chore(deps): bump qs from 6.14.2 to 6.15.2

Bumps [qs](https://github.com/ljharb/qs) from 6.14.2 to 6.15.2.
- [Changelog](https://github.com/ljharb/qs/blob/main/CHANGELOG.md)
- [Commits](https://github.com/ljharb/qs/compare/v6.14.2...v6.15.2)

---
updated-dependencies:
- dependency-name: qs
  dependency-version: 6.15.2
  dependency-type: indirect
...

Signed-off-by: dependabot[bot] <support@github.com>

.gemini/settings.json

@@ -3,7 +3,6 @@
     "extensionReloading": true,
     "modelSteering": true,
     "autoMemory": true,
-    "memoryManager": true,
     "topicUpdateNarration": true,
     "voiceMode": true,
     "adk": {

.gemini/skills/agent-tui/SKILL.md

@@ -0,0 +1,330 @@
+---
+name: agent-tui
+description: >
+  Main Agents: Do NOT use this skill directly. If you need to test the TUI, invoke the `tui_tester` subagent.
+  Drive terminal UI (TUI) applications programmatically for testing, automation, and inspection.
+  Use when: automating CLI/TUI interactions, regression testing terminal apps, or verifying interactive behavior.
+  Also use when: user asks "what is agent-tui", "what does agent-tui do", "demo agent-tui", "show me agent-tui", "how does agent-tui work", or wants to see it in action.
+---
+
+## 🚨 CRITICAL: macOS Daemon Workaround & Gemini CLI Usage 🚨
+
+When using `agent-tui` in this macOS environment, the default background daemonization process crashes, causing `Connection refused (os error 61)` errors. 
+
+**You MUST start the daemon manually shielded from TTY hangups before running any `agent-tui` commands.** Using `nohup` is insufficient; you must use `tmux` to provide a fully isolated pseudo-terminal. 
+
+To support parallel runs, **only restart the daemon if it is not currently running:**
+
+```bash
+# Check if daemon is alive, start it in tmux if it is not
+if ! agent-tui sessions >/dev/null 2>&1; then
+  tmux kill-session -t agent-tui 2>/dev/null || true
+  agent-tui daemon stop 2>/dev/null || true
+  rm -f /tmp/agent-tui*
+  tmux new-session -d -s agent-tui 'agent-tui daemon start --foreground > /tmp/agent-tui-daemon.log 2>&1'
+  sleep 1
+fi
+```
+
+### Session ID vs PID (Crucial for Reconnection)
+
+When `agent-tui run` returns JSON, it includes both a `session_id` and a `pid`. The `pid` is purely informational (the OS process ID of the child command). You **do not** use the `pid` to reconnect or issue commands. You must always use the `session_id` (e.g., `--session <id>`). 
+
+If the daemon crashes (`os error 61`), the pseudo-terminal is destroyed. Even if the child `pid` survives as an orphan, you cannot reconnect to it. You must restart the daemon using the workaround above and start a completely new session.
+
+### Testing the Gemini CLI
+
+When testing the Gemini CLI with `agent-tui`, there are several strict requirements to ensure deterministic and accurate behavior:
+
+1. **Build Before Running**: `agent-tui` runs the built JS files, not TypeScript. You **MUST** run `npm run build` or `npm run build:all` after making code changes and before launching the CLI with `agent-tui`.
+2. **Bypass Trust Modals**: Always pass `GEMINI_CLI_TRUST_WORKSPACE=true` in the environment. If you don't, any new project-level agents or extensions will trigger a full-screen "Acknowledge and Enable" modal. This modal steals focus, swallows automation keystrokes, and causes `agent-tui wait` commands to time out.
+3. **Isolated Environments**: If you need to test without real user credentials or existing agents interfering, isolate the global settings using `GEMINI_CLI_HOME=<some-test-dir>`.
+4. **Testing State Deltas (e.g., Reloads)**: If you are testing features that report deltas (e.g., `/agents reload` outputting "1 new local subagent"), you **MUST**:
+   - Start the CLI *first* so it establishes its baseline registry.
+   - Use a separate shell command (outside of `agent-tui`) to write the new agent `.md`/`.toml` file.
+   - Use `agent-tui type` and `press` to trigger the `/agents reload` command inside the running session.
+   - (If you add the files before starting the CLI, they become part of the baseline and won't trigger the delta logic).
+
+```bash
+# Example: Standard isolated run (sandboxed config + bypass trust modals)
+env GEMINI_CLI_TRUST_WORKSPACE=true GEMINI_CLI_HOME=test-gemini-home agent-tui run -d "$(pwd)" node packages/cli/dist/index.js
+```
+
+# Terminal Automation Mastery
+
+## Prerequisites
+
+- **Supported OS**: macOS or Linux (Windows not supported yet).
+- **Verify install**:
+
+```bash
+agent-tui --version
+```
+
+If not installed, use one of:
+
+```bash
+# Recommended: one-line install (macOS/Linux)
+curl -fsSL https://raw.githubusercontent.com/pproenca/agent-tui/master/install.sh | sh
+```
+
+```bash
+# Package manager
+npm i -g agent-tui
+pnpm add -g agent-tui
+bun add -g agent-tui
+```
+
+```bash
+# Build from source
+cargo install --git https://github.com/pproenca/agent-tui.git --path cli/crates/agent-tui
+```
+
+If you used the install script, ensure `~/.local/bin` is on your PATH.
+
+## Philosophy: Why Terminal Automation Is Different
+
+Terminal UIs are **stateless from the observer's perspective**. Unlike web browsers with a persistent DOM, terminal automation works with a constantly-refreshed character grid. This fundamental difference shapes everything:
+
+| Web Automation | Terminal Automation |
+|----------------|---------------------|
+| DOM persists across interactions | Screen buffer is redrawn constantly |
+| Selectors are stable | Text positions may shift |
+| Query once, act many times | Must re-verify before EVERY action |
+| Network events signal completion | Must detect visual stability |
+
+**The Core Insight**: agent-tui gives you vision without memory. Each screenshot is a fresh observation. Previous state means nothing after the UI changes. This isn't a limitation—it's the nature of terminal interaction.
+
+## Mental Model: The Feedback Loop
+
+Think of terminal automation as a **closed-loop control system**:
+
+```
+    ┌──────────────────────────────────────────────┐
+    │                                              │
+    ▼                                              │
+OBSERVE ──► DECIDE ──► ACT ──► WAIT ──► VERIFY ───┘
+   │                                        │
+   │                                        │
+   └─────── NEVER skip ◄────────────────────┘
+```
+
+**Each phase is mandatory.** Skipping verification is the #1 cause of flaky automation.
+
+### The "Fresh Eyes" Principle
+
+Every time you need to interact with the UI:
+
+1. **Take a fresh screenshot** — your previous one is now stale
+2. **Locate your target visually** — text positions may have changed
+3. **Verify the state** — the UI may have changed unexpectedly
+4. **Act only when stable** — animations and loading states cause failures
+
+This feels slower, but it's the only reliable approach. Optimistic reuse of stale state causes intermittent failures that are painful to debug.
+
+## Critical Rules (Non-Negotiable)
+
+> **RULE 1: Atomic Execution (No Pipelining)**
+> You are FORBIDDEN from chaining commands with `&&` (e.g., `type "x" && press Enter && wait`). Modals or UI updates can intercept your keystrokes. You MUST execute one atomic action, wait, screenshot, and verify before taking the next action in a new turn.
+
+> **RULE 2: Re-snapshot after EVERY action**
+> The UI state is invalidated by any change. Always take a fresh screenshot before acting again.
+
+> **RULE 3: Never act on unstable UI**
+> If the UI is animating, loading, or transitioning, `wait --stable` first. Acting during transitions because race conditions.
+
+> **RULE 4: Verify before claiming success**
+> Use `wait "expected text" --assert` to confirm outcomes. Don't assume an action worked—prove it.
+
+> **RULE 5: Error Recovery**
+> If a `wait` command times out, DO NOT blindly restart or kill the session. Execute `screenshot` to visually diagnose what unexpected UI element (modal, error dialog, lost focus) intercepted the flow.
+
+> **RULE 6: Clean up sessions**
+> Always end with `agent-tui kill`. Orphaned sessions consume resources and can interfere with future runs.
+
+## Decision Framework
+
+### Which Screenshot Mode?
+
+Use `screenshot --format json` when parsing automation output, or plain `screenshot` for human readable text.
+
+### How to Wait?
+
+```
+What are you waiting for?
+│
+├─► Specific text to appear
+│   └─► `wait "text" --assert` (fails if not found)
+│
+├─► Specific text to disappear
+│   └─► `wait "text" --gone --assert`
+│
+├─► UI to stop changing (animations, loading)
+│   └─► `wait --stable`
+│
+└─► Multiple conditions
+    └─► Chain waits sequentially
+```
+
+### How to Act?
+
+```
+What do you need to do?
+│
+├─► Type text into the terminal
+│   └─► `type "text"`
+│
+├─► Send keyboard shortcuts/navigation
+│   └─► `press Ctrl+C` or `press ArrowDown Enter`
+```
+
+## Core Workflow
+
+The canonical automation loop:
+
+```bash
+# 1. START: Launch the TUI app
+agent-tui run <command> [-- args...]
+
+# 2. OBSERVE: Get current UI state
+agent-tui screenshot --format json
+
+# 3. DECIDE: Based on text, determine next action
+# (This happens in your head/code)
+
+# 4. ACT: Execute the action
+agent-tui type "text"
+agent-tui press Enter
+
+# 5. WAIT: Synchronize with UI changes
+agent-tui wait "Expected" --assert    # or wait --stable
+
+# 6. VERIFY: Confirm the outcome (often combined with step 5)
+# If verification fails, handle the error
+
+# 7. REPEAT: Go back to step 2 until done
+
+# 8. CLEANUP: Always clean up
+agent-tui kill
+```
+
+## Anti-Patterns (What NOT to Do)
+
+### ❌ Acting During Animation/Loading
+
+```bash
+# WRONG: Acting immediately on dynamic UI
+agent-tui run my-app
+agent-tui screenshot --format json    # UI might still be loading!
+agent-tui type "value"                # ❌ Might miss the input field
+
+# RIGHT: Wait for stability first
+agent-tui run my-app
+agent-tui wait --stable               # Let UI settle
+agent-tui screenshot --format json    # Now it's reliable
+agent-tui type "value"
+```
+
+### ❌ Assuming Success Without Verification
+
+```bash
+# WRONG: Assuming the type worked
+agent-tui type "value"
+agent-tui press Enter
+# ...proceed as if success...       # ❌ What if it failed silently?
+
+# RIGHT: Verify the outcome
+agent-tui type "value"
+agent-tui press Enter
+agent-tui wait "Success" --assert    # ✓ Proves the action worked
+```
+
+### ❌ Skipping Cleanup
+
+```bash
+# WRONG: Forgetting to kill the session
+agent-tui run my-app
+# ...do stuff...
+# script ends                        # ❌ Session left running!
+
+# RIGHT: Always clean up
+agent-tui run my-app
+# ...do stuff...
+agent-tui kill                       # ✓ Clean exit
+```
+
+## Before You Start: Clarify Requirements
+
+Before automating any TUI, gather this information:
+
+1. **Command**: What exactly to run? (`my-app --flag` or `npm start`?)
+2. **Success criteria**: What text/state indicates success?
+3. **Input sequence**: What keystrokes/data to enter, in what order?
+4. **Safety**: Is it safe to submit forms, delete data, etc.?
+5. **Auth**: Does it need login? Test credentials?
+6. **Live preview**: Does the user want to watch? (`agent-tui live start --open`)
+
+If any of these are unclear, ask before running.
+
+## Demo Mode: Showing What agent-tui Can Do
+
+When a user asks what agent-tui is, wants a demo, or asks "show me how it works":
+
+1. **Don't explain—demonstrate.** Actions speak louder than words.
+2. **Use the live preview** so they can watch in real-time.
+3. **Run `top`**—it's universal and shows dynamic real-time updates.
+
+**Quick demo trigger phrases:**
+- "What is agent-tui?" / "What does agent-tui do?"
+- "Demo agent-tui" / "Show me agent-tui"
+- "How does agent-tui work?" / "See it in action"
+
+## Failure Recovery
+
+| Symptom | Diagnosis | Solution |
+|---------|-----------|----------|
+| "Text not found" | Stale view or text moved | Re-snapshot, locate text again |
+| Wait times out | UI didn't reach expected state | Check screenshot, verify expectations |
+| "Daemon not running" | Daemon crashed or not started | `agent-tui daemon start` |
+| Unexpected layout | Wrong terminal size | `agent-tui resize --cols 120 --rows 40` |
+| Session unresponsive | App crashed or hung | `agent-tui kill`, then re-run |
+| Repeated failures | Something fundamentally wrong | Stop after 3-5 attempts, ask user |
+
+## Self-Discovery: Use --help
+
+You don't need to memorize every flag. The CLI is self-documenting:
+
+```bash
+agent-tui --help                     # List all commands
+agent-tui run --help                 # Options for 'run'
+agent-tui screenshot --help          # Options for 'screenshot'
+agent-tui wait --help                # Options for 'wait'
+```
+
+**When in doubt, ask the CLI.** This skill teaches *when* and *why* to use commands. For exact flags and syntax, `--help` is authoritative.
+
+## Quick Reference
+
+```bash
+# Start app
+agent-tui run <cmd> [-- args]        # Launch TUI under control
+
+# Observe
+agent-tui screenshot                  # Plain text view
+agent-tui screenshot --format json    # Machine-readable output
+
+# Act
+agent-tui press Enter                 # Press key(s)
+agent-tui press Ctrl+C                # Keyboard shortcuts
+agent-tui type "text"                 # Type text
+
+# Wait/Verify
+agent-tui wait "text" --assert        # Wait for text, fail if not found
+agent-tui wait "text" --gone --assert # Wait for text to disappear
+agent-tui wait --stable               # Wait for UI to stop changing
+
+# Manage
+agent-tui sessions                    # List active sessions
+agent-tui live start --open           # Start live preview
+agent-tui kill                        # End current session
+```

.gemini/skills/tui-tester/SKILL.md

@@ -0,0 +1,65 @@
+---
+name: tui-tester
+description: Expert guidance for testing Gemini CLI behavior and visual output using terminal automation.
+---
+
+# TUI Tester Skill
+
+This skill provides the operational manual for verifying Gemini CLI behavioral changes and visual output using terminal automation.
+
+## Core Responsibilities
+
+- **Verify Behavior**: Confirm that code changes result in the expected terminal interactions.
+- **Visual Validation**: Ensure the TUI renders correctly across different terminal sizes and states.
+- **Regression Testing**: Use automation to prevent breaking existing interactive workflows.
+
+## Critical Protocol
+
+When performing TUI testing, you must adhere to these strict rules:
+
+### 1. Initialization
+**YOUR ABSOLUTE FIRST ACTION MUST BE:**
+Activate the `agent-tui` skill. This provides the underlying tools needed for terminal automation.
+
+### 2. Environment Setup (macOS / Parallel Safe)
+Ensure the global daemon is running and the live preview is open:
+```bash
+if ! agent-tui sessions >/dev/null 2>&1; then
+  tmux kill-session -t agent-tui 2>/dev/null || true
+  agent-tui daemon stop 2>/dev/null || true
+  rm -f /tmp/agent-tui*
+  tmux new-session -d -s agent-tui 'agent-tui daemon start --foreground > /tmp/agent-tui-daemon.log 2>&1'
+  sleep 1
+fi
+agent-tui live start --open
+```
+
+### 3. Session Management
+- **Session IDs**: Always use the `session_id` returned by `agent-tui run` for subsequent interactions.
+- **Atomic Execution**: Execute exactly one command per turn. Do not pipeline actions.
+- **The Loop**: Action -> Wait -> Screenshot -> Verify -> Next Action.
+
+### 4. Gemini CLI Specifics
+- **Build First**: Always run `npm run build` or `npm run build:all` before testing local changes.
+- **Bypass Trust**: Set `GEMINI_CLI_TRUST_WORKSPACE=true` to avoid focus-stealing modals.
+- **Isolate Config**: Use `GEMINI_CLI_HOME` to prevent interference with your personal settings.
+
+## Workflow Example
+
+```bash
+# Start the CLI
+env GEMINI_CLI_TRUST_WORKSPACE=true agent-tui run node packages/cli/dist/index.js
+
+# Wait for the prompt
+agent-tui wait "│" --assert
+
+# Send a command
+agent-tui type "/help"
+agent-tui press Enter
+
+# Verify output
+agent-tui wait "Available Commands" --assert
+```
+
+## Error Recovery
+If a wait times out, take a fresh screenshot to diagnose the state. If you see `os error 61`, restart the daemon using the tmux method.

.github/scripts/apply-issue-labels.cjs

@@ -10,31 +10,42 @@ module.exports = async ({ github, context, core }) => {
     try {
       // First, try to parse the raw output as JSON.
       return JSON.parse(raw);
-    } catch (jsonError) {
+    } catch {
       // If that fails, check for a markdown code block.
-      core.info('Direct JSON parsing failed. Trying to extract from a markdown block.');
+      core.info(
+        'Direct JSON parsing failed. Trying to extract from a markdown block.',
+      );
       const jsonMatch = raw.match(/```json\s*([\s\S]*?)\s*```/);
       if (jsonMatch && jsonMatch[1]) {
         try {
           return JSON.parse(jsonMatch[1].trim());
         } catch (markdownError) {
-          core.warning(`Failed to parse extracted JSON from markdown block: ${markdownError.message}`);
+          core.warning(
+            `Failed to parse extracted JSON from markdown block: ${markdownError.message}`,
+          );
         }
       }
 
       // Try to find a raw JSON array in the output.
-      const jsonArrayMatch = raw.match(/\[\s*\{\s*"issue_number"[\s\S]*\}\s*\]/);
+      const jsonArrayMatch = raw.match(
+        /\[\s*\{\s*"issue_number"[\s\S]*\}\s*\]/,
+      );
       if (jsonArrayMatch) {
         try {
           return JSON.parse(jsonArrayMatch[0]);
-        } catch (extractError) {
+        } catch {
           const fallbackMatch = raw.match(/(\[\s*\{\s*"issue_number"[\s\S]*)/);
           if (fallbackMatch) {
             try {
-              const cleaned = fallbackMatch[0].substring(0, fallbackMatch[0].lastIndexOf(']') + 1);
+              const cleaned = fallbackMatch[0].substring(
+                0,
+                fallbackMatch[0].lastIndexOf(']') + 1,
+              );
               return JSON.parse(cleaned);
             } catch (fallbackError) {
-              core.warning(`Failed to parse extracted JSON using fallback regex: ${fallbackError.message}`);
+              core.warning(
+                `Failed to parse extracted JSON using fallback regex: ${fallbackError.message}`,
+              );
             }
           }
         }
@@ -53,7 +64,7 @@ module.exports = async ({ github, context, core }) => {
 
   const resultsByIssue = new Map();
 
-  const processResults = (results, sourceName) => {
+  const processResults = (results, _sourceName) => {
     for (const entry of results) {
       const issueNumber = entry.issue_number;
       if (!issueNumber) continue;
@@ -69,16 +80,29 @@ module.exports = async ({ github, context, core }) => {
       } else {
         const existing = resultsByIssue.get(issueNumber);
         // Combine labels
-        existing.labels_to_add = [...new Set([...existing.labels_to_add, ...(entry.labels_to_add || [])])];
-        existing.labels_to_remove = [...new Set([...existing.labels_to_remove, ...(entry.labels_to_remove || [])])];
-        
+        existing.labels_to_add = [
+          ...new Set([
+            ...existing.labels_to_add,
+            ...(entry.labels_to_add || []),
+          ]),
+        ];
+        existing.labels_to_remove = [
+          ...new Set([
+            ...existing.labels_to_remove,
+            ...(entry.labels_to_remove || []),
+          ]),
+        ];
+
         // Combine explanations (if different)
-        if (entry.explanation && !existing.explanation.includes(entry.explanation)) {
-          existing.explanation = existing.explanation 
+        if (
+          entry.explanation &&
+          !existing.explanation.includes(entry.explanation)
+        ) {
+          existing.explanation = existing.explanation
             ? `${existing.explanation}\n\n${entry.explanation}`
             : entry.explanation;
         }
-        
+
         // Take effort analysis if present
         if (entry.effort_analysis && !existing.effort_analysis) {
           existing.effort_analysis = entry.effort_analysis;
@@ -122,11 +146,15 @@ module.exports = async ({ github, context, core }) => {
       const targetPriority = labelsToAdd.find((l) => l.startsWith('priority/'));
       if (targetPriority) {
         let downgradedPriority = null;
-        if (targetPriority === 'priority/p0') downgradedPriority = 'priority/p1';
-        if (targetPriority === 'priority/p1') downgradedPriority = 'priority/p2';
+        if (targetPriority === 'priority/p0')
+          downgradedPriority = 'priority/p1';
+        if (targetPriority === 'priority/p1')
+          downgradedPriority = 'priority/p2';
 
         if (downgradedPriority) {
-          core.info(`Programmatically downgrading ${targetPriority} to ${downgradedPriority} due to status/need-information`);
+          core.info(
+            `Programmatically downgrading ${targetPriority} to ${downgradedPriority} due to status/need-information`,
+          );
           labelsToAdd = labelsToAdd.filter((l) => l !== targetPriority);
           labelsToAdd.push(downgradedPriority);
         }
@@ -147,26 +175,36 @@ module.exports = async ({ github, context, core }) => {
 
     // Resolve internal conflicts (e.g., adding P1 and P2)
     // We already resolved these by putting Effort first in the combined list
-    
+
     // Resolve external conflicts with existing labels
     if (labelsToAdd.some((l) => l.startsWith('area/'))) {
-      labelsToRemove.push(...existingLabels.filter((l) => l.startsWith('area/')));
+      labelsToRemove.push(
+        ...existingLabels.filter((l) => l.startsWith('area/')),
+      );
     }
     if (labelsToAdd.some((l) => l.startsWith('priority/'))) {
-      labelsToRemove.push(...existingLabels.filter((l) => l.startsWith('priority/')));
+      labelsToRemove.push(
+        ...existingLabels.filter((l) => l.startsWith('priority/')),
+      );
     }
     if (labelsToAdd.some((l) => l.startsWith('kind/'))) {
-      labelsToRemove.push(...existingLabels.filter((l) => l.startsWith('kind/')));
+      labelsToRemove.push(
+        ...existingLabels.filter((l) => l.startsWith('kind/')),
+      );
     }
 
     // Enforce mutual exclusivity in the TO-ADD list (Architect wins)
     const exclusivePrefixes = ['area/', 'priority/', 'kind/'];
     for (const prefix of exclusivePrefixes) {
-      const filtered = labelsToAdd.filter(l => l.startsWith(prefix));
+      const filtered = labelsToAdd.filter((l) => l.startsWith(prefix));
       if (filtered.length > 1) {
         const winner = filtered[0]; // First one wins
-        core.info(`Issue #${issueNumber} has multiple ${prefix} labels suggested. Keeping "${winner}" and discarding others.`);
-        labelsToAdd = labelsToAdd.filter(l => !l.startsWith(prefix) || l === winner);
+        core.info(
+          `Issue #${issueNumber} has multiple ${prefix} labels suggested. Keeping "${winner}" and discarding others.`,
+        );
+        labelsToAdd = labelsToAdd.filter(
+          (l) => !l.startsWith(prefix) || l === winner,
+        );
       }
     }
 
@@ -174,7 +212,9 @@ module.exports = async ({ github, context, core }) => {
     labelsToRemove = [...new Set(labelsToRemove)].filter(
       (l) => !labelsToAdd.includes(l) && existingLabels.includes(l),
     );
-    labelsToAdd = [...new Set(labelsToAdd)].filter((l) => !existingLabels.includes(l));
+    labelsToAdd = [...new Set(labelsToAdd)].filter(
+      (l) => !existingLabels.includes(l),
+    );
 
     // Batch label operations
     if (labelsToAdd.length > 0) {
@@ -184,7 +224,9 @@ module.exports = async ({ github, context, core }) => {
         issue_number: issueNumber,
         labels: labelsToAdd,
       });
-      core.info(`Successfully added labels for #${issueNumber}: ${labelsToAdd.join(', ')}`);
+      core.info(
+        `Successfully added labels for #${issueNumber}: ${labelsToAdd.join(', ')}`,
+      );
     }
 
     if (labelsToRemove.length > 0) {
@@ -197,14 +239,21 @@ module.exports = async ({ github, context, core }) => {
             name: label,
           });
         } catch (e) {
-          if (e.status !== 404) core.warning(`Failed to remove label ${label} from #${issueNumber}: ${e.message}`);
+          if (e.status !== 404)
+            core.warning(
+              `Failed to remove label ${label} from #${issueNumber}: ${e.message}`,
+            );
         }
       }
-      core.info(`Successfully removed labels for #${issueNumber}: ${labelsToRemove.join(', ')}`);
+      core.info(
+        `Successfully removed labels for #${issueNumber}: ${labelsToRemove.join(', ')}`,
+      );
     }
 
     // Post comment if needed
-    const needsInfoAdded = labelsToAdd.includes('status/need-information') && !existingLabels.includes('status/need-information');
+    const needsInfoAdded =
+      labelsToAdd.includes('status/need-information') &&
+      !existingLabels.includes('status/need-information');
     const hasEffortAnalysis = !!entry.effort_analysis;
 
     if (needsInfoAdded || hasEffortAnalysis) {

.github/workflows/gemini-scheduled-issue-triage.yml

@@ -29,6 +29,18 @@ jobs:
         with:
           persist-credentials: false
 
+      - name: 'Install Utilities'
+        run: |
+          sudo apt-get update
+          sudo apt-get install -y ripgrep
+
+      - name: 'Get Current Version'
+        id: 'get_version'
+        run: |
+          VERSION=$(jq -r .version package.json | cut -d'-' -f1)
+          echo "version=${VERSION}" >> "${GITHUB_OUTPUT}"
+          echo "🚀 Current CLI Version: ${VERSION}"
+
       - name: 'Generate GitHub App Token'
         id: 'generate_token'
         uses: 'actions/create-github-app-token@a8d616148505b5069dccd32f177bb87d7f39123b' # ratchet:actions/create-github-app-token@v2
@@ -163,6 +175,7 @@ jobs:
           GITHUB_TOKEN: '' # Do not pass any auth token here since this runs on untrusted inputs
           REPOSITORY: '${{ github.repository }}'
           AVAILABLE_LABELS: '${{ steps.get_labels.outputs.available_labels }}'
+          CLI_VERSION: '${{ steps.get_version.outputs.version }}'
           GEMINI_CLI_TRUST_WORKSPACE: 'true'
           GEMINI_EXP: 'gemini_exp.json'
           GEMINI_STRICT_TELEMETRY_LIMITS: 'true'
@@ -222,9 +235,9 @@ jobs:
                ]
                ```
               If an issue cannot be classified, do not include it in the output array.
-            9. For each issue, carefully check if the CLI version is present. It is usually found under the "### Client information" header, as a bullet point (e.g., "• CLI Version: 0.33.1"), or in the output of the `/about` command.
-              - If the version is provided but is more than 6 minor versions older than the most recent release, apply the status/need-information label and leave a comment politely asking the user to verify if the issue persists in the latest version.
-            10. If the issue does not have sufficient information, recommend the status/need-information label and leave a comment politely requesting the missing details. For example, if repro steps are missing, ask for them; if the CLI version is completely missing, ask for the version information in the explanation section below. Do not ask for version info if it is already in the issue body.
+            9. For each issue, carefully check if the CLI version is present. It is usually found under the "### Client information" header, as a bullet point (e.g., "• CLI Version: 0.33.1", "* **CLI Version:** 0.42.0"), or in the output of the `/about` command.
+              - **Only for issues classified as kind/bug:** If the version is provided but is more than 6 minor versions older than the most recent release (current version is ${{ steps.get_version.outputs.version }}), apply the status/need-information label and leave a comment politely asking the user to verify if the issue persists in the latest version.
+            10. **Only for issues classified as kind/bug:** If the issue does not have sufficient information, recommend the status/need-information label and leave a comment politely requesting the missing details. For example, if repro steps are missing, ask for them; if the CLI version is completely missing, ask for the version information in the explanation section below. Do not ask for version info if it is already in the issue body. (Check both bullet points and bold text). For features and enhancements, the CLI version is NOT required.
             11. If you think an issue is a Priority/P0, you MUST apply the priority/p1 label AND the status/manual-triage label, and include a note in your explanation that it likely requires P0 escalation.
             12. If the issue is highly ambiguous, completely lacks a description, or you are torn between two lower priorities (like P2 vs P3), you MUST retain the existing priority label if one is already present. Do not toggle the priority if you do not have enough information to make a definitive change.
             13. If you are uncertain about a category, use the area/unknown, kind/question, or priority/unknown labels as appropriate. If you are extremely uncertain, apply the status/manual-triage label.
@@ -284,6 +297,7 @@ jobs:
           GITHUB_TOKEN: '' # Do not pass any auth token here since this runs on untrusted inputs
           REPOSITORY: '${{ github.repository }}'
           AVAILABLE_LABELS: '${{ steps.get_labels.outputs.available_labels }}'
+          CLI_VERSION: '${{ steps.get_version.outputs.version }}'
           GEMINI_CLI_TRUST_WORKSPACE: 'true'
           GEMINI_EXP: 'gemini_exp.json'
           GEMINI_STRICT_TELEMETRY_LIMITS: 'true'
@@ -298,7 +312,7 @@ jobs:
           use_gemini_code_assist: '${{ vars.GOOGLE_GENAI_USE_GCA }}'
           settings: |-
             {
-              "maxSessionTurns": 25,
+              "maxSessionTurns": 30,
               "coreTools": [
                 "run_shell_command(echo)",
                 "grep_search",
@@ -394,7 +408,7 @@ jobs:
 
       - name: 'Apply Triaged Labels'
         if: |-
-          always() && 
+          always() &&
           ( (steps.gemini_standard_issue_analysis.outcome == 'success' && steps.gemini_standard_issue_analysis.outputs.summary != '[]' && steps.gemini_standard_issue_analysis.outputs.summary != '') ||
             (steps.gemini_effort_issue_analysis.outcome == 'success' && steps.gemini_effort_issue_analysis.outputs.summary != '[]' && steps.gemini_effort_issue_analysis.outputs.summary != '') )
         env:

.prettierignore

@@ -23,3 +23,4 @@ Thumbs.db
 **/SKILL.md
 packages/sdk/test-data/*.json
 *.mdx
+packages/vscode-ide-companion/NOTICES.txt

docs/changelogs/index.md

@@ -18,6 +18,21 @@ on GitHub.
 | [Preview](preview.md) | Experimental features ready for early feedback. |
 | [Stable](latest.md)   | Stable, recommended for general use.            |
 
+## Announcements: v0.43.0 - 2026-05-22
+
+- **Surgical Code Edits:** Steered Gemini models to prefer the `edit` tool for
+  surgical modifications, improving speed and precision
+  ([#26480](https://github.com/google-gemini/gemini-cli/pull/26480) by
+  @aishaneeshah).
+- **Session Export and Import:** Added the ability to export sessions to files
+  and import them via a new flag, facilitating session portability
+  ([#26514](https://github.com/google-gemini/gemini-cli/pull/26514) by
+  @cocosheng-g).
+- **Adaptive Token Estimation:** Introduced an adaptive token calculator for
+  more accurate content size estimation, enhancing context management efficiency
+  ([#26888](https://github.com/google-gemini/gemini-cli/pull/26888) by
+  @joshualitt).
+
 ## Announcements: v0.42.0 - 2026-05-12
 
 - **Auto Memory Inbox:** Introduced a new inbox flow for Auto Memory with a

docs/changelogs/latest.md

@@ -1,6 +1,6 @@
-# Latest stable release: v0.42.0
+# Latest stable release: v0.43.0
 
-Released: May 12, 2026
+Released: May 22, 2026
 
 For most users, our latest stable release is the recommended release. Install
 the latest stable version with:
@@ -11,272 +11,208 @@ npm install -g @google/gemini-cli
 
 ## Highlights
 
-- **Auto Memory Inbox:** Introduced a new inbox flow for Auto Memory using a
-  canonical-patch contract, enabling more robust and manageable skill
-  extraction.
-- **Gemma 4 Default:** Gemma 4 models are now enabled by default via the Gemini
-  API, providing improved performance and capabilities out of the box.
-- **Voice Mode Polish:** Added wave animations for visual feedback and
-  privacy/compliance UX warnings specifically for the Gemini Live backend.
-- **Session Management:** Added a `--delete` flag to the `/exit` command for
-  instant session deletion and introduced `/bug-memory` for easier heap
-  diagnostics.
-- **Improved Reliability:** Reduced default API timeouts to 60s and implemented
-  retries for undici and premature stream closure errors.
+- **Surgical Code Edits:** Gemini models are now steered to prefer the `edit`
+  tool for surgical modifications, leading to faster and more precise code
+  updates.
+- **Session Portability:** Introduced features to export active sessions to
+  files and import them later via a CLI flag, allowing for easier session
+  sharing and resumption.
+- **Adaptive Token Estimation:** A new adaptive token calculator provides more
+  accurate content size measurements, optimizing context window usage and
+  reducing API overhead.
+- **Improved UI Rendering:** Core tools now utilize native `ToolDisplay`
+  properties, fixing various UI rendering issues and improving the experience in
+  ACP-compliant IDEs.
+- **Enhanced Agent Architecture:** Introduced `LocalSubagentProtocol` and
+  `RemoteSubagentProtocol` behind a unified `AgentProtocol`, laying the
+  groundwork for more complex multi-agent interactions.
 
 ## What's Changed
 
-- fix(cli): prevent automatic updates from switching to less stable channels by
-  @Adib234 in [#26132](https://github.com/google-gemini/gemini-cli/pull/26132)
-- chore(release): bump version to 0.42.0-nightly.20260428.g59b2dea0e by
-  @gemini-cli-robot in
-  [#26142](https://github.com/google-gemini/gemini-cli/pull/26142)
-- fix(cli): pass node arguments via NODE_OPTIONS during relaunch to support SEA
-  by @cocosheng-g in
-  [#26130](https://github.com/google-gemini/gemini-cli/pull/26130)
-- fix(cli): handle DECKPAM keypad Enter sequences in terminal by @Gitanaskhan26
-  in [#26092](https://github.com/google-gemini/gemini-cli/pull/26092)
-- docs(cli): point plan-mode session retention to actual /settings labels by
-  @ifitisit in [#25978](https://github.com/google-gemini/gemini-cli/pull/25978)
-- fix(core): add missing oauth fields support in subagent parsing by
-  @abhipatel12 in
-  [#26141](https://github.com/google-gemini/gemini-cli/pull/26141)
-- fix(core): disconnect extension-backed MCP clients in stopExtension by
-  @cocosheng-g in
-  [#26136](https://github.com/google-gemini/gemini-cli/pull/26136)
-- Update documentation workflows with workspace trust by @g-samroberts in
-  [#26150](https://github.com/google-gemini/gemini-cli/pull/26150)
-- refactor(acp): modularize monolithic acpClient into specialized files by
-  @sripasg in [#26143](https://github.com/google-gemini/gemini-cli/pull/26143)
-- test: fix failures due to antigravity environment leakage by @adamfweidman in
-  [#26162](https://github.com/google-gemini/gemini-cli/pull/26162)
-- fix(core): add explicit empty log guard in A2A pushMessage by @adamfweidman in
-  [#26198](https://github.com/google-gemini/gemini-cli/pull/26198)
-- feat(cli): add --delete flag to /exit command for session deletion by
-  @AbdulTawabJuly in
-  [#19332](https://github.com/google-gemini/gemini-cli/pull/19332)
-- test(core): add regression test for issue for ToolConfirmationResponse by
-  @Adib234 in [#26194](https://github.com/google-gemini/gemini-cli/pull/26194)
-- Add the ability to @ mention the gemini robot. by @gundermanc in
-  [#26207](https://github.com/google-gemini/gemini-cli/pull/26207)
-- test(evals): add EvalMetadata JSDoc annotations to older tests by @akh64bit in
-  [#26147](https://github.com/google-gemini/gemini-cli/pull/26147)
-- fix(core): reduce default API timeout to 60s and enable retries for undici
-  timeouts by @Adib234 in
-  [#26191](https://github.com/google-gemini/gemini-cli/pull/26191)
-- fix(core): distinguish fallback chains and fix maxAttempts for auto vs
-  explicit model selection by @adamfweidman in
-  [#26163](https://github.com/google-gemini/gemini-cli/pull/26163)
-- fix(cli): handle InvalidStream event gracefully without throwing by
-  @adamfweidman in
-  [#26218](https://github.com/google-gemini/gemini-cli/pull/26218)
-- ci(github-actions): switch to github app token and fix bot self-trigger by
-  @gundermanc in
-  [#26223](https://github.com/google-gemini/gemini-cli/pull/26223)
-- Respect logPrompts flag for logging sensitive fields by @lp-peg in
-  [#26153](https://github.com/google-gemini/gemini-cli/pull/26153)
-- fix: correct API key validation logic in handleApiKeySubmit by
-  @martin-hsu-test in
-  [#25453](https://github.com/google-gemini/gemini-cli/pull/25453)
-- fix(agent): prevent exit_plan_mode from being called via shell by
-  @Abhijit-2592 in
-  [#26230](https://github.com/google-gemini/gemini-cli/pull/26230)
-- # Fix: Inconsistent Case-Sensitivity in GrepTool by @.github/workflows/gemini-cli-bot-pulse.yml[bot] in [#26235](https://github.com/google-gemini/gemini-cli/pull/26235)
-- docs(core): add automated gemma setup guide by @Samee24 in
-  [#26233](https://github.com/google-gemini/gemini-cli/pull/26233)
-- Allow non-https proxy urls to support container environments by @stevemk14ebr
-  in [#26234](https://github.com/google-gemini/gemini-cli/pull/26234)
-- fix(bot): productivity and backlog optimizations by @gundermanc in
-  [#26236](https://github.com/google-gemini/gemini-cli/pull/26236)
-- refactor(acp): delegate prompt turn processing logic to GeminiClient by
-  @sripasg in [#26222](https://github.com/google-gemini/gemini-cli/pull/26222)
-- fix(cli): refine platform-specific undo/redo and smart bubbling for WSL by
-  @cocosheng-g in
-  [#26202](https://github.com/google-gemini/gemini-cli/pull/26202)
-- fix: suppress duplicate extension warnings during startup by @cocosheng-g in
-  [#26208](https://github.com/google-gemini/gemini-cli/pull/26208)
-- fix(cli): use byte length instead of string length for readStdin size limits
-  by @Adib234 in
-  [#26224](https://github.com/google-gemini/gemini-cli/pull/26224)
-- fix(ui): made shell tool header wrap on Ctrl+O by @devr0306 in
-  [#26229](https://github.com/google-gemini/gemini-cli/pull/26229)
-- Changelog for v0.41.0-preview.0 by @gemini-cli-robot in
-  [#26244](https://github.com/google-gemini/gemini-cli/pull/26244)
-- Skip binary CLI relaunch by @ruomengz in
-  [#26261](https://github.com/google-gemini/gemini-cli/pull/26261)
-- fix(cli): do not override GOOGLE_CLOUD_PROJECT in Cloud Shell when using
-  Vertex AI by @jackwotherspoon in
-  [#24455](https://github.com/google-gemini/gemini-cli/pull/24455)
-- docs(cli): add skill discovery troubleshooting checklist to tutorial by
-  @pmenic in [#26018](https://github.com/google-gemini/gemini-cli/pull/26018)
-- docs(policy-engine): link to tools reference for tool names and args by
-  @Aaxhirrr in [#22081](https://github.com/google-gemini/gemini-cli/pull/22081)
-- Fix posting invalid response to a comment by @gundermanc in
-  [#26266](https://github.com/google-gemini/gemini-cli/pull/26266)
-- fix(cli): prevent informational logs from polluting json output by
-  @cocosheng-g in
-  [#26264](https://github.com/google-gemini/gemini-cli/pull/26264)
-- feat(ui): added microphone and updated placeholder for voice mode by @devr0306
-  in [#26270](https://github.com/google-gemini/gemini-cli/pull/26270)
-- feat(cli): Add 'list' subcommand to '/commands' by @Jwhyee in
-  [#22324](https://github.com/google-gemini/gemini-cli/pull/22324)
-- fix(core): ensure tool output cleanup on session deletion for legacy files by
-  @cocosheng-g in
-  [#26263](https://github.com/google-gemini/gemini-cli/pull/26263)
-- Docs: Update Agent Skills documentation by @jkcinouye in
-  [#22388](https://github.com/google-gemini/gemini-cli/pull/22388)
-- test(acp): add missing coverage for extensions command error paths by
-  @sahilkirad in
-  [#25313](https://github.com/google-gemini/gemini-cli/pull/25313)
-- Changelog for v0.40.0 by @gemini-cli-robot in
-  [#26245](https://github.com/google-gemini/gemini-cli/pull/26245)
-- fix: report AgentExecutionBlocked in non-interactive programmatic modes by
-  @cocosheng-g in
-  [#26262](https://github.com/google-gemini/gemini-cli/pull/26262)
-- feat(extensions): add 'delete' as an alias for /extensions uninstall by
-  @martin-hsu-test in
-  [#25660](https://github.com/google-gemini/gemini-cli/pull/25660)
-- fix(core): silently skip GEMINI.md paths that are directories (EISDIR) by
-  @martin-hsu-test in
-  [#25662](https://github.com/google-gemini/gemini-cli/pull/25662)
-- fix(ci): checkout PR branch instead of main in bot workflow by @gundermanc in
-  [#26289](https://github.com/google-gemini/gemini-cli/pull/26289)
-- fix(cli): use resolved sandbox state for auto-update check by @Adib234 in
-  [#26285](https://github.com/google-gemini/gemini-cli/pull/26285)
-- # Metrics Integrity & Standardized Reporting (BT-01) by @.github/workflows/gemini-cli-bot-pulse.yml[bot] in [#26240](https://github.com/google-gemini/gemini-cli/pull/26240)
-- Add Star History section to README by @bdmorgan in
-  [#26290](https://github.com/google-gemini/gemini-cli/pull/26290)
-- Add Star History section to README by @bdmorgan in
-  [#26308](https://github.com/google-gemini/gemini-cli/pull/26308)
-- Remove Star History section from README by @bdmorgan in
-  [#26309](https://github.com/google-gemini/gemini-cli/pull/26309)
-- test(evals): add behavioral eval for file creation and write_file tool
-  selection by @akh64bit in
-  [#26292](https://github.com/google-gemini/gemini-cli/pull/26292)
-- feat(config): enable Gemma 4 models by default via Gemini API by @Abhijit-2592
-  in [#26307](https://github.com/google-gemini/gemini-cli/pull/26307)
-- fix(cli): insert voice transcription at cursor position instead of ap… by
-  @Zheyuan-Lin in
-  [#26287](https://github.com/google-gemini/gemini-cli/pull/26287)
-- fix(ui): fix issue with box edges by @gundermanc in
-  [#26148](https://github.com/google-gemini/gemini-cli/pull/26148)
-- fix(cli): respect .env override for GOOGLE_CLOUD_PROJECT by @DavidAPierce in
-  [#26288](https://github.com/google-gemini/gemini-cli/pull/26288)
-- fix(ci): robust version checking in release verification by @scidomino in
-  [#26337](https://github.com/google-gemini/gemini-cli/pull/26337)
-- fix(cli): enable daemon relaunch in binary and bundle keytar by @ruomengz in
-  [#26333](https://github.com/google-gemini/gemini-cli/pull/26333)
-- fix(core): discourage unprompted git add . in prompt snippets by @akh64bit in
-  [#26220](https://github.com/google-gemini/gemini-cli/pull/26220)
-- feat(ui): added wave animation for voice mode by @devr0306 in
-  [#26284](https://github.com/google-gemini/gemini-cli/pull/26284)
-- fix(cli): prevent Escape from clearing input buffer (#17083) by @cocosheng-g
-  in [#26339](https://github.com/google-gemini/gemini-cli/pull/26339)
-- fix(cli): undeprecate --prompt and correct positional query docs by @Adib234
-  in [#26329](https://github.com/google-gemini/gemini-cli/pull/26329)
-- Metrics updates by @.github/workflows/gemini-cli-bot-pulse.yml[bot] in
-  [#26348](https://github.com/google-gemini/gemini-cli/pull/26348)
-- fix(core): remove "System: Please continue." injection on InvalidStream events
-  by @SandyTao520 in
-  [#26340](https://github.com/google-gemini/gemini-cli/pull/26340)
-- docs(policy-engine): add tool argument keys reference and shell policy
-  cross-links by @harshpujari in
-  [#25292](https://github.com/google-gemini/gemini-cli/pull/25292)
-- fix(cli): resolve Ghostty/raw-mode False Cancellation in oauth flow by
-  @Aarchi-07 in [#25026](https://github.com/google-gemini/gemini-cli/pull/25026)
-- fix(core): reset session-scoped state on resumption by @cocosheng-g in
-  [#26342](https://github.com/google-gemini/gemini-cli/pull/26342)
-- Fix bulk of remaining issues with generalist profile by @joshualitt in
-  [#26073](https://github.com/google-gemini/gemini-cli/pull/26073)
-- fix(core): make subagents aware of active approval modes by @akh64bit in
-  [#23608](https://github.com/google-gemini/gemini-cli/pull/23608)
-- fix(acp): resolve agent mode disconnect and improve mode awareness by @sripasg
-  in [#26332](https://github.com/google-gemini/gemini-cli/pull/26332)
-- docs(sdk): add JSDoc to exported interfaces in packages/sdk/src/types.ts by
-  @cocosheng-g in
-  [#26441](https://github.com/google-gemini/gemini-cli/pull/26441)
-- perf: skip redundant GEMINI.md loading in partialConfig by @cocosheng-g in
-  [#26443](https://github.com/google-gemini/gemini-cli/pull/26443)
-- Enhance React guidelines by @psinha40898 in
-  [#22667](https://github.com/google-gemini/gemini-cli/pull/22667)
-- feat(core): reinforce Inquiry constraints to prevent unauthorized changes by
-  @akh64bit in [#26310](https://github.com/google-gemini/gemini-cli/pull/26310)
-- revert: fix(ci): robust version checking in release verification (#26337) by
-  @scidomino in [#26450](https://github.com/google-gemini/gemini-cli/pull/26450)
-- refactor(UI): created constants file for ThemeDialog by @devr0306 in
-  [#26446](https://github.com/google-gemini/gemini-cli/pull/26446)
-- docs: fix GitHub capitalization in releases guide by @haosenwang1018 in
-  [#26379](https://github.com/google-gemini/gemini-cli/pull/26379)
-- fix(cli): ensure branch indicator updates in sub-directories and worktrees by
-  @Adib234 in [#26330](https://github.com/google-gemini/gemini-cli/pull/26330)
-- feat: add minimal V8 heap snapshot utility for memory diagnostics by
-  @cocosheng-g in
-  [#26440](https://github.com/google-gemini/gemini-cli/pull/26440)
-- fix(hooks): preserve non-text parts in fromHookLLMRequest by @SandyTao520 in
-  [#26275](https://github.com/google-gemini/gemini-cli/pull/26275)
-- fix(cli): allow early stdout when config is undefined by @cocosheng-g in
-  [#26453](https://github.com/google-gemini/gemini-cli/pull/26453)
-- fix(cli)#21297: clear skills consent dialog before reload by @manavmax in
-  [#26431](https://github.com/google-gemini/gemini-cli/pull/26431)
-- fix(cli): render LaTeX-style output as Unicode in the TUI by @dimssu in
-  [#25802](https://github.com/google-gemini/gemini-cli/pull/25802)
-- fix(core): use close event instead of exit in child_process fallback by
-  @tusaryan in [#25695](https://github.com/google-gemini/gemini-cli/pull/25695)
-- feat(voice): add privacy and compliance UX warning for Gemini Live backend by
-  @cocosheng-g in
-  [#26454](https://github.com/google-gemini/gemini-cli/pull/26454)
-- feat(memory): add Auto Memory inbox flow with canonical-patch contract by
-  @SandyTao520 in
-  [#26338](https://github.com/google-gemini/gemini-cli/pull/26338)
-- test(cleanup): fix temporary directory leaks in test suites by @Adib234 in
-  [#26217](https://github.com/google-gemini/gemini-cli/pull/26217)
-- feat: add ignoreLocalEnv setting and --ignore-env flag (#2493) by @cocosheng-g
-  in [#26445](https://github.com/google-gemini/gemini-cli/pull/26445)
-- docs(sdk): add JSDoc to all exported interfaces and types by @fauzan171 in
-  [#26277](https://github.com/google-gemini/gemini-cli/pull/26277)
-- feat(cli): improve /agents refresh logging by @cocosheng-g in
-  [#26442](https://github.com/google-gemini/gemini-cli/pull/26442)
-- Fix: make Dockerfile self-contained with multi-stage build by @Famous077 in
-  [#24277](https://github.com/google-gemini/gemini-cli/pull/24277)
-- fix(core): filter unsupported multimodal types from tool responses by
+- feat(core): steer model to use edit tool for surgical edits, fix a typo by
   @aishaneeshah in
-  [#26352](https://github.com/google-gemini/gemini-cli/pull/26352)
-- fix(core): properly format markdown in AskUser tool by unescaping newlines by
-  @Adib234 in [#26349](https://github.com/google-gemini/gemini-cli/pull/26349)
-- feat(bot): add actions spend metric script by @gundermanc in
-  [#26463](https://github.com/google-gemini/gemini-cli/pull/26463)
-- feat(cli): add /bug-memory command and auto-capture heap snapshot in /bug by
-  @Anjaligarhwal in
-  [#25639](https://github.com/google-gemini/gemini-cli/pull/25639)
-- fix(cli): make SkillInboxDialog fit and scroll in alternate buffer by
-  @SandyTao520 in
-  [#26455](https://github.com/google-gemini/gemini-cli/pull/26455)
-- Robust Scale-Safe Lifecycle Consolidation by @gemini-cli-robot in
-  [#26355](https://github.com/google-gemini/gemini-cli/pull/26355)
-- fix(ci): respect exempt labels when closing stale items by @gundermanc in
-  [#26475](https://github.com/google-gemini/gemini-cli/pull/26475)
-- fix(cli): use os.homedir() for home directory warning check by @TirthNaik-99
-  in [#25890](https://github.com/google-gemini/gemini-cli/pull/25890)
-- fix(a2a-server): resolve tool approval race condition and improve status
-  reporting by @kschaab in
-  [#26479](https://github.com/google-gemini/gemini-cli/pull/26479)
-- fix(cli): prevent settings dialog border clipping using maxHeight by
-  @jackwotherspoon in
-  [#26507](https://github.com/google-gemini/gemini-cli/pull/26507)
-- feat: allow queuing messages during compression (#24071) by @cocosheng-g in
-  [#26506](https://github.com/google-gemini/gemini-cli/pull/26506)
-- fix(core): retry on ERR_STREAM_PREMATURE_CLOSE errors by @cocosheng-g in
-  [#26519](https://github.com/google-gemini/gemini-cli/pull/26519)
-- fix(core): Minor fixes for generalist profile. by @joshualitt in
-  [#26357](https://github.com/google-gemini/gemini-cli/pull/26357)
-- fix(patch): cherry-pick 3627f47 to release/v0.42.0-preview.0-pr-26542 to patch
-  version v0.42.0-preview.0 and create version 0.42.0-preview.1 by
-  @gemini-cli-robot in
-  [#26544](https://github.com/google-gemini/gemini-cli/pull/26544)
-- fix(patch): cherry-pick 02995ba to release/v0.42.0-preview.1-pr-26568 to patch
-  version v0.42.0-preview.1 and create version 0.42.0-preview.2 by
-  @gemini-cli-robot in
-  [#26590](https://github.com/google-gemini/gemini-cli/pull/26590)
+  [#26480](https://github.com/google-gemini/gemini-cli/pull/26480)
+- docs: clarify Auto Memory proposes memory updates and skills by @SandyTao520
+  in [#26527](https://github.com/google-gemini/gemini-cli/pull/26527)
+- fix(core): reject numeric project IDs in GOOGLE_CLOUD_PROJECT (#24695) by
+  @Abhijit-2592 in
+  [#26532](https://github.com/google-gemini/gemini-cli/pull/26532)
+- fix(core): remove unsafe type assertion suppressions in error utils by
+  @himanshu748 in
+  [#19881](https://github.com/google-gemini/gemini-cli/pull/19881)
+- fix(core): allow redirection in YOLO and AUTO_EDIT modes without sandboxing by
+  @galz10 in [#26542](https://github.com/google-gemini/gemini-cli/pull/26542)
+- ci(release): build and attach unsigned macOS binaries to releases by @ruomengz
+  in [#26462](https://github.com/google-gemini/gemini-cli/pull/26462)
+- fix(core): Fix chat corruption bug in context manager. by @joshualitt in
+  [#26534](https://github.com/google-gemini/gemini-cli/pull/26534)
+- fix(cli): provide JSON output for AgentExecutionStopped in non-interactive
+  mode by @cynthialong0-0 in
+  [#26504](https://github.com/google-gemini/gemini-cli/pull/26504)
+- feat(evals): add shell command safety evals by @akh64bit in
+  [#26528](https://github.com/google-gemini/gemini-cli/pull/26528)
+- fix(core): handle invalid custom plans directory gracefully by @cynthialong0-0
+  in [#26560](https://github.com/google-gemini/gemini-cli/pull/26560)
+- fix(acp): move tool explanation from thought stream to tool call content by
+  @sripasg in [#26554](https://github.com/google-gemini/gemini-cli/pull/26554)
+- fix(a2a-server): Resolve race condition in tool completion waiting by @kschaab
+  in [#26568](https://github.com/google-gemini/gemini-cli/pull/26568)
+- fix(cli): randomize sandbox container names by @Kkartik14 in
+  [#26014](https://github.com/google-gemini/gemini-cli/pull/26014)
+- fix(core): Fix hysteresis in async context management pipelines. by
+  @joshualitt in
+  [#26452](https://github.com/google-gemini/gemini-cli/pull/26452)
+- Tighten private Auto Memory patch allowlist by @SandyTao520 in
+  [#26535](https://github.com/google-gemini/gemini-cli/pull/26535)
+- fix(cli): hide read-only settings scopes by @cvan20191 in
+  [#26249](https://github.com/google-gemini/gemini-cli/pull/26249)
+- fix(ci): preserve executable bit for mac binaries by @ruomengz in
+  [#26600](https://github.com/google-gemini/gemini-cli/pull/26600)
+- fix(cli): improve mcp list UX in untrusted folders by @Adib234 in
+  [#26457](https://github.com/google-gemini/gemini-cli/pull/26457)
+- fix(core): prevent silent hang during OAuth auth on headless Linux by
+  @RhysSullivan in
+  [#26571](https://github.com/google-gemini/gemini-cli/pull/26571)
+- Changelog for v0.42.0-preview.0 by @gemini-cli-robot in
+  [#26537](https://github.com/google-gemini/gemini-cli/pull/26537)
+- ci: fix Argument list too long in triage workflows by @cocosheng-g in
+  [#26603](https://github.com/google-gemini/gemini-cli/pull/26603)
+- refactor(cli): migrate core tools to native ToolDisplay property and fix UI
+  rendering by @mbleigh in
+  [#25186](https://github.com/google-gemini/gemini-cli/pull/25186)
+- don't wrap args unnecessarily by @scidomino in
+  [#26599](https://github.com/google-gemini/gemini-cli/pull/26599)
+- fix(core): preserve system PATH in Git environment to fix ENOENT (#25034) by
+  @cocosheng-g in
+  [#26587](https://github.com/google-gemini/gemini-cli/pull/26587)
+- fix(routing): fix resolveClassifierModel argument mismatch in
+  ApprovalModeStrategy by @danielweis in
+  [#26658](https://github.com/google-gemini/gemini-cli/pull/26658)
+- docs: add vi mode shortcuts and clarify MCP/custom sandbox setup by
+  @chrisjcthomas in
+  [#23853](https://github.com/google-gemini/gemini-cli/pull/23853)
+- fix(ux): fixed issue with transcribed text not showing after releasing space
+  by @devr0306 in
+  [#26609](https://github.com/google-gemini/gemini-cli/pull/26609)
+- ci: fix json parsing in scheduled triage workflow by @cocosheng-g in
+  [#26656](https://github.com/google-gemini/gemini-cli/pull/26656)
+- fix(cli): hide /memory add subcommand when memoryV2 is enabled by @SandyTao520
+  in [#26605](https://github.com/google-gemini/gemini-cli/pull/26605)
+- fix: prevent false command conflicts when launching from home directory by
+  @Br1an67 in [#23069](https://github.com/google-gemini/gemini-cli/pull/23069)
+- fix(core): cache model routing decision in LocalAgentExecutor by @akh64bit in
+  [#26548](https://github.com/google-gemini/gemini-cli/pull/26548)
+- Changelog for v0.42.0-preview.2 by @gemini-cli-robot in
+  [#26597](https://github.com/google-gemini/gemini-cli/pull/26597)
+- skip broken test by @scidomino in
+  [#26705](https://github.com/google-gemini/gemini-cli/pull/26705)
+- feat: export session to file and import via flag by @cocosheng-g in
+  [#26514](https://github.com/google-gemini/gemini-cli/pull/26514)
+- Feat: Add Machine Hostname to CLI interface by @M-DEV-1 in
+  [#25637](https://github.com/google-gemini/gemini-cli/pull/25637)
+- docs(extensions): refactor releasing guide and add update mechanisms by
+  @ruomengz in [#26595](https://github.com/google-gemini/gemini-cli/pull/26595)
+- fix(ci): fix maintainer identification in lifecycle manager by @gundermanc in
+  [#26706](https://github.com/google-gemini/gemini-cli/pull/26706)
+- fix(ui): added quotes around session id in resume tip by @devr0306 in
+  [#26669](https://github.com/google-gemini/gemini-cli/pull/26669)
+- Changelog for v0.41.0 by @gemini-cli-robot in
+  [#26670](https://github.com/google-gemini/gemini-cli/pull/26670)
+- refactor(core): agent session protocol changes by @adamfweidman in
+  [#26661](https://github.com/google-gemini/gemini-cli/pull/26661)
+- fix(context): implement loose boundary policy for gc backstop. by @joshualitt
+  in [#26594](https://github.com/google-gemini/gemini-cli/pull/26594)
+- fix(core): throw explicit error on dropped tool responses by @aishaneeshah in
+  [#26668](https://github.com/google-gemini/gemini-cli/pull/26668)
+- fix: resolve "function response turn must come immediately after function
+  call" error by @danielweis in
+  [#26691](https://github.com/google-gemini/gemini-cli/pull/26691)
+- fix(core): resolve parallel tool call streaming ID collision by @aishaneeshah
+  in [#26646](https://github.com/google-gemini/gemini-cli/pull/26646)
+- feat(core): add LocalSubagentProtocol behind AgentProtocol by @adamfweidman in
+  [#25302](https://github.com/google-gemini/gemini-cli/pull/25302)
+- fix(cli): remove noisy theme registration logs from terminal by @JayadityaGit
+  in [#25858](https://github.com/google-gemini/gemini-cli/pull/25858)
+- ci: implement codebase-aware effort level triage by @cocosheng-g in
+  [#26666](https://github.com/google-gemini/gemini-cli/pull/26666)
+- feat(acp/core): prefix tool call IDs with tool names to support tool rendering
+  in ACP compliant IDEs. by @sripasg in
+  [#26676](https://github.com/google-gemini/gemini-cli/pull/26676)
+- fix(mcp): treat GET 404 as 405 in StreamableHTTPClientTransport by @krishdef7
+  in [#24847](https://github.com/google-gemini/gemini-cli/pull/24847)
+- feat(core): add RemoteSubagentProtocol behind AgentProtocol by @adamfweidman
+  in [#25303](https://github.com/google-gemini/gemini-cli/pull/25303)
+- feat(context): Improvements to the snapshotter. by @joshualitt in
+  [#26655](https://github.com/google-gemini/gemini-cli/pull/26655)
+- fix(context): Change snapshotter model config. by @joshualitt in
+  [#26745](https://github.com/google-gemini/gemini-cli/pull/26745)
+- fix(cli): allow installing extensions from ssh repo by @danielmundi in
+  [#26274](https://github.com/google-gemini/gemini-cli/pull/26274)
+- fix(cli): prevent duplicate SessionStart systemMessage render by @dimssu in
+  [#25827](https://github.com/google-gemini/gemini-cli/pull/25827)
+- fix(cli/acp): prevent infinite thought loop in ACP mode by disablig
+  nextSpeakerCheck by @sripasg in
+  [#26874](https://github.com/google-gemini/gemini-cli/pull/26874)
+- fix(cli): use static tool name in confirmation prompt to avoid parsing errors
+  by @cocosheng-g in
+  [#26866](https://github.com/google-gemini/gemini-cli/pull/26866)
+- fix(routing): Refactor tool turn handling for the conversation history in
+  NumericalClassifierStrategy to prevent 400 Bad Request by @danielweis in
+  [#26761](https://github.com/google-gemini/gemini-cli/pull/26761)
+- fix(core): handle malformed projects.json in ProjectRegistry by @cocosheng-g
+  in [#26885](https://github.com/google-gemini/gemini-cli/pull/26885)
+- fix(ui): added a gutter width to the input prompt width calculation by
+  @devr0306 in [#26882](https://github.com/google-gemini/gemini-cli/pull/26882)
+- fix: prevent EISDIR crash when customIgnoreFilePaths contains directories
+  (#19868) by @suhaan-24 in
+  [#19898](https://github.com/google-gemini/gemini-cli/pull/19898)
+- revert 6b9b778d821728427eea07b1b97ba07378137d0b by @danielweis in
+  [#26893](https://github.com/google-gemini/gemini-cli/pull/26893)
+- Fix/vscode run current file ts by @Neil-N4 in
+  [#22894](https://github.com/google-gemini/gemini-cli/pull/22894)
+- Allow Enter to select session while in search mode in /resume by @f-pieri in
+  [#21523](https://github.com/google-gemini/gemini-cli/pull/21523)
+- fix(core): ignore .pak and .rpa game archive formats by default by @Eswar809
+  in [#26884](https://github.com/google-gemini/gemini-cli/pull/26884)
+- fix(cli): enable adk non-interactive session by @adamfweidman in
+  [#26895](https://github.com/google-gemini/gemini-cli/pull/26895)
+- fix(cli): restore resume for legacy sessions by @KurodaKayn in
+  [#26577](https://github.com/google-gemini/gemini-cli/pull/26577)
+- fix: respect explicit model selection after Flash quota exhaustion (#26759) by
+  @cocosheng-g in
+  [#26872](https://github.com/google-gemini/gemini-cli/pull/26872)
+- feat(context): Introduce adaptive token calculator to more accurately
+  calculate content sizes. by @joshualitt in
+  [#26888](https://github.com/google-gemini/gemini-cli/pull/26888)
+- chore: update checkout action configuration in workflows by @galz10 in
+  [#26897](https://github.com/google-gemini/gemini-cli/pull/26897)
+- fix (telemetry): inject quota_project_id to prevent fallback to default oauth
+  client by @TNTCompany in
+  [#26698](https://github.com/google-gemini/gemini-cli/pull/26698)
+- Exclude extension context from skill extraction agent by @SandyTao520 in
+  [#26879](https://github.com/google-gemini/gemini-cli/pull/26879)
+- Enable NumericalRouter when using dynamic model configs by @kevinjwang1 in
+  [#26929](https://github.com/google-gemini/gemini-cli/pull/26929)
+- ci: actively triage missing priority labels and intelligently clean up
+  conflicting labels by @cocosheng-g in
+  [#26865](https://github.com/google-gemini/gemini-cli/pull/26865)
+- refactor(core): introduce SubagentState enum for progress by @adamfweidman in
+  [#26934](https://github.com/google-gemini/gemini-cli/pull/26934)
+- fix(ci): replace brittle --no-tag with explicit staging-tmp tag by @scidomino
+  in [#26940](https://github.com/google-gemini/gemini-cli/pull/26940)
+- Incremental refactor repo agent towards skills-based composition by
+  @gundermanc in
+  [#26717](https://github.com/google-gemini/gemini-cli/pull/26717)
+- fix(ui): fixed line wrap padding for selection lists by @devr0306 in
+  [#26944](https://github.com/google-gemini/gemini-cli/pull/26944)
+- fix(core): update read_file schema for v1 compatibility (#22183) by
+  @cocosheng-g in
+  [#26922](https://github.com/google-gemini/gemini-cli/pull/26922)
+- fix(ci): configure git remote with token for authentication by @scidomino in
+  [#26949](https://github.com/google-gemini/gemini-cli/pull/26949)
+- fix(patch): cherry-pick 85566a7 to release/v0.43.0-preview.0-pr-27073
+  [CONFLICTS] by @gemini-cli-robot in
+  [#27256](https://github.com/google-gemini/gemini-cli/pull/27256)
 
 **Full Changelog**:
-https://github.com/google-gemini/gemini-cli/compare/v0.41.2...v0.42.0
+https://github.com/google-gemini/gemini-cli/compare/v0.42.0...v0.43.0

docs/changelogs/preview.md

@@ -1,6 +1,6 @@
-# Preview release: v0.43.0-preview.0
+# Preview release: v0.44.0-preview.0
 
-Released: May 12, 2026
+Released: May 22, 2026
 
 Our preview release includes the latest, new, and experimental features. This
 release may not be as stable as our [latest weekly release](latest.md).
@@ -13,184 +13,208 @@ npm install -g @google/gemini-cli@preview
 
 ## Highlights
 
-- **Surgical Code Edits:** Steer models to use the `edit` tool for precise code
-  modifications, improving accuracy and reducing context usage.
-- **Session Portability:** Added ability to export chat sessions to files and
-  import them via a new CLI flag, enabling session persistence and sharing.
-- **Enhanced Security:** Introduced comprehensive shell command safety
-  evaluations and strengthened model steering to prevent unauthorized changes.
-- **Context Management:** Implemented a new adaptive token calculator for more
-  accurate content size estimations and optimized context pipelines.
-- **UX Improvements:** Enhanced tool call visibility with prefixed IDs and
-  improved the UI for session resumption and MCP list management.
+- **Simplified Modes:** Merged existing Auto modes into a single, unified Auto
+  mode for a more streamlined user experience.
+- **Enhanced Agent Registration:** Improved agent registration logic to
+  prioritize project-specific agents using a first-wins strategy.
+- **New Developer Skills:** Introduced `agent-tui` and `tui-tester` skills to
+  empower developers with better terminal UI testing and automation
+  capabilities.
+- **Expanded Editor Support:** Added support for Sublime Text and Emacs Client,
+  providing more flexibility for external editing tasks.
+- **Session Management:** Added new session invocation types
+  (`LocalSessionInvocation`, `RemoteSessionInvocation`) and improved context
+  recovery across sessions.
 
 ## What's Changed
 
-- feat(core): steer model to use edit tool for surgical edits, fix a typo in
-  [#26480](https://github.com/google-gemini/gemini-cli/pull/26480)
-- docs: clarify Auto Memory proposes memory updates and skills in
-  [#26527](https://github.com/google-gemini/gemini-cli/pull/26527)
-- fix(core): reject numeric project IDs in GOOGLE_CLOUD_PROJECT (#24695) in
-  [#26532](https://github.com/google-gemini/gemini-cli/pull/26532)
-- fix(core): remove unsafe type assertion suppressions in error utils in
-  [#19881](https://github.com/google-gemini/gemini-cli/pull/19881)
-- fix(core): allow redirection in YOLO and AUTO_EDIT modes without sandboxing in
-  [#26542](https://github.com/google-gemini/gemini-cli/pull/26542)
-- ci(release): build and attach unsigned macOS binaries to releases in
-  [#26462](https://github.com/google-gemini/gemini-cli/pull/26462)
-- fix(core): Fix chat corruption bug in context manager. in
-  [#26534](https://github.com/google-gemini/gemini-cli/pull/26534)
-- fix(cli): provide JSON output for AgentExecutionStopped in non-interactive
-  mode in [#26504](https://github.com/google-gemini/gemini-cli/pull/26504)
-- feat(evals): add shell command safety evals in
-  [#26528](https://github.com/google-gemini/gemini-cli/pull/26528)
-- fix(core): handle invalid custom plans directory gracefully in
-  [#26560](https://github.com/google-gemini/gemini-cli/pull/26560)
-- fix(acp): move tool explanation from thought stream to tool call content in
-  [#26554](https://github.com/google-gemini/gemini-cli/pull/26554)
-- fix(a2a-server): Resolve race condition in tool completion waiting in
-  [#26568](https://github.com/google-gemini/gemini-cli/pull/26568)
-- fix(cli): randomize sandbox container names in
-  [#26014](https://github.com/google-gemini/gemini-cli/pull/26014)
-- fix(core): Fix hysteresis in async context management pipelines. in
-  [#26452](https://github.com/google-gemini/gemini-cli/pull/26452)
-- Tighten private Auto Memory patch allowlist in
-  [#26535](https://github.com/google-gemini/gemini-cli/pull/26535)
-- fix(cli): hide read-only settings scopes in
-  [#26249](https://github.com/google-gemini/gemini-cli/pull/26249)
-- fix(ci): preserve executable bit for mac binaries in
-  [#26600](https://github.com/google-gemini/gemini-cli/pull/26600)
-- fix(cli): improve mcp list UX in untrusted folders in
-  [#26457](https://github.com/google-gemini/gemini-cli/pull/26457)
-- fix(core): prevent silent hang during OAuth auth on headless Linux in
-  [#26571](https://github.com/google-gemini/gemini-cli/pull/26571)
-- Changelog for v0.42.0-preview.0 in
-  [#26537](https://github.com/google-gemini/gemini-cli/pull/26537)
-- ci: fix Argument list too long in triage workflows in
-  [#26603](https://github.com/google-gemini/gemini-cli/pull/26603)
-- refactor(cli): migrate core tools to native ToolDisplay property and fix UI
-  rendering in [#25186](https://github.com/google-gemini/gemini-cli/pull/25186)
-- don't wrap args unnecessarily in
-  [#26599](https://github.com/google-gemini/gemini-cli/pull/26599)
-- fix(core): preserve system PATH in Git environment to fix ENOENT (#25034) in
-  [#26587](https://github.com/google-gemini/gemini-cli/pull/26587)
-- fix(routing): fix resolveClassifierModel argument mismatch in
-  ApprovalModeStrategy in
-  [#26658](https://github.com/google-gemini/gemini-cli/pull/26658)
-- docs: add vi mode shortcuts and clarify MCP/custom sandbox setup in
-  [#23853](https://github.com/google-gemini/gemini-cli/pull/23853)
-- fix(ux): fixed issue with transcribed text not showing after releasing space
-  in [#26609](https://github.com/google-gemini/gemini-cli/pull/26609)
-- ci: fix json parsing in scheduled triage workflow in
-  [#26656](https://github.com/google-gemini/gemini-cli/pull/26656)
-- fix(cli): hide /memory add subcommand when memoryV2 is enabled in
-  [#26605](https://github.com/google-gemini/gemini-cli/pull/26605)
-- fix: prevent false command conflicts when launching from home directory in
-  [#23069](https://github.com/google-gemini/gemini-cli/pull/23069)
-- fix(core): cache model routing decision in LocalAgentExecutor in
-  [#26548](https://github.com/google-gemini/gemini-cli/pull/26548)
-- Changelog for v0.42.0-preview.2 in
-  [#26597](https://github.com/google-gemini/gemini-cli/pull/26597)
-- skip broken test in
-  [#26705](https://github.com/google-gemini/gemini-cli/pull/26705)
-- feat: export session to file and import via flag in
-  [#26514](https://github.com/google-gemini/gemini-cli/pull/26514)
-- Feat: Add Machine Hostname to CLI interface in
-  [#25637](https://github.com/google-gemini/gemini-cli/pull/25637)
-- docs(extensions): refactor releasing guide and add update mechanisms in
-  [#26595](https://github.com/google-gemini/gemini-cli/pull/26595)
-- fix(ci): fix maintainer identification in lifecycle manager in
-  [#26706](https://github.com/google-gemini/gemini-cli/pull/26706)
-- fix(ui): added quotes around session id in resume tip in
-  [#26669](https://github.com/google-gemini/gemini-cli/pull/26669)
-- Changelog for v0.41.0 in
-  [#26670](https://github.com/google-gemini/gemini-cli/pull/26670)
-- refactor(core): agent session protocol changes in
-  [#26661](https://github.com/google-gemini/gemini-cli/pull/26661)
-- fix(context): implement loose boundary policy for gc backstop. in
-  [#26594](https://github.com/google-gemini/gemini-cli/pull/26594)
-- fix(core): throw explicit error on dropped tool responses in
-  [#26668](https://github.com/google-gemini/gemini-cli/pull/26668)
-- fix: resolve "function response turn must come immediately after function
-  call" error in
-  [#26691](https://github.com/google-gemini/gemini-cli/pull/26691)
-- fix(core): resolve parallel tool call streaming ID collision in
-  [#26646](https://github.com/google-gemini/gemini-cli/pull/26646)
-- feat(core): add LocalSubagentProtocol behind AgentProtocol in
-  [#25302](https://github.com/google-gemini/gemini-cli/pull/25302)
-- fix(cli): remove noisy theme registration logs from terminal in
-  [#25858](https://github.com/google-gemini/gemini-cli/pull/25858)
-- ci: implement codebase-aware effort level triage in
-  [#26666](https://github.com/google-gemini/gemini-cli/pull/26666)
-- feat(acp/core): prefix tool call IDs with tool names to support tool rendering
-  in ACP compliant IDEs. in
-  [#26676](https://github.com/google-gemini/gemini-cli/pull/26676)
-- fix(mcp): treat GET 404 as 405 in StreamableHTTPClientTransport in
-  [#24847](https://github.com/google-gemini/gemini-cli/pull/24847)
-- feat(core): add RemoteSubagentProtocol behind AgentProtocol in
-  [#25303](https://github.com/google-gemini/gemini-cli/pull/25303)
-- feat(context): Improvements to the snapshotter. in
-  [#26655](https://github.com/google-gemini/gemini-cli/pull/26655)
-- fix(context): Change snapshotter model config. in
-  [#26745](https://github.com/google-gemini/gemini-cli/pull/26745)
-- fix(cli): allow installing extensions from ssh repo in
-  [#26274](https://github.com/google-gemini/gemini-cli/pull/26274)
-- fix(cli): prevent duplicate SessionStart systemMessage render in
-  [#25827](https://github.com/google-gemini/gemini-cli/pull/25827)
-- fix(cli/acp): prevent infinite thought loop in ACP mode by disablig
-  nextSpeakerCheck in
-  [#26874](https://github.com/google-gemini/gemini-cli/pull/26874)
-- fix(cli): use static tool name in confirmation prompt to avoid parsing errors
-  in [#26866](https://github.com/google-gemini/gemini-cli/pull/26866)
-- fix(routing): Refactor tool turn handling for the conversation history in
-  NumericalClassifierStrategy to prevent 400 Bad Request in
-  [#26761](https://github.com/google-gemini/gemini-cli/pull/26761)
-- fix(core): handle malformed projects.json in ProjectRegistry in
-  [#26885](https://github.com/google-gemini/gemini-cli/pull/26885)
-- fix(ui): added a gutter width to the input prompt width calculation in
-  [#26882](https://github.com/google-gemini/gemini-cli/pull/26882)
-- fix: prevent EISDIR crash when customIgnoreFilePaths contains directories
-  (#19868) in [#19898](https://github.com/google-gemini/gemini-cli/pull/19898)
-- revert 6b9b778d821728427eea07b1b97ba07378137d0b in
-  [#26893](https://github.com/google-gemini/gemini-cli/pull/26893)
-- Fix/vscode run current file ts in
-  [#22894](https://github.com/google-gemini/gemini-cli/pull/22894)
-- Allow Enter to select session while in search mode in /resume in
-  [#21523](https://github.com/google-gemini/gemini-cli/pull/21523)
-- fix(core): ignore .pak and .rpa game archive formats by default in
-  [#26884](https://github.com/google-gemini/gemini-cli/pull/26884)
-- fix(cli): enable adk non-interactive session in
-  [#26895](https://github.com/google-gemini/gemini-cli/pull/26895)
-- fix(cli): restore resume for legacy sessions in
-  [#26577](https://github.com/google-gemini/gemini-cli/pull/26577)
-- fix: respect explicit model selection after Flash quota exhaustion (#26759) in
-  [#26872](https://github.com/google-gemini/gemini-cli/pull/26872)
-- feat(context): Introduce adaptive token calculator to more accurately
-  calculate content sizes. in
-  [#26888](https://github.com/google-gemini/gemini-cli/pull/26888)
-- chore: update checkout action configuration in workflows in
-  [#26897](https://github.com/google-gemini/gemini-cli/pull/26897)
-- fix (telemetry): inject quota_project_id to prevent fallback to default oauth
-  client in [#26698](https://github.com/google-gemini/gemini-cli/pull/26698)
-- Exclude extension context from skill extraction agent in
-  [#26879](https://github.com/google-gemini/gemini-cli/pull/26879)
-- Enable NumericalRouter when using dynamic model configs in
-  [#26929](https://github.com/google-gemini/gemini-cli/pull/26929)
-- ci: actively triage missing priority labels and intelligently clean up
-  conflicting labels in
-  [#26865](https://github.com/google-gemini/gemini-cli/pull/26865)
-- refactor(core): introduce SubagentState enum for progress in
-  [#26934](https://github.com/google-gemini/gemini-cli/pull/26934)
-- fix(ci): replace brittle --no-tag with explicit staging-tmp tag in
-  [#26940](https://github.com/google-gemini/gemini-cli/pull/26940)
-- Incremental refactor repo agent towards skills-based composition in
-  [#26717](https://github.com/google-gemini/gemini-cli/pull/26717)
-- fix(ui): fixed line wrap padding for selection lists in
-  [#26944](https://github.com/google-gemini/gemini-cli/pull/26944)
-- fix(core): update read_file schema for v1 compatibility (#22183) in
-  [#26922](https://github.com/google-gemini/gemini-cli/pull/26922)
-- fix(ci): configure git remote with token for authentication in
-  [#26949](https://github.com/google-gemini/gemini-cli/pull/26949)
+- chore(release): bump version to 0.44.0-nightly.20260512.g022e8baef by
+  @gemini-cli-robot in
+  [#26957](https://github.com/google-gemini/gemini-cli/pull/26957)
+- Changelog for v0.42.0 by @gemini-cli-robot in
+  [#26958](https://github.com/google-gemini/gemini-cli/pull/26958)
+- Refactor: Eliminate `no-unsafe-return` suppressions via strict type validation
+  by @M-DEV-1 in
+  [#20668](https://github.com/google-gemini/gemini-cli/pull/20668)
+- Changelog for v0.43.0-preview.0 by @gemini-cli-robot in
+  [#26959](https://github.com/google-gemini/gemini-cli/pull/26959)
+- feat(core): change agent registration to first-wins and prioritize project by
+  @adamfweidman in
+  [#26953](https://github.com/google-gemini/gemini-cli/pull/26953)
+- feat(cli): merge Auto modes into a single Auto mode by @DavidAPierce in
+  [#26714](https://github.com/google-gemini/gemini-cli/pull/26714)
+- fix(core): preserve OAuth refresh tokens during rotation and retrieval by
+  @cocosheng-g in
+  [#26924](https://github.com/google-gemini/gemini-cli/pull/26924)
+- fix(cli): allow keychain auth for --list-sessions and non-interactive mode by
+  @cocosheng-g in
+  [#26921](https://github.com/google-gemini/gemini-cli/pull/26921)
+- fix(core): handle EISDIR on virtual drives in memory discovery by @cocosheng-g
+  in [#26985](https://github.com/google-gemini/gemini-cli/pull/26985)
+- fix(cli): auto-approve shell redirections in AUTO_EDIT mode by @cocosheng-g in
+  [#27003](https://github.com/google-gemini/gemini-cli/pull/27003)
+- ci: suppress bot comments during standard triage maintenance by @cocosheng-g
+  in [#27006](https://github.com/google-gemini/gemini-cli/pull/27006)
+- fix(core): refresh MCP OAuth token usage after re-auth by @sahilkirad in
+  [#26312](https://github.com/google-gemini/gemini-cli/pull/26312)
+- fix(ui): clamped table column widths by @devr0306 in
+  [#26991](https://github.com/google-gemini/gemini-cli/pull/26991)
+- fix(core): isolate subagent thread context by @akh64bit in
+  [#26449](https://github.com/google-gemini/gemini-cli/pull/26449)
+- chore: add execution permission to scripts/review.sh by @scidomino in
+  [#27009](https://github.com/google-gemini/gemini-cli/pull/27009)
+- fix(core): made context files append instead of replace by @devr0306 in
+  [#26950](https://github.com/google-gemini/gemini-cli/pull/26950)
+- fix: add system PATH fallback for ripgrep resolution (#26777) by @cocosheng-g
+  in [#26868](https://github.com/google-gemini/gemini-cli/pull/26868)
+- chore: clean up launched memory features by @SandyTao520 in
+  [#26941](https://github.com/google-gemini/gemini-cli/pull/26941)
+- fix(core): throttle shell text output and bound live UI buffer by
+  @emersonbusson in
+  [#26955](https://github.com/google-gemini/gemini-cli/pull/26955)
+- fix(cli): don't crash when an @-mention captures a non-path blob by @ifitisit
+  in [#25980](https://github.com/google-gemini/gemini-cli/pull/25980)
+- fix(core): ensure stable fallback for restricted preview models by @galz10 in
+  [#26999](https://github.com/google-gemini/gemini-cli/pull/26999)
+- feat(core): expose RAG snippets to local log file for debugging by @spencer426
+  in [#27016](https://github.com/google-gemini/gemini-cli/pull/27016)
+- fix(acp/auth): prevent conflicting credentials on enterprise gateways and
+  support optional API keys natively by @sripasg in
+  [#27021](https://github.com/google-gemini/gemini-cli/pull/27021)
+- fix(core): respect NO_PROXY for network-based MCP servers by @cocosheng-g in
+  [#27012](https://github.com/google-gemini/gemini-cli/pull/27012)
+- fix(cli): resolve permission denied in sandbox on NixOS and other distros by
+  @cocosheng-g in
+  [#27004](https://github.com/google-gemini/gemini-cli/pull/27004)
+- fix(ui): preserve new line at the end of edit window by @devr0306 in
+  [#27057](https://github.com/google-gemini/gemini-cli/pull/27057)
+- fix(core): ensure Vertex AI sets hasAccessToPreviewModels and remove
+  aggressive 404 fallback revocation by @galz10 in
+  [#27067](https://github.com/google-gemini/gemini-cli/pull/27067)
+- fix(core): ensure stable admin settings comparison across IPC to prevent
+  restart loop by @DavidAPierce in
+  [#27066](https://github.com/google-gemini/gemini-cli/pull/27066)
+- fix(deps): update vulnerable dependencies by @scidomino in
+  [#27062](https://github.com/google-gemini/gemini-cli/pull/27062)
+- fix(core): resolve EISDIR errors during file processing (#21527) by @ProthamD
+  in [#27041](https://github.com/google-gemini/gemini-cli/pull/27041)
+- docs(extensions): clarify env var sanitization policy for MCP and ext… by
+  @galz10 in [#22854](https://github.com/google-gemini/gemini-cli/pull/22854)
+- fix(ui): add ENAMETOOLONG and ENOTDIR to exceptions for file parsing errors by
+  @devr0306 in [#27069](https://github.com/google-gemini/gemini-cli/pull/27069)
+- fix(cli): explicitly clear entrypoint when spawning sandbox container by
+  @cocosheng-g in
+  [#27059](https://github.com/google-gemini/gemini-cli/pull/27059)
+- docs: update sandbox image command by @sjhddh in
+  [#26774](https://github.com/google-gemini/gemini-cli/pull/26774)
+- fix(core): externalize https-proxy-agent to fix proxy support by @sotokisehiro
+  in [#26361](https://github.com/google-gemini/gemini-cli/pull/26361)
+- security: update dependencies to fix critical and high vulnerabilities by
+  @scidomino in [#27077](https://github.com/google-gemini/gemini-cli/pull/27077)
+- Fix/web fetch ctrl c abort by @ProthamD in
+  [#24320](https://github.com/google-gemini/gemini-cli/pull/24320)
+- fix(core): add aliases and thinking config for gemini-3.1 models by
+  @anishs1207 in
+  [#27007](https://github.com/google-gemini/gemini-cli/pull/27007)
+- fix(core): use hasAccessToPreview for auto model resolution and fix
+  disappearing models by @DavidAPierce in
+  [#27112](https://github.com/google-gemini/gemini-cli/pull/27112)
+- feat(core): add adk.agentSessionSubagentEnabled flag by @adamfweidman in
+  [#26947](https://github.com/google-gemini/gemini-cli/pull/26947)
+- fix(core): enforce compile-time exhaustiveness in content-utils by
+  @adamfweidman in
+  [#27207](https://github.com/google-gemini/gemini-cli/pull/27207)
+- feat(skills): add agent-tui and tui-tester skills by @adamfweidman in
+  [#27121](https://github.com/google-gemini/gemini-cli/pull/27121)
+- fix(context): Fix snapshot recovery across sessions. by @joshualitt in
+  [#26939](https://github.com/google-gemini/gemini-cli/pull/26939)
+- fix(core): add unit tests for stableStringify by @devr0306 in
+  [#27212](https://github.com/google-gemini/gemini-cli/pull/27212)
+- fix(core): prefer pwsh.exe over Windows PowerShell 5.1 (#25859) by @kaluchi in
+  [#25900](https://github.com/google-gemini/gemini-cli/pull/25900)
+- feat(core): add LocalSessionInvocation by @adamfweidman in
+  [#26665](https://github.com/google-gemini/gemini-cli/pull/26665)
+- refactor: decouple auto model description and configuration from
+  releaseChannel by @danielweis in
+  [#27227](https://github.com/google-gemini/gemini-cli/pull/27227)
+- fix(core): prevent isBinary false-positive on Windows PTY streams by
+  @TirthNaik-99 in
+  [#26565](https://github.com/google-gemini/gemini-cli/pull/26565)
+- fix(cli): Prevent unmapped keys in Vim Normal mode from inserting text into
+  prompt Input. by @Rajeshpatel07 in
+  [#25139](https://github.com/google-gemini/gemini-cli/pull/25139)
+- fix(a2a-server): Implement default policy loading for parity with CLI by
+  @kschaab in [#27073](https://github.com/google-gemini/gemini-cli/pull/27073)
+- feat(core): add RemoteSessionInvocation by @adamfweidman in
+  [#26937](https://github.com/google-gemini/gemini-cli/pull/26937)
+- fix: allow configured MCP servers in non-interactive mode by @cocosheng-g in
+  [#27215](https://github.com/google-gemini/gemini-cli/pull/27215)
+- fix(core): add exception handling to migrateFromFileStorage by @devr0306 in
+  [#27229](https://github.com/google-gemini/gemini-cli/pull/27229)
+- fix(cli): bundle ink worker-entry.js by @rmedranollamas in
+  [#27249](https://github.com/google-gemini/gemini-cli/pull/27249)
+- feat(core): wire AgentSession invocations into agent-tool by @adamfweidman in
+  [#26948](https://github.com/google-gemini/gemini-cli/pull/26948)
+- fix(core): prevent path traversal in custome command file injection by
+  @ompatel-aiml in
+  [#27234](https://github.com/google-gemini/gemini-cli/pull/27234)
+- fix(core): respect NO_PROXY in global fetch dispatcher by @cocosheng-g in
+  [#27216](https://github.com/google-gemini/gemini-cli/pull/27216)
+- fix(core): correctly handle nullable array types in MCP tools by @devr0306 in
+  [#27228](https://github.com/google-gemini/gemini-cli/pull/27228)
+- fix(cli): preserve proxy-agent named exports in ESM bundle by @ashishch432 in
+  [#27145](https://github.com/google-gemini/gemini-cli/pull/27145)
+- Proposal: deterministic encoding for child-process I/O by @kaluchi in
+  [#27247](https://github.com/google-gemini/gemini-cli/pull/27247)
+- feat(cli): add Sublime Text and Emacs Client editors, improve error messages
+  and documentation by @alberti42 in
+  [#21090](https://github.com/google-gemini/gemini-cli/pull/21090)
+- Changelog for v0.43.0-preview.1 by @gemini-cli-robot in
+  [#27297](https://github.com/google-gemini/gemini-cli/pull/27297)
+- fix(devtools): bundle devtools package to avoid resolution errors by
+  @rmedranollamas in
+  [#27250](https://github.com/google-gemini/gemini-cli/pull/27250)
+- fix(cli): integrate PolicyEngine into ACP session to prevent deadlocks
+  (#23507) by @cocosheng-g in
+  [#27252](https://github.com/google-gemini/gemini-cli/pull/27252)
+- fix: robust ripgrep path resolution and 1p hermetic execution support by
+  @cocosheng-g in
+  [#27253](https://github.com/google-gemini/gemini-cli/pull/27253)
+- refactor: decouple stored session deletion from ChatRecordingService (#22920)
+  by @yuvrajangadsingh in
+  [#27039](https://github.com/google-gemini/gemini-cli/pull/27039)
+- fix(core): improve Alpine shell compatibility by @dibyx in
+  [#26770](https://github.com/google-gemini/gemini-cli/pull/26770)
+- fix(core): generalize MCP compliance fix for tool results by @cocosheng-g in
+  [#27045](https://github.com/google-gemini/gemini-cli/pull/27045)
+- fix(scripts): scrub CI env vars in dev to keep interactive mode by @Hashaam101
+  in [#27159](https://github.com/google-gemini/gemini-cli/pull/27159)
+- fix(core): Added date field for the GCal MCP by @devr0306 in
+  [#27251](https://github.com/google-gemini/gemini-cli/pull/27251)
+- fix(core): centralize path validation to prevent crashes from malformed
+  prompts by @cocosheng-g in
+  [#27211](https://github.com/google-gemini/gemini-cli/pull/27211)
+- fix(core): prevent SIGHUP kills in PTY environments (WSL2/Kitty/Alacritty) by
+  @ProthamD in [#27267](https://github.com/google-gemini/gemini-cli/pull/27267)
+- fix(core): dynamic fallback routing for exhausted quota models by @cocosheng-g
+  in [#27315](https://github.com/google-gemini/gemini-cli/pull/27315)
+- Auto detect pnpm global installation path for macOS and Windows by @tisonkun
+  in [#22748](https://github.com/google-gemini/gemini-cli/pull/22748)
+- fix(windows): resolve interactive shell arrow-key navigation on Windows by
+  @KumarADITHYA123 in
+  [#23505](https://github.com/google-gemini/gemini-cli/pull/23505)
+- ci: robust stale issue lifecycle and consolidated triage labels by
+  @cocosheng-g in
+  [#27015](https://github.com/google-gemini/gemini-cli/pull/27015)
+- fix(context): Ensure last message is processed. by @joshualitt in
+  [#27232](https://github.com/google-gemini/gemini-cli/pull/27232)
+- chore/release: bump version to 0.44.0-nightly.20260521.g57c42a5c4 by
+  @gemini-cli-robot in
+  [#27324](https://github.com/google-gemini/gemini-cli/pull/27324)
+- fix(ui): added volta to auto update check by @devr0306 in
+  [#27353](https://github.com/google-gemini/gemini-cli/pull/27353)
+- perf: optimize issue triage and lifecycle management by @cocosheng-g in
+  [#27346](https://github.com/google-gemini/gemini-cli/pull/27346)
 
 **Full Changelog**:
-https://github.com/google-gemini/gemini-cli/compare/v0.42.0-preview.2...v0.43.0-preview.0
+https://github.com/google-gemini/gemini-cli/compare/v0.43.0-preview.1...v0.44.0-preview.0

docs/cli/auto-memory.md

@@ -29,11 +29,10 @@ You'll use Auto Memory when you want to:
   avoid them.
 - **Bootstrap a skills library** without writing every `SKILL.md` by hand.
 
-Auto Memory complements—but does not replace—the
-[`save_memory` tool](../tools/memory.md), which captures single facts into
-`GEMINI.md` when the agent explicitly calls it. Auto Memory infers candidates
-from past sessions, writes reviewable patches or skill drafts, and never applies
-them without your approval.
+Auto Memory complements direct memory-file editing. The agent can still persist
+explicit user instructions by editing the appropriate Markdown memory file; Auto
+Memory infers candidates from past sessions, writes reviewable patches or skill
+drafts, and never applies them without your approval.
 
 ## Prerequisites
 

docs/cli/gemini-md.md

@@ -65,8 +65,6 @@ You can interact with the loaded context files by using the `/memory` command.
   being provided to the model.
 - **`/memory reload`**: Forces a re-scan and reload of all `GEMINI.md` files
   from all configured locations.
-- **`/memory add <text>`**: Appends your text to your global
-  `~/.gemini/GEMINI.md` file. This lets you add persistent memories on the fly.
 
 ## Modularize context with imports
 

docs/cli/plan-mode.md

@@ -138,7 +138,6 @@ These are the only allowed tools:
   [`replace`](../tools/file-system.md#6-replace-edit) only allowed for `.md`
   files in the `~/.gemini/tmp/<project>/<session-id>/plans/` directory or your
   [custom plans directory](#custom-plan-directory-and-policies).
-- **Memory:** [`save_memory`](../tools/memory.md)
 - **Skills:** [`activate_skill`](../cli/skills.md) (allows loading specialized
   instructions and resources in a read-only manner)
 

docs/cli/settings.md

@@ -40,6 +40,7 @@ they appear in the UI.
 | Enable Session Cleanup        | `general.sessionRetention.enabled` | Enable automatic session cleanup                                                                                                                                                                                                                              | `true`      |
 | Keep chat history             | `general.sessionRetention.maxAge`  | Automatically delete chats older than this time period (e.g., "30d", "7d", "24h", "1w")                                                                                                                                                                       | `"30d"`     |
 | Topic & Update Narration      | `general.topicUpdateNarration`     | Enable the Topic & Update communication model for reduced chattiness and structured progress reporting.                                                                                                                                                       | `true`      |
+| Log RAG Snippets              | `general.logRagSnippets`           | Log full Code Customization (RAG) retrieved snippets to a local file for debugging.                                                                                                                                                                           | `false`     |
 
 ### Output
 
@@ -162,25 +163,24 @@ they appear in the UI.
 
 ### Experimental
 
-| UI Label                                             | Setting                                         | Description                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          | Default              |
-| ---------------------------------------------------- | ----------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------- |
-| Gemma Models                                         | `experimental.gemma`                            | Enable access to Gemma 4 models via Gemini API.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      | `true`               |
-| Voice Mode                                           | `experimental.voiceMode`                        | Enable experimental voice dictation and commands (/voice, /voice model).                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                             | `false`              |
-| Voice Activation Mode                                | `experimental.voice.activationMode`             | How to trigger voice recording with the Space key.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                   | `"push-to-talk"`     |
-| Voice Transcription Backend                          | `experimental.voice.backend`                    | The backend to use for voice transcription. Note: When using the Gemini Live backend, voice recordings are sent to Google Cloud for transcription.                                                                                                                                                                                                                                                                                                                                                                                                                                                                   | `"gemini-live"`      |
-| Whisper Model                                        | `experimental.voice.whisperModel`               | The Whisper model to use for local transcription.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    | `"ggml-base.en.bin"` |
-| Voice Stop Grace Period (ms)                         | `experimental.voice.stopGracePeriodMs`          | How long to wait for final transcription after stopping recording.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                   | `4000`               |
-| Enable Git Worktrees                                 | `experimental.worktrees`                        | Enable automated Git worktree management for parallel work.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          | `false`              |
-| Use OSC 52 Paste                                     | `experimental.useOSC52Paste`                    | Use OSC 52 for pasting. This may be more robust than the default system when using remote terminal sessions (if your terminal is configured to allow it).                                                                                                                                                                                                                                                                                                                                                                                                                                                            | `false`              |
-| Use OSC 52 Copy                                      | `experimental.useOSC52Copy`                     | Use OSC 52 for copying. This may be more robust than the default system when using remote terminal sessions (if your terminal is configured to allow it).                                                                                                                                                                                                                                                                                                                                                                                                                                                            | `false`              |
-| Model Steering                                       | `experimental.modelSteering`                    | Enable model steering (user hints) to guide the model during tool execution.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                         | `false`              |
-| Direct Web Fetch                                     | `experimental.directWebFetch`                   | Enable web fetch behavior that bypasses LLM summarization.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                           | `false`              |
-| Enable Gemma Model Router                            | `experimental.gemmaModelRouter.enabled`         | Enable the Gemma Model Router (experimental). Requires a local endpoint serving Gemma via the Gemini API using LiteRT-LM shim.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                       | `false`              |
-| Auto-start LiteRT Server                             | `experimental.gemmaModelRouter.autoStartServer` | Automatically start the LiteRT-LM server when Gemini CLI starts and the Gemma router is enabled.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                     | `false`              |
-| Memory v2                                            | `experimental.memoryV2`                         | Disable the built-in save_memory tool and let the main agent persist project context by editing markdown files directly with edit/write_file. Route facts across four tiers: team-shared conventions go to project GEMINI.md files, project-specific personal notes go to the per-project private memory folder (MEMORY.md as index + sibling .md files for detail), and cross-project personal preferences go to the global ~/.gemini/GEMINI.md (the only file under ~/.gemini/ that the agent can edit — settings, credentials, etc. remain off-limits). Set to false to fall back to the legacy save_memory tool. | `true`               |
-| Auto Memory                                          | `experimental.autoMemory`                       | Automatically extract memory patches and skills from past sessions in the background. Every change is written as a unified diff `.patch` file under `<projectMemoryDir>/.inbox/<kind>/` and held for review in /memory inbox; nothing is applied until you approve it.                                                                                                                                                                                                                                                                                                                                               | `false`              |
-| Use the generalist profile to manage agent contexts. | `experimental.generalistProfile`                | Suitable for general coding and software development tasks.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          | `false`              |
-| Enable Context Management                            | `experimental.contextManagement`                | Enable logic for context management.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                 | `false`              |
+| UI Label                                             | Setting                                         | Description                                                                                                                                                                                                                                                            | Default              |
+| ---------------------------------------------------- | ----------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------- |
+| Gemma Models                                         | `experimental.gemma`                            | Enable access to Gemma 4 models via Gemini API.                                                                                                                                                                                                                        | `true`               |
+| Voice Mode                                           | `experimental.voiceMode`                        | Enable experimental voice dictation and commands (/voice, /voice model).                                                                                                                                                                                               | `false`              |
+| Voice Activation Mode                                | `experimental.voice.activationMode`             | How to trigger voice recording with the Space key.                                                                                                                                                                                                                     | `"push-to-talk"`     |
+| Voice Transcription Backend                          | `experimental.voice.backend`                    | The backend to use for voice transcription. Note: When using the Gemini Live backend, voice recordings are sent to Google Cloud for transcription.                                                                                                                     | `"gemini-live"`      |
+| Whisper Model                                        | `experimental.voice.whisperModel`               | The Whisper model to use for local transcription.                                                                                                                                                                                                                      | `"ggml-base.en.bin"` |
+| Voice Stop Grace Period (ms)                         | `experimental.voice.stopGracePeriodMs`          | How long to wait for final transcription after stopping recording.                                                                                                                                                                                                     | `4000`               |
+| Enable Git Worktrees                                 | `experimental.worktrees`                        | Enable automated Git worktree management for parallel work.                                                                                                                                                                                                            | `false`              |
+| Use OSC 52 Paste                                     | `experimental.useOSC52Paste`                    | Use OSC 52 for pasting. This may be more robust than the default system when using remote terminal sessions (if your terminal is configured to allow it).                                                                                                              | `false`              |
+| Use OSC 52 Copy                                      | `experimental.useOSC52Copy`                     | Use OSC 52 for copying. This may be more robust than the default system when using remote terminal sessions (if your terminal is configured to allow it).                                                                                                              | `false`              |
+| Model Steering                                       | `experimental.modelSteering`                    | Enable model steering (user hints) to guide the model during tool execution.                                                                                                                                                                                           | `false`              |
+| Direct Web Fetch                                     | `experimental.directWebFetch`                   | Enable web fetch behavior that bypasses LLM summarization.                                                                                                                                                                                                             | `false`              |
+| Enable Gemma Model Router                            | `experimental.gemmaModelRouter.enabled`         | Enable the Gemma Model Router (experimental). Requires a local endpoint serving Gemma via the Gemini API using LiteRT-LM shim.                                                                                                                                         | `false`              |
+| Auto-start LiteRT Server                             | `experimental.gemmaModelRouter.autoStartServer` | Automatically start the LiteRT-LM server when Gemini CLI starts and the Gemma router is enabled.                                                                                                                                                                       | `false`              |
+| Auto Memory                                          | `experimental.autoMemory`                       | Automatically extract memory patches and skills from past sessions in the background. Every change is written as a unified diff `.patch` file under `<projectMemoryDir>/.inbox/<kind>/` and held for review in /memory inbox; nothing is applied until you approve it. | `false`              |
+| Use the generalist profile to manage agent contexts. | `experimental.generalistProfile`                | Suitable for general coding and software development tasks.                                                                                                                                                                                                            | `false`              |
+| Enable Context Management                            | `experimental.contextManagement`                | Enable logic for context management.                                                                                                                                                                                                                                   | `false`              |
 
 ### Skills
 

docs/cli/tutorials/memory-management.md

@@ -71,8 +71,8 @@ Just tell the agent to remember something.
 
 **Prompt:** `Remember that I prefer using 'const' over 'let' wherever possible.`
 
-The agent will use the `save_memory` tool to store this fact in your global
-memory file.
+The agent will edit the appropriate memory Markdown file, so the fact is loaded
+in future sessions.
 
 **Prompt:** `Save the fact that the staging server IP is 10.0.0.5.`
 

docs/extensions/reference.md

@@ -210,6 +210,22 @@ To update an extension's settings:
 gemini extensions config <name> [setting] [--scope <scope>]
 ```
 
+#### Environment variable sanitization
+
+For security reasons, sensitive environment variables are filtered out and not
+passed to extensions or MCP servers by default.
+
+Extensions **will not** inherit the user's full shell environment variables.
+They will only have access to:
+
+1. Standard safe variables (e.g., `HOME`, `PATH`, `TMPDIR`).
+2. Variables explicitly declared and requested in the `gemini-extension.json`
+   manifest via the `settings` array (using the `envVar` property).
+
+If your extension requires specific environment variables (like an API key,
+custom host, or config path), you **must** declare them in the `settings` array
+so the CLI can allowlist them for use within the extension.
+
 ### Custom commands
 
 Provide [custom commands](../cli/custom-commands.md) by placing TOML files in a

docs/extensions/writing-extensions.md

@@ -159,6 +159,13 @@ When a user installs this extension, Gemini CLI will prompt them to enter the
 `sensitive` is true) and injected into the MCP server's process as the
 `MY_SERVICE_API_KEY` environment variable.
 
+> **Important (Environment Variable Sanitization):** For security reasons,
+> sensitive environment variables are filtered out and not passed to extensions
+> or MCP servers by default. Extensions will _only_ have access to environment
+> variables that are explicitly declared in the `settings` array using the
+> `envVar` property, plus a few standard safe variables. Do not expect host
+> environment variables to be available otherwise.
+
 ## Step 4: Link your extension
 
 Link your extension to your Gemini CLI installation for local development.

docs/get-started/installation.mdx

@@ -111,8 +111,8 @@ You can also run Gemini CLI using one of the following advanced methods:
     directly. This is useful for environments where you only have Docker and want
     to run the CLI.
     ```bash
-    # Run the published sandbox image
-    docker run --rm -it us-docker.pkg.dev/gemini-code-dev/gemini-cli/sandbox:0.1.1
+    # Run the published sandbox image for a specified CLI version
+    docker run --rm -it us-docker.pkg.dev/gemini-code-dev/gemini-cli/sandbox:0.42.0-nightly.20260428.g59b2dea0e
     ```
   - **Using the `--sandbox` flag:** If you have Gemini CLI installed locally
     (using the standard installation described above), you can instruct it to run

docs/reference/commands.md

@@ -265,9 +265,6 @@ Slash commands provide meta-level control over the CLI itself.
 - **Description:** Manage the AI's instructional context (hierarchical memory
   loaded from `GEMINI.md` files).
 - **Sub-commands:**
-  - **`add`**:
-    - **Description:** Adds the following text to the AI's memory. Usage:
-      `/memory add <text to remember>`
   - **`list`**:
     - **Description:** Lists the paths of the GEMINI.md files in use for
       hierarchical memory.

docs/reference/configuration.md

@@ -105,9 +105,19 @@ their corresponding top-level category object in your `settings.json` file.
 
 #### `general`
 
-- **`general.preferredEditor`** (string):
-  - **Description:** The preferred editor to open files in.
+- **`general.preferredEditor`** (enum):
+  - **Description:** The preferred editor to open files in. Must be one of the
+    built-in supported identifiers. Use /editor in the CLI to pick
+    interactively, or leave unset to use $VISUAL/$EDITOR.
   - **Default:** `undefined`
+  - **Values:** `"vscode"`, `"vscodium"`, `"windsurf"`, `"cursor"`, `"zed"`,
+    `"antigravity"`, `"sublimetext"`, `"lapce"`, `"nova"`, `"bbedit"`, `"vim"`,
+    `"neovim"`, `"emacs"`, `"hx"`, `"emacsclient"`, `"micro"`
+
+- **`general.openEditorInNewWindow`** (boolean):
+  - **Description:** Open VS Code-family editors in a new window when editing
+    files.
+  - **Default:** `false`
 
 - **`general.vimMode`** (boolean):
   - **Description:** Enable Vim keybindings
@@ -203,6 +213,11 @@ their corresponding top-level category object in your `settings.json` file.
     chattiness and structured progress reporting.
   - **Default:** `true`
 
+- **`general.logRagSnippets`** (boolean):
+  - **Description:** Log full Code Customization (RAG) retrieved snippets to a
+    local file for debugging.
+  - **Default:** `false`
+
 #### `output`
 
 - **`output.format`** (enum):
@@ -545,6 +560,24 @@ their corresponding top-level category object in your `settings.json` file.
           "model": "gemini-3-flash-preview"
         }
       },
+      "gemini-3.1-pro-preview": {
+        "extends": "chat-base-3",
+        "modelConfig": {
+          "model": "gemini-3.1-pro-preview"
+        }
+      },
+      "gemini-3.1-pro-preview-customtools": {
+        "extends": "chat-base-3",
+        "modelConfig": {
+          "model": "gemini-3.1-pro-preview-customtools"
+        }
+      },
+      "gemini-3.1-flash-lite-preview": {
+        "extends": "chat-base-3",
+        "modelConfig": {
+          "model": "gemini-3.1-flash-lite-preview"
+        }
+      },
       "gemini-2.5-pro": {
         "extends": "chat-base-2.5",
         "modelConfig": {
@@ -1014,12 +1047,6 @@ their corresponding top-level category object in your `settings.json` file.
       "auto": {
         "default": "gemini-3-pro-preview",
         "contexts": [
-          {
-            "condition": {
-              "releaseChannel": "stable"
-            },
-            "target": "gemini-2.5-pro"
-          },
           {
             "condition": {
               "hasAccessToPreview": false
@@ -1163,13 +1190,6 @@ their corresponding top-level category object in your `settings.json` file.
             },
             "target": "gemini-2.5-pro"
           },
-          {
-            "condition": {
-              "releaseChannel": "stable",
-              "requestedModels": ["auto"]
-            },
-            "target": "gemini-2.5-pro"
-          },
           {
             "condition": {
               "requestedModels": ["gemini-2.5-pro", "auto-gemini-2.5"]
@@ -1831,6 +1851,12 @@ their corresponding top-level category object in your `settings.json` file.
   - **Default:** `false`
   - **Requires restart:** Yes
 
+- **`experimental.adk.agentSessionSubagentEnabled`** (boolean):
+  - **Description:** Route subagent invocations through the AgentSession
+    protocol instead of legacy executors.
+  - **Default:** `false`
+  - **Requires restart:** Yes
+
 - **`experimental.enableAgents`** (boolean):
   - **Description:** Enable local and remote subagents.
   - **Default:** `true`
@@ -1867,13 +1893,6 @@ their corresponding top-level category object in your `settings.json` file.
   - **Default:** `false`
   - **Requires restart:** Yes
 
-- **`experimental.jitContext`** (boolean):
-  - **Description:** Enable Just-In-Time (JIT) context loading. Defaults to
-    true; set to false to opt out and load all GEMINI.md files into the system
-    instruction up-front.
-  - **Default:** `true`
-  - **Requires restart:** Yes
-
 - **`experimental.useOSC52Paste`** (boolean):
   - **Description:** Use OSC 52 for pasting. This may be more robust than the
     default system when using remote terminal sessions (if your terminal is
@@ -1936,19 +1955,6 @@ their corresponding top-level category object in your `settings.json` file.
   - **Default:** `"gemma3-1b-gpu-custom"`
   - **Requires restart:** Yes
 
-- **`experimental.memoryV2`** (boolean):
-  - **Description:** Disable the built-in save_memory tool and let the main
-    agent persist project context by editing markdown files directly with
-    edit/write_file. Route facts across four tiers: team-shared conventions go
-    to project GEMINI.md files, project-specific personal notes go to the
-    per-project private memory folder (MEMORY.md as index + sibling .md files
-    for detail), and cross-project personal preferences go to the global
-    ~/.gemini/GEMINI.md (the only file under ~/.gemini/ that the agent can edit
-    — settings, credentials, etc. remain off-limits). Set to false to fall back
-    to the legacy save_memory tool.
-  - **Default:** `true`
-  - **Requires restart:** Yes
-
 - **`experimental.stressTestProfile`** (boolean):
   - **Description:** Significantly lowers token limits to force early garbage
     collection and distillation for testing purposes.
@@ -1968,6 +1974,11 @@ their corresponding top-level category object in your `settings.json` file.
   - **Default:** `false`
   - **Requires restart:** Yes
 
+- **`experimental.powerUserProfile`** (boolean):
+  - **Description:** Less cache friendly version of the generalist profile.
+  - **Default:** `false`
+  - **Requires restart:** Yes
+
 - **`experimental.contextManagement`** (boolean):
   - **Description:** Enable logic for context management.
   - **Default:** `false`

docs/reference/tools.md

@@ -120,7 +120,6 @@ each tool.
 | :----------------------------------------------- | :------ | :----------------------------------------------------------------------------------- |
 | [`activate_skill`](../tools/activate-skill.md)   | `Other` | Loads specialized procedural expertise from the `.gemini/skills` directory.          |
 | [`get_internal_docs`](../tools/internal-docs.md) | `Think` | Accesses Gemini CLI's own documentation for accurate answers about its capabilities. |
-| [`save_memory`](../tools/memory.md)              | `Think` | Persists specific facts and project details to your `GEMINI.md` file.                |
 
 ### Planning
 
@@ -173,7 +172,6 @@ representation of each tool's arguments.
 | `replace`                | `file_path`, `old_string`, `new_string`, `instruction`, `allow_multiple`                                                                                                                             |
 | `ask_user`               | `questions` (array of `question`, `header`, `type`, `options`)                                                                                                                                       |
 | `write_todos`            | `todos` (array of `description`, `status`)                                                                                                                                                           |
-| `save_memory`            | `fact`                                                                                                                                                                                               |
 | `activate_skill`         | `name`                                                                                                                                                                                               |
 | `get_internal_docs`      | `path`                                                                                                                                                                                               |
 | `enter_plan_mode`        | `reason`                                                                                                                                                                                             |

docs/tools/mcp-server.md

@@ -221,8 +221,10 @@ spawning MCP server processes.
 #### Automatic redaction
 
 By default, the CLI redacts sensitive environment variables from the base
-environment (inherited from the host process) to prevent unintended exposure to
-third-party MCP servers. This includes:
+environment (inherited from the host process). This prevents the accidental
+leakage of sensitive host environment variables (like AWS keys or GitHub tokens)
+to arbitrary third-party MCP servers that might execute malicious code or log
+your environment. This includes:
 
 - Core project keys: `GEMINI_API_KEY`, `GOOGLE_API_KEY`, etc.
 - Variables matching sensitive patterns: `*TOKEN*`, `*SECRET*`, `*PASSWORD*`,
@@ -232,7 +234,8 @@ third-party MCP servers. This includes:
 #### Explicit overrides
 
 If an environment variable must be passed to an MCP server, you must explicitly
-state it in the `env` property of the server configuration in `settings.json`.
+state it in the `env` property of the server configuration in `settings.json`
+(or `mcp_config.json` if configuring standard MCP clients or remote skills).
 Explicitly defined variables (including those from extensions) are trusted and
 are **not** subjected to the automatic redaction process.
 
@@ -247,6 +250,24 @@ specific data with that server.
 > (for example, `"MY_KEY": "$MY_KEY"`) to securely pull the value from your host
 > environment at runtime.
 
+**Example: Passing a GitHub Token securely to the
+[official GitHub MCP server](https://github.com/github/github-mcp-server) via
+`mcp_config.json`**
+
+```json
+{
+  "mcpServers": {
+    "github": {
+      "command": "npx",
+      "args": ["-y", "@github/github-mcp-server"],
+      "env": {
+        "GITHUB_PERSONAL_ACCESS_TOKEN": "$GITHUB_PERSONAL_ACCESS_TOKEN"
+      }
+    }
+  }
+}
+```
+
 ### OAuth support for remote MCP servers
 
 Gemini CLI supports OAuth 2.0 authentication for remote MCP servers using SSE or

docs/tools/memory.md

@@ -1,25 +1,22 @@
-# Memory tool (`save_memory`)
+# Memory files
 
-The `save_memory` tool allows the Gemini agent to persist specific facts, user
-preferences, and project details across sessions.
+Gemini CLI persists durable facts, user preferences, and project details by
+editing Markdown memory files directly.
 
 ## Technical reference
 
-This tool appends information to the `## Gemini Added Memories` section of your
-global `GEMINI.md` file (typically located at `~/.gemini/GEMINI.md`).
-
-### Arguments
-
-- `fact` (string, required): A clear, self-contained statement in natural
-  language.
+The agent routes memories to the appropriate Markdown file: shared project
+instructions go in repository `GEMINI.md` files, private project notes go in the
+per-project private memory folder, and cross-project personal preferences go in
+the global `~/.gemini/GEMINI.md` file.
 
 ## Technical behavior
 
-- **Storage:** Appends to the global context file in the user's home directory.
+- **Storage:** Edits Markdown files with `write_file` or `replace`.
 - **Loading:** The stored facts are automatically included in the hierarchical
   context system for all future sessions.
-- **Format:** Saves data as a bulleted list item within a dedicated Markdown
-  section.
+- **Format:** Keeps durable instructions concise and avoids duplicating the same
+  fact across multiple memory tiers.
 
 ## Use cases
 

esbuild.config.js

@@ -63,7 +63,6 @@ const external = [
   '@lydell/node-pty-win32-arm64',
   '@lydell/node-pty-win32-x64',
   '@github/keytar',
-  '@google/gemini-cli-devtools',
 ];
 
 const baseConfig = {
@@ -102,11 +101,46 @@ const cliConfig = {
   plugins: createWasmPlugins(),
   alias: {
     'is-in-ci': path.resolve(__dirname, 'packages/cli/src/patches/is-in-ci.ts'),
+    'https-proxy-agent': path.resolve(
+      __dirname,
+      'packages/cli/src/patches/https-proxy-agent.ts',
+    ),
+    'http-proxy-agent': path.resolve(
+      __dirname,
+      'packages/cli/src/patches/http-proxy-agent.ts',
+    ),
+    '@google/gemini-cli-devtools': path.resolve(
+      __dirname,
+      'packages/devtools/src/index.ts',
+    ),
     ...commonAliases,
   },
   metafile: true,
 };
 
+const workerConfig = {
+  ...baseConfig,
+  banner: {
+    js: `const require = (await import('node:module')).createRequire(import.meta.url); const __chunk_filename = (await import('node:url')).fileURLToPath(import.meta.url); const __chunk_dirname = (await import('node:path')).dirname(__chunk_filename);`,
+  },
+  entryPoints: {
+    'worker/worker-entry': path.join(
+      path.dirname(require.resolve('ink')),
+      'worker/worker-entry.js',
+    ),
+  },
+  outdir: 'bundle',
+  define: {
+    __filename: '__chunk_filename',
+    __dirname: '__chunk_dirname',
+    'process.env.NODE_ENV': JSON.stringify(
+      process.env.NODE_ENV || 'production',
+    ),
+  },
+  plugins: createWasmPlugins(),
+  alias: commonAliases,
+};
+
 const a2aServerConfig = {
   ...baseConfig,
   banner: {
@@ -133,13 +167,18 @@ Promise.allSettled([
       writeFileSync('./bundle/esbuild.json', JSON.stringify(metafile, null, 2));
     }
   }),
+  esbuild.build(workerConfig),
   esbuild.build(a2aServerConfig),
 ]).then((results) => {
-  const [cliResult, a2aResult] = results;
+  const [cliResult, workerResult, a2aResult] = results;
   if (cliResult.status === 'rejected') {
     console.error('gemini.js build failed:', cliResult.reason);
     process.exit(1);
   }
+  if (workerResult.status === 'rejected') {
+    console.error('worker-entry.js build failed:', workerResult.reason);
+    process.exit(1);
+  }
   // error in a2a-server bundling will not stop gemini.js bundling process
   if (a2aResult.status === 'rejected') {
     console.warn('a2a-server build failed:', a2aResult.reason);

evals/calendar-all-day.eval.ts

@@ -0,0 +1,33 @@
+import { evalTest } from './test-helper.js';
+import { expect } from 'vitest';
+
+evalTest('USUALLY_PASSES', {
+  suiteName: 'default',
+  suiteType: 'behavioral',
+  name: 'should create an all-day event using the optional date field',
+  prompt:
+    'Create an all-day event for 2026-05-20 titled "Company Retreat". Do not use a specific time.',
+  setup: async (rig) => {
+    rig.addTestMcpServer('workspace-server', 'google-workspace');
+  },
+  assert: async (rig) => {
+    const toolLogs = rig.readToolLogs();
+    console.log('TOOL LOGS:', JSON.stringify(toolLogs, null, 2));
+
+    const createEventCall = toolLogs.find(
+      (log) =>
+        log.toolRequest.name === 'mcp_workspace-server_calendar.createEvent',
+    );
+
+    expect(createEventCall).toBeDefined();
+
+    const args = JSON.parse(createEventCall!.toolRequest.args);
+
+    expect(args?.start).toHaveProperty('date');
+    expect(args?.start).not.toHaveProperty('dateTime');
+    expect(args?.start?.date).toBe('2026-05-20');
+
+    expect(args?.end).toHaveProperty('date');
+    expect(args?.end).not.toHaveProperty('dateTime');
+  },
+});

evals/memory_persistence.eval.ts

@@ -11,11 +11,7 @@ import {
   loadConversationRecord,
   SESSION_FILE_PREFIX,
 } from '@google/gemini-cli-core';
-import {
-  evalTest,
-  assertModelHasOutput,
-  checkModelOutputContent,
-} from './test-helper.js';
+import { evalTest, assertModelHasOutput } from './test-helper.js';
 
 function findDir(base: string, name: string): string | null {
   if (!fs.existsSync(base)) return null;
@@ -77,336 +73,13 @@ async function waitForSessionScratchpad(
   return loadLatestSessionRecord(homeDir, sessionId);
 }
 
-describe('save_memory', () => {
-  const TEST_PREFIX = 'Save memory test: ';
-  const rememberingFavoriteColor = "Agent remembers user's favorite color";
-  evalTest('ALWAYS_PASSES', {
-    suiteName: 'default',
-    suiteType: 'behavioral',
-    name: rememberingFavoriteColor,
-    params: {
-      settings: {
-        experimental: { memoryV2: false },
-      },
-    },
-
-    prompt: `remember that my favorite color is  blue.
-  
-    what is my favorite color? tell me that and surround it with $ symbol`,
-    assert: async (rig, result) => {
-      const wasToolCalled = await rig.waitForToolCall('save_memory');
-      expect(wasToolCalled, 'Expected save_memory tool to be called').toBe(
-        true,
-      );
-
-      assertModelHasOutput(result);
-      checkModelOutputContent(result, {
-        expectedContent: 'blue',
-        testName: `${TEST_PREFIX}${rememberingFavoriteColor}`,
-      });
-    },
-  });
-  const rememberingCommandRestrictions = 'Agent remembers command restrictions';
-  evalTest('USUALLY_PASSES', {
-    suiteName: 'default',
-    suiteType: 'behavioral',
-    name: rememberingCommandRestrictions,
-    params: {
-      settings: {
-        experimental: { memoryV2: false },
-      },
-    },
-
-    prompt: `I don't want you to ever run npm commands.`,
-    assert: async (rig, result) => {
-      const wasToolCalled = await rig.waitForToolCall('save_memory');
-      expect(wasToolCalled, 'Expected save_memory tool to be called').toBe(
-        true,
-      );
-
-      assertModelHasOutput(result);
-      checkModelOutputContent(result, {
-        expectedContent: [/not run npm commands|remember|ok/i],
-        testName: `${TEST_PREFIX}${rememberingCommandRestrictions}`,
-      });
-    },
-  });
-
-  const rememberingWorkflow = 'Agent remembers workflow preferences';
-  evalTest('USUALLY_PASSES', {
-    suiteName: 'default',
-    suiteType: 'behavioral',
-    name: rememberingWorkflow,
-    params: {
-      settings: {
-        experimental: { memoryV2: false },
-      },
-    },
-
-    prompt: `I want you to always lint after building.`,
-    assert: async (rig, result) => {
-      const wasToolCalled = await rig.waitForToolCall('save_memory');
-      expect(wasToolCalled, 'Expected save_memory tool to be called').toBe(
-        true,
-      );
-
-      assertModelHasOutput(result);
-      checkModelOutputContent(result, {
-        expectedContent: [/always|ok|remember|will do/i],
-        testName: `${TEST_PREFIX}${rememberingWorkflow}`,
-      });
-    },
-  });
-
-  const ignoringTemporaryInformation =
-    'Agent ignores temporary conversation details';
-  evalTest('ALWAYS_PASSES', {
-    suiteName: 'default',
-    suiteType: 'behavioral',
-    name: ignoringTemporaryInformation,
-    params: {
-      settings: {
-        experimental: { memoryV2: false },
-      },
-    },
-
-    prompt: `I'm going to get a coffee.`,
-    assert: async (rig, result) => {
-      await rig.waitForTelemetryReady();
-      const wasToolCalled = rig
-        .readToolLogs()
-        .some((log) => log.toolRequest.name === 'save_memory');
-      expect(
-        wasToolCalled,
-        'save_memory should not be called for temporary information',
-      ).toBe(false);
-
-      assertModelHasOutput(result);
-      checkModelOutputContent(result, {
-        testName: `${TEST_PREFIX}${ignoringTemporaryInformation}`,
-        forbiddenContent: [/remember|will do/i],
-      });
-    },
-  });
-
-  const rememberingPetName = "Agent remembers user's pet's name";
-  evalTest('ALWAYS_PASSES', {
-    suiteName: 'default',
-    suiteType: 'behavioral',
-    name: rememberingPetName,
-    params: {
-      settings: {
-        experimental: { memoryV2: false },
-      },
-    },
-
-    prompt: `Please remember that my dog's name is Buddy.`,
-    assert: async (rig, result) => {
-      const wasToolCalled = await rig.waitForToolCall('save_memory');
-      expect(wasToolCalled, 'Expected save_memory tool to be called').toBe(
-        true,
-      );
-
-      assertModelHasOutput(result);
-      checkModelOutputContent(result, {
-        expectedContent: [/Buddy/i],
-        testName: `${TEST_PREFIX}${rememberingPetName}`,
-      });
-    },
-  });
-
-  const rememberingCommandAlias = 'Agent remembers custom command aliases';
-  evalTest('ALWAYS_PASSES', {
-    suiteName: 'default',
-    suiteType: 'behavioral',
-    name: rememberingCommandAlias,
-    params: {
-      settings: {
-        experimental: { memoryV2: false },
-      },
-    },
-
-    prompt: `When I say 'start server', you should run 'npm run dev'.`,
-    assert: async (rig, result) => {
-      const wasToolCalled = await rig.waitForToolCall('save_memory');
-      expect(wasToolCalled, 'Expected save_memory tool to be called').toBe(
-        true,
-      );
-
-      assertModelHasOutput(result);
-      checkModelOutputContent(result, {
-        expectedContent: [/npm run dev|start server|ok|remember|will do/i],
-        testName: `${TEST_PREFIX}${rememberingCommandAlias}`,
-      });
-    },
-  });
-
-  const savingDbSchemaLocationAsProjectMemory =
-    'Agent saves workspace database schema location as project memory';
-  evalTest('USUALLY_PASSES', {
-    suiteName: 'default',
-    suiteType: 'behavioral',
-    name: savingDbSchemaLocationAsProjectMemory,
-    params: {
-      settings: {
-        experimental: { memoryV2: false },
-      },
-    },
-    prompt: `The database schema for this workspace is located in \`db/schema.sql\`.`,
-    assert: async (rig, result) => {
-      const wasToolCalled = await rig.waitForToolCall(
-        'save_memory',
-        undefined,
-        (args) => {
-          try {
-            const params = JSON.parse(args);
-            return params.scope === 'project';
-          } catch {
-            return false;
-          }
-        },
-      );
-      expect(
-        wasToolCalled,
-        'Expected save_memory to be called with scope="project" for workspace-specific information',
-      ).toBe(true);
-
-      assertModelHasOutput(result);
-    },
-  });
-
-  const rememberingCodingStyle =
-    "Agent remembers user's coding style preference";
-  evalTest('ALWAYS_PASSES', {
-    suiteName: 'default',
-    suiteType: 'behavioral',
-    name: rememberingCodingStyle,
-    params: {
-      settings: {
-        experimental: { memoryV2: false },
-      },
-    },
-
-    prompt: `I prefer to use tabs instead of spaces for indentation.`,
-    assert: async (rig, result) => {
-      const wasToolCalled = await rig.waitForToolCall('save_memory');
-      expect(wasToolCalled, 'Expected save_memory tool to be called').toBe(
-        true,
-      );
-
-      assertModelHasOutput(result);
-      checkModelOutputContent(result, {
-        expectedContent: [/tabs instead of spaces|ok|remember|will do/i],
-        testName: `${TEST_PREFIX}${rememberingCodingStyle}`,
-      });
-    },
-  });
-
-  const savingBuildArtifactLocationAsProjectMemory =
-    'Agent saves workspace build artifact location as project memory';
-  evalTest('USUALLY_PASSES', {
-    suiteName: 'default',
-    suiteType: 'behavioral',
-    name: savingBuildArtifactLocationAsProjectMemory,
-    params: {
-      settings: {
-        experimental: { memoryV2: false },
-      },
-    },
-    prompt: `In this workspace, build artifacts are stored in the \`dist/artifacts\` directory.`,
-    assert: async (rig, result) => {
-      const wasToolCalled = await rig.waitForToolCall(
-        'save_memory',
-        undefined,
-        (args) => {
-          try {
-            const params = JSON.parse(args);
-            return params.scope === 'project';
-          } catch {
-            return false;
-          }
-        },
-      );
-      expect(
-        wasToolCalled,
-        'Expected save_memory to be called with scope="project" for workspace-specific information',
-      ).toBe(true);
-
-      assertModelHasOutput(result);
-    },
-  });
-
-  const savingMainEntryPointAsProjectMemory =
-    'Agent saves workspace main entry point as project memory';
-  evalTest('USUALLY_PASSES', {
-    suiteName: 'default',
-    suiteType: 'behavioral',
-    name: savingMainEntryPointAsProjectMemory,
-    params: {
-      settings: {
-        experimental: { memoryV2: false },
-      },
-    },
-    prompt: `The main entry point for this workspace is \`src/index.js\`.`,
-    assert: async (rig, result) => {
-      const wasToolCalled = await rig.waitForToolCall(
-        'save_memory',
-        undefined,
-        (args) => {
-          try {
-            const params = JSON.parse(args);
-            return params.scope === 'project';
-          } catch {
-            return false;
-          }
-        },
-      );
-      expect(
-        wasToolCalled,
-        'Expected save_memory to be called with scope="project" for workspace-specific information',
-      ).toBe(true);
-
-      assertModelHasOutput(result);
-    },
-  });
-
-  const rememberingBirthday = "Agent remembers user's birthday";
-  evalTest('ALWAYS_PASSES', {
-    suiteName: 'default',
-    suiteType: 'behavioral',
-    name: rememberingBirthday,
-    params: {
-      settings: {
-        experimental: { memoryV2: false },
-      },
-    },
-
-    prompt: `My birthday is on June 15th.`,
-    assert: async (rig, result) => {
-      const wasToolCalled = await rig.waitForToolCall('save_memory');
-      expect(wasToolCalled, 'Expected save_memory tool to be called').toBe(
-        true,
-      );
-
-      assertModelHasOutput(result);
-      checkModelOutputContent(result, {
-        expectedContent: [/June 15th|ok|remember|will do/i],
-        testName: `${TEST_PREFIX}${rememberingBirthday}`,
-      });
-    },
-  });
-
+describe('memory persistence', () => {
   const proactiveMemoryFromLongSession =
     'Agent saves preference from earlier in conversation history';
   evalTest('USUALLY_PASSES', {
     suiteName: 'default',
     suiteType: 'behavioral',
     name: proactiveMemoryFromLongSession,
-    params: {
-      settings: {
-        experimental: { memoryV2: true },
-      },
-    },
     messages: [
       {
         id: 'msg-1',
@@ -462,9 +135,9 @@ describe('save_memory', () => {
     prompt:
       'Please save any persistent preferences or facts about me from our conversation to memory.',
     assert: async (rig, result) => {
-      // Under experimental.memoryV2, the agent persists memories by
-      // editing markdown files directly with write_file or replace — not via
-      // a save_memory subagent. The user said "I always prefer Vitest over
+      // The agent persists memories by editing markdown files directly with
+      // write_file or replace. The user said
+      // "I always prefer Vitest over
       // Jest for testing in all my projects" — that matches the new
       // cross-project cue phrase ("across all my projects"), so under the
       // 4-tier model the correct destination is the global personal memory
@@ -522,17 +195,12 @@ describe('save_memory', () => {
     },
   });
 
-  const memoryV2RoutesTeamConventionsToProjectGemini =
+  const memoryRoutesTeamConventionsToProjectGemini =
     'Agent routes team-shared project conventions to ./GEMINI.md';
   evalTest('USUALLY_PASSES', {
     suiteName: 'default',
     suiteType: 'behavioral',
-    name: memoryV2RoutesTeamConventionsToProjectGemini,
-    params: {
-      settings: {
-        experimental: { memoryV2: true },
-      },
-    },
+    name: memoryRoutesTeamConventionsToProjectGemini,
     messages: [
       {
         id: 'msg-1',
@@ -573,11 +241,11 @@ describe('save_memory', () => {
     ],
     prompt: 'Please save the preferences I mentioned earlier to memory.',
     assert: async (rig, result) => {
-      // Under experimental.memoryV2, the prompt enforces an explicit
-      // one-tier-per-fact rule: team-shared project conventions (the team's
-      // test command, project-wide indentation rules) belong in the
-      // committed project-root ./GEMINI.md and must NOT be mirrored or
-      // cross-referenced into the private project memory folder
+      // The prompt enforces an explicit one-tier-per-fact rule: team-shared
+      // project conventions (the team's test command, project-wide
+      // indentation rules) belong in the committed project-root ./GEMINI.md
+      // and must NOT be mirrored or cross-referenced into the private project
+      // memory folder
       // (~/.gemini/tmp/<hash>/memory/). The global ~/.gemini/GEMINI.md must
       // never be touched in this mode either.
       await rig.waitForToolCall('write_file').catch(() => {});
@@ -635,18 +303,13 @@ describe('save_memory', () => {
     },
   });
 
-  const memoryV2SessionScratchpad =
+  const memorySessionScratchpad =
     'Session summary persists memory scratchpad for memory-saving sessions';
   evalTest('USUALLY_PASSES', {
     suiteName: 'default',
     suiteType: 'behavioral',
-    name: memoryV2SessionScratchpad,
+    name: memorySessionScratchpad,
     sessionId: 'memory-scratchpad-eval',
-    params: {
-      settings: {
-        experimental: { memoryV2: true },
-      },
-    },
     messages: [
       {
         id: 'msg-1',
@@ -695,7 +358,7 @@ describe('save_memory', () => {
 
       expect(
         writeCalls.length,
-        'Expected memoryV2 save flow to edit a markdown memory file',
+        'Expected memory save flow to edit a markdown memory file',
       ).toBeGreaterThan(0);
 
       await rig.run({
@@ -732,17 +395,12 @@ describe('save_memory', () => {
     },
   });
 
-  const memoryV2RoutesUserProject =
+  const memoryRoutesUserProject =
     'Agent routes personal-to-user project notes to user-project memory';
   evalTest('USUALLY_PASSES', {
     suiteName: 'default',
     suiteType: 'behavioral',
-    name: memoryV2RoutesUserProject,
-    params: {
-      settings: {
-        experimental: { memoryV2: true },
-      },
-    },
+    name: memoryRoutesUserProject,
     prompt: `Please remember my personal local dev setup for THIS project's Postgres database. This is private to my machine — do NOT commit it to the repo.
 
 Connection details:
@@ -761,11 +419,11 @@ Quirks to remember:
 - The migrations runner sometimes hangs on my machine if I forget step 1; kill it with Ctrl+C and rerun.
 - I keep an extra \`scratch\` schema for ad-hoc experiments — never reference it from project code.`,
     assert: async (rig, result) => {
-      // Under experimental.memoryV2 with the Private Project Memory bullet
-      // surfaced in the prompt, a fact that is project-specific AND
-      // personal-to-the-user (must not be committed) should land in the
-      // private project memory folder under ~/.gemini/tmp/<hash>/memory/. The
-      // detailed note should be written to a sibling markdown file, with
+      // With the Private Project Memory bullet surfaced in the prompt, a fact
+      // that is project-specific AND personal-to-the-user (must not be
+      // committed) should land in the private project memory folder under
+      // ~/.gemini/tmp/<hash>/memory/. The detailed note should be written to a
+      // sibling markdown file, with
       // MEMORY.md updated as the index. It must NOT go to committed
       // ./GEMINI.md or the global ~/.gemini/GEMINI.md.
       await rig.waitForToolCall('write_file').catch(() => {});
@@ -828,24 +486,19 @@ Quirks to remember:
     },
   });
 
-  const memoryV2RoutesCrossProjectToGlobal =
+  const memoryRoutesCrossProjectToGlobal =
     'Agent routes cross-project personal preferences to ~/.gemini/GEMINI.md';
   evalTest('USUALLY_PASSES', {
     suiteName: 'default',
     suiteType: 'behavioral',
-    name: memoryV2RoutesCrossProjectToGlobal,
-    params: {
-      settings: {
-        experimental: { memoryV2: true },
-      },
-    },
+    name: memoryRoutesCrossProjectToGlobal,
     prompt:
       'Please remember this about me in general: across all my projects I always prefer Prettier with single quotes and trailing commas, and I always prefer tabs over spaces for indentation. These are my personal coding-style defaults that follow me into every workspace.',
     assert: async (rig, result) => {
-      // Under experimental.memoryV2 with the Global Personal Memory
-      // tier surfaced in the prompt, a fact that explicitly applies to the
-      // user "across all my projects" / "in every workspace" must land in
-      // the global ~/.gemini/GEMINI.md (the cross-project tier). It must
+      // With the Global Personal Memory tier surfaced in the prompt, a fact
+      // that explicitly applies to the user "across all my projects" / "in
+      // every workspace" must land in the global ~/.gemini/GEMINI.md (the
+      // cross-project tier). It must
       // NOT be mirrored into a committed project-root ./GEMINI.md (that
       // tier is for team-shared conventions) or into the per-project
       // private memory folder (that tier is for project-specific personal

evals/test-helper.ts

@@ -32,7 +32,7 @@ export const EVAL_MODEL =
 // Indicates the consistency expectation for this test.
 // - ALWAYS_PASSES - Means that the test is expected to pass 100% of the time. These
 //   These tests are typically trivial and test basic functionality with unambiguous
-//   prompts. For example: "call save_memory to remember foo" should be fairly reliable.
+//   prompts. For example: "remember foo" should be fairly reliable.
 //   These are the first line of defense against regressions in key behaviors and run in
 //   every CI. You can run these locally with 'npm run test:always_passing_evals'.
 //

integration-tests/context-fidelity.test.ts

@@ -0,0 +1,258 @@
+/**
+ * @license
+ * Copyright 2026 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+import { describe, it, expect, beforeEach, afterEach } from 'vitest';
+import { TestRig } from './test-helper.js';
+import * as path from 'node:path';
+import * as fs from 'node:fs';
+import { FinishReason, GenerateContentResponse } from '@google/genai';
+import type { FakeResponse, HistoryTurn } from '@google/gemini-cli-core';
+
+describe('Context Management Fidelity E2E', () => {
+  let rig: TestRig;
+
+  function generateRandomString(length: number): string {
+    const characters =
+      'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789';
+    let result = '';
+    for (let i = 0; i < length; i++) {
+      result += characters.charAt(
+        Math.floor(Math.random() * characters.length),
+      );
+    }
+    return result;
+  }
+
+  beforeEach(() => {
+    rig = new TestRig();
+  });
+
+  afterEach(async () => await rig.cleanup());
+
+  it('should reproduce the exact context working buffer on resume', async () => {
+    // Mock responses to trigger GC (summarization)
+    const snapshotResponse: FakeResponse = {
+      method: 'generateContent',
+      response: {
+        candidates: [
+          {
+            content: {
+              parts: [
+                {
+                  text: JSON.stringify({
+                    new_facts: ['GC Triggered.'],
+                    new_constraints: [],
+                    new_tasks: [],
+                    resolved_task_ids: [],
+                    obsolete_fact_indices: [],
+                    obsolete_constraint_indices: [],
+                    chronological_summary: 'Snapshot created.',
+                  }),
+                },
+              ],
+              role: 'model',
+            },
+            finishReason: FinishReason.STOP,
+            index: 0,
+          },
+        ],
+      } as unknown as GenerateContentResponse,
+    };
+
+    const countTokensResponse: FakeResponse = {
+      method: 'countTokens',
+      response: { totalTokens: 1000 },
+    };
+
+    const streamResponse = (text: string): FakeResponse => ({
+      method: 'generateContentStream',
+      response: [
+        {
+          candidates: [
+            {
+              content: { parts: [{ text }], role: 'model' },
+              finishReason: FinishReason.STOP,
+              index: 0,
+            },
+          ],
+        },
+      ] as unknown as GenerateContentResponse[],
+    });
+
+    const setupResponses = (fileName: string, mocks: FakeResponse[]) => {
+      const filePath = path.join(rig.testDir!, fileName);
+      fs.writeFileSync(
+        filePath,
+        mocks.map((m) => JSON.stringify(m)).join('\n'),
+      );
+      return filePath;
+    };
+
+    await rig.setup('context-fidelity', {
+      settings: {
+        experimental: {
+          stressTestProfile: true, // Lowers thresholds to trigger GC easily
+        },
+      },
+    });
+
+    const traceDir = path.join(rig.testDir!, 'traces');
+    fs.mkdirSync(traceDir, { recursive: true });
+    const traceLog = path.join(traceDir, 'trace.log');
+
+    const commonEnv = {
+      GEMINI_API_KEY: 'mock-key',
+      GEMINI_CONTEXT_TRACE_DIR: traceDir,
+      GEMINI_CONTEXT_TRACE_ENABLED: 'true',
+      GEMINI_DEBUG_LOG_FILE: path.join(rig.testDir!, 'debug.log'),
+    };
+
+    const runMocks: FakeResponse[] = [
+      streamResponse('Ack 1'),
+      streamResponse('Ack 2'),
+      streamResponse('Ack 3'),
+      streamResponse('Ack 4'),
+      streamResponse('Ack 5'),
+      streamResponse('Ack 6'),
+      streamResponse('Ack 7'),
+      streamResponse('Ack 8'),
+      streamResponse('Ack 9'),
+      streamResponse('Ack 10'),
+      streamResponse('Ack 11'),
+      streamResponse('Ack 12'),
+    ];
+    for (let i = 0; i < 50; i++) {
+      runMocks.push(snapshotResponse);
+      runMocks.push(countTokensResponse);
+    }
+
+    // Turns 1-10: Build up history
+    for (let i = 1; i <= 10; i++) {
+      await rig.run({
+        args: [
+          '--debug',
+          i === 1 ? '' : '--resume',
+          i === 1 ? '' : 'latest',
+          '--fake-responses-non-strict',
+          setupResponses(`resp_init_${i}.json`, runMocks),
+        ].filter(Boolean),
+        stdin: `Turn ${i}: ` + generateRandomString(900),
+        env: commonEnv,
+      });
+    }
+
+    // Turn 11: Penultimate turn
+    await rig.run({
+      args: [
+        '--debug',
+        '--resume',
+        'latest',
+        '--fake-responses-non-strict',
+        setupResponses('resp2.json', runMocks),
+      ],
+      stdin: 'Turn 11: ' + generateRandomString(900),
+      env: commonEnv,
+    });
+
+    // Turn 12: Breach threshold and force GC
+    await rig.run({
+      args: [
+        '--debug',
+        '--resume',
+        'latest',
+        '--fake-responses-non-strict',
+        setupResponses('resp3.json', runMocks),
+      ],
+      stdin: 'Turn 12: ' + generateRandomString(900),
+      env: commonEnv,
+    });
+
+    // Extract the rendered context asset from the log
+    const getRenderedContext = (logContent: string): HistoryTurn[] | null => {
+      const lines = logContent.split('\n');
+      const renderLines = lines.filter(
+        (l) =>
+          l.includes('[Render] Render Sanitized Context for LLM') ||
+          l.includes('[Render] Render Context for LLM'),
+      );
+      if (renderLines.length === 0) return null;
+
+      const lastRender = renderLines[renderLines.length - 1];
+      const detailsMatch = lastRender.match(/\| Details: (.*)$/);
+      if (!detailsMatch) return null;
+
+      const details = JSON.parse(detailsMatch[1]);
+      const assetInfo =
+        details.renderedContextSanitized || details.renderedContext;
+      if (assetInfo && assetInfo.$asset) {
+        const assetPath = path.join(traceDir, 'assets', assetInfo.$asset);
+        return JSON.parse(fs.readFileSync(assetPath, 'utf-8'));
+      }
+      return assetInfo;
+    };
+
+    const log1 = fs.readFileSync(traceLog, 'utf-8');
+    const contextBeforeExit = getRenderedContext(log1);
+    expect(contextBeforeExit).toBeDefined();
+    console.log(
+      'Context Before Exit (First 2 turns):',
+      JSON.stringify(contextBeforeExit!.slice(0, 2), null, 2),
+    );
+
+    // Turn 4: Resume and run a small command
+    await rig.run({
+      args: [
+        '--debug',
+        '--resume',
+        'latest',
+        '--fake-responses-non-strict',
+        setupResponses('resp4.json', runMocks),
+        'continue',
+      ],
+      env: commonEnv,
+    });
+
+    const log2 = fs.readFileSync(traceLog, 'utf-8');
+    const contextAfterResume = getRenderedContext(log2);
+    expect(contextAfterResume).toBeDefined();
+    console.log(
+      'Context After Resume (First 2 turns):',
+      JSON.stringify(contextAfterResume!.slice(0, 2), null, 2),
+    );
+
+    expect(contextAfterResume!.length).toBeGreaterThanOrEqual(
+      contextBeforeExit!.length,
+    );
+
+    for (let i = 0; i < contextBeforeExit!.length; i++) {
+      expect(contextAfterResume![i].id).toBe(contextBeforeExit![i].id);
+      expect(contextAfterResume![i].content).toEqual(
+        contextBeforeExit![i].content,
+      );
+    }
+
+    // Most importantly, synthetic IDs (like summaries) must be stable.
+    const syntheticTurns = contextBeforeExit!.filter(
+      (t: HistoryTurn) =>
+        t.content.parts?.some((p) => p.text?.includes('active_tasks')) ||
+        (t.id && t.id.length === 32),
+    );
+    expect(syntheticTurns.length).toBeGreaterThan(0);
+
+    const syntheticTurnsAfter = contextAfterResume!.filter(
+      (t: HistoryTurn) =>
+        t.content.parts?.some((p) => p.text?.includes('active_tasks')) ||
+        (t.id && t.id.length === 32),
+    );
+    expect(syntheticTurnsAfter.length).toBeGreaterThanOrEqual(
+      syntheticTurns.length,
+    );
+
+    // Check if the first synthetic turn is identical
+    expect(syntheticTurnsAfter[0].id).toBe(syntheticTurns[0].id);
+    expect(syntheticTurnsAfter[0].content).toEqual(syntheticTurns[0].content);
+  });
+});

integration-tests/globalSetup.ts

@@ -12,7 +12,7 @@ if (process.env['NO_COLOR'] !== undefined) {
 import { mkdir, readdir, rm, readFile } from 'node:fs/promises';
 import { join, dirname, extname } from 'node:path';
 import { fileURLToPath } from 'node:url';
-import { canUseRipgrep } from '../packages/core/src/tools/ripGrep.js';
+import { resolveRipgrepPath } from '../packages/core/src/tools/ripGrep.js';
 import { disableMouseTracking } from '@google/gemini-cli-core';
 import { isolateTestEnv } from '../packages/test-utils/src/env-setup.js';
 import { createServer, type Server } from 'node:http';
@@ -93,7 +93,7 @@ export async function setup() {
   isolateTestEnv(runDir);
 
   // Download ripgrep to avoid race conditions in parallel tests
-  const available = await canUseRipgrep();
+  const available = await resolveRipgrepPath();
   if (!available) {
     throw new Error('Failed to download ripgrep binary');
   }

integration-tests/resume-gc.test.ts

@@ -0,0 +1,149 @@
+/**
+ * @license
+ * Copyright 2026 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+import { describe, it, expect, beforeEach, afterEach } from 'vitest';
+import { TestRig } from './test-helper.js';
+import * as path from 'node:path';
+import * as fs from 'node:fs';
+import { FinishReason, GenerateContentResponse } from '@google/genai';
+import type { FakeResponse } from '@google/gemini-cli-core';
+
+describe('Context Management Resume E2E', () => {
+  let rig: TestRig;
+
+  beforeEach(() => {
+    rig = new TestRig();
+  });
+
+  afterEach(async () => await rig.cleanup());
+
+  it('should preserve and utilize GC snapshot boundaries when resuming a session', async () => {
+    const snapshotResponse: FakeResponse = {
+      method: 'generateContent',
+      response: {
+        candidates: [
+          {
+            content: {
+              parts: [
+                {
+                  text: JSON.stringify({
+                    new_facts: ['GC Triggered.'],
+                    new_constraints: [],
+                    new_tasks: [],
+                    resolved_task_ids: [],
+                    obsolete_fact_indices: [],
+                    obsolete_constraint_indices: [],
+                    chronological_summary: 'Snapshot created.',
+                  }),
+                },
+              ],
+              role: 'model',
+            },
+            finishReason: FinishReason.STOP,
+            index: 0,
+          },
+        ],
+      } as unknown as GenerateContentResponse,
+    };
+
+    const countTokensResponse: FakeResponse = {
+      method: 'countTokens',
+      response: { totalTokens: 50000 },
+    };
+
+    const streamResponse = (text: string): FakeResponse => ({
+      method: 'generateContentStream',
+      response: [
+        {
+          candidates: [
+            {
+              content: { parts: [{ text }], role: 'model' },
+              finishReason: FinishReason.STOP,
+              index: 0,
+            },
+          ],
+        },
+      ] as unknown as GenerateContentResponse[],
+    });
+
+    const setupResponses = (fileName: string, mocks: FakeResponse[]) => {
+      const filePath = path.join(rig.testDir!, fileName);
+      fs.writeFileSync(
+        filePath,
+        mocks.map((m) => JSON.stringify(m)).join('\n'),
+      );
+      return filePath;
+    };
+
+    await rig.setup('resume-gc-snapshot', {
+      settings: {
+        experimental: {
+          stressTestProfile: true,
+        },
+      },
+    });
+
+    const massivePayload = 'X'.repeat(40000);
+    const logFile = path.join(rig.testDir!, 'debug.log');
+    const traceDir = path.join(rig.testDir!, 'traces');
+    fs.mkdirSync(traceDir, { recursive: true });
+    const traceLog = path.join(traceDir, 'trace.log');
+
+    const commonEnv = {
+      GEMINI_API_KEY: 'mock-key',
+      GEMINI_DEBUG_LOG_FILE: logFile,
+      GEMINI_CONTEXT_TRACE_DIR: traceDir,
+    };
+
+    // Provide a massive pool of responses to prevent exhaustion
+    const runMocks: FakeResponse[] = [streamResponse('Acknowledged block.')];
+    for (let i = 0; i < 50; i++) {
+      runMocks.push(snapshotResponse);
+      runMocks.push(countTokensResponse);
+    }
+
+    // Use stdin for the massive payload to avoid ENAMETOOLONG on Windows
+    await rig.run({
+      args: [
+        '--debug',
+        '--fake-responses-non-strict',
+        setupResponses('resp1.json', runMocks),
+      ],
+      stdin: 'Turn 1: ' + massivePayload,
+      env: commonEnv,
+    });
+
+    await rig.run({
+      args: [
+        '--debug',
+        '--resume',
+        'latest',
+        '--fake-responses-non-strict',
+        setupResponses('resp2.json', runMocks),
+      ],
+      stdin: 'Turn 2: ' + massivePayload,
+      env: commonEnv,
+    });
+
+    const result3 = await rig.run({
+      args: [
+        '--debug',
+        '--resume',
+        'latest',
+        '--fake-responses-non-strict',
+        setupResponses('resp3.json', runMocks),
+        'continue',
+      ],
+      env: commonEnv,
+    });
+
+    expect(result3).toContain('Acknowledged block');
+
+    const traces = fs.readFileSync(traceLog, 'utf-8');
+    expect(traces).toContain('Hitting Synchronous Pressure Barrier');
+    expect(traces).toContain('GC Triggered.');
+  });
+});

integration-tests/ripgrep-real.test.ts

@@ -8,7 +8,10 @@ import { describe, it, expect, beforeAll, afterAll } from 'vitest';
 import * as path from 'node:path';
 import * as fs from 'node:fs/promises';
 import * as os from 'node:os';
-import { RipGrepTool } from '../packages/core/src/tools/ripGrep.js';
+import {
+  RipGrepTool,
+  resolveRipgrepPath,
+} from '../packages/core/src/tools/ripGrep.js';
 import { Config } from '../packages/core/src/config/config.js';
 import { WorkspaceContext } from '../packages/core/src/utils/workspaceContext.js';
 import { createMockMessageBus } from '../packages/core/src/test-utils/mock-message-bus.js';
@@ -48,6 +51,10 @@ class MockConfig {
   validatePathAccess() {
     return null;
   }
+
+  async getRipgrepPath() {
+    return resolveRipgrepPath();
+  }
 }
 
 describe('ripgrep-real-direct', () => {

memory-tests/globalSetup.ts

@@ -7,7 +7,7 @@
 import { mkdir, readdir, rm } from 'node:fs/promises';
 import { join, dirname } from 'node:path';
 import { fileURLToPath } from 'node:url';
-import { canUseRipgrep } from '../packages/core/src/tools/ripGrep.js';
+import { resolveRipgrepPath } from '../packages/core/src/tools/ripGrep.js';
 
 const __dirname = dirname(fileURLToPath(import.meta.url));
 const rootDir = join(__dirname, '..');
@@ -27,7 +27,7 @@ export async function setup() {
   process.env['GEMINI_CONFIG_DIR'] = join(runDir, '.gemini');
 
   // Download ripgrep to avoid race conditions
-  const available = await canUseRipgrep();
+  const available = await resolveRipgrepPath();
   if (!available) {
     throw new Error('Failed to download ripgrep binary');
   }

package.json

@@ -1,6 +1,6 @@
 {
   "name": "@google/gemini-cli",
-  "version": "0.44.0-nightly.20260512.g022e8baef",
+  "version": "0.45.0-nightly.20260521.g854f811be",
   "engines": {
     "node": ">=20.0.0"
   },
@@ -14,7 +14,7 @@
     "url": "git+https://github.com/google-gemini/gemini-cli.git"
   },
   "config": {
-    "sandboxImageUri": "us-docker.pkg.dev/gemini-code-dev/gemini-cli/sandbox:0.44.0-nightly.20260512.g022e8baef"
+    "sandboxImageUri": "us-docker.pkg.dev/gemini-code-dev/gemini-cli/sandbox:0.45.0-nightly.20260521.g854f811be"
   },
   "scripts": {
     "start": "cross-env NODE_ENV=development node scripts/start.js",

packages/a2a-server/development-extension-rfc.md

@@ -418,7 +418,7 @@ confirmations for tool calls (like executing a shell command), will be sent as
 ```proto
 // Request to execute a specific slash command.
 message ExecuteSlashCommandRequest {
-  // The path to the command, e.g., ["memory", "add"] for /memory add
+  // The path to the command, e.g., ["memory", "list"] for /memory list
   repeated string command_path = 1;
   // The arguments for the command as a single string.
   string args = 2;

packages/a2a-server/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@google/gemini-cli-a2a-server",
-  "version": "0.44.0-nightly.20260512.g022e8baef",
+  "version": "0.45.0-nightly.20260521.g854f811be",
   "description": "Gemini CLI A2A Server",
   "repository": {
     "type": "git",
@@ -26,7 +26,7 @@
   ],
   "dependencies": {
     "@a2a-js/sdk": "0.3.11",
-    "@google-cloud/storage": "^7.16.0",
+    "@google-cloud/storage": "^7.19.0",
     "@google/gemini-cli-core": "file:../core",
     "express": "^5.1.0",
     "fs-extra": "^11.3.0",

packages/a2a-server/src/agent/executor.ts

@@ -93,10 +93,16 @@ export class CoderAgentExecutor implements AgentExecutor {
     taskId: string,
   ): Promise<Config> {
     const workspaceRoot = setTargetDir(agentSettings);
+    const isTrusted = agentSettings.isTrusted ?? false;
     loadEnvironment(); // Will override any global env with workspace envs
-    const settings = loadSettings(workspaceRoot);
+    const settings = loadSettings(workspaceRoot, isTrusted);
     const extensions = loadExtensions(workspaceRoot);
-    return loadConfig(settings, new SimpleExtensionLoader(extensions), taskId);
+    return loadConfig(
+      settings,
+      new SimpleExtensionLoader(extensions),
+      taskId,
+      isTrusted,
+    );
   }
 
   /**

packages/a2a-server/src/agent/task.test.ts

@@ -294,6 +294,66 @@ describe('Task', () => {
       ]);
     });
 
+    it('should capture usageMetadata on Finished event and include it in final status update', async () => {
+      const mockConfig = createMockConfig();
+      const mockEventBus: ExecutionEventBus = {
+        publish: vi.fn(),
+        on: vi.fn(),
+        off: vi.fn(),
+        once: vi.fn(),
+        removeAllListeners: vi.fn(),
+        finished: vi.fn(),
+      };
+
+      // @ts-expect-error - Calling private constructor for test purposes.
+      const task = new Task(
+        'task-id',
+        'context-id',
+        mockConfig as Config,
+        mockEventBus,
+      );
+
+      const finishedEvent = {
+        type: GeminiEventType.Finished,
+        value: {
+          reason: 'STOP',
+          usageMetadata: {
+            promptTokenCount: 100,
+            candidatesTokenCount: 50,
+            totalTokenCount: 150,
+          },
+        },
+      };
+
+      await task.acceptAgentMessage(finishedEvent);
+      expect(task.usageMetadata).toEqual({
+        promptTokenCount: 100,
+        candidatesTokenCount: 50,
+        totalTokenCount: 150,
+      });
+
+      task.setTaskStateAndPublishUpdate(
+        'input-required',
+        { kind: CoderAgentEvent.StateChangeEvent },
+        undefined,
+        undefined,
+        true, // final
+      );
+
+      expect(mockEventBus.publish).toHaveBeenCalledWith(
+        expect.objectContaining({
+          final: true,
+          metadata: expect.objectContaining({
+            usageMetadata: {
+              promptTokenCount: 100,
+              candidatesTokenCount: 50,
+              totalTokenCount: 150,
+            },
+          }),
+        }),
+      );
+    });
+
     it('should update modelInfo and reflect it in metadata and status updates', async () => {
       const mockConfig = createMockConfig();
       const mockEventBus: ExecutionEventBus = {

packages/a2a-server/src/agent/task.ts

@@ -89,6 +89,12 @@ export class Task {
   currentAgentMessageId = uuidv4();
   promptCount = 0;
   autoExecute: boolean;
+  usageMetadata?: {
+    promptTokenCount?: number;
+    candidatesTokenCount?: number;
+    totalTokenCount?: number;
+    cachedContentTokenCount?: number;
+  };
   private get isYoloMatch(): boolean {
     return (
       this.autoExecute || this.config.getApprovalMode() === ApprovalMode.YOLO
@@ -274,6 +280,7 @@ export class Task {
       userTier?: UserTierId;
       error?: string;
       traceId?: string;
+      usageMetadata?: Task['usageMetadata'];
     } = {
       coderAgent: coderAgentMessage,
       model: this.modelInfo || this.config.getModel(),
@@ -288,6 +295,10 @@ export class Task {
       metadata.traceId = traceId;
     }
 
+    if (final && this.usageMetadata) {
+      metadata.usageMetadata = this.usageMetadata;
+    }
+
     return {
       kind: 'status-update',
       taskId: this.id,
@@ -857,8 +868,18 @@ export class Task {
         break;
       case GeminiEventType.Finished:
         logger.info(`[Task ${this.id}] Agent finished its turn.`);
+        // Capture the usage metadata when the stream finishes
+        if (
+          event.value &&
+          typeof event.value === 'object' &&
+          'usageMetadata' in event.value
+        ) {
+          this.usageMetadata = event.value
+            .usageMetadata as typeof this.usageMetadata;
+        }
         break;
       case GeminiEventType.ModelInfo:
+        this.usageMetadata = undefined;
         this.modelInfo = event.value;
         break;
       case GeminiEventType.Retry:

packages/a2a-server/src/commands/memory.test.ts

@@ -5,17 +5,13 @@
  */
 
 import {
-  addMemory,
   listMemoryFiles,
   refreshMemory,
   showMemory,
-  type AnyDeclarativeTool,
   type Config,
-  type ToolRegistry,
 } from '@google/gemini-cli-core';
 import { beforeEach, describe, expect, it, vi } from 'vitest';
 import {
-  AddMemoryCommand,
   ListMemoryCommand,
   MemoryCommand,
   RefreshMemoryCommand,
@@ -32,44 +28,23 @@ vi.mock('@google/gemini-cli-core', async (importOriginal) => {
     showMemory: vi.fn(),
     refreshMemory: vi.fn(),
     listMemoryFiles: vi.fn(),
-    addMemory: vi.fn(),
   };
 });
 
 const mockShowMemory = vi.mocked(showMemory);
 const mockRefreshMemory = vi.mocked(refreshMemory);
 const mockListMemoryFiles = vi.mocked(listMemoryFiles);
-const mockAddMemory = vi.mocked(addMemory);
 
 describe('a2a-server memory commands', () => {
   let mockContext: CommandContext;
   let mockConfig: Config;
-  let mockToolRegistry: ToolRegistry;
-  let mockSaveMemoryTool: AnyDeclarativeTool;
 
   beforeEach(() => {
-    mockSaveMemoryTool = {
-      name: 'save_memory',
-      description: 'Saves memory',
-      buildAndExecute: vi.fn().mockResolvedValue(undefined),
-    } as unknown as AnyDeclarativeTool;
-
-    mockToolRegistry = {
-      getTool: vi.fn(),
-    } as unknown as ToolRegistry;
-
-    mockConfig = {
-      get toolRegistry() {
-        return mockToolRegistry;
-      },
-      getToolRegistry: vi.fn().mockReturnValue(mockToolRegistry),
-    } as unknown as Config;
+    mockConfig = {} as unknown as Config;
 
     mockContext = {
       config: mockConfig,
     };
-
-    vi.mocked(mockToolRegistry.getTool).mockReturnValue(mockSaveMemoryTool);
   });
 
   describe('MemoryCommand', () => {
@@ -136,76 +111,4 @@ describe('a2a-server memory commands', () => {
       expect(response.data).toBe('file1.md\nfile2.md');
     });
   });
-
-  describe('AddMemoryCommand', () => {
-    it('returns message content if addMemory returns a message', async () => {
-      const command = new AddMemoryCommand();
-      mockAddMemory.mockReturnValue({
-        type: 'message',
-        messageType: 'error',
-        content: 'error message',
-      });
-
-      const response = await command.execute(mockContext, []);
-
-      expect(mockAddMemory).toHaveBeenCalledWith('');
-      expect(response.name).toBe('memory add');
-      expect(response.data).toBe('error message');
-    });
-
-    it('executes the save_memory tool if found', async () => {
-      const command = new AddMemoryCommand();
-      const fact = 'this is a new fact';
-      mockAddMemory.mockReturnValue({
-        type: 'tool',
-        toolName: 'save_memory',
-        toolArgs: { fact },
-      });
-
-      const response = await command.execute(mockContext, [
-        'this',
-        'is',
-        'a',
-        'new',
-        'fact',
-      ]);
-
-      expect(mockAddMemory).toHaveBeenCalledWith(fact);
-      expect(mockToolRegistry.getTool).toHaveBeenCalledWith('save_memory');
-      expect(mockSaveMemoryTool.buildAndExecute).toHaveBeenCalledWith(
-        { fact },
-        expect.any(AbortSignal),
-        undefined,
-        {
-          shellExecutionConfig: {
-            sanitizationConfig: {
-              allowedEnvironmentVariables: [],
-              blockedEnvironmentVariables: [],
-              enableEnvironmentVariableRedaction: false,
-            },
-            sandboxManager: undefined,
-          },
-        },
-      );
-      expect(mockRefreshMemory).toHaveBeenCalledWith(mockContext.config);
-      expect(response.name).toBe('memory add');
-      expect(response.data).toBe(`Added memory: "${fact}"`);
-    });
-
-    it('returns an error if the tool is not found', async () => {
-      const command = new AddMemoryCommand();
-      const fact = 'another fact';
-      mockAddMemory.mockReturnValue({
-        type: 'tool',
-        toolName: 'save_memory',
-        toolArgs: { fact },
-      });
-      vi.mocked(mockToolRegistry.getTool).mockReturnValue(undefined);
-
-      const response = await command.execute(mockContext, ['another', 'fact']);
-
-      expect(response.name).toBe('memory add');
-      expect(response.data).toBe('Error: Tool save_memory not found.');
-    });
-  });
 });

packages/a2a-server/src/commands/memory.ts

@@ -5,7 +5,6 @@
  */
 
 import {
-  addMemory,
   listMemoryFiles,
   refreshMemory,
   showMemory,
@@ -15,13 +14,6 @@ import type {
   CommandContext,
   CommandExecutionResponse,
 } from './types.js';
-import type { AgentLoopContext } from '@google/gemini-cli-core';
-
-const DEFAULT_SANITIZATION_CONFIG = {
-  allowedEnvironmentVariables: [],
-  blockedEnvironmentVariables: [],
-  enableEnvironmentVariableRedaction: false,
-};
 
 export class MemoryCommand implements Command {
   readonly name = 'memory';
@@ -30,7 +22,6 @@ export class MemoryCommand implements Command {
     new ShowMemoryCommand(),
     new RefreshMemoryCommand(),
     new ListMemoryCommand(),
-    new AddMemoryCommand(),
   ];
   readonly topLevel = true;
   readonly requiresWorkspace = true;
@@ -81,43 +72,3 @@ export class ListMemoryCommand implements Command {
     return { name: this.name, data: result.content };
   }
 }
-
-export class AddMemoryCommand implements Command {
-  readonly name = 'memory add';
-  readonly description = 'Add content to the memory.';
-
-  async execute(
-    context: CommandContext,
-    args: string[],
-  ): Promise<CommandExecutionResponse> {
-    const textToAdd = args.join(' ').trim();
-    const result = addMemory(textToAdd);
-    if (result.type === 'message') {
-      return { name: this.name, data: result.content };
-    }
-
-    const loopContext: AgentLoopContext = context.config;
-    const toolRegistry = loopContext.toolRegistry;
-    const tool = toolRegistry.getTool(result.toolName);
-    if (tool) {
-      const abortController = new AbortController();
-      const abortSignal = abortController.signal;
-      await tool.buildAndExecute(result.toolArgs, abortSignal, undefined, {
-        shellExecutionConfig: {
-          sanitizationConfig: DEFAULT_SANITIZATION_CONFIG,
-          sandboxManager: loopContext.sandboxManager,
-        },
-      });
-      await refreshMemory(context.config);
-      return {
-        name: this.name,
-        data: `Added memory: "${textToAdd}"`,
-      };
-    } else {
-      return {
-        name: this.name,
-        data: `Error: Tool ${result.toolName} not found.`,
-      };
-    }
-  }
-}

packages/a2a-server/src/config/config.test.ts

@@ -10,7 +10,6 @@ import { loadConfig } from './config.js';
 import type { Settings } from './settings.js';
 import {
   type ExtensionLoader,
-  FileDiscoveryService,
   getCodeAssistServer,
   Config,
   ExperimentFlags,
@@ -20,7 +19,9 @@ import {
   isHeadlessMode,
   FatalAuthenticationError,
   PolicyDecision,
+  ApprovalMode,
   PRIORITY_YOLO_ALLOW_ALL,
+  createPolicyEngineConfig,
 } from '@google/gemini-cli-core';
 
 // Mock dependencies
@@ -48,18 +49,38 @@ vi.mock('@google/gemini-cli-core', async (importOriginal) => {
       };
       return mockConfig;
     }),
-    loadServerHierarchicalMemory: vi.fn().mockResolvedValue({
-      memoryContent: { global: '', extension: '', project: '' },
-      fileCount: 0,
-      filePaths: [],
-    }),
     startupProfiler: {
       flush: vi.fn(),
     },
     isHeadlessMode: vi.fn().mockReturnValue(false),
-    FileDiscoveryService: vi.fn(),
     getCodeAssistServer: vi.fn(),
     fetchAdminControlsOnce: vi.fn(),
+    createPolicyEngineConfig: vi
+      .fn()
+      .mockImplementation(
+        (_settings, mode, _defaultPoliciesDir, _interactive) => ({
+          rules:
+            mode === actual.ApprovalMode.YOLO
+              ? [
+                  {
+                    toolName: '*',
+                    decision: actual.PolicyDecision.ALLOW,
+                    priority: actual.PRIORITY_YOLO_ALLOW_ALL,
+                    modes: [actual.ApprovalMode.YOLO],
+                    allowRedirection: true,
+                  },
+                ]
+              : [
+                  {
+                    toolName: 'read_file',
+                    decision: actual.PolicyDecision.ALLOW,
+                    priority: 1.05,
+                    source: 'Default: read-only.toml',
+                  },
+                ],
+          checkers: [],
+        }),
+      ),
     coreEvents: {
       emitAdminSettingsChanged: vi.fn(),
     },
@@ -268,21 +289,82 @@ describe('loadConfig', () => {
     expect((config as any).fileFiltering.customIgnoreFilePaths).toEqual([]);
   });
 
-  it('should initialize FileDiscoveryService with correct options', async () => {
-    const testPath = '/tmp/ignore';
-    vi.stubEnv('CUSTOM_IGNORE_FILE_PATHS', testPath);
-    const settings: Settings = {
-      fileFiltering: {
-        respectGitIgnore: false,
-      },
-    };
+  describe('policy engine configuration', () => {
+    it('should merge V1 and V2 tool settings into policySettings', async () => {
+      const settings: Settings = {
+        allowedTools: ['v1-allowed'],
+        tools: {
+          allowed: ['v2-allowed'],
+          exclude: ['v2-exclude'],
+          core: ['v2-core'],
+        },
+        mcpServers: {
+          test: { command: 'test', args: [] },
+        },
+        policyPaths: ['/path/to/policy'],
+        adminPolicyPaths: ['/path/to/admin/policy'],
+      };
 
-    await loadConfig(settings, mockExtensionLoader, taskId);
+      await loadConfig(settings, mockExtensionLoader, taskId);
 
-    expect(FileDiscoveryService).toHaveBeenCalledWith(expect.any(String), {
-      respectGitIgnore: false,
-      respectGeminiIgnore: undefined,
-      customIgnoreFilePaths: [testPath],
+      expect(createPolicyEngineConfig).toHaveBeenCalledWith(
+        expect.objectContaining({
+          tools: {
+            core: ['v2-core'],
+            exclude: ['v2-exclude'],
+            allowed: ['v1-allowed'],
+          },
+          mcpServers: settings.mcpServers,
+          policyPaths: settings.policyPaths,
+          adminPolicyPaths: settings.adminPolicyPaths,
+        }),
+        ApprovalMode.DEFAULT,
+        undefined,
+        true,
+      );
+    });
+
+    it('should use V2 tool settings when V1 is missing', async () => {
+      const settings: Settings = {
+        tools: {
+          allowed: ['v2-allowed'],
+        },
+      };
+
+      await loadConfig(settings, mockExtensionLoader, taskId);
+
+      expect(createPolicyEngineConfig).toHaveBeenCalledWith(
+        expect.objectContaining({
+          tools: expect.objectContaining({
+            allowed: ['v2-allowed'],
+          }),
+        }),
+        ApprovalMode.DEFAULT,
+        undefined,
+        true,
+      );
+    });
+
+    it('should use V1 tool settings when V2 is also present', async () => {
+      const settings: Settings = {
+        allowedTools: ['v1-allowed'],
+        tools: {
+          allowed: ['v2-allowed'],
+        },
+      };
+
+      await loadConfig(settings, mockExtensionLoader, taskId);
+
+      expect(createPolicyEngineConfig).toHaveBeenCalledWith(
+        expect.objectContaining({
+          tools: expect.objectContaining({
+            allowed: ['v1-allowed'],
+          }),
+        }),
+        ApprovalMode.DEFAULT,
+        undefined,
+        true,
+      );
     });
   });
 
@@ -410,14 +492,19 @@ describe('loadConfig', () => {
         );
       });
 
-      it('should use default approval mode and empty rules when GEMINI_YOLO_MODE is not true', async () => {
+      it('should use default approval mode and load default rules when GEMINI_YOLO_MODE is not true', async () => {
         vi.stubEnv('GEMINI_YOLO_MODE', 'false');
         await loadConfig(mockSettings, mockExtensionLoader, taskId);
         expect(Config).toHaveBeenCalledWith(
           expect.objectContaining({
             approvalMode: 'default',
             policyEngineConfig: expect.objectContaining({
-              rules: [],
+              rules: expect.arrayContaining([
+                expect.objectContaining({
+                  toolName: 'read_file',
+                  decision: PolicyDecision.ALLOW,
+                }),
+              ]),
             }),
           }),
         );

packages/a2a-server/src/config/config.ts

@@ -11,9 +11,7 @@ import * as dotenv from 'dotenv';
 import {
   AuthType,
   Config,
-  FileDiscoveryService,
   ApprovalMode,
-  loadServerHierarchicalMemory,
   GEMINI_DIR,
   DEFAULT_GEMINI_EMBEDDING_MODEL,
   startupProfiler,
@@ -25,8 +23,8 @@ import {
   ExperimentFlags,
   isHeadlessMode,
   FatalAuthenticationError,
-  PolicyDecision,
-  PRIORITY_YOLO_ALLOW_ALL,
+  createPolicyEngineConfig,
+  type PolicySettings,
   type TelemetryTarget,
   type ConfigParameters,
   type ExtensionLoader,
@@ -40,6 +38,7 @@ export async function loadConfig(
   settings: Settings,
   extensionLoader: ExtensionLoader,
   taskId: string,
+  trusted: boolean = false,
 ): Promise<Config> {
   const workspaceDir = process.cwd();
 
@@ -65,6 +64,24 @@ export async function loadConfig(
       ? ApprovalMode.YOLO
       : ApprovalMode.DEFAULT;
 
+  const policySettings: PolicySettings = {
+    mcpServers: settings.mcpServers,
+    tools: {
+      core: settings.coreTools || settings.tools?.core,
+      exclude: settings.excludeTools || settings.tools?.exclude,
+      allowed: settings.allowedTools || settings.tools?.allowed,
+    },
+    policyPaths: settings.policyPaths,
+    adminPolicyPaths: settings.adminPolicyPaths,
+  };
+
+  const policyEngineConfig = await createPolicyEngineConfig(
+    policySettings,
+    approvalMode,
+    undefined,
+    true,
+  );
+
   const configParams: ConfigParameters = {
     sessionId: taskId,
     clientName: 'a2a-server',
@@ -80,20 +97,7 @@ export async function loadConfig(
     allowedTools: settings.allowedTools || settings.tools?.allowed || undefined,
     showMemoryUsage: settings.showMemoryUsage || false,
     approvalMode,
-    policyEngineConfig: {
-      rules:
-        approvalMode === ApprovalMode.YOLO
-          ? [
-              {
-                toolName: '*',
-                decision: PolicyDecision.ALLOW,
-                priority: PRIORITY_YOLO_ALLOW_ALL,
-                modes: [ApprovalMode.YOLO],
-                allowRedirection: true,
-              },
-            ]
-          : [],
-    },
+    policyEngineConfig,
     mcpServers: settings.mcpServers,
     cwd: workspaceDir,
     telemetry: {
@@ -120,7 +124,7 @@ export async function loadConfig(
     },
     ideMode: false,
     folderTrust,
-    trustedFolder: true,
+    trustedFolder: trusted,
     extensionLoader,
     checkpointing,
     interactive: true,
@@ -129,23 +133,6 @@ export async function loadConfig(
     enableAgents: settings.experimental?.enableAgents ?? true,
   };
 
-  const fileService = new FileDiscoveryService(workspaceDir, {
-    respectGitIgnore: configParams?.fileFiltering?.respectGitIgnore,
-    respectGeminiIgnore: configParams?.fileFiltering?.respectGeminiIgnore,
-    customIgnoreFilePaths: configParams?.fileFiltering?.customIgnoreFilePaths,
-  });
-  const { memoryContent, fileCount, filePaths } =
-    await loadServerHierarchicalMemory(
-      workspaceDir,
-      [workspaceDir],
-      fileService,
-      extensionLoader,
-      folderTrust,
-    );
-  configParams.userMemory = memoryContent;
-  configParams.geminiMdFileCount = fileCount;
-  configParams.geminiMdFilePaths = filePaths;
-
   // Set an initial config to use to get a code assist server.
   // This is needed to fetch admin controls.
   const initialConfig = new Config({

packages/a2a-server/src/config/settings.test.ts

@@ -9,7 +9,7 @@ import * as fs from 'node:fs';
 import * as path from 'node:path';
 import * as os from 'node:os';
 import { loadSettings, USER_SETTINGS_PATH } from './settings.js';
-import { debugLogger } from '@google/gemini-cli-core';
+import { debugLogger, checkPathTrust } from '@google/gemini-cli-core';
 
 const mocks = vi.hoisted(() => {
   const suffix = Math.random().toString(36).slice(2);
@@ -40,6 +40,8 @@ vi.mock('@google/gemini-cli-core', async (importOriginal) => {
     },
     getErrorMessage: (error: unknown) => String(error),
     homedir: () => path.join(os.tmpdir(), `gemini-home-${mocks.suffix}`),
+    checkPathTrust: vi.fn(() => ({ isTrusted: false })),
+    isHeadlessMode: vi.fn(() => true),
   };
 });
 
@@ -146,7 +148,7 @@ describe('loadSettings', () => {
     );
     fs.writeFileSync(workspaceSettingsPath, JSON.stringify(workspaceSettings));
 
-    const result = loadSettings(mockWorkspaceDir);
+    const result = loadSettings(mockWorkspaceDir, true);
     // Primitive value overwritten
     expect(result.showMemoryUsage).toBe(true);
 
@@ -154,4 +156,78 @@ describe('loadSettings', () => {
     expect(result.fileFiltering?.respectGitIgnore).toBe(false);
     expect(result.fileFiltering?.enableRecursiveFileSearch).toBeUndefined();
   });
+
+  describe('security', () => {
+    it('should NOT load workspace settings if workspace is NOT trusted', () => {
+      const userSettings = { showMemoryUsage: false };
+      fs.writeFileSync(USER_SETTINGS_PATH, JSON.stringify(userSettings));
+
+      const workspaceSettings = { showMemoryUsage: true };
+      const workspaceSettingsPath = path.join(
+        mockGeminiWorkspaceDir,
+        'settings.json',
+      );
+      fs.writeFileSync(
+        workspaceSettingsPath,
+        JSON.stringify(workspaceSettings),
+      );
+
+      // checkPathTrust is mocked to return isTrusted: false by default
+      const result = loadSettings(mockWorkspaceDir);
+      expect(result.showMemoryUsage).toBe(false);
+    });
+
+    it('should load workspace settings if workspace IS trusted', () => {
+      vi.mocked(checkPathTrust).mockReturnValueOnce({
+        isTrusted: true,
+        source: 'file',
+      });
+      const userSettings = { showMemoryUsage: false };
+      fs.writeFileSync(USER_SETTINGS_PATH, JSON.stringify(userSettings));
+
+      const workspaceSettings = { showMemoryUsage: true };
+      const workspaceSettingsPath = path.join(
+        mockGeminiWorkspaceDir,
+        'settings.json',
+      );
+      fs.writeFileSync(
+        workspaceSettingsPath,
+        JSON.stringify(workspaceSettings),
+      );
+
+      const result = loadSettings(mockWorkspaceDir);
+      expect(result.showMemoryUsage).toBe(true);
+    });
+
+    it('should NOT allow workspace settings to override adminPolicyPaths or policyPaths even if trusted', () => {
+      vi.mocked(checkPathTrust).mockReturnValueOnce({
+        isTrusted: true,
+        source: 'file',
+      });
+      const userSettings = {
+        adminPolicyPaths: ['/trusted/admin'],
+        policyPaths: ['/trusted/user'],
+      };
+      fs.writeFileSync(USER_SETTINGS_PATH, JSON.stringify(userSettings));
+
+      const workspaceSettings = {
+        adminPolicyPaths: ['./malicious/admin'],
+        policyPaths: ['./malicious/user'],
+        showMemoryUsage: true,
+      };
+      const workspaceSettingsPath = path.join(
+        mockGeminiWorkspaceDir,
+        'settings.json',
+      );
+      fs.writeFileSync(
+        workspaceSettingsPath,
+        JSON.stringify(workspaceSettings),
+      );
+
+      const result = loadSettings(mockWorkspaceDir);
+      expect(result.showMemoryUsage).toBe(true);
+      expect(result.adminPolicyPaths).toEqual(['/trusted/admin']);
+      expect(result.policyPaths).toEqual(['/trusted/user']);
+    });
+  });
 });

packages/a2a-server/src/config/settings.ts

@@ -14,6 +14,8 @@ import {
   getErrorMessage,
   type TelemetrySettings,
   homedir,
+  checkPathTrust,
+  isHeadlessMode,
 } from '@google/gemini-cli-core';
 import stripJsonComments from 'strip-json-comments';
 
@@ -51,6 +53,8 @@ export interface Settings {
   experimental?: {
     enableAgents?: boolean;
   };
+  policyPaths?: string[];
+  adminPolicyPaths?: string[];
 }
 
 export interface SettingsError {
@@ -64,13 +68,16 @@ export interface CheckpointingSettings {
 
 /**
  * Loads settings from user and workspace directories.
- * Project settings override user settings.
+ * Project settings override user settings if the workspace is trusted.
  *
  * How is it different to gemini-cli/cli: Returns already merged settings rather
  * than `LoadedSettings` (unnecessary since we are not modifying users
  * settings.json).
  */
-export function loadSettings(workspaceDir: string): Settings {
+export function loadSettings(
+  workspaceDir: string,
+  isTrustedOverride?: boolean,
+): Settings {
   let userSettings: Settings = {};
   let workspaceSettings: Settings = {};
   const settingsErrors: SettingsError[] = [];
@@ -92,27 +99,39 @@ export function loadSettings(workspaceDir: string): Settings {
     });
   }
 
+  let isTrusted = isTrustedOverride;
+  if (isTrusted === undefined) {
+    const { isTrusted: trustResult } = checkPathTrust({
+      path: workspaceDir,
+      isFolderTrustEnabled: userSettings.folderTrust ?? true,
+      isHeadless: isHeadlessMode(),
+    });
+    isTrusted = trustResult ?? false;
+  }
+
   const workspaceSettingsPath = path.join(
     workspaceDir,
     GEMINI_DIR,
     'settings.json',
   );
 
-  // Load workspace settings
-  try {
-    if (fs.existsSync(workspaceSettingsPath)) {
-      const projectContent = fs.readFileSync(workspaceSettingsPath, 'utf-8');
-      // eslint-disable-next-line @typescript-eslint/no-unsafe-type-assertion
-      const parsedWorkspaceSettings = JSON.parse(
-        stripJsonComments(projectContent),
-      ) as Settings;
-      workspaceSettings = resolveEnvVarsInObject(parsedWorkspaceSettings);
+  // Load workspace settings only if trusted
+  if (isTrusted) {
+    try {
+      if (fs.existsSync(workspaceSettingsPath)) {
+        const projectContent = fs.readFileSync(workspaceSettingsPath, 'utf-8');
+        // eslint-disable-next-line @typescript-eslint/no-unsafe-type-assertion
+        const parsedWorkspaceSettings = JSON.parse(
+          stripJsonComments(projectContent),
+        ) as Settings;
+        workspaceSettings = resolveEnvVarsInObject(parsedWorkspaceSettings);
+      }
+    } catch (error: unknown) {
+      settingsErrors.push({
+        message: getErrorMessage(error),
+        path: workspaceSettingsPath,
+      });
     }
-  } catch (error: unknown) {
-    settingsErrors.push({
-      message: getErrorMessage(error),
-      path: workspaceSettingsPath,
-    });
   }
 
   if (settingsErrors.length > 0) {
@@ -125,10 +144,18 @@ export function loadSettings(workspaceDir: string): Settings {
 
   // If there are overlapping keys, the values of workspaceSettings will
   // override values from userSettings
-  return {
+  const mergedSettings = {
     ...userSettings,
     ...workspaceSettings,
   };
+
+  // Security: ensure policyPaths and adminPolicyPaths are only loaded from trusted, user-level
+  // configuration and cannot be overridden by workspace-level settings, even if the
+  // workspace is trusted.
+  mergedSettings.policyPaths = userSettings.policyPaths;
+  mergedSettings.adminPolicyPaths = userSettings.adminPolicyPaths;
+
+  return mergedSettings;
 }
 
 function resolveEnvVarsInString(value: string): string {

packages/a2a-server/src/http/app.ts

@@ -30,6 +30,8 @@ import {
   debugLogger,
   SimpleExtensionLoader,
   GitService,
+  checkPathTrust,
+  isHeadlessMode,
 } from '@google/gemini-cli-core';
 import type { Command, CommandArgument } from '../commands/types.js';
 
@@ -197,12 +199,23 @@ export async function createApp() {
     // Load the server configuration once on startup.
     const workspaceRoot = setTargetDir(undefined);
     loadEnvironment();
-    const settings = loadSettings(workspaceRoot);
+
+    // Use a temporary settings load to check if folder trust is enabled.
+    // This is similar to how the CLI handles the initial trust check.
+    const initialSettings = loadSettings(workspaceRoot, false);
+    const { isTrusted } = checkPathTrust({
+      path: workspaceRoot,
+      isFolderTrustEnabled: initialSettings.folderTrust ?? true,
+      isHeadless: isHeadlessMode(),
+    });
+
+    const settings = loadSettings(workspaceRoot, isTrusted ?? false);
     const extensions = loadExtensions(workspaceRoot);
     const config = await loadConfig(
       settings,
       new SimpleExtensionLoader(extensions),
       'a2a-server',
+      isTrusted ?? false,
     );
 
     let git: GitService | undefined;

packages/a2a-server/src/types.ts

@@ -47,6 +47,7 @@ export interface AgentSettings {
   kind: CoderAgentEvent.StateAgentSettingsEvent;
   workspacePath: string;
   autoExecute?: boolean;
+  isTrusted?: boolean;
 }
 
 export interface ToolCallConfirmation {

packages/cli/index.ts

@@ -126,7 +126,7 @@ async function run() {
     while (true) {
       try {
         const exitCode = await runner();
-        if (exitCode !== RELAUNCH_EXIT_CODE) {
+        if (process.platform === 'android' || exitCode !== RELAUNCH_EXIT_CODE) {
           process.exit(exitCode);
         }
       } catch (error: unknown) {

packages/cli/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@google/gemini-cli",
-  "version": "0.44.0-nightly.20260512.g022e8baef",
+  "version": "0.45.0-nightly.20260521.g854f811be",
   "description": "Gemini CLI",
   "license": "Apache-2.0",
   "repository": {
@@ -27,7 +27,7 @@
     "dist"
   ],
   "config": {
-    "sandboxImageUri": "us-docker.pkg.dev/gemini-code-dev/gemini-cli/sandbox:0.44.0-nightly.20260512.g022e8baef"
+    "sandboxImageUri": "us-docker.pkg.dev/gemini-code-dev/gemini-cli/sandbox:0.45.0-nightly.20260521.g854f811be"
   },
   "dependencies": {
     "@agentclientprotocol/sdk": "^0.16.1",

packages/cli/src/acp/acpCommandHandler.test.ts

@@ -17,9 +17,8 @@ describe('CommandHandler', () => {
     expect(memShow.commandToExecute?.name).toBe('memory show');
     expect(memShow.args).toBe('');
 
-    const memAdd = parse('/memory add hello world');
-    expect(memAdd.commandToExecute?.name).toBe('memory add');
-    expect(memAdd.args).toBe('hello world');
+    const memList = parse('/memory list');
+    expect(memList.commandToExecute?.name).toBe('memory list');
 
     const extList = parse('/extensions list');
     expect(extList.commandToExecute?.name).toBe('extensions list');

packages/cli/src/acp/acpResume.test.ts

@@ -100,6 +100,11 @@ describe('GeminiAgent Session Resume', () => {
         subscribe: vi.fn(),
         unsubscribe: vi.fn(),
       },
+      getMessageBus: vi.fn().mockReturnValue({
+        publish: vi.fn(),
+        subscribe: vi.fn(),
+        unsubscribe: vi.fn(),
+      }),
       getApprovalMode: vi.fn().mockReturnValue('default'),
       isAutoMemoryEnabled: vi.fn().mockReturnValue(false),
       isPlanEnabled: vi.fn().mockReturnValue(true),

packages/cli/src/acp/acpRpcDispatcher.test.ts

@@ -71,6 +71,7 @@ describe('GeminiAgent - RPC Dispatcher', () => {
       validatePathAccess: vi.fn().mockReturnValue(null),
       getWorkspaceContext: vi.fn().mockReturnValue({
         addReadOnlyPath: vi.fn(),
+        getDirectories: vi.fn().mockReturnValue(['/tmp']),
       }),
       getPolicyEngine: vi.fn().mockReturnValue({
         addRule: vi.fn(),

packages/cli/src/acp/acpSession.test.ts

@@ -26,6 +26,10 @@ import {
   InvalidStreamError,
   GeminiEventType,
   type ServerGeminiStreamEvent,
+  PolicyDecision,
+  MessageBusType,
+  type ToolConfirmationRequest,
+  DiscoveredMCPTool,
 } from '@google/gemini-cli-core';
 import type { LoadedSettings } from '../config/settings.js';
 import { type Part, FinishReason } from '@google/genai';
@@ -139,9 +143,13 @@ describe('Session', () => {
       isPlanEnabled: vi.fn().mockReturnValue(true),
       getCheckpointingEnabled: vi.fn().mockReturnValue(false),
       getGitService: vi.fn().mockResolvedValue({} as GitService),
+      getPolicyEngine: vi.fn().mockReturnValue({
+        check: vi.fn(),
+      }),
       validatePathAccess: vi.fn().mockReturnValue(null),
       getWorkspaceContext: vi.fn().mockReturnValue({
         addReadOnlyPath: vi.fn(),
+        getDirectories: vi.fn().mockReturnValue(['/tmp']),
       }),
       waitForMcpInit: vi.fn(),
       getDisableAlwaysAllow: vi.fn().mockReturnValue(false),
@@ -707,4 +715,322 @@ describe('Session', () => {
       }),
     );
   });
+
+  describe('Policy Handling', () => {
+    it('should auto-approve tool calls when PolicyEngine returns ALLOW', async () => {
+      const mockPolicyEngine = mockConfig.getPolicyEngine() as unknown as {
+        check: Mock<
+          (
+            toolCall: { name: string; args: Record<string, unknown> },
+            serverName?: string,
+            toolAnnotations?: Record<string, unknown>,
+            subagent?: string,
+          ) => Promise<{ decision: PolicyDecision }>
+        >;
+      };
+      mockPolicyEngine.check.mockResolvedValue({
+        decision: PolicyDecision.ALLOW,
+      });
+
+      // Trigger the subscription handler
+      const handler = mockMessageBus.subscribe.mock.calls.find(
+        (call) => call[0] === MessageBusType.TOOL_CONFIRMATION_REQUEST,
+      )?.[1] as (request: ToolConfirmationRequest) => Promise<void>;
+
+      expect(handler).toBeDefined();
+
+      await handler({
+        type: MessageBusType.TOOL_CONFIRMATION_REQUEST,
+        correlationId: 'test-id',
+        toolCall: { name: 'ls', args: {} },
+      });
+
+      expect(mockMessageBus.publish).toHaveBeenCalledWith(
+        expect.objectContaining({
+          type: MessageBusType.TOOL_CONFIRMATION_RESPONSE,
+          correlationId: 'test-id',
+          confirmed: true,
+          requiresUserConfirmation: false,
+        }),
+      );
+    });
+
+    it('should request user confirmation when PolicyEngine returns ASK_USER', async () => {
+      const mockPolicyEngine = mockConfig.getPolicyEngine() as unknown as {
+        check: Mock<
+          (
+            toolCall: { name: string; args: Record<string, unknown> },
+            serverName?: string,
+            toolAnnotations?: Record<string, unknown>,
+            subagent?: string,
+          ) => Promise<{ decision: PolicyDecision }>
+        >;
+      };
+      mockPolicyEngine.check.mockResolvedValue({
+        decision: PolicyDecision.ASK_USER,
+      });
+
+      const handler = mockMessageBus.subscribe.mock.calls.find(
+        (call) => call[0] === MessageBusType.TOOL_CONFIRMATION_REQUEST,
+      )?.[1] as (request: ToolConfirmationRequest) => Promise<void>;
+
+      await handler({
+        type: MessageBusType.TOOL_CONFIRMATION_REQUEST,
+        correlationId: 'test-id-2',
+        toolCall: { name: 'rm', args: { path: '/' } },
+      });
+
+      expect(mockMessageBus.publish).toHaveBeenCalledWith(
+        expect.objectContaining({
+          type: MessageBusType.TOOL_CONFIRMATION_RESPONSE,
+          correlationId: 'test-id-2',
+          confirmed: false,
+          requiresUserConfirmation: true,
+        }),
+      );
+    });
+
+    it('should deny tool calls when PolicyEngine returns DENY', async () => {
+      const mockPolicyEngine = mockConfig.getPolicyEngine() as unknown as {
+        check: Mock<
+          (
+            toolCall: { name: string; args: Record<string, unknown> },
+            serverName?: string,
+            toolAnnotations?: Record<string, unknown>,
+            subagent?: string,
+          ) => Promise<{ decision: PolicyDecision }>
+        >;
+      };
+      mockPolicyEngine.check.mockResolvedValue({
+        decision: PolicyDecision.DENY,
+      });
+
+      const handler = mockMessageBus.subscribe.mock.calls.find(
+        (call) => call[0] === MessageBusType.TOOL_CONFIRMATION_REQUEST,
+      )?.[1] as (request: ToolConfirmationRequest) => Promise<void>;
+
+      await handler({
+        type: MessageBusType.TOOL_CONFIRMATION_REQUEST,
+        correlationId: 'test-id-3',
+        toolCall: { name: 'forbidden', args: {} },
+      });
+
+      expect(mockMessageBus.publish).toHaveBeenCalledWith(
+        expect.objectContaining({
+          type: MessageBusType.TOOL_CONFIRMATION_RESPONSE,
+          correlationId: 'test-id-3',
+          confirmed: false,
+          requiresUserConfirmation: false,
+        }),
+      );
+    });
+
+    it('should pass subagent and trusted tool info to PolicyEngine', async () => {
+      const mockPolicyEngine = mockConfig.getPolicyEngine() as unknown as {
+        check: Mock<
+          (
+            toolCall: { name: string; args: Record<string, unknown> },
+            serverName?: string,
+            toolAnnotations?: Record<string, unknown>,
+            subagent?: string,
+          ) => Promise<{ decision: PolicyDecision }>
+        >;
+      };
+      mockPolicyEngine.check.mockResolvedValue({
+        decision: PolicyDecision.ALLOW,
+      });
+
+      // Mock tool in registry with trusted annotations
+      const trustedAnnotations = { safe: true };
+      mockToolRegistry.getTool.mockReturnValue({
+        name: 'ls',
+        toolAnnotations: trustedAnnotations,
+      });
+
+      const handler = mockMessageBus.subscribe.mock.calls.find(
+        (call) => call[0] === MessageBusType.TOOL_CONFIRMATION_REQUEST,
+      )?.[1] as (request: ToolConfirmationRequest) => Promise<void>;
+
+      await handler({
+        type: MessageBusType.TOOL_CONFIRMATION_REQUEST,
+        correlationId: 'test-id-trusted',
+        toolCall: { name: 'ls', args: {} },
+        subagent: 'restricted-subagent',
+        serverName: 'spoofed-server', // Should be ignored
+        toolAnnotations: { malicious: true }, // Should be ignored
+      });
+
+      expect(mockPolicyEngine.check).toHaveBeenCalledWith(
+        expect.anything(),
+        undefined, // serverName for non-MCP tool
+        trustedAnnotations,
+        'restricted-subagent',
+      );
+    });
+
+    it('should handle exceptions in PolicyEngine by failing closed', async () => {
+      const mockPolicyEngine = mockConfig.getPolicyEngine() as unknown as {
+        check: Mock<
+          (
+            toolCall: { name: string; args: Record<string, unknown> },
+            serverName?: string,
+            toolAnnotations?: Record<string, unknown>,
+            subagent?: string,
+          ) => Promise<{ decision: PolicyDecision }>
+        >;
+      };
+      mockPolicyEngine.check.mockRejectedValue(
+        new Error('Policy check failed'),
+      );
+
+      const handler = mockMessageBus.subscribe.mock.calls.find(
+        (call) => call[0] === MessageBusType.TOOL_CONFIRMATION_REQUEST,
+      )?.[1] as (request: ToolConfirmationRequest) => Promise<void>;
+
+      await handler({
+        type: MessageBusType.TOOL_CONFIRMATION_REQUEST,
+        correlationId: 'test-id-error',
+        toolCall: { name: 'ls', args: {} },
+      });
+
+      expect(mockMessageBus.publish).toHaveBeenCalledWith(
+        expect.objectContaining({
+          type: MessageBusType.TOOL_CONFIRMATION_RESPONSE,
+          correlationId: 'test-id-error',
+          confirmed: false,
+          requiresUserConfirmation: false,
+        }),
+      );
+    });
+
+    it('should fail closed when PolicyEngine is missing', async () => {
+      (mockConfig.getPolicyEngine as Mock).mockReturnValue(undefined);
+
+      const handler = mockMessageBus.subscribe.mock.calls.find(
+        (call) => call[0] === MessageBusType.TOOL_CONFIRMATION_REQUEST,
+      )?.[1] as (request: ToolConfirmationRequest) => Promise<void>;
+
+      await handler({
+        type: MessageBusType.TOOL_CONFIRMATION_REQUEST,
+        correlationId: 'test-id-no-engine',
+        toolCall: { name: 'ls', args: {} },
+      });
+
+      expect(mockMessageBus.publish).toHaveBeenCalledWith(
+        expect.objectContaining({
+          type: MessageBusType.TOOL_CONFIRMATION_RESPONSE,
+          correlationId: 'test-id-no-engine',
+          confirmed: false,
+          requiresUserConfirmation: false,
+        }),
+      );
+    });
+
+    it('should handle missing tool name in request by failing closed', async () => {
+      const handler = mockMessageBus.subscribe.mock.calls.find(
+        (call) => call[0] === MessageBusType.TOOL_CONFIRMATION_REQUEST,
+      )?.[1] as (request: ToolConfirmationRequest) => Promise<void>;
+
+      await handler({
+        type: MessageBusType.TOOL_CONFIRMATION_REQUEST,
+        correlationId: 'test-id-no-name',
+        toolCall: { name: '', args: {} },
+      });
+
+      expect(mockMessageBus.publish).toHaveBeenCalledWith(
+        expect.objectContaining({
+          type: MessageBusType.TOOL_CONFIRMATION_RESPONSE,
+          correlationId: 'test-id-no-name',
+          confirmed: false,
+          requiresUserConfirmation: false,
+        }),
+      );
+    });
+
+    it('should trim tool name before lookup and validation', async () => {
+      const handler = mockMessageBus.subscribe.mock.calls.find(
+        (call) => call[0] === MessageBusType.TOOL_CONFIRMATION_REQUEST,
+      )?.[1] as (request: ToolConfirmationRequest) => Promise<void>;
+
+      await handler({
+        type: MessageBusType.TOOL_CONFIRMATION_REQUEST,
+        correlationId: 'test-id-whitespace',
+        toolCall: { name: '  ', args: {} },
+      });
+
+      expect(mockMessageBus.publish).toHaveBeenCalledWith(
+        expect.objectContaining({
+          type: MessageBusType.TOOL_CONFIRMATION_RESPONSE,
+          correlationId: 'test-id-whitespace',
+          confirmed: false,
+          requiresUserConfirmation: false,
+        }),
+      );
+    });
+
+    it('should pass serverName from DiscoveredMCPTool to PolicyEngine', async () => {
+      const mockPolicyEngine = mockConfig.getPolicyEngine() as unknown as {
+        check: Mock<
+          (
+            toolCall: { name: string; args: Record<string, unknown> },
+            serverName?: string,
+            toolAnnotations?: Record<string, unknown>,
+            subagent?: string,
+          ) => Promise<{ decision: PolicyDecision }>
+        >;
+      };
+      mockPolicyEngine.check.mockResolvedValue({
+        decision: PolicyDecision.ALLOW,
+      });
+
+      // Mock tool in registry as a DiscoveredMCPTool instance
+      const mcpTool = {
+        name: 'mcp_server_tool',
+        serverName: 'test-server',
+        toolAnnotations: { mcp: true },
+      };
+      Object.setPrototypeOf(mcpTool, DiscoveredMCPTool.prototype);
+      mockToolRegistry.getTool.mockReturnValue(mcpTool);
+
+      const handler = mockMessageBus.subscribe.mock.calls.find(
+        (call) => call[0] === MessageBusType.TOOL_CONFIRMATION_REQUEST,
+      )?.[1] as (request: ToolConfirmationRequest) => Promise<void>;
+
+      await handler({
+        type: MessageBusType.TOOL_CONFIRMATION_REQUEST,
+        correlationId: 'test-id-mcp',
+        toolCall: { name: 'mcp_server_tool', args: {} },
+      });
+
+      expect(mockPolicyEngine.check).toHaveBeenCalledWith(
+        expect.anything(),
+        'test-server',
+        { mcp: true },
+        undefined,
+      );
+    });
+
+    it('should fail closed and deny unknown tools', async () => {
+      mockToolRegistry.getTool.mockReturnValue(undefined);
+
+      const handler = mockMessageBus.subscribe.mock.calls.find(
+        (call) => call[0] === MessageBusType.TOOL_CONFIRMATION_REQUEST,
+      )?.[1] as (request: ToolConfirmationRequest) => Promise<void>;
+
+      await handler({
+        type: MessageBusType.TOOL_CONFIRMATION_REQUEST,
+        correlationId: 'test-id-unknown',
+        toolCall: { name: 'unknown_tool', args: {} },
+      });
+
+      expect(mockMessageBus.publish).toHaveBeenCalledWith(
+        expect.objectContaining({
+          type: MessageBusType.TOOL_CONFIRMATION_RESPONSE,
+          correlationId: 'test-id-unknown',
+          confirmed: false,
+          requiresUserConfirmation: false,
+        }),
+      );
+    });
+  });
 });

packages/cli/src/acp/acpSession.ts

@@ -34,6 +34,11 @@ import {
   isNodeError,
   REFERENCE_CONTENT_START,
   InvalidStreamError,
+  MessageBusType,
+  PolicyDecision,
+  type ToolConfirmationRequest,
+  resolveAtCommandPath,
+  type ResolvedAtCommandPath,
 } from '@google/gemini-cli-core';
 import * as acp from '@agentclientprotocol/sdk';
 import type { Part, FunctionCall } from '@google/genai';
@@ -61,6 +66,7 @@ export class Session {
   private pendingPrompt: AbortController | null = null;
   private commandHandler = new CommandHandler();
   private callIdCounter = 0;
+  private readonly disposeController = new AbortController();
 
   private generateCallId(name: string): string {
     return `${name}-${Date.now()}-${++this.callIdCounter}`;
@@ -77,8 +83,98 @@ export class Session {
       CoreEvent.ApprovalModeChanged,
       this.handleApprovalModeChanged,
     );
+
+    // Subscribe to tool confirmation requests to handle policy checks (e.g. auto-allowing safe shell commands)
+    this.context.config
+      .getMessageBus()
+      ?.subscribe(
+        MessageBusType.TOOL_CONFIRMATION_REQUEST,
+        this.handleToolConfirmationRequest,
+        { signal: this.disposeController.signal },
+      );
   }
 
+  private handleToolConfirmationRequest = async (
+    request: ToolConfirmationRequest,
+  ) => {
+    try {
+      const policyEngine = this.context.config.getPolicyEngine?.();
+      const messageBus = this.context.config.getMessageBus();
+
+      if (!messageBus) {
+        return;
+      }
+
+      if (!policyEngine) {
+        debugLogger.warn(
+          'Policy engine missing. Denying tool confirmation request.',
+        );
+        await messageBus.publish({
+          type: MessageBusType.TOOL_CONFIRMATION_RESPONSE,
+          correlationId: request.correlationId,
+          confirmed: false,
+          requiresUserConfirmation: false,
+        });
+        return;
+      }
+
+      const toolName = request.toolCall.name?.trim();
+      if (!toolName) {
+        debugLogger.warn(
+          'Tool confirmation request missing tool name. Denying.',
+        );
+        await messageBus.publish({
+          type: MessageBusType.TOOL_CONFIRMATION_RESPONSE,
+          correlationId: request.correlationId,
+          confirmed: false,
+          requiresUserConfirmation: false,
+        });
+        return;
+      }
+
+      const tool = this.context.toolRegistry.getTool(toolName);
+      if (!tool) {
+        debugLogger.warn(
+          `Tool confirmation request for unknown tool: ${toolName}. Denying.`,
+        );
+        await messageBus.publish({
+          type: MessageBusType.TOOL_CONFIRMATION_RESPONSE,
+          correlationId: request.correlationId,
+          confirmed: false,
+          requiresUserConfirmation: false,
+        });
+        return;
+      }
+
+      const serverName =
+        tool instanceof DiscoveredMCPTool ? tool.serverName : undefined;
+      const toolAnnotations = tool.toolAnnotations;
+
+      const result = await policyEngine.check(
+        request.toolCall,
+        serverName,
+        toolAnnotations,
+        request.subagent,
+      );
+
+      await messageBus.publish({
+        type: MessageBusType.TOOL_CONFIRMATION_RESPONSE,
+        correlationId: request.correlationId,
+        confirmed: result.decision === PolicyDecision.ALLOW,
+        requiresUserConfirmation: result.decision === PolicyDecision.ASK_USER,
+      });
+    } catch (error) {
+      debugLogger.error('Error handling tool confirmation request:', error);
+      // Fail closed on exception
+      await this.context.config.getMessageBus()?.publish({
+        type: MessageBusType.TOOL_CONFIRMATION_RESPONSE,
+        correlationId: request.correlationId,
+        confirmed: false,
+        requiresUserConfirmation: false,
+      });
+    }
+  };
+
   private handleApprovalModeChanged = (payload: ApprovalModeChangedPayload) => {
     if (payload.sessionId === this.id) {
       void this.sendUpdate({
@@ -96,6 +192,7 @@ export class Session {
       CoreEvent.ApprovalModeChanged,
       this.handleApprovalModeChanged,
     );
+    this.disposeController.abort();
   }
 
   async cancelPendingPrompt(): Promise<void> {
@@ -928,99 +1025,120 @@ export class Session {
       let currentPathSpec = pathName;
       let resolvedSuccessfully = false;
       let readDirectly = false;
-      try {
-        const absolutePath = path.resolve(
+
+      const result = await resolveAtCommandPath(
+        pathName,
+        this.context.config,
+        (msg) => this.debug(msg),
+      );
+
+      let validationError: string | null = null;
+      let absolutePath: string;
+      let resolved: ResolvedAtCommandPath | undefined;
+
+      if (result.status === 'resolved') {
+        resolved = result.resolved;
+        absolutePath = resolved.absolutePath;
+      } else if (result.status === 'unauthorized') {
+        absolutePath = result.absolutePath;
+        validationError = result.error;
+      } else if (result.status === 'invalid') {
+        // Already logged in resolveAtCommandPath
+        continue;
+      } else {
+        // Result is not_found.
+        // We still check if it's an unauthorized absolute path that we can ask permission for,
+        // specifically for paths that are completely outside the root and not even in any workspace directory.
+        // For relative paths not found anywhere, we resolve relative to targetDir for permission check.
+        absolutePath = path.resolve(
           this.context.config.getTargetDir(),
           pathName,
         );
+      }
 
-        let validationError = this.context.config.validatePathAccess(
-          absolutePath,
-          'read',
-        );
-
-        // We ask the user for explicit permission to read them if outside sandboxed workspace boundaries (and not already authorized).
-        if (
-          validationError &&
-          !isWithinRoot(absolutePath, this.context.config.getTargetDir())
-        ) {
-          try {
-            const stats = await fs.stat(absolutePath);
-            if (stats.isFile()) {
-              const syntheticCallId = `resolve-prompt-${pathName}-${randomUUID()}`;
-              const params = {
-                sessionId: this.id,
-                options: [
-                  {
-                    optionId: ToolConfirmationOutcome.ProceedOnce,
-                    name: 'Allow once',
-                    kind: 'allow_once',
-                  },
-                  {
-                    optionId: ToolConfirmationOutcome.Cancel,
-                    name: 'Deny',
-                    kind: 'reject_once',
-                  },
-                ] as acp.PermissionOption[],
-                toolCall: {
-                  toolCallId: syntheticCallId,
-                  status: 'pending',
-                  title: `Allow access to absolute path: ${pathName}`,
-                  content: [
-                    {
-                      type: 'content',
-                      content: {
-                        type: 'text',
-                        text: `The Agent needs access to read an attached file outside your workspace: ${pathName}`,
-                      },
-                    },
-                  ],
-                  locations: [],
-                  kind: 'read',
+      if (
+        !resolved &&
+        validationError &&
+        !isWithinRoot(absolutePath, this.context.config.getTargetDir())
+      ) {
+        try {
+          const stats = await fs.stat(absolutePath);
+          if (stats.isFile()) {
+            const syntheticCallId = `resolve-prompt-${pathName}-${randomUUID()}`;
+            const params = {
+              sessionId: this.id,
+              options: [
+                {
+                  optionId: ToolConfirmationOutcome.ProceedOnce,
+                  name: 'Allow once',
+                  kind: 'allow_once',
                 },
-              };
-
-              const output = RequestPermissionResponseSchema.parse(
-                await this.connection.requestPermission(params),
-              );
-
-              const outcome =
-                output.outcome.outcome === 'cancelled'
-                  ? ToolConfirmationOutcome.Cancel
-                  : z
-                      .nativeEnum(ToolConfirmationOutcome)
-                      .parse(output.outcome.optionId);
-
-              if (outcome === ToolConfirmationOutcome.ProceedOnce) {
-                this.context.config
-                  .getWorkspaceContext()
-                  .addReadOnlyPath(absolutePath);
-                validationError = null;
-              } else {
-                this.debug(
-                  `Direct read authorization denied for absolute path ${pathName}`,
-                );
-                directContents.push({
-                  spec: pathName,
-                  content: `[Warning: Access to absolute path \`${pathName}\` denied by user.]`,
-                });
-                continue;
-              }
-            }
-          } catch (error) {
-            this.debug(
-              `Failed to request permission for absolute attachment ${pathName}: ${getErrorMessage(error)}`,
-            );
-            await this.sendUpdate({
-              sessionUpdate: 'agent_thought_chunk',
-              content: {
-                type: 'text',
-                text: `Warning: Failed to display permission dialog for \`${absolutePath}\`. Error: ${getErrorMessage(error)}`,
+                {
+                  optionId: ToolConfirmationOutcome.Cancel,
+                  name: 'Deny',
+                  kind: 'reject_once',
+                },
+              ] as acp.PermissionOption[],
+              toolCall: {
+                toolCallId: syntheticCallId,
+                status: 'pending',
+                title: `Allow access to absolute path: ${pathName}`,
+                content: [
+                  {
+                    type: 'content',
+                    content: {
+                      type: 'text',
+                      text: `The Agent needs access to read an attached file outside your workspace: ${pathName}`,
+                    },
+                  },
+                ],
+                locations: [],
+                kind: 'read',
               },
-            });
-          }
-        }
+            };
 
+            const output = RequestPermissionResponseSchema.parse(
+              await this.connection.requestPermission(params),
+            );
+
+            const outcome =
+              output.outcome.outcome === 'cancelled'
+                ? ToolConfirmationOutcome.Cancel
+                : z
+                    .nativeEnum(ToolConfirmationOutcome)
+                    .parse(output.outcome.optionId);
+
+            if (outcome === ToolConfirmationOutcome.ProceedOnce) {
+              this.context.config
+                .getWorkspaceContext()
+                .addReadOnlyPath(absolutePath);
+              validationError = null;
+            } else {
+              this.debug(
+                `Direct read authorization denied for absolute path ${pathName}`,
+              );
+              directContents.push({
+                spec: pathName,
+                content: `[Warning: Access to absolute path \`${pathName}\` denied by user.]`,
+              });
+              continue;
+            }
+          }
+        } catch (error) {
+          this.debug(
+            `Failed to request permission for absolute attachment ${pathName}: ${getErrorMessage(error)}`,
+          );
+          await this.sendUpdate({
+            sessionUpdate: 'agent_thought_chunk',
+            content: {
+              type: 'text',
+              text: `Warning: Failed to display permission dialog for \`${absolutePath}\`. Error: ${getErrorMessage(error)}`,
+            },
+          });
+        }
+      }
+
+      try {
         if (!validationError) {
           // If it's an absolute path that is authorized (e.g. added via readOnlyPaths),
           // read it directly to avoid ReadManyFilesTool absolute path resolution issues.
@@ -1033,7 +1151,9 @@ export class Session {
             !readDirectly
           ) {
             try {
-              const stats = await fs.stat(absolutePath);
+              const stats = resolved
+                ? resolved.stats
+                : await fs.stat(absolutePath);
               if (stats.isFile()) {
                 const fileReadResult = await processSingleFileContent(
                   absolutePath,
@@ -1092,7 +1212,9 @@ export class Session {
           }
 
           if (!readDirectly) {
-            const stats = await fs.stat(absolutePath);
+            const stats = resolved
+              ? resolved.stats
+              : await fs.stat(absolutePath);
             if (stats.isDirectory()) {
               currentPathSpec = pathName.endsWith('/')
                 ? `${pathName}**`

packages/cli/src/acp/acpSessionManager.test.ts

@@ -79,6 +79,7 @@ describe('AcpSessionManager', () => {
       validatePathAccess: vi.fn().mockReturnValue(null),
       getWorkspaceContext: vi.fn().mockReturnValue({
         addReadOnlyPath: vi.fn(),
+        getDirectories: vi.fn().mockReturnValue(['/tmp']),
       }),
       getPolicyEngine: vi.fn().mockReturnValue({
         addRule: vi.fn(),

packages/cli/src/acp/acpSessionManager.ts

@@ -69,7 +69,10 @@ export class AcpSessionManager {
     );
 
     const authType =
-      loadedSettings.merged.security.auth.selectedType || AuthType.USE_GEMINI;
+      loadedSettings.merged.security.auth.selectedType ||
+      (authDetails.baseUrl || process.env['GOOGLE_GEMINI_BASE_URL']
+        ? AuthType.GATEWAY
+        : AuthType.USE_GEMINI);
 
     let isAuthenticated = false;
     let authErrorMessage = '';
@@ -231,7 +234,12 @@ export class AcpSessionManager {
     mcpServers: acp.McpServer[],
     authDetails: AuthDetails,
   ): Promise<Config> {
-    const selectedAuthType = this.settings.merged.security.auth.selectedType;
+    const selectedAuthType =
+      this.settings.merged.security.auth.selectedType ||
+      (authDetails.baseUrl || process.env['GOOGLE_GEMINI_BASE_URL']
+        ? AuthType.GATEWAY
+        : undefined);
+
     if (!selectedAuthType) {
       throw acp.RequestError.authRequired();
     }

packages/cli/src/acp/acpUtils.ts

@@ -22,7 +22,6 @@ import {
   getDisplayString,
   AuthType,
   ToolConfirmationOutcome,
-  getChannelFromVersion,
   getAutoModelDescription,
 } from '@google/gemini-cli-core';
 import type * as acp from '@agentclientprotocol/sdk';
@@ -272,8 +271,6 @@ export function buildAvailableModels(
   const useCustomToolModel =
     useGemini31 && selectedAuthType === AuthType.USE_GEMINI;
 
-  const releaseChannel = getChannelFromVersion(config.clientVersion);
-
   // --- DYNAMIC PATH ---
   if (
     config.getExperimentalDynamicModelConfiguration?.() === true &&
@@ -284,7 +281,6 @@ export function buildAvailableModels(
       useGemini3_1FlashLite: useGemini31FlashLite,
       useCustomTools: useCustomToolModel,
       hasAccessToPreview: shouldShowPreviewModels,
-      releaseChannel,
     });
 
     return {
@@ -298,7 +294,10 @@ export function buildAvailableModels(
     {
       value: GEMINI_MODEL_ALIAS_AUTO,
       title: getDisplayString(GEMINI_MODEL_ALIAS_AUTO),
-      description: getAutoModelDescription(releaseChannel, useGemini31),
+      description: getAutoModelDescription(
+        shouldShowPreviewModels,
+        useGemini31,
+      ),
     },
   ];
 

packages/cli/src/acp/commands/memory.ts

@@ -5,7 +5,6 @@
  */
 
 import {
-  addMemory,
   listInboxMemoryPatches,
   listInboxSkills,
   listInboxPatches,
@@ -19,12 +18,6 @@ import type {
   CommandExecutionResponse,
 } from './types.js';
 
-const DEFAULT_SANITIZATION_CONFIG = {
-  allowedEnvironmentVariables: [],
-  blockedEnvironmentVariables: [],
-  enableEnvironmentVariableRedaction: false,
-};
-
 export class MemoryCommand implements Command {
   readonly name = 'memory';
   readonly description = 'Manage memory.';
@@ -32,7 +25,6 @@ export class MemoryCommand implements Command {
     new ShowMemoryCommand(),
     new RefreshMemoryCommand(),
     new ListMemoryCommand(),
-    new AddMemoryCommand(),
     new InboxMemoryCommand(),
   ];
   readonly requiresWorkspace = true;
@@ -85,48 +77,6 @@ export class ListMemoryCommand implements Command {
   }
 }
 
-export class AddMemoryCommand implements Command {
-  readonly name = 'memory add';
-  readonly description = 'Add content to the memory.';
-
-  async execute(
-    context: CommandContext,
-    args: string[],
-  ): Promise<CommandExecutionResponse> {
-    const textToAdd = args.join(' ').trim();
-    const result = addMemory(textToAdd);
-    if (result.type === 'message') {
-      return { name: this.name, data: result.content };
-    }
-
-    const toolRegistry = context.agentContext.toolRegistry;
-    const tool = toolRegistry.getTool(result.toolName);
-    if (tool) {
-      const abortController = new AbortController();
-      const signal = abortController.signal;
-
-      await context.sendMessage(`Saving memory via ${result.toolName}...`);
-
-      await tool.buildAndExecute(result.toolArgs, signal, undefined, {
-        shellExecutionConfig: {
-          sanitizationConfig: DEFAULT_SANITIZATION_CONFIG,
-          sandboxManager: context.agentContext.sandboxManager,
-        },
-      });
-      await refreshMemory(context.agentContext.config);
-      return {
-        name: this.name,
-        data: `Added memory: "${textToAdd}"`,
-      };
-    } else {
-      return {
-        name: this.name,
-        data: `Error: Tool ${result.toolName} not found.`,
-      };
-    }
-  }
-}
-
 export class InboxMemoryCommand implements Command {
   readonly name = 'memory inbox';
   readonly description =

packages/cli/src/config/config.test.ts

@@ -15,7 +15,6 @@ import {
   EDIT_TOOL_NAME,
   WEB_FETCH_TOOL_NAME,
   ASK_USER_TOOL_NAME,
-  type ExtensionLoader,
   debugLogger,
   ApprovalMode,
   type MCPServerConfig,
@@ -112,27 +111,6 @@ vi.mock('@google/gemini-cli-core', async () => {
       }),
     },
     loadEnvironment: vi.fn(),
-    loadServerHierarchicalMemory: vi.fn(
-      (
-        cwd,
-        dirs,
-        fileService,
-        extensionLoader: ExtensionLoader,
-        _folderTrust,
-        _importFormat,
-        _fileFilteringOptions,
-        _maxDirs,
-      ) => {
-        const extensionPaths =
-          extensionLoader?.getExtensions?.()?.flatMap((e) => e.contextFiles) ||
-          [];
-        return Promise.resolve({
-          memoryContent: extensionPaths.join(',') || '',
-          fileCount: extensionPaths?.length || 0,
-          filePaths: extensionPaths,
-        });
-      },
-    ),
     DEFAULT_MEMORY_FILE_FILTERING_OPTIONS: {
       respectGitIgnore: false,
       respectGeminiIgnore: true,
@@ -1067,151 +1045,6 @@ describe('loadCliConfig', () => {
   });
 });
 
-describe('Hierarchical Memory Loading (config.ts) - Placeholder Suite', () => {
-  beforeEach(() => {
-    vi.resetAllMocks();
-    vi.stubEnv('GEMINI_CLI_IDE_WORKSPACE_PATH', '');
-    // Restore ExtensionManager mocks that were reset
-    ExtensionManager.prototype.getExtensions = vi.fn().mockReturnValue([]);
-    ExtensionManager.prototype.loadExtensions = vi
-      .fn()
-      .mockResolvedValue(undefined);
-
-    vi.mocked(os.homedir).mockReturnValue('/mock/home/user');
-    // Other common mocks would be reset here.
-  });
-
-  afterEach(() => {
-    vi.unstubAllEnvs();
-    vi.restoreAllMocks();
-  });
-
-  it('should pass extension context file paths to loadServerHierarchicalMemory', async () => {
-    process.argv = ['node', 'script.js'];
-    const settings = createTestMergedSettings({
-      experimental: { jitContext: false },
-    });
-    vi.spyOn(ExtensionManager.prototype, 'getExtensions').mockReturnValue([
-      {
-        path: '/path/to/ext1',
-        name: 'ext1',
-        id: 'ext1-id',
-        version: '1.0.0',
-        contextFiles: ['/path/to/ext1/GEMINI.md'],
-        isActive: true,
-      },
-      {
-        path: '/path/to/ext2',
-        name: 'ext2',
-        id: 'ext2-id',
-        version: '1.0.0',
-        contextFiles: [],
-        isActive: true,
-      },
-      {
-        path: '/path/to/ext3',
-        name: 'ext3',
-        id: 'ext3-id',
-        version: '1.0.0',
-        contextFiles: [
-          '/path/to/ext3/context1.md',
-          '/path/to/ext3/context2.md',
-        ],
-        isActive: true,
-      },
-    ]);
-    const argv = await parseArguments(createTestMergedSettings());
-    await loadCliConfig(settings, 'session-id', argv);
-    expect(ServerConfig.loadServerHierarchicalMemory).toHaveBeenCalledWith(
-      expect.any(String),
-      [],
-      expect.any(Object),
-      expect.any(ExtensionManager),
-      true,
-      'tree',
-      expect.objectContaining({
-        respectGitIgnore: true,
-        respectGeminiIgnore: true,
-      }),
-      200, // maxDirs
-      ['.git'], // boundaryMarkers
-    );
-  });
-
-  it('should pass includeDirectories to loadServerHierarchicalMemory when loadMemoryFromIncludeDirectories is true', async () => {
-    process.argv = ['node', 'script.js'];
-    const includeDir = path.resolve(path.sep, 'path', 'to', 'include');
-    const settings = createTestMergedSettings({
-      experimental: { jitContext: false },
-      context: {
-        includeDirectories: [includeDir],
-        loadMemoryFromIncludeDirectories: true,
-      },
-    });
-
-    const argv = await parseArguments(settings);
-    await loadCliConfig(settings, 'session-id', argv);
-
-    expect(ServerConfig.loadServerHierarchicalMemory).toHaveBeenCalledWith(
-      expect.any(String),
-      [includeDir],
-      expect.any(Object),
-      expect.any(ExtensionManager),
-      true,
-      'tree',
-      expect.objectContaining({
-        respectGitIgnore: true,
-        respectGeminiIgnore: true,
-      }),
-      200,
-      ['.git'], // boundaryMarkers
-    );
-  });
-
-  it('should NOT pass includeDirectories to loadServerHierarchicalMemory when loadMemoryFromIncludeDirectories is false', async () => {
-    process.argv = ['node', 'script.js'];
-    const settings = createTestMergedSettings({
-      experimental: { jitContext: false },
-      context: {
-        includeDirectories: ['/path/to/include'],
-        loadMemoryFromIncludeDirectories: false,
-      },
-    });
-
-    const argv = await parseArguments(settings);
-    await loadCliConfig(settings, 'session-id', argv);
-
-    expect(ServerConfig.loadServerHierarchicalMemory).toHaveBeenCalledWith(
-      expect.any(String),
-      [],
-      expect.any(Object),
-      expect.any(ExtensionManager),
-      true,
-      'tree',
-      expect.objectContaining({
-        respectGitIgnore: true,
-        respectGeminiIgnore: true,
-      }),
-      200,
-      ['.git'], // boundaryMarkers
-    );
-  });
-
-  it('should NOT call loadServerHierarchicalMemory when skipMemoryLoad is true', async () => {
-    process.argv = ['node', 'script.js'];
-    const settings = createTestMergedSettings({
-      experimental: { jitContext: false },
-    });
-
-    const argv = await parseArguments(settings);
-    await loadCliConfig(settings, 'session-id', argv, {
-      skipMemoryLoad: true,
-    });
-
-    expect(ServerConfig.loadServerHierarchicalMemory).not.toHaveBeenCalled();
-  });
-});
-
 describe('mergeMcpServers', () => {
   it('should not modify the original settings object', async () => {
     const settings = createTestMergedSettings({

packages/cli/src/config/config.ts

@@ -16,21 +16,19 @@ import { hooksCommand } from '../commands/hooks.js';
 import { gemmaCommand } from '../commands/gemma.js';
 import {
   setGeminiMdFilename as setServerGeminiMdFilename,
-  getCurrentGeminiMdFilename,
+  resetGeminiMdFilename,
+  DEFAULT_CONTEXT_FILENAME,
   ApprovalMode,
   DEFAULT_GEMINI_EMBEDDING_MODEL,
   DEFAULT_FILE_FILTERING_OPTIONS,
-  DEFAULT_MEMORY_FILE_FILTERING_OPTIONS,
   FileDiscoveryService,
   resolveTelemetrySettings,
   FatalConfigError,
   getErrorMessage,
   getPty,
   debugLogger,
-  loadServerHierarchicalMemory,
   ASK_USER_TOOL_NAME,
   getVersion,
-  type HierarchicalMemory,
   coreEvents,
   GEMINI_MODEL_ALIAS_AUTO,
   getAdminErrorMessage,
@@ -105,6 +103,7 @@ export interface CliArgs {
   useWriteTodos: boolean | undefined;
   outputFormat: string | undefined;
   fakeResponses: string | undefined;
+  fakeResponsesNonStrict?: string | undefined;
   recordResponses: string | undefined;
   startupMessages?: string[];
   rawOutput: boolean | undefined;
@@ -476,6 +475,12 @@ export async function parseArguments(
           description: 'Path to a file with fake model responses for testing.',
           hidden: true,
         })
+        .option('fake-responses-non-strict', {
+          type: 'string',
+          description:
+            'Path to a file with fake model responses for testing (non-strict mode).',
+          hidden: true,
+        })
         .option('record-responses', {
           type: 'string',
           description: 'Path to a file to record model responses for testing.',
@@ -571,7 +576,6 @@ export interface LoadCliConfigOptions {
   };
   worktreeSettings?: WorktreeSettings;
   skipExtensions?: boolean;
-  skipMemoryLoad?: boolean;
 }
 
 export async function loadCliConfig(
@@ -580,12 +584,7 @@ export async function loadCliConfig(
   argv: CliArgs,
   options: LoadCliConfigOptions = {},
 ): Promise<Config> {
-  const {
-    cwd = process.cwd(),
-    projectHooks,
-    skipExtensions = false,
-    skipMemoryLoad = false,
-  } = options;
+  const { cwd = process.cwd(), projectHooks, skipExtensions = false } = options;
   const debugMode = isDebugMode(argv);
 
   const worktreeSettings =
@@ -595,7 +594,6 @@ export async function loadCliConfig(
     process.env['GEMINI_SANDBOX'] = 'true';
   }
 
-  const memoryImportFormat = settings.context?.importFormat || 'tree';
   const includeDirectoryTree = settings.context?.includeDirectoryTree ?? true;
 
   const ideMode = settings.ide?.enabled ?? false;
@@ -611,7 +609,7 @@ export async function loadCliConfig(
       query: argv.query,
     })?.isTrusted ?? false;
 
-  // Set the context filename in the server's memoryTool module BEFORE loading memory
+  // Set the context filename in the server's memory file helpers before loading memory
   // TODO(b/343434939): This is a bit of a hack. The contextFileName should ideally be passed
   // directly to the Config constructor in core, and have core handle setGeminiMdFilename.
   // However, loadHierarchicalGeminiMemory is called *before* createServerConfig.
@@ -619,16 +617,11 @@ export async function loadCliConfig(
     setServerGeminiMdFilename(settings.context.fileName);
   } else {
     // Reset to default if not provided in settings.
-    setServerGeminiMdFilename(getCurrentGeminiMdFilename());
+    resetGeminiMdFilename(DEFAULT_CONTEXT_FILENAME);
   }
 
   const fileService = new FileDiscoveryService(cwd);
 
-  const memoryFileFiltering = {
-    ...DEFAULT_MEMORY_FILE_FILTERING_OPTIONS,
-    ...settings.context?.fileFiltering,
-  };
-
   const fileFiltering = {
     ...DEFAULT_FILE_FILTERING_OPTIONS,
     ...settings.context?.fileFiltering,
@@ -679,8 +672,6 @@ export async function loadCliConfig(
     ?.getExtensions()
     ?.find((ext) => ext.isActive && ext.plan?.directory)?.plan;
 
-  const experimentalJitContext = settings.experimental.jitContext ?? true;
-
   let extensionRegistryURI =
     process.env['GEMINI_CLI_EXTENSION_REGISTRY_URI'] ??
     (trustedFolder ? settings.experimental?.extensionRegistryURI : undefined);
@@ -691,33 +682,9 @@ export async function loadCliConfig(
     );
   }
 
-  let memoryContent: string | HierarchicalMemory = '';
-  let fileCount = 0;
-  let filePaths: string[] = [];
-
   const finalExtensionLoader =
     extensionManager ?? new SimpleExtensionLoader([]);
 
-  if (!experimentalJitContext && !skipMemoryLoad) {
-    // Call the (now wrapper) loadHierarchicalGeminiMemory which calls the server's version
-    const result = await loadServerHierarchicalMemory(
-      cwd,
-      settings.context?.loadMemoryFromIncludeDirectories || false
-        ? includeDirectories
-        : [],
-      fileService,
-      finalExtensionLoader,
-      trustedFolder,
-      memoryImportFormat,
-      memoryFileFiltering,
-      settings.context?.discoveryMaxDirs,
-      settings.context?.memoryBoundaryMarkers,
-    );
-    memoryContent = result.memoryContent;
-    fileCount = result.fileCount;
-    filePaths = result.filePaths;
-  }
-
   const question = argv.promptInteractive || argv.prompt || '';
 
   // Determine approval mode with backward compatibility
@@ -969,6 +936,8 @@ export async function loadCliConfig(
   let profileSelector: string | undefined = undefined;
   if (settings.experimental?.stressTestProfile) {
     profileSelector = 'stressTestProfile';
+  } else if (settings.experimental?.powerUserProfile) {
+    profileSelector = 'powerUserProfile';
   } else if (
     settings.experimental?.generalistProfile ||
     settings.experimental?.contextManagement
@@ -1029,9 +998,6 @@ export async function loadCliConfig(
       settings.security?.environmentVariableRedaction?.allowed,
     enableEnvironmentVariableRedaction:
       settings.security?.environmentVariableRedaction?.enabled,
-    userMemory: memoryContent,
-    geminiMdFileCount: fileCount,
-    geminiMdFilePaths: filePaths,
     approvalMode,
     disableYoloMode:
       settings.security?.disableYoloMode || settings.admin?.secureModeEnabled,
@@ -1076,8 +1042,6 @@ export async function loadCliConfig(
     enableEventDrivenScheduler: true,
     skillsSupport: settings.skills?.enabled ?? true,
     disabledSkills: settings.skills?.disabled,
-    experimentalJitContext,
-    experimentalMemoryV2: settings.experimental?.memoryV2,
     experimentalAutoMemory: settings.experimental?.autoMemory,
     experimentalGemma: settings.experimental?.gemma,
     contextManagement,
@@ -1119,6 +1083,7 @@ export async function loadCliConfig(
     gemmaModelRouter: settings.experimental?.gemmaModelRouter,
     adk: settings.experimental?.adk,
     fakeResponses: argv.fakeResponses,
+    fakeResponsesNonStrict: argv.fakeResponsesNonStrict,
     recordResponses: argv.recordResponses,
     retryFetchErrors: settings.general?.retryFetchErrors,
     billing: settings.billing,

packages/cli/src/config/extension-manager-themes.spec.ts

@@ -109,6 +109,7 @@ describe('ExtensionManager theme loading', () => {
       getFileExclusions: () => ({
         isIgnored: () => false,
       }),
+      getMemoryContextManager: () => undefined,
       getGeminiMdFilePaths: () => [],
       getMcpServers: () => ({}),
       getAllowedMcpServers: () => [],
@@ -185,6 +186,7 @@ describe('ExtensionManager theme loading', () => {
       getWorkspaceContext: () => ({
         getDirectories: () => [],
       }),
+      getMemoryContextManager: () => undefined,
       getDebugMode: () => false,
       getFileService: () => ({
         findFiles: async () => [],

packages/cli/src/config/settingsSchema.test.ts

@@ -571,6 +571,18 @@ describe('SettingsSchema', () => {
       expect(agentSessionNoninteractiveEnabled.description).toBe(
         'Enable non-interactive agent sessions.',
       );
+
+      const agentSessionSubagentEnabled =
+        adk.properties.agentSessionSubagentEnabled;
+      expect(agentSessionSubagentEnabled).toBeDefined();
+      expect(agentSessionSubagentEnabled.type).toBe('boolean');
+      expect(agentSessionSubagentEnabled.category).toBe('Experimental');
+      expect(agentSessionSubagentEnabled.default).toBe(false);
+      expect(agentSessionSubagentEnabled.requiresRestart).toBe(true);
+      expect(agentSessionSubagentEnabled.showInDialog).toBe(false);
+      expect(agentSessionSubagentEnabled.description).toBe(
+        'Route subagent invocations through the AgentSession protocol instead of legacy executors.',
+      );
     });
   });
 

packages/cli/src/config/settingsSchema.ts

@@ -12,6 +12,7 @@
 import {
   DEFAULT_TRUNCATE_TOOL_OUTPUT_THRESHOLD,
   DEFAULT_MODEL_CONFIGS,
+  EDITOR_OPTIONS,
   AuthProviderType,
   type MCPServerConfig,
   type RequiredMcpServerConfig,
@@ -192,12 +193,27 @@ const SETTINGS_SCHEMA = {
     showInDialog: false,
     properties: {
       preferredEditor: {
-        type: 'string',
+        type: 'enum',
         label: 'Preferred Editor',
         category: 'General',
         requiresRestart: false,
         default: undefined as string | undefined,
-        description: 'The preferred editor to open files in.',
+        description: oneLine`
+          The preferred editor to open files in. Must be one of the built-in
+          supported identifiers. Use /editor in the CLI to pick interactively,
+          or leave unset to use $VISUAL/$EDITOR.
+        `,
+        showInDialog: false,
+        options: EDITOR_OPTIONS,
+      },
+      openEditorInNewWindow: {
+        type: 'boolean',
+        label: 'Open Editor in New Window',
+        category: 'General',
+        requiresRestart: false,
+        default: false,
+        description:
+          'Open VS Code-family editors in a new window when editing files.',
         showInDialog: false,
       },
       vimMode: {
@@ -429,6 +445,16 @@ const SETTINGS_SCHEMA = {
           'Enable the Topic & Update communication model for reduced chattiness and structured progress reporting.',
         showInDialog: true,
       },
+      logRagSnippets: {
+        type: 'boolean',
+        label: 'Log RAG Snippets',
+        category: 'General',
+        requiresRestart: false,
+        default: false,
+        description:
+          'Log full Code Customization (RAG) retrieved snippets to a local file for debugging.',
+        showInDialog: true,
+      },
     },
   },
   output: {
@@ -2184,6 +2210,16 @@ const SETTINGS_SCHEMA = {
               'Enable the agent session implementation for the interactive CLI.',
             showInDialog: false,
           },
+          agentSessionSubagentEnabled: {
+            type: 'boolean',
+            label: 'Agent Session Subagent Enabled',
+            category: 'Experimental',
+            requiresRestart: true,
+            default: false,
+            description:
+              'Route subagent invocations through the AgentSession protocol instead of legacy executors.',
+            showInDialog: false,
+          },
         },
       },
       enableAgents: {
@@ -2252,16 +2288,6 @@ const SETTINGS_SCHEMA = {
           'Enables extension loading/unloading within the CLI session.',
         showInDialog: false,
       },
-      jitContext: {
-        type: 'boolean',
-        label: 'JIT Context Loading',
-        category: 'Experimental',
-        requiresRestart: true,
-        default: true,
-        description:
-          'Enable Just-In-Time (JIT) context loading. Defaults to true; set to false to opt out and load all GEMINI.md files into the system instruction up-front.',
-        showInDialog: false,
-      },
       useOSC52Paste: {
         type: 'boolean',
         label: 'Use OSC 52 Paste',
@@ -2392,16 +2418,6 @@ const SETTINGS_SCHEMA = {
           },
         },
       },
-      memoryV2: {
-        type: 'boolean',
-        label: 'Memory v2',
-        category: 'Experimental',
-        requiresRestart: true,
-        default: true,
-        description:
-          'Disable the built-in save_memory tool and let the main agent persist project context by editing markdown files directly with edit/write_file. Route facts across four tiers: team-shared conventions go to project GEMINI.md files, project-specific personal notes go to the per-project private memory folder (MEMORY.md as index + sibling .md files for detail), and cross-project personal preferences go to the global ~/.gemini/GEMINI.md (the only file under ~/.gemini/ that the agent can edit — settings, credentials, etc. remain off-limits). Set to false to fall back to the legacy save_memory tool.',
-        showInDialog: true,
-      },
       stressTestProfile: {
         type: 'boolean',
         label:
@@ -2433,6 +2449,15 @@ const SETTINGS_SCHEMA = {
           'Suitable for general coding and software development tasks.',
         showInDialog: true,
       },
+      powerUserProfile: {
+        type: 'boolean',
+        label: 'Use the power user profile to manage agent contexts.',
+        category: 'Experimental',
+        requiresRestart: true,
+        default: false,
+        description: 'Less cache friendly version of the generalist profile.',
+        showInDialog: false,
+      },
       contextManagement: {
         type: 'boolean',
         label: 'Enable Context Management',

packages/cli/src/config/workspace-policy-cli.test.ts

@@ -26,11 +26,6 @@ vi.mock('@google/gemini-cli-core', async () => {
   );
   return {
     ...actual,
-    loadServerHierarchicalMemory: vi.fn().mockResolvedValue({
-      memoryContent: '',
-      fileCount: 0,
-      filePaths: [],
-    }),
     createPolicyEngineConfig: vi.fn().mockResolvedValue({
       rules: [],
       checkers: [],

packages/cli/src/gemini.tsx

@@ -499,7 +499,6 @@ export async function main() {
   const partialConfig = await loadCliConfig(settings.merged, sessionId, argv, {
     projectHooks: settings.workspace.settings.hooks,
     skipExtensions: true,
-    skipMemoryLoad: true,
   });
 
   adminControlsListner.setConfig(partialConfig);

packages/cli/src/patches/http-proxy-agent.ts

@@ -0,0 +1,8 @@
+/**
+ * @license
+ * Copyright 2026 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+// eslint-disable-next-line import/no-relative-packages
+export { HttpProxyAgent } from '../../../../node_modules/http-proxy-agent/dist/index.js';

packages/cli/src/patches/https-proxy-agent.ts

@@ -0,0 +1,8 @@
+/**
+ * @license
+ * Copyright 2026 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+// eslint-disable-next-line import/no-relative-packages
+export { HttpsProxyAgent } from '../../../../node_modules/https-proxy-agent/dist/index.js';

packages/cli/src/test-utils/mockConfig.ts

@@ -38,7 +38,6 @@ export const createMockConfig = (overrides: Partial<Config> = {}): Config =>
       fireSessionEndEvent: vi.fn().mockResolvedValue(undefined),
       fireSessionStartEvent: vi.fn().mockResolvedValue(undefined),
     })),
-    isMemoryV2Enabled: vi.fn(() => false),
     isAutoMemoryEnabled: vi.fn(() => false),
     getListExtensions: vi.fn(() => false),
     getExtensions: vi.fn(() => []),
@@ -166,7 +165,6 @@ export const createMockConfig = (overrides: Partial<Config> = {}): Config =>
     getEnableEventDrivenScheduler: vi.fn().mockReturnValue(false),
     getAdminSkillsEnabled: vi.fn().mockReturnValue(false),
     getDisabledSkills: vi.fn().mockReturnValue([]),
-    getExperimentalJitContext: vi.fn().mockReturnValue(false),
     getExperimentalGemma: vi.fn().mockReturnValue(false),
     getMemoryBoundaryMarkers: vi.fn().mockReturnValue(['.git']),
     getTerminalBackground: vi.fn().mockReturnValue(undefined),

packages/cli/src/ui/AppContainer.tsx

@@ -47,7 +47,6 @@ import { MouseProvider } from './contexts/MouseContext.js';
 import { ScrollProvider } from './contexts/ScrollProvider.js';
 import {
   type StartupWarning,
-  type EditorType,
   type Config,
   type IdeInfo,
   type IdeContext,
@@ -68,9 +67,9 @@ import {
   ShellExecutionService,
   saveApiKey,
   debugLogger,
+  isValidEditorType,
   coreEvents,
   CoreEvent,
-  refreshServerHierarchicalMemory,
   flattenMemory,
   type MemoryChangedPayload,
   writeToStdout,
@@ -255,7 +254,6 @@ export const AppContainer = (props: AppContainerProps) => {
   }, [mouseMode, setOptions]);
 
   const [corgiMode, setCorgiMode] = useState(false);
-  const [forceRerenderKey, setForceRerenderKey] = useState(0);
   const [debugMessage, setDebugMessage] = useState<string>('');
   const [quittingMessages, setQuittingMessages] = useState<
     HistoryItem[] | null
@@ -610,11 +608,10 @@ export const AppContainer = (props: AppContainerProps) => {
 
   const staticAreaMaxItemHeight = Math.max(terminalHeight * 4, 100);
 
-  const getPreferredEditor = useCallback(
-    // eslint-disable-next-line @typescript-eslint/no-unsafe-type-assertion
-    () => settings.merged.general.preferredEditor as EditorType,
-    [settings.merged.general.preferredEditor],
-  );
+  const getPreferredEditor = useCallback(() => {
+    const val = settings.merged.general.preferredEditor;
+    return isValidEditorType(val) ? val : undefined;
+  }, [settings.merged.general.preferredEditor]);
 
   const buffer = useTextBuffer({
     initialText: '',
@@ -1075,19 +1072,10 @@ Logging in with Google... Restarting Gemini CLI to continue.
       Date.now(),
     );
     try {
-      let flattenedMemory: string;
-      let fileCount: number;
-
-      if (config.isJitContextEnabled()) {
-        await config.getMemoryContextManager()?.refresh();
-        config.updateSystemInstructionIfInitialized();
-        flattenedMemory = flattenMemory(config.getUserMemory());
-        fileCount = config.getGeminiMdFileCount();
-      } else {
-        const result = await refreshServerHierarchicalMemory(config);
-        flattenedMemory = flattenMemory(result.memoryContent);
-        fileCount = result.fileCount;
-      }
+      await config.getMemoryContextManager()?.refresh();
+      config.updateSystemInstructionIfInitialized();
+      const flattenedMemory = flattenMemory(config.getUserMemory());
+      const fileCount = config.getGeminiMdFileCount();
 
       historyManager.addItem(
         {
@@ -1698,8 +1686,6 @@ Logging in with Google... Restarting Gemini CLI to continue.
     needsRestart: ideNeedsRestart,
     restartReason: ideTrustRestartReason,
   } = useIdeTrustListener();
-  const isInitialMount = useRef(true);
-
   useIncludeDirsTrust(config, isTrustedFolder, historyManager, setCustomDialog);
 
   const tabFocusTimeoutRef = useRef<NodeJS.Timeout | null>(null);
@@ -1752,8 +1738,6 @@ Logging in with Google... Restarting Gemini CLI to continue.
   const { handleSuspend } = useSuspend({
     handleWarning,
     setRawMode,
-    refreshStatic,
-    setForceRerenderKey,
     shouldUseAlternateScreen,
   });
 
@@ -1764,21 +1748,6 @@ Logging in with Google... Restarting Gemini CLI to continue.
     }
   }, [ideNeedsRestart]);
 
-  useEffect(() => {
-    if (isInitialMount.current) {
-      isInitialMount.current = false;
-      return;
-    }
-
-    const handler = setTimeout(() => {
-      refreshStatic();
-    }, 300);
-
-    return () => {
-      clearTimeout(handler);
-    };
-  }, [terminalWidth, refreshStatic]);
-
   useEffect(() => {
     const unsubscribe = ideContextStore.subscribe(setIdeContextState);
     setIdeContextState(ideContextStore.get());
@@ -2883,7 +2852,7 @@ Logging in with Google... Restarting Gemini CLI to continue.
                   <ShellFocusContext.Provider value={isFocused}>
                     <MouseProvider mouseEventsEnabled={mouseMode}>
                       <ScrollProvider>
-                        <App key={`app-${forceRerenderKey}`} />
+                        <App />
                       </ScrollProvider>
                     </MouseProvider>
                   </ShellFocusContext.Provider>

packages/cli/src/ui/commands/directoryCommand.test.tsx

@@ -80,6 +80,7 @@ describe('directoryCommand', () => {
       }),
       getWorkingDir: () => path.resolve('/test/dir'),
       shouldLoadMemoryFromIncludeDirectories: () => false,
+      getMemoryContextManager: vi.fn(),
       getDebugMode: () => false,
       getFileService: () => ({}),
       getFileFilteringOptions: () => ({ ignore: [], include: [] }),

packages/cli/src/ui/commands/directoryCommand.tsx

@@ -15,10 +15,7 @@ import {
   type CommandContext,
 } from './types.js';
 import { MessageType, type HistoryItem } from '../types.js';
-import {
-  refreshServerHierarchicalMemory,
-  type Config,
-} from '@google/gemini-cli-core';
+import { type Config } from '@google/gemini-cli-core';
 import {
   expandHomeDir,
   getDirectorySuggestions,
@@ -47,7 +44,7 @@ async function finishAddingDirectories(
   if (added.length > 0) {
     try {
       if (config.shouldLoadMemoryFromIncludeDirectories()) {
-        await refreshServerHierarchicalMemory(config);
+        await config.getMemoryContextManager()?.refresh();
       }
       addItem({
         type: MessageType.INFO,

packages/cli/src/ui/commands/memoryCommand.test.ts

@@ -11,13 +11,10 @@ import { createMockCommandContext } from '../../test-utils/mockCommandContext.js
 import { MessageType } from '../types.js';
 import type { LoadedSettings } from '../../config/settings.js';
 import {
-  type Config,
   refreshMemory,
-  refreshServerHierarchicalMemory,
   SimpleExtensionLoader,
   type FileDiscoveryService,
   showMemory,
-  addMemory,
   listMemoryFiles,
   flattenMemory,
 } from '@google/gemini-cli-core';
@@ -32,46 +29,28 @@ vi.mock('@google/gemini-cli-core', async (importOriginal) => {
       return String(error);
     }),
     refreshMemory: vi.fn(async (config) => {
-      if (config.isJitContextEnabled()) {
-        await config.getContextManager()?.refresh();
-        const memoryContent = original.flattenMemory(config.getUserMemory());
-        const fileCount = config.getGeminiMdFileCount() || 0;
-        return {
-          type: 'message',
-          messageType: 'info',
-          content: `Memory reloaded successfully. Loaded ${memoryContent.length} characters from ${fileCount} file(s).`,
-        };
-      }
+      await config.getMemoryContextManager()?.refresh();
+      const memoryContent = original.flattenMemory(config.getUserMemory());
+      const fileCount = config.getGeminiMdFileCount() || 0;
       return {
         type: 'message',
         messageType: 'info',
-        content: 'Memory reloaded successfully.',
+        content: `Memory reloaded successfully. Loaded ${memoryContent.length} characters from ${fileCount} file(s).`,
       };
     }),
     showMemory: vi.fn(),
-    addMemory: vi.fn(),
     listMemoryFiles: vi.fn(),
-    refreshServerHierarchicalMemory: vi.fn(),
   };
 });
 
 const mockRefreshMemory = refreshMemory as Mock;
-const mockRefreshServerHierarchicalMemory =
-  refreshServerHierarchicalMemory as Mock;
 
 describe('memoryCommand', () => {
   let mockContext: CommandContext;
 
-  const buildMemoryCommand = (isMemoryV2 = false): SlashCommand => {
-    const config: Pick<Config, 'isMemoryV2Enabled'> = {
-      isMemoryV2Enabled: () => isMemoryV2,
-    };
-    return memoryCommand(config as Config);
-  };
+  const buildMemoryCommand = (): SlashCommand => memoryCommand(null);
 
-  const getSubCommand = (
-    name: 'show' | 'add' | 'reload' | 'list',
-  ): SlashCommand => {
+  const getSubCommand = (name: 'show' | 'reload' | 'list'): SlashCommand => {
     const subCommand = buildMemoryCommand().subCommands?.find(
       (cmd) => cmd.name === name,
     );
@@ -81,23 +60,11 @@ describe('memoryCommand', () => {
     return subCommand;
   };
 
-  describe('Memory v2', () => {
-    it('omits the /memory add subcommand when memoryV2 is enabled', () => {
-      const command = buildMemoryCommand(true);
+  describe('subcommands', () => {
+    it('does not include the legacy add subcommand', () => {
+      const command = buildMemoryCommand();
       const names = command.subCommands?.map((cmd) => cmd.name) ?? [];
-      expect(names).not.toContain('add');
-    });
-
-    it('includes the /memory add subcommand by default', () => {
-      const command = buildMemoryCommand(false);
-      const names = command.subCommands?.map((cmd) => cmd.name) ?? [];
-      expect(names).toContain('add');
-    });
-
-    it('includes the /memory add subcommand when no config is provided', () => {
-      const command = memoryCommand(null);
-      const names = command.subCommands?.map((cmd) => cmd.name) ?? [];
-      expect(names).toContain('add');
+      expect(names).toEqual(['show', 'reload', 'list', 'inbox']);
     });
   });
 
@@ -178,63 +145,6 @@ describe('memoryCommand', () => {
     });
   });
 
-  describe('/memory add', () => {
-    let addCommand: SlashCommand;
-
-    beforeEach(() => {
-      addCommand = getSubCommand('add');
-      vi.mocked(addMemory).mockImplementation((args) => {
-        if (!args || args.trim() === '') {
-          return {
-            type: 'message',
-            messageType: 'error',
-            content: 'Usage: /memory add <text to remember>',
-          };
-        }
-        return {
-          type: 'tool',
-          toolName: 'save_memory',
-          toolArgs: { fact: args.trim() },
-        };
-      });
-      mockContext = createMockCommandContext();
-    });
-
-    it('should return an error message if no arguments are provided', () => {
-      if (!addCommand.action) throw new Error('Command has no action');
-
-      const result = addCommand.action(mockContext, '  ');
-      expect(result).toEqual({
-        type: 'message',
-        messageType: 'error',
-        content: 'Usage: /memory add <text to remember>',
-      });
-
-      expect(mockContext.ui.addItem).not.toHaveBeenCalled();
-    });
-
-    it('should return a tool action and add an info message when arguments are provided', () => {
-      if (!addCommand.action) throw new Error('Command has no action');
-
-      const fact = 'remember this';
-      const result = addCommand.action(mockContext, `  ${fact}  `);
-
-      expect(mockContext.ui.addItem).toHaveBeenCalledWith(
-        {
-          type: MessageType.INFO,
-          text: `Attempting to save to memory: "${fact}"`,
-        },
-        expect.any(Number),
-      );
-
-      expect(result).toEqual({
-        type: 'tool',
-        toolName: 'save_memory',
-        toolArgs: { fact },
-      });
-    });
-  });
-
   describe('/memory reload', () => {
     let reloadCommand: SlashCommand;
     let mockSetUserMemory: Mock;
@@ -270,8 +180,7 @@ describe('memoryCommand', () => {
         updateSystemInstructionIfInitialized: vi
           .fn()
           .mockResolvedValue(undefined),
-        isJitContextEnabled: vi.fn().mockReturnValue(false),
-        getContextManager: vi.fn().mockReturnValue({
+        getMemoryContextManager: vi.fn().mockReturnValue({
           refresh: mockContextManagerRefresh,
         }),
         getUserMemory: vi.fn().mockReturnValue(''),
@@ -294,21 +203,18 @@ describe('memoryCommand', () => {
       mockRefreshMemory.mockClear();
     });
 
-    it('should use ContextManager.refresh when JIT is enabled', async () => {
+    it('should use MemoryContextManager.refresh', async () => {
       if (!reloadCommand.action) throw new Error('Command has no action');
 
-      // Enable JIT in mock config
       const config = mockContext.services.agentContext?.config;
       if (!config) throw new Error('Config is undefined');
 
-      vi.mocked(config.isJitContextEnabled).mockReturnValue(true);
       vi.mocked(config.getUserMemory).mockReturnValue('JIT Memory Content');
       vi.mocked(config.getGeminiMdFileCount).mockReturnValue(3);
 
       await reloadCommand.action(mockContext, '');
 
       expect(mockContextManagerRefresh).toHaveBeenCalledOnce();
-      expect(mockRefreshServerHierarchicalMemory).not.toHaveBeenCalled();
 
       expect(mockContext.ui.addItem).toHaveBeenCalledWith(
         {
@@ -319,7 +225,7 @@ describe('memoryCommand', () => {
       );
     });
 
-    it('should display success message when memory is reloaded with content (Legacy)', async () => {
+    it('should display success message when memory is reloaded with content', async () => {
       if (!reloadCommand.action) throw new Error('Command has no action');
 
       const successMessage = {

packages/cli/src/ui/commands/memoryCommand.ts

@@ -6,7 +6,6 @@
 
 import React from 'react';
 import {
-  addMemory,
   type Config,
   listMemoryFiles,
   refreshMemory,
@@ -41,30 +40,6 @@ const showSubCommand: SlashCommand = {
   },
 };
 
-const addSubCommand: SlashCommand = {
-  name: 'add',
-  description: 'Add content to the memory',
-  kind: CommandKind.BUILT_IN,
-  autoExecute: false,
-  action: (context, args): SlashCommandActionReturn | void => {
-    const result = addMemory(args);
-
-    if (result.type === 'message') {
-      return result;
-    }
-
-    context.ui.addItem(
-      {
-        type: MessageType.INFO,
-        text: `Attempting to save to memory: "${args.trim()}"`,
-      },
-      Date.now(),
-    );
-
-    return result;
-  },
-};
-
 const reloadSubCommand: SlashCommand = {
   name: 'reload',
   altNames: ['refresh'],
@@ -170,14 +145,9 @@ const inboxSubCommand: SlashCommand = {
   },
 };
 
-export const memoryCommand = (config: Config | null): SlashCommand => {
-  // The `add` subcommand depends on the `save_memory` tool, which is not
-  // registered when Memory v2 is enabled. Omit it in that case.
-  const isMemoryV2 = config?.isMemoryV2Enabled() ?? false;
-
+export const memoryCommand = (_config: Config | null): SlashCommand => {
   const subCommands: SlashCommand[] = [
     showSubCommand,
-    ...(isMemoryV2 ? [] : [addSubCommand]),
     reloadSubCommand,
     listSubCommand,
     inboxSubCommand,

packages/cli/src/ui/commands/rewindCommand.tsx

@@ -14,7 +14,6 @@ import { type HistoryItem } from '../types.js';
 import { convertSessionToHistoryFormats } from '../hooks/useSessionBrowser.js';
 import { revertFileChanges } from '../utils/rewindFileOps.js';
 import { RewindOutcome } from '../components/RewindConfirmation.js';
-import type { Content } from '@google/genai';
 import {
   checkExhaustive,
   coreEvents,
@@ -58,7 +57,7 @@ async function rewindConversation(
     const { uiHistory } = convertSessionToHistoryFormats(conversation.messages);
     const clientHistory = convertSessionToClientHistory(conversation.messages);
 
-    client.setHistory(clientHistory as Content[]);
+    client.setHistory(clientHistory);
 
     // Reset context manager as we are rewinding history
     await context.services.agentContext?.config

packages/cli/src/ui/components/Composer.tsx

@@ -154,6 +154,8 @@ export const Composer = ({ isFocused = true }: { isFocused?: boolean }) => {
           onEscapePromptChange={uiActions.onEscapePromptChange}
           focus={isFocused}
           vimHandleInput={uiActions.vimHandleInput}
+          vimEnabled={vimEnabled}
+          vimMode={vimMode}
           isEmbeddedShellFocused={uiState.embeddedShellFocused}
           popAllMessages={uiActions.popAllMessages}
           onQueueMessage={uiActions.addMessage}

packages/cli/src/ui/components/EditorSettingsDialog.tsx

@@ -22,7 +22,6 @@ import {
   type EditorType,
   isEditorAvailable,
   EDITOR_DISPLAY_NAMES,
-  coreEvents,
 } from '@google/gemini-cli-core';
 import { useKeypress } from '../hooks/useKeypress.js';
 
@@ -72,10 +71,6 @@ export function EditorSettingsDialog({
       )
     : 0;
   if (editorIndex === -1) {
-    coreEvents.emitFeedback(
-      'error',
-      `Editor is not supported: ${currentPreference}`,
-    );
     editorIndex = 0;
   }
 
@@ -131,10 +126,7 @@ export function EditorSettingsDialog({
     isEditorAvailable(settings.merged.general.preferredEditor)
   ) {
     mergedEditorName =
-      EDITOR_DISPLAY_NAMES[
-        // eslint-disable-next-line @typescript-eslint/no-unsafe-type-assertion
-        settings.merged.general.preferredEditor as EditorType
-      ];
+      EDITOR_DISPLAY_NAMES[settings.merged.general.preferredEditor];
   }
 
   return (
@@ -161,6 +153,7 @@ export function EditorSettingsDialog({
           onSelect={handleEditorSelect}
           isFocused={focusedSection === 'editor'}
           key={selectedScope}
+          maxItemsToShow={editorItems.length}
         />
 
         <Box marginTop={1} flexDirection="column">

packages/cli/src/ui/components/InputPrompt.test.tsx

@@ -1962,8 +1962,8 @@ describe('InputPrompt', () => {
       },
       {
         name: 'should NOT trigger completion when cursor is after space following /',
-        text: '/memory add',
-        cursor: [0, 11],
+        text: '/memory list',
+        cursor: [0, 12],
         showSuggestions: false,
       },
       {
@@ -4898,6 +4898,60 @@ describe('InputPrompt', () => {
       unmount();
     });
 
+    it('should NOT open shortcuts help with ? in vim NORMAL mode', async () => {
+      const setShortcutsHelpVisible = vi.fn();
+      const vimHandleInput = vi.fn().mockReturnValue(true);
+
+      const { stdin, unmount } = await renderWithProviders(
+        <TestInputPrompt
+          {...props}
+          vimEnabled={true}
+          vimMode="NORMAL"
+          vimHandleInput={vimHandleInput}
+        />,
+        {
+          uiActions: { setShortcutsHelpVisible },
+        },
+      );
+
+      await act(async () => {
+        stdin.write('?');
+      });
+
+      expect(setShortcutsHelpVisible).not.toHaveBeenCalled();
+      expect(vimHandleInput).toHaveBeenCalled();
+      expect(mockBuffer.handleInput).not.toHaveBeenCalled();
+
+      unmount();
+    });
+
+    it('should open shortcuts help with ? in vim INSERT mode', async () => {
+      const setShortcutsHelpVisible = vi.fn();
+      const vimHandleInput = vi.fn().mockReturnValue(false);
+
+      const { stdin, unmount } = await renderWithProviders(
+        <TestInputPrompt
+          {...props}
+          vimEnabled={true}
+          vimMode="INSERT"
+          vimHandleInput={vimHandleInput}
+        />,
+        {
+          uiActions: { setShortcutsHelpVisible },
+        },
+      );
+
+      await act(async () => {
+        stdin.write('?');
+      });
+
+      await waitFor(() => {
+        expect(setShortcutsHelpVisible).toHaveBeenCalledWith(true);
+      });
+
+      unmount();
+    });
+
     it.each([
       {
         name: 'terminal paste event occurs',

packages/cli/src/ui/components/InputPrompt.tsx

@@ -92,6 +92,7 @@ import { useAlternateBuffer } from '../hooks/useAlternateBuffer.js';
 import { useIsHelpDismissKey } from '../utils/shortcutsHelp.js';
 import { useRepeatedKeyPress } from '../hooks/useRepeatedKeyPress.js';
 import { useKeyMatchers } from '../hooks/useKeyMatchers.js';
+import type { VimMode } from '../contexts/VimModeContext.js';
 
 const SCROLLBAR_GUTTER_WIDTH = 1;
 
@@ -126,6 +127,8 @@ export interface InputPromptProps {
   onEscapePromptChange?: (showPrompt: boolean) => void;
   onSuggestionsVisibilityChange?: (visible: boolean) => void;
   vimHandleInput?: (key: Key) => boolean;
+  vimEnabled?: boolean;
+  vimMode?: VimMode;
   isEmbeddedShellFocused?: boolean;
   setQueueErrorMessage: (message: string | null) => void;
   streamingState: StreamingState;
@@ -214,6 +217,8 @@ export const InputPrompt: React.FC<InputPromptProps> = ({
   onEscapePromptChange,
   onSuggestionsVisibilityChange,
   vimHandleInput,
+  vimEnabled,
+  vimMode,
   isEmbeddedShellFocused,
   setQueueErrorMessage,
   streamingState,
@@ -859,7 +864,11 @@ export const InputPrompt: React.FC<InputPromptProps> = ({
       }
 
       if (shortcutsHelpVisible) {
-        if (key.sequence === '?' && key.insertable) {
+        if (
+          key.sequence === '?' &&
+          key.insertable &&
+          (!vimEnabled || vimMode === 'INSERT')
+        ) {
           setShortcutsHelpVisible(false);
           buffer.handleInput(key);
           return true;
@@ -879,7 +888,8 @@ export const InputPrompt: React.FC<InputPromptProps> = ({
         key.sequence === '?' &&
         key.insertable &&
         !shortcutsHelpVisible &&
-        buffer.text.length === 0
+        buffer.text.length === 0 &&
+        (!vimEnabled || vimMode === 'INSERT')
       ) {
         setShortcutsHelpVisible(true);
         return true;
@@ -1374,6 +1384,8 @@ export const InputPrompt: React.FC<InputPromptProps> = ({
       resetCompletionState,
       resetEscapeState,
       vimHandleInput,
+      vimEnabled,
+      vimMode,
       reverseSearchActive,
       textBeforeReverseSearch,
       cursorPosition,

packages/cli/src/ui/components/ModelDialog.test.tsx

@@ -34,6 +34,11 @@ vi.mock('@google/gemini-cli-core', async (importOriginal) => {
     await importOriginal<typeof import('@google/gemini-cli-core')>();
   return {
     ...actual,
+    getAutoModelDescription: (
+      hasAccessToPreview: boolean,
+      useGemini3_1?: boolean,
+    ) =>
+      `Auto Model Description (preview: ${hasAccessToPreview}, 3.1: ${useGemini3_1})`,
     getDisplayString: (val: string) => mockGetDisplayString(val),
     logModelSlashCommand: (config: Config, event: ModelSlashCommandEvent) =>
       mockLogModelSlashCommand(config, event),

packages/cli/src/ui/components/ModelDialog.tsx

@@ -26,7 +26,6 @@ import {
   AuthType,
   PREVIEW_GEMINI_3_1_CUSTOM_TOOLS_MODEL,
   isProModel,
-  getChannelFromVersion,
   getAutoModelDescription,
 } from '@google/gemini-cli-core';
 import { useKeypress } from '../hooks/useKeypress.js';
@@ -66,7 +65,7 @@ export function ModelDialog({ onClose }: ModelDialogProps): React.JSX.Element {
   // Determine the Preferred Model (read once when the dialog opens).
   const preferredModel = config?.getModel() || GEMINI_MODEL_ALIAS_AUTO;
 
-  const shouldShowPreviewModels = config?.getHasAccessToPreviewModel();
+  const shouldShowPreviewModels = config?.getHasAccessToPreviewModel() ?? false;
   const useGemini31 = config?.getGemini31LaunchedSync?.() ?? false;
   const useGemini31FlashLite =
     config?.getGemini31FlashLiteLaunchedSync?.() ?? false;
@@ -122,12 +121,6 @@ export function ModelDialog({ onClose }: ModelDialogProps): React.JSX.Element {
     },
     { isActive: true },
   );
-
-  const releaseChannel = useMemo(
-    () => getChannelFromVersion(config?.clientVersion ?? ''),
-    [config?.clientVersion],
-  );
-
   const mainOptions = useMemo(() => {
     // --- DYNAMIC PATH ---
     if (
@@ -142,7 +135,6 @@ export function ModelDialog({ onClose }: ModelDialogProps): React.JSX.Element {
           useCustomTools: useCustomToolModel,
           hasAccessToPreview: shouldShowPreviewModels,
           hasAccessToProModel,
-          releaseChannel,
         });
 
       const list = allOptions
@@ -170,7 +162,10 @@ export function ModelDialog({ onClose }: ModelDialogProps): React.JSX.Element {
       {
         value: GEMINI_MODEL_ALIAS_AUTO,
         title: getDisplayString(GEMINI_MODEL_ALIAS_AUTO),
-        description: getAutoModelDescription(releaseChannel, useGemini31),
+        description: getAutoModelDescription(
+          shouldShowPreviewModels,
+          useGemini31,
+        ),
         key: GEMINI_MODEL_ALIAS_AUTO,
       },
       {
@@ -192,7 +187,6 @@ export function ModelDialog({ onClose }: ModelDialogProps): React.JSX.Element {
     useGemini31FlashLite,
     useCustomToolModel,
     hasAccessToProModel,
-    releaseChannel,
   ]);
 
   const manualOptions = useMemo(() => {
@@ -209,7 +203,6 @@ export function ModelDialog({ onClose }: ModelDialogProps): React.JSX.Element {
           useCustomTools: useCustomToolModel,
           hasAccessToPreview: shouldShowPreviewModels,
           hasAccessToProModel,
-          releaseChannel,
         });
 
       return allOptions
@@ -302,7 +295,6 @@ export function ModelDialog({ onClose }: ModelDialogProps): React.JSX.Element {
     useGemini31FlashLite,
     useCustomToolModel,
     hasAccessToProModel,
-    releaseChannel,
     config,
   ]);
 

packages/cli/src/ui/components/SessionSummaryDisplay.test.tsx

@@ -12,7 +12,6 @@ import { useConfig } from '../contexts/ConfigContext.js';
 import { type SessionMetrics } from '../contexts/SessionContext.js';
 import {
   ToolCallDecision,
-  getShellConfiguration,
   isWindows,
   type WorktreeSettings,
 } from '@google/gemini-cli-core';
@@ -22,7 +21,6 @@ vi.mock('@google/gemini-cli-core', async (importOriginal) => {
     await importOriginal<typeof import('@google/gemini-cli-core')>();
   return {
     ...actual,
-    getShellConfiguration: vi.fn(),
     isWindows: vi.fn(),
   };
 });
@@ -45,7 +43,6 @@ vi.mock('../contexts/ConfigContext.js', async (importOriginal) => {
   };
 });
 
-const getShellConfigurationMock = vi.mocked(getShellConfiguration);
 const isWindowsMock = vi.mocked(isWindows);
 const useSessionStatsMock = vi.mocked(SessionContext.useSessionStats);
 
@@ -104,11 +101,6 @@ describe('<SessionSummaryDisplay />', () => {
   };
 
   beforeEach(() => {
-    getShellConfigurationMock.mockReturnValue({
-      executable: 'bash',
-      argsPrefix: ['-c'],
-      shell: 'bash',
-    });
     isWindowsMock.mockReturnValue(false);
   });
 
@@ -173,11 +165,6 @@ describe('<SessionSummaryDisplay />', () => {
 
     it('renders a standard UUID-formatted session ID in the footer (powershell) on Windows', async () => {
       isWindowsMock.mockReturnValue(true);
-      getShellConfigurationMock.mockReturnValue({
-        executable: 'powershell.exe',
-        argsPrefix: ['-NoProfile', '-Command'],
-        shell: 'powershell',
-      });
 
       const uuidSessionId = '1234-abcd-5678-efgh';
       const { lastFrame, unmount } = await renderWithMockedStats(
@@ -192,11 +179,7 @@ describe('<SessionSummaryDisplay />', () => {
     });
 
     it('sanitizes a malicious session ID in the footer (powershell)', async () => {
-      getShellConfigurationMock.mockReturnValue({
-        executable: 'powershell.exe',
-        argsPrefix: ['-NoProfile', '-Command'],
-        shell: 'powershell',
-      });
+      isWindowsMock.mockReturnValue(true);
 
       const maliciousSessionId = "'; rm -rf / #";
       const { lastFrame, unmount } = await renderWithMockedStats(

packages/cli/src/ui/components/SessionSummaryDisplay.tsx

@@ -10,8 +10,8 @@ import { useSessionStats } from '../contexts/SessionContext.js';
 import { useConfig } from '../contexts/ConfigContext.js';
 import {
   escapeShellArg,
-  getShellConfiguration,
   isWindows,
+  type ShellType,
 } from '@google/gemini-cli-core';
 
 interface SessionSummaryDisplayProps {
@@ -23,7 +23,7 @@ export const SessionSummaryDisplay: React.FC<SessionSummaryDisplayProps> = ({
 }) => {
   const { stats } = useSessionStats();
   const config = useConfig();
-  const { shell } = getShellConfiguration();
+  const shell: ShellType = isWindows() ? 'powershell' : 'bash';
 
   const worktreeSettings = config.getWorktreeSettings();
 

packages/cli/src/ui/components/__snapshots__/InputPrompt.test.tsx.snap

@@ -174,27 +174,6 @@ exports[`InputPrompt > mouse interaction > should toggle paste expansion on doub
 "
 `;
 
-exports[`InputPrompt > mouse interaction > should toggle paste expansion on double-click 4`] = `
-"▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄
- > [Pasted Text: 10 lines]
-▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀
-"
-`;
-
-exports[`InputPrompt > mouse interaction > should toggle paste expansion on double-click 5`] = `
-"▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄
- > [Pasted Text: 10 lines]
-▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀
-"
-`;
-
-exports[`InputPrompt > mouse interaction > should toggle paste expansion on double-click 6`] = `
-"▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄
- > [Pasted Text: 10 lines]
-▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀
-"
-`;
-
 exports[`InputPrompt > multiline rendering > should correctly render multiline input including blank lines 1`] = `
 "────────────────────────────────────────────────────────────────────────────────────────────────────
  > hello

packages/cli/src/ui/components/shared/performance.test.ts

@@ -9,6 +9,17 @@ import { renderHook } from '../../../test-utils/render.js';
 import { useTextBuffer } from './text-buffer.js';
 import { parseInputForHighlighting } from '../../utils/highlight.js';
 
+vi.mock('../../contexts/SettingsContext.js', async (importOriginal) => {
+  const actual =
+    await importOriginal<typeof import('../../contexts/SettingsContext.js')>();
+  return {
+    ...actual,
+    useSettings: () => ({
+      merged: { general: { openEditorInNewWindow: false } },
+    }),
+  };
+});
+
 describe('text-buffer performance', () => {
   afterEach(() => {
     vi.restoreAllMocks();

packages/cli/src/ui/components/shared/text-buffer.test.ts

@@ -44,6 +44,17 @@ import { cpLen } from '../../utils/textUtils.js';
 import { type Key } from '../../hooks/useKeypress.js';
 import { escapePath } from '@google/gemini-cli-core';
 
+vi.mock('../../contexts/SettingsContext.js', async (importOriginal) => {
+  const actual =
+    await importOriginal<typeof import('../../contexts/SettingsContext.js')>();
+  return {
+    ...actual,
+    useSettings: () => ({
+      merged: { general: { openEditorInNewWindow: false } },
+    }),
+  };
+});
+
 const defaultVisualLayout: VisualLayout = {
   visualLines: [''],
   logicalToVisualMap: [[[0, 0]]],

packages/cli/src/ui/components/shared/text-buffer.ts

@@ -13,6 +13,7 @@ import { LRUCache } from 'mnemonist';
 import {
   coreEvents,
   debugLogger,
+  getErrorMessage,
   unescapePath,
   type EditorType,
 } from '@google/gemini-cli-core';
@@ -30,6 +31,7 @@ import type { VimAction } from './vim-buffer-actions.js';
 import { handleVimAction } from './vim-buffer-actions.js';
 import { LRU_BUFFER_PERF_CACHE_LIMIT } from '../../constants.js';
 import { openFileInEditor } from '../../utils/editorUtils.js';
+import { useSettings } from '../../contexts/SettingsContext.js';
 import { useKeyMatchers } from '../../hooks/useKeyMatchers.js';
 
 export const LARGE_PASTE_LINE_THRESHOLD = 5;
@@ -2840,6 +2842,7 @@ export function useTextBuffer({
   singleLine = false,
   getPreferredEditor,
 }: UseTextBufferProps): TextBuffer {
+  const settings = useSettings();
   const keyMatchers = useKeyMatchers();
   const initialState = useMemo((): TextBufferState => {
     const lines = initialText.split('\n');
@@ -3325,6 +3328,7 @@ export function useTextBuffer({
         stdin,
         setRawMode,
         getPreferredEditor?.(),
+        settings.merged.general.openEditorInNewWindow,
       );
 
       let newText = fs.readFileSync(filePath, 'utf8');
@@ -3342,11 +3346,7 @@ export function useTextBuffer({
 
       dispatch({ type: 'set_text', payload: newText, pushToUndo: false });
     } catch (err) {
-      coreEvents.emitFeedback(
-        'error',
-        '[useTextBuffer] external editor error',
-        err,
-      );
+      coreEvents.emitFeedback('error', getErrorMessage(err), err);
     } finally {
       try {
         fs.unlinkSync(filePath);
@@ -3359,7 +3359,14 @@ export function useTextBuffer({
         /* ignore */
       }
     }
-  }, [text, pastedContent, stdin, setRawMode, getPreferredEditor]);
+  }, [
+    text,
+    pastedContent,
+    stdin,
+    setRawMode,
+    getPreferredEditor,
+    settings.merged.general.openEditorInNewWindow,
+  ]);
 
   const handleInput = useCallback(
     (key: Key): boolean => {

packages/cli/src/ui/constants/tips.ts

@@ -144,7 +144,6 @@ export const INFORMATIVE_TIPS = [
   'Authenticate with an OAuth-enabled MCP server with /mcp auth',
   'Reload MCP servers with /mcp reload',
   'See the current instructional context with /memory show',
-  'Add content to the instructional memory with /memory add',
   'Reload instructional context from GEMINI.md files with /memory reload',
   'List the paths of the GEMINI.md files in use with /memory list',
   'Choose your Gemini model with /model',

packages/cli/src/ui/hooks/atCommandProcessor.test.ts

@@ -14,6 +14,7 @@ import {
   type Mock,
 } from 'vitest';
 import {
+  checkPermissions,
   handleAtCommand,
   escapeAtSymbols,
   unescapeLiteralAt,
@@ -35,6 +36,7 @@ import {
 import * as core from '@google/gemini-cli-core';
 import * as os from 'node:os';
 import type { UseHistoryManagerReturn } from './useHistoryManager.js';
+import * as fs from 'node:fs';
 import * as fsPromises from 'node:fs/promises';
 import * as path from 'node:path';
 
@@ -75,6 +77,12 @@ describe('handleAtCommand', () => {
       unsubscribe: vi.fn(),
     } as unknown as core.MessageBus;
 
+    const mockWorkspaceContext = {
+      isPathWithinWorkspace: (p: string) =>
+        p.startsWith(testRootDir) || p.startsWith('/private' + testRootDir),
+      getDirectories: () => [testRootDir],
+    };
+
     mockConfig = {
       getToolRegistry,
       getTargetDir: () => testRootDir,
@@ -89,11 +97,8 @@ describe('handleAtCommand', () => {
       }),
       getFileSystemService: () => new StandardFileSystemService(),
       getEnableRecursiveFileSearch: vi.fn(() => true),
-      getWorkspaceContext: () => ({
-        isPathWithinWorkspace: (p: string) =>
-          p.startsWith(testRootDir) || p.startsWith('/private' + testRootDir),
-        getDirectories: () => [testRootDir],
-      }),
+      getWorkspaceContext: () => mockWorkspaceContext,
+      getMemoryContextManager: () => undefined,
       storage: {
         getProjectTempDir: () => path.join(os.tmpdir(), 'gemini-cli-temp'),
       },
@@ -103,7 +108,8 @@ describe('handleAtCommand', () => {
         }
 
         const workspaceContext = this.getWorkspaceContext();
-        if (workspaceContext.isPathWithinWorkspace(absolutePath)) {
+        const directories = workspaceContext.getDirectories();
+        if (directories.some((dir) => absolutePath.startsWith(dir))) {
           return true;
         }
 
@@ -1459,31 +1465,126 @@ describe('handleAtCommand', () => {
     );
   });
 
-  it('should include agent nudge when agents are found', async () => {
-    const agentName = 'my-agent';
-    const otherAgent = 'other-agent';
+  it('should resolve files in multiple workspace directories', async () => {
+    const secondRootDir = await fsPromises.mkdtemp(
+      path.join(os.tmpdir(), 'second-root-'),
+    );
+    try {
+      const fileContent = 'Second root content';
+      const filePath = path.join(secondRootDir, 'second-file.txt');
+      await fsPromises.writeFile(filePath, fileContent);
 
-    // Mock getAgentRegistry on the config
-    mockConfig.getAgentRegistry = vi.fn().mockReturnValue({
-      getDefinition: (name: string) =>
-        name === agentName || name === otherAgent ? { name } : undefined,
+      vi.spyOn(
+        mockConfig.getWorkspaceContext(),
+        'getDirectories',
+      ).mockReturnValue([testRootDir, secondRootDir]);
+
+      const query = '@second-file.txt';
+
+      const result = await handleAtCommand({
+        query,
+        config: mockConfig,
+        addItem: mockAddItem,
+        onDebugMessage: mockOnDebugMessage,
+        messageId: 700,
+        signal: abortController.signal,
+      });
+
+      expect(result.processedQuery).toContainEqual(
+        expect.objectContaining({ text: fileContent }),
+      );
+      expect(mockOnDebugMessage).toHaveBeenCalledWith(
+        expect.stringContaining(`resolved to file: ${filePath}`),
+      );
+    } finally {
+      await fsPromises.rm(secondRootDir, { recursive: true, force: true });
+    }
+  });
+
+  it('should attempt glob fallback if direct resolution is unauthorized', async () => {
+    const fileContent = 'Globbed content';
+    const filePath = await createTestFile(
+      path.join(testRootDir, 'secret', 'file.txt'),
+      fileContent,
+    );
+
+    // Mock validatePathAccess to deny direct access but allow it via glob (just for test purposes)
+    vi.spyOn(mockConfig, 'validatePathAccess').mockImplementation((p) => {
+      if (p.includes('secret') && !p.includes('file.txt'))
+        return 'Unauthorized';
+      // Let's say the direct path 'secret/file.txt' is unauthorized
+      if (p === filePath) return 'Access Denied';
+      return null;
     });
 
-    const query = `@${agentName} @${otherAgent}`;
+    const query = '@secret/file.txt';
+
+    await handleAtCommand({
+      query,
+      config: mockConfig,
+      addItem: mockAddItem,
+      onDebugMessage: mockOnDebugMessage,
+      messageId: 701,
+      signal: abortController.signal,
+    });
+
+    // In this case, resolveAtCommandPath returns status: 'unauthorized'.
+    // resolveFilePaths should then try glob fallback.
+    expect(mockOnDebugMessage).toHaveBeenCalledWith(
+      expect.stringContaining('not found directly, attempting glob search.'),
+    );
+  });
+
+  it('should skip malformed paths (the original crash scenario)', async () => {
+    // We use a quoted path so the parser treats the whole thing as one @path token
+    const malformedPath =
+      '"FAIL tests/int/my.test.ts ... AssertionError: expected true to be false"';
+    const query = `@${malformedPath}`;
 
     const result = await handleAtCommand({
       query,
       config: mockConfig,
       addItem: mockAddItem,
       onDebugMessage: mockOnDebugMessage,
-      messageId: 600,
+      messageId: 702,
       signal: abortController.signal,
     });
 
-    const expectedNudge = `\n<system_note>\nThe user has explicitly selected the following agent(s): ${agentName}, ${otherAgent}. Please use the following tool(s) to delegate the task: '${agentName}', '${otherAgent}'.\n</system_note>\n`;
+    // Malformed path should be skipped and original query part preserved as text
+    expect(result.processedQuery).toEqual([{ text: query }]);
+    expect(mockOnDebugMessage).toHaveBeenCalledWith(
+      expect.stringContaining(
+        'Identified invalid path fragment, attempting to extract path',
+      ),
+    );
+  });
 
+  it('should recover a buried path from a malformed fragment during handleAtCommand', async () => {
+    const buriedFile = 'src/recovered.ts';
+    await createTestFile(
+      path.join(testRootDir, buriedFile),
+      'Recovered content',
+    );
+    const malformedFragment = `"FAIL ${buriedFile}:10:5 (AssertionError)"`;
+    const query = `@${malformedFragment}`;
+
+    const result = await handleAtCommand({
+      query,
+      config: mockConfig,
+      addItem: mockAddItem,
+      onDebugMessage: mockOnDebugMessage,
+      messageId: 703,
+      signal: abortController.signal,
+    });
+
+    // It should extract src/recovered.ts and attach its content
     expect(result.processedQuery).toContainEqual(
-      expect.objectContaining({ text: expectedNudge }),
+      expect.objectContaining({ text: 'Recovered content' }),
+    );
+    expect(mockOnDebugMessage).toHaveBeenCalledWith(
+      expect.stringContaining(
+        'Identified invalid path fragment, attempting to extract path',
+      ),
     );
   });
 });
@@ -1540,3 +1641,57 @@ describe('unescapeLiteralAt', () => {
     expect(unescapeLiteralAt(escapeAtSymbols(input))).toBe(input);
   });
 });
+
+describe('checkPermissions', () => {
+  let testRootDir: string;
+  let mockConfig: Config;
+
+  beforeEach(async () => {
+    vi.restoreAllMocks();
+    testRootDir = await fsPromises.mkdtemp(
+      path.join(os.tmpdir(), 'check-permissions-test-'),
+    );
+
+    mockConfig = {
+      getTargetDir: () => testRootDir,
+      getAgentRegistry: () => ({
+        getDefinition: () => undefined,
+      }),
+      getResourceRegistry: () => ({
+        findResourceByUri: () => undefined,
+        getAllResources: () => [],
+      }),
+      validatePathAccess: () => null,
+    } as unknown as Config;
+  });
+
+  afterEach(async () => {
+    await fsPromises.rm(testRootDir, { recursive: true, force: true });
+  });
+
+  // Regression for #22029 (and related #25910 / #25923): when a user pastes
+  // a JSON-like blob after an @, the @-command regex greedily captures it.
+  // The resolved string is longer than NAME_MAX, so fs.realpathSync throws
+  // ENAMETOOLONG. Previously this bubbled up as an unhandled rejection and
+  // crashed the CLI.
+  it('skips @-mentions whose path is too long to be a real filesystem entry', async () => {
+    const longSegment = 'a'.repeat(8192);
+    const query = `@${longSegment}`;
+    await expect(checkPermissions(query, mockConfig)).resolves.toEqual([]);
+  });
+
+  it('still surfaces real @-mentioned files when a sibling @-mention is unresolvable', async () => {
+    // A real file alongside a giant pasted-blob mention: the bogus mention
+    // should be skipped, the real one should still appear in the result.
+    const realFile = path.join(testRootDir, 'real.txt');
+    await fsPromises.writeFile(realFile, 'hello');
+    const resolvedRealFile = fs.realpathSync(realFile);
+    mockConfig.validatePathAccess = () =>
+      'permission required' as unknown as null;
+    const longSegment = 'b'.repeat(8192);
+    const query = `@real.txt and @${longSegment}`;
+    await expect(checkPermissions(query, mockConfig)).resolves.toEqual([
+      resolvedRealFile,
+    ]);
+  });
+});

packages/cli/src/ui/hooks/atCommandProcessor.ts

@@ -4,14 +4,12 @@
  * SPDX-License-Identifier: Apache-2.0
  */
 
-import * as fs from 'node:fs/promises';
 import * as path from 'node:path';
 import type { PartListUnion, PartUnion } from '@google/genai';
 import type { AnyToolInvocation, Config } from '@google/gemini-cli-core';
 import {
   debugLogger,
   getErrorMessage,
-  isNodeError,
   unescapePath,
   resolveToRealPath,
   fileExists,
@@ -19,6 +17,7 @@ import {
   REFERENCE_CONTENT_START,
   REFERENCE_CONTENT_END,
   CoreToolCallStatus,
+  resolveAtCommandPath,
 } from '@google/gemini-cli-core';
 import { Buffer } from 'node:buffer';
 import type {
@@ -188,9 +187,15 @@ export async function checkPermissions(
     const pathName = part.content.substring(1);
     if (!pathName) continue;
 
-    const resolvedPathName = resolveToRealPath(
-      path.resolve(config.getTargetDir(), pathName),
-    );
+    let resolvedPathName: string;
+    try {
+      resolvedPathName = resolveToRealPath(
+        path.resolve(config.getTargetDir(), pathName),
+      );
+    } catch {
+      // skip if resolveToRealPath errors out
+      continue;
+    }
 
     if (config.validatePathAccess(resolvedPathName, 'read')) {
       if (await fileExists(resolvedPathName)) {
@@ -265,102 +270,100 @@ async function resolveFilePaths(
       continue;
     }
 
-    for (const dir of config.getWorkspaceContext().getDirectories()) {
-      try {
-        const absolutePath = path.resolve(dir, pathName);
-        const stats = await fs.stat(absolutePath);
+    const result = await resolveAtCommandPath(pathName, config, onDebugMessage);
 
-        const relativePath = path.isAbsolute(pathName)
-          ? path.relative(dir, absolutePath)
-          : pathName;
+    if (result.status === 'resolved') {
+      const { absolutePath, relativePath, stats } = result.resolved;
+      if (stats.isDirectory()) {
+        const pathSpec = path.join(relativePath, '**');
+        resolvedFiles.push({
+          part,
+          pathSpec,
+          displayLabel: path.isAbsolute(pathName) ? relativePath : pathName,
+          absolutePath,
+        });
+        onDebugMessage(
+          `Path ${pathName} resolved to directory, using glob: ${pathSpec}`,
+        );
+      } else {
+        resolvedFiles.push({
+          part,
+          pathSpec: relativePath,
+          displayLabel: path.isAbsolute(pathName) ? relativePath : pathName,
+          absolutePath,
+        });
+        onDebugMessage(
+          `Path ${pathName} resolved to file: ${absolutePath}, using relative path: ${relativePath}`,
+        );
+      }
+    } else if (
+      result.status === 'not_found' ||
+      result.status === 'unauthorized'
+    ) {
+      // If direct resolution fails, we attempt glob search if enabled.
+      // We also allow glob fallback for "unauthorized" results from resolveAtCommandPath,
+      // as they might represent a relative path that matched an unauthorized file in one directory
+      // but might have a valid match (via glob) in another.
+      if (config.getEnableRecursiveFileSearch() && globTool) {
+        onDebugMessage(
+          `Path ${pathName} not found directly, attempting glob search.`,
+        );
 
-        if (stats.isDirectory()) {
-          const pathSpec = path.join(relativePath, '**');
-          resolvedFiles.push({
-            part,
-            pathSpec,
-            displayLabel: path.isAbsolute(pathName) ? relativePath : pathName,
-            absolutePath,
-          });
-          onDebugMessage(
-            `Path ${pathName} resolved to directory, using glob: ${pathSpec}`,
-          );
-        } else {
-          resolvedFiles.push({
-            part,
-            pathSpec: relativePath,
-            displayLabel: path.isAbsolute(pathName) ? relativePath : pathName,
-            absolutePath,
-          });
-          onDebugMessage(
-            `Path ${pathName} resolved to file: ${absolutePath}, using relative path: ${relativePath}`,
-          );
-        }
-        break;
-      } catch (error) {
-        if (isNodeError(error) && error.code === 'ENOENT') {
-          if (config.getEnableRecursiveFileSearch() && globTool) {
-            onDebugMessage(
-              `Path ${pathName} not found directly, attempting glob search.`,
+        for (const dir of config.getWorkspaceContext().getDirectories()) {
+          try {
+            const globResult = await globTool.buildAndExecute(
+              {
+                pattern: `**/*${pathName}*`,
+                path: dir,
+              },
+              signal,
             );
-            try {
-              const globResult = await globTool.buildAndExecute(
-                {
-                  pattern: `**/*${pathName}*`,
-                  path: dir,
-                },
-                signal,
-              );
-              if (
-                globResult.llmContent &&
-                typeof globResult.llmContent === 'string' &&
-                !globResult.llmContent.startsWith('No files found') &&
-                !globResult.llmContent.startsWith('Error:')
-              ) {
-                const lines = globResult.llmContent.split('\n');
-                if (lines.length > 1 && lines[1]) {
-                  const firstMatchAbsolute = lines[1].trim();
-                  const pathSpec = path.relative(dir, firstMatchAbsolute);
-                  resolvedFiles.push({
-                    part,
-                    pathSpec,
-                    displayLabel: path.isAbsolute(pathName)
-                      ? pathSpec
-                      : pathName,
-                  });
-                  onDebugMessage(
-                    `Glob search for ${pathName} found ${firstMatchAbsolute}, using relative path: ${pathSpec}`,
-                  );
-                  break;
-                } else {
-                  onDebugMessage(
-                    `Glob search for '**/*${pathName}*' did not return a usable path. Path ${pathName} will be skipped.`,
-                  );
+            if (
+              globResult.llmContent &&
+              typeof globResult.llmContent === 'string' &&
+              !globResult.llmContent.startsWith('No files found') &&
+              !globResult.llmContent.startsWith('Error:')
+            ) {
+              const lines = globResult.llmContent.split('\n');
+              if (lines.length > 1 && lines[1]) {
+                const rawMatch = lines[1].trim();
+                let firstMatchAbsolute: string;
+                try {
+                  firstMatchAbsolute = resolveToRealPath(rawMatch);
+                } catch {
+                  firstMatchAbsolute = rawMatch;
                 }
+                const pathSpec = path.relative(dir, firstMatchAbsolute);
+                resolvedFiles.push({
+                  part,
+                  pathSpec,
+                  displayLabel: path.isAbsolute(pathName) ? pathSpec : pathName,
+                  absolutePath: firstMatchAbsolute,
+                });
+                onDebugMessage(
+                  `Glob search for ${pathName} found ${firstMatchAbsolute}, using relative path: ${pathSpec}`,
+                );
+                break;
               } else {
                 onDebugMessage(
-                  `Glob search for '**/*${pathName}*' found no files or an error. Path ${pathName} will be skipped.`,
+                  `Glob search for '**/*${pathName}*' did not return a usable path. Path ${pathName} will be skipped.`,
                 );
               }
-            } catch (globError) {
-              debugLogger.warn(
-                `Error during glob search for ${pathName}: ${getErrorMessage(globError)}`,
-              );
+            } else {
               onDebugMessage(
-                `Error during glob search for ${pathName}. Path ${pathName} will be skipped.`,
+                `Glob search for '**/*${pathName}*' found no files or an error. Path ${pathName} will be skipped.`,
               );
             }
-          } else {
-            onDebugMessage(
-              `Glob tool not found. Path ${pathName} will be skipped.`,
+          } catch (globError) {
+            debugLogger.warn(
+              `Error during glob search for ${pathName}: ${getErrorMessage(globError)}`,
             );
           }
-        } else {
-          debugLogger.warn(
-            `Error stating path ${pathName}: ${getErrorMessage(error)}`,
-          );
+        }
+      } else {
+        if (!config.getEnableRecursiveFileSearch() || !globTool) {
           onDebugMessage(
-            `Error stating path ${pathName}. Path ${pathName} will be skipped.`,
+            `Glob tool not found. Path ${pathName} will be skipped.`,
           );
         }
       }
@@ -518,7 +521,14 @@ async function readLocalFiles(
     config.getMessageBus(),
   );
 
-  const pathSpecsToRead = resolvedFiles.map((rf) => rf.pathSpec);
+  const pathSpecsToRead = resolvedFiles.map((rf) => {
+    if (rf.absolutePath) {
+      return rf.pathSpec.endsWith('**')
+        ? path.join(rf.absolutePath, '**')
+        : rf.absolutePath;
+    }
+    return rf.pathSpec;
+  });
   const fileLabelsForDisplay = resolvedFiles.map((rf) => rf.displayLabel);
   const respectFileIgnore = config.getFileFilteringOptions();
 

packages/cli/src/ui/hooks/useGeminiStream.test.tsx

@@ -352,7 +352,6 @@ describe('useGeminiStream', () => {
     isInteractive: () => false,
     getExperiments: () => {},
     getMaxSessionTurns: vi.fn(() => 100),
-    isJitContextEnabled: vi.fn(() => false),
     getGlobalMemory: vi.fn(() => ''),
     getUserMemory: vi.fn(() => ''),
     getMessageBus: vi.fn(() => mockMessageBus),
@@ -1951,23 +1950,23 @@ describe('useGeminiStream', () => {
     it('should schedule a tool call when the command processor returns a schedule_tool action', async () => {
       const clientToolRequest: SlashCommandProcessorResult = {
         type: 'schedule_tool',
-        toolName: 'save_memory',
-        toolArgs: { fact: 'test fact' },
+        toolName: 'activate_skill',
+        toolArgs: { name: 'test-skill' },
       };
       mockHandleSlashCommand.mockResolvedValue(clientToolRequest);
 
       const { result } = await renderTestHook();
 
       await act(async () => {
-        await result.current.submitQuery('/memory add "test fact"');
+        await result.current.submitQuery('/memory show');
       });
 
       await waitFor(() => {
         expect(mockScheduleToolCalls).toHaveBeenCalledWith(
           [
             expect.objectContaining({
-              name: 'save_memory',
-              args: { fact: 'test fact' },
+              name: 'activate_skill',
+              args: { name: 'test-skill' },
               isClientInitiated: true,
             }),
           ],
@@ -2195,25 +2194,25 @@ describe('useGeminiStream', () => {
       });
     });
 
-    it('should NOT record other client-initiated tool calls (like save_memory) in history', async () => {
+    it('should NOT record other client-initiated tool calls in history', async () => {
       const { result, client: mockGeminiClient } = await renderTestHook();
 
       mockHandleSlashCommand.mockResolvedValue({
         type: 'schedule_tool',
-        toolName: 'save_memory',
-        toolArgs: { fact: 'test fact' },
+        toolName: 'write_todos',
+        toolArgs: { todos: [] },
       });
 
       await act(async () => {
-        await result.current.submitQuery('/memory add "test fact"');
+        await result.current.submitQuery('/todos');
       });
 
       // Simulate tool completion
       const completedTool = {
         request: {
           callId: 'test-call-id',
-          name: 'save_memory',
-          args: { fact: 'test fact' },
+          name: 'write_todos',
+          args: { todos: [] },
           isClientInitiated: true,
         },
         status: CoreToolCallStatus.Success,
@@ -2227,7 +2226,7 @@ describe('useGeminiStream', () => {
           responseParts: [
             {
               functionResponse: {
-                name: 'save_memory',
+                name: 'write_todos',
                 response: { success: true },
               },
             },
@@ -2246,91 +2245,6 @@ describe('useGeminiStream', () => {
     });
   });
 
-  describe('Memory Refresh on save_memory', () => {
-    it('should call performMemoryRefresh when a save_memory tool call completes successfully', async () => {
-      const mockPerformMemoryRefresh = vi.fn();
-      const completedToolCall: TrackedCompletedToolCall = {
-        request: {
-          callId: 'save-mem-call-1',
-          name: 'save_memory',
-          args: { fact: 'test' },
-          isClientInitiated: true,
-          prompt_id: 'prompt-id-6',
-        },
-        status: CoreToolCallStatus.Success,
-        responseSubmittedToGemini: false,
-        response: {
-          callId: 'save-mem-call-1',
-          responseParts: [{ text: 'Memory saved' }],
-          resultDisplay: 'Success: Memory saved',
-          error: undefined,
-          errorType: undefined, // FIX: Added missing property
-        },
-        tool: {
-          name: 'save_memory',
-          displayName: 'save_memory',
-          description: 'Saves memory',
-          build: vi.fn(),
-        } as unknown as AnyDeclarativeTool,
-        invocation: {
-          getDescription: () => `Mock description`,
-        } as unknown as AnyToolInvocation,
-      };
-
-      // Capture the onComplete callback
-      let capturedOnComplete:
-        | ((completedTools: TrackedToolCall[]) => Promise<void>)
-        | null = null;
-
-      mockUseToolScheduler.mockImplementation((onComplete) => {
-        capturedOnComplete = onComplete;
-        return [
-          [],
-          mockScheduleToolCalls,
-          mockMarkToolsAsSubmitted,
-          vi.fn(),
-          mockCancelAllToolCalls,
-          0,
-        ];
-      });
-
-      await renderHookWithProviders(() =>
-        useGeminiStream(
-          new MockedGeminiClientClass(mockConfig),
-          [],
-          mockAddItem,
-          mockConfig,
-          mockLoadedSettings,
-          mockOnDebugMessage,
-          mockHandleSlashCommand,
-          false,
-          () => 'vscode' as EditorType,
-          () => {},
-          mockPerformMemoryRefresh,
-          false,
-          () => {},
-          () => {},
-          () => {},
-          80,
-          24,
-        ),
-      );
-
-      // Trigger the onComplete callback with the completed save_memory tool
-      await act(async () => {
-        if (capturedOnComplete) {
-          // Wait a tick for refs to be set up
-          await new Promise((resolve) => setTimeout(resolve, 0));
-          await capturedOnComplete([completedToolCall]);
-        }
-      });
-
-      await waitFor(() => {
-        expect(mockPerformMemoryRefresh).toHaveBeenCalledTimes(1);
-      });
-    });
-  });
-
   describe('Error Handling', () => {
     it('should call parseAndFormatApiError with the correct authType on stream initialization failure', async () => {
       // 1. Setup

packages/cli/src/ui/hooks/useGeminiStream.ts

@@ -226,7 +226,7 @@ export const useGeminiStream = (
   shellModeActive: boolean,
   getPreferredEditor: () => EditorType | undefined,
   onAuthError: (error: string) => void,
-  performMemoryRefresh: () => Promise<void>,
+  _performMemoryRefresh: () => Promise<void>,
   modelSwitchedFromQuotaError: boolean,
   setModelSwitchedFromQuotaError: React.Dispatch<React.SetStateAction<boolean>>,
   onCancelSubmit: (
@@ -266,7 +266,6 @@ export const useGeminiStream = (
     useStateAndRef<Set<string>>(new Set());
   const [_isFirstToolInGroup, isFirstToolInGroupRef, setIsFirstToolInGroup] =
     useStateAndRef<boolean>(true);
-  const processedMemoryToolsRef = useRef<Set<string>>(new Set());
   const { startNewPrompt, getPromptCount } = useSessionStats();
   const logger = useLogger(config);
   const gitService = useMemo(() => {
@@ -1897,8 +1896,8 @@ export const useGeminiStream = (
         if (geminiClient) {
           for (const tool of clientTools) {
             // Only manually record skill activations in the chat history.
-            // Other client-initiated tools (like save_memory) update the system
-            // prompt/context and don't strictly need to be in the history.
+            // Other client-initiated tools update context and don't strictly
+            // need to be in the history.
             if (tool.request.name !== ACTIVATE_SKILL_TOOL_NAME) {
               continue;
             }
@@ -1925,14 +1924,6 @@ export const useGeminiStream = (
         }
       }
 
-      // Identify new, successful save_memory calls that we haven't processed yet.
-      const newSuccessfulMemorySaves = completedAndReadyToSubmitTools.filter(
-        (t) =>
-          t.request.name === 'save_memory' &&
-          t.status === 'success' &&
-          !processedMemoryToolsRef.current.has(t.request.callId),
-      );
-
       for (const toolCall of completedAndReadyToSubmitTools) {
         const backgroundedTool = getBackgroundedToolInfo(toolCall);
         if (backgroundedTool) {
@@ -1944,15 +1935,6 @@ export const useGeminiStream = (
         }
       }
 
-      if (newSuccessfulMemorySaves.length > 0) {
-        // Perform the refresh only if there are new ones.
-        void performMemoryRefresh();
-        // Mark them as processed so we don't do this again on the next render.
-        newSuccessfulMemorySaves.forEach((t) =>
-          processedMemoryToolsRef.current.add(t.request.callId),
-        );
-      }
-
       const geminiTools = completedAndReadyToSubmitTools.filter(
         (t) => !t.request.isClientInitiated,
       );
@@ -2076,7 +2058,6 @@ export const useGeminiStream = (
       submitQuery,
       markToolsAsSubmitted,
       geminiClient,
-      performMemoryRefresh,
       modelSwitchedFromQuotaError,
       addItem,
       registerBackgroundTask,

packages/cli/src/ui/hooks/useIncludeDirsTrust.test.tsx

@@ -80,6 +80,8 @@ describe('useIncludeDirsTrust', () => {
       clearPendingIncludeDirectories: vi.fn(),
       getFolderTrust: vi.fn().mockReturnValue(true),
       getWorkspaceContext: () => mockWorkspaceContext,
+      shouldLoadMemoryFromIncludeDirectories: vi.fn().mockReturnValue(false),
+      getMemoryContextManager: vi.fn(),
       getGeminiClient: vi
         .fn()
         .mockReturnValue({ addDirectoryContext: vi.fn() }),

packages/cli/src/ui/hooks/useIncludeDirsTrust.tsx

@@ -8,10 +8,7 @@ import { useEffect } from 'react';
 import { type Config } from '@google/gemini-cli-core';
 import { loadTrustedFolders } from '../../config/trustedFolders.js';
 import { expandHomeDir, batchAddDirectories } from '../utils/directoryUtils.js';
-import {
-  debugLogger,
-  refreshServerHierarchicalMemory,
-} from '@google/gemini-cli-core';
+import { debugLogger } from '@google/gemini-cli-core';
 import { MultiFolderTrustDialog } from '../components/MultiFolderTrustDialog.js';
 import type { UseHistoryManagerReturn } from './useHistoryManager.js';
 import { MessageType, type HistoryItem } from '../types.js';
@@ -35,7 +32,7 @@ async function finishAddingDirectories(
 
   try {
     if (config.shouldLoadMemoryFromIncludeDirectories()) {
-      await refreshServerHierarchicalMemory(config);
+      await config.getMemoryContextManager()?.refresh();
     }
   } catch (error) {
     // eslint-disable-next-line @typescript-eslint/no-unsafe-type-assertion

packages/cli/src/ui/hooks/useSessionBrowser.test.ts

@@ -194,14 +194,16 @@ describe('convertSessionToHistoryFormats', () => {
 
     const clientHistory = convertSessionToClientHistory(messages);
     expect(clientHistory).toHaveLength(2);
-    expect(clientHistory[0]).toEqual({
-      role: 'user',
-      parts: [{ text: 'Hello' }],
-    });
-    expect(clientHistory[1]).toEqual({
-      role: 'model',
-      parts: [{ text: 'Hi there' }],
-    });
+    expect(clientHistory.map((h) => h.content)).toEqual([
+      {
+        role: 'user',
+        parts: [{ text: 'Hello' }],
+      },
+      {
+        role: 'model',
+        parts: [{ text: 'Hi there' }],
+      },
+    ]);
   });
 
   it('should convert thinking tokens (thoughts) to thinking history items', () => {
@@ -254,10 +256,12 @@ describe('convertSessionToHistoryFormats', () => {
 
     const clientHistory = convertSessionToClientHistory(messages);
     expect(clientHistory).toHaveLength(1);
-    expect(clientHistory[0]).toEqual({
-      role: 'user',
-      parts: [{ text: 'Expanded content' }],
-    });
+    expect(clientHistory.map((h) => h.content)).toEqual([
+      {
+        role: 'user',
+        parts: [{ text: 'Expanded content' }],
+      },
+    ]);
   });
 
   it('should filter out slash commands from client history but keep in UI', () => {
@@ -316,33 +320,35 @@ describe('convertSessionToHistoryFormats', () => {
 
     const clientHistory = convertSessionToClientHistory(messages);
     expect(clientHistory).toHaveLength(3); // User, Model (call), User (response)
-    expect(clientHistory[0]).toEqual({
-      role: 'user',
-      parts: [{ text: 'What time is it?' }],
-    });
-    expect(clientHistory[1]).toEqual({
-      role: 'model',
-      parts: [
-        {
-          functionCall: {
-            name: 'get_time',
-            args: {},
-            id: 'call_1',
+    expect(clientHistory.map((h) => h.content)).toEqual([
+      {
+        role: 'user',
+        parts: [{ text: 'What time is it?' }],
+      },
+      {
+        role: 'model',
+        parts: [
+          {
+            functionCall: {
+              name: 'get_time',
+              args: {},
+              id: 'call_1',
+            },
           },
-        },
-      ],
-    });
-    expect(clientHistory[2]).toEqual({
-      role: 'user',
-      parts: [
-        {
-          functionResponse: {
-            id: 'call_1',
-            name: 'get_time',
-            response: { output: '12:00' },
+        ],
+      },
+      {
+        role: 'user',
+        parts: [
+          {
+            functionResponse: {
+              name: 'get_time',
+              response: { output: '12:00' },
+              id: 'call_1',
+            },
           },
-        },
-      ],
-    });
+        ],
+      },
+    ]);
   });
 });

packages/cli/src/ui/hooks/useSessionBrowser.ts

@@ -12,22 +12,28 @@ import {
   convertSessionToClientHistory,
   uiTelemetryService,
   loadConversationRecord,
-  type Config,
-  type ResumedSessionData,
+} from '@google/gemini-cli-core';
+import type {
+  HistoryTurn,
+  Config,
+  ResumedSessionData,
 } from '@google/gemini-cli-core';
 import {
   convertSessionToHistoryFormats,
   type SessionInfo,
 } from '../../utils/sessionUtils.js';
-import type { Part } from '@google/genai';
 
 export { convertSessionToHistoryFormats };
 
+import type { Part } from '@google/genai';
+
 export const useSessionBrowser = (
   config: Config,
   onLoadHistory: (
     uiHistory: HistoryItemWithoutId[],
-    clientHistory: Array<{ role: 'user' | 'model'; parts: Part[] }>,
+    clientHistory: Array<
+      { role: 'user' | 'model'; parts: Part[] } | HistoryTurn
+    >,
     resumedSessionData: ResumedSessionData,
   ) => Promise<void>,
 ) => {

packages/cli/src/ui/hooks/useSessionResume.test.ts

@@ -13,6 +13,7 @@ import type {
   ResumedSessionData,
   ConversationRecord,
   MessageRecord,
+  HistoryTurn,
 } from '@google/gemini-cli-core';
 import type { UseHistoryManagerReturn } from './useHistoryManager.js';
 import type { HistoryItemWithoutId } from '../types.js';
@@ -527,10 +528,12 @@ describe('useSessionResume', () => {
 
       // Should only have the non-slash-command message
       expect(clientHistory).toHaveLength(1);
-      expect(clientHistory[0]).toEqual({
-        role: 'user',
-        parts: [{ text: 'Regular message' }],
-      });
+      expect(clientHistory.map((h: HistoryTurn) => h.content)).toEqual([
+        {
+          role: 'user',
+          parts: [{ text: 'Regular message' }],
+        },
+      ]);
 
       // But UI history should have both
       expect(mockHistoryManager.addItem).toHaveBeenCalledTimes(2);

packages/cli/src/ui/hooks/useSessionResume.ts

@@ -7,14 +7,17 @@
 import { useCallback, useEffect, useRef, useState } from 'react';
 import {
   coreEvents,
-  type Config,
-  type ResumedSessionData,
   convertSessionToClientHistory,
 } from '@google/gemini-cli-core';
-import type { Part } from '@google/genai';
+import type {
+  HistoryTurn,
+  Config,
+  ResumedSessionData,
+} from '@google/gemini-cli-core';
 import type { HistoryItemWithoutId } from '../types.js';
 import type { UseHistoryManagerReturn } from './useHistoryManager.js';
 import { convertSessionToHistoryFormats } from './useSessionBrowser.js';
+import type { Part } from '@google/genai';
 
 interface UseSessionResumeParams {
   config: Config;
@@ -54,7 +57,9 @@ export function useSessionResume({
   const loadHistoryForResume = useCallback(
     async (
       uiHistory: HistoryItemWithoutId[],
-      clientHistory: Array<{ role: 'user' | 'model'; parts: Part[] }>,
+      clientHistory: Array<
+        { role: 'user' | 'model'; parts: Part[] } | HistoryTurn
+      >,
       resumedData: ResumedSessionData,
     ) => {
       // Wait for the client.

packages/cli/src/ui/hooks/useSuspend.test.ts

@@ -83,8 +83,6 @@ describe('useSuspend', () => {
   it('cleans terminal state on suspend and restores/repaints on resume in alternate screen mode', async () => {
     const handleWarning = vi.fn();
     const setRawMode = vi.fn();
-    const refreshStatic = vi.fn();
-    const setForceRerenderKey = vi.fn();
     const enableSupportedModes =
       terminalCapabilityManager.enableSupportedModes as unknown as Mock;
 
@@ -92,8 +90,6 @@ describe('useSuspend', () => {
       useSuspend({
         handleWarning,
         setRawMode,
-        refreshStatic,
-        setForceRerenderKey,
         shouldUseAlternateScreen: true,
       }),
     );
@@ -131,8 +127,6 @@ describe('useSuspend', () => {
     expect(enableSupportedModes).toHaveBeenCalledTimes(1);
     expect(enableMouseEvents).toHaveBeenCalledTimes(1);
     expect(setRawMode).toHaveBeenCalledWith(true);
-    expect(refreshStatic).toHaveBeenCalledTimes(1);
-    expect(setForceRerenderKey).toHaveBeenCalledTimes(1);
 
     unmount();
   });
@@ -140,15 +134,11 @@ describe('useSuspend', () => {
   it('does not toggle alternate screen or mouse restore when alternate screen mode is disabled', async () => {
     const handleWarning = vi.fn();
     const setRawMode = vi.fn();
-    const refreshStatic = vi.fn();
-    const setForceRerenderKey = vi.fn();
 
     const { result, unmount } = await renderHook(() =>
       useSuspend({
         handleWarning,
         setRawMode,
-        refreshStatic,
-        setForceRerenderKey,
         shouldUseAlternateScreen: false,
       }),
     );
@@ -174,15 +164,11 @@ describe('useSuspend', () => {
 
     const handleWarning = vi.fn();
     const setRawMode = vi.fn();
-    const refreshStatic = vi.fn();
-    const setForceRerenderKey = vi.fn();
 
     const { result, unmount } = await renderHook(() =>
       useSuspend({
         handleWarning,
         setRawMode,
-        refreshStatic,
-        setForceRerenderKey,
         shouldUseAlternateScreen: true,
       }),
     );

packages/cli/src/ui/hooks/useSuspend.ts

@@ -26,16 +26,12 @@ import { Command } from '../key/keyBindings.js';
 interface UseSuspendProps {
   handleWarning: (message: string) => void;
   setRawMode: (mode: boolean) => void;
-  refreshStatic: () => void;
-  setForceRerenderKey: (updater: (prev: number) => number) => void;
   shouldUseAlternateScreen: boolean;
 }
 
 export function useSuspend({
   handleWarning,
   setRawMode,
-  refreshStatic,
-  setForceRerenderKey,
   shouldUseAlternateScreen,
 }: UseSuspendProps) {
   const [ctrlZPressCount, setCtrlZPressCount] = useState(0);
@@ -108,16 +104,8 @@ export function useSuspend({
             enableMouseEvents();
           }
 
-          // Force Ink to do a complete repaint by:
-          // 1. Emitting a resize event (tricks Ink into full redraw)
-          // 2. Remounting components via state changes
+          // Force Ink to do a complete repaint without remounting the app.
           process.stdout.emit('resize');
-
-          // Give a tick for resize to process, then trigger remount
-          setImmediate(() => {
-            refreshStatic();
-            setForceRerenderKey((prev) => prev + 1);
-          });
         } finally {
           if (onResumeHandlerRef.current === onResume) {
             onResumeHandlerRef.current = null;
@@ -142,14 +130,7 @@ export function useSuspend({
         ctrlZTimerRef.current = null;
       }, WARNING_PROMPT_DURATION_MS);
     }
-  }, [
-    ctrlZPressCount,
-    handleWarning,
-    setRawMode,
-    refreshStatic,
-    setForceRerenderKey,
-    shouldUseAlternateScreen,
-  ]);
+  }, [ctrlZPressCount, handleWarning, setRawMode, shouldUseAlternateScreen]);
 
   const handleSuspend = useCallback(() => {
     setCtrlZPressCount((prev) => prev + 1);

packages/cli/src/ui/hooks/vim.test.tsx

@@ -2258,6 +2258,80 @@ describe('useVim hook', async () => {
     });
   });
 
+  describe('should handle unmapped keys in Normal mode', () => {
+    type UnmappedKeyCase = {
+      char: string;
+      insertable: boolean;
+    };
+    it.each<UnmappedKeyCase>([
+      { char: 'm', insertable: true },
+      { char: 'n', insertable: true },
+      { char: 'p', insertable: true },
+      { char: 'q', insertable: true },
+      { char: 's', insertable: true },
+      { char: 'v', insertable: true },
+      { char: 'y', insertable: true },
+      { char: 'z', insertable: true },
+      { char: 'H', insertable: true },
+      { char: 'J', insertable: true },
+      { char: 'K', insertable: true },
+      { char: 'L', insertable: true },
+      { char: 'M', insertable: true },
+      { char: 'N', insertable: true },
+      { char: 'P', insertable: true },
+      { char: 'Q', insertable: true },
+      { char: 'R', insertable: true },
+      { char: 'S', insertable: true },
+      { char: 'U', insertable: true },
+      { char: 'V', insertable: true },
+      { char: 'Y', insertable: true },
+      { char: 'Z', insertable: true },
+      { char: '/', insertable: true },
+      { char: '#', insertable: true },
+      { char: '%', insertable: true },
+      { char: '&', insertable: true },
+      { char: "'", insertable: true },
+      { char: '(', insertable: true },
+      { char: ')', insertable: true },
+      { char: '*', insertable: true },
+      { char: '+', insertable: true },
+      { char: '-', insertable: true },
+      { char: '/', insertable: true },
+      { char: ':', insertable: true },
+      { char: '<', insertable: true },
+      { char: '=', insertable: true },
+      { char: '>', insertable: true },
+      { char: '@', insertable: true },
+      { char: '[', insertable: true },
+      { char: '\\', insertable: true },
+      { char: ']', insertable: true },
+      { char: '_', insertable: true },
+      { char: '`', insertable: true },
+      { char: '{', insertable: true },
+      { char: '|', insertable: true },
+      { char: '}', insertable: true },
+    ])(
+      '$char: should be swallowed and do nothing in Normal mode',
+      async ({ char, insertable }) => {
+        const { result } = await renderVimHook();
+        exitInsertMode(result);
+
+        let handled = false;
+        act(() => {
+          handled = result.current.handleInput(
+            createKey({ sequence: char, name: char, insertable }),
+          );
+        });
+
+        expect(handled).toBe(true);
+        expect(mockVimContext.setVimMode).not.toHaveBeenCalledWith('INSERT');
+
+        expect(mockBuffer.vimFindCharForward).not.toHaveBeenCalled();
+        expect(mockBuffer.vimFindCharBackward).not.toHaveBeenCalled();
+      },
+    );
+  });
+
   describe('Operator + find motions (df, dt, dF, dT, cf, ct, cF, cT)', async () => {
     it('df{char}: executes delete-to-char, not a dangling operator', async () => {
       const { result } = await renderVimHook();

packages/cli/src/ui/hooks/vim.ts

@@ -1486,6 +1486,11 @@ export function useVim(buffer: TextBuffer, onSubmit?: (value: string) => void) {
             // Unknown command, clear count and pending states
             dispatch({ type: 'CLEAR_PENDING_STATES' });
 
+            // Ignore any Insertable key in Normal Mode
+            if (normalizedKey.insertable) {
+              return true;
+            }
+
             // Not handled by vim so allow other handlers to process it.
             return false;
           }