fix(cli): enter setup on a requires-model config and hint zero auth login

Two residual first-run gaps after the catalog model-defaulting fix: - An active provider whose model has NO catalog default to fall back on (custom openai-/anthropic-compatible endpoints) still bricked bare `zero` and `zero setup` — the exact commands that could have repaired the config. Tag that resolve failure with ErrProviderRequiresModel and extend the interactive TUI's fixable-error fallback (previously only ErrNoActiveProvider) to drop into the setup wizard for it. The sentinel is attached via a message-preserving wrapper (multi-target Unwrap), so headless commands (zero config / zero exec) print the exact actionable text unchanged and every other resolve error stays fatal. - `zero login` / `zero logout` don't exist (it's `zero auth login`); first-run users try them and got only "unknown command" (reported in the wild). The unknown-command error now answers: did you mean "zero auth login"? Unrelated unknown commands get no suggestion. Tests: the sentinel comes from a REAL Resolve over a real config file (message-prefix asserted, no key leak); the TUI fallback is red-green (reverting the condition reproduces the exact brick with the old error); the existing no-active-provider fallback and other-errors-stay-fatal tests still pass; login/logout hint with a no-false-positive check.
fix(config): default missing google/anthropic models from the catalog
2026-11-08 01:09:46 -10:00 · 2026-07-02 18:25:42 +05:30 · 2026-07-02 18:13:30 +05:30
156 changed files with 522 additions and 9892 deletions
@@ -4,14 +4,12 @@ on:
  pull_request:
    paths:
      - action.yml
-      - docs/GITHUB_ACTION.md
      - .github/workflows/zero-action-smoke.yml
  push:
    branches:
      - main
    paths:
      - action.yml
-      - docs/GITHUB_ACTION.md
      - .github/workflows/zero-action-smoke.yml

 jobs:
@@ -31,8 +29,7 @@ jobs:
          import sys, yaml

          with open("action.yml", "r", encoding="utf-8") as handle:
-              action_raw = handle.read()
-          doc = yaml.safe_load(action_raw)
+              doc = yaml.safe_load(handle)

          assert isinstance(doc, dict), "action.yml must be a mapping"
          assert doc.get("name"), "action must declare a name"
@@ -68,19 +65,6 @@ jobs:
          assert "--skip-permissions-unsafe" not in serialized, \
              "action must never pass --skip-permissions-unsafe"

-          run_zero = next((step for step in steps if step.get("name") == "Run ZERO"), None)
-          assert run_zero is not None, "action.yml must contain a Run ZERO step"
-          run_zero_script = run_zero.get("run") or ""
-          assert 'export "${ZERO_INPUT_API_KEY_ENV}=${ZERO_INPUT_API_KEY}"' in run_zero_script, \
-              "Run ZERO must export the provider key for the current step"
-          assert "later steps inherit" not in action_raw.lower(), \
-              "provider keys must not be documented as inherited by later steps"
-          for line in run_zero_script.splitlines():
-              if "GITHUB_ENV" in line and (
-                  "ZERO_INPUT_API_KEY" in line or "ZERO_INPUT_API_KEY_ENV" in line
-              ):
-                  raise AssertionError("provider key must not be persisted to GITHUB_ENV")
-
          print(f"action.yml OK: {len(inputs)} inputs, {len(outputs)} outputs, {len(steps)} steps")
          PY

@@ -26,7 +26,7 @@ Accepted file names, in priority order at each level:
 | `./ZERO.md` | Brand-specific alias. Same format, lower priority. |
 | `./.zero/AGENTS.md` | Project-local, hidden, gitignored. Personal notes that stay out of git. |

-Matching is **case-insensitive** on the basename, so `AGENTS.md`, `Agents.md`, and `agents.md` resolve to the same file on Windows and macOS. The git-tracked filename in this repo is `AGENTS.md` — keep that on case-sensitive filesystems (Linux, the WSL filesystem, or a CI runner) to match what the loader looks for.
+Matching is **case-insensitive** on the basename, so `AGENTS.md`, `Agents.md`, and `agents.md` resolve to the same file on Windows and macOS. The git-tracked filename in this repo is `AGENTS.MD` (uppercase `MD`) — keep that on case-sensitive filesystems (Linux, the WSL filesystem, or a CI runner) to match what the loader looks for.

 Both files use the same format. YAML frontmatter is optional; the markdown body is loaded as instructions for the agent. Zero reads the file once at session start, so changes take effect on the next `zero` launch — not mid-session.

@@ -1,4 +1,4 @@
-# Zero build/test/lint targets. AGENTS.md says "Build with `make`" and "Run `make
+# Zero build/test/lint targets. AGENTS.MD says "Build with `make`" and "Run `make
 # lint` before opening a PR" — these targets back those instructions.
 .DEFAULT_GOAL := build
 .PHONY: build build-all test test-race vet fmt fmt-check lint tidy clean help
@@ -8,8 +8,6 @@
  <a href="LICENSE"><img alt="license" src="https://img.shields.io/badge/license-MIT-blue"></a>
  <img alt="Go 1.25+" src="https://img.shields.io/badge/Go-1.25+-00ADD8?logo=go&logoColor=white">
  <img alt="25+ providers" src="https://img.shields.io/badge/providers-25+-34E2EA">
-  <br>
-  <strong>English</strong> | <a href="README_ZH.md">中文</a>
 </p>

 Zero is an AI coding agent for your local terminal. It can inspect a repository,
@@ -53,31 +51,6 @@ The npm package installs a small wrapper plus the matching Zero binary for your
 platform from GitHub Releases. It supports Linux, macOS, and Windows on x64 and
 arm64.

-### Bun
-
-Bun does not run dependency lifecycle scripts by default, so the `postinstall`
-that fetches the Zero binary is skipped and the first run fails with
-`No native binary found next to the npm wrapper`.
-
-The simplest fix is to trust the package after installing, which runs the
-blocked postinstall. This works for project and global installs:
-
-```bash
-# project install
-bun add @gitlawb/zero
-bun pm trust @gitlawb/zero
-
-# global install
-bun add -g @gitlawb/zero
-bun pm -g trust @gitlawb/zero
-```
-
-Alternatives: allow the postinstall up front by adding
-`"trustedDependencies": ["@gitlawb/zero"]` to your project's package.json
-before `bun add`, or run the installer manually
-(`node node_modules/@gitlawb/zero/scripts/postinstall.mjs`) on Bun versions
-that do not have `bun pm trust`.
-
 ### Install scripts

 Linux/macOS:
@@ -148,13 +121,6 @@ the key in the wizard:
 export OPENAI_API_KEY=sk-...
 export ANTHROPIC_API_KEY=...
 export GEMINI_API_KEY=...
-export LONGCAT_API_KEY=...
-```
-
-To configure Meituan LongCat (LongCat-2.0) directly, run:
-
-```bash
-zero providers setup longcat --set-active
 ```

 For local models, run Ollama or LM Studio and then use `zero setup` or
@@ -1,297 +0,0 @@
-<p align="center">
-  <img src="docs/assets/zero-logo.png" alt="Zero" width="385">
-</p>
-
-<p align="center"><strong>一个独属于你的终端编码智能体。</strong></p>
-
-<p align="center">
-  <a href="LICENSE"><img alt="license" src="https://img.shields.io/badge/license-MIT-blue"></a>
-  <img alt="Go 1.25+" src="https://img.shields.io/badge/Go-1.25+-00ADD8?logo=go&logoColor=white">
-  <img alt="25+ providers" src="https://img.shields.io/badge/providers-25+-34E2EA">
-  <br>
-  <a href="README.md">English</a> | <strong>中文</strong>
-</p>
-
-Zero 是一个用于本地终端的 AI 编码智能体。它可以检查仓库、编辑文件、运行命令、使用浏览器/终端辅助工具，并在你选择模型和权限级别的同时保持持久的本地会话。
-
-```bash
-zero
-zero exec "修复 ./pkg 中失败的测试"
-zero exec --output-format stream-json < turns.jsonl
-```
-
-## 为什么选择 Zero
-
- **使用你想要的模型。** 支持 OpenAI、Anthropic、Gemini、Groq、OpenRouter、DeepSeek、Mistral、xAI、Qwen、Kimi、GitHub Models、Ollama、LM Studio，或任何 OpenAI/Anthropic 兼容端点。
- **保持控制权。** 文件写入、Shell 命令、网络访问和工作区外写入都经过 Zero 的权限和沙箱策略。
- **在终端中工作。** TUI 具有模型/提供商选择器、图片输入、斜杠命令、实时计划/工具渲染、回滚滚动、主题以及恢复/分叉支持。
- **无 TUI 也能工作。** `zero exec` 可脚本化，支持文本/JSON/stream-JSON I/O、隔离的工作树、规范优先运行，以及用于 CI 的有意义的退出码。
- **保持上下文本地化。** 会话存储在磁盘上，可搜索、可恢复，且 Zero 不会作为遥测数据上传。
- **可扩展。** 使用 MCP 服务器、技能、插件、钩子和来自同一 CLI 的专业子智能体。
-
-## 安装
-
-### npm
-
-```bash
-npm install -g @gitlawb/zero
-zero
-```
-
-npm 包安装一个小型包装器以及与你平台匹配的 Zero 二进制文件（从 GitHub Releases 获取）。支持 Linux、macOS 和 Windows 的 x64 和 arm64。
-
-### Bun
-
-Bun 默认不运行依赖的生命周期脚本，因此获取 Zero 二进制文件的 `postinstall` 会被跳过，首次运行会失败并显示 `No native binary found next to the npm wrapper`。
-
-最简单的解决方法是安装后信任该包，这会运行被阻止的 postinstall。项目安装和全局安装均适用：
-
-```bash
-# 项目安装
-bun add @gitlawb/zero
-bun pm trust @gitlawb/zero
-
-# 全局安装
-bun add -g @gitlawb/zero
-bun pm -g trust @gitlawb/zero
-```
-
-其他方式：在 `bun add` 之前将 `"trustedDependencies": ["@gitlawb/zero"]` 添加到项目的 package.json 以提前允许 postinstall；或在不支持 `bun pm trust` 的旧版 Bun 上手动运行安装程序（`node node_modules/@gitlawb/zero/scripts/postinstall.mjs`）。
-
-### 安装脚本
-
-Linux/macOS：
-
-```bash
-curl -fsSL https://raw.githubusercontent.com/Gitlawb/zero/main/scripts/install.sh | bash
-```
-
-Windows PowerShell：
-
-```powershell
-irm https://raw.githubusercontent.com/Gitlawb/zero/main/scripts/install.ps1 | iex
-```
-
-### 从源码构建
-
-源码构建需要 Go 1.25+。
-
-```bash
-git clone https://github.com/Gitlawb/zero.git
-cd zero
-go run ./cmd/zero
-```
-
-发布安装器和 npm 包需要已发布的 GitHub Release 资源。如果你在首次公开发布之前进行测试，请从源码构建：
-
-```bash
-go build -o zero ./cmd/zero
-```
-
-在 Linux 上，如果你需要原生沙箱，还需要构建沙箱辅助程序：
-
-```bash
-go build -o zero-linux-sandbox ./cmd/zero-linux-sandbox
-go build -o zero-seccomp ./cmd/zero-seccomp   # 可选的兼容性包装器
-```
-
-将 `zero` 和 `zero-linux-sandbox` 放在 `PATH` 上的同一目录中（`~/.local/bin` 是一个好的默认选择）。macOS 不需要额外的辅助二进制文件。Windows 源码构建可以使用主 `zero.exe` 作为沙箱辅助程序；发布包仍然附带独立的 Windows 辅助可执行文件。
-
-更多安装细节：[docs/INSTALL.md](docs/INSTALL.md)。
-
-## 首次运行
-
-启动 TUI：
-
-```bash
-zero
-```
-
-设置向导帮助你选择提供商和模型。你也可以从命令行配置提供商：
-
-```bash
-zero setup
-zero providers list
-zero models list
-zero doctor
-```
-
-对于 API 提供商，在设置之前设置匹配的环境变量或在向导中输入密钥：
-
-```bash
-export OPENAI_API_KEY=sk-...
-export ANTHROPIC_API_KEY=...
-export GEMINI_API_KEY=...
-export LONGCAT_API_KEY=...
-```
-
-要直接配置美团 LongCat（LongCat-2.0），运行：
-
-```bash
-zero providers setup longcat --set-active
-```
-
-对于本地模型，运行 Ollama 或 LM Studio，然后使用 `zero setup` 或 `zero providers detect`。
-
-## 日常使用
-
-### 交互式 TUI
-
-```bash
-zero
-```
-
-常用控制：
-
-| 控制 | 操作 |
-|---|---|
-| `Enter` | 发送提示 |
-| `/` | 打开斜杠命令建议 |
-| `Shift+Tab` | 切换权限模式 |
-| `Ctrl+B` | 显示/隐藏侧边栏 |
-| `Ctrl+C` | 取消或退出 |
-
-常用斜杠命令：
-
-| 命令 | 用途 |
-|---|---|
-| `/model`、`/provider` | 切换活动模型/提供商 |
-| `/spec`、`/plan` | 在构建之前起草和审查计划 |
-| `/image` | 为视觉模型附加图片 |
-| `/resume`、`/rewind` | 继续或回滚本地会话 |
-| `/compact`、`/context` | 管理上下文使用 |
-| `/permissions`、`/tools` | 检查可用工具和策略 |
-| `/add-dir` | 为此会话授予额外的写入目录 |
-| `/theme`、`/doctor`、`/config` | 调整外观和检查设置 |
-
-### 无头 `exec` 模式
-
-```bash
-zero exec "解释 internal/agent/loop.go"
-zero exec --model claude-sonnet-4.5 "重构配置加载器"
-zero exec --use-spec "为 API 客户端添加速率限制"
-zero exec --worktree "在隔离的工作树中尝试迁移"
-zero exec --resume
-zero exec --fork <session-id> "尝试另一种方法"
-```
-
-编程使用：
-
-```bash
-zero exec --input-format stream-json --output-format stream-json < turns.jsonl
-```
-
-Stream-JSON 协议文档在 [docs/STREAM_JSON_PROTOCOL.md](docs/STREAM_JSON_PROTOCOL.md)。
-
-## 安全模型
-
-Zero 旨在使副作用可见。
-
- 工作区读取默认允许。
- 文件写入限制在工作区内，除非你授予其他目录。
- Shell 命令、网络访问、破坏性命令和提权操作需要权限授权。
- `--add-dir <path>` 和 `/add-dir <path>` 授予额外的写入根目录，而不会给智能体整个文件系统。
- 不安全/自主模式是显式选择加入。
- 在 Zero 控制的界面上，密钥会从工具输出和日志中被脱敏。
-
-示例：
-
-```bash
-zero --add-dir ../docs-site
-zero exec --add-dir ../shared "更新两个仓库"
-```
-
-沙箱行为可以通过以下方式检查：
-
-```bash
-zero sandbox policy
-zero sandbox grants list
-```
-
-## Web 和本地控制
-
-Zero 包含本地文件/搜索/编辑/Shell 工具、用于公共 URL 的 `web_fetch`，以及用于额外工具的 MCP 支持。
-
-对于本地开发服务器，使用 Shell 命令（如通过 `exec_command` 的 `curl`），这样正常的沙箱和权限策略就会生效。长时间运行的命令保持附加到后台终端会话，可以从 TUI 中列出或停止。
-
-npm 包还包含本地浏览器/终端工具使用的浏览器和终端辅助包。源码构建可以在它们位于 `PATH` 上或在 Zero 的本地控制设置中配置时使用相同的辅助工具。
-
-## 常用命令
-
-```text
-zero                  交互式 TUI
-zero exec             一次性或脚本化智能体运行
-zero setup            首次运行提供商设置
-zero auth             支持提供商的 OAuth/登录辅助
-zero models           模型注册表和能力
-zero providers        提供商配置和检测
-zero doctor           设置、密钥和连接检查
-zero context          上下文预算报告
-zero repo-map         确定性仓库映射
-zero repo-info        本地仓库摘要
-zero search | find    搜索本地会话历史
-zero sessions         检查、恢复、分叉和回滚会话
-zero spec             管理规范模式草稿
-zero specialist       管理专业子智能体
-zero skills           管理 Markdown 指令技能
-zero plugins          管理插件
-zero hooks            管理生命周期钩子
-zero mcp              管理 MCP 服务器和工具
-zero serve --mcp      通过 MCP stdio 暴露 Zero 工具
-zero sandbox          检查沙箱策略和授权
-zero worktrees        准备隔离的 Git 工作树
-zero verify           检测和运行本地验证检查
-zero changes          检查和提交本地 Git 变更
-zero usage            Token 使用量和估算成本
-zero cron             定时智能体任务
-zero update           检查更新版本
-```
-
-## 外观和无障碍
-
-| 控制 | 效果 |
-|---|---|
-| `NO_COLOR=<任意值>` | 禁用颜色输出 |
-| `ZERO_THEME=<名称>` | 选择启动主题（`auto`、`dark`、`light`，或颜色主题如 `dracula`、`nord`、`gruvbox`、`tokyo-night`、`catppuccin`、`one-dark`、`solarized-dark`、`rose-pine`、`everforest`、`solarized-light`） |
-| `--theme <名称>` | 从 CLI 选择 TUI 主题（相同名称） |
-| `/theme` | 在 TUI 中打开主题选择器（实时预览；`/theme <名称>` 直接切换） |
-| `ZERO_NO_FADE=1` | 禁用流式淡入动画 |
-
-含义不仅仅依赖于颜色；差异、权限和状态也使用文本或标记符号。
-
-## 开发
-
-```bash
-go test ./...
-go run ./cmd/zero-release build
-go run ./cmd/zero-release smoke
-go run ./cmd/zero-perf-bench
-```
-
-交叉编译示例：
-
-```bash
-go run ./cmd/zero-release build --goos linux --goarch amd64
-go run ./cmd/zero-release build --goos windows --goarch amd64 --output dist/zero.exe
-```
-
-## 文档
-
- [安装](docs/INSTALL.md)
- [更新流程](docs/UPDATE.md)
- [Stream-JSON 协议](docs/STREAM_JSON_PROTOCOL.md)
- [专家](docs/SPECIALISTS.md)
- [GitHub Action](docs/GITHUB_ACTION.md)
- [基准测试](docs/BENCHMARK.md)
- [性能](docs/PERFORMANCE.md)
- [智能体评估](docs/AGENT_EVALS.md)
-
-## 贡献
-
-欢迎贡献。阅读 [CONTRIBUTING.md](CONTRIBUTING.md)，运行相关测试，然后提交一个聚焦的拉取请求。
-
-安全报告应遵循 [SECURITY.md](SECURITY.md)。
-
-## 许可证
-
-Zero 基于 [MIT 许可证](LICENSE) 发布。
@@ -27,14 +27,14 @@ inputs:
  api-key:
    description: >-
      The provider API key. Pass it from a repository or organization secret;
-      it is exported only for the ZERO step and never written to the log.
+      it is exported into the step environment and never written to the log.
    required: false
    default: ""
  api-key-env:
    description: >-
      Name of the environment variable the chosen provider reads its key from
      (for example OPENAI_API_KEY or ANTHROPIC_API_KEY). When set together with
-      api-key, that variable is exported only for the ZERO step. Leave the action
+      api-key, that variable is exported for the run. Leave the action
      provider-agnostic by passing the env name your provider expects rather
      than hardcoding one here.
    required: false
@@ -192,9 +192,10 @@ runs:
            echo "::error::api-key-env must be a valid environment variable name." >&2
            exit 2
          fi
-          # Export in-process for this Run ZERO step so zero can read it; do
-          # not persist provider credentials to later job steps.
+          # Export in-process so the zero invocation in this same run block sees
+          # it, and append to GITHUB_ENV so any later steps inherit it too.
          export "${ZERO_INPUT_API_KEY_ENV}=${ZERO_INPUT_API_KEY}"
+          printf '%s=%s\n' "${ZERO_INPUT_API_KEY_ENV}" "${ZERO_INPUT_API_KEY}" >> "${GITHUB_ENV}"
        fi
        if [ -n "${ZERO_INPUT_PROVIDER}" ]; then
          export ZERO_PROVIDER="${ZERO_INPUT_PROVIDER}"
@@ -54,28 +54,8 @@ const nativePath = join(packageRoot, zeroBinaryName());
 const localControlHelpers = localControlHelperManifest(packageRoot);

 if (!existsSync(nativePath)) {
-  const postinstallScript = join(packageRoot, 'scripts', 'postinstall.mjs');
-  const ranByBun = process.execPath.includes('bun') || !!process.versions?.bun;
  console.error(
-    '[zero] No native binary found next to the npm wrapper.\n' +
-      'The platform binary is fetched at install time by a postinstall script,\n' +
-      'which did not run (or was skipped) for this install.\n' +
-      '\n' +
-      'Fix it now by running the installer manually:\n' +
-      `  node "${postinstallScript}"\n` +
-      '\n' +
-      (ranByBun
-        ? 'You installed with Bun, which does not run dependency lifecycle scripts\n' +
-          'by default. Trust the package to run the blocked postinstall:\n' +
-          '  bun pm trust @gitlawb/zero       (project install)\n' +
-          '  bun pm -g trust @gitlawb/zero    (global install)\n' +
-          'On Bun versions without `bun pm trust`, add\n' +
-          '  "trustedDependencies": ["@gitlawb/zero"]\n' +
-          'to your project package.json and reinstall.\n' +
-          '\n'
-        : '') +
-      'If that fails, build from source: https://github.com/Gitlawb/zero\n' +
-      '(go run ./cmd/zero, requires Go 1.25+).',
+    '[zero] No native binary found next to the npm wrapper. Reinstall the zero package or run `go run ./cmd/zero-release build` from the repository.'
  );
  process.exit(1);
 }
@@ -41,9 +41,8 @@ jobs:
 > provider-neutral: `api-key-env` is the environment variable name the chosen
 > provider reads its key from (for example `ANTHROPIC_API_KEY`, `GEMINI_API_KEY`,
 > `OPENROUTER_API_KEY`), and `api-key` is the secret value. The action exports
-> that variable only for the ZERO step and never prints it. If your repository
-> already commits a `.zero/config.json` with an active provider, you can omit
-> `provider`.
+> that variable for the run and never prints it. If your repository already
+> commits a `.zero/config.json` with an active provider, you can omit `provider`.

 ## Inputs

@@ -52,8 +51,8 @@ jobs:
 | `prompt` | one of `prompt`/`prompt-file` | `""` | The instruction for ZERO to execute. |
 | `prompt-file` | one of `prompt`/`prompt-file` | `""` | Path (relative to `working-directory`) to a file whose contents are the prompt. |
 | `provider` | no | `""` | Provider id to activate (e.g. `openai`, `anthropic`, `gemini`, `ollama`, or any compatible endpoint). |
-| `api-key` | no | `""` | The provider API key. Pass from a secret; exported only for the ZERO step and never logged. |
-| `api-key-env` | no | `""` | Env var name the provider reads its key from (e.g. `OPENAI_API_KEY`). Exported only for the ZERO step when used with `api-key`. |
+| `api-key` | no | `""` | The provider API key. Pass from a secret; never logged. |
+| `api-key-env` | no | `""` | Env var name the provider reads its key from (e.g. `OPENAI_API_KEY`). Exported with `api-key`. |
 | `model` | no | `""` | Model id. Defaults to the resolved provider's default. |
 | `mode` | no | `""` | Run mode (`zero exec --mode`), e.g. `smart`, `deep`, `fast`. |
 | `auto` | no | `low` | Autonomy ceiling (`zero exec --auto`): `low`, `medium`, or `high`. Conservative by default. |
@@ -163,10 +162,9 @@ jobs:
 ## Security notes

 - **Secrets are passed as Action secrets and never logged.** The action exports
-  `api-key` (under `api-key-env`) only for the ZERO step. `slack-webhook-url`
-  is passed only to the Slack post step. They are never echoed or persisted to
-  later workflow steps, and ZERO redacts secret-shaped strings from its own
-  output.
+  `api-key` (under `api-key-env`) and `slack-webhook-url` into the step
+  environment only. They are never echoed, and ZERO redacts secret-shaped
+  strings from its own output.
 - **The sandbox is always active.** This action never passes
  `--skip-permissions-unsafe`, so writes stay inside the checked-out repository
  (plus any roots you grant with `add-dir`). Unsafe mode is never enabled
@@ -24,51 +24,6 @@ Requirements:
 - Node.js 18+
 - network access to npm and GitHub Releases

-## Bun
-
-Bun is "default-secure" and does not run lifecycle scripts of installed
-dependencies (only the installing project's own scripts), so the `postinstall`
-that fetches the Zero binary is silently skipped. The first run then fails with
-`No native binary found next to the npm wrapper`.
-
-The simplest fix is to trust the package after installing, which runs the
-blocked postinstall. This works for project and global installs:
-
-```bash
-# project install
-bun add @gitlawb/zero
-bun pm trust @gitlawb/zero
-
-# global install
-bun add -g @gitlawb/zero
-bun pm -g trust @gitlawb/zero
-```
-
-`bun pm untrusted` (or `bun pm -g untrusted`) lists the blocked postinstalls if
-you want to inspect before trusting.
-
-Alternatively, allow the postinstall to run at install time by adding the
-package to your project's `trustedDependencies` before installing:
-
-```json
-{
-  "trustedDependencies": ["@gitlawb/zero"]
-}
-```
-
-```bash
-bun add @gitlawb/zero
-```
-
-On Bun versions that do not have `bun pm trust`, run the installer manually
-after installing:
-
-```bash
-node node_modules/@gitlawb/zero/scripts/postinstall.mjs
-```
-
-Reference: <https://bun.sh/docs/pm/lifecycle>
-
 ## Linux And macOS Script

 Install the latest release:
@@ -1,146 +0,0 @@
-package agent
-
-import (
-	"context"
-	"strings"
-	"testing"
-
-	"github.com/Gitlawb/zero/internal/tools"
-)
-
-// A shell call that sets sandbox_permissions: with_additional_permissions but
-// omits (or malforms) additional_permissions can never succeed: the same
-// validation runs again at grant time regardless of the user's decision. It
-// must be rejected as a plain tool error BEFORE any permission prompt, not
-// surfaced as a confusing "approved but denied" prompt outcome.
-func TestExecuteToolCallRejectsMissingAdditionalPermissionsBeforePrompt(t *testing.T) {
-	root := t.TempDir()
-	registry := tools.NewRegistry()
-	registry.Register(tools.NewBashTool(root))
-
-	promptCalls := 0
-	result, err := executeToolCall(
-		context.Background(),
-		registry,
-		ToolCall{
-			ID:        "c1",
-			Name:      "bash",
-			Arguments: `{"command":"echo hi","sandbox_permissions":"with_additional_permissions"}`,
-		},
-		PermissionModeAuto,
-		Options{
-			OnPermissionRequest: func(ctx context.Context, request PermissionRequest) (PermissionDecision, error) {
-				promptCalls++
-				return PermissionDecision{Action: PermissionDecisionAllow}, nil
-			},
-		},
-	)
-	if err != nil {
-		t.Fatalf("executeToolCall: %v", err)
-	}
-	if result.Status != tools.StatusError {
-		t.Fatalf("status = %q, want error", result.Status)
-	}
-	if promptCalls != 0 {
-		t.Fatalf("OnPermissionRequest called %d times, want 0 (must reject before prompting)", promptCalls)
-	}
-}
-
-// The mismatched-flag case (additional_permissions present without the
-// sandbox_permissions flag) must be rejected the same way.
-func TestExecuteToolCallRejectsAdditionalPermissionsWithoutFlagBeforePrompt(t *testing.T) {
-	root := t.TempDir()
-	registry := tools.NewRegistry()
-	registry.Register(tools.NewBashTool(root))
-
-	promptCalls := 0
-	result, err := executeToolCall(
-		context.Background(),
-		registry,
-		ToolCall{
-			ID:        "c1",
-			Name:      "bash",
-			Arguments: `{"command":"echo hi","additional_permissions":{"network":{"enabled":true}}}`,
-		},
-		PermissionModeAuto,
-		Options{
-			OnPermissionRequest: func(ctx context.Context, request PermissionRequest) (PermissionDecision, error) {
-				promptCalls++
-				return PermissionDecision{Action: PermissionDecisionAllow}, nil
-			},
-		},
-	)
-	if err != nil {
-		t.Fatalf("executeToolCall: %v", err)
-	}
-	if result.Status != tools.StatusError {
-		t.Fatalf("status = %q, want error", result.Status)
-	}
-	if promptCalls != 0 {
-		t.Fatalf("OnPermissionRequest called %d times, want 0 (must reject before prompting)", promptCalls)
-	}
-}
-
-// The rejection message must show a concrete, correctly-shaped example: a
-// model that gets this wrong once (attaching sandbox_permissions out of habit
-// from an earlier call, without a valid payload) needs enough in the error to
-// self-correct on retry instead of repeating the identical mistake.
-func TestExecuteToolCallMissingAdditionalPermissionsErrorIsActionable(t *testing.T) {
-	root := t.TempDir()
-	registry := tools.NewRegistry()
-	registry.Register(tools.NewBashTool(root))
-
-	result, err := executeToolCall(
-		context.Background(),
-		registry,
-		ToolCall{
-			ID:        "c1",
-			Name:      "bash",
-			Arguments: `{"command":"ping example.com","sandbox_permissions":"with_additional_permissions"}`,
-		},
-		PermissionModeAuto,
-		Options{},
-	)
-	if err != nil {
-		t.Fatalf("executeToolCall: %v", err)
-	}
-	if !strings.Contains(result.Output, `{"network": {"enabled": true}}`) {
-		t.Fatalf("output = %q, want a concrete additional_permissions example", result.Output)
-	}
-	if !strings.Contains(result.Output, "omit sandbox_permissions") {
-		t.Fatalf("output = %q, want guidance that the flag can simply be omitted", result.Output)
-	}
-}
-
-// A well-formed additional_permissions payload must still reach the normal
-// permission prompt: this fix only rejects malformed payloads.
-func TestExecuteToolCallStillPromptsForValidAdditionalPermissions(t *testing.T) {
-	root := t.TempDir()
-	registry := tools.NewRegistry()
-	registry.Register(tools.NewBashTool(root))
-
-	promptCalls := 0
-	_, err := executeToolCall(
-		context.Background(),
-		registry,
-		ToolCall{
-			ID:   "c1",
-			Name: "bash",
-			Arguments: `{"command":"echo hi","sandbox_permissions":"with_additional_permissions",` +
-				`"additional_permissions":{"network":{"enabled":true}}}`,
-		},
-		PermissionModeAuto,
-		Options{
-			OnPermissionRequest: func(ctx context.Context, request PermissionRequest) (PermissionDecision, error) {
-				promptCalls++
-				return PermissionDecision{Action: PermissionDecisionDeny}, nil
-			},
-		},
-	)
-	if err != nil {
-		t.Fatalf("executeToolCall: %v", err)
-	}
-	if promptCalls != 1 {
-		t.Fatalf("OnPermissionRequest called %d times, want exactly 1 for a valid elevation request", promptCalls)
-	}
-}
@@ -21,17 +21,12 @@ import (
 // the agent loop owns the provider wiring.

 // defaultCompactionPreserveLast is how many trailing messages are kept verbatim
-// when the caller does not specify a preserve count. Kept in sync with the replay
-// reconstruction default in internal/sessions/replay.go.
-const defaultCompactionPreserveLast = 6
+// when the caller does not specify a preserve count.
+const defaultCompactionPreserveLast = 8

 // compactionTriggerRatio is the fraction of the context window at which
-// proactive compaction kicks in (top of each turn). NOTE: this is speculative
-// tuning — validate against the per-turn latency/compaction metrics (roadmap 5.2)
-// before trusting it. Measured fixed overhead is ~7.4k tokens (not the ~16k the
-// roadmap assumed), so context fills slower; if data shows 0.7 triggers redundant
-// summarization, raise it back toward 0.8.
-const compactionTriggerRatio = 0.7
+// proactive compaction kicks in (top of each turn).
+const compactionTriggerRatio = 0.8

 // summaryLabel prefixes the injected summary so it is unmistakable in the
 // transcript (and so tests can assert on it).
@@ -1,44 +0,0 @@
-package agent
-
-import (
-	"context"
-	"os"
-	"time"
-
-	"github.com/Gitlawb/zero/internal/lsp"
-)
-
-// fileDiagnosticsTimeout bounds one inline post-edit diagnostics check so a
-// slow or wedged language server can never hang a tool call; on timeout the
-// edit simply reports without a diagnostics block.
-const fileDiagnosticsTimeout = 10 * time.Second
-
-// NewFileDiagnostics adapts an *lsp.Manager to the per-edit inline diagnostics
-// callback (tools.RunOptions.Diagnostics): it reads the just-written file,
-// checks it against the file's language server, and formats error-severity
-// diagnostics for the model. Warnings and hints are excluded — nagging about
-// style on every edit is noise, while a type error the edit just introduced is
-// exactly what the model should see before its next step. Returns nil when
-// manager is nil, disabling inline diagnostics entirely.
-func NewFileDiagnostics(manager *lsp.Manager) func(context.Context, string) string {
-	if manager == nil {
-		return nil
-	}
-	return func(ctx context.Context, absPath string) string {
-		text, err := os.ReadFile(absPath)
-		if err != nil {
-			return ""
-		}
-		checkCtx, cancel := context.WithTimeout(ctx, fileDiagnosticsTimeout)
-		defer cancel()
-		diagnostics, err := manager.Check(checkCtx, absPath, string(text))
-		if err != nil {
-			return ""
-		}
-		errors := lsp.FilterBySeverity(diagnostics, lsp.SeverityError)
-		if len(errors) == 0 {
-			return ""
-		}
-		return lsp.FormatDiagnostics(absPath, errors)
-	}
-}
@@ -475,35 +475,11 @@ func Run(ctx context.Context, prompt string, provider Provider, options Options)
 		// between tool_results breaks strict provider replay) — same after-batch
 		// rationale as turnRequestedModel above.
 		var changedFilesThisBatch []string
-		// Parallel read-ahead state: results for calls[precomputedStart:precomputedEnd]
-		// executed concurrently, consumed strictly in order below.
-		var precomputed []precomputedToolResult
-		precomputedStart, precomputedEnd := 0, 0
 		for index, call := range collected.ToolCalls {
-			// When this call starts a consecutive run of >= 2 auto-allowed read-only
-			// calls, execute the whole run concurrently now (see parallel_tools.go).
-			// The scan happens lazily at the run's first index — never ahead of a
-			// pending mutating call — so read-after-write ordering is preserved.
-			if index >= precomputedEnd {
-				runEnd := index
-				for runEnd < len(collected.ToolCalls) && parallelSafeToolCall(registry, collected.ToolCalls[runEnd], options) {
-					runEnd++
-				}
-				if runEnd-index >= 2 {
-					precomputed = executeParallelReadBatch(ctx, registry, collected.ToolCalls, index, runEnd, permissionMode, options)
-					precomputedStart, precomputedEnd = index, runEnd
-				}
-			}
 			if options.OnToolCall != nil {
 				options.OnToolCall(call)
 			}
-			var toolResult ToolResult
-			var abortErr error
-			if index >= precomputedStart && index < precomputedEnd {
-				toolResult, abortErr = precomputed[index-precomputedStart].result, precomputed[index-precomputedStart].abortErr
-			} else {
-				toolResult, abortErr = executeToolCall(ctx, registry, call, permissionMode, options)
-			}
+			toolResult, abortErr := executeToolCall(ctx, registry, call, permissionMode, options)
 			if options.OnToolResult != nil {
 				options.OnToolResult(toolResult)
 			}
@@ -840,25 +816,6 @@ func executeToolCall(ctx context.Context, registry *tools.Registry, call ToolCal
 		}
 	}

-	// A shell command that sets sandbox_permissions: with_additional_permissions
-	// must carry a valid additional_permissions payload; inlineAdditionalPermissionsProfile
-	// is the single source of truth for that shape, and buildPermissionEvent (below)
-	// calls it again to render the prompt's scope text. Check it here, before any
-	// permission prompt is shown: a malformed payload can never be satisfied no
-	// matter what the user decides, so surfacing it as a plain tool error (which the
-	// model can see and retry) is both clearer and avoids presenting a normal-looking
-	// prompt whose "allow" path is guaranteed to fail with a confusing denial.
-	if toolFound && isShellCommandTool(call.Name) {
-		if _, _, err := inlineAdditionalPermissionsProfile(args, options.Cwd); err != nil {
-			return ToolResult{
-				ToolCallID: call.ID,
-				Name:       call.Name,
-				Status:     tools.StatusError,
-				Output:     "Error: " + err.Error(),
-			}, nil
-		}
-	}
-
 	// ask_user is intercepted in the loop (like permissions) so the question can
 	// be routed to an interactive front-end instead of blocking inside the tool.
 	// When no front-end is wired up it degrades to the tool's own graceful Run().
@@ -1075,8 +1032,6 @@ func executeToolCall(ctx context.Context, registry *tools.Registry, call ToolCal
 		// Per-session file version tracker so write_file/edit_file refuse to clobber
 		// a file that changed on disk outside Zero since it was last read.
 		FileTracker: options.FileTracker,
-		// Inline post-edit diagnostics for mutating tools (nil = disabled).
-		Diagnostics: options.FileDiagnostics,
 		// Forward the run's operator tool filters so a filter-aware tool
 		// (tool_search) never discloses or loads an operator-hidden deferred tool.
 		EnabledTools:  options.EnabledTools,
@@ -2204,18 +2159,6 @@ func buildPermissionEvent(call ToolCall, tool tools.Tool, args map[string]any, p
 		}
 	}

-	// A command that explicitly requests additional sandbox permissions
-	// (sandbox_permissions: with_additional_permissions) is an ELEVATION the user
-	// must consent to, even when the base command's sandbox decision was Allow.
-	// shouldRequestPermission blocks on OnPermissionRequest for exactly this case,
-	// so the event MUST be a prompt — otherwise it carried Action=allow while the
-	// loop waited on a decision, and a UI that renders only prompts (the TUI)
-	// dropped it, deadlocking the run. Keep this consistent with
-	// shouldRequestPermission's own condition.
-	if action == PermissionActionAllow && !permissionGranted && shellCommandAdditionalPermissionsRequested(args) {
-		action = PermissionActionPrompt
-	}
-
 	if safety.Permission == tools.PermissionAllow && action == PermissionActionAllow && !grantMatched && block == nil {
 		return PermissionEvent{}, false
 	}
@@ -2367,12 +2310,7 @@ func inlineAdditionalPermissionsProfile(args map[string]any, basePath string) (s
 	}
 	raw, ok := args["additional_permissions"]
 	if !ok || raw == nil {
-		return sandbox.RequestPermissionProfile{}, true, fmt.Errorf(
-			"sandbox_permissions was set to %q but no additional_permissions object was provided. "+
-				`Include one, for example additional_permissions: {"network": {"enabled": true}} or `+
-				`{"file_system": {"write": ["/path"]}}. If this command does not need elevated permissions, `+
-				"omit sandbox_permissions entirely and retry",
-			tools.SandboxPermissionsWithAdditionalPermissions)
+		return sandbox.RequestPermissionProfile{}, true, fmt.Errorf("missing additional_permissions; provide at least one of network or file_system")
 	}
 	data, err := json.Marshal(raw)
 	if err != nil {
@@ -2387,9 +2325,7 @@ func inlineAdditionalPermissionsProfile(args map[string]any, basePath string) (s
 		return sandbox.RequestPermissionProfile{}, true, err
 	}
 	if normalized.Empty() {
-		return sandbox.RequestPermissionProfile{}, true, fmt.Errorf(
-			"additional_permissions must include at least one of network or file_system, for example " +
-				`{"network": {"enabled": true}} or {"file_system": {"write": ["/path"]}}`)
+		return sandbox.RequestPermissionProfile{}, true, fmt.Errorf("additional_permissions must include at least one requested permission in network or file_system")
 	}
 	grantProfile, err := sandbox.RequestPermissionGrantProfile(normalized)
 	if err != nil {
@@ -2522,97 +2458,76 @@ func partitionTools(registry *tools.Registry, permissionMode PermissionMode, opt

 	active := options.DeferThreshold > 0 && eligible >= options.DeferThreshold && loaderUsable

-	// INACTIVE: every visible tool eager (except tool_search), alpha-sorted. With no
-	// deferral there is no mid-session loading, so this is byte-stable across turns
-	// and byte-identical to the pre-deferral output.
-	if !active {
-		definitions := make([]zeroruntime.ToolDefinition, 0, len(visible))
-		for _, tool := range visible {
-			if tool.Name() == tools.ToolSearchToolName {
-				continue
-			}
-			definitions = append(definitions, runtimeToolDefinition(tool))
-		}
-		sort.Slice(definitions, func(left int, right int) bool {
-			return definitions[left].Name < definitions[right].Name
-		})
-		return definitions, ""
-	}
-
-	// ACTIVE: lay the tools array out so its cacheable prefix does NOT shift when a
-	// deferred tool loads mid-session. The tools block is part of the provider's
-	// cached prefix; if a load reorders it, the cache invalidates from that point
-	// through the system prompt and messages — on EVERY load. Previously the whole
-	// array was alpha-sorted each turn, so a newly loaded tool was INSERTED into the
-	// middle and shifted every later definition. Instead we build three append-only
-	// regions:
-	//   1. non-deferred tools, alpha-sorted — always present, identical every turn;
-	//   2. tool_search — always present, right after the stable block;
-	//   3. loaded deferred tools, alpha-sorted — APPENDED, so an unloaded->loaded
-	//      transition grows the tail instead of inserting into the eager block.
-	// (tool_search's discovery text still shrinks as tools load, so keeping it and
-	// the loaded tail AFTER the eager block preserves the eager tools' cache across a
-	// load; fully stabilizing the loader's own description is a scoped follow-up.)
-	eager := make([]zeroruntime.ToolDefinition, 0, len(visible))
-	loadedTail := make([]zeroruntime.ToolDefinition, 0)
+	definitions := make([]zeroruntime.ToolDefinition, 0, len(visible))
+	exposedNames := make(map[string]bool, len(visible))
 	var hiddenTools []tools.Tool
 	for _, tool := range visible {
 		name := tool.Name()
-		if name == tools.ToolSearchToolName {
-			continue // added explicitly between the eager block and the loaded tail
-		}
-		if tools.IsDeferred(tool) {
-			if loaded[name] {
-				loadedTail = append(loadedTail, runtimeToolDefinition(tool))
-			} else {
-				hiddenTools = append(hiddenTools, tool)
+		deferred := tools.IsDeferred(tool)
+
+		if !active {
+			// Inactive: byte-identical to legacy, but tool_search is never advertised.
+			if name == tools.ToolSearchToolName {
+				continue
 			}
+			definitions = append(definitions, zeroruntime.ToolDefinition{
+				Name:        name,
+				Description: tool.Description(),
+				Parameters:  schemaToRuntimeMap(tool.Parameters()),
+			})
+			exposedNames[name] = true
 			continue
 		}
-		eager = append(eager, runtimeToolDefinition(tool))
-	}
-	sort.Slice(eager, func(left int, right int) bool {
-		return eager[left].Name < eager[right].Name
-	})
-	sort.Slice(loadedTail, func(left int, right int) bool {
-		return loadedTail[left].Name < loadedTail[right].Name
-	})

+		// Active path.
+		if deferred && !loaded[name] {
+			hiddenTools = append(hiddenTools, tool)
+			continue
+		}
+		definitions = append(definitions, zeroruntime.ToolDefinition{
+			Name:        name,
+			Description: tool.Description(),
+			Parameters:  schemaToRuntimeMap(tool.Parameters()),
+		})
+		exposedNames[name] = true
+	}
+
+	// On the ACTIVE path tool_search is guaranteed runnable (active implies
+	// loaderUsable), so it must ALWAYS be reachable — even when a non-empty
+	// EnabledTools allowlist omits it (the operator allowlisted the deferred
+	// tools, not the loader). Expose its full definition whenever it is not
+	// already in the exposed set. This never runs on the inactive path, so the
+	// byte-identical below-threshold output is preserved.
 	discovery := ""
-	if len(hiddenTools) > 0 {
+	if active && len(hiddenTools) > 0 {
 		discovery = tools.BuildToolSearchDescription(hiddenTools)
 	}
-
-	// tool_search is guaranteed runnable on the active path, so it is ALWAYS exposed
-	// — even when a non-empty EnabledTools allowlist omits it (the operator
-	// allowlisted the deferred tools, not the loader). It sits right after the stable
-	// eager block and carries the discovery list for still-hidden tools.
-	description := loader.Description()
-	if discovery != "" {
-		description = discovery
+	if active && !exposedNames[tools.ToolSearchToolName] {
+		description := loader.Description()
+		if discovery != "" {
+			description = discovery
+		}
+		definitions = append(definitions, zeroruntime.ToolDefinition{
+			Name:        loader.Name(),
+			Description: description,
+			Parameters:  schemaToRuntimeMap(loader.Parameters()),
+		})
+	} else if active && discovery != "" {
+		for i := range definitions {
+			if definitions[i].Name == tools.ToolSearchToolName {
+				definitions[i].Description = discovery
+				break
+			}
+		}
 	}
-	definitions := make([]zeroruntime.ToolDefinition, 0, len(eager)+1+len(loadedTail))
-	definitions = append(definitions, eager...)
-	definitions = append(definitions, zeroruntime.ToolDefinition{
-		Name:        loader.Name(),
-		Description: description,
-		Parameters:  schemaToRuntimeMap(loader.Parameters()),
+
+	sort.Slice(definitions, func(left int, right int) bool {
+		return definitions[left].Name < definitions[right].Name
 	})
-	definitions = append(definitions, loadedTail...)

 	return definitions, discovery
 }

-// runtimeToolDefinition renders a tool's advertised definition (name, description,
-// JSON-schema parameters) as sent to the provider.
-func runtimeToolDefinition(tool tools.Tool) zeroruntime.ToolDefinition {
-	return zeroruntime.ToolDefinition{
-		Name:        tool.Name(),
-		Description: tool.Description(),
-		Parameters:  schemaToRuntimeMap(tool.Parameters()),
-	}
-}
-
 func ToolVisible(tool tools.Tool, permissionMode PermissionMode, enabledTools []string, disabledTools []string) bool {
 	return ToolAllowedByFilters(tool.Name(), enabledTools, disabledTools) && ToolAdvertised(tool, permissionMode)
 }
@@ -37,35 +37,6 @@ func (provider *mockProvider) StreamCompletion(ctx context.Context, request zero
 	return ch, nil
 }

-type recordingWebSearchTool struct {
-	calls []map[string]any
-}
-
-func (tool *recordingWebSearchTool) Name() string        { return "web_search" }
-func (tool *recordingWebSearchTool) Description() string { return "test web search tool" }
-func (tool *recordingWebSearchTool) Parameters() tools.Schema {
-	return tools.Schema{
-		Type: "object",
-		Properties: map[string]tools.PropertySchema{
-			"query": {Type: "string"},
-		},
-		Required:             []string{"query"},
-		AdditionalProperties: false,
-	}
-}
-func (tool *recordingWebSearchTool) Safety() tools.Safety {
-	return tools.Safety{
-		SideEffect:      tools.SideEffectNetwork,
-		Permission:      tools.PermissionPrompt,
-		Reason:          "Sends model-provided search query text to the configured web search backend.",
-		AdvertiseInAuto: true,
-	}
-}
-func (tool *recordingWebSearchTool) Run(_ context.Context, args map[string]any) tools.Result {
-	tool.calls = append(tool.calls, cloneArgs(args))
-	return tools.Result{Status: tools.StatusOK, Output: "1. T — https://x.test"}
-}
-
 type sandboxDeniedRetryTool struct {
 	calls []map[string]any
 }
@@ -894,7 +865,7 @@ func TestRunRejectsLocalWebFetchBeforePermissionRequest(t *testing.T) {
 	}
 }

-func TestRunAdvertisesPromptedWebSearchInAutoMode(t *testing.T) {
+func TestRunAdvertisesAllowedWebSearchInAutoMode(t *testing.T) {
 	t.Setenv("ZERO_WEBSEARCH_BASE_URL", "https://search.example/api")
 	registry := tools.NewRegistry()
 	for _, tool := range tools.CoreNetworkTools() {
@@ -925,52 +896,6 @@ func TestRunAdvertisesPromptedWebSearchInAutoMode(t *testing.T) {
 	}
 }

-func TestRunRequestsPermissionBeforeWebSearchExecution(t *testing.T) {
-	search := &recordingWebSearchTool{}
-	registry := tools.NewRegistry()
-	registry.Register(search)
-	provider := &mockProvider{
-		turns: [][]zeroruntime.StreamEvent{
-			{
-				{Type: zeroruntime.StreamEventToolCallStart, ToolCallID: "call-1", ToolName: "web_search"},
-				{Type: zeroruntime.StreamEventToolCallDelta, ToolCallID: "call-1", ArgumentsFragment: `{"query":"private workspace detail"}`},
-				{Type: zeroruntime.StreamEventToolCallEnd, ToolCallID: "call-1"},
-				{Type: zeroruntime.StreamEventDone},
-			},
-			{
-				{Type: zeroruntime.StreamEventText, Content: "done"},
-				{Type: zeroruntime.StreamEventDone},
-			},
-		},
-	}
-	var requests []PermissionRequest
-
-	result, err := Run(context.Background(), "search", provider, Options{
-		Registry:       registry,
-		PermissionMode: PermissionModeAsk,
-		OnPermissionRequest: func(_ context.Context, request PermissionRequest) (PermissionDecision, error) {
-			requests = append(requests, request)
-			return PermissionDecision{Action: PermissionDecisionDeny, Reason: "network not approved"}, nil
-		},
-	})
-
-	if err != nil {
-		t.Fatal(err)
-	}
-	if result.FinalAnswer != "done" {
-		t.Fatalf("expected final answer after denied tool call, got %q", result.FinalAnswer)
-	}
-	if len(requests) != 1 {
-		t.Fatalf("expected one permission request, got %#v", requests)
-	}
-	if requests[0].ToolName != "web_search" || requests[0].Permission != string(tools.PermissionPrompt) || requests[0].SideEffect != string(tools.SideEffectNetwork) {
-		t.Fatalf("unexpected permission request: %#v", requests[0])
-	}
-	if len(search.calls) != 0 {
-		t.Fatalf("web_search backend must not run when permission is denied, got calls %#v", search.calls)
-	}
-}
-
 func TestRunFiltersAdvertisedTools(t *testing.T) {
 	root := t.TempDir()
 	registry := tools.NewRegistry()
@@ -1,85 +0,0 @@
-package agent
-
-import (
-	"context"
-	"sync"
-
-	"github.com/Gitlawb/zero/internal/tools"
-)
-
-// Parallel read-ahead for tool batches. When a turn requests several
-// independent lookups (read_file + grep + glob is the common shape), executing
-// them one after another serializes pure I/O waits. A consecutive run of
-// auto-allowed read-only calls is executed concurrently instead; results are
-// then consumed in the original call order, so guard counters, message
-// ordering, abort semantics, and the surface's call/result event pairing are
-// byte-identical to sequential execution. Runs never span a mutating call: a
-// read that follows a write must observe the write, so eligibility is decided
-// per consecutive run, not per batch.
-
-// maxParallelReadTools bounds concurrent read-only tool executions in a turn.
-const maxParallelReadTools = 8
-
-// precomputedToolResult is one parallel read-ahead execution, keyed back to
-// its batch index by the caller.
-type precomputedToolResult struct {
-	result   ToolResult
-	abortErr error
-}
-
-// parallelSafeToolCall reports whether call may run concurrently with its
-// neighbors: the tool must exist, be side-effect-free (SideEffectRead), and be
-// auto-allowed for these args, so no interactive prompt or workspace mutation
-// is on the hot path. Loop-intercepted tools (ask_user, request_permissions)
-// and tool_search (mutates the deferred-tool set) stay sequential.
-func parallelSafeToolCall(registry *tools.Registry, call ToolCall, options Options) bool {
-	switch call.Name {
-	case "ask_user", tools.RequestPermissionsToolName, tools.ToolSearchToolName:
-		return false
-	}
-	tool, found := registry.Get(call.Name)
-	if !found || tool.Safety().SideEffect != tools.SideEffectRead {
-		return false
-	}
-	args := map[string]any{}
-	if call.Arguments != "" {
-		if err := decodeToolArguments(call.Arguments, &args); err != nil {
-			return false
-		}
-	}
-	return effectivePermission(tool, args) == tools.PermissionAllow
-}
-
-// executeParallelReadBatch runs calls[start:end] concurrently (bounded by
-// maxParallelReadTools) and returns results indexed relative to start. Any
-// permission prompt that still occurs (a sandbox preflight can demand one even
-// for an auto-allowed read) is serialized so an interactive front-end never
-// sees two prompts at once.
-func executeParallelReadBatch(ctx context.Context, registry *tools.Registry, calls []ToolCall, start, end int, permissionMode PermissionMode, options Options) []precomputedToolResult {
-	batchOptions := options
-	if options.OnPermissionRequest != nil {
-		var promptMutex sync.Mutex
-		inner := options.OnPermissionRequest
-		batchOptions.OnPermissionRequest = func(ctx context.Context, request PermissionRequest) (PermissionDecision, error) {
-			promptMutex.Lock()
-			defer promptMutex.Unlock()
-			return inner(ctx, request)
-		}
-	}
-
-	results := make([]precomputedToolResult, end-start)
-	semaphore := make(chan struct{}, maxParallelReadTools)
-	var waitGroup sync.WaitGroup
-	for index := start; index < end; index++ {
-		waitGroup.Add(1)
-		go func(index int) {
-			defer waitGroup.Done()
-			semaphore <- struct{}{}
-			defer func() { <-semaphore }()
-			result, abortErr := executeToolCall(ctx, registry, calls[index], permissionMode, batchOptions)
-			results[index-start] = precomputedToolResult{result: result, abortErr: abortErr}
-		}(index)
-	}
-	waitGroup.Wait()
-	return results
-}
@@ -1,184 +0,0 @@
-package agent
-
-import (
-	"context"
-	"fmt"
-	"sync"
-	"testing"
-	"time"
-
-	"github.com/Gitlawb/zero/internal/tools"
-	"github.com/Gitlawb/zero/internal/zeroruntime"
-)
-
-// probeTool records execution overlap and ordering so tests can assert what
-// actually ran concurrently.
-type probeTool struct {
-	name       string
-	sideEffect tools.SideEffect
-	delay      time.Duration
-
-	mu        sync.Mutex
-	active    int
-	maxActive int
-	log       []string
-}
-
-func (tool *probeTool) Name() string        { return tool.name }
-func (tool *probeTool) Description() string { return "test probe tool" }
-func (tool *probeTool) Parameters() tools.Schema {
-	return tools.Schema{
-		Type:                 "object",
-		Properties:           map[string]tools.PropertySchema{"id": {Type: "string"}},
-		AdditionalProperties: false,
-	}
-}
-func (tool *probeTool) Safety() tools.Safety {
-	return tools.Safety{SideEffect: tool.sideEffect, Permission: tools.PermissionAllow, Reason: "test"}
-}
-func (tool *probeTool) Run(_ context.Context, args map[string]any) tools.Result {
-	id, _ := args["id"].(string)
-	tool.mu.Lock()
-	tool.active++
-	if tool.active > tool.maxActive {
-		tool.maxActive = tool.active
-	}
-	tool.log = append(tool.log, "start:"+id)
-	tool.mu.Unlock()
-	time.Sleep(tool.delay)
-	tool.mu.Lock()
-	tool.active--
-	tool.log = append(tool.log, "end:"+id)
-	tool.mu.Unlock()
-	return tools.Result{Status: tools.StatusOK, Output: "probe " + id}
-}
-
-func probeCallEvents(callID, toolName, id string) []zeroruntime.StreamEvent {
-	return []zeroruntime.StreamEvent{
-		{Type: zeroruntime.StreamEventToolCallStart, ToolCallID: callID, ToolName: toolName},
-		{Type: zeroruntime.StreamEventToolCallDelta, ToolCallID: callID, ArgumentsFragment: fmt.Sprintf(`{"id":%q}`, id)},
-		{Type: zeroruntime.StreamEventToolCallEnd, ToolCallID: callID},
-	}
-}
-
-func TestParallelSafeToolCall(t *testing.T) {
-	registry := tools.NewRegistry()
-	registry.Register(&probeTool{name: "probe_read", sideEffect: tools.SideEffectRead})
-	registry.Register(&probeTool{name: "probe_write", sideEffect: tools.SideEffectWrite})
-
-	call := func(name, args string) ToolCall { return ToolCall{ID: "c", Name: name, Arguments: args} }
-	if !parallelSafeToolCall(registry, call("probe_read", `{"id":"a"}`), Options{}) {
-		t.Fatal("auto-allowed read tool must be parallel-safe")
-	}
-	if parallelSafeToolCall(registry, call("probe_write", `{"id":"a"}`), Options{}) {
-		t.Fatal("mutating tool must not be parallel-safe")
-	}
-	if parallelSafeToolCall(registry, call("unknown_tool", `{}`), Options{}) {
-		t.Fatal("unknown tool must not be parallel-safe")
-	}
-	if parallelSafeToolCall(registry, call("probe_read", `{"id":`), Options{}) {
-		t.Fatal("undecodable arguments must not be parallel-safe")
-	}
-	if parallelSafeToolCall(registry, call("ask_user", `{}`), Options{}) {
-		t.Fatal("loop-intercepted tools must stay sequential")
-	}
-}
-
-func TestRunExecutesConsecutiveReadsConcurrently(t *testing.T) {
-	probe := &probeTool{name: "probe_read", sideEffect: tools.SideEffectRead, delay: 60 * time.Millisecond}
-	registry := tools.NewRegistry()
-	registry.Register(probe)
-
-	turnOne := append(probeCallEvents("call-1", "probe_read", "a"), probeCallEvents("call-2", "probe_read", "b")...)
-	turnOne = append(turnOne, probeCallEvents("call-3", "probe_read", "c")...)
-	turnOne = append(turnOne, zeroruntime.StreamEvent{Type: zeroruntime.StreamEventDone})
-	provider := &mockProvider{
-		turns: [][]zeroruntime.StreamEvent{
-			turnOne,
-			{{Type: zeroruntime.StreamEventText, Content: "done"}, {Type: zeroruntime.StreamEventDone}},
-		},
-	}
-
-	var results []ToolResult
-	_, err := Run(context.Background(), "probe", provider, Options{
-		Registry:     registry,
-		OnToolResult: func(result ToolResult) { results = append(results, result) },
-	})
-	if err != nil {
-		t.Fatal(err)
-	}
-	if probe.maxActive < 2 {
-		t.Fatalf("consecutive read-only calls must overlap, max concurrency was %d", probe.maxActive)
-	}
-	// Results must still be recorded in original call order.
-	if len(results) != 3 || results[0].ToolCallID != "call-1" || results[1].ToolCallID != "call-2" || results[2].ToolCallID != "call-3" {
-		t.Fatalf("tool results out of order: %#v", results)
-	}
-	messages := provider.requests[1].Messages
-	var toolOrder []string
-	for _, message := range messages {
-		if message.Role == zeroruntime.MessageRoleTool {
-			toolOrder = append(toolOrder, message.ToolCallID)
-		}
-	}
-	if len(toolOrder) != 3 || toolOrder[0] != "call-1" || toolOrder[1] != "call-2" || toolOrder[2] != "call-3" {
-		t.Fatalf("recorded tool messages out of order: %v", toolOrder)
-	}
-}
-
-func TestRunParallelReadsNeverSpanMutatingCall(t *testing.T) {
-	read := &probeTool{name: "probe_read", sideEffect: tools.SideEffectRead, delay: 30 * time.Millisecond}
-	write := &probeTool{name: "probe_write", sideEffect: tools.SideEffectWrite}
-	// Shared log across both probes so relative ordering is observable.
-	write.mu = sync.Mutex{}
-	registry := tools.NewRegistry()
-	registry.Register(read)
-	registry.Register(write)
-
-	turnOne := append(probeCallEvents("call-1", "probe_read", "r1"), probeCallEvents("call-2", "probe_read", "r2")...)
-	turnOne = append(turnOne, probeCallEvents("call-3", "probe_write", "w")...)
-	turnOne = append(turnOne, probeCallEvents("call-4", "probe_read", "r3")...)
-	turnOne = append(turnOne, probeCallEvents("call-5", "probe_read", "r4")...)
-	turnOne = append(turnOne, zeroruntime.StreamEvent{Type: zeroruntime.StreamEventDone})
-	provider := &mockProvider{
-		turns: [][]zeroruntime.StreamEvent{
-			turnOne,
-			{{Type: zeroruntime.StreamEventText, Content: "done"}, {Type: zeroruntime.StreamEventDone}},
-		},
-	}
-
-	_, err := Run(context.Background(), "probe", provider, Options{Registry: registry})
-	if err != nil {
-		t.Fatal(err)
-	}
-	// The write must start only after r1+r2 finished, and r3/r4 must start only
-	// after the write finished: batches never cross a mutating call.
-	index := func(log []string, entry string) int {
-		for i, e := range log {
-			if e == entry {
-				return i
-			}
-		}
-		return -1
-	}
-	readLog := func() []string { read.mu.Lock(); defer read.mu.Unlock(); return append([]string(nil), read.log...) }()
-	writeLog := func() []string { write.mu.Lock(); defer write.mu.Unlock(); return append([]string(nil), write.log...) }()
-	if index(writeLog, "start:w") == -1 {
-		t.Fatalf("write probe never ran: %v", writeLog)
-	}
-	for _, entry := range []string{"end:r1", "end:r2"} {
-		if index(readLog, entry) == -1 {
-			t.Fatalf("first read batch incomplete: %v", readLog)
-		}
-	}
-	// r3/r4 must appear strictly after r1/r2 in the read log (the write barrier
-	// between the two batches forces full separation).
-	firstBatchMaxEnd := max(index(readLog, "end:r1"), index(readLog, "end:r2"))
-	secondBatchMinStart := min(index(readLog, "start:r3"), index(readLog, "start:r4"))
-	if secondBatchMinStart < firstBatchMaxEnd {
-		t.Fatalf("second read batch started before first batch ended: %v", readLog)
-	}
-	if read.maxActive < 2 {
-		t.Fatalf("reads within a batch must overlap, max concurrency was %d", read.maxActive)
-	}
-}
@@ -1,44 +0,0 @@
-package agent
-
-import (
-	"testing"
-
-	"github.com/Gitlawb/zero/internal/tools"
-)
-
-func TestPartitionToolsActiveAppendsLoadedToolAfterEagerBlock(t *testing.T) {
-	// Cache-stability property: loading a deferred tool must APPEND it after the
-	// always-eager tools, not sort it into the middle of them — otherwise the tool
-	// definitions (the provider's cacheable prefix) shift on every load. The old
-	// behaviour alpha-sorted the whole array, so "mcp__srv__alpha" jumped ahead of
-	// "read_file".
-	root := t.TempDir()
-	registry := tools.NewRegistry()
-	registry.Register(tools.NewReadFileTool(root)) // non-deferred, "read_file"
-	registry.Register(fakeToolSearchTool{})
-	registry.Register(fakeDeferredTool{name: "mcp__srv__alpha", desc: "alpha"})
-	registry.Register(fakeDeferredTool{name: "mcp__srv__beta", desc: "beta"})
-
-	exposed, _ := partitionTools(registry, PermissionModeAuto, Options{DeferThreshold: 2}, map[string]bool{"mcp__srv__alpha": true})
-
-	pos := func(name string) int {
-		for i := range exposed {
-			if exposed[i].Name == name {
-				return i
-			}
-		}
-		return -1
-	}
-	readPos, searchPos, alphaPos := pos("read_file"), pos("tool_search"), pos("mcp__srv__alpha")
-	if readPos < 0 || searchPos < 0 || alphaPos < 0 {
-		t.Fatalf("expected read_file, tool_search and loaded alpha all exposed, got %#v", exposed)
-	}
-	// The eager tools must precede the loaded deferred tool (appended, not inserted).
-	if !(readPos < alphaPos && searchPos < alphaPos) {
-		t.Fatalf("loaded deferred tool must be appended after the eager block; got read=%d search=%d alpha=%d", readPos, searchPos, alphaPos)
-	}
-	// beta was never loaded — it stays hidden.
-	if pos("mcp__srv__beta") != -1 {
-		t.Fatalf("unloaded deferred tool must stay hidden, got %#v", exposed)
-	}
-}
@@ -1,70 +0,0 @@
-package agent
-
-import (
-	"context"
-	"testing"
-
-	"github.com/Gitlawb/zero/internal/sandbox"
-	"github.com/Gitlawb/zero/internal/tools"
-)
-
-// promptShellTool is a minimal shell-style tool whose Safety requires a prompt,
-// standing in for bash so buildPermissionEvent can be exercised directly.
-type promptShellTool struct{}
-
-func (promptShellTool) Name() string        { return "bash" }
-func (promptShellTool) Description() string { return "run a shell command" }
-func (promptShellTool) Parameters() tools.Schema {
-	return tools.Schema{Type: "object", AdditionalProperties: false}
-}
-func (promptShellTool) Safety() tools.Safety {
-	return tools.Safety{SideEffect: tools.SideEffectShell, Permission: tools.PermissionPrompt, Reason: "runs a shell command"}
-}
-func (promptShellTool) Run(context.Context, map[string]any) tools.Result {
-	return tools.Result{Status: tools.StatusOK}
-}
-
-// A command whose sandbox decision is Allow but that explicitly requests
-// additional sandbox permissions is an ELEVATION: it must be surfaced as a
-// prompt, never Action=allow. Previously it carried allow while the loop still
-// blocked on OnPermissionRequest, and the TUI (which renders only prompts)
-// dropped it → the run deadlocked forever. This is the exact gpt-5.5
-// folder-creation shape captured in the reported hang.
-func TestBuildPermissionEventPromptsForAdditionalPermissions(t *testing.T) {
-	call := ToolCall{ID: "call_1", Name: "bash", Arguments: `{}`}
-	args := map[string]any{
-		"command":             "mkdir foo && cd foo && go mod init foo",
-		"sandbox_permissions": string(tools.SandboxPermissionsWithAdditionalPermissions),
-	}
-	// Base command allowed by the sandbox…
-	decision := &sandbox.Decision{Action: sandbox.ActionAllow}
-
-	event, ok := buildPermissionEvent(call, promptShellTool{}, args, false, PermissionModeAsk, Options{}, decision)
-	if !ok {
-		t.Fatal("buildPermissionEvent returned ok=false; the elevation request must produce an event")
-	}
-	if event.Action != PermissionActionPrompt {
-		t.Fatalf("Action = %q, want prompt — an additional-permissions elevation must ask the user, not auto-allow", event.Action)
-	}
-	// Sanity: shouldRequestPermission agrees the loop blocks on this.
-	if !shouldRequestPermission(promptShellTool{}, args, false, decision) {
-		t.Fatal("shouldRequestPermission must be true for an additional-permissions request")
-	}
-}
-
-// Without the additional-permissions flag, a sandbox-allowed command is NOT a
-// prompt (shouldRequestPermission is false; it just runs) — the override must
-// not over-reach and prompt for ordinary allowed commands.
-func TestBuildPermissionEventKeepsAllowForOrdinaryAllowedCommand(t *testing.T) {
-	call := ToolCall{ID: "call_2", Name: "bash", Arguments: `{}`}
-	args := map[string]any{"command": "ls"}
-	decision := &sandbox.Decision{Action: sandbox.ActionAllow}
-
-	event, _ := buildPermissionEvent(call, promptShellTool{}, args, false, PermissionModeAsk, Options{}, decision)
-	if event.Action == PermissionActionPrompt {
-		t.Fatalf("Action = prompt for an ordinary allowed command; want allow (no spurious prompt)")
-	}
-	if shouldRequestPermission(promptShellTool{}, args, false, decision) {
-		t.Fatal("shouldRequestPermission must be false for an ordinary sandbox-allowed command")
-	}
-}
@@ -1,51 +0,0 @@
-package agent
-
-import (
-	"testing"
-
-	"github.com/Gitlawb/zero/internal/tools"
-)
-
-// These ceilings are a deliberate ratchet on Zero's fixed per-turn overhead — the
-// system prompt and the eager tool schemas that ride on EVERY request. They are
-// set ~10% above the current measured cost, using ApproxTextTokens (the same
-// estimate the compaction loop and /context use, ~non-whitespace-bytes/4). A change
-// that pushes either past its ceiling must be justified (and the ceiling raised
-// deliberately) or trimmed — the per-turn floor should not creep up silently.
-//
-// Measured baselines (2026-07): base system prompt ~3160 tokens; the tools a normal
-// (auto permission-mode) interactive turn sends ~2430 tokens. The tool figure is
-// the auto-mode advertised set, not the full core registry — higher-risk tools that
-// only advertise in other modes are excluded, matching what a real turn actually
-// pays.
-const (
-	maxBaseSystemPromptTokens = 3500
-	maxEagerToolSchemaTokens  = 2700
-)
-
-func TestSystemPromptTokenBudget(t *testing.T) {
-	// Minimal render: a model is set (so the session block renders) but no Cwd, so
-	// the workspace map, project guidelines, and repo map are excluded — this is the
-	// fixed base every session pays regardless of the workspace it runs in.
-	prompt := buildSystemPrompt(Options{Model: "claude-opus-4-8"})
-	got := ApproxTextTokens(prompt)
-	t.Logf("base system prompt: %d tokens (%d bytes)", got, len(prompt))
-	if got > maxBaseSystemPromptTokens {
-		t.Fatalf("base system prompt is %d tokens, over the %d ceiling — trim it or raise the ceiling deliberately", got, maxBaseSystemPromptTokens)
-	}
-}
-
-func TestEagerToolSchemaTokenBudget(t *testing.T) {
-	registry := tools.NewRegistry()
-	for _, tool := range tools.CoreToolsScoped(t.TempDir(), nil) {
-		registry.Register(tool)
-	}
-	// Options{} keeps DeferThreshold at 0, so deferral is inactive and every core
-	// tool is exposed eagerly — exactly what a plugin-free session sends each turn.
-	exposed, _ := partitionTools(registry, PermissionModeAuto, Options{}, map[string]bool{})
-	got := estimateToolDefTokens(exposed)
-	t.Logf("eager core tool schemas: %d tokens across %d tools", got, len(exposed))
-	if got > maxEagerToolSchemaTokens {
-		t.Fatalf("eager tool schemas are %d tokens, over the %d ceiling — defer a tool or raise the ceiling deliberately", got, maxEagerToolSchemaTokens)
-	}
-}
@@ -1,63 +0,0 @@
-package agent
-
-import (
-	"strconv"
-	"strings"
-	"testing"
-)
-
-func TestSkillsContextCapsLongList(t *testing.T) {
-	skills := make([]SkillInfo, 0, 40)
-	for i := 0; i < 40; i++ {
-		n := strconv.Itoa(i)
-		skills = append(skills, SkillInfo{Name: "skill-" + n, Description: "does something useful, number " + n})
-	}
-	got := skillsContext(Options{Skills: skills})
-	if len(got) > 1200 {
-		t.Fatalf("skills block should stay bounded, got %d bytes:\n%s", len(got), got)
-	}
-	if !strings.Contains(got, "more (call skill") {
-		t.Fatalf("expected an overflow summary line, got:\n%s", got)
-	}
-	// The first skill is always listed regardless of budget.
-	if !strings.Contains(got, "- skill-0:") {
-		t.Fatalf("expected the first skill to always be listed, got:\n%s", got)
-	}
-}
-
-func TestSkillsContext(t *testing.T) {
-	if got := skillsContext(Options{}); got != "" {
-		t.Fatalf("no skills should yield an empty section, got %q", got)
-	}
-	got := skillsContext(Options{Skills: []SkillInfo{
-		{Name: "commit-writer", Description: "Write a conventional-commit message."},
-		{Name: "  ", Description: "nameless, should be skipped"},
-		{Name: "reviewer"},
-	}})
-	if !strings.Contains(got, "<available_skills>") || !strings.Contains(got, "</available_skills>") {
-		t.Fatalf("missing available_skills block: %q", got)
-	}
-	if !strings.Contains(got, "- commit-writer: Write a conventional-commit message.") {
-		t.Fatalf("missing commit-writer line: %q", got)
-	}
-	if !strings.Contains(got, "- reviewer\n") {
-		t.Fatalf("reviewer (no description) line missing: %q", got)
-	}
-	if strings.Contains(got, "nameless") {
-		t.Fatalf("nameless entry should be skipped: %q", got)
-	}
-}
-
-func TestSystemPromptIncludesSkillsOnlyWhenInstalled(t *testing.T) {
-	with := buildSystemPrompt(Options{Skills: []SkillInfo{
-		{Name: "commit-writer", Description: "Write a commit message."},
-	}})
-	if !strings.Contains(with, "<available_skills>") || !strings.Contains(with, "skill tool") {
-		t.Fatalf("expected available_skills guidance in system prompt: %q", with)
-	}
-	// Default (no skills) must reproduce the prior prompt: no skills block.
-	without := buildSystemPrompt(Options{})
-	if strings.Contains(without, "<available_skills>") {
-		t.Fatalf("available_skills block must not appear without skills")
-	}
-}
@@ -5,7 +5,6 @@ import (
 	"os"
 	"path/filepath"
 	"runtime"
-	"strconv"
 	"strings"
 	"unicode/utf8"

@@ -87,9 +86,6 @@ func buildSystemPrompt(options Options) string {
 	if delegation := specialistDelegationContext(options); delegation != "" {
 		sections = append(sections, delegation)
 	}
-	if skillsBlock := skillsContext(options); skillsBlock != "" {
-		sections = append(sections, skillsBlock)
-	}
 	if style := responseStyleContext(options); style != "" {
 		sections = append(sections, style)
 	}
@@ -168,64 +164,6 @@ func specialistDelegationContext(options Options) string {
 	return b.String()
 }

-// skillsContext lists the reusable skills the model can pull in on demand via the
-// skill tool, so it invokes the right one on the first try instead of guessing a
-// name, failing, and reading the error. It mirrors specialistDelegationContext:
-// names + one-line descriptions only (never skill bodies), and it renders nothing
-// when no skills are installed, so a skill-less run reproduces the previous prompt
-// byte-for-byte.
-// skillsContextListBudget bounds the bytes spent listing individual skills so a
-// workspace with dozens of them can't bloat every turn's prompt. Skills past the
-// budget are summarized as a count rather than dropped — the model can still load
-// any of them by name (an unknown name returns the full list from the skill tool).
-const skillsContextListBudget = 640
-
-func skillsContext(options Options) string {
-	if len(options.Skills) == 0 {
-		return ""
-	}
-	var b strings.Builder
-	b.WriteString("<available_skills>\n")
-	b.WriteString("Reusable, on-demand instruction sets you can load with the skill tool. When a request matches one, call skill with its exact name to pull in its guidance before acting — do not guess names or skip a relevant skill.\n")
-	listed, spent, omitted := 0, 0, 0
-	for _, info := range options.Skills {
-		name := strings.TrimSpace(info.Name)
-		if name == "" {
-			continue
-		}
-		line := "- " + name
-		if desc := strings.TrimSpace(info.Description); desc != "" {
-			line += ": " + truncateForSkillLine(desc)
-		}
-		line += "\n"
-		// Always list at least one skill; past the budget, summarize the remainder
-		// as a count instead of silently dropping it.
-		if listed > 0 && spent+len(line) > skillsContextListBudget {
-			omitted++
-			continue
-		}
-		b.WriteString(line)
-		spent += len(line)
-		listed++
-	}
-	if omitted > 0 {
-		b.WriteString("- …and " + strconv.Itoa(omitted) + " more (call skill with a name; an unknown name lists them all)\n")
-	}
-	b.WriteString("</available_skills>")
-	return b.String()
-}
-
-// truncateForSkillLine keeps a skill's one-line description short so a single
-// verbose description can't dominate the skills-list budget.
-func truncateForSkillLine(desc string) string {
-	const maxDescRunes = 100
-	runes := []rune(desc)
-	if len(runes) <= maxDescRunes {
-		return desc
-	}
-	return strings.TrimSpace(string(runes[:maxDescRunes])) + "…"
-}
-
 func sessionRuntimeContext(options Options) string {
 	provider := strings.TrimSpace(options.ProviderName)
 	model := strings.TrimSpace(options.Model)
@@ -372,9 +310,9 @@ func projectGuidelineLabel(match, gitRoot string) string {

 // findProjectContextFile returns the first matching project guideline file
 // in dir. Lookup is case-insensitive on the basename and on the actual
-// filename returned, so a git-tracked file like AGENTS.md still resolves to
-// its true filename on case-sensitive filesystems — the returned path is what
-// should appear in the project guidelines label.
+// filename returned, so a git-tracked file like AGENTS.MD (uppercase MD)
+// still resolves to its true filename on case-sensitive filesystems — the
+// returned path is what should appear in the project guidelines label.
 // Returns "" when nothing matches.
 func findProjectContextFile(dir string) string {
 	for _, name := range projectContextFiles {
@@ -46,10 +46,14 @@ work.
   formatting-only edits unless the user asked for them.
 4. **Verify.** Verify after edits; see the testing gate below. This is
   mandatory.
-5. **Summarize.** Close with a summary scaled to the work: a trivial fix earns one
-   line; a substantial change earns a few short bullets covering what changed, where
-   it lives, and what you did and did not verify. Lead with the outcome, and never
-   pad — do not restate the task or narrate steps the user already watched you take.
+5. **Summarize.** For a substantial task, close with an ELABORATE, well-structured
+   summary — never a single throwaway line. Use short headings and bullets: a
+   one-line "what I built/changed"; **Where it lives** — the key files and how they
+   fit together; **How each requirement is met** — walk through each requirement
+   from the request and name the specifics that satisfy it; what validation ran and
+   what was NOT verified; and a brief "Next steps" or "Want me to…?" offer. Scale
+   the depth to the work — a big build earns several sections, a trivial fix earns
+   a line or two.

 ## Editing discipline

@@ -60,9 +64,7 @@ work.
 - Make one tool call per file. Do not batch multi-file writes into a single
  shell or script invocation.
 - For edits to existing files, prefer edit_file or apply_patch with minimal,
-  targeted diffs. 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.
+  targeted diffs. Match the existing indentation, imports, and idioms.
 - 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.

@@ -6,13 +6,11 @@ import "strings"
 //
 // Different model families respond to different framing: the GPT family benefits
 // from an explicit markdown/output spec and a strong "prefer native tools" nudge;
-// Gemini benefits from explicit tool-preference and conciseness guidance. The
-// Claude family is already aligned with the core prompt and needs no addendum —
-// comment discipline is universal in the core prompt now, so every family gets it.
-// modelPromptAddendum returns the family-specific block appended after the core
-// prompt, or "" when the family is unknown or needs no specialization.
-// Classification is by model id (the agent only has the model string — no registry
-// dependency).
+// Gemini benefits from explicit tool-preference and conciseness guidance; the
+// Claude family is already well-aligned with the core prompt and only needs a
+// light comment-discipline nudge. modelPromptAddendum returns the family-specific
+// block appended after the core prompt. Classification is by model id (the agent
+// only has the model string — no registry dependency).

 const (
 	familyOpenAI    = "openai"
@@ -47,10 +45,9 @@ func modelPromptAddendum(model string) string {
 		return openAIPromptAddendum
 	case familyGemini:
 		return geminiPromptAddendum
+	case familyAnthropic:
+		return anthropicPromptAddendum
 	default:
-		// Anthropic (aligned with the core prompt) and unknown families get no
-		// family-specific block; comment discipline now lives in the core prompt
-		// for every model.
 		return ""
 	}
 }
@@ -73,3 +70,8 @@ const geminiPromptAddendum = `<model_guidance>
  in one short clause why it is needed.
 - Use update_plan for any multi-step task and keep it current.
 </model_guidance>`
+
+const anthropicPromptAddendum = `<model_guidance>
+- Do not add code comments unless the user asks or the surrounding code is
+  comment-dense; match the file's existing comment density.
+</model_guidance>`
@@ -29,11 +29,9 @@ 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")
 	}
-	// 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"})
-	if strings.Contains(claude, "<model_guidance>") {
-		t.Fatalf("expected no model_guidance block for Claude (aligned with core prompt)")
+	if !strings.Contains(claude, anthropicPromptAddendum) {
+		t.Fatalf("expected the Anthropic addendum in the claude prompt")
 	}
 	if strings.Contains(claude, openAIPromptAddendum) {
 		t.Fatalf("the claude prompt must not contain the OpenAI addendum")
@@ -23,8 +23,7 @@ func TestCoreSystemPromptIncludesCodingQualityRules(t *testing.T) {
 		"avoid broad refactors",
 		"search the web before answering",
 		"do not recognize",
-		"scaled to the work",
-		"comment density",
+		"how each requirement is met",
 	} {
 		if !strings.Contains(prompt, want) {
 			t.Fatalf("expected core system prompt to include %q, got:\n%s", want, buildSystemPrompt(Options{}))
@@ -129,7 +128,7 @@ func systemPromptTestBlock(t *testing.T, prompt, start, end string) string {
 }

 func TestBuildSystemPromptInjectsProjectGuidelinesCaseInsensitive(t *testing.T) {
-	// Git tracks AGENTS.md on a case-sensitive filesystem; the
+	// Git tracks AGENTS.MD (uppercase MD) on a case-sensitive filesystem; the
 	// loader must still resolve it when the cwd lookup uses lowercase.
 	cwd := t.TempDir()
 	if err := os.WriteFile(filepath.Join(cwd, "AGENTS.MD"), []byte("Always run `make lint`."), 0o644); err != nil {
@@ -174,16 +174,6 @@ type SpecialistInfo struct {
 	WhenToUse string
 }

-// SkillInfo is a one-line summary of a reusable, on-demand skill (its name and
-// frontmatter description) surfaced to the system prompt so the model can invoke
-// the right skill with the skill tool on the first try instead of guessing a name
-// and reading the failure. Like SpecialistInfo it is plain data, so the agent
-// package needs no dependency on internal/skills.
-type SkillInfo struct {
-	Name        string
-	Description string
-}
-
 type Options struct {
 	MaxTurns int
 	// DeferThreshold activates deferred MCP-tool loading: when the number of
@@ -199,12 +189,6 @@ type Options struct {
 	// populated only where the Task tool is actually registered, so an empty slice
 	// (the default) reproduces the previous prompt byte-for-byte.
 	Specialists []SpecialistInfo
-	// Skills lists the reusable skills installed for this run (the default skills
-	// dir merged with any plugin skill roots). When non-empty the system prompt
-	// gains an <available_skills> block naming them so the model loads the right one
-	// via the skill tool on the first try. Empty (the default) reproduces the
-	// previous prompt byte-for-byte.
-	Skills []SkillInfo
 	// Specialist/sub-agent metadata is carried through exec now and consumed by
 	// the specialist runtime in later slices.
 	SessionID        string
@@ -285,12 +269,6 @@ type Options struct {
 	// ceiling and the autonomy gate. nil disables it entirely (the loop is
 	// byte-identical to before). One instance per run — it holds attempt state.
 	SelfCorrect *SelfCorrector
-	// FileDiagnostics, when set, is passed to mutating tools so edit_file /
-	// write_file append error-severity language diagnostics for the file they
-	// just wrote directly to their tool output — the model sees an error it
-	// introduced in the same turn instead of a later verification pass. Build
-	// one with NewFileDiagnostics. nil disables inline diagnostics.
-	FileDiagnostics func(ctx context.Context, absPath string) string

 	// RequireCompletionSignal gates run completion for HEADLESS exec. Without it,
 	// any assistant turn that produces text but no tool call is accepted as the
@@ -19,11 +19,9 @@ import (
 	"github.com/Gitlawb/zero/internal/hooks"
 	"github.com/Gitlawb/zero/internal/localcontrol"
 	"github.com/Gitlawb/zero/internal/mcp"
-	"github.com/Gitlawb/zero/internal/modelregistry"
 	"github.com/Gitlawb/zero/internal/observability"
 	"github.com/Gitlawb/zero/internal/plugins"
 	"github.com/Gitlawb/zero/internal/providerhealth"
-	"github.com/Gitlawb/zero/internal/providermodeldiscovery"
 	"github.com/Gitlawb/zero/internal/provideronboarding"
 	"github.com/Gitlawb/zero/internal/providers"
 	"github.com/Gitlawb/zero/internal/redaction"
@@ -55,34 +53,32 @@ type appDeps struct {
 	// config.SetActiveProviderEnv, set in defaultAppDeps — deliberately NOT filled
 	// by fillAppDeps, so tests never mutate the process environment unless they
 	// inject it). nil ⇒ no export.
-	exportActiveProvider   func(providerName string)
-	probeProviderHealth    func(context.Context, providerhealth.Options) providerhealth.Result
-	discoverProviderModels func(context.Context, config.ProviderProfile) ([]providermodeldiscovery.Model, error)
-	detectLocalRuntimes    func(context.Context, provideronboarding.LocalDetectOptions) []provideronboarding.DetectedLocalRuntime
-	newSessionStore        func() *sessions.Store
-	loadPlugins            func(plugins.LoadOptions) (plugins.LoadResult, error)
-	loadHooks              func(hooks.LoadOptions) (hooks.LoadResult, error)
-	skillsDir              func() string
-	pluginsDir             func() string
-	toolsDir               func() string
-	newMCPStore            func() (*mcp.PermissionStore, error)
-	newMCPTokenStore       func() (*mcp.TokenStore, error)
-	newSandboxStore        func() (*sandbox.GrantStore, error)
-	selectSandboxBackend   func(sandbox.BackendOptions) sandbox.Backend
-	runSandboxSetupHelper  func(path string, args []string, stdout io.Writer, stderr io.Writer) error
-	registerMCPTools       func(context.Context, *tools.Registry, config.MCPConfig, mcp.RegisterOptions) (mcpToolRuntime, error)
-	prepareWorktree        func(context.Context, worktrees.Options) (worktrees.Result, error)
-	detectVerifyPlan       func(string) (verify.Plan, error)
-	runVerify              func(context.Context, verify.Plan, verify.RunOptions) verify.Report
-	runSelfVerify          func(context.Context, verify.Plan, selfverify.Options) selfverify.Report
-	runAgentEval           func(context.Context, agentEvalOptions) (agentEvalReport, error)
-	inspectChanges         func(context.Context, zerogit.InspectOptions) (zerogit.ChangeSummary, error)
-	commitChanges          func(context.Context, zerogit.CommitOptions) (zerogit.CommitResult, error)
-	runTUI                 func(context.Context, tui.Options) int
-	runEditor              func(string) error
-	checkUpdate            func(context.Context, update.Options) (update.Result, error)
-	applyUpdate            func(context.Context, update.Options) (update.ApplyResult, error)
-	now                    func() time.Time
+	exportActiveProvider  func(providerName string)
+	probeProviderHealth   func(context.Context, providerhealth.Options) providerhealth.Result
+	detectLocalRuntimes   func(context.Context, provideronboarding.LocalDetectOptions) []provideronboarding.DetectedLocalRuntime
+	newSessionStore       func() *sessions.Store
+	loadPlugins           func(plugins.LoadOptions) (plugins.LoadResult, error)
+	loadHooks             func(hooks.LoadOptions) (hooks.LoadResult, error)
+	skillsDir             func() string
+	pluginsDir            func() string
+	toolsDir              func() string
+	newMCPStore           func() (*mcp.PermissionStore, error)
+	newMCPTokenStore      func() (*mcp.TokenStore, error)
+	newSandboxStore       func() (*sandbox.GrantStore, error)
+	selectSandboxBackend  func(sandbox.BackendOptions) sandbox.Backend
+	runSandboxSetupHelper func(path string, args []string, stdout io.Writer, stderr io.Writer) error
+	registerMCPTools      func(context.Context, *tools.Registry, config.MCPConfig, mcp.RegisterOptions) (mcpToolRuntime, error)
+	prepareWorktree       func(context.Context, worktrees.Options) (worktrees.Result, error)
+	detectVerifyPlan      func(string) (verify.Plan, error)
+	runVerify             func(context.Context, verify.Plan, verify.RunOptions) verify.Report
+	runSelfVerify         func(context.Context, verify.Plan, selfverify.Options) selfverify.Report
+	runAgentEval          func(context.Context, agentEvalOptions) (agentEvalReport, error)
+	inspectChanges        func(context.Context, zerogit.InspectOptions) (zerogit.ChangeSummary, error)
+	commitChanges         func(context.Context, zerogit.CommitOptions) (zerogit.CommitResult, error)
+	runTUI                func(context.Context, tui.Options) int
+	runEditor             func(string) error
+	checkUpdate           func(context.Context, update.Options) (update.Result, error)
+	now                   func() time.Time
 }

 type mcpToolRuntime interface {
@@ -138,9 +134,8 @@ func defaultAppDeps() appDeps {
 				OAuthLoginKey: loginKey,
 			})
 		},
-		probeProviderHealth:    providerhealth.Probe,
-		discoverProviderModels: defaultDiscoverProviderModels,
-		detectLocalRuntimes:    provideronboarding.DetectLocalRuntimes,
+		probeProviderHealth: providerhealth.Probe,
+		detectLocalRuntimes: provideronboarding.DetectLocalRuntimes,
 		newSessionStore: func() *sessions.Store {
 			return sessions.NewStore(sessions.StoreOptions{})
 		},
@@ -182,7 +177,6 @@ func defaultAppDeps() appDeps {
 		runTUI:           tui.Run,
 		runEditor:        openEditor,
 		checkUpdate:      update.Check,
-		applyUpdate:      update.Apply,
 		now:              time.Now,
 	}
 }
@@ -230,12 +224,6 @@ func runWithDeps(args []string, stdout io.Writer, stderr io.Writer, deps appDeps
 	defer observability.Recover(observability.DefaultCrashDir(), "cli", stderr, &exitCode)
 	deps = fillAppDeps(deps)

-	// CLI runs opt into the models.dev overlay (cached live context limits and
-	// pricing on top of the curated catalog). Explicitly enabled here — and only
-	// here — so library consumers and hermetic tests are never perturbed by a
-	// cache file on the machine. The refresh itself is fired in exec/TUI startup.
-	modelregistry.EnableModelsDevOverlay()
-
 	addDirs, args, err := splitLeadingAddDirFlags(args)
 	if err != nil {
 		return writeAppError(stderr, err.Error(), 1)
@@ -392,8 +380,6 @@ func runWithDeps(args []string, stdout io.Writer, stderr io.Writer, deps appDeps
 		return runSandbox(args[1:], stdout, stderr, deps)
 	case "update":
 		return runUpdate(args[1:], stdout, stderr, deps)
-	case "upgrade":
-		return runUpgrade(args[1:], stdout, stderr, deps)
 	case "worktrees", "worktree":
 		return runWorktrees(args[1:], stdout, stderr, deps)
 	case "verify":
@@ -454,9 +440,6 @@ func fillAppDeps(deps appDeps) appDeps {
 	if deps.probeProviderHealth == nil {
 		deps.probeProviderHealth = defaults.probeProviderHealth
 	}
-	if deps.discoverProviderModels == nil {
-		deps.discoverProviderModels = defaults.discoverProviderModels
-	}
 	if deps.detectLocalRuntimes == nil {
 		deps.detectLocalRuntimes = defaults.detectLocalRuntimes
 	}
@@ -526,9 +509,6 @@ func fillAppDeps(deps appDeps) appDeps {
 	if deps.checkUpdate == nil {
 		deps.checkUpdate = defaults.checkUpdate
 	}
-	if deps.applyUpdate == nil {
-		deps.applyUpdate = defaults.applyUpdate
-	}
 	if deps.now == nil {
 		deps.now = defaults.now
 	}
@@ -551,11 +531,6 @@ func runInteractiveTUI(stderr io.Writer, deps appDeps, permissionMode agent.Perm
 }

 func runInteractiveTUIWithSetup(stderr io.Writer, deps appDeps, permissionMode agent.PermissionMode, addDirs []string, theme string, forceSetup bool) int {
-	// Refresh the models.dev pricing/limits cache in the background when stale;
-	// the overlay is read at registry construction from the cache file, so this
-	// benefits the next run and never blocks or fails this one.
-	go func() { _ = modelregistry.RefreshModelsDevCache(context.Background()) }()
-
 	workspaceRoot, err := deps.getwd()
 	if err != nil {
 		return writeAppError(stderr, "failed to resolve workspace: "+err.Error(), 1)
@@ -576,19 +551,8 @@ func runInteractiveTUIWithSetup(stderr io.Writer, deps appDeps, permissionMode a
 		if !errors.Is(err, config.ErrNoActiveProvider) && !errors.Is(err, config.ErrProviderRequiresModel) {
 			return writeAppError(stderr, err.Error(), 1)
 		}
-		// ErrNoActiveProvider can mean "nothing configured yet" (needs onboarding)
-		// or "providers ARE configured, just none marked active" (e.g. config.json's
-		// activeProvider is blank/stale). In the second case resolved.Providers still
-		// carries the already-normalized list — prefer falling back to one of those
-		// over wiping everything and forcing the user to re-enter credentials they
-		// already saved.
-		if usable, ok := firstUsableProvider(resolved.Providers); errors.Is(err, config.ErrNoActiveProvider) && ok {
-			resolved.Provider = usable
-			resolved.ActiveProvider = usable.Name
-		} else {
-			resolved = config.ResolvedConfig{}
-			forceSetup = true
-		}
+		resolved = config.ResolvedConfig{}
+		forceSetup = true
 	}
 	userConfigPath, err := deps.userConfigPath()
 	if err != nil {
@@ -770,11 +734,9 @@ func runInteractiveTUIWithSetup(stderr io.Writer, deps appDeps, permissionMode a
 			Hooks:          newHookDispatcherWithExtra(workspaceRoot, pluginActivation.hooks),
 			DeferThreshold: resolved.Tools.DeferThreshold,
 			Specialists:    specialistRuntime.specialists,
-			Skills:         pluginActivation.skillInfos(deps.skillsDir()),
 		},
 		PermissionMode: permissionMode,
 		Notify:         resolved.Notify,
-		KeyBindings:    resolved.KeyBindings,
 		Setup: tui.SetupOptions{
 			Visible:    setupVisible,
 			Required:   needsSetup,
@@ -1190,8 +1152,7 @@ func profileHasCredential(profile config.ProviderProfile) bool {
 }

 // baseURLIsLoopback reports whether a provider base_url points at a loopback host
-// or a private-network host (192.168.x.y / 10.x.y.z / 172.16.x.y) — a local
-// provider like Ollama/LM Studio that needs no API key.
+// (a keyless local provider like Ollama/LM Studio), which needs no API key.
 func baseURLIsLoopback(baseURL string) bool {
 	u := strings.TrimSpace(baseURL)
 	if u == "" {
@@ -1206,7 +1167,7 @@ func baseURLIsLoopback(baseURL string) bool {
 		return true
 	}
 	if addr, err := netip.ParseAddr(host); err == nil {
-		return addr.IsLoopback() || addr.IsPrivate()
+		return addr.IsLoopback()
 	}
 	return false
 }
@@ -205,67 +205,6 @@ func TestRunNoArgsEntersSetupWhenResolveReportsNoActiveProvider(t *testing.T) {
 	}
 }

-func TestRunNoArgsFallsBackToUsableProviderWhenNoneMarkedActive(t *testing.T) {
-	var stdout bytes.Buffer
-	var stderr bytes.Buffer
-	cwd := t.TempDir()
-	setCLIUserConfigRoot(t)
-	userConfigPath := filepath.Join(t.TempDir(), "zero", "config.json")
-	var launchedOptions tui.Options
-	launched := false
-	var providerProfile config.ProviderProfile
-	fake := &cliFakeProvider{}
-
-	usable := config.ProviderProfile{
-		Name:         "work",
-		ProviderKind: config.ProviderKindOpenAI,
-		BaseURL:      config.OpenAIBaseURL,
-		APIKey:       "sk-test",
-		Model:        "gpt-test",
-	}
-
-	exitCode := runWithDeps([]string{}, &stdout, &stderr, appDeps{
-		getwd: func() (string, error) {
-			return cwd, nil
-		},
-		resolveConfig: func(workspaceRoot string, overrides config.Overrides) (config.ResolvedConfig, error) {
-			// config.json has providers configured but none marked active (e.g. a
-			// blank/stale activeProvider field) — Resolve returns the successfully
-			// normalized providers list alongside ErrNoActiveProvider.
-			return config.ResolvedConfig{Providers: []config.ProviderProfile{usable}},
-				fmt.Errorf("%w: active provider %q not found", config.ErrNoActiveProvider, "")
-		},
-		newProvider: func(profile config.ProviderProfile) (zeroruntime.Provider, error) {
-			providerProfile = profile
-			return fake, nil
-		},
-		userConfigPath: func() (string, error) {
-			return userConfigPath, nil
-		},
-		registerMCPTools: func(context.Context, *tools.Registry, config.MCPConfig, mcp.RegisterOptions) (mcpToolRuntime, error) {
-			return noopMCPRuntime{}, nil
-		},
-		runTUI: func(ctx context.Context, options tui.Options) int {
-			launched = true
-			launchedOptions = options
-			return 0
-		},
-	})
-
-	if exitCode != 0 {
-		t.Fatalf("exit code = %d, want 0, stderr=%q", exitCode, stderr.String())
-	}
-	if !launched {
-		t.Fatal("TUI was not launched")
-	}
-	if launchedOptions.Setup.Visible || launchedOptions.Setup.Required {
-		t.Fatalf("Setup = %#v, want no setup wizard — a usable saved provider exists", launchedOptions.Setup)
-	}
-	if providerProfile.Name != "work" {
-		t.Fatalf("provider used = %q, want fallback to the usable saved provider %q", providerProfile.Name, "work")
-	}
-}
-
 func TestRunNoArgsFailsWhenResolveErrorIsNotProviderRelated(t *testing.T) {
 	var stdout bytes.Buffer
 	var stderr bytes.Buffer
@@ -1328,153 +1267,6 @@ func TestRunUpdateReportsUpToDate(t *testing.T) {
 	}
 }

-func TestRunUpdateApplyTextAndJSON(t *testing.T) {
-	applyResult := update.ApplyResult{
-		Result: update.Result{
-			CurrentVersion:  "dev",
-			LatestVersion:   "0.2.0",
-			UpdateAvailable: true,
-		},
-		Applied:       true,
-		InstallMethod: update.InstallMethodStandalone,
-		BinaryPath:    "/usr/local/bin/zero",
-		Message:       "updated to 0.2.0",
-	}
-	var gotOptions update.Options
-	deps := appDeps{
-		applyUpdate: func(_ context.Context, options update.Options) (update.ApplyResult, error) {
-			gotOptions = options
-			return applyResult, nil
-		},
-		checkUpdate: func(context.Context, update.Options) (update.Result, error) {
-			t.Fatal("checkUpdate should not run for --apply")
-			return update.Result{}, nil
-		},
-	}
-
-	var stdout bytes.Buffer
-	var stderr bytes.Buffer
-	exitCode := runWithDeps([]string{"update", "--apply"}, &stdout, &stderr, deps)
-	if exitCode != exitSuccess {
-		t.Fatalf("expected exit code %d, got %d: %s", exitSuccess, exitCode, stderr.String())
-	}
-	if !strings.Contains(stdout.String(), "updated to 0.2.0") {
-		t.Fatalf("unexpected apply text: %q", stdout.String())
-	}
-	if gotOptions.CurrentVersion != "dev" {
-		t.Fatalf("unexpected options passed to applyUpdate: %#v", gotOptions)
-	}
-
-	stdout.Reset()
-	stderr.Reset()
-	exitCode = runWithDeps([]string{"update", "--apply", "--json"}, &stdout, &stderr, deps)
-	if exitCode != exitSuccess {
-		t.Fatalf("expected exit code %d, got %d: %s", exitSuccess, exitCode, stderr.String())
-	}
-	var payload struct {
-		Applied       bool   `json:"applied"`
-		InstallMethod string `json:"installMethod"`
-		BinaryPath    string `json:"binaryPath"`
-	}
-	if err := json.Unmarshal(stdout.Bytes(), &payload); err != nil {
-		t.Fatalf("apply JSON did not decode: %v\n%s", err, stdout.String())
-	}
-	if !payload.Applied || payload.InstallMethod != string(update.InstallMethodStandalone) || payload.BinaryPath != applyResult.BinaryPath {
-		t.Fatalf("unexpected apply JSON: %#v", payload)
-	}
-}
-
-func TestRunUpgradeDefaultsToApply(t *testing.T) {
-	var applyCalled bool
-	deps := appDeps{
-		applyUpdate: func(context.Context, update.Options) (update.ApplyResult, error) {
-			applyCalled = true
-			return update.ApplyResult{Message: "already up to date"}, nil
-		},
-		checkUpdate: func(context.Context, update.Options) (update.Result, error) {
-			t.Fatal("checkUpdate should not run for `zero upgrade`")
-			return update.Result{}, nil
-		},
-	}
-
-	var stdout bytes.Buffer
-	var stderr bytes.Buffer
-	exitCode := runWithDeps([]string{"upgrade"}, &stdout, &stderr, deps)
-	if exitCode != exitSuccess {
-		t.Fatalf("expected exit code %d, got %d: %s", exitSuccess, exitCode, stderr.String())
-	}
-	if !applyCalled {
-		t.Fatal("expected `zero upgrade` to call applyUpdate")
-	}
-}
-
-func TestRunUpdateRejectsCheckAndApplyTogether(t *testing.T) {
-	var stdout bytes.Buffer
-	var stderr bytes.Buffer
-
-	exitCode := runWithDeps([]string{"update", "--check", "--apply"}, &stdout, &stderr, appDeps{
-		checkUpdate: func(context.Context, update.Options) (update.Result, error) {
-			t.Fatal("checkUpdate should not run")
-			return update.Result{}, nil
-		},
-		applyUpdate: func(context.Context, update.Options) (update.ApplyResult, error) {
-			t.Fatal("applyUpdate should not run")
-			return update.ApplyResult{}, nil
-		},
-	})
-
-	if exitCode != exitUsage {
-		t.Fatalf("expected usage exit code, got %d", exitCode)
-	}
-	if got := stderr.String(); !strings.Contains(got, "only one of --check or --apply") {
-		t.Fatalf("expected --check/--apply usage error, got %q", got)
-	}
-}
-
-func TestRunUpdateRejectsTargetWithApply(t *testing.T) {
-	for _, args := range [][]string{
-		{"update", "--apply", "--target", "linux-arm64"},
-		{"upgrade", "--target", "linux-arm64"},
-	} {
-		t.Run(strings.Join(args, " "), func(t *testing.T) {
-			var stdout bytes.Buffer
-			var stderr bytes.Buffer
-
-			exitCode := runWithDeps(args, &stdout, &stderr, appDeps{
-				applyUpdate: func(context.Context, update.Options) (update.ApplyResult, error) {
-					t.Fatal("applyUpdate should not run when --target is combined with --apply")
-					return update.ApplyResult{}, nil
-				},
-			})
-
-			if exitCode != exitUsage {
-				t.Fatalf("expected usage exit code, got %d", exitCode)
-			}
-			if got := stderr.String(); !strings.Contains(got, "--target cannot be combined with --apply") {
-				t.Fatalf("expected --target/--apply usage error, got %q", got)
-			}
-		})
-	}
-}
-
-func TestRunUpdateReportsApplyError(t *testing.T) {
-	var stdout bytes.Buffer
-	var stderr bytes.Buffer
-
-	exitCode := runWithDeps([]string{"update", "--apply"}, &stdout, &stderr, appDeps{
-		applyUpdate: func(context.Context, update.Options) (update.ApplyResult, error) {
-			return update.ApplyResult{}, errors.New("download failed")
-		},
-	})
-
-	if exitCode == exitSuccess {
-		t.Fatalf("expected non-success exit code, got %d", exitCode)
-	}
-	if got := stderr.String(); !strings.Contains(got, "download failed") {
-		t.Fatalf("expected apply error, got %q", got)
-	}
-}
-
 func assertHelpOutput(t *testing.T, args []string) {
 	t.Helper()

@@ -301,27 +301,12 @@ func runAuthLogin(args []string, stdout io.Writer, stderr io.Writer, deps appDep
 	if len(parsed.positional) != 1 {
 		return writeExecUsageError(stderr, "usage: zero auth login <provider> [--device] [--scope <scope>]")
 	}
-	provider := parsed.positional[0]
-	// ChatGPT (Codex) requires a fixed redirect_uri (http://localhost:1455/
-	// auth/callback) and mandatory authorize params (id_token_add_organizations,
-	// codex_cli_simplified_flow, originator) that the generic loopback flow
-	// cannot supply. Route it to the dedicated ChatGPT login so
-	// `zero auth login chatgpt` behaves identically to `zero auth chatgpt`.
-	if strings.EqualFold(provider, "chatgpt") {
-		if parsed.device {
-			return writeExecUsageError(stderr, "ChatGPT login does not support --device (it is loopback-only)")
-		}
-		if len(parsed.scopes) > 0 {
-			return writeExecUsageError(stderr, "ChatGPT login does not support --scope (the required scopes are fixed by the Codex client registration)")
-		}
-		return runAuthChatGPT(nil, stdout, stderr, deps)
-	}
 	manager, err := newAuthManager(deps, stdout)
 	if err != nil {
 		return writeAppError(stderr, redaction.ErrorMessage(err, redaction.Options{}), exitCrash)
 	}
 	status, err := manager.Login(context.Background(), oauth.LoginOptions{
-		Provider:    provider,
+		Provider:    parsed.positional[0],
 		Device:      parsed.device,
 		ExtraScopes: parsed.scopes,
 	})
@@ -504,9 +489,8 @@ Commands:
 A provider is any OAuth 2.0 / OIDC server. "openrouter" ('zero auth openrouter')
 works out of the box. "xai" ('zero auth login xai') uses a built-in preset that is
 off by default — enable it with ZERO_OAUTH_ALLOW_PRESETS=1, or set the
-ZERO_OAUTH_XAI_* vars yourself. "chatgpt" ('zero auth login chatgpt' or
-'zero auth chatgpt') uses a fixed-port loopback flow against the Codex backend.
-Any preset field is overridable via the env vars below. For a custom provider named <name>, set:
+ZERO_OAUTH_XAI_* vars yourself. Any preset field is overridable via the env vars
+below. For a custom provider named <name>, set:
  ZERO_OAUTH_<NAME>_CLIENT_ID       (required)
  ZERO_OAUTH_<NAME>_CLIENT_SECRET   (optional)
  ZERO_OAUTH_<NAME>_AUTHORIZE_URL   ZERO_OAUTH_<NAME>_TOKEN_URL
@@ -156,44 +156,3 @@ func TestRunAuthHelp(t *testing.T) {
 		}
 	}
 }
-
-// TestRunAuthLoginChatGPTRoutesToDedicatedFlow verifies `zero auth login
-// chatgpt` reaches the dedicated ChatGPT login (fixed-port loopback + mandatory
-// authorize params), not the generic manager path. The generic login accepts
-// --device, so a ChatGPT-specific rejection proves the routing took effect.
-// See issue #430: the generic path built a random-port 127.0.0.1 redirect_uri
-// without the required extra params, so OpenAI's authorize endpoint rejected it.
-func TestRunAuthLoginChatGPTRoutesToDedicatedFlow(t *testing.T) {
-	withAuthStore(t)
-	var stdout, stderr bytes.Buffer
-	if code := runWithDeps([]string{"auth", "login", "chatgpt", "--device"}, &stdout, &stderr, appDeps{}); code == exitSuccess {
-		t.Fatal("auth login chatgpt --device should be rejected (ChatGPT is loopback-only)")
-	}
-	if !strings.Contains(stderr.String(), "ChatGPT login does not support --device") {
-		t.Fatalf("stderr = %q, want the ChatGPT-specific --device rejection", stderr.String())
-	}
-	// Case-insensitive provider name should still route.
-	stdout.Reset()
-	stderr.Reset()
-	if code := runWithDeps([]string{"auth", "login", "ChatGPT", "--device"}, &stdout, &stderr, appDeps{}); code == exitSuccess {
-		t.Fatal("auth login ChatGPT --device should be rejected")
-	}
-	if !strings.Contains(stderr.String(), "ChatGPT login does not support --device") {
-		t.Fatalf("stderr = %q, want the ChatGPT-specific rejection (case-insensitive)", stderr.String())
-	}
-}
-
-// TestRunAuthLoginChatGPTRejectsScope mirrors the --device rejection: --scope
-// must not be silently dropped on the ChatGPT path. The Codex client
-// registration pins a fixed scope set (incl. api.connectors.*), so custom
-// scopes are rejected up front rather than plumbed through.
-func TestRunAuthLoginChatGPTRejectsScope(t *testing.T) {
-	withAuthStore(t)
-	var stdout, stderr bytes.Buffer
-	if code := runWithDeps([]string{"auth", "login", "chatgpt", "--scope", "custom-scope"}, &stdout, &stderr, appDeps{}); code == exitSuccess {
-		t.Fatal("auth login chatgpt --scope should be rejected")
-	}
-	if !strings.Contains(stderr.String(), "ChatGPT login does not support --scope") {
-		t.Fatalf("stderr = %q, want the ChatGPT-specific --scope rejection", stderr.String())
-	}
-}
@@ -81,9 +81,6 @@ func runProviders(args []string, stdout io.Writer, stderr io.Writer, deps appDep
 	if command == "detect" {
 		return runProvidersDetect(args, stdout, stderr, deps)
 	}
-	if command == "models" {
-		return runProvidersModels(args, stdout, stderr, deps)
-	}
 	if command != "list" && command != "current" && command != "catalog" {
 		return writeExecUsageError(stderr, fmt.Sprintf("unknown providers command %q", command))
 	}
@@ -468,11 +465,9 @@ func writeProvidersHelp(w io.Writer) error {
  zero providers use <name> [flags]
  zero providers setup <catalog-id> [flags]
  zero providers detect [flags]
-  zero providers models [name] [flags]

 Inspects resolved provider profiles and provider catalog descriptors without printing secrets.
 Detect probes for running local runtimes (Ollama, LM Studio) and prints adopt commands plus per-provider next steps.
-Models probes a provider's live model-listing endpoint (e.g. an OpenAI-compatible /v1/models) and lists the models it serves — including custom OpenAI-/Anthropic-compatible endpoints — so a self-hosted provider needs no per-model config.

 Flags:
      --json                    Print JSON summary
@@ -135,11 +135,6 @@ func runExec(args []string, stdout io.Writer, stderr io.Writer, deps appDeps) in
 		return exitSuccess
 	}

-	// Refresh the models.dev pricing/limits cache in the background when stale;
-	// the overlay is read at registry construction from the cache file, so this
-	// benefits the next run and never blocks or fails this one.
-	go func() { _ = modelregistry.RefreshModelsDevCache(context.Background()) }()
-
 	// A mode seeds model/effort/max-turns/tool filters as a preset. Expand it up
 	// front — before tool-filter validation and the --list-tools branch — so a
 	// mode-injected tool filter is validated and reflected in --list-tools, and a
@@ -504,17 +499,15 @@ func runExec(args []string, stdout io.Writer, stderr io.Writer, deps appDeps) in
 	// by default the corrector is nil, leaving the agent loop byte-identical. When
 	// on we verify with both the workspace test plan and LSP diagnostics over the
 	// changed files; the autonomy gate inside the corrector still decides whether
-	// failures auto-fix or just report. fileDiagnostics (always on, lazy) gives
-	// edit_file/write_file inline error diagnostics for the file they just wrote.
-	// lspShutdown tears down any language-server sessions either half spawned.
-	selfCorrector, fileDiagnostics, lspShutdown := newExecSelfCorrector(options.selfCorrect, workspaceRoot, options.autonomy)
+	// failures auto-fix or just report. lspShutdown tears down any language-server
+	// sessions the LSP half spawned (no-op when self-correct is off).
+	selfCorrector, lspShutdown := newExecSelfCorrector(options.selfCorrect, workspaceRoot, options.autonomy)
 	defer lspShutdown()
 	result, err := agent.Run(runCtx, agentPrompt, provider, agent.Options{
 		MaxTurns:         resolved.MaxTurns,
 		ContextWindow:    resolveAgentContextWindow(runCtx, modelRegistry, resolved.Provider),
 		DeferThreshold:   effectiveDeferThreshold,
 		Specialists:      specialistRuntime.specialistInfos(),
-		Skills:           pluginActivation.skillInfos(deps.skillsDir()),
 		SessionID:        preparedSession.Session.SessionID,
 		CallingSessionID: options.callingSessionID,
 		CallingToolUseID: options.callingToolUseID,
@@ -531,7 +524,6 @@ func runExec(args []string, stdout io.Writer, stderr io.Writer, deps appDeps) in
 		PermissionMode:   permissionMode,
 		Autonomy:         options.autonomy,
 		SelfCorrect:      selfCorrector,
-		FileDiagnostics:  fileDiagnostics,
 		// 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
@@ -707,28 +699,23 @@ func runExec(args []string, stdout io.Writer, stderr io.Writer, deps appDeps) in
 // unless a changed file's language actually has one installed on PATH. The
 // returned cleanup shuts that manager down (terminating any spawned server
 // sessions); it is a no-op when self-correct is off.
-func newExecSelfCorrector(enabled bool, workspaceRoot string, autonomy string) (*agent.SelfCorrector, func(context.Context, string) string, func()) {
-	// The manager is created regardless of --self-correct: it also backs the
-	// always-on inline post-edit diagnostics (agent.NewFileDiagnostics), and it
-	// stays lazy — no language server is spawned unless an edited file's
-	// language actually has one installed on PATH.
-	manager := lsp.NewManager(workspaceRoot)
-	cleanup := func() {
-		ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
-		defer cancel()
-		_ = manager.Shutdown(ctx)
-	}
-	fileDiagnostics := agent.NewFileDiagnostics(manager)
+func newExecSelfCorrector(enabled bool, workspaceRoot string, autonomy string) (*agent.SelfCorrector, func()) {
 	if !enabled {
-		return nil, fileDiagnostics, cleanup
+		return nil, func() {}
 	}
+	manager := lsp.NewManager(workspaceRoot)
 	corrector := agent.NewSelfCorrector(workspaceRoot, agent.NewLSPDiagnosticsChecker(manager), agent.NewProjectVerifier(workspaceRoot), agent.SelfCorrectConfig{
 		Enabled:      true,
 		IncludeTests: true,
 		IncludeLSP:   true,
 		Autonomy:     autonomy,
 	})
-	return corrector, fileDiagnostics, cleanup
+	cleanup := func() {
+		ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
+		defer cancel()
+		_ = manager.Shutdown(ctx)
+	}
+	return corrector, cleanup
 }

 func deferredEligibleCount(registry *tools.Registry, permissionMode agent.PermissionMode, enabledTools []string, disabledTools []string) int {
@@ -3,9 +3,7 @@ package cli
 import (
 	"fmt"
 	"io"
-	"strings"

-	"github.com/Gitlawb/zero/internal/agent"
 	"github.com/Gitlawb/zero/internal/hooks"
 	"github.com/Gitlawb/zero/internal/plugins"
 	"github.com/Gitlawb/zero/internal/tools"
@@ -59,27 +57,6 @@ func activatePlugins(workspaceRoot string, registry *tools.Registry, deps appDep
 	return pluginActivation{hooks: result.Hooks, skillRoots: result.SkillRoots}
 }

-// skillInfos resolves the reusable skills the model can load via the skill tool —
-// the default skills dir merged with any plugin skill roots, the same set the
-// plugin-aware skill tool resolves against — as plain data for the agent's system
-// prompt. It returns nil when no skills are installed, so a skill-less run leaves
-// the prompt byte-identical.
-func (a pluginActivation) skillInfos(defaultDir string) []agent.SkillInfo {
-	merged, _ := plugins.MergedSkills(defaultDir, a.skillRoots)
-	if len(merged) == 0 {
-		return nil
-	}
-	infos := make([]agent.SkillInfo, 0, len(merged))
-	for _, skill := range merged {
-		name := strings.TrimSpace(skill.Name)
-		if name == "" {
-			continue
-		}
-		infos = append(infos, agent.SkillInfo{Name: name, Description: strings.TrimSpace(skill.Description)})
-	}
-	return infos
-}
-
 // formatLoadDiagnostic renders a plugin load diagnostic into a single warning
 // line, prefixing the diagnostic kind and appending the most specific locator
 // available (manifest path, then plugin path, then plugin ID) so an operator can
@@ -18,7 +18,6 @@ func TestProviderCatalogRuntimeProvidersShowOnboardingSetupHints(t *testing.T) {
 	}{
 		{id: "openai", name: "OpenAI", transport: "openai", defaultModel: "gpt-4.1"},
 		{id: "groq", name: "Groq", transport: "openai-compatible", defaultModel: "llama-3.3-70b-versatile"},
-		{id: "longcat", name: "LongCat", transport: "openai-compatible", defaultModel: "LongCat-2.0"},
 		{id: "ollama-cloud", name: "Ollama Cloud", transport: "openai-compatible", defaultModel: "qwen3-coder:480b"},
 		{id: "ollama", name: "Ollama Local", transport: "openai-compatible", defaultModel: "llama3.1"},
 	}
@@ -47,21 +46,6 @@ func TestProviderCatalogRuntimeProvidersShowOnboardingSetupHints(t *testing.T) {
 	}
 }

-func TestProviderCatalogLongCatRequiresAPIKey(t *testing.T) {
-	output := runProviderCatalogOnboarding(t)
-	block := providerCatalogOnboardingBlock(t, output, "longcat")
-
-	for _, want := range []string{
-		"requiresAuth=true",
-		"authEnvVars=LONGCAT_API_KEY",
-		"setup: zero providers setup longcat --set-active",
-	} {
-		if !strings.Contains(block, want) {
-			t.Fatalf("expected LongCat catalog block to contain %q, got:\n%s", want, block)
-		}
-	}
-}
-
 func TestProviderCatalogOllamaCloudRequiresAPIKey(t *testing.T) {
 	output := runProviderCatalogOnboarding(t)
 	block := providerCatalogOnboardingBlock(t, output, "ollama-cloud")
@@ -1,148 +0,0 @@
-package cli
-
-import (
-	"context"
-	"fmt"
-	"io"
-	"os"
-	"strings"
-
-	"github.com/Gitlawb/zero/internal/config"
-	"github.com/Gitlawb/zero/internal/providermodeldiscovery"
-)
-
-type providerModelsOptions struct {
-	name string
-	json bool
-}
-
-// runProvidersModels lists the models a saved provider actually serves by probing
-// its live model-discovery endpoint (e.g. an OpenAI-compatible `/v1/models`). It
-// works for custom OpenAI-/Anthropic-compatible providers too: discovery runs off
-// the profile's base URL + credentials, so a self-hosted endpoint serving a dozen
-// models no longer needs a config object per model — configure the provider once,
-// then run any listed model with `zero exec --model <id>` (Zero passes unknown
-// model ids through to the provider).
-func runProvidersModels(args []string, stdout io.Writer, stderr io.Writer, deps appDeps) int {
-	options, help, err := parseProviderModelsArgs(args)
-	if err != nil {
-		return writeExecUsageError(stderr, err.Error())
-	}
-	if help {
-		if err := writeProvidersHelp(stdout); err != nil {
-			return exitCrash
-		}
-		return exitSuccess
-	}
-
-	resolved, exitCode := resolveCommandCenterConfig(stderr, deps)
-	if exitCode != exitSuccess {
-		return exitCode
-	}
-	profile, err := selectProviderForCheck(resolved, options.name)
-	if err != nil {
-		return writeExecUsageError(stderr, err.Error())
-	}
-
-	ctx, stop := signalContext()
-	defer stop()
-	models, err := deps.discoverProviderModels(ctx, discoveryCredentialProfile(profile))
-	if err != nil {
-		return writeAppError(stderr, err.Error(), exitProvider)
-	}
-
-	if options.json {
-		items := make([]map[string]any, 0, len(models))
-		for _, model := range models {
-			entry := map[string]any{"id": model.ID}
-			if description := strings.TrimSpace(model.Description); description != "" {
-				entry["description"] = description
-			}
-			items = append(items, entry)
-		}
-		payload := map[string]any{
-			"provider": profile.Name,
-			"count":    len(items),
-			"models":   items,
-		}
-		if err := writePrettyJSON(stdout, payload); err != nil {
-			return exitCrash
-		}
-		return exitSuccess
-	}
-
-	name := strings.TrimSpace(profile.Name)
-	if name == "" {
-		name = "provider"
-	}
-	if _, err := fmt.Fprintf(stdout, "Provider models (%s)\n", name); err != nil {
-		return exitCrash
-	}
-	for _, model := range models {
-		line := strings.TrimSpace(model.ID)
-		if description := strings.TrimSpace(model.Description); description != "" {
-			line += " — " + description
-		}
-		if _, err := fmt.Fprintln(stdout, line); err != nil {
-			return exitCrash
-		}
-	}
-	suffix := "s"
-	if len(models) == 1 {
-		suffix = ""
-	}
-	if _, err := fmt.Fprintf(stdout, "%d model%s discovered\n", len(models), suffix); err != nil {
-		return exitCrash
-	}
-	if len(models) > 0 {
-		if _, err := fmt.Fprintf(stdout, "next: zero exec %q --model %s\n", "hello", setupCommandArg(models[0].ID)); err != nil {
-			return exitCrash
-		}
-	}
-	return exitSuccess
-}
-
-// discoveryCredentialProfile resolves the profile's API key the same way the
-// runtime does — inline, then the stored credential, then the configured env var —
-// so a `providers models` probe authenticates exactly like a real request. Mirrors
-// discoveredModelContextWindow's credential resolution.
-func discoveryCredentialProfile(profile config.ProviderProfile) config.ProviderProfile {
-	authed := profile
-	if strings.TrimSpace(authed.APIKey) == "" {
-		if store, err := config.ProviderKeyStore(); err == nil {
-			authed = config.ApplyStoredAPIKey(authed, store)
-		}
-	}
-	if strings.TrimSpace(authed.APIKey) == "" && strings.TrimSpace(authed.APIKeyEnv) != "" {
-		authed.APIKey = strings.TrimSpace(os.Getenv(authed.APIKeyEnv))
-	}
-	return authed
-}
-
-// defaultDiscoverProviderModels is the production discovery hook: a live probe of
-// the provider's model-listing endpoint with no curated-catalog merge or
-// coding-model filtering, so a custom provider's full model list is returned.
-func defaultDiscoverProviderModels(ctx context.Context, profile config.ProviderProfile) ([]providermodeldiscovery.Model, error) {
-	return providermodeldiscovery.Discover(ctx, profile, providermodeldiscovery.Options{})
-}
-
-func parseProviderModelsArgs(args []string) (providerModelsOptions, bool, error) {
-	options := providerModelsOptions{}
-	for index := 0; index < len(args); index++ {
-		arg := args[index]
-		switch {
-		case arg == "-h" || arg == "--help" || arg == "help":
-			return options, true, nil
-		case arg == "--json":
-			options.json = true
-		case strings.HasPrefix(arg, "-"):
-			return options, false, execUsageError{fmt.Sprintf("unknown flag %q", arg)}
-		default:
-			if options.name != "" {
-				return options, false, execUsageError{fmt.Sprintf("unexpected argument %q", arg)}
-			}
-			options.name = arg
-		}
-	}
-	return options, false, nil
-}
@@ -1,151 +0,0 @@
-package cli
-
-import (
-	"bytes"
-	"context"
-	"encoding/json"
-	"errors"
-	"strings"
-	"testing"
-
-	"github.com/Gitlawb/zero/internal/config"
-	"github.com/Gitlawb/zero/internal/providermodeldiscovery"
-)
-
-func TestRunProvidersModelsListsDiscoveredModels(t *testing.T) {
-	var stdout bytes.Buffer
-	var stderr bytes.Buffer
-	deps := commandCenterDeps(t)
-	var probed config.ProviderProfile
-	deps.discoverProviderModels = func(_ context.Context, profile config.ProviderProfile) ([]providermodeldiscovery.Model, error) {
-		probed = profile
-		return []providermodeldiscovery.Model{
-			{ID: "team/model-a", Description: "first"},
-			{ID: "team/model-b"},
-		}, nil
-	}
-
-	exitCode := runWithDeps([]string{"providers", "models"}, &stdout, &stderr, deps)
-
-	if exitCode != exitSuccess {
-		t.Fatalf("exit = %d, want %d: %s", exitCode, exitSuccess, stderr.String())
-	}
-	// No name given → the active provider is probed, with its resolved credential.
-	if probed.Name != "work" {
-		t.Fatalf("probed provider = %q, want active provider work", probed.Name)
-	}
-	out := stdout.String()
-	for _, want := range []string{"Provider models (work)", "team/model-a — first", "team/model-b", "2 models discovered", "--model team/model-a"} {
-		if !strings.Contains(out, want) {
-			t.Fatalf("output missing %q:\n%s", want, out)
-		}
-	}
-}
-
-func TestRunProvidersModelsJSON(t *testing.T) {
-	var stdout bytes.Buffer
-	var stderr bytes.Buffer
-	deps := commandCenterDeps(t)
-	deps.discoverProviderModels = func(_ context.Context, _ config.ProviderProfile) ([]providermodeldiscovery.Model, error) {
-		return []providermodeldiscovery.Model{{ID: "m1", Description: "d1"}, {ID: "m2"}}, nil
-	}
-
-	exitCode := runWithDeps([]string{"providers", "models", "--json"}, &stdout, &stderr, deps)
-
-	if exitCode != exitSuccess {
-		t.Fatalf("exit = %d, want %d: %s", exitCode, exitSuccess, stderr.String())
-	}
-	var payload struct {
-		Provider string `json:"provider"`
-		Count    int    `json:"count"`
-		Models   []struct {
-			ID          string `json:"id"`
-			Description string `json:"description"`
-		} `json:"models"`
-	}
-	if err := json.Unmarshal(stdout.Bytes(), &payload); err != nil {
-		t.Fatalf("decode json: %v\n%s", err, stdout.String())
-	}
-	if payload.Provider != "work" || payload.Count != 2 || len(payload.Models) != 2 {
-		t.Fatalf("payload = %#v", payload)
-	}
-	if payload.Models[0].ID != "m1" || payload.Models[0].Description != "d1" {
-		t.Fatalf("model[0] = %#v", payload.Models[0])
-	}
-	// A model with no description omits the field rather than emitting an empty string.
-	if payload.Models[1].ID != "m2" || payload.Models[1].Description != "" {
-		t.Fatalf("model[1] = %#v", payload.Models[1])
-	}
-}
-
-func TestRunProvidersModelsSelectsNamedProvider(t *testing.T) {
-	var stdout bytes.Buffer
-	var stderr bytes.Buffer
-	deps := commandCenterDeps(t)
-	custom := config.ProviderProfile{
-		Name:         "self-hosted",
-		ProviderKind: config.ProviderKindOpenAICompatible,
-		BaseURL:      "https://models.internal/v1",
-		APIKey:       "sk-internal",
-		Model:        "house-model",
-	}
-	deps.resolveConfig = func(string, config.Overrides) (config.ResolvedConfig, error) {
-		work := config.ProviderProfile{Name: "work", ProviderKind: config.ProviderKindOpenAI, BaseURL: config.OpenAIBaseURL, APIKey: "sk", Model: "gpt-4.1"}
-		return config.ResolvedConfig{ActiveProvider: "work", Provider: work, Providers: []config.ProviderProfile{work, custom}}, nil
-	}
-	var probed config.ProviderProfile
-	deps.discoverProviderModels = func(_ context.Context, profile config.ProviderProfile) ([]providermodeldiscovery.Model, error) {
-		probed = profile
-		return []providermodeldiscovery.Model{{ID: "house-model"}}, nil
-	}
-
-	exitCode := runWithDeps([]string{"providers", "models", "self-hosted"}, &stdout, &stderr, deps)
-
-	if exitCode != exitSuccess {
-		t.Fatalf("exit = %d, want %d: %s", exitCode, exitSuccess, stderr.String())
-	}
-	if probed.Name != "self-hosted" || probed.BaseURL != "https://models.internal/v1" {
-		t.Fatalf("probed = %#v, want the named custom provider", probed)
-	}
-}
-
-func TestRunProvidersModelsUnknownProviderFails(t *testing.T) {
-	var stdout bytes.Buffer
-	var stderr bytes.Buffer
-	deps := commandCenterDeps(t)
-	called := false
-	deps.discoverProviderModels = func(_ context.Context, _ config.ProviderProfile) ([]providermodeldiscovery.Model, error) {
-		called = true
-		return nil, nil
-	}
-
-	exitCode := runWithDeps([]string{"providers", "models", "ghost"}, &stdout, &stderr, deps)
-
-	if exitCode == exitSuccess {
-		t.Fatalf("exit = %d, want non-zero for unknown provider", exitCode)
-	}
-	if called {
-		t.Fatal("discovery must not run for an unknown provider")
-	}
-	if !strings.Contains(stderr.String(), `provider "ghost" not found`) {
-		t.Fatalf("stderr = %q, want provider-not-found", stderr.String())
-	}
-}
-
-func TestRunProvidersModelsSurfacesDiscoveryError(t *testing.T) {
-	var stdout bytes.Buffer
-	var stderr bytes.Buffer
-	deps := commandCenterDeps(t)
-	deps.discoverProviderModels = func(_ context.Context, _ config.ProviderProfile) ([]providermodeldiscovery.Model, error) {
-		return nil, errors.New("models endpoint returned 404")
-	}
-
-	exitCode := runWithDeps([]string{"providers", "models"}, &stdout, &stderr, deps)
-
-	if exitCode != exitProvider {
-		t.Fatalf("exit = %d, want exitProvider %d", exitCode, exitProvider)
-	}
-	if !strings.Contains(stderr.String(), "models endpoint returned 404") {
-		t.Fatalf("stderr = %q, want the discovery error", stderr.String())
-	}
-}
@@ -3,7 +3,6 @@ package cli
 import (
 	"fmt"
 	"io"
-	"net"
 	"net/url"
 	"strconv"
 	"strings"
@@ -454,11 +453,6 @@ func providerProfileIsLocal(profile config.ProviderProfile) bool {
 	case "localhost", "127.0.0.1", "::1":
 		return true
 	}
-	// Also treat explicit private-network IPs (192.168.x.y, 10.x.y.z,
-	// 172.16-31.x.y) as local — the user is pointing at their own LAN box.
-	if ip := net.ParseIP(parsed.Hostname()); ip != nil && ip.IsPrivate() {
-		return true
-	}
 	return false
 }

@@ -12,7 +12,6 @@ import (

 type updateOptions struct {
 	check      bool
-	apply      bool
 	json       bool
 	repository string
 	endpoint   string
@@ -21,18 +20,6 @@ type updateOptions struct {
 }

 func runUpdate(args []string, stdout io.Writer, stderr io.Writer, deps appDeps) int {
-	return runUpdateCommand(args, stdout, stderr, deps, false)
-}
-
-func runUpgrade(args []string, stdout io.Writer, stderr io.Writer, deps appDeps) int {
-	return runUpdateCommand(args, stdout, stderr, deps, true)
-}
-
-// runUpdateCommand backs both `zero update` and `zero upgrade`. defaultApply
-// makes `--apply` the implicit behavior for `zero upgrade` when neither
-// `--check` nor `--apply` is passed explicitly; `zero update` keeps requiring
-// one of the two so existing scripts around `zero update --check` don't change.
-func runUpdateCommand(args []string, stdout io.Writer, stderr io.Writer, deps appDeps, defaultApply bool) int {
 	options, help, err := parseUpdateArgs(args)
 	if err != nil {
 		return writeUsageError(stderr, err.Error())
@@ -43,19 +30,10 @@ func runUpdateCommand(args []string, stdout io.Writer, stderr io.Writer, deps ap
 		}
 		return exitSuccess
 	}
-	if options.check && options.apply {
-		return writeUsageError(stderr, "Pass only one of --check or --apply.")
+	if !options.check {
+		return writeUsageError(stderr, "Only `zero update --check` is available right now.")
 	}
-	if !options.check && !options.apply {
-		if !defaultApply {
-			return writeUsageError(stderr, "Pass --check to check for updates or --apply to install one (or use `zero upgrade`).")
-		}
-		options.apply = true
-	}
-	if options.apply && options.target != "" {
-		return writeUsageError(stderr, "--target cannot be combined with --apply; it only verifies release assets for --check.")
-	}
-	updateOptions := update.Options{
+	checkOptions := update.Options{
 		CurrentVersion: version,
 		Repository:     options.repository,
 		Endpoint:       options.endpoint,
@@ -66,26 +44,10 @@ func runUpdateCommand(args []string, stdout io.Writer, stderr io.Writer, deps ap
 		if err != nil {
 			return writeUsageError(stderr, err.Error())
 		}
-		updateOptions.GOOS = target.GOOS
-		updateOptions.GOARCH = target.GOARCH
+		checkOptions.GOOS = target.GOOS
+		checkOptions.GOARCH = target.GOARCH
 	}
-	if options.apply {
-		result, err := deps.applyUpdate(context.Background(), updateOptions)
-		if err != nil {
-			return writeAppError(stderr, "Could not install update: "+err.Error(), exitCrash)
-		}
-		if options.json {
-			if err := writePrettyJSON(stdout, result); err != nil {
-				return exitCrash
-			}
-			return exitSuccess
-		}
-		if _, err := fmt.Fprintln(stdout, update.FormatApply(result)); err != nil {
-			return exitCrash
-		}
-		return exitSuccess
-	}
-	result, err := deps.checkUpdate(context.Background(), updateOptions)
+	result, err := deps.checkUpdate(context.Background(), checkOptions)
 	if err != nil {
 		return writeAppError(stderr, "Could not check for updates: "+err.Error(), exitCrash)
 	}
@@ -110,8 +72,6 @@ func parseUpdateArgs(args []string) (updateOptions, bool, error) {
 			return options, true, nil
 		case arg == "--check":
 			options.check = true
-		case arg == "--apply":
-			options.apply = true
 		case arg == "--json":
 			options.json = true
 		case arg == "--repo":
@@ -195,17 +155,14 @@ func parseUpdateTarget(value string) (string, error) {
 func writeUpdateHelp(w io.Writer) error {
 	_, err := fmt.Fprint(w, `Usage:
  zero update --check [flags]
-  zero update --apply [flags]
-  zero upgrade [flags]

 Flags:
      --check                 Check the latest GitHub release without installing
-      --apply                 Download, verify, and install the latest release
-      --json                  Print the update result as JSON
+      --json                  Print the update check result as JSON
      --repo <owner/repo>     Repository to check when no endpoint is provided
      --endpoint <url|repo>   Release API URL or owner/repo slug to check
      --timeout <duration>    Release check timeout (default 5s)
-      --target <platform>     Release target to verify with --check (for example windows-x64); not valid with --apply
+      --target <platform>     Release target to verify (for example windows-x64)
  -h, --help                  Show this help
 `)
 	return err
@@ -662,144 +662,3 @@ func TestRunExecRejectsWorktreeDirWithoutWorktree(t *testing.T) {
 		t.Fatalf("expected empty stdout, got %q", stdout.String())
 	}
 }
-
-func TestParseChangesArgsAuto(t *testing.T) {
-	// 1. Correct parsing of auto
-	for _, args := range [][]string{
-		{"--auto"},
-		{"-a"},
-	} {
-		options, help, err := parseChangesArgs(args, "commit")
-		if err != nil {
-			t.Fatalf("parseChangesArgs(%v) error: %v", args, err)
-		}
-		if help {
-			t.Fatalf("parseChangesArgs(%v) returned help", args)
-		}
-		if !options.auto {
-			t.Fatalf("auto = false, want true (args %v)", args)
-		}
-	}
-
-	// 2. Reject --auto on inspect
-	_, _, err := parseChangesArgs([]string{"--auto"}, "inspect")
-	if err == nil || !strings.Contains(err.Error(), "--auto") {
-		t.Fatalf("expected --auto rejection on inspect, got %v", err)
-	}
-
-	// 3. Reject both --message and --auto on commit
-	_, _, err = parseChangesArgs([]string{"--message", "foo", "--auto"}, "commit")
-	if err == nil || !strings.Contains(err.Error(), "cannot specify both --message and --auto") {
-		t.Fatalf("expected --message and --auto conflict error, got %v", err)
-	}
-
-	// 4. Reject both empty message and --auto on commit
-	_, _, err = parseChangesArgs([]string{"--message=", "--auto"}, "commit")
-	if err == nil || !strings.Contains(err.Error(), "cannot specify both --message and --auto") {
-		t.Fatalf("expected empty --message and --auto conflict error, got %v", err)
-	}
-}
-
-type mockCommitMsgProvider struct {
-	response string
-	req      zeroruntime.CompletionRequest
-}
-
-func (p *mockCommitMsgProvider) StreamCompletion(ctx context.Context, request zeroruntime.CompletionRequest) (<-chan zeroruntime.StreamEvent, error) {
-	p.req = request
-	events := make(chan zeroruntime.StreamEvent, 2)
-	events <- zeroruntime.StreamEvent{Type: zeroruntime.StreamEventText, Content: p.response}
-	events <- zeroruntime.StreamEvent{Type: zeroruntime.StreamEventDone}
-	close(events)
-	return events, nil
-}
-
-func TestRunChangesCommitAuto(t *testing.T) {
-	cwd := t.TempDir()
-	summary := zerogit.ChangeSummary{
-		Root:   cwd,
-		Branch: "main",
-		Files:  []zerogit.FileChange{{Path: "README.md", Status: "modified"}},
-		Diff:   "some diff content with ghp_SECRETKEYHERE",
-	}
-
-	mockProv := &mockCommitMsgProvider{
-		response: "```\nfeat: auto commit message\n```",
-	}
-
-	var stdout bytes.Buffer
-	var stderr bytes.Buffer
-	commitCalled := false
-
-	exitCode := runWithDeps([]string{"changes", "commit", "--auto"}, &stdout, &stderr, appDeps{
-		getwd: func() (string, error) { return cwd, nil },
-		inspectChanges: func(ctx context.Context, options zerogit.InspectOptions) (zerogit.ChangeSummary, error) {
-			return summary, nil
-		},
-		resolveConfig: func(workspaceRoot string, overrides config.Overrides) (config.ResolvedConfig, error) {
-			cfg := execResolvedConfig()
-			cfg.Provider.Name = "openai"
-			cfg.Provider.Model = "gpt-4o"
-			return cfg, nil
-		},
-		newProvider: func(profile config.ProviderProfile) (zeroruntime.Provider, error) {
-			return mockProv, nil
-		},
-		commitChanges: func(ctx context.Context, options zerogit.CommitOptions) (zerogit.CommitResult, error) {
-			commitCalled = true
-			if options.Message != "feat: auto commit message" {
-				t.Fatalf("expected commit message 'feat: auto commit message', got %q", options.Message)
-			}
-			return zerogit.CommitResult{
-				Root:       cwd,
-				Message:    options.Message,
-				Committed:  true,
-				CommitHash: "abc1234",
-				Before:     summary,
-			}, nil
-		},
-	})
-
-	if exitCode != exitSuccess {
-		t.Fatalf("expected exit code %d, got %d: %s", exitSuccess, exitCode, stderr.String())
-	}
-	if !commitCalled {
-		t.Fatal("expected commitChanges to be called")
-	}
-	// Verify that secret in the diff was redacted
-	promptContent := mockProv.req.Messages[0].Content
-	if strings.Contains(promptContent, "ghp_SECRETKEYHERE") {
-		t.Fatal("expected secret in diff to be redacted, but it was found in the prompt")
-	}
-	if !strings.Contains(promptContent, "[REDACTED]") && !strings.Contains(promptContent, "REDACTED") {
-		t.Fatalf("expected redacted diff content in prompt, got: %q", promptContent)
-	}
-	if !strings.Contains(stdout.String(), "Generating commit message using LLM...") {
-		t.Fatalf("expected status message in stdout, got %q", stdout.String())
-	}
-
-	t.Run("EmptyLLMResponse", func(t *testing.T) {
-		mockProvEmpty := &mockCommitMsgProvider{
-			response: "   \n\n   ",
-		}
-		var stdout, stderr bytes.Buffer
-		code := runWithDeps([]string{"changes", "commit", "--auto"}, &stdout, &stderr, appDeps{
-			getwd: func() (string, error) { return cwd, nil },
-			inspectChanges: func(ctx context.Context, options zerogit.InspectOptions) (zerogit.ChangeSummary, error) {
-				return summary, nil
-			},
-			resolveConfig: func(workspaceRoot string, overrides config.Overrides) (config.ResolvedConfig, error) {
-				return execResolvedConfig(), nil
-			},
-			newProvider: func(profile config.ProviderProfile) (zeroruntime.Provider, error) {
-				return mockProvEmpty, nil
-			},
-		})
-		if code == exitSuccess {
-			t.Fatal("expected command to fail when LLM returns empty response, got success")
-		}
-		if !strings.Contains(stderr.String(), "empty commit message") {
-			t.Fatalf("expected empty commit message error in stderr, got %q", stderr.String())
-		}
-	})
-}
@@ -6,16 +6,13 @@ import (
 	"io"
 	"strconv"
 	"strings"
-	"time"

-	"github.com/Gitlawb/zero/internal/config"
 	"github.com/Gitlawb/zero/internal/redaction"
 	"github.com/Gitlawb/zero/internal/selfverify"
 	"github.com/Gitlawb/zero/internal/testrunner"
 	"github.com/Gitlawb/zero/internal/verify"
 	"github.com/Gitlawb/zero/internal/worktrees"
 	"github.com/Gitlawb/zero/internal/zerogit"
-	"github.com/Gitlawb/zero/internal/zeroruntime"
 )

 type worktreeCommandOptions struct {
@@ -38,10 +35,8 @@ type changesCommandOptions struct {
 	cwd          string
 	baseRef      string
 	message      string
-	hasMessage   bool
 	dryRun       bool
 	maxDiffBytes int
-	auto         bool
 }

 func runWorktrees(args []string, stdout io.Writer, stderr io.Writer, deps appDeps) int {
@@ -203,52 +198,9 @@ func runChanges(args []string, stdout io.Writer, stderr io.Writer, deps appDeps)
 		}
 		return exitSuccess
 	case "commit":
-		var message string
-		if options.auto {
-			summary, err := deps.inspectChanges(context.Background(), zerogit.InspectOptions{
-				Cwd:          workspaceRoot,
-				MaxDiffBytes: options.maxDiffBytes,
-			})
-			if err != nil {
-				return writeExecUsageError(stderr, fmt.Sprintf("failed to inspect changes: %v", err))
-			}
-			if summary.Clean {
-				return writeExecUsageError(stderr, "no changes to commit")
-			}
-
-			resolved, err := deps.resolveConfig(workspaceRoot, config.Overrides{})
-			if err != nil {
-				return writeExecUsageError(stderr, fmt.Sprintf("failed to resolve config: %v", err))
-			}
-			if !config.HasProviderProfile(resolved.Provider) {
-				return writeExecUsageError(stderr, "no provider configured for auto-commit message")
-			}
-			provider, err := deps.newProvider(resolved.Provider)
-			if err != nil {
-				return writeExecUsageError(stderr, fmt.Sprintf("failed to create provider: %v", err))
-			}
-
-			if !options.json {
-				if _, err := fmt.Fprintln(stdout, "Generating commit message using LLM..."); err != nil {
-					return exitCrash
-				}
-			}
-
-			safeSummary := redactChangeSummary(summary)
-			genCtx, cancel := context.WithTimeout(context.Background(), 60*time.Second)
-			defer cancel()
-			msg, err := generateAutoCommitMessage(genCtx, provider, resolved.Provider.Model, safeSummary)
-			if err != nil {
-				return writeExecUsageError(stderr, fmt.Sprintf("failed to generate commit message: %v", err))
-			}
-			message = msg
-		} else {
-			message = options.message
-		}
-
 		result, err := deps.commitChanges(context.Background(), zerogit.CommitOptions{
 			Cwd:          workspaceRoot,
-			Message:      message,
+			Message:      options.message,
 			DryRun:       options.dryRun,
 			MaxDiffBytes: options.maxDiffBytes,
 		})
@@ -443,11 +395,9 @@ func parseChangesArgs(args []string, command string) (changesCommandOptions, boo
 				return options, false, err
 			}
 			options.message = value
-			options.hasMessage = true
 			index = next
 		case strings.HasPrefix(arg, "--message="):
 			options.message = strings.TrimSpace(strings.TrimPrefix(arg, "--message="))
-			options.hasMessage = true
 		case arg == "--diff-bytes":
 			value, next, err := nextFlagValue(args, index, arg)
 			if err != nil {
@@ -465,19 +415,14 @@ func parseChangesArgs(args []string, command string) (changesCommandOptions, boo
 				return options, false, err
 			}
 			options.maxDiffBytes = maxDiffBytes
-		case arg == "-a" || arg == "--auto":
-			options.auto = true
 		case strings.HasPrefix(arg, "-"):
 			return options, false, execUsageError{fmt.Sprintf("unknown changes flag %q", arg)}
 		default:
 			return options, false, execUsageError{fmt.Sprintf("unexpected changes argument %q", arg)}
 		}
 	}
-	if command != "commit" && (options.hasMessage || options.dryRun || options.auto) {
-		return options, false, execUsageError{"--message, --dry-run, and --auto are only valid with `zero changes commit`"}
-	}
-	if command == "commit" && options.hasMessage && options.auto {
-		return options, false, execUsageError{"cannot specify both --message and --auto"}
+	if command != "commit" && (options.message != "" || options.dryRun) {
+		return options, false, execUsageError{"--message and --dry-run are only valid with `zero changes commit`"}
 	}
 	if command == "commit" && options.baseRef != "" {
 		return options, false, execUsageError{"--base is only valid with `zero changes inspect`"}
@@ -767,47 +712,9 @@ Flags:
      --base <ref>        Diff against <ref>...HEAD instead of the working tree
      --diff-bytes <n>    Maximum diff bytes to include
  -m, --message <text>    Commit message for `+"`zero changes commit`"+`
-  -a, --auto              Auto-generate commit message using LLM (use --dry-run to preview)
      --dry-run           Preview commit metadata without mutating git state
      --json              Print JSON output
  -h, --help              Show this help
 `)
 	return err
 }
-
-func generateAutoCommitMessage(ctx context.Context, provider zeroruntime.Provider, model string, summary zerogit.ChangeSummary) (string, error) {
-	var promptBuilder strings.Builder
-	promptBuilder.WriteString("Analyze the following git diff and generate a concise, conventional commit message.\n")
-	promptBuilder.WriteString("The commit message subject line must be 72 characters or fewer, starting with a conventional commit type (e.g., feat, fix, docs, style, refactor, test, chore) followed by a colon and space, and a lowercase description.\n")
-	promptBuilder.WriteString("You may optionally include a blank line and a bulleted list of changes for the body if there are multiple files or complex changes.\n")
-	promptBuilder.WriteString("Output ONLY the raw commit message text. Do not wrap the message in markdown code block fence, do not include quotes or any introduction/explanation.\n\n")
-	promptBuilder.WriteString("Git Diff:\n")
-	promptBuilder.WriteString(summary.Diff)
-
-	request := zeroruntime.CompletionRequest{
-		Messages: []zeroruntime.Message{
-			{Role: zeroruntime.MessageRoleUser, Content: promptBuilder.String()},
-		},
-	}
-	stream, err := provider.StreamCompletion(ctx, request)
-	if err != nil {
-		return "", err
-	}
-	collected := zeroruntime.CollectStream(ctx, stream)
-	if collected.Error != "" {
-		return "", fmt.Errorf("%s", collected.Error)
-	}
-
-	msg := strings.TrimSpace(collected.Text)
-	if strings.HasPrefix(msg, "```") {
-		if idx := strings.Index(msg, "\n"); idx != -1 {
-			msg = msg[idx+1:]
-		}
-	}
-	msg = strings.TrimSuffix(msg, "```")
-	msg = strings.TrimSpace(msg)
-	if msg == "" {
-		return "", fmt.Errorf("provider returned empty commit message")
-	}
-	return msg, nil
-}
@@ -130,11 +130,7 @@ func Resolve(options ResolveOptions) (ResolvedConfig, error) {

 	providers, active, err := normalizeProviders(cfg.Providers, cfg.ActiveProvider, options.Env)
 	if err != nil {
-		// On ErrNoActiveProvider, providers may still hold the successfully
-		// normalized (but active-less) profile list — keep it so a caller can fall
-		// back to an already-configured usable provider instead of treating this
-		// like a config with nothing set up at all.
-		return ResolvedConfig{Providers: providers}, err
+		return ResolvedConfig{}, err
 	}

 	return ResolvedConfig{
@@ -148,7 +144,6 @@ func Resolve(options ResolveOptions) (ResolvedConfig, error) {
 		Tools:          cfg.Tools,
 		Swarm:          cfg.Swarm,
 		Preferences:    cfg.Preferences,
-		KeyBindings:    cfg.KeyBindings,
 		LocalControl:   cfg.LocalControl,
 	}, nil
 }
@@ -230,7 +225,6 @@ func mergeConfig(dst *FileConfig, src FileConfig) {
 		dst.Preferences.Theme = strings.TrimSpace(src.Preferences.Theme)
 	}
 	mergeLocalControlConfig(&dst.LocalControl, src.LocalControl)
-	mergeKeyBindings(&dst.KeyBindings, src.KeyBindings)
 }

 func mergeProjectConfig(dst *FileConfig, src FileConfig) error {
@@ -252,17 +246,8 @@ func mergeProjectConfig(dst *FileConfig, src FileConfig) error {
 	// config: a cloned repo's .zero/config.json must not be able to grant
 	// itself write access outside the workspace. Global config and CLI flags
 	// are the only config sources for write roots.
-	//
-	// Sandbox.Network from project config may only TIGHTEN (→ "deny"), never
-	// WEAKEN (→ "allow"). A malicious repo must not be able to open network
-	// access for shell commands. Matches the AdditionalWriteRoots posture.
 	if network := strings.TrimSpace(src.Sandbox.Network); network != "" {
-		// Normalize: anything that isn't literally "allow" counts as deny.
-		if sandbox.NormalizeNetworkMode(sandbox.NetworkMode(network)) != sandbox.NetworkAllow {
-			dst.Sandbox.Network = network
-		}
-		// Silently ignore "allow" from project config — not an error, just
-		// a privilege the project scope does not have.
+		dst.Sandbox.Network = network
 	}
 	if src.Sandbox.BlockUnixSockets {
 		dst.Sandbox.BlockUnixSockets = true
@@ -283,7 +268,6 @@ func mergeProjectConfig(dst *FileConfig, src FileConfig) error {
 	if src.Swarm.MaxTeamSize != 0 {
 		dst.Swarm.MaxTeamSize = src.Swarm.MaxTeamSize
 	}
-	mergeKeyBindings(&dst.KeyBindings, src.KeyBindings)
 	// Local control is intentionally user-config/override only. A cloned project
 	// must not be able to make browser, desktop, or terminal automation tools
 	// appear in the model's tool surface.
@@ -590,17 +574,9 @@ func applyProviderEnv(cfg *FileConfig, providerKind ProviderKind, env envProfile
 	if profile.Name == "" {
 		profile.Name = string(providerKind)
 	}
-	// A non-official baseURL from the environment signals a proxy/gateway, so promote
-	// the first-party kind to its -compatible transport (which accepts a custom URL).
-	// Env-only by design: a custom baseURL in a project config.json is left as-is and
-	// rejected by Resolve, so an untrusted project can't redirect a first-party key to
-	// another host.
 	if providerKind == ProviderKindOpenAI && baseURL != "" && !isOfficialOpenAIBaseURL(baseURL) {
 		profile.ProviderKind = ProviderKindOpenAICompatible
 	}
-	if providerKind == ProviderKindAnthropic && baseURL != "" && !isOfficialAnthropicBaseURL(baseURL) {
-		profile.ProviderKind = ProviderKindAnthropicCompat
-	}
 	// When the env supplies only credentials (no baseURL) for a provider name that
 	// already exists, don't force the standard transport kind — a same-named
 	// openai-compatible/anthropic-compatible proxy or gateway must keep its kind.
@@ -680,7 +656,6 @@ func applyOverrides(cfg *FileConfig, overrides Overrides) {
 		cfg.Tools.deferThresholdSet = true
 	}
 	mergeLocalControlConfig(&cfg.LocalControl, overrides.LocalControl)
-	mergeKeyBindings(&cfg.KeyBindings, overrides.KeyBindings)
 	for _, provider := range overrides.Providers {
 		mergeProvider(cfg, provider)
 	}
@@ -716,24 +691,6 @@ func mergeLocalControlDriverConfig(dst *LocalControlDriverConfig, src LocalContr
 	}
 }

-func mergeKeyBindings(dst *KeyBindingsConfig, src KeyBindingsConfig) {
-	if src.ToggleDetailed != "" {
-		dst.ToggleDetailed = src.ToggleDetailed
-	}
-	if src.ToggleMouse != "" {
-		dst.ToggleMouse = src.ToggleMouse
-	}
-	if src.CycleReasoning != "" {
-		dst.CycleReasoning = src.CycleReasoning
-	}
-	if src.TogglePlan != "" {
-		dst.TogglePlan = src.TogglePlan
-	}
-	if src.ToggleSidebar != "" {
-		dst.ToggleSidebar = src.ToggleSidebar
-	}
-}
-
 func mergeMCPConfig(dst *MCPConfig, src MCPConfig) {
 	if len(src.Servers) == 0 {
 		return
@@ -868,11 +825,7 @@ func normalizeProvidersWithOptions(providers []ProviderProfile, activeName strin
 	}

 	if !activeFound {
-		// Return the successfully normalized list alongside the error (rather than
-		// nil) so a caller like the interactive TUI can still fall back to an
-		// already-configured, usable provider instead of forcing a full
-		// re-onboarding wizard just because none was marked active.
-		return normalized, ProviderProfile{}, fmt.Errorf("%w: active provider %q not found", ErrNoActiveProvider, activeName)
+		return nil, ProviderProfile{}, fmt.Errorf("%w: active provider %q not found", ErrNoActiveProvider, activeName)
 	}
 	if active.Model == "" {
 		return nil, ProviderProfile{}, &setupFixableError{
@@ -617,35 +617,6 @@ func TestResolveUsesOpenAIEnvFallback(t *testing.T) {
 	}
 }

-func TestResolveUsesAnthropicEnvBaseURLAsCompatible(t *testing.T) {
-	// ANTHROPIC_BASE_URL pointing at a proxy/gateway must resolve to an
-	// anthropic-compatible provider (mirroring OPENAI_BASE_URL), not the "requires
-	// official baseURL" rejection — issue #479. The env is user-controlled, so a
-	// custom URL there is a deliberate gateway choice, unlike a project config.json.
-	resolved, err := Resolve(ResolveOptions{
-		Env: map[string]string{
-			"ANTHROPIC_API_KEY":  "sk-ant-env",
-			"ANTHROPIC_BASE_URL": "https://gateway.example/anthropic",
-			"ANTHROPIC_MODEL":    "claude-custom",
-		},
-	})
-	if err != nil {
-		t.Fatalf("Resolve() error = %v", err)
-	}
-	if resolved.ActiveProvider != "anthropic" {
-		t.Fatalf("ActiveProvider = %q, want anthropic", resolved.ActiveProvider)
-	}
-	if resolved.Provider.ProviderKind != ProviderKindAnthropicCompat {
-		t.Fatalf("ProviderKind = %q, want anthropic-compatible", resolved.Provider.ProviderKind)
-	}
-	if resolved.Provider.BaseURL != "https://gateway.example/anthropic" {
-		t.Fatalf("BaseURL = %q, want gateway URL", resolved.Provider.BaseURL)
-	}
-	if resolved.Provider.APIKey != "sk-ant-env" || resolved.Provider.Model != "claude-custom" {
-		t.Fatalf("Provider = %#v, want env credentials/model", resolved.Provider)
-	}
-}
-
 func TestResolveUsesOpenAIAPIKeyOnlyWithDefaultModel(t *testing.T) {
 	resolved, err := Resolve(ResolveOptions{
 		Env: map[string]string{
@@ -945,25 +916,6 @@ func TestResolveRejectsActiveProviderWithoutConfiguredProfiles(t *testing.T) {
 	}
 }

-func TestResolveKeepsNormalizedProvidersWhenNoneMarkedActive(t *testing.T) {
-	// Multiple providers configured (e.g. via `zero provider add`) but
-	// activeProvider is blank/stale — a caller like the interactive TUI still
-	// needs the normalized list to fall back to an already-usable provider
-	// instead of forcing a full re-onboarding wizard.
-	path := writeConfig(t, `{"providers":[
-		{"name":"work","provider_kind":"openai","apiKey":"sk-test","model":"gpt-test"},
-		{"name":"other","provider_kind":"openai","apiKey":"sk-other","model":"gpt-test"}
-	]}`)
-
-	resolved, err := Resolve(ResolveOptions{ProjectConfigPath: path, Env: map[string]string{}})
-	if !errors.Is(err, ErrNoActiveProvider) {
-		t.Fatalf("error = %v, want errors.Is(err, ErrNoActiveProvider)", err)
-	}
-	if len(resolved.Providers) != 2 {
-		t.Fatalf("Providers = %#v, want the 2 normalized profiles preserved despite the error", resolved.Providers)
-	}
-}
-
 func TestResolveTrimsProviderProfileAliasesBeforeFallback(t *testing.T) {
 	path := writeConfig(t, `{
 		"activeProvider": "custom",
@@ -1107,130 +1059,6 @@ func TestResolveAppliesProviderCatalogDefaults(t *testing.T) {
 	}
 }

-func TestResolveAppliesMiniMaxCNCatalogDefaults(t *testing.T) {
-	path := writeConfig(t, `{
-		"activeProvider": "mini-cn",
-		"providers": [{
-			"name": "mini-cn",
-			"catalog_id": "minimaxi-cn"
-		}]
-	}`)
-
-	resolved, err := Resolve(ResolveOptions{
-		ProjectConfigPath: path,
-		Env: map[string]string{
-			"MINIMAXI_API_KEY": "sk-cn-mini",
-		},
-	})
-	if err != nil {
-		t.Fatalf("Resolve() error = %v", err)
-	}
-
-	if resolved.Provider.CatalogID != "minimaxi-cn" {
-		t.Fatalf("CatalogID = %q, want minimaxi-cn", resolved.Provider.CatalogID)
-	}
-	if resolved.Provider.ProviderKind != ProviderKindAnthropicCompat {
-		t.Fatalf("ProviderKind = %q, want %q", resolved.Provider.ProviderKind, ProviderKindAnthropicCompat)
-	}
-	if resolved.Provider.BaseURL != "https://api.minimaxi.com/anthropic" {
-		t.Fatalf("BaseURL = %q, want MiniMax CN default", resolved.Provider.BaseURL)
-	}
-	if resolved.Provider.Model != "MiniMax-M3" {
-		t.Fatalf("Model = %q, want MiniMax-M3", resolved.Provider.Model)
-	}
-	if resolved.Provider.APIKeyEnv != "MINIMAXI_API_KEY" {
-		t.Fatalf("APIKeyEnv = %q, want MINIMAXI_API_KEY", resolved.Provider.APIKeyEnv)
-	}
-	if resolved.Provider.APIKey != "sk-cn-mini" {
-		t.Fatalf("APIKey = %q, want env-resolved secret", resolved.Provider.APIKey)
-	}
-}
-
-func TestResolveAppliesZaiCNCatalogDefaults(t *testing.T) {
-	// The "zai-cn" catalog entry preserves the legacy open.bigmodel.cn endpoint
-	// for users who still target the China hosting; "zai" itself now points at
-	// api.z.ai (international). The two env-vars are intentionally distinct
-	// (ZHIPU_API_KEY for China, ZAI_API_KEY for international) so an account on
-	// one side cannot be silently used against the other.
-	path := writeConfig(t, `{
-		"activeProvider": "zai-cn",
-		"providers": [{
-			"name": "zai-cn",
-			"catalog_id": "zai-cn"
-		}]
-	}`)
-
-	resolved, err := Resolve(ResolveOptions{
-		ProjectConfigPath: path,
-		Env: map[string]string{
-			"ZHIPU_API_KEY": "sk-zhipu-cn",
-		},
-	})
-	if err != nil {
-		t.Fatalf("Resolve() error = %v", err)
-	}
-
-	if resolved.Provider.CatalogID != "zai-cn" {
-		t.Fatalf("CatalogID = %q, want zai-cn", resolved.Provider.CatalogID)
-	}
-	if resolved.Provider.ProviderKind != ProviderKindOpenAICompatible {
-		t.Fatalf("ProviderKind = %q, want %q", resolved.Provider.ProviderKind, ProviderKindOpenAICompatible)
-	}
-	if resolved.Provider.BaseURL != "https://open.bigmodel.cn/api/paas/v4" {
-		t.Fatalf("BaseURL = %q, want Z.ai China default", resolved.Provider.BaseURL)
-	}
-	if resolved.Provider.Model != "glm-4.5" {
-		t.Fatalf("Model = %q, want glm-4.5 (China default)", resolved.Provider.Model)
-	}
-	if resolved.Provider.APIKeyEnv != "ZHIPU_API_KEY" {
-		t.Fatalf("APIKeyEnv = %q, want ZHIPU_API_KEY", resolved.Provider.APIKeyEnv)
-	}
-	if resolved.Provider.APIKey != "sk-zhipu-cn" {
-		t.Fatalf("APIKey = %q, want env-resolved secret", resolved.Provider.APIKey)
-	}
-}
-
-func TestResolveAppliesZaiInternationalCatalogDefaults(t *testing.T) {
-	// "zai" now resolves to the international endpoint; the catalog default
-	// model stays glm-4.5 (live discovery upgrades to glm-5.2 at runtime).
-	path := writeConfig(t, `{
-		"activeProvider": "zai-intl",
-		"providers": [{
-			"name": "zai-intl",
-			"catalog_id": "zai"
-		}]
-	}`)
-
-	resolved, err := Resolve(ResolveOptions{
-		ProjectConfigPath: path,
-		Env: map[string]string{
-			"ZAI_API_KEY": "sk-zai-intl",
-		},
-	})
-	if err != nil {
-		t.Fatalf("Resolve() error = %v", err)
-	}
-
-	if resolved.Provider.CatalogID != "zai" {
-		t.Fatalf("CatalogID = %q, want zai", resolved.Provider.CatalogID)
-	}
-	if resolved.Provider.ProviderKind != ProviderKindOpenAICompatible {
-		t.Fatalf("ProviderKind = %q, want %q", resolved.Provider.ProviderKind, ProviderKindOpenAICompatible)
-	}
-	if resolved.Provider.BaseURL != "https://api.z.ai/api/paas/v4" {
-		t.Fatalf("BaseURL = %q, want Z.ai international default", resolved.Provider.BaseURL)
-	}
-	if resolved.Provider.Model != "glm-4.5" {
-		t.Fatalf("Model = %q, want glm-4.5 (preserved default; live discovery upgrades to glm-5.2 at runtime)", resolved.Provider.Model)
-	}
-	if resolved.Provider.APIKeyEnv != "ZAI_API_KEY" {
-		t.Fatalf("APIKeyEnv = %q, want ZAI_API_KEY", resolved.Provider.APIKeyEnv)
-	}
-	if resolved.Provider.APIKey != "sk-zai-intl" {
-		t.Fatalf("APIKey = %q, want env-resolved secret", resolved.Provider.APIKey)
-	}
-}
-
 func TestResolveProviderCatalogAliasAndLocalNoAuth(t *testing.T) {
 	path := writeConfig(t, `{
 		"activeProvider": "local",
@@ -1445,45 +1273,6 @@ func TestResolveSandboxBlockUnixSocketsFromFile(t *testing.T) {
 	}
 }

-func TestResolveSandboxNetworkProjectConfigCannotWeaken(t *testing.T) {
-	// 1. Project config tries to set network to "allow" (should be ignored).
-	userPath := writeConfig(t, `{}`)
-	projectPath := writeConfig(t, `{
-		"sandbox": {"network": "allow"}
-	}`)
-
-	resolved, err := Resolve(ResolveOptions{
-		UserConfigPath:    userPath,
-		ProjectConfigPath: projectPath,
-		Env:               map[string]string{},
-	})
-	if err != nil {
-		t.Fatalf("Resolve() error = %v", err)
-	}
-	if resolved.Sandbox.Network == "allow" {
-		t.Fatal("resolved.Sandbox.Network = allow, want empty/deny to prevent project config from weakening sandbox")
-	}
-
-	// 2. User config sets network to "allow", project config sets it to "deny" (tightening is allowed).
-	userPath2 := writeConfig(t, `{
-		"sandbox": {"network": "allow"}
-	}`)
-	projectPath2 := writeConfig(t, `{
-		"sandbox": {"network": "deny"}
-	}`)
-	resolved2, err := Resolve(ResolveOptions{
-		UserConfigPath:    userPath2,
-		ProjectConfigPath: projectPath2,
-		Env:               map[string]string{},
-	})
-	if err != nil {
-		t.Fatalf("Resolve() error = %v", err)
-	}
-	if resolved2.Sandbox.Network != "deny" {
-		t.Fatalf("resolved.Sandbox.Network = %q, want deny (project config allowed to tighten)", resolved2.Sandbox.Network)
-	}
-}
-
 func TestResolveNotifyValid(t *testing.T) {
 	path := writeConfig(t, `{"notify":{"mode":"both","focusMode":"always"}}`)
 	resolved, err := Resolve(ResolveOptions{UserConfigPath: path, Env: map[string]string{}})
@@ -112,25 +112,6 @@ func (p PreferencesConfig) RecapsEnabled() bool {
 	return p.Recaps == nil || *p.Recaps
 }

-// KeyBindingDef defines one key binding string (e.g. "ctrl+o") that the TUI
-// can remap. An empty string means "use the built-in default" for that action.
-type KeyBindingDef string
-
-// KeyBindingsConfig holds the subset of TUI keybindings that users may remap
-// via config.json. Each field defaults to a sensible built-in when empty.
-type KeyBindingsConfig struct {
-	// ToggleDetailed toggles the detailed transcript view (default: ctrl+o).
-	ToggleDetailed KeyBindingDef `json:"toggleDetailed,omitempty"`
-	// ToggleMouse toggles mouse capture release (default: ctrl+e).
-	ToggleMouse KeyBindingDef `json:"toggleMouse,omitempty"`
-	// CycleReasoning cycles through reasoning effort levels (default: ctrl+t).
-	CycleReasoning KeyBindingDef `json:"cycleReasoning,omitempty"`
-	// TogglePlan toggles the plan panel expansion (default: ctrl+p).
-	TogglePlan KeyBindingDef `json:"togglePlan,omitempty"`
-	// ToggleSidebar toggles the right context sidebar (default: ctrl+b).
-	ToggleSidebar KeyBindingDef `json:"toggleSidebar,omitempty"`
-}
-
 // LocalControlConfig controls local browser/desktop/terminal automation helpers.
 // Helpers are discovered lazily by the tool that needs them; no setup command or
 // background probe is required during startup.
@@ -225,7 +206,6 @@ type FileConfig struct {
 	Tools          ToolsConfig        `json:"tools,omitempty"`
 	Swarm          SwarmConfig        `json:"swarm,omitempty"`
 	Preferences    PreferencesConfig  `json:"preferences,omitempty"`
-	KeyBindings    KeyBindingsConfig  `json:"keybindings,omitempty"`
 	LocalControl   LocalControlConfig `json:"localControl,omitempty"`
 }

@@ -240,7 +220,6 @@ func (cfg FileConfig) MarshalJSON() ([]byte, error) {
 		Tools          ToolsConfig         `json:"tools,omitempty"`
 		Swarm          SwarmConfig         `json:"swarm,omitempty"`
 		Preferences    PreferencesConfig   `json:"preferences,omitempty"`
-		KeyBindings    KeyBindingsConfig   `json:"keybindings,omitempty"`
 		LocalControl   *LocalControlConfig `json:"localControl,omitempty"`
 	}
 	raw := rawConfig{
@@ -253,7 +232,6 @@ func (cfg FileConfig) MarshalJSON() ([]byte, error) {
 		Tools:          cfg.Tools,
 		Swarm:          cfg.Swarm,
 		Preferences:    cfg.Preferences,
-		KeyBindings:    cfg.KeyBindings,
 	}
 	if !cfg.LocalControl.Empty() {
 		raw.LocalControl = &cfg.LocalControl
@@ -278,7 +256,6 @@ type Overrides struct {
 	Sandbox        SandboxConfig
 	Notify         NotifyConfig
 	Tools          ToolsConfig
-	KeyBindings    KeyBindingsConfig
 	LocalControl   LocalControlConfig
 }

@@ -293,7 +270,6 @@ type ResolvedConfig struct {
 	Tools          ToolsConfig
 	Swarm          SwarmConfig
 	Preferences    PreferencesConfig
-	KeyBindings    KeyBindingsConfig
 	LocalControl   LocalControlConfig
 }

@@ -340,7 +316,6 @@ func (cfg *FileConfig) UnmarshalJSON(data []byte) error {
 		Tools           ToolsConfig                `json:"tools"`
 		Swarm           SwarmConfig                `json:"swarm"`
 		Preferences     PreferencesConfig          `json:"preferences"`
-		KeyBindings     KeyBindingsConfig          `json:"keybindings"`
 		LocalControl    LocalControlConfig         `json:"localControl"`
 		MCPServers      map[string]MCPServerConfig `json:"mcpServers"`
 		MCPServersSnake map[string]MCPServerConfig `json:"mcp_servers"`
@@ -367,7 +342,6 @@ func (cfg *FileConfig) UnmarshalJSON(data []byte) error {
 	cfg.Tools = raw.Tools
 	cfg.Swarm = raw.Swarm
 	cfg.Preferences = raw.Preferences
-	cfg.KeyBindings = raw.KeyBindings
 	cfg.LocalControl = raw.LocalControl
 	if cfg.MCP.Servers == nil && (len(raw.MCPServers) > 0 || len(raw.MCPServersSnake) > 0) {
 		cfg.MCP.Servers = map[string]MCPServerConfig{}
@@ -131,45 +131,29 @@ func doctorSandboxPolicy(cfg config.SandboxConfig) sandbox.Policy {
 // lspServersCheck reports which language servers ZERO would use are present on
 // PATH. Missing servers are not a failure — ZERO degrades to text-only edits for
 // those languages — so the worst status is WARN, and each missing server gets an
-// actionable install command keyed by its binary name. Only the tier-1 servers
-// (lsp.CoreServerBinaries) drive the status: the long-tail servers configured
-// for breadth are listed informationally under missingOptional, because warning
-// about a missing zls on a machine with no Zig code would be permanent noise.
+// actionable install command keyed by its binary name.
 func lspServersCheck(lookup func(string) (string, error)) Check {
 	if lookup == nil {
 		lookup = exec.LookPath
 	}
-	core := map[string]bool{}
-	for _, binary := range lsp.CoreServerBinaries() {
-		core[binary] = true
-	}
 	present := map[string]any{}
 	missing := map[string]any{}
-	missingOptional := map[string]any{}
 	for _, binary := range lsp.ServerBinaries() {
 		if _, err := lookup(binary); err == nil {
 			present[binary] = "on PATH"
 			continue
 		}
-		if core[binary] {
-			missing[binary] = lspRemedy(binary)
-		} else {
-			missingOptional[binary] = lspRemedy(binary)
-		}
-	}
-	details := map[string]any{"present": present}
-	if len(missingOptional) > 0 {
-		details["missingOptional"] = missingOptional
+		missing[binary] = lspRemedy(binary)
 	}
 	if len(missing) == 0 {
-		message := "All core language servers are available on PATH."
-		if len(missingOptional) > 0 {
-			message = fmt.Sprintf("All core language servers are available on PATH (%d optional server(s) not installed).", len(missingOptional))
-		}
-		return check("lsp.servers", "LSP servers", StatusPass, message, details)
+		return check("lsp.servers", "LSP servers", StatusPass, "All known language servers are available on PATH.", map[string]any{
+			"present": present,
+		})
 	}
-	details["missing"] = missing
-	return check("lsp.servers", "LSP servers", StatusWarn, fmt.Sprintf("%d language server(s) missing from PATH; affected files degrade to text-only edits.", len(missing)), details)
+	return check("lsp.servers", "LSP servers", StatusWarn, fmt.Sprintf("%d language server(s) missing from PATH; affected files degrade to text-only edits.", len(missing)), map[string]any{
+		"present": present,
+		"missing": missing,
+	})
 }

 // lspRemedy returns an actionable install command for a missing language-server
@@ -9,134 +9,26 @@ import (

 // serverCommands maps a file extension to the language-server command (argv) ZERO
 // will spawn. The first element is the binary looked up on PATH; missing binaries
-// are not an error, the agent just degrades to text-only for that file. Every
-// command is the language's community-standard server invoked in stdio mode, so
-// a wrong guess can never spawn something surprising — only fail the PATH check.
+// are not an error, the agent just degrades to text-only for that file.
 var serverCommands = map[string][]string{
-	".go":     {"gopls", "serve"},
-	".ts":     {"typescript-language-server", "--stdio"},
-	".tsx":    {"typescript-language-server", "--stdio"},
-	".mts":    {"typescript-language-server", "--stdio"},
-	".cts":    {"typescript-language-server", "--stdio"},
-	".js":     {"typescript-language-server", "--stdio"},
-	".jsx":    {"typescript-language-server", "--stdio"},
-	".mjs":    {"typescript-language-server", "--stdio"},
-	".cjs":    {"typescript-language-server", "--stdio"},
-	".py":     {"pyright-langserver", "--stdio"},
-	".pyi":    {"pyright-langserver", "--stdio"},
-	".rs":     {"rust-analyzer"},
-	".c":      {"clangd"},
-	".h":      {"clangd"},
-	".cpp":    {"clangd"},
-	".cc":     {"clangd"},
-	".cxx":    {"clangd"},
-	".hpp":    {"clangd"},
-	".java":   {"jdtls"},
-	".kt":     {"kotlin-language-server"},
-	".kts":    {"kotlin-language-server"},
-	".rb":     {"ruby-lsp"},
-	".php":    {"intelephense", "--stdio"},
-	".zig":    {"zls"},
-	".lua":    {"lua-language-server"},
-	".ex":     {"elixir-ls"},
-	".exs":    {"elixir-ls"},
-	".hs":     {"haskell-language-server-wrapper", "--lsp"},
-	".swift":  {"sourcekit-lsp"},
-	".ml":     {"ocamllsp"},
-	".mli":    {"ocamllsp"},
-	".scala":  {"metals"},
-	".clj":    {"clojure-lsp"},
-	".cljs":   {"clojure-lsp"},
-	".cljc":   {"clojure-lsp"},
-	".dart":   {"dart", "language-server"},
-	".gleam":  {"gleam", "lsp"},
-	".nix":    {"nixd"},
-	".tf":     {"terraform-ls", "serve"},
-	".sh":     {"bash-language-server", "start"},
-	".bash":   {"bash-language-server", "start"},
-	".yaml":   {"yaml-language-server", "--stdio"},
-	".yml":    {"yaml-language-server", "--stdio"},
-	".json":   {"vscode-json-language-server", "--stdio"},
-	".css":    {"vscode-css-language-server", "--stdio"},
-	".scss":   {"vscode-css-language-server", "--stdio"},
-	".less":   {"vscode-css-language-server", "--stdio"},
-	".html":   {"vscode-html-language-server", "--stdio"},
-	".svelte": {"svelteserver", "--stdio"},
-	".vue":    {"vue-language-server", "--stdio"},
-	".astro":  {"astro-ls", "--stdio"},
+	".go":  {"gopls", "serve"},
+	".ts":  {"typescript-language-server", "--stdio"},
+	".tsx": {"typescript-language-server", "--stdio"},
+	".js":  {"typescript-language-server", "--stdio"},
+	".jsx": {"typescript-language-server", "--stdio"},
+	".py":  {"pyright-langserver", "--stdio"},
+	".rs":  {"rust-analyzer"},
 }

 // languageIDs maps a file extension to the LSP languageId used in didOpen.
 var languageIDs = map[string]string{
-	".go":     "go",
-	".ts":     "typescript",
-	".tsx":    "typescriptreact",
-	".mts":    "typescript",
-	".cts":    "typescript",
-	".js":     "javascript",
-	".jsx":    "javascriptreact",
-	".mjs":    "javascript",
-	".cjs":    "javascript",
-	".py":     "python",
-	".pyi":    "python",
-	".rs":     "rust",
-	".c":      "c",
-	".h":      "c",
-	".cpp":    "cpp",
-	".cc":     "cpp",
-	".cxx":    "cpp",
-	".hpp":    "cpp",
-	".java":   "java",
-	".kt":     "kotlin",
-	".kts":    "kotlin",
-	".rb":     "ruby",
-	".php":    "php",
-	".zig":    "zig",
-	".lua":    "lua",
-	".ex":     "elixir",
-	".exs":    "elixir",
-	".hs":     "haskell",
-	".swift":  "swift",
-	".ml":     "ocaml",
-	".mli":    "ocaml",
-	".scala":  "scala",
-	".clj":    "clojure",
-	".cljs":   "clojure",
-	".cljc":   "clojure",
-	".dart":   "dart",
-	".gleam":  "gleam",
-	".nix":    "nix",
-	".tf":     "terraform",
-	".sh":     "shellscript",
-	".bash":   "shellscript",
-	".yaml":   "yaml",
-	".yml":    "yaml",
-	".json":   "json",
-	".css":    "css",
-	".scss":   "scss",
-	".less":   "less",
-	".html":   "html",
-	".svelte": "svelte",
-	".vue":    "vue",
-	".astro":  "astro",
-}
-
-// coreServerBinaries are the tier-1 servers for the languages agents hit most;
-// `zero doctor` treats their absence as warn-worthy. The long tail of servers
-// configured above for breadth is reported informationally only — warning about
-// a missing zls on a machine with no Zig code would be permanent noise.
-var coreServerBinaries = []string{
-	"gopls",
-	"typescript-language-server",
-	"pyright-langserver",
-	"rust-analyzer",
-}
-
-// CoreServerBinaries returns the tier-1 server binaries (sorted copy).
-func CoreServerBinaries() []string {
-	binaries := append([]string(nil), coreServerBinaries...)
-	sort.Strings(binaries)
-	return binaries
+	".go":  "go",
+	".ts":  "typescript",
+	".tsx": "typescriptreact",
+	".js":  "javascript",
+	".jsx": "javascriptreact",
+	".py":  "python",
+	".rs":  "rust",
 }

 // ServerBinaries returns the unique set of language-server binaries ZERO may
@@ -11,7 +11,6 @@ import (
 	"os"
 	"strings"
 	"sync"
-	"sync/atomic"
 	"testing"
 	"time"

@@ -212,85 +211,6 @@ func TestHTTPClientListsAndCallsTools(t *testing.T) {
 	}
 }

-func TestHTTPClientFollowsSameOriginRedirect(t *testing.T) {
-	ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
-	defer cancel()
-
-	testServer := httptest.NewServer(http.HandlerFunc(func(response http.ResponseWriter, request *http.Request) {
-		if request.URL.Path == "/mcp" {
-			http.Redirect(response, request, "/redirected", http.StatusTemporaryRedirect)
-			return
-		}
-		if request.Method != http.MethodPost || request.URL.Path != "/redirected" {
-			t.Errorf("request = %s %s, want POST /redirected", request.Method, request.URL.Path)
-			http.Error(response, "bad request", http.StatusNotFound)
-			return
-		}
-		if got := request.Header.Get("X-Api-Key"); got != "secret" {
-			t.Errorf("X-Api-Key = %q, want secret", got)
-			http.Error(response, "missing auth", http.StatusUnauthorized)
-			return
-		}
-
-		message := readHTTPRPCMessage(t, request)
-		switch message.Method {
-		case "initialize":
-			writeHTTPRPCResponse(t, response, message.ID, map[string]any{"protocolVersion": "2024-11-05"})
-		case "notifications/initialized":
-			response.WriteHeader(http.StatusAccepted)
-		default:
-			writeHTTPRPCResponse(t, response, message.ID, map[string]any{})
-		}
-	}))
-	defer testServer.Close()
-
-	client, err := Connect(ctx, Server{
-		Name:    "docs",
-		Type:    ServerTypeHTTP,
-		URL:     testServer.URL + "/mcp",
-		Headers: map[string]string{"X-Api-Key": "secret"},
-	})
-	if err != nil {
-		t.Fatalf("Connect() error = %v", err)
-	}
-	if err := client.Close(); err != nil {
-		t.Fatalf("Close() error = %v", err)
-	}
-}
-
-func TestHTTPClientRejectsCrossOriginRedirectBeforeSendingHeaders(t *testing.T) {
-	ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
-	defer cancel()
-
-	var targetHits int32
-	target := httptest.NewServer(http.HandlerFunc(func(response http.ResponseWriter, request *http.Request) {
-		atomic.AddInt32(&targetHits, 1)
-		if got := request.Header.Get("X-Api-Key"); got != "" {
-			t.Errorf("redirect target received X-Api-Key = %q", got)
-		}
-		response.WriteHeader(http.StatusOK)
-	}))
-	defer target.Close()
-
-	redirector := httptest.NewServer(http.HandlerFunc(func(response http.ResponseWriter, request *http.Request) {
-		http.Redirect(response, request, target.URL+"/mcp", http.StatusTemporaryRedirect)
-	}))
-	defer redirector.Close()
-
-	_, err := Connect(ctx, Server{
-		Name:    "docs",
-		Type:    ServerTypeHTTP,
-		URL:     redirector.URL + "/mcp",
-		Headers: map[string]string{"X-Api-Key": "secret"},
-	})
-	if err == nil || !strings.Contains(err.Error(), "cross-origin redirect") {
-		t.Fatalf("Connect() error = %v, want cross-origin redirect error", err)
-	}
-	if got := atomic.LoadInt32(&targetHits); got != 0 {
-		t.Fatalf("redirect target hits = %d, want 0", got)
-	}
-}
-
 func TestSSEClientListsAndCallsToolsFromRemoteStream(t *testing.T) {
 	ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
 	defer cancel()
@@ -420,53 +340,6 @@ func TestSSEClientListsAndCallsToolsFromRemoteStream(t *testing.T) {
 	}
 }

-func TestSSEClientRejectsCrossOriginEndpointBeforeSendingHeaders(t *testing.T) {
-	ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
-	defer cancel()
-
-	var targetHits int32
-	target := httptest.NewServer(http.HandlerFunc(func(response http.ResponseWriter, request *http.Request) {
-		atomic.AddInt32(&targetHits, 1)
-		if got := request.Header.Get("X-Api-Key"); got != "" {
-			t.Errorf("SSE endpoint target received X-Api-Key = %q", got)
-		}
-		response.WriteHeader(http.StatusAccepted)
-	}))
-	defer target.Close()
-
-	stream := httptest.NewServer(http.HandlerFunc(func(response http.ResponseWriter, request *http.Request) {
-		if got := request.Header.Get("X-Api-Key"); got != "secret" {
-			t.Errorf("X-Api-Key = %q, want secret on configured SSE server", got)
-			http.Error(response, "missing auth", http.StatusUnauthorized)
-			return
-		}
-		if request.Method != http.MethodGet || request.URL.Path != "/sse" {
-			t.Errorf("request = %s %s, want GET /sse", request.Method, request.URL.Path)
-			http.Error(response, "bad request", http.StatusNotFound)
-			return
-		}
-		response.Header().Set("Content-Type", "text/event-stream")
-		_, _ = fmt.Fprintf(response, "event: endpoint\ndata: %s/messages\n\n", target.URL)
-		if flusher, ok := response.(http.Flusher); ok {
-			flusher.Flush()
-		}
-	}))
-	defer stream.Close()
-
-	_, err := Connect(ctx, Server{
-		Name:    "docs",
-		Type:    ServerTypeSSE,
-		URL:     stream.URL + "/sse",
-		Headers: map[string]string{"X-Api-Key": "secret"},
-	})
-	if err == nil || !strings.Contains(err.Error(), "endpoint origin") {
-		t.Fatalf("Connect() error = %v, want cross-origin endpoint error", err)
-	}
-	if got := atomic.LoadInt32(&targetHits); got != 0 {
-		t.Fatalf("SSE endpoint target hits = %d, want 0", got)
-	}
-}
-
 func TestHTTPClientReportsNonOKStatus(t *testing.T) {
 	ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
 	defer cancel()
@@ -733,11 +733,7 @@ func resolveSSEEndpointURL(baseValue string, endpointValue string) (string, erro
 	if err != nil {
 		return "", fmt.Errorf("parse MCP SSE endpoint URL: %w", err)
 	}
-	resolvedURL := baseURL.ResolveReference(endpointURL)
-	if !sameMCPOrigin(baseURL, resolvedURL) {
-		return "", fmt.Errorf("MCP SSE endpoint origin %s differs from configured server origin %s", mcpOrigin(resolvedURL), mcpOrigin(baseURL))
-	}
-	return resolvedURL.String(), nil
+	return baseURL.ResolveReference(endpointURL).String(), nil
 }

 func rpcResponseKey(id any) string {
@@ -877,10 +873,10 @@ func (source *storeTokenSource) Refresh(ctx context.Context) (string, error) {

 // oauthHTTPClient returns an HTTP client whose transport attaches OAuth bearer
 // tokens and refreshes them on 401 for OAuth-configured servers. Servers that do
-// not declare OAuth use the default transport with the same MCP redirect guard.
+// not declare OAuth get the default client unchanged.
 func oauthHTTPClient(server Server) (*http.Client, error) {
 	if !strings.EqualFold(strings.TrimSpace(server.Auth), ServerAuthOAuth) {
-		return mcpHTTPClient(server, nil), nil
+		return http.DefaultClient, nil
 	}
 	store, err := NewTokenStore(TokenStoreOptions{})
 	if err != nil {
@@ -892,5 +888,5 @@ func oauthHTTPClient(server Server) (*http.Client, error) {
 		httpClient: http.DefaultClient,
 		now:        time.Now,
 	}
-	return mcpHTTPClient(server, newOAuthRoundTripper(http.DefaultTransport, source, server.Name)), nil
+	return &http.Client{Transport: newOAuthRoundTripper(http.DefaultTransport, source, server.Name)}, nil
 }
@@ -4,7 +4,6 @@ import (
 	"context"
 	"net/http"
 	"net/http/httptest"
-	"net/url"
 	"strings"
 	"sync/atomic"
 	"testing"
@@ -150,141 +149,6 @@ func TestOAuthRoundTripperDoesNotRetryAfterSuccessfulNon401(t *testing.T) {
 	}
 }

-func TestOAuthRoundTripperRejectsCrossOriginRedirectBeforeBearerLeak(t *testing.T) {
-	source := &fakeTokenSource{}
-	source.access.Store("access-secret")
-	source.refreshFunc = func() (string, error) { return "access-fresh", nil }
-
-	var targetHits int32
-	target := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
-		atomic.AddInt32(&targetHits, 1)
-		if got := r.Header.Get("Authorization"); got != "" {
-			t.Errorf("redirect target received Authorization = %q", got)
-		}
-		w.WriteHeader(http.StatusOK)
-	}))
-	defer target.Close()
-
-	redirector := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
-		http.Redirect(w, r, target.URL+"/mcp", http.StatusTemporaryRedirect)
-	}))
-	defer redirector.Close()
-
-	client := mcpHTTPClient(
-		Server{Name: "oauth-docs", Type: ServerTypeHTTP},
-		newOAuthRoundTripper(http.DefaultTransport, source, "oauth-docs"),
-	)
-	resp, err := client.Get(redirector.URL + "/mcp")
-	if resp != nil {
-		_ = resp.Body.Close()
-	}
-	if err == nil || !strings.Contains(err.Error(), "cross-origin redirect") {
-		t.Fatalf("Get() error = %v, want cross-origin redirect error", err)
-	}
-	if got := atomic.LoadInt32(&targetHits); got != 0 {
-		t.Fatalf("redirect target hits = %d, want 0", got)
-	}
-}
-
-func TestSameMCPOriginNormalizesDefaultPorts(t *testing.T) {
-	for _, tc := range []struct {
-		name  string
-		left  string
-		right string
-		want  bool
-	}{
-		{
-			name:  "https default port",
-			left:  "https://example.test/mcp",
-			right: "https://EXAMPLE.test:443/other",
-			want:  true,
-		},
-		{
-			name:  "http default port",
-			left:  "http://example.test/mcp",
-			right: "http://example.test:80/other",
-			want:  true,
-		},
-		{
-			name:  "different scheme",
-			left:  "https://example.test/mcp",
-			right: "http://example.test:443/other",
-			want:  false,
-		},
-		{
-			name:  "different port",
-			left:  "https://example.test/mcp",
-			right: "https://example.test:8443/other",
-			want:  false,
-		},
-	} {
-		t.Run(tc.name, func(t *testing.T) {
-			left, err := url.Parse(tc.left)
-			if err != nil {
-				t.Fatal(err)
-			}
-			right, err := url.Parse(tc.right)
-			if err != nil {
-				t.Fatal(err)
-			}
-			if got := sameMCPOrigin(left, right); got != tc.want {
-				t.Fatalf("sameMCPOrigin(%q, %q) = %v, want %v", tc.left, tc.right, got, tc.want)
-			}
-		})
-	}
-}
-
-func TestResolveSSEEndpointURLRestrictsOrigin(t *testing.T) {
-	for _, tc := range []struct {
-		name     string
-		base     string
-		endpoint string
-		want     string
-		wantErr  string
-	}{
-		{
-			name:     "relative endpoint",
-			base:     "https://example.test/sse",
-			endpoint: "/messages",
-			want:     "https://example.test/messages",
-		},
-		{
-			name:     "absolute same origin",
-			base:     "https://example.test/sse",
-			endpoint: "https://example.test/messages",
-			want:     "https://example.test/messages",
-		},
-		{
-			name:     "default port equivalent",
-			base:     "https://example.test/sse",
-			endpoint: "https://example.test:443/messages",
-			want:     "https://example.test:443/messages",
-		},
-		{
-			name:     "cross origin",
-			base:     "https://example.test/sse",
-			endpoint: "https://evil.test/messages",
-			wantErr:  "differs from configured server origin",
-		},
-	} {
-		t.Run(tc.name, func(t *testing.T) {
-			got, err := resolveSSEEndpointURL(tc.base, tc.endpoint)
-			if tc.wantErr != "" {
-				if err == nil || !strings.Contains(err.Error(), tc.wantErr) {
-					t.Fatalf("resolveSSEEndpointURL() error = %v, want %q", err, tc.wantErr)
-				}
-				return
-			}
-			if err != nil {
-				t.Fatalf("resolveSSEEndpointURL() error = %v", err)
-			}
-			if got != tc.want {
-				t.Fatalf("resolveSSEEndpointURL() = %q, want %q", got, tc.want)
-			}
-		})
-	}
-}
-
 func TestNonOAuthServerIsUnaffected(t *testing.T) {
 	// Regression: a server without auth must not get a bearer header or any
 	// OAuth round tripper, and must connect normally.
@@ -1,74 +0,0 @@
-package mcp
-
-import (
-	"fmt"
-	"net"
-	"net/http"
-	"net/url"
-	"strings"
-)
-
-const maxMCPRedirects = 10
-
-func mcpHTTPClient(server Server, transport http.RoundTripper) *http.Client {
-	return &http.Client{
-		Transport:     transport,
-		CheckRedirect: checkMCPRedirect(server),
-	}
-}
-
-func checkMCPRedirect(server Server) func(*http.Request, []*http.Request) error {
-	return func(request *http.Request, via []*http.Request) error {
-		if len(via) >= maxMCPRedirects {
-			return fmt.Errorf("MCP %s server %s stopped after %d redirects", server.Type, server.Name, maxMCPRedirects)
-		}
-		if len(via) == 0 {
-			return nil
-		}
-		if !sameMCPOrigin(via[0].URL, request.URL) {
-			return fmt.Errorf("MCP %s server %s refused cross-origin redirect to %s", server.Type, server.Name, mcpOrigin(request.URL))
-		}
-		return nil
-	}
-}
-
-func sameMCPOrigin(left *url.URL, right *url.URL) bool {
-	if left == nil || right == nil {
-		return false
-	}
-	return strings.EqualFold(left.Scheme, right.Scheme) &&
-		strings.EqualFold(left.Hostname(), right.Hostname()) &&
-		effectiveMCPPort(left) == effectiveMCPPort(right)
-}
-
-func effectiveMCPPort(value *url.URL) string {
-	if value == nil {
-		return ""
-	}
-	if port := value.Port(); port != "" {
-		return port
-	}
-	switch strings.ToLower(value.Scheme) {
-	case "http":
-		return "80"
-	case "https":
-		return "443"
-	default:
-		return ""
-	}
-}
-
-func mcpOrigin(value *url.URL) string {
-	if value == nil {
-		return "<nil>"
-	}
-	host := value.Hostname()
-	port := effectiveMCPPort(value)
-	if port != "" {
-		host = net.JoinHostPort(host, port)
-	}
-	if value.Scheme == "" {
-		return host
-	}
-	return strings.ToLower(value.Scheme) + "://" + host
-}
@@ -370,14 +370,7 @@ func TestFullFlowStoresTokens(t *testing.T) {
 		redirect := parsed.Query().Get("redirect_uri")
 		go func() {
 			cbURL := redirect + "?code=auth-code&state=" + url.QueryEscape(state)
-			for i := 0; i < 20; i++ {
-				resp, err := http.Get(cbURL)
-				if err == nil {
-					resp.Body.Close()
-					return
-				}
-				time.Sleep(50 * time.Millisecond)
-			}
+			_, _ = http.Get(cbURL)
 		}()
 		return nil
 	}
@@ -63,10 +63,6 @@ func DefaultModelEntries() []ModelEntry {
 		googleModel("gemini-2.5-flash-lite", "Gemini 2.5 Flash-Lite", "gemini-2.5-flash-lite", ModelStatusActive, []string{"google:gemini-2.5-flash-lite", "gemini-flash-lite"}, ContextLimits{ContextWindow: 1_048_576, MaxOutputTokens: 65_536}, ModelCost{InputPerMillion: 0.1, CachedInputPerMillion: 0.01, OutputPerMillion: 0.4}, []ModelCapability{ModelCapabilityVision, ModelCapabilityJSONMode, ModelCapabilityReasoning, ModelCapabilityLongContext}, standardReasoningEfforts(), "Google low-cost Flash model for background routing and summaries."),
 	}
 	decorateModelDepth(entries)
-	// Overlay volatile facts (context limits, base pricing) from a cached
-	// models.dev snapshot when one is present and fresh — see modelsdev.go.
-	// Identity fields (ids, aliases, patterns, deprecations) stay curated.
-	entries = applyModelsDevOverrides(entries, cachedModelsDevProviders())
 	return cloneModelEntries(entries)
 }

@@ -1,269 +0,0 @@
-package modelregistry
-
-import (
-	"context"
-	"encoding/json"
-	"fmt"
-	"io"
-	"net/http"
-	"os"
-	"path/filepath"
-	"strings"
-	"sync"
-	"sync/atomic"
-	"time"
-)
-
-// Live models.dev overlay for the curated catalog. The hand-maintained
-// DefaultModelEntries list is the source of truth for identity — ids, aliases,
-// match patterns, deprecations, escalation targets — but its VOLATILE facts
-// (context window, max output tokens, per-million pricing) go stale between
-// releases. When a cached snapshot of https://models.dev/api.json is present,
-// those fields are refreshed from it at registry construction; everything else
-// stays curated. The overlay never adds models (an auto-added entry would lack
-// aliases, match patterns, and provider wiring) and never touches the network
-// on the registry hot path — fetching happens only in the explicit background
-// refresh, cached to disk with a TTL.
-
-const (
-	modelsDevDefaultURL = "https://models.dev/api.json"
-	// modelsDevRefreshAfter is how old the cache may get before a background
-	// refresh re-fetches it.
-	modelsDevRefreshAfter = 24 * time.Hour
-	// modelsDevMaxAge is the oldest cache still applied as an overlay. Beyond
-	// this the curated catalog (updated with the binary) is likely fresher than
-	// the snapshot, so a stale file is ignored rather than trusted.
-	modelsDevMaxAge      = 7 * 24 * time.Hour
-	modelsDevFetchLimit  = 32 << 20 // 32MiB guard on the response body
-	modelsDevFetchWindow = 15 * time.Second
-)
-
-// modelsDevModel is the subset of a models.dev model record the overlay uses.
-type modelsDevModel struct {
-	Limit struct {
-		Context int `json:"context"`
-		Output  int `json:"output"`
-	} `json:"limit"`
-	Cost struct {
-		Input      float64 `json:"input"`
-		Output     float64 `json:"output"`
-		CacheRead  float64 `json:"cache_read"`
-		CacheWrite float64 `json:"cache_write"`
-	} `json:"cost"`
-}
-
-// modelsDevProvider matches one provider object in api.json.
-type modelsDevProvider struct {
-	Models map[string]modelsDevModel `json:"models"`
-}
-
-// parseModelsDev decodes an api.json document into provider-slug -> api-model
-// -> record. api.json is a top-level object keyed by provider id.
-func parseModelsDev(data []byte) (map[string]map[string]modelsDevModel, error) {
-	var doc map[string]modelsDevProvider
-	if err := json.Unmarshal(data, &doc); err != nil {
-		return nil, fmt.Errorf("modelregistry: parse models.dev: %w", err)
-	}
-	providers := make(map[string]map[string]modelsDevModel, len(doc))
-	for slug, provider := range doc {
-		if len(provider.Models) == 0 {
-			continue
-		}
-		providers[slug] = provider.Models
-	}
-	if len(providers) == 0 {
-		return nil, fmt.Errorf("modelregistry: models.dev document has no providers")
-	}
-	return providers, nil
-}
-
-// modelsDevSlugs maps an entry's provider kind to the models.dev provider ids
-// worth checking. Only first-party slugs are used: router entries on models.dev
-// carry generic or stale numbers.
-func modelsDevSlugs(kind ProviderKind) []string {
-	switch kind {
-	case ProviderAnthropic:
-		return []string{"anthropic"}
-	case ProviderOpenAI:
-		return []string{"openai"}
-	case ProviderGoogle:
-		return []string{"google", "google-vertex"}
-	default:
-		return nil
-	}
-}
-
-// applyModelsDevOverrides refreshes each curated entry's context limits and
-// base pricing from the snapshot, when the snapshot knows the model. Tiered
-// pricing is never touched: models.dev has no tier data, and mixing a live
-// base rate with curated tiers would misprice the tier boundaries.
-func applyModelsDevOverrides(entries []ModelEntry, providers map[string]map[string]modelsDevModel) []ModelEntry {
-	if len(providers) == 0 {
-		return entries
-	}
-	for i := range entries {
-		entry := &entries[i]
-		var record modelsDevModel
-		found := false
-		for _, slug := range modelsDevSlugs(entry.Provider) {
-			if models, ok := providers[slug]; ok {
-				if candidate, ok := models[strings.TrimSpace(entry.APIModel)]; ok {
-					record = candidate
-					found = true
-					break
-				}
-			}
-		}
-		if !found {
-			continue
-		}
-		if record.Limit.Context > 0 {
-			entry.ContextLimits.ContextWindow = record.Limit.Context
-		}
-		if record.Limit.Output > 0 {
-			entry.ContextLimits.MaxOutputTokens = record.Limit.Output
-		}
-		if len(entry.Cost.Tiers) == 0 && record.Cost.Input > 0 && record.Cost.Output > 0 {
-			entry.Cost.InputPerMillion = record.Cost.Input
-			entry.Cost.OutputPerMillion = record.Cost.Output
-			if record.Cost.CacheRead > 0 {
-				entry.Cost.CachedInputPerMillion = record.Cost.CacheRead
-			}
-			if record.Cost.CacheWrite > 0 {
-				entry.Cost.CacheWritePerMillion = record.Cost.CacheWrite
-			}
-			entry.Cost.Source = "models.dev/api.json (cached)"
-		}
-	}
-	return entries
-}
-
-// modelsDevCachePath returns the on-disk cache location. ZERO_MODELS_CACHE_PATH
-// overrides it (used by tests and unusual setups).
-func modelsDevCachePath() (string, error) {
-	if override := strings.TrimSpace(os.Getenv("ZERO_MODELS_CACHE_PATH")); override != "" {
-		return override, nil
-	}
-	base, err := os.UserCacheDir()
-	if err != nil {
-		return "", err
-	}
-	return filepath.Join(base, "zero", "modelsdev.json"), nil
-}
-
-var (
-	modelsDevOnce    sync.Once
-	modelsDevCached  map[string]map[string]modelsDevModel
-	modelsDevEnabled atomic.Bool
-)
-
-// EnableModelsDevOverlay opts the process into applying the cached models.dev
-// snapshot on top of the curated catalog. The CLI entrypoint calls it; library
-// consumers and tests that never do get the curated catalog byte-identical to
-// before, so hermetic tests can't be perturbed by a cache file on the machine.
-// ZERO_DISABLE_MODELS_FETCH disables both the overlay and the fetch.
-func EnableModelsDevOverlay() {
-	modelsDevEnabled.Store(true)
-}
-
-// cachedModelsDevProviders loads the cached snapshot once per process. Not
-// enabled, missing, stale (> modelsDevMaxAge), or malformed all yield nil and
-// the curated catalog is used untouched. Read once deliberately:
-// DefaultRegistry is called on hot paths (pickers, cost views) and must not
-// re-stat the file every time; a background refresh benefits the NEXT process.
-func cachedModelsDevProviders() map[string]map[string]modelsDevModel {
-	if !modelsDevEnabled.Load() || strings.TrimSpace(os.Getenv("ZERO_DISABLE_MODELS_FETCH")) != "" {
-		return nil
-	}
-	modelsDevOnce.Do(func() {
-		path, err := modelsDevCachePath()
-		if err != nil {
-			return
-		}
-		info, err := os.Stat(path)
-		if err != nil || time.Since(info.ModTime()) > modelsDevMaxAge {
-			return
-		}
-		data, err := os.ReadFile(path)
-		if err != nil {
-			return
-		}
-		providers, err := parseModelsDev(data)
-		if err != nil {
-			return
-		}
-		modelsDevCached = providers
-	})
-	return modelsDevCached
-}
-
-// resetModelsDevCacheForTest clears the process-level cache memoization and
-// disables the overlay.
-func resetModelsDevCacheForTest() {
-	modelsDevOnce = sync.Once{}
-	modelsDevCached = nil
-	modelsDevEnabled.Store(false)
-}
-
-// RefreshModelsDevCache fetches models.dev/api.json into the on-disk cache
-// when the cache is missing or older than modelsDevRefreshAfter. It is safe to
-// call fire-and-forget from startup (use a goroutine); it never affects the
-// current process's registry (see cachedModelsDevProviders). Disabled entirely
-// by ZERO_DISABLE_MODELS_FETCH. The URL can be overridden with ZERO_MODELS_URL.
-func RefreshModelsDevCache(ctx context.Context) error {
-	if strings.TrimSpace(os.Getenv("ZERO_DISABLE_MODELS_FETCH")) != "" {
-		return nil
-	}
-	path, err := modelsDevCachePath()
-	if err != nil {
-		return err
-	}
-	if info, err := os.Stat(path); err == nil && time.Since(info.ModTime()) < modelsDevRefreshAfter {
-		return nil
-	}
-
-	url := strings.TrimSpace(os.Getenv("ZERO_MODELS_URL"))
-	if url == "" {
-		url = modelsDevDefaultURL
-	}
-	fetchCtx, cancel := context.WithTimeout(ctx, modelsDevFetchWindow)
-	defer cancel()
-	request, err := http.NewRequestWithContext(fetchCtx, http.MethodGet, url, nil)
-	if err != nil {
-		return err
-	}
-	request.Header.Set("User-Agent", "zero-models-refresh/0.1")
-	response, err := http.DefaultClient.Do(request)
-	if err != nil {
-		return err
-	}
-	defer response.Body.Close()
-	if response.StatusCode != http.StatusOK {
-		return fmt.Errorf("modelregistry: models.dev fetch: HTTP %d", response.StatusCode)
-	}
-	data, err := io.ReadAll(io.LimitReader(response.Body, modelsDevFetchLimit))
-	if err != nil {
-		return err
-	}
-	// Validate before persisting: a bad body must never clobber a good cache.
-	if _, err := parseModelsDev(data); err != nil {
-		return err
-	}
-	if err := os.MkdirAll(filepath.Dir(path), 0o755); err != nil {
-		return err
-	}
-	temp, err := os.CreateTemp(filepath.Dir(path), "modelsdev-*.json")
-	if err != nil {
-		return err
-	}
-	if _, err := temp.Write(data); err != nil {
-		_ = temp.Close()
-		_ = os.Remove(temp.Name())
-		return err
-	}
-	if err := temp.Close(); err != nil {
-		_ = os.Remove(temp.Name())
-		return err
-	}
-	return os.Rename(temp.Name(), path)
-}
@@ -1,228 +0,0 @@
-package modelregistry
-
-import (
-	"net/http"
-	"net/http/httptest"
-	"os"
-	"path/filepath"
-	"testing"
-	"time"
-)
-
-const sampleModelsDev = `{
-  "anthropic": {
-    "id": "anthropic",
-    "models": {
-      "claude-sonnet-4-5-20250929": {
-        "limit": {"context": 1000000, "output": 64000},
-        "cost": {"input": 3.5, "output": 17.5, "cache_read": 0.35, "cache_write": 4.4}
-      }
-    }
-  },
-  "google": {
-    "id": "google",
-    "models": {
-      "gemini-2.5-pro": {
-        "limit": {"context": 2097152, "output": 65536},
-        "cost": {"input": 9.99, "output": 9.99}
-      }
-    }
-  }
-}`
-
-func TestParseModelsDev(t *testing.T) {
-	providers, err := parseModelsDev([]byte(sampleModelsDev))
-	if err != nil {
-		t.Fatal(err)
-	}
-	record, ok := providers["anthropic"]["claude-sonnet-4-5-20250929"]
-	if !ok {
-		t.Fatal("expected anthropic sonnet record")
-	}
-	if record.Limit.Context != 1_000_000 || record.Cost.Input != 3.5 {
-		t.Fatalf("unexpected record: %+v", record)
-	}
-	if _, err := parseModelsDev([]byte(`{}`)); err == nil {
-		t.Fatal("empty document must be rejected")
-	}
-	if _, err := parseModelsDev([]byte(`not json`)); err == nil {
-		t.Fatal("malformed document must be rejected")
-	}
-}
-
-func TestApplyModelsDevOverrides(t *testing.T) {
-	// Point the cache at a non-existent file so DefaultModelEntries returns the
-	// pure curated catalog, then apply the sample snapshot explicitly.
-	t.Setenv("ZERO_MODELS_CACHE_PATH", filepath.Join(t.TempDir(), "absent.json"))
-	resetModelsDevCacheForTest()
-	t.Cleanup(resetModelsDevCacheForTest)
-
-	providers, err := parseModelsDev([]byte(sampleModelsDev))
-	if err != nil {
-		t.Fatal(err)
-	}
-	entries := applyModelsDevOverrides(DefaultModelEntries(), providers)
-
-	var sonnet, geminiPro, opus ModelEntry
-	for _, entry := range entries {
-		switch entry.ID {
-		case "claude-sonnet-4.5":
-			sonnet = entry
-		case "gemini-2.5-pro":
-			geminiPro = entry
-		case "claude-opus-4.1":
-			opus = entry
-		}
-	}
-
-	// Known model: limits and base pricing refreshed from the snapshot.
-	if sonnet.ContextLimits.ContextWindow != 1_000_000 || sonnet.ContextLimits.MaxOutputTokens != 64_000 {
-		t.Fatalf("sonnet limits not overridden: %+v", sonnet.ContextLimits)
-	}
-	if sonnet.Cost.InputPerMillion != 3.5 || sonnet.Cost.OutputPerMillion != 17.5 || sonnet.Cost.CacheWritePerMillion != 4.4 {
-		t.Fatalf("sonnet cost not overridden: %+v", sonnet.Cost)
-	}
-	if sonnet.Cost.Source != "models.dev/api.json (cached)" {
-		t.Fatalf("sonnet cost source not marked: %q", sonnet.Cost.Source)
-	}
-
-	// Tiered pricing is curated: limits refresh, cost must NOT (gemini-2.5-pro
-	// has curated tiers and the snapshot's flat 9.99 would misprice them).
-	if geminiPro.ContextLimits.ContextWindow != 2_097_152 {
-		t.Fatalf("gemini limits not overridden: %+v", geminiPro.ContextLimits)
-	}
-	if geminiPro.Cost.InputPerMillion == 9.99 || len(geminiPro.Cost.Tiers) == 0 {
-		t.Fatalf("tiered cost must stay curated: %+v", geminiPro.Cost)
-	}
-
-	// Model absent from the snapshot: untouched.
-	if opus.ContextLimits.ContextWindow != 200_000 || opus.Cost.InputPerMillion != 15 {
-		t.Fatalf("opus must be untouched: %+v %+v", opus.ContextLimits, opus.Cost)
-	}
-}
-
-func TestRefreshModelsDevCacheFetchesAndCaches(t *testing.T) {
-	hits := 0
-	server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
-		hits++
-		_, _ = w.Write([]byte(sampleModelsDev))
-	}))
-	defer server.Close()
-
-	cachePath := filepath.Join(t.TempDir(), "modelsdev.json")
-	t.Setenv("ZERO_MODELS_CACHE_PATH", cachePath)
-	t.Setenv("ZERO_MODELS_URL", server.URL)
-	t.Setenv("ZERO_DISABLE_MODELS_FETCH", "")
-
-	if err := RefreshModelsDevCache(t.Context()); err != nil {
-		t.Fatal(err)
-	}
-	if hits != 1 {
-		t.Fatalf("expected 1 fetch, got %d", hits)
-	}
-	if _, err := os.Stat(cachePath); err != nil {
-		t.Fatalf("cache file missing: %v", err)
-	}
-	// Fresh cache: second call must not re-fetch.
-	if err := RefreshModelsDevCache(t.Context()); err != nil {
-		t.Fatal(err)
-	}
-	if hits != 1 {
-		t.Fatalf("fresh cache must skip the fetch, got %d hits", hits)
-	}
-}
-
-func TestRefreshModelsDevCacheRejectsBadBodyWithoutClobbering(t *testing.T) {
-	server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
-		_, _ = w.Write([]byte("not json"))
-	}))
-	defer server.Close()
-
-	cachePath := filepath.Join(t.TempDir(), "modelsdev.json")
-	if err := os.WriteFile(cachePath, []byte(sampleModelsDev), 0o644); err != nil {
-		t.Fatal(err)
-	}
-	stale := time.Now().Add(-48 * time.Hour)
-	if err := os.Chtimes(cachePath, stale, stale); err != nil {
-		t.Fatal(err)
-	}
-	t.Setenv("ZERO_MODELS_CACHE_PATH", cachePath)
-	t.Setenv("ZERO_MODELS_URL", server.URL)
-
-	if err := RefreshModelsDevCache(t.Context()); err == nil {
-		t.Fatal("bad body must return an error")
-	}
-	content, err := os.ReadFile(cachePath)
-	if err != nil || string(content) != sampleModelsDev {
-		t.Fatal("bad fetch must not clobber the existing cache")
-	}
-}
-
-func TestRefreshModelsDevCacheDisabledByEnv(t *testing.T) {
-	server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
-		t.Fatal("fetch must not happen when disabled")
-	}))
-	defer server.Close()
-	t.Setenv("ZERO_MODELS_CACHE_PATH", filepath.Join(t.TempDir(), "modelsdev.json"))
-	t.Setenv("ZERO_MODELS_URL", server.URL)
-	t.Setenv("ZERO_DISABLE_MODELS_FETCH", "1")
-	if err := RefreshModelsDevCache(t.Context()); err != nil {
-		t.Fatal(err)
-	}
-}
-
-func TestCachedModelsDevProvidersIgnoresStaleCache(t *testing.T) {
-	cachePath := filepath.Join(t.TempDir(), "modelsdev.json")
-	if err := os.WriteFile(cachePath, []byte(sampleModelsDev), 0o644); err != nil {
-		t.Fatal(err)
-	}
-	stale := time.Now().Add(-modelsDevMaxAge - time.Hour)
-	if err := os.Chtimes(cachePath, stale, stale); err != nil {
-		t.Fatal(err)
-	}
-	t.Setenv("ZERO_MODELS_CACHE_PATH", cachePath)
-	resetModelsDevCacheForTest()
-	t.Cleanup(resetModelsDevCacheForTest)
-	EnableModelsDevOverlay()
-
-	if providers := cachedModelsDevProviders(); providers != nil {
-		t.Fatal("stale cache must be ignored")
-	}
-}
-
-func TestCachedModelsDevProvidersRequiresOptIn(t *testing.T) {
-	cachePath := filepath.Join(t.TempDir(), "modelsdev.json")
-	if err := os.WriteFile(cachePath, []byte(sampleModelsDev), 0o644); err != nil {
-		t.Fatal(err)
-	}
-	t.Setenv("ZERO_MODELS_CACHE_PATH", cachePath)
-	resetModelsDevCacheForTest()
-	t.Cleanup(resetModelsDevCacheForTest)
-
-	// Without EnableModelsDevOverlay a fresh, valid cache must still be ignored:
-	// library consumers and hermetic tests get the pure curated catalog.
-	if providers := cachedModelsDevProviders(); providers != nil {
-		t.Fatal("overlay must be opt-in")
-	}
-}
-
-func TestDefaultModelEntriesAppliesFreshCache(t *testing.T) {
-	cachePath := filepath.Join(t.TempDir(), "modelsdev.json")
-	if err := os.WriteFile(cachePath, []byte(sampleModelsDev), 0o644); err != nil {
-		t.Fatal(err)
-	}
-	t.Setenv("ZERO_MODELS_CACHE_PATH", cachePath)
-	resetModelsDevCacheForTest()
-	t.Cleanup(resetModelsDevCacheForTest)
-	EnableModelsDevOverlay()
-
-	for _, entry := range DefaultModelEntries() {
-		if entry.ID == "claude-sonnet-4.5" {
-			if entry.ContextLimits.ContextWindow != 1_000_000 {
-				t.Fatalf("fresh cache must overlay the registry: %+v", entry.ContextLimits)
-			}
-			return
-		}
-	}
-	t.Fatal("claude-sonnet-4.5 not found")
-}
@@ -114,12 +114,7 @@ func createSecretFile(path string) ([]byte, error) {
 			}
 			return writeNewSecretFile(path)
 		}
-		// On Windows a concurrent holder's os.Remove leaves the lock file in a
-		// "delete pending" state, so an O_EXCL create races it with
-		// ERROR_ACCESS_DENIED (os.ErrPermission) rather than ErrExist. Treat that
-		// as contention and retry too — mirroring acquireFileLock in lock.go —
-		// otherwise concurrent secret creation spuriously fails on Windows.
-		if !errors.Is(err, os.ErrExist) && !errors.Is(err, os.ErrPermission) {
+		if !errors.Is(err, os.ErrExist) {
 			return nil, fmt.Errorf("oauth: create token secret lock: %w", err)
 		}
 		if data, rerr := readSecretFileRetry(path); rerr == nil {
@@ -123,10 +123,8 @@ var descriptors = []Descriptor{
 	openAICompat("together", "Together AI", "https://api.together.xyz/v1", "meta-llama/Llama-3.3-70B-Instruct-Turbo", []string{"TOGETHER_API_KEY"}),
 	openAICompat("dashscope", "DashScope", "https://dashscope-intl.aliyuncs.com/compatible-mode/v1", "qwen-plus", []string{"DASHSCOPE_API_KEY", "QWEN_API_KEY"}, "qwen"),
 	openAICompat("moonshot", "Moonshot AI", "https://api.moonshot.ai/v1", "kimi-k2-0905-preview", []string{"MOONSHOT_API_KEY"}, "kimi"),
-	openAICompat("longcat", "LongCat", "https://api.longcat.chat/openai", "LongCat-2.0", []string{"LONGCAT_API_KEY"}, "meituan longcat", "meituan", "longcat-2.0"),
 	openAICompat("nvidia-nim", "NVIDIA NIM", "https://integrate.api.nvidia.com/v1", "nvidia/llama-3.1-nemotron-70b-instruct", []string{"NVIDIA_API_KEY"}, "nvidia nim"),
 	anthropicCompat("minimax", "MiniMax", "https://api.minimax.io/anthropic", "MiniMax-M3", []string{"MINIMAX_API_KEY"}, "mini-max", "mini_max"),
-	anthropicCompat("minimaxi-cn", "MiniMax CN", "https://api.minimaxi.com/anthropic", "MiniMax-M3", []string{"MINIMAXI_API_KEY"}, "minimax cn", "minimax-cn"),
 	openAICompat("mistral", "Mistral", "https://api.mistral.ai/v1", "mistral-large-latest", []string{"MISTRAL_API_KEY"}),
 	openAICompat("github", "GitHub Models", "https://models.inference.ai.azure.com", "openai/gpt-4.1", []string{"GITHUB_TOKEN"}, "github-models"),
 	transportDescriptor("bedrock", "Amazon Bedrock", TransportBedrock, "https://bedrock-runtime.${AWS_REGION}.amazonaws.com", "anthropic.claude-3-5-sonnet-20241022-v2:0", []string{"AWS_ACCESS_KEY_ID", "AWS_PROFILE"}, []APIFormat{APIFormatBedrockConverse}, true),
@@ -135,11 +133,7 @@ var descriptors = []Descriptor{
 	openAICompat("venice", "Venice AI", "https://api.venice.ai/api/v1", "qwen-2.5-qwq-32b", []string{"VENICE_API_KEY"}),
 	openAICompat("xiaomi-mimo", "Xiaomi MiMo", "https://api.mimo.xiaomi.com/openai/v1", "mimo-vl", []string{"MIMO_API_KEY", "XIAOMI_API_KEY"}, "xiaomi mimo"),
 	openAICompat("bankr", "Bankr", "https://api.bankr.bot/v1", "bankr-large", []string{"BANKR_API_KEY"}),
-	openAICompat("zai", "Z.ai", "https://api.z.ai/api/paas/v4", "glm-4.5", []string{"ZAI_API_KEY"}, "z.ai"),
-	openAICompat("zai-cn", "Z.ai CN", "https://open.bigmodel.cn/api/paas/v4", "glm-4.5", []string{"ZHIPU_API_KEY"}, "z.ai cn"),
-	openAICompat("kilocode", "KiloCode", "https://api.kilo.ai/api/gateway", "anthropic/claude-sonnet-4.6", []string{"KILO_API_KEY"}, "kilo", "kilo gateway"),
-	openAICompat("opencode", "OpenCode Zen", "https://opencode.ai/zen/v1", "deepseek-v4-flash", []string{"OPENCODE_API_KEY"}, "opencode zen"),
-	openAICompat("opencode-go", "OpenCode Go", "https://opencode.ai/zen/go/v1", "deepseek-v4-pro", []string{"OPENCODE_API_KEY"}, "opencode go"),
+	openAICompat("zai", "Z.ai", "https://open.bigmodel.cn/api/paas/v4", "glm-4.5", []string{"ZAI_API_KEY", "ZHIPU_API_KEY"}),
 	openAICompat("atomic-chat", "Atomic Chat", "https://api.atomic.chat/v1", "gpt-4.1", []string{"ATOMIC_CHAT_API_KEY"}),
 	// ChatGPT subscription via a local OAuth proxy. A ChatGPT (Plus/Pro) OAuth
 	// token only works against ChatGPT's own backend (which is Cloudflare-gated to
@@ -23,10 +23,8 @@ var expectedCatalogIDs = []string{
 	"together",
 	"dashscope",
 	"moonshot",
-	"longcat",
 	"nvidia-nim",
 	"minimax",
-	"minimaxi-cn",
 	"mistral",
 	"github",
 	"bedrock",
@@ -36,10 +34,6 @@ var expectedCatalogIDs = []string{
 	"xiaomi-mimo",
 	"bankr",
 	"zai",
-	"zai-cn",
-	"kilocode",
-	"opencode",
-	"opencode-go",
 	"atomic-chat",
 	"chatgpt-proxy",
 	"custom-openai-compatible",
@@ -102,28 +96,6 @@ func TestRecommendedProviderEndpoint(t *testing.T) {
 	}
 }

-func TestLongCatDescriptor(t *testing.T) {
-	descriptor, err := Require("longcat")
-	if err != nil {
-		t.Fatalf("Require(longcat) error = %v", err)
-	}
-	if descriptor.Name != "LongCat" {
-		t.Fatalf("Name = %q, want LongCat", descriptor.Name)
-	}
-	if descriptor.DefaultBaseURL != "https://api.longcat.chat/openai" {
-		t.Fatalf("DefaultBaseURL = %q, want LongCat OpenAI-compatible endpoint", descriptor.DefaultBaseURL)
-	}
-	if descriptor.DefaultModel != "LongCat-2.0" {
-		t.Fatalf("DefaultModel = %q, want LongCat-2.0", descriptor.DefaultModel)
-	}
-	if descriptor.Transport != TransportOpenAICompatible {
-		t.Fatalf("Transport = %q, want %q", descriptor.Transport, TransportOpenAICompatible)
-	}
-	if !reflect.DeepEqual(descriptor.AuthEnvVars, []string{"LONGCAT_API_KEY"}) {
-		t.Fatalf("AuthEnvVars = %#v, want LONGCAT_API_KEY", descriptor.AuthEnvVars)
-	}
-}
-
 func TestCatalogDescriptorsExposeRequiredDefaults(t *testing.T) {
 	for _, descriptor := range All() {
 		if descriptor.ID == "" {
@@ -291,8 +263,8 @@ func TestListByTransportPreservesCatalogOrder(t *testing.T) {
 		TransportGoogle:          {"google"},
 		TransportBedrock:         {"bedrock"},
 		TransportVertex:          {"vertex"},
-		TransportAnthropicCompat: {"minimax", "minimaxi-cn", "custom-anthropic-compatible"},
-		TransportOpenAICompat:    {"gitlawb-opengateway", "ollama-cloud", "ollama", "lmstudio", "openrouter", "huggingface", "chatgpt", "groq", "deepseek", "together", "dashscope", "moonshot", "longcat", "nvidia-nim", "mistral", "github", "xai", "venice", "xiaomi-mimo", "bankr", "zai", "zai-cn", "kilocode", "opencode", "opencode-go", "atomic-chat", "chatgpt-proxy", "custom-openai-compatible"},
+		TransportAnthropicCompat: {"minimax", "custom-anthropic-compatible"},
+		TransportOpenAICompat:    {"gitlawb-opengateway", "ollama-cloud", "ollama", "lmstudio", "openrouter", "huggingface", "chatgpt", "groq", "deepseek", "together", "dashscope", "moonshot", "nvidia-nim", "mistral", "github", "xai", "venice", "xiaomi-mimo", "bankr", "zai", "atomic-chat", "chatgpt-proxy", "custom-openai-compatible"},
 	}

 	for transport, wantIDs := range cases {
@@ -169,8 +169,8 @@ func TestValidateEndpointAllowsLoopbackOnlyForLocalProvider(t *testing.T) {
 		if err := validateEndpoint(ctx, ep, r, true); err != nil {
 			t.Errorf("local provider endpoint %q should be allowed with allowLoopback=true, got %v", ep, err)
 		}
-		if !endpointIsLoopbackOrPrivate(ep) {
-			t.Errorf("endpointIsLoopbackOrPrivate(%q) = false, want true", ep)
+		if !endpointIsLoopback(ep) {
+			t.Errorf("endpointIsLoopback(%q) = false, want true", ep)
 		}
 	}

@@ -179,27 +179,14 @@ func TestValidateEndpointAllowsLoopbackOnlyForLocalProvider(t *testing.T) {
 		t.Error("loopback must remain blocked when allowLoopback=false (redirects / non-local)")
 	}

-	// allowLoopbackOrPrivate relaxes loopback AND private-network ranges — but
-	// link-local and other special ranges (cloud metadata, documentation) stay
-	// blocked even for a local provider config.
-	for _, ep := range []string{"http://169.254.169.254/latest/meta-data", "http://192.0.2.1:8080/v1"} {
+	// allowLoopback relaxes loopback ONLY — other special ranges (cloud metadata,
+	// link-local, private) stay blocked even for a local provider config.
+	for _, ep := range []string{"http://169.254.169.254/latest/meta-data", "http://10.0.0.5:8080/v1"} {
 		if err := validateEndpoint(ctx, ep, staticResolver{addr: netip.MustParseAddr("169.254.169.254")}, true); err == nil {
-			t.Errorf("special-use address %q must stay blocked even with flag=true", ep)
+			t.Errorf("non-loopback special address %q must stay blocked even with allowLoopback=true", ep)
 		}
-		if endpointIsLoopbackOrPrivate(ep) {
-			t.Errorf("endpointIsLoopbackOrPrivate(%q) = true, want false", ep)
-		}
-	}
-
-	// Private-network addresses (192.168.x.y / 10.x.y.z / 172.16.x.y) are
-	// now allowed when the flag is true — the user is pointing at their own
-	// LAN box (e.g. llama.cpp on another local machine).
-	for _, ep := range []string{"http://192.168.1.100:8080/v1", "http://10.0.0.5:8080/v1", "http://172.16.0.10:8080/v1"} {
-		if err := validateEndpoint(ctx, ep, staticResolver{addr: netip.MustParseAddr("192.168.1.100")}, true); err != nil {
-			t.Errorf("private-network address %q should be allowed with flag=true, got %v", ep, err)
-		}
-		if !endpointIsLoopbackOrPrivate(ep) {
-			t.Errorf("endpointIsLoopbackOrPrivate(%q) = false, want true", ep)
+		if endpointIsLoopback(ep) {
+			t.Errorf("endpointIsLoopback(%q) = true, want false", ep)
 		}
 	}
 }
@@ -269,7 +269,7 @@ func connectivityCheck(ctx context.Context, profile config.ProviderProfile, kind
 	requestCtx, cancel := context.WithTimeout(ctx, timeout)
 	defer cancel()

-	request, allowLoopbackOrPrivate, err := healthRequest(requestCtx, profile, kind, options)
+	request, allowLoopback, err := healthRequest(requestCtx, profile, kind, options)
 	if err != nil {
 		category := CategoryConfig
 		var safety endpointSafetyError
@@ -280,7 +280,7 @@ func connectivityCheck(ctx context.Context, profile config.ProviderProfile, kind
 	}
 	client := options.HTTPClient
 	if client == nil {
-		client = newConnectivityClient(timeout, options.Resolver, sensitiveAuthHeaderNames(profile, kind), allowLoopbackOrPrivate)
+		client = newConnectivityClient(timeout, options.Resolver, sensitiveAuthHeaderNames(profile, kind), allowLoopback)
 	}
 	response, err := client.Do(request)
 	if err != nil {
@@ -332,8 +332,8 @@ func healthRequest(ctx context.Context, profile config.ProviderProfile, kind con
 	// Loopback is permitted only when the user's OWN configured base_url is loopback
 	// (a local provider like Ollama/LM Studio) — never for a redirect target. This is
 	// the flag returned to the caller so the dial path applies the same policy. (AUDIT-H1)
-	allowLoopbackOrPrivate := endpointIsLoopbackOrPrivate(endpoint)
-	if err := validateEndpoint(ctx, endpoint, options.Resolver, allowLoopbackOrPrivate); err != nil {
+	allowLoopback := endpointIsLoopback(endpoint)
+	if err := validateEndpoint(ctx, endpoint, options.Resolver, allowLoopback); err != nil {
 		return nil, false, err
 	}
 	request, err := http.NewRequestWithContext(ctx, http.MethodGet, endpoint, nil)
@@ -344,7 +344,7 @@ func healthRequest(ctx context.Context, profile config.ProviderProfile, kind con
 		request.Header.Set("User-Agent", options.UserAgent)
 	}
 	applyAuth(request, profile, kind)
-	return request, allowLoopbackOrPrivate, nil
+	return request, allowLoopback, nil
 }

 func resolvedBaseURL(profile config.ProviderProfile, kind config.ProviderKind) (string, error) {
@@ -367,11 +367,11 @@ func resolvedBaseURL(profile config.ProviderProfile, kind config.ProviderKind) (
 }

 // validateEndpoint enforces the SSRF policy for the provider connectivity probe.
-// allowLoopbackOrPrivate permits loopback hosts (localhost / 127.0.0.0/8 / ::1)
-// and private-network hosts (192.168.0.0/16 / 10.0.0.0/8 / 172.16.0.0/12) — it
-// is set true exclusively for the user's own explicitly-configured base_url
-// (e.g. Ollama/LM Studio on the LAN), never for redirect targets.
-func validateEndpoint(ctx context.Context, endpoint string, resolver Resolver, allowLoopbackOrPrivate bool) error {
+// allowLoopback permits loopback hosts (localhost / 127.0.0.0/8 / ::1) ONLY — it is
+// set true exclusively for the user's own explicitly-configured local provider
+// base_url (e.g. Ollama/LM Studio), never for redirect targets, and it relaxes
+// loopback alone (other private/special ranges, incl. cloud metadata, stay blocked).
+func validateEndpoint(ctx context.Context, endpoint string, resolver Resolver, allowLoopback bool) error {
 	parsed, err := url.Parse(endpoint)
 	if err != nil {
 		return err
@@ -385,13 +385,13 @@ func validateEndpoint(ctx context.Context, endpoint string, resolver Resolver, a
 	}
 	normalized := strings.TrimSuffix(strings.ToLower(host), ".")
 	if normalized == "localhost" || strings.HasSuffix(normalized, ".localhost") {
-		if allowLoopbackOrPrivate {
+		if allowLoopback {
 			return nil // user-configured local provider; loopback is intentional
 		}
 		return endpointSafetyError{message: "provider connectivity URL is unsafe: localhost hosts are blocked"}
 	}
 	if addr, err := netip.ParseAddr(normalized); err == nil {
-		if reason := blockedAddrReason(addr); reason != "" && !(allowLoopbackOrPrivate && (addr.IsLoopback() || addr.IsPrivate())) {
+		if reason := blockedAddrReason(addr); reason != "" && !(allowLoopback && addr.IsLoopback()) {
 			return endpointSafetyError{message: "provider connectivity URL is unsafe: " + reason}
 		}
 		return nil
@@ -407,19 +407,17 @@ func validateEndpoint(ctx context.Context, endpoint string, resolver Resolver, a
 		return endpointSafetyError{message: "provider connectivity host resolved to no addresses"}
 	}
 	for _, addr := range addrs {
-		if reason := blockedAddrReason(addr); reason != "" && !(allowLoopbackOrPrivate && (addr.IsLoopback() || addr.IsPrivate())) {
+		if reason := blockedAddrReason(addr); reason != "" && !(allowLoopback && addr.IsLoopback()) {
 			return endpointSafetyError{message: "provider connectivity URL is unsafe: " + reason}
 		}
 	}
 	return nil
 }

-// endpointIsLoopbackOrPrivate reports whether the configured endpoint's host is a loopback
-// or private-network host the user typed themselves — a local provider on the LAN
-// (e.g. 192.168.x.y / 10.x.y.z) or localhost. Used to decide whether the
-// connectivity probe may relax address-blocking and reach the user's own
-// explicitly-configured provider.
-func endpointIsLoopbackOrPrivate(endpoint string) bool {
+// endpointIsLoopback reports whether the configured endpoint's host is a loopback
+// host the user typed themselves (localhost or a 127.0.0.0/8 / ::1 literal). Used to
+// decide whether the connectivity probe may reach the user's own local provider.
+func endpointIsLoopback(endpoint string) bool {
 	parsed, err := url.Parse(endpoint)
 	if err != nil {
 		return false
@@ -429,7 +427,7 @@ func endpointIsLoopbackOrPrivate(endpoint string) bool {
 		return true
 	}
 	if addr, err := netip.ParseAddr(host); err == nil {
-		return addr.IsLoopback() || addr.IsPrivate()
+		return addr.IsLoopback()
 	}
 	return false
 }
@@ -448,7 +446,7 @@ const maxConnectivityRedirects = 5
 //     time and then dials the validated IP literal, closing the TOCTOU window
 //     between the pre-flight validateEndpoint check and the actual connection
 //     (DNS rebinding).
-func newConnectivityClient(timeout time.Duration, resolver Resolver, sensitiveHeaders []string, allowLoopbackOrPrivate bool) *http.Client {
+func newConnectivityClient(timeout time.Duration, resolver Resolver, sensitiveHeaders []string, allowLoopback bool) *http.Client {
 	if resolver == nil {
 		resolver = defaultResolver{}
 	}
@@ -458,7 +456,7 @@ func newConnectivityClient(timeout time.Duration, resolver Resolver, sensitiveHe
 	} else {
 		transport = &http.Transport{}
 	}
-	transport.DialContext = safeDialContext(resolver, allowLoopbackOrPrivate)
+	transport.DialContext = safeDialContext(resolver, allowLoopback)
 	return &http.Client{
 		Timeout:   timeout,
 		Transport: transport,
@@ -478,8 +476,8 @@ func newConnectivityClient(timeout time.Duration, resolver Resolver, sensitiveHe
 				}
 			}
 			// Redirects are NEVER allowed to reach loopback, even for a local provider:
-			// allowLoopbackOrPrivate covers only the user's own configured base_url,
-			// not a 3xx target (which could be attacker-controlled SSRF). (AUDIT-H1)
+			// allowLoopback covers only the user's own configured base_url, not a 3xx
+			// target (which could be attacker-controlled SSRF). (AUDIT-H1)
 			return validateEndpoint(req.Context(), req.URL.String(), resolver, false)
 		},
 	}
@@ -521,7 +519,7 @@ func sensitiveAuthHeaderNames(profile config.ProviderProfile, kind config.Provid
 // safeDialContext returns a dial function that resolves the target host, refuses
 // the connection if any resolved address is blocked, then dials the validated IP
 // literal so the kernel cannot re-resolve to a different address after the check.
-func safeDialContext(resolver Resolver, allowLoopbackOrPrivate bool) func(context.Context, string, string) (net.Conn, error) {
+func safeDialContext(resolver Resolver, allowLoopback 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) {
 		host, port, err := net.SplitHostPort(address)
@@ -529,7 +527,7 @@ func safeDialContext(resolver Resolver, allowLoopbackOrPrivate bool) func(contex
 			return nil, err
 		}
 		if addr, parseErr := netip.ParseAddr(host); parseErr == nil {
-			if reason := blockedAddrReason(addr); reason != "" && !(allowLoopbackOrPrivate && (addr.IsLoopback() || addr.IsPrivate())) {
+			if reason := blockedAddrReason(addr); reason != "" && !(allowLoopback && addr.IsLoopback()) {
 				return nil, endpointSafetyError{message: "provider connectivity URL is unsafe: " + reason}
 			}
 			return dialer.DialContext(ctx, network, address)
@@ -542,7 +540,7 @@ func safeDialContext(resolver Resolver, allowLoopbackOrPrivate bool) func(contex
 			return nil, endpointSafetyError{message: "provider connectivity host resolved to no addresses"}
 		}
 		for _, addr := range addrs {
-			if reason := blockedAddrReason(addr); reason != "" && !(allowLoopbackOrPrivate && (addr.IsLoopback() || addr.IsPrivate())) {
+			if reason := blockedAddrReason(addr); reason != "" && !(allowLoopback && addr.IsLoopback()) {
 				return nil, endpointSafetyError{message: "provider connectivity URL is unsafe: " + reason}
 			}
 		}
@@ -21,22 +21,6 @@ type Model struct {
 	Source           string
 }

-// Shared by both "minimax" and "minimaxi-cn"; Models() rebuilds a fresh slice
-// per call, so the shared backing slice cannot be mutated by callers.
-var minimaxCuratedModels = []Model{
-	{ID: "MiniMax-M3", Description: "catalog default"},
-	{ID: "MiniMax-M2.1", Description: "agentic coding model"},
-}
-
-// Shared by both "zai" (international, api.z.ai) and "zai-cn" (China,
-// open.bigmodel.cn); same model lineup on both endpoints.
-var zaiCuratedModels = []Model{
-	{ID: "glm-4.5", Description: "catalog default"},
-	{ID: "glm-4.5-air", Description: "fast model"},
-	{ID: "glm-4.6", Description: "latest general model"},
-	{ID: "glm-z1-air", Description: "reasoning model"},
-}
-
 var curatedModels = map[string][]Model{
 	"ollama-cloud": {
 		{ID: "qwen3-coder:480b", Description: "catalog default"},
@@ -104,8 +88,10 @@ var curatedModels = map[string][]Model{
 		{ID: "meta/llama-3.1-70b-instruct", Description: "general model"},
 		{ID: "mistralai/mixtral-8x7b-instruct-v0.1", Description: "mixture model"},
 	},
-	"minimax":     minimaxCuratedModels,
-	"minimaxi-cn": minimaxCuratedModels,
+	"minimax": {
+		{ID: "MiniMax-M3", Description: "catalog default"},
+		{ID: "MiniMax-M2.1", Description: "agentic coding model"},
+	},
 	"mistral": {
 		{ID: "mistral-large-latest", Description: "catalog default"},
 		{ID: "codestral-latest", Description: "coding model"},
@@ -137,8 +123,12 @@ var curatedModels = map[string][]Model{
 	"bankr": {
 		{ID: "bankr-large", Description: "catalog default"},
 	},
-	"zai":    zaiCuratedModels,
-	"zai-cn": zaiCuratedModels,
+	"zai": {
+		{ID: "glm-4.5", Description: "catalog default"},
+		{ID: "glm-4.5-air", Description: "fast model"},
+		{ID: "glm-4.6", Description: "latest general model"},
+		{ID: "glm-z1-air", Description: "reasoning model"},
+	},
 	// OpenGateway smart-routes by model id across its upstream providers
 	// (see /health: xiaomi-mimo, minimax, qwen, google, nvidia, z-ai). These are
 	// the curated coding defaults; the gateway accepts any model its upstreams
@@ -37,16 +37,6 @@ func TestModelsAreProviderScoped(t *testing.T) {
 			want:     []string{"mistral-large-latest", "codestral-latest"},
 			notWant:  []string{"gpt-4.1", "claude-sonnet-4.5"},
 		},
-		{
-			provider: "minimaxi-cn",
-			want:     []string{"MiniMax-M3", "MiniMax-M2.1"},
-			notWant:  []string{"gpt-4.1", "claude-sonnet-4.5"},
-		},
-		{
-			provider: "zai-cn",
-			want:     []string{"glm-4.5", "glm-4.6", "glm-4.5-air", "glm-z1-air"},
-			notWant:  []string{"gpt-4.1", "claude-sonnet-4.5"},
-		},
 	}

 	for _, tt := range tests {
@@ -98,66 +88,3 @@ func modelIDs(models []Model) []string {
 	}
 	return ids
 }
-
-// Pins the contract that MiniMax CN exposes exactly the same model IDs as the
-// international provider; a divergence here is almost always a mistake.
-func TestMiniMaxCNModelsMirrorInternational(t *testing.T) {
-	intl, ok := providercatalog.Get("minimax")
-	if !ok {
-		t.Fatal("provider minimax missing from catalog")
-	}
-	cn, ok := providercatalog.Get("minimaxi-cn")
-	if !ok {
-		t.Fatal("provider minimaxi-cn missing from catalog")
-	}
-	intlModels := Models(intl)
-	cnModels := Models(cn)
-	if len(intlModels) != len(cnModels) {
-		t.Fatalf("model count mismatch: international=%d china=%d", len(intlModels), len(cnModels))
-	}
-	intlIDs := map[string]string{}
-	for _, m := range intlModels {
-		intlIDs[m.ID] = m.Description
-	}
-	for _, m := range cnModels {
-		wantDesc, ok := intlIDs[m.ID]
-		if !ok {
-			t.Fatalf("china provider exposes %q which is not in the international catalog", m.ID)
-		}
-		if m.Description != wantDesc {
-			t.Fatalf("model %q description diverged: international=%q china=%q", m.ID, wantDesc, m.Description)
-		}
-	}
-}
-
-// Same contract as TestMiniMaxCNModelsMirrorInternational, for Z.ai: the
-// international (api.z.ai) and China (open.bigmodel.cn) endpoints expose the
-// same model lineup.
-func TestZaiCNModelsMirrorInternational(t *testing.T) {
-	intl, ok := providercatalog.Get("zai")
-	if !ok {
-		t.Fatal("provider zai missing from catalog")
-	}
-	cn, ok := providercatalog.Get("zai-cn")
-	if !ok {
-		t.Fatal("provider zai-cn missing from catalog")
-	}
-	intlModels := Models(intl)
-	cnModels := Models(cn)
-	if len(intlModels) != len(cnModels) {
-		t.Fatalf("model count mismatch: international=%d china=%d", len(intlModels), len(cnModels))
-	}
-	intlIDs := map[string]string{}
-	for _, m := range intlModels {
-		intlIDs[m.ID] = m.Description
-	}
-	for _, m := range cnModels {
-		wantDesc, ok := intlIDs[m.ID]
-		if !ok {
-			t.Fatalf("china provider exposes %q which is not in the international catalog", m.ID)
-		}
-		if m.Description != wantDesc {
-			t.Fatalf("model %q description diverged: international=%q china=%q", m.ID, wantDesc, m.Description)
-		}
-	}
-}
@@ -128,10 +128,6 @@ func ModelsDevProviderID(provider providercatalog.Descriptor) string {
 		return "nvidia"
 	case "xiaomi-mimo":
 		return "xiaomi"
-	case "zai-cn":
-		return "zai"
-	case "minimaxi-cn":
-		return "minimax"
 	default:
 		return strings.TrimSpace(provider.ID)
 	}
@@ -118,8 +118,6 @@ func TestModelsDevProviderIDMapsZeroAliases(t *testing.T) {
 		"xiaomi-mimo":  "xiaomi",
 		"dashscope":    "alibaba",
 		"ollama-cloud": "ollama-cloud",
-		"zai-cn":       "zai",
-		"minimaxi-cn":  "minimax",
 	}
 	for zeroID, want := range tests {
 		provider, ok := providercatalog.Get(zeroID)
@@ -1,96 +0,0 @@
-package anthropic
-
-import (
-	"context"
-	"encoding/json"
-	"net/http"
-	"net/http/httptest"
-	"testing"
-
-	"github.com/Gitlawb/zero/internal/zeroruntime"
-)
-
-// The final two messages must carry a cache_control breakpoint on their last
-// cacheable block so the conversation transcript — not just system prompt and
-// tools — is a prompt-cache hit on the next turn. Earlier messages must stay
-// unmarked (Anthropic caps breakpoints at 4 per request: system, tools, and
-// these two).
-func TestAnthropicRequestMarksLastTwoMessagesForCaching(t *testing.T) {
-	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: "claude-test"})
-	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: "first"},
-			{
-				Role:      zeroruntime.MessageRoleAssistant,
-				Content:   "calling a tool",
-				ToolCalls: []zeroruntime.ToolCall{{ID: "toolu_1", Name: "grep", Arguments: `{}`}},
-			},
-			{Role: zeroruntime.MessageRoleTool, Content: "result", ToolCallID: "toolu_1"},
-		},
-	})
-	if err != nil {
-		t.Fatalf("StreamCompletion returned error: %v", err)
-	}
-	drain(stream)
-
-	messages := gotBody["messages"].([]any)
-	if len(messages) != 3 {
-		t.Fatalf("expected 3 wire messages, got %d: %#v", len(messages), messages)
-	}
-	lastBlockHasCache := func(message any) bool {
-		blocks, ok := message.(map[string]any)["content"].([]any)
-		if !ok || len(blocks) == 0 {
-			return false
-		}
-		last := blocks[len(blocks)-1].(map[string]any)
-		control, ok := last["cache_control"].(map[string]any)
-		return ok && control["type"] == "ephemeral"
-	}
-	if lastBlockHasCache(messages[0]) {
-		t.Fatalf("first message must not carry a breakpoint: %#v", messages[0])
-	}
-	if !lastBlockHasCache(messages[1]) {
-		t.Fatalf("second-to-last message must carry a breakpoint: %#v", messages[1])
-	}
-	if !lastBlockHasCache(messages[2]) {
-		t.Fatalf("last message must carry a breakpoint: %#v", messages[2])
-	}
-}
-
-// A string-content message must be converted to a block array so it can carry
-// the breakpoint, and thinking blocks must never carry cache_control (the API
-// rejects them) — the marker goes on the last cacheable block instead.
-func TestApplyMessageCacheBreakpointsSkipsThinkingBlocks(t *testing.T) {
-	messages := []anthropicMessage{
-		{Role: "user", Content: "plain string"},
-		{Role: "assistant", Content: []map[string]any{
-			{"type": "text", "text": "answer"},
-			{"type": "thinking", "thinking": "hmm", "signature": "sig"},
-		}},
-	}
-	applyMessageCacheBreakpoints(messages)
-
-	userBlocks := contentBlocks(messages[0].Content)
-	if len(userBlocks) != 1 || userBlocks[0]["cache_control"] == nil {
-		t.Fatalf("string content must become a marked block: %#v", messages[0].Content)
-	}
-	assistantBlocks := contentBlocks(messages[1].Content)
-	if assistantBlocks[1]["cache_control"] != nil {
-		t.Fatalf("thinking block must not be marked: %#v", assistantBlocks[1])
-	}
-	if assistantBlocks[0]["cache_control"] == nil {
-		t.Fatalf("text block must carry the breakpoint instead: %#v", assistantBlocks[0])
-	}
-}
@@ -405,35 +405,9 @@ func (provider *Provider) anthropicRequest(request zeroruntime.CompletionRequest
 		}
 		mapped.Tools[len(mapped.Tools)-1].CacheControl = &cacheControl{Type: cacheEphemeral}
 	}
-	applyMessageCacheBreakpoints(mapped.Messages)
 	return mapped, nil
 }

-// applyMessageCacheBreakpoints marks the last content block of the final two
-// messages with cache_control so the conversation transcript is cached
-// turn-over-turn, not just the system prompt and tool definitions. Two message
-// breakpoints (not one) keep the previous turn's prefix a cache hit while the
-// newest suffix is being written. Anthropic allows at most 4 breakpoints per
-// request: system + tools use two above, these use the remaining two. Thinking
-// blocks cannot carry cache_control, so the marker goes on the last block that
-// can.
-func applyMessageCacheBreakpoints(messages []anthropicMessage) {
-	marked := 0
-	for i := len(messages) - 1; i >= 0 && marked < 2; i-- {
-		blocks := contentBlocks(messages[i].Content)
-		for j := len(blocks) - 1; j >= 0; j-- {
-			blockType, _ := blocks[j]["type"].(string)
-			if blockType == "thinking" || blockType == "redacted_thinking" {
-				continue
-			}
-			blocks[j]["cache_control"] = map[string]any{"type": cacheEphemeral}
-			messages[i].Content = blocks
-			marked++
-			break
-		}
-	}
-}
-
 func mapMessages(messages []zeroruntime.Message) (string, []anthropicMessage, error) {
 	systemParts := []string{}
 	mapped := []anthropicMessage{}
@@ -23,18 +23,12 @@ import (
 // (billable) work. Only the INITIAL request is ever in scope; once the response
 // body starts streaming it is never re-issued.

-const defaultMaxRetryAttempts = 6
+const defaultMaxRetryAttempts = 3

 // maxBackoff caps a single backoff wait so a hostile or buggy Retry-After can't
 // stall the agent for minutes.
 const maxBackoff = 30 * time.Second

-// retryBackoffBase is the first wait when the server supplied no Retry-After.
-// Rate-limit windows are measured in seconds, not milliseconds: retrying a 429
-// after 400ms almost always burns the attempt while still limited, so the
-// schedule is 2s, 4s, 8s, 16s, then maxBackoff. A var so tests can shrink it.
-var retryBackoffBase = 2 * time.Second
-
 // SendWithRetry issues an HTTP request, retrying ONLY the safe-to-replay server
 // responses (429 and 503, see ShouldRetryStatus) up to maxAttempts — backing off
 // between tries and honoring a server Retry-After header and context
@@ -116,11 +110,17 @@ func ShouldRetryStatus(code int) bool {
 }

 // Backoff waits before retry attempt N (1-based), returning false if the context
-// is cancelled during the wait. A server-supplied (positive) Retry-After wins;
-// otherwise the wait doubles from retryBackoffBase per attempt. Either way the
-// wait is capped at maxBackoff.
+// is cancelled during the wait. The wait is attempt*400ms unless the server
+// supplied a (positive) Retry-After, and is capped at maxBackoff.
 func Backoff(ctx context.Context, attempt int, retryAfter time.Duration) bool {
-	timer := time.NewTimer(backoffWait(attempt, retryAfter))
+	wait := time.Duration(attempt) * 400 * time.Millisecond
+	if retryAfter > 0 {
+		wait = retryAfter
+	}
+	if wait > maxBackoff {
+		wait = maxBackoff
+	}
+	timer := time.NewTimer(wait)
 	defer timer.Stop()
 	select {
 	case <-ctx.Done():
@@ -130,27 +130,6 @@ func Backoff(ctx context.Context, attempt int, retryAfter time.Duration) bool {
 	}
 }

-// backoffWait computes the wait before retry attempt N (1-based): Retry-After
-// when supplied, else exponential from retryBackoffBase, both capped at
-// maxBackoff. The exponent is clamped so a large attempt count cannot overflow.
-func backoffWait(attempt int, retryAfter time.Duration) time.Duration {
-	wait := retryAfter
-	if wait <= 0 {
-		exponent := attempt - 1
-		if exponent > 5 {
-			exponent = 5
-		}
-		if exponent < 0 {
-			exponent = 0
-		}
-		wait = retryBackoffBase * time.Duration(1<<exponent)
-	}
-	if wait > maxBackoff {
-		wait = maxBackoff
-	}
-	return wait
-}
-
 // RetryAfter parses a response's Retry-After header (delay-seconds or an HTTP
 // date) into a positive duration, or 0 when absent/unparseable. The result is
 // capped at maxBackoff by Backoff.
@@ -94,40 +94,7 @@ func TestBackoffWaitsThenReturnsTrue(t *testing.T) {
 	}
 }

-// shrinkBackoff makes retry waits negligible for the duration of a test.
-func shrinkBackoff(t *testing.T) {
-	t.Helper()
-	saved := retryBackoffBase
-	retryBackoffBase = time.Millisecond
-	t.Cleanup(func() { retryBackoffBase = saved })
-}
-
-func TestBackoffWaitSchedule(t *testing.T) {
-	// Without Retry-After the wait doubles per attempt from 2s and caps at 30s;
-	// a supplied Retry-After wins but is capped too.
-	cases := []struct {
-		attempt    int
-		retryAfter time.Duration
-		want       time.Duration
-	}{
-		{1, 0, 2 * time.Second},
-		{2, 0, 4 * time.Second},
-		{3, 0, 8 * time.Second},
-		{4, 0, 16 * time.Second},
-		{5, 0, 30 * time.Second},  // 32s capped
-		{50, 0, 30 * time.Second}, // clamped exponent, no overflow
-		{1, 7 * time.Second, 7 * time.Second},
-		{1, 5 * time.Minute, 30 * time.Second}, // hostile Retry-After capped
-	}
-	for _, c := range cases {
-		if got := backoffWait(c.attempt, c.retryAfter); got != c.want {
-			t.Errorf("backoffWait(%d, %v) = %v, want %v", c.attempt, c.retryAfter, got, c.want)
-		}
-	}
-}
-
 func TestSendWithRetryRetriesThenSucceeds(t *testing.T) {
-	shrinkBackoff(t)
 	var hits int32
 	server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
 		if atomic.AddInt32(&hits, 1) == 1 {
@@ -173,7 +140,6 @@ func TestSendWithRetryReturnsNonRetryableImmediately(t *testing.T) {
 }

 func TestSendWithRetryReturnsLastResponseAfterMaxAttempts(t *testing.T) {
-	shrinkBackoff(t)
 	var hits int32
 	server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
 		atomic.AddInt32(&hits, 1)
@@ -9,25 +9,22 @@ import (
 	"time"
 )

-// TestEvaluatePromptsForNetworkToolsButExemptsThemFromShellNetworkPolicy verifies
-// that first-party in-process network tools are governed by their permission
-// metadata, not by the sandboxed shell egress policy.
-func TestEvaluatePromptsForNetworkToolsButExemptsThemFromShellNetworkPolicy(t *testing.T) {
+// TestEvaluateExemptsNetworkToolsFromShellNetworkPolicy verifies that the
+// sandbox network policy gates sandboxed shell egress, not first-party
+// in-process web tools.
+func TestEvaluateExemptsNetworkToolsFromShellNetworkPolicy(t *testing.T) {
 	base := Policy{Mode: ModeEnforce, Network: NetworkDeny}

 	engine := NewEngine(EngineOptions{Policy: base})
 	d := engine.Evaluate(context.Background(), Request{
-		ToolName: "web_search", SideEffect: SideEffectNetwork, Permission: PermissionPrompt,
+		ToolName: "web_search", SideEffect: SideEffectNetwork, Permission: PermissionAllow,
 	})
-	if d.Action != ActionPrompt || d.Block != nil {
-		t.Fatalf("web_search must prompt before permission is granted, got %#v", d)
-	}
-	if d.Reason == ReasonNetworkBlocked {
-		t.Fatalf("web_search prompt should come from tool permission, not shell network policy: %#v", d)
+	if d.Action != ActionAllow || d.Block != nil {
+		t.Fatalf("web_search must be allowed by the sandbox gate, got %#v", d)
 	}

 	allowed := engine.Evaluate(context.Background(), Request{
-		ToolName: "web_search", SideEffect: SideEffectNetwork, Permission: PermissionPrompt, PermissionGranted: true,
+		ToolName: "web_search", SideEffect: SideEffectNetwork, Permission: PermissionAllow, PermissionGranted: true,
 	})
 	if allowed.Action != ActionAllow || allowed.Block != nil {
 		t.Fatalf("granted web_search must be allowed under deny, got %#v", allowed)
@@ -19,13 +19,6 @@ var errWindowsSandboxNotInitialized = errors.New(
 const windowsSetupDowngradeReason = "Windows OS sandbox inactive — commands run with workspace path-confinement and " +
 	"per-command approval only. Run `zero sandbox setup` from an elevated (Administrator) terminal for full filesystem and network isolation."

-// windowsUnelevatedDowngradeReason is surfaced when Windows runs the sandbox in
-// the unelevated tier: the restricted-token write-jail is enforced (the command
-// runner applies the workspace ACLs itself, which needs no Administrator
-// rights), but the WFP network filters are Administrator-only and absent.
-const windowsUnelevatedDowngradeReason = "Windows sandbox running unelevated — the filesystem write-jail is enforced, but network " +
-	"isolation still relies on per-command approval. Run `zero sandbox setup` from an elevated (Administrator) terminal for OS-level network enforcement."
-
 // windowsSandboxInitialized reports whether the per-host Windows sandbox setup
 // marker exists. A missing marker is the common fresh-install state, so the
 // caller degrades rather than bricking the command. Indirected through a var so
@@ -181,28 +174,19 @@ func (manager SandboxManager) BuildExecutionRequest(request SandboxManagerReques
 	if request.ValidateExecution && preference == SandboxPreferenceRequire && backend.SupportLevel() != BackendSupportNative {
 		return SandboxExecutionRequest{}, nativeSandboxUnavailableError(backend)
 	}
-	// Windows: the FULL OS sandbox needs a one-time elevated `zero sandbox setup`
-	// (it applies WFP network filters + workspace ACLs and writes a marker).
-	// Without it, a restricted-filesystem profile can still run in the UNELEVATED
-	// tier: the command runner applies the workspace ACL plan itself (DACL edits
-	// on user-owned roots need no Administrator rights) and wraps the command in
-	// the write-restricted token, so the filesystem write-jail holds. Only the
-	// WFP network filters are Administrator-only, so network stays with the
-	// in-process approval gate at that tier. A profile that needs the sandbox
-	// solely for network isolation gains nothing from the unelevated tier and
-	// DEGRADES to the policy gate as before. A strict caller (--sandbox require)
-	// still gets a clear error pointing at setup.
+	// Windows: the OS sandbox needs a one-time elevated `zero sandbox setup` (it
+	// applies WFP network filters + workspace ACLs and writes a marker). Without
+	// it the command runner hard-fails — so on the default preference, DEGRADE to
+	// the in-process policy gate + per-command approval (matching Linux/macOS when
+	// their sandbox is unavailable) instead of bricking every command. A strict
+	// caller (--sandbox require) still gets a clear error pointing at setup.
 	windowsNeedsSetup := false
 	if manager.goos == "windows" && requiresPlatformSandbox && enforcementLevel == EnforcementNative && !windowsSandboxInitialized() {
 		if preference == SandboxPreferenceRequire {
 			return SandboxExecutionRequest{}, errWindowsSandboxNotInitialized
 		}
+		enforcementLevel = EnforcementDegraded
 		windowsNeedsSetup = true
-		if profile.FileSystem.Kind == FileSystemRestricted {
-			enforcementLevel = EnforcementUnelevated
-		} else {
-			enforcementLevel = EnforcementDegraded
-		}
 	}
 	targetBackend := manager.targetBackend(preference, policy, requiresPlatformSandbox)
 	downgradeReason := ""
@@ -212,11 +196,7 @@ func (manager SandboxManager) BuildExecutionRequest(request SandboxManagerReques
 			downgradeReason = windowsSetupDowngradeReason
 		}
 	}
-	if enforcementLevel == EnforcementUnelevated {
-		downgradeReason = windowsUnelevatedDowngradeReason
-	}
-	wrapped := backend.CommandWrapping && backend.Available &&
-		(enforcementLevel == EnforcementNative || enforcementLevel == EnforcementUnelevated)
+	wrapped := backend.CommandWrapping && backend.Available && enforcementLevel == EnforcementNative
 	markers := backend.SandboxEnvMarkers(policy)
 	if !wrapped && backend.Name != BackendWSL {
 		markers = nil
@@ -72,10 +72,7 @@ func TestPermissionProfileFromPolicyIncludesDefaultTempWriteRoots(t *testing.T)
 	if !writeRootsContain(profile.FileSystem.WriteRoots, tmpdir) {
 		t.Fatalf("write roots = %#v, want temp root %q", profile.FileSystem.WriteRoots, tmpdir)
 	}
-	// /tmp is a default temp write root on POSIX only (see
-	// defaultTempWriteRootCandidatesForGOOS); on Windows the bare path resolves
-	// against the current drive, so a stray C:\tmp must not turn this on.
-	if runtime.GOOS != "windows" && pathExists("/tmp") && !writeRootsContain(profile.FileSystem.WriteRoots, "/tmp") {
+	if pathExists("/tmp") && !writeRootsContain(profile.FileSystem.WriteRoots, "/tmp") {
 		t.Fatalf("write roots = %#v, want /tmp", profile.FileSystem.WriteRoots)
 	}
 }
@@ -132,64 +132,6 @@ exit 0
 	}
 }

-// TestWindowsUnelevatedRealSandboxSmoke exercises the unelevated tier end to
-// end WITHOUT running the elevated setup helper: the command runner applies
-// the workspace ACLs itself, a write inside the workspace succeeds under the
-// restricted token, and a write outside every granted root is denied. Unlike
-// the elevated smoke above it needs no Administrator terminal.
-func TestWindowsUnelevatedRealSandboxSmoke(t *testing.T) {
-	if os.Getenv("ZERO_SANDBOX_REAL_SMOKE") != "1" {
-		t.Skip("set ZERO_SANDBOX_REAL_SMOKE=1 to run real Windows sandbox smoke tests")
-	}
-	runnerExe := realSmokeExecutable(t, "ZERO_WINDOWS_COMMAND_RUNNER_EXE", WindowsSandboxCommandRunnerName)
-
-	root := t.TempDir()
-	outside := t.TempDir()
-	sandboxHome := filepath.Join(root, ".zero-sandbox")
-	profile := PermissionProfile{
-		FileSystem: FileSystemPolicy{
-			Kind:                 FileSystemRestricted,
-			ReadRoots:            []string{root},
-			WriteRoots:           []WritableRoot{{Root: root, ProtectedMetadataNames: []string{".git", ".zero", ".agents"}}},
-			IncludePlatformRoots: true,
-			AllowTemp:            true,
-		},
-		Network: NetworkPolicy{Mode: NetworkDeny},
-	}
-	config := WindowsSandboxCommandArgsOptions{
-		SandboxHome:       sandboxHome,
-		CommandCWD:        root,
-		WorkspaceRoots:    []string{root},
-		PermissionProfile: profile,
-		SandboxLevel:      WindowsSandboxLevelUnelevated,
-	}
-
-	// cmd.exe rather than powershell.exe: managed PowerShell cannot initialize
-	// its crypto provider under a write-restricted token on some hosts
-	// (0x8009001d, the same restricted-token limitation the runner documents for
-	// Schannel), and the write-jail assertion only needs a native shell.
-	insideMarker := filepath.Join(root, "unelevated-write-ok.txt")
-	runWindowsRealSmokeCommand(t, runnerExe, config, []string{
-		"cmd.exe", "/d", "/s", "/c", "echo ok>" + insideMarker,
-	}, 0)
-	if bytes, err := os.ReadFile(insideMarker); err != nil || strings.TrimSpace(string(bytes)) != "ok" {
-		t.Fatalf("unelevated sandboxed write marker = %q, %v; want ok", bytes, err)
-	}
-	if _, err := os.Stat(WindowsUnelevatedSetupMarkerPath(sandboxHome)); err != nil {
-		t.Fatalf("expected the unelevated setup marker to be recorded: %v", err)
-	}
-
-	outsideMarker := filepath.Join(outside, "unelevated-write-denied.txt")
-	runWindowsRealSmokeCommand(t, runnerExe, config, []string{
-		"cmd.exe", "/d", "/s", "/c", "echo leaked>" + outsideMarker,
-	}, 1)
-	if _, err := os.Stat(outsideMarker); err == nil {
-		t.Fatalf("unelevated sandbox allowed a write outside every granted root")
-	} else if !os.IsNotExist(err) {
-		t.Fatalf("stat outside marker: %v", err)
-	}
-}
-
 func realSmokeExecutable(t *testing.T, envKey string, fallbackName string) string {
 	t.Helper()
 	if path := os.Getenv(envKey); path != "" {
@@ -3,7 +3,6 @@ package sandbox
 import (
 	"os"
 	"path/filepath"
-	"runtime"
 	"strings"
 	"testing"
 )
@@ -129,10 +128,7 @@ func TestNewScopeNormalizesAndValidatesExtraRoots(t *testing.T) {
 	if !stringSliceContains(roots, normalizeWorkspaceRootBestEffort(extra)) {
 		t.Fatalf("Roots()=%v want extra root %q", roots, normalizeWorkspaceRootBestEffort(extra))
 	}
-	// /tmp is a default temp write root on POSIX only (see
-	// defaultTempWriteRootCandidatesForGOOS); on Windows the bare path resolves
-	// against the current drive, so a stray C:\tmp must not turn this on.
-	if runtime.GOOS != "windows" && pathExists("/tmp") && !stringSliceContains(roots, normalizeWorkspaceRootBestEffort("/tmp")) {
+	if pathExists("/tmp") && !stringSliceContains(roots, normalizeWorkspaceRootBestEffort("/tmp")) {
 		t.Fatalf("Roots()=%v want default /tmp write root", roots)
 	}
 }
@@ -143,16 +143,9 @@ const (
 )

 const (
-	EnforcementNative EnforcementLevel = "native"
-	// EnforcementUnelevated is the Windows-only middle tier used when the
-	// elevated `zero sandbox setup` has not run: commands still wrap through the
-	// command runner with a write-restricted token and workspace ACLs (which the
-	// runner can apply without Administrator rights), but the WFP network
-	// filters are absent, so network isolation stays with the in-process
-	// approval gate.
-	EnforcementUnelevated EnforcementLevel = "unelevated"
-	EnforcementDegraded   EnforcementLevel = "degraded"
-	EnforcementDisabled   EnforcementLevel = "disabled"
+	EnforcementNative   EnforcementLevel = "native"
+	EnforcementDegraded EnforcementLevel = "degraded"
+	EnforcementDisabled EnforcementLevel = "disabled"
 )

 type Policy struct {
@@ -8,21 +8,14 @@ import (
 )

 func runWindowsSandboxCommand(config WindowsSandboxCommandConfig, stderr io.Writer) int {
-	switch config.SandboxLevel {
-	case WindowsSandboxLevelRestrictedToken:
-		if err := ValidateWindowsSandboxSetupMarker(WindowsSandboxSetupConfigFromCommand(config)); err != nil {
-			fmt.Fprintln(stderr, WindowsSandboxCommandRunnerName+": "+err.Error())
-			return 1
-		}
-	case WindowsSandboxLevelUnelevated:
-		if err := ensureWindowsUnelevatedSetup(config); err != nil {
-			fmt.Fprintln(stderr, WindowsSandboxCommandRunnerName+": "+err.Error())
-			return 1
-		}
-	default:
+	if config.SandboxLevel != WindowsSandboxLevelRestrictedToken {
 		fmt.Fprintf(stderr, "%s: unsupported Windows sandbox level %q\n", WindowsSandboxCommandRunnerName, config.SandboxLevel)
 		return 1
 	}
+	if err := ValidateWindowsSandboxSetupMarker(WindowsSandboxSetupConfigFromCommand(config)); err != nil {
+		fmt.Fprintln(stderr, WindowsSandboxCommandRunnerName+": "+err.Error())
+		return 1
+	}
 	if err := ValidateWindowsNetworkPolicy(config.PermissionProfile.Network); err != nil {
 		fmt.Fprintln(stderr, WindowsSandboxCommandRunnerName+": "+err.Error())
 		return 1
@@ -64,32 +57,3 @@ func runWindowsSandboxCommand(config WindowsSandboxCommandConfig, stderr io.Writ
 	}
 	return exitCode
 }
-
-// ensureWindowsUnelevatedSetup applies the workspace ACL plan from the current
-// (non-elevated) process so the write-restricted token has somewhere its
-// capability SIDs are granted. DACL edits on user-owned workspace and temp
-// roots need no Administrator rights; the WFP network filters DO, so this tier
-// provisions no network enforcement — the offline-marker SID composed into the
-// token stays inert until an elevated `zero sandbox setup` installs the block
-// filters. Applied plans are recorded by hash so repeat commands skip the
-// re-apply; like the elevated setup, grants are left in place (the rollback is
-// deliberately discarded) because they only name synthetic capability SIDs
-// that no other token carries.
-func ensureWindowsUnelevatedSetup(config WindowsSandboxCommandConfig) error {
-	applied, plan, err := buildWindowsUnelevatedAppliedPlan(config)
-	if err != nil {
-		return err
-	}
-	marker, err := loadWindowsUnelevatedSetupMarker(config.SandboxHome)
-	if err != nil {
-		return err
-	}
-	if marker.contains(applied) {
-		return nil
-	}
-	if _, err := applyWindowsACLPlan(plan); err != nil {
-		return fmt.Errorf("apply unelevated workspace ACLs: %w — the workspace may be on a filesystem the current user does not own; "+
-			"run `zero sandbox setup` from an elevated (Administrator) terminal, or re-run with `--sandbox forbid` to skip OS sandboxing", err)
-	}
-	return recordWindowsUnelevatedAppliedPlan(config.SandboxHome, applied)
-}
@@ -2,16 +2,14 @@ package sandbox

 import (
 	"errors"
-	"strings"
 	"testing"
 )

-// On Windows, a not-yet-set-up sandbox must fall back to the UNELEVATED tier
-// (wrapped through the runner with the write-restricted token, network left to
-// the approval gate) on the default preference — never brick the command —
-// while a strict --sandbox require still errors with a setup hint. Once the
-// marker exists, enforcement is native and the command wraps.
-func TestWindowsFallsBackUnelevatedWhenSandboxNotInitialized(t *testing.T) {
+// On Windows, a not-yet-set-up sandbox must DEGRADE (run unwrapped with a
+// downgrade reason) on the default preference — never brick the command — while
+// a strict --sandbox require still errors with a setup hint. Once the marker
+// exists, enforcement is native and the command wraps.
+func TestWindowsDegradesWhenSandboxNotInitialized(t *testing.T) {
 	restore := windowsSandboxInitialized
 	t.Cleanup(func() { windowsSandboxInitialized = restore })

@@ -26,70 +24,13 @@ func TestWindowsFallsBackUnelevatedWhenSandboxNotInitialized(t *testing.T) {
 		ValidateExecution: true,
 	}

-	// Marker missing + auto -> unelevated tier: still wrapped, with a reason
-	// documenting the missing network enforcement, no error.
+	// Marker missing + auto -> degrade (unwrapped, with a reason), no error.
 	windowsSandboxInitialized = func() bool { return false }
 	auto := base
 	auto.Preference = SandboxPreferenceAuto
 	req, err := mgr.BuildExecutionRequest(auto)
 	if err != nil {
-		t.Fatalf("auto must fall back, not error: %v", err)
-	}
-	if req.EnforcementLevel != EnforcementUnelevated {
-		t.Fatalf("enforcement = %v, want unelevated", req.EnforcementLevel)
-	}
-	if !req.CommandWrapped {
-		t.Fatal("unelevated command must still be wrapped through the sandbox runner")
-	}
-	if req.DowngradeReason == "" || !strings.Contains(req.DowngradeReason, "network") {
-		t.Fatalf("downgrade reason = %q, want an explanation of the missing network enforcement", req.DowngradeReason)
-	}
-
-	// Marker missing + require -> hard error pointing at setup.
-	require := base
-	require.Preference = SandboxPreferenceRequire
-	if _, err := mgr.BuildExecutionRequest(require); !errors.Is(err, errWindowsSandboxNotInitialized) {
-		t.Fatalf("require must error with the setup hint, got %v", err)
-	}
-
-	// Marker present -> native, wrapped, no downgrade reason.
-	windowsSandboxInitialized = func() bool { return true }
-	req, err = mgr.BuildExecutionRequest(auto)
-	if err != nil {
-		t.Fatalf("initialized auto: %v", err)
-	}
-	if req.EnforcementLevel != EnforcementNative || !req.CommandWrapped {
-		t.Fatalf("initialized -> native wrapped, got enforcement=%v wrapped=%v", req.EnforcementLevel, req.CommandWrapped)
-	}
-	if req.DowngradeReason != "" {
-		t.Fatalf("native downgrade reason = %q, want empty", req.DowngradeReason)
-	}
-}
-
-// A profile that needs the platform sandbox ONLY for network isolation gains
-// nothing from the unelevated tier (which cannot enforce network), so it must
-// keep the old degrade-to-policy-gate behavior.
-func TestWindowsNetworkOnlyProfileStillDegradesWhenNotInitialized(t *testing.T) {
-	restore := windowsSandboxInitialized
-	t.Cleanup(func() { windowsSandboxInitialized = restore })
-	windowsSandboxInitialized = func() bool { return false }
-
-	mgr := NewSandboxManager(SandboxManagerOptions{
-		GOOS:    "windows",
-		Backend: Backend{Name: BackendWindowsRestrictedToken, Available: true, Executable: "zero.exe", Platform: "windows"},
-	})
-	req, err := mgr.BuildExecutionRequest(SandboxManagerRequest{
-		WorkspaceRoot: `C:\ws`,
-		Command:       CommandSpec{Name: "bash", Args: []string{"-c", "echo hi"}},
-		Policy:        DefaultPolicy(),
-		Profile: PermissionProfile{
-			FileSystem: FileSystemPolicy{Kind: FileSystemUnrestricted, IncludePlatformRoots: true, AllowTemp: true},
-			Network:    NetworkPolicy{Mode: NetworkDeny},
-		},
-		Preference: SandboxPreferenceAuto,
-	})
-	if err != nil {
-		t.Fatalf("network-only profile must degrade, not error: %v", err)
+		t.Fatalf("auto must degrade, not error: %v", err)
 	}
 	if req.EnforcementLevel != EnforcementDegraded {
 		t.Fatalf("enforcement = %v, want degraded", req.EnforcementLevel)
@@ -100,4 +41,21 @@ func TestWindowsNetworkOnlyProfileStillDegradesWhenNotInitialized(t *testing.T)
 	if req.DowngradeReason == "" {
 		t.Fatal("expected a downgrade reason explaining the missing setup")
 	}
+
+	// Marker missing + require -> hard error pointing at setup.
+	require := base
+	require.Preference = SandboxPreferenceRequire
+	if _, err := mgr.BuildExecutionRequest(require); !errors.Is(err, errWindowsSandboxNotInitialized) {
+		t.Fatalf("require must error with the setup hint, got %v", err)
+	}
+
+	// Marker present -> native, wrapped.
+	windowsSandboxInitialized = func() bool { return true }
+	req, err = mgr.BuildExecutionRequest(auto)
+	if err != nil {
+		t.Fatalf("initialized auto: %v", err)
+	}
+	if req.EnforcementLevel != EnforcementNative || !req.CommandWrapped {
+		t.Fatalf("initialized -> native wrapped, got enforcement=%v wrapped=%v", req.EnforcementLevel, req.CommandWrapped)
+	}
 }
@@ -87,20 +87,11 @@ func windowsCommandLine(args []string) (string, error) {
 	if len(args) == 0 {
 		return "", errorsNewWindowsProcess("missing command")
 	}
+	out := make([]string, 0, len(args))
 	for _, arg := range args {
 		if strings.ContainsRune(arg, 0) {
 			return "", errorsNewWindowsProcess("command argument contains NUL")
 		}
-	}
-	// Zero's cmd.exe shell invocation needs its final element (the shell
-	// command text) reaching cmd.exe raw, not escaped like a normal argv
-	// element: see WindowsShellCommandLine for why. Every other command this
-	// runner might launch is escaped normally below.
-	if commandLine, ok := windowsShellCommandLineFromArgs(args); ok {
-		return commandLine, nil
-	}
-	out := make([]string, 0, len(args))
-	for _, arg := range args {
 		out = append(out, syscall.EscapeArg(arg))
 	}
 	return strings.Join(out, " "), nil
@@ -95,66 +95,10 @@ type WindowsSandboxLevel string

 const (
 	WindowsSandboxLevelRestrictedToken WindowsSandboxLevel = "restricted-token"
-	// WindowsSandboxLevelUnelevated is the restricted-token tier without the
-	// elevated setup: the runner applies the workspace ACL plan itself before
-	// launching (no Administrator rights needed) and skips the elevated setup
-	// marker check. Network is NOT enforced at this level — the WFP filters need
-	// the elevated setup — so callers must keep network behind the approval gate.
-	WindowsSandboxLevelUnelevated WindowsSandboxLevel = "unelevated"
-	WindowsSandboxLevelElevated   WindowsSandboxLevel = "elevated"
-	WindowsSandboxLevelDisabled   WindowsSandboxLevel = "disabled"
+	WindowsSandboxLevelElevated        WindowsSandboxLevel = "elevated"
+	WindowsSandboxLevelDisabled        WindowsSandboxLevel = "disabled"
 )

-// WindowsShellArgs returns cmd.exe's argv (after the executable name) for
-// running commandText as a shell command on Windows: no wrapping quotes and
-// no /S, so commandText reaches cmd.exe's own /C remainder parsing exactly as
-// written. See WindowsShellCommandLine for why that matters. Used both as
-// CommandSpec.Args for the plain (unwrapped) path and, via
-// windowsShellCommandLineFromArgs, to recognize this same shape once it has
-// round-tripped through the sandboxed runner's CLI argv.
-func WindowsShellArgs(commandText string) []string {
-	return []string{"/d", "/c", commandText}
-}
-
-// WindowsShellCommandLine builds the raw command line a Windows CreateProcess
-// call should receive to run commandText as a shell command: "cmd.exe /d /c "
-// followed by commandText completely unescaped.
-//
-// cmd.exe's own /C remainder parsing is not CommandLineToArgvW-compatible: it
-// applies its own quote-stripping heuristic (documented in `cmd /?`) whenever
-// the remainder starts with a literal quote, and that heuristic does not
-// understand backslash-escaped inner quotes the way a normal argv consumer
-// would. A command like `python -c "print(15 / 3)"` passed through the
-// standard exec.Cmd Args mechanism gets wrapped in an outer pair of quotes
-// (because it contains spaces) with its own quotes escaped as \" — exactly
-// the shape that heuristic corrupts, stripping the outer quotes but leaving
-// the literal backslashes behind. Passing commandText through raw, exactly as
-// the model wrote it, means cmd.exe parses it the same way it would if typed
-// directly at an interactive prompt: a leading quoted executable path like
-// `"C:\Program Files\foo.exe" arg` is preserved correctly by cmd.exe's own
-// quote-preserving special case, and a command with no leading quote at all,
-// like the python example above, is never touched by the stripping heuristic
-// in the first place.
-func WindowsShellCommandLine(commandText string) string {
-	return "cmd.exe /d /c " + commandText
-}
-
-// windowsShellCommandLineFromArgs reports whether args is exactly
-// ["cmd.exe"]+WindowsShellArgs(text) for some text and, if so, returns
-// WindowsShellCommandLine's result for that text. The sandboxed runner path
-// only has the deserialized argv (WindowsSandboxCommandConfig.Command) to
-// work from, not the original commandText, so it recovers the raw command
-// line by recognizing the shape instead.
-func windowsShellCommandLineFromArgs(args []string) (string, bool) {
-	if len(args) != 4 {
-		return "", false
-	}
-	if !strings.EqualFold(args[0], "cmd.exe") || args[1] != "/d" || args[2] != "/c" {
-		return "", false
-	}
-	return WindowsShellCommandLine(args[3]), true
-}
-
 type WindowsSandboxCommandArgsOptions struct {
 	SandboxHome       string
 	CommandCWD        string
@@ -327,20 +271,13 @@ func windowsRestrictedTokenCommandPlan(execRequest SandboxExecutionRequest, poli
 		return CommandPlan{}, err
 	}
 	childEnv := windowsSandboxChildEnv(spec.Env, policy, execRequest.WorkspaceRoot)
-	// The unelevated enforcement tier maps to the runner's unelevated level: same
-	// restricted token, but the runner applies the workspace ACLs itself instead
-	// of requiring the elevated setup marker.
-	level := WindowsSandboxLevelRestrictedToken
-	if execRequest.EnforcementLevel == EnforcementUnelevated {
-		level = WindowsSandboxLevelUnelevated
-	}
 	args, err := BuildWindowsSandboxCommandArgs(WindowsSandboxCommandArgsOptions{
 		SandboxHome:       sandboxHome,
 		CommandCWD:        spec.Dir,
 		WorkspaceRoots:    []string{execRequest.WorkspaceRoot},
 		PermissionProfile: execRequest.PermissionProfile,
 		Env:               childEnv,
-		SandboxLevel:      level,
+		SandboxLevel:      WindowsSandboxLevelRestrictedToken,
 		Command:           append([]string{spec.Name}, spec.Args...),
 	})
 	if err != nil {
@@ -444,7 +381,7 @@ func nextWindowsSandboxFlagValue(args []string, index int) (string, int, error)

 func validWindowsSandboxLevel(level WindowsSandboxLevel) bool {
 	switch level {
-	case WindowsSandboxLevelRestrictedToken, WindowsSandboxLevelUnelevated, WindowsSandboxLevelElevated, WindowsSandboxLevelDisabled:
+	case WindowsSandboxLevelRestrictedToken, WindowsSandboxLevelElevated, WindowsSandboxLevelDisabled:
 		return true
 	default:
 		return false
@@ -147,56 +147,3 @@ func TestRunWindowsSandboxCommandRunnerRejectsInvalidArgs(t *testing.T) {
 		t.Fatalf("stderr = %q, want runner name", stderr.String())
 	}
 }
-
-func TestWindowsShellArgsHasNoSAndKeepsCommandTextWhole(t *testing.T) {
-	args := WindowsShellArgs(`python -c "print(15 / 3)"`)
-	want := []string{"/d", "/c", `python -c "print(15 / 3)"`}
-	if len(args) != len(want) {
-		t.Fatalf("args = %#v, want %#v", args, want)
-	}
-	for index := range want {
-		if args[index] != want[index] {
-			t.Fatalf("args = %#v, want %#v", args, want)
-		}
-	}
-}
-
-func TestWindowsShellCommandLineLeavesCommandTextUnescaped(t *testing.T) {
-	// The whole point of this function: commandText's own quotes must reach
-	// cmd.exe exactly as written, not re-quoted or backslash-escaped the way
-	// a normal argv-escaping function (like syscall.EscapeArg) would treat an
-	// argument containing spaces and embedded quotes.
-	commandText := `python -c "print(15 / 3)"`
-	got := WindowsShellCommandLine(commandText)
-	want := `cmd.exe /d /c python -c "print(15 / 3)"`
-	if got != want {
-		t.Fatalf("WindowsShellCommandLine = %q, want %q", got, want)
-	}
-}
-
-func TestWindowsShellCommandLineFromArgsRecognizesTheShellShape(t *testing.T) {
-	commandLine, ok := windowsShellCommandLineFromArgs([]string{"cmd.exe", "/d", "/c", `echo "hi"`})
-	if !ok {
-		t.Fatal("windowsShellCommandLineFromArgs did not recognize the shell shape")
-	}
-	if want := `cmd.exe /d /c echo "hi"`; commandLine != want {
-		t.Fatalf("commandLine = %q, want %q", commandLine, want)
-	}
-}
-
-func TestWindowsShellCommandLineFromArgsRejectsOtherShapes(t *testing.T) {
-	cases := [][]string{
-		nil,
-		{"cmd.exe"},
-		{"cmd.exe", "/d", "/c"},
-		{"cmd.exe", "/d", "/c", "echo hi", "extra"},
-		{"git.exe", "/d", "/c", "echo hi"},
-		{"cmd.exe", "/s", "/c", "echo hi"},
-		{"cmd.exe", "/d", "/k", "echo hi"},
-	}
-	for _, args := range cases {
-		if _, ok := windowsShellCommandLineFromArgs(args); ok {
-			t.Fatalf("windowsShellCommandLineFromArgs(%#v) matched, want no match", args)
-		}
-	}
-}
@@ -1,146 +0,0 @@
-package sandbox
-
-import (
-	"encoding/json"
-	"errors"
-	"fmt"
-	"os"
-	"path/filepath"
-	"strings"
-)
-
-const windowsUnelevatedSetupMarkerSchemaVersion = 1
-
-// windowsUnelevatedSetupMarkerMaxPlans bounds the applied-plan history so the
-// marker cannot grow without limit when a user hops between many workspaces.
-// Oldest entries are dropped first; re-applying an already-granted plan is
-// harmless, so eviction only costs a redundant ACL apply.
-const windowsUnelevatedSetupMarkerMaxPlans = 64
-
-// WindowsUnelevatedAppliedPlan fingerprints one workspace ACL plan the
-// unelevated tier has applied. Unlike the elevated setup marker it carries no
-// network infrastructure hash: the unelevated tier never provisions WFP
-// filters, so there is nothing network-side to fingerprint.
-type WindowsUnelevatedAppliedPlan struct {
-	ACLPlanHash    string `json:"aclPlanHash"`
-	ACLPlanEntries int    `json:"aclPlanEntries"`
-}
-
-// WindowsUnelevatedSetupMarker records which workspace ACL plans the command
-// runner has applied without elevation, keyed by plan hash, so repeat commands
-// in a known workspace skip the re-apply. One file serves every workspace under
-// a sandbox home (the elevated marker is instead a single-plan snapshot,
-// because its WFP half genuinely is machine-global).
-type WindowsUnelevatedSetupMarker struct {
-	SchemaVersion int                            `json:"schemaVersion"`
-	AppliedPlans  []WindowsUnelevatedAppliedPlan `json:"appliedPlans,omitempty"`
-}
-
-func WindowsUnelevatedSetupMarkerPath(sandboxHome string) string {
-	return filepath.Join(filepath.Clean(sandboxHome), "windows-unelevated-setup.json")
-}
-
-// buildWindowsUnelevatedAppliedPlan derives the ACL plan for the command's
-// permission profile plus its marker fingerprint. The same BuildWindowsACLPlan
-// output later feeds the apply step, so the fingerprint and the applied grants
-// can never drift apart.
-func buildWindowsUnelevatedAppliedPlan(config WindowsSandboxCommandConfig) (WindowsUnelevatedAppliedPlan, WindowsACLPlan, error) {
-	plan, err := BuildWindowsACLPlan(config)
-	if err != nil {
-		return WindowsUnelevatedAppliedPlan{}, WindowsACLPlan{}, err
-	}
-	hash, err := WindowsACLPlanHash(plan)
-	if err != nil {
-		return WindowsUnelevatedAppliedPlan{}, WindowsACLPlan{}, err
-	}
-	return WindowsUnelevatedAppliedPlan{
-		ACLPlanHash:    hash,
-		ACLPlanEntries: len(plan.Entries),
-	}, plan, nil
-}
-
-// loadWindowsUnelevatedSetupMarker reads the marker; a missing file is the
-// common first-run state and returns an empty marker, not an error. A marker
-// with an unexpected schema version or a corrupt/truncated body is likewise
-// treated as empty so the runner re-applies (and rewrites) rather than failing:
-// the marker only memoizes idempotent ACL applies, so resetting it can only
-// cost redundant work, never skip enforcement.
-func loadWindowsUnelevatedSetupMarker(sandboxHome string) (WindowsUnelevatedSetupMarker, error) {
-	sandboxHome = strings.TrimSpace(sandboxHome)
-	if sandboxHome == "" {
-		return WindowsUnelevatedSetupMarker{}, errors.New("windows sandbox home is required")
-	}
-	path := WindowsUnelevatedSetupMarkerPath(sandboxHome)
-	bytes, err := os.ReadFile(path)
-	if err != nil {
-		if errors.Is(err, os.ErrNotExist) {
-			return WindowsUnelevatedSetupMarker{SchemaVersion: windowsUnelevatedSetupMarkerSchemaVersion}, nil
-		}
-		return WindowsUnelevatedSetupMarker{}, fmt.Errorf("read windows unelevated setup marker: %w", err)
-	}
-	var marker WindowsUnelevatedSetupMarker
-	if err := json.Unmarshal(bytes, &marker); err != nil {
-		return WindowsUnelevatedSetupMarker{SchemaVersion: windowsUnelevatedSetupMarkerSchemaVersion}, nil
-	}
-	if marker.SchemaVersion != windowsUnelevatedSetupMarkerSchemaVersion {
-		return WindowsUnelevatedSetupMarker{SchemaVersion: windowsUnelevatedSetupMarkerSchemaVersion}, nil
-	}
-	return marker, nil
-}
-
-func (marker WindowsUnelevatedSetupMarker) contains(applied WindowsUnelevatedAppliedPlan) bool {
-	if strings.TrimSpace(applied.ACLPlanHash) == "" {
-		return false
-	}
-	for _, plan := range marker.AppliedPlans {
-		if plan.ACLPlanHash == applied.ACLPlanHash && plan.ACLPlanEntries == applied.ACLPlanEntries {
-			return true
-		}
-	}
-	return false
-}
-
-// recordWindowsUnelevatedAppliedPlan appends the plan to the marker (dropping
-// the oldest entries past the cap) and writes it atomically, following the
-// temp-file-then-rename pattern of the sibling marker writers.
-func recordWindowsUnelevatedAppliedPlan(sandboxHome string, applied WindowsUnelevatedAppliedPlan) error {
-	marker, err := loadWindowsUnelevatedSetupMarker(sandboxHome)
-	if err != nil {
-		return err
-	}
-	if marker.contains(applied) {
-		return nil
-	}
-	marker.SchemaVersion = windowsUnelevatedSetupMarkerSchemaVersion
-	marker.AppliedPlans = append(marker.AppliedPlans, applied)
-	if overflow := len(marker.AppliedPlans) - windowsUnelevatedSetupMarkerMaxPlans; overflow > 0 {
-		marker.AppliedPlans = append([]WindowsUnelevatedAppliedPlan(nil), marker.AppliedPlans[overflow:]...)
-	}
-	path := WindowsUnelevatedSetupMarkerPath(sandboxHome)
-	if err := os.MkdirAll(filepath.Dir(path), 0o700); err != nil {
-		return fmt.Errorf("create windows unelevated setup marker dir: %w", err)
-	}
-	bytes, err := json.MarshalIndent(marker, "", "  ")
-	if err != nil {
-		return fmt.Errorf("marshal windows unelevated setup marker: %w", err)
-	}
-	tmp, err := os.CreateTemp(filepath.Dir(path), ".windows-unelevated-setup-*.tmp")
-	if err != nil {
-		return fmt.Errorf("create windows unelevated setup marker temp file: %w", err)
-	}
-	tmpPath := tmp.Name()
-	if _, err := tmp.Write(bytes); err != nil {
-		_ = tmp.Close()
-		_ = os.Remove(tmpPath)
-		return fmt.Errorf("write windows unelevated setup marker temp file: %w", err)
-	}
-	if err := tmp.Close(); err != nil {
-		_ = os.Remove(tmpPath)
-		return fmt.Errorf("close windows unelevated setup marker temp file: %w", err)
-	}
-	if err := os.Rename(tmpPath, path); err != nil {
-		_ = os.Remove(tmpPath)
-		return fmt.Errorf("replace windows unelevated setup marker: %w", err)
-	}
-	return nil
-}
@@ -1,189 +0,0 @@
-package sandbox
-
-import (
-	"fmt"
-	"os"
-	"path/filepath"
-	"testing"
-)
-
-func testWindowsUnelevatedCommandConfig(t *testing.T) WindowsSandboxCommandConfig {
-	t.Helper()
-	root := t.TempDir()
-	return WindowsSandboxCommandConfig{
-		SandboxHome:    filepath.Join(root, ".zero-sandbox"),
-		CommandCWD:     root,
-		WorkspaceRoots: []string{root},
-		PermissionProfile: PermissionProfile{
-			FileSystem: FileSystemPolicy{
-				Kind:       FileSystemRestricted,
-				ReadRoots:  []string{root},
-				WriteRoots: []WritableRoot{{Root: root, ProtectedMetadataNames: []string{".git", ".zero", ".agents"}}},
-				AllowTemp:  true,
-			},
-			Network: NetworkPolicy{Mode: NetworkDeny},
-		},
-		SandboxLevel: WindowsSandboxLevelUnelevated,
-		Command:      []string{"cmd.exe", "/c", "echo hi"},
-	}
-}
-
-func TestWindowsSandboxCommandArgsRoundTripUnelevatedLevel(t *testing.T) {
-	config := testWindowsUnelevatedCommandConfig(t)
-	args, err := BuildWindowsSandboxCommandArgs(WindowsSandboxCommandArgsOptions{
-		SandboxHome:       config.SandboxHome,
-		CommandCWD:        config.CommandCWD,
-		WorkspaceRoots:    config.WorkspaceRoots,
-		PermissionProfile: config.PermissionProfile,
-		SandboxLevel:      WindowsSandboxLevelUnelevated,
-		Command:           config.Command,
-	})
-	if err != nil {
-		t.Fatalf("BuildWindowsSandboxCommandArgs: %v", err)
-	}
-	parsed, err := ParseWindowsSandboxCommandArgs(args)
-	if err != nil {
-		t.Fatalf("ParseWindowsSandboxCommandArgs: %v", err)
-	}
-	if parsed.SandboxLevel != WindowsSandboxLevelUnelevated {
-		t.Fatalf("round-tripped sandbox level = %q, want %q", parsed.SandboxLevel, WindowsSandboxLevelUnelevated)
-	}
-}
-
-func TestBuildWindowsUnelevatedAppliedPlanFingerprint(t *testing.T) {
-	config := testWindowsUnelevatedCommandConfig(t)
-	applied, plan, err := buildWindowsUnelevatedAppliedPlan(config)
-	if err != nil {
-		t.Fatalf("buildWindowsUnelevatedAppliedPlan: %v", err)
-	}
-	if applied.ACLPlanHash == "" || applied.ACLPlanEntries == 0 || applied.ACLPlanEntries != len(plan.Entries) {
-		t.Fatalf("applied plan = %+v with %d plan entries, want a non-empty consistent fingerprint", applied, len(plan.Entries))
-	}
-	// Same config -> same fingerprint (the marker's dedupe key).
-	again, _, err := buildWindowsUnelevatedAppliedPlan(config)
-	if err != nil {
-		t.Fatalf("rebuild: %v", err)
-	}
-	if again != applied {
-		t.Fatalf("fingerprint not stable: %+v then %+v", applied, again)
-	}
-	// An unrestricted profile has no ACL plan to apply and must error.
-	config.PermissionProfile.FileSystem.Kind = FileSystemUnrestricted
-	if _, _, err := buildWindowsUnelevatedAppliedPlan(config); err == nil {
-		t.Fatal("expected an error for an unrestricted filesystem profile")
-	}
-}
-
-func TestWindowsUnelevatedSetupMarkerRecordAndLoad(t *testing.T) {
-	config := testWindowsUnelevatedCommandConfig(t)
-	applied, _, err := buildWindowsUnelevatedAppliedPlan(config)
-	if err != nil {
-		t.Fatalf("buildWindowsUnelevatedAppliedPlan: %v", err)
-	}
-
-	// Missing marker file is the fresh-install state: empty, no error, no match.
-	marker, err := loadWindowsUnelevatedSetupMarker(config.SandboxHome)
-	if err != nil {
-		t.Fatalf("load missing marker: %v", err)
-	}
-	if marker.contains(applied) {
-		t.Fatal("empty marker must not contain the plan")
-	}
-
-	if err := recordWindowsUnelevatedAppliedPlan(config.SandboxHome, applied); err != nil {
-		t.Fatalf("record: %v", err)
-	}
-	marker, err = loadWindowsUnelevatedSetupMarker(config.SandboxHome)
-	if err != nil {
-		t.Fatalf("load recorded marker: %v", err)
-	}
-	if !marker.contains(applied) || len(marker.AppliedPlans) != 1 {
-		t.Fatalf("marker = %+v, want exactly the recorded plan", marker)
-	}
-
-	// Recording the same plan again must not duplicate it.
-	if err := recordWindowsUnelevatedAppliedPlan(config.SandboxHome, applied); err != nil {
-		t.Fatalf("re-record: %v", err)
-	}
-	marker, err = loadWindowsUnelevatedSetupMarker(config.SandboxHome)
-	if err != nil {
-		t.Fatalf("reload marker: %v", err)
-	}
-	if len(marker.AppliedPlans) != 1 {
-		t.Fatalf("marker has %d plans after duplicate record, want 1", len(marker.AppliedPlans))
-	}
-}
-
-func TestWindowsUnelevatedSetupMarkerEvictsOldestPastCap(t *testing.T) {
-	home := filepath.Join(t.TempDir(), ".zero-sandbox")
-	first := WindowsUnelevatedAppliedPlan{ACLPlanHash: "hash-0", ACLPlanEntries: 1}
-	if err := recordWindowsUnelevatedAppliedPlan(home, first); err != nil {
-		t.Fatalf("record first: %v", err)
-	}
-	for index := 1; index <= windowsUnelevatedSetupMarkerMaxPlans; index++ {
-		plan := WindowsUnelevatedAppliedPlan{ACLPlanHash: fmt.Sprintf("hash-%d", index), ACLPlanEntries: index}
-		if err := recordWindowsUnelevatedAppliedPlan(home, plan); err != nil {
-			t.Fatalf("record %d: %v", index, err)
-		}
-	}
-	marker, err := loadWindowsUnelevatedSetupMarker(home)
-	if err != nil {
-		t.Fatalf("load: %v", err)
-	}
-	if len(marker.AppliedPlans) != windowsUnelevatedSetupMarkerMaxPlans {
-		t.Fatalf("marker has %d plans, want the cap of %d", len(marker.AppliedPlans), windowsUnelevatedSetupMarkerMaxPlans)
-	}
-	if marker.contains(first) {
-		t.Fatal("oldest plan should have been evicted past the cap")
-	}
-}
-
-func TestLoadWindowsUnelevatedSetupMarkerSelfHealsCorruptFile(t *testing.T) {
-	home := filepath.Join(t.TempDir(), ".zero-sandbox")
-	if err := os.MkdirAll(home, 0o700); err != nil {
-		t.Fatalf("mkdir sandbox home: %v", err)
-	}
-	path := WindowsUnelevatedSetupMarkerPath(home)
-	// A truncated body must reset like an unknown schema, not brick every
-	// unelevated command until the file is hand-deleted.
-	if err := os.WriteFile(path, []byte(`{"schemaVersion":1,"appliedPlans":[{"aclPlanHash":"h`), 0o600); err != nil {
-		t.Fatalf("write corrupt marker: %v", err)
-	}
-	marker, err := loadWindowsUnelevatedSetupMarker(home)
-	if err != nil {
-		t.Fatalf("corrupt marker must self-heal, got error: %v", err)
-	}
-	if len(marker.AppliedPlans) != 0 || marker.SchemaVersion != windowsUnelevatedSetupMarkerSchemaVersion {
-		t.Fatalf("corrupt marker must reset to empty current-schema marker, got %+v", marker)
-	}
-	// The healed marker must accept new recordings over the corrupt file.
-	applied := WindowsUnelevatedAppliedPlan{ACLPlanHash: "hash-heal", ACLPlanEntries: 2}
-	if err := recordWindowsUnelevatedAppliedPlan(home, applied); err != nil {
-		t.Fatalf("record over corrupt marker: %v", err)
-	}
-	marker, err = loadWindowsUnelevatedSetupMarker(home)
-	if err != nil {
-		t.Fatalf("reload healed marker: %v", err)
-	}
-	if !marker.contains(applied) {
-		t.Fatalf("healed marker = %+v, want the recorded plan", marker)
-	}
-}
-
-func TestLoadWindowsUnelevatedSetupMarkerResetsUnknownSchema(t *testing.T) {
-	home := filepath.Join(t.TempDir(), ".zero-sandbox")
-	if err := os.MkdirAll(home, 0o700); err != nil {
-		t.Fatalf("mkdir sandbox home: %v", err)
-	}
-	path := WindowsUnelevatedSetupMarkerPath(home)
-	if err := os.WriteFile(path, []byte(`{"schemaVersion":99,"appliedPlans":[{"aclPlanHash":"h","aclPlanEntries":1}]}`), 0o600); err != nil {
-		t.Fatalf("write marker: %v", err)
-	}
-	marker, err := loadWindowsUnelevatedSetupMarker(home)
-	if err != nil {
-		t.Fatalf("load: %v", err)
-	}
-	if len(marker.AppliedPlans) != 0 || marker.SchemaVersion != windowsUnelevatedSetupMarkerSchemaVersion {
-		t.Fatalf("unknown schema must reset to empty current-schema marker, got %+v", marker)
-	}
-}
@@ -160,7 +160,10 @@ func FormatExecPrompt(prompt string, prepared PreparedExec) string {
 	if prepared.Mode == ModeNew || len(prepared.ContextEvents) == 0 {
 		return prompt
 	}
-	events := promptContextEvents(prepared.ContextEvents)
+	events := prepared.ContextEvents
+	if len(events) > 20 {
+		events = events[len(events)-20:]
+	}

 	lines := []string{}
 	for _, event := range events {
@@ -184,25 +187,6 @@ func FormatExecPrompt(prompt string, prepared PreparedExec) string {
 	}, "\n")
 }

-func promptContextEvents(events []Event) []Event {
-	const maxPromptContextEvents = 80
-
-	filtered := make([]Event, 0, len(events))
-	for _, event := range events {
-		switch event.Type {
-		case EventMessage, EventCompaction, EventSessionFork, EventSessionChild, EventSpecialistStart, EventSpecialistStop, EventError:
-			filtered = append(filtered, event)
-		}
-	}
-	if len(filtered) == 0 {
-		filtered = append(filtered, events...)
-	}
-	if len(filtered) > maxPromptContextEvents {
-		filtered = filtered[len(filtered)-maxPromptContextEvents:]
-	}
-	return filtered
-}
-
 func forkTitle(title string) string {
 	if title == "" {
 		return ""
@@ -71,7 +71,7 @@ type CompactionPayload struct {
 	Truncated                bool       `json:"truncated,omitempty"`
 }

-const defaultCompactionPreserveLast = 6
+const defaultCompactionPreserveLast = 8
 const defaultCompactionMaxPromptChars = 8000

 func (store *Store) PlanRewind(sessionID string, options RewindOptions) (RewindPlan, error) {
@@ -555,91 +555,6 @@ func TestPrepareExecSessionResolvesResumeAndFork(t *testing.T) {
 	}
 }

-func TestFormatExecPromptKeepsConversationMessagesWhenNoisyEventsFollow(t *testing.T) {
-	events := []Event{
-		{Sequence: 1, Type: EventMessage, Payload: json.RawMessage(`{"role":"user","content":"first user request"}`)},
-		{Sequence: 2, Type: EventMessage, Payload: json.RawMessage(`{"role":"assistant","content":"first assistant answer"}`)},
-	}
-	for sequence := 3; sequence <= 45; sequence++ {
-		events = append(events, Event{Sequence: sequence, Type: EventToolResult, Payload: json.RawMessage(`{"name":"read_file","output":"noisy tool result"}`)})
-	}
-	events = append(events, Event{Sequence: 46, Type: EventMessage, Payload: json.RawMessage(`{"role":"user","content":"latest user request"}`)})
-
-	prompt := FormatExecPrompt("continue", PreparedExec{
-		Mode:          ModeResume,
-		Session:       Metadata{SessionID: "session-with-noise"},
-		ContextEvents: events,
-	})
-
-	for _, want := range []string{"first user request", "first assistant answer", "latest user request", "Current user request:", "continue"} {
-		if !strings.Contains(prompt, want) {
-			t.Fatalf("expected prompt to contain %q, got %q", want, prompt)
-		}
-	}
-	if strings.Contains(prompt, "noisy tool result") {
-		t.Fatalf("expected prompt to omit noisy non-conversation events, got %q", prompt)
-	}
-}
-
-func TestFormatExecPromptTruncatesConversationMessagesAfterFilteringNoise(t *testing.T) {
-	events := make([]Event, 0, 100)
-	for sequence := 1; sequence <= 85; sequence++ {
-		events = append(events, Event{
-			Sequence: sequence,
-			Type:     EventMessage,
-			Payload:  json.RawMessage(fmt.Sprintf(`{"role":"user","content":"conversation message %03d"}`, sequence)),
-		})
-		if sequence%10 == 0 {
-			events = append(events, Event{
-				Sequence: 1000 + sequence,
-				Type:     EventToolResult,
-				Payload:  json.RawMessage(fmt.Sprintf(`{"name":"read_file","output":"noisy tool result %03d"}`, sequence)),
-			})
-		}
-	}
-	events = append(events, Event{
-		Sequence: 2000,
-		Type:     EventToolResult,
-		Payload:  json.RawMessage(`{"name":"bash","output":"trailing noisy tool result"}`),
-	})
-
-	contextEvents := promptContextEvents(events)
-	if len(contextEvents) != 80 {
-		t.Fatalf("expected prompt context to keep 80 events, got %d", len(contextEvents))
-	}
-	if contextEvents[0].Sequence != 6 || contextEvents[len(contextEvents)-1].Sequence != 85 {
-		t.Fatalf("expected prompt context to keep message sequences 6-85, got first=%d last=%d", contextEvents[0].Sequence, contextEvents[len(contextEvents)-1].Sequence)
-	}
-
-	prompt := FormatExecPrompt("continue", PreparedExec{
-		Mode:          ModeResume,
-		Session:       Metadata{SessionID: "long-session-with-noise"},
-		ContextEvents: events,
-	})
-
-	if got, want := strings.Count(prompt, "- #"), len(contextEvents); got != want {
-		t.Fatalf("expected prompt to contain %d context event lines, got %d in %q", want, got, prompt)
-	}
-	for _, want := range []string{"conversation message 006", "conversation message 085", "Current user request:", "continue"} {
-		if !strings.Contains(prompt, want) {
-			t.Fatalf("expected prompt to contain %q, got %q", want, prompt)
-		}
-	}
-	for _, unwanted := range []string{
-		"conversation message 001",
-		"conversation message 002",
-		"conversation message 003",
-		"conversation message 004",
-		"conversation message 005",
-		"noisy tool result",
-		"trailing noisy tool result",
-	} {
-		if strings.Contains(prompt, unwanted) {
-			t.Fatalf("expected prompt to omit %q, got %q", unwanted, prompt)
-		}
-	}
-}
-
 func TestPrepareExecPersistsSpecialistMetadataForNewSession(t *testing.T) {
 	store := NewStore(StoreOptions{RootDir: t.TempDir(), Now: fixedClock("2026-06-04T14:30:00Z")})

@@ -25,7 +25,6 @@ import (
 const (
 	sessionTagSpecialist     = "specialist"
 	promptFileThresholdBytes = 4 * 1024
-	maxSpecialistDepth       = 8 // hard cap to prevent infinite recursion/resource exhaustion via Task
 )

 const SessionTagSpecialist = sessionTagSpecialist
@@ -219,13 +218,6 @@ func (executor Executor) Run(ctx context.Context, params TaskParameters, options
 	if options.CurrentDepth < 0 {
 		return ExecResult{}, fmt.Errorf("current depth cannot be negative")
 	}
-	// >= (not >): this Run call spawns a CHILD at options.CurrentDepth+1, so a
-	// parent already AT the cap must still be rejected here rather than being
-	// allowed to launch one more level before the child's own next call trips
-	// the guard.
-	if options.CurrentDepth >= maxSpecialistDepth {
-		return ExecResult{}, fmt.Errorf("spawning a specialist at depth %d would exceed maximum nesting depth %d", options.CurrentDepth+1, maxSpecialistDepth)
-	}
 	if strings.TrimSpace(params.Prompt) == "" {
 		return ExecResult{}, fmt.Errorf("specialist prompt is required")
 	}
@@ -1,7 +1,6 @@
 package specialist

 import (
-	"context"
 	"os"
 	"path/filepath"
 	"reflect"
@@ -337,39 +336,6 @@ func TestBuildArgsRejectsInvalidInputs(t *testing.T) {
 	}
 }

-func TestRunRejectsDepthExceedingMax(t *testing.T) {
-	_, err := (Executor{}).Run(context.Background(), TaskParameters{
-		Prompt: "hi",
-	}, TaskRunOptions{CurrentDepth: maxSpecialistDepth + 1})
-	if err == nil || !strings.Contains(err.Error(), "depth") {
-		t.Fatalf("Run error = %v, want depth error", err)
-	}
-}
-
-// TestRunRejectsDepthAtMax covers the boundary: a parent already AT the cap
-// must be rejected too, since this Run call would launch a child one level
-// past it (--depth CurrentDepth+1). Only checking ">" here would let that
-// child start before the guard ever caught it. The guard sits before the
-// fresh/resume branch in Run, so both call shapes must be proven to reject
-// here rather than falling through to runFresh/runResume.
-func TestRunRejectsDepthAtMax(t *testing.T) {
-	tests := []struct {
-		name   string
-		params TaskParameters
-	}{
-		{name: "fresh", params: TaskParameters{Prompt: "hi"}},
-		{name: "resume", params: TaskParameters{Prompt: "hi", Resume: "child_session"}},
-	}
-	for _, tc := range tests {
-		t.Run(tc.name, func(t *testing.T) {
-			_, err := (Executor{}).Run(context.Background(), tc.params, TaskRunOptions{CurrentDepth: maxSpecialistDepth})
-			if err == nil || !strings.Contains(err.Error(), "depth") {
-				t.Fatalf("Run error = %v, want depth error", err)
-			}
-		})
-	}
-}
-
 func TestBuildArgsRejectsInvalidSessionIDs(t *testing.T) {
 	_, err := (Executor{NewSessionID: func() (string, error) { return "../escape", nil }}).BuildArgs(BuildArgsInput{
 		Prompt: "hi",
@@ -120,6 +120,7 @@ func (tool bashTool) run(ctx context.Context, args map[string]any, engine *zeroS
 			Meta:   meta,
 		}
 	}
+	// Release any plan-scoped resources once the command has finished running.
 	defer plan.Cleanup()
 	addSandboxMeta(meta, plan)

@@ -220,14 +221,6 @@ func shellIssueBlockResult(issue shellIssue) Result {
 	}
 }

-// buildBashCommand returns the exec.Cmd and the sandbox plan for running
-// commandText. On Windows, when the command is not wrapped by the sandbox
-// engine (plan.Wrapped == false), it also overrides the child's raw command
-// line so commandText reaches cmd.exe unescaped; see
-// zeroSandbox.WindowsShellCommandLine for why that matters. The wrapped case
-// gets the same treatment inside the sandboxed runner process itself
-// (internal/sandbox/windows_process_windows.go), since that command line is
-// built there, not here.
 func buildBashCommand(ctx context.Context, commandText string, absoluteCwd string, engine *zeroSandbox.Engine) (*exec.Cmd, zeroSandbox.CommandPlan, error) {
 	spec := zeroSandbox.CommandSpec{
 		Name: shellExecutable(),
@@ -235,11 +228,7 @@ func buildBashCommand(ctx context.Context, commandText string, absoluteCwd strin
 		Dir:  absoluteCwd,
 	}
 	if engine != nil {
-		command, plan, err := engine.CommandContext(ctx, spec)
-		if err == nil {
-			applyWindowsShellCommandLine(command, commandText, plan.Wrapped)
-		}
-		return command, plan, err
+		return engine.CommandContext(ctx, spec)
 	}
 	plan := zeroSandbox.CommandPlan{
 		Backend: zeroSandbox.Backend{
@@ -253,7 +242,6 @@ func buildBashCommand(ctx context.Context, commandText string, absoluteCwd strin
 	}
 	command := exec.CommandContext(ctx, spec.Name, spec.Args...)
 	command.Dir = spec.Dir
-	applyWindowsShellCommandLine(command, commandText, plan.Wrapped)
 	return command, plan, nil
 }

@@ -314,7 +302,7 @@ func shellExecutable() string {

 func shellArguments(command string) []string {
 	if runtime.GOOS == "windows" {
-		return zeroSandbox.WindowsShellArgs(command)
+		return []string{"/d", "/s", "/c", command}
 	}
 	return []string{"-c", command}
 }
@@ -354,12 +342,7 @@ func formatBashOutput(stdout string, stderr string, exitCode int) string {
 	if len(parts) == 0 {
 		return "Command completed with no output."
 	}
-	// Cap the context cost of a verbose command at the same default budget as
-	// exec_command (head/tail window); the full output is spilled to disk and
-	// referenced in the truncation notice, so nothing is lost. Previously bash
-	// output was unbounded — one chatty build log could flood the context.
-	output, _ := truncateExecOutputSpill(strings.Join(parts, "\n"), defaultMaxOutputTokens, "bash")
-	return output
+	return strings.Join(parts, "\n")
 }

 func formatBashOutputWithShellHint(command string, stdout string, stderr string, exitCode int, meta map[string]string) string {
@@ -42,7 +42,3 @@ func hardenProcessLifetime(command *exec.Cmd) {
 		return nil
 	}
 }
-
-// applyWindowsShellCommandLine is a no-op outside Windows; there is no
-// cmd.exe command-line-parsing quirk to work around here.
-func applyWindowsShellCommandLine(command *exec.Cmd, commandText string, wrapped bool) {}
@@ -5,10 +5,7 @@ package tools
 import (
 	"os/exec"
 	"strconv"
-	"syscall"
 	"time"
-
-	zeroSandbox "github.com/Gitlawb/zero/internal/sandbox"
 )

 // bashWaitDelay bounds how long Wait blocks for the I/O pipes to drain after the
@@ -31,17 +28,3 @@ func hardenProcessLifetime(command *exec.Cmd) {
 		return nil
 	}
 }
-
-// applyWindowsShellCommandLine overrides command's raw child command line so
-// commandText reaches cmd.exe unescaped instead of auto-quoted the way
-// exec.Cmd would normally encode a single Args element. Skipped when wrapped
-// is true: the sandbox engine then routes execution through a separate
-// zero-windows-command-runner process, which builds its own child command
-// line from scratch (internal/sandbox/windows_process_windows.go) rather than
-// inheriting whatever this outer exec.Cmd is configured with.
-func applyWindowsShellCommandLine(command *exec.Cmd, commandText string, wrapped bool) {
-	if wrapped {
-		return
-	}
-	command.SysProcAttr = &syscall.SysProcAttr{CmdLine: zeroSandbox.WindowsShellCommandLine(commandText)}
-}
@@ -17,18 +17,6 @@ import (

 func TestMain(m *testing.M) {
 	if len(os.Args) >= 3 && os.Args[1] == "--zero-bash-helper" {
-		if os.Args[2] == "echo-arg" {
-			// Echoes back exactly the one argument it received, to verify a
-			// quoted, space-and-slash-containing argument (the same shape as
-			// `python -c "print(15 / 3)"`) survives the shell invocation
-			// intact instead of being truncated/corrupted.
-			if len(os.Args) < 4 {
-				fmt.Fprintln(os.Stderr, "echo-arg requires exactly one argument")
-				os.Exit(1)
-			}
-			fmt.Println(os.Args[3])
-			return
-		}
 		runBashToolHelper(os.Args[2])
 		return
 	}
@@ -173,35 +161,6 @@ func TestDetectShellCommandIssueRequiresActualLSCommand(t *testing.T) {
 	}
 }

-func TestDetectShellCommandIssueFlagsPipedPosixUtilities(t *testing.T) {
-	for _, command := range []string{
-		`git log --oneline -- pinokio_compat.py | head`,
-		`git blame -L 40,46 pinokio_compat.py --format=%author | grep summary`,
-		`cat file.txt | wc -l`,
-		`some_command | tail -n 20`,
-	} {
-		if issue := detectShellCommandIssue(command, "windows"); issue == nil {
-			t.Fatalf("expected POSIX utility pipeline to be flagged for %q", command)
-		}
-	}
-}
-
-func TestDetectShellCommandIssueAllowsUnrelatedCommands(t *testing.T) {
-	for _, command := range []string{
-		`git log --oneline`,
-		`dir /b`,
-		`findstr /r "summary" file.txt`,
-		`echo header text`,
-		`tail-log.sh`,
-		`grep-cli --version`,
-		`sed.exe --help`,
-	} {
-		if issue := detectShellCommandIssue(command, "windows"); issue != nil {
-			t.Fatalf("expected unrelated command to pass for %q, got %#v", command, issue)
-		}
-	}
-}
-
 func TestDetectShellOutputIssueAddsWindowsSyntaxHint(t *testing.T) {
 	issue := detectShellOutputIssue(`cd /d/tmp/zero-pr-158 && ls -la`, "The syntax of the command is incorrect.", "windows")
 	if issue == nil {
@@ -547,68 +506,6 @@ func TestBashToolAllowsNonInteractiveCommand(t *testing.T) {
 	}
 }

-// TestBashToolPreservesEmbeddedQuotesOnWindows pins a real, previously-broken
-// case: passing commandText as a normal exec.Cmd argument makes Go wrap it in
-// an outer pair of quotes (it contains spaces) with its own quotes escaped as
-// \", and cmd.exe's /C remainder parsing strips the first and last literal
-// quote character in that remainder without undoing the backslash-escaping -
-// corrupting a command whose own text contains embedded double quotes,
-// exactly the shape of `python -c "print(15 / 3)"`, `git commit -m
-// "message"`, `node -e "..."`. Before the fix, the helper below received a
-// truncated, mis-quoted argument (starting with a stray literal `"`) instead
-// of the text between the quotes.
-func TestBashToolPreservesEmbeddedQuotesOnWindows(t *testing.T) {
-	if runtime.GOOS != "windows" {
-		t.Skip("cmd.exe /S/C quote-remainder parsing is Windows-specific")
-	}
-	root := t.TempDir()
-	executable := shellQuote(os.Args[0])
-	// Space and a slash: the two characters whose position in the original
-	// bug report's SyntaxError ("print(15, truncated right before the /")
-	// showed exactly where the corruption happened.
-	commandText := executable + ` --zero-bash-helper echo-arg "hello / world"`
-
-	result := NewBashTool(root).Run(context.Background(), map[string]any{
-		"command": commandText,
-	})
-
-	if result.Status != StatusOK {
-		t.Fatalf("expected ok status, got %s: %s", result.Status, result.Output)
-	}
-	if !strings.Contains(result.Output, "hello / world") {
-		t.Fatalf("expected the embedded-quote argument to survive intact, got %q", result.Output)
-	}
-}
-
-// TestBashToolRunsCommandLineForLoopSyntax pins cmd.exe command-line syntax,
-// not batch-file syntax: a `for %i in (...) do ...` loop with a single
-// percent sign is valid typed directly at a cmd.exe prompt (or via
-// `cmd /C "..."`), but requires %%i inside an actual .bat/.cmd FILE, because
-// batch files perform an extra pass of percent-substitution before FOR ever
-// runs, consuming the single percent so the loop variable never binds. An
-// earlier version of this fix ran commandText from a temporary .cmd file
-// instead of passing it straight through to cmd.exe's /C remainder, which
-// silently broke single-percent syntax like this.
-func TestBashToolRunsCommandLineForLoopSyntax(t *testing.T) {
-	if runtime.GOOS != "windows" {
-		t.Skip("cmd.exe command-line vs batch-file parsing is Windows-specific")
-	}
-	root := t.TempDir()
-
-	result := NewBashTool(root).Run(context.Background(), map[string]any{
-		"command": "for %i in (1 2 3) do echo %i",
-	})
-
-	if result.Status != StatusOK {
-		t.Fatalf("expected ok status, got %s: %s", result.Status, result.Output)
-	}
-	for _, want := range []string{"1", "2", "3"} {
-		if !strings.Contains(result.Output, want) {
-			t.Fatalf("expected the for-loop to expand %%i to %q, got %q", want, result.Output)
-		}
-	}
-}
-
 func helperCommand(name string) string {
 	executable := shellQuote(os.Args[0])
 	return executable + " --zero-bash-helper " + name
@@ -2,7 +2,6 @@ package tools

 import (
 	"context"
-	"errors"
 	"fmt"
 	"os"
 	"strings"
@@ -45,7 +44,7 @@ func (tool editFileTool) Run(ctx context.Context, args map[string]any) Result {
 	return tool.RunWithOptions(ctx, args, RunOptions{})
 }

-func (tool editFileTool) RunWithOptions(ctx context.Context, args map[string]any, options RunOptions) Result {
+func (tool editFileTool) RunWithOptions(_ context.Context, args map[string]any, options RunOptions) Result {
 	requestedPath, err := aliasedStringArg(args, []string{"path", "file", "file_path", "filename"}, "", true, false)
 	if err != nil {
 		return errorResult("Error: Invalid arguments for edit_file: " + err.Error())
@@ -80,51 +79,6 @@ func (tool editFileTool) RunWithOptions(ctx context.Context, args map[string]any
 	content := string(contentBytes)
 	occurrences := strings.Count(content, oldString)

-	// CRLF fallback: read_file normalizes \r\n → \n before presenting content to
-	// the model, so the model's old_string will use \n line endings. When the raw
-	// file uses \r\n (common on Windows), the \n-based old_string won't match.
-	// Detect this and transparently normalize: if the direct match fails, translate
-	// old_string's line endings to \r\n and search again. If found, use the CRLF-translated
-	// old_string and new_string for the replacement to preserve the file's existing EOL style
-	// without rewriting EOLs in unrelated parts of the file.
-	if occurrences == 0 && strings.Contains(content, "\r\n") && !strings.Contains(oldString, "\r\n") {
-		crlfOldString := strings.ReplaceAll(oldString, "\n", "\r\n")
-		normalizedOccurrences := strings.Count(content, crlfOldString)
-		if normalizedOccurrences > 0 {
-			occurrences = normalizedOccurrences
-			oldString = crlfOldString
-			if !strings.Contains(newString, "\r\n") {
-				newString = strings.ReplaceAll(newString, "\n", "\r\n")
-			}
-		}
-	}
-
-	// Fuzzy fallback: when the exact string (and its CRLF translation) is absent,
-	// run a cascade of tolerant matchers (trimmed lines, block anchors, collapsed
-	// whitespace, indentation drift, escape normalization) to locate the span the
-	// model intended. Only a span that occurs literally in the file is accepted,
-	// so the replacement applied below is still exact.
-	if occurrences == 0 {
-		findOld, findNew := oldString, newString
-		if strings.Contains(content, "\r\n") && !strings.Contains(findOld, "\r\n") {
-			findOld = strings.ReplaceAll(findOld, "\n", "\r\n")
-			findNew = strings.ReplaceAll(findNew, "\n", "\r\n")
-		}
-		search, ferr := fuzzyEditMatch(content, findOld, replaceAll)
-		switch {
-		case ferr == nil:
-			oldString = search
-			newString = findNew
-			occurrences = strings.Count(content, search)
-		case errors.Is(ferr, errEditFuzzyAmbiguous):
-			return errorResult("Error: old_string matches multiple locations in " + relativePath + " even after fuzzy matching. Provide more surrounding context to make the match unique, or pass replace_all: true.")
-		case errors.Is(ferr, errEditFuzzyNotFound):
-			// Fall through to the exact-match error below.
-		default:
-			return errorResult("Error editing " + relativePath + ": " + ferr.Error())
-		}
-	}
-
 	if occurrences == 0 {
 		return errorResult("Error: Could not find the exact string to replace in " + relativePath + ". The old_string must match the file byte-for-byte.")
 	}
@@ -147,10 +101,6 @@ func (tool editFileTool) RunWithOptions(ctx context.Context, args map[string]any
 	if err := os.WriteFile(absolutePath, []byte(updated), 0o644); err != nil {
 		return errorResult("Error writing " + relativePath + ": " + err.Error())
 	}
-	// Optional format-on-write (ZERO_FORMAT_ON_WRITE). Must run BEFORE the
-	// FileTracker re-baseline: recording pre-format content would make the very
-	// next edit look like an external modification and trip the conflict guard.
-	updated = maybeFormatWrittenFile(ctx, absolutePath, updated)
 	// 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)
@@ -161,7 +111,6 @@ func (tool editFileTool) RunWithOptions(ctx context.Context, args map[string]any
 		suffix = "s"
 	}
 	summary := fmt.Sprintf("Successfully edited %s (replaced %d occurrence%s).", relativePath, replacedCount, suffix)
-	summary += inlineDiagnostics(ctx, options, absolutePath, relativePath)
 	result := okResult(summary)
 	result.ChangedFiles = []string{relativePath}
 	// Card-only preview (Display.Preview): the model's Output stays the one-line
@@ -1,457 +0,0 @@
-package tools
-
-// Fuzzy fallback matching for edit_file. When the model's old_string fails to
-// match byte-for-byte (drifted indentation, collapsed whitespace, escaped
-// characters, a slightly-misremembered middle line), these replacers propose
-// candidate spans that plausibly correspond to what the model intended. Only a
-// candidate that occurs literally in the file is accepted, so the replacement
-// itself is always exact even when the match was tolerant.
-//
-// Strategy cascade ported from opencode's edit tool, whose replacers were in
-// turn distilled from Cline's diff-apply evals and gemini-cli's edit corrector.
-
-import (
-	"errors"
-	"regexp"
-	"strings"
-)
-
-// editReplacer proposes candidate spans for find inside content. Candidates
-// are re-validated by fuzzyEditMatch before use.
-type editReplacer func(content, find string) []string
-
-var (
-	errEditFuzzyNotFound  = errors.New("no fuzzy match for old_string")
-	errEditFuzzyAmbiguous = errors.New("fuzzy match for old_string is ambiguous")
-)
-
-// Minimum average middle-line similarity for block-anchor matches.
-const editAnchorSimilarityThreshold = 0.65
-
-// fuzzyEditMatch runs the replacer cascade and returns the exact span of
-// content to replace. When replaceAll is false the span must be unique in
-// content; an ambiguous candidate is skipped in favor of later candidates and
-// only reported if nothing unique is found. A span wildly larger than
-// old_string is refused outright rather than risking a destructive edit.
-func fuzzyEditMatch(content, find string, replaceAll bool) (string, error) {
-	replacers := []editReplacer{
-		lineTrimmedReplacer,
-		blockAnchorReplacer,
-		whitespaceNormalizedReplacer,
-		indentationFlexibleReplacer,
-		escapeNormalizedReplacer,
-		trimmedBoundaryReplacer,
-		contextAwareReplacer,
-	}
-	found := false
-	for _, replacer := range replacers {
-		for _, search := range replacer(content, find) {
-			if search == "" {
-				continue
-			}
-			index := strings.Index(content, search)
-			if index < 0 {
-				continue
-			}
-			found = true
-			if isDisproportionateEditMatch(search, find) {
-				return "", errors.New("refusing replacement because the matched span is much larger than old_string; re-read the file and provide the full exact old_string for the intended replacement")
-			}
-			if replaceAll {
-				return search, nil
-			}
-			if strings.LastIndex(content, search) != index {
-				continue
-			}
-			return search, nil
-		}
-	}
-	if !found {
-		return "", errEditFuzzyNotFound
-	}
-	return "", errEditFuzzyAmbiguous
-}
-
-// isDisproportionateEditMatch guards against anchor-style replacers matching a
-// span far larger than the text the model asked to replace (e.g. first/last
-// line anchors bridging hundreds of unrelated lines).
-func isDisproportionateEditMatch(search, find string) bool {
-	findLines := strings.Count(find, "\n") + 1
-	searchLines := strings.Count(search, "\n") + 1
-	limit := findLines + 3
-	if findLines*2 > limit {
-		limit = findLines * 2
-	}
-	if searchLines >= limit {
-		return true
-	}
-	if findLines == 1 {
-		return false
-	}
-	searchTrimmed := len(strings.TrimSpace(search))
-	findTrimmed := len(strings.TrimSpace(find))
-	byteLimit := findTrimmed + 500
-	if findTrimmed*4 > byteLimit {
-		byteLimit = findTrimmed * 4
-	}
-	return searchTrimmed > byteLimit
-}
-
-// splitFindLines splits find into lines, dropping the trailing empty line a
-// trailing newline produces so windows align with real content lines.
-func splitFindLines(find string) []string {
-	lines := strings.Split(find, "\n")
-	if len(lines) > 0 && lines[len(lines)-1] == "" {
-		lines = lines[:len(lines)-1]
-	}
-	return lines
-}
-
-// lineTrimmedReplacer matches when every line equals the corresponding
-// old_string line after trimming surrounding whitespace.
-func lineTrimmedReplacer(content, find string) []string {
-	contentLines := strings.Split(content, "\n")
-	findLines := splitFindLines(find)
-	if len(findLines) == 0 {
-		return nil
-	}
-	var candidates []string
-	for i := 0; i+len(findLines) <= len(contentLines); i++ {
-		matches := true
-		for j := range findLines {
-			if strings.TrimSpace(contentLines[i+j]) != strings.TrimSpace(findLines[j]) {
-				matches = false
-				break
-			}
-		}
-		if matches {
-			candidates = append(candidates, strings.Join(contentLines[i:i+len(findLines)], "\n"))
-		}
-	}
-	return candidates
-}
-
-// blockAnchorReplacer anchors on the first and last lines (trimmed) and
-// accepts the block when the middle lines average >= the similarity threshold
-// (Levenshtein-based), tolerating a slightly misremembered interior.
-func blockAnchorReplacer(content, find string) []string {
-	findLines := splitFindLines(find)
-	if len(findLines) < 3 {
-		return nil
-	}
-	contentLines := strings.Split(content, "\n")
-	firstAnchor := strings.TrimSpace(findLines[0])
-	lastAnchor := strings.TrimSpace(findLines[len(findLines)-1])
-	searchBlockSize := len(findLines)
-	maxLineDelta := searchBlockSize / 4
-	if maxLineDelta < 1 {
-		maxLineDelta = 1
-	}
-
-	type span struct{ start, end int }
-	var candidates []span
-	for i := 0; i < len(contentLines); i++ {
-		if strings.TrimSpace(contentLines[i]) != firstAnchor {
-			continue
-		}
-		// Only the first occurrence of the last anchor after this start counts,
-		// mirroring the reference implementation: a farther-away closing line is
-		// assumed to close a different block.
-		for j := i + 2; j < len(contentLines); j++ {
-			if strings.TrimSpace(contentLines[j]) != lastAnchor {
-				continue
-			}
-			actualBlockSize := j - i + 1
-			delta := actualBlockSize - searchBlockSize
-			if delta < 0 {
-				delta = -delta
-			}
-			if delta <= maxLineDelta {
-				candidates = append(candidates, span{start: i, end: j})
-			}
-			break
-		}
-	}
-	if len(candidates) == 0 {
-		return nil
-	}
-
-	middleSimilarity := func(candidate span) float64 {
-		actualBlockSize := candidate.end - candidate.start + 1
-		linesToCheck := searchBlockSize - 2
-		if actualBlockSize-2 < linesToCheck {
-			linesToCheck = actualBlockSize - 2
-		}
-		if linesToCheck <= 0 {
-			return 1.0
-		}
-		similarity := 0.0
-		for j := 1; j < searchBlockSize-1 && j < actualBlockSize-1; j++ {
-			contentLine := strings.TrimSpace(contentLines[candidate.start+j])
-			findLine := strings.TrimSpace(findLines[j])
-			maxLen := len(contentLine)
-			if len(findLine) > maxLen {
-				maxLen = len(findLine)
-			}
-			if maxLen == 0 {
-				continue
-			}
-			distance := levenshtein(contentLine, findLine)
-			similarity += 1 - float64(distance)/float64(maxLen)
-		}
-		return similarity / float64(linesToCheck)
-	}
-
-	best := candidates[0]
-	if len(candidates) > 1 {
-		bestSimilarity := -1.0
-		for _, candidate := range candidates {
-			if s := middleSimilarity(candidate); s > bestSimilarity {
-				bestSimilarity = s
-				best = candidate
-			}
-		}
-		if bestSimilarity < editAnchorSimilarityThreshold {
-			return nil
-		}
-	} else if middleSimilarity(best) < editAnchorSimilarityThreshold {
-		return nil
-	}
-	return []string{strings.Join(contentLines[best.start:best.end+1], "\n")}
-}
-
-var editWhitespaceRun = regexp.MustCompile(`\s+`)
-
-func normalizeEditWhitespace(text string) string {
-	return strings.TrimSpace(editWhitespaceRun.ReplaceAllString(text, " "))
-}
-
-// whitespaceNormalizedReplacer matches after collapsing all whitespace runs to
-// a single space: full lines, sub-line spans (via a word-boundary regex), and
-// multi-line windows.
-func whitespaceNormalizedReplacer(content, find string) []string {
-	normalizedFind := normalizeEditWhitespace(find)
-	if normalizedFind == "" {
-		return nil
-	}
-	contentLines := strings.Split(content, "\n")
-	var candidates []string
-	var subLinePattern *regexp.Regexp
-	for _, line := range contentLines {
-		normalizedLine := normalizeEditWhitespace(line)
-		if normalizedLine == normalizedFind {
-			candidates = append(candidates, line)
-			continue
-		}
-		if !strings.Contains(normalizedLine, normalizedFind) {
-			continue
-		}
-		if subLinePattern == nil {
-			words := strings.Fields(find)
-			quoted := make([]string, len(words))
-			for i, word := range words {
-				quoted[i] = regexp.QuoteMeta(word)
-			}
-			pattern, err := regexp.Compile(strings.Join(quoted, `\s+`))
-			if err != nil {
-				continue
-			}
-			subLinePattern = pattern
-		}
-		if match := subLinePattern.FindString(line); match != "" {
-			candidates = append(candidates, match)
-		}
-	}
-
-	findLines := strings.Split(find, "\n")
-	if len(findLines) > 1 {
-		for i := 0; i+len(findLines) <= len(contentLines); i++ {
-			block := strings.Join(contentLines[i:i+len(findLines)], "\n")
-			if normalizeEditWhitespace(block) == normalizedFind {
-				candidates = append(candidates, block)
-			}
-		}
-	}
-	return candidates
-}
-
-// stripCommonIndentation removes the minimum leading-whitespace width shared
-// by all non-empty lines, so blocks match regardless of their nesting depth.
-func stripCommonIndentation(text string) string {
-	lines := strings.Split(text, "\n")
-	minIndent := -1
-	for _, line := range lines {
-		if strings.TrimSpace(line) == "" {
-			continue
-		}
-		indent := len(line) - len(strings.TrimLeft(line, " \t"))
-		if minIndent < 0 || indent < minIndent {
-			minIndent = indent
-		}
-	}
-	if minIndent <= 0 {
-		return text
-	}
-	stripped := make([]string, len(lines))
-	for i, line := range lines {
-		if strings.TrimSpace(line) == "" {
-			stripped[i] = line
-			continue
-		}
-		stripped[i] = line[minIndent:]
-	}
-	return strings.Join(stripped, "\n")
-}
-
-func indentationFlexibleReplacer(content, find string) []string {
-	normalizedFind := stripCommonIndentation(find)
-	contentLines := strings.Split(content, "\n")
-	findLines := strings.Split(find, "\n")
-	var candidates []string
-	for i := 0; i+len(findLines) <= len(contentLines); i++ {
-		block := strings.Join(contentLines[i:i+len(findLines)], "\n")
-		if stripCommonIndentation(block) == normalizedFind {
-			candidates = append(candidates, block)
-		}
-	}
-	return candidates
-}
-
-var editEscapeSequence = regexp.MustCompile("\\\\(n|t|r|'|\"|`|\\\\|\\n|\\$)")
-
-// unescapeEditString undoes one level of string escaping (\n, \t, \", \\, a
-// backslash-newline continuation, \$) — the model sometimes reproduces file
-// content as it appeared inside a quoted string literal.
-func unescapeEditString(text string) string {
-	return editEscapeSequence.ReplaceAllStringFunc(text, func(match string) string {
-		switch match[1:] {
-		case "n":
-			return "\n"
-		case "t":
-			return "\t"
-		case "r":
-			return "\r"
-		case "\n":
-			return "\n"
-		default:
-			// ', ", `, \, $ all unescape to themselves.
-			return match[1:]
-		}
-	})
-}
-
-func escapeNormalizedReplacer(content, find string) []string {
-	unescapedFind := unescapeEditString(find)
-	var candidates []string
-	if strings.Contains(content, unescapedFind) {
-		candidates = append(candidates, unescapedFind)
-	}
-	contentLines := strings.Split(content, "\n")
-	findLines := strings.Split(unescapedFind, "\n")
-	for i := 0; i+len(findLines) <= len(contentLines); i++ {
-		block := strings.Join(contentLines[i:i+len(findLines)], "\n")
-		if unescapeEditString(block) == unescapedFind {
-			candidates = append(candidates, block)
-		}
-	}
-	return candidates
-}
-
-// trimmedBoundaryReplacer tolerates stray leading/trailing whitespace (often
-// blank lines) around an otherwise-exact old_string.
-func trimmedBoundaryReplacer(content, find string) []string {
-	trimmedFind := strings.TrimSpace(find)
-	if trimmedFind == find || trimmedFind == "" {
-		return nil
-	}
-	var candidates []string
-	if strings.Contains(content, trimmedFind) {
-		candidates = append(candidates, trimmedFind)
-	}
-	contentLines := strings.Split(content, "\n")
-	findLines := strings.Split(find, "\n")
-	for i := 0; i+len(findLines) <= len(contentLines); i++ {
-		block := strings.Join(contentLines[i:i+len(findLines)], "\n")
-		if strings.TrimSpace(block) == trimmedFind {
-			candidates = append(candidates, block)
-		}
-	}
-	return candidates
-}
-
-// contextAwareReplacer anchors on the first and last lines and accepts an
-// equal-length block when at least half of its non-empty middle lines match
-// after trimming — a cheaper, stricter cousin of blockAnchorReplacer.
-func contextAwareReplacer(content, find string) []string {
-	findLines := splitFindLines(find)
-	if len(findLines) < 3 {
-		return nil
-	}
-	contentLines := strings.Split(content, "\n")
-	firstAnchor := strings.TrimSpace(findLines[0])
-	lastAnchor := strings.TrimSpace(findLines[len(findLines)-1])
-	var candidates []string
-	for i := 0; i < len(contentLines); i++ {
-		if strings.TrimSpace(contentLines[i]) != firstAnchor {
-			continue
-		}
-		for j := i + 2; j < len(contentLines); j++ {
-			if strings.TrimSpace(contentLines[j]) != lastAnchor {
-				continue
-			}
-			if j-i+1 == len(findLines) {
-				matching, nonEmpty := 0, 0
-				for k := 1; k < len(findLines)-1; k++ {
-					blockLine := strings.TrimSpace(contentLines[i+k])
-					findLine := strings.TrimSpace(findLines[k])
-					if blockLine == "" && findLine == "" {
-						continue
-					}
-					nonEmpty++
-					if blockLine == findLine {
-						matching++
-					}
-				}
-				if nonEmpty == 0 || float64(matching)/float64(nonEmpty) >= 0.5 {
-					candidates = append(candidates, strings.Join(contentLines[i:j+1], "\n"))
-				}
-			}
-			break
-		}
-	}
-	return candidates
-}
-
-// levenshtein computes edit distance with a two-row rolling matrix.
-func levenshtein(a, b string) int {
-	if a == "" {
-		return len(b)
-	}
-	if b == "" {
-		return len(a)
-	}
-	previous := make([]int, len(b)+1)
-	current := make([]int, len(b)+1)
-	for j := range previous {
-		previous[j] = j
-	}
-	for i := 1; i <= len(a); i++ {
-		current[0] = i
-		for j := 1; j <= len(b); j++ {
-			cost := 1
-			if a[i-1] == b[j-1] {
-				cost = 0
-			}
-			minimum := previous[j] + 1
-			if current[j-1]+1 < minimum {
-				minimum = current[j-1] + 1
-			}
-			if previous[j-1]+cost < minimum {
-				minimum = previous[j-1] + cost
-			}
-			current[j] = minimum
-		}
-		previous, current = current, previous
-	}
-	return previous[len(b)]
-}
@@ -1,264 +0,0 @@
-package tools
-
-import (
-	"context"
-	"os"
-	"path/filepath"
-	"strings"
-	"testing"
-)
-
-func runEdit(t *testing.T, dir, initial string, args map[string]any) (Result, string) {
-	t.Helper()
-	path := filepath.Join(dir, "target.txt")
-	if err := os.WriteFile(path, []byte(initial), 0o644); err != nil {
-		t.Fatal(err)
-	}
-	if args["path"] == nil {
-		args["path"] = "target.txt"
-	}
-	result := NewEditFileTool(dir).Run(context.Background(), args)
-	after, err := os.ReadFile(path)
-	if err != nil {
-		t.Fatal(err)
-	}
-	return result, string(after)
-}
-
-func TestEditExactMatchStillPreferred(t *testing.T) {
-	// The fast path must keep byte-exact semantics: an exact match wins even
-	// when fuzzy strategies would also find candidates elsewhere.
-	result, after := runEdit(t, t.TempDir(), "alpha\nbeta\ngamma\n", map[string]any{
-		"old_string": "beta",
-		"new_string": "delta",
-	})
-	if result.Status != StatusOK {
-		t.Fatalf("expected ok, got %q", result.Output)
-	}
-	if after != "alpha\ndelta\ngamma\n" {
-		t.Fatalf("unexpected content: %q", after)
-	}
-}
-
-func TestEditFuzzyLineTrimmed(t *testing.T) {
-	// Model reproduced the lines without the file's leading indentation; the
-	// line-trimmed strategy must find the real indented span and preserve the
-	// file's own indentation on the replaced region boundary.
-	initial := "func a() {\n\tx := 1\n\treturn x\n}\n"
-	result, after := runEdit(t, t.TempDir(), initial, map[string]any{
-		"old_string": "x := 1\nreturn x",
-		"new_string": "\ty := 2\n\treturn y",
-	})
-	if result.Status != StatusOK {
-		t.Fatalf("expected ok, got %q", result.Output)
-	}
-	if !strings.Contains(after, "\ty := 2\n\treturn y\n}") {
-		t.Fatalf("unexpected content: %q", after)
-	}
-	if strings.Contains(after, "x := 1") {
-		t.Fatalf("old span survived: %q", after)
-	}
-}
-
-func TestEditFuzzyWhitespaceNormalizedSingleLine(t *testing.T) {
-	// Whitespace runs collapsed: "x  :=   1" in the file, single spaces from
-	// the model.
-	initial := "start\nx  :=   1\nend\n"
-	result, after := runEdit(t, t.TempDir(), initial, map[string]any{
-		"old_string": "x := 1",
-		"new_string": "x := 2",
-	})
-	if result.Status != StatusOK {
-		t.Fatalf("expected ok, got %q", result.Output)
-	}
-	if !strings.Contains(after, "x := 2") || strings.Contains(after, ":=   1") {
-		t.Fatalf("unexpected content: %q", after)
-	}
-}
-
-func TestEditFuzzyBlockAnchorToleratesMiddleDrift(t *testing.T) {
-	// First and last lines anchor the block; one interior line differs slightly
-	// (comment text drifted). Levenshtein similarity keeps it above 0.65.
-	initial := strings.Join([]string{
-		"func handler(w http.ResponseWriter, r *http.Request) {",
-		"\t// write the response body to the client",
-		"\tw.WriteHeader(http.StatusOK)",
-		"\tfmt.Fprint(w, \"done\")",
-		"}",
-		"",
-	}, "\n")
-	find := strings.Join([]string{
-		"func handler(w http.ResponseWriter, r *http.Request) {",
-		"\t// write the response body to client",
-		"\tw.WriteHeader(http.StatusOK)",
-		"\tfmt.Fprint(w, \"done\")",
-		"}",
-	}, "\n")
-	result, after := runEdit(t, t.TempDir(), initial, map[string]any{
-		"old_string": find,
-		"new_string": "func handler(w http.ResponseWriter, r *http.Request) {\n\tw.WriteHeader(http.StatusNoContent)\n}",
-	})
-	if result.Status != StatusOK {
-		t.Fatalf("expected ok, got %q", result.Output)
-	}
-	if !strings.Contains(after, "StatusNoContent") || strings.Contains(after, "StatusOK") {
-		t.Fatalf("unexpected content: %q", after)
-	}
-}
-
-func TestEditFuzzyIndentationFlexible(t *testing.T) {
-	// The whole block sits one nesting level deeper in the file than in the
-	// model's old_string, with interior relative indentation preserved.
-	initial := "if ok {\n\t\tfor i := range xs {\n\t\t\tsum += xs[i]\n\t\t}\n}\n"
-	result, after := runEdit(t, t.TempDir(), initial, map[string]any{
-		"old_string": "for i := range xs {\n\tsum += xs[i]\n}",
-		"new_string": "\t\tsum += total(xs)",
-	})
-	if result.Status != StatusOK {
-		t.Fatalf("expected ok, got %q", result.Output)
-	}
-	if !strings.Contains(after, "total(xs)") || strings.Contains(after, "range xs") {
-		t.Fatalf("unexpected content: %q", after)
-	}
-}
-
-func TestEditFuzzyEscapeNormalized(t *testing.T) {
-	// Model reproduced the line as it would appear inside a quoted string
-	// literal, with escaped quotes.
-	initial := "console.log(\"hello world\")\n"
-	result, after := runEdit(t, t.TempDir(), initial, map[string]any{
-		"old_string": `console.log(\"hello world\")`,
-		"new_string": `console.log("goodbye")`,
-	})
-	if result.Status != StatusOK {
-		t.Fatalf("expected ok, got %q", result.Output)
-	}
-	if !strings.Contains(after, `console.log("goodbye")`) {
-		t.Fatalf("unexpected content: %q", after)
-	}
-}
-
-func TestEditFuzzyTrimmedBoundary(t *testing.T) {
-	// Stray whitespace around an otherwise-exact old_string; "  two  " is not a
-	// substring of the file, so only the fuzzy cascade can resolve it.
-	initial := "one\ntwo\nthree\n"
-	result, after := runEdit(t, t.TempDir(), initial, map[string]any{
-		"old_string": "  two  ",
-		"new_string": "2",
-	})
-	if result.Status != StatusOK {
-		t.Fatalf("expected ok, got %q", result.Output)
-	}
-	if after != "one\n2\nthree\n" {
-		t.Fatalf("unexpected content: %q", after)
-	}
-}
-
-func TestTrimmedBoundaryReplacerYieldsTrimmedSpan(t *testing.T) {
-	candidates := trimmedBoundaryReplacer("one\ntwo\nthree\n", "\ntwo\n")
-	if len(candidates) == 0 || candidates[0] != "two" {
-		t.Fatalf("expected trimmed candidate \"two\", got %v", candidates)
-	}
-	if trimmedBoundaryReplacer("anything", "already-trimmed") != nil {
-		t.Fatal("already-trimmed find must yield no candidates")
-	}
-}
-
-// Two identical blocks that only match old_string after indentation-tolerant
-// matching: exact search finds nothing, fuzzy finds both.
-const ambiguousBlocks = "\tif x {\n\t\tgo()\n\t}\nmid\n\tif x {\n\t\tgo()\n\t}\n"
-
-func TestEditFuzzyAmbiguousReportsError(t *testing.T) {
-	// No strategy can disambiguate identical blocks, so the tool must refuse
-	// rather than guess, and the file must be untouched.
-	result, after := runEdit(t, t.TempDir(), ambiguousBlocks, map[string]any{
-		"old_string": "if x {\n\tgo()\n}",
-		"new_string": "stop()",
-	})
-	if result.Status != StatusError || !strings.Contains(result.Output, "multiple locations") {
-		t.Fatalf("expected ambiguity error, got %q", result.Output)
-	}
-	if after != ambiguousBlocks {
-		t.Fatalf("file must be unchanged, got %q", after)
-	}
-}
-
-func TestEditFuzzyReplaceAll(t *testing.T) {
-	// replace_all applies the fuzzy-resolved span at every occurrence.
-	result, after := runEdit(t, t.TempDir(), ambiguousBlocks, map[string]any{
-		"old_string":  "if x {\n\tgo()\n}",
-		"new_string":  "stop()",
-		"replace_all": true,
-	})
-	if result.Status != StatusOK {
-		t.Fatalf("expected ok, got %q", result.Output)
-	}
-	if strings.Count(after, "stop()") != 2 || strings.Contains(after, "go()") {
-		t.Fatalf("unexpected content: %q", after)
-	}
-}
-
-func TestEditFuzzyNotFoundKeepsExactError(t *testing.T) {
-	result, after := runEdit(t, t.TempDir(), "alpha\n", map[string]any{
-		"old_string": "omega",
-		"new_string": "x",
-	})
-	if result.Status != StatusError || !strings.Contains(result.Output, "Could not find the exact string") {
-		t.Fatalf("expected not-found error, got %q", result.Output)
-	}
-	if after != "alpha\n" {
-		t.Fatalf("file must be unchanged, got %q", after)
-	}
-}
-
-func TestEditFuzzyCRLFFile(t *testing.T) {
-	// CRLF file + LF old_string with indentation drift: the CRLF translation
-	// feeds the cascade and the replacement preserves CRLF endings.
-	initial := "func a() {\r\n\tx := 1\r\n}\r\n"
-	result, after := runEdit(t, t.TempDir(), initial, map[string]any{
-		"old_string": "x := 1",
-		"new_string": "x := 2",
-	})
-	if result.Status != StatusOK {
-		t.Fatalf("expected ok, got %q", result.Output)
-	}
-	if !strings.Contains(after, "\tx := 2\r\n") {
-		t.Fatalf("unexpected content: %q", after)
-	}
-}
-
-func TestIsDisproportionateEditMatch(t *testing.T) {
-	// A candidate span that dwarfs old_string must be refused: anchors bridging
-	// unrelated code would otherwise delete it all.
-	big := strings.Repeat("line\n", 10)
-	if !isDisproportionateEditMatch(big, "a\nb\nc") {
-		t.Fatal("10-line span for 3-line find must be disproportionate")
-	}
-	if isDisproportionateEditMatch("a\nb\nc\nd", "a\nb\nc") {
-		t.Fatal("one extra line within tolerance must be allowed")
-	}
-	if isDisproportionateEditMatch("single line", "single") {
-		t.Fatal("single-line finds are exempt from the byte-length guard")
-	}
-	if !isDisproportionateEditMatch("xx\n"+strings.Repeat("y", 900)+"\nzz", "xx\nab\nzz") {
-		t.Fatal("byte-length blowup must be disproportionate")
-	}
-}
-
-func TestLevenshtein(t *testing.T) {
-	cases := []struct {
-		a, b string
-		want int
-	}{
-		{"", "", 0},
-		{"abc", "", 3},
-		{"", "abc", 3},
-		{"kitten", "sitting", 3},
-		{"same", "same", 0},
-	}
-	for _, c := range cases {
-		if got := levenshtein(c.a, c.b); got != c.want {
-			t.Fatalf("levenshtein(%q,%q) = %d, want %d", c.a, c.b, got, c.want)
-		}
-	}
-}
@@ -908,15 +908,6 @@ func formatExecCommandOutput(output string, sessionID int, exited bool, exitCode
 }

 func truncateExecOutput(output string, maxOutputTokens int) (string, bool) {
-	return truncateExecOutputSpill(output, maxOutputTokens, "exec_command")
-}
-
-// truncateExecOutputSpill keeps a head/tail window of the output within the
-// token budget and, on truncation, spills the full output to disk so the model
-// can grep/read the elided middle instead of re-running the command with a
-// bigger budget. The spill is best-effort: when it fails the notice simply
-// omits the file hint.
-func truncateExecOutputSpill(output string, maxOutputTokens int, toolName string) (string, bool) {
 	if maxOutputTokens <= 0 {
 		maxOutputTokens = defaultMaxOutputTokens
 	}
@@ -924,13 +915,9 @@ func truncateExecOutputSpill(output string, maxOutputTokens int, toolName string
 	if len(output) <= maxBytes {
 		return output, false
 	}
-	notice := "\n[zero] output truncated\n"
-	if spillPath := spillTruncatedOutput(toolName, output); spillPath != "" {
-		notice = "\n[zero] output truncated — full output saved to " + spillPath + " (grep or read_file it instead of re-running)\n"
-	}
 	head := maxBytes / 2
 	tail := maxBytes - head
-	return utf8Prefix(output, head) + notice + utf8Suffix(output, tail), true
+	return utf8Prefix(output, head) + "\n[zero] output truncated\n" + utf8Suffix(output, tail), true
 }

 func utf8Prefix(value string, maxBytes int) string {
@@ -1,97 +0,0 @@
-package tools
-
-import (
-	"context"
-	"os"
-	"os/exec"
-	"path/filepath"
-	"strings"
-	"time"
-)
-
-// Format-on-write for the mutating file tools. When enabled, a successful
-// edit_file/write_file runs the language's standard formatter on the file it
-// just wrote, so the model's output always lands in project-canonical style
-// and never fails a CI format check it cannot see. Off by default (set
-// ZERO_FORMAT_ON_WRITE=1): auto-reformatting changes bytes the model did not
-// write, which strict workflows may not want.
-//
-// Ordering matters: formatting runs BEFORE the FileTracker re-baseline, and
-// the caller records the POST-format content. Formatting after the baseline
-// would make the very next edit look like an external modification and trip
-// the conflict guard.
-
-// formatOnWriteTimeout bounds one formatter run; a wedged formatter must never
-// hang a tool call. On timeout the unformatted write stands.
-const formatOnWriteTimeout = 10 * time.Second
-
-// formatterCommands maps a file extension to the formatter argv; the file path
-// is appended as the final argument. Only in-place, config-respecting,
-// community-standard formatters — a missing binary silently skips formatting.
-var formatterCommands = map[string][]string{
-	".go":    {"gofmt", "-w"},
-	".rs":    {"rustfmt"},
-	".py":    {"ruff", "format", "--quiet"},
-	".ts":    {"prettier", "--log-level", "silent", "--write"},
-	".tsx":   {"prettier", "--log-level", "silent", "--write"},
-	".js":    {"prettier", "--log-level", "silent", "--write"},
-	".jsx":   {"prettier", "--log-level", "silent", "--write"},
-	".json":  {"prettier", "--log-level", "silent", "--write"},
-	".css":   {"prettier", "--log-level", "silent", "--write"},
-	".scss":  {"prettier", "--log-level", "silent", "--write"},
-	".html":  {"prettier", "--log-level", "silent", "--write"},
-	".md":    {"prettier", "--log-level", "silent", "--write"},
-	".yaml":  {"prettier", "--log-level", "silent", "--write"},
-	".yml":   {"prettier", "--log-level", "silent", "--write"},
-	".zig":   {"zig", "fmt"},
-	".dart":  {"dart", "format"},
-	".tf":    {"terraform", "fmt"},
-	".gleam": {"gleam", "format"},
-	".sh":    {"shfmt", "-w"},
-	".bash":  {"shfmt", "-w"},
-	".c":     {"clang-format", "-i"},
-	".h":     {"clang-format", "-i"},
-	".cpp":   {"clang-format", "-i"},
-	".hpp":   {"clang-format", "-i"},
-	".cc":    {"clang-format", "-i"},
-	".kt":    {"ktlint", "-F"},
-	".swift": {"swiftformat"},
-	".lua":   {"stylua"},
-}
-
-// formatOnWriteEnabled reports whether the opt-in env toggle is set.
-func formatOnWriteEnabled() bool {
-	value := strings.TrimSpace(os.Getenv("ZERO_FORMAT_ON_WRITE"))
-	return value != "" && value != "0" && !strings.EqualFold(value, "false")
-}
-
-// maybeFormatWrittenFile runs the configured formatter for absolutePath (when
-// enabled and on PATH) and returns the file's content afterwards. Best-effort
-// throughout: any failure — no formatter, formatter error, timeout, unreadable
-// result — returns writtenContent so the caller's state matches the last write
-// it performed itself.
-func maybeFormatWrittenFile(ctx context.Context, absolutePath string, writtenContent string) string {
-	if !formatOnWriteEnabled() {
-		return writtenContent
-	}
-	command, ok := formatterCommands[strings.ToLower(filepath.Ext(absolutePath))]
-	if !ok {
-		return writtenContent
-	}
-	if _, err := exec.LookPath(command[0]); err != nil {
-		return writtenContent
-	}
-	formatCtx, cancel := context.WithTimeout(ctx, formatOnWriteTimeout)
-	defer cancel()
-	arguments := append(append([]string(nil), command[1:]...), absolutePath)
-	formatter := exec.CommandContext(formatCtx, command[0], arguments...)
-	formatter.Dir = filepath.Dir(absolutePath)
-	if err := formatter.Run(); err != nil {
-		return writtenContent
-	}
-	formatted, err := os.ReadFile(absolutePath)
-	if err != nil {
-		return writtenContent
-	}
-	return string(formatted)
-}
@@ -1,82 +0,0 @@
-package tools
-
-import (
-	"context"
-	"os"
-	"os/exec"
-	"path/filepath"
-	"strings"
-	"testing"
-)
-
-// gofmt ships with the Go toolchain, so it is the one formatter guaranteed to
-// exist wherever these tests run.
-func requireGofmt(t *testing.T) {
-	t.Helper()
-	if _, err := exec.LookPath("gofmt"); err != nil {
-		t.Skip("gofmt not on PATH")
-	}
-}
-
-func TestFormatOnWriteDisabledByDefault(t *testing.T) {
-	requireGofmt(t)
-	t.Setenv("ZERO_FORMAT_ON_WRITE", "")
-	dir := t.TempDir()
-	ugly := "package a\n\nfunc  A( ) {   }\n"
-
-	result := NewWriteFileTool(dir).(optionsAwareTool).RunWithOptions(context.Background(), map[string]any{
-		"path":    "a.go",
-		"content": ugly,
-	}, RunOptions{})
-	if result.Status != StatusOK {
-		t.Fatalf("write failed: %q", result.Output)
-	}
-	onDisk, err := os.ReadFile(filepath.Join(dir, "a.go"))
-	if err != nil {
-		t.Fatal(err)
-	}
-	if string(onDisk) != ugly {
-		t.Fatalf("formatting must be off by default, got %q", onDisk)
-	}
-}
-
-func TestFormatOnWriteFormatsAndKeepsTrackerConsistent(t *testing.T) {
-	requireGofmt(t)
-	t.Setenv("ZERO_FORMAT_ON_WRITE", "1")
-	dir := t.TempDir()
-	tracker := NewFileTracker()
-
-	write := NewWriteFileTool(dir).(optionsAwareTool).RunWithOptions(context.Background(), map[string]any{
-		"path":    "a.go",
-		"content": "package a\n\nfunc  A( ) {   }\n",
-	}, RunOptions{FileTracker: tracker})
-	if write.Status != StatusOK {
-		t.Fatalf("write failed: %q", write.Output)
-	}
-	onDisk, err := os.ReadFile(filepath.Join(dir, "a.go"))
-	if err != nil {
-		t.Fatal(err)
-	}
-	if !strings.Contains(string(onDisk), "func A() {") {
-		t.Fatalf("expected gofmt-formatted content, got %q", onDisk)
-	}
-
-	// The tracker must have been re-baselined to the POST-format content: a
-	// follow-up edit must not trip the external-modification conflict guard.
-	edit := NewEditFileTool(dir).(optionsAwareTool).RunWithOptions(context.Background(), map[string]any{
-		"path":       "a.go",
-		"old_string": "func A() {",
-		"new_string": "func B() {",
-	}, RunOptions{FileTracker: tracker})
-	if edit.Status != StatusOK {
-		t.Fatalf("follow-up edit must not conflict after formatting: %q", edit.Output)
-	}
-}
-
-func TestFormatOnWriteSkipsUnknownExtensions(t *testing.T) {
-	t.Setenv("ZERO_FORMAT_ON_WRITE", "1")
-	content := maybeFormatWrittenFile(context.Background(), filepath.Join(t.TempDir(), "notes.xyz"), "raw   text")
-	if content != "raw   text" {
-		t.Fatalf("unknown extension must pass through: %q", content)
-	}
-}
@@ -45,18 +45,18 @@ func NewScopedGlobTool(workspaceRoot string, scope PathScope) Tool {
 	}
 }

-func (tool globTool) Run(ctx context.Context, args map[string]any) Result {
-	return tool.runWith(ctx, args, readExcluder{})
+func (tool globTool) Run(_ context.Context, args map[string]any) Result {
+	return tool.runWith(args, readExcluder{})
 }

 // RunWithSandbox runs glob while skipping subtrees the sandbox policy denies
 // reads to (DenyRead). With no DenyRead configured the excluder is a no-op and
 // behavior is unchanged.
-func (tool globTool) RunWithSandbox(ctx context.Context, args map[string]any, engine *sandbox.Engine) Result {
-	return tool.runWith(ctx, args, sandboxReadExcluder(engine))
+func (tool globTool) RunWithSandbox(_ context.Context, args map[string]any, engine *sandbox.Engine) Result {
+	return tool.runWith(args, sandboxReadExcluder(engine))
 }

-func (tool globTool) runWith(ctx context.Context, args map[string]any, exclude readExcluder) Result {
+func (tool globTool) runWith(args map[string]any, exclude readExcluder) Result {
 	pattern, err := aliasedStringArg(args, []string{"pattern", "glob", "match", "query", "expression"}, "", true, false)
 	if err != nil {
 		return errorResult("Error: Invalid arguments for glob: " + err.Error())
@@ -88,11 +88,8 @@ func (tool globTool) runWith(ctx context.Context, args map[string]any, exclude r
 		return errorResult("Error running glob " + fmt.Sprintf("%q", pattern) + ": " + err.Error())
 	}

-	matches, err := scanGlob(ctx, root, displayRoot, matcher, includeDirs, exclude)
+	matches, err := scanGlob(root, displayRoot, matcher, includeDirs, exclude)
 	if err != nil {
-		if res, ok := searchCancelledResult("glob", err); ok {
-			return res
-		}
 		return errorResult("Error running glob " + fmt.Sprintf("%q", pattern) + ": " + err.Error())
 	}
 	if len(matches) == 0 {
@@ -129,15 +126,9 @@ func (tool globTool) runWith(ctx context.Context, args map[string]any, exclude r
 	}
 }

-func scanGlob(ctx context.Context, root string, displayRoot string, matcher *regexp.Regexp, includeDirs bool, exclude readExcluder) ([]string, error) {
+func scanGlob(root string, displayRoot string, matcher *regexp.Regexp, includeDirs bool, exclude readExcluder) ([]string, error) {
 	matches := []string{}
 	err := filepath.WalkDir(root, func(path string, entry fs.DirEntry, walkErr error) error {
-		// Checked first, ahead of walkErr: an unscoped scan over a large tree can
-		// run long enough that cancelling the run must stop the walk promptly
-		// rather than visiting every remaining entry to completion.
-		if err := ctx.Err(); err != nil {
-			return err
-		}
 		if walkErr != nil {
 			if path == root {
 				return walkErr
@@ -55,19 +55,19 @@ func NewScopedGrepTool(workspaceRoot string, scope PathScope) Tool {
 	}
 }

-func (tool grepTool) Run(ctx context.Context, args map[string]any) Result {
-	return tool.runWith(ctx, args, readExcluder{})
+func (tool grepTool) Run(_ context.Context, args map[string]any) Result {
+	return tool.runWith(args, readExcluder{})
 }

 // RunWithSandbox runs the search while skipping subtrees the sandbox policy
 // denies reads to (DenyRead), so grep never surfaces content from a read-denied
 // path. With no DenyRead configured the excluder is a no-op and behavior is
 // unchanged.
-func (tool grepTool) RunWithSandbox(ctx context.Context, args map[string]any, engine *sandbox.Engine) Result {
-	return tool.runWith(ctx, args, sandboxReadExcluder(engine))
+func (tool grepTool) RunWithSandbox(_ context.Context, args map[string]any, engine *sandbox.Engine) Result {
+	return tool.runWith(args, sandboxReadExcluder(engine))
 }

-func (tool grepTool) runWith(ctx context.Context, args map[string]any, exclude readExcluder) Result {
+func (tool grepTool) runWith(args map[string]any, exclude readExcluder) Result {
 	pattern, err := aliasedStringArg(args, []string{"pattern", "query", "regex", "search", "expression"}, "", true, false)
 	if err != nil {
 		return errorResult("Error: Invalid arguments for grep: " + err.Error())
@@ -138,24 +138,15 @@ func (tool grepTool) runWith(ctx context.Context, args map[string]any, exclude r
 		}
 	}

-	files, err := grepFiles(ctx, resolvedRoot, target, globMatcher, exclude)
+	files, err := grepFiles(resolvedRoot, target, globMatcher, exclude)
 	if err != nil {
-		if res, ok := searchCancelledResult("grep", err); ok {
-			return res
-		}
 		return errorResult("Error running grep: " + err.Error())
 	}

 	// resolveScopedPath returns an absolute displayRoot when the target resolved
 	// to an extra (non-workspace) granted root; emit absolute match paths there so
 	// they survive a round-trip through read_file/edit_file (mirrors glob).
-	matches, err := collectGrepMatches(ctx, resolvedRoot, filepath.IsAbs(displayRoot), files, compiled)
-	if err != nil {
-		if res, ok := searchCancelledResult("grep", err); ok {
-			return res
-		}
-		return errorResult("Error running grep: " + err.Error())
-	}
+	matches := collectGrepMatches(resolvedRoot, filepath.IsAbs(displayRoot), files, compiled)
 	if len(matches) == 0 {
 		if outputMode == "count" {
 			return okResult("0 matches found")
@@ -270,7 +261,7 @@ func confineGrepFile(resolvedRoot string, path string) (string, string, bool) {
 	return filepath.ToSlash(relative), resolved, true
 }

-func grepFiles(ctx context.Context, resolvedRoot string, target string, globMatcher *regexp.Regexp, exclude readExcluder) ([]string, error) {
+func grepFiles(resolvedRoot string, target string, globMatcher *regexp.Regexp, exclude readExcluder) ([]string, error) {
 	info, err := os.Stat(target)
 	if err != nil {
 		return nil, err
@@ -297,13 +288,6 @@ func grepFiles(ctx context.Context, resolvedRoot string, target string, globMatc

 	files := []string{}
 	err = filepath.WalkDir(target, func(path string, entry os.DirEntry, walkErr error) error {
-		// Checked first, ahead of walkErr: an unscoped search over a large tree
-		// (e.g. a broad parent directory, not just the workspace) can run long
-		// enough that cancelling the run must stop the walk promptly rather than
-		// visiting every remaining entry to completion.
-		if err := ctx.Err(); err != nil {
-			return err
-		}
 		if walkErr != nil {
 			if path == target {
 				return walkErr
@@ -358,16 +342,9 @@ func grepFiles(ctx context.Context, resolvedRoot string, target string, globMatc
 	return files, nil
 }

-func collectGrepMatches(ctx context.Context, resolvedRoot string, absolutePaths bool, files []string, compiled *regexp.Regexp) ([]grepMatch, error) {
+func collectGrepMatches(resolvedRoot string, absolutePaths bool, files []string, compiled *regexp.Regexp) []grepMatch {
 	matches := []grepMatch{}
 	for _, file := range files {
-		// Checked per file, matching the walk's per-entry check in grepFiles: a
-		// broad search can already have collected many files before the run is
-		// cancelled, and reading/regex-scanning each one is real work that must
-		// stop promptly rather than running to completion.
-		if err := ctx.Err(); err != nil {
-			return matches, err
-		}
 		// Re-confine at read time (defense-in-depth) AND to compute the clean
 		// workspace-relative path used in output.
 		relative, resolvedPath, ok := confineGrepFile(resolvedRoot, file)
@@ -404,5 +381,5 @@ func collectGrepMatches(ctx context.Context, resolvedRoot string, absolutePaths
 			})
 		}
 	}
-	return matches, nil
+	return matches
 }
@@ -1,18 +0,0 @@
-package tools
-
-import "context"
-
-// inlineDiagnostics renders the post-write diagnostics block a mutating tool
-// appends to its output. Empty when no Diagnostics callback is wired, the file
-// is clean, or no language server is available — the tool output is then
-// byte-identical to the pre-diagnostics behavior.
-func inlineDiagnostics(ctx context.Context, options RunOptions, absolutePath, relativePath string) string {
-	if options.Diagnostics == nil {
-		return ""
-	}
-	block := options.Diagnostics(ctx, absolutePath)
-	if block == "" {
-		return ""
-	}
-	return "\n\nDiagnostics in " + relativePath + " after this change (fix any errors you introduced):\n" + block
-}
@@ -1,53 +0,0 @@
-package tools
-
-import (
-	"context"
-	"os"
-	"path/filepath"
-	"strings"
-	"testing"
-)
-
-// A wired Diagnostics callback must surface its block in the tool output for
-// both mutating tools, and a clean file (empty block) must leave the output
-// byte-identical to the pre-diagnostics behavior.
-func TestMutatingToolsAppendInlineDiagnostics(t *testing.T) {
-	dir := t.TempDir()
-	if err := os.WriteFile(filepath.Join(dir, "a.go"), []byte("package a\n"), 0o644); err != nil {
-		t.Fatal(err)
-	}
-	diagnostics := func(_ context.Context, absPath string) string {
-		return absPath + ":1:1: error: undefined: x"
-	}
-
-	editResult := NewEditFileTool(dir).(optionsAwareTool).RunWithOptions(context.Background(), map[string]any{
-		"path":       "a.go",
-		"old_string": "package a",
-		"new_string": "package b",
-	}, RunOptions{Diagnostics: diagnostics})
-	if editResult.Status != StatusOK {
-		t.Fatalf("edit failed: %q", editResult.Output)
-	}
-	if !strings.Contains(editResult.Output, "Diagnostics in a.go after this change") || !strings.Contains(editResult.Output, "undefined: x") {
-		t.Fatalf("edit output missing diagnostics block: %q", editResult.Output)
-	}
-
-	writeResult := NewWriteFileTool(dir).(optionsAwareTool).RunWithOptions(context.Background(), map[string]any{
-		"path":    "b.go",
-		"content": "package b\n",
-	}, RunOptions{Diagnostics: diagnostics})
-	if writeResult.Status != StatusOK {
-		t.Fatalf("write failed: %q", writeResult.Output)
-	}
-	if !strings.Contains(writeResult.Output, "Diagnostics in b.go after this change") {
-		t.Fatalf("write output missing diagnostics block: %q", writeResult.Output)
-	}
-
-	clean := NewWriteFileTool(dir).(optionsAwareTool).RunWithOptions(context.Background(), map[string]any{
-		"path":    "c.go",
-		"content": "package c\n",
-	}, RunOptions{Diagnostics: func(context.Context, string) string { return "" }})
-	if strings.Contains(clean.Output, "Diagnostics") {
-		t.Fatalf("clean file must not gain a diagnostics block: %q", clean.Output)
-	}
-}
@@ -40,12 +40,6 @@ type RunOptions struct {
 	// tool-call progress in the specialist card. nil is a no-op (the default
 	// for every non-Task tool).
 	Progress func(streamjson.Event)
-	// Diagnostics, when set, returns a formatted language-diagnostics block for
-	// a file a mutating tool just wrote ("" when clean or no server available).
-	// edit_file/write_file append it to their output so the model sees an error
-	// it introduced in the same turn instead of waiting for a later verification
-	// pass. nil disables inline diagnostics.
-	Diagnostics func(ctx context.Context, absPath string) string
 }

 type sandboxAwareTool interface {
@@ -104,8 +104,8 @@ func TestCoreNetworkToolsExposeSafetyMetadata(t *testing.T) {
 	if property, ok := search.Parameters().Properties["query"]; !ok || property.Type != "string" {
 		t.Fatalf("web_search must expose a string query property, got %#v", search.Parameters().Properties["query"])
 	}
-	if safety := search.Safety(); safety.Permission != PermissionPrompt || !safety.AdvertiseInAuto {
-		t.Fatalf("web_search safety = %#v, want prompt and advertised in auto", safety)
+	if safety := search.Safety(); safety.Permission != PermissionAllow || safety.AdvertiseInAuto {
+		t.Fatalf("web_search safety = %#v, want allow without prompt-advertise override", safety)
 	}
 }