ci(coderabbit): make Release-As releases explicit in the release check

The release check claimed a Release-As footer could override the bump
rule, but CodeRabbit's pre-merge checker cannot see commit footers, so a
forced-version release would fail with no stated way through. It now
names both versions and says a maintainer must ignore the check for
such a release.

Co-Authored-By: Claude Opus 5.5 <[email protected]>

.coderabbit.yaml

@@ -5,8 +5,13 @@ tone_instructions: "Be direct and prioritize actionable correctness, safety, CLI
 
 reviews:
   profile: "chill"
-  # Allow explicit @coderabbitai approve / resolve commands to submit review verdicts.
-  request_changes_workflow: true
+  # CodeRabbit requests changes for blocking findings and approves the PR once
+  # they are resolved, the latest commit is reviewed, and every pre-merge check
+  # below passes. This is the current key for the deprecated
+  # request_changes_workflow; setting both keys turns approvals off. Explicit
+  # @coderabbitai approve / resolve commands keep working.
+  auto_approvals:
+    enabled: true
   high_level_summary: true
   poem: false
   # Avoid noisy "review skipped" status comments when CodeRabbit decides not to run.
@@ -32,6 +37,26 @@ reviews:
     - path: "**/*.go"
       instructions: |
         Do not request Plan 9 or other unsupported GOOS/GOARCH shims. The five native prebuilt release targets are linux-x64, linux-arm64, macos-arm64, macos-x64, and windows-x64. Android/Termux is also a supported runtime through the documented android-arm64 source build and Linux artifact fallback. Other GOOS/GOARCH combinations are not a review criterion.
+  pre_merge_checks:
+    custom_checks:
+      - name: "npm release PR validated"
+        mode: "error"
+        instructions: |
+          Merging a release PR publishes the package to npm, so CodeRabbit approves one only after this check passes.
+
+          Decide every item from the PR title and the diff alone. This check does not receive the head branch name, the PR body, or GitHub Check results, so no item depends on them. If an item still cannot be decided from the title and the diff, fail it and say what was missing; never report this check as inconclusive.
+
+          Scope: a PR is a release PR when its title starts with `chore(main): release`, or when its diff changes `version` in `package.json` or any value in `.release-please-manifest.json`. Either signal is enough, so editing the title does not take a release PR out of scope. Every other PR passes this check; say "Not a release PR."
+
+          For a release PR, NEW is `version` in `package.json` after the change, and PREVIOUS is the `"."` value of `.release-please-manifest.json` before the change. The check passes only when all of the following hold. When it fails, list each failed item with the file and the value found.
+
+          1. Title: the title is exactly `chore(main): release NEW`. A malformed or edited title fails this item; quote it.
+          2. Changed files: the diff touches only `package.json`, `package-lock.json`, `.release-please-manifest.json`, and `CHANGELOG.md`. Any other path fails, whether source, tests, workflows, scripts, dependency manifests, or lockfiles.
+          3. One version everywhere: NEW equals the top-level `version` and `packages[""].version` in `package-lock.json`, and the `"."` value in `.release-please-manifest.json`.
+          4. Version-only edits: in `package.json` only the `version` line changes, in `package-lock.json` only the two root version fields change, and in `.release-please-manifest.json` only the `"."` value changes. No dependency, `engines`, `files`, `bin`, `exports`, or `scripts` change is allowed.
+          5. Valid increment: NEW is a plain MAJOR.MINOR.PATCH with no prerelease or build suffix, and it is greater than PREVIOUS.
+          6. Bump level: this repo uses release-please defaults, without `bump-minor-pre-major`. A breaking change bumps MAJOR, even from 0.x to 1.0.0. A feat bumps MINOR and resets PATCH, and a fix bumps PATCH. Read the change types from the new CHANGELOG section: a "BREAKING CHANGES" heading means a breaking change, "Features" means a feat, and every other section, such as "Bug Fixes", "Performance Improvements", "Reverts", or "Dependencies", counts as a fix. NEW must be exactly the next version for the highest change type present. This check cannot see commit footers, so it cannot confirm a `Release-As:` override. When NEW differs from the version these rules give, fail this item and name both versions; a release forced with `Release-As:` passes only when a maintainer ignores this check.
+          7. Changelog: `CHANGELOG.md` gains exactly one new section, at the top, headed `## [NEW](https://github.com/Twigpine/zero/compare/vPREVIOUS...vNEW) (YYYY-MM-DD)`, with at least one entry. Everything below it is unchanged, so no earlier section is edited or removed.
   tools:
     github-checks:
       timeout_ms: 300000
@@ -46,10 +71,11 @@ reviews:
       - "[skip review]"
     labels:
       - "!do-not-review"
+    # github-actions[bot] is not ignored on purpose: it opens the release-please
+    # PRs, and the "npm release PR validated" check has to run on them.
     ignore_usernames:
       - "dependabot[bot]"
       - "renovate[bot]"
-      - "github-actions[bot]"
     # CodeRabbit reviews default-branch PRs by default. This extends automatic
     # reviews to PRs targeting any branch, including release and stacked branches.
     base_branches:

.release-please-manifest.json

@@ -1 +1 @@
-{".":"0.11.0"}
+{".":"0.12.0"}

CHANGELOG.md

@@ -6,6 +6,30 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 aims to follow [Semantic Versioning](https://semver.org/spec/v2.0.0.html) once the first release is
 tagged. Until then, source builds report the version `dev`.
 
+## [0.12.0](https://github.com/Twigpine/zero/compare/v0.11.0...v0.12.0) (2026-11-02)
+
+
+### Features
+
+* **providers:** add MiniMax-M3.1-Flash to catalog ([#1180](https://github.com/Twigpine/zero/issues/1180)) ([d99f92b](https://github.com/Twigpine/zero/commit/d99f92b81a671f186cede81614c89b8e8a7f9451))
+* **sandbox:** support self-exec pattern to eliminate separate helper binary ([#946](https://github.com/Twigpine/zero/issues/946)) ([8c4e759](https://github.com/Twigpine/zero/commit/8c4e7597989ef9b3ca67b7703dfd15d92372aed2))
+* **skills:** install a skill's bundled files and point the skill tool at them ([#1167](https://github.com/Twigpine/zero/issues/1167)) ([1641506](https://github.com/Twigpine/zero/commit/164150633a8b2e6ae864ae02fd7105b201eeb68e))
+
+
+### Bug Fixes
+
+* **agent:** mark headless guardrail stops incomplete ([#1182](https://github.com/Twigpine/zero/issues/1182)) ([5aa54fe](https://github.com/Twigpine/zero/commit/5aa54fe1d2b419c9bbef73605a77919c9007cf7b))
+* bump Go to 1.26.10 for GO-2026-6809 ([#1168](https://github.com/Twigpine/zero/issues/1168)) ([6393a90](https://github.com/Twigpine/zero/commit/6393a90ed618a3536e09c02852f4ec829b97545b))
+* **chatgpt:** refresh subscription defaults and compatibility version ([#1179](https://github.com/Twigpine/zero/issues/1179)) ([f912f80](https://github.com/Twigpine/zero/commit/f912f80d002602e11ba0ef8548ecee58442874aa))
+* **deps:** refresh the lockfile to hono 4.13.13 ([#1171](https://github.com/Twigpine/zero/issues/1171)) ([de1443b](https://github.com/Twigpine/zero/commit/de1443b2edb44fd3747cc77200d54dc8cffcd0a7))
+* **oauth:** reuse the crash-safe secret store and sync encrypted publications ([#1165](https://github.com/Twigpine/zero/issues/1165)) ([84c1b15](https://github.com/Twigpine/zero/commit/84c1b1554076679a342e9cac61f8f8cdbaf3a429))
+* **redaction:** redact credentials whose trigger a greedy span swallowed ([#1158](https://github.com/Twigpine/zero/issues/1158)) ([a97db88](https://github.com/Twigpine/zero/commit/a97db8832fdba077f2d31bdf03ecef8d7c774fe1))
+* **sessions:** capture freeform apply_patch checkpoints ([#1183](https://github.com/Twigpine/zero/issues/1183)) ([6396208](https://github.com/Twigpine/zero/commit/63962081cf130c2171407936ce3beb7021d238b8))
+* **sessions:** preserve image attachment summaries on resume ([#1152](https://github.com/Twigpine/zero/issues/1152)) ([1e84849](https://github.com/Twigpine/zero/commit/1e848492e5c1919d187fb5e1eb5e7ef9bc6140dc)), closes [#1135](https://github.com/Twigpine/zero/issues/1135)
+* **tools:** grep stops where a file's line breaks stop ([#1160](https://github.com/Twigpine/zero/issues/1160)) ([aa9ba84](https://github.com/Twigpine/zero/commit/aa9ba8412eb8917daa2ca5cb3fdbd0a39276fa88))
+* **workspaceindex:** import gitsafe under the Twigpine module path ([#1153](https://github.com/Twigpine/zero/issues/1153)) ([ef4da13](https://github.com/Twigpine/zero/commit/ef4da1323f1097863ae278224b5f304c2fff909a))
+* **workspaceindex:** run Scan's git calls through gitsafe ([#1149](https://github.com/Twigpine/zero/issues/1149)) ([2ffe183](https://github.com/Twigpine/zero/commit/2ffe1831b0950b1463ec46d487d03a5fcb679cc6))
+
 ## [0.11.0](https://github.com/Twigpine/zero/compare/v0.10.0...v0.11.0) (2026-10-15)
 
 

internal/agent/checkpoint_targets.go

@@ -0,0 +1,34 @@
+package agent
+
+import "github.com/Twigpine/zero/internal/tools"
+
+// CheckpointTargets returns the workspace-relative paths a tool call will mutate,
+// resolving its arguments exactly as executeToolCall does. Freeform apply_patch
+// input is normalized through the registered built-in tool, so absolute headers
+// are rewritten relative to the selected write root and cwd is set: checkpoint
+// capture and execution therefore agree on the files at stake.
+//
+// Best-effort: nil when the call has no capture targets or its arguments cannot
+// be resolved. Checkpoint capture never fails a run.
+func CheckpointTargets(workspaceRoot string, registry *tools.Registry, call ToolCall) []string {
+	if registry == nil {
+		return nil
+	}
+	args := map[string]any{}
+	if call.Freeform {
+		tool, ok := registry.Get(call.Name)
+		if !ok || !tools.IsBuiltInApplyPatch(tool) {
+			return nil
+		}
+		prepared, err := tools.PrepareFreeformApplyPatchArguments(tool, call.Arguments)
+		if err != nil {
+			return nil
+		}
+		args = prepared
+	} else if call.Arguments != "" {
+		if err := decodeToolArguments(call.Arguments, &args); err != nil {
+			return nil
+		}
+	}
+	return tools.MutationTargets(workspaceRoot, call.Name, args)
+}

internal/agent/checkpoint_targets_test.go

@@ -0,0 +1,99 @@
+package agent
+
+import (
+	"encoding/json"
+	"os"
+	"path/filepath"
+	"slices"
+	"testing"
+
+	"github.com/Twigpine/zero/internal/tools"
+)
+
+func TestCheckpointTargets(t *testing.T) {
+	root := t.TempDir()
+	// Absolute headers must be compared against the physical root: t.TempDir
+	// differs from it on macOS (/var -> /private/var) and via Windows short names.
+	if resolved, err := filepath.EvalSymlinks(root); err == nil {
+		root = resolved
+	}
+	if err := os.WriteFile(filepath.Join(root, "main.txt"), []byte("before\n"), 0o644); err != nil {
+		t.Fatal(err)
+	}
+	relativePatch := "*** Begin Patch\n*** Update File: main.txt\n@@\n-before\n+after\n*** End Patch\n"
+	absolutePatch := "*** Begin Patch\n*** Update File: " + filepath.Join(root, "main.txt") + "\n@@\n-before\n+after\n*** End Patch\n"
+	multiFilePatch := "*** Begin Patch\n*** Update File: main.txt\n@@\n-before\n+after\n*** Add File: notes.txt\n+new\n*** End Patch\n"
+	jsonArgs, err := json.Marshal(map[string]any{"patch": relativePatch})
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	registry := tools.NewRegistry()
+	registry.Register(tools.NewScopedApplyPatchTool(root, nil))
+	unbuiltinRegistry := tools.NewRegistry()
+	unbuiltinRegistry.Register(&customApplyPatchTool{})
+
+	for _, tc := range []struct {
+		name     string
+		registry *tools.Registry
+		call     ToolCall
+		want     []string
+	}{
+		{
+			name: "freeform relative header",
+			call: ToolCall{Name: "apply_patch", Arguments: relativePatch, Freeform: true},
+			want: []string{"main.txt"},
+		},
+		{
+			name: "freeform absolute header stays workspace-relative",
+			call: ToolCall{Name: "apply_patch", Arguments: absolutePatch, Freeform: true},
+			want: []string{"main.txt"},
+		},
+		{
+			name: "freeform multi-file patch",
+			call: ToolCall{Name: "apply_patch", Arguments: multiFilePatch, Freeform: true},
+			want: []string{"main.txt", "notes.txt"},
+		},
+		{
+			name: "json arguments",
+			call: ToolCall{Name: "apply_patch", Arguments: string(jsonArgs)},
+			want: []string{"main.txt"},
+		},
+		{
+			name: "freeform traversal is rejected",
+			call: ToolCall{Name: "apply_patch", Arguments: "*** Begin Patch\n*** Update File: ../escape.txt\n@@\n-x\n+y\n*** End Patch\n", Freeform: true},
+			want: nil,
+		},
+		{
+			name:     "freeform custom apply_patch is not prepared",
+			registry: unbuiltinRegistry,
+			call:     ToolCall{Name: "apply_patch", Arguments: relativePatch, Freeform: true},
+			want:     nil,
+		},
+		{
+			name: "unknown freeform tool",
+			call: ToolCall{Name: "read_file", Arguments: "raw", Freeform: true},
+			want: nil,
+		},
+		{
+			name: "malformed json arguments",
+			call: ToolCall{Name: "apply_patch", Arguments: "{"},
+			want: nil,
+		},
+	} {
+		t.Run(tc.name, func(t *testing.T) {
+			reg := registry
+			if tc.registry != nil {
+				reg = tc.registry
+			}
+			got := CheckpointTargets(root, reg, tc.call)
+			if !slices.Equal(got, tc.want) {
+				t.Fatalf("CheckpointTargets() = %#v, want %#v", got, tc.want)
+			}
+		})
+	}
+
+	if got := CheckpointTargets(root, nil, ToolCall{Name: "apply_patch", Arguments: relativePatch}); got != nil {
+		t.Fatalf("CheckpointTargets(nil registry) = %#v, want nil", got)
+	}
+}

internal/agent/guardrails_test.go

@@ -80,6 +80,9 @@ func TestRunStopsAfterConsecutiveEmptyTurns(t *testing.T) {
 	if result.FinalAnswer == maxTurnsAnswer {
 		t.Fatalf("no-output guard must stop before reaching maxTurns, got max-turns answer")
 	}
+	if result.Incomplete {
+		t.Fatalf("interactive run must not be marked Incomplete; reason=%q", result.IncompleteReason)
+	}
 }
 
 func TestRunResetsEmptyTurnCounterOnVisibleOutput(t *testing.T) {
@@ -513,6 +516,22 @@ func repeatedFlakyTurns(n int) [][]zeroruntime.StreamEvent {
 	return turns
 }
 
+// alwaysSucceedingTool is the successful counterpart to alwaysFailingTool, used
+// to put a productive tool turn before an empty-turn streak.
+type alwaysSucceedingTool struct{}
+
+func (alwaysSucceedingTool) Name() string        { return "ok" }
+func (alwaysSucceedingTool) Description() string { return "always succeeds for testing" }
+func (alwaysSucceedingTool) Parameters() tools.Schema {
+	return tools.Schema{Type: "object", AdditionalProperties: false}
+}
+func (alwaysSucceedingTool) Safety() tools.Safety {
+	return tools.Safety{SideEffect: tools.SideEffectRead, Permission: tools.PermissionAllow}
+}
+func (alwaysSucceedingTool) Run(context.Context, map[string]any) tools.Result {
+	return tools.Result{Status: tools.StatusOK, Output: "ok"}
+}
+
 func TestRunStopsAfterRepeatedToolFailures(t *testing.T) {
 	registry := tools.NewRegistry()
 	registry.Register(alwaysFailingTool{})
@@ -529,6 +548,51 @@ func TestRunStopsAfterRepeatedToolFailures(t *testing.T) {
 	if len(provider.requests) != toolFailureStopAt {
 		t.Fatalf("expected stop at %d failures, made %d requests", toolFailureStopAt, len(provider.requests))
 	}
+	if result.Incomplete {
+		t.Fatalf("interactive run must not be marked Incomplete; reason=%q", result.IncompleteReason)
+	}
+}
+
+// Under the headless completion gate both guardrail stops are unfinished runs,
+// so they must set Result.Incomplete and a reason; exec maps that to exit 4.
+// Thresholds and stop answers stay pinned by the two tests above.
+func TestHeadlessGuardStopsAreIncomplete(t *testing.T) {
+	for _, tc := range []struct {
+		name       string
+		turns      [][]zeroruntime.StreamEvent
+		wantTurns  int
+		wantReason string
+	}{
+		{"empty_turns", [][]zeroruntime.StreamEvent{emptyTurn(), emptyTurn(), emptyTurn()}, maxEmptyTurns, "3 consecutive turns with no output"},
+		{"empty_turns_after_progress", [][]zeroruntime.StreamEvent{
+			toolTurn("ok-1", "ok", "{}"),
+			emptyTurn(), emptyTurn(), emptyTurn(),
+		}, maxEmptyTurns + 1, "3 consecutive turns with no output"},
+		{"repeated_tool_failures", repeatedFlakyTurns(10), toolFailureStopAt, "flaky"},
+	} {
+		t.Run(tc.name, func(t *testing.T) {
+			registry := tools.NewRegistry()
+			registry.Register(alwaysFailingTool{})
+			registry.Register(alwaysSucceedingTool{})
+			result, err := Run(context.Background(), "go", &mockProvider{turns: tc.turns}, Options{
+				Registry:                registry,
+				MaxTurns:                12,
+				RequireCompletionSignal: true,
+			})
+			if err != nil {
+				t.Fatal(err)
+			}
+			if result.Turns != tc.wantTurns {
+				t.Fatalf("guard did not trigger: turns=%d want=%d", result.Turns, tc.wantTurns)
+			}
+			if !result.Incomplete {
+				t.Fatalf("guardrail stop under the headless gate must be Incomplete; final=%q", result.FinalAnswer)
+			}
+			if !strings.Contains(result.IncompleteReason, tc.wantReason) {
+				t.Fatalf("IncompleteReason = %q, want it to mention %q", result.IncompleteReason, tc.wantReason)
+			}
+		})
+	}
 }
 
 func TestRunInjectsToolFailureHintWithSchema(t *testing.T) {

internal/agent/loop.go

@@ -587,6 +587,14 @@ func Run(ctx context.Context, prompt string, provider Provider, options Options)
 			// counted toward the runaway cap so we stop before burning maxTurns.
 			if guards.observeTurn(collected) {
 				result.FinalAnswer = noOutputStopAnswer(result.Turns)
+				// Under the headless completion gate this stop is unfinished work,
+				// not a successful final answer: the guard exists precisely because
+				// the model made no progress. Interactive runs keep the gate off, so
+				// their behavior is unchanged.
+				if options.RequireCompletionSignal {
+					result.Incomplete = true
+					result.IncompleteReason = "stopped after " + strconv.Itoa(guards.emptyTurns) + " consecutive turns with no output"
+				}
 				result.Messages = copyMessages(messages)
 				return result, nil
 			}
@@ -808,6 +816,13 @@ func Run(ctx context.Context, prompt string, provider Provider, options Options)
 				messages = appendAbortedToolResults(messages, collected.ToolCalls[index+1:])
 				messages = append(messages, buildToolImageMessages()...)
 				result.FinalAnswer = toolFailureStopAnswer(call.Name, outcome.Count)
+				// Same headless contract as the empty-turn guard: halting on a
+				// repeated failure is an unfinished run, not success. Gate-off
+				// (interactive / --no-completion-gate) keeps the old behavior.
+				if options.RequireCompletionSignal {
+					result.Incomplete = true
+					result.IncompleteReason = "the " + call.Name + " tool failed " + strconv.Itoa(outcome.Count) + " times in a row with the same error"
+				}
 				result.Messages = copyMessages(messages)
 				return result, nil
 			}

internal/cli/exec.go

@@ -712,7 +712,7 @@ func runExec(args []string, stdout io.Writer, stderr io.Writer, deps appDeps) in
 				"arguments": call.Arguments,
 			})
 			// Snapshot before-state of files this call will mutate (safe rewind).
-			if checkpoint, ok := sessionRecorder.captureCheckpoint(workspaceRoot, call); ok {
+			if checkpoint, ok := sessionRecorder.captureCheckpoint(workspaceRoot, registry, call); ok {
 				writer.checkpoint(checkpoint)
 			}
 		},

internal/cli/exec_checkpoint_freeform_test.go

@@ -0,0 +1,206 @@
+package cli
+
+import (
+	"bytes"
+	"context"
+	"encoding/json"
+	"os"
+	"path/filepath"
+	"testing"
+
+	"github.com/Twigpine/zero/internal/agent"
+	"github.com/Twigpine/zero/internal/config"
+	"github.com/Twigpine/zero/internal/sessions"
+	"github.com/Twigpine/zero/internal/tools"
+	"github.com/Twigpine/zero/internal/zeroruntime"
+)
+
+func freeformApplyPatchArguments(root string, absolute bool) string {
+	target := "main.txt"
+	if absolute {
+		target = filepath.Join(root, "main.txt")
+	}
+	return "*** Begin Patch\n*** Update File: " + target + "\n@@\n-before\n+after\n*** End Patch\n"
+}
+
+// captureCheckpoint must resolve a freeform apply_patch call through the same
+// preparation execution uses, so the before-state is captured and rewind can
+// restore it. The JSON control pins the unchanged path.
+func TestCaptureCheckpointFreeformApplyPatch(t *testing.T) {
+	for _, tc := range []struct {
+		name     string
+		freeform bool
+		absolute bool
+		jsonArgs bool
+	}{
+		{name: "freeform", freeform: true},
+		{name: "freeform absolute header", freeform: true, absolute: true},
+		{name: "json arguments", jsonArgs: true},
+	} {
+		t.Run(tc.name, func(t *testing.T) {
+			t.Setenv("XDG_DATA_HOME", t.TempDir())
+			t.Setenv("ZERO_CHECKPOINTS", "on")
+			root := t.TempDir()
+			// The absolute-header case needs the physical root spelling the tool
+			// resolves (macOS /var vs /private/var, Windows short names).
+			if resolved, err := filepath.EvalSymlinks(root); err == nil {
+				root = resolved
+			}
+			if err := os.WriteFile(filepath.Join(root, "main.txt"), []byte("before\n"), 0o644); err != nil {
+				t.Fatal(err)
+			}
+			store := sessions.NewStore(sessions.StoreOptions{})
+			session, err := store.Create(sessions.CreateInput{Title: "freeform checkpoint"})
+			if err != nil {
+				t.Fatal(err)
+			}
+			if _, err := store.AppendEvent(session.SessionID, sessions.AppendEventInput{
+				Type:    sessions.EventMessage,
+				Payload: map[string]string{"role": "user", "content": "apply the patch"},
+			}); err != nil {
+				t.Fatal(err)
+			}
+			recorder := &execSessionRecorder{prepared: sessions.PreparedExec{Store: store, Session: session}}
+			registry := tools.NewRegistry()
+			registry.Register(tools.NewScopedApplyPatchTool(root, nil))
+
+			call := agent.ToolCall{ID: "call", Name: "apply_patch", Freeform: tc.freeform}
+			if tc.jsonArgs {
+				encoded, err := json.Marshal(map[string]string{"patch": freeformApplyPatchArguments(root, false)})
+				if err != nil {
+					t.Fatal(err)
+				}
+				call.Arguments = string(encoded)
+			} else {
+				call.Arguments = freeformApplyPatchArguments(root, tc.absolute)
+			}
+
+			event, ok := recorder.captureCheckpoint(root, registry, call)
+			if !ok || event.Type != sessions.EventSessionCheckpoint {
+				t.Fatalf("captureCheckpoint() = %#v, %t; want a checkpoint event", event, ok)
+			}
+			var payload sessions.CheckpointPayload
+			if err := json.Unmarshal(event.Payload, &payload); err != nil {
+				t.Fatalf("decode checkpoint payload: %v", err)
+			}
+			if len(payload.Files) != 1 || payload.Files[0].Path != "main.txt" || payload.Files[0].Blob == "" {
+				t.Fatalf("checkpoint files = %#v, want main.txt with a blob", payload.Files)
+			}
+
+			// Simulate the tool's mutation, then rewind past it.
+			if err := os.WriteFile(filepath.Join(root, "main.txt"), []byte("after\n"), 0o644); err != nil {
+				t.Fatal(err)
+			}
+			report, err := store.ApplyRewind(session.SessionID, root, 1)
+			if err != nil {
+				t.Fatalf("ApplyRewind: %v", err)
+			}
+			if report.FilesRestored != 1 {
+				t.Fatalf("restore report = %#v, want one restored file", report)
+			}
+			content, err := os.ReadFile(filepath.Join(root, "main.txt"))
+			if err != nil {
+				t.Fatal(err)
+			}
+			if string(content) != "before\n" {
+				t.Fatalf("restored content = %q, want before newline", content)
+			}
+		})
+	}
+}
+
+// freeformPatchExecProvider emits one native freeform apply_patch call, then a
+// final text turn.
+type freeformPatchExecProvider struct {
+	patch string
+	calls int
+}
+
+func (provider *freeformPatchExecProvider) StreamCompletion(ctx context.Context, request zeroruntime.CompletionRequest) (<-chan zeroruntime.StreamEvent, error) {
+	ch := make(chan zeroruntime.StreamEvent, 5)
+	calls := provider.calls
+	provider.calls++
+	if calls == 0 {
+		ch <- zeroruntime.StreamEvent{Type: zeroruntime.StreamEventToolCallStart, ToolCallID: "call_patch", ToolName: "apply_patch", ToolCallFreeform: true}
+		ch <- zeroruntime.StreamEvent{Type: zeroruntime.StreamEventToolCallDelta, ToolCallID: "call_patch", ArgumentsFragment: provider.patch}
+		ch <- zeroruntime.StreamEvent{Type: zeroruntime.StreamEventToolCallEnd, ToolCallID: "call_patch"}
+	} else {
+		ch <- zeroruntime.StreamEvent{Type: zeroruntime.StreamEventText, Content: "patched"}
+	}
+	ch <- zeroruntime.StreamEvent{Type: zeroruntime.StreamEventDone}
+	close(ch)
+	return ch, nil
+}
+
+// End-to-end: exec captures the freeform checkpoint and `sessions rewind`
+// restores the pre-patch content.
+func TestRunExecFreeformApplyPatchCheckpointsForRewind(t *testing.T) {
+	isolateCLIUserState(t)
+	t.Setenv("ZERO_CHECKPOINTS", "on")
+	root := t.TempDir()
+	if err := os.WriteFile(filepath.Join(root, "main.txt"), []byte("before\n"), 0o644); err != nil {
+		t.Fatal(err)
+	}
+	provider := &freeformPatchExecProvider{patch: freeformApplyPatchArguments(root, false)}
+	var stdout, stderr bytes.Buffer
+	exitCode := runWithDeps([]string{
+		"exec", "--init-session-id", "freeform_rewind", "--skip-permissions-unsafe",
+		"--output-format", "stream-json", "apply the patch",
+	}, &stdout, &stderr, appDeps{
+		getwd: func() (string, error) { return root, nil },
+		resolveConfig: func(string, config.Overrides) (config.ResolvedConfig, error) {
+			return execResolvedConfig(), nil
+		},
+		newProvider: func(config.ProviderProfile) (zeroruntime.Provider, error) {
+			return provider, nil
+		},
+	})
+	if exitCode != exitSuccess {
+		t.Fatalf("exit = %d, want %d; stderr=%q stdout=%q", exitCode, exitSuccess, stderr.String(), stdout.String())
+	}
+	content, err := os.ReadFile(filepath.Join(root, "main.txt"))
+	if err != nil {
+		t.Fatal(err)
+	}
+	if string(content) != "after\n" {
+		t.Fatalf("patched content = %q, want after newline", content)
+	}
+
+	store := sessions.NewStore(sessions.StoreOptions{})
+	events, err := store.ReadEvents("freeform_rewind")
+	if err != nil {
+		t.Fatalf("ReadEvents: %v", err)
+	}
+	checkpoints := 0
+	for _, event := range events {
+		if event.Type == sessions.EventSessionCheckpoint {
+			checkpoints++
+		}
+	}
+	if checkpoints != 1 {
+		t.Fatalf("checkpoint events = %d, want 1; events=%v", checkpoints, sessionEventTypes(events))
+	}
+
+	report, err := store.ApplyRewind("freeform_rewind", root, 1)
+	if err != nil {
+		t.Fatalf("ApplyRewind: %v", err)
+	}
+	if report.FilesRestored != 1 {
+		t.Fatalf("restore report = %#v, want one restored file", report)
+	}
+	content, err = os.ReadFile(filepath.Join(root, "main.txt"))
+	if err != nil {
+		t.Fatal(err)
+	}
+	if string(content) != "before\n" {
+		t.Fatalf("rewound content = %q, want before newline", content)
+	}
+}
+
+func sessionEventTypes(events []sessions.Event) []string {
+	types := make([]string, 0, len(events))
+	for _, event := range events {
+		types = append(types, string(event.Type))
+	}
+	return types
+}

internal/cli/exec_guard_stop_incomplete_test.go

@@ -0,0 +1,90 @@
+package cli
+
+import (
+	"bytes"
+	"context"
+	"slices"
+	"strings"
+	"testing"
+
+	"github.com/Twigpine/zero/internal/config"
+	"github.com/Twigpine/zero/internal/zeroruntime"
+)
+
+// guardStopExecProvider emits turns with no visible text and no tool calls, so
+// the empty-turn guardrail stops the run after its consecutive-empty-turn cap.
+type guardStopExecProvider struct{}
+
+func (guardStopExecProvider) StreamCompletion(ctx context.Context, request zeroruntime.CompletionRequest) (<-chan zeroruntime.StreamEvent, error) {
+	ch := make(chan zeroruntime.StreamEvent, 1)
+	select {
+	case <-ctx.Done():
+		close(ch)
+		return ch, ctx.Err()
+	case ch <- zeroruntime.StreamEvent{Type: zeroruntime.StreamEventDone}:
+	}
+	close(ch)
+	return ch, nil
+}
+
+// A guardrail stop in headless exec must use the existing INCOMPLETE contract
+// (exit 4, error event, run_end status), and --no-completion-gate must keep
+// reporting success. isolateCLIUserState also turns off the models.dev refresh
+// that runExec starts in the background (see the #1152/#1161 flake).
+func TestRunExecGuardrailStopIncompleteContract(t *testing.T) {
+	for _, tc := range []struct {
+		name       string
+		args       []string
+		wantExit   int
+		wantStatus string
+	}{
+		{"gate on", []string{"exec", "--output-format", "stream-json", "complete the task"}, exitIncomplete, "incomplete"},
+		{"gate off", []string{"exec", "--no-completion-gate", "--output-format", "stream-json", "complete the task"}, exitSuccess, "success"},
+	} {
+		t.Run(tc.name, func(t *testing.T) {
+			isolateCLIUserState(t)
+			cwd := t.TempDir()
+			var stdout, stderr bytes.Buffer
+			exitCode := runWithDeps(tc.args, &stdout, &stderr, appDeps{
+				getwd: func() (string, error) { return cwd, nil },
+				resolveConfig: func(string, config.Overrides) (config.ResolvedConfig, error) {
+					return execResolvedConfig(), nil
+				},
+				newProvider: func(config.ProviderProfile) (zeroruntime.Provider, error) {
+					return guardStopExecProvider{}, nil
+				},
+			})
+			if exitCode != tc.wantExit {
+				t.Fatalf("exit code = %d, want %d; stderr=%q", exitCode, tc.wantExit, stderr.String())
+			}
+
+			events := decodeJSONLines(t, stdout.String())
+			if len(events) == 0 || events[len(events)-1]["type"] != "run_end" {
+				t.Fatalf("expected run_end as the last event, got %#v", events)
+			}
+			runEnd := events[len(events)-1]
+			if runEnd["status"] != tc.wantStatus {
+				t.Fatalf("run_end status = %v, want %q", runEnd["status"], tc.wantStatus)
+			}
+			if runEnd["exitCode"] != float64(tc.wantExit) {
+				t.Fatalf("run_end exitCode = %v, want %d", runEnd["exitCode"], tc.wantExit)
+			}
+			finalEvent := findJSONEvent(t, events, "final")
+			if text, _ := finalEvent["text"].(string); !strings.Contains(text, "no output") {
+				t.Fatalf("final text = %q, want the guard stop answer", text)
+			}
+
+			if tc.wantStatus == "incomplete" {
+				errorEvent := findJSONEvent(t, events, "error")
+				if errorEvent["code"] != "incomplete" {
+					t.Fatalf("error code = %v, want incomplete", errorEvent["code"])
+				}
+				if message, _ := errorEvent["message"].(string); !strings.Contains(message, "no output") {
+					t.Fatalf("error message = %q, want the guard reason", message)
+				}
+			} else if slices.Contains(jsonEventTypes(events), "error") {
+				t.Fatalf("gate-off run must not emit an error event: %#v", events)
+			}
+		})
+	}
+}

internal/cli/exec_sessions.go

@@ -1,7 +1,6 @@
 package cli
 
 import (
-	"encoding/json"
 	"fmt"
 	"io"
 	"strings"
@@ -19,15 +18,11 @@ type execSessionRecorder struct {
 // captureCheckpoint snapshots the before-state of files a tool call will mutate.
 // Best-effort: failures never affect the run. Returns the checkpoint event and
 // true when one was recorded.
-func (recorder *execSessionRecorder) captureCheckpoint(workspaceRoot string, call agent.ToolCall) (sessions.Event, bool) {
+func (recorder *execSessionRecorder) captureCheckpoint(workspaceRoot string, registry *tools.Registry, call agent.ToolCall) (sessions.Event, bool) {
 	if recorder.prepared.Store == nil || recorder.prepared.Session.SessionID == "" {
 		return sessions.Event{}, false
 	}
-	var args map[string]any
-	if call.Arguments != "" {
-		_ = json.Unmarshal([]byte(call.Arguments), &args)
-	}
-	targets := tools.MutationTargets(workspaceRoot, call.Name, args)
+	targets := agent.CheckpointTargets(workspaceRoot, registry, call)
 	if len(targets) == 0 {
 		return sessions.Event{}, false
 	}

internal/cli/exec_spec.go

@@ -148,7 +148,7 @@ func runExecSpecDraft(run execSpecDraftRun) int {
 				"name":      call.Name,
 				"arguments": call.Arguments,
 			})
-			if checkpoint, ok := sessionRecorder.captureCheckpoint(run.workspaceRoot, call); ok {
+			if checkpoint, ok := sessionRecorder.captureCheckpoint(run.workspaceRoot, run.registry, call); ok {
 				writer.checkpoint(checkpoint)
 			}
 		},

internal/config/chatgpt_defaults_test.go

@@ -0,0 +1,51 @@
+package config
+
+import (
+	"encoding/json"
+	"os"
+	"path/filepath"
+	"testing"
+)
+
+func TestEnsureChatGPTDefaultPreservesSavedSelection(t *testing.T) {
+	for _, saved := range []string{"", "gpt-explicit-saved"} {
+		name := "new profile"
+		if saved != "" {
+			name = "saved selection"
+		}
+		t.Run(name, func(t *testing.T) {
+			path := filepath.Join(t.TempDir(), "config.json")
+			if saved != "" {
+				body, err := json.Marshal(FileConfig{ActiveProvider: "codex", Providers: []ProviderProfile{{Name: "codex", CatalogID: "chatgpt", Model: saved}}})
+				if err != nil {
+					t.Fatal(err)
+				}
+				if err := os.WriteFile(path, body, 0600); err != nil {
+					t.Fatal(err)
+				}
+			}
+			ensured, err := EnsureCatalogProvider(path, "chatgpt")
+			if err != nil {
+				t.Fatal(err)
+			}
+			body, err := os.ReadFile(path)
+			if err != nil {
+				t.Fatal(err)
+			}
+			var cfg FileConfig
+			if err := json.Unmarshal(body, &cfg); err != nil {
+				t.Fatal(err)
+			}
+			want := "gpt-6.1-sol"
+			if saved != "" {
+				want = saved
+			}
+			if len(cfg.Providers) != 1 || cfg.Providers[0].Model != want {
+				t.Fatalf("ChatGPT default/selection = %#v, want model %q", cfg.Providers, want)
+			}
+			if saved != "" && (ensured.Name != "codex" || ensured.Created) {
+				t.Fatalf("saved subscription profile was replaced: %#v", ensured)
+			}
+		})
+	}
+}

internal/providercatalog/catalog.go

@@ -132,7 +132,9 @@ var descriptors = []Descriptor{
 	// way in; RequiresAuth is forced true so catalog consumers know the provider
 	// needs an interactive login before a request will succeed.
 	func() Descriptor {
-		d := openAICompat("chatgpt", "ChatGPT", "https://chatgpt.com/backend-api/codex", "gpt-5.5", nil)
+		// New ChatGPT profiles follow the vendor's GPT-5.5 replacement guidance:
+		// https://learn.chatgpt.com/docs/models#gpt-55-retirement
+		d := openAICompat("chatgpt", "ChatGPT", "https://chatgpt.com/backend-api/codex", "gpt-6.1-sol", nil)
 		d.RequiresAuth = true
 		return oauthProvider(d, false, false)
 	}(),

internal/providermodelcatalog/catalog.go

@@ -44,6 +44,20 @@ var minimaxCuratedModels = []Model{
 		OutputModalities: []string{"text"},
 		Source:           minimaxModelSource,
 	},
+	{
+		ID:                     "MiniMax-M3.1-Flash",
+		Description:            "fast reasoning model",
+		ContextWindow:          1_000_000,
+		ToolCall:               true,
+		Reasoning:              true,
+		ReasoningEfforts:       []string{"low", "medium", "high", "xhigh", "max"},
+		DefaultReasoningEffort: "max",
+		InputModalities:        []string{"text", "image", "video"},
+		OutputModalities:       []string{"text"},
+		InputCost:              0.15,
+		OutputCost:             0.60,
+		Source:                 minimaxModelSource,
+	},
 	{
 		ID:               "MiniMax-M2.7",
 		Description:      "agentic coding model",
@@ -113,10 +127,12 @@ var curatedModels = map[string][]Model{
 		{ID: "deepseek/deepseek-chat", Description: "coding model"},
 	},
 	"chatgpt": {
-		{ID: "gpt-5.5", Description: "recommended Codex model"},
-		{ID: "gpt-5.4", Description: "strong Codex model"},
-		{ID: "gpt-5.4-mini", Description: "fast Codex model"},
-		{ID: "gpt-5.3-codex-spark", Description: "research preview fast Codex model"},
+		// Suggestions only: availability comes from the authenticated Codex catalog.
+		// https://learn.chatgpt.com/docs/models
+		{ID: "gpt-6.1-sol", Description: "balanced Codex model"},
+		{ID: "gpt-6.1-terra", Description: "fast model for writing, visual understanding, and computer use"},
+		{ID: "gpt-6-astra", Description: "advanced reasoning model"},
+		{ID: "gpt-6-luna", Description: "efficient coding model"},
 	},
 	"deepseek": {
 		{ID: "deepseek-chat", Description: "catalog default"},

internal/providermodelcatalog/catalog_test.go

@@ -35,8 +35,8 @@ func TestModelsAreProviderScoped(t *testing.T) {
 		},
 		{
 			provider: "chatgpt",
-			want:     []string{"gpt-5.5", "gpt-5.4", "gpt-5.4-mini", "gpt-5.3-codex-spark"},
-			notWant:  []string{"gpt-5", "gpt-4.1", "openai/gpt-4.1"},
+			want:     []string{"gpt-6.1-sol", "gpt-6.1-terra", "gpt-6-astra", "gpt-6-luna"},
+			notWant:  []string{"gpt-5.5", "gpt-5.4", "gpt-5.4-mini", "gpt-5.3-codex-spark", "openai/gpt-4.1"},
 		},
 		{
 			provider: "aimlapi",
@@ -65,7 +65,7 @@ func TestModelsAreProviderScoped(t *testing.T) {
 		},
 		{
 			provider: "minimaxi-cn",
-			want:     []string{"MiniMax-M3", "MiniMax-M2.7", "MiniMax-M2.1"},
+			want:     []string{"MiniMax-M3", "MiniMax-M3.1-Flash", "MiniMax-M2.7", "MiniMax-M2.1"},
 			notWant:  []string{"gpt-4.1", "claude-sonnet-4.5"},
 		},
 		{
@@ -165,8 +165,8 @@ func TestMiniMaxModelsExposeCurrentCapabilities(t *testing.T) {
 		t.Fatal("provider minimax missing from catalog")
 	}
 	models := Models(descriptor)
-	if len(models) < 2 || models[0].ID != "MiniMax-M3" || models[1].ID != "MiniMax-M2.7" {
-		t.Fatalf("MiniMax current models = %#v, want MiniMax-M3 followed by MiniMax-M2.7", modelIDs(models))
+	if len(models) < 3 || models[0].ID != "MiniMax-M3" || models[1].ID != "MiniMax-M3.1-Flash" || models[2].ID != "MiniMax-M2.7" {
+		t.Fatalf("MiniMax current models = %#v, want MiniMax-M3, MiniMax-M3.1-Flash, then MiniMax-M2.7", modelIDs(models))
 	}
 
 	m3 := models[0]
@@ -178,7 +178,23 @@ func TestMiniMaxModelsExposeCurrentCapabilities(t *testing.T) {
 		t.Fatalf("MiniMax-M3 modalities = input:%#v output:%#v", m3.InputModalities, m3.OutputModalities)
 	}
 
-	m27 := models[1]
+	m31Flash := models[1]
+	if m31Flash.ContextWindow != 1_000_000 || !m31Flash.ToolCall || !m31Flash.Reasoning {
+		t.Fatalf("MiniMax-M3.1-Flash capabilities = %#v, want 1M context with tools and reasoning", m31Flash)
+	}
+	if !reflect.DeepEqual(m31Flash.ReasoningEfforts, []string{"low", "medium", "high", "xhigh", "max"}) ||
+		m31Flash.DefaultReasoningEffort != "max" {
+		t.Fatalf("MiniMax-M3.1-Flash reasoning efforts = %#v default %q", m31Flash.ReasoningEfforts, m31Flash.DefaultReasoningEffort)
+	}
+	if !reflect.DeepEqual(m31Flash.InputModalities, []string{"text", "image", "video"}) ||
+		!reflect.DeepEqual(m31Flash.OutputModalities, []string{"text"}) {
+		t.Fatalf("MiniMax-M3.1-Flash modalities = input:%#v output:%#v", m31Flash.InputModalities, m31Flash.OutputModalities)
+	}
+	if m31Flash.InputCost != 0.15 || m31Flash.OutputCost != 0.60 {
+		t.Fatalf("MiniMax-M3.1-Flash costs = %f/%f, want 0.15/0.60", m31Flash.InputCost, m31Flash.OutputCost)
+	}
+
+	m27 := models[2]
 	if m27.ContextWindow != 204_800 || !m27.ToolCall || !m27.Reasoning {
 		t.Fatalf("MiniMax-M2.7 capabilities = %#v, want 204.8K context with tools and reasoning", m27)
 	}

internal/providermodeldiscovery/chatgpt_defaults_test.go

@@ -0,0 +1,31 @@
+package providermodeldiscovery
+
+import (
+	"context"
+	"net/http"
+	"net/http/httptest"
+	"testing"
+
+	"github.com/Twigpine/zero/internal/config"
+)
+
+func TestChatGPTDiscoveryUsesCurrentCompatibilityVersion(t *testing.T) {
+	server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		if got := r.URL.Query().Get("client_version"); got != "0.159.0" {
+			t.Errorf("client_version = %q, want documented GPT-6.1 Terra compatibility floor 0.159.0", got)
+		}
+		_, _ = w.Write([]byte(`{"models":[{"slug":"gpt-future-coder"}]}`))
+	}))
+	defer server.Close()
+	profile := config.ProviderProfile{
+		CatalogID: "chatgpt", ProviderKind: config.ProviderKindOpenAICompatible,
+		BaseURL: server.URL + "/backend-api/codex", APIKey: "test-bearer",
+	}
+	models, err := Discover(context.Background(), profile, Options{HTTPClient: server.Client()})
+	if err != nil {
+		t.Fatal(err)
+	}
+	if len(models) != 1 || models[0].ID != "gpt-future-coder" {
+		t.Fatalf("models = %#v, want only gpt-future-coder", models)
+	}
+}

internal/providermodeldiscovery/discovery.go

@@ -20,8 +20,9 @@ import (
 )
 
 const (
-	anthropicVersion             = "2023-06-01"
-	chatGPTModelsProtocolVersion = "0.146.0"
+	anthropicVersion = "2023-06-01"
+	// GPT-6.1 Terra's documented Codex client floor: https://learn.chatgpt.com/docs/models.
+	chatGPTModelsProtocolVersion = "0.159.0"
 )
 
 type Model struct {

internal/providers/anthropic/provider.go

@@ -49,6 +49,19 @@ func thinkingBudgetForEffort(effort string) int {
 	}
 }
 
+func miniMaxM31FlashEffort(model, effort string) string {
+	if !strings.EqualFold(strings.TrimSpace(model), "MiniMax-M3.1-Flash") {
+		return ""
+	}
+	effort = strings.ToLower(strings.TrimSpace(effort))
+	switch effort {
+	case "low", "medium", "high", "xhigh", "max":
+		return effort
+	default:
+		return ""
+	}
+}
+
 // resolveThinking returns the thinking budget and the max_tokens to send. When a
 // budget is requested, max_tokens is raised if needed so the budget plus a
 // minimum response both fit (Anthropic rejects budget >= max_tokens). enabled is
@@ -377,11 +390,15 @@ func (provider *Provider) anthropicRequest(request zeroruntime.CompletionRequest
 		Messages:  messages,
 		Stream:    true,
 	}
-	// Extended thinking: enable when a reasoning effort was requested. The budget
-	// is counted against max_tokens, so raise max_tokens to leave room for the
-	// response. Temperature is intentionally left unset (Anthropic requires the
-	// default when thinking is on).
-	if budget, effectiveMax, enabled := resolveThinking(request.ReasoningEffort, provider.maxTokens); enabled {
+	// MiniMax-M3.1-Flash uses adaptive thinking with output_config.effort instead
+	// of Anthropic's token budget. For other models, the budget is counted against
+	// max_tokens, so raise max_tokens to leave room for the response. Temperature
+	// is intentionally left unset (Anthropic requires the default when thinking
+	// is on).
+	if effort := miniMaxM31FlashEffort(provider.model, request.ReasoningEffort); effort != "" {
+		mapped.Thinking = &thinkingConfig{Type: "adaptive"}
+		mapped.OutputConfig = &outputConfig{Effort: effort}
+	} else if budget, effectiveMax, enabled := resolveThinking(request.ReasoningEffort, provider.maxTokens); enabled {
 		mapped.MaxTokens = effectiveMax
 		mapped.Thinking = &thinkingConfig{Type: "enabled", BudgetTokens: budget}
 	}

internal/providers/anthropic/provider_test.go

@@ -266,6 +266,53 @@ func TestStreamCompletionEnablesThinkingWhenEffortRequested(t *testing.T) {
 	}
 }
 
+func TestStreamCompletionUsesMiniMaxAdaptiveEffort(t *testing.T) {
+	t.Parallel()
+
+	for _, effort := range []string{"low", "xhigh"} {
+		effort := effort
+		t.Run(effort, func(t *testing.T) {
+			t.Parallel()
+			var gotBody map[string]any
+			server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+				if err := json.NewDecoder(r.Body).Decode(&gotBody); err != nil {
+					t.Fatalf("decode request body: %v", err)
+				}
+				writeSSEEvent(w, "message_stop", `{"type":"message_stop"}`)
+			}))
+			defer server.Close()
+
+			provider, err := New(Options{BaseURL: server.URL + "/", Model: "MiniMax-M3.1-Flash", MaxTokens: 64_000})
+			if err != nil {
+				t.Fatalf("New returned error: %v", err)
+			}
+			stream, err := provider.StreamCompletion(context.Background(), zeroruntime.CompletionRequest{
+				Messages:        []zeroruntime.Message{{Role: zeroruntime.MessageRoleUser, Content: "hi"}},
+				ReasoningEffort: effort,
+			})
+			if err != nil {
+				t.Fatalf("StreamCompletion returned error: %v", err)
+			}
+			drain(stream)
+
+			thinking, ok := gotBody["thinking"].(map[string]any)
+			if !ok || thinking["type"] != "adaptive" {
+				t.Fatalf("thinking = %#v, want adaptive", gotBody["thinking"])
+			}
+			if _, ok := thinking["budget_tokens"]; ok {
+				t.Fatalf("MiniMax thinking must not include budget_tokens: %#v", thinking)
+			}
+			outputConfig, ok := gotBody["output_config"].(map[string]any)
+			if !ok || outputConfig["effort"] != effort {
+				t.Fatalf("output_config = %#v, want effort %q", gotBody["output_config"], effort)
+			}
+			if mt, _ := gotBody["max_tokens"].(float64); int(mt) != 64_000 {
+				t.Fatalf("max_tokens = %#v, want unchanged 64000", gotBody["max_tokens"])
+			}
+		})
+	}
+}
+
 func TestStreamCompletionOmitsThinkingWithoutEffort(t *testing.T) {
 	t.Parallel()
 	var gotBody map[string]any

internal/providers/anthropic/types.go

@@ -10,17 +10,21 @@ type messagesRequest struct {
 	System any `json:"system,omitempty"`
 	// Thinking enables extended thinking when a reasoning effort was requested.
 	// Omitted (nil) for normal requests so behavior is unchanged.
-	Thinking *thinkingConfig `json:"thinking,omitempty"`
-	Tools    []anthropicTool `json:"tools,omitempty"`
-	Stream   bool            `json:"stream"`
+	Thinking     *thinkingConfig `json:"thinking,omitempty"`
+	OutputConfig *outputConfig   `json:"output_config,omitempty"`
+	Tools        []anthropicTool `json:"tools,omitempty"`
+	Stream       bool            `json:"stream"`
 }
 
-// thinkingConfig requests extended thinking with a token budget. Type is always
-// "enabled"; BudgetTokens is how many tokens the model may spend thinking (it is
-// counted against max_tokens).
+// thinkingConfig requests extended thinking. Anthropic uses "enabled" with a
+// token budget; MiniMax-M3.1-Flash uses "adaptive" with output_config.effort.
 type thinkingConfig struct {
 	Type         string `json:"type"`
-	BudgetTokens int    `json:"budget_tokens"`
+	BudgetTokens int    `json:"budget_tokens,omitempty"`
+}
+
+type outputConfig struct {
+	Effort string `json:"effort"`
 }
 
 type anthropicMessage struct {

internal/providers/providerio/providerio_test.go

@@ -288,10 +288,11 @@ func TestScanSSEDataWithContextContentResetsOnData(t *testing.T) {
 	pr, pw := io.Pipe()
 
 	go func() {
-		// One data line every 30ms for ~300ms (well past the 120ms content window,
-		// with comfortable slack under the 100ms idle timeout), so the content
-		// watchdog keeps resetting, then close cleanly.
-		for i := 0; i < 10; i++ {
+		// One data line every 30ms for ~750ms (well past the 600ms content window,
+		// with ~470ms of slack under the 500ms idle timeout, so a scheduling stall
+		// on a busy shared runner does not trip it), so the content watchdog keeps
+		// resetting, then close cleanly.
+		for i := 0; i < 25; i++ {
 			if _, err := io.WriteString(pw, "data: chunk\n\n"); err != nil {
 				return
 			}
@@ -303,7 +304,7 @@ func TestScanSSEDataWithContextContentResetsOnData(t *testing.T) {
 	n := 0
 	done := make(chan error, 1)
 	go func() {
-		done <- ScanSSEDataWithContext(context.Background(), func() {}, pr, 100*time.Millisecond, func(string) bool { n++; return true })
+		done <- ScanSSEDataWithContext(context.Background(), func() {}, pr, 500*time.Millisecond, func(string) bool { n++; return true })
 	}()
 
 	select {
@@ -314,8 +315,8 @@ func TestScanSSEDataWithContextContentResetsOnData(t *testing.T) {
 	case <-time.After(3 * time.Second):
 		t.Fatal("ScanSSEDataWithContext hung on a producing stream")
 	}
-	if n != 10 {
-		t.Fatalf("handled %d data lines, want 10", n)
+	if n != 25 {
+		t.Fatalf("handled %d data lines, want 25", n)
 	}
 }
 

internal/swarm/lifecycle_test.go

@@ -148,10 +148,13 @@ func TestConcurrencyCapAndQueueDrains(t *testing.T) {
 	}
 	// Release everyone; the queue should drain one-per-slot until all are done.
 	close(gate)
-	testutil.WaitFor(t, "all tasks done", func() bool { return sw.Coordinator().Summarize().Done == 5 })
-	if team.Running() != 0 || team.QueueDepth() != 0 {
-		t.Fatalf("after drain running=%d queue=%d, want 0/0", team.Running(), team.QueueDepth())
-	}
+	// A member's task reads Done before its slot is released: the supervisor
+	// completes the task, then removes the member and only then frees the slot
+	// in afterExit. So the counts are settled once the drain has finished, not
+	// the moment the fifth task reads Done, and the wait covers both.
+	testutil.WaitFor(t, "all tasks done and every slot released", func() bool {
+		return sw.Coordinator().Summarize().Done == 5 && team.Running() == 0 && team.QueueDepth() == 0
+	})
 	if got := len(l.recorded()); got != 5 {
 		t.Fatalf("launched %d members, want 5", got)
 	}

internal/tools/exec_command_test.go

@@ -936,8 +936,15 @@ func TestExecCommandInteractiveBlockSuggestsTTY(t *testing.T) {
 }
 
 func TestExecCommandTTYSkipsInteractiveBlock(t *testing.T) {
-	tool := NewScopedExecCommandTool(t.TempDir(), nil, newExecSessionManager())
-	// ssh to a bogus host fails fast on its own; the point is that the
+	// The ssh can still be resolving the bogus host when the 250ms yield
+	// returns, which leaves its session running in the test root. Stop it
+	// before the root goes, and use execTestRoot for the moment Windows still
+	// holds the directory after the stop.
+	root := execTestRoot(t)
+	manager := newExecSessionManager()
+	t.Cleanup(func() { manager.StopAll() })
+	tool := NewScopedExecCommandTool(root, nil, manager)
+	// ssh to a bogus host fails on its own; the point is that the
 	// interactive guard must not fire ahead of the tty path.
 	result := tool.Run(context.Background(), map[string]any{
 		"cmd": "ssh host.example.com", "tty": true, "yield_time_ms": 250,

internal/tui/model.go

@@ -2,7 +2,6 @@ package tui
 
 import (
 	"context"
-	"encoding/json"
 	"fmt"
 	"os"
 	"path/filepath"
@@ -5965,11 +5964,7 @@ func (m model) runAgentWithOptions(runID int, runCtx context.Context, prompt str
 			// them is flushed at end-of-run AND on cancel (flushRunIDs), so the blobs
 			// never stay orphaned — see its contract in internal/sessions.
 			if m.sessionStore != nil && m.activeSession.SessionID != "" {
-				var args map[string]any
-				if call.Arguments != "" {
-					_ = json.Unmarshal([]byte(call.Arguments), &args)
-				}
-				if targets := tools.MutationTargets(m.cwd, call.Name, args); len(targets) > 0 {
+				if targets := agent.CheckpointTargets(m.cwd, options.Registry, call); len(targets) > 0 {
 					if payload, ok := m.sessionStore.SnapshotForCheckpoint(m.activeSession.SessionID, m.cwd, call.Name, targets); ok {
 						sessionEvents = append(sessionEvents, pendingSessionEvent{
 							Type:    sessions.EventSessionCheckpoint,

internal/tui/provider_wizard_oauth_test.go

@@ -258,7 +258,7 @@ func TestProviderWizardChatGPTOAuthModelsUseCodexSet(t *testing.T) {
 	for _, model := range models {
 		got[model.ID] = true
 	}
-	for _, want := range []string{"gpt-5.5", "gpt-5.4", "gpt-5.4-mini", "gpt-5.3-codex-spark"} {
+	for _, want := range []string{"gpt-6.1-sol", "gpt-6.1-terra", "gpt-6-astra", "gpt-6-luna"} {
 		if !got[want] {
 			t.Fatalf("ChatGPT OAuth models missing %q; got %#v", want, providerWizardModelIDs(models))
 		}
@@ -266,8 +266,8 @@ func TestProviderWizardChatGPTOAuthModelsUseCodexSet(t *testing.T) {
 	if got["gpt-5"] {
 		t.Fatalf("ChatGPT OAuth models should not include stale gpt-5 fallback; got %#v", providerWizardModelIDs(models))
 	}
-	if models[0].ID != "gpt-5.5" {
-		t.Fatalf("default ChatGPT OAuth model = %q, want gpt-5.5", models[0].ID)
+	if models[0].ID != "gpt-6.1-sol" {
+		t.Fatalf("default ChatGPT OAuth model = %q, want gpt-6.1-sol", models[0].ID)
 	}
 }
 

internal/tui/session_test.go

@@ -492,6 +492,54 @@ func TestPermissionPromptAllowWritesFileAndRecordsDecision(t *testing.T) {
 	}
 }
 
+func TestPermissionPromptFreeformApplyPatchRecordsCheckpoint(t *testing.T) {
+	store := testSessionStore(t)
+	root := t.TempDir()
+	writeTestFile(t, root, "main.txt", "before\n")
+	patch := "*** Begin Patch\n*** Update File: main.txt\n@@\n-before\n+after\n*** End Patch\n"
+	provider := &scriptedProvider{scripts: [][]zeroruntime.StreamEvent{
+		freeformApplyPatchToolScript("call_patch", patch),
+		textScript("patched"),
+	}}
+	registry := tools.NewRegistry()
+	registry.Register(tools.NewScopedApplyPatchTool(root, nil))
+	runtimeMessageCh := make(chan tea.Msg, 8)
+	m := newPermissionTestModel(root, provider, registry, store, nil, runtimeMessageCh)
+
+	next := submitAndDrivePermissionRun(t, m, "apply the patch", "a", runtimeMessageCh, 4)
+
+	content, err := os.ReadFile(filepath.Join(root, "main.txt"))
+	if err != nil {
+		t.Fatal(err)
+	}
+	if string(content) != "after\n" {
+		t.Fatalf("patched content = %q, want after newline", content)
+	}
+	events := readOnlySessionEvents(t, store)
+	if got := eventTypes(events); !equalEventTypes(got, []sessions.EventType{
+		sessions.EventMessage,
+		sessions.EventToolCall,
+		sessions.EventSessionCheckpoint,
+		sessions.EventPermissionRequest,
+		sessions.EventPermissionDecision,
+		sessions.EventToolResult,
+		sessions.EventMessage,
+	}) {
+		t.Fatalf("unexpected event sequence: %#v", got)
+	}
+	checkpoint := nthSessionEvent(t, events, sessions.EventSessionCheckpoint, 1)
+	var payload sessions.CheckpointPayload
+	if err := json.Unmarshal(checkpoint.Payload, &payload); err != nil {
+		t.Fatalf("decode checkpoint payload: %v", err)
+	}
+	if len(payload.Files) != 1 || payload.Files[0].Path != "main.txt" || payload.Files[0].Blob == "" {
+		t.Fatalf("checkpoint files = %#v, want main.txt with a blob", payload.Files)
+	}
+	if !transcriptContains(next.transcript, "permission: apply_patch allow") {
+		t.Fatalf("expected allow decision in transcript, got %#v", next.transcript)
+	}
+}
+
 func TestPermissionPromptAlwaysPersistsGrantAndSkipsLaterPrompt(t *testing.T) {
 	store := testSessionStore(t)
 	root := t.TempDir()
@@ -652,6 +700,17 @@ func writeFileToolScript(callID string, path string, content string) []zerorunti
 	}
 }
 
+// freeformApplyPatchToolScript emits a native freeform apply_patch call: the raw
+// patch rides in ArgumentsFragment instead of a JSON object.
+func freeformApplyPatchToolScript(callID string, patch string) []zeroruntime.StreamEvent {
+	return []zeroruntime.StreamEvent{
+		{Type: zeroruntime.StreamEventToolCallStart, ToolCallID: callID, ToolName: "apply_patch", ToolCallFreeform: true},
+		{Type: zeroruntime.StreamEventToolCallDelta, ToolCallID: callID, ArgumentsFragment: patch},
+		{Type: zeroruntime.StreamEventToolCallEnd, ToolCallID: callID},
+		{Type: zeroruntime.StreamEventDone},
+	}
+}
+
 func textScript(text string) []zeroruntime.StreamEvent {
 	return []zeroruntime.StreamEvent{
 		{Type: zeroruntime.StreamEventText, Content: text},

package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "@twigpine/zero",
-  "version": "0.11.0",
+  "version": "0.12.0",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "@twigpine/zero",
-      "version": "0.11.0",
+      "version": "0.12.0",
       "cpu": [
         "x64",
         "arm64"

package.json

@@ -1,6 +1,6 @@
 {
   "name": "@twigpine/zero",
-  "version": "0.11.0",
+  "version": "0.12.0",
   "description": "Zero — a fast, multi-provider terminal coding agent.",
   "type": "module",
   "module": "bin/zero.js",