test(cli): fix simulator fake timer leak and align with 10-stall limit

- Add session_notes field to simulator JSON response schema.

- Capture and persist factual session notes in sessionMemory.

- Inject episodic memory into system prompt for off-screen context.

- Add background LLM process to compress memory when it exceeds 5 items.

- Add unit tests for note capture, prompt injection, and compression merge.

.gemini/settings.json

@@ -3,9 +3,11 @@
     "extensionReloading": true,
     "modelSteering": true,
     "autoMemory": true,
-    "memoryManager": true,
     "topicUpdateNarration": true,
-    "voiceMode": true
+    "voiceMode": true,
+    "adk": {
+      "agentSessionNoninteractiveEnabled": true
+    }
   },
   "general": {
     "devtools": true

.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/actions/publish-release/action.yml

@@ -114,13 +114,14 @@ runs:
         BRANCH_NAME: '${{ steps.release_branch.outputs.BRANCH_NAME }}'
         DRY_RUN: '${{ inputs.dry-run }}'
         RELEASE_TAG: '${{ inputs.release-tag }}'
+        GIT_PUSH_TOKEN: '${{ inputs.github-release-token || inputs.github-token }}'
       run: |-
         set -e
         git add package.json package-lock.json packages/*/package.json
         git commit -m "chore(release): ${RELEASE_TAG}"
         if [[ "${DRY_RUN}" == "false" ]]; then
           echo "Pushing release branch to remote..."
-          git push --set-upstream origin "${BRANCH_NAME}" --follow-tags
+          git push "https://x-access-token:${GIT_PUSH_TOKEN}@github.com/${{ github.repository }}.git" "HEAD:${BRANCH_NAME}" --follow-tags
         else
           echo "Dry run enabled. Skipping push."
         fi
@@ -174,9 +175,9 @@ runs:
         npm publish \
           --dry-run="${INPUTS_DRY_RUN}" \
           --workspace="${INPUTS_CORE_PACKAGE_NAME}" \
-          --no-tag
+          --tag staging-tmp
         if [[ "${INPUTS_DRY_RUN}" == "false" ]]; then
-          npm dist-tag rm ${INPUTS_CORE_PACKAGE_NAME} false
+          npm dist-tag rm ${INPUTS_CORE_PACKAGE_NAME} staging-tmp
         fi
 
     - name: '🔗 Install latest core package'
@@ -222,9 +223,9 @@ runs:
         npm publish \
           --dry-run="${INPUTS_DRY_RUN}" \
           --workspace="${INPUTS_CLI_PACKAGE_NAME}" \
-          --no-tag
+          --tag staging-tmp
         if [[ "${INPUTS_DRY_RUN}" == "false" ]]; then
-          npm dist-tag rm ${INPUTS_CLI_PACKAGE_NAME} false
+          npm dist-tag rm ${INPUTS_CLI_PACKAGE_NAME} staging-tmp
         fi
 
     - name: 'Get a2a-server Token'
@@ -249,9 +250,9 @@ runs:
         npm publish \
           --dry-run="${INPUTS_DRY_RUN}" \
           --workspace="${INPUTS_A2A_PACKAGE_NAME}" \
-          --no-tag
+          --tag staging-tmp
           if [[ "${INPUTS_DRY_RUN}" == "false" ]]; then
-            npm dist-tag rm ${INPUTS_A2A_PACKAGE_NAME} false
+            npm dist-tag rm ${INPUTS_A2A_PACKAGE_NAME} staging-tmp
           fi
 
     - name: '🔬 Verify NPM release by version'
@@ -336,7 +337,8 @@ runs:
       shell: 'bash'
       run: |
         echo "Cleaning up release branch ${STEPS_RELEASE_BRANCH_OUTPUTS_BRANCH_NAME}..."
-        git push origin --delete "${STEPS_RELEASE_BRANCH_OUTPUTS_BRANCH_NAME}"
+        git push "https://x-access-token:${GIT_PUSH_TOKEN}@github.com/${{ github.repository }}.git" --delete "${STEPS_RELEASE_BRANCH_OUTPUTS_BRANCH_NAME}"
 
       env:
+        GIT_PUSH_TOKEN: '${{ inputs.github-release-token || inputs.github-token }}'
         STEPS_RELEASE_BRANCH_OUTPUTS_BRANCH_NAME: '${{ steps.release_branch.outputs.BRANCH_NAME }}'

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

@@ -5,94 +5,218 @@
  */
 
 module.exports = async ({ github, context, core }) => {
-  const rawLabels = process.env.LABELS_OUTPUT;
-  core.info(`Raw labels JSON: ${rawLabels}`);
-  let parsedLabels;
-  try {
-    // First, try to parse the raw output as JSON.
-    parsedLabels = JSON.parse(rawLabels);
-  } catch (jsonError) {
-    // If that fails, check for a markdown code block.
-    core.warning(
-      `Direct JSON parsing failed: ${jsonError.message}. Trying to extract from a markdown block.`,
-    );
-    const jsonMatch = rawLabels.match(/```json\s*([\s\S]*?)\s*```/);
-    if (jsonMatch && jsonMatch[1]) {
-      try {
-        parsedLabels = JSON.parse(jsonMatch[1].trim());
-      } catch (markdownError) {
-        core.setFailed(
-          `Failed to parse JSON even after extracting from markdown block: ${markdownError.message}\nRaw output: ${rawLabels}`,
-        );
-        return;
+  const extractJson = (raw) => {
+    if (!raw || raw === '[]' || raw === '') return [];
+    try {
+      // First, try to parse the raw output as JSON.
+      return JSON.parse(raw);
+    } catch {
+      // If that fails, check for a markdown code 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}`,
+          );
+        }
       }
-    } else {
-      // If no markdown block, try to find a raw JSON array in the output.
-      // The CLI may include debug/log lines (e.g. telemetry init, YOLO mode)
-      // before the actual JSON response.
-      const jsonArrayMatch = rawLabels.match(
+
+      // Try to find a raw JSON array in the output.
+      const jsonArrayMatch = raw.match(
         /\[\s*\{\s*"issue_number"[\s\S]*\}\s*\]/,
       );
       if (jsonArrayMatch) {
         try {
-          parsedLabels = JSON.parse(jsonArrayMatch[0]);
-        } catch (extractError) {
-          // It's possible the regex matched from a `[STARTUP]` log all the way to the end
-          // of the JSON array. We need to be more aggressive and find the FIRST `[ { "issue_number"`
-          core.warning(
-            `Strict array match failed: ${extractError.message}. Attempting to clean leading noisy brackets.`,
-          );
-          const fallbackMatch = rawLabels.match(
-            /(\[\s*\{\s*"issue_number"[\s\S]*)/,
-          );
+          return JSON.parse(jsonArrayMatch[0]);
+        } catch {
+          const fallbackMatch = raw.match(/(\[\s*\{\s*"issue_number"[\s\S]*)/);
           if (fallbackMatch) {
             try {
-              // We might have grabbed trailing noise too, so we find the last closing bracket
               const cleaned = fallbackMatch[0].substring(
                 0,
                 fallbackMatch[0].lastIndexOf(']') + 1,
               );
-              parsedLabels = JSON.parse(cleaned);
+              return JSON.parse(cleaned);
             } catch (fallbackError) {
-              core.setFailed(
-                `Found JSON-like content but failed to parse: ${fallbackError.message}\nRaw output: ${rawLabels}`,
+              core.warning(
+                `Failed to parse extracted JSON using fallback regex: ${fallbackError.message}`,
               );
-              return;
             }
-          } else {
-            core.setFailed(
-              `Found JSON-like content but failed to parse: ${extractError.message}\nRaw output: ${rawLabels}`,
-            );
-            return;
           }
         }
-      } else {
-        core.setFailed(
-          `Output is not valid JSON and does not contain extractable JSON.\nRaw output: ${rawLabels}`,
-        );
-        return;
       }
     }
-  }
-  core.info(`Parsed labels JSON: ${JSON.stringify(parsedLabels)}`);
+    core.warning('No valid JSON could be extracted from input.');
+    return [];
+  };
 
-  for (const entry of parsedLabels) {
+  // Collect all outputs from environment variables
+  // Prioritize EFFORT results over STANDARD results by processing Effort FIRST
+  // so that its labels appear first in the merged arrays (and thus win in mutually exclusive logic)
+  const effortRaw = process.env.LABELS_OUTPUT_EFFORT;
+  const standardRaw = process.env.LABELS_OUTPUT_STANDARD;
+  const genericRaw = process.env.LABELS_OUTPUT;
+
+  const resultsByIssue = new Map();
+
+  const processResults = (results, _sourceName) => {
+    for (const entry of results) {
+      const issueNumber = entry.issue_number;
+      if (!issueNumber) continue;
+
+      if (!resultsByIssue.has(issueNumber)) {
+        resultsByIssue.set(issueNumber, {
+          issue_number: issueNumber,
+          labels_to_add: [...(entry.labels_to_add || [])],
+          labels_to_remove: [...(entry.labels_to_remove || [])],
+          explanation: entry.explanation || '',
+          effort_analysis: entry.effort_analysis || '',
+        });
+      } 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 || []),
+          ]),
+        ];
+
+        // Combine explanations (if different)
+        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;
+        }
+      }
+    }
+  };
+
+  // Order matters: Effort first so its labels win in conflict resolution
+  processResults(extractJson(effortRaw), 'EFFORT');
+  processResults(extractJson(standardRaw), 'STANDARD');
+  processResults(extractJson(genericRaw), 'GENERIC');
+
+  const finalResults = Array.from(resultsByIssue.values());
+  core.info(`Aggregated triage results for ${finalResults.length} issues.`);
+
+  for (const entry of finalResults) {
     const issueNumber = entry.issue_number;
-    if (!issueNumber) {
-      core.info(
-        `Skipping entry with no issue number: ${JSON.stringify(entry)}`,
+    let labelsToAdd = entry.labels_to_add || [];
+    let labelsToRemove = entry.labels_to_remove || [];
+    let existingLabels = [];
+
+    // Fetch existing labels early
+    try {
+      const { data: issueData } = await github.rest.issues.get({
+        owner: context.repo.owner,
+        repo: context.repo.repo,
+        issue_number: issueNumber,
+      });
+      existingLabels = issueData.labels.map((l) =>
+        typeof l === 'string' ? l : l.name,
+      );
+    } catch (e) {
+      core.warning(
+        `Failed to fetch existing labels for #${issueNumber}: ${e.message}`,
       );
-      continue;
     }
 
-    const labelsToAdd = entry.labels_to_add || [];
-    labelsToAdd.push('status/bot-triaged');
+    // Programmatic Priority Downgrade Logic
+    if (labelsToAdd.includes('status/need-information')) {
+      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 (downgradedPriority) {
+          core.info(
+            `Programmatically downgrading ${targetPriority} to ${downgradedPriority} due to status/need-information`,
+          );
+          labelsToAdd = labelsToAdd.filter((l) => l !== targetPriority);
+          labelsToAdd.push(downgradedPriority);
+        }
+      }
+    }
 
-    let labelsToRemove = entry.labels_to_remove || [];
     labelsToRemove.push('status/need-triage');
-    // Deduplicate array
-    labelsToRemove = [...new Set(labelsToRemove)];
 
+    if (
+      labelsToAdd.includes('status/manual-triage') ||
+      existingLabels.includes('status/manual-triage')
+    ) {
+      labelsToRemove.push('status/bot-triaged');
+      labelsToAdd = labelsToAdd.filter((l) => l !== 'status/bot-triaged');
+    } else {
+      labelsToAdd.push('status/bot-triaged');
+    }
+
+    // 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/')),
+      );
+    }
+    if (labelsToAdd.some((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/')),
+      );
+    }
+
+    // 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));
+      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,
+        );
+      }
+    }
+
+    // Final deduplication and cleanup
+    labelsToRemove = [...new Set(labelsToRemove)].filter(
+      (l) => !labelsToAdd.includes(l) && existingLabels.includes(l),
+    );
+    labelsToAdd = [...new Set(labelsToAdd)].filter(
+      (l) => !existingLabels.includes(l),
+    );
+
+    // Batch label operations
     if (labelsToAdd.length > 0) {
       await github.rest.issues.addLabels({
         owner: context.repo.owner,
@@ -100,10 +224,8 @@ module.exports = async ({ github, context, core }) => {
         issue_number: issueNumber,
         labels: labelsToAdd,
       });
-
-      const explanation = entry.explanation ? ` - ${entry.explanation}` : '';
       core.info(
-        `Successfully added labels for #${issueNumber}: ${labelsToAdd.join(', ')}${explanation}`,
+        `Successfully added labels for #${issueNumber}: ${labelsToAdd.join(', ')}`,
       );
     }
 
@@ -117,11 +239,10 @@ module.exports = async ({ github, context, core }) => {
             name: label,
           });
         } catch (e) {
-          if (e.status !== 404) {
+          if (e.status !== 404)
             core.warning(
               `Failed to remove label ${label} from #${issueNumber}: ${e.message}`,
             );
-          }
         }
       }
       core.info(
@@ -129,31 +250,29 @@ module.exports = async ({ github, context, core }) => {
       );
     }
 
-    if (entry.explanation || entry.effort_analysis) {
+    // Post comment if needed
+    const needsInfoAdded =
+      labelsToAdd.includes('status/need-information') &&
+      !existingLabels.includes('status/need-information');
+    const hasEffortAnalysis = !!entry.effort_analysis;
+
+    if (needsInfoAdded || hasEffortAnalysis) {
       let commentBody = '';
-      if (entry.explanation) {
-        commentBody += entry.explanation;
-      }
-      if (entry.effort_analysis) {
+      if (needsInfoAdded && entry.explanation) commentBody += entry.explanation;
+      if (hasEffortAnalysis) {
         if (commentBody) commentBody += '\n\n';
         commentBody += `**Effort Analysis:**\n${entry.effort_analysis}`;
       }
 
-      await github.rest.issues.createComment({
-        owner: context.repo.owner,
-        repo: context.repo.repo,
-        issue_number: issueNumber,
-        body: commentBody,
-      });
-    }
-
-    if (
-      (!entry.labels_to_add || entry.labels_to_add.length === 0) &&
-      (!entry.labels_to_remove || entry.labels_to_remove.length === 0)
-    ) {
-      core.info(
-        `No labels to add or remove for #${issueNumber}, leaving as is`,
-      );
+      if (commentBody) {
+        await github.rest.issues.createComment({
+          owner: context.repo.owner,
+          repo: context.repo.repo,
+          issue_number: issueNumber,
+          body: commentBody,
+        });
+        core.info(`Posted required comment for #${issueNumber}`);
+      }
     }
   }
 };

.github/scripts/cleanup-triage-labels.cjs

@@ -22,29 +22,53 @@ module.exports = async ({ github, context, core }) => {
 
   for (const issue of issuesToCleanup) {
     try {
-      await github.rest.issues.removeLabel({
+      const { data: issueData } = await github.rest.issues.get({
         owner: context.repo.owner,
         repo: context.repo.repo,
         issue_number: issue.number,
-        name: 'status/need-triage',
       });
-      core.info(
-        `Successfully removed status/need-triage from #${issue.number}`,
+
+      const labels = issueData.labels.map((l) =>
+        typeof l === 'string' ? l : l.name,
       );
-    } catch (error) {
-      if (error.status === 404) {
+
+      if (
+        labels.includes('status/bot-triaged') &&
+        labels.includes('status/need-triage')
+      ) {
+        await github.rest.issues.removeLabel({
+          owner: context.repo.owner,
+          repo: context.repo.repo,
+          issue_number: issue.number,
+          name: 'status/need-triage',
+        });
         core.info(
-          `Label status/need-triage not found on #${issue.number}, skipping.`,
-        );
-      } else {
-        core.warning(
-          `Failed to remove label from #${issue.number}: ${error.message}`,
+          `Successfully removed status/need-triage from #${issue.number}`,
         );
       }
+
+      if (
+        labels.includes('status/bot-triaged') &&
+        labels.includes('status/manual-triage')
+      ) {
+        await github.rest.issues.removeLabel({
+          owner: context.repo.owner,
+          repo: context.repo.repo,
+          issue_number: issue.number,
+          name: 'status/bot-triaged',
+        });
+        core.info(
+          `Successfully removed status/bot-triaged from #${issue.number} because it requires manual triage`,
+        );
+      }
+    } catch (error) {
+      core.warning(
+        `Failed to clean up labels for #${issue.number}: ${error.message}`,
+      );
     }
   }
 
   core.info(
-    `Cleaned up status/need-triage from ${issuesToCleanup.length} issues.`,
+    `Cleaned up conflicting labels from ${issuesToCleanup.length} issues.`,
   );
 };

.github/scripts/gemini-lifecycle-manager.cjs

@@ -16,6 +16,8 @@ module.exports = async ({ github, context, core }) => {
   const owner = context.repo.owner;
   const repo = context.repo.repo;
 
+  core.info(`Running in ${dryRun ? 'DRY RUN' : 'PRODUCTION'} mode.`);
+
   const STALE_LABEL = 'stale';
   const NEED_INFO_LABEL = 'status/need-information';
   const EXEMPT_LABELS = [
@@ -79,14 +81,16 @@ module.exports = async ({ github, context, core }) => {
   async function processItems(query, callback) {
     core.info(`Searching: ${query}`);
     try {
-      const response = await github.rest.search.issuesAndPullRequests({
-        q: query,
-        per_page: 100,
-        sort: 'updated',
-        order: 'asc',
-      });
-      const items = response.data.items;
-      core.info(`Found ${items.length} items (batch limited).`);
+      let items = await github.paginate(
+        github.rest.search.issuesAndPullRequests,
+        {
+          q: query,
+          per_page: 100,
+          sort: 'updated',
+          order: 'asc',
+        },
+      );
+      core.info(`Found ${items.length} items.`);
       for (const item of items) {
         try {
           await callback(item);
@@ -114,16 +118,21 @@ module.exports = async ({ github, context, core }) => {
         per_page: 5,
       });
 
-      // Check if the last comment is from a non-maintainer
+      // Check if the last comment is from a non-maintainer and not a bot
       const lastComment = comments[0];
       if (
         lastComment &&
+        lastComment.user?.type !== 'Bot' &&
         !(await isMaintainer(lastComment.user, lastComment.author_association))
       ) {
-        core.info(
-          `Removing ${NEED_INFO_LABEL} from #${item.number} due to contributor response.`,
-        );
-        if (!dryRun) {
+        if (dryRun) {
+          core.info(
+            `[DRY RUN] Would remove ${NEED_INFO_LABEL} from #${item.number} due to contributor response.`,
+          );
+        } else {
+          core.info(
+            `Removing ${NEED_INFO_LABEL} from #${item.number} due to contributor response.`,
+          );
           await github.rest.issues
             .removeLabel({
               owner,
@@ -141,10 +150,14 @@ module.exports = async ({ github, context, core }) => {
   await processItems(
     `repo:${owner}/${repo} is:open label:"${NEED_INFO_LABEL}" updated:<${noResponseThreshold.toISOString()}`,
     async (item) => {
-      core.info(
-        `Closing #${item.number} due to no response for ${NO_RESPONSE_DAYS} days.`,
-      );
-      if (!dryRun) {
+      if (dryRun) {
+        core.info(
+          `[DRY RUN] Would close #${item.number} due to no response for ${NO_RESPONSE_DAYS} days.`,
+        );
+      } else {
+        core.info(
+          `Closing #${item.number} due to no response for ${NO_RESPONSE_DAYS} days.`,
+        );
         await github.rest.issues.createComment({
           owner,
           repo,
@@ -156,6 +169,7 @@ module.exports = async ({ github, context, core }) => {
           repo,
           issue_number: item.number,
           state: 'closed',
+          state_reason: 'not_planned',
         });
       }
     },
@@ -163,11 +177,21 @@ module.exports = async ({ github, context, core }) => {
 
   // 2. Handle Stale Mark (60 days inactivity, no stale label)
   const exemptQuery = EXEMPT_LABELS.map((l) => `-label:"${l}"`).join(' ');
+
   await processItems(
     `repo:${owner}/${repo} is:open -label:"${STALE_LABEL}" ${exemptQuery} updated:<${staleThreshold.toISOString()}`,
     async (item) => {
-      core.info(`Marking #${item.number} as stale.`);
-      if (!dryRun) {
+      const isBug = item.labels.some((l) =>
+        (typeof l === 'string' ? l : l.name).toLowerCase().includes('bug'),
+      );
+      const bodyText = isBug
+        ? `This bug report has been automatically marked as stale due to ${STALE_DAYS} days of inactivity. Many issues are resolved in newer releases. Please verify if the issue persists in the latest Gemini CLI version. If it does, please leave a comment to keep this open. It will be closed in ${CLOSE_DAYS} days if no further activity occurs. Thank you!`
+        : `This item has been automatically marked as stale due to ${STALE_DAYS} days of inactivity. It will be closed in ${CLOSE_DAYS} days if no further activity occurs. Thank you!`;
+
+      if (dryRun) {
+        core.info(`[DRY RUN] Would mark #${item.number} as stale.`);
+      } else {
+        core.info(`Marking #${item.number} as stale.`);
         await github.rest.issues.addLabels({
           owner,
           repo,
@@ -178,18 +202,97 @@ module.exports = async ({ github, context, core }) => {
           owner,
           repo,
           issue_number: item.number,
-          body: `This item has been automatically marked as stale due to ${STALE_DAYS} days of inactivity. It will be closed in ${CLOSE_DAYS} days if no further activity occurs. Thank you!`,
+          body: bodyText,
         });
       }
     },
   );
 
-  // 3. Handle Stale Close (14 days with stale label)
+  // 3. Handle Stale Removal & Close
   await processItems(
-    `repo:${owner}/${repo} is:open label:"${STALE_LABEL}" ${exemptQuery} updated:<${closeThreshold.toISOString()}`,
+    `repo:${owner}/${repo} is:open label:"${STALE_LABEL}" ${exemptQuery}`,
     async (item) => {
-      core.info(`Closing stale item #${item.number}.`);
-      if (!dryRun) {
+      // Fetch full timeline to see events and comments
+      const timeline = await github.paginate(
+        github.rest.issues.listEventsForTimeline,
+        {
+          owner,
+          repo,
+          issue_number: item.number,
+          per_page: 100,
+        },
+      );
+
+      // Find exactly when the Stale label was added
+      // We look for the last 'labeled' event for STALE_LABEL
+      const staleEventIndex = timeline.findLastIndex(
+        (e) =>
+          e.event === 'labeled' &&
+          e.label?.name?.toLowerCase() === STALE_LABEL.toLowerCase(),
+      );
+
+      if (staleEventIndex === -1) return; // Fallback if no event found
+
+      const staleEvent = timeline[staleEventIndex];
+      const eventsAfterStale = timeline.slice(staleEventIndex + 1);
+
+      // Check for meaningful activity after the Stale label was applied
+      const meaningfulEvents = eventsAfterStale.filter((e) => {
+        const actor = e.actor?.login || '';
+        const isBot =
+          actor.includes('[bot]') || actor.includes('github-actions');
+
+        if (isBot) return false;
+
+        // Explicit whitelist of meaningful events for humans
+        if (
+          [
+            'commented',
+            'cross-referenced',
+            'connected',
+            'reopened',
+            'assigned',
+          ].includes(e.event)
+        ) {
+          return true;
+        }
+
+        return false;
+      });
+
+      if (meaningfulEvents.length > 0) {
+        // Activity detected, remove Stale label
+        if (dryRun) {
+          core.info(
+            `[DRY RUN] Would remove ${STALE_LABEL} from #${item.number} due to meaningful activity (e.g., comment or PR).`,
+          );
+        } else {
+          core.info(
+            `Removing ${STALE_LABEL} from #${item.number} due to meaningful activity (e.g., comment or PR).`,
+          );
+          await github.rest.issues
+            .removeLabel({
+              owner,
+              repo,
+              issue_number: item.number,
+              name: STALE_LABEL,
+            })
+            .catch(() => {});
+        }
+        return;
+      }
+
+      // No meaningful activity. Check if 14 days have passed.
+      const labeledDate = new Date(staleEvent.created_at);
+      if (labeledDate > closeThreshold) {
+        // Has not been 14 days since it was ACTUALLY marked stale
+        return;
+      }
+
+      if (dryRun) {
+        core.info(`[DRY RUN] Would close stale item #${item.number}.`);
+      } else {
+        core.info(`Closing stale item #${item.number}.`);
         await github.rest.issues.createComment({
           owner,
           repo,
@@ -201,6 +304,7 @@ module.exports = async ({ github, context, core }) => {
           repo,
           issue_number: item.number,
           state: 'closed',
+          state_reason: 'not_planned',
         });
       }
     },
@@ -222,8 +326,12 @@ module.exports = async ({ github, context, core }) => {
     async (pr) => {
       if (await isMaintainer(pr.user, pr.author_association)) return;
 
-      core.info(`Nudging PR #${pr.number} for contribution policy.`);
-      if (!dryRun) {
+      if (dryRun) {
+        core.info(
+          `[DRY RUN] Would nudge PR #${pr.number} for contribution policy.`,
+        );
+      } else {
+        core.info(`Nudging PR #${pr.number} for contribution policy.`);
         await github.rest.issues.addLabels({
           owner,
           repo,
@@ -246,10 +354,14 @@ module.exports = async ({ github, context, core }) => {
     async (pr) => {
       if (await isMaintainer(pr.user, pr.author_association)) return;
 
-      core.info(
-        `Closing PR #${pr.number} per contribution policy (no 'help wanted').`,
-      );
-      if (!dryRun) {
+      if (dryRun) {
+        core.info(
+          `[DRY RUN] Would close PR #${pr.number} per contribution policy (no 'help wanted').`,
+        );
+      } else {
+        core.info(
+          `Closing PR #${pr.number} per contribution policy (no 'help wanted').`,
+        );
         await github.rest.issues.createComment({
           owner,
           repo,

.github/workflows/build-unsigned-mac-binaries.yml

@@ -30,6 +30,7 @@ jobs:
         uses: 'actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5' # ratchet:actions/checkout@v4
         with:
           ref: '${{ inputs.ref || github.ref }}'
+          persist-credentials: false
 
       - name: 'Set up Node.js'
         uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions/setup-node@v4

.github/workflows/chained_e2e.yml

@@ -148,6 +148,7 @@ jobs:
         with:
           ref: '${{ needs.parse_run_context.outputs.sha }}'
           repository: '${{ needs.parse_run_context.outputs.repository }}'
+          persist-credentials: false
 
       - name: 'Set up Node.js ${{ matrix.node-version }}'
         uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions-node@v4
@@ -193,6 +194,7 @@ jobs:
         with:
           ref: '${{ needs.parse_run_context.outputs.sha }}'
           repository: '${{ needs.parse_run_context.outputs.repository }}'
+          persist-credentials: false
 
       - name: 'Set up Node.js 20.x'
         uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions-node@v4
@@ -233,6 +235,7 @@ jobs:
         with:
           ref: '${{ needs.parse_run_context.outputs.sha }}'
           repository: '${{ needs.parse_run_context.outputs.repository }}'
+          persist-credentials: false
 
       - name: 'Set up Node.js 20.x'
         uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions-node@v4
@@ -314,6 +317,7 @@ jobs:
         with:
           ref: '${{ needs.parse_run_context.outputs.sha }}'
           repository: '${{ needs.parse_run_context.outputs.repository }}'
+          persist-credentials: false
           fetch-depth: 0
 
       - name: 'Set up Node.js 20.x'

.github/workflows/ci.yml

@@ -57,6 +57,7 @@ jobs:
       - name: 'Checkout'
         uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
         with:
+          persist-credentials: false
           ref: '${{ github.event.inputs.branch_ref || github.ref }}'
           fetch-depth: 0
 
@@ -130,6 +131,8 @@ jobs:
     steps:
       - name: 'Checkout'
         uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
+        with:
+          persist-credentials: false
       - name: 'Link Checker'
         uses: 'lycheeverse/lychee-action@885c65f3dc543b57c898c8099f4e08c8afd178a2' # ratchet: lycheeverse/lychee-action@v2.6.1
         with:
@@ -157,6 +160,8 @@ jobs:
     steps:
       - name: 'Checkout'
         uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
+        with:
+          persist-credentials: false
 
       - name: 'Set up Node.js ${{ matrix.node-version }}'
         uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions/setup-node@v4
@@ -252,6 +257,8 @@ jobs:
     steps:
       - name: 'Checkout'
         uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
+        with:
+          persist-credentials: false
 
       - name: 'Set up Node.js ${{ matrix.node-version }}'
         uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions/setup-node@v4
@@ -339,6 +346,7 @@ jobs:
       - name: 'Checkout'
         uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
         with:
+          persist-credentials: false
           ref: '${{ github.event.inputs.branch_ref || github.ref }}'
 
       - name: 'Initialize CodeQL'
@@ -363,6 +371,7 @@ jobs:
       - name: 'Checkout'
         uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
         with:
+          persist-credentials: false
           ref: '${{ github.event.inputs.branch_ref || github.ref }}'
           fetch-depth: 1
 
@@ -390,6 +399,7 @@ jobs:
       - name: 'Checkout'
         uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
         with:
+          persist-credentials: false
           ref: '${{ github.event.inputs.branch_ref || github.ref }}'
 
       - name: 'Set up Node.js 20.x'

.github/workflows/deflake.yml

@@ -43,6 +43,7 @@ jobs:
         with:
           ref: '${{ github.event.pull_request.head.sha }}'
           repository: '${{ github.repository }}'
+          persist-credentials: false
 
       - name: 'Set up Node.js ${{ matrix.node-version }}'
         uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions-node@v4
@@ -86,6 +87,7 @@ jobs:
         with:
           ref: '${{ github.event.pull_request.head.sha }}'
           repository: '${{ github.repository }}'
+          persist-credentials: false
 
       - name: 'Set up Node.js 20.x'
         uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions-node@v4
@@ -125,6 +127,7 @@ jobs:
         with:
           ref: '${{ github.event.pull_request.head.sha }}'
           repository: '${{ github.repository }}'
+          persist-credentials: false
 
       - name: 'Set up Node.js 20.x'
         uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions-node@v4

.github/workflows/docs-audit.yml

@@ -19,6 +19,7 @@ jobs:
         with:
           fetch-depth: 0
           ref: 'main'
+          persist-credentials: false
 
       - name: 'Set up Node.js'
         uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020'

.github/workflows/docs-page-action.yml

@@ -24,6 +24,8 @@ jobs:
     steps:
       - name: 'Checkout'
         uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
+        with:
+          persist-credentials: false
 
       - name: 'Setup Pages'
         uses: 'actions/configure-pages@983d7736d9b0ae728b81ab479565c72886d7745b' # ratchet:actions/configure-pages@v5

.github/workflows/eval-pr.yml

@@ -38,6 +38,7 @@ jobs:
         with:
           # Check out the trusted code from main for detection
           fetch-depth: 0
+          persist-credentials: false
 
       - name: 'Detect Steering Changes'
         id: 'detect'
@@ -102,6 +103,7 @@ jobs:
           # This only runs AFTER manual approval
           ref: '${{ github.event.pull_request.head.sha }}'
           fetch-depth: 0
+          persist-credentials: false
 
       - name: 'Remove Approval Notification'
         # Run even if other steps fail, to ensure we clean up the "Action Required" message

.github/workflows/evals-nightly.yml

@@ -46,6 +46,8 @@ jobs:
     steps:
       - name: 'Checkout'
         uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
+        with:
+          persist-credentials: false
 
       - name: 'Set up Node.js'
         uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions/setup-node@v4
@@ -105,6 +107,8 @@ jobs:
     steps:
       - name: 'Checkout'
         uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
+        with:
+          persist-credentials: false
 
       - name: 'Download Logs'
         uses: 'actions/download-artifact@cc203385981b70ca67e1cc392babf9cc229d5806' # ratchet:actions/download-artifact@v4

.github/workflows/gemini-automated-issue-dedup.yml

@@ -48,6 +48,8 @@ jobs:
     steps:
       - name: 'Checkout'
         uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
+        with:
+          persist-credentials: false
 
       - name: 'Log in to GitHub Container Registry'
         uses: 'docker/login-action@184bdaa0721073962dff0199f1fb9940f07167d1' # ratchet:docker/login-action@v3
@@ -66,6 +68,7 @@ jobs:
           ISSUE_NUMBER: '${{ github.event.issue.number }}'
           REPOSITORY: '${{ github.repository }}'
           FIRESTORE_PROJECT: '${{ vars.FIRESTORE_PROJECT }}'
+          GEMINI_CLI_TRUST_WORKSPACE: 'true'
         with:
           gcp_workload_identity_provider: '${{ vars.GCP_WIF_PROVIDER }}'
           gcp_project_id: '${{ vars.GOOGLE_CLOUD_PROJECT }}'

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

@@ -90,6 +90,8 @@ jobs:
 
       - name: 'Checkout'
         uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
+        with:
+          persist-credentials: false
 
       - name: 'Generate GitHub App Token'
         id: 'generate_token'
@@ -333,14 +335,41 @@ jobs:
               return;
             }
 
+            const newAreaLabel = labelsToAdd[0];
+
+            // Get current labels to resolve conflicts
+            const { data: currentLabels } = await github.rest.issues.listLabelsOnIssue({
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              issue_number: issueNumber,
+            });
+            const currentLabelNames = currentLabels.map(l => l.name);
+            const currentAreaLabels = currentLabelNames.filter(name => name.startsWith('area/'));
+
+            const labelsToRemove = currentAreaLabels.filter(name => name !== newAreaLabel);
+
+            for (const label of labelsToRemove) {
+              try {
+                await github.rest.issues.removeLabel({
+                  owner: context.repo.owner,
+                  repo: context.repo.repo,
+                  issue_number: issueNumber,
+                  name: label
+                });
+                core.info(`Removed conflicting area label: ${label}`);
+              } catch (e) {
+                core.warning(`Failed to remove label ${label}: ${e.message}`);
+              }
+            }
+
             // Set labels based on triage result
             await github.rest.issues.addLabels({
               owner: context.repo.owner,
               repo: context.repo.repo,
               issue_number: issueNumber,
-              labels: labelsToAdd
+              labels: [newAreaLabel]
             });
-            core.info(`Successfully added labels for #${issueNumber}: ${labelsToAdd.join(', ')}`);
+            core.info(`Successfully added labels for #${issueNumber}: ${newAreaLabel}`);
 
       - name: 'Post Issue Analysis Failure Comment'
         if: |-

.github/workflows/gemini-cli-bot-brain.yml

@@ -29,7 +29,7 @@ on:
         default: false
 
 concurrency:
-  group: '${{ github.workflow }}-${{ github.event.issue.number || github.event.pull_request.number || github.event.inputs.issue_number || github.ref }}'
+  group: '${{ github.workflow }}-${{ github.event.issue.number || github.event.inputs.issue_number || github.ref }}'
   cancel-in-progress: true
 
 jobs:
@@ -41,14 +41,12 @@ jobs:
         github.event_name == 'schedule' ||
         (github.event_name == 'workflow_dispatch' && github.event.inputs.run_interactive != 'true') ||
         (github.event_name == 'workflow_dispatch' && github.event.inputs.run_interactive == 'true') ||
-        (github.event_name == 'issue_comment' && github.event.comment.user.login != 'gemini-cli[bot]' && contains(github.event.comment.body, '@gemini-cli') && contains(fromJSON('["COLLABORATOR", "MEMBER", "OWNER"]'), github.event.comment.author_association)) ||
-        (github.event_name == 'pull_request_review_comment' && github.event.comment.user.login != 'gemini-cli[bot]' && contains(github.event.comment.body, '@gemini-cli') && contains(fromJSON('["COLLABORATOR", "MEMBER", "OWNER"]'), github.event.comment.author_association))
+        (github.event_name == 'issue_comment' && github.event.comment.user.login != 'gemini-cli[bot]' && contains(github.event.comment.body, '@gemini-cli') && contains(fromJSON('["COLLABORATOR", "MEMBER", "OWNER"]'), github.event.comment.author_association))
       )
     # The reasoning phase is strictly readonly.
     permissions:
       contents: 'read'
       issues: 'read'
-      pull-requests: 'read'
       actions: 'read'
     env:
       GEMINI_CLI_TRUST_WORKSPACE: 'true'
@@ -57,7 +55,7 @@ jobs:
         id: 'determine_ref'
         env:
           GITHUB_TOKEN: '${{ secrets.GITHUB_TOKEN }}'
-          ISSUE_NUMBER: '${{ github.event.issue.number || github.event.pull_request.number || github.event.inputs.issue_number }}'
+          ISSUE_NUMBER: '${{ github.event.issue.number || github.event.inputs.issue_number }}'
         run: |
           REF="${{ github.ref }}"
           if [ -n "$ISSUE_NUMBER" ]; then
@@ -125,11 +123,12 @@ jobs:
           GEMINI_API_KEY: '${{ secrets.GEMINI_API_KEY }}'
           GITHUB_TOKEN: '${{ secrets.GITHUB_TOKEN }}'
           GEMINI_MODEL: 'gemini-3-flash-preview'
+          GEMINI_CLI_HOME: 'tools/gemini-cli-bot'
           ENABLE_PRS: "${{ github.event.inputs.enable_prs || 'false' }}"
           TRIGGER_ISSUE_NUMBER: '${{ github.event.issue.number || github.event.inputs.issue_number }}'
           TRIGGER_COMMENT_ID: '${{ github.event.comment.id || github.event.inputs.comment_id }}'
         run: |
-          PROMPT_PATH="tools/gemini-cli-bot/brain/metrics.md"
+          PROMPT_PATH="tools/gemini-cli-bot/brain/scheduled.md"
           if [ "${{ github.event_name }}" = "issue_comment" ] || [ "${{ github.event.inputs.run_interactive }}" = "true" ]; then
             PROMPT_PATH="tools/gemini-cli-bot/brain/interactive.md"
             export ENABLE_PRS="true"
@@ -152,9 +151,16 @@ jobs:
             echo "</untrusted_context>" >> trigger_context.md
           fi
 
-          cat trigger_context.md "$PROMPT_PATH" tools/gemini-cli-bot/brain/common.md > combined_prompt.md
+          if [ "$ENABLE_PRS" = "true" ]; then
+            echo "**System Directive**: PR creation is ENABLED for this run. You MUST activate the **'prs' skill** to stage your changes and generate a \`pr-description.md\` file if you are proposing fixes." >> trigger_context.md
+            echo "**CRITICAL System Directive**: You MUST ONLY propose and implement a **SINGLE** improvement or fix per run. Bundling unrelated changes (e.g., a documentation update and a script fix, or a metrics update and a logic fix) into a single PR is STRICTLY FORBIDDEN and will result in immediate rejection during the critique phase. If you identify multiple issues, pick the most impactful one and ignore the others for now." >> trigger_context.md
+          else
+            echo "**System Directive**: PR creation is DISABLED for this run. You MUST NOT stage files or attempt to create a PR description." >> trigger_context.md
+          fi
+          echo "" >> trigger_context.md
 
-          node bundle/gemini.js --policy tools/gemini-cli-bot/ci-policy.toml -p "$(cat combined_prompt.md)"
+          cat trigger_context.md "$PROMPT_PATH" > combined_prompt.md
+          node bundle/gemini.js --policy tools/gemini-cli-bot/ci-policy.toml --prompt="$(cat combined_prompt.md)"
 
           if [ -n "$TRIGGER_ISSUE_NUMBER" ] && [ ! -s "issue-comment.md" ] && [ ! -s "pr-comment.md" ]; then
             echo "Agent failed to respond. Generating fallback error message."
@@ -164,17 +170,18 @@ jobs:
           fi
 
       - name: 'Run Critique Phase'
-        if: "${{ github.event.inputs.enable_prs == 'true' || github.event_name == 'issue_comment' || github.event_name == 'pull_request_review_comment' || github.event.inputs.run_interactive == 'true' }}"
+        if: "${{ github.event.inputs.enable_prs == 'true' || github.event_name == 'issue_comment' || github.event.inputs.run_interactive == 'true' }}"
         env:
           GEMINI_API_KEY: '${{ secrets.GEMINI_API_KEY }}'
           GITHUB_TOKEN: '${{ secrets.GITHUB_TOKEN }}'
           GEMINI_MODEL: 'gemini-3-flash-preview'
+          GEMINI_CLI_HOME: 'tools/gemini-cli-bot'
         run: |
           if git diff --staged --quiet; then
              echo "No changes staged. Skipping critique."
              echo "[APPROVED]" > critique_result.txt
           else
-             node bundle/gemini.js --policy tools/gemini-cli-bot/ci-policy.toml -p "$(cat tools/gemini-cli-bot/brain/critique.md)" 2>&1 | tee critique_output.log
+             node bundle/gemini.js --policy tools/gemini-cli-bot/ci-policy.toml --prompt="$(cat tools/gemini-cli-bot/.gemini/skills/critique/SKILL.md)" 2>&1 | tee critique_output.log
 
              if [ "${PIPESTATUS[0]}" -eq 0 ] && grep -q "\[APPROVED\]" critique_output.log && ! grep -q "\[REJECTED\]" critique_output.log; then
                echo "[APPROVED]" > critique_result.txt
@@ -185,7 +192,7 @@ jobs:
           fi
 
       - name: 'Generate Patch'
-        if: "${{ github.event.inputs.enable_prs == 'true' || github.event_name == 'issue_comment' || github.event_name == 'pull_request_review_comment' || github.event.inputs.run_interactive == 'true' }}"
+        if: "${{ github.event.inputs.enable_prs == 'true' || github.event_name == 'issue_comment' || github.event.inputs.run_interactive == 'true' }}"
         run: |
           touch bot-changes.patch
           touch pr-description.md
@@ -223,7 +230,7 @@ jobs:
     steps:
       - name: 'Generate GitHub App Token 🔑'
         id: 'generate_token'
-        if: "${{ github.event.inputs.enable_prs == 'true' || github.event_name == 'issue_comment' || github.event_name == 'pull_request_review_comment' || github.event.inputs.run_interactive == 'true' }}"
+        if: "${{ github.event.inputs.enable_prs == 'true' || github.event_name == 'issue_comment' || github.event.inputs.run_interactive == 'true' }}"
         uses: 'actions/create-github-app-token@a8d616148505b5069dccd32f177bb87d7f39123b' # ratchet:actions/create-github-app-token@v2
         with:
           app-id: '${{ secrets.APP_ID }}'
@@ -238,7 +245,7 @@ jobs:
         id: 'determine_ref'
         env:
           GITHUB_TOKEN: '${{ secrets.GITHUB_TOKEN }}'
-          ISSUE_NUMBER: '${{ github.event.issue.number || github.event.pull_request.number || github.event.inputs.issue_number }}'
+          ISSUE_NUMBER: '${{ github.event.issue.number || github.event.inputs.issue_number }}'
         run: |
           REF="main"
           if [ -n "$ISSUE_NUMBER" ]; then
@@ -263,7 +270,7 @@ jobs:
           path: '${{ runner.temp }}/brain-data/'
 
       - name: 'Create or Update PR'
-        if: "${{ github.event.inputs.enable_prs == 'true' || github.event_name == 'issue_comment' || github.event_name == 'pull_request_review_comment' || github.event.inputs.run_interactive == 'true' }}"
+        if: "${{ github.event.inputs.enable_prs == 'true' || github.event_name == 'issue_comment' || github.event.inputs.run_interactive == 'true' }}"
         env:
           GH_TOKEN: '${{ steps.generate_token.outputs.token }}'
           FALLBACK_PAT: '${{ secrets.GEMINI_CLI_ROBOT_GITHUB_PAT }}'

.github/workflows/gemini-cli-bot-pulse.yml

@@ -23,6 +23,7 @@ jobs:
       - name: 'Checkout'
         uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
         with:
+          persist-credentials: false
           fetch-depth: 0
 
       - name: 'Setup Node.js'

.github/workflows/gemini-lifecycle-manager.yml

@@ -33,6 +33,8 @@ jobs:
 
       - name: 'Checkout repository'
         uses: 'actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683' # ratchet:actions/checkout@v4
+        with:
+          persist-credentials: false
 
       - name: 'Lifecycle Management'
         uses: 'actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea'

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

@@ -28,6 +28,8 @@ jobs:
     steps:
       - name: 'Checkout'
         uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
+        with:
+          persist-credentials: false
 
       - name: 'Log in to GitHub Container Registry'
         uses: 'docker/login-action@184bdaa0721073962dff0199f1fb9940f07167d1' # ratchet:docker/login-action@v3

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

@@ -1,10 +1,6 @@
 name: '📋 Gemini Scheduled Issue Triage'
 
 on:
-  issues:
-    types:
-      - 'opened'
-      - 'reopened'
   schedule:
     - cron: '0 * * * *' # Runs every hour
   workflow_dispatch:
@@ -30,6 +26,20 @@ jobs:
     steps:
       - name: 'Checkout'
         uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
+        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'
@@ -61,6 +71,24 @@ jobs:
             const syncIssueTypes = require('./.github/scripts/sync-issue-types.cjs');
             await syncIssueTypes({ github, context, core });
 
+      - name: 'Find Issues with Conflicting Labels'
+        if: |-
+          ${{ github.event_name == 'schedule' || github.event_name == 'workflow_dispatch' }}
+        env:
+          GITHUB_TOKEN: '${{ steps.generate_token.outputs.token }}'
+          GITHUB_REPOSITORY: '${{ github.repository }}'
+        run: |-
+          set -euo pipefail
+          echo '🔍 Fetching open issues to find conflicts...'
+          # Fetch up to 2000 open issues in one quick GraphQL-backed query
+          gh issue list --repo "${GITHUB_REPOSITORY}" --search "is:issue is:open" --limit 2000 --json number,title,body,labels > all_open_issues.json
+
+          echo '🧹 Filtering issues with multiple area/ or priority/ labels...'
+          jq -c '[ .[] | select( (.labels | map(select(.name | startswith("area/"))) | length) > 1 or (.labels | map(select(.name | startswith("priority/"))) | length) > 1 ) ] | .[0:50]' all_open_issues.json > conflicting_labels_issues.json
+
+          CONFLICT_COUNT=$(jq 'length' conflicting_labels_issues.json)
+          echo "Found ${CONFLICT_COUNT} issues with conflicting labels (capped at 50 for processing)."
+
       - name: 'Find untriaged issues'
         if: |-
           ${{ github.event_name == 'schedule' || github.event_name == 'workflow_dispatch' }}
@@ -73,30 +101,39 @@ jobs:
 
           echo '🔍 Finding issues missing area labels...'
           gh issue list --repo "${GITHUB_REPOSITORY}" \
-            --search 'is:open is:issue -label:status/bot-triaged -label:area/core -label:area/agent -label:area/enterprise -label:area/non-interactive -label:area/security -label:area/platform -label:area/extensions -label:area/documentation -label:area/unknown' --limit 50 --json number,title,body > no_area_issues.json
+            --search 'is:open is:issue -label:area/core -label:area/agent -label:area/enterprise -label:area/non-interactive -label:area/security -label:area/platform -label:area/extensions -label:area/documentation -label:area/unknown' --limit 50 --json number,title,body,labels > no_area_issues.json
 
           echo '🔍 Finding issues missing kind labels...'
           gh issue list --repo "${GITHUB_REPOSITORY}" \
-            --search 'is:open is:issue -label:status/bot-triaged -label:kind/bug -label:kind/enhancement -label:kind/customer-issue -label:kind/question' --limit 50 --json number,title,body > no_kind_issues.json
+            --search 'is:open is:issue -label:kind/bug -label:kind/enhancement -label:kind/customer-issue -label:kind/question' --limit 50 --json number,title,body,labels > no_kind_issues.json
 
           echo '🏷️ Finding issues missing priority labels...'
           gh issue list --repo "${GITHUB_REPOSITORY}" \
-            --search 'is:open is:issue -label:status/bot-triaged -label:priority/p0 -label:priority/p1 -label:priority/p2 -label:priority/p3 -label:priority/unknown' --limit 50 --json number,title,body > no_priority_issues.json
+            --search 'is:open is:issue -label:priority/p0 -label:priority/p1 -label:priority/p2 -label:priority/p3 -label:priority/unknown' --limit 50 --json number,title,body,labels > no_priority_issues.json
 
           echo '📏 Finding issues missing effort labels...'
           gh issue list --repo "${GITHUB_REPOSITORY}" \
-            --search 'is:open is:issue -label:status/bot-triaged -label:effort/small -label:effort/medium -label:effort/large label:area/core,area/extensions,area/site,area/non-interactive' --limit 20 --json number,title,body > no_effort_issues.json
+            --search 'is:open is:issue -label:effort/small -label:effort/medium -label:effort/large label:area/core,area/extensions,area/site,area/non-interactive' --limit 20 --json number,title,body,labels > no_effort_issues.json
 
-          echo '🔄 Merging and deduplicating issues...'
-          jq -c -s 'add | unique_by(.number)' no_area_issues.json no_kind_issues.json no_priority_issues.json no_effort_issues.json no_type_issues.json > issues_to_triage.json
+          echo '🔄 Merging and deduplicating standard triage issues...'
+          if [ ! -f conflicting_labels_issues.json ]; then echo "[]" > conflicting_labels_issues.json; fi
+          jq -c -s 'add | unique_by(.number)' no_area_issues.json no_kind_issues.json no_priority_issues.json conflicting_labels_issues.json > standard_issues_to_triage.json
 
-          ISSUE_COUNT="$(jq 'length' issues_to_triage.json)"
-          if [ "$ISSUE_COUNT" -gt 0 ]; then
+          echo '📏 Deduplicating effort issues...'
+          jq -c -s 'add | unique_by(.number)' no_effort_issues.json > effort_issues_to_triage.json
+
+          STANDARD_COUNT="$(jq 'length' standard_issues_to_triage.json)"
+          EFFORT_COUNT="$(jq 'length' effort_issues_to_triage.json)"
+          if [ "$STANDARD_COUNT" -gt 0 ] || [ "$EFFORT_COUNT" -gt 0 ]; then
             echo "has_issues=true" >> "${GITHUB_OUTPUT}"
+            echo "has_standard_issues=$([ "$STANDARD_COUNT" -gt 0 ] && echo 'true' || echo 'false')" >> "${GITHUB_OUTPUT}"
+            echo "has_effort_issues=$([ "$EFFORT_COUNT" -gt 0 ] && echo 'true' || echo 'false')" >> "${GITHUB_OUTPUT}"
           else
             echo "has_issues=false" >> "${GITHUB_OUTPUT}"
+            echo "has_standard_issues=false" >> "${GITHUB_OUTPUT}"
+            echo "has_effort_issues=false" >> "${GITHUB_OUTPUT}"
           fi
-          echo "✅ Found ${ISSUE_COUNT} unique issues to triage! 🎯"
+          echo "✅ Found ${STANDARD_COUNT} standard issues and ${EFFORT_COUNT} effort issues to triage! 🎯"
 
       - name: 'Create Gemini CLI Experiments Override'
         if: |-
@@ -129,18 +166,20 @@ jobs:
             core.info(`Found ${labelNames.length} labels: ${labelNames.join(', ')}`);
             return labelNames;
 
-      - name: 'Run Gemini Issue Analysis'
+      - name: 'Run Standard Triage Analysis'
         if: |-
-          steps.get_issue_from_event.outputs.has_issues == 'true' || steps.find_issues.outputs.has_issues == 'true'
+          steps.get_issue_from_event.outputs.has_issues == 'true' || steps.find_issues.outputs.has_standard_issues == 'true'
         uses: 'google-github-actions/run-gemini-cli@a3bf79042542528e91937b3a3a6fbc4967ee3c31' # ratchet:google-github-actions/run-gemini-cli@v0
-        id: 'gemini_issue_analysis'
+        id: 'gemini_standard_issue_analysis'
         env:
           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: '${{ steps.get_version.outputs.version }}'
           GEMINI_CLI_TRUST_WORKSPACE: 'true'
           GEMINI_EXP: 'gemini_exp.json'
           GEMINI_STRICT_TELEMETRY_LIMITS: 'true'
+          GEMINI_MODEL: 'gemini-3-flash-preview'
         with:
           gcp_workload_identity_provider: '${{ vars.GCP_WIF_PROVIDER }}'
           gcp_project_id: '${{ vars.GOOGLE_CLOUD_PROJECT }}'
@@ -154,12 +193,10 @@ jobs:
               "maxSessionTurns": 25,
               "coreTools": [
                 "run_shell_command(echo)",
-                "grep_search",
-                "glob",
                 "read_file"
               ],
               "telemetry": {
-                "enabled": true,
+                "enabled": false,
                 "target": "gcp"
               }
             }
@@ -173,37 +210,37 @@ jobs:
             ## Steps
 
             1. You are only able to use the echo and read_file commands. Review the available labels in the environment variable: "${AVAILABLE_LABELS}".
-            2. Use the read_file tool to read the file "issues_to_triage.json" which contains the JSON array of issues to triage.
-            3. Review the issue title, body and any comments provided in the JSON file.
-            4. Identify the most relevant labels from the existing labels, specifically focusing on area/*, kind/*, priority/*, and effort/*.
+            2. Use the read_file tool to read the file "standard_issues_to_triage.json" which contains the JSON array of issues to triage (including their current labels).
+            3. Review the issue title, body, current labels, and any comments provided in the JSON file.
+            4. Identify the most relevant labels from the existing labels, specifically focusing on area/*, kind/*, and priority/*.
             5. Label Policy:
                - If the issue already has a kind/ label, do not change it.
-               - If the issue already has a priority/ label, do not change it.
-               - If the issue already has an area/ label, do not change it.
-               - If the issue already has an effort/ label, do not change it.
-               - If the issue is missing an effort/ label AND its area is area/core, area/extensions, area/site, or area/non-interactive, you must evaluate the architectural complexity to determine the effort level. You MUST NOT guess the root cause. You MUST actively use your codebase search tools (grep_search and glob) to search for keywords from the issue and explore the codebase. You must identify the specific files and components involved before deciding the effort. Do NOT evaluate or assign an effort/ label to issues in any other areas (such as area/agent).
+               - If the issue has exactly ONE priority/ label, do not change it (unless you are explicitly re-evaluating an ambiguous priority).
+               - If the issue is missing a priority/ label, OR if the issue currently has MULTIPLE priority/ labels, you must evaluate the issue's impact to determine exactly ONE priority level (priority/p0, priority/p1, priority/p2, priority/p3, or priority/unknown) based the guidelines. If you are fixing an issue with multiple priority/ labels, put the correct one in `labels_to_add` and put all the incorrect ones in `labels_to_remove`.
+               - If the issue has exactly ONE area/ label, do not change it.
+               - If the issue is missing an area/ label, OR if the issue currently has MULTIPLE area/ labels, select exactly ONE area/ label that best fits the issue. Issues MUST NOT have multiple area/ labels. If you are fixing an issue with multiple area/ labels, put the correct one in `labels_to_add` and put all the incorrect ones in `labels_to_remove`.
                - If any of these are missing, select exactly ONE appropriate label for the missing category.
             6. Identify other applicable labels based on the issue content, such as status/*, help wanted, good first issue, etc.
             7. Give me a single short explanation about why you are selecting each label in the process.
             8. Output a JSON array of objects, each containing the issue number
-               and the labels to add and remove, along with an explanation. If you assigned an effort/ label, you MUST also include an effort_analysis field. This effort_analysis must be highly detailed, technical, and empirical. It MUST NOT contain vague guesses (e.g., avoid words like "likely points to" or "possibly"). You must explicitly cite the specific file paths and architectural mechanisms you discovered using your search tools, explain the root cause, and then explicitly state how that complexity maps to the chosen effort level guidelines. For example:
+               and the labels to add and remove, along with an explanation. For example:
                ```
                [
                  {
                    "issue_number": 123,
-                   "labels_to_add": ["area/core", "kind/bug", "priority/p2", "effort/small"],
+                   "labels_to_add": ["area/core", "kind/bug", "priority/p2"],
                    "labels_to_remove": ["status/need-triage"],
-                   "explanation": "This issue is a UI bug that needs to be addressed with medium priority.",
-                   "effort_analysis": "The `vscode-ide-companion` extension indiscriminately tracks active text editors via `vscode.window.onDidChangeActiveTextEditor` in `open-files-manager.ts`. When a user opens `.vscode/settings.json`, its content is sent to the CLI's context. The fix is highly localized to the VS Code companion extension's event listener. It involves adding a simple conditional check to exclude specific configuration files from the active editor tracking logic, which is a trivial logic adjustment with a clear root cause."
+                   "explanation": "This issue is a UI bug that needs to be addressed with medium priority."
                  }
                ]
                ```
               If an issue cannot be classified, do not include it in the output array.
-            9. For each issue please check if CLI version is present, this is usually in the output of the /about command and will look like 0.1.5
-              - Anything more than 6 versions older than the most recent should add the status/need-retesting label
-            10. If you see that the issue doesn't look like it has sufficient information recommend the status/need-information label and leave a comment politely requesting the relevant information, eg.. if repro steps are missing request for repro steps. if version information is missing request for version information into the explanation section below.
-            11. If you think an issue might be a Priority/P0 do not apply the priority/p0 label. Instead apply a status/manual-triage label and include a note in your explanation.
-            12. 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.
+            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.
 
             ## Guidelines
 
@@ -213,10 +250,107 @@ jobs:
               - Do not add comments or modify the issue content.
               - Do not remove the following labels maintainer, help wanted or good first issue.
               - Triage only the current issue.
-              - Identify only one area/ label.
+              - Identify exactly ONE area/ label. Do NOT assign multiple area/ labels to a single issue.
               - Identify only one kind/ label (Do not apply kind/duplicate or kind/parent-issue)
-              - Identify only one priority/ label.
-              - Once you categorize the issue if it needs information bump down the priority by 1 eg.. a p0 would become a p1 a p1 would become a p2. P2 and P3 can stay as is in this scenario.
+              - Identify exactly ONE priority/ label. Do NOT assign multiple priority/ labels to a single issue.
+              - **Do not manually downgrade the priority.** Always assign the true priority based on the guidelines. The system will handle downgrades programmatically if information is missing.
+              - **NEVER mention label names, label removals, or label additions in your `explanation`.** The explanation must be purely written for the user (e.g., "Please provide your CLI version.") without exposing internal triage mechanics (e.g., do NOT say "Removing area/unknown to leave only area/core").
+
+            Categorization Guidelines (Priority):
+            P0 - Urgent Blocking Issues:
+              - DO NOT APPLY THE priority/p0 LABEL AUTOMATICALLY. Instead apply priority/p1 and status/manual-triage.
+              - Definition: Critical failures breaking core functionality for a large portion of users. Examples: CLI fails to launch globally, core commands (gemini run) crash on valid input, unhandled promise rejections on boot, critical security vulnerability.
+              - Note: You must apply priority/p1 and status/manual-triage instead of priority/p0.
+            P1 - Critical but Workable:
+              - Definition: Severe issues without a reasonable workaround, significantly degrading the developer experience but not globally blocking. Examples: Specific tools failing consistently (e.g., `web_search` returns 500s), persistent PTY streaming hangs, memory leaks leading to OOM after short use.
+            P2 - Significant Issues:
+              - Definition: Affect some workflows but a clear workaround exists, or non-critical bugs. Examples: Theme flickering, confusing error messages, minor UI misalignment, failing to read deeply nested config files correctly.
+            P3 - Minor/Enhancements:
+              - Definition: Trivial bugs, typos, documentation requests, or feature requests.
+
+            Categorization Guidelines (Kind):
+            kind/bug: The issue is describing an unexpected behavior or failure in the application.
+            kind/enhancement: The issue is describing a feature request or an improvement to an existing feature.
+            kind/question: The issue is asking a question about how to use the CLI or about a specific feature.
+
+            Categorization Guidelines (Area):
+            area/agent: The "brain" of the CLI. Core agent logic, model quality, tool/function calling, memory, web search, generated code quality, sub-agents.
+            area/core: The fundamental CLI app. UI/UX, installation, OS compatibility, performance, command parsing, theming, flickering.
+            area/documentation: Website docs, READMEs, inline help text.
+            area/enterprise: Telemetry, Policy, Quota / Licensing
+            area/extensions: Gemini CLI extensions capability
+            area/non-interactive: GitHub Actions, SDK, 3P Integrations, Shell Scripting, Command line automation
+            area/platform: Platform specific behavior
+            area/security: Authentication, authorization, privacy, data leaks, credential storage.
+
+      - name: 'Stop Telemetry Collector'
+        if: |-
+          steps.find_issues.outputs.has_effort_issues == 'true'
+        run: 'docker rm -f gemini-telemetry-collector || true'
+
+      - name: 'Run Effort Triage Analysis'
+        if: |-
+          steps.find_issues.outputs.has_effort_issues == 'true'
+        uses: 'google-github-actions/run-gemini-cli@a3bf79042542528e91937b3a3a6fbc4967ee3c31' # ratchet:google-github-actions/run-gemini-cli@v0
+        id: 'gemini_effort_issue_analysis'
+        env:
+          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: '${{ steps.get_version.outputs.version }}'
+          GEMINI_CLI_TRUST_WORKSPACE: 'true'
+          GEMINI_EXP: 'gemini_exp.json'
+          GEMINI_STRICT_TELEMETRY_LIMITS: 'true'
+          GEMINI_MODEL: 'gemini-3-flash-preview'
+        with:
+          gcp_workload_identity_provider: '${{ vars.GCP_WIF_PROVIDER }}'
+          gcp_project_id: '${{ vars.GOOGLE_CLOUD_PROJECT }}'
+          gcp_location: '${{ vars.GOOGLE_CLOUD_LOCATION }}'
+          gcp_service_account: '${{ vars.SERVICE_ACCOUNT_EMAIL }}'
+          gemini_api_key: '${{ secrets.GEMINI_API_KEY }}'
+          use_vertex_ai: '${{ vars.GOOGLE_GENAI_USE_VERTEXAI }}'
+          use_gemini_code_assist: '${{ vars.GOOGLE_GENAI_USE_GCA }}'
+          settings: |-
+            {
+              "maxSessionTurns": 30,
+              "coreTools": [
+                "run_shell_command(echo)",
+                "grep_search",
+                "glob",
+                "read_file"
+              ],
+              "telemetry": {
+                "enabled": false,
+                "target": "gcp"
+              }
+            }
+          prompt: |-
+            ## Role
+
+            You are an expert software architect. Analyze the provided GitHub issues and assign the correct `effort/*` label based on the codebase complexity.
+
+            ## Steps
+
+            1. Use the read_file tool to read "effort_issues_to_triage.json".
+            2. For each issue in the array:
+               - You must evaluate the architectural complexity to determine the effort level. You MUST NOT guess the root cause. You MUST actively use your codebase search tools (grep_search and glob) to search for keywords from the issue and explore the codebase. You must identify the specific files and components involved before deciding the effort.
+            3. Output a JSON array of objects, each containing the issue number and the effort label to add, along with an explanation and an effort_analysis field. This effort_analysis must be highly detailed, technical, and empirical. It MUST NOT contain vague guesses (e.g., avoid words like "likely points to" or "possibly"). You must explicitly cite the specific file paths and architectural mechanisms you discovered using your search tools, explain the root cause, and then explicitly state how that complexity maps to the chosen effort level guidelines. For example:
+               ```
+               [
+                 {
+                   "issue_number": 123,
+                   "labels_to_add": ["effort/small"],
+                   "explanation": "This is a simple logic fix.",
+                   "effort_analysis": "The `vscode-ide-companion` extension indiscriminately tracks active text editors via `vscode.window.onDidChangeActiveTextEditor` in `open-files-manager.ts`. When a user opens `.vscode/settings.json`, its content is sent to the CLI's context. The fix is highly localized to the VS Code companion extension's event listener. It involves adding a simple conditional check to exclude specific configuration files from the active editor tracking logic, which is a trivial logic adjustment with a clear root cause."
+                 }
+               ]
+               ```
+
+            ## Guidelines
+
+            - Output only valid JSON format
+            - Do not include any explanation or additional text, just the JSON
+            - Triage only the current issue.
 
             Categorization Guidelines (Effort):
             effort/small (1 day or less):
@@ -272,13 +406,14 @@ jobs:
             - This product is designed to use different models eg.. using pro, downgrading to flash etc.
             - When users report that they dont expect the model to change those would be categorized as feature requests.
 
-      - name: 'Apply Labels to Issues'
+      - name: 'Apply Triaged Labels'
         if: |-
-          ${{ steps.gemini_issue_analysis.outcome == 'success' &&
-              steps.gemini_issue_analysis.outputs.summary != '[]' }}
+          always() &&
+          ( (steps.gemini_standard_issue_analysis.outcome == 'success' && steps.gemini_standard_issue_analysis.outputs.summary != '[]' && steps.gemini_standard_issue_analysis.outputs.summary != '') ||
+            (steps.gemini_effort_issue_analysis.outcome == 'success' && steps.gemini_effort_issue_analysis.outputs.summary != '[]' && steps.gemini_effort_issue_analysis.outputs.summary != '') )
         env:
-          REPOSITORY: '${{ github.repository }}'
-          LABELS_OUTPUT: '${{ steps.gemini_issue_analysis.outputs.summary }}'
+          LABELS_OUTPUT_STANDARD: '${{ steps.gemini_standard_issue_analysis.outputs.summary }}'
+          LABELS_OUTPUT_EFFORT: '${{ steps.gemini_effort_issue_analysis.outputs.summary }}'
         uses: 'actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea'
         with:
           github-token: '${{ steps.generate_token.outputs.token }}'
@@ -304,9 +439,12 @@ jobs:
           GITHUB_REPOSITORY: '${{ github.repository }}'
         run: |-
           set -euo pipefail
-          echo '🧹 Finding issues that have both bot-triaged and need-triage labels...'
+          echo '🧹 Finding issues that have conflicting status labels...'
           gh issue list --repo "${GITHUB_REPOSITORY}" \
-            --search 'is:open is:issue label:status/bot-triaged label:status/need-triage' --limit 50 --json number > issues_to_cleanup.json
+            --search 'is:open is:issue label:status/bot-triaged label:status/need-triage' --limit 50 --json number > cleanup_1.json
+          gh issue list --repo "${GITHUB_REPOSITORY}" \
+            --search 'is:open is:issue label:status/bot-triaged label:status/manual-triage' --limit 50 --json number > cleanup_2.json
+          jq -c -s 'add | unique_by(.number)' cleanup_1.json cleanup_2.json > issues_to_cleanup.json
 
       - name: 'Clean Up Triage Labels'
         if: |-

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

@@ -21,6 +21,8 @@ jobs:
     steps:
       - name: 'Checkout'
         uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
+        with:
+          persist-credentials: false
 
       - name: 'Generate GitHub App Token'
         id: 'generate_token'

.github/workflows/label-backlog-child-issues.yml

@@ -19,6 +19,8 @@ jobs:
     steps:
       - name: 'Checkout'
         uses: 'actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5' # ratchet:actions/checkout@v4
+        with:
+          persist-credentials: false
 
       - name: 'Setup Node.js'
         uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions/setup-node@v4
@@ -41,6 +43,8 @@ jobs:
     steps:
       - name: 'Checkout'
         uses: 'actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5' # ratchet:actions/checkout@v4
+        with:
+          persist-credentials: false
 
       - name: 'Setup Node.js'
         uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions/setup-node@v4

.github/workflows/links.yml

@@ -17,6 +17,8 @@ jobs:
     runs-on: 'ubuntu-latest'
     steps:
       - uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
+        with:
+          persist-credentials: false
 
       - name: 'Link Checker'
         id: 'lychee'

.github/workflows/memory-nightly.yml

@@ -16,6 +16,8 @@ jobs:
     steps:
       - name: 'Checkout'
         uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
+        with:
+          persist-credentials: false
 
       - name: 'Set up Node.js'
         uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions/setup-node@v4

.github/workflows/perf-nightly.yml

@@ -16,6 +16,8 @@ jobs:
     steps:
       - name: 'Checkout'
         uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
+        with:
+          persist-credentials: false
 
       - name: 'Set up Node.js'
         uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions/setup-node@v4

.github/workflows/release-change-tags.yml

@@ -44,6 +44,7 @@ jobs:
         with:
           ref: '${{ github.ref }}'
           fetch-depth: 0
+          persist-credentials: false
 
       - name: 'Setup Node.js'
         uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020'

.github/workflows/release-manual.yml

@@ -65,11 +65,13 @@ jobs:
       - name: 'Checkout'
         uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8'
         with:
+          persist-credentials: false
           fetch-depth: 0
 
       - name: 'Checkout Release Code'
         uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8'
         with:
+          persist-credentials: false
           ref: '${{ github.event.inputs.ref }}'
           path: 'release'
           fetch-depth: 0

.github/workflows/release-nightly.yml

@@ -50,11 +50,13 @@ jobs:
       - name: 'Checkout'
         uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8'
         with:
+          persist-credentials: false
           fetch-depth: 0
 
       - name: 'Checkout Release Code'
         uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8'
         with:
+          persist-credentials: false
           ref: '${{ github.event.inputs.ref }}'
           path: 'release'
           fetch-depth: 0

.github/workflows/release-notes.yml

@@ -31,6 +31,7 @@ jobs:
       - name: 'Checkout repository'
         uses: 'actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5' # ratchet:actions/checkout@v4
         with:
+          persist-credentials: false
           # The user-level skills need to be available to the workflow
           fetch-depth: 0
           ref: 'main'

.github/workflows/release-patch-0-from-comment.yml

@@ -17,6 +17,7 @@ jobs:
       - name: 'Checkout'
         uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8'
         with:
+          persist-credentials: false
           fetch-depth: 1
 
       - name: 'Slash Command Dispatch'

.github/workflows/release-patch-1-create-pr.yml

@@ -54,6 +54,7 @@ jobs:
         with:
           ref: '${{ github.event.inputs.ref }}'
           fetch-depth: 0
+          persist-credentials: false
 
       - name: 'Setup Node.js'
         uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions/setup-node@v4

.github/workflows/release-patch-2-trigger.yml

@@ -64,6 +64,7 @@ jobs:
       - name: 'Checkout'
         uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8'
         with:
+          persist-credentials: false
           ref: "${{ github.event.inputs.workflow_ref || 'main' }}"
           fetch-depth: 1
 

.github/workflows/release-patch-3-release.yml

@@ -53,12 +53,14 @@ jobs:
       - name: 'Checkout'
         uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8'
         with:
+          persist-credentials: false
           fetch-depth: 0
           fetch-tags: true
 
       - name: 'Checkout Release Code'
         uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8'
         with:
+          persist-credentials: false
           ref: '${{ github.event.inputs.release_ref }}'
           path: 'release'
           fetch-depth: 0

.github/workflows/release-promote.yml

@@ -55,6 +55,7 @@ jobs:
       - name: 'Checkout'
         uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8'
         with:
+          persist-credentials: false
           fetch-depth: 0
           fetch-tags: true
 
@@ -171,11 +172,13 @@ jobs:
       - name: 'Checkout Ref'
         uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8'
         with:
+          persist-credentials: false
           ref: '${{ github.event.inputs.ref }}'
 
       - name: 'Checkout correct SHA'
         uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8'
         with:
+          persist-credentials: false
           ref: '${{ matrix.sha }}'
           path: 'release'
           fetch-depth: 0
@@ -216,11 +219,13 @@ jobs:
       - name: 'Checkout Ref'
         uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8'
         with:
+          persist-credentials: false
           ref: '${{ github.event.inputs.ref }}'
 
       - name: 'Checkout correct SHA'
         uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8'
         with:
+          persist-credentials: false
           ref: '${{ needs.calculate-versions.outputs.PREVIEW_SHA }}'
           path: 'release'
           fetch-depth: 0
@@ -288,11 +293,13 @@ jobs:
       - name: 'Checkout Ref'
         uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8'
         with:
+          persist-credentials: false
           ref: '${{ github.event.inputs.ref }}'
 
       - name: 'Checkout correct SHA'
         uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8'
         with:
+          persist-credentials: false
           ref: '${{ needs.calculate-versions.outputs.STABLE_SHA }}'
           path: 'release'
           fetch-depth: 0
@@ -360,6 +367,7 @@ jobs:
       - name: 'Checkout Ref'
         uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8'
         with:
+          persist-credentials: false
           ref: '${{ github.event.inputs.ref }}'
 
       - name: 'Setup Node.js'
@@ -395,6 +403,7 @@ jobs:
           BRANCH_NAME: '${{ steps.release_branch.outputs.BRANCH_NAME }}'
           DRY_RUN: '${{ github.event.inputs.dry_run }}'
           NEEDS_CALCULATE_VERSIONS_OUTPUTS_NEXT_NIGHTLY_VERSION: '${{ needs.calculate-versions.outputs.NEXT_NIGHTLY_VERSION }}'
+          GIT_PUSH_TOKEN: '${{ secrets.GEMINI_CLI_ROBOT_GITHUB_PAT }}'
         run: |-
           git add package.json packages/*/package.json
           if [ -f package-lock.json ]; then
@@ -403,7 +412,7 @@ jobs:
           git commit -m "chore(release): bump version to ${NEEDS_CALCULATE_VERSIONS_OUTPUTS_NEXT_NIGHTLY_VERSION}"
           if [[ "${DRY_RUN}" == "false" ]]; then
             echo "Pushing release branch to remote..."
-            git push --set-upstream origin "${BRANCH_NAME}"
+            git push "https://x-access-token:${GIT_PUSH_TOKEN}@github.com/${{ github.repository }}.git" "HEAD:${BRANCH_NAME}" --follow-tags
           else
             echo "Dry run enabled. Skipping push."
           fi

.github/workflows/release-rollback.yml

@@ -52,6 +52,7 @@ jobs:
       - name: 'Checkout repository'
         uses: 'actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955' # ratchet:actions/checkout@v4
         with:
+          persist-credentials: false
           ref: '${{ github.event.inputs.ref }}'
           fetch-depth: 0
 
@@ -192,7 +193,7 @@ jobs:
         run: |
           echo "ROLLBACK_TAG=$ROLLBACK_TAG_NAME" >> "$GITHUB_OUTPUT"
           git tag "$ROLLBACK_TAG_NAME" "${ORIGIN_HASH}"
-          git push origin --tags
+          git push "https://x-access-token:${GITHUB_TOKEN}@github.com/${{ github.repository }}.git" --tags
 
       - name: 'Verify Rollback Tag Added'
         if: "${{ github.event.inputs.dry-run == 'false' }}"

.github/workflows/release-sandbox.yml

@@ -26,6 +26,7 @@ jobs:
       - name: 'Checkout'
         uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8'
         with:
+          persist-credentials: false
           ref: '${{ github.event.inputs.ref || github.sha }}'
           fetch-depth: 0
       - name: 'Push'

.github/workflows/smoke-test.yml

@@ -32,6 +32,7 @@ jobs:
         with:
           ref: '${{ github.event.inputs.ref || github.sha }}'
           fetch-depth: 0
+          persist-credentials: false
       - name: 'Install Dependencies'
         run: 'npm ci'
       - name: 'Build bundle'

.github/workflows/test-build-binary.yml

@@ -34,6 +34,8 @@ jobs:
     steps:
       - name: 'Checkout'
         uses: 'actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5' # ratchet:actions/checkout@v4
+        with:
+          persist-credentials: false
 
       - name: 'Optimize Windows Performance'
         if: "matrix.os == 'windows-latest'"

.github/workflows/verify-release.yml

@@ -44,6 +44,8 @@ jobs:
         shell: 'bash'
         run: 'echo "${{ toJSON(vars) }}"'
       - uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8'
+        with:
+          persist-credentials: false
       - name: 'Verify release'
         uses: './.github/actions/verify-release'
         with:

.gitignore

@@ -68,3 +68,4 @@ temp_agents/
 
 # conductor extension and planning directories
 conductor/
+simulator_workspace_*

.prettierignore

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

.vscode/launch.json

@@ -43,9 +43,13 @@
     {
       "type": "node",
       "request": "launch",
-      "name": "Launch Program",
+      "name": "CLI: Run Current File",
+      "runtimeExecutable": "node",
+      "runtimeArgs": ["--import", "tsx"],
       "skipFiles": ["<node_internals>/**"],
       "program": "${file}",
+      "cwd": "${workspaceFolder}",
+      "console": "integratedTerminal",
       "outFiles": ["${workspaceFolder}/**/*.js"]
     },
     {

USER_SIMULATION_DOCKER.md

@@ -0,0 +1,111 @@
+# Running User Simulation in Docker with External Knowledge Source
+
+This guide explains how to run the User Simulator in a Docker environment while
+mounting an external knowledge base. This setup allows the simulator to "learn"
+from its interactions and persist that knowledge back to your host machine.
+
+We have provided an automated script that handles the entire setup, execution,
+and cleanup process.
+
+## Prerequisites
+
+- **Docker** installed and running.
+- **Gemini API Key** (standard `AIza...` key).
+- Local checkout of the `gemini-cli` repository.
+
+## Execution via Automation Script (Recommended)
+
+The easiest and most reliable way to run the simulation is using the provided
+bash script. This script automatically:
+
+1. Creates a uniquely timestamped workspace folder on your host.
+2. Generates a global `settings.json` file to natively bypass the CLI's
+   interactive Folder Trust and Authentication dialogs.
+3. Builds the sandbox image from your current branch.
+4. Mounts the workspace and runs the container with `--init` to gracefully
+   handle termination (e.g., `Ctrl+C`).
+
+### Running the Script
+
+Ensure your API key is exported:
+
+```bash
+export GEMINI_API_KEY="AIzaSy..."
+```
+
+Run the script from the root of the repository:
+
+```bash
+# Uses the default prompt ("make a snake game in python")
+./scripts/run_simulator_docker.sh
+
+# Or, provide a custom prompt:
+./scripts/run_simulator_docker.sh "create a simple react counter component"
+```
+
+## Manual Execution Breakdown
+
+If you need to run the simulation manually, here is exactly what the automated
+script does under the hood:
+
+### 1. Prepare Workspace & Knowledge Source
+
+```bash
+WORKSPACE_DIR="/tmp/gemini_docker_workspace"
+mkdir -p "$WORKSPACE_DIR"
+touch "$WORKSPACE_DIR/knowledge.md"
+chmod -R 777 "$WORKSPACE_DIR"
+```
+
+### 2. Bypass Interactive Startup Dialogs
+
+To prevent the simulator from getting stuck on the initial Auth or Folder Trust
+screens, generate a global `settings.json` file.
+
+```bash
+mkdir -p "$WORKSPACE_DIR/.gemini"
+echo '{
+  "security": {
+    "auth": { "selectedType": "gemini-api-key" },
+    "folderTrust": { "enabled": false }
+  }
+}' > "$WORKSPACE_DIR/.gemini/settings.json"
+chmod 777 "$WORKSPACE_DIR/.gemini/settings.json"
+```
+
+### 3. Build the Image
+
+```bash
+GEMINI_SANDBOX=docker npm run build:sandbox -- -i gemini-cli-simulator:latest
+```
+
+### 4. Run the Container
+
+Notice the `--init` flag (for `Ctrl+C` support) and the explicit mount mapping
+the `settings.json` file into `/home/node/.gemini/` inside the container.
+
+```bash
+docker run -it --rm --init \
+  -v "$WORKSPACE_DIR:/workspace" \
+  -v "$WORKSPACE_DIR/.gemini/settings.json:/home/node/.gemini/settings.json" \
+  -w /workspace \
+  -e GEMINI_API_KEY="$GEMINI_API_KEY" \
+  -e GEMINI_DEBUG_LOG_FILE="/workspace/debug.log" \
+  gemini-cli-simulator:latest \
+  gemini --prompt-interactive "make a snake game in python" \
+  --approval-mode plan \
+  --simulate-user \
+  --knowledge-source "/workspace/knowledge.md"
+```
+
+## Verification
+
+Once the simulation completes, verify the results in your workspace folder:
+
+1. **Generated Code:** Check for project files (e.g., `snake.py`).
+2. **Persistent Knowledge:** Check `knowledge.md`. You should see new rules
+   dynamically appended by the simulator.
+3. **Logs:**
+   - `debug.log`: Detailed internal LLM decision logic.
+   - `interactions_<timestamp>.txt`: Raw screen scrape frames seen by the
+     simulator's "eyes".

docs/changelogs/index.md

@@ -18,6 +18,37 @@ 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
+  canonical-patch contract for seamless skill management
+  ([#26338](https://github.com/google-gemini/gemini-cli/pull/26338) by
+  @SandyTao520).
+- **Gemma 4 by Default:** Enabled Gemma 4 models by default via the Gemini API
+  for all users
+  ([#26307](https://github.com/google-gemini/gemini-cli/pull/26307) by
+  @Abhijit-2592).
+- **Voice Mode Enhancements:** Added wave animations and privacy/compliance UX
+  warnings for the Gemini Live backend
+  ([#26284](https://github.com/google-gemini/gemini-cli/pull/26284) by
+  @devr0306, [#26454](https://github.com/google-gemini/gemini-cli/pull/26454) by
+  @cocosheng-g).
+
 ## Announcements: v0.41.0 - 2026-05-05
 
 - **Real-time Voice Mode:** Implemented real-time voice mode with cloud and

docs/changelogs/latest.md

@@ -1,6 +1,6 @@
-# Latest stable release: v0.41.0
+# Latest stable release: v0.43.0
 
-Released: May 05, 2026
+Released: May 22, 2026
 
 For most users, our latest stable release is the recommended release. Install
 the latest stable version with:
@@ -11,119 +11,208 @@ npm install -g @google/gemini-cli
 
 ## Highlights
 
-- **Real-time Voice Mode:** Introduced support for real-time voice interaction
-  with both cloud-based and local processing backends.
-- **Enhanced Security:** Implemented mandatory workspace trust for headless
-  environments and secured the loading of `.env` configuration files.
-- **Advanced Shell Validation:** Added a robust shell command validation layer
-  and a core tools allowlist to prevent unauthorized execution.
-- **Improved Context Management:** Integrated a new `ContextManager` and
-  `AgentChatHistory` to provide more reliable and efficient session handling.
-- **Auto-Memory Persistence:** Enabled the persistence of the auto-memory
-  scratchpad, allowing for seamless skill extraction across turns.
+- **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
 
-- chore(release): bump version to 0.41.0-nightly.20260423.gaa05b4583 by
-  @gemini-cli-robot in
-  [#25847](https://github.com/google-gemini/gemini-cli/pull/25847)
-- fix(core): only show `list` suggestion if the partial input is empty by
-  @cynthialong0-0 in
-  [#25821](https://github.com/google-gemini/gemini-cli/pull/25821)
-- feat(cli): secure .env loading and enforce workspace trust in headless mode by
-  @ehedlund in [#25814](https://github.com/google-gemini/gemini-cli/pull/25814)
-- fix: fatal hard-crash on loop detection via unhandled AbortError by @hsm207 in
-  [#20108](https://github.com/google-gemini/gemini-cli/pull/20108)
-- update package-lock.json by @ehedlund in
-  [#25876](https://github.com/google-gemini/gemini-cli/pull/25876)
-- feat(core): enhance shell command validation and add core tools allowlist by
-  @galz10 in [#25720](https://github.com/google-gemini/gemini-cli/pull/25720)
-- fix(ui): corrected background color check in user message components by
-  @devr0306 in [#25880](https://github.com/google-gemini/gemini-cli/pull/25880)
-- perf(core): fix slow boot by fetching experiments and quota asynchronously by
-  @spencer426 in
-  [#25758](https://github.com/google-gemini/gemini-cli/pull/25758)
-- feat(core,cli): add support for Gemma 4 models (experimental) by @Abhijit-2592
-  in [#25604](https://github.com/google-gemini/gemini-cli/pull/25604)
-- update FatalUntrustedWorkspaceError message to include doc link by @ehedlund
-  in [#25874](https://github.com/google-gemini/gemini-cli/pull/25874)
-- docs: add Gemini CLI course link to README by @JayadityaGit in
-  [#25925](https://github.com/google-gemini/gemini-cli/pull/25925)
-- feat(repo): add gemini-cli-bot metrics and workflows by @gundermanc in
-  [#25888](https://github.com/google-gemini/gemini-cli/pull/25888)
-- fix(cli): allow output redirection for cli commands by @spencer426 in
-  [#25894](https://github.com/google-gemini/gemini-cli/pull/25894)
-- fix(core): fail closed in YOLO mode when shell parsing fails for restricted
-  rules by @ehedlund in
-  [#25935](https://github.com/google-gemini/gemini-cli/pull/25935)
-- fix(cli-ui): revert backspace handling to fix Windows regression by @scidomino
-  in [#25941](https://github.com/google-gemini/gemini-cli/pull/25941)
-- feat(voice): implement real-time voice mode with cloud and local backends by
+- feat(core): steer model to use edit tool for surgical edits, fix a typo by
+  @aishaneeshah in
+  [#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
-  [#24174](https://github.com/google-gemini/gemini-cli/pull/24174)
-- Changelog for v0.39.0 by @gemini-cli-robot in
-  [#25848](https://github.com/google-gemini/gemini-cli/pull/25848)
-- feat(memory): persist auto-memory scratchpad for skill extraction by
-  @SandyTao520 in
-  [#25873](https://github.com/google-gemini/gemini-cli/pull/25873)
-- fix(cli): add missing response key to custom theme text schema by @gaurav0107
-  in [#25822](https://github.com/google-gemini/gemini-cli/pull/25822)
-- fix(cli): provide manual update command when automatic update fails by
+  [#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
-  [#26052](https://github.com/google-gemini/gemini-cli/pull/26052)
-- test(cli): add unit tests for restore ACP command (#23402) by @cocosheng-g in
-  [#26053](https://github.com/google-gemini/gemini-cli/pull/26053)
-- fix(ui): better error messages for ECONNRESET and ETIMEDOUT by @devr0306 in
-  [#26059](https://github.com/google-gemini/gemini-cli/pull/26059)
-- feat(core): wire up the new ContextManager and AgentChatHistory by @joshualitt
-  in [#25409](https://github.com/google-gemini/gemini-cli/pull/25409)
-- fix(cli): ensure sandbox proxy cleanup and remove handler leaks by @ehedlund
-  in [#26065](https://github.com/google-gemini/gemini-cli/pull/26065)
-- fix(cli): correct alternate buffer warning logic for JetBrains by @Adib234 in
-  [#26067](https://github.com/google-gemini/gemini-cli/pull/26067)
-- fix(cli): make MCP ping optional in list command and use configured timeout by
+  [#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
-  [#26068](https://github.com/google-gemini/gemini-cli/pull/26068)
-- fix(core): better error message for failed cloudshell-gca auth by @devr0306 in
-  [#26079](https://github.com/google-gemini/gemini-cli/pull/26079)
-- feat(cli): provide manual session UUID via command line arg by @cocosheng-g in
-  [#26060](https://github.com/google-gemini/gemini-cli/pull/26060)
-- Changelog for v0.40.0-preview.2 by @gemini-cli-robot in
-  [#25846](https://github.com/google-gemini/gemini-cli/pull/25846)
-- (docs) update sandboxing documentation by @g-samroberts in
-  [#25930](https://github.com/google-gemini/gemini-cli/pull/25930)
-- fix(core): enforce parallel task tracker updates by @anj-s in
-  [#24477](https://github.com/google-gemini/gemini-cli/pull/24477)
-- Update policy so transient errors are not marked terminal by @DavidAPierce in
-  [#26066](https://github.com/google-gemini/gemini-cli/pull/26066)
-- Implement bot that performs time-series metric analysis and suggests repo
-  management improvements by @gundermanc in
-  [#25945](https://github.com/google-gemini/gemini-cli/pull/25945)
-- fix(core): handle non-string model flags in resolution by @Adib234 in
-  [#26069](https://github.com/google-gemini/gemini-cli/pull/26069)
-- fix(ux): added error message for ENOTDIR by @devr0306 in
-  [#26128](https://github.com/google-gemini/gemini-cli/pull/26128)
-- Changelog for v0.40.0-preview.3 by @gemini-cli-robot in
-  [#25904](https://github.com/google-gemini/gemini-cli/pull/25904)
-- fix(cli): prevent ACP stdout pollution from SessionEnd hooks by @cocosheng-g
-  in [#26125](https://github.com/google-gemini/gemini-cli/pull/26125)
-- feat(cli): support boolean and number casting for env vars in settings.json by
+  [#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
-  [#26118](https://github.com/google-gemini/gemini-cli/pull/26118)
-- fix(cli): preserve Request headers in DevTools activity logger by @Adib234 in
-  [#26078](https://github.com/google-gemini/gemini-cli/pull/26078)
-- fix(patch): cherry-pick 2194da2 to release/v0.41.0-preview.0-pr-26153 to patch
-  version v0.41.0-preview.0 and create version 0.41.0-preview.1 by
-  @gemini-cli-robot in
-  [#26269](https://github.com/google-gemini/gemini-cli/pull/26269)
-- fix(patch): cherry-pick 1d72a12 to release/v0.41.0-preview.1-pr-26479 to patch
-  version v0.41.0-preview.1 and create version 0.41.0-preview.2 by
-  @gemini-cli-robot in
-  [#26508](https://github.com/google-gemini/gemini-cli/pull/26508)
-- fix(patch): cherry-pick 7cc19c2 to release/v0.41.0-preview.2-pr-26507 to patch
-  version v0.41.0-preview.2 and create version 0.41.0-preview.3 by
-  @gemini-cli-robot in
-  [#26530](https://github.com/google-gemini/gemini-cli/pull/26530)
+  [#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/v0.40.1...v0.41.0
+https://github.com/google-gemini/gemini-cli/compare/v0.42.0...v0.43.0

docs/changelogs/preview.md

@@ -1,6 +1,6 @@
-# Preview release: v0.42.0-preview.2
+# Preview release: v0.44.0-preview.0
 
-Released: May 06, 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).
@@ -13,233 +13,208 @@ npm install -g @google/gemini-cli@preview
 
 ## Highlights
 
-- **Auto Memory Enhancements:** Introduced an Auto Memory inbox flow with a
-  canonical-patch contract for better memory management.
-- **Improved Voice Mode:** Added a wave animation, microphone icon updates, and
-  privacy/compliance UX warnings for the Gemini Live backend.
-- **New CLI Commands & Flags:** Added a `--delete` flag to the `/exit` command
-  for session deletion, a `list` subcommand to `/commands`, and a `/bug-memory`
-  command for heap snapshots.
-- **Expanded Model Support:** Gemma 4 models are now enabled by default via the
-  Gemini API.
-- **Enhanced Core Resilience:** Improved API resilience with reduced timeouts,
-  automatic retries for stream errors, and better handling of invalid stream
-  events.
+- **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
 
-- fix(cli): prevent automatic updates from switching to less stable channels in
-  [#26132](https://github.com/google-gemini/gemini-cli/pull/26132)
-- chore(release): bump version to 0.42.0-nightly.20260428.g59b2dea0e in
-  [#26142](https://github.com/google-gemini/gemini-cli/pull/26142)
-- fix(cli): pass node arguments via NODE_OPTIONS during relaunch to support SEA
-  in [#26130](https://github.com/google-gemini/gemini-cli/pull/26130)
-- fix(cli): handle DECKPAM keypad Enter sequences in terminal in
-  [#26092](https://github.com/google-gemini/gemini-cli/pull/26092)
-- docs(cli): point plan-mode session retention to actual /settings labels in
-  [#25978](https://github.com/google-gemini/gemini-cli/pull/25978)
-- fix(core): add missing oauth fields support in subagent parsing in
-  [#26141](https://github.com/google-gemini/gemini-cli/pull/26141)
-- fix(core): disconnect extension-backed MCP clients in stopExtension in
-  [#26136](https://github.com/google-gemini/gemini-cli/pull/26136)
-- Update documentation workflows with workspace trust in
-  [#26150](https://github.com/google-gemini/gemini-cli/pull/26150)
-- refactor(acp): modularize monolithic acpClient into specialized files in
-  [#26143](https://github.com/google-gemini/gemini-cli/pull/26143)
-- test: fix failures due to antigravity environment leakage in
-  [#26162](https://github.com/google-gemini/gemini-cli/pull/26162)
-- fix(core): add explicit empty log guard in A2A pushMessage in
-  [#26198](https://github.com/google-gemini/gemini-cli/pull/26198)
-- feat(cli): add --delete flag to /exit command for session deletion in
-  [#19332](https://github.com/google-gemini/gemini-cli/pull/19332)
-- test(core): add regression test for issue for ToolConfirmationResponse in
-  [#26194](https://github.com/google-gemini/gemini-cli/pull/26194)
-- Add the ability to @ mention the gemini robot. in
-  [#26207](https://github.com/google-gemini/gemini-cli/pull/26207)
-- test(evals): add EvalMetadata JSDoc annotations to older tests 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 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 in
-  [#26163](https://github.com/google-gemini/gemini-cli/pull/26163)
-- fix(cli): handle InvalidStream event gracefully without throwing in
-  [#26218](https://github.com/google-gemini/gemini-cli/pull/26218)
-- ci(github-actions): switch to github app token and fix bot self-trigger in
-  [#26223](https://github.com/google-gemini/gemini-cli/pull/26223)
-- Respect logPrompts flag for logging sensitive fields in
-  [#26153](https://github.com/google-gemini/gemini-cli/pull/26153)
-- fix: correct API key validation logic in handleApiKeySubmit in
-  [#25453](https://github.com/google-gemini/gemini-cli/pull/25453)
-- fix(agent): prevent exit_plan_mode from being called via shell in
-  [#26230](https://github.com/google-gemini/gemini-cli/pull/26230)
-- # Fix: Inconsistent Case-Sensitivity in GrepTool in [#26235](https://github.com/google-gemini/gemini-cli/pull/26235)
-- docs(core): add automated gemma setup guide in
-  [#26233](https://github.com/google-gemini/gemini-cli/pull/26233)
-- Allow non-https proxy urls to support container environments in
-  [#26234](https://github.com/google-gemini/gemini-cli/pull/26234)
-- fix(bot): productivity and backlog optimizations in
-  [#26236](https://github.com/google-gemini/gemini-cli/pull/26236)
-- refactor(acp): delegate prompt turn processing logic to GeminiClient in
-  [#26222](https://github.com/google-gemini/gemini-cli/pull/26222)
-- fix(cli): refine platform-specific undo/redo and smart bubbling for WSL in
-  [#26202](https://github.com/google-gemini/gemini-cli/pull/26202)
-- fix: suppress duplicate extension warnings during startup in
-  [#26208](https://github.com/google-gemini/gemini-cli/pull/26208)
-- fix(cli): use byte length instead of string length for readStdin size limits
-  in [#26224](https://github.com/google-gemini/gemini-cli/pull/26224)
-- fix(ui): made shell tool header wrap on Ctrl+O in
-  [#26229](https://github.com/google-gemini/gemini-cli/pull/26229)
-- Changelog for v0.41.0-preview.0 in
-  [#26244](https://github.com/google-gemini/gemini-cli/pull/26244)
-- Skip binary CLI relaunch 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 in [#24455](https://github.com/google-gemini/gemini-cli/pull/24455)
-- docs(cli): add skill discovery troubleshooting checklist to tutorial in
-  [#26018](https://github.com/google-gemini/gemini-cli/pull/26018)
-- docs(policy-engine): link to tools reference for tool names and args in
-  [#22081](https://github.com/google-gemini/gemini-cli/pull/22081)
-- Fix posting invalid response to a comment in
-  [#26266](https://github.com/google-gemini/gemini-cli/pull/26266)
-- fix(cli): prevent informational logs from polluting json output in
-  [#26264](https://github.com/google-gemini/gemini-cli/pull/26264)
-- feat(ui): added microphone and updated placeholder for voice mode in
-  [#26270](https://github.com/google-gemini/gemini-cli/pull/26270)
-- feat(cli): Add 'list' subcommand to '/commands' in
-  [#22324](https://github.com/google-gemini/gemini-cli/pull/22324)
-- fix(core): ensure tool output cleanup on session deletion for legacy files in
-  [#26263](https://github.com/google-gemini/gemini-cli/pull/26263)
-- Docs: Update Agent Skills documentation in
-  [#22388](https://github.com/google-gemini/gemini-cli/pull/22388)
-- test(acp): add missing coverage for extensions command error paths in
-  [#25313](https://github.com/google-gemini/gemini-cli/pull/25313)
-- Changelog for v0.40.0 in
-  [#26245](https://github.com/google-gemini/gemini-cli/pull/26245)
-- fix: report AgentExecutionBlocked in non-interactive programmatic modes in
-  [#26262](https://github.com/google-gemini/gemini-cli/pull/26262)
-- feat(extensions): add 'delete' as an alias for /extensions uninstall in
-  [#25660](https://github.com/google-gemini/gemini-cli/pull/25660)
-- fix(core): silently skip GEMINI.md paths that are directories (EISDIR) in
-  [#25662](https://github.com/google-gemini/gemini-cli/pull/25662)
-- fix(ci): checkout PR branch instead of main in bot workflow in
-  [#26289](https://github.com/google-gemini/gemini-cli/pull/26289)
-- fix(cli): use resolved sandbox state for auto-update check in
-  [#26285](https://github.com/google-gemini/gemini-cli/pull/26285)
-- # Metrics Integrity & Standardized Reporting (BT-01) in [#26240](https://github.com/google-gemini/gemini-cli/pull/26240)
-- Add Star History section to README in
-  [#26290](https://github.com/google-gemini/gemini-cli/pull/26290)
-- Add Star History section to README in
-  [#26308](https://github.com/google-gemini/gemini-cli/pull/26308)
-- Remove Star History section from README in
-  [#26309](https://github.com/google-gemini/gemini-cli/pull/26309)
-- test(evals): add behavioral eval for file creation and write_file tool
-  selection in [#26292](https://github.com/google-gemini/gemini-cli/pull/26292)
-- feat(config): enable Gemma 4 models by default via Gemini API in
-  [#26307](https://github.com/google-gemini/gemini-cli/pull/26307)
-- fix(cli): insert voice transcription at cursor position instead of ap… in
-  [#26287](https://github.com/google-gemini/gemini-cli/pull/26287)
-- fix(ui): fix issue with box edges in
-  [#26148](https://github.com/google-gemini/gemini-cli/pull/26148)
-- fix(cli): respect .env override for GOOGLE_CLOUD_PROJECT in
-  [#26288](https://github.com/google-gemini/gemini-cli/pull/26288)
-- fix(ci): robust version checking in release verification in
-  [#26337](https://github.com/google-gemini/gemini-cli/pull/26337)
-- fix(cli): enable daemon relaunch in binary and bundle keytar in
-  [#26333](https://github.com/google-gemini/gemini-cli/pull/26333)
-- fix(core): discourage unprompted git add . in prompt snippets in
-  [#26220](https://github.com/google-gemini/gemini-cli/pull/26220)
-- feat(ui): added wave animation for voice mode in
-  [#26284](https://github.com/google-gemini/gemini-cli/pull/26284)
-- fix(cli): prevent Escape from clearing input buffer (#17083) in
-  [#26339](https://github.com/google-gemini/gemini-cli/pull/26339)
-- fix(cli): undeprecate --prompt and correct positional query docs in
-  [#26329](https://github.com/google-gemini/gemini-cli/pull/26329)
-- Metrics updates in
-  [#26348](https://github.com/google-gemini/gemini-cli/pull/26348)
-- fix(core): remove "System: Please continue." injection on InvalidStream events
-  in [#26340](https://github.com/google-gemini/gemini-cli/pull/26340)
-- docs(policy-engine): add tool argument keys reference and shell policy
-  cross-links in
-  [#25292](https://github.com/google-gemini/gemini-cli/pull/25292)
-- fix(cli): resolve Ghostty/raw-mode False Cancellation in oauth flow in
-  [#25026](https://github.com/google-gemini/gemini-cli/pull/25026)
-- fix(core): reset session-scoped state on resumption in
-  [#26342](https://github.com/google-gemini/gemini-cli/pull/26342)
-- Fix bulk of remaining issues with generalist profile in
-  [#26073](https://github.com/google-gemini/gemini-cli/pull/26073)
-- fix(core): make subagents aware of active approval modes in
-  [#23608](https://github.com/google-gemini/gemini-cli/pull/23608)
-- fix(acp): resolve agent mode disconnect and improve mode awareness in
-  [#26332](https://github.com/google-gemini/gemini-cli/pull/26332)
-- docs(sdk): add JSDoc to exported interfaces in packages/sdk/src/types.ts in
-  [#26441](https://github.com/google-gemini/gemini-cli/pull/26441)
-- perf: skip redundant GEMINI.md loading in partialConfig in
-  [#26443](https://github.com/google-gemini/gemini-cli/pull/26443)
-- Enhance React guidelines in
-  [#22667](https://github.com/google-gemini/gemini-cli/pull/22667)
-- feat(core): reinforce Inquiry constraints to prevent unauthorized changes in
-  [#26310](https://github.com/google-gemini/gemini-cli/pull/26310)
-- revert: fix(ci): robust version checking in release verification (#26337) in
-  [#26450](https://github.com/google-gemini/gemini-cli/pull/26450)
-- refactor(UI): created constants file for ThemeDialog in
-  [#26446](https://github.com/google-gemini/gemini-cli/pull/26446)
-- docs: fix GitHub capitalization in releases guide in
-  [#26379](https://github.com/google-gemini/gemini-cli/pull/26379)
-- fix(cli): ensure branch indicator updates in sub-directories and worktrees in
-  [#26330](https://github.com/google-gemini/gemini-cli/pull/26330)
-- feat: add minimal V8 heap snapshot utility for memory diagnostics in
-  [#26440](https://github.com/google-gemini/gemini-cli/pull/26440)
-- fix(hooks): preserve non-text parts in fromHookLLMRequest in
-  [#26275](https://github.com/google-gemini/gemini-cli/pull/26275)
-- fix(cli): allow early stdout when config is undefined in
-  [#26453](https://github.com/google-gemini/gemini-cli/pull/26453)
-- fix(cli)#21297: clear skills consent dialog before reload in
-  [#26431](https://github.com/google-gemini/gemini-cli/pull/26431)
-- fix(cli): render LaTeX-style output as Unicode in the TUI in
-  [#25802](https://github.com/google-gemini/gemini-cli/pull/25802)
-- fix(core): use close event instead of exit in child_process fallback in
-  [#25695](https://github.com/google-gemini/gemini-cli/pull/25695)
-- feat(voice): add privacy and compliance UX warning for Gemini Live backend in
-  [#26454](https://github.com/google-gemini/gemini-cli/pull/26454)
-- feat(memory): add Auto Memory inbox flow with canonical-patch contract in
-  [#26338](https://github.com/google-gemini/gemini-cli/pull/26338)
-- test(cleanup): fix temporary directory leaks in test suites in
-  [#26217](https://github.com/google-gemini/gemini-cli/pull/26217)
-- feat: add ignoreLocalEnv setting and --ignore-env flag (#2493) in
-  [#26445](https://github.com/google-gemini/gemini-cli/pull/26445)
-- docs(sdk): add JSDoc to all exported interfaces and types in
-  [#26277](https://github.com/google-gemini/gemini-cli/pull/26277)
-- feat(cli): improve /agents refresh logging in
-  [#26442](https://github.com/google-gemini/gemini-cli/pull/26442)
-- Fix: make Dockerfile self-contained with multi-stage build in
-  [#24277](https://github.com/google-gemini/gemini-cli/pull/24277)
-- fix(core): filter unsupported multimodal types from tool responses in
-  [#26352](https://github.com/google-gemini/gemini-cli/pull/26352)
-- fix(core): properly format markdown in AskUser tool by unescaping newlines in
-  [#26349](https://github.com/google-gemini/gemini-cli/pull/26349)
-- feat(bot): add actions spend metric script in
-  [#26463](https://github.com/google-gemini/gemini-cli/pull/26463)
-- feat(cli): add /bug-memory command and auto-capture heap snapshot in /bug in
-  [#25639](https://github.com/google-gemini/gemini-cli/pull/25639)
-- fix(cli): make SkillInboxDialog fit and scroll in alternate buffer in
-  [#26455](https://github.com/google-gemini/gemini-cli/pull/26455)
-- Robust Scale-Safe Lifecycle Consolidation in
-  [#26355](https://github.com/google-gemini/gemini-cli/pull/26355)
-- fix(ci): respect exempt labels when closing stale items in
-  [#26475](https://github.com/google-gemini/gemini-cli/pull/26475)
-- fix(cli): use os.homedir() for home directory warning check in
-  [#25890](https://github.com/google-gemini/gemini-cli/pull/25890)
-- fix(a2a-server): resolve tool approval race condition and improve status
-  reporting in [#26479](https://github.com/google-gemini/gemini-cli/pull/26479)
-- fix(cli): prevent settings dialog border clipping using maxHeight in
-  [#26507](https://github.com/google-gemini/gemini-cli/pull/26507)
-- feat: allow queuing messages during compression (#24071) in
-  [#26506](https://github.com/google-gemini/gemini-cli/pull/26506)
-- fix(core): retry on ERR_STREAM_PREMATURE_CLOSE errors in
-  [#26519](https://github.com/google-gemini/gemini-cli/pull/26519)
-- fix(core): Minor fixes for generalist profile. in
-  [#26357](https://github.com/google-gemini/gemini-cli/pull/26357)
+- 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/v0.41.0-preview.3...v0.42.0-preview.2
+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": {
@@ -563,6 +596,12 @@ their corresponding top-level category object in your `settings.json` file.
           "model": "gemini-2.5-flash-lite"
         }
       },
+      "gemini-3.1-flash-lite": {
+        "extends": "chat-base-3",
+        "modelConfig": {
+          "model": "gemini-3.1-flash-lite"
+        }
+      },
       "gemma-4-31b-it": {
         "extends": "chat-base-3",
         "modelConfig": {
@@ -590,7 +629,7 @@ their corresponding top-level category object in your `settings.json` file.
       "classifier": {
         "extends": "base",
         "modelConfig": {
-          "model": "gemini-2.5-flash-lite",
+          "model": "flash-lite",
           "generateContentConfig": {
             "maxOutputTokens": 1024,
             "thinkingConfig": {
@@ -602,7 +641,7 @@ their corresponding top-level category object in your `settings.json` file.
       "prompt-completion": {
         "extends": "base",
         "modelConfig": {
-          "model": "gemini-2.5-flash-lite",
+          "model": "flash-lite",
           "generateContentConfig": {
             "temperature": 0.3,
             "maxOutputTokens": 16000,
@@ -615,7 +654,7 @@ their corresponding top-level category object in your `settings.json` file.
       "fast-ack-helper": {
         "extends": "base",
         "modelConfig": {
-          "model": "gemini-2.5-flash-lite",
+          "model": "flash-lite",
           "generateContentConfig": {
             "temperature": 0.2,
             "maxOutputTokens": 120,
@@ -628,7 +667,7 @@ their corresponding top-level category object in your `settings.json` file.
       "edit-corrector": {
         "extends": "base",
         "modelConfig": {
-          "model": "gemini-2.5-flash-lite",
+          "model": "flash-lite",
           "generateContentConfig": {
             "thinkingConfig": {
               "thinkingBudget": 0
@@ -639,7 +678,7 @@ their corresponding top-level category object in your `settings.json` file.
       "summarizer-default": {
         "extends": "base",
         "modelConfig": {
-          "model": "gemini-2.5-flash-lite",
+          "model": "flash-lite",
           "generateContentConfig": {
             "maxOutputTokens": 2000
           }
@@ -648,7 +687,7 @@ their corresponding top-level category object in your `settings.json` file.
       "summarizer-shell": {
         "extends": "base",
         "modelConfig": {
-          "model": "gemini-2.5-flash-lite",
+          "model": "flash-lite",
           "generateContentConfig": {
             "maxOutputTokens": 2000
           }
@@ -725,7 +764,7 @@ their corresponding top-level category object in your `settings.json` file.
       },
       "chat-compression-3.1-flash-lite": {
         "modelConfig": {
-          "model": "gemini-3.1-flash-lite-preview"
+          "model": "gemini-3.1-flash-lite"
         }
       },
       "chat-compression-2.5-pro": {
@@ -779,10 +818,10 @@ their corresponding top-level category object in your `settings.json` file.
 
     ```json
     {
-      "gemini-3.1-flash-lite-preview": {
+      "gemini-3.1-flash-lite": {
         "tier": "flash-lite",
         "family": "gemini-3",
-        "isPreview": true,
+        "isPreview": false,
         "isVisible": true,
         "features": {
           "thinking": false,
@@ -882,9 +921,10 @@ their corresponding top-level category object in your `settings.json` file.
         }
       },
       "auto": {
+        "displayName": "Auto",
         "tier": "auto",
         "isPreview": true,
-        "isVisible": false,
+        "isVisible": true,
         "features": {
           "thinking": true,
           "multimodalToolUse": false
@@ -918,26 +958,16 @@ their corresponding top-level category object in your `settings.json` file.
         }
       },
       "auto-gemini-3": {
-        "displayName": "Auto (Gemini 3)",
         "tier": "auto",
+        "family": "gemini-3",
         "isPreview": true,
-        "isVisible": true,
-        "dialogDescription": "Let Gemini CLI decide the best model for the task: gemini-3-pro, gemini-3-flash",
-        "features": {
-          "thinking": true,
-          "multimodalToolUse": false
-        }
+        "isVisible": false
       },
       "auto-gemini-2.5": {
-        "displayName": "Auto (Gemini 2.5)",
         "tier": "auto",
+        "family": "gemini-2.5",
         "isPreview": false,
-        "isVisible": true,
-        "dialogDescription": "Let Gemini CLI decide the best model for the task: gemini-2.5-pro, gemini-2.5-flash",
-        "features": {
-          "thinking": false,
-          "multimodalToolUse": false
-        }
+        "isVisible": false
       }
     }
     ```
@@ -1020,30 +1050,6 @@ their corresponding top-level category object in your `settings.json` file.
           }
         ]
       },
-      "auto-gemini-3": {
-        "default": "gemini-3-pro-preview",
-        "contexts": [
-          {
-            "condition": {
-              "hasAccessToPreview": false
-            },
-            "target": "gemini-2.5-pro"
-          },
-          {
-            "condition": {
-              "useGemini3_1": true,
-              "useCustomTools": true
-            },
-            "target": "gemini-3.1-pro-preview-customtools"
-          },
-          {
-            "condition": {
-              "useGemini3_1": true
-            },
-            "target": "gemini-3.1-pro-preview"
-          }
-        ]
-      },
       "auto": {
         "default": "gemini-3-pro-preview",
         "contexts": [
@@ -1092,19 +1098,8 @@ their corresponding top-level category object in your `settings.json` file.
           }
         ]
       },
-      "auto-gemini-2.5": {
-        "default": "gemini-2.5-pro"
-      },
-      "gemini-3.1-flash-lite-preview": {
-        "default": "gemini-3.1-flash-lite-preview",
-        "contexts": [
-          {
-            "condition": {
-              "useGemini3_1FlashLite": false
-            },
-            "target": "gemini-2.5-flash-lite"
-          }
-        ]
+      "gemini-3.1-flash-lite": {
+        "default": "gemini-3.1-flash-lite"
       },
       "flash": {
         "default": "gemini-3-flash-preview",
@@ -1118,15 +1113,34 @@ their corresponding top-level category object in your `settings.json` file.
         ]
       },
       "flash-lite": {
-        "default": "gemini-2.5-flash-lite",
+        "default": "gemini-3.1-flash-lite"
+      },
+      "auto-gemini-3": {
+        "default": "gemini-3-pro-preview",
         "contexts": [
           {
             "condition": {
-              "useGemini3_1FlashLite": true
+              "hasAccessToPreview": false
             },
-            "target": "gemini-3.1-flash-lite-preview"
+            "target": "gemini-2.5-pro"
+          },
+          {
+            "condition": {
+              "useGemini3_1": true,
+              "useCustomTools": true
+            },
+            "target": "gemini-3.1-pro-preview-customtools"
+          },
+          {
+            "condition": {
+              "useGemini3_1": true
+            },
+            "target": "gemini-3.1-pro-preview"
           }
         ]
+      },
+      "auto-gemini-2.5": {
+        "default": "gemini-2.5-pro"
       }
     }
     ```
@@ -1145,15 +1159,15 @@ their corresponding top-level category object in your `settings.json` file.
         "contexts": [
           {
             "condition": {
-              "requestedModels": ["auto-gemini-2.5", "gemini-2.5-pro"]
+              "hasAccessToPreview": false
             },
             "target": "gemini-2.5-flash"
           },
           {
             "condition": {
-              "requestedModels": ["auto-gemini-3", "gemini-3-pro-preview"]
+              "requestedModels": ["gemini-2.5-pro", "auto-gemini-2.5"]
             },
-            "target": "gemini-3-flash-preview"
+            "target": "gemini-2.5-flash"
           }
         ]
       },
@@ -1162,7 +1176,13 @@ their corresponding top-level category object in your `settings.json` file.
         "contexts": [
           {
             "condition": {
-              "requestedModels": ["auto-gemini-2.5", "gemini-2.5-pro"]
+              "hasAccessToPreview": false
+            },
+            "target": "gemini-2.5-pro"
+          },
+          {
+            "condition": {
+              "requestedModels": ["gemini-2.5-pro", "auto-gemini-2.5"]
             },
             "target": "gemini-2.5-pro"
           },
@@ -1333,7 +1353,7 @@ their corresponding top-level category object in your `settings.json` file.
       ],
       "lite": [
         {
-          "model": "gemini-2.5-flash-lite",
+          "model": "flash-lite",
           "actions": {
             "terminal": "silent",
             "transient": "silent",
@@ -1821,6 +1841,12 @@ 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`
@@ -1857,13 +1883,6 @@ 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
@@ -1926,19 +1945,6 @@ 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.
@@ -1958,6 +1964,11 @@ 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 +1,287 @@
+/**
+ * @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',
+    { timeout: 300000 },
+    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');
+
+      // Ignore trace and response files to keep environment context clean and stable
+      fs.writeFileSync(
+        path.join(rig.testDir!, '.geminiignore'),
+        'traces/\nresp*.json\ndebug.log\n',
+      );
+
+      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,
+      );
+
+      // The environment context is intentionally refreshed on resume to reflect
+      // the current state of the workspace (e.g. new files, current date).
+      // We allow its content to differ but ensure it's still an environment context.
+      const isEnvContext = (turn: HistoryTurn) =>
+        turn.content.parts?.some((p) => p.text?.includes('<session_context>'));
+
+      for (let i = 0; i < contextBeforeExit!.length; i++) {
+        expect(contextAfterResume![i].id).toBe(contextBeforeExit![i].id);
+
+        const turnBefore = contextBeforeExit![i];
+        const turnAfter = contextAfterResume![i];
+
+        if (isEnvContext(turnBefore)) {
+          expect(isEnvContext(turnAfter)).toBe(true);
+          continue;
+        }
+
+        expect(turnAfter.content).toEqual(turnBefore.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 (with relaxation for environment context)
+      expect(syntheticTurnsAfter[0].id).toBe(syntheticTurns[0].id);
+      if (isEnvContext(syntheticTurns[0])) {
+        expect(isEnvContext(syntheticTurnsAfter[0])).toBe(true);
+      } else {
+        expect(syntheticTurnsAfter[0].content).toEqual(
+          syntheticTurns[0].content,
+        );
+      }
+    },
+  );
+});

integration-tests/file-system.test.ts

@@ -172,7 +172,7 @@ describe('file-system', () => {
     ).toBeDefined();
 
     const newFileContent = rig.readFile(fileName);
-    expect(newFileContent).toBe('1.0.1');
+    expect(newFileContent.trimEnd()).toBe('1.0.1');
   });
 
   it.skip('should replace multiple instances of a string', async () => {

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": "0.42.0-nightly.20260428.g59b2dea0e",
+  "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:0.42.0-nightly.20260428.g59b2dea0e"
+    "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": "0.42.0-nightly.20260428.g59b2dea0e",
+  "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": "0.42.0-nightly.20260428.g59b2dea0e",
+  "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:0.42.0-nightly.20260428.g59b2dea0e"
+    "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/acpFileSystemService.ts

@@ -60,8 +60,11 @@ export class AcpFileSystemService implements FileSystemService {
         sessionId: this.sessionId,
       });
 
-      // eslint-disable-next-line @typescript-eslint/no-unsafe-return
-      return response.content;
+      const content: unknown = response.content;
+      if (typeof content !== 'string') {
+        throw new Error('content must be a string'); // replace with other response type formats when modified in the future
+      }
+      return content;
     } catch (err: unknown) {
       this.normalizeFileSystemError(err);
     }

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

@@ -19,6 +19,7 @@ import type * as acp from '@agentclientprotocol/sdk';
 import {
   AuthType,
   type Config,
+  GEMINI_MODEL_ALIAS_AUTO,
   type MessageBus,
   type Storage,
 } from '@google/gemini-cli-core';
@@ -78,6 +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(),
@@ -208,20 +210,19 @@ describe('AcpSessionManager', () => {
     expect(response.models?.availableModels).toEqual(
       expect.arrayContaining([
         expect.objectContaining({
-          modelId: 'auto-gemini-3',
+          modelId: GEMINI_MODEL_ALIAS_AUTO,
           name: expect.stringContaining('Auto'),
         }),
       ]),
     );
   });
 
-  it('should include gemini-3.1-flash-lite when useGemini31FlashLite is true', async () => {
+  it('should NOT include retired preview models (none) in available models', async () => {
     mockConfig.getContentGeneratorConfig = vi.fn().mockReturnValue({
       apiKey: 'test-key',
     });
     mockConfig.getHasAccessToPreviewModel = vi.fn().mockReturnValue(true);
     mockConfig.getGemini31LaunchedSync = vi.fn().mockReturnValue(true);
-    mockConfig.getGemini31FlashLiteLaunchedSync = vi.fn().mockReturnValue(true);
 
     const response = await manager.newSession(
       {
@@ -231,14 +232,9 @@ describe('AcpSessionManager', () => {
       {},
     );
 
-    expect(response.models?.availableModels).toEqual(
-      expect.arrayContaining([
-        expect.objectContaining({
-          modelId: 'gemini-3.1-flash-lite-preview',
-          name: 'gemini-3.1-flash-lite-preview',
-        }),
-      ]),
-    );
+    const modelIds =
+      response.models?.availableModels?.map((m) => m.modelId) ?? [];
+    expect(modelIds).not.toContain('none');
   });
 
   it('should return modes with plan mode when plan is enabled', async () => {

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

@@ -10,8 +10,7 @@ import {
   type ToolCallConfirmationDetails,
   Kind,
   ApprovalMode,
-  DEFAULT_GEMINI_MODEL_AUTO,
-  PREVIEW_GEMINI_MODEL_AUTO,
+  GEMINI_MODEL_ALIAS_AUTO,
   DEFAULT_GEMINI_MODEL,
   DEFAULT_GEMINI_FLASH_MODEL,
   DEFAULT_GEMINI_FLASH_LITE_MODEL,
@@ -19,10 +18,11 @@ import {
   PREVIEW_GEMINI_MODEL,
   PREVIEW_GEMINI_3_1_CUSTOM_TOOLS_MODEL,
   PREVIEW_GEMINI_FLASH_MODEL,
-  PREVIEW_GEMINI_3_1_FLASH_LITE_MODEL,
+  PREVIEW_GEMINI_FLASH_LITE_MODEL,
   getDisplayString,
   AuthType,
   ToolConfirmationOutcome,
+  getAutoModelDescription,
 } from '@google/gemini-cli-core';
 import type * as acp from '@agentclientprotocol/sdk';
 import { z } from 'zod';
@@ -262,11 +262,9 @@ export function buildAvailableModels(
   }>;
   currentModelId: string;
 } {
-  const preferredModel = config.getModel() || DEFAULT_GEMINI_MODEL_AUTO;
+  const preferredModel = config.getModel() || GEMINI_MODEL_ALIAS_AUTO;
   const shouldShowPreviewModels = config.getHasAccessToPreviewModel();
   const useGemini31 = config.getGemini31LaunchedSync?.() ?? false;
-  const useGemini31FlashLite =
-    config.getGemini31FlashLiteLaunchedSync?.() ?? false;
   const selectedAuthType = settings.merged.security.auth.selectedType;
   const useCustomToolModel =
     useGemini31 && selectedAuthType === AuthType.USE_GEMINI;
@@ -278,7 +276,6 @@ export function buildAvailableModels(
   ) {
     const options = config.getModelConfigService().getAvailableModelOptions({
       useGemini3_1: useGemini31,
-      useGemini3_1FlashLite: useGemini31FlashLite,
       useCustomTools: useCustomToolModel,
       hasAccessToPreview: shouldShowPreviewModels,
     });
@@ -292,23 +289,15 @@ export function buildAvailableModels(
   // --- LEGACY PATH ---
   const mainOptions = [
     {
-      value: DEFAULT_GEMINI_MODEL_AUTO,
-      title: getDisplayString(DEFAULT_GEMINI_MODEL_AUTO),
-      description:
-        'Let Gemini CLI decide the best model for the task: gemini-2.5-pro, gemini-2.5-flash',
+      value: GEMINI_MODEL_ALIAS_AUTO,
+      title: getDisplayString(GEMINI_MODEL_ALIAS_AUTO),
+      description: getAutoModelDescription(
+        shouldShowPreviewModels,
+        useGemini31,
+      ),
     },
   ];
 
-  if (shouldShowPreviewModels) {
-    mainOptions.unshift({
-      value: PREVIEW_GEMINI_MODEL_AUTO,
-      title: getDisplayString(PREVIEW_GEMINI_MODEL_AUTO),
-      description: useGemini31
-        ? 'Let Gemini CLI decide the best model for the task: gemini-3.1-pro, gemini-3-flash'
-        : 'Let Gemini CLI decide the best model for the task: gemini-3-pro, gemini-3-flash',
-    });
-  }
-
   const manualOptions = [
     {
       value: DEFAULT_GEMINI_MODEL,
@@ -344,10 +333,10 @@ export function buildAvailableModels(
       },
     ];
 
-    if (useGemini31FlashLite) {
+    if (PREVIEW_GEMINI_FLASH_LITE_MODEL !== 'none') {
       previewOptions.push({
-        value: PREVIEW_GEMINI_3_1_FLASH_LITE_MODEL,
-        title: getDisplayString(PREVIEW_GEMINI_3_1_FLASH_LITE_MODEL),
+        value: PREVIEW_GEMINI_FLASH_LITE_MODEL,
+        title: getDisplayString(PREVIEW_GEMINI_FLASH_LITE_MODEL),
       });
     }
 

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/commands/extensions/utils.ts

@@ -27,7 +27,7 @@ export interface ConfigLogger {
 
 export type RequestSettingCallback = (
   setting: ExtensionSetting,
-) => Promise<string>;
+) => Promise<string | undefined>;
 export type RequestConfirmationCallback = (message: string) => Promise<boolean>;
 
 const defaultLogger: ConfigLogger = {
@@ -47,8 +47,7 @@ const defaultRequestConfirmation: RequestConfirmationCallback = async (
     message,
     initial: false,
   });
-  // eslint-disable-next-line @typescript-eslint/no-unsafe-return
-  return response.confirm;
+  return typeof response.confirm === 'boolean' ? response.confirm : false;
 };
 
 export async function getExtensionManager() {

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

@@ -8,6 +8,15 @@ import { AuthType } from '@google/gemini-cli-core';
 import { afterEach, beforeEach, describe, expect, it, vi } from 'vitest';
 import { validateAuthMethod } from './auth.js';
 
+vi.mock('@google/gemini-cli-core', async (importOriginal) => {
+  const actual =
+    await importOriginal<typeof import('@google/gemini-cli-core')>();
+  return {
+    ...actual,
+    loadApiKey: vi.fn().mockResolvedValue(null),
+  };
+});
+
 vi.mock('./settings.js', () => ({
   loadEnvironment: vi.fn(),
   loadSettings: vi.fn().mockReturnValue({
@@ -90,10 +99,10 @@ describe('validateAuthMethod', () => {
       envs: {},
       expected: 'Invalid auth method selected.',
     },
-  ])('$description', ({ authType, envs, expected }) => {
+  ])('$description', async ({ authType, envs, expected }) => {
     for (const [key, value] of Object.entries(envs)) {
       vi.stubEnv(key, value as string);
     }
-    expect(validateAuthMethod(authType)).toBe(expected);
+    expect(await validateAuthMethod(authType)).toBe(expected);
   });
 });