fix(tui): keep the profile name on /model switch so the stored key resolves

normalizeProfileForProvider rewrote profile.Name to the catalog provider.ID
whenever normalizeIdentity was true — which includes any first-party provider
whose saved baseURL matches the catalog default. The credential store is keyed
by profile.Name, and this rewrite runs before profileWithCredential, so the
stored-key lookup missed and the rebuilt provider went out with no key: a 401 on
every /model switch for a profile named differently from its catalog id (e.g.
"my-openai").

Only canonicalize an empty or generic placeholder name now; a real user-provided
name is preserved. CatalogID canonicalization is unchanged (it is not the store
key). Adds regression tests covering a custom-named first-party profile surviving
normalization and placeholder names still canonicalizing.

Fixes #440

.github/workflows/ci.yml

@@ -100,10 +100,9 @@ jobs:
           go-version-file: go.mod
           cache: true
 
-      # govulncheck, deadcode, and golangci-lint each resolve a toolchain from
-      # their own modules, which can drop below the version go.mod requires and
-      # then fail to load our packages. Pin GOTOOLCHAIN to the go.mod toolchain
-      # so all three run under it.
+      # govulncheck and deadcode resolve a toolchain from their own modules, which
+      # can drop below the version go.mod requires and then fail to load our
+      # packages. Pin GOTOOLCHAIN to the go.mod toolchain so both run under it.
       - name: Pin toolchain from go.mod
         run: |
           toolchain="$(awk '/^toolchain /{print $2}' go.mod)"
@@ -121,13 +120,3 @@ jobs:
       - name: deadcode (advisory)
         continue-on-error: true
         run: go run golang.org/x/tools/cmd/[email protected] -test=false ./...
-
-      # 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: go run github.com/golangci/golangci-lint/v2/cmd/[email protected] run --enable-only unused,ineffassign,staticcheck ./...

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

@@ -4,14 +4,12 @@ on:
   pull_request:
     paths:
       - action.yml
-      - docs/GITHUB_ACTION.md
       - .github/workflows/zero-action-smoke.yml
   push:
     branches:
       - main
     paths:
       - action.yml
-      - docs/GITHUB_ACTION.md
       - .github/workflows/zero-action-smoke.yml
 
 jobs:
@@ -31,8 +29,7 @@ jobs:
           import sys, yaml
 
           with open("action.yml", "r", encoding="utf-8") as handle:
-              action_raw = handle.read()
-          doc = yaml.safe_load(action_raw)
+              doc = yaml.safe_load(handle)
 
           assert isinstance(doc, dict), "action.yml must be a mapping"
           assert doc.get("name"), "action must declare a name"
@@ -68,19 +65,6 @@ jobs:
           assert "--skip-permissions-unsafe" not in serialized, \
               "action must never pass --skip-permissions-unsafe"
 
-          run_zero = next((step for step in steps if step.get("name") == "Run ZERO"), None)
-          assert run_zero is not None, "action.yml must contain a Run ZERO step"
-          run_zero_script = run_zero.get("run") or ""
-          assert 'export "${ZERO_INPUT_API_KEY_ENV}=${ZERO_INPUT_API_KEY}"' in run_zero_script, \
-              "Run ZERO must export the provider key for the current step"
-          assert "later steps inherit" not in action_raw.lower(), \
-              "provider keys must not be documented as inherited by later steps"
-          for line in run_zero_script.splitlines():
-              if "GITHUB_ENV" in line and (
-                  "ZERO_INPUT_API_KEY" in line or "ZERO_INPUT_API_KEY_ENV" in line
-              ):
-                  raise AssertionError("provider key must not be persisted to GITHUB_ENV")
-
           print(f"action.yml OK: {len(inputs)} inputs, {len(outputs)} outputs, {len(steps)} steps")
           PY
 

.gitignore

@@ -37,13 +37,8 @@ report.[0-9]_.[0-9]_.[0-9]_.[0-9]_.json
 
 /zero
 /zero.exe
-/zero-skills
 /snake-game.html
 
 # Superpowers skill artifacts (brainstorm mockups, specs, plans) — local only
 .superpowers/
 docs/superpowers/
-
-# Termux/Android build artifacts
-zero-termux-arm64
-zero-linux-sandbox

AGENTS.MD

@@ -26,7 +26,7 @@ Accepted file names, in priority order at each level:
 | `./ZERO.md` | Brand-specific alias. Same format, lower priority. |
 | `./.zero/AGENTS.md` | Project-local, hidden, gitignored. Personal notes that stay out of git. |
 
-Matching is **case-insensitive** on the basename, so `AGENTS.md`, `Agents.md`, and `agents.md` resolve to the same file on Windows and macOS. The git-tracked filename in this repo is `AGENTS.md` — keep that on case-sensitive filesystems (Linux, the WSL filesystem, or a CI runner) to match what the loader looks for.
+Matching is **case-insensitive** on the basename, so `AGENTS.md`, `Agents.md`, and `agents.md` resolve to the same file on Windows and macOS. The git-tracked filename in this repo is `AGENTS.MD` (uppercase `MD`) — keep that on case-sensitive filesystems (Linux, the WSL filesystem, or a CI runner) to match what the loader looks for.
 
 Both files use the same format. YAML frontmatter is optional; the markdown body is loaded as instructions for the agent. Zero reads the file once at session start, so changes take effect on the next `zero` launch — not mid-session.
 
@@ -47,12 +47,6 @@ Tips:
 - In a monorepo, drop a narrower `AGENTS.md` in each sub-tree (e.g. `services/api/AGENTS.md`). Zero picks those up automatically when you launch from inside the sub-tree.
 - A YAML frontmatter block (`---\n...\n---`) at the top is preserved verbatim in the injected prompt but is not parsed for `globs:` or `alwaysApply:` scoping today — keep the body self-contained.
 
-### Personal guidelines, across every project
-
-For preferences that follow *you*, not a specific repo (tone, tooling habits, workflow), drop a `ZERO.md` in your user config directory: `~/.config/zero/ZERO.md` on Linux/macOS, `%AppData%\Roaming\zero\ZERO.md` on Windows — the same directory as `config.json` and your personal specialists. Same format and 8 KiB cap as the project files above, and the same case-insensitive basename match.
-
-This file is injected as its own `## User guidelines` section, before the project's `AGENTS.md`/`ZERO.md`, and is labeled as personal preference in the prompt: project guidelines are the later, more specific instruction and take precedence over it when the two conflict.
-
 ## 2. Custom specialists
 
 Specialists are Zero's sub-agents. Three scopes, in priority order:
@@ -313,7 +307,6 @@ A team that wants every contributor's Zero to behave the same way commits:
 Each contributor adds only:
 
 - `~/.config/zero/config.json` — their personal API keys, theme, default mode.
-- `~/.config/zero/ZERO.md` — personal preferences that follow them across every project (see section 1).
 - `~/.local/share/zero/skills/` — personal skills they keep across projects.
 
 That's it. Run `zero` from the repo root and the agent has the team's full instruction set, every contributor's personal setup, and nothing else.

Makefile

@@ -1,4 +1,4 @@
-# Zero build/test/lint targets. AGENTS.md says "Build with `make`" and "Run `make
+# Zero build/test/lint targets. AGENTS.MD says "Build with `make`" and "Run `make
 # lint` before opening a PR" — these targets back those instructions.
 .DEFAULT_GOAL := build
 .PHONY: build build-all test test-race vet fmt fmt-check lint tidy clean help

README.md

@@ -59,24 +59,20 @@ Bun does not run dependency lifecycle scripts by default, so the `postinstall`
 that fetches the Zero binary is skipped and the first run fails with
 `No native binary found next to the npm wrapper`.
 
-The simplest fix is to trust the package after installing, which runs the
-blocked postinstall. This works for project and global installs:
+Install with Bun, then fetch the binary in one of two ways:
 
 ```bash
-# project install
+# Option A: run the installer manually
 bun add @gitlawb/zero
-bun pm trust @gitlawb/zero
+node node_modules/@gitlawb/zero/scripts/postinstall.mjs
 
-# global install
-bun add -g @gitlawb/zero
-bun pm -g trust @gitlawb/zero
+# Option B: allow the postinstall to run on install
+# add to your package.json:  "trustedDependencies": ["@gitlawb/zero"]
+bun add @gitlawb/zero
 ```
 
-Alternatives: allow the postinstall up front by adding
-`"trustedDependencies": ["@gitlawb/zero"]` to your project's package.json
-before `bun add`, or run the installer manually
-(`node node_modules/@gitlawb/zero/scripts/postinstall.mjs`) on Bun versions
-that do not have `bun pm trust`.
+For global installs (`bun add -g @gitlawb/zero`), use Option A against the
+global install path, or prefer the install scripts below.
 
 ### Install scripts
 
@@ -186,7 +182,6 @@ Common slash commands:
 | `/spec`, `/plan` | draft and review a plan before building |
 | `/image` | attach an image for vision-capable models |
 | `/resume`, `/rewind` | continue or roll back local sessions |
-| `/loop` | repeat a prompt or custom `/command` on an interval (`/loop 5m /babysit-prs`) or self-paced |
 | `/compact`, `/context` | manage context usage |
 | `/permissions`, `/tools` | inspect available tools and policy |
 | `/add-dir` | allow an extra write directory for this session |
@@ -284,39 +279,6 @@ zero cron             scheduled agent jobs
 zero update           check for newer releases
 ```
 
-## Extending Zero
-
-### Project and personal instructions
-
-Zero appends project-specific guidance to the system prompt from the first
-`AGENTS.md`, `ZERO.md`, or `.zero/AGENTS.md` file found in each directory from
-the git root down to your current working directory (checked in that order
-per directory). Files are injected general-to-specific, capped at 8 KiB per
-file and 32 KiB total.
-
-A personal `ZERO.md` under `config.UserConfigDir()/zero/ZERO.md`
-(`$XDG_CONFIG_HOME/zero/ZERO.md` or `~/.config/zero/ZERO.md` on Linux/macOS,
-`%AppData%\Roaming\zero\ZERO.md` on Windows) applies across every workspace, ahead of any project guidelines.
-
-### Plugins
-
-Plugins are discovered from `~/.config/zero/plugins/<name>/plugin.json` (user
-scope — `$XDG_CONFIG_HOME` or `~/.config` on every OS, independent of the
-`config.UserConfigDir()` path used above) and `<cwd>/.zero/plugins/<name>/plugin.json`
-(project scope — resolved from the current working directory, not the repo
-root), and managed with `zero plugins`. A manifest can declare:
-
-- `tools` — custom tools (`command`, `args`, `inputSchema`, and a
-  `permission` of `prompt` or `deny`; `allow` is honored only when manifest tool
-  auto-approval is enabled)
-- `hooks` — commands run on `beforeTool`, `afterTool`, `sessionStart`, or
-  `sessionEnd`
-- `prompts` and `skills` — additional prompt/skill files
-
-MCP servers (`zero mcp`) and standalone markdown skills (`zero skills`) use
-the same extension points and can also be wired up outside of a plugin
-manifest.
-
 ## Appearance And Accessibility
 
 | Control | Effect |

README_ZH.md

@@ -44,19 +44,19 @@ npm 包安装一个小型包装器以及与你平台匹配的 Zero 二进制文
 
 Bun 默认不运行依赖的生命周期脚本，因此获取 Zero 二进制文件的 `postinstall` 会被跳过，首次运行会失败并显示 `No native binary found next to the npm wrapper`。
 
-最简单的解决方法是安装后信任该包，这会运行被阻止的 postinstall。项目安装和全局安装均适用：
+使用 Bun 安装后，通过以下两种方式之一获取二进制文件：
 
 ```bash
-# 项目安装
+# 选项 A：手动运行安装程序
 bun add @gitlawb/zero
-bun pm trust @gitlawb/zero
+node node_modules/@gitlawb/zero/scripts/postinstall.mjs
 
-# 全局安装
-bun add -g @gitlawb/zero
-bun pm -g trust @gitlawb/zero
+# 选项 B：允许 postinstall 在安装时运行
+# 添加到你的 package.json:  "trustedDependencies": ["@gitlawb/zero"]
+bun add @gitlawb/zero
 ```
 
-其他方式：在 `bun add` 之前将 `"trustedDependencies": ["@gitlawb/zero"]` 添加到项目的 package.json 以提前允许 postinstall；或在不支持 `bun pm trust` 的旧版 Bun 上手动运行安装程序（`node node_modules/@gitlawb/zero/scripts/postinstall.mjs`）。
+对于全局安装（`bun add -g @gitlawb/zero`），请对全局安装路径使用选项 A，或使用下面的安装脚本。
 
 ### 安装脚本
 

action.yml

@@ -27,14 +27,14 @@ inputs:
   api-key:
     description: >-
       The provider API key. Pass it from a repository or organization secret;
-      it is exported only for the ZERO step and never written to the log.
+      it is exported into the step environment and never written to the log.
     required: false
     default: ""
   api-key-env:
     description: >-
       Name of the environment variable the chosen provider reads its key from
       (for example OPENAI_API_KEY or ANTHROPIC_API_KEY). When set together with
-      api-key, that variable is exported only for the ZERO step. Leave the action
+      api-key, that variable is exported for the run. Leave the action
       provider-agnostic by passing the env name your provider expects rather
       than hardcoding one here.
     required: false
@@ -180,7 +180,6 @@ runs:
         ZERO_INPUT_ADD_DIR: ${{ inputs.add-dir }}
         ZERO_INPUT_WORKTREE: ${{ inputs.worktree }}
         ZERO_INPUT_OUTPUT_FORMAT: ${{ inputs.output-format }}
-        ACTION_PATH: ${{ github.action_path }}
         RUNNER_TEMP: ${{ runner.temp }}
       run: |
         set -euo pipefail
@@ -193,9 +192,10 @@ runs:
             echo "::error::api-key-env must be a valid environment variable name." >&2
             exit 2
           fi
-          # Export in-process for this Run ZERO step so zero can read it; do
-          # not persist provider credentials to later job steps.
+          # Export in-process so the zero invocation in this same run block sees
+          # it, and append to GITHUB_ENV so any later steps inherit it too.
           export "${ZERO_INPUT_API_KEY_ENV}=${ZERO_INPUT_API_KEY}"
+          printf '%s=%s\n' "${ZERO_INPUT_API_KEY_ENV}" "${ZERO_INPUT_API_KEY}" >> "${GITHUB_ENV}"
         fi
         if [ -n "${ZERO_INPUT_PROVIDER}" ]; then
           export ZERO_PROVIDER="${ZERO_INPUT_PROVIDER}"
@@ -248,9 +248,10 @@ runs:
         echo "exit-code=${code}" >> "${GITHUB_OUTPUT}"
         echo "output-file=${output_file}" >> "${GITHUB_OUTPUT}"
 
-        # Best-effort one-line summary. Structured output ends with lifecycle
-        # metadata, so parse final/error events instead of tailing stdout.
-        summary="$(node "${ACTION_PATH}/scripts/action-summary.mjs" "${ZERO_INPUT_OUTPUT_FORMAT}" "${output_file}" || true)"
+        # Best-effort one-line summary: last non-empty line of the captured output.
+        summary="$(grep -v '^[[:space:]]*$' "${output_file}" | tail -n 1 || true)"
+        # Keep the summary single-line and bounded for the step output.
+        summary="$(printf '%s' "${summary}" | cut -c1-280)"
         {
           echo "summary<<ZERO_EOF"
           printf '%s\n' "${summary}"

bin/zero.js

@@ -66,12 +66,10 @@ if (!existsSync(nativePath)) {
       '\n' +
       (ranByBun
         ? 'You installed with Bun, which does not run dependency lifecycle scripts\n' +
-          'by default. Trust the package to run the blocked postinstall:\n' +
-          '  bun pm trust @gitlawb/zero       (project install)\n' +
-          '  bun pm -g trust @gitlawb/zero    (global install)\n' +
-          'On Bun versions without `bun pm trust`, add\n' +
+          'by default. To let it run on future installs, add zero to your\n' +
+          'project\'s trustedDependencies:\n' +
           '  "trustedDependencies": ["@gitlawb/zero"]\n' +
-          'to your project package.json and reinstall.\n' +
+          'then reinstall.\n' +
           '\n'
         : '') +
       'If that fails, build from source: https://github.com/Gitlawb/zero\n' +

docs/GITHUB_ACTION.md

@@ -41,9 +41,8 @@ jobs:
 > provider-neutral: `api-key-env` is the environment variable name the chosen
 > provider reads its key from (for example `ANTHROPIC_API_KEY`, `GEMINI_API_KEY`,
 > `OPENROUTER_API_KEY`), and `api-key` is the secret value. The action exports
-> that variable only for the ZERO step and never prints it. If your repository
-> already commits a `.zero/config.json` with an active provider, you can omit
-> `provider`.
+> that variable for the run and never prints it. If your repository already
+> commits a `.zero/config.json` with an active provider, you can omit `provider`.
 
 ## Inputs
 
@@ -52,8 +51,8 @@ jobs:
 | `prompt` | one of `prompt`/`prompt-file` | `""` | The instruction for ZERO to execute. |
 | `prompt-file` | one of `prompt`/`prompt-file` | `""` | Path (relative to `working-directory`) to a file whose contents are the prompt. |
 | `provider` | no | `""` | Provider id to activate (e.g. `openai`, `anthropic`, `gemini`, `ollama`, or any compatible endpoint). |
-| `api-key` | no | `""` | The provider API key. Pass from a secret; exported only for the ZERO step and never logged. |
-| `api-key-env` | no | `""` | Env var name the provider reads its key from (e.g. `OPENAI_API_KEY`). Exported only for the ZERO step when used with `api-key`. |
+| `api-key` | no | `""` | The provider API key. Pass from a secret; never logged. |
+| `api-key-env` | no | `""` | Env var name the provider reads its key from (e.g. `OPENAI_API_KEY`). Exported with `api-key`. |
 | `model` | no | `""` | Model id. Defaults to the resolved provider's default. |
 | `mode` | no | `""` | Run mode (`zero exec --mode`), e.g. `smart`, `deep`, `fast`. |
 | `auto` | no | `low` | Autonomy ceiling (`zero exec --auto`): `low`, `medium`, or `high`. Conservative by default. |
@@ -163,10 +162,9 @@ jobs:
 ## Security notes
 
 - **Secrets are passed as Action secrets and never logged.** The action exports
-  `api-key` (under `api-key-env`) only for the ZERO step. `slack-webhook-url`
-  is passed only to the Slack post step. They are never echoed or persisted to
-  later workflow steps, and ZERO redacts secret-shaped strings from its own
-  output.
+  `api-key` (under `api-key-env`) and `slack-webhook-url` into the step
+  environment only. They are never echoed, and ZERO redacts secret-shaped
+  strings from its own output.
 - **The sandbox is always active.** This action never passes
   `--skip-permissions-unsafe`, so writes stay inside the checked-out repository
   (plus any roots you grant with `add-dir`). Unsafe mode is never enabled

docs/INSTALL.md

@@ -31,24 +31,15 @@ dependencies (only the installing project's own scripts), so the `postinstall`
 that fetches the Zero binary is silently skipped. The first run then fails with
 `No native binary found next to the npm wrapper`.
 
-The simplest fix is to trust the package after installing, which runs the
-blocked postinstall. This works for project and global installs:
+To install with Bun, either run the installer manually after installing:
 
 ```bash
-# project install
 bun add @gitlawb/zero
-bun pm trust @gitlawb/zero
-
-# global install
-bun add -g @gitlawb/zero
-bun pm -g trust @gitlawb/zero
+node node_modules/@gitlawb/zero/scripts/postinstall.mjs
 ```
 
-`bun pm untrusted` (or `bun pm -g untrusted`) lists the blocked postinstalls if
-you want to inspect before trusting.
-
-Alternatively, allow the postinstall to run at install time by adding the
-package to your project's `trustedDependencies` before installing:
+Or allow the postinstall to run by adding the package to your project's
+`trustedDependencies` before installing:
 
 ```json
 {
@@ -60,12 +51,8 @@ package to your project's `trustedDependencies` before installing:
 bun add @gitlawb/zero
 ```
 
-On Bun versions that do not have `bun pm trust`, run the installer manually
-after installing:
-
-```bash
-node node_modules/@gitlawb/zero/scripts/postinstall.mjs
-```
+For global installs (`bun add -g @gitlawb/zero`), run the installer manually
+against the global install path, or use the install scripts below.
 
 Reference: <https://bun.sh/docs/pm/lifecycle>
 
@@ -173,61 +160,6 @@ Linux native sandboxing also requires Bubblewrap to be installed.
 
 macOS uses the system sandbox and does not need an extra helper binary.
 
-### Termux (Android)
-
-Zero can run natively on Android via [Termux](https://termux.dev/). Build with
-`GOOS=android` to avoid the `faccessat2` syscall that is blocked by Samsung's
-seccomp filter on Android:
-
-```bash
-# Install Go in Termux
-pkg install golang
-
-# Build Zero for Android
-git clone https://github.com/Gitlawb/zero.git
-cd zero
-CGO_ENABLED=0 GOOS=android GOARCH=arm64 go build -ldflags="-s -w" -o zero ./cmd/zero
-
-# Move into PATH
-mv zero ~/.local/bin/
-```
-
-> **Why `GOOS=android`?** Go 1.26+ detects `runtime.GOOS == "android"` and skips
-> the `faccessat2` syscall inside `os/exec.findExecutable`, falling back to
-> permission-bit checks. Without this flag, Android's seccomp sends SIGSYS and
-> kills the process whenever Zero looks up a binary on `PATH` (git, sh, etc.).
-
-**DNS.** Android does not expose `/etc/resolv.conf`. Go's pure-Go DNS resolver
-needs one. Use `proot` to bind-mount Termux's resolver config:
-
-```bash
-pkg install proot
-proot -b "$PREFIX/etc/resolv.conf:/etc/resolv.conf" zero
-```
-
-Create a wrapper at `~/.local/bin/zero` to avoid typing proot every time:
-
-```bash
-#!/data/data/com.termux/files/usr/bin/bash
-exec proot -b "$PREFIX/etc/resolv.conf:/etc/resolv.conf" ~/.local/bin/zero.bin "$@"
-```
-
-**Scroll.** On native Termux (not under PRoot), mouse scrolling works out of the
-box. The TUI uses Bubble Tea's `AllMotion` mouse mode by default. If you run Zero
-inside PRoot (e.g. through proot-distro), the scroll fix activates `CellMotion`
-to avoid PRoot's ptrace interference with the 1003 escape sequence.
-
-**Providers.** Zero works with any OpenAI-compatible provider on Termux. For
-example, to use OpenCode Zen's free tier:
-
-```bash
-zero providers add opencode \
-  --name opencode \
-  --model deepseek-v4-flash-free \
-  --base-url https://opencode.ai/zen/v1 \
-  --set-active
-```
-
 Windows source builds can use the main `zero.exe` as the command runner and setup
 helper through Zero's built-in self-dispatch path. If you want a release-style
 layout anyway, build the standalone helper executables next to `zero.exe`:

docs/STREAM_JSON_PROTOCOL.md

@@ -41,7 +41,6 @@ events when present.
 
 ```json
 { "schemaVersion": 2, "type": "run_start", "runId": "run_20260603_abc123", "sessionId": "zero_20260603100000_abc123", "cwd": "/repo", "provider": "openai", "model": "gpt-4.1", "apiModel": "gpt-4.1" }
-{ "schemaVersion": 2, "type": "reasoning", "runId": "run_20260603_abc123", "delta": "Thinking..." }
 { "schemaVersion": 2, "type": "text", "runId": "run_20260603_abc123", "delta": "..." }
 { "schemaVersion": 2, "type": "tool_call", "runId": "run_20260603_abc123", "id": "call_1", "name": "read_file", "args": { "path": "README.md" }, "sideEffect": "read" }
 { "schemaVersion": 2, "type": "permission_request", "runId": "run_20260603_abc123", "id": "call_2", "name": "write_file", "action": "prompt", "permission": "prompt", "permissionMode": "ask", "sideEffect": "write", "reason": "Creates or overwrites files." }
@@ -52,10 +51,6 @@ events when present.
 { "schemaVersion": 2, "type": "run_end", "runId": "run_20260603_abc123", "status": "success", "exitCode": 0 }
 ```
 
-`reasoning` events carry live model reasoning/status deltas for providers that
-stream them separately from answer text. They are liveness/progress events only:
-they are not folded into `text` or the final answer.
-
 Permission events may include structured sandbox metadata:
 
 ```json

internal/agent/additional_permissions_validation_test.go

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

internal/agent/async_diagnostics.go

@@ -1,185 +0,0 @@
-package agent
-
-import (
-	"context"
-	"path/filepath"
-	"sort"
-	"strings"
-	"sync"
-	"time"
-)
-
-// Post-edit LSP diagnostics used to run synchronously inside edit_file /
-// write_file: every edit blocked its tool result on a fresh-publish wait with
-// a quiet-period debounce (≥300ms floor that reset on each publish, 10s cap) —
-// the largest recurring latency tax in an edit-heavy session. Collection is
-// now asynchronous: a file is enqueued the moment a mutating tool finishes, a
-// single worker checks it while the rest of the tool batch (and any
-// self-correct verification) runs, and the loop drains completed results just
-// before building the NEXT provider request, appending errors as a user-role
-// nudge. The model always issues another request after an edit turn — it has
-// to read its tool results — so it still sees introduced errors at the same
-// decision point as before, without any tool call stalling on the language
-// server.
-//
-// A file re-edited before its check runs is checked once in its final state
-// (the checker re-reads the file); a file re-edited after its check completed
-// is re-enqueued and the newer result wins. When the worker is still busy at
-// drain time, the drain gives up after a short wait and the results are
-// delivered on the following turn instead — they stay accurate because any
-// further edit re-enqueues the file.
-
-// asyncDiagnosticsDrainTimeout bounds how long a turn waits on the in-flight
-// check before deferring delivery to the next turn. Most checks finish well
-// under it (debounce floor + analysis); a cold language server on a large
-// repo does not get to stall the loop the way the old inline 10s cap could.
-// A var so tests can shorten the wait.
-var asyncDiagnosticsDrainTimeout = 3 * time.Second
-
-// asyncDiagnosticsFinalDrainTimeout is the wait used when the run is about to
-// FINALIZE (natural completion or the max-turns summary): there is no later
-// turn to defer to, so the gate waits out the old inline-era budget rather
-// than silently dropping an error the last edit introduced. A var so tests
-// can shorten the wait.
-var asyncDiagnosticsFinalDrainTimeout = 10 * time.Second
-
-// asyncDiagnosticsNudge prefixes the drained diagnostics blocks; phrased like
-// the old inline block so the model reacts the same way.
-const asyncDiagnosticsNudge = "Diagnostics after your recent edits (fix any errors you introduced):\n"
-
-type asyncDiagnostics struct {
-	check         func(context.Context, string) string
-	workspaceRoot string
-
-	mu      sync.Mutex
-	queue   []string
-	queued  map[string]bool
-	results map[string]string
-	// working is non-nil while the worker goroutine runs and is closed when it
-	// exits, so drain can wait for quiescence without polling.
-	working chan struct{}
-}
-
-// newAsyncDiagnostics returns nil when check is nil, and every method on a nil
-// receiver is a no-op — callers wire it unconditionally.
-func newAsyncDiagnostics(check func(context.Context, string) string, workspaceRoot string) *asyncDiagnostics {
-	if check == nil {
-		return nil
-	}
-	return &asyncDiagnostics{
-		check:         check,
-		workspaceRoot: workspaceRoot,
-		queued:        map[string]bool{},
-		results:       map[string]string{},
-	}
-}
-
-// enqueue schedules changed files for a background check. Paths are
-// workspace-relative from Result.ChangedFiles (absolute when under a granted
-// extra write root), mirroring SelfCorrector's resolution.
-func (diagnostics *asyncDiagnostics) enqueue(ctx context.Context, files []string) {
-	if diagnostics == nil || len(files) == 0 {
-		return
-	}
-	diagnostics.mu.Lock()
-	defer diagnostics.mu.Unlock()
-	for _, file := range files {
-		path := diagnostics.absPath(file)
-		if diagnostics.queued[path] {
-			continue
-		}
-		diagnostics.queued[path] = true
-		// A completed result for this file describes a pre-edit state now.
-		delete(diagnostics.results, path)
-		diagnostics.queue = append(diagnostics.queue, path)
-	}
-	if diagnostics.working == nil && len(diagnostics.queue) > 0 {
-		done := make(chan struct{})
-		diagnostics.working = done
-		go diagnostics.work(ctx, done)
-	}
-}
-
-func (diagnostics *asyncDiagnostics) work(ctx context.Context, done chan struct{}) {
-	defer close(done)
-	for {
-		diagnostics.mu.Lock()
-		if len(diagnostics.queue) == 0 || ctx.Err() != nil {
-			diagnostics.working = nil
-			diagnostics.mu.Unlock()
-			return
-		}
-		path := diagnostics.queue[0]
-		diagnostics.queue = diagnostics.queue[1:]
-		// Un-mark before checking so an edit that lands DURING the check
-		// re-enqueues the file and it is checked again in its final state.
-		delete(diagnostics.queued, path)
-		diagnostics.mu.Unlock()
-
-		block := diagnostics.check(ctx, path)
-
-		diagnostics.mu.Lock()
-		if block != "" {
-			diagnostics.results[path] = block
-		} else {
-			delete(diagnostics.results, path)
-		}
-		diagnostics.mu.Unlock()
-	}
-}
-
-// drain waits briefly for the worker to go quiet, then formats and consumes
-// all completed error blocks as one nudge. Returns "" when there is nothing
-// to report or the worker is still busy (results then surface next turn).
-func (diagnostics *asyncDiagnostics) drain(ctx context.Context) string {
-	return diagnostics.drainWithin(ctx, asyncDiagnosticsDrainTimeout)
-}
-
-// drainFinal is drain with the finalization budget: called before the run's
-// last model request, where an undelivered result would otherwise be lost.
-func (diagnostics *asyncDiagnostics) drainFinal(ctx context.Context) string {
-	return diagnostics.drainWithin(ctx, asyncDiagnosticsFinalDrainTimeout)
-}
-
-func (diagnostics *asyncDiagnostics) drainWithin(ctx context.Context, timeout time.Duration) string {
-	if diagnostics == nil {
-		return ""
-	}
-	diagnostics.mu.Lock()
-	busy := diagnostics.working
-	diagnostics.mu.Unlock()
-	if busy != nil {
-		timer := time.NewTimer(timeout)
-		defer timer.Stop()
-		select {
-		case <-busy:
-		case <-timer.C:
-			return ""
-		case <-ctx.Done():
-			return ""
-		}
-	}
-	diagnostics.mu.Lock()
-	defer diagnostics.mu.Unlock()
-	if len(diagnostics.results) == 0 {
-		return ""
-	}
-	paths := make([]string, 0, len(diagnostics.results))
-	for path := range diagnostics.results {
-		paths = append(paths, path)
-	}
-	sort.Strings(paths)
-	blocks := make([]string, 0, len(paths))
-	for _, path := range paths {
-		blocks = append(blocks, diagnostics.results[path])
-	}
-	diagnostics.results = map[string]string{}
-	return asyncDiagnosticsNudge + strings.Join(blocks, "\n")
-}
-
-func (diagnostics *asyncDiagnostics) absPath(path string) string {
-	if filepath.IsAbs(path) {
-		return path
-	}
-	return filepath.Join(diagnostics.workspaceRoot, path)
-}

internal/agent/async_diagnostics_test.go

@@ -1,338 +0,0 @@
-package agent
-
-import (
-	"context"
-	"path/filepath"
-	"strings"
-	"sync"
-	"testing"
-	"time"
-
-	"github.com/Gitlawb/zero/internal/tools"
-	"github.com/Gitlawb/zero/internal/zeroruntime"
-)
-
-func TestAsyncDiagnosticsNilCollectorNoOps(t *testing.T) {
-	var diagnostics *asyncDiagnostics
-	if diagnostics != newAsyncDiagnostics(nil, "/ws") {
-		t.Fatal("nil check must yield a nil collector")
-	}
-	diagnostics.enqueue(context.Background(), []string{"a.go"})
-	if nudge := diagnostics.drain(context.Background()); nudge != "" {
-		t.Fatalf("nil collector drain = %q, want empty", nudge)
-	}
-}
-
-func TestAsyncDiagnosticsCollectsAndDrainsOnce(t *testing.T) {
-	// A real absolute root: a literal "/ws" is not filepath.IsAbs on Windows
-	// (no drive letter), which is exactly what the assertions below check.
-	root := t.TempDir()
-	var mu sync.Mutex
-	var checked []string
-	check := func(_ context.Context, absPath string) string {
-		mu.Lock()
-		checked = append(checked, absPath)
-		mu.Unlock()
-		if filepath.Base(absPath) == "clean.go" {
-			return ""
-		}
-		return "ERR " + filepath.Base(absPath)
-	}
-	diagnostics := newAsyncDiagnostics(check, root)
-	diagnostics.enqueue(context.Background(), []string{"broken.go", "clean.go"})
-
-	nudge := diagnostics.drain(context.Background())
-	if !strings.HasPrefix(nudge, asyncDiagnosticsNudge) {
-		t.Fatalf("nudge missing prefix: %q", nudge)
-	}
-	if !strings.Contains(nudge, "ERR broken.go") || strings.Contains(nudge, "clean.go") {
-		t.Fatalf("nudge = %q, want broken.go errors only", nudge)
-	}
-	mu.Lock()
-	for _, path := range checked {
-		if !filepath.IsAbs(path) || !strings.HasPrefix(path, root+string(filepath.Separator)) {
-			t.Fatalf("check received %q, want path under workspace root %q", path, root)
-		}
-	}
-	mu.Unlock()
-	if second := diagnostics.drain(context.Background()); second != "" {
-		t.Fatalf("second drain = %q, want empty (results are consumed)", second)
-	}
-}
-
-// A check still running at drain time defers delivery to the next drain
-// instead of blocking the turn.
-func TestAsyncDiagnosticsSlowCheckDefersToNextDrain(t *testing.T) {
-	previous := asyncDiagnosticsDrainTimeout
-	asyncDiagnosticsDrainTimeout = 20 * time.Millisecond
-	defer func() { asyncDiagnosticsDrainTimeout = previous }()
-
-	release := make(chan struct{})
-	check := func(_ context.Context, absPath string) string {
-		<-release
-		return "ERR " + filepath.Base(absPath)
-	}
-	diagnostics := newAsyncDiagnostics(check, "/ws")
-	diagnostics.enqueue(context.Background(), []string{"slow.go"})
-
-	start := time.Now()
-	if nudge := diagnostics.drain(context.Background()); nudge != "" {
-		t.Fatalf("drain during in-flight check = %q, want empty", nudge)
-	}
-	if elapsed := time.Since(start); elapsed > time.Second {
-		t.Fatalf("drain blocked %v, want bounded by the (shortened) timeout", elapsed)
-	}
-
-	close(release)
-	deadline := time.Now().Add(2 * time.Second)
-	for {
-		if nudge := diagnostics.drain(context.Background()); nudge != "" {
-			if !strings.Contains(nudge, "ERR slow.go") {
-				t.Fatalf("deferred nudge = %q", nudge)
-			}
-			return
-		}
-		if time.Now().After(deadline) {
-			t.Fatal("deferred diagnostics never delivered")
-		}
-		time.Sleep(5 * time.Millisecond)
-	}
-}
-
-// Re-enqueueing a file after its check completed replaces the stale result.
-func TestAsyncDiagnosticsReEditReplacesResult(t *testing.T) {
-	var mu sync.Mutex
-	response := "ERR old"
-	check := func(context.Context, string) string {
-		mu.Lock()
-		defer mu.Unlock()
-		return response
-	}
-	diagnostics := newAsyncDiagnostics(check, "/ws")
-
-	diagnostics.enqueue(context.Background(), []string{"a.go"})
-	waitForIdle(t, diagnostics)
-	mu.Lock()
-	response = "ERR new"
-	mu.Unlock()
-	diagnostics.enqueue(context.Background(), []string{"a.go"})
-
-	nudge := diagnostics.drain(context.Background())
-	if !strings.Contains(nudge, "ERR new") || strings.Contains(nudge, "ERR old") {
-		t.Fatalf("nudge = %q, want only the re-check result", nudge)
-	}
-}
-
-func waitForIdle(t *testing.T, diagnostics *asyncDiagnostics) {
-	t.Helper()
-	deadline := time.Now().Add(2 * time.Second)
-	for {
-		diagnostics.mu.Lock()
-		busy := diagnostics.working
-		diagnostics.mu.Unlock()
-		if busy == nil {
-			return
-		}
-		if time.Now().After(deadline) {
-			t.Fatal("worker never went idle")
-		}
-		time.Sleep(2 * time.Millisecond)
-	}
-}
-
-// changedFilesTool is a fake mutating tool reporting a changed file without
-// touching the filesystem.
-type changedFilesTool struct{}
-
-func (changedFilesTool) Name() string        { return "fake_edit" }
-func (changedFilesTool) Description() string { return "test mutating tool" }
-func (changedFilesTool) Parameters() tools.Schema {
-	return tools.Schema{Type: "object", Properties: map[string]tools.PropertySchema{}}
-}
-func (changedFilesTool) Safety() tools.Safety {
-	return tools.Safety{SideEffect: tools.SideEffectWrite, Permission: tools.PermissionAllow, Reason: "test"}
-}
-func (changedFilesTool) Run(context.Context, map[string]any) tools.Result {
-	return tools.Result{Status: tools.StatusOK, Output: "edited", ChangedFiles: []string{"main.go"}}
-}
-
-// End-to-end through Run: an edit turn does NOT carry diagnostics in the tool
-// result (the old inline path), but the next request contains the background
-// diagnostics nudge, before the model finalizes.
-func TestRunDeliversAsyncDiagnosticsNudgeNextTurn(t *testing.T) {
-	registry := tools.NewRegistry()
-	registry.Register(changedFilesTool{})
-	provider := &mockProvider{
-		turns: [][]zeroruntime.StreamEvent{
-			{
-				{Type: zeroruntime.StreamEventToolCallStart, ToolCallID: "call-1", ToolName: "fake_edit"},
-				{Type: zeroruntime.StreamEventToolCallDelta, ToolCallID: "call-1", ArgumentsFragment: `{}`},
-				{Type: zeroruntime.StreamEventToolCallEnd, ToolCallID: "call-1"},
-				{Type: zeroruntime.StreamEventDone},
-			},
-			{
-				{Type: zeroruntime.StreamEventText, Content: "done"},
-				{Type: zeroruntime.StreamEventDone},
-			},
-		},
-	}
-	root := t.TempDir()
-	var checkedPath string
-	var mu sync.Mutex
-
-	result, err := Run(context.Background(), "fix main.go", provider, Options{
-		Registry: registry,
-		Cwd:      root,
-		FileDiagnostics: func(_ context.Context, absPath string) string {
-			mu.Lock()
-			checkedPath = absPath
-			mu.Unlock()
-			return "main.go:1:1 error: boom"
-		},
-	})
-	if err != nil {
-		t.Fatal(err)
-	}
-	if result.FinalAnswer != "done" {
-		t.Fatalf("final answer = %q", result.FinalAnswer)
-	}
-	if len(provider.requests) != 2 {
-		t.Fatalf("expected 2 provider turns, got %d", len(provider.requests))
-	}
-
-	// The tool result itself must NOT block on / embed diagnostics.
-	for _, message := range provider.requests[1].Messages {
-		if message.Role == zeroruntime.MessageRoleTool && strings.Contains(message.Content, "boom") {
-			t.Fatalf("diagnostics leaked into the tool result: %q", message.Content)
-		}
-	}
-	// The nudge must be present in the second request as a user message.
-	found := false
-	for _, message := range provider.requests[1].Messages {
-		if message.Role == zeroruntime.MessageRoleUser && strings.HasPrefix(message.Content, asyncDiagnosticsNudge) {
-			if !strings.Contains(message.Content, "boom") {
-				t.Fatalf("nudge missing diagnostics: %q", message.Content)
-			}
-			found = true
-		}
-	}
-	if !found {
-		t.Fatal("no async diagnostics nudge in the follow-up request")
-	}
-	mu.Lock()
-	defer mu.Unlock()
-	if want := filepath.Join(root, "main.go"); checkedPath != want {
-		t.Fatalf("checked path = %q, want %q", checkedPath, want)
-	}
-}
-
-// When the run hits the maxTurns ceiling right after an edit turn, the
-// final-answer request must still carry the diagnostics nudge — otherwise an
-// error introduced by the last edit would go unreported in the summary.
-func TestRunDrainsAsyncDiagnosticsBeforeMaxTurnsFinalAnswer(t *testing.T) {
-	registry := tools.NewRegistry()
-	registry.Register(changedFilesTool{})
-	provider := &mockProvider{
-		turns: [][]zeroruntime.StreamEvent{
-			{
-				{Type: zeroruntime.StreamEventToolCallStart, ToolCallID: "call-1", ToolName: "fake_edit"},
-				{Type: zeroruntime.StreamEventToolCallDelta, ToolCallID: "call-1", ArgumentsFragment: `{}`},
-				{Type: zeroruntime.StreamEventToolCallEnd, ToolCallID: "call-1"},
-				{Type: zeroruntime.StreamEventDone},
-			},
-			{
-				{Type: zeroruntime.StreamEventText, Content: "summary"},
-				{Type: zeroruntime.StreamEventDone},
-			},
-		},
-	}
-
-	result, err := Run(context.Background(), "fix main.go", provider, Options{
-		Registry: registry,
-		Cwd:      t.TempDir(),
-		MaxTurns: 1,
-		FileDiagnostics: func(context.Context, string) string {
-			return "main.go:1:1 error: boom"
-		},
-	})
-	if err != nil {
-		t.Fatal(err)
-	}
-	if result.FinalAnswer != "summary" {
-		t.Fatalf("final answer = %q", result.FinalAnswer)
-	}
-	if len(provider.requests) != 2 {
-		t.Fatalf("expected the max-turns final-answer request, got %d requests", len(provider.requests))
-	}
-	found := false
-	for _, message := range provider.requests[1].Messages {
-		if message.Role == zeroruntime.MessageRoleUser && strings.HasPrefix(message.Content, asyncDiagnosticsNudge) {
-			found = true
-		}
-	}
-	if !found {
-		t.Fatal("max-turns final-answer request missing the diagnostics nudge")
-	}
-}
-
-// When the model finalizes while a slow check is still in flight (the
-// per-turn drain missed it), the finalization gate must wait it out and give
-// the model one more turn with the nudge instead of dropping the errors.
-func TestRunFinalizationGateDeliversLateDiagnostics(t *testing.T) {
-	previous := asyncDiagnosticsDrainTimeout
-	asyncDiagnosticsDrainTimeout = time.Millisecond
-	defer func() { asyncDiagnosticsDrainTimeout = previous }()
-
-	registry := tools.NewRegistry()
-	registry.Register(changedFilesTool{})
-	provider := &mockProvider{
-		turns: [][]zeroruntime.StreamEvent{
-			{
-				{Type: zeroruntime.StreamEventToolCallStart, ToolCallID: "call-1", ToolName: "fake_edit"},
-				{Type: zeroruntime.StreamEventToolCallDelta, ToolCallID: "call-1", ArgumentsFragment: `{}`},
-				{Type: zeroruntime.StreamEventToolCallEnd, ToolCallID: "call-1"},
-				{Type: zeroruntime.StreamEventDone},
-			},
-			{
-				{Type: zeroruntime.StreamEventText, Content: "done"},
-				{Type: zeroruntime.StreamEventDone},
-			},
-			{
-				{Type: zeroruntime.StreamEventText, Content: "done after fix"},
-				{Type: zeroruntime.StreamEventDone},
-			},
-		},
-	}
-
-	result, err := Run(context.Background(), "fix main.go", provider, Options{
-		Registry: registry,
-		Cwd:      t.TempDir(),
-		FileDiagnostics: func(context.Context, string) string {
-			// Slower than the (shortened) per-turn drain, well under the
-			// finalization budget.
-			time.Sleep(100 * time.Millisecond)
-			return "main.go:1:1 error: boom"
-		},
-	})
-	if err != nil {
-		t.Fatal(err)
-	}
-	if result.FinalAnswer != "done after fix" {
-		t.Fatalf("final answer = %q, want the post-nudge answer", result.FinalAnswer)
-	}
-	if len(provider.requests) != 3 {
-		t.Fatalf("expected a third request carrying the late nudge, got %d requests", len(provider.requests))
-	}
-	found := false
-	for _, message := range provider.requests[2].Messages {
-		if message.Role == zeroruntime.MessageRoleUser && strings.HasPrefix(message.Content, asyncDiagnosticsNudge) {
-			if !strings.Contains(message.Content, "boom") {
-				t.Fatalf("nudge missing diagnostics: %q", message.Content)
-			}
-			found = true
-		}
-	}
-	if !found {
-		t.Fatal("finalization gate did not deliver the late diagnostics nudge")
-	}
-}

internal/agent/command_prefix.go

@@ -2,7 +2,6 @@ package agent
 
 import (
 	"fmt"
-	"runtime"
 	"strings"
 
 	"github.com/Gitlawb/zero/internal/sandbox"
@@ -28,20 +27,10 @@ func proposedCommandPrefix(toolName string, args map[string]any) []string {
 		}
 		return nil
 	}
-	// Only propose approving a prefix of one segment when every other segment
-	// in the command is independently known-safe. Once a prefix is approved,
-	// shellExecutionArgsForApproval escalates the whole command (every
-	// segment, not just the approved one) to bypass the sandbox, so offering a
-	// prefix that leaves an MSYS-prone (or otherwise unsafe) segment uncovered
-	// would let that segment run unsandboxed without ever being reviewed.
-	for index, tokens := range segments {
-		if knownSafeCommandSegment(tokens) {
-			continue
+	for _, tokens := range segments {
+		if !knownSafeCommandSegment(tokens) && sandbox.ValidCommandPrefix(tokens) {
+			return append([]string(nil), tokens...)
 		}
-		if !sandbox.ValidCommandPrefix(tokens) || !otherSegmentsKnownSafe(segments, index) {
-			return nil
-		}
-		return append([]string(nil), tokens...)
 	}
 	if len(segments) == 0 || !sandbox.ValidCommandPrefix(segments[0]) {
 		return nil
@@ -49,20 +38,6 @@ func proposedCommandPrefix(toolName string, args map[string]any) []string {
 	return append([]string(nil), segments[0]...)
 }
 
-// otherSegmentsKnownSafe reports whether every segment other than the one at
-// skip is known-safe on its own.
-func otherSegmentsKnownSafe(segments [][]string, skip int) bool {
-	for index, tokens := range segments {
-		if index == skip {
-			continue
-		}
-		if !knownSafeCommandSegment(tokens) {
-			return false
-		}
-	}
-	return true
-}
-
 func matchCommandPrefix(toolName string, args map[string]any, options Options) (sandbox.CommandPrefixGrant, bool, bool) {
 	if !isShellCommandTool(toolName) || options.Sandbox == nil {
 		return sandbox.CommandPrefixGrant{}, false, false
@@ -193,6 +168,10 @@ func cleanPrefixRule(prefix []string) []string {
 	return cleaned
 }
 
+func safeRequestedPrefix(prefix []string, command []string) bool {
+	return safeRequestedPrefixForSegments(prefix, [][]string{command})
+}
+
 func safeRequestedPrefixForSegments(prefix []string, segments [][]string) bool {
 	if len(prefix) == 0 || !sandbox.ValidCommandPrefix(prefix) {
 		return false
@@ -217,6 +196,14 @@ func safeRequestedPrefixForSegments(prefix []string, segments [][]string) bool {
 	return matched
 }
 
+func safeShellCommandTokens(command string) ([]string, bool) {
+	segments, ok := safeShellCommandSegments(command)
+	if !ok || len(segments) != 1 {
+		return nil, false
+	}
+	return segments[0], true
+}
+
 func safeShellCommandSegments(command string) ([][]string, bool) {
 	command = strings.TrimSpace(command)
 	if command == "" {
@@ -288,11 +275,7 @@ func knownSafeCommandSegment(command []string) bool {
 	if len(command) == 0 {
 		return false
 	}
-	name := commandName(command[0])
-	if runtime.GOOS == "windows" && tools.MsysProneCommandName(name) {
-		return false
-	}
-	switch name {
+	switch commandName(command[0]) {
 	case "cat", "cd", "cut", "echo", "expr", "false", "grep", "head", "id",
 		"ls", "nl", "paste", "pwd", "rev", "seq", "stat", "tail", "tr",
 		"true", "uname", "uniq", "wc", "which", "whoami":

internal/agent/command_prefix_test.go

@@ -1,11 +1,9 @@
 package agent
 
 import (
-	"runtime"
 	"testing"
 
 	"github.com/Gitlawb/zero/internal/sandbox"
-	"github.com/Gitlawb/zero/internal/tools"
 )
 
 func TestProposedCommandPrefixUsesSafeSimpleCommands(t *testing.T) {
@@ -37,37 +35,12 @@ func TestProposedCommandPrefixHonorsValidatedRequestedPrefix(t *testing.T) {
 
 func TestProposedCommandPrefixSupportsSegmentedCommands(t *testing.T) {
 	got := proposedCommandPrefix("bash", map[string]any{"command": "ps aux | head -5"})
-	if runtime.GOOS == "windows" {
-		// head is MSYS-prone on Windows (#458), so proposedCommandPrefix must
-		// not offer "ps aux" as a reusable prefix here: approving it would
-		// escalate the whole command, including the uncovered head segment,
-		// to bypass the sandbox unreviewed. See
-		// TestProposedCommandPrefixRejectsPrefixLeavingUnsafeTailUncovered for
-		// the platform-independent regression coverage of this behavior.
-		if got != nil {
-			t.Fatalf("expected no prefix on Windows because head is MSYS-prone, got %#v", got)
-		}
-		return
-	}
 	want := []string{"ps", "aux"}
 	if !equalStringSlices(got, want) {
 		t.Fatalf("prefix = %#v, want %#v", got, want)
 	}
 }
 
-// TestProposedCommandPrefixRejectsPrefixLeavingUnsafeTailUncovered guards
-// against proposedCommandPrefix offering to approve one segment of a
-// multi-segment command (e.g. "ps aux") while a different segment (e.g. "npm
-// install") is not known-safe. shellExecutionArgsForApproval escalates the
-// entire command once any prefix is approved, so an uncovered unsafe segment
-// would bypass the sandbox unreviewed. Uses npm, which is never known-safe on
-// any platform, so the assertion does not depend on runtime.GOOS.
-func TestProposedCommandPrefixRejectsPrefixLeavingUnsafeTailUncovered(t *testing.T) {
-	if got := proposedCommandPrefix("bash", map[string]any{"command": "ps aux && npm install"}); got != nil {
-		t.Fatalf("expected no prefix because npm segment is not known-safe, got %#v", got)
-	}
-}
-
 func TestProposedCommandPrefixHonorsRequestedPrefixAcrossSegments(t *testing.T) {
 	got := proposedCommandPrefix("bash", map[string]any{
 		"command":     "git status --short && git status --branch",
@@ -147,35 +120,13 @@ func TestProposedCommandPrefixRejectsUnsafeLaunchers(t *testing.T) {
 func TestMatchCommandPrefixCoversSegmentedCommandWithSafeTail(t *testing.T) {
 	engine := sandbox.NewEngine(sandbox.EngineOptions{WorkspaceRoot: t.TempDir()})
 	engine.GrantCommandPrefixForSession("bash", []string{"ps", "aux"})
-	// head is MSYS-prone on Windows (#458) and must not count as a known-safe tail.
-	command := "ps aux | head -5"
-	if runtime.GOOS == "windows" {
-		command = "ps aux | echo ok"
-	}
 
-	grant, ok, session := matchCommandPrefix("bash", map[string]any{"command": command}, Options{Sandbox: engine})
+	grant, ok, session := matchCommandPrefix("bash", map[string]any{"command": "ps aux | head -5"}, Options{Sandbox: engine})
 	if !ok || !session || !equalStringSlices(grant.Prefix, []string{"ps", "aux"}) {
 		t.Fatalf("match = %#v ok=%v session=%v, want session ps aux prefix", grant, ok, session)
 	}
 }
 
-func TestKnownSafeCommandSegmentRejectsMsysProneOnWindows(t *testing.T) {
-	if runtime.GOOS != "windows" {
-		t.Skip("windows-only known-safe MSYS guard")
-	}
-	for _, command := range [][]string{{"head", "-5"}, {"cat", "file.txt"}, {"grep", "pat"}} {
-		if knownSafeCommandSegment(command) {
-			t.Fatalf("expected %q to be unsafe on Windows, got known-safe", command)
-		}
-	}
-	if !knownSafeCommandSegment([]string{"echo", "ok"}) {
-		t.Fatal("expected echo to remain known-safe on Windows")
-	}
-	if !tools.MsysProneCommandName("head") {
-		t.Fatal("expected head to be MSYS-prone")
-	}
-}
-
 func TestMatchCommandPrefixRejectsUncoveredSegment(t *testing.T) {
 	engine := sandbox.NewEngine(sandbox.EngineOptions{WorkspaceRoot: t.TempDir()})
 	engine.GrantCommandPrefixForSession("bash", []string{"ps", "aux"})

internal/agent/compaction.go

@@ -21,17 +21,12 @@ import (
 // the agent loop owns the provider wiring.
 
 // defaultCompactionPreserveLast is how many trailing messages are kept verbatim
-// when the caller does not specify a preserve count. Kept in sync with the replay
-// reconstruction default in internal/sessions/replay.go.
-const defaultCompactionPreserveLast = 6
+// when the caller does not specify a preserve count.
+const defaultCompactionPreserveLast = 8
 
 // compactionTriggerRatio is the fraction of the context window at which
-// proactive compaction kicks in (top of each turn). NOTE: this is speculative
-// tuning — validate against the per-turn latency/compaction metrics (roadmap 5.2)
-// before trusting it. Measured fixed overhead is ~7.4k tokens (not the ~16k the
-// roadmap assumed), so context fills slower; if data shows 0.7 triggers redundant
-// summarization, raise it back toward 0.8.
-const compactionTriggerRatio = 0.7
+// proactive compaction kicks in (top of each turn).
+const compactionTriggerRatio = 0.8
 
 // summaryLabel prefixes the injected summary so it is unmistakable in the
 // transcript (and so tests can assert on it).
@@ -325,43 +320,6 @@ type compactionState struct {
 	// OnText is deliberately NOT forwarded (compaction stays invisible to the user),
 	// but its token COST must still be counted so usage reports and budgets include it.
 	onUsage func(Usage)
-
-	// calibrationRatio scales the raw byte/4 token estimate toward the provider's
-	// real prompt-token count. ApproxTextTokens over-counts code-heavy content by
-	// ~15-20%, which would trip compaction early (at ~60% of true capacity). It
-	// 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
-}
-
-// calibrate folds one turn's (rawEstimate, actualPromptTokens) sample into the
-// running calibration ratio. A single sample is clamped to a sane band so an
-// outlier (a huge cache-read turn, a provider-overhead spike) can't skew the
-// estimate enough to disable or thrash compaction.
-func (state *compactionState) calibrate(rawEstimate int, actualPromptTokens int) {
-	if !state.enabled || rawEstimate <= 0 || actualPromptTokens <= 0 {
-		return
-	}
-	sample := float64(actualPromptTokens) / float64(rawEstimate)
-	if sample < 0.5 {
-		sample = 0.5
-	} else if sample > 2.0 {
-		sample = 2.0
-	}
-	if state.calibrationRatio <= 0 {
-		state.calibrationRatio = 1.0
-	}
-	const alpha = 0.3 // weight on the newest sample; smooths jitter across turns
-	state.calibrationRatio = state.calibrationRatio*(1-alpha) + sample*alpha
-}
-
-// calibratedTokens applies the learned ratio to a raw estimate. Before any sample
-// arrives (ratio unset) it returns the raw estimate unchanged.
-func (state *compactionState) calibratedTokens(raw int) int {
-	if state.calibrationRatio <= 0 {
-		return raw
-	}
-	return int(float64(raw) * state.calibrationRatio)
 }
 
 func newCompactionState(options Options) *compactionState {
@@ -390,7 +348,7 @@ func (state *compactionState) maybeCompact(
 	// the messages; both the threshold check and the shrink check below use the
 	// same term so they stay consistent.
 	toolTokens := estimateToolDefTokens(tools)
-	size := state.calibratedTokens(estimateTokens(messages) + toolTokens)
+	size := estimateTokens(messages) + toolTokens
 	if size <= state.threshold {
 		return messages
 	}
@@ -407,7 +365,7 @@ func (state *compactionState) maybeCompact(
 	// entirely and preserve recent turns verbatim.
 	if pruned, reclaimed := pruneStaleToolOutput(messages, state.preserveLast); reclaimed > 0 {
 		messages = pruned
-		size = state.calibratedTokens(estimateTokens(messages) + toolTokens)
+		size = estimateTokens(messages) + toolTokens
 		if size <= state.threshold {
 			state.lowWaterMark = size
 			return messages
@@ -423,7 +381,7 @@ func (state *compactionState) maybeCompact(
 		// later turn) can try again; we never drop messages on failure here.
 		return messages
 	}
-	newSize := state.calibratedTokens(estimateTokens(compacted) + toolTokens)
+	newSize := estimateTokens(compacted) + toolTokens
 	if newSize >= size {
 		// Compaction did not actually shrink anything (e.g. nothing to
 		// summarize). Leave the history untouched and don't churn next turn.
@@ -481,7 +439,7 @@ func (state *compactionState) recover(
 	// the SAME combined (messages + tool-defs) domain maybeCompact uses, so the
 	// proactive shrink-guard compares like with like.
 	state.reactiveAttempted = true
-	state.lowWaterMark = state.calibratedTokens(estimateTokens(result) + estimateToolDefTokens(tools))
+	state.lowWaterMark = estimateTokens(result) + estimateToolDefTokens(tools)
 	return result, true, nil
 }
 

internal/agent/compaction_calibrate_test.go

@@ -1,50 +0,0 @@
-package agent
-
-import "testing"
-
-func TestCalibrationConvergesTowardActual(t *testing.T) {
-	state := &compactionState{enabled: true}
-
-	// Before any sample, the estimate is unchanged.
-	if got := state.calibratedTokens(1000); got != 1000 {
-		t.Fatalf("uncalibrated tokens = %d, want 1000", got)
-	}
-
-	// The estimator over-counts: our raw estimate is 1000 but the provider reports
-	// 850 (a 0.85 ratio). Feeding that sample repeatedly should pull the ratio
-	// toward 0.85, so a 1000-token raw estimate calibrates downward.
-	for range 20 {
-		state.calibrate(1000, 850)
-	}
-	got := state.calibratedTokens(1000)
-	if got >= 1000 || got < 820 || got > 880 {
-		t.Fatalf("calibrated tokens = %d, want ~850 after convergence", got)
-	}
-}
-
-func TestCalibrateIgnoresDegenerateSamples(t *testing.T) {
-	state := &compactionState{enabled: true}
-	state.calibrate(0, 500) // zero estimate
-	state.calibrate(500, 0) // zero actual
-	if state.calibrationRatio != 0 {
-		t.Fatalf("degenerate samples must not move the ratio, got %v", state.calibrationRatio)
-	}
-	// Disabled state never calibrates.
-	disabled := &compactionState{enabled: false}
-	disabled.calibrate(1000, 850)
-	if disabled.calibrationRatio != 0 {
-		t.Fatalf("disabled compaction must not calibrate, got %v", disabled.calibrationRatio)
-	}
-}
-
-func TestCalibrateClampsOutliers(t *testing.T) {
-	state := &compactionState{enabled: true}
-	// A wild outlier (10x) is clamped to 2.0, so one bad sample can't blow up the
-	// ratio and disable compaction.
-	for range 50 {
-		state.calibrate(1000, 10000)
-	}
-	if state.calibrationRatio > 2.0 {
-		t.Fatalf("ratio should be clamped at 2.0, got %v", state.calibrationRatio)
-	}
-}

internal/agent/compaction_preserve.go

@@ -20,16 +20,6 @@ const (
 	toolNameUpdatePlan = "update_plan"
 	toolNameToolSearch = "tool_search"
 	toolNameSkill      = "skill"
-	toolNameWriteFile  = "write_file"
-	toolNameEditFile   = "edit_file"
-)
-
-// maxRecentEdits caps how many edited files are carried across a compaction, and
-// maxEditNoteBytes caps each edit's one-line note, so a long editing run can't
-// bloat the preserved-state block.
-const (
-	maxRecentEdits   = 20
-	maxEditNoteBytes = 160
 )
 
 const (
@@ -110,123 +100,12 @@ func formatPlanArguments(arguments string) string {
 }
 
 // skillEntry is a named preserved body. It began as loaded-skill state and is
-// reused for loaded tools, project instruction blocks, and recent file edits.
+// reused for loaded tools and project instruction blocks.
 type skillEntry struct {
 	name string
 	body string
 }
 
-// recentEdits returns the files mutated by write_file/edit_file calls in messages
-// — latest note per path, in last-seen order — as skillEntry{name: path, body:
-// note}. After compaction elides the editing turns, this tells the model WHAT it
-// changed in each file (from the tool's result) so it need not re-read to
-// rediscover its own footprint. Capped at maxRecentEdits paths.
-//
-// Ordering is by LAST edit, not first: re-editing a file moves it to the newest
-// position so the tail cap below keeps the file the model most recently touched
-// rather than an earlier, now-stale entry.
-func recentEdits(messages []zeroruntime.Message) []skillEntry {
-	pathByID := map[string]string{}
-	sequence := make([]string, 0)
-	for _, message := range messages {
-		for _, call := range message.ToolCalls {
-			if call.Name != toolNameWriteFile && call.Name != toolNameEditFile {
-				continue
-			}
-			path := editPathFromArguments(call.Arguments)
-			if path == "" {
-				continue
-			}
-			if call.ID != "" {
-				pathByID[call.ID] = path
-			}
-			sequence = append(sequence, path)
-		}
-	}
-	order := lastSeenOrder(sequence)
-	if len(order) == 0 {
-		return nil
-	}
-
-	noteByPath := map[string]string{}
-	for _, message := range messages {
-		if message.Role != zeroruntime.MessageRoleTool || message.ToolCallID == "" {
-			continue
-		}
-		if path, ok := pathByID[message.ToolCallID]; ok {
-			noteByPath[path] = editNote(message.Content)
-		}
-	}
-
-	// Keep the most recent maxRecentEdits paths (the tail of last-seen order).
-	if len(order) > maxRecentEdits {
-		order = order[len(order)-maxRecentEdits:]
-	}
-	entries := make([]skillEntry, 0, len(order))
-	for _, path := range order {
-		entries = append(entries, skillEntry{name: path, body: noteByPath[path]})
-	}
-	return entries
-}
-
-// lastSeenOrder dedupes paths keeping each at its LAST occurrence, preserving
-// chronological order otherwise. A re-edited path therefore lands at the newest
-// position rather than staying pinned to where it first appeared.
-func lastSeenOrder(paths []string) []string {
-	lastIdx := make(map[string]int, len(paths))
-	for i, p := range paths {
-		lastIdx[p] = i
-	}
-	order := make([]string, 0, len(lastIdx))
-	for i, p := range paths {
-		if lastIdx[p] == i {
-			order = append(order, p)
-		}
-	}
-	return order
-}
-
-// editPathFromArguments pulls the target file path from a write_file/edit_file
-// call's JSON arguments (path/file/file_path/filename aliases). Returns "" on
-// malformed arguments or no path.
-func editPathFromArguments(arguments string) string {
-	var parsed struct {
-		Path     string `json:"path"`
-		File     string `json:"file"`
-		FilePath string `json:"file_path"`
-		Filename string `json:"filename"`
-	}
-	if err := json.Unmarshal([]byte(strings.TrimSpace(arguments)), &parsed); err != nil {
-		return ""
-	}
-	for _, candidate := range []string{parsed.Path, parsed.File, parsed.FilePath, parsed.Filename} {
-		if s := strings.TrimSpace(candidate); s != "" {
-			return s
-		}
-	}
-	return ""
-}
-
-// editNote reduces an edit tool's result to a single short line (its first
-// non-empty line, byte-capped on a rune boundary) for the preserved summary.
-func editNote(content string) string {
-	for _, line := range strings.Split(content, "\n") {
-		s := strings.TrimSpace(line)
-		if s == "" {
-			continue
-		}
-		if len(s) > maxEditNoteBytes {
-			limit := maxEditNoteBytes
-			for limit > 0 && !utf8.RuneStart(s[limit]) {
-				limit--
-			}
-			s = s[:limit] + "…"
-		}
-		return s
-	}
-	return ""
-}
-
 // loadedSkills returns the skills loaded via the skill tool in messages — the
 // latest body per name, in first-seen order — matching each skill tool call to
 // its tool result by id.
@@ -431,17 +310,11 @@ func capBody(body string) string {
 // preservedState is the JSON shape of the carried-across-compaction block.
 type preservedState struct {
 	Plan                string                 `json:"plan,omitempty"`
-	RecentEdits         []preservedEdit        `json:"recent_edits,omitempty"`
 	Tools               []preservedTool        `json:"tools,omitempty"`
 	Skills              []preservedSkill       `json:"skills,omitempty"`
 	ProjectInstructions []preservedInstruction `json:"project_instructions,omitempty"`
 }
 
-type preservedEdit struct {
-	Path string `json:"path"`
-	Note string `json:"note,omitempty"`
-}
-
 type preservedTool struct {
 	Name string `json:"name"`
 	Body string `json:"body"`
@@ -474,12 +347,6 @@ func appendPreservedState(summary string, middle []zeroruntime.Message) string {
 		plan = priorState.Plan
 	}
 
-	// Recent edits: merge edits preserved earlier with fresh write_file/edit_file
-	// results in middle (newer note per path wins AND moves to the newest
-	// position), so the tail cap keeps the files the model most recently touched
-	// across repeated compactions rather than dropping a just-re-edited file.
-	edits := capRecentEdits(mergeRecentEdits(preservedEditsToEntries(priorState.RecentEdits), recentEdits(middle)))
-
 	// Tools: preserve deferred tool_search schemas from the transcript. Fresh
 	// loads override older carried copies by name.
 	tools := mergeSkillEntries(preservedToolsToEntries(priorState.Tools), loadedToolSchemas(middle))
@@ -493,76 +360,19 @@ func appendPreservedState(summary string, middle []zeroruntime.Message) string {
 		projectInstructionEntries(middle),
 	)
 
-	if block := formatPreservedState(plan, edits, tools, skills, instructions); block != "" {
+	if block := formatPreservedState(plan, tools, skills, instructions); block != "" {
 		summary += "\n\n" + block
 	}
 	return summary
 }
 
-// mergeRecentEdits overlays fresh edits onto edits preserved by an earlier
-// compaction. Unlike mergeSkillEntries (which keeps refreshed entries in their
-// original slot), a path touched again by a fresh edit MOVES to the newest
-// position and takes the fresh note, so capRecentEdits — which keeps only the
-// most-recent tail — never drops a file the model just re-edited. Paths present
-// only in the older set keep their relative order, ahead of the fresh ones.
-func mergeRecentEdits(older, newer []skillEntry) []skillEntry {
-	if len(newer) == 0 {
-		return older
-	}
-	freshBody := make(map[string]string, len(newer))
-	freshOrder := make([]string, 0, len(newer))
-	for _, e := range newer {
-		if _, ok := freshBody[e.name]; !ok {
-			freshOrder = append(freshOrder, e.name)
-		}
-		freshBody[e.name] = e.body
-	}
-	merged := make([]skillEntry, 0, len(older)+len(freshOrder))
-	// Older entries that were NOT re-edited keep their position, oldest first.
-	for _, e := range older {
-		if _, refreshed := freshBody[e.name]; refreshed {
-			continue // re-appended at its newest position below
-		}
-		merged = append(merged, e)
-	}
-	// Fresh edits follow, in last-seen order, each carrying the fresh note — so
-	// the most recently touched files sit at the tail the cap preserves.
-	for _, name := range freshOrder {
-		merged = append(merged, skillEntry{name: name, body: freshBody[name]})
-	}
-	return merged
-}
-
-// capRecentEdits bounds the preserved edit list to the most recent maxRecentEdits
-// entries after a merge, so repeated compactions can't grow it without limit.
-func capRecentEdits(entries []skillEntry) []skillEntry {
-	if len(entries) > maxRecentEdits {
-		return entries[len(entries)-maxRecentEdits:]
-	}
-	return entries
-}
-
-func preservedEditsToEntries(edits []preservedEdit) []skillEntry {
-	entries := make([]skillEntry, 0, len(edits))
-	for _, e := range edits {
-		if e.Path == "" {
-			continue
-		}
-		entries = append(entries, skillEntry{name: e.Path, body: e.Note})
-	}
-	return entries
-}
-
 // formatPreservedState renders state as the labelled, single-line
 // JSON block. Returns "" when there is nothing to preserve.
-func formatPreservedState(plan string, edits, tools, skills, instructions []skillEntry) string {
-	if plan == "" && len(edits) == 0 && len(tools) == 0 && len(skills) == 0 && len(instructions) == 0 {
+func formatPreservedState(plan string, tools, skills, instructions []skillEntry) string {
+	if plan == "" && len(tools) == 0 && len(skills) == 0 && len(instructions) == 0 {
 		return ""
 	}
 	state := preservedState{Plan: plan}
-	for _, e := range edits {
-		state.RecentEdits = append(state.RecentEdits, preservedEdit{Path: e.name, Note: e.body})
-	}
 	for _, t := range tools {
 		state.Tools = append(state.Tools, preservedTool{Name: t.name, Body: t.body})
 	}

internal/agent/compaction_recent_edits_test.go

@@ -1,121 +0,0 @@
-package agent
-
-import (
-	"fmt"
-	"strings"
-	"testing"
-
-	"github.com/Gitlawb/zero/internal/zeroruntime"
-)
-
-// recentEdits extracts each mutated file's path and a one-line note from the
-// matching tool result, latest note per path in last-seen order.
-func TestRecentEditsExtractsPathsAndNotes(t *testing.T) {
-	messages := []zeroruntime.Message{
-		{Role: zeroruntime.MessageRoleAssistant, ToolCalls: []zeroruntime.ToolCall{
-			{ID: "e1", Name: "write_file", Arguments: `{"path":"internal/foo.go","content":"package foo"}`},
-		}},
-		{Role: zeroruntime.MessageRoleTool, ToolCallID: "e1", Content: "Wrote internal/foo.go (12 lines)"},
-		{Role: zeroruntime.MessageRoleAssistant, ToolCalls: []zeroruntime.ToolCall{
-			{ID: "e2", Name: "edit_file", Arguments: `{"path":"internal/bar.go","old_string":"a","new_string":"b"}`},
-		}},
-		{Role: zeroruntime.MessageRoleTool, ToolCallID: "e2", Content: "Applied edit to internal/bar.go"},
-	}
-
-	edits := recentEdits(messages)
-	if len(edits) != 2 {
-		t.Fatalf("expected 2 edited files, got %d: %#v", len(edits), edits)
-	}
-	if edits[0].name != "internal/foo.go" || !strings.Contains(edits[0].body, "12 lines") {
-		t.Fatalf("first edit = %#v, want foo.go with its note", edits[0])
-	}
-	if edits[1].name != "internal/bar.go" || !strings.Contains(edits[1].body, "Applied edit") {
-		t.Fatalf("second edit = %#v, want bar.go with its note", edits[1])
-	}
-}
-
-// After compaction elides the editing turns, the preserved-state block still
-// names the edited files and what changed, so the model needn't re-read them.
-func TestCompactionPreservesRecentEdits(t *testing.T) {
-	messages := []zeroruntime.Message{
-		{Role: zeroruntime.MessageRoleSystem, Content: "system"},
-		{Role: zeroruntime.MessageRoleUser, Content: "add a flag"},
-		{Role: zeroruntime.MessageRoleAssistant, Content: "editing", ToolCalls: []zeroruntime.ToolCall{
-			{ID: "e1", Name: "write_file", Arguments: `{"path":"cmd/main.go","content":"..."}`},
-		}},
-		{Role: zeroruntime.MessageRoleTool, ToolCallID: "e1", Content: "Wrote cmd/main.go (adds --version flag)"},
-		{Role: zeroruntime.MessageRoleAssistant, Content: "done"},
-		{Role: zeroruntime.MessageRoleUser, Content: "continue"},
-		{Role: zeroruntime.MessageRoleAssistant, Content: "continuing"},
-	}
-	summary := compactStateConversation(t, messages)
-
-	state := parsePreservedStateBlock(summary)
-	if len(state.RecentEdits) != 1 {
-		t.Fatalf("expected 1 preserved edit, got %#v", state.RecentEdits)
-	}
-	if state.RecentEdits[0].Path != "cmd/main.go" || !strings.Contains(state.RecentEdits[0].Note, "--version") {
-		t.Fatalf("preserved edit = %#v, want cmd/main.go + its note", state.RecentEdits[0])
-	}
-}
-
-// A fresh edit note for a path overrides the one carried from an earlier
-// compaction (newer wins) and moves the path to the newest position rather than
-// duplicating it or leaving it pinned to its old slot.
-func TestRecentEditsMergeNewerWins(t *testing.T) {
-	prior := preservedState{RecentEdits: []preservedEdit{{Path: "a.go", Note: "old note"}, {Path: "z.go", Note: "z"}}}
-	older := preservedEditsToEntries(prior.RecentEdits)
-	newer := []skillEntry{{name: "a.go", body: "new note"}, {name: "b.go", body: "added"}}
-
-	merged := mergeRecentEdits(older, newer)
-	// z.go (untouched) keeps its lead; a.go is re-edited so it takes the new note
-	// and moves behind z.go, ahead of the brand-new b.go: [z.go, a.go, b.go].
-	if len(merged) != 3 {
-		t.Fatalf("expected z.go + refreshed a.go + b.go, got %#v", merged)
-	}
-	if merged[0].name != "z.go" {
-		t.Fatalf("untouched z.go should stay first, got %#v", merged)
-	}
-	if merged[1].name != "a.go" || merged[1].body != "new note" {
-		t.Fatalf("re-edited a.go should move to the newest edits with the new note, got %#v", merged[1])
-	}
-	if merged[2].name != "b.go" {
-		t.Fatalf("brand-new b.go should be last, got %#v", merged[2])
-	}
-}
-
-// Regression: once more than maxRecentEdits distinct files are tracked, re-editing
-// an early file must move it into the capped tail rather than leaving it to be
-// dropped — otherwise the next compaction omits exactly the file the model most
-// recently touched.
-func TestRecentEditsCapKeepsReeditedFile(t *testing.T) {
-	// Earlier compaction preserved exactly maxRecentEdits files, f0 the oldest.
-	older := make([]skillEntry, 0, maxRecentEdits)
-	for i := 0; i < maxRecentEdits; i++ {
-		older = append(older, skillEntry{name: fmt.Sprintf("f%d.go", i), body: "old"})
-	}
-	// Fresh window re-edits the OLDEST file (f0) and adds a brand-new file, so the
-	// merged list exceeds the cap and something must be dropped.
-	newer := []skillEntry{{name: "f0.go", body: "re-edited"}, {name: "fresh.go", body: "new"}}
-
-	merged := capRecentEdits(mergeRecentEdits(older, newer))
-	if len(merged) != maxRecentEdits {
-		t.Fatalf("cap should keep %d entries, got %d", maxRecentEdits, len(merged))
-	}
-
-	var f0 *skillEntry
-	for i := range merged {
-		if merged[i].name == "f0.go" {
-			f0 = &merged[i]
-		}
-		if merged[i].name == "f1.go" {
-			t.Fatalf("f1.go (now the least-recently touched) should have been dropped, got %#v", merged)
-		}
-	}
-	if f0 == nil {
-		t.Fatalf("re-edited f0.go must survive the cap, got %#v", merged)
-	}
-	if f0.body != "re-edited" {
-		t.Fatalf("surviving f0.go should carry the fresh note, got %q", f0.body)
-	}
-}

internal/agent/file_diagnostics.go

@@ -1,62 +0,0 @@
-package agent
-
-import (
-	"context"
-	"os"
-	"path/filepath"
-	"strings"
-	"time"
-
-	"github.com/Gitlawb/zero/internal/lsp"
-)
-
-// fileDiagnosticsTimeout bounds one inline post-edit diagnostics check so a
-// slow or wedged language server can never hang a tool call; on timeout the
-// edit simply reports without a diagnostics block.
-const fileDiagnosticsTimeout = 10 * time.Second
-
-// NewFileDiagnostics adapts an *lsp.Manager to the per-edit inline diagnostics
-// callback (tools.RunOptions.Diagnostics): it reads the just-written file,
-// checks it against the file's language server, and formats error-severity
-// diagnostics for the model. Warnings and hints are excluded — nagging about
-// style on every edit is noise, while a type error the edit just introduced is
-// exactly what the model should see before its next step. Diagnostics are
-// rendered with workspace-relative paths: the absolute path would put the
-// local username/home directory into the model prompt and session transcript
-// on every edit. Returns nil when manager is nil, disabling inline diagnostics
-// entirely.
-func NewFileDiagnostics(manager *lsp.Manager, workspaceRoot string) func(context.Context, string) string {
-	if manager == nil {
-		return nil
-	}
-	return func(ctx context.Context, absPath string) string {
-		text, err := os.ReadFile(absPath)
-		if err != nil {
-			return ""
-		}
-		checkCtx, cancel := context.WithTimeout(ctx, fileDiagnosticsTimeout)
-		defer cancel()
-		diagnostics, err := manager.Check(checkCtx, absPath, string(text))
-		if err != nil {
-			return ""
-		}
-		errors := lsp.FilterBySeverity(diagnostics, lsp.SeverityError)
-		if len(errors) == 0 {
-			return ""
-		}
-		return lsp.FormatDiagnostics(diagnosticsDisplayPath(workspaceRoot, absPath), errors)
-	}
-}
-
-// diagnosticsDisplayPath renders absPath relative to the workspace root for
-// model-facing output, falling back to the file's base name when the path is
-// outside the workspace (a bare name still identifies the file without
-// exposing the directory layout).
-func diagnosticsDisplayPath(workspaceRoot, absPath string) string {
-	if workspaceRoot != "" {
-		if rel, err := filepath.Rel(workspaceRoot, absPath); err == nil && !strings.HasPrefix(rel, "..") {
-			return rel
-		}
-	}
-	return filepath.Base(absPath)
-}

internal/agent/file_diagnostics_test.go

@@ -1,24 +0,0 @@
-package agent
-
-import (
-	"path/filepath"
-	"testing"
-)
-
-// Diagnostics are model-facing: absolute paths would leak the local username
-// and directory layout into the prompt and session transcript on every edit.
-func TestDiagnosticsDisplayPath(t *testing.T) {
-	root := filepath.Join("/Users", "someone", "project")
-	cases := []struct {
-		root, abs, want string
-	}{
-		{root, filepath.Join(root, "internal", "a.go"), filepath.Join("internal", "a.go")},
-		{root, filepath.Join("/etc", "other.go"), "other.go"}, // outside root -> base name only
-		{"", filepath.Join("/home", "user", "x.go"), "x.go"},  // no root -> base name only
-	}
-	for _, c := range cases {
-		if got := diagnosticsDisplayPath(c.root, c.abs); got != c.want {
-			t.Errorf("diagnosticsDisplayPath(%q, %q) = %q, want %q", c.root, c.abs, got, c.want)
-		}
-	}
-}

internal/agent/guardrails.go

@@ -22,12 +22,6 @@ const (
 	// calls have executed since the last update_plan call.
 	staleToolCallThreshold = 10
 
-	// stalePlanTurnThreshold injects the same one-shot reminder once this many
-	// turns have passed since the last update_plan while plan items are still
-	// pending — the turn-based complement to staleToolCallThreshold, catching a
-	// plan that drifts stale across many turns that each make few tool calls.
-	stalePlanTurnThreshold = 8
-
 	// toolOnlyProgressReminderAt injects a one-shot progress nudge after this
 	// many consecutive turns contain tool calls but no visible assistant text.
 	// It does not stop the run; it tells the model to synthesize what it already
@@ -49,12 +43,8 @@ const (
 	toolFailureHintAt = 2
 	// toolFailureStopAt halts the run after a tool fails this many times in a row
 	// with the same error, so NO model (weak or strong) burns turns looping on a
-	// bad call. Set to 6 (not 4): a corrective hint fires at toolFailureHintAt (2),
-	// and a model iterating on a genuinely tricky edit can legitimately fail a few
-	// times after the hint while converging — stopping at 4 cut those runs short.
-	// The streak still resets the moment the tool succeeds or hits a different
-	// error, so this only affects true same-error loops.
-	toolFailureStopAt = 6
+	// bad call.
+	toolFailureStopAt = 4
 
 	// maxContinueNudges bounds how many times the headless completion gate
 	// (Options.RequireCompletionSignal) re-prompts a model that stopped without a
@@ -364,13 +354,8 @@ type guardState struct {
 	emptyTurns               int
 	totalToolCalls           int
 	toolCallsSincePlanUpdate int
-	// turnsSincePlanUpdate counts turns (not individual tool calls) since the last
-	// update_plan, so a plan that goes stale across many low-tool-call turns is
-	// still caught — the tool-call counter alone can take many turns to trip when
-	// the model makes only one call per turn.
-	turnsSincePlanUpdate  int
-	planEverCalled        bool
-	notCalledReminderSent bool
+	planEverCalled           bool
+	notCalledReminderSent    bool
 	// staleReminderSent records whether the stale reminder has already fired for
 	// the current stale interval. It is cleared when a plan update opens a new
 	// interval, making the reminder one-shot per interval rather than per turn.
@@ -429,9 +414,8 @@ func (state *guardState) observeToolResult(name string, failed bool, output stri
 func (state *guardState) observeTurn(collected zeroruntime.CollectedStream) (stop bool) {
 	hasToolCalls := len(collected.ToolCalls) > 0
 	hasVisibleText := strings.TrimSpace(collected.Text) != ""
-	hasReasoning := collected.HasReasoning || len(collected.ReasoningBlocks) > 0
 
-	if hasToolCalls || hasVisibleText || hasReasoning {
+	if hasToolCalls || hasVisibleText {
 		state.emptyTurns = 0
 	} else {
 		state.emptyTurns++
@@ -443,16 +427,11 @@ func (state *guardState) observeTurn(collected zeroruntime.CollectedStream) (sto
 		state.toolOnlyReminderSent = false
 	}
 
-	// One turn has passed; the plan-update below resets this to 0 when the model
-	// refreshes the plan this turn.
-	state.turnsSincePlanUpdate++
-
 	for _, call := range collected.ToolCalls {
 		state.totalToolCalls++
 		if call.Name == planToolName {
 			state.planEverCalled = true
 			state.toolCallsSincePlanUpdate = 0
-			state.turnsSincePlanUpdate = 0
 			// A fresh plan update opens a new stale interval.
 			state.staleReminderSent = false
 			// Record how many items remain so the completion gate knows whether
@@ -506,12 +485,10 @@ func (state *guardState) progressReminder() string {
 // number of turns completed so far).
 func (state *guardState) planReminder(turn int) string {
 	// STALE reminder takes priority: a long run without a plan update is the
-	// stronger signal. Fires on either the tool-call streak OR a turn streak with
-	// pending items (so a plan drifting stale across many low-call turns is caught,
-	// while a fully-completed plan is left alone). One-shot per stale interval.
-	if state.planEverCalled && !state.staleReminderSent &&
-		(state.toolCallsSincePlanUpdate >= staleToolCallThreshold ||
-			(state.turnsSincePlanUpdate >= stalePlanTurnThreshold && state.planItemsPending > 0)) {
+	// stronger signal. One-shot per stale interval.
+	if state.planEverCalled &&
+		!state.staleReminderSent &&
+		state.toolCallsSincePlanUpdate >= staleToolCallThreshold {
 		state.staleReminderSent = true
 		return planStaleReminder(state.toolCallsSincePlanUpdate)
 	}

internal/agent/guardrails_test.go

@@ -22,14 +22,6 @@ func textTurn(content string) []zeroruntime.StreamEvent {
 	}
 }
 
-// reasoningTurn produces live reasoning without visible assistant text.
-func reasoningTurn(content string) []zeroruntime.StreamEvent {
-	return []zeroruntime.StreamEvent{
-		{Type: zeroruntime.StreamEventReasoning, Content: content},
-		{Type: zeroruntime.StreamEventDone},
-	}
-}
-
 // toolTurn produces a turn that calls a named tool with the given args JSON.
 func toolTurn(callID string, toolName string, args string) []zeroruntime.StreamEvent {
 	return []zeroruntime.StreamEvent{
@@ -109,31 +101,6 @@ func TestRunResetsEmptyTurnCounterOnVisibleOutput(t *testing.T) {
 	}
 }
 
-func TestRunResetsEmptyTurnCounterOnReasoning(t *testing.T) {
-	provider := &mockProvider{
-		turns: [][]zeroruntime.StreamEvent{
-			reasoningTurn("thinking 1"),
-			reasoningTurn("thinking 2"),
-			reasoningTurn("thinking 3"),
-			textTurn("done"),
-		},
-	}
-
-	result, err := Run(context.Background(), "go", provider, Options{
-		Registry: tools.NewRegistry(),
-		MaxTurns: 12,
-	})
-	if err != nil {
-		t.Fatal(err)
-	}
-	if result.FinalAnswer != "done" {
-		t.Fatalf("expected reasoning-only turns to keep the run live until final answer, got %q", result.FinalAnswer)
-	}
-	if len(provider.requests) != 4 {
-		t.Fatalf("expected 4 turns, got %d", len(provider.requests))
-	}
-}
-
 func TestRunResetsEmptyTurnCounterOnToolCall(t *testing.T) {
 	root := t.TempDir()
 	writeAgentTestFile(t, root+"/notes.txt", "alpha")

internal/agent/loop.go

@@ -25,12 +25,7 @@ const maxTurnsFinalAnswerPrompt = "You have reached the tool-turn limit. Do not
 // WITH NO OUTPUT yet is re-issued on a fresh connection before giving up. Only
 // the no-output case is retried (a partial turn would duplicate), so this is a
 // safe recovery for a stalled/dead pooled connection.
-//
-// Set to 1 (not 2): each attempt can itself idle for the full stream timeout
-// (~5min) before the stall is even detected, so 2 retries left an interactive
-// session frozen for ~15min. One retry keeps the common single-hiccup recovery
-// while bounding the worst case to ~2× the idle timeout.
-const maxStreamStallRetries = 1
+const maxStreamStallRetries = 2
 
 const (
 	toolResultMetaControl       = "control"
@@ -137,12 +132,6 @@ func Run(ctx context.Context, prompt string, provider Provider, options Options)
 	guards := newGuardState()
 	compactor := newCompactionState(options)
 
-	// Background post-edit diagnostics: files changed by mutating tools are
-	// checked off the tool-call critical path and any errors are appended as a
-	// nudge before the NEXT request (see async_diagnostics.go). nil when no
-	// FileDiagnostics callback is wired; every method no-ops on nil.
-	postEditDiagnostics := newAsyncDiagnostics(options.FileDiagnostics, options.Cwd)
-
 	// loaded tracks deferred-eligible tools the model has pulled via tool_search
 	// during THIS run. It is consulted by partitionTools each turn to expose a
 	// loaded tool's full schema; it lives only for the run (v1 within-run scope).
@@ -156,31 +145,15 @@ func Run(ctx context.Context, prompt string, provider Provider, options Options)
 	// has already been demanded this run, so it fires at most once.
 	acceptanceRequested := false
 
-	// toolDefCache memoizes each tool's rendered JSON-schema definition across
-	// turns (a tool's advertised schema is stable for the run), so partitionTools
-	// doesn't re-run the recursive schema→map conversion for every tool every turn.
-	toolDefCache := map[string]zeroruntime.ToolDefinition{}
-
 	result := Result{Messages: copyMessages(messages)}
 	for turn := 0; turn < maxTurns; turn++ {
 		result.Turns = turn + 1
 
-		// Deliver background post-edit diagnostics from the previous turn's edits
-		// BEFORE compaction so the nudge is part of the request being budgeted.
-		// A brief wait at most (asyncDiagnosticsDrainTimeout); an unfinished check
-		// simply delivers on a later turn.
-		if nudge := postEditDiagnostics.drain(ctx); nudge != "" {
-			messages = append(messages, zeroruntime.Message{
-				Role:    zeroruntime.MessageRoleUser,
-				Content: nudge,
-			})
-		}
-
 		// Build the per-turn tool list first so proactive compaction can include
 		// the tool-definition tokens (they ride on every request) in its estimate.
 		// partitionTools depends only on registry/permissions/options/loaded, not on
 		// the messages, so computing it before compaction is safe.
-		exposed, _ := partitionToolsCached(registry, permissionMode, options, loaded, toolDefCache)
+		exposed, _ := partitionTools(registry, permissionMode, options, loaded)
 
 		// PROACTIVE compaction: if the history is approaching the model's
 		// context window, summarize the oldest middle before building the
@@ -190,7 +163,6 @@ func Run(ctx context.Context, prompt string, provider Provider, options Options)
 			Messages:        copyMessages(messages),
 			Tools:           exposed,
 			ReasoningEffort: options.ReasoningEffort,
-			PromptCacheKey:  options.SessionID,
 		}
 
 		// Report the per-category context budget for this turn so a surface can
@@ -226,7 +198,6 @@ func Run(ctx context.Context, prompt string, provider Provider, options Options)
 					Messages:        copyMessages(messages),
 					Tools:           exposed,
 					ReasoningEffort: options.ReasoningEffort,
-					PromptCacheKey:  options.SessionID,
 				}
 				// Pre-content connect after a context-limit compaction: route through the
 				// reconnect helper so a transient upstream hiccup here doesn't fail the
@@ -287,7 +258,6 @@ func Run(ctx context.Context, prompt string, provider Provider, options Options)
 					Messages:        copyMessages(messages),
 					Tools:           exposed,
 					ReasoningEffort: options.ReasoningEffort,
-					PromptCacheKey:  options.SessionID,
 				}
 				retryStream, retryStreamErr := streamWithReconnect(ctx, provider, retryRequest, reconnectNoticeFor(options))
 				if retryStreamErr != nil {
@@ -346,7 +316,6 @@ func Run(ctx context.Context, prompt string, provider Provider, options Options)
 				Messages:        copyMessages(messages),
 				Tools:           exposed,
 				ReasoningEffort: options.ReasoningEffort,
-				PromptCacheKey:  options.SessionID,
 			}
 			retryStream, retryErr := streamWithReconnect(ctx, provider, retryRequest, reconnectNoticeFor(options))
 			if retryErr != nil {
@@ -371,16 +340,6 @@ func Run(ctx context.Context, prompt string, provider Provider, options Options)
 			}
 		}
 
-		// Calibrate the compaction token estimator against the provider's real
-		// prompt-token count for the request we just sent, so later turns trigger
-		// compaction near true capacity instead of ~15% early on code-heavy history.
-		// Recompute the estimate HERE (not at request-build time): a reactive
-		// compaction may have replaced `messages` with a smaller set and re-sent, so
-		// this reflects the request that actually produced collected.Usage. The
-		// assistant reply is appended below, after this, so `messages` is still the
-		// sent request.
-		compactor.calibrate(estimateTokens(messages)+estimateToolDefTokens(exposed), collected.Usage.InputTokens)
-
 		// Carry the turn's terminal stop reason so a final answer cut off at the
 		// output token cap (or by a content filter) is reported as truncated. A
 		// tool-call turn normalizes to "" and clears any prior reason.
@@ -491,19 +450,6 @@ func Run(ctx context.Context, prompt string, provider Provider, options Options)
 					continue
 				}
 			}
-			// Finalization diagnostics gate: edits from this run may still have
-			// checks in flight — the per-turn drain waits only briefly and defers
-			// to "a later turn", but a final answer means there is no later turn.
-			// Wait out the full inline-era budget once; an introduced error gives
-			// the model one more turn to see (and fix) it instead of being lost.
-			// Free for runs that never edited: an idle collector returns "".
-			if nudge := postEditDiagnostics.drainFinal(ctx); nudge != "" {
-				messages = append(messages, zeroruntime.Message{
-					Role:    zeroruntime.MessageRoleUser,
-					Content: nudge,
-				})
-				continue
-			}
 			result.FinalAnswer = collected.Text
 			result.Messages = copyMessages(messages)
 			return result, nil
@@ -529,35 +475,11 @@ func Run(ctx context.Context, prompt string, provider Provider, options Options)
 		// between tool_results breaks strict provider replay) — same after-batch
 		// rationale as turnRequestedModel above.
 		var changedFilesThisBatch []string
-		// Parallel read-ahead state: results for calls[precomputedStart:precomputedEnd]
-		// executed concurrently, consumed strictly in order below.
-		var precomputed []precomputedToolResult
-		precomputedStart, precomputedEnd := 0, 0
 		for index, call := range collected.ToolCalls {
-			// When this call starts a consecutive run of >= 2 auto-allowed read-only
-			// calls, execute the whole run concurrently now (see parallel_tools.go).
-			// The scan happens lazily at the run's first index — never ahead of a
-			// pending mutating call — so read-after-write ordering is preserved.
-			if index >= precomputedEnd {
-				runEnd := index
-				for runEnd < len(collected.ToolCalls) && parallelSafeToolCall(registry, collected.ToolCalls[runEnd], options) {
-					runEnd++
-				}
-				if runEnd-index >= 2 {
-					precomputed = executeParallelReadBatch(ctx, registry, collected.ToolCalls, index, runEnd, permissionMode, options)
-					precomputedStart, precomputedEnd = index, runEnd
-				}
-			}
 			if options.OnToolCall != nil {
 				options.OnToolCall(call)
 			}
-			var toolResult ToolResult
-			var abortErr error
-			if index >= precomputedStart && index < precomputedEnd {
-				toolResult, abortErr = precomputed[index-precomputedStart].result, precomputed[index-precomputedStart].abortErr
-			} else {
-				toolResult, abortErr = executeToolCall(ctx, registry, call, permissionMode, options)
-			}
+			toolResult, abortErr := executeToolCall(ctx, registry, call, permissionMode, options)
 			if options.OnToolResult != nil {
 				options.OnToolResult(toolResult)
 			}
@@ -620,14 +542,11 @@ func Run(ctx context.Context, prompt string, provider Provider, options Options)
 				failureHint = toolFailureHint(call.Name, toolSchemaJSON(registry, call.Name), toolResult.Output)
 			}
 
-			// Collect the files this successful mutating tool changed. Self-correct
-			// verification runs once over the union after the batch; background
-			// diagnostics start NOW so the language server analyzes while the rest
-			// of the batch executes. A read-only tool (no ChangedFiles) never
-			// contributes.
-			if toolResult.Status == tools.StatusOK && len(toolResult.ChangedFiles) > 0 {
+			// Post-edit self-correction: collect the files this successful mutating
+			// tool changed; verification runs once over the union after the batch.
+			// A read-only tool (no ChangedFiles) never contributes.
+			if options.SelfCorrect != nil && toolResult.Status == tools.StatusOK && len(toolResult.ChangedFiles) > 0 {
 				changedFilesThisBatch = append(changedFilesThisBatch, toolResult.ChangedFiles...)
-				postEditDiagnostics.enqueue(ctx, toolResult.ChangedFiles)
 			}
 		}
 
@@ -710,17 +629,6 @@ func Run(ctx context.Context, prompt string, provider Provider, options Options)
 	// mid-run, not a natural completion (a finished run returns via the no-tool-call
 	// success path before this). Under the headless completion gate that is INCOMPLETE,
 	// not success, so a run that loops to the turn limit isn't reported as done.
-	//
-	// The final-answer call is one more model request, so diagnostics from the
-	// LAST turn's edits get a drain too — with the finalization budget, since
-	// there is no later turn to defer to — otherwise an error introduced by
-	// the final edit would go unreported in the summary.
-	if nudge := postEditDiagnostics.drainFinal(ctx); nudge != "" {
-		messages = append(messages, zeroruntime.Message{
-			Role:    zeroruntime.MessageRoleUser,
-			Content: nudge,
-		})
-	}
 	if answer, finalMessages, finishReason := finalAnswerAfterMaxTurns(ctx, provider, messages, options); strings.TrimSpace(answer) != "" {
 		result.FinalAnswer = answer
 		result.FinishReason = finishReason
@@ -753,7 +661,6 @@ func finalAnswerAfterMaxTurns(ctx context.Context, provider Provider, messages [
 	stream, err := streamWithReconnect(ctx, provider, zeroruntime.CompletionRequest{
 		Messages:        copyMessages(finalMessages),
 		ReasoningEffort: options.ReasoningEffort,
-		PromptCacheKey:  options.SessionID,
 	}, reconnectNoticeFor(options))
 	if err != nil {
 		return "", messages, ""
@@ -909,25 +816,6 @@ func executeToolCall(ctx context.Context, registry *tools.Registry, call ToolCal
 		}
 	}
 
-	// A shell command that sets sandbox_permissions: with_additional_permissions
-	// must carry a valid additional_permissions payload; inlineAdditionalPermissionsProfile
-	// is the single source of truth for that shape, and buildPermissionEvent (below)
-	// calls it again to render the prompt's scope text. Check it here, before any
-	// permission prompt is shown: a malformed payload can never be satisfied no
-	// matter what the user decides, so surfacing it as a plain tool error (which the
-	// model can see and retry) is both clearer and avoids presenting a normal-looking
-	// prompt whose "allow" path is guaranteed to fail with a confusing denial.
-	if toolFound && isShellCommandTool(call.Name) {
-		if _, _, err := inlineAdditionalPermissionsProfile(args, options.Cwd); err != nil {
-			return ToolResult{
-				ToolCallID: call.ID,
-				Name:       call.Name,
-				Status:     tools.StatusError,
-				Output:     "Error: " + err.Error(),
-			}, nil
-		}
-	}
-
 	// ask_user is intercepted in the loop (like permissions) so the question can
 	// be routed to an interactive front-end instead of blocking inside the tool.
 	// When no front-end is wired up it degrades to the tool's own graceful Run().
@@ -1144,12 +1032,6 @@ func executeToolCall(ctx context.Context, registry *tools.Registry, call ToolCal
 		// Per-session file version tracker so write_file/edit_file refuse to clobber
 		// a file that changed on disk outside Zero since it was last read.
 		FileTracker: options.FileTracker,
-		// Post-edit diagnostics are NOT forwarded to the tools: they used to run
-		// synchronously inside edit_file/write_file and block every mutating tool
-		// call on the language server (≥300ms debounce floor, 10s cap). The loop
-		// now checks changed files in the background and nudges the model before
-		// its next request instead (see async_diagnostics.go). The tools' inline
-		// mechanism (tools.RunOptions.Diagnostics) stays for direct API callers.
 		// Forward the run's operator tool filters so a filter-aware tool
 		// (tool_search) never discloses or loads an operator-hidden deferred tool.
 		EnabledTools:  options.EnabledTools,
@@ -2440,12 +2322,7 @@ func inlineAdditionalPermissionsProfile(args map[string]any, basePath string) (s
 	}
 	raw, ok := args["additional_permissions"]
 	if !ok || raw == nil {
-		return sandbox.RequestPermissionProfile{}, true, fmt.Errorf(
-			"sandbox_permissions was set to %q but no additional_permissions object was provided. "+
-				`Include one, for example additional_permissions: {"network": {"enabled": true}} or `+
-				`{"file_system": {"write": ["/path"]}}. If this command does not need elevated permissions, `+
-				"omit sandbox_permissions entirely and retry",
-			tools.SandboxPermissionsWithAdditionalPermissions)
+		return sandbox.RequestPermissionProfile{}, true, fmt.Errorf("missing additional_permissions; provide at least one of network or file_system")
 	}
 	data, err := json.Marshal(raw)
 	if err != nil {
@@ -2460,9 +2337,7 @@ func inlineAdditionalPermissionsProfile(args map[string]any, basePath string) (s
 		return sandbox.RequestPermissionProfile{}, true, err
 	}
 	if normalized.Empty() {
-		return sandbox.RequestPermissionProfile{}, true, fmt.Errorf(
-			"additional_permissions must include at least one of network or file_system, for example " +
-				`{"network": {"enabled": true}} or {"file_system": {"write": ["/path"]}}`)
+		return sandbox.RequestPermissionProfile{}, true, fmt.Errorf("additional_permissions must include at least one requested permission in network or file_system")
 	}
 	grantProfile, err := sandbox.RequestPermissionGrantProfile(normalized)
 	if err != nil {
@@ -2561,17 +2436,6 @@ func permissionActionFromSandbox(action sandbox.Action) PermissionAction {
 // exposed. The exposed slice is alpha-sorted by name, matching the legacy order
 // so the inactive path is stable.
 func partitionTools(registry *tools.Registry, permissionMode PermissionMode, options Options, loaded map[string]bool) ([]zeroruntime.ToolDefinition, string) {
-	return partitionToolsCached(registry, permissionMode, options, loaded, nil)
-}
-
-// partitionToolsCached is partitionTools with an optional per-tool definition
-// cache. The partitioning itself (visibility, deferral, ordering) is recomputed
-// every call — it must be, because a tool's deferred state can flip mid-run (e.g.
-// swarm tools un-defer once a swarm is active). Only the expensive part —
-// rendering each tool's JSON-schema parameters — is memoized by tool name, since a
-// tool's advertised name/description/schema is stable for the run. defCache nil
-// disables caching (used by tests and the plain partitionTools entrypoint).
-func partitionToolsCached(registry *tools.Registry, permissionMode PermissionMode, options Options, loaded map[string]bool, defCache map[string]zeroruntime.ToolDefinition) ([]zeroruntime.ToolDefinition, string) {
 	registeredTools := registry.All()
 
 	visible := make([]tools.Tool, 0, len(registeredTools))
@@ -2606,115 +2470,76 @@ func partitionToolsCached(registry *tools.Registry, permissionMode PermissionMod
 
 	active := options.DeferThreshold > 0 && eligible >= options.DeferThreshold && loaderUsable
 
-	// INACTIVE: every visible tool eager (except tool_search), alpha-sorted. With no
-	// deferral there is no mid-session loading, so this is byte-stable across turns
-	// and byte-identical to the pre-deferral output.
-	if !active {
-		definitions := make([]zeroruntime.ToolDefinition, 0, len(visible))
-		for _, tool := range visible {
-			if tool.Name() == tools.ToolSearchToolName {
-				continue
-			}
-			definitions = append(definitions, cachedRuntimeToolDefinition(defCache, tool))
-		}
-		sort.Slice(definitions, func(left int, right int) bool {
-			return definitions[left].Name < definitions[right].Name
-		})
-		return definitions, ""
-	}
-
-	// ACTIVE: lay the tools array out so its cacheable prefix does NOT shift when a
-	// deferred tool loads mid-session. The tools block is part of the provider's
-	// cached prefix; if a load reorders it, the cache invalidates from that point
-	// through the system prompt and messages — on EVERY load. Previously the whole
-	// array was alpha-sorted each turn, so a newly loaded tool was INSERTED into the
-	// middle and shifted every later definition. Instead we build three append-only
-	// regions:
-	//   1. non-deferred tools, alpha-sorted — always present, identical every turn;
-	//   2. tool_search — always present, right after the stable block;
-	//   3. loaded deferred tools, alpha-sorted — APPENDED, so an unloaded->loaded
-	//      transition grows the tail instead of inserting into the eager block.
-	// (tool_search's discovery text still shrinks as tools load, so keeping it and
-	// the loaded tail AFTER the eager block preserves the eager tools' cache across a
-	// load; fully stabilizing the loader's own description is a scoped follow-up.)
-	eager := make([]zeroruntime.ToolDefinition, 0, len(visible))
-	loadedTail := make([]zeroruntime.ToolDefinition, 0)
+	definitions := make([]zeroruntime.ToolDefinition, 0, len(visible))
+	exposedNames := make(map[string]bool, len(visible))
 	var hiddenTools []tools.Tool
 	for _, tool := range visible {
 		name := tool.Name()
-		if name == tools.ToolSearchToolName {
-			continue // added explicitly between the eager block and the loaded tail
-		}
-		if tools.IsDeferred(tool) {
-			if loaded[name] {
-				loadedTail = append(loadedTail, cachedRuntimeToolDefinition(defCache, tool))
-			} else {
-				hiddenTools = append(hiddenTools, tool)
+		deferred := tools.IsDeferred(tool)
+
+		if !active {
+			// Inactive: byte-identical to legacy, but tool_search is never advertised.
+			if name == tools.ToolSearchToolName {
+				continue
 			}
+			definitions = append(definitions, zeroruntime.ToolDefinition{
+				Name:        name,
+				Description: tool.Description(),
+				Parameters:  schemaToRuntimeMap(tool.Parameters()),
+			})
+			exposedNames[name] = true
 			continue
 		}
-		eager = append(eager, cachedRuntimeToolDefinition(defCache, tool))
-	}
-	sort.Slice(eager, func(left int, right int) bool {
-		return eager[left].Name < eager[right].Name
-	})
-	sort.Slice(loadedTail, func(left int, right int) bool {
-		return loadedTail[left].Name < loadedTail[right].Name
-	})
 
+		// Active path.
+		if deferred && !loaded[name] {
+			hiddenTools = append(hiddenTools, tool)
+			continue
+		}
+		definitions = append(definitions, zeroruntime.ToolDefinition{
+			Name:        name,
+			Description: tool.Description(),
+			Parameters:  schemaToRuntimeMap(tool.Parameters()),
+		})
+		exposedNames[name] = true
+	}
+
+	// On the ACTIVE path tool_search is guaranteed runnable (active implies
+	// loaderUsable), so it must ALWAYS be reachable — even when a non-empty
+	// EnabledTools allowlist omits it (the operator allowlisted the deferred
+	// tools, not the loader). Expose its full definition whenever it is not
+	// already in the exposed set. This never runs on the inactive path, so the
+	// byte-identical below-threshold output is preserved.
 	discovery := ""
-	if len(hiddenTools) > 0 {
+	if active && len(hiddenTools) > 0 {
 		discovery = tools.BuildToolSearchDescription(hiddenTools)
 	}
-
-	// tool_search is guaranteed runnable on the active path, so it is ALWAYS exposed
-	// — even when a non-empty EnabledTools allowlist omits it (the operator
-	// allowlisted the deferred tools, not the loader). It sits right after the stable
-	// eager block and carries the discovery list for still-hidden tools.
-	description := loader.Description()
-	if discovery != "" {
-		description = discovery
+	if active && !exposedNames[tools.ToolSearchToolName] {
+		description := loader.Description()
+		if discovery != "" {
+			description = discovery
+		}
+		definitions = append(definitions, zeroruntime.ToolDefinition{
+			Name:        loader.Name(),
+			Description: description,
+			Parameters:  schemaToRuntimeMap(loader.Parameters()),
+		})
+	} else if active && discovery != "" {
+		for i := range definitions {
+			if definitions[i].Name == tools.ToolSearchToolName {
+				definitions[i].Description = discovery
+				break
+			}
+		}
 	}
-	definitions := make([]zeroruntime.ToolDefinition, 0, len(eager)+1+len(loadedTail))
-	definitions = append(definitions, eager...)
-	definitions = append(definitions, zeroruntime.ToolDefinition{
-		Name:        loader.Name(),
-		Description: description,
-		Parameters:  schemaToRuntimeMap(loader.Parameters()),
+
+	sort.Slice(definitions, func(left int, right int) bool {
+		return definitions[left].Name < definitions[right].Name
 	})
-	definitions = append(definitions, loadedTail...)
 
 	return definitions, discovery
 }
 
-// cachedRuntimeToolDefinition returns the tool's rendered definition, reusing a
-// cached render when defCache holds one for this tool name. A tool's advertised
-// definition is stable across a run, so caching skips the recursive schema→map
-// conversion (schemaToRuntimeMap) that would otherwise run for every tool on every
-// turn. tool_search is excluded by its callers (its description is dynamic), so it
-// never poisons the cache. A nil cache computes fresh.
-func cachedRuntimeToolDefinition(defCache map[string]zeroruntime.ToolDefinition, tool tools.Tool) zeroruntime.ToolDefinition {
-	if defCache == nil {
-		return runtimeToolDefinition(tool)
-	}
-	if def, ok := defCache[tool.Name()]; ok {
-		return def
-	}
-	def := runtimeToolDefinition(tool)
-	defCache[tool.Name()] = def
-	return def
-}
-
-// runtimeToolDefinition renders a tool's advertised definition (name, description,
-// JSON-schema parameters) as sent to the provider.
-func runtimeToolDefinition(tool tools.Tool) zeroruntime.ToolDefinition {
-	return zeroruntime.ToolDefinition{
-		Name:        tool.Name(),
-		Description: tool.Description(),
-		Parameters:  schemaToRuntimeMap(tool.Parameters()),
-	}
-}
-
 func ToolVisible(tool tools.Tool, permissionMode PermissionMode, enabledTools []string, disabledTools []string) bool {
 	return ToolAllowedByFilters(tool.Name(), enabledTools, disabledTools) && ToolAdvertised(tool, permissionMode)
 }

internal/agent/loop_test.go

@@ -4,7 +4,6 @@ import (
 	"context"
 	"encoding/json"
 	"errors"
-	"fmt"
 	"os"
 	"path/filepath"
 	"runtime"
@@ -1946,11 +1945,6 @@ func TestRunCommandPrefixApprovalBypassesSandboxForMatchingShellCalls(t *testing
 
 func TestRunCommandPrefixApprovalCoversSegmentedShellWithSafeTail(t *testing.T) {
 	root := t.TempDir()
-	segmentedCommand := `ps aux | head -5`
-	if runtime.GOOS == "windows" {
-		// head is MSYS-prone on Windows (#458) and no longer counts as a known-safe tail.
-		segmentedCommand = `ps aux | echo ok`
-	}
 	retryTool := &sandboxDeniedRetryTool{}
 	registry := tools.NewRegistry()
 	registry.Register(retryTool)
@@ -1964,7 +1958,7 @@ func TestRunCommandPrefixApprovalCoversSegmentedShellWithSafeTail(t *testing.T)
 			},
 			{
 				{Type: zeroruntime.StreamEventToolCallStart, ToolCallID: "call-2", ToolName: "bash"},
-				{Type: zeroruntime.StreamEventToolCallDelta, ToolCallID: "call-2", ArgumentsFragment: fmt.Sprintf(`{"command":%q}`, segmentedCommand)},
+				{Type: zeroruntime.StreamEventToolCallDelta, ToolCallID: "call-2", ArgumentsFragment: `{"command":"ps aux | head -5"}`},
 				{Type: zeroruntime.StreamEventToolCallEnd, ToolCallID: "call-2"},
 				{Type: zeroruntime.StreamEventDone},
 			},
@@ -2913,10 +2907,8 @@ func TestBuildSystemPromptInjectsHostShellContext(t *testing.T) {
 		t.Fatalf("expected operating system in environment block, got %q", prompt)
 	}
 	if runtime.GOOS == "windows" {
-		for _, want := range []string{"Windows cmd.exe syntax", "cwd argument", "MSYS binaries", "grep", "require_escalated"} {
-			if !strings.Contains(prompt, want) {
-				t.Fatalf("expected Windows shell guidance to mention %q, got %q", want, prompt)
-			}
+		if !strings.Contains(prompt, "Windows cmd.exe syntax") || !strings.Contains(prompt, "cwd argument") {
+			t.Fatalf("expected Windows cmd.exe shell guidance in prompt, got %q", prompt)
 		}
 	} else if !strings.Contains(prompt, "/bin/sh syntax") {
 		t.Fatalf("expected POSIX shell guidance in prompt, got %q", prompt)

internal/agent/parallel_tools.go

@@ -1,97 +0,0 @@
-package agent
-
-import (
-	"context"
-	"sync"
-
-	"github.com/Gitlawb/zero/internal/tools"
-)
-
-// Parallel read-ahead for tool batches. When a turn requests several
-// independent lookups (read_file + grep + glob is the common shape), executing
-// them one after another serializes pure I/O waits. A consecutive run of
-// auto-allowed read-only calls is executed concurrently instead; results are
-// then consumed in the original call order, so guard counters, message
-// ordering, abort semantics, and the surface's call/result event pairing are
-// byte-identical to sequential execution. Runs never span a mutating call: a
-// read that follows a write must observe the write, so eligibility is decided
-// per consecutive run, not per batch.
-
-// maxParallelReadTools bounds concurrent read-only tool executions in a turn.
-const maxParallelReadTools = 8
-
-// precomputedToolResult is one parallel read-ahead execution, keyed back to
-// its batch index by the caller.
-type precomputedToolResult struct {
-	result   ToolResult
-	abortErr error
-}
-
-// parallelSafeToolCall reports whether call may run concurrently with its
-// neighbors: the tool must exist, be side-effect-free (SideEffectRead), and be
-// auto-allowed for these args, so no interactive prompt or workspace mutation
-// is on the hot path. Loop-intercepted tools (ask_user, request_permissions)
-// and tool_search (mutates the deferred-tool set) stay sequential.
-func parallelSafeToolCall(registry *tools.Registry, call ToolCall, options Options) bool {
-	switch call.Name {
-	case "ask_user", tools.RequestPermissionsToolName, tools.ToolSearchToolName:
-		return false
-	}
-	tool, found := registry.Get(call.Name)
-	if !found || tool.Safety().SideEffect != tools.SideEffectRead {
-		return false
-	}
-	args := map[string]any{}
-	if call.Arguments != "" {
-		if err := decodeToolArguments(call.Arguments, &args); err != nil {
-			return false
-		}
-	}
-	return effectivePermission(tool, args) == tools.PermissionAllow
-}
-
-// executeParallelReadBatch runs calls[start:end] concurrently (bounded by
-// maxParallelReadTools) and returns results indexed relative to start. All
-// execution-side callbacks that can fire inside executeToolCall are serialized
-// behind one mutex: a permission prompt (a sandbox preflight can demand one
-// even for an auto-allowed read) must never appear twice at once on an
-// interactive front-end, and OnPermission event handlers append to shared
-// session-recording state without their own locking — two batched reads under
-// a granted extra root would otherwise race (the pre-batch serial loop never
-// had two callbacks in flight at once).
-func executeParallelReadBatch(ctx context.Context, registry *tools.Registry, calls []ToolCall, start, end int, permissionMode PermissionMode, options Options) []precomputedToolResult {
-	batchOptions := options
-	var callbackMutex sync.Mutex
-	if options.OnPermissionRequest != nil {
-		inner := options.OnPermissionRequest
-		batchOptions.OnPermissionRequest = func(ctx context.Context, request PermissionRequest) (PermissionDecision, error) {
-			callbackMutex.Lock()
-			defer callbackMutex.Unlock()
-			return inner(ctx, request)
-		}
-	}
-	if options.OnPermission != nil {
-		inner := options.OnPermission
-		batchOptions.OnPermission = func(event PermissionEvent) {
-			callbackMutex.Lock()
-			defer callbackMutex.Unlock()
-			inner(event)
-		}
-	}
-
-	results := make([]precomputedToolResult, end-start)
-	semaphore := make(chan struct{}, maxParallelReadTools)
-	var waitGroup sync.WaitGroup
-	for index := start; index < end; index++ {
-		waitGroup.Add(1)
-		go func(index int) {
-			defer waitGroup.Done()
-			semaphore <- struct{}{}
-			defer func() { <-semaphore }()
-			result, abortErr := executeToolCall(ctx, registry, calls[index], permissionMode, batchOptions)
-			results[index-start] = precomputedToolResult{result: result, abortErr: abortErr}
-		}(index)
-	}
-	waitGroup.Wait()
-	return results
-}

internal/agent/parallel_tools_test.go

@@ -1,204 +0,0 @@
-package agent
-
-import (
-	"context"
-	"fmt"
-	"sync"
-	"testing"
-	"time"
-
-	"github.com/Gitlawb/zero/internal/tools"
-	"github.com/Gitlawb/zero/internal/zeroruntime"
-)
-
-// probeTool records execution overlap and ordering so tests can assert what
-// actually ran concurrently.
-type probeTool struct {
-	name       string
-	sideEffect tools.SideEffect
-	delay      time.Duration
-	// shared, when set, receives this probe's start/end entries too, so a test
-	// can observe ordering ACROSS probes (e.g. reads vs a write barrier).
-	shared *probeLog
-
-	mu        sync.Mutex
-	active    int
-	maxActive int
-	log       []string
-}
-
-// probeLog is a mutex-guarded event log shared between probes.
-type probeLog struct {
-	mu      sync.Mutex
-	entries []string
-}
-
-func (log *probeLog) append(entry string) {
-	log.mu.Lock()
-	defer log.mu.Unlock()
-	log.entries = append(log.entries, entry)
-}
-
-func (log *probeLog) snapshot() []string {
-	log.mu.Lock()
-	defer log.mu.Unlock()
-	return append([]string(nil), log.entries...)
-}
-
-func (tool *probeTool) Name() string        { return tool.name }
-func (tool *probeTool) Description() string { return "test probe tool" }
-func (tool *probeTool) Parameters() tools.Schema {
-	return tools.Schema{
-		Type:                 "object",
-		Properties:           map[string]tools.PropertySchema{"id": {Type: "string"}},
-		AdditionalProperties: false,
-	}
-}
-func (tool *probeTool) Safety() tools.Safety {
-	return tools.Safety{SideEffect: tool.sideEffect, Permission: tools.PermissionAllow, Reason: "test"}
-}
-func (tool *probeTool) Run(_ context.Context, args map[string]any) tools.Result {
-	id, _ := args["id"].(string)
-	tool.mu.Lock()
-	tool.active++
-	if tool.active > tool.maxActive {
-		tool.maxActive = tool.active
-	}
-	tool.log = append(tool.log, "start:"+id)
-	tool.mu.Unlock()
-	if tool.shared != nil {
-		tool.shared.append("start:" + id)
-	}
-	time.Sleep(tool.delay)
-	if tool.shared != nil {
-		tool.shared.append("end:" + id)
-	}
-	tool.mu.Lock()
-	tool.active--
-	tool.log = append(tool.log, "end:"+id)
-	tool.mu.Unlock()
-	return tools.Result{Status: tools.StatusOK, Output: "probe " + id}
-}
-
-func probeCallEvents(callID, toolName, id string) []zeroruntime.StreamEvent {
-	return []zeroruntime.StreamEvent{
-		{Type: zeroruntime.StreamEventToolCallStart, ToolCallID: callID, ToolName: toolName},
-		{Type: zeroruntime.StreamEventToolCallDelta, ToolCallID: callID, ArgumentsFragment: fmt.Sprintf(`{"id":%q}`, id)},
-		{Type: zeroruntime.StreamEventToolCallEnd, ToolCallID: callID},
-	}
-}
-
-func TestParallelSafeToolCall(t *testing.T) {
-	registry := tools.NewRegistry()
-	registry.Register(&probeTool{name: "probe_read", sideEffect: tools.SideEffectRead})
-	registry.Register(&probeTool{name: "probe_write", sideEffect: tools.SideEffectWrite})
-
-	call := func(name, args string) ToolCall { return ToolCall{ID: "c", Name: name, Arguments: args} }
-	if !parallelSafeToolCall(registry, call("probe_read", `{"id":"a"}`), Options{}) {
-		t.Fatal("auto-allowed read tool must be parallel-safe")
-	}
-	if parallelSafeToolCall(registry, call("probe_write", `{"id":"a"}`), Options{}) {
-		t.Fatal("mutating tool must not be parallel-safe")
-	}
-	if parallelSafeToolCall(registry, call("unknown_tool", `{}`), Options{}) {
-		t.Fatal("unknown tool must not be parallel-safe")
-	}
-	if parallelSafeToolCall(registry, call("probe_read", `{"id":`), Options{}) {
-		t.Fatal("undecodable arguments must not be parallel-safe")
-	}
-	if parallelSafeToolCall(registry, call("ask_user", `{}`), Options{}) {
-		t.Fatal("loop-intercepted tools must stay sequential")
-	}
-}
-
-func TestRunExecutesConsecutiveReadsConcurrently(t *testing.T) {
-	probe := &probeTool{name: "probe_read", sideEffect: tools.SideEffectRead, delay: 60 * time.Millisecond}
-	registry := tools.NewRegistry()
-	registry.Register(probe)
-
-	turnOne := append(probeCallEvents("call-1", "probe_read", "a"), probeCallEvents("call-2", "probe_read", "b")...)
-	turnOne = append(turnOne, probeCallEvents("call-3", "probe_read", "c")...)
-	turnOne = append(turnOne, zeroruntime.StreamEvent{Type: zeroruntime.StreamEventDone})
-	provider := &mockProvider{
-		turns: [][]zeroruntime.StreamEvent{
-			turnOne,
-			{{Type: zeroruntime.StreamEventText, Content: "done"}, {Type: zeroruntime.StreamEventDone}},
-		},
-	}
-
-	var results []ToolResult
-	_, err := Run(context.Background(), "probe", provider, Options{
-		Registry:     registry,
-		OnToolResult: func(result ToolResult) { results = append(results, result) },
-	})
-	if err != nil {
-		t.Fatal(err)
-	}
-	if probe.maxActive < 2 {
-		t.Fatalf("consecutive read-only calls must overlap, max concurrency was %d", probe.maxActive)
-	}
-	// Results must still be recorded in original call order.
-	if len(results) != 3 || results[0].ToolCallID != "call-1" || results[1].ToolCallID != "call-2" || results[2].ToolCallID != "call-3" {
-		t.Fatalf("tool results out of order: %#v", results)
-	}
-	messages := provider.requests[1].Messages
-	var toolOrder []string
-	for _, message := range messages {
-		if message.Role == zeroruntime.MessageRoleTool {
-			toolOrder = append(toolOrder, message.ToolCallID)
-		}
-	}
-	if len(toolOrder) != 3 || toolOrder[0] != "call-1" || toolOrder[1] != "call-2" || toolOrder[2] != "call-3" {
-		t.Fatalf("recorded tool messages out of order: %v", toolOrder)
-	}
-}
-
-func TestRunParallelReadsNeverSpanMutatingCall(t *testing.T) {
-	shared := &probeLog{}
-	read := &probeTool{name: "probe_read", sideEffect: tools.SideEffectRead, delay: 30 * time.Millisecond, shared: shared}
-	write := &probeTool{name: "probe_write", sideEffect: tools.SideEffectWrite, shared: shared}
-	registry := tools.NewRegistry()
-	registry.Register(read)
-	registry.Register(write)
-
-	turnOne := append(probeCallEvents("call-1", "probe_read", "r1"), probeCallEvents("call-2", "probe_read", "r2")...)
-	turnOne = append(turnOne, probeCallEvents("call-3", "probe_write", "w")...)
-	turnOne = append(turnOne, probeCallEvents("call-4", "probe_read", "r3")...)
-	turnOne = append(turnOne, probeCallEvents("call-5", "probe_read", "r4")...)
-	turnOne = append(turnOne, zeroruntime.StreamEvent{Type: zeroruntime.StreamEventDone})
-	provider := &mockProvider{
-		turns: [][]zeroruntime.StreamEvent{
-			turnOne,
-			{{Type: zeroruntime.StreamEventText, Content: "done"}, {Type: zeroruntime.StreamEventDone}},
-		},
-	}
-
-	_, err := Run(context.Background(), "probe", provider, Options{Registry: registry})
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	// Cross-probe ordering on the SHARED log: the write must start only after
-	// both first-batch reads finished, and both second-batch reads must start
-	// only after the write finished — batches never cross a mutating call.
-	log := shared.snapshot()
-	index := func(entry string) int {
-		for i, e := range log {
-			if e == entry {
-				return i
-			}
-		}
-		t.Fatalf("entry %q missing from shared log: %v", entry, log)
-		return -1
-	}
-	writeStart, writeEnd := index("start:w"), index("end:w")
-	if firstBatchMaxEnd := max(index("end:r1"), index("end:r2")); writeStart < firstBatchMaxEnd {
-		t.Fatalf("write started before the first read batch finished: %v", log)
-	}
-	if secondBatchMinStart := min(index("start:r3"), index("start:r4")); secondBatchMinStart < writeEnd {
-		t.Fatalf("second read batch started before the write finished: %v", log)
-	}
-	if read.maxActive < 2 {
-		t.Fatalf("reads within a batch must overlap, max concurrency was %d", read.maxActive)
-	}
-}

internal/agent/partition_cache_stable_test.go

@@ -1,44 +0,0 @@
-package agent
-
-import (
-	"testing"
-
-	"github.com/Gitlawb/zero/internal/tools"
-)
-
-func TestPartitionToolsActiveAppendsLoadedToolAfterEagerBlock(t *testing.T) {
-	// Cache-stability property: loading a deferred tool must APPEND it after the
-	// always-eager tools, not sort it into the middle of them — otherwise the tool
-	// definitions (the provider's cacheable prefix) shift on every load. The old
-	// behaviour alpha-sorted the whole array, so "mcp__srv__alpha" jumped ahead of
-	// "read_file".
-	root := t.TempDir()
-	registry := tools.NewRegistry()
-	registry.Register(tools.NewReadFileTool(root)) // non-deferred, "read_file"
-	registry.Register(fakeToolSearchTool{})
-	registry.Register(fakeDeferredTool{name: "mcp__srv__alpha", desc: "alpha"})
-	registry.Register(fakeDeferredTool{name: "mcp__srv__beta", desc: "beta"})
-
-	exposed, _ := partitionTools(registry, PermissionModeAuto, Options{DeferThreshold: 2}, map[string]bool{"mcp__srv__alpha": true})
-
-	pos := func(name string) int {
-		for i := range exposed {
-			if exposed[i].Name == name {
-				return i
-			}
-		}
-		return -1
-	}
-	readPos, searchPos, alphaPos := pos("read_file"), pos("tool_search"), pos("mcp__srv__alpha")
-	if readPos < 0 || searchPos < 0 || alphaPos < 0 {
-		t.Fatalf("expected read_file, tool_search and loaded alpha all exposed, got %#v", exposed)
-	}
-	// The eager tools must precede the loaded deferred tool (appended, not inserted).
-	if readPos >= alphaPos || searchPos >= alphaPos {
-		t.Fatalf("loaded deferred tool must be appended after the eager block; got read=%d search=%d alpha=%d", readPos, searchPos, alphaPos)
-	}
-	// beta was never loaded — it stays hidden.
-	if pos("mcp__srv__beta") != -1 {
-		t.Fatalf("unloaded deferred tool must stay hidden, got %#v", exposed)
-	}
-}

internal/agent/partition_cache_test.go

@@ -1,63 +0,0 @@
-package agent
-
-import (
-	"context"
-	"reflect"
-	"testing"
-
-	"github.com/Gitlawb/zero/internal/tools"
-	"github.com/Gitlawb/zero/internal/zeroruntime"
-)
-
-// countingSchemaTool records how many times its Parameters() schema is read, so a
-// test can prove the definition cache avoids re-rendering across turns.
-type countingSchemaTool struct {
-	name  string
-	calls *int
-}
-
-func (t countingSchemaTool) Name() string        { return t.name }
-func (t countingSchemaTool) Description() string { return "counts schema reads" }
-func (t countingSchemaTool) Parameters() tools.Schema {
-	*t.calls++
-	return tools.Schema{Type: "object", AdditionalProperties: false, Properties: map[string]tools.PropertySchema{
-		"x": {Type: "string"},
-	}}
-}
-func (t countingSchemaTool) Safety() tools.Safety {
-	return tools.Safety{SideEffect: tools.SideEffectRead, Permission: tools.PermissionAllow}
-}
-func (t countingSchemaTool) Run(_ context.Context, _ map[string]any) tools.Result {
-	return tools.Result{Status: tools.StatusOK}
-}
-
-// The cache renders a tool's schema once and reuses it across calls, and its
-// output is identical to the uncached path.
-func TestPartitionToolsCacheRendersOnceAndMatchesUncached(t *testing.T) {
-	calls := 0
-	registry := tools.NewRegistry()
-	registry.Register(countingSchemaTool{name: "alpha", calls: &calls})
-	registry.Register(countingSchemaTool{name: "beta", calls: &calls})
-
-	uncached, _ := partitionTools(registry, PermissionModeAuto, Options{}, map[string]bool{})
-
-	base := calls
-	cache := map[string]zeroruntime.ToolDefinition{}
-	first, _ := partitionToolsCached(registry, PermissionModeAuto, Options{}, map[string]bool{}, cache)
-	rendersAfterFirst := calls - base
-	second, _ := partitionToolsCached(registry, PermissionModeAuto, Options{}, map[string]bool{}, cache)
-	rendersAfterSecond := calls - base
-
-	if rendersAfterFirst != 2 {
-		t.Fatalf("first cached call should render 2 tools once each, rendered %d times", rendersAfterFirst)
-	}
-	if rendersAfterSecond != 2 {
-		t.Fatalf("second cached call must reuse the cache (no new schema reads), total renders = %d", rendersAfterSecond)
-	}
-	if !reflect.DeepEqual(first, second) {
-		t.Fatal("cached calls must return identical definitions")
-	}
-	if !reflect.DeepEqual(first, uncached) {
-		t.Fatal("cached output must match the uncached partitionTools output")
-	}
-}

internal/agent/plan_staleness_test.go

@@ -1,64 +0,0 @@
-package agent
-
-import (
-	"strings"
-	"testing"
-
-	"github.com/Gitlawb/zero/internal/zeroruntime"
-)
-
-func planUpdateTurn(status string) zeroruntime.CollectedStream {
-	return zeroruntime.CollectedStream{ToolCalls: []zeroruntime.ToolCall{
-		{Name: "update_plan", Arguments: `{"plan":[{"content":"step one","status":"` + status + `"}]}`},
-	}}
-}
-
-// Turn-based staleness: a plan that goes many turns without an update — while
-// items are still pending — draws the stale reminder even though few tool calls
-// have run (the tool-call streak alone would not have tripped).
-func TestPlanReminderFiresOnTurnStaleness(t *testing.T) {
-	state := newGuardState()
-	state.observeTurn(planUpdateTurn("in_progress"))
-
-	// Text-only turns advance the turn counter without adding tool calls.
-	for range stalePlanTurnThreshold {
-		state.observeTurn(zeroruntime.CollectedStream{Text: "still working…"})
-	}
-
-	if state.toolCallsSincePlanUpdate >= staleToolCallThreshold {
-		t.Fatalf("precondition: the tool-call trigger must not fire (%d calls)", state.toolCallsSincePlanUpdate)
-	}
-	if got := state.planReminder(stalePlanTurnThreshold + 2); !strings.Contains(got, planStaleReminderMarker) {
-		t.Fatalf("expected a turn-based stale reminder, got %q", got)
-	}
-}
-
-// A fully-completed plan is NOT stale: no pending items means the turn-based
-// trigger stays quiet even after many turns, so a finished plan isn't nagged.
-func TestPlanReminderSkipsTurnStalenessWhenComplete(t *testing.T) {
-	state := newGuardState()
-	state.observeTurn(planUpdateTurn("completed"))
-
-	for range stalePlanTurnThreshold + 3 {
-		state.observeTurn(zeroruntime.CollectedStream{Text: "wrapping up…"})
-	}
-
-	if got := state.planReminder(stalePlanTurnThreshold + 5); got != "" {
-		t.Fatalf("a completed plan must not draw a stale reminder, got %q", got)
-	}
-}
-
-// A plan update resets the turn counter, so the stale reminder does not fire
-// right after a fresh update.
-func TestPlanUpdateResetsTurnStaleness(t *testing.T) {
-	state := newGuardState()
-	state.observeTurn(planUpdateTurn("in_progress"))
-	for range stalePlanTurnThreshold - 1 {
-		state.observeTurn(zeroruntime.CollectedStream{Text: "working…"})
-	}
-	// Refresh the plan — resets the turn streak.
-	state.observeTurn(planUpdateTurn("in_progress"))
-	if got := state.planReminder(stalePlanTurnThreshold + 1); got != "" {
-		t.Fatalf("a just-refreshed plan must not be stale, got %q", got)
-	}
-}

internal/agent/prompt_budget_test.go

@@ -1,51 +0,0 @@
-package agent
-
-import (
-	"testing"
-
-	"github.com/Gitlawb/zero/internal/tools"
-)
-
-// These ceilings are a deliberate ratchet on Zero's fixed per-turn overhead — the
-// system prompt and the eager tool schemas that ride on EVERY request. They are
-// set ~10% above the current measured cost, using ApproxTextTokens (the same
-// estimate the compaction loop and /context use, ~non-whitespace-bytes/4). A change
-// that pushes either past its ceiling must be justified (and the ceiling raised
-// deliberately) or trimmed — the per-turn floor should not creep up silently.
-//
-// Measured baselines (2026-07): base system prompt ~3160 tokens; the tools a normal
-// (auto permission-mode) interactive turn sends ~2430 tokens. The tool figure is
-// the auto-mode advertised set, not the full core registry — higher-risk tools that
-// only advertise in other modes are excluded, matching what a real turn actually
-// pays.
-const (
-	maxBaseSystemPromptTokens = 3500
-	maxEagerToolSchemaTokens  = 2700
-)
-
-func TestSystemPromptTokenBudget(t *testing.T) {
-	// Minimal render: a model is set (so the session block renders) but no Cwd, so
-	// the workspace map, project guidelines, and repo map are excluded — this is the
-	// fixed base every session pays regardless of the workspace it runs in.
-	prompt := buildSystemPrompt(Options{Model: "claude-opus-4-8"})
-	got := ApproxTextTokens(prompt)
-	t.Logf("base system prompt: %d tokens (%d bytes)", got, len(prompt))
-	if got > maxBaseSystemPromptTokens {
-		t.Fatalf("base system prompt is %d tokens, over the %d ceiling — trim it or raise the ceiling deliberately", got, maxBaseSystemPromptTokens)
-	}
-}
-
-func TestEagerToolSchemaTokenBudget(t *testing.T) {
-	registry := tools.NewRegistry()
-	for _, tool := range tools.CoreToolsScoped(t.TempDir(), nil) {
-		registry.Register(tool)
-	}
-	// Options{} keeps DeferThreshold at 0, so deferral is inactive and every core
-	// tool is exposed eagerly — exactly what a plugin-free session sends each turn.
-	exposed, _ := partitionTools(registry, PermissionModeAuto, Options{}, map[string]bool{})
-	got := estimateToolDefTokens(exposed)
-	t.Logf("eager core tool schemas: %d tokens across %d tools", got, len(exposed))
-	if got > maxEagerToolSchemaTokens {
-		t.Fatalf("eager tool schemas are %d tokens, over the %d ceiling — defer a tool or raise the ceiling deliberately", got, maxEagerToolSchemaTokens)
-	}
-}

internal/agent/reconnect.go

@@ -3,11 +3,9 @@ package agent
 import (
 	"context"
 	"fmt"
-	"math/rand"
 	"strings"
 	"time"
 
-	"github.com/Gitlawb/zero/internal/errhint"
 	"github.com/Gitlawb/zero/internal/zeroruntime"
 )
 
@@ -19,20 +17,10 @@ import (
 // times. We retry ONLY the connect (not a partially-consumed stream), so no
 // already-forwarded OnText is ever duplicated.
 const (
-	// maxStreamReconnects is how many times the connect is re-issued after a
-	// transient disconnect. 4 (not 2): with jittered exponential backoff this rides
-	// out a multi-second network blip (~0.5s + 1s + 2s + 4s worst case) instead of
-	// dying on a 2s hiccup and re-burning every token on a restart.
-	maxStreamReconnects = 4
-	// streamReconnectMax caps a single backoff so the tail attempts don't wait
-	// minutes on a long outage.
-	streamReconnectMax = 8 * time.Second
+	maxStreamReconnects = 2
+	streamReconnectBase = 500 * time.Millisecond
 )
 
-// streamReconnectBase is the first-retry delay (doubled each subsequent attempt).
-// A var, not a const, so tests can shrink it to keep the exhaustion path fast.
-var streamReconnectBase = 500 * time.Millisecond
-
 // reconnectNotifier is called before each retry with the 1-based attempt number
 // and the max, so the caller can surface a "Reconnecting N/max" notice. Nil is
 // fine.
@@ -85,7 +73,7 @@ func streamWithReconnect(ctx context.Context, provider Provider, request zerorun
 		if notify != nil {
 			notify(attempt, maxStreamReconnects)
 		}
-		if waitErr := sleepWithContext(ctx, jitteredBackoff(attempt)); waitErr != nil {
+		if waitErr := sleepWithContext(ctx, backoffFor(attempt)); waitErr != nil {
 			return nil, err // ctx cancelled while waiting; surface the original error
 		}
 		stream, err = provider.StreamCompletion(ctx, request)
@@ -108,19 +96,6 @@ func shouldReconnect(ctx context.Context, err error) bool {
 	if isContextLimitError(msg) || isImageRejectionError(err) {
 		return false
 	}
-	// HTTP 5xx statuses are non-reconnectable and must be excluded BEFORE the
-	// transport substring match below — otherwise "504 Gateway Timeout" would slip
-	// through on the generic "timeout" needle. 503 already exhausted
-	// providerio.SendWithRetry (retrying is a redundant double-retry); 500/502/504
-	// are non-idempotent by providerio's rule — the completion POST may already
-	// have reached the model before the upstream/gateway gave up, so replaying the
-	// connect risks duplicate billable work. Digit-boundary matched so an
-	// incidental "504" inside a latency/id number is not mistaken for a status.
-	if errhint.HasStatusCode(msg, "500", "502", "503", "504") {
-		return false
-	}
-	// Transport-level disconnects only. A genuine transport failure (EOF, reset,
-	// refused, timeout) means no response was received, which is safe to reconnect.
 	for _, needle := range []string{
 		"eof",
 		"connection reset",
@@ -131,6 +106,8 @@ func shouldReconnect(ctx context.Context, err error) bool {
 		"timed out",
 		"temporarily unavailable",
 		"i/o timeout",
+		"503",
+		"502",
 		"server closed",
 		"unexpected end",
 	} {
@@ -141,31 +118,14 @@ func shouldReconnect(ctx context.Context, err error) bool {
 	return false
 }
 
-// backoffFor is the deterministic exponential base delay for a 1-based attempt,
-// capped at streamReconnectMax. Jitter is layered on separately (jitteredBackoff).
 func backoffFor(attempt int) time.Duration {
 	d := streamReconnectBase
 	for i := 1; i < attempt; i++ {
-		if d >= streamReconnectMax {
-			return streamReconnectMax
-		}
 		d *= 2
 	}
-	if d > streamReconnectMax {
-		d = streamReconnectMax
-	}
 	return d
 }
 
-// jitteredBackoff adds up to 50% random jitter on top of backoffFor so concurrent
-// runs (swarm members, a cron fleet) that all trip on the same outage don't
-// reconnect in lockstep and hammer a recovering endpoint. Never shorter than the
-// deterministic base, so backoff still grows attempt over attempt.
-func jitteredBackoff(attempt int) time.Duration {
-	base := backoffFor(attempt)
-	return base + time.Duration(rand.Int63n(int64(base/2)+1))
-}
-
 func sleepWithContext(ctx context.Context, d time.Duration) error {
 	timer := time.NewTimer(d)
 	defer timer.Stop()

internal/agent/reconnect_test.go

@@ -44,10 +44,6 @@ func TestStreamWithReconnectRecoversFromTransientDisconnect(t *testing.T) {
 }
 
 func TestStreamWithReconnectGivesUpAfterMax(t *testing.T) {
-	// Shrink the backoff so exhausting all retries stays fast (real base would
-	// sleep ~7.5s across 4 attempts).
-	defer func(orig time.Duration) { streamReconnectBase = orig }(streamReconnectBase)
-	streamReconnectBase = time.Millisecond
 	// Always fails with a disconnect error → exhausts retries and returns it.
 	p := &flakyProvider{failBefore: 99, failErr: errors.New("connection reset by peer")}
 	_, err := streamWithReconnect(context.Background(), p, zeroruntime.CompletionRequest{}, nil)
@@ -91,7 +87,7 @@ func TestShouldReconnectClassification(t *testing.T) {
 	ctx := context.Background()
 	disconnects := []string{
 		"unexpected EOF", "connection reset by peer", "broken pipe",
-		"i/o timeout", "server closed the connection", "connection refused",
+		"i/o timeout", "503 Service Unavailable", "server closed the connection",
 	}
 	for _, m := range disconnects {
 		if !shouldReconnect(ctx, errors.New(m)) {
@@ -101,13 +97,6 @@ func TestShouldReconnectClassification(t *testing.T) {
 	notDisconnects := []string{
 		"context length exceeded", "invalid api key", "model not found",
 		"400 bad request: unsupported parameter",
-		// HTTP 5xx statuses are handled by providerio.SendWithRetry (503) or are
-		// non-idempotent (500/502/504); the reconnect path must not double-retry
-		// them. "504 Gateway Timeout" must NOT slip through on the generic "timeout"
-		// transport signal — a gateway timeout is non-idempotent, since the upstream
-		// may have already processed the completion POST before giving up.
-		"503 Service Unavailable", "502 Bad Gateway",
-		"504 Gateway Timeout", "500 Internal Server Error",
 	}
 	for _, m := range notDisconnects {
 		if shouldReconnect(ctx, errors.New(m)) {
@@ -123,24 +112,6 @@ func TestBackoffGrows(t *testing.T) {
 	if backoffFor(2) != 2*streamReconnectBase {
 		t.Fatalf("attempt 2 backoff = %v, want %v", backoffFor(2), 2*streamReconnectBase)
 	}
-	// The exponential base is capped so late attempts don't wait minutes.
-	if got := backoffFor(20); got != streamReconnectMax {
-		t.Fatalf("attempt 20 backoff = %v, want cap %v", got, streamReconnectMax)
-	}
-}
-
-func TestJitteredBackoffStaysInBounds(t *testing.T) {
-	// Jitter never drops below the deterministic base and never exceeds base*1.5,
-	// so backoff still grows attempt over attempt while decorrelating retries.
-	for attempt := 1; attempt <= 5; attempt++ {
-		base := backoffFor(attempt)
-		for i := 0; i < 200; i++ {
-			got := jitteredBackoff(attempt)
-			if got < base || got > base+base/2 {
-				t.Fatalf("attempt %d jittered backoff %v out of [%v, %v]", attempt, got, base, base+base/2)
-			}
-		}
-	}
 }
 
 func TestReconnectNoticeRoutesThroughReasoning(t *testing.T) {

internal/agent/skills_context_test.go

@@ -1,88 +0,0 @@
-package agent
-
-import (
-	"strconv"
-	"strings"
-	"testing"
-)
-
-func TestSkillsContextCapsLongList(t *testing.T) {
-	// 60 skills with realistic trigger-rich descriptions (~180 chars each, under
-	// the 200-rune truncation) total well past the 4096-byte list budget, so the
-	// overflow summary must kick in while the block stays bounded.
-	longDesc := strings.Repeat("use when the request touches deployments, release notes, or verification; ", 2) + "number "
-	skills := make([]SkillInfo, 0, 60)
-	for i := 0; i < 60; i++ {
-		n := strconv.Itoa(i)
-		skills = append(skills, SkillInfo{Name: "skill-" + n, Description: longDesc + n})
-	}
-	got := skillsContext(Options{Skills: skills})
-	if len(got) > skillsContextListBudget+1000 {
-		t.Fatalf("skills block should stay bounded near the %d-byte budget, got %d bytes:\n%s", skillsContextListBudget, len(got), got)
-	}
-	if !strings.Contains(got, "more (call skill") {
-		t.Fatalf("expected an overflow summary line, got:\n%s", got)
-	}
-	// The first skill is always listed regardless of budget.
-	if !strings.Contains(got, "- skill-0:") {
-		t.Fatalf("expected the first skill to always be listed, got:\n%s", got)
-	}
-}
-
-// A realistic mid-size skill set (20 skills, trigger-rich descriptions) must be
-// listed in FULL — no overflow summary. This pins the fix for the old 640-byte
-// budget, under which skills past ~#6 were invisible to the model and therefore
-// never triggered.
-func TestSkillsContextListsRealisticSetInFull(t *testing.T) {
-	desc := "Use when the user asks about deployments, release notes, or pre-merge verification runs."
-	skills := make([]SkillInfo, 0, 20)
-	for i := 0; i < 20; i++ {
-		skills = append(skills, SkillInfo{Name: "skill-" + strconv.Itoa(i), Description: desc})
-	}
-	got := skillsContext(Options{Skills: skills})
-	if strings.Contains(got, "more (call skill") {
-		t.Fatalf("20 described skills must all be listed without overflow, got:\n%s", got)
-	}
-	for i := 0; i < 20; i++ {
-		if !strings.Contains(got, "- skill-"+strconv.Itoa(i)+":") {
-			t.Fatalf("skill-%d missing from the list:\n%s", i, got)
-		}
-	}
-}
-
-func TestSkillsContext(t *testing.T) {
-	if got := skillsContext(Options{}); got != "" {
-		t.Fatalf("no skills should yield an empty section, got %q", got)
-	}
-	got := skillsContext(Options{Skills: []SkillInfo{
-		{Name: "commit-writer", Description: "Write a conventional-commit message."},
-		{Name: "  ", Description: "nameless, should be skipped"},
-		{Name: "reviewer"},
-	}})
-	if !strings.Contains(got, "<available_skills>") || !strings.Contains(got, "</available_skills>") {
-		t.Fatalf("missing available_skills block: %q", got)
-	}
-	if !strings.Contains(got, "- commit-writer: Write a conventional-commit message.") {
-		t.Fatalf("missing commit-writer line: %q", got)
-	}
-	if !strings.Contains(got, "- reviewer\n") {
-		t.Fatalf("reviewer (no description) line missing: %q", got)
-	}
-	if strings.Contains(got, "nameless") {
-		t.Fatalf("nameless entry should be skipped: %q", got)
-	}
-}
-
-func TestSystemPromptIncludesSkillsOnlyWhenInstalled(t *testing.T) {
-	with := buildSystemPrompt(Options{Skills: []SkillInfo{
-		{Name: "commit-writer", Description: "Write a commit message."},
-	}})
-	if !strings.Contains(with, "<available_skills>") || !strings.Contains(with, "skill tool") {
-		t.Fatalf("expected available_skills guidance in system prompt: %q", with)
-	}
-	// Default (no skills) must reproduce the prior prompt: no skills block.
-	without := buildSystemPrompt(Options{})
-	if strings.Contains(without, "<available_skills>") {
-		t.Fatalf("available_skills block must not appear without skills")
-	}
-}

internal/agent/system_prompt.go

@@ -5,11 +5,9 @@ import (
 	"os"
 	"path/filepath"
 	"runtime"
-	"strconv"
 	"strings"
 	"unicode/utf8"
 
-	"github.com/Gitlawb/zero/internal/config"
 	"github.com/Gitlawb/zero/internal/repomap"
 	"github.com/Gitlawb/zero/internal/workspaceseed"
 )
@@ -39,14 +37,6 @@ const fallbackSystemPrompt = "You are Zero, a terminal coding agent. Help with t
 // general-to-specific order.
 var projectContextFiles = []string{"AGENTS.md", "ZERO.md", ".zero/AGENTS.md"}
 
-// userContextFile is the per-user instruction file, resolved under
-// config.UserConfigDir()/zero/ alongside the rest of Zero's per-user config
-// (config.json, commands, specialists) so users can keep personal guidance out
-// of individual repositories.
-const userContextFile = "ZERO.md"
-
-var userConfigDirForPrompt = config.UserConfigDir
-
 // maxProjectContextBytes caps how much of a single project doc is injected so
 // a large guidelines file can't blow the context budget.
 const maxProjectContextBytes = 8 << 10 // 8 KiB per file
@@ -90,22 +80,12 @@ func buildSystemPrompt(options Options) string {
 	if seed := workspaceSeedContext(options.Cwd); seed != "" {
 		sections = append(sections, seed)
 	}
-	// User guidelines are injected before workspace/project guidelines so the
-	// project's AGENTS.md/ZERO.md is the later, more specific instruction
-	// block. See userGuidelines for the explicit precedence note carried in
-	// the section text itself.
-	if user := userGuidelines(); user != "" {
-		sections = append(sections, user)
-	}
 	if ws := workspaceContext(options.Cwd); ws != "" {
 		sections = append(sections, ws)
 	}
 	if delegation := specialistDelegationContext(options); delegation != "" {
 		sections = append(sections, delegation)
 	}
-	if skillsBlock := skillsContext(options); skillsBlock != "" {
-		sections = append(sections, skillsBlock)
-	}
 	if style := responseStyleContext(options); style != "" {
 		sections = append(sections, style)
 	}
@@ -184,75 +164,6 @@ func specialistDelegationContext(options Options) string {
 	return b.String()
 }
 
-// skillsContext lists the reusable skills the model can pull in on demand via the
-// skill tool, so it invokes the right one on the first try instead of guessing a
-// name, failing, and reading the error. It mirrors specialistDelegationContext:
-// names + one-line descriptions only (never skill bodies), and it renders nothing
-// when no skills are installed, so a skill-less run reproduces the previous prompt
-// byte-for-byte.
-// skillsContextListBudget bounds the bytes spent listing individual skills so a
-// workspace with an extreme number of them can't bloat every turn's prompt.
-// Skills past the budget are summarized as a count rather than dropped — the
-// model can still load any of them by name (an unknown name returns the full
-// list from the skill tool).
-//
-// The budget is deliberately generous — roughly 18 skills with maximally long
-// (200-rune, ASCII) descriptions, or 40+ with typical terser ones; non-ASCII
-// descriptions consume it faster since the budget counts bytes. This list is
-// the model's ONLY discovery surface, so a skill squeezed out of it effectively
-// never triggers. The previous 640-byte cap silently broke invocation for
-// anyone with more than ~6 skills — the model cannot match a request against a
-// skill it cannot see.
-const skillsContextListBudget = 4096
-
-func skillsContext(options Options) string {
-	if len(options.Skills) == 0 {
-		return ""
-	}
-	var b strings.Builder
-	b.WriteString("<available_skills>\n")
-	b.WriteString("Reusable, on-demand instruction sets you can load with the skill tool. Before acting on a request, scan this list; when the request matches a skill's name or description, call skill with its exact name FIRST and follow the loaded guidance — do not guess names, do not skip a matching skill, and do not substitute your own approach for its instructions.\n")
-	listed, spent, omitted := 0, 0, 0
-	for _, info := range options.Skills {
-		name := strings.TrimSpace(info.Name)
-		if name == "" {
-			continue
-		}
-		line := "- " + name
-		if desc := strings.TrimSpace(info.Description); desc != "" {
-			line += ": " + truncateForSkillLine(desc)
-		}
-		line += "\n"
-		// Always list at least one skill; past the budget, summarize the remainder
-		// as a count instead of silently dropping it.
-		if listed > 0 && spent+len(line) > skillsContextListBudget {
-			omitted++
-			continue
-		}
-		b.WriteString(line)
-		spent += len(line)
-		listed++
-	}
-	if omitted > 0 {
-		b.WriteString("- …and " + strconv.Itoa(omitted) + " more (call skill with a name; an unknown name lists them all)\n")
-	}
-	b.WriteString("</available_skills>")
-	return b.String()
-}
-
-// truncateForSkillLine keeps a skill's one-line description short so a single
-// verbose description can't dominate the skills-list budget. The cap is roomy on
-// purpose: the description carries the skill's trigger conditions ("use when…"),
-// and truncating those is what stops the model from ever invoking the skill.
-func truncateForSkillLine(desc string) string {
-	const maxDescRunes = 200
-	runes := []rune(desc)
-	if len(runes) <= maxDescRunes {
-		return desc
-	}
-	return strings.TrimSpace(string(runes[:maxDescRunes])) + "…"
-}
-
 func sessionRuntimeContext(options Options) string {
 	provider := strings.TrimSpace(options.ProviderName)
 	model := strings.TrimSpace(options.Model)
@@ -286,7 +197,7 @@ func workspaceContext(cwd string) string {
 	b.WriteString("Working directory: " + cwd + "\n")
 	b.WriteString("Operating system: " + runtime.GOOS + "\n")
 	if runtime.GOOS == "windows" {
-		b.WriteString("Shell syntax: Windows cmd.exe syntax for exec_command/bash tools; prefer the workdir/cwd argument instead of cd when changing directories. Do not pipe to or invoke POSIX coreutils from Git for Windows (usr\\bin head/grep/tail/cat/...): they are MSYS binaries and fail under the write-restricted sandbox; use native Zero tools (grep, read_file, list_directory, glob) or cmd.exe findstr/more instead, or sandbox_permissions require_escalated only when host-level execution is truly required.\n")
+		b.WriteString("Shell syntax: Windows cmd.exe syntax for exec_command/bash tools; prefer the workdir/cwd argument instead of cd when changing directories.\n")
 	} else {
 		b.WriteString("Shell syntax: /bin/sh syntax for exec_command/bash tools; prefer the workdir/cwd argument instead of cd when changing directories.\n")
 	}
@@ -339,7 +250,13 @@ func projectGuidelines(cwd, gitRoot string) string {
 		if remaining := maxProjectContextTotalBytes - totalUsed; remaining < limit {
 			limit = remaining
 		}
-		content = truncateGuidelineContent(content, limit)
+		if len(content) > limit {
+			cut := limit
+			for cut > 0 && !utf8.RuneStart(content[cut]) {
+				cut--
+			}
+			content = content[:cut] + "\n… (truncated)"
+		}
 		label := projectGuidelineLabel(match, gitRoot)
 		b.WriteString("\n\n## Project guidelines (" + label + ")\n\n" + content)
 		totalUsed += len(content)
@@ -347,92 +264,6 @@ func projectGuidelines(cwd, gitRoot string) string {
 	return b.String()
 }
 
-// userGuidelines returns the per-user ZERO.md instructions block, if present.
-// The file lives in config.UserConfigDir()/zero/ next to Zero's other
-// per-user config; the basename match is case-insensitive so a file saved as
-// zero.md still resolves on case-sensitive filesystems, mirroring the project
-// guideline loader. The section carries an explicit precedence note because
-// this is a global, personal preferences file: it is injected earlier in the
-// prompt than the project's AGENTS.md/ZERO.md (see buildSystemPrompt), and
-// the note keeps that precedence unambiguous even if a model weighs later
-// context more heavily than section order alone implies.
-func userGuidelines() string {
-	configDir, err := userConfigDirForPrompt()
-	if err != nil {
-		return ""
-	}
-	configDir = strings.TrimSpace(configDir)
-	if configDir == "" {
-		return ""
-	}
-	match := findCaseInsensitiveFile(filepath.Join(configDir, "zero"), userContextFile)
-	if match == "" {
-		return ""
-	}
-	data, err := os.ReadFile(match)
-	if err != nil {
-		return ""
-	}
-	content := strings.TrimSpace(string(data))
-	if content == "" {
-		return ""
-	}
-	content = truncateGuidelineContent(content, maxProjectContextBytes)
-	return "## User guidelines (" + filepath.Base(match) + ")\n\n" +
-		"These are the operator's personal preferences, not project policy. " +
-		"Where they conflict with a repository's project guidelines below (AGENTS.md/ZERO.md), the project guidelines take precedence.\n\n" +
-		content
-}
-
-// truncationMarker is appended to guideline content that was cut short.
-const truncationMarker = "\n… (truncated)"
-
-// truncateGuidelineContent caps content at limit bytes without splitting a
-// UTF-8 rune, appending a truncation marker when anything was cut. Space for
-// the marker is reserved before choosing the cut point. When limit is too
-// small to fit the marker itself, the marker is dropped instead, so the
-// returned string never exceeds limit for any non-negative limit.
-func truncateGuidelineContent(content string, limit int) string {
-	if len(content) <= limit {
-		return content
-	}
-	if limit <= 0 {
-		return ""
-	}
-	cut := limit - len(truncationMarker)
-	if cut < 0 {
-		cut = 0
-	}
-	for cut > 0 && !utf8.RuneStart(content[cut]) {
-		cut--
-	}
-	if truncated := content[:cut] + truncationMarker; len(truncated) <= limit {
-		return truncated
-	}
-	// limit is smaller than the marker itself: fall back to a hard,
-	// rune-safe cut at limit bytes with no marker rather than exceeding it.
-	end := limit
-	for end > 0 && !utf8.RuneStart(content[end]) {
-		end--
-	}
-	return content[:end]
-}
-
-// findCaseInsensitiveFile returns the on-disk path of the regular file in dir
-// whose name matches basename case-insensitively, or "" when absent.
-func findCaseInsensitiveFile(dir, basename string) string {
-	entries, err := os.ReadDir(dir)
-	if err != nil {
-		return ""
-	}
-	for _, e := range entries {
-		if !e.IsDir() && strings.EqualFold(e.Name(), basename) {
-			return filepath.Join(dir, e.Name())
-		}
-	}
-	return ""
-}
-
 // projectGuidelineDirs returns the directory chain from gitRoot to cwd
 // (inclusive), in root-to-leaf order. If gitRoot is empty or unreachable
 // from cwd, the chain collapses to [cwd].
@@ -479,22 +310,29 @@ func projectGuidelineLabel(match, gitRoot string) string {
 
 // findProjectContextFile returns the first matching project guideline file
 // in dir. Lookup is case-insensitive on the basename and on the actual
-// filename returned, so a git-tracked file like AGENTS.md still resolves to
-// its true filename on case-sensitive filesystems — the returned path is what
-// should appear in the project guidelines label.
+// filename returned, so a git-tracked file like AGENTS.MD (uppercase MD)
+// still resolves to its true filename on case-sensitive filesystems — the
+// returned path is what should appear in the project guidelines label.
 // Returns "" when nothing matches.
 func findProjectContextFile(dir string) string {
 	for _, name := range projectContextFiles {
+		baseLower := strings.ToLower(filepath.Base(name))
 		// Walk to the file's parent through dir with case-insensitive segment
-		// matching, then find a regular file with the same basename. This works
-		// on both case-sensitive and case-insensitive filesystems and always
-		// returns the on-disk filename.
+		// matching, then find a regular file with the same lowercased
+		// basename. This works on both case-sensitive and case-insensitive
+		// filesystems and always returns the on-disk filename.
 		parent, ok := resolveDirCaseInsensitive(filepath.Dir(filepath.Join(dir, name)), dir)
 		if !ok {
 			continue
 		}
-		if match := findCaseInsensitiveFile(parent, filepath.Base(name)); match != "" {
-			return match
+		entries, err := os.ReadDir(parent)
+		if err != nil {
+			continue
+		}
+		for _, e := range entries {
+			if !e.IsDir() && strings.ToLower(e.Name()) == baseLower {
+				return filepath.Join(parent, e.Name())
+			}
 		}
 	}
 	return ""

internal/agent/system_prompt.md

@@ -46,10 +46,14 @@ work.
    formatting-only edits unless the user asked for them.
 4. **Verify.** Verify after edits; see the testing gate below. This is
    mandatory.
-5. **Summarize.** Close with a summary scaled to the work: a trivial fix earns one
-   line; a substantial change earns a few short bullets covering what changed, where
-   it lives, and what you did and did not verify. Lead with the outcome, and never
-   pad — do not restate the task or narrate steps the user already watched you take.
+5. **Summarize.** For a substantial task, close with an ELABORATE, well-structured
+   summary — never a single throwaway line. Use short headings and bullets: a
+   one-line "what I built/changed"; **Where it lives** — the key files and how they
+   fit together; **How each requirement is met** — walk through each requirement
+   from the request and name the specifics that satisfy it; what validation ran and
+   what was NOT verified; and a brief "Next steps" or "Want me to…?" offer. Scale
+   the depth to the work — a big build earns several sections, a trivial fix earns
+   a line or two.
 
 ## Editing discipline
 
@@ -60,13 +64,7 @@ work.
 - Make one tool call per file. Do not batch multi-file writes into a single
   shell or script invocation.
 - For edits to existing files, prefer edit_file or apply_patch with minimal,
-  targeted diffs. Match the existing indentation, imports, and idioms. Match the
-  file's comment density: do not add explanatory comments unless the user asks or
-  the code is already comment-dense.
-- Solve the problem as posed, not a more general version of it. Add no
-  speculative abstraction, configurability, or handling for cases that cannot
-  occur, and nothing the user did not ask for. A small diff can still be
-  over-built; if a 200-line solution could be 50, rewrite it.
+  targeted diffs. Match the existing indentation, imports, and idioms.
 - Preserve behavior you were not asked to change. Do not delete or rewrite code
   you did not author unless the task requires it; if you must, say so.
 

internal/agent/system_prompt_models.go

@@ -6,13 +6,11 @@ import "strings"
 //
 // Different model families respond to different framing: the GPT family benefits
 // from an explicit markdown/output spec and a strong "prefer native tools" nudge;
-// Gemini benefits from explicit tool-preference and conciseness guidance. The
-// Claude family is already aligned with the core prompt and needs no addendum —
-// comment discipline is universal in the core prompt now, so every family gets it.
-// modelPromptAddendum returns the family-specific block appended after the core
-// prompt, or "" when the family is unknown or needs no specialization.
-// Classification is by model id (the agent only has the model string — no registry
-// dependency).
+// Gemini benefits from explicit tool-preference and conciseness guidance; the
+// Claude family is already well-aligned with the core prompt and only needs a
+// light comment-discipline nudge. modelPromptAddendum returns the family-specific
+// block appended after the core prompt. Classification is by model id (the agent
+// only has the model string — no registry dependency).
 
 const (
 	familyOpenAI    = "openai"
@@ -47,10 +45,9 @@ func modelPromptAddendum(model string) string {
 		return openAIPromptAddendum
 	case familyGemini:
 		return geminiPromptAddendum
+	case familyAnthropic:
+		return anthropicPromptAddendum
 	default:
-		// Anthropic (aligned with the core prompt) and unknown families get no
-		// family-specific block; comment discipline now lives in the core prompt
-		// for every model.
 		return ""
 	}
 }
@@ -73,3 +70,8 @@ const geminiPromptAddendum = `<model_guidance>
   in one short clause why it is needed.
 - Use update_plan for any multi-step task and keep it current.
 </model_guidance>`
+
+const anthropicPromptAddendum = `<model_guidance>
+- Do not add code comments unless the user asks or the surrounding code is
+  comment-dense; match the file's existing comment density.
+</model_guidance>`

internal/agent/system_prompt_models_test.go

@@ -29,11 +29,9 @@ func TestBuildSystemPromptAppendsModelAddendum(t *testing.T) {
 	if got := buildSystemPrompt(Options{Model: "gpt-5"}); !strings.Contains(got, openAIPromptAddendum) {
 		t.Fatalf("expected the OpenAI addendum in the gpt-5 prompt")
 	}
-	// Claude is aligned with the core prompt and gets no family addendum now that
-	// comment discipline is universal; it must not pick up another family's block.
 	claude := buildSystemPrompt(Options{Model: "claude-opus-4-6"})
-	if strings.Contains(claude, "<model_guidance>") {
-		t.Fatalf("expected no model_guidance block for Claude (aligned with core prompt)")
+	if !strings.Contains(claude, anthropicPromptAddendum) {
+		t.Fatalf("expected the Anthropic addendum in the claude prompt")
 	}
 	if strings.Contains(claude, openAIPromptAddendum) {
 		t.Fatalf("the claude prompt must not contain the OpenAI addendum")

internal/agent/system_prompt_test.go

@@ -9,25 +9,6 @@ import (
 	"github.com/Gitlawb/zero/internal/sandbox"
 )
 
-// TestMain points userConfigDirForPrompt at an empty, package-wide temp
-// directory for every test in this package. Without this, buildSystemPrompt
-// falls back to the real config.UserConfigDir, so any developer with a
-// personal ~/.config/zero/ZERO.md would get its content folded into
-// otherwise-unrelated prompt assertions, making test runs non-deterministic
-// across contributor machines. Tests that specifically exercise user
-// guidelines stub userConfigDirForPrompt themselves via
-// withSystemPromptTestUserConfigDir(Func) and restore this default on cleanup.
-func TestMain(m *testing.M) {
-	dir, err := os.MkdirTemp("", "zero-agent-tests-*")
-	if err != nil {
-		panic(err)
-	}
-	userConfigDirForPrompt = func() (string, error) { return dir, nil }
-	code := m.Run()
-	os.RemoveAll(dir)
-	os.Exit(code)
-}
-
 func TestCoreSystemPromptIncludesCodingQualityRules(t *testing.T) {
 	prompt := strings.ToLower(buildSystemPrompt(Options{}))
 
@@ -42,8 +23,7 @@ func TestCoreSystemPromptIncludesCodingQualityRules(t *testing.T) {
 		"avoid broad refactors",
 		"search the web before answering",
 		"do not recognize",
-		"scaled to the work",
-		"comment density",
+		"how each requirement is met",
 	} {
 		if !strings.Contains(prompt, want) {
 			t.Fatalf("expected core system prompt to include %q, got:\n%s", want, buildSystemPrompt(Options{}))
@@ -147,90 +127,8 @@ func systemPromptTestBlock(t *testing.T, prompt, start, end string) string {
 	return body
 }
 
-func TestBuildSystemPromptIncludesUserGuidelines(t *testing.T) {
-	configDir := t.TempDir()
-	writeSystemPromptTestFile(t, configDir, "zero/ZERO.md", "  Prefer concise summaries.  \n")
-	t.Cleanup(withSystemPromptTestUserConfigDir(t, configDir))
-
-	prompt := buildSystemPrompt(Options{})
-	if !strings.Contains(prompt, "## User guidelines (ZERO.md)") {
-		t.Fatalf("expected user guidelines header, got:\n%s", prompt)
-	}
-	if !strings.Contains(prompt, "Prefer concise summaries.") {
-		t.Fatalf("expected user guidelines content, got:\n%s", prompt)
-	}
-	if strings.Contains(prompt, "  Prefer concise summaries.  ") {
-		t.Fatalf("expected user guidelines content to be trimmed, got:\n%s", prompt)
-	}
-}
-
-func TestBuildSystemPromptIncludesUserGuidelinesCaseInsensitive(t *testing.T) {
-	configDir := t.TempDir()
-	writeSystemPromptTestFile(t, configDir, "zero/zero.md", "Prefer concise summaries.\n")
-	t.Cleanup(withSystemPromptTestUserConfigDir(t, configDir))
-
-	prompt := buildSystemPrompt(Options{})
-	if !strings.Contains(prompt, "## User guidelines (zero.md)") {
-		t.Fatalf("expected case-insensitive zero.md resolution, got:\n%s", prompt)
-	}
-	if !strings.Contains(prompt, "Prefer concise summaries.") {
-		t.Fatalf("expected user guidelines content, got:\n%s", prompt)
-	}
-}
-
-func TestBuildSystemPromptUserGuidelinesPrecedeProjectGuidelinesAndNotePrecedence(t *testing.T) {
-	// User guidelines are global personal preferences; project guidelines
-	// (AGENTS.md/ZERO.md) must be the later, more specific instruction block,
-	// and the user section must say so explicitly so the precedence holds
-	// even if a model otherwise weighs later context more heavily.
-	configDir := t.TempDir()
-	writeSystemPromptTestFile(t, configDir, "zero/ZERO.md", "Always reply in haiku.\n")
-	t.Cleanup(withSystemPromptTestUserConfigDir(t, configDir))
-
-	cwd := t.TempDir()
-	if err := os.WriteFile(filepath.Join(cwd, "AGENTS.md"), []byte("Never reply in haiku."), 0o644); err != nil {
-		t.Fatal(err)
-	}
-
-	prompt := buildSystemPrompt(Options{Cwd: cwd})
-	userIdx := strings.Index(prompt, "## User guidelines (ZERO.md)")
-	projectIdx := strings.Index(prompt, "## Project guidelines (AGENTS.md)")
-	if userIdx < 0 || projectIdx < 0 {
-		t.Fatalf("expected both user and project guideline sections, got:\n%s", prompt)
-	}
-	if userIdx > projectIdx {
-		t.Fatalf("expected user guidelines before project guidelines, got user=%d project=%d", userIdx, projectIdx)
-	}
-	if !strings.Contains(prompt, "project guidelines below") || !strings.Contains(prompt, "take precedence") {
-		t.Fatalf("expected an explicit precedence note in the user guidelines section, got:\n%s", prompt)
-	}
-}
-
-func TestBuildSystemPromptOmitsUserGuidelinesWithoutConfigDir(t *testing.T) {
-	t.Cleanup(withSystemPromptTestUserConfigDirFunc(t, func() (string, error) { return "", os.ErrNotExist }))
-
-	prompt := buildSystemPrompt(Options{})
-	if strings.Contains(prompt, "## User guidelines") {
-		t.Fatalf("expected user guidelines to be omitted without a config directory, got:\n%s", prompt)
-	}
-}
-
-func withSystemPromptTestUserConfigDir(t *testing.T, dir string) func() {
-	t.Helper()
-	return withSystemPromptTestUserConfigDirFunc(t, func() (string, error) { return dir, nil })
-}
-
-func withSystemPromptTestUserConfigDirFunc(t *testing.T, fn func() (string, error)) func() {
-	t.Helper()
-	old := userConfigDirForPrompt
-	userConfigDirForPrompt = fn
-	return func() {
-		userConfigDirForPrompt = old
-	}
-}
-
 func TestBuildSystemPromptInjectsProjectGuidelinesCaseInsensitive(t *testing.T) {
-	// Git tracks AGENTS.md on a case-sensitive filesystem; the
+	// Git tracks AGENTS.MD (uppercase MD) on a case-sensitive filesystem; the
 	// loader must still resolve it when the cwd lookup uses lowercase.
 	cwd := t.TempDir()
 	if err := os.WriteFile(filepath.Join(cwd, "AGENTS.MD"), []byte("Always run `make lint`."), 0o644); err != nil {
@@ -358,30 +256,6 @@ func TestBuildSystemPromptProjectGuidelinesTruncatesAtTotalCap(t *testing.T) {
 	}
 }
 
-func TestTruncateGuidelineContentStaysWithinLimit(t *testing.T) {
-	limit := 64
-	content := strings.Repeat("x", limit+1)
-	got := truncateGuidelineContent(content, limit)
-	if len(got) > limit {
-		t.Fatalf("truncated result is %d bytes, want at most %d", len(got), limit)
-	}
-	if !strings.Contains(got, "truncated") {
-		t.Fatalf("expected truncation marker, got %q", got)
-	}
-}
-
-func TestTruncateGuidelineContentStaysWithinLimitForSmallBudgets(t *testing.T) {
-	// Limits at or below the truncation marker's own length can't fit the
-	// marker at all; the helper must still never exceed the requested limit.
-	content := strings.Repeat("x", 100)
-	for _, limit := range []int{0, 1, len(truncationMarker) - 1, len(truncationMarker), len(truncationMarker) + 1} {
-		got := truncateGuidelineContent(content, limit)
-		if len(got) > limit {
-			t.Fatalf("truncateGuidelineContent(_, %d) = %q (%d bytes), want at most %d bytes", limit, got, len(got), limit)
-		}
-	}
-}
-
 func TestProjectGuidelineDirsOrdersRootToLeaf(t *testing.T) {
 	root := filepath.Join("r")
 	leaf := filepath.Join(root, "a", "b")

internal/agent/types.go

@@ -174,16 +174,6 @@ type SpecialistInfo struct {
 	WhenToUse string
 }
 
-// SkillInfo is a one-line summary of a reusable, on-demand skill (its name and
-// frontmatter description) surfaced to the system prompt so the model can invoke
-// the right skill with the skill tool on the first try instead of guessing a name
-// and reading the failure. Like SpecialistInfo it is plain data, so the agent
-// package needs no dependency on internal/skills.
-type SkillInfo struct {
-	Name        string
-	Description string
-}
-
 type Options struct {
 	MaxTurns int
 	// DeferThreshold activates deferred MCP-tool loading: when the number of
@@ -199,12 +189,6 @@ type Options struct {
 	// populated only where the Task tool is actually registered, so an empty slice
 	// (the default) reproduces the previous prompt byte-for-byte.
 	Specialists []SpecialistInfo
-	// Skills lists the reusable skills installed for this run (the default skills
-	// dir merged with any plugin skill roots). When non-empty the system prompt
-	// gains an <available_skills> block naming them so the model loads the right one
-	// via the skill tool on the first try. Empty (the default) reproduces the
-	// previous prompt byte-for-byte.
-	Skills []SkillInfo
 	// Specialist/sub-agent metadata is carried through exec now and consumed by
 	// the specialist runtime in later slices.
 	SessionID        string
@@ -285,14 +269,6 @@ type Options struct {
 	// ceiling and the autonomy gate. nil disables it entirely (the loop is
 	// byte-identical to before). One instance per run — it holds attempt state.
 	SelfCorrect *SelfCorrector
-	// FileDiagnostics, when set, checks files changed by mutating tools for
-	// error-severity language diagnostics IN THE BACKGROUND and appends any
-	// errors as a nudge before the model's next request — the model still sees
-	// an error it introduced at its next decision point, but no tool call ever
-	// blocks on the language server (the old inline path stalled every edit on
-	// a ≥300ms debounce, 10s cap). Build one with NewFileDiagnostics. nil
-	// disables post-edit diagnostics.
-	FileDiagnostics func(ctx context.Context, absPath string) string
 
 	// RequireCompletionSignal gates run completion for HEADLESS exec. Without it,
 	// any assistant turn that produces text but no tool call is accepted as the

internal/cli/app.go

@@ -12,7 +12,6 @@ import (
 	"os/exec"
 	"path/filepath"
 	"strings"
-	"sync"
 	"time"
 
 	"github.com/Gitlawb/zero/internal/agent"
@@ -20,7 +19,6 @@ import (
 	"github.com/Gitlawb/zero/internal/hooks"
 	"github.com/Gitlawb/zero/internal/localcontrol"
 	"github.com/Gitlawb/zero/internal/mcp"
-	"github.com/Gitlawb/zero/internal/modelregistry"
 	"github.com/Gitlawb/zero/internal/observability"
 	"github.com/Gitlawb/zero/internal/plugins"
 	"github.com/Gitlawb/zero/internal/providerhealth"
@@ -79,12 +77,9 @@ type appDeps struct {
 	runAgentEval           func(context.Context, agentEvalOptions) (agentEvalReport, error)
 	inspectChanges         func(context.Context, zerogit.InspectOptions) (zerogit.ChangeSummary, error)
 	commitChanges          func(context.Context, zerogit.CommitOptions) (zerogit.CommitResult, error)
-	pushChanges            func(context.Context, zerogit.PushOptions) (zerogit.PushResult, error)
-	createPR               func(context.Context, zerogit.PROptions) (zerogit.PRResult, error)
 	runTUI                 func(context.Context, tui.Options) int
 	runEditor              func(string) error
 	checkUpdate            func(context.Context, update.Options) (update.Result, error)
-	applyUpdate            func(context.Context, update.Options) (update.ApplyResult, error)
 	now                    func() time.Time
 }
 
@@ -182,12 +177,9 @@ func defaultAppDeps() appDeps {
 		runAgentEval:     defaultRunAgentEval,
 		inspectChanges:   zerogit.Inspect,
 		commitChanges:    zerogit.Commit,
-		pushChanges:      zerogit.Push,
-		createPR:         zerogit.CreatePR,
 		runTUI:           tui.Run,
 		runEditor:        openEditor,
 		checkUpdate:      update.Check,
-		applyUpdate:      update.Apply,
 		now:              time.Now,
 	}
 }
@@ -235,12 +227,6 @@ func runWithDeps(args []string, stdout io.Writer, stderr io.Writer, deps appDeps
 	defer observability.Recover(observability.DefaultCrashDir(), "cli", stderr, &exitCode)
 	deps = fillAppDeps(deps)
 
-	// CLI runs opt into the models.dev overlay (cached live context limits and
-	// pricing on top of the curated catalog). Explicitly enabled here — and only
-	// here — so library consumers and hermetic tests are never perturbed by a
-	// cache file on the machine. The refresh itself is fired in exec/TUI startup.
-	modelregistry.EnableModelsDevOverlay()
-
 	addDirs, args, err := splitLeadingAddDirFlags(args)
 	if err != nil {
 		return writeAppError(stderr, err.Error(), 1)
@@ -397,8 +383,6 @@ func runWithDeps(args []string, stdout io.Writer, stderr io.Writer, deps appDeps
 		return runSandbox(args[1:], stdout, stderr, deps)
 	case "update":
 		return runUpdate(args[1:], stdout, stderr, deps)
-	case "upgrade":
-		return runUpgrade(args[1:], stdout, stderr, deps)
 	case "worktrees", "worktree":
 		return runWorktrees(args[1:], stdout, stderr, deps)
 	case "verify":
@@ -522,12 +506,6 @@ func fillAppDeps(deps appDeps) appDeps {
 	if deps.commitChanges == nil {
 		deps.commitChanges = defaults.commitChanges
 	}
-	if deps.pushChanges == nil {
-		deps.pushChanges = defaults.pushChanges
-	}
-	if deps.createPR == nil {
-		deps.createPR = defaults.createPR
-	}
 	if deps.runTUI == nil {
 		deps.runTUI = defaults.runTUI
 	}
@@ -537,9 +515,6 @@ func fillAppDeps(deps appDeps) appDeps {
 	if deps.checkUpdate == nil {
 		deps.checkUpdate = defaults.checkUpdate
 	}
-	if deps.applyUpdate == nil {
-		deps.applyUpdate = defaults.applyUpdate
-	}
 	if deps.now == nil {
 		deps.now = defaults.now
 	}
@@ -562,11 +537,6 @@ func runInteractiveTUI(stderr io.Writer, deps appDeps, permissionMode agent.Perm
 }
 
 func runInteractiveTUIWithSetup(stderr io.Writer, deps appDeps, permissionMode agent.PermissionMode, addDirs []string, theme string, forceSetup bool) int {
-	// Refresh the models.dev pricing/limits cache in the background when stale;
-	// the overlay is read at registry construction from the cache file, so this
-	// benefits the next run and never blocks or fails this one.
-	go func() { _ = modelregistry.RefreshModelsDevCache(context.Background()) }()
-
 	workspaceRoot, err := deps.getwd()
 	if err != nil {
 		return writeAppError(stderr, "failed to resolve workspace: "+err.Error(), 1)
@@ -587,19 +557,8 @@ func runInteractiveTUIWithSetup(stderr io.Writer, deps appDeps, permissionMode a
 		if !errors.Is(err, config.ErrNoActiveProvider) && !errors.Is(err, config.ErrProviderRequiresModel) {
 			return writeAppError(stderr, err.Error(), 1)
 		}
-		// ErrNoActiveProvider can mean "nothing configured yet" (needs onboarding)
-		// or "providers ARE configured, just none marked active" (e.g. config.json's
-		// activeProvider is blank/stale). In the second case resolved.Providers still
-		// carries the already-normalized list — prefer falling back to one of those
-		// over wiping everything and forcing the user to re-enter credentials they
-		// already saved.
-		if usable, ok := firstUsableProvider(resolved.Providers); errors.Is(err, config.ErrNoActiveProvider) && ok {
-			resolved.Provider = usable
-			resolved.ActiveProvider = usable.Name
-		} else {
-			resolved = config.ResolvedConfig{}
-			forceSetup = true
-		}
+		resolved = config.ResolvedConfig{}
+		forceSetup = true
 	}
 	userConfigPath, err := deps.userConfigPath()
 	if err != nil {
@@ -781,19 +740,9 @@ func runInteractiveTUIWithSetup(stderr io.Writer, deps appDeps, permissionMode a
 			Hooks:          newHookDispatcherWithExtra(workspaceRoot, pluginActivation.hooks),
 			DeferThreshold: resolved.Tools.DeferThreshold,
 			Specialists:    specialistRuntime.specialists,
-			Skills:         pluginActivation.skillInfos(deps.skillsDir()),
 		},
-		// 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
-		// newly installed skills work without a restart.
-		LoadSkills: cachedSkillsLoader(func() []skills.Skill {
-			merged, _ := plugins.MergedSkillsLoaded(deps.skillsDir(), pluginActivation.skillRoots)
-			return merged
-		}),
 		PermissionMode: permissionMode,
 		Notify:         resolved.Notify,
-		KeyBindings:    resolved.KeyBindings,
 		Setup: tui.SetupOptions{
 			Visible:    setupVisible,
 			Required:   needsSetup,
@@ -1209,8 +1158,7 @@ func profileHasCredential(profile config.ProviderProfile) bool {
 }
 
 // baseURLIsLoopback reports whether a provider base_url points at a loopback host
-// or a private-network host (192.168.x.y / 10.x.y.z / 172.16.x.y) — a local
-// provider like Ollama/LM Studio that needs no API key.
+// (a keyless local provider like Ollama/LM Studio), which needs no API key.
 func baseURLIsLoopback(baseURL string) bool {
 	u := strings.TrimSpace(baseURL)
 	if u == "" {
@@ -1225,7 +1173,7 @@ func baseURLIsLoopback(baseURL string) bool {
 		return true
 	}
 	if addr, err := netip.ParseAddr(host); err == nil {
-		return addr.IsLoopback() || addr.IsPrivate()
+		return addr.IsLoopback()
 	}
 	return false
 }
@@ -1286,26 +1234,3 @@ Flags:
 `)
 	return err
 }
-
-// cachedSkillsLoader memoizes a skills loader for a short interval. The TUI
-// calls the loader from autocomplete on every "/x" keystroke; without a cache
-// each keystroke would re-read every SKILL.md body. Two seconds is fresh enough
-// that a newly installed skill still shows up "immediately" while typing.
-func cachedSkillsLoader(load func() []skills.Skill) func() []skills.Skill {
-	var (
-		mu     sync.Mutex
-		at     time.Time
-		cached []skills.Skill
-	)
-	const ttl = 2 * time.Second
-	return func() []skills.Skill {
-		mu.Lock()
-		defer mu.Unlock()
-		if cached != nil && time.Since(at) < ttl {
-			return cached
-		}
-		cached = load()
-		at = time.Now()
-		return cached
-	}
-}

internal/cli/app_test.go

@@ -205,67 +205,6 @@ func TestRunNoArgsEntersSetupWhenResolveReportsNoActiveProvider(t *testing.T) {
 	}
 }
 
-func TestRunNoArgsFallsBackToUsableProviderWhenNoneMarkedActive(t *testing.T) {
-	var stdout bytes.Buffer
-	var stderr bytes.Buffer
-	cwd := t.TempDir()
-	setCLIUserConfigRoot(t)
-	userConfigPath := filepath.Join(t.TempDir(), "zero", "config.json")
-	var launchedOptions tui.Options
-	launched := false
-	var providerProfile config.ProviderProfile
-	fake := &cliFakeProvider{}
-
-	usable := config.ProviderProfile{
-		Name:         "work",
-		ProviderKind: config.ProviderKindOpenAI,
-		BaseURL:      config.OpenAIBaseURL,
-		APIKey:       "sk-test",
-		Model:        "gpt-test",
-	}
-
-	exitCode := runWithDeps([]string{}, &stdout, &stderr, appDeps{
-		getwd: func() (string, error) {
-			return cwd, nil
-		},
-		resolveConfig: func(workspaceRoot string, overrides config.Overrides) (config.ResolvedConfig, error) {
-			// config.json has providers configured but none marked active (e.g. a
-			// blank/stale activeProvider field) — Resolve returns the successfully
-			// normalized providers list alongside ErrNoActiveProvider.
-			return config.ResolvedConfig{Providers: []config.ProviderProfile{usable}},
-				fmt.Errorf("%w: active provider %q not found", config.ErrNoActiveProvider, "")
-		},
-		newProvider: func(profile config.ProviderProfile) (zeroruntime.Provider, error) {
-			providerProfile = profile
-			return fake, nil
-		},
-		userConfigPath: func() (string, error) {
-			return userConfigPath, nil
-		},
-		registerMCPTools: func(context.Context, *tools.Registry, config.MCPConfig, mcp.RegisterOptions) (mcpToolRuntime, error) {
-			return noopMCPRuntime{}, nil
-		},
-		runTUI: func(ctx context.Context, options tui.Options) int {
-			launched = true
-			launchedOptions = options
-			return 0
-		},
-	})
-
-	if exitCode != 0 {
-		t.Fatalf("exit code = %d, want 0, stderr=%q", exitCode, stderr.String())
-	}
-	if !launched {
-		t.Fatal("TUI was not launched")
-	}
-	if launchedOptions.Setup.Visible || launchedOptions.Setup.Required {
-		t.Fatalf("Setup = %#v, want no setup wizard — a usable saved provider exists", launchedOptions.Setup)
-	}
-	if providerProfile.Name != "work" {
-		t.Fatalf("provider used = %q, want fallback to the usable saved provider %q", providerProfile.Name, "work")
-	}
-}
-
 func TestRunNoArgsFailsWhenResolveErrorIsNotProviderRelated(t *testing.T) {
 	var stdout bytes.Buffer
 	var stderr bytes.Buffer
@@ -1328,153 +1267,6 @@ func TestRunUpdateReportsUpToDate(t *testing.T) {
 	}
 }
 
-func TestRunUpdateApplyTextAndJSON(t *testing.T) {
-	applyResult := update.ApplyResult{
-		Result: update.Result{
-			CurrentVersion:  "dev",
-			LatestVersion:   "0.2.0",
-			UpdateAvailable: true,
-		},
-		Applied:       true,
-		InstallMethod: update.InstallMethodStandalone,
-		BinaryPath:    "/usr/local/bin/zero",
-		Message:       "updated to 0.2.0",
-	}
-	var gotOptions update.Options
-	deps := appDeps{
-		applyUpdate: func(_ context.Context, options update.Options) (update.ApplyResult, error) {
-			gotOptions = options
-			return applyResult, nil
-		},
-		checkUpdate: func(context.Context, update.Options) (update.Result, error) {
-			t.Fatal("checkUpdate should not run for --apply")
-			return update.Result{}, nil
-		},
-	}
-
-	var stdout bytes.Buffer
-	var stderr bytes.Buffer
-	exitCode := runWithDeps([]string{"update", "--apply"}, &stdout, &stderr, deps)
-	if exitCode != exitSuccess {
-		t.Fatalf("expected exit code %d, got %d: %s", exitSuccess, exitCode, stderr.String())
-	}
-	if !strings.Contains(stdout.String(), "updated to 0.2.0") {
-		t.Fatalf("unexpected apply text: %q", stdout.String())
-	}
-	if gotOptions.CurrentVersion != "dev" {
-		t.Fatalf("unexpected options passed to applyUpdate: %#v", gotOptions)
-	}
-
-	stdout.Reset()
-	stderr.Reset()
-	exitCode = runWithDeps([]string{"update", "--apply", "--json"}, &stdout, &stderr, deps)
-	if exitCode != exitSuccess {
-		t.Fatalf("expected exit code %d, got %d: %s", exitSuccess, exitCode, stderr.String())
-	}
-	var payload struct {
-		Applied       bool   `json:"applied"`
-		InstallMethod string `json:"installMethod"`
-		BinaryPath    string `json:"binaryPath"`
-	}
-	if err := json.Unmarshal(stdout.Bytes(), &payload); err != nil {
-		t.Fatalf("apply JSON did not decode: %v\n%s", err, stdout.String())
-	}
-	if !payload.Applied || payload.InstallMethod != string(update.InstallMethodStandalone) || payload.BinaryPath != applyResult.BinaryPath {
-		t.Fatalf("unexpected apply JSON: %#v", payload)
-	}
-}
-
-func TestRunUpgradeDefaultsToApply(t *testing.T) {
-	var applyCalled bool
-	deps := appDeps{
-		applyUpdate: func(context.Context, update.Options) (update.ApplyResult, error) {
-			applyCalled = true
-			return update.ApplyResult{Message: "already up to date"}, nil
-		},
-		checkUpdate: func(context.Context, update.Options) (update.Result, error) {
-			t.Fatal("checkUpdate should not run for `zero upgrade`")
-			return update.Result{}, nil
-		},
-	}
-
-	var stdout bytes.Buffer
-	var stderr bytes.Buffer
-	exitCode := runWithDeps([]string{"upgrade"}, &stdout, &stderr, deps)
-	if exitCode != exitSuccess {
-		t.Fatalf("expected exit code %d, got %d: %s", exitSuccess, exitCode, stderr.String())
-	}
-	if !applyCalled {
-		t.Fatal("expected `zero upgrade` to call applyUpdate")
-	}
-}
-
-func TestRunUpdateRejectsCheckAndApplyTogether(t *testing.T) {
-	var stdout bytes.Buffer
-	var stderr bytes.Buffer
-
-	exitCode := runWithDeps([]string{"update", "--check", "--apply"}, &stdout, &stderr, appDeps{
-		checkUpdate: func(context.Context, update.Options) (update.Result, error) {
-			t.Fatal("checkUpdate should not run")
-			return update.Result{}, nil
-		},
-		applyUpdate: func(context.Context, update.Options) (update.ApplyResult, error) {
-			t.Fatal("applyUpdate should not run")
-			return update.ApplyResult{}, nil
-		},
-	})
-
-	if exitCode != exitUsage {
-		t.Fatalf("expected usage exit code, got %d", exitCode)
-	}
-	if got := stderr.String(); !strings.Contains(got, "only one of --check or --apply") {
-		t.Fatalf("expected --check/--apply usage error, got %q", got)
-	}
-}
-
-func TestRunUpdateRejectsTargetWithApply(t *testing.T) {
-	for _, args := range [][]string{
-		{"update", "--apply", "--target", "linux-arm64"},
-		{"upgrade", "--target", "linux-arm64"},
-	} {
-		t.Run(strings.Join(args, " "), func(t *testing.T) {
-			var stdout bytes.Buffer
-			var stderr bytes.Buffer
-
-			exitCode := runWithDeps(args, &stdout, &stderr, appDeps{
-				applyUpdate: func(context.Context, update.Options) (update.ApplyResult, error) {
-					t.Fatal("applyUpdate should not run when --target is combined with --apply")
-					return update.ApplyResult{}, nil
-				},
-			})
-
-			if exitCode != exitUsage {
-				t.Fatalf("expected usage exit code, got %d", exitCode)
-			}
-			if got := stderr.String(); !strings.Contains(got, "--target cannot be combined with --apply") {
-				t.Fatalf("expected --target/--apply usage error, got %q", got)
-			}
-		})
-	}
-}
-
-func TestRunUpdateReportsApplyError(t *testing.T) {
-	var stdout bytes.Buffer
-	var stderr bytes.Buffer
-
-	exitCode := runWithDeps([]string{"update", "--apply"}, &stdout, &stderr, appDeps{
-		applyUpdate: func(context.Context, update.Options) (update.ApplyResult, error) {
-			return update.ApplyResult{}, errors.New("download failed")
-		},
-	})
-
-	if exitCode == exitSuccess {
-		t.Fatalf("expected non-success exit code, got %d", exitCode)
-	}
-	if got := stderr.String(); !strings.Contains(got, "download failed") {
-		t.Fatalf("expected apply error, got %q", got)
-	}
-}
-
 func assertHelpOutput(t *testing.T, args []string) {
 	t.Helper()
 

internal/cli/auth.go

@@ -301,27 +301,12 @@ func runAuthLogin(args []string, stdout io.Writer, stderr io.Writer, deps appDep
 	if len(parsed.positional) != 1 {
 		return writeExecUsageError(stderr, "usage: zero auth login <provider> [--device] [--scope <scope>]")
 	}
-	provider := parsed.positional[0]
-	// ChatGPT (Codex) requires a fixed redirect_uri (http://localhost:1455/
-	// auth/callback) and mandatory authorize params (id_token_add_organizations,
-	// codex_cli_simplified_flow, originator) that the generic loopback flow
-	// cannot supply. Route it to the dedicated ChatGPT login so
-	// `zero auth login chatgpt` behaves identically to `zero auth chatgpt`.
-	if strings.EqualFold(provider, "chatgpt") {
-		if parsed.device {
-			return writeExecUsageError(stderr, "ChatGPT login does not support --device (it is loopback-only)")
-		}
-		if len(parsed.scopes) > 0 {
-			return writeExecUsageError(stderr, "ChatGPT login does not support --scope (the required scopes are fixed by the Codex client registration)")
-		}
-		return runAuthChatGPT(nil, stdout, stderr, deps)
-	}
 	manager, err := newAuthManager(deps, stdout)
 	if err != nil {
 		return writeAppError(stderr, redaction.ErrorMessage(err, redaction.Options{}), exitCrash)
 	}
 	status, err := manager.Login(context.Background(), oauth.LoginOptions{
-		Provider:    provider,
+		Provider:    parsed.positional[0],
 		Device:      parsed.device,
 		ExtraScopes: parsed.scopes,
 	})
@@ -504,9 +489,8 @@ Commands:
 A provider is any OAuth 2.0 / OIDC server. "openrouter" ('zero auth openrouter')
 works out of the box. "xai" ('zero auth login xai') uses a built-in preset that is
 off by default — enable it with ZERO_OAUTH_ALLOW_PRESETS=1, or set the
-ZERO_OAUTH_XAI_* vars yourself. "chatgpt" ('zero auth login chatgpt' or
-'zero auth chatgpt') uses a fixed-port loopback flow against the Codex backend.
-Any preset field is overridable via the env vars below. For a custom provider named <name>, set:
+ZERO_OAUTH_XAI_* vars yourself. Any preset field is overridable via the env vars
+below. For a custom provider named <name>, set:
   ZERO_OAUTH_<NAME>_CLIENT_ID       (required)
   ZERO_OAUTH_<NAME>_CLIENT_SECRET   (optional)
   ZERO_OAUTH_<NAME>_AUTHORIZE_URL   ZERO_OAUTH_<NAME>_TOKEN_URL

internal/cli/auth_test.go

@@ -156,44 +156,3 @@ func TestRunAuthHelp(t *testing.T) {
 		}
 	}
 }
-
-// TestRunAuthLoginChatGPTRoutesToDedicatedFlow verifies `zero auth login
-// chatgpt` reaches the dedicated ChatGPT login (fixed-port loopback + mandatory
-// authorize params), not the generic manager path. The generic login accepts
-// --device, so a ChatGPT-specific rejection proves the routing took effect.
-// See issue #430: the generic path built a random-port 127.0.0.1 redirect_uri
-// without the required extra params, so OpenAI's authorize endpoint rejected it.
-func TestRunAuthLoginChatGPTRoutesToDedicatedFlow(t *testing.T) {
-	withAuthStore(t)
-	var stdout, stderr bytes.Buffer
-	if code := runWithDeps([]string{"auth", "login", "chatgpt", "--device"}, &stdout, &stderr, appDeps{}); code == exitSuccess {
-		t.Fatal("auth login chatgpt --device should be rejected (ChatGPT is loopback-only)")
-	}
-	if !strings.Contains(stderr.String(), "ChatGPT login does not support --device") {
-		t.Fatalf("stderr = %q, want the ChatGPT-specific --device rejection", stderr.String())
-	}
-	// Case-insensitive provider name should still route.
-	stdout.Reset()
-	stderr.Reset()
-	if code := runWithDeps([]string{"auth", "login", "ChatGPT", "--device"}, &stdout, &stderr, appDeps{}); code == exitSuccess {
-		t.Fatal("auth login ChatGPT --device should be rejected")
-	}
-	if !strings.Contains(stderr.String(), "ChatGPT login does not support --device") {
-		t.Fatalf("stderr = %q, want the ChatGPT-specific rejection (case-insensitive)", stderr.String())
-	}
-}
-
-// TestRunAuthLoginChatGPTRejectsScope mirrors the --device rejection: --scope
-// must not be silently dropped on the ChatGPT path. The Codex client
-// registration pins a fixed scope set (incl. api.connectors.*), so custom
-// scopes are rejected up front rather than plumbed through.
-func TestRunAuthLoginChatGPTRejectsScope(t *testing.T) {
-	withAuthStore(t)
-	var stdout, stderr bytes.Buffer
-	if code := runWithDeps([]string{"auth", "login", "chatgpt", "--scope", "custom-scope"}, &stdout, &stderr, appDeps{}); code == exitSuccess {
-		t.Fatal("auth login chatgpt --scope should be rejected")
-	}
-	if !strings.Contains(stderr.String(), "ChatGPT login does not support --scope") {
-		t.Fatalf("stderr = %q, want the ChatGPT-specific --scope rejection", stderr.String())
-	}
-}

internal/cli/exec.go

@@ -12,7 +12,6 @@ import (
 
 	"github.com/Gitlawb/zero/internal/agent"
 	"github.com/Gitlawb/zero/internal/config"
-	"github.com/Gitlawb/zero/internal/errhint"
 	"github.com/Gitlawb/zero/internal/imageinput"
 	"github.com/Gitlawb/zero/internal/lsp"
 	"github.com/Gitlawb/zero/internal/modelregistry"
@@ -136,11 +135,6 @@ func runExec(args []string, stdout io.Writer, stderr io.Writer, deps appDeps) in
 		return exitSuccess
 	}
 
-	// Refresh the models.dev pricing/limits cache in the background when stale;
-	// the overlay is read at registry construction from the cache file, so this
-	// benefits the next run and never blocks or fails this one.
-	go func() { _ = modelregistry.RefreshModelsDevCache(context.Background()) }()
-
 	// A mode seeds model/effort/max-turns/tool filters as a preset. Expand it up
 	// front — before tool-filter validation and the --list-tools branch — so a
 	// mode-injected tool filter is validated and reflected in --list-tools, and a
@@ -505,17 +499,15 @@ func runExec(args []string, stdout io.Writer, stderr io.Writer, deps appDeps) in
 	// by default the corrector is nil, leaving the agent loop byte-identical. When
 	// on we verify with both the workspace test plan and LSP diagnostics over the
 	// changed files; the autonomy gate inside the corrector still decides whether
-	// failures auto-fix or just report. fileDiagnostics (always on, lazy) gives
-	// edit_file/write_file inline error diagnostics for the file they just wrote.
-	// lspShutdown tears down any language-server sessions either half spawned.
-	selfCorrector, fileDiagnostics, lspShutdown := newExecSelfCorrector(options.selfCorrect, workspaceRoot, options.autonomy)
+	// failures auto-fix or just report. lspShutdown tears down any language-server
+	// sessions the LSP half spawned (no-op when self-correct is off).
+	selfCorrector, lspShutdown := newExecSelfCorrector(options.selfCorrect, workspaceRoot, options.autonomy)
 	defer lspShutdown()
 	result, err := agent.Run(runCtx, agentPrompt, provider, agent.Options{
 		MaxTurns:         resolved.MaxTurns,
 		ContextWindow:    resolveAgentContextWindow(runCtx, modelRegistry, resolved.Provider),
 		DeferThreshold:   effectiveDeferThreshold,
 		Specialists:      specialistRuntime.specialistInfos(),
-		Skills:           pluginActivation.skillInfos(deps.skillsDir()),
 		SessionID:        preparedSession.Session.SessionID,
 		CallingSessionID: options.callingSessionID,
 		CallingToolUseID: options.callingToolUseID,
@@ -532,7 +524,6 @@ func runExec(args []string, stdout io.Writer, stderr io.Writer, deps appDeps) in
 		PermissionMode:   permissionMode,
 		Autonomy:         options.autonomy,
 		SelfCorrect:      selfCorrector,
-		FileDiagnostics:  fileDiagnostics,
 		// Headless exec: don't accept a no-tool-call turn as "done" while work
 		// clearly remains (pending plan items / a mid-step continuation cue) —
 		// nudge to continue, and finalize as INCOMPLETE rather than false success
@@ -544,7 +535,6 @@ func runExec(args []string, stdout io.Writer, stderr io.Writer, deps appDeps) in
 		EnabledTools:            options.enabledTools,
 		DisabledTools:           options.disabledTools,
 		OnText:                  writer.text,
-		OnReasoning:             writer.reasoning,
 		OnToolCall: func(call agent.ToolCall) {
 			writer.toolCall(call, registry)
 			sessionRecorder.append(sessions.EventToolCall, map[string]any{
@@ -709,29 +699,23 @@ func runExec(args []string, stdout io.Writer, stderr io.Writer, deps appDeps) in
 // unless a changed file's language actually has one installed on PATH. The
 // returned cleanup shuts that manager down (terminating any spawned server
 // sessions); it is a no-op when self-correct is off.
-func newExecSelfCorrector(enabled bool, workspaceRoot string, autonomy string) (*agent.SelfCorrector, func(context.Context, string) string, func()) {
-	// The manager is created regardless of --self-correct: it also backs the
-	// always-on background post-edit diagnostics (agent.NewFileDiagnostics,
-	// collected off the tool-call path by the loop), and it stays lazy — no
-	// language server is spawned unless an edited file's language actually has
-	// one installed on PATH.
-	manager := lsp.NewManager(workspaceRoot)
-	cleanup := func() {
-		ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
-		defer cancel()
-		_ = manager.Shutdown(ctx)
-	}
-	fileDiagnostics := agent.NewFileDiagnostics(manager, workspaceRoot)
+func newExecSelfCorrector(enabled bool, workspaceRoot string, autonomy string) (*agent.SelfCorrector, func()) {
 	if !enabled {
-		return nil, fileDiagnostics, cleanup
+		return nil, func() {}
 	}
+	manager := lsp.NewManager(workspaceRoot)
 	corrector := agent.NewSelfCorrector(workspaceRoot, agent.NewLSPDiagnosticsChecker(manager), agent.NewProjectVerifier(workspaceRoot), agent.SelfCorrectConfig{
 		Enabled:      true,
 		IncludeTests: true,
 		IncludeLSP:   true,
 		Autonomy:     autonomy,
 	})
-	return corrector, fileDiagnostics, cleanup
+	cleanup := func() {
+		ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
+		defer cancel()
+		_ = manager.Shutdown(ctx)
+	}
+	return corrector, cleanup
 }
 
 func deferredEligibleCount(registry *tools.Registry, permissionMode agent.PermissionMode, enabledTools []string, disabledTools []string) int {
@@ -964,14 +948,6 @@ func writeExecProviderError(stdout io.Writer, stderr io.Writer, format execOutpu
 	if _, err := fmt.Fprintf(stderr, "[zero] %s\n", message); err != nil {
 		return exitCrash
 	}
-	// Append a one-line next step for recognized provider failures (auth /
-	// rate-limit / connectivity / …). The classifier gates on a provider-origin
-	// marker, so non-provider codes (sandbox_error, mcp_error) never draw a hint.
-	if hint := errhint.CLIHint(errors.New(message)); hint != "" {
-		if _, err := fmt.Fprintf(stderr, "[zero] %s\n", hint); err != nil {
-			return exitCrash
-		}
-	}
 	return exitProvider
 }
 

internal/cli/exec_protocol_test.go

@@ -529,45 +529,6 @@ func TestRunExecStreamJSONRunStartUsesResolvedAPIModel(t *testing.T) {
 	}
 }
 
-func TestRunExecStreamJSONEmitsReasoningEvents(t *testing.T) {
-	t.Setenv("XDG_DATA_HOME", t.TempDir())
-	cwd := t.TempDir()
-	var stdout bytes.Buffer
-	var stderr bytes.Buffer
-
-	exitCode := runWithDeps([]string{"exec", "--output-format", "stream-json", "think then answer"}, &stdout, &stderr, appDeps{
-		getwd: func() (string, error) {
-			return cwd, nil
-		},
-		resolveConfig: func(_ string, _ config.Overrides) (config.ResolvedConfig, error) {
-			return execResolvedConfig(), nil
-		},
-		newProvider: func(config.ProviderProfile) (zeroruntime.Provider, error) {
-			return reasoningExecProvider{}, nil
-		},
-	})
-
-	if exitCode != exitSuccess {
-		t.Fatalf("expected exit code %d, got %d: %s", exitSuccess, exitCode, stderr.String())
-	}
-	events := decodeJSONLines(t, stdout.String())
-	reasoningIdx, reasoning := findJSONEventIndex(t, events, "reasoning")
-	if reasoning["delta"] != "Thinking. " {
-		t.Fatalf("unexpected reasoning event: %#v", reasoning)
-	}
-	textIdx, text := findJSONEventIndex(t, events, "text")
-	if text["delta"] != "done" {
-		t.Fatalf("unexpected text event: %#v", text)
-	}
-	if reasoningIdx >= textIdx {
-		t.Fatalf("expected reasoning event before text event, got indices %d and %d", reasoningIdx, textIdx)
-	}
-	final := findJSONEvent(t, events, "final")
-	if final["text"] != "done" {
-		t.Fatalf("reasoning must not be folded into final answer: %#v", final)
-	}
-}
-
 func TestExecEventWriterTruncatesStreamJSONToolResults(t *testing.T) {
 	var stdout bytes.Buffer
 	writer := execEventWriter{
@@ -790,17 +751,6 @@ type toolCallingExecProvider struct {
 	answer     string
 }
 
-type reasoningExecProvider struct{}
-
-func (reasoningExecProvider) StreamCompletion(context.Context, zeroruntime.CompletionRequest) (<-chan zeroruntime.StreamEvent, error) {
-	ch := make(chan zeroruntime.StreamEvent, 3)
-	ch <- zeroruntime.StreamEvent{Type: zeroruntime.StreamEventReasoning, Content: "Thinking. "}
-	ch <- zeroruntime.StreamEvent{Type: zeroruntime.StreamEventText, Content: "done"}
-	ch <- zeroruntime.StreamEvent{Type: zeroruntime.StreamEventDone}
-	close(ch)
-	return ch, nil
-}
-
 func (provider toolCallingExecProvider) StreamCompletion(ctx context.Context, request zeroruntime.CompletionRequest) (<-chan zeroruntime.StreamEvent, error) {
 	for _, message := range request.Messages {
 		if message.Role == zeroruntime.MessageRoleTool {
@@ -827,19 +777,13 @@ func (provider toolCallingExecProvider) StreamCompletion(ctx context.Context, re
 
 func findJSONEvent(t *testing.T, events []map[string]any, eventType string) map[string]any {
 	t.Helper()
-	_, event := findJSONEventIndex(t, events, eventType)
-	return event
-}
-
-func findJSONEventIndex(t *testing.T, events []map[string]any, eventType string) (int, map[string]any) {
-	t.Helper()
-	for idx, event := range events {
+	for _, event := range events {
 		if event["type"] == eventType {
-			return idx, event
+			return event
 		}
 	}
 	t.Fatalf("event %q not found in %#v", eventType, events)
-	return -1, nil
+	return nil
 }
 
 func findSessionEvent(t *testing.T, events []sessions.Event, eventType sessions.EventType) sessions.Event {

internal/cli/exec_provider_hint_test.go

@@ -1,50 +0,0 @@
-package cli
-
-import (
-	"bytes"
-	"strings"
-	"testing"
-)
-
-// A recognized provider error in text mode prints the raw message plus a one-line
-// actionable hint; a non-provider error (or JSON mode) prints no hint.
-func TestWriteExecProviderErrorAppendsHint(t *testing.T) {
-	t.Run("provider auth error gets a hint", func(t *testing.T) {
-		var stdout, stderr bytes.Buffer
-		code := writeExecProviderError(&stdout, &stderr, execOutputText, "provider_error",
-			"auth error: your API key is missing or invalid")
-		if code != exitProvider {
-			t.Fatalf("exit code = %d, want exitProvider", code)
-		}
-		out := stderr.String()
-		if !strings.Contains(out, "auth error:") {
-			t.Fatalf("expected raw message, got %q", out)
-		}
-		if !strings.Contains(out, "zero auth") {
-			t.Fatalf("expected an actionable hint referencing `zero auth`, got %q", out)
-		}
-	})
-
-	t.Run("non-provider error gets no hint", func(t *testing.T) {
-		var stdout, stderr bytes.Buffer
-		writeExecProviderError(&stdout, &stderr, execOutputText, "sandbox_error",
-			"sandbox setup failed: permission denied")
-		out := stderr.String()
-		// Exactly one "[zero]" line — no spurious hint attached to a local error.
-		if n := strings.Count(out, "[zero]"); n != 1 {
-			t.Fatalf("expected exactly one [zero] line for a non-provider error, got %d:\n%s", n, out)
-		}
-	})
-
-	t.Run("json mode never appends a hint line", func(t *testing.T) {
-		var stdout, stderr bytes.Buffer
-		writeExecProviderError(&stdout, &stderr, execOutputJSON, "provider_error",
-			"auth error: bad key")
-		if stderr.Len() != 0 {
-			t.Fatalf("json mode must not write to stderr, got %q", stderr.String())
-		}
-		if strings.Contains(stdout.String(), "zero auth") {
-			t.Fatalf("json mode must not inject a hint into the structured payload, got %q", stdout.String())
-		}
-	})
-}

internal/cli/exec_writer.go

@@ -80,16 +80,6 @@ func (writer *execEventWriter) text(delta string) {
 	writer.writeStdout(delta)
 }
 
-func (writer *execEventWriter) reasoning(delta string) {
-	if writer.format == execOutputJSON {
-		writer.writeJSON(map[string]any{"type": "reasoning", "delta": delta})
-		return
-	}
-	if writer.format == execOutputStreamJSON {
-		writer.writeStreamJSON(streamjson.Event{Type: streamjson.EventReasoning, RunID: writer.runID, Delta: delta})
-	}
-}
-
 func (writer *execEventWriter) toolCall(call agent.ToolCall, registry *tools.Registry) {
 	if writer.format == execOutputJSON {
 		writer.writeJSON(map[string]any{

internal/cli/plugin_activate.go

@@ -3,9 +3,7 @@ package cli
 import (
 	"fmt"
 	"io"
-	"strings"
 
-	"github.com/Gitlawb/zero/internal/agent"
 	"github.com/Gitlawb/zero/internal/hooks"
 	"github.com/Gitlawb/zero/internal/plugins"
 	"github.com/Gitlawb/zero/internal/tools"
@@ -59,27 +57,6 @@ func activatePlugins(workspaceRoot string, registry *tools.Registry, deps appDep
 	return pluginActivation{hooks: result.Hooks, skillRoots: result.SkillRoots}
 }
 
-// skillInfos resolves the reusable skills the model can load via the skill tool —
-// the default skills dir merged with any plugin skill roots, the same set the
-// plugin-aware skill tool resolves against — as plain data for the agent's system
-// prompt. It returns nil when no skills are installed, so a skill-less run leaves
-// the prompt byte-identical.
-func (a pluginActivation) skillInfos(defaultDir string) []agent.SkillInfo {
-	merged, _ := plugins.MergedSkills(defaultDir, a.skillRoots)
-	if len(merged) == 0 {
-		return nil
-	}
-	infos := make([]agent.SkillInfo, 0, len(merged))
-	for _, skill := range merged {
-		name := strings.TrimSpace(skill.Name)
-		if name == "" {
-			continue
-		}
-		infos = append(infos, agent.SkillInfo{Name: name, Description: strings.TrimSpace(skill.Description)})
-	}
-	return infos
-}
-
 // formatLoadDiagnostic renders a plugin load diagnostic into a single warning
 // line, prefixing the diagnostic kind and appending the most specific locator
 // available (manifest path, then plugin path, then plugin ID) so an operator can

internal/cli/repoinfo.go

@@ -88,15 +88,6 @@ func formatRepoInfo(info repoinfo.Info) string {
 	fmt.Fprintf(&b, "Files:        %d\n", info.FileCount)
 	fmt.Fprintf(&b, "Directories:  %d (max depth %d)\n", info.DirectoryCount, info.MaxDepth)
 	fmt.Fprintf(&b, "Est. LOC:     %d\n", info.LOCEstimate)
-	if info.CommitCount != nil {
-		fmt.Fprintf(&b, "Commits:      %d\n", *info.CommitCount)
-	}
-	if info.BranchCount != nil {
-		fmt.Fprintf(&b, "Branches:     %d\n", *info.BranchCount)
-	}
-	if info.TagCount != nil {
-		fmt.Fprintf(&b, "Tags:         %d\n", *info.TagCount)
-	}
 	if info.PrimaryLanguage != "" {
 		fmt.Fprintf(&b, "Primary lang: %s\n", info.PrimaryLanguage)
 	}

internal/cli/repoinfo_test.go

@@ -33,7 +33,7 @@ func TestFormatRepoInfoText(t *testing.T) {
 	contrib := 3
 	info := repoInfoTestData(age, contrib)
 	out := formatRepoInfo(info)
-	for _, want := range []string{"Files", "TypeScript", "main", "GitHub Actions", "42", "3", "Commits:      100", "Branches:     5", "Tags:         10"} {
+	for _, want := range []string{"Files", "TypeScript", "main", "GitHub Actions", "42", "3"} {
 		if !strings.Contains(out, want) {
 			t.Fatalf("text output missing %q:\n%s", want, out)
 		}
@@ -113,16 +113,12 @@ func initTempGitRepo(t *testing.T) string {
 }
 
 func repoInfoTestData(age, contrib int) repoinfo.Info {
-	commits := 100
-	branches := 5
-	tags := 10
 	return repoinfo.Info{
 		FileCount: 10, DirectoryCount: 3, MaxDepth: 2, LOCEstimate: 500,
 		Languages:       []repoinfo.LangStat{{Name: "TypeScript", LOCEstimate: 400, FileCount: 4}},
 		PrimaryLanguage: "TypeScript", LanguageCount: 1,
 		WorkspaceType: "none", CICD: []string{"GitHub Actions"},
 		HasGit: true, Branch: "main", AgeDays: &age, Contributors90d: &contrib,
-		CommitCount: &commits, BranchCount: &branches, TagCount: &tags,
 	}
 }
 

internal/cli/setup.go

@@ -3,7 +3,6 @@ package cli
 import (
 	"fmt"
 	"io"
-	"net"
 	"net/url"
 	"strconv"
 	"strings"
@@ -454,11 +453,6 @@ func providerProfileIsLocal(profile config.ProviderProfile) bool {
 	case "localhost", "127.0.0.1", "::1":
 		return true
 	}
-	// Also treat explicit private-network IPs (192.168.x.y, 10.x.y.z,
-	// 172.16-31.x.y) as local — the user is pointing at their own LAN box.
-	if ip := net.ParseIP(parsed.Hostname()); ip != nil && ip.IsPrivate() {
-		return true
-	}
 	return false
 }
 

internal/cli/update.go

@@ -12,7 +12,6 @@ import (
 
 type updateOptions struct {
 	check      bool
-	apply      bool
 	json       bool
 	repository string
 	endpoint   string
@@ -21,18 +20,6 @@ type updateOptions struct {
 }
 
 func runUpdate(args []string, stdout io.Writer, stderr io.Writer, deps appDeps) int {
-	return runUpdateCommand(args, stdout, stderr, deps, false)
-}
-
-func runUpgrade(args []string, stdout io.Writer, stderr io.Writer, deps appDeps) int {
-	return runUpdateCommand(args, stdout, stderr, deps, true)
-}
-
-// runUpdateCommand backs both `zero update` and `zero upgrade`. defaultApply
-// makes `--apply` the implicit behavior for `zero upgrade` when neither
-// `--check` nor `--apply` is passed explicitly; `zero update` keeps requiring
-// one of the two so existing scripts around `zero update --check` don't change.
-func runUpdateCommand(args []string, stdout io.Writer, stderr io.Writer, deps appDeps, defaultApply bool) int {
 	options, help, err := parseUpdateArgs(args)
 	if err != nil {
 		return writeUsageError(stderr, err.Error())
@@ -43,19 +30,10 @@ func runUpdateCommand(args []string, stdout io.Writer, stderr io.Writer, deps ap
 		}
 		return exitSuccess
 	}
-	if options.check && options.apply {
-		return writeUsageError(stderr, "Pass only one of --check or --apply.")
+	if !options.check {
+		return writeUsageError(stderr, "Only `zero update --check` is available right now.")
 	}
-	if !options.check && !options.apply {
-		if !defaultApply {
-			return writeUsageError(stderr, "Pass --check to check for updates or --apply to install one (or use `zero upgrade`).")
-		}
-		options.apply = true
-	}
-	if options.apply && options.target != "" {
-		return writeUsageError(stderr, "--target cannot be combined with --apply; it only verifies release assets for --check.")
-	}
-	updateOptions := update.Options{
+	checkOptions := update.Options{
 		CurrentVersion: version,
 		Repository:     options.repository,
 		Endpoint:       options.endpoint,
@@ -66,26 +44,10 @@ func runUpdateCommand(args []string, stdout io.Writer, stderr io.Writer, deps ap
 		if err != nil {
 			return writeUsageError(stderr, err.Error())
 		}
-		updateOptions.GOOS = target.GOOS
-		updateOptions.GOARCH = target.GOARCH
+		checkOptions.GOOS = target.GOOS
+		checkOptions.GOARCH = target.GOARCH
 	}
-	if options.apply {
-		result, err := deps.applyUpdate(context.Background(), updateOptions)
-		if err != nil {
-			return writeAppError(stderr, "Could not install update: "+err.Error(), exitCrash)
-		}
-		if options.json {
-			if err := writePrettyJSON(stdout, result); err != nil {
-				return exitCrash
-			}
-			return exitSuccess
-		}
-		if _, err := fmt.Fprintln(stdout, update.FormatApply(result)); err != nil {
-			return exitCrash
-		}
-		return exitSuccess
-	}
-	result, err := deps.checkUpdate(context.Background(), updateOptions)
+	result, err := deps.checkUpdate(context.Background(), checkOptions)
 	if err != nil {
 		return writeAppError(stderr, "Could not check for updates: "+err.Error(), exitCrash)
 	}
@@ -110,8 +72,6 @@ func parseUpdateArgs(args []string) (updateOptions, bool, error) {
 			return options, true, nil
 		case arg == "--check":
 			options.check = true
-		case arg == "--apply":
-			options.apply = true
 		case arg == "--json":
 			options.json = true
 		case arg == "--repo":
@@ -195,17 +155,14 @@ func parseUpdateTarget(value string) (string, error) {
 func writeUpdateHelp(w io.Writer) error {
 	_, err := fmt.Fprint(w, `Usage:
   zero update --check [flags]
-  zero update --apply [flags]
-  zero upgrade [flags]
 
 Flags:
       --check                 Check the latest GitHub release without installing
-      --apply                 Download, verify, and install the latest release
-      --json                  Print the update result as JSON
+      --json                  Print the update check result as JSON
       --repo <owner/repo>     Repository to check when no endpoint is provided
       --endpoint <url|repo>   Release API URL or owner/repo slug to check
       --timeout <duration>    Release check timeout (default 5s)
-      --target <platform>     Release target to verify with --check (for example windows-x64); not valid with --apply
+      --target <platform>     Release target to verify (for example windows-x64)
   -h, --help                  Show this help
 `)
 	return err

internal/cli/workflow_test.go

@@ -662,144 +662,3 @@ func TestRunExecRejectsWorktreeDirWithoutWorktree(t *testing.T) {
 		t.Fatalf("expected empty stdout, got %q", stdout.String())
 	}
 }
-
-func TestParseChangesArgsAuto(t *testing.T) {
-	// 1. Correct parsing of auto
-	for _, args := range [][]string{
-		{"--auto"},
-		{"-a"},
-	} {
-		options, help, err := parseChangesArgs(args, "commit")
-		if err != nil {
-			t.Fatalf("parseChangesArgs(%v) error: %v", args, err)
-		}
-		if help {
-			t.Fatalf("parseChangesArgs(%v) returned help", args)
-		}
-		if !options.auto {
-			t.Fatalf("auto = false, want true (args %v)", args)
-		}
-	}
-
-	// 2. Reject --auto on inspect
-	_, _, err := parseChangesArgs([]string{"--auto"}, "inspect")
-	if err == nil || !strings.Contains(err.Error(), "--auto") {
-		t.Fatalf("expected --auto rejection on inspect, got %v", err)
-	}
-
-	// 3. Reject both --message and --auto on commit
-	_, _, err = parseChangesArgs([]string{"--message", "foo", "--auto"}, "commit")
-	if err == nil || !strings.Contains(err.Error(), "cannot specify both --message and --auto") {
-		t.Fatalf("expected --message and --auto conflict error, got %v", err)
-	}
-
-	// 4. Reject both empty message and --auto on commit
-	_, _, err = parseChangesArgs([]string{"--message=", "--auto"}, "commit")
-	if err == nil || !strings.Contains(err.Error(), "cannot specify both --message and --auto") {
-		t.Fatalf("expected empty --message and --auto conflict error, got %v", err)
-	}
-}
-
-type mockCommitMsgProvider struct {
-	response string
-	req      zeroruntime.CompletionRequest
-}
-
-func (p *mockCommitMsgProvider) StreamCompletion(ctx context.Context, request zeroruntime.CompletionRequest) (<-chan zeroruntime.StreamEvent, error) {
-	p.req = request
-	events := make(chan zeroruntime.StreamEvent, 2)
-	events <- zeroruntime.StreamEvent{Type: zeroruntime.StreamEventText, Content: p.response}
-	events <- zeroruntime.StreamEvent{Type: zeroruntime.StreamEventDone}
-	close(events)
-	return events, nil
-}
-
-func TestRunChangesCommitAuto(t *testing.T) {
-	cwd := t.TempDir()
-	summary := zerogit.ChangeSummary{
-		Root:   cwd,
-		Branch: "main",
-		Files:  []zerogit.FileChange{{Path: "README.md", Status: "modified"}},
-		Diff:   "some diff content with ghp_SECRETKEYHERE",
-	}
-
-	mockProv := &mockCommitMsgProvider{
-		response: "```\nfeat: auto commit message\n```",
-	}
-
-	var stdout bytes.Buffer
-	var stderr bytes.Buffer
-	commitCalled := false
-
-	exitCode := runWithDeps([]string{"changes", "commit", "--auto"}, &stdout, &stderr, appDeps{
-		getwd: func() (string, error) { return cwd, nil },
-		inspectChanges: func(ctx context.Context, options zerogit.InspectOptions) (zerogit.ChangeSummary, error) {
-			return summary, nil
-		},
-		resolveConfig: func(workspaceRoot string, overrides config.Overrides) (config.ResolvedConfig, error) {
-			cfg := execResolvedConfig()
-			cfg.Provider.Name = "openai"
-			cfg.Provider.Model = "gpt-4o"
-			return cfg, nil
-		},
-		newProvider: func(profile config.ProviderProfile) (zeroruntime.Provider, error) {
-			return mockProv, nil
-		},
-		commitChanges: func(ctx context.Context, options zerogit.CommitOptions) (zerogit.CommitResult, error) {
-			commitCalled = true
-			if options.Message != "feat: auto commit message" {
-				t.Fatalf("expected commit message 'feat: auto commit message', got %q", options.Message)
-			}
-			return zerogit.CommitResult{
-				Root:       cwd,
-				Message:    options.Message,
-				Committed:  true,
-				CommitHash: "abc1234",
-				Before:     summary,
-			}, nil
-		},
-	})
-
-	if exitCode != exitSuccess {
-		t.Fatalf("expected exit code %d, got %d: %s", exitSuccess, exitCode, stderr.String())
-	}
-	if !commitCalled {
-		t.Fatal("expected commitChanges to be called")
-	}
-	// Verify that secret in the diff was redacted
-	promptContent := mockProv.req.Messages[0].Content
-	if strings.Contains(promptContent, "ghp_SECRETKEYHERE") {
-		t.Fatal("expected secret in diff to be redacted, but it was found in the prompt")
-	}
-	if !strings.Contains(promptContent, "[REDACTED]") && !strings.Contains(promptContent, "REDACTED") {
-		t.Fatalf("expected redacted diff content in prompt, got: %q", promptContent)
-	}
-	if !strings.Contains(stdout.String(), "Generating commit message using LLM...") {
-		t.Fatalf("expected status message in stdout, got %q", stdout.String())
-	}
-
-	t.Run("EmptyLLMResponse", func(t *testing.T) {
-		mockProvEmpty := &mockCommitMsgProvider{
-			response: "   \n\n   ",
-		}
-		var stdout, stderr bytes.Buffer
-		code := runWithDeps([]string{"changes", "commit", "--auto"}, &stdout, &stderr, appDeps{
-			getwd: func() (string, error) { return cwd, nil },
-			inspectChanges: func(ctx context.Context, options zerogit.InspectOptions) (zerogit.ChangeSummary, error) {
-				return summary, nil
-			},
-			resolveConfig: func(workspaceRoot string, overrides config.Overrides) (config.ResolvedConfig, error) {
-				return execResolvedConfig(), nil
-			},
-			newProvider: func(profile config.ProviderProfile) (zeroruntime.Provider, error) {
-				return mockProvEmpty, nil
-			},
-		})
-		if code == exitSuccess {
-			t.Fatal("expected command to fail when LLM returns empty response, got success")
-		}
-		if !strings.Contains(stderr.String(), "empty commit message") {
-			t.Fatalf("expected empty commit message error in stderr, got %q", stderr.String())
-		}
-	})
-}

internal/cli/workflows.go

@@ -6,16 +6,13 @@ import (
 	"io"
 	"strconv"
 	"strings"
-	"time"
 
-	"github.com/Gitlawb/zero/internal/config"
 	"github.com/Gitlawb/zero/internal/redaction"
 	"github.com/Gitlawb/zero/internal/selfverify"
 	"github.com/Gitlawb/zero/internal/testrunner"
 	"github.com/Gitlawb/zero/internal/verify"
 	"github.com/Gitlawb/zero/internal/worktrees"
 	"github.com/Gitlawb/zero/internal/zerogit"
-	"github.com/Gitlawb/zero/internal/zeroruntime"
 )
 
 type worktreeCommandOptions struct {
@@ -38,17 +35,8 @@ type changesCommandOptions struct {
 	cwd          string
 	baseRef      string
 	message      string
-	hasMessage   bool
 	dryRun       bool
 	maxDiffBytes int
-	remote       string
-	force        bool
-	title        string
-	body         string
-	fill         bool
-	draft        bool
-	yes          bool
-	auto         bool
 }
 
 func runWorktrees(args []string, stdout io.Writer, stderr io.Writer, deps appDeps) int {
@@ -210,52 +198,9 @@ func runChanges(args []string, stdout io.Writer, stderr io.Writer, deps appDeps)
 		}
 		return exitSuccess
 	case "commit":
-		var message string
-		if options.auto {
-			summary, err := deps.inspectChanges(context.Background(), zerogit.InspectOptions{
-				Cwd:          workspaceRoot,
-				MaxDiffBytes: options.maxDiffBytes,
-			})
-			if err != nil {
-				return writeExecUsageError(stderr, fmt.Sprintf("failed to inspect changes: %v", err))
-			}
-			if summary.Clean {
-				return writeExecUsageError(stderr, "no changes to commit")
-			}
-
-			resolved, err := deps.resolveConfig(workspaceRoot, config.Overrides{})
-			if err != nil {
-				return writeExecUsageError(stderr, fmt.Sprintf("failed to resolve config: %v", err))
-			}
-			if !config.HasProviderProfile(resolved.Provider) {
-				return writeExecUsageError(stderr, "no provider configured for auto-commit message")
-			}
-			provider, err := deps.newProvider(resolved.Provider)
-			if err != nil {
-				return writeExecUsageError(stderr, fmt.Sprintf("failed to create provider: %v", err))
-			}
-
-			if !options.json {
-				if _, err := fmt.Fprintln(stdout, "Generating commit message using LLM..."); err != nil {
-					return exitCrash
-				}
-			}
-
-			safeSummary := redactChangeSummary(summary)
-			genCtx, cancel := context.WithTimeout(context.Background(), 60*time.Second)
-			defer cancel()
-			msg, err := generateAutoCommitMessage(genCtx, provider, resolved.Provider.Model, safeSummary)
-			if err != nil {
-				return writeExecUsageError(stderr, fmt.Sprintf("failed to generate commit message: %v", err))
-			}
-			message = msg
-		} else {
-			message = options.message
-		}
-
 		result, err := deps.commitChanges(context.Background(), zerogit.CommitOptions{
 			Cwd:          workspaceRoot,
-			Message:      message,
+			Message:      options.message,
 			DryRun:       options.dryRun,
 			MaxDiffBytes: options.maxDiffBytes,
 		})
@@ -273,10 +218,6 @@ func runChanges(args []string, stdout io.Writer, stderr io.Writer, deps appDeps)
 			return exitCrash
 		}
 		return exitSuccess
-	case "push":
-		return runChangesPush(args, stdout, stderr, deps)
-	case "pr", "pull-request":
-		return runChangesPR(args, stdout, stderr, deps)
 	default:
 		return writeExecUsageError(stderr, fmt.Sprintf("unknown changes command %q", command))
 	}
@@ -454,11 +395,9 @@ func parseChangesArgs(args []string, command string) (changesCommandOptions, boo
 				return options, false, err
 			}
 			options.message = value
-			options.hasMessage = true
 			index = next
 		case strings.HasPrefix(arg, "--message="):
 			options.message = strings.TrimSpace(strings.TrimPrefix(arg, "--message="))
-			options.hasMessage = true
 		case arg == "--diff-bytes":
 			value, next, err := nextFlagValue(args, index, arg)
 			if err != nil {
@@ -476,73 +415,18 @@ func parseChangesArgs(args []string, command string) (changesCommandOptions, boo
 				return options, false, err
 			}
 			options.maxDiffBytes = maxDiffBytes
-		case arg == "--remote":
-			value, next, err := nextFlagValue(args, index, arg)
-			if err != nil {
-				return options, false, err
-			}
-			options.remote = strings.TrimSpace(value)
-			index = next
-		case strings.HasPrefix(arg, "--remote="):
-			options.remote = strings.TrimSpace(strings.TrimPrefix(arg, "--remote="))
-		case arg == "--force":
-			options.force = true
-		case arg == "--title":
-			value, next, err := nextFlagValue(args, index, arg)
-			if err != nil {
-				return options, false, err
-			}
-			options.title = value
-			index = next
-		case strings.HasPrefix(arg, "--title="):
-			options.title = strings.TrimPrefix(arg, "--title=")
-		case arg == "--body":
-			value, next, err := nextFlagValue(args, index, arg)
-			if err != nil {
-				return options, false, err
-			}
-			options.body = value
-			index = next
-		case strings.HasPrefix(arg, "--body="):
-			options.body = strings.TrimPrefix(arg, "--body=")
-		case arg == "--fill":
-			options.fill = true
-		case arg == "--draft":
-			options.draft = true
-		case arg == "--yes":
-			options.yes = true
-		case arg == "-a" || arg == "--auto":
-			options.auto = true
 		case strings.HasPrefix(arg, "-"):
 			return options, false, execUsageError{fmt.Sprintf("unknown changes flag %q", arg)}
 		default:
 			return options, false, execUsageError{fmt.Sprintf("unexpected changes argument %q", arg)}
 		}
 	}
-	if command != "commit" && options.message != "" {
-		return options, false, execUsageError{"--message is only valid with `zero changes commit`"}
+	if command != "commit" && (options.message != "" || options.dryRun) {
+		return options, false, execUsageError{"--message and --dry-run are only valid with `zero changes commit`"}
 	}
-	if command != "commit" && (options.hasMessage || options.dryRun || options.auto) {
-		return options, false, execUsageError{"--message, --dry-run, and --auto are only valid with `zero changes commit`"}
-	}
-	if command == "commit" && options.hasMessage && options.auto {
-		return options, false, execUsageError{"cannot specify both --message and --auto"}
-	}
-	if command != "commit" && command != "push" && options.dryRun {
-		return options, false, execUsageError{"--dry-run is only valid with commit or push"}
-	}
-	if command != "inspect" && options.baseRef != "" {
+	if command == "commit" && options.baseRef != "" {
 		return options, false, execUsageError{"--base is only valid with `zero changes inspect`"}
 	}
-	if command != "push" && command != "pr" && (options.remote != "" || options.force) {
-		return options, false, execUsageError{"--remote and --force are only valid with push or pr"}
-	}
-	if command != "pr" && (options.title != "" || options.body != "" || options.fill || options.draft) {
-		return options, false, execUsageError{"--title, --body, --fill, and --draft are only valid with `zero changes pr`"}
-	}
-	if command != "push" && command != "pr" && options.yes {
-		return options, false, execUsageError{"--yes is only valid with push or pr"}
-	}
 	return options, false, nil
 }
 
@@ -820,187 +704,17 @@ func writeChangesHelp(w io.Writer) error {
 	_, err := fmt.Fprint(w, `Usage:
   zero changes inspect [flags]
   zero changes commit [flags]
-  zero changes push [flags]
-  zero changes pr [flags]
 
-Inspects, commits, pushes, and creates pull requests for local git changes.
+Inspects local git changes and optionally creates a commit.
 
 Flags:
   -C, --cwd <path>        Workspace directory
       --base <ref>        Diff against <ref>...HEAD instead of the working tree
       --diff-bytes <n>    Maximum diff bytes to include
   -m, --message <text>    Commit message for `+"`zero changes commit`"+`
-      --dry-run           Preview commit metadata / push without mutating git state
-      --remote <name>     Remote to push to (defaults to upstream tracked branch or origin)
-      --force             Use force-with-lease when pushing
-      --title <text>      PR title
-      --body <text>       PR body
-      --fill              Automatically populate PR title and body from commits
-      --draft             Create PR as a draft
-      --yes               Confirm pushing to a default/protected branch
-  -a, --auto              Auto-generate commit message using LLM (use --dry-run to preview)
       --dry-run           Preview commit metadata without mutating git state
       --json              Print JSON output
   -h, --help              Show this help
 `)
 	return err
 }
-
-func runChangesPush(args []string, stdout io.Writer, stderr io.Writer, deps appDeps) int {
-	options, help, err := parseChangesArgs(args, "push")
-	if err != nil {
-		return writeExecUsageError(stderr, err.Error())
-	}
-	if help {
-		if err := writeChangesHelp(stdout); err != nil {
-			return exitCrash
-		}
-		return exitSuccess
-	}
-	workspaceRoot, err := resolveWorkspaceRoot(options.cwd, deps)
-	if err != nil {
-		return writeExecUsageError(stderr, err.Error())
-	}
-
-	result, err := deps.pushChanges(context.Background(), zerogit.PushOptions{
-		Cwd:                    workspaceRoot,
-		Remote:                 options.remote,
-		Force:                  options.force,
-		DryRun:                 options.dryRun,
-		AllowPushDefaultBranch: options.yes,
-	})
-	if err != nil {
-		return writeExecUsageError(stderr, err.Error())
-	}
-
-	if options.json {
-		if err := writePrettyJSON(stdout, result); err != nil {
-			return exitCrash
-		}
-		return exitSuccess
-	}
-
-	dryRunStr := ""
-	if options.dryRun {
-		dryRunStr = " (dry run)"
-	}
-	if _, err := fmt.Fprintf(stdout, "Pushed branch %s to remote %s%s\n", result.Branch, result.Remote, dryRunStr); err != nil {
-		return exitCrash
-	}
-	if result.Output != "" {
-		if _, err := fmt.Fprintln(stdout, result.Output); err != nil {
-			return exitCrash
-		}
-	}
-	return exitSuccess
-}
-
-func runChangesPR(args []string, stdout io.Writer, stderr io.Writer, deps appDeps) int {
-	options, help, err := parseChangesArgs(args, "pr")
-	if err != nil {
-		return writeExecUsageError(stderr, err.Error())
-	}
-	if help {
-		if err := writeChangesHelp(stdout); err != nil {
-			return exitCrash
-		}
-		return exitSuccess
-	}
-	if !options.fill && options.title == "" {
-		return writeExecUsageError(stderr, "must provide either --fill or --title to run non-interactively")
-	}
-	workspaceRoot, err := resolveWorkspaceRoot(options.cwd, deps)
-	if err != nil {
-		return writeExecUsageError(stderr, err.Error())
-	}
-
-	if !options.json {
-		if _, err := fmt.Fprintln(stdout, "Pushing current branch to set upstream..."); err != nil {
-			return exitCrash
-		}
-	}
-	pushResult, err := deps.pushChanges(context.Background(), zerogit.PushOptions{
-		Cwd:                    workspaceRoot,
-		Remote:                 options.remote,
-		Force:                  options.force,
-		AllowPushDefaultBranch: options.yes,
-	})
-	if err != nil {
-		return writeExecUsageError(stderr, fmt.Sprintf("auto-push failed: %v", err))
-	}
-	if !options.json {
-		if _, err := fmt.Fprintf(stdout, "Pushed branch %s to remote %s\n", pushResult.Branch, pushResult.Remote); err != nil {
-			return exitCrash
-		}
-	}
-
-	prResult, err := deps.createPR(context.Background(), zerogit.PROptions{
-		Cwd:   workspaceRoot,
-		Fill:  options.fill,
-		Draft: options.draft,
-		Title: options.title,
-		Body:  options.body,
-	})
-	if err != nil {
-		return writeExecUsageError(stderr, err.Error())
-	}
-
-	if options.json {
-		type prJSONResult struct {
-			Branch string `json:"branch"`
-			Remote string `json:"remote"`
-			Output string `json:"output"`
-		}
-		res := prJSONResult{
-			Branch: pushResult.Branch,
-			Remote: pushResult.Remote,
-			Output: strings.TrimSpace(prResult.Output),
-		}
-		if err := writePrettyJSON(stdout, res); err != nil {
-			return exitCrash
-		}
-		return exitSuccess
-	}
-
-	if _, err := fmt.Fprintln(stdout, strings.TrimSpace(prResult.Output)); err != nil {
-		return exitCrash
-	}
-	return exitSuccess
-}
-
-func generateAutoCommitMessage(ctx context.Context, provider zeroruntime.Provider, model string, summary zerogit.ChangeSummary) (string, error) {
-	var promptBuilder strings.Builder
-	promptBuilder.WriteString("Analyze the following git diff and generate a concise, conventional commit message.\n")
-	promptBuilder.WriteString("The commit message subject line must be 72 characters or fewer, starting with a conventional commit type (e.g., feat, fix, docs, style, refactor, test, chore) followed by a colon and space, and a lowercase description.\n")
-	promptBuilder.WriteString("You may optionally include a blank line and a bulleted list of changes for the body if there are multiple files or complex changes.\n")
-	promptBuilder.WriteString("Output ONLY the raw commit message text. Do not wrap the message in markdown code block fence, do not include quotes or any introduction/explanation.\n\n")
-	promptBuilder.WriteString("Git Diff:\n")
-	promptBuilder.WriteString(summary.Diff)
-
-	request := zeroruntime.CompletionRequest{
-		Messages: []zeroruntime.Message{
-			{Role: zeroruntime.MessageRoleUser, Content: promptBuilder.String()},
-		},
-	}
-	stream, err := provider.StreamCompletion(ctx, request)
-	if err != nil {
-		return "", err
-	}
-	collected := zeroruntime.CollectStream(ctx, stream)
-	if collected.Error != "" {
-		return "", fmt.Errorf("%s", collected.Error)
-	}
-
-	msg := strings.TrimSpace(collected.Text)
-	if strings.HasPrefix(msg, "```") {
-		if idx := strings.Index(msg, "\n"); idx != -1 {
-			msg = msg[idx+1:]
-		}
-	}
-	msg = strings.TrimSuffix(msg, "```")
-	msg = strings.TrimSpace(msg)
-	if msg == "" {
-		return "", fmt.Errorf("provider returned empty commit message")
-	}
-	return msg, nil
-}

internal/config/resolver.go

@@ -130,11 +130,7 @@ func Resolve(options ResolveOptions) (ResolvedConfig, error) {
 
 	providers, active, err := normalizeProviders(cfg.Providers, cfg.ActiveProvider, options.Env)
 	if err != nil {
-		// On ErrNoActiveProvider, providers may still hold the successfully
-		// normalized (but active-less) profile list — keep it so a caller can fall
-		// back to an already-configured usable provider instead of treating this
-		// like a config with nothing set up at all.
-		return ResolvedConfig{Providers: providers}, err
+		return ResolvedConfig{}, err
 	}
 
 	return ResolvedConfig{
@@ -148,7 +144,6 @@ func Resolve(options ResolveOptions) (ResolvedConfig, error) {
 		Tools:          cfg.Tools,
 		Swarm:          cfg.Swarm,
 		Preferences:    cfg.Preferences,
-		KeyBindings:    cfg.KeyBindings,
 		LocalControl:   cfg.LocalControl,
 	}, nil
 }
@@ -230,7 +225,6 @@ func mergeConfig(dst *FileConfig, src FileConfig) {
 		dst.Preferences.Theme = strings.TrimSpace(src.Preferences.Theme)
 	}
 	mergeLocalControlConfig(&dst.LocalControl, src.LocalControl)
-	mergeKeyBindings(&dst.KeyBindings, src.KeyBindings)
 }
 
 func mergeProjectConfig(dst *FileConfig, src FileConfig) error {
@@ -283,7 +277,6 @@ func mergeProjectConfig(dst *FileConfig, src FileConfig) error {
 	if src.Swarm.MaxTeamSize != 0 {
 		dst.Swarm.MaxTeamSize = src.Swarm.MaxTeamSize
 	}
-	mergeKeyBindings(&dst.KeyBindings, src.KeyBindings)
 	// Local control is intentionally user-config/override only. A cloned project
 	// must not be able to make browser, desktop, or terminal automation tools
 	// appear in the model's tool surface.
@@ -590,17 +583,9 @@ func applyProviderEnv(cfg *FileConfig, providerKind ProviderKind, env envProfile
 	if profile.Name == "" {
 		profile.Name = string(providerKind)
 	}
-	// A non-official baseURL from the environment signals a proxy/gateway, so promote
-	// the first-party kind to its -compatible transport (which accepts a custom URL).
-	// Env-only by design: a custom baseURL in a project config.json is left as-is and
-	// rejected by Resolve, so an untrusted project can't redirect a first-party key to
-	// another host.
 	if providerKind == ProviderKindOpenAI && baseURL != "" && !isOfficialOpenAIBaseURL(baseURL) {
 		profile.ProviderKind = ProviderKindOpenAICompatible
 	}
-	if providerKind == ProviderKindAnthropic && baseURL != "" && !isOfficialAnthropicBaseURL(baseURL) {
-		profile.ProviderKind = ProviderKindAnthropicCompat
-	}
 	// When the env supplies only credentials (no baseURL) for a provider name that
 	// already exists, don't force the standard transport kind — a same-named
 	// openai-compatible/anthropic-compatible proxy or gateway must keep its kind.
@@ -680,7 +665,6 @@ func applyOverrides(cfg *FileConfig, overrides Overrides) {
 		cfg.Tools.deferThresholdSet = true
 	}
 	mergeLocalControlConfig(&cfg.LocalControl, overrides.LocalControl)
-	mergeKeyBindings(&cfg.KeyBindings, overrides.KeyBindings)
 	for _, provider := range overrides.Providers {
 		mergeProvider(cfg, provider)
 	}
@@ -716,24 +700,6 @@ func mergeLocalControlDriverConfig(dst *LocalControlDriverConfig, src LocalContr
 	}
 }
 
-func mergeKeyBindings(dst *KeyBindingsConfig, src KeyBindingsConfig) {
-	if src.ToggleDetailed != "" {
-		dst.ToggleDetailed = src.ToggleDetailed
-	}
-	if src.ToggleMouse != "" {
-		dst.ToggleMouse = src.ToggleMouse
-	}
-	if src.CycleReasoning != "" {
-		dst.CycleReasoning = src.CycleReasoning
-	}
-	if src.TogglePlan != "" {
-		dst.TogglePlan = src.TogglePlan
-	}
-	if src.ToggleSidebar != "" {
-		dst.ToggleSidebar = src.ToggleSidebar
-	}
-}
-
 func mergeMCPConfig(dst *MCPConfig, src MCPConfig) {
 	if len(src.Servers) == 0 {
 		return
@@ -868,11 +834,7 @@ func normalizeProvidersWithOptions(providers []ProviderProfile, activeName strin
 	}
 
 	if !activeFound {
-		// Return the successfully normalized list alongside the error (rather than
-		// nil) so a caller like the interactive TUI can still fall back to an
-		// already-configured, usable provider instead of forcing a full
-		// re-onboarding wizard just because none was marked active.
-		return normalized, ProviderProfile{}, fmt.Errorf("%w: active provider %q not found", ErrNoActiveProvider, activeName)
+		return nil, ProviderProfile{}, fmt.Errorf("%w: active provider %q not found", ErrNoActiveProvider, activeName)
 	}
 	if active.Model == "" {
 		return nil, ProviderProfile{}, &setupFixableError{

internal/config/resolver_test.go

@@ -617,35 +617,6 @@ func TestResolveUsesOpenAIEnvFallback(t *testing.T) {
 	}
 }
 
-func TestResolveUsesAnthropicEnvBaseURLAsCompatible(t *testing.T) {
-	// ANTHROPIC_BASE_URL pointing at a proxy/gateway must resolve to an
-	// anthropic-compatible provider (mirroring OPENAI_BASE_URL), not the "requires
-	// official baseURL" rejection — issue #479. The env is user-controlled, so a
-	// custom URL there is a deliberate gateway choice, unlike a project config.json.
-	resolved, err := Resolve(ResolveOptions{
-		Env: map[string]string{
-			"ANTHROPIC_API_KEY":  "sk-ant-env",
-			"ANTHROPIC_BASE_URL": "https://gateway.example/anthropic",
-			"ANTHROPIC_MODEL":    "claude-custom",
-		},
-	})
-	if err != nil {
-		t.Fatalf("Resolve() error = %v", err)
-	}
-	if resolved.ActiveProvider != "anthropic" {
-		t.Fatalf("ActiveProvider = %q, want anthropic", resolved.ActiveProvider)
-	}
-	if resolved.Provider.ProviderKind != ProviderKindAnthropicCompat {
-		t.Fatalf("ProviderKind = %q, want anthropic-compatible", resolved.Provider.ProviderKind)
-	}
-	if resolved.Provider.BaseURL != "https://gateway.example/anthropic" {
-		t.Fatalf("BaseURL = %q, want gateway URL", resolved.Provider.BaseURL)
-	}
-	if resolved.Provider.APIKey != "sk-ant-env" || resolved.Provider.Model != "claude-custom" {
-		t.Fatalf("Provider = %#v, want env credentials/model", resolved.Provider)
-	}
-}
-
 func TestResolveUsesOpenAIAPIKeyOnlyWithDefaultModel(t *testing.T) {
 	resolved, err := Resolve(ResolveOptions{
 		Env: map[string]string{
@@ -945,25 +916,6 @@ func TestResolveRejectsActiveProviderWithoutConfiguredProfiles(t *testing.T) {
 	}
 }
 
-func TestResolveKeepsNormalizedProvidersWhenNoneMarkedActive(t *testing.T) {
-	// Multiple providers configured (e.g. via `zero provider add`) but
-	// activeProvider is blank/stale — a caller like the interactive TUI still
-	// needs the normalized list to fall back to an already-usable provider
-	// instead of forcing a full re-onboarding wizard.
-	path := writeConfig(t, `{"providers":[
-		{"name":"work","provider_kind":"openai","apiKey":"sk-test","model":"gpt-test"},
-		{"name":"other","provider_kind":"openai","apiKey":"sk-other","model":"gpt-test"}
-	]}`)
-
-	resolved, err := Resolve(ResolveOptions{ProjectConfigPath: path, Env: map[string]string{}})
-	if !errors.Is(err, ErrNoActiveProvider) {
-		t.Fatalf("error = %v, want errors.Is(err, ErrNoActiveProvider)", err)
-	}
-	if len(resolved.Providers) != 2 {
-		t.Fatalf("Providers = %#v, want the 2 normalized profiles preserved despite the error", resolved.Providers)
-	}
-}
-
 func TestResolveTrimsProviderProfileAliasesBeforeFallback(t *testing.T) {
 	path := writeConfig(t, `{
 		"activeProvider": "custom",

internal/config/types.go

@@ -112,25 +112,6 @@ func (p PreferencesConfig) RecapsEnabled() bool {
 	return p.Recaps == nil || *p.Recaps
 }
 
-// KeyBindingDef defines one key binding string (e.g. "ctrl+o") that the TUI
-// can remap. An empty string means "use the built-in default" for that action.
-type KeyBindingDef string
-
-// KeyBindingsConfig holds the subset of TUI keybindings that users may remap
-// via config.json. Each field defaults to a sensible built-in when empty.
-type KeyBindingsConfig struct {
-	// ToggleDetailed toggles the detailed transcript view (default: ctrl+o).
-	ToggleDetailed KeyBindingDef `json:"toggleDetailed,omitempty"`
-	// ToggleMouse toggles mouse capture release (default: ctrl+e).
-	ToggleMouse KeyBindingDef `json:"toggleMouse,omitempty"`
-	// CycleReasoning cycles through reasoning effort levels (default: ctrl+t).
-	CycleReasoning KeyBindingDef `json:"cycleReasoning,omitempty"`
-	// TogglePlan toggles the plan panel expansion (default: ctrl+p).
-	TogglePlan KeyBindingDef `json:"togglePlan,omitempty"`
-	// ToggleSidebar toggles the right context sidebar (default: ctrl+b).
-	ToggleSidebar KeyBindingDef `json:"toggleSidebar,omitempty"`
-}
-
 // LocalControlConfig controls local browser/desktop/terminal automation helpers.
 // Helpers are discovered lazily by the tool that needs them; no setup command or
 // background probe is required during startup.
@@ -225,7 +206,6 @@ type FileConfig struct {
 	Tools          ToolsConfig        `json:"tools,omitempty"`
 	Swarm          SwarmConfig        `json:"swarm,omitempty"`
 	Preferences    PreferencesConfig  `json:"preferences,omitempty"`
-	KeyBindings    KeyBindingsConfig  `json:"keybindings,omitempty"`
 	LocalControl   LocalControlConfig `json:"localControl,omitempty"`
 }
 
@@ -240,7 +220,6 @@ func (cfg FileConfig) MarshalJSON() ([]byte, error) {
 		Tools          ToolsConfig         `json:"tools,omitempty"`
 		Swarm          SwarmConfig         `json:"swarm,omitempty"`
 		Preferences    PreferencesConfig   `json:"preferences,omitempty"`
-		KeyBindings    KeyBindingsConfig   `json:"keybindings,omitempty"`
 		LocalControl   *LocalControlConfig `json:"localControl,omitempty"`
 	}
 	raw := rawConfig{
@@ -253,7 +232,6 @@ func (cfg FileConfig) MarshalJSON() ([]byte, error) {
 		Tools:          cfg.Tools,
 		Swarm:          cfg.Swarm,
 		Preferences:    cfg.Preferences,
-		KeyBindings:    cfg.KeyBindings,
 	}
 	if !cfg.LocalControl.Empty() {
 		raw.LocalControl = &cfg.LocalControl
@@ -278,7 +256,6 @@ type Overrides struct {
 	Sandbox        SandboxConfig
 	Notify         NotifyConfig
 	Tools          ToolsConfig
-	KeyBindings    KeyBindingsConfig
 	LocalControl   LocalControlConfig
 }
 
@@ -293,7 +270,6 @@ type ResolvedConfig struct {
 	Tools          ToolsConfig
 	Swarm          SwarmConfig
 	Preferences    PreferencesConfig
-	KeyBindings    KeyBindingsConfig
 	LocalControl   LocalControlConfig
 }
 
@@ -340,7 +316,6 @@ func (cfg *FileConfig) UnmarshalJSON(data []byte) error {
 		Tools           ToolsConfig                `json:"tools"`
 		Swarm           SwarmConfig                `json:"swarm"`
 		Preferences     PreferencesConfig          `json:"preferences"`
-		KeyBindings     KeyBindingsConfig          `json:"keybindings"`
 		LocalControl    LocalControlConfig         `json:"localControl"`
 		MCPServers      map[string]MCPServerConfig `json:"mcpServers"`
 		MCPServersSnake map[string]MCPServerConfig `json:"mcp_servers"`
@@ -367,7 +342,6 @@ func (cfg *FileConfig) UnmarshalJSON(data []byte) error {
 	cfg.Tools = raw.Tools
 	cfg.Swarm = raw.Swarm
 	cfg.Preferences = raw.Preferences
-	cfg.KeyBindings = raw.KeyBindings
 	cfg.LocalControl = raw.LocalControl
 	if cfg.MCP.Servers == nil && (len(raw.MCPServers) > 0 || len(raw.MCPServersSnake) > 0) {
 		cfg.MCP.Servers = map[string]MCPServerConfig{}

internal/doctor/hardening.go

@@ -131,45 +131,29 @@ func doctorSandboxPolicy(cfg config.SandboxConfig) sandbox.Policy {
 // lspServersCheck reports which language servers ZERO would use are present on
 // PATH. Missing servers are not a failure — ZERO degrades to text-only edits for
 // those languages — so the worst status is WARN, and each missing server gets an
-// actionable install command keyed by its binary name. Only the tier-1 servers
-// (lsp.CoreServerBinaries) drive the status: the long-tail servers configured
-// for breadth are listed informationally under missingOptional, because warning
-// about a missing zls on a machine with no Zig code would be permanent noise.
+// actionable install command keyed by its binary name.
 func lspServersCheck(lookup func(string) (string, error)) Check {
 	if lookup == nil {
 		lookup = exec.LookPath
 	}
-	core := map[string]bool{}
-	for _, binary := range lsp.CoreServerBinaries() {
-		core[binary] = true
-	}
 	present := map[string]any{}
 	missing := map[string]any{}
-	missingOptional := map[string]any{}
 	for _, binary := range lsp.ServerBinaries() {
 		if _, err := lookup(binary); err == nil {
 			present[binary] = "on PATH"
 			continue
 		}
-		if core[binary] {
-			missing[binary] = lspRemedy(binary)
-		} else {
-			missingOptional[binary] = lspRemedy(binary)
-		}
-	}
-	details := map[string]any{"present": present}
-	if len(missingOptional) > 0 {
-		details["missingOptional"] = missingOptional
+		missing[binary] = lspRemedy(binary)
 	}
 	if len(missing) == 0 {
-		message := "All core language servers are available on PATH."
-		if len(missingOptional) > 0 {
-			message = fmt.Sprintf("All core language servers are available on PATH (%d optional server(s) not installed).", len(missingOptional))
-		}
-		return check("lsp.servers", "LSP servers", StatusPass, message, details)
+		return check("lsp.servers", "LSP servers", StatusPass, "All known language servers are available on PATH.", map[string]any{
+			"present": present,
+		})
 	}
-	details["missing"] = missing
-	return check("lsp.servers", "LSP servers", StatusWarn, fmt.Sprintf("%d language server(s) missing from PATH; affected files degrade to text-only edits.", len(missing)), details)
+	return check("lsp.servers", "LSP servers", StatusWarn, fmt.Sprintf("%d language server(s) missing from PATH; affected files degrade to text-only edits.", len(missing)), map[string]any{
+		"present": present,
+		"missing": missing,
+	})
 }
 
 // lspRemedy returns an actionable install command for a missing language-server

internal/errhint/errhint.go

@@ -1,167 +0,0 @@
-// Package errhint classifies provider/model failures into a few user-actionable
-// categories and turns them into a one-line "next step" hint.
-//
-// Provider errors already arrive with a classified string prefix from
-// providerio.ClassifiedError ("auth error:", "rate limit error:", …); lower-level
-// failures (DNS, TLS, timeouts, context-length) arrive as raw driver or library
-// messages. Classify matches both so the interactive error row (TUI) and the
-// `zero exec` provider-error path (CLI) can append one concrete next step instead
-// of dumping an identical red blob for every failure mode.
-package errhint
-
-import "strings"
-
-// Category buckets a provider/model failure into a small set of classes that each
-// map to a distinct recovery action.
-type Category int
-
-const (
-	// Unknown means the error didn't match any known signature; callers should
-	// emit no hint rather than guess.
-	Unknown Category = iota
-	Auth
-	RateLimit
-	Connectivity
-	ModelNotFound
-	ContextOverflow
-)
-
-// providerMarkers are the prefixes the provider layer attaches to every
-// provider-originated failure: providerio.ClassifiedError emits "auth error:",
-// "rate limit error:", "provider error:", and "provider request error:", and the
-// streaming paths wrap transport/decoding failures as "provider stream error:".
-// A UI surface's error can also be a *local* failure (a tool's "permission
-// denied", a "file does not exist", a config error), so Classify only proceeds
-// past this gate for messages that are recognizably from the provider — otherwise
-// a broad substring like "does not exist" would attach a bogus /model hint to an
-// unrelated local error.
-var providerMarkers = []string{
-	"auth error:",
-	"rate limit error:",
-	"provider error:",
-	"provider request error:",
-	"provider stream error:",
-}
-
-// Classify buckets err by scanning its message for known signatures. It is a
-// deliberately conservative string heuristic — the provider layer has already
-// discarded the numeric HTTP status by the time the error reaches a UI surface,
-// so the message is all we have. It first gates on a provider-origin marker (see
-// providerMarkers) so local failures never draw a provider hint, then sub-classifies.
-// Order matters: more specific signatures are tested before broader ones (e.g.
-// "context length" as overflow before the generic "timeout" as connectivity).
-func Classify(err error) Category {
-	if err == nil {
-		return Unknown
-	}
-	m := strings.ToLower(err.Error())
-	if !containsAny(m, providerMarkers...) {
-		return Unknown
-	}
-	switch {
-	case containsAny(m, "auth error:", "unauthorized", "api key", "api_key", "invalid_api_key",
-		"authentication", "permission denied", "forbidden") || containsStatusCode(m, "401", "403"):
-		return Auth
-	case containsAny(m, "rate limit", "rate_limit", "too many requests", "quota",
-		"resource_exhausted", "overloaded") || containsStatusCode(m, "429", "529"):
-		return RateLimit
-	case containsAny(m, "context length", "context window", "maximum context", "context_length_exceeded",
-		"too many tokens", "prompt is too long", "reduce the length", "maximum context length"):
-		return ContextOverflow
-	case containsAny(m, "model not found", "model_not_found", "does not exist", "unknown model",
-		"no such model", "unsupported model", "invalid model", "model is not"):
-		return ModelNotFound
-	case containsAny(m, "dial tcp", "no such host", "connection refused", "network is unreachable",
-		"i/o timeout", "context deadline exceeded", "tls handshake", "connection reset",
-		"unexpected eof", "lookup ", "timeout"):
-		return Connectivity
-	default:
-		return Unknown
-	}
-}
-
-// TUIHint returns a one-line hint referencing interactive slash commands, or ""
-// when the category is Unknown. Meant to sit under the raw error in the live
-// error row.
-func TUIHint(err error) string {
-	switch Classify(err) {
-	case Auth:
-		return "API key rejected — run /provider to re-check your credentials"
-	case RateLimit:
-		return "Rate limited — wait a moment, or switch model with /model"
-	case Connectivity:
-		return "Can't reach the provider — run /doctor --connectivity"
-	case ModelNotFound:
-		return "Model unavailable — pick another with /model"
-	case ContextOverflow:
-		return "Context window full — run /compact to free space"
-	default:
-		return ""
-	}
-}
-
-// CLIHint returns a one-line hint referencing `zero …` subcommands, or "" when the
-// category is Unknown. Meant for the non-interactive `zero exec` error path, where
-// slash commands don't apply.
-func CLIHint(err error) string {
-	switch Classify(err) {
-	case Auth:
-		return "API key rejected — run `zero auth` or set the provider's API key, then retry"
-	case RateLimit:
-		return "Rate limited — wait a moment, or switch model with --model"
-	case Connectivity:
-		return "Can't reach the provider — run `zero doctor`"
-	case ModelNotFound:
-		return "Model unavailable — run `zero doctor` or pick another with --model"
-	case ContextOverflow:
-		return "Context window full — shorten the prompt or start a fresh session"
-	default:
-		return ""
-	}
-}
-
-func containsAny(haystack string, needles ...string) bool {
-	for _, n := range needles {
-		if strings.Contains(haystack, n) {
-			return true
-		}
-	}
-	return false
-}
-
-// containsStatusCode reports whether haystack contains any of the given HTTP
-// status codes as a standalone number — not embedded in a longer digit run like
-// "completed in 4290ms" or "request id 14015" — so an incidental number can't be
-// mis-bucketed as an auth/rate-limit failure.
-func containsStatusCode(haystack string, codes ...string) bool {
-	return HasStatusCode(haystack, codes...)
-}
-
-// HasStatusCode reports whether haystack contains any of the given HTTP status
-// codes as a standalone number — not embedded in a longer digit run like
-// "completed in 4290ms" or "request id 14015". Exported so other packages (e.g.
-// the reconnect classifier) can gate on a status code without re-implementing
-// the digit-boundary check.
-func HasStatusCode(haystack string, codes ...string) bool {
-	for _, code := range codes {
-		for from := 0; ; {
-			rel := strings.Index(haystack[from:], code)
-			if rel < 0 {
-				break
-			}
-			pos := from + rel
-			beforeOK := pos == 0 || !isASCIIDigit(haystack[pos-1])
-			end := pos + len(code)
-			afterOK := end >= len(haystack) || !isASCIIDigit(haystack[end])
-			if beforeOK && afterOK {
-				return true
-			}
-			from = pos + 1
-		}
-	}
-	return false
-}
-
-func isASCIIDigit(b byte) bool {
-	return b >= '0' && b <= '9'
-}

internal/errhint/errhint_test.go

@@ -1,94 +0,0 @@
-package errhint
-
-import (
-	"errors"
-	"strings"
-	"testing"
-)
-
-func TestClassify(t *testing.T) {
-	cases := []struct {
-		name string
-		msg  string
-		want Category
-	}{
-		{"nil-ish empty", "", Unknown},
-		{"providerio auth prefix", "auth error: your API key is missing or invalid — run `zero auth`", Auth},
-		{"raw 401", "provider request error: 401 Unauthorized", Auth},
-		{"invalid api key", "provider request error: invalid_api_key: incorrect key provided", Auth},
-		{"rate limit prefix", "rate limit error: 429 too many requests", RateLimit},
-		{"overloaded", "provider error: model is overloaded, please retry", RateLimit},
-		{"resource exhausted gemini", "provider stream error: rpc error: code = ResourceExhausted desc = quota exceeded", RateLimit},
-		{"context length openai", "provider request error: this model's maximum context length is 128000 tokens", ContextOverflow},
-		{"context_length_exceeded", "provider request error: context_length_exceeded", ContextOverflow},
-		{"model not found", "provider request error: 404 the model `gpt-9` does not exist", ModelNotFound},
-		{"unknown model", "provider request error: unknown model: sonnet-99", ModelNotFound},
-		{"dns failure", "provider stream error: Post \"https://api...\": dial tcp: lookup api.foo.com: no such host", Connectivity},
-		{"connection refused", "provider stream error: dial tcp 127.0.0.1:443: connection refused", Connectivity},
-		{"deadline", "provider stream error: context deadline exceeded (Client.Timeout exceeded)", Connectivity},
-		{"provider-marked but no sub-signature", "provider error: something totally unexpected happened", Unknown},
-
-		// An incidental number that merely contains a status-code digit run must NOT
-		// be mis-bucketed (digit-boundary check), even behind a provider marker.
-		{"incidental latency number", "provider error: request completed in 4290ms then failed", Unknown},
-		{"incidental request id", "provider error: request id 14015 failed unexpectedly", Unknown},
-		{"standalone 401 still auth", "provider request error: got 401 from upstream", Auth},
-		{"standalone 429 still rate limit", "provider error: 429 returned", RateLimit},
-
-		// Local (non-provider) failures must NOT be classified — no provider marker,
-		// so no bogus recovery hint attaches to them.
-		{"local fs permission denied", "open /etc/shadow: permission denied", Unknown},
-		{"local file missing", "stat foo.go: no such file or directory", Unknown},
-		{"local model config typo", "unknown model: sonnet-99", Unknown},
-		{"tool timeout local", "tool bash timed out after 600s", Unknown},
-	}
-	for _, tc := range cases {
-		t.Run(tc.name, func(t *testing.T) {
-			if got := Classify(errors.New(tc.msg)); got != tc.want {
-				t.Fatalf("Classify(%q) = %v, want %v", tc.msg, got, tc.want)
-			}
-		})
-	}
-}
-
-func TestClassifyNil(t *testing.T) {
-	if got := Classify(nil); got != Unknown {
-		t.Fatalf("Classify(nil) = %v, want Unknown", got)
-	}
-}
-
-// Context-overflow must win over the connectivity "timeout" catch-all: a message
-// mentioning both "context length" and a timeout is an overflow, not a network
-// problem.
-func TestContextOverflowBeatsConnectivity(t *testing.T) {
-	err := errors.New("provider request error: maximum context length exceeded; request timeout")
-	if got := Classify(err); got != ContextOverflow {
-		t.Fatalf("Classify = %v, want ContextOverflow", got)
-	}
-}
-
-func TestHintsPresentForKnownCategories(t *testing.T) {
-	known := []error{
-		errors.New("auth error: bad key"),
-		errors.New("rate limit error: 429"),
-		errors.New("provider stream error: dial tcp: no such host"),
-		errors.New("provider request error: model does not exist"),
-		errors.New("provider request error: maximum context length is 128000 tokens"),
-	}
-	for _, err := range known {
-		if h := TUIHint(err); strings.TrimSpace(h) == "" {
-			t.Fatalf("TUIHint(%q) empty, want a hint", err)
-		}
-		if h := CLIHint(err); strings.TrimSpace(h) == "" {
-			t.Fatalf("CLIHint(%q) empty, want a hint", err)
-		}
-	}
-	// Unknown yields no hint on either surface.
-	unknown := errors.New("provider error: mystery")
-	if h := TUIHint(unknown); h != "" {
-		t.Fatalf("TUIHint(unknown) = %q, want empty", h)
-	}
-	if h := CLIHint(unknown); h != "" {
-		t.Fatalf("CLIHint(unknown) = %q, want empty", h)
-	}
-}

internal/lsp/registry.go

@@ -9,134 +9,26 @@ import (
 
 // serverCommands maps a file extension to the language-server command (argv) ZERO
 // will spawn. The first element is the binary looked up on PATH; missing binaries
-// are not an error, the agent just degrades to text-only for that file. Every
-// command is the language's community-standard server invoked in stdio mode, so
-// a wrong guess can never spawn something surprising — only fail the PATH check.
+// are not an error, the agent just degrades to text-only for that file.
 var serverCommands = map[string][]string{
-	".go":     {"gopls", "serve"},
-	".ts":     {"typescript-language-server", "--stdio"},
-	".tsx":    {"typescript-language-server", "--stdio"},
-	".mts":    {"typescript-language-server", "--stdio"},
-	".cts":    {"typescript-language-server", "--stdio"},
-	".js":     {"typescript-language-server", "--stdio"},
-	".jsx":    {"typescript-language-server", "--stdio"},
-	".mjs":    {"typescript-language-server", "--stdio"},
-	".cjs":    {"typescript-language-server", "--stdio"},
-	".py":     {"pyright-langserver", "--stdio"},
-	".pyi":    {"pyright-langserver", "--stdio"},
-	".rs":     {"rust-analyzer"},
-	".c":      {"clangd"},
-	".h":      {"clangd"},
-	".cpp":    {"clangd"},
-	".cc":     {"clangd"},
-	".cxx":    {"clangd"},
-	".hpp":    {"clangd"},
-	".java":   {"jdtls"},
-	".kt":     {"kotlin-language-server"},
-	".kts":    {"kotlin-language-server"},
-	".rb":     {"ruby-lsp"},
-	".php":    {"intelephense", "--stdio"},
-	".zig":    {"zls"},
-	".lua":    {"lua-language-server"},
-	".ex":     {"elixir-ls"},
-	".exs":    {"elixir-ls"},
-	".hs":     {"haskell-language-server-wrapper", "--lsp"},
-	".swift":  {"sourcekit-lsp"},
-	".ml":     {"ocamllsp"},
-	".mli":    {"ocamllsp"},
-	".scala":  {"metals"},
-	".clj":    {"clojure-lsp"},
-	".cljs":   {"clojure-lsp"},
-	".cljc":   {"clojure-lsp"},
-	".dart":   {"dart", "language-server"},
-	".gleam":  {"gleam", "lsp"},
-	".nix":    {"nixd"},
-	".tf":     {"terraform-ls", "serve"},
-	".sh":     {"bash-language-server", "start"},
-	".bash":   {"bash-language-server", "start"},
-	".yaml":   {"yaml-language-server", "--stdio"},
-	".yml":    {"yaml-language-server", "--stdio"},
-	".json":   {"vscode-json-language-server", "--stdio"},
-	".css":    {"vscode-css-language-server", "--stdio"},
-	".scss":   {"vscode-css-language-server", "--stdio"},
-	".less":   {"vscode-css-language-server", "--stdio"},
-	".html":   {"vscode-html-language-server", "--stdio"},
-	".svelte": {"svelteserver", "--stdio"},
-	".vue":    {"vue-language-server", "--stdio"},
-	".astro":  {"astro-ls", "--stdio"},
+	".go":  {"gopls", "serve"},
+	".ts":  {"typescript-language-server", "--stdio"},
+	".tsx": {"typescript-language-server", "--stdio"},
+	".js":  {"typescript-language-server", "--stdio"},
+	".jsx": {"typescript-language-server", "--stdio"},
+	".py":  {"pyright-langserver", "--stdio"},
+	".rs":  {"rust-analyzer"},
 }
 
 // languageIDs maps a file extension to the LSP languageId used in didOpen.
 var languageIDs = map[string]string{
-	".go":     "go",
-	".ts":     "typescript",
-	".tsx":    "typescriptreact",
-	".mts":    "typescript",
-	".cts":    "typescript",
-	".js":     "javascript",
-	".jsx":    "javascriptreact",
-	".mjs":    "javascript",
-	".cjs":    "javascript",
-	".py":     "python",
-	".pyi":    "python",
-	".rs":     "rust",
-	".c":      "c",
-	".h":      "c",
-	".cpp":    "cpp",
-	".cc":     "cpp",
-	".cxx":    "cpp",
-	".hpp":    "cpp",
-	".java":   "java",
-	".kt":     "kotlin",
-	".kts":    "kotlin",
-	".rb":     "ruby",
-	".php":    "php",
-	".zig":    "zig",
-	".lua":    "lua",
-	".ex":     "elixir",
-	".exs":    "elixir",
-	".hs":     "haskell",
-	".swift":  "swift",
-	".ml":     "ocaml",
-	".mli":    "ocaml",
-	".scala":  "scala",
-	".clj":    "clojure",
-	".cljs":   "clojure",
-	".cljc":   "clojure",
-	".dart":   "dart",
-	".gleam":  "gleam",
-	".nix":    "nix",
-	".tf":     "terraform",
-	".sh":     "shellscript",
-	".bash":   "shellscript",
-	".yaml":   "yaml",
-	".yml":    "yaml",
-	".json":   "json",
-	".css":    "css",
-	".scss":   "scss",
-	".less":   "less",
-	".html":   "html",
-	".svelte": "svelte",
-	".vue":    "vue",
-	".astro":  "astro",
-}
-
-// coreServerBinaries are the tier-1 servers for the languages agents hit most;
-// `zero doctor` treats their absence as warn-worthy. The long tail of servers
-// configured above for breadth is reported informationally only — warning about
-// a missing zls on a machine with no Zig code would be permanent noise.
-var coreServerBinaries = []string{
-	"gopls",
-	"typescript-language-server",
-	"pyright-langserver",
-	"rust-analyzer",
-}
-
-// CoreServerBinaries returns the tier-1 server binaries (sorted copy).
-func CoreServerBinaries() []string {
-	binaries := append([]string(nil), coreServerBinaries...)
-	sort.Strings(binaries)
-	return binaries
+	".go":  "go",
+	".ts":  "typescript",
+	".tsx": "typescriptreact",
+	".js":  "javascript",
+	".jsx": "javascriptreact",
+	".py":  "python",
+	".rs":  "rust",
 }
 
 // ServerBinaries returns the unique set of language-server binaries ZERO may

internal/modelregistry/catalog.go

@@ -63,10 +63,6 @@ func DefaultModelEntries() []ModelEntry {
 		googleModel("gemini-2.5-flash-lite", "Gemini 2.5 Flash-Lite", "gemini-2.5-flash-lite", ModelStatusActive, []string{"google:gemini-2.5-flash-lite", "gemini-flash-lite"}, ContextLimits{ContextWindow: 1_048_576, MaxOutputTokens: 65_536}, ModelCost{InputPerMillion: 0.1, CachedInputPerMillion: 0.01, OutputPerMillion: 0.4}, []ModelCapability{ModelCapabilityVision, ModelCapabilityJSONMode, ModelCapabilityReasoning, ModelCapabilityLongContext}, standardReasoningEfforts(), "Google low-cost Flash model for background routing and summaries."),
 	}
 	decorateModelDepth(entries)
-	// Overlay volatile facts (context limits, base pricing) from a cached
-	// models.dev snapshot when one is present and fresh — see modelsdev.go.
-	// Identity fields (ids, aliases, patterns, deprecations) stay curated.
-	entries = applyModelsDevOverrides(entries, cachedModelsDevProviders())
 	return cloneModelEntries(entries)
 }
 

internal/modelregistry/modelsdev.go

@@ -1,269 +0,0 @@
-package modelregistry
-
-import (
-	"context"
-	"encoding/json"
-	"fmt"
-	"io"
-	"net/http"
-	"os"
-	"path/filepath"
-	"strings"
-	"sync"
-	"sync/atomic"
-	"time"
-)
-
-// Live models.dev overlay for the curated catalog. The hand-maintained
-// DefaultModelEntries list is the source of truth for identity — ids, aliases,
-// match patterns, deprecations, escalation targets — but its VOLATILE facts
-// (context window, max output tokens, per-million pricing) go stale between
-// releases. When a cached snapshot of https://models.dev/api.json is present,
-// those fields are refreshed from it at registry construction; everything else
-// stays curated. The overlay never adds models (an auto-added entry would lack
-// aliases, match patterns, and provider wiring) and never touches the network
-// on the registry hot path — fetching happens only in the explicit background
-// refresh, cached to disk with a TTL.
-
-const (
-	modelsDevDefaultURL = "https://models.dev/api.json"
-	// modelsDevRefreshAfter is how old the cache may get before a background
-	// refresh re-fetches it.
-	modelsDevRefreshAfter = 24 * time.Hour
-	// modelsDevMaxAge is the oldest cache still applied as an overlay. Beyond
-	// this the curated catalog (updated with the binary) is likely fresher than
-	// the snapshot, so a stale file is ignored rather than trusted.
-	modelsDevMaxAge      = 7 * 24 * time.Hour
-	modelsDevFetchLimit  = 32 << 20 // 32MiB guard on the response body
-	modelsDevFetchWindow = 15 * time.Second
-)
-
-// modelsDevModel is the subset of a models.dev model record the overlay uses.
-type modelsDevModel struct {
-	Limit struct {
-		Context int `json:"context"`
-		Output  int `json:"output"`
-	} `json:"limit"`
-	Cost struct {
-		Input      float64 `json:"input"`
-		Output     float64 `json:"output"`
-		CacheRead  float64 `json:"cache_read"`
-		CacheWrite float64 `json:"cache_write"`
-	} `json:"cost"`
-}
-
-// modelsDevProvider matches one provider object in api.json.
-type modelsDevProvider struct {
-	Models map[string]modelsDevModel `json:"models"`
-}
-
-// parseModelsDev decodes an api.json document into provider-slug -> api-model
-// -> record. api.json is a top-level object keyed by provider id.
-func parseModelsDev(data []byte) (map[string]map[string]modelsDevModel, error) {
-	var doc map[string]modelsDevProvider
-	if err := json.Unmarshal(data, &doc); err != nil {
-		return nil, fmt.Errorf("modelregistry: parse models.dev: %w", err)
-	}
-	providers := make(map[string]map[string]modelsDevModel, len(doc))
-	for slug, provider := range doc {
-		if len(provider.Models) == 0 {
-			continue
-		}
-		providers[slug] = provider.Models
-	}
-	if len(providers) == 0 {
-		return nil, fmt.Errorf("modelregistry: models.dev document has no providers")
-	}
-	return providers, nil
-}
-
-// modelsDevSlugs maps an entry's provider kind to the models.dev provider ids
-// worth checking. Only first-party slugs are used: router entries on models.dev
-// carry generic or stale numbers.
-func modelsDevSlugs(kind ProviderKind) []string {
-	switch kind {
-	case ProviderAnthropic:
-		return []string{"anthropic"}
-	case ProviderOpenAI:
-		return []string{"openai"}
-	case ProviderGoogle:
-		return []string{"google", "google-vertex"}
-	default:
-		return nil
-	}
-}
-
-// applyModelsDevOverrides refreshes each curated entry's context limits and
-// base pricing from the snapshot, when the snapshot knows the model. Tiered
-// pricing is never touched: models.dev has no tier data, and mixing a live
-// base rate with curated tiers would misprice the tier boundaries.
-func applyModelsDevOverrides(entries []ModelEntry, providers map[string]map[string]modelsDevModel) []ModelEntry {
-	if len(providers) == 0 {
-		return entries
-	}
-	for i := range entries {
-		entry := &entries[i]
-		var record modelsDevModel
-		found := false
-		for _, slug := range modelsDevSlugs(entry.Provider) {
-			if models, ok := providers[slug]; ok {
-				if candidate, ok := models[strings.TrimSpace(entry.APIModel)]; ok {
-					record = candidate
-					found = true
-					break
-				}
-			}
-		}
-		if !found {
-			continue
-		}
-		if record.Limit.Context > 0 {
-			entry.ContextLimits.ContextWindow = record.Limit.Context
-		}
-		if record.Limit.Output > 0 {
-			entry.ContextLimits.MaxOutputTokens = record.Limit.Output
-		}
-		if len(entry.Cost.Tiers) == 0 && record.Cost.Input > 0 && record.Cost.Output > 0 {
-			entry.Cost.InputPerMillion = record.Cost.Input
-			entry.Cost.OutputPerMillion = record.Cost.Output
-			if record.Cost.CacheRead > 0 {
-				entry.Cost.CachedInputPerMillion = record.Cost.CacheRead
-			}
-			if record.Cost.CacheWrite > 0 {
-				entry.Cost.CacheWritePerMillion = record.Cost.CacheWrite
-			}
-			entry.Cost.Source = "models.dev/api.json (cached)"
-		}
-	}
-	return entries
-}
-
-// modelsDevCachePath returns the on-disk cache location. ZERO_MODELS_CACHE_PATH
-// overrides it (used by tests and unusual setups).
-func modelsDevCachePath() (string, error) {
-	if override := strings.TrimSpace(os.Getenv("ZERO_MODELS_CACHE_PATH")); override != "" {
-		return override, nil
-	}
-	base, err := os.UserCacheDir()
-	if err != nil {
-		return "", err
-	}
-	return filepath.Join(base, "zero", "modelsdev.json"), nil
-}
-
-var (
-	modelsDevOnce    sync.Once
-	modelsDevCached  map[string]map[string]modelsDevModel
-	modelsDevEnabled atomic.Bool
-)
-
-// EnableModelsDevOverlay opts the process into applying the cached models.dev
-// snapshot on top of the curated catalog. The CLI entrypoint calls it; library
-// consumers and tests that never do get the curated catalog byte-identical to
-// before, so hermetic tests can't be perturbed by a cache file on the machine.
-// ZERO_DISABLE_MODELS_FETCH disables both the overlay and the fetch.
-func EnableModelsDevOverlay() {
-	modelsDevEnabled.Store(true)
-}
-
-// cachedModelsDevProviders loads the cached snapshot once per process. Not
-// enabled, missing, stale (> modelsDevMaxAge), or malformed all yield nil and
-// the curated catalog is used untouched. Read once deliberately:
-// DefaultRegistry is called on hot paths (pickers, cost views) and must not
-// re-stat the file every time; a background refresh benefits the NEXT process.
-func cachedModelsDevProviders() map[string]map[string]modelsDevModel {
-	if !modelsDevEnabled.Load() || strings.TrimSpace(os.Getenv("ZERO_DISABLE_MODELS_FETCH")) != "" {
-		return nil
-	}
-	modelsDevOnce.Do(func() {
-		path, err := modelsDevCachePath()
-		if err != nil {
-			return
-		}
-		info, err := os.Stat(path)
-		if err != nil || time.Since(info.ModTime()) > modelsDevMaxAge {
-			return
-		}
-		data, err := os.ReadFile(path)
-		if err != nil {
-			return
-		}
-		providers, err := parseModelsDev(data)
-		if err != nil {
-			return
-		}
-		modelsDevCached = providers
-	})
-	return modelsDevCached
-}
-
-// resetModelsDevCacheForTest clears the process-level cache memoization and
-// disables the overlay.
-func resetModelsDevCacheForTest() {
-	modelsDevOnce = sync.Once{}
-	modelsDevCached = nil
-	modelsDevEnabled.Store(false)
-}
-
-// RefreshModelsDevCache fetches models.dev/api.json into the on-disk cache
-// when the cache is missing or older than modelsDevRefreshAfter. It is safe to
-// call fire-and-forget from startup (use a goroutine); it never affects the
-// current process's registry (see cachedModelsDevProviders). Disabled entirely
-// by ZERO_DISABLE_MODELS_FETCH. The URL can be overridden with ZERO_MODELS_URL.
-func RefreshModelsDevCache(ctx context.Context) error {
-	if strings.TrimSpace(os.Getenv("ZERO_DISABLE_MODELS_FETCH")) != "" {
-		return nil
-	}
-	path, err := modelsDevCachePath()
-	if err != nil {
-		return err
-	}
-	if info, err := os.Stat(path); err == nil && time.Since(info.ModTime()) < modelsDevRefreshAfter {
-		return nil
-	}
-
-	url := strings.TrimSpace(os.Getenv("ZERO_MODELS_URL"))
-	if url == "" {
-		url = modelsDevDefaultURL
-	}
-	fetchCtx, cancel := context.WithTimeout(ctx, modelsDevFetchWindow)
-	defer cancel()
-	request, err := http.NewRequestWithContext(fetchCtx, http.MethodGet, url, nil)
-	if err != nil {
-		return err
-	}
-	request.Header.Set("User-Agent", "zero-models-refresh/0.1")
-	response, err := http.DefaultClient.Do(request)
-	if err != nil {
-		return err
-	}
-	defer response.Body.Close()
-	if response.StatusCode != http.StatusOK {
-		return fmt.Errorf("modelregistry: models.dev fetch: HTTP %d", response.StatusCode)
-	}
-	data, err := io.ReadAll(io.LimitReader(response.Body, modelsDevFetchLimit))
-	if err != nil {
-		return err
-	}
-	// Validate before persisting: a bad body must never clobber a good cache.
-	if _, err := parseModelsDev(data); err != nil {
-		return err
-	}
-	if err := os.MkdirAll(filepath.Dir(path), 0o755); err != nil {
-		return err
-	}
-	temp, err := os.CreateTemp(filepath.Dir(path), "modelsdev-*.json")
-	if err != nil {
-		return err
-	}
-	if _, err := temp.Write(data); err != nil {
-		_ = temp.Close()
-		_ = os.Remove(temp.Name())
-		return err
-	}
-	if err := temp.Close(); err != nil {
-		_ = os.Remove(temp.Name())
-		return err
-	}
-	return os.Rename(temp.Name(), path)
-}

internal/modelregistry/modelsdev_test.go

@@ -1,228 +0,0 @@
-package modelregistry
-
-import (
-	"net/http"
-	"net/http/httptest"
-	"os"
-	"path/filepath"
-	"testing"
-	"time"
-)
-
-const sampleModelsDev = `{
-  "anthropic": {
-    "id": "anthropic",
-    "models": {
-      "claude-sonnet-4-5-20250929": {
-        "limit": {"context": 1000000, "output": 64000},
-        "cost": {"input": 3.5, "output": 17.5, "cache_read": 0.35, "cache_write": 4.4}
-      }
-    }
-  },
-  "google": {
-    "id": "google",
-    "models": {
-      "gemini-2.5-pro": {
-        "limit": {"context": 2097152, "output": 65536},
-        "cost": {"input": 9.99, "output": 9.99}
-      }
-    }
-  }
-}`
-
-func TestParseModelsDev(t *testing.T) {
-	providers, err := parseModelsDev([]byte(sampleModelsDev))
-	if err != nil {
-		t.Fatal(err)
-	}
-	record, ok := providers["anthropic"]["claude-sonnet-4-5-20250929"]
-	if !ok {
-		t.Fatal("expected anthropic sonnet record")
-	}
-	if record.Limit.Context != 1_000_000 || record.Cost.Input != 3.5 {
-		t.Fatalf("unexpected record: %+v", record)
-	}
-	if _, err := parseModelsDev([]byte(`{}`)); err == nil {
-		t.Fatal("empty document must be rejected")
-	}
-	if _, err := parseModelsDev([]byte(`not json`)); err == nil {
-		t.Fatal("malformed document must be rejected")
-	}
-}
-
-func TestApplyModelsDevOverrides(t *testing.T) {
-	// Point the cache at a non-existent file so DefaultModelEntries returns the
-	// pure curated catalog, then apply the sample snapshot explicitly.
-	t.Setenv("ZERO_MODELS_CACHE_PATH", filepath.Join(t.TempDir(), "absent.json"))
-	resetModelsDevCacheForTest()
-	t.Cleanup(resetModelsDevCacheForTest)
-
-	providers, err := parseModelsDev([]byte(sampleModelsDev))
-	if err != nil {
-		t.Fatal(err)
-	}
-	entries := applyModelsDevOverrides(DefaultModelEntries(), providers)
-
-	var sonnet, geminiPro, opus ModelEntry
-	for _, entry := range entries {
-		switch entry.ID {
-		case "claude-sonnet-4.5":
-			sonnet = entry
-		case "gemini-2.5-pro":
-			geminiPro = entry
-		case "claude-opus-4.1":
-			opus = entry
-		}
-	}
-
-	// Known model: limits and base pricing refreshed from the snapshot.
-	if sonnet.ContextLimits.ContextWindow != 1_000_000 || sonnet.ContextLimits.MaxOutputTokens != 64_000 {
-		t.Fatalf("sonnet limits not overridden: %+v", sonnet.ContextLimits)
-	}
-	if sonnet.Cost.InputPerMillion != 3.5 || sonnet.Cost.OutputPerMillion != 17.5 || sonnet.Cost.CacheWritePerMillion != 4.4 {
-		t.Fatalf("sonnet cost not overridden: %+v", sonnet.Cost)
-	}
-	if sonnet.Cost.Source != "models.dev/api.json (cached)" {
-		t.Fatalf("sonnet cost source not marked: %q", sonnet.Cost.Source)
-	}
-
-	// Tiered pricing is curated: limits refresh, cost must NOT (gemini-2.5-pro
-	// has curated tiers and the snapshot's flat 9.99 would misprice them).
-	if geminiPro.ContextLimits.ContextWindow != 2_097_152 {
-		t.Fatalf("gemini limits not overridden: %+v", geminiPro.ContextLimits)
-	}
-	if geminiPro.Cost.InputPerMillion == 9.99 || len(geminiPro.Cost.Tiers) == 0 {
-		t.Fatalf("tiered cost must stay curated: %+v", geminiPro.Cost)
-	}
-
-	// Model absent from the snapshot: untouched.
-	if opus.ContextLimits.ContextWindow != 200_000 || opus.Cost.InputPerMillion != 15 {
-		t.Fatalf("opus must be untouched: %+v %+v", opus.ContextLimits, opus.Cost)
-	}
-}
-
-func TestRefreshModelsDevCacheFetchesAndCaches(t *testing.T) {
-	hits := 0
-	server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
-		hits++
-		_, _ = w.Write([]byte(sampleModelsDev))
-	}))
-	defer server.Close()
-
-	cachePath := filepath.Join(t.TempDir(), "modelsdev.json")
-	t.Setenv("ZERO_MODELS_CACHE_PATH", cachePath)
-	t.Setenv("ZERO_MODELS_URL", server.URL)
-	t.Setenv("ZERO_DISABLE_MODELS_FETCH", "")
-
-	if err := RefreshModelsDevCache(t.Context()); err != nil {
-		t.Fatal(err)
-	}
-	if hits != 1 {
-		t.Fatalf("expected 1 fetch, got %d", hits)
-	}
-	if _, err := os.Stat(cachePath); err != nil {
-		t.Fatalf("cache file missing: %v", err)
-	}
-	// Fresh cache: second call must not re-fetch.
-	if err := RefreshModelsDevCache(t.Context()); err != nil {
-		t.Fatal(err)
-	}
-	if hits != 1 {
-		t.Fatalf("fresh cache must skip the fetch, got %d hits", hits)
-	}
-}
-
-func TestRefreshModelsDevCacheRejectsBadBodyWithoutClobbering(t *testing.T) {
-	server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
-		_, _ = w.Write([]byte("not json"))
-	}))
-	defer server.Close()
-
-	cachePath := filepath.Join(t.TempDir(), "modelsdev.json")
-	if err := os.WriteFile(cachePath, []byte(sampleModelsDev), 0o644); err != nil {
-		t.Fatal(err)
-	}
-	stale := time.Now().Add(-48 * time.Hour)
-	if err := os.Chtimes(cachePath, stale, stale); err != nil {
-		t.Fatal(err)
-	}
-	t.Setenv("ZERO_MODELS_CACHE_PATH", cachePath)
-	t.Setenv("ZERO_MODELS_URL", server.URL)
-
-	if err := RefreshModelsDevCache(t.Context()); err == nil {
-		t.Fatal("bad body must return an error")
-	}
-	content, err := os.ReadFile(cachePath)
-	if err != nil || string(content) != sampleModelsDev {
-		t.Fatal("bad fetch must not clobber the existing cache")
-	}
-}
-
-func TestRefreshModelsDevCacheDisabledByEnv(t *testing.T) {
-	server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
-		t.Fatal("fetch must not happen when disabled")
-	}))
-	defer server.Close()
-	t.Setenv("ZERO_MODELS_CACHE_PATH", filepath.Join(t.TempDir(), "modelsdev.json"))
-	t.Setenv("ZERO_MODELS_URL", server.URL)
-	t.Setenv("ZERO_DISABLE_MODELS_FETCH", "1")
-	if err := RefreshModelsDevCache(t.Context()); err != nil {
-		t.Fatal(err)
-	}
-}
-
-func TestCachedModelsDevProvidersIgnoresStaleCache(t *testing.T) {
-	cachePath := filepath.Join(t.TempDir(), "modelsdev.json")
-	if err := os.WriteFile(cachePath, []byte(sampleModelsDev), 0o644); err != nil {
-		t.Fatal(err)
-	}
-	stale := time.Now().Add(-modelsDevMaxAge - time.Hour)
-	if err := os.Chtimes(cachePath, stale, stale); err != nil {
-		t.Fatal(err)
-	}
-	t.Setenv("ZERO_MODELS_CACHE_PATH", cachePath)
-	resetModelsDevCacheForTest()
-	t.Cleanup(resetModelsDevCacheForTest)
-	EnableModelsDevOverlay()
-
-	if providers := cachedModelsDevProviders(); providers != nil {
-		t.Fatal("stale cache must be ignored")
-	}
-}
-
-func TestCachedModelsDevProvidersRequiresOptIn(t *testing.T) {
-	cachePath := filepath.Join(t.TempDir(), "modelsdev.json")
-	if err := os.WriteFile(cachePath, []byte(sampleModelsDev), 0o644); err != nil {
-		t.Fatal(err)
-	}
-	t.Setenv("ZERO_MODELS_CACHE_PATH", cachePath)
-	resetModelsDevCacheForTest()
-	t.Cleanup(resetModelsDevCacheForTest)
-
-	// Without EnableModelsDevOverlay a fresh, valid cache must still be ignored:
-	// library consumers and hermetic tests get the pure curated catalog.
-	if providers := cachedModelsDevProviders(); providers != nil {
-		t.Fatal("overlay must be opt-in")
-	}
-}
-
-func TestDefaultModelEntriesAppliesFreshCache(t *testing.T) {
-	cachePath := filepath.Join(t.TempDir(), "modelsdev.json")
-	if err := os.WriteFile(cachePath, []byte(sampleModelsDev), 0o644); err != nil {
-		t.Fatal(err)
-	}
-	t.Setenv("ZERO_MODELS_CACHE_PATH", cachePath)
-	resetModelsDevCacheForTest()
-	t.Cleanup(resetModelsDevCacheForTest)
-	EnableModelsDevOverlay()
-
-	for _, entry := range DefaultModelEntries() {
-		if entry.ID == "claude-sonnet-4.5" {
-			if entry.ContextLimits.ContextWindow != 1_000_000 {
-				t.Fatalf("fresh cache must overlay the registry: %+v", entry.ContextLimits)
-			}
-			return
-		}
-	}
-	t.Fatal("claude-sonnet-4.5 not found")
-}

internal/oauth/encrypt.go

@@ -114,12 +114,7 @@ func createSecretFile(path string) ([]byte, error) {
 			}
 			return writeNewSecretFile(path)
 		}
-		// On Windows a concurrent holder's os.Remove leaves the lock file in a
-		// "delete pending" state, so an O_EXCL create races it with
-		// ERROR_ACCESS_DENIED (os.ErrPermission) rather than ErrExist. Treat that
-		// as contention and retry too — mirroring acquireFileLock in lock.go —
-		// otherwise concurrent secret creation spuriously fails on Windows.
-		if !errors.Is(err, os.ErrExist) && !errors.Is(err, os.ErrPermission) {
+		if !errors.Is(err, os.ErrExist) {
 			return nil, fmt.Errorf("oauth: create token secret lock: %w", err)
 		}
 		if data, rerr := readSecretFileRetry(path); rerr == nil {

internal/providerhealth/connectivity_client_test.go

@@ -169,8 +169,8 @@ func TestValidateEndpointAllowsLoopbackOnlyForLocalProvider(t *testing.T) {
 		if err := validateEndpoint(ctx, ep, r, true); err != nil {
 			t.Errorf("local provider endpoint %q should be allowed with allowLoopback=true, got %v", ep, err)
 		}
-		if !endpointIsLoopbackOrPrivate(ep) {
-			t.Errorf("endpointIsLoopbackOrPrivate(%q) = false, want true", ep)
+		if !endpointIsLoopback(ep) {
+			t.Errorf("endpointIsLoopback(%q) = false, want true", ep)
 		}
 	}
 
@@ -179,27 +179,14 @@ func TestValidateEndpointAllowsLoopbackOnlyForLocalProvider(t *testing.T) {
 		t.Error("loopback must remain blocked when allowLoopback=false (redirects / non-local)")
 	}
 
-	// allowLoopbackOrPrivate relaxes loopback AND private-network ranges — but
-	// link-local and other special ranges (cloud metadata, documentation) stay
-	// blocked even for a local provider config.
-	for _, ep := range []string{"http://169.254.169.254/latest/meta-data", "http://192.0.2.1:8080/v1"} {
+	// allowLoopback relaxes loopback ONLY — other special ranges (cloud metadata,
+	// link-local, private) stay blocked even for a local provider config.
+	for _, ep := range []string{"http://169.254.169.254/latest/meta-data", "http://10.0.0.5:8080/v1"} {
 		if err := validateEndpoint(ctx, ep, staticResolver{addr: netip.MustParseAddr("169.254.169.254")}, true); err == nil {
-			t.Errorf("special-use address %q must stay blocked even with flag=true", ep)
+			t.Errorf("non-loopback special address %q must stay blocked even with allowLoopback=true", ep)
 		}
-		if endpointIsLoopbackOrPrivate(ep) {
-			t.Errorf("endpointIsLoopbackOrPrivate(%q) = true, want false", ep)
-		}
-	}
-
-	// Private-network addresses (192.168.x.y / 10.x.y.z / 172.16.x.y) are
-	// now allowed when the flag is true — the user is pointing at their own
-	// LAN box (e.g. llama.cpp on another local machine).
-	for _, ep := range []string{"http://192.168.1.100:8080/v1", "http://10.0.0.5:8080/v1", "http://172.16.0.10:8080/v1"} {
-		if err := validateEndpoint(ctx, ep, staticResolver{addr: netip.MustParseAddr("192.168.1.100")}, true); err != nil {
-			t.Errorf("private-network address %q should be allowed with flag=true, got %v", ep, err)
-		}
-		if !endpointIsLoopbackOrPrivate(ep) {
-			t.Errorf("endpointIsLoopbackOrPrivate(%q) = false, want true", ep)
+		if endpointIsLoopback(ep) {
+			t.Errorf("endpointIsLoopback(%q) = true, want false", ep)
 		}
 	}
 }

internal/providerhealth/providerhealth.go

@@ -269,7 +269,7 @@ func connectivityCheck(ctx context.Context, profile config.ProviderProfile, kind
 	requestCtx, cancel := context.WithTimeout(ctx, timeout)
 	defer cancel()
 
-	request, allowLoopbackOrPrivate, err := healthRequest(requestCtx, profile, kind, options)
+	request, allowLoopback, err := healthRequest(requestCtx, profile, kind, options)
 	if err != nil {
 		category := CategoryConfig
 		var safety endpointSafetyError
@@ -280,7 +280,7 @@ func connectivityCheck(ctx context.Context, profile config.ProviderProfile, kind
 	}
 	client := options.HTTPClient
 	if client == nil {
-		client = newConnectivityClient(timeout, options.Resolver, sensitiveAuthHeaderNames(profile, kind), allowLoopbackOrPrivate)
+		client = newConnectivityClient(timeout, options.Resolver, sensitiveAuthHeaderNames(profile, kind), allowLoopback)
 	}
 	response, err := client.Do(request)
 	if err != nil {
@@ -332,8 +332,8 @@ func healthRequest(ctx context.Context, profile config.ProviderProfile, kind con
 	// Loopback is permitted only when the user's OWN configured base_url is loopback
 	// (a local provider like Ollama/LM Studio) — never for a redirect target. This is
 	// the flag returned to the caller so the dial path applies the same policy. (AUDIT-H1)
-	allowLoopbackOrPrivate := endpointIsLoopbackOrPrivate(endpoint)
-	if err := validateEndpoint(ctx, endpoint, options.Resolver, allowLoopbackOrPrivate); err != nil {
+	allowLoopback := endpointIsLoopback(endpoint)
+	if err := validateEndpoint(ctx, endpoint, options.Resolver, allowLoopback); err != nil {
 		return nil, false, err
 	}
 	request, err := http.NewRequestWithContext(ctx, http.MethodGet, endpoint, nil)
@@ -344,7 +344,7 @@ func healthRequest(ctx context.Context, profile config.ProviderProfile, kind con
 		request.Header.Set("User-Agent", options.UserAgent)
 	}
 	applyAuth(request, profile, kind)
-	return request, allowLoopbackOrPrivate, nil
+	return request, allowLoopback, nil
 }
 
 func resolvedBaseURL(profile config.ProviderProfile, kind config.ProviderKind) (string, error) {
@@ -367,11 +367,11 @@ func resolvedBaseURL(profile config.ProviderProfile, kind config.ProviderKind) (
 }
 
 // validateEndpoint enforces the SSRF policy for the provider connectivity probe.
-// allowLoopbackOrPrivate permits loopback hosts (localhost / 127.0.0.0/8 / ::1)
-// and private-network hosts (192.168.0.0/16 / 10.0.0.0/8 / 172.16.0.0/12) — it
-// is set true exclusively for the user's own explicitly-configured base_url
-// (e.g. Ollama/LM Studio on the LAN), never for redirect targets.
-func validateEndpoint(ctx context.Context, endpoint string, resolver Resolver, allowLoopbackOrPrivate bool) error {
+// allowLoopback permits loopback hosts (localhost / 127.0.0.0/8 / ::1) ONLY — it is
+// set true exclusively for the user's own explicitly-configured local provider
+// base_url (e.g. Ollama/LM Studio), never for redirect targets, and it relaxes
+// loopback alone (other private/special ranges, incl. cloud metadata, stay blocked).
+func validateEndpoint(ctx context.Context, endpoint string, resolver Resolver, allowLoopback bool) error {
 	parsed, err := url.Parse(endpoint)
 	if err != nil {
 		return err
@@ -385,13 +385,13 @@ func validateEndpoint(ctx context.Context, endpoint string, resolver Resolver, a
 	}
 	normalized := strings.TrimSuffix(strings.ToLower(host), ".")
 	if normalized == "localhost" || strings.HasSuffix(normalized, ".localhost") {
-		if allowLoopbackOrPrivate {
+		if allowLoopback {
 			return nil // user-configured local provider; loopback is intentional
 		}
 		return endpointSafetyError{message: "provider connectivity URL is unsafe: localhost hosts are blocked"}
 	}
 	if addr, err := netip.ParseAddr(normalized); err == nil {
-		if reason := blockedAddrReason(addr); reason != "" && !(allowLoopbackOrPrivate && (addr.IsLoopback() || addr.IsPrivate())) {
+		if reason := blockedAddrReason(addr); reason != "" && !(allowLoopback && addr.IsLoopback()) {
 			return endpointSafetyError{message: "provider connectivity URL is unsafe: " + reason}
 		}
 		return nil
@@ -407,19 +407,17 @@ func validateEndpoint(ctx context.Context, endpoint string, resolver Resolver, a
 		return endpointSafetyError{message: "provider connectivity host resolved to no addresses"}
 	}
 	for _, addr := range addrs {
-		if reason := blockedAddrReason(addr); reason != "" && !(allowLoopbackOrPrivate && (addr.IsLoopback() || addr.IsPrivate())) {
+		if reason := blockedAddrReason(addr); reason != "" && !(allowLoopback && addr.IsLoopback()) {
 			return endpointSafetyError{message: "provider connectivity URL is unsafe: " + reason}
 		}
 	}
 	return nil
 }
 
-// endpointIsLoopbackOrPrivate reports whether the configured endpoint's host is a loopback
-// or private-network host the user typed themselves — a local provider on the LAN
-// (e.g. 192.168.x.y / 10.x.y.z) or localhost. Used to decide whether the
-// connectivity probe may relax address-blocking and reach the user's own
-// explicitly-configured provider.
-func endpointIsLoopbackOrPrivate(endpoint string) bool {
+// endpointIsLoopback reports whether the configured endpoint's host is a loopback
+// host the user typed themselves (localhost or a 127.0.0.0/8 / ::1 literal). Used to
+// decide whether the connectivity probe may reach the user's own local provider.
+func endpointIsLoopback(endpoint string) bool {
 	parsed, err := url.Parse(endpoint)
 	if err != nil {
 		return false
@@ -429,7 +427,7 @@ func endpointIsLoopbackOrPrivate(endpoint string) bool {
 		return true
 	}
 	if addr, err := netip.ParseAddr(host); err == nil {
-		return addr.IsLoopback() || addr.IsPrivate()
+		return addr.IsLoopback()
 	}
 	return false
 }
@@ -448,7 +446,7 @@ const maxConnectivityRedirects = 5
 //     time and then dials the validated IP literal, closing the TOCTOU window
 //     between the pre-flight validateEndpoint check and the actual connection
 //     (DNS rebinding).
-func newConnectivityClient(timeout time.Duration, resolver Resolver, sensitiveHeaders []string, allowLoopbackOrPrivate bool) *http.Client {
+func newConnectivityClient(timeout time.Duration, resolver Resolver, sensitiveHeaders []string, allowLoopback bool) *http.Client {
 	if resolver == nil {
 		resolver = defaultResolver{}
 	}
@@ -458,7 +456,7 @@ func newConnectivityClient(timeout time.Duration, resolver Resolver, sensitiveHe
 	} else {
 		transport = &http.Transport{}
 	}
-	transport.DialContext = safeDialContext(resolver, allowLoopbackOrPrivate)
+	transport.DialContext = safeDialContext(resolver, allowLoopback)
 	return &http.Client{
 		Timeout:   timeout,
 		Transport: transport,
@@ -478,8 +476,8 @@ func newConnectivityClient(timeout time.Duration, resolver Resolver, sensitiveHe
 				}
 			}
 			// Redirects are NEVER allowed to reach loopback, even for a local provider:
-			// allowLoopbackOrPrivate covers only the user's own configured base_url,
-			// not a 3xx target (which could be attacker-controlled SSRF). (AUDIT-H1)
+			// allowLoopback covers only the user's own configured base_url, not a 3xx
+			// target (which could be attacker-controlled SSRF). (AUDIT-H1)
 			return validateEndpoint(req.Context(), req.URL.String(), resolver, false)
 		},
 	}
@@ -521,7 +519,7 @@ func sensitiveAuthHeaderNames(profile config.ProviderProfile, kind config.Provid
 // safeDialContext returns a dial function that resolves the target host, refuses
 // the connection if any resolved address is blocked, then dials the validated IP
 // literal so the kernel cannot re-resolve to a different address after the check.
-func safeDialContext(resolver Resolver, allowLoopbackOrPrivate bool) func(context.Context, string, string) (net.Conn, error) {
+func safeDialContext(resolver Resolver, allowLoopback bool) func(context.Context, string, string) (net.Conn, error) {
 	dialer := &net.Dialer{Timeout: 10 * time.Second, KeepAlive: 30 * time.Second}
 	return func(ctx context.Context, network, address string) (net.Conn, error) {
 		host, port, err := net.SplitHostPort(address)
@@ -529,7 +527,7 @@ func safeDialContext(resolver Resolver, allowLoopbackOrPrivate bool) func(contex
 			return nil, err
 		}
 		if addr, parseErr := netip.ParseAddr(host); parseErr == nil {
-			if reason := blockedAddrReason(addr); reason != "" && !(allowLoopbackOrPrivate && (addr.IsLoopback() || addr.IsPrivate())) {
+			if reason := blockedAddrReason(addr); reason != "" && !(allowLoopback && addr.IsLoopback()) {
 				return nil, endpointSafetyError{message: "provider connectivity URL is unsafe: " + reason}
 			}
 			return dialer.DialContext(ctx, network, address)
@@ -542,7 +540,7 @@ func safeDialContext(resolver Resolver, allowLoopbackOrPrivate bool) func(contex
 			return nil, endpointSafetyError{message: "provider connectivity host resolved to no addresses"}
 		}
 		for _, addr := range addrs {
-			if reason := blockedAddrReason(addr); reason != "" && !(allowLoopbackOrPrivate && (addr.IsLoopback() || addr.IsPrivate())) {
+			if reason := blockedAddrReason(addr); reason != "" && !(allowLoopback && addr.IsLoopback()) {
 				return nil, endpointSafetyError{message: "provider connectivity URL is unsafe: " + reason}
 			}
 		}

internal/providers/anthropic/cache_breakpoints_test.go

@@ -1,96 +0,0 @@
-package anthropic
-
-import (
-	"context"
-	"encoding/json"
-	"net/http"
-	"net/http/httptest"
-	"testing"
-
-	"github.com/Gitlawb/zero/internal/zeroruntime"
-)
-
-// The final two messages must carry a cache_control breakpoint on their last
-// cacheable block so the conversation transcript — not just system prompt and
-// tools — is a prompt-cache hit on the next turn. Earlier messages must stay
-// unmarked (Anthropic caps breakpoints at 4 per request: system, tools, and
-// these two).
-func TestAnthropicRequestMarksLastTwoMessagesForCaching(t *testing.T) {
-	var gotBody map[string]any
-	server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
-		if err := json.NewDecoder(r.Body).Decode(&gotBody); err != nil {
-			t.Fatalf("decode request body: %v", err)
-		}
-		writeSSEEvent(w, "message_stop", `{"type":"message_stop"}`)
-	}))
-	defer server.Close()
-
-	provider, err := New(Options{BaseURL: server.URL + "/", Model: "claude-test"})
-	if err != nil {
-		t.Fatalf("New returned error: %v", err)
-	}
-	stream, err := provider.StreamCompletion(context.Background(), zeroruntime.CompletionRequest{
-		Messages: []zeroruntime.Message{
-			{Role: zeroruntime.MessageRoleUser, Content: "first"},
-			{
-				Role:      zeroruntime.MessageRoleAssistant,
-				Content:   "calling a tool",
-				ToolCalls: []zeroruntime.ToolCall{{ID: "toolu_1", Name: "grep", Arguments: `{}`}},
-			},
-			{Role: zeroruntime.MessageRoleTool, Content: "result", ToolCallID: "toolu_1"},
-		},
-	})
-	if err != nil {
-		t.Fatalf("StreamCompletion returned error: %v", err)
-	}
-	drain(stream)
-
-	messages := gotBody["messages"].([]any)
-	if len(messages) != 3 {
-		t.Fatalf("expected 3 wire messages, got %d: %#v", len(messages), messages)
-	}
-	lastBlockHasCache := func(message any) bool {
-		blocks, ok := message.(map[string]any)["content"].([]any)
-		if !ok || len(blocks) == 0 {
-			return false
-		}
-		last := blocks[len(blocks)-1].(map[string]any)
-		control, ok := last["cache_control"].(map[string]any)
-		return ok && control["type"] == "ephemeral"
-	}
-	if lastBlockHasCache(messages[0]) {
-		t.Fatalf("first message must not carry a breakpoint: %#v", messages[0])
-	}
-	if !lastBlockHasCache(messages[1]) {
-		t.Fatalf("second-to-last message must carry a breakpoint: %#v", messages[1])
-	}
-	if !lastBlockHasCache(messages[2]) {
-		t.Fatalf("last message must carry a breakpoint: %#v", messages[2])
-	}
-}
-
-// A string-content message must be converted to a block array so it can carry
-// the breakpoint, and thinking blocks must never carry cache_control (the API
-// rejects them) — the marker goes on the last cacheable block instead.
-func TestApplyMessageCacheBreakpointsSkipsThinkingBlocks(t *testing.T) {
-	messages := []anthropicMessage{
-		{Role: "user", Content: "plain string"},
-		{Role: "assistant", Content: []map[string]any{
-			{"type": "text", "text": "answer"},
-			{"type": "thinking", "thinking": "hmm", "signature": "sig"},
-		}},
-	}
-	applyMessageCacheBreakpoints(messages)
-
-	userBlocks := contentBlocks(messages[0].Content)
-	if len(userBlocks) != 1 || userBlocks[0]["cache_control"] == nil {
-		t.Fatalf("string content must become a marked block: %#v", messages[0].Content)
-	}
-	assistantBlocks := contentBlocks(messages[1].Content)
-	if assistantBlocks[1]["cache_control"] != nil {
-		t.Fatalf("thinking block must not be marked: %#v", assistantBlocks[1])
-	}
-	if assistantBlocks[0]["cache_control"] == nil {
-		t.Fatalf("text block must carry the breakpoint instead: %#v", assistantBlocks[0])
-	}
-}

internal/providers/anthropic/provider.go

@@ -405,35 +405,9 @@ func (provider *Provider) anthropicRequest(request zeroruntime.CompletionRequest
 		}
 		mapped.Tools[len(mapped.Tools)-1].CacheControl = &cacheControl{Type: cacheEphemeral}
 	}
-	applyMessageCacheBreakpoints(mapped.Messages)
 	return mapped, nil
 }
 
-// applyMessageCacheBreakpoints marks the last content block of the final two
-// messages with cache_control so the conversation transcript is cached
-// turn-over-turn, not just the system prompt and tool definitions. Two message
-// breakpoints (not one) keep the previous turn's prefix a cache hit while the
-// newest suffix is being written. Anthropic allows at most 4 breakpoints per
-// request: system + tools use two above, these use the remaining two. Thinking
-// blocks cannot carry cache_control, so the marker goes on the last block that
-// can.
-func applyMessageCacheBreakpoints(messages []anthropicMessage) {
-	marked := 0
-	for i := len(messages) - 1; i >= 0 && marked < 2; i-- {
-		blocks := contentBlocks(messages[i].Content)
-		for j := len(blocks) - 1; j >= 0; j-- {
-			blockType, _ := blocks[j]["type"].(string)
-			if blockType == "thinking" || blockType == "redacted_thinking" {
-				continue
-			}
-			blocks[j]["cache_control"] = map[string]any{"type": cacheEphemeral}
-			messages[i].Content = blocks
-			marked++
-			break
-		}
-	}
-}
-
 func mapMessages(messages []zeroruntime.Message) (string, []anthropicMessage, error) {
 	systemParts := []string{}
 	mapped := []anthropicMessage{}

internal/providers/factory.go

@@ -24,7 +24,7 @@ type Options struct {
 	ModelRegistry *modelregistry.Registry
 	// OAuthResolver, when set, lets the provider authenticate model calls with an
 	// OAuth bearer token (preferred over the API key). nil => API-key auth only.
-	// Applied to the OpenAI, Anthropic, and Google (Gemini) providers.
+	// Applied to the OpenAI and Anthropic providers.
 	OAuthResolver providerio.TokenResolver
 	// OAuthLoginKey is the credential-store key OAuthResolver bound to (empty when
 	// there is no OAuth login). It is the SAME selection the bearer resolver made,
@@ -91,7 +91,6 @@ func New(profile config.ProviderProfile, options Options) (zeroruntime.Provider,
 			AuthScheme:      profile.AuthScheme,
 			AuthHeaderValue: profile.AuthHeaderValue,
 			CustomHeaders:   profile.CustomHeaders,
-			OAuthResolver:   options.OAuthResolver,
 			MaxTokens:       resolved.maxOutputTokens,
 			HTTPClient:      options.HTTPClient,
 			UserAgent:       options.UserAgent,

internal/providers/gemini/provider.go

@@ -49,10 +49,6 @@ type Options struct {
 	CustomHeaders   map[string]string
 	HTTPClient      *http.Client
 	UserAgent       string
-	// OAuthResolver, when set, supplies an OAuth bearer credential per request and
-	// is retried once with a forced token refresh after an upstream 401 (matching
-	// the OpenAI and Anthropic providers). Nil falls back to plain API-key auth.
-	OAuthResolver providerio.TokenResolver
 	// StreamIdleTimeout aborts the stream if no data arrives for this long.
 	// When unset, Zero uses providerio.ResolveStreamIdleTimeout — the
 	// ZERO_STREAM_IDLE_TIMEOUT override or providerio.DefaultStreamIdleTimeout.
@@ -71,7 +67,6 @@ type Provider struct {
 	customHeaders     map[string]string
 	httpClient        *http.Client
 	userAgent         string
-	oauthResolver     providerio.TokenResolver
 	streamIdleTimeout time.Duration
 }
 
@@ -100,7 +95,6 @@ func New(options Options) (*Provider, error) {
 		customHeaders:     providerio.CopyHeaders(options.CustomHeaders),
 		httpClient:        providerio.HTTPClient(options.HTTPClient),
 		userAgent:         options.UserAgent,
-		oauthResolver:     options.OAuthResolver,
 		streamIdleTimeout: providerio.ResolveStreamIdleTimeout(options.StreamIdleTimeout),
 	}, nil
 }
@@ -133,22 +127,20 @@ func (provider *Provider) stream(ctx context.Context, body []byte, events chan<-
 	streamCtx, cancelStream := context.WithCancel(ctx)
 	defer cancelStream()
 
-	response, err := providerio.SendWithAuthRetry(streamCtx, provider.httpClient, http.MethodPost, provider.streamURL(), body,
-		providerio.AuthHeaders{
+	response, err := providerio.SendWithRetry(streamCtx, provider.httpClient, http.MethodPost, provider.streamURL(), body, func(request *http.Request) {
+		request.Header.Set("Content-Type", "application/json")
+		if provider.userAgent != "" {
+			request.Header.Set("User-Agent", provider.userAgent)
+		}
+		providerio.ApplyAuthHeaders(request, providerio.AuthHeaders{
 			APIKey:            provider.apiKey,
 			DefaultAuthHeader: "x-goog-api-key",
 			AuthHeader:        provider.authHeader,
 			AuthScheme:        provider.authScheme,
 			AuthHeaderValue:   provider.authHeaderValue,
 			CustomHeaders:     provider.customHeaders,
-		},
-		provider.oauthResolver,
-		func(request *http.Request) {
-			request.Header.Set("Content-Type", "application/json")
-			if provider.userAgent != "" {
-				request.Header.Set("User-Agent", provider.userAgent)
-			}
-		}, 0)
+		})
+	}, 0)
 	if err != nil {
 		providerio.SendEvent(ctx, events, zeroruntime.StreamEvent{Type: zeroruntime.StreamEventError, Error: provider.redact("provider stream error: " + err.Error())})
 		return

internal/providers/gemini/provider_test.go

@@ -370,57 +370,6 @@ func TestStreamCompletionClassifiesHTTPAndPromptBlockErrors(t *testing.T) {
 	}
 }
 
-// A 401 with an OAuth resolver is retried once with a force-refreshed token; the
-// replayed request carries the refreshed bearer and succeeds.
-func TestStreamCompletionRetries401WithRefreshedToken(t *testing.T) {
-	var attempts int
-	var secondAuth string
-	server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
-		attempts++
-		if attempts == 1 {
-			http.Error(w, `{"error":{"message":"token expired"}}`, http.StatusUnauthorized)
-			return
-		}
-		secondAuth = r.Header.Get("Authorization")
-		writeSSE(w, `{}`)
-	}))
-	defer server.Close()
-
-	var forceRefreshOnRetry bool
-	resolver := func(ctx context.Context, forceRefresh bool) (string, string, bool, error) {
-		if forceRefresh {
-			forceRefreshOnRetry = true
-			return "Authorization", "Bearer refreshed", true, nil
-		}
-		return "Authorization", "Bearer stale", true, nil
-	}
-
-	provider, err := New(Options{
-		APIKey:        "sk-google",
-		BaseURL:       server.URL,
-		Model:         "gemini-test",
-		OAuthResolver: resolver,
-	})
-	if err != nil {
-		t.Fatalf("New returned error: %v", err)
-	}
-	stream, err := provider.StreamCompletion(context.Background(), validRequest())
-	if err != nil {
-		t.Fatalf("StreamCompletion returned error: %v", err)
-	}
-	drain(stream)
-
-	if attempts != 2 {
-		t.Fatalf("attempts = %d, want 2 (initial 401 + one refreshed retry)", attempts)
-	}
-	if !forceRefreshOnRetry {
-		t.Fatalf("resolver was not called with forceRefresh on the retry")
-	}
-	if secondAuth != "Bearer refreshed" {
-		t.Fatalf("retry Authorization = %q, want refreshed bearer", secondAuth)
-	}
-}
-
 func TestStreamCompletionEmitsStreamErrorObject(t *testing.T) {
 	provider := newTestProviderWithKey(t, "sk-google", func(w http.ResponseWriter, r *http.Request) {
 		writeSSE(w, `{"error":{"code":429,"message":"stream failed sk-google","status":"RESOURCE_EXHAUSTED"}}`)

internal/providers/openai/provider.go

@@ -9,7 +9,6 @@ import (
 	"io"
 	"net/http"
 	"net/url"
-	"os"
 	"strings"
 	"time"
 
@@ -284,10 +283,10 @@ func (provider *Provider) emitChunk(
 	events chan<- zeroruntime.StreamEvent,
 ) {
 	for _, choice := range chunk.Choices {
-		if reasoning := choice.Delta.reasoningText(); reasoning != "" {
+		if choice.Delta.ReasoningContent != "" {
 			sendEvent(ctx, events, zeroruntime.StreamEvent{
 				Type:    zeroruntime.StreamEventReasoning,
-				Content: reasoning,
+				Content: choice.Delta.ReasoningContent,
 			})
 		}
 		if choice.Delta.Content != "" {
@@ -318,13 +317,6 @@ func (provider *Provider) emitChunk(
 	}
 }
 
-func (delta streamDelta) reasoningText() string {
-	if delta.ReasoningContent != "" {
-		return delta.ReasoningContent
-	}
-	return delta.Reasoning
-}
-
 // mapFinishReason maps OpenAI's finish_reason onto the runtime's normalized
 // terminal reasons. A normal finish ("stop"/"tool_calls"/"") returns "".
 func mapFinishReason(reason string) string {
@@ -422,12 +414,6 @@ func (provider *Provider) openAIRequest(request zeroruntime.CompletionRequest) c
 	if effort := openAIReasoningEffort(request.ReasoningEffort); effort != "" {
 		mapped.ReasoningEffort = effort
 	}
-	// prompt_cache_key is a documented OpenAI parameter; compatible servers
-	// ignore unknown fields, but a strict endpoint that rejects it can be
-	// accommodated with ZERO_DISABLE_PROMPT_CACHE_KEY=1.
-	if key := strings.TrimSpace(request.PromptCacheKey); key != "" && !promptCacheKeyDisabled() {
-		mapped.PromptCacheKey = key
-	}
 	if len(request.Tools) > 0 {
 		mapped.Tools = make([]toolDefinition, 0, len(request.Tools))
 		for _, tool := range request.Tools {
@@ -444,15 +430,6 @@ func (provider *Provider) openAIRequest(request zeroruntime.CompletionRequest) c
 	return mapped
 }
 
-// promptCacheKeyDisabled reports whether the ZERO_DISABLE_PROMPT_CACHE_KEY
-// kill switch is set to a truthy value. "0" and "false" (any case) are
-// no-ops, matching how ZERO_FORMAT_ON_WRITE parses boolean flags, so an
-// explicitly-disabled toggle never flips the behavior it names.
-func promptCacheKeyDisabled() bool {
-	value := strings.TrimSpace(os.Getenv("ZERO_DISABLE_PROMPT_CACHE_KEY"))
-	return value != "" && value != "0" && !strings.EqualFold(value, "false")
-}
-
 // openAIReasoningEffort normalizes a requested effort to a value the OpenAI chat
 // completions API accepts, or "" to omit the field. "none" (and anything else)
 // is dropped rather than risking a 400 on an unrecognized enum.

internal/providers/openai/provider_test.go

@@ -227,39 +227,6 @@ func TestStreamCompletionEmitsReasoningContentDeltas(t *testing.T) {
 	}
 }
 
-func TestStreamCompletionEmitsReasoningAliasDeltas(t *testing.T) {
-	provider := newTestProvider(t, func(w http.ResponseWriter, r *http.Request) {
-		writeSSE(w, `{"choices":[{"delta":{"reasoning":"Thinking. "}}]}`)
-		writeSSE(w, `{"choices":[{"delta":{"reasoning":"Answering now."}}]}`)
-		writeSSE(w, `[DONE]`)
-	})
-
-	events := collectProviderEvents(t, provider)
-	reasoning := eventsOfType(events, zeroruntime.StreamEventReasoning)
-	if len(reasoning) != 2 {
-		t.Fatalf("reasoning events = %#v, want two reasoning deltas", reasoning)
-	}
-	if reasoning[0].Content != "Thinking. " || reasoning[1].Content != "Answering now." {
-		t.Fatalf("unexpected reasoning events: %#v", reasoning)
-	}
-	if text := eventsOfType(events, zeroruntime.StreamEventText); len(text) != 0 {
-		t.Fatalf("reasoning must not emit text events, got %#v", text)
-	}
-}
-
-func TestStreamCompletionPrefersReasoningContentOverAlias(t *testing.T) {
-	provider := newTestProvider(t, func(w http.ResponseWriter, r *http.Request) {
-		writeSSE(w, `{"choices":[{"delta":{"reasoning_content":"standard","reasoning":"alias"}}]}`)
-		writeSSE(w, `[DONE]`)
-	})
-
-	events := collectProviderEvents(t, provider)
-	reasoning := eventsOfType(events, zeroruntime.StreamEventReasoning)
-	if len(reasoning) != 1 || reasoning[0].Content != "standard" {
-		t.Fatalf("reasoning events = %#v, want standard reasoning_content", reasoning)
-	}
-}
-
 func TestStreamCompletionEmitsReasoningBeforeRegularContent(t *testing.T) {
 	provider := newTestProvider(t, func(w http.ResponseWriter, r *http.Request) {
 		writeSSE(w, `{"choices":[{"delta":{"reasoning_content":"Thinking. ","content":"Answer."}}]}`)
@@ -1259,61 +1226,3 @@ func TestOpenAIRequestEmptyContentHandling(t *testing.T) {
 		t.Fatalf("assistant tool calls dropped: %#v", req.Messages[1])
 	}
 }
-
-// TestOpenAIRequestPromptCacheKey locks in prompt_cache_key forwarding: a
-// session-carrying request serializes the key so the backend can route to a
-// replica holding the cached prefix, a keyless request omits the field
-// entirely (strict servers see byte-identical requests to before), and
-// ZERO_DISABLE_PROMPT_CACHE_KEY suppresses it for endpoints that reject it.
-func TestOpenAIRequestPromptCacheKey(t *testing.T) {
-	provider, err := New(Options{Model: "gpt-test"})
-	if err != nil {
-		t.Fatalf("New returned error: %v", err)
-	}
-	messages := []zeroruntime.Message{{Role: zeroruntime.MessageRoleUser, Content: "hi"}}
-
-	req := provider.openAIRequest(zeroruntime.CompletionRequest{
-		Messages:       messages,
-		PromptCacheKey: "sess_123",
-	})
-	if req.PromptCacheKey != "sess_123" {
-		t.Fatalf("PromptCacheKey = %q, want sess_123", req.PromptCacheKey)
-	}
-	data, err := json.Marshal(req)
-	if err != nil {
-		t.Fatalf("marshal: %v", err)
-	}
-	if !strings.Contains(string(data), `"prompt_cache_key":"sess_123"`) {
-		t.Fatalf("prompt_cache_key not serialized: %s", data)
-	}
-
-	req = provider.openAIRequest(zeroruntime.CompletionRequest{Messages: messages})
-	if data, err = json.Marshal(req); err != nil {
-		t.Fatalf("marshal: %v", err)
-	}
-	if strings.Contains(string(data), "prompt_cache_key") {
-		t.Fatalf("keyless request must omit prompt_cache_key: %s", data)
-	}
-
-	t.Setenv("ZERO_DISABLE_PROMPT_CACHE_KEY", "1")
-	req = provider.openAIRequest(zeroruntime.CompletionRequest{
-		Messages:       messages,
-		PromptCacheKey: "sess_123",
-	})
-	if req.PromptCacheKey != "" {
-		t.Fatalf("kill switch ignored; PromptCacheKey = %q", req.PromptCacheKey)
-	}
-
-	// Explicitly-falsy kill switch values must NOT disable forwarding — only
-	// truthy values flip the toggle (same parsing as ZERO_FORMAT_ON_WRITE).
-	for _, value := range []string{"0", "false", "FALSE"} {
-		t.Setenv("ZERO_DISABLE_PROMPT_CACHE_KEY", value)
-		req = provider.openAIRequest(zeroruntime.CompletionRequest{
-			Messages:       messages,
-			PromptCacheKey: "sess_123",
-		})
-		if req.PromptCacheKey != "sess_123" {
-			t.Fatalf("ZERO_DISABLE_PROMPT_CACHE_KEY=%q must be a no-op; PromptCacheKey = %q", value, req.PromptCacheKey)
-		}
-	}
-}

internal/providers/openai/types.go

@@ -8,11 +8,6 @@ type chatCompletionRequest struct {
 	ReasoningEffort     string           `json:"reasoning_effort,omitempty"`
 	Stream              bool             `json:"stream"`
 	StreamOptions       *streamOptions   `json:"stream_options,omitempty"`
-	// PromptCacheKey asks the backend to route the request to a replica that
-	// already holds this conversation's prefix in its prompt cache (the OpenAI
-	// `prompt_cache_key` parameter). Omitted when the caller carries no session
-	// identity or when ZERO_DISABLE_PROMPT_CACHE_KEY is set.
-	PromptCacheKey string `json:"prompt_cache_key,omitempty"`
 }
 
 // streamOptions requests the final usage chunk on a streaming response. Without
@@ -83,7 +78,6 @@ type streamChoice struct {
 type streamDelta struct {
 	Content          string                `json:"content"`
 	ReasoningContent string                `json:"reasoning_content"`
-	Reasoning        string                `json:"reasoning"`
 	ToolCalls        []streamToolCallDelta `json:"tool_calls"`
 }
 

internal/providers/providerio/retry.go

@@ -23,18 +23,12 @@ import (
 // (billable) work. Only the INITIAL request is ever in scope; once the response
 // body starts streaming it is never re-issued.
 
-const defaultMaxRetryAttempts = 6
+const defaultMaxRetryAttempts = 3
 
 // maxBackoff caps a single backoff wait so a hostile or buggy Retry-After can't
 // stall the agent for minutes.
 const maxBackoff = 30 * time.Second
 
-// retryBackoffBase is the first wait when the server supplied no Retry-After.
-// Rate-limit windows are measured in seconds, not milliseconds: retrying a 429
-// after 400ms almost always burns the attempt while still limited, so the
-// schedule is 2s, 4s, 8s, 16s, then maxBackoff. A var so tests can shrink it.
-var retryBackoffBase = 2 * time.Second
-
 // SendWithRetry issues an HTTP request, retrying ONLY the safe-to-replay server
 // responses (429 and 503, see ShouldRetryStatus) up to maxAttempts — backing off
 // between tries and honoring a server Retry-After header and context
@@ -116,11 +110,17 @@ func ShouldRetryStatus(code int) bool {
 }
 
 // Backoff waits before retry attempt N (1-based), returning false if the context
-// is cancelled during the wait. A server-supplied (positive) Retry-After wins;
-// otherwise the wait doubles from retryBackoffBase per attempt. Either way the
-// wait is capped at maxBackoff.
+// is cancelled during the wait. The wait is attempt*400ms unless the server
+// supplied a (positive) Retry-After, and is capped at maxBackoff.
 func Backoff(ctx context.Context, attempt int, retryAfter time.Duration) bool {
-	timer := time.NewTimer(backoffWait(attempt, retryAfter))
+	wait := time.Duration(attempt) * 400 * time.Millisecond
+	if retryAfter > 0 {
+		wait = retryAfter
+	}
+	if wait > maxBackoff {
+		wait = maxBackoff
+	}
+	timer := time.NewTimer(wait)
 	defer timer.Stop()
 	select {
 	case <-ctx.Done():
@@ -130,27 +130,6 @@ func Backoff(ctx context.Context, attempt int, retryAfter time.Duration) bool {
 	}
 }
 
-// backoffWait computes the wait before retry attempt N (1-based): Retry-After
-// when supplied, else exponential from retryBackoffBase, both capped at
-// maxBackoff. The exponent is clamped so a large attempt count cannot overflow.
-func backoffWait(attempt int, retryAfter time.Duration) time.Duration {
-	wait := retryAfter
-	if wait <= 0 {
-		exponent := attempt - 1
-		if exponent > 5 {
-			exponent = 5
-		}
-		if exponent < 0 {
-			exponent = 0
-		}
-		wait = retryBackoffBase * time.Duration(1<<exponent)
-	}
-	if wait > maxBackoff {
-		wait = maxBackoff
-	}
-	return wait
-}
-
 // RetryAfter parses a response's Retry-After header (delay-seconds or an HTTP
 // date) into a positive duration, or 0 when absent/unparseable. The result is
 // capped at maxBackoff by Backoff.

internal/providers/providerio/retry_test.go

@@ -94,40 +94,7 @@ func TestBackoffWaitsThenReturnsTrue(t *testing.T) {
 	}
 }
 
-// shrinkBackoff makes retry waits negligible for the duration of a test.
-func shrinkBackoff(t *testing.T) {
-	t.Helper()
-	saved := retryBackoffBase
-	retryBackoffBase = time.Millisecond
-	t.Cleanup(func() { retryBackoffBase = saved })
-}
-
-func TestBackoffWaitSchedule(t *testing.T) {
-	// Without Retry-After the wait doubles per attempt from 2s and caps at 30s;
-	// a supplied Retry-After wins but is capped too.
-	cases := []struct {
-		attempt    int
-		retryAfter time.Duration
-		want       time.Duration
-	}{
-		{1, 0, 2 * time.Second},
-		{2, 0, 4 * time.Second},
-		{3, 0, 8 * time.Second},
-		{4, 0, 16 * time.Second},
-		{5, 0, 30 * time.Second},  // 32s capped
-		{50, 0, 30 * time.Second}, // clamped exponent, no overflow
-		{1, 7 * time.Second, 7 * time.Second},
-		{1, 5 * time.Minute, 30 * time.Second}, // hostile Retry-After capped
-	}
-	for _, c := range cases {
-		if got := backoffWait(c.attempt, c.retryAfter); got != c.want {
-			t.Errorf("backoffWait(%d, %v) = %v, want %v", c.attempt, c.retryAfter, got, c.want)
-		}
-	}
-}
-
 func TestSendWithRetryRetriesThenSucceeds(t *testing.T) {
-	shrinkBackoff(t)
 	var hits int32
 	server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
 		if atomic.AddInt32(&hits, 1) == 1 {
@@ -173,7 +140,6 @@ func TestSendWithRetryReturnsNonRetryableImmediately(t *testing.T) {
 }
 
 func TestSendWithRetryReturnsLastResponseAfterMaxAttempts(t *testing.T) {
-	shrinkBackoff(t)
 	var hits int32
 	server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
 		atomic.AddInt32(&hits, 1)

internal/repoinfo/repoinfo.go

@@ -54,9 +54,6 @@ type Info struct {
 	AgeDays               *int       `json:"ageDays,omitempty"`
 	Contributors90d       *int       `json:"contributors90d,omitempty"`
 	CommitVelocity30d     *int       `json:"commitVelocity30d,omitempty"`
-	BranchCount           *int       `json:"branchCount,omitempty"`
-	CommitCount           *int       `json:"commitCount,omitempty"`
-	TagCount              *int       `json:"tagCount,omitempty"`
 }
 
 // RunGit runs a git subcommand in dir and returns raw stdout. A non-zero exit
@@ -232,43 +229,6 @@ func Collect(ctx context.Context, opts Options) (Info, error) {
 			info.CommitVelocity30d = &n
 		}
 	}
-	if count, err := run(ctx, dir, "rev-list", "--count", "HEAD"); err == nil {
-		if n, perr := strconv.Atoi(strings.TrimSpace(count)); perr == nil {
-			info.CommitCount = &n
-		}
-	}
-	if branches, err := run(ctx, dir, "branch", "-a"); err == nil {
-		set := map[string]bool{}
-		for _, line := range strings.Split(branches, "\n") {
-			line = strings.TrimSpace(line)
-			if line == "" || strings.Contains(line, "->") {
-				continue
-			}
-			// Strip leading '* ' (current branch) or '+ ' (checked out in another worktree).
-			line = strings.TrimPrefix(line, "* ")
-			line = strings.TrimPrefix(line, "+ ")
-			line = strings.TrimSpace(line)
-			if line == "" || strings.HasPrefix(line, "(") {
-				continue
-			}
-			// If it's a remote branch, extract the branch name.
-			// E.g., remotes/origin/main -> main
-			// E.g., remotes/origin/feature/xyz -> feature/xyz
-			if strings.HasPrefix(line, "remotes/") {
-				line = strings.TrimPrefix(line, "remotes/")
-				if slashIdx := strings.Index(line, "/"); slashIdx != -1 {
-					line = line[slashIdx+1:]
-				}
-			}
-			set[line] = true
-		}
-		n := len(set)
-		info.BranchCount = &n
-	}
-	if tags, err := run(ctx, dir, "tag"); err == nil {
-		n := countNonEmptyLines(tags)
-		info.TagCount = &n
-	}
 
 	return info, nil
 }
@@ -368,13 +328,3 @@ func defaultRunGit(ctx context.Context, dir string, args ...string) (string, err
 	}
 	return stdout.String(), nil
 }
-
-func countNonEmptyLines(s string) int {
-	count := 0
-	for _, line := range strings.Split(s, "\n") {
-		if strings.TrimSpace(line) != "" {
-			count++
-		}
-	}
-	return count
-}

internal/repoinfo/repoinfo_test.go

@@ -43,8 +43,6 @@ func TestCollectCoreMetrics(t *testing.T) {
 			"remote":    "https://github.com/x/y.git\n",
 			"log":       "0\n",
 			"rev-list":  "12\n",
-			"branch":    "  main\n  remotes/origin/HEAD -> origin/main\n  remotes/origin/main\n  remotes/origin/feature\n",
-			"tag":       "v0.1.0\nv0.2.0\n",
 		}, nil),
 	})
 	if err != nil {
@@ -87,15 +85,6 @@ func TestCollectCoreMetrics(t *testing.T) {
 	if info.CommitVelocity30d == nil || *info.CommitVelocity30d != 12 {
 		t.Fatalf("CommitVelocity30d=%v want 12", info.CommitVelocity30d)
 	}
-	if info.CommitCount == nil || *info.CommitCount != 12 {
-		t.Fatalf("CommitCount=%v want 12", info.CommitCount)
-	}
-	if info.BranchCount == nil || *info.BranchCount != 2 {
-		t.Fatalf("BranchCount=%v want 2", info.BranchCount)
-	}
-	if info.TagCount == nil || *info.TagCount != 2 {
-		t.Fatalf("TagCount=%v want 2", info.TagCount)
-	}
 }
 
 func TestCollectContributorsUnique(t *testing.T) {
@@ -263,13 +252,12 @@ func TestCollectNotGitRepo(t *testing.T) {
 }
 
 func TestCollectOnlyReadOnlyLocalSubcommands(t *testing.T) {
-	allowed := map[string]bool{"ls-tree": true, "rev-parse": true, "remote": true, "log": true, "rev-list": true, "branch": true, "tag": true}
+	allowed := map[string]bool{"ls-tree": true, "rev-parse": true, "remote": true, "log": true, "rev-list": true}
 	var used []string
 	_, err := Collect(context.Background(), Options{
 		Now: time.Unix(0, 0),
 		RunGit: fakeGit(t, map[string]string{
 			"ls-tree": lsTree, "rev-parse": "main\n", "remote": "u\n", "log": "0\n", "rev-list": "1\n",
-			"branch": "main\n", "tag": "v0.1.0\n",
 		}, &used),
 	})
 	if err != nil {

internal/sandbox/manager.go

@@ -3,9 +3,8 @@ package sandbox
 import (
 	"errors"
 	"os"
-	"path/filepath"
+	"os/exec"
 	"runtime"
-	"strings"
 )
 
 // errWindowsSandboxNotInitialized is returned only to a caller that explicitly
@@ -122,55 +121,9 @@ func (manager SandboxManager) Backend() Backend {
 	return manager.backend
 }
 
-// isExecutable checks whether a file is executable. On Unix, this checks the
-// execute permission bits. On Windows, Go's os.FileMode does not set execute
-// bits, so we check for common executable extensions instead.
-func isExecutable(fi os.FileInfo) bool {
-	if !fi.Mode().IsRegular() {
-		return false
-	}
-	if runtime.GOOS == "windows" {
-		name := strings.ToLower(fi.Name())
-		return strings.HasSuffix(name, ".exe") ||
-			strings.HasSuffix(name, ".com") ||
-			strings.HasSuffix(name, ".bat") ||
-			strings.HasSuffix(name, ".cmd")
-	}
-	return fi.Mode()&0o111 != 0
-}
-
-// lookupExecutable checks whether a named binary exists and is executable,
-// using os.Stat instead of exec.LookPath. exec.LookPath internally uses the
-// faccessat2 syscall, which is blocked by Android's seccomp filter (SIGSYS).
-func lookupExecutable(name string) (string, error) {
-	if !strings.Contains(name, string(os.PathSeparator)) {
-		path := os.Getenv("PATH")
-		for _, dir := range strings.Split(path, string(os.PathListSeparator)) {
-			if dir == "" {
-				continue // skip empty entries (e.g. trailing colon)
-			}
-			candidate := filepath.Join(dir, name)
-			if fi, err := os.Stat(candidate); err == nil {
-				if isExecutable(fi) {
-					return candidate, nil
-				}
-			}
-		}
-		return "", errors.New("executable file not found in $PATH")
-	}
-	fi, err := os.Stat(name)
-	if err != nil {
-		return "", err
-	}
-	if isExecutable(fi) {
-		return name, nil
-	}
-	return "", errors.New("executable file not found")
-}
-
 func selectPlatformBackend(goos string, lookup func(string) (string, error)) Backend {
 	if lookup == nil {
-		lookup = lookupExecutable
+		lookup = exec.LookPath
 	}
 	switch goos {
 	case "linux":

internal/sandbox/manager_test.go

@@ -72,9 +72,6 @@ func TestPermissionProfileFromPolicyIncludesDefaultTempWriteRoots(t *testing.T)
 	if !writeRootsContain(profile.FileSystem.WriteRoots, tmpdir) {
 		t.Fatalf("write roots = %#v, want temp root %q", profile.FileSystem.WriteRoots, tmpdir)
 	}
-	// /tmp is a default temp write root on POSIX only (see
-	// defaultTempWriteRootCandidatesForGOOS); on Windows the bare path resolves
-	// against the current drive, so a stray C:\tmp must not turn this on.
 	if runtime.GOOS != "windows" && pathExists("/tmp") && !writeRootsContain(profile.FileSystem.WriteRoots, "/tmp") {
 		t.Fatalf("write roots = %#v, want /tmp", profile.FileSystem.WriteRoots)
 	}

internal/sandbox/runner_windows_integration_test.go

@@ -190,67 +190,6 @@ func TestWindowsUnelevatedRealSandboxSmoke(t *testing.T) {
 	}
 }
 
-// TestWindowsRestrictedTokenNestedPipeCapture pins the fix in
-// broadenWindowsRestrictedTokenDefaultDacl (windows_token_windows.go): a
-// nested subprocess spawned FROM WITHIN the sandboxed process, with its
-// output captured via a pipe, must succeed. Before the fix, the sandboxed
-// process's own attempt to create a pipe for such a subprocess failed with
-// ERROR_ACCESS_DENIED (Win32 error 5) — the WRITE_RESTRICTED token's extra
-// access check has no restricted-SID match against a freshly created pipe's
-// default security descriptor. This is exactly the pattern any tool that
-// shells out internally and captures output hits (`gh` invoking `git`, for
-// one; cmd.exe's own FOR /F does the identical CreatePipe+CreateProcess
-// dance internally, so it reproduces the bug with no external dependency
-// beyond cmd.exe itself).
-func TestWindowsRestrictedTokenNestedPipeCapture(t *testing.T) {
-	if os.Getenv("ZERO_SANDBOX_REAL_SMOKE") != "1" {
-		t.Skip("set ZERO_SANDBOX_REAL_SMOKE=1 to run real Windows sandbox smoke tests")
-	}
-	runnerExe := realSmokeExecutable(t, "ZERO_WINDOWS_COMMAND_RUNNER_EXE", WindowsSandboxCommandRunnerName)
-
-	root := t.TempDir()
-	sandboxHome := filepath.Join(root, ".zero-sandbox")
-	profile := PermissionProfile{
-		FileSystem: FileSystemPolicy{
-			Kind:                 FileSystemRestricted,
-			ReadRoots:            []string{root},
-			WriteRoots:           []WritableRoot{{Root: root, ProtectedMetadataNames: []string{".git", ".zero", ".agents"}}},
-			IncludePlatformRoots: true,
-			AllowTemp:            true,
-		},
-		Network: NetworkPolicy{Mode: NetworkDeny},
-	}
-	config := WindowsSandboxCommandArgsOptions{
-		SandboxHome:       sandboxHome,
-		CommandCWD:        root,
-		WorkspaceRoots:    []string{root},
-		PermissionProfile: profile,
-		SandboxLevel:      WindowsSandboxLevelUnelevated,
-	}
-
-	marker := filepath.Join(root, "nested-pipe-marker.txt")
-	script := filepath.Join(root, "nested-pipe.cmd")
-	// FOR /F drives cmd.exe's own internal CreatePipe+CreateProcess capture
-	// of the quoted command's output — the exact mechanism this fix targets.
-	// The full path to whoami.exe sidesteps PATH resolution inside the
-	// sandboxed process's minimal environment.
-	scriptBody := "for /F %%i in ('C:\\Windows\\System32\\whoami.exe') do echo %%i> " + marker + "\r\n"
-	if err := os.WriteFile(script, []byte(scriptBody), 0o644); err != nil {
-		t.Fatalf("write nested-pipe script: %v", err)
-	}
-
-	runWindowsRealSmokeCommand(t, runnerExe, config, []string{
-		"cmd.exe", "/d", "/s", "/c", script,
-	}, 0)
-	captured, err := os.ReadFile(marker)
-	if err != nil {
-		t.Fatalf("read nested-pipe marker: %v", err)
-	}
-	if strings.TrimSpace(string(captured)) == "" {
-		t.Fatalf("nested-pipe marker is empty; FOR /F failed to capture the subprocess's output")
-	}
-}
-
 func realSmokeExecutable(t *testing.T, envKey string, fallbackName string) string {
 	t.Helper()
 	if path := os.Getenv(envKey); path != "" {

internal/sandbox/scope_test.go

@@ -129,9 +129,6 @@ func TestNewScopeNormalizesAndValidatesExtraRoots(t *testing.T) {
 	if !stringSliceContains(roots, normalizeWorkspaceRootBestEffort(extra)) {
 		t.Fatalf("Roots()=%v want extra root %q", roots, normalizeWorkspaceRootBestEffort(extra))
 	}
-	// /tmp is a default temp write root on POSIX only (see
-	// defaultTempWriteRootCandidatesForGOOS); on Windows the bare path resolves
-	// against the current drive, so a stray C:\tmp must not turn this on.
 	if runtime.GOOS != "windows" && pathExists("/tmp") && !stringSliceContains(roots, normalizeWorkspaceRootBestEffort("/tmp")) {
 		t.Fatalf("Roots()=%v want default /tmp write root", roots)
 	}

internal/sandbox/windows_process_windows.go

@@ -87,20 +87,11 @@ func windowsCommandLine(args []string) (string, error) {
 	if len(args) == 0 {
 		return "", errorsNewWindowsProcess("missing command")
 	}
+	out := make([]string, 0, len(args))
 	for _, arg := range args {
 		if strings.ContainsRune(arg, 0) {
 			return "", errorsNewWindowsProcess("command argument contains NUL")
 		}
-	}
-	// Zero's cmd.exe shell invocation needs its final element (the shell
-	// command text) reaching cmd.exe raw, not escaped like a normal argv
-	// element: see WindowsShellCommandLine for why. Every other command this
-	// runner might launch is escaped normally below.
-	if commandLine, ok := windowsShellCommandLineFromArgs(args); ok {
-		return commandLine, nil
-	}
-	out := make([]string, 0, len(args))
-	for _, arg := range args {
 		out = append(out, syscall.EscapeArg(arg))
 	}
 	return strings.Join(out, " "), nil

internal/sandbox/windows_runner.go

@@ -105,56 +105,6 @@ const (
 	WindowsSandboxLevelDisabled   WindowsSandboxLevel = "disabled"
 )
 
-// WindowsShellArgs returns cmd.exe's argv (after the executable name) for
-// running commandText as a shell command on Windows: no wrapping quotes and
-// no /S, so commandText reaches cmd.exe's own /C remainder parsing exactly as
-// written. See WindowsShellCommandLine for why that matters. Used both as
-// CommandSpec.Args for the plain (unwrapped) path and, via
-// windowsShellCommandLineFromArgs, to recognize this same shape once it has
-// round-tripped through the sandboxed runner's CLI argv.
-func WindowsShellArgs(commandText string) []string {
-	return []string{"/d", "/c", commandText}
-}
-
-// WindowsShellCommandLine builds the raw command line a Windows CreateProcess
-// call should receive to run commandText as a shell command: "cmd.exe /d /c "
-// followed by commandText completely unescaped.
-//
-// cmd.exe's own /C remainder parsing is not CommandLineToArgvW-compatible: it
-// applies its own quote-stripping heuristic (documented in `cmd /?`) whenever
-// the remainder starts with a literal quote, and that heuristic does not
-// understand backslash-escaped inner quotes the way a normal argv consumer
-// would. A command like `python -c "print(15 / 3)"` passed through the
-// standard exec.Cmd Args mechanism gets wrapped in an outer pair of quotes
-// (because it contains spaces) with its own quotes escaped as \" — exactly
-// the shape that heuristic corrupts, stripping the outer quotes but leaving
-// the literal backslashes behind. Passing commandText through raw, exactly as
-// the model wrote it, means cmd.exe parses it the same way it would if typed
-// directly at an interactive prompt: a leading quoted executable path like
-// `"C:\Program Files\foo.exe" arg` is preserved correctly by cmd.exe's own
-// quote-preserving special case, and a command with no leading quote at all,
-// like the python example above, is never touched by the stripping heuristic
-// in the first place.
-func WindowsShellCommandLine(commandText string) string {
-	return "cmd.exe /d /c " + commandText
-}
-
-// windowsShellCommandLineFromArgs reports whether args is exactly
-// ["cmd.exe"]+WindowsShellArgs(text) for some text and, if so, returns
-// WindowsShellCommandLine's result for that text. The sandboxed runner path
-// only has the deserialized argv (WindowsSandboxCommandConfig.Command) to
-// work from, not the original commandText, so it recovers the raw command
-// line by recognizing the shape instead.
-func windowsShellCommandLineFromArgs(args []string) (string, bool) {
-	if len(args) != 4 {
-		return "", false
-	}
-	if !strings.EqualFold(args[0], "cmd.exe") || args[1] != "/d" || args[2] != "/c" {
-		return "", false
-	}
-	return WindowsShellCommandLine(args[3]), true
-}
-
 type WindowsSandboxCommandArgsOptions struct {
 	SandboxHome       string
 	CommandCWD        string

internal/sandbox/windows_runner_test.go

@@ -147,56 +147,3 @@ func TestRunWindowsSandboxCommandRunnerRejectsInvalidArgs(t *testing.T) {
 		t.Fatalf("stderr = %q, want runner name", stderr.String())
 	}
 }
-
-func TestWindowsShellArgsHasNoSAndKeepsCommandTextWhole(t *testing.T) {
-	args := WindowsShellArgs(`python -c "print(15 / 3)"`)
-	want := []string{"/d", "/c", `python -c "print(15 / 3)"`}
-	if len(args) != len(want) {
-		t.Fatalf("args = %#v, want %#v", args, want)
-	}
-	for index := range want {
-		if args[index] != want[index] {
-			t.Fatalf("args = %#v, want %#v", args, want)
-		}
-	}
-}
-
-func TestWindowsShellCommandLineLeavesCommandTextUnescaped(t *testing.T) {
-	// The whole point of this function: commandText's own quotes must reach
-	// cmd.exe exactly as written, not re-quoted or backslash-escaped the way
-	// a normal argv-escaping function (like syscall.EscapeArg) would treat an
-	// argument containing spaces and embedded quotes.
-	commandText := `python -c "print(15 / 3)"`
-	got := WindowsShellCommandLine(commandText)
-	want := `cmd.exe /d /c python -c "print(15 / 3)"`
-	if got != want {
-		t.Fatalf("WindowsShellCommandLine = %q, want %q", got, want)
-	}
-}
-
-func TestWindowsShellCommandLineFromArgsRecognizesTheShellShape(t *testing.T) {
-	commandLine, ok := windowsShellCommandLineFromArgs([]string{"cmd.exe", "/d", "/c", `echo "hi"`})
-	if !ok {
-		t.Fatal("windowsShellCommandLineFromArgs did not recognize the shell shape")
-	}
-	if want := `cmd.exe /d /c echo "hi"`; commandLine != want {
-		t.Fatalf("commandLine = %q, want %q", commandLine, want)
-	}
-}
-
-func TestWindowsShellCommandLineFromArgsRejectsOtherShapes(t *testing.T) {
-	cases := [][]string{
-		nil,
-		{"cmd.exe"},
-		{"cmd.exe", "/d", "/c"},
-		{"cmd.exe", "/d", "/c", "echo hi", "extra"},
-		{"git.exe", "/d", "/c", "echo hi"},
-		{"cmd.exe", "/s", "/c", "echo hi"},
-		{"cmd.exe", "/d", "/k", "echo hi"},
-	}
-	for _, args := range cases {
-		if _, ok := windowsShellCommandLineFromArgs(args); ok {
-			t.Fatalf("windowsShellCommandLineFromArgs(%#v) matched, want no match", args)
-		}
-	}
-}

internal/sandbox/windows_token_windows.go

@@ -21,11 +21,6 @@ const (
 
 var procCreateRestrictedToken = windows.NewLazySystemDLL("advapi32.dll").NewProc("CreateRestrictedToken")
 
-// procSetEntriesInAclW merges new ACEs into an existing ACL. Not wrapped by
-// x/sys/windows (its internal setEntriesInAcl is unexported), so it is
-// declared directly the same way procCreateRestrictedToken is.
-var procSetEntriesInAclW = windows.NewLazySystemDLL("advapi32.dll").NewProc("SetEntriesInAclW")
-
 type windowsLocalSID struct {
 	sid *windows.SID
 }
@@ -127,139 +122,9 @@ func createWindowsRestrictedTokenFromBase(base windows.Token, capabilitySIDs []w
 		_ = restricted.Close()
 		return 0, err
 	}
-	if err := broadenWindowsRestrictedTokenDefaultDacl(restricted, sidFromBytes(logonSID)); err != nil {
-		_ = restricted.Close()
-		return 0, err
-	}
-	runtime.KeepAlive(logonSID)
 	return restricted, nil
 }
 
-// broadenWindowsRestrictedTokenDefaultDacl adds the token's own logon SID to
-// its default DACL (the DACL applied to any kernel object the token's process
-// creates WITHOUT an explicit security descriptor, e.g. anonymous pipes,
-// events, mutexes).
-//
-// A WRITE_RESTRICTED token requires a WRITE-type access check to match BOTH
-// the normal enabled-SID grant AND a SEPARATE grant to one of the token's
-// restricted SIDs. CreateRestrictedToken does not touch the default DACL it
-// inherits from the base token, so newly created objects only carry ACEs for
-// the base token's normal identity (owner, SYSTEM, Administrators) — none of
-// which are in the restricted-SID list — so the second check fails. This
-// breaks anything that creates a pipe/handle for itself with default
-// security, which is exactly what any tool using a language runtime's
-// "spawn a subprocess and capture its output" primitive does (Go's os/exec,
-// and by extension `gh`, and many other CLI tools that shell out
-// internally): CreatePipe() succeeds, but the creating process's own token
-// then fails to actually read/write the handle it just made.
-//
-// The logon SID is already unconditionally present in this token's
-// restricted-SID list (see createWindowsRestrictedTokenFromBase), so adding
-// it here — and ONLY it — to the default DACL is the minimal change that
-// satisfies the WRITE_RESTRICTED extra check for self-created objects. It
-// does not touch file-system access: NTFS write-jailing is enforced by the
-// explicit ACL grants applied to workspace paths (windows_acl.go), which are
-// created WITH an explicit security descriptor and never consult the token's
-// default DACL. The exposure is bounded to the same logon session (other
-// processes running as the same signed-in user could, in principle, open a
-// NAMED kernel object the sandboxed process creates with default security;
-// anonymous pipes — the actual object type this fixes — have no name and are
-// only reachable via an inherited handle, so this is a no-op for them).
-func broadenWindowsRestrictedTokenDefaultDacl(token windows.Token, logonSID *windows.SID) error {
-	oldDacl, oldDaclBuf, err := windowsTokenDefaultDacl(token)
-	if err != nil {
-		return fmt.Errorf("read token default DACL: %w", err)
-	}
-	// The second (WRITE-type) access check only needs a read/write match; a
-	// full GENERIC_ALL grant (which also implies DELETE, WRITE_DAC, and
-	// WRITE_OWNER) is broader than the pipe/event/mutex use case this exists
-	// for actually requires.
-	access := []windows.EXPLICIT_ACCESS{{
-		AccessPermissions: windows.GENERIC_READ | windows.GENERIC_WRITE,
-		AccessMode:        windows.GRANT_ACCESS,
-		Inheritance:       windows.NO_INHERITANCE,
-		Trustee: windows.TRUSTEE{
-			MultipleTrusteeOperation: windows.NO_MULTIPLE_TRUSTEE,
-			TrusteeForm:              windows.TRUSTEE_IS_SID,
-			TrusteeType:              windows.TRUSTEE_IS_USER,
-			TrusteeValue:             windows.TrusteeValueFromSID(logonSID),
-		},
-	}}
-	newDacl, err := setEntriesInACL(access, oldDacl)
-	// oldDacl points INTO oldDaclBuf (see windowsTokenDefaultDacl) and is
-	// dereferenced by native code inside setEntriesInACL, above. Nothing in Go
-	// references oldDaclBuf once windowsTokenDefaultDacl returned, so without
-	// this KeepAlive it is eligible for GC the moment an allocation in this
-	// function (the EXPLICIT_ACCESS literal, TrusteeValueFromSID) hits a
-	// safepoint, before the native call ever reads it - a real, if narrow,
-	// use-after-free window in security-boundary code.
-	runtime.KeepAlive(oldDaclBuf)
-	if err != nil {
-		return fmt.Errorf("merge token default DACL: %w", err)
-	}
-	defer func() { _, _ = windows.LocalFree(windows.Handle(unsafe.Pointer(newDacl))) }()
-	if err := windowsSetTokenDefaultDacl(token, newDacl); err != nil {
-		return fmt.Errorf("set token default DACL: %w", err)
-	}
-	return nil
-}
-
-type windowsTokenDefaultDaclInfo struct {
-	DefaultDacl *windows.ACL
-}
-
-// windowsTokenDefaultDacl returns the token's current default DACL along with
-// the buffer backing it. TOKEN_DEFAULT_DACL embeds the ACL data inside the
-// same allocation GetTokenInformation fills, so the returned *windows.ACL is
-// only valid for as long as the returned buffer stays reachable: the caller
-// must runtime.KeepAlive(buf) until every native call that dereferences the
-// ACL has completed. A KeepAlive inside this function, ending at its own
-// return, would not protect any use by the caller after that.
-func windowsTokenDefaultDacl(token windows.Token) (*windows.ACL, []byte, error) {
-	var size uint32
-	err := windows.GetTokenInformation(token, windows.TokenDefaultDacl, nil, 0, &size)
-	if err == nil || err != windows.ERROR_INSUFFICIENT_BUFFER {
-		return nil, nil, fmt.Errorf("size TokenDefaultDacl: %w", err)
-	}
-	buf := make([]byte, size)
-	if err := windows.GetTokenInformation(token, windows.TokenDefaultDacl, &buf[0], size, &size); err != nil {
-		return nil, nil, fmt.Errorf("get TokenDefaultDacl: %w", err)
-	}
-	info := (*windowsTokenDefaultDaclInfo)(unsafe.Pointer(&buf[0]))
-	return info.DefaultDacl, buf, nil
-}
-
-func windowsSetTokenDefaultDacl(token windows.Token, dacl *windows.ACL) error {
-	info := windowsTokenDefaultDaclInfo{DefaultDacl: dacl}
-	err := windows.SetTokenInformation(token, windows.TokenDefaultDacl, (*byte)(unsafe.Pointer(&info)), uint32(unsafe.Sizeof(info)))
-	runtime.KeepAlive(info)
-	return err
-}
-
-// setEntriesInACL merges entries into oldACL via Win32 SetEntriesInAclW,
-// returning a newly allocated ACL the caller must free with windows.LocalFree.
-func setEntriesInACL(entries []windows.EXPLICIT_ACCESS, oldACL *windows.ACL) (*windows.ACL, error) {
-	if len(entries) == 0 {
-		return nil, errors.New("setEntriesInACL requires at least one entry")
-	}
-	var newACL *windows.ACL
-	// SetEntriesInAclW reports failure directly in its return value (ERROR_SUCCESS
-	// on success, a Win32 error code otherwise); unlike many Win32 APIs it does not
-	// set the thread's last-error, so the syscall trio's second/third return
-	// values (which surface GetLastError) are not meaningful here.
-	ret, _, _ := procSetEntriesInAclW.Call(
-		uintptr(len(entries)),
-		uintptr(unsafe.Pointer(&entries[0])),
-		uintptr(unsafe.Pointer(oldACL)),
-		uintptr(unsafe.Pointer(&newACL)),
-	)
-	runtime.KeepAlive(entries)
-	if ret != 0 {
-		return nil, fmt.Errorf("SetEntriesInAclW: %w", syscall.Errno(ret))
-	}
-	return newACL, nil
-}
-
 func copyWindowsLogonSID(token windows.Token) ([]byte, error) {
 	groups, err := token.GetTokenGroups()
 	if err == nil {

internal/sandbox/windows_unelevated.go

@@ -61,10 +61,8 @@ func buildWindowsUnelevatedAppliedPlan(config WindowsSandboxCommandConfig) (Wind
 
 // loadWindowsUnelevatedSetupMarker reads the marker; a missing file is the
 // common first-run state and returns an empty marker, not an error. A marker
-// with an unexpected schema version or a corrupt/truncated body is likewise
-// treated as empty so the runner re-applies (and rewrites) rather than failing:
-// the marker only memoizes idempotent ACL applies, so resetting it can only
-// cost redundant work, never skip enforcement.
+// with an unexpected schema version is treated as empty so the runner re-applies
+// (and rewrites) rather than failing.
 func loadWindowsUnelevatedSetupMarker(sandboxHome string) (WindowsUnelevatedSetupMarker, error) {
 	sandboxHome = strings.TrimSpace(sandboxHome)
 	if sandboxHome == "" {
@@ -80,7 +78,7 @@ func loadWindowsUnelevatedSetupMarker(sandboxHome string) (WindowsUnelevatedSetu
 	}
 	var marker WindowsUnelevatedSetupMarker
 	if err := json.Unmarshal(bytes, &marker); err != nil {
-		return WindowsUnelevatedSetupMarker{SchemaVersion: windowsUnelevatedSetupMarkerSchemaVersion}, nil
+		return WindowsUnelevatedSetupMarker{}, fmt.Errorf("parse windows unelevated setup marker %s: %w", path, err)
 	}
 	if marker.SchemaVersion != windowsUnelevatedSetupMarkerSchemaVersion {
 		return WindowsUnelevatedSetupMarker{SchemaVersion: windowsUnelevatedSetupMarkerSchemaVersion}, nil

internal/sandbox/windows_unelevated_test.go

@@ -138,38 +138,6 @@ func TestWindowsUnelevatedSetupMarkerEvictsOldestPastCap(t *testing.T) {
 	}
 }
 
-func TestLoadWindowsUnelevatedSetupMarkerSelfHealsCorruptFile(t *testing.T) {
-	home := filepath.Join(t.TempDir(), ".zero-sandbox")
-	if err := os.MkdirAll(home, 0o700); err != nil {
-		t.Fatalf("mkdir sandbox home: %v", err)
-	}
-	path := WindowsUnelevatedSetupMarkerPath(home)
-	// A truncated body must reset like an unknown schema, not brick every
-	// unelevated command until the file is hand-deleted.
-	if err := os.WriteFile(path, []byte(`{"schemaVersion":1,"appliedPlans":[{"aclPlanHash":"h`), 0o600); err != nil {
-		t.Fatalf("write corrupt marker: %v", err)
-	}
-	marker, err := loadWindowsUnelevatedSetupMarker(home)
-	if err != nil {
-		t.Fatalf("corrupt marker must self-heal, got error: %v", err)
-	}
-	if len(marker.AppliedPlans) != 0 || marker.SchemaVersion != windowsUnelevatedSetupMarkerSchemaVersion {
-		t.Fatalf("corrupt marker must reset to empty current-schema marker, got %+v", marker)
-	}
-	// The healed marker must accept new recordings over the corrupt file.
-	applied := WindowsUnelevatedAppliedPlan{ACLPlanHash: "hash-heal", ACLPlanEntries: 2}
-	if err := recordWindowsUnelevatedAppliedPlan(home, applied); err != nil {
-		t.Fatalf("record over corrupt marker: %v", err)
-	}
-	marker, err = loadWindowsUnelevatedSetupMarker(home)
-	if err != nil {
-		t.Fatalf("reload healed marker: %v", err)
-	}
-	if !marker.contains(applied) {
-		t.Fatalf("healed marker = %+v, want the recorded plan", marker)
-	}
-}
-
 func TestLoadWindowsUnelevatedSetupMarkerResetsUnknownSchema(t *testing.T) {
 	home := filepath.Join(t.TempDir(), ".zero-sandbox")
 	if err := os.MkdirAll(home, 0o700); err != nil {

internal/sessions/append_events_test.go

@@ -1,233 +0,0 @@
-package sessions
-
-import (
-	"encoding/json"
-	"fmt"
-	"reflect"
-	"strings"
-	"sync"
-	"testing"
-	"time"
-)
-
-func TestStoreAppendEventsBatchesSequencesAndMetadata(t *testing.T) {
-	store := NewStore(StoreOptions{RootDir: t.TempDir(), Now: sequenceClock([]time.Time{
-		time.Date(2026, 6, 4, 15, 0, 0, 0, time.UTC),
-		time.Date(2026, 6, 4, 15, 0, 1, 0, time.UTC),
-		time.Date(2026, 6, 4, 15, 0, 2, 0, time.UTC),
-		time.Date(2026, 6, 4, 15, 0, 3, 0, time.UTC),
-	})})
-	session, err := store.Create(CreateInput{SessionID: "batch"})
-	if err != nil {
-		t.Fatalf("Create returned error: %v", err)
-	}
-
-	appended, err := store.AppendEvents(session.SessionID, []AppendEventInput{
-		{Type: EventMessage, Payload: map[string]any{"role": "user", "content": "one"}},
-		{Type: EventToolCall, Payload: map[string]any{"id": "call_1", "name": "read_file"}},
-		{Type: EventToolResult, Payload: map[string]any{"toolCallId": "call_1", "status": "ok"}},
-	})
-	if err != nil {
-		t.Fatalf("AppendEvents returned error: %v", err)
-	}
-	if len(appended) != 3 {
-		t.Fatalf("expected 3 appended events, got %#v", appended)
-	}
-	for index, event := range appended {
-		wantSequence := index + 1
-		if event.Sequence != wantSequence || event.ID != fmt.Sprintf("batch:%d", wantSequence) {
-			t.Fatalf("event identity mismatch at %d: %#v", index, event)
-		}
-	}
-	if appended[0].CreatedAt != "2026-06-04T15:00:01Z" || appended[2].CreatedAt != "2026-06-04T15:00:03Z" {
-		t.Fatalf("unexpected event timestamps: %#v", appended)
-	}
-
-	loaded, err := store.Get(session.SessionID)
-	if err != nil {
-		t.Fatalf("Get returned error: %v", err)
-	}
-	if loaded == nil || loaded.EventCount != 3 || loaded.LastEventType != EventToolResult || loaded.UpdatedAt != appended[2].CreatedAt {
-		t.Fatalf("metadata not updated from final batch event: %#v", loaded)
-	}
-	events, err := store.ReadEvents(session.SessionID)
-	if err != nil {
-		t.Fatalf("ReadEvents returned error: %v", err)
-	}
-	if !reflect.DeepEqual(eventTypesForTest(events), []EventType{EventMessage, EventToolCall, EventToolResult}) {
-		t.Fatalf("unexpected event types: %#v", events)
-	}
-}
-
-func TestStoreAppendEventsEmptyBatchDoesNotRewriteMetadata(t *testing.T) {
-	store := NewStore(StoreOptions{RootDir: t.TempDir(), Now: fixedClock("2026-06-04T15:10:00Z")})
-	session, err := store.Create(CreateInput{SessionID: "empty_batch", Title: "unchanged"})
-	if err != nil {
-		t.Fatalf("Create returned error: %v", err)
-	}
-
-	appended, err := store.AppendEvents(session.SessionID, nil)
-	if err != nil {
-		t.Fatalf("AppendEvents empty returned error: %v", err)
-	}
-	if len(appended) != 0 {
-		t.Fatalf("empty AppendEvents returned %#v", appended)
-	}
-	loaded, err := store.Get(session.SessionID)
-	if err != nil {
-		t.Fatalf("Get returned error: %v", err)
-	}
-	if loaded == nil || !reflect.DeepEqual(*loaded, session) {
-		t.Fatalf("empty AppendEvents rewrote metadata: before=%#v after=%#v", session, loaded)
-	}
-}
-
-func TestStoreAppendEventsInvalidPayloadDoesNotPartiallyAppend(t *testing.T) {
-	store := NewStore(StoreOptions{RootDir: t.TempDir(), Now: fixedClock("2026-06-04T15:20:00Z")})
-	session, err := store.Create(CreateInput{SessionID: "invalid_batch"})
-	if err != nil {
-		t.Fatalf("Create returned error: %v", err)
-	}
-
-	_, err = store.AppendEvents(session.SessionID, []AppendEventInput{
-		{Type: EventMessage, Payload: map[string]any{"content": "valid first"}},
-		{Type: EventMessage, Payload: json.RawMessage(`{"broken"`)},
-	})
-	if err == nil || !strings.Contains(err.Error(), "invalid raw JSON payload") {
-		t.Fatalf("expected invalid raw payload error, got %v", err)
-	}
-	events, err := store.ReadEvents(session.SessionID)
-	if err != nil {
-		t.Fatalf("ReadEvents returned error: %v", err)
-	}
-	if len(events) != 0 {
-		t.Fatalf("invalid batch should not append partial events: %#v", events)
-	}
-	loaded, err := store.Get(session.SessionID)
-	if err != nil {
-		t.Fatalf("Get returned error: %v", err)
-	}
-	if loaded == nil || loaded.EventCount != 0 || loaded.LastEventType != "" {
-		t.Fatalf("invalid batch should not update metadata: %#v", loaded)
-	}
-}
-
-func TestStoreAppendEventsSequencesAfterMetadataLag(t *testing.T) {
-	store := NewStore(StoreOptions{RootDir: t.TempDir(), Now: fixedClock("2026-06-04T15:30:00Z")})
-	session, err := store.Create(CreateInput{SessionID: "lagging"})
-	if err != nil {
-		t.Fatalf("Create returned error: %v", err)
-	}
-	if _, err := store.AppendEvent(session.SessionID, AppendEventInput{Type: EventMessage, Payload: map[string]any{"content": "already durable"}}); err != nil {
-		t.Fatalf("AppendEvent returned error: %v", err)
-	}
-	lagging, err := store.Get(session.SessionID)
-	if err != nil {
-		t.Fatalf("Get returned error: %v", err)
-	}
-	lagging.EventCount = 0
-	lagging.LastEventType = ""
-	if err := store.writeMetadata(*lagging); err != nil {
-		t.Fatalf("writeMetadata returned error: %v", err)
-	}
-
-	appended, err := store.AppendEvents(session.SessionID, []AppendEventInput{
-		{Type: EventToolCall, Payload: map[string]any{"id": "call"}},
-		{Type: EventToolResult, Payload: map[string]any{"toolCallId": "call"}},
-	})
-	if err != nil {
-		t.Fatalf("AppendEvents returned error: %v", err)
-	}
-	if len(appended) != 2 || appended[0].Sequence != 2 || appended[1].Sequence != 3 {
-		t.Fatalf("batch did not sequence after durable log tail: %#v", appended)
-	}
-	loaded, err := store.Get(session.SessionID)
-	if err != nil {
-		t.Fatalf("Get returned error: %v", err)
-	}
-	if loaded == nil || loaded.EventCount != 3 || loaded.LastEventType != EventToolResult {
-		t.Fatalf("metadata not repaired by batch append: %#v", loaded)
-	}
-}
-
-func TestStoreAppendEventsSerializesConcurrentBatches(t *testing.T) {
-	store := NewStore(StoreOptions{RootDir: t.TempDir(), Now: fixedClock("2026-06-04T15:40:00Z")})
-	session, err := store.Create(CreateInput{SessionID: "concurrent_batches"})
-	if err != nil {
-		t.Fatalf("Create returned error: %v", err)
-	}
-
-	const writers = 8
-	const perBatch = 3
-	var wg sync.WaitGroup
-	errs := make(chan error, writers)
-	for writer := 0; writer < writers; writer++ {
-		wg.Add(1)
-		go func(writer int) {
-			defer wg.Done()
-			appended, err := store.AppendEvents(session.SessionID, []AppendEventInput{
-				{Type: EventMessage, Payload: map[string]int{"writer": writer, "index": 0}},
-				{Type: EventMessage, Payload: map[string]int{"writer": writer, "index": 1}},
-				{Type: EventMessage, Payload: map[string]int{"writer": writer, "index": 2}},
-			})
-			if err != nil {
-				errs <- err
-				return
-			}
-			if len(appended) != perBatch {
-				errs <- fmt.Errorf("writer %d appended %d events", writer, len(appended))
-				return
-			}
-			for index := 1; index < len(appended); index++ {
-				if appended[index].Sequence != appended[index-1].Sequence+1 {
-					errs <- fmt.Errorf("writer %d batch was interleaved: %#v", writer, appended)
-					return
-				}
-			}
-			errs <- nil
-		}(writer)
-	}
-	wg.Wait()
-	close(errs)
-	for err := range errs {
-		if err != nil {
-			t.Fatalf("AppendEvents returned error: %v", err)
-		}
-	}
-
-	events, err := store.ReadEvents(session.SessionID)
-	if err != nil {
-		t.Fatalf("ReadEvents returned error: %v", err)
-	}
-	total := writers * perBatch
-	if len(events) != total {
-		t.Fatalf("expected %d events, got %d", total, len(events))
-	}
-	seen := map[int]bool{}
-	for _, event := range events {
-		if seen[event.Sequence] {
-			t.Fatalf("duplicate sequence %d in %#v", event.Sequence, events)
-		}
-		seen[event.Sequence] = true
-	}
-	for sequence := 1; sequence <= total; sequence++ {
-		if !seen[sequence] {
-			t.Fatalf("missing sequence %d in %#v", sequence, events)
-		}
-	}
-	loaded, err := store.Get(session.SessionID)
-	if err != nil {
-		t.Fatalf("Get returned error: %v", err)
-	}
-	if loaded == nil || loaded.EventCount != total || loaded.LastEventType != EventMessage {
-		t.Fatalf("metadata not updated after concurrent batches: %#v", loaded)
-	}
-}
-
-func eventTypesForTest(events []Event) []EventType {
-	types := make([]EventType, 0, len(events))
-	for _, event := range events {
-		types = append(types, event.Type)
-	}
-	return types
-}

internal/sessions/exec_session.go

@@ -160,7 +160,10 @@ func FormatExecPrompt(prompt string, prepared PreparedExec) string {
 	if prepared.Mode == ModeNew || len(prepared.ContextEvents) == 0 {
 		return prompt
 	}
-	events := promptContextEvents(prepared.ContextEvents)
+	events := prepared.ContextEvents
+	if len(events) > 20 {
+		events = events[len(events)-20:]
+	}
 
 	lines := []string{}
 	for _, event := range events {
@@ -184,25 +187,6 @@ func FormatExecPrompt(prompt string, prepared PreparedExec) string {
 	}, "\n")
 }
 
-func promptContextEvents(events []Event) []Event {
-	const maxPromptContextEvents = 80
-
-	filtered := make([]Event, 0, len(events))
-	for _, event := range events {
-		switch event.Type {
-		case EventMessage, EventCompaction, EventSessionFork, EventSessionChild, EventSpecialistStart, EventSpecialistStop, EventError:
-			filtered = append(filtered, event)
-		}
-	}
-	if len(filtered) == 0 {
-		filtered = append(filtered, events...)
-	}
-	if len(filtered) > maxPromptContextEvents {
-		filtered = filtered[len(filtered)-maxPromptContextEvents:]
-	}
-	return filtered
-}
-
 func forkTitle(title string) string {
 	if title == "" {
 		return ""

internal/sessions/replay.go

@@ -71,7 +71,7 @@ type CompactionPayload struct {
 	Truncated                bool       `json:"truncated,omitempty"`
 }
 
-const defaultCompactionPreserveLast = 6
+const defaultCompactionPreserveLast = 8
 const defaultCompactionMaxPromptChars = 8000
 
 func (store *Store) PlanRewind(sessionID string, options RewindOptions) (RewindPlan, error) {

internal/sessions/store.go

@@ -153,11 +153,6 @@ type AppendEventInput struct {
 	Payload any
 }
 
-type preparedAppendEvent struct {
-	Type    EventType
-	Payload json.RawMessage
-}
-
 type RecordSpecInput struct {
 	SpecID              string
 	SpecFilePath        string
@@ -431,7 +426,7 @@ func (store *Store) Fork(parentSessionID string, input ForkInput) (Metadata, err
 	if err != nil {
 		return Metadata{}, err
 	}
-	copyInputs := []AppendEventInput{}
+	copied := 0
 	for _, event := range events {
 		// Do NOT copy usage accounting into the fork. It already counted against the
 		// parent, and a usage report that aggregates the parent and the fork would
@@ -440,12 +435,11 @@ func (store *Store) Fork(parentSessionID string, input ForkInput) (Metadata, err
 		if event.Type == EventUsage {
 			continue
 		}
-		copyInputs = append(copyInputs, AppendEventInput{Type: event.Type, Payload: event.Payload})
+		if _, err := store.AppendEvent(fork.SessionID, AppendEventInput{Type: event.Type, Payload: event.Payload}); err != nil {
+			return Metadata{}, err
+		}
+		copied++
 	}
-	if _, err := store.AppendEvents(fork.SessionID, copyInputs); err != nil {
-		return Metadata{}, err
-	}
-	copied := len(copyInputs)
 	// Copy the parent's content-addressed checkpoint blobs into the fork so the
 	// copied EventSessionCheckpoint events resolve to real blobs and a rewind on
 	// the fork can restore file content (otherwise rewind reads missing blobs
@@ -519,34 +513,19 @@ func (store *Store) RecordSpec(sessionID string, input RecordSpecInput) (Metadat
 }
 
 func (store *Store) AppendEvent(sessionID string, input AppendEventInput) (Event, error) {
-	events, err := store.AppendEvents(sessionID, []AppendEventInput{input})
-	if err != nil {
-		return Event{}, err
-	}
-	return events[0], nil
-}
-
-// AppendEvents appends a batch of events atomically under one session lock and
-// durability pass. The returned events have contiguous sequences in input order.
-// An empty batch is a no-op and does not rewrite metadata.
-func (store *Store) AppendEvents(sessionID string, inputs []AppendEventInput) ([]Event, error) {
 	if !ValidSessionID(sessionID) {
-		return nil, fmt.Errorf("invalid zero session id %q", sessionID)
+		return Event{}, fmt.Errorf("invalid zero session id %q", sessionID)
 	}
-	prepared, err := prepareAppendEventInputs(inputs)
-	if err != nil {
-		return nil, err
-	}
-	if len(prepared) == 0 {
-		return []Event{}, nil
+	if strings.TrimSpace(string(input.Type)) == "" {
+		return Event{}, fmt.Errorf("zero session event type is required")
 	}
 	unlock, err := store.lockSession(sessionID)
 	if err != nil {
-		return nil, err
+		return Event{}, err
 	}
 	defer unlock()
 
-	return store.appendPreparedEventsLocked(sessionID, prepared)
+	return store.appendEventLocked(sessionID, input)
 }
 
 // AppendEventUnlessExists appends input only when exists(currentEvents) is false,
@@ -593,26 +572,13 @@ func (store *Store) AppendEventUnlessExists(sessionID string, input AppendEventI
 // the single lock they already hold, instead of re-locking (which would deadlock
 // on the non-reentrant in-process mutex).
 func (store *Store) appendEventLocked(sessionID string, input AppendEventInput) (Event, error) {
-	prepared, err := prepareAppendEventInputs([]AppendEventInput{input})
-	if err != nil {
-		return Event{}, err
-	}
-	events, err := store.appendPreparedEventsLocked(sessionID, prepared)
-	if err != nil {
-		return Event{}, err
-	}
-	return events[0], nil
-}
-
-// appendPreparedEventsLocked appends pre-validated events WITHOUT acquiring the
-// session lock. The caller MUST already hold store.lockSession(sessionID).
-func (store *Store) appendPreparedEventsLocked(sessionID string, inputs []preparedAppendEvent) ([]Event, error) {
-	if len(inputs) == 0 {
-		return []Event{}, nil
-	}
 	session, err := store.readMetadata(sessionID)
 	if err != nil {
-		return nil, err
+		return Event{}, err
+	}
+	payload, err := rawPayload(input.Payload)
+	if err != nil {
+		return Event{}, err
 	}
 	sequence := session.EventCount + 1
 	// The events log is the source of truth for sequencing. metadata.EventCount is
@@ -624,54 +590,46 @@ func (store *Store) appendPreparedEventsLocked(sessionID string, inputs []prepar
 	if logSeq, err := store.lastEventSequence(sessionID); err == nil && logSeq >= sequence {
 		sequence = logSeq + 1
 	}
-	events := make([]Event, 0, len(inputs))
-	var batch bytes.Buffer
-	for index, input := range inputs {
-		timestamp := store.timestamp()
-		event := Event{
-			ID:        fmt.Sprintf("%s:%d", sessionID, sequence+index),
-			SessionID: sessionID,
-			Sequence:  sequence + index,
-			Type:      input.Type,
-			CreatedAt: timestamp,
-			Payload:   input.Payload,
-		}
-		data, err := json.Marshal(event)
-		if err != nil {
-			return nil, fmt.Errorf("encode zero session event: %w", err)
-		}
-		batch.Write(data)
-		batch.WriteByte('\n')
-		events = append(events, event)
+	timestamp := store.timestamp()
+	event := Event{
+		ID:        fmt.Sprintf("%s:%d", sessionID, sequence),
+		SessionID: sessionID,
+		Sequence:  sequence,
+		Type:      input.Type,
+		CreatedAt: timestamp,
+		Payload:   payload,
+	}
+	data, err := json.Marshal(event)
+	if err != nil {
+		return Event{}, fmt.Errorf("encode zero session event: %w", err)
 	}
 	file, err := os.OpenFile(store.eventsPath(sessionID), os.O_WRONLY|os.O_APPEND|os.O_CREATE, 0o600)
 	if err != nil {
-		return nil, fmt.Errorf("append zero session event: %w", err)
+		return Event{}, fmt.Errorf("append zero session event: %w", err)
 	}
-	if _, err := file.Write(batch.Bytes()); err != nil {
+	if _, err := file.Write(append(data, '\n')); err != nil {
 		_ = file.Close()
-		return nil, fmt.Errorf("append zero session event: %w", err)
+		return Event{}, fmt.Errorf("append zero session event: %w", err)
 	}
-	// fsync the events before reporting success: the derived metadata.json IS
+	// fsync the event before reporting success: the derived metadata.json IS
 	// fsync'd (writeMetadata), so without this a crash after the metadata flush
 	// but before the events.jsonl page reaches disk leaves EventCount ahead of the
-	// durable log — silently losing just-appended events (incl. checkpoints
+	// durable log — silently losing the just-appended event (incl. the checkpoint
 	// that /rewind targets). Make the log at least as durable as its metadata. (AUDIT-M12)
 	if err := file.Sync(); err != nil {
 		_ = file.Close()
-		return nil, fmt.Errorf("sync zero session event: %w", err)
+		return Event{}, fmt.Errorf("sync zero session event: %w", err)
 	}
 	if err := file.Close(); err != nil {
-		return nil, fmt.Errorf("close zero session event file: %w", err)
+		return Event{}, fmt.Errorf("close zero session event file: %w", err)
 	}
-	last := events[len(events)-1]
-	session.UpdatedAt = last.CreatedAt
-	session.EventCount = last.Sequence
-	session.LastEventType = last.Type
+	session.UpdatedAt = timestamp
+	session.EventCount = sequence
+	session.LastEventType = input.Type
 	if err := store.writeMetadata(session); err != nil {
-		return nil, err
+		return Event{}, err
 	}
-	return events, nil
+	return event, nil
 }
 
 // UpdateTitle replaces a session's Title and returns the updated metadata. It is
@@ -1006,24 +964,6 @@ func rawPayload(payload any) (json.RawMessage, error) {
 	return data, nil
 }
 
-func prepareAppendEventInputs(inputs []AppendEventInput) ([]preparedAppendEvent, error) {
-	prepared := make([]preparedAppendEvent, 0, len(inputs))
-	for _, input := range inputs {
-		if strings.TrimSpace(string(input.Type)) == "" {
-			return nil, fmt.Errorf("zero session event type is required")
-		}
-		payload, err := rawPayload(input.Payload)
-		if err != nil {
-			return nil, err
-		}
-		prepared = append(prepared, preparedAppendEvent{
-			Type:    input.Type,
-			Payload: payload,
-		})
-	}
-	return prepared, nil
-}
-
 func envValue(env map[string]string, key string) string {
 	if env != nil {
 		return env[key]

internal/sessions/store_test.go

@@ -555,91 +555,6 @@ func TestPrepareExecSessionResolvesResumeAndFork(t *testing.T) {
 	}
 }
 
-func TestFormatExecPromptKeepsConversationMessagesWhenNoisyEventsFollow(t *testing.T) {
-	events := []Event{
-		{Sequence: 1, Type: EventMessage, Payload: json.RawMessage(`{"role":"user","content":"first user request"}`)},
-		{Sequence: 2, Type: EventMessage, Payload: json.RawMessage(`{"role":"assistant","content":"first assistant answer"}`)},
-	}
-	for sequence := 3; sequence <= 45; sequence++ {
-		events = append(events, Event{Sequence: sequence, Type: EventToolResult, Payload: json.RawMessage(`{"name":"read_file","output":"noisy tool result"}`)})
-	}
-	events = append(events, Event{Sequence: 46, Type: EventMessage, Payload: json.RawMessage(`{"role":"user","content":"latest user request"}`)})
-
-	prompt := FormatExecPrompt("continue", PreparedExec{
-		Mode:          ModeResume,
-		Session:       Metadata{SessionID: "session-with-noise"},
-		ContextEvents: events,
-	})
-
-	for _, want := range []string{"first user request", "first assistant answer", "latest user request", "Current user request:", "continue"} {
-		if !strings.Contains(prompt, want) {
-			t.Fatalf("expected prompt to contain %q, got %q", want, prompt)
-		}
-	}
-	if strings.Contains(prompt, "noisy tool result") {
-		t.Fatalf("expected prompt to omit noisy non-conversation events, got %q", prompt)
-	}
-}
-
-func TestFormatExecPromptTruncatesConversationMessagesAfterFilteringNoise(t *testing.T) {
-	events := make([]Event, 0, 100)
-	for sequence := 1; sequence <= 85; sequence++ {
-		events = append(events, Event{
-			Sequence: sequence,
-			Type:     EventMessage,
-			Payload:  json.RawMessage(fmt.Sprintf(`{"role":"user","content":"conversation message %03d"}`, sequence)),
-		})
-		if sequence%10 == 0 {
-			events = append(events, Event{
-				Sequence: 1000 + sequence,
-				Type:     EventToolResult,
-				Payload:  json.RawMessage(fmt.Sprintf(`{"name":"read_file","output":"noisy tool result %03d"}`, sequence)),
-			})
-		}
-	}
-	events = append(events, Event{
-		Sequence: 2000,
-		Type:     EventToolResult,
-		Payload:  json.RawMessage(`{"name":"bash","output":"trailing noisy tool result"}`),
-	})
-
-	contextEvents := promptContextEvents(events)
-	if len(contextEvents) != 80 {
-		t.Fatalf("expected prompt context to keep 80 events, got %d", len(contextEvents))
-	}
-	if contextEvents[0].Sequence != 6 || contextEvents[len(contextEvents)-1].Sequence != 85 {
-		t.Fatalf("expected prompt context to keep message sequences 6-85, got first=%d last=%d", contextEvents[0].Sequence, contextEvents[len(contextEvents)-1].Sequence)
-	}
-
-	prompt := FormatExecPrompt("continue", PreparedExec{
-		Mode:          ModeResume,
-		Session:       Metadata{SessionID: "long-session-with-noise"},
-		ContextEvents: events,
-	})
-
-	if got, want := strings.Count(prompt, "- #"), len(contextEvents); got != want {
-		t.Fatalf("expected prompt to contain %d context event lines, got %d in %q", want, got, prompt)
-	}
-	for _, want := range []string{"conversation message 006", "conversation message 085", "Current user request:", "continue"} {
-		if !strings.Contains(prompt, want) {
-			t.Fatalf("expected prompt to contain %q, got %q", want, prompt)
-		}
-	}
-	for _, unwanted := range []string{
-		"conversation message 001",
-		"conversation message 002",
-		"conversation message 003",
-		"conversation message 004",
-		"conversation message 005",
-		"noisy tool result",
-		"trailing noisy tool result",
-	} {
-		if strings.Contains(prompt, unwanted) {
-			t.Fatalf("expected prompt to omit %q, got %q", unwanted, prompt)
-		}
-	}
-}
-
 func TestPrepareExecPersistsSpecialistMetadataForNewSession(t *testing.T) {
 	store := NewStore(StoreOptions{RootDir: t.TempDir(), Now: fixedClock("2026-06-04T14:30:00Z")})
 

internal/specialist/exec.go

@@ -25,7 +25,6 @@ import (
 const (
 	sessionTagSpecialist     = "specialist"
 	promptFileThresholdBytes = 4 * 1024
-	maxSpecialistDepth       = 8 // hard cap to prevent infinite recursion/resource exhaustion via Task
 )
 
 const SessionTagSpecialist = sessionTagSpecialist
@@ -219,13 +218,6 @@ func (executor Executor) Run(ctx context.Context, params TaskParameters, options
 	if options.CurrentDepth < 0 {
 		return ExecResult{}, fmt.Errorf("current depth cannot be negative")
 	}
-	// >= (not >): this Run call spawns a CHILD at options.CurrentDepth+1, so a
-	// parent already AT the cap must still be rejected here rather than being
-	// allowed to launch one more level before the child's own next call trips
-	// the guard.
-	if options.CurrentDepth >= maxSpecialistDepth {
-		return ExecResult{}, fmt.Errorf("spawning a specialist at depth %d would exceed maximum nesting depth %d", options.CurrentDepth+1, maxSpecialistDepth)
-	}
 	if strings.TrimSpace(params.Prompt) == "" {
 		return ExecResult{}, fmt.Errorf("specialist prompt is required")
 	}

internal/specialist/exec_test.go

@@ -1,7 +1,6 @@
 package specialist
 
 import (
-	"context"
 	"os"
 	"path/filepath"
 	"reflect"
@@ -337,39 +336,6 @@ func TestBuildArgsRejectsInvalidInputs(t *testing.T) {
 	}
 }
 
-func TestRunRejectsDepthExceedingMax(t *testing.T) {
-	_, err := (Executor{}).Run(context.Background(), TaskParameters{
-		Prompt: "hi",
-	}, TaskRunOptions{CurrentDepth: maxSpecialistDepth + 1})
-	if err == nil || !strings.Contains(err.Error(), "depth") {
-		t.Fatalf("Run error = %v, want depth error", err)
-	}
-}
-
-// TestRunRejectsDepthAtMax covers the boundary: a parent already AT the cap
-// must be rejected too, since this Run call would launch a child one level
-// past it (--depth CurrentDepth+1). Only checking ">" here would let that
-// child start before the guard ever caught it. The guard sits before the
-// fresh/resume branch in Run, so both call shapes must be proven to reject
-// here rather than falling through to runFresh/runResume.
-func TestRunRejectsDepthAtMax(t *testing.T) {
-	tests := []struct {
-		name   string
-		params TaskParameters
-	}{
-		{name: "fresh", params: TaskParameters{Prompt: "hi"}},
-		{name: "resume", params: TaskParameters{Prompt: "hi", Resume: "child_session"}},
-	}
-	for _, tc := range tests {
-		t.Run(tc.name, func(t *testing.T) {
-			_, err := (Executor{}).Run(context.Background(), tc.params, TaskRunOptions{CurrentDepth: maxSpecialistDepth})
-			if err == nil || !strings.Contains(err.Error(), "depth") {
-				t.Fatalf("Run error = %v, want depth error", err)
-			}
-		})
-	}
-}
-
 func TestBuildArgsRejectsInvalidSessionIDs(t *testing.T) {
 	_, err := (Executor{NewSessionID: func() (string, error) { return "../escape", nil }}).BuildArgs(BuildArgsInput{
 		Prompt: "hi",

internal/streamjson/streamjson.go

@@ -21,7 +21,6 @@ type EventType string
 const (
 	EventRunStart           EventType = "run_start"
 	EventText               EventType = "text"
-	EventReasoning          EventType = "reasoning"
 	EventToolCall           EventType = "tool_call"
 	EventPermission         EventType = "permission"
 	EventPermissionRequest  EventType = "permission_request"