feat(graph): /graph ships on by default — end the KIGI_GRAPH gray release

resolve_graph() read only the KIGI_GRAPH env var with default(false)
(plan.md G0 gate), so /graph existed solely on machines whose environment
exported the dev flag — which presented as '/graph is missing on
Windows'. There was never any platform-conditional code: the Mac worked
because the dev env var was set there.

Default is now true (matching /goal's shipped state); KIGI_GRAPH=0
remains the off-switch, and availability still requires the goal harness
(BuiltinGate::Graph). AGENTS.md updated; new test pins fresh-install-on
plus env-zero-off.

Verified: kigi-shell 5262 + kigi-tui 6874 tests green, clippy clean.

.github/workflows/warm-cache.yml

@@ -0,0 +1,85 @@
+name: Warm build cache
+
+# Release builds run on TAG refs, and GitHub Actions cache isolation only
+# lets a run restore caches created on its OWN ref or the DEFAULT branch.
+# No workflow ran on `main`, so every release compiled the whole workspace
+# cold on all five targets (~50 min wall clock, gated by Windows). This
+# workflow builds the same `release-dist` profile on `main` so tag builds
+# restore a warm default-branch cache.
+#
+# Triggers: dependency-affecting pushes to main (each release's version-bump
+# commit warms the cache for the NEXT release), a weekly refresh so the
+# cache never hits GitHub's 7-day unused-eviction, and manual dispatch.
+#
+# The setup steps mirror release.yml's build job (toolchain, target,
+# dotslash/protoc, rust-cache key) — keep them in lockstep, or the cache
+# key won't match and releases go back to cold builds.
+
+on:
+  push:
+    branches: ["main"]
+    paths:
+      - "Cargo.lock"
+      - "Cargo.toml"
+      - "rust-toolchain.toml"
+      - ".github/workflows/warm-cache.yml"
+  schedule:
+    - cron: "17 5 * * 1"
+  workflow_dispatch:
+
+permissions:
+  contents: read
+
+env:
+  CARGO_TERM_COLOR: always
+
+concurrency:
+  group: warm-cache
+  cancel-in-progress: true
+
+jobs:
+  warm:
+    name: warm (${{ matrix.target }})
+    strategy:
+      fail-fast: false
+      matrix:
+        include:
+          - target: aarch64-apple-darwin
+            os: macos-14
+          - target: x86_64-apple-darwin
+            os: macos-14
+          - target: x86_64-unknown-linux-gnu
+            os: ubuntu-24.04
+          - target: aarch64-unknown-linux-gnu
+            os: ubuntu-24.04-arm
+          - target: x86_64-pc-windows-msvc
+            os: windows-2022
+    runs-on: ${{ matrix.os }}
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Install toolchain (rust-toolchain.toml)
+        run: rustup show
+
+      - name: Add build target
+        run: rustup target add ${{ matrix.target }}
+
+      - name: Install dotslash (protoc launcher)
+        run: cargo install dotslash --locked
+
+      - name: Install protoc (Windows PATH fallback)
+        if: runner.os == 'Windows'
+        shell: pwsh
+        run: |
+          $url = "https://github.com/protocolbuffers/protobuf/releases/download/v29.3/protoc-29.3-win64.zip"
+          Invoke-WebRequest -Uri $url -OutFile protoc.zip
+          Expand-Archive protoc.zip -DestinationPath "$env:USERPROFILE\protoc"
+          Add-Content $env:GITHUB_PATH "$env:USERPROFILE\protoc\bin"
+
+      # Same key as release.yml so tag builds restore this cache verbatim.
+      - uses: Swatinem/rust-cache@v2
+        with:
+          key: ${{ matrix.target }}
+
+      - name: Build kigi (release-dist)
+        run: cargo build --profile release-dist -p kigi-bin --locked --target ${{ matrix.target }}

AGENTS.md

@@ -32,9 +32,19 @@ import) or any `KIMI_*` env var.
 - **Observability is local**: `kigi-log` (unified session log, `--debug`
   firehose, subsystem file logs, opt-in instrumentation) writes under
   `~/.kigi` only. Its zero-network property is a contract.
+- **Atomic file replace goes through `util::fs::replace_file`** (tmp+rename
+  commit step; async callers wrap in `spawn_blocking`). Never inline a bare
+  `fs::rename` replace: Windows `MoveFileExW(REPLACE_EXISTING)` fails with a
+  sharing violation while AV/indexer/cloud-sync holds the destination open —
+  the "persists on macOS, silently doesn't on Windows" class (a /model
+  switch that never stuck). Plain rename stays correct only for true moves
+  whose destination doesn't pre-exist (worktree-pool markers, corrupt-file
+  backups). Write failures must at least `warn!` — never `let _ =`.
 - The root `Cargo.toml` is hand-maintained (upstream's generator is not in
   this repo). Members sorted; versions inherited from
-  `workspace.package.version` (0.1.0).
+  `workspace.package.version` — the single source of truth for the release
+  version (`kigi_version::VERSION` derives from it; the release workflow
+  gates the `v*` tag against it).
 
 ## Layout
 
@@ -79,8 +89,9 @@ node as one ordinary goal — the agentic loop lives INSIDE the node; the
 edges stay deterministic Rust. The harness appends a terminal
 `gn-final` verification node depending on every planner node.
 
-- Feature flag `KIGI_GRAPH=1` (default off); availability additionally
+- Enabled by default (`KIGI_GRAPH=0` is the off-switch; the G0 gray
-  requires the goal harness (`BuiltinGate::Graph`).
+  release is over); availability additionally requires the goal harness
+  (`BuiltinGate::Graph`).
 - Key modules (kigi-shell): `session/graph_tracker.rs` (pure state
   machine; reuses `GoalStatus`/`GoalPhase`/`GoalPauseReason`),
   `session/graph_plan.rs` (planner-JSON contract + validation + fnv id

Cargo.lock

@@ -5442,7 +5442,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-acp-lib"
-version = "0.1.4"
+version = "0.1.5"
 dependencies = [
  "agent-client-protocol",
  "async-trait",
@@ -5456,7 +5456,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-agent"
-version = "0.1.4"
+version = "0.1.5"
 dependencies = [
  "chrono",
  "dirs 6.0.0",
@@ -5486,7 +5486,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-agent-lifecycle"
-version = "0.1.4"
+version = "0.1.5"
 dependencies = [
  "async-trait",
  "tokio",
@@ -5495,7 +5495,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-auth"
-version = "0.1.4"
+version = "0.1.5"
 dependencies = [
  "async-trait",
  "http 1.4.2",
@@ -5508,7 +5508,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-bin"
-version = "0.1.4"
+version = "0.1.5"
 dependencies = [
  "anyhow",
  "clap",
@@ -5543,7 +5543,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-chat-state"
-version = "0.1.4"
+version = "0.1.5"
 dependencies = [
  "indexmap",
  "kigi-compaction",
@@ -5560,7 +5560,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-codebase-graph"
-version = "0.1.4"
+version = "0.1.5"
 dependencies = [
  "ahash",
  "clap",
@@ -5596,7 +5596,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-compaction"
-version = "0.1.4"
+version = "0.1.5"
 dependencies = [
  "anyhow",
  "async-trait",
@@ -5609,7 +5609,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-config"
-version = "0.1.4"
+version = "0.1.5"
 dependencies = [
  "base64",
  "blake3",
@@ -5632,7 +5632,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-config-types"
-version = "0.1.4"
+version = "0.1.5"
 dependencies = [
  "agent-client-protocol",
  "indexmap",
@@ -5646,7 +5646,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-crash-handler"
-version = "0.1.4"
+version = "0.1.5"
 dependencies = [
  "backtrace",
  "libc",
@@ -5657,7 +5657,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-env"
-version = "0.1.4"
+version = "0.1.5"
 dependencies = [
  "tracing",
  "url",
@@ -5665,7 +5665,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-fast-worktree"
-version = "0.1.4"
+version = "0.1.5"
 dependencies = [
  "anyhow",
  "bytes",
@@ -5697,7 +5697,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-file-utils"
-version = "0.1.4"
+version = "0.1.5"
 dependencies = [
  "anyhow",
  "aws-config",
@@ -5721,7 +5721,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-fsnotify"
-version = "0.1.4"
+version = "0.1.5"
 dependencies = [
  "criterion",
  "dunce",
@@ -5742,7 +5742,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-gix-status"
-version = "0.1.4"
+version = "0.1.5"
 dependencies = [
  "gix",
  "kigi-test-utils",
@@ -5752,7 +5752,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-hooks"
-version = "0.1.4"
+version = "0.1.5"
 dependencies = [
  "fastrand",
  "kigi-config",
@@ -5771,7 +5771,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-hooks-plugins-types"
-version = "0.1.4"
+version = "0.1.5"
 dependencies = [
  "serde",
  "serde_json",
@@ -5779,7 +5779,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-http"
-version = "0.1.4"
+version = "0.1.5"
 dependencies = [
  "kigi-auth",
  "kigi-log",
@@ -5794,7 +5794,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-hunk-tracker"
-version = "0.1.4"
+version = "0.1.5"
 dependencies = [
  "chrono",
  "dunce",
@@ -5815,14 +5815,14 @@ dependencies = [
 
 [[package]]
 name = "kigi-interjection-core"
-version = "0.1.4"
+version = "0.1.5"
 dependencies = [
  "serde",
 ]
 
 [[package]]
 name = "kigi-log"
-version = "0.1.4"
+version = "0.1.5"
 dependencies = [
  "anyhow",
  "chrono",
@@ -5840,7 +5840,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-markdown"
-version = "0.1.4"
+version = "0.1.5"
 dependencies = [
  "anstyle",
  "anstyle-lossy",
@@ -5864,14 +5864,14 @@ dependencies = [
 
 [[package]]
 name = "kigi-markdown-core"
-version = "0.1.4"
+version = "0.1.5"
 dependencies = [
  "pulldown-cmark",
 ]
 
 [[package]]
 name = "kigi-mcp"
-version = "0.1.4"
+version = "0.1.5"
 dependencies = [
  "agent-client-protocol",
  "async-trait",
@@ -5908,7 +5908,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-memory"
-version = "0.1.4"
+version = "0.1.5"
 dependencies = [
  "anyhow",
  "arc-swap",
@@ -5942,7 +5942,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-mermaid"
-version = "0.1.4"
+version = "0.1.5"
 dependencies = [
  "fontdb",
  "image",
@@ -5960,7 +5960,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-models"
-version = "0.1.4"
+version = "0.1.5"
 dependencies = [
  "kigi-env",
  "serde",
@@ -5970,7 +5970,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-pager-minimal"
-version = "0.1.4"
+version = "0.1.5"
 dependencies = [
  "chrono",
  "crossterm",
@@ -5987,7 +5987,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-pager-pty-harness"
-version = "0.1.4"
+version = "0.1.5"
 dependencies = [
  "alacritty_terminal",
  "anyhow",
@@ -6012,7 +6012,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-pager-render"
-version = "0.1.4"
+version = "0.1.5"
 dependencies = [
  "agent-client-protocol",
  "anstyle",
@@ -6064,7 +6064,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-paths"
-version = "0.1.4"
+version = "0.1.5"
 dependencies = [
  "camino",
  "serde",
@@ -6074,7 +6074,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-prompt-queue"
-version = "0.1.4"
+version = "0.1.5"
 dependencies = [
  "serde",
  "serde_json",
@@ -6082,7 +6082,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-proto-build"
-version = "0.1.4"
+version = "0.1.5"
 dependencies = [
  "anyhow",
  "pbjson-build",
@@ -6093,7 +6093,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-ratatui-inline"
-version = "0.1.4"
+version = "0.1.5"
 dependencies = [
  "ansi-width",
  "anstyle-parse 0.2.7",
@@ -6110,7 +6110,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-ratatui-textarea"
-version = "0.1.4"
+version = "0.1.5"
 dependencies = [
  "arboard",
  "chrono",
@@ -6131,7 +6131,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-sampler"
-version = "0.1.4"
+version = "0.1.5"
 dependencies = [
  "async-openai",
  "async-stream",
@@ -6154,7 +6154,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-sampling-types"
-version = "0.1.4"
+version = "0.1.5"
 dependencies = [
  "assert_matches",
  "async-openai",
@@ -6171,7 +6171,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-sandbox"
-version = "0.1.4"
+version = "0.1.5"
 dependencies = [
  "anyhow",
  "chrono",
@@ -6192,7 +6192,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-secrets"
-version = "0.1.4"
+version = "0.1.5"
 dependencies = [
  "regex",
  "serde_json",
@@ -6230,7 +6230,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-shell"
-version = "0.1.4"
+version = "0.1.5"
 dependencies = [
  "agent-client-protocol",
  "anyhow",
@@ -6367,7 +6367,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-shell-base"
-version = "0.1.4"
+version = "0.1.5"
 dependencies = [
  "anyhow",
  "chrono",
@@ -6392,7 +6392,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-sqlite-journal"
-version = "0.1.4"
+version = "0.1.5"
 dependencies = [
  "libc",
  "rusqlite",
@@ -6403,7 +6403,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-subagent-resolution"
-version = "0.1.4"
+version = "0.1.5"
 dependencies = [
  "kigi-sampling-types",
  "kigi-tool-types",
@@ -6418,7 +6418,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-system-power"
-version = "0.1.4"
+version = "0.1.5"
 dependencies = [
  "windows-sys 0.59.0",
  "zbus",
@@ -6426,7 +6426,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-test-support"
-version = "0.1.4"
+version = "0.1.5"
 dependencies = [
  "agent-client-protocol",
  "anyhow",
@@ -6448,7 +6448,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-test-utils"
-version = "0.1.4"
+version = "0.1.5"
 dependencies = [
  "runfiles",
  "tracing",
@@ -6457,11 +6457,11 @@ dependencies = [
 
 [[package]]
 name = "kigi-token-estimation"
-version = "0.1.4"
+version = "0.1.5"
 
 [[package]]
 name = "kigi-tool-protocol"
-version = "0.1.4"
+version = "0.1.5"
 dependencies = [
  "kigi-tool-types",
  "serde",
@@ -6472,7 +6472,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-tool-runtime"
-version = "0.1.4"
+version = "0.1.5"
 dependencies = [
  "anyhow",
  "async-trait",
@@ -6490,7 +6490,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-tool-types"
-version = "0.1.4"
+version = "0.1.5"
 dependencies = [
  "minijinja",
  "schemars 1.2.1",
@@ -6500,7 +6500,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-tools"
-version = "0.1.4"
+version = "0.1.5"
 dependencies = [
  "anyhow",
  "arc-swap",
@@ -6577,7 +6577,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-tools-api"
-version = "0.1.4"
+version = "0.1.5"
 dependencies = [
  "kigi-proto-build",
  "kigi-tool-protocol",
@@ -6590,11 +6590,11 @@ dependencies = [
 
 [[package]]
 name = "kigi-tracing-macros"
-version = "0.1.4"
+version = "0.1.5"
 
 [[package]]
 name = "kigi-tty-utils"
-version = "0.1.4"
+version = "0.1.5"
 dependencies = [
  "libc",
  "nix 0.30.1",
@@ -6604,7 +6604,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-tui"
-version = "0.1.4"
+version = "0.1.5"
 dependencies = [
  "agent-client-protocol",
  "ansi-to-tui",
@@ -6691,7 +6691,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-update"
-version = "0.1.4"
+version = "0.1.5"
 dependencies = [
  "anyhow",
  "dunce",
@@ -6720,14 +6720,14 @@ dependencies = [
 
 [[package]]
 name = "kigi-version"
-version = "0.1.4"
+version = "0.1.5"
 dependencies = [
  "semver",
 ]
 
 [[package]]
 name = "kigi-workspace"
-version = "0.1.4"
+version = "0.1.5"
 dependencies = [
  "agent-client-protocol",
  "anyhow",
@@ -6806,7 +6806,7 @@ dependencies = [
 
 [[package]]
 name = "kigi-workspace-types"
-version = "0.1.4"
+version = "0.1.5"
 dependencies = [
  "base64",
  "chrono",
@@ -8840,7 +8840,7 @@ dependencies = [
 
 [[package]]
 name = "ptyctl"
-version = "0.1.4"
+version = "0.1.5"
 dependencies = [
  "alacritty_terminal",
  "anyhow",
@@ -8858,7 +8858,7 @@ dependencies = [
 
 [[package]]
 name = "ptyctl-cli"
-version = "0.1.4"
+version = "0.1.5"
 dependencies = [
  "anyhow",
  "axum",

Cargo.toml

@@ -76,7 +76,7 @@ members = [
 ]
 
 [workspace.package]
-version = "0.1.4"
+version = "0.1.5"
 edition = "2024"
 license = "Apache-2.0"
 

crates/codegen/kigi-shell-base/src/util/fs.rs

@@ -0,0 +1,87 @@
+//! Filesystem primitives shared across the shell.
+
+use std::io;
+use std::path::Path;
+
+/// Replace `dest` with `tmp` — the commit step of every tmp+rename atomic
+/// write in the product. This is the ONE place that knows how to make that
+/// commit stick on Windows; call sites must never inline a bare
+/// `fs::rename` replace again.
+///
+/// Unix `rename(2)` replaces atomically and needs no help. Windows
+/// `MoveFileExW(REPLACE_EXISTING)` fails with a sharing violation while
+/// ANOTHER process (antivirus scanner, search indexer, cloud sync) holds
+/// `dest` open — the classic "persists on macOS, silently doesn't on
+/// Windows" failure (a model switch that never sticks, a stale models
+/// cache). On Windows a failed rename therefore deletes the destination
+/// first (the pattern `auth/storage.rs` shipped first) and retries with two
+/// short back-offs for scanners that hold the file for a few milliseconds.
+///
+/// On final failure the tmp file is removed (no litter) and the error is
+/// returned — callers decide severity, but MUST at least log it (errors
+/// never pass silently).
+pub fn replace_file(tmp: &Path, dest: &Path) -> io::Result<()> {
+    let result = replace_file_inner(tmp, dest);
+    if result.is_err() {
+        let _ = std::fs::remove_file(tmp);
+    }
+    result
+}
+
+#[cfg(not(windows))]
+fn replace_file_inner(tmp: &Path, dest: &Path) -> io::Result<()> {
+    std::fs::rename(tmp, dest)
+}
+
+#[cfg(windows)]
+fn replace_file_inner(tmp: &Path, dest: &Path) -> io::Result<()> {
+    let mut last = match std::fs::rename(tmp, dest) {
+        Ok(()) => return Ok(()),
+        Err(e) => e,
+    };
+    for backoff_ms in [0u64, 10, 50] {
+        if backoff_ms > 0 {
+            std::thread::sleep(std::time::Duration::from_millis(backoff_ms));
+        }
+        // Delete-first: marks an open-with-delete-sharing file for deletion
+        // and clears the way for a plain rename; harmless when absent.
+        let _ = std::fs::remove_file(dest);
+        match std::fs::rename(tmp, dest) {
+            Ok(()) => return Ok(()),
+            Err(e) => last = e,
+        }
+    }
+    Err(last)
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    /// The common contract on every platform: replace over an existing
+    /// destination, create a missing one, and error (cleaning the tmp)
+    /// when the tmp itself is missing.
+    #[test]
+    fn replace_file_commits_and_cleans_up() {
+        let dir = tempfile::tempdir().expect("tempdir");
+        let dest = dir.path().join("target.json");
+        let tmp = dir.path().join("target.json.tmp");
+
+        // Create-missing.
+        std::fs::write(&tmp, b"v1").unwrap();
+        replace_file(&tmp, &dest).expect("create");
+        assert_eq!(std::fs::read(&dest).unwrap(), b"v1");
+        assert!(!tmp.exists(), "tmp must be consumed");
+
+        // Replace-existing.
+        std::fs::write(&tmp, b"v2").unwrap();
+        replace_file(&tmp, &dest).expect("replace");
+        assert_eq!(std::fs::read(&dest).unwrap(), b"v2");
+        assert!(!tmp.exists());
+
+        // Missing tmp → error, dest untouched.
+        let err = replace_file(&tmp, &dest).expect_err("missing tmp must fail");
+        assert_eq!(err.kind(), io::ErrorKind::NotFound);
+        assert_eq!(std::fs::read(&dest).unwrap(), b"v2");
+    }
+}

crates/codegen/kigi-shell-base/src/util/mod.rs

@@ -1,4 +1,5 @@
 pub mod event_id;
+pub mod fs;
 pub mod kigi_home;
 pub mod secure_file;
 pub mod tips;

crates/codegen/kigi-shell/build.rs

@@ -109,21 +109,43 @@ fn main() -> Result<(), Box<dyn std::error::Error>> {
         t = asset_triple
     );
 
+    // Transient CDN hiccups (502/503/timeouts) are retried with backoff: a
+    // single flaky response must not kill a ~50-minute release build (it
+    // did — the v0.1.5 tag build failed on one 502). Genuine failures
+    // (404, offline) still error out with the offline-build hint.
     let bytes: Vec<u8> = {
-        let resp = reqwest::blocking::get(&url).map_err(|e| {
+        let mut last_err = String::new();
-            format!(
+        let mut bytes = None;
-                "Failed to download ripgrep: {}\nSet KIGI_SHELL_BUNDLE_RG_PATH to a local rg for offline builds.",
+        for (attempt, backoff_secs) in [0u64, 2, 8].into_iter().enumerate() {
-                e
+            if backoff_secs > 0 {
-            )
+                std::thread::sleep(std::time::Duration::from_secs(backoff_secs));
-        })?;
+            }
-        if !resp.status().is_success() {
+            match reqwest::blocking::get(&url) {
-            return Err(format!(
+                Ok(resp) if resp.status().is_success() => match resp.bytes() {
-                "HTTP {} downloading ripgrep. Set KIGI_SHELL_BUNDLE_RG_PATH for offline builds.",
+                    Ok(b) => {
-                resp.status()
+                        bytes = Some(b.to_vec());
-            )
+                        break;
-            .into());
+                    }
+                    Err(e) => last_err = format!("reading ripgrep body: {e}"),
+                },
+                Ok(resp) => {
+                    let status = resp.status();
+                    last_err = format!("HTTP {status} downloading ripgrep");
+                    // Only server-side/transient statuses are worth retrying.
+                    if !(status.is_server_error() || status.as_u16() == 429) {
+                        break;
+                    }
+                }
+                Err(e) => last_err = format!("Failed to download ripgrep: {e}"),
+            }
+            println!(
+                "cargo:warning=ripgrep download attempt {} failed: {last_err}",
+                attempt + 1
+            );
         }
-        resp.bytes()?.to_vec()
+        bytes.ok_or_else(|| {
+            format!("{last_err}. Set KIGI_SHELL_BUNDLE_RG_PATH for offline builds.")
+        })?
     };
 
     let gz = flate2::read::GzDecoder::new(&bytes[..]);

crates/codegen/kigi-shell/src/active_sessions.rs

@@ -170,9 +170,7 @@ fn write_data_file_atomic(
     let json = serde_json::to_string_pretty(sessions)
         .map_err(|e| io::Error::new(io::ErrorKind::InvalidData, e))?;
     fs::write(tmp_path, json.as_bytes())?;
-    fs::rename(tmp_path, data_path).inspect_err(|_| {
+    crate::util::fs::replace_file(tmp_path, data_path)
-        let _ = fs::remove_file(tmp_path);
-    })
 }
 
 fn is_pid_alive(pid: u32) -> bool {

crates/codegen/kigi-shell/src/agent/config.rs

@@ -1881,12 +1881,14 @@ impl Config {
             .default(true)
             .resolve()
     }
-    /// Graph mode (`/graph`) master switch. Default OFF — gray-released via
+    /// Graph mode (`/graph`) master switch. Default ON — the gray release
-    /// `KIGI_GRAPH=1` only (plan.md G0 gate). Graph mode additionally
+    /// (plan.md G0, `KIGI_GRAPH=1` only) is over; every install gets the
+    /// same commands (its absence on non-dev machines read as a platform
+    /// bug). `KIGI_GRAPH=0` remains the off-switch. Graph mode additionally
     /// requires the goal harness (nodes execute as goals), enforced at
     /// availability time, not here.
     pub(crate) fn resolve_graph(&self) -> Resolved<bool> {
-        BoolFlag::env("KIGI_GRAPH").default(false).resolve()
+        BoolFlag::env("KIGI_GRAPH").default(true).resolve()
     }
     /// Max graph nodes running concurrently (`KIGI_GRAPH_CONCURRENCY`).
     /// 1 = serial (G0-identical); clamped to [1, 8] — the coordinator has
@@ -4337,6 +4339,24 @@ mod tests {
     /// Catalog key of the bundled fallback default (`default_models.json`):
     /// `{platform_id}/{model_id}` for `crate::models::default_model()`.
     const BUNDLED_DEFAULT_KEY: &str = "kimi-code/kimi-for-coding";
+
+    /// `/graph` ships ON by default: the G0 gray release (`KIGI_GRAPH=1`
+    /// only) made the command exist solely on machines with the dev env
+    /// var — which read as "missing on Windows". A fresh install with no
+    /// env must resolve `true`; `KIGI_GRAPH=0` stays the off-switch.
+    #[test]
+    #[serial]
+    fn graph_defaults_on_and_env_zero_disables() {
+        let cfg = Config::default();
+        {
+            let _unset = EnvGuard::unset("KIGI_GRAPH");
+            assert!(cfg.resolve_graph().value, "fresh install must offer /graph");
+        }
+        {
+            let _off = EnvGuard::set("KIGI_GRAPH", "0");
+            assert!(!cfg.resolve_graph().value, "KIGI_GRAPH=0 must disable");
+        }
+    }
     #[test]
     fn main_cli_tools_override_preserves_profile_injection_policy() {
         let overrides = CliAgentOverrides {

crates/codegen/kigi-shell/src/agent/models.rs

@@ -1637,16 +1637,31 @@ impl ModelsCacheManager {
         }
     }
 
-    /// Sync; see `load_fresh` note.
+    /// Unique tmp suffix (PID + nanos) so concurrent writers never share an
+    /// inode (mirrors `util::config::persist`).
+    fn tmp_path(&self) -> std::path::PathBuf {
+        let nanos = std::time::SystemTime::now()
+            .duration_since(std::time::UNIX_EPOCH)
+            .map(|d| d.as_nanos())
+            .unwrap_or(0);
+        self.path
+            .with_extension(format!("json.tmp.{}.{}", std::process::id(), nanos))
+    }
+
+    /// Sync; see `load_fresh` note. Best-effort, but NEVER silent: a failed
+    /// cache write leaves a stale catalog on disk, which on Windows (sharing
+    /// violations) previously diverged picker behavior with zero trace.
     fn atomic_write(&self, cache: &ModelsCache) {
         if let Some(parent) = self.path.parent() {
             let _ = std::fs::create_dir_all(parent);
         }
-        let tmp = self.path.with_extension("json.tmp");
+        let tmp = self.tmp_path();
-        if let Ok(json) = serde_json::to_vec_pretty(cache)
+        let result = serde_json::to_vec_pretty(cache)
-            && std::fs::write(&tmp, &json).is_ok()
+            .map_err(std::io::Error::other)
-        {
+            .and_then(|json| std::fs::write(&tmp, &json))
-            let _ = std::fs::rename(&tmp, &self.path);
+            .and_then(|()| crate::util::fs::replace_file(&tmp, &self.path));
+        if let Err(e) = result {
+            tracing::warn!(error = %e, path = %self.path.display(), "models cache write failed");
         }
     }
 
@@ -1654,12 +1669,25 @@ impl ModelsCacheManager {
         if let Some(parent) = self.path.parent() {
             let _ = tokio::fs::create_dir_all(parent).await;
         }
-        let tmp = self.path.with_extension("json.tmp");
+        let tmp = self.tmp_path();
-        let Ok(json) = serde_json::to_vec_pretty(cache) else {
+        let json = match serde_json::to_vec_pretty(cache) {
-            return;
+            Ok(json) => json,
+            Err(e) => {
+                tracing::warn!(error = %e, "models cache serialize failed");
+                return;
+            }
         };
-        if tokio::fs::write(&tmp, &json).await.is_ok() {
+        let result = match tokio::fs::write(&tmp, &json).await {
-            let _ = tokio::fs::rename(&tmp, &self.path).await;
+            Ok(()) => {
+                let dest = self.path.clone();
+                tokio::task::spawn_blocking(move || crate::util::fs::replace_file(&tmp, &dest))
+                    .await
+                    .unwrap_or_else(|e| Err(std::io::Error::other(e)))
+            }
+            Err(e) => Err(e),
+        };
+        if let Err(e) = result {
+            tracing::warn!(error = %e, path = %self.path.display(), "models cache write failed");
         }
     }
 }

crates/codegen/kigi-shell/src/auth/storage.rs

@@ -430,17 +430,12 @@ fn write_store_to(path: &Path, auth_store: &AuthStore) -> std::io::Result<()> {
     Ok(())
 }
 
-/// Atomic write: tmp + rename. Unix `rename(2)` replaces atomically;
+/// Atomic write: tmp + Windows-safe replace (see `util::fs::replace_file`,
-/// Windows `rename` requires removing the target first.
+/// which this site's inline delete-first pattern graduated into).
 fn write_auth_json_atomic(auth_file: &Path, auth_store: &AuthStore) -> std::io::Result<()> {
     let tmp = auth_file.with_extension(format!("json.{}.tmp", std::process::id()));
     write_store_to(&tmp, auth_store)?;
-    #[cfg(windows)]
+    crate::util::fs::replace_file(&tmp, auth_file)
-    {
-        let _ = std::fs::remove_file(auth_file);
-    }
-    std::fs::rename(&tmp, auth_file)?;
-    Ok(())
 }
 
 /// Non-atomic fallback: truncate and rewrite `auth.json` in place.

crates/codegen/kigi-shell/src/claude_import.rs

@@ -670,10 +670,7 @@ fn write_import_marker(config_path: &Path) -> anyhow::Result<()> {
         let _ = std::fs::remove_file(&tmp);
         return Err(e.into());
     }
-    if let Err(e) = std::fs::rename(&tmp, config_path) {
+    crate::util::fs::replace_file(&tmp, config_path)?;
-        let _ = std::fs::remove_file(&tmp);
-        return Err(e.into());
-    }
     Ok(())
 }
 
@@ -854,7 +851,7 @@ fn apply_items_to_config(config_path: &Path, items: &[ImportableItem]) -> anyhow
             std::fs::create_dir_all(parent)?;
         }
         std::fs::write(&tmp, &toml_str)?;
-        std::fs::rename(&tmp, config_path)?;
+        crate::util::fs::replace_file(&tmp, config_path)?;
         info!(
             path = %config_path.display(),
             count,
@@ -1204,7 +1201,7 @@ fn apply_hooks_to_dir(hooks_dir: &Path, items: &[ImportableItem]) -> anyhow::Res
         let json_str = serde_json::to_string_pretty(&root)?;
         let tmp = target.with_extension("json.tmp");
         std::fs::write(&tmp, &json_str)?;
-        std::fs::rename(&tmp, &target)?;
+        crate::util::fs::replace_file(&tmp, &target)?;
         info!(
             path = %target.display(),
             count,

crates/codegen/kigi-shell/src/claude_import_state.rs

@@ -90,7 +90,7 @@ pub fn save_import_state(state: &ImportState) -> std::io::Result<()> {
     // `claude_import_state.json.tmp` (the last extension is replaced).
     let tmp = path.with_extension("json.tmp");
     std::fs::write(&tmp, &json)?;
-    std::fs::rename(&tmp, &path)?;
+    crate::util::fs::replace_file(&tmp, &path)?;
     Ok(())
 }
 

crates/codegen/kigi-shell/src/kimi_import.rs

@@ -528,10 +528,7 @@ pub fn apply_at(plan: &KimiImportPlan, kigi_home: &Path) -> anyhow::Result<KimiA
             let _ = std::fs::remove_file(&tmp);
             return Err(e.into());
         }
-        if let Err(e) = std::fs::rename(&tmp, &config_path) {
+        crate::util::fs::replace_file(&tmp, &config_path)?;
-            let _ = std::fs::remove_file(&tmp);
-            return Err(e.into());
-        }
         info!(
             path = %config_path.display(),
             added = applied.total_added(),

crates/codegen/kigi-shell/src/session/acp_session.rs

@@ -1147,7 +1147,7 @@ fn persist_chat_history_jsonl_sync(session_info: &SessionInfo, conversation: &[C
             buf.push(b'\n');
         }
         std::fs::File::create(&tmp_path)?.write_all(&buf)?;
-        std::fs::rename(&tmp_path, &final_path)?;
+        crate::util::fs::replace_file(&tmp_path, &final_path)?;
         Ok(())
     })();
     if let Err(e) = result {

crates/codegen/kigi-shell/src/session/goal_classifier.rs

@@ -594,10 +594,10 @@ async fn write_patch_file_atomic(path: &Path, body: &str) -> std::io::Result<()>
         .unwrap_or("goal-classifier.patch");
     let tmp = dir.join(format!(".{file_name}.{}.tmp", uuid::Uuid::now_v7()));
     tokio::fs::write(&tmp, body).await?;
-    if let Err(err) = tokio::fs::rename(&tmp, path).await {
+    let dest = path.to_path_buf();
-        let _ = tokio::fs::remove_file(&tmp).await;
+    tokio::task::spawn_blocking(move || crate::util::fs::replace_file(&tmp, &dest))
-        return Err(err);
+        .await
-    }
+        .map_err(std::io::Error::other)??;
     Ok(())
 }
 

crates/codegen/kigi-shell/src/session/goal_tracker.rs

@@ -895,7 +895,8 @@ impl GoalTracker {
         };
         let dest = goal_dir.join(name);
         let _ = std::fs::create_dir_all(&goal_dir);
-        if std::fs::rename(&src, &dest).is_ok() || copy_no_follow(&src, &dest).is_ok() {
+        if crate::util::fs::replace_file(&src, &dest).is_ok() || copy_no_follow(&src, &dest).is_ok()
+        {
             append_skeptic_reports(&scratch_root, &dest);
             o.last_classifier_details_path = Some(dest.to_string_lossy().into_owned());
         }

crates/codegen/kigi-shell/src/session/graph_project.rs

@@ -120,7 +120,7 @@ pub fn project(dir: &Path, state: &GraphOrchestration) -> std::io::Result<()> {
         f.write_all(&buf)?;
         f.sync_all()?;
     }
-    std::fs::rename(&tmp, &target)
+    crate::util::fs::replace_file(&tmp, &target)
 }
 
 /// Load the projected graph, `Ok(None)` when absent. Malformed content

crates/codegen/kigi-shell/src/session/prompt_history.rs

@@ -98,7 +98,7 @@ pub fn truncate_if_needed(cwd: &str) -> io::Result<()> {
         }
     }
 
-    std::fs::rename(temp_path, path)?;
+    crate::util::fs::replace_file(&temp_path, &path)?;
     Ok(())
 }
 

crates/codegen/kigi-shell/src/session/storage/jsonl/mod.rs

@@ -13,6 +13,16 @@ use std::fs::OpenOptions;
 use std::io::{self, Read};
 use std::path::{Path, PathBuf};
 use tokio::io::AsyncWriteExt;
+
+/// Commit `tmp` over `target` with the shared Windows-safe replace
+/// (`util::fs::replace_file`): a bare async rename silently lost session
+/// state — including the switched model — on Windows whenever AV/indexer
+/// held the destination open.
+async fn replace_file_async(tmp: PathBuf, target: PathBuf) -> io::Result<()> {
+    tokio::task::spawn_blocking(move || crate::util::fs::replace_file(&tmp, &target))
+        .await
+        .unwrap_or_else(|e| Err(io::Error::other(e)))
+}
 /// How the adapter resolves the session directory on disk.
 ///
 /// - `FromRoot` (default): computes `{root}/sessions/{urlencoded(cwd)}/{session_id}/`
@@ -289,7 +299,7 @@ impl JsonlStorageAdapter {
         }
         let tmp = path.with_extension("jsonl.tmp");
         tokio::fs::write(&tmp, &content).await?;
-        tokio::fs::rename(&tmp, &path).await
+        replace_file_async(tmp, path).await
     }
     fn read_jsonl<T: serde::de::DeserializeOwned>(&self, path: PathBuf) -> io::Result<Vec<T>> {
         if !path.exists() {
@@ -378,7 +388,7 @@ impl JsonlStorageAdapter {
             .map_err(|e| io::Error::new(io::ErrorKind::InvalidData, e))?;
         let tmp = summary_path.with_extension("json.tmp");
         std::fs::write(&tmp, &bytes)?;
-        std::fs::rename(&tmp, &summary_path)
+        crate::util::fs::replace_file(&tmp, &summary_path)
     }
     fn read_summary_sync(&self, info: &Info) -> io::Result<Summary> {
         let path = self.summary_file(info);
@@ -1057,7 +1067,7 @@ impl StorageAdapter for JsonlStorageAdapter {
         let target = self.plan_mode_state_file(info);
         let tmp = target.with_extension("json.tmp");
         tokio::fs::write(&tmp, json).await?;
-        tokio::fs::rename(&tmp, &target).await
+        replace_file_async(tmp, target).await
     }
     async fn write_signals(
         &self,
@@ -1069,7 +1079,7 @@ impl StorageAdapter for JsonlStorageAdapter {
         let target = self.signals_file(info);
         let tmp = target.with_extension("json.tmp");
         tokio::fs::write(&tmp, signals_json).await?;
-        tokio::fs::rename(&tmp, &target).await
+        replace_file_async(tmp, target).await
     }
     async fn write_announcement_state(
         &self,
@@ -1081,7 +1091,7 @@ impl StorageAdapter for JsonlStorageAdapter {
         let target = self.announcement_state_file(info);
         let tmp = target.with_extension("json.tmp");
         tokio::fs::write(&tmp, json).await?;
-        tokio::fs::rename(&tmp, &target).await
+        replace_file_async(tmp, target).await
     }
     async fn write_goal_mode_state(
         &self,
@@ -1096,7 +1106,7 @@ impl StorageAdapter for JsonlStorageAdapter {
         }
         let tmp = target.with_extension("json.tmp");
         tokio::fs::write(&tmp, json).await?;
-        tokio::fs::rename(&tmp, &target).await
+        replace_file_async(tmp, target).await
     }
     async fn write_graph_mode_state(
         &self,
@@ -1119,7 +1129,7 @@ impl StorageAdapter for JsonlStorageAdapter {
         }
         let tmp = target.with_extension("json.tmp");
         tokio::fs::write(&tmp, json).await?;
-        tokio::fs::rename(&tmp, &target).await
+        replace_file_async(tmp, target).await
     }
     async fn load_session(&self, info: &Info) -> io::Result<PersistedData> {
         let summary = self.read_summary_sync(info)?;

crates/codegen/kigi-shell/src/session/storage/summary_write.rs

@@ -230,7 +230,10 @@ fn write_summary_atomic(summary_path: &Path, summary: &Summary) -> io::Result<()
         .map_err(|e| io::Error::new(io::ErrorKind::InvalidData, e))?;
     let tmp = summary_path.with_extension("json.tmp");
     std::fs::write(&tmp, &bytes)?;
-    std::fs::rename(&tmp, summary_path)
+    // Windows-safe replace: this is the write that persists a session's
+    // CURRENT MODEL — a bare rename made a switched model silently revert
+    // on resume whenever AV/indexer held summary.json open on Windows.
+    crate::util::fs::replace_file(&tmp, summary_path)
 }
 
 #[cfg(test)]

crates/codegen/kigi-shell/src/util/config/campaigns.rs

@@ -114,9 +114,7 @@ fn dismiss_campaign_ids_at(
     let nonce = DISMISS_TMP_NONCE.fetch_add(1, Ordering::Relaxed);
     let tmp = path.with_extension(format!("json.{}.{}.tmp", std::process::id(), nonce));
     std::fs::write(&tmp, &json)?;
-    std::fs::rename(&tmp, &path).inspect_err(|_| {
+    crate::util::fs::replace_file(&tmp, &path)
-        let _ = std::fs::remove_file(&tmp);
-    })
 }
 
 /// `KIGI_CAMPAIGNS_OVERRIDE` JSON array replaces all sources (`[]` = none; beats

crates/codegen/kigi-shell/src/util/config/mcp.rs

@@ -367,7 +367,9 @@ pub async fn save_mcp_disabled_tools(server_name: &str, disabled_tools: &[String
         let _ = tokio::fs::create_dir_all(parent).await;
     }
     tokio::fs::write(&tmp, &toml_str).await?;
-    tokio::fs::rename(&tmp, &path).await?;
+    tokio::task::spawn_blocking(move || crate::util::fs::replace_file(&tmp, &path))
+        .await
+        .map_err(std::io::Error::other)??;
     Ok(())
 }
 
@@ -419,7 +421,9 @@ pub async fn save_mcp_server_enabled(server_name: &str, enabled: bool) -> Result
         let _ = tokio::fs::create_dir_all(parent).await;
     }
     tokio::fs::write(&tmp, &toml_str).await?;
-    tokio::fs::rename(&tmp, &path).await?;
+    tokio::task::spawn_blocking(move || crate::util::fs::replace_file(&tmp, &path))
+        .await
+        .map_err(std::io::Error::other)??;
     Ok(())
 }
 
@@ -476,7 +480,10 @@ pub async fn save_mcp_server_config_at(
         let _ = tokio::fs::create_dir_all(parent).await;
     }
     tokio::fs::write(&tmp, &toml_str).await?;
-    tokio::fs::rename(&tmp, &path).await?;
+    let dest = path.to_path_buf();
+    tokio::task::spawn_blocking(move || crate::util::fs::replace_file(&tmp, &dest))
+        .await
+        .map_err(std::io::Error::other)??;
     Ok(())
 }
 
@@ -553,7 +560,12 @@ pub async fn delete_mcp_server_config_at(
         let _ = tokio::fs::create_dir_all(parent).await;
     }
     tokio::fs::write(&tmp, &toml_str).await?;
-    tokio::fs::rename(&tmp, &path).await?;
+    {
+        let dest = path.to_path_buf();
+        tokio::task::spawn_blocking(move || crate::util::fs::replace_file(&tmp, &dest))
+            .await
+            .map_err(std::io::Error::other)??;
+    }
 
     // Clean up OAuth credentials for the deleted server.
     if let Ok(mut cred_store) = kigi_mcp::credentials::McpCredentialStore::load_default() {

crates/codegen/kigi-shell/src/util/config/persist.rs

@@ -88,7 +88,12 @@ pub async fn save_config(config: &Config) -> Result<()> {
     }
     let _ = prior_mode;
 
-    tokio::fs::rename(&tmp, &path).await?;
+    // Windows-safe replace (delete-first + retry on sharing violations) —
+    // a bare rename made `/model` persistence silently fail on Windows
+    // whenever AV/indexer/cloud-sync held config.toml open.
+    tokio::task::spawn_blocking(move || crate::util::fs::replace_file(&tmp, &path))
+        .await
+        .map_err(|e| anyhow::anyhow!("config replace task: {e}"))??;
     Ok(())
 }
 
@@ -138,11 +143,8 @@ pub(crate) fn atomic_write_string(path: &std::path::Path, content: &str) -> std:
     }
     let _ = prior_mode;
 
-    if let Err(e) = std::fs::rename(&tmp, path) {
+    // Windows-safe replace; cleans up the tmp file on failure itself.
-        let _ = std::fs::remove_file(&tmp);
+    crate::util::fs::replace_file(&tmp, path)
-        return Err(e);
-    }
-    Ok(())
 }
 
 /// Merge `[toolset.ask_user_question]` into the root table. `[toolset]` is

crates/codegen/kigi-tui/src/app/dispatch/settings/ui.rs

@@ -3,7 +3,7 @@
 use super::setters::{
     pr13_effective_default, set_ask_user_question_timeout_enabled_inner, set_auto_dark_theme_inner,
     set_auto_light_theme_inner, set_auto_update_inner, set_collapsed_edit_blocks_inner,
-    set_compact_mode, set_compact_mode_inner, set_contextual_hint_inner, set_default_model_inner,
+    set_compact_mode, set_compact_mode_inner, set_contextual_hint_inner,
     set_default_selected_permission_inner, set_display_refresh_auto_cadence_inner,
     set_fork_secondary_model_inner, set_group_tool_verbs_inner, set_hunk_tracker_mode_inner,
     set_invert_scroll_inner, set_keep_text_selection_inner, set_max_thoughts_width_inner,
@@ -844,7 +844,7 @@ pub(in crate::app::dispatch) fn apply_setting_rollback(
     rollback_value: &crate::settings::SettingValue,
 ) -> Vec<Effect> {
     use crate::settings::SettingValue;
-    let mut companion_effects: Vec<Effect> = Vec::new();
+    let companion_effects: Vec<Effect> = Vec::new();
     match (key, rollback_value) {
         ("compact_mode", SettingValue::Bool(b)) => set_compact_mode_inner(app, *b),
         ("show_timestamps", SettingValue::Bool(b)) => set_timestamps_inner(app, *b),
@@ -934,65 +934,24 @@ pub(in crate::app::dispatch) fn apply_setting_rollback(
             // other rollback arms must not clobber it from the global canonical.
             sync_active_auto_flag(app);
         }
-        // default_model: best-effort rollback. If the prior model no
+        // default_model: deliberately NO revert. The session switch already
-        // longer resolves, leave optimistic value + log.
+        // succeeded independently (its own failure path reports via
-        ("default_model", SettingValue::String(s)) => {
+        // `handle_switch_model_complete`); this arm fires when only the
-            if s.is_empty() {
+        // DISK write of the next-launch default failed — which must not
-                tracing::warn!(
+        // undo a working switch. Same policy as `PersistPreferredModel`
-                    target: "settings",
+        // ("still active for this session"). Regression: reverting here
-                    key = "default_model",
+        // (plus a reverse SwitchModel) made every picker selection appear
-                    "rollback to empty string requested but no \
+        // to not take on Windows, where AV/indexer file locks routinely
-                     'clear current model' API exists — leaving live \
+        // fail config.toml persists.
-                     state at optimistic value (next session reload \
+        ("default_model", SettingValue::String(prior)) => {
-                     will resolve via shell default-resolution chain)",
+            tracing::warn!(
-                );
+                target: "settings",
-            } else {
+                key = "default_model",
-                // Resolve the prior model ID back to a ModelId
+                prior = %prior,
-                // and call the typed inner. If resolution fails
+                "default-model persist failed; keeping the live session's \
-                // (catalog changed mid-flight), log + leave
+                 model (the switch succeeded) — only the next-launch \
-                // optimistic.
+                 default is unsaved",
-                let (resolved, session_id) = if let ActiveView::Agent(aid) = app.active_view
+            );
-                    && let Some(agent) = app.agents.get(&aid)
-                {
-                    (
-                        agent.session.models.resolve_by_name_or_id(s),
-                        agent.session.session_id.clone(),
-                    )
-                } else {
-                    (None, None)
-                };
-                match resolved {
-                    Some(id) => {
-                        let _ = set_default_model_inner(app, &id);
-                        // Emit reverse SwitchModel so the ACP session
-                        // matches the rolled-back pager mirror.
-                        if let ActiveView::Agent(aid) = app.active_view
-                            && let Some(sid) = session_id
-                        {
-                            if let Some(agent) = app.agents.get_mut(&aid) {
-                                agent.session.model_switch_pending = true;
-                            }
-                            companion_effects.push(Effect::SwitchModel {
-                                agent_id: aid,
-                                session_id: sid,
-                                model_id: id,
-                                effort: None,
-                                prev_model_id: None,
-                            });
-                        }
-                    }
-                    None => {
-                        tracing::warn!(
-                            target: "settings",
-                            key = "default_model",
-                            value = %s,
-                            "rollback model id no longer resolves in catalog — \
-                             in-memory state stays at optimistic value; ACP session \
-                             may diverge from pager mirror until next setter dispatch",
-                        );
-                    }
-                }
-            }
         }
         // max_thoughts_width: direct inner call.
         ("max_thoughts_width", SettingValue::Int(i)) => set_max_thoughts_width_inner(app, *i),

crates/codegen/kigi-tui/src/app/dispatch/tests/task_result.rs

@@ -1592,6 +1592,78 @@ fn rollback_reverts_thread_local_cache_too() {
     .unwrap();
 }
 
+/// A default_model persist failure must NOT revert the live session's
+/// model. The switch already succeeded in the session (its own failure
+/// path reports separately); a DISK write failure only means the default
+/// won't stick for the next launch — same policy as PersistPreferredModel
+/// ("still active for this session"). Regression: the rollback arm
+/// re-showed the ORIGINAL model and issued a reverse SwitchModel, which
+/// on Windows (persist failures from AV/indexer file locks) made every
+/// picker selection appear to not take.
+#[test]
+fn default_model_persist_failure_keeps_live_model() {
+    use crate::settings::SettingValue;
+    let mut app = test_app_with_agent();
+    let id = AgentId(0);
+    for (mid, name) in [("old-model", "Old Model"), ("new-model", "New Model")] {
+        let model_id = acp::ModelId::new(std::sync::Arc::from(mid));
+        let info = acp::ModelInfo::new(model_id.clone(), name.to_string());
+        app.agents
+            .get_mut(&id)
+            .unwrap()
+            .session
+            .models
+            .available
+            .insert(model_id.clone(), info.clone());
+        app.models.available.insert(model_id, info);
+    }
+    // User picked the new model; optimistic update applied.
+    let _ = dispatch(
+        Action::SetDefaultModel(acp::ModelId::new(std::sync::Arc::from("new-model"))),
+        &mut app,
+    );
+    assert_eq!(
+        app.agents[&id]
+            .session
+            .models
+            .current
+            .as_ref()
+            .map(|m| m.0.as_ref()),
+        Some("new-model"),
+    );
+
+    // Disk persist fails (the Windows sharing-violation shape).
+    let effects = dispatch(
+        Action::TaskComplete(TaskResult::SettingPersistFailed {
+            key: "default_model",
+            rollback_value: SettingValue::String("Old Model".into()),
+            error: "Access is denied. (os error 5)".into(),
+        }),
+        &mut app,
+    );
+
+    assert_eq!(
+        app.agents[&id]
+            .session
+            .models
+            .current
+            .as_ref()
+            .map(|m| m.0.as_ref()),
+        Some("new-model"),
+        "a persist failure must not revert the live session's model"
+    );
+    assert!(
+        !effects
+            .iter()
+            .any(|e| matches!(e, Effect::SwitchModel { .. })),
+        "no reverse SwitchModel may be issued for a disk-persist failure"
+    );
+    assert!(
+        read_toast(&app).contains("Could not save"),
+        "the save failure must still be surfaced"
+    );
+}
+
 /// `set_yolo_mode_inner` is the backstop: even a (stale) rollback
 /// value of "always-approve" must not re-enable yolo under the pin.
 #[test]