Intentionally cause memory leaks on pressing x

Support ctrl+shift+g (#25035 )
refactor(core): use centralized path resolution for Linux sandbox (#24985 )
2026-07-28 02:31:05 -07:00 · 2026-04-09 13:59:42 -04:00 · 2026-04-09 16:23:04 +00:00 · 2026-04-09 15:28:58 +00:00 · 2026-04-09 03:39:36 +00:00 · 2026-04-09 03:30:52 +00:00
165 changed files with 6881 additions and 2956 deletions
@@ -2,7 +2,6 @@
  "experimental": {
    "extensionReloading": true,
    "modelSteering": true,
-    "memoryManager": false,
    "topicUpdateNarration": true
  },
  "general": {
@@ -1,39 +0,0 @@
---
-name: github-issue-triage
-description: Analyzes and cleans up GitHub issues. DO NOT trigger this skill automatically. ONLY use when the user explicitly mentions "github-issue-triage", or explicitly asks to "triage issues", "clean up old issues", or "triage this issue".
---
-
-# GitHub Issue Triage
-
-This skill provides workflows for finding, analyzing, and triaging GitHub issues to maintain a clean and actionable backlog.
-
-## Phase 1: Discovery (Optional)
-
-If the user asks you to "triage issues" or "clean up old issues" without providing a specific issue URL, you must first find candidate issues.
-
-Run the following script to get a list of issues:
-`node scripts/find_issues.cjs <owner/repo>` (e.g., `node scripts/find_issues.cjs google-gemini/gemini-cli`)
-
-You may optionally pass a custom search string and limit.
-`node scripts/find_issues.cjs <owner/repo> "<search_string>" <limit>`
-
-Pick the first issue from the list to triage and proceed to Phase 2. If the user provided a specific issue URL, start at Phase 2 directly.
-
-## Phase 2: Analysis
-
-For the target issue, you must run the analysis script to gather metadata and determine staleness/inactivity heuristics.
-
-Run:
-`node scripts/analyze_issue.cjs <issue_url> "<optional_comma_separated_maintainers>"`
-
-Read the JSON output carefully.
- If `is_stale` is `true`, the issue has already been marked as stale and should be closed according to the rules in Phase 3.
- Take note of `inactive_over_30_days`, `inactive_over_60_days`, `is_epic`, and other boolean flags.
-
-## Phase 3: Triage Execution
-
-After analyzing the issue and receiving the JSON output, you MUST consult the detailed triage rules to determine the next steps.
-
-Read the rules in [references/triage_rules.md](references/triage_rules.md) and execute the appropriate steps. You must follow the steps sequentially.
-
-If a step instructs you to **STOP EXECUTION**, you must conclude your work on this issue and not proceed to subsequent steps. If you are triaging a batch of issues, you may move on to the next issue in the list.
@@ -1,162 +0,0 @@
-# Issue Triage Rules
-
-**Important Note on CLI Commands**: When posting comments via the `gh` CLI that contain newlines (e.g. `\n`), you MUST use bash command substitution with `echo -e` so the newlines are rendered correctly. For example: `gh issue comment <issue_url> --body "$(echo -e "### Triage Summary\n\n<your summary>")"`.
-
-When executing triage on an issue, you must evaluate the following steps sequentially using the data provided from `scripts/analyze_issue.cjs` and the issue comments (`gh issue view <issue_url> --json comments`).
-
-## Categorization Guide: Help-wanted
-When categorizing an issue, determine if it is a good candidate for community contributions. Only use the **Help-wanted** label for these types of issues. Everything else remains unassigned to a specific whitelist label. Examples of **Help-wanted** issues include:
-    *   Small, well-defined features.
-    *   Easy-to-fix bugs (where the root cause might be identified but the fix isn't trivially "simple" enough to just patch immediately).
-    *   Tasks that are clearly scoped and ready for external help.
-    *   Issues that DO NOT require deep architectural knowledge, significant maintainer review time, modifications to core sensitive business logic (telemetry, security, billing), or sweeping UI/UX changes.
-
-Conversely, do **NOT** use the `help wanted` label for issues such as:
-    *   Easily reproducible bugs with a simple identified fix.
-    *   Epics or roadmap initiatives.
-    *   Changes to core architecture, sensitive security fixes, or internal tasks.
-    *   Issues requiring deep investigation.
-    *   Changes to key UI/UX that affect all users.
-    *   Modifications to core internal data structures and IPC mechanisms.
-    *   Changes to token/billing logic.
-    *   Changes to key model and diff/edit functionalities.
-    *   Features or changes that touch multiple parts of the codebase and would require significant reviewer time from maintainers.
-    *   Changes touching key workflows (like the core stream or execution workflows) that affect all users and require careful architectural consideration.
-    *   Changes touching sensitive business logic, telemetry, or API usage statistics/tracking.
-    *   Proposals affecting community guidelines, contributor frameworks, or project governance that require significant maintainer discretion and alignment.
-    *   Complex new subsystems, such as background LLM integration tasks, AI-driven automation, or new agentic behaviors that require significant design validation.
-
-## Step 1: Resolution Check
-**CRITICAL MISTAKE PREVENTION**: You MUST thoroughly read every single comment. Look explicitly for phrases like "appears to fix", "fixes this", "might be fixed", "resolved by", "no longer an issue", or links to other PRs/issues that suggest a resolution. Do not skim. If a user (even a non-maintainer) suggests a fix or PR exists, and the original reporter has not contradicted them, you MUST treat the issue as resolved.
-
-Read ALL the comments from the issue carefully, and review the JSON output for `cross_references`. 
-Check if ANY of the following conditions are met:
-1. Is there a cross-referenced PR in `cross_references` where `is_pr` is `true` and `is_merged` is `true`? If so, use `gh pr view <pr_url> --json title,body` to verify that the PR actually addresses and resolves the issue's request. If it does not, treat condition 1 as NOT met.
-2. Is it fixed, resolved, no longer reproducible, or functioning properly in the comments? (e.g., someone mentions it `might be fixed`, `should be fixed`, or `no longer an issue`) AND the reporter has not replied afterward to contradict this?
-3. Is there a workaround provided in the comments?
-4. Does someone state the issue is actually unrelated to this repository/project, or is an external problem (like a terminal emulator bug)?
-
- If condition 1 is met: Execute `gh issue close <issue_url> --comment "Closing because this issue was referenced by a merged pull request. Feel free to reopen if the problem persists or if the PR did not fully resolve this." --reason "completed"` and **STOP EXECUTION**.
- If condition 2 or 3 is met: Execute `gh issue close <issue_url> --comment "Closing because the comments indicate this issue might be fixed, has a workaround, is no longer an issue, or is resolved. Feel free to reopen if the problem persists." --reason "completed"` and **STOP EXECUTION**.
- If condition 4 is met: Execute `gh issue close <issue_url> --comment "Closing because the comments indicate this issue is unrelated to this project or is an external problem." --reason "not planned"` and **STOP EXECUTION**.
- If NONE of these conditions are met: Proceed to Step 1.1.
-
-## Step 1.1: Existing Feature Check
-**CRITICAL MISTAKE PREVENTION**: If the issue describes a feature request or enhancement (regardless of whether the JSON `is_feature_request` flag is true or false), you **MUST explicitly search the codebase** to verify if it is already implemented. You cannot skip this step for feature requests.
-1. Use the `grep_search` tool to look for relevant keywords related to the feature in files like `schemas/settings.schema.json`, `packages/cli/src/config/config.ts`, command definitions, or UI components.
-   - **Hotkeys & UI Actions**: If the user asks for a way to expand text, pause output, copy text, or perform a UI action, explicitly check `packages/cli/src/ui/key/keyBindings.ts` and the `Command` enum. Many interactive features (e.g., `Ctrl+O` for expanding truncated tool confirmations or output) already exist natively.
-2. If you verify that the requested functionality (e.g., a setting, flag, hotkey, or command) already exists natively:
-   - Execute `gh issue close <issue_url> --comment "This feature is actually already implemented! <Provide a brief explanation of how to use the feature, such as the command to run, the setting to change, or the hotkey to press>.\n\nI'm going to close this issue since the functionality already exists natively. Let us know if you run into any other issues!" --reason "completed"`
-   - **STOP EXECUTION**.
-3. If the feature does NOT exist, proceed to Step 1.2.
-
-## Step 1.2: Closed PR Re-evaluation
-If there is a cross-referenced PR in `cross_references` where `is_pr` is `true` and `is_merged` is `false` (and its state is `closed` or it has an automated closure comment):
-1. Use `gh pr view <pr_url> --json author,comments,state,title,body` to analyze the PR.
-2. Check the comments to see if it was closed by an automated bot (e.g., `gemini-cli` bot closing it automatically due to missing labels like 'help wanted' after 14 days).
-3. Analyze the PR's title, body, and comments to determine if it implements a valid and useful feature/fix and is worth resuming. 
-4. **Existing Feature Check**: Check if the requested feature is actually already implemented natively in the codebase (e.g., an existing hotkey, setting, or command). Search the codebase using `grep_search` if unsure.
- If the feature is ALREADY IMPLEMENTED:
-  a. Do NOT reopen the PR.
-  b. Execute `gh issue close <issue_url> --comment "This feature is actually already implemented! <Provide a brief explanation of how to use the feature>.\n\nI'm going to close this issue since the functionality already exists natively. Let us know if you run into any other issues!" --reason "completed"`
-  c. Comment on the PR: `gh pr comment <pr_url> --body "@<author_username>, thank you for your contribution! We've reviewed this again and decided to keep it closed. The core feature requested in the parent issue is actually already implemented natively in the CLI. We appreciate the effort, but this specific PR is no longer needed!"`
-  d. **STOP EXECUTION**.
-5. Critically evaluate the PR's approach for correctness and safety. Ensure it does not introduce breaking changes, make false assumptions (e.g., making an optional configuration mandatory for all users), or negatively impact other workflows.
- If the PR's approach is flawed or introduces breaking changes:
-  a. Do NOT reopen the PR.
-  b. Determine if the issue itself should be **Help-wanted** (using the Categorization Guide).
-  c. If **Help-wanted**, run `gh issue edit <issue_url> --remove-label "status/need-triage" --add-label "help wanted"`. If not, just remove `status/need-triage`.
-  d. Execute `gh issue comment <issue_url> --body "### Triage Summary\n\nWhile this issue is valid, the proposed fix in PR <pr_url> introduces potential breaking changes or relies on incorrect assumptions (e.g., <brief explanation of the flaw>). Therefore, we will not reopen that PR, but we still welcome a different approach to fix this issue!"`
-  e. Comment on the PR: `gh pr comment <pr_url> --body "@<author_username>, thank you for your contribution! We've reviewed the approach in this PR and decided to keep it closed because <brief explanation of the flaw>. We still welcome improvements here using a different approach! Feel free to open a new PR if you're interested."`
-  f. **STOP EXECUTION**.
- If it is worth resuming AND was closed by a bot:
-  a. Determine if the issue should be **Help-wanted** (using the Categorization Guide).
-  b. If it should NOT be **Help-wanted**:
-     - Execute `gh issue edit <issue_url> --remove-label "status/need-triage"`
-     - Execute `gh issue comment <issue_url> --body "$(echo -e "### Triage Summary\n\n<brief explanation of why this issue requires maintainer attention and is not suitable for community contribution>")"`
-     - **STOP EXECUTION**. (Do not reopen the PR).
-  c. If it should be **Help-wanted**:
-     - Reopen the PR: `gh pr reopen <pr_url>`
-     - Assign the PR to the author: `gh pr edit <pr_url> --add-assignee <author_username>`
-     - Assign the issue to the author: `gh issue edit <issue_url> --add-assignee <author_username>`
-     - Add the help wanted label to the issue to prevent the bot from closing the PR again: `gh issue edit <issue_url> --add-label "help wanted"`
-     - Comment on the issue: `gh issue comment <issue_url> --body "### Triage Summary\n\n<brief explanation of why this is a help-wanted task>\n\n@<author_username>, apologies! It looks like your PR <pr_url> was incorrectly closed by our bot. I have reopened it and assigned this issue to you. Would you like to continue working on it?"`
-     - Comment on the PR: `gh pr comment <pr_url> --body "@<author_username>, apologies for the bot closing this PR! We have reopened it. Please sync your branch to the latest \`main\` and we will have someone review it shortly."`
-     - Execute `gh issue edit <issue_url> --remove-label "status/need-triage"`
-     - **STOP EXECUTION**.
- If NOT met: Proceed to Step 1.5.
-
-## Step 1.5: Pending Response Check
-Read ALL the comments from the issue carefully.
-1. Check if the most recent comments include a request for more information, clarification, or reproduction steps directed at the reporter from any other user (maintainer or community member).
-2. Check if the reporter has NOT replied to that request.
-3. Check if that request was made over 14 days ago. (You can check the date of the comment vs today's date).
-4. **CRITICAL**: Before closing, verify if OTHER users have chimed in after the request to provide the necessary context, answer the question on behalf of the reporter, or confirm the bug's existence. If they have, the issue is NO LONGER pending response and you must proceed to Step 2.
-
- If conditions 1, 2, and 3 are met AND condition 4 is false: Execute `gh issue close <issue_url> --comment "Closing because more information was requested over 2 weeks ago and we haven't received a response. Feel free to reopen if you can provide the requested details." --reason "not planned"` and **STOP EXECUTION**.
- If NOT met: Proceed to Step 2.
-
-## Step 2: Assignee and Inactivity Handling
-Use the JSON output from `analyze_issue.cjs` to determine necessary actions.
-
-**CRITICAL VERIFICATION**: Before proceeding, explicitly verify the exact boolean values of `inactive_over_60_days`, `inactive_over_30_days`, and `is_feature_request` in the JSON output. Do not guess these values based on the date. Note that `is_feature_request` might be `false` even for feature requests if the title/labels lack specific keywords; if the body clearly asks for a new feature/enhancement, treat it as a feature request regardless of the JSON flag.
-
-1. **Assignee Check:** If an assignee is a contributor and hasn't made any updates on the issue for over 2 weeks, execute `gh issue edit <issue_url> --remove-assignee <username>` to remove them. (Do this before proceeding further).
-2. **Inactivity Check:** 
-   - If `inactive_over_60_days` is `true`: 
-     a. Formulate a comment to the reporter (@<reporter_username>). Evaluate the issue description and whether it is an Epic (`is_epic`):
-        - Always mention that the issue is being closed or pinged because it has been inactive for over 60 days.
-        - IF IT IS AN EPIC: Ask the reporter if it is still in progress or complete, and if it is complete, ask them to close it.
-        - IF IT IS NOT AN EPIC:
-          - If it's a feature/enhancement request and the description is relatively vague, ask: 1) if it is still needed and 2) if they can provide more details on the feature request.
-          - If the issue was mentioned by another issue that is closed as completed or by a pull request that is merged/closed (check `cross_references`), mention this cross-reference (e.g., "I see this issue was mentioned by #123 which is closed as completed...") and ask if this means it is resolved. Do NOT mention cross-references that are still open or closed as "not planned".
-          - If it's a feature/enhancement request but well-described, just ask if it's still needed.
-          - If it's a bug, ask if they can reproduce it with the latest build and provide detailed reproduction steps.
-          - If the issue has assignees, append a ping to the assignees to check in.
-          - If it is NOT an Epic AND `is_tracked_by_epic` is `false`, append "Feel free to reopen this issue." to the comment.
-     b. Execute `gh issue edit <issue_url> --remove-label "status/need-triage"`. If it is NOT an Epic, also append `--add-label "status/needs-info"`.
-     c. Execute `gh issue comment <issue_url> --body "<your formulated comment>"`
-     d. If it is NOT an Epic AND `is_tracked_by_epic` is `false`, execute `gh issue close <issue_url> --reason "not planned"`.
-     - After executing these actions, **STOP EXECUTION**.
-   - If `inactive_over_30_days` is `true` AND it is a bug report (`is_feature_request` is `false`) AND it is NOT an Epic (`is_epic` is `false`):
-     a. Execute `gh issue edit <issue_url> --remove-label "status/need-triage" --add-label "status/needs-info"`.
-     b. Execute `gh issue comment <issue_url> --body "@<reporter_username>, this issue has been inactive for over a month. Could you please try reproducing it with the latest nightly build and let us know if it still occurs? If we don't hear back, we will close this issue on <deadline_date>."`
-     - After executing these actions, **STOP EXECUTION**.
-   - If neither condition is met, proceed to Step 3.
-
-## Step 3: Vagueness Check
-**CRITICAL MISTAKE PREVENTION**: You MUST NOT skip this step just because you recognize the problem domain as complex or requiring maintainer attention. No matter how obvious the problem domain might seem, a bug report without explicit, step-by-step reproduction instructions must be halted and marked as vague first.
-
-Is the issue fundamentally missing context AND no one has asked for more information yet?
- **For bugs**: Explicit reproduction steps are **REQUIRED**. Even if the user provides logs, error traces, or screenshots, if they do not provide clear, step-by-step instructions on how to reproduce the bug, it MUST be considered vague.
- **For feature requests**: If it is just a vague statement without clear use cases or details, it is considered vague.
- If YES (it is vague): Execute `gh issue edit <issue_url> --remove-label "status/need-triage" --add-label "status/needs-info"`. Ask the reporter: `gh issue comment <issue_url> --body "@<reporter_username>, thank you for the report! Could you please provide more specific details (e.g., detailed reproduction steps, expected behavior, logs, and environment details)? Closing this as vague if no response is received in a week."` and **STOP EXECUTION**.
- If NO: Proceed to Step 4.
-
-## Step 4: Reproduction & Code Validity
-1. Review the issue comments. If a community member has already clearly identified the root cause of the bug or answered the feature request, DO NOT investigate the code. Proceed to Step 5.
-2. Clone the target repository to a temporary directory (`git clone <repo_url> target-repo`).
-3. Search the `target-repo/` codebase using `grep_search` and `read_file` ONLY. You are explicitly FORBIDDEN from writing new files, running tests, attempting to fix the code, OR attempting to reproduce the bug by executing code or shell commands. Your ONLY goal is to perform STATIC code analysis to determine if the logic for the bug still exists or if the reported behavior is actually intentional by design.
- If definitively NO LONGER VALID: Close it: `gh issue close <issue_url> --comment "Closing because I have verified this works correctly in the latest codebase. <brief explanation>"` and **STOP EXECUTION**.
- If INTENTIONAL BY DESIGN: Close it: `gh issue close <issue_url> --reason "not planned" --comment "Closing this issue as the reported behavior is intentional by design. <brief explanation of the design logic>"` and **STOP EXECUTION**.
- If still valid: Proceed to Step 5.
-
-## Step 5: Duplicates
-Search for duplicates using `gh issue list --search "<keywords>" --repo <owner/repo> --state all`. 
- **CRITICAL**: Pay special attention to newer issues that might already have active pull requests or more detailed context. If a duplicate exists that already has an active PR or more maintainer engagement, close the *current* issue you are triaging in favor of the active one.
- If found: `gh issue close <issue_url> --reason "not planned" --comment "Closing as duplicate of #<duplicate_number>."` and **STOP EXECUTION**.
- If no duplicates: Proceed to Step 6.
-
-## Step 6: Triage Summary
-Review the issue comments to see if a community member has already identified the root cause.
- Determine if it should be **Help-wanted** (using the Categorization Guide) and explain why in your summary. 
- If you categorized the issue as **Help-wanted**, run `gh issue edit <issue_url> --remove-label "status/need-triage" --add-label "help wanted"`. 
- If it does not fit **Help-wanted**, you must still explain *why* it requires maintainer attention or why it's not a good fit for community contribution (e.g., "This issue touches core architecture and requires significant maintainer review time"). Simply run `gh issue edit <issue_url> --remove-label "status/need-triage"` to mark it triaged without a specific whitelist label.
- Action: `gh issue comment <issue_url> --body "### Triage Summary\n\n<your summary>"`
- **STOP EXECUTION**.
-
-## Mandatory Final Step
-Every issue that is triaged and remains OPEN MUST be assigned at least one of the following labels before you finish your triage process for that issue:
- `status/needs-info` (for inactive, vague, or issues requiring more details)
- `help wanted` (for well-defined, community-friendly issues)
- NONE of the above (If the issue is triaged, valid, but too complex for a community contribution, it should simply remain open without `status/need-triage`). If an issue reaches the end of triage and remains open, you must remove `status/need-triage`.
@@ -1,161 +0,0 @@
-const { execSync } = require('child_process');
-
-function runCommand(cmd) {
-  try {
-    return execSync(cmd, { encoding: 'utf-8' }).trim();
-  } catch (error) {
-    // Return empty or structured error so the agent can see it rather than failing the whole script
-    return JSON.stringify({ error: error.message });
-  }
-}
-
-async function analyzeIssue(issueLink, maintainersList) {
-  if (!issueLink) {
-    console.error(JSON.stringify({ error: "Issue link is required." }));
-    process.exit(1);
-  }
-
-  const parts = issueLink.split('/');
-  const issueNumberStr = parts[parts.length - 1];
-  const issueNumber = parseInt(issueNumberStr, 10);
-  const repoName = parts[parts.length - 3];
-  const repoOwner = parts[parts.length - 4];
-  const repo = `${repoOwner}/${repoName}`;
-
-  const maintainers = maintainersList ? maintainersList.split(',').map(m => m.trim()) : [];
-
-  const deadline = new Date();
-  deadline.setDate(deadline.getDate() + 14);
-
-  const result = {
-    issue_link: issueLink,
-    repo: repo,
-    issue_number: issueNumber,
-    is_tracked_by_epic: false,
-    is_stale: false,
-    inactive_over_30_days: false,
-    inactive_over_60_days: false,
-    has_assignees: false,
-    is_feature_request: false,
-    is_high_priority: false,
-    is_epic: false,
-    reporter: null,
-    assignees: [],
-    labels: [],
-    cross_references: [],
-    deadline_date: deadline.toISOString().split('T')[0]
-  };
-
-  try {
-    // 1. Fetch Issue Data
-    const issueDataRaw = runCommand(`gh issue view ${issueLink} --json title,body,author,comments,labels,assignees,updatedAt`);
-    if (issueDataRaw.startsWith('{"error"')) {
-       console.error(issueDataRaw);
-       process.exit(1);
-    }
-    const issue = JSON.parse(issueDataRaw);
-    
-    result.reporter = issue.author.login;
-    result.assignees = issue.assignees.map(a => a.login);
-    result.has_assignees = result.assignees.length > 0;
-    result.labels = issue.labels.map(l => l.name);
-    
-    result.is_feature_request = result.labels.some(l => {
-      const lower = l.toLowerCase();
-      return lower.includes('feature') || lower.includes('enhancement');
-    }) || issue.title.toLowerCase().includes('feature') || issue.title.toLowerCase().includes('proposal');
-    
-    result.is_high_priority = result.labels.some(l => {
-      const lower = l.toLowerCase();
-      return lower.includes('priority/p0') || lower.includes('priority/p1');
-    });
-
-    // 2. Fetch Timeline for cross references
-    const timelineCmd = `gh api repos/${repo}/issues/${issueNumber}/timeline --jq '[.[] | select(.event == "cross-referenced" and .source.issue)] | map({issue: .source.issue.number, state: .source.issue.state, state_reason: .source.issue.state_reason, is_pr: (.source.issue.pull_request != null), is_merged: (.source.issue.pull_request.merged_at != null)})'`;
-    const timelineRaw = runCommand(timelineCmd);
-    if (!timelineRaw.startsWith('{"error"')) {
-        result.cross_references = JSON.parse(timelineRaw);
-    }
-
-    // 3. Check if Epic (has sub issues or title starts with [Epic])
-    const epicCmd = `gh api repos/${repo}/issues/${issueNumber} --jq '{is_epic: (.sub_issues_summary.total > 0)}'`;
-    const epicRaw = runCommand(epicCmd);
-    if (!epicRaw.startsWith('{"error"')) {
-        result.is_epic = JSON.parse(epicRaw).is_epic || issue.title.toLowerCase().startsWith('[epic]');
-    } else {
-        result.is_epic = issue.title.toLowerCase().startsWith('[epic]');
-    }
-
-    // 4. Check for Parent Issue via GraphQL
-    const query = `query($owner: String!, $repo: String!, $issueNumber: Int!) { repository(owner: $owner, name: $repo) { issue(number: $issueNumber) { trackedInIssues(first: 1) { totalCount } } } }`;
-    const gqlCmd = `gh api graphql -F owner=${repoOwner} -F repo=${repoName} -F issueNumber=${issueNumber} -f query='${query}' --jq '.data.repository.issue.trackedInIssues.totalCount'`;
-    const parentCountRaw = runCommand(gqlCmd);
-    if (!parentCountRaw.startsWith('{"error"')) {
-        const count = parseInt(parentCountRaw, 10);
-        result.is_tracked_by_epic = !isNaN(count) && count > 0;
-    }
-
-    // Staleness Logic
-    if (result.is_tracked_by_epic) {
-      result.is_stale = true;
-    } else {
-      // Find last maintainer comment
-      const maintainerComments = issue.comments.filter(c => {
-        if (c.author.login === result.reporter) return false;
-        
-        const isMaintainer = maintainers.includes(c.author.login) || 
-                             ['OWNER', 'MEMBER', 'COLLABORATOR'].includes(c.authorAssociation);
-        
-        if (maintainers.length > 0) return isMaintainer;
-        // Basic bot exclusion if no maintainers defined
-        return !c.author.login.includes('github-actions') && c.author.login !== 'app/github-actions';
-      });
-
-      if (maintainerComments.length > 0) {
-        const lastMaintainerComment = maintainerComments[maintainerComments.length - 1];
-        
-        // Did reporter reply after maintainer?
-        const reporterReplied = issue.comments.some(c => {
-            return c.author.login === result.reporter && 
-                   new Date(c.updatedAt) > new Date(lastMaintainerComment.updatedAt);
-        });
-
-        if (!reporterReplied) {
-          const daysAgo = (new Date() - new Date(lastMaintainerComment.updatedAt)) / (1000 * 60 * 60 * 24);
-          if (daysAgo > 7) {
-             result.is_stale = true;
-          }
-        }
-      }
-    }
-
-    // Age / Inactivity check
-    if (!result.is_stale) {
-       const lastUpdateDaysAgo = (new Date() - new Date(issue.updatedAt)) / (1000 * 60 * 60 * 24);
-       if (lastUpdateDaysAgo > 60) {
-          result.inactive_over_60_days = true;
-          result.inactive_over_30_days = true;
-       } else if (lastUpdateDaysAgo > 30) {
-          result.inactive_over_30_days = true;
-       }
-    }
-
-    console.log(JSON.stringify(result, null, 2));
-
-  } catch (error) {
-    console.error(JSON.stringify({ error: error.message }));
-    process.exit(1);
-  }
-}
-
-const args = process.argv.slice(2);
-const issueLink = args[0];
-const maintainers = args[1] || ""; // Comma separated list of maintainers
-
-if (!issueLink) {
-  console.log("Usage: node analyze_issue.cjs <issue_link> [maintainers_csv]");
-  console.log("Example: node analyze_issue.cjs https://github.com/owner/repo/issues/123 'user1,user2'");
-  process.exit(1);
-}
-
-analyzeIssue(issueLink, maintainers);
@@ -1,34 +0,0 @@
-const { execSync } = require('child_process');
-
-function findIssues(repo, searchString = "label:area/core,area/extensions,area/site,area/non-interactive sort:updated-asc", limit = 10) {
-  if (!repo) {
-    console.error(JSON.stringify({ error: "Repository is required (e.g., owner/repo)" }));
-    process.exit(1);
-  }
-
-  try {
-    const cmd = `gh issue list --repo ${repo} --state open --search "${searchString}" --json url --limit ${limit}`;
-    const output = execSync(cmd, { encoding: 'utf-8' });
-    const issues = JSON.parse(output);
-    const urls = issues.map(issue => issue.url);
-    
-    console.log(JSON.stringify({ issue_urls: urls }, null, 2));
-  } catch (error) {
-    console.error(JSON.stringify({ error: error.message }));
-    process.exit(1);
-  }
-}
-
-const args = process.argv.slice(2);
-const repo = args[0];
-const searchString = args[1];
-const limitStr = args[2];
-const limit = limitStr ? parseInt(limitStr, 10) : 10;
-
-if (!repo) {
-  console.log("Usage: node find_issues.cjs <owner/repo> [search_string] [limit]");
-  console.log("Example: node find_issues.cjs google-gemini/gemini-cli 'label:area/core sort:updated-asc' 10");
-  process.exit(1);
-}
-
-findIssues(repo, searchString, limit);
@@ -335,6 +335,8 @@ jobs:
        env:
          GEMINI_API_KEY: '${{ secrets.GEMINI_API_KEY }}'
          GEMINI_MODEL: 'gemini-3-pro-preview'
+          # Only run always passes behavioral tests.
+          EVAL_SUITE_TYPE: 'behavioral'
          # Disable Vitest internal retries to avoid double-retrying;
          # custom retry logic is handled in evals/test-helper.ts
          VITEST_RETRY: 0
@@ -5,10 +5,18 @@ on:
    - cron: '0 1 * * *' # Runs at 1 AM every day
  workflow_dispatch:
    inputs:
-      run_all:
-        description: 'Run all evaluations (including usually passing)'
-        type: 'boolean'
-        default: true
+      suite_type:
+        description: 'Suite type to run'
+        type: 'choice'
+        options:
+          - 'behavioral'
+          - 'component-level'
+          - 'hero-scenario'
+        default: 'behavioral'
+      suite_name:
+        description: 'Specific suite name to run'
+        required: false
+        type: 'string'
      test_name_pattern:
        description: 'Test name pattern or file name'
        required: false
@@ -59,7 +67,9 @@ jobs:
        env:
          GEMINI_API_KEY: '${{ secrets.GEMINI_API_KEY }}'
          GEMINI_MODEL: '${{ matrix.model }}'
-          RUN_EVALS: "${{ github.event.inputs.run_all != 'false' }}"
+          RUN_EVALS: 'true'
+          EVAL_SUITE_TYPE: "${{ github.event.inputs.suite_type || 'behavioral' }}"
+          EVAL_SUITE_NAME: '${{ github.event.inputs.suite_name }}'
          TEST_NAME_PATTERN: '${{ github.event.inputs.test_name_pattern }}'
          # Disable Vitest internal retries to avoid double-retrying;
          # custom retry logic is handled in evals/test-helper.ts
@@ -0,0 +1,33 @@
+name: 'Memory Tests: Nightly'
+
+on:
+  schedule:
+    - cron: '0 2 * * *' # Runs at 2 AM every day
+  workflow_dispatch: # Allow manual trigger
+
+permissions:
+  contents: 'read'
+
+jobs:
+  memory-test:
+    name: 'Run Memory Usage Tests'
+    runs-on: 'gemini-cli-ubuntu-16-core'
+    if: "github.repository == 'google-gemini/gemini-cli'"
+    steps:
+      - name: 'Checkout'
+        uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
+
+      - name: 'Set up Node.js'
+        uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions/setup-node@v4
+        with:
+          node-version-file: '.nvmrc'
+          cache: 'npm'
+
+      - name: 'Install dependencies'
+        run: 'npm ci'
+
+      - name: 'Build project'
+        run: 'npm run build'
+
+      - name: 'Run Memory Tests'
+        run: 'npm run test:memory'
@@ -0,0 +1,33 @@
+name: 'Performance Tests: Nightly'
+
+on:
+  schedule:
+    - cron: '0 3 * * *' # Runs at 3 AM every day
+  workflow_dispatch: # Allow manual trigger
+
+permissions:
+  contents: 'read'
+
+jobs:
+  perf-test:
+    name: 'Run Performance Usage Tests'
+    runs-on: 'gemini-cli-ubuntu-16-core'
+    if: "github.repository == 'google-gemini/gemini-cli'"
+    steps:
+      - name: 'Checkout'
+        uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
+
+      - name: 'Set up Node.js'
+        uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions/setup-node@v4
+        with:
+          node-version-file: '.nvmrc'
+          cache: 'npm'
+
+      - name: 'Install dependencies'
+        run: 'npm ci'
+
+      - name: 'Build project'
+        run: 'npm run build'
+
+      - name: 'Run Performance Tests'
+        run: 'npm run test:perf'
@@ -48,6 +48,7 @@ packages/cli/src/generated/
 packages/core/src/generated/
 packages/devtools/src/_client-assets.ts
 .integration-tests/
+.perf-tests/
 packages/vscode-ide-companion/*.vsix
 packages/cli/download-ripgrep*/

@@ -64,3 +65,6 @@ gemini-debug.log
 evals/logs/

 temp_agents/
+
+# conductor extension and planning directories
+conductor/
@@ -44,6 +44,13 @@ powerful tool for developers.
 - **Test Commands:**
  - **Unit (All):** `npm run test`
  - **Integration (E2E):** `npm run test:e2e`
+  - > **NOTE**: Please run the memory and perf tests locally **only if** you are
+    > implementing changes related to those test areas. Otherwise skip these
+    > tests locally and rely on CI to run them on nightly builds.
+  - **Memory (Nightly):** `npm run test:memory` (Runs memory regression tests
+    against baselines. Excluded from `preflight`, run nightly.)
+  - **Performance (Nightly):** `npm run test:perf` (Runs CPU performance
+    regression tests against baselines. Excluded from `preflight`, run nightly.)
  - **Workspace-Specific:** `npm test -w <pkg> -- <path>` (Note: `<path>` must
    be relative to the workspace root, e.g.,
    `-w @google/gemini-cli-core -- src/routing/modelRouterService.test.ts`)
@@ -18,6 +18,27 @@ on GitHub.
 | [Preview](preview.md) | Experimental features ready for early feedback. |
 | [Stable](latest.md)   | Stable, recommended for general use.            |

+## Announcements: v0.37.0 - 2026-04-08
+
+- **Dynamic Sandbox Expansion:** Implemented dynamic sandbox expansion and
+  worktree support for Linux and Windows, improving developer workflows in
+  isolated environments
+  ([#23692](https://github.com/google-gemini/gemini-cli/pull/23692) by @galz10,
+  [#23691](https://github.com/google-gemini/gemini-cli/pull/23691) by
+  @scidomino).
+- **Chapters Narrative Flow:** Introduced tool-based topic grouping ("Chapters")
+  to provide better session structure and narrative continuity
+  ([#23150](https://github.com/google-gemini/gemini-cli/pull/23150) by
+  @Abhijit-2592,
+  [#24079](https://github.com/google-gemini/gemini-cli/pull/24079) by
+  @gundermanc).
+- **Advanced Browser Capabilities:** Enhanced the browser agent with persistent
+  sessions and dynamic tool discovery
+  ([#21306](https://github.com/google-gemini/gemini-cli/pull/21306) by
+  @kunal-10-cloud,
+  [#23805](https://github.com/google-gemini/gemini-cli/pull/23805) by
+  @cynthialong0-0).
+
 ## Announcements: v0.36.0 - 2026-04-01

 - **Multi-Registry Architecture and Sandboxing:** Introduced a multi-registry
@@ -1,6 +1,6 @@
-# Latest stable release: v0.36.0
+# Latest stable release: v0.37.0

-Released: April 1, 2026
+Released: April 08, 2026

 For most users, our latest stable release is the recommended release. Install
 the latest stable version with:
@@ -11,372 +11,409 @@ npm install -g @google/gemini-cli

 ## Highlights

- **Multi-Registry Architecture and Tool Isolation:** Introduced a
-  multi-registry architecture for subagents and implemented strict sandboxing
-  for macOS (Seatbelt) and Windows to enhance security and isolation.
- **Improved Subagent Coordination:** Enhanced subagents with local execution
-  capabilities, JIT context injection (upward traversal capped at git root), and
-  resilient tool rejection with contextual feedback.
- **Enhanced UI and UX:** Implemented a refreshed UX for the Composer layout,
-  improved terminal fallback warnings, and resolved various UI flickering and
-  state persistence issues.
- **Git Worktree Support:** Added support for Git worktrees to enable isolated
-  parallel sessions within the same repository.
- **Plan Mode Improvements:** Plan mode now supports non-interactive execution
-  and includes hardened sandbox path resolution to prevent hallucinations.
+- **Dynamic Sandbox Expansion:** Implemented dynamic sandbox expansion and
+  worktree support for both Linux and Windows, enhancing development flexibility
+  in restricted environments.
+- **Tool-Based Topic Grouping (Chapters):** Introduced "Chapters" to logically
+  group agent interactions based on tool usage and intent, providing a clearer
+  narrative flow in long sessions.
+- **Enhanced Browser Agent:** Added persistent session management, dynamic
+  read-only tool discovery, and sandbox-aware initialization for the browser
+  agent.
+- **Security & Permission Hardening:** Implemented secret visibility lockdown
+  for environment files and integrated integrity controls for Windows
+  sandboxing.

 ## What's Changed

- Changelog for v0.33.2 by @gemini-cli-robot in
-  [#22730](https://github.com/google-gemini/gemini-cli/pull/22730)
- feat(core): multi-registry architecture and tool filtering for subagents by
-  @akh64bit in [#22712](https://github.com/google-gemini/gemini-cli/pull/22712)
- Changelog for v0.34.0-preview.4 by @gemini-cli-robot in
-  [#22752](https://github.com/google-gemini/gemini-cli/pull/22752)
- fix(devtools): use theme-aware text colors for console warnings and errors by
-  @SandyTao520 in
-  [#22181](https://github.com/google-gemini/gemini-cli/pull/22181)
- Add support for dynamic model Resolution to ModelConfigService by @kevinjwang1
-  in [#22578](https://github.com/google-gemini/gemini-cli/pull/22578)
- chore(release): bump version to 0.36.0-nightly.20260317.2f90b4653 by
-  @gemini-cli-robot in
-  [#22858](https://github.com/google-gemini/gemini-cli/pull/22858)
- fix(cli): use active sessionId in useLogger and improve resume robustness by
-  @mattKorwel in
-  [#22606](https://github.com/google-gemini/gemini-cli/pull/22606)
- fix(cli): expand tilde in policy paths from settings.json by @abhipatel12 in
-  [#22772](https://github.com/google-gemini/gemini-cli/pull/22772)
- fix(core): add actionable warnings for terminal fallbacks (#14426) by
-  @spencer426 in
-  [#22211](https://github.com/google-gemini/gemini-cli/pull/22211)
- feat(tracker): integrate task tracker protocol into core system prompt by
-  @anj-s in [#22442](https://github.com/google-gemini/gemini-cli/pull/22442)
- chore: add posttest build hooks and fix missing dependencies by @NTaylorMullen
-  in [#22865](https://github.com/google-gemini/gemini-cli/pull/22865)
- feat(a2a): add agent acknowledgment command and enhance registry discovery by
-  @alisa-alisa in
-  [#22389](https://github.com/google-gemini/gemini-cli/pull/22389)
- fix(cli): automatically add all VSCode workspace folders to Gemini context by
-  @sakshisemalti in
-  [#21380](https://github.com/google-gemini/gemini-cli/pull/21380)
- feat: add 'blocked' status to tasks and todos by @anj-s in
-  [#22735](https://github.com/google-gemini/gemini-cli/pull/22735)
- refactor(cli): remove extra newlines in ShellToolMessage.tsx by @NTaylorMullen
-  in [#22868](https://github.com/google-gemini/gemini-cli/pull/22868)
- fix(cli): lazily load settings in onModelChange to prevent stale closure data
-  loss by @KumarADITHYA123 in
-  [#20403](https://github.com/google-gemini/gemini-cli/pull/20403)
- feat(core): subagent local execution and tool isolation by @akh64bit in
-  [#22718](https://github.com/google-gemini/gemini-cli/pull/22718)
- fix(cli): resolve subagent grouping and UI state persistence by @abhipatel12
-  in [#22252](https://github.com/google-gemini/gemini-cli/pull/22252)
- refactor(ui): extract SessionBrowser search and navigation components by
-  @abhipatel12 in
-  [#22377](https://github.com/google-gemini/gemini-cli/pull/22377)
- fix: updates Docker image reference for GitHub MCP server by @jhhornn in
-  [#22938](https://github.com/google-gemini/gemini-cli/pull/22938)
- refactor(cli): group subagent trajectory deletion and use native filesystem
-  testing by @abhipatel12 in
-  [#22890](https://github.com/google-gemini/gemini-cli/pull/22890)
- refactor(cli): simplify keypress and mouse providers and update tests by
-  @scidomino in [#22853](https://github.com/google-gemini/gemini-cli/pull/22853)
- Changelog for v0.34.0 by @gemini-cli-robot in
-  [#22860](https://github.com/google-gemini/gemini-cli/pull/22860)
- test(cli): simplify createMockSettings calls by @scidomino in
-  [#22952](https://github.com/google-gemini/gemini-cli/pull/22952)
- feat(ui): format multi-line banner warnings with a bold title by @keithguerin
-  in [#22955](https://github.com/google-gemini/gemini-cli/pull/22955)
- Docs: Remove references to stale Gemini CLI file structure info by
-  @g-samroberts in
-  [#22976](https://github.com/google-gemini/gemini-cli/pull/22976)
- feat(ui): remove write todo list tool from UI tips by @aniruddhaadak80 in
-  [#22281](https://github.com/google-gemini/gemini-cli/pull/22281)
- Fix issue where subagent thoughts are appended. by @gundermanc in
-  [#22975](https://github.com/google-gemini/gemini-cli/pull/22975)
- Feat/browser privacy consent by @kunal-10-cloud in
-  [#21119](https://github.com/google-gemini/gemini-cli/pull/21119)
- fix(core): explicitly map execution context in LocalAgentExecutor by @akh64bit
-  in [#22949](https://github.com/google-gemini/gemini-cli/pull/22949)
- feat(plan): support plan mode in non-interactive mode by @ruomengz in
-  [#22670](https://github.com/google-gemini/gemini-cli/pull/22670)
- feat(core): implement strict macOS sandboxing using Seatbelt allowlist by
-  @ehedlund in [#22832](https://github.com/google-gemini/gemini-cli/pull/22832)
- docs: add additional notes by @abhipatel12 in
-  [#23008](https://github.com/google-gemini/gemini-cli/pull/23008)
- fix(cli): resolve duplicate footer on tool cancel via ESC (#21743) by
-  @ruomengz in [#21781](https://github.com/google-gemini/gemini-cli/pull/21781)
- Changelog for v0.35.0-preview.1 by @gemini-cli-robot in
-  [#23012](https://github.com/google-gemini/gemini-cli/pull/23012)
- fix(ui): fix flickering on small terminal heights by @devr0306 in
-  [#21416](https://github.com/google-gemini/gemini-cli/pull/21416)
- fix(acp): provide more meta in tool_call_update by @Mervap in
-  [#22663](https://github.com/google-gemini/gemini-cli/pull/22663)
- docs: add FAQ entry for checking Gemini CLI version by @surajsahani in
-  [#21271](https://github.com/google-gemini/gemini-cli/pull/21271)
- feat(core): resilient subagent tool rejection with contextual feedback by
-  @abhipatel12 in
-  [#22951](https://github.com/google-gemini/gemini-cli/pull/22951)
- fix(cli): correctly handle auto-update for standalone binaries by @bdmorgan in
-  [#23038](https://github.com/google-gemini/gemini-cli/pull/23038)
- feat(core): add content-utils by @adamfweidman in
-  [#22984](https://github.com/google-gemini/gemini-cli/pull/22984)
- fix: circumvent genai sdk requirement for api key when using gateway auth via
-  ACP by @sripasg in
-  [#23042](https://github.com/google-gemini/gemini-cli/pull/23042)
- fix(core): don't persist browser consent sentinel in non-interactive mode by
-  @jasonmatthewsuhari in
-  [#23073](https://github.com/google-gemini/gemini-cli/pull/23073)
- fix(core): narrow browser agent description to prevent stealing URL tasks from
-  web_fetch by @gsquared94 in
-  [#23086](https://github.com/google-gemini/gemini-cli/pull/23086)
- feat(cli): Partial threading of AgentLoopContext. by @joshualitt in
-  [#22978](https://github.com/google-gemini/gemini-cli/pull/22978)
- fix(browser-agent): enable "Allow all server tools" session policy by
+- feat(evals): centralize test agents into test-utils for reuse by @Samee24 in
+  [#23616](https://github.com/google-gemini/gemini-cli/pull/23616)
+- revert: chore(config): disable agents by default by @abhipatel12 in
+  [#23672](https://github.com/google-gemini/gemini-cli/pull/23672)
+- fix(plan): update telemetry attribute keys and add timestamp by @Adib234 in
+  [#23685](https://github.com/google-gemini/gemini-cli/pull/23685)
+- fix(core): prevent premature MCP discovery completion by @jackwotherspoon in
+  [#23637](https://github.com/google-gemini/gemini-cli/pull/23637)
+- feat(browser): add maxActionsPerTask for browser agent setting by
  @cynthialong0-0 in
-  [#22343](https://github.com/google-gemini/gemini-cli/pull/22343)
- refactor(cli): integrate real config loading into async test utils by
-  @scidomino in [#23040](https://github.com/google-gemini/gemini-cli/pull/23040)
- feat(core): inject memory and JIT context into subagents by @abhipatel12 in
-  [#23032](https://github.com/google-gemini/gemini-cli/pull/23032)
- Fix logging and virtual list. by @jacob314 in
-  [#23080](https://github.com/google-gemini/gemini-cli/pull/23080)
- feat(core): cap JIT context upward traversal at git root by @SandyTao520 in
-  [#23074](https://github.com/google-gemini/gemini-cli/pull/23074)
- Docs: Minor style updates from initial docs audit. by @g-samroberts in
-  [#22872](https://github.com/google-gemini/gemini-cli/pull/22872)
- feat(core): add experimental memory manager agent to replace save_memory tool
-  by @SandyTao520 in
-  [#22726](https://github.com/google-gemini/gemini-cli/pull/22726)
- Changelog for v0.35.0-preview.2 by @gemini-cli-robot in
-  [#23142](https://github.com/google-gemini/gemini-cli/pull/23142)
- Update website issue template for label and title by @g-samroberts in
-  [#23036](https://github.com/google-gemini/gemini-cli/pull/23036)
- fix: upgrade ACP SDK from 0.12 to 0.16.1 by @sripasg in
-  [#23132](https://github.com/google-gemini/gemini-cli/pull/23132)
- Update callouts to work on github. by @g-samroberts in
-  [#22245](https://github.com/google-gemini/gemini-cli/pull/22245)
- feat: ACP: Add token usage metadata to the `send` method's return value by
-  @sripasg in [#23148](https://github.com/google-gemini/gemini-cli/pull/23148)
- fix(plan): clarify that plan mode policies are combined with normal mode by
-  @ruomengz in [#23158](https://github.com/google-gemini/gemini-cli/pull/23158)
- Add ModelChain support to ModelConfigService and make ModelDialog dynamic by
-  @kevinjwang1 in
-  [#22914](https://github.com/google-gemini/gemini-cli/pull/22914)
- Ensure that copied extensions are writable in the user's local directory by
-  @kevinjwang1 in
-  [#23016](https://github.com/google-gemini/gemini-cli/pull/23016)
- feat(core): implement native Windows sandboxing by @mattKorwel in
-  [#21807](https://github.com/google-gemini/gemini-cli/pull/21807)
- feat(core): add support for admin-forced MCP server installations by
-  @gsquared94 in
-  [#23163](https://github.com/google-gemini/gemini-cli/pull/23163)
- chore(lint): ignore .gemini directory and recursive node_modules by
-  @mattKorwel in
-  [#23211](https://github.com/google-gemini/gemini-cli/pull/23211)
- feat(cli): conditionally exclude ask_user tool in ACP mode by @nmcnamara-eng
-  in [#23045](https://github.com/google-gemini/gemini-cli/pull/23045)
- feat(core): introduce AgentSession and rename stream events to agent events by
-  @mbleigh in [#23159](https://github.com/google-gemini/gemini-cli/pull/23159)
- feat(worktree): add Git worktree support for isolated parallel sessions by
-  @jerop in [#22973](https://github.com/google-gemini/gemini-cli/pull/22973)
- Add support for linking in the extension registry by @kevinjwang1 in
-  [#23153](https://github.com/google-gemini/gemini-cli/pull/23153)
- feat(extensions): add --skip-settings flag to install command by @Ratish1 in
-  [#17212](https://github.com/google-gemini/gemini-cli/pull/17212)
- feat(telemetry): track if session is running in a Git worktree by @jerop in
-  [#23265](https://github.com/google-gemini/gemini-cli/pull/23265)
- refactor(core): use absolute paths in GEMINI.md context markers by
-  @SandyTao520 in
-  [#23135](https://github.com/google-gemini/gemini-cli/pull/23135)
- fix(core): add sanitization to sub agent thoughts and centralize utilities by
-  @devr0306 in [#22828](https://github.com/google-gemini/gemini-cli/pull/22828)
- feat(core): refine User-Agent for VS Code traffic (unified format) by
-  @sehoon38 in [#23256](https://github.com/google-gemini/gemini-cli/pull/23256)
- Fix schema for ModelChains by @kevinjwang1 in
-  [#23284](https://github.com/google-gemini/gemini-cli/pull/23284)
- test(cli): refactor tests for async render utilities by @scidomino in
-  [#23252](https://github.com/google-gemini/gemini-cli/pull/23252)
- feat(core): add security prompt for browser agent by @cynthialong0-0 in
-  [#23241](https://github.com/google-gemini/gemini-cli/pull/23241)
- refactor(ide): replace dynamic undici import with static fetch import by
-  @cocosheng-g in
-  [#23268](https://github.com/google-gemini/gemini-cli/pull/23268)
- test(cli): address unresolved feedback from PR #23252 by @scidomino in
-  [#23303](https://github.com/google-gemini/gemini-cli/pull/23303)
- feat(browser): add sensitive action controls and read-only noise reduction by
-  @cynthialong0-0 in
-  [#22867](https://github.com/google-gemini/gemini-cli/pull/22867)
- Disabling failing test while investigating by @alisa-alisa in
-  [#23311](https://github.com/google-gemini/gemini-cli/pull/23311)
- fix broken extension link in hooks guide by @Indrapal-70 in
-  [#21728](https://github.com/google-gemini/gemini-cli/pull/21728)
- fix(core): fix agent description indentation by @abhipatel12 in
-  [#23315](https://github.com/google-gemini/gemini-cli/pull/23315)
- Wrap the text under TOML rule for easier readability in policy-engine.md… by
-  @CogitationOps in
-  [#23076](https://github.com/google-gemini/gemini-cli/pull/23076)
- fix(extensions): revert broken extension removal behavior by @ehedlund in
-  [#23317](https://github.com/google-gemini/gemini-cli/pull/23317)
- feat(core): set up onboarding telemetry by @yunaseoul in
-  [#23118](https://github.com/google-gemini/gemini-cli/pull/23118)
- Retry evals on API error. by @gundermanc in
-  [#23322](https://github.com/google-gemini/gemini-cli/pull/23322)
- fix(evals): remove tool restrictions and add compile-time guards by
-  @SandyTao520 in
-  [#23312](https://github.com/google-gemini/gemini-cli/pull/23312)
- fix(hooks): support 'ask' decision for BeforeTool hooks by @gundermanc in
-  [#21146](https://github.com/google-gemini/gemini-cli/pull/21146)
- feat(browser): add warning message for session mode 'existing' by
-  @cynthialong0-0 in
-  [#23288](https://github.com/google-gemini/gemini-cli/pull/23288)
- chore(lint): enforce zero warnings and cleanup syntax restrictions by
-  @alisa-alisa in
-  [#22902](https://github.com/google-gemini/gemini-cli/pull/22902)
- fix(cli): add Esc instruction to HooksDialog footer by @abhipatel12 in
-  [#23258](https://github.com/google-gemini/gemini-cli/pull/23258)
- Disallow and suppress misused spread operator. by @gundermanc in
-  [#23294](https://github.com/google-gemini/gemini-cli/pull/23294)
- fix(core): refine CliHelpAgent description for better delegation by
-  @abhipatel12 in
-  [#23310](https://github.com/google-gemini/gemini-cli/pull/23310)
- fix(core): enable global session and persistent approval for web_fetch by
-  @NTaylorMullen in
-  [#23295](https://github.com/google-gemini/gemini-cli/pull/23295)
- fix(plan): add state transition override to prevent plan mode freeze by
-  @Adib234 in [#23020](https://github.com/google-gemini/gemini-cli/pull/23020)
- fix(cli): record skill activation tool calls in chat history by @NTaylorMullen
-  in [#23203](https://github.com/google-gemini/gemini-cli/pull/23203)
- fix(core): ensure subagent tool updates apply configuration overrides
-  immediately by @abhipatel12 in
-  [#23161](https://github.com/google-gemini/gemini-cli/pull/23161)
- fix(cli): resolve flicker at boundaries of list in BaseSelectionList by
-  @jackwotherspoon in
-  [#23298](https://github.com/google-gemini/gemini-cli/pull/23298)
- test(cli): force generic terminal in tests to fix snapshot failures by
-  @abhipatel12 in
-  [#23499](https://github.com/google-gemini/gemini-cli/pull/23499)
- Evals: PR Guidance adding workflow by @alisa-alisa in
-  [#23164](https://github.com/google-gemini/gemini-cli/pull/23164)
- feat(core): refactor SandboxManager to a stateless architecture and introduce
-  explicit Deny interface by @ehedlund in
-  [#23141](https://github.com/google-gemini/gemini-cli/pull/23141)
- feat(core): add event-translator and update agent types by @adamfweidman in
-  [#22985](https://github.com/google-gemini/gemini-cli/pull/22985)
- perf(cli): parallelize and background startup cleanup tasks by @sehoon38 in
-  [#23545](https://github.com/google-gemini/gemini-cli/pull/23545)
- fix: "allow always" for commands with paths by @scidomino in
-  [#23558](https://github.com/google-gemini/gemini-cli/pull/23558)
- fix(cli): prevent terminal escape sequences from leaking on exit by
-  @mattKorwel in
-  [#22682](https://github.com/google-gemini/gemini-cli/pull/22682)
- feat(cli): implement full "GEMINI CLI" logo for logged-out state by
-  @keithguerin in
-  [#22412](https://github.com/google-gemini/gemini-cli/pull/22412)
- fix(plan): reserve minimum height for selection list in AskUserDialog by
-  @ruomengz in [#23280](https://github.com/google-gemini/gemini-cli/pull/23280)
- fix(core): harden AgentSession replay semantics by @adamfweidman in
-  [#23548](https://github.com/google-gemini/gemini-cli/pull/23548)
- test(core): migrate hook tests to scheduler by @abhipatel12 in
-  [#23496](https://github.com/google-gemini/gemini-cli/pull/23496)
- chore(config): disable agents by default by @abhipatel12 in
-  [#23546](https://github.com/google-gemini/gemini-cli/pull/23546)
- fix(ui): make tool confirmations take up entire terminal height by @devr0306
-  in [#22366](https://github.com/google-gemini/gemini-cli/pull/22366)
- fix(core): prevent redundant remote agent loading on model switch by
+  [#23216](https://github.com/google-gemini/gemini-cli/pull/23216)
+- fix(core): improve agent loader error formatting for empty paths by
  @adamfweidman in
-  [#23576](https://github.com/google-gemini/gemini-cli/pull/23576)
- refactor(core): update production type imports from coreToolScheduler by
-  @abhipatel12 in
-  [#23498](https://github.com/google-gemini/gemini-cli/pull/23498)
- feat(cli): always prefix extension skills with colon separator by
-  @NTaylorMullen in
-  [#23566](https://github.com/google-gemini/gemini-cli/pull/23566)
- fix(core): properly support allowRedirect in policy engine by @scidomino in
-  [#23579](https://github.com/google-gemini/gemini-cli/pull/23579)
- fix(cli): prevent subcommand shadowing and skip auth for commands by
+  [#23690](https://github.com/google-gemini/gemini-cli/pull/23690)
+- fix(cli): only show updating spinner when auto-update is in progress by
+  @scidomino in [#23709](https://github.com/google-gemini/gemini-cli/pull/23709)
+- Refine onboarding metrics to log the duration explicitly and use the tier
+  name. by @yunaseoul in
+  [#23678](https://github.com/google-gemini/gemini-cli/pull/23678)
+- chore(tools): add toJSON to tools and invocations to reduce logging verbosity
+  by @alisa-alisa in
+  [#22899](https://github.com/google-gemini/gemini-cli/pull/22899)
+- fix(cli): stabilize copy mode to prevent flickering and cursor resets by
  @mattKorwel in
-  [#23177](https://github.com/google-gemini/gemini-cli/pull/23177)
- fix(test): move flaky tests to non-blocking suite by @mattKorwel in
-  [#23259](https://github.com/google-gemini/gemini-cli/pull/23259)
- Changelog for v0.35.0-preview.3 by @gemini-cli-robot in
-  [#23574](https://github.com/google-gemini/gemini-cli/pull/23574)
- feat(skills): add behavioral-evals skill with fixing and promoting guides by
+  [#22584](https://github.com/google-gemini/gemini-cli/pull/22584)
+- fix(test): move flaky ctrl-c-exit test to non-blocking suite by @mattKorwel in
+  [#23732](https://github.com/google-gemini/gemini-cli/pull/23732)
+- feat(skills): add ci skill for automated failure replication by @mattKorwel in
+  [#23720](https://github.com/google-gemini/gemini-cli/pull/23720)
+- feat(sandbox): implement forbiddenPaths for OS-specific sandbox managers by
+  @ehedlund in [#23282](https://github.com/google-gemini/gemini-cli/pull/23282)
+- fix(core): conditionally expose additional_permissions in shell tool by
+  @galz10 in [#23729](https://github.com/google-gemini/gemini-cli/pull/23729)
+- refactor(core): standardize OS-specific sandbox tests and extract linux helper
+  methods by @ehedlund in
+  [#23715](https://github.com/google-gemini/gemini-cli/pull/23715)
+- format recently added script by @scidomino in
+  [#23739](https://github.com/google-gemini/gemini-cli/pull/23739)
+- fix(ui): prevent over-eager slash subcommand completion by @keithguerin in
+  [#20136](https://github.com/google-gemini/gemini-cli/pull/20136)
+- Fix dynamic model routing for gemini 3.1 pro to customtools model by
+  @kevinjwang1 in
+  [#23641](https://github.com/google-gemini/gemini-cli/pull/23641)
+- feat(core): support inline agentCardJson for remote agents by @adamfweidman in
+  [#23743](https://github.com/google-gemini/gemini-cli/pull/23743)
+- fix(cli): skip console log/info in headless mode by @cynthialong0-0 in
+  [#22739](https://github.com/google-gemini/gemini-cli/pull/22739)
+- test(core): install bubblewrap on Linux CI for sandbox integration tests by
+  @ehedlund in [#23583](https://github.com/google-gemini/gemini-cli/pull/23583)
+- docs(reference): split tools table into category sections by @sheikhlimon in
+  [#21516](https://github.com/google-gemini/gemini-cli/pull/21516)
+- fix(browser): detect embedded URLs in query params to prevent allowedDomains
+  bypass by @tony-shi in
+  [#23225](https://github.com/google-gemini/gemini-cli/pull/23225)
+- fix(browser): add proxy bypass constraint to domain restriction system prompt
+  by @tony-shi in
+  [#23229](https://github.com/google-gemini/gemini-cli/pull/23229)
+- fix(policy): relax write_file argsPattern in plan mode to allow paths without
+  session ID by @Adib234 in
+  [#23695](https://github.com/google-gemini/gemini-cli/pull/23695)
+- docs: fix grammar in CONTRIBUTING and numbering in sandbox docs by
+  @splint-disk-8i in
+  [#23448](https://github.com/google-gemini/gemini-cli/pull/23448)
+- fix(acp): allow attachments by adding a permission prompt by @sripasg in
+  [#23680](https://github.com/google-gemini/gemini-cli/pull/23680)
+- fix(core): thread AbortSignal to chat compression requests (#20405) by
+  @SH20RAJ in [#20778](https://github.com/google-gemini/gemini-cli/pull/20778)
+- feat(core): implement Windows sandbox dynamic expansion Phase 1 and 2.1 by
+  @scidomino in [#23691](https://github.com/google-gemini/gemini-cli/pull/23691)
+- Add note about root privileges in sandbox docs by @diodesign in
+  [#23314](https://github.com/google-gemini/gemini-cli/pull/23314)
+- docs(core): document agent_card_json string literal options for remote agents
+  by @adamfweidman in
+  [#23797](https://github.com/google-gemini/gemini-cli/pull/23797)
+- fix(cli): resolve TTY hang on headless environments by unconditionally
+  resuming process.stdin before React Ink launch by @cocosheng-g in
+  [#23673](https://github.com/google-gemini/gemini-cli/pull/23673)
+- fix(ui): cleanup estimated string length hacks in composer by @keithguerin in
+  [#23694](https://github.com/google-gemini/gemini-cli/pull/23694)
+- feat(browser): dynamically discover read-only tools by @cynthialong0-0 in
+  [#23805](https://github.com/google-gemini/gemini-cli/pull/23805)
+- docs: clarify policy requirement for `general.plan.directory` in settings
+  schema by @jerop in
+  [#23784](https://github.com/google-gemini/gemini-cli/pull/23784)
+- Revert "perf(cli): optimize --version startup time (#23671)" by @scidomino in
+  [#23812](https://github.com/google-gemini/gemini-cli/pull/23812)
+- don't silence errors from wombat by @scidomino in
+  [#23822](https://github.com/google-gemini/gemini-cli/pull/23822)
+- fix(ui): prevent escape key from cancelling requests in shell mode by
+  @PrasannaPal21 in
+  [#21245](https://github.com/google-gemini/gemini-cli/pull/21245)
+- Changelog for v0.36.0-preview.0 by @gemini-cli-robot in
+  [#23702](https://github.com/google-gemini/gemini-cli/pull/23702)
+- feat(core,ui): Add experiment-gated support for gemini flash 3.1 lite by
+  @chrstnb in [#23794](https://github.com/google-gemini/gemini-cli/pull/23794)
+- Changelog for v0.36.0-preview.3 by @gemini-cli-robot in
+  [#23827](https://github.com/google-gemini/gemini-cli/pull/23827)
+- new linting check: github-actions-pinning by @alisa-alisa in
+  [#23808](https://github.com/google-gemini/gemini-cli/pull/23808)
+- fix(cli): show helpful guidance when no skills are available by @Niralisj in
+  [#23785](https://github.com/google-gemini/gemini-cli/pull/23785)
+- fix: Chat logs and errors handle tail tool calls correctly by @googlestrobe in
+  [#22460](https://github.com/google-gemini/gemini-cli/pull/22460)
+- Don't try removing a tag from a non-existent release. by @scidomino in
+  [#23830](https://github.com/google-gemini/gemini-cli/pull/23830)
+- fix(cli): allow ask question dialog to take full window height by @jacob314 in
+  [#23693](https://github.com/google-gemini/gemini-cli/pull/23693)
+- fix(core): strip leading underscores from error types in telemetry by
+  @yunaseoul in [#23824](https://github.com/google-gemini/gemini-cli/pull/23824)
+- Changelog for v0.35.0 by @gemini-cli-robot in
+  [#23819](https://github.com/google-gemini/gemini-cli/pull/23819)
+- feat(evals): add reliability harvester and 500/503 retry support by
+  @alisa-alisa in
+  [#23626](https://github.com/google-gemini/gemini-cli/pull/23626)
+- feat(sandbox): dynamic Linux sandbox expansion and worktree support by @galz10
+  in [#23692](https://github.com/google-gemini/gemini-cli/pull/23692)
+- Merge examples of use into quickstart documentation by @diodesign in
+  [#23319](https://github.com/google-gemini/gemini-cli/pull/23319)
+- fix(cli): prioritize primary name matches in slash command search by @sehoon38
+  in [#23850](https://github.com/google-gemini/gemini-cli/pull/23850)
+- Changelog for v0.35.1 by @gemini-cli-robot in
+  [#23840](https://github.com/google-gemini/gemini-cli/pull/23840)
+- fix(browser): keep input blocker active across navigations by @kunal-10-cloud
+  in [#22562](https://github.com/google-gemini/gemini-cli/pull/22562)
+- feat(core): new skill to look for duplicated code while reviewing PRs by
+  @devr0306 in [#23704](https://github.com/google-gemini/gemini-cli/pull/23704)
+- fix(core): replace hardcoded non-interactive ASK_USER denial with explicit
+  policy rules by @ruomengz in
+  [#23668](https://github.com/google-gemini/gemini-cli/pull/23668)
+- fix(plan): after exiting plan mode switches model to a flash model by @Adib234
+  in [#23885](https://github.com/google-gemini/gemini-cli/pull/23885)
+- feat(gcp): add development worker infrastructure by @mattKorwel in
+  [#23814](https://github.com/google-gemini/gemini-cli/pull/23814)
+- fix(a2a-server): A2A server should execute ask policies in interactive mode by
+  @kschaab in [#23831](https://github.com/google-gemini/gemini-cli/pull/23831)
+- feat(core): define TrajectoryProvider interface by @sehoon38 in
+  [#23050](https://github.com/google-gemini/gemini-cli/pull/23050)
+- Docs: Update quotas and pricing by @jkcinouye in
+  [#23835](https://github.com/google-gemini/gemini-cli/pull/23835)
+- fix(core): allow disabling environment variable redaction by @galz10 in
+  [#23927](https://github.com/google-gemini/gemini-cli/pull/23927)
+- feat(cli): enable notifications cross-platform via terminal bell fallback by
+  @genneth in [#21618](https://github.com/google-gemini/gemini-cli/pull/21618)
+- feat(sandbox): implement secret visibility lockdown for env files by
+  @DavidAPierce in
+  [#23712](https://github.com/google-gemini/gemini-cli/pull/23712)
+- fix(core): remove shell outputChunks buffer caching to prevent memory bloat
+  and sanitize prompt input by @spencer426 in
+  [#23751](https://github.com/google-gemini/gemini-cli/pull/23751)
+- feat(core): implement persistent browser session management by @kunal-10-cloud
+  in [#21306](https://github.com/google-gemini/gemini-cli/pull/21306)
+- refactor(core): delegate sandbox denial parsing to SandboxManager by
+  @scidomino in [#23928](https://github.com/google-gemini/gemini-cli/pull/23928)
+- dep(update) Update Ink version to 6.5.0 by @jacob314 in
+  [#23843](https://github.com/google-gemini/gemini-cli/pull/23843)
+- Docs: Update 'docs-writer' skill for relative links by @jkcinouye in
+  [#21463](https://github.com/google-gemini/gemini-cli/pull/21463)
+- Changelog for v0.36.0-preview.4 by @gemini-cli-robot in
+  [#23935](https://github.com/google-gemini/gemini-cli/pull/23935)
+- fix(acp): Update allow approval policy flow for ACP clients to fix config
+  persistence and compatible with TUI by @sripasg in
+  [#23818](https://github.com/google-gemini/gemini-cli/pull/23818)
+- Changelog for v0.35.2 by @gemini-cli-robot in
+  [#23960](https://github.com/google-gemini/gemini-cli/pull/23960)
+- ACP integration documents by @g-samroberts in
+  [#22254](https://github.com/google-gemini/gemini-cli/pull/22254)
+- fix(core): explicitly set error names to avoid bundling renaming issues by
+  @yunaseoul in [#23913](https://github.com/google-gemini/gemini-cli/pull/23913)
+- feat(core): subagent isolation and cleanup hardening by @abhipatel12 in
+  [#23903](https://github.com/google-gemini/gemini-cli/pull/23903)
+- disable extension-reload test by @scidomino in
+  [#24018](https://github.com/google-gemini/gemini-cli/pull/24018)
+- feat(core): add forbiddenPaths to GlobalSandboxOptions and refactor
+  createSandboxManager by @ehedlund in
+  [#23936](https://github.com/google-gemini/gemini-cli/pull/23936)
+- refactor(core): improve ignore resolution and fix directory-matching bug by
+  @ehedlund in [#23816](https://github.com/google-gemini/gemini-cli/pull/23816)
+- revert(core): support custom base URL via env vars by @spencer426 in
+  [#23976](https://github.com/google-gemini/gemini-cli/pull/23976)
+- Increase memory limited for eslint. by @jacob314 in
+  [#24022](https://github.com/google-gemini/gemini-cli/pull/24022)
+- fix(acp): prevent crash on empty response in ACP mode by @sripasg in
+  [#23952](https://github.com/google-gemini/gemini-cli/pull/23952)
+- feat(core): Land `AgentHistoryProvider`. by @joshualitt in
+  [#23978](https://github.com/google-gemini/gemini-cli/pull/23978)
+- fix(core): switch to subshells for shell tool wrapping to fix heredocs and
+  edge cases by @abhipatel12 in
+  [#24024](https://github.com/google-gemini/gemini-cli/pull/24024)
+- Debug command. by @jacob314 in
+  [#23851](https://github.com/google-gemini/gemini-cli/pull/23851)
+- Changelog for v0.36.0-preview.5 by @gemini-cli-robot in
+  [#24046](https://github.com/google-gemini/gemini-cli/pull/24046)
+- Fix test flakes by globally mocking ink-spinner by @jacob314 in
+  [#24044](https://github.com/google-gemini/gemini-cli/pull/24044)
+- Enable network access in sandbox configuration by @galz10 in
+  [#24055](https://github.com/google-gemini/gemini-cli/pull/24055)
+- feat(context): add configurable memoryBoundaryMarkers setting by @SandyTao520
+  in [#24020](https://github.com/google-gemini/gemini-cli/pull/24020)
+- feat(core): implement windows sandbox expansion and denial detection by
+  @scidomino in [#24027](https://github.com/google-gemini/gemini-cli/pull/24027)
+- fix(core): resolve ACP Operation Aborted Errors in grep_search by @ivanporty
+  in [#23821](https://github.com/google-gemini/gemini-cli/pull/23821)
+- fix(hooks): prevent SessionEnd from firing twice in non-interactive mode by
+  @krishdef7 in [#22139](https://github.com/google-gemini/gemini-cli/pull/22139)
+- Re-word intro to Gemini 3 page. by @g-samroberts in
+  [#24069](https://github.com/google-gemini/gemini-cli/pull/24069)
+- fix(cli): resolve layout contention and flashing loop in StatusRow by
+  @keithguerin in
+  [#24065](https://github.com/google-gemini/gemini-cli/pull/24065)
+- fix(sandbox): implement Windows Mandatory Integrity Control for GeminiSandbox
+  by @galz10 in [#24057](https://github.com/google-gemini/gemini-cli/pull/24057)
+- feat(core): implement tool-based topic grouping (Chapters) by @Abhijit-2592 in
+  [#23150](https://github.com/google-gemini/gemini-cli/pull/23150)
+- feat(cli): support 'tab to queue' for messages while generating by @gundermanc
+  in [#24052](https://github.com/google-gemini/gemini-cli/pull/24052)
+- feat(core): agnostic background task UI with CompletionBehavior by
+  @adamfweidman in
+  [#22740](https://github.com/google-gemini/gemini-cli/pull/22740)
+- UX for topic narration tool by @gundermanc in
+  [#24079](https://github.com/google-gemini/gemini-cli/pull/24079)
+- fix: shellcheck warnings in scripts by @scidomino in
+  [#24035](https://github.com/google-gemini/gemini-cli/pull/24035)
+- test(evals): add comprehensive subagent delegation evaluations by @abhipatel12
+  in [#24132](https://github.com/google-gemini/gemini-cli/pull/24132)
+- fix(a2a-server): prioritize ADC before evaluating headless constraints for
+  auth initialization by @spencer426 in
+  [#23614](https://github.com/google-gemini/gemini-cli/pull/23614)
+- Text can be added after /plan command by @rambleraptor in
+  [#22833](https://github.com/google-gemini/gemini-cli/pull/22833)
+- fix(cli): resolve missing F12 logs via global console store by @scidomino in
+  [#24235](https://github.com/google-gemini/gemini-cli/pull/24235)
+- fix broken tests by @scidomino in
+  [#24279](https://github.com/google-gemini/gemini-cli/pull/24279)
+- fix(evals): add update_topic behavioral eval by @gundermanc in
+  [#24223](https://github.com/google-gemini/gemini-cli/pull/24223)
+- feat(core): Unified Context Management and Tool Distillation. by @joshualitt
+  in [#24157](https://github.com/google-gemini/gemini-cli/pull/24157)
+- Default enable narration for the team. by @gundermanc in
+  [#24224](https://github.com/google-gemini/gemini-cli/pull/24224)
+- fix(core): ensure default agents provide tools and use model-specific schemas
+  by @abhipatel12 in
+  [#24268](https://github.com/google-gemini/gemini-cli/pull/24268)
+- feat(cli): show Flash Lite Preview model regardless of user tier by @sehoon38
+  in [#23904](https://github.com/google-gemini/gemini-cli/pull/23904)
+- feat(cli): implement compact tool output by @jwhelangoog in
+  [#20974](https://github.com/google-gemini/gemini-cli/pull/20974)
+- Add security settings for tool sandboxing by @galz10 in
+  [#23923](https://github.com/google-gemini/gemini-cli/pull/23923)
+- chore(test-utils): switch integration tests to use PREVIEW_GEMINI_MODEL by
+  @sehoon38 in [#24276](https://github.com/google-gemini/gemini-cli/pull/24276)
+- feat(core): enable topic update narration for legacy models by @Abhijit-2592
+  in [#24241](https://github.com/google-gemini/gemini-cli/pull/24241)
+- feat(core): add project-level memory scope to save_memory tool by @SandyTao520
+  in [#24161](https://github.com/google-gemini/gemini-cli/pull/24161)
+- test(integration): fix plan mode write denial test false positive by @sehoon38
+  in [#24299](https://github.com/google-gemini/gemini-cli/pull/24299)
+- feat(plan): support `Plan` mode in untrusted folders by @Adib234 in
+  [#17586](https://github.com/google-gemini/gemini-cli/pull/17586)
+- fix(core): enable mid-stream retries for all models and re-enable compression
+  test by @sehoon38 in
+  [#24302](https://github.com/google-gemini/gemini-cli/pull/24302)
+- Changelog for v0.36.0-preview.6 by @gemini-cli-robot in
+  [#24082](https://github.com/google-gemini/gemini-cli/pull/24082)
+- Changelog for v0.35.3 by @gemini-cli-robot in
+  [#24083](https://github.com/google-gemini/gemini-cli/pull/24083)
+- feat(cli): add auth info to footer by @sehoon38 in
+  [#24042](https://github.com/google-gemini/gemini-cli/pull/24042)
+- fix(browser): reset action counter for each agent session and let it ignore
+  internal actions by @cynthialong0-0 in
+  [#24228](https://github.com/google-gemini/gemini-cli/pull/24228)
+- feat(plan): promote planning feature to stable by @ruomengz in
+  [#24282](https://github.com/google-gemini/gemini-cli/pull/24282)
+- fix(browser): terminate subagent immediately on domain restriction violations
+  by @gsquared94 in
+  [#24313](https://github.com/google-gemini/gemini-cli/pull/24313)
+- feat(cli): add UI to update extensions by @ruomengz in
+  [#23682](https://github.com/google-gemini/gemini-cli/pull/23682)
+- Fix(browser): terminate immediately for "browser is already running" error by
+  @cynthialong0-0 in
+  [#24233](https://github.com/google-gemini/gemini-cli/pull/24233)
+- docs: Add 'plan' option to approval mode in CLI reference by @YifanRuan in
+  [#24134](https://github.com/google-gemini/gemini-cli/pull/24134)
+- fix(core): batch macOS seatbelt rules into a profile file to prevent ARG_MAX
+  errors by @ehedlund in
+  [#24255](https://github.com/google-gemini/gemini-cli/pull/24255)
+- fix(core): fix race condition between browser agent and main closing process
+  by @cynthialong0-0 in
+  [#24340](https://github.com/google-gemini/gemini-cli/pull/24340)
+- perf(build): optimize build scripts for parallel execution and remove
+  redundant checks by @sehoon38 in
+  [#24307](https://github.com/google-gemini/gemini-cli/pull/24307)
+- ci: install bubblewrap on Linux for release workflows by @ehedlund in
+  [#24347](https://github.com/google-gemini/gemini-cli/pull/24347)
+- chore(release): allow bundling for all builds, including stable by @sehoon38
+  in [#24305](https://github.com/google-gemini/gemini-cli/pull/24305)
+- Revert "Add security settings for tool sandboxing" by @jerop in
+  [#24357](https://github.com/google-gemini/gemini-cli/pull/24357)
+- docs: update subagents docs to not be experimental by @abhipatel12 in
+  [#24343](https://github.com/google-gemini/gemini-cli/pull/24343)
+- fix(core): implement **read and **write commands in sandbox managers by
+  @galz10 in [#24283](https://github.com/google-gemini/gemini-cli/pull/24283)
+- don't try to remove tags in dry run by @scidomino in
+  [#24356](https://github.com/google-gemini/gemini-cli/pull/24356)
+- fix(config): disable JIT context loading by default by @SandyTao520 in
+  [#24364](https://github.com/google-gemini/gemini-cli/pull/24364)
+- test(sandbox): add integration test for dynamic permission expansion by
+  @galz10 in [#24359](https://github.com/google-gemini/gemini-cli/pull/24359)
+- docs(policy): remove unsupported mcpName wildcard edge case by @abhipatel12 in
+  [#24133](https://github.com/google-gemini/gemini-cli/pull/24133)
+- docs: fix broken GEMINI.md link in CONTRIBUTING.md by @Panchal-Tirth in
+  [#24182](https://github.com/google-gemini/gemini-cli/pull/24182)
+- feat(core): infrastructure for event-driven subagent history by @abhipatel12
+  in [#23914](https://github.com/google-gemini/gemini-cli/pull/23914)
+- fix(core): resolve Plan Mode deadlock during plan file creation due to sandbox
+  restrictions by @DavidAPierce in
+  [#24047](https://github.com/google-gemini/gemini-cli/pull/24047)
+- fix(core): fix browser agent UX issues and improve E2E test reliability by
+  @gsquared94 in
+  [#24312](https://github.com/google-gemini/gemini-cli/pull/24312)
+- fix(ui): wrap topic and intent fields in TopicMessage by @jwhelangoog in
+  [#24386](https://github.com/google-gemini/gemini-cli/pull/24386)
+- refactor(core): Centralize context management logic into src/context by
+  @joshualitt in
+  [#24380](https://github.com/google-gemini/gemini-cli/pull/24380)
+- fix(core): pin AuthType.GATEWAY to use Gemini 3.1 Pro/Flash Lite by default by
+  @sripasg in [#24375](https://github.com/google-gemini/gemini-cli/pull/24375)
+- feat(ui): add Tokyo Night theme by @danrneal in
+  [#24054](https://github.com/google-gemini/gemini-cli/pull/24054)
+- fix(cli): refactor test config loading and mock debugLogger in test-setup by
+  @mattKorwel in
+  [#24389](https://github.com/google-gemini/gemini-cli/pull/24389)
+- Set memoryManager to false in settings.json by @mattKorwel in
+  [#24393](https://github.com/google-gemini/gemini-cli/pull/24393)
+- ink 6.6.3 by @jacob314 in
+  [#24372](https://github.com/google-gemini/gemini-cli/pull/24372)
+- fix(core): resolve subagent chat recording gaps and directory inheritance by
  @abhipatel12 in
-  [#23349](https://github.com/google-gemini/gemini-cli/pull/23349)
- refactor(core): delete obsolete coreToolScheduler by @abhipatel12 in
-  [#23502](https://github.com/google-gemini/gemini-cli/pull/23502)
- Changelog for v0.35.0-preview.4 by @gemini-cli-robot in
-  [#23581](https://github.com/google-gemini/gemini-cli/pull/23581)
- feat(core): add LegacyAgentSession by @adamfweidman in
-  [#22986](https://github.com/google-gemini/gemini-cli/pull/22986)
- feat(test-utils): add TestMcpServerBuilder and support in TestRig by
-  @abhipatel12 in
-  [#23491](https://github.com/google-gemini/gemini-cli/pull/23491)
- fix(core)!: Force policy config to specify toolName by @kschaab in
-  [#23330](https://github.com/google-gemini/gemini-cli/pull/23330)
- eval(save_memory): add multi-turn interactive evals for memoryManager by
-  @SandyTao520 in
-  [#23572](https://github.com/google-gemini/gemini-cli/pull/23572)
- fix(telemetry): patch memory leak and enforce logPrompts privacy by
-  @spencer426 in
-  [#23281](https://github.com/google-gemini/gemini-cli/pull/23281)
- perf(cli): background IDE client to speed up initialization by @sehoon38 in
-  [#23603](https://github.com/google-gemini/gemini-cli/pull/23603)
- fix(cli): prevent Ctrl+D exit when input buffer is not empty by @wtanaka in
-  [#23306](https://github.com/google-gemini/gemini-cli/pull/23306)
- fix: ACP: separate conversational text from execute tool command title by
-  @sripasg in [#23179](https://github.com/google-gemini/gemini-cli/pull/23179)
- feat(evals): add behavioral evaluations for subagent routing by @Samee24 in
-  [#23272](https://github.com/google-gemini/gemini-cli/pull/23272)
- refactor(cli,core): foundational layout, identity management, and type safety
-  by @jwhelangoog in
-  [#23286](https://github.com/google-gemini/gemini-cli/pull/23286)
- fix(core): accurately reflect subagent tool failure in UI by @abhipatel12 in
-  [#23187](https://github.com/google-gemini/gemini-cli/pull/23187)
- Changelog for v0.35.0-preview.5 by @gemini-cli-robot in
-  [#23606](https://github.com/google-gemini/gemini-cli/pull/23606)
- feat(ui): implement refreshed UX for Composer layout by @jwhelangoog in
-  [#21212](https://github.com/google-gemini/gemini-cli/pull/21212)
- fix: API key input dialog user interaction when selected Gemini API Key by
-  @kartikangiras in
-  [#21057](https://github.com/google-gemini/gemini-cli/pull/21057)
- docs: update `/mcp refresh` to `/mcp reload` by @adamfweidman in
-  [#23631](https://github.com/google-gemini/gemini-cli/pull/23631)
- Implementation of sandbox "Write-Protected" Governance Files by @DavidAPierce
-  in [#23139](https://github.com/google-gemini/gemini-cli/pull/23139)
- feat(sandbox): dynamic macOS sandbox expansion and worktree support by @galz10
-  in [#23301](https://github.com/google-gemini/gemini-cli/pull/23301)
- fix(acp): Pass the cwd to `AcpFileSystemService` to avoid looping failures in
-  asking for perms to write plan md file by @sripasg in
-  [#23612](https://github.com/google-gemini/gemini-cli/pull/23612)
- fix(plan): sandbox path resolution in Plan Mode to prevent hallucinations by
-  @Adib234 in [#22737](https://github.com/google-gemini/gemini-cli/pull/22737)
- feat(ui): allow immediate user input during startup by @sehoon38 in
-  [#23661](https://github.com/google-gemini/gemini-cli/pull/23661)
- refactor(sandbox): reorganize Windows sandbox files by @galz10 in
-  [#23645](https://github.com/google-gemini/gemini-cli/pull/23645)
- fix(core): improve remote agent streaming UI and UX by @adamfweidman in
-  [#23633](https://github.com/google-gemini/gemini-cli/pull/23633)
- perf(cli): optimize --version startup time by @sehoon38 in
-  [#23671](https://github.com/google-gemini/gemini-cli/pull/23671)
- refactor(core): stop gemini CLI from producing unsafe casts by @gundermanc in
-  [#23611](https://github.com/google-gemini/gemini-cli/pull/23611)
- use enableAutoUpdate in test rig by @scidomino in
-  [#23681](https://github.com/google-gemini/gemini-cli/pull/23681)
- feat(core): change user-facing auth type from oauth2 to oauth by @adamfweidman
-  in [#23639](https://github.com/google-gemini/gemini-cli/pull/23639)
- chore(deps): fix npm audit vulnerabilities by @scidomino in
-  [#23679](https://github.com/google-gemini/gemini-cli/pull/23679)
- test(evals): fix overlapping act() deadlock in app-test-helper by @Adib234 in
-  [#23666](https://github.com/google-gemini/gemini-cli/pull/23666)
- fix(patch): cherry-pick 055ff92 to release/v0.36.0-preview.0-pr-23672 to patch
-  version v0.36.0-preview.0 and create version 0.36.0-preview.1 by
+  [#24368](https://github.com/google-gemini/gemini-cli/pull/24368)
+- fix(cli): cap shell output at 10 MB to prevent RangeError crash by @ProthamD
+  in [#24168](https://github.com/google-gemini/gemini-cli/pull/24168)
+- feat(plan): conditionally add enter/exit plan mode tools based on current mode
+  by @ruomengz in
+  [#24378](https://github.com/google-gemini/gemini-cli/pull/24378)
+- feat(core): prioritize discussion before formal plan approval by @jerop in
+  [#24423](https://github.com/google-gemini/gemini-cli/pull/24423)
+- fix(ui): add accelerated scrolling on alternate buffer mode by @devr0306 in
+  [#23940](https://github.com/google-gemini/gemini-cli/pull/23940)
+- feat(core): populate sandbox forbidden paths with project ignore file contents
+  by @ehedlund in
+  [#24038](https://github.com/google-gemini/gemini-cli/pull/24038)
+- fix(core): ensure blue border overlay and input blocker to act correctly
+  depending on browser agent activities by @cynthialong0-0 in
+  [#24385](https://github.com/google-gemini/gemini-cli/pull/24385)
+- fix(ui): removed additional vertical padding for tables by @devr0306 in
+  [#24381](https://github.com/google-gemini/gemini-cli/pull/24381)
+- fix(build): upload full bundle directory archive to GitHub releases by
+  @sehoon38 in [#24403](https://github.com/google-gemini/gemini-cli/pull/24403)
+- fix(build): wire bundle:browser-mcp into bundle pipeline by @gsquared94 in
+  [#24424](https://github.com/google-gemini/gemini-cli/pull/24424)
+- feat(browser): add sandbox-aware browser agent initialization by @gsquared94
+  in [#24419](https://github.com/google-gemini/gemini-cli/pull/24419)
+- feat(core): enhance tracker task schemas for detailed titles and descriptions
+  by @anj-s in [#23902](https://github.com/google-gemini/gemini-cli/pull/23902)
+- refactor(core): Unified context management settings schema by @joshualitt in
+  [#24391](https://github.com/google-gemini/gemini-cli/pull/24391)
+- feat(core): update browser agent prompt to check open pages first when
+  bringing up by @cynthialong0-0 in
+  [#24431](https://github.com/google-gemini/gemini-cli/pull/24431)
+- fix(acp) refactor(core,cli): centralize model discovery logic in
+  ModelConfigService by @sripasg in
+  [#24392](https://github.com/google-gemini/gemini-cli/pull/24392)
+- Changelog for v0.36.0-preview.7 by @gemini-cli-robot in
+  [#24346](https://github.com/google-gemini/gemini-cli/pull/24346)
+- fix: update task tracker storage location in system prompt by @anj-s in
+  [#24034](https://github.com/google-gemini/gemini-cli/pull/24034)
+- feat(browser): supersede stale snapshots to reclaim context-window tokens by
+  @gsquared94 in
+  [#24440](https://github.com/google-gemini/gemini-cli/pull/24440)
+- docs(core): add subagent tool isolation draft doc by @akh64bit in
+  [#23275](https://github.com/google-gemini/gemini-cli/pull/23275)
+- fix(patch): cherry-pick 64c928f to release/v0.37.0-preview.0-pr-23257 to patch
+  version v0.37.0-preview.0 and create version 0.37.0-preview.1 by
  @gemini-cli-robot in
-  [#23723](https://github.com/google-gemini/gemini-cli/pull/23723)
- fix(patch): cherry-pick 765fb67 to release/v0.36.0-preview.5-pr-24055 to patch
-  version v0.36.0-preview.5 and create version 0.36.0-preview.6 by
+  [#24561](https://github.com/google-gemini/gemini-cli/pull/24561)
+- fix(patch): cherry-pick cb7f7d6 to release/v0.37.0-preview.1-pr-24342 to patch
+  version v0.37.0-preview.1 and create version 0.37.0-preview.2 by
  @gemini-cli-robot in
-  [#24061](https://github.com/google-gemini/gemini-cli/pull/24061)
+  [#24842](https://github.com/google-gemini/gemini-cli/pull/24842)

 **Full Changelog**:
-https://github.com/google-gemini/gemini-cli/compare/v0.35.3...v0.36.0
+https://github.com/google-gemini/gemini-cli/compare/v0.36.0...v0.37.0
@@ -1,6 +1,6 @@
-# Preview release: v0.37.0-preview.2
+# Preview release: v0.38.0-preview.0

-Released: April 07, 2026
+Released: April 08, 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).
@@ -13,414 +13,256 @@ npm install -g @google/gemini-cli@preview

 ## Highlights

- **Plan Mode Enhancements**: Plan now includes support for untrusted folders,
-  prioritized pre-approval discussions, and a resolve for sandbox-related
-  deadlocks during file creation.
- **Browser Agent Evolved**: Significant updates to the browser agent, including
-  persistent session management, dynamic discovery of read-only tools,
-  sandbox-aware initialization, and automated reclamation of stale snapshots to
-  optimize context window usage.
- **Advanced Sandbox Security**: Implementation of dynamic sandbox expansion for
-  both Linux and Windows, alongside secret visibility lockdown for environment
-  files and OS-specific forbidden path support.
- **Unified Core Architecture**: Centralized context management and a new
-  `ModelConfigService` for unified model discovery, complemented by the
-  introduction of `AgentHistoryProvider` and tool-based topic grouping
-  (Chapters).
- **UI/UX & Performance Improvements**: New Tokyo Night theme, "tab to queue"
-  message support, and compact tool output formatting, plus optimized build
-  scripts and improved layout stability for TUI components.
+- **Context Management:** Introduced a Context Compression Service to optimize
+  context window usage and landed a background memory service for skill
+  extraction.
+- **Enhanced Security:** Implemented context-aware persistent policy approvals
+  for smarter tool permissions and enabled `web_fetch` in plan mode with user
+  confirmation.
+- **Workflow Monitoring:** Added background process monitoring and inspection
+  tools for better visibility into long-running tasks.
+- **UI/UX Refinements:** Enhanced the tool confirmation UI, selection layout,
+  and added support for selective topic expansion and click-to-expand.
+- **Core Stability:** Improved sandbox reliability on Linux and Windows,
+  resolved shebang compatibility issues, and fixed various crashes in the CLI
+  and core services.

 ## What's Changed

- fix(patch): cherry-pick cb7f7d6 to release/v0.37.0-preview.1-pr-24342 to patch
-  version v0.37.0-preview.1 and create version 0.37.0-preview.2 by
-  @gemini-cli-robot in
-  [#24842](https://github.com/google-gemini/gemini-cli/pull/24842)
- fix(patch): cherry-pick 64c928f to release/v0.37.0-preview.0-pr-23257 to patch
-  version v0.37.0-preview.0 and create version 0.37.0-preview.1 by
-  @gemini-cli-robot in
-  [#24561](https://github.com/google-gemini/gemini-cli/pull/24561)
- feat(evals): centralize test agents into test-utils for reuse by @Samee24 in
-  [#23616](https://github.com/google-gemini/gemini-cli/pull/23616)
- revert: chore(config): disable agents by default by @abhipatel12 in
-  [#23672](https://github.com/google-gemini/gemini-cli/pull/23672)
- fix(plan): update telemetry attribute keys and add timestamp by @Adib234 in
-  [#23685](https://github.com/google-gemini/gemini-cli/pull/23685)
- fix(core): prevent premature MCP discovery completion by @jackwotherspoon in
-  [#23637](https://github.com/google-gemini/gemini-cli/pull/23637)
- feat(browser): add maxActionsPerTask for browser agent setting by
-  @cynthialong0-0 in
-  [#23216](https://github.com/google-gemini/gemini-cli/pull/23216)
- fix(core): improve agent loader error formatting for empty paths by
-  @adamfweidman in
-  [#23690](https://github.com/google-gemini/gemini-cli/pull/23690)
- fix(cli): only show updating spinner when auto-update is in progress by
-  @scidomino in [#23709](https://github.com/google-gemini/gemini-cli/pull/23709)
- Refine onboarding metrics to log the duration explicitly and use the tier
-  name. by @yunaseoul in
-  [#23678](https://github.com/google-gemini/gemini-cli/pull/23678)
- chore(tools): add toJSON to tools and invocations to reduce logging verbosity
-  by @alisa-alisa in
-  [#22899](https://github.com/google-gemini/gemini-cli/pull/22899)
- fix(cli): stabilize copy mode to prevent flickering and cursor resets by
-  @mattKorwel in
-  [#22584](https://github.com/google-gemini/gemini-cli/pull/22584)
- fix(test): move flaky ctrl-c-exit test to non-blocking suite by @mattKorwel in
-  [#23732](https://github.com/google-gemini/gemini-cli/pull/23732)
- feat(skills): add ci skill for automated failure replication by @mattKorwel in
-  [#23720](https://github.com/google-gemini/gemini-cli/pull/23720)
- feat(sandbox): implement forbiddenPaths for OS-specific sandbox managers by
-  @ehedlund in [#23282](https://github.com/google-gemini/gemini-cli/pull/23282)
- fix(core): conditionally expose additional_permissions in shell tool by
-  @galz10 in [#23729](https://github.com/google-gemini/gemini-cli/pull/23729)
- refactor(core): standardize OS-specific sandbox tests and extract linux helper
-  methods by @ehedlund in
-  [#23715](https://github.com/google-gemini/gemini-cli/pull/23715)
- format recently added script by @scidomino in
-  [#23739](https://github.com/google-gemini/gemini-cli/pull/23739)
- fix(ui): prevent over-eager slash subcommand completion by @keithguerin in
-  [#20136](https://github.com/google-gemini/gemini-cli/pull/20136)
- Fix dynamic model routing for gemini 3.1 pro to customtools model by
-  @kevinjwang1 in
-  [#23641](https://github.com/google-gemini/gemini-cli/pull/23641)
- feat(core): support inline agentCardJson for remote agents by @adamfweidman in
-  [#23743](https://github.com/google-gemini/gemini-cli/pull/23743)
- fix(cli): skip console log/info in headless mode by @cynthialong0-0 in
-  [#22739](https://github.com/google-gemini/gemini-cli/pull/22739)
- test(core): install bubblewrap on Linux CI for sandbox integration tests by
-  @ehedlund in [#23583](https://github.com/google-gemini/gemini-cli/pull/23583)
- docs(reference): split tools table into category sections by @sheikhlimon in
-  [#21516](https://github.com/google-gemini/gemini-cli/pull/21516)
- fix(browser): detect embedded URLs in query params to prevent allowedDomains
-  bypass by @tony-shi in
-  [#23225](https://github.com/google-gemini/gemini-cli/pull/23225)
- fix(browser): add proxy bypass constraint to domain restriction system prompt
-  by @tony-shi in
-  [#23229](https://github.com/google-gemini/gemini-cli/pull/23229)
- fix(policy): relax write_file argsPattern in plan mode to allow paths without
-  session ID by @Adib234 in
-  [#23695](https://github.com/google-gemini/gemini-cli/pull/23695)
- docs: fix grammar in CONTRIBUTING and numbering in sandbox docs by
-  @splint-disk-8i in
-  [#23448](https://github.com/google-gemini/gemini-cli/pull/23448)
- fix(acp): allow attachments by adding a permission prompt by @sripasg in
-  [#23680](https://github.com/google-gemini/gemini-cli/pull/23680)
- fix(core): thread AbortSignal to chat compression requests (#20405) by
-  @SH20RAJ in [#20778](https://github.com/google-gemini/gemini-cli/pull/20778)
- feat(core): implement Windows sandbox dynamic expansion Phase 1 and 2.1 by
-  @scidomino in [#23691](https://github.com/google-gemini/gemini-cli/pull/23691)
- Add note about root privileges in sandbox docs by @diodesign in
-  [#23314](https://github.com/google-gemini/gemini-cli/pull/23314)
- docs(core): document agent_card_json string literal options for remote agents
-  by @adamfweidman in
-  [#23797](https://github.com/google-gemini/gemini-cli/pull/23797)
- fix(cli): resolve TTY hang on headless environments by unconditionally
-  resuming process.stdin before React Ink launch by @cocosheng-g in
-  [#23673](https://github.com/google-gemini/gemini-cli/pull/23673)
- fix(ui): cleanup estimated string length hacks in composer by @keithguerin in
-  [#23694](https://github.com/google-gemini/gemini-cli/pull/23694)
- feat(browser): dynamically discover read-only tools by @cynthialong0-0 in
-  [#23805](https://github.com/google-gemini/gemini-cli/pull/23805)
- docs: clarify policy requirement for `general.plan.directory` in settings
-  schema by @jerop in
-  [#23784](https://github.com/google-gemini/gemini-cli/pull/23784)
- Revert "perf(cli): optimize --version startup time (#23671)" by @scidomino in
-  [#23812](https://github.com/google-gemini/gemini-cli/pull/23812)
- don't silence errors from wombat by @scidomino in
-  [#23822](https://github.com/google-gemini/gemini-cli/pull/23822)
- fix(ui): prevent escape key from cancelling requests in shell mode by
-  @PrasannaPal21 in
-  [#21245](https://github.com/google-gemini/gemini-cli/pull/21245)
- Changelog for v0.36.0-preview.0 by @gemini-cli-robot in
-  [#23702](https://github.com/google-gemini/gemini-cli/pull/23702)
- feat(core,ui): Add experiment-gated support for gemini flash 3.1 lite by
-  @chrstnb in [#23794](https://github.com/google-gemini/gemini-cli/pull/23794)
- Changelog for v0.36.0-preview.3 by @gemini-cli-robot in
-  [#23827](https://github.com/google-gemini/gemini-cli/pull/23827)
- new linting check: github-actions-pinning by @alisa-alisa in
-  [#23808](https://github.com/google-gemini/gemini-cli/pull/23808)
- fix(cli): show helpful guidance when no skills are available by @Niralisj in
-  [#23785](https://github.com/google-gemini/gemini-cli/pull/23785)
- fix: Chat logs and errors handle tail tool calls correctly by @googlestrobe in
-  [#22460](https://github.com/google-gemini/gemini-cli/pull/22460)
- Don't try removing a tag from a non-existent release. by @scidomino in
-  [#23830](https://github.com/google-gemini/gemini-cli/pull/23830)
- fix(cli): allow ask question dialog to take full window height by @jacob314 in
-  [#23693](https://github.com/google-gemini/gemini-cli/pull/23693)
- fix(core): strip leading underscores from error types in telemetry by
-  @yunaseoul in [#23824](https://github.com/google-gemini/gemini-cli/pull/23824)
- Changelog for v0.35.0 by @gemini-cli-robot in
-  [#23819](https://github.com/google-gemini/gemini-cli/pull/23819)
- feat(evals): add reliability harvester and 500/503 retry support by
-  @alisa-alisa in
-  [#23626](https://github.com/google-gemini/gemini-cli/pull/23626)
- feat(sandbox): dynamic Linux sandbox expansion and worktree support by @galz10
-  in [#23692](https://github.com/google-gemini/gemini-cli/pull/23692)
- Merge examples of use into quickstart documentation by @diodesign in
-  [#23319](https://github.com/google-gemini/gemini-cli/pull/23319)
- fix(cli): prioritize primary name matches in slash command search by @sehoon38
-  in [#23850](https://github.com/google-gemini/gemini-cli/pull/23850)
- Changelog for v0.35.1 by @gemini-cli-robot in
-  [#23840](https://github.com/google-gemini/gemini-cli/pull/23840)
- fix(browser): keep input blocker active across navigations by @kunal-10-cloud
-  in [#22562](https://github.com/google-gemini/gemini-cli/pull/22562)
- feat(core): new skill to look for duplicated code while reviewing PRs by
-  @devr0306 in [#23704](https://github.com/google-gemini/gemini-cli/pull/23704)
- fix(core): replace hardcoded non-interactive ASK_USER denial with explicit
-  policy rules by @ruomengz in
-  [#23668](https://github.com/google-gemini/gemini-cli/pull/23668)
- fix(plan): after exiting plan mode switches model to a flash model by @Adib234
-  in [#23885](https://github.com/google-gemini/gemini-cli/pull/23885)
- feat(gcp): add development worker infrastructure by @mattKorwel in
-  [#23814](https://github.com/google-gemini/gemini-cli/pull/23814)
- fix(a2a-server): A2A server should execute ask policies in interactive mode by
-  @kschaab in [#23831](https://github.com/google-gemini/gemini-cli/pull/23831)
- feat(core): define TrajectoryProvider interface by @sehoon38 in
-  [#23050](https://github.com/google-gemini/gemini-cli/pull/23050)
- Docs: Update quotas and pricing by @jkcinouye in
-  [#23835](https://github.com/google-gemini/gemini-cli/pull/23835)
- fix(core): allow disabling environment variable redaction by @galz10 in
-  [#23927](https://github.com/google-gemini/gemini-cli/pull/23927)
- feat(cli): enable notifications cross-platform via terminal bell fallback by
-  @genneth in [#21618](https://github.com/google-gemini/gemini-cli/pull/21618)
- feat(sandbox): implement secret visibility lockdown for env files by
-  @DavidAPierce in
-  [#23712](https://github.com/google-gemini/gemini-cli/pull/23712)
- fix(core): remove shell outputChunks buffer caching to prevent memory bloat
-  and sanitize prompt input by @spencer426 in
-  [#23751](https://github.com/google-gemini/gemini-cli/pull/23751)
- feat(core): implement persistent browser session management by @kunal-10-cloud
-  in [#21306](https://github.com/google-gemini/gemini-cli/pull/21306)
- refactor(core): delegate sandbox denial parsing to SandboxManager by
-  @scidomino in [#23928](https://github.com/google-gemini/gemini-cli/pull/23928)
- dep(update) Update Ink version to 6.5.0 by @jacob314 in
-  [#23843](https://github.com/google-gemini/gemini-cli/pull/23843)
- Docs: Update 'docs-writer' skill for relative links by @jkcinouye in
-  [#21463](https://github.com/google-gemini/gemini-cli/pull/21463)
- Changelog for v0.36.0-preview.4 by @gemini-cli-robot in
-  [#23935](https://github.com/google-gemini/gemini-cli/pull/23935)
- fix(acp): Update allow approval policy flow for ACP clients to fix config
-  persistence and compatible with TUI by @sripasg in
-  [#23818](https://github.com/google-gemini/gemini-cli/pull/23818)
- Changelog for v0.35.2 by @gemini-cli-robot in
-  [#23960](https://github.com/google-gemini/gemini-cli/pull/23960)
- ACP integration documents by @g-samroberts in
-  [#22254](https://github.com/google-gemini/gemini-cli/pull/22254)
- fix(core): explicitly set error names to avoid bundling renaming issues by
-  @yunaseoul in [#23913](https://github.com/google-gemini/gemini-cli/pull/23913)
- feat(core): subagent isolation and cleanup hardening by @abhipatel12 in
-  [#23903](https://github.com/google-gemini/gemini-cli/pull/23903)
- disable extension-reload test by @scidomino in
-  [#24018](https://github.com/google-gemini/gemini-cli/pull/24018)
- feat(core): add forbiddenPaths to GlobalSandboxOptions and refactor
-  createSandboxManager by @ehedlund in
-  [#23936](https://github.com/google-gemini/gemini-cli/pull/23936)
- refactor(core): improve ignore resolution and fix directory-matching bug by
-  @ehedlund in [#23816](https://github.com/google-gemini/gemini-cli/pull/23816)
- revert(core): support custom base URL via env vars by @spencer426 in
-  [#23976](https://github.com/google-gemini/gemini-cli/pull/23976)
- Increase memory limited for eslint. by @jacob314 in
-  [#24022](https://github.com/google-gemini/gemini-cli/pull/24022)
- fix(acp): prevent crash on empty response in ACP mode by @sripasg in
-  [#23952](https://github.com/google-gemini/gemini-cli/pull/23952)
- feat(core): Land `AgentHistoryProvider`. by @joshualitt in
-  [#23978](https://github.com/google-gemini/gemini-cli/pull/23978)
- fix(core): switch to subshells for shell tool wrapping to fix heredocs and
-  edge cases by @abhipatel12 in
-  [#24024](https://github.com/google-gemini/gemini-cli/pull/24024)
- Debug command. by @jacob314 in
-  [#23851](https://github.com/google-gemini/gemini-cli/pull/23851)
- Changelog for v0.36.0-preview.5 by @gemini-cli-robot in
-  [#24046](https://github.com/google-gemini/gemini-cli/pull/24046)
- Fix test flakes by globally mocking ink-spinner by @jacob314 in
-  [#24044](https://github.com/google-gemini/gemini-cli/pull/24044)
- Enable network access in sandbox configuration by @galz10 in
-  [#24055](https://github.com/google-gemini/gemini-cli/pull/24055)
- feat(context): add configurable memoryBoundaryMarkers setting by @SandyTao520
-  in [#24020](https://github.com/google-gemini/gemini-cli/pull/24020)
- feat(core): implement windows sandbox expansion and denial detection by
-  @scidomino in [#24027](https://github.com/google-gemini/gemini-cli/pull/24027)
- fix(core): resolve ACP Operation Aborted Errors in grep_search by @ivanporty
-  in [#23821](https://github.com/google-gemini/gemini-cli/pull/23821)
- fix(hooks): prevent SessionEnd from firing twice in non-interactive mode by
-  @krishdef7 in [#22139](https://github.com/google-gemini/gemini-cli/pull/22139)
- Re-word intro to Gemini 3 page. by @g-samroberts in
-  [#24069](https://github.com/google-gemini/gemini-cli/pull/24069)
- fix(cli): resolve layout contention and flashing loop in StatusRow by
-  @keithguerin in
-  [#24065](https://github.com/google-gemini/gemini-cli/pull/24065)
- fix(sandbox): implement Windows Mandatory Integrity Control for GeminiSandbox
-  by @galz10 in [#24057](https://github.com/google-gemini/gemini-cli/pull/24057)
- feat(core): implement tool-based topic grouping (Chapters) by @Abhijit-2592 in
-  [#23150](https://github.com/google-gemini/gemini-cli/pull/23150)
- feat(cli): support 'tab to queue' for messages while generating by @gundermanc
-  in [#24052](https://github.com/google-gemini/gemini-cli/pull/24052)
- feat(core): agnostic background task UI with CompletionBehavior by
-  @adamfweidman in
-  [#22740](https://github.com/google-gemini/gemini-cli/pull/22740)
- UX for topic narration tool by @gundermanc in
-  [#24079](https://github.com/google-gemini/gemini-cli/pull/24079)
- fix: shellcheck warnings in scripts by @scidomino in
-  [#24035](https://github.com/google-gemini/gemini-cli/pull/24035)
- test(evals): add comprehensive subagent delegation evaluations by @abhipatel12
-  in [#24132](https://github.com/google-gemini/gemini-cli/pull/24132)
- fix(a2a-server): prioritize ADC before evaluating headless constraints for
-  auth initialization by @spencer426 in
-  [#23614](https://github.com/google-gemini/gemini-cli/pull/23614)
- Text can be added after /plan command by @rambleraptor in
-  [#22833](https://github.com/google-gemini/gemini-cli/pull/22833)
- fix(cli): resolve missing F12 logs via global console store by @scidomino in
-  [#24235](https://github.com/google-gemini/gemini-cli/pull/24235)
- fix broken tests by @scidomino in
-  [#24279](https://github.com/google-gemini/gemini-cli/pull/24279)
- fix(evals): add update_topic behavioral eval by @gundermanc in
-  [#24223](https://github.com/google-gemini/gemini-cli/pull/24223)
- feat(core): Unified Context Management and Tool Distillation. by @joshualitt
-  in [#24157](https://github.com/google-gemini/gemini-cli/pull/24157)
- Default enable narration for the team. by @gundermanc in
-  [#24224](https://github.com/google-gemini/gemini-cli/pull/24224)
- fix(core): ensure default agents provide tools and use model-specific schemas
-  by @abhipatel12 in
-  [#24268](https://github.com/google-gemini/gemini-cli/pull/24268)
- feat(cli): show Flash Lite Preview model regardless of user tier by @sehoon38
-  in [#23904](https://github.com/google-gemini/gemini-cli/pull/23904)
- feat(cli): implement compact tool output by @jwhelangoog in
-  [#20974](https://github.com/google-gemini/gemini-cli/pull/20974)
- Add security settings for tool sandboxing by @galz10 in
-  [#23923](https://github.com/google-gemini/gemini-cli/pull/23923)
- chore(test-utils): switch integration tests to use PREVIEW_GEMINI_MODEL by
-  @sehoon38 in [#24276](https://github.com/google-gemini/gemini-cli/pull/24276)
- feat(core): enable topic update narration for legacy models by @Abhijit-2592
-  in [#24241](https://github.com/google-gemini/gemini-cli/pull/24241)
- feat(core): add project-level memory scope to save_memory tool by @SandyTao520
-  in [#24161](https://github.com/google-gemini/gemini-cli/pull/24161)
- test(integration): fix plan mode write denial test false positive by @sehoon38
-  in [#24299](https://github.com/google-gemini/gemini-cli/pull/24299)
- feat(plan): support `Plan` mode in untrusted folders by @Adib234 in
-  [#17586](https://github.com/google-gemini/gemini-cli/pull/17586)
- fix(core): enable mid-stream retries for all models and re-enable compression
-  test by @sehoon38 in
-  [#24302](https://github.com/google-gemini/gemini-cli/pull/24302)
- Changelog for v0.36.0-preview.6 by @gemini-cli-robot in
-  [#24082](https://github.com/google-gemini/gemini-cli/pull/24082)
- Changelog for v0.35.3 by @gemini-cli-robot in
-  [#24083](https://github.com/google-gemini/gemini-cli/pull/24083)
- feat(cli): add auth info to footer by @sehoon38 in
-  [#24042](https://github.com/google-gemini/gemini-cli/pull/24042)
- fix(browser): reset action counter for each agent session and let it ignore
-  internal actions by @cynthialong0-0 in
-  [#24228](https://github.com/google-gemini/gemini-cli/pull/24228)
- feat(plan): promote planning feature to stable by @ruomengz in
-  [#24282](https://github.com/google-gemini/gemini-cli/pull/24282)
- fix(browser): terminate subagent immediately on domain restriction violations
-  by @gsquared94 in
-  [#24313](https://github.com/google-gemini/gemini-cli/pull/24313)
- feat(cli): add UI to update extensions by @ruomengz in
-  [#23682](https://github.com/google-gemini/gemini-cli/pull/23682)
- Fix(browser): terminate immediately for "browser is already running" error by
-  @cynthialong0-0 in
-  [#24233](https://github.com/google-gemini/gemini-cli/pull/24233)
- docs: Add 'plan' option to approval mode in CLI reference by @YifanRuan in
-  [#24134](https://github.com/google-gemini/gemini-cli/pull/24134)
- fix(core): batch macOS seatbelt rules into a profile file to prevent ARG_MAX
-  errors by @ehedlund in
-  [#24255](https://github.com/google-gemini/gemini-cli/pull/24255)
- fix(core): fix race condition between browser agent and main closing process
-  by @cynthialong0-0 in
-  [#24340](https://github.com/google-gemini/gemini-cli/pull/24340)
- perf(build): optimize build scripts for parallel execution and remove
-  redundant checks by @sehoon38 in
-  [#24307](https://github.com/google-gemini/gemini-cli/pull/24307)
- ci: install bubblewrap on Linux for release workflows by @ehedlund in
-  [#24347](https://github.com/google-gemini/gemini-cli/pull/24347)
- chore(release): allow bundling for all builds, including stable by @sehoon38
-  in [#24305](https://github.com/google-gemini/gemini-cli/pull/24305)
- Revert "Add security settings for tool sandboxing" by @jerop in
-  [#24357](https://github.com/google-gemini/gemini-cli/pull/24357)
- docs: update subagents docs to not be experimental by @abhipatel12 in
-  [#24343](https://github.com/google-gemini/gemini-cli/pull/24343)
- fix(core): implement **read and **write commands in sandbox managers by
-  @galz10 in [#24283](https://github.com/google-gemini/gemini-cli/pull/24283)
- don't try to remove tags in dry run by @scidomino in
-  [#24356](https://github.com/google-gemini/gemini-cli/pull/24356)
- fix(config): disable JIT context loading by default by @SandyTao520 in
-  [#24364](https://github.com/google-gemini/gemini-cli/pull/24364)
- test(sandbox): add integration test for dynamic permission expansion by
-  @galz10 in [#24359](https://github.com/google-gemini/gemini-cli/pull/24359)
- docs(policy): remove unsupported mcpName wildcard edge case by @abhipatel12 in
-  [#24133](https://github.com/google-gemini/gemini-cli/pull/24133)
- docs: fix broken GEMINI.md link in CONTRIBUTING.md by @Panchal-Tirth in
-  [#24182](https://github.com/google-gemini/gemini-cli/pull/24182)
- feat(core): infrastructure for event-driven subagent history by @abhipatel12
-  in [#23914](https://github.com/google-gemini/gemini-cli/pull/23914)
- fix(core): resolve Plan Mode deadlock during plan file creation due to sandbox
-  restrictions by @DavidAPierce in
-  [#24047](https://github.com/google-gemini/gemini-cli/pull/24047)
- fix(core): fix browser agent UX issues and improve E2E test reliability by
-  @gsquared94 in
-  [#24312](https://github.com/google-gemini/gemini-cli/pull/24312)
- fix(ui): wrap topic and intent fields in TopicMessage by @jwhelangoog in
-  [#24386](https://github.com/google-gemini/gemini-cli/pull/24386)
- refactor(core): Centralize context management logic into src/context by
-  @joshualitt in
-  [#24380](https://github.com/google-gemini/gemini-cli/pull/24380)
- fix(core): pin AuthType.GATEWAY to use Gemini 3.1 Pro/Flash Lite by default by
-  @sripasg in [#24375](https://github.com/google-gemini/gemini-cli/pull/24375)
- feat(ui): add Tokyo Night theme by @danrneal in
-  [#24054](https://github.com/google-gemini/gemini-cli/pull/24054)
- fix(cli): refactor test config loading and mock debugLogger in test-setup by
-  @mattKorwel in
-  [#24389](https://github.com/google-gemini/gemini-cli/pull/24389)
- Set memoryManager to false in settings.json by @mattKorwel in
-  [#24393](https://github.com/google-gemini/gemini-cli/pull/24393)
- ink 6.6.3 by @jacob314 in
-  [#24372](https://github.com/google-gemini/gemini-cli/pull/24372)
- fix(core): resolve subagent chat recording gaps and directory inheritance by
+- fix(cli): refresh slash command list after /skills reload by @NTaylorMullen in
+  [#24454](https://github.com/google-gemini/gemini-cli/pull/24454)
+- Update README.md for links. by @g-samroberts in
+  [#22759](https://github.com/google-gemini/gemini-cli/pull/22759)
+- fix(core): ensure complete_task tool calls are recorded in chat history by
  @abhipatel12 in
-  [#24368](https://github.com/google-gemini/gemini-cli/pull/24368)
- fix(cli): cap shell output at 10 MB to prevent RangeError crash by @ProthamD
-  in [#24168](https://github.com/google-gemini/gemini-cli/pull/24168)
- feat(plan): conditionally add enter/exit plan mode tools based on current mode
-  by @ruomengz in
-  [#24378](https://github.com/google-gemini/gemini-cli/pull/24378)
- feat(core): prioritize discussion before formal plan approval by @jerop in
-  [#24423](https://github.com/google-gemini/gemini-cli/pull/24423)
- fix(ui): add accelerated scrolling on alternate buffer mode by @devr0306 in
-  [#23940](https://github.com/google-gemini/gemini-cli/pull/23940)
- feat(core): populate sandbox forbidden paths with project ignore file contents
-  by @ehedlund in
-  [#24038](https://github.com/google-gemini/gemini-cli/pull/24038)
- fix(core): ensure blue border overlay and input blocker to act correctly
-  depending on browser agent activities by @cynthialong0-0 in
-  [#24385](https://github.com/google-gemini/gemini-cli/pull/24385)
- fix(ui): removed additional vertical padding for tables by @devr0306 in
-  [#24381](https://github.com/google-gemini/gemini-cli/pull/24381)
- fix(build): upload full bundle directory archive to GitHub releases by
-  @sehoon38 in [#24403](https://github.com/google-gemini/gemini-cli/pull/24403)
- fix(build): wire bundle:browser-mcp into bundle pipeline by @gsquared94 in
-  [#24424](https://github.com/google-gemini/gemini-cli/pull/24424)
- feat(browser): add sandbox-aware browser agent initialization by @gsquared94
-  in [#24419](https://github.com/google-gemini/gemini-cli/pull/24419)
- feat(core): enhance tracker task schemas for detailed titles and descriptions
-  by @anj-s in [#23902](https://github.com/google-gemini/gemini-cli/pull/23902)
- refactor(core): Unified context management settings schema by @joshualitt in
-  [#24391](https://github.com/google-gemini/gemini-cli/pull/24391)
- feat(core): update browser agent prompt to check open pages first when
-  bringing up by @cynthialong0-0 in
-  [#24431](https://github.com/google-gemini/gemini-cli/pull/24431)
- fix(acp) refactor(core,cli): centralize model discovery logic in
-  ModelConfigService by @sripasg in
-  [#24392](https://github.com/google-gemini/gemini-cli/pull/24392)
- Changelog for v0.36.0-preview.7 by @gemini-cli-robot in
-  [#24346](https://github.com/google-gemini/gemini-cli/pull/24346)
- fix: update task tracker storage location in system prompt by @anj-s in
-  [#24034](https://github.com/google-gemini/gemini-cli/pull/24034)
- feat(browser): supersede stale snapshots to reclaim context-window tokens by
+  [#24437](https://github.com/google-gemini/gemini-cli/pull/24437)
+- feat(policy): explicitly allow web_fetch in plan mode with ask_user by
+  @Adib234 in [#24456](https://github.com/google-gemini/gemini-cli/pull/24456)
+- fix(core): refactor linux sandbox to fix ARG_MAX crashes by @ehedlund in
+  [#24286](https://github.com/google-gemini/gemini-cli/pull/24286)
+- feat(config): add experimental.adk.agentSessionNoninteractiveEnabled setting
+  by @adamfweidman in
+  [#24439](https://github.com/google-gemini/gemini-cli/pull/24439)
+- Changelog for v0.36.0-preview.8 by @gemini-cli-robot in
+  [#24453](https://github.com/google-gemini/gemini-cli/pull/24453)
+- feat(cli): change default loadingPhrases to 'off' to hide tips by @keithguerin
+  in [#24342](https://github.com/google-gemini/gemini-cli/pull/24342)
+- fix(cli): ensure agent stops when all declinable tools are cancelled by
+  @NTaylorMullen in
+  [#24479](https://github.com/google-gemini/gemini-cli/pull/24479)
+- fix(core): enhance sandbox usability and fix build error by @galz10 in
+  [#24460](https://github.com/google-gemini/gemini-cli/pull/24460)
+- Terminal Serializer Optimization by @jacob314 in
+  [#24485](https://github.com/google-gemini/gemini-cli/pull/24485)
+- Auto configure memory. by @jacob314 in
+  [#24474](https://github.com/google-gemini/gemini-cli/pull/24474)
+- Unused error variables in catch block are not allowed by @alisa-alisa in
+  [#24487](https://github.com/google-gemini/gemini-cli/pull/24487)
+- feat(core): add background memory service for skill extraction by @SandyTao520
+  in [#24274](https://github.com/google-gemini/gemini-cli/pull/24274)
+- feat: implement high-signal PR regression check for evaluations by
+  @alisa-alisa in
+  [#23937](https://github.com/google-gemini/gemini-cli/pull/23937)
+- Fix shell output display by @jacob314 in
+  [#24490](https://github.com/google-gemini/gemini-cli/pull/24490)
+- fix(ui): resolve unwanted vertical spacing around various tool output
+  treatments by @jwhelangoog in
+  [#24449](https://github.com/google-gemini/gemini-cli/pull/24449)
+- revert(cli): bring back input box and footer visibility in copy mode by
+  @sehoon38 in [#24504](https://github.com/google-gemini/gemini-cli/pull/24504)
+- fix(cli): prevent crash in AnsiOutputText when handling non-array data by
+  @sehoon38 in [#24498](https://github.com/google-gemini/gemini-cli/pull/24498)
+- feat(cli): support default values for environment variables by @ruomengz in
+  [#24469](https://github.com/google-gemini/gemini-cli/pull/24469)
+- Implement background process monitoring and inspection tools by @cocosheng-g
+  in [#23799](https://github.com/google-gemini/gemini-cli/pull/23799)
+- docs(browser-agent): update stale browser agent documentation by @gsquared94
+  in [#24463](https://github.com/google-gemini/gemini-cli/pull/24463)
+- fix: enable browser_agent in integration tests and add localhost fixture tests
+  by @gsquared94 in
+  [#24523](https://github.com/google-gemini/gemini-cli/pull/24523)
+- fix(browser): handle computer-use model detection for analyze_screenshot by
  @gsquared94 in
-  [#24440](https://github.com/google-gemini/gemini-cli/pull/24440)
- docs(core): add subagent tool isolation draft doc by @akh64bit in
-  [#23275](https://github.com/google-gemini/gemini-cli/pull/23275)
+  [#24502](https://github.com/google-gemini/gemini-cli/pull/24502)
+- feat(core): Land ContextCompressionService by @joshualitt in
+  [#24483](https://github.com/google-gemini/gemini-cli/pull/24483)
+- feat(core): scope subagent workspace directories via AsyncLocalStorage by
+  @SandyTao520 in
+  [#24445](https://github.com/google-gemini/gemini-cli/pull/24445)
+- Update ink version to 6.6.7 by @jacob314 in
+  [#24514](https://github.com/google-gemini/gemini-cli/pull/24514)
+- fix(acp): handle all InvalidStreamError types gracefully in prompt by @sripasg
+  in [#24540](https://github.com/google-gemini/gemini-cli/pull/24540)
+- Fix crash when vim editor is not found in PATH on Windows by
+  @Nagajyothi-tammisetti in
+  [#22423](https://github.com/google-gemini/gemini-cli/pull/22423)
+- fix(core): move project memory dir under tmp directory by @SandyTao520 in
+  [#24542](https://github.com/google-gemini/gemini-cli/pull/24542)
+- Enable 'Other' option for yesno question type by @ruomengz in
+  [#24545](https://github.com/google-gemini/gemini-cli/pull/24545)
+- fix(cli): clear stale retry/loading state after cancellation (#21096) by
+  @Aaxhirrr in [#21960](https://github.com/google-gemini/gemini-cli/pull/21960)
+- Changelog for v0.37.0-preview.0 by @gemini-cli-robot in
+  [#24464](https://github.com/google-gemini/gemini-cli/pull/24464)
+- feat(core): implement context-aware persistent policy approvals by @jerop in
+  [#23257](https://github.com/google-gemini/gemini-cli/pull/23257)
+- docs: move agent disabling instructions and update remote agent status by
+  @jackwotherspoon in
+  [#24559](https://github.com/google-gemini/gemini-cli/pull/24559)
+- feat(cli): migrate nonInteractiveCli to LegacyAgentSession by @adamfweidman in
+  [#22987](https://github.com/google-gemini/gemini-cli/pull/22987)
+- fix(core): unsafe type assertions in Core File System #19712 by
+  @aniketsaurav18 in
+  [#19739](https://github.com/google-gemini/gemini-cli/pull/19739)
+- fix(ui): hide model quota in /stats and refactor quota display by @danzaharia1
+  in [#24206](https://github.com/google-gemini/gemini-cli/pull/24206)
+- Changelog for v0.36.0 by @gemini-cli-robot in
+  [#24558](https://github.com/google-gemini/gemini-cli/pull/24558)
+- Changelog for v0.37.0-preview.1 by @gemini-cli-robot in
+  [#24568](https://github.com/google-gemini/gemini-cli/pull/24568)
+- docs: add missing .md extensions to internal doc links by @ishaan-arora-1 in
+  [#24145](https://github.com/google-gemini/gemini-cli/pull/24145)
+- fix(ui): fixed table styling by @devr0306 in
+  [#24565](https://github.com/google-gemini/gemini-cli/pull/24565)
+- fix(core): pass includeDirectories to sandbox configuration by @galz10 in
+  [#24573](https://github.com/google-gemini/gemini-cli/pull/24573)
+- feat(ui): enable "TerminalBuffer" mode to solve flicker by @jacob314 in
+  [#24512](https://github.com/google-gemini/gemini-cli/pull/24512)
+- docs: clarify release coordination by @scidomino in
+  [#24575](https://github.com/google-gemini/gemini-cli/pull/24575)
+- fix(core): remove broken PowerShell translation and fix native \_\_write in
+  Windows sandbox by @scidomino in
+  [#24571](https://github.com/google-gemini/gemini-cli/pull/24571)
+- Add instructions for how to start react in prod and force react to prod mode
+  by @jacob314 in
+  [#24590](https://github.com/google-gemini/gemini-cli/pull/24590)
+- feat(cli): minimalist sandbox status labels by @galz10 in
+  [#24582](https://github.com/google-gemini/gemini-cli/pull/24582)
+- Feat/browser agent metrics by @kunal-10-cloud in
+  [#24210](https://github.com/google-gemini/gemini-cli/pull/24210)
+- test: fix Windows CI execution and resolve exposed platform failures by
+  @ehedlund in [#24476](https://github.com/google-gemini/gemini-cli/pull/24476)
+- feat(core,cli): prioritize summary for topics (#24608) by @Abhijit-2592 in
+  [#24609](https://github.com/google-gemini/gemini-cli/pull/24609)
+- show color by @jacob314 in
+  [#24613](https://github.com/google-gemini/gemini-cli/pull/24613)
+- feat(cli): enable compact tool output by default (#24509) by @jwhelangoog in
+  [#24510](https://github.com/google-gemini/gemini-cli/pull/24510)
+- fix(core): inject skill system instructions into subagent prompts if activated
+  by @abhipatel12 in
+  [#24620](https://github.com/google-gemini/gemini-cli/pull/24620)
+- fix(core): improve windows sandbox reliability and fix integration tests by
+  @ehedlund in [#24480](https://github.com/google-gemini/gemini-cli/pull/24480)
+- fix(core): ensure sandbox approvals are correctly persisted and matched for
+  proactive expansions by @galz10 in
+  [#24577](https://github.com/google-gemini/gemini-cli/pull/24577)
+- feat(cli) Scrollbar for input prompt by @jacob314 in
+  [#21992](https://github.com/google-gemini/gemini-cli/pull/21992)
+- Do not run pr-eval workflow when no steering changes detected by @alisa-alisa
+  in [#24621](https://github.com/google-gemini/gemini-cli/pull/24621)
+- Fix restoration of topic headers. by @gundermanc in
+  [#24650](https://github.com/google-gemini/gemini-cli/pull/24650)
+- feat(core): discourage update topic tool for simple tasks by @Samee24 in
+  [#24640](https://github.com/google-gemini/gemini-cli/pull/24640)
+- fix(core): ensure global temp directory is always in sandbox allowed paths by
+  @galz10 in [#24638](https://github.com/google-gemini/gemini-cli/pull/24638)
+- fix(core): detect uninitialized lines by @jacob314 in
+  [#24646](https://github.com/google-gemini/gemini-cli/pull/24646)
+- docs: update sandboxing documentation and toolSandboxing settings by @galz10
+  in [#24655](https://github.com/google-gemini/gemini-cli/pull/24655)
+- feat(cli): enhance tool confirmation UI and selection layout by @galz10 in
+  [#24376](https://github.com/google-gemini/gemini-cli/pull/24376)
+- feat(acp): add support for `/about` command by @sripasg in
+  [#24649](https://github.com/google-gemini/gemini-cli/pull/24649)
+- feat(cli): add role specific metrics to /stats by @cynthialong0-0 in
+  [#24659](https://github.com/google-gemini/gemini-cli/pull/24659)
+- split context by @jacob314 in
+  [#24623](https://github.com/google-gemini/gemini-cli/pull/24623)
+- fix(cli): remove -S from shebang to fix Windows and BSD execution by
+  @scidomino in [#24756](https://github.com/google-gemini/gemini-cli/pull/24756)
+- Fix issue where topic headers can be posted back to back by @gundermanc in
+  [#24759](https://github.com/google-gemini/gemini-cli/pull/24759)
+- fix(core): handle partial llm_request in BeforeModel hook override by
+  @krishdef7 in [#22326](https://github.com/google-gemini/gemini-cli/pull/22326)
+- fix(ui): improve narration suppression and reduce flicker by @gundermanc in
+  [#24635](https://github.com/google-gemini/gemini-cli/pull/24635)
+- fix(ui): fixed auth race condition causing logo to flicker by @devr0306 in
+  [#24652](https://github.com/google-gemini/gemini-cli/pull/24652)
+- fix(browser): remove premature browser cleanup after subagent invocation by
+  @gsquared94 in
+  [#24753](https://github.com/google-gemini/gemini-cli/pull/24753)
+- Revert "feat(core,cli): prioritize summary for topics (#24608)" by
+  @Abhijit-2592 in
+  [#24777](https://github.com/google-gemini/gemini-cli/pull/24777)
+- relax tool sandboxing overrides for plan mode to match defaults. by
+  @DavidAPierce in
+  [#24762](https://github.com/google-gemini/gemini-cli/pull/24762)
+- fix(cli): respect global environment variable allowlist by @scidomino in
+  [#24767](https://github.com/google-gemini/gemini-cli/pull/24767)
+- fix(cli): ensure skills list outputs to stdout in non-interactive environments
+  by @spencer426 in
+  [#24566](https://github.com/google-gemini/gemini-cli/pull/24566)
+- Add an eval for and fix unsafe cloning behavior. by @gundermanc in
+  [#24457](https://github.com/google-gemini/gemini-cli/pull/24457)
+- fix(policy): allow complete_task in plan mode by @abhipatel12 in
+  [#24771](https://github.com/google-gemini/gemini-cli/pull/24771)
+- feat(telemetry): add browser agent clearcut metrics by @gsquared94 in
+  [#24688](https://github.com/google-gemini/gemini-cli/pull/24688)
+- feat(cli): support selective topic expansion and click-to-expand by
+  @Abhijit-2592 in
+  [#24793](https://github.com/google-gemini/gemini-cli/pull/24793)
+- temporarily disable sandbox integration test on windows by @ehedlund in
+  [#24786](https://github.com/google-gemini/gemini-cli/pull/24786)
+- Remove flakey test by @scidomino in
+  [#24837](https://github.com/google-gemini/gemini-cli/pull/24837)
+- Alisa/approve button by @alisa-alisa in
+  [#24645](https://github.com/google-gemini/gemini-cli/pull/24645)
+- feat(hooks): display hook system messages in UI by @mbleigh in
+  [#24616](https://github.com/google-gemini/gemini-cli/pull/24616)
+- fix(core): propagate BeforeModel hook model override end-to-end by @krishdef7
+  in [#24784](https://github.com/google-gemini/gemini-cli/pull/24784)
+- chore: fix formatting for behavioral eval skill reference file by @abhipatel12
+  in [#24846](https://github.com/google-gemini/gemini-cli/pull/24846)
+- fix: use directory junctions on Windows for skill linking by @enjoykumawat in
+  [#24823](https://github.com/google-gemini/gemini-cli/pull/24823)
+- fix(cli): prevent multiple banner increments on remount by @sehoon38 in
+  [#24843](https://github.com/google-gemini/gemini-cli/pull/24843)
+- feat(acp): add /help command by @sripasg in
+  [#24839](https://github.com/google-gemini/gemini-cli/pull/24839)
+- fix(core): remove tmux alternate buffer warning by @jackwotherspoon in
+  [#24852](https://github.com/google-gemini/gemini-cli/pull/24852)
+- Improve sandbox error matching and caching by @DavidAPierce in
+  [#24550](https://github.com/google-gemini/gemini-cli/pull/24550)
+- feat(core): add agent protocol UI types and experimental flag by @mbleigh in
+  [#24275](https://github.com/google-gemini/gemini-cli/pull/24275)
+- feat(core): use experiment flags for default fetch timeouts by @yunaseoul in
+  [#24261](https://github.com/google-gemini/gemini-cli/pull/24261)
+- Revert "fix(ui): improve narration suppression and reduce flicker (#2… by
+  @gundermanc in
+  [#24857](https://github.com/google-gemini/gemini-cli/pull/24857)
+- refactor(cli): remove duplication in interactive shell awaiting input hint by
+  @JayadityaGit in
+  [#24801](https://github.com/google-gemini/gemini-cli/pull/24801)
+- refactor(core): make LegacyAgentSession dependencies optional by @mbleigh in
+  [#24287](https://github.com/google-gemini/gemini-cli/pull/24287)
+- Changelog for v0.37.0-preview.2 by @gemini-cli-robot in
+  [#24848](https://github.com/google-gemini/gemini-cli/pull/24848)
+- fix(cli): always show shell command description or actual command by @jacob314
+  in [#24774](https://github.com/google-gemini/gemini-cli/pull/24774)
+- Added flag for ept size and increased default size by @devr0306 in
+  [#24859](https://github.com/google-gemini/gemini-cli/pull/24859)
+- fix(core): dispose Scheduler to prevent McpProgress listener leak by
+  @Anjaligarhwal in
+  [#24870](https://github.com/google-gemini/gemini-cli/pull/24870)
+- fix(cli): switch default back to terminalBuffer=false and fix regressions
+  introduced for that mode by @jacob314 in
+  [#24873](https://github.com/google-gemini/gemini-cli/pull/24873)
+- feat(cli): switch to ctrl+g from ctrl-x by @jacob314 in
+  [#24861](https://github.com/google-gemini/gemini-cli/pull/24861)
+- fix: isolate concurrent browser agent instances by @gsquared94 in
+  [#24794](https://github.com/google-gemini/gemini-cli/pull/24794)
+- docs: update MCP server OAuth redirect port documentation by @adamfweidman in
+  [#24844](https://github.com/google-gemini/gemini-cli/pull/24844)

 **Full Changelog**:
-https://github.com/google-gemini/gemini-cli/compare/v0.36.0-preview.8...v0.37.0-preview.2
+https://github.com/google-gemini/gemini-cli/compare/v0.37.0-preview.2...v0.38.0-preview.0
@@ -153,9 +153,9 @@ they appear in the UI.

 ### Advanced

-| UI Label                          | Setting                        | Description                                   | Default |
-| --------------------------------- | ------------------------------ | --------------------------------------------- | ------- |
-| Auto Configure Max Old Space Size | `advanced.autoConfigureMemory` | Automatically configure Node.js memory limits | `true`  |
+| UI Label                          | Setting                        | Description                                                                                                                                                                                                           | Default |
+| --------------------------------- | ------------------------------ | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------- |
+| Auto Configure Max Old Space Size | `advanced.autoConfigureMemory` | Automatically configure Node.js memory limits. Note: Because memory is allocated during the initial process boot, this setting is only read from the global user settings file and ignores workspace-level overrides. | `true`  |

 ### Experimental

@@ -117,6 +117,88 @@ npm run test:integration:sandbox:docker
 npm run test:integration:sandbox:podman
 ```

+## Memory regression tests
+
+Memory regression tests are designed to detect heap growth and leaks across key
+CLI scenarios. They are located in the `memory-tests` directory.
+
+These tests are distinct from standard integration tests because they measure
+memory usage and compare it against committed baselines.
+
+### Running memory tests
+
+Memory tests are not run as part of the default `npm run test` or
+`npm run test:e2e` commands. They are run nightly in CI but can be run manually:
+
+```bash
+npm run test:memory
+```
+
+### Updating baselines
+
+If you intentionally change behavior that affects memory usage, you may need to
+update the baselines. Set the `UPDATE_MEMORY_BASELINES` environment variable to
+`true`:
+
+```bash
+UPDATE_MEMORY_BASELINES=true npm run test:memory
+```
+
+This will run the tests, take median snapshots, and overwrite
+`memory-tests/baselines.json`. You should review the changes and commit the
+updated baseline file.
+
+### How it works
+
+The harness (`MemoryTestHarness` in `packages/test-utils`):
+
+- Forces garbage collection multiple times to reduce noise.
+- Takes median snapshots to filter spikes.
+- Compares against baselines with a 10% tolerance.
+- Can analyze sustained leaks across 3 snapshots using `analyzeSnapshots()`.
+
+## Performance regression tests
+
+Performance regression tests are designed to detect wall-clock time, CPU usage,
+and event loop delay regressions across key CLI scenarios. They are located in
+the `perf-tests` directory.
+
+These tests are distinct from standard integration tests because they measure
+performance metrics and compare it against committed baselines.
+
+### Running performance tests
+
+Performance tests are not run as part of the default `npm run test` or
+`npm run test:e2e` commands. They are run nightly in CI but can be run manually:
+
+```bash
+npm run test:perf
+```
+
+### Updating baselines
+
+If you intentionally change behavior that affects performance, you may need to
+update the baselines. Set the `UPDATE_PERF_BASELINES` environment variable to
+`true`:
+
+```bash
+UPDATE_PERF_BASELINES=true npm run test:perf
+```
+
+This will run the tests multiple times (with warmup), apply IQR outlier
+filtering, and overwrite `perf-tests/baselines.json`. You should review the
+changes and commit the updated baseline file.
+
+### How it works
+
+The harness (`PerfTestHarness` in `packages/test-utils`):
+
+- Measures wall-clock time using `performance.now()`.
+- Measures CPU usage using `process.cpuUsage()`.
+- Monitors event loop delay using `perf_hooks.monitorEventLoopDelay()`.
+- Applies IQR (Interquartile Range) filtering to remove outlier samples.
+- Compares against baselines with a 15% tolerance.
+
 ## Diagnostics

 The integration test runner provides several options for diagnostics to help
@@ -1578,7 +1578,10 @@ their corresponding top-level category object in your `settings.json` file.
 #### `advanced`

 - **`advanced.autoConfigureMemory`** (boolean):
-  - **Description:** Automatically configure Node.js memory limits
+  - **Description:** Automatically configure Node.js memory limits. Note:
+    Because memory is allocated during the initial process boot, this setting is
+    only read from the global user settings file and ignores workspace-level
+    overrides.
  - **Default:** `true`
  - **Requires restart:** Yes

@@ -91,7 +91,7 @@ available combinations.
 | `input.submit`                       | Submit the current prompt.                                                | `Enter`                                                                             |
 | `input.queueMessage`                 | Queue the current prompt to be processed after the current task finishes. | `Tab`                                                                               |
 | `input.newline`                      | Insert a newline without submitting.                                      | `Ctrl+Enter`<br />`Cmd/Win+Enter`<br />`Alt+Enter`<br />`Shift+Enter`<br />`Ctrl+J` |
-| `input.openExternalEditor`           | Open the current prompt or the plan in an external editor.                | `Ctrl+G`                                                                            |
+| `input.openExternalEditor`           | Open the current prompt or the plan in an external editor.                | `Ctrl+G`<br />`Ctrl+Shift+G`                                                        |
 | `input.deprecatedOpenExternalEditor` | Deprecated command to open external editor.                               | `Ctrl+X`                                                                            |
 | `input.paste`                        | Paste from the clipboard.                                                 | `Ctrl+V`<br />`Cmd/Win+V`<br />`Alt+V`                                              |

@@ -19,6 +19,8 @@ describe('Answer vs. ask eval', () => {
   * automatically modify the file, but instead asks for permission.
   */
  evalTest('USUALLY_PASSES', {
+    suiteName: 'default',
+    suiteType: 'behavioral',
    name: 'should not edit files when asked to inspect for bugs',
    prompt: 'Inspect app.ts for bugs',
    files: FILES,
@@ -42,6 +44,8 @@ describe('Answer vs. ask eval', () => {
   * does modify the file.
   */
  evalTest('USUALLY_PASSES', {
+    suiteName: 'default',
+    suiteType: 'behavioral',
    name: 'should edit files when asked to fix bug',
    prompt: 'Fix the bug in app.ts - it should add numbers not subtract',
    files: FILES,
@@ -66,6 +70,8 @@ describe('Answer vs. ask eval', () => {
   * automatically modify the file, but instead asks for permission.
   */
  evalTest('USUALLY_PASSES', {
+    suiteName: 'default',
+    suiteType: 'behavioral',
    name: 'should not edit when asking "any bugs"',
    prompt: 'Any bugs in app.ts?',
    files: FILES,
@@ -89,6 +95,8 @@ describe('Answer vs. ask eval', () => {
   * automatically modify the file.
   */
  evalTest('ALWAYS_PASSES', {
+    suiteName: 'default',
+    suiteType: 'behavioral',
    name: 'should not edit files when asked a general question',
    prompt: 'How does app.ts work?',
    files: FILES,
@@ -112,6 +120,8 @@ describe('Answer vs. ask eval', () => {
   * automatically modify the file.
   */
  evalTest('ALWAYS_PASSES', {
+    suiteName: 'default',
+    suiteType: 'behavioral',
    name: 'should not edit files when asked about style',
    prompt: 'Is app.ts following good style?',
    files: FILES,
@@ -135,6 +145,8 @@ describe('Answer vs. ask eval', () => {
   * the agent does NOT automatically modify the file.
   */
  evalTest('USUALLY_PASSES', {
+    suiteName: 'default',
+    suiteType: 'behavioral',
    name: 'should not edit files when user notes an issue',
    prompt: 'The add function subtracts numbers.',
    files: FILES,
@@ -10,10 +10,13 @@ import {
  runEval,
  prepareLogDir,
  symlinkNodeModules,
+  withEvalRetries,
+  prepareWorkspace,
+  type BaseEvalCase,
+  EVAL_MODEL,
 } from './test-helper.js';
 import fs from 'node:fs';
 import path from 'node:path';
-import { DEFAULT_GEMINI_MODEL } from '@google/gemini-cli-core';

 /**
 * Config overrides for evals, with tool-restriction fields explicitly
@@ -29,15 +32,13 @@ interface EvalConfigOverrides {
  allowedTools?: never;
  /** Restricting tools via mainAgentTools in evals is forbidden. */
  mainAgentTools?: never;
+
  [key: string]: unknown;
 }

-export interface AppEvalCase {
-  name: string;
+export interface AppEvalCase extends BaseEvalCase {
  configOverrides?: EvalConfigOverrides;
  prompt: string;
-  timeout?: number;
-  files?: Record<string, string>;
  setup?: (rig: AppRig) => Promise<void>;
  assert: (rig: AppRig, output: string) => Promise<void>;
 }
@@ -48,56 +49,55 @@ export interface AppEvalCase {
 */
 export function appEvalTest(policy: EvalPolicy, evalCase: AppEvalCase) {
  const fn = async () => {
-    const rig = new AppRig({
-      configOverrides: {
-        model: DEFAULT_GEMINI_MODEL,
-        ...evalCase.configOverrides,
-      },
-    });
+    await withEvalRetries(evalCase.name, async () => {
+      const rig = new AppRig({
+        configOverrides: {
+          model: EVAL_MODEL,
+          ...evalCase.configOverrides,
+        },
+      });

-    const { logDir, sanitizedName } = await prepareLogDir(evalCase.name);
-    const logFile = path.join(logDir, `${sanitizedName}.log`);
+      const { logDir, sanitizedName } = await prepareLogDir(evalCase.name);
+      const logFile = path.join(logDir, `${sanitizedName}.log`);

-    try {
-      await rig.initialize();
+      try {
+        await rig.initialize();

-      const testDir = rig.getTestDir();
-      symlinkNodeModules(testDir);
+        const testDir = rig.getTestDir();
+        symlinkNodeModules(testDir);

-      // Setup initial files
-      if (evalCase.files) {
-        for (const [filePath, content] of Object.entries(evalCase.files)) {
-          const fullPath = path.join(testDir, filePath);
-          fs.mkdirSync(path.dirname(fullPath), { recursive: true });
-          fs.writeFileSync(fullPath, content);
+        // Setup initial files
+        if (evalCase.files) {
+          // Note: AppRig does not use a separate homeDir, so we use testDir twice
+          await prepareWorkspace(testDir, testDir, evalCase.files);
        }
+
+        // Run custom setup if provided (e.g. for breakpoints)
+        if (evalCase.setup) {
+          await evalCase.setup(rig);
+        }
+
+        // Render the app!
+        await rig.render();
+
+        // Wait for initial ready state
+        await rig.waitForIdle();
+
+        // Send the initial prompt
+        await rig.sendMessage(evalCase.prompt);
+
+        // Run assertion. Interaction-heavy tests can do their own waiting/steering here.
+        const output = rig.getStaticOutput();
+        await evalCase.assert(rig, output);
+      } finally {
+        const output = rig.getStaticOutput();
+        if (output) {
+          await fs.promises.writeFile(logFile, output);
+        }
+        await rig.unmount();
      }
-
-      // Run custom setup if provided (e.g. for breakpoints)
-      if (evalCase.setup) {
-        await evalCase.setup(rig);
-      }
-
-      // Render the app!
-      await rig.render();
-
-      // Wait for initial ready state
-      await rig.waitForIdle();
-
-      // Send the initial prompt
-      await rig.sendMessage(evalCase.prompt);
-
-      // Run assertion. Interaction-heavy tests can do their own waiting/steering here.
-      const output = rig.getStaticOutput();
-      await evalCase.assert(rig, output);
-    } finally {
-      const output = rig.getStaticOutput();
-      if (output) {
-        await fs.promises.writeFile(logFile, output);
-      }
-      await rig.unmount();
-    }
+    });
  };

-  runEval(policy, evalCase.name, fn, (evalCase.timeout ?? 60000) + 10000);
+  runEval(policy, evalCase, fn, (evalCase.timeout ?? 60000) + 10000);
 }
@@ -5,17 +5,21 @@
 */

 import { describe, expect } from 'vitest';
-import { appEvalTest, AppEvalCase } from './app-test-helper.js';
-import { EvalPolicy } from './test-helper.js';
+import { ApprovalMode, isRecord } from '@google/gemini-cli-core';
+import { appEvalTest, type AppEvalCase } from './app-test-helper.js';
+import { type EvalPolicy } from './test-helper.js';

 function askUserEvalTest(policy: EvalPolicy, evalCase: AppEvalCase) {
+  const existingGeneral = evalCase.configOverrides?.['general'];
+  const generalBase = isRecord(existingGeneral) ? existingGeneral : {};
+
  return appEvalTest(policy, {
    ...evalCase,
    configOverrides: {
      ...evalCase.configOverrides,
+      approvalMode: ApprovalMode.DEFAULT,
      general: {
-        ...evalCase.configOverrides?.general,
-        approvalMode: 'default',
+        ...generalBase,
        enableAutoUpdate: false,
        enableAutoUpdateNotification: false,
      },
@@ -28,6 +32,8 @@ function askUserEvalTest(policy: EvalPolicy, evalCase: AppEvalCase) {

 describe('ask_user', () => {
  askUserEvalTest('USUALLY_PASSES', {
+    suiteName: 'default',
+    suiteType: 'behavioral',
    name: 'Agent uses AskUser tool to present multiple choice options',
    prompt: `Use the ask_user tool to ask me what my favorite color is. Provide 3 options: red, green, or blue.`,
    setup: async (rig) => {
@@ -43,6 +49,8 @@ describe('ask_user', () => {
  });

  askUserEvalTest('USUALLY_PASSES', {
+    suiteName: 'default',
+    suiteType: 'behavioral',
    name: 'Agent uses AskUser tool to clarify ambiguous requirements',
    files: {
      'package.json': JSON.stringify({ name: 'my-app', version: '1.0.0' }),
@@ -61,6 +69,8 @@ describe('ask_user', () => {
  });

  askUserEvalTest('USUALLY_PASSES', {
+    suiteName: 'default',
+    suiteType: 'behavioral',
    name: 'Agent uses AskUser tool before performing significant ambiguous rework',
    files: {
      'packages/core/src/index.ts': '// index\nexport const version = "1.0.0";',
@@ -82,8 +92,8 @@ describe('ask_user', () => {
      ]);
      expect(confirmation, 'Expected a tool call confirmation').toBeDefined();

-      if (confirmation?.name === 'enter_plan_mode') {
-        rig.acceptConfirmation('enter_plan_mode');
+      if (confirmation?.toolName === 'enter_plan_mode') {
+        await rig.resolveTool('enter_plan_mode');
        confirmation = await rig.waitForPendingConfirmation('ask_user');
      }

@@ -101,6 +111,8 @@ describe('ask_user', () => {
  // updates to clarify that shell command confirmation is handled by the UI.
  // See fix: https://github.com/google-gemini/gemini-cli/pull/20504
  askUserEvalTest('USUALLY_PASSES', {
+    suiteName: 'default',
+    suiteType: 'behavioral',
    name: 'Agent does NOT use AskUser to confirm shell commands',
    files: {
      'package.json': JSON.stringify({
@@ -14,6 +14,8 @@ describe('Automated tool use', () => {
   * a repro by guiding the agent into using the existing deficient script.
   */
  evalTest('USUALLY_PASSES', {
+    suiteName: 'default',
+    suiteType: 'behavioral',
    name: 'should use automated tools (eslint --fix) to fix code style issues',
    files: {
      'package.json': JSON.stringify(
@@ -102,6 +104,8 @@ describe('Automated tool use', () => {
   * instead of trying to edit the files itself.
   */
  evalTest('USUALLY_PASSES', {
+    suiteName: 'default',
+    suiteType: 'behavioral',
    name: 'should use automated tools (prettier --write) to fix formatting issues',
    files: {
      'package.json': JSON.stringify(
@@ -3,6 +3,8 @@ import { evalTest } from './test-helper.js';

 describe('CliHelpAgent Delegation', () => {
  evalTest('USUALLY_PASSES', {
+    suiteName: 'default',
+    suiteType: 'behavioral',
    name: 'should delegate to cli_help agent for subagent creation questions',
    params: {
      settings: {
@@ -0,0 +1,136 @@
+/**
+ * @license
+ * Copyright 2026 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+import {
+  type EvalPolicy,
+  runEval,
+  prepareLogDir,
+  withEvalRetries,
+  prepareWorkspace,
+  type BaseEvalCase,
+} from './test-helper.js';
+import fs from 'node:fs';
+import path from 'node:path';
+import os from 'node:os';
+import { randomUUID } from 'node:crypto';
+import {
+  Config,
+  type ConfigParameters,
+  AuthType,
+  ApprovalMode,
+  createPolicyEngineConfig,
+  ExtensionLoader,
+  IntegrityDataStatus,
+  makeFakeConfig,
+  type GeminiCLIExtension,
+} from '@google/gemini-cli-core';
+import { createMockSettings } from '../packages/cli/src/test-utils/settings.js';
+
+// A minimal mock ExtensionManager to bypass integrity checks
+class MockExtensionManager extends ExtensionLoader {
+  override getExtensions(): GeminiCLIExtension[] {
+    return [];
+  }
+  setRequestConsent = (): void => {};
+  setRequestSetting = (): void => {};
+  integrityManager = {
+    verifyExtensionIntegrity: async (): Promise<IntegrityDataStatus> =>
+      IntegrityDataStatus.VERIFIED,
+    storeExtensionIntegrity: async (): Promise<void> => undefined,
+  };
+}
+
+export interface ComponentEvalCase extends BaseEvalCase {
+  configOverrides?: Partial<ConfigParameters>;
+  setup?: (config: Config) => Promise<void>;
+  assert: (config: Config) => Promise<void>;
+}
+
+export class ComponentRig {
+  public config: Config | undefined;
+  public testDir: string;
+  public sessionId: string;
+
+  constructor(
+    private options: { configOverrides?: Partial<ConfigParameters> } = {},
+  ) {
+    const uniqueId = randomUUID();
+    this.testDir = fs.mkdtempSync(
+      path.join(os.tmpdir(), `gemini-component-rig-${uniqueId.slice(0, 8)}-`),
+    );
+    this.sessionId = `test-session-${uniqueId}`;
+  }
+
+  async initialize() {
+    const settings = createMockSettings();
+    const policyEngineConfig = await createPolicyEngineConfig(
+      settings.merged,
+      ApprovalMode.DEFAULT,
+    );
+
+    const configParams: ConfigParameters = {
+      sessionId: this.sessionId,
+      targetDir: this.testDir,
+      cwd: this.testDir,
+      debugMode: false,
+      model: 'test-model',
+      interactive: false,
+      approvalMode: ApprovalMode.DEFAULT,
+      policyEngineConfig,
+      enableEventDrivenScheduler: false, // Don't need scheduler for direct component tests
+      extensionLoader: new MockExtensionManager(),
+      useAlternateBuffer: false,
+      ...this.options.configOverrides,
+    };
+
+    this.config = makeFakeConfig(configParams);
+    await this.config.initialize();
+
+    // Refresh auth using USE_GEMINI to initialize the real BaseLlmClient
+    await this.config.refreshAuth(AuthType.USE_GEMINI);
+  }
+
+  async cleanup() {
+    fs.rmSync(this.testDir, { recursive: true, force: true });
+  }
+}
+
+/**
+ * A helper for running behavioral evaluations directly against backend components.
+ * It provides a fully initialized Config with real API access, bypassing the UI.
+ */
+export function componentEvalTest(
+  policy: EvalPolicy,
+  evalCase: ComponentEvalCase,
+) {
+  const fn = async () => {
+    await withEvalRetries(evalCase.name, async () => {
+      const rig = new ComponentRig({
+        configOverrides: evalCase.configOverrides,
+      });
+
+      await prepareLogDir(evalCase.name);
+
+      try {
+        await rig.initialize();
+
+        if (evalCase.files) {
+          await prepareWorkspace(rig.testDir, rig.testDir, evalCase.files);
+        }
+
+        if (evalCase.setup) {
+          await evalCase.setup(rig.config!);
+        }
+
+        await evalCase.assert(rig.config!);
+      } finally {
+        await rig.cleanup();
+      }
+    });
+  };
+
+  runEval(policy, evalCase, fn, (evalCase.timeout ?? 60000) + 10000);
+}
@@ -20,6 +20,8 @@ You are the mutation agent. Do the mutation requested.

 describe('concurrency safety eval test cases', () => {
  evalTest('USUALLY_PASSES', {
+    suiteName: 'default',
+    suiteType: 'behavioral',
    name: 'mutation agents are run in parallel when explicitly requested',
    params: {
      settings: {
@@ -13,6 +13,8 @@ describe('Edits location eval', () => {
   * instead of creating a new one.
   */
  evalTest('USUALLY_PASSES', {
+    suiteName: 'default',
+    suiteType: 'behavioral',
    name: 'should update existing test file instead of creating a new one',
    files: {
      'package.json': JSON.stringify(
@@ -15,6 +15,8 @@ describe('Frugal reads eval', () => {
   * nearby ranges into a single contiguous read to save tool calls.
   */
  evalTest('USUALLY_PASSES', {
+    suiteName: 'default',
+    suiteType: 'behavioral',
    name: 'should use ranged read when nearby lines are targeted',
    files: {
      'package.json': JSON.stringify({
@@ -135,6 +137,8 @@ describe('Frugal reads eval', () => {
   * apart to avoid the need to read the whole file.
   */
  evalTest('USUALLY_PASSES', {
+    suiteName: 'default',
+    suiteType: 'behavioral',
    name: 'should use ranged read when targets are far apart',
    files: {
      'package.json': JSON.stringify({
@@ -204,6 +208,8 @@ describe('Frugal reads eval', () => {
   * (e.g.: 10), as it's more efficient than many small ranged reads.
   */
  evalTest('USUALLY_PASSES', {
+    suiteName: 'default',
+    suiteType: 'behavioral',
    name: 'should read the entire file when there are many matches',
    files: {
      'package.json': JSON.stringify({
@@ -13,18 +13,6 @@ import { evalTest } from './test-helper.js';
 * This ensures the agent doesn't flood the context window with unnecessary search results.
 */
 describe('Frugal Search', () => {
-  const getGrepParams = (call: any): any => {
-    let args = call.toolRequest.args;
-    if (typeof args === 'string') {
-      try {
-        args = JSON.parse(args);
-      } catch (e) {
-        // Ignore parse errors
-      }
-    }
-    return args;
-  };
-
  /**
   * Ensure that the agent makes use of either grep or ranged reads in fulfilling this task.
   * The task is specifically phrased to not evoke "view" or "search" specifically because
@@ -33,6 +21,8 @@ describe('Frugal Search', () => {
   * ranged reads.
   */
  evalTest('USUALLY_PASSES', {
+    suiteName: 'default',
+    suiteType: 'behavioral',
    name: 'should use grep or ranged read for large files',
    prompt: 'What year was legacy_processor.ts written?',
    files: {
@@ -11,6 +11,8 @@ import fs from 'node:fs/promises';

 describe('generalist_agent', () => {
  evalTest('USUALLY_PASSES', {
+    suiteName: 'default',
+    suiteType: 'behavioral',
    name: 'should be able to use generalist agent by explicitly asking the main agent to invoke it',
    params: {
      settings: {
@@ -11,6 +11,8 @@ describe('generalist_delegation', () => {
  // --- Positive Evals (Should Delegate) ---

  appEvalTest('USUALLY_PASSES', {
+    suiteName: 'default',
+    suiteType: 'behavioral',
    name: 'should delegate batch error fixing to generalist agent',
    configOverrides: {
      agents: {
@@ -54,6 +56,8 @@ describe('generalist_delegation', () => {
  });

  appEvalTest('USUALLY_PASSES', {
+    suiteName: 'default',
+    suiteType: 'behavioral',
    name: 'should autonomously delegate complex batch task to generalist agent',
    configOverrides: {
      agents: {
@@ -94,6 +98,8 @@ describe('generalist_delegation', () => {
  // --- Negative Evals (Should NOT Delegate - Assertive Handling) ---

  appEvalTest('USUALLY_PASSES', {
+    suiteName: 'default',
+    suiteType: 'behavioral',
    name: 'should NOT delegate simple read and fix to generalist agent',
    configOverrides: {
      agents: {
@@ -128,6 +134,8 @@ describe('generalist_delegation', () => {
  });

  appEvalTest('USUALLY_PASSES', {
+    suiteName: 'default',
+    suiteType: 'behavioral',
    name: 'should NOT delegate simple direct question to generalist agent',
    configOverrides: {
      agents: {
@@ -26,6 +26,8 @@ describe('git repo eval', () => {
   * be more consistent.
   */
  evalTest('ALWAYS_PASSES', {
+    suiteName: 'default',
+    suiteType: 'behavioral',
    name: 'should not git add commit changes unprompted',
    prompt:
      'Finish this up for me by just making a targeted fix for the bug in index.ts. Do not build, install anything, or add tests',
@@ -55,6 +57,8 @@ describe('git repo eval', () => {
   * instructed to not do so by default.
   */
  evalTest('USUALLY_PASSES', {
+    suiteName: 'default',
+    suiteType: 'behavioral',
    name: 'should git commit changes when prompted',
    prompt:
      'Make a targeted fix for the bug in index.ts without building, installing anything, or adding tests. Then, commit your changes.',
@@ -15,6 +15,8 @@ describe('grep_search_functionality', () => {
  const TEST_PREFIX = 'Grep Search Functionality: ';

  evalTest('USUALLY_PASSES', {
+    suiteName: 'default',
+    suiteType: 'behavioral',
    name: 'should find a simple string in a file',
    files: {
      'test.txt': `hello
@@ -33,6 +35,8 @@ describe('grep_search_functionality', () => {
  });

  evalTest('USUALLY_PASSES', {
+    suiteName: 'default',
+    suiteType: 'behavioral',
    name: 'should perform a case-sensitive search',
    files: {
      'test.txt': `Hello
@@ -63,6 +67,8 @@ describe('grep_search_functionality', () => {
  });

  evalTest('USUALLY_PASSES', {
+    suiteName: 'default',
+    suiteType: 'behavioral',
    name: 'should return only file names when names_only is used',
    files: {
      'file1.txt': 'match me',
@@ -93,6 +99,8 @@ describe('grep_search_functionality', () => {
  });

  evalTest('USUALLY_PASSES', {
+    suiteName: 'default',
+    suiteType: 'behavioral',
    name: 'should search only within the specified include_pattern glob',
    files: {
      'file.js': 'my_function();',
@@ -123,6 +131,8 @@ describe('grep_search_functionality', () => {
  });

  evalTest('USUALLY_PASSES', {
+    suiteName: 'default',
+    suiteType: 'behavioral',
    name: 'should search within a specific subdirectory',
    files: {
      'src/main.js': 'unique_string_1',
@@ -153,6 +163,8 @@ describe('grep_search_functionality', () => {
  });

  evalTest('USUALLY_PASSES', {
+    suiteName: 'default',
+    suiteType: 'behavioral',
    name: 'should report no matches correctly',
    files: {
      'file.txt': 'nothing to see here',
@@ -5,13 +5,14 @@
 */

 import { describe, expect } from 'vitest';
-import { evalTest } from './test-helper.js';
-import { assertModelHasOutput } from '../integration-tests/test-helper.js';
+import { evalTest, assertModelHasOutput } from './test-helper.js';

 describe('Hierarchical Memory', () => {
  const conflictResolutionTest =
    'Agent follows hierarchy for contradictory instructions';
  evalTest('ALWAYS_PASSES', {
+    suiteName: 'default',
+    suiteType: 'behavioral',
    name: conflictResolutionTest,
    params: {
      settings: {
@@ -48,6 +49,8 @@ What is my favorite fruit? Tell me just the name of the fruit.`,

  const provenanceAwarenessTest = 'Agent is aware of memory provenance';
  evalTest('USUALLY_PASSES', {
+    suiteName: 'default',
+    suiteType: 'behavioral',
    name: provenanceAwarenessTest,
    params: {
      settings: {
@@ -87,6 +90,8 @@ Provide the answer as an XML block like this:

  const extensionVsGlobalTest = 'Extension memory wins over Global memory';
  evalTest('ALWAYS_PASSES', {
+    suiteName: 'default',
+    suiteType: 'behavioral',
    name: extensionVsGlobalTest,
    params: {
      settings: {
@@ -8,6 +8,8 @@ describe('interactive_commands', () => {
   * intervention.
   */
  evalTest('USUALLY_PASSES', {
+    suiteName: 'default',
+    suiteType: 'behavioral',
    name: 'should not use interactive commands',
    prompt: 'Execute tests.',
    files: {
@@ -49,6 +51,8 @@ describe('interactive_commands', () => {
   * Validates that the agent uses non-interactive flags when scaffolding a new project.
   */
  evalTest('ALWAYS_PASSES', {
+    suiteName: 'default',
+    suiteType: 'behavioral',
    name: 'should use non-interactive flags when scaffolding a new app',
    prompt: 'Create a new react application named my-app using vite.',
    assert: async (rig, result) => {
@@ -5,14 +5,14 @@
 */

 import { describe, expect } from 'vitest';
-import { act } from 'react';
 import path from 'node:path';
 import fs from 'node:fs';
 import { appEvalTest } from './app-test-helper.js';
-import { PolicyDecision } from '@google/gemini-cli-core';

 describe('Model Steering Behavioral Evals', () => {
  appEvalTest('USUALLY_PASSES', {
+    suiteName: 'default',
+    suiteType: 'behavioral',
    name: 'Corrective Hint: Model switches task based on hint during tool turn',
    configOverrides: {
      modelSteering: true,
@@ -52,6 +52,8 @@ describe('Model Steering Behavioral Evals', () => {
  });

  appEvalTest('USUALLY_PASSES', {
+    suiteName: 'default',
+    suiteType: 'behavioral',
    name: 'Suggestive Hint: Model incorporates user guidance mid-stream',
    configOverrides: {
      modelSteering: true,
@@ -33,6 +33,8 @@ describe('plan_mode', () => {
      .filter(Boolean);

  evalTest('ALWAYS_PASSES', {
+    suiteName: 'default',
+    suiteType: 'behavioral',
    name: 'should refuse file modification when in plan mode',
    approvalMode: ApprovalMode.PLAN,
    params: {
@@ -68,6 +70,8 @@ describe('plan_mode', () => {
  });

  evalTest('ALWAYS_PASSES', {
+    suiteName: 'default',
+    suiteType: 'behavioral',
    name: 'should refuse saving new documentation to the repo when in plan mode',
    approvalMode: ApprovalMode.PLAN,
    params: {
@@ -105,6 +109,8 @@ describe('plan_mode', () => {
  });

  evalTest('USUALLY_PASSES', {
+    suiteName: 'default',
+    suiteType: 'behavioral',
    name: 'should enter plan mode when asked to create a plan',
    approvalMode: ApprovalMode.DEFAULT,
    params: {
@@ -122,6 +128,8 @@ describe('plan_mode', () => {
  });

  evalTest('USUALLY_PASSES', {
+    suiteName: 'default',
+    suiteType: 'behavioral',
    name: 'should exit plan mode when plan is complete and implementation is requested',
    approvalMode: ApprovalMode.PLAN,
    params: {
@@ -169,6 +177,8 @@ describe('plan_mode', () => {
  });

  evalTest('USUALLY_PASSES', {
+    suiteName: 'default',
+    suiteType: 'behavioral',
    name: 'should allow file modification in plans directory when in plan mode',
    approvalMode: ApprovalMode.PLAN,
    params: {
@@ -201,6 +211,8 @@ describe('plan_mode', () => {
  });

  evalTest('USUALLY_PASSES', {
+    suiteName: 'default',
+    suiteType: 'behavioral',
    name: 'should create a plan in plan mode and implement it for a refactoring task',
    params: {
      settings,
@@ -11,6 +11,8 @@ import fs from 'node:fs/promises';

 describe('redundant_casts', () => {
  evalTest('USUALLY_PASSES', {
+    suiteName: 'default',
+    suiteType: 'behavioral',
    name: 'should not add redundant or unsafe casts when modifying typescript code',
    files: {
      'src/cast_example.ts': `
@@ -3,6 +3,8 @@ import { evalTest } from './test-helper.js';

 describe('Sandbox recovery', () => {
  evalTest('USUALLY_PASSES', {
+    suiteName: 'default',
+    suiteType: 'behavioral',
    name: 'attempts to use additional_permissions when operation not permitted',
    prompt:
      'Run ./script.sh. It will fail with "Operation not permitted". When it does, you must retry running it by passing the appropriate additional_permissions.',
@@ -5,16 +5,18 @@
 */

 import { describe, expect } from 'vitest';
-import { evalTest } from './test-helper.js';
 import {
+  evalTest,
  assertModelHasOutput,
  checkModelOutputContent,
-} from '../integration-tests/test-helper.js';
+} from './test-helper.js';

 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,

    prompt: `remember that my favorite color is  blue.
@@ -35,6 +37,8 @@ describe('save_memory', () => {
  });
  const rememberingCommandRestrictions = 'Agent remembers command restrictions';
  evalTest('USUALLY_PASSES', {
+    suiteName: 'default',
+    suiteType: 'behavioral',
    name: rememberingCommandRestrictions,

    prompt: `I don't want you to ever run npm commands.`,
@@ -54,6 +58,8 @@ describe('save_memory', () => {

  const rememberingWorkflow = 'Agent remembers workflow preferences';
  evalTest('USUALLY_PASSES', {
+    suiteName: 'default',
+    suiteType: 'behavioral',
    name: rememberingWorkflow,

    prompt: `I want you to always lint after building.`,
@@ -74,6 +80,8 @@ describe('save_memory', () => {
  const ignoringTemporaryInformation =
    'Agent ignores temporary conversation details';
  evalTest('ALWAYS_PASSES', {
+    suiteName: 'default',
+    suiteType: 'behavioral',
    name: ignoringTemporaryInformation,

    prompt: `I'm going to get a coffee.`,
@@ -97,6 +105,8 @@ describe('save_memory', () => {

  const rememberingPetName = "Agent remembers user's pet's name";
  evalTest('ALWAYS_PASSES', {
+    suiteName: 'default',
+    suiteType: 'behavioral',
    name: rememberingPetName,

    prompt: `Please remember that my dog's name is Buddy.`,
@@ -116,6 +126,8 @@ describe('save_memory', () => {

  const rememberingCommandAlias = 'Agent remembers custom command aliases';
  evalTest('ALWAYS_PASSES', {
+    suiteName: 'default',
+    suiteType: 'behavioral',
    name: rememberingCommandAlias,

    prompt: `When I say 'start server', you should run 'npm run dev'.`,
@@ -136,6 +148,8 @@ describe('save_memory', () => {
  const ignoringDbSchemaLocation =
    "Agent ignores workspace's database schema location";
  evalTest('USUALLY_PASSES', {
+    suiteName: 'default',
+    suiteType: 'behavioral',
    name: ignoringDbSchemaLocation,
    prompt: `The database schema for this workspace is located in \`db/schema.sql\`.`,
    assert: async (rig, result) => {
@@ -155,6 +169,8 @@ describe('save_memory', () => {
  const rememberingCodingStyle =
    "Agent remembers user's coding style preference";
  evalTest('ALWAYS_PASSES', {
+    suiteName: 'default',
+    suiteType: 'behavioral',
    name: rememberingCodingStyle,

    prompt: `I prefer to use tabs instead of spaces for indentation.`,
@@ -175,6 +191,8 @@ describe('save_memory', () => {
  const ignoringBuildArtifactLocation =
    'Agent ignores workspace build artifact location';
  evalTest('USUALLY_PASSES', {
+    suiteName: 'default',
+    suiteType: 'behavioral',
    name: ignoringBuildArtifactLocation,
    prompt: `In this workspace, build artifacts are stored in the \`dist/artifacts\` directory.`,
    assert: async (rig, result) => {
@@ -193,6 +211,8 @@ describe('save_memory', () => {

  const ignoringMainEntryPoint = "Agent ignores workspace's main entry point";
  evalTest('USUALLY_PASSES', {
+    suiteName: 'default',
+    suiteType: 'behavioral',
    name: ignoringMainEntryPoint,
    prompt: `The main entry point for this workspace is \`src/index.js\`.`,
    assert: async (rig, result) => {
@@ -211,6 +231,8 @@ describe('save_memory', () => {

  const rememberingBirthday = "Agent remembers user's birthday";
  evalTest('ALWAYS_PASSES', {
+    suiteName: 'default',
+    suiteType: 'behavioral',
    name: rememberingBirthday,

    prompt: `My birthday is on June 15th.`,
@@ -231,6 +253,8 @@ describe('save_memory', () => {
  const proactiveMemoryFromLongSession =
    'Agent saves preference from earlier in conversation history';
  evalTest('USUALLY_PASSES', {
+    suiteName: 'default',
+    suiteType: 'behavioral',
    name: proactiveMemoryFromLongSession,
    params: {
      settings: {
@@ -309,6 +333,8 @@ describe('save_memory', () => {
  const memoryManagerRoutingPreferences =
    'Agent routes global and project preferences to memory';
  evalTest('USUALLY_PASSES', {
+    suiteName: 'default',
+    suiteType: 'behavioral',
    name: memoryManagerRoutingPreferences,
    params: {
      settings: {
@@ -21,6 +21,8 @@ describe('Shell Efficiency', () => {
  };

  evalTest('USUALLY_PASSES', {
+    suiteName: 'default',
+    suiteType: 'behavioral',
    name: 'should use --silent/--quiet flags when installing packages',
    prompt: 'Install the "lodash" package using npm.',
    assert: async (rig) => {
@@ -50,6 +52,8 @@ describe('Shell Efficiency', () => {
  });

  evalTest('USUALLY_PASSES', {
+    suiteName: 'default',
+    suiteType: 'behavioral',
    name: 'should use --no-pager with git commands',
    prompt: 'Show the git log.',
    assert: async (rig) => {
@@ -73,6 +77,8 @@ describe('Shell Efficiency', () => {
  });

  evalTest('ALWAYS_PASSES', {
+    suiteName: 'default',
+    suiteType: 'behavioral',
    name: 'should NOT use efficiency flags when enableShellOutputEfficiency is disabled',
    params: {
      settings: {
@@ -45,6 +45,8 @@ describe('subagent eval test cases', () => {
   * This tests the system prompt's subagent specific clauses.
   */
  evalTest('USUALLY_PASSES', {
+    suiteName: 'default',
+    suiteType: 'behavioral',
    name: 'should delegate to user provided agent with relevant expertise',
    params: {
      settings: {
@@ -69,6 +71,8 @@ describe('subagent eval test cases', () => {
   * subagents are available. This helps catch orchestration overuse.
   */
  evalTest('USUALLY_PASSES', {
+    suiteName: 'default',
+    suiteType: 'behavioral',
    name: 'should avoid delegating trivial direct edit work',
    params: {
      settings: {
@@ -113,6 +117,8 @@ describe('subagent eval test cases', () => {
   * This is meant to codify the "overusing Generalist" failure mode.
   */
  evalTest('USUALLY_PASSES', {
+    suiteName: 'default',
+    suiteType: 'behavioral',
    name: 'should prefer relevant specialist over generalist',
    params: {
      settings: {
@@ -149,6 +155,8 @@ describe('subagent eval test cases', () => {
   * naturally spans docs and tests, so multiple specialists should be used.
   */
  evalTest('USUALLY_PASSES', {
+    suiteName: 'default',
+    suiteType: 'behavioral',
    name: 'should use multiple relevant specialists for multi-surface task',
    params: {
      settings: {
@@ -193,6 +201,8 @@ describe('subagent eval test cases', () => {
   * from a large pool of available subagents (10 total).
   */
  evalTest('USUALLY_PASSES', {
+    suiteName: 'default',
+    suiteType: 'behavioral',
    name: 'should select the correct subagent from a pool of 10 different agents',
    prompt: 'Please add a new SQL table migration for a user profile.',
    files: {
@@ -243,6 +253,8 @@ describe('subagent eval test cases', () => {
   * This test includes stress tests the subagent delegation with ~80 tools.
   */
  evalTest('USUALLY_PASSES', {
+    suiteName: 'default',
+    suiteType: 'behavioral',
    name: 'should select the correct subagent from a pool of 10 different agents with MCP tools present',
    prompt: 'Please add a new SQL table migration for a user profile.',
    setup: async (rig) => {
@@ -49,6 +49,8 @@ describe('evalTest reliability logic', () => {

    // Execute the test function directly
    await internalEvalTest({
+      suiteName: 'test',
+      suiteType: 'behavioral',
      name: 'test-api-failure',
      prompt: 'do something',
      assert: async () => {},
@@ -83,6 +85,8 @@ describe('evalTest reliability logic', () => {
    // Expect the test function to throw immediately
    await expect(
      internalEvalTest({
+        suiteName: 'test',
+        suiteType: 'behavioral',
        name: 'test-logic-failure',
        prompt: 'do something',
        assert: async () => {
@@ -108,6 +112,8 @@ describe('evalTest reliability logic', () => {
      .mockResolvedValueOnce('Success');

    await internalEvalTest({
+      suiteName: 'test',
+      suiteType: 'behavioral',
      name: 'test-recovery',
      prompt: 'do something',
      assert: async () => {},
@@ -135,6 +141,8 @@ describe('evalTest reliability logic', () => {
    );

    await internalEvalTest({
+      suiteName: 'test',
+      suiteType: 'behavioral',
      name: 'test-api-503',
      prompt: 'do something',
      assert: async () => {},
@@ -162,6 +170,8 @@ describe('evalTest reliability logic', () => {
    try {
      await expect(
        internalEvalTest({
+          suiteName: 'test',
+          suiteType: 'behavioral',
          name: 'test-absolute-path',
          prompt: 'do something',
          files: {
@@ -190,6 +200,8 @@ describe('evalTest reliability logic', () => {
    try {
      await expect(
        internalEvalTest({
+          suiteName: 'test',
+          suiteType: 'behavioral',
          name: 'test-traversal',
          prompt: 'do something',
          files: {
@@ -16,10 +16,19 @@ import {
  Storage,
  getProjectHash,
  SESSION_FILE_PREFIX,
+  PREVIEW_GEMINI_FLASH_MODEL,
+  getErrorMessage,
 } from '@google/gemini-cli-core';

 export * from '@google/gemini-cli-test-utils';

+/**
+ * The default model used for all evaluations.
+ * Can be overridden by setting the GEMINI_MODEL environment variable.
+ */
+export const EVAL_MODEL =
+  process.env['GEMINI_MODEL'] || PREVIEW_GEMINI_FLASH_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
@@ -39,19 +48,49 @@ export * from '@google/gemini-cli-test-utils';
 export type EvalPolicy = 'ALWAYS_PASSES' | 'USUALLY_PASSES';

 export function evalTest(policy: EvalPolicy, evalCase: EvalCase) {
-  runEval(
-    policy,
-    evalCase.name,
-    () => internalEvalTest(evalCase),
-    evalCase.timeout,
-  );
+  runEval(policy, evalCase, () => internalEvalTest(evalCase));
 }

-export async function internalEvalTest(evalCase: EvalCase) {
+export async function withEvalRetries(
+  name: string,
+  attemptFn: (attempt: number) => Promise<void>,
+) {
  const maxRetries = 3;
  let attempt = 0;

  while (attempt <= maxRetries) {
+    try {
+      await attemptFn(attempt);
+      return; // Success! Exit the retry loop.
+    } catch (error: unknown) {
+      const errorMessage = getErrorMessage(error);
+      const errorCode = getApiErrorCode(errorMessage);
+
+      if (errorCode) {
+        const status = attempt < maxRetries ? 'RETRY' : 'SKIP';
+        logReliabilityEvent(name, attempt, status, errorCode, errorMessage);
+
+        if (attempt < maxRetries) {
+          attempt++;
+          console.warn(
+            `[Eval] Attempt ${attempt} failed with ${errorCode} Error. Retrying...`,
+          );
+          continue; // Retry
+        }
+
+        console.warn(
+          `[Eval] '${name}' failed after ${maxRetries} retries due to persistent API errors. Skipping failure to avoid blocking PR.`,
+        );
+        return; // Gracefully exit without failing the test
+      }
+
+      throw error; // Real failure
+    }
+  }
+}
+
+export async function internalEvalTest(evalCase: EvalCase) {
+  await withEvalRetries(evalCase.name, async () => {
    const rig = new TestRig();
    const { logDir, sanitizedName } = await prepareLogDir(evalCase.name);
    const activityLogFile = path.join(logDir, `${sanitizedName}.jsonl`);
@@ -59,14 +98,21 @@ export async function internalEvalTest(evalCase: EvalCase) {
    let isSuccess = false;

    try {
-      rig.setup(evalCase.name, evalCase.params);
+      const setupOptions = {
+        ...evalCase.params,
+        settings: {
+          model: { name: EVAL_MODEL },
+          ...evalCase.params?.settings,
+        },
+      };
+      rig.setup(evalCase.name, setupOptions);

      if (evalCase.setup) {
        await evalCase.setup(rig);
      }

      if (evalCase.files) {
-        await setupTestFiles(rig, evalCase.files);
+        await prepareWorkspace(rig.testDir!, rig.homeDir!, evalCase.files);
      }

      symlinkNodeModules(rig.testDir || '');
@@ -139,37 +185,6 @@ export async function internalEvalTest(evalCase: EvalCase) {

      await evalCase.assert(rig, result);
      isSuccess = true;
-      return; // Success! Exit the retry loop.
-    } catch (error: unknown) {
-      const errorMessage =
-        error instanceof Error ? error.message : String(error);
-      const errorCode = getApiErrorCode(errorMessage);
-
-      if (errorCode) {
-        const status = attempt < maxRetries ? 'RETRY' : 'SKIP';
-        logReliabilityEvent(
-          evalCase.name,
-          attempt,
-          status,
-          errorCode,
-          errorMessage,
-        );
-
-        if (attempt < maxRetries) {
-          attempt++;
-          console.warn(
-            `[Eval] Attempt ${attempt} failed with ${errorCode} Error. Retrying...`,
-          );
-          continue; // Retry
-        }
-
-        console.warn(
-          `[Eval] '${evalCase.name}' failed after ${maxRetries} retries due to persistent API errors. Skipping failure to avoid blocking PR.`,
-        );
-        return; // Gracefully exit without failing the test
-      }
-
-      throw error; // Real failure
    } finally {
      if (isSuccess) {
        await fs.promises.unlink(activityLogFile).catch((err) => {
@@ -188,7 +203,7 @@ export async function internalEvalTest(evalCase: EvalCase) {
      );
      await rig.cleanup();
    }
-  }
+  });
 }

 function getApiErrorCode(message: string): '500' | '503' | undefined {
@@ -226,7 +241,7 @@ function logReliabilityEvent(
  const reliabilityLog = {
    timestamp: new Date().toISOString(),
    testName,
-    model: process.env.GEMINI_MODEL || 'unknown',
+    model: process.env['GEMINI_MODEL'] || 'unknown',
    attempt,
    status,
    errorCode,
@@ -252,9 +267,13 @@ function logReliabilityEvent(
 * intentionally uses synchronous filesystem and child_process operations
 * for simplicity and to ensure sequential environment preparation.
 */
-async function setupTestFiles(rig: TestRig, files: Record<string, string>) {
+export async function prepareWorkspace(
+  testDir: string,
+  homeDir: string,
+  files: Record<string, string>,
+) {
  const acknowledgedAgents: Record<string, Record<string, string>> = {};
-  const projectRoot = fs.realpathSync(rig.testDir!);
+  const projectRoot = fs.realpathSync(testDir);

  for (const [filePath, content] of Object.entries(files)) {
    if (filePath.includes('..') || path.isAbsolute(filePath)) {
@@ -290,7 +309,7 @@ async function setupTestFiles(rig: TestRig, files: Record<string, string>) {

  if (Object.keys(acknowledgedAgents).length > 0) {
    const ackPath = path.join(
-      rig.homeDir!,
+      homeDir,
      '.gemini',
      'acknowledgments',
      'agents.json',
@@ -299,7 +318,7 @@ async function setupTestFiles(rig: TestRig, files: Record<string, string>) {
    fs.writeFileSync(ackPath, JSON.stringify(acknowledgedAgents, null, 2));
  }

-  const execOptions = { cwd: rig.testDir!, stdio: 'inherit' as const };
+  const execOptions = { cwd: testDir, stdio: 'ignore' as const };
  execSync('git init --initial-branch=main', execOptions);
  execSync('git config user.email "test@example.com"', execOptions);
  execSync('git config user.name "Test User"', execOptions);
@@ -320,14 +339,30 @@ async function setupTestFiles(rig: TestRig, files: Record<string, string>) {
 */
 export function runEval(
  policy: EvalPolicy,
-  name: string,
+  evalCase: BaseEvalCase,
  fn: () => Promise<void>,
-  timeout?: number,
+  timeoutOverride?: number,
 ) {
-  if (policy === 'USUALLY_PASSES' && !process.env['RUN_EVALS']) {
-    it.skip(name, fn);
+  const { name, timeout, suiteName, suiteType } = evalCase;
+  const targetSuiteType = process.env['EVAL_SUITE_TYPE'];
+  const targetSuiteName = process.env['EVAL_SUITE_NAME'];
+
+  const meta = { suiteType, suiteName };
+
+  const skipBySuiteType =
+    targetSuiteType && suiteType && suiteType !== targetSuiteType;
+  const skipBySuiteName =
+    targetSuiteName && suiteName && suiteName !== targetSuiteName;
+
+  const options = { timeout: timeoutOverride ?? timeout, meta };
+  if (
+    (policy === 'USUALLY_PASSES' && !process.env['RUN_EVALS']) ||
+    skipBySuiteType ||
+    skipBySuiteName
+  ) {
+    it.skip(name, options, fn);
  } else {
-    it(name, fn, timeout);
+    it(name, options, fn);
  }
 }

@@ -366,15 +401,20 @@ interface ForbiddenToolSettings {
  };
 }

-export interface EvalCase {
+export interface BaseEvalCase {
+  suiteName: string;
+  suiteType: 'behavioral' | 'component-level' | 'hero-scenario';
  name: string;
+  timeout?: number;
+  files?: Record<string, string>;
+}
+
+export interface EvalCase extends BaseEvalCase {
  params?: {
    settings?: ForbiddenToolSettings & Record<string, unknown>;
    [key: string]: unknown;
  };
  prompt: string;
-  timeout?: number;
-  files?: Record<string, string>;
  setup?: (rig: TestRig) => Promise<void> | void;
  /** Conversation history to pre-load via --resume. Each entry is a message object with type, content, etc. */
  messages?: Record<string, unknown>[];
@@ -31,6 +31,8 @@ describe('Tool Output Masking Behavioral Evals', () => {
   * It should recognize the <tool_output_masked> tag and use a tool to read the file.
   */
  evalTest('USUALLY_PASSES', {
+    suiteName: 'default',
+    suiteType: 'behavioral',
    name: 'should attempt to read the redirected full output file when information is masked',
    params: {
      security: {
@@ -167,6 +169,8 @@ Output too large. Full output available at: ${outputFilePath}
   * Scenario: Information is in the preview.
   */
  evalTest('USUALLY_PASSES', {
+    suiteName: 'default',
+    suiteType: 'behavioral',
    name: 'should NOT read the full output file when the information is already in the preview',
    params: {
      security: {
@@ -25,6 +25,8 @@ const FILES = {

 describe('tracker_mode', () => {
  evalTest('USUALLY_PASSES', {
+    suiteName: 'default',
+    suiteType: 'behavioral',
    name: 'should manage tasks in the tracker when explicitly requested during a bug fix',
    params: {
      settings: { experimental: { taskTracker: true } },
@@ -78,6 +80,8 @@ describe('tracker_mode', () => {
  });

  evalTest('USUALLY_PASSES', {
+    suiteName: 'default',
+    suiteType: 'behavioral',
    name: 'should implicitly create tasks when asked to build a feature plan',
    params: {
      settings: { experimental: { taskTracker: true } },
@@ -9,6 +9,8 @@ import { evalTest } from './test-helper.js';

 describe('validation_fidelity', () => {
  evalTest('USUALLY_PASSES', {
+    suiteName: 'default',
+    suiteType: 'behavioral',
    name: 'should perform exhaustive validation autonomously when guided by system instructions',
    files: {
      'src/types.ts': `
@@ -9,6 +9,8 @@ import { evalTest } from './test-helper.js';

 describe('validation_fidelity_pre_existing_errors', () => {
  evalTest('USUALLY_PASSES', {
+    suiteName: 'default',
+    suiteType: 'behavioral',
    name: 'should handle pre-existing project errors gracefully during validation',
    files: {
      'src/math.ts': `
@@ -24,7 +24,10 @@ export default defineConfig({
    environment: 'node',
    globals: true,
    alias: {
-      react: path.resolve(__dirname, '../node_modules/react'),
+      '@google/gemini-cli-core': path.resolve(
+        __dirname,
+        '../packages/core/index.ts',
+      ),
    },
    setupFiles: [path.resolve(__dirname, '../packages/cli/test-setup.ts')],
    server: {
@@ -14,6 +14,7 @@ import { join, dirname, extname } from 'node:path';
 import { fileURLToPath } from 'node:url';
 import { canUseRipgrep } 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';

 const __dirname = dirname(fileURLToPath(import.meta.url));
@@ -88,15 +89,8 @@ export async function setup() {
  runDir = join(integrationTestsDir, `${Date.now()}`);
  await mkdir(runDir, { recursive: true });

-  // Set the home directory to the test run directory to avoid conflicts
-  // with the user's local config.
-  process.env['HOME'] = runDir;
-  if (process.platform === 'win32') {
-    process.env['USERPROFILE'] = runDir;
-  }
-  // We also need to set the config dir explicitly, since the code might
-  // construct the path before the HOME env var is set.
-  process.env['GEMINI_CONFIG_DIR'] = join(runDir, '.gemini');
+  // Isolate environment variables
+  isolateTestEnv(runDir);

  // Download ripgrep to avoid race conditions in parallel tests
  const available = await canUseRipgrep();
@@ -127,10 +121,6 @@ export async function setup() {
  }

  process.env['INTEGRATION_TEST_FILE_DIR'] = runDir;
-  process.env['GEMINI_CLI_INTEGRATION_TEST'] = 'true';
-  // Force file storage to avoid keychain prompts/hangs in CI, especially on macOS
-  process.env['GEMINI_FORCE_FILE_STORAGE'] = 'true';
-  process.env['TELEMETRY_LOG_FILE'] = join(runDir, 'telemetry.log');

  if (process.env['KEEP_OUTPUT']) {
    console.log(`Keeping output for test run in: ${runDir}`);
@@ -0,0 +1,30 @@
+{
+  "version": 1,
+  "updatedAt": "2026-04-08T01:21:58.770Z",
+  "scenarios": {
+    "multi-turn-conversation": {
+      "heapUsedBytes": 120082704,
+      "heapTotalBytes": 177586176,
+      "rssBytes": 269172736,
+      "timestamp": "2026-04-08T01:21:57.127Z"
+    },
+    "multi-function-call-repo-search": {
+      "heapUsedBytes": 104644984,
+      "heapTotalBytes": 111575040,
+      "rssBytes": 204079104,
+      "timestamp": "2026-04-08T01:21:58.770Z"
+    },
+    "idle-session-startup": {
+      "heapUsedBytes": 119813672,
+      "heapTotalBytes": 177061888,
+      "rssBytes": 267943936,
+      "timestamp": "2026-04-08T01:21:53.855Z"
+    },
+    "simple-prompt-response": {
+      "heapUsedBytes": 119722064,
+      "heapTotalBytes": 177324032,
+      "rssBytes": 268812288,
+      "timestamp": "2026-04-08T01:21:55.491Z"
+    }
+  }
+}
@@ -0,0 +1,71 @@
+/**
+ * @license
+ * Copyright 2026 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+import { mkdir, readdir, rm } from 'node:fs/promises';
+import { join, dirname } from 'node:path';
+import { fileURLToPath } from 'node:url';
+import { canUseRipgrep } from '../packages/core/src/tools/ripGrep.js';
+
+const __dirname = dirname(fileURLToPath(import.meta.url));
+const rootDir = join(__dirname, '..');
+const memoryTestsDir = join(rootDir, '.memory-tests');
+let runDir = '';
+
+export async function setup() {
+  runDir = join(memoryTestsDir, `${Date.now()}`);
+  await mkdir(runDir, { recursive: true });
+
+  // Set the home directory to the test run directory to avoid conflicts
+  // with the user's local config.
+  process.env['HOME'] = runDir;
+  if (process.platform === 'win32') {
+    process.env['USERPROFILE'] = runDir;
+  }
+  process.env['GEMINI_CONFIG_DIR'] = join(runDir, '.gemini');
+
+  // Download ripgrep to avoid race conditions
+  const available = await canUseRipgrep();
+  if (!available) {
+    throw new Error('Failed to download ripgrep binary');
+  }
+
+  // Clean up old test runs, keeping the latest few for debugging
+  try {
+    const testRuns = await readdir(memoryTestsDir);
+    if (testRuns.length > 3) {
+      const oldRuns = testRuns.sort().slice(0, testRuns.length - 3);
+      await Promise.all(
+        oldRuns.map((oldRun) =>
+          rm(join(memoryTestsDir, oldRun), {
+            recursive: true,
+            force: true,
+          }),
+        ),
+      );
+    }
+  } catch (e) {
+    console.error('Error cleaning up old memory test runs:', e);
+  }
+
+  process.env['INTEGRATION_TEST_FILE_DIR'] = runDir;
+  process.env['GEMINI_CLI_INTEGRATION_TEST'] = 'true';
+  process.env['GEMINI_FORCE_FILE_STORAGE'] = 'true';
+  process.env['TELEMETRY_LOG_FILE'] = join(runDir, 'telemetry.log');
+  process.env['VERBOSE'] = process.env['VERBOSE'] ?? 'false';
+
+  console.log(`\nMemory test output directory: ${runDir}`);
+}
+
+export async function teardown() {
+  // Cleanup unless KEEP_OUTPUT is set
+  if (process.env['KEEP_OUTPUT'] !== 'true' && runDir) {
+    try {
+      await rm(runDir, { recursive: true, force: true });
+    } catch (e) {
+      console.warn('Failed to clean up memory test directory:', e);
+    }
+  }
+}
@@ -0,0 +1,185 @@
+/**
+ * @license
+ * Copyright 2026 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+import { describe, it, beforeAll, afterAll, afterEach } from 'vitest';
+import { TestRig, MemoryTestHarness } from '@google/gemini-cli-test-utils';
+import { join, dirname } from 'node:path';
+import { fileURLToPath } from 'node:url';
+
+const __dirname = dirname(fileURLToPath(import.meta.url));
+const BASELINES_PATH = join(__dirname, 'baselines.json');
+const UPDATE_BASELINES = process.env['UPDATE_MEMORY_BASELINES'] === 'true';
+const TOLERANCE_PERCENT = 10;
+
+// Fake API key for tests using fake responses
+const TEST_ENV = { GEMINI_API_KEY: 'fake-memory-test-key' };
+
+describe('Memory Usage Tests', () => {
+  let harness: MemoryTestHarness;
+  let rig: TestRig;
+
+  beforeAll(() => {
+    harness = new MemoryTestHarness({
+      baselinesPath: BASELINES_PATH,
+      defaultTolerancePercent: TOLERANCE_PERCENT,
+      gcCycles: 3,
+      gcDelayMs: 100,
+      sampleCount: 3,
+    });
+  });
+
+  afterEach(async () => {
+    await rig.cleanup();
+  });
+
+  afterAll(async () => {
+    // Generate the summary report after all tests
+    await harness.generateReport();
+  });
+
+  it('idle-session-startup: memory usage within baseline', async () => {
+    rig = new TestRig();
+    rig.setup('memory-idle-startup', {
+      fakeResponsesPath: join(__dirname, 'memory.idle-startup.responses'),
+    });
+
+    const result = await harness.runScenario(
+      'idle-session-startup',
+      async (recordSnapshot) => {
+        await rig.run({
+          args: ['hello'],
+          timeout: 120000,
+          env: TEST_ENV,
+        });
+
+        await recordSnapshot('after-startup');
+      },
+    );
+
+    if (UPDATE_BASELINES) {
+      harness.updateScenarioBaseline(result);
+      console.log(
+        `Updated baseline for idle-session-startup: ${(result.finalHeapUsed / (1024 * 1024)).toFixed(1)} MB`,
+      );
+    } else {
+      harness.assertWithinBaseline(result);
+    }
+  });
+
+  it('simple-prompt-response: memory usage within baseline', async () => {
+    rig = new TestRig();
+    rig.setup('memory-simple-prompt', {
+      fakeResponsesPath: join(__dirname, 'memory.simple-prompt.responses'),
+    });
+
+    const result = await harness.runScenario(
+      'simple-prompt-response',
+      async (recordSnapshot) => {
+        await rig.run({
+          args: ['What is the capital of France?'],
+          timeout: 120000,
+          env: TEST_ENV,
+        });
+
+        await recordSnapshot('after-response');
+      },
+    );
+
+    if (UPDATE_BASELINES) {
+      harness.updateScenarioBaseline(result);
+      console.log(
+        `Updated baseline for simple-prompt-response: ${(result.finalHeapUsed / (1024 * 1024)).toFixed(1)} MB`,
+      );
+    } else {
+      harness.assertWithinBaseline(result);
+    }
+  });
+
+  it('multi-turn-conversation: memory remains stable over turns', async () => {
+    rig = new TestRig();
+    rig.setup('memory-multi-turn', {
+      fakeResponsesPath: join(__dirname, 'memory.multi-turn.responses'),
+    });
+
+    const prompts = [
+      'Hello, what can you help me with?',
+      'Tell me about JavaScript',
+      'How is TypeScript different?',
+      'Can you write a simple TypeScript function?',
+      'What are some TypeScript best practices?',
+    ];
+
+    const result = await harness.runScenario(
+      'multi-turn-conversation',
+      async (recordSnapshot) => {
+        // Run through all turns as a piped sequence
+        const stdinContent = prompts.join('\n');
+        await rig.run({
+          stdin: stdinContent,
+          timeout: 120000,
+          env: TEST_ENV,
+        });
+
+        // Take snapshots after the conversation completes
+        await recordSnapshot('after-all-turns');
+      },
+    );
+
+    if (UPDATE_BASELINES) {
+      harness.updateScenarioBaseline(result);
+      console.log(
+        `Updated baseline for multi-turn-conversation: ${(result.finalHeapUsed / (1024 * 1024)).toFixed(1)} MB`,
+      );
+    } else {
+      harness.assertWithinBaseline(result);
+    }
+  });
+
+  it('multi-function-call-repo-search: memory after tool use', async () => {
+    rig = new TestRig();
+    rig.setup('memory-multi-func-call', {
+      fakeResponsesPath: join(
+        __dirname,
+        'memory.multi-function-call.responses',
+      ),
+    });
+
+    // Create directories first, then files in the workspace so the tools have targets
+    rig.mkdir('packages/core/src/telemetry');
+    rig.createFile(
+      'packages/core/src/telemetry/memory-monitor.ts',
+      'export class MemoryMonitor { constructor() {} }',
+    );
+    rig.createFile(
+      'packages/core/src/telemetry/metrics.ts',
+      'export function recordMemoryUsage() {}',
+    );
+
+    const result = await harness.runScenario(
+      'multi-function-call-repo-search',
+      async (recordSnapshot) => {
+        await rig.run({
+          args: [
+            'Search this repository for MemoryMonitor and tell me what it does',
+          ],
+          timeout: 120000,
+          env: TEST_ENV,
+        });
+
+        await recordSnapshot('after-tool-calls');
+      },
+    );
+
+    if (UPDATE_BASELINES) {
+      harness.updateScenarioBaseline(result);
+      console.log(
+        `Updated baseline for multi-function-call-repo-search: ${(result.finalHeapUsed / (1024 * 1024)).toFixed(1)} MB`,
+      );
+    } else {
+      harness.assertWithinBaseline(result);
+    }
+  });
+});
@@ -0,0 +1,2 @@
+{"method":"generateContent","response":{"candidates":[{"content":{"parts":[{"text":"0"}],"role":"model"},"finishReason":"STOP","index":0}]}}
+{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"Hello! I'm ready to help. What would you like to work on?"}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":5,"candidatesTokenCount":12,"totalTokenCount":17,"promptTokensDetails":[{"modality":"TEXT","tokenCount":5}]}}]}
@@ -0,0 +1,4 @@
+{"method":"generateContent","response":{"candidates":[{"content":{"parts":[{"text":"0"}],"role":"model"},"finishReason":"STOP","index":0}]}}
+{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"I'll search for MemoryMonitor in the repository and analyze what it does."}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":30,"candidatesTokenCount":15,"totalTokenCount":45,"promptTokensDetails":[{"modality":"TEXT","tokenCount":30}]}}]}
+{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"grep_search","args":{"pattern":"MemoryMonitor","path":".","include_pattern":"*.ts"}}},{"functionCall":{"name":"list_directory","args":{"path":"packages/core/src/telemetry"}}},{"functionCall":{"name":"read_file","args":{"file_path":"packages/core/src/telemetry/memory-monitor.ts"}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":30,"candidatesTokenCount":80,"totalTokenCount":110,"promptTokensDetails":[{"modality":"TEXT","tokenCount":30}]}}]}
+{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"I found the memory monitoring code. Here's a summary:\n\nThe `MemoryMonitor` class in `packages/core/src/telemetry/memory-monitor.ts` provides:\n\n1. **Continuous monitoring** via `start()`/`stop()` with configurable intervals\n2. **V8 heap snapshots** using `v8.getHeapStatistics()` and `process.memoryUsage()`\n3. **High-water mark tracking** to detect significant memory growth\n4. **Rate-limited recording** to avoid metric flood\n5. **Activity detection** — only records when user is active\n\nThe class uses a singleton pattern via `initializeMemoryMonitor()` for global access."}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":500,"candidatesTokenCount":120,"totalTokenCount":620,"promptTokensDetails":[{"modality":"TEXT","tokenCount":500}]}}]}
@@ -0,0 +1,10 @@
+{"method":"generateContent","response":{"candidates":[{"content":{"parts":[{"text":"0"}],"role":"model"},"finishReason":"STOP","index":0}]}}
+{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"Hello! I'm ready to help you with your coding tasks. What would you like to work on today?"}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":5,"candidatesTokenCount":18,"totalTokenCount":23,"promptTokensDetails":[{"modality":"TEXT","tokenCount":5}]}}]}
+{"method":"generateContent","response":{"candidates":[{"content":{"parts":[{"text":"0"}],"role":"model"},"finishReason":"STOP","index":0}]}}
+{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"JavaScript is a high-level, interpreted programming language. It was originally designed for adding interactivity to web pages."}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":25,"candidatesTokenCount":60,"totalTokenCount":85,"promptTokensDetails":[{"modality":"TEXT","tokenCount":25}]}}]}
+{"method":"generateContent","response":{"candidates":[{"content":{"parts":[{"text":"0"}],"role":"model"},"finishReason":"STOP","index":0}]}}
+{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"TypeScript is a typed superset of JavaScript developed by Microsoft. The main differences from JavaScript are static typing and better tooling."}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":45,"candidatesTokenCount":80,"totalTokenCount":125,"promptTokensDetails":[{"modality":"TEXT","tokenCount":45}]}}]}
+{"method":"generateContent","response":{"candidates":[{"content":{"parts":[{"text":"0"}],"role":"model"},"finishReason":"STOP","index":0}]}}
+{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"Here is a simple TypeScript function:\n\nfunction greet(name: string): string { return `Hello, ${name}!`; }"}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":60,"candidatesTokenCount":55,"totalTokenCount":115,"promptTokensDetails":[{"modality":"TEXT","tokenCount":60}]}}]}
+{"method":"generateContent","response":{"candidates":[{"content":{"parts":[{"text":"0"}],"role":"model"},"finishReason":"STOP","index":0}]}}
+{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"Here are 5 key TypeScript best practices: Enable strict mode, prefer interfaces, use union types, leverage type inference, and use readonly."}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":75,"candidatesTokenCount":70,"totalTokenCount":145,"promptTokensDetails":[{"modality":"TEXT","tokenCount":75}]}}]}
@@ -0,0 +1,2 @@
+{"method":"generateContent","response":{"candidates":[{"content":{"parts":[{"text":"0"}],"role":"model"},"finishReason":"STOP","index":0}]}}
+{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"The capital of France is Paris. It has been the capital since the 10th century and is known for iconic landmarks like the Eiffel Tower, the Louvre Museum, and Notre-Dame Cathedral. Paris is also the most populous city in France, with a metropolitan area population of over 12 million people."}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":7,"candidatesTokenCount":55,"totalTokenCount":62,"promptTokensDetails":[{"modality":"TEXT","tokenCount":7}]}}]}
@@ -0,0 +1,12 @@
+{
+  "extends": "../tsconfig.json",
+  "compilerOptions": {
+    "noEmit": true,
+    "allowJs": true
+  },
+  "include": ["**/*.ts"],
+  "references": [
+    { "path": "../packages/core" },
+    { "path": "../packages/test-utils" }
+  ]
+}
@@ -0,0 +1,28 @@
+/**
+ * @license
+ * Copyright 2026 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+import { defineConfig } from 'vitest/config';
+
+export default defineConfig({
+  test: {
+    testTimeout: 600000, // 10 minutes — memory profiling is slow
+    globalSetup: './globalSetup.ts',
+    reporters: ['default'],
+    include: ['**/*.test.ts'],
+    retry: 0, // No retries for memory tests — noise is handled by tolerance
+    fileParallelism: false, // Must run serially to avoid memory interference
+    pool: 'forks', // Use forks pool for --expose-gc support
+    poolOptions: {
+      forks: {
+        singleFork: true, // Single process for accurate per-test memory readings
+        execArgv: ['--expose-gc'], // Enable global.gc() for forced GC
+      },
+    },
+    env: {
+      GEMINI_TEST_TYPE: 'memory',
+    },
+  },
+});
@@ -1,17 +1,17 @@
 {
  "name": "@google/gemini-cli",
-  "version": "0.36.0-nightly.20260317.2f90b4653",
+  "version": "0.39.0-nightly.20260408.e77b22e63",
  "lockfileVersion": 3,
  "requires": true,
  "packages": {
    "": {
      "name": "@google/gemini-cli",
-      "version": "0.36.0-nightly.20260317.2f90b4653",
+      "version": "0.39.0-nightly.20260408.e77b22e63",
      "workspaces": [
        "packages/*"
      ],
      "dependencies": {
-        "ink": "npm:@jrichman/ink@6.6.7",
+        "ink": "npm:@jrichman/ink@6.6.9",
        "latest-version": "^9.0.0",
        "node-fetch-native": "^1.6.7",
        "proper-lockfile": "^4.1.2",
@@ -36,6 +36,7 @@
        "@types/ws": "^8.18.1",
        "@vitest/coverage-v8": "^3.1.1",
        "@vitest/eslint-plugin": "^1.3.4",
+        "asciichart": "^1.5.25",
        "cross-env": "^7.0.3",
        "depcheck": "^1.4.7",
        "domexception": "^4.0.0",
@@ -5569,6 +5570,12 @@
      "dev": true,
      "license": "MIT"
    },
+    "node_modules/asciichart": {
+      "version": "1.5.25",
+      "resolved": "https://registry.npmjs.org/asciichart/-/asciichart-1.5.25.tgz",
+      "integrity": "sha512-PNxzXIPPOtWq8T7bgzBtk9cI2lgS4SJZthUHEiQ1aoIc3lNzGfUvIvo9LiAnq26TACo9t1/4qP6KTGAUbzX9Xg==",
+      "license": "MIT"
+    },
    "node_modules/assertion-error": {
      "version": "2.0.1",
      "resolved": "https://registry.npmjs.org/assertion-error/-/assertion-error-2.0.1.tgz",
@@ -10049,9 +10056,9 @@
    },
    "node_modules/ink": {
      "name": "@jrichman/ink",
-      "version": "6.6.7",
-      "resolved": "https://registry.npmjs.org/@jrichman/ink/-/ink-6.6.7.tgz",
-      "integrity": "sha512-bDzQLpLzK/dn9Ur/Ku88ZZR9totVcMGrGYAgPHidsAAbe9NKztU1fggj/iu0wRp5g1kBeALb3cfagFGdDxAU1w==",
+      "version": "6.6.9",
+      "resolved": "https://registry.npmjs.org/@jrichman/ink/-/ink-6.6.9.tgz",
+      "integrity": "sha512-RL9sSiLQZECnjbmBwjIHOp8yVGdWF7C/uifg7ISv/e+F3nLNsfl7FdUFQs8iZARFMJAYxMFpxW6OW+HSt9drwQ==",
      "license": "MIT",
      "dependencies": {
        "ansi-escapes": "^7.0.0",
@@ -17389,7 +17396,7 @@
    },
    "packages/a2a-server": {
      "name": "@google/gemini-cli-a2a-server",
-      "version": "0.36.0-nightly.20260317.2f90b4653",
+      "version": "0.39.0-nightly.20260408.e77b22e63",
      "dependencies": {
        "@a2a-js/sdk": "0.3.11",
        "@google-cloud/storage": "^7.16.0",
@@ -17504,7 +17511,7 @@
    },
    "packages/cli": {
      "name": "@google/gemini-cli",
-      "version": "0.36.0-nightly.20260317.2f90b4653",
+      "version": "0.39.0-nightly.20260408.e77b22e63",
      "license": "Apache-2.0",
      "dependencies": {
        "@agentclientprotocol/sdk": "^0.16.1",
@@ -17526,7 +17533,7 @@
        "fzf": "^0.5.2",
        "glob": "^12.0.0",
        "highlight.js": "^11.11.1",
-        "ink": "npm:@jrichman/ink@6.6.7",
+        "ink": "npm:@jrichman/ink@6.6.9",
        "ink-gradient": "^3.0.0",
        "ink-spinner": "^5.0.0",
        "latest-version": "^9.0.0",
@@ -17676,7 +17683,7 @@
    },
    "packages/core": {
      "name": "@google/gemini-cli-core",
-      "version": "0.36.0-nightly.20260317.2f90b4653",
+      "version": "0.39.0-nightly.20260408.e77b22e63",
      "license": "Apache-2.0",
      "dependencies": {
        "@a2a-js/sdk": "0.3.11",
@@ -17942,7 +17949,7 @@
    },
    "packages/devtools": {
      "name": "@google/gemini-cli-devtools",
-      "version": "0.36.0-nightly.20260317.2f90b4653",
+      "version": "0.39.0-nightly.20260408.e77b22e63",
      "license": "Apache-2.0",
      "dependencies": {
        "ws": "^8.16.0"
@@ -17957,7 +17964,7 @@
    },
    "packages/sdk": {
      "name": "@google/gemini-cli-sdk",
-      "version": "0.36.0-nightly.20260317.2f90b4653",
+      "version": "0.39.0-nightly.20260408.e77b22e63",
      "license": "Apache-2.0",
      "dependencies": {
        "@google/gemini-cli-core": "file:../core",
@@ -17974,11 +17981,12 @@
    },
    "packages/test-utils": {
      "name": "@google/gemini-cli-test-utils",
-      "version": "0.36.0-nightly.20260317.2f90b4653",
+      "version": "0.39.0-nightly.20260408.e77b22e63",
      "license": "Apache-2.0",
      "dependencies": {
        "@google/gemini-cli-core": "file:../core",
        "@lydell/node-pty": "1.1.0",
+        "asciichart": "^1.5.25",
        "strip-ansi": "^7.1.2",
        "vitest": "^3.2.4"
      },
@@ -17991,7 +17999,7 @@
    },
    "packages/vscode-ide-companion": {
      "name": "gemini-cli-vscode-ide-companion",
-      "version": "0.36.0-nightly.20260317.2f90b4653",
+      "version": "0.39.0-nightly.20260408.e77b22e63",
      "license": "LICENSE",
      "dependencies": {
        "@modelcontextprotocol/sdk": "^1.23.0",
@@ -1,6 +1,6 @@
 {
  "name": "@google/gemini-cli",
-  "version": "0.36.0-nightly.20260317.2f90b4653",
+  "version": "0.39.0-nightly.20260408.e77b22e63",
  "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:0.36.0-nightly.20260317.2f90b4653"
+    "sandboxImageUri": "us-docker.pkg.dev/gemini-code-dev/gemini-cli/sandbox:0.39.0-nightly.20260408.e77b22e63"
  },
  "scripts": {
    "start": "cross-env NODE_ENV=development node scripts/start.js",
@@ -51,6 +51,10 @@
    "test:integration:all": "npm run test:integration:sandbox:none && npm run test:integration:sandbox:docker && npm run test:integration:sandbox:podman",
    "test:integration:flaky": "cross-env RUN_FLAKY_INTEGRATION=1 npm run test:integration:sandbox:none",
    "test:integration:sandbox:none": "cross-env GEMINI_SANDBOX=false vitest run --root ./integration-tests",
+    "test:memory": "vitest run --root ./memory-tests",
+    "test:memory:update-baselines": "cross-env UPDATE_MEMORY_BASELINES=true vitest run --root ./memory-tests",
+    "test:perf": "vitest run --root ./perf-tests",
+    "test:perf:update-baselines": "cross-env UPDATE_PERF_BASELINES=true vitest run --root ./perf-tests",
    "test:integration:sandbox:docker": "cross-env GEMINI_SANDBOX=docker npm run build:sandbox && cross-env GEMINI_SANDBOX=docker vitest run --root ./integration-tests",
    "test:integration:sandbox:podman": "cross-env GEMINI_SANDBOX=podman vitest run --root ./integration-tests",
    "lint": "cross-env NODE_OPTIONS=\"--max-old-space-size=8192\" eslint . --cache --max-warnings 0",
@@ -69,7 +73,7 @@
    "pre-commit": "node scripts/pre-commit.js"
  },
  "overrides": {
-    "ink": "npm:@jrichman/ink@6.6.7",
+    "ink": "npm:@jrichman/ink@6.6.9",
    "wrap-ansi": "9.0.2",
    "cliui": {
      "wrap-ansi": "7.0.0"
@@ -103,6 +107,7 @@
    "@types/ws": "^8.18.1",
    "@vitest/coverage-v8": "^3.1.1",
    "@vitest/eslint-plugin": "^1.3.4",
+    "asciichart": "^1.5.25",
    "cross-env": "^7.0.3",
    "depcheck": "^1.4.7",
    "domexception": "^4.0.0",
@@ -137,7 +142,7 @@
    "yargs": "^17.7.2"
  },
  "dependencies": {
-    "ink": "npm:@jrichman/ink@6.6.7",
+    "ink": "npm:@jrichman/ink@6.6.9",
    "latest-version": "^9.0.0",
    "node-fetch-native": "^1.6.7",
    "proper-lockfile": "^4.1.2",
@@ -1,6 +1,6 @@
 {
  "name": "@google/gemini-cli-a2a-server",
-  "version": "0.36.0-nightly.20260317.2f90b4653",
+  "version": "0.39.0-nightly.20260408.e77b22e63",
  "description": "Gemini CLI A2A Server",
  "repository": {
    "type": "git",
@@ -6,9 +6,9 @@
 * SPDX-License-Identifier: Apache-2.0
 */

-import { main } from './src/gemini.js';
-import { FatalError, writeToStderr } from '@google/gemini-cli-core';
-import { runExitCleanup } from './src/utils/cleanup.js';
+import { spawn } from 'node:child_process';
+import os from 'node:os';
+import v8 from 'node:v8';

 // --- Global Entry Point ---

@@ -28,44 +28,162 @@ process.on('uncaughtException', (error) => {
  // For other errors, we rely on the default behavior, but since we attached a listener,
  // we must manually replicate it.
  if (error instanceof Error) {
-    writeToStderr(error.stack + '\n');
+    process.stderr.write(error.stack + '\n');
  } else {
-    writeToStderr(String(error) + '\n');
+    process.stderr.write(String(error) + '\n');
  }
  process.exit(1);
 });

-main().catch(async (error) => {
-  // Set a timeout to force exit if cleanup hangs
-  const cleanupTimeout = setTimeout(() => {
-    writeToStderr('Cleanup timed out, forcing exit...\n');
-    process.exit(1);
-  }, 5000);
-
+async function getMemoryNodeArgs(): Promise<string[]> {
+  let autoConfigureMemory = true;
  try {
-    await runExitCleanup();
-  } catch (cleanupError) {
-    writeToStderr(
-      `Error during final cleanup: ${cleanupError instanceof Error ? cleanupError.message : String(cleanupError)}\n`,
-    );
-  } finally {
-    clearTimeout(cleanupTimeout);
-  }
-
-  if (error instanceof FatalError) {
-    let errorMessage = error.message;
-    if (!process.env['NO_COLOR']) {
-      errorMessage = `\x1b[31m${errorMessage}\x1b[0m`;
+    const { readFileSync } = await import('node:fs');
+    const { join } = await import('node:path');
+    // Respect GEMINI_CLI_HOME environment variable, falling back to os.homedir()
+    const baseDir =
+      process.env['GEMINI_CLI_HOME'] || join(os.homedir(), '.gemini');
+    const settingsPath = join(baseDir, 'settings.json');
+    const rawSettings = readFileSync(settingsPath, 'utf8');
+    const settings = JSON.parse(rawSettings);
+    if (settings?.advanced?.autoConfigureMemory === false) {
+      autoConfigureMemory = false;
    }
-    writeToStderr(errorMessage + '\n');
-    process.exit(error.exitCode);
+  } catch {
+    // ignore
  }

-  writeToStderr('An unexpected critical error occurred:');
-  if (error instanceof Error) {
-    writeToStderr(error.stack + '\n');
-  } else {
-    writeToStderr(String(error) + '\n');
+  if (autoConfigureMemory) {
+    const totalMemoryMB = os.totalmem() / (1024 * 1024);
+    const heapStats = v8.getHeapStatistics();
+    const currentMaxOldSpaceSizeMb = Math.floor(
+      heapStats.heap_size_limit / 1024 / 1024,
+    );
+    const targetMaxOldSpaceSizeInMB = Math.floor(totalMemoryMB * 0.5);
+
+    if (targetMaxOldSpaceSizeInMB > currentMaxOldSpaceSizeMb) {
+      return [`--max-old-space-size=${targetMaxOldSpaceSizeInMB}`];
+    }
  }
-  process.exit(1);
-});
+
+  return [];
+}
+
+async function run() {
+  if (!process.env['GEMINI_CLI_NO_RELAUNCH'] && !process.env['SANDBOX']) {
+    // --- Lightweight Parent Process / Daemon ---
+    // We avoid importing heavy dependencies here to save ~1.5s of startup time.
+
+    const nodeArgs: string[] = [...process.execArgv];
+    const scriptArgs = process.argv.slice(2);
+
+    const memoryArgs = await getMemoryNodeArgs();
+    nodeArgs.push(...memoryArgs);
+
+    const script = process.argv[1];
+    nodeArgs.push(script);
+    nodeArgs.push(...scriptArgs);
+
+    const newEnv = { ...process.env, GEMINI_CLI_NO_RELAUNCH: 'true' };
+    const RELAUNCH_EXIT_CODE = 199;
+    let latestAdminSettings: unknown = undefined;
+
+    // Prevent the parent process from exiting prematurely on signals.
+    // The child process will receive the same signals and handle its own cleanup.
+    for (const sig of ['SIGINT', 'SIGTERM', 'SIGHUP']) {
+      process.on(sig as NodeJS.Signals, () => {});
+    }
+
+    const runner = () => {
+      process.stdin.pause();
+
+      const child = spawn(process.execPath, nodeArgs, {
+        stdio: ['inherit', 'inherit', 'inherit', 'ipc'],
+        env: newEnv,
+      });
+
+      if (latestAdminSettings) {
+        child.send({ type: 'admin-settings', settings: latestAdminSettings });
+      }
+
+      child.on('message', (msg: { type?: string; settings?: unknown }) => {
+        if (msg.type === 'admin-settings-update' && msg.settings) {
+          latestAdminSettings = msg.settings;
+        }
+      });
+
+      return new Promise<number>((resolve) => {
+        child.on('error', (err) => {
+          process.stderr.write(
+            'Error: Failed to start child process: ' + err.message + '\n',
+          );
+          resolve(1);
+        });
+        child.on('close', (code) => {
+          process.stdin.resume();
+          resolve(code ?? 1);
+        });
+      });
+    };
+
+    while (true) {
+      try {
+        const exitCode = await runner();
+        if (exitCode !== RELAUNCH_EXIT_CODE) {
+          process.exit(exitCode);
+        }
+      } catch (error: unknown) {
+        process.stdin.resume();
+        process.stderr.write(
+          `Fatal error: Failed to relaunch the CLI process.\n${error instanceof Error ? (error.stack ?? error.message) : String(error)}\n`,
+        );
+        process.exit(1);
+      }
+    }
+  } else {
+    // --- Heavy Child Process ---
+    // Now we can safely import everything.
+    const { main } = await import('./src/gemini.js');
+    const { FatalError, writeToStderr } = await import(
+      '@google/gemini-cli-core'
+    );
+    const { runExitCleanup } = await import('./src/utils/cleanup.js');
+
+    main().catch(async (error: unknown) => {
+      // Set a timeout to force exit if cleanup hangs
+      const cleanupTimeout = setTimeout(() => {
+        writeToStderr('Cleanup timed out, forcing exit...\n');
+        process.exit(1);
+      }, 5000);
+
+      try {
+        await runExitCleanup();
+      } catch (cleanupError: unknown) {
+        writeToStderr(
+          `Error during final cleanup: ${cleanupError instanceof Error ? cleanupError.message : String(cleanupError)}\n`,
+        );
+      } finally {
+        clearTimeout(cleanupTimeout);
+      }
+
+      if (error instanceof FatalError) {
+        let errorMessage = error.message;
+        if (!process.env['NO_COLOR']) {
+          errorMessage = `\x1b[31m${errorMessage}\x1b[0m`;
+        }
+        writeToStderr(errorMessage + '\n');
+        process.exit(error.exitCode);
+      }
+
+      writeToStderr('An unexpected critical error occurred:');
+      if (error instanceof Error) {
+        writeToStderr(error.stack + '\n');
+      } else {
+        writeToStderr(String(error) + '\n');
+      }
+      process.exit(1);
+    });
+  }
+}
+
+run();
@@ -1,6 +1,6 @@
 {
  "name": "@google/gemini-cli",
-  "version": "0.36.0-nightly.20260317.2f90b4653",
+  "version": "0.39.0-nightly.20260408.e77b22e63",
  "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:0.36.0-nightly.20260317.2f90b4653"
+    "sandboxImageUri": "us-docker.pkg.dev/gemini-code-dev/gemini-cli/sandbox:0.39.0-nightly.20260408.e77b22e63"
  },
  "dependencies": {
    "@agentclientprotocol/sdk": "^0.16.1",
@@ -49,7 +49,7 @@
    "fzf": "^0.5.2",
    "glob": "^12.0.0",
    "highlight.js": "^11.11.1",
-    "ink": "npm:@jrichman/ink@6.6.7",
+    "ink": "npm:@jrichman/ink@6.6.9",
    "ink-gradient": "^3.0.0",
    "ink-spinner": "^5.0.0",
    "latest-version": "^9.0.0",
@@ -372,7 +372,7 @@ export class GeminiAgent {
      mcpServers,
    );

-    const sessionSelector = new SessionSelector(config);
+    const sessionSelector = new SessionSelector(config.storage);
    const { sessionData, sessionPath } =
      await sessionSelector.resolveSession(sessionId);

@@ -6,6 +6,7 @@

 import {
  addMemory,
+  listInboxSkills,
  listMemoryFiles,
  refreshMemory,
  showMemory,
@@ -30,6 +31,7 @@ export class MemoryCommand implements Command {
    new RefreshMemoryCommand(),
    new ListMemoryCommand(),
    new AddMemoryCommand(),
+    new InboxMemoryCommand(),
  ];
  readonly requiresWorkspace = true;

@@ -122,3 +124,39 @@ export class AddMemoryCommand implements Command {
    }
  }
 }
+
+export class InboxMemoryCommand implements Command {
+  readonly name = 'memory inbox';
+  readonly description =
+    'Lists skills extracted from past sessions that are pending review.';
+
+  async execute(
+    context: CommandContext,
+    _: string[],
+  ): Promise<CommandExecutionResponse> {
+    if (!context.agentContext.config.isMemoryManagerEnabled()) {
+      return {
+        name: this.name,
+        data: 'The memory inbox requires the experimental memory manager. Enable it with: experimental.memoryManager = true in settings.',
+      };
+    }
+
+    const skills = await listInboxSkills(context.agentContext.config);
+
+    if (skills.length === 0) {
+      return { name: this.name, data: 'No extracted skills in inbox.' };
+    }
+
+    const lines = skills.map((s) => {
+      const date = s.extractedAt
+        ? ` (extracted: ${new Date(s.extractedAt).toLocaleDateString()})`
+        : '';
+      return `- **${s.name}**: ${s.description}${date}`;
+    });
+
+    return {
+      name: this.name,
+      data: `Skill inbox (${skills.length}):\n${lines.join('\n')}`,
+    };
+  }
+}
@@ -1907,7 +1907,8 @@ const SETTINGS_SCHEMA = {
        category: 'Advanced',
        requiresRestart: true,
        default: true,
-        description: 'Automatically configure Node.js memory limits',
+        description:
+          'Automatically configure Node.js memory limits. Note: Because memory is allocated during the initial process boot, this setting is only read from the global user settings file and ignores workspace-level overrides.',
        showInDialog: true,
      },
      dnsResolutionOrder: {
@@ -13,7 +13,7 @@ import {
  type OutputPayload,
  type ConsoleLogPayload,
  type UserFeedbackPayload,
-  sessionId,
+  createSessionId,
  logUserPrompt,
  AuthType,
  UserPromptEvent,
@@ -33,6 +33,7 @@ import {
  type AdminControlsSettings,
  debugLogger,
  isHeadlessMode,
+  Storage,
 } from '@google/gemini-cli-core';

 import { loadCliConfig, parseArguments } from './config/config.js';
@@ -80,10 +81,7 @@ import { validateNonInteractiveAuth } from './validateNonInterActiveAuth.js';
 import { appEvents, AppEvent } from './utils/events.js';
 import { SessionError, SessionSelector } from './utils/sessionUtils.js';

-import {
-  relaunchAppInChildProcess,
-  relaunchOnExitCode,
-} from './utils/relaunch.js';
+import { relaunchOnExitCode } from './utils/relaunch.js';
 import { loadSandboxConfig } from './config/sandboxConfig.js';
 import { deleteSession, listSessions } from './utils/sessions.js';
 import { createPolicyUpdater } from './config/policy.js';
@@ -185,6 +183,39 @@ ${reason.stack}`
  });
 }

+export async function resolveSessionId(resumeArg: string | undefined): Promise<{
+  sessionId: string;
+  resumedSessionData?: ResumedSessionData;
+}> {
+  if (!resumeArg) {
+    return { sessionId: createSessionId() };
+  }
+
+  const storage = new Storage(process.cwd());
+  await storage.initialize();
+
+  try {
+    const { sessionData, sessionPath } = await new SessionSelector(
+      storage,
+    ).resolveSession(resumeArg);
+    return {
+      sessionId: sessionData.sessionId,
+      resumedSessionData: { conversation: sessionData, filePath: sessionPath },
+    };
+  } catch (error) {
+    if (error instanceof SessionError && error.code === 'NO_SESSIONS_FOUND') {
+      coreEvents.emitFeedback('warning', error.message);
+      return { sessionId: createSessionId() };
+    }
+    coreEvents.emitFeedback(
+      'error',
+      `Error resuming session: ${error instanceof Error ? error.message : 'Unknown error'}`,
+    );
+    await runExitCleanup();
+    process.exit(ExitCodes.FATAL_INPUT_ERROR);
+  }
+}
+
 export async function startInteractiveUI(
  config: Config,
  settings: LoadedSettings,
@@ -280,6 +311,8 @@ export async function main() {

  const argv = await argvPromise;

+  const { sessionId, resumedSessionData } = await resolveSessionId(argv.resume);
+
  if (
    (argv.allowedTools && argv.allowedTools.length > 0) ||
    (settings.merged.tools?.allowed && settings.merged.tools.allowed.length > 0)
@@ -403,6 +436,12 @@ export async function main() {
  // Set remote admin settings if returned from CCPA.
  if (remoteAdminSettings) {
    settings.setRemoteAdminSettings(remoteAdminSettings);
+    if (process.send) {
+      process.send({
+        type: 'admin-settings-update',
+        settings: remoteAdminSettings,
+      });
+    }
  }

  // Run deferred command now that we have admin settings.
@@ -460,10 +499,6 @@ export async function main() {
      );
      await runExitCleanup();
      process.exit(ExitCodes.SUCCESS);
-    } else {
-      // Relaunch app so we always have a child process that can be internally
-      // restarted if needed.
-      await relaunchAppInChildProcess(memoryArgs, [], remoteAdminSettings);
    }
  }

@@ -599,40 +634,6 @@ export async function main() {
      })),
    ];

-    // Handle --resume flag
-    let resumedSessionData: ResumedSessionData | undefined = undefined;
-    if (argv.resume) {
-      const sessionSelector = new SessionSelector(config);
-      try {
-        const result = await sessionSelector.resolveSession(argv.resume);
-        resumedSessionData = {
-          conversation: result.sessionData,
-          filePath: result.sessionPath,
-        };
-        // Use the existing session ID to continue recording to the same session
-        config.setSessionId(resumedSessionData.conversation.sessionId);
-      } catch (error) {
-        if (
-          error instanceof SessionError &&
-          error.code === 'NO_SESSIONS_FOUND'
-        ) {
-          // No sessions to resume — start a fresh session with a warning
-          startupWarnings.push({
-            id: 'resume-no-sessions',
-            message: error.message,
-            priority: WarningPriority.High,
-          });
-        } else {
-          coreEvents.emitFeedback(
-            'error',
-            `Error resuming session: ${error instanceof Error ? error.message : 'Unknown error'}`,
-          );
-          await runExitCleanup();
-          process.exit(ExitCodes.FATAL_INPUT_ERROR);
-        }
-      }
-    }
-
    cliStartupHandle?.end();

    // Render UI, passing necessary config values. Check that there is no command line question.
@@ -73,6 +73,7 @@ vi.mock('./config/config.js', () => ({
    getSandbox: vi.fn(() => false),
    getQuestion: vi.fn(() => ''),
    isInteractive: () => false,
+    getSessionId: vi.fn().mockReturnValue('test-session-id'),
    storage: { initialize: vi.fn().mockResolvedValue(undefined) },
  } as unknown as Config),
  parseArguments: vi.fn().mockResolvedValue({}),
@@ -213,6 +214,7 @@ describe('gemini.tsx main function cleanup', () => {
      getSandbox: vi.fn(() => false),
      getDebugMode: vi.fn(() => false),
      getPolicyEngine: vi.fn(),
+      getSessionId: vi.fn().mockReturnValue('test-session-id'),
      getMessageBus: () => ({ subscribe: vi.fn() }),
      getEnableHooks: vi.fn(() => false),
      getHookSystem: () => undefined,
@@ -273,6 +275,7 @@ describe('gemini.tsx main function cleanup', () => {
    vi.mocked(loadCliConfig).mockResolvedValue(
      buildMockConfig({
        getHookSystem: vi.fn(() => mockHookSystem),
+        getSessionId: vi.fn().mockReturnValue('test-session-id'),
      }),
    );

@@ -107,7 +107,7 @@ export async function startInteractiveUI(
              <TerminalProvider>
                <ScrollProvider>
                  <OverflowProvider>
-                    <SessionStatsProvider>
+                    <SessionStatsProvider sessionId={config.getSessionId()}>
                      <VimModeProvider>
                        <AppContainer
                          config={config}
@@ -731,7 +731,7 @@ export const renderWithProviders = async (
            <UIStateContext.Provider value={finalUiState}>
              <VimModeProvider>
                <ShellFocusContext.Provider value={shellFocus}>
-                  <SessionStatsProvider>
+                  <SessionStatsProvider sessionId={config.getSessionId()}>
                    <StreamingContext.Provider
                      value={finalUiState.streamingState}
                    >
@@ -444,7 +444,7 @@ export const AppContainer = (props: AppContainerProps) => {

  const [isConfigInitialized, setConfigInitialized] = useState(false);

-  const logger = useLogger(config.storage);
+  const logger = useLogger(config);
  const { inputHistory, addInput, initializeFromLogger } =
    useInputHistoryStore();

@@ -14,7 +14,8 @@
    <text x="0" y="19" fill="#000000" textLength="900" lengthAdjust="spacingAndGlyphs">▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄</text>
    <text x="0" y="53" fill="#333333" textLength="891" lengthAdjust="spacingAndGlyphs">╭─────────────────────────────────────────────────────────────────────────────────────────────────╮</text>
    <text x="0" y="70" fill="#333333" textLength="9" lengthAdjust="spacingAndGlyphs">│</text>
-    <text x="18" y="70" fill="#ffffaf" textLength="54" lengthAdjust="spacingAndGlyphs" font-weight="bold">? Edit</text>
+    <text x="18" y="70" fill="#ffffaf" textLength="63" lengthAdjust="spacingAndGlyphs" font-weight="bold">? Edit </text>
+    <text x="81" y="70" fill="#ffffff" textLength="783" lengthAdjust="spacingAndGlyphs">packages/.../InputPrompt.tsx:   return kittyProtocolSupporte... =&gt;   return kittyProto…</text>
    <text x="882" y="70" fill="#333333" textLength="9" lengthAdjust="spacingAndGlyphs">│</text>
    <text x="0" y="87" fill="#333333" textLength="9" lengthAdjust="spacingAndGlyphs">│</text>
    <text x="18" y="87" fill="#333333" textLength="855" lengthAdjust="spacingAndGlyphs">╭─────────────────────────────────────────────────────────────────────────────────────────────╮</text>
@@ -5,7 +5,7 @@ exports[`Full Terminal Tool Confirmation Snapshot > renders tool confirmation bo
 ▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄

 ╭─────────────────────────────────────────────────────────────────────────────────────────────────╮
-│ ? Edit                                                                                          │
+│ ? Edit packages/.../InputPrompt.tsx:   return kittyProtocolSupporte... =>   return kittyProto…  │
 │ ╭─────────────────────────────────────────────────────────────────────────────────────────────╮ │
 │ │ ... first 42 lines hidden (Ctrl+O to show) ...                                              │ │
 │ │ 43   const line43 = true;                                                                   │ │
@@ -9,7 +9,7 @@ import open from 'open';
 import path from 'node:path';
 import { bugCommand } from './bugCommand.js';
 import { createMockCommandContext } from '../../test-utils/mockCommandContext.js';
-import { getVersion } from '@google/gemini-cli-core';
+import { getVersion, type Config } from '@google/gemini-cli-core';
 import { GIT_COMMIT_INFO } from '../../generated/git-commit.js';
 import { formatBytes } from '../utils/formatters.js';

@@ -89,7 +89,8 @@ describe('bugCommand', () => {
            getBugCommand: () => undefined,
            getIdeMode: () => true,
            getContentGeneratorConfig: () => ({ authType: 'oauth-personal' }),
-          },
+            getSessionId: vi.fn().mockReturnValue('test-session-id'),
+          } as unknown as Config,
          geminiClient: {
            getChat: () => ({
              getHistory: () => [],
@@ -137,7 +138,8 @@ describe('bugCommand', () => {
            storage: {
              getProjectTempDir: () => '/tmp/gemini',
            },
-          },
+            getSessionId: vi.fn().mockReturnValue('test-session-id'),
+          } as unknown as Config,
          geminiClient: {
            getChat: () => ({
              getHistory: () => history,
@@ -182,7 +184,8 @@ describe('bugCommand', () => {
            getBugCommand: () => ({ urlTemplate: customTemplate }),
            getIdeMode: () => true,
            getContentGeneratorConfig: () => ({ authType: 'vertex-ai' }),
-          },
+            getSessionId: vi.fn().mockReturnValue('test-session-id'),
+          } as unknown as Config,
          geminiClient: {
            getChat: () => ({
              getHistory: () => [],
@@ -16,7 +16,6 @@ import { GIT_COMMIT_INFO } from '../../generated/git-commit.js';
 import { formatBytes } from '../utils/formatters.js';
 import {
  IdeClient,
-  sessionId,
  getVersion,
  INITIAL_HISTORY_LENGTH,
  debugLogger,
@@ -59,7 +58,7 @@ export const bugCommand: SlashCommand = {
    let info = `
 * **CLI Version:** ${cliVersion}
 * **Git Commit:** ${GIT_COMMIT_INFO}
-* **Session ID:** ${sessionId}
+* **Session ID:** ${config?.getSessionId() || 'Unknown'}
 * **Operating System:** ${osVersion}
 * **Sandbox Environment:** ${sandboxEnv}
 * **Model Version:** ${modelVersion}
@@ -457,4 +457,78 @@ describe('memoryCommand', () => {
      );
    });
  });
+
+  describe('/memory inbox', () => {
+    let inboxCommand: SlashCommand;
+
+    beforeEach(() => {
+      inboxCommand = memoryCommand.subCommands!.find(
+        (cmd) => cmd.name === 'inbox',
+      )!;
+      expect(inboxCommand).toBeDefined();
+    });
+
+    it('should return custom_dialog when config is available and flag is enabled', () => {
+      if (!inboxCommand.action) throw new Error('Command has no action');
+
+      const mockConfig = {
+        reloadSkills: vi.fn(),
+        isMemoryManagerEnabled: vi.fn().mockReturnValue(true),
+      };
+      const context = createMockCommandContext({
+        services: {
+          agentContext: { config: mockConfig },
+        },
+        ui: {
+          removeComponent: vi.fn(),
+          reloadCommands: vi.fn(),
+        },
+      });
+
+      const result = inboxCommand.action(context, '');
+
+      expect(result).toHaveProperty('type', 'custom_dialog');
+      expect(result).toHaveProperty('component');
+    });
+
+    it('should return info message when memory manager is disabled', () => {
+      if (!inboxCommand.action) throw new Error('Command has no action');
+
+      const mockConfig = {
+        isMemoryManagerEnabled: vi.fn().mockReturnValue(false),
+      };
+      const context = createMockCommandContext({
+        services: {
+          agentContext: { config: mockConfig },
+        },
+      });
+
+      const result = inboxCommand.action(context, '');
+
+      expect(result).toEqual({
+        type: 'message',
+        messageType: 'info',
+        content:
+          'The memory inbox requires the experimental memory manager. Enable it with: experimental.memoryManager = true in settings.',
+      });
+    });
+
+    it('should return error when config is not loaded', () => {
+      if (!inboxCommand.action) throw new Error('Command has no action');
+
+      const context = createMockCommandContext({
+        services: {
+          agentContext: null,
+        },
+      });
+
+      const result = inboxCommand.action(context, '');
+
+      expect(result).toEqual({
+        type: 'message',
+        messageType: 'error',
+        content: 'Config not loaded.',
+      });
+    });
+  });
 });
@@ -4,6 +4,7 @@
 * SPDX-License-Identifier: Apache-2.0
 */

+import React from 'react';
 import {
  addMemory,
  listMemoryFiles,
@@ -13,9 +14,11 @@ import {
 import { MessageType } from '../types.js';
 import {
  CommandKind,
+  type OpenCustomDialogActionReturn,
  type SlashCommand,
  type SlashCommandActionReturn,
 } from './types.js';
+import { SkillInboxDialog } from '../components/SkillInboxDialog.js';

 export const memoryCommand: SlashCommand = {
  name: 'memory',
@@ -124,5 +127,45 @@ export const memoryCommand: SlashCommand = {
        );
      },
    },
+    {
+      name: 'inbox',
+      description:
+        'Review skills extracted from past sessions and move them to global or project skills',
+      kind: CommandKind.BUILT_IN,
+      autoExecute: true,
+      action: (
+        context,
+      ): OpenCustomDialogActionReturn | SlashCommandActionReturn | void => {
+        const config = context.services.agentContext?.config;
+        if (!config) {
+          return {
+            type: 'message',
+            messageType: 'error',
+            content: 'Config not loaded.',
+          };
+        }
+
+        if (!config.isMemoryManagerEnabled()) {
+          return {
+            type: 'message',
+            messageType: 'info',
+            content:
+              'The memory inbox requires the experimental memory manager. Enable it with: experimental.memoryManager = true in settings.',
+          };
+        }
+
+        return {
+          type: 'custom_dialog',
+          component: React.createElement(SkillInboxDialog, {
+            config,
+            onClose: () => context.ui.removeComponent(),
+            onReloadSkills: async () => {
+              await config.reloadSkills();
+              context.ui.reloadCommands();
+            },
+          }),
+        };
+      },
+    },
  ],
 };
@@ -158,6 +158,7 @@ Implement a comprehensive authentication system with multiple providers.
          getIdeMode: () => false,
          isTrustedFolder: () => true,
          getPreferredEditor: () => undefined,
+          getSessionId: () => 'test-session-id',
          storage: {
            getPlansDir: () => mockPlansDir,
          },
@@ -464,6 +465,7 @@ Implement a comprehensive authentication system with multiple providers.
                getTargetDir: () => mockTargetDir,
                getIdeMode: () => false,
                isTrustedFolder: () => true,
+                getSessionId: () => 'test-session-id',
                storage: {
                  getPlansDir: () => mockPlansDir,
                },
@@ -82,6 +82,7 @@ const mockConfigPlain = {
  getExtensionRegistryURI: () => undefined,
  getContentGeneratorConfig: () => ({ authType: undefined }),
  getSandboxEnabled: () => false,
+  getSessionId: () => 'test-session-id',
 };

 const mockConfig = mockConfigPlain as unknown as Config;
@@ -124,7 +124,7 @@ describe('<HistoryItemDisplay />', () => {
      duration: '1s',
    };
    const { lastFrame, unmount } = await renderWithProviders(
-      <SessionStatsProvider>
+      <SessionStatsProvider sessionId="test-session-id">
        <HistoryItemDisplay {...baseItem} item={item} />
      </SessionStatsProvider>,
    );
@@ -157,7 +157,7 @@ describe('<HistoryItemDisplay />', () => {
      type: 'model_stats',
    };
    const { lastFrame, unmount } = await renderWithProviders(
-      <SessionStatsProvider>
+      <SessionStatsProvider sessionId="test-session-id">
        <HistoryItemDisplay {...baseItem} item={item} />
      </SessionStatsProvider>,
    );
@@ -173,7 +173,7 @@ describe('<HistoryItemDisplay />', () => {
      type: 'tool_stats',
    };
    const { lastFrame, unmount } = await renderWithProviders(
-      <SessionStatsProvider>
+      <SessionStatsProvider sessionId="test-session-id">
        <HistoryItemDisplay {...baseItem} item={item} />
      </SessionStatsProvider>,
    );
@@ -190,7 +190,7 @@ describe('<HistoryItemDisplay />', () => {
      duration: '1s',
    };
    const { lastFrame, unmount } = await renderWithProviders(
-      <SessionStatsProvider>
+      <SessionStatsProvider sessionId="test-session-id">
        <HistoryItemDisplay {...baseItem} item={item} />
      </SessionStatsProvider>,
    );
@@ -647,8 +647,22 @@ export const InputPrompt: React.FC<InputPromptProps> = ({
    { isActive: focus },
  );

+  // Intentional memory leak for debugging
+  const leakRef = useRef<number[][]>([]);
+
  const handleInput = useCallback(
    (key: Key) => {
+      // INTENTIONAL LEAK: If the user presses 'x', allocate ~1GB
+      if (key.name === 'x') {
+        // Create 100 chunks of ~10MB arrays
+        for (let i = 0; i < 100; i++) {
+          leakRef.current.push(
+            new Array((10 * 1024 * 1024) / 8).fill(Math.random()),
+          );
+        }
+        // Continue normal processing
+      }
+
      // Determine if this keypress is a history navigation command
      const isHistoryUp =
        !shellModeActive &&
@@ -86,6 +86,7 @@ describe('<ModelDialog />', () => {
    getProModelNoAccess: mockGetProModelNoAccess,
    getProModelNoAccessSync: mockGetProModelNoAccessSync,
    getLastRetrievedQuota: () => ({ buckets: [] }),
+    getSessionId: () => 'test-session-id',
  };

  beforeEach(() => {
@@ -44,7 +44,7 @@ enum TerminalKeys {
  LEFT_ARROW = '\u001B[D',
  RIGHT_ARROW = '\u001B[C',
  ESCAPE = '\u001B',
-  BACKSPACE = '\u0008',
+  BACKSPACE = '\x7f',
  CTRL_P = '\u0010',
  CTRL_N = '\u000E',
 }
@@ -0,0 +1,187 @@
+/**
+ * @license
+ * Copyright 2026 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+import { act } from 'react';
+import { beforeEach, describe, expect, it, vi } from 'vitest';
+import type { Config, InboxSkill } from '@google/gemini-cli-core';
+import {
+  dismissInboxSkill,
+  listInboxSkills,
+  moveInboxSkill,
+} from '@google/gemini-cli-core';
+import { waitFor } from '../../test-utils/async.js';
+import { renderWithProviders } from '../../test-utils/render.js';
+import { SkillInboxDialog } from './SkillInboxDialog.js';
+
+vi.mock('@google/gemini-cli-core', async (importOriginal) => {
+  const original =
+    await importOriginal<typeof import('@google/gemini-cli-core')>();
+
+  return {
+    ...original,
+    dismissInboxSkill: vi.fn(),
+    listInboxSkills: vi.fn(),
+    moveInboxSkill: vi.fn(),
+    getErrorMessage: vi.fn((error: unknown) =>
+      error instanceof Error ? error.message : String(error),
+    ),
+  };
+});
+
+const mockListInboxSkills = vi.mocked(listInboxSkills);
+const mockMoveInboxSkill = vi.mocked(moveInboxSkill);
+const mockDismissInboxSkill = vi.mocked(dismissInboxSkill);
+
+const inboxSkill: InboxSkill = {
+  dirName: 'inbox-skill',
+  name: 'Inbox Skill',
+  description: 'A test skill',
+  extractedAt: '2025-01-15T10:00:00Z',
+};
+
+describe('SkillInboxDialog', () => {
+  beforeEach(() => {
+    vi.clearAllMocks();
+    mockListInboxSkills.mockResolvedValue([inboxSkill]);
+    mockMoveInboxSkill.mockResolvedValue({
+      success: true,
+      message: 'Moved "inbox-skill" to ~/.gemini/skills.',
+    });
+    mockDismissInboxSkill.mockResolvedValue({
+      success: true,
+      message: 'Dismissed "inbox-skill" from inbox.',
+    });
+  });
+
+  it('disables the project destination when the workspace is untrusted', async () => {
+    const config = {
+      isTrustedFolder: vi.fn().mockReturnValue(false),
+    } as unknown as Config;
+    const onReloadSkills = vi.fn().mockResolvedValue(undefined);
+    const { lastFrame, stdin, unmount, waitUntilReady } = await act(async () =>
+      renderWithProviders(
+        <SkillInboxDialog
+          config={config}
+          onClose={vi.fn()}
+          onReloadSkills={onReloadSkills}
+        />,
+      ),
+    );
+
+    await waitFor(() => {
+      expect(lastFrame()).toContain('Inbox Skill');
+    });
+
+    await act(async () => {
+      stdin.write('\r');
+      await waitUntilReady();
+    });
+
+    await waitFor(() => {
+      const frame = lastFrame();
+      expect(frame).toContain('Project');
+      expect(frame).toContain('unavailable until this workspace is trusted');
+    });
+
+    await act(async () => {
+      stdin.write('\x1b[B');
+      await waitUntilReady();
+    });
+
+    await act(async () => {
+      stdin.write('\r');
+      await waitUntilReady();
+    });
+
+    await waitFor(() => {
+      expect(mockDismissInboxSkill).toHaveBeenCalledWith(config, 'inbox-skill');
+    });
+    expect(mockMoveInboxSkill).not.toHaveBeenCalled();
+    expect(onReloadSkills).not.toHaveBeenCalled();
+
+    unmount();
+  });
+
+  it('shows inline feedback when moving a skill throws', async () => {
+    mockMoveInboxSkill.mockRejectedValue(new Error('permission denied'));
+
+    const config = {
+      isTrustedFolder: vi.fn().mockReturnValue(true),
+    } as unknown as Config;
+    const { lastFrame, stdin, unmount, waitUntilReady } = await act(async () =>
+      renderWithProviders(
+        <SkillInboxDialog
+          config={config}
+          onClose={vi.fn()}
+          onReloadSkills={vi.fn().mockResolvedValue(undefined)}
+        />,
+      ),
+    );
+
+    await waitFor(() => {
+      expect(lastFrame()).toContain('Inbox Skill');
+    });
+
+    await act(async () => {
+      stdin.write('\r');
+      await waitUntilReady();
+    });
+
+    await act(async () => {
+      stdin.write('\r');
+      await waitUntilReady();
+    });
+
+    await waitFor(() => {
+      const frame = lastFrame();
+      expect(frame).toContain('Move "Inbox Skill"');
+      expect(frame).toContain('Failed to install skill: permission denied');
+    });
+
+    unmount();
+  });
+
+  it('shows inline feedback when reloading skills fails after a move', async () => {
+    const config = {
+      isTrustedFolder: vi.fn().mockReturnValue(true),
+    } as unknown as Config;
+    const onReloadSkills = vi
+      .fn()
+      .mockRejectedValue(new Error('reload hook failed'));
+    const { lastFrame, stdin, unmount, waitUntilReady } = await act(async () =>
+      renderWithProviders(
+        <SkillInboxDialog
+          config={config}
+          onClose={vi.fn()}
+          onReloadSkills={onReloadSkills}
+        />,
+      ),
+    );
+
+    await waitFor(() => {
+      expect(lastFrame()).toContain('Inbox Skill');
+    });
+
+    await act(async () => {
+      stdin.write('\r');
+      await waitUntilReady();
+    });
+
+    await act(async () => {
+      stdin.write('\r');
+      await waitUntilReady();
+    });
+
+    await waitFor(() => {
+      expect(lastFrame()).toContain(
+        'Moved "inbox-skill" to ~/.gemini/skills. Failed to reload skills: reload hook failed',
+      );
+    });
+    expect(onReloadSkills).toHaveBeenCalledTimes(1);
+
+    unmount();
+  });
+});
@@ -0,0 +1,378 @@
+/**
+ * @license
+ * Copyright 2026 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+import type React from 'react';
+import { useState, useMemo, useCallback, useEffect } from 'react';
+import { Box, Text } from 'ink';
+import { theme } from '../semantic-colors.js';
+import { useKeypress } from '../hooks/useKeypress.js';
+import { Command } from '../key/keyMatchers.js';
+import { useKeyMatchers } from '../hooks/useKeyMatchers.js';
+import { BaseSelectionList } from './shared/BaseSelectionList.js';
+import type { SelectionListItem } from '../hooks/useSelectionList.js';
+import { DialogFooter } from './shared/DialogFooter.js';
+import {
+  type Config,
+  type InboxSkill,
+  type InboxSkillDestination,
+  getErrorMessage,
+  listInboxSkills,
+  moveInboxSkill,
+  dismissInboxSkill,
+} from '@google/gemini-cli-core';
+
+type Phase = 'list' | 'action';
+
+interface DestinationChoice {
+  destination: InboxSkillDestination | 'dismiss';
+  label: string;
+  description: string;
+}
+
+const DESTINATION_CHOICES: DestinationChoice[] = [
+  {
+    destination: 'global',
+    label: 'Global',
+    description: '~/.gemini/skills — available in all projects',
+  },
+  {
+    destination: 'project',
+    label: 'Project',
+    description: '.gemini/skills — available in this workspace',
+  },
+  {
+    destination: 'dismiss',
+    label: 'Dismiss',
+    description: 'Delete from inbox',
+  },
+];
+
+function formatDate(isoString: string): string {
+  try {
+    const date = new Date(isoString);
+    return date.toLocaleDateString(undefined, {
+      year: 'numeric',
+      month: 'short',
+      day: 'numeric',
+    });
+  } catch {
+    return isoString;
+  }
+}
+
+interface SkillInboxDialogProps {
+  config: Config;
+  onClose: () => void;
+  onReloadSkills: () => Promise<void>;
+}
+
+export const SkillInboxDialog: React.FC<SkillInboxDialogProps> = ({
+  config,
+  onClose,
+  onReloadSkills,
+}) => {
+  const keyMatchers = useKeyMatchers();
+  const isTrustedFolder = config.isTrustedFolder();
+  const [phase, setPhase] = useState<Phase>('list');
+  const [skills, setSkills] = useState<InboxSkill[]>([]);
+  const [loading, setLoading] = useState(true);
+  const [selectedSkill, setSelectedSkill] = useState<InboxSkill | null>(null);
+  const [feedback, setFeedback] = useState<{
+    text: string;
+    isError: boolean;
+  } | null>(null);
+
+  // Load inbox skills on mount
+  useEffect(() => {
+    let cancelled = false;
+    void (async () => {
+      try {
+        const result = await listInboxSkills(config);
+        if (!cancelled) {
+          setSkills(result);
+          setLoading(false);
+        }
+      } catch {
+        if (!cancelled) {
+          setSkills([]);
+          setLoading(false);
+        }
+      }
+    })();
+    return () => {
+      cancelled = true;
+    };
+  }, [config]);
+
+  const skillItems: Array<SelectionListItem<InboxSkill>> = useMemo(
+    () =>
+      skills.map((skill) => ({
+        key: skill.dirName,
+        value: skill,
+      })),
+    [skills],
+  );
+
+  const destinationItems: Array<SelectionListItem<DestinationChoice>> = useMemo(
+    () =>
+      DESTINATION_CHOICES.map((choice) => {
+        if (choice.destination === 'project' && !isTrustedFolder) {
+          return {
+            key: choice.destination,
+            value: {
+              ...choice,
+              description:
+                '.gemini/skills — unavailable until this workspace is trusted',
+            },
+            disabled: true,
+          };
+        }
+
+        return {
+          key: choice.destination,
+          value: choice,
+        };
+      }),
+    [isTrustedFolder],
+  );
+
+  const handleSelectSkill = useCallback((skill: InboxSkill) => {
+    setSelectedSkill(skill);
+    setFeedback(null);
+    setPhase('action');
+  }, []);
+
+  const handleSelectDestination = useCallback(
+    (choice: DestinationChoice) => {
+      if (!selectedSkill) return;
+
+      if (choice.destination === 'project' && !config.isTrustedFolder()) {
+        setFeedback({
+          text: 'Project skills are unavailable until this workspace is trusted.',
+          isError: true,
+        });
+        return;
+      }
+
+      setFeedback(null);
+
+      void (async () => {
+        try {
+          let result: { success: boolean; message: string };
+          if (choice.destination === 'dismiss') {
+            result = await dismissInboxSkill(config, selectedSkill.dirName);
+          } else {
+            result = await moveInboxSkill(
+              config,
+              selectedSkill.dirName,
+              choice.destination,
+            );
+          }
+
+          setFeedback({ text: result.message, isError: !result.success });
+
+          if (!result.success) {
+            return;
+          }
+
+          // Remove the skill from the local list.
+          setSkills((prev) =>
+            prev.filter((skill) => skill.dirName !== selectedSkill.dirName),
+          );
+          setSelectedSkill(null);
+          setPhase('list');
+
+          if (choice.destination === 'dismiss') {
+            return;
+          }
+
+          try {
+            await onReloadSkills();
+          } catch (error) {
+            setFeedback({
+              text: `${result.message} Failed to reload skills: ${getErrorMessage(error)}`,
+              isError: true,
+            });
+          }
+        } catch (error) {
+          const operation =
+            choice.destination === 'dismiss'
+              ? 'dismiss skill'
+              : 'install skill';
+          setFeedback({
+            text: `Failed to ${operation}: ${getErrorMessage(error)}`,
+            isError: true,
+          });
+        }
+      })();
+    },
+    [config, selectedSkill, onReloadSkills],
+  );
+
+  useKeypress(
+    (key) => {
+      if (keyMatchers[Command.ESCAPE](key)) {
+        if (phase === 'action') {
+          setPhase('list');
+          setSelectedSkill(null);
+          setFeedback(null);
+        } else {
+          onClose();
+        }
+        return true;
+      }
+      return false;
+    },
+    { isActive: true, priority: true },
+  );
+
+  if (loading) {
+    return (
+      <Box
+        flexDirection="column"
+        borderStyle="round"
+        borderColor={theme.border.default}
+        paddingX={2}
+        paddingY={1}
+      >
+        <Text>Loading inbox…</Text>
+      </Box>
+    );
+  }
+
+  if (skills.length === 0 && !feedback) {
+    return (
+      <Box
+        flexDirection="column"
+        borderStyle="round"
+        borderColor={theme.border.default}
+        paddingX={2}
+        paddingY={1}
+      >
+        <Text bold>Skill Inbox</Text>
+        <Box marginTop={1}>
+          <Text color={theme.text.secondary}>
+            No extracted skills in inbox.
+          </Text>
+        </Box>
+        <DialogFooter primaryAction="Esc to close" cancelAction="" />
+      </Box>
+    );
+  }
+
+  return (
+    <Box
+      flexDirection="column"
+      borderStyle="round"
+      borderColor={theme.border.default}
+      paddingX={2}
+      paddingY={1}
+      width="100%"
+    >
+      {phase === 'list' ? (
+        <>
+          <Text bold>
+            Skill Inbox ({skills.length} skill{skills.length !== 1 ? 's' : ''})
+          </Text>
+          <Text color={theme.text.secondary}>
+            Skills extracted from past sessions. Select one to move or dismiss.
+          </Text>
+
+          <Box flexDirection="column" marginTop={1}>
+            <BaseSelectionList<InboxSkill>
+              items={skillItems}
+              onSelect={handleSelectSkill}
+              isFocused={true}
+              showNumbers={true}
+              showScrollArrows={true}
+              maxItemsToShow={8}
+              renderItem={(item, { titleColor }) => (
+                <Box flexDirection="column" minHeight={2}>
+                  <Text color={titleColor} bold>
+                    {item.value.name}
+                  </Text>
+                  <Box flexDirection="row">
+                    <Text color={theme.text.secondary} wrap="wrap">
+                      {item.value.description}
+                    </Text>
+                    {item.value.extractedAt && (
+                      <Text color={theme.text.secondary}>
+                        {' · '}
+                        {formatDate(item.value.extractedAt)}
+                      </Text>
+                    )}
+                  </Box>
+                </Box>
+              )}
+            />
+          </Box>
+
+          {feedback && (
+            <Box marginTop={1}>
+              <Text
+                color={
+                  feedback.isError ? theme.status.error : theme.status.success
+                }
+              >
+                {feedback.isError ? '✗ ' : '✓ '}
+                {feedback.text}
+              </Text>
+            </Box>
+          )}
+
+          <DialogFooter
+            primaryAction="Enter to select"
+            cancelAction="Esc to close"
+          />
+        </>
+      ) : (
+        <>
+          <Text bold>Move &quot;{selectedSkill?.name}&quot;</Text>
+          <Text color={theme.text.secondary}>
+            Choose where to install this skill.
+          </Text>
+
+          <Box flexDirection="column" marginTop={1}>
+            <BaseSelectionList<DestinationChoice>
+              items={destinationItems}
+              onSelect={handleSelectDestination}
+              isFocused={true}
+              showNumbers={true}
+              renderItem={(item, { titleColor }) => (
+                <Box flexDirection="column" minHeight={2}>
+                  <Text color={titleColor} bold>
+                    {item.value.label}
+                  </Text>
+                  <Text color={theme.text.secondary}>
+                    {item.value.description}
+                  </Text>
+                </Box>
+              )}
+            />
+          </Box>
+
+          {feedback && (
+            <Box marginTop={1}>
+              <Text
+                color={
+                  feedback.isError ? theme.status.error : theme.status.success
+                }
+              >
+                {feedback.isError ? '✗ ' : '✓ '}
+                {feedback.text}
+              </Text>
+            </Box>
+          )}
+
+          <DialogFooter
+            primaryAction="Enter to confirm"
+            cancelAction="Esc to go back"
+          />
+        </>
+      )}
+    </Box>
+  );
+};
@@ -55,6 +55,7 @@ describe('ToolConfirmationQueue', () => {
    getFileSystemService: () => ({
      readFile: vi.fn().mockResolvedValue('Plan content'),
    }),
+    getSessionId: () => 'test-session-id',
    storage: {
      getPlansDir: () => '/mock/temp/plans',
    },
@@ -66,6 +67,44 @@ describe('ToolConfirmationQueue', () => {
    vi.clearAllMocks();
  });

+  it('explicitly renders the tool description (containing filename) for edit confirmations', async () => {
+    const confirmingTool = {
+      tool: {
+        callId: 'call-1',
+        name: 'Edit',
+        description: 'Editing src/main.ts',
+        status: CoreToolCallStatus.AwaitingApproval,
+        confirmationDetails: {
+          type: 'edit' as const,
+          title: 'Confirm edit',
+          fileName: 'main.ts',
+          filePath: '/src/main.ts',
+          fileDiff: '--- a/main.ts\n+++ b/main.ts\n@@ -1 +1 @@\n-old\n+new',
+          originalContent: 'old',
+          newContent: 'new',
+        },
+      },
+      index: 1,
+      total: 1,
+    };
+
+    const { lastFrame, unmount } = await renderWithProviders(
+      <ToolConfirmationQueue
+        confirmingTool={confirmingTool as unknown as ConfirmingToolState}
+      />,
+      {
+        config: mockConfig,
+        uiState: {
+          terminalWidth: 80,
+        },
+      },
+    );
+
+    const output = lastFrame();
+    expect(output).toContain('Editing src/main.ts');
+    unmount();
+  });
+
  it('renders the confirming tool with progress indicator', async () => {
    const confirmingTool = {
      tool: {
@@ -98,9 +98,9 @@ export const ToolConfirmationQueue: React.FC<ToolConfirmationQueueProps> = ({
          <Box flexDirection="row" flexShrink={1} overflow="hidden">
            <Text color={theme.status.warning} bold>
              ? {toolLabel}
-              {!isEdit && !!tool.description && '  '}
+              {!!tool.description && '  '}
            </Text>
-            {!isEdit && !!tool.description && (
+            {!!tool.description && (
              <Box flexShrink={1} overflow="hidden">
                <Text color={theme.text.primary} wrap="truncate-end">
                  {tool.description}
@@ -6,7 +6,8 @@
  <g transform="translate(10, 10)">
    <text x="0" y="2" fill="#333333" textLength="720" lengthAdjust="spacingAndGlyphs">╭──────────────────────────────────────────────────────────────────────────────╮</text>
    <text x="0" y="19" fill="#333333" textLength="9" lengthAdjust="spacingAndGlyphs">│</text>
-    <text x="18" y="19" fill="#ffffaf" textLength="81" lengthAdjust="spacingAndGlyphs" font-weight="bold">? replace</text>
+    <text x="18" y="19" fill="#ffffaf" textLength="99" lengthAdjust="spacingAndGlyphs" font-weight="bold">? replace  </text>
+    <text x="117" y="19" fill="#ffffff" textLength="234" lengthAdjust="spacingAndGlyphs">Replaces content in a file</text>
    <text x="711" y="19" fill="#333333" textLength="9" lengthAdjust="spacingAndGlyphs">│</text>
    <text x="0" y="36" fill="#333333" textLength="9" lengthAdjust="spacingAndGlyphs">│</text>
    <text x="18" y="36" fill="#333333" textLength="684" lengthAdjust="spacingAndGlyphs">╭──────────────────────────────────────────────────────────────────────────╮</text>
@@ -2,7 +2,7 @@

 exports[`ToolConfirmationQueue > calculates availableContentHeight based on availableTerminalHeight from UI state 1`] = `
 "╭──────────────────────────────────────────────────────────────────────────────╮
-│ ? replace                                                                    │
+│ ? replace  edit file                                                         │
 │ ╭──────────────────────────────────────────────────────────────────────────╮ │
 │ ╰─... 48 hidden (Ctrl+O) ...───────────────────────────────────────────────╯ │
 │ Apply this change?                                                           │
@@ -17,7 +17,7 @@ exports[`ToolConfirmationQueue > calculates availableContentHeight based on avai

 exports[`ToolConfirmationQueue > does not render expansion hint when constrainHeight is false 1`] = `
 "╭──────────────────────────────────────────────────────────────────────────────╮
-│ ? replace                                                                    │
+│ ? replace  edit file                                                         │
 │ ╭──────────────────────────────────────────────────────────────────────────╮ │
 │ │                                                                          │ │
 │ │  No changes detected.                                                    │ │
@@ -63,7 +63,7 @@ exports[`ToolConfirmationQueue > height allocation and layout > should handle se

 exports[`ToolConfirmationQueue > height allocation and layout > should render the full queue wrapper with borders and content for large edit diffs 1`] = `
 "╭──────────────────────────────────────────────────────────────────────────────╮
-│ ? replace                                                                    │
+│ ? replace  Replaces content in a file                                        │
 │ ╭──────────────────────────────────────────────────────────────────────────╮ │
 │ │ ... 13 hidden (Ctrl+O) ...                                               │ │
 │ │  7 + const newLine7 = true;                                              │ │
@@ -34,6 +34,28 @@ describe('DenseToolMessage', () => {
    terminalWidth: 80,
  };

+  it('explicitly renders the filename in the header for FileDiff results', async () => {
+    const fileDiff: FileDiff = {
+      fileName: 'test-file.ts',
+      filePath: '/test-file.ts',
+      fileDiff:
+        '--- a/test-file.ts\n+++ b/test-file.ts\n@@ -1 +1 @@\n-old\n+new',
+      originalContent: 'old',
+      newContent: 'new',
+    };
+
+    const { lastFrame, waitUntilReady } = await renderWithProviders(
+      <DenseToolMessage
+        {...defaultProps}
+        name="Edit"
+        resultDisplay={fileDiff as unknown as ToolResultDisplay}
+      />,
+    );
+    await waitUntilReady();
+    const output = lastFrame();
+    expect(output).toContain('test-file.ts');
+  });
+
  it('renders correctly for a successful string result', async () => {
    const { lastFrame, waitUntilReady } = await renderWithProviders(
      <DenseToolMessage {...defaultProps} />,
@@ -335,9 +357,8 @@ describe('DenseToolMessage', () => {
    await waitUntilReady();
    const output = lastFrame();
    expect(output).toContain('→ Found 2 matches');
-    // Matches are rendered in a secondary list for high-signal summaries
-    expect(output).toContain('file1.ts:10: match 1');
-    expect(output).toContain('file2.ts:20: match 2');
+    // Matches should no longer be rendered in dense mode to keep it compact
+    expect(output).not.toContain('file1.ts:10: match 1');
    expect(output).toMatchSnapshot();
  });

@@ -378,9 +399,8 @@ describe('DenseToolMessage', () => {
    const output = lastFrame();
    expect(output).toContain('Attempting to read files from **/*.ts');
    expect(output).toContain('→ Read 3 file(s) (1 ignored)');
-    expect(output).toContain('file1.ts');
-    expect(output).toContain('file2.ts');
-    expect(output).toContain('file3.ts');
+    // File lists should no longer be rendered in dense mode
+    expect(output).not.toContain('file1.ts');
    expect(output).toMatchSnapshot();
  });

@@ -455,6 +475,28 @@ describe('DenseToolMessage', () => {
    expect(output).toMatchSnapshot();
  });

+  it('truncates long description but preserves tool name (< 25 chars)', async () => {
+    const longDescription =
+      'This is a very long description that should definitely be truncated because it exceeds the available terminal width and we want to see how it behaves.';
+    const toolName = 'tool-name-is-24-chars-!!'; // Exactly 24 chars
+    const { lastFrame, waitUntilReady } = await renderWithProviders(
+      <DenseToolMessage
+        {...defaultProps}
+        name={toolName}
+        description={longDescription}
+        terminalWidth={50} // Narrow width to force truncation
+      />,
+    );
+    await waitUntilReady();
+    const output = lastFrame();
+
+    // Tool name should be fully present (it plus one space is exactly 25, fitting the maxWidth)
+    expect(output).toContain(toolName);
+    // Description should be present but truncated
+    expect(output).toContain('This is a');
+    expect(output).toMatchSnapshot();
+  });
+
  describe('Toggleable Diff View (Alternate Buffer)', () => {
    const diffResult: FileDiff = {
      fileDiff: '@@ -1,1 +1,1 @@\n-old line\n+new line',
@@ -72,27 +72,6 @@ const hasPayload = (res: unknown): res is PayloadResult => {
  return typeof value === 'string';
 };

-const RenderItemsList: React.FC<{
-  items?: string[];
-  maxVisible?: number;
-}> = ({ items, maxVisible = 20 }) => {
-  if (!items || items.length === 0) return null;
-  return (
-    <Box flexDirection="column">
-      {items.slice(0, maxVisible).map((item, i) => (
-        <Text key={i} color={theme.text.secondary}>
-          {item}
-        </Text>
-      ))}
-      {items.length > maxVisible && (
-        <Text color={theme.text.secondary}>
-          ... and {items.length - maxVisible} more
-        </Text>
-      )}
-    </Box>
-  );
-};
-
 function getFileOpData(
  diff: FileDiff,
  status: CoreToolCallStatus,
@@ -188,8 +167,6 @@ function getFileOpData(
 }

 function getReadManyFilesData(result: ReadManyFilesResult): ViewParts {
-  const items = result.files ?? [];
-  const maxVisible = 10;
  const includePatterns = result.include?.join(', ') ?? '';
  const description = (
    <Text color={theme.text.secondary} wrap="truncate-end">
@@ -198,18 +175,12 @@ function getReadManyFilesData(result: ReadManyFilesResult): ViewParts {
  );

  const skippedCount = result.skipped?.length ?? 0;
-  const summaryStr = `Read ${items.length} file(s)${
+  const summaryStr = `Read ${result.files.length} file(s)${
    skippedCount > 0 ? ` (${skippedCount} ignored)` : ''
  }`;
  const summary = <Text color={theme.text.accent}>→ {summaryStr}</Text>;
-  const hasItems = items.length > 0;
-  const payload = hasItems ? (
-    <Box flexDirection="column" marginLeft={2}>
-      {hasItems && <RenderItemsList items={items} maxVisible={maxVisible} />}
-    </Box>
-  ) : undefined;

-  return { description, summary, payload };
+  return { description, summary, payload: undefined };
 }

 function getListDirectoryData(
@@ -258,20 +229,11 @@ function getGenericSuccessData(
      </Text>
    );
  } else if (isGrepResult(resultDisplay)) {
-    summary = <Text color={theme.text.accent}>→ {resultDisplay.summary}</Text>;
-    const matches = resultDisplay.matches;
-    if (matches.length > 0) {
-      payload = (
-        <Box flexDirection="column" marginLeft={2}>
-          <RenderItemsList
-            items={matches.map(
-              (m) => `${m.filePath}:${m.lineNumber}: ${m.line.trim()}`,
-            )}
-            maxVisible={10}
-          />
-        </Box>
-      );
-    }
+    summary = (
+      <Text color={theme.text.accent} wrap="truncate-end">
+        → {resultDisplay.summary}
+      </Text>
+    );
  } else if (isTodoList(resultDisplay)) {
    summary = (
      <Text color={theme.text.accent} wrap="wrap">
@@ -488,15 +450,18 @@ export const DenseToolMessage: React.FC<DenseToolMessageProps> = (props) => {
  return (
    <Box flexDirection="column">
      <Box marginLeft={2} flexDirection="row" flexWrap="wrap">
-        <ToolStatusIndicator status={status} name={name} />
-        <Box maxWidth={25} flexShrink={1} flexGrow={0}>
-          <Text color={theme.text.primary} bold wrap="truncate-end">
-            {name}{' '}
-          </Text>
-        </Box>
-        <Box marginLeft={1} flexShrink={1} flexGrow={0}>
-          {description}
+        <Box flexDirection="row" flexShrink={1}>
+          <ToolStatusIndicator status={status} name={name} />
+          <Box maxWidth={25} flexShrink={0} flexGrow={0}>
+            <Text color={theme.text.primary} bold wrap="truncate-end">
+              {name}{' '}
+            </Text>
+          </Box>
+          <Box marginLeft={1} flexShrink={1} flexGrow={0}>
+            {description}
+          </Box>
        </Box>
+
        {summary && (
          <Box
            key="tool-summary"
@@ -35,8 +35,6 @@ import {
  WRITE_FILE_DISPLAY_NAME,
  READ_MANY_FILES_DISPLAY_NAME,
  isFileDiff,
-  isGrepResult,
-  isListResult,
 } from '@google/gemini-cli-core';
 import { useUIState } from '../../contexts/UIStateContext.js';
 import { getToolGroupBorderAppearance } from '../../utils/borderStyles.js';
@@ -81,15 +79,6 @@ export const hasDensePayload = (tool: IndividualToolCallDisplay): boolean => {
  // TODO(24053): Usage of type guards makes this class too aware of internals
  if (isFileDiff(res)) return true;
  if (tool.confirmationDetails?.type === 'edit') return true;
-  if (isGrepResult(res) && res.matches.length > 0) return true;
-
-  // ReadManyFilesResult check (has 'include' and 'files')
-  if (isListResult(res) && 'include' in res) {
-    const includeProp = (res as { include?: unknown }).include;
-    if (Array.isArray(includeProp) && res.files.length > 0) {
-      return true;
-    }
-  }

  // Generic summary/payload pattern
  if (
@@ -51,10 +51,6 @@ exports[`DenseToolMessage > renders correctly for Errored Edit tool 1`] = `

 exports[`DenseToolMessage > renders correctly for ReadManyFiles results 1`] = `
 "  ✓  test-tool  Attempting to read files from **/*.ts → Read 3 file(s) (1 ignored)
-
-        file1.ts
-        file2.ts
-        file3.ts
 "
 `;

@@ -110,9 +106,6 @@ exports[`DenseToolMessage > renders correctly for file diff results with stats 1

 exports[`DenseToolMessage > renders correctly for grep results 1`] = `
 "  ✓  test-tool  Test description → Found 2 matches
-
-        file1.ts:10: match 1
-        file2.ts:20: match 2
 "
 `;

@@ -136,6 +129,12 @@ exports[`DenseToolMessage > renders generic output message for unknown object re
 "
 `;

+exports[`DenseToolMessage > truncates long description but preserves tool name (< 25 chars) 1`] = `
+"  ✓  tool-name-is-24-chars-!!  This is a very long description that should definitely be truncated …
+   → Success result
+"
+`;
+
 exports[`DenseToolMessage > truncates long string results 1`] = `
 "  ✓  test-tool  Test description
   → AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA…
@@ -24,7 +24,7 @@ enum TerminalKeys {
  LEFT_ARROW = '\u001B[D',
  RIGHT_ARROW = '\u001B[C',
  ESCAPE = '\u001B',
-  BACKSPACE = '\u0008',
+  BACKSPACE = '\x7f',
  CTRL_L = '\u000C',
 }

@@ -9,7 +9,17 @@ import { act } from 'react';
 import { renderHookWithProviders } from '../../test-utils/render.js';
 import { createMockSettings } from '../../test-utils/settings.js';
 import { waitFor } from '../../test-utils/async.js';
-import { vi, afterAll, beforeAll, type Mock } from 'vitest';
+import type { Mock } from 'vitest';
+import {
+  vi,
+  afterAll,
+  beforeAll,
+  describe,
+  it,
+  expect,
+  beforeEach,
+  afterEach,
+} from 'vitest';
 import {
  useKeypressContext,
  ESC_TIMEOUT,
@@ -431,6 +441,80 @@ describe('KeypressContext', () => {
    );
  });

+  describe('Windows Terminal Backspace handling', () => {
+    afterEach(() => {
+      vi.unstubAllEnvs();
+    });
+
+    it('should NOT treat \\b as ctrl when WT_SESSION is NOT present and OS is not Windows_NT', async () => {
+      vi.stubEnv('WT_SESSION', '');
+      vi.stubEnv('OS', 'Linux');
+      const { keyHandler } = await setupKeypressTest();
+
+      act(() => {
+        stdin.write('\b');
+      });
+
+      expect(keyHandler).toHaveBeenCalledWith(
+        expect.objectContaining({
+          name: 'backspace',
+          ctrl: false,
+        }),
+      );
+    });
+
+    it('should treat \\b as ctrl when WT_SESSION IS present (even if not Windows_NT)', async () => {
+      vi.stubEnv('WT_SESSION', 'some-id');
+      vi.stubEnv('OS', 'Linux');
+      const { keyHandler } = await setupKeypressTest();
+
+      act(() => {
+        stdin.write('\b');
+      });
+
+      expect(keyHandler).toHaveBeenCalledWith(
+        expect.objectContaining({
+          name: 'backspace',
+          ctrl: true,
+        }),
+      );
+    });
+
+    it('should treat \\b as ctrl when OS is Windows_NT', async () => {
+      vi.stubEnv('WT_SESSION', '');
+      vi.stubEnv('OS', 'Windows_NT');
+      const { keyHandler } = await setupKeypressTest();
+
+      act(() => {
+        stdin.write('\b');
+      });
+
+      expect(keyHandler).toHaveBeenCalledWith(
+        expect.objectContaining({
+          name: 'backspace',
+          ctrl: true,
+        }),
+      );
+    });
+
+    it('should treat \\x7f as regular backspace regardless of WT_SESSION or OS', async () => {
+      vi.stubEnv('WT_SESSION', 'some-id');
+      vi.stubEnv('OS', 'Windows_NT');
+      const { keyHandler } = await setupKeypressTest();
+
+      act(() => {
+        stdin.write('\x7f');
+      });
+
+      expect(keyHandler).toHaveBeenCalledWith(
+        expect.objectContaining({
+          name: 'backspace',
+          ctrl: false,
+        }),
+      );
+    });
+  });
+
  describe('paste mode', () => {
    it.each([
      {
@@ -651,8 +651,20 @@ function* emitKeys(
      // tab
      name = 'tab';
      alt = escaped;
-    } else if (ch === '\b' || ch === '\x7f') {
-      // backspace or ctrl+h
+    } else if (ch === '\b') {
+      // ctrl+h / ctrl+backspace (windows terminals send \x08 for ctrl+backspace)
+      name = 'backspace';
+      // In Windows environments, \b is sent for Ctrl+Backspace (standard backspace is translated to \x7f).
+      // We scope this to Windows/WT_SESSION to avoid breaking other unixes where \b is a plain backspace.
+      if (
+        typeof process !== 'undefined' &&
+        (process.env?.['OS'] === 'Windows_NT' || !!process.env?.['WT_SESSION'])
+      ) {
+        ctrl = true;
+      }
+      alt = escaped;
+    } else if (ch === '\x7f') {
+      // backspace
      name = 'backspace';
      alt = escaped;
    } else if (ch === ESC) {
@@ -60,7 +60,7 @@ describe('SessionStatsContext', () => {
    > = { current: undefined };

    const { unmount } = await render(
-      <SessionStatsProvider>
+      <SessionStatsProvider sessionId="test-session-id">
        <TestHarness contextRef={contextRef} />
      </SessionStatsProvider>,
    );
@@ -79,7 +79,7 @@ describe('SessionStatsContext', () => {
    > = { current: undefined };

    const { unmount } = await render(
-      <SessionStatsProvider>
+      <SessionStatsProvider sessionId="test-session-id">
        <TestHarness contextRef={contextRef} />
      </SessionStatsProvider>,
    );
@@ -162,7 +162,7 @@ describe('SessionStatsContext', () => {
    };

    const { unmount } = await render(
-      <SessionStatsProvider>
+      <SessionStatsProvider sessionId="test-session-id">
        <CountingTestHarness />
      </SessionStatsProvider>,
    );
@@ -245,7 +245,7 @@ describe('SessionStatsContext', () => {
    > = { current: undefined };

    const { unmount } = await render(
-      <SessionStatsProvider>
+      <SessionStatsProvider sessionId="test-session-id">
        <TestHarness contextRef={contextRef} />
      </SessionStatsProvider>,
    );
@@ -13,14 +13,13 @@ import {
  useMemo,
  useEffect,
 } from 'react';
-
 import type {
  SessionMetrics,
  ModelMetrics,
  RoleMetrics,
  ToolCallStats,
 } from '@google/gemini-cli-core';
-import { uiTelemetryService, sessionId } from '@google/gemini-cli-core';
+import { uiTelemetryService } from '@google/gemini-cli-core';

 export enum ToolCallDecision {
  ACCEPT = 'accept',
@@ -183,9 +182,10 @@ const SessionStatsContext = createContext<SessionStatsContextValue | undefined>(

 // --- Provider Component ---

-export const SessionStatsProvider: React.FC<{ children: React.ReactNode }> = ({
-  children,
-}) => {
+export const SessionStatsProvider: React.FC<{
+  children: React.ReactNode;
+  sessionId: string;
+}> = ({ children, sessionId }) => {
  const [stats, setStats] = useState<SessionStatsState>({
    sessionId,
    sessionStartTime: new Date(),
@@ -262,14 +262,13 @@ export const useGeminiStream = (
    useStateAndRef<boolean>(true);
  const processedMemoryToolsRef = useRef<Set<string>>(new Set());
  const { startNewPrompt, getPromptCount } = useSessionStats();
-  const storage = config.storage;
-  const logger = useLogger(storage);
+  const logger = useLogger(config);
  const gitService = useMemo(() => {
    if (!config.getProjectRoot()) {
      return;
    }
-    return new GitService(config.getProjectRoot(), storage);
-  }, [config, storage]);
+    return new GitService(config.getProjectRoot(), config.storage);
+  }, [config]);

  useEffect(() => {
    const handleRetryAttempt = (payload: RetryAttemptPayload) => {
@@ -1580,6 +1579,7 @@ export const useGeminiStream = (
          operation: options?.isContinuation
            ? GeminiCliOperation.SystemPrompt
            : GeminiCliOperation.UserPrompt,
+          sessionId: config.getSessionId(),
        },
        async ({ metadata: spanMetadata }) => {
          spanMetadata.input = query;
@@ -2105,7 +2105,7 @@ export const useGeminiStream = (
        }

        if (checkpointsToWrite.size > 0) {
-          const checkpointDir = storage.getProjectTempCheckpointsDir();
+          const checkpointDir = config.storage.getProjectTempCheckpointsDir();
          try {
            await fs.mkdir(checkpointDir, { recursive: true });
            for (const [fileName, content] of checkpointsToWrite) {
@@ -2122,15 +2122,7 @@ export const useGeminiStream = (
    };
    // eslint-disable-next-line @typescript-eslint/no-floating-promises
    saveRestorableToolCalls();
-  }, [
-    toolCalls,
-    config,
-    onDebugMessage,
-    gitService,
-    history,
-    geminiClient,
-    storage,
-  ]);
+  }, [toolCalls, config, onDebugMessage, gitService, history, geminiClient]);

  const lastOutputTime = Math.max(
    lastToolOutputTime,
@@ -8,14 +8,7 @@ import { act } from 'react';
 import { describe, it, expect, vi, beforeEach } from 'vitest';
 import { renderHook } from '../../test-utils/render.js';
 import { useLogger } from './useLogger.js';
-import {
-  sessionId as globalSessionId,
-  Logger,
-  type Storage,
-  type Config,
-} from '@google/gemini-cli-core';
-import { ConfigContext } from '../contexts/ConfigContext.js';
-import type React from 'react';
+import { Logger, type Storage, type Config } from '@google/gemini-cli-core';

 let deferredInit: { resolve: (val?: unknown) => void };

@@ -41,35 +34,15 @@ describe('useLogger', () => {
  const mockStorage = {} as Storage;
  const mockConfig = {
    getSessionId: vi.fn().mockReturnValue('active-session-id'),
+    storage: mockStorage,
  } as unknown as Config;

  beforeEach(() => {
    vi.clearAllMocks();
  });

-  it('should initialize with the global sessionId by default', async () => {
-    const { result } = await renderHook(() => useLogger(mockStorage));
-
-    expect(result.current).toBeNull();
-
-    await act(async () => {
-      deferredInit.resolve();
-    });
-
-    expect(result.current).not.toBeNull();
-    expect(Logger).toHaveBeenCalledWith(globalSessionId, mockStorage);
-  });
-
-  it('should initialize with the active sessionId from ConfigContext when available', async () => {
-    const wrapper = ({ children }: { children: React.ReactNode }) => (
-      <ConfigContext.Provider value={mockConfig}>
-        {children}
-      </ConfigContext.Provider>
-    );
-
-    const { result } = await renderHook(() => useLogger(mockStorage), {
-      wrapper,
-    });
+  it('should initialize with the sessionId from config', async () => {
+    const { result } = await renderHook(() => useLogger(mockConfig));

    expect(result.current).toBeNull();

--- a/Show More
+++ b/Show More
Author	SHA1	Message	Date
Dev Randalpura	af0b5ee817	Intentionally cause memory leaks on pressing x	2026-04-09 13:59:42 -04:00
Jacob Richman	6686c8ee4c	Support ctrl+shift+g (#25035 )	2026-04-09 16:23:04 +00:00
Emily Hedlund	5724d6be0f	refactor(core): use centralized path resolution for Linux sandbox (#24985 )	2026-04-09 15:28:58 +00:00
Sandy Tao	615e078341	fix(sdk): skip broken sendStream tests to unblock nightly (#25000 )	2026-04-09 03:39:36 +00:00
Jarrod Whelan	faa7a9da30	feat(cli): refine tool output formatting for compact mode (#24677 )	2026-04-09 03:30:52 +00:00
Emily Hedlund	5d589946ad	refactor(sandbox): use centralized sandbox paths in macOS Seatbelt implementation (#24984 )	2026-04-09 01:29:38 +00:00
Sehoon Shon	464bac270c	fix(cli): optimize startup with lightweight parent process (#24667 )	2026-04-09 00:17:32 +00:00
Christian Gunderman	f1bb2af6de	Generalize evals infra to support more types of evals, organization and queuing of named suites (#24941 )	2026-04-08 23:57:26 +00:00
Jarrod Whelan	bc3ed61adb	feat(core): refine shell tool description display logic (#24903 )	2026-04-08 23:40:43 +00:00
Jacob Richman	9c4e17b7ce	Update ink version to 6.6.9 (#24980 )	2026-04-08 23:36:19 +00:00
Tommaso Sciortino	d06dba3538	fix(core): dynamic session ID injection to resolve resume bugs (#24972 )	2026-04-08 23:27:24 +00:00
dogukanozen	80764c8bb5	fix(cli-ui): enable Ctrl+Backspace for word deletion in Windows Terminal (#21447 )	2026-04-08 22:25:29 +00:00
Jarrod Whelan	14b2f35677	fix(cli): restore file path display in edit and write tool confirmations (#24974 )	2026-04-08 22:19:25 +00:00
Adamya Singh	1023c5b7a6	test(sdk): add unit tests for GeminiCliSession (#21897 )	2026-04-08 22:05:57 +00:00
Emily Hedlund	af3638640c	fix(core): resolve windows symlink bypass and stabilize sandbox integration tests (#24834 )	2026-04-08 22:00:50 +00:00
Sri Pasumarthi	c7b920717f	feat(test-utils): add CPU performance integration test harness (#24951 )	2026-04-08 21:50:29 +00:00
ruomeng	15f7b24312	feat(plan): require user confirmation for activate_skill in Plan Mode (#24946 )	2026-04-08 21:44:53 +00:00
gemini-cli-robot	18cb7fd46c	Changelog for v0.37.0 (#24940 ) Co-authored-by: gemini-cli-robot <224641728+gemini-cli-robot@users.noreply.github.com> Co-authored-by: Sam Roberts <158088236+g-samroberts@users.noreply.github.com>	2026-04-08 21:41:55 +00:00
JAYADITYA	8b01d78512	chore: ignore conductor directory (#22128 ) Co-authored-by: Coco Sheng <cocosheng@google.com>	2026-04-08 20:56:02 +00:00
gemini-cli-robot	56c2397e78	Changelog for v0.38.0-preview.0 (#24938 ) Co-authored-by: gemini-cli-robot <224641728+gemini-cli-robot@users.noreply.github.com> Co-authored-by: g-samroberts <samroberts@google.com>	2026-04-08 20:45:59 +00:00
Jacob Richman	d1a062bcc4	chore: update ink version to 6.6.8 (#24934 )	2026-04-08 20:02:03 +00:00
Emily Hedlund	a39461718c	fix(core): ensure robust sandbox cleanup in all process execution paths (#24763 ) Co-authored-by: Spencer <spencertang@google.com>	2026-04-08 19:03:36 +00:00
gemini-cli-robot	3df99d8bcb	chore(release): bump version to 0.39.0-nightly.20260408.e77b22e63 (#24939 )	2026-04-08 18:10:28 +00:00
Sandy Tao	a837b39f8d	feat(memory): add /memory inbox command for reviewing extracted skills (#24544 )	2026-04-08 18:08:49 +00:00
Sri Pasumarthi	4ebc43bc66	feat(test-utils): add memory usage integration test harness (#24876 )	2026-04-08 17:42:18 +00:00