fix(tools): reject mixed-root freeform patches

.coderabbit.yaml

@@ -29,9 +29,6 @@ reviews:
     - path: "tests/**/*.ts"
       instructions: |
         Review tests for Bun test idioms, deterministic behavior, and meaningful coverage of safety decisions, provider/runtime flows, session events, and TUI command behavior.
-    - path: "**/*.go"
-      instructions: |
-        Do not request Plan 9 or other unsupported GOOS/GOARCH shims. The five native prebuilt release targets are linux-x64, linux-arm64, macos-arm64, macos-x64, and windows-x64. Android/Termux is also a supported runtime through the documented android-arm64 source build and Linux artifact fallback. Other GOOS/GOARCH combinations are not a review criterion.
   tools:
     github-checks:
       timeout_ms: 300000

.github/workflows/ci.yml

@@ -6,109 +6,10 @@ on:
     branches:
       - main
 
-concurrency:
-  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
-  cancel-in-progress: ${{ github.event_name == 'pull_request' }}
-
-permissions:
-  contents: read
-
 jobs:
-  quality:
-    name: Code Quality & Lint
-    runs-on: ubuntu-latest
-    timeout-minutes: 10
-    permissions:
-      contents: read
-
-    steps:
-      - name: Checkout
-        uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4.2.2
-        with:
-          persist-credentials: false
-
-      - name: Setup Go
-        uses: actions/setup-go@40f1582b2485089dde7abd97c1529aa768e1baff # v5.3.0
-        with:
-          go-version-file: go.mod
-          cache: true
-
-      - name: Check formatting
-        run: make fmt-check
-
-      - name: Vet
-        run: go vet ./...
-
-      - name: deadcode (advisory)
-        continue-on-error: true
-        run: make deadcode
-
-      - name: golangci-lint (advisory)
-        continue-on-error: true
-        run: make lint-static
-
-  test:
-    name: Unit Tests & Coverage
-    runs-on: ubuntu-latest
-    timeout-minutes: 15
-    permissions:
-      contents: read
-
-    steps:
-      - name: Checkout
-        uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4.2.2
-        with:
-          persist-credentials: false
-
-      - name: Setup Go
-        uses: actions/setup-go@40f1582b2485089dde7abd97c1529aa768e1baff # v5.3.0
-        with:
-          go-version-file: go.mod
-          cache: true
-
-      - name: Test with coverage
-        run: |
-          go test -count=1 -coverprofile=coverage.out -covermode=atomic ./...
-
-      - name: Publish coverage summary
-        if: always()
-        shell: bash
-        run: |
-          if [ -f coverage.out ]; then
-            go tool cover -func=coverage.out | awk '
-            BEGIN {
-              total = "unknown"
-              rows = ""
-            }
-            $1 == "total:" {
-              total = $3
-              next
-            }
-            {
-              rows = rows sprintf("| `%s` | `%s` | **%s** |\n", $1, $2, $3)
-            }
-            END {
-              print "### 📊 Test Coverage Summary: **" total "**"
-              print "<details><summary>Coverage per function</summary>\n"
-              print "| File | Function | Coverage |"
-              print "| :--- | :--- | :--- |"
-              printf "%s", rows
-              print "</details>"
-            }' >> "$GITHUB_STEP_SUMMARY"
-          fi
-
-      - name: Upload coverage artifact
-        if: always()
-        uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4.6.2
-        with:
-          name: zero-coverage-report
-          path: coverage.out
-          if-no-files-found: warn
-
   smoke:
     name: Smoke (${{ matrix.os }})
     runs-on: ${{ matrix.os }}
-    timeout-minutes: 15
     strategy:
       fail-fast: false
       matrix:
@@ -117,40 +18,6 @@ jobs:
           - macos-latest
           - windows-latest
 
-    permissions:
-      contents: read
-
-    steps:
-      - name: Checkout
-        uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4.2.2
-        with:
-          persist-credentials: false
-
-      - name: Setup Go
-        uses: actions/setup-go@40f1582b2485089dde7abd97c1529aa768e1baff # v5.3.0
-        with:
-          go-version-file: go.mod
-          cache: true
-
-      - name: Test (Fast Non-Race)
-        run: go test ./...
-
-      - name: Build binary
-        run: go run ./cmd/zero-release build
-
-      - name: Smoke binary
-        run: go run ./cmd/zero-release smoke
-
-  race:
-    name: Race Detector
-    runs-on: ubuntu-latest
-    permissions:
-      contents: read
-    # A race the detector newly reports can present as a deadlock rather than a
-    # failure, and the default job timeout is six hours. This job is expected to
-    # be the longest in the workflow, so the ceiling is generous but finite.
-    timeout-minutes: 30
-
     steps:
       - name: Checkout
         uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4
@@ -163,29 +30,72 @@ jobs:
           go-version-file: go.mod
           cache: true
 
-      # Invoke the Makefile target rather than repeating its flags. `make test`
-      # is already `go test ./... -race -count=1`, so running it here is what
-      # stops the project's declared test command and what CI actually runs
-      # from drifting apart again. The race detector needs cgo, which the
-      # hosted ubuntu runner supplies without an extra setup step.
-      - name: Test with the race detector
-        run: make test
+      - name: Install Make on Windows
+        if: matrix.os == 'windows-latest'
+        shell: pwsh
+        run: choco install make --no-progress -y
+
+      - name: Validate quality targets with stock macOS Make
+        if: matrix.os == 'macos-latest'
+        env:
+          GIT_CONFIG_COUNT: 1
+          GIT_CONFIG_KEY_0: grep.patternType
+          GIT_CONFIG_VALUE_0: fixed
+        run: make -n vulncheck
+
+      - name: Check vulnerabilities through native Windows Make
+        if: matrix.os == 'windows-latest'
+        shell: cmd
+        run: make vulncheck
+
+      - name: Check dead code through native Windows Make
+        if: matrix.os == 'windows-latest'
+        continue-on-error: true
+        shell: cmd
+        run: make deadcode
+
+      - name: Run static lint through native Windows Make
+        if: matrix.os == 'windows-latest'
+        continue-on-error: true
+        shell: cmd
+        run: make lint-static
+
+      - name: Check formatting
+        if: matrix.os == 'ubuntu-latest'
+        shell: bash
+        run: |
+          unformatted="$(gofmt -l .)"
+          if [ -n "$unformatted" ]; then
+            echo "gofmt needed on:" >&2
+            echo "$unformatted" >&2
+            exit 1
+          fi
+
+      - name: Vet
+        if: matrix.os == 'ubuntu-latest'
+        run: go vet ./...
+
+      - name: Test
+        run: go test ./...
+
+      - name: Build binary
+        run: go run ./cmd/zero-release build
+
+      - name: Smoke binary
+        run: go run ./cmd/zero-release smoke
 
   performance:
     name: Performance Smoke
     runs-on: ubuntu-latest
-    timeout-minutes: 10
-    permissions:
-      contents: read
 
     steps:
       - name: Checkout
-        uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4.2.2
+        uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4
         with:
           persist-credentials: false
 
       - name: Setup Go
-        uses: actions/setup-go@40f1582b2485089dde7abd97c1529aa768e1baff # v5.3.0
+        uses: actions/setup-go@40f1582b2485089dde7abd97c1529aa768e1baff
         with:
           go-version-file: go.mod
           cache: true
@@ -194,39 +104,51 @@ jobs:
         run: go run ./cmd/zero-release build
 
       - name: Performance smoke
-        run: |
-          mkdir -p dist/perf
-          go run ./cmd/zero-perf-bench --output dist/perf/perf-bench.json --ci
+        run: go run ./cmd/zero-perf-bench --output dist/perf/perf-bench.json --ci
 
       - name: Upload performance report
         if: always()
-        uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4.6.2
+        uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4
         with:
           name: zero-performance-smoke
           path: dist/perf/perf-bench.json
           if-no-files-found: warn
 
   security:
-    name: Security & Code Health
+    name: Security & code health
     runs-on: ubuntu-latest
-    timeout-minutes: 10
-    permissions:
-      contents: read
 
     steps:
       - name: Checkout
-        uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4.2.2
+        uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4
         with:
           persist-credentials: false
 
       - name: Setup Go
-        uses: actions/setup-go@40f1582b2485089dde7abd97c1529aa768e1baff # v5.3.0
+        uses: actions/setup-go@40f1582b2485089dde7abd97c1529aa768e1baff
         with:
           go-version-file: go.mod
           cache: true
 
-      - name: govulncheck (linux)
+      # Hard gate: fails the build when code reaches a known vulnerability. A stdlib
+      # CVE is cleared by a toolchain bump (see go.mod). May also flag a newly
+      # published advisory on an unrelated PR — intentional: do not ship known vulns.
+      - name: govulncheck
         run: make vulncheck
 
-      - name: govulncheck (windows)
-        run: make vulncheck-windows
+      # Advisory: reports functions unreachable from any cmd/* main so dormant
+      # code is visible in CI. Non-blocking while the dormant subsystems are
+      # still being wired or removed.
+      - name: deadcode (advisory)
+        continue-on-error: true
+        run: make deadcode
+
+      # Advisory: catches what deadcode's whole-program reachability analysis
+      # doesn't, unused private functions/assignments reachable within a
+      # package but never actually called, plus staticcheck-style correctness
+      # and readability issues. Scoped to a few linters rather than the full
+      # default battery, and non-blocking, while the existing findings across
+      # the repo are cleaned up incrementally (see #527).
+      - name: golangci-lint (advisory)
+        continue-on-error: true
+        run: make lint-static

.github/workflows/zero-action-smoke.yml

@@ -14,9 +14,6 @@ on:
       - docs/GITHUB_ACTION.md
       - .github/workflows/zero-action-smoke.yml
 
-permissions:
-  contents: read
-
 jobs:
   validate:
     name: Validate action.yml

AGENTS.md

@@ -81,13 +81,6 @@ These classes drive multi-round reviews. Fix them before requesting review:
   assert raw `t.TempDir()` spellings (`/var` vs `/private/var` on macOS, short
   paths on Windows). Prefer one cross-platform function with small `GOOS`
   checks over duplicated helpers that drift.
-- **Supported targets only:** CONTRIBUTING.md names the five native prebuilt
-  release artifacts (`linux-x64`, `linux-arm64`, `macos-arm64`, `macos-x64`,
-  `windows-x64`) and the additional supported Android/Termux source-build and
-  artifact-fallback path. Other `GOOS`/`GOARCH` combinations, including
-  `plan9`, are unsupported and are not a review criterion. Do not block a PR
-  for failing to compile on an unsupported `GOOS`/`GOARCH`. Tests may use
-  `plan9` as a fixture for "unsupported".
 - **Security edges:** Keep secrets out of argv, env dumps, and logs. Redact
   success and error paths (including stderr). Fail closed on ownership, lease,
   and permission checks. Do not rely on pre-open path resolution

CONTRIBUTING.md

@@ -126,31 +126,6 @@ not enough. Dependency changes need a clear project benefit, such as fixing a
 specific bug, addressing a security issue, improving compatibility, or supporting
 an approved feature.
 
-## Supported platforms
-
-Zero publishes five native prebuilt artifacts from
-`.github/workflows/release-artifacts.yml`:
-
-- `linux-x64` (`linux/amd64`)
-- `linux-arm64` (`linux/arm64`)
-- `macos-arm64` (`darwin/arm64`)
-- `macos-x64` (`darwin/amd64`)
-- `windows-x64` (`windows/amd64`)
-
-The shell installer and npm wrapper resolve the applicable artifacts from that
-list. The PowerShell installer supports the published `windows-x64` artifact;
-there is no native Windows ARM64 artifact. Windows on ARM users can run the x64
-build under emulation or build from source.
-
-Android/Termux is also supported even though it has no distinct release
-artifact. The npm wrapper maps Android to the Linux artifact, and
-`docs/INSTALL.md` documents the native `android/arm64` source build needed on
-devices whose seccomp policy blocks the Linux build's syscall path.
-
-Other `GOOS`/`GOARCH` values, including Plan 9, are unsupported. They are not a
-review criterion. Do not block a pull request for failing to compile on an
-unsupported target. Tests may use `plan9` as a fixture for an unsupported OS.
-
 ## What We Prioritize
 
 The core team will prioritize:

Makefile

@@ -7,7 +7,7 @@ DEADCODE_VERSION := v0.46.0
 GOLANGCI_LINT_VERSION := v2.12.2
 GOVULNCHECK_VERSION := v1.3.0
 
-.PHONY: build build-all test test-race vet fmt fmt-check lint lint-static deadcode vulncheck vulncheck-windows tidy clean baseline help
+.PHONY: build build-all test test-race vet fmt fmt-check lint lint-static deadcode vulncheck tidy clean baseline help
 
 # Build the main CLI binary into ./zero.
 build:
@@ -44,8 +44,7 @@ lint: fmt-check vet
 # the possibly stale Go toolchain or consulting a multi-module GOWORK. git grep
 # works with both POSIX shells and cmd.exe, including GNU Make 3.81 on macOS.
 # The target-specific export is shell-independent.
-lint-static deadcode vulncheck vulncheck-windows: export GOTOOLCHAIN = $(GO_TOOLCHAIN)
-lint-static deadcode vulncheck vulncheck-windows: export GOWORK = off
+lint-static deadcode vulncheck: export GOTOOLCHAIN = $(GO_TOOLCHAIN)
 
 lint-static:
 	go run github.com/golangci/golangci-lint/v2/cmd/golangci-lint@$(GOLANGCI_LINT_VERSION) run --enable-only unused,ineffassign,staticcheck ./...
@@ -56,11 +55,6 @@ deadcode:
 vulncheck:
 	go run golang.org/x/vuln/cmd/govulncheck@$(GOVULNCHECK_VERSION) ./...
 
-vulncheck-windows:
-	mkdir -p "$(CURDIR)/.cache/gobin"
-	GOBIN="$(CURDIR)/.cache/gobin" go install golang.org/x/vuln/cmd/govulncheck@$(GOVULNCHECK_VERSION)
-	GOOS=windows "$(CURDIR)/.cache/gobin/govulncheck" ./...
-
 tidy:
 	go mod tidy
 
@@ -83,4 +77,4 @@ baseline: build
 		--output internal/perfbench/reports/baseline.json
 
 help:
-	@echo "Targets: build (default), build-all, test, test-quick, vet, fmt, fmt-check, lint, lint-static, deadcode, vulncheck, vulncheck-windows, tidy, clean, baseline"
+	@echo "Targets: build (default), build-all, test, test-quick, vet, fmt, fmt-check, lint, lint-static, deadcode, vulncheck, tidy, clean, baseline"

README.md

@@ -26,7 +26,7 @@ zero exec --output-format stream-json < turns.jsonl
 ## Why Zero
 
 - **Use the model you want.** Bring OpenAI, Anthropic, Gemini, Groq, OpenRouter,
-  DeepSeek, Mistral, xAI, Qwen, Kimi, GitHub Models, Ollama, LM Studio, Atomic Chat, or any
+  DeepSeek, Mistral, xAI, Qwen, Kimi, GitHub Models, Ollama, LM Studio, or any
   OpenAI-/Anthropic-compatible endpoint.
 - **Stay in control.** File writes, shell commands, network access, and
   out-of-workspace writes go through Zero's permission and sandbox policy.
@@ -182,12 +182,8 @@ zero providers add custom-openai-compatible \
   --set-active
 ```
 
-For local models, run Ollama, LM Studio, or the [Atomic Chat](https://atomic.chat)
-desktop app, then use `zero setup` or `zero providers detect`. For Atomic Chat,
-load a model and enable its local OpenAI-compatible API (default
-`http://127.0.0.1:1337/v1`). Choose `atomic-chat-local`; detection includes the
-loaded model ID in the add command. If no usable ID is discovered, load a model
-and retry. Model IDs requiring shell-specific quoting use interactive setup.
+For local models, run Ollama or LM Studio and then use `zero setup` or
+`zero providers detect`.
 
 ## Daily Use
 
@@ -277,19 +273,6 @@ zero sandbox grants list
 Zero includes local file/search/edit/shell tools, `web_fetch` for public URLs,
 and MCP support for additional tools.
 
-`web_fetch` refuses loopback, private and other special-use addresses: it checks
-the URL before asking permission, resolves the host, and dials the address it
-validated so a name cannot resolve to something else in between.
-
-If `HTTP_PROXY`/`HTTPS_PROXY` is set, `web_fetch` and the provider connectivity
-probe use it, and that last step changes: the proxy is dialed and the target
-hostname is sent to it, so the proxy decides which address the request actually
-reaches. The URL is still checked and resolved locally first, but a proxy that
-answers differently can reach a private service. A forward proxy already sees
-and can rewrite every request through it, so this is the trust you accept by
-configuring one. Leave the variables unset for the checks to be enforced end to
-end.
-
 For local dev servers, use shell commands such as `curl` through `exec_command`
 so the normal sandbox and permission policy applies. Long-running commands stay
 attached to a background terminal session and can be listed or stopped from the

README_ZH.md

@@ -23,7 +23,7 @@ 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、Atomic Chat，或任何 OpenAI/Anthropic 兼容端点。
+- **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。
@@ -114,11 +114,7 @@ export LONGCAT_API_KEY=...
 zero providers setup longcat --set-active
 ```
 
-对于本地模型，运行 Ollama、LM Studio 或 [Atomic Chat](https://atomic.chat) 桌面应用，
-然后使用 `zero setup` 或 `zero providers detect`。使用 Atomic Chat 时，请先加载模型并启用
-本地 OpenAI 兼容 API（默认地址为 `http://127.0.0.1:1337/v1`），再选择 `atomic-chat-local`。
-检测生成的添加命令会包含已加载的模型 ID；如果未发现可用的 ID，请加载模型后重试。
-对于需要特定 Shell 转义的模型 ID，请使用交互式设置。
+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
 

docs/HOW_ZERO_WORKS.md

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

docs/UPDATE.md

@@ -93,24 +93,14 @@ binary:
 
 | State on disk | Meaning |
 |---|---|
-| `<binary>.old` (or `<binary>.<suffix>.old`) plus a `.keep` marker, or a per-user update-recovery record naming that copy | A previous update could not restore the original binary. The `.old` file may be the last binary the updater verified; the installed one may be unverified. The `.keep` marker is in the installation directory and can be deleted; the identity-bound record is not, so deleting the marker alone does not end the refusal. |
+| `<binary>.old` (or `<binary>.<suffix>.old`) plus a `.keep` marker | A previous update could not restore the original binary. The `.old` file may be the last binary the updater verified; the installed one may be unverified. |
 | `<binary>.…old.<suffix>.recovery` | A previous update could not even write the marker, so it moved the last verified binary to that name. |
 | The binary is missing and one or more `*.old` files exist | The previous attempt was interrupted between moves. |
 
 The refusal names the paths involved and the two moves that end the state:
 either move the recovery binary back over the executable path, or — if the
-installed binary is the one you want — delete the recovery copy itself (not
-only the `.keep` marker) after verifying the installed binary, then update
-again. Deleting the marker alone is not enough: a failed restore also records
-that copy in per-user state outside the installation directory, and the next
-update consults that record even if the marker is gone.
-
-That trusted record lives under `%AppData%\zero\update-recovery` (per-user).
-The recovery copy and its `.keep` marker sit in the installation directory
-(per-machine). A second Windows account on the same machine does not see the
-first account's unresolved record; the sibling marker is the machine-visible
-signal for every account. There is no separate machine-wide store: writing one
-would need a shared writable location and ACL rules the updater does not own.
+installed binary is the one you want — delete the `.keep` marker (or the
+`.recovery` copy, once you have verified the installed binary) and update again.
 
 This is deliberately fail-closed and differs from older releases, which deleted
 `<binary>.old` and proceeded. The trade-off is that anyone who can write in the

go.mod

@@ -18,7 +18,6 @@ require (
 	github.com/ledongthuc/pdf v0.0.0-20250511090121-5959a4027728
 	golang.org/x/image v0.45.0
 	golang.org/x/sys v0.47.0
-	gopkg.in/yaml.v3 v3.0.1
 	mvdan.cc/sh/v3 v3.13.1
 )
 

go.sum

@@ -70,9 +70,5 @@ golang.org/x/sync v0.22.0 h1:SZjpbeLmrCk4xhRSZFNZW5gFUeCeFgjekvI/+gfScek=
 golang.org/x/sync v0.22.0/go.mod h1:9xrNwdLfx4jkKbNva9FpL6vEN7evnE43NNNJQ2LF3+0=
 golang.org/x/sys v0.47.0 h1:o7XGOvZQCADBQQ4Y7VNq2dRWQR7JmOUW8Kxx4ZsNgWs=
 golang.org/x/sys v0.47.0/go.mod h1:4GL1E5IUh+htKOUEOaiffhrAeqysfVGipDYzABqnCmw=
-gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405 h1:yhCVgyC4o1eVCa2tZl7eS0r+SDo693bJlVdllGtEeKM=
-gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
-gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA=
-gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
 mvdan.cc/sh/v3 v3.13.1 h1:DP3TfgZhDkT7lerUdnp6PTGKyxxzz6T+cOlY/xEvfWk=
 mvdan.cc/sh/v3 v3.13.1/go.mod h1:lXJ8SexMvEVcHCoDvAGLZgFJ9Wsm2sulmoNEXGhYZD0=

internal/acp/agent.go

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

internal/acp/agent_test.go

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

internal/acp/permission.go

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

internal/acp/permission_test.go

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

internal/acp/translate.go

@@ -2,10 +2,7 @@ package acp
 
 import (
 	"encoding/json"
-	"net/url"
-	"path/filepath"
 	"strings"
-	"unicode"
 	"unicode/utf8"
 
 	"github.com/Gitlawb/zero/internal/agent"
@@ -47,125 +44,12 @@ func toolKindFor(name string) string {
 
 // toolTitle builds a concise human title, e.g. "read_file src/main.go".
 func toolTitle(name, rawArgs string) string {
-	if browser, ok := browserToolDetails(name); ok {
-		return browserToolTitle(browser.Command, rawArgs)
-	}
 	if hint := primaryArgHint(rawArgs); hint != "" {
 		return name + " " + hint
 	}
 	return name
 }
 
-// browserToolDetails identifies ZERO's local browser helpers without treating
-// similarly named MCP tools as browser automation. The descriptor intentionally
-// contains no request data: ACP tool input is already protocol-visible, but a
-// durable UI must not need to retain text, local CDP targets, or full URLs just
-// to recognise the browser operation.
-func browserToolDetails(name string) (*BrowserToolDetails, bool) {
-	const prefix = "browser_"
-	command, ok := strings.CutPrefix(name, prefix)
-	if !ok {
-		return nil, false
-	}
-	switch command {
-	case "install", "launch", "connect", "open", "snapshot", "click", "type", "press", "action":
-		return &BrowserToolDetails{Version: 1, Command: command}, true
-	default:
-		return nil, false
-	}
-}
-
-const zeroBrowserMetaKey = "github.com/Gitlawb/zero/browser"
-
-// attachBrowserToolDetails stores ZERO's browser descriptor in ACP's reserved
-// extension channel. Keeping this in one helper prevents start, result, and
-// permission payloads from drifting onto different wire shapes.
-func attachBrowserToolDetails(update *ToolCallUpdate, name string) {
-	browser, ok := browserToolDetails(name)
-	if !ok {
-		return
-	}
-	raw, err := json.Marshal(browser)
-	if err != nil {
-		return
-	}
-	update.Meta = map[string]json.RawMessage{zeroBrowserMetaKey: raw}
-}
-
-// browserToolTitle avoids putting browser_type text, an attached DevTools
-// endpoint, or a URL query/fragment in a tool-card title. Those values can
-// carry credentials or session data; the UI only needs the operation and, for
-// navigation, a human-recognisable origin.
-func browserToolTitle(command, rawArgs string) string {
-	switch command {
-	case "action":
-		action, ok := exactJSONStringArg(rawArgs, "command")
-		if !ok {
-			return "browser action"
-		}
-		if action, ok := tools.NormalizedBrowserActionCommand(action); ok {
-			return "browser action " + action
-		}
-		return "browser action"
-	case "open":
-		rawURL, ok := exactJSONStringArg(rawArgs, "url")
-		if !ok {
-			return "browser open"
-		}
-		normalized, err := tools.NormalizeBrowserOpenURL(rawURL)
-		if err != nil {
-			return "browser open"
-		}
-		u, err := url.Parse(normalized)
-		if err != nil || u.Scheme == "" || u.Host == "" {
-			return "browser open"
-		}
-		origin := u.Scheme + "://" + u.Host
-		if !browserTitleTextSafe(origin) {
-			return "browser open"
-		}
-		return "browser open " + truncateHint(origin)
-	default:
-		return "browser " + command
-	}
-}
-
-// browserTitleTextSafe validates text after URL parsing has decoded escaped
-// UTF-8 in the host. Valid UTF-8 alone is not presentation-safe: control,
-// format/bidi, and line/paragraph separator runes can reorder or split the
-// permission label shown to a user. The execution URL remains unchanged.
-func browserTitleTextSafe(text string) bool {
-	if !utf8.ValidString(text) {
-		return false
-	}
-	for _, r := range text {
-		if unicode.IsControl(r) || unicode.Is(unicode.Cf, r) || unicode.Is(unicode.Zl, r) || unicode.Is(unicode.Zp, r) {
-			return false
-		}
-	}
-	return true
-}
-
-// exactJSONStringArg mirrors ZERO's map-based tool argument decoding: only the
-// exact JSON key is considered, and a non-string value is invalid. In
-// particular, an incidental "URL" key must not change a permission title when
-// browser_open will only read "url".
-func exactJSONStringArg(rawArgs, key string) (string, bool) {
-	var args map[string]json.RawMessage
-	if json.Unmarshal([]byte(rawArgs), &args) != nil {
-		return "", false
-	}
-	raw, ok := args[key]
-	if !ok {
-		return "", false
-	}
-	var value string
-	if json.Unmarshal(raw, &value) != nil {
-		return "", false
-	}
-	return value, true
-}
-
 // primaryArgHint extracts the most relevant argument (path/pattern/command) from
 // raw JSON arguments. Best-effort; returns "" when it can't parse.
 func primaryArgHint(rawArgs string) string {
@@ -205,7 +89,7 @@ func rawInput(args string) json.RawMessage {
 // toolCallStart maps an advertised ZERO tool call to the initial ACP "tool_call"
 // update (status in_progress — ZERO executes immediately after advertising).
 func toolCallStart(call agent.ToolCall) ToolCallUpdate {
-	upd := ToolCallUpdate{
+	return ToolCallUpdate{
 		SessionUpdate: UpdateToolCall,
 		ToolCallID:    call.ID,
 		Title:         toolTitle(call.Name, call.Arguments),
@@ -213,8 +97,6 @@ func toolCallStart(call agent.ToolCall) ToolCallUpdate {
 		Status:        ToolStatusInProgress,
 		RawInput:      rawInput(call.Arguments),
 	}
-	attachBrowserToolDetails(&upd, call.Name)
-	return upd
 }
 
 // toolCallResult maps a finished ZERO tool result to a "tool_call_update".
@@ -234,64 +116,26 @@ func toolCallResult(result agent.ToolResult) ToolCallUpdate {
 	if locs := toolResultLocations(result); len(locs) > 0 {
 		upd.Locations = locs
 	}
-	attachBrowserToolDetails(&upd, result.Name)
 	return upd
 }
 
 func toolResultContent(result agent.ToolResult) []ToolCallContent {
-	content := make([]ToolCallContent, 0, 1+len(result.FileDiffs))
 	text := strings.TrimRight(result.Output, "\n")
 	if text == "" {
 		text = result.Display.Summary
 	}
 	if text == "" {
-		return appendToolResultDiffs(content, result.FileDiffs)
+		return nil
 	}
-	content = append(content, ToolContent(TextBlock(text)))
-	return appendToolResultDiffs(content, result.FileDiffs)
-}
-
-func appendToolResultDiffs(content []ToolCallContent, diffs []tools.FileDiff) []ToolCallContent {
-	for _, diff := range diffs {
-		if !filepath.IsAbs(diff.Path) || (!diff.OldExists && !diff.NewExists) {
-			continue
-		}
-		var oldText *string
-		if diff.OldExists {
-			old := diff.OldText
-			oldText = &old
-		}
-		var newText *string
-		if diff.NewExists {
-			updated := diff.NewText
-			newText = &updated
-		}
-		content = append(content, ToolCallContent{Type: "diff", Path: diff.Path, OldText: oldText, NewText: newText})
-	}
-	return content
+	return []ToolCallContent{ToolContent(TextBlock(text))}
 }
 
 func toolResultLocations(result agent.ToolResult) []ToolCallLocation {
-	locs := make([]ToolCallLocation, 0, len(result.FileDiffs)+len(result.ChangedFiles))
-	seen := make(map[string]bool, len(result.FileDiffs)+len(result.ChangedFiles))
-	for _, diff := range result.FileDiffs {
-		path := diff.Path
-		if path == "" || seen[path] {
-			continue
-		}
-		seen[path] = true
-		locs = append(locs, ToolCallLocation{Path: path})
-	}
-	// FileDiff.Path is canonical absolute path data while ChangedFiles is
-	// normally workspace-relative. Without the trusted workspace root these
-	// coordinate systems cannot be correlated safely: a suffix match would let
-	// /workspace/sub/a.go consume the fallback for a distinct root a.go. The
-	// shared seen set deduplicates only identities already exactly comparable.
+	locs := make([]ToolCallLocation, 0, len(result.ChangedFiles))
 	for _, f := range result.ChangedFiles {
-		if f == "" || seen[f] {
+		if strings.TrimSpace(f) == "" {
 			continue
 		}
-		seen[f] = true
 		locs = append(locs, ToolCallLocation{Path: f})
 	}
 	return locs

internal/acp/translate_test.go

@@ -1,30 +1,14 @@
 package acp
 
 import (
-	"encoding/json"
-	"path/filepath"
 	"strings"
 	"testing"
-	"unicode"
 	"unicode/utf8"
 
 	"github.com/Gitlawb/zero/internal/agent"
 	"github.com/Gitlawb/zero/internal/tools"
 )
 
-func browserDescriptor(t *testing.T, update ToolCallUpdate) BrowserToolDetails {
-	t.Helper()
-	raw, ok := update.Meta[zeroBrowserMetaKey]
-	if !ok {
-		t.Fatalf("browser metadata = %#v, want %q", update.Meta, zeroBrowserMetaKey)
-	}
-	var details BrowserToolDetails
-	if err := json.Unmarshal(raw, &details); err != nil {
-		t.Fatalf("decode browser metadata: %v", err)
-	}
-	return details
-}
-
 func TestAgentMessageAndThoughtChunks(t *testing.T) {
 	m := agentMessageChunk("hello")
 	if m.SessionUpdate != UpdateAgentMessageChunk || m.Content.Type != "text" || m.Content.Text != "hello" {
@@ -72,217 +56,6 @@ func TestToolTitleAndHint(t *testing.T) {
 	}
 }
 
-func TestBrowserToolUpdatesAreStructuredAndPresentationSafe(t *testing.T) {
-	start := toolCallStart(agent.ToolCall{
-		ID:        "browser-1",
-		Name:      "browser_open",
-		Arguments: `{"url":"https://example.com/settings?token=not-for-a-title#account"}`,
-	})
-	if got := browserDescriptor(t, start); got != (BrowserToolDetails{Version: 1, Command: "open"}) {
-		t.Fatalf("browser descriptor = %#v, want open", got)
-	}
-	if start.Title != "browser open https://example.com" {
-		t.Fatalf("browser title = %q", start.Title)
-	}
-	if strings.Contains(start.Title, "token=") || strings.Contains(start.Title, "#account") {
-		t.Fatalf("browser title leaked URL-sensitive data: %q", start.Title)
-	}
-	encoded, err := json.Marshal(start)
-	if err != nil {
-		t.Fatal(err)
-	}
-	var wire struct {
-		Meta map[string]json.RawMessage `json:"_meta"`
-	}
-	if err := json.Unmarshal(encoded, &wire); err != nil {
-		t.Fatal(err)
-	}
-	if _, ok := wire.Meta[zeroBrowserMetaKey]; !ok {
-		t.Fatalf("browser wire metadata = %#v", wire.Meta)
-	}
-
-	typed := toolCallStart(agent.ToolCall{
-		ID:        "browser-2",
-		Name:      "browser_type",
-		Arguments: `{"ref":"email","text":"[email protected]"}`,
-	})
-	if got := browserDescriptor(t, typed); got.Command != "type" {
-		t.Fatalf("browser type descriptor = %#v", got)
-	}
-	if typed.Title != "browser type" || strings.Contains(typed.Title, "[email protected]") {
-		t.Fatalf("browser type title = %q", typed.Title)
-	}
-
-	action := toolCallStart(agent.ToolCall{
-		ID:        "browser-3",
-		Name:      "browser_action",
-		Arguments: `{"command":"keyboard_insert_text","args":["[email protected]"]}`,
-	})
-	if action.Title != "browser action keyboard_insert_text" {
-		t.Fatalf("browser action title = %q", action.Title)
-	}
-
-	result := toolCallResult(agent.ToolResult{
-		ToolCallID: "browser-2",
-		Name:       "browser_type",
-		Status:     tools.StatusOK,
-	})
-	if got := browserDescriptor(t, result); got.Command != "type" {
-		t.Fatalf("browser result descriptor = %#v", got)
-	}
-}
-
-func TestBrowserDescriptorSurvivesProtocolShapedRoundTrip(t *testing.T) {
-	updates := []ToolCallUpdate{
-		toolCallStart(agent.ToolCall{
-			ID:        "start",
-			Name:      "browser_open",
-			Arguments: `{"url":"https://user:[email protected]/private?token=secret#fragment"}`,
-		}),
-		toolCallResult(agent.ToolResult{
-			ToolCallID: "result",
-			Name:       "browser_type",
-			Status:     tools.StatusOK,
-		}),
-		permissionToolCall(agent.PermissionRequest{
-			ToolCallID: "permission",
-			ToolName:   "browser_connect",
-			Args:       map[string]any{"target": "127.0.0.1:9222"},
-		}),
-	}
-
-	type protocolToolCallUpdate struct {
-		SessionUpdate string                     `json:"sessionUpdate,omitempty"`
-		ToolCallID    string                     `json:"toolCallId"`
-		Title         string                     `json:"title,omitempty"`
-		Kind          string                     `json:"kind,omitempty"`
-		Status        string                     `json:"status,omitempty"`
-		RawInput      json.RawMessage            `json:"rawInput,omitempty"`
-		Content       []ToolCallContent          `json:"content,omitempty"`
-		Locations     []ToolCallLocation         `json:"locations,omitempty"`
-		Meta          map[string]json.RawMessage `json:"_meta,omitempty"`
-	}
-
-	for _, update := range updates {
-		encoded, err := json.Marshal(update)
-		if err != nil {
-			t.Fatal(err)
-		}
-		var root map[string]json.RawMessage
-		if err := json.Unmarshal(encoded, &root); err != nil {
-			t.Fatal(err)
-		}
-		if _, ok := root["browser"]; ok {
-			t.Fatalf("browser descriptor escaped ACP _meta: %s", encoded)
-		}
-
-		var protocol protocolToolCallUpdate
-		if err := json.Unmarshal(encoded, &protocol); err != nil {
-			t.Fatal(err)
-		}
-		forwarded, err := json.Marshal(protocol)
-		if err != nil {
-			t.Fatal(err)
-		}
-		var roundTripped ToolCallUpdate
-		if err := json.Unmarshal(forwarded, &roundTripped); err != nil {
-			t.Fatal(err)
-		}
-		details := browserDescriptor(t, roundTripped)
-		if details.Version != 1 || details.Command == "" {
-			t.Fatalf("round-tripped browser descriptor = %#v", details)
-		}
-		descriptorJSON := string(roundTripped.Meta[zeroBrowserMetaKey])
-		for _, secret := range []string{"password", "private", "token", "fragment", "127.0.0.1", "9222"} {
-			if strings.Contains(descriptorJSON, secret) {
-				t.Fatalf("browser descriptor leaked %q: %s", secret, descriptorJSON)
-			}
-		}
-	}
-}
-
-func TestBrowserPermissionTitlesMirrorSafeToolArguments(t *testing.T) {
-	if got := browserToolTitle("open", `{"url":"evil.example.test/pay?token=hidden#fragment"}`); got != "browser open https://evil.example.test" {
-		t.Fatalf("bare-host title = %q", got)
-	}
-	if got := browserToolTitle("open", `{"URL":"https://different.example.test"}`); got != "browser open" {
-		t.Fatalf("case-variant URL title = %q", got)
-	}
-	if got := browserToolTitle("open", `{"URL":"https://different.example.test","url":"https://actual.example.test/path"}`); got != "browser open https://actual.example.test" {
-		t.Fatalf("exact URL key title = %q", got)
-	}
-	if got := browserToolTitle("action", `{"command":"not an action"}`); got != "browser action" {
-		t.Fatalf("unknown browser action title = %q", got)
-	}
-
-	longHost := "https://" + strings.Repeat("a", 200) + ".example.test/path?token=hidden"
-	title := browserToolTitle("open", `{"url":"`+longHost+`"}`)
-	if !utf8.ValidString(title) || utf8.RuneCountInString(title) > len("browser open ")+61 || strings.Contains(title, "token=") {
-		t.Fatalf("bounded browser origin title = %q", title)
-	}
-}
-
-func TestBrowserOpenTitlesRejectDecodedUnicodePresentationControls(t *testing.T) {
-	for _, rawURL := range []string{
-		"https://safe.example%E2%80%AEevil.test/path",
-		"https://safe.example%E2%81%A6evil.test/path",
-		"https://safe.example%C2%85evil.test/path",
-		"https://safe.example%E2%80%A8evil.test/path",
-		"https://safe.example%E2%80%A9evil.test/path",
-	} {
-		t.Run(rawURL, func(t *testing.T) {
-			normalized, err := tools.NormalizeBrowserOpenURL(rawURL)
-			if err != nil {
-				t.Fatalf("execution URL rejected: %v", err)
-			}
-			if normalized != rawURL {
-				t.Fatalf("execution URL = %q, want unchanged %q", normalized, rawURL)
-			}
-
-			args, err := json.Marshal(map[string]any{"url": rawURL})
-			if err != nil {
-				t.Fatal(err)
-			}
-			updates := []ToolCallUpdate{
-				toolCallStart(agent.ToolCall{ID: "start", Name: "browser_open", Arguments: string(args)}),
-				permissionToolCall(agent.PermissionRequest{ToolCallID: "permission", ToolName: "browser_open", Args: map[string]any{"url": rawURL}}),
-			}
-			for _, update := range updates {
-				encoded, err := json.Marshal(update)
-				if err != nil {
-					t.Fatal(err)
-				}
-				var decoded ToolCallUpdate
-				if err := json.Unmarshal(encoded, &decoded); err != nil {
-					t.Fatal(err)
-				}
-				if decoded.Title != "browser open" {
-					t.Fatalf("unsafe browser title survived wire round trip: %q", decoded.Title)
-				}
-				for _, r := range decoded.Title {
-					if unicode.IsControl(r) || unicode.Is(unicode.Cf, r) || unicode.Is(unicode.Zl, r) || unicode.Is(unicode.Zp, r) {
-						t.Fatalf("browser title contains unsafe presentation rune %U: %q", r, decoded.Title)
-					}
-				}
-			}
-		})
-	}
-}
-
-func TestBrowserDescriptorDoesNotClaimSimilarlyNamedMCPTools(t *testing.T) {
-	start := toolCallStart(agent.ToolCall{ID: "mcp-1", Name: "browser_plugin_open", Arguments: `{}`})
-	if len(start.Meta) != 0 {
-		t.Fatalf("MCP-like tool received built-in browser metadata: %#v", start.Meta)
-	}
-	encoded, err := json.Marshal(start)
-	if err != nil {
-		t.Fatal(err)
-	}
-	if strings.Contains(string(encoded), `"browser"`) {
-		t.Fatalf("non-browser tool encoded browser field: %s", encoded)
-	}
-}
-
 func TestToolCallStart(t *testing.T) {
 	upd := toolCallStart(agent.ToolCall{ID: "tc1", Name: "read_file", Arguments: `{"path":"a.go"}`})
 	if upd.SessionUpdate != UpdateToolCall {
@@ -301,26 +74,21 @@ func TestToolCallStart(t *testing.T) {
 }
 
 func TestToolCallResult(t *testing.T) {
-	path := filepath.Join(t.TempDir(), "a.go")
 	ok := toolCallResult(agent.ToolResult{
 		ToolCallID:   "tc1",
 		Name:         "edit_file",
 		Status:       tools.StatusOK,
 		Output:       "applied\n",
 		ChangedFiles: []string{"a.go", ""},
-		FileDiffs:    []tools.FileDiff{{Path: path, OldExists: true, NewExists: true, OldText: "before\n", NewText: "after\n"}},
 	})
 	if ok.SessionUpdate != UpdateToolCallUpdate || ok.Status != ToolStatusCompleted {
 		t.Fatalf("unexpected ok result: %+v", ok)
 	}
-	if len(ok.Content) != 2 || ok.Content[0].Type != "content" || ok.Content[0].Content.Text != "applied" {
+	if len(ok.Content) != 1 || ok.Content[0].Type != "content" || ok.Content[0].Content.Text != "applied" {
 		t.Fatalf("unexpected content: %+v", ok.Content)
 	}
-	if diff := ok.Content[1]; diff.Type != "diff" || diff.Path != path || diff.OldText == nil || *diff.OldText != "before\n" || diff.NewText == nil || *diff.NewText != "after\n" {
-		t.Fatalf("unexpected diff content: %+v", diff)
-	}
-	if len(ok.Locations) != 2 || ok.Locations[0].Path != path || ok.Locations[1].Path != "a.go" {
-		t.Fatalf("unproven absolute/relative aliases must both remain visible, got %+v", ok.Locations)
+	if len(ok.Locations) != 1 || ok.Locations[0].Path != "a.go" {
+		t.Fatalf("blank changed files should be dropped, got %+v", ok.Locations)
 	}
 
 	failed := toolCallResult(agent.ToolResult{ToolCallID: "tc2", Status: tools.StatusError, Output: "boom"})
@@ -329,190 +97,6 @@ func TestToolCallResult(t *testing.T) {
 	}
 }
 
-func TestToolCallDiffJSONDistinguishesEmptyFilesAndDeletion(t *testing.T) {
-	path := filepath.Join(t.TempDir(), "empty.txt")
-	content := appendToolResultDiffs(nil, []tools.FileDiff{
-		{Path: path, OldExists: false, NewExists: true, NewText: ""},
-		{Path: path, OldExists: true, NewExists: true, OldText: "before", NewText: ""},
-		{Path: path, OldExists: true, NewExists: false, OldText: "before"},
-	})
-	if len(content) != 3 {
-		t.Fatalf("diff content = %#v", content)
-	}
-	for index, diff := range content {
-		encoded, err := json.Marshal(diff)
-		if err != nil {
-			t.Fatal(err)
-		}
-		var wire map[string]any
-		if err := json.Unmarshal(encoded, &wire); err != nil {
-			t.Fatal(err)
-		}
-		if wire["path"] != path {
-			t.Fatalf("wire diff %d = %s", index, encoded)
-		}
-		switch index {
-		case 0:
-			oldText, present := wire["oldText"]
-			if !present || oldText != nil || wire["newText"] != "" {
-				t.Fatalf("create diff = %s, want null oldText and empty newText", encoded)
-			}
-		case 1:
-			if wire["oldText"] != "before" || wire["newText"] != "" {
-				t.Fatalf("empty replacement diff = %s", encoded)
-			}
-		case 2:
-			newText, present := wire["newText"]
-			if wire["oldText"] != "before" || !present || newText != nil {
-				t.Fatalf("deletion diff = %s, want oldText and null newText", encoded)
-			}
-		}
-	}
-}
-
-func TestToolResultLocationsPreserveDistinctPathIdentities(t *testing.T) {
-	root := t.TempDir()
-	rootPath := filepath.Join(root, "a.go")
-	nestedPath := filepath.Join(root, "sub", "a.go")
-	diff := func(path string) tools.FileDiff {
-		return tools.FileDiff{Path: path, OldExists: true, NewExists: true, OldText: "before", NewText: "after"}
-	}
-	for _, tc := range []struct {
-		name  string
-		diffs []tools.FileDiff
-		want  []string
-	}{
-		{name: "both rich", diffs: []tools.FileDiff{diff(rootPath), diff(nestedPath)}, want: []string{rootPath, nestedPath, "a.go", filepath.Join("sub", "a.go")}},
-		{name: "root rich", diffs: []tools.FileDiff{diff(rootPath)}, want: []string{rootPath, "a.go", filepath.Join("sub", "a.go")}},
-		{name: "nested rich", diffs: []tools.FileDiff{diff(nestedPath)}, want: []string{nestedPath, "a.go", filepath.Join("sub", "a.go")}},
-	} {
-		t.Run(tc.name, func(t *testing.T) {
-			locations := toolResultLocations(agent.ToolResult{
-				ChangedFiles: []string{"a.go", filepath.Join("sub", "a.go")},
-				FileDiffs:    tc.diffs,
-			})
-			if len(locations) != len(tc.want) {
-				t.Fatalf("locations = %#v, want %#v", locations, tc.want)
-			}
-			for index := range tc.want {
-				if locations[index].Path != tc.want[index] {
-					t.Fatalf("locations = %#v, want %#v", locations, tc.want)
-				}
-			}
-		})
-	}
-}
-
-func TestToolCallResultPreservesWhitespaceInFilePaths(t *testing.T) {
-	relativePath := " report.txt "
-	absolutePath := filepath.Join(t.TempDir(), relativePath)
-	update := toolCallResult(agent.ToolResult{
-		ChangedFiles: []string{relativePath},
-		FileDiffs: []tools.FileDiff{{
-			Path: absolutePath, OldExists: true, NewExists: true, OldText: "before", NewText: "after",
-		}},
-	})
-	if len(update.Content) != 1 || update.Content[0].Path != absolutePath {
-		t.Fatalf("diff content path = %#v, want %q", update.Content, absolutePath)
-	}
-	if len(update.Locations) != 2 || update.Locations[0].Path != absolutePath || update.Locations[1].Path != relativePath {
-		t.Fatalf("locations = %#v, want exact paths %q and %q", update.Locations, absolutePath, relativePath)
-	}
-}
-
-func TestToolResultLocationsDeduplicateOnlyExactPaths(t *testing.T) {
-	path := filepath.Join(t.TempDir(), "a.go")
-	locations := toolResultLocations(agent.ToolResult{
-		ChangedFiles: []string{path, path},
-		FileDiffs:    []tools.FileDiff{{Path: path, OldExists: true, NewExists: true, OldText: "before", NewText: "after"}},
-	})
-	if len(locations) != 1 || locations[0].Path != path {
-		t.Fatalf("exact duplicate locations = %#v", locations)
-	}
-}
-
-func TestDeletedFileEmitsDiffAndKeepsLocations(t *testing.T) {
-	relativePath := "deleted.go"
-	absolutePath := filepath.Join(t.TempDir(), relativePath)
-	update := toolCallResult(agent.ToolResult{
-		ChangedFiles: []string{relativePath},
-		FileDiffs: []tools.FileDiff{{
-			Path: absolutePath, OldExists: true, NewExists: false, OldText: "before",
-		}},
-	})
-	if len(update.Content) != 1 || update.Content[0].OldText == nil || *update.Content[0].OldText != "before" || update.Content[0].NewText != nil {
-		t.Fatalf("deleted file diff = %#v, want oldText with null newText", update.Content)
-	}
-	if len(update.Locations) != 2 || update.Locations[0].Path != absolutePath || update.Locations[1].Path != relativePath {
-		t.Fatalf("deleted file locations = %#v", update.Locations)
-	}
-}
-
-func TestToolCallResultEmitsOnlyRedactedFileDiffs(t *testing.T) {
-	secret := "sk-proj-abcdefghijklmnopqrstuvwxyz"
-	path := filepath.Join(t.TempDir(), "secret.txt")
-	scrubbed := tools.ScrubResultSecrets(tools.Result{FileDiffs: []tools.FileDiff{{
-		Path: path, OldExists: true, NewExists: true, OldText: "token=" + secret, NewText: "safe",
-	}}})
-	update := toolCallResult(agent.ToolResult{ToolCallID: "call", Status: tools.StatusError, FileDiffs: scrubbed.FileDiffs})
-	if len(update.Content) != 1 || update.Content[0].OldText == nil || strings.Contains(*update.Content[0].OldText, secret) {
-		t.Fatalf("ACP content leaked unredacted diff: %#v", update.Content)
-	}
-}
-
-func TestToolCallResultOmitsSemanticallyUnchangedRedactedDiff(t *testing.T) {
-	oldSecret := "ghp_ABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789"
-	newSecret := "ghp_9876543210ZYXWVUTSRQPONMLKJIHGFEDCBA"
-	scrubbed := tools.ScrubResultSecrets(tools.Result{
-		ChangedFiles: []string{"credentials.txt"},
-		FileDiffs: []tools.FileDiff{{
-			Path: filepath.Join(t.TempDir(), "credentials.txt"), OldExists: true, NewExists: true,
-			OldText: "token=" + oldSecret, NewText: "token=" + newSecret,
-		}},
-	})
-	update := toolCallResult(agent.ToolResult{
-		ToolCallID: "call", Status: tools.StatusOK,
-		ChangedFiles: scrubbed.ChangedFiles, FileDiffs: scrubbed.FileDiffs,
-	})
-	if len(update.Content) != 0 {
-		t.Fatalf("ACP emitted semantically unchanged redacted diff: %#v", update.Content)
-	}
-	if len(update.Locations) != 1 || update.Locations[0].Path != "credentials.txt" {
-		t.Fatalf("ACP path fallback = %#v", update.Locations)
-	}
-}
-
-func TestToolCallResultOmitsDefaultIgnorableSplitSecretsOnEitherSide(t *testing.T) {
-	secret := "sk-ant-api03-AAAABBBBCCCCDDDDEEEEFFFFGGGG"
-	for name, separator := range map[string]string{
-		"combining grapheme joiner": "\u034f",
-		"variation selector":        "\ufe0f",
-	} {
-		for _, side := range []string{"old", "new"} {
-			t.Run(name+" "+side, func(t *testing.T) {
-				obfuscated := secret[:20] + separator + secret[20:]
-				diff := tools.FileDiff{
-					Path: filepath.Join(t.TempDir(), "secret.txt"), OldExists: true, NewExists: true,
-					OldText: "safe old", NewText: "safe new",
-				}
-				if side == "old" {
-					diff.OldText = obfuscated
-				} else {
-					diff.NewText = obfuscated
-				}
-				scrubbed := tools.ScrubResultSecrets(tools.Result{FileDiffs: []tools.FileDiff{diff}})
-				if !scrubbed.Redacted || len(scrubbed.FileDiffs) != 0 {
-					t.Fatalf("registry boundary retained an obfuscated secret: %#v", scrubbed)
-				}
-				update := toolCallResult(agent.ToolResult{ToolCallID: "call", Status: tools.StatusOK, FileDiffs: scrubbed.FileDiffs})
-				if len(update.Content) != 0 {
-					t.Fatalf("ACP content retained an obfuscated secret: %#v", update.Content)
-				}
-			})
-		}
-	}
-}
-
 func TestPlanUpdateAndStatus(t *testing.T) {
 	upd := planUpdate([]tools.PlanItem{
 		{Content: "step a", Status: "completed"},

internal/acp/types.go

@@ -210,21 +210,6 @@ type ToolCallUpdate struct {
 	RawInput      json.RawMessage    `json:"rawInput,omitempty"`
 	Content       []ToolCallContent  `json:"content,omitempty"`
 	Locations     []ToolCallLocation `json:"locations,omitempty"`
-	// Meta is ACP's extension channel. ZERO-owned values must remain beneath a
-	// namespaced key so protocol-shaped clients can preserve them while decoding
-	// and re-encoding a tool call.
-	Meta map[string]json.RawMessage `json:"_meta,omitempty"`
-}
-
-// BrowserToolDetails identifies the browser helper operation behind a tool
-// call. Version is the schema version for this optional ZERO extension;
-// Command is one of install, launch, connect, open, snapshot, click, type,
-// press, or action. Future fields must remain display-safe and must not
-// include browser profile data, cookies, typed text, URL paths/queries, or
-// DevTools endpoints.
-type BrowserToolDetails struct {
-	Version int    `json:"version"`
-	Command string `json:"command"`
 }
 
 // ToolCallContent is a tool call's rendered output. ZERO emits "content" (a
@@ -235,30 +220,9 @@ type ToolCallContent struct {
 	// type == "content"
 	Content *ContentBlock `json:"content,omitempty"`
 	// type == "diff"
-	Path    string  `json:"path,omitempty"`
-	OldText *string `json:"oldText,omitempty"`
-	NewText *string `json:"newText,omitempty"`
-}
-
-// MarshalJSON preserves ACP's discriminated content union. A diff always has
-// path, while nullable oldText/newText distinguish creation, deletion, and an
-// existing file replaced with empty content. Other content variants omit all
-// diff fields rather than serializing irrelevant nulls.
-func (content ToolCallContent) MarshalJSON() ([]byte, error) {
-	if content.Type == "diff" {
-		return json.Marshal(struct {
-			Type    string  `json:"type"`
-			Path    string  `json:"path"`
-			OldText *string `json:"oldText"`
-			NewText *string `json:"newText"`
-		}{
-			Type: content.Type, Path: content.Path, OldText: content.OldText, NewText: content.NewText,
-		})
-	}
-	return json.Marshal(struct {
-		Type    string        `json:"type"`
-		Content *ContentBlock `json:"content,omitempty"`
-	}{Type: content.Type, Content: content.Content})
+	Path    string `json:"path,omitempty"`
+	OldText string `json:"oldText,omitempty"`
+	NewText string `json:"newText,omitempty"`
 }
 
 func ToolContent(block ContentBlock) ToolCallContent {

internal/agent/compaction.go

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

internal/agent/compaction_cheap_test.go

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

internal/agent/loop.go

@@ -846,21 +846,11 @@ func Run(ctx context.Context, prompt string, provider Provider, options Options)
 					options.ServiceTier = ""
 					planner.config.serviceTier = ""
 					options.Trace.Counter(trace.CounterModelSwitches, 1)
-					// Re-derive the context window for the new model so compaction and
-					// the OnContext budget report track the model actually in force —
-					// without this a switch to a smaller-window model can overflow the
-					// target, and a switch to a larger one over-compacts. An unknown
-					// model (<= 0) keeps the original window. The compactor also
-					// re-resolves its dedicated summarizer against the new model.
-					window := 0
-					if options.ContextWindowFor != nil {
-						window = options.ContextWindowFor(turnRequestedModel)
-					}
-					if window > 0 {
-						options.ContextWindow = window
-						planner.config.contextWindow = window
-					}
-					compactor.switchModel(turnRequestedModel, window)
+					// KNOWN LIMITATION (deferred): the compactor's context-window budget
+					// is fixed at run start from options.ContextWindow and is NOT updated
+					// here, so a switch to a model with a different window keeps compacting
+					// against the original budget. Fixing it needs the switcher to also
+					// report the new window — out of scope for this change.
 				}
 			}
 		}
@@ -1527,7 +1517,6 @@ func executeToolCall(ctx context.Context, registry *tools.Registry, call ToolCal
 		Images:          result.Images,
 		Redacted:        result.Redacted,
 		ChangedFiles:    result.ChangedFiles,
-		FileDiffs:       result.FileDiffs,
 		ChangeSummaries: result.ChangeSummaries,
 		Display:         result.HumanDisplay(),
 		Outcome:         result.Outcome,
@@ -1834,10 +1823,6 @@ func runToolForUnsandboxedRetry(ctx context.Context, registry *tools.Registry, n
 }
 
 func toolResultFromPrePermissionReject(call ToolCall, result tools.Result) ToolResult {
-	// PrePermissionRejecter runs before Registry.RunWithOptions, so it must
-	// explicitly cross the same transcript/redaction boundary before its result
-	// can be forwarded through ACP.
-	result = tools.ScrubResultSecrets(result)
 	output, outputRedacted := scrubInterceptedOutput(result.Output)
 	display := result.Display
 	summary, summaryRedacted := scrubInterceptedOutput(display.Summary)
@@ -1865,7 +1850,6 @@ func toolResultFromPrePermissionReject(call ToolCall, result tools.Result) ToolR
 		Meta:            meta,
 		Redacted:        result.Redacted || outputRedacted || summaryRedacted || metaRedacted,
 		ChangedFiles:    result.ChangedFiles,
-		FileDiffs:       result.FileDiffs,
 		ChangeSummaries: result.ChangeSummaries,
 		Display:         display,
 		LoadedTools:     loadedToolsFromResult(meta),
@@ -2159,7 +2143,6 @@ func askUserFallbackResult(ctx context.Context, registry *tools.Registry, call T
 			Meta:            result.Meta,
 			Redacted:        result.Redacted,
 			ChangedFiles:    result.ChangedFiles,
-			FileDiffs:       result.FileDiffs,
 			ChangeSummaries: result.ChangeSummaries,
 			Display:         result.HumanDisplay(),
 			Outcome:         result.Outcome,

internal/agent/loop_test.go

@@ -27,23 +27,6 @@ type mockProvider struct {
 	requests []zeroruntime.CompletionRequest
 }
 
-func TestPrePermissionRejectScrubsFileDiffs(t *testing.T) {
-	secret := "sk-proj-abcdefghijklmnopqrstuvwxyz"
-	result := toolResultFromPrePermissionReject(ToolCall{ID: "call", Name: "test"}, tools.Result{
-		Status: tools.StatusError,
-		FileDiffs: []tools.FileDiff{{
-			Path:      filepath.Join(t.TempDir(), "secret.txt"),
-			OldExists: true,
-			NewExists: true,
-			OldText:   "token=" + secret,
-			NewText:   "safe",
-		}},
-	})
-	if len(result.FileDiffs) != 1 || strings.Contains(result.FileDiffs[0].OldText, secret) || !result.Redacted {
-		t.Fatalf("pre-permission FileDiff = %#v, redacted = %t", result.FileDiffs, result.Redacted)
-	}
-}
-
 func TestTypedExecutionOutcomeOverridesLegacySandboxHeuristics(t *testing.T) {
 	engine := sandbox.NewEngine(sandbox.EngineOptions{WorkspaceRoot: t.TempDir(), Policy: sandbox.DefaultPolicy()})
 	call := ToolCall{Name: tools.ExecCommandToolName}

internal/agent/prompt_budget_test.go

@@ -1,11 +1,9 @@
 package agent
 
 import (
-	"strings"
 	"testing"
 
 	"github.com/Gitlawb/zero/internal/tools"
-	"github.com/Gitlawb/zero/internal/zeroruntime"
 )
 
 // These ceilings are a deliberate ratchet on Zero's fixed per-turn overhead — the
@@ -35,24 +33,7 @@ const (
 	// The ratchet did its job: it caught the creep and forced a decision instead
 	// of a drift. That is the point of it, so keep raising it deliberately rather
 	// than reflexively.
-	//
-	// THIS COUNTS THE SCHEMAS ONLY, NOT THE HOST'S SHELL GUIDANCE. Until
-	// 2026-09-07 it counted both, and that made it a different measurement on
-	// every machine: exec_command appends shell guidance whose size depends on
-	// which shell was detected, so the same tree measured 3498 on Linux, ~3600 on
-	// a Windows host with pwsh 7, and 3653 on Windows PowerShell 5.1, which is
-	// stock Windows. The 5.1 case has been over this ceiling since view_image
-	// landed, so `go test ./...` failed for anyone on a stock Windows box while
-	// CI stayed green, because the runners have pwsh 7 and take the cheaper
-	// branch. A budget that passes or fails on which PowerShell happens to be
-	// installed is not ratcheting anything.
 	maxEagerToolSchemaTokens = 3650
-	// The host-specific half, ratcheted on its own so it cannot creep either.
-	// Measured 2026-09-07: Windows PowerShell 5.1 is the most expensive host at
-	// 155 tokens (722 chars), pwsh 7 is 110, cmd.exe is 87, and every POSIX host
-	// is 0 because no guidance is appended there. Set above the worst case, not
-	// above whatever this machine happens to be.
-	maxExecCommandShellGuidanceTokens = 200
 )
 
 func TestSystemPromptTokenBudget(t *testing.T) {
@@ -75,35 +56,8 @@ func TestEagerToolSchemaTokenBudget(t *testing.T) {
 	// 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{})
-	total := estimateToolDefTokens(exposed)
-	// exec_command's description carries this host's shell guidance, and that
-	// guidance is the one part of the eager set that is not the same everywhere.
-	// Charged separately below rather than folded in here, or this ceiling would
-	// mean a different thing on every machine. See the constants above.
-	//
-	// Removed from the description BEFORE estimating rather than subtracted from
-	// the total afterwards. ApproxTextTokens is an integer division, so
-	// floor((schema+guidance)/4) - floor(guidance/4) comes out one token high
-	// whenever the two remainders add past four, and which side of that line a
-	// host lands on depends on the length of its guidance: exactly the
-	// host-dependence this number is supposed to be rid of.
-	guidance := tools.HostExecCommandShellGuidance()
-	schemas := make([]zeroruntime.ToolDefinition, len(exposed))
-	copy(schemas, exposed)
-	stripped := 0
-	for index := range schemas {
-		without := strings.TrimSuffix(schemas[index].Description, guidance)
-		if without != schemas[index].Description {
-			stripped++
-		}
-		schemas[index].Description = without
-	}
-	if guidance != "" && stripped != 1 {
-		t.Fatalf("SETUP INVALID: this host's shell guidance came off %d descriptions, want exactly exec_command's; internal/tools pins it as that description's tail", stripped)
-	}
-	got := estimateToolDefTokens(schemas)
-	guidanceTokens := ApproxTextTokens(guidance)
-	t.Logf("eager core tool schemas: %d tokens across %d tools (%d total, %d host shell guidance)", got, len(exposed), total, guidanceTokens)
+	got := estimateToolDefTokens(exposed)
+	t.Logf("eager core tool schemas: %d tokens across %d tools", got, len(exposed))
 	if got > maxEagerToolSchemaTokens {
 		// NOT "defer a tool": this test pins DeferThreshold at 0, so marking a
 		// tool deferred leaves it exposed here and changes nothing. Deferral is
@@ -112,9 +66,6 @@ func TestEagerToolSchemaTokenBudget(t *testing.T) {
 		// deliberate raise.
 		t.Fatalf("eager tool schemas are %d tokens, over the %d ceiling — trim a schema, drop a core tool, or raise the ceiling deliberately (deferring will NOT help: this test disables deferral)", got, maxEagerToolSchemaTokens)
 	}
-	if guidanceTokens > maxExecCommandShellGuidanceTokens {
-		t.Fatalf("this host's exec_command shell guidance is %d tokens, over the %d ceiling — trim the guidance in internal/tools/shell_runtime.go or raise the ceiling deliberately", guidanceTokens, maxExecCommandShellGuidanceTokens)
-	}
 }
 
 func TestAgentAdvertisesBothEditTools(t *testing.T) {

internal/agent/types.go

@@ -84,7 +84,6 @@ type ToolResult struct {
 	Images       []zeroruntime.ImageBlock
 	Redacted     bool
 	ChangedFiles []string
-	FileDiffs    []tools.FileDiff
 	// ChangeSummaries are non-selectable generated-tree summaries emitted by
 	// command execution; callers must not schedule per-file work from them.
 	ChangeSummaries []execution.Change
@@ -349,26 +348,10 @@ type Options struct {
 	// CompactionPreserveLast is how many trailing messages compaction keeps
 	// verbatim. <= 0 falls back to defaultCompactionPreserveLast.
 	CompactionPreserveLast int
-	// Summarizer, when set, lazily builds the provider used for compaction
-	// summarization calls — typically a cheap/fast model, since summaries at
-	// main-model prices are the single most expensive recurring event in a
-	// long run. It receives the main model currently in force and may return
-	// (nil, nil) when no dedicated summarizer applies to it (the main model is
-	// already the cheap one). Built on the first paid compaction and again
-	// after a mid-run model switch. Any failure (build or call) falls back to
-	// the run's main provider until the next switch, so a misconfigured
-	// summarizer can never break compaction. nil keeps today's behavior.
-	Summarizer func(ctx context.Context, mainModelID string) (Provider, error)
-	// ContextWindowFor, when set, resolves a model ID to its context window so
-	// the compactor can re-derive its threshold after a mid-run model switch
-	// (escalate_model). Without it a switch keeps compacting against the
-	// original model's window — overflowing a smaller target or over-compacting
-	// a larger one. Return <= 0 when the model is unknown (window unchanged).
-	ContextWindowFor func(modelID string) int
-	Registry         *tools.Registry
-	PermissionMode   PermissionMode
-	Autonomy         string
-	Sandbox          *sandbox.Engine
+	Registry               *tools.Registry
+	PermissionMode         PermissionMode
+	Autonomy               string
+	Sandbox                *sandbox.Engine
 	// FileTracker records per-session file read/write versions so the write tools
 	// can detect a file changed on disk outside Zero since it was last read. nil
 	// disables the check. Created once per session and threaded into every tool run.

internal/background/process_posix.go

@@ -3,9 +3,7 @@
 package background
 
 import (
-	"errors"
 	"os/exec"
-	"syscall"
 	"time"
 
 	"github.com/Gitlawb/zero/internal/execution"
@@ -47,16 +45,6 @@ func terminateProcess(pid int) error {
 // rediscovery after an owned leader exits. Ordinary commands fall back to the
 // safe PID/tree path rather than assuming their PID is also a process-group ID.
 //
-// The bool result is whether the leader had already exited before termination
-// was attempted — the POSIX analogue of Windows GetExitCodeProcess returning a
-// value other than STILL_ACTIVE. A waitable zombie is already-exited: Wait can
-// collect it, but kill(0) still succeeds, and when ps is unavailable
-// signalTargetRunning conservatively treats that as "still running".
-// TerminateCommand uses the flag to discard the resulting spurious
-// SIGKILL-timeout once the reap has independently succeeded. The flag is about
-// the leader only; group/tree termination is still invoked so live descendants
-// are signalled.
-//
 // The Setpgid && Pgid == 0 guard only recognizes ConfigureChildProcessGroup's
 // own convention. A command made its own session leader via Setsid (as opposed
 // to Setpgid) is also its own process-group leader in practice, but takes the
@@ -64,20 +52,8 @@ func terminateProcess(pid int) error {
 // because TerminateCommand has exactly one caller in this codebase; worth
 // covering explicitly if Setsid-configured commands start using this path too.
 func terminateOwnedProcess(cmd *exec.Cmd) (bool, error) {
-	alreadyExited := leaderWaitableExited(cmd.Process.Pid)
 	if cmd.SysProcAttr != nil && cmd.SysProcAttr.Setpgid && cmd.SysProcAttr.Pgid == 0 {
-		return alreadyExited, execution.TerminateProcessGroup(cmd.Process.Pid, terminationGracePeriod, terminationPollInterval)
+		return false, execution.TerminateProcessGroup(cmd.Process.Pid, terminationGracePeriod, terminationPollInterval)
 	}
-	return alreadyExited, terminateProcess(cmd.Process.Pid)
-}
-
-// terminationTargetGoneAfterReap independently checks the exact signal target
-// used for an owned command. In particular, reaping a zombie group leader does
-// not make this return true while any descendant still occupies that group.
-func terminationTargetGoneAfterReap(cmd *exec.Cmd) bool {
-	target := cmd.Process.Pid
-	if cmd.SysProcAttr != nil && cmd.SysProcAttr.Setpgid && cmd.SysProcAttr.Pgid == 0 {
-		target = -target
-	}
-	return errors.Is(syscall.Kill(target, syscall.Signal(0)), syscall.ESRCH)
+	return false, terminateProcess(cmd.Process.Pid)
 }

internal/background/process_posix_test.go

@@ -6,7 +6,6 @@ import (
 	"bufio"
 	"errors"
 	"os/exec"
-	"runtime"
 	"strconv"
 	"strings"
 	"syscall"
@@ -221,109 +220,6 @@ func TestTerminateCommandKillsChildAfterLeaderExits(t *testing.T) {
 	}
 }
 
-func TestTerminateCommandZombieLeaderWithoutPS(t *testing.T) {
-	if runtime.GOOS != "linux" && runtime.GOOS != "darwin" {
-		t.Skip("waitable-exited leader probe is implemented on linux and darwin")
-	}
-
-	grace, poll := terminationGracePeriod, terminationPollInterval
-	terminationGracePeriod, terminationPollInterval = 150*time.Millisecond, 10*time.Millisecond
-	t.Cleanup(func() { terminationGracePeriod, terminationPollInterval = grace, poll })
-
-	// Issue #862: a zombie group leader with ps unresolvable used to burn both
-	// grace periods (kill(0) succeeds against a zombie) and return
-	// "did not exit after SIGKILL" even though cmd.Wait reaped exit status 0.
-	// The already-exited probe must answer without ps so TerminateCommand can
-	// discard that spurious timeout after a successful reap.
-	cmd := exec.Command("sh", "-c", "exit 0")
-	ConfigureChildProcessGroup(cmd)
-	if err := cmd.Start(); err != nil {
-		t.Fatalf("start: %v", err)
-	}
-	pid := cmd.Process.Pid
-	t.Cleanup(func() {
-		if cmd.ProcessState == nil {
-			_ = cmd.Process.Kill()
-			_ = cmd.Wait()
-		}
-	})
-
-	deadline := time.Now().Add(5 * time.Second)
-	for !leaderWaitableExited(pid) {
-		if time.Now().After(deadline) {
-			t.Fatalf("leader %d did not become waitable-exited within 5s", pid)
-		}
-		time.Sleep(10 * time.Millisecond)
-	}
-
-	t.Setenv("PATH", "")
-	if err := TerminateCommand(cmd); err != nil {
-		t.Fatalf("TerminateCommand: %v, want nil (zombie leader with ps unavailable must not report SIGKILL timeout)", err)
-	}
-	if cmd.ProcessState == nil {
-		t.Fatal("zombie leader was not reaped")
-	}
-}
-
-func TestTerminateCommandPreservesGroupFailureWithExitedLeaderAndLiveChild(t *testing.T) {
-	if runtime.GOOS != "linux" && runtime.GOOS != "darwin" {
-		t.Skip("waitable-exited leader probe is implemented on linux and darwin")
-	}
-
-	cmd := exec.Command("sh", "-c", "sleep 300 & echo $!; exit 0")
-	ConfigureChildProcessGroup(cmd)
-	stdout, err := cmd.StdoutPipe()
-	if err != nil {
-		t.Fatalf("stdout pipe: %v", err)
-	}
-	if err := cmd.Start(); err != nil {
-		t.Fatalf("start: %v", err)
-	}
-	line, err := bufio.NewReader(stdout).ReadString('\n')
-	if err != nil {
-		t.Fatalf("read forked child pid: %v", err)
-	}
-	childPID, err := strconv.Atoi(strings.TrimSpace(line))
-	if err != nil {
-		t.Fatalf("parse forked child pid %q: %v", line, err)
-	}
-	t.Cleanup(func() {
-		_ = syscall.Kill(childPID, syscall.SIGKILL)
-		if cmd.ProcessState == nil {
-			_ = cmd.Wait()
-		}
-	})
-
-	deadline := time.Now().Add(5 * time.Second)
-	for !leaderWaitableExited(cmd.Process.Pid) {
-		if time.Now().After(deadline) {
-			t.Fatalf("leader %d did not become waitable-exited within 5s", cmd.Process.Pid)
-		}
-		time.Sleep(10 * time.Millisecond)
-	}
-
-	treeErr := errors.New("process group could not be terminated")
-	originalTerminateOwnedProcess := terminateOwnedProcessForTest
-	terminateOwnedProcessForTest = func(got *exec.Cmd) (bool, error) {
-		if got != cmd {
-			t.Fatalf("terminate called with %p, want %p", got, cmd)
-		}
-		return true, treeErr
-	}
-	t.Cleanup(func() { terminateOwnedProcessForTest = originalTerminateOwnedProcess })
-
-	err = TerminateCommand(cmd)
-	if !errors.Is(err, treeErr) {
-		t.Fatalf("TerminateCommand error = %v, want live-group termination failure", err)
-	}
-	if cmd.ProcessState == nil {
-		t.Fatal("exited leader was not reaped")
-	}
-	if processStopped(childPID) {
-		t.Fatalf("child %d unexpectedly stopped; failure boundary needs a live group member", childPID)
-	}
-}
-
 func processStopped(pid int) bool {
 	if errors.Is(syscall.Kill(pid, syscall.Signal(0)), syscall.ESRCH) {
 		return true

internal/background/process_waitable_darwin.go

@@ -1,28 +0,0 @@
-//go:build darwin
-
-package background
-
-import "golang.org/x/sys/unix"
-
-// szomb is sys/proc.h SZOMB: the process has exited and is waiting to be reaped.
-const szomb int8 = 5
-
-// leaderWaitableExited reports whether pid has already exited and is waiting
-// to be reaped. This is the POSIX analogue of Windows GetExitCodeProcess
-// returning a value other than STILL_ACTIVE: the leader is a zombie, waitable
-// as exited, without collecting it. A true result does not mean the process
-// group is empty — descendants may still be running.
-//
-// Darwin has no /proc and x/sys/unix does not wrap waitid here, so the probe
-// is kern.proc.pid via sysctl. It does not use ps, which is the #862 failure
-// mode when PATH cannot resolve ps.
-func leaderWaitableExited(pid int) bool {
-	if pid <= 1 {
-		return false
-	}
-	kinfo, err := unix.SysctlKinfoProc("kern.proc.pid", pid)
-	if err != nil {
-		return false
-	}
-	return kinfo.Proc.P_stat == szomb
-}

internal/background/process_waitable_linux.go

@@ -1,68 +0,0 @@
-//go:build linux
-
-package background
-
-import (
-	"bytes"
-	"os"
-	"strconv"
-
-	"golang.org/x/sys/unix"
-)
-
-// POSIX waitid si_code values for an already-exited child (bits/waitflags.h).
-const (
-	cldExited int32 = 1
-	cldKilled int32 = 2
-	cldDumped int32 = 3
-)
-
-// leaderWaitableExited reports whether pid has already exited and is waiting
-// to be reaped. This is the POSIX analogue of Windows GetExitCodeProcess
-// returning a value other than STILL_ACTIVE: the leader is waitable as exited
-// (typically a zombie) without collecting it. A true result does not mean the
-// process group is empty — descendants may still be running.
-//
-// Detection does not use ps. waitid(WNOHANG|WNOWAIT) asks the kernel whether
-// an exit status is already available. /proc/<pid>/stat state Z is the
-// fallback when waitid cannot answer (for example if procfs is the only
-// usable source). Either path is independent of PATH, which is the #862
-// failure mode: empty PATH makes ps unresolvable and kill(0) still succeeds
-// against a zombie.
-func leaderWaitableExited(pid int) bool {
-	if pid <= 1 {
-		return false
-	}
-	if waitidAlreadyExited(pid) {
-		return true
-	}
-	return procIsZombie(pid)
-}
-
-func waitidAlreadyExited(pid int) bool {
-	var info unix.Siginfo
-	err := unix.Waitid(unix.P_PID, pid, &info, unix.WEXITED|unix.WNOHANG|unix.WNOWAIT, nil)
-	if err != nil {
-		return false
-	}
-	switch info.Code {
-	case cldExited, cldKilled, cldDumped:
-		return true
-	}
-	return false
-}
-
-func procIsZombie(pid int) bool {
-	data, err := os.ReadFile("/proc/" + strconv.Itoa(pid) + "/stat")
-	if err != nil {
-		return false
-	}
-	// /proc/<pid>/stat: pid (comm) state ... — comm may contain spaces or
-	// parentheses, so the state is the first field after the last ')'.
-	i := bytes.LastIndexByte(data, ')')
-	if i < 0 || i+1 >= len(data) {
-		return false
-	}
-	rest := bytes.TrimSpace(data[i+1:])
-	return len(rest) > 0 && rest[0] == 'Z'
-}

internal/background/process_waitable_other.go

@@ -1,10 +0,0 @@
-//go:build !windows && !linux && !darwin
-
-package background
-
-// leaderWaitableExited cannot positively identify a waitable-exited leader on
-// this platform without ps. Returning false keeps TerminateCommand's existing
-// conservative behaviour: a termination error is not discarded after reap.
-func leaderWaitableExited(pid int) bool {
-	return false
-}

internal/background/process_windows.go

@@ -50,8 +50,3 @@ func terminateOwnedProcess(cmd *exec.Cmd) (bool, error) {
 	}
 	return alreadyExited, terminateErr
 }
-
-// Windows has no persistent process-group identity to query after a dead root
-// is reaped. Preserve TerminateCommand's existing, documented dead-root
-// behavior; the stronger independent target check is available on POSIX.
-func terminationTargetGoneAfterReap(*exec.Cmd) bool { return true }

internal/background/terminate.go

@@ -9,10 +9,6 @@ import (
 
 const commandReapTimeout = 3 * time.Second
 
-// terminateOwnedProcessForTest is a seam for the failure-boundary tests. Tests
-// replace it only while no other test in this package is running in parallel.
-var terminateOwnedProcessForTest = terminateOwnedProcess
-
 // TerminateProcess stops a background process by PID — on Windows its process
 // tree; on POSIX its whole process group when the PID leads its own group (the
 // invariant ConfigureChildProcessGroup establishes for processes started through
@@ -30,15 +26,11 @@ func TerminateProcess(pid int) error {
 // have exclusive ownership of cmd: it must not have previously called Wait or
 // Process.Release, and no goroutine may call either concurrently. On POSIX it
 // stops the whole group when the command was configured as its leader; ordinary
-// commands safely fall back to PID/tree discovery. When POSIX observes a
-// waitable-zombie leader before signalling, a termination error is discarded
-// after reap only if the launch-time signal target is independently gone; the
-// leader observation alone says nothing about descendants. Windows retains its
-// existing behavior of ignoring the expected kill-attempt error when
-// GetExitCodeProcess shows that the root was already dead. Windows cannot
-// rediscover a tree from a dead root, so descendants may survive there. `zero
-// daemon start` needs this operation when readiness times out: it launched the
-// child, so it must both stop the tree and collect the leader.
+// commands safely fall back to PID/tree discovery. On Windows, success for a
+// leader that was already dead confirms only that the leader was reaped;
+// descendants may survive because Windows cannot rediscover a tree from a dead
+// root. `zero daemon start` needs this operation when readiness times out: it
+// launched the child, so it must both stop the tree and collect the leader.
 //
 // The order matters: the tree is signalled first, because Wait releases the
 // leader's PID and a later group lookup could then resolve to nothing (or, worse,
@@ -52,7 +44,7 @@ func TerminateCommand(cmd *exec.Cmd) error {
 	if cmd == nil || cmd.Process == nil {
 		return errors.New("terminate command: process was never started")
 	}
-	leaderAlreadyExited, terminateErr := terminateOwnedProcessForTest(cmd)
+	leaderAlreadyExited, terminateErr := terminateOwnedProcess(cmd)
 	reapErr := waitForTerminatedCommandWithin(cmd, commandReapTimeout)
 	if reapErr != nil {
 		if terminateErr != nil {
@@ -60,16 +52,12 @@ func TerminateCommand(cmd *exec.Cmd) error {
 		}
 		return reapErr
 	}
-	if terminateErr != nil {
-		if !leaderAlreadyExited || !terminationTargetGoneAfterReap(cmd) {
-			return terminateErr
-		}
+	if terminateErr != nil && !leaderAlreadyExited {
+		return terminateErr
 	}
-	// On POSIX, discard a termination error only when the leader was already
-	// exited and the launch-time signal target is independently gone after reap.
-	// A successful leader reap alone says nothing about live descendants.
-	// Windows retains its existing dead-root semantics because it has no
-	// persistent group identity to query after the root exits.
+	// Only discard a termination error when the platform demonstrated before
+	// attempting termination that the leader had already exited. A successful
+	// reap alone says nothing about whether a live descendant tree was stopped.
 	return nil
 }
 

internal/cli/acp.go

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

internal/cli/acp_test.go

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

internal/cli/app.go

@@ -311,35 +311,40 @@ func runWithDeps(args []string, stdout io.Writer, stderr io.Writer, deps appDeps
 	// cache file on the machine. The refresh itself is fired in exec/TUI startup.
 	modelregistry.EnableModelsDevOverlay()
 
-	// --add-dir, --theme and --allow-escalation may be written in any order;
-	// see splitLeadingRootFlags for why they are split together.
-	root, args, err := splitLeadingRootFlags(args)
+	addDirs, args, err := splitLeadingAddDirFlags(args)
 	if err != nil {
 		return writeAppError(stderr, err.Error(), 1)
 	}
-	addDirs, theme, allowEscalation := root.addDirs, root.theme, root.allowEscalation
+	// --theme <name> selects the TUI palette non-interactively (auto or any registered
+	// theme; populates tui.Options.Theme, which resolveThemeMode prefers over
+	// ZERO_THEME). Re-split --add-dir afterward so it may appear on either side of --theme.
+	theme, args, err := splitLeadingThemeFlag(args)
+	if err != nil {
+		return writeAppError(stderr, err.Error(), 1)
+	}
+	moreDirs, args, err := splitLeadingAddDirFlags(args)
+	if err != nil {
+		return writeAppError(stderr, err.Error(), 1)
+	}
+	addDirs = append(addDirs, moreDirs...)
 
 	if len(args) == 0 {
-		return runInteractiveTUI(stderr, deps, agent.PermissionModeAsk, addDirs, theme, allowEscalation)
+		return runInteractiveTUI(stderr, deps, agent.PermissionModeAsk, addDirs, theme)
 	}
 
-	// --add-dir grants an extra write root and --allow-escalation opts a run
-	// into mid-run model escalation; only the interactive TUI and exec consume
-	// either. Both are forwarded to exec below and rejected loudly everywhere
-	// else rather than silently discarded, including help/version, which run
-	// no agent and could only ignore them. The allowlist names exactly the
-	// cases below that forward; a future subcommand is rejected by default
-	// until it opts in here.
-	forwardsRootFlags := false
-	switch args[0] {
-	case "--skip-permissions-unsafe", "-p", "--prompt", "exec":
-		forwardsRootFlags = true
-	}
-	if len(addDirs) > 0 && !forwardsRootFlags {
-		return writeAppError(stderr, "--add-dir is only supported for the interactive TUI and exec", 1)
-	}
-	if allowEscalation && !forwardsRootFlags {
-		return writeAppError(stderr, "--allow-escalation is only supported for the interactive TUI and exec", 1)
+	// --add-dir grants an extra write root, and only the interactive TUI and
+	// exec dispatch paths consume one. Fail loud everywhere else rather than
+	// silently discarding an explicit grant — including help/version, which
+	// run no agent and could only ignore it. The allowlist names exactly the
+	// cases below that forward addDirs; a future subcommand is rejected by
+	// default until it opts in here.
+	if len(addDirs) > 0 {
+		switch args[0] {
+		case "--skip-permissions-unsafe", "-p", "--prompt", "exec":
+			// Forwarded by the matching case below.
+		default:
+			return writeAppError(stderr, "--add-dir is only supported for the interactive TUI and exec", 1)
+		}
 	}
 
 	switch args[0] {
@@ -349,24 +354,26 @@ func runWithDeps(args []string, stdout io.Writer, stderr io.Writer, deps appDeps
 		// reach unsafe mode in the shell — and the "!" shell escape (which is
 		// gated behind unsafe) was therefore unreachable.
 		//
-		// The root flags may legally appear on either side of this flag, so
-		// split them again from what follows it and merge with what the root
-		// already took. Any trailing non-flag args were ignored on this path
-		// before --add-dir existed and still are, but an --add-dir hidden
-		// BEHIND one would be silently dropped with them, so reject that
-		// misplacement loudly below.
-		more, rest, err := splitLeadingRootFlags(args[1:])
+		// --add-dir may legally appear on either side of the flag, so re-split
+		// the remaining args and merge with the dirs already collected. Any
+		// trailing non-flag args were ignored on this path before --add-dir
+		// existed and still are — but an --add-dir hidden BEHIND one would be
+		// silently dropped with them, so reject that misplacement loudly.
+		moreDirs, rest, err := splitLeadingAddDirFlags(args[1:])
 		if err != nil {
 			return writeAppError(stderr, err.Error(), 1)
 		}
-		moreDirs := more.addDirs
-		// A --theme written before the flag was taken at the root and used to be
-		// dropped here; one written after it wins, as the last occurrence does.
-		skipTheme := theme
-		if more.theme != "" {
-			skipTheme = more.theme
+		// --theme may appear here too; extract it before the stray-arg checks so it is
+		// not rejected as an unexpected positional, then re-split --add-dir after it.
+		skipTheme, rest, err := splitLeadingThemeFlag(rest)
+		if err != nil {
+			return writeAppError(stderr, err.Error(), 1)
 		}
-		skipAllowEscalation := more.allowEscalation
+		evenMoreDirs, rest, err := splitLeadingAddDirFlags(rest)
+		if err != nil {
+			return writeAppError(stderr, err.Error(), 1)
+		}
+		moreDirs = append(moreDirs, evenMoreDirs...)
 		// A misplaced --add-dir anywhere in the remainder is the more specific error,
 		// so check for it across all of rest before rejecting stray args.
 		for _, arg := range rest {
@@ -383,7 +390,7 @@ func runWithDeps(args []string, stdout io.Writer, stderr io.Writer, deps appDeps
 				return writeAppError(stderr, "--skip-permissions-unsafe launches the interactive TUI and takes no prompt or subcommand; for a one-shot unsafe run use `zero exec --skip-permissions-unsafe -p \"...\"`", 1)
 			}
 		}
-		return runInteractiveTUI(stderr, deps, agent.PermissionModeUnsafe, append(append([]string{}, addDirs...), moreDirs...), skipTheme, allowEscalation || skipAllowEscalation)
+		return runInteractiveTUI(stderr, deps, agent.PermissionModeUnsafe, append(append([]string{}, addDirs...), moreDirs...), skipTheme)
 	case "-h", "--help", "help":
 		if err := writeHelp(stdout); err != nil {
 			return 1
@@ -416,16 +423,16 @@ func runWithDeps(args []string, stdout io.Writer, stderr io.Writer, deps appDeps
 		if len(args) < 2 {
 			return writePromptRequired(stderr)
 		}
-		// Forward the root flags exec consumes so its own parser collects them.
+		// Forward leading --add-dir occurrences so exec's own parser collects them.
 		// Use the inline --prompt=<value> form so a prompt whose first character is a
 		// dash (e.g. `zero -p "-foo"`) is taken verbatim instead of being mistaken for
 		// a flag and rejected with "--prompt requires a value" (matches the cron path).
-		execArgs := append(rootFlagArgs(addDirs, allowEscalation), "--prompt="+args[1])
+		execArgs := append(addDirFlagArgs(addDirs), "--prompt="+args[1])
 		execArgs = append(execArgs, args[2:]...)
 		return runExec(execArgs, stdout, stderr, deps)
 	case "exec":
-		// Forward the root flags exec consumes so its own parser collects them.
-		return runExec(append(rootFlagArgs(addDirs, allowEscalation), args[1:]...), stdout, stderr, deps)
+		// Forward leading --add-dir occurrences so exec's own parser collects them.
+		return runExec(append(addDirFlagArgs(addDirs), args[1:]...), stdout, stderr, deps)
 	case "completions":
 		return runCompletions(args[1:], stdout, stderr)
 	case "daemon":
@@ -687,11 +694,11 @@ func fillAppDeps(deps appDeps) appDeps {
 	return deps
 }
 
-func runInteractiveTUI(stderr io.Writer, deps appDeps, permissionMode agent.PermissionMode, addDirs []string, theme string, allowEscalation bool) int {
-	return runInteractiveTUIWithSetup(stderr, deps, permissionMode, addDirs, theme, false, allowEscalation)
+func runInteractiveTUI(stderr io.Writer, deps appDeps, permissionMode agent.PermissionMode, addDirs []string, theme string) int {
+	return runInteractiveTUIWithSetup(stderr, deps, permissionMode, addDirs, theme, false)
 }
 
-func runInteractiveTUIWithSetup(stderr io.Writer, deps appDeps, permissionMode agent.PermissionMode, addDirs []string, theme string, forceSetup bool, allowEscalation bool) int {
+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.
@@ -783,14 +790,6 @@ func runInteractiveTUIWithSetup(stderr io.Writer, deps appDeps, permissionMode a
 
 	registry := newCoreRegistryScoped(workspaceRoot, scope)
 	registerLocalControlTools(registry, workspaceRoot, resolved.LocalControl)
-	// Mid-run model escalation is opt-in on this surface too. The tool is present
-	// only when the operator asked for it with --allow-escalation, and the
-	// switchers that make it do anything ride on the same flag through
-	// Options.AllowEscalation below. Registering one without the other ships a
-	// tool the loop will never act on, which looks like a feature and is not.
-	if allowEscalation {
-		registry.Register(tools.NewEscalateModelTool())
-	}
 	executionRunner := execution.NewRunner(nil)
 	sandboxStore, err := deps.newSandboxStore()
 	if err != nil {
@@ -975,7 +974,6 @@ func runInteractiveTUIWithSetup(stderr io.Writer, deps appDeps, permissionMode a
 		FavoriteModels:       resolved.Preferences.FavoriteModels,
 		RecentModels:         resolved.Preferences.RecentModels,
 		RecapsEnabled:        resolved.Preferences.RecapsEnabled(),
-		CompactionModel:      resolved.Preferences.CompactionModel,
 		Provider:             provider,
 		NewProvider:          deps.newProvider,
 		NewTurnSessionProvider: func(profile config.ProviderProfile, provider zeroruntime.Provider) zeroruntime.TurnSessionProvider {
@@ -1034,7 +1032,6 @@ func runInteractiveTUIWithSetup(stderr io.Writer, deps appDeps, permissionMode a
 			Specialists:    specialistRuntime.specialists,
 			Skills:         pluginActivation.skillInfos(deps.skillsDir()),
 		},
-		AllowEscalation: allowEscalation,
 		// LoadSkills backs /skills and direct /<skill-name> invocation in the TUI.
 		// It resolves against the same merged set (default dir + plugin skill
 		// roots) as the skill tool and the system-prompt list, re-read per use so
@@ -1380,7 +1377,6 @@ Flags:
   -v, --version                  Print version
   -p, --prompt                   Run a one-shot prompt
       --add-dir <path>           Allow writes in an extra directory (repeatable)
-      --allow-escalation         Let the agent escalate to a stronger model mid-run via escalate_model
       --skip-permissions-unsafe  Launch the interactive shell in unsafe mode (enables the ! shell escape)
 `)
 	return err
@@ -1397,17 +1393,6 @@ func addDirFlagArgs(addDirs []string) []string {
 	return flags
 }
 
-// rootFlagArgs re-synthesises the root flags exec consumes, in the spelling
-// its own parser accepts, so a flag written before the subcommand reaches
-// the run exactly as one written after it would.
-func rootFlagArgs(addDirs []string, allowEscalation bool) []string {
-	flags := addDirFlagArgs(addDirs)
-	if allowEscalation {
-		flags = append(flags, "--allow-escalation")
-	}
-	return flags
-}
-
 // splitLeadingAddDirFlags strips leading --add-dir flags from the root
 // argument list (zero --add-dir <path> [--add-dir <path>] [subcommand …]).
 // Subcommands like exec parse their own --add-dir occurrences.
@@ -1448,83 +1433,6 @@ func splitLeadingAddDirFlags(args []string) ([]string, []string, error) {
 	return addDirs, args, nil
 }
 
-// rootFlags is what the leading root flags amount to once every one of them
-// has been stripped from the front of the argument list.
-type rootFlags struct {
-	addDirs         []string
-	theme           string
-	allowEscalation bool
-}
-
-// splitLeadingRootFlags strips --add-dir, --theme and --allow-escalation from
-// the front of args in whatever order they were written, stopping at the
-// first token none of them claims.
-//
-// EACH SPLITTER STOPS AT THE FIRST TOKEN IT DOES NOT OWN, so running them once
-// in a fixed sequence made the order the operator wrote them in load-bearing:
-// a flag handled late in the sequence stranded every flag written after it as
-// an unknown command, and `zero --allow-escalation --theme auto` exited with
-// an argument error instead of launching. Running the sequence until it makes
-// no progress accepts every ordering, including a flag repeated on both sides
-// of another.
-func splitLeadingRootFlags(args []string) (rootFlags, []string, error) {
-	var flags rootFlags
-	for {
-		before := len(args)
-		addDirs, rest, err := splitLeadingAddDirFlags(args)
-		if err != nil {
-			return rootFlags{}, nil, err
-		}
-		flags.addDirs = append(flags.addDirs, addDirs...)
-		theme, rest, err := splitLeadingThemeFlag(rest)
-		if err != nil {
-			return rootFlags{}, nil, err
-		}
-		if theme != "" {
-			// The last occurrence wins across passes, as it does within one.
-			flags.theme = theme
-		}
-		allowEscalation, rest, err := splitLeadingAllowEscalationFlag(rest)
-		if err != nil {
-			return rootFlags{}, nil, err
-		}
-		flags.allowEscalation = flags.allowEscalation || allowEscalation
-		args = rest
-		if len(args) == before {
-			return flags, args, nil
-		}
-	}
-}
-
-// splitLeadingAllowEscalationFlag strips a leading --allow-escalation from the
-// root argument list, opting the interactive session into mid-run model
-// escalation.
-//
-// OPT-IN, THE SAME WAY exec IS. Escalation moves a run onto a different model,
-// which changes what the run costs and which provider sees the conversation, so
-// it is a decision the operator makes rather than a default. The exec flag
-// already answers this conservatively and the interactive surface should not
-// answer it differently.
-//
-// Bare flag only: repeating it is harmless, and an =value form is rejected so a
-// mistyped --allow-escalation=false is a loud error instead of silently enabling
-// the thing it was trying to turn off.
-func splitLeadingAllowEscalationFlag(args []string) (bool, []string, error) {
-	allow := false
-	for len(args) > 0 {
-		switch {
-		case args[0] == "--allow-escalation":
-			allow = true
-			args = args[1:]
-		case strings.HasPrefix(args[0], "--allow-escalation="):
-			return false, nil, errors.New("--allow-escalation takes no value; pass it bare to enable mid-run model escalation, or omit it")
-		default:
-			return allow, args, nil
-		}
-	}
-	return allow, args, nil
-}
-
 // splitLeadingThemeFlag strips a leading --theme <auto|theme-name> (space or =form)
 // from the root argument list and validates it against the registered themes. The
 // last occurrence wins. A value outside the allowed set is a loud error rather than

internal/cli/auth.go

@@ -74,8 +74,6 @@ func runAuth(args []string, stdout io.Writer, stderr io.Writer, deps appDeps) in
 		return runAuthStatus(args[1:], stdout, stderr, deps)
 	case "refresh":
 		return runAuthRefresh(args[1:], stdout, stderr, deps)
-	case "reset":
-		return runAuthReset(args[1:], stdout, stderr, deps)
 	case "openrouter":
 		return runAuthOpenRouter(args[1:], stdout, stderr, deps)
 	case "chatgpt":
@@ -263,7 +261,6 @@ type authArgs struct {
 	json       bool
 	device     bool
 	watch      bool
-	confirm    bool
 	scopes     []string
 	help       bool
 }
@@ -289,8 +286,6 @@ func parseAuthArgs(sub string, args []string) (authArgs, error) {
 			parsed.device = true
 		case arg == "--watch":
 			parsed.watch = true
-		case arg == "--confirm":
-			parsed.confirm = true
 		case arg == "--scope":
 			if i+1 >= len(args) {
 				return authArgs{}, fmt.Errorf("--scope requires a value")
@@ -326,7 +321,6 @@ func validateAuthFlags(sub string, a authArgs) error {
 		"logout":  {"json": true},
 		"status":  {"json": true},
 		"refresh": {"watch": true},
-		"reset":   {"json": true, "confirm": true},
 	}[sub]
 	bad := func(name string) error { return fmt.Errorf("zero auth %s does not accept %s", sub, name) }
 	if a.json && !allowed["json"] {
@@ -338,9 +332,6 @@ func validateAuthFlags(sub string, a authArgs) error {
 	if a.watch && !allowed["watch"] {
 		return bad("--watch")
 	}
-	if a.confirm && !allowed["confirm"] {
-		return bad("--confirm")
-	}
 	if len(a.scopes) > 0 && !allowed["scope"] {
 		return bad("--scope")
 	}
@@ -578,43 +569,6 @@ func runAuthRefreshWatch(manager *oauth.Manager, key, provider string, stdout io
 	return exitSuccess
 }
 
-func runAuthReset(args []string, stdout io.Writer, stderr io.Writer, deps appDeps) int {
-	parsed, err := parseAuthArgs("reset", args)
-	if err != nil {
-		return writeExecUsageError(stderr, err.Error())
-	}
-	if parsed.help {
-		_ = writeAuthHelp(stdout)
-		return exitSuccess
-	}
-	if len(parsed.positional) > 0 {
-		return writeExecUsageError(stderr, fmt.Sprintf("zero auth reset takes no arguments (got %q)", parsed.positional[0]))
-	}
-	if !parsed.confirm {
-		return writeExecUsageError(stderr, "zero auth reset clears all stored OAuth logins and shared MCP tokens; rerun with --confirm to reset")
-	}
-	manager, err := newAuthManager(deps, stdout)
-	if err != nil {
-		return writeAppError(stderr, redaction.ErrorMessage(err, redaction.Options{}), exitCrash)
-	}
-	if err := manager.Reset(); err != nil {
-		return writeAppError(stderr, redaction.ErrorMessage(err, redaction.Options{}), exitCrash)
-	}
-	if parsed.json {
-		payload := struct {
-			Reset bool `json:"reset"`
-		}{Reset: true}
-		if err := writePrettyJSON(stdout, payload); err != nil {
-			return exitCrash
-		}
-		return exitSuccess
-	}
-	if _, err := fmt.Fprintln(stdout, "Reset OAuth token store."); err != nil {
-		return exitCrash
-	}
-	return exitSuccess
-}
-
 func filterAuthStatuses(statuses []oauth.Status, provider string) []oauth.Status {
 	want := oauth.ProviderKey(provider)
 	filtered := make([]oauth.Status, 0, 1)
@@ -635,7 +589,6 @@ Commands:
   logout <provider>                               Delete a provider's stored login
   status [provider]                               Show login presence/expiry (never the token)
   refresh <provider> [--watch]                    Force a token refresh (--watch keeps it fresh)
-  reset --confirm [--json]                        Clear all OAuth logins and shared MCP tokens (also repairs corrupted stores)
   openrouter                                      Log in to OpenRouter in the browser; mints an API key
   chatgpt                                         Log in to ChatGPT in the browser (Codex backend, ChatGPT Plus/Pro)
 
@@ -662,7 +615,7 @@ Flags:
       --device   Use the device-code flow (headless/SSH; no browser)
       --scope    Add an OAuth scope (repeatable)
       --watch    Keep the token fresh in the foreground (refresh only)
-      --json     Print result as JSON (status/logout/reset)
+      --json     Print result as JSON (status/logout)
   -h, --help     Show this help
 `)
 	return err

internal/cli/auth_test.go

@@ -129,8 +129,6 @@ func TestRunAuthRejectsWrongFlags(t *testing.T) {
 		{"auth", "logout", "demo", "--scope", "x"}, // scope is login-only
 		{"auth", "refresh", "demo", "--json"},      // json not for refresh
 		{"auth", "login", "demo", "--scope", ""},   // empty scope rejected
-		{"auth", "status", "--confirm"},            // confirm is reset-only
-		{"auth", "reset", "--confirm", "--watch"},  // confirmation does not allow unrelated flags
 	}
 	for _, args := range cases {
 		var stdout, stderr bytes.Buffer
@@ -198,102 +196,13 @@ func TestRunAuthHelp(t *testing.T) {
 	if code := runWithDeps([]string{"auth", "--help"}, &stdout, &stderr, appDeps{}); code != exitSuccess {
 		t.Fatalf("exit = %d", code)
 	}
-	for _, want := range []string{"zero auth", "login", "logout", "status", "refresh", "reset --confirm", "--device"} {
+	for _, want := range []string{"zero auth", "login", "logout", "status", "refresh", "--device"} {
 		if !strings.Contains(stdout.String(), want) {
 			t.Fatalf("help missing %q:\n%s", want, stdout.String())
 		}
 	}
 }
 
-func TestRunAuthResetRequiresConfirmation(t *testing.T) {
-	for _, args := range [][]string{{}, {"--json"}} {
-		t.Run(strings.Join(args, " "), func(t *testing.T) {
-			path := withAuthStore(t)
-			store, err := oauth.NewStore(oauth.StoreOptions{FilePath: path})
-			if err != nil {
-				t.Fatal(err)
-			}
-			if err := store.Save(oauth.ProviderKey("demo"), oauth.Token{AccessToken: "synthetic-reset-test-token"}); err != nil {
-				t.Fatal(err)
-			}
-			before, err := os.ReadFile(path)
-			if err != nil {
-				t.Fatal(err)
-			}
-			var stdout, stderr bytes.Buffer
-			code := runAuthReset(args, &stdout, &stderr, appDeps{})
-			after, readErr := os.ReadFile(path)
-			if readErr != nil || !bytes.Equal(before, after) {
-				t.Fatalf("unconfirmed reset changed the store: %v", readErr)
-			}
-			if code == exitSuccess || !strings.Contains(stderr.String(), "--confirm") || stdout.Len() != 0 {
-				t.Fatalf("unconfirmed reset: exit=%d stdout=%q stderr=%q", code, stdout.String(), stderr.String())
-			}
-		})
-	}
-}
-
-func TestRunAuthResetJSON(t *testing.T) {
-	path := withAuthStore(t)
-	store, err := oauth.NewStore(oauth.StoreOptions{FilePath: path})
-	if err != nil {
-		t.Fatalf("NewStore: %v", err)
-	}
-	if err := store.Save(oauth.ProviderKey("demo"), oauth.Token{AccessToken: "synthetic-reset-test-token"}); err != nil {
-		t.Fatalf("Save: %v", err)
-	}
-	var stdout, stderr bytes.Buffer
-	if code := runWithDeps([]string{"auth", "reset", "--confirm", "--json"}, &stdout, &stderr, appDeps{}); code != exitSuccess {
-		t.Fatalf("exit = %d stderr=%s", code, stderr.String())
-	}
-	var payload struct {
-		Reset bool `json:"reset"`
-	}
-	if err := json.Unmarshal(stdout.Bytes(), &payload); err != nil {
-		t.Fatalf("decode JSON: %v (stdout=%q)", err, stdout.String())
-	}
-	if !payload.Reset {
-		t.Fatalf("payload = %+v, want reset=true", payload)
-	}
-	stdout.Reset()
-	stderr.Reset()
-	if code := runWithDeps([]string{"auth", "status"}, &stdout, &stderr, appDeps{}); code != exitSuccess {
-		t.Fatalf("status exit = %d stderr=%s", code, stderr.String())
-	}
-	if !strings.Contains(stdout.String(), "No OAuth provider logins are stored.") {
-		t.Fatalf("expected empty store after JSON reset, got: %q", stdout.String())
-	}
-}
-
-func TestRunAuthReset(t *testing.T) {
-	path := withAuthStore(t)
-	store, err := oauth.NewStore(oauth.StoreOptions{FilePath: path})
-	if err != nil {
-		t.Fatalf("NewStore: %v", err)
-	}
-	if err := store.Save(oauth.ProviderKey("demo"), oauth.Token{AccessToken: "secret"}); err != nil {
-		t.Fatalf("Save: %v", err)
-	}
-
-	var stdout, stderr bytes.Buffer
-	if code := runWithDeps([]string{"auth", "reset", "--confirm"}, &stdout, &stderr, appDeps{}); code != exitSuccess {
-		t.Fatalf("exit = %d stderr=%s", code, stderr.String())
-	}
-	if !strings.Contains(stdout.String(), "Reset OAuth token store") {
-		t.Fatalf("stdout = %q", stdout.String())
-	}
-
-	// Verify store is now empty.
-	stdout.Reset()
-	stderr.Reset()
-	if code := runWithDeps([]string{"auth", "status"}, &stdout, &stderr, appDeps{}); code != exitSuccess {
-		t.Fatalf("status exit = %d", code)
-	}
-	if !strings.Contains(stdout.String(), "No OAuth provider logins are stored.") {
-		t.Fatalf("expected empty store after reset, got: %q", stdout.String())
-	}
-}
-
 // 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

internal/cli/command_center.go

@@ -407,11 +407,7 @@ func formatProviderCatalogLine(provider providerCatalogSummary) string {
 		provider.RuntimeSupported,
 	))
 	if provider.RuntimeSupported {
-		setup := "    setup: zero providers setup " + displayCLIValue(provider.ID, "unknown") + " --set-active"
-		if provider.ID == "atomic-chat-local" {
-			setup = "    setup: run zero setup to select a loaded model, or zero providers detect to get an add command"
-		}
-		lines = append(lines, setup)
+		lines = append(lines, "    setup: zero providers setup "+displayCLIValue(provider.ID, "unknown")+" --set-active")
 	} else {
 		lines = append(lines, "    unsupported: "+displayCLIValue(provider.RuntimeUnsupportedReason, "unknown"))
 	}
@@ -506,7 +502,7 @@ func writeProvidersHelp(w io.Writer) error {
   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, Atomic Chat) and prints adopt commands plus per-provider next steps.
+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:

internal/cli/command_center_test.go

@@ -967,10 +967,3 @@ func TestProvidersListMarksOAuthLoginProviders(t *testing.T) {
 		t.Fatalf("list should render the oauth login state, got:\n%s", rendered)
 	}
 }
-
-func TestAtomicCatalogSetupRequiresLoadedModel(t *testing.T) {
-	out := formatProviderCatalogLine(providerCatalogSummary{ID: "atomic-chat-local", RuntimeSupported: true})
-	if strings.Contains(out, "zero providers setup atomic-chat-local --set-active") || !strings.Contains(out, "zero setup") {
-		t.Fatalf("catalog advertises a failing setup command: %s", out)
-	}
-}

internal/cli/completions.go

@@ -20,7 +20,7 @@ type completionContext struct {
 }
 
 var completionRoot = completionNode{
-	flags: []string{"-h", "--help", "-v", "--version", "-p", "--prompt", "--add-dir", "--allow-escalation", "--theme", "--skip-permissions-unsafe"},
+	flags: []string{"-h", "--help", "-v", "--version", "-p", "--prompt", "--add-dir", "--theme", "--skip-permissions-unsafe"},
 	children: []completionNode{
 		{names: []string{"exec"}, flags: []string{
 			"-h", "--help", "-f", "--file", "--image", "--add-dir", "--mode", "-m", "--model",
@@ -78,8 +78,7 @@ var completionRoot = completionNode{
 			{names: []string{"tools"}, children: leafNodes("list")},
 			{names: []string{"oauth"}, children: leafNodes("login", "logout", "status")},
 		}},
-		{names: []string{"auth"}, children: append(leafNodes("openrouter", "chatgpt", "login", "logout", "status", "refresh"),
-			completionNode{names: []string{"reset"}, flags: []string{"--confirm", "--json", "--help"}})},
+		{names: []string{"auth"}, children: leafNodes("openrouter", "chatgpt", "login", "logout", "status", "refresh")},
 		{names: []string{"sandbox"}, children: []completionNode{
 			{names: []string{"policy"}}, {names: []string{"setup"}}, {names: []string{"check"}},
 			{names: []string{"grants"}, children: leafNodes("list", "allow", "deny", "revoke", "clear")},

internal/cli/completions_test.go

@@ -159,8 +159,6 @@ func TestCompletionTreeCoversAliasesNestingAndCommonFlags(t *testing.T) {
 	assertCandidates(t, byPath["worktree"], "prepare", "release")
 	assertCandidates(t, byPath["daemon"], "start", "stop", "status", "run", "attach")
 	assertCandidates(t, byPath["mcp oauth"], "login", "logout", "status")
-	assertCandidates(t, byPath["auth"], "openrouter", "chatgpt", "login", "logout", "status", "refresh", "reset")
-	assertCandidates(t, byPath["auth reset"], "--confirm", "--json", "--help")
 	assertCandidates(t, byPath["sandbox grants"], "list", "allow", "deny", "revoke", "clear")
 	assertCandidates(t, byPath["completions"], "bash", "zsh", "fish", "powershell", "elvish")
 	assertCandidates(t, byPath["plugins"], "list", "add", "info", "remove", "rm")

internal/cli/deferred_wiring_test.go

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

internal/cli/exec.go

@@ -442,22 +442,57 @@ func runExec(args []string, stdout io.Writer, stderr io.Writer, deps appDeps) in
 	// the resolved model and is reassigned by the model switcher on a mid-run
 	// escalation so post-switch turns are attributed to the escalated model.
 	currentModel := resolved.Provider.Model
-	// Optimized OpenAI turn sessions (ZERO_OPENAI_TURN_SESSION, default off). nil
-	// when gated off or the profile is ineligible: agent.Run then wraps the
-	// provider in its default adapter. This is the run's STARTING session provider
-	// and is used whether or not escalation is enabled.
-	turnSessions, _ := providers.OptimizedTurnSessions(resolved.Provider, provider, providers.Options{})
-	// Both switchers come from one shared builder so exec and the interactive TUI
-	// cannot drift on the nil contracts the agent loop depends on. The session
-	// switcher is nil unless this run STARTED optimized, which is what keeps a
-	// default-adapter run on the default adapter.
 	var modelSwitcher func(context.Context, string) (agent.Provider, error)
-	var modelSessionSwitcher func(context.Context, string) (zeroruntime.TurnSessionProvider, error)
 	if options.allowEscalation {
-		modelSwitcher, modelSessionSwitcher = providers.EscalationSwitchers(
-			resolved.Provider, provider, deps.newProvider,
-			func(modelID string) { currentModel = modelID },
-		)
+		modelSwitcher = func(_ context.Context, modelID string) (agent.Provider, error) {
+			// deps.newProvider is wrapped (fillAppDeps) to apply the stored key, so
+			// the escalated provider is authenticated even though resolved.Provider
+			// is the pure profile — no per-site key handling here.
+			switchedProfile := resolved.Provider
+			switchedProfile.Model = modelID
+			switchedProvider, err := deps.newProvider(switchedProfile)
+			if err != nil {
+				return nil, err
+			}
+			// Mirror the agent loop's switch guard (it only reassigns the provider
+			// when newProvider != nil). Updating currentModel only on a non-nil
+			// provider keeps usage attribution consistent with whether the loop
+			// actually switched — a (nil, nil) return leaves both untouched.
+			if switchedProvider != nil {
+				currentModel = modelID
+			}
+			return switchedProvider, nil
+		}
+	}
+
+	// Optimized OpenAI turn sessions (ZERO_OPENAI_TURN_SESSION, default off).
+	// nil when gated off or the profile is ineligible: agent.Run then wraps the
+	// provider in its default adapter — the exact code path of today. The
+	// session switcher is installed only when the run START is optimized, so
+	// the legacy ModelSwitcher path above stays untouched otherwise.
+	turnSessions, _ := providers.OptimizedTurnSessions(resolved.Provider, provider, providers.Options{})
+	var modelSessionSwitcher func(context.Context, string) (zeroruntime.TurnSessionProvider, error)
+	if options.allowEscalation && turnSessions != nil {
+		modelSessionSwitcher = func(_ context.Context, modelID string) (zeroruntime.TurnSessionProvider, error) {
+			switchedProfile := resolved.Provider
+			switchedProfile.Model = modelID
+			switchedProvider, err := deps.newProvider(switchedProfile)
+			if err != nil {
+				return nil, err
+			}
+			if switchedProvider == nil {
+				// The loop treats a nil session source as "no swap" — mirror the
+				// legacy closure's (nil, nil) contract.
+				return nil, nil
+			}
+			currentModel = modelID
+			if optimized, ok := providers.OptimizedTurnSessions(switchedProfile, switchedProvider, providers.Options{}); ok {
+				return optimized, nil
+			}
+			// Ineligible switch target: default adapter, but with the switched
+			// model's resolved capability projection preserved.
+			return providers.DefaultTurnSessions(switchedProfile, switchedProvider, providers.Options{}), nil
+		}
 	}
 
 	runMetadata, err := resolveExecRunMetadata(resolved.Provider)
@@ -647,20 +682,16 @@ func runExec(args []string, stdout io.Writer, stderr io.Writer, deps appDeps) in
 		ModelSwitcher:        modelSwitcher,
 		TurnSessionProvider:  turnSessions,
 		ModelSessionSwitcher: modelSessionSwitcher,
-		Summarizer:           summarizerFactory(resolved, deps.newProvider),
-		ContextWindowFor: func(modelID string) int {
-			return modelregistry.AgentContextWindow(modelContextWindow(modelRegistry, modelID))
-		},
-		ReasoningEffort: forwardEffort,
-		Trace:           traceRecorder,
-		Cwd:             workspaceRoot,
-		Images:          images,
-		Registry:        registry,
-		PermissionMode:  permissionMode,
-		Autonomy:        options.autonomy,
-		SelfCorrect:     selfCorrector,
-		FileDiagnostics: fileDiagnostics,
-		Profile:         execProfile.Policy(displacedMaxTurns, execProfileFilledEffort),
+		ReasoningEffort:      forwardEffort,
+		Trace:                traceRecorder,
+		Cwd:                  workspaceRoot,
+		Images:               images,
+		Registry:             registry,
+		PermissionMode:       permissionMode,
+		Autonomy:             options.autonomy,
+		SelfCorrect:          selfCorrector,
+		FileDiagnostics:      fileDiagnostics,
+		Profile:              execProfile.Policy(displacedMaxTurns, execProfileFilledEffort),
 		// Headless exec: don't accept a no-tool-call turn as "done" while work
 		// clearly remains (pending plan items / a mid-step continuation cue) —
 		// nudge to continue, and finalize as INCOMPLETE rather than false success

internal/cli/mcp_config.go

@@ -29,8 +29,6 @@ type mcpWritableConfig struct {
 	serverRaw map[string]json.RawMessage
 }
 
-var lockMCPConfigFile = config.LockFile
-
 // projectMCPConfigExists reports whether the workspace's project ./.zero/config.json
 // declares any MCP servers, so the trust notice fires only when project MCP config was
 // actually skipped (mirroring projectHooksFileExists / projectPluginsDirExists). A
@@ -52,7 +50,7 @@ func projectMCPConfigExists(workspaceRoot string) bool {
 	return len(fc.MCP.Servers) > 0
 }
 
-func runMCPAdd(args []string, stdout io.Writer, stderr io.Writer, deps appDeps) (exitCode int) {
+func runMCPAdd(args []string, stdout io.Writer, stderr io.Writer, deps appDeps) int {
 	options, help, err := parseMCPAddArgs(args)
 	if err != nil {
 		return writeExecUsageError(stderr, err.Error())
@@ -68,26 +66,6 @@ func runMCPAdd(args []string, stdout io.Writer, stderr io.Writer, deps appDeps)
 	if err != nil {
 		return writeAppError(stderr, "failed to resolve user config: "+err.Error(), exitCrash)
 	}
-	// This edits the same user config document the config package mutates, with
-	// the same read-modify-write + rename shape, so it takes the same
-	// cross-process lock. Without it, an MCP config edit racing a provider or
-	// preference write would silently drop whichever landed first (issue #832).
-	unlock, err := lockMCPConfigFile(configPath)
-	if err != nil {
-		return writeAppError(stderr, redaction.ErrorMessage(err, redaction.Options{}), exitCrash)
-	}
-	released := false
-	defer func() {
-		if released {
-			return
-		}
-		// A failed release leaves the lock held for the rest of the process, so
-		// exiting success here would claim a state the next config write cannot
-		// reproduce. It must not mask a failure this command already reported.
-		if releaseErr := unlock(); releaseErr != nil && exitCode == exitSuccess {
-			exitCode = writeAppError(stderr, redaction.ErrorMessage(releaseErr, redaction.Options{}), exitCrash)
-		}
-	}()
 	cfg, err := readMCPWritableConfig(configPath)
 	if err != nil {
 		return writeAppError(stderr, redaction.ErrorMessage(err, redaction.Options{}), exitCrash)
@@ -102,10 +80,6 @@ func runMCPAdd(args []string, stdout io.Writer, stderr io.Writer, deps appDeps)
 	if err := writeMCPWritableConfig(configPath, cfg); err != nil {
 		return writeAppError(stderr, redaction.ErrorMessage(err, redaction.Options{}), exitCrash)
 	}
-	if err := unlock(); err != nil {
-		return writeAppError(stderr, redaction.ErrorMessage(err, redaction.Options{}), exitCrash)
-	}
-	released = true
 
 	if options.json {
 		payload := struct {
@@ -135,7 +109,7 @@ func runMCPAdd(args []string, stdout io.Writer, stderr io.Writer, deps appDeps)
 	return exitSuccess
 }
 
-func runMCPRemove(args []string, stdout io.Writer, stderr io.Writer, deps appDeps) (exitCode int) {
+func runMCPRemove(args []string, stdout io.Writer, stderr io.Writer, deps appDeps) int {
 	options, positional, help, err := parseMCPConfigPositionalCommand(args, "remove")
 	if err != nil {
 		return writeExecUsageError(stderr, err.Error())
@@ -158,26 +132,6 @@ func runMCPRemove(args []string, stdout io.Writer, stderr io.Writer, deps appDep
 	if err != nil {
 		return writeAppError(stderr, "failed to resolve user config: "+err.Error(), exitCrash)
 	}
-	// This edits the same user config document the config package mutates, with
-	// the same read-modify-write + rename shape, so it takes the same
-	// cross-process lock. Without it, an MCP config edit racing a provider or
-	// preference write would silently drop whichever landed first (issue #832).
-	unlock, err := lockMCPConfigFile(configPath)
-	if err != nil {
-		return writeAppError(stderr, redaction.ErrorMessage(err, redaction.Options{}), exitCrash)
-	}
-	released := false
-	defer func() {
-		if released {
-			return
-		}
-		// A failed release leaves the lock held for the rest of the process, so
-		// exiting success here would claim a state the next config write cannot
-		// reproduce. It must not mask a failure this command already reported.
-		if releaseErr := unlock(); releaseErr != nil && exitCode == exitSuccess {
-			exitCode = writeAppError(stderr, redaction.ErrorMessage(releaseErr, redaction.Options{}), exitCrash)
-		}
-	}()
 	cfg, err := readMCPWritableConfig(configPath)
 	if err != nil {
 		return writeAppError(stderr, redaction.ErrorMessage(err, redaction.Options{}), exitCrash)
@@ -191,10 +145,6 @@ func runMCPRemove(args []string, stdout io.Writer, stderr io.Writer, deps appDep
 			return writeAppError(stderr, redaction.ErrorMessage(err, redaction.Options{}), exitCrash)
 		}
 	}
-	if err := unlock(); err != nil {
-		return writeAppError(stderr, redaction.ErrorMessage(err, redaction.Options{}), exitCrash)
-	}
-	released = true
 
 	if options.json {
 		payload := struct {
@@ -217,7 +167,7 @@ func runMCPRemove(args []string, stdout io.Writer, stderr io.Writer, deps appDep
 	return exitSuccess
 }
 
-func runMCPToggle(args []string, stdout io.Writer, stderr io.Writer, deps appDeps, disabled bool) (exitCode int) {
+func runMCPToggle(args []string, stdout io.Writer, stderr io.Writer, deps appDeps, disabled bool) int {
 	commandName := "enable"
 	if disabled {
 		commandName = "disable"
@@ -244,26 +194,6 @@ func runMCPToggle(args []string, stdout io.Writer, stderr io.Writer, deps appDep
 	if err != nil {
 		return writeAppError(stderr, "failed to resolve user config: "+err.Error(), exitCrash)
 	}
-	// This edits the same user config document the config package mutates, with
-	// the same read-modify-write + rename shape, so it takes the same
-	// cross-process lock. Without it, an MCP config edit racing a provider or
-	// preference write would silently drop whichever landed first (issue #832).
-	unlock, err := lockMCPConfigFile(configPath)
-	if err != nil {
-		return writeAppError(stderr, redaction.ErrorMessage(err, redaction.Options{}), exitCrash)
-	}
-	released := false
-	defer func() {
-		if released {
-			return
-		}
-		// A failed release leaves the lock held for the rest of the process, so
-		// exiting success here would claim a state the next config write cannot
-		// reproduce. It must not mask a failure this command already reported.
-		if releaseErr := unlock(); releaseErr != nil && exitCode == exitSuccess {
-			exitCode = writeAppError(stderr, redaction.ErrorMessage(releaseErr, redaction.Options{}), exitCrash)
-		}
-	}()
 	cfg, err := readMCPWritableConfig(configPath)
 	if err != nil {
 		return writeAppError(stderr, redaction.ErrorMessage(err, redaction.Options{}), exitCrash)
@@ -280,10 +210,6 @@ func runMCPToggle(args []string, stdout io.Writer, stderr io.Writer, deps appDep
 			return writeAppError(stderr, redaction.ErrorMessage(err, redaction.Options{}), exitCrash)
 		}
 	}
-	if err := unlock(); err != nil {
-		return writeAppError(stderr, redaction.ErrorMessage(err, redaction.Options{}), exitCrash)
-	}
-	released = true
 
 	if options.json {
 		payload := struct {

internal/cli/mcp_config_lock_test.go

@@ -1,221 +0,0 @@
-package cli
-
-import (
-	"bytes"
-	"errors"
-	"os"
-	"path/filepath"
-	"strings"
-	"testing"
-	"time"
-
-	"github.com/Gitlawb/zero/internal/config"
-)
-
-type mcpConfigLockCase struct {
-	name     string
-	args     []string
-	disabled bool
-	server   bool
-}
-
-func mcpConfigLockCases() []mcpConfigLockCase {
-	return []mcpConfigLockCase{
-		{name: "add", args: []string{"mcp", "add", "docs", "--", "docs-mcp"}},
-		{name: "remove", args: []string{"mcp", "remove", "docs"}, server: true},
-		{name: "enable", args: []string{"mcp", "enable", "docs"}, server: true, disabled: true},
-		{name: "disable", args: []string{"mcp", "disable", "docs"}, server: true},
-	}
-}
-
-func seedMCPConfigLockCase(t *testing.T, path string, testCase mcpConfigLockCase) {
-	t.Helper()
-	servers := map[string]config.MCPServerConfig{}
-	if testCase.server {
-		servers["docs"] = config.MCPServerConfig{Type: "stdio", Command: "docs-mcp", Disabled: testCase.disabled}
-	}
-	writeMCPCommandConfig(t, path, config.FileConfig{
-		ActiveProvider: "seed",
-		Providers:      []config.ProviderProfile{{Name: "seed", Model: "seed-model"}},
-		MCP:            config.MCPConfig{Servers: servers},
-	})
-}
-
-func assertMCPConfigLockMutation(t *testing.T, path string, testCase mcpConfigLockCase) {
-	t.Helper()
-	cfg := readMCPCommandConfig(t, path)
-	server, exists := cfg.MCP.Servers["docs"]
-	switch testCase.name {
-	case "add":
-		if !exists {
-			t.Fatal("mcp add did not persist the server")
-		}
-	case "remove":
-		if exists {
-			t.Fatal("mcp remove left the server configured")
-		}
-	case "enable":
-		if !exists || server.Disabled {
-			t.Fatalf("mcp enable result = %+v, exists=%v", server, exists)
-		}
-	case "disable":
-		if !exists || !server.Disabled {
-			t.Fatalf("mcp disable result = %+v, exists=%v", server, exists)
-		}
-	}
-	if cfg.Preferences.Theme != "dracula" {
-		t.Errorf("theme update was lost: theme = %q, want dracula", cfg.Preferences.Theme)
-	}
-	if cfg.ActiveProvider != "seed" || len(cfg.Providers) != 1 || cfg.Providers[0].Name != "seed" {
-		t.Errorf("seeded provider was lost: active=%q providers=%#v", cfg.ActiveProvider, cfg.Providers)
-	}
-}
-
-// TestRunMCPConfigCommandsParticipateInConfigLock covers the half of issue #832
-// that lives outside internal/config. MCP config commands read the SAME user
-// config document, edit it, and republish it with the same temp-file+rename
-// shape as the config package's mutators. Locking only the config package would
-// leave these writers free to clobber a concurrent provider or preference
-// update, and be clobbered by one, with the file still valid JSON afterwards.
-//
-// Racing the two writers and hoping to observe a lost update is unreliable —
-// the interleaving that loses one is narrow, and the test passed consistently
-// against the unlocked code. So this asserts the property that actually matters
-// and is deterministic: while the config lock is held elsewhere, the MCP
-// writer's update CANNOT land. Once released it completes, and both updates
-// survive.
-func TestRunMCPConfigCommandsParticipateInConfigLock(t *testing.T) {
-	for _, testCase := range mcpConfigLockCases() {
-		t.Run(testCase.name, func(t *testing.T) {
-			configPath := filepath.Join(t.TempDir(), "zero", "config.json")
-			seedMCPConfigLockCase(t, configPath, testCase)
-			before, err := os.ReadFile(configPath)
-			if err != nil {
-				t.Fatal(err)
-			}
-
-			unlock, err := config.LockFile(configPath)
-			if err != nil {
-				t.Fatalf("acquire config lock: %v", err)
-			}
-			released := false
-			release := func() {
-				if !released {
-					released = true
-					if err := unlock(); err != nil {
-						t.Fatalf("release config lock: %v", err)
-					}
-				}
-			}
-			defer release()
-
-			original := lockMCPConfigFile
-			lockAttempted := make(chan struct{})
-			lockMCPConfigFile = func(path string) (func() error, error) {
-				close(lockAttempted)
-				return original(path)
-			}
-			t.Cleanup(func() { lockMCPConfigFile = original })
-
-			var stdout, stderr bytes.Buffer
-			done := make(chan int, 1)
-			go func() {
-				done <- runWithDeps(testCase.args, &stdout, &stderr, appDeps{
-					userConfigPath: func() (string, error) { return configPath, nil },
-				})
-			}()
-
-			select {
-			case <-lockAttempted:
-			case <-time.After(30 * time.Second):
-				t.Fatalf("mcp %s did not attempt config lock acquisition", testCase.name)
-			}
-
-			for range 20 {
-				after, err := os.ReadFile(configPath)
-				if err != nil {
-					t.Fatal(err)
-				}
-				if !bytes.Equal(after, before) {
-					t.Fatalf("mcp %s changed config while its lock was held", testCase.name)
-				}
-				select {
-				case exitCode := <-done:
-					t.Fatalf("mcp %s completed (exit %d) while its lock was held", testCase.name, exitCode)
-				default:
-				}
-				time.Sleep(5 * time.Millisecond)
-			}
-
-			release()
-			select {
-			case exitCode := <-done:
-				if exitCode != exitSuccess {
-					t.Fatalf("mcp %s exitCode = %d stderr=%s", testCase.name, exitCode, stderr.String())
-				}
-			case <-time.After(30 * time.Second):
-				t.Fatalf("mcp %s did not finish after the config lock was released", testCase.name)
-			}
-
-			if _, err := config.SetTheme(configPath, "dracula"); err != nil {
-				t.Fatalf("SetTheme: %v", err)
-			}
-			assertMCPConfigLockMutation(t, configPath, testCase)
-		})
-	}
-}
-
-func TestRunMCPConfigCommandsReportLockAcquisitionFailure(t *testing.T) {
-	sentinel := errors.New("injected lock acquisition failure")
-	original := lockMCPConfigFile
-	lockMCPConfigFile = func(string) (func() error, error) { return nil, sentinel }
-	t.Cleanup(func() { lockMCPConfigFile = original })
-
-	for _, testCase := range mcpConfigLockCases() {
-		t.Run(testCase.name, func(t *testing.T) {
-			configPath := filepath.Join(t.TempDir(), "zero", "config.json")
-			seedMCPConfigLockCase(t, configPath, testCase)
-			before, err := os.ReadFile(configPath)
-			if err != nil {
-				t.Fatal(err)
-			}
-			var stdout, stderr bytes.Buffer
-			exitCode := runWithDeps(testCase.args, &stdout, &stderr, appDeps{
-				userConfigPath: func() (string, error) { return configPath, nil },
-			})
-			if exitCode != exitCrash || stdout.Len() != 0 || !strings.Contains(stderr.String(), sentinel.Error()) {
-				t.Fatalf("exit=%d stdout=%q stderr=%q, want lock error without success output", exitCode, stdout.String(), stderr.String())
-			}
-			after, err := os.ReadFile(configPath)
-			if err != nil {
-				t.Fatal(err)
-			}
-			if !bytes.Equal(after, before) {
-				t.Fatal("command changed config after lock acquisition failed")
-			}
-		})
-	}
-}
-
-func TestRunMCPConfigCommandsReleaseBeforeSuccessOutput(t *testing.T) {
-	sentinel := errors.New("injected lock release failure")
-	original := lockMCPConfigFile
-	lockMCPConfigFile = func(string) (func() error, error) {
-		return func() error { return sentinel }, nil
-	}
-	t.Cleanup(func() { lockMCPConfigFile = original })
-
-	for _, testCase := range mcpConfigLockCases() {
-		t.Run(testCase.name, func(t *testing.T) {
-			configPath := filepath.Join(t.TempDir(), "zero", "config.json")
-			seedMCPConfigLockCase(t, configPath, testCase)
-			var stdout, stderr bytes.Buffer
-			exitCode := runWithDeps(testCase.args, &stdout, &stderr, appDeps{
-				userConfigPath: func() (string, error) { return configPath, nil },
-			})
-			if exitCode != exitCrash || stdout.Len() != 0 || !strings.Contains(stderr.String(), sentinel.Error()) {
-				t.Fatalf("exit=%d stdout=%q stderr=%q, want unlock error before success output", exitCode, stdout.String(), stderr.String())
-			}
-		})
-	}
-}

internal/cli/mcp_tools.go

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

internal/cli/provider_adoption_test.go

@@ -1,117 +0,0 @@
-package cli
-
-import (
-	"context"
-	"encoding/json"
-	"fmt"
-	"net/http"
-	"net/http/httptest"
-	"os"
-	"os/exec"
-	"path/filepath"
-	"strings"
-	"testing"
-	"time"
-
-	"github.com/Gitlawb/zero/internal/provideronboarding"
-	"mvdan.cc/sh/v3/shell"
-)
-
-func TestLocalAdoptionSavesAndReloadsEligibleModel(t *testing.T) {
-	const wantModel = "-loaded chat model"
-	requests := make(chan string, 4)
-	server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
-		switch r.URL.Path {
-		case "/v1/models":
-			w.Header().Set("Content-Type", "application/json")
-			_, _ = fmt.Fprintf(w, `{"data":[{"id":"text-embedding-local"},{"id":%q}]}`, wantModel)
-		case "/v1/chat/completions":
-			var body struct {
-				Model string `json:"model"`
-			}
-			if err := json.NewDecoder(r.Body).Decode(&body); err != nil {
-				t.Errorf("decode completion request: %v", err)
-				w.WriteHeader(http.StatusBadRequest)
-				return
-			}
-			if r.Header.Get("Authorization") != "" {
-				t.Error("local adoption unexpectedly sent authorization")
-			}
-			select {
-			case requests <- body.Model:
-			default:
-				t.Error("unexpected extra completion requests")
-			}
-			w.Header().Set("Content-Type", "text/event-stream")
-			_, _ = fmt.Fprint(w, "data: {\"choices\":[{\"delta\":{\"content\":\"adoption ok\"},\"finish_reason\":\"stop\"}]}\n\ndata: [DONE]\n\n")
-		default:
-			w.WriteHeader(http.StatusNotFound)
-		}
-	}))
-	defer server.Close()
-	detected := provideronboarding.DetectLocalRuntimes(context.Background(), provideronboarding.LocalDetectOptions{
-		HTTPClient: server.Client(),
-		Candidates: []provideronboarding.LocalRuntime{{CatalogID: "atomic-chat-local", Name: "Atomic Chat Local", DefaultModel: "local-model", BaseURL: server.URL + "/v1"}},
-	})
-	if len(detected) != 1 {
-		t.Fatalf("expected one detected runtime: %+v", detected)
-	}
-	args, err := shell.Fields(detected[0].SetupAction().Command, func(string) string { return "" })
-	if err != nil || len(args) < 4 {
-		t.Fatalf("invalid adoption command: args=%q err=%v", args, err)
-	}
-	root := t.TempDir()
-	run := func(args ...string) string {
-		t.Helper()
-		ctx, cancel := context.WithTimeout(context.Background(), 30*time.Second)
-		defer cancel()
-		childArgs := append([]string{"-test.run=^TestLocalAdoptionCLIProcess$", "--"}, args...)
-		cmd := exec.CommandContext(ctx, os.Args[0], childArgs...)
-		cmd.Dir = root
-		cmd.Env = []string{
-			"ZERO_TEST_LOCAL_ADOPTION=1", "ZERO_CRED_STORAGE=encrypted-file",
-			"HOME=" + root, "USERPROFILE=" + root,
-			"XDG_CONFIG_HOME=" + filepath.Join(root, "config"),
-			"XDG_CACHE_HOME=" + filepath.Join(root, "cache"),
-			"XDG_STATE_HOME=" + filepath.Join(root, "state"),
-			"APPDATA=" + filepath.Join(root, "config"),
-			"LOCALAPPDATA=" + filepath.Join(root, "cache"),
-		}
-		for _, key := range []string{"PATH", "SystemRoot", "WINDIR", "TMPDIR", "TEMP", "TMP"} {
-			if value, ok := os.LookupEnv(key); ok {
-				cmd.Env = append(cmd.Env, key+"="+value)
-			}
-		}
-		output, err := cmd.CombinedOutput()
-		if err != nil {
-			t.Fatalf("CLI %q failed: %v\n%s", args, err, output)
-		}
-		return string(output)
-	}
-	// The mock uses a random port; only override the endpoint, retaining all
-	// generated arguments for the real add parser and persistence path.
-	run(append(args[1:], "--base-url", server.URL+"/v1")...)
-	if output := run("exec", "--cwd", root, "Reply with adoption ok"); !strings.Contains(output, "adoption ok") {
-		t.Fatalf("completion output = %q", output)
-	}
-	select {
-	case model := <-requests:
-		if model != wantModel {
-			t.Fatalf("fresh process sent model %q, want eligible model %q", model, wantModel)
-		}
-	default:
-		t.Fatal("fresh process did not send a completion request")
-	}
-}
-
-func TestLocalAdoptionCLIProcess(t *testing.T) {
-	if os.Getenv("ZERO_TEST_LOCAL_ADOPTION") != "1" {
-		return
-	}
-	for i, arg := range os.Args {
-		if arg == "--" {
-			os.Exit(Run(os.Args[i+1:], os.Stdout, os.Stderr))
-		}
-	}
-	t.Fatal("missing helper argument separator")
-}

internal/cli/provider_detect.go

@@ -40,7 +40,7 @@ type providerDetectReport struct {
 }
 
 // runProvidersDetect probes the machine for running local, OpenAI-compatible
-// model runtimes (Ollama, LM Studio, Atomic Chat) and prints a no-key adopt command for each
+// model runtimes (Ollama, LM Studio) and prints a no-key adopt command for each
 // one it finds, followed by the next-step actions for every already-configured
 // provider. It is the onboarding-advice surface — "what can I do right now?" —
 // and never errors on a machine with nothing running locally (it just reports an
@@ -146,8 +146,6 @@ func formatProviderDetectReport(report providerDetectReport) string {
 		}
 		if command := strings.TrimSpace(runtime.Action.Command); command != "" {
 			lines = append(lines, "    "+runtime.Action.Label+": "+command)
-		} else if detail := strings.TrimSpace(runtime.Action.Detail); detail != "" {
-			lines = append(lines, "    "+runtime.Action.Label+": "+detail)
 		}
 	}
 

internal/cli/provider_detect_test.go

@@ -105,13 +105,3 @@ func TestRunProvidersDetectJSONNoRuntimesActiveProvider(t *testing.T) {
 		t.Fatalf("expected only a Check action for an active keyed provider, got %#v", payload.Providers[0].Actions)
 	}
 }
-
-func TestProviderDetectShowsGuidanceWithoutCommand(t *testing.T) {
-	for _, models := range [][]string{nil, {"local-model"}, {"x&calc"}} {
-		runtime := provideronboarding.DetectedLocalRuntime{LocalRuntime: provideronboarding.LocalRuntime{CatalogID: "atomic-chat-local", Name: "Atomic Chat Local", DefaultModel: "local-model"}, Models: models}
-		out := formatProviderDetectReport(buildProviderDetectReport(config.ResolvedConfig{}, []provideronboarding.DetectedLocalRuntime{runtime}))
-		if strings.Contains(out, "providers add") || !strings.Contains(out, runtime.SetupAction().Detail) {
-			t.Fatalf("missing actionable guidance: %s", out)
-		}
-	}
-}

internal/cli/provider_setup.go

@@ -434,14 +434,6 @@ func providerProfileForAdd(options providerAddOptions) (config.ProviderProfile,
 			catalogHeaders = aimlapi.WithResolvedPartnerHeader(catalogHeaders)
 		}
 	}
-	// Discovery fallback can pass the nonempty catalog placeholder through
-	// either CLI setup path. Never persist it as an Atomic Chat model.
-	if descriptor.ID == "atomic-chat-local" {
-		model := strings.TrimSpace(options.model)
-		if model == "" || model == "local-model" {
-			return config.ProviderProfile{}, fmt.Errorf("provider %q serves a locally loaded model; pass --model <id> (run `zero providers detect` to see the served model)", descriptor.ID)
-		}
-	}
 	profile := config.ProviderProfile{
 		Name:            name,
 		ProviderKind:    providerKindForDescriptor(descriptor),

internal/cli/provider_setup_test.go

@@ -1,12 +1,9 @@
 package cli
 
 import (
-	"strings"
 	"testing"
 
 	"github.com/Gitlawb/zero/internal/config"
-	"github.com/Gitlawb/zero/internal/provideronboarding"
-	"mvdan.cc/sh/v3/shell"
 )
 
 // Regression for issue #555's follow-up: `zero providers check` must not
@@ -69,58 +66,3 @@ func TestValidateProviderRuntimeReadyCustomEndpoint(t *testing.T) {
 		})
 	}
 }
-
-// atomic-chat-local without --model would persist the catalog placeholder
-// "local-model", which the Atomic Chat server never serves, so the first
-// completion fails. Adding it must require a real model instead.
-func TestProviderProfileForAddRequiresModelForAtomicChatLocal(t *testing.T) {
-	if _, err := providerProfileForAdd(providerAddOptions{catalogID: "atomic-chat-local"}); err == nil {
-		t.Fatalf("providerProfileForAdd(atomic-chat-local, no --model) = nil error, want a require-model error")
-	} else if !strings.Contains(err.Error(), "--model") {
-		t.Fatalf("error should tell the user to pass --model, got %v", err)
-	}
-
-	// The interactive wizards and the no-id detect fallback resolve the model to
-	// the catalog DefaultModel and pass it through as a non-empty value, so the
-	// placeholder itself must be rejected, not just an empty --model.
-	if _, err := providerProfileForAdd(providerAddOptions{catalogID: "atomic-chat-local", model: "local-model"}); err == nil {
-		t.Fatalf("providerProfileForAdd(atomic-chat-local, --model local-model) = nil error, want reject of the catalog placeholder")
-	}
-
-	profile, err := providerProfileForAdd(providerAddOptions{catalogID: "atomic-chat-local", model: "unsloth/gemma-4-E2B-it-GGUF"})
-	if err != nil {
-		t.Fatalf("providerProfileForAdd(atomic-chat-local, --model) returned error: %v", err)
-	}
-	if profile.Model != "unsloth/gemma-4-E2B-it-GGUF" {
-		t.Fatalf("profile.Model = %q, want the explicit model", profile.Model)
-	}
-	if profile.Model == "local-model" {
-		t.Fatalf("profile persisted the catalog placeholder")
-	}
-}
-
-func TestDetectedModelActionSurvivesAddParser(t *testing.T) {
-	for _, catalogID := range []string{"atomic-chat-local", "lmstudio", "ollama"} {
-		for _, modelID := range []string{"-loaded-model", "--set-active", "--model", "-loaded model", "ordinary/model", "model with spaces"} {
-			t.Run(catalogID+"/"+modelID, func(t *testing.T) {
-				detected := provideronboarding.DetectedLocalRuntime{
-					LocalRuntime: provideronboarding.LocalRuntime{CatalogID: catalogID, Name: "Local Runtime", DefaultModel: "local-model"},
-					Models:       []string{modelID},
-				}
-				command := detected.SetupAction().Command
-				args, err := shell.Fields(command, func(string) string { return "" })
-				if err != nil || len(args) < 4 {
-					t.Fatalf("invalid adoption command %q: %v", command, err)
-				}
-				options, help, err := parseProviderAddArgs(args[3:])
-				if err != nil || help {
-					t.Fatalf("generated adoption command rejected by add parser: %q: %v", command, err)
-				}
-				profile, err := providerProfileForAdd(options)
-				if err != nil || profile.Model != modelID || !options.setActive || profile.Name != "Local Runtime" {
-					t.Fatalf("adoption changed model or options: model=%q name=%q active=%v err=%v", profile.Model, profile.Name, options.setActive, err)
-				}
-			})
-		}
-	}
-}

internal/cli/root_flag_order_test.go

@@ -1,211 +0,0 @@
-package cli
-
-import (
-	"bytes"
-	"context"
-	"path/filepath"
-	"strings"
-	"testing"
-
-	"github.com/Gitlawb/zero/internal/agent"
-	"github.com/Gitlawb/zero/internal/config"
-	"github.com/Gitlawb/zero/internal/sandbox"
-	"github.com/Gitlawb/zero/internal/tui"
-	"github.com/Gitlawb/zero/internal/zeroruntime"
-)
-
-// rootFlagOrderings is every ordering of the given flag groups, each group
-// kept intact so a flag stays next to its value.
-func rootFlagOrderings(groups [][]string) [][]string {
-	if len(groups) == 0 {
-		return [][]string{{}}
-	}
-	var orderings [][]string
-	for index, group := range groups {
-		rest := append(append([][]string{}, groups[:index]...), groups[index+1:]...)
-		for _, tail := range rootFlagOrderings(rest) {
-			orderings = append(orderings, append(append([]string{}, group...), tail...))
-		}
-	}
-	return orderings
-}
-
-// ROOT FLAGS COMPOSE IN ANY ORDER. Each leading-flag splitter stops at the first
-// token it does not own, so running them once in a fixed sequence made the
-// order the operator wrote them in load-bearing: `zero --allow-escalation
-// --theme auto` stranded `--theme auto` as an unknown command and exited with
-// an argument error instead of launching. Every ordering of the three root
-// flags, with --skip-permissions-unsafe absent or at any position, has to reach
-// the TUI with all three applied.
-func TestRootFlagsComposeInAnyOrder(t *testing.T) {
-	extra := t.TempDir()
-	resolvedExtra, err := filepath.EvalSymlinks(extra)
-	if err != nil {
-		t.Fatal(err)
-	}
-	groups := [][]string{{"--add-dir", extra}, {"--theme", "auto"}, {"--allow-escalation"}}
-	cases := rootFlagOrderings(groups)
-	cases = append(cases, rootFlagOrderings(append(groups, []string{"--skip-permissions-unsafe"}))...)
-	if len(cases) != 6+24 {
-		t.Fatalf("SETUP INVALID: %d orderings, want 30", len(cases))
-	}
-	for _, args := range cases {
-		t.Run(strings.Join(args, " "), func(t *testing.T) {
-			options := captureTUIOptions(t, args...)
-			wantMode := agent.PermissionModeAsk
-			for _, arg := range args {
-				if arg == "--skip-permissions-unsafe" {
-					wantMode = agent.PermissionModeUnsafe
-				}
-			}
-			if options.PermissionMode != wantMode {
-				t.Errorf("PermissionMode = %q, want %q", options.PermissionMode, wantMode)
-			}
-			if !options.AllowEscalation {
-				t.Error("escalation not enabled")
-			}
-			if options.Theme != "auto" {
-				t.Errorf("Theme = %q, want auto", options.Theme)
-			}
-			if options.AgentOptions.Sandbox == nil {
-				t.Fatal("no sandbox engine on the launched options")
-			}
-			roots := options.AgentOptions.Sandbox.Scope().Roots()
-			found := false
-			for _, root := range roots {
-				if root == resolvedExtra {
-					found = true
-				}
-			}
-			if !found {
-				t.Errorf("scope roots = %v, want the --add-dir root %q", roots, resolvedExtra)
-			}
-		})
-	}
-}
-
-// The last --theme wins even with another root flag between two of them, and a
-// --theme written before --skip-permissions-unsafe reaches the TUI: the unsafe
-// path used to launch with only the theme written after the flag, dropping one
-// written before it.
-func TestRootThemeLastOccurrenceWinsAcrossOtherFlags(t *testing.T) {
-	for _, testCase := range []struct {
-		args []string
-		want string
-	}{
-		{[]string{"--theme", "light", "--allow-escalation", "--theme", "auto"}, "auto"},
-		{[]string{"--theme", "auto", "--skip-permissions-unsafe"}, "auto"},
-		{[]string{"--theme", "light", "--skip-permissions-unsafe", "--theme", "auto"}, "auto"},
-	} {
-		t.Run(strings.Join(testCase.args, " "), func(t *testing.T) {
-			options := captureTUIOptions(t, testCase.args...)
-			if options.Theme != testCase.want {
-				t.Fatalf("Theme = %q, want %q", options.Theme, testCase.want)
-			}
-		})
-	}
-}
-
-// THE ROOT FLAG REACHES EXEC. A --allow-escalation written before the
-// subcommand is forwarded the way --add-dir is, so `zero --allow-escalation -p
-// "..."` runs with the opt-in the help text promises instead of silently
-// without it. The negative control is the same run without the flag, which
-// must not advertise escalate_model.
-func TestRootAllowEscalationForwardsIntoExec(t *testing.T) {
-	for _, testCase := range []struct {
-		name string
-		args []string
-	}{
-		{"exec subcommand", []string{"--allow-escalation", "exec", "say hi"}},
-		{"prompt flag", []string{"--allow-escalation", "-p", "say hi"}},
-	} {
-		t.Run(testCase.name, func(t *testing.T) {
-			if !execAdvertisesEscalateModel(t, testCase.args) {
-				t.Fatalf("%v ran without escalate_model advertised: the root flag was dropped before exec", testCase.args)
-			}
-			if execAdvertisesEscalateModel(t, testCase.args[1:]) {
-				t.Fatalf("%v advertised escalate_model without the flag", testCase.args[1:])
-			}
-		})
-	}
-}
-
-// Everywhere else the flag is rejected loudly rather than discarded, the way
-// --add-dir is: help and version run no agent and could only ignore it.
-func TestRootAllowEscalationIsRejectedWhereNothingConsumesIt(t *testing.T) {
-	for _, args := range [][]string{
-		{"--allow-escalation", "version"},
-		{"--allow-escalation", "help"},
-		{"--allow-escalation", "completions", "bash"},
-	} {
-		t.Run(strings.Join(args, " "), func(t *testing.T) {
-			var stdout, stderr bytes.Buffer
-			launched := false
-			exitCode := runWithDeps(args, &stdout, &stderr, appDeps{
-				getwd:  func() (string, error) { return t.TempDir(), nil },
-				runTUI: func(context.Context, tui.Options) int { launched = true; return exitSuccess },
-			})
-			if exitCode == exitSuccess || launched {
-				t.Fatalf("exit = %d launched = %v: the flag was discarded instead of rejected", exitCode, launched)
-			}
-			if !strings.Contains(stderr.String(), "--allow-escalation is only supported for the interactive TUI and exec") {
-				t.Fatalf("stderr does not name the flag: %s", stderr.String())
-			}
-		})
-	}
-}
-
-// execAdvertisesEscalateModel dispatches args through the root command with a
-// provider that records the tools advertised on the first request, and reports
-// whether escalate_model was among them.
-func execAdvertisesEscalateModel(t *testing.T, args []string) bool {
-	t.Helper()
-	isolateCLIUserState(t)
-	provider := &toolListingProvider{}
-	var stdout, stderr bytes.Buffer
-	exitCode := runWithDeps(args, &stdout, &stderr, appDeps{
-		getwd: func() (string, error) { return t.TempDir(), nil },
-		resolveConfig: func(string, config.Overrides) (config.ResolvedConfig, error) {
-			return execResolvedConfig(), nil
-		},
-		newProvider: func(config.ProviderProfile) (zeroruntime.Provider, error) {
-			return provider, nil
-		},
-		newSandboxStore: func() (*sandbox.GrantStore, error) {
-			return sandbox.NewGrantStore(sandbox.StoreOptions{FilePath: filepath.Join(t.TempDir(), "sandbox-grants.json")})
-		},
-	})
-	if exitCode != exitSuccess {
-		t.Fatalf("%v: exit = %d, stderr = %s", args, exitCode, stderr.String())
-	}
-	if provider.requests == 0 {
-		t.Fatalf("SETUP INVALID: %v never reached the provider", args)
-	}
-	for _, name := range provider.toolNames {
-		if name == "escalate_model" {
-			return true
-		}
-	}
-	return false
-}
-
-// toolListingProvider answers every request with a one-line text reply and
-// keeps the tool names advertised on the first one.
-type toolListingProvider struct {
-	requests  int
-	toolNames []string
-}
-
-func (provider *toolListingProvider) StreamCompletion(_ context.Context, request zeroruntime.CompletionRequest) (<-chan zeroruntime.StreamEvent, error) {
-	provider.requests++
-	if provider.requests == 1 {
-		for _, tool := range request.Tools {
-			provider.toolNames = append(provider.toolNames, tool.Name)
-		}
-	}
-	ch := make(chan zeroruntime.StreamEvent, 2)
-	ch <- zeroruntime.StreamEvent{Type: zeroruntime.StreamEventText, Content: "hi"}
-	ch <- zeroruntime.StreamEvent{Type: zeroruntime.StreamEventDone}
-	close(ch)
-	return ch, nil
-}

internal/cli/serve_test.go

@@ -168,18 +168,11 @@ func TestBuildServeScopeKeepsLexicalPaths(t *testing.T) {
 	}
 	linkWorkspace := filepath.Join(base, "link-workspace")
 	linkExtra := filepath.Join(base, "link-extra")
-	// SKIPPED, NOT FAILED, WHEN THE PLATFORM WILL NOT MAKE THE LINK. Creating a
-	// symlink on Windows needs SeCreateSymbolicLinkPrivilege, which an ordinary
-	// developer account does not hold, so this reported a failure with nothing
-	// wrong in the code: "A required privilege is not held by the client". CI
-	// runners are elevated, so it only ever showed up locally, where it cost a
-	// round of triage before being ruled environmental. The sibling tests that
-	// need a link already answer this way.
 	if err := os.Symlink(realWorkspace, linkWorkspace); err != nil {
-		t.Skipf("symlink unavailable: %v", err)
+		t.Fatal(err)
 	}
 	if err := os.Symlink(realExtra, linkExtra); err != nil {
-		t.Skipf("symlink unavailable: %v", err)
+		t.Fatal(err)
 	}
 
 	scope, err := buildServeScope(linkWorkspace, []string{linkExtra})

internal/cli/setup.go

@@ -42,7 +42,7 @@ func runSetup(args []string, stdout io.Writer, stderr io.Writer, deps appDeps) i
 		return exitSuccess
 	}
 	if strings.TrimSpace(options.catalogID) == "" {
-		return runInteractiveTUIWithSetup(stderr, deps, "", nil, "", true, false)
+		return runInteractiveTUIWithSetup(stderr, deps, "", nil, "", true)
 	}
 
 	result, err := saveSetupProvider(deps, tui.SetupSelection{

internal/cli/setup_test.go

@@ -367,14 +367,3 @@ func TestVerifySetupProviderDistinguishesMissingFromRejectedKey(t *testing.T) {
 		t.Fatal("a keyless local provider should still be probed")
 	}
 }
-
-func TestSaveSetupProviderRejectsAtomicPlaceholderBeforeConfigAccess(t *testing.T) {
-	for _, model := range []string{"", "local-model", " local-model "} {
-		accessed := false
-		deps := appDeps{userConfigPath: func() (string, error) { accessed = true; return filepath.Join(t.TempDir(), "config.json"), nil }}
-		_, err := saveSetupProvider(deps, tui.SetupSelection{CatalogID: "atomic-chat-local", Model: model}, setupSaveOptions{})
-		if err == nil || !strings.Contains(err.Error(), "--model") || accessed {
-			t.Fatalf("invalid model %q reached config access: accessed=%v err=%v", model, accessed, err)
-		}
-	}
-}

internal/cli/summarizer.go

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

internal/cli/tui_escalation_test.go

@@ -1,126 +0,0 @@
-package cli
-
-import (
-	"bytes"
-	"context"
-	"strings"
-	"testing"
-
-	"github.com/Gitlawb/zero/internal/tui"
-)
-
-// captureTUIOptions runs the root command with the TUI launch intercepted, and
-// returns the options the interactive session would have started with.
-func captureTUIOptions(t *testing.T, args ...string) tui.Options {
-	t.Helper()
-	isolateCLIUserState(t)
-	var captured tui.Options
-	var stdout, stderr bytes.Buffer
-	workspace := t.TempDir()
-	exitCode := runWithDeps(args, &stdout, &stderr, appDeps{
-		getwd: func() (string, error) { return workspace, nil },
-		runTUI: func(_ context.Context, options tui.Options) int {
-			captured = options
-			return exitSuccess
-		},
-	})
-	if exitCode != exitSuccess {
-		t.Fatalf("exitCode = %d stdout=%s stderr=%s", exitCode, stdout.String(), stderr.String())
-	}
-	return captured
-}
-
-func hasEscalateModel(options tui.Options) bool {
-	if options.AgentOptions.Registry == nil {
-		return false
-	}
-	_, registered := options.AgentOptions.Registry.Get("escalate_model")
-	return registered
-}
-
-// ESCALATION IS OFF UNLESS THE OPERATOR ASKS FOR IT.
-//
-// Escalation moves a run onto a different model, changing what it costs and which
-// provider sees the conversation, so the interactive surface answers this the same
-// conservative way `zero exec --allow-escalation` already does.
-func TestInteractiveTUIRegistersEscalateModelOnlyWithTheFlag(t *testing.T) {
-	if hasEscalateModel(captureTUIOptions(t)) {
-		t.Error("escalate_model was registered without --allow-escalation")
-	}
-	if !hasEscalateModel(captureTUIOptions(t, "--allow-escalation")) {
-		t.Error("--allow-escalation did not register escalate_model")
-	}
-}
-
-// THE TOOL AND THE SWITCHERS ARE ONE FEATURE, NOT TWO.
-//
-// This is the failure the whole change exists to avoid. The agent loop performs a
-// switch only when a switcher is wired, so registering escalate_model without
-// wiring one ships a tool the model can call and the loop will silently ignore:
-// the run reports an escalation that never happened. The reverse is merely dead
-// code. Both halves ride on the same flag and this asserts they cannot be
-// separated, whichever half a future change touches.
-func TestInteractiveTUIEscalationToolAndSwitchersAreWiredTogether(t *testing.T) {
-	for _, testCase := range []struct {
-		name string
-		args []string
-		want bool
-	}{
-		{name: "default", args: nil, want: false},
-		{name: "flagged", args: []string{"--allow-escalation"}, want: true},
-	} {
-		t.Run(testCase.name, func(t *testing.T) {
-			options := captureTUIOptions(t, testCase.args...)
-			if got := hasEscalateModel(options); got != testCase.want {
-				t.Fatalf("escalate_model registered = %v, want %v", got, testCase.want)
-			}
-			if options.AllowEscalation != testCase.want {
-				t.Errorf("AllowEscalation = %v, want %v: the tool is registered on one gate and the switchers on another, so they can drift apart",
-					options.AllowEscalation, testCase.want)
-			}
-		})
-	}
-}
-
-// The flag is accepted on either side of --skip-permissions-unsafe, like the
-// other root flags that may appear there.
-func TestInteractiveTUIAcceptsAllowEscalationAroundUnsafe(t *testing.T) {
-	for _, args := range [][]string{
-		{"--allow-escalation", "--skip-permissions-unsafe"},
-		{"--skip-permissions-unsafe", "--allow-escalation"},
-	} {
-		options := captureTUIOptions(t, args...)
-		if !options.AllowEscalation {
-			t.Errorf("%v did not enable escalation", args)
-		}
-		if !hasEscalateModel(options) {
-			t.Errorf("%v did not register escalate_model", args)
-		}
-	}
-}
-
-// An =value form is a loud error rather than a silent enable, so a mistyped
-// --allow-escalation=false cannot turn the feature ON.
-func TestAllowEscalationRejectsAValue(t *testing.T) {
-	var stdout, stderr bytes.Buffer
-	exitCode := runWithDeps([]string{"--allow-escalation=false"}, &stdout, &stderr, appDeps{
-		getwd:  func() (string, error) { return t.TempDir(), nil },
-		runTUI: func(context.Context, tui.Options) int { return exitSuccess },
-	})
-	if exitCode == exitSuccess {
-		t.Fatal("--allow-escalation=false was accepted; a mistyped disable must not silently enable escalation")
-	}
-	if !strings.Contains(stderr.String(), "--allow-escalation takes no value") {
-		t.Errorf("stderr does not explain the flag: %s", stderr.String())
-	}
-}
-
-func TestRootHelpDocumentsAllowEscalation(t *testing.T) {
-	var stdout, stderr bytes.Buffer
-	if exitCode := runWithDeps([]string{"--help"}, &stdout, &stderr, appDeps{}); exitCode != exitSuccess {
-		t.Fatalf("exitCode = %d stderr=%s", exitCode, stderr.String())
-	}
-	if !strings.Contains(stdout.String(), "--allow-escalation") {
-		t.Error("the root help does not mention --allow-escalation, so the flag is undiscoverable")
-	}
-}

internal/cli/user_state_isolation_test.go

@@ -1,139 +0,0 @@
-package cli
-
-import (
-	"os"
-	"path/filepath"
-	"strings"
-	"testing"
-
-	"github.com/Gitlawb/zero/internal/config"
-)
-
-// userStateEnvNames is every per-user base directory the root command can
-// resolve against, across platforms. One throwaway root behind all of them
-// lands the resolution inside it whichever branch it takes.
-var userStateEnvNames = []string{
-	"HOME", "USERPROFILE", "APPDATA", "LOCALAPPDATA",
-	"XDG_CONFIG_HOME", "XDG_DATA_HOME", "XDG_CACHE_HOME", "XDG_STATE_HOME",
-}
-
-// isolateCLIUserState points every user-scoped path the root command touches at
-// throwaway directories, and keeps credential work off the host keyring.
-//
-// A TEMPORARY WORKING DIRECTORY IS NOT ISOLATION. runWithDeps fills the
-// dependencies a test leaves out with the production ones, and the launch paths
-// read user config, open stores, refresh the models.dev cache and, for an
-// interactive run, migrate any inline plaintext API key into the credential
-// store before they ever reach an injected callback. Without this, running these
-// tests on a developer machine rewrites that developer's config.json and moves
-// their key into their keychain, makes a real network call, and reports results
-// that depend on whatever providers, MCP servers and plugins that machine has.
-func isolateCLIUserState(t *testing.T) {
-	t.Helper()
-	root := t.TempDir()
-	for _, name := range userStateEnvNames {
-		t.Setenv(name, root)
-	}
-	// The models.dev overlay cache, and the background refresh that writes it:
-	// a wiring test has no business making a network call or leaving a cache
-	// file behind.
-	t.Setenv("ZERO_MODELS_CACHE_PATH", filepath.Join(root, "modelsdev.json"))
-	t.Setenv("ZERO_DISABLE_MODELS_FETCH", "1")
-	// Credentials resolve keyring-first. This keeps a migrated key in a file
-	// under the fixture root rather than in the developer's OS keychain.
-	t.Setenv("ZERO_CRED_STORAGE", "encrypted-file")
-}
-
-// AND THE ISOLATION IS ITSELF PINNED, ONE HELPER AT A TIME. A seeded config
-// outside the helper fixture roots stands in for a developer's real one: the
-// launch helper must leave it exactly as it found it, inline API key included,
-// must not write a credential file beside it, and must have moved the per-user
-// paths off that root before running anything.
-//
-// EACH HELPER GETS ITS OWN SUBTEST because t.Setenv restores at the end of the
-// test, not when the helper returns: exercising both in one test would let the
-// first helper isolation cover for a second helper that had none.
-func TestCLILaunchHelpersLeaveUserStateAlone(t *testing.T) {
-	for _, testCase := range []struct {
-		name     string
-		exercise func(*testing.T)
-	}{
-		{"captureTUIOptions", func(t *testing.T) { _ = captureTUIOptions(t, "--allow-escalation") }},
-		{"execAdvertisesEscalateModel", func(t *testing.T) {
-			_ = execAdvertisesEscalateModel(t, []string{"--allow-escalation", "exec", "say hi"})
-		}},
-	} {
-		t.Run(testCase.name, func(t *testing.T) {
-			seedRoot, configPath, seeded, before := seedEmulatedUserConfig(t)
-
-			testCase.exercise(t)
-
-			after, err := os.ReadFile(configPath)
-			if err != nil {
-				t.Fatal(err)
-			}
-			if string(after) != string(seeded) {
-				t.Errorf("the seeded user config was rewritten:\n before: %s\n  after: %s", seeded, after)
-			}
-			entries, err := os.ReadDir(filepath.Dir(configPath))
-			if err != nil {
-				t.Fatal(err)
-			}
-			if len(entries) != len(before) {
-				names := []string{}
-				for _, entry := range entries {
-					names = append(names, entry.Name())
-				}
-				t.Errorf("the user config directory gained entries: %v", names)
-			}
-
-			// The checks above catch what this platform happens to write. This
-			// one catches the missing isolation itself, so a startup path that
-			// writes somewhere else, or only sometimes, is covered too.
-			resolved, err := config.DefaultUserConfigPath()
-			if err != nil {
-				t.Fatal(err)
-			}
-			if strings.HasPrefix(resolved, seedRoot) {
-				t.Errorf("user config still resolves inside the seeded root (%s): the helper installed no isolation", resolved)
-			}
-			if os.Getenv("ZERO_DISABLE_MODELS_FETCH") == "" {
-				t.Error("the helper left the background models.dev refresh enabled, so this test can make a network call and write a cache file")
-			}
-			if os.Getenv("ZERO_CRED_STORAGE") == "" {
-				t.Error("the helper left credential storage resolving keyring-first, so a migrated key can reach the host keychain")
-			}
-		})
-	}
-}
-
-// seedEmulatedUserConfig points the per-user base directories at a throwaway
-// root and writes a config carrying an inline plaintext API key there, which is
-// what the startup migration rewrites. It returns that root, the config path,
-// its bytes, and the directory listing to compare against.
-func seedEmulatedUserConfig(t *testing.T) (string, string, []byte, []os.DirEntry) {
-	t.Helper()
-	seedRoot := t.TempDir()
-	for _, name := range userStateEnvNames {
-		t.Setenv(name, seedRoot)
-	}
-	configPath, err := config.DefaultUserConfigPath()
-	if err != nil {
-		t.Fatal(err)
-	}
-	if !strings.HasPrefix(configPath, seedRoot) {
-		t.Fatalf("SETUP INVALID: user config resolved to %q, outside the seeded root %q", configPath, seedRoot)
-	}
-	if err := os.MkdirAll(filepath.Dir(configPath), 0o755); err != nil {
-		t.Fatal(err)
-	}
-	seeded := []byte(`{"providers":[{"name":"anthropic","providerKind":"anthropic","model":"claude-haiku-4.5","apiKey":"sk-seeded-plaintext-key"}]}`)
-	if err := os.WriteFile(configPath, seeded, 0o600); err != nil {
-		t.Fatal(err)
-	}
-	before, err := os.ReadDir(filepath.Dir(configPath))
-	if err != nil {
-		t.Fatal(err)
-	}
-	return seedRoot, configPath, seeded, before
-}

internal/config/concurrent_writer_test.go

@@ -1,396 +0,0 @@
-package config
-
-import (
-	"encoding/json"
-	"errors"
-	"fmt"
-	"io"
-	"os"
-	"os/exec"
-	"path/filepath"
-	"strings"
-	"sync"
-	"testing"
-	"time"
-)
-
-func readTestConfig(t *testing.T, path string) FileConfig {
-	t.Helper()
-	data, err := os.ReadFile(path)
-	if err != nil {
-		t.Fatalf("read config: %v", err)
-	}
-	cfg := FileConfig{}
-	if err := json.Unmarshal(data, &cfg); err != nil {
-		t.Fatalf("invalid config JSON after concurrent writes: %v\n%s", err, data)
-	}
-	return cfg
-}
-
-func seedTestConfig(t *testing.T, path string) {
-	t.Helper()
-	if _, err := UpsertProvider(path, ProviderProfile{Name: "seed", Model: "seed-model"}, true); err != nil {
-		t.Fatalf("seed config: %v", err)
-	}
-}
-
-// TestConcurrentMutationsDoNotLoseUpdates is the issue #832 regression. Each
-// mutator loads the whole document, edits one field, and publishes a complete
-// replacement by rename. Without a lock spanning load-through-publish, two
-// writers that loaded the same revision both write a full document and the
-// second rename silently discards the first one's acknowledged update.
-//
-// Every mutation below touches an INDEPENDENT field, so a correct
-// implementation ends with all of them present. A lost update shows up as a
-// zero value in exactly one of the fields, with valid JSON either way — which
-// is what made the bug silent.
-func TestConcurrentMutationsDoNotLoseUpdates(t *testing.T) {
-	path := filepath.Join(t.TempDir(), "config.json")
-	seedTestConfig(t, path)
-
-	mutations := []struct {
-		name  string
-		apply func() error
-		check func(FileConfig) error
-	}{
-		{
-			name:  "theme",
-			apply: func() error { _, err := SetTheme(path, "dracula"); return err },
-			check: func(cfg FileConfig) error {
-				if cfg.Preferences.Theme != "dracula" {
-					return fmt.Errorf("theme = %q, want dracula", cfg.Preferences.Theme)
-				}
-				return nil
-			},
-		},
-		{
-			name:  "pet",
-			apply: func() error { _, err := SetPet(path, "otter"); return err },
-			check: func(cfg FileConfig) error {
-				if cfg.Preferences.Pet != "otter" {
-					return fmt.Errorf("pet = %q, want otter", cfg.Preferences.Pet)
-				}
-				return nil
-			},
-		},
-		{
-			name:  "recaps",
-			apply: func() error { _, err := SetRecapsEnabled(path, true); return err },
-			check: func(cfg FileConfig) error {
-				if cfg.Preferences.Recaps == nil || !*cfg.Preferences.Recaps {
-					return fmt.Errorf("recaps = %v, want true", cfg.Preferences.Recaps)
-				}
-				return nil
-			},
-		},
-		{
-			name:  "favorites",
-			apply: func() error { _, err := SetFavoriteModels(path, []string{"fav-model"}); return err },
-			check: func(cfg FileConfig) error {
-				if len(cfg.Preferences.FavoriteModels) != 1 || cfg.Preferences.FavoriteModels[0] != "fav-model" {
-					return fmt.Errorf("favorites = %v, want [fav-model]", cfg.Preferences.FavoriteModels)
-				}
-				return nil
-			},
-		},
-		{
-			name: "provider",
-			apply: func() error {
-				_, err := UpsertProvider(path, ProviderProfile{Name: "added", Model: "added-model"}, false)
-				return err
-			},
-			check: func(cfg FileConfig) error {
-				for _, provider := range cfg.Providers {
-					if provider.Name == "added" {
-						return nil
-					}
-				}
-				return fmt.Errorf("provider %q missing from %d providers", "added", len(cfg.Providers))
-			},
-		},
-	}
-
-	// SetPet edits the raw bytes rather than round-tripping the struct, so it is
-	// included deliberately: it must take the same lock as the struct writers or
-	// it would clobber, and be clobbered by, everything else.
-	errs := make([]error, len(mutations))
-	start := make(chan struct{})
-	var wg sync.WaitGroup
-	for index, mutation := range mutations {
-		wg.Add(1)
-		go func() {
-			defer wg.Done()
-			<-start
-			errs[index] = mutation.apply()
-		}()
-	}
-	close(start)
-	wg.Wait()
-
-	for index, err := range errs {
-		if err != nil {
-			t.Fatalf("%s mutation failed: %v", mutations[index].name, err)
-		}
-	}
-	cfg := readTestConfig(t, path)
-	for _, mutation := range mutations {
-		if err := mutation.check(cfg); err != nil {
-			t.Errorf("%s update was lost: %v", mutation.name, err)
-		}
-	}
-	if cfg.ActiveProvider != "seed" {
-		t.Errorf("activeProvider = %q, want the seeded value preserved", cfg.ActiveProvider)
-	}
-}
-
-// TestConcurrentSameFieldMutationsSerialize proves the lock serializes writers
-// that contend on ONE field: every call must succeed and the file must end with
-// exactly one of the written values, never a merged or truncated document.
-func TestConcurrentSameFieldMutationsSerialize(t *testing.T) {
-	path := filepath.Join(t.TempDir(), "config.json")
-	seedTestConfig(t, path)
-
-	const writers = 24
-	errs := make([]error, writers)
-	start := make(chan struct{})
-	var wg sync.WaitGroup
-	for index := range writers {
-		wg.Add(1)
-		go func() {
-			defer wg.Done()
-			<-start
-			_, errs[index] = SetTheme(path, fmt.Sprintf("theme-%02d", index))
-		}()
-	}
-	close(start)
-	wg.Wait()
-
-	for index, err := range errs {
-		if err != nil {
-			t.Fatalf("writer %d failed: %v", index, err)
-		}
-	}
-	cfg := readTestConfig(t, path)
-	if !strings.HasPrefix(cfg.Preferences.Theme, "theme-") {
-		t.Fatalf("theme = %q, want one of the written values", cfg.Preferences.Theme)
-	}
-}
-
-// TestConcurrentProviderUpsertsAllSurvive is the shape the issue describes most
-// directly: N distinct providers added at once. Each add is an independent
-// successful mutation, so all N must be present afterwards.
-func TestConcurrentProviderUpsertsAllSurvive(t *testing.T) {
-	path := filepath.Join(t.TempDir(), "config.json")
-	seedTestConfig(t, path)
-
-	const providers = 16
-	errs := make([]error, providers)
-	start := make(chan struct{})
-	var wg sync.WaitGroup
-	for index := range providers {
-		wg.Add(1)
-		go func() {
-			defer wg.Done()
-			<-start
-			_, errs[index] = UpsertProvider(path, ProviderProfile{
-				Name:  fmt.Sprintf("provider-%02d", index),
-				Model: fmt.Sprintf("model-%02d", index),
-			}, false)
-		}()
-	}
-	close(start)
-	wg.Wait()
-
-	for index, err := range errs {
-		if err != nil {
-			t.Fatalf("upsert %d failed: %v", index, err)
-		}
-	}
-	cfg := readTestConfig(t, path)
-	present := map[string]string{}
-	for _, provider := range cfg.Providers {
-		present[provider.Name] = provider.Model
-	}
-	for index := range providers {
-		name := fmt.Sprintf("provider-%02d", index)
-		want := fmt.Sprintf("model-%02d", index)
-		if got, ok := present[name]; !ok {
-			t.Errorf("provider %s was lost (config holds %d providers)", name, len(cfg.Providers))
-		} else if got != want {
-			t.Errorf("provider %s model = %q, want %q", name, got, want)
-		}
-	}
-}
-
-// TestCrossProcessMutationExcludesAndPreserves is the coordinated two-process
-// test the issue asks for. Goroutines share this process's descriptors, so only
-// a second OS process shows the lock is held by the kernel rather than by
-// in-process state.
-//
-// The child announces itself and then mutates; the parent holds the lock across
-// that window and asserts the child's write CANNOT land, then does its own
-// mutation and releases. Both updates must survive. The exclusion window is
-// what makes this deterministic in the passing direction: with the lock held,
-// the child is blocked in its retry loop and the theme provably stays unset.
-func TestCrossProcessMutationExcludesAndPreserves(t *testing.T) {
-	path := filepath.Join(t.TempDir(), "config.json")
-	seedTestConfig(t, path)
-
-	unlock, err := lockConfigFile(path)
-	if err != nil {
-		t.Fatalf("acquire lock: %v", err)
-	}
-	released := false
-	release := func() {
-		if !released {
-			released = true
-			unlock()
-		}
-	}
-	defer release()
-
-	child := exec.Command(os.Args[0], "-test.run=^TestConfigConcurrentHelperProcess$")
-	child.Env = append(os.Environ(),
-		"ZERO_CONFIG_CONCURRENT_HELPER=1",
-		"ZERO_CONFIG_CONCURRENT_PATH="+path,
-	)
-	stdout, err := child.StdoutPipe()
-	if err != nil {
-		t.Fatalf("stdout pipe: %v", err)
-	}
-	if err := child.Start(); err != nil {
-		t.Fatalf("start helper: %v", err)
-	}
-	defer func() {
-		if child.ProcessState == nil {
-			_ = child.Process.Kill()
-			_ = child.Wait()
-		}
-	}()
-
-	ready := make([]byte, len("ready\n"))
-	if _, err := io.ReadFull(stdout, ready); err != nil {
-		t.Fatalf("helper never signalled ready: %v", err)
-	}
-
-	// The child is now live and contending for a lock this process holds. Its
-	// write must not appear while we hold it.
-	for range 20 {
-		if theme := readTestConfig(t, path).Preferences.Theme; theme != "" {
-			t.Fatalf("child wrote %q while the lock was held elsewhere; mutations are not excluded", theme)
-		}
-		time.Sleep(5 * time.Millisecond)
-	}
-
-	if _, err := upsertProviderLocked(path, ProviderProfile{Name: "parent", Model: "parent-model"}, false); err != nil {
-		t.Fatalf("parent mutation: %v", err)
-	}
-	release()
-
-	if err := child.Wait(); err != nil {
-		t.Fatalf("helper process failed: %v", err)
-	}
-
-	cfg := readTestConfig(t, path)
-	if cfg.Preferences.Theme != "child-theme" {
-		t.Errorf("child update was lost: theme = %q, want child-theme", cfg.Preferences.Theme)
-	}
-	found := false
-	for _, provider := range cfg.Providers {
-		if provider.Name == "parent" {
-			found = true
-		}
-	}
-	if !found {
-		t.Errorf("parent update was lost: provider %q missing from %d providers", "parent", len(cfg.Providers))
-	}
-}
-
-// TestConfigConcurrentHelperProcess is the child half of the cross-process
-// test. It is skipped unless the parent selected it through the environment.
-func TestConfigConcurrentHelperProcess(t *testing.T) {
-	if os.Getenv("ZERO_CONFIG_CONCURRENT_HELPER") == "" {
-		t.Skip("helper process for TestCrossProcessMutationExcludesAndPreserves")
-	}
-	path := os.Getenv("ZERO_CONFIG_CONCURRENT_PATH")
-	if path == "" {
-		t.Fatal("ZERO_CONFIG_CONCURRENT_PATH is required")
-	}
-	// Announce BEFORE contending, so the parent's exclusion window starts with
-	// this process already running rather than still being forked.
-	fmt.Println("ready")
-	if _, err := SetTheme(path, "child-theme"); err != nil {
-		t.Fatalf("child mutation: %v", err)
-	}
-}
-
-// TestMutationReportsUnlockFailure pins the AGENTS.md rule that a mutator must
-// never report success when unlock failed. A failed release can leave the lock
-// held for the rest of the process, so returning (cfg, nil) after one would
-// claim a state the next mutation cannot reproduce.
-//
-// lockutil.Release is idempotent and reports nil once released, so a real
-// release failure cannot be provoked through the public API — hence the seam.
-// The mutation itself must still have been published: the release failure
-// annotates the result, it does not undo the write.
-func TestMutationReportsUnlockFailure(t *testing.T) {
-	path := filepath.Join(t.TempDir(), "config.json")
-	seedTestConfig(t, path)
-
-	releaseErr := errors.New("release exploded")
-	original := lockConfigFileFn
-	t.Cleanup(func() { lockConfigFileFn = original })
-	lockConfigFileFn = func(p string) (func() error, error) {
-		unlock, err := original(p)
-		if err != nil {
-			return nil, err
-		}
-		return func() error {
-			_ = unlock()
-			return releaseErr
-		}, nil
-	}
-
-	cfg, err := SetTheme(path, "dracula")
-	if !errors.Is(err, releaseErr) {
-		t.Fatalf("SetTheme err = %v, want it to carry the release failure", err)
-	}
-	if cfg.Preferences.Theme != "dracula" {
-		t.Errorf("returned config lost the mutation: theme = %q", cfg.Preferences.Theme)
-	}
-	if got := readTestConfig(t, path).Preferences.Theme; got != "dracula" {
-		t.Errorf("mutation was not published despite only the release failing: theme = %q", got)
-	}
-}
-
-// TestMutationErrorSurvivesUnlockFailure proves the two errors are joined
-// rather than chosen between: a release failure must not mask the mutation
-// error that actually explains what went wrong.
-func TestMutationErrorSurvivesUnlockFailure(t *testing.T) {
-	path := filepath.Join(t.TempDir(), "config.json")
-	seedTestConfig(t, path)
-
-	releaseErr := errors.New("release exploded")
-	original := lockConfigFileFn
-	t.Cleanup(func() { lockConfigFileFn = original })
-	lockConfigFileFn = func(p string) (func() error, error) {
-		unlock, err := original(p)
-		if err != nil {
-			return nil, err
-		}
-		return func() error {
-			_ = unlock()
-			return releaseErr
-		}, nil
-	}
-
-	// An unknown provider is the mutation error; the release failure is joined
-	// onto it, and neither one disappears.
-	_, err := SetActiveProvider(path, "definitely-not-configured")
-	if !errors.Is(err, releaseErr) {
-		t.Fatalf("err = %v, want it to carry the release failure", err)
-	}
-	if !strings.Contains(err.Error(), "definitely-not-configured") {
-		t.Fatalf("err = %v, want it to still name the missing provider", err)
-	}
-}

internal/config/credentials.go

@@ -2,7 +2,6 @@ package config
 
 import (
 	"encoding/json"
-	"errors"
 	"fmt"
 	"os"
 	"path/filepath"
@@ -81,21 +80,12 @@ func ForgetProviderKey(provider string) (bool, error) {
 // config at path, so credential checks no longer claim a stored key after one is
 // removed. No-op when path/provider is empty, the config is absent, or the marker
 // is already unset.
-func ClearProviderKeyStored(path, provider string) (cleared bool, err error) {
+func ClearProviderKeyStored(path, provider string) (bool, error) {
 	path = strings.TrimSpace(path)
 	provider = strings.TrimSpace(provider)
 	if path == "" || provider == "" {
 		return false, nil
 	}
-	unlock, err := lockConfigFileFn(path)
-	if err != nil {
-		return false, err
-	}
-	// Joined, not chosen between: a release failure annotates the result
-	// instead of masking the mutation error that actually explains what went
-	// wrong. Reporting success after a failed unlock would claim a state the
-	// next mutation cannot reproduce.
-	defer func() { err = errors.Join(err, unlock()) }()
 	data, err := os.ReadFile(path)
 	if err != nil {
 		if os.IsNotExist(err) {
@@ -126,22 +116,11 @@ func ClearProviderKeyStored(path, provider string) (cleared bool, err error) {
 // leaves the plaintext key in place and never strands a credential. Returns how
 // many keys were migrated; a no-op (0, nil) when path is empty/absent or nothing
 // needs migrating. Safe to run on every startup (idempotent).
-func MigratePlaintextProviderKeys(path string, store APIKeySetter) (count int, err error) {
+func MigratePlaintextProviderKeys(path string, store APIKeySetter) (int, error) {
 	path = strings.TrimSpace(path)
 	if path == "" || store == nil {
 		return 0, nil
 	}
-	// This runs on every startup, so it is the most likely writer to be racing
-	// an interactive mutation in another Zero process.
-	unlock, err := lockConfigFileFn(path)
-	if err != nil {
-		return 0, err
-	}
-	// Joined, not chosen between: a release failure annotates the result
-	// instead of masking the mutation error that actually explains what went
-	// wrong. Reporting success after a failed unlock would claim a state the
-	// next mutation cannot reproduce.
-	defer func() { err = errors.Join(err, unlock()) }()
 	data, err := os.ReadFile(path)
 	if err != nil {
 		if os.IsNotExist(err) {

internal/config/credentials_test.go

@@ -257,21 +257,6 @@ func TestProviderProfileMissingCredentialEnv(t *testing.T) {
 			profile: ProviderProfile{Name: "local", CatalogID: "ollama"},
 			want:    false,
 		},
-		{
-			// A profile saved against the hosted atomic-chat preset keeps its
-			// remote base URL and key, so it must still be reported as missing a
-			// credential. The keyless local runtime is a separate catalog ID
-			// (atomic-chat-local) precisely so this identity is never repurposed.
-			name:    "hosted atomic-chat profile still requires its key",
-			profile: ProviderProfile{Name: "atomic-chat", CatalogID: "atomic-chat", BaseURL: "https://api.atomic.chat/v1"},
-			wantEnv: "ATOMIC_CHAT_API_KEY",
-			want:    true,
-		},
-		{
-			name:    "local atomic chat runtime needs no credential",
-			profile: ProviderProfile{Name: "atomic-local", CatalogID: "atomic-chat-local"},
-			want:    false,
-		},
 		{
 			name:    "credential resolved via inline key",
 			profile: ProviderProfile{Name: "openai", ProviderKind: ProviderKindOpenAI, APIKey: "sk-test"},

internal/config/export_test.go

@@ -3,7 +3,6 @@ package config
 
 import (
 	"encoding/json"
-	"errors"
 	"fmt"
 	"os"
 	"strings"
@@ -42,7 +41,7 @@ func ValidateFile(path string) (FileConfig, []Issue) {
 // SetProviderDescription sets a provider's description VERBATIM — including to
 // empty. The generic UpsertProvider merge treats empty fields as "leave
 // unchanged", so clearing a description needs this dedicated setter.
-func SetProviderDescription(path string, name string, description string) (result FileConfig, err error) {
+func SetProviderDescription(path string, name string, description string) (FileConfig, error) {
 	path = strings.TrimSpace(path)
 	if path == "" {
 		return FileConfig{}, fmt.Errorf("config path is required")
@@ -51,17 +50,6 @@ func SetProviderDescription(path string, name string, description string) (resul
 	if name == "" {
 		return FileConfig{}, fmt.Errorf("provider name is required")
 	}
-	// Locks like the production mutators so this seam can stand in for one in a
-	// concurrency test rather than being the one unsynchronized writer.
-	unlock, err := lockConfigFileFn(path)
-	if err != nil {
-		return FileConfig{}, err
-	}
-	// Joined, not chosen between: a release failure annotates the result
-	// instead of masking the mutation error that actually explains what went
-	// wrong. Reporting success after a failed unlock would claim a state the
-	// next mutation cannot reproduce.
-	defer func() { err = errors.Join(err, unlock()) }()
 
 	data, err := os.ReadFile(path)
 	if err != nil {

internal/config/lock.go

@@ -1,94 +0,0 @@
-package config
-
-import (
-	"errors"
-	"fmt"
-	"os"
-	"path/filepath"
-	"time"
-
-	"github.com/Gitlawb/zero/internal/lockutil"
-)
-
-// ErrLockUnavailable reports that the config lock was still held by another
-// process (or goroutine) when configLockTimeout expired. A caller that would
-// otherwise make a SECOND config write after a failed one branches on this: the
-// lock has not been released, so the second attempt can only spend another full
-// timeout to fail the same way, turning one keystroke into two stalls.
-var ErrLockUnavailable = errors.New("config lock unavailable")
-
-const (
-	configLockTimeout    = 10 * time.Second
-	configLockRetryDelay = 20 * time.Millisecond
-)
-
-// lockConfigFile serializes a config read-modify-write across processes.
-//
-// Every mutator in this package loads the whole document, edits independent
-// fields, and publishes a complete replacement by rename. The rename is atomic,
-// so a reader never sees partial JSON — but two processes that both loaded the
-// same revision each write a full document, and the second rename silently
-// discards the first one's acknowledged update (issue #832). Startup work makes
-// this easy to hit: MigratePlaintextProviderKeys rewrites the config on every
-// launch, so it collides with any concurrent mutation from another Zero.
-//
-// The lock must therefore span load, mutation, validation AND publication:
-// holding it only around the write would still let both processes read the same
-// stale revision first. Callers acquire before their first read, which is what
-// makes the re-read inside the lock authoritative.
-//
-// The lock file is a sibling of the config, never the config itself. The kernel
-// holds an advisory lock against an inode, and publishing the config by rename
-// installs a NEW inode — locking the config directly would leave each process
-// holding a different one. lockutil keeps the sibling's path stable for the
-// same reason, and never removes it.
-//
-// The returned release function reports its own failure rather than swallowing
-// it: a failed Release can leave the lock held for the rest of the process, so
-// a mutator that returned success after it would be reporting a state the next
-// mutation cannot reproduce. Callers join it into their result (AGENTS.md:
-// "never report success when cleanup or unlock failed").
-//
-// This also serializes goroutines within one process: each acquisition opens
-// its own file description, so a second in-process attempt contends exactly as
-// another process would. The lock is NOT reentrant, so an exported mutator that
-// needs another mutator's work calls the unexported *Locked form instead of
-// re-entering through the public function.
-// LockFile exposes lockConfigFile to packages that edit the SAME user config
-// document without going through this package's mutators — internal/cli's MCP
-// editor reads, edits and republishes it with the identical temp-file+rename
-// shape. A writer that skipped this lock would reintroduce the lost update for
-// every field, so the lock has to be one authority across packages rather than
-// a private detail of this one.
-func LockFile(path string) (func() error, error) {
-	return lockConfigFileFn(path)
-}
-
-// lockConfigFileFn is the seam the mutators call. Release failures cannot be
-// provoked through the public API — lockutil.Release is idempotent and reports
-// nil once released — so substituting this is the only way to assert that a
-// failed unlock actually reaches the caller instead of being swallowed.
-var lockConfigFileFn = lockConfigFile
-
-func lockConfigFile(path string) (func() error, error) {
-	lockPath := path + ".lock"
-	if dir := filepath.Dir(lockPath); dir != "." && dir != "" {
-		if err := os.MkdirAll(dir, 0o700); err != nil {
-			return nil, fmt.Errorf("create config directory %s: %w", dir, err)
-		}
-	}
-	deadline := time.Now().Add(configLockTimeout)
-	for {
-		lock, err := lockutil.TryAcquireFileLock(lockPath)
-		if err == nil {
-			return lock.Release, nil
-		}
-		if !errors.Is(err, lockutil.ErrLockHeld) {
-			return nil, fmt.Errorf("config: acquire config lock: %w", err)
-		}
-		if !time.Now().Before(deadline) {
-			return nil, fmt.Errorf("config: timed out acquiring config lock for %s: %w", path, ErrLockUnavailable)
-		}
-		time.Sleep(configLockRetryDelay)
-	}
-}

internal/config/types.go

@@ -3,7 +3,6 @@ package config
 import (
 	"encoding/json"
 	"fmt"
-	"reflect"
 	"strings"
 )
 
@@ -120,12 +119,6 @@ type PreferencesConfig struct {
 	// the user turned idle recaps off. A *bool is its own tri-state, so no
 	// custom unmarshal is needed (unlike ToolsConfig.DeferThreshold's int).
 	Recaps *bool `json:"recaps,omitempty"`
-	// CompactionModel routes compaction summarization calls to this model
-	// instead of the session's main model (summaries at main-model prices are
-	// the most expensive recurring event in long runs). Empty = automatic: a
-	// curated cheap model on official endpoints, the main model elsewhere.
-	// "main" forces the main model. ZERO_COMPACTION_MODEL overrides.
-	CompactionModel string `json:"compactionModel,omitempty"`
 }
 
 // RecentModelEntry is one provider-qualified model selection recorded in
@@ -364,9 +357,6 @@ type FileConfig struct {
 	LocalControl        LocalControlConfig `json:"localControl,omitempty"`
 	STT                 STTConfig          `json:"stt,omitempty"`
 	CrossSessionInbound string             `json:"crossSessionInbound,omitempty"`
-	// Extra preserves top-level fields written by newer Zero versions or
-	// extensions so a read-modify-write through this version is non-destructive.
-	Extra map[string]json.RawMessage `json:"-"`
 }
 
 func (cfg FileConfig) MarshalJSON() ([]byte, error) {
@@ -404,32 +394,7 @@ func (cfg FileConfig) MarshalJSON() ([]byte, error) {
 	if !cfg.STT.Empty() {
 		raw.STT = &cfg.STT
 	}
-	known, err := json.Marshal(raw)
-	if err != nil || len(cfg.Extra) == 0 {
-		return known, err
-	}
-	var merged map[string]json.RawMessage
-	if err := json.Unmarshal(known, &merged); err != nil {
-		return nil, err
-	}
-	for key, value := range cfg.Extra {
-		if !fileConfigKnownJSONKey(key) {
-			merged[key] = value
-		}
-	}
-	return json.Marshal(merged)
-}
-
-func fileConfigKnownJSONKey(key string) bool {
-	if strings.EqualFold(key, "mcpServers") || strings.EqualFold(key, "mcp_servers") {
-		return true
-	}
-	for _, field := range knownJSONFields(reflect.TypeOf(FileConfig{})) {
-		if strings.EqualFold(key, field.canonical) {
-			return true
-		}
-	}
-	return false
+	return json.Marshal(raw)
 }
 
 type ResolveOptions struct {
@@ -545,18 +510,6 @@ func (cfg *FileConfig) UnmarshalJSON(data []byte) error {
 	if err := json.Unmarshal(data, &raw); err != nil {
 		return err
 	}
-	var extra map[string]json.RawMessage
-	if err := json.Unmarshal(data, &extra); err != nil {
-		return err
-	}
-	for key := range extra {
-		if fileConfigKnownJSONKey(key) {
-			delete(extra, key)
-		}
-	}
-	if len(extra) == 0 {
-		extra = nil
-	}
 	cfg.ActiveProvider = raw.ActiveProvider
 	cfg.Providers = raw.Providers
 	// A negative maxTurns is unambiguously invalid; without this it would be
@@ -578,7 +531,6 @@ func (cfg *FileConfig) UnmarshalJSON(data []byte) error {
 	cfg.LocalControl = raw.LocalControl
 	cfg.STT = raw.STT
 	cfg.CrossSessionInbound = raw.CrossSessionInbound
-	cfg.Extra = extra
 	if cfg.MCP.Servers == nil && (len(raw.MCPServers) > 0 || len(raw.MCPServersSnake) > 0) {
 		cfg.MCP.Servers = map[string]MCPServerConfig{}
 	}

internal/config/types_test.go

@@ -43,58 +43,3 @@ func TestToolsConfigPresentOnOverridesAndResolved(t *testing.T) {
 		t.Fatalf("ResolvedConfig.Tools.DeferThreshold = %d, want 4", resolved.Tools.DeferThreshold)
 	}
 }
-
-func TestFileConfigExtraCannotOverrideKnownFields(t *testing.T) {
-	cfg := FileConfig{
-		MaxTurns: 3,
-		Extra: map[string]json.RawMessage{
-			"maxTurns": json.RawMessage(`99`),
-			"MaxTurns": json.RawMessage(`100`),
-			"future":   json.RawMessage(`{"enabled":true}`),
-		},
-	}
-	data, err := json.Marshal(cfg)
-	if err != nil {
-		t.Fatal(err)
-	}
-	var persisted map[string]json.RawMessage
-	if err := json.Unmarshal(data, &persisted); err != nil {
-		t.Fatal(err)
-	}
-	if got := string(persisted["maxTurns"]); got != "3" {
-		t.Fatalf("maxTurns = %s, want 3", got)
-	}
-	if _, exists := persisted["MaxTurns"]; exists {
-		t.Fatalf("case-variant extra overrode a known field: %s", data)
-	}
-	if got := string(persisted["future"]); got != `{"enabled":true}` {
-		t.Fatalf("future = %s, want preserved object", got)
-	}
-}
-
-func TestFileConfigUnicodeFoldedKnownFieldRoundTrip(t *testing.T) {
-	const data = `{"mcpſervers":{"docs":{"url":"https://example.com/mcp"}}}`
-
-	var cfg FileConfig
-	if err := json.Unmarshal([]byte(data), &cfg); err != nil {
-		t.Fatal(err)
-	}
-	if _, exists := cfg.MCP.Servers["docs"]; !exists {
-		t.Fatalf("MCP.Servers = %#v, want docs server", cfg.MCP.Servers)
-	}
-	if cfg.Extra != nil {
-		t.Fatalf("Extra = %#v, want Unicode-folded known field excluded", cfg.Extra)
-	}
-
-	encoded, err := json.Marshal(cfg)
-	if err != nil {
-		t.Fatal(err)
-	}
-	var roundTripped FileConfig
-	if err := json.Unmarshal(encoded, &roundTripped); err != nil {
-		t.Fatal(err)
-	}
-	if _, exists := roundTripped.MCP.Servers["docs"]; !exists {
-		t.Fatalf("round-tripped MCP.Servers = %#v, want docs server", roundTripped.MCP.Servers)
-	}
-}

internal/config/unknownfields.go

@@ -131,7 +131,7 @@ type knownField struct {
 }
 
 func derefType(t reflect.Type) reflect.Type {
-	for t != nil && t.Kind() == reflect.Pointer {
+	for t != nil && t.Kind() == reflect.Ptr {
 		t = t.Elem()
 	}
 	return t

internal/config/writer.go

@@ -2,7 +2,6 @@ package config
 
 import (
 	"encoding/json"
-	"errors"
 	"fmt"
 	"os"
 	"path/filepath"
@@ -12,28 +11,11 @@ import (
 	"github.com/Gitlawb/zero/internal/providercatalog"
 )
 
-func UpsertProvider(path string, profile ProviderProfile, setActive bool) (result FileConfig, err error) {
+func UpsertProvider(path string, profile ProviderProfile, setActive bool) (FileConfig, error) {
 	path = strings.TrimSpace(path)
 	if path == "" {
 		return FileConfig{}, fmt.Errorf("config path is required")
 	}
-	unlock, err := lockConfigFileFn(path)
-	if err != nil {
-		return FileConfig{}, err
-	}
-	// Joined, not chosen between: a release failure annotates the result
-	// instead of masking the mutation error that actually explains what went
-	// wrong. Reporting success after a failed unlock would claim a state the
-	// next mutation cannot reproduce.
-	defer func() { err = errors.Join(err, unlock()) }()
-	return upsertProviderLocked(path, profile, setActive)
-}
-
-// upsertProviderLocked is UpsertProvider's body for a caller that already holds
-// the config lock. EnsureCatalogProvider reads the document and then upserts
-// into it, and the lock is not reentrant, so it must reach the work this way
-// rather than through the exported function.
-func upsertProviderLocked(path string, profile ProviderProfile, setActive bool) (FileConfig, error) {
 	profile.Name = strings.TrimSpace(profile.Name)
 	if profile.Name == "" {
 		return FileConfig{}, fmt.Errorf("provider name is required")
@@ -90,7 +72,7 @@ type EnsuredProvider struct {
 // Name or CatalogID already matches is left completely untouched (its name,
 // credentials, and model are the user's), and a created profile is NOT marked
 // active unless no provider was active at all.
-func EnsureCatalogProvider(path string, catalogID string) (result EnsuredProvider, err error) {
+func EnsureCatalogProvider(path string, catalogID string) (EnsuredProvider, error) {
 	path = strings.TrimSpace(path)
 	if path == "" {
 		return EnsuredProvider{}, fmt.Errorf("config path is required")
@@ -99,18 +81,6 @@ func EnsureCatalogProvider(path string, catalogID string) (result EnsuredProvide
 	if err != nil {
 		return EnsuredProvider{}, err
 	}
-	// One lock spans the existence scan AND the upsert: releasing between them
-	// would let another process create the same catalog profile in the window,
-	// and the second writer would clobber the first.
-	unlock, err := lockConfigFileFn(path)
-	if err != nil {
-		return EnsuredProvider{}, err
-	}
-	// Joined, not chosen between: a release failure annotates the result
-	// instead of masking the mutation error that actually explains what went
-	// wrong. Reporting success after a failed unlock would claim a state the
-	// next mutation cannot reproduce.
-	defer func() { err = errors.Join(err, unlock()) }()
 
 	cfg := FileConfig{}
 	if data, err := os.ReadFile(path); err == nil {
@@ -134,7 +104,7 @@ func EnsureCatalogProvider(path string, catalogID string) (result EnsuredProvide
 		BaseURL:      descriptor.DefaultBaseURL,
 		Model:        descriptor.DefaultModel,
 	}
-	written, err := upsertProviderLocked(path, profile, false)
+	written, err := UpsertProvider(path, profile, false)
 	if err != nil {
 		return EnsuredProvider{}, err
 	}
@@ -145,20 +115,11 @@ func EnsureCatalogProvider(path string, catalogID string) (result EnsuredProvide
 // credential store. It also clears inline/env key fields so the stored key is the
 // runtime credential; an old apiKeyEnv value must not keep overriding a freshly
 // captured key from `zero auth openrouter` or provider setup.
-func MarkProviderAPIKeyStored(path string, provider string) (err error) {
+func MarkProviderAPIKeyStored(path string, provider string) error {
 	path = strings.TrimSpace(path)
 	if path == "" {
 		return fmt.Errorf("config path is required")
 	}
-	unlock, err := lockConfigFileFn(path)
-	if err != nil {
-		return err
-	}
-	// Joined, not chosen between: a release failure annotates the result
-	// instead of masking the mutation error that actually explains what went
-	// wrong. Reporting success after a failed unlock would claim a state the
-	// next mutation cannot reproduce.
-	defer func() { err = errors.Join(err, unlock()) }()
 	provider = strings.TrimSpace(provider)
 	if provider == "" {
 		return fmt.Errorf("provider name is required")
@@ -183,20 +144,11 @@ func MarkProviderAPIKeyStored(path string, provider string) (err error) {
 	return fmt.Errorf("provider %q not found", provider)
 }
 
-func SetActiveProvider(path string, name string) (result FileConfig, err error) {
+func SetActiveProvider(path string, name string) (FileConfig, error) {
 	path = strings.TrimSpace(path)
 	if path == "" {
 		return FileConfig{}, fmt.Errorf("config path is required")
 	}
-	unlock, err := lockConfigFileFn(path)
-	if err != nil {
-		return FileConfig{}, err
-	}
-	// Joined, not chosen between: a release failure annotates the result
-	// instead of masking the mutation error that actually explains what went
-	// wrong. Reporting success after a failed unlock would claim a state the
-	// next mutation cannot reproduce.
-	defer func() { err = errors.Join(err, unlock()) }()
 	name = strings.TrimSpace(name)
 	if name == "" {
 		return FileConfig{}, fmt.Errorf("provider name is required")
@@ -225,51 +177,6 @@ func SetActiveProvider(path string, name string) (result FileConfig, err error)
 	return FileConfig{}, fmt.Errorf("provider %q not found", name)
 }
 
-// SetActiveProviderModel persists a provider selection as one lock-held
-// read-modify-write. The active provider and that provider's model are one UI
-// choice; publishing them separately can leave a partially applied selection
-// if another writer wins the lock between calls.
-func SetActiveProviderModel(path string, name string, model string) (result FileConfig, err error) {
-	path = strings.TrimSpace(path)
-	if path == "" {
-		return FileConfig{}, fmt.Errorf("config path is required")
-	}
-	name = strings.TrimSpace(name)
-	if name == "" {
-		return FileConfig{}, fmt.Errorf("provider name is required")
-	}
-	model = strings.TrimSpace(model)
-	if model == "" {
-		return FileConfig{}, fmt.Errorf("model is required")
-	}
-
-	unlock, err := lockConfigFileFn(path)
-	if err != nil {
-		return FileConfig{}, err
-	}
-	defer func() { err = errors.Join(err, unlock()) }()
-
-	data, err := os.ReadFile(path)
-	if err != nil {
-		return FileConfig{}, fmt.Errorf("read config %s: %w", path, err)
-	}
-	cfg := FileConfig{}
-	if err := json.Unmarshal(data, &cfg); err != nil {
-		return FileConfig{}, fmt.Errorf("invalid config JSON %s: %w", path, err)
-	}
-	for index := range cfg.Providers {
-		if strings.EqualFold(strings.TrimSpace(cfg.Providers[index].Name), name) {
-			cfg.ActiveProvider = cfg.Providers[index].Name
-			cfg.Providers[index].Model = model
-			if err := writeConfigFile(path, cfg); err != nil {
-				return FileConfig{}, err
-			}
-			return cfg, nil
-		}
-	}
-	return FileConfig{}, fmt.Errorf("provider %q not found", name)
-}
-
 // ProviderPersisted reports whether a provider profile named name actually has
 // a row in the config file at path. A provider can appear in the resolved/
 // in-memory provider list without ever being written to config.json — e.g.
@@ -303,20 +210,11 @@ func ProviderPersisted(path string, name string) (bool, error) {
 // a profile that no longer exists. The caller owns cleaning up the credential
 // store entry — config stays pure of secret I/O on the read path, and remove
 // keeps that symmetry by only touching config.json.
-func RemoveProvider(path string, name string) (result FileConfig, err error) {
+func RemoveProvider(path string, name string) (FileConfig, error) {
 	path = strings.TrimSpace(path)
 	if path == "" {
 		return FileConfig{}, fmt.Errorf("config path is required")
 	}
-	unlock, err := lockConfigFileFn(path)
-	if err != nil {
-		return FileConfig{}, err
-	}
-	// Joined, not chosen between: a release failure annotates the result
-	// instead of masking the mutation error that actually explains what went
-	// wrong. Reporting success after a failed unlock would claim a state the
-	// next mutation cannot reproduce.
-	defer func() { err = errors.Join(err, unlock()) }()
 	name = strings.TrimSpace(name)
 	if name == "" {
 		return FileConfig{}, fmt.Errorf("provider name is required")
@@ -363,20 +261,11 @@ func RemoveProvider(path string, name string) (result FileConfig, err error) {
 // resolves. OAuth tokens are deliberately not migrated: the runtime's login
 // candidates fall back to the profile's CatalogID, which every OAuth-capable
 // catalog profile carries, so a rename keeps the login reachable.
-func RenameProvider(path string, oldName string, newName string) (result FileConfig, err error) {
+func RenameProvider(path string, oldName string, newName string) (FileConfig, error) {
 	path = strings.TrimSpace(path)
 	if path == "" {
 		return FileConfig{}, fmt.Errorf("config path is required")
 	}
-	unlock, err := lockConfigFileFn(path)
-	if err != nil {
-		return FileConfig{}, err
-	}
-	// Joined, not chosen between: a release failure annotates the result
-	// instead of masking the mutation error that actually explains what went
-	// wrong. Reporting success after a failed unlock would claim a state the
-	// next mutation cannot reproduce.
-	defer func() { err = errors.Join(err, unlock()) }()
 	oldName = strings.TrimSpace(oldName)
 	newName = strings.TrimSpace(newName)
 	if oldName == "" || newName == "" {
@@ -458,20 +347,11 @@ type ProviderEdit struct {
 // and, unlike UpsertProvider's exact-name merge, the case-insensitive match
 // here makes a case-only rename (groq -> Groq) an in-place update instead of
 // an appended duplicate profile.
-func EditProvider(path string, edit ProviderEdit) (result FileConfig, err error) {
+func EditProvider(path string, edit ProviderEdit) (FileConfig, error) {
 	path = strings.TrimSpace(path)
 	if path == "" {
 		return FileConfig{}, fmt.Errorf("config path is required")
 	}
-	unlock, err := lockConfigFileFn(path)
-	if err != nil {
-		return FileConfig{}, err
-	}
-	// Joined, not chosen between: a release failure annotates the result
-	// instead of masking the mutation error that actually explains what went
-	// wrong. Reporting success after a failed unlock would claim a state the
-	// next mutation cannot reproduce.
-	defer func() { err = errors.Join(err, unlock()) }()
 	oldName := strings.TrimSpace(edit.Name)
 	if oldName == "" {
 		return FileConfig{}, fmt.Errorf("provider name is required")
@@ -581,20 +461,11 @@ func migrateStoredProviderKey(configPath string, oldName string, newName string)
 	return nil
 }
 
-func SetProviderModel(path string, name string, model string) (result FileConfig, err error) {
+func SetProviderModel(path string, name string, model string) (FileConfig, error) {
 	path = strings.TrimSpace(path)
 	if path == "" {
 		return FileConfig{}, fmt.Errorf("config path is required")
 	}
-	unlock, err := lockConfigFileFn(path)
-	if err != nil {
-		return FileConfig{}, err
-	}
-	// Joined, not chosen between: a release failure annotates the result
-	// instead of masking the mutation error that actually explains what went
-	// wrong. Reporting success after a failed unlock would claim a state the
-	// next mutation cannot reproduce.
-	defer func() { err = errors.Join(err, unlock()) }()
 	name = strings.TrimSpace(name)
 	if name == "" {
 		return FileConfig{}, fmt.Errorf("provider name is required")
@@ -627,20 +498,11 @@ func SetProviderModel(path string, name string, model string) (result FileConfig
 	return FileConfig{}, fmt.Errorf("provider %q not found", name)
 }
 
-func SetFavoriteModels(path string, models []string) (result FileConfig, err error) {
+func SetFavoriteModels(path string, models []string) (FileConfig, error) {
 	path = strings.TrimSpace(path)
 	if path == "" {
 		return FileConfig{}, fmt.Errorf("config path is required")
 	}
-	unlock, err := lockConfigFileFn(path)
-	if err != nil {
-		return FileConfig{}, err
-	}
-	// Joined, not chosen between: a release failure annotates the result
-	// instead of masking the mutation error that actually explains what went
-	// wrong. Reporting success after a failed unlock would claim a state the
-	// next mutation cannot reproduce.
-	defer func() { err = errors.Join(err, unlock()) }()
 
 	cfg := FileConfig{}
 	if data, err := os.ReadFile(path); err == nil {
@@ -662,20 +524,11 @@ func SetFavoriteModels(path string, models []string) (result FileConfig, err err
 // mirroring SetFavoriteModels (read-modify-atomic-write). Unlike favorites,
 // order is preserved (newest first) rather than sorted, since it reflects
 // switch recency, not an alphabetical preference list.
-func SetRecentModels(path string, entries []RecentModelEntry) (result FileConfig, err error) {
+func SetRecentModels(path string, entries []RecentModelEntry) (FileConfig, error) {
 	path = strings.TrimSpace(path)
 	if path == "" {
 		return FileConfig{}, fmt.Errorf("config path is required")
 	}
-	unlock, err := lockConfigFileFn(path)
-	if err != nil {
-		return FileConfig{}, err
-	}
-	// Joined, not chosen between: a release failure annotates the result
-	// instead of masking the mutation error that actually explains what went
-	// wrong. Reporting success after a failed unlock would claim a state the
-	// next mutation cannot reproduce.
-	defer func() { err = errors.Join(err, unlock()) }()
 
 	cfg := FileConfig{}
 	if data, err := os.ReadFile(path); err == nil {
@@ -695,20 +548,11 @@ func SetRecentModels(path string, entries []RecentModelEntry) (result FileConfig
 
 // SetRecapsEnabled persists the idle recap preference, mirroring
 // SetFavoriteModels (read-modify-atomic-write).
-func SetRecapsEnabled(path string, enabled bool) (result FileConfig, err error) {
+func SetRecapsEnabled(path string, enabled bool) (FileConfig, error) {
 	path = strings.TrimSpace(path)
 	if path == "" {
 		return FileConfig{}, fmt.Errorf("config path is required")
 	}
-	unlock, err := lockConfigFileFn(path)
-	if err != nil {
-		return FileConfig{}, err
-	}
-	// Joined, not chosen between: a release failure annotates the result
-	// instead of masking the mutation error that actually explains what went
-	// wrong. Reporting success after a failed unlock would claim a state the
-	// next mutation cannot reproduce.
-	defer func() { err = errors.Join(err, unlock()) }()
 	cfg := FileConfig{}
 	if data, err := os.ReadFile(path); err == nil {
 		if err := json.Unmarshal(data, &cfg); err != nil {
@@ -727,20 +571,11 @@ func SetRecapsEnabled(path string, enabled bool) (result FileConfig, err error)
 
 // SetTheme persists the TUI theme preference, mirroring SetFavoriteModels
 // (read-modify-atomic-write). A blank theme clears the stored preference.
-func SetTheme(path string, theme string) (result FileConfig, err error) {
+func SetTheme(path string, theme string) (FileConfig, error) {
 	path = strings.TrimSpace(path)
 	if path == "" {
 		return FileConfig{}, fmt.Errorf("config path is required")
 	}
-	unlock, err := lockConfigFileFn(path)
-	if err != nil {
-		return FileConfig{}, err
-	}
-	// Joined, not chosen between: a release failure annotates the result
-	// instead of masking the mutation error that actually explains what went
-	// wrong. Reporting success after a failed unlock would claim a state the
-	// next mutation cannot reproduce.
-	defer func() { err = errors.Join(err, unlock()) }()
 	cfg := FileConfig{}
 	if data, err := os.ReadFile(path); err == nil {
 		if err := json.Unmarshal(data, &cfg); err != nil {
@@ -758,20 +593,11 @@ func SetTheme(path string, theme string) (result FileConfig, err error) {
 
 // SetPet persists only the terminal-pet preference while preserving every
 // unrelated user setting through the config writer's atomic replace path.
-func SetPet(path string, pet string) (result FileConfig, err error) {
+func SetPet(path string, pet string) (FileConfig, error) {
 	path = strings.TrimSpace(path)
 	if path == "" {
 		return FileConfig{}, fmt.Errorf("config path is required")
 	}
-	unlock, err := lockConfigFileFn(path)
-	if err != nil {
-		return FileConfig{}, err
-	}
-	// Joined, not chosen between: a release failure annotates the result
-	// instead of masking the mutation error that actually explains what went
-	// wrong. Reporting success after a failed unlock would claim a state the
-	// next mutation cannot reproduce.
-	defer func() { err = errors.Join(err, unlock()) }()
 	cfg := FileConfig{}
 	data := []byte("{}")
 	if existing, err := os.ReadFile(path); err == nil {
@@ -784,7 +610,7 @@ func SetPet(path string, pet string) (result FileConfig, err error) {
 	}
 	pet = strings.TrimSpace(pet)
 	cfg.Preferences.Pet = pet
-	data, err = setPetPreferenceJSON(data, pet)
+	data, err := setPetPreferenceJSON(data, pet)
 	if err != nil {
 		return FileConfig{}, fmt.Errorf("invalid config JSON %s: %w", path, err)
 	}
@@ -798,20 +624,11 @@ func SetPet(path string, pet string) (result FileConfig, err error) {
 // SetTheme (read-modify-atomic-write). provider must be one of the known STT
 // provider kinds; a local provider stores the model as stt.localModelPath,
 // otherwise as stt.model. A blank model clears the stored value for that slot.
-func SetSTTModel(path string, provider STTProviderKind, model string) (result FileConfig, err error) {
+func SetSTTModel(path string, provider STTProviderKind, model string) (FileConfig, error) {
 	path = strings.TrimSpace(path)
 	if path == "" {
 		return FileConfig{}, fmt.Errorf("config path is required")
 	}
-	unlock, err := lockConfigFileFn(path)
-	if err != nil {
-		return FileConfig{}, err
-	}
-	// Joined, not chosen between: a release failure annotates the result
-	// instead of masking the mutation error that actually explains what went
-	// wrong. Reporting success after a failed unlock would claim a state the
-	// next mutation cannot reproduce.
-	defer func() { err = errors.Join(err, unlock()) }()
 	cfg := FileConfig{}
 	if data, err := os.ReadFile(path); err == nil {
 		if err := json.Unmarshal(data, &cfg); err != nil {
@@ -843,20 +660,11 @@ func SetSTTModel(path string, provider STTProviderKind, model string) (result Fi
 // (read-modify-atomic-write). streaming selects the pipeline matching the
 // downloaded model (a streaming transducer vs a batch model). Called after a
 // download completes.
-func SetSTTLocalEngine(path, binary, serverBinary, modelPath string, streaming bool) (result FileConfig, err error) {
+func SetSTTLocalEngine(path, binary, serverBinary, modelPath string, streaming bool) (FileConfig, error) {
 	path = strings.TrimSpace(path)
 	if path == "" {
 		return FileConfig{}, fmt.Errorf("config path is required")
 	}
-	unlock, err := lockConfigFileFn(path)
-	if err != nil {
-		return FileConfig{}, err
-	}
-	// Joined, not chosen between: a release failure annotates the result
-	// instead of masking the mutation error that actually explains what went
-	// wrong. Reporting success after a failed unlock would claim a state the
-	// next mutation cannot reproduce.
-	defer func() { err = errors.Join(err, unlock()) }()
 	cfg := FileConfig{}
 	if data, err := os.ReadFile(path); err == nil {
 		if err := json.Unmarshal(data, &cfg); err != nil {
@@ -889,20 +697,11 @@ func SetSTTLocalEngine(path, binary, serverBinary, modelPath string, streaming b
 }
 
 // SetSTTProvider persists just the dictation batch provider, mirroring SetTheme.
-func SetSTTProvider(path string, provider STTProviderKind) (result FileConfig, err error) {
+func SetSTTProvider(path string, provider STTProviderKind) (FileConfig, error) {
 	path = strings.TrimSpace(path)
 	if path == "" {
 		return FileConfig{}, fmt.Errorf("config path is required")
 	}
-	unlock, err := lockConfigFileFn(path)
-	if err != nil {
-		return FileConfig{}, err
-	}
-	// Joined, not chosen between: a release failure annotates the result
-	// instead of masking the mutation error that actually explains what went
-	// wrong. Reporting success after a failed unlock would claim a state the
-	// next mutation cannot reproduce.
-	defer func() { err = errors.Join(err, unlock()) }()
 	cfg := FileConfig{}
 	if data, err := os.ReadFile(path); err == nil {
 		if err := json.Unmarshal(data, &cfg); err != nil {

internal/config/writer_test.go

@@ -151,32 +151,6 @@ func TestSetActiveProviderTightensExistingConfigFilePermissions(t *testing.T) {
 	}
 }
 
-func TestSetActiveProviderModelPersistsSelectionTogether(t *testing.T) {
-	path := filepath.Join(t.TempDir(), "zero.json")
-	writeConfigFixture(t, path, FileConfig{
-		ActiveProvider: "openai",
-		Providers: []ProviderProfile{
-			{Name: "openai", ProviderKind: ProviderKindOpenAI, Model: "gpt-4.1"},
-			{Name: "Anthropic", ProviderKind: ProviderKindAnthropic, Model: "old-model"},
-		},
-	}, 0o600)
-
-	cfg, err := SetActiveProviderModel(path, " anthropic ", " claude-sonnet-4.5 ")
-	if err != nil {
-		t.Fatalf("SetActiveProviderModel() error = %v", err)
-	}
-	if cfg.ActiveProvider != "Anthropic" || cfg.Providers[1].Model != "claude-sonnet-4.5" {
-		t.Fatalf("returned selection = active %q model %q", cfg.ActiveProvider, cfg.Providers[1].Model)
-	}
-	persisted := readConfigFixture(t, path)
-	if persisted.ActiveProvider != "Anthropic" || persisted.Providers[1].Model != "claude-sonnet-4.5" {
-		t.Fatalf("persisted selection = active %q model %q", persisted.ActiveProvider, persisted.Providers[1].Model)
-	}
-	if persisted.Providers[0].Model != "gpt-4.1" {
-		t.Fatalf("unrelated provider changed: %#v", persisted.Providers[0])
-	}
-}
-
 func TestSetProviderModelUpdatesConfiguredProvider(t *testing.T) {
 	path := filepath.Join(t.TempDir(), "zero.json")
 	writeConfigFixture(t, path, FileConfig{
@@ -395,37 +369,6 @@ func TestSetThemePersistsUserPreference(t *testing.T) {
 	}
 }
 
-func TestSetThemePreservesUnknownTopLevelFields(t *testing.T) {
-	path := filepath.Join(t.TempDir(), "zero.json")
-	if err := os.WriteFile(path, []byte(`{
-  "preferences": {"theme": "default"},
-  "futureSetting": {"a": 1}
-}`), 0o600); err != nil {
-		t.Fatal(err)
-	}
-
-	if _, err := SetTheme(path, "dracula"); err != nil {
-		t.Fatalf("SetTheme() error = %v", err)
-	}
-	data, err := os.ReadFile(path)
-	if err != nil {
-		t.Fatal(err)
-	}
-	var persisted map[string]json.RawMessage
-	if err := json.Unmarshal(data, &persisted); err != nil {
-		t.Fatal(err)
-	}
-	var futureSetting struct {
-		A int `json:"a"`
-	}
-	if err := json.Unmarshal(persisted["futureSetting"], &futureSetting); err != nil {
-		t.Fatalf("unknown field was not preserved: %v\nconfig: %s", err, data)
-	}
-	if futureSetting.A != 1 {
-		t.Fatalf("futureSetting = %s, want {\"a\":1}", persisted["futureSetting"])
-	}
-}
-
 func TestRecapsPreferenceRoundTrips(t *testing.T) {
 	// Default (unset) is ON.
 	if !(PreferencesConfig{}).RecapsEnabled() {

internal/cron/lock.go

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

internal/cron/mutate_test.go

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

internal/daemon/lock.go

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

internal/daemon/lock_test.go

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

internal/daemon/server_test.go

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

internal/doctor/doctor.go

@@ -142,10 +142,9 @@ func providerConfigCheck(profile config.ProviderProfile) Check {
 		return check("provider.config", "Provider config", StatusFail, "No LLM provider is configured.", map[string]any{"help": "Set a provider in config or environment."})
 	}
 	// Report credential PRESENCE, never the value. Reported under a non-sensitive
-	// key ("authConfigured"): "apiKey" and "credentialConfigured" are themselves
-	// sensitive after camelCase normalization, so check()'s redaction would scrub
-	// the indicator to [REDACTED] — making "set"/"not set" invisible.
-	// HasConfiguredCredential is the shared definition of
+	// key ("credentialConfigured"): the prior "apiKey" key was itself sensitive, so
+	// check()'s redaction scrubbed the indicator to [REDACTED] — making "set"/"not
+	// set" invisible. HasConfiguredCredential is the shared definition of
 	// "key-authed" (inline key, raw auth header, or a key in the encrypted
 	// credential store), matching ProviderSnapshot.APIKeySet — checking only the
 	// inline fields made doctor and `zero providers list` disagree about the
@@ -160,11 +159,11 @@ func providerConfigCheck(profile config.ProviderProfile) Check {
 		credential = "oauth login"
 	}
 	details := map[string]any{
-		"name":           profile.Name,
-		"provider":       profile.ProviderKind,
-		"baseURL":        profile.BaseURL,
-		"model":          profile.Model,
-		"authConfigured": credential,
+		"name":                 profile.Name,
+		"provider":             profile.ProviderKind,
+		"baseURL":              profile.BaseURL,
+		"model":                profile.Model,
+		"credentialConfigured": credential,
 	}
 	// A remote provider with no credential cannot make a request, so doctor must NOT
 	// report it as healthy — otherwise "Overall: pass" gives a false all-clear for the

internal/doctor/doctor_test.go

@@ -388,9 +388,9 @@ func TestProviderConfigCheckCredentialPresence(t *testing.T) {
 	}
 	for _, tc := range cases {
 		t.Run(tc.name, func(t *testing.T) {
-			got := providerConfigCheck(tc.profile).Details["authConfigured"]
+			got := providerConfigCheck(tc.profile).Details["credentialConfigured"]
 			if got != tc.want {
-				t.Fatalf("authConfigured = %v, want %q (matches ProviderSnapshot.APIKeySet trimming)", got, tc.want)
+				t.Fatalf("credentialConfigured = %v, want %q (matches ProviderSnapshot.APIKeySet trimming)", got, tc.want)
 			}
 		})
 	}

internal/execution/process_unix_test.go

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

internal/hooks/lock.go

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

internal/installtest/workflow_permissions_test.go

@@ -1,184 +0,0 @@
-package installtest
-
-import (
-	"os"
-	"path/filepath"
-	"strings"
-	"testing"
-
-	"gopkg.in/yaml.v3"
-)
-
-func TestPullRequestWorkflowsDeclareContentsRead(t *testing.T) {
-	root := filepath.Join(repoRoot(t), ".github", "workflows")
-	entries, err := os.ReadDir(root)
-	if err != nil {
-		t.Fatal(err)
-	}
-	var missing []string
-	for _, e := range entries {
-		if e.IsDir() || !(strings.HasSuffix(e.Name(), ".yml") || strings.HasSuffix(e.Name(), ".yaml")) {
-			continue
-		}
-		rel := filepath.Join(".github", "workflows", e.Name())
-		body := readRepoText(t, rel)
-		doc, err := parseWorkflow(body)
-		if err != nil {
-			t.Errorf("%s: yaml: %v", rel, err)
-			continue
-		}
-		if !workflowOnHasPullRequest(doc.On) {
-			continue
-		}
-		if !workflowPermissionsContentsRead(doc.Permissions) {
-			missing = append(missing, rel)
-		}
-	}
-	if len(missing) > 0 {
-		t.Fatalf("pull_request workflows missing permissions contents: read: %s", strings.Join(missing, ", "))
-	}
-}
-
-func TestWorkflowPermissionParsing(t *testing.T) {
-	tests := []struct {
-		name     string
-		yml      string
-		wantPR   bool
-		wantPerm bool
-	}{
-		{
-			name:     "mapping trigger",
-			yml:      "on:\n  pull_request:\npermissions:\n  contents: read\n",
-			wantPR:   true,
-			wantPerm: true,
-		},
-		{
-			name:     "inline trigger list",
-			yml:      "on: [pull_request]\npermissions:\n  contents: read\n",
-			wantPR:   true,
-			wantPerm: true,
-		},
-		{
-			name:     "commented permissions ignored",
-			yml:      "on:\n  pull_request:\n# permissions:\n#   contents: read\n",
-			wantPR:   true,
-			wantPerm: false,
-		},
-		{
-			name:     "nested script text is not a trigger",
-			yml:      "on:\n  push:\njobs:\n  x:\n    steps:\n      - run: echo pull_request: permissions: contents: read\n",
-			wantPR:   false,
-			wantPerm: false,
-		},
-		{
-			name:     "inline comment does not fake contents read",
-			yml:      "on: [pull_request]\npermissions: write-all # contents: read\n",
-			wantPR:   true,
-			wantPerm: false,
-		},
-		{
-			name:     "empty permissions mapping",
-			yml:      "on: [pull_request]\npermissions: {}\n",
-			wantPR:   true,
-			wantPerm: false,
-		},
-		{
-			name:     "write-all is not contents read",
-			yml:      "on: [pull_request]\npermissions: write-all\n",
-			wantPR:   true,
-			wantPerm: false,
-		},
-		{
-			name:     "quoted on and permissions keys",
-			yml:      "\"on\": [pull_request]\n\"permissions\":\n  \"contents\": read\n",
-			wantPR:   true,
-			wantPerm: true,
-		},
-		{
-			name:     "nested job permissions are not top-level",
-			yml:      "on:\n  pull_request:\njobs:\n  x:\n    permissions:\n      contents: read\n",
-			wantPR:   true,
-			wantPerm: false,
-		},
-	}
-	for _, tc := range tests {
-		t.Run(tc.name, func(t *testing.T) {
-			if got := workflowHasPullRequestTrigger(tc.yml); got != tc.wantPR {
-				t.Fatalf("trigger = %v, want %v", got, tc.wantPR)
-			}
-			if got := workflowHasTopLevelContentsRead(tc.yml); got != tc.wantPerm {
-				t.Fatalf("permissions = %v, want %v", got, tc.wantPerm)
-			}
-		})
-	}
-}
-
-func TestVulncheckWindowsQuotesGobinPath(t *testing.T) {
-	body := readRepoText(t, "Makefile")
-	for _, want := range []string{
-		`mkdir -p "$(CURDIR)/.cache/gobin"`,
-		`GOBIN="$(CURDIR)/.cache/gobin"`,
-		`"$(CURDIR)/.cache/gobin/govulncheck"`,
-	} {
-		if !strings.Contains(body, want) {
-			t.Fatalf("vulncheck-windows missing quoted path %s", want)
-		}
-	}
-}
-
-type workflowFile struct {
-	On          any `yaml:"on"`
-	Permissions any `yaml:"permissions"`
-}
-
-func parseWorkflow(body string) (workflowFile, error) {
-	var doc workflowFile
-	err := yaml.Unmarshal([]byte(body), &doc)
-	return doc, err
-}
-
-func workflowHasPullRequestTrigger(body string) bool {
-	doc, err := parseWorkflow(body)
-	if err != nil {
-		return false
-	}
-	return workflowOnHasPullRequest(doc.On)
-}
-
-func workflowHasTopLevelContentsRead(body string) bool {
-	doc, err := parseWorkflow(body)
-	if err != nil {
-		return false
-	}
-	return workflowPermissionsContentsRead(doc.Permissions)
-}
-
-func workflowOnHasPullRequest(on any) bool {
-	switch v := on.(type) {
-	case string:
-		return v == "pull_request"
-	case []any:
-		for _, item := range v {
-			if workflowOnHasPullRequest(item) {
-				return true
-			}
-		}
-	case map[string]any:
-		_, ok := v["pull_request"]
-		return ok
-	}
-	return false
-}
-
-func workflowPermissionsContentsRead(perm any) bool {
-	m, ok := perm.(map[string]any)
-	if !ok {
-		return false
-	}
-	contents, ok := m["contents"]
-	if !ok {
-		return false
-	}
-	s, ok := contents.(string)
-	return ok && s == "read"
-}

internal/installtxn/installtxn.go

@@ -8,27 +8,10 @@ import (
 	"fmt"
 	"os"
 	"path/filepath"
-	"strings"
 )
 
 const lockFileName = ".zero-install.lock"
 
-// workspacePrefix names the per-transaction workspaces created inside an install
-// root. Dot-prefixed so it is never mistaken for an installed plugin or skill.
-const workspacePrefix = ".zero-install-txn-"
-
-// markerFileName records, inside a workspace, which install the backup beside it
-// belongs to. Without it a workspace left by a killed process holds a tree
-// nothing can attribute, and so nothing can put back.
-const markerFileName = ".zero-install-txn"
-
-// markerMagic is the first line of that marker. Ownership has to be proven
-// rather than inferred from filesystem shape: a user authored skill directory
-// may legitimately be named with the workspace prefix and hold a previous
-// directory, and recovery acting on one would destroy installed content. No
-// ordinary content carries this line by accident.
-const markerMagic = "zero-install-txn v1"
-
 // Lock takes the per-install-root cross-process lock. It blocks until any other
 // installer or remover using dir has completed.
 func Lock(dir string) (func(), error) {
@@ -45,7 +28,7 @@ func StageDir(dir string) (stage string, cleanup func(), err error) {
 	if err := os.MkdirAll(dir, 0o755); err != nil {
 		return "", func() {}, fmt.Errorf("create install dir: %w", err)
 	}
-	workspace, err := os.MkdirTemp(dir, workspacePrefix)
+	workspace, err := os.MkdirTemp(dir, ".zero-install-txn-")
 	if err != nil {
 		return "", func() {}, fmt.Errorf("create install staging dir: %w", err)
 	}
@@ -62,12 +45,6 @@ func CommitDir(target string, staged string, publish func() error) error {
 	backup := filepath.Join(workspace, "previous")
 	hadPrevious := false
 	if _, err := os.Stat(target); err == nil {
-		// Record the target before moving its tree. The two renames below cannot
-		// be made atomic, so a process killed between them leaves the only copy
-		// in the backup, and without this nothing could tell which install it is.
-		if err := os.WriteFile(filepath.Join(workspace, markerFileName), []byte(markerMagic+"\ntarget "+filepath.Base(target)+"\n"), 0o600); err != nil {
-			return fmt.Errorf("record install target: %w", err)
-		}
 		if err := os.Rename(target, backup); err != nil {
 			return fmt.Errorf("retain previous install: %w", err)
 		}
@@ -99,7 +76,7 @@ func CommitDir(target string, staged string, publish func() error) error {
 //
 // The caller must hold the install-root lock returned by Lock.
 func RemoveDir(target string, publish func() error) error {
-	workspace, err := os.MkdirTemp(filepath.Dir(target), workspacePrefix)
+	workspace, err := os.MkdirTemp(filepath.Dir(target), ".zero-install-txn-")
 	if err != nil {
 		return fmt.Errorf("create removal staging dir: %w", err)
 	}
@@ -118,339 +95,15 @@ func RemoveDir(target string, publish func() error) error {
 	return nil
 }
 
-// Phase names which tree in an interrupted workspace the caller's published
-// metadata records.
-type Phase int
-
-const (
-	// PhaseUnknown means the metadata matches neither tree. Recovery refuses to
-	// act and reports the workspace as unresolved.
-	PhaseUnknown Phase = iota
-	// PhaseCommitted means the live target is what the metadata records: the
-	// publish committed, and the backup beside it is superseded.
-	PhaseCommitted
-	// PhasePrePublish means the metadata still records the retained backup: the
-	// tree swap landed but the publish never did.
-	PhasePrePublish
-)
-
-// Reconciler classifies one interrupted workspace for the install named name.
-// target is the live install path, backup the retained tree beside it. An error
-// means the classification could not be made and recovery must not act.
-type Reconciler func(name string, target string, backup string) (Phase, error)
-
-// Recover resolves the workspaces an earlier run was killed inside, which is
-// what a process killed mid-commit leaves: a tree retained in a workspace
-// nothing else reads. How far that commit got cannot be read off the
-// filesystem. CommitDir swaps the trees and only then publishes, so a kill
-// between the two leaves exactly what a kill after both leaves, and a phase bit
-// written after the publish only inverts which side of the write the ambiguity
-// falls on. Only the caller knows what its published metadata records, so
-// reconcile is asked which of the two trees that is, and its answer decides:
-// the live target stands and the backup beside it is retired, or the backup is
-// the truthful tree and goes back over the target. A nil reconciler means the
-// caller publishes no metadata beside the tree, so a live target is the
-// committed one. With nothing at the target there is no choice to make and the
-// backup, the only copy in existence, is put back.
-//
-// The returned error means an attributable transaction was left unresolved,
-// never that there was nothing to do. Malformed, legacy, and unattributable
-// workspaces are skipped without error, since they may be somebody's content or
-// somebody else's transaction, but a workspace we own and could not resolve is
-// reported. Every workspace is processed before returning, so one unresolved
-// transaction does not strand the rest.
-//
-// The caller must hold the install-root lock returned by Lock, and EVERY caller
-// that takes that lock must call this first and abort on its error before it
-// reads the lockfile, inspects the target, installs over it, or reports a
-// successful removal. Recovering only on the install path is worse than not
-// recovering at all: a removal would then report success while the backup it
-// never saw stayed on disk, and the next install would publish it again,
-// reinstating something the user deleted. Recovery is deliberately an explicit
-// call rather than a side effect of Lock, matching how the other staged-swap
-// transactions in this repo invoke their repair pass.
-func Recover(dir string, reconcile Reconciler) error {
-	entries, err := os.ReadDir(dir)
-	if err != nil {
-		// A recovery set that was never enumerated is not an empty one, and the
-		// caller must not go on to install over or report the removal of a tree
-		// that may still be owed a restore.
-		return fmt.Errorf("enumerate install workspaces: %w", err)
-	}
-	var unresolved []error
-	// Gather first, act second. A pass that acts as it walks cannot see that two
-	// workspaces claim one install, and acting on both in turn publishes one over
-	// the other and deletes the rest.
-	type claim struct {
-		workspace string
-		name      string
-		target    string
-		backup    string
-	}
-	var claims []claim
-	claimants := map[string]int{}
-	for _, entry := range entries {
-		if !entry.IsDir() || !strings.HasPrefix(entry.Name(), workspacePrefix) {
-			continue
-		}
-		workspace := filepath.Join(dir, entry.Name())
-		recorded, ok, err := markerTarget(workspace)
-		if err != nil {
-			// A marker we could not read is not a marker that is absent. Skipping
-			// silently would tell the caller there was nothing to do while the only
-			// copy of an install stays in the workspace.
-			unresolved = append(unresolved, fmt.Errorf("read the transaction marker in %s: %w", workspace, err))
-			continue
-		}
-		if !ok {
-			continue
-		}
-		name, target, ok := recoverableTarget(dir, recorded)
-		if !ok {
-			continue
-		}
-		backup := filepath.Join(workspace, "previous")
-		info, err := os.Lstat(backup)
-		if err != nil {
-			if errors.Is(err, os.ErrNotExist) {
-				// Mid-transaction: the trees never moved, so there is nothing to
-				// put back and the workspace belongs to whoever made it.
-				continue
-			}
-			unresolved = append(unresolved, fmt.Errorf("inspect the retained install in %s: %w", workspace, err))
-			continue
-		}
-		if !info.IsDir() {
-			// Only a directory is something this package set aside. Renaming a
-			// symlink into the install root publishes whatever it points at, from
-			// anywhere on the filesystem.
-			unresolved = append(unresolved, fmt.Errorf("the retained install in %s is not a directory, so recovery will not publish it", workspace))
-			continue
-		}
-		claims = append(claims, claim{workspace: workspace, name: name, target: target, backup: backup})
-		claimants[name]++
-	}
-	for _, c := range claims {
-		if claimants[c.name] > 1 {
-			// Nothing ranks two claims on one install, and publishing them in turn
-			// destroys every tree but the last.
-			unresolved = append(unresolved, fmt.Errorf("install %s is claimed by more than one interrupted transaction, including %s: resolve them by hand", c.name, c.workspace))
-			continue
-		}
-		if err := recoverWorkspace(c.workspace, c.target, c.backup, c.name, reconcile); err != nil {
-			unresolved = append(unresolved, err)
-		}
-	}
-	return errors.Join(unresolved...)
-}
-
-// recoverWorkspace resolves one attributable workspace whose backup is present.
-func recoverWorkspace(workspace string, target string, backup string, name string, reconcile Reconciler) error {
-	info, err := os.Lstat(target)
-	if err != nil {
-		if !errors.Is(err, os.ErrNotExist) {
-			// A target we could not probe is not a target that is absent. Reading
-			// it as absent enters the restore branch, the one branch that moves a
-			// tree, on the strength of a question that never got an answer. No test
-			// injects this on Linux: the names that used to reach here and fail are
-			// now refused by recoverableTarget, and a permission fault on the root
-			// stops at the marker read above. It is kept for the platforms that can
-			// still fail this call, Windows reserved device names among them.
-			return fmt.Errorf("inspect install %s: %w", name, err)
-		}
-		// Nothing at the target, so the swap never finished and the backup is the
-		// only copy there is. There is no second tree to weigh it against, and
-		// asking could only produce an answer that throws it away.
-		if err := os.Rename(backup, target); err != nil {
-			return fmt.Errorf("restore interrupted install %s: %w", name, err)
-		}
-		cleanupWorkspace(workspace)
-		return nil
-	}
-	if !info.IsDir() {
-		// An entry at the target is not an install at the target. A dangling
-		// symlink satisfies Lstat, and reading it as a live install retires the
-		// backup beside it, which is the only real copy there is.
-		return fmt.Errorf("install %s is not a directory, so recovery cannot tell what it is: resolve %s by hand", name, workspace)
-	}
-	phase := PhaseCommitted
-	if reconcile != nil {
-		classified, err := reconcile(name, target, backup)
-		if err != nil {
-			// A caller that could not classify is not permission to fall back on
-			// filesystem shape, which is the inference this protocol exists to
-			// remove.
-			return fmt.Errorf("classify interrupted install %s: %w", name, err)
-		}
-		phase = classified
-	}
-	switch phase {
-	case PhaseCommitted:
-		// The backup holds what the committed publish replaced. Keeping it made a
-		// removal reversible by accident: the removal deleted the live target, and
-		// the next recovery then read the absent target as an interrupted swap and
-		// published the stale tree again. Only the workspace goes, never the live
-		// install. This is the one place os.RemoveAll is right over
-		// cleanupWorkspace, which refuses a workspace holding a previous precisely
-		// because it cannot tell a superseded backup from one still owed a
-		// restore.
-		//
-		// The backup goes before the workspace around it, because os.RemoveAll
-		// walks the workspace in name order and so unlinks the marker first. A
-		// removal that then failed inside the backup left a workspace holding a
-		// tree nothing could attribute, which the next pass reads as somebody
-		// else's content and stays silent about. Clearing the backup first means
-		// whatever survives a failure is still ours and is still reported.
-		if err := os.RemoveAll(backup); err != nil {
-			return fmt.Errorf("retire superseded install %s: %w", name, err)
-		}
-		if err := os.RemoveAll(workspace); err != nil {
-			return fmt.Errorf("retire superseded install %s: %w", name, err)
-		}
-		return nil
-	case PhasePrePublish:
-		return restoreOverTarget(workspace, target, backup, name)
-	default:
-		// Neither tree is the one the metadata records, so recovery cannot tell
-		// which one the user is owed and either guess risks destroying the other.
-		return fmt.Errorf("interrupted install %s matches neither the live target nor the retained backup: resolve %s by hand", name, workspace)
-	}
-}
-
-// restoreOverTarget puts the backup back over a target that is still there,
-// which is what the metadata recording the backup means: the tree swap landed
-// but the publish never did, and recovery cannot publish forward because it does
-// not know the source the interrupted install was writing.
-func restoreOverTarget(workspace string, target string, backup string, name string) error {
-	// Same ordering rollback uses. Removing the superseded tree in place would
-	// leave a husk at the target while the backup was still the only complete
-	// copy, and a kill in that window is unrecoverable. With the renames in this
-	// order every instant has either a whole tree at the target or nothing there
-	// and the backup intact, which is exactly what this pass can tell apart.
-	failed := filepath.Join(workspace, "failed")
-	// An earlier rollback can have left a tree here. The workspace is proven ours
-	// by its marker, so clearing it is safe, and leaving it is not: the rename
-	// below fails for as long as it is there, and because every caller aborts on a
-	// recovery error that wedges every install and removal in this root.
-	if err := os.RemoveAll(failed); err != nil {
-		return fmt.Errorf("clear the superseded install set aside in %s: %w", workspace, err)
-	}
-	if err := os.Rename(target, failed); err != nil {
-		return fmt.Errorf("set aside superseded install %s: %w", name, err)
-	}
-	if err := os.Rename(backup, target); err != nil {
-		return fmt.Errorf("restore interrupted install %s: %w", name, err)
-	}
-	if err := os.RemoveAll(failed); err != nil {
-		return fmt.Errorf("remove superseded install %s: %w", name, err)
-	}
-	cleanupWorkspace(workspace)
-	return nil
-}
-
-// markerTarget reads the install name a workspace records, and reports whether
-// the workspace is one of ours at all. The prefix alone does not prove that: it
-// is a public dot prefixed name and the skill loader enumerates dot prefixed
-// directories, so a user authored skill can carry it and hold the same entries a
-// workspace does. Only the magic and version first line is evidence no ordinary
-// content produces by accident, so anything else is somebody's content and is
-// left alone.
-func markerTarget(workspace string) (string, bool, error) {
-	path := filepath.Join(workspace, markerFileName)
-	info, err := os.Lstat(path)
-	if err != nil {
-		if errors.Is(err, os.ErrNotExist) {
-			return "", false, nil
-		}
-		return "", false, err
-	}
-	if !info.Mode().IsRegular() {
-		return "", false, nil
-	}
-	data, err := os.ReadFile(path)
-	if err != nil {
-		// Present but unreadable is not absent, and the difference decides whether
-		// a retained tree is put back or stranded where nothing reads it.
-		return "", false, err
-	}
-	magic, rest, ok := strings.Cut(string(data), "\n")
-	if !ok || magic != markerMagic {
-		return "", false, nil
-	}
-	line, _, ok := strings.Cut(rest, "\n")
-	if !ok {
-		return "", false, nil
-	}
-	name, ok := strings.CutPrefix(line, "target ")
-	if !ok {
-		return "", false, nil
-	}
-	return name, true, nil
-}
-
-// recoverableTarget resolves a recorded target name to a path directly inside
-// dir, and returns the normalized name alongside it. Both come back because the
-// caller needs them to agree: the path is resolved from the trimmed name, so
-// asking the reconciler about the raw one would split the decision across two
-// values, and a lookup that missed on the untrimmed name would read as a publish
-// that never ran and replace the committed target with the tree it superseded.
-//
-// A name that is not a single path element could name anything on the
-// filesystem, so it is refused rather than restored over. A name carrying the
-// workspace prefix is refused for the same reason: it names another
-// transaction, not an install, and restoring over one that is still in flight
-// would destroy it.
-func recoverableTarget(dir string, name string) (string, string, bool) {
-	name = strings.TrimSpace(name)
-	if name == "" || name == "." || name == ".." || name != filepath.Base(name) {
-		return "", "", false
-	}
-	if strings.HasPrefix(name, workspacePrefix) {
-		return "", "", false
-	}
-	// A name no filesystem can resolve is not an install to recover. Left to reach
-	// Lstat it answers with an error that is not not-exist, which would be reported
-	// as an unresolved transaction on every pass forever, with no way for a caller
-	// to clear it.
-	if strings.ContainsRune(name, 0) || len(name) > 255 {
-		return "", "", false
-	}
-	return name, filepath.Join(dir, name), true
-}
-
 func rollback(target string, backup string, hadPrevious bool, cause error) error {
-	if !hadPrevious {
-		// A first install has no backup to protect and recorded no target, so
-		// recovery never looks here and deleting in place costs nothing.
-		if err := os.RemoveAll(target); err != nil {
-			return errors.Join(cause, fmt.Errorf("remove failed install: %w", err))
-		}
-		return cause
-	}
-	// Move the failed install aside before restoring rather than deleting it in
-	// place. A process killed partway through an in-place delete would leave a
-	// half removed tree at the target while the backup was still the only
-	// complete copy, and recovery reads a target that is there as a committed
-	// publish and retires the backup beside it. With the renames in this order
-	// every instant of the rollback has either a whole tree at the target or
-	// nothing there and the backup intact, which is exactly what recovery's two
-	// branches are able to tell apart.
-	failed := filepath.Join(filepath.Dir(backup), "failed")
-	if err := os.Rename(target, failed); err != nil {
-		// The move aside can fail too, and then the failed install stays live at
-		// the target while the backup is still the only copy of what it replaced.
-		// A caller with no reconciler reads a tree at the target as a committed
-		// publish, so it would retire that backup, and one that has a reconciler
-		// cannot classify a tree its own publish never recorded. Dropping the
-		// marker leaves a workspace nothing can attribute, which recovery already
-		// leaves alone, and the copy is still there to rescue by hand.
-		_ = os.Remove(filepath.Join(filepath.Dir(backup), markerFileName))
+	if err := os.RemoveAll(target); err != nil {
 		return errors.Join(cause, fmt.Errorf("remove failed install: %w", err))
 	}
-	if err := os.Rename(backup, target); err != nil {
-		return errors.Join(cause, fmt.Errorf("restore previous install: %w", err))
+	if hadPrevious {
+		if err := os.Rename(backup, target); err != nil {
+			return errors.Join(cause, fmt.Errorf("restore previous install: %w", err))
+		}
 	}
-	_ = os.RemoveAll(failed)
 	return cause
 }
 

internal/keyring/keyring.go

@@ -9,9 +9,7 @@
 // through `security -i` (interactive mode), whose command parser is line-based
 // with a fixed 4096-byte line buffer, so Set rejects secrets containing
 // newlines or exceeding that budget rather than silently corrupting them;
-// Linux's secret-tool has no such restriction. MaxSecretLen reports that budget
-// so a caller holding a larger value can split it across entries instead of
-// being turned away.
+// Linux's secret-tool has no such restriction.
 package keyring
 
 import (
@@ -84,7 +82,7 @@ func (k *Keyring) Set(service, account, secret string) error {
 			}
 		}
 		// -U updates the item if it already exists rather than failing.
-		line := securityAddLine(service, account, secret)
+		line := "add-generic-password -U -s " + securityQuote(service) + " -a " + securityQuote(account) + " -w " + securityQuote(secret) + "\n"
 		if len(line) > securityMaxLine {
 			return wrap("set", fmt.Errorf("secret too large for the macOS security tool's %d-byte command line; use the file backend instead", securityMaxLine))
 		}
@@ -164,42 +162,11 @@ func (k *Keyring) Delete(service, account string) (bool, error) {
 	}
 }
 
-// MaxSecretLen reports the largest secret, in bytes, that Set accepts under
-// (service, account) on this platform. ok is false when the backend imposes no
-// practical limit, which is the case for Linux's secret-tool: it reads the
-// secret from stdin rather than a command line. On macOS the secret shares the
-// `security -i` command line with the service and account, so the budget
-// depends on both and a caller that splits an oversized value must size each
-// part against the exact account name it will be stored under.
-//
-// The budget assumes the secret needs no quote escaping. securityQuote only
-// expands `\` and `"`, neither of which appears in base64 or hex, so a caller
-// storing encoded data gets the exact figure.
-func (k *Keyring) MaxSecretLen(service, account string) (int, bool) {
-	if k.goos != "darwin" {
-		return 0, false
-	}
-	// Measuring the real command with an empty secret counts the surrounding
-	// quotes too, so a secret of exactly this length lands on securityMaxLine.
-	budget := securityMaxLine - len(securityAddLine(service, account, ""))
-	if budget < 0 {
-		budget = 0
-	}
-	return budget, true
-}
-
 // securityMaxLine is the most `security -i` can read as one command: its line
 // buffer is MAX_LINE_LEN (4096) bytes in Apple's SecurityTool, one of which the
 // terminating NUL consumes.
 const securityMaxLine = 4095
 
-// securityAddLine renders the `security -i` command that stores secret under
-// (service, account). Set writes it and MaxSecretLen measures it, so the two
-// cannot disagree about how much of the line the overhead consumes.
-func securityAddLine(service, account, secret string) string {
-	return "add-generic-password -U -s " + securityQuote(service) + " -a " + securityQuote(account) + " -w " + securityQuote(secret) + "\n"
-}
-
 // securityQuote wraps s for one argument of a `security -i` command line. The
 // tool's parser (split_line in Apple's SecurityTool) treats a backslash inside
 // double quotes as escaping the next character and the matching quote as the

internal/keyring/keyring_test.go

@@ -375,46 +375,3 @@ func TestAvailable(t *testing.T) {
 		t.Fatal("linux should be available")
 	}
 }
-
-// TestMaxSecretLenMatchesTheDarwinSetBoundary pins the budget to the boundary
-// Set actually enforces. A caller that splits an oversized value depends on the
-// two agreeing exactly: one byte of drift either wastes an entry or produces a
-// chunk security silently splits into two garbage commands.
-func TestMaxSecretLenMatchesTheDarwinSetBoundary(t *testing.T) {
-	k := newFake("darwin").keyring()
-	budget, bounded := k.MaxSecretLen("zero", "oauth-tokens")
-	if !bounded {
-		t.Fatal("MaxSecretLen reported darwin as unbounded")
-	}
-	if err := newFake("darwin").keyring().Set("zero", "oauth-tokens", strings.Repeat("a", budget)); err != nil {
-		t.Errorf("Set(budget=%d bytes): %v, want acceptance at the boundary", budget, err)
-	}
-	if err := newFake("darwin").keyring().Set("zero", "oauth-tokens", strings.Repeat("a", budget+1)); err == nil {
-		t.Errorf("Set(%d bytes) succeeded, want rejection one byte past the budget", budget+1)
-	}
-}
-
-// TestMaxSecretLenShrinksWithTheAccountName covers why the budget takes the
-// account: on macOS the account and the secret share one command line, so a
-// longer account name leaves less room for the secret.
-func TestMaxSecretLenShrinksWithTheAccountName(t *testing.T) {
-	k := newFake("darwin").keyring()
-	short, _ := k.MaxSecretLen("zero", "oauth-tokens")
-	long, _ := k.MaxSecretLen("zero", "oauth-tokens.a.63")
-	if want := short - len(".a.63"); long != want {
-		t.Fatalf("MaxSecretLen for the longer account = %d, want %d", long, want)
-	}
-	if err := newFake("darwin").keyring().Set("zero", "oauth-tokens.a.63", strings.Repeat("a", long+1)); err == nil {
-		t.Error("Set one byte past the longer account's budget succeeded")
-	}
-}
-
-// TestMaxSecretLenUnboundedOffDarwin keeps the limit platform-specific:
-// secret-tool reads the secret from stdin, so there is no command line to fill.
-func TestMaxSecretLenUnboundedOffDarwin(t *testing.T) {
-	for _, goos := range []string{"linux", "windows"} {
-		if n, bounded := newFake(goos).keyring().MaxSecretLen("zero", "oauth-tokens"); bounded || n != 0 {
-			t.Errorf("MaxSecretLen on %s = (%d, %v), want (0, false)", goos, n, bounded)
-		}
-	}
-}

internal/lockutil/lockutil.go

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

internal/lockutil/lockutil_other.go

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

internal/lockutil/lockutil_test.go

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

internal/lockutil/lockutil_windows.go

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

internal/lockutil/lockutil_windows_test.go

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

internal/lockutil/reclaim.go

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

internal/lockutil/reclaim_other_test.go

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

internal/lockutil/reclaim_test.go

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

internal/lockutil/reclaim_windows_test.go

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

internal/mcp/client.go

@@ -7,7 +7,6 @@ import (
 	"errors"
 	"fmt"
 	"io"
-	"math"
 	"os"
 	"os/exec"
 	"strconv"
@@ -50,21 +49,13 @@ type Client struct {
 	stdin   io.WriteCloser
 	reader  *messageReader
 	writer  *messageWriter
+	mu      sync.Mutex
 	closeMu sync.Mutex
-	idMu    sync.Mutex
 	nextID  int
 	cleanup func()
 
-	writeMu          sync.Mutex
-	writeQueue       chan writeOp
-	writeClosed      bool
-	writeSenders     sync.WaitGroup
-	writerStop       chan struct{}
-	writerDone       chan struct{}
-	courtesyOverflow []writeOp
-
 	// dispatchMu guards the response-dispatch state shared with the single
-	// reader goroutine. It is never held across a blocking read or write.
+	// reader goroutine. It is never held across a blocking read.
 	dispatchMu sync.Mutex
 	readerOnce sync.Once
 	pending    map[int]chan dispatchResult
@@ -72,17 +63,6 @@ type Client struct {
 	readDone   bool
 }
 
-type writeOp struct {
-	ctx     context.Context
-	message rpcMessage
-	done    chan error
-}
-
-const writeQueueCapacity = 32
-const courtesyOverflowCap = writeQueueCapacity
-
-var errMCPClientClosed = errors.New("MCP client closed")
-
 // dispatchResult carries one matched JSON-RPC response (or a terminal reader
 // error) to a waiting caller.
 type dispatchResult struct {
@@ -272,8 +252,7 @@ func (client *Client) Close() error {
 	// Fail any callers still waiting on a response. The blocking read in the
 	// reader goroutine is released below when stdin closes and the process
 	// exits (or is killed), EOFing stdout.
-	client.failAll(errMCPClientClosed)
-	client.beginWriterShutdown()
+	client.failAll(errors.New("MCP client closed"))
 
 	var err error
 	stdin := client.stdin
@@ -313,7 +292,6 @@ func (client *Client) Close() error {
 		client.cleanup()
 		client.cleanup = nil
 	}
-	client.finishWriterShutdown()
 	return err
 }
 
@@ -329,20 +307,20 @@ func (client *Client) request(ctx context.Context, method string, params any, ta
 		return err
 	}
 
-	// Allocate an id and register a response channel. ID allocation and dispatch
-	// registrations are fast non-blocking operations. Message transmission is
-	// handled via writeMessage so a caller with a canceled context can stop
-	// waiting even when the peer is not draining its input.
-	client.idMu.Lock()
+	// Allocate an id, register a response channel, and write the request while
+	// holding client.mu. The mutex serializes writes and id allocation but is
+	// released before the (potentially unbounded) wait for the response, so a
+	// hung server never holds the lock and blocks other callers/Close.
+	client.mu.Lock()
 	id := client.nextID
 	client.nextID++
-	client.idMu.Unlock()
 
 	responses := make(chan dispatchResult, 1)
 	client.dispatchMu.Lock()
 	if client.readDone {
 		readErr := client.readErr
 		client.dispatchMu.Unlock()
+		client.mu.Unlock()
 		if readErr != nil {
 			return readErr
 		}
@@ -351,14 +329,16 @@ func (client *Client) request(ctx context.Context, method string, params any, ta
 	client.pending[id] = responses
 	client.dispatchMu.Unlock()
 
-	if err := client.writeMessage(ctx, rpcMessage{
+	if err := client.writer.write(rpcMessage{
 		ID:     id,
 		Method: method,
 		Params: rawParams,
 	}); err != nil {
 		client.removePending(id)
+		client.mu.Unlock()
 		return err
 	}
+	client.mu.Unlock()
 
 	select {
 	case <-ctx.Done():
@@ -381,189 +361,6 @@ func (client *Client) request(ctx context.Context, method string, params any, ta
 	}
 }
 
-func (client *Client) ensureWriter() {
-	_ = client.startWriter()
-}
-
-func (client *Client) startWriter() error {
-	client.writeMu.Lock()
-	defer client.writeMu.Unlock()
-	if client.writeClosed {
-		return errMCPClientClosed
-	}
-	if client.writeQueue != nil {
-		return nil
-	}
-	queue := make(chan writeOp, writeQueueCapacity)
-	client.writeQueue = queue
-	client.writerStop = make(chan struct{})
-	client.writerDone = make(chan struct{})
-	go client.writeLoop(queue)
-	return nil
-}
-
-func (client *Client) writerStopped() bool {
-	if client.writerStop == nil {
-		return false
-	}
-	select {
-	case <-client.writerStop:
-		return true
-	default:
-		return false
-	}
-}
-
-func (client *Client) beginWriterShutdown() {
-	client.writeMu.Lock()
-	defer client.writeMu.Unlock()
-	if client.writeClosed {
-		return
-	}
-	client.writeClosed = true
-	if client.writerStop != nil {
-		close(client.writerStop)
-	}
-	for _, op := range client.courtesyOverflow {
-		if op.done != nil {
-			op.done <- errMCPClientClosed
-		}
-	}
-	client.courtesyOverflow = nil
-}
-
-func (client *Client) finishWriterShutdown() {
-	client.writeMu.Lock()
-	queue := client.writeQueue
-	done := client.writerDone
-	client.writeQueue = nil
-	client.writeMu.Unlock()
-	if queue == nil {
-		return
-	}
-	client.writeSenders.Wait()
-	close(queue)
-	if done != nil {
-		<-done
-	}
-}
-
-func (client *Client) writeLoop(queue <-chan writeOp) {
-	defer close(client.writerDone)
-	if queue == nil {
-		return
-	}
-	for op := range queue {
-		if client.writerStopped() {
-			if op.done != nil {
-				op.done <- errMCPClientClosed
-			}
-			continue
-		}
-		if op.ctx != nil {
-			select {
-			case <-op.ctx.Done():
-				if op.done != nil {
-					op.done <- op.ctx.Err()
-				}
-				continue
-			default:
-			}
-		}
-		err := client.writer.write(op.message)
-		if op.done != nil {
-			op.done <- err
-		}
-		client.drainCourtesyOverflow()
-	}
-}
-
-func (client *Client) drainCourtesyOverflow() {
-	client.writeMu.Lock()
-	defer client.writeMu.Unlock()
-	if client.writeClosed || client.writeQueue == nil {
-		client.courtesyOverflow = nil
-		return
-	}
-	for len(client.courtesyOverflow) > 0 {
-		select {
-		case client.writeQueue <- client.courtesyOverflow[0]:
-			client.courtesyOverflow = client.courtesyOverflow[1:]
-		default:
-			return
-		}
-	}
-}
-
-func (client *Client) enqueueCourtesy(message rpcMessage) {
-	if err := client.startWriter(); err != nil {
-		return
-	}
-	op := writeOp{message: message}
-	client.writeMu.Lock()
-	defer client.writeMu.Unlock()
-	if client.writeClosed || client.writeQueue == nil {
-		return
-	}
-	select {
-	case client.writeQueue <- op:
-	default:
-		if len(client.courtesyOverflow) >= courtesyOverflowCap {
-			return
-		}
-		client.courtesyOverflow = append(client.courtesyOverflow, op)
-	}
-}
-
-func (client *Client) writeMessage(ctx context.Context, message rpcMessage) error {
-	if err := ctx.Err(); err != nil {
-		return err
-	}
-	if err := client.startWriter(); err != nil {
-		return err
-	}
-	done := make(chan error, 1)
-	op := writeOp{ctx: ctx, message: message, done: done}
-
-	client.writeMu.Lock()
-	if client.writeClosed {
-		client.writeMu.Unlock()
-		return errMCPClientClosed
-	}
-	stop := client.writerStop
-	queue := client.writeQueue
-	client.writeSenders.Add(1)
-	client.writeMu.Unlock()
-
-	select {
-	case <-ctx.Done():
-		client.writeSenders.Done()
-		return ctx.Err()
-	case <-stop:
-		client.writeSenders.Done()
-		return errMCPClientClosed
-	case queue <- op:
-		client.writeSenders.Done()
-	}
-
-	select {
-	case <-ctx.Done():
-		return ctx.Err()
-	case <-stop:
-		select {
-		case err := <-done:
-			if err != nil {
-				return err
-			}
-			return errMCPClientClosed
-		case <-ctx.Done():
-			return ctx.Err()
-		}
-	case err := <-done:
-		return err
-	}
-}
-
 // ensureReader lazily starts the single reader goroutine. It runs once per
 // client; subsequent calls are no-ops.
 func (client *Client) ensureReader() {
@@ -588,20 +385,6 @@ func (client *Client) readLoop() {
 			client.failAll(err)
 			return
 		}
-		// A message with a Method is a server-initiated request or notification.
-		// It must never be routed as a response to a pending client request.
-		if message.isRequestOrNotification() {
-			if message.ID != nil && jsonRPCIDEchoable(message.ID) {
-				client.enqueueCourtesy(rpcMessage{
-					ID: message.ID,
-					Error: &rpcError{
-						Code:    -32601,
-						Message: fmt.Sprintf("Method %q not supported", message.Method),
-					},
-				})
-			}
-			continue
-		}
 		if message.ID == nil {
 			continue
 		}
@@ -645,20 +428,6 @@ func (client *Client) failAll(err error) {
 
 // rpcMessageID extracts the integer id from a JSON-RPC id value across the
 // numeric/string encodings a server may use.
-func jsonNumberAsInt(n json.Number) (int64, bool) {
-	if parsed, err := n.Int64(); err == nil {
-		return parsed, true
-	}
-	f, err := n.Float64()
-	if err != nil || math.IsNaN(f) || math.IsInf(f, 0) || f != math.Trunc(f) {
-		return 0, false
-	}
-	if f > float64(math.MaxInt64) || f < float64(math.MinInt64) {
-		return 0, false
-	}
-	return int64(f), true
-}
-
 func rpcMessageID(value any) (int, bool) {
 	switch typed := value.(type) {
 	case int:
@@ -666,13 +435,10 @@ func rpcMessageID(value any) (int, bool) {
 	case int64:
 		return int(typed), true
 	case float64:
-		if math.IsNaN(typed) || math.IsInf(typed, 0) || typed != math.Trunc(typed) {
-			return 0, false
-		}
 		return int(typed), true
 	case json.Number:
-		parsed, ok := jsonNumberAsInt(typed)
-		if !ok {
+		parsed, err := typed.Int64()
+		if err != nil {
 			return 0, false
 		}
 		return int(parsed), true
@@ -688,30 +454,18 @@ func rpcMessageID(value any) (int, bool) {
 }
 
 func rpcIDMatches(value any, id int) bool {
-	got, ok := rpcMessageID(value)
-	return ok && got == id
-}
-
-// jsonRPCIDEchoable reports whether id is a valid JSON-RPC 2.0 identifier type
-// (string or finite number) that is safe to echo back.
-func jsonRPCIDEchoable(id any) bool {
-	if id == nil {
-		return false
-	}
-	switch v := id.(type) {
-	case string:
-		return true
-	case int, int8, int16, int32, int64, uint, uint8, uint16, uint32, uint64:
-		return true
+	switch typed := value.(type) {
+	case int:
+		return typed == id
+	case int64:
+		return typed == int64(id)
 	case float64:
-		return !math.IsNaN(v) && !math.IsInf(v, 0)
+		return typed == float64(id)
 	case json.Number:
-		parsed, err := v.Float64()
-		if err != nil || math.IsNaN(parsed) || math.IsInf(parsed, 0) {
-			return false
-		}
-		_, err = json.Marshal(v)
-		return err == nil
+		parsed, err := typed.Int64()
+		return err == nil && parsed == int64(id)
+	case string:
+		return typed == strconv.Itoa(id)
 	default:
 		return false
 	}
@@ -722,7 +476,7 @@ func (client *Client) notify(method string, params any) error {
 	if err != nil {
 		return err
 	}
-	return client.writeMessage(context.Background(), rpcMessage{
+	return client.writer.write(rpcMessage{
 		Method: method,
 		Params: rawParams,
 	})

internal/mcp/client_test.go

@@ -1,19 +1,15 @@
 package mcp
 
 import (
-	"bufio"
-	"bytes"
 	"context"
 	"encoding/json"
 	"errors"
 	"fmt"
 	"io"
-	"math"
 	"net/http"
 	"net/http/httptest"
 	"os"
 	"os/exec"
-	"runtime"
 	"strings"
 	"sync"
 	"sync/atomic"
@@ -846,837 +842,3 @@ func TestBoundedBufferCapsRetainedBytes(t *testing.T) {
 		t.Fatalf("retained %q, want %q (capped at 8 bytes, head kept)", got, "hellowor")
 	}
 }
-
-func TestStdioClientIgnoresServerInitiatedRequestsInPendingResponses(t *testing.T) {
-	inReader, inWriter := io.Pipe()
-	outReader, outWriter := io.Pipe()
-
-	client := &Client{
-		reader:  newMessageReader(inReader),
-		writer:  newMessageWriter(outWriter),
-		pending: make(map[int]chan dispatchResult),
-	}
-	defer func() {
-		_ = inWriter.Close()
-		_ = outReader.Close()
-	}()
-
-	client.ensureReader()
-
-	// Register a pending response for ID 1
-	responses := make(chan dispatchResult, 1)
-	client.dispatchMu.Lock()
-	client.pending[1] = responses
-	client.dispatchMu.Unlock()
-
-	// Simulate server sending a request with ID 1 ("roots/list")
-	serverReq := `{"jsonrpc":"2.0","id":1,"method":"roots/list","params":{}}` + "\n"
-	if _, err := inWriter.Write([]byte(serverReq)); err != nil {
-		t.Fatalf("write server request: %v", err)
-	}
-
-	// The server request must take the separate request path: it receives a
-	// method-not-found response and cannot resolve the pending client call.
-	courtesyResult := make(chan dispatchResult, 1)
-	go func() {
-		message, err := newMessageReader(outReader).read()
-		courtesyResult <- dispatchResult{message: message, err: err}
-	}()
-	select {
-	case result := <-courtesyResult:
-		if result.err != nil {
-			t.Fatalf("read courtesy response: %v", result.err)
-		}
-		if !rpcIDMatches(result.message.ID, 1) || result.message.Error == nil || result.message.Error.Code != -32601 {
-			t.Fatalf("courtesy response = %#v, want id 1 and error -32601", result.message)
-		}
-	case <-time.After(time.Second):
-		t.Fatal("timed out waiting for method-not-found response")
-	}
-	select {
-	case res := <-responses:
-		t.Fatalf("pending request 1 received server request: %#v", res.message)
-	default:
-	}
-
-	// Now send the actual response for ID 1
-	serverResp := `{"jsonrpc":"2.0","id":1,"result":{"tools":[]}}` + "\n"
-	if _, err := inWriter.Write([]byte(serverResp)); err != nil {
-		t.Fatalf("write server response: %v", err)
-	}
-
-	select {
-	case res := <-responses:
-		if res.message.Method != "" || len(res.message.Result) == 0 {
-			t.Fatalf("expected valid response, got %#v", res.message)
-		}
-	case <-time.After(500 * time.Millisecond):
-		t.Fatal("timed out waiting for actual response")
-	}
-}
-
-// TestStdioClientUndrainedServerDoesNotStallReadLoop proves that when a server
-// stops draining its stdin, an asynchronous courtesy -32601 reply does not stall
-// the read loop from servicing legitimate responses.
-func TestStdioClientUndrainedServerDoesNotStallReadLoop(t *testing.T) {
-	inReader, inWriter := io.Pipe()
-	outReader, outWriter := io.Pipe()
-
-	client := &Client{
-		reader:  newMessageReader(inReader),
-		writer:  newMessageWriter(outWriter),
-		pending: make(map[int]chan dispatchResult),
-	}
-	defer func() {
-		_ = inWriter.Close()
-		_ = outReader.Close()
-	}()
-
-	client.ensureReader()
-
-	// 1. Register a pending response for call ID 1
-	responses := make(chan dispatchResult, 1)
-	client.dispatchMu.Lock()
-	client.pending[1] = responses
-	client.dispatchMu.Unlock()
-
-	// 2. Server sends request ID 2 (we DO NOT drain outReader so server stdin pipe is blocked)
-	serverReq := `{"jsonrpc":"2.0","id":2,"method":"roots/list","params":{}}` + "\n"
-	go func() {
-		_, _ = inWriter.Write([]byte(serverReq))
-		// 3. Immediately send response for ID 1
-		serverResp := `{"jsonrpc":"2.0","id":1,"result":{"tools":[]}}` + "\n"
-		_, _ = inWriter.Write([]byte(serverResp))
-	}()
-
-	// 4. Verify the response for ID 1 is delivered without being stalled by the undrained pipe
-	select {
-	case res := <-responses:
-		if res.message.Method != "" || len(res.message.Result) == 0 {
-			t.Fatalf("expected valid response for ID 1, got %#v", res.message)
-		}
-	case <-time.After(1 * time.Second):
-		t.Fatal("readLoop stalled on undrained error write; pending response was not delivered")
-	}
-}
-
-func TestStdioClientDropsInvalidServerRequestIDs(t *testing.T) {
-	inReader, inWriter := io.Pipe()
-	outReader, outWriter := io.Pipe()
-
-	client := &Client{
-		reader:  newMessageReader(inReader),
-		writer:  newMessageWriter(outWriter),
-		pending: make(map[int]chan dispatchResult),
-	}
-	defer func() {
-		_ = inWriter.Close()
-		_ = outReader.Close()
-	}()
-
-	client.ensureReader()
-
-	// Server sends request with boolean ID (invalid JSON-RPC id)
-	serverReq := `{"jsonrpc":"2.0","id":true,"method":"roots/list","params":{}}` + "\n"
-	if _, err := inWriter.Write([]byte(serverReq)); err != nil {
-		t.Fatalf("write invalid server request: %v", err)
-	}
-
-	// A following valid request acts as an ordering barrier: receiving its
-	// response proves readLoop already processed the invalid request. Because the
-	// writer is serial, any incorrect reply to the boolean ID would arrive first.
-	validReq := `{"jsonrpc":"2.0","id":7,"method":"roots/list","params":{}}` + "\n"
-	if _, err := inWriter.Write([]byte(validReq)); err != nil {
-		t.Fatalf("write valid server request: %v", err)
-	}
-	readResult := make(chan dispatchResult, 1)
-	go func() {
-		message, err := newMessageReader(outReader).read()
-		readResult <- dispatchResult{message: message, err: err}
-	}()
-
-	select {
-	case result := <-readResult:
-		if result.err != nil {
-			t.Fatalf("read valid request response: %v", result.err)
-		}
-		if !rpcIDMatches(result.message.ID, 7) || result.message.Error == nil || result.message.Error.Code != -32601 {
-			t.Fatalf("response = %#v, want only valid id 7 and error -32601", result.message)
-		}
-	case <-time.After(time.Second):
-		t.Fatal("timed out waiting for valid request response")
-	}
-}
-
-func TestStdioClientRepliesToValidNonIntegerServerRequestIDs(t *testing.T) {
-	requests := []struct {
-		name string
-		wire string
-		want string
-	}{
-		{name: "fractional", wire: `{"jsonrpc":"2.0","id":1.5,"method":"roots/list","params":{}}` + "\n", want: "1.5"},
-		{name: "exponent", wire: `{"jsonrpc":"2.0","id":2e2,"method":"roots/list","params":{}}` + "\n", want: "2e2"},
-	}
-	for _, request := range requests {
-		t.Run(request.name, func(t *testing.T) {
-			inReader, inWriter := io.Pipe()
-			outReader, outWriter := io.Pipe()
-			client := &Client{
-				reader:  newMessageReader(inReader),
-				writer:  newMessageWriter(outWriter),
-				pending: make(map[int]chan dispatchResult),
-			}
-			t.Cleanup(func() {
-				_ = inWriter.Close()
-				_ = outReader.Close()
-			})
-			client.ensureReader()
-			if _, err := inWriter.Write([]byte(request.wire)); err != nil {
-				t.Fatalf("write server request: %v", err)
-			}
-			result := make(chan dispatchResult, 1)
-			go func() {
-				response, err := newMessageReader(outReader).read()
-				result <- dispatchResult{message: response, err: err}
-			}()
-			select {
-			case response := <-result:
-				if response.err != nil {
-					t.Fatalf("read method-not-found response: %v", response.err)
-				}
-				got, err := json.Marshal(response.message.ID)
-				if err != nil {
-					t.Fatalf("marshal id: %v", err)
-				}
-				if string(got) != request.want || response.message.Error == nil || response.message.Error.Code != -32601 {
-					t.Fatalf("response = %#v, want id %s and error -32601", response.message, request.want)
-				}
-			case <-time.After(time.Second):
-				t.Fatal("timed out waiting for method-not-found response")
-			}
-		})
-	}
-}
-
-func TestJSONRPCIDEchoableAcceptsFiniteJSONNumbers(t *testing.T) {
-	for _, test := range []struct {
-		name string
-		id   any
-		want bool
-	}{
-		{name: "fractional float", id: 1.5, want: true},
-		{name: "exponent json number", id: json.Number("2e2"), want: true},
-		{name: "not a number", id: math.NaN(), want: false},
-		{name: "positive infinity", id: math.Inf(1), want: false},
-		{name: "invalid json number", id: json.Number("not-a-number"), want: false},
-	} {
-		t.Run(test.name, func(t *testing.T) {
-			if got := jsonRPCIDEchoable(test.id); got != test.want {
-				t.Fatalf("jsonRPCIDEchoable(%v) = %v, want %v", test.id, got, test.want)
-			}
-		})
-	}
-}
-
-type gatedCaptureWriter struct {
-	started     chan struct{}
-	release     chan struct{}
-	startedOnce sync.Once
-	releaseOnce sync.Once
-	mu          sync.Mutex
-	buffer      bytes.Buffer
-}
-
-func newGatedCaptureWriter() *gatedCaptureWriter {
-	return &gatedCaptureWriter{
-		started: make(chan struct{}),
-		release: make(chan struct{}),
-	}
-}
-
-func (writer *gatedCaptureWriter) Write(p []byte) (int, error) {
-	writer.startedOnce.Do(func() { close(writer.started) })
-	<-writer.release
-	writer.mu.Lock()
-	defer writer.mu.Unlock()
-	return writer.buffer.Write(p)
-}
-
-func (writer *gatedCaptureWriter) Release() {
-	writer.releaseOnce.Do(func() { close(writer.release) })
-}
-
-func (writer *gatedCaptureWriter) Bytes() []byte {
-	writer.mu.Lock()
-	defer writer.mu.Unlock()
-	return append([]byte(nil), writer.buffer.Bytes()...)
-}
-
-func TestStdioClientDoesNotWriteCanceledQueuedRequest(t *testing.T) {
-	reader := newBlockingReader()
-	defer reader.Close()
-
-	output := newGatedCaptureWriter()
-	defer output.Release()
-	client := &Client{
-		reader:  newMessageReader(reader),
-		writer:  newMessageWriter(output),
-		pending: make(map[int]chan dispatchResult),
-	}
-
-	blockerDone := make(chan error, 1)
-	go func() {
-		blockerDone <- client.writeMessage(context.Background(), rpcMessage{Method: "notifications/blocker"})
-	}()
-	select {
-	case <-output.started:
-	case <-time.After(time.Second):
-		t.Fatal("initial write did not reach the blocked transport")
-	}
-
-	ctx, cancel := context.WithTimeout(context.Background(), 50*time.Millisecond)
-	defer cancel()
-	if err := client.request(ctx, "tools/call", map[string]any{"name": "side_effect"}, nil); !errors.Is(err, context.DeadlineExceeded) {
-		t.Fatalf("request() error = %v, want context deadline exceeded", err)
-	}
-
-	output.Release()
-	if err := <-blockerDone; err != nil {
-		t.Fatalf("release initial write: %v", err)
-	}
-	if err := client.writeMessage(context.Background(), rpcMessage{Method: "notifications/sentinel"}); err != nil {
-		t.Fatalf("write sentinel: %v", err)
-	}
-
-	messages := newMessageReader(bytes.NewReader(output.Bytes()))
-	first, err := messages.read()
-	if err != nil {
-		t.Fatalf("read initial message: %v", err)
-	}
-	if first.Method != "notifications/blocker" {
-		t.Fatalf("first method = %q, want notifications/blocker", first.Method)
-	}
-	second, err := messages.read()
-	if err != nil {
-		t.Fatalf("read sentinel message: %v", err)
-	}
-	if second.Method != "notifications/sentinel" {
-		t.Fatalf("second method = %q, want notifications/sentinel", second.Method)
-	}
-	if extra, err := messages.read(); !errors.Is(err, io.EOF) {
-		t.Fatalf("unexpected queued message %#v, read error = %v", extra, err)
-	}
-}
-
-// TestStdioClientUndrainedServerDoesNotBlockCallerWithDeadline verifies that
-// when the server's input pipe is completely blocked and courtesy replies are
-// queued/dropped, a caller invoking request() with a deadline aborts cleanly
-// when the context expires rather than hanging indefinitely on a write or mutex.
-func TestStdioClientUndrainedServerDoesNotBlockCallerWithDeadline(t *testing.T) {
-	inReader, inWriter := io.Pipe()
-	outReader, outWriter := io.Pipe()
-
-	client := &Client{
-		reader:  newMessageReader(inReader),
-		writer:  newMessageWriter(outWriter),
-		pending: make(map[int]chan dispatchResult),
-	}
-	defer func() {
-		_ = inWriter.Close()
-		_ = outReader.Close()
-	}()
-
-	client.ensureReader()
-
-	// Flood server requests to saturate write queue while outReader is NOT drained.
-	for i := 1; i <= 50; i++ {
-		serverReq := fmt.Sprintf(`{"jsonrpc":"2.0","id":%d,"method":"roots/list","params":{}}`+"\n", i+100)
-		_, err := inWriter.Write([]byte(serverReq))
-		if err != nil {
-			t.Fatalf("failed to write server request: %v", err)
-		}
-	}
-
-	// Caller with short deadline invokes request()
-	ctx, cancel := context.WithTimeout(context.Background(), 100*time.Millisecond)
-	defer cancel()
-
-	start := time.Now()
-	err := client.request(ctx, "tools/list", map[string]any{}, nil)
-	elapsed := time.Since(start)
-
-	if !errors.Is(err, context.DeadlineExceeded) && !errors.Is(err, context.Canceled) {
-		t.Fatalf("expected deadline exceeded, got: %v", err)
-	}
-	if elapsed > 1*time.Second {
-		t.Fatalf("request took too long to abort on deadline: %v", elapsed)
-	}
-}
-
-func TestStdioClientEmptyMethodDoesNotCompletePending(t *testing.T) {
-	inReader, inWriter := io.Pipe()
-	outReader, outWriter := io.Pipe()
-	client := &Client{
-		reader:  newMessageReader(inReader),
-		writer:  newMessageWriter(outWriter),
-		pending: make(map[int]chan dispatchResult),
-	}
-	defer func() {
-		_ = inWriter.Close()
-		_ = outReader.Close()
-	}()
-	client.ensureReader()
-
-	responses := make(chan dispatchResult, 1)
-	client.dispatchMu.Lock()
-	client.pending[1] = responses
-	client.dispatchMu.Unlock()
-
-	if _, err := inWriter.Write([]byte(`{"jsonrpc":"2.0","id":1,"method":""}` + "\n")); err != nil {
-		t.Fatalf("write empty-method frame: %v", err)
-	}
-
-	courtesyResult := make(chan dispatchResult, 1)
-	go func() {
-		message, err := newMessageReader(outReader).read()
-		courtesyResult <- dispatchResult{message: message, err: err}
-	}()
-	select {
-	case result := <-courtesyResult:
-		if result.err != nil {
-			t.Fatalf("read courtesy response: %v", result.err)
-		}
-		if !rpcIDMatches(result.message.ID, 1) || result.message.Error == nil || result.message.Error.Code != -32601 {
-			t.Fatalf("courtesy response = %#v, want id 1 and error -32601", result.message)
-		}
-	case <-time.After(time.Second):
-		t.Fatal("timed out waiting for method-not-found response")
-	}
-	select {
-	case res := <-responses:
-		t.Fatalf("pending request 1 completed by empty-method frame: %#v", res.message)
-	default:
-	}
-
-	if _, err := inWriter.Write([]byte(`{"jsonrpc":"2.0","id":1,"result":{"tools":[]}}` + "\n")); err != nil {
-		t.Fatalf("write server response: %v", err)
-	}
-	select {
-	case res := <-responses:
-		if res.message.Method != "" || len(res.message.Result) == 0 {
-			t.Fatalf("expected valid response, got %#v", res.message)
-		}
-	case <-time.After(500 * time.Millisecond):
-		t.Fatal("timed out waiting for actual response")
-	}
-}
-
-func TestStdioClientNullMethodDoesNotCompletePending(t *testing.T) {
-	inReader, inWriter := io.Pipe()
-	outReader, outWriter := io.Pipe()
-	client := &Client{
-		reader:  newMessageReader(inReader),
-		writer:  newMessageWriter(outWriter),
-		pending: make(map[int]chan dispatchResult),
-	}
-	defer func() {
-		_ = inWriter.Close()
-		_ = outReader.Close()
-	}()
-	client.ensureReader()
-
-	responses := make(chan dispatchResult, 1)
-	client.dispatchMu.Lock()
-	client.pending[1] = responses
-	client.dispatchMu.Unlock()
-
-	if _, err := inWriter.Write([]byte(`{"jsonrpc":"2.0","id":1,"method":null}` + "\n")); err != nil {
-		t.Fatalf("write null-method frame: %v", err)
-	}
-
-	courtesyResult := make(chan dispatchResult, 1)
-	go func() {
-		message, err := newMessageReader(outReader).read()
-		courtesyResult <- dispatchResult{message: message, err: err}
-	}()
-	select {
-	case result := <-courtesyResult:
-		if result.err != nil {
-			t.Fatalf("read courtesy response: %v", result.err)
-		}
-		if !rpcIDMatches(result.message.ID, 1) || result.message.Error == nil || result.message.Error.Code != -32601 {
-			t.Fatalf("courtesy response = %#v, want id 1 and error -32601", result.message)
-		}
-	case <-time.After(time.Second):
-		t.Fatal("timed out waiting for method-not-found response")
-	}
-	select {
-	case res := <-responses:
-		t.Fatalf("pending request 1 completed by null-method frame: %#v", res.message)
-	default:
-	}
-
-	if _, err := inWriter.Write([]byte(`{"jsonrpc":"2.0","id":1,"result":{"tools":[]}}` + "\n")); err != nil {
-		t.Fatalf("write server response: %v", err)
-	}
-	select {
-	case res := <-responses:
-		if res.message.Method != "" || len(res.message.Result) == 0 {
-			t.Fatalf("expected valid response, got %#v", res.message)
-		}
-	case <-time.After(500 * time.Millisecond):
-		t.Fatal("timed out waiting for actual response")
-	}
-}
-
-func TestStdioClientCourtesyReplySurvivesFullWriteQueue(t *testing.T) {
-	inReader, inWriter := io.Pipe()
-	outReader, outWriter := io.Pipe()
-	client := &Client{
-		reader:  newMessageReader(inReader),
-		writer:  newMessageWriter(outWriter),
-		pending: make(map[int]chan dispatchResult),
-	}
-	defer func() {
-		_ = inWriter.Close()
-		_ = outReader.Close()
-	}()
-	client.ensureReader()
-
-	responses := make(chan dispatchResult, 1)
-	client.dispatchMu.Lock()
-	client.pending[1] = responses
-	client.dispatchMu.Unlock()
-
-	const extra = 8
-	n := writeQueueCapacity + extra
-	for i := 0; i < n; i++ {
-		frame := fmt.Sprintf(`{"jsonrpc":"2.0","id":%d,"method":"roots/list","params":{}}`+"\n", i+100)
-		if _, err := inWriter.Write([]byte(frame)); err != nil {
-			t.Fatalf("write server request %d: %v", i, err)
-		}
-	}
-	if _, err := inWriter.Write([]byte(`{"jsonrpc":"2.0","id":1,"result":{"ok":true}}` + "\n")); err != nil {
-		t.Fatalf("write pending response: %v", err)
-	}
-	select {
-	case res := <-responses:
-		if res.err != nil || len(res.message.Result) == 0 {
-			t.Fatalf("pending response = %#v err=%v", res.message, res.err)
-		}
-	case <-time.After(2 * time.Second):
-		t.Fatal("readLoop stalled while the write queue was full")
-	}
-
-	drainDone := make(chan []rpcMessage, 1)
-	go func() {
-		reader := newMessageReader(outReader)
-		var got []rpcMessage
-		for len(got) < n {
-			message, err := reader.read()
-			if err != nil {
-				drainDone <- got
-				return
-			}
-			got = append(got, message)
-		}
-		drainDone <- got
-	}()
-	select {
-	case got := <-drainDone:
-		if len(got) != n {
-			t.Fatalf("courtesy replies = %d, want %d (queue-full requests dropped)", len(got), n)
-		}
-		seen := make(map[int]bool, n)
-		for _, message := range got {
-			id, ok := rpcMessageID(message.ID)
-			if !ok || message.Error == nil || message.Error.Code != -32601 {
-				t.Fatalf("courtesy reply = %#v, want -32601", message)
-			}
-			seen[id] = true
-		}
-		for i := 0; i < n; i++ {
-			if !seen[i+100] {
-				t.Fatalf("missing courtesy reply for id %d after output resumed", i+100)
-			}
-		}
-	case <-time.After(3 * time.Second):
-		t.Fatal("timed out draining courtesy replies after output resumed")
-	}
-}
-
-func TestWriterLoopExitsOnRepeatedClose(t *testing.T) {
-	before := runtime.NumGoroutine()
-	for i := 0; i < 25; i++ {
-		inReader, inWriter := io.Pipe()
-		outReader, outWriter := io.Pipe()
-		copied := make(chan struct{})
-		go func() {
-			_, _ = io.Copy(io.Discard, outReader)
-			close(copied)
-		}()
-		client := &Client{
-			stdin:  outWriter,
-			reader: newMessageReader(inReader),
-			writer: newMessageWriter(outWriter),
-		}
-		client.ensureWriter()
-		if err := client.writeMessage(context.Background(), rpcMessage{Method: "notifications/ping"}); err != nil {
-			t.Fatalf("writeMessage: %v", err)
-		}
-		if err := client.Close(); err != nil && !errors.Is(err, io.ErrClosedPipe) {
-			t.Fatalf("Close: %v", err)
-		}
-		_ = inWriter.Close()
-		<-copied
-	}
-	runtime.GC()
-	time.Sleep(20 * time.Millisecond)
-	after := runtime.NumGoroutine()
-	if after > before+8 {
-		t.Fatalf("goroutines leaked: before=%d after=%d", before, after)
-	}
-}
-
-func TestWriteMessageReleasedOnClose(t *testing.T) {
-	reader := newBlockingReader()
-	defer reader.Close()
-	output := newGatedCaptureWriter()
-	client := &Client{
-		reader: newMessageReader(reader),
-		writer: newMessageWriter(output),
-	}
-
-	blockerDone := make(chan error, 1)
-	go func() {
-		blockerDone <- client.writeMessage(context.Background(), rpcMessage{Method: "notifications/blocker"})
-	}()
-	select {
-	case <-output.started:
-	case <-time.After(time.Second):
-		t.Fatal("initial write did not reach the transport")
-	}
-
-	queuedDone := make(chan error, 1)
-	go func() {
-		queuedDone <- client.writeMessage(context.Background(), rpcMessage{Method: "notifications/queued"})
-	}()
-	deadline := time.Now().Add(time.Second)
-	for len(client.writeQueue) == 0 {
-		if time.Now().After(deadline) {
-			t.Fatal("queued write did not enqueue")
-		}
-		time.Sleep(time.Millisecond)
-	}
-
-	closeDone := make(chan error, 1)
-	go func() {
-		closeDone <- client.Close()
-	}()
-	select {
-	case <-client.writerStop:
-	case <-time.After(time.Second):
-		t.Fatal("Close did not begin writer shutdown")
-	}
-	output.Release()
-	select {
-	case err := <-closeDone:
-		if err != nil && !errors.Is(err, io.ErrClosedPipe) {
-			t.Fatalf("Close: %v", err)
-		}
-	case <-time.After(2 * time.Second):
-		t.Fatal("Close hung waiting for the writer worker")
-	}
-
-	select {
-	case err := <-queuedDone:
-		if err == nil {
-			t.Fatal("queued write succeeded after Close")
-		}
-	case <-time.After(2 * time.Second):
-		t.Fatal("queued write was not released on Close")
-	}
-	select {
-	case <-blockerDone:
-	case <-time.After(2 * time.Second):
-		t.Fatal("blocked write was not released on Close")
-	}
-
-	messages := newMessageReader(bytes.NewReader(output.Bytes()))
-	for {
-		message, err := messages.read()
-		if errors.Is(err, io.EOF) {
-			break
-		}
-		if err != nil {
-			t.Fatalf("read captured output: %v", err)
-		}
-		if message.Method == "notifications/queued" {
-			t.Fatal("queued request was written after Close")
-		}
-	}
-}
-
-func TestStdioClientPreservesLargeNumericRequestID(t *testing.T) {
-	inReader, inWriter := io.Pipe()
-	outReader, outWriter := io.Pipe()
-	client := &Client{
-		reader:  newMessageReader(inReader),
-		writer:  newMessageWriter(outWriter),
-		pending: make(map[int]chan dispatchResult),
-	}
-	defer func() {
-		_ = inWriter.Close()
-		_ = outReader.Close()
-	}()
-	client.ensureReader()
-
-	const rawID = "9007199254740993"
-	if _, err := inWriter.Write([]byte(`{"jsonrpc":"2.0","id":` + rawID + `,"method":"roots/list","params":{}}` + "\n")); err != nil {
-		t.Fatalf("write server request: %v", err)
-	}
-
-	lineDone := make(chan struct {
-		line string
-		err  error
-	}, 1)
-	go func() {
-		line, err := bufio.NewReader(outReader).ReadString('\n')
-		lineDone <- struct {
-			line string
-			err  error
-		}{line: line, err: err}
-	}()
-	select {
-	case got := <-lineDone:
-		if got.err != nil {
-			t.Fatalf("read courtesy response: %v", got.err)
-		}
-		if !strings.Contains(got.line, rawID) {
-			t.Fatalf("serialized courtesy response %q does not preserve id %s", got.line, rawID)
-		}
-		if !strings.Contains(got.line, `"-32601"`) && !strings.Contains(got.line, `-32601`) {
-			t.Fatalf("serialized courtesy response %q missing -32601", got.line)
-		}
-	case <-time.After(time.Second):
-		t.Fatal("timed out waiting for courtesy response")
-	}
-}
-
-func TestRPCMessageIDAcceptsExponentForm(t *testing.T) {
-	got, ok := rpcMessageID(json.Number("1e0"))
-	if !ok || got != 1 {
-		t.Fatalf("rpcMessageID(1e0) = %d, %v, want 1, true", got, ok)
-	}
-	got, ok = rpcMessageID(json.Number("2e2"))
-	if !ok || got != 200 {
-		t.Fatalf("rpcMessageID(2e2) = %d, %v, want 200, true", got, ok)
-	}
-	if _, ok := rpcMessageID(json.Number("1.5")); ok {
-		t.Fatal("fractional json.Number should not match")
-	}
-	if rpcIDMatches(json.Number("1e0"), 1) != true {
-		t.Fatal("rpcIDMatches(1e0, 1) = false")
-	}
-}
-
-func TestStdioClientMatchesExponentFormResponseID(t *testing.T) {
-	inReader, inWriter := io.Pipe()
-	outReader, outWriter := io.Pipe()
-	client := &Client{
-		reader:  newMessageReader(inReader),
-		writer:  newMessageWriter(outWriter),
-		pending: make(map[int]chan dispatchResult),
-	}
-	defer func() {
-		_ = inWriter.Close()
-		_ = outReader.Close()
-	}()
-	client.ensureReader()
-
-	responses := make(chan dispatchResult, 1)
-	client.dispatchMu.Lock()
-	client.pending[1] = responses
-	client.dispatchMu.Unlock()
-
-	if _, err := inWriter.Write([]byte(`{"jsonrpc":"2.0","id":1e0,"result":{"ok":true}}` + "\n")); err != nil {
-		t.Fatalf("write exponent-id response: %v", err)
-	}
-	select {
-	case res := <-responses:
-		if res.err != nil || len(res.message.Result) == 0 {
-			t.Fatalf("pending 1 not completed by id 1e0: %#v err=%v", res.message, res.err)
-		}
-	case <-time.After(time.Second):
-		t.Fatal("response id 1e0 did not resolve pending request 1")
-	}
-}
-
-func TestStdioClientCourtesyOverflowIsBounded(t *testing.T) {
-	inReader, inWriter := io.Pipe()
-	outReader, outWriter := io.Pipe()
-	client := &Client{
-		reader:  newMessageReader(inReader),
-		writer:  newMessageWriter(outWriter),
-		pending: make(map[int]chan dispatchResult),
-	}
-	defer func() {
-		_ = inWriter.Close()
-		_ = outReader.Close()
-	}()
-	client.ensureReader()
-
-	responses := make(chan dispatchResult, 1)
-	client.dispatchMu.Lock()
-	client.pending[1] = responses
-	client.dispatchMu.Unlock()
-
-	flood := writeQueueCapacity + courtesyOverflowCap + 64
-	for i := 0; i < flood; i++ {
-		frame := fmt.Sprintf(`{"jsonrpc":"2.0","id":%d,"method":"roots/list","params":{}}`+"\n", i+100)
-		if _, err := inWriter.Write([]byte(frame)); err != nil {
-			t.Fatalf("write server request %d: %v", i, err)
-		}
-	}
-	if _, err := inWriter.Write([]byte(`{"jsonrpc":"2.0","id":1,"result":{"ok":true}}` + "\n")); err != nil {
-		t.Fatalf("write pending response: %v", err)
-	}
-	select {
-	case res := <-responses:
-		if res.err != nil {
-			t.Fatalf("pending stalled: %v", res.err)
-		}
-	case <-time.After(2 * time.Second):
-		t.Fatal("readLoop stalled during courtesy flood")
-	}
-
-	client.writeMu.Lock()
-	n := len(client.courtesyOverflow)
-	client.writeMu.Unlock()
-	if n > courtesyOverflowCap {
-		t.Fatalf("courtesyOverflow = %d, want <= %d", n, courtesyOverflowCap)
-	}
-}
-
-func TestWriterLoopCloseBeforeScheduleDoesNotHang(t *testing.T) {
-	for i := 0; i < 50; i++ {
-		client := &Client{
-			writer: newMessageWriter(io.Discard),
-		}
-		if err := client.startWriter(); err != nil {
-			t.Fatalf("startWriter: %v", err)
-		}
-		done := make(chan error, 1)
-		go func() {
-			done <- client.Close()
-		}()
-		select {
-		case err := <-done:
-			if err != nil && !errors.Is(err, io.ErrClosedPipe) {
-				t.Fatalf("Close: %v", err)
-			}
-		case <-time.After(2 * time.Second):
-			t.Fatal("Close hung: writeLoop ranged over a nil queue")
-		}
-	}
-}

internal/mcp/hang_test.go

@@ -62,15 +62,6 @@ type blockingReader struct {
 	release chan struct{}
 }
 
-type signalingWriter struct {
-	writes chan struct{}
-}
-
-func (writer *signalingWriter) Write(p []byte) (int, error) {
-	writer.writes <- struct{}{}
-	return len(p), nil
-}
-
 func newBlockingReader() *blockingReader {
 	return &blockingReader{release: make(chan struct{})}
 }
@@ -91,15 +82,14 @@ func (reader *blockingReader) Close() error {
 
 // A hung stdio server must not block Client.request forever: a cancelled
 // per-call context must unblock the wait and surface ctx.Err(), and it must
-// not hold shared client state that prevents a second caller from proceeding.
+// not hold client.mu (a second caller must still be able to proceed).
 func TestClientRequestUnblocksOnContextCancel(t *testing.T) {
 	reader := newBlockingReader()
 	defer reader.Close()
-	writes := make(chan struct{}, 2)
 
 	client := &Client{
 		reader: newMessageReader(reader),
-		writer: newMessageWriter(&signalingWriter{writes: writes}),
+		writer: newMessageWriter(io.Discard),
 		nextID: 1,
 	}
 
@@ -109,11 +99,6 @@ func TestClientRequestUnblocksOnContextCancel(t *testing.T) {
 		done <- client.request(ctx, "tools/list", map[string]any{}, nil)
 	}()
 
-	select {
-	case <-writes:
-	case <-time.After(time.Second):
-		t.Fatal("first request did not reach the transport")
-	}
 	// The request is now parked waiting for a response that never comes.
 	cancel()
 
@@ -126,27 +111,21 @@ func TestClientRequestUnblocksOnContextCancel(t *testing.T) {
 		t.Fatal("request() hung on a non-responsive server")
 	}
 
-	// The shared state must be free: prove a second live request reaches the
-	// transport, then cancel it and verify cancellation releases the caller.
-	secondCtx, cancel2 := context.WithCancel(context.Background())
-	defer cancel2()
+	// The lock must be free: a second request under an already-cancelled
+	// context must return immediately rather than block.
+	cancelled, cancel2 := context.WithCancel(context.Background())
+	cancel2()
 	second := make(chan error, 1)
 	go func() {
-		second <- client.request(secondCtx, "tools/list", map[string]any{}, nil)
+		second <- client.request(cancelled, "tools/list", map[string]any{}, nil)
 	}()
 	select {
-	case <-writes:
-	case <-time.After(time.Second):
-		t.Fatal("second request did not reach the transport")
-	}
-	cancel2()
-	select {
 	case err := <-second:
 		if !errors.Is(err, context.Canceled) {
 			t.Fatalf("second request() error = %v, want context.Canceled", err)
 		}
 	case <-time.After(3 * time.Second):
-		t.Fatal("second request() blocked behind the hung read")
+		t.Fatal("second request() blocked — client.mu was held across the hung read")
 	}
 }
 

internal/mcp/network_client.go

@@ -539,9 +539,6 @@ func (client *remoteSSEClient) deliverEventMessage(value string) error {
 	if err := decoder.Decode(&message); err != nil {
 		return fmt.Errorf("decode MCP SSE stream message: %w", err)
 	}
-	if message.isRequestOrNotification() {
-		return nil
-	}
 	key := rpcResponseKey(message.ID)
 	if key == "" {
 		return nil
@@ -636,7 +633,7 @@ func decodeSSERPCMessage(reader io.Reader) (rpcMessage, error) {
 		// those — the response has no method — and keep scanning. Previously the
 		// first message event was returned unconditionally, so a leading
 		// notification surfaced to the caller as an id mismatch and failed the call.
-		if candidate.isRequestOrNotification() {
+		if candidate.Method != "" {
 			return true
 		}
 		decoded = candidate

internal/mcp/network_client_test.go

@@ -339,60 +339,3 @@ func TestDecodeSSERPCMessageSkipsNotifications(t *testing.T) {
 		t.Fatalf("expected a result payload, got %#v", msg)
 	}
 }
-
-func TestDecodeSSERPCMessageSkipsEmptyAndNullMethod(t *testing.T) {
-	stream := "event: message\n" +
-		`data: {"jsonrpc":"2.0","id":7,"method":""}` + "\n\n" +
-		"event: message\n" +
-		`data: {"jsonrpc":"2.0","id":7,"method":null}` + "\n\n" +
-		"event: message\n" +
-		`data: {"jsonrpc":"2.0","id":7,"result":{"ok":true}}` + "\n\n"
-
-	msg, err := decodeSSERPCMessage(strings.NewReader(stream))
-	if err != nil {
-		t.Fatalf("decodeSSERPCMessage: %v", err)
-	}
-	if msg.isRequestOrNotification() {
-		t.Fatalf("empty/null method must not be treated as the response, got method %q present=%v", msg.Method, msg.methodPresent)
-	}
-	if !rpcIDMatches(msg.ID, 7) {
-		t.Fatalf("expected response id 7, got %#v", msg.ID)
-	}
-}
-
-func TestDeliverEventMessageSkipsMethodPresence(t *testing.T) {
-	client := &remoteSSEClient{pending: map[string]chan ssePendingResponse{}}
-	key := rpcResponseKey(1)
-	pending := make(chan ssePendingResponse, 1)
-	client.pending[key] = pending
-
-	if err := client.deliverEventMessage(`{"jsonrpc":"2.0","id":1,"method":""}`); err != nil {
-		t.Fatalf("deliverEventMessage empty method: %v", err)
-	}
-	if err := client.deliverEventMessage(`{"jsonrpc":"2.0","id":1,"method":null}`); err != nil {
-		t.Fatalf("deliverEventMessage null method: %v", err)
-	}
-	select {
-	case got := <-pending:
-		t.Fatalf("method presence must not complete pending, got %#v", got)
-	default:
-	}
-	if _, ok := client.pending[key]; !ok {
-		t.Fatal("deliverEventMessage must not delete pending for a request/notification")
-	}
-
-	if err := client.deliverEventMessage(`{"jsonrpc":"2.0","id":1,"result":{"ok":true}}`); err != nil {
-		t.Fatalf("deliverEventMessage response: %v", err)
-	}
-	select {
-	case got := <-pending:
-		if got.err != nil {
-			t.Fatalf("true response: %v", got.err)
-		}
-		if got.message.isRequestOrNotification() {
-			t.Fatal("true response must not carry a method")
-		}
-	default:
-		t.Fatal("true response must complete pending")
-	}
-}

internal/mcp/oauth.go

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

internal/mcp/oauth_discovery_network.go

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

internal/mcp/oauth_discovery_network_test.go

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

internal/mcp/oauth_protected_resource.go

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