testing.T) {
-		resumed, err := (Executor{}).BuildResumeArgs(BuildResumeArgsInput{
-			SessionID:             "01HZZZZZZZZZZZZZZZZZZZZZZZ",
-			Prompt:                "keep going",
-			CurrentDepth:          0,
-			Manifest:              pinnedManifest("claude-haiku-4.5", ""),
-			ParentModel:           "claude-opus-4.1",
-			ParentReasoningEffort: "high",
-		})
-		if err != nil {
-			t.Fatalf("BuildResumeArgs: %v", err)
-		}
-		if effort, ok := argValue(resumed.Args, "--reasoning-effort"); ok {
-			t.Fatalf("a manifest that pinned its own model inherited the parent's effort %q", effort)
-		}
-	})
-
-	t.Run("no pinned model inherits parent effort", func(t *testing.T) {
-		resumed, err := (Executor{}).BuildResumeArgs(BuildResumeArgsInput{
-			SessionID:             "01HZZZZZZZZZZZZZZZZZZZZZZZ",
-			Prompt:                "keep going",
-			CurrentDepth:          0,
-			Manifest:              pinnedManifest("", ""),
-			ParentModel:           "claude-opus-4.1",
-			ParentReasoningEffort: "high",
-		})
-		if err != nil {
-			t.Fatalf("BuildResumeArgs: %v", err)
-		}
-		effort, ok := argValue(resumed.Args, "--reasoning-effort")
-		if !ok || effort != "high" {
-			t.Fatalf("a manifest pinning nothing passed --reasoning-effort %q (present=%t), want the parent's", effort, ok)
-		}
-	})
-}
-
-// The two builders agree on where the flag sits relative to the rest of the
-// argv, so a future change to one does not silently reorder only the other.
-func TestBothBuildersPlaceTheModelBeforeTheAutonomyFlag(t *testing.T) {
-	manifest := pinnedManifest("claude-haiku-4.5", "")
-	fresh, err := (Executor{}).BuildArgs(BuildArgsInput{Manifest: manifest, Prompt: "go", CurrentDepth: 0})
-	if err != nil {
-		t.Fatalf("BuildArgs: %v", err)
-	}
-	resumed, err := (Executor{}).BuildResumeArgs(BuildResumeArgsInput{
-		SessionID: "01HZZZZZZZZZZZZZZZZZZZZZZZ", Prompt: "go", CurrentDepth: 0, Manifest: manifest,
-	})
-	if err != nil {
-		t.Fatalf("BuildResumeArgs: %v", err)
-	}
-	for _, argv := range [][]string{fresh.Args, resumed.Args} {
-		model := indexOf(argv, "--model")
-		auto := indexOf(argv, "--auto")
-		if model < 0 || auto < 0 || model > auto {
-			t.Fatalf("--model at %d, --auto at %d in %s", model, auto, strings.Join(argv, " "))
-		}
-	}
-}
-
-func indexOf(args []string, want string) int {
-	for index, arg := range args {
-		if arg == want {
-			return index
-		}
-	}
-	return -1
-}
-
-// AND THE CALL SITE PASSES IT, WHICH THE BUILDER TESTS ABOVE CANNOT SEE.
-//
-// Every test above calls BuildResumeArgs directly. Dropping the ParentModel
-// field from the runResume call site still compiles and still passes all of
-// them, because the builder is doing its job with whatever it is handed. The
-// defect this fix repairs lived at the call site, not in the builder, so it
-// needs a test that goes through Run.
-//
-// Driven through the real Run dispatch with the RunChild seam capturing argv.
-func TestRunResumePassesTheParentModelThroughToTheChild(t *testing.T) {
-	store := sessions.NewStore(sessions.StoreOptions{RootDir: t.TempDir()})
-	parent, err := store.Create(sessions.CreateInput{SessionID: "parent_session"})
-	if err != nil {
-		t.Fatalf("create parent: %v", err)
-	}
-	if _, err := store.Create(sessions.CreateInput{
-		SessionID:       "child_task",
-		SessionKind:     sessions.SessionKindChild,
-		Tag:             SessionTagSpecialist,
-		Depth:           1,
-		ParentSessionID: parent.SessionID,
-		AgentName:       "skim",
-		TaskID:          "child_task",
-	}); err != nil {
-		t.Fatalf("create child: %v", err)
-	}
-
-	zero := 0
-	var captured []string
-	executor := Executor{
-		BinaryPath:   "/usr/local/bin/zero",
-		SessionStore: store,
-		NewSessionID: func() (string, error) { return "child_task", nil },
-		Load: func(LoadOptions) (LoadResult, error) {
-			// No pinned model, so the parent's is the only thing that can supply one.
-			return LoadResult{Specialists: []Manifest{pinnedManifest("", "")}}, nil
-		},
-		RunChild: func(_ context.Context, _ string, args []string, _ func(streamjson.Event)) (ChildRunResult, error) {
-			captured = append([]string(nil), args...)
-			return ChildRunResult{
-				Events: []streamjson.Event{
-					{Type: streamjson.EventRunStart, RunID: "run_1", SessionID: "child_task"},
-					{Type: streamjson.EventFinal, RunID: "run_1", Text: "done"},
-					{Type: streamjson.EventRunEnd, RunID: "run_1", Status: "success", ExitCode: &zero},
-				},
-			}, nil
-		},
-	}
-
-	if _, err := executor.Run(context.Background(), TaskParameters{
-		Name:   "skim",
-		Prompt: "keep going",
-		Resume: "child_task",
-	}, TaskRunOptions{
-		ParentSessionID: parent.SessionID,
-		ParentModel:     "claude-opus-4.1",
-	}); err != nil {
-		t.Fatalf("Run(resume): %v", err)
-	}
-
-	// SETUP: this really was the resume path, not a fresh spawn.
-	if index := indexOf(captured, "--resume"); index < 0 {
-		t.Fatalf("SETUP INVALID: the child was not resumed: %v", captured)
-	}
-	model, ok := argValue(captured, "--model")
-	if !ok {
-		t.Fatalf("the resumed child was launched with no --model, so it runs on whatever the config default resolves to: %v", captured)
-	}
-	if model != "claude-opus-4.1" {
-		t.Fatalf("the resumed child was launched with --model %q, want the parent's %q", model, "claude-opus-4.1")
-	}
-}
-
-// THE FRESH CALL SITE NEEDS THE SAME GUARD, FOR THE SAME REASON.
-//
-// runFresh and runResume both construct their builder input by hand, and both
-// have a byte-identical ParentModel line. Deleting either one compiles. The
-// resume half is what this change repairs; this covers the other half so the
-// pair cannot drift again in the direction nobody was looking.
-func TestRunFreshPassesTheParentModelThroughToTheChild(t *testing.T) {
-	store := sessions.NewStore(sessions.StoreOptions{RootDir: t.TempDir()})
-	parent, err := store.Create(sessions.CreateInput{SessionID: "parent_session"})
-	if err != nil {
-		t.Fatalf("create parent: %v", err)
-	}
-
-	zero := 0
-	var captured []string
-	executor := Executor{
-		BinaryPath:   "/usr/local/bin/zero",
-		SessionStore: store,
-		NewSessionID: func() (string, error) { return "child_task", nil },
-		Load: func(LoadOptions) (LoadResult, error) {
-			return LoadResult{Specialists: []Manifest{pinnedManifest("", "")}}, nil
-		},
-		RunChild: func(_ context.Context, _ string, args []string, _ func(streamjson.Event)) (ChildRunResult, error) {
-			captured = append([]string(nil), args...)
-			return ChildRunResult{
-				Events: []streamjson.Event{
-					{Type: streamjson.EventRunStart, RunID: "run_1", SessionID: "child_task"},
-					{Type: streamjson.EventFinal, RunID: "run_1", Text: "done"},
-					{Type: streamjson.EventRunEnd, RunID: "run_1", Status: "success", ExitCode: &zero},
-				},
-			}, nil
-		},
-	}
-
-	if _, err := executor.Run(context.Background(), TaskParameters{
-		Name:   "skim",
-		Prompt: "find the thing",
-	}, TaskRunOptions{
-		ParentSessionID: parent.SessionID,
-		ParentModel:     "claude-opus-4.1",
-	}); err != nil {
-		t.Fatalf("Run(fresh): %v", err)
-	}
-
-	// SETUP: a fresh spawn, not a resume, or this covers the wrong site.
-	if indexOf(captured, "--resume") >= 0 {
-		t.Fatalf("SETUP INVALID: the child was resumed rather than freshly spawned: %v", captured)
-	}
-	model, ok := argValue(captured, "--model")
-	if !ok || model != "claude-opus-4.1" {
-		t.Fatalf("the fresh child was launched with --model %q (present=%t), want the parent's", model, ok)
-	}
-}

internal/streamjson/streamjson.go

@@ -94,8 +94,6 @@ type Event struct {
 	Meta              map[string]string `json:"meta,omitempty"`
 	PromptTokens      *int              `json:"promptTokens,omitempty"`
 	CompletionTokens  *int              `json:"completionTokens,omitempty"`
-	CachedInputTokens *int              `json:"cachedInputTokens,omitempty"`
-	CacheWriteTokens  *int              `json:"cacheWriteTokens,omitempty"`
 	TotalTokens       *int              `json:"totalTokens,omitempty"`
 	CostUSD           *float64          `json:"costUsd,omitempty"`
 	Text              string            `json:"text,omitempty"`

internal/tools/apply_patch.go

@@ -3,11 +3,11 @@ package tools
 import (
 	"context"
 	"fmt"
+	"os"
+	"os/exec"
 	"path/filepath"
 	"strconv"
 	"strings"
-
-	"github.com/Gitlawb/zero/internal/sandbox"
 )
 
 type applyPatchTool struct {
@@ -16,110 +16,15 @@ type applyPatchTool struct {
 	scope         PathScope
 }
 
-func (applyPatchTool) isBuiltInApplyPatch() {}
-
-// PrepareFreeformApplyPatchArguments converts native structured-patch input
-// into the ordinary apply_patch argument map used by permission checks and tool
-// execution. Absolute patch-header paths select a granted write root and are
-// rewritten relative to that root; relative-only patches keep workspace-root
-// behavior.
-func PrepareFreeformApplyPatchArguments(tool Tool, patch string) (map[string]any, error) {
-	preparer, ok := tool.(interface {
-		prepareFreeformArguments(string) (map[string]any, error)
-	})
-	if !ok {
-		return nil, fmt.Errorf("tool is not Zero's built-in apply_patch")
-	}
-	return preparer.prepareFreeformArguments(patch)
-}
-
-func (tool applyPatchTool) prepareFreeformArguments(patch string) (map[string]any, error) {
-	args := map[string]any{"patch": patch}
-	if !isStructuredPatch(patch) {
-		return args, nil
-	}
-
-	lines := strings.Split(strings.ReplaceAll(patch, "\r\n", "\n"), "\n")
-	selectedRoot := ""
-	hasRelativeHeader := false
-	for index, line := range lines {
-		prefix := ""
-		switch {
-		case strings.HasPrefix(line, structuredAddFile):
-			prefix = structuredAddFile
-		case strings.HasPrefix(line, structuredDeleteFile):
-			prefix = structuredDeleteFile
-		case strings.HasPrefix(line, structuredUpdateFile):
-			prefix = structuredUpdateFile
-		case strings.HasPrefix(line, structuredMoveTo):
-			prefix = structuredMoveTo
-		default:
-			continue
-		}
-		path := strings.TrimSpace(strings.TrimPrefix(line, prefix))
-		if !filepath.IsAbs(path) {
-			hasRelativeHeader = true
-			continue
-		}
-		root, relative, err := tool.freeformPatchRoot(path)
-		if err != nil {
-			return nil, err
-		}
-		if selectedRoot != "" && selectedRoot != root {
-			return nil, fmt.Errorf("freeform patch spans multiple write roots")
-		}
-		selectedRoot = root
-		lines[index] = prefix + filepath.ToSlash(relative)
-	}
-	if selectedRoot != "" {
-		roots, err := scopedRoots(tool.workspaceRoot, tool.scope)
-		if err != nil {
-			return nil, err
-		}
-		if hasRelativeHeader && selectedRoot != roots[0] {
-			return nil, fmt.Errorf("freeform patch mixes workspace-relative paths with an extra write root")
-		}
-		args["cwd"] = selectedRoot
-		args["patch"] = strings.Join(lines, "\n")
-	}
-	return args, nil
-}
-
-func (tool applyPatchTool) freeformPatchRoot(path string) (string, string, error) {
-	roots, err := scopedRoots(tool.workspaceRoot, tool.scope)
-	if err != nil {
-		return "", "", err
-	}
-	var firstErr error
-	for _, root := range roots {
-		candidate := sandbox.NormalizePrefixForRoot(path, root)
-		candidate, err = filepath.Abs(candidate)
-		if err != nil {
-			if firstErr == nil {
-				firstErr = err
-			}
-			continue
-		}
-		relative, err := filepath.Rel(root, candidate)
-		if err == nil && relative != ".." && !strings.HasPrefix(relative, ".."+string(filepath.Separator)) && !filepath.IsAbs(relative) {
-			return root, filepath.ToSlash(relative), nil
-		}
-		if firstErr == nil {
-			firstErr = outsideWorkspaceError(path)
-		}
-	}
-	return "", "", firstErr
-}
-
 func NewScopedApplyPatchTool(workspaceRoot string, scope PathScope) Tool {
 	return applyPatchTool{
 		baseTool: baseTool{
 			name:        "apply_patch",
-			description: "Apply a multi-hunk or multi-file patch inside the workspace (or a granted extra write root). Structured format:\n*** Begin Patch\n*** Update File: src/app.js\n@@\n unchanged context line\n-removed line\n+added line\n*** End Patch\nUse \"*** Add File: path\" with \"+\" lines to create a file and \"*** Delete File: path\" to remove one; several sections may follow each other. A unified diff (---/+++ headers with a/ b/ prefixes, @@ hunks) is also accepted and applied in-process. Paths are workspace-relative; absolute paths inside the workspace are fine. For a single targeted change, edit_file is simpler.",
+			description: "Apply a patch inside the workspace or an explicitly granted extra write root.",
 			parameters: Schema{
 				Type: "object",
 				Properties: map[string]PropertySchema{
-					"patch": {Type: "string", Description: "The structured (*** Begin Patch) or unified-diff patch text."},
+					"patch": {Type: "string", Description: "A unified diff or a structured *** Begin Patch patch to apply."},
 					"cwd":   {Type: "string", Description: "Directory where the patch should be applied. Relative paths stay in the workspace; use an absolute path to target a granted extra write root. Defaults to workspace root.", Default: "."},
 				},
 				Required:             []string{"patch"},
@@ -154,14 +59,177 @@ func (tool applyPatchTool) RunWithOptions(ctx context.Context, args map[string]a
 	if isStructuredPatch(patch) {
 		return tool.runStructuredPatch(applyRoot, relativeRoot, patch, options)
 	}
-	// Unified diffs are translated into the same operations and applied by
-	// the same os.Root engine, so neither format opens a target by pathname
-	// after validation (no check-to-use window) and git is not needed.
-	operations, err := parseUnifiedPatch(patch)
+	if err := validatePatchPaths(applyRoot, patch); err != nil {
+		return errorResult("Error applying patch: " + err.Error())
+	}
+
+	tempFile, err := os.CreateTemp("", "zero-patch-*.patch")
 	if err != nil {
 		return errorResult("Error applying patch: " + err.Error())
 	}
-	return applyPatchOperations(applyRoot, relativeRoot, operations, options)
+	patchPath := tempFile.Name()
+	defer func() {
+		_ = os.Remove(patchPath)
+	}()
+	if _, err := tempFile.WriteString(patch); err != nil {
+		_ = tempFile.Close()
+		return errorResult("Error applying patch: " + err.Error())
+	}
+	if err := tempFile.Close(); err != nil {
+		return errorResult("Error applying patch: " + err.Error())
+	}
+
+	if err := recheckPatchWriteTargets(applyRoot, patch); err != nil {
+		return errorResult("Error applying patch: " + err.Error())
+	}
+	var createdTargets []string
+	var fullySuppliedTargets []string
+	wholeBefore := map[string]bool{}
+	if options.FileTracker != nil {
+		createdTargets = missingPatchTargets(applyRoot, patch)
+		fullySuppliedTargets = completeCreatedPatchTargets(applyRoot, patch)
+		for _, path := range patchHeaderPaths(patch) {
+			if path == "" || path == "/dev/null" {
+				continue
+			}
+			if absolute, _, rerr := resolveWorkspaceTargetPath(applyRoot, path); rerr == nil {
+				wholeBefore[absolute] = options.FileTracker.SeenWhole(absolute)
+			}
+		}
+	}
+
+	command := exec.CommandContext(ctx, "git", "apply", "--whitespace=nowarn", patchPath)
+	command.Dir = applyRoot
+	output, err := command.CombinedOutput()
+	if err != nil {
+		message := strings.TrimSpace(string(output))
+		if message == "" {
+			message = err.Error()
+		}
+		return errorResult("Error applying patch: " + message)
+	}
+
+	summary := "Patch applied successfully."
+	if relativeRoot != "." {
+		summary = "Patch applied successfully in " + relativeRoot + "."
+	}
+	result := okResult(summary)
+	result.ChangedFiles = changedFilesFromPatch(relativeRoot, patch)
+	result.Display = Display{Summary: summary, Kind: "diff", Preview: capPreviewDiff(patch)}
+	fullySupplied := make(map[string]bool, len(fullySuppliedTargets))
+	for _, absolute := range fullySuppliedTargets {
+		fullySupplied[absolute] = true
+	}
+	// Re-baseline files changed by this tool. When the model had already seen the
+	// whole input (or supplied a complete new file), the exact patch plus that
+	// input determines the whole output, so a follow-up edit needs no wasted read.
+	// Partial observations remain conservative and are cleared by Record.
+	for _, changed := range result.ChangedFiles {
+		if absolute, _, rerr := resolveScopedPath(tool.workspaceRoot, tool.scope, changed); rerr == nil {
+			content, readErr := os.ReadFile(absolute)
+			if readErr != nil {
+				options.FileTracker.Forget(absolute)
+				continue
+			}
+			info, _ := os.Stat(absolute)
+			wasWhole := wholeBefore[absolute] || fullySupplied[absolute]
+			options.FileTracker.Record(absolute, content, info)
+			if wasWhole {
+				lines := lineCount(string(content))
+				options.FileTracker.RecordSeenRange(absolute, 1, lines, lines)
+			}
+		}
+	}
+	recordCreatedPatchTargets(options.FileTracker, createdTargets)
+	return result
+}
+
+func missingPatchTargets(root string, patch string) []string {
+	seen := map[string]bool{}
+	var missing []string
+	for _, path := range patchHeaderPaths(patch) {
+		if path == "" || path == "/dev/null" {
+			continue
+		}
+		absolute, _, err := resolveWorkspaceTargetPath(root, path)
+		if err != nil || seen[absolute] {
+			continue
+		}
+		seen[absolute] = true
+		if _, err := os.Stat(absolute); os.IsNotExist(err) {
+			missing = append(missing, absolute)
+		}
+	}
+	return missing
+}
+
+// completeCreatedPatchTargets returns only files whose full contents are
+// supplied by a /dev/null creation patch. A missing rename/copy destination is
+// created by git too, but its bytes come from an unread source and must not gain
+// whole-file observation credit.
+func completeCreatedPatchTargets(root string, patch string) []string {
+	seen := map[string]bool{}
+	var created []string
+	oldRemaining, newRemaining := 0, 0
+	inHunk := false
+	fromDevNull := false
+	for _, line := range strings.Split(strings.ReplaceAll(patch, "\r\n", "\n"), "\n") {
+		if inHunk && (oldRemaining > 0 || newRemaining > 0) {
+			switch {
+			case strings.HasPrefix(line, "-"):
+				oldRemaining--
+			case strings.HasPrefix(line, "+"):
+				newRemaining--
+			case strings.HasPrefix(line, "\\"):
+			default:
+				oldRemaining--
+				newRemaining--
+			}
+			continue
+		}
+		inHunk = false
+		switch {
+		case strings.HasPrefix(line, "diff --git "):
+			fromDevNull = false
+		case strings.HasPrefix(line, "@@"):
+			oldRemaining, newRemaining = parseHunkCounts(line)
+			inHunk = oldRemaining > 0 || newRemaining > 0
+		case strings.HasPrefix(line, "--- "):
+			fromDevNull = patchFileHeaderPath(line) == "/dev/null"
+		case strings.HasPrefix(line, "+++ "):
+			path := patchFileHeaderPath(line)
+			if !fromDevNull || path == "" || path == "/dev/null" {
+				fromDevNull = false
+				continue
+			}
+			fromDevNull = false
+			absolute, _, err := resolveWorkspaceTargetPath(root, stripPatchPrefix(path))
+			if err != nil || seen[absolute] {
+				continue
+			}
+			if _, err := os.Stat(absolute); !os.IsNotExist(err) {
+				continue
+			}
+			seen[absolute] = true
+			created = append(created, absolute)
+		}
+	}
+	return created
+}
+
+func recordCreatedPatchTargets(tracker *FileTracker, missingBefore []string) {
+	if tracker == nil {
+		return
+	}
+	for _, absolute := range missingBefore {
+		if _, err := os.Stat(absolute); err != nil {
+			continue
+		}
+		if resolved, err := filepath.EvalSymlinks(absolute); err == nil {
+			absolute = resolved
+		}
+		tracker.RecordCreated(absolute)
+	}
 }
 
 // changedFilesFromPatch extracts the unique, WORKSPACE-relative paths a patch
@@ -192,35 +260,27 @@ func changedFilesFromPatch(relativeRoot string, patch string) []string {
 	return paths
 }
 
-// normalizePatchPathForRoot resolves platform-level symlinks (macOS /var ->
-// /private/var) in the prefix of an absolute patch path that lies outside the
-// apply root, so a path the model copied from read_file compares equal to the
-// symlink-resolved root. Relative paths are returned unchanged.
-func normalizePatchPathForRoot(root string, path string) string {
-	if !filepath.IsAbs(path) {
-		return path
-	}
-	resolvedRoot, err := filepath.Abs(root)
-	if err != nil {
-		return path
-	}
-	if evaluated, err := filepath.EvalSymlinks(resolvedRoot); err == nil {
-		resolvedRoot = evaluated
-	}
-	return sandbox.NormalizePrefixForRoot(path, resolvedRoot)
-}
-
 func validatePatchPaths(root string, patch string) error {
 	for _, path := range patchHeaderPaths(patch) {
 		if path == "" || path == "/dev/null" {
 			continue
 		}
-		// Relative traversal is rejected here; an absolute path is checked by
-		// resolveWorkspaceTargetPath, which only accepts one inside the root.
-		if path == ".." || strings.HasPrefix(path, "../") {
+		if filepath.IsAbs(path) || path == ".." || strings.HasPrefix(path, "../") {
 			return fmt.Errorf("patch path %q must stay inside the workspace", path)
 		}
-		if _, _, err := resolveWorkspaceTargetPath(root, normalizePatchPathForRoot(root, path)); err != nil {
+		if _, _, err := resolveWorkspaceTargetPath(root, path); err != nil {
+			return err
+		}
+	}
+	return nil
+}
+
+func recheckPatchWriteTargets(root string, patch string) error {
+	for _, path := range patchHeaderPaths(patch) {
+		if path == "" || path == "/dev/null" {
+			continue
+		}
+		if err := recheckWorkspaceWriteTarget(root, path); err != nil {
 			return err
 		}
 	}
@@ -291,7 +351,7 @@ func patchFileHeaderPath(line string) string {
 // tokens. Scanning the whole line would let a crafted heading like
 // "@@ -1,1 +1,1 @@ +1,999999" overwrite the real count, keep the parser stuck in
 // hunk mode, and swallow later "--- "/"+++ " file headers so they escape
-// validatePatchPaths — a workspace-confinement bypass.
+// validatePatchPaths / recheckPatchWriteTargets — a workspace-confinement bypass.
 func parseHunkCounts(line string) (int, int) {
 	_, rest, ok := strings.Cut(line, "@@")
 	if !ok {

internal/tools/apply_patch_tolerance_test.go

@@ -1,712 +0,0 @@
-package tools
-
-import (
-	"context"
-	"os"
-	"path/filepath"
-	"strconv"
-	"strings"
-	"testing"
-)
-
-// Models routinely decorate the structured markers ("*** Begin Patch ***") and
-// write unified-diff ranges after "@@"; both used to fail on the first line and
-// pushed the model into whole-file rewrites.
-func TestApplyPatchToleratesDecoratedMarkersAndRangeHeaders(t *testing.T) {
-	root := t.TempDir()
-	writeTestFile(t, filepath.Join(root, "hello.txt"), "hello\nold\nbye\n")
-
-	patch := strings.Join([]string{
-		"*** Begin Patch ***",
-		"*** Update File: hello.txt",
-		"@@ -1,3 +1,3 @@",
-		" hello",
-		"-old",
-		"+new",
-		"*** End Patch ***",
-		"",
-	}, "\n")
-
-	if !isStructuredPatch(patch) {
-		t.Fatal("decorated begin marker must still be recognised as a structured patch")
-	}
-	result := NewScopedApplyPatchTool(root, nil).Run(context.Background(), map[string]any{"patch": patch})
-	if result.Status != StatusOK {
-		t.Fatalf("decorated structured patch should apply, got %s: %s", result.Status, result.Output)
-	}
-	content, err := os.ReadFile(filepath.Join(root, "hello.txt"))
-	if err != nil {
-		t.Fatal(err)
-	}
-	if got := strings.ReplaceAll(string(content), "\r\n", "\n"); got != "hello\nnew\nbye\n" {
-		t.Fatalf("patched content = %q", got)
-	}
-}
-
-func TestStructuredHunkAnchorKeepsHeadingAndPlainContext(t *testing.T) {
-	cases := map[string]string{
-		"-12,4 +12,6":                  "",
-		"-12 +12":                      "",
-		"-12,4 +12,6 @@":               "",
-		"-12,4 +12,6 @@ func main() {": "func main() {",
-		"func main() {":                "func main() {",
-		"":                             "",
-	}
-	for input, want := range cases {
-		if got := structuredHunkAnchor(input); got != want {
-			t.Fatalf("structuredHunkAnchor(%q) = %q, want %q", input, got, want)
-		}
-	}
-}
-
-func TestStructuredPatchMarkerSpellings(t *testing.T) {
-	begin := []string{"*** Begin Patch", "*** Begin Patch ***", "***Begin Patch", "  *** Begin Patch  ", "*** Begin Patch **"}
-	for _, line := range begin {
-		if structuredPatchMarker(line) != "begin" {
-			t.Fatalf("%q must read as the begin marker", line)
-		}
-	}
-	if structuredPatchMarker("*** End Patch ***") != "end" {
-		t.Fatal("decorated end marker must read as the end marker")
-	}
-	for _, line := range []string{"*** Update File: x", "Begin Patch", "*** Begin Patchwork"} {
-		if structuredPatchMarker(line) != "" {
-			t.Fatalf("%q must not read as a marker", line)
-		}
-	}
-}
-
-func TestStructuredPatchHeaderErrorCarriesFormatHint(t *testing.T) {
-	_, err := parseStructuredPatch("--- a/x\n+++ b/x\n")
-	if err == nil || !strings.Contains(err.Error(), "*** Update File: path") {
-		t.Fatalf("header error should teach the format, got %v", err)
-	}
-}
-
-func TestApplyPatchAcceptsAbsoluteInWorkspacePaths(t *testing.T) {
-	root := t.TempDir()
-	writeTestFile(t, filepath.Join(root, "hello.txt"), "hello\nold\n")
-	absolute := filepath.Join(root, "hello.txt")
-
-	structured := strings.Join([]string{
-		"*** Begin Patch",
-		"*** Update File: " + absolute,
-		"@@",
-		" hello",
-		"-old",
-		"+structured",
-		"*** End Patch",
-		"",
-	}, "\n")
-	result := NewScopedApplyPatchTool(root, nil).Run(context.Background(), map[string]any{"patch": structured})
-	if result.Status != StatusOK {
-		t.Fatalf("absolute in-workspace structured path should apply, got %s: %s", result.Status, result.Output)
-	}
-	content, _ := os.ReadFile(absolute)
-	if got := strings.ReplaceAll(string(content), "\r\n", "\n"); got != "hello\nstructured\n" {
-		t.Fatalf("structured content = %q", got)
-	}
-	if len(result.ChangedFiles) != 1 || result.ChangedFiles[0] != "hello.txt" {
-		t.Fatalf("changed files should be workspace-relative, got %v", result.ChangedFiles)
-	}
-
-	unified := strings.Join([]string{
-		"--- " + absolute,
-		"+++ " + absolute,
-		"@@ -1,2 +1,2 @@",
-		" hello",
-		"-structured",
-		"+unified",
-		"",
-	}, "\n")
-	result = NewScopedApplyPatchTool(root, nil).Run(context.Background(), map[string]any{"patch": unified})
-	if result.Status != StatusOK {
-		t.Fatalf("absolute in-workspace unified path should apply, got %s: %s", result.Status, result.Output)
-	}
-	content, _ = os.ReadFile(absolute)
-	if got := strings.ReplaceAll(string(content), "\r\n", "\n"); got != "hello\nunified\n" {
-		t.Fatalf("unified content = %q", got)
-	}
-}
-
-func TestApplyPatchStillRejectsAbsolutePathsOutsideWorkspace(t *testing.T) {
-	root := t.TempDir()
-	outside := filepath.Join(t.TempDir(), "escape.txt")
-	writeTestFile(t, outside, "old\n")
-
-	for name, patch := range map[string]string{
-		"structured": strings.Join([]string{"*** Begin Patch", "*** Update File: " + outside, "@@", "-old", "+new", "*** End Patch", ""}, "\n"),
-		"unified":    strings.Join([]string{"--- " + outside, "+++ " + outside, "@@ -1 +1 @@", "-old", "+new", ""}, "\n"),
-	} {
-		result := NewScopedApplyPatchTool(root, nil).Run(context.Background(), map[string]any{"patch": patch})
-		if result.Status == StatusOK {
-			t.Fatalf("%s patch outside the workspace must be rejected", name)
-		}
-		if content, _ := os.ReadFile(outside); string(content) != "old\n" {
-			t.Fatalf("%s patch must not touch a file outside the workspace", name)
-		}
-	}
-}
-
-// Unified diffs are applied in-process through the same os.Root engine as
-// structured patches: git C-quoted paths with whitespace resolve to one file,
-// and the same header outside the workspace is refused before anything is
-// written.
-func TestUnifiedPatchQuotedWhitespacePaths(t *testing.T) {
-	root := t.TempDir()
-	dir := filepath.Join(root, "work tree")
-	if err := os.MkdirAll(dir, 0o755); err != nil {
-		t.Fatal(err)
-	}
-	target := filepath.Join(dir, "file.txt")
-	writeTestFile(t, target, "hello\nold\n")
-
-	quoted := func(path string) string { return strconv.Quote(path) }
-	inside := strings.Join([]string{
-		"diff --git " + quoted("a/"+filepath.ToSlash(target)) + " " + quoted("b/"+filepath.ToSlash(target)),
-		"--- " + quoted(target),
-		"+++ " + quoted(target),
-		"@@ -1,2 +1,2 @@",
-		" hello",
-		"-old",
-		"+new",
-		"",
-	}, "\n")
-	result := NewScopedApplyPatchTool(root, nil).Run(context.Background(), map[string]any{"patch": inside})
-	if result.Status != StatusOK {
-		t.Fatalf("quoted whitespace path inside the workspace should apply, got %s: %s", result.Status, result.Output)
-	}
-	content, _ := os.ReadFile(target)
-	if got := strings.ReplaceAll(string(content), "\r\n", "\n"); got != "hello\nnew\n" {
-		t.Fatalf("content = %q", got)
-	}
-	if len(result.ChangedFiles) != 1 || result.ChangedFiles[0] != "work tree/file.txt" {
-		t.Fatalf("changed files = %v", result.ChangedFiles)
-	}
-
-	outsideDir := filepath.Join(t.TempDir(), "other tree")
-	if err := os.MkdirAll(outsideDir, 0o755); err != nil {
-		t.Fatal(err)
-	}
-	outside := filepath.Join(outsideDir, "file.txt")
-	writeTestFile(t, outside, "hello\nold\n")
-	escape := strings.Join([]string{"--- " + quoted(outside), "+++ " + quoted(outside), "@@ -1,2 +1,2 @@", " hello", "-old", "+new", ""}, "\n")
-	result = NewScopedApplyPatchTool(root, nil).Run(context.Background(), map[string]any{"patch": escape})
-	if result.Status == StatusOK {
-		t.Fatal("quoted whitespace path outside the workspace must be rejected")
-	}
-	if content, _ := os.ReadFile(outside); string(content) != "hello\nold\n" {
-		t.Fatal("outside file must be untouched")
-	}
-}
-
-// A workspace path that is swapped for a symlink escaping the root — the
-// classic check-to-use attack — is refused by the os.Root engine for both
-// formats, and the outside file is never modified.
-func TestApplyPatchRefusesSymlinkEscapingWorkspace(t *testing.T) {
-	root := t.TempDir()
-	outside := filepath.Join(t.TempDir(), "secret.txt")
-	writeTestFile(t, outside, "hello\nold\n")
-	link := filepath.Join(root, "target.txt")
-	if err := os.Symlink(outside, link); err != nil {
-		t.Skipf("symlinks unavailable: %v", err)
-	}
-	for name, patch := range map[string]string{
-		"unified":    strings.Join([]string{"--- a/target.txt", "+++ b/target.txt", "@@ -1,2 +1,2 @@", " hello", "-old", "+new", ""}, "\n"),
-		"structured": strings.Join([]string{"*** Begin Patch", "*** Update File: target.txt", "@@", " hello", "-old", "+new", "*** End Patch", ""}, "\n"),
-	} {
-		result := NewScopedApplyPatchTool(root, nil).Run(context.Background(), map[string]any{"patch": patch})
-		if result.Status == StatusOK {
-			t.Fatalf("%s patch through an escaping symlink must be refused", name)
-		}
-		if content, _ := os.ReadFile(outside); string(content) != "hello\nold\n" {
-			t.Fatalf("%s patch must not modify the file outside the workspace", name)
-		}
-	}
-}
-
-func TestUnifiedPatchCreatesDeletesAndHonoursNoNewlineMarker(t *testing.T) {
-	root := t.TempDir()
-	writeTestFile(t, filepath.Join(root, "gone.txt"), "bye\n")
-	writeTestFile(t, filepath.Join(root, "keep.txt"), "a\nb\n")
-	patch := strings.Join([]string{
-		"diff --git a/new.txt b/new.txt",
-		"new file mode 100644",
-		"--- /dev/null",
-		"+++ b/new.txt",
-		"@@ -0,0 +1,2 @@",
-		"+first",
-		"+second",
-		"\\ No newline at end of file",
-		"diff --git a/gone.txt b/gone.txt",
-		"deleted file mode 100644",
-		"--- a/gone.txt",
-		"+++ /dev/null",
-		"@@ -1 +0,0 @@",
-		"-bye",
-		"--- a/keep.txt",
-		"+++ b/keep.txt",
-		"@@ -1,2 +1,2 @@",
-		" a",
-		"-b",
-		"+c",
-		"\\ No newline at end of file",
-		"",
-	}, "\n")
-	result := NewScopedApplyPatchTool(root, nil).Run(context.Background(), map[string]any{"patch": patch})
-	if result.Status != StatusOK {
-		t.Fatalf("multi-file unified patch should apply, got %s: %s", result.Status, result.Output)
-	}
-	if content, _ := os.ReadFile(filepath.Join(root, "new.txt")); string(content) != "first\nsecond" {
-		t.Fatalf("created file = %q", string(content))
-	}
-	if _, err := os.Stat(filepath.Join(root, "gone.txt")); !os.IsNotExist(err) {
-		t.Fatal("deleted file must be gone")
-	}
-	if content, _ := os.ReadFile(filepath.Join(root, "keep.txt")); string(content) != "a\nc" {
-		t.Fatalf("updated file = %q", string(content))
-	}
-	if len(result.ChangedFiles) != 3 {
-		t.Fatalf("changed files = %v", result.ChangedFiles)
-	}
-}
-
-func TestUnifiedPatchUsesRangeHintThenFallsBackToContext(t *testing.T) {
-	root := t.TempDir()
-	// Two identical blocks: the hunk's range picks the second one, which
-	// content search alone would call ambiguous.
-	writeTestFile(t, filepath.Join(root, "dup.txt"), "x\ny\nx\ny\n")
-	patch := strings.Join([]string{"--- a/dup.txt", "+++ b/dup.txt", "@@ -3,2 +3,2 @@", " x", "-y", "+z", ""}, "\n")
-	result := NewScopedApplyPatchTool(root, nil).Run(context.Background(), map[string]any{"patch": patch})
-	if result.Status != StatusOK {
-		t.Fatalf("range-hinted hunk should apply, got %s: %s", result.Status, result.Output)
-	}
-	if content, _ := os.ReadFile(filepath.Join(root, "dup.txt")); string(content) != "x\ny\nx\nz\n" {
-		t.Fatalf("content = %q", string(content))
-	}
-	// A stale range (file grew above the hunk) still applies by unique context.
-	writeTestFile(t, filepath.Join(root, "moved.txt"), "header\nhello\nold\n")
-	patch = strings.Join([]string{"--- a/moved.txt", "+++ b/moved.txt", "@@ -1,2 +1,2 @@", " hello", "-old", "+new", ""}, "\n")
-	result = NewScopedApplyPatchTool(root, nil).Run(context.Background(), map[string]any{"patch": patch})
-	if result.Status != StatusOK {
-		t.Fatalf("offset hunk should apply by context, got %s: %s", result.Status, result.Output)
-	}
-	if content, _ := os.ReadFile(filepath.Join(root, "moved.txt")); string(content) != "header\nhello\nnew\n" {
-		t.Fatalf("content = %q", string(content))
-	}
-}
-
-func TestUnifiedPatchRenameWithHunkAndRejectsBinary(t *testing.T) {
-	root := t.TempDir()
-	writeTestFile(t, filepath.Join(root, "x.txt"), "hello\nold\n")
-	rename := strings.Join([]string{
-		"diff --git a/x.txt b/y.txt",
-		"similarity index 90%",
-		"rename from x.txt",
-		"rename to y.txt",
-		"--- a/x.txt",
-		"+++ b/y.txt",
-		"@@ -1,2 +1,2 @@",
-		" hello",
-		"-old",
-		"+new",
-		"",
-	}, "\n")
-	result := NewScopedApplyPatchTool(root, nil).Run(context.Background(), map[string]any{"patch": rename})
-	if result.Status != StatusOK {
-		t.Fatalf("rename with hunk should apply, got %s: %s", result.Status, result.Output)
-	}
-	if _, err := os.Stat(filepath.Join(root, "x.txt")); !os.IsNotExist(err) {
-		t.Fatal("renamed source must be gone")
-	}
-	if content, _ := os.ReadFile(filepath.Join(root, "y.txt")); string(content) != "hello\nnew\n" {
-		t.Fatalf("renamed content = %q", string(content))
-	}
-	for name, patch := range map[string]string{
-		"binary": "diff --git a/x b/x\nBinary files a/x and b/x differ\n",
-		"empty":  "diff --git a/x b/x\n",
-	} {
-		if result := NewScopedApplyPatchTool(root, nil).Run(context.Background(), map[string]any{"patch": patch}); result.Status == StatusOK {
-			t.Fatalf("%s patch must be rejected", name)
-		}
-	}
-}
-
-func TestUnifiedPatchCopyOperation(t *testing.T) {
-	root := t.TempDir()
-	writeTestFile(t, filepath.Join(root, "src.txt"), "hello\nold\n")
-	copyPatch := func(from, to string, hunk bool) string {
-		lines := []string{"diff --git a/" + from + " b/" + to, "similarity index 90%", "copy from " + from, "copy to " + to}
-		if hunk {
-			lines = append(lines, "--- a/"+from, "+++ b/"+to, "@@ -1,2 +1,2 @@", " hello", "-old", "+new")
-		}
-		return strings.Join(append(lines, ""), "\n")
-	}
-
-	// Success: source kept, destination created with the hunk applied, and the
-	// destination inherits the source's tracker state (read whole -> whole).
-	tracker := NewFileTracker()
-	registry := NewRegistry()
-	registry.Register(NewScopedReadFileTool(root, nil))
-	registry.Register(NewScopedApplyPatchTool(root, nil))
-	opts := RunOptions{PermissionGranted: true, FileTracker: tracker}
-	if r := registry.RunWithOptions(context.Background(), "read_file", map[string]any{"path": "src.txt"}, opts); r.Status != StatusOK {
-		t.Fatalf("read: %s", r.Output)
-	}
-	result := registry.RunWithOptions(context.Background(), "apply_patch", map[string]any{"patch": copyPatch("src.txt", "dst.txt", true)}, opts)
-	if result.Status != StatusOK {
-		t.Fatalf("copy with hunk should apply, got %s: %s", result.Status, result.Output)
-	}
-	if content, _ := os.ReadFile(filepath.Join(root, "src.txt")); string(content) != "hello\nold\n" {
-		t.Fatalf("copy must keep the source, got %q", string(content))
-	}
-	if content, _ := os.ReadFile(filepath.Join(root, "dst.txt")); string(content) != "hello\nnew\n" {
-		t.Fatalf("copy destination = %q", string(content))
-	}
-	if len(result.ChangedFiles) != 2 || result.ChangedFiles[0] != "src.txt" || result.ChangedFiles[1] != "dst.txt" {
-		t.Fatalf("changed files = %v", result.ChangedFiles)
-	}
-	destination, err := filepath.EvalSymlinks(filepath.Join(root, "dst.txt"))
-	if err != nil {
-		t.Fatal(err)
-	}
-	if !tracker.SeenWhole(destination) {
-		t.Fatal("destination copied from a fully read source must be tracked as seen whole")
-	}
-	unreadSource, _ := filepath.EvalSymlinks(filepath.Join(root, "src.txt"))
-	if _, tracked := tracker.Version(unreadSource); !tracked {
-		t.Fatal("source must stay tracked after a copy")
-	}
-
-	// Failure: destination already exists — nothing is written.
-	writeTestFile(t, filepath.Join(root, "taken.txt"), "keep\n")
-	result = NewScopedApplyPatchTool(root, nil).Run(context.Background(), map[string]any{"patch": copyPatch("src.txt", "taken.txt", false)})
-	if result.Status == StatusOK || !strings.Contains(result.Output, "already exists") {
-		t.Fatalf("copy onto an existing destination must be refused, got %s: %s", result.Status, result.Output)
-	}
-	if content, _ := os.ReadFile(filepath.Join(root, "taken.txt")); string(content) != "keep\n" {
-		t.Fatal("existing destination must be untouched")
-	}
-
-	// Failure: copy onto itself.
-	result = NewScopedApplyPatchTool(root, nil).Run(context.Background(), map[string]any{"patch": copyPatch("src.txt", "src.txt", false)})
-	if result.Status == StatusOK || !strings.Contains(result.Output, "onto itself") {
-		t.Fatalf("copy onto itself must be refused, got %s: %s", result.Status, result.Output)
-	}
-}
-
-func TestUnifiedPatchRejectsOverDeclaredHunkCounts(t *testing.T) {
-	root := t.TempDir()
-	writeTestFile(t, filepath.Join(root, "a.txt"), "hello\nold\n")
-	writeTestFile(t, filepath.Join(root, "b.txt"), "x\n")
-	// "-1,3 +1,3" over-declares a two-line hunk, so without a guard the next
-	// file's ---/+++ headers would be swallowed as "-"/"+" content.
-	patch := strings.Join([]string{
-		"--- a/a.txt", "+++ b/a.txt", "@@ -1,3 +1,3 @@", " hello", "-old", "+new",
-		"--- a/b.txt", "+++ b/b.txt", "@@ -1 +1 @@", "-x", "+y", "",
-	}, "\n")
-	result := NewScopedApplyPatchTool(root, nil).Run(context.Background(), map[string]any{"patch": patch})
-	if result.Status == StatusOK || !strings.Contains(result.Output, "declared line counts") {
-		t.Fatalf("over-declared hunk must be reported as malformed, got %s: %s", result.Status, result.Output)
-	}
-	for name, want := range map[string]string{"a.txt": "hello\nold\n", "b.txt": "x\n"} {
-		if content, _ := os.ReadFile(filepath.Join(root, name)); string(content) != want {
-			t.Fatalf("%s must be untouched after a malformed patch, got %q", name, string(content))
-		}
-	}
-	// Truncated at end of input is reported the same way.
-	truncated := "--- a/a.txt\n+++ b/a.txt\n@@ -1,2 +1,2 @@\n hello\n-old\n"
-	if result := NewScopedApplyPatchTool(root, nil).Run(context.Background(), map[string]any{"patch": truncated}); result.Status == StatusOK || !strings.Contains(result.Output, "declared line counts") {
-		t.Fatalf("truncated hunk must be reported as malformed, got %s: %s", result.Status, result.Output)
-	}
-}
-
-func TestUnifiedPatchNoNewlineMarkerOnlyAfterFinalHunk(t *testing.T) {
-	root := t.TempDir()
-	writeTestFile(t, filepath.Join(root, "two.txt"), "a\nb\nc\nd\ne\nf\n")
-	// A marker after the first of two hunks describes nothing real and must
-	// not leak into the second hunk's result: the patch is rejected untouched.
-	early := strings.Join([]string{
-		"--- a/two.txt", "+++ b/two.txt",
-		"@@ -1,2 +1,2 @@", " a", "-b", "+B", "\\ No newline at end of file",
-		"@@ -5,2 +5,2 @@", " e", "-f", "+F", "",
-	}, "\n")
-	result := NewScopedApplyPatchTool(root, nil).Run(context.Background(), map[string]any{"patch": early})
-	if result.Status == StatusOK || !strings.Contains(result.Output, "must follow the last hunk") {
-		t.Fatalf("marker before a later hunk must be rejected, got %s: %s", result.Status, result.Output)
-	}
-	if content, _ := os.ReadFile(filepath.Join(root, "two.txt")); string(content) != "a\nb\nc\nd\ne\nf\n" {
-		t.Fatal("rejected patch must not modify the file")
-	}
-	// The same marker after the final hunk applies and strips the newline.
-	final := strings.Join([]string{
-		"--- a/two.txt", "+++ b/two.txt",
-		"@@ -1,2 +1,2 @@", " a", "-b", "+B",
-		"@@ -5,2 +5,2 @@", " e", "-f", "+F", "\\ No newline at end of file", "",
-	}, "\n")
-	result = NewScopedApplyPatchTool(root, nil).Run(context.Background(), map[string]any{"patch": final})
-	if result.Status != StatusOK {
-		t.Fatalf("two-hunk patch with a final marker should apply, got %s: %s", result.Status, result.Output)
-	}
-	if content, _ := os.ReadFile(filepath.Join(root, "two.txt")); string(content) != "a\nB\nc\nd\ne\nF" {
-		t.Fatalf("content = %q", string(content))
-	}
-}
-
-// A removed "-- …" line directly followed by an added "++ …" line looks like a
-// ---/+++ header pair; the boundary check must not mistake it for one.
-func TestUnifiedPatchKeepsAdjacentDashPlusContentLines(t *testing.T) {
-	root := t.TempDir()
-	writeTestFile(t, filepath.Join(root, "notes.sql"), "select 1;\n-- old comment\nselect 2;\n")
-	patch := strings.Join([]string{
-		"--- a/notes.sql", "+++ b/notes.sql",
-		"@@ -1,3 +1,3 @@", " select 1;", "--- old comment", "+++ new comment", " select 2;", "",
-	}, "\n")
-	result := NewScopedApplyPatchTool(root, nil).Run(context.Background(), map[string]any{"patch": patch})
-	if result.Status != StatusOK {
-		t.Fatalf("adjacent -- / ++ content lines must apply, got %s: %s", result.Status, result.Output)
-	}
-	if content, _ := os.ReadFile(filepath.Join(root, "notes.sql")); string(content) != "select 1;\n++ new comment\nselect 2;\n" {
-		t.Fatalf("content = %q", string(content))
-	}
-}
-
-// A unified deletion states the content it removes; it must be verified
-// against the current file before anything is deleted.
-func TestUnifiedPatchDeletionVerifiesExpectedContent(t *testing.T) {
-	deletion := func(path string, hunks ...string) string {
-		lines := []string{"diff --git a/" + path + " b/" + path, "deleted file mode 100644", "--- a/" + path, "+++ /dev/null"}
-		return strings.Join(append(append(lines, hunks...), ""), "\n")
-	}
-	t.Run("matching deletion succeeds", func(t *testing.T) {
-		root := t.TempDir()
-		writeTestFile(t, filepath.Join(root, "gone.txt"), "current\n")
-		result := NewScopedApplyPatchTool(root, nil).Run(context.Background(), map[string]any{"patch": deletion("gone.txt", "@@ -1 +0,0 @@", "-current")})
-		if result.Status != StatusOK {
-			t.Fatalf("matching deletion should apply, got %s: %s", result.Status, result.Output)
-		}
-		if _, err := os.Stat(filepath.Join(root, "gone.txt")); !os.IsNotExist(err) {
-			t.Fatal("file must be deleted")
-		}
-	})
-	t.Run("stale deletion is refused untouched", func(t *testing.T) {
-		root := t.TempDir()
-		writeTestFile(t, filepath.Join(root, "gone.txt"), "current\n")
-		result := NewScopedApplyPatchTool(root, nil).Run(context.Background(), map[string]any{"patch": deletion("gone.txt", "@@ -1 +0,0 @@", "-stale")})
-		if result.Status == StatusOK || !strings.Contains(result.Output, "does not match its current content") {
-			t.Fatalf("stale deletion must be refused, got %s: %s", result.Status, result.Output)
-		}
-		if content, _ := os.ReadFile(filepath.Join(root, "gone.txt")); string(content) != "current\n" {
-			t.Fatalf("file must be byte-for-byte unchanged, got %q", string(content))
-		}
-	})
-	t.Run("partial deletion is refused", func(t *testing.T) {
-		root := t.TempDir()
-		writeTestFile(t, filepath.Join(root, "gone.txt"), "one\ntwo\n")
-		result := NewScopedApplyPatchTool(root, nil).Run(context.Background(), map[string]any{"patch": deletion("gone.txt", "@@ -1 +0,0 @@", "-one")})
-		if result.Status == StatusOK || !strings.Contains(result.Output, "does not match its current content") {
-			t.Fatalf("deletion that does not cover the file must be refused, got %s: %s", result.Status, result.Output)
-		}
-		if content, _ := os.ReadFile(filepath.Join(root, "gone.txt")); string(content) != "one\ntwo\n" {
-			t.Fatal("file must be unchanged")
-		}
-	})
-	t.Run("header-only deletion is refused", func(t *testing.T) {
-		root := t.TempDir()
-		writeTestFile(t, filepath.Join(root, "gone.txt"), "current\n")
-		result := NewScopedApplyPatchTool(root, nil).Run(context.Background(), map[string]any{"patch": deletion("gone.txt")})
-		if result.Status == StatusOK || !strings.Contains(result.Output, "must include the hunk") {
-			t.Fatalf("header-only deletion must be refused, got %s: %s", result.Status, result.Output)
-		}
-		if _, err := os.Stat(filepath.Join(root, "gone.txt")); err != nil {
-			t.Fatal("file must still exist")
-		}
-	})
-	t.Run("multi-hunk deletion verifies everything before removing", func(t *testing.T) {
-		root := t.TempDir()
-		writeTestFile(t, filepath.Join(root, "gone.txt"), "a\nb\nc\nd\n")
-		good := deletion("gone.txt", "@@ -1,2 +0,0 @@", "-a", "-b", "@@ -3,2 +0,0 @@", "-c", "-d")
-		bad := deletion("gone.txt", "@@ -1,2 +0,0 @@", "-a", "-b", "@@ -3,2 +0,0 @@", "-c", "-stale")
-		result := NewScopedApplyPatchTool(root, nil).Run(context.Background(), map[string]any{"patch": bad})
-		if result.Status == StatusOK {
-			t.Fatalf("deletion with one stale hunk must be refused: %s", result.Output)
-		}
-		if content, _ := os.ReadFile(filepath.Join(root, "gone.txt")); string(content) != "a\nb\nc\nd\n" {
-			t.Fatal("no hunk may be applied when any hunk is stale")
-		}
-		result = NewScopedApplyPatchTool(root, nil).Run(context.Background(), map[string]any{"patch": good})
-		if result.Status != StatusOK {
-			t.Fatalf("multi-hunk deletion should apply, got %s: %s", result.Status, result.Output)
-		}
-		if _, err := os.Stat(filepath.Join(root, "gone.txt")); !os.IsNotExist(err) {
-			t.Fatal("file must be deleted")
-		}
-	})
-	t.Run("structured delete stays unconditional", func(t *testing.T) {
-		root := t.TempDir()
-		writeTestFile(t, filepath.Join(root, "gone.txt"), "anything\n")
-		patch := "*** Begin Patch\n*** Delete File: gone.txt\n*** End Patch\n"
-		if result := NewScopedApplyPatchTool(root, nil).Run(context.Background(), map[string]any{"patch": patch}); result.Status != StatusOK {
-			t.Fatalf("structured delete should apply, got %s: %s", result.Status, result.Output)
-		}
-	})
-}
-
-// The source is re-read through the root immediately before commit, so a
-// change made after planning is refused instead of overwritten or removed.
-func TestApplyStructuredPatchChangeRefusesSourceChangedAfterPlanning(t *testing.T) {
-	root := t.TempDir()
-	path := filepath.Join(root, "file.txt")
-	writeTestFile(t, path, "planned\n")
-	workspace, err := os.OpenRoot(root)
-	if err != nil {
-		t.Fatal(err)
-	}
-	defer workspace.Close()
-	target := structuredPatchTarget{requested: "file.txt", absolute: path, relative: "file.txt"}
-	destination := structuredPatchTarget{requested: "copy.txt", absolute: filepath.Join(root, "copy.txt"), relative: "copy.txt"}
-	for name, change := range map[string]structuredPatchChange{
-		"update": {kind: structuredPatchUpdate, from: target, to: target, before: "planned\n", after: "new\n", mode: 0o644},
-		"delete": {kind: structuredPatchDelete, from: target, to: target, before: "planned\n", mode: 0o644},
-		"copy":   {kind: structuredPatchCopy, from: target, to: destination, before: "planned\n", after: "planned\n", mode: 0o644},
-	} {
-		writeTestFile(t, path, "changed after planning\n")
-		committed, err := applyStructuredPatchChange(workspace, change)
-		if err == nil || committed || !strings.Contains(err.Error(), "changed on disk between planning and commit") {
-			t.Fatalf("%s: expected a refusal, got committed=%v err=%v", name, committed, err)
-		}
-		if content, _ := os.ReadFile(path); string(content) != "changed after planning\n" {
-			t.Fatalf("%s: file must be untouched, got %q", name, string(content))
-		}
-		if _, statErr := os.Stat(filepath.Join(root, "copy.txt")); !os.IsNotExist(statErr) {
-			t.Fatalf("%s: refused change must not create copy.txt", name)
-		}
-	}
-}
-
-func TestUnifiedPatchDeletionIsByteExact(t *testing.T) {
-	deletion := func(hunks ...string) string {
-		return strings.Join(append(append([]string{"--- a/gone.txt", "+++ /dev/null"}, hunks...), ""), "\n")
-	}
-	for name, tc := range map[string]struct{ file, patch string }{
-		"trailing whitespace differs": {"current  \n", deletion("@@ -1 +0,0 @@", "-current")},
-		"indentation differs":         {"  current\n", deletion("@@ -1 +0,0 @@", "-current")},
-		"blank line not covered":      {"current\n\n", deletion("@@ -1 +0,0 @@", "-current")},
-		"space-only line not covered": {"current\n   \n", deletion("@@ -1 +0,0 @@", "-current")},
-		"missing final newline":       {"current", deletion("@@ -1 +0,0 @@", "-current")},
-	} {
-		t.Run(name, func(t *testing.T) {
-			root := t.TempDir()
-			writeTestFile(t, filepath.Join(root, "gone.txt"), tc.file)
-			result := NewScopedApplyPatchTool(root, nil).Run(context.Background(), map[string]any{"patch": tc.patch})
-			if result.Status == StatusOK {
-				t.Fatalf("deletion must be byte-exact; %q was deleted by a non-matching hunk", tc.file)
-			}
-			if content, _ := os.ReadFile(filepath.Join(root, "gone.txt")); string(content) != tc.file {
-				t.Fatalf("file must be unchanged, got %q", string(content))
-			}
-		})
-	}
-	t.Run("no-newline marker on the removed side matches exactly", func(t *testing.T) {
-		root := t.TempDir()
-		writeTestFile(t, filepath.Join(root, "gone.txt"), "current")
-		patch := deletion("@@ -1 +0,0 @@", "-current", "\\ No newline at end of file")
-		if result := NewScopedApplyPatchTool(root, nil).Run(context.Background(), map[string]any{"patch": patch}); result.Status != StatusOK {
-			t.Fatalf("deletion with a matching no-newline marker should apply, got %s: %s", result.Status, result.Output)
-		}
-		if _, err := os.Stat(filepath.Join(root, "gone.txt")); !os.IsNotExist(err) {
-			t.Fatal("file must be deleted")
-		}
-	})
-	t.Run("CRLF file matches an LF patch of the same content", func(t *testing.T) {
-		root := t.TempDir()
-		writeTestFile(t, filepath.Join(root, "gone.txt"), "a\r\nb\r\n")
-		if result := NewScopedApplyPatchTool(root, nil).Run(context.Background(), map[string]any{"patch": deletion("@@ -1,2 +0,0 @@", "-a", "-b")}); result.Status != StatusOK {
-			t.Fatalf("CRLF deletion should apply, got %s: %s", result.Status, result.Output)
-		}
-	})
-}
-
-// git describes an empty file's creation or deletion with header lines only.
-func TestUnifiedPatchHeaderOnlyEmptyFileForms(t *testing.T) {
-	root := t.TempDir()
-	writeTestFile(t, filepath.Join(root, "empty.txt"), "")
-	writeTestFile(t, filepath.Join(root, "full.txt"), "content\n")
-	writeTestFile(t, filepath.Join(root, "keep.txt"), "a\n")
-	deleteHeader := func(path string) string {
-		return "diff --git a/" + path + " b/" + path + "\ndeleted file mode 100644\nindex e69de29..0000000\n"
-	}
-	// A non-empty file is not deleted by the header-only form.
-	result := NewScopedApplyPatchTool(root, nil).Run(context.Background(), map[string]any{"patch": deleteHeader("full.txt")})
-	if result.Status == StatusOK || !strings.Contains(result.Output, "expects an empty file") {
-		t.Fatalf("header-only deletion of a non-empty file must be refused, got %s: %s", result.Status, result.Output)
-	}
-	if _, err := os.Stat(filepath.Join(root, "full.txt")); err != nil {
-		t.Fatal("non-empty file must still exist")
-	}
-	// In a multi-file patch the empty-file deletion and creation are applied
-	// alongside a normal hunk.
-	patch := deleteHeader("empty.txt") +
-		"diff --git a/blank.txt b/blank.txt\nnew file mode 100644\nindex 0000000..e69de29\n" +
-		"diff --git a/keep.txt b/keep.txt\n--- a/keep.txt\n+++ b/keep.txt\n@@ -1 +1 @@\n-a\n+b\n"
-	result = NewScopedApplyPatchTool(root, nil).Run(context.Background(), map[string]any{"patch": patch})
-	if result.Status != StatusOK {
-		t.Fatalf("multi-file patch with header-only forms should apply, got %s: %s", result.Status, result.Output)
-	}
-	if _, err := os.Stat(filepath.Join(root, "empty.txt")); !os.IsNotExist(err) {
-		t.Fatal("empty file must be deleted")
-	}
-	if content, err := os.ReadFile(filepath.Join(root, "blank.txt")); err != nil || len(content) != 0 {
-		t.Fatalf("empty file must be created, got err=%v content=%q", err, string(content))
-	}
-	if content, _ := os.ReadFile(filepath.Join(root, "keep.txt")); string(content) != "b\n" {
-		t.Fatalf("hunk file = %q", string(content))
-	}
-	if len(result.ChangedFiles) != 3 {
-		t.Fatalf("changed files = %v", result.ChangedFiles)
-	}
-}
-
-// When a later change fails, the error names exactly which files were already
-// committed so the caller knows what changed and what did not.
-func TestApplyPatchOperationsReportsCommittedPrefixOnFailure(t *testing.T) {
-	root := t.TempDir()
-	writeTestFile(t, filepath.Join(root, "first.txt"), "one\n")
-	writeTestFile(t, filepath.Join(root, "second.txt"), "two\n")
-	writeTestFile(t, filepath.Join(root, "third.txt"), "three\n")
-	// Make second.txt change after planning so its commit is refused.
-	structuredPatchBeforeCommit = func(change structuredPatchChange) {
-		if change.to.relative == "second.txt" {
-			writeTestFile(t, filepath.Join(root, "second.txt"), "changed\n")
-		}
-	}
-	defer func() { structuredPatchBeforeCommit = nil }()
-	patch := strings.Join([]string{
-		"*** Begin Patch",
-		"*** Update File: first.txt", "@@", "-one", "+ONE",
-		"*** Update File: second.txt", "@@", "-two", "+TWO",
-		"*** Update File: third.txt", "@@", "-three", "+THREE",
-		"*** End Patch", "",
-	}, "\n")
-	result := NewScopedApplyPatchTool(root, nil).Run(context.Background(), map[string]any{"patch": patch})
-	if result.Status == StatusOK {
-		t.Fatal("patch must fail when a later change is refused")
-	}
-	for _, want := range []string{"already committed: first.txt", "remaining files are unchanged"} {
-		if !strings.Contains(result.Output, want) {
-			t.Fatalf("error must report the committed prefix, got: %s", result.Output)
-		}
-	}
-	if strings.Contains(result.Output, "committed: first.txt, second.txt") || strings.Contains(result.Output, "third.txt") {
-		t.Fatalf("error must not list uncommitted files as committed: %s", result.Output)
-	}
-	if content, _ := os.ReadFile(filepath.Join(root, "first.txt")); string(content) != "ONE\n" {
-		t.Fatalf("first.txt must hold the committed change, got %q", string(content))
-	}
-	if content, _ := os.ReadFile(filepath.Join(root, "second.txt")); string(content) != "changed\n" {
-		t.Fatalf("second.txt must be untouched by the patch, got %q", string(content))
-	}
-	if content, _ := os.ReadFile(filepath.Join(root, "third.txt")); string(content) != "three\n" {
-		t.Fatalf("third.txt must be untouched, got %q", string(content))
-	}
-}

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, lineCount(updated), lineCount(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_tools_test.go

@@ -26,8 +26,8 @@ func TestReadFileToolReadsLineRanges(t *testing.T) {
 	}
 	for _, want := range []string{
 		"File: notes.txt (lines 2-3 of 4)",
-		"2→beta",
-		"3→gamma",
+		"2 | beta",
+		"3 | gamma",
 	} {
 		if !strings.Contains(result.Output, want) {
 			t.Fatalf("expected output to contain %q, got %q", want, result.Output)
@@ -54,7 +54,7 @@ func TestReadFileToolReadsCanonicalLineRange(t *testing.T) {
 	if result.Truncated {
 		t.Fatalf("canonical limit defines the requested range and must not mark it truncated: %#v", result.Meta)
 	}
-	if !strings.Contains(result.Output, "2→beta") || !strings.Contains(result.Output, "3→gamma") {
+	if !strings.Contains(result.Output, "2 | beta") || !strings.Contains(result.Output, "3 | gamma") {
 		t.Fatalf("canonical range returned the wrong lines: %q", result.Output)
 	}
 	if strings.Contains(result.Output, "alpha") || strings.Contains(result.Output, "delta") {
@@ -94,7 +94,7 @@ func TestReadFileToolMixedLegacyRangesPreferLines(t *testing.T) {
 	if result.Status != StatusOK {
 		t.Fatalf("mixed legacy range should recover, got %s: %s", result.Status, result.Output)
 	}
-	if !strings.Contains(result.Output, "2→beta") || !strings.Contains(result.Output, "3→gamma") {
+	if !strings.Contains(result.Output, "2 | beta") || !strings.Contains(result.Output, "3 | gamma") {
 		t.Fatalf("mixed legacy range did not prefer lines: %q", result.Output)
 	}
 }
@@ -110,7 +110,7 @@ func TestReadFileToolCombinesLegacyStartWithCanonicalLimit(t *testing.T) {
 	if result.Status != StatusOK || result.Truncated {
 		t.Fatalf("mixed compatible range should be exact, got status=%s truncated=%v: %s", result.Status, result.Truncated, result.Output)
 	}
-	if !strings.Contains(result.Output, "2→beta") || !strings.Contains(result.Output, "3→gamma") {
+	if !strings.Contains(result.Output, "2 | beta") || !strings.Contains(result.Output, "3 | gamma") {
 		t.Fatalf("mixed compatible range returned the wrong lines: %q", result.Output)
 	}
 	if strings.Contains(result.Output, "alpha") || strings.Contains(result.Output, "delta") {
@@ -955,7 +955,7 @@ func TestReadFileToolRecoversBackwardsRange(t *testing.T) {
 	for _, want := range []string{
 		"end_line 2 was before start_line 3", // the note
 		"only line 3 was read",
-		"3→gamma",
+		"3 | gamma",
 	} {
 		if !strings.Contains(result.Output, want) {
 			t.Fatalf("expected %q in output, got %q", want, result.Output)
@@ -984,7 +984,7 @@ func TestReadFileToolValidRangeUnchangedByRecovery(t *testing.T) {
 	// Byte-for-byte: header, blank separator, the exact selected lines, and no
 	// recovery note or trailing content. An altered header/separator or a stray
 	// out-of-range line would fail this where a substring check would not.
-	const want = "File: notes.txt (lines 2-4 of 5)\n\n2→beta\n3→gamma\n4→delta"
+	const want = "File: notes.txt (lines 2-4 of 5)\n\n2 | beta\n3 | gamma\n4 | delta"
 	if result.Output != want {
 		t.Fatalf("valid-range output changed by the recovery path:\n got: %q\nwant: %q", result.Output, 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/tools/local_browser.go

@@ -548,11 +548,11 @@ func browserActionArgs(args map[string]any) (string, []string, error) {
 	if err != nil {
 		return "", nil, err
 	}
-	command, ok := NormalizedBrowserActionCommand(command)
+	command = strings.ToLower(strings.TrimSpace(command))
+	spec, ok := browserActionSpecs[command]
 	if !ok {
 		return "", nil, fmt.Errorf("command must be one of: %s", strings.Join(browserActionCommandNames(), ", "))
 	}
-	spec := browserActionSpecs[command]
 	values, err := stringArrayArg(args, "args")
 	if err != nil {
 		return "", nil, err
@@ -570,16 +570,6 @@ func browserActionArgs(args map[string]any) (string, []string, error) {
 	return command, commandArgs, nil
 }
 
-// NormalizedBrowserActionCommand returns the exact action that browser_action
-// will execute after normalizing its command argument. ACP uses it only for a
-// permission title, so an unrecognised command is never reflected as text that
-// the tool would reject.
-func NormalizedBrowserActionCommand(command string) (string, bool) {
-	command = strings.ToLower(strings.TrimSpace(command))
-	_, ok := browserActionSpecs[command]
-	return command, ok
-}
-
 func browserActionCommandArgs(command string, spec browserActionSpec, values []string) ([]string, error) {
 	switch command {
 	case "connect":
@@ -667,13 +657,6 @@ func browserOpenURLArg(args map[string]any) (string, error) {
 	if err != nil {
 		return "", err
 	}
-	return NormalizeBrowserOpenURL(rawURL)
-}
-
-// NormalizeBrowserOpenURL applies the browser_open URL rules before execution.
-// Keeping this exported within the internal package lets permission displays
-// describe the same destination the browser helper will open.
-func NormalizeBrowserOpenURL(rawURL string) (string, error) {
 	normalized := strings.TrimSpace(rawURL)
 	if !strings.Contains(normalized, "://") {
 		normalized = "https://" + normalized

internal/tools/model_visibility.go

@@ -1,11 +1,9 @@
 package tools
 
 // ModelVisible reports whether a registered tool is advertised to an agent.
-// Every registered tool is visible. edit_file (exact search/replace with a
-// uniqueness guard, CRLF and fuzzy fallbacks) was hidden for a while in favour
-// of apply_patch; head-to-head benchmarking showed that when a model misses the
-// patch grammar it degrades to whole-file rewrites, so both edit tools are
-// advertised and the prompt steers between them.
+// edit_file remains implemented for compatibility with existing integrations,
+// but its text-only replacement contract cannot safely disambiguate repeated
+// source fragments. Agents use apply_patch for contextual existing-file edits.
 func ModelVisible(tool Tool) bool {
-	return tool != nil
+	return tool != nil && tool.Name() != "edit_file"
 }

internal/tools/model_visibility_test.go

@@ -2,28 +2,17 @@ package tools
 
 import "testing"
 
-func TestToolSearchSurfacesBothEditTools(t *testing.T) {
+func TestToolSearchDoesNotSurfaceLegacyStringReplacement(t *testing.T) {
 	registry := NewRegistry()
 	registry.Register(NewScopedEditFileTool(t.TempDir(), nil))
 	registry.Register(NewScopedApplyPatchTool(t.TempDir(), nil))
 	search := NewToolSearchTool(registry).(toolSearchTool)
 
 	eager := search.visibleEagerToolNames(nil, nil, "ask")
-	if !eager["edit_file"] {
-		t.Fatal("tool_search must describe edit_file as available to the model")
+	if eager["edit_file"] {
+		t.Fatal("tool_search must not describe edit_file as available to the model")
 	}
 	if !eager["apply_patch"] {
-		t.Fatal("tool_search must retain apply_patch as an available edit tool")
-	}
-}
-
-func TestModelVisibleAdvertisesEveryRegisteredTool(t *testing.T) {
-	if ModelVisible(nil) {
-		t.Fatal("a nil tool must not be visible")
-	}
-	for _, tool := range []Tool{NewScopedEditFileTool(t.TempDir(), nil), NewScopedApplyPatchTool(t.TempDir(), nil), NewScopedWriteFileTool(t.TempDir(), nil)} {
-		if !ModelVisible(tool) {
-			t.Fatalf("%s must be visible to the model", tool.Name())
-		}
+		t.Fatal("tool_search must retain apply_patch as the available edit tool")
 	}
 }

internal/tools/plan_tool_test.go

@@ -9,9 +9,6 @@ import (
 
 func TestUpdatePlanToolStoresAndFormatsPlan(t *testing.T) {
 	tool := NewUpdatePlanTool()
-	if description := strings.ToLower(tool.Description()); !strings.Contains(description, "skip it for bounded changes in one component") {
-		t.Fatalf("update_plan description must preserve the bounded-task fast path: %q", description)
-	}
 
 	result := tool.Run(context.Background(), map[string]any{
 		"plan": []any{

internal/tools/read_file.go

@@ -9,14 +9,12 @@ import (
 	"io"
 	"os"
 	"strconv"
+	"strings"
 	"unicode/utf8"
 )
 
 const readFileByteChunkMax = 64 * 1024
 
-// readFileLinePrefixSeparator follows the line number on every read_file line.
-const readFileLinePrefixSeparator = "→"
-
 type readFileTool struct {
 	baseTool
 	workspaceRoot string
@@ -33,7 +31,7 @@ func NewScopedReadFileTool(workspaceRoot string, scope PathScope) Tool {
 	return readFileTool{
 		baseTool: baseTool{
 			name:        "read_file",
-			description: "Read exact file text, each line prefixed with its line number and →. Use directly for small files likely to be edited, or when comments, formatting, or line numbers matter. Prefer read_minified_file only for exploratory understanding of large or unfamiliar code. Use offset and limit for a line range.",
+			description: "Read exact file text with line numbers. Use for comments, formatting, or edits; prefer read_minified_file for initial code understanding. Use offset and limit for a line range.",
 			parameters: Schema{
 				Type: "object",
 				Properties: map[string]PropertySchema{
@@ -223,6 +221,7 @@ func renderReadFileRange(absolutePath string, relativePath string, total int, st
 	}
 
 	lastLine := startLine + selectedLines - 1
+	width := len(strconv.Itoa(lastLine))
 	header := fmt.Sprintf("File: %s (%d lines)", relativePath, total)
 	if startLine != 1 || endLine != total || maxLines > 0 {
 		header = fmt.Sprintf("File: %s (lines %d-%d of %d)", relativePath, startLine, lastLine, total)
@@ -245,7 +244,7 @@ func renderReadFileRange(absolutePath string, relativePath string, total int, st
 		budgetedOutput.WriteString("\n")
 	}
 	budgetedOutput.WriteString("\n")
-	if err := appendReadFileRange(budgetedOutput, absolutePath, startLine, selectedLines); err != nil {
+	if err := appendReadFileRange(budgetedOutput, absolutePath, startLine, selectedLines, width); err != nil {
 		return errorResult("Error reading file " + relativePath + ": " + err.Error())
 	}
 	if truncated {
@@ -358,7 +357,7 @@ func renderReadFileBytes(path, relativePath string, total, requestedStart, limit
 	return Result{Status: StatusOK, Output: output, Meta: map[string]string{"next_byte_offset": strconv.Itoa(end)}}, start, end
 }
 
-func appendReadFileRange(output *outputBudgetBuilder, path string, startLine int, selectedLines int) error {
+func appendReadFileRange(output *outputBudgetBuilder, path string, startLine int, selectedLines int, width int) error {
 	file, err := os.Open(path)
 	if err != nil {
 		return err
@@ -381,11 +380,10 @@ func appendReadFileRange(output *outputBudgetBuilder, path string, startLine int
 			if emitted > 0 {
 				output.WriteString("\n")
 			}
-			// Compact "N→" prefix: the padded "  N | " form cost ~19% of every
-			// read (about 1.5k tokens per 800-line file) and was re-sent on each
-			// later call; no consumer parses it, and models read "N→" natively.
-			output.WriteString(strconv.Itoa(lineNumber))
-			output.WriteString(readFileLinePrefixSeparator)
+			number := strconv.Itoa(lineNumber)
+			output.WriteString(strings.Repeat(" ", width-len(number)))
+			output.WriteString(number)
+			output.WriteString(" | ")
 			output.WriteString(string(trimLineBreak(raw, ended)))
 			emitted++
 		}

internal/tools/read_minified_file.go

@@ -28,7 +28,7 @@ func NewScopedReadMinifiedFileTool(workspaceRoot string, scope PathScope) Tool {
 	return readMinifiedFileTool{
 		baseTool: baseTool{
 			name:        "read_minified_file",
-			description: "Read source code in a token-efficient, language-aware form. Use for exploratory understanding of large or unfamiliar source when no exact edit is planned; use read_file directly for likely edit targets. Do not immediately reread the same file exactly unless a new need for exact text or line numbers appears.",
+			description: "Read source code in a token-efficient, language-aware form. Prefer this for initial understanding; use read_file for exact text or line numbers.",
 			parameters: Schema{
 				Type: "object",
 				Properties: map[string]PropertySchema{
@@ -171,9 +171,14 @@ func selectSourceLines(content []byte, offset, limit int) sourceSelection {
 }
 
 func sourceLineCount(content []byte) int {
-	// One implementation for reader and writer: the tracker contract lives on
-	// trackedLineTotal, and this must never drift from it.
-	return trackedLineTotal(string(content))
+	if len(content) == 0 {
+		return 1
+	}
+	lines := strings.Count(string(content), "\n")
+	if content[len(content)-1] != '\n' {
+		lines++
+	}
+	return lines
 }
 
 // lineCount reports the number of newline-separated lines in s (an empty string
@@ -184,20 +189,3 @@ func lineCount(s string) int {
 	}
 	return strings.Count(s, "\n") + 1
 }
-
-// trackedLineTotal reports a file's line count the way read_file reports it
-// to the FileTracker (newline-terminated lines, plus an unterminated last
-// line; an empty file is one line). Writers must record this same number:
-// RecordSeenRange resets every observation when the total changes, so a
-// writer that recorded lineCount (one higher for a trailing newline) made the
-// next partial read_file wipe whole-file knowledge and refuse the next edit.
-func trackedLineTotal(s string) int {
-	if s == "" {
-		return 1
-	}
-	total := strings.Count(s, "\n")
-	if !strings.HasSuffix(s, "\n") {
-		total++
-	}
-	return total
-}

internal/tools/read_minified_file_test.go

@@ -8,29 +8,6 @@ import (
 	"testing"
 )
 
-func TestReadToolsDescribeExploratoryAndExactUseWithoutRedundantRereads(t *testing.T) {
-	root := t.TempDir()
-	minified := strings.ToLower(NewScopedReadMinifiedFileTool(root, nil).Description())
-	for _, want := range []string{
-		"exploratory understanding",
-		"use read_file directly for likely edit targets",
-		"unless a new need for exact text or line numbers appears",
-	} {
-		if !strings.Contains(minified, want) {
-			t.Fatalf("read_minified_file description missing %q: %s", want, minified)
-		}
-	}
-	exact := strings.ToLower(NewScopedReadFileTool(root, nil).Description())
-	for _, want := range []string{
-		"use directly for small files likely to be edited",
-		"prefer read_minified_file only for exploratory understanding",
-	} {
-		if !strings.Contains(exact, want) {
-			t.Fatalf("read_file description missing %q: %s", want, exact)
-		}
-	}
-}
-
 func TestReadMinifiedFileStripsCommentsAndLineNumbers(t *testing.T) {
 	dir := t.TempDir()
 	src := "package demo\n\nimport \"fmt\"\n\n// secret doc comment\nfunc F() { fmt.Println(\"x\") }\n"

internal/tools/registry.go

@@ -5,7 +5,6 @@ import (
 	"fmt"
 	"sort"
 	"strings"
-	"sync"
 
 	"github.com/Gitlawb/zero/internal/redaction"
 	"github.com/Gitlawb/zero/internal/sandbox"
@@ -13,17 +12,7 @@ import (
 )
 
 type Registry struct {
-	mu         sync.RWMutex
-	tools      map[string]Tool
-	generation uint64
-}
-
-// RegistrySnapshot is one immutable registry generation. Tools is a detached,
-// name-sorted slice: later registrations cannot change the snapshot observed by
-// an in-flight agent turn.
-type RegistrySnapshot struct {
-	Tools      []Tool
-	Generation uint64
+	tools map[string]Tool
 }
 
 type RunOptions struct {
@@ -118,69 +107,23 @@ func IsDeferralEligible(t Tool) bool {
 }
 
 func (registry *Registry) Register(tool Tool) {
-	registry.mu.Lock()
-	defer registry.mu.Unlock()
 	registry.tools[tool.Name()] = tool
-	registry.generation++
-}
-
-// RegisterBatch publishes a group of tools as one registry generation. Readers
-// observe either the complete prior generation or the complete new one.
-func (registry *Registry) RegisterBatch(batch []Tool) {
-	if len(batch) == 0 {
-		return
-	}
-	registry.mu.Lock()
-	defer registry.mu.Unlock()
-	for _, tool := range batch {
-		registry.tools[tool.Name()] = tool
-	}
-	registry.generation++
 }
 
 func (registry *Registry) Get(name string) (Tool, bool) {
-	registry.mu.RLock()
-	defer registry.mu.RUnlock()
 	tool, ok := registry.tools[name]
 	return tool, ok
 }
 
 func (registry *Registry) All() []Tool {
-	return registry.Snapshot().Tools
-}
-
-// Snapshot returns a stable, sorted view of the registry at one generation.
-func (registry *Registry) Snapshot() RegistrySnapshot {
-	registry.mu.RLock()
 	tools := make([]Tool, 0, len(registry.tools))
 	for _, tool := range registry.tools {
 		tools = append(tools, tool)
 	}
-	generation := registry.generation
-	registry.mu.RUnlock()
 	sort.Slice(tools, func(left, right int) bool {
 		return tools[left].Name() < tools[right].Name()
 	})
-	return RegistrySnapshot{Tools: tools, Generation: generation}
-}
-
-// Clone returns an independent registry containing exactly one source snapshot.
-func (registry *Registry) Clone() *Registry {
-	clone := NewRegistry()
-	if registry == nil {
-		return clone
-	}
-	snapshot := registry.Snapshot()
-	clonedTools := make([]Tool, 0, len(snapshot.Tools))
-	for _, tool := range snapshot.Tools {
-		if cloner, ok := tool.(interface{ cloneForRegistry(*Registry) Tool }); ok {
-			tool = cloner.cloneForRegistry(clone)
-		}
-		clonedTools = append(clonedTools, tool)
-	}
-	clone.RegisterBatch(clonedTools)
-	clone.generation = snapshot.Generation
-	return clone
+	return tools
 }
 
 func (registry *Registry) Run(ctx context.Context, name string, args map[string]any) Result {

internal/tools/registry_test.go

@@ -2,12 +2,10 @@ package tools
 
 import (
 	"context"
-	"fmt"
 	"os"
 	"path/filepath"
 	"slices"
 	"strings"
-	"sync"
 	"testing"
 
 	"github.com/Gitlawb/zero/internal/sandbox"
@@ -97,81 +95,6 @@ func TestRegistryAllReturnsToolsSortedByName(t *testing.T) {
 	}
 }
 
-func TestRegistrySnapshotAndCloneStayOnOneGeneration(t *testing.T) {
-	registry := NewRegistry()
-	registry.Register(fakePlainTool{baseTool: baseTool{name: "alpha", description: "alpha"}})
-	first := registry.Snapshot()
-
-	registry.RegisterBatch([]Tool{
-		fakePlainTool{baseTool: baseTool{name: "charlie", description: "charlie"}},
-		fakePlainTool{baseTool: baseTool{name: "bravo", description: "bravo"}},
-	})
-	second := registry.Snapshot()
-	clone := registry.Clone()
-	registry.Register(fakePlainTool{baseTool: baseTool{name: "delta", description: "delta"}})
-
-	if got := toolNames(first.Tools); !slices.Equal(got, []string{"alpha"}) {
-		t.Fatalf("first snapshot changed after registration: %v", got)
-	}
-	if second.Generation != first.Generation+1 {
-		t.Fatalf("batch generation = %d, want %d", second.Generation, first.Generation+1)
-	}
-	if got := toolNames(second.Tools); !slices.Equal(got, []string{"alpha", "bravo", "charlie"}) {
-		t.Fatalf("second snapshot tools = %v", got)
-	}
-	if got := toolNames(clone.All()); !slices.Equal(got, toolNames(second.Tools)) {
-		t.Fatalf("clone changed with source registry: %v", got)
-	}
-	if clone.Snapshot().Generation != second.Generation {
-		t.Fatalf("clone generation = %d, want %d", clone.Snapshot().Generation, second.Generation)
-	}
-}
-
-func TestRegistryBatchIsAtomicForConcurrentReaders(t *testing.T) {
-	registry := NewRegistry()
-	registry.Register(fakePlainTool{baseTool: baseTool{name: "base", description: "base"}})
-	batch := make([]Tool, 128)
-	for index := range batch {
-		name := fmt.Sprintf("tool_%03d", index)
-		batch[index] = fakePlainTool{baseTool: baseTool{name: name, description: name}}
-	}
-
-	start := make(chan struct{})
-	done := make(chan struct{})
-	var readers sync.WaitGroup
-	for range 4 {
-		readers.Add(1)
-		go func() {
-			defer readers.Done()
-			<-start
-			for {
-				count := len(registry.Snapshot().Tools)
-				if count != 1 && count != len(batch)+1 {
-					t.Errorf("reader observed partial batch with %d tools", count)
-					return
-				}
-				select {
-				case <-done:
-					return
-				default:
-				}
-			}
-		}()
-	}
-	close(start)
-	registry.RegisterBatch(batch)
-	close(done)
-	readers.Wait()
-}
-
-func toolNames(toolset []Tool) []string {
-	names := make([]string, 0, len(toolset))
-	for _, tool := range toolset {
-		names = append(names, tool.Name())
-	}
-	return names
-}
-
 func TestCoreNetworkToolsExposeSafetyMetadata(t *testing.T) {
 	// web_search is only registered when a backend is configured.
 	t.Setenv("ZERO_WEBSEARCH_BASE_URL", "https://search.example/api")

internal/tools/structured_patch.go

@@ -6,11 +6,9 @@ import (
 	"io"
 	"os"
 	"path/filepath"
-	"regexp"
 	"strings"
 
 	"github.com/Gitlawb/zero/internal/pathjail"
-	"github.com/Gitlawb/zero/internal/sandbox"
 )
 
 const (
@@ -30,9 +28,6 @@ const (
 	structuredPatchAdd structuredPatchKind = iota
 	structuredPatchDelete
 	structuredPatchUpdate
-	// structuredPatchCopy creates movePath from path's content (plus any
-	// hunks) and keeps path; produced by a unified diff's "copy from/to".
-	structuredPatchCopy
 )
 
 type structuredPatchOperation struct {
@@ -42,29 +37,8 @@ type structuredPatchOperation struct {
 	contents string
 	chunks   []structuredPatchChunk
 	line     int
-	// eofNewline lets a unified diff's "\ No newline at end of file" marker
-	// force the trailing-newline state of the result; structured patches keep
-	// the file's existing state.
-	eofNewline eofNewlineMode
-	// verifyDelete marks a deletion that carries the expected old content
-	// (a unified diff's "+++ /dev/null" hunks, or git's header-only form for
-	// an empty file): the removed lines must equal the current file byte for
-	// byte, otherwise the deletion is stale and refused. A structured
-	// "*** Delete File" means "delete this path" and has no chunks.
-	verifyDelete bool
-	// oldNoNewline records a unified diff's "\ No newline at end of file"
-	// on the removed side, i.e. the old content did not end with a newline.
-	oldNoNewline bool
 }
 
-type eofNewlineMode uint8
-
-const (
-	eofNewlineKeep eofNewlineMode = iota
-	eofNewlinePresent
-	eofNewlineAbsent
-)
-
 type structuredPatchChunk struct {
 	context          string
 	hasContext       bool
@@ -72,11 +46,6 @@ type structuredPatchChunk struct {
 	new              []string
 	newSourceOffsets []int
 	endOfFile        bool
-	// hint is the 0-based line the hunk is expected at (from a unified diff's
-	// "@@ -a,b" range). When the expected lines match there it is used as-is;
-	// otherwise the hunk is located by content like a structured hunk.
-	hint    int
-	hasHint bool
 }
 
 type structuredPatchTarget struct {
@@ -94,36 +63,8 @@ type structuredPatchChange struct {
 	mode   os.FileMode
 }
 
-// unifiedHunkRangePattern recognises a unified-diff range header ("-12,4 +12,6",
-// optionally followed by "@@ heading") written inside a structured hunk marker.
-// The line numbers carry no information for the context-anchored grammar, so
-// the range is dropped and only an explicit heading is kept as the anchor.
-var unifiedHunkRangePattern = regexp.MustCompile(`^-\d+(?:,\d+)?\s+\+\d+(?:,\d+)?\s*(?:@@\s*(.*))?$`)
-
-const structuredPatchFormatHint = ` (format: "*** Begin Patch", then "*** Update File: path" / "*** Add File: path" / "*** Delete File: path" sections whose hunks start with "@@" and use " " context, "-" removed and "+" added lines, then "*** End Patch")`
-
-// structuredPatchMarker classifies a line as the "begin" or "end" marker of a
-// structured patch, or "" when it is neither. The classifier is owned by the
-// sandbox package so the boundary check and the tool accept exactly the same
-// spellings; a strict byte-equal match here once made every patch from some
-// models fail on line 1 and pushed them into whole-file rewrites.
-func structuredPatchMarker(line string) string {
-	return sandbox.StructuredPatchMarker(line)
-}
-
-// structuredHunkAnchor normalises the text after a hunk's "@@ " marker. A
-// unified-diff range is dropped (its optional heading survives as the anchor);
-// anything else is used verbatim.
-func structuredHunkAnchor(context string) string {
-	context = strings.TrimSpace(context)
-	if match := unifiedHunkRangePattern.FindStringSubmatch(context); match != nil {
-		return strings.TrimSpace(match[1])
-	}
-	return context
-}
-
 func isStructuredPatch(patch string) bool {
-	return sandbox.IsStructuredPatch(patch)
+	return strings.HasPrefix(strings.TrimSpace(strings.TrimPrefix(patch, "\ufeff")), structuredPatchBegin)
 }
 
 func (tool applyPatchTool) runStructuredPatch(applyRoot, relativeRoot, patch string, options RunOptions) Result {
@@ -131,14 +72,6 @@ func (tool applyPatchTool) runStructuredPatch(applyRoot, relativeRoot, patch str
 	if err != nil {
 		return errorResult("Error applying patch: " + err.Error())
 	}
-	return applyPatchOperations(applyRoot, relativeRoot, operations, options)
-}
-
-// applyPatchOperations applies parsed operations (from either patch format)
-// through an opened workspace root: every stat, read, create and write is
-// descriptor-relative and refuses to follow a link out of the root, so there
-// is no pathname check-to-use window between validation and write.
-func applyPatchOperations(applyRoot, relativeRoot string, operations []structuredPatchOperation, options RunOptions) Result {
 	workspace, err := os.OpenRoot(applyRoot)
 	if err != nil {
 		return errorResult("Error applying patch: " + err.Error())
@@ -151,7 +84,7 @@ func applyPatchOperations(applyRoot, relativeRoot string, operations []structure
 	wholeBefore := make(map[string]bool, len(changes))
 	if options.FileTracker != nil {
 		for _, change := range changes {
-			if change.kind == structuredPatchUpdate || change.kind == structuredPatchCopy {
+			if change.kind == structuredPatchUpdate {
 				wholeBefore[change.from.absolute] = options.FileTracker.SeenWhole(change.from.absolute)
 			}
 		}
@@ -170,10 +103,6 @@ func applyPatchOperations(applyRoot, relativeRoot string, operations []structure
 			wasWhole := wholeBefore[change.from.absolute]
 			options.FileTracker.Forget(change.from.absolute)
 			recordStructuredPatchFile(options.FileTracker, change.to.absolute, false, wasWhole)
-		case structuredPatchCopy:
-			// The source is untouched; the destination inherits only what the
-			// model had actually seen of the source.
-			recordStructuredPatchFile(options.FileTracker, change.to.absolute, true, wholeBefore[change.from.absolute])
 		}
 	}
 
@@ -193,11 +122,11 @@ func parseStructuredPatch(patch string) ([]structuredPatchOperation, error) {
 		return nil, fmt.Errorf("structured patch is empty")
 	}
 	lines := strings.Split(normalized, "\n")
-	if structuredPatchMarker(lines[0]) != "begin" {
-		return nil, fmt.Errorf("the first line of a structured patch must be %q%s", structuredPatchBegin, structuredPatchFormatHint)
+	if strings.TrimSpace(lines[0]) != structuredPatchBegin {
+		return nil, fmt.Errorf("the first line of a structured patch must be %q", structuredPatchBegin)
 	}
-	if structuredPatchMarker(lines[len(lines)-1]) != "end" {
-		return nil, fmt.Errorf("the last line of a structured patch must be %q%s", structuredPatchEnd, structuredPatchFormatHint)
+	if strings.TrimSpace(lines[len(lines)-1]) != structuredPatchEnd {
+		return nil, fmt.Errorf("the last line of a structured patch must be %q", structuredPatchEnd)
 	}
 
 	var operations []structuredPatchOperation
@@ -262,12 +191,8 @@ func parseStructuredPatch(patch string) ([]structuredPatchOperation, error) {
 				}
 				if trimmed == "@@" || strings.HasPrefix(trimmed, structuredHunkContext) {
 					chunk := structuredPatchChunk{}
-					rest := ""
 					if trimmed != "@@" {
-						rest = strings.TrimPrefix(trimmed, structuredHunkContext)
-					}
-					if anchor := structuredHunkAnchor(rest); anchor != "" {
-						chunk.context = anchor
+						chunk.context = strings.TrimPrefix(trimmed, structuredHunkContext)
 						chunk.hasContext = true
 					}
 					op.chunks = append(op.chunks, chunk)
@@ -323,7 +248,7 @@ func structuredPatchPath(header, prefix string, line int) (string, error) {
 }
 
 func isStructuredPatchHeader(line string) bool {
-	return structuredPatchMarker(line) == "end" || strings.HasPrefix(line, structuredAddFile) || strings.HasPrefix(line, structuredDeleteFile) || strings.HasPrefix(line, structuredUpdateFile)
+	return line == structuredPatchEnd || strings.HasPrefix(line, structuredAddFile) || strings.HasPrefix(line, structuredDeleteFile) || strings.HasPrefix(line, structuredUpdateFile)
 }
 
 func structuredPatchLineError(line int, message string) error {
@@ -393,7 +318,7 @@ func planStructuredPatch(root *os.Root, operations []structuredPatchOperation, t
 				return nil, err
 			}
 			change.after = operation.contents
-		case structuredPatchDelete, structuredPatchUpdate, structuredPatchCopy:
+		case structuredPatchDelete, structuredPatchUpdate:
 			info, err := root.Stat(from.relative)
 			if err != nil {
 				return nil, fmt.Errorf("stating %s: %w", from.relative, err)
@@ -407,20 +332,12 @@ func planStructuredPatch(root *os.Root, operations []structuredPatchOperation, t
 				return nil, fmt.Errorf("%s", fileConflictMessage(from.relative))
 			}
 			change.before = string(content)
-			if operation.kind == structuredPatchDelete && operation.verifyDelete {
-				if err := verifyUnifiedDeletion(change.before, from.relative, operation); err != nil {
-					return nil, err
-				}
-			}
-			if operation.kind == structuredPatchUpdate || operation.kind == structuredPatchCopy {
+			if operation.kind == structuredPatchUpdate {
 				updated, err := applyStructuredPatchUpdate(change.before, from.relative, operation.chunks)
 				if err != nil {
 					return nil, err
 				}
-				change.after = applyEOFNewline(updated, operation.eofNewline)
-				if operation.kind == structuredPatchCopy && from.absolute == to.absolute {
-					return nil, fmt.Errorf("cannot copy %s onto itself", from.relative)
-				}
+				change.after = updated
 				if from.absolute != to.absolute {
 					if _, err := root.Lstat(to.relative); err == nil {
 						return nil, fmt.Errorf("cannot move %s to %s because the destination already exists", from.relative, to.relative)
@@ -436,14 +353,10 @@ func planStructuredPatch(root *os.Root, operations []structuredPatchOperation, t
 }
 
 func resolveStructuredPatchTarget(root, path string) (structuredPatchTarget, error) {
-	// Relative traversal is rejected outright. An absolute path is allowed when
-	// it resolves inside the apply root (models routinely echo the absolute path
-	// they were shown by read_file); resolveWorkspaceTargetPath rejects anything
-	// that lands outside.
-	if path == ".." || strings.HasPrefix(filepath.ToSlash(path), "../") {
+	if filepath.IsAbs(path) || path == ".." || strings.HasPrefix(filepath.ToSlash(path), "../") {
 		return structuredPatchTarget{}, fmt.Errorf("patch path %q must stay inside the workspace", path)
 	}
-	absolute, relative, err := resolveWorkspaceTargetPath(root, normalizePatchPathForRoot(root, path))
+	absolute, relative, err := resolveWorkspaceTargetPath(root, path)
 	if err != nil {
 		return structuredPatchTarget{}, err
 	}
@@ -476,15 +389,9 @@ func applyStructuredPatchUpdate(content, path string, chunks []structuredPatchCh
 		if len(chunk.old) == 0 {
 			// A context anchor identifies the line immediately before a pure
 			// insertion. Only an explicit end-of-file hunk (or an unanchored
-			// insertion) belongs at the file end. A unified diff names the
-			// insertion point in its range instead; a zero-context hunk (as
-			// from `git diff -U0`) has nothing to verify the position against,
-			// so it is position-trusting by design — the same semantics git
-			// apply uses without fuzz. Hunks that carry context are verified.
+			// insertion) belongs at the file end.
 			start := lineIndex
-			if chunk.hasHint {
-				start = max(chunk.hint, lineIndex)
-			} else if chunk.endOfFile || !chunk.hasContext {
+			if chunk.endOfFile || !chunk.hasContext {
 				start = len(lines)
 			}
 			if start > len(lines) {
@@ -498,13 +405,7 @@ func applyStructuredPatchUpdate(content, path string, chunks []structuredPatchCh
 			lineIndex = start
 			continue
 		}
-		var index int
-		ambiguous := false
-		if chunk.hasHint && chunk.hint >= lineIndex && sequenceMatchesAt(lines, chunk.old, chunk.hint) {
-			index = chunk.hint
-		} else {
-			index, ambiguous = findStructuredPatchSequence(lines, chunk.old, lineIndex, chunk.endOfFile)
-		}
+		index, ambiguous := findStructuredPatchSequence(lines, chunk.old, lineIndex, chunk.endOfFile)
 		if ambiguous {
 			return "", fmt.Errorf("expected lines are ambiguous in %s; provide more surrounding context:\n%s", path, strings.Join(chunk.old, "\n"))
 		}
@@ -539,64 +440,6 @@ func applyStructuredPatchUpdate(content, path string, chunks []structuredPatchCh
 	return updated, nil
 }
 
-// verifyUnifiedDeletion checks, byte for byte, that the lines a unified
-// deletion removes are exactly the file's current content. A deletion is not
-// recoverable, so none of the whitespace tolerance used to locate update
-// hunks applies here; only the file's own line-ending style is normalised.
-// With no hunks (git's header-only form) the file must be empty.
-func verifyUnifiedDeletion(current, path string, operation structuredPatchOperation) error {
-	var removed []string
-	for _, chunk := range operation.chunks {
-		if len(chunk.new) > 0 {
-			return fmt.Errorf("deletion of %s must not add lines", path)
-		}
-		removed = append(removed, chunk.old...)
-	}
-	expected := strings.Join(removed, "\n")
-	if len(removed) > 0 && !operation.oldNoNewline {
-		expected += "\n"
-	}
-	actual := current
-	if structuredPatchLineEnding(current) == "\r\n" {
-		actual = strings.ReplaceAll(current, "\r\n", "\n")
-	}
-	if actual != expected {
-		if len(removed) == 0 {
-			return fmt.Errorf("deletion of %s expects an empty file but it has content; include the removed lines in the patch", path)
-		}
-		return fmt.Errorf("deletion of %s does not match its current content; the removed lines must equal the whole file", path)
-	}
-	return nil
-}
-
-// sequenceMatchesAt reports whether wanted appears verbatim at lines[start:].
-func sequenceMatchesAt(lines, wanted []string, start int) bool {
-	if start < 0 || start+len(wanted) > len(lines) {
-		return false
-	}
-	for offset, line := range wanted {
-		if lines[start+offset] != line {
-			return false
-		}
-	}
-	return true
-}
-
-// applyEOFNewline forces or strips a single trailing line ending when a
-// unified diff's end-of-file marker asked for it.
-func applyEOFNewline(content string, mode eofNewlineMode) string {
-	switch mode {
-	case eofNewlinePresent:
-		if content != "" && !strings.HasSuffix(content, "\n") {
-			return content + structuredPatchLineEnding(content)
-		}
-	case eofNewlineAbsent:
-		content = strings.TrimSuffix(content, "\n")
-		content = strings.TrimSuffix(content, "\r")
-	}
-	return content
-}
-
 func structuredPatchReplacement(chunk structuredPatchChunk, source []string, start int) ([]string, error) {
 	if len(chunk.newSourceOffsets) != len(chunk.new) {
 		return nil, fmt.Errorf("context mapping has %d entries for %d output lines", len(chunk.newSourceOffsets), len(chunk.new))
@@ -673,19 +516,14 @@ func findStructuredPatchSequence(lines, wanted []string, start int, endOfFile bo
 }
 
 func applyStructuredPatchChanges(root *os.Root, changes []structuredPatchChange, tracker *FileTracker) error {
-	// committed lists, in order, the paths whose change reached disk before a
-	// later change failed, so the caller (and the model) knows exactly which
-	// files now hold the patched content and which were never touched.
-	var committed []string
+	mutated := false
 	for _, change := range changes {
-		done, err := applyStructuredPatchChange(root, change)
-		if done {
-			committed = append(committed, structuredPatchChangePaths(change)...)
-		}
+		committed, err := applyStructuredPatchChange(root, change)
+		mutated = mutated || committed
 		if err != nil {
 			forgetStructuredPatchFiles(tracker, changes)
-			if len(committed) > 0 {
-				return fmt.Errorf("%w; patch was partially applied — already committed: %s; the remaining files are unchanged; re-read the committed files before retrying", err, strings.Join(committed, ", "))
+			if mutated {
+				return fmt.Errorf("%w; structured patch was partially applied; re-read affected files before retrying", err)
 			}
 			return err
 		}
@@ -693,19 +531,6 @@ func applyStructuredPatchChanges(root *os.Root, changes []structuredPatchChange,
 	return nil
 }
 
-// structuredPatchChangePaths names the workspace-relative paths a committed
-// change touched: the destination, plus the source of a move or copy.
-func structuredPatchChangePaths(change structuredPatchChange) []string {
-	if change.kind == structuredPatchDelete {
-		return []string{change.from.relative}
-	}
-	paths := []string{change.to.relative}
-	if change.from.absolute != change.to.absolute && change.from.relative != "" {
-		paths = append([]string{change.from.relative}, paths...)
-	}
-	return paths
-}
-
 func forgetStructuredPatchFiles(tracker *FileTracker, changes []structuredPatchChange) {
 	if tracker == nil {
 		return
@@ -718,35 +543,14 @@ func forgetStructuredPatchFiles(tracker *FileTracker, changes []structuredPatchC
 	}
 }
 
-// structuredPatchBeforeCommit, when set, runs before each change's pre-commit
-// recheck. Tests use it to alter the filesystem between planning and commit
-// deterministically; it is nil in production.
-var structuredPatchBeforeCommit func(change structuredPatchChange)
-
 func applyStructuredPatchChange(root *os.Root, change structuredPatchChange) (bool, error) {
-	if structuredPatchBeforeCommit != nil {
-		structuredPatchBeforeCommit(change)
-	}
-	// The planner validated the source against the bytes it read; re-read
-	// through the same root immediately before committing so a change made
-	// by another process in between is refused rather than overwritten or
-	// removed.
-	if change.kind != structuredPatchAdd {
-		current, err := root.ReadFile(change.from.relative)
-		if err != nil {
-			return false, fmt.Errorf("re-reading %s before commit: %w", change.from.relative, err)
-		}
-		if string(current) != change.before {
-			return false, fmt.Errorf("%s changed on disk between planning and commit; re-read it and retry", change.from.relative)
-		}
-	}
 	switch change.kind {
 	case structuredPatchDelete:
 		if err := root.Remove(change.from.relative); err != nil {
 			return false, fmt.Errorf("deleting %s: %w", change.from.relative, err)
 		}
 		return true, nil
-	case structuredPatchAdd, structuredPatchCopy:
+	case structuredPatchAdd:
 		return writeStructuredPatchFile(root, change.to, change.after, change.mode, true)
 	case structuredPatchUpdate:
 		moving := change.from.absolute != change.to.absolute
@@ -902,7 +706,7 @@ func recordStructuredPatchFile(tracker *FileTracker, absolute string, created, s
 	info, _ := os.Stat(absolute)
 	tracker.Record(absolute, content, info)
 	if seenWhole {
-		lines := trackedLineTotal(string(content))
+		lines := lineCount(string(content))
 		tracker.RecordSeenRange(absolute, 1, lines, lines)
 	}
 	if created {

internal/tools/tool_search.go

@@ -58,11 +58,6 @@ func NewToolSearchTool(registry *Registry) Tool {
 	}
 }
 
-func (tool toolSearchTool) cloneForRegistry(registry *Registry) Tool {
-	tool.registry = registry
-	return tool
-}
-
 // Run satisfies the Tool interface; actual dispatch goes through RunWithOptions.
 func (tool toolSearchTool) Run(ctx context.Context, args map[string]any) Result {
 	return tool.RunWithOptions(ctx, args, RunOptions{})